From 955d3411a17f590364238bd0d3329b61f20c1cd2 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Sun, 30 Dec 2018 12:46:01 +0100 Subject: [PATCH 001/525] batman-adv: Avoid WARN on net_device without parent in netns It is not allowed to use WARN* helpers on potential incorrect input from the user or transient problems because systems configured as panic_on_warn will reboot due to such a problem. A NULL return value of __dev_get_by_index can be caused by various problems which can either be related to the system configuration or problems (incorrectly returned network namespaces) in other (virtual) net_device drivers. batman-adv should not cause a (harmful) WARN in this situation and instead only report it via a simple message. Fixes: b7eddd0b3950 ("batman-adv: prevent using any virtual device created on batman-adv as hard-interface") Reported-by: syzbot+c764de0fcfadca9a8595@syzkaller.appspotmail.com Reported-by: Dmitry Vyukov Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich --- net/batman-adv/hard-interface.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 508f4416dfc9..415d494cbe22 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -20,7 +20,6 @@ #include "main.h" #include -#include #include #include #include @@ -179,8 +178,10 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev) parent_dev = __dev_get_by_index((struct net *)parent_net, dev_get_iflink(net_dev)); /* if we got a NULL parent_dev there is something broken.. */ - if (WARN(!parent_dev, "Cannot find parent device")) + if (!parent_dev) { + pr_err("Cannot find parent device\n"); return false; + } if (batadv_mutual_parents(net_dev, net, parent_dev, parent_net)) return false; From 9114daa825fc3f335f9bea3313ce667090187280 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Mon, 31 Dec 2018 22:31:01 +0100 Subject: [PATCH 002/525] batman-adv: Force mac header to start of data on xmit The caller of ndo_start_xmit may not already have called skb_reset_mac_header. The returned value of skb_mac_header/eth_hdr therefore can be in the wrong position and even outside the current skbuff. This for example happens when the user binds to the device using a PF_PACKET-SOCK_RAW with enabled qdisc-bypass: int opt = 4; setsockopt(sock, SOL_PACKET, PACKET_QDISC_BYPASS, &opt, sizeof(opt)); Since eth_hdr is used all over the codebase, the batadv_interface_tx function must always take care of resetting it. Fixes: c6c8fea29769 ("net: Add batman-adv meshing protocol") Reported-by: syzbot+9d7405c7faa390e60b4e@syzkaller.appspotmail.com Reported-by: syzbot+7d20bc3f1ddddc0f9079@syzkaller.appspotmail.com Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich --- net/batman-adv/soft-interface.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 5db5a0a4c959..b85ca809e509 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -221,6 +221,8 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb, netif_trans_update(soft_iface); vid = batadv_get_vid(skb, 0); + + skb_reset_mac_header(skb); ethhdr = eth_hdr(skb); switch (ntohs(ethhdr->h_proto)) { From 4ab88516b097ac8c23e00e7c3a26fbcd16feeefd Mon Sep 17 00:00:00 2001 From: Paul Kocialkowski Date: Mon, 10 Dec 2018 11:14:29 +0100 Subject: [PATCH 003/525] arm64: dts: allwinner: a64: Fix the video engine compatible When introducing the video-codec node for the video engine, the compatible for the H5 was used instead of the compatible for the A64. Use the right compatible instead. Fixes: d60ce24740d2 ("arm64: dts: allwinner: a64: Add Video Engine node") Signed-off-by: Paul Kocialkowski Signed-off-by: Maxime Ripard --- arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi index 837a03dee875..2abb335145a6 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi @@ -390,7 +390,7 @@ }; video-codec@1c0e000 { - compatible = "allwinner,sun50i-h5-video-engine"; + compatible = "allwinner,sun50i-a64-video-engine"; reg = <0x01c0e000 0x1000>; clocks = <&ccu CLK_BUS_VE>, <&ccu CLK_VE>, <&ccu CLK_DRAM_VE>; From 8443e4843e1c2594bf5664e1d993a1be71d1befb Mon Sep 17 00:00:00 2001 From: Aaro Koskinen Date: Sun, 23 Dec 2018 20:24:13 +0200 Subject: [PATCH 004/525] ARM: OMAP: dts: N950/N9: fix onenand timings Commit a758f50f10cf ("mtd: onenand: omap2: Configure driver from DT") started using DT specified timings for GPMC, and as a result the OneNAND stopped working on N950/N9 as we had wrong values in the DT. Fix by updating the values to bootloader timings that have been tested to be working on both Nokia N950 and N9. Fixes: a758f50f10cf ("mtd: onenand: omap2: Configure driver from DT") Signed-off-by: Aaro Koskinen Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/omap3-n950-n9.dtsi | 42 ++++++++++++++++++---------- 1 file changed, 28 insertions(+), 14 deletions(-) diff --git a/arch/arm/boot/dts/omap3-n950-n9.dtsi b/arch/arm/boot/dts/omap3-n950-n9.dtsi index 0d9b85317529..e142e6c70a59 100644 --- a/arch/arm/boot/dts/omap3-n950-n9.dtsi +++ b/arch/arm/boot/dts/omap3-n950-n9.dtsi @@ -370,6 +370,19 @@ compatible = "ti,omap2-onenand"; reg = <0 0 0x20000>; /* CS0, offset 0, IO size 128K */ + /* + * These timings are based on CONFIG_OMAP_GPMC_DEBUG=y reported + * bootloader set values when booted with v4.19 using both N950 + * and N9 devices (OneNAND Manufacturer: Samsung): + * + * gpmc cs0 before gpmc_cs_program_settings: + * cs0 GPMC_CS_CONFIG1: 0xfd001202 + * cs0 GPMC_CS_CONFIG2: 0x00181800 + * cs0 GPMC_CS_CONFIG3: 0x00030300 + * cs0 GPMC_CS_CONFIG4: 0x18001804 + * cs0 GPMC_CS_CONFIG5: 0x03171d1d + * cs0 GPMC_CS_CONFIG6: 0x97080000 + */ gpmc,sync-read; gpmc,sync-write; gpmc,burst-length = <16>; @@ -379,26 +392,27 @@ gpmc,device-width = <2>; gpmc,mux-add-data = <2>; gpmc,cs-on-ns = <0>; - gpmc,cs-rd-off-ns = <87>; - gpmc,cs-wr-off-ns = <87>; + gpmc,cs-rd-off-ns = <122>; + gpmc,cs-wr-off-ns = <122>; gpmc,adv-on-ns = <0>; - gpmc,adv-rd-off-ns = <10>; - gpmc,adv-wr-off-ns = <10>; - gpmc,oe-on-ns = <15>; - gpmc,oe-off-ns = <87>; + gpmc,adv-rd-off-ns = <15>; + gpmc,adv-wr-off-ns = <15>; + gpmc,oe-on-ns = <20>; + gpmc,oe-off-ns = <122>; gpmc,we-on-ns = <0>; - gpmc,we-off-ns = <87>; - gpmc,rd-cycle-ns = <112>; - gpmc,wr-cycle-ns = <112>; - gpmc,access-ns = <81>; + gpmc,we-off-ns = <122>; + gpmc,rd-cycle-ns = <148>; + gpmc,wr-cycle-ns = <148>; + gpmc,access-ns = <117>; gpmc,page-burst-access-ns = <15>; gpmc,bus-turnaround-ns = <0>; gpmc,cycle2cycle-delay-ns = <0>; gpmc,wait-monitoring-ns = <0>; - gpmc,clk-activation-ns = <5>; - gpmc,wr-data-mux-bus-ns = <30>; - gpmc,wr-access-ns = <81>; - gpmc,sync-clk-ps = <15000>; + gpmc,clk-activation-ns = <10>; + gpmc,wr-data-mux-bus-ns = <40>; + gpmc,wr-access-ns = <117>; + + gpmc,sync-clk-ps = <15000>; /* TBC; Where this value came? */ /* * MTD partition table corresponding to Nokia's MeeGo 1.2 From ef4a55b9197a8f844ea0663138e902dcce3e2f36 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 7 Jan 2019 09:52:43 -0800 Subject: [PATCH 005/525] ARM: dts: omap4-droid4: Fix typo in cpcap IRQ flags We're now getting the following error: genirq: Setting trigger mode 1 for irq 230 failed (regmap_irq_set_type+0x0/0x15c) cpcap-usb-phy cpcap-usb-phy.0: could not get irq dp: -524 Cc: Sebastian Reichel Reported-by: Pavel Machek Tested-by: Pavel Machek Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi index ddc7a7bb33c0..f57acf8f66b9 100644 --- a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi +++ b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi @@ -105,7 +105,7 @@ interrupts-extended = < &cpcap 15 0 &cpcap 14 0 &cpcap 28 0 &cpcap 19 0 &cpcap 18 0 &cpcap 17 0 &cpcap 16 0 &cpcap 49 0 - &cpcap 48 1 + &cpcap 48 0 >; interrupt-names = "id_ground", "id_float", "se0conn", "vbusvld", From 2bb7babaae8780dd257abeb354c70cc176fd9dfa Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 7 Jan 2019 13:42:40 -0800 Subject: [PATCH 006/525] ARM: dts: Remove unnecessary idle flags for omap5 uart3 Looks like I accidentally left some extra flags for uart3 to not idle it. This happened as I generated the data from a running system where these flags are set dynamically on boot by omap_hwmod_setup_earlycon_flags() if earlycon is enabled. We can just remove them. Fixes: 4c387984618f ("ARM: dts: omap5: Add l4 interconnect hierarchy and ti-sysc data") Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/omap5-l4.dtsi | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/arm/boot/dts/omap5-l4.dtsi b/arch/arm/boot/dts/omap5-l4.dtsi index 9c7e309d9c2c..0960348002ad 100644 --- a/arch/arm/boot/dts/omap5-l4.dtsi +++ b/arch/arm/boot/dts/omap5-l4.dtsi @@ -1046,8 +1046,6 @@ , ; ti,syss-mask = <1>; - ti,no-reset-on-init; - ti,no-idle-on-init; /* Domains (V, P, C): core, core_pwrdm, l4per_clkdm */ clocks = <&l4per_clkctrl OMAP5_UART3_CLKCTRL 0>; clock-names = "fck"; From aa9ad54285c78e7f69b20b3734c0c79aa98af3c3 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Tue, 8 Jan 2019 15:25:26 +0800 Subject: [PATCH 007/525] ARM: dts: sun6i: Add clock-output-names to osc24M clock The osc24M clock does not have a "clock-output-names" property, which means that the clock name is derived from the node name in Linux. The node name was changed in commit acfd5bbe2641 ("ARM: dts: sun6i: Change clock node names to avoid warnings"). This breaks Linux as the sunxi-ng clock driver implicitly depends on the external clock being named "osc24M". Add a "clock-output-names" property to restore the previous behavior. Fixes: acfd5bbe2641 ("ARM: dts: sun6i: Change clock node names to avoid warnings") Signed-off-by: Chen-Yu Tsai Signed-off-by: Maxime Ripard --- arch/arm/boot/dts/sun6i-a31.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/boot/dts/sun6i-a31.dtsi b/arch/arm/boot/dts/sun6i-a31.dtsi index 353d90f99b40..13304b8c5139 100644 --- a/arch/arm/boot/dts/sun6i-a31.dtsi +++ b/arch/arm/boot/dts/sun6i-a31.dtsi @@ -216,6 +216,7 @@ #clock-cells = <0>; compatible = "fixed-clock"; clock-frequency = <24000000>; + clock-output-names = "osc24M"; }; osc32k: clk-32k { From cc4bddade114b696ab27c1a77cfc7040151306da Mon Sep 17 00:00:00 2001 From: Jernej Skrabec Date: Tue, 8 Jan 2019 20:18:40 +0100 Subject: [PATCH 008/525] ARM: dts: sun8i: h3: Add ethernet0 alias to Beelink X2 Because "ethernet0" alias is missing, U-Boot doesn't generate board specific MAC address. Effect of this is random MAC address every boot and thus new IP address is assigned to the board. Fix this by adding alias. Fixes: 7389172fc3ed ("ARM: dts: sun8i: h3: Enable dwmac-sun8i on the Beelink X2") Signed-off-by: Jernej Skrabec [Maxime: Removed unneeded comment] Signed-off-by: Maxime Ripard --- arch/arm/boot/dts/sun8i-h3-beelink-x2.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/sun8i-h3-beelink-x2.dts b/arch/arm/boot/dts/sun8i-h3-beelink-x2.dts index 5d23667dc2d2..25540b7694d5 100644 --- a/arch/arm/boot/dts/sun8i-h3-beelink-x2.dts +++ b/arch/arm/boot/dts/sun8i-h3-beelink-x2.dts @@ -53,7 +53,7 @@ aliases { serial0 = &uart0; - /* ethernet0 is the H3 emac, defined in sun8i-h3.dtsi */ + ethernet0 = &emac; ethernet1 = &sdiowifi; }; From 0977b2383de69dc48e9fa61c5c77878ed08d87fe Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 4 Jan 2019 14:16:59 +0100 Subject: [PATCH 009/525] selftests: xfrm: add block rules with adjacent/overlapping subnets The existing script lacks a policy pattern that triggers 'tree node merges' in the kernel. Consider adding policy affecting following subnet: pol1: dst 10.0.0.0/22 pol2: dst 10.0.0.0/23 # adds to existing 10.0.0.0/22 node -> no problems here. But now, lets consider reverse order: pol1: dst 10.0.0.0/24 pol2: dst 10.0.0.0/23 # CANNOT add to existing node When second policy gets added, the kernel must check that the new node ("10.0.0.0/23") doesn't overlap with any existing subnet. Example: dst 10.0.0.0/24 dst 10.0.0.1/24 dst 10.0.0.0/23 When the third policy gets added, the kernel must replace the nodes for the 10.0.0.0/24 and 10.0.0.1/24 policies with a single one and must merge all the subtrees/lists stored in those nodes into the new node. The existing test cases only have overlaps with a single node, so no merging takes place (we can always remove the 'old' node and replace it with the new subnet prefix). Add a few 'block policies' in a pattern that triggers this, with a priority that will make kernel prefer the 'esp' rules. Make sure the 'tunnel ping' tests still pass after they have been added. Signed-off-by: Florian Westphal Signed-off-by: Steffen Klassert --- tools/testing/selftests/net/xfrm_policy.sh | 109 +++++++++++++++++---- 1 file changed, 91 insertions(+), 18 deletions(-) diff --git a/tools/testing/selftests/net/xfrm_policy.sh b/tools/testing/selftests/net/xfrm_policy.sh index 8db35b99457c..b5a1b565a7e6 100755 --- a/tools/testing/selftests/net/xfrm_policy.sh +++ b/tools/testing/selftests/net/xfrm_policy.sh @@ -46,6 +46,58 @@ do_esp() { ip -net $ns xfrm policy add src $rnet dst $lnet dir fwd tmpl src $remote dst $me proto esp mode tunnel priority 100 action allow } +# add policies with different netmasks, to make sure kernel carries +# the policies contained within new netmask over when search tree is +# re-built. +# peer netns that are supposed to be encapsulated via esp have addresses +# in the 10.0.1.0/24 and 10.0.2.0/24 subnets, respectively. +# +# Adding a policy for '10.0.1.0/23' will make it necessary to +# alter the prefix of 10.0.1.0 subnet. +# In case new prefix overlaps with existing node, the node and all +# policies it carries need to be merged with the existing one(s). +# +# Do that here. +do_overlap() +{ + local ns=$1 + + # adds new nodes to tree (neither network exists yet in policy database). + ip -net $ns xfrm policy add src 10.1.0.0/24 dst 10.0.0.0/24 dir fwd priority 200 action block + + # adds a new node in the 10.0.0.0/24 tree (dst node exists). + ip -net $ns xfrm policy add src 10.2.0.0/24 dst 10.0.0.0/24 dir fwd priority 200 action block + + # adds a 10.2.0.0/24 node, but for different dst. + ip -net $ns xfrm policy add src 10.2.0.0/24 dst 10.0.1.0/24 dir fwd priority 200 action block + + # dst now overlaps with the 10.0.1.0/24 ESP policy in fwd. + # kernel must 'promote' existing one (10.0.0.0/24) to 10.0.0.0/23. + # But 10.0.0.0/23 also includes existing 10.0.1.0/24, so that node + # also has to be merged too, including source-sorted subtrees. + # old: + # 10.0.0.0/24 (node 1 in dst tree of the bin) + # 10.1.0.0/24 (node in src tree of dst node 1) + # 10.2.0.0/24 (node in src tree of dst node 1) + # 10.0.1.0/24 (node 2 in dst tree of the bin) + # 10.0.2.0/24 (node in src tree of dst node 2) + # 10.2.0.0/24 (node in src tree of dst node 2) + # + # The next 'policy add' adds dst '10.0.0.0/23', which means + # that dst node 1 and dst node 2 have to be merged including + # the sub-tree. As no duplicates are allowed, policies in + # the two '10.0.2.0/24' are also merged. + # + # after the 'add', internal search tree should look like this: + # 10.0.0.0/23 (node in dst tree of bin) + # 10.0.2.0/24 (node in src tree of dst node) + # 10.1.0.0/24 (node in src tree of dst node) + # 10.2.0.0/24 (node in src tree of dst node) + # + # 10.0.0.0/24 and 10.0.1.0/24 nodes have been merged as 10.0.0.0/23. + ip -net $ns xfrm policy add src 10.1.0.0/24 dst 10.0.0.0/23 dir fwd priority 200 action block +} + do_esp_policy_get_check() { local ns=$1 local lnet=$2 @@ -160,6 +212,41 @@ check_xfrm() { return $lret } +check_exceptions() +{ + logpostfix="$1" + local lret=0 + + # ping to .254 should be excluded from the tunnel (exception is in place). + check_xfrm 0 254 + if [ $? -ne 0 ]; then + echo "FAIL: expected ping to .254 to fail ($logpostfix)" + lret=1 + else + echo "PASS: ping to .254 bypassed ipsec tunnel ($logpostfix)" + fi + + # ping to .253 should use use ipsec due to direct policy exception. + check_xfrm 1 253 + if [ $? -ne 0 ]; then + echo "FAIL: expected ping to .253 to use ipsec tunnel ($logpostfix)" + lret=1 + else + echo "PASS: direct policy matches ($logpostfix)" + fi + + # ping to .2 should use ipsec. + check_xfrm 1 2 + if [ $? -ne 0 ]; then + echo "FAIL: expected ping to .2 to use ipsec tunnel ($logpostfix)" + lret=1 + else + echo "PASS: policy matches ($logpostfix)" + fi + + return $lret +} + #check for needed privileges if [ "$(id -u)" -ne 0 ];then echo "SKIP: Need root privileges" @@ -270,31 +357,17 @@ do_exception ns4 10.0.3.10 10.0.3.1 10.0.1.253 10.0.1.240/28 do_exception ns3 dead:3::1 dead:3::10 dead:2::fd dead:2:f0::/96 do_exception ns4 dead:3::10 dead:3::1 dead:1::fd dead:1:f0::/96 -# ping to .254 should now be excluded from the tunnel -check_xfrm 0 254 +check_exceptions "exceptions" if [ $? -ne 0 ]; then - echo "FAIL: expected ping to .254 to fail" ret=1 -else - echo "PASS: ping to .254 bypassed ipsec tunnel" fi -# ping to .253 should use use ipsec due to direct policy exception. -check_xfrm 1 253 -if [ $? -ne 0 ]; then - echo "FAIL: expected ping to .253 to use ipsec tunnel" - ret=1 -else - echo "PASS: direct policy matches" -fi +# insert block policies with adjacent/overlapping netmasks +do_overlap ns3 -# ping to .2 should use ipsec. -check_xfrm 1 2 +check_exceptions "exceptions and block policies" if [ $? -ne 0 ]; then - echo "FAIL: expected ping to .2 to use ipsec tunnel" ret=1 -else - echo "PASS: policy matches" fi for i in 1 2 3 4;do ip netns del ns$i;done From 355b00d1e14051c13aea48c1c5430c486fed2d7a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 4 Jan 2019 14:17:00 +0100 Subject: [PATCH 010/525] xfrm: policy: use hlist rcu variants on inexact insert, part 2 This function was modeled on the 'exact' insert one, which did not use the rcu variant either. When I fixed the 'exact' insert I forgot to propagate this to my development tree, so the inexact variant retained the bug. Fixes: 9cf545ebd591d ("xfrm: policy: store inexact policies in a tree ordered by destination address") Signed-off-by: Florian Westphal Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 934492bad8e0..628b389af2ba 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -856,9 +856,9 @@ static void xfrm_policy_inexact_list_reinsert(struct net *net, } if (newpos) - hlist_add_behind(&policy->bydst, newpos); + hlist_add_behind_rcu(&policy->bydst, newpos); else - hlist_add_head(&policy->bydst, &n->hhead); + hlist_add_head_rcu(&policy->bydst, &n->hhead); /* paranoia checks follow. * Check that the reinserted policy matches at least From 7a474c36586f4277f930ab7e6865c97e44dfc3bc Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 4 Jan 2019 14:17:01 +0100 Subject: [PATCH 011/525] xfrm: policy: increment xfrm_hash_generation on hash rebuild Hash rebuild will re-set all the inexact entries, then re-insert them. Lookups that can occur in parallel will therefore not find any policies. This was safe when lookups were still guarded by rwlock. After rcu-ification, lookups check the hash_generation seqcount to detect when a hash resize takes place. Hash rebuild missed the needed increment. Hash resizes and hash rebuilds cannot occur in parallel (both acquire hash_resize_mutex), so just increment xfrm_hash_generation, like resize. Fixes: a7c44247f704e3 ("xfrm: policy: make xfrm_policy_lookup_bytype lockless") Signed-off-by: Florian Westphal Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 628b389af2ba..d8fba27a4bfb 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1235,6 +1235,7 @@ static void xfrm_hash_rebuild(struct work_struct *work) } while (read_seqretry(&net->xfrm.policy_hthresh.lock, seq)); spin_lock_bh(&net->xfrm.xfrm_policy_lock); + write_seqcount_begin(&xfrm_policy_hash_generation); /* make sure that we can insert the indirect policies again before * we start with destructive action. @@ -1334,6 +1335,7 @@ static void xfrm_hash_rebuild(struct work_struct *work) out_unlock: __xfrm_policy_inexact_flush(net); + write_seqcount_end(&xfrm_policy_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); mutex_unlock(&hash_resize_mutex); From 1548bc4e0512700cf757192c106b3a20ab639223 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 4 Jan 2019 14:17:02 +0100 Subject: [PATCH 012/525] xfrm: policy: delete inexact policies from inexact list on hash rebuild An xfrm hash rebuild has to reset the inexact policy list before the policies get re-inserted: A change of hash thresholds will result in policies to get moved from inexact tree to the policy hash table. If the thresholds are increased again later, they get moved from hash table to inexact tree. We must unlink all policies from the inexact tree before re-insertion. Otherwise 'migrate' may find policies that are in main hash table a second time, when it searches the inexact lists. Furthermore, re-insertion without deletion can cause elements ->next to point back to itself, causing soft lockups or double-frees. Reported-by: syzbot+9d971dd21eb26567036b@syzkaller.appspotmail.com Fixes: 9cf545ebd591da ("xfrm: policy: store inexact policies in a tree ordered by destination address") Signed-off-by: Florian Westphal Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 23 ++++++++++------------- 1 file changed, 10 insertions(+), 13 deletions(-) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index d8fba27a4bfb..24dfd1e47cf0 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -680,16 +680,6 @@ static void xfrm_hash_resize(struct work_struct *work) mutex_unlock(&hash_resize_mutex); } -static void xfrm_hash_reset_inexact_table(struct net *net) -{ - struct xfrm_pol_inexact_bin *b; - - lockdep_assert_held(&net->xfrm.xfrm_policy_lock); - - list_for_each_entry(b, &net->xfrm.inexact_bins, inexact_bins) - INIT_HLIST_HEAD(&b->hhead); -} - /* Make sure *pol can be inserted into fastbin. * Useful to check that later insert requests will be sucessful * (provided xfrm_policy_lock is held throughout). @@ -1279,10 +1269,14 @@ static void xfrm_hash_rebuild(struct work_struct *work) } /* reset the bydst and inexact table in all directions */ - xfrm_hash_reset_inexact_table(net); - for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { - INIT_HLIST_HEAD(&net->xfrm.policy_inexact[dir]); + struct hlist_node *n; + + hlist_for_each_entry_safe(policy, n, + &net->xfrm.policy_inexact[dir], + bydst_inexact_list) + hlist_del_init(&policy->bydst_inexact_list); + hmask = net->xfrm.policy_bydst[dir].hmask; odst = net->xfrm.policy_bydst[dir].table; for (i = hmask; i >= 0; i--) @@ -1314,6 +1308,9 @@ static void xfrm_hash_rebuild(struct work_struct *work) newpos = NULL; chain = policy_hash_bysel(net, &policy->selector, policy->family, dir); + + hlist_del_rcu(&policy->bydst); + if (!chain) { void *p = xfrm_policy_inexact_insert(policy, dir, 0); From 1d38900cb85d5d311dbd23c2c93294527b82cd2b Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 4 Jan 2019 14:17:03 +0100 Subject: [PATCH 013/525] xfrm: policy: fix reinsertion on node merge "newpos" has wrong scope. It must be NULL on each iteration of the loop. Otherwise, when policy is to be inserted at the start, we would instead insert at point found by the previous loop-iteration instead. Also, we need to unlink the policy before we reinsert it to the new node, else we can get next-points-to-self loops. Because policies are only ordered by priority it is irrelevant which policy is "more recent" except when two policies have same priority. (the more recent one is placed after the older one). In these cases, we can use the ->pos id number to know which one is the 'older': the higher the id, the more recent the policy. So we only need to unlink all policies from the node that is about to be removed, and insert them to the replacement node. Fixes: 9cf545ebd591da ("xfrm: policy: store inexact policies in a tree ordered by destination address") Signed-off-by: Florian Westphal Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 24dfd1e47cf0..e691683223ee 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -823,13 +823,13 @@ static void xfrm_policy_inexact_list_reinsert(struct net *net, u16 family) { unsigned int matched_s, matched_d; - struct hlist_node *newpos = NULL; struct xfrm_policy *policy, *p; matched_s = 0; matched_d = 0; list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) { + struct hlist_node *newpos = NULL; bool matches_s, matches_d; if (!policy->bydst_reinsert) @@ -839,7 +839,10 @@ static void xfrm_policy_inexact_list_reinsert(struct net *net, policy->bydst_reinsert = false; hlist_for_each_entry(p, &n->hhead, bydst) { - if (policy->priority >= p->priority) + if (policy->priority > p->priority) + newpos = &p->bydst; + else if (policy->priority == p->priority && + policy->pos > p->pos) newpos = &p->bydst; else break; @@ -955,12 +958,11 @@ static void xfrm_policy_inexact_node_merge(struct net *net, family); } - hlist_for_each_entry(tmp, &v->hhead, bydst) - tmp->bydst_reinsert = true; - hlist_for_each_entry(tmp, &n->hhead, bydst) + hlist_for_each_entry(tmp, &v->hhead, bydst) { tmp->bydst_reinsert = true; + hlist_del_rcu(&tmp->bydst); + } - INIT_HLIST_HEAD(&n->hhead); xfrm_policy_inexact_list_reinsert(net, n, family); } From fcf86f55f2d4a6b58da5feccd45d9584edc17c5a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 4 Jan 2019 14:17:04 +0100 Subject: [PATCH 014/525] selftests: xfrm: alter htresh to trigger move of policies to hash table ... and back to inexact tree. Repeat ping test after each htresh change: lookup results must not change. Signed-off-by: Florian Westphal Signed-off-by: Steffen Klassert --- tools/testing/selftests/net/xfrm_policy.sh | 44 ++++++++++++++++++++-- 1 file changed, 40 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/net/xfrm_policy.sh b/tools/testing/selftests/net/xfrm_policy.sh index b5a1b565a7e6..8ce54600d4d1 100755 --- a/tools/testing/selftests/net/xfrm_policy.sh +++ b/tools/testing/selftests/net/xfrm_policy.sh @@ -28,6 +28,19 @@ KEY_AES=0x0123456789abcdef0123456789012345 SPI1=0x1 SPI2=0x2 +do_esp_policy() { + local ns=$1 + local me=$2 + local remote=$3 + local lnet=$4 + local rnet=$5 + + # to encrypt packets as they go out (includes forwarded packets that need encapsulation) + ip -net $ns xfrm policy add src $lnet dst $rnet dir out tmpl src $me dst $remote proto esp mode tunnel priority 100 action allow + # to fwd decrypted packets after esp processing: + ip -net $ns xfrm policy add src $rnet dst $lnet dir fwd tmpl src $remote dst $me proto esp mode tunnel priority 100 action allow +} + do_esp() { local ns=$1 local me=$2 @@ -40,10 +53,7 @@ do_esp() { ip -net $ns xfrm state add src $remote dst $me proto esp spi $spi_in enc aes $KEY_AES auth sha1 $KEY_SHA mode tunnel sel src $rnet dst $lnet ip -net $ns xfrm state add src $me dst $remote proto esp spi $spi_out enc aes $KEY_AES auth sha1 $KEY_SHA mode tunnel sel src $lnet dst $rnet - # to encrypt packets as they go out (includes forwarded packets that need encapsulation) - ip -net $ns xfrm policy add src $lnet dst $rnet dir out tmpl src $me dst $remote proto esp mode tunnel priority 100 action allow - # to fwd decrypted packets after esp processing: - ip -net $ns xfrm policy add src $rnet dst $lnet dir fwd tmpl src $remote dst $me proto esp mode tunnel priority 100 action allow + do_esp_policy $ns $me $remote $lnet $rnet } # add policies with different netmasks, to make sure kernel carries @@ -370,6 +380,32 @@ if [ $? -ne 0 ]; then ret=1 fi +for n in ns3 ns4;do + ip -net $n xfrm policy set hthresh4 28 24 hthresh6 126 125 + sleep $((RANDOM%5)) +done + +check_exceptions "exceptions and block policies after hresh changes" + +# full flush of policy db, check everything gets freed incl. internal meta data +ip -net ns3 xfrm policy flush + +do_esp_policy ns3 10.0.3.1 10.0.3.10 10.0.1.0/24 10.0.2.0/24 +do_exception ns3 10.0.3.1 10.0.3.10 10.0.2.253 10.0.2.240/28 + +# move inexact policies to hash table +ip -net ns3 xfrm policy set hthresh4 16 16 + +sleep $((RANDOM%5)) +check_exceptions "exceptions and block policies after hthresh change in ns3" + +# restore original hthresh settings -- move policies back to tables +for n in ns3 ns4;do + ip -net $n xfrm policy set hthresh4 32 32 hthresh6 128 128 + sleep $((RANDOM%5)) +done +check_exceptions "exceptions and block policies after hresh change to normal" + for i in 1 2 3 4;do ip netns del ns$i;done exit $ret From 12750abad517a991c4568969bc748db302ab52cd Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 4 Jan 2019 14:17:05 +0100 Subject: [PATCH 015/525] xfrm: policy: fix infinite loop when merging src-nodes With very small change to test script we can trigger softlockup due to bogus assignment of 'p' (policy to be examined) on restart. Previously the two to-be-merged nodes had same address/prefixlength pair, so no erase/reinsert was necessary, we only had to append the list from node a to b. If prefix lengths are different, the node has to be deleted and re-inserted into the tree, with the updated prefix length. This was broken; due to bogus update to 'p' this loops forever. Add a 'restart' label and use that instead. While at it, don't perform the unneeded reinserts of the policies that are already sorted into the 'new' node. A previous patch in this series made xfrm_policy_inexact_list_reinsert() use the relative position indicator to sort policies according to age in case priorities are identical. Fixes: 6ac098b2a9d30 ("xfrm: policy: add 2nd-level saddr trees for inexact policies") Signed-off-by: Florian Westphal Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 15 +++++++-------- tools/testing/selftests/net/xfrm_policy.sh | 4 ++-- 2 files changed, 9 insertions(+), 10 deletions(-) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index e691683223ee..8cfd75b62396 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -886,12 +886,13 @@ static void xfrm_policy_inexact_node_reinsert(struct net *net, struct rb_root *new, u16 family) { - struct rb_node **p, *parent = NULL; struct xfrm_pol_inexact_node *node; + struct rb_node **p, *parent; /* we should not have another subtree here */ WARN_ON_ONCE(!RB_EMPTY_ROOT(&n->root)); - +restart: + parent = NULL; p = &new->rb_node; while (*p) { u8 prefixlen; @@ -911,12 +912,11 @@ static void xfrm_policy_inexact_node_reinsert(struct net *net, } else { struct xfrm_policy *tmp; - hlist_for_each_entry(tmp, &node->hhead, bydst) - tmp->bydst_reinsert = true; - hlist_for_each_entry(tmp, &n->hhead, bydst) + hlist_for_each_entry(tmp, &n->hhead, bydst) { tmp->bydst_reinsert = true; + hlist_del_rcu(&tmp->bydst); + } - INIT_HLIST_HEAD(&node->hhead); xfrm_policy_inexact_list_reinsert(net, node, family); if (node->prefixlen == n->prefixlen) { @@ -928,8 +928,7 @@ static void xfrm_policy_inexact_node_reinsert(struct net *net, kfree_rcu(n, rcu); n = node; n->prefixlen = prefixlen; - *p = new->rb_node; - parent = NULL; + goto restart; } } diff --git a/tools/testing/selftests/net/xfrm_policy.sh b/tools/testing/selftests/net/xfrm_policy.sh index 8ce54600d4d1..71d7fdc513c1 100755 --- a/tools/testing/selftests/net/xfrm_policy.sh +++ b/tools/testing/selftests/net/xfrm_policy.sh @@ -78,8 +78,8 @@ do_overlap() # adds a new node in the 10.0.0.0/24 tree (dst node exists). ip -net $ns xfrm policy add src 10.2.0.0/24 dst 10.0.0.0/24 dir fwd priority 200 action block - # adds a 10.2.0.0/24 node, but for different dst. - ip -net $ns xfrm policy add src 10.2.0.0/24 dst 10.0.1.0/24 dir fwd priority 200 action block + # adds a 10.2.0.0/23 node, but for different dst. + ip -net $ns xfrm policy add src 10.2.0.0/23 dst 10.0.1.0/24 dir fwd priority 200 action block # dst now overlaps with the 10.0.1.0/24 ESP policy in fwd. # kernel must 'promote' existing one (10.0.0.0/24) to 10.0.0.0/23. From dd9ee3444014e8f28c0eefc9fffc9ac9c5248c12 Mon Sep 17 00:00:00 2001 From: Su Yanjun Date: Sun, 6 Jan 2019 21:31:20 -0500 Subject: [PATCH 016/525] vti4: Fix a ipip packet processing bug in 'IPCOMP' virtual tunnel Recently we run a network test over ipcomp virtual tunnel.We find that if a ipv4 packet needs fragment, then the peer can't receive it. We deep into the code and find that when packet need fragment the smaller fragment will be encapsulated by ipip not ipcomp. So when the ipip packet goes into xfrm, it's skb->dev is not properly set. The ipv4 reassembly code always set skb'dev to the last fragment's dev. After ipv4 defrag processing, when the kernel rp_filter parameter is set, the skb will be drop by -EXDEV error. This patch adds compatible support for the ipip process in ipcomp virtual tunnel. Signed-off-by: Su Yanjun Signed-off-by: Steffen Klassert --- net/ipv4/ip_vti.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index d7b43e700023..68a21bf75dd0 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -74,6 +74,33 @@ drop: return 0; } +static int vti_input_ipip(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type) +{ + struct ip_tunnel *tunnel; + const struct iphdr *iph = ip_hdr(skb); + struct net *net = dev_net(skb->dev); + struct ip_tunnel_net *itn = net_generic(net, vti_net_id); + + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, + iph->saddr, iph->daddr, 0); + if (tunnel) { + if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + goto drop; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel; + + skb->dev = tunnel->dev; + + return xfrm_input(skb, nexthdr, spi, encap_type); + } + + return -EINVAL; +drop: + kfree_skb(skb); + return 0; +} + static int vti_rcv(struct sk_buff *skb) { XFRM_SPI_SKB_CB(skb)->family = AF_INET; @@ -82,6 +109,14 @@ static int vti_rcv(struct sk_buff *skb) return vti_input(skb, ip_hdr(skb)->protocol, 0, 0); } +static int vti_rcv_ipip(struct sk_buff *skb) +{ + XFRM_SPI_SKB_CB(skb)->family = AF_INET; + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); + + return vti_input_ipip(skb, ip_hdr(skb)->protocol, ip_hdr(skb)->saddr, 0); +} + static int vti_rcv_cb(struct sk_buff *skb, int err) { unsigned short family; @@ -435,6 +470,12 @@ static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = { .priority = 100, }; +static struct xfrm_tunnel ipip_handler __read_mostly = { + .handler = vti_rcv_ipip, + .err_handler = vti4_err, + .priority = 0, +}; + static int __net_init vti_init_net(struct net *net) { int err; @@ -603,6 +644,13 @@ static int __init vti_init(void) if (err < 0) goto xfrm_proto_comp_failed; + msg = "ipip tunnel"; + err = xfrm4_tunnel_register(&ipip_handler, AF_INET); + if (err < 0) { + pr_info("%s: cant't register tunnel\n",__func__); + goto xfrm_tunnel_failed; + } + msg = "netlink interface"; err = rtnl_link_register(&vti_link_ops); if (err < 0) @@ -612,6 +660,8 @@ static int __init vti_init(void) rtnl_link_failed: xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP); +xfrm_tunnel_failed: + xfrm4_tunnel_deregister(&ipip_handler, AF_INET); xfrm_proto_comp_failed: xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); xfrm_proto_ah_failed: From b1360dcfdaa1d55952e5ec8dd9d99f88965d7ac9 Mon Sep 17 00:00:00 2001 From: Jernej Skrabec Date: Wed, 9 Jan 2019 19:16:04 +0100 Subject: [PATCH 017/525] arm64: dts: allwinner: a64: Fix USB OTG regulator Currently, AXP803 driver assumes that reg_drivevbus is input which is wrong. Unfortunate consequence of that is that none of the USB ports work on the board, even USB HOST port, because USB PHY driver probing fails due to missing regulator. Fix that by adding "x-powers,drive-vbus-en" property to AXP803 node. Fixes: 14ff5d8f9151 ("arm64: dts: allwinner: a64: Orange Pi Win: Enable USB OTG socket") Cc: stable@vger.kernel.org Signed-off-by: Jernej Skrabec Signed-off-by: Maxime Ripard --- arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts index b0c64f75792c..8974b5a1d3b1 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts @@ -188,6 +188,7 @@ reg = <0x3a3>; interrupt-parent = <&r_intc>; interrupts = <0 IRQ_TYPE_LEVEL_LOW>; + x-powers,drive-vbus-en; /* set N_VBUSEN as output pin */ }; }; From 35e6103861a3a970de6c84688c6e7a1f65b164ca Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 9 Jan 2019 14:37:34 +0100 Subject: [PATCH 018/525] xfrm: refine validation of template and selector families The check assumes that in transport mode, the first templates family must match the address family of the policy selector. Syzkaller managed to build a template using MODE_ROUTEOPTIMIZATION, with ipv4-in-ipv6 chain, leading to following splat: BUG: KASAN: stack-out-of-bounds in xfrm_state_find+0x1db/0x1854 Read of size 4 at addr ffff888063e57aa0 by task a.out/2050 xfrm_state_find+0x1db/0x1854 xfrm_tmpl_resolve+0x100/0x1d0 xfrm_resolve_and_create_bundle+0x108/0x1000 [..] Problem is that addresses point into flowi4 struct, but xfrm_state_find treats them as being ipv6 because it uses templ->encap_family is used (AF_INET6 in case of reproducer) rather than family (AF_INET). This patch inverts the logic: Enforce 'template family must match selector' EXCEPT for tunnel and BEET mode. In BEET and Tunnel mode, xfrm_tmpl_resolve_one will have remote/local address pointers changed to point at the addresses found in the template, rather than the flowi ones, so no oob read will occur. Reported-by: 3ntr0py1337@gmail.com Reported-by: Daniel Borkmann Signed-off-by: Florian Westphal Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_user.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 277c1c46fe94..c6d26afcf89d 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1488,10 +1488,15 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family) if (!ut[i].family) ut[i].family = family; - if ((ut[i].mode == XFRM_MODE_TRANSPORT) && - (ut[i].family != prev_family)) - return -EINVAL; - + switch (ut[i].mode) { + case XFRM_MODE_TUNNEL: + case XFRM_MODE_BEET: + break; + default: + if (ut[i].family != prev_family) + return -EINVAL; + break; + } if (ut[i].mode >= XFRM_MODE_MAX) return -EINVAL; From e35e26b26e955c53e61c154ba26b9bb15da6b858 Mon Sep 17 00:00:00 2001 From: Carlo Caione Date: Fri, 7 Dec 2018 10:52:31 +0000 Subject: [PATCH 019/525] arm: dts: meson: Fix IRQ trigger type for macirq A long running stress test on a custom board shipping an AXG SoCs and a Realtek RTL8211F PHY revealed that after a few hours the connection speed would drop drastically, from ~1000Mbps to ~3Mbps. At the same time the 'macirq' (eth0) IRQ would stop being triggered at all and as consequence the GMAC IRQs never ACKed. After a painful investigation the problem seemed to be due to a wrong defined IRQ type for the GMAC IRQ that should be LEVEL_HIGH instead of EDGE_RISING. The change in the macirq IRQ type also solved another long standing issue affecting this SoC/PHY where EEE was causing the network connection to die after stressing it with iperf3 (even though much sooner). It's now possible to remove the 'eee-broken-1000t' quirk as well. Fixes: 9c15795a4f96 ("ARM: dts: meson8b-odroidc1: ethernet support") Signed-off-by: Carlo Caione Reviewed-by: Martin Blumenstingl Tested-by: Martin Blumenstingl Signed-off-by: Kevin Hilman --- arch/arm/boot/dts/meson.dtsi | 2 +- arch/arm/boot/dts/meson8b-odroidc1.dts | 1 - 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/meson.dtsi b/arch/arm/boot/dts/meson.dtsi index e4645f612712..2ab74860d962 100644 --- a/arch/arm/boot/dts/meson.dtsi +++ b/arch/arm/boot/dts/meson.dtsi @@ -274,7 +274,7 @@ compatible = "amlogic,meson6-dwmac", "snps,dwmac"; reg = <0xc9410000 0x10000 0xc1108108 0x4>; - interrupts = ; + interrupts = ; interrupt-names = "macirq"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/meson8b-odroidc1.dts b/arch/arm/boot/dts/meson8b-odroidc1.dts index 58669abda259..a951a6632d0c 100644 --- a/arch/arm/boot/dts/meson8b-odroidc1.dts +++ b/arch/arm/boot/dts/meson8b-odroidc1.dts @@ -221,7 +221,6 @@ /* Realtek RTL8211F (0x001cc916) */ eth_phy: ethernet-phy@0 { reg = <0>; - eee-broken-1000t; interrupt-parent = <&gpio_intc>; /* GPIOH_3 */ interrupts = <17 IRQ_TYPE_LEVEL_LOW>; From 3fb348e030319f20ebbde082a449d4bf8a96f2fd Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Sat, 29 Dec 2018 13:57:09 +0100 Subject: [PATCH 020/525] ARM: dts: meson8b: odroidc1: mark the SD card detection GPIO active-low After commit 89a5e15bcba87d ("gpio/mmc/of: Respect polarity in the device tree") SD cards are not detected anymore. The CD GPIO is "active low" on Odroid-C1. The MMC dt-bindings specify: "[...] using the "cd-inverted" property means, that the CD line is active high, i.e. it is high, when a card is inserted". Fix the description of the SD card by marking it as GPIO_ACTIVE_LOW and drop the "cd-inverted" property. This makes the definition consistent with the existing dt-bindings and fixes the check whether an SD card is inserted. Fixes: e03efbce6bebf5 ("ARM: dts: meson8b-odroidc1: add microSD support") Signed-off-by: Martin Blumenstingl Reviewed-by: Linus Walleij Tested-by: Anand Moon Signed-off-by: Kevin Hilman --- arch/arm/boot/dts/meson8b-odroidc1.dts | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/meson8b-odroidc1.dts b/arch/arm/boot/dts/meson8b-odroidc1.dts index a951a6632d0c..0f0a46ddf3ff 100644 --- a/arch/arm/boot/dts/meson8b-odroidc1.dts +++ b/arch/arm/boot/dts/meson8b-odroidc1.dts @@ -272,8 +272,7 @@ cap-sd-highspeed; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&tflash_vdd>; vqmmc-supply = <&tf_io>; From c8bfe65fb1fb7a43d766df1dfa379406112cba61 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Sat, 29 Dec 2018 13:57:10 +0100 Subject: [PATCH 021/525] ARM: dts: meson8b: ec100: mark the SD card detection GPIO active-low After commit 89a5e15bcba87d ("gpio/mmc/of: Respect polarity in the device tree") SD cards are not detected anymore. The CD GPIO is "active low" on the EC-100. The MMC dt-bindings specify: "[...] using the "cd-inverted" property means, that the CD line is active high, i.e. it is high, when a card is inserted". Fix the description of the SD card by marking it as GPIO_ACTIVE_LOW and drop the "cd-inverted" property. This makes the definition consistent with the existing dt-bindings and fixes the check whether an SD card is inserted. Fixes: bbedc1f1d90e33 ("ARM: dts: meson8b: Add support for the Endless Mini (EC-100)") Signed-off-by: Martin Blumenstingl Reviewed-by: Linus Walleij Signed-off-by: Kevin Hilman --- arch/arm/boot/dts/meson8b-ec100.dts | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/meson8b-ec100.dts b/arch/arm/boot/dts/meson8b-ec100.dts index 0872f6e3abf5..d50fc2f60fa3 100644 --- a/arch/arm/boot/dts/meson8b-ec100.dts +++ b/arch/arm/boot/dts/meson8b-ec100.dts @@ -205,8 +205,7 @@ cap-sd-highspeed; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vcc_3v3>; }; From 8615f5596335db0978cea593dcd0070dc5f8b116 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Sat, 29 Dec 2018 13:57:11 +0100 Subject: [PATCH 022/525] ARM: dts: meson8m2: mxiii-plus: mark the SD card detection GPIO active-low After commit 89a5e15bcba87d ("gpio/mmc/of: Respect polarity in the device tree") SD cards are not detected anymore. The CD GPIO is "active low" on the MXIII-Plus. The MMC dt-bindings specify: "[...] using the "cd-inverted" property means, that the CD line is active high, i.e. it is high, when a card is inserted". Fix the description of the SD card by marking it as GPIO_ACTIVE_LOW and drop the "cd-inverted" property. This makes the definition consistent with the existing dt-bindings and fixes the check whether an SD card is inserted. Fixes: 35ee52bea66c74 ("ARM: dts: meson8m2: add support for the Tronsmart MXIII Plus") Signed-off-by: Martin Blumenstingl Reviewed-by: Linus Walleij Signed-off-by: Kevin Hilman --- arch/arm/boot/dts/meson8m2-mxiii-plus.dts | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/meson8m2-mxiii-plus.dts b/arch/arm/boot/dts/meson8m2-mxiii-plus.dts index f5853610b20b..6ac02beb5fa7 100644 --- a/arch/arm/boot/dts/meson8m2-mxiii-plus.dts +++ b/arch/arm/boot/dts/meson8m2-mxiii-plus.dts @@ -206,8 +206,7 @@ cap-sd-highspeed; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vcc_3v3>; }; From 2d2d478576d71000b29c52668c5712c825ee9af8 Mon Sep 17 00:00:00 2001 From: Ryder Lee Date: Wed, 9 Jan 2019 10:13:55 +0800 Subject: [PATCH 023/525] pinctrl: mediatek: fix Kconfig build errors for moore core on i386 or x86_64: Lots of build errors for drivers/pinctrl/mediatek/pinctrl-moore.c when CONFIG_OF is not enabled (but COMPILE_TEST is). first this: WARNING: unmet direct dependencies detected for PINCTRL_MTK_MOORE Depends on [n]: PINCTRL [=y] && (ARCH_MEDIATEK || COMPILE_TEST [=y]) && OF [=n] Selected by [y]: - PINCTRL_MT7623 [=y] && PINCTRL [=y] && (ARCH_MEDIATEK || COMPILE_TEST [=y]) && (MACH_MT7623 || COMPILE_TEST [=y]) and then: ../drivers/pinctrl/mediatek/pinctrl-moore.c:22:44: error: array type has incomplete element type static const struct pinconf_generic_params mtk_custom_bindings[] = { (etc) Fixes: b5af33df50e9 ("pinctrl: mediatek: improve Kconfig dependencies") Cc: stable@vger.kernel.org Reported-by: Randy Dunlap Signed-off-by: Ryder Lee Acked-by: Sean Wang Signed-off-by: Linus Walleij --- drivers/pinctrl/mediatek/Kconfig | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/pinctrl/mediatek/Kconfig b/drivers/pinctrl/mediatek/Kconfig index 1817786ab6aa..a005cbccb4f7 100644 --- a/drivers/pinctrl/mediatek/Kconfig +++ b/drivers/pinctrl/mediatek/Kconfig @@ -45,12 +45,14 @@ config PINCTRL_MT2701 config PINCTRL_MT7623 bool "Mediatek MT7623 pin control with generic binding" depends on MACH_MT7623 || COMPILE_TEST + depends on OF default MACH_MT7623 select PINCTRL_MTK_MOORE config PINCTRL_MT7629 bool "Mediatek MT7629 pin control" depends on MACH_MT7629 || COMPILE_TEST + depends on OF default MACH_MT7629 select PINCTRL_MTK_MOORE @@ -92,6 +94,7 @@ config PINCTRL_MT6797 config PINCTRL_MT7622 bool "MediaTek MT7622 pin control" + depends on OF depends on ARM64 || COMPILE_TEST default ARM64 && ARCH_MEDIATEK select PINCTRL_MTK_MOORE From 00ccd4532c8a61e6c65ca62eb7b6da6a272c30f1 Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Sat, 12 Jan 2019 09:02:51 +0800 Subject: [PATCH 024/525] ARM: dts: vf610-bk4: fix incorrect #address-cells for dspi3 The dspi3 is used as slave controller on vf610-bk4, and the default '#address-cells = <1>;' setting in vfxxx.dtsi causes the following DTC warning. DTC arch/arm/boot/dts/vf610-bk4.dtb ../arch/arm/boot/dts/vfxxx.dtsi:550.24-563.6: Warning (spi_bus_bridge): /soc/aips-bus@40080000/spi@400ad000: incorrect #address-cells for SPI bus also defined at ../arch/arm/boot/dts/vf610-bk4.dts:107.8-119.3 arch/arm/boot/dts/vf610-bk4.dtb: Warning (spi_bus_reg): Failed prerequisite 'spi_bus_bridge' For spi device used as slave controller, '#address-cells' should be 0. Let's overwrite the property in vf610-bk4.dts to fix the warning. Reported-by: Stephen Rothwell Signed-off-by: Shawn Guo --- arch/arm/boot/dts/vf610-bk4.dts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/vf610-bk4.dts b/arch/arm/boot/dts/vf610-bk4.dts index 689c8930dce3..b08d561d6748 100644 --- a/arch/arm/boot/dts/vf610-bk4.dts +++ b/arch/arm/boot/dts/vf610-bk4.dts @@ -110,11 +110,11 @@ bus-num = <3>; status = "okay"; spi-slave; + #address-cells = <0>; - slave@0 { + slave { compatible = "lwn,bk4"; spi-max-frequency = <30000000>; - reg = <0>; }; }; From 08b88e80a1f476970284235278bf27a273b94118 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Fri, 21 Dec 2018 18:12:03 +0000 Subject: [PATCH 025/525] ARM: dts: imx: replace gpio-key,wakeup with wakeup-source property Most of the legacy "gpio-key,wakeup" and "enable-sdio-wakeup" boolean properties are already replaced with "wakeup-source". However few occurrences of old property has popped up again, probably from the remnants in downstream trees. Almost all of those were remove couple of years back. Replace the legacy properties with the unified "wakeup-source" property introduced in the commit 700a38b27eef ("Input: gpio_keys - switch to using generic device properties") and commit 0dbcdc0622ea ("mmc: core: enable support for the standard "wakeup-source" property") Cc: Fabio Estevam Cc: Shawn Guo Cc: NXP Linux Team Signed-off-by: Sudeep Holla Signed-off-by: Shawn Guo --- arch/arm/boot/dts/imx6q-pistachio.dts | 2 +- arch/arm/boot/dts/imx6sll-evk.dts | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/imx6q-pistachio.dts b/arch/arm/boot/dts/imx6q-pistachio.dts index 5edf858c8b86..a31b17eaf51c 100644 --- a/arch/arm/boot/dts/imx6q-pistachio.dts +++ b/arch/arm/boot/dts/imx6q-pistachio.dts @@ -103,7 +103,7 @@ power { label = "Power Button"; gpios = <&gpio2 12 GPIO_ACTIVE_LOW>; - gpio-key,wakeup; + wakeup-source; linux,code = ; }; }; diff --git a/arch/arm/boot/dts/imx6sll-evk.dts b/arch/arm/boot/dts/imx6sll-evk.dts index d8163705363e..4a31a415f88e 100644 --- a/arch/arm/boot/dts/imx6sll-evk.dts +++ b/arch/arm/boot/dts/imx6sll-evk.dts @@ -309,7 +309,7 @@ pinctrl-2 = <&pinctrl_usdhc3_200mhz>; cd-gpios = <&gpio3 22 GPIO_ACTIVE_LOW>; keep-power-in-suspend; - enable-sdio-wakeup; + wakeup-source; vmmc-supply = <®_sd3_vmmc>; status = "okay"; }; From 0808831dc62e90023ad14ff8da4804c7846e904b Mon Sep 17 00:00:00 2001 From: Matt Ranostay Date: Sun, 30 Dec 2018 19:07:01 -0800 Subject: [PATCH 026/525] iio: chemical: atlas-ph-sensor: correct IIO_TEMP values to millicelsius IIO_TEMP scale value for temperature was incorrect and not in millicelsius as required by the ABI documentation. Signed-off-by: Matt Ranostay Fixes: 27dec00ecf2d (iio: chemical: add Atlas pH-SM sensor support) Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/chemical/atlas-ph-sensor.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/iio/chemical/atlas-ph-sensor.c b/drivers/iio/chemical/atlas-ph-sensor.c index a406ad31b096..3a20cb5d9bff 100644 --- a/drivers/iio/chemical/atlas-ph-sensor.c +++ b/drivers/iio/chemical/atlas-ph-sensor.c @@ -444,9 +444,8 @@ static int atlas_read_raw(struct iio_dev *indio_dev, case IIO_CHAN_INFO_SCALE: switch (chan->type) { case IIO_TEMP: - *val = 1; /* 0.01 */ - *val2 = 100; - break; + *val = 10; + return IIO_VAL_INT; case IIO_PH: *val = 1; /* 0.001 */ *val2 = 1000; @@ -477,7 +476,7 @@ static int atlas_write_raw(struct iio_dev *indio_dev, int val, int val2, long mask) { struct atlas_data *data = iio_priv(indio_dev); - __be32 reg = cpu_to_be32(val); + __be32 reg = cpu_to_be32(val / 10); if (val2 != 0 || val < 0 || val > 20000) return -EINVAL; From 9bcf15f75cac3c6a00d8f8083a635de9c8537799 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 5 Jan 2019 19:36:18 +0100 Subject: [PATCH 027/525] iio: adc: axp288: Fix TS-pin handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Prior to this commit there were 3 issues with our handling of the TS-pin: 1) There are 2 ways how the firmware can disable monitoring of the TS-pin for designs which do not have a temperature-sensor for the battery: a) Clearing bit 0 of the AXP20X_ADC_EN1 register b) Setting bit 2 of the AXP288_ADC_TS_PIN_CTRL monitoring Prior to this commit we were unconditionally setting both bits to the value used on devices with a TS. This causes the temperature protection to kick in on devices without a TS, such as the Jumper ezbook v2, causing them to not charge under Linux. This commit fixes this by using regmap_update_bits when updating these 2 registers, leaving the 2 mentioned bits alone. The next 2 problems are related to our handling of the current-source for the TS-pin. The current-source used for the battery temp-sensor (TS) is shared with the GPADC. For proper fuel-gauge and charger operation the TS current-source needs to be permanently on. But to read the GPADC we need to temporary switch the TS current-source to ondemand, so that the GPADC can use it, otherwise we will always read an all 0 value. 2) Problem 2 is we were writing hardcoded values to the ADC TS pin-ctrl register, overwriting various other unrelated bits. Specifically we were overwriting the current-source setting for the TS and GPIO0 pins, forcing it to 80ųA independent of its original setting. On a Chuwi Vi10 tablet this was causing us to get a too high adc value (due to a too high current-source) resulting in the following errors being logged: ACPI Error: AE_ERROR, Returned by Handler for [UserDefinedRegion] ACPI Error: Method parse/execution failed \_SB.SXP1._TMP, AE_ERROR This commit fixes this by using regmap_update_bits to change only the relevant bits. 3) After reading the GPADC channel we were unconditionally enabling the TS current-source even on devices where the TS-pin is not used and the current-source thus was off before axp288_adc_read_raw call. This commit fixes this by making axp288_adc_set_ts a nop on devices where the ADC is not enabled for the TS-pin. BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=1610545 Fixes: 3091141d7803 ("iio: adc: axp288: Fix the GPADC pin ...") Signed-off-by: Hans de Goede Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/adc/axp288_adc.c | 76 ++++++++++++++++++++++++++++-------- 1 file changed, 60 insertions(+), 16 deletions(-) diff --git a/drivers/iio/adc/axp288_adc.c b/drivers/iio/adc/axp288_adc.c index 031d568b4972..4e339cfd0c54 100644 --- a/drivers/iio/adc/axp288_adc.c +++ b/drivers/iio/adc/axp288_adc.c @@ -27,9 +27,18 @@ #include #include -#define AXP288_ADC_EN_MASK 0xF1 -#define AXP288_ADC_TS_PIN_GPADC 0xF2 -#define AXP288_ADC_TS_PIN_ON 0xF3 +/* + * This mask enables all ADCs except for the battery temp-sensor (TS), that is + * left as-is to avoid breaking charging on devices without a temp-sensor. + */ +#define AXP288_ADC_EN_MASK 0xF0 +#define AXP288_ADC_TS_ENABLE 0x01 + +#define AXP288_ADC_TS_CURRENT_ON_OFF_MASK GENMASK(1, 0) +#define AXP288_ADC_TS_CURRENT_OFF (0 << 0) +#define AXP288_ADC_TS_CURRENT_ON_WHEN_CHARGING (1 << 0) +#define AXP288_ADC_TS_CURRENT_ON_ONDEMAND (2 << 0) +#define AXP288_ADC_TS_CURRENT_ON (3 << 0) enum axp288_adc_id { AXP288_ADC_TS, @@ -44,6 +53,7 @@ enum axp288_adc_id { struct axp288_adc_info { int irq; struct regmap *regmap; + bool ts_enabled; }; static const struct iio_chan_spec axp288_adc_channels[] = { @@ -115,21 +125,33 @@ static int axp288_adc_read_channel(int *val, unsigned long address, return IIO_VAL_INT; } -static int axp288_adc_set_ts(struct regmap *regmap, unsigned int mode, - unsigned long address) +/* + * The current-source used for the battery temp-sensor (TS) is shared + * with the GPADC. For proper fuel-gauge and charger operation the TS + * current-source needs to be permanently on. But to read the GPADC we + * need to temporary switch the TS current-source to ondemand, so that + * the GPADC can use it, otherwise we will always read an all 0 value. + */ +static int axp288_adc_set_ts(struct axp288_adc_info *info, + unsigned int mode, unsigned long address) { int ret; - /* channels other than GPADC do not need to switch TS pin */ + /* No need to switch the current-source if the TS pin is disabled */ + if (!info->ts_enabled) + return 0; + + /* Channels other than GPADC do not need the current source */ if (address != AXP288_GP_ADC_H) return 0; - ret = regmap_write(regmap, AXP288_ADC_TS_PIN_CTRL, mode); + ret = regmap_update_bits(info->regmap, AXP288_ADC_TS_PIN_CTRL, + AXP288_ADC_TS_CURRENT_ON_OFF_MASK, mode); if (ret) return ret; /* When switching to the GPADC pin give things some time to settle */ - if (mode == AXP288_ADC_TS_PIN_GPADC) + if (mode == AXP288_ADC_TS_CURRENT_ON_ONDEMAND) usleep_range(6000, 10000); return 0; @@ -145,14 +167,14 @@ static int axp288_adc_read_raw(struct iio_dev *indio_dev, mutex_lock(&indio_dev->mlock); switch (mask) { case IIO_CHAN_INFO_RAW: - if (axp288_adc_set_ts(info->regmap, AXP288_ADC_TS_PIN_GPADC, + if (axp288_adc_set_ts(info, AXP288_ADC_TS_CURRENT_ON_ONDEMAND, chan->address)) { dev_err(&indio_dev->dev, "GPADC mode\n"); ret = -EINVAL; break; } ret = axp288_adc_read_channel(val, chan->address, info->regmap); - if (axp288_adc_set_ts(info->regmap, AXP288_ADC_TS_PIN_ON, + if (axp288_adc_set_ts(info, AXP288_ADC_TS_CURRENT_ON, chan->address)) dev_err(&indio_dev->dev, "TS pin restore\n"); break; @@ -164,13 +186,35 @@ static int axp288_adc_read_raw(struct iio_dev *indio_dev, return ret; } -static int axp288_adc_set_state(struct regmap *regmap) +static int axp288_adc_initialize(struct axp288_adc_info *info) { - /* ADC should be always enabled for internal FG to function */ - if (regmap_write(regmap, AXP288_ADC_TS_PIN_CTRL, AXP288_ADC_TS_PIN_ON)) - return -EIO; + int ret, adc_enable_val; - return regmap_write(regmap, AXP20X_ADC_EN1, AXP288_ADC_EN_MASK); + /* + * Determine if the TS pin is enabled and set the TS current-source + * accordingly. + */ + ret = regmap_read(info->regmap, AXP20X_ADC_EN1, &adc_enable_val); + if (ret) + return ret; + + if (adc_enable_val & AXP288_ADC_TS_ENABLE) { + info->ts_enabled = true; + ret = regmap_update_bits(info->regmap, AXP288_ADC_TS_PIN_CTRL, + AXP288_ADC_TS_CURRENT_ON_OFF_MASK, + AXP288_ADC_TS_CURRENT_ON); + } else { + info->ts_enabled = false; + ret = regmap_update_bits(info->regmap, AXP288_ADC_TS_PIN_CTRL, + AXP288_ADC_TS_CURRENT_ON_OFF_MASK, + AXP288_ADC_TS_CURRENT_OFF); + } + if (ret) + return ret; + + /* Turn on the ADC for all channels except TS, leave TS as is */ + return regmap_update_bits(info->regmap, AXP20X_ADC_EN1, + AXP288_ADC_EN_MASK, AXP288_ADC_EN_MASK); } static const struct iio_info axp288_adc_iio_info = { @@ -200,7 +244,7 @@ static int axp288_adc_probe(struct platform_device *pdev) * Set ADC to enabled state at all time, including system suspend. * otherwise internal fuel gauge functionality may be affected. */ - ret = axp288_adc_set_state(axp20x->regmap); + ret = axp288_adc_initialize(info); if (ret) { dev_err(&pdev->dev, "unable to enable ADC device\n"); return ret; From ee17e5d6201c66492a0e8053190fca2ed2b8457d Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 12 Jan 2019 11:48:20 -0600 Subject: [PATCH 028/525] signal: Make siginmask safe when passed a signal of 0 Eric Biggers reported: > The following commit, which went into v4.20, introduced undefined behavior when > sys_rt_sigqueueinfo() is called with sig=0: > > commit 4ce5f9c9e7546915c559ffae594e6d73f918db00 > Author: Eric W. Biederman > Date: Tue Sep 25 12:59:31 2018 +0200 > > signal: Use a smaller struct siginfo in the kernel > > In sig_specific_sicodes(), used from known_siginfo_layout(), the expression > '1ULL << ((sig)-1)' is undefined as it evaluates to 1ULL << 4294967295. > > Reproducer: > > #include > #include > #include > > int main(void) > { > siginfo_t si = { .si_code = 1 }; > syscall(__NR_rt_sigqueueinfo, 0, 0, &si); > } > > UBSAN report for v5.0-rc1: > > UBSAN: Undefined behaviour in kernel/signal.c:2946:7 > shift exponent 4294967295 is too large for 64-bit type 'long unsigned int' > CPU: 2 PID: 346 Comm: syz_signal Not tainted 5.0.0-rc1 #25 > Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 > Call Trace: > __dump_stack lib/dump_stack.c:77 [inline] > dump_stack+0x70/0xa5 lib/dump_stack.c:113 > ubsan_epilogue+0xd/0x40 lib/ubsan.c:159 > __ubsan_handle_shift_out_of_bounds+0x12c/0x170 lib/ubsan.c:425 > known_siginfo_layout+0xae/0xe0 kernel/signal.c:2946 > post_copy_siginfo_from_user kernel/signal.c:3009 [inline] > __copy_siginfo_from_user+0x35/0x60 kernel/signal.c:3035 > __do_sys_rt_sigqueueinfo kernel/signal.c:3553 [inline] > __se_sys_rt_sigqueueinfo kernel/signal.c:3549 [inline] > __x64_sys_rt_sigqueueinfo+0x31/0x70 kernel/signal.c:3549 > do_syscall_64+0x4c/0x1b0 arch/x86/entry/common.c:290 > entry_SYSCALL_64_after_hwframe+0x49/0xbe > RIP: 0033:0x433639 > Code: c4 18 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b 27 00 00 c3 66 2e 0f 1f 84 00 00 00 00 > RSP: 002b:00007fffcb289fc8 EFLAGS: 00000246 ORIG_RAX: 0000000000000081 > RAX: ffffffffffffffda RBX: 00000000004002e0 RCX: 0000000000433639 > RDX: 00007fffcb289fd0 RSI: 0000000000000000 RDI: 0000000000000000 > RBP: 00000000006b2018 R08: 000000000000004d R09: 0000000000000000 > R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000401560 > R13: 00000000004015f0 R14: 0000000000000000 R15: 0000000000000000 I have looked at the other callers of siginmask and they all appear to in locations where sig can not be zero. I have looked at the code generation of adding an extra test against zero and gcc was able with a simple decrement instruction to combine the two tests together. So the at most adding this test cost a single cpu cycle. In practice that decrement instruction was already present as part of the mask comparison, so the only change was when the instruction was executed. So given that it is cheap, and obviously correct to update siginmask to verify the signal is not zero. Fix this issue there to avoid any future problems. Reported-by: Eric Biggers Fixes: 4ce5f9c9e754 ("signal: Use a smaller struct siginfo in the kernel") Signed-off-by: "Eric W. Biederman" --- include/linux/signal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/signal.h b/include/linux/signal.h index cc7e2c1cd444..9702016734b1 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -392,7 +392,7 @@ extern bool unhandled_signal(struct task_struct *tsk, int sig); #endif #define siginmask(sig, mask) \ - ((sig) < SIGRTMIN && (rt_sigmask(sig) & (mask))) + ((sig) > 0 && (sig) < SIGRTMIN && (rt_sigmask(sig) & (mask))) #define SIG_KERNEL_ONLY_MASK (\ rt_sigmask(SIGKILL) | rt_sigmask(SIGSTOP)) From b119d3bc328e7a9574861ebe0c2110e2776c2de1 Mon Sep 17 00:00:00 2001 From: Martin Kelly Date: Fri, 11 Jan 2019 23:13:09 +0000 Subject: [PATCH 029/525] tools: iio: iio_generic_buffer: make num_loops signed Currently, num_loops is unsigned, but it's set by strtoll, which returns a (signed) long long int. This could lead to overflow, and it also makes the check "num_loops < 0" always be false, since num_loops is unsigned. Setting num_loops to -1 to loop forever is almost working because num_loops is getting set to a very high number, but it's technically still incorrect. Fix this issue by making num_loops signed. This also fixes an error found by Smatch. Signed-off-by: Martin Kelly Reported-by: Dan Carpenter Fixes: 55dda0abcf9d ("tools: iio: iio_generic_buffer: allow continuous looping") Cc: Signed-off-by: Jonathan Cameron --- tools/iio/iio_generic_buffer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/iio/iio_generic_buffer.c b/tools/iio/iio_generic_buffer.c index 3040830d7797..84545666a09c 100644 --- a/tools/iio/iio_generic_buffer.c +++ b/tools/iio/iio_generic_buffer.c @@ -330,7 +330,7 @@ static const struct option longopts[] = { int main(int argc, char **argv) { - unsigned long long num_loops = 2; + long long num_loops = 2; unsigned long timedelay = 1000000; unsigned long buf_len = 128; From f214ff521fb1f861c8d7f7d0af98b06bf61b3369 Mon Sep 17 00:00:00 2001 From: Dan Murphy Date: Fri, 11 Jan 2019 13:57:07 -0600 Subject: [PATCH 030/525] iio: ti-ads8688: Update buffer allocation for timestamps Per Jonathan Cameron, the buffer needs to allocate room for a 64 bit timestamp as well as the channels. Change the buffer to allocate this additional space. Fixes: 2a86487786b5c ("iio: adc: ti-ads8688: add trigger and buffer support") Signed-off-by: Dan Murphy Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/adc/ti-ads8688.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/iio/adc/ti-ads8688.c b/drivers/iio/adc/ti-ads8688.c index 184d686ebd99..8b4568edd5cb 100644 --- a/drivers/iio/adc/ti-ads8688.c +++ b/drivers/iio/adc/ti-ads8688.c @@ -41,6 +41,7 @@ #define ADS8688_VREF_MV 4096 #define ADS8688_REALBITS 16 +#define ADS8688_MAX_CHANNELS 8 /* * enum ads8688_range - ADS8688 reference voltage range @@ -385,7 +386,7 @@ static irqreturn_t ads8688_trigger_handler(int irq, void *p) { struct iio_poll_func *pf = p; struct iio_dev *indio_dev = pf->indio_dev; - u16 buffer[8]; + u16 buffer[ADS8688_MAX_CHANNELS + sizeof(s64)/sizeof(u16)]; int i, j = 0; for (i = 0; i < indio_dev->masklength; i++) { From ba0f4560526ba19300c07ed5a3c1df7592815dc6 Mon Sep 17 00:00:00 2001 From: Anson Huang Date: Sat, 29 Dec 2018 10:01:18 +0000 Subject: [PATCH 031/525] ARM: dts: imx6sx: correct backward compatible of gpt i.MX6SX has same GPT type as i.MX6DL, in GPT driver, it uses below TIMER_OF_DECLARE, so the backward compatible should be "fsl,imx6dl-gpt", correct it. TIMER_OF_DECLARE(imx6sx_timer, "fsl,imx6sx-gpt", imx6dl_timer_init_dt); Signed-off-by: Anson Huang Signed-off-by: Shawn Guo --- arch/arm/boot/dts/imx6sx.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/imx6sx.dtsi b/arch/arm/boot/dts/imx6sx.dtsi index 272ff6133ec1..d1375d3650fd 100644 --- a/arch/arm/boot/dts/imx6sx.dtsi +++ b/arch/arm/boot/dts/imx6sx.dtsi @@ -467,7 +467,7 @@ }; gpt: gpt@2098000 { - compatible = "fsl,imx6sx-gpt", "fsl,imx31-gpt"; + compatible = "fsl,imx6sx-gpt", "fsl,imx6dl-gpt"; reg = <0x02098000 0x4000>; interrupts = ; clocks = <&clks IMX6SX_CLK_GPT_BUS>, From dc14455841773df52b15a17b36d01a26745f212b Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Sun, 13 Jan 2019 17:57:22 +0800 Subject: [PATCH 032/525] pinctrl: sunxi: Fix and simplify pin bank regulator handling The new per-pin-bank regulator handling code in the sunxi pinctrl driver has mismatched conditions for enabling and disabling the regulator: it is enabled each time a pin is requested, but only disabled when the pin-bank's reference count reaches zero. Since we are doing reference counting already, there's no need to enable the regulator each time a pin is requested. Instead we can just do it for the first requested pin of each pin-bank. Thus we can reverse the test and bail out early if it's not the first occurrence. Fixes: 9a2a566adb00 ("pinctrl: sunxi: Deal with per-bank regulators") Acked-by: Maxime Ripard Signed-off-by: Chen-Yu Tsai Signed-off-by: Linus Walleij --- drivers/pinctrl/sunxi/pinctrl-sunxi.c | 36 ++++++++++++--------------- 1 file changed, 16 insertions(+), 20 deletions(-) diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c index 5d9184d18c16..9ad6e9c2adab 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c +++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c @@ -699,25 +699,21 @@ static int sunxi_pmx_request(struct pinctrl_dev *pctldev, unsigned offset) struct sunxi_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev); unsigned short bank = offset / PINS_PER_BANK; struct sunxi_pinctrl_regulator *s_reg = &pctl->regulators[bank]; - struct regulator *reg; + struct regulator *reg = s_reg->regulator; + char supply[16]; int ret; - reg = s_reg->regulator; - if (!reg) { - char supply[16]; - - snprintf(supply, sizeof(supply), "vcc-p%c", 'a' + bank); - reg = regulator_get(pctl->dev, supply); - if (IS_ERR(reg)) { - dev_err(pctl->dev, "Couldn't get bank P%c regulator\n", - 'A' + bank); - return PTR_ERR(reg); - } - - s_reg->regulator = reg; - refcount_set(&s_reg->refcount, 1); - } else { + if (reg) { refcount_inc(&s_reg->refcount); + return 0; + } + + snprintf(supply, sizeof(supply), "vcc-p%c", 'a' + bank); + reg = regulator_get(pctl->dev, supply); + if (IS_ERR(reg)) { + dev_err(pctl->dev, "Couldn't get bank P%c regulator\n", + 'A' + bank); + return PTR_ERR(reg); } ret = regulator_enable(reg); @@ -727,13 +723,13 @@ static int sunxi_pmx_request(struct pinctrl_dev *pctldev, unsigned offset) goto out; } + s_reg->regulator = reg; + refcount_set(&s_reg->refcount, 1); + return 0; out: - if (refcount_dec_and_test(&s_reg->refcount)) { - regulator_put(s_reg->regulator); - s_reg->regulator = NULL; - } + regulator_put(s_reg->regulator); return ret; } From ca4438442ef263cbaa3ae62a712143132cf508c1 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Sun, 13 Jan 2019 17:57:23 +0800 Subject: [PATCH 033/525] pinctrl: sunxi: Consider pin_base when calculating regulator array index On most newer Allwinner SoCs, there are two pinctrl devices, the PIO and R_PIO. PIO covers pin-banks PA to PI (PJ and PK have not been seen), while R_PIO covers PL to PN. The regulator array only has space for 12 entries, which was designed to cover PA to PL. On the A80, the pin banks go up to PN, which would be the 14th entry in the regulator array. However since the driver only needs to track regulators for its own pin banks, the array only needs to have 9 entries, and also take in to account the value of pin_base, such that the regulator for the first pin-bank of the pinctrl device, be it "PA" or "PL" uses the first entry of the array. Base the regulator array index on pin_base, such that "PA" for PIO and "PL" for R_PIO both take the first element within their respective device's regulator array. Also decrease the size of the regulator array to 9, just enough to cover "PA" to "PI". Fixes: 9a2a566adb00 ("pinctrl: sunxi: Deal with per-bank regulators") Signed-off-by: Chen-Yu Tsai Signed-off-by: Linus Walleij --- drivers/pinctrl/sunxi/pinctrl-sunxi.c | 8 ++++++-- drivers/pinctrl/sunxi/pinctrl-sunxi.h | 2 +- 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c index 9ad6e9c2adab..0e7fa69e93df 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c +++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c @@ -698,7 +698,9 @@ static int sunxi_pmx_request(struct pinctrl_dev *pctldev, unsigned offset) { struct sunxi_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev); unsigned short bank = offset / PINS_PER_BANK; - struct sunxi_pinctrl_regulator *s_reg = &pctl->regulators[bank]; + unsigned short bank_offset = bank - pctl->desc->pin_base / + PINS_PER_BANK; + struct sunxi_pinctrl_regulator *s_reg = &pctl->regulators[bank_offset]; struct regulator *reg = s_reg->regulator; char supply[16]; int ret; @@ -738,7 +740,9 @@ static int sunxi_pmx_free(struct pinctrl_dev *pctldev, unsigned offset) { struct sunxi_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev); unsigned short bank = offset / PINS_PER_BANK; - struct sunxi_pinctrl_regulator *s_reg = &pctl->regulators[bank]; + unsigned short bank_offset = bank - pctl->desc->pin_base / + PINS_PER_BANK; + struct sunxi_pinctrl_regulator *s_reg = &pctl->regulators[bank_offset]; if (!refcount_dec_and_test(&s_reg->refcount)) return 0; diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.h b/drivers/pinctrl/sunxi/pinctrl-sunxi.h index e340d2a24b44..034c0317c8d6 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sunxi.h +++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.h @@ -136,7 +136,7 @@ struct sunxi_pinctrl { struct gpio_chip *chip; const struct sunxi_pinctrl_desc *desc; struct device *dev; - struct sunxi_pinctrl_regulator regulators[12]; + struct sunxi_pinctrl_regulator regulators[9]; struct irq_domain *domain; struct sunxi_pinctrl_function *functions; unsigned nfunctions; From f29200c8b1e267b109242677ae7f2146c7682d14 Mon Sep 17 00:00:00 2001 From: Loys Ollivier Date: Mon, 14 Jan 2019 15:44:21 +0100 Subject: [PATCH 034/525] arm64: dts: meson: Fix mmc cd-gpios polarity Commit 89a5e15bcba8 ("gpio/mmc/of: Respect polarity in the device tree") changed the behavior of "cd-inverted" to follow the device tree bindings specification: According to SDHCI standard, CD lines are specified as "active low". Using the "cd-inverted" property means that the CD line is "active high". Fix the SD card description for meson by setting the cd-gpios as "active low", according to the boards specifications, and dropping the "cd-inverted" property. Fixes: 89a5e15bcba8 ("gpio/mmc/of: Respect polarity in the device tree") Signed-off-by: Loys Ollivier Signed-off-by: Kevin Hilman --- arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi | 3 +-- arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts | 3 +-- arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts | 3 +-- arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts | 3 +-- arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi | 3 +-- arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi | 3 +-- arch/arm64/boot/dts/amlogic/meson-gxbb-wetek.dtsi | 3 +-- arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts | 3 +-- arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts | 3 +-- arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts | 3 +-- arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi | 3 +-- arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts | 3 +-- arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts | 3 +-- arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts | 3 +-- 14 files changed, 14 insertions(+), 28 deletions(-) diff --git a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi index e14e0ce7e89f..016641a41694 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi @@ -187,8 +187,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_boot>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts index 8cd50b75171d..ade2ee09ae96 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts @@ -305,8 +305,7 @@ max-frequency = <200000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddio_ao3v3>; vqmmc-supply = <&vddio_tf>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts index 4cf7f6e80c6a..25105ac96d55 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts @@ -238,8 +238,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_card>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts index 2e1cd5e3a246..1cc9dc68ef00 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts @@ -258,8 +258,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&tflash_vdd>; vqmmc-supply = <&tf_io>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi index ce862266b9aa..0be0f2a5d2fe 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi @@ -196,8 +196,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_card>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi index 93a4acf2c46c..ad4d50bd9d77 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi @@ -154,8 +154,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vcc_3v3>; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek.dtsi index ec09bb5792b7..2d2db783c44c 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek.dtsi @@ -211,8 +211,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vcc_3v3>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts index f1c410e2da2b..796baea7a0bf 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts @@ -131,8 +131,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_card>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts index db293440e4ca..255cede7b447 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts @@ -238,8 +238,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vcc_3v3>; vqmmc-supply = <&vcc_card>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts index 6739697be1de..9cbdb85fb591 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts @@ -183,8 +183,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_card>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi index a1b31013ab6e..bc811a2faf42 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi @@ -137,8 +137,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_boot>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts index 3c3a667a8df8..3f086ed7de05 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts @@ -356,8 +356,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_boot>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts index f7a1cffab4a8..8acfd40090d2 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts @@ -147,8 +147,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_boot>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts index 7212dc4531e4..7fa20a8ede17 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts @@ -170,8 +170,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_boot>; From 97e1532ef81acb31c30f9e75bf00306c33a77812 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 16 Jan 2019 10:27:59 +0100 Subject: [PATCH 035/525] fuse: handle zero sized retrieve correctly Dereferencing req->page_descs[0] will Oops if req->max_pages is zero. Reported-by: syzbot+c1e36d30ee3416289cc0@syzkaller.appspotmail.com Tested-by: syzbot+c1e36d30ee3416289cc0@syzkaller.appspotmail.com Fixes: b2430d7567a3 ("fuse: add per-page descriptor to fuse_req") Cc: # v3.9 Signed-off-by: Miklos Szeredi --- fs/fuse/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index a5e516a40e7a..fc29264011a6 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -1742,7 +1742,6 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, req->in.h.nodeid = outarg->nodeid; req->in.numargs = 2; req->in.argpages = 1; - req->page_descs[0].offset = offset; req->end = fuse_retrieve_end; index = outarg->offset >> PAGE_SHIFT; @@ -1757,6 +1756,7 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, this_num = min_t(unsigned, num, PAGE_SIZE - offset); req->pages[req->num_pages] = page; + req->page_descs[req->num_pages].offset = offset; req->page_descs[req->num_pages].length = this_num; req->num_pages++; From 8a3177db59cd644fde05ba9efee29392dfdec8aa Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 16 Jan 2019 10:27:59 +0100 Subject: [PATCH 036/525] cuse: fix ioctl cuse_process_init_reply() doesn't initialize fc->max_pages and thus all cuse bases ioctls fail with ENOMEM. Reported-by: Andreas Steinmetz Fixes: 5da784cce430 ("fuse: add max_pages to init_out") Cc: # v4.20 Signed-off-by: Miklos Szeredi --- fs/fuse/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 76baaa6be393..c2d4099429be 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -628,6 +628,7 @@ void fuse_conn_init(struct fuse_conn *fc, struct user_namespace *user_ns) get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key)); fc->pid_ns = get_pid_ns(task_active_pid_ns(current)); fc->user_ns = get_user_ns(user_ns); + fc->max_pages = FUSE_DEFAULT_MAX_PAGES_PER_REQ; } EXPORT_SYMBOL_GPL(fuse_conn_init); @@ -1162,7 +1163,6 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) fc->user_id = d.user_id; fc->group_id = d.group_id; fc->max_read = max_t(unsigned, 4096, d.max_read); - fc->max_pages = FUSE_DEFAULT_MAX_PAGES_PER_REQ; /* Used by get_root_inode() */ sb->s_fs_info = fc; From 9509941e9c534920ccc4771ae70bd6cbbe79df1c Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Sat, 12 Jan 2019 02:39:05 +0100 Subject: [PATCH 037/525] fuse: call pipe_buf_release() under pipe lock Some of the pipe_buf_release() handlers seem to assume that the pipe is locked - in particular, anon_pipe_buf_release() accesses pipe->tmp_page without taking any extra locks. From a glance through the callers of pipe_buf_release(), it looks like FUSE is the only one that calls pipe_buf_release() without having the pipe locked. This bug should only lead to a memory leak, nothing terrible. Fixes: dd3bb14f44a6 ("fuse: support splice() writing to fuse device") Cc: stable@vger.kernel.org Signed-off-by: Jann Horn Signed-off-by: Miklos Szeredi --- fs/fuse/dev.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index fc29264011a6..809c0f2f9942 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -2077,8 +2077,10 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, ret = fuse_dev_do_write(fud, &cs, len); + pipe_lock(pipe); for (idx = 0; idx < nbuf; idx++) pipe_buf_release(pipe, &bufs[idx]); + pipe_unlock(pipe); out: kvfree(bufs); From a2ebba824106dabe79937a9f29a875f837e1b6d4 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 16 Jan 2019 10:27:59 +0100 Subject: [PATCH 038/525] fuse: decrement NR_WRITEBACK_TEMP on the right page NR_WRITEBACK_TEMP is accounted on the temporary page in the request, not the page cache page. Fixes: 8b284dc47291 ("fuse: writepages: handle same page rewrites") Cc: # v3.13 Signed-off-by: Miklos Szeredi --- fs/fuse/file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index ffaffe18352a..a59c16bd90ac 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1782,7 +1782,7 @@ static bool fuse_writepage_in_flight(struct fuse_req *new_req, spin_unlock(&fc->lock); dec_wb_stat(&bdi->wb, WB_WRITEBACK); - dec_node_page_state(page, NR_WRITEBACK_TEMP); + dec_node_page_state(new_req->pages[0], NR_WRITEBACK_TEMP); wb_writeout_inc(&bdi->wb); fuse_writepage_free(fc, new_req); fuse_request_free(new_req); From e2612cd496e7b465711d219ea6118893d7253f52 Mon Sep 17 00:00:00 2001 From: Benedict Wong Date: Mon, 14 Jan 2019 11:24:38 -0800 Subject: [PATCH 039/525] xfrm: Make set-mark default behavior backward compatible MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes 9b42c1f179a6, which changed the default route lookup behavior for tunnel mode SAs in the outbound direction to use the skb mark, whereas previously mark=0 was used if the output mark was unspecified. In mark-based routing schemes such as Android’s, this change in default behavior causes routing loops or lookup failures. This patch restores the default behavior of using a 0 mark while still incorporating the skb mark if the SET_MARK (and SET_MARK_MASK) is specified. Tested with additions to Android's kernel unit test suite: https://android-review.googlesource.com/c/kernel/tests/+/860150 Fixes: 9b42c1f179a6 ("xfrm: Extend the output_mark to support input direction and masking") Signed-off-by: Benedict Wong Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 8cfd75b62396..ba0a4048c846 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2600,7 +2600,10 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, dst_copy_metrics(dst1, dst); if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) { - __u32 mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]); + __u32 mark = 0; + + if (xfrm[i]->props.smark.v || xfrm[i]->props.smark.m) + mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]); family = xfrm[i]->props.family; dst = xfrm_dst_lookup(xfrm[i], tos, fl->flowi_oif, From c5b11ee9f1c22a8d6b5cab2099904f7adbe79a7f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Guido=20G=C3=BCnther?= Date: Wed, 16 Jan 2019 09:41:22 +0100 Subject: [PATCH 040/525] dt-bindings: imx8mq: Number clocks consecutively MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This fixes a duplicate use of 232 and numbers the clocks without holes. Fixes: 1cf3817bf1f5 ("dt-bindings: Add binding for i.MX8MQ CCM") Signed-off-by: Guido Günther Reviewed-by: Lucas Stach Signed-off-by: Shawn Guo --- include/dt-bindings/clock/imx8mq-clock.h | 26 ++++++++++++------------ 1 file changed, 13 insertions(+), 13 deletions(-) diff --git a/include/dt-bindings/clock/imx8mq-clock.h b/include/dt-bindings/clock/imx8mq-clock.h index b53be41929be..04f7ac345984 100644 --- a/include/dt-bindings/clock/imx8mq-clock.h +++ b/include/dt-bindings/clock/imx8mq-clock.h @@ -350,7 +350,7 @@ #define IMX8MQ_CLK_VPU_G2_ROOT 241 /* SCCG PLL GATE */ -#define IMX8MQ_SYS1_PLL_OUT 232 +#define IMX8MQ_SYS1_PLL_OUT 242 #define IMX8MQ_SYS2_PLL_OUT 243 #define IMX8MQ_SYS3_PLL_OUT 244 #define IMX8MQ_DRAM_PLL_OUT 245 @@ -372,24 +372,24 @@ /* txesc clock */ #define IMX8MQ_CLK_DSI_IPG_DIV 256 -#define IMX8MQ_CLK_TMU_ROOT 265 +#define IMX8MQ_CLK_TMU_ROOT 257 /* Display root clocks */ -#define IMX8MQ_CLK_DISP_AXI_ROOT 266 -#define IMX8MQ_CLK_DISP_APB_ROOT 267 -#define IMX8MQ_CLK_DISP_RTRM_ROOT 268 +#define IMX8MQ_CLK_DISP_AXI_ROOT 258 +#define IMX8MQ_CLK_DISP_APB_ROOT 259 +#define IMX8MQ_CLK_DISP_RTRM_ROOT 260 -#define IMX8MQ_CLK_OCOTP_ROOT 269 +#define IMX8MQ_CLK_OCOTP_ROOT 261 -#define IMX8MQ_CLK_DRAM_ALT_ROOT 270 -#define IMX8MQ_CLK_DRAM_CORE 271 +#define IMX8MQ_CLK_DRAM_ALT_ROOT 262 +#define IMX8MQ_CLK_DRAM_CORE 263 -#define IMX8MQ_CLK_MU_ROOT 272 -#define IMX8MQ_VIDEO2_PLL_OUT 273 +#define IMX8MQ_CLK_MU_ROOT 264 +#define IMX8MQ_VIDEO2_PLL_OUT 265 -#define IMX8MQ_CLK_CLKO2 274 +#define IMX8MQ_CLK_CLKO2 266 -#define IMX8MQ_CLK_NAND_USDHC_BUS_RAWNAND_CLK 275 +#define IMX8MQ_CLK_NAND_USDHC_BUS_RAWNAND_CLK 267 -#define IMX8MQ_CLK_END 276 +#define IMX8MQ_CLK_END 268 #endif /* __DT_BINDINGS_CLOCK_IMX8MQ_H */ From ec5aecc0b227f5509d25853537f989ca303e2be1 Mon Sep 17 00:00:00 2001 From: Luca Coelho Date: Mon, 14 Jan 2019 13:00:23 +0200 Subject: [PATCH 041/525] iwlwifi: make IWLWIFI depend on CFG80211 Since IWLWIFI doesn't depend on MAC80211 anymore, it needs to depend on CFG80211, because it uses a few symbols from it. Add the dependency on CFG80211 accordingly. Additionally, make IWLWIFI_LEDS depend on IWLMVM or IWLDVM, since it doesn't need mac80211 but must be used for these. Fixes: aca432f06b8a ("iwlwifi: make MVM and DVM depend on MAC80211") Signed-off-by: Luca Coelho Signed-off-by: Kalle Valo --- drivers/net/wireless/intel/iwlwifi/Kconfig | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/Kconfig b/drivers/net/wireless/intel/iwlwifi/Kconfig index 491ca3c8b43c..83d5bceea08f 100644 --- a/drivers/net/wireless/intel/iwlwifi/Kconfig +++ b/drivers/net/wireless/intel/iwlwifi/Kconfig @@ -1,6 +1,6 @@ config IWLWIFI tristate "Intel Wireless WiFi Next Gen AGN - Wireless-N/Advanced-N/Ultimate-N (iwlwifi) " - depends on PCI && HAS_IOMEM + depends on PCI && HAS_IOMEM && CFG80211 select FW_LOADER ---help--- Select to build the driver supporting the: @@ -47,6 +47,7 @@ if IWLWIFI config IWLWIFI_LEDS bool depends on LEDS_CLASS=y || LEDS_CLASS=IWLWIFI + depends on IWLMVM || IWLDVM select LEDS_TRIGGERS select MAC80211_LEDS default y From e3966a766865da7ced1dece663697861dd5cf103 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 11 Jan 2019 18:21:18 +0100 Subject: [PATCH 042/525] ARM: dts: da850: fix interrupt numbers for clocksource The timer interrupts specified in commit 3652e2741f42 ("ARM: dts: da850: Add clocks") are wrong but since the current timer code hard-codes them, the bug was never spotted. This patch must go into stable since, once we introduce a proper clocksource driver, devices with buggy device tree will stop booting. Fixes: 3652e2741f42 ("ARM: dts: da850: Add clocks") Cc: stable@vger.kernel.org Signed-off-by: Bartosz Golaszewski Signed-off-by: Sekhar Nori --- arch/arm/boot/dts/da850.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/da850.dtsi b/arch/arm/boot/dts/da850.dtsi index 47aa53ba6b92..559659b399d0 100644 --- a/arch/arm/boot/dts/da850.dtsi +++ b/arch/arm/boot/dts/da850.dtsi @@ -476,7 +476,7 @@ clocksource: timer@20000 { compatible = "ti,da830-timer"; reg = <0x20000 0x1000>; - interrupts = <12>, <13>; + interrupts = <21>, <22>; interrupt-names = "tint12", "tint34"; clocks = <&pll0_auxclk>; }; From 2bb7b675248c3ad11ada0ce3d0f6d480ec8cc87b Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 10 Jan 2019 14:39:13 +0100 Subject: [PATCH 043/525] arm64: dts: renesas: r8a774a1: Enable DMA for SCIF2 SCIF2 on RZ/G2M can be used with both DMAC1 and DMAC2. Fixes: 3a3933a4fa36430a ("arm64: dts: renesas: r8a774a1: Add SCIF and HSCIF nodes") Signed-off-by: Geert Uytterhoeven Signed-off-by: Simon Horman --- arch/arm64/boot/dts/renesas/r8a774a1.dtsi | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm64/boot/dts/renesas/r8a774a1.dtsi b/arch/arm64/boot/dts/renesas/r8a774a1.dtsi index 20745a8528c5..719ed9d9067d 100644 --- a/arch/arm64/boot/dts/renesas/r8a774a1.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a774a1.dtsi @@ -1011,6 +1011,9 @@ <&cpg CPG_CORE R8A774A1_CLK_S3D1>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; + dmas = <&dmac1 0x13>, <&dmac1 0x12>, + <&dmac2 0x13>, <&dmac2 0x12>; + dma-names = "tx", "rx", "tx", "rx"; power-domains = <&sysc R8A774A1_PD_ALWAYS_ON>; resets = <&cpg 310>; status = "disabled"; From 97f26702bc95b5c3a72671d5c6675e4d6ee0a2f4 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 10 Jan 2019 14:39:15 +0100 Subject: [PATCH 044/525] arm64: dts: renesas: r8a7796: Enable DMA for SCIF2 SCIF2 on R-Car M3-W can be used with both DMAC1 and DMAC2. Fixes: dbcae5ea4bd27409 ("arm64: dts: r8a7796: Enable SCIF DMA") Signed-off-by: Geert Uytterhoeven Signed-off-by: Simon Horman --- arch/arm64/boot/dts/renesas/r8a7796.dtsi | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm64/boot/dts/renesas/r8a7796.dtsi b/arch/arm64/boot/dts/renesas/r8a7796.dtsi index afedbf5728ec..0648d12778ed 100644 --- a/arch/arm64/boot/dts/renesas/r8a7796.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a7796.dtsi @@ -1262,6 +1262,9 @@ <&cpg CPG_CORE R8A7796_CLK_S3D1>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; + dmas = <&dmac1 0x13>, <&dmac1 0x12>, + <&dmac2 0x13>, <&dmac2 0x12>; + dma-names = "tx", "rx", "tx", "rx"; power-domains = <&sysc R8A7796_PD_ALWAYS_ON>; resets = <&cpg 310>; status = "disabled"; From 05c8478abd485507c25aa565afab604af8d8fe46 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 10 Jan 2019 14:39:16 +0100 Subject: [PATCH 045/525] arm64: dts: renesas: r8a77965: Enable DMA for SCIF2 SCIF2 on R-Car M3-N can be used with both DMAC1 and DMAC2. Fixes: 0ea5b2fd38db56aa ("arm64: dts: renesas: r8a77965: Add SCIF device nodes") Signed-off-by: Geert Uytterhoeven Signed-off-by: Simon Horman --- arch/arm64/boot/dts/renesas/r8a77965.dtsi | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm64/boot/dts/renesas/r8a77965.dtsi b/arch/arm64/boot/dts/renesas/r8a77965.dtsi index 6dc9b1fef830..4b3730f640ef 100644 --- a/arch/arm64/boot/dts/renesas/r8a77965.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a77965.dtsi @@ -1068,6 +1068,9 @@ <&cpg CPG_CORE R8A77965_CLK_S3D1>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; + dmas = <&dmac1 0x13>, <&dmac1 0x12>, + <&dmac2 0x13>, <&dmac2 0x12>; + dma-names = "tx", "rx", "tx", "rx"; power-domains = <&sysc R8A77965_PD_ALWAYS_ON>; resets = <&cpg 310>; status = "disabled"; From 99d86c8b88393e29cf07c020585f2c8afbcdd97d Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 17 Jan 2019 12:30:17 +0100 Subject: [PATCH 046/525] perf ordered_events: Fix crash in ordered_events__free Song Liu reported crash in 'perf record': > #0 0x0000000000500055 in ordered_events(float, long double,...)(...) () > #1 0x0000000000500196 in ordered_events.reinit () > #2 0x00000000004fe413 in perf_session.process_events () > #3 0x0000000000440431 in cmd_record () > #4 0x00000000004a439f in run_builtin () > #5 0x000000000042b3e5 in main ()" This can happen when we get out of buffers during event processing. The subsequent ordered_events__free() call assumes oe->buffer != NULL and crashes. Add a check to prevent that. Reported-by: Song Liu Signed-off-by: Jiri Olsa Reviewed-by: Song Liu Tested-by: Song Liu Cc: Alexander Shishkin Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/20190117113017.12977-1-jolsa@kernel.org Fixes: d5ceb62b3654 ("perf ordered_events: Add 'struct ordered_events_buffer' layer") Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/ordered-events.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c index 897589507d97..ea523d3b248f 100644 --- a/tools/perf/util/ordered-events.c +++ b/tools/perf/util/ordered-events.c @@ -391,8 +391,10 @@ void ordered_events__free(struct ordered_events *oe) * Current buffer might not have all the events allocated * yet, we need to free only allocated ones ... */ - list_del(&oe->buffer->list); - ordered_events_buffer__free(oe->buffer, oe->buffer_idx, oe); + if (oe->buffer) { + list_del(&oe->buffer->list); + ordered_events_buffer__free(oe->buffer, oe->buffer_idx, oe); + } /* ... and continue with the rest */ list_for_each_entry_safe(buffer, tmp, &oe->to_free, list) { From ea6eb5e7d15e1838de335609994b4546e2abcaaf Mon Sep 17 00:00:00 2001 From: Andreas Ziegler Date: Thu, 17 Jan 2019 14:30:23 +0100 Subject: [PATCH 047/525] tracing: uprobes: Fix typo in pr_fmt string The subsystem-specific message prefix for uprobes was also "trace_kprobe: " instead of "trace_uprobe: " as described in the original commit message. Link: http://lkml.kernel.org/r/20190117133023.19292-1-andreas.ziegler@fau.de Cc: Ingo Molnar Cc: stable@vger.kernel.org Acked-by: Masami Hiramatsu Fixes: 7257634135c24 ("tracing/probe: Show subsystem name in messages") Signed-off-by: Andreas Ziegler Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_uprobe.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index e335576b9411..19a1a8e19062 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -5,7 +5,7 @@ * Copyright (C) IBM Corporation, 2010-2012 * Author: Srikar Dronamraju */ -#define pr_fmt(fmt) "trace_kprobe: " fmt +#define pr_fmt(fmt) "trace_uprobe: " fmt #include #include From 0722069a5374b904ec1a67f91249f90e1cfae259 Mon Sep 17 00:00:00 2001 From: Andreas Ziegler Date: Wed, 16 Jan 2019 15:16:29 +0100 Subject: [PATCH 048/525] tracing/uprobes: Fix output for multiple string arguments When printing multiple uprobe arguments as strings the output for the earlier arguments would also include all later string arguments. This is best explained in an example: Consider adding a uprobe to a function receiving two strings as parameters which is at offset 0xa0 in strlib.so and we want to print both parameters when the uprobe is hit (on x86_64): $ echo 'p:func /lib/strlib.so:0xa0 +0(%di):string +0(%si):string' > \ /sys/kernel/debug/tracing/uprobe_events When the function is called as func("foo", "bar") and we hit the probe, the trace file shows a line like the following: [...] func: (0x7f7e683706a0) arg1="foobar" arg2="bar" Note the extra "bar" printed as part of arg1. This behaviour stacks up for additional string arguments. The strings are stored in a dynamically growing part of the uprobe buffer by fetch_store_string() after copying them from userspace via strncpy_from_user(). The return value of strncpy_from_user() is then directly used as the required size for the string. However, this does not take the terminating null byte into account as the documentation for strncpy_from_user() cleary states that it "[...] returns the length of the string (not including the trailing NUL)" even though the null byte will be copied to the destination. Therefore, subsequent calls to fetch_store_string() will overwrite the terminating null byte of the most recently fetched string with the first character of the current string, leading to the "accumulation" of strings in earlier arguments in the output. Fix this by incrementing the return value of strncpy_from_user() by one if we did not hit the maximum buffer size. Link: http://lkml.kernel.org/r/20190116141629.5752-1-andreas.ziegler@fau.de Cc: Ingo Molnar Cc: stable@vger.kernel.org Fixes: 5baaa59ef09e ("tracing/probes: Implement 'memory' fetch method for uprobes") Acked-by: Masami Hiramatsu Signed-off-by: Andreas Ziegler Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_uprobe.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 19a1a8e19062..9bde07c06362 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -160,6 +160,13 @@ fetch_store_string(unsigned long addr, void *dest, void *base) if (ret >= 0) { if (ret == maxlen) dst[ret - 1] = '\0'; + else + /* + * Include the terminating null byte. In this case it + * was copied by strncpy_from_user but not accounted + * for in ret. + */ + ret++; *(u32 *)dest = make_data_loc(ret, (void *)dst - base); } From 12c44aba6618b7f6c437076e5722237190f6cd5f Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 14 Jan 2019 14:28:48 +0100 Subject: [PATCH 049/525] netfilter: nft_compat: use refcnt_t type for nft_xt reference count Using standard integer type was fine while all operations on it were guarded by the nftnl subsys mutex. This isn't true anymore: 1. transactions are guarded only by a pernet mutex, so concurrent rule manipulation in different netns is racy 2. the ->destroy hook runs from a work queue after the transaction mutex has been released already. cpu0 cpu1 (net 1) cpu2 (net 2) kworker nft_compat->destroy nft_compat->init nft_compat->init if (--nft_xt->ref == 0) nft_xt->ref++ nft_xt->ref++ Switch to refcount_t. Doing this however only fixes a minor aspect, nft_compat also performs linked-list operations in an unsafe way. This is addressed in the next two patches. Fixes: f102d66b335a ("netfilter: nf_tables: use dedicated mutex to guard transactions") Fixes: 0935d5588400 ("netfilter: nf_tables: asynchronous release") Reported-by: Taehee Yoo Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_compat.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 7334e0b80a5e..acc85acad31b 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -26,7 +26,7 @@ struct nft_xt { struct list_head head; struct nft_expr_ops ops; - unsigned int refcnt; + refcount_t refcnt; /* Unlike other expressions, ops doesn't have static storage duration. * nft core assumes they do. We use kfree_rcu so that nft core can @@ -45,7 +45,7 @@ struct nft_xt_match_priv { static bool nft_xt_put(struct nft_xt *xt) { - if (--xt->refcnt == 0) { + if (refcount_dec_and_test(&xt->refcnt)) { list_del(&xt->head); kfree_rcu(xt, rcu_head); return true; @@ -273,7 +273,7 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return -EINVAL; nft_xt = container_of(expr->ops, struct nft_xt, ops); - nft_xt->refcnt++; + refcount_inc(&nft_xt->refcnt); return 0; } @@ -486,7 +486,7 @@ __nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return ret; nft_xt = container_of(expr->ops, struct nft_xt, ops); - nft_xt->refcnt++; + refcount_inc(&nft_xt->refcnt); return 0; } @@ -789,7 +789,7 @@ nft_match_select_ops(const struct nft_ctx *ctx, goto err; } - nft_match->refcnt = 0; + refcount_set(&nft_match->refcnt, 0); nft_match->ops.type = &nft_match_type; nft_match->ops.eval = nft_match_eval; nft_match->ops.init = nft_match_init; @@ -893,7 +893,7 @@ nft_target_select_ops(const struct nft_ctx *ctx, goto err; } - nft_target->refcnt = 0; + refcount_set(&nft_target->refcnt, 0); nft_target->ops.type = &nft_target_type; nft_target->ops.size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize)); nft_target->ops.init = nft_target_init; @@ -964,7 +964,7 @@ static void __exit nft_compat_module_exit(void) list_for_each_entry_safe(xt, next, &nft_target_list, head) { struct xt_target *target = xt->ops.data; - if (WARN_ON_ONCE(xt->refcnt)) + if (WARN_ON_ONCE(refcount_read(&xt->refcnt))) continue; module_put(target->me); kfree(xt); @@ -973,7 +973,7 @@ static void __exit nft_compat_module_exit(void) list_for_each_entry_safe(xt, next, &nft_match_list, head) { struct xt_match *match = xt->ops.data; - if (WARN_ON_ONCE(xt->refcnt)) + if (WARN_ON_ONCE(refcount_read(&xt->refcnt))) continue; module_put(match->me); kfree(xt); From cf52572ebbd7189a1966c2b5fc34b97078cd1dce Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 14 Jan 2019 14:28:49 +0100 Subject: [PATCH 050/525] netfilter: nft_compat: make lists per netns There are two problems with nft_compat since the netlink config plane uses a per-netns mutex: 1. Concurrent add/del accesses to the same list 2. accesses to a list element after it has been free'd already. This patch fixes the first problem. Freeing occurs from a work queue, after transaction mutexes have been released, i.e., it still possible for a new transaction (even from same net ns) to find the to-be-deleted expression in the list. The ->destroy functions are not allowed to have any such side effects, i.e. the list_del() in the destroy function is not allowed. This part of the problem is solved in the next patch. I tried to make this work by serializing list access via mutex and by moving list_del() to a deactivate callback, but Taehee spotted following race on this approach: NET #0 NET #1 >select_ops() ->init() ->select_ops() ->deactivate() ->destroy() nft_xt_put() kfree_rcu(xt, rcu_head); ->init() <-- use-after-free occurred. Unfortunately, we can't increment reference count in select_ops(), because we can't undo the refcount increase in case a different expression fails in the same batch. (The destroy hook will only be called in case the expression was initialized successfully). Fixes: f102d66b335a ("netfilter: nf_tables: use dedicated mutex to guard transactions") Reported-by: Taehee Yoo Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_compat.c | 129 +++++++++++++++++++++++++------------ 1 file changed, 89 insertions(+), 40 deletions(-) diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index acc85acad31b..abed3490a8f8 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -22,6 +22,7 @@ #include #include #include +#include struct nft_xt { struct list_head head; @@ -43,6 +44,20 @@ struct nft_xt_match_priv { void *info; }; +struct nft_compat_net { + struct list_head nft_target_list; + struct list_head nft_match_list; +}; + +static unsigned int nft_compat_net_id __read_mostly; +static struct nft_expr_type nft_match_type; +static struct nft_expr_type nft_target_type; + +static struct nft_compat_net *nft_compat_pernet(struct net *net) +{ + return net_generic(net, nft_compat_net_id); +} + static bool nft_xt_put(struct nft_xt *xt) { if (refcount_dec_and_test(&xt->refcnt)) { @@ -734,10 +749,6 @@ static const struct nfnetlink_subsystem nfnl_compat_subsys = { .cb = nfnl_nft_compat_cb, }; -static LIST_HEAD(nft_match_list); - -static struct nft_expr_type nft_match_type; - static bool nft_match_cmp(const struct xt_match *match, const char *name, u32 rev, u32 family) { @@ -749,6 +760,7 @@ static const struct nft_expr_ops * nft_match_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { + struct nft_compat_net *cn; struct nft_xt *nft_match; struct xt_match *match; unsigned int matchsize; @@ -765,8 +777,10 @@ nft_match_select_ops(const struct nft_ctx *ctx, rev = ntohl(nla_get_be32(tb[NFTA_MATCH_REV])); family = ctx->family; + cn = nft_compat_pernet(ctx->net); + /* Re-use the existing match if it's already loaded. */ - list_for_each_entry(nft_match, &nft_match_list, head) { + list_for_each_entry(nft_match, &cn->nft_match_list, head) { struct xt_match *match = nft_match->ops.data; if (nft_match_cmp(match, mt_name, rev, family)) @@ -810,7 +824,7 @@ nft_match_select_ops(const struct nft_ctx *ctx, nft_match->ops.size = matchsize; - list_add(&nft_match->head, &nft_match_list); + list_add(&nft_match->head, &cn->nft_match_list); return &nft_match->ops; err: @@ -826,10 +840,6 @@ static struct nft_expr_type nft_match_type __read_mostly = { .owner = THIS_MODULE, }; -static LIST_HEAD(nft_target_list); - -static struct nft_expr_type nft_target_type; - static bool nft_target_cmp(const struct xt_target *tg, const char *name, u32 rev, u32 family) { @@ -841,6 +851,7 @@ static const struct nft_expr_ops * nft_target_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { + struct nft_compat_net *cn; struct nft_xt *nft_target; struct xt_target *target; char *tg_name; @@ -861,8 +872,9 @@ nft_target_select_ops(const struct nft_ctx *ctx, strcmp(tg_name, "standard") == 0) return ERR_PTR(-EINVAL); + cn = nft_compat_pernet(ctx->net); /* Re-use the existing target if it's already loaded. */ - list_for_each_entry(nft_target, &nft_target_list, head) { + list_for_each_entry(nft_target, &cn->nft_target_list, head) { struct xt_target *target = nft_target->ops.data; if (!target->target) @@ -907,7 +919,7 @@ nft_target_select_ops(const struct nft_ctx *ctx, else nft_target->ops.eval = nft_target_eval_xt; - list_add(&nft_target->head, &nft_target_list); + list_add(&nft_target->head, &cn->nft_target_list); return &nft_target->ops; err: @@ -923,13 +935,74 @@ static struct nft_expr_type nft_target_type __read_mostly = { .owner = THIS_MODULE, }; +static int __net_init nft_compat_init_net(struct net *net) +{ + struct nft_compat_net *cn = nft_compat_pernet(net); + + INIT_LIST_HEAD(&cn->nft_target_list); + INIT_LIST_HEAD(&cn->nft_match_list); + + return 0; +} + +static void __net_exit nft_compat_exit_net(struct net *net) +{ + struct nft_compat_net *cn = nft_compat_pernet(net); + struct nft_xt *xt, *next; + + if (list_empty(&cn->nft_match_list) && + list_empty(&cn->nft_target_list)) + return; + + /* If there was an error that caused nft_xt expr to not be initialized + * fully and noone else requested the same expression later, the lists + * contain 0-refcount entries that still hold module reference. + * + * Clean them here. + */ + mutex_lock(&net->nft.commit_mutex); + list_for_each_entry_safe(xt, next, &cn->nft_target_list, head) { + struct xt_target *target = xt->ops.data; + + list_del_init(&xt->head); + + if (refcount_read(&xt->refcnt)) + continue; + module_put(target->me); + kfree(xt); + } + + list_for_each_entry_safe(xt, next, &cn->nft_match_list, head) { + struct xt_match *match = xt->ops.data; + + list_del_init(&xt->head); + + if (refcount_read(&xt->refcnt)) + continue; + module_put(match->me); + kfree(xt); + } + mutex_unlock(&net->nft.commit_mutex); +} + +static struct pernet_operations nft_compat_net_ops = { + .init = nft_compat_init_net, + .exit = nft_compat_exit_net, + .id = &nft_compat_net_id, + .size = sizeof(struct nft_compat_net), +}; + static int __init nft_compat_module_init(void) { int ret; + ret = register_pernet_subsys(&nft_compat_net_ops); + if (ret < 0) + goto err_target; + ret = nft_register_expr(&nft_match_type); if (ret < 0) - return ret; + goto err_pernet; ret = nft_register_expr(&nft_target_type); if (ret < 0) @@ -942,45 +1015,21 @@ static int __init nft_compat_module_init(void) } return ret; - err_target: nft_unregister_expr(&nft_target_type); err_match: nft_unregister_expr(&nft_match_type); +err_pernet: + unregister_pernet_subsys(&nft_compat_net_ops); return ret; } static void __exit nft_compat_module_exit(void) { - struct nft_xt *xt, *next; - - /* list should be empty here, it can be non-empty only in case there - * was an error that caused nft_xt expr to not be initialized fully - * and noone else requested the same expression later. - * - * In this case, the lists contain 0-refcount entries that still - * hold module reference. - */ - list_for_each_entry_safe(xt, next, &nft_target_list, head) { - struct xt_target *target = xt->ops.data; - - if (WARN_ON_ONCE(refcount_read(&xt->refcnt))) - continue; - module_put(target->me); - kfree(xt); - } - - list_for_each_entry_safe(xt, next, &nft_match_list, head) { - struct xt_match *match = xt->ops.data; - - if (WARN_ON_ONCE(refcount_read(&xt->refcnt))) - continue; - module_put(match->me); - kfree(xt); - } nfnetlink_subsys_unregister(&nfnl_compat_subsys); nft_unregister_expr(&nft_target_type); nft_unregister_expr(&nft_match_type); + unregister_pernet_subsys(&nft_compat_net_ops); } MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_NFT_COMPAT); From b2e3d68d1251a051a620f9086e18f7ffa6833b5b Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 14 Jan 2019 14:28:50 +0100 Subject: [PATCH 051/525] netfilter: nft_compat: destroy function must not have side effects The nft_compat destroy function deletes the nft_xt object from a list. This isn't allowed anymore. Destroy functions are called asynchronously, i.e. next batch can find the object that has a pending ->destroy() invocation: cpu0 cpu1 worker ->destroy for_each_entry() if (x == ... return x->ops; list_del(x) kfree_rcu(x) expr->ops->... // ops was free'd To resolve this, the list_del needs to occur before the transaction mutex gets released. nf_tables has a 'deactivate' hook for this purpose, so use that to unlink the object from the list. Fixes: 0935d5588400 ("netfilter: nf_tables: asynchronous release") Reported-by: Taehee Yoo Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_compat.c | 48 +++++++++++++++++++++++++++++++++++++- 1 file changed, 47 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index abed3490a8f8..5eb269428832 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -29,6 +29,9 @@ struct nft_xt { struct nft_expr_ops ops; refcount_t refcnt; + /* used only when transaction mutex is locked */ + unsigned int listcnt; + /* Unlike other expressions, ops doesn't have static storage duration. * nft core assumes they do. We use kfree_rcu so that nft core can * can check expr->ops->size even after nft_compat->destroy() frees @@ -61,7 +64,7 @@ static struct nft_compat_net *nft_compat_pernet(struct net *net) static bool nft_xt_put(struct nft_xt *xt) { if (refcount_dec_and_test(&xt->refcnt)) { - list_del(&xt->head); + WARN_ON_ONCE(!list_empty(&xt->head)); kfree_rcu(xt, rcu_head); return true; } @@ -555,6 +558,43 @@ nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) __nft_match_destroy(ctx, expr, nft_expr_priv(expr)); } +static void nft_compat_activate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + struct list_head *h) +{ + struct nft_xt *xt = container_of(expr->ops, struct nft_xt, ops); + + if (xt->listcnt == 0) + list_add(&xt->head, h); + + xt->listcnt++; +} + +static void nft_compat_activate_mt(const struct nft_ctx *ctx, + const struct nft_expr *expr) +{ + struct nft_compat_net *cn = nft_compat_pernet(ctx->net); + + nft_compat_activate(ctx, expr, &cn->nft_match_list); +} + +static void nft_compat_activate_tg(const struct nft_ctx *ctx, + const struct nft_expr *expr) +{ + struct nft_compat_net *cn = nft_compat_pernet(ctx->net); + + nft_compat_activate(ctx, expr, &cn->nft_target_list); +} + +static void nft_compat_deactivate(const struct nft_ctx *ctx, + const struct nft_expr *expr) +{ + struct nft_xt *xt = container_of(expr->ops, struct nft_xt, ops); + + if (--xt->listcnt == 0) + list_del_init(&xt->head); +} + static void nft_match_large_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { @@ -808,6 +848,8 @@ nft_match_select_ops(const struct nft_ctx *ctx, nft_match->ops.eval = nft_match_eval; nft_match->ops.init = nft_match_init; nft_match->ops.destroy = nft_match_destroy; + nft_match->ops.activate = nft_compat_activate_mt; + nft_match->ops.deactivate = nft_compat_deactivate; nft_match->ops.dump = nft_match_dump; nft_match->ops.validate = nft_match_validate; nft_match->ops.data = match; @@ -824,6 +866,7 @@ nft_match_select_ops(const struct nft_ctx *ctx, nft_match->ops.size = matchsize; + nft_match->listcnt = 1; list_add(&nft_match->head, &cn->nft_match_list); return &nft_match->ops; @@ -910,6 +953,8 @@ nft_target_select_ops(const struct nft_ctx *ctx, nft_target->ops.size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize)); nft_target->ops.init = nft_target_init; nft_target->ops.destroy = nft_target_destroy; + nft_target->ops.activate = nft_compat_activate_tg; + nft_target->ops.deactivate = nft_compat_deactivate; nft_target->ops.dump = nft_target_dump; nft_target->ops.validate = nft_target_validate; nft_target->ops.data = target; @@ -919,6 +964,7 @@ nft_target_select_ops(const struct nft_ctx *ctx, else nft_target->ops.eval = nft_target_eval_xt; + nft_target->listcnt = 1; list_add(&nft_target->head, &cn->nft_target_list); return &nft_target->ops; From 96167167b6e17b25c0e05ecc31119b73baeab094 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 17 Jan 2019 11:48:34 -0800 Subject: [PATCH 052/525] perf script: Fix crash with printing mixed trace point and other events 'perf script' crashes currently when printing mixed trace points and other events because the trace format does not handle events without trace meta data. Add a simple check to avoid that. % cat > test.c main() { printf("Hello world\n"); } ^D % gcc -g -o test test.c % sudo perf probe -x test 'test.c:3' % perf record -e '{cpu/cpu-cycles,period=10000/,probe_test:main}:S' ./test % perf script Committer testing: Before: # perf probe -x /lib64/libc-2.28.so malloc Added new event: probe_libc:malloc (on malloc in /usr/lib64/libc-2.28.so) You can now use it in all perf tools, such as: perf record -e probe_libc:malloc -aR sleep 1 # perf probe -l probe_libc:malloc (on __libc_malloc@malloc/malloc.c in /usr/lib64/libc-2.28.so) # perf record -e '{cpu/cpu-cycles,period=10000/,probe_libc:*}:S' sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.023 MB perf.data (40 samples) ] # perf script Segmentation fault (core dumped) ^C # After: # perf script | head -6 sleep 2888 94796.944981: 16198 cpu/cpu-cycles,period=10000/: ffffffff925dc04f get_random_u32+0x1f (/lib/modules/5.0.0-rc2+/build/vmlinux) sleep 2888 [-01] 94796.944981: probe_libc:malloc: sleep 2888 94796.944983: 4713 cpu/cpu-cycles,period=10000/: ffffffff922763af change_protection+0xcf (/lib/modules/5.0.0-rc2+/build/vmlinux) sleep 2888 [-01] 94796.944983: probe_libc:malloc: sleep 2888 94796.944986: 9934 cpu/cpu-cycles,period=10000/: ffffffff922777e0 move_page_tables+0x0 (/lib/modules/5.0.0-rc2+/build/vmlinux) sleep 2888 [-01] 94796.944986: probe_libc:malloc: # Signed-off-by: Andi Kleen Tested-by: Arnaldo Carvalho de Melo Acked-by: Jiri Olsa Link: http://lkml.kernel.org/r/20190117194834.21940-1-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index d079f36d342d..357906ed1898 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1794,7 +1794,7 @@ static void process_event(struct perf_script *script, return; } - if (PRINT_FIELD(TRACE)) { + if (PRINT_FIELD(TRACE) && sample->raw_data) { event_format__fprintf(evsel->tp_format, sample->cpu, sample->raw_data, sample->raw_size, fp); } From 1a51c5da5acc6c188c917ba572eebac5f8793432 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 10 Jan 2019 17:17:16 -0800 Subject: [PATCH 053/525] perf core: Fix perf_proc_update_handler() bug The perf_proc_update_handler() handles /proc/sys/kernel/perf_event_max_sample_rate syctl variable. When the PMU IRQ handler timing monitoring is disabled, i.e, when /proc/sys/kernel/perf_cpu_time_max_percent is equal to 0 or 100, then no modification to sysctl_perf_event_sample_rate is allowed to prevent possible hang from wrong values. The problem is that the test to prevent modification is made after the sysctl variable is modified in perf_proc_update_handler(). You get an error: $ echo 10001 >/proc/sys/kernel/perf_event_max_sample_rate echo: write error: invalid argument But the value is still modified causing all sorts of inconsistencies: $ cat /proc/sys/kernel/perf_event_max_sample_rate 10001 This patch fixes the problem by moving the parsing of the value after the test. Committer testing: # echo 100 > /proc/sys/kernel/perf_cpu_time_max_percent # echo 10001 > /proc/sys/kernel/perf_event_max_sample_rate -bash: echo: write error: Invalid argument # cat /proc/sys/kernel/perf_event_max_sample_rate 10001 # Signed-off-by: Stephane Eranian Reviewed-by: Andi Kleen Reviewed-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Kan Liang Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1547169436-6266-1-git-send-email-eranian@google.com Signed-off-by: Arnaldo Carvalho de Melo --- kernel/events/core.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 3cd13a30f732..e5ede6918050 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -436,18 +436,18 @@ int perf_proc_update_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - - if (ret || !write) - return ret; - + int ret; + int perf_cpu = sysctl_perf_cpu_time_max_percent; /* * If throttling is disabled don't allow the write: */ - if (sysctl_perf_cpu_time_max_percent == 100 || - sysctl_perf_cpu_time_max_percent == 0) + if (write && (perf_cpu == 100 || perf_cpu == 0)) return -EINVAL; + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (ret || !write) + return ret; + max_samples_per_tick = DIV_ROUND_UP(sysctl_perf_event_sample_rate, HZ); perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate; update_perf_cpu_limits(); From 94ec1eb711db69be1414b56b3160b816e86a5c5b Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 18 Jan 2019 11:34:15 -0300 Subject: [PATCH 054/525] perf python: Remove -fstack-clash-protection when building with some clang versions These options are not present in some (all?) clang versions, so when we build for a distro that has a gcc new enough to have these options and that the distro python build config settings use them but clang doesn't support, b00m. This is the case with fedora rawhide (now gearing towards f30), so check if clang has the and remove the missing ones from CFLAGS. Cc: Eduardo Habkost Cc: Thiago Macieira Cc: Adrian Hunter Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-5q50q9w458yawgxf9ez54jbp@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/setup.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index 63f758c655d5..64d1f36dee99 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -17,6 +17,8 @@ if cc == "clang": vars[var] = sub("-mcet", "", vars[var]) if not clang_has_option("-fcf-protection"): vars[var] = sub("-fcf-protection", "", vars[var]) + if not clang_has_option("-fstack-clash-protection"): + vars[var] = sub("-fstack-clash-protection", "", vars[var]) from distutils.core import setup, Extension From 89857a8a5c89a406b967ab2be7bd2ccdbe75e73d Mon Sep 17 00:00:00 2001 From: Madalin Bucur Date: Fri, 21 Dec 2018 16:41:42 +0200 Subject: [PATCH 055/525] soc: fsl: qbman: avoid race in clearing QMan interrupt By clearing all interrupt sources, not only those that already occurred, the existing code may acknowledge by mistake interrupts that occurred after the code checks for them. Signed-off-by: Madalin Bucur Signed-off-by: Roy Pledge Signed-off-by: Li Yang --- drivers/soc/fsl/qbman/qman.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c index 52c153cd795a..636f83f781f5 100644 --- a/drivers/soc/fsl/qbman/qman.c +++ b/drivers/soc/fsl/qbman/qman.c @@ -1143,18 +1143,19 @@ static void qm_mr_process_task(struct work_struct *work); static irqreturn_t portal_isr(int irq, void *ptr) { struct qman_portal *p = ptr; - - u32 clear = QM_DQAVAIL_MASK | p->irq_sources; u32 is = qm_in(&p->p, QM_REG_ISR) & p->irq_sources; + u32 clear = 0; if (unlikely(!is)) return IRQ_NONE; /* DQRR-handling if it's interrupt-driven */ - if (is & QM_PIRQ_DQRI) + if (is & QM_PIRQ_DQRI) { __poll_portal_fast(p, QMAN_POLL_LIMIT); + clear = QM_DQAVAIL_MASK | QM_PIRQ_DQRI; + } /* Handling of anything else that's interrupt-driven */ - clear |= __poll_portal_slow(p, is); + clear |= __poll_portal_slow(p, is) & QM_PIRQ_SLOW; qm_out(&p->p, QM_REG_ISR, clear); return IRQ_HANDLED; } From e3f72b749da2bf63bed7409e416f160418d475b6 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Mon, 14 Jan 2019 19:38:36 -0800 Subject: [PATCH 056/525] pinctrl: cherryview: fix Strago DMI workaround Well, hopefully 3rd time is a charm. We tried making that check DMI_BIOS_VERSION and DMI_BOARD_VERSION, but the real one is DMI_PRODUCT_VERSION. Fixes: 86c5dd6860a6 ("pinctrl: cherryview: limit Strago DMI workarounds to version 1.0") Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=197953 Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1631930 Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov Reviewed-by: Andy Shevchenko Acked-by: Mika Westerberg Signed-off-by: Linus Walleij --- drivers/pinctrl/intel/pinctrl-cherryview.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c index 05044e323ea5..03ec7a5d9d0b 100644 --- a/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -1513,7 +1513,7 @@ static const struct dmi_system_id chv_no_valid_mask[] = { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"), DMI_MATCH(DMI_PRODUCT_FAMILY, "Intel_Strago"), - DMI_MATCH(DMI_BOARD_VERSION, "1.0"), + DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), }, }, { @@ -1521,7 +1521,7 @@ static const struct dmi_system_id chv_no_valid_mask[] = { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "HP"), DMI_MATCH(DMI_PRODUCT_NAME, "Setzer"), - DMI_MATCH(DMI_BOARD_VERSION, "1.0"), + DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), }, }, { @@ -1529,7 +1529,7 @@ static const struct dmi_system_id chv_no_valid_mask[] = { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"), DMI_MATCH(DMI_PRODUCT_NAME, "Cyan"), - DMI_MATCH(DMI_BOARD_VERSION, "1.0"), + DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), }, }, { @@ -1537,7 +1537,7 @@ static const struct dmi_system_id chv_no_valid_mask[] = { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"), DMI_MATCH(DMI_PRODUCT_NAME, "Celes"), - DMI_MATCH(DMI_BOARD_VERSION, "1.0"), + DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), }, }, {} From f165988b77ef849eb0c1aebd94fe778024f88314 Mon Sep 17 00:00:00 2001 From: Jason Kridner Date: Fri, 11 Jan 2019 10:02:13 -0500 Subject: [PATCH 057/525] pinctrl: mcp23s08: spi: Fix regmap allocation for mcp23s18 Fixes issue created by 9b3e4207661e67f04c72af15e29f74cd944f5964. It wasn't possible for one_regmap_config to be non-NULL at the point it was tested for mcp23s18 devices. Applied the same pattern of allocating one_regmap_config using devm_kmemdump() and then initializing the local regmap structure from that. Signed-off-by: Jason Kridner Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-mcp23s08.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/pinctrl/pinctrl-mcp23s08.c b/drivers/pinctrl/pinctrl-mcp23s08.c index b03481ef99a1..98905d4a79ca 100644 --- a/drivers/pinctrl/pinctrl-mcp23s08.c +++ b/drivers/pinctrl/pinctrl-mcp23s08.c @@ -832,8 +832,13 @@ static int mcp23s08_probe_one(struct mcp23s08 *mcp, struct device *dev, break; case MCP_TYPE_S18: + one_regmap_config = + devm_kmemdup(dev, &mcp23x17_regmap, + sizeof(struct regmap_config), GFP_KERNEL); + if (!one_regmap_config) + return -ENOMEM; mcp->regmap = devm_regmap_init(dev, &mcp23sxx_spi_regmap, mcp, - &mcp23x17_regmap); + one_regmap_config); mcp->reg_shift = 1; mcp->chip.ngpio = 16; mcp->chip.label = "mcp23s18"; From 1497e804d1a6e2bd9107ddf64b0310449f4673eb Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Sat, 19 Jan 2019 00:12:39 -0800 Subject: [PATCH 058/525] perf tools: Handle TOPOLOGY headers with no CPU This patch fixes an issue in cpumap.c when used with the TOPOLOGY header. In some configurations, some NUMA nodes may have no CPU (empty cpulist). Yet a cpumap map must be created otherwise perf abort with an error. This patch handles this case by creating a dummy map. Before: $ perf record -o - -e cycles noploop 2 | perf script -i - 0x6e8 [0x6c]: failed to process type: 80 After: $ perf record -o - -e cycles noploop 2 | perf script -i - noploop for 2 seconds Signed-off-by: Stephane Eranian Acked-by: Jiri Olsa Cc: Andi Kleen Cc: Kan Liang Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1547885559-1657-1-git-send-email-eranian@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cpumap.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 1ccbd3342069..383674f448fc 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -134,7 +134,12 @@ struct cpu_map *cpu_map__new(const char *cpu_list) if (!cpu_list) return cpu_map__read_all_cpu_map(); - if (!isdigit(*cpu_list)) + /* + * must handle the case of empty cpumap to cover + * TOPOLOGY header for NUMA nodes with no CPU + * ( e.g., because of CPU hotplug) + */ + if (!isdigit(*cpu_list) && *cpu_list != '\0') goto out; while (isdigit(*cpu_list)) { @@ -181,8 +186,10 @@ struct cpu_map *cpu_map__new(const char *cpu_list) if (nr_cpus > 0) cpus = cpu_map__trim_new(nr_cpus, tmp_cpus); - else + else if (*cpu_list != '\0') cpus = cpu_map__default_new(); + else + cpus = cpu_map__dummy_new(); invalid: free(tmp_cpus); out: From da06d568386877809532e8ec678f4a5e300f0951 Mon Sep 17 00:00:00 2001 From: He Kuang Date: Mon, 21 Jan 2019 00:05:22 +0800 Subject: [PATCH 059/525] perf top: Fix wrong hottest instruction highlighted The annotation line percentage is compared and inserted into the rbtree, but the percent field of 'struct annotation_data' is an array, the comparison result between them is the address difference. This patch compares the right slot of percent array according to opts->percent_type and makes things right. The problem can be reproduced by pressing 'H' in perf top annotation view. It should highlight the instruction line which has the highest sampling percentage. Signed-off-by: He Kuang Reviewed-by: Jiri Olsa Cc: Alexander Shishkin Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20190120160523.4391-1-hekuang@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/ui/browsers/annotate.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index 1d00e5ec7906..82e16bf84466 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -224,20 +224,24 @@ static unsigned int annotate_browser__refresh(struct ui_browser *browser) return ret; } -static int disasm__cmp(struct annotation_line *a, struct annotation_line *b) +static double disasm__cmp(struct annotation_line *a, struct annotation_line *b, + int percent_type) { int i; for (i = 0; i < a->data_nr; i++) { - if (a->data[i].percent == b->data[i].percent) + if (a->data[i].percent[percent_type] == b->data[i].percent[percent_type]) continue; - return a->data[i].percent < b->data[i].percent; + return a->data[i].percent[percent_type] - + b->data[i].percent[percent_type]; } return 0; } -static void disasm_rb_tree__insert(struct rb_root *root, struct annotation_line *al) +static void disasm_rb_tree__insert(struct annotate_browser *browser, + struct annotation_line *al) { + struct rb_root *root = &browser->entries; struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; struct annotation_line *l; @@ -246,7 +250,7 @@ static void disasm_rb_tree__insert(struct rb_root *root, struct annotation_line parent = *p; l = rb_entry(parent, struct annotation_line, rb_node); - if (disasm__cmp(al, l)) + if (disasm__cmp(al, l, browser->opts->percent_type) < 0) p = &(*p)->rb_left; else p = &(*p)->rb_right; @@ -329,7 +333,7 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser, RB_CLEAR_NODE(&pos->al.rb_node); continue; } - disasm_rb_tree__insert(&browser->entries, &pos->al); + disasm_rb_tree__insert(browser, &pos->al); } pthread_mutex_unlock(¬es->lock); From 8bf8c6da53c2265aea365a1de6038f118f522113 Mon Sep 17 00:00:00 2001 From: Tony Jones Date: Sun, 20 Jan 2019 11:14:14 -0800 Subject: [PATCH 060/525] perf script: Fix crash when processing recorded stat data While updating perf to work with Python3 and Python2 I noticed that the stat-cpi script was dumping core. $ perf stat -e cycles,instructions record -o /tmp/perf.data /bin/false Performance counter stats for '/bin/false': 802,148 cycles 604,622 instructions 802,148 cycles 604,622 instructions 0.001445842 seconds time elapsed $ perf script -i /tmp/perf.data -s scripts/python/stat-cpi.py Segmentation fault (core dumped) ... ... rblist=rblist@entry=0xb2a200 , new_entry=new_entry@entry=0x7ffcb755c310) at util/rblist.c:33 ctx=, type=, create=, cpu=, evsel=) at util/stat-shadow.c:118 ctx=, type=, st=) at util/stat-shadow.c:196 count=count@entry=727442, cpu=cpu@entry=0, st=0xb2a200 ) at util/stat-shadow.c:239 config=config@entry=0xafeb40 , counter=counter@entry=0x133c6e0) at util/stat.c:372 ... ... The issue is that since 1fcd03946b52 perf_stat__update_shadow_stats now calls update_runtime_stat passing rt_stat rather than calling update_stats but perf_stat__init_shadow_stats has never been called to initialize rt_stat in the script path processing recorded stat data. Since I can't see any reason why perf_stat__init_shadow_stats() is presently initialized like it is in builtin-script.c::perf_sample__fprint_metric() [4bd1bef8bba2f] I'm proposing it instead be initialized once in __cmd_script Committer testing: After applying the patch: # perf script -i /tmp/perf.data -s tools/perf/scripts/python/stat-cpi.py 0.001970: cpu -1, thread -1 -> cpi 1.709079 (1075684/629394) # No segfault. Signed-off-by: Tony Jones Reviewed-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Tested-by: Ravi Bangoria Cc: Andi Kleen Cc: Jin Yao Fixes: 1fcd03946b52 ("perf stat: Update per-thread shadow stats") Link: http://lkml.kernel.org/r/20190120191414.12925-1-tonyj@suse.de Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 357906ed1898..ac221f137ed2 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1681,13 +1681,8 @@ static void perf_sample__fprint_metric(struct perf_script *script, .force_header = false, }; struct perf_evsel *ev2; - static bool init; u64 val; - if (!init) { - perf_stat__init_shadow_stats(); - init = true; - } if (!evsel->stats) perf_evlist__alloc_stats(script->session->evlist, false); if (evsel_script(evsel->leader)->gnum++ == 0) @@ -2359,6 +2354,8 @@ static int __cmd_script(struct perf_script *script) signal(SIGINT, sig_handler); + perf_stat__init_shadow_stats(); + /* override event processing functions */ if (script->show_task_events) { script->tool.comm = process_comm_event; From 8af526e035357d2df1d7cacc51bcde0a5d9f9f9f Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 15 Jan 2019 16:45:32 +0200 Subject: [PATCH 061/525] RDMA/mlx5: Fix check for supported user flags when creating a QP When the flags verification was added two flags were missed from the check: * MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC * MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC This causes user applications that were using these flags to break. Fixes: 2e43bb31b8df ("IB/mlx5: Verify that driver supports user flags") Signed-off-by: Mark Bloch Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/qp.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index dd2ae640bc84..7db778d96ef5 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -1912,14 +1912,16 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd, } if (!check_flags_mask(ucmd.flags, + MLX5_QP_FLAG_ALLOW_SCATTER_CQE | + MLX5_QP_FLAG_BFREG_INDEX | + MLX5_QP_FLAG_PACKET_BASED_CREDIT_MODE | + MLX5_QP_FLAG_SCATTER_CQE | MLX5_QP_FLAG_SIGNATURE | - MLX5_QP_FLAG_SCATTER_CQE | - MLX5_QP_FLAG_TUNNEL_OFFLOADS | - MLX5_QP_FLAG_BFREG_INDEX | - MLX5_QP_FLAG_TYPE_DCT | - MLX5_QP_FLAG_TYPE_DCI | - MLX5_QP_FLAG_ALLOW_SCATTER_CQE | - MLX5_QP_FLAG_PACKET_BASED_CREDIT_MODE)) + MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC | + MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC | + MLX5_QP_FLAG_TUNNEL_OFFLOADS | + MLX5_QP_FLAG_TYPE_DCI | + MLX5_QP_FLAG_TYPE_DCT)) return -EINVAL; err = get_qp_user_index(to_mucontext(pd->uobject->context), From f45f8edbe1d345273ba0d8d8a9872bb30966869b Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Tue, 15 Jan 2019 16:45:48 +0200 Subject: [PATCH 062/525] IB/mlx4: Fix using wrong function to destroy sqp AHs under SRIOV The commit cited below replaced rdma_create_ah with mlx4_ib_create_slave_ah when creating AHs for the paravirtualized special QPs. However, this change also required replacing rdma_destroy_ah with mlx4_ib_destroy_ah in the affected flows. The commit missed 3 places where rdma_destroy_ah should have been replaced with mlx4_ib_destroy_ah. As a result, the pd usecount was decremented when the ah was destroyed -- although the usecount was NOT incremented when the ah was created. This caused the pd usecount to become negative, and resulted in the WARN_ON stack trace below when the mlx4_ib.ko module was unloaded: WARNING: CPU: 3 PID: 25303 at drivers/infiniband/core/verbs.c:329 ib_dealloc_pd+0x6d/0x80 [ib_core] Modules linked in: rdma_ucm rdma_cm iw_cm ib_cm ib_umad mlx4_ib(-) ib_uverbs ib_core mlx4_en mlx4_core nfsv3 nfs fscache configfs xt_conntrack nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 libcrc32c ipt_REJECT nf_reject_ipv4 tun ebtable_filter ebtables ip6table_filter ip6_tables iptable_filter bridge stp llc dm_mirror dm_region_hash dm_log dm_mod dax rndis_wlan rndis_host coretemp kvm_intel cdc_ether kvm usbnet iTCO_wdt iTCO_vendor_support cfg80211 irqbypass lpc_ich ipmi_si i2c_i801 mii pcspkr i2c_core mfd_core ipmi_devintf i7core_edac ipmi_msghandler ioatdma pcc_cpufreq dca acpi_cpufreq nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables ext4 mbcache jbd2 sr_mod cdrom ata_generic pata_acpi mptsas scsi_transport_sas mptscsih crc32c_intel ata_piix bnx2 mptbase ipv6 crc_ccitt autofs4 [last unloaded: mlx4_core] CPU: 3 PID: 25303 Comm: modprobe Tainted: G W I 5.0.0-rc1-net-mlx4+ #1 Hardware name: IBM -[7148ZV6]-/Node 1, System Card, BIOS -[MLE170CUS-1.70]- 09/23/2011 RIP: 0010:ib_dealloc_pd+0x6d/0x80 [ib_core] Code: 00 00 85 c0 75 02 5b c3 80 3d aa 87 03 00 00 75 f5 48 c7 c7 88 d7 8f a0 31 c0 c6 05 98 87 03 00 01 e8 07 4c 79 e0 0f 0b 5b c3 <0f> 0b eb be 0f 0b eb ab 90 66 2e 0f 1f 84 00 00 00 00 00 66 66 66 RSP: 0018:ffffc90005347e30 EFLAGS: 00010282 RAX: 00000000ffffffea RBX: ffff8888589e9540 RCX: 0000000000000006 RDX: 0000000000000006 RSI: ffff88885d57ad40 RDI: 0000000000000000 RBP: ffff88885b029c00 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000004 R12: ffff8887f06c0000 R13: ffff8887f06c13e8 R14: 0000000000000000 R15: 0000000000000000 FS: 00007fd6743c6740(0000) GS:ffff88887fcc0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000ed1038 CR3: 00000007e3156000 CR4: 00000000000006e0 Call Trace: mlx4_ib_close_sriov+0x125/0x180 [mlx4_ib] mlx4_ib_remove+0x57/0x1f0 [mlx4_ib] mlx4_remove_device+0x92/0xa0 [mlx4_core] mlx4_unregister_interface+0x39/0x90 [mlx4_core] mlx4_ib_cleanup+0xc/0xd7 [mlx4_ib] __x64_sys_delete_module+0x17d/0x290 ? trace_hardirqs_off_thunk+0x1a/0x1c ? do_syscall_64+0x12/0x180 do_syscall_64+0x4a/0x180 entry_SYSCALL_64_after_hwframe+0x49/0xbe Fixes: 5e62d5ff1b9a ("IB/mlx4: Create slave AH's directly") Signed-off-by: Jack Morgenstein Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx4/mad.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index 25439da8976c..936ee1314bcd 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -1411,7 +1411,7 @@ int mlx4_ib_send_to_wire(struct mlx4_ib_dev *dev, int slave, u8 port, sqp_mad = (struct mlx4_mad_snd_buf *) (sqp->tx_ring[wire_tx_ix].buf.addr); if (sqp->tx_ring[wire_tx_ix].ah) - rdma_destroy_ah(sqp->tx_ring[wire_tx_ix].ah, 0); + mlx4_ib_destroy_ah(sqp->tx_ring[wire_tx_ix].ah, 0); sqp->tx_ring[wire_tx_ix].ah = ah; ib_dma_sync_single_for_cpu(&dev->ib_dev, sqp->tx_ring[wire_tx_ix].buf.map, @@ -1902,7 +1902,7 @@ static void mlx4_ib_sqp_comp_worker(struct work_struct *work) if (wc.status == IB_WC_SUCCESS) { switch (wc.opcode) { case IB_WC_SEND: - rdma_destroy_ah(sqp->tx_ring[wc.wr_id & + mlx4_ib_destroy_ah(sqp->tx_ring[wc.wr_id & (MLX4_NUM_TUNNEL_BUFS - 1)].ah, 0); sqp->tx_ring[wc.wr_id & (MLX4_NUM_TUNNEL_BUFS - 1)].ah = NULL; @@ -1931,7 +1931,7 @@ static void mlx4_ib_sqp_comp_worker(struct work_struct *work) " status = %d, wrid = 0x%llx\n", ctx->slave, wc.status, wc.wr_id); if (!MLX4_TUN_IS_RECV(wc.wr_id)) { - rdma_destroy_ah(sqp->tx_ring[wc.wr_id & + mlx4_ib_destroy_ah(sqp->tx_ring[wc.wr_id & (MLX4_NUM_TUNNEL_BUFS - 1)].ah, 0); sqp->tx_ring[wc.wr_id & (MLX4_NUM_TUNNEL_BUFS - 1)].ah = NULL; From 904bba211acc2112fdf866e5a2bc6cd9ecd0de1b Mon Sep 17 00:00:00 2001 From: Brian Welty Date: Thu, 17 Jan 2019 12:41:32 -0800 Subject: [PATCH 063/525] IB/{hfi1, qib}: Fix WC.byte_len calculation for UD_SEND_WITH_IMM The work completion length for a receiving a UD send with immediate is short by 4 bytes causing application using this opcode to fail. The UD receive logic incorrectly subtracts 4 bytes for immediate value. These bytes are already included in header length and are used to calculate header/payload split, so the result is these 4 bytes are subtracted twice, once when the header length subtracted from the overall length and once again in the UD opcode specific path. Remove the extra subtraction when handling the opcode. Fixes: 7724105686e7 ("IB/hfi1: add driver files") Reviewed-by: Michael J. Ruhl Signed-off-by: Brian Welty Signed-off-by: Mike Marciniszyn Signed-off-by: Dennis Dalessandro Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/hfi1/ud.c | 1 - drivers/infiniband/hw/qib/qib_ud.c | 1 - 2 files changed, 2 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/ud.c b/drivers/infiniband/hw/hfi1/ud.c index 88242fe95eaa..bf96067876c9 100644 --- a/drivers/infiniband/hw/hfi1/ud.c +++ b/drivers/infiniband/hw/hfi1/ud.c @@ -987,7 +987,6 @@ void hfi1_ud_rcv(struct hfi1_packet *packet) opcode == IB_OPCODE_UD_SEND_ONLY_WITH_IMMEDIATE) { wc.ex.imm_data = packet->ohdr->u.ud.imm_data; wc.wc_flags = IB_WC_WITH_IMM; - tlen -= sizeof(u32); } else if (opcode == IB_OPCODE_UD_SEND_ONLY) { wc.ex.imm_data = 0; wc.wc_flags = 0; diff --git a/drivers/infiniband/hw/qib/qib_ud.c b/drivers/infiniband/hw/qib/qib_ud.c index 868da0ece7ba..445ea19a2ec8 100644 --- a/drivers/infiniband/hw/qib/qib_ud.c +++ b/drivers/infiniband/hw/qib/qib_ud.c @@ -512,7 +512,6 @@ void qib_ud_rcv(struct qib_ibport *ibp, struct ib_header *hdr, opcode == IB_OPCODE_UD_SEND_ONLY_WITH_IMMEDIATE) { wc.ex.imm_data = ohdr->u.ud.imm_data; wc.wc_flags = IB_WC_WITH_IMM; - tlen -= sizeof(u32); } else if (opcode == IB_OPCODE_UD_SEND_ONLY) { wc.ex.imm_data = 0; wc.wc_flags = 0; From 7709b0dc265f28695487712c45f02bbd1f98415d Mon Sep 17 00:00:00 2001 From: "Michael J. Ruhl" Date: Thu, 17 Jan 2019 12:42:04 -0800 Subject: [PATCH 064/525] IB/hfi1: Remove overly conservative VM_EXEC flag check Applications that use the stack for execution purposes cause userspace PSM jobs to fail during mmap(). Both Fortran (non-standard format parsing) and C (callback functions located in the stack) applications can be written such that stack execution is required. The linker notes this via the gnu_stack ELF flag. This causes READ_IMPLIES_EXEC to be set which forces all PROT_READ mmaps to have PROT_EXEC for the process. Checking for VM_EXEC bit and failing the request with EPERM is overly conservative and will break any PSM application using executable stacks. Cc: #v4.14+ Fixes: 12220267645c ("IB/hfi: Protect against writable mmap") Reviewed-by: Mike Marciniszyn Reviewed-by: Dennis Dalessandro Reviewed-by: Ira Weiny Signed-off-by: Michael J. Ruhl Signed-off-by: Dennis Dalessandro Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/hfi1/file_ops.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index c22ebc774a6a..f9a7e9d29c8b 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -488,7 +488,7 @@ static int hfi1_file_mmap(struct file *fp, struct vm_area_struct *vma) vmf = 1; break; case STATUS: - if (flags & (unsigned long)(VM_WRITE | VM_EXEC)) { + if (flags & VM_WRITE) { ret = -EPERM; goto done; } From 09ce351dff8e7636af0beb72cd4a86c3904a0500 Mon Sep 17 00:00:00 2001 From: Mike Marciniszyn Date: Thu, 17 Jan 2019 12:42:16 -0800 Subject: [PATCH 065/525] IB/hfi1: Add limit test for RC/UC send via loopback Fix potential memory corruption and panic in loopback for IB_WR_SEND variants. The code blindly assumes the posted length will fit in the fetched rwqe, which is not a valid assumption. Fix by adding a limit test, and triggering the appropriate send completion and putting the QP in an error state. This mimics the handling for non-loopback QPs. Fixes: 15703461533a ("IB/{hfi1, qib, rdmavt}: Move ruc_loopback to rdmavt") Cc: #v4.20+ Reviewed-by: Michael J. Ruhl Signed-off-by: Mike Marciniszyn Signed-off-by: Dennis Dalessandro Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rdmavt/qp.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index a1bd8cfc2c25..c6cc3e4ab71d 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -2910,6 +2910,8 @@ send: goto op_err; if (!ret) goto rnr_nak; + if (wqe->length > qp->r_len) + goto inv_err; break; case IB_WR_RDMA_WRITE_WITH_IMM: @@ -3078,7 +3080,10 @@ op_err: goto err; inv_err: - send_status = IB_WC_REM_INV_REQ_ERR; + send_status = + sqp->ibqp.qp_type == IB_QPT_RC ? + IB_WC_REM_INV_REQ_ERR : + IB_WC_SUCCESS; wc.status = IB_WC_LOC_QP_OP_ERR; goto err; From d79af7242bb237d00e40092810e6828fbb929d2d Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 10 Jan 2019 14:02:24 -0700 Subject: [PATCH 066/525] RDMA/device: Expose ib_device_try_get(() It turns out future patches need this capability quite widely now, not just for netlink, so provide two global functions to manage the registration lock refcount. This also moves the point the lock becomes 1 to within ib_register_device() so that the semantics of the public API are very sane and clear. Calling ib_device_try_get() will fail on devices that are only allocated but not yet registered. Signed-off-by: Jason Gunthorpe Reviewed-by: Steve Wise Reviewed-by: Parav Pandit --- drivers/infiniband/core/core_priv.h | 1 - drivers/infiniband/core/device.c | 13 ++++++++++--- include/rdma/ib_verbs.h | 24 ++++++++++++++++++++++-- 3 files changed, 32 insertions(+), 6 deletions(-) diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h index 3cd830d52967..616734313f0c 100644 --- a/drivers/infiniband/core/core_priv.h +++ b/drivers/infiniband/core/core_priv.h @@ -267,7 +267,6 @@ static inline int ib_mad_enforce_security(struct ib_mad_agent_private *map, #endif struct ib_device *ib_device_get_by_index(u32 ifindex); -void ib_device_put(struct ib_device *device); /* RDMA device netlink */ void nldev_init(void); void nldev_exit(void); diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 8872453e26c0..238ec42778ef 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -156,19 +156,26 @@ struct ib_device *ib_device_get_by_index(u32 index) down_read(&lists_rwsem); device = __ib_device_get_by_index(index); if (device) { - /* Do not return a device if unregistration has started. */ - if (!refcount_inc_not_zero(&device->refcount)) + if (!ib_device_try_get(device)) device = NULL; } up_read(&lists_rwsem); return device; } +/** + * ib_device_put - Release IB device reference + * @device: device whose reference to be released + * + * ib_device_put() releases reference to the IB device to allow it to be + * unregistered and eventually free. + */ void ib_device_put(struct ib_device *device) { if (refcount_dec_and_test(&device->refcount)) complete(&device->unreg_completion); } +EXPORT_SYMBOL(ib_device_put); static struct ib_device *__ib_device_get_by_name(const char *name) { @@ -303,7 +310,6 @@ struct ib_device *ib_alloc_device(size_t size) rwlock_init(&device->client_data_lock); INIT_LIST_HEAD(&device->client_data_list); INIT_LIST_HEAD(&device->port_list); - refcount_set(&device->refcount, 1); init_completion(&device->unreg_completion); return device; @@ -620,6 +626,7 @@ int ib_register_device(struct ib_device *device, const char *name, goto cg_cleanup; } + refcount_set(&device->refcount, 1); device->reg_state = IB_DEV_REGISTERED; list_for_each_entry(client, &client_list, list) diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index a3ceed3a040a..80debf5982ac 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2579,9 +2579,10 @@ struct ib_device { const struct uapi_definition *driver_def; enum rdma_driver_id driver_id; + /* - * Provides synchronization between device unregistration and netlink - * commands on a device. To be used only by core. + * Positive refcount indicates that the device is currently + * registered and cannot be unregistered. */ refcount_t refcount; struct completion unreg_completion; @@ -3926,6 +3927,25 @@ static inline bool ib_access_writable(int access_flags) int ib_check_mr_status(struct ib_mr *mr, u32 check_mask, struct ib_mr_status *mr_status); +/** + * ib_device_try_get: Hold a registration lock + * device: The device to lock + * + * A device under an active registration lock cannot become unregistered. It + * is only possible to obtain a registration lock on a device that is fully + * registered, otherwise this function returns false. + * + * The registration lock is only necessary for actions which require the + * device to still be registered. Uses that only require the device pointer to + * be valid should use get_device(&ibdev->dev) to hold the memory. + * + */ +static inline bool ib_device_try_get(struct ib_device *dev) +{ + return refcount_inc_not_zero(&dev->refcount); +} + +void ib_device_put(struct ib_device *device); struct net_device *ib_get_net_dev_by_params(struct ib_device *dev, u8 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr); From 951d01b96f174ded6180e7e4e14929ef22e7da7e Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 11 Jan 2019 19:31:24 -0700 Subject: [PATCH 067/525] IB/mlx5: Fix how advise_mr() launches async work Work must hold a kref on the ib_device otherwise the dev pointer can become free before the work runs. This can happen because the work is being pushed onto the system work queue which is not flushed during driver unregister. Remove the bogus use of 'reg_state': - While in uverbs the reg_state is guaranteed to always be REGISTERED - Testing reg_state with no locking is bogus. Use ib_device_try_get() to get back into a region that prevents unregistration. For now continue with a flow that is similar to the existing code. Fixes: 813e90b1aeaa ("IB/mlx5: Add advise_mr() support") Signed-off-by: Jason Gunthorpe Reviewed-by: Moni Shoua --- drivers/infiniband/hw/mlx5/odp.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 01e0f6200631..4ee32964e1dd 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -1595,10 +1595,12 @@ static void mlx5_ib_prefetch_mr_work(struct work_struct *work) struct prefetch_mr_work *w = container_of(work, struct prefetch_mr_work, work); - if (w->dev->ib_dev.reg_state == IB_DEV_REGISTERED) + if (ib_device_try_get(&w->dev->ib_dev)) { mlx5_ib_prefetch_sg_list(w->dev, w->pf_flags, w->sg_list, w->num_sge); - + ib_device_put(&w->dev->ib_dev); + } + put_device(&w->dev->ib_dev.dev); kfree(w); } @@ -1617,15 +1619,13 @@ int mlx5_ib_advise_mr_prefetch(struct ib_pd *pd, return mlx5_ib_prefetch_sg_list(dev, pf_flags, sg_list, num_sge); - if (dev->ib_dev.reg_state != IB_DEV_REGISTERED) - return -ENODEV; - work = kvzalloc(struct_size(work, sg_list, num_sge), GFP_KERNEL); if (!work) return -ENOMEM; memcpy(work->sg_list, sg_list, num_sge * sizeof(struct ib_sge)); + get_device(&dev->ib_dev.dev); work->dev = dev; work->pf_flags = pf_flags; work->num_sge = num_sge; From 10098709b4ee6f6f19f25ba81d9c6f83518c584c Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Tue, 15 Jan 2019 10:45:43 +0800 Subject: [PATCH 068/525] pinctrl: sunxi: Correct number of IRQ banks on H6 main pin controller The H6 main pin controller has four banks of interrupt-triggering pins. The driver as originally submitted only specified three, but had pin descriptions referencing a fourth bank. This results in a out-of-bounds access into .irq_array of struct sunxi_pinctrl. This however did not result in a crash until v4.20, with commit a66d972465d1 ("devres: Align data[] to ARCH_KMALLOC_MINALIGN"), which changed the alignment of memory region returned by devm_kcalloc(). The increase likely moved the out-of-bounds access into the next, unmapped page. With KASAN on, the bug is quite clear: BUG: KASAN: slab-out-of-bounds in sunxi_pinctrl_init_with_variant+0x49c/0x12b8 Write of size 4 at addr ffff80002c680280 by task swapper/0/1 CPU: 2 PID: 1 Comm: swapper/0 Not tainted 5.0.0-rc1-00016-gc480a5e6a077 #3 Hardware name: OrangePi Lite2 (DT) Call trace: dump_backtrace+0x0/0x220 show_stack+0x14/0x20 dump_stack+0xac/0xd4 print_address_description+0x60/0x25c kasan_report+0x14c/0x1ac __asan_store4+0x80/0xa0 sunxi_pinctrl_init_with_variant+0x49c/0x12b8 h6_pinctrl_probe+0x18/0x20 platform_drv_probe+0x6c/0xc8 really_probe+0x244/0x4b0 driver_probe_device.part.4+0x11c/0x164 __driver_attach+0x120/0x190 bus_for_each_dev+0xe8/0x158 driver_attach+0x30/0x40 bus_add_driver+0x308/0x318 driver_register+0xbc/0x1d0 __platform_driver_register+0x7c/0x88 h6_pinctrl_driver_init+0x18/0x20 do_one_initcall+0xd4/0x208 kernel_init_freeable+0x230/0x2c8 kernel_init+0x10/0x108 ret_from_fork+0x10/0x1c Allocated by task 1: kasan_kmalloc.part.0+0x4c/0x100 kasan_kmalloc+0xc4/0xe8 kasan_slab_alloc+0x14/0x20 __kmalloc_track_caller+0x130/0x238 devm_kmalloc+0x34/0xd0 sunxi_pinctrl_init_with_variant+0x1d8/0x12b8 h6_pinctrl_probe+0x18/0x20 platform_drv_probe+0x6c/0xc8 really_probe+0x244/0x4b0 driver_probe_device.part.4+0x11c/0x164 __driver_attach+0x120/0x190 bus_for_each_dev+0xe8/0x158 driver_attach+0x30/0x40 bus_add_driver+0x308/0x318 driver_register+0xbc/0x1d0 __platform_driver_register+0x7c/0x88 h6_pinctrl_driver_init+0x18/0x20 do_one_initcall+0xd4/0x208 kernel_init_freeable+0x230/0x2c8 kernel_init+0x10/0x108 ret_from_fork+0x10/0x1c Freed by task 0: (stack is not available) The buggy address belongs to the object at ffff80002c680080 which belongs to the cache kmalloc-512 of size 512 The buggy address is located 0 bytes to the right of 512-byte region [ffff80002c680080, ffff80002c680280) The buggy address belongs to the page: page:ffff7e0000b1a000 count:1 mapcount:0 mapping:ffff80002e00c780 index:0xffff80002c683c80 compound_mapcount: 0 flags: 0x10200(slab|head) raw: 0000000000010200 ffff80002e003a10 ffff80002e003a10 ffff80002e00c780 raw: ffff80002c683c80 0000000000100001 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff80002c680180: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff80002c680200: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffff80002c680280: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ^ ffff80002c680300: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff80002c680380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc Correct the number of IRQ banks so there are no more mismatches. Fixes: c8a830904991 ("pinctrl: sunxi: add support for the Allwinner H6 main pin controller") Cc: Signed-off-by: Chen-Yu Tsai Tested-by: Neil Armstrong Acked-by: Maxime Ripard Signed-off-by: Linus Walleij --- drivers/pinctrl/sunxi/pinctrl-sun50i-h6.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pinctrl/sunxi/pinctrl-sun50i-h6.c b/drivers/pinctrl/sunxi/pinctrl-sun50i-h6.c index aa8b58125568..ef4268cc6227 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sun50i-h6.c +++ b/drivers/pinctrl/sunxi/pinctrl-sun50i-h6.c @@ -588,7 +588,7 @@ static const unsigned int h6_irq_bank_map[] = { 1, 5, 6, 7 }; static const struct sunxi_pinctrl_desc h6_pinctrl_data = { .pins = h6_pins, .npins = ARRAY_SIZE(h6_pins), - .irq_banks = 3, + .irq_banks = 4, .irq_bank_map = h6_irq_bank_map, .irq_read_needs_mux = true, }; From 51d8838d66d3249508940d8f59b07701f2129723 Mon Sep 17 00:00:00 2001 From: Jerry Snitselaar Date: Thu, 17 Jan 2019 12:29:02 -0700 Subject: [PATCH 069/525] iommu/amd: Call free_iova_fast with pfn in map_sg In the error path of map_sg, free_iova_fast is being called with address instead of the pfn. This results in a bad value getting into the rcache, and can result in hitting a BUG_ON when iova_magazine_free_pfns is called. Cc: Joerg Roedel Cc: Suravee Suthikulpanit Signed-off-by: Jerry Snitselaar Fixes: 80187fd39dcb ("iommu/amd: Optimize map_sg and unmap_sg") Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 87ba23a75b38..418df8ff3e50 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -2623,7 +2623,7 @@ out_unmap: } out_free_iova: - free_iova_fast(&dma_dom->iovad, address, npages); + free_iova_fast(&dma_dom->iovad, address >> PAGE_SHIFT, npages); out_err: return 0; From f1724c0883bb0ce93b8dcb94b53dcca3b75ac9a7 Mon Sep 17 00:00:00 2001 From: Jerry Snitselaar Date: Sat, 19 Jan 2019 10:38:05 -0700 Subject: [PATCH 070/525] iommu/amd: Unmap all mapped pages in error path of map_sg In the error path of map_sg there is an incorrect if condition for breaking out of the loop that searches the scatterlist for mapped pages to unmap. Instead of breaking out of the loop once all the pages that were mapped have been unmapped, it will break out of the loop after it has unmapped 1 page. Fix the condition, so it breaks out of the loop only after all the mapped pages have been unmapped. Fixes: 80187fd39dcb ("iommu/amd: Optimize map_sg and unmap_sg") Cc: Joerg Roedel Signed-off-by: Jerry Snitselaar Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 418df8ff3e50..843b825cc1c4 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -2617,7 +2617,7 @@ out_unmap: bus_addr = address + s->dma_address + (j << PAGE_SHIFT); iommu_unmap_page(domain, bus_addr, PAGE_SIZE); - if (--mapped_pages) + if (--mapped_pages == 0) goto out_free_iova; } } From 3a34c986324c07dde32903f7bb262e6138e77c2a Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Wed, 19 Dec 2018 16:16:03 +0800 Subject: [PATCH 071/525] cacheinfo: Keep the old value if of_property_read_u32 fails Commit 448a5a552f336bd7b847b1951 ("drivers: base: cacheinfo: use OF property_read_u32 instead of get_property,read_number") makes cache size and number_of_sets be 0 if DT doesn't provide there values. I think this is unreasonable so make them keep the old values, which is the same as old kernels. Fixes: 448a5a552f33 ("drivers: base: cacheinfo: use OF property_read_u32 instead of get_property,read_number") Cc: stable@vger.kernel.org Signed-off-by: Huacai Chen Reviewed-by: Sudeep Holla Signed-off-by: Greg Kroah-Hartman --- drivers/base/cacheinfo.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c index cf78fa6d470d..a7359535caf5 100644 --- a/drivers/base/cacheinfo.c +++ b/drivers/base/cacheinfo.c @@ -79,8 +79,7 @@ static void cache_size(struct cacheinfo *this_leaf, struct device_node *np) ct_idx = get_cacheinfo_idx(this_leaf->type); propname = cache_type_info[ct_idx].size_prop; - if (of_property_read_u32(np, propname, &this_leaf->size)) - this_leaf->size = 0; + of_property_read_u32(np, propname, &this_leaf->size); } /* not cache_line_size() because that's a macro in include/linux/cache.h */ @@ -114,8 +113,7 @@ static void cache_nr_sets(struct cacheinfo *this_leaf, struct device_node *np) ct_idx = get_cacheinfo_idx(this_leaf->type); propname = cache_type_info[ct_idx].nr_sets_prop; - if (of_property_read_u32(np, propname, &this_leaf->number_of_sets)) - this_leaf->number_of_sets = 0; + of_property_read_u32(np, propname, &this_leaf->number_of_sets); } static void cache_associativity(struct cacheinfo *this_leaf) From 198bc3252ea3a45b0c5d500e6a5b91cfdd08f001 Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Wed, 16 Jan 2019 20:11:44 +0100 Subject: [PATCH 072/525] iommu/vt-d: Fix memory leak in intel_iommu_put_resv_regions() Commit 9d3a4de4cb8d ("iommu: Disambiguate MSI region types") changed the reserved region type in intel_iommu_get_resv_regions() from IOMMU_RESV_RESERVED to IOMMU_RESV_MSI, but it forgot to also change the type in intel_iommu_put_resv_regions(). This leads to a memory leak, because now the check in intel_iommu_put_resv_regions() for IOMMU_RESV_RESERVED will never be true, and no allocated regions will be freed. Fix this by changing the region type in intel_iommu_put_resv_regions() to IOMMU_RESV_MSI, matching the type of the allocated regions. Fixes: 9d3a4de4cb8d ("iommu: Disambiguate MSI region types") Cc: # v4.11+ Signed-off-by: Gerald Schaefer Reviewed-by: Eric Auger Signed-off-by: Joerg Roedel --- drivers/iommu/intel-iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 2bd9ac285c0d..1457f931218e 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -5294,7 +5294,7 @@ static void intel_iommu_put_resv_regions(struct device *dev, struct iommu_resv_region *entry, *next; list_for_each_entry_safe(entry, next, head, list) { - if (entry->type == IOMMU_RESV_RESERVED) + if (entry->type == IOMMU_RESV_MSI) kfree(entry); } } From 13e62626c578d9889ebbda7c521be5adff9bef8e Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Wed, 16 Jan 2019 12:37:23 +0100 Subject: [PATCH 073/525] wlcore: sdio: Fixup power on/off sequence During "wlan-up", we are programming the FW into the WiFi-chip. However, re-programming the FW doesn't work, unless a power cycle of the WiFi-chip is made in-between the programmings. To conform to this requirement and to fix the regression in a simple way, let's start by allowing that the SDIO card (WiFi-chip) may stay powered on (runtime resumed) when wl12xx_sdio_power_off() returns. The intent with the current code is to treat this scenario as an error, but unfortunate this doesn't work as expected, so let's fix this. The other part is to guarantee that a power cycle of the SDIO card has been completed when wl12xx_sdio_power_on() returns, as to allow the FW programming to succeed. However, relying solely on runtime PM to deal with this isn't sufficient. For example, userspace may prevent runtime suspend via sysfs for the device that represents the SDIO card, leading to that the mmc core also keeps it powered on. For this reason, let's instead do a brute force power cycle in wl12xx_sdio_power_on(). Fixes: 728a9dc61f13 ("wlcore: sdio: Fix flakey SDIO runtime PM handling") Signed-off-by: Ulf Hansson Tested-by: Tony Lindgren Tested-by: Anders Roxell Signed-off-by: Ulf Hansson Signed-off-by: Kalle Valo --- drivers/net/wireless/ti/wlcore/sdio.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/net/wireless/ti/wlcore/sdio.c b/drivers/net/wireless/ti/wlcore/sdio.c index bd10165d7eec..4d4b07701149 100644 --- a/drivers/net/wireless/ti/wlcore/sdio.c +++ b/drivers/net/wireless/ti/wlcore/sdio.c @@ -164,6 +164,12 @@ static int wl12xx_sdio_power_on(struct wl12xx_sdio_glue *glue) } sdio_claim_host(func); + /* + * To guarantee that the SDIO card is power cycled, as required to make + * the FW programming to succeed, let's do a brute force HW reset. + */ + mmc_hw_reset(card->host); + sdio_enable_func(func); sdio_release_host(func); @@ -174,20 +180,13 @@ static int wl12xx_sdio_power_off(struct wl12xx_sdio_glue *glue) { struct sdio_func *func = dev_to_sdio_func(glue->dev); struct mmc_card *card = func->card; - int error; sdio_claim_host(func); sdio_disable_func(func); sdio_release_host(func); /* Let runtime PM know the card is powered off */ - error = pm_runtime_put(&card->dev); - if (error < 0 && error != -EBUSY) { - dev_err(&card->dev, "%s failed: %i\n", __func__, error); - - return error; - } - + pm_runtime_put(&card->dev); return 0; } From 752bcf80f5549c9901b2e8bc77b2138de55b1026 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 18 Jan 2019 13:58:17 +0100 Subject: [PATCH 074/525] bpftool: Fix prog dump by tag Lance reported an issue with bpftool not being able to dump program if there are more programs loaded and you want to dump any but the first program, like: # bpftool prog 28: kprobe name trace_req_start tag 1dfc28ba8b3dd597 gpl loaded_at 2019-01-18T17:02:40+1100 uid 0 xlated 112B jited 109B memlock 4096B map_ids 13 29: kprobe name trace_req_compl tag 5b6a5ecc6030a683 gpl loaded_at 2019-01-18T17:02:40+1100 uid 0 xlated 928B jited 575B memlock 4096B map_ids 13,14 # bpftool prog dum jited tag 1dfc28ba8b3dd597 0: push %rbp 1: mov %rsp,%rbp ... # bpftool prog dum jited tag 5b6a5ecc6030a683 Error: can't get prog info (29): Bad address The problem is in the prog_fd_by_tag function not cleaning the struct bpf_prog_info before another request, so the previous program length is still in there and kernel assumes it needs to dump the program, which fails because there's no user pointer set. Moving the struct bpf_prog_info declaration into the loop, so it gets cleaned before each query. Fixes: 71bb428fe2c1 ("tools: bpf: add bpftool") Reported-by: Lance Digby Signed-off-by: Jiri Olsa Reviewed-by: Quentin Monnet Acked-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- tools/bpf/bpftool/prog.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 2d1bb7d6ff51..b54ed82b9589 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -78,13 +78,14 @@ static void print_boot_time(__u64 nsecs, char *buf, unsigned int size) static int prog_fd_by_tag(unsigned char *tag) { - struct bpf_prog_info info = {}; - __u32 len = sizeof(info); unsigned int id = 0; int err; int fd; while (true) { + struct bpf_prog_info info = {}; + __u32 len = sizeof(info); + err = bpf_prog_get_next_id(id, &id); if (err) { p_err("%s", strerror(errno)); From b0ca5ecb8e2279d706261f525f1bd0ba9e3fe800 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 21 Jan 2019 12:36:12 +0100 Subject: [PATCH 075/525] bpftool: fix percpu maps updating When updating a percpu map, bpftool currently copies the provided value only into the first per CPU copy of the specified value, all others instances are left zeroed. This change explicitly copies the user-provided bytes to all the per CPU instances, keeping the sub-command syntax unchanged. v2 -> v3: - drop unused argument, as per Quentin's suggestion v1 -> v2: - rename the helper as per Quentin's suggestion Fixes: 71bb428fe2c1 ("tools: bpf: add bpftool") Signed-off-by: Paolo Abeni Reviewed-by: Quentin Monnet Signed-off-by: Daniel Borkmann --- tools/bpf/bpftool/map.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index 2037e3dc864b..29a3468c6cf6 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -347,6 +347,20 @@ static char **parse_bytes(char **argv, const char *name, unsigned char *val, return argv + i; } +/* on per cpu maps we must copy the provided value on all value instances */ +static void fill_per_cpu_value(struct bpf_map_info *info, void *value) +{ + unsigned int i, n, step; + + if (!map_is_per_cpu(info->type)) + return; + + n = get_possible_cpus(); + step = round_up(info->value_size, 8); + for (i = 1; i < n; i++) + memcpy(value + i * step, value, info->value_size); +} + static int parse_elem(char **argv, struct bpf_map_info *info, void *key, void *value, __u32 key_size, __u32 value_size, __u32 *flags, __u32 **value_fd) @@ -426,6 +440,8 @@ static int parse_elem(char **argv, struct bpf_map_info *info, argv = parse_bytes(argv, "value", value, value_size); if (!argv) return -1; + + fill_per_cpu_value(info, value); } return parse_elem(argv, info, key, NULL, key_size, value_size, From 6a6a797625b5fe855bf60c798561896e311d58ce Mon Sep 17 00:00:00 2001 From: Biju Das Date: Tue, 22 Jan 2019 15:25:45 +0000 Subject: [PATCH 076/525] ARM: dts: r8a7743: Convert to new LVDS DT bindings The internal LVDS encoder now has DT bindings separate from the DU. Port the device tree over to the new model. Fixes: c6a27fa41fab ("drm: rcar-du: Convert LVDS encoder code to bridge driver") Signed-off-by: Biju Das Reviewed-by: Laurent Pinchart Signed-off-by: Simon Horman --- arch/arm/boot/dts/r8a7743.dtsi | 36 ++++++++++++++++++++++++++++------ 1 file changed, 30 insertions(+), 6 deletions(-) diff --git a/arch/arm/boot/dts/r8a7743.dtsi b/arch/arm/boot/dts/r8a7743.dtsi index 3cc33f7ff7fe..3adc158a40bb 100644 --- a/arch/arm/boot/dts/r8a7743.dtsi +++ b/arch/arm/boot/dts/r8a7743.dtsi @@ -1681,15 +1681,12 @@ du: display@feb00000 { compatible = "renesas,du-r8a7743"; - reg = <0 0xfeb00000 0 0x40000>, - <0 0xfeb90000 0 0x1c>; - reg-names = "du", "lvds.0"; + reg = <0 0xfeb00000 0 0x40000>; interrupts = , ; clocks = <&cpg CPG_MOD 724>, - <&cpg CPG_MOD 723>, - <&cpg CPG_MOD 726>; - clock-names = "du.0", "du.1", "lvds.0"; + <&cpg CPG_MOD 723>; + clock-names = "du.0", "du.1"; status = "disabled"; ports { @@ -1704,6 +1701,33 @@ port@1 { reg = <1>; du_out_lvds0: endpoint { + remote-endpoint = <&lvds0_in>; + }; + }; + }; + }; + + lvds0: lvds@feb90000 { + compatible = "renesas,r8a7743-lvds"; + reg = <0 0xfeb90000 0 0x1c>; + clocks = <&cpg CPG_MOD 726>; + power-domains = <&sysc R8A7743_PD_ALWAYS_ON>; + resets = <&cpg 726>; + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + lvds0_in: endpoint { + remote-endpoint = <&du_out_lvds0>; + }; + }; + port@1 { + reg = <1>; + lvds0_out: endpoint { }; }; }; From c9e4576743eeda8d24dedc164d65b78877f9a98c Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Wed, 23 Jan 2019 12:37:19 +0800 Subject: [PATCH 077/525] bpf: sock recvbuff must be limited by rmem_max in bpf_setsockopt() When sock recvbuff is set by bpf_setsockopt(), the value must by limited by rmem_max. It is the same with sendbuff. Fixes: 8c4b4c7e9ff0 ("bpf: Add setsockopt helper function to bpf") Signed-off-by: Yafang Shao Acked-by: Martin KaFai Lau Acked-by: Lawrence Brakmo Signed-off-by: Daniel Borkmann --- net/core/filter.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/core/filter.c b/net/core/filter.c index 7559d6835ecb..7a54dc11ac2d 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4112,10 +4112,12 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, /* Only some socketops are supported */ switch (optname) { case SO_RCVBUF: + val = min_t(u32, val, sysctl_rmem_max); sk->sk_userlocks |= SOCK_RCVBUF_LOCK; sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF); break; case SO_SNDBUF: + val = min_t(u32, val, sysctl_wmem_max); sk->sk_userlocks |= SOCK_SNDBUF_LOCK; sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF); break; From da5d2748e4a4512237764d2a53bdf686eccee18b Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 23 Jan 2019 08:46:29 +0100 Subject: [PATCH 078/525] iommu/mediatek: Use correct fwspec in mtk_iommu_add_device() The mtk_iommu_add_device() function keeps the fwspec in an on-stack pointer and calls mtk_iommu_create_mapping(), which might change its source, dev->iommu_fwspec. This causes the on-stack pointer to be obsoleted and the device initialization to fail. Update the on-stack fwspec pointer after mtk_iommu_create_mapping() has been called. Reported-by: Frank Wunderlich Fixes: a9bf2eec5a6f ('iommu/mediatek: Use helper functions to access dev->iommu_fwspec') Tested-by: Frank Wunderlich Signed-off-by: Joerg Roedel --- drivers/iommu/mtk_iommu_v1.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index 6ede4286b835..f60bdb85c4c0 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -442,6 +442,10 @@ static int mtk_iommu_add_device(struct device *dev) iommu_spec.args_count = count; mtk_iommu_create_mapping(dev, &iommu_spec); + + /* dev->iommu_fwspec might have changed */ + fwspec = dev_iommu_fwspec_get(dev); + of_node_put(iommu_spec.np); } From 5fa98c2eda35fcd1a1d91a9785c390f54688240c Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 22 Jan 2019 09:10:10 -0600 Subject: [PATCH 079/525] dt-bindings: Fix dt_binding_check target for in tree builds On in tree builds, subsequent builds will incorrectly include the intermediate file 'processed-schema.yaml' with the input schema files resulting in a build error. Update the find command to ignore processed-schema.yaml. Signed-off-by: Rob Herring --- Documentation/devicetree/bindings/Makefile | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/Makefile b/Documentation/devicetree/bindings/Makefile index 6e5cef0ed6fb..50daa0b3b032 100644 --- a/Documentation/devicetree/bindings/Makefile +++ b/Documentation/devicetree/bindings/Makefile @@ -17,7 +17,11 @@ extra-y += $(DT_TMP_SCHEMA) quiet_cmd_mk_schema = SCHEMA $@ cmd_mk_schema = $(DT_MK_SCHEMA) $(DT_MK_SCHEMA_FLAGS) -o $@ $(filter-out FORCE, $^) -DT_DOCS = $(shell cd $(srctree)/$(src) && find * -name '*.yaml') +DT_DOCS = $(shell \ + cd $(srctree)/$(src) && \ + find * \( -name '*.yaml' ! -name $(DT_TMP_SCHEMA) \) \ + ) + DT_SCHEMA_FILES ?= $(addprefix $(src)/,$(DT_DOCS)) extra-y += $(patsubst $(src)/%.yaml,%.example.dts, $(DT_SCHEMA_FILES)) From 2486e67374aa8b7854c2de32869642c2873b3d53 Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Wed, 9 Jan 2019 11:11:24 +0200 Subject: [PATCH 080/525] gpio: pcf857x: Fix interrupts on multiple instances When multiple instances of pcf857x chips are present, a fix up message [1] is printed during the probe of the 2nd and later instances. The issue is that the driver is using the same irq_chip data structure between multiple instances. Fix this by allocating the irq_chip data structure per instance. [1] fix up message addressed by this patch [ 1.212100] gpio gpiochip9: (pcf8575): detected irqchip that is shared with multiple gpiochips: please fix the driver. Cc: Stable Signed-off-by: Roger Quadros Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-pcf857x.c | 26 ++++++++++++-------------- 1 file changed, 12 insertions(+), 14 deletions(-) diff --git a/drivers/gpio/gpio-pcf857x.c b/drivers/gpio/gpio-pcf857x.c index adf72dda25a2..68a35b65925a 100644 --- a/drivers/gpio/gpio-pcf857x.c +++ b/drivers/gpio/gpio-pcf857x.c @@ -84,6 +84,7 @@ MODULE_DEVICE_TABLE(of, pcf857x_of_table); */ struct pcf857x { struct gpio_chip chip; + struct irq_chip irqchip; struct i2c_client *client; struct mutex lock; /* protect 'out' */ unsigned out; /* software latch */ @@ -252,18 +253,6 @@ static void pcf857x_irq_bus_sync_unlock(struct irq_data *data) mutex_unlock(&gpio->lock); } -static struct irq_chip pcf857x_irq_chip = { - .name = "pcf857x", - .irq_enable = pcf857x_irq_enable, - .irq_disable = pcf857x_irq_disable, - .irq_ack = noop, - .irq_mask = noop, - .irq_unmask = noop, - .irq_set_wake = pcf857x_irq_set_wake, - .irq_bus_lock = pcf857x_irq_bus_lock, - .irq_bus_sync_unlock = pcf857x_irq_bus_sync_unlock, -}; - /*-------------------------------------------------------------------------*/ static int pcf857x_probe(struct i2c_client *client, @@ -376,8 +365,17 @@ static int pcf857x_probe(struct i2c_client *client, /* Enable irqchip if we have an interrupt */ if (client->irq) { + gpio->irqchip.name = "pcf857x", + gpio->irqchip.irq_enable = pcf857x_irq_enable, + gpio->irqchip.irq_disable = pcf857x_irq_disable, + gpio->irqchip.irq_ack = noop, + gpio->irqchip.irq_mask = noop, + gpio->irqchip.irq_unmask = noop, + gpio->irqchip.irq_set_wake = pcf857x_irq_set_wake, + gpio->irqchip.irq_bus_lock = pcf857x_irq_bus_lock, + gpio->irqchip.irq_bus_sync_unlock = pcf857x_irq_bus_sync_unlock, status = gpiochip_irqchip_add_nested(&gpio->chip, - &pcf857x_irq_chip, + &gpio->irqchip, 0, handle_level_irq, IRQ_TYPE_NONE); if (status) { @@ -392,7 +390,7 @@ static int pcf857x_probe(struct i2c_client *client, if (status) goto fail; - gpiochip_set_nested_irqchip(&gpio->chip, &pcf857x_irq_chip, + gpiochip_set_nested_irqchip(&gpio->chip, &gpio->irqchip, client->irq); gpio->irq_parent = client->irq; } From 1033be58992f818dc564196ded2bcc3f360bc297 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 4 Jan 2019 11:24:20 +0100 Subject: [PATCH 081/525] gpiolib: fix line event timestamps for nested irqs Nested interrupts run inside the calling thread's context and the top half handler is never called which means that we never read the timestamp. This issue came up when trying to read line events from a gpiochip using regmap_irq_chip for interrupts. Fix it by reading the timestamp from the irq thread function if it's still 0 by the time the second handler is called. Fixes: d58f2bf261fd ("gpio: Timestamp events in hardirq handler") Cc: stable@vger.kernel.org Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpiolib.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 1651d7f0a303..d1adfdf50fb3 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -828,7 +828,14 @@ static irqreturn_t lineevent_irq_thread(int irq, void *p) /* Do not leak kernel stack to userspace */ memset(&ge, 0, sizeof(ge)); - ge.timestamp = le->timestamp; + /* + * We may be running from a nested threaded interrupt in which case + * we didn't get the timestamp from lineevent_irq_handler(). + */ + if (!le->timestamp) + ge.timestamp = ktime_get_real_ns(); + else + ge.timestamp = le->timestamp; if (le->eflags & GPIOEVENT_REQUEST_RISING_EDGE && le->eflags & GPIOEVENT_REQUEST_FALLING_EDGE) { From 09d158d52d2bceda736797a61b6c13d7fc83707b Mon Sep 17 00:00:00 2001 From: Neo Hou Date: Wed, 16 Jan 2019 13:06:13 +0800 Subject: [PATCH 082/525] gpio: sprd: Fix the incorrect data register Since differnt type EICs have its own data register to read, thus fix the incorrect data register. Fixes: 25518e024e3a ("gpio: Add Spreadtrum EIC driver support") Cc: Signed-off-by: Neo Hou Signed-off-by: Baolin Wang Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-eic-sprd.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/drivers/gpio/gpio-eic-sprd.c b/drivers/gpio/gpio-eic-sprd.c index e0d6a0a7bc69..257df59815c9 100644 --- a/drivers/gpio/gpio-eic-sprd.c +++ b/drivers/gpio/gpio-eic-sprd.c @@ -180,7 +180,18 @@ static void sprd_eic_free(struct gpio_chip *chip, unsigned int offset) static int sprd_eic_get(struct gpio_chip *chip, unsigned int offset) { - return sprd_eic_read(chip, offset, SPRD_EIC_DBNC_DATA); + struct sprd_eic *sprd_eic = gpiochip_get_data(chip); + + switch (sprd_eic->type) { + case SPRD_EIC_DEBOUNCE: + return sprd_eic_read(chip, offset, SPRD_EIC_DBNC_DATA); + case SPRD_EIC_ASYNC: + return sprd_eic_read(chip, offset, SPRD_EIC_ASYNC_DATA); + case SPRD_EIC_SYNC: + return sprd_eic_read(chip, offset, SPRD_EIC_SYNC_DATA); + default: + return -ENOTSUPP; + } } static int sprd_eic_direction_input(struct gpio_chip *chip, unsigned int offset) From f785ffb61605734b518afa766d1b5445e9f38c8d Mon Sep 17 00:00:00 2001 From: Neo Hou Date: Wed, 16 Jan 2019 13:06:14 +0800 Subject: [PATCH 083/525] gpio: sprd: Fix incorrect irq type setting for the async EIC When setting async EIC as IRQ_TYPE_EDGE_BOTH type, we missed to set the SPRD_EIC_ASYNC_INTMODE register to 0, which means detecting edge signals. Thus this patch fixes the issue. Fixes: 25518e024e3a ("gpio: Add Spreadtrum EIC driver support") Cc: Signed-off-by: Neo Hou Signed-off-by: Baolin Wang Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-eic-sprd.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpio/gpio-eic-sprd.c b/drivers/gpio/gpio-eic-sprd.c index 257df59815c9..e41223c05f6e 100644 --- a/drivers/gpio/gpio-eic-sprd.c +++ b/drivers/gpio/gpio-eic-sprd.c @@ -379,6 +379,7 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type) irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_EDGE_BOTH: + sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 1); irq_set_handler_locked(data, handle_edge_irq); break; From 2095a45e345e669ea77a9b34bdd7de5ceb422f93 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Wed, 23 Jan 2019 08:00:57 +0800 Subject: [PATCH 084/525] gpio: altera-a10sr: Set proper output level for direction_output The altr_a10sr_gpio_direction_output should set proper output level based on the value argument. Fixes: 26a48c4cc2f1 ("gpio: altera-a10sr: Add A10 System Resource Chip GPIO support.") Cc: Signed-off-by: Axel Lin Tested by: Thor Thayer Reviewed by: Thor Thayer Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-altera-a10sr.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpio/gpio-altera-a10sr.c b/drivers/gpio/gpio-altera-a10sr.c index 6b11f1314248..7f9e0304b510 100644 --- a/drivers/gpio/gpio-altera-a10sr.c +++ b/drivers/gpio/gpio-altera-a10sr.c @@ -66,8 +66,10 @@ static int altr_a10sr_gpio_direction_input(struct gpio_chip *gc, static int altr_a10sr_gpio_direction_output(struct gpio_chip *gc, unsigned int nr, int value) { - if (nr <= (ALTR_A10SR_OUT_VALID_RANGE_HI - ALTR_A10SR_LED_VALID_SHIFT)) + if (nr <= (ALTR_A10SR_OUT_VALID_RANGE_HI - ALTR_A10SR_LED_VALID_SHIFT)) { + altr_a10sr_gpio_set(gc, nr, value); return 0; + } return -EINVAL; } From ba16adeb346387eb2d1ada69003588be96f098fa Mon Sep 17 00:00:00 2001 From: Peng Hao Date: Sat, 29 Dec 2018 13:10:06 +0800 Subject: [PATCH 085/525] ARM: pxa: ssp: unneeded to free devm_ allocated data devm_ allocated data will be automatically freed. The free of devm_ allocated data is invalid. Fixes: 1c459de1e645 ("ARM: pxa: ssp: use devm_ functions") Signed-off-by: Peng Hao [title's prefix changed] Signed-off-by: Robert Jarzmik --- arch/arm/plat-pxa/ssp.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/arm/plat-pxa/ssp.c b/arch/arm/plat-pxa/ssp.c index ed36dcab80f1..f51919974183 100644 --- a/arch/arm/plat-pxa/ssp.c +++ b/arch/arm/plat-pxa/ssp.c @@ -190,8 +190,6 @@ static int pxa_ssp_remove(struct platform_device *pdev) if (ssp == NULL) return -ENODEV; - iounmap(ssp->mmio_base); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); release_mem_region(res->start, resource_size(res)); @@ -201,7 +199,6 @@ static int pxa_ssp_remove(struct platform_device *pdev) list_del(&ssp->node); mutex_unlock(&ssp_lock); - kfree(ssp); return 0; } From 99fd6e875d0c24448a5e2c241422a691be46b241 Mon Sep 17 00:00:00 2001 From: Vincent Chen Date: Thu, 3 Jan 2019 11:32:33 +0800 Subject: [PATCH 086/525] RISC-V: Add _TIF_NEED_RESCHED check for kernel thread when CONFIG_PREEMPT=y The cond_resched() can be used to yield the CPU resource if CONFIG_PREEMPT is not defined. Otherwise, cond_resched() is a dummy function. In order to avoid kernel thread occupying entire CPU, when CONFIG_PREEMPT=y, the kernel thread needs to follow the rescheduling mechanism like a user thread. Signed-off-by: Vincent Chen Tested-by: Guenter Roeck Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/asm-offsets.c | 1 + arch/riscv/kernel/entry.S | 18 +++++++++++++++++- 2 files changed, 18 insertions(+), 1 deletion(-) diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c index 6a92a2fe198e..dac98348c6a3 100644 --- a/arch/riscv/kernel/asm-offsets.c +++ b/arch/riscv/kernel/asm-offsets.c @@ -39,6 +39,7 @@ void asm_offsets(void) OFFSET(TASK_STACK, task_struct, stack); OFFSET(TASK_TI, task_struct, thread_info); OFFSET(TASK_TI_FLAGS, task_struct, thread_info.flags); + OFFSET(TASK_TI_PREEMPT_COUNT, task_struct, thread_info.preempt_count); OFFSET(TASK_TI_KERNEL_SP, task_struct, thread_info.kernel_sp); OFFSET(TASK_TI_USER_SP, task_struct, thread_info.user_sp); OFFSET(TASK_TI_CPU, task_struct, thread_info.cpu); diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 355166f57205..fd9b57c8b4ce 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -144,6 +144,10 @@ _save_context: REG_L x2, PT_SP(sp) .endm +#if !IS_ENABLED(CONFIG_PREEMPT) +.set resume_kernel, restore_all +#endif + ENTRY(handle_exception) SAVE_ALL @@ -228,7 +232,7 @@ ret_from_exception: REG_L s0, PT_SSTATUS(sp) csrc sstatus, SR_SIE andi s0, s0, SR_SPP - bnez s0, restore_all + bnez s0, resume_kernel resume_userspace: /* Interrupts must be disabled here so flags are checked atomically */ @@ -250,6 +254,18 @@ restore_all: RESTORE_ALL sret +#if IS_ENABLED(CONFIG_PREEMPT) +resume_kernel: + REG_L s0, TASK_TI_PREEMPT_COUNT(tp) + bnez s0, restore_all +need_resched: + REG_L s0, TASK_TI_FLAGS(tp) + andi s0, s0, _TIF_NEED_RESCHED + beqz s0, restore_all + call preempt_schedule_irq + j need_resched +#endif + work_pending: /* Enter slow path for supplementary processing */ la ra, ret_from_exception From 2bb10639f12c925faeed8b4c3678fb92f97b90b7 Mon Sep 17 00:00:00 2001 From: Andreas Schwab Date: Mon, 7 Jan 2019 15:16:35 +0100 Subject: [PATCH 087/525] RISC-V: fix bad use of of_node_put of_find_node_by_type already calls of_node_put, don't call it again. Fixes: 94f9bf118f ("RISC-V: Fix of_node_* refcount") Signed-off-by: Andreas Schwab Reviewed-by: Atish Patra Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/smpboot.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index fc185ecabb0a..18cda0e8cf94 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -57,15 +57,12 @@ void __init setup_smp(void) while ((dn = of_find_node_by_type(dn, "cpu"))) { hart = riscv_of_processor_hartid(dn); - if (hart < 0) { - of_node_put(dn); + if (hart < 0) continue; - } if (hart == cpuid_to_hartid_map(0)) { BUG_ON(found_boot_cpu); found_boot_cpu = 1; - of_node_put(dn); continue; } @@ -73,7 +70,6 @@ void __init setup_smp(void) set_cpu_possible(cpuid, true); set_cpu_present(cpuid, true); cpuid++; - of_node_put(dn); } BUG_ON(!found_boot_cpu); From 8581f38742cf98f55e53a384a2612a1171b3600a Mon Sep 17 00:00:00 2001 From: Antony Pavlov Date: Tue, 8 Jan 2019 22:45:38 +0300 Subject: [PATCH 088/525] RISC-V: asm/page.h: fix spelling mistake "CONFIG_64BITS" -> "CONFIG_64BIT" There is no CONFIG_64BITS Kconfig macro. Please see arch/riscv/Kconfig for details, e.g. linux$ git grep -HnA 1 "config 64BIT" arch/riscv/Kconfig arch/riscv/Kconfig:6:config 64BIT arch/riscv/Kconfig-7- bool Signed-off-by: Antony Pavlov Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/page.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 06cfbb3aacbb..2a546a52f02a 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -80,7 +80,7 @@ typedef struct page *pgtable_t; #define __pgd(x) ((pgd_t) { (x) }) #define __pgprot(x) ((pgprot_t) { (x) }) -#ifdef CONFIG_64BITS +#ifdef CONFIG_64BIT #define PTE_FMT "%016lx" #else #define PTE_FMT "%08lx" From 86cca81a31cdc6f1f292b5b0c6a4e7e06863cdc9 Mon Sep 17 00:00:00 2001 From: Antony Pavlov Date: Tue, 8 Jan 2019 22:45:57 +0300 Subject: [PATCH 089/525] RISC-V: Kconfig: fix spelling mistake "traget" -> "target" Signed-off-by: Antony Pavlov Reviewed-by: Christoph Hellwig Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index feeeaa60697c..515fc3cc9687 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -103,7 +103,7 @@ choice prompt "Base ISA" default ARCH_RV64I help - This selects the base ISA that this kernel will traget and must match + This selects the base ISA that this kernel will target and must match the target platform. config ARCH_RV32I From a37ead8f2efb1595c15079eddac2672630f750ea Mon Sep 17 00:00:00 2001 From: Palmer Dabbelt Date: Wed, 23 Jan 2019 12:59:17 -0800 Subject: [PATCH 090/525] RISC-V: defconfig: Move CONFIG_PCI{,E_XILINX} eb01d42a7778 ("PCI: consolidate PCI config entry in drivers/pci") reorganized the PCI-related Kconfig entries and resulted in a diff in our defconfig. This simply removes the diff. Signed-off-by: Palmer Dabbelt --- arch/riscv/configs/defconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index f399659d3b8d..658be23fa2c6 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -13,8 +13,6 @@ CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y CONFIG_BPF_SYSCALL=y CONFIG_SMP=y -CONFIG_PCI=y -CONFIG_PCIE_XILINX=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_NET=y @@ -28,6 +26,8 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_IP_PNP_RARP=y CONFIG_NETLINK_DIAG=y +CONFIG_PCI=y +CONFIG_PCIE_XILINX=y CONFIG_DEVTMPFS=y CONFIG_BLK_DEV_LOOP=y CONFIG_VIRTIO_BLK=y From e4cf9e47ab244977d12513bb4610a44f88ad5e68 Mon Sep 17 00:00:00 2001 From: Alistair Francis Date: Sat, 12 Jan 2019 00:41:26 +0000 Subject: [PATCH 091/525] RISC-V: defconfig: Enable Generic PCIE by default Enable generic PCIe by default in the RISC-V defconfig, this allows us to use QEMU's PCIe support out of the box. CONFIG_RAS=y is automatically selected by generic PCIe, so it has been dropped from the defconfig. Signed-off-by: Alistair Francis [Palmer: Split out PCIE_XILINX and CRYPTO_DEV_VIRTIO] Signed-off-by: Palmer Dabbelt --- arch/riscv/configs/defconfig | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index 658be23fa2c6..01fe50707d98 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -27,6 +27,8 @@ CONFIG_IP_PNP_BOOTP=y CONFIG_IP_PNP_RARP=y CONFIG_NETLINK_DIAG=y CONFIG_PCI=y +CONFIG_PCIEPORTBUS=y +CONFIG_PCI_HOST_GENERIC=y CONFIG_PCIE_XILINX=y CONFIG_DEVTMPFS=y CONFIG_BLK_DEV_LOOP=y @@ -63,7 +65,6 @@ CONFIG_USB_STORAGE=y CONFIG_USB_UAS=y CONFIG_VIRTIO_MMIO=y CONFIG_SIFIVE_PLIC=y -CONFIG_RAS=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_AUTOFS4_FS=y From 2a200fb9fb124e2889516c4668c5483bf7107044 Mon Sep 17 00:00:00 2001 From: Palmer Dabbelt Date: Wed, 23 Jan 2019 14:09:01 -0800 Subject: [PATCH 092/525] RISC-V: defconfig: Add CRYPTO_DEV_VIRTIO=y This allows acceleration of cryptography inside QEMU. Signed-off-by: Palmer Dabbelt --- arch/riscv/configs/defconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index 01fe50707d98..2fd3461e50ab 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -78,5 +78,6 @@ CONFIG_NFS_V4_1=y CONFIG_NFS_V4_2=y CONFIG_ROOT_NFS=y CONFIG_CRYPTO_USER_API_HASH=y +CONFIG_CRYPTO_DEV_VIRTIO=y CONFIG_PRINTK_TIME=y # CONFIG_RCU_TRACE is not set From a19f74708ef693d7ddc3ee577a458b6807d43e5b Mon Sep 17 00:00:00 2001 From: Andreas Schwab Date: Thu, 10 Jan 2019 18:11:39 +0100 Subject: [PATCH 093/525] tty/serial: use uart_console_write in the RISC-V SBL early console This enables proper NLCR processing. Suggested-by: Anup Patel Signed-off-by: Andreas Schwab Reviewed-by: Anup Patel Reviewed-by: Christoph Hellwig Signed-off-by: Palmer Dabbelt --- drivers/tty/serial/earlycon-riscv-sbi.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/tty/serial/earlycon-riscv-sbi.c b/drivers/tty/serial/earlycon-riscv-sbi.c index e1a551aae336..ce81523c3113 100644 --- a/drivers/tty/serial/earlycon-riscv-sbi.c +++ b/drivers/tty/serial/earlycon-riscv-sbi.c @@ -10,13 +10,16 @@ #include #include -static void sbi_console_write(struct console *con, - const char *s, unsigned int n) +static void sbi_putc(struct uart_port *port, int c) { - int i; + sbi_console_putchar(c); +} - for (i = 0; i < n; ++i) - sbi_console_putchar(s[i]); +static void sbi_console_write(struct console *con, + const char *s, unsigned n) +{ + struct earlycon_device *dev = con->data; + uart_console_write(&dev->port, s, n, sbi_putc); } static int __init early_sbi_setup(struct earlycon_device *device, From 5b90df44fd9b415d8c5d11b92746212a63d3c47f Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Wed, 9 Jan 2019 20:01:56 +0100 Subject: [PATCH 094/525] ARM: dts: omap3-gta04: Fix graph_port warning We're currently getting a warning with make dtbs: arch/arm/boot/dts/omap3-gta04.dtsi:720.7-727.4: Warning (graph_port): /ocp@68000000/dss@48050000/encoder@48050c0 0/port: graph node unit address error, expected "0" Tested-by: H. Nikolaus Schaller Acked-by: Rob Herring Signed-off-by: H. Nikolaus Schaller Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/omap3-gta04.dtsi | 4 ---- 1 file changed, 4 deletions(-) diff --git a/arch/arm/boot/dts/omap3-gta04.dtsi b/arch/arm/boot/dts/omap3-gta04.dtsi index e53d32691308..93b420934e8e 100644 --- a/arch/arm/boot/dts/omap3-gta04.dtsi +++ b/arch/arm/boot/dts/omap3-gta04.dtsi @@ -714,11 +714,7 @@ vdda-supply = <&vdac>; - #address-cells = <1>; - #size-cells = <0>; - port { - reg = <0>; venc_out: endpoint { remote-endpoint = <&opa_in>; ti,channels = <1>; From ac9c908eecde3ed252cb1d67fc79b3c1346f76bc Mon Sep 17 00:00:00 2001 From: Arthur Demchenkov Date: Mon, 21 Jan 2019 06:21:09 +0300 Subject: [PATCH 095/525] ARM: dts: n900: fix mmc1 card detect gpio polarity Wrong polarity of card detect GPIO pin leads to the system not booting from external mmc, if the back cover of N900 is closed. When the cover is open the system boots fine. This wasn't noticed before, because of a bug, which was fixed by commit e63201f19 (mmc: omap_hsmmc: Delete platform data GPIO CD and WP). Kernels up to 4.19 ignored the card detect GPIO from DT. Fixes: e63201f19438 ("mmc: omap_hsmmc: Delete platform data GPIO CD and WP") Signed-off-by: Arthur Demchenkov Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/omap3-n900.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts index 182a53991c90..826920e6b878 100644 --- a/arch/arm/boot/dts/omap3-n900.dts +++ b/arch/arm/boot/dts/omap3-n900.dts @@ -814,7 +814,7 @@ /* For debugging, it is often good idea to remove this GPIO. It means you can remove back cover (to reboot by removing battery) and still use the MMC card. */ - cd-gpios = <&gpio6 0 GPIO_ACTIVE_HIGH>; /* 160 */ + cd-gpios = <&gpio6 0 GPIO_ACTIVE_LOW>; /* 160 */ }; /* most boards use vaux3, only some old versions use vmmc2 instead */ From 063c20e12f8bbbc10cabc2413606b140085beb62 Mon Sep 17 00:00:00 2001 From: Heiko Schocher Date: Tue, 22 Jan 2019 06:26:23 +0100 Subject: [PATCH 096/525] ARM: dts: am335x-shc.dts: fix wrong cd pin level cd pin on mmc1 is GPIO_ACTIVE_LOW not GPIO_ACTIVE_HIGH Fixes: e63201f19438 ("mmc: omap_hsmmc: Delete platform data GPIO CD and WP") Signed-off-by: Heiko Schocher Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/am335x-shc.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/am335x-shc.dts b/arch/arm/boot/dts/am335x-shc.dts index d0fd68873689..5b250060f6dd 100644 --- a/arch/arm/boot/dts/am335x-shc.dts +++ b/arch/arm/boot/dts/am335x-shc.dts @@ -215,7 +215,7 @@ pinctrl-names = "default"; pinctrl-0 = <&mmc1_pins>; bus-width = <0x4>; - cd-gpios = <&gpio0 6 GPIO_ACTIVE_HIGH>; + cd-gpios = <&gpio0 6 GPIO_ACTIVE_LOW>; cd-inverted; max-frequency = <26000000>; vmmc-supply = <&vmmcsd_fixed>; From 28198c4639b39899a728ac89aea29d2a7a72562f Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Sat, 12 Jan 2019 16:16:27 +0800 Subject: [PATCH 097/525] riscv: fixup max_low_pfn with PFN_DOWN. max_low_pfn should be pfn_size not byte_size. Signed-off-by: Guo Ren Signed-off-by: Mao Han Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/setup.c | 2 +- arch/riscv/mm/init.c | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 6e079e94b638..77564310235f 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -181,7 +181,7 @@ static void __init setup_bootmem(void) BUG_ON(mem_size == 0); set_max_mapnr(PFN_DOWN(mem_size)); - max_low_pfn = memblock_end_of_DRAM(); + max_low_pfn = PFN_DOWN(memblock_end_of_DRAM()); #ifdef CONFIG_BLK_DEV_INITRD setup_initrd(); diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 1d9bfaff60bc..658ebf645f42 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -28,7 +28,8 @@ static void __init zone_sizes_init(void) unsigned long max_zone_pfns[MAX_NR_ZONES] = { 0, }; #ifdef CONFIG_ZONE_DMA32 - max_zone_pfns[ZONE_DMA32] = PFN_DOWN(min(4UL * SZ_1G, max_low_pfn)); + max_zone_pfns[ZONE_DMA32] = PFN_DOWN(min(4UL * SZ_1G, + (unsigned long) PFN_PHYS(max_low_pfn))); #endif max_zone_pfns[ZONE_NORMAL] = max_low_pfn; From a2fcd5c84f7a7825e028381b10182439067aa90d Mon Sep 17 00:00:00 2001 From: Tina Zhang Date: Wed, 23 Jan 2019 15:28:59 +0800 Subject: [PATCH 098/525] drm/modes: Prevent division by zero htotal This patch prevents division by zero htotal. In a follow-up mail Tina writes: > > How did you manage to get here with htotal == 0? This needs backtraces (or if > > this is just about static checkers, a mention of that). > > -Daniel > > In GVT-g, we are trying to enable a virtual display w/o setting timings for a pipe > (a.k.a htotal=0), then we met the following kernel panic: > > [ 32.832048] divide error: 0000 [#1] SMP PTI > [ 32.833614] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.18.0-rc4-sriov+ #33 > [ 32.834438] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.10.1-0-g8891697-dirty-20180511_165818-tinazhang-linux-1 04/01/2014 > [ 32.835901] RIP: 0010:drm_mode_hsync+0x1e/0x40 > [ 32.836004] Code: 31 c0 c3 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 8b 87 d8 00 00 00 85 c0 75 22 8b 4f 68 85 c9 78 1b 69 47 58 e8 03 00 00 99 f9 b9 d3 4d 62 10 05 f4 01 00 00 f7 e1 89 d0 c1 e8 06 f3 c3 66 > [ 32.836004] RSP: 0000:ffffc900000ebb90 EFLAGS: 00010206 > [ 32.836004] RAX: 0000000000000000 RBX: ffff88001c67c8a0 RCX: 0000000000000000 > [ 32.836004] RDX: 0000000000000000 RSI: ffff88001c67c000 RDI: ffff88001c67c8a0 > [ 32.836004] RBP: ffff88001c7d03a0 R08: ffff88001c67c8a0 R09: ffff88001c7d0330 > [ 32.836004] R10: ffffffff822c3a98 R11: 0000000000000001 R12: ffff88001c67c000 > [ 32.836004] R13: ffff88001c7d0370 R14: ffffffff8207eb78 R15: ffff88001c67c800 > [ 32.836004] FS: 0000000000000000(0000) GS:ffff88001da00000(0000) knlGS:0000000000000000 > [ 32.836004] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 > [ 32.836004] CR2: 0000000000000000 CR3: 000000000220a000 CR4: 00000000000006f0 > [ 32.836004] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > [ 32.836004] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 > [ 32.836004] Call Trace: > [ 32.836004] intel_mode_from_pipe_config+0x72/0x90 > [ 32.836004] intel_modeset_setup_hw_state+0x569/0xf90 > [ 32.836004] intel_modeset_init+0x905/0x1db0 > [ 32.836004] i915_driver_load+0xb8c/0x1120 > [ 32.836004] i915_pci_probe+0x4d/0xb0 > [ 32.836004] local_pci_probe+0x44/0xa0 > [ 32.836004] ? pci_assign_irq+0x27/0x130 > [ 32.836004] pci_device_probe+0x102/0x1c0 > [ 32.836004] driver_probe_device+0x2b8/0x480 > [ 32.836004] __driver_attach+0x109/0x110 > [ 32.836004] ? driver_probe_device+0x480/0x480 > [ 32.836004] bus_for_each_dev+0x67/0xc0 > [ 32.836004] ? klist_add_tail+0x3b/0x70 > [ 32.836004] bus_add_driver+0x1e8/0x260 > [ 32.836004] driver_register+0x5b/0xe0 > [ 32.836004] ? mipi_dsi_bus_init+0x11/0x11 > [ 32.836004] do_one_initcall+0x4d/0x1eb > [ 32.836004] kernel_init_freeable+0x197/0x237 > [ 32.836004] ? rest_init+0xd0/0xd0 > [ 32.836004] kernel_init+0xa/0x110 > [ 32.836004] ret_from_fork+0x35/0x40 > [ 32.836004] Modules linked in: > [ 32.859183] ---[ end trace 525608b0ed0e8665 ]--- > [ 32.859722] RIP: 0010:drm_mode_hsync+0x1e/0x40 > [ 32.860287] Code: 31 c0 c3 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 8b 87 d8 00 00 00 85 c0 75 22 8b 4f 68 85 c9 78 1b 69 47 58 e8 03 00 00 99 f9 b9 d3 4d 62 10 05 f4 01 00 00 f7 e1 89 d0 c1 e8 06 f3 c3 66 > [ 32.862680] RSP: 0000:ffffc900000ebb90 EFLAGS: 00010206 > [ 32.863309] RAX: 0000000000000000 RBX: ffff88001c67c8a0 RCX: 0000000000000000 > [ 32.864182] RDX: 0000000000000000 RSI: ffff88001c67c000 RDI: ffff88001c67c8a0 > [ 32.865206] RBP: ffff88001c7d03a0 R08: ffff88001c67c8a0 R09: ffff88001c7d0330 > [ 32.866359] R10: ffffffff822c3a98 R11: 0000000000000001 R12: ffff88001c67c000 > [ 32.867213] R13: ffff88001c7d0370 R14: ffffffff8207eb78 R15: ffff88001c67c800 > [ 32.868075] FS: 0000000000000000(0000) GS:ffff88001da00000(0000) knlGS:0000000000000000 > [ 32.868983] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 > [ 32.869659] CR2: 0000000000000000 CR3: 000000000220a000 CR4: 00000000000006f0 > [ 32.870599] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > [ 32.871598] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 > [ 32.872549] Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b > > Since drm_mode_hsync() has the logic to check mode->htotal, I just extend it to cover the case htotal==0. Signed-off-by: Tina Zhang Cc: Adam Jackson Cc: Dave Airlie Cc: Daniel Vetter [danvet: Add additional explanations + cc: stable.] Cc: stable@vger.kernel.org Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/1548228539-3061-1-git-send-email-tina.zhang@intel.com --- drivers/gpu/drm/drm_modes.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index 24a750436559..f91e02c87fd8 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -758,7 +758,7 @@ int drm_mode_hsync(const struct drm_display_mode *mode) if (mode->hsync) return mode->hsync; - if (mode->htotal < 0) + if (mode->htotal <= 0) return 0; calc_val = (mode->clock * 1000) / mode->htotal; /* hsync in Hz */ From 53ab60baa1ac4f20b080a22c13b77b6373922fd7 Mon Sep 17 00:00:00 2001 From: ZhangXiaoxu Date: Thu, 10 Jan 2019 16:39:06 +0800 Subject: [PATCH 099/525] ipvs: Fix signed integer overflow when setsockopt timeout There is a UBSAN bug report as below: UBSAN: Undefined behaviour in net/netfilter/ipvs/ip_vs_ctl.c:2227:21 signed integer overflow: -2147483647 * 1000 cannot be represented in type 'int' Reproduce program: #include #include #include #define IPPROTO_IP 0 #define IPPROTO_RAW 255 #define IP_VS_BASE_CTL (64+1024+64) #define IP_VS_SO_SET_TIMEOUT (IP_VS_BASE_CTL+10) /* The argument to IP_VS_SO_GET_TIMEOUT */ struct ipvs_timeout_t { int tcp_timeout; int tcp_fin_timeout; int udp_timeout; }; int main() { int ret = -1; int sockfd = -1; struct ipvs_timeout_t to; sockfd = socket(AF_INET, SOCK_RAW, IPPROTO_RAW); if (sockfd == -1) { printf("socket init error\n"); return -1; } to.tcp_timeout = -2147483647; to.tcp_fin_timeout = -2147483647; to.udp_timeout = -2147483647; ret = setsockopt(sockfd, IPPROTO_IP, IP_VS_SO_SET_TIMEOUT, (char *)(&to), sizeof(to)); printf("setsockopt return %d\n", ret); return ret; } Return -EINVAL if the timeout value is negative or max than 'INT_MAX / HZ'. Signed-off-by: ZhangXiaoxu Acked-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipvs/ip_vs_ctl.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 432141f04af3..7d6318664eb2 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2220,6 +2220,18 @@ static int ip_vs_set_timeout(struct netns_ipvs *ipvs, struct ip_vs_timeout_user u->tcp_fin_timeout, u->udp_timeout); +#ifdef CONFIG_IP_VS_PROTO_TCP + if (u->tcp_timeout < 0 || u->tcp_timeout > (INT_MAX / HZ) || + u->tcp_fin_timeout < 0 || u->tcp_fin_timeout > (INT_MAX / HZ)) { + return -EINVAL; + } +#endif + +#ifdef CONFIG_IP_VS_PROTO_UDP + if (u->udp_timeout < 0 || u->udp_timeout > (INT_MAX / HZ)) + return -EINVAL; +#endif + #ifdef CONFIG_IP_VS_PROTO_TCP if (u->tcp_timeout) { pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP); From 9825bd94e3a2baae1f4874767ae3a7d4c049720e Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Thu, 24 Jan 2019 04:16:45 +0000 Subject: [PATCH 100/525] iommu/amd: Fix IOMMU page flush when detach device from a domain When a VM is terminated, the VFIO driver detaches all pass-through devices from VFIO domain by clearing domain id and page table root pointer from each device table entry (DTE), and then invalidates the DTE. Then, the VFIO driver unmap pages and invalidate IOMMU pages. Currently, the IOMMU driver keeps track of which IOMMU and how many devices are attached to the domain. When invalidate IOMMU pages, the driver checks if the IOMMU is still attached to the domain before issuing the invalidate page command. However, since VFIO has already detached all devices from the domain, the subsequent INVALIDATE_IOMMU_PAGES commands are being skipped as there is no IOMMU attached to the domain. This results in data corruption and could cause the PCI device to end up in indeterministic state. Fix this by invalidate IOMMU pages when detach a device, and before decrementing the per-domain device reference counts. Cc: Boris Ostrovsky Suggested-by: Joerg Roedel Co-developed-by: Brijesh Singh Signed-off-by: Brijesh Singh Signed-off-by: Suravee Suthikulpanit Fixes: 6de8ad9b9ee0 ('x86/amd-iommu: Make iommu_flush_pages aware of multiple IOMMUs') Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 843b825cc1c4..2a7b78bb98b4 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -1991,16 +1991,13 @@ static void do_attach(struct iommu_dev_data *dev_data, static void do_detach(struct iommu_dev_data *dev_data) { + struct protection_domain *domain = dev_data->domain; struct amd_iommu *iommu; u16 alias; iommu = amd_iommu_rlookup_table[dev_data->devid]; alias = dev_data->alias; - /* decrease reference counters */ - dev_data->domain->dev_iommu[iommu->index] -= 1; - dev_data->domain->dev_cnt -= 1; - /* Update data structures */ dev_data->domain = NULL; list_del(&dev_data->list); @@ -2010,6 +2007,16 @@ static void do_detach(struct iommu_dev_data *dev_data) /* Flush the DTE entry */ device_flush_dte(dev_data); + + /* Flush IOTLB */ + domain_flush_tlb_pde(domain); + + /* Wait for the flushes to finish */ + domain_flush_complete(domain); + + /* decrease reference counters - needs to happen after the flushes */ + domain->dev_iommu[iommu->index] -= 1; + domain->dev_cnt -= 1; } /* From 45383fb0f42db3945ac6cc658704706cdae19528 Mon Sep 17 00:00:00 2001 From: Tiwei Bie Date: Wed, 23 Jan 2019 17:50:26 +0800 Subject: [PATCH 101/525] virtio: support VIRTIO_F_ORDER_PLATFORM This patch introduces the support for VIRTIO_F_ORDER_PLATFORM. If this feature is negotiated, the driver must use the barriers suitable for hardware devices. Otherwise, the device and driver are assumed to be implemented in software, that is they can be assumed to run on identical CPUs in an SMP configuration. Thus a weaker form of memory barriers is sufficient to yield better performance. It is recommended that an add-in card based PCI device offers this feature for portability. The device will fail to operate further or will operate in a slower emulation mode if this feature is offered but not accepted. Signed-off-by: Tiwei Bie Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio_ring.c | 8 ++++++++ include/uapi/linux/virtio_config.h | 6 ++++++ 2 files changed, 14 insertions(+) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index cd7e755484e3..27d3f057493e 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -1609,6 +1609,9 @@ static struct virtqueue *vring_create_virtqueue_packed( !context; vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX); + if (virtio_has_feature(vdev, VIRTIO_F_ORDER_PLATFORM)) + vq->weak_barriers = false; + vq->packed.ring_dma_addr = ring_dma_addr; vq->packed.driver_event_dma_addr = driver_event_dma_addr; vq->packed.device_event_dma_addr = device_event_dma_addr; @@ -2079,6 +2082,9 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index, !context; vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX); + if (virtio_has_feature(vdev, VIRTIO_F_ORDER_PLATFORM)) + vq->weak_barriers = false; + vq->split.queue_dma_addr = 0; vq->split.queue_size_in_bytes = 0; @@ -2213,6 +2219,8 @@ void vring_transport_features(struct virtio_device *vdev) break; case VIRTIO_F_RING_PACKED: break; + case VIRTIO_F_ORDER_PLATFORM: + break; default: /* We don't understand this bit. */ __virtio_clear_bit(vdev, i); diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h index 1196e1c1d4f6..ff8e7dc9d4dd 100644 --- a/include/uapi/linux/virtio_config.h +++ b/include/uapi/linux/virtio_config.h @@ -78,6 +78,12 @@ /* This feature indicates support for the packed virtqueue layout. */ #define VIRTIO_F_RING_PACKED 34 +/* + * This feature indicates that memory accesses by the driver and the + * device are ordered in a way described by the platform. + */ +#define VIRTIO_F_ORDER_PLATFORM 36 + /* * Does the device support Single Root I/O Virtualization? */ From 0113613faf0214b5e04ccf9149c330ee67f9779c Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Mon, 21 Jan 2019 07:22:54 +0100 Subject: [PATCH 102/525] Revert "Input: olpc_apsp - enable the SP clock" Turns out this is not such a great idea. Once the SP clock is disabled, it's not sufficient to just enable in order to bring the SP core back up. It seems that the kernel has no business managing this clock. Just let the firmware keep it enabled. This reverts commit ed22cee91a88c47e564478b012fdbcb079653499. Link: https://lore.kernel.org/lkml/154783267051.169631.3197836544646625747@swboyd.mtv.corp.google.com/ Signed-off-by: Lubomir Rintel Acked-by: Dmitry Torokhov Signed-off-by: Stephen Boyd --- .../devicetree/bindings/serio/olpc,ap-sp.txt | 4 ---- drivers/input/serio/olpc_apsp.c | 14 -------------- 2 files changed, 18 deletions(-) diff --git a/Documentation/devicetree/bindings/serio/olpc,ap-sp.txt b/Documentation/devicetree/bindings/serio/olpc,ap-sp.txt index 36603419d6f8..0e72183f52bc 100644 --- a/Documentation/devicetree/bindings/serio/olpc,ap-sp.txt +++ b/Documentation/devicetree/bindings/serio/olpc,ap-sp.txt @@ -4,14 +4,10 @@ Required properties: - compatible : "olpc,ap-sp" - reg : base address and length of SoC's WTM registers - interrupts : SP-AP interrupt -- clocks : phandle + clock-specifier for the clock that drives the WTM -- clock-names: should be "sp" Example: ap-sp@d4290000 { compatible = "olpc,ap-sp"; reg = <0xd4290000 0x1000>; interrupts = <40>; - clocks = <&soc_clocks MMP2_CLK_SP>; - clock-names = "sp"; } diff --git a/drivers/input/serio/olpc_apsp.c b/drivers/input/serio/olpc_apsp.c index b36084710f69..698003309d2c 100644 --- a/drivers/input/serio/olpc_apsp.c +++ b/drivers/input/serio/olpc_apsp.c @@ -23,7 +23,6 @@ #include #include #include -#include /* * The OLPC XO-1.75 and XO-4 laptops do not have a hardware PS/2 controller. @@ -75,7 +74,6 @@ struct olpc_apsp { struct serio *kbio; struct serio *padio; void __iomem *base; - struct clk *clk; int open_count; int irq; }; @@ -148,17 +146,11 @@ static int olpc_apsp_open(struct serio *port) struct olpc_apsp *priv = port->port_data; unsigned int tmp; unsigned long l; - int error; if (priv->open_count++ == 0) { - error = clk_prepare_enable(priv->clk); - if (error) - return error; - l = readl(priv->base + COMMAND_FIFO_STATUS); if (!(l & CMD_STS_MASK)) { dev_err(priv->dev, "SP cannot accept commands.\n"); - clk_disable_unprepare(priv->clk); return -EIO; } @@ -179,8 +171,6 @@ static void olpc_apsp_close(struct serio *port) /* Disable interrupt 0 */ tmp = readl(priv->base + PJ_INTERRUPT_MASK); writel(tmp | INT_0, priv->base + PJ_INTERRUPT_MASK); - - clk_disable_unprepare(priv->clk); } } @@ -206,10 +196,6 @@ static int olpc_apsp_probe(struct platform_device *pdev) if (priv->irq < 0) return priv->irq; - priv->clk = devm_clk_get(&pdev->dev, "sp"); - if (IS_ERR(priv->clk)) - return PTR_ERR(priv->clk); - /* KEYBOARD */ kb_serio = kzalloc(sizeof(struct serio), GFP_KERNEL); if (!kb_serio) From 0acb69e7b904135ff540bc483942c0dba40ecdb9 Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Mon, 21 Jan 2019 07:22:55 +0100 Subject: [PATCH 103/525] Revert "clk: mmp2: add SP clock" It seems that the kernel has no business managing this clock: once the SP clock is disabled, it's not sufficient to just enable in order to bring the SP core back up. Just let the firmware keep it enabled and don't expose it to drivers. This reverts commit fc27c2394d96fd19854b7e2d3f0e60df0d86fc90. Link: https://lore.kernel.org/lkml/154783267051.169631.3197836544646625747@swboyd.mtv.corp.google.com/ Signed-off-by: Lubomir Rintel Signed-off-by: Stephen Boyd --- drivers/clk/mmp/clk-of-mmp2.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/clk/mmp/clk-of-mmp2.c b/drivers/clk/mmp/clk-of-mmp2.c index 61fefc046ec5..d083b860f083 100644 --- a/drivers/clk/mmp/clk-of-mmp2.c +++ b/drivers/clk/mmp/clk-of-mmp2.c @@ -53,7 +53,6 @@ #define APMU_DISP1 0x110 #define APMU_CCIC0 0x50 #define APMU_CCIC1 0xf4 -#define APMU_SP 0x68 #define MPMU_UART_PLL 0x14 struct mmp2_clk_unit { @@ -210,8 +209,6 @@ static struct mmp_clk_mix_config ccic1_mix_config = { .reg_info = DEFINE_MIX_REG_INFO(4, 16, 2, 6, 32), }; -static DEFINE_SPINLOCK(sp_lock); - static struct mmp_param_mux_clk apmu_mux_clks[] = { {MMP2_CLK_DISP0_MUX, "disp0_mux", disp_parent_names, ARRAY_SIZE(disp_parent_names), CLK_SET_RATE_PARENT, APMU_DISP0, 6, 2, 0, &disp0_lock}, {MMP2_CLK_DISP1_MUX, "disp1_mux", disp_parent_names, ARRAY_SIZE(disp_parent_names), CLK_SET_RATE_PARENT, APMU_DISP1, 6, 2, 0, &disp1_lock}, @@ -242,7 +239,6 @@ static struct mmp_param_gate_clk apmu_gate_clks[] = { {MMP2_CLK_CCIC1, "ccic1_clk", "ccic1_mix_clk", CLK_SET_RATE_PARENT, APMU_CCIC1, 0x1b, 0x1b, 0x0, 0, &ccic1_lock}, {MMP2_CLK_CCIC1_PHY, "ccic1_phy_clk", "ccic1_mix_clk", CLK_SET_RATE_PARENT, APMU_CCIC1, 0x24, 0x24, 0x0, 0, &ccic1_lock}, {MMP2_CLK_CCIC1_SPHY, "ccic1_sphy_clk", "ccic1_sphy_div", CLK_SET_RATE_PARENT, APMU_CCIC1, 0x300, 0x300, 0x0, 0, &ccic1_lock}, - {MMP2_CLK_SP, "sp_clk", NULL, CLK_SET_RATE_PARENT, APMU_SP, 0x1b, 0x1b, 0x0, 0, &sp_lock}, }; static void mmp2_axi_periph_clk_init(struct mmp2_clk_unit *pxa_unit) From 401fbb34f53e20a8d4734136a2d02ff1ee76f86e Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Mon, 21 Jan 2019 07:22:56 +0100 Subject: [PATCH 104/525] Revert "dt-bindings: marvell,mmp2: Add clock id for the SP clock" It seems that the kernel has no business managing this clock: once the SP clock is disabled, it's not sufficient to just enable it in order to bring the SP core back up. Pretty sure nothing ever used this and it's safe to remove. This reverts commit e8a2c779141415105825e65a4715f1130bba61b1. Signed-off-by: Lubomir Rintel Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/marvell,mmp2.h | 1 - 1 file changed, 1 deletion(-) diff --git a/include/dt-bindings/clock/marvell,mmp2.h b/include/dt-bindings/clock/marvell,mmp2.h index 7b24fc791146..228a5e234af0 100644 --- a/include/dt-bindings/clock/marvell,mmp2.h +++ b/include/dt-bindings/clock/marvell,mmp2.h @@ -71,7 +71,6 @@ #define MMP2_CLK_CCIC1_MIX 117 #define MMP2_CLK_CCIC1_PHY 118 #define MMP2_CLK_CCIC1_SPHY 119 -#define MMP2_CLK_SP 120 #define MMP2_NR_CLKS 200 #endif From ede77858473ae4cab6f8f147efcaa76989761535 Mon Sep 17 00:00:00 2001 From: Derek Basehore Date: Thu, 20 Dec 2018 16:31:00 -0800 Subject: [PATCH 105/525] clk: Remove global clk traversal on fetch parent index It's not required to traverse the entire clk tree when the parents array contains a NULL value. We already have the parent clk_core pointer, so we can just compare the parent->name and parent_names[i] pointers. This can be a substantial power improvement in cases where the parent clk isn't known and that clk is never registered, because a mux having an unregistered parent name may traverse the clk tree on every clk_set_rate() call in clk_mux_determine_rate_flags(). This can happen hundreds of times a second for CPU clks. This patch is the combination of reverting commit 470b5e2f97cf ("clk: simplify clk_fetch_parent_index() function") and optimizing the resulting code to never call __clk_lookup() because we already have the clk_core pointer we're looking for. That optimization went unnoticed even after commit da0f0b2c3ad2 ("clk: Correct lookup logic in clk_fetch_parent_index()") tried to optimize this path. Signed-off-by: Derek Basehore [sboyd@kernel.org: More description in commit text] Signed-off-by: Stephen Boyd --- drivers/clk/clk.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 6ccdbedb02f3..d2477a5058ac 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -1513,10 +1513,20 @@ static int clk_fetch_parent_index(struct clk_core *core, if (!parent) return -EINVAL; - for (i = 0; i < core->num_parents; i++) - if (clk_core_get_parent_by_index(core, i) == parent) + for (i = 0; i < core->num_parents; i++) { + if (core->parents[i] == parent) return i; + if (core->parents[i]) + continue; + + /* Fallback to comparing globally unique names */ + if (!strcmp(parent->name, core->parent_names[i])) { + core->parents[i] = parent; + return i; + } + } + return -EINVAL; } From a64a9c088b75cba5840320d57e0bbfb36739c3b5 Mon Sep 17 00:00:00 2001 From: Abel Vesa Date: Fri, 18 Jan 2019 12:54:13 +0000 Subject: [PATCH 106/525] clk: imx: Fix fractional clock set rate computation Before multiplying by PLL_FRAC_DENOM, the temp64 needs to be temp64 = rate * 2 - divfi * parent_rate * 8, instead of: temp64 = (rate * 2 - divfi) * parent_rate Fixes: 6209624b9a5c1e ("clk: imx: Add fractional PLL output clock") Signed-off-by: Abel Vesa Signed-off-by: Stephen Boyd --- drivers/clk/imx/clk-frac-pll.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/clk/imx/clk-frac-pll.c b/drivers/clk/imx/clk-frac-pll.c index 0026c3969b1e..76b9eb15604e 100644 --- a/drivers/clk/imx/clk-frac-pll.c +++ b/drivers/clk/imx/clk-frac-pll.c @@ -155,13 +155,14 @@ static int clk_pll_set_rate(struct clk_hw *hw, unsigned long rate, { struct clk_frac_pll *pll = to_clk_frac_pll(hw); u32 val, divfi, divff; - u64 temp64 = parent_rate; + u64 temp64; int ret; parent_rate *= 8; rate *= 2; divfi = rate / parent_rate; - temp64 *= rate - divfi; + temp64 = parent_rate * divfi; + temp64 = rate - temp64; temp64 *= PLL_FRAC_DENOM; do_div(temp64, parent_rate); divff = temp64; From 303aef8b84272d73999a3207dd05bbe10ed89dc5 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 15 Jan 2019 22:46:25 +0300 Subject: [PATCH 107/525] clk: ti: Fix error handling in ti_clk_parse_divider_data() The ti_clk_parse_divider_data() function is only called from _get_div_table_from_setup(). That function doesn't look at the return value but instead looks at the "*table" pointer. In this case, if the kcalloc() fails then *table is NULL (which means success). It should instead be an error pointer. The ti_clk_parse_divider_data() function has two callers. One checks for errors and the other doesn't. I have fixed it so now both handle errors. Fixes: 4f6be5655dc9 ("clk: ti: divider: add driver internal API for parsing divider data") Signed-off-by: Dan Carpenter Acked-by: Tero Kristo Signed-off-by: Stephen Boyd --- drivers/clk/ti/divider.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/clk/ti/divider.c b/drivers/clk/ti/divider.c index 8d77090ad94a..0241450f3eb3 100644 --- a/drivers/clk/ti/divider.c +++ b/drivers/clk/ti/divider.c @@ -403,8 +403,10 @@ int ti_clk_parse_divider_data(int *div_table, int num_dividers, int max_div, num_dividers = i; tmp = kcalloc(valid_div + 1, sizeof(*tmp), GFP_KERNEL); - if (!tmp) + if (!tmp) { + *table = ERR_PTR(-ENOMEM); return -ENOMEM; + } valid_div = 0; *width = 0; @@ -439,6 +441,7 @@ struct clk_hw *ti_clk_build_component_div(struct ti_clk_divider *setup) { struct clk_omap_divider *div; struct clk_omap_reg *reg; + int ret; if (!setup) return NULL; @@ -458,6 +461,12 @@ struct clk_hw *ti_clk_build_component_div(struct ti_clk_divider *setup) div->flags |= CLK_DIVIDER_POWER_OF_TWO; div->table = _get_div_table_from_setup(setup, &div->width); + if (IS_ERR(div->table)) { + ret = PTR_ERR(div->table); + kfree(div); + return ERR_PTR(ret); + } + div->shift = setup->bit_shift; div->latch = -EINVAL; From 9ff1a3b4912528f853048ccd9757ba6a2cc75557 Mon Sep 17 00:00:00 2001 From: Taniya Das Date: Tue, 18 Dec 2018 23:49:41 +0530 Subject: [PATCH 108/525] clk: qcom: gcc: Use active only source for CPUSS clocks The clocks of the CPUSS such as "gcc_cpuss_ahb_clk_src" is a CRITICAL clock and needs to vote on the active only source of XO, so as to keep the vote as long as CPUSS is active. Similar rbcpr_clk_src is also has the same requirement. Signed-off-by: Taniya Das Fixes: 06391eddb60a ("clk: qcom: Add Global Clock controller (GCC) driver for SDM845") Signed-off-by: Stephen Boyd --- drivers/clk/qcom/gcc-sdm845.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/drivers/clk/qcom/gcc-sdm845.c b/drivers/clk/qcom/gcc-sdm845.c index c782e62dd98b..58fa5c247af1 100644 --- a/drivers/clk/qcom/gcc-sdm845.c +++ b/drivers/clk/qcom/gcc-sdm845.c @@ -115,8 +115,8 @@ static const char * const gcc_parent_names_6[] = { "core_bi_pll_test_se", }; -static const char * const gcc_parent_names_7[] = { - "bi_tcxo", +static const char * const gcc_parent_names_7_ao[] = { + "bi_tcxo_ao", "gpll0", "gpll0_out_even", "core_bi_pll_test_se", @@ -128,6 +128,12 @@ static const char * const gcc_parent_names_8[] = { "core_bi_pll_test_se", }; +static const char * const gcc_parent_names_8_ao[] = { + "bi_tcxo_ao", + "gpll0", + "core_bi_pll_test_se", +}; + static const struct parent_map gcc_parent_map_10[] = { { P_BI_TCXO, 0 }, { P_GPLL0_OUT_MAIN, 1 }, @@ -210,7 +216,7 @@ static struct clk_rcg2 gcc_cpuss_ahb_clk_src = { .freq_tbl = ftbl_gcc_cpuss_ahb_clk_src, .clkr.hw.init = &(struct clk_init_data){ .name = "gcc_cpuss_ahb_clk_src", - .parent_names = gcc_parent_names_7, + .parent_names = gcc_parent_names_7_ao, .num_parents = 4, .ops = &clk_rcg2_ops, }, @@ -229,7 +235,7 @@ static struct clk_rcg2 gcc_cpuss_rbcpr_clk_src = { .freq_tbl = ftbl_gcc_cpuss_rbcpr_clk_src, .clkr.hw.init = &(struct clk_init_data){ .name = "gcc_cpuss_rbcpr_clk_src", - .parent_names = gcc_parent_names_8, + .parent_names = gcc_parent_names_8_ao, .num_parents = 3, .ops = &clk_rcg2_ops, }, From 4fe8713b873fc881284722ce4ac47995de7cf62c Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Mon, 29 Jan 2018 09:09:41 -0800 Subject: [PATCH 109/525] xtensa: SMP: fix ccount_timer_shutdown ccount_timer_shutdown is called from the atomic context in the secondary_start_kernel, resulting in the following BUG: BUG: sleeping function called from invalid context in_atomic(): 1, irqs_disabled(): 1, pid: 0, name: swapper/1 Preemption disabled at: secondary_start_kernel+0xa1/0x130 Call Trace: ___might_sleep+0xe7/0xfc __might_sleep+0x41/0x44 synchronize_irq+0x24/0x64 disable_irq+0x11/0x14 ccount_timer_shutdown+0x12/0x20 clockevents_switch_state+0x82/0xb4 clockevents_exchange_device+0x54/0x60 tick_check_new_device+0x46/0x70 clockevents_register_device+0x8c/0xc8 clockevents_config_and_register+0x1d/0x2c local_timer_setup+0x75/0x7c secondary_start_kernel+0xb4/0x130 should_never_return+0x32/0x35 Use disable_irq_nosync instead of disable_irq to avoid it. This is safe because the ccount timer IRQ is per-CPU, and once IRQ is masked the ISR will not be called. Signed-off-by: Max Filippov --- arch/xtensa/kernel/time.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c index fd524a54d2ab..378186b5eb40 100644 --- a/arch/xtensa/kernel/time.c +++ b/arch/xtensa/kernel/time.c @@ -89,7 +89,7 @@ static int ccount_timer_shutdown(struct clock_event_device *evt) container_of(evt, struct ccount_timer, evt); if (timer->irq_enabled) { - disable_irq(evt->irq); + disable_irq_nosync(evt->irq); timer->irq_enabled = 0; } return 0; From 2a81efb0de0e33f2d2c83154af0bd3ce389b3269 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Mon, 10 Dec 2018 13:56:33 +0000 Subject: [PATCH 110/525] arm64: dts: add msm8996 compatible to gicv3 Add compatible to gicv3 node to enable quirk required to restrict writing to GICR_WAKER register which is restricted on msm8996 SoC in Hypervisor. With this quirk MSM8996 can at least boot out of mainline, which can help community to work with boards based on MSM8996. Without this patch Qualcomm DB820c board reboots on mainline. Signed-off-by: Srinivas Kandagatla Signed-off-by: Andy Gross --- arch/arm64/boot/dts/qcom/msm8996.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index 99b7495455a6..838e32cc14c9 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -404,7 +404,7 @@ }; intc: interrupt-controller@9bc0000 { - compatible = "arm,gic-v3"; + compatible = "qcom,msm8996-gic-v3", "arm,gic-v3"; #interrupt-cells = <3>; interrupt-controller; #redistributor-regions = <1>; From 093c61b6a0d5768f48442ec59d671496314cc47d Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Fri, 25 Jan 2019 07:40:32 +0000 Subject: [PATCH 111/525] i3c: fix missing detach if failed to retrieve i3c dev If we failed to retrieve the i3c dev, we should detach the i3c dev I.E i3c_master_detach_i3c_dev(). Signed-off-by: Jisheng Zhang Signed-off-by: Boris Brezillon --- drivers/i3c/master.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c index c39f89d2deba..2dc628d4f1ae 100644 --- a/drivers/i3c/master.c +++ b/drivers/i3c/master.c @@ -1828,7 +1828,7 @@ int i3c_master_add_i3c_dev_locked(struct i3c_master_controller *master, ret = i3c_master_retrieve_dev_info(newdev); if (ret) - goto err_free_dev; + goto err_detach_dev; olddev = i3c_master_search_i3c_dev_duplicate(newdev); if (olddev) { From 7d652669b61d702c6e62a39579d17f6881670ab6 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Fri, 25 Jan 2019 08:21:26 +0100 Subject: [PATCH 112/525] batman-adv: release station info tidstats With the addition of TXQ stats in the per-tid statistics the struct station_info grew significantly. This resulted in stack size warnings due to the structure itself being above the limit for the warnings. To work around this, the TID array was allocated dynamically. Also a function to free this content was introduced with commit 7ea3e110f2f8 ("cfg80211: release station info tidstats where needed") but the necessary changes were not provided for batman-adv's B.A.T.M.A.N. V implementation. Signed-off-by: Felix Fietkau Fixes: 8689c051a201 ("cfg80211: dynamically allocate per-tid stats for station info") [sven@narfation.org: add commit message] Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich --- net/batman-adv/bat_v_elp.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index e8090f099eb8..ef0dec20c7d8 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -104,6 +104,9 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh) ret = cfg80211_get_station(real_netdev, neigh->addr, &sinfo); + /* free the TID stats immediately */ + cfg80211_sinfo_release_content(&sinfo); + dev_put(real_netdev); if (ret == -ENOENT) { /* Node is not associated anymore! It would be From 356690d029e10f1aadebc49819d3908d5f6389fb Mon Sep 17 00:00:00 2001 From: Nagadheeraj Rottela Date: Mon, 14 Jan 2019 13:52:24 +0000 Subject: [PATCH 113/525] crypto: cavium/nitrox - Invoke callback after DMA unmap In process_response_list() invoke the callback handler after unmapping the DMA buffers. It ensures DMA data is synced form device to cpu before the client code access the data from callback handler. Fixes: c9613335bf4f ("crypto: cavium/nitrox - Added AEAD cipher support") Signed-off-by: Nagadheeraj Rottela Signed-off-by: Herbert Xu --- drivers/crypto/cavium/nitrox/nitrox_reqmgr.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c b/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c index fe070d75c842..4c97478d44bd 100644 --- a/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c +++ b/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c @@ -537,6 +537,8 @@ static void process_response_list(struct nitrox_cmdq *cmdq) struct nitrox_device *ndev = cmdq->ndev; struct nitrox_softreq *sr; int req_completed = 0, err = 0, budget; + completion_t callback; + void *cb_arg; /* check all pending requests */ budget = atomic_read(&cmdq->pending_count); @@ -564,13 +566,13 @@ static void process_response_list(struct nitrox_cmdq *cmdq) smp_mb__after_atomic(); /* remove from response list */ response_list_del(sr, cmdq); - /* ORH error code */ err = READ_ONCE(*sr->resp.orh) & 0xff; - - if (sr->callback) - sr->callback(sr->cb_arg, err); + callback = sr->callback; + cb_arg = sr->cb_arg; softreq_destroy(sr); + if (callback) + callback(cb_arg, err); req_completed++; } From d88c93f090f708c18195553b352b9f205e65418f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 23 Jan 2019 11:27:02 +0100 Subject: [PATCH 114/525] debugfs: fix debugfs_rename parameter checking debugfs_rename() needs to check that the dentries passed into it really are valid, as sometimes they are not (i.e. if the return value of another debugfs call is passed into this one.) So fix this up by properly checking if the two parent directories are errors (they are allowed to be NULL), and if the dentry to rename is not NULL or an error. Cc: stable Signed-off-by: Greg Kroah-Hartman --- fs/debugfs/inode.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 13b01351dd1c..41ef452c1fcf 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -787,6 +787,13 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, struct dentry *dentry = NULL, *trap; struct name_snapshot old_name; + if (IS_ERR(old_dir)) + return old_dir; + if (IS_ERR(new_dir)) + return new_dir; + if (IS_ERR_OR_NULL(old_dentry)) + return old_dentry; + trap = lock_rename(new_dir, old_dir); /* Source or destination directories don't exist? */ if (d_really_is_negative(old_dir) || d_really_is_negative(new_dir)) From 053ff09f1a8f2151339f9fda457c5250929d1c49 Mon Sep 17 00:00:00 2001 From: Sandy Huang Date: Wed, 23 Jan 2019 18:14:39 +0800 Subject: [PATCH 115/525] drm/rockchip: rgb: update SPDX license identifier Update SPDX License Identifier from GPL-2.0+ to GPL-2.0 and drop some GPL text. This fixes a mismatch between the existing SPDX headers and GPL boilerplate text. Fixes: 1f0f01515172 ("Add support for Rockchip Soc RGB output interface") Cc: stable@vger.kernel.org Reported-by: Thomas Gleixner Signed-off-by: Sandy Huang Signed-off-by: Heiko Stuebner Link: https://patchwork.freedesktop.org/patch/msgid/1548238479-171491-1-git-send-email-hjc@rock-chips.com --- drivers/gpu/drm/rockchip/rockchip_rgb.c | 11 +---------- drivers/gpu/drm/rockchip/rockchip_rgb.h | 11 +---------- 2 files changed, 2 insertions(+), 20 deletions(-) diff --git a/drivers/gpu/drm/rockchip/rockchip_rgb.c b/drivers/gpu/drm/rockchip/rockchip_rgb.c index 37f93022a106..c0351abf83a3 100644 --- a/drivers/gpu/drm/rockchip/rockchip_rgb.c +++ b/drivers/gpu/drm/rockchip/rockchip_rgb.c @@ -1,17 +1,8 @@ -//SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd * Author: * Sandy Huang - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #include diff --git a/drivers/gpu/drm/rockchip/rockchip_rgb.h b/drivers/gpu/drm/rockchip/rockchip_rgb.h index 38b52e63b2b0..27b9635124bc 100644 --- a/drivers/gpu/drm/rockchip/rockchip_rgb.h +++ b/drivers/gpu/drm/rockchip/rockchip_rgb.h @@ -1,17 +1,8 @@ -//SPDX-License-Identifier: GPL-2.0+ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd * Author: * Sandy Huang - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifdef CONFIG_ROCKCHIP_RGB From 9d9d4ff788845fad1626b80164e43a1f0f17ccbc Mon Sep 17 00:00:00 2001 From: Lijun Ou Date: Wed, 23 Jan 2019 10:09:27 +0800 Subject: [PATCH 116/525] RDMA/hns: Update the kernel header file of hns The hns_roce_ib_create_srq_resp is used to interact with the user for data, this was open coded to use a u32 directly, instead use a properly sized structure. Fixes: c7bcb13442e1 ("RDMA/hns: Add SRQ support for hip08 kernel mode") Signed-off-by: Lijun Ou Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/hns/hns_roce_srq.c | 10 ++++++++-- include/uapi/rdma/hns-abi.h | 5 +++++ 2 files changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_srq.c b/drivers/infiniband/hw/hns/hns_roce_srq.c index 960b1946c365..12deacf442cf 100644 --- a/drivers/infiniband/hw/hns/hns_roce_srq.c +++ b/drivers/infiniband/hw/hns/hns_roce_srq.c @@ -210,6 +210,7 @@ struct ib_srq *hns_roce_create_srq(struct ib_pd *pd, struct ib_udata *udata) { struct hns_roce_dev *hr_dev = to_hr_dev(pd->device); + struct hns_roce_ib_create_srq_resp resp = {}; struct hns_roce_srq *srq; int srq_desc_size; int srq_buf_size; @@ -378,16 +379,21 @@ struct ib_srq *hns_roce_create_srq(struct ib_pd *pd, srq->event = hns_roce_ib_srq_event; srq->ibsrq.ext.xrc.srq_num = srq->srqn; + resp.srqn = srq->srqn; if (udata) { - if (ib_copy_to_udata(udata, &srq->srqn, sizeof(__u32))) { + if (ib_copy_to_udata(udata, &resp, + min(udata->outlen, sizeof(resp)))) { ret = -EFAULT; - goto err_wrid; + goto err_srqc_alloc; } } return &srq->ibsrq; +err_srqc_alloc: + hns_roce_srq_free(hr_dev, srq); + err_wrid: kvfree(srq->wrid); diff --git a/include/uapi/rdma/hns-abi.h b/include/uapi/rdma/hns-abi.h index ef3c7ec793a7..eb76b38a00d4 100644 --- a/include/uapi/rdma/hns-abi.h +++ b/include/uapi/rdma/hns-abi.h @@ -52,6 +52,11 @@ struct hns_roce_ib_create_srq { __aligned_u64 que_addr; }; +struct hns_roce_ib_create_srq_resp { + __u32 srqn; + __u32 reserved; +}; + struct hns_roce_ib_create_qp { __aligned_u64 buf_addr; __aligned_u64 db_addr; From a2093dd35f8cfb28dd7c878ccbd020c1bb20d0d7 Mon Sep 17 00:00:00 2001 From: Artemy Kovalyov Date: Tue, 22 Jan 2019 09:16:10 +0200 Subject: [PATCH 117/525] RDMA/umem: Add missing initialization of owning_mm When allocating a umem leaf for implicit ODP MR during page fault the field owning_mm was not set. Initialize and take a reference on this field to avoid kernel panic when trying to access this field. BUG: unable to handle kernel NULL pointer dereference at 0000000000000058 PGD 800000022dfed067 P4D 800000022dfed067 PUD 22dfcf067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 634 Comm: kworker/u33:0 Not tainted 4.20.0-rc6+ #89 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: mlx5_ib_page_fault mlx5_ib_eqe_pf_action [mlx5_ib] RIP: 0010:ib_umem_odp_map_dma_pages+0xf3/0x710 [ib_core] Code: 45 c0 48 21 f3 48 89 75 b0 31 f6 4a 8d 04 33 48 89 45 a8 49 8b 44 24 60 48 8b 78 10 e8 66 16 a8 c5 49 8b 54 24 08 48 89 45 98 <8b> 42 58 85 c0 0f 84 8e 05 00 00 8d 48 01 48 8d 72 58 f0 0f b1 4a RSP: 0000:ffffb610813a7c20 EFLAGS: 00010202 RAX: ffff95ace6e8ac80 RBX: 0000000000000000 RCX: 000000000000000c RDX: 0000000000000000 RSI: 0000000000000850 RDI: ffff95aceaadae80 RBP: ffffb610813a7ce0 R08: 0000000000000000 R09: 0000000000080c77 R10: ffff95acfffdbd00 R11: 0000000000000000 R12: ffff95aceaa20a00 R13: 0000000000001000 R14: 0000000000001000 R15: 000000000000000c FS: 0000000000000000(0000) GS:ffff95acf7800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000058 CR3: 000000022c834001 CR4: 00000000001606f0 Call Trace: pagefault_single_data_segment+0x1df/0xc60 [mlx5_ib] mlx5_ib_eqe_pf_action+0x7bc/0xa70 [mlx5_ib] ? __switch_to+0xe1/0x470 process_one_work+0x174/0x390 worker_thread+0x4f/0x3e0 kthread+0x102/0x140 ? drain_workqueue+0x130/0x130 ? kthread_stop+0x110/0x110 ret_from_fork+0x1f/0x30 Fixes: f27a0d50a4bc ("RDMA/umem: Use umem->owning_mm inside ODP") Signed-off-by: Artemy Kovalyov Signed-off-by: Moni Shoua Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/umem_odp.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c index a4ec43093cb3..acb882f279cb 100644 --- a/drivers/infiniband/core/umem_odp.c +++ b/drivers/infiniband/core/umem_odp.c @@ -352,6 +352,8 @@ struct ib_umem_odp *ib_alloc_odp_umem(struct ib_ucontext_per_mm *per_mm, umem->writable = 1; umem->is_odp = 1; odp_data->per_mm = per_mm; + umem->owning_mm = per_mm->mm; + mmgrab(umem->owning_mm); mutex_init(&odp_data->umem_mutex); init_completion(&odp_data->notifier_completion); @@ -384,6 +386,7 @@ struct ib_umem_odp *ib_alloc_odp_umem(struct ib_ucontext_per_mm *per_mm, out_page_list: vfree(odp_data->page_list); out_odp_data: + mmdrop(umem->owning_mm); kfree(odp_data); return ERR_PTR(ret); } From 9e6966646b6bc5078d579151b90016522d4ff2cb Mon Sep 17 00:00:00 2001 From: Olek Poplavsky Date: Thu, 24 Jan 2019 23:30:03 -0500 Subject: [PATCH 118/525] ALSA: usb-audio: Add Opus #3 to quirks for native DSD support This patch adds quirk VID/PID IDs for the Opus #3 DAP (made by 'The Bit') in order to enable Native DSD support. [ NOTE: this could be handled in the generic way with fp->dvd_raw if we add 0x10cb to the vendor whitelist, but since 0x10cb shows a different vendor name (Erantech), put to the individual entry at this time -- tiwai ] Signed-off-by: Olek Poplavsky Cc: Signed-off-by: Takashi Iwai --- sound/usb/quirks.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index ebbadb3a7094..bb8372833fc2 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1492,6 +1492,7 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip, return SNDRV_PCM_FMTBIT_DSD_U32_BE; break; + case USB_ID(0x10cb, 0x0103): /* The Bit Opus #3; with fp->dsd_raw */ case USB_ID(0x152a, 0x85de): /* SMSL D1 DAC */ case USB_ID(0x16d0, 0x09dd): /* Encore mDSD */ case USB_ID(0x0d8c, 0x0316): /* Hegel HD12 DSD */ From e190161f96b88ffae870405fd6c3fdd1d2e7f98d Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 25 Jan 2019 17:11:32 +0100 Subject: [PATCH 119/525] ALSA: pcm: Fix tight loop of OSS capture stream When the trigger=off is passed for a PCM OSS stream, it sets the start_threshold of the given substream to the boundary size, so that it won't be automatically started. This can be problematic for a capture stream, unfortunately, as detected by syzkaller. The scenario is like the following: - In __snd_pcm_lib_xfer() that is invoked from snd_pcm_oss_read() loop, we have a check whether the stream was already started or the stream can be auto-started. - The function at this check returns 0 with trigger=off since we explicitly disable the auto-start. - The loop continues and repeats calling __snd_pcm_lib_xfer() tightly, which may lead to an RCU stall. This patch fixes the bug by simply allowing the wait for non-started stream in the case of OSS capture. For native usages, it's supposed to be done by the caller side (which is user-space), hence it returns zero like before. (In theory, __snd_pcm_lib_xfer() could wait even for the native API usage cases, too; but I'd like to stay in a safer side for not breaking the existing stuff for now.) Reported-by: syzbot+fbe0496f92a0ce7b786c@syzkaller.appspotmail.com Cc: Signed-off-by: Takashi Iwai --- sound/core/pcm_lib.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index 40013b26f671..6c99fa8ac5fa 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -2112,6 +2112,13 @@ int pcm_lib_apply_appl_ptr(struct snd_pcm_substream *substream, return 0; } +/* allow waiting for a capture stream that hasn't been started */ +#if IS_ENABLED(CONFIG_SND_PCM_OSS) +#define wait_capture_start(substream) ((substream)->oss.oss) +#else +#define wait_capture_start(substream) false +#endif + /* the common loop for read/write data */ snd_pcm_sframes_t __snd_pcm_lib_xfer(struct snd_pcm_substream *substream, void *data, bool interleaved, @@ -2182,7 +2189,7 @@ snd_pcm_sframes_t __snd_pcm_lib_xfer(struct snd_pcm_substream *substream, err = snd_pcm_start(substream); if (err < 0) goto _end_unlock; - } else { + } else if (!wait_capture_start(substream)) { /* nothing to do */ err = 0; goto _end_unlock; From ae662eec8a515ab550524e04c793b5ddf1aae3a1 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Mon, 10 Dec 2018 06:21:46 +0000 Subject: [PATCH 120/525] riscv: Adjust mmap base address at a third of task size This ratio is the most used among all other architectures and make icache_hygiene libhugetlbfs test pass: this test mmap lots of hugepages whose addresses, without this patch, reach the end of the process user address space. Signed-off-by: Alexandre Ghiti Reviewed-by: Christoph Hellwig Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/processor.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h index 0531f49af5c3..ce70bceb8872 100644 --- a/arch/riscv/include/asm/processor.h +++ b/arch/riscv/include/asm/processor.h @@ -22,7 +22,7 @@ * This decides where the kernel will search for a free chunk of vm * space during mmap's. */ -#define TASK_UNMAPPED_BASE PAGE_ALIGN(TASK_SIZE >> 1) +#define TASK_UNMAPPED_BASE PAGE_ALIGN(TASK_SIZE / 3) #define STACK_TOP TASK_SIZE #define STACK_TOP_MAX STACK_TOP From 425784aa5b029eeb80498c73a68f62c3ad1d3b3f Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 24 Jan 2019 14:33:12 +0200 Subject: [PATCH 121/525] IB/uverbs: Fix OOPs upon device disassociation The async_file might be freed before the disassociation has been ended, causing qp shutdown to use after free on it. Since uverbs_destroy_ufile_hw is not a fence, it returns if a disassociation is ongoing in another thread. It has to be written this way to avoid deadlock. However this means that the ufile FD close cannot destroy anything that may still be used by an active kref, such as the the async_file. To fix that move the kref_put() to be in ib_uverbs_release_file(). BUG: unable to handle kernel paging request at ffffffffba682787 PGD bc80e067 P4D bc80e067 PUD bc80f063 PMD 1313df163 PTE 80000000bc682061 Oops: 0003 [#1] SMP PTI CPU: 1 PID: 32410 Comm: bash Tainted: G OE 4.20.0-rc6+ #3 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:__pv_queued_spin_lock_slowpath+0x1b3/0x2a0 Code: 98 83 e2 60 49 89 df 48 8b 04 c5 80 18 72 ba 48 8d ba 80 32 02 00 ba 00 80 00 00 4c 8d 65 14 41 bd 01 00 00 00 48 01 c7 85 d2 <48> 89 2f 48 89 fb 74 14 8b 45 08 85 c0 75 42 84 d2 74 6b f3 90 83 RSP: 0018:ffffc1bbc064fb58 EFLAGS: 00010006 RAX: ffffffffba65f4e7 RBX: ffff9f209c656c00 RCX: 0000000000000001 RDX: 0000000000008000 RSI: 0000000000000000 RDI: ffffffffba682787 RBP: ffff9f217bb23280 R08: 0000000000000001 R09: 0000000000000000 R10: ffff9f209d2c7800 R11: ffffffffffffffe8 R12: ffff9f217bb23294 R13: 0000000000000001 R14: 0000000000000000 R15: ffff9f209c656c00 FS: 00007fac55aad740(0000) GS:ffff9f217bb00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffba682787 CR3: 000000012f8e0000 CR4: 00000000000006e0 Call Trace: _raw_spin_lock_irq+0x27/0x30 ib_uverbs_release_uevent+0x1e/0xa0 [ib_uverbs] uverbs_free_qp+0x7e/0x90 [ib_uverbs] destroy_hw_idr_uobject+0x1c/0x50 [ib_uverbs] uverbs_destroy_uobject+0x2e/0x180 [ib_uverbs] __uverbs_cleanup_ufile+0x73/0x90 [ib_uverbs] uverbs_destroy_ufile_hw+0x5d/0x120 [ib_uverbs] ib_uverbs_remove_one+0xea/0x240 [ib_uverbs] ib_unregister_device+0xfb/0x200 [ib_core] mlx5_ib_remove+0x51/0xe0 [mlx5_ib] mlx5_remove_device+0xc1/0xd0 [mlx5_core] mlx5_unregister_device+0x3d/0xb0 [mlx5_core] remove_one+0x2a/0x90 [mlx5_core] pci_device_remove+0x3b/0xc0 device_release_driver_internal+0x16d/0x240 unbind_store+0xb2/0x100 kernfs_fop_write+0x102/0x180 __vfs_write+0x36/0x1a0 ? __alloc_fd+0xa9/0x170 ? set_close_on_exec+0x49/0x70 vfs_write+0xad/0x1a0 ksys_write+0x52/0xc0 do_syscall_64+0x5b/0x180 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7fac551aac60 Cc: # 4.2 Fixes: 036b10635739 ("IB/uverbs: Enable device removal when there are active user space applications") Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/uverbs_main.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 2890a77339e1..15add0688fbb 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -204,6 +204,9 @@ void ib_uverbs_release_file(struct kref *ref) if (atomic_dec_and_test(&file->device->refcount)) ib_uverbs_comp_dev(file->device); + if (file->async_file) + kref_put(&file->async_file->ref, + ib_uverbs_release_async_event_file); put_device(&file->device->dev); kfree(file); } @@ -1096,10 +1099,6 @@ static int ib_uverbs_close(struct inode *inode, struct file *filp) list_del_init(&file->list); mutex_unlock(&file->device->lists_mutex); - if (file->async_file) - kref_put(&file->async_file->ref, - ib_uverbs_release_async_event_file); - kref_put(&file->ref, ib_uverbs_release_file); return 0; From c1b03c25f5c1503e2db3ac1c0e12ef3e054fa065 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Thu, 24 Jan 2019 14:33:32 +0200 Subject: [PATCH 122/525] RDMA/mlx5: Fix flow creation on representors The intention of the flow_is_supported was to disable the entire tree and methods that allow raw flow creation, but the grammar syntax has this disable the entire UVERBS_FLOW object. Since the method requires a MLX5_IB_OBJECT_FLOW_MATCHER there is no need to do anything, as it is automatically disabled when matchers are disabled. This restores the ability to create flow steering rules on representors via regular verbs. Fixes: a1462351b590 ("RDMA/mlx5: Fail early if user tries to create flows on IB representors") Signed-off-by: Mark Bloch Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/flow.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/flow.c b/drivers/infiniband/hw/mlx5/flow.c index e8a1e4498e3f..798591a18484 100644 --- a/drivers/infiniband/hw/mlx5/flow.c +++ b/drivers/infiniband/hw/mlx5/flow.c @@ -630,8 +630,7 @@ const struct uapi_definition mlx5_ib_flow_defs[] = { UAPI_DEF_IS_OBJ_SUPPORTED(flow_is_supported)), UAPI_DEF_CHAIN_OBJ_TREE( UVERBS_OBJECT_FLOW, - &mlx5_ib_fs, - UAPI_DEF_IS_OBJ_SUPPORTED(flow_is_supported)), + &mlx5_ib_fs), UAPI_DEF_CHAIN_OBJ_TREE(UVERBS_OBJECT_FLOW_ACTION, &mlx5_ib_flow_actions), {}, From f8ade8e2429758efa1eddf0a6e2cc936714afc8d Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 24 Jan 2019 15:00:07 +0200 Subject: [PATCH 123/525] IB/uverbs: Fix ioctl query port to consider device disassociation Methods cannot peak into the ufile, the only way to get a ucontext and hence a device is via the ib_uverbs_get_ucontext() call or inspecing a locked uobject. Otherwise during/after disassociation the pointers may be null or free'd. BUG: unable to handle kernel NULL pointer dereference at 0000000000000078 PGD 800000005ece6067 P4D 800000005ece6067 PUD 5ece7067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 10631 Comm: ibv_ud_pingpong Tainted: GW OE 4.20.0-rc6+ #3 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:ib_uverbs_handler_UVERBS_METHOD_QUERY_PORT+0x53/0x191 [ib_uverbs] Code: 80 00 00 00 31 c0 48 8b 47 40 48 8d 5c 24 38 48 8d 6c 24 08 48 89 df 48 8b 40 08 4c 8b a0 18 03 00 00 31 c0 f3 48 ab 48 89 ef <49> 83 7c 24 78 00 b1 06 f3 48 ab 0f 84 89 00 00 00 45 31 c9 31 d2 RSP: 0018:ffffb54802ccfb10 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffffb54802ccfb48 RCX:0000000000000000 RDX: fffffffffffffffa RSI: ffffb54802ccfcf8 RDI:ffffb54802ccfb18 RBP: ffffb54802ccfb18 R08: ffffb54802ccfd18 R09:0000000000000000 R10: 0000000000000000 R11: 00000000000000d0 R12:0000000000000000 R13: ffffb54802ccfcb0 R14: ffffb54802ccfc48 R15:ffff9f736e0059a0 FS: 00007f55a6bd7740(0000) GS:ffff9f737ba00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000078 CR3: 0000000064214000 CR4:00000000000006f0 Call Trace: ib_uverbs_cmd_verbs.isra.5+0x94d/0xa60 [ib_uverbs] ? copy_port_attr_to_resp+0x120/0x120 [ib_uverbs] ? arch_tlb_finish_mmu+0x16/0xc0 ? tlb_finish_mmu+0x1f/0x30 ? unmap_region+0xd9/0x120 ib_uverbs_ioctl+0xbc/0x120 [ib_uverbs] do_vfs_ioctl+0xa9/0x620 ? __do_munmap+0x29f/0x3a0 ksys_ioctl+0x60/0x90 __x64_sys_ioctl+0x16/0x20 do_syscall_64+0x5b/0x180 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f55a62cb567 Fixes: 641d1207d2ed ("IB/core: Move query port to ioctl") Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/uverbs_std_types_device.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/core/uverbs_std_types_device.c b/drivers/infiniband/core/uverbs_std_types_device.c index 5030ec480370..2a3f2f01028d 100644 --- a/drivers/infiniband/core/uverbs_std_types_device.c +++ b/drivers/infiniband/core/uverbs_std_types_device.c @@ -168,12 +168,18 @@ void copy_port_attr_to_resp(struct ib_port_attr *attr, static int UVERBS_HANDLER(UVERBS_METHOD_QUERY_PORT)( struct uverbs_attr_bundle *attrs) { - struct ib_device *ib_dev = attrs->ufile->device->ib_dev; + struct ib_device *ib_dev; struct ib_port_attr attr = {}; struct ib_uverbs_query_port_resp_ex resp = {}; + struct ib_ucontext *ucontext; int ret; u8 port_num; + ucontext = ib_uverbs_get_ucontext(attrs); + if (IS_ERR(ucontext)) + return PTR_ERR(ucontext); + ib_dev = ucontext->device; + /* FIXME: Extend the UAPI_DEF_OBJ_NEEDS_FN stuff.. */ if (!ib_dev->ops.query_port) return -EOPNOTSUPP; From 70999ec1c9d3f783a7232973cfc26971e5732758 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Fri, 25 Jan 2019 15:12:45 -0300 Subject: [PATCH 124/525] MIPS: DTS: jz4740: Correct interrupt number of DMA core The interrupt number set in the devicetree node of the DMA driver was wrong. Signed-off-by: Paul Cercueil Signed-off-by: Paul Burton Cc: Rob Herring Cc: Mark Rutland Cc: Ralf Baechle Cc: James Hogan Cc: devicetree@vger.kernel.org Cc: linux-mips@vger.kernel.org Cc: linux-kernel@vger.kernel.org --- arch/mips/boot/dts/ingenic/jz4740.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/boot/dts/ingenic/jz4740.dtsi b/arch/mips/boot/dts/ingenic/jz4740.dtsi index 6fb16fd24035..2beb78a62b7d 100644 --- a/arch/mips/boot/dts/ingenic/jz4740.dtsi +++ b/arch/mips/boot/dts/ingenic/jz4740.dtsi @@ -161,7 +161,7 @@ #dma-cells = <2>; interrupt-parent = <&intc>; - interrupts = <29>; + interrupts = <20>; clocks = <&cgu JZ4740_CLK_DMA>; From 6ab4aba00f811a5265acc4d3eb1863bb3ca60562 Mon Sep 17 00:00:00 2001 From: Feras Daoud Date: Thu, 24 Jan 2019 14:33:19 +0200 Subject: [PATCH 125/525] IB/ipoib: Fix for use-after-free in ipoib_cm_tx_start The following BUG was reported by kasan: BUG: KASAN: use-after-free in ipoib_cm_tx_start+0x430/0x1390 [ib_ipoib] Read of size 80 at addr ffff88034c30bcd0 by task kworker/u16:1/24020 Workqueue: ipoib_wq ipoib_cm_tx_start [ib_ipoib] Call Trace: dump_stack+0x9a/0xeb print_address_description+0xe3/0x2e0 kasan_report+0x18a/0x2e0 ? ipoib_cm_tx_start+0x430/0x1390 [ib_ipoib] memcpy+0x1f/0x50 ipoib_cm_tx_start+0x430/0x1390 [ib_ipoib] ? kvm_clock_read+0x1f/0x30 ? ipoib_cm_skb_reap+0x610/0x610 [ib_ipoib] ? __lock_is_held+0xc2/0x170 ? process_one_work+0x880/0x1960 ? process_one_work+0x912/0x1960 process_one_work+0x912/0x1960 ? wq_pool_ids_show+0x310/0x310 ? lock_acquire+0x145/0x440 worker_thread+0x87/0xbb0 ? process_one_work+0x1960/0x1960 kthread+0x314/0x3d0 ? kthread_create_worker_on_cpu+0xc0/0xc0 ret_from_fork+0x3a/0x50 Allocated by task 0: kasan_kmalloc+0xa0/0xd0 kmem_cache_alloc_trace+0x168/0x3e0 path_rec_create+0xa2/0x1f0 [ib_ipoib] ipoib_start_xmit+0xa98/0x19e0 [ib_ipoib] dev_hard_start_xmit+0x159/0x8d0 sch_direct_xmit+0x226/0xb40 __dev_queue_xmit+0x1d63/0x2950 neigh_update+0x889/0x1770 arp_process+0xc47/0x21f0 arp_rcv+0x462/0x760 __netif_receive_skb_core+0x1546/0x2da0 netif_receive_skb_internal+0xf2/0x590 napi_gro_receive+0x28e/0x390 ipoib_ib_handle_rx_wc_rss+0x873/0x1b60 [ib_ipoib] ipoib_rx_poll_rss+0x17d/0x320 [ib_ipoib] net_rx_action+0x427/0xe30 __do_softirq+0x28e/0xc42 Freed by task 26680: __kasan_slab_free+0x11d/0x160 kfree+0xf5/0x360 ipoib_flush_paths+0x532/0x9d0 [ib_ipoib] ipoib_set_mode_rss+0x1ad/0x560 [ib_ipoib] set_mode+0xc8/0x150 [ib_ipoib] kernfs_fop_write+0x279/0x440 __vfs_write+0xd8/0x5c0 vfs_write+0x15e/0x470 ksys_write+0xb8/0x180 do_syscall_64+0x9b/0x420 entry_SYSCALL_64_after_hwframe+0x49/0xbe The buggy address belongs to the object at ffff88034c30bcc8 which belongs to the cache kmalloc-512 of size 512 The buggy address is located 8 bytes inside of 512-byte region [ffff88034c30bcc8, ffff88034c30bec8) The buggy address belongs to the page: The following race between change mode and xmit flow is the reason for this use-after-free: Change mode Send packet 1 to GID XX Send packet 2 to GID XX | | | start | | | | | | | | | Create new path for GID XX | | and update neigh path | | | | | | | | | | flush_paths | | | | queue_work(cm.start_task) | | Path for GID XX not found | create new path | | start_task runs with old released path There is no locking to protect the lifetime of the path through the ipoib_cm_tx struct, so delete it entirely and always use the newly looked up path under the priv->lock. Fixes: 546481c2816e ("IB/ipoib: Fix memory corruption in ipoib cm mode connect flow") Signed-off-by: Feras Daoud Reviewed-by: Erez Shitrit Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/ulp/ipoib/ipoib.h | 1 - drivers/infiniband/ulp/ipoib/ipoib_cm.c | 3 +-- 2 files changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index 1da119d901a9..73e808c1e6ad 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -248,7 +248,6 @@ struct ipoib_cm_tx { struct list_head list; struct net_device *dev; struct ipoib_neigh *neigh; - struct ipoib_path *path; struct ipoib_tx_buf *tx_ring; unsigned int tx_head; unsigned int tx_tail; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index 0428e01e8f69..aa9dcfc36cd3 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -1312,7 +1312,6 @@ struct ipoib_cm_tx *ipoib_cm_create_tx(struct net_device *dev, struct ipoib_path neigh->cm = tx; tx->neigh = neigh; - tx->path = path; tx->dev = dev; list_add(&tx->list, &priv->cm.start_list); set_bit(IPOIB_FLAG_INITIALIZED, &tx->flags); @@ -1371,7 +1370,7 @@ static void ipoib_cm_tx_start(struct work_struct *work) neigh->daddr + QPN_AND_OPTIONS_OFFSET); goto free_neigh; } - memcpy(&pathrec, &p->path->pathrec, sizeof(pathrec)); + memcpy(&pathrec, &path->pathrec, sizeof(pathrec)); spin_unlock_irqrestore(&priv->lock, flags); netif_tx_unlock_bh(dev); From 1ca1c87f91d9dc50d6a38e2177b2032996e7901c Mon Sep 17 00:00:00 2001 From: Zhou Yanjie Date: Fri, 25 Jan 2019 02:22:15 +0800 Subject: [PATCH 126/525] DTS: CI20: Fix bugs in ci20's device tree. According to the Schematic, the hardware of ci20 leads to uart3, but not to uart2. Uart2 is miswritten in the original code. Signed-off-by: Zhou Yanjie Signed-off-by: Paul Burton Cc: linux-mips Cc: linux-kernel Cc: devicetree@vger.kernel.org Cc: robh+dt@kernel.org Cc: ralf@linux-mips.org Cc: jhogan@kernel.org Cc: mark.rutland@arm.com Cc: malat@debian.org Cc: ezequiel@collabora.co.uk Cc: ulf.hansson@linaro.org Cc: syq Cc: jiaxun.yang --- arch/mips/boot/dts/ingenic/ci20.dts | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/mips/boot/dts/ingenic/ci20.dts b/arch/mips/boot/dts/ingenic/ci20.dts index 50cff3cbcc6d..4f7b1fa31cf5 100644 --- a/arch/mips/boot/dts/ingenic/ci20.dts +++ b/arch/mips/boot/dts/ingenic/ci20.dts @@ -76,7 +76,7 @@ status = "okay"; pinctrl-names = "default"; - pinctrl-0 = <&pins_uart2>; + pinctrl-0 = <&pins_uart3>; }; &uart4 { @@ -196,9 +196,9 @@ bias-disable; }; - pins_uart2: uart2 { - function = "uart2"; - groups = "uart2-data", "uart2-hwflow"; + pins_uart3: uart3 { + function = "uart3"; + groups = "uart3-data", "uart3-hwflow"; bias-disable; }; From 4e046de0f50e04acd48eb373d6a9061ddf014e0c Mon Sep 17 00:00:00 2001 From: Bodong Wang Date: Sun, 13 Jan 2019 22:47:26 -0600 Subject: [PATCH 127/525] Revert "net/mlx5e: E-Switch, Initialize eswitch only if eswitch manager" This reverts commit 5f5991f36dce1e69dd8bd7495763eec2e28f08e7. With the original commit, eswitch instance will not be initialized for a function which is vport group manager but not eswitch manager such as host PF on SmartNIC (BlueField) card. This will result in a kernel crash when such a vport group manager is trying to access vports in its group. E.g, PF vport manager (not eswitch manager) tries to configure the MAC of its VF vport, a kernel trace will happen similar as bellow: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 ... RIP: 0010:mlx5_eswitch_get_vport_config+0xc/0x180 [mlx5_core] ... Fixes: 5f5991f36dce ("net/mlx5e: E-Switch, Initialize eswitch only if eswitch manager") Signed-off-by: Bodong Wang Reported-by: Yuval Avnery Reviewed-by: Daniel Jurgens Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index a44ea7b85614..ab7a038c207c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1728,7 +1728,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) int vport_num; int err; - if (!MLX5_ESWITCH_MANAGER(dev)) + if (!MLX5_VPORT_MANAGER(dev)) return 0; esw_info(dev, @@ -1797,7 +1797,7 @@ abort: void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) { - if (!esw || !MLX5_ESWITCH_MANAGER(esw->dev)) + if (!esw || !MLX5_VPORT_MANAGER(esw->dev)) return; esw_info(esw->dev, "cleanup\n"); From 92b32772940b981240f6471a70c0fdbff23983ea Mon Sep 17 00:00:00 2001 From: Shay Agroskin Date: Sun, 6 Jan 2019 17:55:59 +0200 Subject: [PATCH 128/525] net/mlx5e: Fix wrong private flag usage causing checksum disable MLX5E_PFLAG_* definitions were changed from bitmask to enumerated values. However, in mlx5e_open_rq(), the proper API (MLX5E_GET_PFLAG macro) was not used to read the flag value of MLX5E_PFLAG_RX_NO_CSUM_COMPLETE. Fixed it. Fixes: 8ff57c18e9f6 ("net/mlx5e: Improve ethtool private-flags code structure") Signed-off-by: Shay Agroskin Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 8cfd2ec7c0a2..01819e5c9975 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -950,7 +950,7 @@ static int mlx5e_open_rq(struct mlx5e_channel *c, if (params->rx_dim_enabled) __set_bit(MLX5E_RQ_STATE_AM, &c->rq.state); - if (params->pflags & MLX5E_PFLAG_RX_NO_CSUM_COMPLETE) + if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE)) __set_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &c->rq.state); return 0; From 33814e5d127e21f53b52e17b0722c1b57d4f4d29 Mon Sep 17 00:00:00 2001 From: Moni Shoua Date: Wed, 26 Dec 2018 19:21:21 +0200 Subject: [PATCH 129/525] net/mlx5: Take lock with IRQs disabled to avoid deadlock The lock in qp_table might be taken from process context or from interrupt context. This may lead to a deadlock unless it is taken with IRQs disabled. Discovered by lockdep ================================ WARNING: inconsistent lock state 4.20.0-rc6 -------------------------------- inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} python/12572 [HC1[1]:SC0[0]:HE0:SE1] takes: 00000000052a4df4 (&(&table->lock)->rlock#2){?.+.}, /0x50 [mlx5_core] {HARDIRQ-ON-W} state was registered at: _raw_spin_lock+0x33/0x70 mlx5_get_rsc+0x1a/0x50 [mlx5_core] mlx5_ib_eqe_pf_action+0x493/0x1be0 [mlx5_ib] process_one_work+0x90c/0x1820 worker_thread+0x87/0xbb0 kthread+0x320/0x3e0 ret_from_fork+0x24/0x30 irq event stamp: 103928 hardirqs last enabled at (103927): [] nk+0x1a/0x1c hardirqs last disabled at (103928): [] unk+0x1a/0x1c softirqs last enabled at (103924): [] tcp_sendmsg+0x31/0x40 softirqs last disabled at (103922): [] 80 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&(&table->lock)->rlock#2); lock(&(&table->lock)->rlock#2); *** DEADLOCK *** Fixes: 032080ab43ac ("IB/mlx5: Lock QP during page fault handling") Signed-off-by: Moni Shoua Reviewed-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/qp.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c index 388f205a497f..370ca94b6775 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c @@ -44,14 +44,15 @@ static struct mlx5_core_rsc_common * mlx5_get_rsc(struct mlx5_qp_table *table, u32 rsn) { struct mlx5_core_rsc_common *common; + unsigned long flags; - spin_lock(&table->lock); + spin_lock_irqsave(&table->lock, flags); common = radix_tree_lookup(&table->tree, rsn); if (common) atomic_inc(&common->refcount); - spin_unlock(&table->lock); + spin_unlock_irqrestore(&table->lock, flags); return common; } From 9d2cbdc5d334967c35b5f58c7bf3208e17325647 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Mon, 24 Dec 2018 09:48:42 +0200 Subject: [PATCH 130/525] net/mlx5e: Allow MAC invalidation while spoofchk is ON Prior to this patch the driver prohibited spoof checking on invalid MAC. Now the user can set this configuration if it wishes to. This is required since libvirt might invalidate the VF Mac by setting it to zero, while spoofcheck is ON. Fixes: 1ab2068a4c66 ("net/mlx5: Implement vports admin state backup/restore") Signed-off-by: Aya Levin Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/eswitch.c | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index ab7a038c207c..5b492b67f4e1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1134,13 +1134,6 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw, int err = 0; u8 *smac_v; - if (vport->info.spoofchk && !is_valid_ether_addr(vport->info.mac)) { - mlx5_core_warn(esw->dev, - "vport[%d] configure ingress rules failed, illegal mac with spoofchk\n", - vport->vport); - return -EPERM; - } - esw_vport_cleanup_ingress_rules(esw, vport); if (!vport->info.vlan && !vport->info.qos && !vport->info.spoofchk) { @@ -1827,13 +1820,10 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw, mutex_lock(&esw->state_lock); evport = &esw->vports[vport]; - if (evport->info.spoofchk && !is_valid_ether_addr(mac)) { + if (evport->info.spoofchk && !is_valid_ether_addr(mac)) mlx5_core_warn(esw->dev, - "MAC invalidation is not allowed when spoofchk is on, vport(%d)\n", + "Set invalid MAC while spoofchk is on, vport(%d)\n", vport); - err = -EPERM; - goto unlock; - } err = mlx5_modify_nic_vport_mac_address(esw->dev, vport, mac); if (err) { @@ -1979,6 +1969,10 @@ int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw, evport = &esw->vports[vport]; pschk = evport->info.spoofchk; evport->info.spoofchk = spoofchk; + if (pschk && !is_valid_ether_addr(evport->info.mac)) + mlx5_core_warn(esw->dev, + "Spoofchk in set while MAC is invalid, vport(%d)\n", + evport->vport); if (evport->enabled && esw->mode == SRIOV_LEGACY) err = esw_vport_ingress_config(esw, evport); if (err) From c12ecc2305648822970002871230979359edb2c0 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Wed, 25 Apr 2018 17:32:04 +0300 Subject: [PATCH 131/525] net/mlx5e: Move to use common phys port names for vport representors With VF LAG commit 491c37e49b48 "net/mlx5e: In case of LAG, one switch parent id is used for all representors", both uplinks and all the VFs (on both of them) get the same switchdev id. This cause the provisioning system method to identify the rep of a given VF from the parent PF PCI device using switchev id and physical port name to break, since VFm of PF0 will have the (id, name) as VFm of PF1. To fix that, we align to use the framework agreed upstream and set by nfp commit 168c478e107e "nfp: wire get_phys_port_name on representors": $ cat /sys/class/net/eth4_*/phys_port_name p0 pf0vf0 pf0vf1 Now, the names will be different, e.g. pf0vf0 vs. pf1vf0. Fixes: 491c37e49b48 ("net/mlx5e: In case of LAG, one switch parent id is used for all representors") Signed-off-by: Or Gerlitz Reported-by: Waleed Musa Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/en_rep.c | 12 +++++++++-- drivers/net/ethernet/mellanox/mlx5/core/lag.c | 21 +++++++++++++++++++ .../ethernet/mellanox/mlx5/core/mlx5_core.h | 2 ++ 3 files changed, 33 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 04736212a21c..f75227222db3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1126,9 +1126,17 @@ static int mlx5e_rep_get_phys_port_name(struct net_device *dev, struct mlx5e_priv *priv = netdev_priv(dev); struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *rep = rpriv->rep; - int ret; + int ret, pf_num; + + ret = mlx5_lag_get_pf_num(priv->mdev, &pf_num); + if (ret) + return ret; + + if (rep->vport == FDB_UPLINK_VPORT) + ret = snprintf(buf, len, "p%d", pf_num); + else + ret = snprintf(buf, len, "pf%dvf%d", pf_num, rep->vport - 1); - ret = snprintf(buf, len, "%d", rep->vport - 1); if (ret >= len) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c index 3a6baed722d8..2d223385dc81 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c @@ -616,6 +616,27 @@ void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev) } } +int mlx5_lag_get_pf_num(struct mlx5_core_dev *dev, int *pf_num) +{ + struct mlx5_lag *ldev; + int n; + + ldev = mlx5_lag_dev_get(dev); + if (!ldev) { + mlx5_core_warn(dev, "no lag device, can't get pf num\n"); + return -EINVAL; + } + + for (n = 0; n < MLX5_MAX_PORTS; n++) + if (ldev->pf[n].dev == dev) { + *pf_num = n; + return 0; + } + + mlx5_core_warn(dev, "wasn't able to locate pf in the lag device\n"); + return -EINVAL; +} + /* Must be called with intf_mutex held */ void mlx5_lag_remove(struct mlx5_core_dev *dev) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index c68dcea5985b..5300b0b6d836 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -187,6 +187,8 @@ static inline int mlx5_lag_is_lacp_owner(struct mlx5_core_dev *dev) MLX5_CAP_GEN(dev, lag_master); } +int mlx5_lag_get_pf_num(struct mlx5_core_dev *dev, int *pf_num); + void mlx5_reload_interface(struct mlx5_core_dev *mdev, int protocol); void mlx5_lag_update(struct mlx5_core_dev *dev); From 6ce966fd2671899a48037abe7bf1df80a5adf029 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Tue, 1 Jan 2019 12:44:52 +0200 Subject: [PATCH 132/525] net/mlx5e: Unblock setting vid 0 for VFs through the uplink rep It turns out that libvirt uses 0-vid as a default if no vlan was set for the guest (which is the case for switchdev mode) and errs if we disallow that: error: Failed to start domain vm75 error: Cannot set interface MAC/vlanid to 6a:66:2d:48:92:c2/0 \ for ifname enp59s0f0 vf 0: Operation not supported So allow this in order not to break existing systems. Signed-off-by: Or Gerlitz Reported-by: Maor Dickman Reviewed-by: Gavi Teitz Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index f75227222db3..f2573c2d2b5c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1293,6 +1293,18 @@ static int mlx5e_uplink_rep_set_mac(struct net_device *netdev, void *addr) return 0; } +static int mlx5e_uplink_rep_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos, + __be16 vlan_proto) +{ + netdev_warn_once(dev, "legacy vf vlan setting isn't supported in switchdev mode\n"); + + if (vlan != 0) + return -EOPNOTSUPP; + + /* allow setting 0-vid for compatibility with libvirt */ + return 0; +} + static const struct switchdev_ops mlx5e_rep_switchdev_ops = { .switchdev_port_attr_get = mlx5e_attr_get, }; @@ -1327,6 +1339,7 @@ static const struct net_device_ops mlx5e_netdev_ops_uplink_rep = { .ndo_set_vf_rate = mlx5e_set_vf_rate, .ndo_get_vf_config = mlx5e_get_vf_config, .ndo_get_vf_stats = mlx5e_get_vf_stats, + .ndo_set_vf_vlan = mlx5e_uplink_rep_set_vf_vlan, }; bool mlx5e_eswitch_rep(struct net_device *netdev) From 2b531b6137834a55857a337ac17510d6436b6fbb Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 10 Jan 2019 12:38:02 +0000 Subject: [PATCH 133/525] selftests: cpu-hotplug: fix case where CPUs offline > CPUs present The cpu-hotplug test assumes that we can offline the maximum CPU as described by /sys/devices/system/cpu/offline. However, in the case where the number of CPUs exceeds like kernel configuration then the offline count can be greater than the present count and we end up trying to test the offlining of a CPU that is not available to offline. Fix this by testing the maximum present CPU instead. Also, the test currently offlines the CPU and does not online it, so fix this by onlining the CPU after the test. Fixes: d89dffa976bc ("fault-injection: add selftests for cpu and memory hotplug") Signed-off-by: Colin Ian King Signed-off-by: Shuah Khan --- .../selftests/cpu-hotplug/cpu-on-off-test.sh | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh index bab13dd025a6..0d26b5e3f966 100755 --- a/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh +++ b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh @@ -37,6 +37,10 @@ prerequisite() exit $ksft_skip fi + present_cpus=`cat $SYSFS/devices/system/cpu/present` + present_max=${present_cpus##*-} + echo "present_cpus = $present_cpus present_max = $present_max" + echo -e "\t Cpus in online state: $online_cpus" offline_cpus=`cat $SYSFS/devices/system/cpu/offline` @@ -151,6 +155,8 @@ online_cpus=0 online_max=0 offline_cpus=0 offline_max=0 +present_cpus=0 +present_max=0 while getopts e:ahp: opt; do case $opt in @@ -190,9 +196,10 @@ if [ $allcpus -eq 0 ]; then online_cpu_expect_success $online_max if [[ $offline_cpus -gt 0 ]]; then - echo -e "\t offline to online to offline: cpu $offline_max" - online_cpu_expect_success $offline_max - offline_cpu_expect_success $offline_max + echo -e "\t offline to online to offline: cpu $present_max" + online_cpu_expect_success $present_max + offline_cpu_expect_success $present_max + online_cpu $present_max fi exit 0 else From 7e35a5940fab59eeccb9162eb2389342e0a87e53 Mon Sep 17 00:00:00 2001 From: Sean Young Date: Thu, 17 Jan 2019 15:29:38 +0000 Subject: [PATCH 134/525] selftests: Use lirc.h from kernel tree, not from system MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When the system lirc.h is older than v4.16, you will get errors like: ir_loopback.c:32:16: error: field ‘proto’ has incomplete type enum rc_proto proto; Cc: Shuah Khan Signed-off-by: Sean Young Signed-off-by: Shuah Khan --- tools/testing/selftests/ir/Makefile | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/ir/Makefile b/tools/testing/selftests/ir/Makefile index f4ba8eb84b95..ad06489c22a5 100644 --- a/tools/testing/selftests/ir/Makefile +++ b/tools/testing/selftests/ir/Makefile @@ -1,5 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 TEST_PROGS := ir_loopback.sh TEST_GEN_PROGS_EXTENDED := ir_loopback +APIDIR := ../../../include/uapi +CFLAGS += -Wall -O2 -I$(APIDIR) include ../lib.mk From ed5f13261cb65b02c611ae9971677f33581d4286 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 25 Jan 2019 10:33:59 -0800 Subject: [PATCH 135/525] selftests/seccomp: Enhance per-arch ptrace syscall skip tests Passing EPERM during syscall skipping was confusing since the test wasn't actually exercising the errno evaluation -- it was just passing a literal "1" (EPERM). Instead, expand the tests to check both direct value returns (positive, 45000 in this case), and errno values (negative, -ESRCH in this case) to check both fake success and fake failure during syscall skipping. Reported-by: Colin Ian King Fixes: a33b2d0359a0 ("selftests/seccomp: Add tests for basic ptrace actions") Cc: stable@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: Shuah Khan --- tools/testing/selftests/seccomp/seccomp_bpf.c | 72 +++++++++++++++---- 1 file changed, 57 insertions(+), 15 deletions(-) diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 496a9a8c773a..7e632b465ab4 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -1608,7 +1608,16 @@ TEST_F(TRACE_poke, getpid_runs_normally) #ifdef SYSCALL_NUM_RET_SHARE_REG # define EXPECT_SYSCALL_RETURN(val, action) EXPECT_EQ(-1, action) #else -# define EXPECT_SYSCALL_RETURN(val, action) EXPECT_EQ(val, action) +# define EXPECT_SYSCALL_RETURN(val, action) \ + do { \ + errno = 0; \ + if (val < 0) { \ + EXPECT_EQ(-1, action); \ + EXPECT_EQ(-(val), errno); \ + } else { \ + EXPECT_EQ(val, action); \ + } \ + } while (0) #endif /* Use PTRACE_GETREGS and PTRACE_SETREGS when available. This is useful for @@ -1647,7 +1656,7 @@ int get_syscall(struct __test_metadata *_metadata, pid_t tracee) /* Architecture-specific syscall changing routine. */ void change_syscall(struct __test_metadata *_metadata, - pid_t tracee, int syscall) + pid_t tracee, int syscall, int result) { int ret; ARCH_REGS regs; @@ -1706,7 +1715,7 @@ void change_syscall(struct __test_metadata *_metadata, #ifdef SYSCALL_NUM_RET_SHARE_REG TH_LOG("Can't modify syscall return on this architecture"); #else - regs.SYSCALL_RET = EPERM; + regs.SYSCALL_RET = result; #endif #ifdef HAVE_GETREGS @@ -1734,14 +1743,19 @@ void tracer_syscall(struct __test_metadata *_metadata, pid_t tracee, case 0x1002: /* change getpid to getppid. */ EXPECT_EQ(__NR_getpid, get_syscall(_metadata, tracee)); - change_syscall(_metadata, tracee, __NR_getppid); + change_syscall(_metadata, tracee, __NR_getppid, 0); break; case 0x1003: - /* skip gettid. */ + /* skip gettid with valid return code. */ EXPECT_EQ(__NR_gettid, get_syscall(_metadata, tracee)); - change_syscall(_metadata, tracee, -1); + change_syscall(_metadata, tracee, -1, 45000); break; case 0x1004: + /* skip openat with error. */ + EXPECT_EQ(__NR_openat, get_syscall(_metadata, tracee)); + change_syscall(_metadata, tracee, -1, -ESRCH); + break; + case 0x1005: /* do nothing (allow getppid) */ EXPECT_EQ(__NR_getppid, get_syscall(_metadata, tracee)); break; @@ -1774,9 +1788,11 @@ void tracer_ptrace(struct __test_metadata *_metadata, pid_t tracee, nr = get_syscall(_metadata, tracee); if (nr == __NR_getpid) - change_syscall(_metadata, tracee, __NR_getppid); + change_syscall(_metadata, tracee, __NR_getppid, 0); + if (nr == __NR_gettid) + change_syscall(_metadata, tracee, -1, 45000); if (nr == __NR_openat) - change_syscall(_metadata, tracee, -1); + change_syscall(_metadata, tracee, -1, -ESRCH); } FIXTURE_DATA(TRACE_syscall) { @@ -1793,8 +1809,10 @@ FIXTURE_SETUP(TRACE_syscall) BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1002), BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_gettid, 0, 1), BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1003), - BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_openat, 0, 1), BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1004), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1005), BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), }; @@ -1842,15 +1860,26 @@ TEST_F(TRACE_syscall, ptrace_syscall_redirected) EXPECT_NE(self->mypid, syscall(__NR_getpid)); } -TEST_F(TRACE_syscall, ptrace_syscall_dropped) +TEST_F(TRACE_syscall, ptrace_syscall_errno) { /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ teardown_trace_fixture(_metadata, self->tracer); self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, true); - /* Tracer should skip the open syscall, resulting in EPERM. */ - EXPECT_SYSCALL_RETURN(EPERM, syscall(__NR_openat)); + /* Tracer should skip the open syscall, resulting in ESRCH. */ + EXPECT_SYSCALL_RETURN(-ESRCH, syscall(__NR_openat)); +} + +TEST_F(TRACE_syscall, ptrace_syscall_faked) +{ + /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ + teardown_trace_fixture(_metadata, self->tracer); + self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, + true); + + /* Tracer should skip the gettid syscall, resulting fake pid. */ + EXPECT_SYSCALL_RETURN(45000, syscall(__NR_gettid)); } TEST_F(TRACE_syscall, syscall_allowed) @@ -1883,7 +1912,21 @@ TEST_F(TRACE_syscall, syscall_redirected) EXPECT_NE(self->mypid, syscall(__NR_getpid)); } -TEST_F(TRACE_syscall, syscall_dropped) +TEST_F(TRACE_syscall, syscall_errno) +{ + long ret; + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret); + + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); + ASSERT_EQ(0, ret); + + /* openat has been skipped and an errno return. */ + EXPECT_SYSCALL_RETURN(-ESRCH, syscall(__NR_openat)); +} + +TEST_F(TRACE_syscall, syscall_faked) { long ret; @@ -1894,8 +1937,7 @@ TEST_F(TRACE_syscall, syscall_dropped) ASSERT_EQ(0, ret); /* gettid has been skipped and an altered return value stored. */ - EXPECT_SYSCALL_RETURN(EPERM, syscall(__NR_gettid)); - EXPECT_NE(self->mytid, syscall(__NR_gettid)); + EXPECT_SYSCALL_RETURN(45000, syscall(__NR_gettid)); } TEST_F(TRACE_syscall, skip_after_RET_TRACE) From 32a7726c4f4aadfabdb82440d84f88a5a2c8fe13 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Fri, 21 Dec 2018 08:26:20 -0800 Subject: [PATCH 136/525] xtensa: SMP: fix secondary CPU initialization - add missing memory barriers to the secondary CPU synchronization spin loops; add comment to the matching memory barrier in the boot_secondary and __cpu_die functions; - use READ_ONCE/WRITE_ONCE to access cpu_start_id/cpu_start_ccount instead of reading/writing them directly; - re-initialize cpu_running every time before starting secondary CPU to flush possible previous CPU startup results. Signed-off-by: Max Filippov --- arch/xtensa/kernel/head.S | 5 ++++- arch/xtensa/kernel/smp.c | 34 +++++++++++++++++++++------------- 2 files changed, 25 insertions(+), 14 deletions(-) diff --git a/arch/xtensa/kernel/head.S b/arch/xtensa/kernel/head.S index da08e75100ab..7f009719304e 100644 --- a/arch/xtensa/kernel/head.S +++ b/arch/xtensa/kernel/head.S @@ -276,12 +276,13 @@ should_never_return: movi a2, cpu_start_ccount 1: + memw l32i a3, a2, 0 beqi a3, 0, 1b movi a3, 0 s32i a3, a2, 0 - memw 1: + memw l32i a3, a2, 0 beqi a3, 0, 1b wsr a3, ccount @@ -317,11 +318,13 @@ ENTRY(cpu_restart) rsr a0, prid neg a2, a0 movi a3, cpu_start_id + memw s32i a2, a3, 0 #if XCHAL_DCACHE_IS_WRITEBACK dhwbi a3, 0 #endif 1: + memw l32i a2, a3, 0 dhi a3, 0 bne a2, a0, 1b diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c index 932d64689bac..c9fc2c4f71b3 100644 --- a/arch/xtensa/kernel/smp.c +++ b/arch/xtensa/kernel/smp.c @@ -195,9 +195,11 @@ static int boot_secondary(unsigned int cpu, struct task_struct *ts) int i; #ifdef CONFIG_HOTPLUG_CPU - cpu_start_id = cpu; - system_flush_invalidate_dcache_range( - (unsigned long)&cpu_start_id, sizeof(cpu_start_id)); + WRITE_ONCE(cpu_start_id, cpu); + /* Pairs with the third memw in the cpu_restart */ + mb(); + system_flush_invalidate_dcache_range((unsigned long)&cpu_start_id, + sizeof(cpu_start_id)); #endif smp_call_function_single(0, mx_cpu_start, (void *)cpu, 1); @@ -206,18 +208,21 @@ static int boot_secondary(unsigned int cpu, struct task_struct *ts) ccount = get_ccount(); while (!ccount); - cpu_start_ccount = ccount; + WRITE_ONCE(cpu_start_ccount, ccount); - while (time_before(jiffies, timeout)) { + do { + /* + * Pairs with the first two memws in the + * .Lboot_secondary. + */ mb(); - if (!cpu_start_ccount) - break; - } + ccount = READ_ONCE(cpu_start_ccount); + } while (ccount && time_before(jiffies, timeout)); - if (cpu_start_ccount) { + if (ccount) { smp_call_function_single(0, mx_cpu_stop, - (void *)cpu, 1); - cpu_start_ccount = 0; + (void *)cpu, 1); + WRITE_ONCE(cpu_start_ccount, 0); return -EIO; } } @@ -237,6 +242,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) pr_debug("%s: Calling wakeup_secondary(cpu:%d, idle:%p, sp: %08lx)\n", __func__, cpu, idle, start_info.stack); + init_completion(&cpu_running); ret = boot_secondary(cpu, idle); if (ret == 0) { wait_for_completion_timeout(&cpu_running, @@ -298,8 +304,10 @@ void __cpu_die(unsigned int cpu) unsigned long timeout = jiffies + msecs_to_jiffies(1000); while (time_before(jiffies, timeout)) { system_invalidate_dcache_range((unsigned long)&cpu_start_id, - sizeof(cpu_start_id)); - if (cpu_start_id == -cpu) { + sizeof(cpu_start_id)); + /* Pairs with the second memw in the cpu_restart */ + mb(); + if (READ_ONCE(cpu_start_id) == -cpu) { platform_cpu_kill(cpu); return; } From 306b38305c0f86de7f17c5b091a95451dcc93d7d Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Thu, 24 Jan 2019 17:16:11 -0800 Subject: [PATCH 137/525] xtensa: smp_lx200_defconfig: fix vectors clash Secondary CPU reset vector overlaps part of the double exception handler code, resulting in weird crashes and hangups when running user code. Move exception vectors one page up so that they don't clash with the secondary CPU reset vector. Signed-off-by: Max Filippov --- arch/xtensa/configs/smp_lx200_defconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/xtensa/configs/smp_lx200_defconfig b/arch/xtensa/configs/smp_lx200_defconfig index 11fed6c06a7c..b5938160fb3d 100644 --- a/arch/xtensa/configs/smp_lx200_defconfig +++ b/arch/xtensa/configs/smp_lx200_defconfig @@ -33,6 +33,7 @@ CONFIG_SMP=y CONFIG_HOTPLUG_CPU=y # CONFIG_INITIALIZE_XTENSA_MMU_INSIDE_VMLINUX is not set # CONFIG_PCI is not set +CONFIG_VECTORS_OFFSET=0x00002000 CONFIG_XTENSA_PLATFORM_XTFPGA=y CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=96M@0" From 8b1c42cdd7181200dc1fff39dcb6ac1a3fac2c25 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Sat, 19 Jan 2019 00:26:48 -0800 Subject: [PATCH 138/525] xtensa: SMP: mark each possible CPU as present Otherwise it is impossible to enable CPUs after booting with 'maxcpus' parameter. Signed-off-by: Max Filippov --- arch/xtensa/kernel/smp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c index c9fc2c4f71b3..80be6449c497 100644 --- a/arch/xtensa/kernel/smp.c +++ b/arch/xtensa/kernel/smp.c @@ -83,7 +83,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) { unsigned i; - for (i = 0; i < max_cpus; ++i) + for_each_possible_cpu(i) set_cpu_present(i, true); } From bb6652363be0415578ec4a8794cbe9403db9c336 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Thu, 24 Jan 2019 16:51:28 -0800 Subject: [PATCH 139/525] drivers/irqchip: xtensa: add warning to irq_retrigger XEA2 and MX PIC can only retrigger software interrupts. Issue a warning if an interrupt of any other type is retriggered. Signed-off-by: Max Filippov --- drivers/irqchip/irq-xtensa-mx.c | 6 +++++- drivers/irqchip/irq-xtensa-pic.c | 6 +++++- 2 files changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/irqchip/irq-xtensa-mx.c b/drivers/irqchip/irq-xtensa-mx.c index 5385f5768345..0bd3fe3b969e 100644 --- a/drivers/irqchip/irq-xtensa-mx.c +++ b/drivers/irqchip/irq-xtensa-mx.c @@ -113,7 +113,11 @@ static void xtensa_mx_irq_ack(struct irq_data *d) static int xtensa_mx_irq_retrigger(struct irq_data *d) { - xtensa_set_sr(1 << d->hwirq, intset); + unsigned int mask = 1u << d->hwirq; + + if (WARN_ON(mask & ~XCHAL_INTTYPE_MASK_SOFTWARE)) + return 0; + xtensa_set_sr(mask, intset); return 1; } diff --git a/drivers/irqchip/irq-xtensa-pic.c b/drivers/irqchip/irq-xtensa-pic.c index c200234dd2c9..ab12328be5ee 100644 --- a/drivers/irqchip/irq-xtensa-pic.c +++ b/drivers/irqchip/irq-xtensa-pic.c @@ -70,7 +70,11 @@ static void xtensa_irq_ack(struct irq_data *d) static int xtensa_irq_retrigger(struct irq_data *d) { - xtensa_set_sr(1 << d->hwirq, intset); + unsigned int mask = 1u << d->hwirq; + + if (WARN_ON(mask & ~XCHAL_INTTYPE_MASK_SOFTWARE)) + return 0; + xtensa_set_sr(mask, intset); return 1; } From eb271710ec0241a99d1cfcd2a887172ac0858aa9 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Thu, 24 Jan 2019 14:06:49 -0800 Subject: [PATCH 140/525] drivers/irqchip: xtensa-mx: fix mask and unmask xtensa_irq_mask and xtensa_irq_unmask don't do the right thing when called for the first two external IRQs. Treat these IRQs as per-CPU IRQs. Signed-off-by: Max Filippov --- drivers/irqchip/irq-xtensa-mx.c | 34 +++++++++++++++++++-------------- 1 file changed, 20 insertions(+), 14 deletions(-) diff --git a/drivers/irqchip/irq-xtensa-mx.c b/drivers/irqchip/irq-xtensa-mx.c index 0bd3fe3b969e..27933338f7b3 100644 --- a/drivers/irqchip/irq-xtensa-mx.c +++ b/drivers/irqchip/irq-xtensa-mx.c @@ -71,14 +71,17 @@ static void xtensa_mx_irq_mask(struct irq_data *d) unsigned int mask = 1u << d->hwirq; if (mask & (XCHAL_INTTYPE_MASK_EXTERN_EDGE | - XCHAL_INTTYPE_MASK_EXTERN_LEVEL)) { - set_er(1u << (xtensa_get_ext_irq_no(d->hwirq) - - HW_IRQ_MX_BASE), MIENG); - } else { - mask = __this_cpu_read(cached_irq_mask) & ~mask; - __this_cpu_write(cached_irq_mask, mask); - xtensa_set_sr(mask, intenable); + XCHAL_INTTYPE_MASK_EXTERN_LEVEL)) { + unsigned int ext_irq = xtensa_get_ext_irq_no(d->hwirq); + + if (ext_irq >= HW_IRQ_MX_BASE) { + set_er(1u << (ext_irq - HW_IRQ_MX_BASE), MIENG); + return; + } } + mask = __this_cpu_read(cached_irq_mask) & ~mask; + __this_cpu_write(cached_irq_mask, mask); + xtensa_set_sr(mask, intenable); } static void xtensa_mx_irq_unmask(struct irq_data *d) @@ -86,14 +89,17 @@ static void xtensa_mx_irq_unmask(struct irq_data *d) unsigned int mask = 1u << d->hwirq; if (mask & (XCHAL_INTTYPE_MASK_EXTERN_EDGE | - XCHAL_INTTYPE_MASK_EXTERN_LEVEL)) { - set_er(1u << (xtensa_get_ext_irq_no(d->hwirq) - - HW_IRQ_MX_BASE), MIENGSET); - } else { - mask |= __this_cpu_read(cached_irq_mask); - __this_cpu_write(cached_irq_mask, mask); - xtensa_set_sr(mask, intenable); + XCHAL_INTTYPE_MASK_EXTERN_LEVEL)) { + unsigned int ext_irq = xtensa_get_ext_irq_no(d->hwirq); + + if (ext_irq >= HW_IRQ_MX_BASE) { + set_er(1u << (ext_irq - HW_IRQ_MX_BASE), MIENGSET); + return; + } } + mask |= __this_cpu_read(cached_irq_mask); + __this_cpu_write(cached_irq_mask, mask); + xtensa_set_sr(mask, intenable); } static void xtensa_mx_irq_enable(struct irq_data *d) From ad33cc805223614166c8f4081288f0b3c4b0862d Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Fri, 18 Jan 2019 13:45:27 +0000 Subject: [PATCH 141/525] xtensa: Fix typo use space=>user space This patch fix a simple typo. Signed-off-by: Corentin Labbe Signed-off-by: Max Filippov --- arch/xtensa/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 20a0756f27ef..48906ac5fd25 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -164,7 +164,7 @@ config XTENSA_FAKE_NMI If unsure, say N. config XTENSA_UNALIGNED_USER - bool "Unaligned memory access in use space" + bool "Unaligned memory access in user space" help The Xtensa architecture currently does not handle unaligned memory accesses in hardware but through an exception handler. From 687cffd3450911b1b7449fd6c30f598b35666b41 Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Wed, 23 Jan 2019 09:49:18 +0000 Subject: [PATCH 142/525] xtensa: rename BUILTIN_DTB to BUILTIN_DTB_SOURCE When building some xtensa config, I hit the following warning: drivers/staging/mt7621-dts/Kconfig:4:warning: 'BUILTIN_DTB' has wrong type. 'select' only accept arguments of bool and tristate type It is due to some arch use BUILTIN_DTB as a flag for the need to builtin dtb but xtensa use it as a string for which dtb to bulltin. But for this (which dtb to build), it is better to use BUILTIN_DTB_SOURCE like other arch do. Signed-off-by: Corentin Labbe Signed-off-by: Max Filippov --- arch/xtensa/Kconfig | 2 +- arch/xtensa/boot/dts/Makefile | 6 +++--- arch/xtensa/configs/audio_kc705_defconfig | 2 +- arch/xtensa/configs/cadence_csp_defconfig | 2 +- arch/xtensa/configs/generic_kc705_defconfig | 2 +- arch/xtensa/configs/nommu_kc705_defconfig | 2 +- arch/xtensa/configs/smp_lx200_defconfig | 2 +- 7 files changed, 9 insertions(+), 9 deletions(-) diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 48906ac5fd25..ce91682770cb 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -451,7 +451,7 @@ config USE_OF help Include support for flattened device tree machine descriptions. -config BUILTIN_DTB +config BUILTIN_DTB_SOURCE string "DTB to build into the kernel image" depends on OF diff --git a/arch/xtensa/boot/dts/Makefile b/arch/xtensa/boot/dts/Makefile index f8052ba5aea8..0b8d00cdae7c 100644 --- a/arch/xtensa/boot/dts/Makefile +++ b/arch/xtensa/boot/dts/Makefile @@ -7,9 +7,9 @@ # # -BUILTIN_DTB := $(patsubst "%",%,$(CONFIG_BUILTIN_DTB)).dtb.o -ifneq ($(CONFIG_BUILTIN_DTB),"") -obj-$(CONFIG_OF) += $(BUILTIN_DTB) +BUILTIN_DTB_SOURCE := $(patsubst "%",%,$(CONFIG_BUILTIN_DTB_SOURCE)).dtb.o +ifneq ($(CONFIG_BUILTIN_DTB_SOURCE),"") +obj-$(CONFIG_OF) += $(BUILTIN_DTB_SOURCE) endif # for CONFIG_OF_ALL_DTBS test diff --git a/arch/xtensa/configs/audio_kc705_defconfig b/arch/xtensa/configs/audio_kc705_defconfig index 2bf964df37ba..f378e56f9ce6 100644 --- a/arch/xtensa/configs/audio_kc705_defconfig +++ b/arch/xtensa/configs/audio_kc705_defconfig @@ -34,7 +34,7 @@ CONFIG_XTENSA_PLATFORM_XTFPGA=y CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=0x38000000@0" CONFIG_USE_OF=y -CONFIG_BUILTIN_DTB="kc705" +CONFIG_BUILTIN_DTB_SOURCE="kc705" # CONFIG_COMPACTION is not set # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_PM=y diff --git a/arch/xtensa/configs/cadence_csp_defconfig b/arch/xtensa/configs/cadence_csp_defconfig index 3221b7053fa3..62f32a902568 100644 --- a/arch/xtensa/configs/cadence_csp_defconfig +++ b/arch/xtensa/configs/cadence_csp_defconfig @@ -38,7 +38,7 @@ CONFIG_HIGHMEM=y # CONFIG_PCI is not set CONFIG_XTENSA_PLATFORM_XTFPGA=y CONFIG_USE_OF=y -CONFIG_BUILTIN_DTB="csp" +CONFIG_BUILTIN_DTB_SOURCE="csp" # CONFIG_COMPACTION is not set CONFIG_XTFPGA_LCD=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set diff --git a/arch/xtensa/configs/generic_kc705_defconfig b/arch/xtensa/configs/generic_kc705_defconfig index 985fa8546e4e..8bebe07f1060 100644 --- a/arch/xtensa/configs/generic_kc705_defconfig +++ b/arch/xtensa/configs/generic_kc705_defconfig @@ -33,7 +33,7 @@ CONFIG_XTENSA_PLATFORM_XTFPGA=y CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=0x38000000@0" CONFIG_USE_OF=y -CONFIG_BUILTIN_DTB="kc705" +CONFIG_BUILTIN_DTB_SOURCE="kc705" # CONFIG_COMPACTION is not set # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_NET=y diff --git a/arch/xtensa/configs/nommu_kc705_defconfig b/arch/xtensa/configs/nommu_kc705_defconfig index f3fc4f970ca8..933ab2adf434 100644 --- a/arch/xtensa/configs/nommu_kc705_defconfig +++ b/arch/xtensa/configs/nommu_kc705_defconfig @@ -39,7 +39,7 @@ CONFIG_XTENSA_PLATFORM_XTFPGA=y CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0x9d050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=256M@0x60000000" CONFIG_USE_OF=y -CONFIG_BUILTIN_DTB="kc705_nommu" +CONFIG_BUILTIN_DTB_SOURCE="kc705_nommu" CONFIG_BINFMT_FLAT=y CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/xtensa/configs/smp_lx200_defconfig b/arch/xtensa/configs/smp_lx200_defconfig index b5938160fb3d..e29c5b179a5b 100644 --- a/arch/xtensa/configs/smp_lx200_defconfig +++ b/arch/xtensa/configs/smp_lx200_defconfig @@ -38,7 +38,7 @@ CONFIG_XTENSA_PLATFORM_XTFPGA=y CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=96M@0" CONFIG_USE_OF=y -CONFIG_BUILTIN_DTB="lx200mx" +CONFIG_BUILTIN_DTB_SOURCE="lx200mx" # CONFIG_COMPACTION is not set # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_NET=y From f36c1f9a8dfd6a78e6c3fe7aff5e722b84307597 Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Fri, 25 Jan 2019 07:29:20 +0000 Subject: [PATCH 143/525] i3c: master: dw: fix deadlock MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In dw_i3c_master_irq_handler(), we already have gotten &master->xferqueue.lock, if we try to get the same lock again in dw_i3c_master_dequeue_xfer(), deadlock happens. We fix this issue by introduing dw_i3c_master_dequeue_xfer_locked() which does all what dw_i3c_master_dequeue_xfer() does without trying to lock &master->xferqueue.lock. Signed-off-by: Jisheng Zhang Acked-by: Vitor Soares  Signed-off-by: Boris Brezillon --- drivers/i3c/master/dw-i3c-master.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c index f8c00b94817f..bb03079fbade 100644 --- a/drivers/i3c/master/dw-i3c-master.c +++ b/drivers/i3c/master/dw-i3c-master.c @@ -419,12 +419,9 @@ static void dw_i3c_master_enqueue_xfer(struct dw_i3c_master *master, spin_unlock_irqrestore(&master->xferqueue.lock, flags); } -static void dw_i3c_master_dequeue_xfer(struct dw_i3c_master *master, - struct dw_i3c_xfer *xfer) +static void dw_i3c_master_dequeue_xfer_locked(struct dw_i3c_master *master, + struct dw_i3c_xfer *xfer) { - unsigned long flags; - - spin_lock_irqsave(&master->xferqueue.lock, flags); if (master->xferqueue.cur == xfer) { u32 status; @@ -439,6 +436,15 @@ static void dw_i3c_master_dequeue_xfer(struct dw_i3c_master *master, } else { list_del_init(&xfer->node); } +} + +static void dw_i3c_master_dequeue_xfer(struct dw_i3c_master *master, + struct dw_i3c_xfer *xfer) +{ + unsigned long flags; + + spin_lock_irqsave(&master->xferqueue.lock, flags); + dw_i3c_master_dequeue_xfer_locked(master, xfer); spin_unlock_irqrestore(&master->xferqueue.lock, flags); } @@ -494,7 +500,7 @@ static void dw_i3c_master_end_xfer_locked(struct dw_i3c_master *master, u32 isr) complete(&xfer->comp); if (ret < 0) { - dw_i3c_master_dequeue_xfer(master, xfer); + dw_i3c_master_dequeue_xfer_locked(master, xfer); writel(readl(master->regs + DEVICE_CTRL) | DEV_CTRL_RESUME, master->regs + DEVICE_CTRL); } From 6a730fcb9cb472ba2d42b26a50ac65dacdd68882 Mon Sep 17 00:00:00 2001 From: "Darren Hart (VMware)" Date: Sat, 12 Jan 2019 20:27:35 -0800 Subject: [PATCH 144/525] Documentation/ABI: Correct mlxreg-io KernelVersion for 5.0 The mlxreg-io for the merge window assumed 4.21 as the next kernel version. Replace 4.21 with 5.0. Signed-off-by: Darren Hart (VMware) Reviewed-by: Andy Shevchenko --- Documentation/ABI/stable/sysfs-driver-mlxreg-io | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/Documentation/ABI/stable/sysfs-driver-mlxreg-io b/Documentation/ABI/stable/sysfs-driver-mlxreg-io index 9b642669cb16..169fe08a649b 100644 --- a/Documentation/ABI/stable/sysfs-driver-mlxreg-io +++ b/Documentation/ABI/stable/sysfs-driver-mlxreg-io @@ -24,7 +24,7 @@ What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/ cpld3_version Date: November 2018 -KernelVersion: 4.21 +KernelVersion: 5.0 Contact: Vadim Pasternak Description: These files show with which CPLD versions have been burned on LED board. @@ -35,7 +35,7 @@ What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/ jtag_enable Date: November 2018 -KernelVersion: 4.21 +KernelVersion: 5.0 Contact: Vadim Pasternak Description: These files enable and disable the access to the JTAG domain. By default access to the JTAG domain is disabled. @@ -105,7 +105,7 @@ What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/ reset_voltmon_upgrade_fail Date: November 2018 -KernelVersion: 4.21 +KernelVersion: 5.0 Contact: Vadim Pasternak Description: These files show the system reset cause, as following: ComEx power fail, reset from ComEx, system platform reset, reset From 8e47a457321ca1a74ad194ab5dcbca764bc70731 Mon Sep 17 00:00:00 2001 From: Piotr Jaroszynski Date: Sun, 27 Jan 2019 08:46:45 -0800 Subject: [PATCH 145/525] iomap: get/put the page in iomap_page_create/release() migrate_page_move_mapping() expects pages with private data set to have a page_count elevated by 1. This is what used to happen for xfs through the buffer_heads code before the switch to iomap in commit 82cb14175e7d ("xfs: add support for sub-pagesize writeback without buffer_heads"). Not having the count elevated causes move_pages() to fail on memory mapped files coming from xfs. Make iomap compatible with the migrate_page_move_mapping() assumption by elevating the page count as part of iomap_page_create() and lowering it in iomap_page_release(). It causes the move_pages() syscall to misbehave on memory mapped files from xfs. It does not not move any pages, which I suppose is "just" a perf issue, but it also ends up returning a positive number which is out of spec for the syscall. Talking to Michal Hocko, it sounds like returning positive numbers might be a necessary update to move_pages() anyway though. Fixes: 82cb14175e7d ("xfs: add support for sub-pagesize writeback without buffer_heads") Signed-off-by: Piotr Jaroszynski [hch: actually get/put the page iomap_migrate_page() to make it work properly] Signed-off-by: Christoph Hellwig Reviewed-by: Dave Chinner Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/iomap.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/fs/iomap.c b/fs/iomap.c index a3088fae567b..cb184ff68680 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -116,6 +116,12 @@ iomap_page_create(struct inode *inode, struct page *page) atomic_set(&iop->read_count, 0); atomic_set(&iop->write_count, 0); bitmap_zero(iop->uptodate, PAGE_SIZE / SECTOR_SIZE); + + /* + * migrate_page_move_mapping() assumes that pages with private data have + * their count elevated by 1. + */ + get_page(page); set_page_private(page, (unsigned long)iop); SetPagePrivate(page); return iop; @@ -132,6 +138,7 @@ iomap_page_release(struct page *page) WARN_ON_ONCE(atomic_read(&iop->write_count)); ClearPagePrivate(page); set_page_private(page, 0); + put_page(page); kfree(iop); } @@ -569,8 +576,10 @@ iomap_migrate_page(struct address_space *mapping, struct page *newpage, if (page_has_private(page)) { ClearPagePrivate(page); + get_page(newpage); set_page_private(newpage, page_private(page)); set_page_private(page, 0); + put_page(page); SetPagePrivate(newpage); } From 4ea899ead2786a30aaa8181fefa81a3df4ad28f6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 17 Jan 2019 08:58:58 -0800 Subject: [PATCH 146/525] iomap: fix a use after free in iomap_dio_rw Introduce a local wait_for_completion variable to avoid an access to the potentially freed dio struture after dropping the last reference count. Also use the chance to document the completion behavior to make the refcounting clear to the reader of the code. Fixes: ff6a9292e6 ("iomap: implement direct I/O") Reported-by: Chandan Rajendra Reported-by: Darrick J. Wong Signed-off-by: Christoph Hellwig Tested-by: Chandan Rajendra Tested-by: Darrick J. Wong Reviewed-by: Dave Chinner Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/iomap.c | 28 +++++++++++++++++++++------- 1 file changed, 21 insertions(+), 7 deletions(-) diff --git a/fs/iomap.c b/fs/iomap.c index cb184ff68680..897c60215dd1 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -1813,6 +1813,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, loff_t pos = iocb->ki_pos, start = pos; loff_t end = iocb->ki_pos + count - 1, ret = 0; unsigned int flags = IOMAP_DIRECT; + bool wait_for_completion = is_sync_kiocb(iocb); struct blk_plug plug; struct iomap_dio *dio; @@ -1832,7 +1833,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, dio->end_io = end_io; dio->error = 0; dio->flags = 0; - dio->wait_for_completion = is_sync_kiocb(iocb); dio->submit.iter = iter; dio->submit.waiter = current; @@ -1887,7 +1887,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, dio_warn_stale_pagecache(iocb->ki_filp); ret = 0; - if (iov_iter_rw(iter) == WRITE && !dio->wait_for_completion && + if (iov_iter_rw(iter) == WRITE && !wait_for_completion && !inode->i_sb->s_dio_done_wq) { ret = sb_init_dio_done_wq(inode->i_sb); if (ret < 0) @@ -1903,7 +1903,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (ret <= 0) { /* magic error code to fall back to buffered I/O */ if (ret == -ENOTBLK) { - dio->wait_for_completion = true; + wait_for_completion = true; ret = 0; } break; @@ -1925,8 +1925,24 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (dio->flags & IOMAP_DIO_WRITE_FUA) dio->flags &= ~IOMAP_DIO_NEED_SYNC; + /* + * We are about to drop our additional submission reference, which + * might be the last reference to the dio. There are three three + * different ways we can progress here: + * + * (a) If this is the last reference we will always complete and free + * the dio ourselves. + * (b) If this is not the last reference, and we serve an asynchronous + * iocb, we must never touch the dio after the decrement, the + * I/O completion handler will complete and free it. + * (c) If this is not the last reference, but we serve a synchronous + * iocb, the I/O completion handler will wake us up on the drop + * of the final reference, and we will complete and free it here + * after we got woken by the I/O completion handler. + */ + dio->wait_for_completion = wait_for_completion; if (!atomic_dec_and_test(&dio->ref)) { - if (!dio->wait_for_completion) + if (!wait_for_completion) return -EIOCBQUEUED; for (;;) { @@ -1943,9 +1959,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, __set_current_state(TASK_RUNNING); } - ret = iomap_dio_complete(dio); - - return ret; + return iomap_dio_complete(dio); out_free_dio: kfree(dio); From 25384ce5f9530def39421597b1457d9462df6455 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Sat, 26 Jan 2019 20:35:18 -0800 Subject: [PATCH 147/525] xtensa: SMP: limit number of possible CPUs by NR_CPUS This fixes the following warning at boot when the kernel is booted on a board with more CPU cores than was configured in NR_CPUS: smp_init_cpus: Core Count = 8 smp_init_cpus: Core Id = 0 ------------[ cut here ]------------ WARNING: CPU: 0 PID: 0 at include/linux/cpumask.h:121 smp_init_cpus+0x54/0x74 Modules linked in: CPU: 0 PID: 0 Comm: swapper Not tainted 5.0.0-rc3-00015-g1459333f88a0 #124 Call Trace: __warn$part$3+0x6a/0x7c warn_slowpath_null+0x35/0x3c smp_init_cpus+0x54/0x74 setup_arch+0x1c0/0x1d0 start_kernel+0x44/0x310 _startup+0x107/0x107 Signed-off-by: Max Filippov --- arch/xtensa/kernel/smp.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c index 80be6449c497..be1f280c322c 100644 --- a/arch/xtensa/kernel/smp.c +++ b/arch/xtensa/kernel/smp.c @@ -96,6 +96,11 @@ void __init smp_init_cpus(void) pr_info("%s: Core Count = %d\n", __func__, ncpus); pr_info("%s: Core Id = %d\n", __func__, core_id); + if (ncpus > NR_CPUS) { + ncpus = NR_CPUS; + pr_info("%s: limiting core count by %d\n", __func__, ncpus); + } + for (i = 0; i < ncpus; ++i) set_cpu_possible(i, true); } From 63346650c1a94a92be61a57416ac88c0a47c4327 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 24 Jan 2019 14:18:18 -0800 Subject: [PATCH 148/525] netrom: switch to sock timer API sk_reset_timer() and sk_stop_timer() properly handle sock refcnt for timer function. Switching to them could fix a refcounting bug reported by syzbot. Reported-and-tested-by: syzbot+defa700d16f1bd1b9a05@syzkaller.appspotmail.com Cc: Ralf Baechle Cc: linux-hams@vger.kernel.org Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/netrom/nr_timer.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c index cbd51ed5a2d7..908e53ab47a4 100644 --- a/net/netrom/nr_timer.c +++ b/net/netrom/nr_timer.c @@ -52,21 +52,21 @@ void nr_start_t1timer(struct sock *sk) { struct nr_sock *nr = nr_sk(sk); - mod_timer(&nr->t1timer, jiffies + nr->t1); + sk_reset_timer(sk, &nr->t1timer, jiffies + nr->t1); } void nr_start_t2timer(struct sock *sk) { struct nr_sock *nr = nr_sk(sk); - mod_timer(&nr->t2timer, jiffies + nr->t2); + sk_reset_timer(sk, &nr->t2timer, jiffies + nr->t2); } void nr_start_t4timer(struct sock *sk) { struct nr_sock *nr = nr_sk(sk); - mod_timer(&nr->t4timer, jiffies + nr->t4); + sk_reset_timer(sk, &nr->t4timer, jiffies + nr->t4); } void nr_start_idletimer(struct sock *sk) @@ -74,37 +74,37 @@ void nr_start_idletimer(struct sock *sk) struct nr_sock *nr = nr_sk(sk); if (nr->idle > 0) - mod_timer(&nr->idletimer, jiffies + nr->idle); + sk_reset_timer(sk, &nr->idletimer, jiffies + nr->idle); } void nr_start_heartbeat(struct sock *sk) { - mod_timer(&sk->sk_timer, jiffies + 5 * HZ); + sk_reset_timer(sk, &sk->sk_timer, jiffies + 5 * HZ); } void nr_stop_t1timer(struct sock *sk) { - del_timer(&nr_sk(sk)->t1timer); + sk_stop_timer(sk, &nr_sk(sk)->t1timer); } void nr_stop_t2timer(struct sock *sk) { - del_timer(&nr_sk(sk)->t2timer); + sk_stop_timer(sk, &nr_sk(sk)->t2timer); } void nr_stop_t4timer(struct sock *sk) { - del_timer(&nr_sk(sk)->t4timer); + sk_stop_timer(sk, &nr_sk(sk)->t4timer); } void nr_stop_idletimer(struct sock *sk) { - del_timer(&nr_sk(sk)->idletimer); + sk_stop_timer(sk, &nr_sk(sk)->idletimer); } void nr_stop_heartbeat(struct sock *sk) { - del_timer(&sk->sk_timer); + sk_stop_timer(sk, &sk->sk_timer); } int nr_t1timer_running(struct sock *sk) From 6571ebce112a21ec9be68ef2f53b96fcd41fd81b Mon Sep 17 00:00:00 2001 From: Tomonori Sakita Date: Fri, 25 Jan 2019 11:02:22 +0900 Subject: [PATCH 149/525] net: altera_tse: fix msgdma_tx_completion on non-zero fill_level case If fill_level was not zero and status was not BUSY, result of "tx_prod - tx_cons - inuse" might be zero. Subtracting 1 unconditionally results invalid negative return value on this case. Make sure not to return an negative value. Signed-off-by: Tomonori Sakita Signed-off-by: Atsushi Nemoto Reviewed-by: Dalon L Westergreen Acked-by: Thor Thayer Signed-off-by: David S. Miller --- drivers/net/ethernet/altera/altera_msgdma.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/altera/altera_msgdma.c b/drivers/net/ethernet/altera/altera_msgdma.c index 0fb986ba3290..0ae723f75341 100644 --- a/drivers/net/ethernet/altera/altera_msgdma.c +++ b/drivers/net/ethernet/altera/altera_msgdma.c @@ -145,7 +145,8 @@ u32 msgdma_tx_completions(struct altera_tse_private *priv) & 0xffff; if (inuse) { /* Tx FIFO is not empty */ - ready = priv->tx_prod - priv->tx_cons - inuse - 1; + ready = max_t(int, + priv->tx_prod - priv->tx_cons - inuse - 1, 0); } else { /* Check for buffered last packet */ status = csrrd32(priv->tx_dma_csr, msgdma_csroffs(status)); From b0cf029234f9b18e10703ba5147f0389c382bccc Mon Sep 17 00:00:00 2001 From: Bernard Pidoux Date: Fri, 25 Jan 2019 11:46:40 +0100 Subject: [PATCH 150/525] net/rose: fix NULL ax25_cb kernel panic When an internally generated frame is handled by rose_xmit(), rose_route_frame() is called: if (!rose_route_frame(skb, NULL)) { dev_kfree_skb(skb); stats->tx_errors++; return NETDEV_TX_OK; } We have the same code sequence in Net/Rom where an internally generated frame is handled by nr_xmit() calling nr_route_frame(skb, NULL). However, in this function NULL argument is tested while it is not in rose_route_frame(). Then kernel panic occurs later on when calling ax25cmp() with a NULL ax25_cb argument as reported many times and recently with syzbot. We need to test if ax25 is NULL before using it. Testing: Built kernel with CONFIG_ROSE=y. Signed-off-by: Bernard Pidoux Acked-by: Dmitry Vyukov Reported-by: syzbot+1a2c456a1ea08fa5b5f7@syzkaller.appspotmail.com Cc: "David S. Miller" Cc: Ralf Baechle Cc: Bernard Pidoux Cc: linux-hams@vger.kernel.org Cc: netdev@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller --- net/rose/rose_route.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index 77e9f85a2c92..f2ff21d7df08 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -850,6 +850,7 @@ void rose_link_device_down(struct net_device *dev) /* * Route a frame to an appropriate AX.25 connection. + * A NULL ax25_cb indicates an internally generated frame. */ int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25) { @@ -867,6 +868,10 @@ int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25) if (skb->len < ROSE_MIN_LEN) return res; + + if (!ax25) + return rose_loopback_queue(skb, NULL); + frametype = skb->data[2]; lci = ((skb->data[0] << 8) & 0xF00) + ((skb->data[1] << 0) & 0x0FF); if (frametype == ROSE_CALL_REQUEST && From 263c6d75f9a544a3c2f8f6a26de4f4808d8f59cf Mon Sep 17 00:00:00 2001 From: Yonglong Liu Date: Sat, 26 Jan 2019 17:18:25 +0800 Subject: [PATCH 151/525] net: hns: Fix for missing of_node_put() after of_parse_phandle() In hns enet driver, we use of_parse_handle() to get hold of the device node related to "ae-handle" but we have missed to put the node reference using of_node_put() after we are done using the node. This patch fixes it. Note: This problem is stated in Link: https://lkml.org/lkml/2018/12/22/217 Fixes: 48189d6aaf1e ("net: hns: enet specifies a reference to dsaf") Reported-by: Alexey Khoroshilov Signed-off-by: Yonglong Liu Signed-off-by: Peng Li Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hns_enet.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 5b33238c6680..60e7d7ae3787 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -2418,6 +2418,8 @@ static int hns_nic_dev_probe(struct platform_device *pdev) out_notify_fail: (void)cancel_work_sync(&priv->service_task); out_read_prop_fail: + /* safe for ACPI FW */ + of_node_put(to_of_node(priv->fwnode)); free_netdev(ndev); return ret; } @@ -2447,6 +2449,9 @@ static int hns_nic_dev_remove(struct platform_device *pdev) set_bit(NIC_STATE_REMOVING, &priv->state); (void)cancel_work_sync(&priv->service_task); + /* safe for ACPI FW */ + of_node_put(to_of_node(priv->fwnode)); + free_netdev(ndev); return 0; } From ed29ca8b9592562559c64d027fb5eb126e463e2c Mon Sep 17 00:00:00 2001 From: Yonglong Liu Date: Sat, 26 Jan 2019 17:18:26 +0800 Subject: [PATCH 152/525] net: hns: Restart autoneg need return failed when autoneg off The hns driver of earlier devices, when autoneg off, restart autoneg will return -EINVAL, so make the hns driver for the latest devices do the same. Signed-off-by: Yonglong Liu Signed-off-by: Peng Li Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hns_ethtool.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index 8e9b95871d30..ce15d2350db9 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -1157,16 +1157,18 @@ static int hns_get_regs_len(struct net_device *net_dev) */ static int hns_nic_nway_reset(struct net_device *netdev) { - int ret = 0; struct phy_device *phy = netdev->phydev; - if (netif_running(netdev)) { - /* if autoneg is disabled, don't restart auto-negotiation */ - if (phy && phy->autoneg == AUTONEG_ENABLE) - ret = genphy_restart_aneg(phy); - } + if (!netif_running(netdev)) + return 0; - return ret; + if (!phy) + return -EOPNOTSUPP; + + if (phy->autoneg != AUTONEG_ENABLE) + return -EINVAL; + + return genphy_restart_aneg(phy); } static u32 From cec8abba13e6a26729dfed41019720068eeeff2b Mon Sep 17 00:00:00 2001 From: Yonglong Liu Date: Sat, 26 Jan 2019 17:18:27 +0800 Subject: [PATCH 153/525] net: hns: Fix wrong read accesses via Clause 45 MDIO protocol When reading phy registers via Clause 45 MDIO protocol, after write address operation, the driver use another write address operation, so can not read the right value of any phy registers. This patch fixes it. Signed-off-by: Yonglong Liu Signed-off-by: Peng Li Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns_mdio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c index 017e08452d8c..baf5cc251f32 100644 --- a/drivers/net/ethernet/hisilicon/hns_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns_mdio.c @@ -321,7 +321,7 @@ static int hns_mdio_read(struct mii_bus *bus, int phy_id, int regnum) } hns_mdio_cmd_write(mdio_dev, is_c45, - MDIO_C45_WRITE_ADDR, phy_id, devad); + MDIO_C45_READ, phy_id, devad); } /* Step 5: waitting for MDIO_COMMAND_REG 's mdio_start==0,*/ From c69c29a1a0a8f68cd87e98ba4a5a79fb8ef2a58c Mon Sep 17 00:00:00 2001 From: Alexey Khoroshilov Date: Sat, 26 Jan 2019 22:48:57 +0300 Subject: [PATCH 154/525] net: stmmac: dwmac-rk: fix error handling in rk_gmac_powerup() If phy_power_on() fails in rk_gmac_powerup(), clocks are left enabled. Found by Linux Driver Verification project (linuxtesting.org). Signed-off-by: Alexey Khoroshilov Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index 7b923362ee55..3b174eae77c1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -1342,8 +1342,10 @@ static int rk_gmac_powerup(struct rk_priv_data *bsp_priv) } ret = phy_power_on(bsp_priv, true); - if (ret) + if (ret) { + gmac_clk_enable(bsp_priv, false); return ret; + } pm_runtime_enable(dev); pm_runtime_get_sync(dev); From 50c2936634bcb1db78a8ca63249236810c11a80f Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sat, 26 Jan 2019 21:12:19 +0100 Subject: [PATCH 155/525] decnet: fix DN_IFREQ_SIZE Digging through the ioctls with Al because of the previous patches, we found that on 64-bit decnet's dn_dev_ioctl() is wrong, because struct ifreq::ifr_ifru is actually 24 bytes (not 16 as expected from struct sockaddr) due to the ifru_map and ifru_settings members. Clearly, decnet expects the ioctl to be called with a struct like struct ifreq_dn { char ifr_name[IFNAMSIZ]; struct sockaddr_dn ifr_addr; }; since it does struct ifreq *ifr = ...; struct sockaddr_dn *sdn = (struct sockaddr_dn *)&ifr->ifr_addr; This means that DN_IFREQ_SIZE is too big for what it wants on 64-bit, as it is sizeof(struct ifreq) - sizeof(struct sockaddr) + sizeof(struct sockaddr_dn) This assumes that sizeof(struct sockaddr) is the size of ifr_ifru but that isn't true. Fix this to use offsetof(struct ifreq, ifr_ifru). This indeed doesn't really matter much - the result is that we copy in/out 8 bytes more than we should on 64-bit platforms. In case the "struct ifreq_dn" lands just on the end of a page though it might lead to faults. As far as I can tell, it has been like this forever, so it seems very likely that nobody cares. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- net/decnet/dn_dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index d0b3e69c6b39..0962f9201baa 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -56,7 +56,7 @@ #include #include -#define DN_IFREQ_SIZE (sizeof(struct ifreq) - sizeof(struct sockaddr) + sizeof(struct sockaddr_dn)) +#define DN_IFREQ_SIZE (offsetof(struct ifreq, ifr_ifru) + sizeof(struct sockaddr_dn)) static char dn_rt_all_end_mcast[ETH_ALEN] = {0xAB,0x00,0x00,0x04,0x00,0x00}; static char dn_rt_all_rt_mcast[ETH_ALEN] = {0xAB,0x00,0x00,0x03,0x00,0x00}; From 146820cc240f4389cf33481c058d9493aef95e25 Mon Sep 17 00:00:00 2001 From: Nir Dotan Date: Sun, 27 Jan 2019 09:26:22 +0200 Subject: [PATCH 156/525] ip6mr: Fix notifiers call on mroute_clean_tables() When the MC route socket is closed, mroute_clean_tables() is called to cleanup existing routes. Mistakenly notifiers call was put on the cleanup of the unresolved MC route entries cache. In a case where the MC socket closes before an unresolved route expires, the notifier call leads to a crash, caused by the driver trying to increment a non initialized refcount_t object [1] and then when handling is done, to decrement it [2]. This was detected by a test recently added in commit 6d4efada3b82 ("selftests: forwarding: Add multicast routing test"). Fix that by putting notifiers call on the resolved entries traversal, instead of on the unresolved entries traversal. [1] [ 245.748967] refcount_t: increment on 0; use-after-free. [ 245.754829] WARNING: CPU: 3 PID: 3223 at lib/refcount.c:153 refcount_inc_checked+0x2b/0x30 ... [ 245.802357] Hardware name: Mellanox Technologies Ltd. MSN2740/SA001237, BIOS 5.6.5 06/07/2016 [ 245.811873] RIP: 0010:refcount_inc_checked+0x2b/0x30 ... [ 245.907487] Call Trace: [ 245.910231] mlxsw_sp_router_fib_event.cold.181+0x42/0x47 [mlxsw_spectrum] [ 245.917913] notifier_call_chain+0x45/0x7 [ 245.922484] atomic_notifier_call_chain+0x15/0x20 [ 245.927729] call_fib_notifiers+0x15/0x30 [ 245.932205] mroute_clean_tables+0x372/0x3f [ 245.936971] ip6mr_sk_done+0xb1/0xc0 [ 245.940960] ip6_mroute_setsockopt+0x1da/0x5f0 ... [2] [ 246.128487] refcount_t: underflow; use-after-free. [ 246.133859] WARNING: CPU: 0 PID: 7 at lib/refcount.c:187 refcount_sub_and_test_checked+0x4c/0x60 [ 246.183521] Hardware name: Mellanox Technologies Ltd. MSN2740/SA001237, BIOS 5.6.5 06/07/2016 ... [ 246.193062] Workqueue: mlxsw_core_ordered mlxsw_sp_router_fibmr_event_work [mlxsw_spectrum] [ 246.202394] RIP: 0010:refcount_sub_and_test_checked+0x4c/0x60 ... [ 246.298889] Call Trace: [ 246.301617] refcount_dec_and_test_checked+0x11/0x20 [ 246.307170] mlxsw_sp_router_fibmr_event_work.cold.196+0x47/0x78 [mlxsw_spectrum] [ 246.315531] process_one_work+0x1fa/0x3f0 [ 246.320005] worker_thread+0x2f/0x3e0 [ 246.324083] kthread+0x118/0x130 [ 246.327683] ? wq_update_unbound_numa+0x1b0/0x1b0 [ 246.332926] ? kthread_park+0x80/0x80 [ 246.337013] ret_from_fork+0x1f/0x30 Fixes: 088aa3eec2ce ("ip6mr: Support fib notifications") Signed-off-by: Nir Dotan Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- net/ipv6/ip6mr.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 30337b38274b..cc01aa3f2b5e 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1516,6 +1516,9 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all) continue; rhltable_remove(&mrt->mfc_hash, &c->mnode, ip6mr_rht_params); list_del_rcu(&c->list); + call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net), + FIB_EVENT_ENTRY_DEL, + (struct mfc6_cache *)c, mrt->id); mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE); mr_cache_put(c); } @@ -1524,10 +1527,6 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all) spin_lock_bh(&mfc_unres_lock); list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) { list_del(&c->list); - call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net), - FIB_EVENT_ENTRY_DEL, - (struct mfc6_cache *)c, - mrt->id); mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE); ip6mr_destroy_unres(mrt, (struct mfc6_cache *)c); From 6fb6e6371f8c463020a41cc0ed1915e140219c3d Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 27 Jan 2019 22:48:00 +0100 Subject: [PATCH 157/525] net: dsa: mv88e6xxx: Fix serdes irq setup going recursive Duec to a typo, mv88e6390_serdes_irq_setup() calls itself, rather than mv88e6390x_serdes_irq_setup(). It then blows the stack, and shortly after the machine blows up. Fixes: 2defda1f4b91 ("net: dsa: mv88e6xxx: Add support for SERDES on ports 2-8 for 6390X") Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/serdes.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c index 2caa8c8b4b55..1bfc5ff8d81d 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.c +++ b/drivers/net/dsa/mv88e6xxx/serdes.c @@ -664,7 +664,7 @@ int mv88e6390_serdes_irq_setup(struct mv88e6xxx_chip *chip, int port) if (port < 9) return 0; - return mv88e6390_serdes_irq_setup(chip, port); + return mv88e6390x_serdes_irq_setup(chip, port); } void mv88e6390x_serdes_irq_free(struct mv88e6xxx_chip *chip, int port) From 2035f3ff8eaa29cfb5c8e2160b0f6e85eeb21a95 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 21 Jan 2019 21:54:36 +0100 Subject: [PATCH 158/525] netfilter: ebtables: compat: un-break 32bit setsockopt when no rules are present Unlike ip(6)tables ebtables only counts user-defined chains. The effect is that a 32bit ebtables binary on a 64bit kernel can do 'ebtables -N FOO' only after adding at least one rule, else the request fails with -EINVAL. This is a similar fix as done in 3f1e53abff84 ("netfilter: ebtables: don't attempt to allocate 0-sized compat array"). Fixes: 7d7d7e02111e9 ("netfilter: compat: reject huge allocation requests") Reported-by: Francesco Ruggeri Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/bridge/netfilter/ebtables.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 5e55cef0cec3..6693e209efe8 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -2293,9 +2293,12 @@ static int compat_do_replace(struct net *net, void __user *user, xt_compat_lock(NFPROTO_BRIDGE); - ret = xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries); - if (ret < 0) - goto out_unlock; + if (tmp.nentries) { + ret = xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries); + if (ret < 0) + goto out_unlock; + } + ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state); if (ret < 0) goto out_unlock; From 1a6a0951fc009f6d9fe8ebea2d2417d80d54097b Mon Sep 17 00:00:00 2001 From: Fernando Fernandez Mancera Date: Mon, 21 Jan 2019 12:53:21 +0100 Subject: [PATCH 159/525] netfilter: nfnetlink_osf: add missing fmatch check When we check the tcp options of a packet and it doesn't match the current fingerprint, the tcp packet option pointer must be restored to its initial value in order to do the proper tcp options check for the next fingerprint. Here we can see an example. Assumming the following fingerprint base with two lines: S10:64:1:60:M*,S,T,N,W6: Linux:3.0::Linux 3.0 S20:64:1:60:M*,S,T,N,W7: Linux:4.19:arch:Linux 4.1 Where TCP options are the last field in the OS signature, all of them overlap except by the last one, ie. 'W6' versus 'W7'. In case a packet for Linux 4.19 kicks in, the osf finds no matching because the TCP options pointer is updated after checking for the TCP options in the first line. Therefore, reset pointer back to where it should be. Fixes: 11eeef41d5f6 ("netfilter: passive OS fingerprint xtables match") Signed-off-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_osf.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c index 6f41dd74729d..1f1d90c1716b 100644 --- a/net/netfilter/nfnetlink_osf.c +++ b/net/netfilter/nfnetlink_osf.c @@ -66,6 +66,7 @@ static bool nf_osf_match_one(const struct sk_buff *skb, int ttl_check, struct nf_osf_hdr_ctx *ctx) { + const __u8 *optpinit = ctx->optp; unsigned int check_WSS = 0; int fmatch = FMATCH_WRONG; int foptsize, optnum; @@ -155,6 +156,9 @@ static bool nf_osf_match_one(const struct sk_buff *skb, } } + if (fmatch != FMATCH_OK) + ctx->optp = optpinit; + return fmatch == FMATCH_OK; } From 206b8cc514d7ff2b79dd2d5ad939adc7c493f07a Mon Sep 17 00:00:00 2001 From: Anders Roxell Date: Wed, 23 Jan 2019 12:48:11 +0100 Subject: [PATCH 160/525] netfilter: ipt_CLUSTERIP: fix warning unused variable cn MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When CONFIG_PROC_FS isn't set the variable cn isn't used. net/ipv4/netfilter/ipt_CLUSTERIP.c: In function ‘clusterip_net_exit’: net/ipv4/netfilter/ipt_CLUSTERIP.c:849:24: warning: unused variable ‘cn’ [-Wunused-variable] struct clusterip_net *cn = clusterip_pernet(net); ^~ Rework so the variable 'cn' is declared inside "#ifdef CONFIG_PROC_FS". Fixes: b12f7bad5ad3 ("netfilter: ipt_CLUSTERIP: remove wrong WARN_ON_ONCE in netns exit routine") Signed-off-by: Anders Roxell Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/ipt_CLUSTERIP.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index b61977db9b7f..2a909e5f9ba0 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -846,9 +846,9 @@ static int clusterip_net_init(struct net *net) static void clusterip_net_exit(struct net *net) { +#ifdef CONFIG_PROC_FS struct clusterip_net *cn = clusterip_pernet(net); -#ifdef CONFIG_PROC_FS mutex_lock(&cn->mutex); proc_remove(cn->procdir); cn->procdir = NULL; From 8c9620b1cc9b69e82fa8d4081d646d0016b602e7 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 19 Jan 2019 16:31:00 +0100 Subject: [PATCH 161/525] mmc: bcm2835: Fix DMA channel leak on probe error The BCM2835 MMC host driver requests a DMA channel on probe but neglects to release the channel in the probe error path. The channel may therefore be leaked, in particular if devm_clk_get() causes probe deferral. Fix it. Fixes: 660fc733bd74 ("mmc: bcm2835: Add new driver for the sdhost controller.") Signed-off-by: Lukas Wunner Cc: stable@vger.kernel.org # v4.12+ Cc: Frank Pavlic Tested-by: Stefan Wahren Signed-off-by: Ulf Hansson --- drivers/mmc/host/bcm2835.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/mmc/host/bcm2835.c b/drivers/mmc/host/bcm2835.c index 50293529d6de..c9e7aa50bb0a 100644 --- a/drivers/mmc/host/bcm2835.c +++ b/drivers/mmc/host/bcm2835.c @@ -1431,6 +1431,8 @@ static int bcm2835_probe(struct platform_device *pdev) err: dev_dbg(dev, "%s -> err %d\n", __func__, ret); + if (host->dma_chan_rxtx) + dma_release_channel(host->dma_chan_rxtx); mmc_free_host(mmc); return ret; From 3751e008da0df4384031bd66a516c0292f915605 Mon Sep 17 00:00:00 2001 From: Chaotian Jing Date: Wed, 23 Jan 2019 20:05:25 +0800 Subject: [PATCH 162/525] mmc: mediatek: fix incorrect register setting of hs400_cmd_int_delay to set cmd internal delay, need set PAD_TUNE register but not PAD_CMD_TUNE register. Signed-off-by: Chaotian Jing Fixes: 1ede5cb88a29 ("mmc: mediatek: Use data tune for CMD line tune") Cc: stable@vger.kernel.org # v4.12+ Signed-off-by: Ulf Hansson --- drivers/mmc/host/mtk-sd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index 8afeaf81ae66..833ef0590af8 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -846,7 +846,7 @@ static void msdc_set_mclk(struct msdc_host *host, unsigned char timing, u32 hz) if (timing == MMC_TIMING_MMC_HS400 && host->dev_comp->hs400_tune) - sdr_set_field(host->base + PAD_CMD_TUNE, + sdr_set_field(host->base + tune_reg, MSDC_PAD_TUNE_CMDRRDLY, host->hs400_cmd_int_delay); dev_dbg(host->dev, "sclk: %d, timing: %d\n", host->mmc->actual_clock, From 1e19cdc8060227b0802bda6bc0bd22b23679ba32 Mon Sep 17 00:00:00 2001 From: Tejas Joglekar Date: Tue, 22 Jan 2019 13:26:51 +0530 Subject: [PATCH 163/525] usb: dwc3: gadget: Handle 0 xfer length for OUT EP For OUT endpoints, zero-length transfers require MaxPacketSize buffer as per the DWC_usb3 programming guide 3.30a section 4.2.3.3. This patch fixes this by explicitly checking zero length transfer to correctly pad up to MaxPacketSize. Fixes: c6267a51639b ("usb: dwc3: gadget: align transfers to wMaxPacketSize") Cc: stable@vger.kernel.org Signed-off-by: Tejas Joglekar Signed-off-by: Felipe Balbi --- drivers/usb/dwc3/gadget.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index bed2ff42780b..6c9b76bcc2e1 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1119,7 +1119,7 @@ static void dwc3_prepare_one_trb_linear(struct dwc3_ep *dep, unsigned int maxp = usb_endpoint_maxp(dep->endpoint.desc); unsigned int rem = length % maxp; - if (rem && usb_endpoint_dir_out(dep->endpoint.desc)) { + if ((!length || rem) && usb_endpoint_dir_out(dep->endpoint.desc)) { struct dwc3 *dwc = dep->dwc; struct dwc3_trb *trb; From 07c69f1148da7de3978686d3af9263325d9d60bd Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 22 Jan 2019 15:28:08 -0600 Subject: [PATCH 164/525] usb: gadget: udc: net2272: Fix bitwise and boolean operations (!x & y) strikes again. Fix bitwise and boolean operations by enclosing the expression: intcsr & (1 << NET2272_PCI_IRQ) in parentheses, before applying the boolean operator '!'. Notice that this code has been there since 2011. So, it would be helpful if someone can double-check this. This issue was detected with the help of Coccinelle. Fixes: ceb80363b2ec ("USB: net2272: driver for PLX NET2272 USB device controller") Cc: stable@vger.kernel.org Signed-off-by: Gustavo A. R. Silva Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc/net2272.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/gadget/udc/net2272.c b/drivers/usb/gadget/udc/net2272.c index 660878a19505..b77f3126580e 100644 --- a/drivers/usb/gadget/udc/net2272.c +++ b/drivers/usb/gadget/udc/net2272.c @@ -2083,7 +2083,7 @@ static irqreturn_t net2272_irq(int irq, void *_dev) #if defined(PLX_PCI_RDK2) /* see if PCI int for us by checking irqstat */ intcsr = readl(dev->rdk2.fpga_base_addr + RDK2_IRQSTAT); - if (!intcsr & (1 << NET2272_PCI_IRQ)) { + if (!(intcsr & (1 << NET2272_PCI_IRQ))) { spin_unlock(&dev->lock); return IRQ_NONE; } From f2105d42597f4d10e431b195d69e96dccaf9b012 Mon Sep 17 00:00:00 2001 From: Anders Roxell Date: Tue, 22 Jan 2019 11:36:02 +0100 Subject: [PATCH 165/525] usb: phy: fix link errors Fix link errors when CONFIG_FSL_USB2_OTG is enabled and USB_OTG_FSM is set to module then the following link error occurs. aarch64-linux-gnu-ld: drivers/usb/phy/phy-fsl-usb.o: in function `fsl_otg_ioctl': drivers/usb/phy/phy-fsl-usb.c:1083: undefined reference to `otg_statemachine' aarch64-linux-gnu-ld: drivers/usb/phy/phy-fsl-usb.c:1083:(.text+0x574): relocation truncated to fit: R_AARCH64_CALL26 against undefined symbol `otg_statemachine' aarch64-linux-gnu-ld: drivers/usb/phy/phy-fsl-usb.o: in function `fsl_otg_start_srp': drivers/usb/phy/phy-fsl-usb.c:674: undefined reference to `otg_statemachine' aarch64-linux-gnu-ld: drivers/usb/phy/phy-fsl-usb.c:674:(.text+0x61c): relocation truncated to fit: R_AARCH64_CALL26 against undefined symbol `otg_statemachine' aarch64-linux-gnu-ld: drivers/usb/phy/phy-fsl-usb.o: in function `fsl_otg_set_host': drivers/usb/phy/phy-fsl-usb.c:593: undefined reference to `otg_statemachine' aarch64-linux-gnu-ld: drivers/usb/phy/phy-fsl-usb.c:593:(.text+0x7a4): relocation truncated to fit: R_AARCH64_CALL26 against undefined symbol `otg_statemachine' aarch64-linux-gnu-ld: drivers/usb/phy/phy-fsl-usb.o: in function `fsl_otg_start_hnp': drivers/usb/phy/phy-fsl-usb.c:695: undefined reference to `otg_statemachine' aarch64-linux-gnu-ld: drivers/usb/phy/phy-fsl-usb.c:695:(.text+0x858): relocation truncated to fit: R_AARCH64_CALL26 against undefined symbol `otg_statemachine' aarch64-linux-gnu-ld: drivers/usb/phy/phy-fsl-usb.o: in function `a_wait_enum': drivers/usb/phy/phy-fsl-usb.c:274: undefined reference to `otg_statemachine' aarch64-linux-gnu-ld: drivers/usb/phy/phy-fsl-usb.c:274:(.text+0x16f0): relocation truncated to fit: R_AARCH64_CALL26 against undefined symbol `otg_statemachine' aarch64-linux-gnu-ld: drivers/usb/phy/phy-fsl-usb.o:drivers/usb/phy/phy-fsl-usb.c:619: more undefined references to `otg_statemachine' follow aarch64-linux-gnu-ld: drivers/usb/phy/phy-fsl-usb.o: in function `fsl_otg_set_peripheral': drivers/usb/phy/phy-fsl-usb.c:619:(.text+0x1fa0): relocation truncated to fit: R_AARCH64_CALL26 against undefined symbol `otg_statemachine' make[1]: *** [Makefile:1020: vmlinux] Error 1 make[1]: Target 'Image' not remade because of errors. make: *** [Makefile:152: sub-make] Error 2 make: Target 'Image' not remade because of errors. Rework so that FSL_USB2_OTG depends on that the USB_OTG_FSM is builtin. Signed-off-by: Anders Roxell Signed-off-by: Felipe Balbi --- drivers/usb/phy/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/phy/Kconfig b/drivers/usb/phy/Kconfig index d7312eed6088..91ea3083e7ad 100644 --- a/drivers/usb/phy/Kconfig +++ b/drivers/usb/phy/Kconfig @@ -21,7 +21,7 @@ config AB8500_USB config FSL_USB2_OTG bool "Freescale USB OTG Transceiver Driver" - depends on USB_EHCI_FSL && USB_FSL_USB2 && USB_OTG_FSM && PM + depends on USB_EHCI_FSL && USB_FSL_USB2 && USB_OTG_FSM=y && PM depends on USB_GADGET || !USB_GADGET # if USB_GADGET=m, this can't be 'y' select USB_PHY help From 512e6fb589bc18f9321457632e89b95017447db9 Mon Sep 17 00:00:00 2001 From: Alexey Khoroshilov Date: Tue, 22 Jan 2019 00:23:50 +0300 Subject: [PATCH 166/525] usb: dwc3: exynos: Fix error handling of clk_prepare_enable If clk_prepare_enable() fails in dwc3_exynos_probe() or in dwc3_exynos_resume(), exynos->clks[0] is left undisabled because of usage preincrement in while condition. Found by Linux Driver Verification project (linuxtesting.org). Fixes: 9f2168367a0a ("usb: dwc3: exynos: Rework clock handling and prepare for new variants") Acked-by: Marek Szyprowski Signed-off-by: Alexey Khoroshilov Signed-off-by: Felipe Balbi --- drivers/usb/dwc3/dwc3-exynos.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/usb/dwc3/dwc3-exynos.c b/drivers/usb/dwc3/dwc3-exynos.c index cb7fcd7c0ad8..c1e9ea621f41 100644 --- a/drivers/usb/dwc3/dwc3-exynos.c +++ b/drivers/usb/dwc3/dwc3-exynos.c @@ -78,7 +78,7 @@ static int dwc3_exynos_probe(struct platform_device *pdev) for (i = 0; i < exynos->num_clks; i++) { ret = clk_prepare_enable(exynos->clks[i]); if (ret) { - while (--i > 0) + while (i-- > 0) clk_disable_unprepare(exynos->clks[i]); return ret; } @@ -223,7 +223,7 @@ static int dwc3_exynos_resume(struct device *dev) for (i = 0; i < exynos->num_clks; i++) { ret = clk_prepare_enable(exynos->clks[i]); if (ret) { - while (--i > 0) + while (i-- > 0) clk_disable_unprepare(exynos->clks[i]); return ret; } From a53469a68eb886e84dd8b69a1458a623d3591793 Mon Sep 17 00:00:00 2001 From: Bin Liu Date: Wed, 16 Jan 2019 11:54:07 -0600 Subject: [PATCH 167/525] usb: phy: am335x: fix race condition in _probe power off the phy should be done before populate the phy. Otherwise, am335x_init() could be called by the phy owner to power on the phy first, then am335x_phy_probe() turns off the phy again without the caller knowing it. Fixes: 2fc711d76352 ("usb: phy: am335x: Enable USB remote wakeup using PHY wakeup") Cc: stable@vger.kernel.org # v3.18+ Signed-off-by: Bin Liu Signed-off-by: Felipe Balbi --- drivers/usb/phy/phy-am335x.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/usb/phy/phy-am335x.c b/drivers/usb/phy/phy-am335x.c index 27bdb7222527..f5f0568d8533 100644 --- a/drivers/usb/phy/phy-am335x.c +++ b/drivers/usb/phy/phy-am335x.c @@ -61,9 +61,6 @@ static int am335x_phy_probe(struct platform_device *pdev) if (ret) return ret; - ret = usb_add_phy_dev(&am_phy->usb_phy_gen.phy); - if (ret) - return ret; am_phy->usb_phy_gen.phy.init = am335x_init; am_phy->usb_phy_gen.phy.shutdown = am335x_shutdown; @@ -82,7 +79,7 @@ static int am335x_phy_probe(struct platform_device *pdev) device_set_wakeup_enable(dev, false); phy_ctrl_power(am_phy->phy_ctrl, am_phy->id, am_phy->dr_mode, false); - return 0; + return usb_add_phy_dev(&am_phy->usb_phy_gen.phy); } static int am335x_phy_remove(struct platform_device *pdev) From a6279470762c19ba97e454f90798373dccdf6148 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Fri, 25 Jan 2019 11:48:51 +0000 Subject: [PATCH 168/525] Btrfs: fix deadlock when allocating tree block during leaf/node split When splitting a leaf or node from one of the trees that are modified when flushing pending block groups (extent, chunk, device and free space trees), we need to allocate a new tree block, which in turn can result in the need to allocate a new block group. After allocating the new block group we may need to flush new block groups that were previously allocated during the course of the current transaction, which is what may cause a deadlock due to attempts to write lock twice the same leaf or node, as when splitting a leaf or node we are holding a write lock on it and its parent node. The same type of deadlock can also happen when increasing the tree's height, since we are holding a lock on the existing root while allocating the tree block to use as the new root node. An example trace when the deadlock happens during the leaf split path is: [27175.293054] CPU: 0 PID: 3005 Comm: kworker/u17:6 Tainted: G W 4.19.16 #1 [27175.293942] Hardware name: Penguin Computing Relion 1900/MD90-FS0-ZB-XX, BIOS R15 06/25/2018 [27175.294846] Workqueue: btrfs-extent-refs btrfs_extent_refs_helper [btrfs] (...) [27175.298384] RSP: 0018:ffffab2087107758 EFLAGS: 00010246 [27175.299269] RAX: 0000000000000bbd RBX: ffff9fadc7141c48 RCX: 0000000000000001 [27175.300155] RDX: 0000000000000001 RSI: 0000000000000002 RDI: ffff9fadc7141c48 [27175.301023] RBP: 0000000000000001 R08: ffff9faeb6ac1040 R09: ffff9fa9c0000000 [27175.301887] R10: 0000000000000000 R11: 0000000000000040 R12: ffff9fb21aac8000 [27175.302743] R13: ffff9fb1a64d6a20 R14: 0000000000000001 R15: ffff9fb1a64d6a18 [27175.303601] FS: 0000000000000000(0000) GS:ffff9fb21fa00000(0000) knlGS:0000000000000000 [27175.304468] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [27175.305339] CR2: 00007fdc8743ead8 CR3: 0000000763e0a006 CR4: 00000000003606f0 [27175.306220] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [27175.307087] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [27175.307940] Call Trace: [27175.308802] btrfs_search_slot+0x779/0x9a0 [btrfs] [27175.309669] ? update_space_info+0xba/0xe0 [btrfs] [27175.310534] btrfs_insert_empty_items+0x67/0xc0 [btrfs] [27175.311397] btrfs_insert_item+0x60/0xd0 [btrfs] [27175.312253] btrfs_create_pending_block_groups+0xee/0x210 [btrfs] [27175.313116] do_chunk_alloc+0x25f/0x300 [btrfs] [27175.313984] find_free_extent+0x706/0x10d0 [btrfs] [27175.314855] btrfs_reserve_extent+0x9b/0x1d0 [btrfs] [27175.315707] btrfs_alloc_tree_block+0x100/0x5b0 [btrfs] [27175.316548] split_leaf+0x130/0x610 [btrfs] [27175.317390] btrfs_search_slot+0x94d/0x9a0 [btrfs] [27175.318235] btrfs_insert_empty_items+0x67/0xc0 [btrfs] [27175.319087] alloc_reserved_file_extent+0x84/0x2c0 [btrfs] [27175.319938] __btrfs_run_delayed_refs+0x596/0x1150 [btrfs] [27175.320792] btrfs_run_delayed_refs+0xed/0x1b0 [btrfs] [27175.321643] delayed_ref_async_start+0x81/0x90 [btrfs] [27175.322491] normal_work_helper+0xd0/0x320 [btrfs] [27175.323328] ? move_linked_works+0x6e/0xa0 [27175.324160] process_one_work+0x191/0x370 [27175.324976] worker_thread+0x4f/0x3b0 [27175.325763] kthread+0xf8/0x130 [27175.326531] ? rescuer_thread+0x320/0x320 [27175.327284] ? kthread_create_worker_on_cpu+0x50/0x50 [27175.328027] ret_from_fork+0x35/0x40 [27175.328741] ---[ end trace 300a1b9f0ac30e26 ]--- Fix this by preventing the flushing of new blocks groups when splitting a leaf/node and when inserting a new root node for one of the trees modified by the flushing operation, similar to what is done when COWing a node/leaf from on of these trees. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202383 Reported-by: Eli V CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/ctree.c | 78 +++++++++++++++++++++++++++++++----------------- 1 file changed, 50 insertions(+), 28 deletions(-) diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index f64aad613727..5a6c39b44c84 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -968,6 +968,48 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, return 0; } +static struct extent_buffer *alloc_tree_block_no_bg_flush( + struct btrfs_trans_handle *trans, + struct btrfs_root *root, + u64 parent_start, + const struct btrfs_disk_key *disk_key, + int level, + u64 hint, + u64 empty_size) +{ + struct btrfs_fs_info *fs_info = root->fs_info; + struct extent_buffer *ret; + + /* + * If we are COWing a node/leaf from the extent, chunk, device or free + * space trees, make sure that we do not finish block group creation of + * pending block groups. We do this to avoid a deadlock. + * COWing can result in allocation of a new chunk, and flushing pending + * block groups (btrfs_create_pending_block_groups()) can be triggered + * when finishing allocation of a new chunk. Creation of a pending block + * group modifies the extent, chunk, device and free space trees, + * therefore we could deadlock with ourselves since we are holding a + * lock on an extent buffer that btrfs_create_pending_block_groups() may + * try to COW later. + * For similar reasons, we also need to delay flushing pending block + * groups when splitting a leaf or node, from one of those trees, since + * we are holding a write lock on it and its parent or when inserting a + * new root node for one of those trees. + */ + if (root == fs_info->extent_root || + root == fs_info->chunk_root || + root == fs_info->dev_root || + root == fs_info->free_space_root) + trans->can_flush_pending_bgs = false; + + ret = btrfs_alloc_tree_block(trans, root, parent_start, + root->root_key.objectid, disk_key, level, + hint, empty_size); + trans->can_flush_pending_bgs = true; + + return ret; +} + /* * does the dirty work in cow of a single block. The parent block (if * supplied) is updated to point to the new cow copy. The new buffer is marked @@ -1015,28 +1057,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, if ((root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) && parent) parent_start = parent->start; - /* - * If we are COWing a node/leaf from the extent, chunk, device or free - * space trees, make sure that we do not finish block group creation of - * pending block groups. We do this to avoid a deadlock. - * COWing can result in allocation of a new chunk, and flushing pending - * block groups (btrfs_create_pending_block_groups()) can be triggered - * when finishing allocation of a new chunk. Creation of a pending block - * group modifies the extent, chunk, device and free space trees, - * therefore we could deadlock with ourselves since we are holding a - * lock on an extent buffer that btrfs_create_pending_block_groups() may - * try to COW later. - */ - if (root == fs_info->extent_root || - root == fs_info->chunk_root || - root == fs_info->dev_root || - root == fs_info->free_space_root) - trans->can_flush_pending_bgs = false; - - cow = btrfs_alloc_tree_block(trans, root, parent_start, - root->root_key.objectid, &disk_key, level, - search_start, empty_size); - trans->can_flush_pending_bgs = true; + cow = alloc_tree_block_no_bg_flush(trans, root, parent_start, &disk_key, + level, search_start, empty_size); if (IS_ERR(cow)) return PTR_ERR(cow); @@ -3345,8 +3367,8 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans, else btrfs_node_key(lower, &lower_key, 0); - c = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid, - &lower_key, level, root->node->start, 0); + c = alloc_tree_block_no_bg_flush(trans, root, 0, &lower_key, level, + root->node->start, 0); if (IS_ERR(c)) return PTR_ERR(c); @@ -3475,8 +3497,8 @@ static noinline int split_node(struct btrfs_trans_handle *trans, mid = (c_nritems + 1) / 2; btrfs_node_key(c, &disk_key, mid); - split = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid, - &disk_key, level, c->start, 0); + split = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, level, + c->start, 0); if (IS_ERR(split)) return PTR_ERR(split); @@ -4260,8 +4282,8 @@ again: else btrfs_item_key(l, &disk_key, mid); - right = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid, - &disk_key, 0, l->start, 0); + right = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, 0, + l->start, 0); if (IS_ERR(right)) return PTR_ERR(right); From 7ae710f9f8b2cf95297e7bbfe1c09789a7dc43d4 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 27 Jan 2019 22:58:00 +0100 Subject: [PATCH 169/525] gpio: vf610: Mask all GPIO interrupts On SoC reset all GPIO interrupts are disable. However, if kexec is used to boot into a new kernel, the SoC does not experience a reset. Hence GPIO interrupts can be left enabled from the previous kernel. It is then possible for the interrupt to fire before an interrupt handler is registered, resulting in the kernel complaining of an "unexpected IRQ trap", the interrupt is never cleared, and so fires again, resulting in an interrupt storm. Disable all GPIO interrupts before registering the GPIO IRQ chip. Fixes: 7f2691a19627 ("gpio: vf610: add gpiolib/IRQ chip driver for Vybrid") Signed-off-by: Andrew Lunn Acked-by: Stefan Agner Signed-off-by: Linus Walleij --- drivers/gpio/gpio-vf610.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/gpio/gpio-vf610.c b/drivers/gpio/gpio-vf610.c index 1b79ebcfce3e..541fa6ac399d 100644 --- a/drivers/gpio/gpio-vf610.c +++ b/drivers/gpio/gpio-vf610.c @@ -253,6 +253,7 @@ static int vf610_gpio_probe(struct platform_device *pdev) struct vf610_gpio_port *port; struct resource *iores; struct gpio_chip *gc; + int i; int ret; port = devm_kzalloc(&pdev->dev, sizeof(*port), GFP_KERNEL); @@ -319,6 +320,10 @@ static int vf610_gpio_probe(struct platform_device *pdev) if (ret < 0) return ret; + /* Mask all GPIO interrupts */ + for (i = 0; i < gc->ngpio; i++) + vf610_gpio_writel(0, port->base + PORT_PCR(i)); + /* Clear the interrupt status register for all GPIO's */ vf610_gpio_writel(~0, port->base + PORT_ISFR); From 302167c50b32e7fccc98994a91d40ddbbab04e52 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Thu, 24 Jan 2019 09:31:43 -0500 Subject: [PATCH 170/525] btrfs: don't end the transaction for delayed refs in throttle Previously callers to btrfs_end_transaction_throttle() would commit the transaction if there wasn't enough delayed refs space. This happens in relocation, and if the fs is relatively empty we'll run out of delayed refs space basically immediately, so we'll just be stuck in this loop of committing the transaction over and over again. This code existed because we didn't have a good feedback mechanism for running delayed refs, but with the delayed refs rsv we do now. Delete this throttling code and let the btrfs_start_transaction() in relocation deal with putting pressure on the delayed refs infrastructure. With this patch we no longer take 5 minutes to balance a metadata only fs. Qu has submitted a fstest to catch slow balance or excessive transaction commits. Steps to reproduce: * create subvolume * create many (eg. 16000) inlined files, of size 2KiB * iteratively snapshot and touch several files to trigger metadata updates * start balance -m Reported-by: Qu Wenruo Fixes: 64403612b73a ("btrfs: rework btrfs_check_space_for_delayed_refs") Signed-off-by: Josef Bacik [ add tags and steps to reproduce ] Signed-off-by: David Sterba --- fs/btrfs/transaction.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 127fa1535f58..f15cf46f1b9d 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -850,14 +850,6 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, btrfs_trans_release_chunk_metadata(trans); - if (lock && should_end_transaction(trans) && - READ_ONCE(cur_trans->state) == TRANS_STATE_RUNNING) { - spin_lock(&info->trans_lock); - if (cur_trans->state == TRANS_STATE_RUNNING) - cur_trans->state = TRANS_STATE_BLOCKED; - spin_unlock(&info->trans_lock); - } - if (lock && READ_ONCE(cur_trans->state) == TRANS_STATE_BLOCKED) { if (throttle) return btrfs_commit_transaction(trans); From 870f193d48c25a97d61a8e6c04e3c29a2c606850 Mon Sep 17 00:00:00 2001 From: Fathi Boudra Date: Wed, 16 Jan 2019 11:43:18 -0600 Subject: [PATCH 171/525] selftests: net: use LDLIBS instead of LDFLAGS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit reuseport_bpf_numa fails to build due to undefined reference errors: aarch64-linaro-linux-gcc --sysroot=/build/tmp-rpb-glibc/sysroots/hikey -Wall -Wl,--no-as-needed -O2 -g -I../../../../usr/include/ -Wl,-O1 -Wl,--hash-style=gnu -Wl,--as-needed -lnuma reuseport_bpf_numa.c -o /build/tmp-rpb-glibc/work/hikey-linaro-linux/kselftests/4.12-r0/linux-4.12-rc7/tools/testing/selftests/net/reuseport_bpf_numa /tmp/ccfUuExT.o: In function `send_from_node': /build/tmp-rpb-glibc/work/hikey-linaro-linux/kselftests/4.12-r0/linux-4.12-rc7/tools/testing/selftests/net/reuseport_bpf_numa.c:138: undefined reference to `numa_run_on_node' /tmp/ccfUuExT.o: In function `main': /build/tmp-rpb-glibc/work/hikey-linaro-linux/kselftests/4.12-r0/linux-4.12-rc7/tools/testing/selftests/net/reuseport_bpf_numa.c:230: undefined reference to `numa_available' /build/tmp-rpb-glibc/work/hikey-linaro-linux/kselftests/4.12-r0/linux-4.12-rc7/tools/testing/selftests/net/reuseport_bpf_numa.c:233: undefined reference to `numa_max_node' It's GNU Make and linker specific. The default Makefile rule looks like: $(CC) $(CFLAGS) $(LDFLAGS) $@ $^ $(LDLIBS) When linking is done by gcc itself, no issue, but when it needs to be passed to proper ld, only LDLIBS follows and then ld cannot know what libs to link with. More detail: https://www.gnu.org/software/make/manual/html_node/Implicit-Variables.html LDFLAGS Extra flags to give to compilers when they are supposed to invoke the linker, ‘ld’, such as -L. Libraries (-lfoo) should be added to the LDLIBS variable instead. LDLIBS Library flags or names given to compilers when they are supposed to invoke the linker, ‘ld’. LOADLIBES is a deprecated (but still supported) alternative to LDLIBS. Non-library linker flags, such as -L, should go in the LDFLAGS variable. https://lkml.org/lkml/2010/2/10/362 tools/perf: libraries must come after objects Link order matters, use LDLIBS instead of LDFLAGS to properly link against libnuma. Signed-off-by: Fathi Boudra Signed-off-by: Shuah Khan --- tools/testing/selftests/net/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index f8f3e90700c0..1e6d14d2825c 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -21,6 +21,6 @@ TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls KSFT_KHDR_INSTALL := 1 include ../lib.mk -$(OUTPUT)/reuseport_bpf_numa: LDFLAGS += -lnuma +$(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma $(OUTPUT)/tcp_mmap: LDFLAGS += -lpthread $(OUTPUT)/tcp_inq: LDFLAGS += -lpthread From 7d4e591bc051d3382c45caaa2530969fb42ed23d Mon Sep 17 00:00:00 2001 From: Fathi Boudra Date: Wed, 16 Jan 2019 11:43:20 -0600 Subject: [PATCH 172/525] selftests: timers: use LDLIBS instead of LDFLAGS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit posix_timers fails to build due to undefined reference errors: aarch64-linaro-linux-gcc --sysroot=/build/tmp-rpb-glibc/sysroots/hikey -O2 -pipe -g -feliminate-unused-debug-types -O3 -Wl,-no-as-needed -Wall -DKTEST -Wl,-O1 -Wl,--hash-style=gnu -Wl,--as-needed -lrt -lpthread posix_timers.c -o /build/tmp-rpb-glibc/work/hikey-linaro-linux/kselftests/4.12-r0/linux-4.12-rc7/tools/testing/selftests/timers/posix_timers /tmp/cc1FTZzT.o: In function `check_timer_create': /usr/src/debug/kselftests/4.12-r0/linux-4.12-rc7/tools/testing/selftests/timers/posix_timers.c:157: undefined reference to `timer_create' /usr/src/debug/kselftests/4.12-r0/linux-4.12-rc7/tools/testing/selftests/timers/posix_timers.c:170: undefined reference to `timer_settime' collect2: error: ld returned 1 exit status It's GNU Make and linker specific. The default Makefile rule looks like: $(CC) $(CFLAGS) $(LDFLAGS) $@ $^ $(LDLIBS) When linking is done by gcc itself, no issue, but when it needs to be passed to proper ld, only LDLIBS follows and then ld cannot know what libs to link with. More detail: https://www.gnu.org/software/make/manual/html_node/Implicit-Variables.html LDFLAGS Extra flags to give to compilers when they are supposed to invoke the linker, ‘ld’, such as -L. Libraries (-lfoo) should be added to the LDLIBS variable instead. LDLIBS Library flags or names given to compilers when they are supposed to invoke the linker, ‘ld’. LOADLIBES is a deprecated (but still supported) alternative to LDLIBS. Non-library linker flags, such as -L, should go in the LDFLAGS variable. https://lkml.org/lkml/2010/2/10/362 tools/perf: libraries must come after objects Link order matters, use LDLIBS instead of LDFLAGS to properly link against libpthread. Signed-off-by: Denys Dmytriyenko Signed-off-by: Fathi Boudra Signed-off-by: Shuah Khan --- tools/testing/selftests/timers/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/timers/Makefile b/tools/testing/selftests/timers/Makefile index c02683cfb6c9..7656c7ce79d9 100644 --- a/tools/testing/selftests/timers/Makefile +++ b/tools/testing/selftests/timers/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += -O3 -Wl,-no-as-needed -Wall -LDFLAGS += -lrt -lpthread -lm +LDLIBS += -lrt -lpthread -lm # these are all "safe" tests that don't modify # system time or require escalated privileges From 80ff00172407e0aad4b10b94ef0816fc3e7813cb Mon Sep 17 00:00:00 2001 From: Yao Liu Date: Mon, 28 Jan 2019 19:44:14 +0800 Subject: [PATCH 173/525] nfs: Fix NULL pointer dereference of dev_name There is a NULL pointer dereference of dev_name in nfs_parse_devname() The oops looks something like: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 ... RIP: 0010:nfs_fs_mount+0x3b6/0xc20 [nfs] ... Call Trace: ? ida_alloc_range+0x34b/0x3d0 ? nfs_clone_super+0x80/0x80 [nfs] ? nfs_free_parsed_mount_data+0x60/0x60 [nfs] mount_fs+0x52/0x170 ? __init_waitqueue_head+0x3b/0x50 vfs_kern_mount+0x6b/0x170 do_mount+0x216/0xdc0 ksys_mount+0x83/0xd0 __x64_sys_mount+0x25/0x30 do_syscall_64+0x65/0x220 entry_SYSCALL_64_after_hwframe+0x49/0xbe Fix this by adding a NULL check on dev_name Signed-off-by: Yao Liu Signed-off-by: Anna Schumaker --- fs/nfs/super.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 22ce3c8a2f46..0570391eaa16 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1895,6 +1895,11 @@ static int nfs_parse_devname(const char *dev_name, size_t len; char *end; + if (unlikely(!dev_name || !*dev_name)) { + dfprintk(MOUNT, "NFS: device name not specified\n"); + return -EINVAL; + } + /* Is the host name protected with square brakcets? */ if (*dev_name == '[') { end = strchr(++dev_name, ']'); From 6479450f72c1391c03f08affe0d0110f41ae7ca0 Mon Sep 17 00:00:00 2001 From: Heyi Guo Date: Thu, 24 Jan 2019 21:37:08 +0800 Subject: [PATCH 174/525] irqchip/gic-v4: Fix occasional VLPI drop 1. In current implementation, every VLPI will temporarily be mapped to the first CPU in system (normally CPU0) and then moved to the real scheduled CPU later. 2. So there is a time window and a VLPI may be sent to CPU0 instead of the real scheduled vCPU, in a multi-CPU virtual machine. 3. However, CPU0 may have not been scheduled as a virtual CPU after system boots up, so the value of its GICR_VPROPBASER is unknown at that moment. 4. If the INTID of VLPI is larger than 2^(GICR_VPROPBASER.IDbits+1), while IDbits is also in unknown state, GIC will behave as if the VLPI is out of range and simply drop it, which results in interrupt missing in Guest. As no code will clear GICR_VPROPBASER at runtime, we can safely initialize the IDbits field at boot time for each CPU to get rid of this issue. We also clear Valid bit of GICR_VPENDBASER in case any ancient programming gets left in and causes memory corrupting. A new function its_clear_vpend_valid() is added to reuse the code in its_vpe_deschedule(). Fixes: e643d8034036 ("irqchip/gic-v3-its: Add VPE scheduling") Signed-off-by: Heyi Guo Signed-off-by: Heyi Guo Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-gic-v3-its.c | 66 ++++++++++++++++++++++++-------- 1 file changed, 49 insertions(+), 17 deletions(-) diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 7f2a45445b00..36181197d5e0 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -2059,6 +2059,29 @@ static int __init allocate_lpi_tables(void) return 0; } +static u64 its_clear_vpend_valid(void __iomem *vlpi_base) +{ + u32 count = 1000000; /* 1s! */ + bool clean; + u64 val; + + val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER); + val &= ~GICR_VPENDBASER_Valid; + gits_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); + + do { + val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER); + clean = !(val & GICR_VPENDBASER_Dirty); + if (!clean) { + count--; + cpu_relax(); + udelay(1); + } + } while (!clean && count); + + return val; +} + static void its_cpu_init_lpis(void) { void __iomem *rbase = gic_data_rdist_rd_base(); @@ -2144,6 +2167,30 @@ static void its_cpu_init_lpis(void) val |= GICR_CTLR_ENABLE_LPIS; writel_relaxed(val, rbase + GICR_CTLR); + if (gic_rdists->has_vlpis) { + void __iomem *vlpi_base = gic_data_rdist_vlpi_base(); + + /* + * It's possible for CPU to receive VLPIs before it is + * sheduled as a vPE, especially for the first CPU, and the + * VLPI with INTID larger than 2^(IDbits+1) will be considered + * as out of range and dropped by GIC. + * So we initialize IDbits to known value to avoid VLPI drop. + */ + val = (LPI_NRBITS - 1) & GICR_VPROPBASER_IDBITS_MASK; + pr_debug("GICv4: CPU%d: Init IDbits to 0x%llx for GICR_VPROPBASER\n", + smp_processor_id(), val); + gits_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER); + + /* + * Also clear Valid bit of GICR_VPENDBASER, in case some + * ancient programming gets left in and has possibility of + * corrupting memory. + */ + val = its_clear_vpend_valid(vlpi_base); + WARN_ON(val & GICR_VPENDBASER_Dirty); + } + /* Make sure the GIC has seen the above */ dsb(sy); out: @@ -2755,26 +2802,11 @@ static void its_vpe_schedule(struct its_vpe *vpe) static void its_vpe_deschedule(struct its_vpe *vpe) { void __iomem *vlpi_base = gic_data_rdist_vlpi_base(); - u32 count = 1000000; /* 1s! */ - bool clean; u64 val; - /* We're being scheduled out */ - val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER); - val &= ~GICR_VPENDBASER_Valid; - gits_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); + val = its_clear_vpend_valid(vlpi_base); - do { - val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER); - clean = !(val & GICR_VPENDBASER_Dirty); - if (!clean) { - count--; - cpu_relax(); - udelay(1); - } - } while (!clean && count); - - if (unlikely(!clean && !count)) { + if (unlikely(val & GICR_VPENDBASER_Dirty)) { pr_err_ratelimited("ITS virtual pending table not cleaning\n"); vpe->idai = false; vpe->pending_last = true; From 4aa9fc2a435abe95a1e8d7f8c7b3d6356514b37a Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 25 Jan 2019 19:08:58 +0100 Subject: [PATCH 175/525] Revert "mm, memory_hotplug: initialize struct pages for the full memory section" This reverts commit 2830bf6f05fb3e05bc4743274b806c821807a684. The underlying assumption that one sparse section belongs into a single numa node doesn't hold really. Robert Shteynfeld has reported a boot failure. The boot log was not captured but his memory layout is as follows: Early memory node ranges node 1: [mem 0x0000000000001000-0x0000000000090fff] node 1: [mem 0x0000000000100000-0x00000000dbdf8fff] node 1: [mem 0x0000000100000000-0x0000001423ffffff] node 0: [mem 0x0000001424000000-0x0000002023ffffff] This means that node0 starts in the middle of a memory section which is also in node1. memmap_init_zone tries to initialize padding of a section even when it is outside of the given pfn range because there are code paths (e.g. memory hotplug) which assume that the full worth of memory section is always initialized. In this particular case, though, such a range is already intialized and most likely already managed by the page allocator. Scribbling over those pages corrupts the internal state and likely blows up when any of those pages gets used. Reported-by: Robert Shteynfeld Fixes: 2830bf6f05fb ("mm, memory_hotplug: initialize struct pages for the full memory section") Cc: stable@kernel.org Signed-off-by: Michal Hocko Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 12 ------------ 1 file changed, 12 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d295c9bc01a8..35fdde041f5c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5701,18 +5701,6 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, cond_resched(); } } -#ifdef CONFIG_SPARSEMEM - /* - * If the zone does not span the rest of the section then - * we should at least initialize those pages. Otherwise we - * could blow up on a poisoned page in some paths which depend - * on full sections being initialized (e.g. memory hotplug). - */ - while (end_pfn % PAGES_PER_SECTION) { - __init_single_page(pfn_to_page(end_pfn), end_pfn, zone, nid); - end_pfn++; - } -#endif } #ifdef CONFIG_ZONE_DEVICE From ca899324305d953c19abb583b96f0dd81274b0b2 Mon Sep 17 00:00:00 2001 From: Yang Wei Date: Mon, 28 Jan 2019 22:42:25 +0800 Subject: [PATCH 176/525] net: i825xx: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles dev_consume_skb_irq() should be called in i596_interrupt() when skb xmit done. It makes drop profiles(dropwatch, perf) more friendly. Signed-off-by: Yang Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/i825xx/82596.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/i825xx/82596.c b/drivers/net/ethernet/i825xx/82596.c index d719668a6684..92929750f832 100644 --- a/drivers/net/ethernet/i825xx/82596.c +++ b/drivers/net/ethernet/i825xx/82596.c @@ -1310,7 +1310,7 @@ static irqreturn_t i596_interrupt(int irq, void *dev_id) dev->stats.tx_aborted_errors++; } - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); tx_cmd->cmd.command = 0; /* Mark free */ break; From 9e71a15d8b5bbce25c637f7f8833cd3f45b65646 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Mon, 28 Jan 2019 10:05:04 -0800 Subject: [PATCH 177/525] qed: Fix bug in tx promiscuous mode settings When running tx switched traffic between VNICs created via a bridge(to which VFs are added), adapter drops the unicast packets in tx flow due to VNIC's ucast mac being unknown to it. But VF interfaces being in promiscuous mode should have caused adapter to accept all the unknown ucast packets. Later, it was found that driver doesn't really configure tx promiscuous mode settings to accept all unknown unicast macs. This patch fixes tx promiscuous mode settings to accept all unknown/unmatched unicast macs and works out the scenario. Signed-off-by: Manish Chopra Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_l2.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 67c02ea93906..b8baa6fcef8e 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -609,6 +609,10 @@ qed_sp_update_accept_mode(struct qed_hwfn *p_hwfn, (!!(accept_filter & QED_ACCEPT_MCAST_MATCHED) && !!(accept_filter & QED_ACCEPT_MCAST_UNMATCHED))); + SET_FIELD(state, ETH_VPORT_TX_MODE_UCAST_ACCEPT_ALL, + (!!(accept_filter & QED_ACCEPT_UCAST_MATCHED) && + !!(accept_filter & QED_ACCEPT_UCAST_UNMATCHED))); + SET_FIELD(state, ETH_VPORT_TX_MODE_BCAST_ACCEPT_ALL, !!(accept_filter & QED_ACCEPT_BCAST)); @@ -2688,7 +2692,8 @@ static int qed_configure_filter_rx_mode(struct qed_dev *cdev, if (type == QED_FILTER_RX_MODE_TYPE_PROMISC) { accept_flags.rx_accept_filter |= QED_ACCEPT_UCAST_UNMATCHED | QED_ACCEPT_MCAST_UNMATCHED; - accept_flags.tx_accept_filter |= QED_ACCEPT_MCAST_UNMATCHED; + accept_flags.tx_accept_filter |= QED_ACCEPT_UCAST_UNMATCHED | + QED_ACCEPT_MCAST_UNMATCHED; } else if (type == QED_FILTER_RX_MODE_TYPE_MULTI_PROMISC) { accept_flags.rx_accept_filter |= QED_ACCEPT_MCAST_UNMATCHED; accept_flags.tx_accept_filter |= QED_ACCEPT_MCAST_UNMATCHED; From ff9296966e5e00b0d0d00477b2365a178f0f06a3 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Mon, 28 Jan 2019 10:05:05 -0800 Subject: [PATCH 178/525] qed: Fix LACP pdu drops for VFs VF is always configured to drop control frames (with reserved mac addresses) but to work LACP on the VFs, it would require LACP control frames to be forwarded or transmitted successfully. This patch fixes this in such a way that trusted VFs (marked through ndo_set_vf_trust) would be allowed to pass the control frames such as LACP pdus. Signed-off-by: Manish Chopra Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_l2.c | 5 +++++ drivers/net/ethernet/qlogic/qed/qed_l2.h | 3 +++ drivers/net/ethernet/qlogic/qed/qed_sriov.c | 10 ++++++++-- 3 files changed, 16 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index b8baa6fcef8e..e68ca83ae915 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -748,6 +748,11 @@ int qed_sp_vport_update(struct qed_hwfn *p_hwfn, return rc; } + if (p_params->update_ctl_frame_check) { + p_cmn->ctl_frame_mac_check_en = p_params->mac_chk_en; + p_cmn->ctl_frame_ethtype_check_en = p_params->ethtype_chk_en; + } + /* Update mcast bins for VFs, PF doesn't use this functionality */ qed_sp_update_mcast_bin(p_hwfn, p_ramrod, p_params); diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.h b/drivers/net/ethernet/qlogic/qed/qed_l2.h index 8d80f1095d17..7127d5aaac42 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.h +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.h @@ -219,6 +219,9 @@ struct qed_sp_vport_update_params { struct qed_rss_params *rss_params; struct qed_filter_accept_flags accept_flags; struct qed_sge_tpa_params *sge_tpa_params; + u8 update_ctl_frame_check; + u8 mac_chk_en; + u8 ethtype_chk_en; }; int qed_sp_vport_update(struct qed_hwfn *p_hwfn, diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index ca6290fa0f30..71a7af134dd8 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -1969,7 +1969,9 @@ static void qed_iov_vf_mbx_start_vport(struct qed_hwfn *p_hwfn, params.vport_id = vf->vport_id; params.max_buffers_per_cqe = start->max_buffers_per_cqe; params.mtu = vf->mtu; - params.check_mac = true; + + /* Non trusted VFs should enable control frame filtering */ + params.check_mac = !vf->p_vf_info.is_trusted_configured; rc = qed_sp_eth_vport_start(p_hwfn, ¶ms); if (rc) { @@ -5130,6 +5132,9 @@ static void qed_iov_handle_trust_change(struct qed_hwfn *hwfn) params.opaque_fid = vf->opaque_fid; params.vport_id = vf->vport_id; + params.update_ctl_frame_check = 1; + params.mac_chk_en = !vf_info->is_trusted_configured; + if (vf_info->rx_accept_mode & mask) { flags->update_rx_mode_config = 1; flags->rx_accept_filter = vf_info->rx_accept_mode; @@ -5147,7 +5152,8 @@ static void qed_iov_handle_trust_change(struct qed_hwfn *hwfn) } if (flags->update_rx_mode_config || - flags->update_tx_mode_config) + flags->update_tx_mode_config || + params.update_ctl_frame_check) qed_sp_vport_update(hwfn, ¶ms, QED_SPQ_MODE_EBLOCK, NULL); } From 327852ec64205bb651be391a069784872098a3b2 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Mon, 28 Jan 2019 10:05:06 -0800 Subject: [PATCH 179/525] qed: Fix VF probe failure while FLR VFs may hit VF-PF channel timeout while probing, as in some cases it was observed that VF FLR and VF "acquire" message transaction (i.e first message from VF to PF in VF's probe flow) could occur simultaneously which could lead VF to fail sending "acquire" message to PF as VF is marked disabled from HW perspective due to FLR, which will result into channel timeout and VF probe failure. In such cases, try retrying VF "acquire" message so that in later attempts it could be successful to pass message to PF after the VF FLR is completed and can be probed successfully. Signed-off-by: Manish Chopra Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_vf.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c index b6cccf44bf40..5dda547772c1 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.c +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c @@ -261,6 +261,7 @@ static int qed_vf_pf_acquire(struct qed_hwfn *p_hwfn) struct pfvf_acquire_resp_tlv *resp = &p_iov->pf2vf_reply->acquire_resp; struct pf_vf_pfdev_info *pfdev_info = &resp->pfdev_info; struct vf_pf_resc_request *p_resc; + u8 retry_cnt = VF_ACQUIRE_THRESH; bool resources_acquired = false; struct vfpf_acquire_tlv *req; int rc = 0, attempts = 0; @@ -314,6 +315,15 @@ static int qed_vf_pf_acquire(struct qed_hwfn *p_hwfn) /* send acquire request */ rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp)); + + /* Re-try acquire in case of vf-pf hw channel timeout */ + if (retry_cnt && rc == -EBUSY) { + DP_VERBOSE(p_hwfn, QED_MSG_IOV, + "VF retrying to acquire due to VPC timeout\n"); + retry_cnt--; + continue; + } + if (rc) goto exit; From 7c81626a3c37e4ac320b8ad785694ba498f24794 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Mon, 28 Jan 2019 10:05:07 -0800 Subject: [PATCH 180/525] qed: Fix system crash in ll2 xmit Cache number of fragments in the skb locally as in case of linear skb (with zero fragments), tx completion (or freeing of skb) may happen before driver tries to get number of frgaments from the skb which could lead to stale access to an already freed skb. Signed-off-by: Manish Chopra Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_ll2.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index d9237c65a838..b5f419b71287 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -2451,19 +2451,24 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb, { struct qed_ll2_tx_pkt_info pkt; const skb_frag_t *frag; + u8 flags = 0, nr_frags; int rc = -EINVAL, i; dma_addr_t mapping; u16 vlan = 0; - u8 flags = 0; if (unlikely(skb->ip_summed != CHECKSUM_NONE)) { DP_INFO(cdev, "Cannot transmit a checksummed packet\n"); return -EINVAL; } - if (1 + skb_shinfo(skb)->nr_frags > CORE_LL2_TX_MAX_BDS_PER_PACKET) { + /* Cache number of fragments from SKB since SKB may be freed by + * the completion routine after calling qed_ll2_prepare_tx_packet() + */ + nr_frags = skb_shinfo(skb)->nr_frags; + + if (1 + nr_frags > CORE_LL2_TX_MAX_BDS_PER_PACKET) { DP_ERR(cdev, "Cannot transmit a packet with %d fragments\n", - 1 + skb_shinfo(skb)->nr_frags); + 1 + nr_frags); return -EINVAL; } @@ -2485,7 +2490,7 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb, } memset(&pkt, 0, sizeof(pkt)); - pkt.num_of_bds = 1 + skb_shinfo(skb)->nr_frags; + pkt.num_of_bds = 1 + nr_frags; pkt.vlan = vlan; pkt.bd_flags = flags; pkt.tx_dest = QED_LL2_TX_DEST_NW; @@ -2496,12 +2501,17 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb, test_bit(QED_LL2_XMIT_FLAGS_FIP_DISCOVERY, &xmit_flags)) pkt.remove_stag = true; + /* qed_ll2_prepare_tx_packet() may actually send the packet if + * there are no fragments in the skb and subsequently the completion + * routine may run and free the SKB, so no dereferencing the SKB + * beyond this point unless skb has any fragments. + */ rc = qed_ll2_prepare_tx_packet(&cdev->hwfns[0], cdev->ll2->handle, &pkt, 1); if (rc) goto err; - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + for (i = 0; i < nr_frags; i++) { frag = &skb_shinfo(skb)->frags[i]; mapping = skb_frag_dma_map(&cdev->pdev->dev, frag, 0, From ffb057f98928aa099b08e419bbe5afc26ec9f448 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Mon, 28 Jan 2019 10:05:08 -0800 Subject: [PATCH 181/525] qed: Fix stack out of bounds bug KASAN reported following bug in qed_init_qm_get_idx_from_flags due to inappropriate casting of "pq_flags". Fix the type of "pq_flags". [ 196.624707] BUG: KASAN: stack-out-of-bounds in qed_init_qm_get_idx_from_flags+0x1a4/0x1b8 [qed] [ 196.624712] Read of size 8 at addr ffff809b00bc7360 by task kworker/0:9/1712 [ 196.624714] [ 196.624720] CPU: 0 PID: 1712 Comm: kworker/0:9 Not tainted 4.18.0-60.el8.aarch64+debug #1 [ 196.624723] Hardware name: To be filled by O.E.M. Saber/Saber, BIOS 0ACKL024 09/26/2018 [ 196.624733] Workqueue: events work_for_cpu_fn [ 196.624738] Call trace: [ 196.624742] dump_backtrace+0x0/0x2f8 [ 196.624745] show_stack+0x24/0x30 [ 196.624749] dump_stack+0xe0/0x11c [ 196.624755] print_address_description+0x68/0x260 [ 196.624759] kasan_report+0x178/0x340 [ 196.624762] __asan_report_load_n_noabort+0x38/0x48 [ 196.624786] qed_init_qm_get_idx_from_flags+0x1a4/0x1b8 [qed] [ 196.624808] qed_init_qm_info+0xec0/0x2200 [qed] [ 196.624830] qed_resc_alloc+0x284/0x7e8 [qed] [ 196.624853] qed_slowpath_start+0x6cc/0x1ae8 [qed] [ 196.624864] __qede_probe.isra.10+0x1cc/0x12c0 [qede] [ 196.624874] qede_probe+0x78/0xf0 [qede] [ 196.624879] local_pci_probe+0xc4/0x180 [ 196.624882] work_for_cpu_fn+0x54/0x98 [ 196.624885] process_one_work+0x758/0x1900 [ 196.624888] worker_thread+0x4e0/0xd18 [ 196.624892] kthread+0x2c8/0x350 [ 196.624897] ret_from_fork+0x10/0x18 [ 196.624899] [ 196.624902] Allocated by task 2: [ 196.624906] kasan_kmalloc.part.1+0x40/0x108 [ 196.624909] kasan_kmalloc+0xb4/0xc8 [ 196.624913] kasan_slab_alloc+0x14/0x20 [ 196.624916] kmem_cache_alloc_node+0x1dc/0x480 [ 196.624921] copy_process.isra.1.part.2+0x1d8/0x4a98 [ 196.624924] _do_fork+0x150/0xfa0 [ 196.624926] kernel_thread+0x48/0x58 [ 196.624930] kthreadd+0x3a4/0x5a0 [ 196.624932] ret_from_fork+0x10/0x18 [ 196.624934] [ 196.624937] Freed by task 0: [ 196.624938] (stack is not available) [ 196.624940] [ 196.624943] The buggy address belongs to the object at ffff809b00bc0000 [ 196.624943] which belongs to the cache thread_stack of size 32768 [ 196.624946] The buggy address is located 29536 bytes inside of [ 196.624946] 32768-byte region [ffff809b00bc0000, ffff809b00bc8000) [ 196.624948] The buggy address belongs to the page: [ 196.624952] page:ffff7fe026c02e00 count:1 mapcount:0 mapping:ffff809b4001c000 index:0x0 compound_mapcount: 0 [ 196.624960] flags: 0xfffff8000008100(slab|head) [ 196.624967] raw: 0fffff8000008100 dead000000000100 dead000000000200 ffff809b4001c000 [ 196.624970] raw: 0000000000000000 0000000000080008 00000001ffffffff 0000000000000000 [ 196.624973] page dumped because: kasan: bad access detected [ 196.624974] [ 196.624976] Memory state around the buggy address: [ 196.624980] ffff809b00bc7200: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 196.624983] ffff809b00bc7280: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 196.624985] >ffff809b00bc7300: 00 00 00 00 00 00 00 00 f1 f1 f1 f1 04 f2 f2 f2 [ 196.624988] ^ [ 196.624990] ffff809b00bc7380: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 196.624993] ffff809b00bc7400: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 196.624995] ================================================================== Signed-off-by: Manish Chopra Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_dev.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 8f6551421945..2ecaaaa4469a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -795,19 +795,19 @@ static void qed_init_qm_pq(struct qed_hwfn *p_hwfn, /* get pq index according to PQ_FLAGS */ static u16 *qed_init_qm_get_idx_from_flags(struct qed_hwfn *p_hwfn, - u32 pq_flags) + unsigned long pq_flags) { struct qed_qm_info *qm_info = &p_hwfn->qm_info; /* Can't have multiple flags set here */ - if (bitmap_weight((unsigned long *)&pq_flags, + if (bitmap_weight(&pq_flags, sizeof(pq_flags) * BITS_PER_BYTE) > 1) { - DP_ERR(p_hwfn, "requested multiple pq flags 0x%x\n", pq_flags); + DP_ERR(p_hwfn, "requested multiple pq flags 0x%lx\n", pq_flags); goto err; } if (!(qed_get_pq_flags(p_hwfn) & pq_flags)) { - DP_ERR(p_hwfn, "pq flag 0x%x is not set\n", pq_flags); + DP_ERR(p_hwfn, "pq flag 0x%lx is not set\n", pq_flags); goto err; } From 483cbbeddd5fe2c80fd4141ff0748fa06c4ff146 Mon Sep 17 00:00:00 2001 From: Alexei Naberezhnov Date: Tue, 27 Mar 2018 16:54:16 -0700 Subject: [PATCH 182/525] md/raid5: fix 'out of memory' during raid cache recovery This fixes the case when md array assembly fails because of raid cache recovery unable to allocate a stripe, despite attempts to replay stripes and increase cache size. This happens because stripes released by r5c_recovery_replay_stripes and raid5_set_cache_size don't become available for allocation immediately. Released stripes first are placed on conf->released_stripes list and require md thread to merge them on conf->inactive_list before they can be allocated. Patch allows final allocation attempt during cache recovery to wait for new stripes to become availabe for allocation. Cc: linux-raid@vger.kernel.org Cc: Shaohua Li Cc: linux-stable # 4.10+ Fixes: b4c625c67362 ("md/r5cache: r5cache recovery: part 1") Signed-off-by: Alexei Naberezhnov Signed-off-by: Song Liu --- drivers/md/raid5-cache.c | 33 ++++++++++++++++++++++----------- drivers/md/raid5.c | 8 ++++++-- 2 files changed, 28 insertions(+), 13 deletions(-) diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index ec3a5ef7fee0..cbbe6b6535be 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -1935,12 +1935,14 @@ out: } static struct stripe_head * -r5c_recovery_alloc_stripe(struct r5conf *conf, - sector_t stripe_sect) +r5c_recovery_alloc_stripe( + struct r5conf *conf, + sector_t stripe_sect, + int noblock) { struct stripe_head *sh; - sh = raid5_get_active_stripe(conf, stripe_sect, 0, 1, 0); + sh = raid5_get_active_stripe(conf, stripe_sect, 0, noblock, 0); if (!sh) return NULL; /* no more stripe available */ @@ -2150,7 +2152,7 @@ r5c_recovery_analyze_meta_block(struct r5l_log *log, stripe_sect); if (!sh) { - sh = r5c_recovery_alloc_stripe(conf, stripe_sect); + sh = r5c_recovery_alloc_stripe(conf, stripe_sect, 1); /* * cannot get stripe from raid5_get_active_stripe * try replay some stripes @@ -2159,20 +2161,29 @@ r5c_recovery_analyze_meta_block(struct r5l_log *log, r5c_recovery_replay_stripes( cached_stripe_list, ctx); sh = r5c_recovery_alloc_stripe( - conf, stripe_sect); + conf, stripe_sect, 1); } if (!sh) { + int new_size = conf->min_nr_stripes * 2; pr_debug("md/raid:%s: Increasing stripe cache size to %d to recovery data on journal.\n", mdname(mddev), - conf->min_nr_stripes * 2); - raid5_set_cache_size(mddev, - conf->min_nr_stripes * 2); - sh = r5c_recovery_alloc_stripe(conf, - stripe_sect); + new_size); + ret = raid5_set_cache_size(mddev, new_size); + if (conf->min_nr_stripes <= new_size / 2) { + pr_err("md/raid:%s: Cannot increase cache size, ret=%d, new_size=%d, min_nr_stripes=%d, max_nr_stripes=%d\n", + mdname(mddev), + ret, + new_size, + conf->min_nr_stripes, + conf->max_nr_stripes); + return -ENOMEM; + } + sh = r5c_recovery_alloc_stripe( + conf, stripe_sect, 0); } if (!sh) { pr_err("md/raid:%s: Cannot get enough stripes due to memory pressure. Recovery failed.\n", - mdname(mddev)); + mdname(mddev)); return -ENOMEM; } list_add_tail(&sh->lru, cached_stripe_list); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 4990f0319f6c..cecea901ab8c 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -6369,6 +6369,7 @@ raid5_show_stripe_cache_size(struct mddev *mddev, char *page) int raid5_set_cache_size(struct mddev *mddev, int size) { + int result = 0; struct r5conf *conf = mddev->private; if (size <= 16 || size > 32768) @@ -6385,11 +6386,14 @@ raid5_set_cache_size(struct mddev *mddev, int size) mutex_lock(&conf->cache_size_mutex); while (size > conf->max_nr_stripes) - if (!grow_one_stripe(conf, GFP_KERNEL)) + if (!grow_one_stripe(conf, GFP_KERNEL)) { + conf->min_nr_stripes = conf->max_nr_stripes; + result = -ENOMEM; break; + } mutex_unlock(&conf->cache_size_mutex); - return 0; + return result; } EXPORT_SYMBOL(raid5_set_cache_size); From 8d2df8a2d0fa59d1214841202d8e9176057c42ae Mon Sep 17 00:00:00 2001 From: Souptick Joarder Date: Mon, 7 Jan 2019 23:07:19 +0530 Subject: [PATCH 183/525] arch/arm/xen: Remove duplicate header Remove duplicate header which is included twice. Signed-off-by: Souptick Joarder Reviewed-by: Oleksandr Andrushchenko Acked-by: Stefano Stabellini Signed-off-by: Boris Ostrovsky --- arch/arm/xen/mm.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c index cb44aa290e73..e1d44b903dfc 100644 --- a/arch/arm/xen/mm.c +++ b/arch/arm/xen/mm.c @@ -7,7 +7,6 @@ #include #include #include -#include #include #include From 8c79b35693380d856dcbbc21629682a90f26ca62 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 28 Jan 2019 10:01:21 -0800 Subject: [PATCH 184/525] tools: bpftool: fix crash with un-owned prog arrays Prog arrays don't have 'owner_prog_type' and 'owner_jited' fields in their fdinfo when they are created. Those fields are set and reported when first program is checked for compatibility by bpf_prog_array_compatible(). This means that bpftool cannot expect the fields to always be there. Currently trying to show maps on a system with an un-owned prog array leads to a crash: $ bpftool map show 389: prog_array name tail_call_map flags 0x0 Error: key 'owner_prog_type' not found in fdinfo Error: key 'owner_jited' not found in fdinfo key 4B value 4B max_entries 4 memlock 4096B Segmentation fault (core dumped) We pass a NULL pointer to atoi(). Remove the assumption that fdinfo keys are always present. Add missing validations and remove the p_err() calls which may lead to broken JSON output as caller will not propagate the failure. Fixes: 99a44bef5870 ("tools: bpftool: add owner_prog_type and owner_jited to bpftool output") Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- tools/bpf/bpftool/common.c | 6 +----- tools/bpf/bpftool/map.c | 17 ++++++++--------- 2 files changed, 9 insertions(+), 14 deletions(-) diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 897483457bf0..f7261fad45c1 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -297,10 +297,8 @@ char *get_fdinfo(int fd, const char *key) snprintf(path, sizeof(path), "/proc/self/fdinfo/%d", fd); fdi = fopen(path, "r"); - if (!fdi) { - p_err("can't open fdinfo: %s", strerror(errno)); + if (!fdi) return NULL; - } while ((n = getline(&line, &line_n, fdi)) > 0) { char *value; @@ -313,7 +311,6 @@ char *get_fdinfo(int fd, const char *key) value = strchr(line, '\t'); if (!value || !value[1]) { - p_err("malformed fdinfo!?"); free(line); return NULL; } @@ -326,7 +323,6 @@ char *get_fdinfo(int fd, const char *key) return line; } - p_err("key '%s' not found in fdinfo", key); free(line); fclose(fdi); return NULL; diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index 29a3468c6cf6..1ef1ee2280a2 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -513,10 +513,9 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) jsonw_uint_field(json_wtr, "owner_prog_type", prog_type); } - if (atoi(owner_jited)) - jsonw_bool_field(json_wtr, "owner_jited", true); - else - jsonw_bool_field(json_wtr, "owner_jited", false); + if (owner_jited) + jsonw_bool_field(json_wtr, "owner_jited", + !!atoi(owner_jited)); free(owner_prog_type); free(owner_jited); @@ -569,7 +568,8 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) char *owner_prog_type = get_fdinfo(fd, "owner_prog_type"); char *owner_jited = get_fdinfo(fd, "owner_jited"); - printf("\n\t"); + if (owner_prog_type || owner_jited) + printf("\n\t"); if (owner_prog_type) { unsigned int prog_type = atoi(owner_prog_type); @@ -579,10 +579,9 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) else printf("owner_prog_type %d ", prog_type); } - if (atoi(owner_jited)) - printf("owner jited"); - else - printf("owner not jited"); + if (owner_jited) + printf("owner%s jited", + atoi(owner_jited) ? "" : " not"); free(owner_prog_type); free(owner_jited); From 1d79895aef18fa05789995d86d523c9b2ee58a02 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Mon, 28 Jan 2019 10:13:35 +0100 Subject: [PATCH 185/525] sk_msg: Always cancel strp work before freeing the psock Despite having stopped the parser, we still need to deinitialize it by calling strp_done so that it cancels its work. Otherwise the worker thread can run after we have freed the parser, and attempt to access its workqueue resulting in a use-after-free: ================================================================== BUG: KASAN: use-after-free in pwq_activate_delayed_work+0x1b/0x1d0 Read of size 8 at addr ffff888069975240 by task kworker/u2:2/93 CPU: 0 PID: 93 Comm: kworker/u2:2 Not tainted 5.0.0-rc2-00335-g28f9d1a3d4fe-dirty #14 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-2.fc27 04/01/2014 Workqueue: (null) (kstrp) Call Trace: print_address_description+0x6e/0x2b0 ? pwq_activate_delayed_work+0x1b/0x1d0 kasan_report+0xfd/0x177 ? pwq_activate_delayed_work+0x1b/0x1d0 ? pwq_activate_delayed_work+0x1b/0x1d0 pwq_activate_delayed_work+0x1b/0x1d0 ? process_one_work+0x4aa/0x660 pwq_dec_nr_in_flight+0x9b/0x100 worker_thread+0x82/0x680 ? process_one_work+0x660/0x660 kthread+0x1b9/0x1e0 ? __kthread_create_on_node+0x250/0x250 ret_from_fork+0x1f/0x30 Allocated by task 111: sk_psock_init+0x3c/0x1b0 sock_map_link.isra.2+0x103/0x4b0 sock_map_update_common+0x94/0x270 sock_map_update_elem+0x145/0x160 __se_sys_bpf+0x152e/0x1e10 do_syscall_64+0xb2/0x3e0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Freed by task 112: kfree+0x7f/0x140 process_one_work+0x40b/0x660 worker_thread+0x82/0x680 kthread+0x1b9/0x1e0 ret_from_fork+0x1f/0x30 The buggy address belongs to the object at ffff888069975180 which belongs to the cache kmalloc-512 of size 512 The buggy address is located 192 bytes inside of 512-byte region [ffff888069975180, ffff888069975380) The buggy address belongs to the page: page:ffffea0001a65d00 count:1 mapcount:0 mapping:ffff88806d401280 index:0x0 compound_mapcount: 0 flags: 0x4000000000010200(slab|head) raw: 4000000000010200 dead000000000100 dead000000000200 ffff88806d401280 raw: 0000000000000000 00000000800c000c 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888069975100: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff888069975180: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff888069975200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff888069975280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888069975300: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== Reported-by: Marek Majkowski Signed-off-by: Jakub Sitnicki Link: https://lore.kernel.org/netdev/CAJPywTLwgXNEZ2dZVoa=udiZmtrWJ0q5SuBW64aYs0Y1khXX3A@mail.gmail.com Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- net/core/skmsg.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index d6d5c20d7044..8c826603bf36 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -545,8 +545,7 @@ static void sk_psock_destroy_deferred(struct work_struct *gc) struct sk_psock *psock = container_of(gc, struct sk_psock, gc); /* No sk_callback_lock since already detached. */ - if (psock->parser.enabled) - strp_done(&psock->parser.strp); + strp_done(&psock->parser.strp); cancel_work_sync(&psock->work); From 2fa53f8924223e81cd85e19f0c2caf110f086752 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 28 Jan 2019 23:55:26 +0100 Subject: [PATCH 186/525] bpf, doc: add reviewers to maintainers entry In order to better scale BPF development on netdev, we've adopted a reviewer rotation for all BPF patches among the five of us for some time now. Lets give credit where credit is due, and add Martin, Song and Yonghong as official BPF reviewers to MAINTAINERS file. Also while at it, add regex matching for BPF such that we get properly Cc'ed for files not listed here. Signed-off-by: Daniel Borkmann Acked-by: Martin KaFai Lau Acked-by: Yonghong Song Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- MAINTAINERS | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 51029a425dbe..6e13378f9746 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2848,6 +2848,9 @@ F: include/uapi/linux/if_bonding.h BPF (Safe dynamic programs and tools) M: Alexei Starovoitov M: Daniel Borkmann +R: Martin KaFai Lau +R: Song Liu +R: Yonghong Song L: netdev@vger.kernel.org L: linux-kernel@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git @@ -2873,6 +2876,8 @@ F: samples/bpf/ F: tools/bpf/ F: tools/lib/bpf/ F: tools/testing/selftests/bpf/ +K: bpf +N: bpf BPF JIT for ARM M: Shubham Bansal From b63195698dea6ea83eeede20e38dbc6ad67076b6 Mon Sep 17 00:00:00 2001 From: Steffen Maier Date: Thu, 24 Jan 2019 17:40:34 +0100 Subject: [PATCH 187/525] scsi: zfcp: fix sysfs block queue limit output for max_segment_size Since v2.6.35 commit 683229845f17 ("[SCSI] zfcp: Report scatter-gather limits to SCSI and block layer"), zfcp set dma_parms.max_segment_size == PAGE_SIZE (but without using the setter dma_set_max_seg_size()) and scsi_host_template.dma_boundary == PAGE_SIZE - 1. v5.0-rc1 commit 50c2e9107f17 ("scsi: introduce a max_segment_size host_template parameters") introduced a new field scsi_host_template.max_segment_size. If an LLDD such as zfcp does not set it, scsi_host_alloc() uses BLK_MAX_SEGMENT_SIZE = 65536 for Scsi_Host.max_segment_size. __scsi_init_queue() announced the minimum of Scsi_Host.max_segment_size and dma_parms.max_segment_size to the block layer. For zfcp: min(65536, 4096) == 4096 which was still good. v5.0 commit a8cf59a6692c ("scsi: communicate max segment size to the DMA mapping code") announces Scsi_Host.max_segment_size to the block layer and overwrites dma_parms.max_segment_size with Scsi_Host.max_segment_size. For zfcp dma_parms.max_segment_size == Scsi_Host.max_segment_size == 65536 which is also reflected in block queue limits. $ cd /sys/bus/ccw/drivers/zfcp $ cd 0.0.3c40/host5/rport-5:0-4/target5:0:4/5:0:4:10/block/sdi/queue $ cat max_segment_size 65536 Zfcp I/O still works because dma_boundary implicitly still keeps the effective max segment size <= PAGE_SIZE. However, dma_boundary does not seem visible to user space, but max_segment_size is visible and shows a misleading wrong value. Fix it and inherit the stable tag of a8cf59a6692c. Devices on our bus ccw support DMA but no DMA mapping. Of multiple device types on the ccw bus, only zfcp needs dma_parms for SCSI limits. So, leave dma_parms setup in zfcp and do not move it to the bus. Signed-off-by: Steffen Maier Fixes: 50c2e9107f ("scsi: introduce a max_segment_size host_template parameters") Signed-off-by: Martin K. Petersen --- drivers/s390/scsi/zfcp_aux.c | 1 - drivers/s390/scsi/zfcp_scsi.c | 2 ++ 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/s390/scsi/zfcp_aux.c b/drivers/s390/scsi/zfcp_aux.c index 9cf30d124b9e..e390f8c6d5f3 100644 --- a/drivers/s390/scsi/zfcp_aux.c +++ b/drivers/s390/scsi/zfcp_aux.c @@ -403,7 +403,6 @@ struct zfcp_adapter *zfcp_adapter_enqueue(struct ccw_device *ccw_device) goto failed; /* report size limit per scatter-gather segment */ - adapter->dma_parms.max_segment_size = ZFCP_QDIO_SBALE_LEN; adapter->ccw_device->dev.dma_parms = &adapter->dma_parms; adapter->stat_read_buf_num = FSF_STATUS_READS_RECOM; diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c index 00acc7144bbc..f4f6a07c5222 100644 --- a/drivers/s390/scsi/zfcp_scsi.c +++ b/drivers/s390/scsi/zfcp_scsi.c @@ -428,6 +428,8 @@ static struct scsi_host_template zfcp_scsi_host_template = { .max_sectors = (((QDIO_MAX_ELEMENTS_PER_BUFFER - 1) * ZFCP_QDIO_MAX_SBALS_PER_REQ) - 2) * 8, /* GCD, adjusted later */ + /* report size limit per scatter-gather segment */ + .max_segment_size = ZFCP_QDIO_SBALE_LEN, .dma_boundary = ZFCP_QDIO_SBALE_LEN - 1, .shost_attrs = zfcp_sysfs_shost_attrs, .sdev_attrs = zfcp_sysfs_sdev_attrs, From 5d8fc4a9f0eec20b6c07895022a6bea3fb6dfb38 Mon Sep 17 00:00:00 2001 From: Ming Lu Date: Thu, 24 Jan 2019 13:25:42 +0800 Subject: [PATCH 188/525] scsi: libfc: free skb when receiving invalid flogi resp The issue to be fixed in this commit is when libfc found it received a invalid FLOGI response from FC switch, it would return without freeing the fc frame, which is just the skb data. This would cause memory leak if FC switch keeps sending invalid FLOGI responses. This fix is just to make it execute `fc_frame_free(fp)` before returning from function `fc_lport_flogi_resp`. Signed-off-by: Ming Lu Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- drivers/scsi/libfc/fc_lport.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/libfc/fc_lport.c b/drivers/scsi/libfc/fc_lport.c index be83590ed955..ff943f477d6f 100644 --- a/drivers/scsi/libfc/fc_lport.c +++ b/drivers/scsi/libfc/fc_lport.c @@ -1726,14 +1726,14 @@ void fc_lport_flogi_resp(struct fc_seq *sp, struct fc_frame *fp, fc_frame_payload_op(fp) != ELS_LS_ACC) { FC_LPORT_DBG(lport, "FLOGI not accepted or bad response\n"); fc_lport_error(lport, fp); - goto err; + goto out; } flp = fc_frame_payload_get(fp, sizeof(*flp)); if (!flp) { FC_LPORT_DBG(lport, "FLOGI bad response\n"); fc_lport_error(lport, fp); - goto err; + goto out; } mfs = ntohs(flp->fl_csp.sp_bb_data) & @@ -1743,7 +1743,7 @@ void fc_lport_flogi_resp(struct fc_seq *sp, struct fc_frame *fp, FC_LPORT_DBG(lport, "FLOGI bad mfs:%hu response, " "lport->mfs:%hu\n", mfs, lport->mfs); fc_lport_error(lport, fp); - goto err; + goto out; } if (mfs <= lport->mfs) { From 40d07b523cf434f252b134c86b1f8f2d907ffb0b Mon Sep 17 00:00:00 2001 From: Douglas Gilbert Date: Fri, 25 Jan 2019 12:46:09 -0500 Subject: [PATCH 189/525] scsi: scsi_debug: fix write_same with virtual_gb problem The WRITE SAME(10) and (16) implementations didn't take account of the buffer wrap required when the virtual_gb parameter is greater than 0. Fix that and rename the fake_store() function to lba2fake_store() to lessen confusion with the global fake_storep pointer. Bump version date. Signed-off-by: Douglas Gilbert Reported-by: Bart Van Assche Tested by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_debug.c | 41 ++++++++++++++++++++------------------- 1 file changed, 21 insertions(+), 20 deletions(-) diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 661512bec3ac..e27f4df24021 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -62,7 +62,7 @@ /* make sure inq_product_rev string corresponds to this version */ #define SDEBUG_VERSION "0188" /* format to fit INQUIRY revision field */ -static const char *sdebug_version_date = "20180128"; +static const char *sdebug_version_date = "20190125"; #define MY_NAME "scsi_debug" @@ -735,7 +735,7 @@ static inline bool scsi_debug_lbp(void) (sdebug_lbpu || sdebug_lbpws || sdebug_lbpws10); } -static void *fake_store(unsigned long long lba) +static void *lba2fake_store(unsigned long long lba) { lba = do_div(lba, sdebug_store_sectors); @@ -2514,8 +2514,8 @@ static int do_device_access(struct scsi_cmnd *scmd, u32 sg_skip, u64 lba, return ret; } -/* If fake_store(lba,num) compares equal to arr(num), then copy top half of - * arr into fake_store(lba,num) and return true. If comparison fails then +/* If lba2fake_store(lba,num) compares equal to arr(num), then copy top half of + * arr into lba2fake_store(lba,num) and return true. If comparison fails then * return false. */ static bool comp_write_worker(u64 lba, u32 num, const u8 *arr) { @@ -2643,7 +2643,7 @@ static int prot_verify_read(struct scsi_cmnd *SCpnt, sector_t start_sec, if (sdt->app_tag == cpu_to_be16(0xffff)) continue; - ret = dif_verify(sdt, fake_store(sector), sector, ei_lba); + ret = dif_verify(sdt, lba2fake_store(sector), sector, ei_lba); if (ret) { dif_errors++; return ret; @@ -3261,10 +3261,12 @@ err_out: static int resp_write_same(struct scsi_cmnd *scp, u64 lba, u32 num, u32 ei_lba, bool unmap, bool ndob) { + int ret; unsigned long iflags; unsigned long long i; - int ret; - u64 lba_off; + u32 lb_size = sdebug_sector_size; + u64 block, lbaa; + u8 *fs1p; ret = check_device_access_params(scp, lba, num); if (ret) @@ -3276,31 +3278,30 @@ static int resp_write_same(struct scsi_cmnd *scp, u64 lba, u32 num, unmap_region(lba, num); goto out; } - - lba_off = lba * sdebug_sector_size; + lbaa = lba; + block = do_div(lbaa, sdebug_store_sectors); /* if ndob then zero 1 logical block, else fetch 1 logical block */ + fs1p = fake_storep + (block * lb_size); if (ndob) { - memset(fake_storep + lba_off, 0, sdebug_sector_size); + memset(fs1p, 0, lb_size); ret = 0; } else - ret = fetch_to_dev_buffer(scp, fake_storep + lba_off, - sdebug_sector_size); + ret = fetch_to_dev_buffer(scp, fs1p, lb_size); if (-1 == ret) { write_unlock_irqrestore(&atomic_rw, iflags); return DID_ERROR << 16; - } else if (sdebug_verbose && !ndob && (ret < sdebug_sector_size)) + } else if (sdebug_verbose && !ndob && (ret < lb_size)) sdev_printk(KERN_INFO, scp->device, "%s: %s: lb size=%u, IO sent=%d bytes\n", - my_name, "write same", - sdebug_sector_size, ret); + my_name, "write same", lb_size, ret); /* Copy first sector to remaining blocks */ - for (i = 1 ; i < num ; i++) - memcpy(fake_storep + ((lba + i) * sdebug_sector_size), - fake_storep + lba_off, - sdebug_sector_size); - + for (i = 1 ; i < num ; i++) { + lbaa = lba + i; + block = do_div(lbaa, sdebug_store_sectors); + memmove(fake_storep + (block * lb_size), fs1p, lb_size); + } if (scsi_debug_lbp()) map_region(lba, num); out: From b2d3492fc591b1fb46b81d79ca1fc44cac6ae0ae Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 24 Jan 2019 13:29:40 +0300 Subject: [PATCH 190/525] scsi: bnx2fc: Fix error handling in probe() There are two issues here. First if cmgr->hba is not set early enough then it leads to a NULL dereference. Second if we don't completely initialize cmgr->io_bdt_pool[] then we end up dereferencing uninitialized pointers. Fixes: 853e2bd2103a ("[SCSI] bnx2fc: Broadcom FCoE offload driver") Signed-off-by: Dan Carpenter Signed-off-by: Martin K. Petersen --- drivers/scsi/bnx2fc/bnx2fc_io.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/bnx2fc/bnx2fc_io.c b/drivers/scsi/bnx2fc/bnx2fc_io.c index 350257c13a5b..bc9f2a2365f4 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_io.c +++ b/drivers/scsi/bnx2fc/bnx2fc_io.c @@ -240,6 +240,7 @@ struct bnx2fc_cmd_mgr *bnx2fc_cmd_mgr_alloc(struct bnx2fc_hba *hba) return NULL; } + cmgr->hba = hba; cmgr->free_list = kcalloc(arr_sz, sizeof(*cmgr->free_list), GFP_KERNEL); if (!cmgr->free_list) { @@ -256,7 +257,6 @@ struct bnx2fc_cmd_mgr *bnx2fc_cmd_mgr_alloc(struct bnx2fc_hba *hba) goto mem_err; } - cmgr->hba = hba; cmgr->cmds = (struct bnx2fc_cmd **)(cmgr + 1); for (i = 0; i < arr_sz; i++) { @@ -295,7 +295,7 @@ struct bnx2fc_cmd_mgr *bnx2fc_cmd_mgr_alloc(struct bnx2fc_hba *hba) /* Allocate pool of io_bdts - one for each bnx2fc_cmd */ mem_size = num_ios * sizeof(struct io_bdt *); - cmgr->io_bdt_pool = kmalloc(mem_size, GFP_KERNEL); + cmgr->io_bdt_pool = kzalloc(mem_size, GFP_KERNEL); if (!cmgr->io_bdt_pool) { printk(KERN_ERR PFX "failed to alloc io_bdt_pool\n"); goto mem_err; From 8437fcf14deed67e5ad90b5e8abf62fb20f30881 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 24 Jan 2019 13:33:27 +0300 Subject: [PATCH 191/525] scsi: 53c700: pass correct "dev" to dma_alloc_attrs() The "hostdata->dev" pointer is NULL here. We set "hostdata->dev = dev;" later in the function and we also use "hostdata->dev" when we call dma_free_attrs() in NCR_700_release(). This bug predates git version control. Signed-off-by: Dan Carpenter Signed-off-by: Martin K. Petersen --- drivers/scsi/53c700.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c index 128d658d472a..16957d7ac414 100644 --- a/drivers/scsi/53c700.c +++ b/drivers/scsi/53c700.c @@ -295,7 +295,7 @@ NCR_700_detect(struct scsi_host_template *tpnt, if(tpnt->sdev_attrs == NULL) tpnt->sdev_attrs = NCR_700_dev_attrs; - memory = dma_alloc_attrs(hostdata->dev, TOTAL_MEM_SIZE, &pScript, + memory = dma_alloc_attrs(dev, TOTAL_MEM_SIZE, &pScript, GFP_KERNEL, DMA_ATTR_NON_CONSISTENT); if(memory == NULL) { printk(KERN_ERR "53c700: Failed to allocate memory for driver, detaching\n"); From b46a0bf78ad7b150ef5910da83859f7f5a514ffd Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Mon, 28 Jan 2019 15:05:05 +0800 Subject: [PATCH 192/525] vhost: fix OOB in get_rx_bufs() After batched used ring updating was introduced in commit e2b3b35eb989 ("vhost_net: batch used ring update in rx"). We tend to batch heads in vq->heads for more than one packet. But the quota passed to get_rx_bufs() was not correctly limited, which can result a OOB write in vq->heads. headcount = get_rx_bufs(vq, vq->heads + nvq->done_idx, vhost_len, &in, vq_log, &log, likely(mergeable) ? UIO_MAXIOV : 1); UIO_MAXIOV was still used which is wrong since we could have batched used in vq->heads, this will cause OOB if the next buffer needs more than 960 (1024 (UIO_MAXIOV) - 64 (VHOST_NET_BATCH)) heads after we've batched 64 (VHOST_NET_BATCH) heads: Acked-by: Stefan Hajnoczi ============================================================================= BUG kmalloc-8k (Tainted: G B ): Redzone overwritten ----------------------------------------------------------------------------- INFO: 0x00000000fd93b7a2-0x00000000f0713384. First byte 0xa9 instead of 0xcc INFO: Allocated in alloc_pd+0x22/0x60 age=3933677 cpu=2 pid=2674 kmem_cache_alloc_trace+0xbb/0x140 alloc_pd+0x22/0x60 gen8_ppgtt_create+0x11d/0x5f0 i915_ppgtt_create+0x16/0x80 i915_gem_create_context+0x248/0x390 i915_gem_context_create_ioctl+0x4b/0xe0 drm_ioctl_kernel+0xa5/0xf0 drm_ioctl+0x2ed/0x3a0 do_vfs_ioctl+0x9f/0x620 ksys_ioctl+0x6b/0x80 __x64_sys_ioctl+0x11/0x20 do_syscall_64+0x43/0xf0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 INFO: Slab 0x00000000d13e87af objects=3 used=3 fp=0x (null) flags=0x200000000010201 INFO: Object 0x0000000003278802 @offset=17064 fp=0x00000000e2e6652b Fixing this by allocating UIO_MAXIOV + VHOST_NET_BATCH iovs for vhost-net. This is done through set the limitation through vhost_dev_init(), then set_owner can allocate the number of iov in a per device manner. This fixes CVE-2018-16880. Fixes: e2b3b35eb989 ("vhost_net: batch used ring update in rx") Signed-off-by: Jason Wang Signed-off-by: David S. Miller --- drivers/vhost/net.c | 3 ++- drivers/vhost/scsi.c | 2 +- drivers/vhost/vhost.c | 7 ++++--- drivers/vhost/vhost.h | 4 +++- drivers/vhost/vsock.c | 2 +- 5 files changed, 11 insertions(+), 7 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index bca86bf7189f..df51a35cf537 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1337,7 +1337,8 @@ static int vhost_net_open(struct inode *inode, struct file *f) n->vqs[i].rx_ring = NULL; vhost_net_buf_init(&n->vqs[i].rxq); } - vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX); + vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX, + UIO_MAXIOV + VHOST_NET_BATCH); vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, EPOLLOUT, dev); vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, EPOLLIN, dev); diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 344684f3e2e4..23593cb23dd0 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -1627,7 +1627,7 @@ static int vhost_scsi_open(struct inode *inode, struct file *f) vqs[i] = &vs->vqs[i].vq; vs->vqs[i].vq.handle_kick = vhost_scsi_handle_kick; } - vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ); + vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ, UIO_MAXIOV); vhost_scsi_init_inflight(vs, NULL); diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 15a216cdd507..24a129fcdd61 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -390,9 +390,9 @@ static long vhost_dev_alloc_iovecs(struct vhost_dev *dev) vq->indirect = kmalloc_array(UIO_MAXIOV, sizeof(*vq->indirect), GFP_KERNEL); - vq->log = kmalloc_array(UIO_MAXIOV, sizeof(*vq->log), + vq->log = kmalloc_array(dev->iov_limit, sizeof(*vq->log), GFP_KERNEL); - vq->heads = kmalloc_array(UIO_MAXIOV, sizeof(*vq->heads), + vq->heads = kmalloc_array(dev->iov_limit, sizeof(*vq->heads), GFP_KERNEL); if (!vq->indirect || !vq->log || !vq->heads) goto err_nomem; @@ -414,7 +414,7 @@ static void vhost_dev_free_iovecs(struct vhost_dev *dev) } void vhost_dev_init(struct vhost_dev *dev, - struct vhost_virtqueue **vqs, int nvqs) + struct vhost_virtqueue **vqs, int nvqs, int iov_limit) { struct vhost_virtqueue *vq; int i; @@ -427,6 +427,7 @@ void vhost_dev_init(struct vhost_dev *dev, dev->iotlb = NULL; dev->mm = NULL; dev->worker = NULL; + dev->iov_limit = iov_limit; init_llist_head(&dev->work_list); init_waitqueue_head(&dev->wait); INIT_LIST_HEAD(&dev->read_list); diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index 1b675dad5e05..9490e7ddb340 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -170,9 +170,11 @@ struct vhost_dev { struct list_head read_list; struct list_head pending_list; wait_queue_head_t wait; + int iov_limit; }; -void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs, int nvqs); +void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs, + int nvqs, int iov_limit); long vhost_dev_set_owner(struct vhost_dev *dev); bool vhost_dev_has_owner(struct vhost_dev *dev); long vhost_dev_check_owner(struct vhost_dev *); diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 3fbc068eaa9b..bb5fc0e9fbc2 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -531,7 +531,7 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file) vsock->vqs[VSOCK_VQ_TX].handle_kick = vhost_vsock_handle_tx_kick; vsock->vqs[VSOCK_VQ_RX].handle_kick = vhost_vsock_handle_rx_kick; - vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs)); + vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs), UIO_MAXIOV); file->private_data = vsock; spin_lock_init(&vsock->send_pkt_list_lock); From 32eb67b93c9e3cd62cb423e30b090cdd4aa8d275 Mon Sep 17 00:00:00 2001 From: Dave Watson Date: Sun, 27 Jan 2019 00:57:38 +0000 Subject: [PATCH 193/525] net: tls: Save iv in tls_rec for async crypto requests aead_request_set_crypt takes an iv pointer, and we change the iv soon after setting it. Some async crypto algorithms don't save the iv, so we need to save it in the tls_rec for async requests. Found by hardcoding x64 aesni to use async crypto manager (to test the async codepath), however I don't think this combination can happen in the wild. Presumably other hardware offloads will need this fix, but there have been no user reports. Fixes: a42055e8d2c30 ("Add support for async encryption of records...") Signed-off-by: Dave Watson Signed-off-by: David S. Miller --- include/net/tls.h | 2 ++ net/tls/tls_sw.c | 4 +++- 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/include/net/tls.h b/include/net/tls.h index 2a6ac8d642af..1486b60c4de8 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -120,6 +120,8 @@ struct tls_rec { struct scatterlist sg_aead_out[2]; char aad_space[TLS_AAD_SPACE_SIZE]; + u8 iv_data[TLS_CIPHER_AES_GCM_128_IV_SIZE + + TLS_CIPHER_AES_GCM_128_SALT_SIZE]; struct aead_request aead_req; u8 aead_req_ctx[]; }; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 11cdc8f7db63..7e963560edef 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -439,6 +439,8 @@ static int tls_do_encryption(struct sock *sk, struct scatterlist *sge = sk_msg_elem(msg_en, start); int rc; + memcpy(rec->iv_data, tls_ctx->tx.iv, sizeof(rec->iv_data)); + sge->offset += tls_ctx->tx.prepend_size; sge->length -= tls_ctx->tx.prepend_size; @@ -448,7 +450,7 @@ static int tls_do_encryption(struct sock *sk, aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE); aead_request_set_crypt(aead_req, rec->sg_aead_in, rec->sg_aead_out, - data_len, tls_ctx->tx.iv); + data_len, rec->iv_data); aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG, tls_encrypt_done, sk); From 1023121375c6b0b3dc00334983c762ba2b76cb19 Mon Sep 17 00:00:00 2001 From: Dave Watson Date: Sun, 27 Jan 2019 00:59:03 +0000 Subject: [PATCH 194/525] net: tls: Fix deadlock in free_resources tx If there are outstanding async tx requests (when crypto returns EINPROGRESS), there is a potential deadlock: the tx work acquires the lock, while we cancel_delayed_work_sync() while holding the lock. Drop the lock while waiting for the work to complete. Fixes: a42055e8d2c30 ("Add support for async encryption of records...") Signed-off-by: Dave Watson Signed-off-by: David S. Miller --- net/tls/tls_sw.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 7e963560edef..bf5b54b513bc 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1794,7 +1794,9 @@ void tls_sw_free_resources_tx(struct sock *sk) if (atomic_read(&ctx->encrypt_pending)) crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + release_sock(sk); cancel_delayed_work_sync(&ctx->tx_work.work); + lock_sock(sk); /* Tx whatever records we can transmit and abandon the rest */ tls_tx_records(sk, -1); From f48af114895b2f9cdc218ed75666ade83380255b Mon Sep 17 00:00:00 2001 From: Yang Wei Date: Sun, 27 Jan 2019 23:56:34 +0800 Subject: [PATCH 195/525] net: alteon: replace dev_kfree_skb_irq by dev_consume_skb_irq dev_consume_skb_irq() should be called in ace_tx_int() when xmit done. It makes drop profiles more friendly. Signed-off-by: Yang Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/alteon/acenic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c index 4f11f98347ed..1827ef1f6d55 100644 --- a/drivers/net/ethernet/alteon/acenic.c +++ b/drivers/net/ethernet/alteon/acenic.c @@ -2059,7 +2059,7 @@ static inline void ace_tx_int(struct net_device *dev, if (skb) { dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); info->skb = NULL; } From 3afa73dd7c8b586d9d01a96063d537e1550d1287 Mon Sep 17 00:00:00 2001 From: Yang Wei Date: Sun, 27 Jan 2019 23:58:25 +0800 Subject: [PATCH 196/525] net: amd8111e: replace dev_kfree_skb_irq by dev_consume_skb_irq dev_consume_skb_irq() should be called in amd8111e_tx() when xmit done. It makes drop profiles more friendly. Signed-off-by: Yang Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/amd/amd8111e.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c index a90080f12e67..e548c0ae2e00 100644 --- a/drivers/net/ethernet/amd/amd8111e.c +++ b/drivers/net/ethernet/amd/amd8111e.c @@ -666,7 +666,7 @@ static int amd8111e_tx(struct net_device *dev) pci_unmap_single(lp->pci_dev, lp->tx_dma_addr[tx_index], lp->tx_skbuff[tx_index]->len, PCI_DMA_TODEVICE); - dev_kfree_skb_irq (lp->tx_skbuff[tx_index]); + dev_consume_skb_irq(lp->tx_skbuff[tx_index]); lp->tx_skbuff[tx_index] = NULL; lp->tx_dma_addr[tx_index] = 0; } From 100091156c1a4da11c0764265b9e328d7858f2bb Mon Sep 17 00:00:00 2001 From: Yang Wei Date: Tue, 29 Jan 2019 07:39:13 +0800 Subject: [PATCH 197/525] net: apple: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles dev_consume_skb_irq() should be called in bmac_txdma_intr() when xmit done. It makes drop profiles more friendly. Signed-off-by: Yang Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/apple/bmac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c index 6a8e2567f2bd..4d3855ceb500 100644 --- a/drivers/net/ethernet/apple/bmac.c +++ b/drivers/net/ethernet/apple/bmac.c @@ -777,7 +777,7 @@ static irqreturn_t bmac_txdma_intr(int irq, void *dev_id) if (bp->tx_bufs[bp->tx_empty]) { ++dev->stats.tx_packets; - dev_kfree_skb_irq(bp->tx_bufs[bp->tx_empty]); + dev_consume_skb_irq(bp->tx_bufs[bp->tx_empty]); } bp->tx_bufs[bp->tx_empty] = NULL; bp->tx_fullup = 0; From b3379a424dde97755ad7a6f4405648a9ea13d6e3 Mon Sep 17 00:00:00 2001 From: Yang Wei Date: Tue, 29 Jan 2019 07:40:10 +0800 Subject: [PATCH 198/525] net: ti: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles dev_consume_skb_irq() should be called in cpmac_end_xmit() when xmit done. It makes drop profiles more friendly. Signed-off-by: Yang Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/ti/cpmac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ti/cpmac.c b/drivers/net/ethernet/ti/cpmac.c index 810dfc7de1f9..e2d47b24a869 100644 --- a/drivers/net/ethernet/ti/cpmac.c +++ b/drivers/net/ethernet/ti/cpmac.c @@ -608,7 +608,7 @@ static void cpmac_end_xmit(struct net_device *dev, int queue) netdev_dbg(dev, "sent 0x%p, len=%d\n", desc->skb, desc->skb->len); - dev_kfree_skb_irq(desc->skb); + dev_consume_skb_irq(desc->skb); desc->skb = NULL; if (__netif_subqueue_stopped(dev, queue)) netif_wake_subqueue(dev, queue); From 9baddb61dfec0215da5d10a1d173790443e276c2 Mon Sep 17 00:00:00 2001 From: Sinan Kaya Date: Mon, 21 Jan 2019 23:19:57 +0000 Subject: [PATCH 199/525] mfd: Fix unmet dependency warning for MFD_TPS68470 After commit 5d32a66541c4 ("PCI/ACPI: Allow ACPI to be built without CONFIG_PCI set") dependencies on CONFIG_PCI that previously were satisfied implicitly through dependencies on CONFIG_ACPI have to be specified directly. WARNING: unmet direct dependencies detected for I2C_DESIGNWARE_PLATFORM Depends on [n]: I2C [=y] && HAS_IOMEM [=y] && (ACPI [=y] && COMMON_CLK [=n] || !ACPI [=y]) Selected by [y]: - MFD_TPS68470 [=y] && HAS_IOMEM [=y] && ACPI [=y] && I2C [=y]=y MFD_TPS68470 is an ACPI only device and selects I2C_DESIGNWARE_PLATFORM. I2C_DESIGNWARE_PLATFORM does not have any configuration today for ACPI support without CONFIG_PCI set. For sake of a quick fix this introduces a new mandatory dependency to the driver which may survive without it. Otherwise we need to revisit the driver architecture to address this properly. Fixes: 5d32a66541c46 ("PCI/ACPI: Allow ACPI to be built without CONFIG_PCI set") Signed-off-by: Sinan Kaya Acked-by: Lee Jones Signed-off-by: Rafael J. Wysocki --- drivers/mfd/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index f461460a2aeb..76f9909cf396 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -1419,7 +1419,7 @@ config MFD_TPS65217 config MFD_TPS68470 bool "TI TPS68470 Power Management / LED chips" - depends on ACPI && I2C=y + depends on ACPI && PCI && I2C=y select MFD_CORE select REGMAP_I2C select I2C_DESIGNWARE_PLATFORM From d58bf90a32a33becec78c3034e781735049fcd25 Mon Sep 17 00:00:00 2001 From: Sinan Kaya Date: Thu, 24 Jan 2019 19:31:00 +0000 Subject: [PATCH 200/525] platform/x86: Fix unmet dependency warning for ACPI_CMPC Add BACKLIGHT_LCD_SUPPORT for ACPI_CMPC to fix the warning: unmet direct dependencies detected for BACKLIGHT_CLASS_DEVICE. ACPI_CMPC selects BACKLIGHT_CLASS_DEVICE but BACKLIGHT_CLASS_DEVICE depends on BACKLIGHT_LCD_SUPPORT. Copy BACKLIGHT_LCD_SUPPORT dependency into ACPI_CMPC to fix WARNING: unmet direct dependencies detected for BACKLIGHT_CLASS_DEVICE Depends on [n]: HAS_IOMEM [=y] && BACKLIGHT_LCD_SUPPORT [=n] Selected by [y]: - ACPI_CMPC [=y] && X86 [=y] && X86_PLATFORM_DEVICES [=y] && ACPI [=y] && INPUT [=y] && (RFKILL [=n] || RFKILL [=n]=n) Signed-off-by: Sinan Kaya Acked-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- drivers/platform/x86/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 5e2109c54c7c..11810591840d 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -905,6 +905,7 @@ config TOSHIBA_WMI config ACPI_CMPC tristate "CMPC Laptop Extras" depends on ACPI && INPUT + depends on BACKLIGHT_LCD_SUPPORT depends on RFKILL || RFKILL=n select BACKLIGHT_CLASS_DEVICE help From 0ee4b5f801b73b83a9fb3921d725f2162fd4a2e5 Mon Sep 17 00:00:00 2001 From: Sinan Kaya Date: Thu, 24 Jan 2019 19:31:01 +0000 Subject: [PATCH 201/525] platform/x86: Fix unmet dependency warning for SAMSUNG_Q10 Add BACKLIGHT_LCD_SUPPORT for SAMSUNG_Q10 to fix the warning: unmet direct dependencies detected for BACKLIGHT_CLASS_DEVICE. SAMSUNG_Q10 selects BACKLIGHT_CLASS_DEVICE but BACKLIGHT_CLASS_DEVICE depends on BACKLIGHT_LCD_SUPPORT. Copy BACKLIGHT_LCD_SUPPORT dependency into SAMSUNG_Q10 to fix: WARNING: unmet direct dependencies detected for BACKLIGHT_CLASS_DEVICE Depends on [n]: HAS_IOMEM [=y] && BACKLIGHT_LCD_SUPPORT [=n] Selected by [y]: - SAMSUNG_Q10 [=y] && X86 [=y] && X86_PLATFORM_DEVICES [=y] && ACPI [=y] Signed-off-by: Sinan Kaya Acked-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- drivers/platform/x86/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 11810591840d..b5e9db85e881 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -1129,6 +1129,7 @@ config INTEL_OAKTRAIL config SAMSUNG_Q10 tristate "Samsung Q10 Extras" depends on ACPI + depends on BACKLIGHT_LCD_SUPPORT select BACKLIGHT_CLASS_DEVICE ---help--- This driver provides support for backlight control on Samsung Q10 From 13054abbaa4f1fd4e6f3b4b63439ec033b4c8035 Mon Sep 17 00:00:00 2001 From: Vladis Dronov Date: Tue, 29 Jan 2019 11:58:35 +0100 Subject: [PATCH 202/525] HID: debug: fix the ring buffer implementation Ring buffer implementation in hid_debug_event() and hid_debug_events_read() is strange allowing lost or corrupted data. After commit 717adfdaf147 ("HID: debug: check length before copy_to_user()") it is possible to enter an infinite loop in hid_debug_events_read() by providing 0 as count, this locks up a system. Fix this by rewriting the ring buffer implementation with kfifo and simplify the code. This fixes CVE-2019-3819. v2: fix an execution logic and add a comment v3: use __set_current_state() instead of set_current_state() Link: https://bugzilla.redhat.com/show_bug.cgi?id=1669187 Cc: stable@vger.kernel.org # v4.18+ Fixes: cd667ce24796 ("HID: use debugfs for events/reports dumping") Fixes: 717adfdaf147 ("HID: debug: check length before copy_to_user()") Signed-off-by: Vladis Dronov Reviewed-by: Oleg Nesterov Signed-off-by: Benjamin Tissoires --- drivers/hid/hid-debug.c | 122 +++++++++++++++----------------------- include/linux/hid-debug.h | 9 ++- 2 files changed, 52 insertions(+), 79 deletions(-) diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c index c530476edba6..ac9fda1b5a72 100644 --- a/drivers/hid/hid-debug.c +++ b/drivers/hid/hid-debug.c @@ -30,6 +30,7 @@ #include #include +#include #include #include #include @@ -661,17 +662,12 @@ EXPORT_SYMBOL_GPL(hid_dump_device); /* enqueue string to 'events' ring buffer */ void hid_debug_event(struct hid_device *hdev, char *buf) { - unsigned i; struct hid_debug_list *list; unsigned long flags; spin_lock_irqsave(&hdev->debug_list_lock, flags); - list_for_each_entry(list, &hdev->debug_list, node) { - for (i = 0; buf[i]; i++) - list->hid_debug_buf[(list->tail + i) % HID_DEBUG_BUFSIZE] = - buf[i]; - list->tail = (list->tail + i) % HID_DEBUG_BUFSIZE; - } + list_for_each_entry(list, &hdev->debug_list, node) + kfifo_in(&list->hid_debug_fifo, buf, strlen(buf)); spin_unlock_irqrestore(&hdev->debug_list_lock, flags); wake_up_interruptible(&hdev->debug_wait); @@ -722,8 +718,7 @@ void hid_dump_input(struct hid_device *hdev, struct hid_usage *usage, __s32 valu hid_debug_event(hdev, buf); kfree(buf); - wake_up_interruptible(&hdev->debug_wait); - + wake_up_interruptible(&hdev->debug_wait); } EXPORT_SYMBOL_GPL(hid_dump_input); @@ -1083,8 +1078,8 @@ static int hid_debug_events_open(struct inode *inode, struct file *file) goto out; } - if (!(list->hid_debug_buf = kzalloc(HID_DEBUG_BUFSIZE, GFP_KERNEL))) { - err = -ENOMEM; + err = kfifo_alloc(&list->hid_debug_fifo, HID_DEBUG_FIFOSIZE, GFP_KERNEL); + if (err) { kfree(list); goto out; } @@ -1104,77 +1099,57 @@ static ssize_t hid_debug_events_read(struct file *file, char __user *buffer, size_t count, loff_t *ppos) { struct hid_debug_list *list = file->private_data; - int ret = 0, len; + int ret = 0, copied; DECLARE_WAITQUEUE(wait, current); mutex_lock(&list->read_mutex); - while (ret == 0) { - if (list->head == list->tail) { - add_wait_queue(&list->hdev->debug_wait, &wait); - set_current_state(TASK_INTERRUPTIBLE); + if (kfifo_is_empty(&list->hid_debug_fifo)) { + add_wait_queue(&list->hdev->debug_wait, &wait); + set_current_state(TASK_INTERRUPTIBLE); - while (list->head == list->tail) { - if (file->f_flags & O_NONBLOCK) { - ret = -EAGAIN; - break; - } - if (signal_pending(current)) { - ret = -ERESTARTSYS; - break; - } - - if (!list->hdev || !list->hdev->debug) { - ret = -EIO; - set_current_state(TASK_RUNNING); - goto out; - } - - /* allow O_NONBLOCK from other threads */ - mutex_unlock(&list->read_mutex); - schedule(); - mutex_lock(&list->read_mutex); - set_current_state(TASK_INTERRUPTIBLE); + while (kfifo_is_empty(&list->hid_debug_fifo)) { + if (file->f_flags & O_NONBLOCK) { + ret = -EAGAIN; + break; } - set_current_state(TASK_RUNNING); - remove_wait_queue(&list->hdev->debug_wait, &wait); + if (signal_pending(current)) { + ret = -ERESTARTSYS; + break; + } + + /* if list->hdev is NULL we cannot remove_wait_queue(). + * if list->hdev->debug is 0 then hid_debug_unregister() + * was already called and list->hdev is being destroyed. + * if we add remove_wait_queue() here we can hit a race. + */ + if (!list->hdev || !list->hdev->debug) { + ret = -EIO; + set_current_state(TASK_RUNNING); + goto out; + } + + /* allow O_NONBLOCK from other threads */ + mutex_unlock(&list->read_mutex); + schedule(); + mutex_lock(&list->read_mutex); + set_current_state(TASK_INTERRUPTIBLE); } + __set_current_state(TASK_RUNNING); + remove_wait_queue(&list->hdev->debug_wait, &wait); + if (ret) goto out; - - /* pass the ringbuffer contents to userspace */ -copy_rest: - if (list->tail == list->head) - goto out; - if (list->tail > list->head) { - len = list->tail - list->head; - if (len > count) - len = count; - - if (copy_to_user(buffer + ret, &list->hid_debug_buf[list->head], len)) { - ret = -EFAULT; - goto out; - } - ret += len; - list->head += len; - } else { - len = HID_DEBUG_BUFSIZE - list->head; - if (len > count) - len = count; - - if (copy_to_user(buffer, &list->hid_debug_buf[list->head], len)) { - ret = -EFAULT; - goto out; - } - list->head = 0; - ret += len; - count -= len; - if (count > 0) - goto copy_rest; - } - } + + /* pass the fifo content to userspace, locking is not needed with only + * one concurrent reader and one concurrent writer + */ + ret = kfifo_to_user(&list->hid_debug_fifo, buffer, count, &copied); + if (ret) + goto out; + ret = copied; out: mutex_unlock(&list->read_mutex); return ret; @@ -1185,7 +1160,7 @@ static __poll_t hid_debug_events_poll(struct file *file, poll_table *wait) struct hid_debug_list *list = file->private_data; poll_wait(file, &list->hdev->debug_wait, wait); - if (list->head != list->tail) + if (!kfifo_is_empty(&list->hid_debug_fifo)) return EPOLLIN | EPOLLRDNORM; if (!list->hdev->debug) return EPOLLERR | EPOLLHUP; @@ -1200,7 +1175,7 @@ static int hid_debug_events_release(struct inode *inode, struct file *file) spin_lock_irqsave(&list->hdev->debug_list_lock, flags); list_del(&list->node); spin_unlock_irqrestore(&list->hdev->debug_list_lock, flags); - kfree(list->hid_debug_buf); + kfifo_free(&list->hid_debug_fifo); kfree(list); return 0; @@ -1246,4 +1221,3 @@ void hid_debug_exit(void) { debugfs_remove_recursive(hid_debug_root); } - diff --git a/include/linux/hid-debug.h b/include/linux/hid-debug.h index 8663f216c563..2d6100edf204 100644 --- a/include/linux/hid-debug.h +++ b/include/linux/hid-debug.h @@ -24,7 +24,10 @@ #ifdef CONFIG_DEBUG_FS +#include + #define HID_DEBUG_BUFSIZE 512 +#define HID_DEBUG_FIFOSIZE 512 void hid_dump_input(struct hid_device *, struct hid_usage *, __s32); void hid_dump_report(struct hid_device *, int , u8 *, int); @@ -37,11 +40,8 @@ void hid_debug_init(void); void hid_debug_exit(void); void hid_debug_event(struct hid_device *, char *); - struct hid_debug_list { - char *hid_debug_buf; - int head; - int tail; + DECLARE_KFIFO_PTR(hid_debug_fifo, char); struct fasync_struct *fasync; struct hid_device *hdev; struct list_head node; @@ -64,4 +64,3 @@ struct hid_debug_list { #endif #endif - From 3f47d00bc65ba11b3e5753d733a74ca4f7af3240 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 5 Jan 2019 09:01:05 +0100 Subject: [PATCH 203/525] drm/vmwgfx: remove CONFIG_X86 ifdefs The driver depends on CONFIG_X86 so these are dead code. Signed-off-by: Christoph Hellwig Reviewed-by: Thomas Hellstrom Signed-off-by: Thomas Hellstrom --- drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 25afb1d594e3..69e325b2d954 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -565,7 +565,6 @@ static int vmw_dma_select_mode(struct vmw_private *dev_priv) [vmw_dma_alloc_coherent] = "Using coherent TTM pages.", [vmw_dma_map_populate] = "Keeping DMA mappings.", [vmw_dma_map_bind] = "Giving up DMA mappings early."}; -#ifdef CONFIG_X86 const struct dma_map_ops *dma_ops = get_dma_ops(dev_priv->dev->dev); #ifdef CONFIG_INTEL_IOMMU @@ -607,11 +606,6 @@ out_fixup: if (dev_priv->map_mode == vmw_dma_alloc_coherent) return -EINVAL; #endif - -#else /* CONFIG_X86 */ - dev_priv->map_mode = vmw_dma_map_populate; -#endif /* CONFIG_X86 */ - DRM_INFO("DMA map mode: %s\n", names[dev_priv->map_mode]); return 0; From 9b5bf2421b43ef85568f9b875d6387a114e92efe Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 5 Jan 2019 09:01:06 +0100 Subject: [PATCH 204/525] drm/vmwgfx: remove CONFIG_INTEL_IOMMU ifdefs v2 intel_iommu_enabled is defined as always false for !CONFIG_INTEL_IOMMU, so remove the ifdefs around it. Signed-off-by: Christoph Hellwig Reviewed-by: Thomas Hellstrom Signed-off-by: Thomas Hellstrom --- drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 21 ++++----------------- 1 file changed, 4 insertions(+), 17 deletions(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 69e325b2d954..b7777b5b4a81 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -567,12 +567,10 @@ static int vmw_dma_select_mode(struct vmw_private *dev_priv) [vmw_dma_map_bind] = "Giving up DMA mappings early."}; const struct dma_map_ops *dma_ops = get_dma_ops(dev_priv->dev->dev); -#ifdef CONFIG_INTEL_IOMMU if (intel_iommu_enabled) { dev_priv->map_mode = vmw_dma_map_populate; goto out_fixup; } -#endif if (!(vmw_force_iommu || vmw_force_coherent)) { dev_priv->map_mode = vmw_dma_phys; @@ -589,9 +587,7 @@ static int vmw_dma_select_mode(struct vmw_private *dev_priv) dev_priv->map_mode = vmw_dma_map_populate; #endif -#ifdef CONFIG_INTEL_IOMMU out_fixup: -#endif if (dev_priv->map_mode == vmw_dma_map_populate && vmw_restrict_iommu) dev_priv->map_mode = vmw_dma_map_bind; @@ -599,13 +595,11 @@ out_fixup: if (vmw_force_coherent) dev_priv->map_mode = vmw_dma_alloc_coherent; -#if !defined(CONFIG_SWIOTLB) && !defined(CONFIG_INTEL_IOMMU) - /* - * No coherent page pool - */ - if (dev_priv->map_mode == vmw_dma_alloc_coherent) + /* No TTM coherent page pool? FIXME: Ask TTM instead! */ + if (!(IS_ENABLED(CONFIG_SWIOTLB) || IS_ENABLED(CONFIG_INTEL_IOMMU)) && + (dev_priv->map_mode == vmw_dma_alloc_coherent)) return -EINVAL; -#endif + DRM_INFO("DMA map mode: %s\n", names[dev_priv->map_mode]); return 0; @@ -619,7 +613,6 @@ out_fixup: * With 32-bit we can only handle 32 bit PFNs. Optionally set that * restriction also for 64-bit systems. */ -#ifdef CONFIG_INTEL_IOMMU static int vmw_dma_masks(struct vmw_private *dev_priv) { struct drm_device *dev = dev_priv->dev; @@ -631,12 +624,6 @@ static int vmw_dma_masks(struct vmw_private *dev_priv) } return 0; } -#else -static int vmw_dma_masks(struct vmw_private *dev_priv) -{ - return 0; -} -#endif static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) { From 2b3cd6249b14e25da14f13cd520eb336230a4422 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 5 Jan 2019 09:01:07 +0100 Subject: [PATCH 205/525] drm/vmwgfx: fix the check when to use dma_alloc_coherent Since Linux 4.21 we merged the swiotlb ops into the DMA direct ops, so they would always have a the sync_single methods. But late in the cicle we also removed the direct ops entirely, so we'd see NULL DMA ops. Switch vmw_dma_select_mode to only detect swiotlb presence using swiotlb_nr_tbl() instead. Fixes: 55897af630 ("dma-direct: merge swiotlb_dma_ops into the dma_direct code") Fixes: 356da6d0cd ("dma-mapping: bypass indirect calls for dma-direct") Signed-off-by: Christoph Hellwig Reviewed-by: Thomas Hellstrom Signed-off-by: Thomas Hellstrom --- drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index b7777b5b4a81..1456101e67a9 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -565,7 +565,6 @@ static int vmw_dma_select_mode(struct vmw_private *dev_priv) [vmw_dma_alloc_coherent] = "Using coherent TTM pages.", [vmw_dma_map_populate] = "Keeping DMA mappings.", [vmw_dma_map_bind] = "Giving up DMA mappings early."}; - const struct dma_map_ops *dma_ops = get_dma_ops(dev_priv->dev->dev); if (intel_iommu_enabled) { dev_priv->map_mode = vmw_dma_map_populate; @@ -578,14 +577,12 @@ static int vmw_dma_select_mode(struct vmw_private *dev_priv) return 0; } - dev_priv->map_mode = vmw_dma_map_populate; - - if (dma_ops && dma_ops->sync_single_for_cpu) - dev_priv->map_mode = vmw_dma_alloc_coherent; #ifdef CONFIG_SWIOTLB - if (swiotlb_nr_tbl() == 0) - dev_priv->map_mode = vmw_dma_map_populate; + if (swiotlb_nr_tbl()) + dev_priv->map_mode = vmw_dma_alloc_coherent; + else #endif + dev_priv->map_mode = vmw_dma_map_populate; out_fixup: if (dev_priv->map_mode == vmw_dma_map_populate && From 05f9467e70ed7c9cd19fd3d42346941cdc03eef3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 5 Jan 2019 09:01:08 +0100 Subject: [PATCH 206/525] drm/vmwgfx: unwind spaghetti code in vmw_dma_select_mode Just use a simple if/else chain to select the DMA mode. Signed-off-by: Christoph Hellwig Reviewed-by: Thomas Hellstrom Signed-off-by: Thomas Hellstrom --- drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 35 +++++++++-------------------- 1 file changed, 11 insertions(+), 24 deletions(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 1456101e67a9..3e2bcff34032 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -566,31 +566,19 @@ static int vmw_dma_select_mode(struct vmw_private *dev_priv) [vmw_dma_map_populate] = "Keeping DMA mappings.", [vmw_dma_map_bind] = "Giving up DMA mappings early."}; - if (intel_iommu_enabled) { - dev_priv->map_mode = vmw_dma_map_populate; - goto out_fixup; - } - - if (!(vmw_force_iommu || vmw_force_coherent)) { - dev_priv->map_mode = vmw_dma_phys; - DRM_INFO("DMA map mode: %s\n", names[dev_priv->map_mode]); - return 0; - } - -#ifdef CONFIG_SWIOTLB - if (swiotlb_nr_tbl()) - dev_priv->map_mode = vmw_dma_alloc_coherent; - else -#endif - dev_priv->map_mode = vmw_dma_map_populate; - -out_fixup: - if (dev_priv->map_mode == vmw_dma_map_populate && - vmw_restrict_iommu) - dev_priv->map_mode = vmw_dma_map_bind; - if (vmw_force_coherent) dev_priv->map_mode = vmw_dma_alloc_coherent; + else if (intel_iommu_enabled) + dev_priv->map_mode = vmw_dma_map_populate; + else if (!vmw_force_iommu) + dev_priv->map_mode = vmw_dma_phys; + else if (IS_ENABLED(CONFIG_SWIOTLB) && swiotlb_nr_tbl()) + dev_priv->map_mode = vmw_dma_alloc_coherent; + else + dev_priv->map_mode = vmw_dma_map_populate; + + if (dev_priv->map_mode == vmw_dma_map_populate && vmw_restrict_iommu) + dev_priv->map_mode = vmw_dma_map_bind; /* No TTM coherent page pool? FIXME: Ask TTM instead! */ if (!(IS_ENABLED(CONFIG_SWIOTLB) || IS_ENABLED(CONFIG_INTEL_IOMMU)) && @@ -598,7 +586,6 @@ out_fixup: return -EINVAL; DRM_INFO("DMA map mode: %s\n", names[dev_priv->map_mode]); - return 0; } From 693abe11aa6b27aed6eb8222162f8fb986325cef Mon Sep 17 00:00:00 2001 From: Kailang Yang Date: Tue, 29 Jan 2019 15:38:21 +0800 Subject: [PATCH 207/525] ALSA: hda/realtek - Fixed hp_pin no value Fix hp_pin always no value. [More notes on the changes: The hp_pin value that is referred in alc294_hp_init() is always zero at the moment the function gets called, hence this is actually useless as in the current code. And, this kind of init sequence should be called from the codec init callback, instead of the parser function. So, the first fix in this patch to move the call call into its own init_hook. OTOH, this function is needed to be called only once after the boot, and it'd take too long for invoking at each resume (where the init callback gets called). So we add a new flag and invoke this only once as an additional fix. The one case is still not covered, though: S4 resume. But this change itself won't lead to any regression in that regard, so we leave S4 issue as is for now and fix it later. -- tiwai ] Fixes: bde1a7459623 ("ALSA: hda/realtek - Fixed headphone issue for ALC700") Signed-off-by: Kailang Yang Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 78 ++++++++++++++++++++--------------- 1 file changed, 45 insertions(+), 33 deletions(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index b4f472157ebd..4139aced63f8 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -117,6 +117,7 @@ struct alc_spec { int codec_variant; /* flag for other variants */ unsigned int has_alc5505_dsp:1; unsigned int no_depop_delay:1; + unsigned int done_hp_init:1; /* for PLL fix */ hda_nid_t pll_nid; @@ -3372,6 +3373,48 @@ static void alc_default_shutup(struct hda_codec *codec) snd_hda_shutup_pins(codec); } +static void alc294_hp_init(struct hda_codec *codec) +{ + struct alc_spec *spec = codec->spec; + hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + int i, val; + + if (!hp_pin) + return; + + snd_hda_codec_write(codec, hp_pin, 0, + AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE); + + msleep(100); + + snd_hda_codec_write(codec, hp_pin, 0, + AC_VERB_SET_PIN_WIDGET_CONTROL, 0x0); + + alc_update_coef_idx(codec, 0x6f, 0x000f, 0);/* Set HP depop to manual mode */ + alc_update_coefex_idx(codec, 0x58, 0x00, 0x8000, 0x8000); /* HP depop procedure start */ + + /* Wait for depop procedure finish */ + val = alc_read_coefex_idx(codec, 0x58, 0x01); + for (i = 0; i < 20 && val & 0x0080; i++) { + msleep(50); + val = alc_read_coefex_idx(codec, 0x58, 0x01); + } + /* Set HP depop to auto mode */ + alc_update_coef_idx(codec, 0x6f, 0x000f, 0x000b); + msleep(50); +} + +static void alc294_init(struct hda_codec *codec) +{ + struct alc_spec *spec = codec->spec; + + if (!spec->done_hp_init) { + alc294_hp_init(codec); + spec->done_hp_init = true; + } + alc_default_init(codec); +} + static void alc5505_coef_set(struct hda_codec *codec, unsigned int index_reg, unsigned int val) { @@ -7373,37 +7416,6 @@ static void alc269_fill_coef(struct hda_codec *codec) alc_update_coef_idx(codec, 0x4, 0, 1<<11); } -static void alc294_hp_init(struct hda_codec *codec) -{ - struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; - int i, val; - - if (!hp_pin) - return; - - snd_hda_codec_write(codec, hp_pin, 0, - AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE); - - msleep(100); - - snd_hda_codec_write(codec, hp_pin, 0, - AC_VERB_SET_PIN_WIDGET_CONTROL, 0x0); - - alc_update_coef_idx(codec, 0x6f, 0x000f, 0);/* Set HP depop to manual mode */ - alc_update_coefex_idx(codec, 0x58, 0x00, 0x8000, 0x8000); /* HP depop procedure start */ - - /* Wait for depop procedure finish */ - val = alc_read_coefex_idx(codec, 0x58, 0x01); - for (i = 0; i < 20 && val & 0x0080; i++) { - msleep(50); - val = alc_read_coefex_idx(codec, 0x58, 0x01); - } - /* Set HP depop to auto mode */ - alc_update_coef_idx(codec, 0x6f, 0x000f, 0x000b); - msleep(50); -} - /* */ static int patch_alc269(struct hda_codec *codec) @@ -7529,7 +7541,7 @@ static int patch_alc269(struct hda_codec *codec) spec->codec_variant = ALC269_TYPE_ALC294; spec->gen.mixer_nid = 0; /* ALC2x4 does not have any loopback mixer path */ alc_update_coef_idx(codec, 0x6b, 0x0018, (1<<4) | (1<<3)); /* UAJ MIC Vref control by verb */ - alc294_hp_init(codec); + spec->init_hook = alc294_init; break; case 0x10ec0300: spec->codec_variant = ALC269_TYPE_ALC300; @@ -7541,7 +7553,7 @@ static int patch_alc269(struct hda_codec *codec) spec->codec_variant = ALC269_TYPE_ALC700; spec->gen.mixer_nid = 0; /* ALC700 does not have any loopback mixer path */ alc_update_coef_idx(codec, 0x4a, 1 << 15, 0); /* Combo jack auto trigger control */ - alc294_hp_init(codec); + spec->init_hook = alc294_init; break; } From 00ae831dfe4474ef6029558f5eb3ef0332d80043 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 25 Jan 2019 11:59:01 -0800 Subject: [PATCH 208/525] x86/cpu: Add Atom Tremont (Jacobsville) Add the Atom Tremont model number to the Intel family list. [ Tony: Also update comment at head of file to say "_X" suffix is also used for microserver parts. ] Signed-off-by: Kan Liang Signed-off-by: Qiuxu Zhuo Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov Cc: Andy Shevchenko Cc: Aristeu Rozanski Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: linux-edac Cc: Mauro Carvalho Chehab Cc: Megha Dey Cc: Peter Zijlstra Cc: Qiuxu Zhuo Cc: Rajneesh Bhardwaj Cc: Thomas Gleixner Cc: x86-ml Link: https://lkml.kernel.org/r/20190125195902.17109-4-tony.luck@intel.com --- arch/x86/include/asm/intel-family.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 0dd6b0f4000e..d9a9993af882 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -6,7 +6,7 @@ * "Big Core" Processors (Branded as Core, Xeon, etc...) * * The "_X" parts are generally the EP and EX Xeons, or the - * "Extreme" ones, like Broadwell-E. + * "Extreme" ones, like Broadwell-E, or Atom microserver. * * While adding a new CPUID for a new microarchitecture, add a new * group to keep logically sorted out in chronological order. Within @@ -71,6 +71,7 @@ #define INTEL_FAM6_ATOM_GOLDMONT 0x5C /* Apollo Lake */ #define INTEL_FAM6_ATOM_GOLDMONT_X 0x5F /* Denverton */ #define INTEL_FAM6_ATOM_GOLDMONT_PLUS 0x7A /* Gemini Lake */ +#define INTEL_FAM6_ATOM_TREMONT_X 0x86 /* Jacobsville */ /* Xeon Phi */ From 9791ec7df0e7b4d80706ccea8f24b6542f6059e9 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 29 Jan 2019 10:02:33 +0000 Subject: [PATCH 209/525] irqchip/gic-v3-its: Plug allocation race for devices sharing a DevID On systems or VMs where multiple devices share a single DevID (because they sit behind a PCI bridge, or because the HW is broken in funky ways), we reuse the save its_device structure in order to reflect this. It turns out that there is a distinct lack of locking when looking up the its_device, and two device being probed concurrently can result in double allocations. That's obviously not nice. A solution for this is to have a per-ITS mutex that serializes device allocation. A similar issue exists on the freeing side, which can run concurrently with the allocation. On top of now taking the appropriate lock, we also make sure that a shared device is never freed, as we have no way to currently track the life cycle of such object. Reported-by: Zheng Xiang Tested-by: Zheng Xiang Cc: stable@vger.kernel.org Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-gic-v3-its.c | 32 +++++++++++++++++++++++++++----- 1 file changed, 27 insertions(+), 5 deletions(-) diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 36181197d5e0..f25ec92f23ee 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -97,9 +97,14 @@ struct its_device; * The ITS structure - contains most of the infrastructure, with the * top-level MSI domain, the command queue, the collections, and the * list of devices writing to it. + * + * dev_alloc_lock has to be taken for device allocations, while the + * spinlock must be taken to parse data structures such as the device + * list. */ struct its_node { raw_spinlock_t lock; + struct mutex dev_alloc_lock; struct list_head entry; void __iomem *base; phys_addr_t phys_base; @@ -156,6 +161,7 @@ struct its_device { void *itt; u32 nr_ites; u32 device_id; + bool shared; }; static struct { @@ -2469,6 +2475,7 @@ static int its_msi_prepare(struct irq_domain *domain, struct device *dev, struct its_device *its_dev; struct msi_domain_info *msi_info; u32 dev_id; + int err = 0; /* * We ignore "dev" entierely, and rely on the dev_id that has @@ -2491,6 +2498,7 @@ static int its_msi_prepare(struct irq_domain *domain, struct device *dev, return -EINVAL; } + mutex_lock(&its->dev_alloc_lock); its_dev = its_find_device(its, dev_id); if (its_dev) { /* @@ -2498,18 +2506,22 @@ static int its_msi_prepare(struct irq_domain *domain, struct device *dev, * another alias (PCI bridge of some sort). No need to * create the device. */ + its_dev->shared = true; pr_debug("Reusing ITT for devID %x\n", dev_id); goto out; } its_dev = its_create_device(its, dev_id, nvec, true); - if (!its_dev) - return -ENOMEM; + if (!its_dev) { + err = -ENOMEM; + goto out; + } pr_debug("ITT %d entries, %d bits\n", nvec, ilog2(nvec)); out: + mutex_unlock(&its->dev_alloc_lock); info->scratchpad[0].ptr = its_dev; - return 0; + return err; } static struct msi_domain_ops its_msi_domain_ops = { @@ -2613,6 +2625,7 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq, { struct irq_data *d = irq_domain_get_irq_data(domain, virq); struct its_device *its_dev = irq_data_get_irq_chip_data(d); + struct its_node *its = its_dev->its; int i; for (i = 0; i < nr_irqs; i++) { @@ -2627,8 +2640,14 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq, irq_domain_reset_irq_data(data); } - /* If all interrupts have been freed, start mopping the floor */ - if (bitmap_empty(its_dev->event_map.lpi_map, + mutex_lock(&its->dev_alloc_lock); + + /* + * If all interrupts have been freed, start mopping the + * floor. This is conditionned on the device not being shared. + */ + if (!its_dev->shared && + bitmap_empty(its_dev->event_map.lpi_map, its_dev->event_map.nr_lpis)) { its_lpi_free(its_dev->event_map.lpi_map, its_dev->event_map.lpi_base, @@ -2640,6 +2659,8 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq, its_free_device(its_dev); } + mutex_unlock(&its->dev_alloc_lock); + irq_domain_free_irqs_parent(domain, virq, nr_irqs); } @@ -3549,6 +3570,7 @@ static int __init its_probe_one(struct resource *res, } raw_spin_lock_init(&its->lock); + mutex_init(&its->dev_alloc_lock); INIT_LIST_HEAD(&its->entry); INIT_LIST_HEAD(&its->its_device_list); typer = gic_read_typer(its_base + GITS_TYPER); From 45725e0fc3e7fe52fedb94f59806ec50e9618682 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 29 Jan 2019 15:19:23 +0000 Subject: [PATCH 210/525] irqchip/gic-v3-its: Gracefully fail on LPI exhaustion In the unlikely event that we cannot find any available LPI in the system, we should gracefully return an error instead of carrying on with no LPI allocated at all. Fixes: 38dd7c494cf6 ("irqchip/gic-v3-its: Drop chunk allocation compatibility") Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-gic-v3-its.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index f25ec92f23ee..c3aba3fc818d 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -1586,6 +1586,9 @@ static unsigned long *its_lpi_alloc(int nr_irqs, u32 *base, int *nr_ids) nr_irqs /= 2; } while (nr_irqs > 0); + if (!nr_irqs) + err = -ENOSPC; + if (err) goto out; From 2380a22b60ce6f995eac806e69c66e397b59d045 Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Mon, 28 Jan 2019 16:59:35 +0100 Subject: [PATCH 211/525] irqchip/mmp: Only touch the PJ4 IRQ & FIQ bits on enable/disable Resetting bit 4 disables the interrupt delivery to the "secure processor" core. This breaks the keyboard on a OLPC XO 1.75 laptop, where the firmware running on the "secure processor" bit-bangs the PS/2 protocol over the GPIO lines. It is not clear what the rest of the bits are and Marvell was unhelpful when asked for documentation. Aside from the SP bit, there are probably priority bits. Leaving the unknown bits as the firmware set them up seems to be a wiser course of action compared to just turning them off. Signed-off-by: Lubomir Rintel Acked-by: Pavel Machek [maz: fixed-up subject and commit message] Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-mmp.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/irqchip/irq-mmp.c b/drivers/irqchip/irq-mmp.c index 25f32e1d7764..3496b61a312a 100644 --- a/drivers/irqchip/irq-mmp.c +++ b/drivers/irqchip/irq-mmp.c @@ -34,6 +34,9 @@ #define SEL_INT_PENDING (1 << 6) #define SEL_INT_NUM_MASK 0x3f +#define MMP2_ICU_INT_ROUTE_PJ4_IRQ (1 << 5) +#define MMP2_ICU_INT_ROUTE_PJ4_FIQ (1 << 6) + struct icu_chip_data { int nr_irqs; unsigned int virq_base; @@ -190,7 +193,8 @@ static const struct mmp_intc_conf mmp_conf = { static const struct mmp_intc_conf mmp2_conf = { .conf_enable = 0x20, .conf_disable = 0x0, - .conf_mask = 0x7f, + .conf_mask = MMP2_ICU_INT_ROUTE_PJ4_IRQ | + MMP2_ICU_INT_ROUTE_PJ4_FIQ, }; static void __exception_irq_entry mmp_handle_irq(struct pt_regs *regs) From dc14eb12f6bb3e779c5461429c1889a339c67aab Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 9 Jan 2019 22:19:28 -0500 Subject: [PATCH 212/525] drm/amdgpu: Add missing power attribute to APU check Add missing power_average to visible check for power attributes for APUs. Was missed before. Reviewed-by: Evan Quan Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index 6896dec97fc7..0ed41a9d2d77 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -1686,7 +1686,8 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj, effective_mode &= ~S_IWUSR; if ((adev->flags & AMD_IS_APU) && - (attr == &sensor_dev_attr_power1_cap_max.dev_attr.attr || + (attr == &sensor_dev_attr_power1_average.dev_attr.attr || + attr == &sensor_dev_attr_power1_cap_max.dev_attr.attr || attr == &sensor_dev_attr_power1_cap_min.dev_attr.attr|| attr == &sensor_dev_attr_power1_cap.dev_attr.attr)) return 0; From afeff4c16edaa6275b903f82b0561406259aa3a3 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Tue, 15 Jan 2019 12:05:16 -0500 Subject: [PATCH 213/525] drm/radeon: check if device is root before getting pci speed caps Check if the device is root rather before attempting to see what speeds the pcie port supports. Fixes a crash with pci passthrough in a VM. Bug: https://bugs.freedesktop.org/show_bug.cgi?id=109366 Reviewed-by: Evan Quan Signed-off-by: Alex Deucher --- drivers/gpu/drm/radeon/ci_dpm.c | 5 +++-- drivers/gpu/drm/radeon/si_dpm.c | 5 +++-- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c index d587779a80b4..a97294ac96d5 100644 --- a/drivers/gpu/drm/radeon/ci_dpm.c +++ b/drivers/gpu/drm/radeon/ci_dpm.c @@ -5676,7 +5676,7 @@ int ci_dpm_init(struct radeon_device *rdev) u16 data_offset, size; u8 frev, crev; struct ci_power_info *pi; - enum pci_bus_speed speed_cap; + enum pci_bus_speed speed_cap = PCI_SPEED_UNKNOWN; struct pci_dev *root = rdev->pdev->bus->self; int ret; @@ -5685,7 +5685,8 @@ int ci_dpm_init(struct radeon_device *rdev) return -ENOMEM; rdev->pm.dpm.priv = pi; - speed_cap = pcie_get_speed_cap(root); + if (!pci_is_root_bus(rdev->pdev->bus)) + speed_cap = pcie_get_speed_cap(root); if (speed_cap == PCI_SPEED_UNKNOWN) { pi->sys_pcie_mask = 0; } else { diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index 8fb60b3af015..0a785ef0ab66 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -6899,7 +6899,7 @@ int si_dpm_init(struct radeon_device *rdev) struct ni_power_info *ni_pi; struct si_power_info *si_pi; struct atom_clock_dividers dividers; - enum pci_bus_speed speed_cap; + enum pci_bus_speed speed_cap = PCI_SPEED_UNKNOWN; struct pci_dev *root = rdev->pdev->bus->self; int ret; @@ -6911,7 +6911,8 @@ int si_dpm_init(struct radeon_device *rdev) eg_pi = &ni_pi->eg; pi = &eg_pi->rv7xx; - speed_cap = pcie_get_speed_cap(root); + if (!pci_is_root_bus(rdev->pdev->bus)) + speed_cap = pcie_get_speed_cap(root); if (speed_cap == PCI_SPEED_UNKNOWN) { si_pi->sys_pcie_mask = 0; } else { From 2f10d823739680d2477ce34437e8a08a53117f40 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Fri, 25 Jan 2019 15:55:33 -0600 Subject: [PATCH 214/525] drm/amd/powerplay: Fix missing break in switch Add missing break statement in order to prevent the code from falling through to the default case. The resoning for this is that pclk_vol_table is an automatic variable. So, it makes no sense to update it just before falling through to the default case and return -EINVAL. This bug was found thanks to the ongoing efforts to enabling -Wimplicit-fallthrough. Fixes: cd70f3d6e3fa ("drm/amd/powerplay: PP/DAL interface changes for dynamic clock switch") Cc: stable@vger.kernel.org Signed-off-by: Gustavo A. R. Silva Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c index f95c5f50eb0f..5273de3c5b98 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c @@ -1033,6 +1033,7 @@ static int smu10_get_clock_by_type_with_latency(struct pp_hwmgr *hwmgr, break; case amd_pp_dpp_clock: pclk_vol_table = pinfo->vdd_dep_on_dppclk; + break; default: return -EINVAL; } From e501070e4db0b67a4c17a5557d1e9d098f3db310 Mon Sep 17 00:00:00 2001 From: Harini Katakam Date: Tue, 29 Jan 2019 15:20:03 +0530 Subject: [PATCH 215/525] net: macb: Apply RXUBR workaround only to versions with errata The interrupt handler contains a workaround for RX hang applicable to Zynq and AT91RM9200 only. Subsequent versions do not need this workaround. This workaround unnecessarily resets RX whenever RX used bit read is observed, which can be often under heavy traffic. There is no other action performed on RX UBR interrupt. Hence introduce a CAPS mask; enable this interrupt and workaround only on affected versions. Signed-off-by: Harini Katakam Signed-off-by: David S. Miller --- drivers/net/ethernet/cadence/macb.h | 3 +++ drivers/net/ethernet/cadence/macb_main.c | 28 ++++++++++++++---------- 2 files changed, 20 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index 3d45f4c92cf6..9bbaad9f3d63 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -643,6 +643,7 @@ #define MACB_CAPS_JUMBO 0x00000020 #define MACB_CAPS_GEM_HAS_PTP 0x00000040 #define MACB_CAPS_BD_RD_PREFETCH 0x00000080 +#define MACB_CAPS_NEEDS_RSTONUBR 0x00000100 #define MACB_CAPS_FIFO_MODE 0x10000000 #define MACB_CAPS_GIGABIT_MODE_AVAILABLE 0x20000000 #define MACB_CAPS_SG_DISABLED 0x40000000 @@ -1214,6 +1215,8 @@ struct macb { int rx_bd_rd_prefetch; int tx_bd_rd_prefetch; + + u32 rx_intr_mask; }; #ifdef CONFIG_MACB_USE_HWSTAMP diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 66cc7927061a..2b2882615e8b 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -56,8 +56,7 @@ /* level of occupied TX descriptors under which we wake up TX process */ #define MACB_TX_WAKEUP_THRESH(bp) (3 * (bp)->tx_ring_size / 4) -#define MACB_RX_INT_FLAGS (MACB_BIT(RCOMP) | MACB_BIT(RXUBR) \ - | MACB_BIT(ISR_ROVR)) +#define MACB_RX_INT_FLAGS (MACB_BIT(RCOMP) | MACB_BIT(ISR_ROVR)) #define MACB_TX_ERR_FLAGS (MACB_BIT(ISR_TUND) \ | MACB_BIT(ISR_RLE) \ | MACB_BIT(TXERR)) @@ -1270,7 +1269,7 @@ static int macb_poll(struct napi_struct *napi, int budget) queue_writel(queue, ISR, MACB_BIT(RCOMP)); napi_reschedule(napi); } else { - queue_writel(queue, IER, MACB_RX_INT_FLAGS); + queue_writel(queue, IER, bp->rx_intr_mask); } } @@ -1288,7 +1287,7 @@ static void macb_hresp_error_task(unsigned long data) u32 ctrl; for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { - queue_writel(queue, IDR, MACB_RX_INT_FLAGS | + queue_writel(queue, IDR, bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); } @@ -1318,7 +1317,7 @@ static void macb_hresp_error_task(unsigned long data) /* Enable interrupts */ queue_writel(queue, IER, - MACB_RX_INT_FLAGS | + bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); } @@ -1372,14 +1371,14 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id) (unsigned int)(queue - bp->queues), (unsigned long)status); - if (status & MACB_RX_INT_FLAGS) { + if (status & bp->rx_intr_mask) { /* There's no point taking any more interrupts * until we have processed the buffers. The * scheduling call may fail if the poll routine * is already scheduled, so disable interrupts * now. */ - queue_writel(queue, IDR, MACB_RX_INT_FLAGS); + queue_writel(queue, IDR, bp->rx_intr_mask); if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE) queue_writel(queue, ISR, MACB_BIT(RCOMP)); @@ -1412,8 +1411,9 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id) /* There is a hardware issue under heavy load where DMA can * stop, this causes endless "used buffer descriptor read" * interrupts but it can be cleared by re-enabling RX. See - * the at91 manual, section 41.3.1 or the Zynq manual - * section 16.7.4 for details. + * the at91rm9200 manual, section 41.3.1 or the Zynq manual + * section 16.7.4 for details. RXUBR is only enabled for + * these two versions. */ if (status & MACB_BIT(RXUBR)) { ctrl = macb_readl(bp, NCR); @@ -2259,7 +2259,7 @@ static void macb_init_hw(struct macb *bp) /* Enable interrupts */ queue_writel(queue, IER, - MACB_RX_INT_FLAGS | + bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); } @@ -3907,6 +3907,7 @@ static const struct macb_config sama5d4_config = { }; static const struct macb_config emac_config = { + .caps = MACB_CAPS_NEEDS_RSTONUBR, .clk_init = at91ether_clk_init, .init = at91ether_init, }; @@ -3928,7 +3929,8 @@ static const struct macb_config zynqmp_config = { }; static const struct macb_config zynq_config = { - .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_NO_GIGABIT_HALF, + .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_NO_GIGABIT_HALF | + MACB_CAPS_NEEDS_RSTONUBR, .dma_burst_length = 16, .clk_init = macb_clk_init, .init = macb_init, @@ -4083,6 +4085,10 @@ static int macb_probe(struct platform_device *pdev) macb_dma_desc_get_size(bp); } + bp->rx_intr_mask = MACB_RX_INT_FLAGS; + if (bp->caps & MACB_CAPS_NEEDS_RSTONUBR) + bp->rx_intr_mask |= MACB_BIT(RXUBR); + mac = of_get_mac_address(np); if (mac) { ether_addr_copy(bp->dev->dev_addr, mac); From 896cebc0e261a29a6f0b20ab21d1bfc06959e91d Mon Sep 17 00:00:00 2001 From: Yang Wei Date: Tue, 29 Jan 2019 22:40:51 +0800 Subject: [PATCH 216/525] net: 8139cp: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles dev_consume_skb_irq() should be called in cp_tx() when skb xmit done. It makes drop profiles(dropwatch, perf) more friendly. Signed-off-by: Yang Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/realtek/8139cp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c index 44f6e4873aad..4f910c4f67b0 100644 --- a/drivers/net/ethernet/realtek/8139cp.c +++ b/drivers/net/ethernet/realtek/8139cp.c @@ -691,7 +691,7 @@ static void cp_tx (struct cp_private *cp) } bytes_compl += skb->len; pkts_compl++; - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); } cp->tx_skb[tx_tail] = NULL; From e339f8631eb70fb48b2801e9e66a267c9a730a6a Mon Sep 17 00:00:00 2001 From: Yang Wei Date: Tue, 29 Jan 2019 23:32:22 +0800 Subject: [PATCH 217/525] net: caif: call dev_consume_skb_any when skb xmit done The skb shouled be consumed when xmit done, it makes drop profiles (dropwatch, perf) more friendly. dev_kfree_skb_irq()/kfree_skb() shouled be replaced by dev_consume_skb_any(), it makes code cleaner. Signed-off-by: Yang Wei Signed-off-by: David S. Miller --- drivers/net/caif/caif_serial.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c index a0f954f36c09..44e6c7b1b222 100644 --- a/drivers/net/caif/caif_serial.c +++ b/drivers/net/caif/caif_serial.c @@ -257,10 +257,7 @@ static int handle_tx(struct ser_device *ser) if (skb->len == 0) { struct sk_buff *tmp = skb_dequeue(&ser->head); WARN_ON(tmp != skb); - if (in_interrupt()) - dev_kfree_skb_irq(skb); - else - kfree_skb(skb); + dev_consume_skb_any(skb); } } /* Send flow off if queue is empty */ From 0f0ed8282e5bfdc87cdd562e58f3d90d893e7ee5 Mon Sep 17 00:00:00 2001 From: Yang Wei Date: Tue, 29 Jan 2019 23:04:40 +0800 Subject: [PATCH 218/525] net: b44: replace dev_kfree_skb_xxx by dev_consume_skb_xxx for drop profiles The skb should be freed by dev_consume_skb_any() in b44_start_xmit() when bounce_skb is used. The skb is be replaced by bounce_skb, so the original skb should be consumed(not drop). dev_consume_skb_irq() should be called in b44_tx() when skb xmit done. It makes drop profiles(dropwatch, perf) more friendly. Signed-off-by: Yang Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/b44.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index f44808959ff3..97ab0dd25552 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -638,7 +638,7 @@ static void b44_tx(struct b44 *bp) bytes_compl += skb->len; pkts_compl++; - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); } netdev_completed_queue(bp->dev, pkts_compl, bytes_compl); @@ -1012,7 +1012,7 @@ static netdev_tx_t b44_start_xmit(struct sk_buff *skb, struct net_device *dev) } skb_copy_from_linear_data(skb, skb_put(bounce_skb, len), len); - dev_kfree_skb_any(skb); + dev_consume_skb_any(skb); skb = bounce_skb; } From 35edfdc77f683c8fd27d7732af06cf6489af60a5 Mon Sep 17 00:00:00 2001 From: Josh Elsasser Date: Sat, 26 Jan 2019 14:38:33 -0800 Subject: [PATCH 219/525] net: set default network namespace in init_dummy_netdev() Assign a default net namespace to netdevs created by init_dummy_netdev(). Fixes a NULL pointer dereference caused by busy-polling a socket bound to an iwlwifi wireless device, which bumps the per-net BUSYPOLLRXPACKETS stat if napi_poll() received packets: BUG: unable to handle kernel NULL pointer dereference at 0000000000000190 IP: napi_busy_loop+0xd6/0x200 Call Trace: sock_poll+0x5e/0x80 do_sys_poll+0x324/0x5a0 SyS_poll+0x6c/0xf0 do_syscall_64+0x6b/0x1f0 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 Fixes: 7db6b048da3b ("net: Commonize busy polling code to focus on napi_id instead of socket") Signed-off-by: Josh Elsasser Signed-off-by: David S. Miller --- net/core/dev.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/core/dev.c b/net/core/dev.c index 82f20022259d..8e276e0192a1 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8712,6 +8712,9 @@ int init_dummy_netdev(struct net_device *dev) set_bit(__LINK_STATE_PRESENT, &dev->state); set_bit(__LINK_STATE_START, &dev->state); + /* napi_busy_loop stats accounting wants this */ + dev_net_set(dev, &init_net); + /* Note : We dont allocate pcpu_refcnt for dummy devices, * because users of this 'device' dont need to change * its refcount. From d07e1e0febe10b65eecd3205ad3bd1e999754887 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 29 Jan 2019 14:22:33 +0100 Subject: [PATCH 220/525] MAINTAINERS: Add entry for XDP (eXpress Data Path) Add multiple people as maintainers for XDP, sorted alphabetically. XDP is also tied to driver level support and code, but we cannot add all drivers to the list. Instead K: and N: match on 'xdp' in hope to catch some of those changes in drivers. Signed-off-by: Jesper Dangaard Brouer Acked-by: John Fastabend Acked-by: Jakub Kicinski Acked-by: David S. Miller Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- MAINTAINERS | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 9f64f8d3740e..2d3c1918f1b0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -16673,6 +16673,24 @@ T: git git://linuxtv.org/media_tree.git S: Maintained F: drivers/media/tuners/tuner-xc2028.* +XDP (eXpress Data Path) +M: Alexei Starovoitov +M: Daniel Borkmann +M: David S. Miller +M: Jakub Kicinski +M: Jesper Dangaard Brouer +M: John Fastabend +L: netdev@vger.kernel.org +L: xdp-newbies@vger.kernel.org +S: Supported +F: net/core/xdp.c +F: include/net/xdp.h +F: kernel/bpf/devmap.c +F: kernel/bpf/cpumap.c +F: include/trace/events/xdp.h +K: xdp +N: xdp + XDP SOCKETS (AF_XDP) M: Björn Töpel M: Magnus Karlsson From dcf300a69ac307053dfb35c2e33972e754a98bce Mon Sep 17 00:00:00 2001 From: Aaro Koskinen Date: Sun, 27 Jan 2019 23:28:33 +0200 Subject: [PATCH 221/525] MIPS: OCTEON: don't set octeon_dma_bar_type if PCI is disabled Don't set octeon_dma_bar_type if PCI is disabled. This avoids creation of the MSI irqchip later on, and saves a bit of memory. Signed-off-by: Aaro Koskinen Signed-off-by: Paul Burton Fixes: a214720cbf50 ("Disable MSI also when pcie-octeon.pcie_disable on") Cc: stable@vger.kernel.org # v3.3+ Cc: linux-mips@vger.kernel.org --- arch/mips/pci/pci-octeon.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/mips/pci/pci-octeon.c b/arch/mips/pci/pci-octeon.c index 5017d5843c5a..fc29b85cfa92 100644 --- a/arch/mips/pci/pci-octeon.c +++ b/arch/mips/pci/pci-octeon.c @@ -568,6 +568,11 @@ static int __init octeon_pci_setup(void) if (octeon_has_feature(OCTEON_FEATURE_PCIE)) return 0; + if (!octeon_is_pci_host()) { + pr_notice("Not in host mode, PCI Controller not initialized\n"); + return 0; + } + /* Point pcibios_map_irq() to the PCI version of it */ octeon_pcibios_map_irq = octeon_pci_pcibios_map_irq; @@ -579,11 +584,6 @@ static int __init octeon_pci_setup(void) else octeon_dma_bar_type = OCTEON_DMA_BAR_TYPE_BIG; - if (!octeon_is_pci_host()) { - pr_notice("Not in host mode, PCI Controller not initialized\n"); - return 0; - } - /* PCI I/O and PCI MEM values */ set_io_port_base(OCTEON_PCI_IOSPACE_BASE); ioport_resource.start = 0; From 0648e50e548d881d025b9419a1a168753c8e2bf7 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Mon, 28 Jan 2019 22:21:17 +0000 Subject: [PATCH 222/525] MIPS: VDSO: Use same -m%-float cflag as the kernel proper The MIPS VDSO build currently doesn't provide the -msoft-float flag to the compiler as the kernel proper does. This results in an attempt to use the compiler's default floating point configuration, which can be problematic in cases where this is incompatible with the target CPU's -march= flag. For example decstation_defconfig fails to build using toolchains in which gcc was configured --with-fp-32=xx with the following error: LDS arch/mips/vdso/vdso.lds cc1: error: '-march=r3000' requires '-mfp32' make[2]: *** [scripts/Makefile.build:379: arch/mips/vdso/vdso.lds] Error 1 The kernel proper avoids this error because we build with the -msoft-float compiler flag, rather than using the compiler's default. Pass this flag through to the VDSO build so that it too becomes agnostic to the toolchain's floating point configuration. Note that this is filtered out from KBUILD_CFLAGS rather than simply always using -msoft-float such that if we switch the kernel to use -mno-float in the future the VDSO will automatically inherit the change. The VDSO doesn't actually include any floating point code, and its .MIPS.abiflags section is already manually generated to specify that it's compatible with any floating point ABI. As such this change should have no effect on the resulting VDSO, apart from fixing the build failure for affected toolchains. Signed-off-by: Paul Burton Reported-by: Kevin Hilman Reported-by: Guenter Roeck Tested-by: Kevin Hilman References: https://lore.kernel.org/linux-mips/1477843551-21813-1-git-send-email-linux@roeck-us.net/ References: https://kernelci.org/build/id/5c4e4ae059b5142a249ad004/logs/ Fixes: ebb5e78cc634 ("MIPS: Initial implementation of a VDSO") Cc: Maciej W. Rozycki Cc: linux-mips@vger.kernel.org Cc: stable@vger.kernel.org # v4.4+ --- arch/mips/vdso/Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index f6fd340e39c2..314949b2261d 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -8,6 +8,7 @@ ccflags-vdso := \ $(filter -E%,$(KBUILD_CFLAGS)) \ $(filter -mmicromips,$(KBUILD_CFLAGS)) \ $(filter -march=%,$(KBUILD_CFLAGS)) \ + $(filter -m%-float,$(KBUILD_CFLAGS)) \ -D__VDSO__ ifdef CONFIG_CC_IS_CLANG From 67fc5dc8a541e8f458d7f08bf88ff55933bf9f9d Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Mon, 28 Jan 2019 23:16:22 +0000 Subject: [PATCH 223/525] MIPS: VDSO: Include $(ccflags-vdso) in o32,n32 .lds builds When generating vdso-o32.lds & vdso-n32.lds for use with programs running as compat ABIs under 64b kernels, we previously haven't included the compiler flags that are supposedly common to all ABIs - ie. those in the ccflags-vdso variable. This is problematic in cases where we need to provide the -m%-float flag in order to ensure that we don't attempt to use a floating point ABI that's incompatible with the target CPU & ABI. For example a toolchain using current gcc trunk configured --with-fp-32=xx fails to build a 64r6el_defconfig kernel with the following error: cc1: error: '-march=mips1' requires '-mfp32' make[2]: *** [arch/mips/vdso/Makefile:135: arch/mips/vdso/vdso-o32.lds] Error 1 Include $(ccflags-vdso) for the compat VDSO .lds builds, just as it is included for the native VDSO .lds & when compiling objects for the compat VDSOs. This ensures we consistently provide the -msoft-float flag amongst others, avoiding the problem by ensuring we're agnostic to the toolchain defaults. Signed-off-by: Paul Burton Fixes: ebb5e78cc634 ("MIPS: Initial implementation of a VDSO") Cc: linux-mips@vger.kernel.org Cc: Kevin Hilman Cc: Guenter Roeck Cc: Maciej W . Rozycki Cc: stable@vger.kernel.org # v4.4+ --- arch/mips/vdso/Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index 314949b2261d..0ede4deb8181 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -130,7 +130,7 @@ $(obj)/%-o32.o: $(src)/%.c FORCE $(call cmd,force_checksrc) $(call if_changed_rule,cc_o_c) -$(obj)/vdso-o32.lds: KBUILD_CPPFLAGS := -mabi=32 +$(obj)/vdso-o32.lds: KBUILD_CPPFLAGS := $(ccflags-vdso) -mabi=32 $(obj)/vdso-o32.lds: $(src)/vdso.lds.S FORCE $(call if_changed_dep,cpp_lds_S) @@ -170,7 +170,7 @@ $(obj)/%-n32.o: $(src)/%.c FORCE $(call cmd,force_checksrc) $(call if_changed_rule,cc_o_c) -$(obj)/vdso-n32.lds: KBUILD_CPPFLAGS := -mabi=n32 +$(obj)/vdso-n32.lds: KBUILD_CPPFLAGS := $(ccflags-vdso) -mabi=n32 $(obj)/vdso-n32.lds: $(src)/vdso.lds.S FORCE $(call if_changed_dep,cpp_lds_S) From ff9fb72bc07705c00795ca48631f7fffe24d2c6b Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 23 Jan 2019 11:28:14 +0100 Subject: [PATCH 224/525] debugfs: return error values, not NULL When an error happens, debugfs should return an error pointer value, not NULL. This will prevent the totally theoretical error where a debugfs call fails due to lack of memory, returning NULL, and that dentry value is then passed to another debugfs call, which would end up succeeding, creating a file at the root of the debugfs tree, but would then be impossible to remove (because you can not remove the directory NULL). So, to make everyone happy, always return errors, this makes the users of debugfs much simpler (they do not have to ever check the return value), and everyone can rest easy. Reported-by: Gary R Hook Reported-by: Heiko Carstens Reported-by: Masami Hiramatsu Reported-by: Michal Hocko Reported-by: Sebastian Andrzej Siewior Reported-by: Ulf Hansson Reviewed-by: Masami Hiramatsu Reviewed-by: Sebastian Andrzej Siewior Signed-off-by: Greg Kroah-Hartman --- fs/debugfs/inode.c | 39 ++++++++++++++++++++++----------------- 1 file changed, 22 insertions(+), 17 deletions(-) diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 41ef452c1fcf..b16f8035b1af 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -254,8 +254,8 @@ MODULE_ALIAS_FS("debugfs"); * @parent: a pointer to the parent dentry of the file. * * This function will return a pointer to a dentry if it succeeds. If the file - * doesn't exist or an error occurs, %NULL will be returned. The returned - * dentry must be passed to dput() when it is no longer needed. + * doesn't exist or an error occurs, %ERR_PTR(-ERROR) will be returned. The + * returned dentry must be passed to dput() when it is no longer needed. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. @@ -265,17 +265,17 @@ struct dentry *debugfs_lookup(const char *name, struct dentry *parent) struct dentry *dentry; if (IS_ERR(parent)) - return NULL; + return parent; if (!parent) parent = debugfs_mount->mnt_root; dentry = lookup_one_len_unlocked(name, parent, strlen(name)); if (IS_ERR(dentry)) - return NULL; + return dentry; if (!d_really_is_positive(dentry)) { dput(dentry); - return NULL; + return ERR_PTR(-EINVAL); } return dentry; } @@ -324,7 +324,7 @@ static struct dentry *failed_creating(struct dentry *dentry) inode_unlock(d_inode(dentry->d_parent)); dput(dentry); simple_release_fs(&debugfs_mount, &debugfs_mount_count); - return NULL; + return ERR_PTR(-ENOMEM); } static struct dentry *end_creating(struct dentry *dentry) @@ -347,7 +347,7 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode, dentry = start_creating(name, parent); if (IS_ERR(dentry)) - return NULL; + return dentry; inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) @@ -386,7 +386,8 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode, * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, %NULL will be returned. + * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be + * returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. @@ -464,7 +465,8 @@ EXPORT_SYMBOL_GPL(debugfs_create_file_unsafe); * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, %NULL will be returned. + * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be + * returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. @@ -495,7 +497,8 @@ EXPORT_SYMBOL_GPL(debugfs_create_file_size); * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, %NULL will be returned. + * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be + * returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. @@ -506,7 +509,7 @@ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent) struct inode *inode; if (IS_ERR(dentry)) - return NULL; + return dentry; inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) @@ -545,7 +548,7 @@ struct dentry *debugfs_create_automount(const char *name, struct inode *inode; if (IS_ERR(dentry)) - return NULL; + return dentry; inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) @@ -581,8 +584,8 @@ EXPORT_SYMBOL(debugfs_create_automount); * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the symbolic * link is to be removed (no automatic cleanup happens if your module is - * unloaded, you are responsible here.) If an error occurs, %NULL will be - * returned. + * unloaded, you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) + * will be returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. @@ -594,12 +597,12 @@ struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent, struct inode *inode; char *link = kstrdup(target, GFP_KERNEL); if (!link) - return NULL; + return ERR_PTR(-ENOMEM); dentry = start_creating(name, parent); if (IS_ERR(dentry)) { kfree(link); - return NULL; + return dentry; } inode = debugfs_get_inode(dentry->d_sb); @@ -827,7 +830,9 @@ exit: if (dentry && !IS_ERR(dentry)) dput(dentry); unlock_rename(new_dir, old_dir); - return NULL; + if (IS_ERR(dentry)) + return dentry; + return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(debugfs_rename); From 7b21b69ab203136fdc153c7707fa6c409e523c2e Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Sun, 27 Jan 2019 10:11:27 +0200 Subject: [PATCH 225/525] IB/uverbs: Fix OOPs in uverbs_user_mmap_disassociate The vma->vm_mm can become impossible to get before rdma_umap_close() is called, in this case we must not try to get an mm that is already undergoing process exit. In this case there is no need to wait for anything as the VMA will be destroyed by another thread soon and is already effectively 'unreachable' by userspace. BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 PGD 800000012bc50067 P4D 800000012bc50067 PUD 129db5067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 1 PID: 2050 Comm: bash Tainted: G W OE 4.20.0-rc6+ #3 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:__rb_erase_color+0xb9/0x280 Code: 84 17 01 00 00 48 3b 68 10 0f 84 15 01 00 00 48 89 58 08 48 89 de 48 89 ef 4c 89 e3 e8 90 84 22 00 e9 60 ff ff ff 48 8b 5d 10 03 01 0f 84 9c 00 00 00 48 8b 43 10 48 85 c0 74 09 f6 00 01 0f RSP: 0018:ffffbecfc090bab8 EFLAGS: 00010246 RAX: ffff97616346cf30 RBX: 0000000000000000 RCX: 0000000000000101 RDX: 0000000000000000 RSI: ffff97623b6ca828 RDI: ffff97621ef10828 RBP: ffff97621ef10828 R08: ffff97621ef10828 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff97623b6ca838 R13: ffffffffbb3fef50 R14: ffff97623b6ca828 R15: 0000000000000000 FS: 00007f7a5c31d740(0000) GS:ffff97623bb00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000011255a000 CR4: 00000000000006e0 Call Trace: unlink_file_vma+0x3b/0x50 free_pgtables+0xa1/0x110 exit_mmap+0xca/0x1a0 ? mlx5_ib_dealloc_pd+0x28/0x30 [mlx5_ib] mmput+0x54/0x140 uverbs_user_mmap_disassociate+0xcc/0x160 [ib_uverbs] uverbs_destroy_ufile_hw+0xf7/0x120 [ib_uverbs] ib_uverbs_remove_one+0xea/0x240 [ib_uverbs] ib_unregister_device+0xfb/0x200 [ib_core] mlx5_ib_remove+0x51/0xe0 [mlx5_ib] mlx5_remove_device+0xc1/0xd0 [mlx5_core] mlx5_unregister_device+0x3d/0xb0 [mlx5_core] remove_one+0x2a/0x90 [mlx5_core] pci_device_remove+0x3b/0xc0 device_release_driver_internal+0x16d/0x240 unbind_store+0xb2/0x100 kernfs_fop_write+0x102/0x180 __vfs_write+0x36/0x1a0 ? __alloc_fd+0xa9/0x170 ? set_close_on_exec+0x49/0x70 vfs_write+0xad/0x1a0 ksys_write+0x52/0xc0 do_syscall_64+0x5b/0x180 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Cc: # 4.19 Fixes: 5f9794dc94f5 ("RDMA/ucontext: Add a core API for mmaping driver IO memory") Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/uverbs_main.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 15add0688fbb..5f366838b7ff 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -967,11 +967,19 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile) /* Get an arbitrary mm pointer that hasn't been cleaned yet */ mutex_lock(&ufile->umap_lock); - if (!list_empty(&ufile->umaps)) { - mm = list_first_entry(&ufile->umaps, - struct rdma_umap_priv, list) - ->vma->vm_mm; - mmget(mm); + while (!list_empty(&ufile->umaps)) { + int ret; + + priv = list_first_entry(&ufile->umaps, + struct rdma_umap_priv, list); + mm = priv->vma->vm_mm; + ret = mmget_not_zero(mm); + if (!ret) { + list_del_init(&priv->list); + mm = NULL; + continue; + } + break; } mutex_unlock(&ufile->umap_lock); if (!mm) From b677dfae5aa197afc5191755a76a8727ffca538a Mon Sep 17 00:00:00 2001 From: Wei Huang Date: Thu, 3 Jan 2019 23:44:11 -0600 Subject: [PATCH 226/525] x86/boot/compressed/64: Set EFER.LME=1 in 32-bit trampoline before returning to long mode In some old AMD KVM implementation, guest's EFER.LME bit is cleared by KVM when the hypervsior detects that the guest sets CR0.PG to 0. This causes the guest OS to reboot when it tries to return from 32-bit trampoline code because the CPU is in incorrect state: CR4.PAE=1, CR0.PG=1, CS.L=1, but EFER.LME=0. As a precaution, set EFER.LME=1 as part of long mode activation procedure. This extra step won't cause any harm when Linux is booted on a bare-metal machine. Signed-off-by: Wei Huang Signed-off-by: Thomas Gleixner Acked-by: Kirill A. Shutemov Cc: bp@alien8.de Cc: hpa@zytor.com Link: https://lkml.kernel.org/r/20190104054411.12489-1-wei@redhat.com --- arch/x86/boot/compressed/head_64.S | 8 ++++++++ arch/x86/boot/compressed/pgtable.h | 2 +- 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 64037895b085..f105ae8651c9 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -600,6 +600,14 @@ ENTRY(trampoline_32bit_src) leal TRAMPOLINE_32BIT_PGTABLE_OFFSET(%ecx), %eax movl %eax, %cr3 3: + /* Set EFER.LME=1 as a precaution in case hypervsior pulls the rug */ + pushl %ecx + movl $MSR_EFER, %ecx + rdmsr + btsl $_EFER_LME, %eax + wrmsr + popl %ecx + /* Enable PAE and LA57 (if required) paging modes */ movl $X86_CR4_PAE, %eax cmpl $0, %edx diff --git a/arch/x86/boot/compressed/pgtable.h b/arch/x86/boot/compressed/pgtable.h index 91f75638f6e6..6ff7e81b5628 100644 --- a/arch/x86/boot/compressed/pgtable.h +++ b/arch/x86/boot/compressed/pgtable.h @@ -6,7 +6,7 @@ #define TRAMPOLINE_32BIT_PGTABLE_OFFSET 0 #define TRAMPOLINE_32BIT_CODE_OFFSET PAGE_SIZE -#define TRAMPOLINE_32BIT_CODE_SIZE 0x60 +#define TRAMPOLINE_32BIT_CODE_SIZE 0x70 #define TRAMPOLINE_32BIT_STACK_END TRAMPOLINE_32BIT_SIZE From 5ccd35287edae4107475a141a477a6a4ecbe1cab Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Sat, 22 Dec 2018 19:11:16 +0000 Subject: [PATCH 227/525] x86/fault: Fix sign-extend unintended sign extension show_ldttss() shifts desc.base2 by 24 bit, but base2 is 8 bits of a bitfield in a u16. Due to the really great idea of integer promotion in C99 base2 is promoted to an int, because that's the standard defined behaviour when all values which can be represented by base2 fit into an int. Now if bit 7 is set in desc.base2 the result of the shift left by 24 makes the resulting integer negative and the following conversion to unsigned long legitmately sign extends first causing the upper bits 32 bits to be set in the result. Fix this by casting desc.base2 to unsigned long before the shift. Detected by CoverityScan, CID#1475635 ("Unintended sign extension") [ tglx: Reworded the changelog a bit as I actually had to lookup the standard (again) to decode the original one. ] Fixes: a1a371c468f7 ("x86/fault: Decode page fault OOPSes better") Signed-off-by: Colin Ian King Signed-off-by: Thomas Gleixner Cc: Dave Hansen Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Borislav Petkov Cc: "H . Peter Anvin" Cc: kernel-janitors@vger.kernel.org Link: https://lkml.kernel.org/r/20181222191116.21831-1-colin.king@canonical.com --- arch/x86/mm/fault.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 2ff25ad33233..9d5c75f02295 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -595,7 +595,7 @@ static void show_ldttss(const struct desc_ptr *gdt, const char *name, u16 index) return; } - addr = desc.base0 | (desc.base1 << 16) | (desc.base2 << 24); + addr = desc.base0 | (desc.base1 << 16) | ((unsigned long)desc.base2 << 24); #ifdef CONFIG_X86_64 addr |= ((u64)desc.base3 << 32); #endif From 34d66caf251df91ff27b24a3a786810d29989eca Mon Sep 17 00:00:00 2001 From: Zhenzhong Duan Date: Thu, 17 Jan 2019 02:10:59 -0800 Subject: [PATCH 228/525] x86/speculation: Remove redundant arch_smt_update() invocation With commit a74cfffb03b7 ("x86/speculation: Rework SMT state change"), arch_smt_update() is invoked from each individual CPU hotplug function. Therefore the extra arch_smt_update() call in the sysfs SMT control is redundant. Fixes: a74cfffb03b7 ("x86/speculation: Rework SMT state change") Signed-off-by: Zhenzhong Duan Signed-off-by: Thomas Gleixner Cc: Cc: Cc: Cc: Cc: Cc: Link: https://lkml.kernel.org/r/e2e064f2-e8ef-42ca-bf4f-76b612964752@default --- kernel/cpu.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/kernel/cpu.c b/kernel/cpu.c index 91d5c38eb7e5..c0c7f64573ed 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -2090,10 +2090,8 @@ static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) */ cpuhp_offline_cpu_device(cpu); } - if (!ret) { + if (!ret) cpu_smt_control = ctrlval; - arch_smt_update(); - } cpu_maps_update_done(); return ret; } @@ -2104,7 +2102,6 @@ static int cpuhp_smt_enable(void) cpu_maps_update_begin(); cpu_smt_control = CPU_SMT_ENABLED; - arch_smt_update(); for_each_present_cpu(cpu) { /* Skip online CPUs and CPUs on offline nodes */ if (cpu_online(cpu) || !node_online(cpu_to_node(cpu))) From 8fc75bed96bb94e23ca51bd9be4daf65c57697bf Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 29 Jan 2019 15:52:55 -0500 Subject: [PATCH 229/525] NFS: Fix up return value on fatal errors in nfs_page_async_flush() Ensure that we return the fatal error value that caused us to exit nfs_page_async_flush(). Fixes: c373fff7bd25 ("NFSv4: Don't special case "launder"") Signed-off-by: Trond Myklebust Cc: stable@vger.kernel.org # v4.12+ Reviewed-by: Benjamin Coddington Signed-off-by: Anna Schumaker --- fs/nfs/write.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 5a0bbf917a32..f12cb31a41e5 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -621,11 +621,12 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, nfs_set_page_writeback(page); WARN_ON_ONCE(test_bit(PG_CLEAN, &req->wb_flags)); - ret = 0; + ret = req->wb_context->error; /* If there is a fatal error that covers this write, just exit */ - if (nfs_error_is_fatal_on_server(req->wb_context->error)) + if (nfs_error_is_fatal_on_server(ret)) goto out_launder; + ret = 0; if (!nfs_pageio_add_request(pgio, req)) { ret = pgio->pg_error; /* @@ -635,9 +636,9 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, nfs_context_set_write_error(req->wb_context, ret); if (nfs_error_is_fatal_on_server(ret)) goto out_launder; - } + } else + ret = -EAGAIN; nfs_redirty_request(req); - ret = -EAGAIN; } else nfs_add_stats(page_file_mapping(page)->host, NFSIOS_WRITEPAGES, 1); From 58d15ed1203f4d858c339ea4d7dafa94bd2a56d3 Mon Sep 17 00:00:00 2001 From: Ronnie Sahlberg Date: Tue, 29 Jan 2019 12:46:16 +1000 Subject: [PATCH 230/525] cifs: fix computation for MAX_SMB2_HDR_SIZE The size of the fixed part of the create response is 88 bytes not 56. Signed-off-by: Ronnie Sahlberg Signed-off-by: Steve French Reviewed-by: Pavel Shilovsky --- fs/cifs/smb2pdu.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 7a2d0a2255e6..e9cc6775df21 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -84,8 +84,8 @@ #define NUMBER_OF_SMB2_COMMANDS 0x0013 -/* 4 len + 52 transform hdr + 64 hdr + 56 create rsp */ -#define MAX_SMB2_HDR_SIZE 0x00b0 +/* 52 transform hdr + 64 hdr + 88 create rsp */ +#define MAX_SMB2_HDR_SIZE 204 #define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe) #define SMB2_TRANSFORM_PROTO_NUM cpu_to_le32(0x424d53fd) From c4627e66f73a28c5515b908c90c2bf7120086497 Mon Sep 17 00:00:00 2001 From: Ronnie Sahlberg Date: Tue, 29 Jan 2019 12:46:17 +1000 Subject: [PATCH 231/525] cifs: limit amount of data we request for xattrs to CIFSMaxBufSize minus the various headers and blobs that will be part of the reply. or else we might trigger a session reconnect. Signed-off-by: Ronnie Sahlberg Signed-off-by: Steve French Reviewed-by: Pavel Shilovsky --- fs/cifs/smb2ops.c | 4 +++- fs/cifs/smb2pdu.h | 15 +++++++++++++-- 2 files changed, 16 insertions(+), 3 deletions(-) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 153238fc4fa9..6f96e2292856 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -866,7 +866,9 @@ smb2_query_eas(const unsigned int xid, struct cifs_tcon *tcon, FILE_READ_EA, FILE_FULL_EA_INFORMATION, SMB2_O_INFO_FILE, - SMB2_MAX_EA_BUF, + CIFSMaxBufSize - + MAX_SMB2_CREATE_RESPONSE_SIZE - + MAX_SMB2_CLOSE_RESPONSE_SIZE, &rsp_iov, &buftype, cifs_sb); if (rc) { /* diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index e9cc6775df21..538e2299805f 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -85,6 +85,7 @@ #define NUMBER_OF_SMB2_COMMANDS 0x0013 /* 52 transform hdr + 64 hdr + 88 create rsp */ +#define SMB2_TRANSFORM_HEADER_SIZE 52 #define MAX_SMB2_HDR_SIZE 204 #define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe) @@ -648,6 +649,13 @@ struct smb2_create_req { __u8 Buffer[0]; } __packed; +/* + * Maximum size of a SMB2_CREATE response is 64 (smb2 header) + + * 88 (fixed part of create response) + 520 (path) + 150 (contexts) + + * 2 bytes of padding. + */ +#define MAX_SMB2_CREATE_RESPONSE_SIZE 824 + struct smb2_create_rsp { struct smb2_sync_hdr sync_hdr; __le16 StructureSize; /* Must be 89 */ @@ -996,6 +1004,11 @@ struct smb2_close_req { __u64 VolatileFileId; /* opaque endianness */ } __packed; +/* + * Maximum size of a SMB2_CLOSE response is 64 (smb2 header) + 60 (data) + */ +#define MAX_SMB2_CLOSE_RESPONSE_SIZE 124 + struct smb2_close_rsp { struct smb2_sync_hdr sync_hdr; __le16 StructureSize; /* 60 */ @@ -1398,8 +1411,6 @@ struct smb2_file_link_info { /* encoding of request for level 11 */ char FileName[0]; /* Name to be assigned to new link */ } __packed; /* level 11 Set */ -#define SMB2_MAX_EA_BUF 65536 - struct smb2_file_full_ea_info { /* encoding of response for level 15 */ __le32 next_entry_offset; __u8 flags; From 9bda8723da2d55b1de833b98cf802b88006e5b69 Mon Sep 17 00:00:00 2001 From: Pavel Shilovsky Date: Wed, 23 Jan 2019 17:12:09 -0800 Subject: [PATCH 232/525] CIFS: Fix possible oops and memory leaks in async IO Allocation of a page array for non-cached IO was separated from allocation of rdata and wdata structures and this introduced memory leaks and a possible null pointer dereference. This patch fixes these problems. Cc: Signed-off-by: Pavel Shilovsky Signed-off-by: Steve French --- fs/cifs/file.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 2c7689f3998d..659ce1b92c44 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2696,6 +2696,7 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from, rc = cifs_write_allocate_pages(wdata->pages, nr_pages); if (rc) { + kvfree(wdata->pages); kfree(wdata); add_credits_and_wake_if(server, credits, 0); break; @@ -2707,6 +2708,7 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from, if (rc) { for (i = 0; i < nr_pages; i++) put_page(wdata->pages[i]); + kvfree(wdata->pages); kfree(wdata); add_credits_and_wake_if(server, credits, 0); break; @@ -3386,8 +3388,12 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file, } rc = cifs_read_allocate_pages(rdata, npages); - if (rc) - goto error; + if (rc) { + kvfree(rdata->pages); + kfree(rdata); + add_credits_and_wake_if(server, credits, 0); + break; + } rdata->tailsz = PAGE_SIZE; } @@ -3407,7 +3413,6 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file, if (!rdata->cfile->invalidHandle || !(rc = cifs_reopen_file(rdata->cfile, true))) rc = server->ops->async_readv(rdata); -error: if (rc) { add_credits_and_wake_if(server, rdata->credits, 0); kref_put(&rdata->refcount, From 7d42e72fe8ee5ab70b1af843dd7d8615e6fb0abe Mon Sep 17 00:00:00 2001 From: Pavel Shilovsky Date: Fri, 25 Jan 2019 11:38:53 -0800 Subject: [PATCH 233/525] CIFS: Fix trace command logging for SMB2 reads and writes Currently we log success once we send an async IO request to the server. Instead we need to analyse a response and then log success or failure for a particular command. Also fix argument list for read logging. Cc: # 4.18 Signed-off-by: Pavel Shilovsky Signed-off-by: Steve French --- fs/cifs/smb2pdu.c | 46 ++++++++++++++++++++++++++++++---------------- 1 file changed, 30 insertions(+), 16 deletions(-) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 2ff209ec4fab..4b5ab9c80cc3 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -3241,8 +3241,17 @@ smb2_readv_callback(struct mid_q_entry *mid) rdata->mr = NULL; } #endif - if (rdata->result) + if (rdata->result) { cifs_stats_fail_inc(tcon, SMB2_READ_HE); + trace_smb3_read_err(0 /* xid */, + rdata->cfile->fid.persistent_fid, + tcon->tid, tcon->ses->Suid, rdata->offset, + rdata->bytes, rdata->result); + } else + trace_smb3_read_done(0 /* xid */, + rdata->cfile->fid.persistent_fid, + tcon->tid, tcon->ses->Suid, + rdata->offset, rdata->got_bytes); queue_work(cifsiod_wq, &rdata->work); DeleteMidQEntry(mid); @@ -3317,13 +3326,11 @@ smb2_async_readv(struct cifs_readdata *rdata) if (rc) { kref_put(&rdata->refcount, cifs_readdata_release); cifs_stats_fail_inc(io_parms.tcon, SMB2_READ_HE); - trace_smb3_read_err(rc, 0 /* xid */, io_parms.persistent_fid, - io_parms.tcon->tid, io_parms.tcon->ses->Suid, - io_parms.offset, io_parms.length); - } else - trace_smb3_read_done(0 /* xid */, io_parms.persistent_fid, - io_parms.tcon->tid, io_parms.tcon->ses->Suid, - io_parms.offset, io_parms.length); + trace_smb3_read_err(0 /* xid */, io_parms.persistent_fid, + io_parms.tcon->tid, + io_parms.tcon->ses->Suid, + io_parms.offset, io_parms.length, rc); + } cifs_small_buf_release(buf); return rc; @@ -3367,10 +3374,11 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms, if (rc != -ENODATA) { cifs_stats_fail_inc(io_parms->tcon, SMB2_READ_HE); cifs_dbg(VFS, "Send error in read = %d\n", rc); + trace_smb3_read_err(xid, req->PersistentFileId, + io_parms->tcon->tid, ses->Suid, + io_parms->offset, io_parms->length, + rc); } - trace_smb3_read_err(rc, xid, req->PersistentFileId, - io_parms->tcon->tid, ses->Suid, - io_parms->offset, io_parms->length); free_rsp_buf(resp_buftype, rsp_iov.iov_base); return rc == -ENODATA ? 0 : rc; } else @@ -3459,8 +3467,17 @@ smb2_writev_callback(struct mid_q_entry *mid) wdata->mr = NULL; } #endif - if (wdata->result) + if (wdata->result) { cifs_stats_fail_inc(tcon, SMB2_WRITE_HE); + trace_smb3_write_err(0 /* no xid */, + wdata->cfile->fid.persistent_fid, + tcon->tid, tcon->ses->Suid, wdata->offset, + wdata->bytes, wdata->result); + } else + trace_smb3_write_done(0 /* no xid */, + wdata->cfile->fid.persistent_fid, + tcon->tid, tcon->ses->Suid, + wdata->offset, wdata->bytes); queue_work(cifsiod_wq, &wdata->work); DeleteMidQEntry(mid); @@ -3602,10 +3619,7 @@ smb2_async_writev(struct cifs_writedata *wdata, wdata->bytes, rc); kref_put(&wdata->refcount, release); cifs_stats_fail_inc(tcon, SMB2_WRITE_HE); - } else - trace_smb3_write_done(0 /* no xid */, req->PersistentFileId, - tcon->tid, tcon->ses->Suid, wdata->offset, - wdata->bytes); + } async_writev_out: cifs_small_buf_release(req); From 8e6e72aeceaaed5aeeb1cb43d3085de7ceb14f79 Mon Sep 17 00:00:00 2001 From: Pavel Shilovsky Date: Sat, 26 Jan 2019 12:21:32 -0800 Subject: [PATCH 234/525] CIFS: Do not count -ENODATA as failure for query directory Signed-off-by: Pavel Shilovsky Signed-off-by: Steve French CC: Stable --- fs/cifs/smb2pdu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 4b5ab9c80cc3..d858dc04fdc3 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -3845,8 +3845,8 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon, rsp->sync_hdr.Status == STATUS_NO_MORE_FILES) { srch_inf->endOfSearch = true; rc = 0; - } - cifs_stats_fail_inc(tcon, SMB2_QUERY_DIRECTORY_HE); + } else + cifs_stats_fail_inc(tcon, SMB2_QUERY_DIRECTORY_HE); goto qdir_exit; } From 082aaa8700415f6471ec9c5ef0c8307ca214989a Mon Sep 17 00:00:00 2001 From: Pavel Shilovsky Date: Fri, 18 Jan 2019 15:54:34 -0800 Subject: [PATCH 235/525] CIFS: Do not consider -ENODATA as stat failure for reads When doing reads beyound the end of a file the server returns error STATUS_END_OF_FILE error which is mapped to -ENODATA. Currently we report it as a failure which confuses read stats. Change it to not consider -ENODATA as failure for stat purposes. Signed-off-by: Pavel Shilovsky Signed-off-by: Steve French CC: Stable --- fs/cifs/smb2pdu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index d858dc04fdc3..ef52d6642431 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -3241,7 +3241,7 @@ smb2_readv_callback(struct mid_q_entry *mid) rdata->mr = NULL; } #endif - if (rdata->result) { + if (rdata->result && rdata->result != -ENODATA) { cifs_stats_fail_inc(tcon, SMB2_READ_HE); trace_smb3_read_err(0 /* xid */, rdata->cfile->fid.persistent_fid, From 81f5c6f5db37bf2360b64c304b27b8f499b48367 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 29 Jan 2019 16:38:16 -0800 Subject: [PATCH 236/525] bpf: btf: allow typedef func_proto Current implementation does not allow typedef func_proto. But it is actually allowed. -bash-4.4$ cat t.c typedef int (f) (int); f *g; -bash-4.4$ clang -O2 -g -c -target bpf t.c -Xclang -target-feature -Xclang +dwarfris -bash-4.4$ pahole -JV t.o File t.o: [1] PTR (anon) type_id=2 [2] TYPEDEF f type_id=3 [3] FUNC_PROTO (anon) return=4 args=(4 (anon)) [4] INT int size=4 bit_offset=0 nr_bits=32 encoding=SIGNED -bash-4.4$ This patch related btf verifier to allow such (typedef func_proto) patterns. Fixes: 2667a2626f4d ("bpf: btf: Add BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO") Acked-by: Martin KaFai Lau Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov --- kernel/bpf/btf.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index befe570be5ba..c57bd10340ed 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -1459,7 +1459,8 @@ static int btf_modifier_resolve(struct btf_verifier_env *env, /* "typedef void new_void", "const void"...etc */ if (!btf_type_is_void(next_type) && - !btf_type_is_fwd(next_type)) { + !btf_type_is_fwd(next_type) && + !btf_type_is_func_proto(next_type)) { btf_verifier_log_type(env, v->t, "Invalid type_id"); return -EINVAL; } From 32b750b925040565bbeff1fe2f7510e3dc71ce2e Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 29 Jan 2019 16:38:17 -0800 Subject: [PATCH 237/525] tools/bpf: fix test_btf for typedef func_proto case Fixed one test_btf raw test such that typedef func_proto is permitted now. Fixes: 78a2540e8945 ("tools/bpf: Add tests for BTF_KIND_FUNC_PROTO and BTF_KIND_FUNC") Acked-by: Martin KaFai Lau Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/test_btf.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index a0bd04befe87..91420fa83b08 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -1881,13 +1881,12 @@ static struct btf_raw_test raw_tests[] = { }, { - .descr = "func proto (CONST=>TYPEDEF=>FUNC_PROTO)", + .descr = "func proto (TYPEDEF=>FUNC_PROTO)", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */ - BTF_CONST_ENC(4), /* [3] */ - BTF_TYPEDEF_ENC(NAME_TBD, 5), /* [4] */ - BTF_FUNC_PROTO_ENC(0, 2), /* [5] */ + BTF_TYPEDEF_ENC(NAME_TBD, 4), /* [3] */ + BTF_FUNC_PROTO_ENC(0, 2), /* [4] */ BTF_FUNC_PROTO_ARG_ENC(0, 1), BTF_FUNC_PROTO_ARG_ENC(0, 2), BTF_END_RAW, @@ -1901,8 +1900,6 @@ static struct btf_raw_test raw_tests[] = { .key_type_id = 1, .value_type_id = 1, .max_entries = 4, - .btf_load_err = true, - .err_str = "Invalid type_id", }, { From 1575c083a78cc1137ad8bfa042d02eeb9dc86ef4 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 22 Jan 2019 13:57:19 -0600 Subject: [PATCH 238/525] tty: serial: 8250_mtk: Fix potential NULL pointer dereference There is a potential NULL pointer dereference in case devm_kzalloc() fails and returns NULL. Fix this by adding a NULL check on data->dma This bug was detected with the help of Coccinelle. Fixes: 85b5c1dd0456 ("serial: 8250-mtk: add uart DMA support") Signed-off-by: Gustavo A. R. Silva Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_mtk.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/tty/serial/8250/8250_mtk.c b/drivers/tty/serial/8250/8250_mtk.c index e2c407656fa6..c1fdbc0b6840 100644 --- a/drivers/tty/serial/8250/8250_mtk.c +++ b/drivers/tty/serial/8250/8250_mtk.c @@ -357,6 +357,9 @@ static int mtk8250_probe_of(struct platform_device *pdev, struct uart_port *p, if (dmacnt == 2) { data->dma = devm_kzalloc(&pdev->dev, sizeof(*data->dma), GFP_KERNEL); + if (!data->dma) + return -ENOMEM; + data->dma->fn = mtk8250_dma_filter; data->dma->rx_size = MTK_UART_RX_SIZE; data->dma->rxconf.src_maxburst = MTK_UART_RX_TRIGGER; From 824d17c57b0abbcb9128fb3f7327fae14761914b Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 24 Jan 2019 23:51:21 +0200 Subject: [PATCH 239/525] serial: 8250_pci: Make PCI class test non fatal As has been reported the National Instruments serial cards have broken PCI class. The commit 7d8905d06405 ("serial: 8250_pci: Enable device after we check black list") made the PCI class check mandatory for the case when device is listed in a quirk list. Make PCI class test non fatal to allow broken card be enumerated. Fixes: 7d8905d06405 ("serial: 8250_pci: Enable device after we check black list") Cc: stable Reported-by: Guan Yung Tseng Tested-by: Guan Yung Tseng Tested-by: KHUENY.Gerhard Signed-off-by: Andy Shevchenko Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_pci.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index f80a300b5d68..48bd694a5fa1 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -3420,6 +3420,11 @@ static int serial_pci_guess_board(struct pci_dev *dev, struct pciserial_board *board) { int num_iomem, num_port, first_port = -1, i; + int rc; + + rc = serial_pci_is_class_communication(dev); + if (rc) + return rc; /* * Should we try to make guesses for multiport serial devices later? @@ -3647,10 +3652,6 @@ pciserial_init_one(struct pci_dev *dev, const struct pci_device_id *ent) board = &pci_boards[ent->driver_data]; - rc = serial_pci_is_class_communication(dev); - if (rc) - return rc; - rc = serial_pci_is_blacklisted(dev); if (rc) return rc; From 4d95987a32db53f3beca76f8c4c8309ef6a5f192 Mon Sep 17 00:00:00 2001 From: Chris Brandt Date: Mon, 28 Jan 2019 13:25:56 -0500 Subject: [PATCH 240/525] serial: sh-sci: Do not free irqs that have already been freed Since IRQs might be muxed on some parts, we need to pay attention when we are freeing them. Otherwise we get the ugly WARNING "Trying to free already-free IRQ 20". Fixes: 628c534ae735 ("serial: sh-sci: Improve support for separate TEI and DRI interrupts") Cc: stable Signed-off-by: Chris Brandt Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/sh-sci.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 8df0fd824520..64bbeb7d7e0c 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -1921,7 +1921,7 @@ out_nomem: static void sci_free_irq(struct sci_port *port) { - int i; + int i, j; /* * Intentionally in reverse order so we iterate over the muxed @@ -1937,6 +1937,13 @@ static void sci_free_irq(struct sci_port *port) if (unlikely(irq < 0)) continue; + /* Check if already freed (irq was muxed) */ + for (j = 0; j < i; j++) + if (port->irqs[j] == irq) + j = i + 1; + if (j > i) + continue; + free_irq(port->irqs[i], port); kfree(port->irqstr[i]); From db4090920ba2d61a5827a23e441447926a02ffee Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 25 Jan 2019 20:10:15 +0000 Subject: [PATCH 241/525] ARM: iop32x/n2100: fix PCI IRQ mapping Booting 4.20 on a TheCUS N2100 results in a kernel oops while probing PCI, due to n2100_pci_map_irq() having been discarded during boot. Signed-off-by: Russell King Cc: stable@vger.kernel.org # 2.6.18+ Signed-off-by: Arnd Bergmann --- arch/arm/mach-iop32x/n2100.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/arm/mach-iop32x/n2100.c b/arch/arm/mach-iop32x/n2100.c index 3b73813c6b04..23e8c93515d4 100644 --- a/arch/arm/mach-iop32x/n2100.c +++ b/arch/arm/mach-iop32x/n2100.c @@ -75,8 +75,7 @@ void __init n2100_map_io(void) /* * N2100 PCI. */ -static int __init -n2100_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) +static int n2100_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { int irq; From 46edb8d1322c1763dd04e179992f8e9996085047 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 22 Jan 2019 11:35:25 +0000 Subject: [PATCH 242/525] firmware: arm_scmi: provide the mandatory device release callback The device/driver model clearly mandates that bus driver that discover and allocate the device must set the release callback. This callback will be used to free the device after all references have gone away. scmi bus driver is missing the obvious callback which will result in the following warning if the device is unregistered: Device 'scmi_dev.1' does not have a release() function, it is broken and must be fixed. See Documentation/kobject.txt. WARNING at drivers/base/core.c:922 device_release+0x8c/0xa0 Hardware name: ARM LTD Juno Development Platform BIOS EDK II Jan 21 2019 Workqueue: events deferred_probe_work_func pstate: 60000005 (nZCv daif -PAN -UAO) pc : device_release+0x8c/0xa0 lr : device_release+0x8c/0xa0 Call trace: device_release+0x8c/0xa0 kobject_put+0x8c/0x208 device_unregister+0x30/0x78 scmi_device_destroy+0x28/0x50 scmi_probe+0x354/0x5b0 platform_drv_probe+0x58/0xa8 really_probe+0x2c4/0x3e8 driver_probe_device+0x12c/0x148 __device_attach_driver+0xac/0x150 bus_for_each_drv+0x78/0xd8 __device_attach+0xe0/0x168 device_initial_probe+0x24/0x30 bus_probe_device+0xa0/0xa8 deferred_probe_work_func+0x8c/0xe0 process_one_work+0x1f0/0x478 worker_thread+0x22c/0x450 kthread+0x134/0x138 ret_from_fork+0x10/0x1c ---[ end trace 420bdb7f6af50937 ]--- Fix the issue by providing scmi_device_release callback. We have everything required for device release already in scmi_device_destroy, so we just need to move freeing of the device to scmi_device_release. Fixes: 933c504424a2 ("firmware: arm_scmi: add scmi protocol bus to enumerate protocol devices") Signed-off-by: Sudeep Holla Cc: stable@vger.kernel.org # 4.17+ Signed-off-by: Arnd Bergmann --- drivers/firmware/arm_scmi/bus.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c index 472c88ae1c0f..92f843eaf1e0 100644 --- a/drivers/firmware/arm_scmi/bus.c +++ b/drivers/firmware/arm_scmi/bus.c @@ -119,6 +119,11 @@ void scmi_driver_unregister(struct scmi_driver *driver) } EXPORT_SYMBOL_GPL(scmi_driver_unregister); +static void scmi_device_release(struct device *dev) +{ + kfree(to_scmi_dev(dev)); +} + struct scmi_device * scmi_device_create(struct device_node *np, struct device *parent, int protocol) { @@ -138,6 +143,7 @@ scmi_device_create(struct device_node *np, struct device *parent, int protocol) scmi_dev->dev.parent = parent; scmi_dev->dev.of_node = np; scmi_dev->dev.bus = &scmi_bus_type; + scmi_dev->dev.release = scmi_device_release; dev_set_name(&scmi_dev->dev, "scmi_dev.%d", id); retval = device_register(&scmi_dev->dev); @@ -156,9 +162,8 @@ free_mem: void scmi_device_destroy(struct scmi_device *scmi_dev) { scmi_handle_put(scmi_dev->handle); - device_unregister(&scmi_dev->dev); ida_simple_remove(&scmi_bus_id, scmi_dev->id); - kfree(scmi_dev); + device_unregister(&scmi_dev->dev); } void scmi_set_handle(struct scmi_device *scmi_dev) From d0f9f16788e15d9eb40f68b047732d49658c5a3a Mon Sep 17 00:00:00 2001 From: Marc Gonzalez Date: Wed, 16 Jan 2019 16:49:58 +0100 Subject: [PATCH 243/525] ARM: tango: Improve ARCH_MULTIPLATFORM compatibility Calling platform-specific code unconditionally blows up when running an ARCH_MULTIPLATFORM kernel on a different platform. Don't do it. Reported-by: Paolo Pisati Signed-off-by: Marc Gonzalez Acked-by: Pavel Machek Cc: stable@vger.kernel.org # v4.8+ Fixes: a30eceb7a59d ("ARM: tango: add Suspend-to-RAM support") Signed-off-by: Arnd Bergmann --- arch/arm/mach-tango/pm.c | 6 ++---- arch/arm/mach-tango/pm.h | 7 +++++++ arch/arm/mach-tango/setup.c | 2 ++ 3 files changed, 11 insertions(+), 4 deletions(-) create mode 100644 arch/arm/mach-tango/pm.h diff --git a/arch/arm/mach-tango/pm.c b/arch/arm/mach-tango/pm.c index 028e50c6383f..a32c3b631484 100644 --- a/arch/arm/mach-tango/pm.c +++ b/arch/arm/mach-tango/pm.c @@ -3,6 +3,7 @@ #include #include #include "smc.h" +#include "pm.h" static int tango_pm_powerdown(unsigned long arg) { @@ -24,10 +25,7 @@ static const struct platform_suspend_ops tango_pm_ops = { .valid = suspend_valid_only_mem, }; -static int __init tango_pm_init(void) +void __init tango_pm_init(void) { suspend_set_ops(&tango_pm_ops); - return 0; } - -late_initcall(tango_pm_init); diff --git a/arch/arm/mach-tango/pm.h b/arch/arm/mach-tango/pm.h new file mode 100644 index 000000000000..35ea705a0ee2 --- /dev/null +++ b/arch/arm/mach-tango/pm.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifdef CONFIG_SUSPEND +void __init tango_pm_init(void); +#else +#define tango_pm_init NULL +#endif diff --git a/arch/arm/mach-tango/setup.c b/arch/arm/mach-tango/setup.c index 677dd7b5efd9..824f90737b04 100644 --- a/arch/arm/mach-tango/setup.c +++ b/arch/arm/mach-tango/setup.c @@ -2,6 +2,7 @@ #include #include #include "smc.h" +#include "pm.h" static void tango_l2c_write(unsigned long val, unsigned int reg) { @@ -15,4 +16,5 @@ DT_MACHINE_START(TANGO_DT, "Sigma Tango DT") .dt_compat = tango_dt_compat, .l2c_aux_mask = ~0, .l2c_write_sec = tango_l2c_write, + .init_late = tango_pm_init, MACHINE_END From 0b053bbf07867c9942d706e70040398df59de54b Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Thu, 24 Jan 2019 11:18:48 +0100 Subject: [PATCH 244/525] MAINTAINERS: Add Andy and Darren as arch/x86/platform/ reviewers ... so that they can get CCed on platform patches. Signed-off-by: Borislav Petkov Acked-by: Andy Shevchenko Acked-by: Thomas Gleixner Cc: Darren Hart Cc: Andy Shevchenko Cc: x86@kernel.org Link: https://lkml.kernel.org/r/20190128113619.19025-1-bp@alien8.de --- MAINTAINERS | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 32d444476a90..a98a7325df8c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -16631,6 +16631,15 @@ S: Maintained F: drivers/platform/x86/ F: drivers/platform/olpc/ +X86 PLATFORM DRIVERS - ARCH +R: Darren Hart +R: Andy Shevchenko +L: platform-driver-x86@vger.kernel.org +L: x86@kernel.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/core +S: Maintained +F: arch/x86/platform + X86 VDSO M: Andy Lutomirski L: linux-kernel@vger.kernel.org From a1960e0f1639cb1f7a3d94521760fc73091f6640 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 30 Jan 2019 10:49:34 +0100 Subject: [PATCH 245/525] staging: speakup: fix tty-operation NULL derefs The send_xchar() and tiocmset() tty operations are optional. Add the missing sanity checks to prevent user-space triggerable NULL-pointer dereferences. Fixes: 6b9ad1c742bf ("staging: speakup: add send_xchar, tiocmset and input functionality for tty") Cc: stable # 4.13 Cc: Okash Khawaja Cc: Samuel Thibault Signed-off-by: Johan Hovold Reviewed-by: Samuel Thibault Signed-off-by: Greg Kroah-Hartman --- drivers/staging/speakup/spk_ttyio.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/staging/speakup/spk_ttyio.c b/drivers/staging/speakup/spk_ttyio.c index c92bbd05516e..005de0024dd4 100644 --- a/drivers/staging/speakup/spk_ttyio.c +++ b/drivers/staging/speakup/spk_ttyio.c @@ -265,7 +265,8 @@ static void spk_ttyio_send_xchar(char ch) return; } - speakup_tty->ops->send_xchar(speakup_tty, ch); + if (speakup_tty->ops->send_xchar) + speakup_tty->ops->send_xchar(speakup_tty, ch); mutex_unlock(&speakup_tty_mutex); } @@ -277,7 +278,8 @@ static void spk_ttyio_tiocmset(unsigned int set, unsigned int clear) return; } - speakup_tty->ops->tiocmset(speakup_tty, set, clear); + if (speakup_tty->ops->tiocmset) + speakup_tty->ops->tiocmset(speakup_tty, set, clear); mutex_unlock(&speakup_tty_mutex); } From 37ea7b630ae5cdea4e8ff381d9d23abfef5939e6 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 30 Jan 2019 12:37:35 +0100 Subject: [PATCH 246/525] debugfs: debugfs_lookup() should return NULL if not found Lots of callers of debugfs_lookup() were just checking NULL to see if the file/directory was found or not. By changing this in ff9fb72bc077 ("debugfs: return error values, not NULL") we caused some subsystems to easily crash. Fixes: ff9fb72bc077 ("debugfs: return error values, not NULL") Reported-by: syzbot+b382ba6a802a3d242790@syzkaller.appspotmail.com Reported-by: Tetsuo Handa Cc: Omar Sandoval Cc: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- fs/debugfs/inode.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index b16f8035b1af..29c68c5d44d5 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -254,8 +254,8 @@ MODULE_ALIAS_FS("debugfs"); * @parent: a pointer to the parent dentry of the file. * * This function will return a pointer to a dentry if it succeeds. If the file - * doesn't exist or an error occurs, %ERR_PTR(-ERROR) will be returned. The - * returned dentry must be passed to dput() when it is no longer needed. + * doesn't exist or an error occurs, %NULL will be returned. The returned + * dentry must be passed to dput() when it is no longer needed. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. @@ -265,17 +265,17 @@ struct dentry *debugfs_lookup(const char *name, struct dentry *parent) struct dentry *dentry; if (IS_ERR(parent)) - return parent; + return NULL; if (!parent) parent = debugfs_mount->mnt_root; dentry = lookup_one_len_unlocked(name, parent, strlen(name)); if (IS_ERR(dentry)) - return dentry; + return NULL; if (!d_really_is_positive(dentry)) { dput(dentry); - return ERR_PTR(-EINVAL); + return NULL; } return dentry; } From 75abec73de65a86a23019ee7a3569220ee344f37 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 17 Jan 2019 12:48:54 +0100 Subject: [PATCH 247/525] selftests: add binderfs selftests This adds the promised selftest for binderfs. It will verify the following things: - binderfs mounting works - binder device allocation works - performing a binder ioctl() request through a binderfs device works - binder device removal works - binder-control removal fails - binderfs unmounting works The tests are performed both privileged and unprivileged. The latter verifies that binderfs behaves correctly in user namespaces. Cc: Todd Kjos Signed-off-by: Christian Brauner Acked-by: Shuah Khan Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/Makefile | 1 + .../selftests/filesystems/binderfs/.gitignore | 1 + .../selftests/filesystems/binderfs/Makefile | 6 + .../filesystems/binderfs/binderfs_test.c | 275 ++++++++++++++++++ .../selftests/filesystems/binderfs/config | 3 + 5 files changed, 286 insertions(+) create mode 100644 tools/testing/selftests/filesystems/binderfs/.gitignore create mode 100644 tools/testing/selftests/filesystems/binderfs/Makefile create mode 100644 tools/testing/selftests/filesystems/binderfs/binderfs_test.c create mode 100644 tools/testing/selftests/filesystems/binderfs/config diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 1a2bd15c5b6e..400ee81a3043 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -10,6 +10,7 @@ TARGETS += drivers/dma-buf TARGETS += efivarfs TARGETS += exec TARGETS += filesystems +TARGETS += filesystems/binderfs TARGETS += firmware TARGETS += ftrace TARGETS += futex diff --git a/tools/testing/selftests/filesystems/binderfs/.gitignore b/tools/testing/selftests/filesystems/binderfs/.gitignore new file mode 100644 index 000000000000..8a5d9bf63dd4 --- /dev/null +++ b/tools/testing/selftests/filesystems/binderfs/.gitignore @@ -0,0 +1 @@ +binderfs_test diff --git a/tools/testing/selftests/filesystems/binderfs/Makefile b/tools/testing/selftests/filesystems/binderfs/Makefile new file mode 100644 index 000000000000..58cb659b56b4 --- /dev/null +++ b/tools/testing/selftests/filesystems/binderfs/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 + +CFLAGS += -I../../../../../usr/include/ +TEST_GEN_PROGS := binderfs_test + +include ../../lib.mk diff --git a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c new file mode 100644 index 000000000000..8c2ed962e1c7 --- /dev/null +++ b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c @@ -0,0 +1,275 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "../../kselftest.h" + +static ssize_t write_nointr(int fd, const void *buf, size_t count) +{ + ssize_t ret; +again: + ret = write(fd, buf, count); + if (ret < 0 && errno == EINTR) + goto again; + + return ret; +} + +static void write_to_file(const char *filename, const void *buf, size_t count, + int allowed_errno) +{ + int fd, saved_errno; + ssize_t ret; + + fd = open(filename, O_WRONLY | O_CLOEXEC); + if (fd < 0) + ksft_exit_fail_msg("%s - Failed to open file %s\n", + strerror(errno), filename); + + ret = write_nointr(fd, buf, count); + if (ret < 0) { + if (allowed_errno && (errno == allowed_errno)) { + close(fd); + return; + } + + goto on_error; + } + + if ((size_t)ret != count) + goto on_error; + + close(fd); + return; + +on_error: + saved_errno = errno; + close(fd); + errno = saved_errno; + + if (ret < 0) + ksft_exit_fail_msg("%s - Failed to write to file %s\n", + strerror(errno), filename); + + ksft_exit_fail_msg("Failed to write to file %s\n", filename); +} + +static void change_to_userns(void) +{ + int ret; + uid_t uid; + gid_t gid; + /* {g,u}id_map files only allow a max of 4096 bytes written to them */ + char idmap[4096]; + + uid = getuid(); + gid = getgid(); + + ret = unshare(CLONE_NEWUSER); + if (ret < 0) + ksft_exit_fail_msg("%s - Failed to unshare user namespace\n", + strerror(errno)); + + write_to_file("/proc/self/setgroups", "deny", strlen("deny"), ENOENT); + + ret = snprintf(idmap, sizeof(idmap), "0 %d 1", uid); + if (ret < 0 || (size_t)ret >= sizeof(idmap)) + ksft_exit_fail_msg("%s - Failed to prepare uid mapping\n", + strerror(errno)); + + write_to_file("/proc/self/uid_map", idmap, strlen(idmap), 0); + + ret = snprintf(idmap, sizeof(idmap), "0 %d 1", gid); + if (ret < 0 || (size_t)ret >= sizeof(idmap)) + ksft_exit_fail_msg("%s - Failed to prepare uid mapping\n", + strerror(errno)); + + write_to_file("/proc/self/gid_map", idmap, strlen(idmap), 0); + + ret = setgid(0); + if (ret) + ksft_exit_fail_msg("%s - Failed to setgid(0)\n", + strerror(errno)); + + ret = setuid(0); + if (ret) + ksft_exit_fail_msg("%s - Failed to setgid(0)\n", + strerror(errno)); +} + +static void change_to_mountns(void) +{ + int ret; + + ret = unshare(CLONE_NEWNS); + if (ret < 0) + ksft_exit_fail_msg("%s - Failed to unshare mount namespace\n", + strerror(errno)); + + ret = mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0); + if (ret < 0) + ksft_exit_fail_msg("%s - Failed to mount / as private\n", + strerror(errno)); +} + +static void rmdir_protect_errno(const char *dir) +{ + int saved_errno = errno; + (void)rmdir(dir); + errno = saved_errno; +} + +static void __do_binderfs_test(void) +{ + int fd, ret, saved_errno; + size_t len; + ssize_t wret; + bool keep = false; + struct binderfs_device device = { 0 }; + struct binder_version version = { 0 }; + + change_to_mountns(); + + ret = mkdir("/dev/binderfs", 0755); + if (ret < 0) { + if (errno != EEXIST) + ksft_exit_fail_msg( + "%s - Failed to create binderfs mountpoint\n", + strerror(errno)); + + keep = true; + } + + ret = mount(NULL, "/dev/binderfs", "binder", 0, 0); + if (ret < 0) { + if (errno != ENODEV) + ksft_exit_fail_msg("%s - Failed to mount binderfs\n", + strerror(errno)); + + keep ? : rmdir_protect_errno("/dev/binderfs"); + ksft_exit_skip( + "The Android binderfs filesystem is not available\n"); + } + + /* binderfs mount test passed */ + ksft_inc_pass_cnt(); + + memcpy(device.name, "my-binder", strlen("my-binder")); + + fd = open("/dev/binderfs/binder-control", O_RDONLY | O_CLOEXEC); + if (fd < 0) + ksft_exit_fail_msg( + "%s - Failed to open binder-control device\n", + strerror(errno)); + + ret = ioctl(fd, BINDER_CTL_ADD, &device); + saved_errno = errno; + close(fd); + errno = saved_errno; + if (ret < 0) { + keep ? : rmdir_protect_errno("/dev/binderfs"); + ksft_exit_fail_msg( + "%s - Failed to allocate new binder device\n", + strerror(errno)); + } + + ksft_print_msg( + "Allocated new binder device with major %d, minor %d, and name %s\n", + device.major, device.minor, device.name); + + /* binder device allocation test passed */ + ksft_inc_pass_cnt(); + + fd = open("/dev/binderfs/my-binder", O_CLOEXEC | O_RDONLY); + if (fd < 0) { + keep ? : rmdir_protect_errno("/dev/binderfs"); + ksft_exit_fail_msg("%s - Failed to open my-binder device\n", + strerror(errno)); + } + + ret = ioctl(fd, BINDER_VERSION, &version); + saved_errno = errno; + close(fd); + errno = saved_errno; + if (ret < 0) { + keep ? : rmdir_protect_errno("/dev/binderfs"); + ksft_exit_fail_msg( + "%s - Failed to open perform BINDER_VERSION request\n", + strerror(errno)); + } + + ksft_print_msg("Detected binder version: %d\n", + version.protocol_version); + + /* binder transaction with binderfs binder device passed */ + ksft_inc_pass_cnt(); + + ret = unlink("/dev/binderfs/my-binder"); + if (ret < 0) { + keep ? : rmdir_protect_errno("/dev/binderfs"); + ksft_exit_fail_msg("%s - Failed to delete binder device\n", + strerror(errno)); + } + + /* binder device removal passed */ + ksft_inc_pass_cnt(); + + ret = unlink("/dev/binderfs/binder-control"); + if (!ret) { + keep ? : rmdir_protect_errno("/dev/binderfs"); + ksft_exit_fail_msg("Managed to delete binder-control device\n"); + } else if (errno != EPERM) { + keep ? : rmdir_protect_errno("/dev/binderfs"); + ksft_exit_fail_msg( + "%s - Failed to delete binder-control device but exited with unexpected error code\n", + strerror(errno)); + } + + /* binder-control device removal failed as expected */ + ksft_inc_xfail_cnt(); + +on_error: + ret = umount2("/dev/binderfs", MNT_DETACH); + keep ?: rmdir_protect_errno("/dev/binderfs"); + if (ret < 0) + ksft_exit_fail_msg("%s - Failed to unmount binderfs\n", + strerror(errno)); + + /* binderfs unmount test passed */ + ksft_inc_pass_cnt(); +} + +static void binderfs_test_privileged() +{ + if (geteuid() != 0) + ksft_print_msg( + "Tests are not run as root. Skipping privileged tests\n"); + else + __do_binderfs_test(); +} + +static void binderfs_test_unprivileged() +{ + change_to_userns(); + __do_binderfs_test(); +} + +int main(int argc, char *argv[]) +{ + binderfs_test_privileged(); + binderfs_test_unprivileged(); + ksft_exit_pass(); +} diff --git a/tools/testing/selftests/filesystems/binderfs/config b/tools/testing/selftests/filesystems/binderfs/config new file mode 100644 index 000000000000..02dd6cc9cf99 --- /dev/null +++ b/tools/testing/selftests/filesystems/binderfs/config @@ -0,0 +1,3 @@ +CONFIG_ANDROID=y +CONFIG_ANDROID_BINDERFS=y +CONFIG_ANDROID_BINDER_IPC=y From 793c8232937610ae00bc174b87d7fc324346eaea Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Sat, 26 Jan 2019 11:23:20 +0100 Subject: [PATCH 248/525] binder: fix CONFIG_ANDROID_BINDER_DEVICES Several users have tried to only rely on binderfs to provide binder devices and set CONFIG_ANDROID_BINDER_DEVICES="" empty. This is a great use-case of binderfs and one that was always intended to work. However, this is currently not possible since setting CONFIG_ANDROID_BINDER_DEVICES="" emtpy will simply panic the kernel: kobject: (00000000028c2f79): attempted to be registered with empty name! WARNING: CPU: 7 PID: 1703 at lib/kobject.c:228 kobject_add_internal+0x288/0x2b0 Modules linked in: binder_linux(+) bridge stp llc ipmi_ssif gpio_ich dcdbas coretemp kvm_intel kvm irqbypass serio_raw input_leds lpc_ich i5100_edac mac_hid ipmi_si ipmi_devintf ipmi_msghandler sch_fq_codel ib_i CPU: 7 PID: 1703 Comm: modprobe Not tainted 5.0.0-rc2-brauner-binderfs #263 Hardware name: Dell DCS XS24-SC2 /XS24-SC2 , BIOS S59_3C20 04/07/2011 RIP: 0010:kobject_add_internal+0x288/0x2b0 Code: 12 95 48 c7 c7 78 63 3b 95 e8 77 35 71 ff e9 91 fe ff ff 0f 0b eb a7 0f 0b eb 9a 48 89 de 48 c7 c7 00 63 3b 95 e8 f8 95 6a ff <0f> 0b 41 bc ea ff ff ff e9 6d fe ff ff 41 bc fe ff ff ff e9 62 fe RSP: 0018:ffff973f84237a30 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffff8b53e2472010 RCX: 0000000000000006 RDX: 0000000000000007 RSI: 0000000000000086 RDI: ffff8b53edbd63a0 RBP: ffff973f84237a60 R08: 0000000000000342 R09: 0000000000000004 R10: ffff973f84237af0 R11: 0000000000000001 R12: 0000000000000000 R13: ffff8b53e9f1a1e0 R14: 00000000e9f1a1e0 R15: 0000000000a00037 FS: 00007fbac36f7540(0000) GS:ffff8b53edbc0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fbac364cfa7 CR3: 00000004a6d48000 CR4: 00000000000406e0 Call Trace: kobject_add+0x71/0xd0 ? _cond_resched+0x19/0x40 ? mutex_lock+0x12/0x40 device_add+0x12e/0x6b0 device_create_groups_vargs+0xe4/0xf0 device_create_with_groups+0x3f/0x60 ? _cond_resched+0x19/0x40 misc_register+0x140/0x180 binder_init+0x1ed/0x2d4 [binder_linux] ? trace_event_define_fields_binder_transaction_fd_send+0x8e/0x8e [binder_linux] do_one_initcall+0x4a/0x1c9 ? _cond_resched+0x19/0x40 ? kmem_cache_alloc_trace+0x151/0x1c0 do_init_module+0x5f/0x216 load_module+0x223d/0x2b20 __do_sys_finit_module+0xfc/0x120 ? __do_sys_finit_module+0xfc/0x120 __x64_sys_finit_module+0x1a/0x20 do_syscall_64+0x5a/0x120 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7fbac3202839 Code: 00 f3 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 1f f6 2c 00 f7 d8 64 89 01 48 RSP: 002b:00007ffd1494a908 EFLAGS: 00000246 ORIG_RAX: 0000000000000139 RAX: ffffffffffffffda RBX: 000055b629ebec60 RCX: 00007fbac3202839 RDX: 0000000000000000 RSI: 000055b629c20d2e RDI: 0000000000000003 RBP: 000055b629c20d2e R08: 0000000000000000 R09: 000055b629ec2310 R10: 0000000000000003 R11: 0000000000000246 R12: 0000000000000000 R13: 000055b629ebed70 R14: 0000000000040000 R15: 000055b629ebec60 So check for the empty string since strsep() will otherwise return the emtpy string which will cause kobject_add_internal() to panic when trying to add a kobject with an emtpy name. Fixes: ac4812c5ffbb ("binder: Support multiple /dev instances") Cc: Martijn Coenen Signed-off-by: Christian Brauner Acked-by: Todd Kjos Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 30 ++++++++++++++++-------------- 1 file changed, 16 insertions(+), 14 deletions(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index cdfc87629efb..57cf259de600 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -5898,21 +5898,23 @@ static int __init binder_init(void) &transaction_log_fops); } - /* - * Copy the module_parameter string, because we don't want to - * tokenize it in-place. - */ - device_names = kstrdup(binder_devices_param, GFP_KERNEL); - if (!device_names) { - ret = -ENOMEM; - goto err_alloc_device_names_failed; - } + if (strcmp(binder_devices_param, "") != 0) { + /* + * Copy the module_parameter string, because we don't want to + * tokenize it in-place. + */ + device_names = kstrdup(binder_devices_param, GFP_KERNEL); + if (!device_names) { + ret = -ENOMEM; + goto err_alloc_device_names_failed; + } - device_tmp = device_names; - while ((device_name = strsep(&device_tmp, ","))) { - ret = init_binder_device(device_name); - if (ret) - goto err_init_binder_device_failed; + device_tmp = device_names; + while ((device_name = strsep(&device_tmp, ","))) { + ret = init_binder_device(device_name); + if (ret) + goto err_init_binder_device_failed; + } } return ret; From da8ddba566ff0a883237dbc8c5dadef1ca769e19 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 23 Jan 2019 12:41:15 +0100 Subject: [PATCH 249/525] binderfs: respect limit on binder control creation We currently adhere to the reserved devices limit when creating new binderfs devices in binderfs instances not located in the inital ipc namespace. But it is still possible to rob the host instances of their 4 reserved devices by creating the maximum allowed number of devices in a single binderfs instance located in a non-initial ipc namespace and then mounting 4 separate binderfs instances in non-initial ipc namespaces. That happens because the limit is currently not respected for the creation of the initial binder-control device node. Block this nonsense by performing the same check in binderfs_binder_ctl_create() that we perform in binderfs_binder_device_create(). Fixes: 36bdf3cae09d ("binderfs: reserve devices for initial mount") Signed-off-by: Christian Brauner Signed-off-by: Greg Kroah-Hartman --- drivers/android/binderfs.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/android/binderfs.c b/drivers/android/binderfs.c index 6a2185eb66c5..7a550104a722 100644 --- a/drivers/android/binderfs.c +++ b/drivers/android/binderfs.c @@ -395,6 +395,11 @@ static int binderfs_binder_ctl_create(struct super_block *sb) struct inode *inode = NULL; struct dentry *root = sb->s_root; struct binderfs_info *info = sb->s_fs_info; +#if defined(CONFIG_IPC_NS) + bool use_reserve = (info->ipc_ns == &init_ipc_ns); +#else + bool use_reserve = true; +#endif device = kzalloc(sizeof(*device), GFP_KERNEL); if (!device) @@ -413,7 +418,10 @@ static int binderfs_binder_ctl_create(struct super_block *sb) /* Reserve a new minor number for the new device. */ mutex_lock(&binderfs_minors_mutex); - minor = ida_alloc_max(&binderfs_minors, BINDERFS_MAX_MINOR, GFP_KERNEL); + minor = ida_alloc_max(&binderfs_minors, + use_reserve ? BINDERFS_MAX_MINOR : + BINDERFS_MAX_MINOR_CAPPED, + GFP_KERNEL); mutex_unlock(&binderfs_minors_mutex); if (minor < 0) { ret = minor; From efe814e90b98aed6d655b5a4092b9114b8b26e42 Mon Sep 17 00:00:00 2001 From: Tomas Winkler Date: Thu, 24 Jan 2019 14:45:02 +0200 Subject: [PATCH 250/525] mei: me: add ice lake point device id. Add icelake mei device id. Cc: Signed-off-by: Tomas Winkler Signed-off-by: Greg Kroah-Hartman --- drivers/misc/mei/hw-me-regs.h | 2 ++ drivers/misc/mei/pci-me.c | 2 ++ 2 files changed, 4 insertions(+) diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h index 23739a60517f..bb1ee9834a02 100644 --- a/drivers/misc/mei/hw-me-regs.h +++ b/drivers/misc/mei/hw-me-regs.h @@ -139,6 +139,8 @@ #define MEI_DEV_ID_CNP_H 0xA360 /* Cannon Point H */ #define MEI_DEV_ID_CNP_H_4 0xA364 /* Cannon Point H 4 (iTouch) */ +#define MEI_DEV_ID_ICP_LP 0x34E0 /* Ice Lake Point LP */ + /* * MEI HW Section */ diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index e89497f858ae..3ab946ad3257 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -105,6 +105,8 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_H, MEI_ME_PCH12_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_H_4, MEI_ME_PCH8_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ICP_LP, MEI_ME_PCH12_CFG)}, + /* required last entry */ {0, } }; From c4a46acf1db3ce547d290c29e55b3476c78dd76c Mon Sep 17 00:00:00 2001 From: Tomas Winkler Date: Thu, 24 Jan 2019 14:45:03 +0200 Subject: [PATCH 251/525] samples: mei: use /dev/mei0 instead of /dev/mei The device was moved from misc device to character devices to support multiple mei devices. Cc: #v4.9+ Signed-off-by: Tomas Winkler Signed-off-by: Greg Kroah-Hartman --- samples/mei/mei-amt-version.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/samples/mei/mei-amt-version.c b/samples/mei/mei-amt-version.c index 33e67bd1dc34..32234481ad7d 100644 --- a/samples/mei/mei-amt-version.c +++ b/samples/mei/mei-amt-version.c @@ -117,7 +117,7 @@ static bool mei_init(struct mei *me, const uuid_le *guid, me->verbose = verbose; - me->fd = open("/dev/mei", O_RDWR); + me->fd = open("/dev/mei0", O_RDWR); if (me->fd == -1) { mei_err(me, "Cannot establish a handle to the Intel MEI driver\n"); goto err; From cee4c4d63ba7b0df9b2d2a6724c41b2a260d72ec Mon Sep 17 00:00:00 2001 From: Alexander Usyskin Date: Wed, 30 Jan 2019 10:12:26 +0200 Subject: [PATCH 252/525] mei: free read cb on ctrl_wr list flush There is a little window during disconnection flow when read cb is moved between lists and may be not freed. Remove moving read cbs explicitly during flash fixes this memory leak. Signed-off-by: Alexander Usyskin Signed-off-by: Tomas Winkler Signed-off-by: Greg Kroah-Hartman --- drivers/misc/mei/client.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c index 1fc8ea0f519b..ca4c9cc218a2 100644 --- a/drivers/misc/mei/client.c +++ b/drivers/misc/mei/client.c @@ -401,8 +401,11 @@ static void mei_io_list_flush_cl(struct list_head *head, struct mei_cl_cb *cb, *next; list_for_each_entry_safe(cb, next, head, list) { - if (cl == cb->cl) + if (cl == cb->cl) { list_del_init(&cb->list); + if (cb->fop_type == MEI_FOP_READ) + mei_io_cb_free(cb); + } } } From 49230b49c4398765feba809ac27ae09562cbead1 Mon Sep 17 00:00:00 2001 From: Aaro Koskinen Date: Sun, 27 Jan 2019 21:54:50 +0200 Subject: [PATCH 253/525] staging: octeon: fix broken phylib usage Commit 2b3e88ea6528 ("net: phy: improve phy state checking") added checks for phylib usage, and this triggers with OCTEON ethernet and results in broken networking. Fix by replacing phy_start_aneg() with phy_start(). Fixes: 2b3e88ea6528 ("net: phy: improve phy state checking") Signed-off-by: Aaro Koskinen Signed-off-by: Greg Kroah-Hartman --- drivers/staging/octeon/ethernet-mdio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/octeon/ethernet-mdio.c b/drivers/staging/octeon/ethernet-mdio.c index 2848fa71a33d..d6248eecf123 100644 --- a/drivers/staging/octeon/ethernet-mdio.c +++ b/drivers/staging/octeon/ethernet-mdio.c @@ -170,7 +170,7 @@ int cvm_oct_phy_setup_device(struct net_device *dev) return -ENODEV; priv->last_link = 0; - phy_start_aneg(phydev); + phy_start(phydev); return 0; no_phy: From d4104c5e783f5d053b97268fb92001d785de7dd5 Mon Sep 17 00:00:00 2001 From: Gao Xiang Date: Tue, 29 Jan 2019 23:55:40 +0800 Subject: [PATCH 254/525] staging: erofs: keep corrupted fs from crashing kernel in erofs_namei() As Al pointed out, " ... and while we are at it, what happens to unsigned int nameoff = le16_to_cpu(de[mid].nameoff); unsigned int matched = min(startprfx, endprfx); struct qstr dname = QSTR_INIT(data + nameoff, unlikely(mid >= ndirents - 1) ? maxsize - nameoff : le16_to_cpu(de[mid + 1].nameoff) - nameoff); /* string comparison without already matched prefix */ int ret = dirnamecmp(name, &dname, &matched); if le16_to_cpu(de[...].nameoff) is not monotonically increasing? I.e. what's to prevent e.g. (unsigned)-1 ending up in dname.len? Corrupted fs image shouldn't oops the kernel.. " Revisit the related lookup flow to address the issue. Fixes: d72d1ce60174 ("staging: erofs: add namei functions") Cc: # 4.19+ Suggested-by: Al Viro Signed-off-by: Gao Xiang Signed-off-by: Greg Kroah-Hartman --- drivers/staging/erofs/namei.c | 167 ++++++++++++++++++---------------- 1 file changed, 89 insertions(+), 78 deletions(-) diff --git a/drivers/staging/erofs/namei.c b/drivers/staging/erofs/namei.c index 5596c52e246d..a1300c420e63 100644 --- a/drivers/staging/erofs/namei.c +++ b/drivers/staging/erofs/namei.c @@ -15,74 +15,76 @@ #include -/* based on the value of qn->len is accurate */ -static inline int dirnamecmp(struct qstr *qn, - struct qstr *qd, unsigned int *matched) +struct erofs_qstr { + const unsigned char *name; + const unsigned char *end; +}; + +/* based on the end of qn is accurate and it must have the trailing '\0' */ +static inline int dirnamecmp(const struct erofs_qstr *qn, + const struct erofs_qstr *qd, + unsigned int *matched) { - unsigned int i = *matched, len = min(qn->len, qd->len); -loop: - if (unlikely(i >= len)) { - *matched = i; - if (qn->len < qd->len) { - /* - * actually (qn->len == qd->len) - * when qd->name[i] == '\0' - */ - return qd->name[i] == '\0' ? 0 : -1; + unsigned int i = *matched; + + /* + * on-disk error, let's only BUG_ON in the debugging mode. + * otherwise, it will return 1 to just skip the invalid name + * and go on (in consideration of the lookup performance). + */ + DBG_BUGON(qd->name > qd->end); + + /* qd could not have trailing '\0' */ + /* However it is absolutely safe if < qd->end */ + while (qd->name + i < qd->end && qd->name[i] != '\0') { + if (qn->name[i] != qd->name[i]) { + *matched = i; + return qn->name[i] > qd->name[i] ? 1 : -1; } - return (qn->len > qd->len); + ++i; } - - if (qn->name[i] != qd->name[i]) { - *matched = i; - return qn->name[i] > qd->name[i] ? 1 : -1; - } - - ++i; - goto loop; + *matched = i; + /* See comments in __d_alloc on the terminating NUL character */ + return qn->name[i] == '\0' ? 0 : 1; } -static struct erofs_dirent *find_target_dirent( - struct qstr *name, - u8 *data, int maxsize) +#define nameoff_from_disk(off, sz) (le16_to_cpu(off) & ((sz) - 1)) + +static struct erofs_dirent *find_target_dirent(struct erofs_qstr *name, + u8 *data, + unsigned int dirblksize, + const int ndirents) { - unsigned int ndirents, head, back; + int head, back; unsigned int startprfx, endprfx; struct erofs_dirent *const de = (struct erofs_dirent *)data; - /* make sure that maxsize is valid */ - BUG_ON(maxsize < sizeof(struct erofs_dirent)); - - ndirents = le16_to_cpu(de->nameoff) / sizeof(*de); - - /* corrupted dir (may be unnecessary...) */ - BUG_ON(!ndirents); - head = 0; back = ndirents - 1; startprfx = endprfx = 0; while (head <= back) { - unsigned int mid = head + (back - head) / 2; - unsigned int nameoff = le16_to_cpu(de[mid].nameoff); + const int mid = head + (back - head) / 2; + const int nameoff = nameoff_from_disk(de[mid].nameoff, + dirblksize); unsigned int matched = min(startprfx, endprfx); - - struct qstr dname = QSTR_INIT(data + nameoff, - unlikely(mid >= ndirents - 1) ? - maxsize - nameoff : - le16_to_cpu(de[mid + 1].nameoff) - nameoff); + struct erofs_qstr dname = { + .name = data + nameoff, + .end = unlikely(mid >= ndirents - 1) ? + data + dirblksize : + data + nameoff_from_disk(de[mid + 1].nameoff, + dirblksize) + }; /* string comparison without already matched prefix */ int ret = dirnamecmp(name, &dname, &matched); - if (unlikely(!ret)) + if (unlikely(!ret)) { return de + mid; - else if (ret > 0) { + } else if (ret > 0) { head = mid + 1; startprfx = matched; - } else if (unlikely(mid < 1)) /* fix "mid" overflow */ - break; - else { + } else { back = mid - 1; endprfx = matched; } @@ -91,12 +93,13 @@ static struct erofs_dirent *find_target_dirent( return ERR_PTR(-ENOENT); } -static struct page *find_target_block_classic( - struct inode *dir, - struct qstr *name, int *_diff) +static struct page *find_target_block_classic(struct inode *dir, + struct erofs_qstr *name, + int *_diff, + int *_ndirents) { unsigned int startprfx, endprfx; - unsigned int head, back; + int head, back; struct address_space *const mapping = dir->i_mapping; struct page *candidate = ERR_PTR(-ENOENT); @@ -105,33 +108,34 @@ static struct page *find_target_block_classic( back = inode_datablocks(dir) - 1; while (head <= back) { - unsigned int mid = head + (back - head) / 2; + const int mid = head + (back - head) / 2; struct page *page = read_mapping_page(mapping, mid, NULL); - if (IS_ERR(page)) { -exact_out: - if (!IS_ERR(candidate)) /* valid candidate */ - put_page(candidate); - return page; - } else { - int diff; - unsigned int ndirents, matched; - struct qstr dname; + if (!IS_ERR(page)) { struct erofs_dirent *de = kmap_atomic(page); - unsigned int nameoff = le16_to_cpu(de->nameoff); + const int nameoff = nameoff_from_disk(de->nameoff, + EROFS_BLKSIZ); + const int ndirents = nameoff / sizeof(*de); + int diff; + unsigned int matched; + struct erofs_qstr dname; - ndirents = nameoff / sizeof(*de); - - /* corrupted dir (should have one entry at least) */ - BUG_ON(!ndirents || nameoff > PAGE_SIZE); + if (unlikely(!ndirents)) { + DBG_BUGON(1); + put_page(page); + page = ERR_PTR(-EIO); + goto out; + } matched = min(startprfx, endprfx); dname.name = (u8 *)de + nameoff; - dname.len = ndirents == 1 ? - /* since the rest of the last page is 0 */ - EROFS_BLKSIZ - nameoff - : le16_to_cpu(de[1].nameoff) - nameoff; + if (ndirents == 1) + dname.end = (u8 *)de + EROFS_BLKSIZ; + else + dname.end = (u8 *)de + + nameoff_from_disk(de[1].nameoff, + EROFS_BLKSIZ); /* string comparison without already matched prefix */ diff = dirnamecmp(name, &dname, &matched); @@ -139,7 +143,7 @@ exact_out: if (unlikely(!diff)) { *_diff = 0; - goto exact_out; + goto out; } else if (diff > 0) { head = mid + 1; startprfx = matched; @@ -147,35 +151,42 @@ exact_out: if (likely(!IS_ERR(candidate))) put_page(candidate); candidate = page; + *_ndirents = ndirents; } else { put_page(page); - if (unlikely(mid < 1)) /* fix "mid" overflow */ - break; - back = mid - 1; endprfx = matched; } + continue; } +out: /* free if the candidate is valid */ + if (!IS_ERR(candidate)) + put_page(candidate); + return page; } *_diff = 1; return candidate; } int erofs_namei(struct inode *dir, - struct qstr *name, - erofs_nid_t *nid, unsigned int *d_type) + struct qstr *name, + erofs_nid_t *nid, unsigned int *d_type) { - int diff; + int diff, ndirents; struct page *page; u8 *data; struct erofs_dirent *de; + struct erofs_qstr qn; if (unlikely(!dir->i_size)) return -ENOENT; + qn.name = name->name; + qn.end = name->name + name->len; + diff = 1; - page = find_target_block_classic(dir, name, &diff); + page = find_target_block_classic(dir, &qn, &diff, &ndirents); if (unlikely(IS_ERR(page))) return PTR_ERR(page); @@ -184,7 +195,7 @@ int erofs_namei(struct inode *dir, /* the target page has been mapped */ de = likely(diff) ? /* since the rest of the last page is 0 */ - find_target_dirent(name, data, EROFS_BLKSIZ) : + find_target_dirent(&qn, data, EROFS_BLKSIZ, ndirents) : (struct erofs_dirent *)data; if (likely(!IS_ERR(de))) { From 5aa608348f86d90f05b16dec93963801e2dd4ef5 Mon Sep 17 00:00:00 2001 From: Vincent Whitchurch Date: Tue, 29 Jan 2019 11:22:07 +0100 Subject: [PATCH 255/525] mic: vop: Fix broken virtqueues VOP is broken in mainline since commit 1ce9e6055fa0a9043 ("virtio_ring: introduce packed ring support"); attempting to use the virtqueues leads to various kernel crashes. I'm testing it with my not-yet-merged loopback patches, but even the in-tree MIC hardware cannot work. The problem is not in the referenced commit per se, but is due to the following hack in vop_find_vq() which depends on the layout of private structures in other source files, which that commit happened to change: /* * To reassign the used ring here we are directly accessing * struct vring_virtqueue which is a private data structure * in virtio_ring.c. At the minimum, a BUILD_BUG_ON() in * vring_new_virtqueue() would ensure that * (&vq->vring == (struct vring *) (&vq->vq + 1)); */ vr = (struct vring *)(vq + 1); vr->used = used; Fix vop by using __vring_new_virtqueue() to create the needed vring layout from the start, instead of attempting to patch in the used ring later. __vring_new_virtqueue() was added way back in commit 2a2d1382fe9dcc ("virtio: Add improved queue allocation API") in order to address mic's usecase, according to the commit message. Fixes: 1ce9e6055fa0 ("virtio_ring: introduce packed ring support") Signed-off-by: Vincent Whitchurch Signed-off-by: Greg Kroah-Hartman --- drivers/misc/mic/vop/vop_main.c | 60 +++++++++++++++++++-------------- 1 file changed, 34 insertions(+), 26 deletions(-) diff --git a/drivers/misc/mic/vop/vop_main.c b/drivers/misc/mic/vop/vop_main.c index 2bfa3a903bf9..2bd57c2ca02b 100644 --- a/drivers/misc/mic/vop/vop_main.c +++ b/drivers/misc/mic/vop/vop_main.c @@ -283,6 +283,26 @@ static void vop_del_vqs(struct virtio_device *dev) vop_del_vq(vq, idx++); } +static struct virtqueue *vop_new_virtqueue(unsigned int index, + unsigned int num, + struct virtio_device *vdev, + bool context, + void *pages, + bool (*notify)(struct virtqueue *vq), + void (*callback)(struct virtqueue *vq), + const char *name, + void *used) +{ + bool weak_barriers = false; + struct vring vring; + + vring_init(&vring, num, pages, MIC_VIRTIO_RING_ALIGN); + vring.used = used; + + return __vring_new_virtqueue(index, vring, vdev, weak_barriers, context, + notify, callback, name); +} + /* * This routine will assign vring's allocated in host/io memory. Code in * virtio_ring.c however continues to access this io memory as if it were local @@ -302,7 +322,6 @@ static struct virtqueue *vop_find_vq(struct virtio_device *dev, struct _mic_vring_info __iomem *info; void *used; int vr_size, _vr_size, err, magic; - struct vring *vr; u8 type = ioread8(&vdev->desc->type); if (index >= ioread8(&vdev->desc->num_vq)) @@ -322,17 +341,7 @@ static struct virtqueue *vop_find_vq(struct virtio_device *dev, return ERR_PTR(-ENOMEM); vdev->vr[index] = va; memset_io(va, 0x0, _vr_size); - vq = vring_new_virtqueue( - index, - le16_to_cpu(config.num), MIC_VIRTIO_RING_ALIGN, - dev, - false, - ctx, - (void __force *)va, vop_notify, callback, name); - if (!vq) { - err = -ENOMEM; - goto unmap; - } + info = va + _vr_size; magic = ioread32(&info->magic); @@ -341,7 +350,6 @@ static struct virtqueue *vop_find_vq(struct virtio_device *dev, goto unmap; } - /* Allocate and reassign used ring now */ vdev->used_size[index] = PAGE_ALIGN(sizeof(__u16) * 3 + sizeof(struct vring_used_elem) * le16_to_cpu(config.num)); @@ -351,8 +359,17 @@ static struct virtqueue *vop_find_vq(struct virtio_device *dev, err = -ENOMEM; dev_err(_vop_dev(vdev), "%s %d err %d\n", __func__, __LINE__, err); - goto del_vq; + goto unmap; } + + vq = vop_new_virtqueue(index, le16_to_cpu(config.num), dev, ctx, + (void __force *)va, vop_notify, callback, + name, used); + if (!vq) { + err = -ENOMEM; + goto free_used; + } + vdev->used[index] = dma_map_single(&vpdev->dev, used, vdev->used_size[index], DMA_BIDIRECTIONAL); @@ -360,26 +377,17 @@ static struct virtqueue *vop_find_vq(struct virtio_device *dev, err = -ENOMEM; dev_err(_vop_dev(vdev), "%s %d err %d\n", __func__, __LINE__, err); - goto free_used; + goto del_vq; } writeq(vdev->used[index], &vqconfig->used_address); - /* - * To reassign the used ring here we are directly accessing - * struct vring_virtqueue which is a private data structure - * in virtio_ring.c. At the minimum, a BUILD_BUG_ON() in - * vring_new_virtqueue() would ensure that - * (&vq->vring == (struct vring *) (&vq->vq + 1)); - */ - vr = (struct vring *)(vq + 1); - vr->used = used; vq->priv = vdev; return vq; +del_vq: + vring_del_virtqueue(vq); free_used: free_pages((unsigned long)used, get_order(vdev->used_size[index])); -del_vq: - vring_del_virtqueue(vq); unmap: vpdev->hw_ops->iounmap(vpdev, vdev->vr[index]); return ERR_PTR(err); From c418fd6c01fbc5516a2cd1eaf1df1ec86869028a Mon Sep 17 00:00:00 2001 From: Paul Elder Date: Wed, 30 Jan 2019 08:13:21 -0600 Subject: [PATCH 256/525] usb: gadget: musb: fix short isoc packets with inventra dma Handling short packets (length < max packet size) in the Inventra DMA engine in the MUSB driver causes the MUSB DMA controller to hang. An example of a problem that is caused by this problem is when streaming video out of a UVC gadget, only the first video frame is transferred. For short packets (mode-0 or mode-1 DMA), MUSB_TXCSR_TXPKTRDY must be set manually by the driver. This was previously done in musb_g_tx (musb_gadget.c), but incorrectly (all csr flags were cleared, and only MUSB_TXCSR_MODE and MUSB_TXCSR_TXPKTRDY were set). Fixing that problem allows some requests to be transferred correctly, but multiple requests were often put together in one USB packet, and caused problems if the packet size was not a multiple of 4. Instead, set MUSB_TXCSR_TXPKTRDY in dma_controller_irq (musbhsdma.c), just like host mode transfers. This topic was originally tackled by Nicolas Boichat [0] [1] and is discussed further at [2] as part of his GSoC project [3]. [0] https://groups.google.com/forum/?hl=en#!topic/beagleboard-gsoc/k8Azwfp75CU [1] https://gitorious.org/beagleboard-usbsniffer/beagleboard-usbsniffer-kernel/commit/b0be3b6cc195ba732189b04f1d43ec843c3e54c9?p=beagleboard-usbsniffer:beagleboard-usbsniffer-kernel.git;a=patch;h=b0be3b6cc195ba732189b04f1d43ec843c3e54c9 [2] http://beagleboard-usbsniffer.blogspot.com/2010/07/musb-isochronous-transfers-fixed.html [3] http://elinux.org/BeagleBoard/GSoC/USBSniffer Fixes: 550a7375fe72 ("USB: Add MUSB and TUSB support") Signed-off-by: Paul Elder Signed-off-by: Bin Liu Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/usb/musb/musb_gadget.c | 13 +------------ drivers/usb/musb/musbhsdma.c | 21 +++++++++++---------- 2 files changed, 12 insertions(+), 22 deletions(-) diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c index eae8b1b1b45b..ffe462a657b1 100644 --- a/drivers/usb/musb/musb_gadget.c +++ b/drivers/usb/musb/musb_gadget.c @@ -452,13 +452,10 @@ void musb_g_tx(struct musb *musb, u8 epnum) } if (request) { - u8 is_dma = 0; - bool short_packet = false; trace_musb_req_tx(req); if (dma && (csr & MUSB_TXCSR_DMAENAB)) { - is_dma = 1; csr |= MUSB_TXCSR_P_WZC_BITS; csr &= ~(MUSB_TXCSR_DMAENAB | MUSB_TXCSR_P_UNDERRUN | MUSB_TXCSR_TXPKTRDY | MUSB_TXCSR_AUTOSET); @@ -476,16 +473,8 @@ void musb_g_tx(struct musb *musb, u8 epnum) */ if ((request->zero && request->length) && (request->length % musb_ep->packet_sz == 0) - && (request->actual == request->length)) - short_packet = true; + && (request->actual == request->length)) { - if ((musb_dma_inventra(musb) || musb_dma_ux500(musb)) && - (is_dma && (!dma->desired_mode || - (request->actual & - (musb_ep->packet_sz - 1))))) - short_packet = true; - - if (short_packet) { /* * On DMA completion, FIFO may not be * available yet... diff --git a/drivers/usb/musb/musbhsdma.c b/drivers/usb/musb/musbhsdma.c index a688f7f87829..5fc6825745f2 100644 --- a/drivers/usb/musb/musbhsdma.c +++ b/drivers/usb/musb/musbhsdma.c @@ -346,12 +346,10 @@ static irqreturn_t dma_controller_irq(int irq, void *private_data) channel->status = MUSB_DMA_STATUS_FREE; /* completed */ - if ((devctl & MUSB_DEVCTL_HM) - && (musb_channel->transmit) - && ((channel->desired_mode == 0) - || (channel->actual_len & - (musb_channel->max_packet_sz - 1))) - ) { + if (musb_channel->transmit && + (!channel->desired_mode || + (channel->actual_len % + musb_channel->max_packet_sz))) { u8 epnum = musb_channel->epnum; int offset = musb->io.ep_offset(epnum, MUSB_TXCSR); @@ -363,11 +361,14 @@ static irqreturn_t dma_controller_irq(int irq, void *private_data) */ musb_ep_select(mbase, epnum); txcsr = musb_readw(mbase, offset); - txcsr &= ~(MUSB_TXCSR_DMAENAB + if (channel->desired_mode == 1) { + txcsr &= ~(MUSB_TXCSR_DMAENAB | MUSB_TXCSR_AUTOSET); - musb_writew(mbase, offset, txcsr); - /* Send out the packet */ - txcsr &= ~MUSB_TXCSR_DMAMODE; + musb_writew(mbase, offset, txcsr); + /* Send out the packet */ + txcsr &= ~MUSB_TXCSR_DMAMODE; + txcsr |= MUSB_TXCSR_DMAENAB; + } txcsr |= MUSB_TXCSR_TXPKTRDY; musb_writew(mbase, offset, txcsr); } From 2e3c18d0ada16f145087b2687afcad1748c0827c Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Wed, 30 Jan 2019 22:21:45 +0900 Subject: [PATCH 257/525] block: pass no-op callback to INIT_WORK(). syzbot is hitting flush_work() warning caused by commit 4d43d395fed12463 ("workqueue: Try to catch flush_work() without INIT_WORK().") [1]. Although that commit did not expect INIT_WORK(NULL) case, calling flush_work() without setting a valid callback should be avoided anyway. Fix this problem by setting a no-op callback instead of NULL. [1] https://syzkaller.appspot.com/bug?id=e390366bc48bc82a7c668326e0663be3b91cbd29 Signed-off-by: Tetsuo Handa Reported-and-tested-by: syzbot Cc: Tejun Heo Signed-off-by: Jens Axboe --- block/blk-core.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/block/blk-core.c b/block/blk-core.c index 3c5f61ceeb67..6b78ec56a4f2 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -462,6 +462,10 @@ static void blk_rq_timed_out_timer(struct timer_list *t) kblockd_schedule_work(&q->timeout_work); } +static void blk_timeout_work(struct work_struct *work) +{ +} + /** * blk_alloc_queue_node - allocate a request queue * @gfp_mask: memory allocation flags @@ -505,7 +509,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) timer_setup(&q->backing_dev_info->laptop_mode_wb_timer, laptop_mode_timer_fn, 0); timer_setup(&q->timeout, blk_rq_timed_out_timer, 0); - INIT_WORK(&q->timeout_work, NULL); + INIT_WORK(&q->timeout_work, blk_timeout_work); INIT_LIST_HEAD(&q->icq_list); #ifdef CONFIG_BLK_CGROUP INIT_LIST_HEAD(&q->blkg_list); From 85bd6e61f34dffa8ec2dc75ff3c02ee7b2f1cbce Mon Sep 17 00:00:00 2001 From: Jianchao Wang Date: Wed, 30 Jan 2019 17:01:56 +0800 Subject: [PATCH 258/525] blk-mq: fix a hung issue when fsync Florian reported a io hung issue when fsync(). It should be triggered by following race condition. data + post flush a flush blk_flush_complete_seq case REQ_FSEQ_DATA blk_flush_queue_rq issued to driver blk_mq_dispatch_rq_list try to issue a flush req failed due to NON-NCQ command .queue_rq return BLK_STS_DEV_RESOURCE request completion req->end_io // doesn't check RESTART mq_flush_data_end_io case REQ_FSEQ_POSTFLUSH blk_kick_flush do nothing because previous flush has not been completed blk_mq_run_hw_queue insert rq to hctx->dispatch due to RESTART is still set, do nothing To fix this, replace the blk_mq_run_hw_queue in mq_flush_data_end_io with blk_mq_sched_restart to check and clear the RESTART flag. Fixes: bd166ef1 (blk-mq-sched: add framework for MQ capable IO schedulers) Reported-by: Florian Stecker Tested-by: Florian Stecker Signed-off-by: Jianchao Wang Signed-off-by: Jens Axboe --- block/blk-flush.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/blk-flush.c b/block/blk-flush.c index a3fc7191c694..6e0f2d97fc6d 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -335,7 +335,7 @@ static void mq_flush_data_end_io(struct request *rq, blk_status_t error) blk_flush_complete_seq(rq, fq, REQ_FSEQ_DATA, error); spin_unlock_irqrestore(&fq->mq_flush_lock, flags); - blk_mq_run_hw_queue(hctx, true); + blk_mq_sched_restart(hctx); } /** From 8950dcd83ae7d62bdc2a60507949acebd85399f2 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 24 Jan 2019 10:31:32 +0800 Subject: [PATCH 259/525] iommu/vt-d: Leave scalable mode default off Commit 765b6a98c1de3 ("iommu/vt-d: Enumerate the scalable mode capability") enables VT-d scalable mode if hardware advertises the capability. As we will bring up different features and use cases to upstream in different patch series, it will leave some intermediate kernel versions which support partial features. Hence, end user might run into problems when they use such kernels on bare metals or virtualization environments. This leaves scalable mode default off and end users could turn it on with "intel-iommu=sm_on" only when they have clear ideas about which scalable features are supported in the kernel. Cc: Liu Yi L Cc: Jacob Pan Suggested-by: Ashok Raj Suggested-by: Kevin Tian Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- Documentation/admin-guide/kernel-parameters.txt | 7 +++---- drivers/iommu/intel-iommu.c | 8 ++++---- 2 files changed, 7 insertions(+), 8 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index b799bcf67d7b..858b6c0b9a15 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1696,12 +1696,11 @@ By default, super page will be supported if Intel IOMMU has the capability. With this option, super page will not be supported. - sm_off [Default Off] - By default, scalable mode will be supported if the + sm_on [Default Off] + By default, scalable mode will be disabled even if the hardware advertises that it has support for the scalable mode translation. With this option set, scalable mode - will not be used even on hardware which claims to support - it. + will be used on hardware which claims to support it. tboot_noforce [Default Off] Do not force the Intel IOMMU enabled under tboot. By default, tboot will force Intel IOMMU on, which diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 1457f931218e..78188bf7e90d 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -363,7 +363,7 @@ static int dmar_map_gfx = 1; static int dmar_forcedac; static int intel_iommu_strict; static int intel_iommu_superpage = 1; -static int intel_iommu_sm = 1; +static int intel_iommu_sm; static int iommu_identity_mapping; #define IDENTMAP_ALL 1 @@ -456,9 +456,9 @@ static int __init intel_iommu_setup(char *str) } else if (!strncmp(str, "sp_off", 6)) { pr_info("Disable supported super page\n"); intel_iommu_superpage = 0; - } else if (!strncmp(str, "sm_off", 6)) { - pr_info("Intel-IOMMU: disable scalable mode support\n"); - intel_iommu_sm = 0; + } else if (!strncmp(str, "sm_on", 5)) { + pr_info("Intel-IOMMU: scalable mode supported\n"); + intel_iommu_sm = 1; } else if (!strncmp(str, "tboot_noforce", 13)) { printk(KERN_INFO "Intel-IOMMU: not forcing on after tboot. This could expose security risk for tboot\n"); From 92900e5160a5444d47dd376bc40066b709fbb5a6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 27 Jan 2019 04:58:00 +0000 Subject: [PATCH 260/525] btrfs: fix potential oops in device_list_add alloc_fs_devices() can return ERR_PTR(-ENOMEM), so dereferencing its result before the check for IS_ERR() is a bad idea. Fixes: d1a63002829a4 ("btrfs: add members to fs_devices to track fsid changes") Reviewed-by: Nikolay Borisov Reviewed-by: Anand Jain Signed-off-by: Al Viro Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/volumes.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 3e4f8f88353e..15561926ab32 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -957,11 +957,11 @@ static noinline struct btrfs_device *device_list_add(const char *path, else fs_devices = alloc_fs_devices(disk_super->fsid, NULL); - fs_devices->fsid_change = fsid_change_in_progress; - if (IS_ERR(fs_devices)) return ERR_CAST(fs_devices); + fs_devices->fsid_change = fsid_change_in_progress; + mutex_lock(&fs_devices->device_list_mutex); list_add(&fs_devices->fs_list, &fs_uuids); From c7cc64a98512ffc41df86d14a414eb3b09bf7481 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Wed, 23 Jan 2019 17:09:16 +0100 Subject: [PATCH 261/525] btrfs: clean up pending block groups when transaction commit aborts The fstests generic/475 stresses transaction aborts and can reveal space accounting or use-after-free bugs regarding block goups. In this case the pending block groups that remain linked to the structures after transaction commit aborts in the middle. The corrupted slabs lead to failures in following tests, eg. generic/476 [ 8172.752887] BUG: unable to handle kernel NULL pointer dereference at 0000000000000058 [ 8172.755799] #PF error: [normal kernel read fault] [ 8172.757571] PGD 661ae067 P4D 661ae067 PUD 3db8e067 PMD 0 [ 8172.759000] Oops: 0000 [#1] PREEMPT SMP [ 8172.760209] CPU: 0 PID: 39 Comm: kswapd0 Tainted: G W 5.0.0-rc2-default #408 [ 8172.762495] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.2-0-gf9626cc-prebuilt.qemu-project.org 04/01/2014 [ 8172.765772] RIP: 0010:shrink_page_list+0x2f9/0xe90 [ 8172.770453] RSP: 0018:ffff967f00663b18 EFLAGS: 00010287 [ 8172.771184] RAX: 0000000000000000 RBX: ffff967f00663c20 RCX: 0000000000000000 [ 8172.772850] RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8c0620ab20e0 [ 8172.774629] RBP: ffff967f00663dd8 R08: 0000000000000000 R09: 0000000000000000 [ 8172.776094] R10: ffff8c0620ab22f8 R11: ffff8c063f772688 R12: ffff967f00663b78 [ 8172.777533] R13: ffff8c063f625600 R14: ffff8c063f625608 R15: dead000000000200 [ 8172.778886] FS: 0000000000000000(0000) GS:ffff8c063d400000(0000) knlGS:0000000000000000 [ 8172.780545] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 8172.781787] CR2: 0000000000000058 CR3: 000000004e962000 CR4: 00000000000006f0 [ 8172.783547] Call Trace: [ 8172.784112] shrink_inactive_list+0x194/0x410 [ 8172.784747] shrink_node_memcg.constprop.85+0x3a5/0x6a0 [ 8172.785472] shrink_node+0x62/0x1e0 [ 8172.786011] balance_pgdat+0x216/0x460 [ 8172.786577] kswapd+0xe3/0x4a0 [ 8172.787085] ? finish_wait+0x80/0x80 [ 8172.787795] ? balance_pgdat+0x460/0x460 [ 8172.788799] kthread+0x116/0x130 [ 8172.789640] ? kthread_create_on_node+0x60/0x60 [ 8172.790323] ret_from_fork+0x24/0x30 [ 8172.794253] CR2: 0000000000000058 or accounting errors at umount time: [ 8159.537251] WARNING: CPU: 2 PID: 19031 at fs/btrfs/extent-tree.c:5987 btrfs_free_block_groups+0x3d5/0x410 [btrfs] [ 8159.543325] CPU: 2 PID: 19031 Comm: umount Tainted: G W 5.0.0-rc2-default #408 [ 8159.545472] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.2-0-gf9626cc-prebuilt.qemu-project.org 04/01/2014 [ 8159.548155] RIP: 0010:btrfs_free_block_groups+0x3d5/0x410 [btrfs] [ 8159.554030] RSP: 0018:ffff967f079cbde8 EFLAGS: 00010206 [ 8159.555144] RAX: 0000000001000000 RBX: ffff8c06366cf800 RCX: 0000000000000000 [ 8159.556730] RDX: 0000000000000002 RSI: 0000000000000001 RDI: ffff8c06255ad800 [ 8159.558279] RBP: ffff8c0637ac0000 R08: 0000000000000001 R09: 0000000000000000 [ 8159.559797] R10: 0000000000000000 R11: 0000000000000001 R12: ffff8c0637ac0108 [ 8159.561296] R13: ffff8c0637ac0158 R14: 0000000000000000 R15: dead000000000100 [ 8159.562852] FS: 00007f7f693b9fc0(0000) GS:ffff8c063d800000(0000) knlGS:0000000000000000 [ 8159.564839] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 8159.566160] CR2: 00007f7f68fab7b0 CR3: 000000000aec7000 CR4: 00000000000006e0 [ 8159.567898] Call Trace: [ 8159.568597] close_ctree+0x17f/0x350 [btrfs] [ 8159.569628] generic_shutdown_super+0x64/0x100 [ 8159.570808] kill_anon_super+0x14/0x30 [ 8159.571857] btrfs_kill_super+0x12/0xa0 [btrfs] [ 8159.573063] deactivate_locked_super+0x29/0x60 [ 8159.574234] cleanup_mnt+0x3b/0x70 [ 8159.575176] task_work_run+0x98/0xc0 [ 8159.576177] exit_to_usermode_loop+0x83/0x90 [ 8159.577315] do_syscall_64+0x15b/0x180 [ 8159.578339] entry_SYSCALL_64_after_hwframe+0x49/0xbe This fix is based on 2 Josef's patches that used sideefects of btrfs_create_pending_block_groups, this fix introduces the helper that does what we need. CC: stable@vger.kernel.org # 4.4+ CC: Josef Bacik Reviewed-by: Nikolay Borisov Signed-off-by: David Sterba --- fs/btrfs/transaction.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index f15cf46f1b9d..4ec2b660d014 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1871,6 +1871,21 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans, int err) kmem_cache_free(btrfs_trans_handle_cachep, trans); } +/* + * Release reserved delayed ref space of all pending block groups of the + * transaction and remove them from the list + */ +static void btrfs_cleanup_pending_block_groups(struct btrfs_trans_handle *trans) +{ + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_block_group_cache *block_group, *tmp; + + list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) { + btrfs_delayed_refs_rsv_release(fs_info, 1); + list_del_init(&block_group->bg_list); + } +} + static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info) { /* @@ -2262,6 +2277,7 @@ scrub_continue: btrfs_scrub_continue(fs_info); cleanup_transaction: btrfs_trans_release_metadata(trans); + btrfs_cleanup_pending_block_groups(trans); btrfs_trans_release_chunk_metadata(trans); trans->block_rsv = NULL; btrfs_warn(fs_info, "Skipping commit of aborted transaction."); From 532b618bdf237250d6d4566536d4b6ce3d0a31fe Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 30 Jan 2019 07:54:12 -0600 Subject: [PATCH 262/525] btrfs: On error always free subvol_name in btrfs_mount The subvol_name is allocated in btrfs_parse_subvol_options and is consumed and freed in mount_subvol. Add a free to the error paths that don't call mount_subvol so that it is guaranteed that subvol_name is freed when an error happens. Fixes: 312c89fbca06 ("btrfs: cleanup btrfs_mount() using btrfs_mount_root()") Cc: stable@vger.kernel.org # v4.19+ Reviewed-by: Nikolay Borisov Signed-off-by: "Eric W. Biederman" Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/super.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 368a5b9e6c13..74023786a735 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1677,6 +1677,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, flags | SB_RDONLY, device_name, data); if (IS_ERR(mnt_root)) { root = ERR_CAST(mnt_root); + kfree(subvol_name); goto out; } @@ -1686,12 +1687,14 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, if (error < 0) { root = ERR_PTR(error); mntput(mnt_root); + kfree(subvol_name); goto out; } } } if (IS_ERR(mnt_root)) { root = ERR_CAST(mnt_root); + kfree(subvol_name); goto out; } From 6e11ea9de9576a644045ffdc2067c09bc2012eda Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 30 Jan 2019 10:55:17 +0000 Subject: [PATCH 263/525] drm/amdgpu: Transfer fences to dmabuf importer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit amdgpu only uses shared-fences internally, but dmabuf importers rely on implicit write hazard tracking via the reservation_object.fence_excl. For example, the importer use the write hazard for timing a page flip to only occur after the exporter has finished flushing its write into the surface. As such, on exporting a dmabuf, we must either flush all outstanding fences (for we do not know which are writes and should have been exclusive) or alternatively create a new exclusive fence that is the composite of all the existing shared fences, and so will only be signaled when all earlier fences are signaled (ensuring that we can not be signaled before the completion of any earlier write). v2: reservation_object is already locked by amdgpu_bo_reserve() v3: Replace looping with get_fences_rcu and special case the promotion of a single shared fence directly to an exclusive fence, bypassing the fence array. v4: Drop the fence array ref after assigning to reservation_object Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107341 Testcase: igt/amd_prime/amd-to-i915 References: 8e94a46c1770 ("drm/amdgpu: Attach exclusive fence to prime exported bo's. (v5)") Signed-off-by: Chris Wilson Cc: Alex Deucher Cc: "Christian König" Reviewed-by: "Christian König" Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c | 59 ++++++++++++++++++++--- 1 file changed, 51 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c index 71913a18d142..a38e0fb4a6fe 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c @@ -38,6 +38,7 @@ #include "amdgpu_gem.h" #include #include +#include /** * amdgpu_gem_prime_get_sg_table - &drm_driver.gem_prime_get_sg_table @@ -187,6 +188,48 @@ error: return ERR_PTR(ret); } +static int +__reservation_object_make_exclusive(struct reservation_object *obj) +{ + struct dma_fence **fences; + unsigned int count; + int r; + + if (!reservation_object_get_list(obj)) /* no shared fences to convert */ + return 0; + + r = reservation_object_get_fences_rcu(obj, NULL, &count, &fences); + if (r) + return r; + + if (count == 0) { + /* Now that was unexpected. */ + } else if (count == 1) { + reservation_object_add_excl_fence(obj, fences[0]); + dma_fence_put(fences[0]); + kfree(fences); + } else { + struct dma_fence_array *array; + + array = dma_fence_array_create(count, fences, + dma_fence_context_alloc(1), 0, + false); + if (!array) + goto err_fences_put; + + reservation_object_add_excl_fence(obj, &array->base); + dma_fence_put(&array->base); + } + + return 0; + +err_fences_put: + while (count--) + dma_fence_put(fences[count]); + kfree(fences); + return -ENOMEM; +} + /** * amdgpu_gem_map_attach - &dma_buf_ops.attach implementation * @dma_buf: Shared DMA buffer @@ -218,16 +261,16 @@ static int amdgpu_gem_map_attach(struct dma_buf *dma_buf, if (attach->dev->driver != adev->dev->driver) { /* - * Wait for all shared fences to complete before we switch to future - * use of exclusive fence on this prime shared bo. + * We only create shared fences for internal use, but importers + * of the dmabuf rely on exclusive fences for implicitly + * tracking write hazards. As any of the current fences may + * correspond to a write, we need to convert all existing + * fences on the reservation object into a single exclusive + * fence. */ - r = reservation_object_wait_timeout_rcu(bo->tbo.resv, - true, false, - MAX_SCHEDULE_TIMEOUT); - if (unlikely(r < 0)) { - DRM_DEBUG_PRIME("Fence wait failed: %li\n", r); + r = __reservation_object_make_exclusive(bo->tbo.resv); + if (r) goto error_unreserve; - } } /* pin buffer into GTT */ From 798badf8467f41af6dfbf5621e1fc966c80446fd Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 30 Jan 2019 19:17:53 +0100 Subject: [PATCH 264/525] Revert "staging: erofs: keep corrupted fs from crashing kernel in erofs_namei()" This reverts commit d4104c5e783f5d053b97268fb92001d785de7dd5. Turns out it still needs some more work, I merged it to soon :( Reported-by: Gao Xiang Reported-by: Dan Carpenter Cc: Al Viro Signed-off-by: Greg Kroah-Hartman --- drivers/staging/erofs/namei.c | 167 ++++++++++++++++------------------ 1 file changed, 78 insertions(+), 89 deletions(-) diff --git a/drivers/staging/erofs/namei.c b/drivers/staging/erofs/namei.c index a1300c420e63..5596c52e246d 100644 --- a/drivers/staging/erofs/namei.c +++ b/drivers/staging/erofs/namei.c @@ -15,76 +15,74 @@ #include -struct erofs_qstr { - const unsigned char *name; - const unsigned char *end; -}; - -/* based on the end of qn is accurate and it must have the trailing '\0' */ -static inline int dirnamecmp(const struct erofs_qstr *qn, - const struct erofs_qstr *qd, - unsigned int *matched) +/* based on the value of qn->len is accurate */ +static inline int dirnamecmp(struct qstr *qn, + struct qstr *qd, unsigned int *matched) { - unsigned int i = *matched; - - /* - * on-disk error, let's only BUG_ON in the debugging mode. - * otherwise, it will return 1 to just skip the invalid name - * and go on (in consideration of the lookup performance). - */ - DBG_BUGON(qd->name > qd->end); - - /* qd could not have trailing '\0' */ - /* However it is absolutely safe if < qd->end */ - while (qd->name + i < qd->end && qd->name[i] != '\0') { - if (qn->name[i] != qd->name[i]) { - *matched = i; - return qn->name[i] > qd->name[i] ? 1 : -1; + unsigned int i = *matched, len = min(qn->len, qd->len); +loop: + if (unlikely(i >= len)) { + *matched = i; + if (qn->len < qd->len) { + /* + * actually (qn->len == qd->len) + * when qd->name[i] == '\0' + */ + return qd->name[i] == '\0' ? 0 : -1; } - ++i; + return (qn->len > qd->len); } - *matched = i; - /* See comments in __d_alloc on the terminating NUL character */ - return qn->name[i] == '\0' ? 0 : 1; + + if (qn->name[i] != qd->name[i]) { + *matched = i; + return qn->name[i] > qd->name[i] ? 1 : -1; + } + + ++i; + goto loop; } -#define nameoff_from_disk(off, sz) (le16_to_cpu(off) & ((sz) - 1)) - -static struct erofs_dirent *find_target_dirent(struct erofs_qstr *name, - u8 *data, - unsigned int dirblksize, - const int ndirents) +static struct erofs_dirent *find_target_dirent( + struct qstr *name, + u8 *data, int maxsize) { - int head, back; + unsigned int ndirents, head, back; unsigned int startprfx, endprfx; struct erofs_dirent *const de = (struct erofs_dirent *)data; + /* make sure that maxsize is valid */ + BUG_ON(maxsize < sizeof(struct erofs_dirent)); + + ndirents = le16_to_cpu(de->nameoff) / sizeof(*de); + + /* corrupted dir (may be unnecessary...) */ + BUG_ON(!ndirents); + head = 0; back = ndirents - 1; startprfx = endprfx = 0; while (head <= back) { - const int mid = head + (back - head) / 2; - const int nameoff = nameoff_from_disk(de[mid].nameoff, - dirblksize); + unsigned int mid = head + (back - head) / 2; + unsigned int nameoff = le16_to_cpu(de[mid].nameoff); unsigned int matched = min(startprfx, endprfx); - struct erofs_qstr dname = { - .name = data + nameoff, - .end = unlikely(mid >= ndirents - 1) ? - data + dirblksize : - data + nameoff_from_disk(de[mid + 1].nameoff, - dirblksize) - }; + + struct qstr dname = QSTR_INIT(data + nameoff, + unlikely(mid >= ndirents - 1) ? + maxsize - nameoff : + le16_to_cpu(de[mid + 1].nameoff) - nameoff); /* string comparison without already matched prefix */ int ret = dirnamecmp(name, &dname, &matched); - if (unlikely(!ret)) { + if (unlikely(!ret)) return de + mid; - } else if (ret > 0) { + else if (ret > 0) { head = mid + 1; startprfx = matched; - } else { + } else if (unlikely(mid < 1)) /* fix "mid" overflow */ + break; + else { back = mid - 1; endprfx = matched; } @@ -93,13 +91,12 @@ static struct erofs_dirent *find_target_dirent(struct erofs_qstr *name, return ERR_PTR(-ENOENT); } -static struct page *find_target_block_classic(struct inode *dir, - struct erofs_qstr *name, - int *_diff, - int *_ndirents) +static struct page *find_target_block_classic( + struct inode *dir, + struct qstr *name, int *_diff) { unsigned int startprfx, endprfx; - int head, back; + unsigned int head, back; struct address_space *const mapping = dir->i_mapping; struct page *candidate = ERR_PTR(-ENOENT); @@ -108,34 +105,33 @@ static struct page *find_target_block_classic(struct inode *dir, back = inode_datablocks(dir) - 1; while (head <= back) { - const int mid = head + (back - head) / 2; + unsigned int mid = head + (back - head) / 2; struct page *page = read_mapping_page(mapping, mid, NULL); - if (!IS_ERR(page)) { - struct erofs_dirent *de = kmap_atomic(page); - const int nameoff = nameoff_from_disk(de->nameoff, - EROFS_BLKSIZ); - const int ndirents = nameoff / sizeof(*de); + if (IS_ERR(page)) { +exact_out: + if (!IS_ERR(candidate)) /* valid candidate */ + put_page(candidate); + return page; + } else { int diff; - unsigned int matched; - struct erofs_qstr dname; + unsigned int ndirents, matched; + struct qstr dname; + struct erofs_dirent *de = kmap_atomic(page); + unsigned int nameoff = le16_to_cpu(de->nameoff); - if (unlikely(!ndirents)) { - DBG_BUGON(1); - put_page(page); - page = ERR_PTR(-EIO); - goto out; - } + ndirents = nameoff / sizeof(*de); + + /* corrupted dir (should have one entry at least) */ + BUG_ON(!ndirents || nameoff > PAGE_SIZE); matched = min(startprfx, endprfx); dname.name = (u8 *)de + nameoff; - if (ndirents == 1) - dname.end = (u8 *)de + EROFS_BLKSIZ; - else - dname.end = (u8 *)de + - nameoff_from_disk(de[1].nameoff, - EROFS_BLKSIZ); + dname.len = ndirents == 1 ? + /* since the rest of the last page is 0 */ + EROFS_BLKSIZ - nameoff + : le16_to_cpu(de[1].nameoff) - nameoff; /* string comparison without already matched prefix */ diff = dirnamecmp(name, &dname, &matched); @@ -143,7 +139,7 @@ static struct page *find_target_block_classic(struct inode *dir, if (unlikely(!diff)) { *_diff = 0; - goto out; + goto exact_out; } else if (diff > 0) { head = mid + 1; startprfx = matched; @@ -151,42 +147,35 @@ static struct page *find_target_block_classic(struct inode *dir, if (likely(!IS_ERR(candidate))) put_page(candidate); candidate = page; - *_ndirents = ndirents; } else { put_page(page); + if (unlikely(mid < 1)) /* fix "mid" overflow */ + break; + back = mid - 1; endprfx = matched; } - continue; } -out: /* free if the candidate is valid */ - if (!IS_ERR(candidate)) - put_page(candidate); - return page; } *_diff = 1; return candidate; } int erofs_namei(struct inode *dir, - struct qstr *name, - erofs_nid_t *nid, unsigned int *d_type) + struct qstr *name, + erofs_nid_t *nid, unsigned int *d_type) { - int diff, ndirents; + int diff; struct page *page; u8 *data; struct erofs_dirent *de; - struct erofs_qstr qn; if (unlikely(!dir->i_size)) return -ENOENT; - qn.name = name->name; - qn.end = name->name + name->len; - diff = 1; - page = find_target_block_classic(dir, &qn, &diff, &ndirents); + page = find_target_block_classic(dir, name, &diff); if (unlikely(IS_ERR(page))) return PTR_ERR(page); @@ -195,7 +184,7 @@ int erofs_namei(struct inode *dir, /* the target page has been mapped */ de = likely(diff) ? /* since the rest of the last page is 0 */ - find_target_dirent(&qn, data, EROFS_BLKSIZ, ndirents) : + find_target_dirent(name, data, EROFS_BLKSIZ) : (struct erofs_dirent *)data; if (likely(!IS_ERR(de))) { From 63ff03ab786ab1bc6cca01d48eacd22c95b9b3eb Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 25 Jan 2019 22:43:17 +0100 Subject: [PATCH 265/525] Revert "socket: fix struct ifreq size in compat ioctl" This reverts commit 1cebf8f143c2 ("socket: fix struct ifreq size in compat ioctl"), it's a bugfix for another commit that I'll revert next. This is not a 'perfect' revert, I'm keeping some coding style intact rather than revert to the state with indentation errors. Cc: stable@vger.kernel.org Fixes: 1cebf8f143c2 ("socket: fix struct ifreq size in compat ioctl") Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- net/socket.c | 22 ++++++++-------------- 1 file changed, 8 insertions(+), 14 deletions(-) diff --git a/net/socket.c b/net/socket.c index e89884e2197b..63b53af7379b 100644 --- a/net/socket.c +++ b/net/socket.c @@ -941,8 +941,7 @@ void dlci_ioctl_set(int (*hook) (unsigned int, void __user *)) EXPORT_SYMBOL(dlci_ioctl_set); static long sock_do_ioctl(struct net *net, struct socket *sock, - unsigned int cmd, unsigned long arg, - unsigned int ifreq_size) + unsigned int cmd, unsigned long arg) { int err; void __user *argp = (void __user *)arg; @@ -968,11 +967,11 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, } else { struct ifreq ifr; bool need_copyout; - if (copy_from_user(&ifr, argp, ifreq_size)) + if (copy_from_user(&ifr, argp, sizeof(struct ifreq))) return -EFAULT; err = dev_ioctl(net, cmd, &ifr, &need_copyout); if (!err && need_copyout) - if (copy_to_user(argp, &ifr, ifreq_size)) + if (copy_to_user(argp, &ifr, sizeof(struct ifreq))) return -EFAULT; } return err; @@ -1071,8 +1070,7 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) err = open_related_ns(&net->ns, get_net_ns); break; default: - err = sock_do_ioctl(net, sock, cmd, arg, - sizeof(struct ifreq)); + err = sock_do_ioctl(net, sock, cmd, arg); break; } return err; @@ -2780,8 +2778,7 @@ static int do_siocgstamp(struct net *net, struct socket *sock, int err; set_fs(KERNEL_DS); - err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv, - sizeof(struct compat_ifreq)); + err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv); set_fs(old_fs); if (!err) err = compat_put_timeval(&ktv, up); @@ -2797,8 +2794,7 @@ static int do_siocgstampns(struct net *net, struct socket *sock, int err; set_fs(KERNEL_DS); - err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts, - sizeof(struct compat_ifreq)); + err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts); set_fs(old_fs); if (!err) err = compat_put_timespec(&kts, up); @@ -3109,8 +3105,7 @@ static int routing_ioctl(struct net *net, struct socket *sock, } set_fs(KERNEL_DS); - ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r, - sizeof(struct compat_ifreq)); + ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r); set_fs(old_fs); out: @@ -3223,8 +3218,7 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCBONDSETHWADDR: case SIOCBONDCHANGEACTIVE: case SIOCGIFNAME: - return sock_do_ioctl(net, sock, cmd, arg, - sizeof(struct compat_ifreq)); + return sock_do_ioctl(net, sock, cmd, arg); } return -ENOIOCTLCMD; From 37ac39bdddc528c998a9f36db36937de923fdf2a Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 25 Jan 2019 22:43:18 +0100 Subject: [PATCH 266/525] Revert "kill dev_ifsioc()" This reverts commit bf4405737f9f ("kill dev_ifsioc()"). This wasn't really unused as implied by the original commit, it still handles the copy to/from user differently, and the commit thus caused issues such as https://bugzilla.kernel.org/show_bug.cgi?id=199469 and https://bugzilla.kernel.org/show_bug.cgi?id=202273 However, deviating from a strict revert, rename dev_ifsioc() to compat_ifreq_ioctl() to be clearer as to its purpose and add a comment. Cc: stable@vger.kernel.org Fixes: bf4405737f9f ("kill dev_ifsioc()") Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- net/socket.c | 49 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) diff --git a/net/socket.c b/net/socket.c index 63b53af7379b..fbf80f9fb057 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2990,6 +2990,53 @@ static int compat_ifr_data_ioctl(struct net *net, unsigned int cmd, return dev_ioctl(net, cmd, &ifreq, NULL); } +static int compat_ifreq_ioctl(struct net *net, struct socket *sock, + unsigned int cmd, + struct compat_ifreq __user *uifr32) +{ + struct ifreq __user *uifr; + int err; + + /* Handle the fact that while struct ifreq has the same *layout* on + * 32/64 for everything but ifreq::ifru_ifmap and ifreq::ifru_data, + * which are handled elsewhere, it still has different *size* due to + * ifreq::ifru_ifmap (which is 16 bytes on 32 bit, 24 bytes on 64-bit, + * resulting in struct ifreq being 32 and 40 bytes respectively). + * As a result, if the struct happens to be at the end of a page and + * the next page isn't readable/writable, we get a fault. To prevent + * that, copy back and forth to the full size. + */ + + uifr = compat_alloc_user_space(sizeof(*uifr)); + if (copy_in_user(uifr, uifr32, sizeof(*uifr32))) + return -EFAULT; + + err = sock_do_ioctl(net, sock, cmd, (unsigned long)uifr); + + if (!err) { + switch (cmd) { + case SIOCGIFFLAGS: + case SIOCGIFMETRIC: + case SIOCGIFMTU: + case SIOCGIFMEM: + case SIOCGIFHWADDR: + case SIOCGIFINDEX: + case SIOCGIFADDR: + case SIOCGIFBRDADDR: + case SIOCGIFDSTADDR: + case SIOCGIFNETMASK: + case SIOCGIFPFLAGS: + case SIOCGIFTXQLEN: + case SIOCGMIIPHY: + case SIOCGMIIREG: + if (copy_in_user(uifr32, uifr, sizeof(*uifr32))) + err = -EFAULT; + break; + } + } + return err; +} + static int compat_sioc_ifmap(struct net *net, unsigned int cmd, struct compat_ifreq __user *uifr32) { @@ -3209,6 +3256,8 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCSMIIREG: + return compat_ifreq_ioctl(net, sock, cmd, argp); + case SIOCSARP: case SIOCGARP: case SIOCDARP: From c6c9fee35dc27362b7bac34b2fc9f5b8ace2e22c Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 25 Jan 2019 22:43:19 +0100 Subject: [PATCH 267/525] net: socket: fix SIOCGIFNAME in compat As reported by Robert O'Callahan in https://bugzilla.kernel.org/show_bug.cgi?id=202273 reverting the previous changes in this area broke the SIOCGIFNAME ioctl in compat again (I'd previously fixed it after his previous report of breakage in https://bugzilla.kernel.org/show_bug.cgi?id=199469). This is obviously because I fixed SIOCGIFNAME more or less by accident. Fix it explicitly now by making it pass through the restored compat translation code. Cc: stable@vger.kernel.org Fixes: 4cf808e7ac32 ("kill dev_ifname32()") Reported-by: Robert O'Callahan Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- net/socket.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/socket.c b/net/socket.c index fbf80f9fb057..473ac8d7c54e 100644 --- a/net/socket.c +++ b/net/socket.c @@ -3029,6 +3029,7 @@ static int compat_ifreq_ioctl(struct net *net, struct socket *sock, case SIOCGIFTXQLEN: case SIOCGMIIPHY: case SIOCGMIIREG: + case SIOCGIFNAME: if (copy_in_user(uifr32, uifr, sizeof(*uifr32))) err = -EFAULT; break; @@ -3252,6 +3253,7 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCSIFTXQLEN: case SIOCBRADDIF: case SIOCBRDELIF: + case SIOCGIFNAME: case SIOCSIFNAME: case SIOCGMIIPHY: case SIOCGMIIREG: @@ -3266,7 +3268,6 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCBONDRELEASE: case SIOCBONDSETHWADDR: case SIOCBONDCHANGEACTIVE: - case SIOCGIFNAME: return sock_do_ioctl(net, sock, cmd, arg); } From 98406133dd9cb9f195676eab540c270dceca879a Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 25 Jan 2019 22:43:20 +0100 Subject: [PATCH 268/525] net: socket: make bond ioctls go through compat_ifreq_ioctl() Same story as before, these use struct ifreq and thus need to be read with the shorter version to not cause faults. Cc: stable@vger.kernel.org Fixes: f92d4fc95341 ("kill bond_ioctl()") Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- net/socket.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/socket.c b/net/socket.c index 473ac8d7c54e..d80d87a395ea 100644 --- a/net/socket.c +++ b/net/socket.c @@ -3258,16 +3258,16 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCSMIIREG: + case SIOCBONDENSLAVE: + case SIOCBONDRELEASE: + case SIOCBONDSETHWADDR: + case SIOCBONDCHANGEACTIVE: return compat_ifreq_ioctl(net, sock, cmd, argp); case SIOCSARP: case SIOCGARP: case SIOCDARP: case SIOCATMARK: - case SIOCBONDENSLAVE: - case SIOCBONDRELEASE: - case SIOCBONDSETHWADDR: - case SIOCBONDCHANGEACTIVE: return sock_do_ioctl(net, sock, cmd, arg); } From b284909abad48b07d3071a9fc9b5692b3e64914b Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 30 Jan 2019 07:13:58 -0600 Subject: [PATCH 269/525] cpu/hotplug: Fix "SMT disabled by BIOS" detection for KVM With the following commit: 73d5e2b47264 ("cpu/hotplug: detect SMT disabled by BIOS") ... the hotplug code attempted to detect when SMT was disabled by BIOS, in which case it reported SMT as permanently disabled. However, that code broke a virt hotplug scenario, where the guest is booted with only primary CPU threads, and a sibling is brought online later. The problem is that there doesn't seem to be a way to reliably distinguish between the HW "SMT disabled by BIOS" case and the virt "sibling not yet brought online" case. So the above-mentioned commit was a bit misguided, as it permanently disabled SMT for both cases, preventing future virt sibling hotplugs. Going back and reviewing the original problems which were attempted to be solved by that commit, when SMT was disabled in BIOS: 1) /sys/devices/system/cpu/smt/control showed "on" instead of "notsupported"; and 2) vmx_vm_init() was incorrectly showing the L1TF_MSG_SMT warning. I'd propose that we instead consider #1 above to not actually be a problem. Because, at least in the virt case, it's possible that SMT wasn't disabled by BIOS and a sibling thread could be brought online later. So it makes sense to just always default the smt control to "on" to allow for that possibility (assuming cpuid indicates that the CPU supports SMT). The real problem is #2, which has a simple fix: change vmx_vm_init() to query the actual current SMT state -- i.e., whether any siblings are currently online -- instead of looking at the SMT "control" sysfs value. So fix it by: a) reverting the original "fix" and its followup fix: 73d5e2b47264 ("cpu/hotplug: detect SMT disabled by BIOS") bc2d8d262cba ("cpu/hotplug: Fix SMT supported evaluation") and b) changing vmx_vm_init() to query the actual current SMT state -- instead of the sysfs control value -- to determine whether the L1TF warning is needed. This also requires the 'sched_smt_present' variable to exported, instead of 'cpu_smt_control'. Fixes: 73d5e2b47264 ("cpu/hotplug: detect SMT disabled by BIOS") Reported-by: Igor Mammedov Signed-off-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner Cc: Joe Mario Cc: Jiri Kosina Cc: Peter Zijlstra Cc: kvm@vger.kernel.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/e3a85d585da28cc333ecbc1e78ee9216e6da9396.1548794349.git.jpoimboe@redhat.com --- arch/x86/kernel/cpu/bugs.c | 2 +- arch/x86/kvm/vmx/vmx.c | 3 ++- include/linux/cpu.h | 2 -- kernel/cpu.c | 33 ++++----------------------------- kernel/sched/fair.c | 1 + kernel/smp.c | 2 -- 6 files changed, 8 insertions(+), 35 deletions(-) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 1de0f4170178..01874d54f4fd 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -71,7 +71,7 @@ void __init check_bugs(void) * identify_boot_cpu() initialized SMT support information, let the * core code know. */ - cpu_smt_check_topology_early(); + cpu_smt_check_topology(); if (!IS_ENABLED(CONFIG_SMP)) { pr_info("CPU: "); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 4341175339f3..95d618045001 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include @@ -6823,7 +6824,7 @@ static int vmx_vm_init(struct kvm *kvm) * Warn upon starting the first VM in a potentially * insecure environment. */ - if (cpu_smt_control == CPU_SMT_ENABLED) + if (sched_smt_active()) pr_warn_once(L1TF_MSG_SMT); if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER) pr_warn_once(L1TF_MSG_L1D); diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 218df7f4d3e1..5041357d0297 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -180,12 +180,10 @@ enum cpuhp_smt_control { #if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT) extern enum cpuhp_smt_control cpu_smt_control; extern void cpu_smt_disable(bool force); -extern void cpu_smt_check_topology_early(void); extern void cpu_smt_check_topology(void); #else # define cpu_smt_control (CPU_SMT_ENABLED) static inline void cpu_smt_disable(bool force) { } -static inline void cpu_smt_check_topology_early(void) { } static inline void cpu_smt_check_topology(void) { } #endif diff --git a/kernel/cpu.c b/kernel/cpu.c index c0c7f64573ed..d1c6d152da89 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -376,9 +376,6 @@ void __weak arch_smt_update(void) { } #ifdef CONFIG_HOTPLUG_SMT enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED; -EXPORT_SYMBOL_GPL(cpu_smt_control); - -static bool cpu_smt_available __read_mostly; void __init cpu_smt_disable(bool force) { @@ -397,25 +394,11 @@ void __init cpu_smt_disable(bool force) /* * The decision whether SMT is supported can only be done after the full - * CPU identification. Called from architecture code before non boot CPUs - * are brought up. - */ -void __init cpu_smt_check_topology_early(void) -{ - if (!topology_smt_supported()) - cpu_smt_control = CPU_SMT_NOT_SUPPORTED; -} - -/* - * If SMT was disabled by BIOS, detect it here, after the CPUs have been - * brought online. This ensures the smt/l1tf sysfs entries are consistent - * with reality. cpu_smt_available is set to true during the bringup of non - * boot CPUs when a SMT sibling is detected. Note, this may overwrite - * cpu_smt_control's previous setting. + * CPU identification. Called from architecture code. */ void __init cpu_smt_check_topology(void) { - if (!cpu_smt_available) + if (!topology_smt_supported()) cpu_smt_control = CPU_SMT_NOT_SUPPORTED; } @@ -428,18 +411,10 @@ early_param("nosmt", smt_cmdline_disable); static inline bool cpu_smt_allowed(unsigned int cpu) { - if (topology_is_primary_thread(cpu)) + if (cpu_smt_control == CPU_SMT_ENABLED) return true; - /* - * If the CPU is not a 'primary' thread and the booted_once bit is - * set then the processor has SMT support. Store this information - * for the late check of SMT support in cpu_smt_check_topology(). - */ - if (per_cpu(cpuhp_state, cpu).booted_once) - cpu_smt_available = true; - - if (cpu_smt_control == CPU_SMT_ENABLED) + if (topology_is_primary_thread(cpu)) return true; /* diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 50aa2aba69bd..310d0637fe4b 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5980,6 +5980,7 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p #ifdef CONFIG_SCHED_SMT DEFINE_STATIC_KEY_FALSE(sched_smt_present); +EXPORT_SYMBOL_GPL(sched_smt_present); static inline void set_idle_cores(int cpu, int val) { diff --git a/kernel/smp.c b/kernel/smp.c index 163c451af42e..f4cf1b0bb3b8 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -584,8 +584,6 @@ void __init smp_init(void) num_nodes, (num_nodes > 1 ? "s" : ""), num_cpus, (num_cpus > 1 ? "s" : "")); - /* Final decision about SMT support */ - cpu_smt_check_topology(); /* Any cleanup work */ smp_cpus_done(setup_max_cpus); } From e15aa3b2b1388c399c1a2ce08550d2cc4f7e3e14 Mon Sep 17 00:00:00 2001 From: Mathias Thore Date: Mon, 28 Jan 2019 10:07:47 +0100 Subject: [PATCH 270/525] ucc_geth: Reset BQL queue when stopping device After a timeout event caused by for example a broadcast storm, when the MAC and PHY are reset, the BQL TX queue needs to be reset as well. Otherwise, the device will exhibit severe performance issues even after the storm has ended. Co-authored-by: David Gounaris Signed-off-by: Mathias Thore Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/ucc_geth.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index c3d539e209ed..eb3e65e8868f 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -1879,6 +1879,8 @@ static void ucc_geth_free_tx(struct ucc_geth_private *ugeth) u16 i, j; u8 __iomem *bd; + netdev_reset_queue(ugeth->ndev); + ug_info = ugeth->ug_info; uf_info = &ug_info->uf_info; From 1dbd449c9943e3145148cc893c2461b72ba6fef0 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 30 Jan 2019 13:52:36 -0500 Subject: [PATCH 271/525] fs/dcache: Fix incorrect nr_dentry_unused accounting in shrink_dcache_sb() The nr_dentry_unused per-cpu counter tracks dentries in both the LRU lists and the shrink lists where the DCACHE_LRU_LIST bit is set. The shrink_dcache_sb() function moves dentries from the LRU list to a shrink list and subtracts the dentry count from nr_dentry_unused. This is incorrect as the nr_dentry_unused count will also be decremented in shrink_dentry_list() via d_shrink_del(). To fix this double decrement, the decrement in the shrink_dcache_sb() function is taken out. Fixes: 4e717f5c1083 ("list_lru: remove special case function list_lru_dispose_all." Cc: stable@kernel.org Signed-off-by: Waiman Long Reviewed-by: Dave Chinner Signed-off-by: Linus Torvalds --- fs/dcache.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/fs/dcache.c b/fs/dcache.c index 2593153471cf..44e5652b2664 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1188,15 +1188,11 @@ static enum lru_status dentry_lru_isolate_shrink(struct list_head *item, */ void shrink_dcache_sb(struct super_block *sb) { - long freed; - do { LIST_HEAD(dispose); - freed = list_lru_walk(&sb->s_dentry_lru, + list_lru_walk(&sb->s_dentry_lru, dentry_lru_isolate_shrink, &dispose, 1024); - - this_cpu_sub(nr_dentry_unused, freed); shrink_dentry_list(&dispose); } while (list_lru_count(&sb->s_dentry_lru) > 0); } From 7d10f70fc198877b43d92bdcd7604279788b9568 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 30 Jan 2019 13:52:37 -0500 Subject: [PATCH 272/525] fs: Don't need to put list_lru into its own cacheline The list_lru structure is essentially just a pointer to a table of per-node LRU lists. Even if CONFIG_MEMCG_KMEM is defined, the list field is just used for LRU list registration and shrinker_id is set at initialization. Those fields won't need to be touched that often. So there is no point to make the list_lru structures to sit in their own cachelines. Signed-off-by: Waiman Long Reviewed-by: Dave Chinner Signed-off-by: Linus Torvalds --- include/linux/fs.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/include/linux/fs.h b/include/linux/fs.h index 811c77743dad..29d8e2cfed0e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1479,11 +1479,12 @@ struct super_block { struct user_namespace *s_user_ns; /* - * Keep the lru lists last in the structure so they always sit on their - * own individual cachelines. + * The list_lru structure is essentially just a pointer to a table + * of per-node lru lists, each of which has its own spinlock. + * There is no need to put them into separate cachelines. */ - struct list_lru s_dentry_lru ____cacheline_aligned_in_smp; - struct list_lru s_inode_lru ____cacheline_aligned_in_smp; + struct list_lru s_dentry_lru; + struct list_lru s_inode_lru; struct rcu_head rcu; struct work_struct destroy_work; From af0c9af1b3f66052c369d08be3f60fa9a9559e48 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 30 Jan 2019 13:52:38 -0500 Subject: [PATCH 273/525] fs/dcache: Track & report number of negative dentries The current dentry number tracking code doesn't distinguish between positive & negative dentries. It just reports the total number of dentries in the LRU lists. As excessive number of negative dentries can have an impact on system performance, it will be wise to track the number of positive and negative dentries separately. This patch adds tracking for the total number of negative dentries in the system LRU lists and reports it in the 5th field in the /proc/sys/fs/dentry-state file. The number, however, does not include negative dentries that are in flight but not in the LRU yet as well as those in the shrinker lists which are on the way out anyway. The number of positive dentries in the LRU lists can be roughly found by subtracting the number of negative dentries from the unused count. Matthew Wilcox had confirmed that since the introduction of the dentry_stat structure in 2.1.60, the dummy array was there, probably for future extension. They were not replacements of pre-existing fields. So no sane applications that read the value of /proc/sys/fs/dentry-state will do dummy thing if the last 2 fields of the sysctl parameter are not zero. IOW, it will be safe to use one of the dummy array entry for negative dentry count. Signed-off-by: Waiman Long Signed-off-by: Linus Torvalds --- Documentation/sysctl/fs.txt | 24 +++++++++++++++--------- fs/dcache.c | 32 ++++++++++++++++++++++++++++++++ include/linux/dcache.h | 7 ++++--- 3 files changed, 51 insertions(+), 12 deletions(-) diff --git a/Documentation/sysctl/fs.txt b/Documentation/sysctl/fs.txt index 819caf8ca05f..58649bd4fcfc 100644 --- a/Documentation/sysctl/fs.txt +++ b/Documentation/sysctl/fs.txt @@ -56,26 +56,32 @@ of any kernel data structures. dentry-state: -From linux/fs/dentry.c: +From linux/include/linux/dcache.h: -------------------------------------------------------------- -struct { +struct dentry_stat_t dentry_stat { int nr_dentry; int nr_unused; int age_limit; /* age in seconds */ int want_pages; /* pages requested by system */ - int dummy[2]; -} dentry_stat = {0, 0, 45, 0,}; --------------------------------------------------------------- + int nr_negative; /* # of unused negative dentries */ + int dummy; /* Reserved for future use */ +}; +-------------------------------------------------------------- + +Dentries are dynamically allocated and deallocated. + +nr_dentry shows the total number of dentries allocated (active ++ unused). nr_unused shows the number of dentries that are not +actively used, but are saved in the LRU list for future reuse. -Dentries are dynamically allocated and deallocated, and -nr_dentry seems to be 0 all the time. Hence it's safe to -assume that only nr_unused, age_limit and want_pages are -used. Nr_unused seems to be exactly what its name says. Age_limit is the age in seconds after which dcache entries can be reclaimed when memory is short and want_pages is nonzero when shrink_dcache_pages() has been called and the dcache isn't pruned yet. +nr_negative shows the number of unused dentries that are also +negative dentries which do not mapped to actual files. + ============================================================== dquot-max & dquot-nr: diff --git a/fs/dcache.c b/fs/dcache.c index 44e5652b2664..aac41adf4743 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -119,6 +119,7 @@ struct dentry_stat_t dentry_stat = { static DEFINE_PER_CPU(long, nr_dentry); static DEFINE_PER_CPU(long, nr_dentry_unused); +static DEFINE_PER_CPU(long, nr_dentry_negative); #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) @@ -152,11 +153,22 @@ static long get_nr_dentry_unused(void) return sum < 0 ? 0 : sum; } +static long get_nr_dentry_negative(void) +{ + int i; + long sum = 0; + + for_each_possible_cpu(i) + sum += per_cpu(nr_dentry_negative, i); + return sum < 0 ? 0 : sum; +} + int proc_nr_dentry(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { dentry_stat.nr_dentry = get_nr_dentry(); dentry_stat.nr_unused = get_nr_dentry_unused(); + dentry_stat.nr_negative = get_nr_dentry_negative(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } #endif @@ -317,6 +329,8 @@ static inline void __d_clear_type_and_inode(struct dentry *dentry) flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); WRITE_ONCE(dentry->d_flags, flags); dentry->d_inode = NULL; + if (dentry->d_flags & DCACHE_LRU_LIST) + this_cpu_inc(nr_dentry_negative); } static void dentry_free(struct dentry *dentry) @@ -371,6 +385,11 @@ static void dentry_unlink_inode(struct dentry * dentry) * The per-cpu "nr_dentry_unused" counters are updated with * the DCACHE_LRU_LIST bit. * + * The per-cpu "nr_dentry_negative" counters are only updated + * when deleted from or added to the per-superblock LRU list, not + * from/to the shrink list. That is to avoid an unneeded dec/inc + * pair when moving from LRU to shrink list in select_collect(). + * * These helper functions make sure we always follow the * rules. d_lock must be held by the caller. */ @@ -380,6 +399,8 @@ static void d_lru_add(struct dentry *dentry) D_FLAG_VERIFY(dentry, 0); dentry->d_flags |= DCACHE_LRU_LIST; this_cpu_inc(nr_dentry_unused); + if (d_is_negative(dentry)) + this_cpu_inc(nr_dentry_negative); WARN_ON_ONCE(!list_lru_add(&dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } @@ -388,6 +409,8 @@ static void d_lru_del(struct dentry *dentry) D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); + if (d_is_negative(dentry)) + this_cpu_dec(nr_dentry_negative); WARN_ON_ONCE(!list_lru_del(&dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } @@ -418,6 +441,8 @@ static void d_lru_isolate(struct list_lru_one *lru, struct dentry *dentry) D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); + if (d_is_negative(dentry)) + this_cpu_dec(nr_dentry_negative); list_lru_isolate(lru, &dentry->d_lru); } @@ -426,6 +451,8 @@ static void d_lru_shrink_move(struct list_lru_one *lru, struct dentry *dentry, { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags |= DCACHE_SHRINK_LIST; + if (d_is_negative(dentry)) + this_cpu_dec(nr_dentry_negative); list_lru_isolate_move(lru, &dentry->d_lru, list); } @@ -1816,6 +1843,11 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) WARN_ON(d_in_lookup(dentry)); spin_lock(&dentry->d_lock); + /* + * Decrement negative dentry count if it was in the LRU list. + */ + if (dentry->d_flags & DCACHE_LRU_LIST) + this_cpu_dec(nr_dentry_negative); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); diff --git a/include/linux/dcache.h b/include/linux/dcache.h index ef4b70f64f33..60996e64c579 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -62,9 +62,10 @@ extern const struct qstr slash_name; struct dentry_stat_t { long nr_dentry; long nr_unused; - long age_limit; /* age in seconds */ - long want_pages; /* pages requested by system */ - long dummy[2]; + long age_limit; /* age in seconds */ + long want_pages; /* pages requested by system */ + long nr_negative; /* # of unused negative dentries */ + long dummy; /* Reserved for future use */ }; extern struct dentry_stat_t dentry_stat; From 15efb47dc560849d0c07db96fdad5121f2cf736e Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Wed, 30 Jan 2019 18:26:02 +0100 Subject: [PATCH 274/525] PM-runtime: Fix deadlock with ktime_get() A deadlock has been seen when swicthing clocksources which use PM-runtime. The call path is: change_clocksource ... write_seqcount_begin ... timekeeping_update ... sh_cmt_clocksource_enable ... rpm_resume pm_runtime_mark_last_busy ktime_get do read_seqcount_begin while read_seqcount_retry .... write_seqcount_end Although we should be safe because we haven't yet changed the clocksource at that time, we can't do that because of seqcount protection. Use ktime_get_mono_fast_ns() instead which is lock safe for such cases. With ktime_get_mono_fast_ns, the timestamp is not guaranteed to be monotonic across an update and as a result can goes backward. According to update_fast_timekeeper() description: "In the worst case, this can result is a slightly wrong timestamp (a few nanoseconds)". For PM-runtime autosuspend, this means only that the suspend decision may be slightly suboptimal. Fixes: 8234f6734c5d ("PM-runtime: Switch autosuspend over to using hrtimers") Reported-by: Biju Das Signed-off-by: Vincent Guittot Reviewed-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- drivers/base/power/runtime.c | 10 +++++----- include/linux/pm_runtime.h | 2 +- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 457be03b744d..0ea2139c50d8 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -130,7 +130,7 @@ u64 pm_runtime_autosuspend_expiration(struct device *dev) { int autosuspend_delay; u64 last_busy, expires = 0; - u64 now = ktime_to_ns(ktime_get()); + u64 now = ktime_get_mono_fast_ns(); if (!dev->power.use_autosuspend) goto out; @@ -909,7 +909,7 @@ static enum hrtimer_restart pm_suspend_timer_fn(struct hrtimer *timer) * If 'expires' is after the current time, we've been called * too early. */ - if (expires > 0 && expires < ktime_to_ns(ktime_get())) { + if (expires > 0 && expires < ktime_get_mono_fast_ns()) { dev->power.timer_expires = 0; rpm_suspend(dev, dev->power.timer_autosuspends ? (RPM_ASYNC | RPM_AUTO) : RPM_ASYNC); @@ -928,7 +928,7 @@ static enum hrtimer_restart pm_suspend_timer_fn(struct hrtimer *timer) int pm_schedule_suspend(struct device *dev, unsigned int delay) { unsigned long flags; - ktime_t expires; + u64 expires; int retval; spin_lock_irqsave(&dev->power.lock, flags); @@ -945,8 +945,8 @@ int pm_schedule_suspend(struct device *dev, unsigned int delay) /* Other scheduled or pending requests need to be canceled. */ pm_runtime_cancel_pending(dev); - expires = ktime_add(ktime_get(), ms_to_ktime(delay)); - dev->power.timer_expires = ktime_to_ns(expires); + expires = ktime_get_mono_fast_ns() + (u64)delay * NSEC_PER_MSEC; + dev->power.timer_expires = expires; dev->power.timer_autosuspends = 0; hrtimer_start(&dev->power.suspend_timer, expires, HRTIMER_MODE_ABS); diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 54af4eef169f..fed5be706bc9 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -105,7 +105,7 @@ static inline bool pm_runtime_callbacks_present(struct device *dev) static inline void pm_runtime_mark_last_busy(struct device *dev) { - WRITE_ONCE(dev->power.last_busy, ktime_to_ns(ktime_get())); + WRITE_ONCE(dev->power.last_busy, ktime_get_mono_fast_ns()); } static inline bool pm_runtime_is_irq_safe(struct device *dev) From 1617971c6616c87185cbc78fa1a86dfc70dd16b6 Mon Sep 17 00:00:00 2001 From: Doug Smythies Date: Wed, 30 Jan 2019 08:28:22 -0800 Subject: [PATCH 275/525] cpuidle: poll_state: Fix default time limit The default time is declared in units of microsecnds, but is used as nanoseconds, resulting in significant accounting errors for idle state 0 time when all idle states deeper than 0 are disabled. Under these unusual conditions, we don't really care about the poll time limit anyhow. Fixes: 800fb34a99ce ("cpuidle: poll_state: Disregard disable idle states") Signed-off-by: Doug Smythies Signed-off-by: Rafael J. Wysocki --- drivers/cpuidle/poll_state.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c index b17d153e724f..23a1b27579a5 100644 --- a/drivers/cpuidle/poll_state.c +++ b/drivers/cpuidle/poll_state.c @@ -21,7 +21,7 @@ static int __cpuidle poll_idle(struct cpuidle_device *dev, local_irq_enable(); if (!current_set_polling_and_test()) { unsigned int loop_count = 0; - u64 limit = TICK_USEC; + u64 limit = TICK_NSEC; int i; for (i = 1; i < drv->state_count; i++) { From feaf5c796b3f0240f10d0d6d0b686715fd58a05b Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Mon, 28 Jan 2019 22:23:48 +0100 Subject: [PATCH 276/525] net: ip_gre: always reports o_key to userspace Erspan protocol (version 1 and 2) relies on o_key to configure session id header field. However TUNNEL_KEY bit is cleared in erspan_xmit since ERSPAN protocol does not set the key field of the external GRE header and so the configured o_key is not reported to userspace. The issue can be triggered with the following reproducer: $ip link add erspan1 type erspan local 192.168.0.1 remote 192.168.0.2 \ key 1 seq erspan_ver 1 $ip link set erspan1 up $ip -d link sh erspan1 erspan1@NONE: mtu 1450 qdisc pfifo_fast state UNKNOWN mode DEFAULT link/ether 52:aa:99:95:9a:b5 brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 1500 erspan remote 192.168.0.2 local 192.168.0.1 ttl inherit ikey 0.0.0.1 iseq oseq erspan_index 0 Fix the issue adding TUNNEL_KEY bit to the o_flags parameter in ipgre_fill_info Fixes: 84e54fe0a5ea ("gre: introduce native tunnel support for ERSPAN") Signed-off-by: Lorenzo Bianconi Signed-off-by: David S. Miller --- net/ipv4/ip_gre.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 20a64fe6254b..3978f807fa8b 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1455,12 +1455,17 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm *p = &t->parms; + __be16 o_flags = p->o_flags; + + if ((t->erspan_ver == 1 || t->erspan_ver == 2) && + !t->collect_md) + o_flags |= TUNNEL_KEY; if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, gre_tnl_flags_to_gre_flags(p->i_flags)) || nla_put_be16(skb, IFLA_GRE_OFLAGS, - gre_tnl_flags_to_gre_flags(p->o_flags)) || + gre_tnl_flags_to_gre_flags(o_flags)) || nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || nla_put_in_addr(skb, IFLA_GRE_LOCAL, p->iph.saddr) || From c706863bc8902d0c2d1a5a27ac8e1ead5d06b79d Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Mon, 28 Jan 2019 22:23:49 +0100 Subject: [PATCH 277/525] net: ip6_gre: always reports o_key to userspace As Erspan_v4, Erspan_v6 protocol relies on o_key to configure session id header field. However TUNNEL_KEY bit is cleared in ip6erspan_tunnel_xmit since ERSPAN protocol does not set the key field of the external GRE header and so the configured o_key is not reported to userspace. The issue can be triggered with the following reproducer: $ip link add ip6erspan1 type ip6erspan local 2000::1 remote 2000::2 \ key 1 seq erspan_ver 1 $ip link set ip6erspan1 up ip -d link sh ip6erspan1 ip6erspan1@NONE: mtu 1422 qdisc noop state DOWN mode DEFAULT link/ether ba:ff:09:24:c3:0e brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 1500 ip6erspan remote 2000::2 local 2000::1 encaplimit 4 flowlabel 0x00000 ikey 0.0.0.1 iseq oseq Fix the issue adding TUNNEL_KEY bit to the o_flags parameter in ip6gre_fill_info Fixes: 5a963eb61b7c ("ip6_gre: Add ERSPAN native tunnel support") Signed-off-by: Lorenzo Bianconi Signed-off-by: David S. Miller --- net/ipv6/ip6_gre.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 4416368dbd49..801a9a0c217e 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -2098,12 +2098,17 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct __ip6_tnl_parm *p = &t->parms; + __be16 o_flags = p->o_flags; + + if ((p->erspan_ver == 1 || p->erspan_ver == 2) && + !p->collect_md) + o_flags |= TUNNEL_KEY; if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, gre_tnl_flags_to_gre_flags(p->i_flags)) || nla_put_be16(skb, IFLA_GRE_OFLAGS, - gre_tnl_flags_to_gre_flags(p->o_flags)) || + gre_tnl_flags_to_gre_flags(o_flags)) || nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || nla_put_in6_addr(skb, IFLA_GRE_LOCAL, &p->laddr) || From 8be4d9a492f88b96d4d3a06c6cbedbc40ca14c83 Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Tue, 29 Jan 2019 09:45:53 +0900 Subject: [PATCH 278/525] virtio_net: Don't enable NAPI when interface is down Commit 4e09ff536284 ("virtio-net: disable NAPI only when enabled during XDP set") tried to fix inappropriate NAPI enabling/disabling when !netif_running(), but was not complete. On error path virtio_net could enable NAPI even when !netif_running(). This can cause enabling NAPI twice on virtnet_open(), which would trigger BUG_ON() in napi_enable(). Fixes: 4941d472bf95b ("virtio-net: do not reset during XDP set") Signed-off-by: Toshiaki Makita Acked-by: Jason Wang Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 8fadd8eaf601..8e4c5d432206 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2430,8 +2430,10 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, return 0; err: - for (i = 0; i < vi->max_queue_pairs; i++) - virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); + if (netif_running(dev)) { + for (i = 0; i < vi->max_queue_pairs; i++) + virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); + } if (prog) bpf_prog_sub(prog, vi->max_queue_pairs - 1); return err; From 534da5e856334fb54cb0272a9fb3afec28ea3aed Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Tue, 29 Jan 2019 09:45:54 +0900 Subject: [PATCH 279/525] virtio_net: Don't call free_old_xmit_skbs for xdp_frames When napi_tx is enabled, virtnet_poll_cleantx() called free_old_xmit_skbs() even for xdp send queue. This is bogus since the queue has xdp_frames, not sk_buffs, thus mangled device tx bytes counters because skb->len is meaningless value, and even triggered oops due to general protection fault on freeing them. Since xdp send queues do not aquire locks, old xdp_frames should be freed only in virtnet_xdp_xmit(), so just skip free_old_xmit_skbs() for xdp send queues. Similarly virtnet_poll_tx() called free_old_xmit_skbs(). This NAPI handler is called even without calling start_xmit() because cb for tx is by default enabled. Once the handler is called, it enabled the cb again, and then the handler would be called again. We don't need this handler for XDP, so don't enable cb as well as not calling free_old_xmit_skbs(). Also, we need to disable tx NAPI when disabling XDP, so virtnet_poll_tx() can safely access curr_queue_pairs and xdp_queue_pairs, which are not atomically updated while disabling XDP. Fixes: b92f1e6751a6 ("virtio-net: transmit napi") Fixes: 7b0411ef4aa6 ("virtio-net: clean tx descriptors from rx napi") Signed-off-by: Toshiaki Makita Acked-by: Jason Wang Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 49 +++++++++++++++++++++++++++------------- 1 file changed, 33 insertions(+), 16 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 8e4c5d432206..046f955495a8 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1358,6 +1358,16 @@ static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi) u64_stats_update_end(&sq->stats.syncp); } +static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q) +{ + if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs)) + return false; + else if (q < vi->curr_queue_pairs) + return true; + else + return false; +} + static void virtnet_poll_cleantx(struct receive_queue *rq) { struct virtnet_info *vi = rq->vq->vdev->priv; @@ -1365,7 +1375,7 @@ static void virtnet_poll_cleantx(struct receive_queue *rq) struct send_queue *sq = &vi->sq[index]; struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, index); - if (!sq->napi.weight) + if (!sq->napi.weight || is_xdp_raw_buffer_queue(vi, index)) return; if (__netif_tx_trylock(txq)) { @@ -1442,8 +1452,16 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget) { struct send_queue *sq = container_of(napi, struct send_queue, napi); struct virtnet_info *vi = sq->vq->vdev->priv; - struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, vq2txq(sq->vq)); + unsigned int index = vq2txq(sq->vq); + struct netdev_queue *txq; + if (unlikely(is_xdp_raw_buffer_queue(vi, index))) { + /* We don't need to enable cb for XDP */ + napi_complete_done(napi, 0); + return 0; + } + + txq = netdev_get_tx_queue(vi->dev, index); __netif_tx_lock(txq, raw_smp_processor_id()); free_old_xmit_skbs(sq, true); __netif_tx_unlock(txq); @@ -2402,9 +2420,12 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, } /* Make sure NAPI is not using any XDP TX queues for RX. */ - if (netif_running(dev)) - for (i = 0; i < vi->max_queue_pairs; i++) + if (netif_running(dev)) { + for (i = 0; i < vi->max_queue_pairs; i++) { napi_disable(&vi->rq[i].napi); + virtnet_napi_tx_disable(&vi->sq[i].napi); + } + } netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp); err = _virtnet_set_queues(vi, curr_qp + xdp_qp); @@ -2423,16 +2444,22 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, } if (old_prog) bpf_prog_put(old_prog); - if (netif_running(dev)) + if (netif_running(dev)) { virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); + virtnet_napi_tx_enable(vi, vi->sq[i].vq, + &vi->sq[i].napi); + } } return 0; err: if (netif_running(dev)) { - for (i = 0; i < vi->max_queue_pairs; i++) + for (i = 0; i < vi->max_queue_pairs; i++) { virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); + virtnet_napi_tx_enable(vi, vi->sq[i].vq, + &vi->sq[i].napi); + } } if (prog) bpf_prog_sub(prog, vi->max_queue_pairs - 1); @@ -2615,16 +2642,6 @@ static void free_receive_page_frags(struct virtnet_info *vi) put_page(vi->rq[i].alloc_frag.page); } -static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q) -{ - if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs)) - return false; - else if (q < vi->curr_queue_pairs) - return true; - else - return false; -} - static void free_unused_bufs(struct virtnet_info *vi) { void *buf; From 188313c137c4f76afd0862f50dbc185b198b9e2a Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Tue, 29 Jan 2019 09:45:55 +0900 Subject: [PATCH 280/525] virtio_net: Fix not restoring real_num_rx_queues When _virtnet_set_queues() failed we did not restore real_num_rx_queues. Fix this by placing the change of real_num_rx_queues after _virtnet_set_queues(). This order is also in line with virtnet_set_channels(). Fixes: 4941d472bf95 ("virtio-net: do not reset during XDP set") Signed-off-by: Toshiaki Makita Acked-by: Jason Wang Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 046f955495a8..0e1a36908419 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2427,10 +2427,10 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, } } - netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp); err = _virtnet_set_queues(vi, curr_qp + xdp_qp); if (err) goto err; + netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp); vi->xdp_queue_pairs = xdp_qp; for (i = 0; i < vi->max_queue_pairs; i++) { From 1667c08a9d31c7cdf09f4890816bfbf20b685495 Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Tue, 29 Jan 2019 09:45:56 +0900 Subject: [PATCH 281/525] virtio_net: Fix out of bounds access of sq When XDP is disabled, curr_queue_pairs + smp_processor_id() can be larger than max_queue_pairs. There is no guarantee that we have enough XDP send queues dedicated for each cpu when XDP is disabled, so do not count drops on sq in that case. Fixes: 5b8f3c8d30a6 ("virtio_net: Add XDP related stats") Signed-off-by: Toshiaki Makita Acked-by: Jason Wang Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 0e1a36908419..669b65c232a2 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -491,20 +491,17 @@ static int virtnet_xdp_xmit(struct net_device *dev, int ret, err; int i; - sq = virtnet_xdp_sq(vi); - - if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) { - ret = -EINVAL; - drops = n; - goto out; - } - /* Only allow ndo_xdp_xmit if XDP is loaded on dev, as this * indicate XDP resources have been successfully allocated. */ xdp_prog = rcu_dereference(rq->xdp_prog); - if (!xdp_prog) { - ret = -ENXIO; + if (!xdp_prog) + return -ENXIO; + + sq = virtnet_xdp_sq(vi); + + if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) { + ret = -EINVAL; drops = n; goto out; } From 03aa6d34868c07b2b1b8b2db080602d7ec528173 Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Tue, 29 Jan 2019 09:45:57 +0900 Subject: [PATCH 282/525] virtio_net: Don't process redirected XDP frames when XDP is disabled Commit 8dcc5b0ab0ec ("virtio_net: fix ndo_xdp_xmit crash towards dev not ready for XDP") tried to avoid access to unexpected sq while XDP is disabled, but was not complete. There was a small window which causes out of bounds sq access in virtnet_xdp_xmit() while disabling XDP. An example case of - curr_queue_pairs = 6 (2 for SKB and 4 for XDP) - online_cpu_num = xdp_queue_paris = 4 when XDP is enabled: CPU 0 CPU 1 (Disabling XDP) (Processing redirected XDP frames) virtnet_xdp_xmit() virtnet_xdp_set() _virtnet_set_queues() set curr_queue_pairs (2) check if rq->xdp_prog is not NULL virtnet_xdp_sq(vi) qp = curr_queue_pairs - xdp_queue_pairs + smp_processor_id() = 2 - 4 + 1 = -1 sq = &vi->sq[qp] // out of bounds access set xdp_queue_pairs (0) rq->xdp_prog = NULL Basically we should not change curr_queue_pairs and xdp_queue_pairs while someone can read the values. Thus, when disabling XDP, assign NULL to rq->xdp_prog first, and wait for RCU grace period, then change xxx_queue_pairs. Note that we need to keep the current order when enabling XDP though. - v2: Make rcu_assign_pointer/synchronize_net conditional instead of _virtnet_set_queues. Fixes: 186b3c998c50 ("virtio-net: support XDP_REDIRECT") Signed-off-by: Toshiaki Makita Acked-by: Jason Wang Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 33 ++++++++++++++++++++++++++------- 1 file changed, 26 insertions(+), 7 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 669b65c232a2..cea52e47dc65 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2410,6 +2410,10 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, return -ENOMEM; } + old_prog = rtnl_dereference(vi->rq[0].xdp_prog); + if (!prog && !old_prog) + return 0; + if (prog) { prog = bpf_prog_add(prog, vi->max_queue_pairs - 1); if (IS_ERR(prog)) @@ -2424,21 +2428,30 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, } } + if (!prog) { + for (i = 0; i < vi->max_queue_pairs; i++) { + rcu_assign_pointer(vi->rq[i].xdp_prog, prog); + if (i == 0) + virtnet_restore_guest_offloads(vi); + } + synchronize_net(); + } + err = _virtnet_set_queues(vi, curr_qp + xdp_qp); if (err) goto err; netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp); vi->xdp_queue_pairs = xdp_qp; - for (i = 0; i < vi->max_queue_pairs; i++) { - old_prog = rtnl_dereference(vi->rq[i].xdp_prog); - rcu_assign_pointer(vi->rq[i].xdp_prog, prog); - if (i == 0) { - if (!old_prog) + if (prog) { + for (i = 0; i < vi->max_queue_pairs; i++) { + rcu_assign_pointer(vi->rq[i].xdp_prog, prog); + if (i == 0 && !old_prog) virtnet_clear_guest_offloads(vi); - if (!prog) - virtnet_restore_guest_offloads(vi); } + } + + for (i = 0; i < vi->max_queue_pairs; i++) { if (old_prog) bpf_prog_put(old_prog); if (netif_running(dev)) { @@ -2451,6 +2464,12 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, return 0; err: + if (!prog) { + virtnet_clear_guest_offloads(vi); + for (i = 0; i < vi->max_queue_pairs; i++) + rcu_assign_pointer(vi->rq[i].xdp_prog, old_prog); + } + if (netif_running(dev)) { for (i = 0; i < vi->max_queue_pairs; i++) { virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); From 07b344f494ddda9f061b396407c96df8c46c82b5 Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Tue, 29 Jan 2019 09:45:58 +0900 Subject: [PATCH 283/525] virtio_net: Use xdp_return_frame to free xdp_frames on destroying vqs put_page() can work as a fallback for freeing xdp_frames, but the appropriate way is to use xdp_return_frame(). Fixes: cac320c850ef ("virtio_net: convert to use generic xdp_frame and xdp_return_frame API") Signed-off-by: Toshiaki Makita Acked-by: Jason Wang Acked-by: Jesper Dangaard Brouer Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index cea52e47dc65..1d454cee641c 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2669,7 +2669,7 @@ static void free_unused_bufs(struct virtnet_info *vi) if (!is_xdp_raw_buffer_queue(vi, i)) dev_kfree_skb(buf); else - put_page(virt_to_head_page(buf)); + xdp_return_frame(buf); } } From 5050471d35d1316ba32dfcbb409978337eb9e75e Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Tue, 29 Jan 2019 09:45:59 +0900 Subject: [PATCH 284/525] virtio_net: Differentiate sk_buff and xdp_frame on freeing We do not reset or free up unused buffers when enabling/disabling XDP, so it can happen that xdp_frames are freed after disabling XDP or sk_buffs are freed after enabling XDP on xdp tx queues. Thus we need to handle both forms (xdp_frames and sk_buffs) regardless of XDP setting. One way to trigger this problem is to disable XDP when napi_tx is enabled. In that case, virtnet_xdp_set() calls virtnet_napi_enable() which kicks NAPI. The NAPI handler will call virtnet_poll_cleantx() which invokes free_old_xmit_skbs() for queues which have been used by XDP. Note that even with this change we need to keep skipping free_old_xmit_skbs() from NAPI handlers when XDP is enabled, because XDP tx queues do not aquire queue locks. - v2: Use napi_consume_skb() instead of dev_consume_skb_any() Fixes: 4941d472bf95 ("virtio-net: do not reset during XDP set") Signed-off-by: Toshiaki Makita Acked-by: Jason Wang Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 54 +++++++++++++++++++++++++++++++--------- 1 file changed, 42 insertions(+), 12 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 1d454cee641c..259448182272 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -57,6 +57,8 @@ module_param(napi_tx, bool, 0644); #define VIRTIO_XDP_TX BIT(0) #define VIRTIO_XDP_REDIR BIT(1) +#define VIRTIO_XDP_FLAG BIT(0) + /* RX packet size EWMA. The average packet size is used to determine the packet * buffer size when refilling RX rings. As the entire RX ring may be refilled * at once, the weight is chosen so that the EWMA will be insensitive to short- @@ -252,6 +254,21 @@ struct padded_vnet_hdr { char padding[4]; }; +static bool is_xdp_frame(void *ptr) +{ + return (unsigned long)ptr & VIRTIO_XDP_FLAG; +} + +static void *xdp_to_ptr(struct xdp_frame *ptr) +{ + return (void *)((unsigned long)ptr | VIRTIO_XDP_FLAG); +} + +static struct xdp_frame *ptr_to_xdp(void *ptr) +{ + return (struct xdp_frame *)((unsigned long)ptr & ~VIRTIO_XDP_FLAG); +} + /* Converting between virtqueue no. and kernel tx/rx queue no. * 0:rx0 1:tx0 2:rx1 3:tx1 ... 2N:rxN 2N+1:txN 2N+2:cvq */ @@ -462,7 +479,8 @@ static int __virtnet_xdp_xmit_one(struct virtnet_info *vi, sg_init_one(sq->sg, xdpf->data, xdpf->len); - err = virtqueue_add_outbuf(sq->vq, sq->sg, 1, xdpf, GFP_ATOMIC); + err = virtqueue_add_outbuf(sq->vq, sq->sg, 1, xdp_to_ptr(xdpf), + GFP_ATOMIC); if (unlikely(err)) return -ENOSPC; /* Caller handle free/refcnt */ @@ -482,13 +500,13 @@ static int virtnet_xdp_xmit(struct net_device *dev, { struct virtnet_info *vi = netdev_priv(dev); struct receive_queue *rq = vi->rq; - struct xdp_frame *xdpf_sent; struct bpf_prog *xdp_prog; struct send_queue *sq; unsigned int len; int drops = 0; int kicks = 0; int ret, err; + void *ptr; int i; /* Only allow ndo_xdp_xmit if XDP is loaded on dev, as this @@ -507,8 +525,12 @@ static int virtnet_xdp_xmit(struct net_device *dev, } /* Free up any pending old buffers before queueing new ones. */ - while ((xdpf_sent = virtqueue_get_buf(sq->vq, &len)) != NULL) - xdp_return_frame(xdpf_sent); + while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) { + if (likely(is_xdp_frame(ptr))) + xdp_return_frame(ptr_to_xdp(ptr)); + else + napi_consume_skb(ptr, false); + } for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; @@ -1329,18 +1351,26 @@ static int virtnet_receive(struct receive_queue *rq, int budget, static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi) { - struct sk_buff *skb; unsigned int len; unsigned int packets = 0; unsigned int bytes = 0; + void *ptr; - while ((skb = virtqueue_get_buf(sq->vq, &len)) != NULL) { - pr_debug("Sent skb %p\n", skb); + while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) { + if (likely(!is_xdp_frame(ptr))) { + struct sk_buff *skb = ptr; - bytes += skb->len; + pr_debug("Sent skb %p\n", skb); + + bytes += skb->len; + napi_consume_skb(skb, in_napi); + } else { + struct xdp_frame *frame = ptr_to_xdp(ptr); + + bytes += frame->len; + xdp_return_frame(frame); + } packets++; - - napi_consume_skb(skb, in_napi); } /* Avoid overhead when no packets have been processed @@ -2666,10 +2696,10 @@ static void free_unused_bufs(struct virtnet_info *vi) for (i = 0; i < vi->max_queue_pairs; i++) { struct virtqueue *vq = vi->sq[i].vq; while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) { - if (!is_xdp_raw_buffer_queue(vi, i)) + if (!is_xdp_frame(buf)) dev_kfree_skb(buf); else - xdp_return_frame(buf); + xdp_return_frame(ptr_to_xdp(buf)); } } From ef489749aae508e6f17886775c075f12ff919fb1 Mon Sep 17 00:00:00 2001 From: Yohei Kanemaru Date: Tue, 29 Jan 2019 15:52:34 +0900 Subject: [PATCH 285/525] ipv6: sr: clear IP6CB(skb) on SRH ip4ip6 encapsulation skb->cb may contain data from previous layers (in an observed case IPv4 with L3 Master Device). In the observed scenario, the data in IPCB(skb)->frags was misinterpreted as IP6CB(skb)->frag_max_size, eventually caused an unexpected IPv6 fragmentation in ip6_fragment() through ip6_finish_output(). This patch clears IP6CB(skb), which potentially contains garbage data, on the SRH ip4ip6 encapsulation. Fixes: 32d99d0b6702 ("ipv6: sr: add support for ip4ip6 encapsulation") Signed-off-by: Yohei Kanemaru Signed-off-by: David S. Miller --- net/ipv6/seg6_iptunnel.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 8181ee7e1e27..ee5403cbe655 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -146,6 +146,8 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) } else { ip6_flow_hdr(hdr, 0, flowlabel); hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb)); + + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); } hdr->nexthdr = NEXTHDR_ROUTING; From 3a03cb8456cc1d61c467a5375e0a10e5207b948c Mon Sep 17 00:00:00 2001 From: George Amanakis Date: Tue, 29 Jan 2019 22:50:13 -0500 Subject: [PATCH 286/525] tun: move the call to tun_set_real_num_queues Call tun_set_real_num_queues() after the increment of tun->numqueues since the former depends on it. Otherwise, the number of queues is not correctly accounted for, which results to warnings similar to: "vnet0 selects TX queue 11, but real number of TX queues is 11". Fixes: 0b7959b62573 ("tun: publish tfile after it's fully initialized") Reported-and-tested-by: George Amanakis Signed-off-by: George Amanakis Signed-off-by: Stanislav Fomichev Signed-off-by: David S. Miller --- drivers/net/tun.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 18656c4094b3..fed298c0cb39 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -866,8 +866,6 @@ static int tun_attach(struct tun_struct *tun, struct file *file, if (rtnl_dereference(tun->xdp_prog)) sock_set_flag(&tfile->sk, SOCK_XDP); - tun_set_real_num_queues(tun); - /* device is allowed to go away first, so no need to hold extra * refcnt. */ @@ -879,6 +877,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file, rcu_assign_pointer(tfile->tun, tun); rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile); tun->numqueues++; + tun_set_real_num_queues(tun); out: return err; } From 4522a70db7aa5e77526a4079628578599821b193 Mon Sep 17 00:00:00 2001 From: Jacob Wen Date: Wed, 30 Jan 2019 14:55:14 +0800 Subject: [PATCH 287/525] l2tp: fix reading optional fields of L2TPv3 Use pskb_may_pull() to make sure the optional fields are in skb linear parts, so we can safely read them later. It's easy to reproduce the issue with a net driver that supports paged skb data. Just create a L2TPv3 over IP tunnel and then generates some network traffic. Once reproduced, rx err in /sys/kernel/debug/l2tp/tunnels will increase. Changes in v4: 1. s/l2tp_v3_pull_opt/l2tp_v3_ensure_opt_in_linear/ 2. s/tunnel->version != L2TP_HDR_VER_2/tunnel->version == L2TP_HDR_VER_3/ 3. Add 'Fixes' in commit messages. Changes in v3: 1. To keep consistency, move the code out of l2tp_recv_common. 2. Use "net" instead of "net-next", since this is a bug fix. Changes in v2: 1. Only fix L2TPv3 to make code simple. To fix both L2TPv3 and L2TPv2, we'd better refactor l2tp_recv_common. It's complicated to do so. 2. Reloading pointers after pskb_may_pull Fixes: f7faffa3ff8e ("l2tp: Add L2TPv3 protocol support") Fixes: 0d76751fad77 ("l2tp: Add L2TPv3 IP encapsulation (no UDP) support") Fixes: a32e0eec7042 ("l2tp: introduce L2TPv3 IP encapsulation support for IPv6") Signed-off-by: Jacob Wen Acked-by: Guillaume Nault Signed-off-by: David S. Miller --- net/l2tp/l2tp_core.c | 4 ++++ net/l2tp/l2tp_core.h | 20 ++++++++++++++++++++ net/l2tp/l2tp_ip.c | 3 +++ net/l2tp/l2tp_ip6.c | 3 +++ 4 files changed, 30 insertions(+) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 26f1d435696a..dd5ba0c11ab3 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -884,6 +884,10 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) goto error; } + if (tunnel->version == L2TP_HDR_VER_3 && + l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) + goto error; + l2tp_recv_common(session, skb, ptr, optr, hdrflags, length); l2tp_session_dec_refcount(session); diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 9c9afe94d389..b2ce90260c35 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -301,6 +301,26 @@ static inline bool l2tp_tunnel_uses_xfrm(const struct l2tp_tunnel *tunnel) } #endif +static inline int l2tp_v3_ensure_opt_in_linear(struct l2tp_session *session, struct sk_buff *skb, + unsigned char **ptr, unsigned char **optr) +{ + int opt_len = session->peer_cookie_len + l2tp_get_l2specific_len(session); + + if (opt_len > 0) { + int off = *ptr - *optr; + + if (!pskb_may_pull(skb, off + opt_len)) + return -1; + + if (skb->data != *optr) { + *optr = skb->data; + *ptr = skb->data + off; + } + } + + return 0; +} + #define l2tp_printk(ptr, type, func, fmt, ...) \ do { \ if (((ptr)->debug) & (type)) \ diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 35f6f86d4dcc..d4c60523c549 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -165,6 +165,9 @@ static int l2tp_ip_recv(struct sk_buff *skb) print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); } + if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) + goto discard_sess; + l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); l2tp_session_dec_refcount(session); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 237f1a4a0b0c..0ae6899edac0 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -178,6 +178,9 @@ static int l2tp_ip6_recv(struct sk_buff *skb) print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); } + if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) + goto discard_sess; + l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); l2tp_session_dec_refcount(session); From d5256083f62e2720f75bb3c5a928a0afe47d6bc3 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 30 Jan 2019 12:49:48 +0100 Subject: [PATCH 288/525] ipvlan, l3mdev: fix broken l3s mode wrt local routes While implementing ipvlan l3 and l3s mode for kubernetes CNI plugin, I ran into the issue that while l3 mode is working fine, l3s mode does not have any connectivity to kube-apiserver and hence all pods end up in Error state as well. The ipvlan master device sits on top of a bond device and hostns traffic to kube-apiserver (also running in hostns) is DNATed from 10.152.183.1:443 to 139.178.29.207:37573 where the latter is the address of the bond0. While in l3 mode, a curl to https://10.152.183.1:443 or to https://139.178.29.207:37573 works fine from hostns, neither of them do in case of l3s. In the latter only a curl to https://127.0.0.1:37573 appeared to work where for local addresses of bond0 I saw kernel suddenly starting to emit ARP requests to query HW address of bond0 which remained unanswered and neighbor entries in INCOMPLETE state. These ARP requests only happen while in l3s. Debugging this further, I found the issue is that l3s mode is piggy- backing on l3 master device, and in this case local routes are using l3mdev_master_dev_rcu(dev) instead of net->loopback_dev as per commit f5a0aab84b74 ("net: ipv4: dst for local input routes should use l3mdev if relevant") and 5f02ce24c269 ("net: l3mdev: Allow the l3mdev to be a loopback"). I found that reverting them back into using the net->loopback_dev fixed ipvlan l3s connectivity and got everything working for the CNI. Now judging from 4fbae7d83c98 ("ipvlan: Introduce l3s mode") and the l3mdev paper in [0] the only sole reason why ipvlan l3s is relying on l3 master device is to get the l3mdev_ip_rcv() receive hook for setting the dst entry of the input route without adding its own ipvlan specific hacks into the receive path, however, any l3 domain semantics beyond just that are breaking l3s operation. Note that ipvlan also has the ability to dynamically switch its internal operation from l3 to l3s for all ports via ipvlan_set_port_mode() at runtime. In any case, l3 vs l3s soley distinguishes itself by 'de-confusing' netfilter through switching skb->dev to ipvlan slave device late in NF_INET_LOCAL_IN before handing the skb to L4. Minimal fix taken here is to add a IFF_L3MDEV_RX_HANDLER flag which, if set from ipvlan setup, gets us only the wanted l3mdev_l3_rcv() hook without any additional l3mdev semantics on top. This should also have minimal impact since dev->priv_flags is already hot in cache. With this set, l3s mode is working fine and I also get things like masquerading pod traffic on the ipvlan master properly working. [0] https://netdevconf.org/1.2/papers/ahern-what-is-l3mdev-paper.pdf Fixes: f5a0aab84b74 ("net: ipv4: dst for local input routes should use l3mdev if relevant") Fixes: 5f02ce24c269 ("net: l3mdev: Allow the l3mdev to be a loopback") Fixes: 4fbae7d83c98 ("ipvlan: Introduce l3s mode") Signed-off-by: Daniel Borkmann Cc: Mahesh Bandewar Cc: David Ahern Cc: Florian Westphal Cc: Martynas Pumputis Acked-by: David Ahern Signed-off-by: David S. Miller --- drivers/net/ipvlan/ipvlan_main.c | 6 +++--- include/linux/netdevice.h | 8 ++++++++ include/net/l3mdev.h | 3 ++- 3 files changed, 13 insertions(+), 4 deletions(-) diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 19bdde60680c..7cdac77d0c68 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -100,12 +100,12 @@ static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval, err = ipvlan_register_nf_hook(read_pnet(&port->pnet)); if (!err) { mdev->l3mdev_ops = &ipvl_l3mdev_ops; - mdev->priv_flags |= IFF_L3MDEV_MASTER; + mdev->priv_flags |= IFF_L3MDEV_RX_HANDLER; } else goto fail; } else if (port->mode == IPVLAN_MODE_L3S) { /* Old mode was L3S */ - mdev->priv_flags &= ~IFF_L3MDEV_MASTER; + mdev->priv_flags &= ~IFF_L3MDEV_RX_HANDLER; ipvlan_unregister_nf_hook(read_pnet(&port->pnet)); mdev->l3mdev_ops = NULL; } @@ -167,7 +167,7 @@ static void ipvlan_port_destroy(struct net_device *dev) struct sk_buff *skb; if (port->mode == IPVLAN_MODE_L3S) { - dev->priv_flags &= ~IFF_L3MDEV_MASTER; + dev->priv_flags &= ~IFF_L3MDEV_RX_HANDLER; ipvlan_unregister_nf_hook(dev_net(dev)); dev->l3mdev_ops = NULL; } diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1377d085ef99..86dbb3e29139 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1483,6 +1483,7 @@ struct net_device_ops { * @IFF_NO_RX_HANDLER: device doesn't support the rx_handler hook * @IFF_FAILOVER: device is a failover master device * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device + * @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1514,6 +1515,7 @@ enum netdev_priv_flags { IFF_NO_RX_HANDLER = 1<<26, IFF_FAILOVER = 1<<27, IFF_FAILOVER_SLAVE = 1<<28, + IFF_L3MDEV_RX_HANDLER = 1<<29, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1544,6 +1546,7 @@ enum netdev_priv_flags { #define IFF_NO_RX_HANDLER IFF_NO_RX_HANDLER #define IFF_FAILOVER IFF_FAILOVER #define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE +#define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER /** * struct net_device - The DEVICE structure. @@ -4549,6 +4552,11 @@ static inline bool netif_supports_nofcs(struct net_device *dev) return dev->priv_flags & IFF_SUPP_NOFCS; } +static inline bool netif_has_l3_rx_handler(const struct net_device *dev) +{ + return dev->priv_flags & IFF_L3MDEV_RX_HANDLER; +} + static inline bool netif_is_l3_master(const struct net_device *dev) { return dev->priv_flags & IFF_L3MDEV_MASTER; diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index 78fa0ac4613c..5175fd63cd82 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -153,7 +153,8 @@ struct sk_buff *l3mdev_l3_rcv(struct sk_buff *skb, u16 proto) if (netif_is_l3_slave(skb->dev)) master = netdev_master_upper_dev_get_rcu(skb->dev); - else if (netif_is_l3_master(skb->dev)) + else if (netif_is_l3_master(skb->dev) || + netif_has_l3_rx_handler(skb->dev)) master = skb->dev; if (master && master->l3mdev_ops->l3mdev_l3_rcv) From 4ec5302fa906ec9d86597b236f62315bacdb9622 Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Wed, 30 Jan 2019 15:54:19 +0100 Subject: [PATCH 289/525] net: stmmac: Fallback to Platform Data clock in Watchdog conversion If we don't have DT then stmmac_clk will not be available. Let's add a new Platform Data field so that we can specify the refclk by this mean. This way we can still use the coalesce command in PCI based setups. Signed-off-by: Jose Abreu Cc: Joao Pinto Cc: David S. Miller Cc: Giuseppe Cavallaro Cc: Alexandre Torgue Signed-off-by: David S. Miller --- .../net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 14 ++++++++++---- include/linux/stmmac.h | 1 + 2 files changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index d1f61c25d82b..5d85742a2be0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -721,8 +721,11 @@ static u32 stmmac_usec2riwt(u32 usec, struct stmmac_priv *priv) { unsigned long clk = clk_get_rate(priv->plat->stmmac_clk); - if (!clk) - return 0; + if (!clk) { + clk = priv->plat->clk_ref_rate; + if (!clk) + return 0; + } return (usec * (clk / 1000000)) / 256; } @@ -731,8 +734,11 @@ static u32 stmmac_riwt2usec(u32 riwt, struct stmmac_priv *priv) { unsigned long clk = clk_get_rate(priv->plat->stmmac_clk); - if (!clk) - return 0; + if (!clk) { + clk = priv->plat->clk_ref_rate; + if (!clk) + return 0; + } return (riwt * 256) / (clk / 1000000); } diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 7ddfc65586b0..4335bd771ce5 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -184,6 +184,7 @@ struct plat_stmmacenet_data { struct clk *pclk; struct clk *clk_ptp_ref; unsigned int clk_ptp_rate; + unsigned int clk_ref_rate; struct reset_control *stmmac_rst; struct stmmac_axi *axi; int has_gmac4; From c5acdbee22a1b200dde07effd26fd1f649e9ab8a Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Wed, 30 Jan 2019 15:54:20 +0100 Subject: [PATCH 290/525] net: stmmac: Send TSO packets always from Queue 0 The number of TSO enabled channels in HW can be different than the number of total channels. There is no way to determined, at runtime, the number of TSO capable channels and its safe to assume that if TSO is enabled then at least channel 0 will be TSO capable. Lets always send TSO packets from Queue 0. Signed-off-by: Jose Abreu Cc: Joao Pinto Cc: David S. Miller Cc: Giuseppe Cavallaro Cc: Alexandre Torgue Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 5afba69981cf..6656008068de 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3025,8 +3025,17 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) /* Manage oversized TCP frames for GMAC4 device */ if (skb_is_gso(skb) && priv->tso) { - if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) + if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) { + /* + * There is no way to determine the number of TSO + * capable Queues. Let's use always the Queue 0 + * because if TSO is supported then at least this + * one will be capable. + */ + skb_set_queue_mapping(skb, 0); + return stmmac_tso_xmit(skb, dev); + } } if (unlikely(stmmac_tx_avail(priv, queue) < nfrags + 1)) { From e2cd682deb231ba6f80524bb84e57e7138261149 Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Wed, 30 Jan 2019 15:54:21 +0100 Subject: [PATCH 291/525] net: stmmac: Disable EEE mode earlier in XMIT callback In stmmac xmit callback we use a different flow for TSO packets but TSO xmit callback is not disabling the EEE mode. Fix this by disabling earlier the EEE mode, i.e. before calling the TSO xmit callback. Signed-off-by: Jose Abreu Cc: Joao Pinto Cc: David S. Miller Cc: Giuseppe Cavallaro Cc: Alexandre Torgue Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 6656008068de..685d20472358 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3023,6 +3023,9 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) tx_q = &priv->tx_queue[queue]; + if (priv->tx_path_in_lpi_mode) + stmmac_disable_eee_mode(priv); + /* Manage oversized TCP frames for GMAC4 device */ if (skb_is_gso(skb) && priv->tso) { if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) { @@ -3050,9 +3053,6 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_BUSY; } - if (priv->tx_path_in_lpi_mode) - stmmac_disable_eee_mode(priv); - entry = tx_q->cur_tx; first_entry = entry; WARN_ON(tx_q->tx_skbuff[first_entry]); From a07ddce4df807e41a85245e769b6f6f14f0c6db0 Mon Sep 17 00:00:00 2001 From: Kyle Tso Date: Wed, 30 Jan 2019 11:13:53 +0800 Subject: [PATCH 292/525] usb: typec: tcpm: Correct the PPS out_volt calculation When Sink negotiates PPS, the voltage range of selected PPS APDO might not cover the previous voltage (out_volt). If the previous out_volt is lower than the new min_volt, the output voltage in RDO might be set to an invalid value. For instance, supposed that the previous voltage is 5V, and the new voltage range in the APDO is 7V-12V. Then the output voltage in the RDO should not be set to 5V which is lower than the possible min_volt 7V. Fix this by choosing the maximal value between the previous voltage and the new min_volt first. And ensure that this value will not exceed the new max_volt. The new out_volt will fall within the new voltage range while being the closest value compared to the previous out_volt. Signed-off-by: Kyle Tso Reviewed-by: Adam Thomson Reviewed-by: Guenter Roeck Reviewed-by: Heikki Krogerus Fixes: c710d0bb76ff0 ("usb: typec: tcpm: Extend the matching rules on PPS APDO selection") Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/tcpm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 4bc29b586698..f1c39a3c7534 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -2297,7 +2297,8 @@ static unsigned int tcpm_pd_select_pps_apdo(struct tcpm_port *port) pdo_pps_apdo_max_voltage(snk)); port->pps_data.max_curr = min_pps_apdo_current(src, snk); port->pps_data.out_volt = min(port->pps_data.max_volt, - port->pps_data.out_volt); + max(port->pps_data.min_volt, + port->pps_data.out_volt)); port->pps_data.op_curr = min(port->pps_data.max_curr, port->pps_data.op_curr); } From 579b9239c1f38665b21e8d0e6ee83ecc96dbd6bb Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 23 Jan 2019 11:51:38 +0530 Subject: [PATCH 293/525] powerpc/radix: Fix kernel crash with mremap() With support for split pmd lock, we use pmd page pmd_huge_pte pointer to store the deposited page table. In those config when we move page tables we need to make sure we move the deposited page table to the correct pmd page. Otherwise this can result in crash when we withdraw of deposited page table because we can find the pmd_huge_pte NULL. eg: __split_huge_pmd+0x1070/0x1940 __split_huge_pmd+0xe34/0x1940 (unreliable) vma_adjust_trans_huge+0x110/0x1c0 __vma_adjust+0x2b4/0x9b0 __split_vma+0x1b8/0x280 __do_munmap+0x13c/0x550 sys_mremap+0x220/0x7e0 system_call+0x5c/0x70 Fixes: 675d995297d4 ("powerpc/book3s64: Enable split pmd ptlock.") Cc: stable@vger.kernel.org # v4.18+ Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/64/pgtable.h | 22 +++++++------------- arch/powerpc/mm/pgtable-book3s64.c | 22 ++++++++++++++++++++ 2 files changed, 29 insertions(+), 15 deletions(-) diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 2e6ada28da64..c9bfe526ca9d 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -1258,21 +1258,13 @@ extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, #define pmd_move_must_withdraw pmd_move_must_withdraw struct spinlock; -static inline int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, - struct spinlock *old_pmd_ptl, - struct vm_area_struct *vma) -{ - if (radix_enabled()) - return false; - /* - * Archs like ppc64 use pgtable to store per pmd - * specific information. So when we switch the pmd, - * we should also withdraw and deposit the pgtable - */ - return true; -} - - +extern int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, + struct spinlock *old_pmd_ptl, + struct vm_area_struct *vma); +/* + * Hash translation mode use the deposited table to store hash pte + * slot information. + */ #define arch_needs_pgtable_deposit arch_needs_pgtable_deposit static inline bool arch_needs_pgtable_deposit(void) { diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index f3c31f5e1026..ecd31569a120 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -400,3 +400,25 @@ void arch_report_meminfo(struct seq_file *m) atomic_long_read(&direct_pages_count[MMU_PAGE_1G]) << 20); } #endif /* CONFIG_PROC_FS */ + +/* + * For hash translation mode, we use the deposited table to store hash slot + * information and they are stored at PTRS_PER_PMD offset from related pmd + * location. Hence a pmd move requires deposit and withdraw. + * + * For radix translation with split pmd ptl, we store the deposited table in the + * pmd page. Hence if we have different pmd page we need to withdraw during pmd + * move. + * + * With hash we use deposited table always irrespective of anon or not. + * With radix we use deposited table only for anonymous mapping. + */ +int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, + struct spinlock *old_pmd_ptl, + struct vm_area_struct *vma) +{ + if (radix_enabled()) + return (new_pmd_ptl != old_pmd_ptl) && vma_is_anonymous(vma); + + return true; +} From 13c15e07eedf26092054c8c71f2f47edb8388310 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 24 Jan 2019 15:20:07 +0100 Subject: [PATCH 294/525] mtd: spinand: Handle the case where PROGRAM LOAD does not reset the cache Looks like PROGRAM LOAD (AKA write cache) does not necessarily reset the cache content to 0xFF (depends on vendor implementation), so we must fill the page cache entirely even if we only want to program the data portion of the page, otherwise we might corrupt the BBM or user data previously programmed in OOB area. Fixes: 7529df465248 ("mtd: nand: Add core infrastructure to support SPI NANDs") Reported-by: Stefan Roese Cc: Signed-off-by: Boris Brezillon Tested-by: Stefan Roese Reviewed-by: Stefan Roese Acked-by: Miquel Raynal --- drivers/mtd/nand/spi/core.c | 42 ++++++++++++++++++------------------- 1 file changed, 20 insertions(+), 22 deletions(-) diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c index 479c2f2cf17f..8bf37da19663 100644 --- a/drivers/mtd/nand/spi/core.c +++ b/drivers/mtd/nand/spi/core.c @@ -304,24 +304,30 @@ static int spinand_write_to_cache_op(struct spinand_device *spinand, struct nand_device *nand = spinand_to_nand(spinand); struct mtd_info *mtd = nanddev_to_mtd(nand); struct nand_page_io_req adjreq = *req; - unsigned int nbytes = 0; - void *buf = NULL; + void *buf = spinand->databuf; + unsigned int nbytes; u16 column = 0; int ret; - memset(spinand->databuf, 0xff, - nanddev_page_size(nand) + - nanddev_per_page_oobsize(nand)); + /* + * Looks like PROGRAM LOAD (AKA write cache) does not necessarily reset + * the cache content to 0xFF (depends on vendor implementation), so we + * must fill the page cache entirely even if we only want to program + * the data portion of the page, otherwise we might corrupt the BBM or + * user data previously programmed in OOB area. + */ + nbytes = nanddev_page_size(nand) + nanddev_per_page_oobsize(nand); + memset(spinand->databuf, 0xff, nbytes); + adjreq.dataoffs = 0; + adjreq.datalen = nanddev_page_size(nand); + adjreq.databuf.out = spinand->databuf; + adjreq.ooblen = nanddev_per_page_oobsize(nand); + adjreq.ooboffs = 0; + adjreq.oobbuf.out = spinand->oobbuf; - if (req->datalen) { + if (req->datalen) memcpy(spinand->databuf + req->dataoffs, req->databuf.out, req->datalen); - adjreq.dataoffs = 0; - adjreq.datalen = nanddev_page_size(nand); - adjreq.databuf.out = spinand->databuf; - nbytes = adjreq.datalen; - buf = spinand->databuf; - } if (req->ooblen) { if (req->mode == MTD_OPS_AUTO_OOB) @@ -332,14 +338,6 @@ static int spinand_write_to_cache_op(struct spinand_device *spinand, else memcpy(spinand->oobbuf + req->ooboffs, req->oobbuf.out, req->ooblen); - - adjreq.ooblen = nanddev_per_page_oobsize(nand); - adjreq.ooboffs = 0; - nbytes += nanddev_per_page_oobsize(nand); - if (!buf) { - buf = spinand->oobbuf; - column = nanddev_page_size(nand); - } } spinand_cache_op_adjust_colum(spinand, &adjreq, &column); @@ -370,8 +368,8 @@ static int spinand_write_to_cache_op(struct spinand_device *spinand, /* * We need to use the RANDOM LOAD CACHE operation if there's - * more than one iteration, because the LOAD operation resets - * the cache to 0xff. + * more than one iteration, because the LOAD operation might + * reset the cache to 0xff. */ if (nbytes) { column = op.addr.val; From c3c7dbf4887ab3ed9d611cd1f6e16937f8700743 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 24 Jan 2019 15:46:54 +0100 Subject: [PATCH 295/525] mtd: spinand: Fix the error/cleanup path in spinand_init() The manufacturer specific initialization has already been done when block unlocking takes place, and if anything goes wrong during this procedure we should call spinand_manufacturer_cleanup(). Fixes: 7529df465248 ("mtd: nand: Add core infrastructure to support SPI NANDs") Cc: Signed-off-by: Boris Brezillon Acked-by: Miquel Raynal --- drivers/mtd/nand/spi/core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c index 8bf37da19663..fa87ae28cdfe 100644 --- a/drivers/mtd/nand/spi/core.c +++ b/drivers/mtd/nand/spi/core.c @@ -1016,11 +1016,11 @@ static int spinand_init(struct spinand_device *spinand) for (i = 0; i < nand->memorg.ntargets; i++) { ret = spinand_select_target(spinand, i); if (ret) - goto err_free_bufs; + goto err_manuf_cleanup; ret = spinand_lock_block(spinand, BL_ALL_UNLOCKED); if (ret) - goto err_free_bufs; + goto err_manuf_cleanup; } ret = nanddev_init(nand, &spinand_ops, THIS_MODULE); From 455e7b387b441ddd1da1df35251c179fe7805b53 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 27 Jan 2019 18:21:42 -0800 Subject: [PATCH 296/525] mtd: rawnand: fix kernel-doc warnings Fix kernel-doc warnings in drivers/mtd/nand/raw: ../drivers/mtd/nand/raw/nand_base.c:420: warning: Function parameter or member 'chip' not described in 'nand_fill_oob' ../drivers/mtd/nand/raw/nand_bbt.c:173: warning: Function parameter or member 'this' not described in 'read_bbt' ../drivers/mtd/nand/raw/nand_bbt.c:173: warning: Excess function parameter 'chip' description in 'read_bbt' Fixes: 0813621ba898a ("mtd: rawnand: Stop passing mtd_info objects to internal functions") Signed-off-by: Randy Dunlap Cc: Boris Brezillon Cc: Miquel Raynal Cc: Richard Weinberger Cc: linux-mtd@lists.infradead.org Acked-by: Miquel Raynal Signed-off-by: Boris Brezillon --- drivers/mtd/nand/raw/nand_base.c | 1 + drivers/mtd/nand/raw/nand_bbt.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index cca4b24d2ffa..839494ac457c 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -410,6 +410,7 @@ static int nand_check_wp(struct nand_chip *chip) /** * nand_fill_oob - [INTERN] Transfer client buffer to oob + * @chip: NAND chip object * @oob: oob data buffer * @len: oob data write length * @ops: oob ops structure diff --git a/drivers/mtd/nand/raw/nand_bbt.c b/drivers/mtd/nand/raw/nand_bbt.c index 1b722fe9213c..19a2b563acdf 100644 --- a/drivers/mtd/nand/raw/nand_bbt.c +++ b/drivers/mtd/nand/raw/nand_bbt.c @@ -158,7 +158,7 @@ static u32 add_marker_len(struct nand_bbt_descr *td) /** * read_bbt - [GENERIC] Read the bad block table starting from page - * @chip: NAND chip object + * @this: NAND chip object * @buf: temporary buffer * @page: the starting page * @num: the number of bbt descriptors to read From 89e3a5682edaa4e5bb334719afb180256ac7bf78 Mon Sep 17 00:00:00 2001 From: Jeremy Soller Date: Wed, 30 Jan 2019 16:12:31 -0700 Subject: [PATCH 297/525] ALSA: hda/realtek - Headset microphone support for System76 darp5 On the System76 Darter Pro (darp5), there is a headset microphone input attached to 0x1a that does not have a jack detect. In order to get it working, the pin configuration needs to be set correctly, and the ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC fixup needs to be applied. This is similar to the MIC_NO_PRESENCE fixups for some Dell laptops, except we have a separate microphone jack that is already configured correctly. Signed-off-by: Jeremy Soller Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 4139aced63f8..f2523fab5fed 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5634,6 +5634,7 @@ enum { ALC294_FIXUP_ASUS_HEADSET_MIC, ALC294_FIXUP_ASUS_SPK, ALC225_FIXUP_HEADSET_JACK, + ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE, }; static const struct hda_fixup alc269_fixups[] = { @@ -6580,6 +6581,15 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc_fixup_headset_jack, }, + [ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x1a, 0x01a1913c }, /* use as headset mic, without its own jack detect */ + { } + }, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -6758,6 +6768,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb171, "Cubi N 8GL (MS-B171)", ALC283_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1558, 0x1325, "System76 Darter Pro (darp5)", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC233_FIXUP_LENOVO_MULTI_CODECS), SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE), From 56841070ccc87b463ac037d2d1f2beb8e5e35f0c Mon Sep 17 00:00:00 2001 From: Zenghui Yu Date: Thu, 31 Jan 2019 11:19:43 +0000 Subject: [PATCH 298/525] irqchip/gic-v3-its: Fix ITT_entry_size accessor According to ARM IHI 0069C (ID070116), we should use GITS_TYPER's bits [7:4] as ITT_entry_size instead of [8:4]. Although this is pretty annoying, it only results in a potential over-allocation of memory, and nothing bad happens. Fixes: 3dfa576bfb45 ("irqchip/gic-v3-its: Add probing for VLPI properties") Signed-off-by: Zenghui Yu [maz: massaged subject and commit message] Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 071b4cbdf010..c848a7cc502e 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -319,7 +319,7 @@ #define GITS_TYPER_PLPIS (1UL << 0) #define GITS_TYPER_VLPIS (1UL << 1) #define GITS_TYPER_ITT_ENTRY_SIZE_SHIFT 4 -#define GITS_TYPER_ITT_ENTRY_SIZE(r) ((((r) >> GITS_TYPER_ITT_ENTRY_SIZE_SHIFT) & 0x1f) + 1) +#define GITS_TYPER_ITT_ENTRY_SIZE(r) ((((r) >> GITS_TYPER_ITT_ENTRY_SIZE_SHIFT) & 0xf) + 1) #define GITS_TYPER_IDBITS_SHIFT 8 #define GITS_TYPER_DEVBITS_SHIFT 13 #define GITS_TYPER_DEVBITS(r) ((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1) From 2c1cf00eeacb784781cf1c9896b8af001246d339 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 31 Jan 2019 13:57:58 +0100 Subject: [PATCH 299/525] relay: check return of create_buf_file() properly If create_buf_file() returns an error, don't try to reference it later as a valid dentry pointer. This problem was exposed when debugfs started to return errors instead of just NULL for some calls when they do not succeed properly. Also, the check for WARN_ON(dentry) was just wrong :) Reported-by: Kees Cook Reported-and-tested-by: syzbot+16c3a70e1e9b29346c43@syzkaller.appspotmail.com Reported-by: Tetsuo Handa Cc: Andrew Morton Cc: David Rientjes Fixes: ff9fb72bc077 ("debugfs: return error values, not NULL") Signed-off-by: Greg Kroah-Hartman --- kernel/relay.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/kernel/relay.c b/kernel/relay.c index 04f248644e06..9e0f52375487 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -428,6 +428,8 @@ static struct dentry *relay_create_buf_file(struct rchan *chan, dentry = chan->cb->create_buf_file(tmpname, chan->parent, S_IRUSR, buf, &chan->is_global); + if (IS_ERR(dentry)) + dentry = NULL; kfree(tmpname); @@ -461,7 +463,7 @@ static struct rchan_buf *relay_open_buf(struct rchan *chan, unsigned int cpu) dentry = chan->cb->create_buf_file(NULL, NULL, S_IRUSR, buf, &chan->is_global); - if (WARN_ON(dentry)) + if (IS_ERR_OR_NULL(dentry)) goto free_buf; } From d339adc12a4f885b572c5412e4869af8939db854 Mon Sep 17 00:00:00 2001 From: Aurelien Aptel Date: Thu, 31 Jan 2019 13:46:07 +0100 Subject: [PATCH 300/525] CIFS: fix use-after-free of the lease keys The request buffers are freed right before copying the pointers. Use the func args instead which are identical and still valid. Simple reproducer (requires KASAN enabled) on a cifs mount: echo foo > foo ; tail -f foo & rm foo Cc: # 4.20 Fixes: 179e44d49c2f ("smb3: add tracepoint for sending lease break responses to server") Signed-off-by: Aurelien Aptel Signed-off-by: Steve French Reviewed-by: Paulo Alcantara --- fs/cifs/smb2pdu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index ef52d6642431..77b3aaa39b35 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -4441,8 +4441,8 @@ SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon, rc = cifs_send_recv(xid, ses, &rqst, &resp_buf_type, flags, &rsp_iov); cifs_small_buf_release(req); - please_key_low = (__u64 *)req->LeaseKey; - please_key_high = (__u64 *)(req->LeaseKey+8); + please_key_low = (__u64 *)lease_key; + please_key_high = (__u64 *)(lease_key+8); if (rc) { cifs_stats_fail_inc(tcon, SMB2_OPLOCK_BREAK_HE); trace_smb3_lease_err(le32_to_cpu(lease_state), tcon->tid, From b9b9378b49030d1aeca2387660fcd1ac1f306cad Mon Sep 17 00:00:00 2001 From: Steve French Date: Tue, 29 Jan 2019 17:27:33 -0600 Subject: [PATCH 301/525] cifs: update internal module version number To 2.17 Signed-off-by: Steve French --- fs/cifs/cifsfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index d1f9c2f3f575..7652551a1fc4 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -150,5 +150,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ -#define CIFS_VERSION "2.16" +#define CIFS_VERSION "2.17" #endif /* _CIFSFS_H */ From 36991ca68db9dd43bac7f3519f080ee3939263ef Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 23 Jan 2019 14:48:54 +0100 Subject: [PATCH 302/525] blk-mq: protect debugfs_create_files() from failures If debugfs were to return a non-NULL error for a debugfs call, using that pointer later in debugfs_create_files() would crash. Fix that by properly checking the pointer before referencing it. Reported-by: Michal Hocko Reported-and-tested-by: syzbot+b382ba6a802a3d242790@syzkaller.appspotmail.com Reported-by: Tetsuo Handa Signed-off-by: Greg Kroah-Hartman --- block/blk-mq-debugfs.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 90d68760af08..777638f597aa 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -838,6 +838,9 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_ctx_attrs[] = { static bool debugfs_create_files(struct dentry *parent, void *data, const struct blk_mq_debugfs_attr *attr) { + if (IS_ERR_OR_NULL(parent)) + return false; + d_inode(parent)->i_private = data; for (; attr->name; attr++) { From 32a66374487bbd78115747f0084cea5e8fca4c80 Mon Sep 17 00:00:00 2001 From: Nicolas Saenz Julienne Date: Sat, 26 Jan 2019 10:38:29 -0600 Subject: [PATCH 303/525] fpga: stratix10-soc: fix wrong of_node_put() in init function After finding a "firmware" dt node stratix10 tries to match it's compatible string with it. To do so it's calling of_find_matching_node() which already takes care of decreasing the refcount on the "firmware" node. We are then incorrectly decreasing the refcount on that node again. This patch removes the unwarranted call to of_node_put(). Fixes: e7eef1d7633a ("fpga: add intel stratix10 soc fpga manager driver") Signed-off-by: Nicolas Saenz Julienne Acked-by: Alan Tull Acked-by: Moritz Fischer [atull: remove unnecessary braces] Signed-off-by: Greg Kroah-Hartman --- drivers/fpga/stratix10-soc.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/fpga/stratix10-soc.c b/drivers/fpga/stratix10-soc.c index a1a09e04fab8..13851b3d1c56 100644 --- a/drivers/fpga/stratix10-soc.c +++ b/drivers/fpga/stratix10-soc.c @@ -508,14 +508,11 @@ static int __init s10_init(void) return -ENODEV; np = of_find_matching_node(fw_np, s10_of_match); - if (!np) { - of_node_put(fw_np); + if (!np) return -ENODEV; - } of_node_put(np); ret = of_platform_populate(fw_np, s10_of_match, NULL, NULL); - of_node_put(fw_np); if (ret) return ret; From 9a6d5488002fdca7134a0e59b0ae252f61042810 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 30 Jan 2019 08:41:40 -0700 Subject: [PATCH 304/525] ide: ensure atapi sense request aren't preempted There's an issue with how sense requests are handled in IDE. If ide-cd encounters an error, it queues a sense request. With how IDE request handling is done, this is the next request we need to handle. But it's impossible to guarantee this, as another request could come in between the sense being queued, and ->queue_rq() being run and handling it. If that request ALSO fails, then we attempt to doubly queue the single sense request we have. Since we only support one active request at the time, defer request processing when a sense request is queued. Fixes: 600335205b8d "ide: convert to blk-mq" Reported-by: He Zhe Tested-by: He Zhe Signed-off-by: Jens Axboe --- drivers/ide/ide-atapi.c | 9 +++++- drivers/ide/ide-io.c | 61 +++++++++++++++++++++-------------------- drivers/ide/ide-park.c | 2 ++ drivers/ide/ide-probe.c | 23 +++++++++++----- include/linux/ide.h | 2 ++ 5 files changed, 59 insertions(+), 38 deletions(-) diff --git a/drivers/ide/ide-atapi.c b/drivers/ide/ide-atapi.c index da58020a144e..33a28cde126c 100644 --- a/drivers/ide/ide-atapi.c +++ b/drivers/ide/ide-atapi.c @@ -235,21 +235,28 @@ EXPORT_SYMBOL_GPL(ide_prep_sense); int ide_queue_sense_rq(ide_drive_t *drive, void *special) { - struct request *sense_rq = drive->sense_rq; + ide_hwif_t *hwif = drive->hwif; + struct request *sense_rq; + unsigned long flags; + + spin_lock_irqsave(&hwif->lock, flags); /* deferred failure from ide_prep_sense() */ if (!drive->sense_rq_armed) { printk(KERN_WARNING PFX "%s: error queuing a sense request\n", drive->name); + spin_unlock_irqrestore(&hwif->lock, flags); return -ENOMEM; } + sense_rq = drive->sense_rq; ide_req(sense_rq)->special = special; drive->sense_rq_armed = false; drive->hwif->rq = NULL; ide_insert_request_head(drive, sense_rq); + spin_unlock_irqrestore(&hwif->lock, flags); return 0; } EXPORT_SYMBOL_GPL(ide_queue_sense_rq); diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c index 8445b484ae69..b137f27a34d5 100644 --- a/drivers/ide/ide-io.c +++ b/drivers/ide/ide-io.c @@ -68,8 +68,10 @@ int ide_end_rq(ide_drive_t *drive, struct request *rq, blk_status_t error, } if (!blk_update_request(rq, error, nr_bytes)) { - if (rq == drive->sense_rq) + if (rq == drive->sense_rq) { drive->sense_rq = NULL; + drive->sense_rq_active = false; + } __blk_mq_end_request(rq, error); return 0; @@ -451,16 +453,11 @@ void ide_requeue_and_plug(ide_drive_t *drive, struct request *rq) blk_mq_delay_run_hw_queue(q->queue_hw_ctx[0], 3); } -/* - * Issue a new request to a device. - */ -blk_status_t ide_queue_rq(struct blk_mq_hw_ctx *hctx, - const struct blk_mq_queue_data *bd) +blk_status_t ide_issue_rq(ide_drive_t *drive, struct request *rq, + bool local_requeue) { - ide_drive_t *drive = hctx->queue->queuedata; - ide_hwif_t *hwif = drive->hwif; + ide_hwif_t *hwif = drive->hwif; struct ide_host *host = hwif->host; - struct request *rq = bd->rq; ide_startstop_t startstop; if (!blk_rq_is_passthrough(rq) && !(rq->rq_flags & RQF_DONTPREP)) { @@ -474,8 +471,6 @@ blk_status_t ide_queue_rq(struct blk_mq_hw_ctx *hctx, if (ide_lock_host(host, hwif)) return BLK_STS_DEV_RESOURCE; - blk_mq_start_request(rq); - spin_lock_irq(&hwif->lock); if (!ide_lock_port(hwif)) { @@ -510,18 +505,6 @@ repeat: hwif->cur_dev = drive; drive->dev_flags &= ~(IDE_DFLAG_SLEEPING | IDE_DFLAG_PARKED); - /* - * we know that the queue isn't empty, but this can happen - * if ->prep_rq() decides to kill a request - */ - if (!rq) { - rq = bd->rq; - if (!rq) { - ide_unlock_port(hwif); - goto out; - } - } - /* * Sanity: don't accept a request that isn't a PM request * if we are currently power managed. This is very important as @@ -560,9 +543,12 @@ repeat: } } else { plug_device: + if (local_requeue) + list_add(&rq->queuelist, &drive->rq_list); spin_unlock_irq(&hwif->lock); ide_unlock_host(host); - ide_requeue_and_plug(drive, rq); + if (!local_requeue) + ide_requeue_and_plug(drive, rq); return BLK_STS_OK; } @@ -573,6 +559,26 @@ out: return BLK_STS_OK; } +/* + * Issue a new request to a device. + */ +blk_status_t ide_queue_rq(struct blk_mq_hw_ctx *hctx, + const struct blk_mq_queue_data *bd) +{ + ide_drive_t *drive = hctx->queue->queuedata; + ide_hwif_t *hwif = drive->hwif; + + spin_lock_irq(&hwif->lock); + if (drive->sense_rq_active) { + spin_unlock_irq(&hwif->lock); + return BLK_STS_DEV_RESOURCE; + } + spin_unlock_irq(&hwif->lock); + + blk_mq_start_request(bd->rq); + return ide_issue_rq(drive, bd->rq, false); +} + static int drive_is_ready(ide_drive_t *drive) { ide_hwif_t *hwif = drive->hwif; @@ -893,13 +899,8 @@ EXPORT_SYMBOL_GPL(ide_pad_transfer); void ide_insert_request_head(ide_drive_t *drive, struct request *rq) { - ide_hwif_t *hwif = drive->hwif; - unsigned long flags; - - spin_lock_irqsave(&hwif->lock, flags); + drive->sense_rq_active = true; list_add_tail(&rq->queuelist, &drive->rq_list); - spin_unlock_irqrestore(&hwif->lock, flags); - kblockd_schedule_work(&drive->rq_work); } EXPORT_SYMBOL_GPL(ide_insert_request_head); diff --git a/drivers/ide/ide-park.c b/drivers/ide/ide-park.c index 102aa3bc3e7f..8af7af6001eb 100644 --- a/drivers/ide/ide-park.c +++ b/drivers/ide/ide-park.c @@ -54,7 +54,9 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout) scsi_req(rq)->cmd[0] = REQ_UNPARK_HEADS; scsi_req(rq)->cmd_len = 1; ide_req(rq)->type = ATA_PRIV_MISC; + spin_lock_irq(&hwif->lock); ide_insert_request_head(drive, rq); + spin_unlock_irq(&hwif->lock); out: return; diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c index 63627be0811a..5aeaca24a28f 100644 --- a/drivers/ide/ide-probe.c +++ b/drivers/ide/ide-probe.c @@ -1159,18 +1159,27 @@ static void drive_rq_insert_work(struct work_struct *work) ide_drive_t *drive = container_of(work, ide_drive_t, rq_work); ide_hwif_t *hwif = drive->hwif; struct request *rq; + blk_status_t ret; LIST_HEAD(list); + blk_mq_quiesce_queue(drive->queue); + + ret = BLK_STS_OK; spin_lock_irq(&hwif->lock); - if (!list_empty(&drive->rq_list)) - list_splice_init(&drive->rq_list, &list); + while (!list_empty(&drive->rq_list)) { + rq = list_first_entry(&drive->rq_list, struct request, queuelist); + list_del_init(&rq->queuelist); + + spin_unlock_irq(&hwif->lock); + ret = ide_issue_rq(drive, rq, true); + spin_lock_irq(&hwif->lock); + } spin_unlock_irq(&hwif->lock); - while (!list_empty(&list)) { - rq = list_first_entry(&list, struct request, queuelist); - list_del_init(&rq->queuelist); - blk_execute_rq_nowait(drive->queue, rq->rq_disk, rq, true, NULL); - } + blk_mq_unquiesce_queue(drive->queue); + + if (ret != BLK_STS_OK) + kblockd_schedule_work(&drive->rq_work); } static const u8 ide_hwif_to_major[] = diff --git a/include/linux/ide.h b/include/linux/ide.h index e7d29ae633cd..971cf76a78a0 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -615,6 +615,7 @@ struct ide_drive_s { /* current sense rq and buffer */ bool sense_rq_armed; + bool sense_rq_active; struct request *sense_rq; struct request_sense sense_data; @@ -1219,6 +1220,7 @@ extern void ide_stall_queue(ide_drive_t *drive, unsigned long timeout); extern void ide_timer_expiry(struct timer_list *t); extern irqreturn_t ide_intr(int irq, void *dev_id); extern blk_status_t ide_queue_rq(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *); +extern blk_status_t ide_issue_rq(ide_drive_t *, struct request *, bool); extern void ide_requeue_and_plug(ide_drive_t *drive, struct request *rq); void ide_init_disk(struct gendisk *, ide_drive_t *); From 912139cfbfa6a2bc1da052314d2c29338dae1f6a Mon Sep 17 00:00:00 2001 From: Thomas Lendacky Date: Thu, 31 Jan 2019 14:33:06 +0000 Subject: [PATCH 305/525] x86/microcode/amd: Don't falsely trick the late loading mechanism The load_microcode_amd() function searches for microcode patches and attempts to apply a microcode patch if it is of different level than the currently installed level. While the processor won't actually load a level that is less than what is already installed, the logic wrongly returns UCODE_NEW thus signaling to its caller reload_store() that a late loading should be attempted. If the file-system contains an older microcode revision than what is currently running, such a late microcode reload can result in these misleading messages: x86/CPU: CPU features have changed after loading microcode, but might not take effect. x86/CPU: Please consider either early loading through initrd/built-in or a potential BIOS update. These messages were issued on a system where SME/SEV are not enabled by the BIOS (MSR C001_0010[23] = 0b) because during boot, early_detect_mem_encrypt() is called and cleared the SME and SEV features in this case. However, after the wrong late load attempt, get_cpu_cap() is called and reloads the SME and SEV feature bits, resulting in the messages. Update the microcode level check to not attempt microcode loading if the current level is greater than(!) and not only equal to the current patch level. [ bp: massage commit message. ] Fixes: 2613f36ed965 ("x86/microcode: Attempt late loading only when new microcode is present") Signed-off-by: Tom Lendacky Signed-off-by: Borislav Petkov Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Thomas Gleixner Cc: x86-ml Link: https://lkml.kernel.org/r/154894518427.9406.8246222496874202773.stgit@tlendack-t1.amdoffice.net --- arch/x86/kernel/cpu/microcode/amd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 51adde0a0f1a..e1f3ba19ba54 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -855,7 +855,7 @@ load_microcode_amd(bool save, u8 family, const u8 *data, size_t size) if (!p) { return ret; } else { - if (boot_cpu_data.microcode == p->patch_id) + if (boot_cpu_data.microcode >= p->patch_id) return ret; ret = UCODE_NEW; From 34aaaac815d166daef361f49529f4c6b77da49f1 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Mon, 14 Jan 2019 15:48:34 +0000 Subject: [PATCH 306/525] ieee802154: mcr20a: fix indentation, remove tabs The are a couple of statments that are one level too deep, fix this by removing tabs. Signed-off-by: Colin Ian King Signed-off-by: Stefan Schmidt --- drivers/net/ieee802154/mcr20a.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ieee802154/mcr20a.c b/drivers/net/ieee802154/mcr20a.c index 44de81e5f140..c589f5ae75bb 100644 --- a/drivers/net/ieee802154/mcr20a.c +++ b/drivers/net/ieee802154/mcr20a.c @@ -905,9 +905,9 @@ mcr20a_irq_clean_complete(void *context) } break; case (DAR_IRQSTS1_RXIRQ | DAR_IRQSTS1_SEQIRQ): - /* rx is starting */ - dev_dbg(printdev(lp), "RX is starting\n"); - mcr20a_handle_rx(lp); + /* rx is starting */ + dev_dbg(printdev(lp), "RX is starting\n"); + mcr20a_handle_rx(lp); break; case (DAR_IRQSTS1_RXIRQ | DAR_IRQSTS1_TXIRQ | DAR_IRQSTS1_SEQIRQ): if (lp->is_tx) { From 05672636b339c557feb6a98b2f2034be790aa4fb Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Sun, 27 Jan 2019 12:15:49 +0100 Subject: [PATCH 307/525] mt76x0: eeprom: fix chan_vs_power map in mt76x0_get_power_info Report correct eeprom per channel power value. Fix chan_vs_power map in mt76x0_get_power_info routine Fixes: f2a2e819d672 ("mt76x0: remove eeprom dependency from mt76x0_get_power_info") Signed-off-by: Lorenzo Bianconi Signed-off-by: Kalle Valo --- .../wireless/mediatek/mt76/mt76x0/eeprom.c | 40 +++++++++---------- .../wireless/mediatek/mt76/mt76x0/eeprom.h | 2 +- .../net/wireless/mediatek/mt76/mt76x0/phy.c | 10 ++--- 3 files changed, 25 insertions(+), 27 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c index 497e762978cc..b2cabce1d74d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c @@ -212,24 +212,24 @@ void mt76x0_get_tx_power_per_rate(struct mt76x02_dev *dev) mt76x02_add_rate_power_offset(t, delta); } -void mt76x0_get_power_info(struct mt76x02_dev *dev, u8 *info) +void mt76x0_get_power_info(struct mt76x02_dev *dev, s8 *tp) { struct mt76x0_chan_map { u8 chan; u8 offset; } chan_map[] = { - { 2, 0 }, { 4, 1 }, { 6, 2 }, { 8, 3 }, - { 10, 4 }, { 12, 5 }, { 14, 6 }, { 38, 0 }, - { 44, 1 }, { 48, 2 }, { 54, 3 }, { 60, 4 }, - { 64, 5 }, { 102, 6 }, { 108, 7 }, { 112, 8 }, - { 118, 9 }, { 124, 10 }, { 128, 11 }, { 134, 12 }, - { 140, 13 }, { 151, 14 }, { 157, 15 }, { 161, 16 }, - { 167, 17 }, { 171, 18 }, { 173, 19 }, + { 2, 0 }, { 4, 2 }, { 6, 4 }, { 8, 6 }, + { 10, 8 }, { 12, 10 }, { 14, 12 }, { 38, 0 }, + { 44, 2 }, { 48, 4 }, { 54, 6 }, { 60, 8 }, + { 64, 10 }, { 102, 12 }, { 108, 14 }, { 112, 16 }, + { 118, 18 }, { 124, 20 }, { 128, 22 }, { 134, 24 }, + { 140, 26 }, { 151, 28 }, { 157, 30 }, { 161, 32 }, + { 167, 34 }, { 171, 36 }, { 175, 38 }, }; struct ieee80211_channel *chan = dev->mt76.chandef.chan; u8 offset, addr; + int i, idx = 0; u16 data; - int i; if (mt76x0_tssi_enabled(dev)) { s8 target_power; @@ -239,14 +239,14 @@ void mt76x0_get_power_info(struct mt76x02_dev *dev, u8 *info) else data = mt76x02_eeprom_get(dev, MT_EE_2G_TARGET_POWER); target_power = (data & 0xff) - dev->mt76.rate_power.ofdm[7]; - info[0] = target_power + mt76x0_get_delta(dev); - info[1] = 0; + *tp = target_power + mt76x0_get_delta(dev); return; } for (i = 0; i < ARRAY_SIZE(chan_map); i++) { - if (chan_map[i].chan <= chan->hw_value) { + if (chan->hw_value <= chan_map[i].chan) { + idx = (chan->hw_value == chan_map[i].chan); offset = chan_map[i].offset; break; } @@ -258,13 +258,16 @@ void mt76x0_get_power_info(struct mt76x02_dev *dev, u8 *info) addr = MT_EE_TX_POWER_DELTA_BW80 + offset; } else { switch (chan->hw_value) { + case 42: + offset = 2; + break; case 58: offset = 8; break; case 106: offset = 14; break; - case 112: + case 122: offset = 20; break; case 155: @@ -277,14 +280,9 @@ void mt76x0_get_power_info(struct mt76x02_dev *dev, u8 *info) } data = mt76x02_eeprom_get(dev, addr); - - info[0] = data; - if (!info[0] || info[0] > 0x3f) - info[0] = 5; - - info[1] = data >> 8; - if (!info[1] || info[1] > 0x3f) - info[1] = 5; + *tp = data >> (8 * idx); + if (*tp < 0 || *tp > 0x3f) + *tp = 5; } static int mt76x0_check_eeprom(struct mt76x02_dev *dev) diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.h b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.h index ee9ade9f3c8b..42b259f90b6d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.h +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.h @@ -26,7 +26,7 @@ struct mt76x02_dev; int mt76x0_eeprom_init(struct mt76x02_dev *dev); void mt76x0_read_rx_gain(struct mt76x02_dev *dev); void mt76x0_get_tx_power_per_rate(struct mt76x02_dev *dev); -void mt76x0_get_power_info(struct mt76x02_dev *dev, u8 *info); +void mt76x0_get_power_info(struct mt76x02_dev *dev, s8 *tp); static inline s8 s6_to_s8(u32 val) { diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c index 1eb1a802ed20..b6166703ad76 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c @@ -845,17 +845,17 @@ static void mt76x0_phy_tssi_calibrate(struct mt76x02_dev *dev) void mt76x0_phy_set_txpower(struct mt76x02_dev *dev) { struct mt76_rate_power *t = &dev->mt76.rate_power; - u8 info[2]; + s8 info; mt76x0_get_tx_power_per_rate(dev); - mt76x0_get_power_info(dev, info); + mt76x0_get_power_info(dev, &info); - mt76x02_add_rate_power_offset(t, info[0]); + mt76x02_add_rate_power_offset(t, info); mt76x02_limit_rate_power(t, dev->mt76.txpower_conf); dev->mt76.txpower_cur = mt76x02_get_max_rate_power(t); - mt76x02_add_rate_power_offset(t, -info[0]); + mt76x02_add_rate_power_offset(t, -info); - mt76x02_phy_set_txpower(dev, info[0], info[1]); + mt76x02_phy_set_txpower(dev, info, info); } void mt76x0_phy_calibrate(struct mt76x02_dev *dev, bool power_on) From 2c2008a63e482654ab137c84d3c61c03b75e7df6 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Tue, 29 Jan 2019 15:12:01 -0800 Subject: [PATCH 308/525] ath10k: correct bus type for WCN3990 WCN3990 is SNOC, not PCI. This prevents probing WCN3990. Fixes: 367c899f622c ("ath10k: add bus type check in ath10k_init_hw_params") Signed-off-by: Brian Norris Reviewed-by: Bjorn Andersson Signed-off-by: Kalle Valo --- drivers/net/wireless/ath/ath10k/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c index 399b501f3c3c..e8891f5fc83a 100644 --- a/drivers/net/wireless/ath/ath10k/core.c +++ b/drivers/net/wireless/ath/ath10k/core.c @@ -548,7 +548,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { { .id = WCN3990_HW_1_0_DEV_VERSION, .dev_id = 0, - .bus = ATH10K_BUS_PCI, + .bus = ATH10K_BUS_SNOC, .name = "wcn3990 hw1.0", .continuous_frag_desc = true, .tx_chain_mask = 0x7, From 91c524708de6207f59dd3512518d8a1c7b434ee3 Mon Sep 17 00:00:00 2001 From: Jacob Wen Date: Thu, 31 Jan 2019 15:18:56 +0800 Subject: [PATCH 309/525] l2tp: copy 4 more bytes to linear part if necessary The size of L2TPv2 header with all optional fields is 14 bytes. l2tp_udp_recv_core only moves 10 bytes to the linear part of a skb. This may lead to l2tp_recv_common read data outside of a skb. This patch make sure that there is at least 14 bytes in the linear part of a skb to meet the maximum need of l2tp_udp_recv_core and l2tp_recv_common. The minimum size of both PPP HDLC-like frame and Ethernet frame is larger than 14 bytes, so we are safe to do so. Also remove L2TP_HDR_SIZE_NOSEQ, it is unused now. Fixes: fd558d186df2 ("l2tp: Split pppol2tp patch into separate l2tp and ppp parts") Suggested-by: Guillaume Nault Signed-off-by: Jacob Wen Acked-by: Guillaume Nault Signed-off-by: David S. Miller --- net/l2tp/l2tp_core.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index dd5ba0c11ab3..fed6becc5daf 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -83,8 +83,7 @@ #define L2TP_SLFLAG_S 0x40000000 #define L2TP_SL_SEQ_MASK 0x00ffffff -#define L2TP_HDR_SIZE_SEQ 10 -#define L2TP_HDR_SIZE_NOSEQ 6 +#define L2TP_HDR_SIZE_MAX 14 /* Default trace flags */ #define L2TP_DEFAULT_DEBUG_FLAGS 0 @@ -808,7 +807,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) __skb_pull(skb, sizeof(struct udphdr)); /* Short packet? */ - if (!pskb_may_pull(skb, L2TP_HDR_SIZE_SEQ)) { + if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) { l2tp_info(tunnel, L2TP_MSG_DATA, "%s: recv short packet (len=%d)\n", tunnel->name, skb->len); From fc42a689c4c097859e5bd37b5ea11b60dc426df6 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 30 Jan 2019 10:42:30 -0800 Subject: [PATCH 310/525] lib/test_rhashtable: Make test_insert_dup() allocate its hash table dynamically The test_insert_dup() function from lib/test_rhashtable.c passes a pointer to a stack object to rhltable_init(). Allocate the hash table dynamically to avoid that the following is reported with object debugging enabled: ODEBUG: object (ptrval) is on stack (ptrval), but NOT annotated. WARNING: CPU: 0 PID: 1 at lib/debugobjects.c:368 __debug_object_init+0x312/0x480 Modules linked in: EIP: __debug_object_init+0x312/0x480 Call Trace: ? debug_object_init+0x1a/0x20 ? __init_work+0x16/0x30 ? rhashtable_init+0x1e1/0x460 ? sched_clock_cpu+0x57/0xe0 ? rhltable_init+0xb/0x20 ? test_insert_dup+0x32/0x20f ? trace_hardirqs_on+0x38/0xf0 ? ida_dump+0x10/0x10 ? jhash+0x130/0x130 ? my_hashfn+0x30/0x30 ? test_rht_init+0x6aa/0xab4 ? ida_dump+0x10/0x10 ? test_rhltable+0xc5c/0xc5c ? do_one_initcall+0x67/0x28e ? trace_hardirqs_off+0x22/0xe0 ? restore_all_kernel+0xf/0x70 ? trace_hardirqs_on_thunk+0xc/0x10 ? restore_all_kernel+0xf/0x70 ? kernel_init_freeable+0x142/0x213 ? rest_init+0x230/0x230 ? kernel_init+0x10/0x110 ? schedule_tail_wrapper+0x9/0xc ? ret_from_fork+0x19/0x24 Cc: Thomas Graf Cc: Herbert Xu Cc: netdev@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Bart Van Assche Acked-by: Herbert Xu Signed-off-by: David S. Miller --- lib/test_rhashtable.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c index 6a8ac7626797..e52f8cafe227 100644 --- a/lib/test_rhashtable.c +++ b/lib/test_rhashtable.c @@ -541,38 +541,45 @@ static unsigned int __init print_ht(struct rhltable *rhlt) static int __init test_insert_dup(struct test_obj_rhl *rhl_test_objects, int cnt, bool slow) { - struct rhltable rhlt; + struct rhltable *rhlt; unsigned int i, ret; const char *key; int err = 0; - err = rhltable_init(&rhlt, &test_rht_params_dup); - if (WARN_ON(err)) + rhlt = kmalloc(sizeof(*rhlt), GFP_KERNEL); + if (WARN_ON(!rhlt)) + return -EINVAL; + + err = rhltable_init(rhlt, &test_rht_params_dup); + if (WARN_ON(err)) { + kfree(rhlt); return err; + } for (i = 0; i < cnt; i++) { rhl_test_objects[i].value.tid = i; - key = rht_obj(&rhlt.ht, &rhl_test_objects[i].list_node.rhead); + key = rht_obj(&rhlt->ht, &rhl_test_objects[i].list_node.rhead); key += test_rht_params_dup.key_offset; if (slow) { - err = PTR_ERR(rhashtable_insert_slow(&rhlt.ht, key, + err = PTR_ERR(rhashtable_insert_slow(&rhlt->ht, key, &rhl_test_objects[i].list_node.rhead)); if (err == -EAGAIN) err = 0; } else - err = rhltable_insert(&rhlt, + err = rhltable_insert(rhlt, &rhl_test_objects[i].list_node, test_rht_params_dup); if (WARN(err, "error %d on element %d/%d (%s)\n", err, i, cnt, slow? "slow" : "fast")) goto skip_print; } - ret = print_ht(&rhlt); + ret = print_ht(rhlt); WARN(ret != cnt, "missing rhltable elements (%d != %d, %s)\n", ret, cnt, slow? "slow" : "fast"); skip_print: - rhltable_destroy(&rhlt); + rhltable_destroy(rhlt); + kfree(rhlt); return 0; } From 6fa19f5637a6c22bc0999596bcc83bdcac8a4fa6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 31 Jan 2019 08:47:10 -0800 Subject: [PATCH 311/525] rds: fix refcount bug in rds_sock_addref syzbot was able to catch a bug in rds [1] The issue here is that the socket might be found in a hash table but that its refcount has already be set to 0 by another cpu. We need to use refcount_inc_not_zero() to be safe here. [1] refcount_t: increment on 0; use-after-free. WARNING: CPU: 1 PID: 23129 at lib/refcount.c:153 refcount_inc_checked lib/refcount.c:153 [inline] WARNING: CPU: 1 PID: 23129 at lib/refcount.c:153 refcount_inc_checked+0x61/0x70 lib/refcount.c:151 Kernel panic - not syncing: panic_on_warn set ... CPU: 1 PID: 23129 Comm: syz-executor3 Not tainted 5.0.0-rc4+ #53 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1db/0x2d0 lib/dump_stack.c:113 panic+0x2cb/0x65c kernel/panic.c:214 __warn.cold+0x20/0x48 kernel/panic.c:571 report_bug+0x263/0x2b0 lib/bug.c:186 fixup_bug arch/x86/kernel/traps.c:178 [inline] fixup_bug arch/x86/kernel/traps.c:173 [inline] do_error_trap+0x11b/0x200 arch/x86/kernel/traps.c:271 do_invalid_op+0x37/0x50 arch/x86/kernel/traps.c:290 invalid_op+0x14/0x20 arch/x86/entry/entry_64.S:973 RIP: 0010:refcount_inc_checked lib/refcount.c:153 [inline] RIP: 0010:refcount_inc_checked+0x61/0x70 lib/refcount.c:151 Code: 1d 51 63 c8 06 31 ff 89 de e8 eb 1b f2 fd 84 db 75 dd e8 a2 1a f2 fd 48 c7 c7 60 9f 81 88 c6 05 31 63 c8 06 01 e8 af 65 bb fd <0f> 0b eb c1 90 66 2e 0f 1f 84 00 00 00 00 00 55 48 89 e5 41 54 49 RSP: 0018:ffff8880a0cbf1e8 EFLAGS: 00010282 RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffffc90006113000 RDX: 000000000001047d RSI: ffffffff81685776 RDI: 0000000000000005 RBP: ffff8880a0cbf1f8 R08: ffff888097c9e100 R09: ffffed1015ce5021 R10: ffffed1015ce5020 R11: ffff8880ae728107 R12: ffff8880723c20c0 R13: ffff8880723c24b0 R14: dffffc0000000000 R15: ffffed1014197e64 sock_hold include/net/sock.h:647 [inline] rds_sock_addref+0x19/0x20 net/rds/af_rds.c:675 rds_find_bound+0x97c/0x1080 net/rds/bind.c:82 rds_recv_incoming+0x3be/0x1430 net/rds/recv.c:362 rds_loop_xmit+0xf3/0x2a0 net/rds/loop.c:96 rds_send_xmit+0x1355/0x2a10 net/rds/send.c:355 rds_sendmsg+0x323c/0x44e0 net/rds/send.c:1368 sock_sendmsg_nosec net/socket.c:621 [inline] sock_sendmsg+0xdd/0x130 net/socket.c:631 __sys_sendto+0x387/0x5f0 net/socket.c:1788 __do_sys_sendto net/socket.c:1800 [inline] __se_sys_sendto net/socket.c:1796 [inline] __x64_sys_sendto+0xe1/0x1a0 net/socket.c:1796 do_syscall_64+0x1a3/0x800 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x458089 Code: 6d b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 3b b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fc266df8c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 0000000000000006 RCX: 0000000000458089 RDX: 0000000000000000 RSI: 00000000204b3fff RDI: 0000000000000005 RBP: 000000000073bf00 R08: 00000000202b4000 R09: 0000000000000010 R10: 0000000000000000 R11: 0000000000000246 R12: 00007fc266df96d4 R13: 00000000004c56e4 R14: 00000000004d94a8 R15: 00000000ffffffff Fixes: cc4dfb7f70a3 ("rds: fix two RCU related problems") Signed-off-by: Eric Dumazet Reported-by: syzbot Cc: Sowmini Varadhan Cc: Santosh Shilimkar Cc: rds-devel@oss.oracle.com Cc: Cong Wang Acked-by: Santosh Shilimkar Signed-off-by: David S. Miller --- net/rds/bind.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/rds/bind.c b/net/rds/bind.c index 762d2c6788a3..17c9d9f0c848 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -78,10 +78,10 @@ struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port, __rds_create_bind_key(key, addr, port, scope_id); rcu_read_lock(); rs = rhashtable_lookup(&bind_hash_table, key, ht_parms); - if (rs && !sock_flag(rds_rs_to_sk(rs), SOCK_DEAD)) - rds_sock_addref(rs); - else + if (rs && (sock_flag(rds_rs_to_sk(rs), SOCK_DEAD) || + !refcount_inc_not_zero(&rds_rs_to_sk(rs)->sk_refcnt))) rs = NULL; + rcu_read_unlock(); rdsdebug("returning rs %p for %pI6c:%u\n", rs, addr, From fedb5760648a291e949f2380d383b5b2d2749b5e Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 31 Jan 2019 17:43:16 +0800 Subject: [PATCH 312/525] serial: fix race between flush_to_ldisc and tty_open There still is a race window after the commit b027e2298bd588 ("tty: fix data race between tty_init_dev and flush of buf"), and we encountered this crash issue if receive_buf call comes before tty initialization completes in tty_open and tty->driver_data may be NULL. CPU0 CPU1 ---- ---- tty_open tty_init_dev tty_ldisc_unlock schedule flush_to_ldisc receive_buf tty_port_default_receive_buf tty_ldisc_receive_buf n_tty_receive_buf_common __receive_buf uart_flush_chars uart_start /*tty->driver_data is NULL*/ tty->ops->open /*init tty->driver_data*/ it can be fixed by extending ldisc semaphore lock in tty_init_dev to driver_data initialized completely after tty->ops->open(), but this will lead to get lock on one function and unlock in some other function, and hard to maintain, so fix this race only by checking tty->driver_data when receiving, and return if tty->driver_data is NULL, and n_tty_receive_buf_common maybe calls uart_unthrottle, so add the same check. Because the tty layer knows nothing about the driver associated with the device, the tty layer can not do anything here, it is up to the tty driver itself to check for this type of race. Fix up the serial driver to correctly check to see if it is finished binding with the device when being called, and if not, abort the tty calls. [Description and problem report and testing from Li RongQing, I rewrote the patch to be in the serial layer, not in the tty core - gregkh] Reported-by: Li RongQing Tested-by: Li RongQing Signed-off-by: Wang Li Signed-off-by: Zhang Yu Signed-off-by: Li RongQing Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/serial_core.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 5c01bb6d1c24..556f50aa1b58 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -130,6 +130,9 @@ static void uart_start(struct tty_struct *tty) struct uart_port *port; unsigned long flags; + if (!state) + return; + port = uart_port_lock(state, flags); __uart_start(tty); uart_port_unlock(port, flags); @@ -727,6 +730,9 @@ static void uart_unthrottle(struct tty_struct *tty) upstat_t mask = UPSTAT_SYNC_FIFO; struct uart_port *port; + if (!state) + return; + port = uart_port_ref(state); if (!port) return; From e74c98ca2d6ae4376cc15fa2a22483430909d96b Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Wed, 30 Jan 2019 21:30:36 +0100 Subject: [PATCH 313/525] gfs2: Revert "Fix loop in gfs2_rbm_find" This reverts commit 2d29f6b96d8f80322ed2dd895bca590491c38d34. It turns out that the fix can lead to a ~20 percent performance regression in initial writes to the page cache according to iozone. Let's revert this for now to have more time for a proper fix. Cc: stable@vger.kernel.org # v3.13+ Signed-off-by: Andreas Gruenbacher Signed-off-by: Bob Peterson Signed-off-by: Linus Torvalds --- fs/gfs2/rgrp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 831d7cb5a49c..17a8d3b43990 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -1780,9 +1780,9 @@ static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 *minext, goto next_iter; } if (ret == -E2BIG) { - n += rbm->bii - initial_bii; rbm->bii = 0; rbm->offset = 0; + n += (rbm->bii - initial_bii); goto res_covered_end_of_rgrp; } return ret; From 5e66e35aab335b83d9ffb220d8a3a13986a7a60e Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Thu, 31 Jan 2019 14:31:48 -0500 Subject: [PATCH 314/525] bnxt_en: Disable interrupts when allocating CP rings or NQs. When calling firmware to allocate a CP ring or NQ, an interrupt associated with that ring may be generated immediately before the doorbell is even setup after the firmware call returns. When servicing the interrupt, the driver may crash when trying to access the doorbell. Fix it by disabling interrupt on that vector until the doorbell is set up. Fixes: 697197e5a173 ("bnxt_en: Re-structure doorbells.") Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 6a512871176b..8bc7e495b027 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -4973,12 +4973,18 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp) struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring; struct bnxt_ring_struct *ring = &cpr->cp_ring_struct; u32 map_idx = ring->map_idx; + unsigned int vector; + vector = bp->irq_tbl[map_idx].vector; + disable_irq_nosync(vector); rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx); - if (rc) + if (rc) { + enable_irq(vector); goto err_out; + } bnxt_set_db(bp, &cpr->cp_db, type, map_idx, ring->fw_ring_id); bnxt_db_nq(bp, &cpr->cp_db, cpr->cp_raw_cons); + enable_irq(vector); bp->grp_info[i].cp_fw_ring_id = ring->fw_ring_id; if (!i) { From a6093ad7fc4962099d2d723bcca72f8175b58c82 Mon Sep 17 00:00:00 2001 From: Leonard Crestez Date: Thu, 31 Jan 2019 14:59:50 -0600 Subject: [PATCH 315/525] PCI: imx: Fix probe failure without power domain On chips without a separate power domain for PCI (such as 6q/6qp) the imx6_pcie_attach_pd() function incorrectly returns an error. Fix by returning 0 if dev_pm_domain_attach_by_name() does not find anything. Fixes: 3f7cceeab895 ("PCI: imx: Add multi-pd support") Reported-by: Lukas F.Hartmann Signed-off-by: Leonard Crestez [lorenzo.pieralisi@arm.com: updated commit log] Signed-off-by: Lorenzo Pieralisi --- drivers/pci/controller/dwc/pci-imx6.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c index 52e47dac028f..ac5f6ae0b254 100644 --- a/drivers/pci/controller/dwc/pci-imx6.c +++ b/drivers/pci/controller/dwc/pci-imx6.c @@ -310,6 +310,9 @@ static int imx6_pcie_attach_pd(struct device *dev) imx6_pcie->pd_pcie = dev_pm_domain_attach_by_name(dev, "pcie"); if (IS_ERR(imx6_pcie->pd_pcie)) return PTR_ERR(imx6_pcie->pd_pcie); + /* Do nothing when power domain missing */ + if (!imx6_pcie->pd_pcie) + return 0; link = device_link_add(dev, imx6_pcie->pd_pcie, DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME | From a4ace4fa20072dfe60ab48ba227e50bc2d69c246 Mon Sep 17 00:00:00 2001 From: Leonard Crestez Date: Thu, 31 Jan 2019 14:59:56 -0600 Subject: [PATCH 316/525] PCI: imx: Fix checking pd_pcie_phy device link addition The check on the device_link_add() return value is wrong; this leads to erroneous code execution, so fix it. Fixes: 3f7cceeab895 ("PCI: imx: Add multi-pd support") Signed-off-by: Leonard Crestez [lorenzo.pieralisi@arm.com: updated commit log] Signed-off-by: Lorenzo Pieralisi --- drivers/pci/controller/dwc/pci-imx6.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c index ac5f6ae0b254..80f843030e36 100644 --- a/drivers/pci/controller/dwc/pci-imx6.c +++ b/drivers/pci/controller/dwc/pci-imx6.c @@ -326,13 +326,13 @@ static int imx6_pcie_attach_pd(struct device *dev) if (IS_ERR(imx6_pcie->pd_pcie_phy)) return PTR_ERR(imx6_pcie->pd_pcie_phy); - device_link_add(dev, imx6_pcie->pd_pcie_phy, + link = device_link_add(dev, imx6_pcie->pd_pcie_phy, DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE); - if (IS_ERR(link)) { - dev_err(dev, "Failed to add device_link to pcie_phy pd: %ld\n", PTR_ERR(link)); - return PTR_ERR(link); + if (!link) { + dev_err(dev, "Failed to add device_link to pcie_phy pd.\n"); + return -EINVAL; } return 0; From 65dbb423cf28232fed1732b779249d6164c5999b Mon Sep 17 00:00:00 2001 From: Koen Vandeputte Date: Thu, 31 Jan 2019 15:00:01 -0600 Subject: [PATCH 317/525] ARM: cns3xxx: Fix writing to wrong PCI config registers after alignment Originally, cns3xxx used its own functions for mapping, reading and writing config registers. Commit 802b7c06adc7 ("ARM: cns3xxx: Convert PCI to use generic config accessors") removed the internal PCI config write function in favor of the generic one: cns3xxx_pci_write_config() --> pci_generic_config_write() cns3xxx_pci_write_config() expected aligned addresses, being produced by cns3xxx_pci_map_bus() while the generic one pci_generic_config_write() actually expects the real address as both the function and hardware are capable of byte-aligned writes. This currently leads to pci_generic_config_write() writing to the wrong registers. For instance, upon ath9k module loading: - driver ath9k gets loaded - The driver wants to write value 0xA8 to register PCI_LATENCY_TIMER, located at 0x0D - cns3xxx_pci_map_bus() aligns the address to 0x0C - pci_generic_config_write() effectively writes 0xA8 into register 0x0C (CACHE_LINE_SIZE) Fix the bug by removing the alignment in the cns3xxx mapping function. Fixes: 802b7c06adc7 ("ARM: cns3xxx: Convert PCI to use generic config accessors") Signed-off-by: Koen Vandeputte [lorenzo.pieralisi@arm.com: updated commit log] Signed-off-by: Lorenzo Pieralisi Acked-by: Krzysztof Halasa Acked-by: Tim Harvey Acked-by: Arnd Bergmann CC: stable@vger.kernel.org # v4.0+ CC: Bjorn Helgaas CC: Olof Johansson CC: Robin Leblon CC: Rob Herring CC: Russell King --- arch/arm/mach-cns3xxx/pcie.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/mach-cns3xxx/pcie.c b/arch/arm/mach-cns3xxx/pcie.c index 318394ed5c7a..5e11ad3164e0 100644 --- a/arch/arm/mach-cns3xxx/pcie.c +++ b/arch/arm/mach-cns3xxx/pcie.c @@ -83,7 +83,7 @@ static void __iomem *cns3xxx_pci_map_bus(struct pci_bus *bus, } else /* remote PCI bus */ base = cnspci->cfg1_regs + ((busno & 0xf) << 20); - return base + (where & 0xffc) + (devfn << 12); + return base + where + (devfn << 12); } static int cns3xxx_pci_read_config(struct pci_bus *bus, unsigned int devfn, From 432dd7064aa1c030a488745917cfa4ebc6c8c060 Mon Sep 17 00:00:00 2001 From: Koen Vandeputte Date: Thu, 31 Jan 2019 15:00:11 -0600 Subject: [PATCH 318/525] ARM: cns3xxx: Use actual size reads for PCIe commit 802b7c06adc7 ("ARM: cns3xxx: Convert PCI to use generic config accessors") reimplemented cns3xxx_pci_read_config() using pci_generic_config_read32(), which preserved the property of only doing 32-bit reads. It also replaced cns3xxx_pci_write_config() with pci_generic_config_write(), so it changed writes from always being 32 bits to being the actual size, which works just fine. Given that: - The documentation does not mention that only 32 bit access is allowed. - Writes are already executed using the actual size - Extensive testing shows that 8b, 16b and 32b reads work as intended Allow read access of any size by replacing pci_generic_config_read32() with the pci_generic_config_read() accessors. Fixes: 802b7c06adc7 ("ARM: cns3xxx: Convert PCI to use generic config accessors") Suggested-by: Bjorn Helgaas Signed-off-by: Koen Vandeputte [lorenzo.pieralisi@arm.com: updated commit log] Signed-off-by: Lorenzo Pieralisi Acked-by: Krzysztof Halasa Acked-by: Arnd Bergmann CC: Krzysztof Halasa CC: Olof Johansson CC: Robin Leblon CC: Rob Herring CC: Russell King CC: Tim Harvey --- arch/arm/mach-cns3xxx/pcie.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/mach-cns3xxx/pcie.c b/arch/arm/mach-cns3xxx/pcie.c index 5e11ad3164e0..95a11d5b3587 100644 --- a/arch/arm/mach-cns3xxx/pcie.c +++ b/arch/arm/mach-cns3xxx/pcie.c @@ -93,7 +93,7 @@ static int cns3xxx_pci_read_config(struct pci_bus *bus, unsigned int devfn, u32 mask = (0x1ull << (size * 8)) - 1; int shift = (where % 4) * 8; - ret = pci_generic_config_read32(bus, devfn, where, size, val); + ret = pci_generic_config_read(bus, devfn, where, size, val); if (ret == PCIBIOS_SUCCESSFUL && !bus->number && !devfn && (where & 0xffc) == PCI_CLASS_REVISION) From f14bcc0add3abecceca1a3fe538c4ec9566893f3 Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Thu, 31 Jan 2019 15:00:18 -0600 Subject: [PATCH 319/525] Revert "PCI: armada8k: Add support for gpio controlled reset signal" Revert commit 3d71746c42 ("PCI: armada8k: Add support for gpio controlled reset signal"). That commit breaks boot on Macchiatobin board when a Mellanox NIC is present in the PCIe slot. It turns out that full reset cycle requires first comphy serdes initialization. Reset signal toggle without comphy initialization makes access to PCI configuration registers stall indefinitely. U-Boot toggles the Macchiatobin PCIe reset line already at boot, after initializing the comphy serdes. So while commit 3d71746c42 ("PCI: armada8k: Add support for gpio controlled reset signal") enables PCIe on platforms that U-Boot does not touch the reset line (like Clearfog GT-8K), it breaks PCIe (and boot) on the Macchiatobin board. Revert commit 3d71746c42 ("PCI: armada8k: Add support for gpio controlled reset signal") entirely to fix the Macchiatobin regression. Reported-by: Sven Auhagen Signed-off-by: Baruch Siach Signed-off-by: Lorenzo Pieralisi --- drivers/pci/controller/dwc/pcie-armada8k.c | 16 ---------------- 1 file changed, 16 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-armada8k.c b/drivers/pci/controller/dwc/pcie-armada8k.c index b171b6bc15c8..0c389a30ef5d 100644 --- a/drivers/pci/controller/dwc/pcie-armada8k.c +++ b/drivers/pci/controller/dwc/pcie-armada8k.c @@ -22,7 +22,6 @@ #include #include #include -#include #include "pcie-designware.h" @@ -30,7 +29,6 @@ struct armada8k_pcie { struct dw_pcie *pci; struct clk *clk; struct clk *clk_reg; - struct gpio_desc *reset_gpio; }; #define PCIE_VENDOR_REGS_OFFSET 0x8000 @@ -139,12 +137,6 @@ static int armada8k_pcie_host_init(struct pcie_port *pp) struct dw_pcie *pci = to_dw_pcie_from_pp(pp); struct armada8k_pcie *pcie = to_armada8k_pcie(pci); - if (pcie->reset_gpio) { - /* assert and then deassert the reset signal */ - gpiod_set_value_cansleep(pcie->reset_gpio, 1); - msleep(100); - gpiod_set_value_cansleep(pcie->reset_gpio, 0); - } dw_pcie_setup_rc(pp); armada8k_pcie_establish_link(pcie); @@ -257,14 +249,6 @@ static int armada8k_pcie_probe(struct platform_device *pdev) goto fail_clkreg; } - /* Get reset gpio signal and hold asserted (logically high) */ - pcie->reset_gpio = devm_gpiod_get_optional(dev, "reset", - GPIOD_OUT_HIGH); - if (IS_ERR(pcie->reset_gpio)) { - ret = PTR_ERR(pcie->reset_gpio); - goto fail_clkreg; - } - platform_set_drvdata(pdev, pcie); ret = armada8k_add_pcie_port(pcie, pdev); From 1bb54c4071f585ebef56ce8fdfe6026fa2cbcddd Mon Sep 17 00:00:00 2001 From: Martynas Pumputis Date: Thu, 31 Jan 2019 10:19:33 +0100 Subject: [PATCH 320/525] bpf, selftests: fix handling of sparse CPU allocations Previously, bpf_num_possible_cpus() had a bug when calculating a number of possible CPUs in the case of sparse CPU allocations, as it was considering only the first range or element of /sys/devices/system/cpu/possible. E.g. in the case of "0,2-3" (CPU 1 is not available), the function returned 1 instead of 3. This patch fixes the function by making it parse all CPU ranges and elements. Signed-off-by: Martynas Pumputis Acked-by: Yonghong Song Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/bpf_util.h | 32 +++++++++++++++++--------- 1 file changed, 21 insertions(+), 11 deletions(-) diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h index 315a44fa32af..84fd6f1bf33e 100644 --- a/tools/testing/selftests/bpf/bpf_util.h +++ b/tools/testing/selftests/bpf/bpf_util.h @@ -13,7 +13,7 @@ static inline unsigned int bpf_num_possible_cpus(void) unsigned int start, end, possible_cpus = 0; char buff[128]; FILE *fp; - int n; + int len, n, i, j = 0; fp = fopen(fcpu, "r"); if (!fp) { @@ -21,17 +21,27 @@ static inline unsigned int bpf_num_possible_cpus(void) exit(1); } - while (fgets(buff, sizeof(buff), fp)) { - n = sscanf(buff, "%u-%u", &start, &end); - if (n == 0) { - printf("Failed to retrieve # possible CPUs!\n"); - exit(1); - } else if (n == 1) { - end = start; - } - possible_cpus = start == 0 ? end + 1 : 0; - break; + if (!fgets(buff, sizeof(buff), fp)) { + printf("Failed to read %s!\n", fcpu); + exit(1); } + + len = strlen(buff); + for (i = 0; i <= len; i++) { + if (buff[i] == ',' || buff[i] == '\0') { + buff[i] = '\0'; + n = sscanf(&buff[j], "%u-%u", &start, &end); + if (n <= 0) { + printf("Failed to retrieve # possible CPUs!\n"); + exit(1); + } else if (n == 1) { + end = start; + } + possible_cpus += end - start + 1; + j = i + 1; + } + } + fclose(fp); return possible_cpus; From 6cab5e90ab2bd323c9f3811b6c70a4687df51e27 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 28 Jan 2019 18:43:34 -0800 Subject: [PATCH 321/525] bpf: run bpf programs with preemption disabled Disabled preemption is necessary for proper access to per-cpu maps from BPF programs. But the sender side of socket filters didn't have preemption disabled: unix_dgram_sendmsg->sk_filter->sk_filter_trim_cap->bpf_prog_run_save_cb->BPF_PROG_RUN and a combination of af_packet with tun device didn't disable either: tpacket_snd->packet_direct_xmit->packet_pick_tx_queue->ndo_select_queue-> tun_select_queue->tun_ebpf_select_queue->bpf_prog_run_clear_cb->BPF_PROG_RUN Disable preemption before executing BPF programs (both classic and extended). Reported-by: Jann Horn Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- include/linux/filter.h | 21 ++++++++++++++++++--- kernel/bpf/cgroup.c | 2 +- 2 files changed, 19 insertions(+), 4 deletions(-) diff --git a/include/linux/filter.h b/include/linux/filter.h index ad106d845b22..e532fcc6e4b5 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -591,8 +591,8 @@ static inline u8 *bpf_skb_cb(struct sk_buff *skb) return qdisc_skb_cb(skb)->data; } -static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, - struct sk_buff *skb) +static inline u32 __bpf_prog_run_save_cb(const struct bpf_prog *prog, + struct sk_buff *skb) { u8 *cb_data = bpf_skb_cb(skb); u8 cb_saved[BPF_SKB_CB_LEN]; @@ -611,15 +611,30 @@ static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, return res; } +static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, + struct sk_buff *skb) +{ + u32 res; + + preempt_disable(); + res = __bpf_prog_run_save_cb(prog, skb); + preempt_enable(); + return res; +} + static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, struct sk_buff *skb) { u8 *cb_data = bpf_skb_cb(skb); + u32 res; if (unlikely(prog->cb_access)) memset(cb_data, 0, BPF_SKB_CB_LEN); - return BPF_PROG_RUN(prog, skb); + preempt_disable(); + res = BPF_PROG_RUN(prog, skb); + preempt_enable(); + return res; } static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index ab612fe9862f..d17d05570a3f 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -572,7 +572,7 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, bpf_compute_and_save_data_end(skb, &saved_data_end); ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb, - bpf_prog_run_save_cb); + __bpf_prog_run_save_cb); bpf_restore_data_end(skb, saved_data_end); __skb_pull(skb, offset); skb->sk = save_sk; From a89fac57b5d080771efd4d71feaae19877cf68f0 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 30 Jan 2019 18:12:43 -0800 Subject: [PATCH 322/525] bpf: fix lockdep false positive in percpu_freelist Lockdep warns about false positive: [ 12.492084] 00000000e6b28347 (&head->lock){+...}, at: pcpu_freelist_push+0x2a/0x40 [ 12.492696] but this lock was taken by another, HARDIRQ-safe lock in the past: [ 12.493275] (&rq->lock){-.-.} [ 12.493276] [ 12.493276] [ 12.493276] and interrupts could create inverse lock ordering between them. [ 12.493276] [ 12.494435] [ 12.494435] other info that might help us debug this: [ 12.494979] Possible interrupt unsafe locking scenario: [ 12.494979] [ 12.495518] CPU0 CPU1 [ 12.495879] ---- ---- [ 12.496243] lock(&head->lock); [ 12.496502] local_irq_disable(); [ 12.496969] lock(&rq->lock); [ 12.497431] lock(&head->lock); [ 12.497890] [ 12.498104] lock(&rq->lock); [ 12.498368] [ 12.498368] *** DEADLOCK *** [ 12.498368] [ 12.498837] 1 lock held by dd/276: [ 12.499110] #0: 00000000c58cb2ee (rcu_read_lock){....}, at: trace_call_bpf+0x5e/0x240 [ 12.499747] [ 12.499747] the shortest dependencies between 2nd lock and 1st lock: [ 12.500389] -> (&rq->lock){-.-.} { [ 12.500669] IN-HARDIRQ-W at: [ 12.500934] _raw_spin_lock+0x2f/0x40 [ 12.501373] scheduler_tick+0x4c/0xf0 [ 12.501812] update_process_times+0x40/0x50 [ 12.502294] tick_periodic+0x27/0xb0 [ 12.502723] tick_handle_periodic+0x1f/0x60 [ 12.503203] timer_interrupt+0x11/0x20 [ 12.503651] __handle_irq_event_percpu+0x43/0x2c0 [ 12.504167] handle_irq_event_percpu+0x20/0x50 [ 12.504674] handle_irq_event+0x37/0x60 [ 12.505139] handle_level_irq+0xa7/0x120 [ 12.505601] handle_irq+0xa1/0x150 [ 12.506018] do_IRQ+0x77/0x140 [ 12.506411] ret_from_intr+0x0/0x1d [ 12.506834] _raw_spin_unlock_irqrestore+0x53/0x60 [ 12.507362] __setup_irq+0x481/0x730 [ 12.507789] setup_irq+0x49/0x80 [ 12.508195] hpet_time_init+0x21/0x32 [ 12.508644] x86_late_time_init+0xb/0x16 [ 12.509106] start_kernel+0x390/0x42a [ 12.509554] secondary_startup_64+0xa4/0xb0 [ 12.510034] IN-SOFTIRQ-W at: [ 12.510305] _raw_spin_lock+0x2f/0x40 [ 12.510772] try_to_wake_up+0x1c7/0x4e0 [ 12.511220] swake_up_locked+0x20/0x40 [ 12.511657] swake_up_one+0x1a/0x30 [ 12.512070] rcu_process_callbacks+0xc5/0x650 [ 12.512553] __do_softirq+0xe6/0x47b [ 12.512978] irq_exit+0xc3/0xd0 [ 12.513372] smp_apic_timer_interrupt+0xa9/0x250 [ 12.513876] apic_timer_interrupt+0xf/0x20 [ 12.514343] default_idle+0x1c/0x170 [ 12.514765] do_idle+0x199/0x240 [ 12.515159] cpu_startup_entry+0x19/0x20 [ 12.515614] start_kernel+0x422/0x42a [ 12.516045] secondary_startup_64+0xa4/0xb0 [ 12.516521] INITIAL USE at: [ 12.516774] _raw_spin_lock_irqsave+0x38/0x50 [ 12.517258] rq_attach_root+0x16/0xd0 [ 12.517685] sched_init+0x2f2/0x3eb [ 12.518096] start_kernel+0x1fb/0x42a [ 12.518525] secondary_startup_64+0xa4/0xb0 [ 12.518986] } [ 12.519132] ... key at: [] __key.71384+0x0/0x8 [ 12.519649] ... acquired at: [ 12.519892] pcpu_freelist_pop+0x7b/0xd0 [ 12.520221] bpf_get_stackid+0x1d2/0x4d0 [ 12.520563] ___bpf_prog_run+0x8b4/0x11a0 [ 12.520887] [ 12.521008] -> (&head->lock){+...} { [ 12.521292] HARDIRQ-ON-W at: [ 12.521539] _raw_spin_lock+0x2f/0x40 [ 12.521950] pcpu_freelist_push+0x2a/0x40 [ 12.522396] bpf_get_stackid+0x494/0x4d0 [ 12.522828] ___bpf_prog_run+0x8b4/0x11a0 [ 12.523296] INITIAL USE at: [ 12.523537] _raw_spin_lock+0x2f/0x40 [ 12.523944] pcpu_freelist_populate+0xc0/0x120 [ 12.524417] htab_map_alloc+0x405/0x500 [ 12.524835] __do_sys_bpf+0x1a3/0x1a90 [ 12.525253] do_syscall_64+0x4a/0x180 [ 12.525659] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 12.526167] } [ 12.526311] ... key at: [] __key.13130+0x0/0x8 [ 12.526812] ... acquired at: [ 12.527047] __lock_acquire+0x521/0x1350 [ 12.527371] lock_acquire+0x98/0x190 [ 12.527680] _raw_spin_lock+0x2f/0x40 [ 12.527994] pcpu_freelist_push+0x2a/0x40 [ 12.528325] bpf_get_stackid+0x494/0x4d0 [ 12.528645] ___bpf_prog_run+0x8b4/0x11a0 [ 12.528970] [ 12.529092] [ 12.529092] stack backtrace: [ 12.529444] CPU: 0 PID: 276 Comm: dd Not tainted 5.0.0-rc3-00018-g2fa53f892422 #475 [ 12.530043] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-2.el7 04/01/2014 [ 12.530750] Call Trace: [ 12.530948] dump_stack+0x5f/0x8b [ 12.531248] check_usage_backwards+0x10c/0x120 [ 12.531598] ? ___bpf_prog_run+0x8b4/0x11a0 [ 12.531935] ? mark_lock+0x382/0x560 [ 12.532229] mark_lock+0x382/0x560 [ 12.532496] ? print_shortest_lock_dependencies+0x180/0x180 [ 12.532928] __lock_acquire+0x521/0x1350 [ 12.533271] ? find_get_entry+0x17f/0x2e0 [ 12.533586] ? find_get_entry+0x19c/0x2e0 [ 12.533902] ? lock_acquire+0x98/0x190 [ 12.534196] lock_acquire+0x98/0x190 [ 12.534482] ? pcpu_freelist_push+0x2a/0x40 [ 12.534810] _raw_spin_lock+0x2f/0x40 [ 12.535099] ? pcpu_freelist_push+0x2a/0x40 [ 12.535432] pcpu_freelist_push+0x2a/0x40 [ 12.535750] bpf_get_stackid+0x494/0x4d0 [ 12.536062] ___bpf_prog_run+0x8b4/0x11a0 It has been explained that is a false positive here: https://lkml.org/lkml/2018/7/25/756 Recap: - stackmap uses pcpu_freelist - The lock in pcpu_freelist is a percpu lock - stackmap is only used by tracing bpf_prog - A tracing bpf_prog cannot be run if another bpf_prog has already been running (ensured by the percpu bpf_prog_active counter). Eric pointed out that this lockdep splats stops other legit lockdep splats in selftests/bpf/test_progs.c. Fix this by calling local_irq_save/restore for stackmap. Another false positive had also been worked around by calling local_irq_save in commit 89ad2fa3f043 ("bpf: fix lockdep splat"). That commit added unnecessary irq_save/restore to fast path of bpf hash map. irqs are already disabled at that point, since htab is holding per bucket spin_lock with irqsave. Let's reduce overhead for htab by introducing __pcpu_freelist_push/pop function w/o irqsave and convert pcpu_freelist_push/pop to irqsave to be used elsewhere (right now only in stackmap). It stops lockdep false positive in stackmap with a bit of acceptable overhead. Fixes: 557c0c6e7df8 ("bpf: convert stackmap to pre-allocation") Reported-by: Naresh Kamboju Reported-by: Eric Dumazet Acked-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- kernel/bpf/hashtab.c | 4 ++-- kernel/bpf/percpu_freelist.c | 41 +++++++++++++++++++++++++----------- kernel/bpf/percpu_freelist.h | 4 ++++ 3 files changed, 35 insertions(+), 14 deletions(-) diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 4b7c76765d9d..f9274114c88d 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -686,7 +686,7 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) } if (htab_is_prealloc(htab)) { - pcpu_freelist_push(&htab->freelist, &l->fnode); + __pcpu_freelist_push(&htab->freelist, &l->fnode); } else { atomic_dec(&htab->count); l->htab = htab; @@ -748,7 +748,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, } else { struct pcpu_freelist_node *l; - l = pcpu_freelist_pop(&htab->freelist); + l = __pcpu_freelist_pop(&htab->freelist); if (!l) return ERR_PTR(-E2BIG); l_new = container_of(l, struct htab_elem, fnode); diff --git a/kernel/bpf/percpu_freelist.c b/kernel/bpf/percpu_freelist.c index 673fa6fe2d73..0c1b4ba9e90e 100644 --- a/kernel/bpf/percpu_freelist.c +++ b/kernel/bpf/percpu_freelist.c @@ -28,8 +28,8 @@ void pcpu_freelist_destroy(struct pcpu_freelist *s) free_percpu(s->freelist); } -static inline void __pcpu_freelist_push(struct pcpu_freelist_head *head, - struct pcpu_freelist_node *node) +static inline void ___pcpu_freelist_push(struct pcpu_freelist_head *head, + struct pcpu_freelist_node *node) { raw_spin_lock(&head->lock); node->next = head->first; @@ -37,12 +37,22 @@ static inline void __pcpu_freelist_push(struct pcpu_freelist_head *head, raw_spin_unlock(&head->lock); } -void pcpu_freelist_push(struct pcpu_freelist *s, +void __pcpu_freelist_push(struct pcpu_freelist *s, struct pcpu_freelist_node *node) { struct pcpu_freelist_head *head = this_cpu_ptr(s->freelist); - __pcpu_freelist_push(head, node); + ___pcpu_freelist_push(head, node); +} + +void pcpu_freelist_push(struct pcpu_freelist *s, + struct pcpu_freelist_node *node) +{ + unsigned long flags; + + local_irq_save(flags); + __pcpu_freelist_push(s, node); + local_irq_restore(flags); } void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size, @@ -63,7 +73,7 @@ void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size, for_each_possible_cpu(cpu) { again: head = per_cpu_ptr(s->freelist, cpu); - __pcpu_freelist_push(head, buf); + ___pcpu_freelist_push(head, buf); i++; buf += elem_size; if (i == nr_elems) @@ -74,14 +84,12 @@ again: local_irq_restore(flags); } -struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s) +struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *s) { struct pcpu_freelist_head *head; struct pcpu_freelist_node *node; - unsigned long flags; int orig_cpu, cpu; - local_irq_save(flags); orig_cpu = cpu = raw_smp_processor_id(); while (1) { head = per_cpu_ptr(s->freelist, cpu); @@ -89,16 +97,25 @@ struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s) node = head->first; if (node) { head->first = node->next; - raw_spin_unlock_irqrestore(&head->lock, flags); + raw_spin_unlock(&head->lock); return node; } raw_spin_unlock(&head->lock); cpu = cpumask_next(cpu, cpu_possible_mask); if (cpu >= nr_cpu_ids) cpu = 0; - if (cpu == orig_cpu) { - local_irq_restore(flags); + if (cpu == orig_cpu) return NULL; - } } } + +struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s) +{ + struct pcpu_freelist_node *ret; + unsigned long flags; + + local_irq_save(flags); + ret = __pcpu_freelist_pop(s); + local_irq_restore(flags); + return ret; +} diff --git a/kernel/bpf/percpu_freelist.h b/kernel/bpf/percpu_freelist.h index 3049aae8ea1e..c3960118e617 100644 --- a/kernel/bpf/percpu_freelist.h +++ b/kernel/bpf/percpu_freelist.h @@ -22,8 +22,12 @@ struct pcpu_freelist_node { struct pcpu_freelist_node *next; }; +/* pcpu_freelist_* do spin_lock_irqsave. */ void pcpu_freelist_push(struct pcpu_freelist *, struct pcpu_freelist_node *); struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *); +/* __pcpu_freelist_* do spin_lock only. caller must disable irqs. */ +void __pcpu_freelist_push(struct pcpu_freelist *, struct pcpu_freelist_node *); +struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *); void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size, u32 nr_elems); int pcpu_freelist_init(struct pcpu_freelist *); From e16ec34039c701594d55d08a5aa49ee3e1abc821 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 30 Jan 2019 18:12:44 -0800 Subject: [PATCH 323/525] bpf: fix potential deadlock in bpf_prog_register Lockdep found a potential deadlock between cpu_hotplug_lock, bpf_event_mutex, and cpuctx_mutex: [ 13.007000] WARNING: possible circular locking dependency detected [ 13.007587] 5.0.0-rc3-00018-g2fa53f892422-dirty #477 Not tainted [ 13.008124] ------------------------------------------------------ [ 13.008624] test_progs/246 is trying to acquire lock: [ 13.009030] 0000000094160d1d (tracepoints_mutex){+.+.}, at: tracepoint_probe_register_prio+0x2d/0x300 [ 13.009770] [ 13.009770] but task is already holding lock: [ 13.010239] 00000000d663ef86 (bpf_event_mutex){+.+.}, at: bpf_probe_register+0x1d/0x60 [ 13.010877] [ 13.010877] which lock already depends on the new lock. [ 13.010877] [ 13.011532] [ 13.011532] the existing dependency chain (in reverse order) is: [ 13.012129] [ 13.012129] -> #4 (bpf_event_mutex){+.+.}: [ 13.012582] perf_event_query_prog_array+0x9b/0x130 [ 13.013016] _perf_ioctl+0x3aa/0x830 [ 13.013354] perf_ioctl+0x2e/0x50 [ 13.013668] do_vfs_ioctl+0x8f/0x6a0 [ 13.014003] ksys_ioctl+0x70/0x80 [ 13.014320] __x64_sys_ioctl+0x16/0x20 [ 13.014668] do_syscall_64+0x4a/0x180 [ 13.015007] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 13.015469] [ 13.015469] -> #3 (&cpuctx_mutex){+.+.}: [ 13.015910] perf_event_init_cpu+0x5a/0x90 [ 13.016291] perf_event_init+0x1b2/0x1de [ 13.016654] start_kernel+0x2b8/0x42a [ 13.016995] secondary_startup_64+0xa4/0xb0 [ 13.017382] [ 13.017382] -> #2 (pmus_lock){+.+.}: [ 13.017794] perf_event_init_cpu+0x21/0x90 [ 13.018172] cpuhp_invoke_callback+0xb3/0x960 [ 13.018573] _cpu_up+0xa7/0x140 [ 13.018871] do_cpu_up+0xa4/0xc0 [ 13.019178] smp_init+0xcd/0xd2 [ 13.019483] kernel_init_freeable+0x123/0x24f [ 13.019878] kernel_init+0xa/0x110 [ 13.020201] ret_from_fork+0x24/0x30 [ 13.020541] [ 13.020541] -> #1 (cpu_hotplug_lock.rw_sem){++++}: [ 13.021051] static_key_slow_inc+0xe/0x20 [ 13.021424] tracepoint_probe_register_prio+0x28c/0x300 [ 13.021891] perf_trace_event_init+0x11f/0x250 [ 13.022297] perf_trace_init+0x6b/0xa0 [ 13.022644] perf_tp_event_init+0x25/0x40 [ 13.023011] perf_try_init_event+0x6b/0x90 [ 13.023386] perf_event_alloc+0x9a8/0xc40 [ 13.023754] __do_sys_perf_event_open+0x1dd/0xd30 [ 13.024173] do_syscall_64+0x4a/0x180 [ 13.024519] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 13.024968] [ 13.024968] -> #0 (tracepoints_mutex){+.+.}: [ 13.025434] __mutex_lock+0x86/0x970 [ 13.025764] tracepoint_probe_register_prio+0x2d/0x300 [ 13.026215] bpf_probe_register+0x40/0x60 [ 13.026584] bpf_raw_tracepoint_open.isra.34+0xa4/0x130 [ 13.027042] __do_sys_bpf+0x94f/0x1a90 [ 13.027389] do_syscall_64+0x4a/0x180 [ 13.027727] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 13.028171] [ 13.028171] other info that might help us debug this: [ 13.028171] [ 13.028807] Chain exists of: [ 13.028807] tracepoints_mutex --> &cpuctx_mutex --> bpf_event_mutex [ 13.028807] [ 13.029666] Possible unsafe locking scenario: [ 13.029666] [ 13.030140] CPU0 CPU1 [ 13.030510] ---- ---- [ 13.030875] lock(bpf_event_mutex); [ 13.031166] lock(&cpuctx_mutex); [ 13.031645] lock(bpf_event_mutex); [ 13.032135] lock(tracepoints_mutex); [ 13.032441] [ 13.032441] *** DEADLOCK *** [ 13.032441] [ 13.032911] 1 lock held by test_progs/246: [ 13.033239] #0: 00000000d663ef86 (bpf_event_mutex){+.+.}, at: bpf_probe_register+0x1d/0x60 [ 13.033909] [ 13.033909] stack backtrace: [ 13.034258] CPU: 1 PID: 246 Comm: test_progs Not tainted 5.0.0-rc3-00018-g2fa53f892422-dirty #477 [ 13.034964] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-2.el7 04/01/2014 [ 13.035657] Call Trace: [ 13.035859] dump_stack+0x5f/0x8b [ 13.036130] print_circular_bug.isra.37+0x1ce/0x1db [ 13.036526] __lock_acquire+0x1158/0x1350 [ 13.036852] ? lock_acquire+0x98/0x190 [ 13.037154] lock_acquire+0x98/0x190 [ 13.037447] ? tracepoint_probe_register_prio+0x2d/0x300 [ 13.037876] __mutex_lock+0x86/0x970 [ 13.038167] ? tracepoint_probe_register_prio+0x2d/0x300 [ 13.038600] ? tracepoint_probe_register_prio+0x2d/0x300 [ 13.039028] ? __mutex_lock+0x86/0x970 [ 13.039337] ? __mutex_lock+0x24a/0x970 [ 13.039649] ? bpf_probe_register+0x1d/0x60 [ 13.039992] ? __bpf_trace_sched_wake_idle_without_ipi+0x10/0x10 [ 13.040478] ? tracepoint_probe_register_prio+0x2d/0x300 [ 13.040906] tracepoint_probe_register_prio+0x2d/0x300 [ 13.041325] bpf_probe_register+0x40/0x60 [ 13.041649] bpf_raw_tracepoint_open.isra.34+0xa4/0x130 [ 13.042068] ? __might_fault+0x3e/0x90 [ 13.042374] __do_sys_bpf+0x94f/0x1a90 [ 13.042678] do_syscall_64+0x4a/0x180 [ 13.042975] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 13.043382] RIP: 0033:0x7f23b10a07f9 [ 13.045155] RSP: 002b:00007ffdef42fdd8 EFLAGS: 00000202 ORIG_RAX: 0000000000000141 [ 13.045759] RAX: ffffffffffffffda RBX: 00007ffdef42ff70 RCX: 00007f23b10a07f9 [ 13.046326] RDX: 0000000000000070 RSI: 00007ffdef42fe10 RDI: 0000000000000011 [ 13.046893] RBP: 00007ffdef42fdf0 R08: 0000000000000038 R09: 00007ffdef42fe10 [ 13.047462] R10: 0000000000000000 R11: 0000000000000202 R12: 0000000000000000 [ 13.048029] R13: 0000000000000016 R14: 00007f23b1db4690 R15: 0000000000000000 Since tracepoints_mutex will be taken in tracepoint_probe_register/unregister() there is no need to take bpf_event_mutex too. bpf_event_mutex is protecting modifications to prog array used in kprobe/perf bpf progs. bpf_raw_tracepoints don't need to take this mutex. Fixes: c4f6699dfcb8 ("bpf: introduce BPF_RAW_TRACEPOINT") Acked-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- kernel/trace/bpf_trace.c | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 8b068adb9da1..f1a86a0d881d 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1204,22 +1204,12 @@ static int __bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog * int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog) { - int err; - - mutex_lock(&bpf_event_mutex); - err = __bpf_probe_register(btp, prog); - mutex_unlock(&bpf_event_mutex); - return err; + return __bpf_probe_register(btp, prog); } int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog) { - int err; - - mutex_lock(&bpf_event_mutex); - err = tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, prog); - mutex_unlock(&bpf_event_mutex); - return err; + return tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, prog); } int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, From 7c4cd051add3d00bbff008a133c936c515eaa8fe Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 30 Jan 2019 18:12:45 -0800 Subject: [PATCH 324/525] bpf: Fix syscall's stackmap lookup potential deadlock The map_lookup_elem used to not acquiring spinlock in order to optimize the reader. It was true until commit 557c0c6e7df8 ("bpf: convert stackmap to pre-allocation") The syscall's map_lookup_elem(stackmap) calls bpf_stackmap_copy(). bpf_stackmap_copy() may find the elem no longer needed after the copy is done. If that is the case, pcpu_freelist_push() saves this elem for reuse later. This push requires a spinlock. If a tracing bpf_prog got run in the middle of the syscall's map_lookup_elem(stackmap) and this tracing bpf_prog is calling bpf_get_stackid(stackmap) which also requires the same pcpu_freelist's spinlock, it may end up with a dead lock situation as reported by Eric Dumazet in https://patchwork.ozlabs.org/patch/1030266/ The situation is the same as the syscall's map_update_elem() which needs to acquire the pcpu_freelist's spinlock and could race with tracing bpf_prog. Hence, this patch fixes it by protecting bpf_stackmap_copy() with this_cpu_inc(bpf_prog_active) to prevent tracing bpf_prog from running. A later syscall's map_lookup_elem commit f1a2e44a3aec ("bpf: add queue and stack maps") also acquires a spinlock and races with tracing bpf_prog similarly. Hence, this patch is forward looking and protects the majority of the map lookups. bpf_map_offload_lookup_elem() is the exception since it is for network bpf_prog only (i.e. never called by tracing bpf_prog). Fixes: 557c0c6e7df8 ("bpf: convert stackmap to pre-allocation") Reported-by: Eric Dumazet Acked-by: Alexei Starovoitov Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- kernel/bpf/syscall.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b155cd17c1bd..8577bb7f8be6 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -713,8 +713,13 @@ static int map_lookup_elem(union bpf_attr *attr) if (bpf_map_is_dev_bound(map)) { err = bpf_map_offload_lookup_elem(map, key, value); - } else if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { + goto done; + } + + preempt_disable(); + this_cpu_inc(bpf_prog_active); + if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { err = bpf_percpu_hash_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_copy(map, key, value); @@ -744,7 +749,10 @@ static int map_lookup_elem(union bpf_attr *attr) } rcu_read_unlock(); } + this_cpu_dec(bpf_prog_active); + preempt_enable(); +done: if (err) goto free_value; From 5a3840a470c41ec0b85cd36ca80370330656b163 Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Thu, 31 Jan 2019 12:53:47 +1100 Subject: [PATCH 325/525] powerpc/papr_scm: Use the correct bind address When binding an SCM volume to a physical address the hypervisor has the option to return early with a continue token with the expectation that the guest will resume the bind operation until it completes. A quirk of this interface is that the bind address will only be returned by the first bind h-call and the subsequent calls will return 0xFFFF_FFFF_FFFF_FFFF for the bind address. We currently do not save the address returned by the first h-call. As a result we will use the junk address as the base of the bound region if the hypervisor decides to split the bind across multiple h-calls. This bug was found when testing with very large SCM volumes where the bind process would take more time than they hypervisor's internal h-call time limit would allow. This patch fixes the issue by saving the bind address from the first call. Cc: stable@vger.kernel.org Fixes: b5beae5e224f ("powerpc/pseries: Add driver for PAPR SCM regions") Signed-off-by: Oliver O'Halloran Signed-off-by: Michael Ellerman --- arch/powerpc/platforms/pseries/papr_scm.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 7d6457ab5d34..bba281b1fe1b 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -43,6 +43,7 @@ static int drc_pmem_bind(struct papr_scm_priv *p) { unsigned long ret[PLPAR_HCALL_BUFSIZE]; uint64_t rc, token; + uint64_t saved = 0; /* * When the hypervisor cannot map all the requested memory in a single @@ -56,6 +57,8 @@ static int drc_pmem_bind(struct papr_scm_priv *p) rc = plpar_hcall(H_SCM_BIND_MEM, ret, p->drc_index, 0, p->blocks, BIND_ANY_ADDR, token); token = ret[0]; + if (!saved) + saved = ret[1]; cond_resched(); } while (rc == H_BUSY); @@ -64,7 +67,7 @@ static int drc_pmem_bind(struct papr_scm_priv *p) return -ENXIO; } - p->bound_addr = ret[1]; + p->bound_addr = saved; dev_dbg(&p->pdev->dev, "bound drc %x to %pR\n", p->drc_index, &p->res); From 1f66b7ea8c4c99dba1e4e4a85ac532eee00af908 Mon Sep 17 00:00:00 2001 From: Roman Li Date: Thu, 17 Jan 2019 15:47:54 -0500 Subject: [PATCH 326/525] drm/amd/display: Fix fclk idle state [Why] The earlier change 'Fix 6x4K displays' led to fclk value idling at higher DPM level. [How] Apply the fix only to respective multi-display configuration. Signed-off-by: Roman Li Reviewed-by: Feifei Xu Acked-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c index afd287f08bc9..19801bdba0d2 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c @@ -591,7 +591,15 @@ static void dce11_pplib_apply_display_requirements( dc, context->bw.dce.sclk_khz); - pp_display_cfg->min_dcfclock_khz = pp_display_cfg->min_engine_clock_khz; + /* + * As workaround for >4x4K lightup set dcfclock to min_engine_clock value. + * This is not required for less than 5 displays, + * thus don't request decfclk in dc to avoid impact + * on power saving. + * + */ + pp_display_cfg->min_dcfclock_khz = (context->stream_count > 4)? + pp_display_cfg->min_engine_clock_khz : 0; pp_display_cfg->min_engine_clock_deep_sleep_khz = context->bw.dce.sclk_deep_sleep_khz; From 12292519d919ecde92e7e7c8acbcdb9f0c7c6013 Mon Sep 17 00:00:00 2001 From: Jay Cornwall Date: Wed, 30 Jan 2019 12:53:29 -0600 Subject: [PATCH 327/525] drm/amdgpu: Implement doorbell self-ring for NBIO 7.4 Fixes doorbell reflection on Vega20. Change-Id: I0495139d160a9032dff5977289b1eec11c16f781 Signed-off-by: Jay Cornwall Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c index 4cd31a276dcd..186db182f924 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c @@ -93,7 +93,20 @@ static void nbio_v7_4_enable_doorbell_aperture(struct amdgpu_device *adev, static void nbio_v7_4_enable_doorbell_selfring_aperture(struct amdgpu_device *adev, bool enable) { + u32 tmp = 0; + if (enable) { + tmp = REG_SET_FIELD(tmp, DOORBELL_SELFRING_GPA_APER_CNTL, DOORBELL_SELFRING_GPA_APER_EN, 1) | + REG_SET_FIELD(tmp, DOORBELL_SELFRING_GPA_APER_CNTL, DOORBELL_SELFRING_GPA_APER_MODE, 1) | + REG_SET_FIELD(tmp, DOORBELL_SELFRING_GPA_APER_CNTL, DOORBELL_SELFRING_GPA_APER_SIZE, 0); + + WREG32_SOC15(NBIO, 0, mmDOORBELL_SELFRING_GPA_APER_BASE_LOW, + lower_32_bits(adev->doorbell.base)); + WREG32_SOC15(NBIO, 0, mmDOORBELL_SELFRING_GPA_APER_BASE_HIGH, + upper_32_bits(adev->doorbell.base)); + } + + WREG32_SOC15(NBIO, 0, mmDOORBELL_SELFRING_GPA_APER_CNTL, tmp); } static void nbio_v7_4_ih_doorbell_range(struct amdgpu_device *adev, From 7e4545d372b560df10fa47281ef0783a479ce435 Mon Sep 17 00:00:00 2001 From: Huang Rui Date: Wed, 30 Jan 2019 19:50:04 +0800 Subject: [PATCH 328/525] drm/amdgpu: fix the incorrect external id for raven series This patch fixes the incorrect external id that kernel reports to user mode driver. Raven2's rev_id is starts from 0x8, so its external id (0x81) should start from rev_id + 0x79 (0x81 - 0x8). And Raven's rev_id should be 0x21 while rev_id == 1. Reported-by: Crystal Jin Signed-off-by: Huang Rui Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/soc15.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 8849b74078d6..9b639974c70c 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -729,11 +729,13 @@ static int soc15_common_early_init(void *handle) case CHIP_RAVEN: adev->asic_funcs = &soc15_asic_funcs; if (adev->rev_id >= 0x8) - adev->external_rev_id = adev->rev_id + 0x81; + adev->external_rev_id = adev->rev_id + 0x79; else if (adev->pdev->device == 0x15d8) adev->external_rev_id = adev->rev_id + 0x41; + else if (adev->rev_id == 1) + adev->external_rev_id = adev->rev_id + 0x20; else - adev->external_rev_id = 0x1; + adev->external_rev_id = adev->rev_id + 0x01; if (adev->rev_id >= 0x8) { adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG | From bda2ab56356b9acdfab150f31c4bac9846253092 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Wed, 30 Jan 2019 09:47:00 +0100 Subject: [PATCH 329/525] mtd: Remove a debug trace in mtdpart.c Commit 2b6f0090a333 ("mtd: Check add_mtd_device() ret code") contained a leftover of the debug session that led to this bug fix. Remove this pr_info(). Fixes: 2b6f0090a333 ("mtd: Check add_mtd_device() ret code") Signed-off-by: Boris Brezillon --- drivers/mtd/mtdpart.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index 60104e1079c5..e6d9467f6be0 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -632,7 +632,6 @@ err_remove_part: mutex_unlock(&mtd_partitions_mutex); free_partition(new); - pr_info("%s:%i\n", __func__, __LINE__); return ret; } From 9d0f50b80222dc273e67e4e14410fcfa4130a90c Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Tue, 29 Jan 2019 11:10:57 +0100 Subject: [PATCH 330/525] mac80211: ensure that mgmt tx skbs have tailroom for encryption Some drivers use IEEE80211_KEY_FLAG_SW_MGMT_TX to indicate that management frames need to be software encrypted. Since normal data packets are still encrypted by the hardware, crypto_tx_tailroom_needed_cnt gets decremented after key upload to hw. This can lead to passing skbs to ccmp_encrypt_skb, which don't have the necessary tailroom for software encryption. Change the code to add tailroom for encrypted management packets, even if crypto_tx_tailroom_needed_cnt is 0. Cc: stable@vger.kernel.org Signed-off-by: Felix Fietkau Signed-off-by: Johannes Berg --- net/mac80211/tx.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index f170d6c6629a..928f13a208b0 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1938,9 +1938,16 @@ static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata, int head_need, bool may_encrypt) { struct ieee80211_local *local = sdata->local; + struct ieee80211_hdr *hdr; + bool enc_tailroom; int tail_need = 0; - if (may_encrypt && sdata->crypto_tx_tailroom_needed_cnt) { + hdr = (struct ieee80211_hdr *) skb->data; + enc_tailroom = may_encrypt && + (sdata->crypto_tx_tailroom_needed_cnt || + ieee80211_is_mgmt(hdr->frame_control)); + + if (enc_tailroom) { tail_need = IEEE80211_ENCRYPT_TAILROOM; tail_need -= skb_tailroom(skb); tail_need = max_t(int, tail_need, 0); @@ -1948,8 +1955,7 @@ static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata, if (skb_cloned(skb) && (!ieee80211_hw_check(&local->hw, SUPPORTS_CLONED_SKBS) || - !skb_clone_writable(skb, ETH_HLEN) || - (may_encrypt && sdata->crypto_tx_tailroom_needed_cnt))) + !skb_clone_writable(skb, ETH_HLEN) || enc_tailroom)) I802_DEBUG_INC(local->tx_expand_skb_head_cloned); else if (head_need || tail_need) I802_DEBUG_INC(local->tx_expand_skb_head); From e005bd7ddea06784c1eb91ac5bb6b171a94f3b05 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 1 Feb 2019 11:09:54 +0100 Subject: [PATCH 331/525] cfg80211: call disconnect_wk when AP stops Since we now prevent regulatory restore during STA disconnect if concurrent AP interfaces are active, we need to reschedule this check when the AP state changes. This fixes never doing a restore when an AP is the last interface to stop. Or to put it another way: we need to re-check after anything we check here changes. Cc: stable@vger.kernel.org Fixes: 113f3aaa81bd ("cfg80211: Prevent regulatory restore during STA disconnect in concurrent interfaces") Signed-off-by: Johannes Berg --- net/wireless/ap.c | 2 ++ net/wireless/core.h | 2 ++ net/wireless/sme.c | 2 +- 3 files changed, 5 insertions(+), 1 deletion(-) diff --git a/net/wireless/ap.c b/net/wireless/ap.c index 882d97bdc6bf..550ac9d827fe 100644 --- a/net/wireless/ap.c +++ b/net/wireless/ap.c @@ -41,6 +41,8 @@ int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev, cfg80211_sched_dfs_chan_update(rdev); } + schedule_work(&cfg80211_disconnect_work); + return err; } diff --git a/net/wireless/core.h b/net/wireless/core.h index c5d6f3418601..f6b40563dc63 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -445,6 +445,8 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev); bool cfg80211_does_bw_fit_range(const struct ieee80211_freq_range *freq_range, u32 center_freq_khz, u32 bw_khz); +extern struct work_struct cfg80211_disconnect_work; + /** * cfg80211_chandef_dfs_usable - checks if chandef is DFS usable * @wiphy: the wiphy to validate against diff --git a/net/wireless/sme.c b/net/wireless/sme.c index f741d8376a46..7d34cb884840 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -667,7 +667,7 @@ static void disconnect_work(struct work_struct *work) rtnl_unlock(); } -static DECLARE_WORK(cfg80211_disconnect_work, disconnect_work); +DECLARE_WORK(cfg80211_disconnect_work, disconnect_work); /* From d561aa0a70bb2e1dd85fde98b6a5561e4175ac3e Mon Sep 17 00:00:00 2001 From: Kailang Yang Date: Fri, 1 Feb 2019 16:51:10 +0800 Subject: [PATCH 332/525] ALSA: hda/realtek - Fix lose hp_pins for disable auto mute When auto_mute = no or spec->suppress_auto_mute = 1, cfg->hp_pins will lose value. Add this patch to find hp_pins value. I add fixed for ALC282 ALC225 ALC256 ALC294 and alc_default_init() alc_default_shutup(). Signed-off-by: Kailang Yang Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 45 +++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index f2523fab5fed..5b1a71fb909c 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2963,6 +2963,11 @@ static void alc282_init(struct hda_codec *codec) bool hp_pin_sense; int coef78; + if (!spec->gen.autocfg.hp_outs && spec->gen.suppress_auto_mute) { + if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) + hp_pin = spec->gen.autocfg.line_out_pins[0]; + } + alc282_restore_default_value(codec); if (!hp_pin) @@ -3000,6 +3005,11 @@ static void alc282_shutup(struct hda_codec *codec) bool hp_pin_sense; int coef78; + if (!spec->gen.autocfg.hp_outs && spec->gen.suppress_auto_mute) { + if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) + hp_pin = spec->gen.autocfg.line_out_pins[0]; + } + if (!hp_pin) { alc269_shutup(codec); return; @@ -3159,6 +3169,11 @@ static void alc256_init(struct hda_codec *codec) hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; bool hp_pin_sense; + if (!spec->gen.autocfg.hp_outs && spec->gen.suppress_auto_mute) { + if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) + hp_pin = spec->gen.autocfg.line_out_pins[0]; + } + if (!hp_pin) return; @@ -3195,6 +3210,11 @@ static void alc256_shutup(struct hda_codec *codec) hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; bool hp_pin_sense; + if (!spec->gen.autocfg.hp_outs && spec->gen.suppress_auto_mute) { + if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) + hp_pin = spec->gen.autocfg.line_out_pins[0]; + } + if (!hp_pin) { alc269_shutup(codec); return; @@ -3231,6 +3251,11 @@ static void alc225_init(struct hda_codec *codec) hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; bool hp1_pin_sense, hp2_pin_sense; + if (!spec->gen.autocfg.hp_outs && spec->gen.suppress_auto_mute) { + if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) + hp_pin = spec->gen.autocfg.line_out_pins[0]; + } + if (!hp_pin) return; @@ -3274,6 +3299,11 @@ static void alc225_shutup(struct hda_codec *codec) hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; bool hp1_pin_sense, hp2_pin_sense; + if (!spec->gen.autocfg.hp_outs && spec->gen.suppress_auto_mute) { + if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) + hp_pin = spec->gen.autocfg.line_out_pins[0]; + } + if (!hp_pin) { alc269_shutup(codec); return; @@ -3318,6 +3348,11 @@ static void alc_default_init(struct hda_codec *codec) hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; bool hp_pin_sense; + if (!spec->gen.autocfg.hp_outs && spec->gen.suppress_auto_mute) { + if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) + hp_pin = spec->gen.autocfg.line_out_pins[0]; + } + if (!hp_pin) return; @@ -3347,6 +3382,11 @@ static void alc_default_shutup(struct hda_codec *codec) hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; bool hp_pin_sense; + if (!spec->gen.autocfg.hp_outs && spec->gen.suppress_auto_mute) { + if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) + hp_pin = spec->gen.autocfg.line_out_pins[0]; + } + if (!hp_pin) { alc269_shutup(codec); return; @@ -3379,6 +3419,11 @@ static void alc294_hp_init(struct hda_codec *codec) hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; int i, val; + if (!spec->gen.autocfg.hp_outs && spec->gen.suppress_auto_mute) { + if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) + hp_pin = spec->gen.autocfg.line_out_pins[0]; + } + if (!hp_pin) return; From 35a39f98567d8d3f1cea48f0f30de1a7e736b644 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 1 Feb 2019 11:19:50 +0100 Subject: [PATCH 333/525] ALSA: hda/realtek - Use a common helper for hp pin reference Replace the open-codes in many places with a new common helper for performing the same thing: referring to the primary headphone pin. This eventually fixes the potentially missing headphone pin on some weird devices, too. Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 96 +++++++++-------------------------- 1 file changed, 24 insertions(+), 72 deletions(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 5b1a71fb909c..6df758adff84 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -515,6 +515,15 @@ static void alc_auto_init_amp(struct hda_codec *codec, int type) } } +/* get a primary headphone pin if available */ +static hda_nid_t alc_get_hp_pin(struct alc_spec *spec) +{ + if (spec->gen.autocfg.hp_pins[0]) + return spec->gen.autocfg.hp_pins[0]; + if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) + return spec->gen.autocfg.line_out_pins[0]; + return 0; +} /* * Realtek SSID verification @@ -725,9 +734,7 @@ do_sku: * 15 : 1 --> enable the function "Mute internal speaker * when the external headphone out jack is plugged" */ - if (!spec->gen.autocfg.hp_pins[0] && - !(spec->gen.autocfg.line_out_pins[0] && - spec->gen.autocfg.line_out_type == AUTO_PIN_HP_OUT)) { + if (!alc_get_hp_pin(spec)) { hda_nid_t nid; tmp = (ass >> 11) & 0x3; /* HP to chassis */ nid = ports[tmp]; @@ -2959,15 +2966,10 @@ static void alc282_restore_default_value(struct hda_codec *codec) static void alc282_init(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp_pin_sense; int coef78; - if (!spec->gen.autocfg.hp_outs && spec->gen.suppress_auto_mute) { - if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) - hp_pin = spec->gen.autocfg.line_out_pins[0]; - } - alc282_restore_default_value(codec); if (!hp_pin) @@ -3001,15 +3003,10 @@ static void alc282_init(struct hda_codec *codec) static void alc282_shutup(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp_pin_sense; int coef78; - if (!spec->gen.autocfg.hp_outs && spec->gen.suppress_auto_mute) { - if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) - hp_pin = spec->gen.autocfg.line_out_pins[0]; - } - if (!hp_pin) { alc269_shutup(codec); return; @@ -3084,14 +3081,9 @@ static void alc283_restore_default_value(struct hda_codec *codec) static void alc283_init(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp_pin_sense; - if (!spec->gen.autocfg.hp_outs) { - if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) - hp_pin = spec->gen.autocfg.line_out_pins[0]; - } - alc283_restore_default_value(codec); if (!hp_pin) @@ -3125,14 +3117,9 @@ static void alc283_init(struct hda_codec *codec) static void alc283_shutup(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp_pin_sense; - if (!spec->gen.autocfg.hp_outs) { - if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) - hp_pin = spec->gen.autocfg.line_out_pins[0]; - } - if (!hp_pin) { alc269_shutup(codec); return; @@ -3166,14 +3153,9 @@ static void alc283_shutup(struct hda_codec *codec) static void alc256_init(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp_pin_sense; - if (!spec->gen.autocfg.hp_outs && spec->gen.suppress_auto_mute) { - if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) - hp_pin = spec->gen.autocfg.line_out_pins[0]; - } - if (!hp_pin) return; @@ -3207,14 +3189,9 @@ static void alc256_init(struct hda_codec *codec) static void alc256_shutup(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp_pin_sense; - if (!spec->gen.autocfg.hp_outs && spec->gen.suppress_auto_mute) { - if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) - hp_pin = spec->gen.autocfg.line_out_pins[0]; - } - if (!hp_pin) { alc269_shutup(codec); return; @@ -3248,14 +3225,9 @@ static void alc256_shutup(struct hda_codec *codec) static void alc225_init(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp1_pin_sense, hp2_pin_sense; - if (!spec->gen.autocfg.hp_outs && spec->gen.suppress_auto_mute) { - if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) - hp_pin = spec->gen.autocfg.line_out_pins[0]; - } - if (!hp_pin) return; @@ -3296,14 +3268,9 @@ static void alc225_init(struct hda_codec *codec) static void alc225_shutup(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp1_pin_sense, hp2_pin_sense; - if (!spec->gen.autocfg.hp_outs && spec->gen.suppress_auto_mute) { - if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) - hp_pin = spec->gen.autocfg.line_out_pins[0]; - } - if (!hp_pin) { alc269_shutup(codec); return; @@ -3345,14 +3312,9 @@ static void alc225_shutup(struct hda_codec *codec) static void alc_default_init(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp_pin_sense; - if (!spec->gen.autocfg.hp_outs && spec->gen.suppress_auto_mute) { - if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) - hp_pin = spec->gen.autocfg.line_out_pins[0]; - } - if (!hp_pin) return; @@ -3379,14 +3341,9 @@ static void alc_default_init(struct hda_codec *codec) static void alc_default_shutup(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp_pin_sense; - if (!spec->gen.autocfg.hp_outs && spec->gen.suppress_auto_mute) { - if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) - hp_pin = spec->gen.autocfg.line_out_pins[0]; - } - if (!hp_pin) { alc269_shutup(codec); return; @@ -3416,14 +3373,9 @@ static void alc_default_shutup(struct hda_codec *codec) static void alc294_hp_init(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); int i, val; - if (!spec->gen.autocfg.hp_outs && spec->gen.suppress_auto_mute) { - if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) - hp_pin = spec->gen.autocfg.line_out_pins[0]; - } - if (!hp_pin) return; @@ -4825,7 +4777,7 @@ static void alc_update_headset_mode(struct hda_codec *codec) struct alc_spec *spec = codec->spec; hda_nid_t mux_pin = spec->gen.imux_pins[spec->gen.cur_mux[0]]; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); int new_headset_mode; @@ -5104,7 +5056,7 @@ static void alc_fixup_tpt470_dock(struct hda_codec *codec, static void alc_shutup_dell_xps13(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - int hp_pin = spec->gen.autocfg.hp_pins[0]; + int hp_pin = alc_get_hp_pin(spec); /* Prevent pop noises when headphones are plugged in */ snd_hda_codec_write(codec, hp_pin, 0, @@ -5197,7 +5149,7 @@ static void alc271_hp_gate_mic_jack(struct hda_codec *codec, if (action == HDA_FIXUP_ACT_PROBE) { int mic_pin = find_ext_mic_pin(codec); - int hp_pin = spec->gen.autocfg.hp_pins[0]; + int hp_pin = alc_get_hp_pin(spec); if (snd_BUG_ON(!mic_pin || !hp_pin)) return; From 305a0ade180981686eec1f92aa6252a7c6ebb1cf Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 30 Jan 2019 17:46:03 +0100 Subject: [PATCH 334/525] ALSA: hda - Serialize codec registrations In the current code, the codec registration may happen both at the codec bind time and the end of the controller probe time. In a rare occasion, they race with each other, leading to Oops due to the still uninitialized card device. This patch introduces a simple flag to prevent the codec registration at the codec bind time as long as the controller probe is going on. The controller probe invokes snd_card_register() that does the whole registration task, and we don't need to register each piece beforehand. Cc: Signed-off-by: Takashi Iwai --- include/sound/hda_codec.h | 1 + sound/pci/hda/hda_bind.c | 3 ++- sound/pci/hda/hda_intel.c | 2 ++ 3 files changed, 5 insertions(+), 1 deletion(-) diff --git a/include/sound/hda_codec.h b/include/sound/hda_codec.h index 7fa48b100936..cc7c8d42d4fd 100644 --- a/include/sound/hda_codec.h +++ b/include/sound/hda_codec.h @@ -68,6 +68,7 @@ struct hda_bus { unsigned int response_reset:1; /* controller was reset */ unsigned int in_reset:1; /* during reset operation */ unsigned int no_response_fallback:1; /* don't fallback at RIRB error */ + unsigned int bus_probing :1; /* during probing process */ int primary_dig_out_type; /* primary digital out PCM type */ unsigned int mixer_assigned; /* codec addr for mixer name */ diff --git a/sound/pci/hda/hda_bind.c b/sound/pci/hda/hda_bind.c index 9174f1b3a987..1ec706ced75c 100644 --- a/sound/pci/hda/hda_bind.c +++ b/sound/pci/hda/hda_bind.c @@ -115,7 +115,8 @@ static int hda_codec_driver_probe(struct device *dev) err = snd_hda_codec_build_controls(codec); if (err < 0) goto error_module; - if (codec->card->registered) { + /* only register after the bus probe finished; otherwise it's racy */ + if (!codec->bus->bus_probing && codec->card->registered) { err = snd_card_register(codec->card); if (err < 0) goto error_module; diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index e784130ea4e0..e5c49003e75f 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2185,6 +2185,7 @@ static int azx_probe_continue(struct azx *chip) int dev = chip->dev_index; int err; + to_hda_bus(bus)->bus_probing = 1; hda->probe_continued = 1; /* bind with i915 if needed */ @@ -2269,6 +2270,7 @@ out_free: if (err < 0) hda->init_failed = 1; complete_all(&hda->probe_wait); + to_hda_bus(bus)->bus_probing = 0; return err; } From a1a02062ad466052a34a8c4323143ccf9726eb52 Mon Sep 17 00:00:00 2001 From: Petr Vorel Date: Mon, 12 Nov 2018 11:59:12 +0100 Subject: [PATCH 335/525] apparmor: Fix warning about unused function apparmor_ipv6_postroute MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit when compiled without CONFIG_IPV6: security/apparmor/lsm.c:1601:21: warning: ‘apparmor_ipv6_postroute’ defined but not used [-Wunused-function] static unsigned int apparmor_ipv6_postroute(void *priv, ^~~~~~~~~~~~~~~~~~~~~~~ Reported-by: Jordan Glover Tested-by: Jordan Glover Signed-off-by: Petr Vorel Signed-off-by: John Johansen --- security/apparmor/lsm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 2c010874329f..8db1731d046a 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -1599,12 +1599,14 @@ static unsigned int apparmor_ipv4_postroute(void *priv, return apparmor_ip_postroute(priv, skb, state); } +#if IS_ENABLED(CONFIG_IPV6) static unsigned int apparmor_ipv6_postroute(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return apparmor_ip_postroute(priv, skb, state); } +#endif static const struct nf_hook_ops apparmor_nf_ops[] = { { From b14e945bda8ae227d1bf2b1837c0c4a61721cd1a Mon Sep 17 00:00:00 2001 From: Paul Kocialkowski Date: Thu, 31 Jan 2019 14:25:50 +0100 Subject: [PATCH 336/525] drm/sun4i: tcon: Prepare and enable TCON channel 0 clock at init When initializing clocks, a reference to the TCON channel 0 clock is obtained. However, the clock is never prepared and enabled later. Switching from simplefb to DRM actually disables the clock (that was usually configured by U-Boot) because of that. On the V3s, this results in a hang when writing to some mixer registers when switching over to DRM from simplefb. Fix this by preparing and enabling the clock when initializing other clocks. Waiting for sun4i_tcon_channel_enable to enable the clock is apparently too late and results in the same mixer register access hang. Signed-off-by: Paul Kocialkowski Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20190131132550.26355-1-paul.kocialkowski@bootlin.com --- drivers/gpu/drm/sun4i/sun4i_tcon.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c index 0420f5c978b9..cf45d0f940f9 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.c +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c @@ -761,6 +761,7 @@ static int sun4i_tcon_init_clocks(struct device *dev, return PTR_ERR(tcon->sclk0); } } + clk_prepare_enable(tcon->sclk0); if (tcon->quirks->has_channel_1) { tcon->sclk1 = devm_clk_get(dev, "tcon-ch1"); @@ -775,6 +776,7 @@ static int sun4i_tcon_init_clocks(struct device *dev, static void sun4i_tcon_free_clocks(struct sun4i_tcon *tcon) { + clk_disable_unprepare(tcon->sclk0); clk_disable_unprepare(tcon->clk); } From 132fdc379eb143932d209a20fd581e1ce7630960 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Thu, 24 Jan 2019 17:28:37 +0000 Subject: [PATCH 337/525] arm64: Do not issue IPIs for user executable ptes Commit 3b8c9f1cdfc5 ("arm64: IPI each CPU after invalidating the I-cache for kernel mappings") was aimed at fixing the I-cache invalidation for kernel mappings. However, it inadvertently caused all cache maintenance for user mappings via set_pte_at() -> __sync_icache_dcache() -> sync_icache_aliases() to call kick_all_cpus_sync(). Reported-by: Shijith Thotton Tested-by: Shijith Thotton Reported-by: Wandun Chen Fixes: 3b8c9f1cdfc5 ("arm64: IPI each CPU after invalidating the I-cache for kernel mappings") Cc: # 4.19.x- Signed-off-by: Catalin Marinas Signed-off-by: Will Deacon --- arch/arm64/mm/flush.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c index 30695a868107..5c9073bace83 100644 --- a/arch/arm64/mm/flush.c +++ b/arch/arm64/mm/flush.c @@ -33,7 +33,11 @@ void sync_icache_aliases(void *kaddr, unsigned long len) __clean_dcache_area_pou(kaddr, len); __flush_icache_all(); } else { - flush_icache_range(addr, addr + len); + /* + * Don't issue kick_all_cpus_sync() after I-cache invalidation + * for user mappings. + */ + __flush_icache_range(addr, addr + len); } } From 8ea235932314311f15ea6cf65c1393ed7e31af70 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Sun, 27 Jan 2019 09:29:42 +0100 Subject: [PATCH 338/525] arm64: kaslr: ensure randomized quantities are clean also when kaslr is off Commit 1598ecda7b23 ("arm64: kaslr: ensure randomized quantities are clean to the PoC") added cache maintenance to ensure that global variables set by the kaslr init routine are not wiped clean due to cache invalidation occurring during the second round of page table creation. However, if kaslr_early_init() exits early with no randomization being applied (either due to the lack of a seed, or because the user has disabled kaslr explicitly), no cache maintenance is performed, leading to the same issue we attempted to fix earlier, as far as the module_alloc_base variable is concerned. Note that module_alloc_base cannot be initialized statically, because that would cause it to be subject to a R_AARCH64_RELATIVE relocation, causing it to be overwritten by the second round of KASLR relocation processing. Fixes: f80fb3a3d508 ("arm64: add support for kernel ASLR") Cc: # v4.6+ Signed-off-by: Ard Biesheuvel Signed-off-by: Will Deacon --- arch/arm64/kernel/kaslr.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index ba6b41790fcd..b09b6f75f759 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -88,6 +88,7 @@ u64 __init kaslr_early_init(u64 dt_phys) * we end up running with module randomization disabled. */ module_alloc_base = (u64)_etext - MODULES_VSIZE; + __flush_dcache_area(&module_alloc_base, sizeof(module_alloc_base)); /* * Try to map the FDT early. If this fails, we simply bail, From f2b3d8566d81deaca31f4e3163def0bea7746e11 Mon Sep 17 00:00:00 2001 From: James Morse Date: Thu, 24 Jan 2019 16:32:55 +0000 Subject: [PATCH 339/525] arm64: kprobe: Always blacklist the KVM world-switch code On systems with VHE the kernel and KVM's world-switch code run at the same exception level. Code that is only used on a VHE system does not need to be annotated as __hyp_text as it can reside anywhere in the kernel text. __hyp_text was also used to prevent kprobes from patching breakpoint instructions into this region, as this code runs at a different exception level. While this is no longer true with VHE, KVM still switches VBAR_EL1, meaning a kprobe's breakpoint executed in the world-switch code will cause a hyp-panic. Move the __hyp_text check in the kprobes blacklist so it applies on VHE systems too, to cover the common code and guest enter/exit assembly. Fixes: 888b3c8720e0 ("arm64: Treat all entry code as non-kprobe-able") Reviewed-by: Christoffer Dall Signed-off-by: James Morse Acked-by: Masami Hiramatsu Signed-off-by: Will Deacon --- arch/arm64/kernel/probes/kprobes.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index 2a5b338b2542..f17afb99890c 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -478,13 +478,13 @@ bool arch_within_kprobe_blacklist(unsigned long addr) addr < (unsigned long)__entry_text_end) || (addr >= (unsigned long)__idmap_text_start && addr < (unsigned long)__idmap_text_end) || + (addr >= (unsigned long)__hyp_text_start && + addr < (unsigned long)__hyp_text_end) || !!search_exception_tables(addr)) return true; if (!is_kernel_in_hyp_mode()) { - if ((addr >= (unsigned long)__hyp_text_start && - addr < (unsigned long)__hyp_text_end) || - (addr >= (unsigned long)__hyp_idmap_text_start && + if ((addr >= (unsigned long)__hyp_idmap_text_start && addr < (unsigned long)__hyp_idmap_text_end)) return true; } From 8fac5cbdfe0f01254d9d265c6aa1a95f94f58595 Mon Sep 17 00:00:00 2001 From: James Morse Date: Thu, 24 Jan 2019 16:32:56 +0000 Subject: [PATCH 340/525] arm64: hyp-stub: Forbid kprobing of the hyp-stub The hyp-stub is loaded by the kernel's early startup code at EL2 during boot, before KVM takes ownership later. The hyp-stub's text is part of the regular kernel text, meaning it can be kprobed. A breakpoint in the hyp-stub causes the CPU to spin in el2_sync_invalid. Add it to the __hyp_text. Signed-off-by: James Morse Cc: stable@vger.kernel.org Signed-off-by: Will Deacon --- arch/arm64/kernel/hyp-stub.S | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S index e1261fbaa374..17f325ba831e 100644 --- a/arch/arm64/kernel/hyp-stub.S +++ b/arch/arm64/kernel/hyp-stub.S @@ -28,6 +28,8 @@ #include .text + .pushsection .hyp.text, "ax" + .align 11 ENTRY(__hyp_stub_vectors) From f7daa9c8fd191724b9ab9580a7be55cd1a67d799 Mon Sep 17 00:00:00 2001 From: James Morse Date: Thu, 24 Jan 2019 16:32:57 +0000 Subject: [PATCH 341/525] arm64: hibernate: Clean the __hyp_text to PoC after resume During resume hibernate restores all physical memory. Any memory that is accessed with the MMU disabled needs to be cleaned to the PoC. KVMs __hyp_text was previously ommitted as it runs with the MMU enabled, but now that the hyp-stub is located in this section, we must clean __hyp_text too. This ensures secondary CPUs that come online after hibernate has finished resuming, and load KVM via the freshly written hyp-stub see the correct instructions. Signed-off-by: James Morse Cc: stable@vger.kernel.org Signed-off-by: Will Deacon --- arch/arm64/kernel/hibernate.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index 29cdc99688f3..9859e1178e6b 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -299,8 +299,10 @@ int swsusp_arch_suspend(void) dcache_clean_range(__idmap_text_start, __idmap_text_end); /* Clean kvm setup code to PoC? */ - if (el2_reset_needed()) + if (el2_reset_needed()) { dcache_clean_range(__hyp_idmap_text_start, __hyp_idmap_text_end); + dcache_clean_range(__hyp_text_start, __hyp_text_end); + } /* make the crash dump kernel image protected again */ crash_post_resume(); From 5b9633af298bfd1de650f6774d3fada546543101 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 31 Jan 2019 01:25:02 +0100 Subject: [PATCH 342/525] binderfs: remove separate device_initcall() binderfs should not have a separate device_initcall(). When a kernel is compiled with CONFIG_ANDROID_BINDERFS register the filesystem alongside CONFIG_ANDROID_IPC. This use-case is especially sensible when users specify CONFIG_ANDROID_IPC=y, CONFIG_ANDROID_BINDERFS=y and ANDROID_BINDER_DEVICES="". When CONFIG_ANDROID_BINDERFS=n then this always succeeds so there's no regression potential for legacy workloads. Signed-off-by: Christian Brauner Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 7 ++++++- drivers/android/binder_internal.h | 9 +++++++++ drivers/android/binderfs.c | 4 +--- 3 files changed, 16 insertions(+), 4 deletions(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 57cf259de600..4d2b2ad1ee0e 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -5854,9 +5854,10 @@ static int __init init_binder_device(const char *name) static int __init binder_init(void) { int ret; - char *device_name, *device_names, *device_tmp; + char *device_name, *device_tmp; struct binder_device *device; struct hlist_node *tmp; + char *device_names = NULL; ret = binder_alloc_shrinker_init(); if (ret) @@ -5917,6 +5918,10 @@ static int __init binder_init(void) } } + ret = init_binderfs(); + if (ret) + goto err_init_binder_device_failed; + return ret; err_init_binder_device_failed: diff --git a/drivers/android/binder_internal.h b/drivers/android/binder_internal.h index 7fb97f503ef2..045b3e42d98b 100644 --- a/drivers/android/binder_internal.h +++ b/drivers/android/binder_internal.h @@ -46,4 +46,13 @@ static inline bool is_binderfs_device(const struct inode *inode) } #endif +#ifdef CONFIG_ANDROID_BINDERFS +extern int __init init_binderfs(void); +#else +static inline int __init init_binderfs(void) +{ + return 0; +} +#endif + #endif /* _LINUX_BINDER_INTERNAL_H */ diff --git a/drivers/android/binderfs.c b/drivers/android/binderfs.c index 7a550104a722..e773f45d19d9 100644 --- a/drivers/android/binderfs.c +++ b/drivers/android/binderfs.c @@ -550,7 +550,7 @@ static struct file_system_type binder_fs_type = { .fs_flags = FS_USERNS_MOUNT, }; -static int __init init_binderfs(void) +int __init init_binderfs(void) { int ret; @@ -568,5 +568,3 @@ static int __init init_binderfs(void) return ret; } - -device_initcall(init_binderfs); From 70ed7148dadb812f2f7c9927e98ef3cf4869dfa9 Mon Sep 17 00:00:00 2001 From: Vincent Whitchurch Date: Fri, 1 Feb 2019 10:03:12 +0100 Subject: [PATCH 343/525] mic: vop: Fix use-after-free on remove KASAN detects a use-after-free when vop devices are removed. This problem was introduced by commit 0063e8bbd2b62d136 ("virtio_vop: don't kfree device on register failure"). That patch moved the freeing of the struct _vop_vdev to the release function, but failed to ensure that vop holds a reference to the device when it doesn't want it to go away. A kfree() was replaced with a put_device() in the unregistration path, but the last reference to the device is already dropped in unregister_virtio_device() so the struct is freed before vop is done with it. Fix it by holding a reference until cleanup is done. This is similar to the fix in virtio_pci in commit 2989be09a8a9d6 ("virtio_pci: fix use after free on release"). ================================================================== BUG: KASAN: use-after-free in vop_scan_devices+0xc6c/0xe50 [vop] Read of size 8 at addr ffff88800da18580 by task kworker/0:1/12 CPU: 0 PID: 12 Comm: kworker/0:1 Not tainted 5.0.0-rc4+ #53 Workqueue: events vop_hotplug_devices [vop] Call Trace: dump_stack+0x74/0xbb print_address_description+0x5d/0x2b0 ? vop_scan_devices+0xc6c/0xe50 [vop] kasan_report+0x152/0x1aa ? vop_scan_devices+0xc6c/0xe50 [vop] ? vop_scan_devices+0xc6c/0xe50 [vop] vop_scan_devices+0xc6c/0xe50 [vop] ? vop_loopback_free_irq+0x160/0x160 [vop_loopback] process_one_work+0x7c0/0x14b0 ? pwq_dec_nr_in_flight+0x2d0/0x2d0 ? do_raw_spin_lock+0x120/0x280 worker_thread+0x8f/0xbf0 ? __kthread_parkme+0x78/0xf0 ? process_one_work+0x14b0/0x14b0 kthread+0x2ae/0x3a0 ? kthread_park+0x120/0x120 ret_from_fork+0x3a/0x50 Allocated by task 12: kmem_cache_alloc_trace+0x13a/0x2a0 vop_scan_devices+0x473/0xe50 [vop] process_one_work+0x7c0/0x14b0 worker_thread+0x8f/0xbf0 kthread+0x2ae/0x3a0 ret_from_fork+0x3a/0x50 Freed by task 12: kfree+0x104/0x310 device_release+0x73/0x1d0 kobject_put+0x14f/0x420 unregister_virtio_device+0x32/0x50 vop_scan_devices+0x19d/0xe50 [vop] process_one_work+0x7c0/0x14b0 worker_thread+0x8f/0xbf0 kthread+0x2ae/0x3a0 ret_from_fork+0x3a/0x50 The buggy address belongs to the object at ffff88800da18008 which belongs to the cache kmalloc-2k of size 2048 The buggy address is located 1400 bytes inside of 2048-byte region [ffff88800da18008, ffff88800da18808) The buggy address belongs to the page: page:ffffea0000368600 count:1 mapcount:0 mapping:ffff88801440dbc0 index:0x0 compound_mapcount: 0 flags: 0x4000000000010200(slab|head) raw: 4000000000010200 ffffea0000378608 ffffea000037a008 ffff88801440dbc0 raw: 0000000000000000 00000000000d000d 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88800da18480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88800da18500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff88800da18580: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff88800da18600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88800da18680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== Fixes: 0063e8bbd2b62d136 ("virtio_vop: don't kfree device on register failure") Signed-off-by: Vincent Whitchurch Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/misc/mic/vop/vop_main.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/misc/mic/vop/vop_main.c b/drivers/misc/mic/vop/vop_main.c index 2bd57c2ca02b..9ee3fff3446a 100644 --- a/drivers/misc/mic/vop/vop_main.c +++ b/drivers/misc/mic/vop/vop_main.c @@ -589,6 +589,8 @@ static int _vop_remove_device(struct mic_device_desc __iomem *d, int ret = -1; if (ioread8(&dc->config_change) == MIC_VIRTIO_PARAM_DEV_REMOVE) { + struct device *dev = get_device(&vdev->vdev.dev); + dev_dbg(&vpdev->dev, "%s %d config_change %d type %d vdev %p\n", __func__, __LINE__, @@ -600,7 +602,7 @@ static int _vop_remove_device(struct mic_device_desc __iomem *d, iowrite8(-1, &dc->h2c_vdev_db); if (status & VIRTIO_CONFIG_S_DRIVER_OK) wait_for_completion(&vdev->reset_done); - put_device(&vdev->vdev.dev); + put_device(dev); iowrite8(1, &dc->guest_ack); dev_dbg(&vpdev->dev, "%s %d guest_ack %d\n", __func__, __LINE__, ioread8(&dc->guest_ack)); From 4bf13fdbc3567e571c20b415e4df70f564d54067 Mon Sep 17 00:00:00 2001 From: Vincent Whitchurch Date: Fri, 1 Feb 2019 09:45:09 +0100 Subject: [PATCH 344/525] mic: vop: Fix crash on remove The remove path contains a hack which depends on internal structures in other source files, similar to the one which was recently removed from the registration path. Since commit 1ce9e6055fa0 ("virtio_ring: introduce packed ring support"), this leads to a crash when vop devices are removed. The structure in question is only examined to get the virtual address of the allocated used page. Store that pointer locally instead to fix the crash. Fixes: 1ce9e6055fa0 ("virtio_ring: introduce packed ring support") Signed-off-by: Vincent Whitchurch Signed-off-by: Greg Kroah-Hartman --- drivers/misc/mic/vop/vop_main.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/misc/mic/vop/vop_main.c b/drivers/misc/mic/vop/vop_main.c index 9ee3fff3446a..744757f541be 100644 --- a/drivers/misc/mic/vop/vop_main.c +++ b/drivers/misc/mic/vop/vop_main.c @@ -47,7 +47,8 @@ * @dc: Virtio device control * @vpdev: VOP device which is the parent for this virtio device * @vr: Buffer for accessing the VRING - * @used: Buffer for used + * @used_virt: Virtual address of used ring + * @used: DMA address of used ring * @used_size: Size of the used buffer * @reset_done: Track whether VOP reset is complete * @virtio_cookie: Cookie returned upon requesting a interrupt @@ -61,6 +62,7 @@ struct _vop_vdev { struct mic_device_ctrl __iomem *dc; struct vop_device *vpdev; void __iomem *vr[VOP_MAX_VRINGS]; + void *used_virt[VOP_MAX_VRINGS]; dma_addr_t used[VOP_MAX_VRINGS]; int used_size[VOP_MAX_VRINGS]; struct completion reset_done; @@ -260,12 +262,12 @@ static bool vop_notify(struct virtqueue *vq) static void vop_del_vq(struct virtqueue *vq, int n) { struct _vop_vdev *vdev = to_vopvdev(vq->vdev); - struct vring *vr = (struct vring *)(vq + 1); struct vop_device *vpdev = vdev->vpdev; dma_unmap_single(&vpdev->dev, vdev->used[n], vdev->used_size[n], DMA_BIDIRECTIONAL); - free_pages((unsigned long)vr->used, get_order(vdev->used_size[n])); + free_pages((unsigned long)vdev->used_virt[n], + get_order(vdev->used_size[n])); vring_del_virtqueue(vq); vpdev->hw_ops->iounmap(vpdev, vdev->vr[n]); vdev->vr[n] = NULL; @@ -355,6 +357,7 @@ static struct virtqueue *vop_find_vq(struct virtio_device *dev, le16_to_cpu(config.num)); used = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, get_order(vdev->used_size[index])); + vdev->used_virt[index] = used; if (!used) { err = -ENOMEM; dev_err(_vop_dev(vdev), "%s %d err %d\n", From d6d478aee003e19ef90321176552a8ad2929a47f Mon Sep 17 00:00:00 2001 From: John Johansen Date: Thu, 24 Jan 2019 13:53:05 -0800 Subject: [PATCH 345/525] apparmor: Fix aa_label_build() error handling for failed merges aa_label_merge() can return NULL for memory allocations failures make sure to handle and set the correct error in this case. Reported-by: Peng Hao Signed-off-by: John Johansen --- security/apparmor/domain.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c index 08c88de0ffda..11975ec8d566 100644 --- a/security/apparmor/domain.c +++ b/security/apparmor/domain.c @@ -1444,7 +1444,10 @@ check: new = aa_label_merge(label, target, GFP_KERNEL); if (IS_ERR_OR_NULL(new)) { info = "failed to build target label"; - error = PTR_ERR(new); + if (!new) + error = -ENOMEM; + else + error = PTR_ERR(new); new = NULL; perms.allow = 0; goto audit; From c228d294f2040c3a5f5965ff04d4947d0bf6e7da Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 31 Jan 2019 11:10:20 -0800 Subject: [PATCH 346/525] x86: explicitly align IO accesses in memcpy_{to,from}io In commit 170d13ca3a2f ("x86: re-introduce non-generic memcpy_{to,from}io") I made our copy from IO space use a separate copy routine rather than rely on the generic memcpy. I did that because our generic memory copy isn't actually well-defined when it comes to internal access ordering or alignment, and will in fact depend on various CPUID flags. In particular, the default memcpy() for a modern Intel CPU will generally be just a "rep movsb", which works reasonably well for medium-sized memory copies of regular RAM, since the CPU will turn it into fairly optimized microcode. However, for non-cached memory and IO, "rep movs" ends up being horrendously slow and will just do the architectural "one byte at a time" accesses implied by the movsb. At the other end of the spectrum, if you _don't_ end up using the "rep movsb" code, you'd likely fall back to the software copy, which does overlapping accesses for the tail, and may copy things backwards. Again, for regular memory that's fine, for IO memory not so much. The thinking was that clearly nobody really cared (because things worked), but some people had seen horrible performance due to the byte accesses, so let's just revert back to our long ago version that dod "rep movsl" for the bulk of the copy, and then fixed up the potentially last few bytes of the tail with "movsw/b". Interestingly (and perhaps not entirely surprisingly), while that was our original memory copy implementation, and had been used before for IO, in the meantime many new users of memcpy_*io() had come about. And while the access patterns for the memory copy weren't well-defined (so arguably _any_ access pattern should work), in practice the "rep movsb" case had been very common for the last several years. In particular Jarkko Sakkinen reported that the memcpy_*io() change resuled in weird errors from his Geminilake NUC TPM module. And it turns out that the TPM TCG accesses according to spec require that the accesses be (a) done strictly sequentially (b) be naturally aligned otherwise the TPM chip will abort the PCI transaction. And, in fact, the tpm_crb.c driver did this: memcpy_fromio(buf, priv->rsp, 6); ... memcpy_fromio(&buf[6], &priv->rsp[6], expected - 6); which really should never have worked in the first place, but back before commit 170d13ca3a2f it *happened* to work, because the memcpy_fromio() would be expanded to a regular memcpy, and (a) gcc would expand the first memcpy in-line, and turn it into a 4-byte and a 2-byte read, and they happened to be in the right order, and the alignment was right. (b) gcc would call "memcpy()" for the second one, and the machines that had this TPM chip also apparently ended up always having ERMS ("Enhanced REP MOVSB/STOSB instructions"), so we'd use the "rep movbs" for that copy. In other words, basically by pure luck, the code happened to use the right access sizes in the (two different!) memcpy() implementations to make it all work. But after commit 170d13ca3a2f, both of the memcpy_fromio() calls resulted in a call to the routine with the consistent memory accesses, and in both cases it started out transferring with 4-byte accesses. Which worked for the first copy, but resulted in the second copy doing a 32-bit read at an address that was only 2-byte aligned. Jarkko is actually fixing the fragile code in the TPM driver, but since this is an excellent example of why we absolutely must not use a generic memcpy for IO accesses, _and_ an IO-specific one really should strive to align the IO accesses, let's do exactly that. Side note: Jarkko also noted that the driver had been used on ARM platforms, and had worked. That was because on 32-bit ARM, memcpy_*io() ends up always doing byte accesses, and on 64-bit ARM it first does byte accesses to align to 8-byte boundaries, and then does 8-byte accesses for the bulk. So ARM actually worked by design, and the x86 case worked by pure luck. We *might* want to make x86-64 do the 8-byte case too. That should be a pretty straightforward extension, but let's do one thing at a time. And generally MMIO accesses aren't really all that performance-critical, as shown by the fact that for a long time we just did them a byte at a time, and very few people ever noticed. Reported-and-tested-by: Jarkko Sakkinen Tested-by: Jerry Snitselaar Cc: David Laight Fixes: 170d13ca3a2f ("x86: re-introduce non-generic memcpy_{to,from}io") Signed-off-by: Linus Torvalds --- arch/x86/lib/iomem.c | 33 ++++++++++++++++++++++++++++++--- 1 file changed, 30 insertions(+), 3 deletions(-) diff --git a/arch/x86/lib/iomem.c b/arch/x86/lib/iomem.c index 66894675f3c8..df50451d94ef 100644 --- a/arch/x86/lib/iomem.c +++ b/arch/x86/lib/iomem.c @@ -2,8 +2,11 @@ #include #include +#define movs(type,to,from) \ + asm volatile("movs" type:"=&D" (to), "=&S" (from):"0" (to), "1" (from):"memory") + /* Originally from i386/string.h */ -static __always_inline void __iomem_memcpy(void *to, const void *from, size_t n) +static __always_inline void rep_movs(void *to, const void *from, size_t n) { unsigned long d0, d1, d2; asm volatile("rep ; movsl\n\t" @@ -21,13 +24,37 @@ static __always_inline void __iomem_memcpy(void *to, const void *from, size_t n) void memcpy_fromio(void *to, const volatile void __iomem *from, size_t n) { - __iomem_memcpy(to, (const void *)from, n); + if (unlikely(!n)) + return; + + /* Align any unaligned source IO */ + if (unlikely(1 & (unsigned long)from)) { + movs("b", to, from); + n--; + } + if (n > 1 && unlikely(2 & (unsigned long)from)) { + movs("w", to, from); + n-=2; + } + rep_movs(to, (const void *)from, n); } EXPORT_SYMBOL(memcpy_fromio); void memcpy_toio(volatile void __iomem *to, const void *from, size_t n) { - __iomem_memcpy((void *)to, (const void *) from, n); + if (unlikely(!n)) + return; + + /* Align any unaligned destination IO */ + if (unlikely(1 & (unsigned long)to)) { + movs("b", to, from); + n--; + } + if (n > 1 && unlikely(2 & (unsigned long)to)) { + movs("w", to, from); + n-=2; + } + rep_movs((void *)to, (const void *) from, n); } EXPORT_SYMBOL(memcpy_toio); From 2aa958c99c7fd3162b089a1a56a34a0cdb778de1 Mon Sep 17 00:00:00 2001 From: Kairui Song Date: Fri, 18 Jan 2019 19:13:08 +0800 Subject: [PATCH 347/525] x86/kexec: Don't setup EFI info if EFI runtime is not enabled Kexec-ing a kernel with "efi=noruntime" on the first kernel's command line causes the following null pointer dereference: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] Call Trace: efi_runtime_map_copy+0x28/0x30 bzImage64_load+0x688/0x872 arch_kexec_kernel_image_load+0x6d/0x70 kimage_file_alloc_init+0x13e/0x220 __x64_sys_kexec_file_load+0x144/0x290 do_syscall_64+0x55/0x1a0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Just skip the EFI info setup if EFI runtime services are not enabled. [ bp: Massage commit message. ] Suggested-by: Dave Young Signed-off-by: Kairui Song Signed-off-by: Borislav Petkov Acked-by: Dave Young Cc: AKASHI Takahiro Cc: Andrew Morton Cc: Ard Biesheuvel Cc: bhe@redhat.com Cc: David Howells Cc: erik.schmauss@intel.com Cc: fanc.fnst@cn.fujitsu.com Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: kexec@lists.infradead.org Cc: lenb@kernel.org Cc: linux-acpi@vger.kernel.org Cc: Philipp Rudo Cc: rafael.j.wysocki@intel.com Cc: robert.moore@intel.com Cc: Thomas Gleixner Cc: x86-ml Cc: Yannik Sembritzki Link: https://lkml.kernel.org/r/20190118111310.29589-2-kasong@redhat.com --- arch/x86/kernel/kexec-bzimage64.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 0d5efa34f359..53917a3ebf94 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -167,6 +167,9 @@ setup_efi_state(struct boot_params *params, unsigned long params_load_addr, struct efi_info *current_ei = &boot_params.efi_info; struct efi_info *ei = ¶ms->efi_info; + if (!efi_enabled(EFI_RUNTIME_SERVICES)) + return 0; + if (!current_ei->efi_memmap_size) return 0; From 294c149a209c6196c2de85f512b52ef50f519949 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 1 Feb 2019 11:28:16 +0300 Subject: [PATCH 348/525] skge: potential memory corruption in skge_get_regs() The "p" buffer is 0x4000 bytes long. B3_RI_WTO_R1 is 0x190. The value of "regs->len" is in the 1-0x4000 range. The bug here is that "regs->len - B3_RI_WTO_R1" can be a negative value which would lead to memory corruption and an abrupt crash. Fixes: c3f8be961808 ("[PATCH] skge: expand ethtool debug register dump") Signed-off-by: Dan Carpenter Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/skge.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c index 04fd1f135011..654ac534b10e 100644 --- a/drivers/net/ethernet/marvell/skge.c +++ b/drivers/net/ethernet/marvell/skge.c @@ -152,8 +152,10 @@ static void skge_get_regs(struct net_device *dev, struct ethtool_regs *regs, memset(p, 0, regs->len); memcpy_fromio(p, io, B3_RAM_ADDR); - memcpy_fromio(p + B3_RI_WTO_R1, io + B3_RI_WTO_R1, - regs->len - B3_RI_WTO_R1); + if (regs->len > B3_RI_WTO_R1) { + memcpy_fromio(p + B3_RI_WTO_R1, io + B3_RI_WTO_R1, + regs->len - B3_RI_WTO_R1); + } } /* Wake on Lan only supported on Yukon chips with rev 1 or above */ From ba59fb0273076637f0add4311faa990a5eec27c0 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 1 Feb 2019 15:15:22 +0100 Subject: [PATCH 349/525] sctp: walk the list of asoc safely In sctp_sendmesg(), when walking the list of endpoint associations, the association can be dropped from the list, making the list corrupt. Properly handle this by using list_for_each_entry_safe() Fixes: 4910280503f3 ("sctp: add support for snd flag SCTP_SENDALL process in sendmsg") Reported-by: Secunia Research Tested-by: Secunia Research Signed-off-by: Greg Kroah-Hartman Acked-by: Marcelo Ricardo Leitner Acked-by: Neil Horman Signed-off-by: David S. Miller --- net/sctp/socket.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index f93c3cf9e567..65d6d04546ae 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2027,7 +2027,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_transport *transport = NULL; struct sctp_sndrcvinfo _sinfo, *sinfo; - struct sctp_association *asoc; + struct sctp_association *asoc, *tmp; struct sctp_cmsgs cmsgs; union sctp_addr *daddr; bool new = false; @@ -2053,7 +2053,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) /* SCTP_SENDALL process */ if ((sflags & SCTP_SENDALL) && sctp_style(sk, UDP)) { - list_for_each_entry(asoc, &ep->asocs, asocs) { + list_for_each_entry_safe(asoc, tmp, &ep->asocs, asocs) { err = sctp_sendmsg_check_sflags(asoc, sflags, msg, msg_len); if (err == 0) From 7596175e99b3d4bce28022193efd954c201a782a Mon Sep 17 00:00:00 2001 From: Govindarajulu Varadarajan Date: Wed, 30 Jan 2019 06:59:00 -0800 Subject: [PATCH 350/525] enic: fix checksum validation for IPv6 In case of IPv6 pkts, ipv4_csum_ok is 0. Because of this, driver does not set skb->ip_summed. So IPv6 rx checksum is not offloaded. Signed-off-by: Govindarajulu Varadarajan Signed-off-by: David S. Miller --- drivers/net/ethernet/cisco/enic/enic_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index 60641e202534..9a7f70db20c7 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -1434,7 +1434,8 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq, * csum is correct or is zero. */ if ((netdev->features & NETIF_F_RXCSUM) && !csum_not_calc && - tcp_udp_csum_ok && ipv4_csum_ok && outer_csum_ok) { + tcp_udp_csum_ok && outer_csum_ok && + (ipv4_csum_ok || ipv6)) { skb->ip_summed = CHECKSUM_UNNECESSARY; skb->csum_level = encap; } From 14d22d4d61e40623a7c5816728bfe55c322e779a Mon Sep 17 00:00:00 2001 From: Ursula Braun Date: Wed, 30 Jan 2019 18:51:00 +0100 Subject: [PATCH 351/525] net/smc: fix another sizeof to int comparison Comparing an int to a size, which is unsigned, causes the int to become unsigned, giving the wrong result. kernel_sendmsg can return a negative error code. Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/smc_clc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 776e9dfc915d..d53fd588d1f5 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -378,7 +378,7 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info) vec.iov_len = sizeof(struct smc_clc_msg_decline); len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1, sizeof(struct smc_clc_msg_decline)); - if (len < sizeof(struct smc_clc_msg_decline)) + if (len < 0 || len < sizeof(struct smc_clc_msg_decline)) len = -EPROTO; return len > 0 ? 0 : len; } From ca8dc1334a71d6081b09e18d55198a27e28fd44b Mon Sep 17 00:00:00 2001 From: Hans Wippel Date: Wed, 30 Jan 2019 18:51:01 +0100 Subject: [PATCH 352/525] net/smc: allow 16 byte pnetids in netlink policy Currently, users can only send pnetids with a maximum length of 15 bytes over the SMC netlink interface although the maximum pnetid length is 16 bytes. This patch changes the SMC netlink policy to accept 16 byte pnetids. Signed-off-by: Hans Wippel Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/smc_pnet.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 7cb3e4f07c10..632c3109dee5 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -27,7 +27,7 @@ static struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = { [SMC_PNETID_NAME] = { .type = NLA_NUL_STRING, - .len = SMC_MAX_PNETID_LEN - 1 + .len = SMC_MAX_PNETID_LEN }, [SMC_PNETID_ETHNAME] = { .type = NLA_NUL_STRING, From 77f838ace755d2f466536c44dac6c856f62cd901 Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Wed, 30 Jan 2019 18:51:02 +0100 Subject: [PATCH 353/525] net/smc: prevent races between smc_lgr_terminate() and smc_conn_free() To prevent races between smc_lgr_terminate() and smc_conn_free() add an extra check of the lgr field before accessing it, and cancel a delayed free_work when a new smc connection is created. This fixes the problem that free_work cleared the lgr variable but smc_lgr_terminate() or smc_conn_free() still access it in parallel. Signed-off-by: Karsten Graul Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/smc_core.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 35c1cdc93e1c..097c798983ca 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -128,6 +128,8 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn) { struct smc_link_group *lgr = conn->lgr; + if (!lgr) + return; write_lock_bh(&lgr->conns_lock); if (conn->alert_token_local) { __smc_lgr_unregister_conn(conn); @@ -628,6 +630,8 @@ int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact, local_contact = SMC_REUSE_CONTACT; conn->lgr = lgr; smc_lgr_register_conn(conn); /* add smc conn to lgr */ + if (delayed_work_pending(&lgr->free_work)) + cancel_delayed_work(&lgr->free_work); write_unlock_bh(&lgr->conns_lock); break; } From 6889b36da78a21a312d8b462c1fa25a03c2ff192 Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Wed, 30 Jan 2019 18:51:03 +0100 Subject: [PATCH 354/525] net/smc: don't wait for send buffer space when data was already sent When there is no more send buffer space and at least 1 byte was already sent then return to user space. The wait is only done when no data was sent by the sendmsg() call. This fixes smc_tx_sendmsg() which tried to always send all user data and started to wait for free send buffer space when needed. During this wait the user space program was blocked in the sendmsg() call and hence not able to receive incoming data. When both sides were in such a situation then the connection stalled forever. Signed-off-by: Karsten Graul Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/smc_tx.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index d8366ed51757..f99951f3f7fd 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -165,12 +165,11 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len) conn->local_tx_ctrl.prod_flags.urg_data_pending = 1; if (!atomic_read(&conn->sndbuf_space) || conn->urg_tx_pend) { + if (send_done) + return send_done; rc = smc_tx_wait(smc, msg->msg_flags); - if (rc) { - if (send_done) - return send_done; + if (rc) goto out_err; - } continue; } From 51c5aba3b672c4285fca052817f34b22dc79dda7 Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Wed, 30 Jan 2019 18:51:04 +0100 Subject: [PATCH 355/525] net/smc: recvmsg and splice_read should return 0 after shutdown When a socket was connected and is now shut down for read, return 0 to indicate end of data in recvmsg and splice_read (like TCP) and do not return ENOTCONN. This behavior is required by the socket api. Signed-off-by: Karsten Graul Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/af_smc.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index c4e56602e0c6..b04a813fc865 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1505,6 +1505,11 @@ static int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, smc = smc_sk(sk); lock_sock(sk); + if (sk->sk_state == SMC_CLOSED && (sk->sk_shutdown & RCV_SHUTDOWN)) { + /* socket was connected before, no more data to read */ + rc = 0; + goto out; + } if ((sk->sk_state == SMC_INIT) || (sk->sk_state == SMC_LISTEN) || (sk->sk_state == SMC_CLOSED)) @@ -1840,7 +1845,11 @@ static ssize_t smc_splice_read(struct socket *sock, loff_t *ppos, smc = smc_sk(sk); lock_sock(sk); - + if (sk->sk_state == SMC_CLOSED && (sk->sk_shutdown & RCV_SHUTDOWN)) { + /* socket was connected before, no more data to read */ + rc = 0; + goto out; + } if (sk->sk_state == SMC_INIT || sk->sk_state == SMC_LISTEN || sk->sk_state == SMC_CLOSED) From 33f3fcc290671590821ff3c0c9396db1ec9b7d4c Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Wed, 30 Jan 2019 18:51:05 +0100 Subject: [PATCH 356/525] net/smc: do not wait under send_lock smc_cdc_get_free_slot() might wait for free transfer buffers when using SMC-R. This wait should not be done under the send_lock, which is a spin_lock. This fixes a cpu loop in parallel threads waiting for the send_lock. Signed-off-by: Karsten Graul Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/smc_tx.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index f99951f3f7fd..36af3de731b9 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -488,25 +488,23 @@ static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn) struct smc_wr_buf *wr_buf; int rc; - spin_lock_bh(&conn->send_lock); rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend); if (rc < 0) { if (rc == -EBUSY) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); - if (smc->sk.sk_err == ECONNABORTED) { - rc = sock_error(&smc->sk); - goto out_unlock; - } + if (smc->sk.sk_err == ECONNABORTED) + return sock_error(&smc->sk); rc = 0; if (conn->alert_token_local) /* connection healthy */ mod_delayed_work(system_wq, &conn->tx_work, SMC_TX_WORK_DELAY); } - goto out_unlock; + return rc; } + spin_lock_bh(&conn->send_lock); if (!conn->local_tx_ctrl.prod_flags.urg_data_present) { rc = smc_tx_rdma_writes(conn); if (rc) { From 2dee25af42f99b476d5916aeac5c994e4dcc910b Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Wed, 30 Jan 2019 18:51:06 +0100 Subject: [PATCH 357/525] net/smc: call smc_cdc_msg_send() under send_lock Call smc_cdc_msg_send() under the connection send_lock to make sure all send operations for one connection are serialized. Signed-off-by: Karsten Graul Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/smc_cdc.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index db83332ac1c8..1c5333d494e9 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -125,7 +125,10 @@ static int smcr_cdc_get_slot_and_msg_send(struct smc_connection *conn) if (rc) return rc; - return smc_cdc_msg_send(conn, wr_buf, pend); + spin_lock_bh(&conn->send_lock); + rc = smc_cdc_msg_send(conn, wr_buf, pend); + spin_unlock_bh(&conn->send_lock); + return rc; } int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn) From e5f3aa04dbfd92154f21edfeb7a1676a45918928 Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Wed, 30 Jan 2019 18:51:07 +0100 Subject: [PATCH 358/525] net/smc: use device link provided in qp_context The device field of the IB event structure does not always point to the SMC IB device. Load the pointer from the qp_context which is always provided to smc_ib_qp_event_handler() in the priv field. And for qp events the affected port is given in the qp structure of the ibevent, derive it from there. Signed-off-by: Karsten Graul Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/smc_ib.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index e519ef29c0ff..76487a16934e 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -289,8 +289,8 @@ int smc_ib_create_protection_domain(struct smc_link *lnk) static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv) { - struct smc_ib_device *smcibdev = - (struct smc_ib_device *)ibevent->device; + struct smc_link *lnk = (struct smc_link *)priv; + struct smc_ib_device *smcibdev = lnk->smcibdev; u8 port_idx; switch (ibevent->event) { @@ -298,7 +298,7 @@ static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv) case IB_EVENT_GID_CHANGE: case IB_EVENT_PORT_ERR: case IB_EVENT_QP_ACCESS_ERR: - port_idx = ibevent->element.port_num - 1; + port_idx = ibevent->element.qp->port - 1; set_bit(port_idx, &smcibdev->port_event_mask); schedule_work(&smcibdev->port_event_work); break; From 46ad02229d6b4ee276eb295ca08f039993f323c8 Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Wed, 30 Jan 2019 18:51:08 +0100 Subject: [PATCH 359/525] net/smc: fix use of variable in cleared area Do not use pend->idx as index for the arrays because its value is located in the cleared area. Use the existing local variable instead. Without this fix the wrong area might be cleared. Signed-off-by: Karsten Graul Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/smc_wr.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index c2694750a6a8..1dc88c32d6bb 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -218,10 +218,10 @@ int smc_wr_tx_put_slot(struct smc_link *link, u32 idx = pend->idx; /* clear the full struct smc_wr_tx_pend including .priv */ - memset(&link->wr_tx_pends[pend->idx], 0, - sizeof(link->wr_tx_pends[pend->idx])); - memset(&link->wr_tx_bufs[pend->idx], 0, - sizeof(link->wr_tx_bufs[pend->idx])); + memset(&link->wr_tx_pends[idx], 0, + sizeof(link->wr_tx_pends[idx])); + memset(&link->wr_tx_bufs[idx], 0, + sizeof(link->wr_tx_bufs[idx])); test_and_clear_bit(idx, link->wr_tx_mask); return 1; } From 9b1f19d810e92d6cdc68455fbc22d9f961a58ce1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 30 Jan 2019 11:39:41 -0800 Subject: [PATCH 360/525] dccp: fool proof ccid_hc_[rt]x_parse_options() Similarly to commit 276bdb82dedb ("dccp: check ccid before dereferencing") it is wise to test for a NULL ccid. kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] PREEMPT SMP KASAN CPU: 1 PID: 16 Comm: ksoftirqd/1 Not tainted 5.0.0-rc3+ #37 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:ccid_hc_tx_parse_options net/dccp/ccid.h:205 [inline] RIP: 0010:dccp_parse_options+0x8d9/0x12b0 net/dccp/options.c:233 Code: c5 0f b6 75 b3 80 38 00 0f 85 d6 08 00 00 48 b9 00 00 00 00 00 fc ff df 48 8b 45 b8 4c 8b b8 f8 07 00 00 4c 89 f8 48 c1 e8 03 <80> 3c 08 00 0f 85 95 08 00 00 48 b8 00 00 00 00 00 fc ff df 4d 8b kobject: 'loop5' (0000000080f78fc1): kobject_uevent_env RSP: 0018:ffff8880a94df0b8 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff8880858ac723 RCX: dffffc0000000000 RDX: 0000000000000100 RSI: 0000000000000007 RDI: 0000000000000001 RBP: ffff8880a94df140 R08: 0000000000000001 R09: ffff888061b83a80 R10: ffffed100c370752 R11: ffff888061b83a97 R12: 0000000000000026 R13: 0000000000000001 R14: 0000000000000000 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff8880ae700000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f0defa33518 CR3: 000000008db5e000 CR4: 00000000001406e0 kobject: 'loop5' (0000000080f78fc1): fill_kobj_path: path = '/devices/virtual/block/loop5' DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: dccp_rcv_state_process+0x2b6/0x1af6 net/dccp/input.c:654 dccp_v4_do_rcv+0x100/0x190 net/dccp/ipv4.c:688 sk_backlog_rcv include/net/sock.h:936 [inline] __sk_receive_skb+0x3a9/0xea0 net/core/sock.c:473 dccp_v4_rcv+0x10cb/0x1f80 net/dccp/ipv4.c:880 ip_protocol_deliver_rcu+0xb6/0xa20 net/ipv4/ip_input.c:208 ip_local_deliver_finish+0x23b/0x390 net/ipv4/ip_input.c:234 NF_HOOK include/linux/netfilter.h:289 [inline] NF_HOOK include/linux/netfilter.h:283 [inline] ip_local_deliver+0x1f0/0x740 net/ipv4/ip_input.c:255 dst_input include/net/dst.h:450 [inline] ip_rcv_finish+0x1f4/0x2f0 net/ipv4/ip_input.c:414 NF_HOOK include/linux/netfilter.h:289 [inline] NF_HOOK include/linux/netfilter.h:283 [inline] ip_rcv+0xed/0x620 net/ipv4/ip_input.c:524 __netif_receive_skb_one_core+0x160/0x210 net/core/dev.c:4973 __netif_receive_skb+0x2c/0x1c0 net/core/dev.c:5083 process_backlog+0x206/0x750 net/core/dev.c:5923 napi_poll net/core/dev.c:6346 [inline] net_rx_action+0x76d/0x1930 net/core/dev.c:6412 __do_softirq+0x30b/0xb11 kernel/softirq.c:292 run_ksoftirqd kernel/softirq.c:654 [inline] run_ksoftirqd+0x8e/0x110 kernel/softirq.c:646 smpboot_thread_fn+0x6ab/0xa10 kernel/smpboot.c:164 kthread+0x357/0x430 kernel/kthread.c:246 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:352 Modules linked in: ---[ end trace 58a0ba03bea2c376 ]--- RIP: 0010:ccid_hc_tx_parse_options net/dccp/ccid.h:205 [inline] RIP: 0010:dccp_parse_options+0x8d9/0x12b0 net/dccp/options.c:233 Code: c5 0f b6 75 b3 80 38 00 0f 85 d6 08 00 00 48 b9 00 00 00 00 00 fc ff df 48 8b 45 b8 4c 8b b8 f8 07 00 00 4c 89 f8 48 c1 e8 03 <80> 3c 08 00 0f 85 95 08 00 00 48 b8 00 00 00 00 00 fc ff df 4d 8b RSP: 0018:ffff8880a94df0b8 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff8880858ac723 RCX: dffffc0000000000 RDX: 0000000000000100 RSI: 0000000000000007 RDI: 0000000000000001 RBP: ffff8880a94df140 R08: 0000000000000001 R09: ffff888061b83a80 R10: ffffed100c370752 R11: ffff888061b83a97 R12: 0000000000000026 R13: 0000000000000001 R14: 0000000000000000 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff8880ae700000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f0defa33518 CR3: 0000000009871000 CR4: 00000000001406e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Signed-off-by: Eric Dumazet Reported-by: syzbot Cc: Gerrit Renker Signed-off-by: David S. Miller --- net/dccp/ccid.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h index 6eb837a47b5c..baaaeb2b2c42 100644 --- a/net/dccp/ccid.h +++ b/net/dccp/ccid.h @@ -202,7 +202,7 @@ static inline void ccid_hc_tx_packet_recv(struct ccid *ccid, struct sock *sk, static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk, u8 pkt, u8 opt, u8 *val, u8 len) { - if (ccid->ccid_ops->ccid_hc_tx_parse_options == NULL) + if (!ccid || !ccid->ccid_ops->ccid_hc_tx_parse_options) return 0; return ccid->ccid_ops->ccid_hc_tx_parse_options(sk, pkt, opt, val, len); } @@ -214,7 +214,7 @@ static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk, static inline int ccid_hc_rx_parse_options(struct ccid *ccid, struct sock *sk, u8 pkt, u8 opt, u8 *val, u8 len) { - if (ccid->ccid_ops->ccid_hc_rx_parse_options == NULL) + if (!ccid || !ccid->ccid_ops->ccid_hc_rx_parse_options) return 0; return ccid->ccid_ops->ccid_hc_rx_parse_options(sk, pkt, opt, val, len); } From 42caa0edabd6a0a392ec36a5f0943924e4954311 Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Wed, 30 Jan 2019 16:42:12 -0800 Subject: [PATCH 361/525] scsi: aic94xx: fix module loading The aic94xx driver is currently failing to load with errors like sysfs: cannot create duplicate filename '/devices/pci0000:00/0000:00:03.0/0000:02:00.3/0000:07:02.0/revision' Because the PCI code had recently added a file named 'revision' to every PCI device. Fix this by renaming the aic94xx revision file to aic_revision. This is safe to do for us because as far as I can tell, there's nothing in userspace relying on the current aic94xx revision file so it can be renamed without breaking anything. Fixes: 702ed3be1b1b (PCI: Create revision file in sysfs) Cc: stable@vger.kernel.org Signed-off-by: James Bottomley Signed-off-by: Martin K. Petersen --- drivers/scsi/aic94xx/aic94xx_init.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/aic94xx/aic94xx_init.c b/drivers/scsi/aic94xx/aic94xx_init.c index f83f79b07b50..07efcb9b5b94 100644 --- a/drivers/scsi/aic94xx/aic94xx_init.c +++ b/drivers/scsi/aic94xx/aic94xx_init.c @@ -280,7 +280,7 @@ static ssize_t asd_show_dev_rev(struct device *dev, return snprintf(buf, PAGE_SIZE, "%s\n", asd_dev_rev[asd_ha->revision_id]); } -static DEVICE_ATTR(revision, S_IRUGO, asd_show_dev_rev, NULL); +static DEVICE_ATTR(aic_revision, S_IRUGO, asd_show_dev_rev, NULL); static ssize_t asd_show_dev_bios_build(struct device *dev, struct device_attribute *attr,char *buf) @@ -477,7 +477,7 @@ static int asd_create_dev_attrs(struct asd_ha_struct *asd_ha) { int err; - err = device_create_file(&asd_ha->pcidev->dev, &dev_attr_revision); + err = device_create_file(&asd_ha->pcidev->dev, &dev_attr_aic_revision); if (err) return err; @@ -499,13 +499,13 @@ err_update_bios: err_biosb: device_remove_file(&asd_ha->pcidev->dev, &dev_attr_bios_build); err_rev: - device_remove_file(&asd_ha->pcidev->dev, &dev_attr_revision); + device_remove_file(&asd_ha->pcidev->dev, &dev_attr_aic_revision); return err; } static void asd_remove_dev_attrs(struct asd_ha_struct *asd_ha) { - device_remove_file(&asd_ha->pcidev->dev, &dev_attr_revision); + device_remove_file(&asd_ha->pcidev->dev, &dev_attr_aic_revision); device_remove_file(&asd_ha->pcidev->dev, &dev_attr_bios_build); device_remove_file(&asd_ha->pcidev->dev, &dev_attr_pcba_sn); device_remove_file(&asd_ha->pcidev->dev, &dev_attr_update_bios); From 1723058eab19de741b80ac8ad25bfe2a00e02987 Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Fri, 1 Feb 2019 14:19:57 -0800 Subject: [PATCH 362/525] mm, memory_hotplug: don't bail out in do_migrate_range() prematurely do_migrate_range() takes a memory range and tries to isolate the pages to put them into a list. This list will be later on used in migrate_pages() to know the pages we need to migrate. Currently, if we fail to isolate a single page, we put all already isolated pages back to their LRU and we bail out from the function. This is quite suboptimal, as this will force us to start over again because scan_movable_pages will give us the same range. If there is no chance that we can isolate that page, we will loop here forever. Issue debugged in [1] has proved that. During the debugging of that issue, it was noticed that if do_migrate_ranges() fails to isolate a single page, we will just discard the work we have done so far and bail out, which means that scan_movable_pages() will find again the same set of pages. Instead, we can just skip the error, keep isolating as much pages as possible and then proceed with the call to migrate_pages(). This will allow us to do as much work as possible at once. [1] https://lkml.org/lkml/2018/12/6/324 Michal said: : I still think that this doesn't give us a whole picture. Looping for : ever is a bug. Failing the isolation is quite possible and it should : be a ephemeral condition (e.g. a race with freeing the page or : somebody else isolating the page for whatever reason). And here comes : the disadvantage of the current implementation. We simply throw : everything on the floor just because of a ephemeral condition. The : racy page_count check is quite dubious to prevent from that. Link: http://lkml.kernel.org/r/20181211135312.27034-1-osalvador@suse.de Signed-off-by: Oscar Salvador Acked-by: Michal Hocko Cc: David Hildenbrand Cc: Dan Williams Cc: Jan Kara Cc: Kirill A. Shutemov Cc: William Kucharski Cc: Pavel Tatashin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 18 ++---------------- 1 file changed, 2 insertions(+), 16 deletions(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index b9a667d36c55..d7b7d221c284 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1344,7 +1344,6 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) { unsigned long pfn; struct page *page; - int not_managed = 0; int ret = 0; LIST_HEAD(source); @@ -1392,7 +1391,6 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) else ret = isolate_movable_page(page, ISOLATE_UNEVICTABLE); if (!ret) { /* Success */ - put_page(page); list_add_tail(&page->lru, &source); if (!__PageMovable(page)) inc_node_page_state(page, NR_ISOLATED_ANON + @@ -1401,22 +1399,10 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) } else { pr_warn("failed to isolate pfn %lx\n", pfn); dump_page(page, "isolation failed"); - put_page(page); - /* Because we don't have big zone->lock. we should - check this again here. */ - if (page_count(page)) { - not_managed++; - ret = -EBUSY; - break; - } } + put_page(page); } if (!list_empty(&source)) { - if (not_managed) { - putback_movable_pages(&source); - goto out; - } - /* Allocate a new page from the nearest neighbor node */ ret = migrate_pages(&source, new_node_page, NULL, 0, MIGRATE_SYNC, MR_MEMORY_HOTPLUG); @@ -1429,7 +1415,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) putback_movable_pages(&source); } } -out: + return ret; } From 1fde6f21d90f8ba5da3cb9c54ca991ed72696c43 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 1 Feb 2019 14:20:01 -0800 Subject: [PATCH 363/525] proc: fix /proc/net/* after setns(2) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit /proc entries under /proc/net/* can't be cached into dcache because setns(2) can change current net namespace. [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: avoid vim miscolorization] [adobriyan@gmail.com: write test, add dummy ->d_revalidate hook: necessary if /proc/net/* is pinned at setns time] Link: http://lkml.kernel.org/r/20190108192350.GA12034@avx2 Link: http://lkml.kernel.org/r/20190107162336.GA9239@avx2 Fixes: 1da4d377f943fe4194ffb9fb9c26cc58fad4dd24 ("proc: revalidate misc dentries") Signed-off-by: Alexey Dobriyan Reported-by: Mateusz Stępień Reported-by: Ahmad Fatoum Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/generic.c | 4 +- fs/proc/internal.h | 1 + fs/proc/proc_net.c | 20 +++ tools/testing/selftests/proc/.gitignore | 1 + tools/testing/selftests/proc/Makefile | 1 + tools/testing/selftests/proc/setns-dcache.c | 129 ++++++++++++++++++++ 6 files changed, 155 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/proc/setns-dcache.c diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 8ae109429a88..e39bac94dead 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -256,7 +256,7 @@ struct dentry *proc_lookup_de(struct inode *dir, struct dentry *dentry, inode = proc_get_inode(dir->i_sb, de); if (!inode) return ERR_PTR(-ENOMEM); - d_set_d_op(dentry, &proc_misc_dentry_ops); + d_set_d_op(dentry, de->proc_dops); return d_splice_alias(inode, dentry); } read_unlock(&proc_subdir_lock); @@ -429,6 +429,8 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent, INIT_LIST_HEAD(&ent->pde_openers); proc_set_user(ent, (*parent)->uid, (*parent)->gid); + ent->proc_dops = &proc_misc_dentry_ops; + out: return ent; } diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 5185d7f6a51e..95b14196f284 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -44,6 +44,7 @@ struct proc_dir_entry { struct completion *pde_unload_completion; const struct inode_operations *proc_iops; const struct file_operations *proc_fops; + const struct dentry_operations *proc_dops; union { const struct seq_operations *seq_ops; int (*single_show)(struct seq_file *, void *); diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index d5e0fcb3439e..a7b12435519e 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -38,6 +38,22 @@ static struct net *get_proc_net(const struct inode *inode) return maybe_get_net(PDE_NET(PDE(inode))); } +static int proc_net_d_revalidate(struct dentry *dentry, unsigned int flags) +{ + return 0; +} + +static const struct dentry_operations proc_net_dentry_ops = { + .d_revalidate = proc_net_d_revalidate, + .d_delete = always_delete_dentry, +}; + +static void pde_force_lookup(struct proc_dir_entry *pde) +{ + /* /proc/net/ entries can be changed under us by setns(CLONE_NEWNET) */ + pde->proc_dops = &proc_net_dentry_ops; +} + static int seq_open_net(struct inode *inode, struct file *file) { unsigned int state_size = PDE(inode)->state_size; @@ -90,6 +106,7 @@ struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode, p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; + pde_force_lookup(p); p->proc_fops = &proc_net_seq_fops; p->seq_ops = ops; p->state_size = state_size; @@ -133,6 +150,7 @@ struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; + pde_force_lookup(p); p->proc_fops = &proc_net_seq_fops; p->seq_ops = ops; p->state_size = state_size; @@ -181,6 +199,7 @@ struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode, p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; + pde_force_lookup(p); p->proc_fops = &proc_net_single_fops; p->single_show = show; return proc_register(parent, p); @@ -223,6 +242,7 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; + pde_force_lookup(p); p->proc_fops = &proc_net_single_fops; p->single_show = show; p->write = write; diff --git a/tools/testing/selftests/proc/.gitignore b/tools/testing/selftests/proc/.gitignore index 82121a81681f..29bac5ef9a93 100644 --- a/tools/testing/selftests/proc/.gitignore +++ b/tools/testing/selftests/proc/.gitignore @@ -10,4 +10,5 @@ /proc-uptime-002 /read /self +/setns-dcache /thread-self diff --git a/tools/testing/selftests/proc/Makefile b/tools/testing/selftests/proc/Makefile index 1c12c34cf85d..434d033ee067 100644 --- a/tools/testing/selftests/proc/Makefile +++ b/tools/testing/selftests/proc/Makefile @@ -14,6 +14,7 @@ TEST_GEN_PROGS += proc-uptime-001 TEST_GEN_PROGS += proc-uptime-002 TEST_GEN_PROGS += read TEST_GEN_PROGS += self +TEST_GEN_PROGS += setns-dcache TEST_GEN_PROGS += thread-self include ../lib.mk diff --git a/tools/testing/selftests/proc/setns-dcache.c b/tools/testing/selftests/proc/setns-dcache.c new file mode 100644 index 000000000000..60ab197a73fc --- /dev/null +++ b/tools/testing/selftests/proc/setns-dcache.c @@ -0,0 +1,129 @@ +/* + * Copyright © 2019 Alexey Dobriyan + * + * Permission to use, copy, modify, and distribute this software for any + * purpose with or without fee is hereby granted, provided that the above + * copyright notice and this permission notice appear in all copies. + * + * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES + * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR + * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES + * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN + * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF + * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + */ +/* + * Test that setns(CLONE_NEWNET) points to new /proc/net content even + * if old one is in dcache. + * + * FIXME /proc/net/unix is under CONFIG_UNIX which can be disabled. + */ +#undef NDEBUG +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static pid_t pid = -1; + +static void f(void) +{ + if (pid > 0) { + kill(pid, SIGTERM); + } +} + +int main(void) +{ + int fd[2]; + char _ = 0; + int nsfd; + + atexit(f); + + /* Check for priviledges and syscall availability straight away. */ + if (unshare(CLONE_NEWNET) == -1) { + if (errno == ENOSYS || errno == EPERM) { + return 4; + } + return 1; + } + /* Distinguisher between two otherwise empty net namespaces. */ + if (socket(AF_UNIX, SOCK_STREAM, 0) == -1) { + return 1; + } + + if (pipe(fd) == -1) { + return 1; + } + + pid = fork(); + if (pid == -1) { + return 1; + } + + if (pid == 0) { + if (unshare(CLONE_NEWNET) == -1) { + return 1; + } + + if (write(fd[1], &_, 1) != 1) { + return 1; + } + + pause(); + + return 0; + } + + if (read(fd[0], &_, 1) != 1) { + return 1; + } + + { + char buf[64]; + snprintf(buf, sizeof(buf), "/proc/%u/ns/net", pid); + nsfd = open(buf, O_RDONLY); + if (nsfd == -1) { + return 1; + } + } + + /* Reliably pin dentry into dcache. */ + (void)open("/proc/net/unix", O_RDONLY); + + if (setns(nsfd, CLONE_NEWNET) == -1) { + return 1; + } + + kill(pid, SIGTERM); + pid = 0; + + { + char buf[4096]; + ssize_t rv; + int fd; + + fd = open("/proc/net/unix", O_RDONLY); + if (fd == -1) { + return 1; + } + +#define S "Num RefCount Protocol Flags Type St Inode Path\n" + rv = read(fd, buf, sizeof(buf)); + + assert(rv == strlen(S)); + assert(memcmp(buf, S, strlen(S)) == 0); + } + + return 0; +} From 36c0f7f0f89984bb21e6d0f92d776faf7be73096 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 1 Feb 2019 14:20:12 -0800 Subject: [PATCH 364/525] arch: unexport asm/shmparam.h for all architectures Most architectures do not export shmparam.h to user-space. $ find arch -name shmparam.h | sort arch/alpha/include/asm/shmparam.h arch/arc/include/asm/shmparam.h arch/arm64/include/asm/shmparam.h arch/arm/include/asm/shmparam.h arch/csky/include/asm/shmparam.h arch/ia64/include/asm/shmparam.h arch/mips/include/asm/shmparam.h arch/nds32/include/asm/shmparam.h arch/nios2/include/asm/shmparam.h arch/parisc/include/asm/shmparam.h arch/powerpc/include/asm/shmparam.h arch/s390/include/asm/shmparam.h arch/sh/include/asm/shmparam.h arch/sparc/include/asm/shmparam.h arch/x86/include/asm/shmparam.h arch/xtensa/include/asm/shmparam.h Strangely, some users of the asm-generic wrapper export shmparam.h $ git grep 'generic-y += shmparam.h' arch/c6x/include/uapi/asm/Kbuild:generic-y += shmparam.h arch/h8300/include/uapi/asm/Kbuild:generic-y += shmparam.h arch/hexagon/include/uapi/asm/Kbuild:generic-y += shmparam.h arch/m68k/include/uapi/asm/Kbuild:generic-y += shmparam.h arch/microblaze/include/uapi/asm/Kbuild:generic-y += shmparam.h arch/openrisc/include/uapi/asm/Kbuild:generic-y += shmparam.h arch/riscv/include/asm/Kbuild:generic-y += shmparam.h arch/unicore32/include/uapi/asm/Kbuild:generic-y += shmparam.h The newly added riscv correctly creates the asm-generic wrapper in the kernel space, but the others (c6x, h8300, hexagon, m68k, microblaze, openrisc, unicore32) create the one in the uapi directory. Digging into the git history, now I guess fcc8487d477a ("uapi: export all headers under uapi directories") was the misconversion. Prior to that commit, no architecture exported to shmparam.h As its commit description said, that commit exported shmparam.h for c6x, h8300, hexagon, m68k, openrisc, unicore32. 83f0124ad81e ("microblaze: remove asm-generic wrapper headers") accidentally exported shmparam.h for microblaze. This commit unexports shmparam.h for those architectures. There is no more reason to export include/uapi/asm-generic/shmparam.h, so it has been moved to include/asm-generic/shmparam.h Link: http://lkml.kernel.org/r/1546904307-11124-1-git-send-email-yamada.masahiro@socionext.com Signed-off-by: Masahiro Yamada Acked-by: Stafford Horne Cc: Geert Uytterhoeven Cc: Michal Simek Cc: Yoshinori Sato Cc: Richard Kuo Cc: Guan Xuetao Cc: Nicolas Dichtel Cc: Arnd Bergmann Cc: Aurelien Jacquiot Cc: Greentime Hu Cc: Guo Ren Cc: Palmer Dabbelt Cc: Stefan Kristiansson Cc: Mark Salter Cc: Albert Ou Cc: Jonas Bonn Cc: Vincent Chen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/c6x/include/asm/Kbuild | 1 + arch/c6x/include/uapi/asm/Kbuild | 1 - arch/h8300/include/asm/Kbuild | 1 + arch/h8300/include/uapi/asm/Kbuild | 1 - arch/hexagon/include/asm/Kbuild | 1 + arch/hexagon/include/uapi/asm/Kbuild | 1 - arch/m68k/include/asm/Kbuild | 1 + arch/m68k/include/uapi/asm/Kbuild | 1 - arch/microblaze/include/asm/Kbuild | 1 + arch/microblaze/include/uapi/asm/Kbuild | 1 - arch/openrisc/include/asm/Kbuild | 1 + arch/openrisc/include/uapi/asm/Kbuild | 1 - arch/unicore32/include/asm/Kbuild | 1 + arch/unicore32/include/uapi/asm/Kbuild | 1 - 14 files changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild index 33a2c94fed0d..63b4a1705182 100644 --- a/arch/c6x/include/asm/Kbuild +++ b/arch/c6x/include/asm/Kbuild @@ -30,6 +30,7 @@ generic-y += pgalloc.h generic-y += preempt.h generic-y += segment.h generic-y += serial.h +generic-y += shmparam.h generic-y += tlbflush.h generic-y += topology.h generic-y += trace_clock.h diff --git a/arch/c6x/include/uapi/asm/Kbuild b/arch/c6x/include/uapi/asm/Kbuild index 6c6f6301012e..0febf1a07c30 100644 --- a/arch/c6x/include/uapi/asm/Kbuild +++ b/arch/c6x/include/uapi/asm/Kbuild @@ -1,5 +1,4 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += kvm_para.h -generic-y += shmparam.h generic-y += ucontext.h diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild index cd400d353d18..961c1dc064e1 100644 --- a/arch/h8300/include/asm/Kbuild +++ b/arch/h8300/include/asm/Kbuild @@ -40,6 +40,7 @@ generic-y += preempt.h generic-y += scatterlist.h generic-y += sections.h generic-y += serial.h +generic-y += shmparam.h generic-y += sizes.h generic-y += spinlock.h generic-y += timex.h diff --git a/arch/h8300/include/uapi/asm/Kbuild b/arch/h8300/include/uapi/asm/Kbuild index 6c6f6301012e..0febf1a07c30 100644 --- a/arch/h8300/include/uapi/asm/Kbuild +++ b/arch/h8300/include/uapi/asm/Kbuild @@ -1,5 +1,4 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += kvm_para.h -generic-y += shmparam.h generic-y += ucontext.h diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild index 47c4da3d64a4..b25fd42aa0f4 100644 --- a/arch/hexagon/include/asm/Kbuild +++ b/arch/hexagon/include/asm/Kbuild @@ -30,6 +30,7 @@ generic-y += rwsem.h generic-y += sections.h generic-y += segment.h generic-y += serial.h +generic-y += shmparam.h generic-y += sizes.h generic-y += topology.h generic-y += trace_clock.h diff --git a/arch/hexagon/include/uapi/asm/Kbuild b/arch/hexagon/include/uapi/asm/Kbuild index 61d955c1747a..c1b06dcf6cf8 100644 --- a/arch/hexagon/include/uapi/asm/Kbuild +++ b/arch/hexagon/include/uapi/asm/Kbuild @@ -1,4 +1,3 @@ include include/uapi/asm-generic/Kbuild.asm -generic-y += shmparam.h generic-y += ucontext.h diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild index 9f1dd26903e3..95f8f631c4df 100644 --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -20,6 +20,7 @@ generic-y += mm-arch-hooks.h generic-y += percpu.h generic-y += preempt.h generic-y += sections.h +generic-y += shmparam.h generic-y += spinlock.h generic-y += topology.h generic-y += trace_clock.h diff --git a/arch/m68k/include/uapi/asm/Kbuild b/arch/m68k/include/uapi/asm/Kbuild index b8b3525271fa..960bf1e4be53 100644 --- a/arch/m68k/include/uapi/asm/Kbuild +++ b/arch/m68k/include/uapi/asm/Kbuild @@ -2,4 +2,3 @@ include include/uapi/asm-generic/Kbuild.asm generated-y += unistd_32.h generic-y += kvm_para.h -generic-y += shmparam.h diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild index 9c7d1d25bf3d..791cc8d54d0a 100644 --- a/arch/microblaze/include/asm/Kbuild +++ b/arch/microblaze/include/asm/Kbuild @@ -26,6 +26,7 @@ generic-y += parport.h generic-y += percpu.h generic-y += preempt.h generic-y += serial.h +generic-y += shmparam.h generic-y += syscalls.h generic-y += topology.h generic-y += trace_clock.h diff --git a/arch/microblaze/include/uapi/asm/Kbuild b/arch/microblaze/include/uapi/asm/Kbuild index 28823e3db825..97823ec46e97 100644 --- a/arch/microblaze/include/uapi/asm/Kbuild +++ b/arch/microblaze/include/uapi/asm/Kbuild @@ -2,5 +2,4 @@ include include/uapi/asm-generic/Kbuild.asm generated-y += unistd_32.h generic-y += kvm_para.h -generic-y += shmparam.h generic-y += ucontext.h diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild index eb87cd8327c8..1f04844b6b82 100644 --- a/arch/openrisc/include/asm/Kbuild +++ b/arch/openrisc/include/asm/Kbuild @@ -34,6 +34,7 @@ generic-y += qrwlock_types.h generic-y += qrwlock.h generic-y += sections.h generic-y += segment.h +generic-y += shmparam.h generic-y += string.h generic-y += switch_to.h generic-y += topology.h diff --git a/arch/openrisc/include/uapi/asm/Kbuild b/arch/openrisc/include/uapi/asm/Kbuild index 6c6f6301012e..0febf1a07c30 100644 --- a/arch/openrisc/include/uapi/asm/Kbuild +++ b/arch/openrisc/include/uapi/asm/Kbuild @@ -1,5 +1,4 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += kvm_para.h -generic-y += shmparam.h generic-y += ucontext.h diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild index 1372553dc0a9..1d1544b6ca74 100644 --- a/arch/unicore32/include/asm/Kbuild +++ b/arch/unicore32/include/asm/Kbuild @@ -28,6 +28,7 @@ generic-y += preempt.h generic-y += sections.h generic-y += segment.h generic-y += serial.h +generic-y += shmparam.h generic-y += sizes.h generic-y += syscalls.h generic-y += topology.h diff --git a/arch/unicore32/include/uapi/asm/Kbuild b/arch/unicore32/include/uapi/asm/Kbuild index 6c6f6301012e..0febf1a07c30 100644 --- a/arch/unicore32/include/uapi/asm/Kbuild +++ b/arch/unicore32/include/uapi/asm/Kbuild @@ -1,5 +1,4 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += kvm_para.h -generic-y += shmparam.h generic-y += ucontext.h From 1ac25013fb9e4ed595cd608a406191e93520881e Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Fri, 1 Feb 2019 14:20:16 -0800 Subject: [PATCH 365/525] mm/hugetlb.c: teach follow_hugetlb_page() to handle FOLL_NOWAIT hugetlb needs the same fix as faultin_nopage (which was applied in commit 96312e61282a ("mm/gup.c: teach get_user_pages_unlocked to handle FOLL_NOWAIT")) or KVM hangs because it thinks the mmap_sem was already released by hugetlb_fault() if it returned VM_FAULT_RETRY, but it wasn't in the FOLL_NOWAIT case. Link: http://lkml.kernel.org/r/20190109020203.26669-2-aarcange@redhat.com Fixes: ce53053ce378 ("kvm: switch get_user_page_nowait() to get_user_pages_unlocked()") Signed-off-by: Andrea Arcangeli Tested-by: "Dr. David Alan Gilbert" Reported-by: "Dr. David Alan Gilbert" Reviewed-by: Mike Kravetz Reviewed-by: Peter Xu Cc: Mike Rapoport Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index df2e7dd5ff17..afef61656c1e 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4268,7 +4268,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, break; } if (ret & VM_FAULT_RETRY) { - if (nonblocking) + if (nonblocking && + !(fault_flags & FAULT_FLAG_RETRY_NOWAIT)) *nonblocking = 0; *nr_pages = 0; /* From a8e911d13540487942d53137c156bd7707f66e5d Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Fri, 1 Feb 2019 14:20:20 -0800 Subject: [PATCH 366/525] x86_64: increase stack size for KASAN_EXTRA If the kernel is configured with KASAN_EXTRA, the stack size is increasted significantly because this option sets "-fstack-reuse" to "none" in GCC [1]. As a result, it triggers stack overrun quite often with 32k stack size compiled using GCC 8. For example, this reproducer https://github.com/linux-test-project/ltp/blob/master/testcases/kernel/syscalls/madvise/madvise06.c triggers a "corrupted stack end detected inside scheduler" very reliably with CONFIG_SCHED_STACK_END_CHECK enabled. There are just too many functions that could have a large stack with KASAN_EXTRA due to large local variables that have been called over and over again without being able to reuse the stacks. Some noticiable ones are size 7648 shrink_page_list 3584 xfs_rmap_convert 3312 migrate_page_move_mapping 3312 dev_ethtool 3200 migrate_misplaced_transhuge_page 3168 copy_process There are other 49 functions are over 2k in size while compiling kernel with "-Wframe-larger-than=" even with a related minimal config on this machine. Hence, it is too much work to change Makefiles for each object to compile without "-fsanitize-address-use-after-scope" individually. [1] https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81715#c23 Although there is a patch in GCC 9 to help the situation, GCC 9 probably won't be released in a few months and then it probably take another 6-month to 1-year for all major distros to include it as a default. Hence, the stack usage with KASAN_EXTRA can be revisited again in 2020 when GCC 9 is everywhere. Until then, this patch will help users avoid stack overrun. This has already been fixed for arm64 for the same reason via 6e8830674ea ("arm64: kasan: Increase stack size for KASAN_EXTRA"). Link: http://lkml.kernel.org/r/20190109215209.2903-1-cai@lca.pw Signed-off-by: Qian Cai Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Dmitry Vyukov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/page_64_types.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 8f657286d599..0ce558a8150d 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -7,7 +7,11 @@ #endif #ifdef CONFIG_KASAN +#ifdef CONFIG_KASAN_EXTRA +#define KASAN_STACK_ORDER 2 +#else #define KASAN_STACK_ORDER 1 +#endif #else #define KASAN_STACK_ORDER 0 #endif From 8fb335e078378c8426fabeed1ebee1fbf915690c Mon Sep 17 00:00:00 2001 From: Andrei Vagin Date: Fri, 1 Feb 2019 14:20:24 -0800 Subject: [PATCH 367/525] kernel/exit.c: release ptraced tasks before zap_pid_ns_processes Currently, exit_ptrace() adds all ptraced tasks in a dead list, then zap_pid_ns_processes() waits on all tasks in a current pidns, and only then are tasks from the dead list released. zap_pid_ns_processes() can get stuck on waiting tasks from the dead list. In this case, we will have one unkillable process with one or more dead children. Thanks to Oleg for the advice to release tasks in find_child_reaper(). Link: http://lkml.kernel.org/r/20190110175200.12442-1-avagin@gmail.com Fixes: 7c8bd2322c7f ("exit: ptrace: shift "reap dead" code from exit_ptrace() to forget_original_parent()") Signed-off-by: Andrei Vagin Signed-off-by: Oleg Nesterov Cc: "Eric W. Biederman" Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/exit.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/kernel/exit.c b/kernel/exit.c index 3fb7be001964..2639a30a8aa5 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -558,12 +558,14 @@ static struct task_struct *find_alive_thread(struct task_struct *p) return NULL; } -static struct task_struct *find_child_reaper(struct task_struct *father) +static struct task_struct *find_child_reaper(struct task_struct *father, + struct list_head *dead) __releases(&tasklist_lock) __acquires(&tasklist_lock) { struct pid_namespace *pid_ns = task_active_pid_ns(father); struct task_struct *reaper = pid_ns->child_reaper; + struct task_struct *p, *n; if (likely(reaper != father)) return reaper; @@ -579,6 +581,12 @@ static struct task_struct *find_child_reaper(struct task_struct *father) panic("Attempted to kill init! exitcode=0x%08x\n", father->signal->group_exit_code ?: father->exit_code); } + + list_for_each_entry_safe(p, n, dead, ptrace_entry) { + list_del_init(&p->ptrace_entry); + release_task(p); + } + zap_pid_ns_processes(pid_ns); write_lock_irq(&tasklist_lock); @@ -668,7 +676,7 @@ static void forget_original_parent(struct task_struct *father, exit_ptrace(father, dead); /* Can drop and reacquire tasklist_lock */ - reaper = find_child_reaper(father); + reaper = find_child_reaper(father, dead); if (list_empty(&father->children)) return; From 80409c65e2c6cd1540045ee01fc55e50d95e0983 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 1 Feb 2019 14:20:27 -0800 Subject: [PATCH 368/525] mm: migrate: make buffer_migrate_page_norefs() actually succeed Currently, buffer_migrate_page_norefs() was constantly failing because buffer_migrate_lock_buffers() grabbed reference on each buffer. In fact, there's no reason for buffer_migrate_lock_buffers() to grab any buffer references as the page is locked during all our operation and thus nobody can reclaim buffers from the page. So remove grabbing of buffer references which also makes buffer_migrate_page_norefs() succeed. Link: http://lkml.kernel.org/r/20190116131217.7226-1-jack@suse.cz Fixes: 89cb0888ca14 "mm: migrate: provide buffer_migrate_page_norefs()" Signed-off-by: Jan Kara Cc: Sergey Senozhatsky Cc: Pavel Machek Cc: Mel Gorman Cc: Vlastimil Babka Cc: Andrea Arcangeli Cc: David Rientjes Cc: Michal Hocko Cc: Zi Yan Cc: Johannes Weiner Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/migrate.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/mm/migrate.c b/mm/migrate.c index a16b15090df3..712b231a7376 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -709,7 +709,6 @@ static bool buffer_migrate_lock_buffers(struct buffer_head *head, /* Simple case, sync compaction */ if (mode != MIGRATE_ASYNC) { do { - get_bh(bh); lock_buffer(bh); bh = bh->b_this_page; @@ -720,18 +719,15 @@ static bool buffer_migrate_lock_buffers(struct buffer_head *head, /* async case, we cannot block on lock_buffer so use trylock_buffer */ do { - get_bh(bh); if (!trylock_buffer(bh)) { /* * We failed to lock the buffer and cannot stall in * async migration. Release the taken locks */ struct buffer_head *failed_bh = bh; - put_bh(failed_bh); bh = head; while (bh != failed_bh) { unlock_buffer(bh); - put_bh(bh); bh = bh->b_this_page; } return false; @@ -818,7 +814,6 @@ unlock_buffers: bh = head; do { unlock_buffer(bh); - put_bh(bh); bh = bh->b_this_page; } while (bh != head); From 9bcdeb51bd7d2ae9fe65ea4d60643d2aeef5bfe3 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Fri, 1 Feb 2019 14:20:31 -0800 Subject: [PATCH 369/525] oom, oom_reaper: do not enqueue same task twice Arkadiusz reported that enabling memcg's group oom killing causes strange memcg statistics where there is no task in a memcg despite the number of tasks in that memcg is not 0. It turned out that there is a bug in wake_oom_reaper() which allows enqueuing same task twice which makes impossible to decrease the number of tasks in that memcg due to a refcount leak. This bug existed since the OOM reaper became invokable from task_will_free_mem(current) path in out_of_memory() in Linux 4.7, T1@P1 |T2@P1 |T3@P1 |OOM reaper ----------+----------+----------+------------ # Processing an OOM victim in a different memcg domain. try_charge() mem_cgroup_out_of_memory() mutex_lock(&oom_lock) try_charge() mem_cgroup_out_of_memory() mutex_lock(&oom_lock) try_charge() mem_cgroup_out_of_memory() mutex_lock(&oom_lock) out_of_memory() oom_kill_process(P1) do_send_sig_info(SIGKILL, @P1) mark_oom_victim(T1@P1) wake_oom_reaper(T1@P1) # T1@P1 is enqueued. mutex_unlock(&oom_lock) out_of_memory() mark_oom_victim(T2@P1) wake_oom_reaper(T2@P1) # T2@P1 is enqueued. mutex_unlock(&oom_lock) out_of_memory() mark_oom_victim(T1@P1) wake_oom_reaper(T1@P1) # T1@P1 is enqueued again due to oom_reaper_list == T2@P1 && T1@P1->oom_reaper_list == NULL. mutex_unlock(&oom_lock) # Completed processing an OOM victim in a different memcg domain. spin_lock(&oom_reaper_lock) # T1P1 is dequeued. spin_unlock(&oom_reaper_lock) but memcg's group oom killing made it easier to trigger this bug by calling wake_oom_reaper() on the same task from one out_of_memory() request. Fix this bug using an approach used by commit 855b018325737f76 ("oom, oom_reaper: disable oom_reaper for oom_kill_allocating_task"). As a side effect of this patch, this patch also avoids enqueuing multiple threads sharing memory via task_will_free_mem(current) path. Link: http://lkml.kernel.org/r/e865a044-2c10-9858-f4ef-254bc71d6cc2@i-love.sakura.ne.jp Link: http://lkml.kernel.org/r/5ee34fc6-1485-34f8-8790-903ddabaa809@i-love.sakura.ne.jp Fixes: af8e15cc85a25315 ("oom, oom_reaper: do not enqueue task if it is on the oom_reaper_list head") Signed-off-by: Tetsuo Handa Reported-by: Arkadiusz Miskiewicz Tested-by: Arkadiusz Miskiewicz Acked-by: Michal Hocko Acked-by: Roman Gushchin Cc: Tejun Heo Cc: Aleksa Sarai Cc: Jay Kamat Cc: Johannes Weiner Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched/coredump.h | 1 + mm/oom_kill.c | 4 ++-- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index ec912d01126f..ecdc6542070f 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -71,6 +71,7 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ #define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ #define MMF_OOM_VICTIM 25 /* mm is the oom victim */ +#define MMF_OOM_REAP_QUEUED 26 /* mm was queued for oom_reaper */ #define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ diff --git a/mm/oom_kill.c b/mm/oom_kill.c index f0e8cd9edb1a..059e617a1847 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -647,8 +647,8 @@ static int oom_reaper(void *unused) static void wake_oom_reaper(struct task_struct *tsk) { - /* tsk is already queued? */ - if (tsk == oom_reaper_list || tsk->oom_reaper_list) + /* mm is already queued? */ + if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags)) return; get_task_struct(tsk); From efad4e475c312456edb3c789d0996d12ed744c13 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 1 Feb 2019 14:20:34 -0800 Subject: [PATCH 370/525] mm, memory_hotplug: is_mem_section_removable do not pass the end of a zone Patch series "mm, memory_hotplug: fix uninitialized pages fallouts", v2. Mikhail Zaslonko has posted fixes for the two bugs quite some time ago [1]. I have pushed back on those fixes because I believed that it is much better to plug the problem at the initialization time rather than play whack-a-mole all over the hotplug code and find all the places which expect the full memory section to be initialized. We have ended up with commit 2830bf6f05fb ("mm, memory_hotplug: initialize struct pages for the full memory section") merged and cause a regression [2][3]. The reason is that there might be memory layouts when two NUMA nodes share the same memory section so the merged fix is simply incorrect. In order to plug this hole we really have to be zone range aware in those handlers. I have split up the original patch into two. One is unchanged (patch 2) and I took a different approach for `removable' crash. [1] http://lkml.kernel.org/r/20181105150401.97287-2-zaslonko@linux.ibm.com [2] https://bugzilla.redhat.com/show_bug.cgi?id=1666948 [3] http://lkml.kernel.org/r/20190125163938.GA20411@dhcp22.suse.cz This patch (of 2): Mikhail has reported the following VM_BUG_ON triggered when reading sysfs removable state of a memory block: page:000003d08300c000 is uninitialized and poisoned page dumped because: VM_BUG_ON_PAGE(PagePoisoned(p)) Call Trace: is_mem_section_removable+0xb4/0x190 show_mem_removable+0x9a/0xd8 dev_attr_show+0x34/0x70 sysfs_kf_seq_show+0xc8/0x148 seq_read+0x204/0x480 __vfs_read+0x32/0x178 vfs_read+0x82/0x138 ksys_read+0x5a/0xb0 system_call+0xdc/0x2d8 Last Breaking-Event-Address: is_mem_section_removable+0xb4/0x190 Kernel panic - not syncing: Fatal exception: panic_on_oops The reason is that the memory block spans the zone boundary and we are stumbling over an unitialized struct page. Fix this by enforcing zone range in is_mem_section_removable so that we never run away from a zone. Link: http://lkml.kernel.org/r/20190128144506.15603-2-mhocko@kernel.org Signed-off-by: Michal Hocko Reported-by: Mikhail Zaslonko Debugged-by: Mikhail Zaslonko Tested-by: Gerald Schaefer Tested-by: Mikhail Gavrilov Reviewed-by: Oscar Salvador Cc: Pavel Tatashin Cc: Heiko Carstens Cc: Martin Schwidefsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index d7b7d221c284..91e6fef4cf9f 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1233,7 +1233,8 @@ static bool is_pageblock_removable_nolock(struct page *page) bool is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages) { struct page *page = pfn_to_page(start_pfn); - struct page *end_page = page + nr_pages; + unsigned long end_pfn = min(start_pfn + nr_pages, zone_end_pfn(page_zone(page))); + struct page *end_page = pfn_to_page(end_pfn); /* Check the starting page of each pageblock within the range */ for (; page < end_page; page = next_active_pageblock(page)) { From 24feb47c5fa5b825efb0151f28906dfdad027e61 Mon Sep 17 00:00:00 2001 From: Mikhail Zaslonko Date: Fri, 1 Feb 2019 14:20:38 -0800 Subject: [PATCH 371/525] mm, memory_hotplug: test_pages_in_a_zone do not pass the end of zone If memory end is not aligned with the sparse memory section boundary, the mapping of such a section is only partly initialized. This may lead to VM_BUG_ON due to uninitialized struct pages access from test_pages_in_a_zone() function triggered by memory_hotplug sysfs handlers. Here are the the panic examples: CONFIG_DEBUG_VM_PGFLAGS=y kernel parameter mem=2050M -------------------------- page:000003d082008000 is uninitialized and poisoned page dumped because: VM_BUG_ON_PAGE(PagePoisoned(p)) Call Trace: test_pages_in_a_zone+0xde/0x160 show_valid_zones+0x5c/0x190 dev_attr_show+0x34/0x70 sysfs_kf_seq_show+0xc8/0x148 seq_read+0x204/0x480 __vfs_read+0x32/0x178 vfs_read+0x82/0x138 ksys_read+0x5a/0xb0 system_call+0xdc/0x2d8 Last Breaking-Event-Address: test_pages_in_a_zone+0xde/0x160 Kernel panic - not syncing: Fatal exception: panic_on_oops Fix this by checking whether the pfn to check is within the zone. [mhocko@suse.com: separated this change from http://lkml.kernel.org/r/20181105150401.97287-2-zaslonko@linux.ibm.com] Link: http://lkml.kernel.org/r/20190128144506.15603-3-mhocko@kernel.org [mhocko@suse.com: separated this change from http://lkml.kernel.org/r/20181105150401.97287-2-zaslonko@linux.ibm.com] Signed-off-by: Michal Hocko Signed-off-by: Mikhail Zaslonko Tested-by: Mikhail Gavrilov Reviewed-by: Oscar Salvador Tested-by: Gerald Schaefer Cc: Heiko Carstens Cc: Martin Schwidefsky Cc: Mikhail Gavrilov Cc: Pavel Tatashin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 91e6fef4cf9f..ecc5ee04e301 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1274,6 +1274,9 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, i++; if (i == MAX_ORDER_NR_PAGES || pfn + i >= end_pfn) continue; + /* Check if we got outside of the zone */ + if (zone && !zone_spans_pfn(zone, pfn + i)) + return 0; page = pfn_to_page(pfn + i); if (zone && page_zone(page) != zone) return 0; From 1b69ac6b40ebd85eed73e4dbccde2a36961ab990 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 1 Feb 2019 14:20:42 -0800 Subject: [PATCH 372/525] psi: fix aggregation idle shut-off psi has provisions to shut off the periodic aggregation worker when there is a period of no task activity - and thus no data that needs aggregating. However, while developing psi monitoring, Suren noticed that the aggregation clock currently won't stay shut off for good. Debugging this revealed a flaw in the idle design: an aggregation run will see no task activity and decide to go to sleep; shortly thereafter, the kworker thread that executed the aggregation will go idle and cause a scheduling change, during which the psi callback will kick the !pending worker again. This will ping-pong forever, and is equivalent to having no shut-off logic at all (but with more code!) Fix this by exempting aggregation workers from psi's clock waking logic when the state change is them going to sleep. To do this, tag workers with the last work function they executed, and if in psi we see a worker going to sleep after aggregating psi data, we will not reschedule the aggregation work item. What if the worker is also executing other items before or after? Any psi state times that were incurred by work items preceding the aggregation work will have been collected from the per-cpu buckets during the aggregation itself. If there are work items following the aggregation work, the worker's last_func tag will be overwritten and the aggregator will be kept alive to process this genuine new activity. If the aggregation work is the last thing the worker does, and we decide to go idle, the brief period of non-idle time incurred between the aggregation run and the kworker's dequeue will be stranded in the per-cpu buckets until the clock is woken by later activity. But that should not be a problem. The buckets can hold 4s worth of time, and future activity will wake the clock with a 2s delay, giving us 2s worth of data we can leave behind when disabling aggregation. If it takes a worker more than two seconds to go idle after it finishes its last work item, we likely have bigger problems in the system, and won't notice one sample that was averaged with a bogus per-CPU weight. Link: http://lkml.kernel.org/r/20190116193501.1910-1-hannes@cmpxchg.org Fixes: eb414681d5a0 ("psi: pressure stall information for CPU, memory, and IO") Signed-off-by: Johannes Weiner Reported-by: Suren Baghdasaryan Acked-by: Tejun Heo Cc: Peter Zijlstra Cc: Lai Jiangshan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sched/psi.c | 21 +++++++++++++++++---- kernel/workqueue.c | 23 +++++++++++++++++++++++ kernel/workqueue_internal.h | 6 +++++- 3 files changed, 45 insertions(+), 5 deletions(-) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index fe24de3fbc93..c3484785b179 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -124,6 +124,7 @@ * sampling of the aggregate task states would be. */ +#include "../workqueue_internal.h" #include #include #include @@ -480,9 +481,6 @@ static void psi_group_change(struct psi_group *group, int cpu, groupc->tasks[t]++; write_seqcount_end(&groupc->seq); - - if (!delayed_work_pending(&group->clock_work)) - schedule_delayed_work(&group->clock_work, PSI_FREQ); } static struct psi_group *iterate_groups(struct task_struct *task, void **iter) @@ -513,6 +511,7 @@ void psi_task_change(struct task_struct *task, int clear, int set) { int cpu = task_cpu(task); struct psi_group *group; + bool wake_clock = true; void *iter = NULL; if (!task->pid) @@ -530,8 +529,22 @@ void psi_task_change(struct task_struct *task, int clear, int set) task->psi_flags &= ~clear; task->psi_flags |= set; - while ((group = iterate_groups(task, &iter))) + /* + * Periodic aggregation shuts off if there is a period of no + * task changes, so we wake it back up if necessary. However, + * don't do this if the task change is the aggregation worker + * itself going to sleep, or we'll ping-pong forever. + */ + if (unlikely((clear & TSK_RUNNING) && + (task->flags & PF_WQ_WORKER) && + wq_worker_last_func(task) == psi_update_work)) + wake_clock = false; + + while ((group = iterate_groups(task, &iter))) { psi_group_change(group, cpu, clear, set); + if (wake_clock && !delayed_work_pending(&group->clock_work)) + schedule_delayed_work(&group->clock_work, PSI_FREQ); + } } void psi_memstall_tick(struct task_struct *task, int cpu) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 392be4b252f6..fc5d23d752a5 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -909,6 +909,26 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task) return to_wakeup ? to_wakeup->task : NULL; } +/** + * wq_worker_last_func - retrieve worker's last work function + * + * Determine the last function a worker executed. This is called from + * the scheduler to get a worker's last known identity. + * + * CONTEXT: + * spin_lock_irq(rq->lock) + * + * Return: + * The last work function %current executed as a worker, NULL if it + * hasn't executed any work yet. + */ +work_func_t wq_worker_last_func(struct task_struct *task) +{ + struct worker *worker = kthread_data(task); + + return worker->last_func; +} + /** * worker_set_flags - set worker flags and adjust nr_running accordingly * @worker: self @@ -2184,6 +2204,9 @@ __acquires(&pool->lock) if (unlikely(cpu_intensive)) worker_clr_flags(worker, WORKER_CPU_INTENSIVE); + /* tag the worker for identification in schedule() */ + worker->last_func = worker->current_func; + /* we're done with it, release */ hash_del(&worker->hentry); worker->current_work = NULL; diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h index 66fbb5a9e633..cb68b03ca89a 100644 --- a/kernel/workqueue_internal.h +++ b/kernel/workqueue_internal.h @@ -53,6 +53,9 @@ struct worker { /* used only by rescuers to point to the target workqueue */ struct workqueue_struct *rescue_wq; /* I: the workqueue to rescue */ + + /* used by the scheduler to determine a worker's last known identity */ + work_func_t last_func; }; /** @@ -67,9 +70,10 @@ static inline struct worker *current_wq_worker(void) /* * Scheduler hooks for concurrency managed workqueue. Only to be used from - * sched/core.c and workqueue.c. + * sched/ and workqueue.c. */ void wq_worker_waking_up(struct task_struct *task, int cpu); struct task_struct *wq_worker_sleeping(struct task_struct *task); +work_func_t wq_worker_last_func(struct task_struct *task); #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */ From eeb0efd071d821a88da3fbd35f2d478f40d3b2ea Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Fri, 1 Feb 2019 14:20:47 -0800 Subject: [PATCH 373/525] mm,memory_hotplug: fix scan_movable_pages() for gigantic hugepages This is the same sort of error we saw in commit 17e2e7d7e1b8 ("mm, page_alloc: fix has_unmovable_pages for HugePages"). Gigantic hugepages cross several memblocks, so it can be that the page we get in scan_movable_pages() is a page-tail belonging to a 1G-hugepage. If that happens, page_hstate()->size_to_hstate() will return NULL, and we will blow up in hugepage_migration_supported(). The splat is as follows: BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 1 PID: 1350 Comm: bash Tainted: G E 5.0.0-rc1-mm1-1-default+ #27 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.0.0-prebuilt.qemu-project.org 04/01/2014 RIP: 0010:__offline_pages+0x6ae/0x900 Call Trace: memory_subsys_offline+0x42/0x60 device_offline+0x80/0xa0 state_store+0xab/0xc0 kernfs_fop_write+0x102/0x180 __vfs_write+0x26/0x190 vfs_write+0xad/0x1b0 ksys_write+0x42/0x90 do_syscall_64+0x5b/0x180 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Modules linked in: af_packet(E) xt_tcpudp(E) ipt_REJECT(E) xt_conntrack(E) nf_conntrack(E) nf_defrag_ipv4(E) ip_set(E) nfnetlink(E) ebtable_nat(E) ebtable_broute(E) bridge(E) stp(E) llc(E) iptable_mangle(E) iptable_raw(E) iptable_security(E) ebtable_filter(E) ebtables(E) iptable_filter(E) ip_tables(E) x_tables(E) kvm_intel(E) kvm(E) irqbypass(E) crct10dif_pclmul(E) crc32_pclmul(E) ghash_clmulni_intel(E) bochs_drm(E) ttm(E) aesni_intel(E) drm_kms_helper(E) aes_x86_64(E) crypto_simd(E) cryptd(E) glue_helper(E) drm(E) virtio_net(E) syscopyarea(E) sysfillrect(E) net_failover(E) sysimgblt(E) pcspkr(E) failover(E) i2c_piix4(E) fb_sys_fops(E) parport_pc(E) parport(E) button(E) btrfs(E) libcrc32c(E) xor(E) zstd_decompress(E) zstd_compress(E) xxhash(E) raid6_pq(E) sd_mod(E) ata_generic(E) ata_piix(E) ahci(E) libahci(E) libata(E) crc32c_intel(E) serio_raw(E) virtio_pci(E) virtio_ring(E) virtio(E) sg(E) scsi_mod(E) autofs4(E) [akpm@linux-foundation.org: fix brace layout, per David. Reduce indentation] Link: http://lkml.kernel.org/r/20190122154407.18417-1-osalvador@suse.de Signed-off-by: Oscar Salvador Reviewed-by: Anthony Yznaga Acked-by: Michal Hocko Reviewed-by: David Hildenbrand Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 36 ++++++++++++++++++++---------------- 1 file changed, 20 insertions(+), 16 deletions(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index ecc5ee04e301..a0130633a6e1 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1305,23 +1305,27 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, static unsigned long scan_movable_pages(unsigned long start, unsigned long end) { unsigned long pfn; - struct page *page; + for (pfn = start; pfn < end; pfn++) { - if (pfn_valid(pfn)) { - page = pfn_to_page(pfn); - if (PageLRU(page)) - return pfn; - if (__PageMovable(page)) - return pfn; - if (PageHuge(page)) { - if (hugepage_migration_supported(page_hstate(page)) && - page_huge_active(page)) - return pfn; - else - pfn = round_up(pfn + 1, - 1 << compound_order(page)) - 1; - } - } + struct page *page, *head; + unsigned long skip; + + if (!pfn_valid(pfn)) + continue; + page = pfn_to_page(pfn); + if (PageLRU(page)) + return pfn; + if (__PageMovable(page)) + return pfn; + + if (!PageHuge(page)) + continue; + head = compound_head(page); + if (hugepage_migration_supported(page_hstate(head)) && + page_huge_active(head)) + return pfn; + skip = (1 << compound_order(head)) - (page - head); + pfn += skip - 1; } return 0; } From b13bc35193d9e7a8c050a24928ca5c9e7c9a009b Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Fri, 1 Feb 2019 14:20:51 -0800 Subject: [PATCH 374/525] mm/hotplug: invalid PFNs from pfn_to_online_page() On an arm64 ThunderX2 server, the first kmemleak scan would crash [1] with CONFIG_DEBUG_VM_PGFLAGS=y due to page_to_nid() found a pfn that is not directly mapped (MEMBLOCK_NOMAP). Hence, the page->flags is uninitialized. This is due to the commit 9f1eb38e0e11 ("mm, kmemleak: little optimization while scanning") starts to use pfn_to_online_page() instead of pfn_valid(). However, in the CONFIG_MEMORY_HOTPLUG=y case, pfn_to_online_page() does not call memblock_is_map_memory() while pfn_valid() does. Historically, the commit 68709f45385a ("arm64: only consider memblocks with NOMAP cleared for linear mapping") causes pages marked as nomap being no long reassigned to the new zone in memmap_init_zone() by calling __init_single_page(). Since the commit 2d070eab2e82 ("mm: consider zone which is not fully populated to have holes") introduced pfn_to_online_page() and was designed to return a valid pfn only, but it is clearly broken on arm64. Therefore, let pfn_to_online_page() call pfn_valid_within(), so it can handle nomap thanks to the commit f52bb98f5ade ("arm64: mm: always enable CONFIG_HOLES_IN_ZONE"), while it will be optimized away on architectures where have no HOLES_IN_ZONE. [1] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000006 Mem abort info: ESR = 0x96000005 Exception class = DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 Data abort info: ISV = 0, ISS = 0x00000005 CM = 0, WnR = 0 Internal error: Oops: 96000005 [#1] SMP CPU: 60 PID: 1408 Comm: kmemleak Not tainted 5.0.0-rc2+ #8 pstate: 60400009 (nZCv daif +PAN -UAO) pc : page_mapping+0x24/0x144 lr : __dump_page+0x34/0x3dc sp : ffff00003a5cfd10 x29: ffff00003a5cfd10 x28: 000000000000802f x27: 0000000000000000 x26: 0000000000277d00 x25: ffff000010791f56 x24: ffff7fe000000000 x23: ffff000010772f8b x22: ffff00001125f670 x21: ffff000011311000 x20: ffff000010772f8b x19: fffffffffffffffe x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000 x14: ffff802698b19600 x13: ffff802698b1a200 x12: ffff802698b16f00 x11: ffff802698b1a400 x10: 0000000000001400 x9 : 0000000000000001 x8 : ffff00001121a000 x7 : 0000000000000000 x6 : ffff0000102c53b8 x5 : 0000000000000000 x4 : 0000000000000003 x3 : 0000000000000100 x2 : 0000000000000000 x1 : ffff000010772f8b x0 : ffffffffffffffff Process kmemleak (pid: 1408, stack limit = 0x(____ptrval____)) Call trace: page_mapping+0x24/0x144 __dump_page+0x34/0x3dc dump_page+0x28/0x4c kmemleak_scan+0x4ac/0x680 kmemleak_scan_thread+0xb4/0xdc kthread+0x12c/0x13c ret_from_fork+0x10/0x18 Code: d503201f f9400660 36000040 d1000413 (f9400661) ---[ end trace 4d4bd7f573490c8e ]--- Kernel panic - not syncing: Fatal exception SMP: stopping secondary CPUs Kernel Offset: disabled CPU features: 0x002,20000c38 Memory Limit: none ---[ end Kernel panic - not syncing: Fatal exception ]--- Link: http://lkml.kernel.org/r/20190122132916.28360-1-cai@lca.pw Fixes: 9f1eb38e0e11 ("mm, kmemleak: little optimization while scanning") Signed-off-by: Qian Cai Acked-by: Michal Hocko Cc: Oscar Salvador Cc: Catalin Marinas Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 07da5c6c5ba0..368267c1b71b 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -21,14 +21,16 @@ struct vmem_altmap; * walkers which rely on the fully initialized page->flags and others * should use this rather than pfn_valid && pfn_to_page */ -#define pfn_to_online_page(pfn) \ -({ \ - struct page *___page = NULL; \ - unsigned long ___nr = pfn_to_section_nr(pfn); \ - \ - if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr))\ - ___page = pfn_to_page(pfn); \ - ___page; \ +#define pfn_to_online_page(pfn) \ +({ \ + struct page *___page = NULL; \ + unsigned long ___pfn = pfn; \ + unsigned long ___nr = pfn_to_section_nr(___pfn); \ + \ + if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr) && \ + pfn_valid_within(___pfn)) \ + ___page = pfn_to_page(___pfn); \ + ___page; \ }) /* From cefc7ef3c87d02fc9307835868ff721ea12cc597 Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Fri, 1 Feb 2019 14:20:54 -0800 Subject: [PATCH 375/525] mm, oom: fix use-after-free in oom_kill_process Syzbot instance running on upstream kernel found a use-after-free bug in oom_kill_process. On further inspection it seems like the process selected to be oom-killed has exited even before reaching read_lock(&tasklist_lock) in oom_kill_process(). More specifically the tsk->usage is 1 which is due to get_task_struct() in oom_evaluate_task() and the put_task_struct within for_each_thread() frees the tsk and for_each_thread() tries to access the tsk. The easiest fix is to do get/put across the for_each_thread() on the selected task. Now the next question is should we continue with the oom-kill as the previously selected task has exited? However before adding more complexity and heuristics, let's answer why we even look at the children of oom-kill selected task? The select_bad_process() has already selected the worst process in the system/memcg. Due to race, the selected process might not be the worst at the kill time but does that matter? The userspace can use the oom_score_adj interface to prefer children to be killed before the parent. I looked at the history but it seems like this is there before git history. Link: http://lkml.kernel.org/r/20190121215850.221745-1-shakeelb@google.com Reported-by: syzbot+7fbbfa368521945f0e3d@syzkaller.appspotmail.com Fixes: 6b0c81b3be11 ("mm, oom: reduce dependency on tasklist_lock") Signed-off-by: Shakeel Butt Reviewed-by: Roman Gushchin Acked-by: Michal Hocko Cc: David Rientjes Cc: Johannes Weiner Cc: Tetsuo Handa Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/oom_kill.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 059e617a1847..26ea8636758f 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -975,6 +975,13 @@ static void oom_kill_process(struct oom_control *oc, const char *message) * still freeing memory. */ read_lock(&tasklist_lock); + + /* + * The task 'p' might have already exited before reaching here. The + * put_task_struct() will free task_struct 'p' while the loop still try + * to access the field of 'p', so, get an extra reference. + */ + get_task_struct(p); for_each_thread(p, t) { list_for_each_entry(child, &t->children, sibling) { unsigned int child_points; @@ -994,6 +1001,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message) } } } + put_task_struct(p); read_unlock(&tasklist_lock); /* From db7ddeab3ce5d64c9696e70d61f45ea9909cd196 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 1 Feb 2019 14:20:58 -0800 Subject: [PATCH 376/525] lib/test_kmod.c: potential double free in error handling There is a copy and paste bug so we set "config->test_driver" to NULL twice instead of setting "config->test_fs". Smatch complains that it leads to a double free: lib/test_kmod.c:840 __kmod_config_init() warn: 'config->test_fs' double freed Link: http://lkml.kernel.org/r/20190121140011.GA14283@kadam Fixes: d9c6a72d6fa2 ("kmod: add test driver to stress test the module loader") Signed-off-by: Dan Carpenter Acked-by: Luis Chamberlain Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/test_kmod.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/test_kmod.c b/lib/test_kmod.c index d82d022111e0..9cf77628fc91 100644 --- a/lib/test_kmod.c +++ b/lib/test_kmod.c @@ -632,7 +632,7 @@ static void __kmod_config_free(struct test_config *config) config->test_driver = NULL; kfree_const(config->test_fs); - config->test_driver = NULL; + config->test_fs = NULL; } static void kmod_config_free(struct kmod_test_device *test_dev) From 980768338488921b15c2f01d67f0324a48ef8625 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jonathan=20Neusch=C3=A4fer?= Date: Fri, 1 Feb 2019 14:21:01 -0800 Subject: [PATCH 377/525] init/Kconfig: fix grammar by moving a closing parenthesis MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Link: http://lkml.kernel.org/r/20190129150813.15785-1-j.neuschaefer@gmx.net Signed-off-by: Jonathan Neuschäfer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/init/Kconfig b/init/Kconfig index 513fa544a134..354146666d97 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -825,7 +825,7 @@ config CGROUP_PIDS PIDs controller is designed to stop this from happening. It should be noted that organisational operations (such as attaching - to a cgroup hierarchy will *not* be blocked by the PIDs controller), + to a cgroup hierarchy) will *not* be blocked by the PIDs controller, since the PIDs limit only affects a process's ability to fork, not to attach to a cgroup. From 0d0c8de8788b6c441ea01365612de7efc20cc682 Mon Sep 17 00:00:00 2001 From: Anders Roxell Date: Fri, 1 Feb 2019 14:21:05 -0800 Subject: [PATCH 378/525] kasan: mark file common so ftrace doesn't trace it When option CONFIG_KASAN is enabled toghether with ftrace, function ftrace_graph_caller() gets in to a recursion, via functions kasan_check_read() and kasan_check_write(). Breakpoint 2, ftrace_graph_caller () at ../arch/arm64/kernel/entry-ftrace.S:179 179 mcount_get_pc x0 // function's pc (gdb) bt #0 ftrace_graph_caller () at ../arch/arm64/kernel/entry-ftrace.S:179 #1 0xffffff90101406c8 in ftrace_caller () at ../arch/arm64/kernel/entry-ftrace.S:151 #2 0xffffff90106fd084 in kasan_check_write (p=0xffffffc06c170878, size=4) at ../mm/kasan/common.c:105 #3 0xffffff90104a2464 in atomic_add_return (v=, i=) at ./include/generated/atomic-instrumented.h:71 #4 atomic_inc_return (v=) at ./include/generated/atomic-fallback.h:284 #5 trace_graph_entry (trace=0xffffffc03f5ff380) at ../kernel/trace/trace_functions_graph.c:441 #6 0xffffff9010481774 in trace_graph_entry_watchdog (trace=) at ../kernel/trace/trace_selftest.c:741 #7 0xffffff90104a185c in function_graph_enter (ret=, func=, frame_pointer=18446743799894897728, retp=) at ../kernel/trace/trace_functions_graph.c:196 #8 0xffffff9010140628 in prepare_ftrace_return (self_addr=18446743592948977792, parent=0xffffffc03f5ff418, frame_pointer=18446743799894897728) at ../arch/arm64/kernel/ftrace.c:231 #9 0xffffff90101406f4 in ftrace_graph_caller () at ../arch/arm64/kernel/entry-ftrace.S:182 Backtrace stopped: previous frame identical to this frame (corrupt stack?) (gdb) Rework so that the kasan implementation isn't traced. Link: http://lkml.kernel.org/r/20181212183447.15890-1-anders.roxell@linaro.org Signed-off-by: Anders Roxell Acked-by: Dmitry Vyukov Tested-by: Dmitry Vyukov Acked-by: Steven Rostedt (VMware) Cc: Andrey Ryabinin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kasan/Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile index 0a14fcff70ed..e2bb06c1b45e 100644 --- a/mm/kasan/Makefile +++ b/mm/kasan/Makefile @@ -5,6 +5,7 @@ UBSAN_SANITIZE_generic.o := n UBSAN_SANITIZE_tags.o := n KCOV_INSTRUMENT := n +CFLAGS_REMOVE_common.o = -pg CFLAGS_REMOVE_generic.o = -pg # Function splitter causes unnecessary splits in __asan_load1/__asan_store1 # see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63533 From 6376360ecbe525a9c17b3d081dfd88ba3e4ed65b Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 1 Feb 2019 14:21:08 -0800 Subject: [PATCH 379/525] mm: hwpoison: use do_send_sig_info() instead of force_sig() Currently memory_failure() is racy against process's exiting, which results in kernel crash by null pointer dereference. The root cause is that memory_failure() uses force_sig() to forcibly kill asynchronous (meaning not in the current context) processes. As discussed in thread https://lkml.org/lkml/2010/6/8/236 years ago for OOM fixes, this is not a right thing to do. OOM solves this issue by using do_send_sig_info() as done in commit d2d393099de2 ("signal: oom_kill_task: use SEND_SIG_FORCED instead of force_sig()"), so this patch is suggesting to do the same for hwpoison. do_send_sig_info() properly accesses to siglock with lock_task_sighand(), so is free from the reported race. I confirmed that the reported bug reproduces with inserting some delay in kill_procs(), and it never reproduces with this patch. Note that memory_failure() can send another type of signal using force_sig_mceerr(), and the reported race shouldn't happen on it because force_sig_mceerr() is called only for synchronous processes (i.e. BUS_MCEERR_AR happens only when some process accesses to the corrupted memory.) Link: http://lkml.kernel.org/r/20190116093046.GA29835@hori1.linux.bs1.fc.nec.co.jp Signed-off-by: Naoya Horiguchi Reported-by: Jane Chu Reviewed-by: Dan Williams Reviewed-by: William Kucharski Cc: Oleg Nesterov Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 7c72f2a95785..831be5ff5f4d 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -372,7 +372,8 @@ static void kill_procs(struct list_head *to_kill, int forcekill, bool fail, if (fail || tk->addr_valid == 0) { pr_err("Memory failure: %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n", pfn, tk->tsk->comm, tk->tsk->pid); - force_sig(SIGKILL, tk->tsk); + do_send_sig_info(SIGKILL, SEND_SIG_PRIV, + tk->tsk, PIDTYPE_PID); } /* From e3df4c6e4836ce93cd5cf92d9cbdeaf4439a0241 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 1 Feb 2019 14:21:12 -0800 Subject: [PATCH 380/525] mm, memory_hotplug: __offline_pages fix wrong locking Jan has noticed that we do double unlock on some failure paths when offlining a page range. This is indeed the case when test_pages_in_a_zone respp. start_isolate_page_range fail. This was an omission when forward porting the debugging patch from an older kernel. Fix the issue by dropping mem_hotplug_done from the failure condition and keeping the single unlock in the catch all failure path. Link: http://lkml.kernel.org/r/20190115120307.22768-1-mhocko@kernel.org Fixes: 7960509329c2 ("mm, memory_hotplug: print reason for the offlining failure") Signed-off-by: Michal Hocko Reported-by: Jan Kara Reviewed-by: Jan Kara Tested-by: Jan Kara Reviewed-by: Oscar Salvador Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index a0130633a6e1..124e794867c5 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1570,7 +1570,6 @@ static int __ref __offline_pages(unsigned long start_pfn, we assume this for now. .*/ if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end)) { - mem_hotplug_done(); ret = -EINVAL; reason = "multizone range"; goto failed_removal; @@ -1585,7 +1584,6 @@ static int __ref __offline_pages(unsigned long start_pfn, MIGRATE_MOVABLE, SKIP_HWPOISON | REPORT_FAILURE); if (ret) { - mem_hotplug_done(); reason = "failure to isolate range"; goto failed_removal; } From 7b2489d37e1e355228f7c55724f77580e1dec22a Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 1 Feb 2019 14:21:15 -0800 Subject: [PATCH 381/525] psi: clarify the Kconfig text for the default-disable option The current help text caused some confusion in online forums about whether or not to default-enable or default-disable psi in vendor kernels. This is because it doesn't communicate the reason for why we made this setting configurable in the first place: that the overhead is non-zero in an artificial scheduler stress test. Since this isn't representative of real workloads, and the effect was not measurable in scheduler-heavy real world applications such as the webservers and memcache installations at Facebook, it's fair to point out that this is a pretty cautious option to select. Link: http://lkml.kernel.org/r/20190129233617.16767-1-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Reviewed-by: Andrew Morton Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/Kconfig | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/init/Kconfig b/init/Kconfig index 354146666d97..c9386a365eea 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -512,6 +512,17 @@ config PSI_DEFAULT_DISABLED per default but can be enabled through passing psi=1 on the kernel commandline during boot. + This feature adds some code to the task wakeup and sleep + paths of the scheduler. The overhead is too low to affect + common scheduling-intense workloads in practice (such as + webservers, memcache), but it does show up in artificial + scheduler stress tests, such as hackbench. + + If you are paranoid and not sure what the kernel will be + used for, say Y. + + Say N if unsure. + endmenu # "CPU/Task time and stats accounting" config CPU_ISOLATION From e0a352fabce61f730341d119fbedf71ffdb8663f Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 1 Feb 2019 14:21:19 -0800 Subject: [PATCH 382/525] mm: migrate: don't rely on __PageMovable() of newpage after unlocking it We had a race in the old balloon compaction code before b1123ea6d3b3 ("mm: balloon: use general non-lru movable page feature") refactored it that became visible after backporting 195a8c43e93d ("virtio-balloon: deflate via a page list") without the refactoring. The bug existed from commit d6d86c0a7f8d ("mm/balloon_compaction: redesign ballooned pages management") till b1123ea6d3b3 ("mm: balloon: use general non-lru movable page feature"). d6d86c0a7f8d ("mm/balloon_compaction: redesign ballooned pages management") was backported to 3.12, so the broken kernels are stable kernels [3.12 - 4.7]. There was a subtle race between dropping the page lock of the newpage in __unmap_and_move() and checking for __is_movable_balloon_page(newpage). Just after dropping this page lock, virtio-balloon could go ahead and deflate the newpage, effectively dequeueing it and clearing PageBalloon, in turn making __is_movable_balloon_page(newpage) fail. This resulted in dropping the reference of the newpage via putback_lru_page(newpage) instead of put_page(newpage), leading to page->lru getting modified and a !LRU page ending up in the LRU lists. With 195a8c43e93d ("virtio-balloon: deflate via a page list") backported, one would suddenly get corrupted lists in release_pages_balloon(): - WARNING: CPU: 13 PID: 6586 at lib/list_debug.c:59 __list_del_entry+0xa1/0xd0 - list_del corruption. prev->next should be ffffe253961090a0, but was dead000000000100 Nowadays this race is no longer possible, but it is hidden behind very ugly handling of __ClearPageMovable() and __PageMovable(). __ClearPageMovable() will not make __PageMovable() fail, only PageMovable(). So the new check (__PageMovable(newpage)) will still hold even after newpage was dequeued by virtio-balloon. If anybody would ever change that special handling, the BUG would be introduced again. So instead, make it explicit and use the information of the original isolated page before migration. This patch can be backported fairly easy to stable kernels (in contrast to the refactoring). Link: http://lkml.kernel.org/r/20190129233217.10747-1-david@redhat.com Fixes: d6d86c0a7f8d ("mm/balloon_compaction: redesign ballooned pages management") Signed-off-by: David Hildenbrand Reported-by: Vratislav Bendel Acked-by: Michal Hocko Acked-by: Rafael Aquini Cc: Mel Gorman Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Naoya Horiguchi Cc: Jan Kara Cc: Andrea Arcangeli Cc: Dominik Brodowski Cc: Matthew Wilcox Cc: Vratislav Bendel Cc: Rafael Aquini Cc: Konstantin Khlebnikov Cc: Minchan Kim Cc: [3.12 - 4.7] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/migrate.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/mm/migrate.c b/mm/migrate.c index 712b231a7376..d4fd680be3b0 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1130,10 +1130,13 @@ out: * If migration is successful, decrease refcount of the newpage * which will not free the page because new page owner increased * refcounter. As well, if it is LRU page, add the page to LRU - * list in here. + * list in here. Use the old state of the isolated source page to + * determine if we migrated a LRU page. newpage was already unlocked + * and possibly modified by its owner - don't rely on the page + * state. */ if (rc == MIGRATEPAGE_SUCCESS) { - if (unlikely(__PageMovable(newpage))) + if (unlikely(!is_lru)) put_page(newpage); else putback_lru_page(newpage); From c27d82f52f75fc9d8d9d40d120d2a96fdeeada5e Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 1 Feb 2019 14:21:23 -0800 Subject: [PATCH 383/525] fs/drop_caches.c: avoid softlockups in drop_pagecache_sb() When superblock has lots of inodes without any pagecache (like is the case for /proc), drop_pagecache_sb() will iterate through all of them without dropping sb->s_inode_list_lock which can lead to softlockups (one of our customers hit this). Fix the problem by going to the slow path and doing cond_resched() in case the process needs rescheduling. Link: http://lkml.kernel.org/r/20190114085343.15011-1-jack@suse.cz Signed-off-by: Jan Kara Acked-by: Michal Hocko Reviewed-by: Andrew Morton Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/drop_caches.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/drop_caches.c b/fs/drop_caches.c index 82377017130f..d31b6c72b476 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -21,8 +21,13 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused) spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { spin_lock(&inode->i_lock); + /* + * We must skip inodes in unusual state. We may also skip + * inodes without pages but we deliberately won't in case + * we need to reschedule to avoid softlockups. + */ if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) || - (inode->i_mapping->nrpages == 0)) { + (inode->i_mapping->nrpages == 0 && !need_resched())) { spin_unlock(&inode->i_lock); continue; } @@ -30,6 +35,7 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused) spin_unlock(&inode->i_lock); spin_unlock(&sb->s_inode_list_lock); + cond_resched(); invalidate_mapping_pages(inode->i_mapping, 0, -1); iput(toput_inode); toput_inode = inode; From 63ce5f552beb9bdb41546b3a26c4374758b21815 Mon Sep 17 00:00:00 2001 From: Pan Bian Date: Fri, 1 Feb 2019 14:21:26 -0800 Subject: [PATCH 384/525] autofs: drop dentry reference only when it is never used autofs_expire_run() calls dput(dentry) to drop the reference count of dentry. However, dentry is read via autofs_dentry_ino(dentry) after that. This may result in a use-free-bug. The patch drops the reference count of dentry only when it is never used. Link: http://lkml.kernel.org/r/154725122396.11260.16053424107144453867.stgit@pluto-themaw-net Signed-off-by: Pan Bian Signed-off-by: Ian Kent Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/autofs/expire.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/autofs/expire.c b/fs/autofs/expire.c index d441244b79df..28d9c2b1b3bb 100644 --- a/fs/autofs/expire.c +++ b/fs/autofs/expire.c @@ -596,7 +596,6 @@ int autofs_expire_run(struct super_block *sb, pkt.len = dentry->d_name.len; memcpy(pkt.name, dentry->d_name.name, pkt.len); pkt.name[pkt.len] = '\0'; - dput(dentry); if (copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire))) ret = -EFAULT; @@ -609,6 +608,8 @@ int autofs_expire_run(struct super_block *sb, complete_all(&ino->expire_complete); spin_unlock(&sbi->fs_lock); + dput(dentry); + return ret; } From f585b283e3f025754c45bbe7533fc6e5c4643700 Mon Sep 17 00:00:00 2001 From: Ian Kent Date: Fri, 1 Feb 2019 14:21:29 -0800 Subject: [PATCH 385/525] autofs: fix error return in autofs_fill_super() In autofs_fill_super() on error of get inode/make root dentry the return should be ENOMEM as this is the only failure case of the called functions. Link: http://lkml.kernel.org/r/154725123240.11260.796773942606871359.stgit@pluto-themaw-net Signed-off-by: Ian Kent Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/autofs/inode.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c index 0e8ea2d9a2bb..078992eee299 100644 --- a/fs/autofs/inode.c +++ b/fs/autofs/inode.c @@ -266,8 +266,10 @@ int autofs_fill_super(struct super_block *s, void *data, int silent) } root_inode = autofs_get_inode(s, S_IFDIR | 0755); root = d_make_root(root_inode); - if (!root) + if (!root) { + ret = -ENOMEM; goto fail_ino; + } pipe = NULL; root->d_fsdata = ino; From e6d429313ea5c776d2e76b4494df69102e6b7115 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 29 Jan 2019 17:44:36 -0500 Subject: [PATCH 386/525] x86/resctrl: Avoid confusion over the new X86_RESCTRL config "Resource Control" is a very broad term for this CPU feature, and a term that is also associated with containers, cgroups etc. This can easily cause confusion. Make the user prompt more specific. Match the config symbol name. [ bp: In the future, the corresponding ARM arch-specific code will be under ARM_CPU_RESCTRL and the arch-agnostic bits will be carved out under the CPU_RESCTRL umbrella symbol. ] Signed-off-by: Johannes Weiner Signed-off-by: Borislav Petkov Cc: Babu Moger Cc: Fenghua Yu Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: James Morse Cc: Jonathan Corbet Cc: "Kirill A. Shutemov" Cc: linux-doc@vger.kernel.org Cc: Peter Zijlstra Cc: Pu Wen Cc: Reinette Chatre Cc: Thomas Gleixner Cc: Tony Luck Cc: x86-ml Link: https://lkml.kernel.org/r/20190130195621.GA30653@cmpxchg.org --- Documentation/x86/resctrl_ui.txt | 2 +- arch/x86/Kconfig | 6 +++--- arch/x86/include/asm/resctrl_sched.h | 4 ++-- arch/x86/kernel/cpu/Makefile | 2 +- arch/x86/kernel/cpu/resctrl/Makefile | 4 ++-- include/linux/sched.h | 2 +- 6 files changed, 10 insertions(+), 10 deletions(-) diff --git a/Documentation/x86/resctrl_ui.txt b/Documentation/x86/resctrl_ui.txt index e8e8d14d3c4e..c1f95b59e14d 100644 --- a/Documentation/x86/resctrl_ui.txt +++ b/Documentation/x86/resctrl_ui.txt @@ -9,7 +9,7 @@ Fenghua Yu Tony Luck Vikas Shivappa -This feature is enabled by the CONFIG_X86_RESCTRL and the x86 /proc/cpuinfo +This feature is enabled by the CONFIG_X86_CPU_RESCTRL and the x86 /proc/cpuinfo flag bits: RDT (Resource Director Technology) Allocation - "rdt_a" CAT (Cache Allocation Technology) - "cat_l3", "cat_l2" diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 26387c7bf305..68261430fe6e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -446,12 +446,12 @@ config RETPOLINE branches. Requires a compiler with -mindirect-branch=thunk-extern support for full protection. The kernel may run slower. -config X86_RESCTRL - bool "Resource Control support" +config X86_CPU_RESCTRL + bool "x86 CPU resource control support" depends on X86 && (CPU_SUP_INTEL || CPU_SUP_AMD) select KERNFS help - Enable Resource Control support. + Enable x86 CPU resource control support. Provide support for the allocation and monitoring of system resources usage by the CPU. diff --git a/arch/x86/include/asm/resctrl_sched.h b/arch/x86/include/asm/resctrl_sched.h index 40ebddde6ac2..f6b7fe2833cc 100644 --- a/arch/x86/include/asm/resctrl_sched.h +++ b/arch/x86/include/asm/resctrl_sched.h @@ -2,7 +2,7 @@ #ifndef _ASM_X86_RESCTRL_SCHED_H #define _ASM_X86_RESCTRL_SCHED_H -#ifdef CONFIG_X86_RESCTRL +#ifdef CONFIG_X86_CPU_RESCTRL #include #include @@ -88,6 +88,6 @@ static inline void resctrl_sched_in(void) static inline void resctrl_sched_in(void) {} -#endif /* CONFIG_X86_RESCTRL */ +#endif /* CONFIG_X86_CPU_RESCTRL */ #endif /* _ASM_X86_RESCTRL_SCHED_H */ diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index b6fa0869f7aa..cfd24f9f7614 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -39,7 +39,7 @@ obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o obj-$(CONFIG_X86_MCE) += mce/ obj-$(CONFIG_MTRR) += mtrr/ obj-$(CONFIG_MICROCODE) += microcode/ -obj-$(CONFIG_X86_RESCTRL) += resctrl/ +obj-$(CONFIG_X86_CPU_RESCTRL) += resctrl/ obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o diff --git a/arch/x86/kernel/cpu/resctrl/Makefile b/arch/x86/kernel/cpu/resctrl/Makefile index 1cabe6fd8e11..4a06c37b9cf1 100644 --- a/arch/x86/kernel/cpu/resctrl/Makefile +++ b/arch/x86/kernel/cpu/resctrl/Makefile @@ -1,4 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_X86_RESCTRL) += core.o rdtgroup.o monitor.o -obj-$(CONFIG_X86_RESCTRL) += ctrlmondata.o pseudo_lock.o +obj-$(CONFIG_X86_CPU_RESCTRL) += core.o rdtgroup.o monitor.o +obj-$(CONFIG_X86_CPU_RESCTRL) += ctrlmondata.o pseudo_lock.o CFLAGS_pseudo_lock.o = -I$(src) diff --git a/include/linux/sched.h b/include/linux/sched.h index 224666226e87..8c328b14c424 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -995,7 +995,7 @@ struct task_struct { /* cg_list protected by css_set_lock and tsk->alloc_lock: */ struct list_head cg_list; #endif -#ifdef CONFIG_X86_RESCTRL +#ifdef CONFIG_X86_CPU_RESCTRL u32 closid; u32 rmid; #endif From dc3f595b6617ebc0307e0ce151e8f2f2b2489b95 Mon Sep 17 00:00:00 2001 From: Codrin Ciubotariu Date: Wed, 23 Jan 2019 16:33:47 +0000 Subject: [PATCH 387/525] dmaengine: at_xdmac: Fix wrongfull report of a channel as in use atchan->status variable is used to store two different information: - pass channel interrupts status from interrupt handler to tasklet; - channel information like whether it is cyclic or paused; This causes a bug when device_terminate_all() is called, (AT_XDMAC_CHAN_IS_CYCLIC cleared on atchan->status) and then a late End of Block interrupt arrives (AT_XDMAC_CIS_BIS), which sets bit 0 of atchan->status. Bit 0 is also used for AT_XDMAC_CHAN_IS_CYCLIC, so when a new descriptor for a cyclic transfer is created, the driver reports the channel as in use: if (test_and_set_bit(AT_XDMAC_CHAN_IS_CYCLIC, &atchan->status)) { dev_err(chan2dev(chan), "channel currently used\n"); return NULL; } This patch fixes the bug by adding a different struct member to keep the interrupts status separated from the channel status bits. Fixes: e1f7c9eee707 ("dmaengine: at_xdmac: creation of the atmel eXtended DMA Controller driver") Signed-off-by: Codrin Ciubotariu Acked-by: Ludovic Desroches Signed-off-by: Vinod Koul --- drivers/dma/at_xdmac.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 4e557684f792..fe69dccfa0c0 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -203,6 +203,7 @@ struct at_xdmac_chan { u32 save_cim; u32 save_cnda; u32 save_cndc; + u32 irq_status; unsigned long status; struct tasklet_struct tasklet; struct dma_slave_config sconfig; @@ -1580,8 +1581,8 @@ static void at_xdmac_tasklet(unsigned long data) struct at_xdmac_desc *desc; u32 error_mask; - dev_dbg(chan2dev(&atchan->chan), "%s: status=0x%08lx\n", - __func__, atchan->status); + dev_dbg(chan2dev(&atchan->chan), "%s: status=0x%08x\n", + __func__, atchan->irq_status); error_mask = AT_XDMAC_CIS_RBEIS | AT_XDMAC_CIS_WBEIS @@ -1589,15 +1590,15 @@ static void at_xdmac_tasklet(unsigned long data) if (at_xdmac_chan_is_cyclic(atchan)) { at_xdmac_handle_cyclic(atchan); - } else if ((atchan->status & AT_XDMAC_CIS_LIS) - || (atchan->status & error_mask)) { + } else if ((atchan->irq_status & AT_XDMAC_CIS_LIS) + || (atchan->irq_status & error_mask)) { struct dma_async_tx_descriptor *txd; - if (atchan->status & AT_XDMAC_CIS_RBEIS) + if (atchan->irq_status & AT_XDMAC_CIS_RBEIS) dev_err(chan2dev(&atchan->chan), "read bus error!!!"); - if (atchan->status & AT_XDMAC_CIS_WBEIS) + if (atchan->irq_status & AT_XDMAC_CIS_WBEIS) dev_err(chan2dev(&atchan->chan), "write bus error!!!"); - if (atchan->status & AT_XDMAC_CIS_ROIS) + if (atchan->irq_status & AT_XDMAC_CIS_ROIS) dev_err(chan2dev(&atchan->chan), "request overflow error!!!"); spin_lock(&atchan->lock); @@ -1652,7 +1653,7 @@ static irqreturn_t at_xdmac_interrupt(int irq, void *dev_id) atchan = &atxdmac->chan[i]; chan_imr = at_xdmac_chan_read(atchan, AT_XDMAC_CIM); chan_status = at_xdmac_chan_read(atchan, AT_XDMAC_CIS); - atchan->status = chan_status & chan_imr; + atchan->irq_status = chan_status & chan_imr; dev_vdbg(atxdmac->dma.dev, "%s: chan%d: imr=0x%x, status=0x%x\n", __func__, i, chan_imr, chan_status); @@ -1666,7 +1667,7 @@ static irqreturn_t at_xdmac_interrupt(int irq, void *dev_id) at_xdmac_chan_read(atchan, AT_XDMAC_CDA), at_xdmac_chan_read(atchan, AT_XDMAC_CUBC)); - if (atchan->status & (AT_XDMAC_CIS_RBEIS | AT_XDMAC_CIS_WBEIS)) + if (atchan->irq_status & (AT_XDMAC_CIS_RBEIS | AT_XDMAC_CIS_WBEIS)) at_xdmac_write(atxdmac, AT_XDMAC_GD, atchan->mask); tasklet_schedule(&atchan->tasklet); From 74c953ca5f6b4d5f1daa1ef34f4317e15c1a2987 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Sat, 2 Feb 2019 10:50:17 +0100 Subject: [PATCH 388/525] efi/arm64: Fix debugfs crash by adding a terminator for ptdump marker When reading 'efi_page_tables' debugfs triggers an out-of-bounds access here: arch/arm64/mm/dump.c: 282 if (addr >= st->marker[1].start_address) { called from: arch/arm64/mm/dump.c: 331 note_page(st, addr, 2, pud_val(pud)); because st->marker++ is is called after "UEFI runtime end" which is the last element in addr_marker[]. Therefore, add a terminator like the one for kernel_page_tables, so it can be skipped to print out non-existent markers. Here's the KASAN bug report: # cat /sys/kernel/debug/efi_page_tables ---[ UEFI runtime start ]--- 0x0000000020000000-0x0000000020010000 64K PTE RW NX SHD AF ... 0x0000000020200000-0x0000000021340000 17664K PTE RW NX SHD AF ... ... 0x0000000021920000-0x0000000021950000 192K PTE RW x SHD AF ... 0x0000000021950000-0x00000000219a0000 320K PTE RW NX SHD AF ... ---[ UEFI runtime end ]--- ---[ (null) ]--- ---[ (null) ]--- BUG: KASAN: global-out-of-bounds in note_page+0x1f0/0xac0 Read of size 8 at addr ffff2000123f2ac0 by task read_all/42464 Call trace: dump_backtrace+0x0/0x298 show_stack+0x24/0x30 dump_stack+0xb0/0xdc print_address_description+0x64/0x2b0 kasan_report+0x150/0x1a4 __asan_report_load8_noabort+0x30/0x3c note_page+0x1f0/0xac0 walk_pgd+0xb4/0x244 ptdump_walk_pgd+0xec/0x140 ptdump_show+0x40/0x50 seq_read+0x3f8/0xad0 full_proxy_read+0x9c/0xc0 __vfs_read+0xfc/0x4c8 vfs_read+0xec/0x208 ksys_read+0xd0/0x15c __arm64_sys_read+0x84/0x94 el0_svc_handler+0x258/0x304 el0_svc+0x8/0xc The buggy address belongs to the variable: __compound_literal.0+0x20/0x800 Memory state around the buggy address: ffff2000123f2980: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff2000123f2a00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 fa >ffff2000123f2a80: fa fa fa fa 00 00 00 00 fa fa fa fa 00 00 00 00 ^ ffff2000123f2b00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff2000123f2b80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 0 [ ardb: fix up whitespace ] [ mingo: fix up some moar ] Signed-off-by: Qian Cai Signed-off-by: Ard Biesheuvel Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Fixes: 9d80448ac92b ("efi/arm64: Add debugfs node to dump UEFI runtime page tables") Link: http://lkml.kernel.org/r/20190202095017.13799-2-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar --- drivers/firmware/efi/arm-runtime.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c index 23ea1ed409d1..352bd2473162 100644 --- a/drivers/firmware/efi/arm-runtime.c +++ b/drivers/firmware/efi/arm-runtime.c @@ -37,8 +37,9 @@ extern u64 efi_system_table; static struct ptdump_info efi_ptdump_info = { .mm = &efi_mm, .markers = (struct addr_marker[]){ - { 0, "UEFI runtime start" }, - { DEFAULT_MAP_WINDOW_64, "UEFI runtime end" } + { 0, "UEFI runtime start" }, + { DEFAULT_MAP_WINDOW_64, "UEFI runtime end" }, + { -1, NULL } }, .base_addr = 0, }; From c14f07c6211cc01d52ed92cce1fade5071b8d197 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 31 Jan 2019 16:59:46 +0000 Subject: [PATCH 389/525] Revert "net: phy: marvell: avoid pause mode on SGMII-to-Copper for 88e151x" This reverts commit 6623c0fba10ef45b64ca213ad5dec926f37fa9a0. The original diagnosis was incorrect: it appears that the NIC had PHY polling mode enabled, which meant that it overwrote the PHYs advertisement register during negotiation. Signed-off-by: Russell King Tested-by: Yonglong Liu Signed-off-by: David S. Miller --- drivers/net/phy/marvell.c | 16 ---------------- 1 file changed, 16 deletions(-) diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 2e12f982534f..abb7876a8776 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -847,7 +847,6 @@ static int m88e1510_config_init(struct phy_device *phydev) /* SGMII-to-Copper mode initialization */ if (phydev->interface == PHY_INTERFACE_MODE_SGMII) { - /* Select page 18 */ err = marvell_set_page(phydev, 18); if (err < 0) @@ -870,21 +869,6 @@ static int m88e1510_config_init(struct phy_device *phydev) err = marvell_set_page(phydev, MII_MARVELL_COPPER_PAGE); if (err < 0) return err; - - /* There appears to be a bug in the 88e1512 when used in - * SGMII to copper mode, where the AN advertisement register - * clears the pause bits each time a negotiation occurs. - * This means we can never be truely sure what was advertised, - * so disable Pause support. - */ - linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, - phydev->supported); - linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT, - phydev->supported); - linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, - phydev->advertising); - linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT, - phydev->advertising); } return m88e1318_config_init(phydev); From d28af26faa0b1daf3c692603d46bc4687c16f19e Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Thu, 31 Jan 2019 16:33:41 -0800 Subject: [PATCH 390/525] x86/MCE: Initialize mce.bank in the case of a fatal error in mce_no_way_out() Internal injection testing crashed with a console log that said: mce: [Hardware Error]: CPU 7: Machine Check Exception: f Bank 0: bd80000000100134 This caused a lot of head scratching because the MCACOD (bits 15:0) of that status is a signature from an L1 data cache error. But Linux says that it found it in "Bank 0", which on this model CPU only reports L1 instruction cache errors. The answer was that Linux doesn't initialize "m->bank" in the case that it finds a fatal error in the mce_no_way_out() pre-scan of banks. If this was a local machine check, then this partially initialized struct mce is being passed to mce_panic(). Fix is simple: just initialize m->bank in the case of a fatal error. Fixes: 40c36e2741d7 ("x86/mce: Fix incorrect "Machine check from unknown source" message") Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Vishal Verma Cc: x86-ml Cc: stable@vger.kernel.org # v4.18 Note pre-v5.0 arch/x86/kernel/cpu/mce/core.c was called arch/x86/kernel/cpu/mcheck/mce.c Link: https://lkml.kernel.org/r/20190201003341.10638-1-tony.luck@intel.com --- arch/x86/kernel/cpu/mce/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 672c7225cb1b..6ce290c506d9 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -784,6 +784,7 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, quirk_no_way_out(i, m, regs); if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) { + m->bank = i; mce_read_aux(m, i); *msg = tmp; return 1; From 22b5c0b63f32568e130fa2df4ba23efce3eb495b Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Fri, 1 Feb 2019 12:42:06 +0100 Subject: [PATCH 391/525] vsock/virtio: fix kernel panic after device hot-unplug virtio_vsock_remove() invokes the vsock_core_exit() also if there are opened sockets for the AF_VSOCK protocol family. In this way the vsock "transport" pointer is set to NULL, triggering the kernel panic at the first socket activity. This patch move the vsock_core_init()/vsock_core_exit() in the virtio_vsock respectively in module_init and module_exit functions, that cannot be invoked until there are open sockets. Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1609699 Reported-by: Yan Fu Signed-off-by: Stefano Garzarella Acked-by: Stefan Hajnoczi Signed-off-by: David S. Miller --- net/vmw_vsock/virtio_transport.c | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-) diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 5d3cce9e8744..9dae54698737 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -75,6 +75,9 @@ static u32 virtio_transport_get_local_cid(void) { struct virtio_vsock *vsock = virtio_vsock_get(); + if (!vsock) + return VMADDR_CID_ANY; + return vsock->guest_cid; } @@ -584,10 +587,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev) virtio_vsock_update_guest_cid(vsock); - ret = vsock_core_init(&virtio_transport.transport); - if (ret < 0) - goto out_vqs; - vsock->rx_buf_nr = 0; vsock->rx_buf_max_nr = 0; atomic_set(&vsock->queued_replies, 0); @@ -618,8 +617,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev) mutex_unlock(&the_virtio_vsock_mutex); return 0; -out_vqs: - vsock->vdev->config->del_vqs(vsock->vdev); out: kfree(vsock); mutex_unlock(&the_virtio_vsock_mutex); @@ -669,7 +666,6 @@ static void virtio_vsock_remove(struct virtio_device *vdev) mutex_lock(&the_virtio_vsock_mutex); the_virtio_vsock = NULL; - vsock_core_exit(); mutex_unlock(&the_virtio_vsock_mutex); vdev->config->del_vqs(vdev); @@ -702,14 +698,28 @@ static int __init virtio_vsock_init(void) virtio_vsock_workqueue = alloc_workqueue("virtio_vsock", 0, 0); if (!virtio_vsock_workqueue) return -ENOMEM; + ret = register_virtio_driver(&virtio_vsock_driver); if (ret) - destroy_workqueue(virtio_vsock_workqueue); + goto out_wq; + + ret = vsock_core_init(&virtio_transport.transport); + if (ret) + goto out_vdr; + + return 0; + +out_vdr: + unregister_virtio_driver(&virtio_vsock_driver); +out_wq: + destroy_workqueue(virtio_vsock_workqueue); return ret; + } static void __exit virtio_vsock_exit(void) { + vsock_core_exit(); unregister_virtio_driver(&virtio_vsock_driver); destroy_workqueue(virtio_vsock_workqueue); } From 85965487abc540368393a15491e6e7fcd230039d Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Fri, 1 Feb 2019 12:42:07 +0100 Subject: [PATCH 392/525] vsock/virtio: reset connected sockets on device removal When the virtio transport device disappear, we should reset all connected sockets in order to inform the users. Signed-off-by: Stefano Garzarella Reviewed-by: Stefan Hajnoczi Signed-off-by: David S. Miller --- net/vmw_vsock/virtio_transport.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 9dae54698737..15eb5d3d4750 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -634,6 +634,9 @@ static void virtio_vsock_remove(struct virtio_device *vdev) flush_work(&vsock->event_work); flush_work(&vsock->send_pkt_work); + /* Reset all connected sockets when the device disappear */ + vsock_for_each_connected_socket(virtio_vsock_reset_sock); + vdev->config->reset(vdev); mutex_lock(&vsock->rx_lock); From 8dfb8d2cceb76b74ad5b58cc65c75994329b4d5e Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 1 Feb 2019 13:23:38 -0800 Subject: [PATCH 393/525] net: systemport: Fix WoL with password after deep sleep Broadcom STB chips support a deep sleep mode where all register contents are lost. Because we were stashing the MagicPacket password into some of these registers a suspend into that deep sleep then a resumption would not lead to being able to wake-up from MagicPacket with password again. Fix this by keeping a software copy of the password and program it during suspend. Fixes: 83e82f4c706b ("net: systemport: add Wake-on-LAN support") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bcmsysport.c | 25 +++++++++------------- drivers/net/ethernet/broadcom/bcmsysport.h | 2 ++ 2 files changed, 12 insertions(+), 15 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index f9521d0274b7..28c9b0bdf2f6 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -520,7 +520,6 @@ static void bcm_sysport_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) { struct bcm_sysport_priv *priv = netdev_priv(dev); - u32 reg; wol->supported = WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER; wol->wolopts = priv->wolopts; @@ -528,11 +527,7 @@ static void bcm_sysport_get_wol(struct net_device *dev, if (!(priv->wolopts & WAKE_MAGICSECURE)) return; - /* Return the programmed SecureOn password */ - reg = umac_readl(priv, UMAC_PSW_MS); - put_unaligned_be16(reg, &wol->sopass[0]); - reg = umac_readl(priv, UMAC_PSW_LS); - put_unaligned_be32(reg, &wol->sopass[2]); + memcpy(wol->sopass, priv->sopass, sizeof(priv->sopass)); } static int bcm_sysport_set_wol(struct net_device *dev, @@ -548,13 +543,8 @@ static int bcm_sysport_set_wol(struct net_device *dev, if (wol->wolopts & ~supported) return -EINVAL; - /* Program the SecureOn password */ - if (wol->wolopts & WAKE_MAGICSECURE) { - umac_writel(priv, get_unaligned_be16(&wol->sopass[0]), - UMAC_PSW_MS); - umac_writel(priv, get_unaligned_be32(&wol->sopass[2]), - UMAC_PSW_LS); - } + if (wol->wolopts & WAKE_MAGICSECURE) + memcpy(priv->sopass, wol->sopass, sizeof(priv->sopass)); /* Flag the device and relevant IRQ as wakeup capable */ if (wol->wolopts) { @@ -2649,13 +2639,18 @@ static int bcm_sysport_suspend_to_wol(struct bcm_sysport_priv *priv) unsigned int index, i = 0; u32 reg; - /* Password has already been programmed */ reg = umac_readl(priv, UMAC_MPD_CTRL); if (priv->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE)) reg |= MPD_EN; reg &= ~PSW_EN; - if (priv->wolopts & WAKE_MAGICSECURE) + if (priv->wolopts & WAKE_MAGICSECURE) { + /* Program the SecureOn password */ + umac_writel(priv, get_unaligned_be16(&priv->sopass[0]), + UMAC_PSW_MS); + umac_writel(priv, get_unaligned_be32(&priv->sopass[2]), + UMAC_PSW_LS); reg |= PSW_EN; + } umac_writel(priv, reg, UMAC_MPD_CTRL); if (priv->wolopts & WAKE_FILTER) { diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h index 0887e6356649..0b192fea9c5d 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.h +++ b/drivers/net/ethernet/broadcom/bcmsysport.h @@ -12,6 +12,7 @@ #define __BCM_SYSPORT_H #include +#include #include #include @@ -778,6 +779,7 @@ struct bcm_sysport_priv { unsigned int crc_fwd:1; u16 rev; u32 wolopts; + u8 sopass[SOPASS_MAX]; unsigned int wol_irq_disabled:1; /* MIB related fields */ From 8c22d81d55353209f8976074ffa9fb1085da0830 Mon Sep 17 00:00:00 2001 From: Siva Rebbagondla Date: Fri, 1 Feb 2019 16:35:20 +0530 Subject: [PATCH 394/525] MAINTAINERS: add entry for redpine wireless driver Create an entry for Redpine wireless driver and add Amit and myself as maintainers. Signed-off-by: Siva Rebbagondla Signed-off-by: Kalle Valo --- MAINTAINERS | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 32d444476a90..1043125a52b6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -12864,6 +12864,13 @@ F: Documentation/devicetree/bindings/net/dsa/realtek-smi.txt F: drivers/net/dsa/realtek-smi* F: drivers/net/dsa/rtl83* +REDPINE WIRELESS DRIVER +M: Amitkumar Karwar +M: Siva Rebbagondla +L: linux-wireless@vger.kernel.org +S: Maintained +F: drivers/net/wireless/rsi/ + REGISTER MAP ABSTRACTION M: Mark Brown L: linux-kernel@vger.kernel.org From 8834f5600cf3c8db365e18a3d5cac2c2780c81e5 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 3 Feb 2019 13:48:04 -0800 Subject: [PATCH 395/525] Linux 5.0-rc5 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 141653226f3c..3142e67d03f1 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 0 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc5 NAME = Shy Crocodile # *DOCUMENTATION* From aa6ee4ab69293969867ab09b57546d226ace3d7a Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Fri, 1 Feb 2019 09:36:36 -0800 Subject: [PATCH 396/525] xfs: eof trim writeback mapping as soon as it is cached The cached writeback mapping is EOF trimmed to try and avoid races between post-eof block management and writeback that result in sending cached data to a stale location. The cached mapping is currently trimmed on the validation check, which leaves a race window between the time the mapping is cached and when it is trimmed against the current inode size. For example, if a new mapping is cached by delalloc conversion on a blocksize == page size fs, we could cycle various locks, perform memory allocations, etc. in the writeback codepath before the associated mapping is eventually trimmed to i_size. This leaves enough time for a post-eof truncate and file append before the cached mapping is trimmed. The former event essentially invalidates a range of the cached mapping and the latter bumps the inode size such the trim on the next writepage event won't trim all of the invalid blocks. fstest generic/464 reproduces this scenario occasionally and causes a lost writeback and stale delalloc blocks warning on inode inactivation. To work around this problem, trim the cached writeback mapping as soon as it is cached in addition to on subsequent validation checks. This is a minor tweak to tighten the race window as much as possible until a proper invalidation mechanism is available. Fixes: 40214d128e07 ("xfs: trim writepage mapping to within eof") Cc: # v4.14+ Signed-off-by: Brian Foster Reviewed-by: Allison Henderson Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_aops.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 338b9d9984e0..d9048bcea49c 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -449,6 +449,7 @@ xfs_map_blocks( } wpc->imap = imap; + xfs_trim_extent_eof(&wpc->imap, ip); trace_xfs_map_blocks_found(ip, offset, count, wpc->io_type, &imap); return 0; allocate_blocks: @@ -459,6 +460,7 @@ allocate_blocks: ASSERT(whichfork == XFS_COW_FORK || cow_fsb == NULLFILEOFF || imap.br_startoff + imap.br_blockcount <= cow_fsb); wpc->imap = imap; + xfs_trim_extent_eof(&wpc->imap, ip); trace_xfs_map_blocks_alloc(ip, offset, count, wpc->io_type, &imap); return 0; } From 465fa17f4a303d9fdff9eac4d45f91ece92e96ca Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Sun, 3 Feb 2019 14:03:06 -0800 Subject: [PATCH 397/525] xfs: end sync buffer I/O properly on shutdown error As of commit e339dd8d8b ("xfs: use sync buffer I/O for sync delwri queue submission"), the delwri submission code uses sync buffer I/O for sync delwri I/O. Instead of waiting on async I/O to unlock the buffer, it uses the underlying sync I/O completion mechanism. If delwri buffer submission fails due to a shutdown scenario, an error is set on the buffer and buffer completion never occurs. This can cause xfs_buf_delwri_submit() to deadlock waiting on a completion event. We could check the error state before waiting on such buffers, but that doesn't serialize against the case of an error set via a racing I/O completion. Instead, invoke I/O completion in the shutdown case regardless of buffer I/O type. Signed-off-by: Brian Foster Reviewed-by: Dave Chinner Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_buf.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index eedc5e0156ff..1f9857e3630a 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1536,8 +1536,7 @@ __xfs_buf_submit( xfs_buf_ioerror(bp, -EIO); bp->b_flags &= ~XBF_DONE; xfs_buf_stale(bp); - if (bp->b_flags & XBF_ASYNC) - xfs_buf_ioend(bp); + xfs_buf_ioend(bp); return -EIO; } From add46b3b021263c02d5a7080c58e5b459479fafd Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Sun, 3 Feb 2019 14:03:59 -0800 Subject: [PATCH 398/525] xfs: set buffer ops when repair probes for btree type In xrep_findroot_block, we work out the btree type and correctness of a given block by calling different btree verifiers on root block candidates. However, we leave the NULL b_ops while ->verify_read validates the block, which means that if the verifier calls xfs_buf_verifier_error it'll crash on the null b_ops. Fix it to set b_ops before calling the verifier and unsetting it if the verifier fails. Furthermore, improve the documentation around xfs_buf_ensure_ops, which is the function that is responsible for cleaning up the b_ops state of buffers that go through xrep_findroot_block but don't match anything. Signed-off-by: Darrick J. Wong Reviewed-by: Brian Foster --- fs/xfs/scrub/repair.c | 11 ++++++++--- fs/xfs/xfs_buf.c | 16 ++++++++++++++++ 2 files changed, 24 insertions(+), 3 deletions(-) diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c index 1c8eecfe52b8..6acf1bfa0bfe 100644 --- a/fs/xfs/scrub/repair.c +++ b/fs/xfs/scrub/repair.c @@ -768,18 +768,23 @@ xrep_findroot_block( if (!uuid_equal(&btblock->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid)) goto out; + /* + * Read verifiers can reference b_ops, so we set the pointer + * here. If the verifier fails we'll reset the buffer state + * to what it was before we touched the buffer. + */ + bp->b_ops = fab->buf_ops; fab->buf_ops->verify_read(bp); if (bp->b_error) { + bp->b_ops = NULL; bp->b_error = 0; goto out; } /* * Some read verifiers will (re)set b_ops, so we must be - * careful not to blow away any such assignment. + * careful not to change b_ops after running the verifier. */ - if (!bp->b_ops) - bp->b_ops = fab->buf_ops; } /* diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 1f9857e3630a..4f5f2ff3f70f 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -776,10 +776,26 @@ _xfs_buf_read( } /* + * Set buffer ops on an unchecked buffer and validate it, if possible. + * * If the caller passed in an ops structure and the buffer doesn't have ops * assigned, set the ops and use them to verify the contents. If the contents * cannot be verified, we'll clear XBF_DONE. We assume the buffer has no * recorded errors and is already in XBF_DONE state. + * + * Under normal operations, every in-core buffer must have buffer ops assigned + * to them when the buffer is read in from disk so that we can validate the + * metadata. + * + * However, there are two scenarios where one can encounter in-core buffers + * that don't have buffer ops. The first is during log recovery of buffers on + * a V4 filesystem, though these buffers are purged at the end of recovery. + * + * The other is online repair, which tries to match arbitrary metadata blocks + * with btree types in order to find the root. If online repair doesn't match + * the buffer with /any/ btree type, the buffer remains in memory in DONE state + * with no ops, and a subsequent read_buf call from elsewhere will not set the + * ops. This function helps us fix this situation. */ int xfs_buf_ensure_ops( From cfe4bd7a257f6d6f81d3458d8c9d9ec4957539e6 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 4 Feb 2019 03:27:58 +0800 Subject: [PATCH 399/525] sctp: check and update stream->out_curr when allocating stream_out Now when using stream reconfig to add out streams, stream->out will get re-allocated, and all old streams' information will be copied to the new ones and the old ones will be freed. So without stream->out_curr updated, next time when trying to send from stream->out_curr stream, a panic would be caused. This patch is to check and update stream->out_curr when allocating stream_out. v1->v2: - define fa_index() to get elem index from stream->out_curr. v2->v3: - repost with no change. Fixes: 5bbbbe32a431 ("sctp: introduce stream scheduler foundations") Reported-by: Ying Xu Reported-by: syzbot+e33a3a138267ca119c7d@syzkaller.appspotmail.com Signed-off-by: Xin Long Acked-by: Neil Horman Signed-off-by: David S. Miller --- net/sctp/stream.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 80e0ae5534ec..f24633114dfd 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -84,6 +84,19 @@ static void fa_zero(struct flex_array *fa, size_t index, size_t count) } } +static size_t fa_index(struct flex_array *fa, void *elem, size_t count) +{ + size_t index = 0; + + while (count--) { + if (elem == flex_array_get(fa, index)) + break; + index++; + } + + return index; +} + /* Migrates chunks from stream queues to new stream queues if needed, * but not across associations. Also, removes those chunks to streams * higher than the new max. @@ -147,6 +160,13 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, if (stream->out) { fa_copy(out, stream->out, 0, min(outcnt, stream->outcnt)); + if (stream->out_curr) { + size_t index = fa_index(stream->out, stream->out_curr, + stream->outcnt); + + BUG_ON(index == stream->outcnt); + stream->out_curr = flex_array_get(out, index); + } fa_free(stream->out); } From 546f28974d771b124fb0bf7b551b343888cf0419 Mon Sep 17 00:00:00 2001 From: Toshiaki Makita Date: Thu, 31 Jan 2019 20:40:30 +0900 Subject: [PATCH 400/525] virtio_net: Account for tx bytes and packets on sending xdp_frames Previously virtnet_xdp_xmit() did not account for device tx counters, which caused confusions. To be consistent with SKBs, account them on freeing xdp_frames. Reported-by: David Ahern Signed-off-by: Toshiaki Makita Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 259448182272..4cfceb789eea 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -503,6 +503,8 @@ static int virtnet_xdp_xmit(struct net_device *dev, struct bpf_prog *xdp_prog; struct send_queue *sq; unsigned int len; + int packets = 0; + int bytes = 0; int drops = 0; int kicks = 0; int ret, err; @@ -526,10 +528,18 @@ static int virtnet_xdp_xmit(struct net_device *dev, /* Free up any pending old buffers before queueing new ones. */ while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) { - if (likely(is_xdp_frame(ptr))) - xdp_return_frame(ptr_to_xdp(ptr)); - else - napi_consume_skb(ptr, false); + if (likely(is_xdp_frame(ptr))) { + struct xdp_frame *frame = ptr_to_xdp(ptr); + + bytes += frame->len; + xdp_return_frame(frame); + } else { + struct sk_buff *skb = ptr; + + bytes += skb->len; + napi_consume_skb(skb, false); + } + packets++; } for (i = 0; i < n; i++) { @@ -549,6 +559,8 @@ static int virtnet_xdp_xmit(struct net_device *dev, } out: u64_stats_update_begin(&sq->stats.syncp); + sq->stats.bytes += bytes; + sq->stats.packets += packets; sq->stats.xdp_tx += n; sq->stats.xdp_tx_drops += drops; sq->stats.kicks += kicks; From 341198eda723c8c1cddbb006a89ad9e362502ea2 Mon Sep 17 00:00:00 2001 From: Leonid Iziumtsev Date: Tue, 15 Jan 2019 17:15:23 +0000 Subject: [PATCH 401/525] dmaengine: imx-dma: fix wrong callback invoke Once the "ld_queue" list is not empty, next descriptor will migrate into "ld_active" list. The "desc" variable will be overwritten during that transition. And later the dmaengine_desc_get_callback_invoke() will use it as an argument. As result we invoke wrong callback. That behaviour was in place since: commit fcaaba6c7136 ("dmaengine: imx-dma: fix callback path in tasklet"). But after commit 4cd13c21b207 ("softirq: Let ksoftirqd do its job") things got worse, since possible delay between tasklet_schedule() from DMA irq handler and actual tasklet function execution got bigger. And that gave more time for new DMA request to be submitted and to be put into "ld_queue" list. It has been noticed that DMA issue is causing problems for "mxc-mmc" driver. While stressing the system with heavy network traffic and writing/reading to/from sd card simultaneously the timeout may happen: 10013000.sdhci: mxcmci_watchdog: read time out (status = 0x30004900) That often lead to file system corruption. Signed-off-by: Leonid Iziumtsev Signed-off-by: Vinod Koul Cc: stable@vger.kernel.org --- drivers/dma/imx-dma.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c index c2fff3f6c9ca..4a09af3cd546 100644 --- a/drivers/dma/imx-dma.c +++ b/drivers/dma/imx-dma.c @@ -618,7 +618,7 @@ static void imxdma_tasklet(unsigned long data) { struct imxdma_channel *imxdmac = (void *)data; struct imxdma_engine *imxdma = imxdmac->imxdma; - struct imxdma_desc *desc; + struct imxdma_desc *desc, *next_desc; unsigned long flags; spin_lock_irqsave(&imxdma->lock, flags); @@ -648,10 +648,10 @@ static void imxdma_tasklet(unsigned long data) list_move_tail(imxdmac->ld_active.next, &imxdmac->ld_free); if (!list_empty(&imxdmac->ld_queue)) { - desc = list_first_entry(&imxdmac->ld_queue, struct imxdma_desc, - node); + next_desc = list_first_entry(&imxdmac->ld_queue, + struct imxdma_desc, node); list_move_tail(imxdmac->ld_queue.next, &imxdmac->ld_active); - if (imxdma_xfer_desc(desc) < 0) + if (imxdma_xfer_desc(next_desc) < 0) dev_warn(imxdma->dev, "%s: channel: %d couldn't xfer desc\n", __func__, imxdmac->channel); } From f7da7782aba92593f7b82f03d2409a1c5f4db91b Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Wed, 23 Jan 2019 09:26:00 +0100 Subject: [PATCH 402/525] dmaengine: bcm2835: Fix interrupt race on RT If IRQ handlers are threaded (either because CONFIG_PREEMPT_RT_BASE is enabled or "threadirqs" was passed on the command line) and if system load is sufficiently high that wakeup latency of IRQ threads degrades, SPI DMA transactions on the BCM2835 occasionally break like this: ks8851 spi0.0: SPI transfer timed out bcm2835-dma 3f007000.dma: DMA transfer could not be terminated ks8851 spi0.0 eth2: ks8851_rdfifo: spi_sync() failed The root cause is an assumption made by the DMA driver which is documented in a code comment in bcm2835_dma_terminate_all(): /* * Stop DMA activity: we assume the callback will not be called * after bcm_dma_abort() returns (even if it does, it will see * c->desc is NULL and exit.) */ That assumption falls apart if the IRQ handler bcm2835_dma_callback() is threaded: A client may terminate a descriptor and issue a new one before the IRQ handler had a chance to run. In fact the IRQ handler may miss an *arbitrary* number of descriptors. The result is the following race condition: 1. A descriptor finishes, its interrupt is deferred to the IRQ thread. 2. A client calls dma_terminate_async() which sets channel->desc = NULL. 3. The client issues a new descriptor. Because channel->desc is NULL, bcm2835_dma_issue_pending() immediately starts the descriptor. 4. Finally the IRQ thread runs and writes BCM2835_DMA_INT to the CS register to acknowledge the interrupt. This clears the ACTIVE flag, so the newly issued descriptor is paused in the middle of the transaction. Because channel->desc is not NULL, the IRQ thread finalizes the descriptor and tries to start the next one. I see two possible solutions: The first is to call synchronize_irq() in bcm2835_dma_issue_pending() to wait until the IRQ thread has finished before issuing a new descriptor. The downside of this approach is unnecessary latency if clients desire rapidly terminating and re-issuing descriptors and don't have any use for an IRQ callback. (The SPI TX DMA channel is a case in point.) A better alternative is to make the IRQ thread recognize that it has missed descriptors and avoid finalizing the newly issued descriptor. So first of all, set the ACTIVE flag when acknowledging the interrupt. This keeps a newly issued descriptor running. If the descriptor was finished, the channel remains idle despite the ACTIVE flag being set. However the ACTIVE flag can then no longer be used to check whether the channel is idle, so instead check whether the register containing the current control block address is zero and finalize the current descriptor only if so. That way, there is no impact on latency and throughput if the client doesn't care for the interrupt: Only minimal additional overhead is introduced for non-cyclic descriptors as one further MMIO read is necessary per interrupt to check for idleness of the channel. Cyclic descriptors are sped up slightly by removing one MMIO write per interrupt. Fixes: 96286b576690 ("dmaengine: Add support for BCM2835") Signed-off-by: Lukas Wunner Cc: stable@vger.kernel.org # v3.14+ Cc: Frank Pavlic Cc: Martin Sperl Cc: Florian Meier Cc: Clive Messer Cc: Matthias Reichl Tested-by: Stefan Wahren Acked-by: Florian Kauer Signed-off-by: Vinod Koul --- drivers/dma/bcm2835-dma.c | 33 ++++++++++++++++++--------------- 1 file changed, 18 insertions(+), 15 deletions(-) diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c index 1a44c8086d77..0c3f5c71bb48 100644 --- a/drivers/dma/bcm2835-dma.c +++ b/drivers/dma/bcm2835-dma.c @@ -412,7 +412,12 @@ static int bcm2835_dma_abort(void __iomem *chan_base) long int timeout = 10000; cs = readl(chan_base + BCM2835_DMA_CS); - if (!(cs & BCM2835_DMA_ACTIVE)) + + /* + * A zero control block address means the channel is idle. + * (The ACTIVE flag in the CS register is not a reliable indicator.) + */ + if (!readl(chan_base + BCM2835_DMA_ADDR)) return 0; /* Write 0 to the active bit - Pause the DMA */ @@ -476,8 +481,15 @@ static irqreturn_t bcm2835_dma_callback(int irq, void *data) spin_lock_irqsave(&c->vc.lock, flags); - /* Acknowledge interrupt */ - writel(BCM2835_DMA_INT, c->chan_base + BCM2835_DMA_CS); + /* + * Clear the INT flag to receive further interrupts. Keep the channel + * active in case the descriptor is cyclic or in case the client has + * already terminated the descriptor and issued a new one. (May happen + * if this IRQ handler is threaded.) If the channel is finished, it + * will remain idle despite the ACTIVE flag being set. + */ + writel(BCM2835_DMA_INT | BCM2835_DMA_ACTIVE, + c->chan_base + BCM2835_DMA_CS); d = c->desc; @@ -485,11 +497,7 @@ static irqreturn_t bcm2835_dma_callback(int irq, void *data) if (d->cyclic) { /* call the cyclic callback */ vchan_cyclic_callback(&d->vd); - - /* Keep the DMA engine running */ - writel(BCM2835_DMA_ACTIVE, - c->chan_base + BCM2835_DMA_CS); - } else { + } else if (!readl(c->chan_base + BCM2835_DMA_ADDR)) { vchan_cookie_complete(&c->desc->vd); bcm2835_dma_start_desc(c); } @@ -789,11 +797,7 @@ static int bcm2835_dma_terminate_all(struct dma_chan *chan) list_del_init(&c->node); spin_unlock(&d->lock); - /* - * Stop DMA activity: we assume the callback will not be called - * after bcm_dma_abort() returns (even if it does, it will see - * c->desc is NULL and exit.) - */ + /* stop DMA activity */ if (c->desc) { vchan_terminate_vdesc(&c->desc->vd); c->desc = NULL; @@ -801,8 +805,7 @@ static int bcm2835_dma_terminate_all(struct dma_chan *chan) /* Wait for stopping */ while (--timeout) { - if (!(readl(c->chan_base + BCM2835_DMA_CS) & - BCM2835_DMA_ACTIVE)) + if (!readl(c->chan_base + BCM2835_DMA_ADDR)) break; cpu_relax(); From 9e528c799d17a4ac37d788c81440b50377dd592d Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Wed, 23 Jan 2019 09:26:00 +0100 Subject: [PATCH 403/525] dmaengine: bcm2835: Fix abort of transactions There are multiple issues with bcm2835_dma_abort() (which is called on termination of a transaction): * The algorithm to abort the transaction first pauses the channel by clearing the ACTIVE flag in the CS register, then waits for the PAUSED flag to clear. Page 49 of the spec documents the latter as follows: "Indicates if the DMA is currently paused and not transferring data. This will occur if the active bit has been cleared [...]" https://www.raspberrypi.org/app/uploads/2012/02/BCM2835-ARM-Peripherals.pdf So the function is entering an infinite loop because it is waiting for PAUSED to clear which is always set due to the function having cleared the ACTIVE flag. The only thing that's saving it from itself is the upper bound of 10000 loop iterations. The code comment says that the intention is to "wait for any current AXI transfer to complete", so the author probably wanted to check the WAITING_FOR_OUTSTANDING_WRITES flag instead. Amend the function accordingly. * The CS register is only read at the beginning of the function. It needs to be read again after pausing the channel and before checking for outstanding writes, otherwise writes which were issued between the register read at the beginning of the function and pausing the channel may not be waited for. * The function seeks to abort the transfer by writing 0 to the NEXTCONBK register and setting the ABORT and ACTIVE flags. Thereby, the 0 in NEXTCONBK is sought to be loaded into the CONBLK_AD register. However experimentation has shown this approach to not work: The CONBLK_AD register remains the same as before and the CS register contains 0x00000030 (PAUSED | DREQ_STOPS_DMA). In other words, the control block is not aborted but merely paused and it will be resumed once the next DMA transaction is started. That is absolutely not the desired behavior. A simpler approach is to set the channel's RESET flag instead. This reliably zeroes the NEXTCONBK as well as the CS register. It requires less code and only a single MMIO write. This is also what popular user space DMA drivers do, e.g.: https://github.com/metachris/RPIO/blob/master/source/c_pwm/pwm.c Note that the spec is contradictory whether the NEXTCONBK register is writeable at all. On the one hand, page 41 claims: "The value loaded into the NEXTCONBK register can be overwritten so that the linked list of Control Block data structures can be dynamically altered. However it is only safe to do this when the DMA is paused." On the other hand, page 40 specifies: "Only three registers in each channel's register set are directly writeable (CS, CONBLK_AD and DEBUG). The other registers (TI, SOURCE_AD, DEST_AD, TXFR_LEN, STRIDE & NEXTCONBK), are automatically loaded from a Control Block data structure held in external memory." Fixes: 96286b576690 ("dmaengine: Add support for BCM2835") Signed-off-by: Lukas Wunner Cc: stable@vger.kernel.org # v3.14+ Cc: Frank Pavlic Cc: Martin Sperl Cc: Florian Meier Cc: Clive Messer Cc: Matthias Reichl Tested-by: Stefan Wahren Acked-by: Florian Kauer Signed-off-by: Vinod Koul --- drivers/dma/bcm2835-dma.c | 41 +++++++++------------------------------ 1 file changed, 9 insertions(+), 32 deletions(-) diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c index 0c3f5c71bb48..ae10f5614f95 100644 --- a/drivers/dma/bcm2835-dma.c +++ b/drivers/dma/bcm2835-dma.c @@ -406,13 +406,11 @@ static void bcm2835_dma_fill_cb_chain_with_sg( } } -static int bcm2835_dma_abort(void __iomem *chan_base) +static int bcm2835_dma_abort(struct bcm2835_chan *c) { - unsigned long cs; + void __iomem *chan_base = c->chan_base; long int timeout = 10000; - cs = readl(chan_base + BCM2835_DMA_CS); - /* * A zero control block address means the channel is idle. * (The ACTIVE flag in the CS register is not a reliable indicator.) @@ -424,25 +422,16 @@ static int bcm2835_dma_abort(void __iomem *chan_base) writel(0, chan_base + BCM2835_DMA_CS); /* Wait for any current AXI transfer to complete */ - while ((cs & BCM2835_DMA_ISPAUSED) && --timeout) { + while ((readl(chan_base + BCM2835_DMA_CS) & + BCM2835_DMA_WAITING_FOR_WRITES) && --timeout) cpu_relax(); - cs = readl(chan_base + BCM2835_DMA_CS); - } - /* We'll un-pause when we set of our next DMA */ + /* Peripheral might be stuck and fail to signal AXI write responses */ if (!timeout) - return -ETIMEDOUT; - - if (!(cs & BCM2835_DMA_ACTIVE)) - return 0; - - /* Terminate the control block chain */ - writel(0, chan_base + BCM2835_DMA_NEXTCB); - - /* Abort the whole DMA */ - writel(BCM2835_DMA_ABORT | BCM2835_DMA_ACTIVE, - chan_base + BCM2835_DMA_CS); + dev_err(c->vc.chan.device->dev, + "failed to complete outstanding writes\n"); + writel(BCM2835_DMA_RESET, chan_base + BCM2835_DMA_CS); return 0; } @@ -787,7 +776,6 @@ static int bcm2835_dma_terminate_all(struct dma_chan *chan) struct bcm2835_chan *c = to_bcm2835_dma_chan(chan); struct bcm2835_dmadev *d = to_bcm2835_dma_dev(c->vc.chan.device); unsigned long flags; - int timeout = 10000; LIST_HEAD(head); spin_lock_irqsave(&c->vc.lock, flags); @@ -801,18 +789,7 @@ static int bcm2835_dma_terminate_all(struct dma_chan *chan) if (c->desc) { vchan_terminate_vdesc(&c->desc->vd); c->desc = NULL; - bcm2835_dma_abort(c->chan_base); - - /* Wait for stopping */ - while (--timeout) { - if (!readl(c->chan_base + BCM2835_DMA_ADDR)) - break; - - cpu_relax(); - } - - if (!timeout) - dev_err(d->ddev.dev, "DMA transfer could not be terminated\n"); + bcm2835_dma_abort(c); } vchan_get_all_descriptors(&c->vc, &head); From 9e63a7894fd302082cf3627fe90844421a6cbe7f Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Sun, 27 Jan 2019 06:53:14 -0800 Subject: [PATCH 404/525] perf/x86/intel/uncore: Add Node ID mask Some PCI uncore PMUs cannot be registered on an 8-socket system (HPE Superdome Flex). To understand which Socket the PCI uncore PMUs belongs to, perf retrieves the local Node ID of the uncore device from CPUNODEID(0xC0) of the PCI configuration space, and the mapping between Socket ID and Node ID from GIDNIDMAP(0xD4). The Socket ID can be calculated accordingly. The local Node ID is only available at bit 2:0, but current code doesn't mask it. If a BIOS doesn't clear the rest of the bits, an incorrect Node ID will be fetched. Filter the Node ID by adding a mask. Reported-by: Song Liu Tested-by: Song Liu Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: # v3.7+ Fixes: 7c94ee2e0917 ("perf/x86: Add Intel Nehalem and Sandy Bridge-EP uncore support") Link: https://lkml.kernel.org/r/1548600794-33162-1-git-send-email-kan.liang@linux.intel.com Signed-off-by: Ingo Molnar --- arch/x86/events/intel/uncore_snbep.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index c07bee31abe8..b10e04387f38 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -1222,6 +1222,8 @@ static struct pci_driver snbep_uncore_pci_driver = { .id_table = snbep_uncore_pci_ids, }; +#define NODE_ID_MASK 0x7 + /* * build pci bus to socket mapping */ @@ -1243,7 +1245,7 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool err = pci_read_config_dword(ubox_dev, nodeid_loc, &config); if (err) break; - nodeid = config; + nodeid = config & NODE_ID_MASK; /* get the Node ID mapping */ err = pci_read_config_dword(ubox_dev, idmap_loc, &config); if (err) From 602cae04c4864bb3487dfe4c2126c8d9e7e1614a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 19 Dec 2018 17:53:50 +0100 Subject: [PATCH 405/525] perf/x86/intel: Delay memory deallocation until x86_pmu_dead_cpu() intel_pmu_cpu_prepare() allocated memory for ->shared_regs among other members of struct cpu_hw_events. This memory is released in intel_pmu_cpu_dying() which is wrong. The counterpart of the intel_pmu_cpu_prepare() callback is x86_pmu_dead_cpu(). Otherwise if the CPU fails on the UP path between CPUHP_PERF_X86_PREPARE and CPUHP_AP_PERF_X86_STARTING then it won't release the memory but allocate new memory on the next attempt to online the CPU (leaking the old memory). Also, if the CPU down path fails between CPUHP_AP_PERF_X86_STARTING and CPUHP_PERF_X86_PREPARE then the CPU will go back online but never allocate the memory that was released in x86_pmu_dying_cpu(). Make the memory allocation/free symmetrical in regard to the CPU hotplug notifier by moving the deallocation to intel_pmu_cpu_dead(). This started in commit: a7e3ed1e47011 ("perf: Add support for supplementary event registers"). In principle the bug was introduced in v2.6.39 (!), but it will almost certainly not backport cleanly across the big CPU hotplug rewrite between v4.7-v4.15... [ bigeasy: Added patch description. ] [ mingo: Added backporting guidance. ] Reported-by: He Zhe Signed-off-by: Peter Zijlstra (Intel) # With developer hat on Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) # With maintainer hat on Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: acme@kernel.org Cc: bp@alien8.de Cc: hpa@zytor.com Cc: jolsa@kernel.org Cc: kan.liang@linux.intel.com Cc: namhyung@kernel.org Cc: Fixes: a7e3ed1e47011 ("perf: Add support for supplementary event registers"). Link: https://lkml.kernel.org/r/20181219165350.6s3jvyxbibpvlhtq@linutronix.de Signed-off-by: Ingo Molnar --- arch/x86/events/intel/core.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 40e12cfc87f6..daafb893449b 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3558,6 +3558,14 @@ static void free_excl_cntrs(int cpu) } static void intel_pmu_cpu_dying(int cpu) +{ + fini_debug_store_on_cpu(cpu); + + if (x86_pmu.counter_freezing) + disable_counter_freeze(); +} + +static void intel_pmu_cpu_dead(int cpu) { struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); struct intel_shared_regs *pc; @@ -3570,11 +3578,6 @@ static void intel_pmu_cpu_dying(int cpu) } free_excl_cntrs(cpu); - - fini_debug_store_on_cpu(cpu); - - if (x86_pmu.counter_freezing) - disable_counter_freeze(); } static void intel_pmu_sched_task(struct perf_event_context *ctx, @@ -3663,6 +3666,7 @@ static __initconst const struct x86_pmu core_pmu = { .cpu_prepare = intel_pmu_cpu_prepare, .cpu_starting = intel_pmu_cpu_starting, .cpu_dying = intel_pmu_cpu_dying, + .cpu_dead = intel_pmu_cpu_dead, }; static struct attribute *intel_pmu_attrs[]; @@ -3703,6 +3707,8 @@ static __initconst const struct x86_pmu intel_pmu = { .cpu_prepare = intel_pmu_cpu_prepare, .cpu_starting = intel_pmu_cpu_starting, .cpu_dying = intel_pmu_cpu_dying, + .cpu_dead = intel_pmu_cpu_dead, + .guest_get_msrs = intel_guest_get_msrs, .sched_task = intel_pmu_sched_task, }; From 9dff0aa95a324e262ffb03f425d00e4751f3294e Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 10 Jan 2019 14:27:45 +0000 Subject: [PATCH 406/525] perf/core: Don't WARN() for impossible ring-buffer sizes The perf tool uses /proc/sys/kernel/perf_event_mlock_kb to determine how large its ringbuffer mmap should be. This can be configured to arbitrary values, which can be larger than the maximum possible allocation from kmalloc. When this is configured to a suitably large value (e.g. thanks to the perf fuzzer), attempting to use perf record triggers a WARN_ON_ONCE() in __alloc_pages_nodemask(): WARNING: CPU: 2 PID: 5666 at mm/page_alloc.c:4511 __alloc_pages_nodemask+0x3f8/0xbc8 Let's avoid this by checking that the requested allocation is possible before calling kzalloc. Reported-by: Julien Thierry Signed-off-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Julien Thierry Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Link: https://lkml.kernel.org/r/20190110142745.25495-1-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- kernel/events/ring_buffer.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 4a9937076331..309ef5a64af5 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -734,6 +734,9 @@ struct ring_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags) size = sizeof(struct ring_buffer); size += nr_pages * sizeof(void *); + if (order_base_2(size) >= MAX_ORDER) + goto fail; + rb = kzalloc(size, GFP_KERNEL); if (!rb) goto fail; From 6454368a804c4955ccd116236037536f81e5b1f1 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 30 Jan 2019 21:48:44 +0200 Subject: [PATCH 407/525] dmaengine: dmatest: Abort test in case of mapping error In case of mapping error the DMA addresses are invalid and continuing will screw system memory or potentially something else. [ 222.480310] dmatest: dma0chan7-copy0: summary 1 tests, 3 failures 6 iops 349 KB/s (0) ... [ 240.912725] check: Corrupted low memory at 00000000c7c75ac9 (2940 phys) = 5656000000000000 [ 240.921998] check: Corrupted low memory at 000000005715a1cd (2948 phys) = 279f2aca5595ab2b [ 240.931280] check: Corrupted low memory at 000000002f4024c0 (2950 phys) = 5e5624f349e793cf ... Abort any test if mapping failed. Fixes: 4076e755dbec ("dmatest: convert to dmaengine_unmap_data") Cc: Dan Williams Signed-off-by: Andy Shevchenko Signed-off-by: Vinod Koul --- drivers/dma/dmatest.c | 32 ++++++++++++++------------------ 1 file changed, 14 insertions(+), 18 deletions(-) diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c index 2eea4ef72915..6511928b4cdf 100644 --- a/drivers/dma/dmatest.c +++ b/drivers/dma/dmatest.c @@ -711,11 +711,9 @@ static int dmatest_func(void *data) srcs[i] = um->addr[i] + src_off; ret = dma_mapping_error(dev->dev, um->addr[i]); if (ret) { - dmaengine_unmap_put(um); result("src mapping error", total_tests, src_off, dst_off, len, ret); - failed_tests++; - continue; + goto error_unmap_continue; } um->to_cnt++; } @@ -730,11 +728,9 @@ static int dmatest_func(void *data) DMA_BIDIRECTIONAL); ret = dma_mapping_error(dev->dev, dsts[i]); if (ret) { - dmaengine_unmap_put(um); result("dst mapping error", total_tests, src_off, dst_off, len, ret); - failed_tests++; - continue; + goto error_unmap_continue; } um->bidi_cnt++; } @@ -762,12 +758,10 @@ static int dmatest_func(void *data) } if (!tx) { - dmaengine_unmap_put(um); result("prep error", total_tests, src_off, dst_off, len, ret); msleep(100); - failed_tests++; - continue; + goto error_unmap_continue; } done->done = false; @@ -776,12 +770,10 @@ static int dmatest_func(void *data) cookie = tx->tx_submit(tx); if (dma_submit_error(cookie)) { - dmaengine_unmap_put(um); result("submit error", total_tests, src_off, dst_off, len, ret); msleep(100); - failed_tests++; - continue; + goto error_unmap_continue; } dma_async_issue_pending(chan); @@ -790,22 +782,20 @@ static int dmatest_func(void *data) status = dma_async_is_tx_complete(chan, cookie, NULL, NULL); - dmaengine_unmap_put(um); - if (!done->done) { result("test timed out", total_tests, src_off, dst_off, len, 0); - failed_tests++; - continue; + goto error_unmap_continue; } else if (status != DMA_COMPLETE) { result(status == DMA_ERROR ? "completion error status" : "completion busy status", total_tests, src_off, dst_off, len, ret); - failed_tests++; - continue; + goto error_unmap_continue; } + dmaengine_unmap_put(um); + if (params->noverify) { verbose_result("test passed", total_tests, src_off, dst_off, len, 0); @@ -846,6 +836,12 @@ static int dmatest_func(void *data) verbose_result("test passed", total_tests, src_off, dst_off, len, 0); } + + continue; + +error_unmap_continue: + dmaengine_unmap_put(um); + failed_tests++; } ktime = ktime_sub(ktime_get(), ktime); ktime = ktime_sub(ktime, comparetime); From 952b72f89ae23b316da8c1021b18d0c388ad6cc4 Mon Sep 17 00:00:00 2001 From: Naresh Kamboju Date: Tue, 29 Jan 2019 06:28:35 +0000 Subject: [PATCH 408/525] selftests: netfilter: fix config fragment CONFIG_NF_TABLES_INET In selftests the config fragment for netfilter was added as NF_TABLES_INET=y and this patch correct it as CONFIG_NF_TABLES_INET=y Signed-off-by: Naresh Kamboju Acked-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- tools/testing/selftests/netfilter/config | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/netfilter/config b/tools/testing/selftests/netfilter/config index 1017313e41a8..59caa8f71cd8 100644 --- a/tools/testing/selftests/netfilter/config +++ b/tools/testing/selftests/netfilter/config @@ -1,2 +1,2 @@ CONFIG_NET_NS=y -NF_TABLES_INET=y +CONFIG_NF_TABLES_INET=y From 98bfc3414bda335dbd7fec58bde6266f991801d7 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 29 Jan 2019 15:16:23 +0100 Subject: [PATCH 409/525] selftests: netfilter: add simple masq/redirect test cases Check basic nat/redirect/masquerade for ipv4 and ipv6. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- tools/testing/selftests/netfilter/Makefile | 2 +- tools/testing/selftests/netfilter/nft_nat.sh | 762 +++++++++++++++++++ 2 files changed, 763 insertions(+), 1 deletion(-) create mode 100755 tools/testing/selftests/netfilter/nft_nat.sh diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index 47ed6cef93fb..c9ff2b47bd1c 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for netfilter selftests -TEST_PROGS := nft_trans_stress.sh +TEST_PROGS := nft_trans_stress.sh nft_nat.sh include ../lib.mk diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh new file mode 100755 index 000000000000..8ec76681605c --- /dev/null +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -0,0 +1,762 @@ +#!/bin/bash +# +# This test is for basic NAT functionality: snat, dnat, redirect, masquerade. +# + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 +ret=0 + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +ip netns add ns0 +ip netns add ns1 +ip netns add ns2 + +ip link add veth0 netns ns0 type veth peer name eth0 netns ns1 +ip link add veth1 netns ns0 type veth peer name eth0 netns ns2 + +ip -net ns0 link set lo up +ip -net ns0 link set veth0 up +ip -net ns0 addr add 10.0.1.1/24 dev veth0 +ip -net ns0 addr add dead:1::1/64 dev veth0 + +ip -net ns0 link set veth1 up +ip -net ns0 addr add 10.0.2.1/24 dev veth1 +ip -net ns0 addr add dead:2::1/64 dev veth1 + +for i in 1 2; do + ip -net ns$i link set lo up + ip -net ns$i link set eth0 up + ip -net ns$i addr add 10.0.$i.99/24 dev eth0 + ip -net ns$i route add default via 10.0.$i.1 + ip -net ns$i addr add dead:$i::99/64 dev eth0 + ip -net ns$i route add default via dead:$i::1 +done + +bad_counter() +{ + local ns=$1 + local counter=$2 + local expect=$3 + + echo "ERROR: $counter counter in $ns has unexpected value (expected $expect)" 1>&2 + ip netns exec $ns nft list counter inet filter $counter 1>&2 +} + +check_counters() +{ + ns=$1 + local lret=0 + + cnt=$(ip netns exec $ns nft list counter inet filter ns0in | grep -q "packets 1 bytes 84") + if [ $? -ne 0 ]; then + bad_counter $ns ns0in "packets 1 bytes 84" + lret=1 + fi + cnt=$(ip netns exec $ns nft list counter inet filter ns0out | grep -q "packets 1 bytes 84") + if [ $? -ne 0 ]; then + bad_counter $ns ns0out "packets 1 bytes 84" + lret=1 + fi + + expect="packets 1 bytes 104" + cnt=$(ip netns exec $ns nft list counter inet filter ns0in6 | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter $ns ns0in6 "$expect" + lret=1 + fi + cnt=$(ip netns exec $ns nft list counter inet filter ns0out6 | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter $ns ns0out6 "$expect" + lret=1 + fi + + return $lret +} + +check_ns0_counters() +{ + local ns=$1 + local lret=0 + + cnt=$(ip netns exec ns0 nft list counter inet filter ns0in | grep -q "packets 0 bytes 0") + if [ $? -ne 0 ]; then + bad_counter ns0 ns0in "packets 0 bytes 0" + lret=1 + fi + + cnt=$(ip netns exec ns0 nft list counter inet filter ns0in6 | grep -q "packets 0 bytes 0") + if [ $? -ne 0 ]; then + bad_counter ns0 ns0in6 "packets 0 bytes 0" + lret=1 + fi + + cnt=$(ip netns exec ns0 nft list counter inet filter ns0out | grep -q "packets 0 bytes 0") + if [ $? -ne 0 ]; then + bad_counter ns0 ns0out "packets 0 bytes 0" + lret=1 + fi + cnt=$(ip netns exec ns0 nft list counter inet filter ns0out6 | grep -q "packets 0 bytes 0") + if [ $? -ne 0 ]; then + bad_counter ns0 ns0out6 "packets 0 bytes 0" + lret=1 + fi + + for dir in "in" "out" ; do + expect="packets 1 bytes 84" + cnt=$(ip netns exec ns0 nft list counter inet filter ${ns}${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 $ns$dir "$expect" + lret=1 + fi + + expect="packets 1 bytes 104" + cnt=$(ip netns exec ns0 nft list counter inet filter ${ns}${dir}6 | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 $ns$dir6 "$expect" + lret=1 + fi + done + + return $lret +} + +reset_counters() +{ + for i in 0 1 2;do + ip netns exec ns$i nft reset counters inet > /dev/null + done +} + +test_local_dnat6() +{ + local lret=0 +ip netns exec ns0 nft -f - < /dev/null + if [ $? -ne 0 ]; then + lret=1 + echo "ERROR: ping6 failed" + return $lret + fi + + expect="packets 0 bytes 0" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 ns1$dir "$expect" + lret=1 + fi + done + + expect="packets 1 bytes 104" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 ns2$dir "$expect" + lret=1 + fi + done + + # expect 0 count in ns1 + expect="packets 0 bytes 0" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + done + + # expect 1 packet in ns2 + expect="packets 1 bytes 104" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns0$dir "$expect" + lret=1 + fi + done + + test $lret -eq 0 && echo "PASS: ipv6 ping to ns1 was NATted to ns2" + ip netns exec ns0 nft flush chain ip6 nat output + + return $lret +} + +test_local_dnat() +{ + local lret=0 +ip netns exec ns0 nft -f - < /dev/null + if [ $? -ne 0 ]; then + lret=1 + echo "ERROR: ping failed" + return $lret + fi + + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 ns1$dir "$expect" + lret=1 + fi + done + + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 ns2$dir "$expect" + lret=1 + fi + done + + # expect 0 count in ns1 + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + done + + # expect 1 packet in ns2 + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns0$dir "$expect" + lret=1 + fi + done + + test $lret -eq 0 && echo "PASS: ping to ns1 was NATted to ns2" + + ip netns exec ns0 nft flush chain ip nat output + + reset_counters + ip netns exec ns0 ping -q -c 1 10.0.1.99 > /dev/null + if [ $? -ne 0 ]; then + lret=1 + echo "ERROR: ping failed" + return $lret + fi + + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns1$dir "$expect" + lret=1 + fi + done + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 ns2$dir "$expect" + lret=1 + fi + done + + # expect 1 count in ns1 + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 ns0$dir "$expect" + lret=1 + fi + done + + # expect 0 packet in ns2 + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns2$dir "$expect" + lret=1 + fi + done + + test $lret -eq 0 && echo "PASS: ping to ns1 OK after nat output chain flush" + + return $lret +} + + +test_masquerade6() +{ + local lret=0 + + ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null + + ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 via ipv6" + return 1 + lret=1 + fi + + expect="packets 1 bytes 104" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns2$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + reset_counters + +# add masquerading rule +ip netns exec ns0 nft -f - < /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerading" + lret=1 + fi + + # ns1 should have seen packets from ns0, due to masquerade + expect="packets 1 bytes 104" + for dir in "in6" "out6" ; do + + cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + # ns1 should not have seen packets from ns2, due to masquerade + expect="packets 0 bytes 0" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + ip netns exec ns0 nft flush chain ip6 nat postrouting + if [ $? -ne 0 ]; then + echo "ERROR: Could not flush ip6 nat postrouting" 1>&2 + lret=1 + fi + + test $lret -eq 0 && echo "PASS: IPv6 masquerade for ns2" + + return $lret +} + +test_masquerade() +{ + local lret=0 + + ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null + ip netns exec ns0 sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null + + ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: canot ping ns1 from ns2" + lret=1 + fi + + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns2$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + reset_counters + +# add masquerading rule +ip netns exec ns0 nft -f - < /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 with active ip masquerading" + lret=1 + fi + + # ns1 should have seen packets from ns0, due to masquerade + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + # ns1 should not have seen packets from ns2, due to masquerade + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + ip netns exec ns0 nft flush chain ip nat postrouting + if [ $? -ne 0 ]; then + echo "ERROR: Could not flush nat postrouting" 1>&2 + lret=1 + fi + + test $lret -eq 0 && echo "PASS: IP masquerade for ns2" + + return $lret +} + +test_redirect6() +{ + local lret=0 + + ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null + + ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannnot ping ns1 from ns2 via ipv6" + lret=1 + fi + + expect="packets 1 bytes 104" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns2$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + reset_counters + +# add redirect rule +ip netns exec ns0 nft -f - < /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 with active ip6 redirect" + lret=1 + fi + + # ns1 should have seen no packets from ns2, due to redirection + expect="packets 0 bytes 0" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + done + + # ns0 should have seen packets from ns2, due to masquerade + expect="packets 1 bytes 104" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + done + + ip netns exec ns0 nft delete table ip6 nat + if [ $? -ne 0 ]; then + echo "ERROR: Could not delete ip6 nat table" 1>&2 + lret=1 + fi + + test $lret -eq 0 && echo "PASS: IPv6 redirection for ns2" + + return $lret +} + +test_redirect() +{ + local lret=0 + + ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null + ip netns exec ns0 sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null + + ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2" + lret=1 + fi + + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns2$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + reset_counters + +# add redirect rule +ip netns exec ns0 nft -f - < /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 with active ip redirect" + lret=1 + fi + + # ns1 should have seen no packets from ns2, due to redirection + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + done + + # ns0 should have seen packets from ns2, due to masquerade + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + done + + ip netns exec ns0 nft delete table ip nat + if [ $? -ne 0 ]; then + echo "ERROR: Could not delete nat table" 1>&2 + lret=1 + fi + + test $lret -eq 0 && echo "PASS: IP redirection for ns2" + + return $lret +} + + +# ip netns exec ns0 ping -c 1 -q 10.0.$i.99 +for i in 0 1 2; do +ip netns exec ns$i nft -f - < /dev/null + if [ $? -ne 0 ];then + echo "ERROR: Could not reach other namespace(s)" 1>&2 + ret=1 + fi + + ip netns exec ns0 ping -c 1 -q dead:$i::99 > /dev/null + if [ $? -ne 0 ];then + echo "ERROR: Could not reach other namespace(s) via ipv6" 1>&2 + ret=1 + fi + check_counters ns$i + if [ $? -ne 0 ]; then + ret=1 + fi + + check_ns0_counters ns$i + if [ $? -ne 0 ]; then + ret=1 + fi + reset_counters +done + +if [ $ret -eq 0 ];then + echo "PASS: netns routing/connectivity: ns0 can reach ns1 and ns2" +fi + +reset_counters +test_local_dnat +test_local_dnat6 + +reset_counters +test_masquerade +test_masquerade6 + +reset_counters +test_redirect +test_redirect6 + +for i in 0 1 2; do ip netns del ns$i;done + +exit $ret From 4e35c1cb9460240e983a01745b5f29fe3a4d8e39 Mon Sep 17 00:00:00 2001 From: Martynas Pumputis Date: Tue, 29 Jan 2019 15:51:42 +0100 Subject: [PATCH 410/525] netfilter: nf_nat: skip nat clash resolution for same-origin entries It is possible that two concurrent packets originating from the same socket of a connection-less protocol (e.g. UDP) can end up having different IP_CT_DIR_REPLY tuples which results in one of the packets being dropped. To illustrate this, consider the following simplified scenario: 1. Packet A and B are sent at the same time from two different threads by same UDP socket. No matching conntrack entry exists yet. Both packets cause allocation of a new conntrack entry. 2. get_unique_tuple gets called for A. No clashing entry found. conntrack entry for A is added to main conntrack table. 3. get_unique_tuple is called for B and will find that the reply tuple of B is already taken by A. It will allocate a new UDP source port for B to resolve the clash. 4. conntrack entry for B cannot be added to main conntrack table because its ORIGINAL direction is clashing with A and the REPLY directions of A and B are not the same anymore due to UDP source port reallocation done in step 3. This patch modifies nf_conntrack_tuple_taken so it doesn't consider colliding reply tuples if the IP_CT_DIR_ORIGINAL tuples are equal. [ Florian: simplify patch to not use .allow_clash setting and always ignore identical flows ] Signed-off-by: Martynas Pumputis Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_core.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 741b533148ba..db4d46332e86 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1007,6 +1007,22 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple, } if (nf_ct_key_equal(h, tuple, zone, net)) { + /* Tuple is taken already, so caller will need to find + * a new source port to use. + * + * Only exception: + * If the *original tuples* are identical, then both + * conntracks refer to the same flow. + * This is a rare situation, it can occur e.g. when + * more than one UDP packet is sent from same socket + * in different threads. + * + * Let nf_ct_resolve_clash() deal with this later. + */ + if (nf_ct_tuple_equal(&ignored_conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple)) + continue; + NF_CT_STAT_INC_ATOMIC(net, found); rcu_read_unlock(); return 1; From 489338a717a0dfbbd5a3fabccf172b78f0ac9015 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 22 Jan 2019 17:34:39 -0600 Subject: [PATCH 411/525] perf tests evsel-tp-sched: Fix bitwise operator Notice that the use of the bitwise OR operator '|' always leads to true in this particular case, which seems a bit suspicious due to the context in which this expression is being used. Fix this by using bitwise AND operator '&' instead. This bug was detected with the help of Coccinelle. Signed-off-by: Gustavo A. R. Silva Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Namhyung Kim Cc: Peter Zijlstra Cc: stable@vger.kernel.org Fixes: 6a6cd11d4e57 ("perf test: Add test for the sched tracepoint format fields") Link: http://lkml.kernel.org/r/20190122233439.GA5868@embeddedor Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/evsel-tp-sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c index 5f8501c68da4..5cbba70bcdd0 100644 --- a/tools/perf/tests/evsel-tp-sched.c +++ b/tools/perf/tests/evsel-tp-sched.c @@ -17,7 +17,7 @@ static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name, return -1; } - is_signed = !!(field->flags | TEP_FIELD_IS_SIGNED); + is_signed = !!(field->flags & TEP_FIELD_IS_SIGNED); if (should_be_signed && !is_signed) { pr_debug("%s: \"%s\" signedness(%d) is wrong, should be %d\n", evsel->name, name, is_signed, should_be_signed); From f0fabf9c897327abd39018aefb5029aff8c7e133 Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Tue, 29 Jan 2019 18:54:12 +0530 Subject: [PATCH 412/525] perf mem/c2c: Fix perf_mem_events to support powerpc PowerPC hardware does not have a builtin latency filter (--ldlat) for the "mem-load" event and perf_mem_events by default includes "/ldlat=30/" which is causing a failure on PowerPC. Refactor the code to support "perf mem/c2c" on PowerPC. This patch depends on kernel side changes done my Madhavan: https://lists.ozlabs.org/pipermail/linuxppc-dev/2018-December/182596.html Signed-off-by: Ravi Bangoria Acked-by: Jiri Olsa Cc: Dick Fowles Cc: Don Zickus Cc: Joe Mario Cc: Madhavan Srinivasan Cc: Michael Ellerman Cc: Namhyung Kim Cc: linuxppc-dev@lists.ozlabs.org Link: http://lkml.kernel.org/r/20190129132412.771-1-ravi.bangoria@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-c2c.txt | 16 ++++++++++++---- tools/perf/Documentation/perf-mem.txt | 2 +- tools/perf/arch/powerpc/util/Build | 1 + tools/perf/arch/powerpc/util/mem-events.c | 11 +++++++++++ tools/perf/util/mem-events.c | 2 +- 5 files changed, 26 insertions(+), 6 deletions(-) create mode 100644 tools/perf/arch/powerpc/util/mem-events.c diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt index 095aebdc5bb7..e6150f21267d 100644 --- a/tools/perf/Documentation/perf-c2c.txt +++ b/tools/perf/Documentation/perf-c2c.txt @@ -19,8 +19,11 @@ C2C stands for Cache To Cache. The perf c2c tool provides means for Shared Data C2C/HITM analysis. It allows you to track down the cacheline contentions. -The tool is based on x86's load latency and precise store facility events -provided by Intel CPUs. These events provide: +On x86, the tool is based on load latency and precise store facility events +provided by Intel CPUs. On PowerPC, the tool uses random instruction sampling +with thresholding feature. + +These events provide: - memory address of the access - type of the access (load and store details) - latency (in cycles) of the load access @@ -46,7 +49,7 @@ RECORD OPTIONS -l:: --ldlat:: - Configure mem-loads latency. + Configure mem-loads latency. (x86 only) -k:: --all-kernel:: @@ -119,11 +122,16 @@ Following perf record options are configured by default: -W,-d,--phys-data,--sample-cpu Unless specified otherwise with '-e' option, following events are monitored by -default: +default on x86: cpu/mem-loads,ldlat=30/P cpu/mem-stores/P +and following on PowerPC: + + cpu/mem-loads/ + cpu/mem-stores/ + User can pass any 'perf record' option behind '--' mark, like (to enable callchains and system wide monitoring): diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt index f8d2167cf3e7..199ea0f0a6c0 100644 --- a/tools/perf/Documentation/perf-mem.txt +++ b/tools/perf/Documentation/perf-mem.txt @@ -82,7 +82,7 @@ RECORD OPTIONS Be more verbose (show counter open errors, etc) --ldlat :: - Specify desired latency for loads event. + Specify desired latency for loads event. (x86 only) In addition, for report all perf report options are valid, and for record all perf record options. diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build index 2e6595310420..ba98bd006488 100644 --- a/tools/perf/arch/powerpc/util/Build +++ b/tools/perf/arch/powerpc/util/Build @@ -2,6 +2,7 @@ libperf-y += header.o libperf-y += sym-handling.o libperf-y += kvm-stat.o libperf-y += perf_regs.o +libperf-y += mem-events.o libperf-$(CONFIG_DWARF) += dwarf-regs.o libperf-$(CONFIG_DWARF) += skip-callchain-idx.o diff --git a/tools/perf/arch/powerpc/util/mem-events.c b/tools/perf/arch/powerpc/util/mem-events.c new file mode 100644 index 000000000000..d08311f04e95 --- /dev/null +++ b/tools/perf/arch/powerpc/util/mem-events.c @@ -0,0 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "mem-events.h" + +/* PowerPC does not support 'ldlat' parameter. */ +char *perf_mem_events__name(int i) +{ + if (i == PERF_MEM_EVENTS__LOAD) + return (char *) "cpu/mem-loads/"; + + return (char *) "cpu/mem-stores/"; +} diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index 93f74d8d3cdd..42c3e5a229d2 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -28,7 +28,7 @@ struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = { static char mem_loads_name[100]; static bool mem_loads_name__init; -char *perf_mem_events__name(int i) +char * __weak perf_mem_events__name(int i) { if (i == PERF_MEM_EVENTS__LOAD) { if (!mem_loads_name__init) { From d34cecfb6b2bdc35713180ba4fcfd912a2f3e9bf Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 4 Feb 2019 11:04:20 -0300 Subject: [PATCH 413/525] perf clang: Do not use 'return std::move(something)' MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It prevents copy elision, generating this warning when building with fedora:rawhide's clang: clang version 7.0.1 (Fedora 7.0.1-2.fc30) Target: x86_64-unknown-linux-gnu Thread model: posix InstalledDir: /usr/bin Found candidate GCC installation: /usr/bin/../lib/gcc/x86_64-redhat-linux/9 Found candidate GCC installation: /usr/lib/gcc/x86_64-redhat-linux/9 Selected GCC installation: /usr/bin/../lib/gcc/x86_64-redhat-linux/9 Candidate multilib: .;@m64 Candidate multilib: 32;@m32 Selected multilib: .;@m64 $ make -C tools/perf CC=clang LIBCLANGLLVM=1 util/c++/clang.cpp: In function 'std::unique_ptr > perf::getBPFObjectFromModule(llvm::Module*)': util/c++/clang.cpp:163:18: error: moving a local object in a return statement prevents copy elision [-Werror=pessimizing-move] 163 | return std::move(Buffer); | ~~~~~~~~~^~~~~~~~ util/c++/clang.cpp:163:18: note: remove 'std::move' call cc1plus: all warnings being treated as errors References: http://www.cplusplus.com/forum/general/186411/#msg908572 https://en.cppreference.com/w/cpp/language/return#Notes https://en.cppreference.com/w/cpp/language/copy_elision Cc: Adrian Hunter Cc: Jiri Olsa Cc: Luis Cláudio Gonçalves Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-lehqf5x5q96l0o8myhb6blz6@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/c++/clang.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp index 89512504551b..39c0004f2886 100644 --- a/tools/perf/util/c++/clang.cpp +++ b/tools/perf/util/c++/clang.cpp @@ -160,7 +160,7 @@ getBPFObjectFromModule(llvm::Module *Module) } PM.run(*Module); - return std::move(Buffer); + return Buffer; } } From 27b8e90eaea6a6fe8c1ab457443601dabff500d0 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 4 Feb 2019 11:34:20 -0300 Subject: [PATCH 414/525] tools headers uapi: Sync linux/in.h copy from the kernel sources To get the changes in this cset: f275ee0fa3a0 ("IN_BADCLASS: fix macro to actually work") The macros changed in this cset are not used in tools/, so this is just to silence this perf tools build warning: Warning: Kernel ABI header at 'tools/include/uapi/linux/in.h' differs from latest version at 'include/uapi/linux/in.h' diff -u tools/include/uapi/linux/in.h include/uapi/linux/in.h Cc: Adrian Hunter Cc: David S. Miller Cc: Greg Kroah-Hartman Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-xbk34kwamn8bw8ywpuxetct9@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/in.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index f6052e70bf40..a55cb8b10165 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -268,7 +268,7 @@ struct sockaddr_in { #define IN_MULTICAST(a) IN_CLASSD(a) #define IN_MULTICAST_NET 0xe0000000 -#define IN_BADCLASS(a) ((((long int) (a) ) == 0xffffffff) +#define IN_BADCLASS(a) (((long int) (a) ) == (long int)0xffffffff) #define IN_EXPERIMENTAL(a) IN_BADCLASS((a)) #define IN_CLASSE(a) ((((long int) (a)) & 0xf0000000) == 0xf0000000) From d23c808c6fc6132e812690648e14c0d6b0cbe273 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Mon, 4 Feb 2019 14:37:38 +0000 Subject: [PATCH 415/525] arm64: ptdump: Don't iterate kernel page tables using PTRS_PER_PXX When 52-bit virtual addressing is enabled for userspace (CONFIG_ARM64_USER_VA_BITS_52=y), the kernel continues to utilise 48-bit virtual addressing in TTBR1. Consequently, PTRS_PER_PGD reflects the larger page table size for userspace and the pgd pointer for kernel page tables is offset before being written to TTBR1. This means that we can't use PTRS_PER_PGD to iterate over kernel page tables unless we apply the same offset, which is fiddly to get right and leads to some non-idiomatic walking code. Instead, just follow the usual pattern when walking page tables by using a while loop driven by pXd_offset() and pXd_addr_end(). Reported-by: Qian Cai Tested-by: Qian Cai Acked-by: Steve Capper Tested-by: Steve Capper Signed-off-by: Will Deacon --- arch/arm64/mm/dump.c | 59 ++++++++++++++++++++++---------------------- 1 file changed, 29 insertions(+), 30 deletions(-) diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c index fcb1f2a6d7c6..99bb8facb5cb 100644 --- a/arch/arm64/mm/dump.c +++ b/arch/arm64/mm/dump.c @@ -286,74 +286,73 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level, } -static void walk_pte(struct pg_state *st, pmd_t *pmdp, unsigned long start) +static void walk_pte(struct pg_state *st, pmd_t *pmdp, unsigned long start, + unsigned long end) { - pte_t *ptep = pte_offset_kernel(pmdp, 0UL); - unsigned long addr; - unsigned i; + unsigned long addr = start; + pte_t *ptep = pte_offset_kernel(pmdp, start); - for (i = 0; i < PTRS_PER_PTE; i++, ptep++) { - addr = start + i * PAGE_SIZE; + do { note_page(st, addr, 4, READ_ONCE(pte_val(*ptep))); - } + } while (ptep++, addr += PAGE_SIZE, addr != end); } -static void walk_pmd(struct pg_state *st, pud_t *pudp, unsigned long start) +static void walk_pmd(struct pg_state *st, pud_t *pudp, unsigned long start, + unsigned long end) { - pmd_t *pmdp = pmd_offset(pudp, 0UL); - unsigned long addr; - unsigned i; + unsigned long next, addr = start; + pmd_t *pmdp = pmd_offset(pudp, start); - for (i = 0; i < PTRS_PER_PMD; i++, pmdp++) { + do { pmd_t pmd = READ_ONCE(*pmdp); + next = pmd_addr_end(addr, end); - addr = start + i * PMD_SIZE; if (pmd_none(pmd) || pmd_sect(pmd)) { note_page(st, addr, 3, pmd_val(pmd)); } else { BUG_ON(pmd_bad(pmd)); - walk_pte(st, pmdp, addr); + walk_pte(st, pmdp, addr, next); } - } + } while (pmdp++, addr = next, addr != end); } -static void walk_pud(struct pg_state *st, pgd_t *pgdp, unsigned long start) +static void walk_pud(struct pg_state *st, pgd_t *pgdp, unsigned long start, + unsigned long end) { - pud_t *pudp = pud_offset(pgdp, 0UL); - unsigned long addr; - unsigned i; + unsigned long next, addr = start; + pud_t *pudp = pud_offset(pgdp, start); - for (i = 0; i < PTRS_PER_PUD; i++, pudp++) { + do { pud_t pud = READ_ONCE(*pudp); + next = pud_addr_end(addr, end); - addr = start + i * PUD_SIZE; if (pud_none(pud) || pud_sect(pud)) { note_page(st, addr, 2, pud_val(pud)); } else { BUG_ON(pud_bad(pud)); - walk_pmd(st, pudp, addr); + walk_pmd(st, pudp, addr, next); } - } + } while (pudp++, addr = next, addr != end); } static void walk_pgd(struct pg_state *st, struct mm_struct *mm, unsigned long start) { - pgd_t *pgdp = pgd_offset(mm, 0UL); - unsigned i; - unsigned long addr; + unsigned long end = (start < TASK_SIZE_64) ? TASK_SIZE_64 : 0; + unsigned long next, addr = start; + pgd_t *pgdp = pgd_offset(mm, start); - for (i = 0; i < PTRS_PER_PGD; i++, pgdp++) { + do { pgd_t pgd = READ_ONCE(*pgdp); + next = pgd_addr_end(addr, end); - addr = start + i * PGDIR_SIZE; if (pgd_none(pgd)) { note_page(st, addr, 1, pgd_val(pgd)); } else { BUG_ON(pgd_bad(pgd)); - walk_pud(st, pgdp, addr); + walk_pud(st, pgdp, addr, next); } - } + } while (pgdp++, addr = next, addr != end); } void ptdump_walk_pgd(struct seq_file *m, struct ptdump_info *info) From f6ac8585897684374a19863fff21186a05805286 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sat, 2 Feb 2019 10:49:13 +0100 Subject: [PATCH 416/525] netfilter: nf_tables: unbind set in rule from commit path Anonymous sets that are bound to rules from the same transaction trigger a kernel splat from the abort path due to double set list removal and double free. This patch updates the logic to search for the transaction that is responsible for creating the set and disable the set list removal and release, given the rule is now responsible for this. Lookup is reverse since the transaction that adds the set is likely to be at the tail of the list. Moreover, this patch adds the unbind step to deliver the event from the commit path. This should not be done from the worker thread, since we have no guarantees of in-order delivery to the listener. This patch removes the assumption that both activate and deactivate callbacks need to be provided. Fixes: cd5125d8f518 ("netfilter: nf_tables: split set destruction in deactivate and destroy phase") Reported-by: Mikhail Morfikov Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 17 +++++-- net/netfilter/nf_tables_api.c | 85 +++++++++++++++---------------- net/netfilter/nft_compat.c | 6 ++- net/netfilter/nft_dynset.c | 18 +++---- net/netfilter/nft_immediate.c | 6 ++- net/netfilter/nft_lookup.c | 18 +++---- net/netfilter/nft_objref.c | 18 +++---- 7 files changed, 85 insertions(+), 83 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 841835a387e1..b4984bbbe157 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -469,9 +469,7 @@ struct nft_set_binding { int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding); void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_binding *binding); -void nf_tables_rebind_set(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_binding *binding); + struct nft_set_binding *binding, bool commit); void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set); /** @@ -721,6 +719,13 @@ struct nft_expr_type { #define NFT_EXPR_STATEFUL 0x1 #define NFT_EXPR_GC 0x2 +enum nft_trans_phase { + NFT_TRANS_PREPARE, + NFT_TRANS_ABORT, + NFT_TRANS_COMMIT, + NFT_TRANS_RELEASE +}; + /** * struct nft_expr_ops - nf_tables expression operations * @@ -750,7 +755,8 @@ struct nft_expr_ops { void (*activate)(const struct nft_ctx *ctx, const struct nft_expr *expr); void (*deactivate)(const struct nft_ctx *ctx, - const struct nft_expr *expr); + const struct nft_expr *expr, + enum nft_trans_phase phase); void (*destroy)(const struct nft_ctx *ctx, const struct nft_expr *expr); void (*destroy_clone)(const struct nft_ctx *ctx, @@ -1323,12 +1329,15 @@ struct nft_trans_rule { struct nft_trans_set { struct nft_set *set; u32 set_id; + bool bound; }; #define nft_trans_set(trans) \ (((struct nft_trans_set *)trans->data)->set) #define nft_trans_set_id(trans) \ (((struct nft_trans_set *)trans->data)->set_id) +#define nft_trans_set_bound(trans) \ + (((struct nft_trans_set *)trans->data)->bound) struct nft_trans_chain { bool update; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index fb07f6cfc719..5a92f23f179f 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -116,6 +116,23 @@ static void nft_trans_destroy(struct nft_trans *trans) kfree(trans); } +static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set) +{ + struct net *net = ctx->net; + struct nft_trans *trans; + + if (!nft_set_is_anonymous(set)) + return; + + list_for_each_entry_reverse(trans, &net->nft.commit_list, list) { + if (trans->msg_type == NFT_MSG_NEWSET && + nft_trans_set(trans) == set) { + nft_trans_set_bound(trans) = true; + break; + } + } +} + static int nf_tables_register_hook(struct net *net, const struct nft_table *table, struct nft_chain *chain) @@ -211,18 +228,6 @@ static int nft_delchain(struct nft_ctx *ctx) return err; } -/* either expr ops provide both activate/deactivate, or neither */ -static bool nft_expr_check_ops(const struct nft_expr_ops *ops) -{ - if (!ops) - return true; - - if (WARN_ON_ONCE((!ops->activate ^ !ops->deactivate))) - return false; - - return true; -} - static void nft_rule_expr_activate(const struct nft_ctx *ctx, struct nft_rule *rule) { @@ -238,14 +243,15 @@ static void nft_rule_expr_activate(const struct nft_ctx *ctx, } static void nft_rule_expr_deactivate(const struct nft_ctx *ctx, - struct nft_rule *rule) + struct nft_rule *rule, + enum nft_trans_phase phase) { struct nft_expr *expr; expr = nft_expr_first(rule); while (expr != nft_expr_last(rule) && expr->ops) { if (expr->ops->deactivate) - expr->ops->deactivate(ctx, expr); + expr->ops->deactivate(ctx, expr, phase); expr = nft_expr_next(expr); } @@ -296,7 +302,7 @@ static int nft_delrule(struct nft_ctx *ctx, struct nft_rule *rule) nft_trans_destroy(trans); return err; } - nft_rule_expr_deactivate(ctx, rule); + nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_PREPARE); return 0; } @@ -1929,9 +1935,6 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk, */ int nft_register_expr(struct nft_expr_type *type) { - if (!nft_expr_check_ops(type->ops)) - return -EINVAL; - nfnl_lock(NFNL_SUBSYS_NFTABLES); if (type->family == NFPROTO_UNSPEC) list_add_tail_rcu(&type->list, &nf_tables_expressions); @@ -2079,10 +2082,6 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx, err = PTR_ERR(ops); goto err1; } - if (!nft_expr_check_ops(ops)) { - err = -EINVAL; - goto err1; - } } else ops = type->ops; @@ -2511,7 +2510,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx, static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule) { - nft_rule_expr_deactivate(ctx, rule); + nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_RELEASE); nf_tables_rule_destroy(ctx, rule); } @@ -3708,39 +3707,30 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, bind: binding->chain = ctx->chain; list_add_tail_rcu(&binding->list, &set->bindings); + nft_set_trans_bind(ctx, set); + return 0; } EXPORT_SYMBOL_GPL(nf_tables_bind_set); -void nf_tables_rebind_set(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_binding *binding) -{ - if (list_empty(&set->bindings) && nft_set_is_anonymous(set) && - nft_is_active(ctx->net, set)) - list_add_tail_rcu(&set->list, &ctx->table->sets); - - list_add_tail_rcu(&binding->list, &set->bindings); -} -EXPORT_SYMBOL_GPL(nf_tables_rebind_set); - void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_binding *binding) + struct nft_set_binding *binding, bool event) { list_del_rcu(&binding->list); - if (list_empty(&set->bindings) && nft_set_is_anonymous(set) && - nft_is_active(ctx->net, set)) + if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) { list_del_rcu(&set->list); + if (event) + nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, + GFP_KERNEL); + } } EXPORT_SYMBOL_GPL(nf_tables_unbind_set); void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set) { - if (list_empty(&set->bindings) && nft_set_is_anonymous(set) && - nft_is_active(ctx->net, set)) { - nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, GFP_ATOMIC); + if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) nft_set_destroy(set); - } } EXPORT_SYMBOL_GPL(nf_tables_destroy_set); @@ -6535,6 +6525,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_rule_notify(&trans->ctx, nft_trans_rule(trans), NFT_MSG_DELRULE); + nft_rule_expr_deactivate(&trans->ctx, + nft_trans_rule(trans), + NFT_TRANS_COMMIT); break; case NFT_MSG_NEWSET: nft_clear(net, nft_trans_set(trans)); @@ -6621,7 +6614,8 @@ static void nf_tables_abort_release(struct nft_trans *trans) nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); break; case NFT_MSG_NEWSET: - nft_set_destroy(nft_trans_set(trans)); + if (!nft_trans_set_bound(trans)) + nft_set_destroy(nft_trans_set(trans)); break; case NFT_MSG_NEWSETELEM: nft_set_elem_destroy(nft_trans_elem_set(trans), @@ -6682,7 +6676,9 @@ static int __nf_tables_abort(struct net *net) case NFT_MSG_NEWRULE: trans->ctx.chain->use--; list_del_rcu(&nft_trans_rule(trans)->list); - nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans)); + nft_rule_expr_deactivate(&trans->ctx, + nft_trans_rule(trans), + NFT_TRANS_ABORT); break; case NFT_MSG_DELRULE: trans->ctx.chain->use++; @@ -6692,7 +6688,8 @@ static int __nf_tables_abort(struct net *net) break; case NFT_MSG_NEWSET: trans->ctx.table->use--; - list_del_rcu(&nft_trans_set(trans)->list); + if (!nft_trans_set_bound(trans)) + list_del_rcu(&nft_trans_set(trans)->list); break; case NFT_MSG_DELSET: trans->ctx.table->use++; diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 5eb269428832..0732a2fc697c 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -587,10 +587,14 @@ static void nft_compat_activate_tg(const struct nft_ctx *ctx, } static void nft_compat_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr) + const struct nft_expr *expr, + enum nft_trans_phase phase) { struct nft_xt *xt = container_of(expr->ops, struct nft_xt, ops); + if (phase == NFT_TRANS_COMMIT) + return; + if (--xt->listcnt == 0) list_del_init(&xt->head); } diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 07d4efd3d851..f1172f99752b 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -235,20 +235,17 @@ err1: return err; } -static void nft_dynset_activate(const struct nft_ctx *ctx, - const struct nft_expr *expr) -{ - struct nft_dynset *priv = nft_expr_priv(expr); - - nf_tables_rebind_set(ctx, priv->set, &priv->binding); -} - static void nft_dynset_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr) + const struct nft_expr *expr, + enum nft_trans_phase phase) { struct nft_dynset *priv = nft_expr_priv(expr); - nf_tables_unbind_set(ctx, priv->set, &priv->binding); + if (phase == NFT_TRANS_PREPARE) + return; + + nf_tables_unbind_set(ctx, priv->set, &priv->binding, + phase == NFT_TRANS_COMMIT); } static void nft_dynset_destroy(const struct nft_ctx *ctx, @@ -296,7 +293,6 @@ static const struct nft_expr_ops nft_dynset_ops = { .eval = nft_dynset_eval, .init = nft_dynset_init, .destroy = nft_dynset_destroy, - .activate = nft_dynset_activate, .deactivate = nft_dynset_deactivate, .dump = nft_dynset_dump, }; diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 0777a93211e2..3f6d1d2a6281 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -72,10 +72,14 @@ static void nft_immediate_activate(const struct nft_ctx *ctx, } static void nft_immediate_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr) + const struct nft_expr *expr, + enum nft_trans_phase phase) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); + if (phase == NFT_TRANS_COMMIT) + return; + return nft_data_release(&priv->data, nft_dreg_to_type(priv->dreg)); } diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 227b2b15a19c..14496da5141d 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -121,20 +121,17 @@ static int nft_lookup_init(const struct nft_ctx *ctx, return 0; } -static void nft_lookup_activate(const struct nft_ctx *ctx, - const struct nft_expr *expr) -{ - struct nft_lookup *priv = nft_expr_priv(expr); - - nf_tables_rebind_set(ctx, priv->set, &priv->binding); -} - static void nft_lookup_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr) + const struct nft_expr *expr, + enum nft_trans_phase phase) { struct nft_lookup *priv = nft_expr_priv(expr); - nf_tables_unbind_set(ctx, priv->set, &priv->binding); + if (phase == NFT_TRANS_PREPARE) + return; + + nf_tables_unbind_set(ctx, priv->set, &priv->binding, + phase == NFT_TRANS_COMMIT); } static void nft_lookup_destroy(const struct nft_ctx *ctx, @@ -225,7 +222,6 @@ static const struct nft_expr_ops nft_lookup_ops = { .size = NFT_EXPR_SIZE(sizeof(struct nft_lookup)), .eval = nft_lookup_eval, .init = nft_lookup_init, - .activate = nft_lookup_activate, .deactivate = nft_lookup_deactivate, .destroy = nft_lookup_destroy, .dump = nft_lookup_dump, diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index a3185ca2a3a9..ae178e914486 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -155,20 +155,17 @@ nla_put_failure: return -1; } -static void nft_objref_map_activate(const struct nft_ctx *ctx, - const struct nft_expr *expr) -{ - struct nft_objref_map *priv = nft_expr_priv(expr); - - nf_tables_rebind_set(ctx, priv->set, &priv->binding); -} - static void nft_objref_map_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr) + const struct nft_expr *expr, + enum nft_trans_phase phase) { struct nft_objref_map *priv = nft_expr_priv(expr); - nf_tables_unbind_set(ctx, priv->set, &priv->binding); + if (phase == NFT_TRANS_PREPARE) + return; + + nf_tables_unbind_set(ctx, priv->set, &priv->binding, + phase == NFT_TRANS_COMMIT); } static void nft_objref_map_destroy(const struct nft_ctx *ctx, @@ -185,7 +182,6 @@ static const struct nft_expr_ops nft_objref_map_ops = { .size = NFT_EXPR_SIZE(sizeof(struct nft_objref_map)), .eval = nft_objref_map_eval, .init = nft_objref_map_init, - .activate = nft_objref_map_activate, .deactivate = nft_objref_map_deactivate, .destroy = nft_objref_map_destroy, .dump = nft_objref_map_dump, From 53bc8d2af08654659abfadfd3e98eb9922ff787c Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 4 Feb 2019 11:20:29 +0100 Subject: [PATCH 417/525] net: dp83640: expire old TX-skb During sendmsg() a cloned skb is saved via dp83640_txtstamp() in ->tx_queue. After the NIC sends this packet, the PHY will reply with a timestamp for that TX packet. If the cable is pulled at the right time I don't see that packet. It might gets flushed as part of queue shutdown on NIC's side. Once the link is up again then after the next sendmsg() we enqueue another skb in dp83640_txtstamp() and have two on the list. Then the PHY will send a reply and decode_txts() attaches it to the first skb on the list. No crash occurs since refcounting works but we are one packet behind. linuxptp/ptp4l usually closes the socket and opens a new one (in such a timeout case) so those "stale" replies never get there. However it does not resume normal operation anymore. Purge old skbs in decode_txts(). Fixes: cb646e2b02b2 ("ptp: Added a clock driver for the National Semiconductor PHYTER.") Signed-off-by: Sebastian Andrzej Siewior Reviewed-by: Kurt Kanzenbach Acked-by: Richard Cochran Signed-off-by: David S. Miller --- drivers/net/phy/dp83640.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 18b41bc345ab..6e8807212aa3 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -898,14 +898,14 @@ static void decode_txts(struct dp83640_private *dp83640, struct phy_txts *phy_txts) { struct skb_shared_hwtstamps shhwtstamps; + struct dp83640_skb_info *skb_info; struct sk_buff *skb; - u64 ns; u8 overflow; + u64 ns; /* We must already have the skb that triggered this. */ - +again: skb = skb_dequeue(&dp83640->tx_queue); - if (!skb) { pr_debug("have timestamp but tx_queue empty\n"); return; @@ -920,6 +920,11 @@ static void decode_txts(struct dp83640_private *dp83640, } return; } + skb_info = (struct dp83640_skb_info *)skb->cb; + if (time_after(jiffies, skb_info->tmo)) { + kfree_skb(skb); + goto again; + } ns = phy2txts(phy_txts); memset(&shhwtstamps, 0, sizeof(shhwtstamps)); @@ -1472,6 +1477,7 @@ static bool dp83640_rxtstamp(struct phy_device *phydev, static void dp83640_txtstamp(struct phy_device *phydev, struct sk_buff *skb, int type) { + struct dp83640_skb_info *skb_info = (struct dp83640_skb_info *)skb->cb; struct dp83640_private *dp83640 = phydev->priv; switch (dp83640->hwts_tx_en) { @@ -1484,6 +1490,7 @@ static void dp83640_txtstamp(struct phy_device *phydev, /* fall through */ case HWTSTAMP_TX_ON: skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + skb_info->tmo = jiffies + SKB_TIMESTAMP_TIMEOUT; skb_queue_tail(&dp83640->tx_queue, skb); break; From ad6f317f720f4a3121756c23831a43dda9b095e5 Mon Sep 17 00:00:00 2001 From: Ursula Braun Date: Mon, 4 Feb 2019 13:44:44 +0100 Subject: [PATCH 418/525] net/smc: preallocated memory for rdma work requests The work requests for rdma writes are built in local variables within function smc_tx_rdma_write(). This violates the rule that the work request storage has to stay till the work request is confirmed by a completion queue response. This patch introduces preallocated memory for these work requests. The storage is allocated, once a link (and thus a queue pair) is established. Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/smc_cdc.c | 11 +++-------- net/smc/smc_cdc.h | 8 +++++++- net/smc/smc_core.h | 20 ++++++++++++++++++++ net/smc/smc_llc.c | 3 ++- net/smc/smc_tx.c | 44 ++++++++++++++++++++++---------------------- net/smc/smc_wr.c | 38 +++++++++++++++++++++++++++++++++++++- net/smc/smc_wr.h | 1 + 7 files changed, 92 insertions(+), 33 deletions(-) diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index 1c5333d494e9..b80ef104ab4e 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -21,13 +21,6 @@ /********************************** send *************************************/ -struct smc_cdc_tx_pend { - struct smc_connection *conn; /* socket connection */ - union smc_host_cursor cursor; /* tx sndbuf cursor sent */ - union smc_host_cursor p_cursor; /* rx RMBE cursor produced */ - u16 ctrl_seq; /* conn. tx sequence # */ -}; - /* handler for send/transmission completion of a CDC msg */ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd, struct smc_link *link, @@ -61,12 +54,14 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd, int smc_cdc_get_free_slot(struct smc_connection *conn, struct smc_wr_buf **wr_buf, + struct smc_rdma_wr **wr_rdma_buf, struct smc_cdc_tx_pend **pend) { struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK]; int rc; rc = smc_wr_tx_get_free_slot(link, smc_cdc_tx_handler, wr_buf, + wr_rdma_buf, (struct smc_wr_tx_pend_priv **)pend); if (!conn->alert_token_local) /* abnormal termination */ @@ -121,7 +116,7 @@ static int smcr_cdc_get_slot_and_msg_send(struct smc_connection *conn) struct smc_wr_buf *wr_buf; int rc; - rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend); + rc = smc_cdc_get_free_slot(conn, &wr_buf, NULL, &pend); if (rc) return rc; diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h index b5bfe38c7f9b..2148da7a26b1 100644 --- a/net/smc/smc_cdc.h +++ b/net/smc/smc_cdc.h @@ -270,10 +270,16 @@ static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local, smcr_cdc_msg_to_host(local, peer, conn); } -struct smc_cdc_tx_pend; +struct smc_cdc_tx_pend { + struct smc_connection *conn; /* socket connection */ + union smc_host_cursor cursor; /* tx sndbuf cursor sent */ + union smc_host_cursor p_cursor; /* rx RMBE cursor produced */ + u16 ctrl_seq; /* conn. tx sequence # */ +}; int smc_cdc_get_free_slot(struct smc_connection *conn, struct smc_wr_buf **wr_buf, + struct smc_rdma_wr **wr_rdma_buf, struct smc_cdc_tx_pend **pend); void smc_cdc_tx_dismiss_slots(struct smc_connection *conn); int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf, diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index b00287989a3d..8806d2afa6ed 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -52,6 +52,24 @@ enum smc_wr_reg_state { FAILED /* ib_wr_reg_mr response: failure */ }; +struct smc_rdma_sge { /* sges for RDMA writes */ + struct ib_sge wr_tx_rdma_sge[SMC_IB_MAX_SEND_SGE]; +}; + +#define SMC_MAX_RDMA_WRITES 2 /* max. # of RDMA writes per + * message send + */ + +struct smc_rdma_sges { /* sges per message send */ + struct smc_rdma_sge tx_rdma_sge[SMC_MAX_RDMA_WRITES]; +}; + +struct smc_rdma_wr { /* work requests per message + * send + */ + struct ib_rdma_wr wr_tx_rdma[SMC_MAX_RDMA_WRITES]; +}; + struct smc_link { struct smc_ib_device *smcibdev; /* ib-device */ u8 ibport; /* port - values 1 | 2 */ @@ -64,6 +82,8 @@ struct smc_link { struct smc_wr_buf *wr_tx_bufs; /* WR send payload buffers */ struct ib_send_wr *wr_tx_ibs; /* WR send meta data */ struct ib_sge *wr_tx_sges; /* WR send gather meta data */ + struct smc_rdma_sges *wr_tx_rdma_sges;/*RDMA WRITE gather meta data*/ + struct smc_rdma_wr *wr_tx_rdmas; /* WR RDMA WRITE */ struct smc_wr_tx_pend *wr_tx_pends; /* WR send waiting for CQE */ /* above four vectors have wr_tx_cnt elements and use the same index */ dma_addr_t wr_tx_dma_addr; /* DMA address of wr_tx_bufs */ diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index a6d3623d06f4..4fd60c522802 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -166,7 +166,8 @@ static int smc_llc_add_pending_send(struct smc_link *link, { int rc; - rc = smc_wr_tx_get_free_slot(link, smc_llc_tx_handler, wr_buf, pend); + rc = smc_wr_tx_get_free_slot(link, smc_llc_tx_handler, wr_buf, NULL, + pend); if (rc < 0) return rc; BUILD_BUG_ON_MSG( diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index 36af3de731b9..2fdfaff60cf9 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -266,27 +266,23 @@ int smcd_tx_ism_write(struct smc_connection *conn, void *data, size_t len, /* sndbuf consumer: actual data transfer of one target chunk with RDMA write */ static int smc_tx_rdma_write(struct smc_connection *conn, int peer_rmbe_offset, - int num_sges, struct ib_sge sges[]) + int num_sges, struct ib_rdma_wr *rdma_wr) { struct smc_link_group *lgr = conn->lgr; - struct ib_rdma_wr rdma_wr; struct smc_link *link; int rc; - memset(&rdma_wr, 0, sizeof(rdma_wr)); link = &lgr->lnk[SMC_SINGLE_LINK]; - rdma_wr.wr.wr_id = smc_wr_tx_get_next_wr_id(link); - rdma_wr.wr.sg_list = sges; - rdma_wr.wr.num_sge = num_sges; - rdma_wr.wr.opcode = IB_WR_RDMA_WRITE; - rdma_wr.remote_addr = + rdma_wr->wr.wr_id = smc_wr_tx_get_next_wr_id(link); + rdma_wr->wr.num_sge = num_sges; + rdma_wr->remote_addr = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].dma_addr + /* RMBE within RMB */ conn->tx_off + /* offset within RMBE */ peer_rmbe_offset; - rdma_wr.rkey = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].rkey; - rc = ib_post_send(link->roce_qp, &rdma_wr.wr, NULL); + rdma_wr->rkey = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].rkey; + rc = ib_post_send(link->roce_qp, &rdma_wr->wr, NULL); if (rc) { conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1; smc_lgr_terminate(lgr); @@ -313,24 +309,25 @@ static inline void smc_tx_advance_cursors(struct smc_connection *conn, /* SMC-R helper for smc_tx_rdma_writes() */ static int smcr_tx_rdma_writes(struct smc_connection *conn, size_t len, size_t src_off, size_t src_len, - size_t dst_off, size_t dst_len) + size_t dst_off, size_t dst_len, + struct smc_rdma_wr *wr_rdma_buf) { dma_addr_t dma_addr = sg_dma_address(conn->sndbuf_desc->sgt[SMC_SINGLE_LINK].sgl); - struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK]; int src_len_sum = src_len, dst_len_sum = dst_len; - struct ib_sge sges[SMC_IB_MAX_SEND_SGE]; int sent_count = src_off; int srcchunk, dstchunk; int num_sges; int rc; for (dstchunk = 0; dstchunk < 2; dstchunk++) { + struct ib_sge *sge = + wr_rdma_buf->wr_tx_rdma[dstchunk].wr.sg_list; + num_sges = 0; for (srcchunk = 0; srcchunk < 2; srcchunk++) { - sges[srcchunk].addr = dma_addr + src_off; - sges[srcchunk].length = src_len; - sges[srcchunk].lkey = link->roce_pd->local_dma_lkey; + sge[srcchunk].addr = dma_addr + src_off; + sge[srcchunk].length = src_len; num_sges++; src_off += src_len; @@ -343,7 +340,8 @@ static int smcr_tx_rdma_writes(struct smc_connection *conn, size_t len, src_len = dst_len - src_len; /* remainder */ src_len_sum += src_len; } - rc = smc_tx_rdma_write(conn, dst_off, num_sges, sges); + rc = smc_tx_rdma_write(conn, dst_off, num_sges, + &wr_rdma_buf->wr_tx_rdma[dstchunk]); if (rc) return rc; if (dst_len_sum == len) @@ -402,7 +400,8 @@ static int smcd_tx_rdma_writes(struct smc_connection *conn, size_t len, /* sndbuf consumer: prepare all necessary (src&dst) chunks of data transmit; * usable snd_wnd as max transmit */ -static int smc_tx_rdma_writes(struct smc_connection *conn) +static int smc_tx_rdma_writes(struct smc_connection *conn, + struct smc_rdma_wr *wr_rdma_buf) { size_t len, src_len, dst_off, dst_len; /* current chunk values */ union smc_host_cursor sent, prep, prod, cons; @@ -463,7 +462,7 @@ static int smc_tx_rdma_writes(struct smc_connection *conn) dst_off, dst_len); else rc = smcr_tx_rdma_writes(conn, len, sent.count, src_len, - dst_off, dst_len); + dst_off, dst_len, wr_rdma_buf); if (rc) return rc; @@ -484,11 +483,12 @@ static int smc_tx_rdma_writes(struct smc_connection *conn) static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn) { struct smc_cdc_producer_flags *pflags; + struct smc_rdma_wr *wr_rdma_buf; struct smc_cdc_tx_pend *pend; struct smc_wr_buf *wr_buf; int rc; - rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend); + rc = smc_cdc_get_free_slot(conn, &wr_buf, &wr_rdma_buf, &pend); if (rc < 0) { if (rc == -EBUSY) { struct smc_sock *smc = @@ -506,7 +506,7 @@ static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn) spin_lock_bh(&conn->send_lock); if (!conn->local_tx_ctrl.prod_flags.urg_data_present) { - rc = smc_tx_rdma_writes(conn); + rc = smc_tx_rdma_writes(conn, wr_rdma_buf); if (rc) { smc_wr_tx_put_slot(&conn->lgr->lnk[SMC_SINGLE_LINK], (struct smc_wr_tx_pend_priv *)pend); @@ -533,7 +533,7 @@ static int smcd_tx_sndbuf_nonempty(struct smc_connection *conn) spin_lock_bh(&conn->send_lock); if (!pflags->urg_data_present) - rc = smc_tx_rdma_writes(conn); + rc = smc_tx_rdma_writes(conn, NULL); if (!rc) rc = smcd_cdc_msg_send(conn); diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index 1dc88c32d6bb..253aa75dc2b6 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -160,6 +160,7 @@ static inline int smc_wr_tx_get_free_slot_index(struct smc_link *link, u32 *idx) * @link: Pointer to smc_link used to later send the message. * @handler: Send completion handler function pointer. * @wr_buf: Out value returns pointer to message buffer. + * @wr_rdma_buf: Out value returns pointer to rdma work request. * @wr_pend_priv: Out value returns pointer serving as handler context. * * Return: 0 on success, or -errno on error. @@ -167,6 +168,7 @@ static inline int smc_wr_tx_get_free_slot_index(struct smc_link *link, u32 *idx) int smc_wr_tx_get_free_slot(struct smc_link *link, smc_wr_tx_handler handler, struct smc_wr_buf **wr_buf, + struct smc_rdma_wr **wr_rdma_buf, struct smc_wr_tx_pend_priv **wr_pend_priv) { struct smc_wr_tx_pend *wr_pend; @@ -204,6 +206,8 @@ int smc_wr_tx_get_free_slot(struct smc_link *link, wr_ib = &link->wr_tx_ibs[idx]; wr_ib->wr_id = wr_id; *wr_buf = &link->wr_tx_bufs[idx]; + if (wr_rdma_buf) + *wr_rdma_buf = &link->wr_tx_rdmas[idx]; *wr_pend_priv = &wr_pend->priv; return 0; } @@ -465,12 +469,26 @@ static void smc_wr_init_sge(struct smc_link *lnk) lnk->wr_tx_dma_addr + i * SMC_WR_BUF_SIZE; lnk->wr_tx_sges[i].length = SMC_WR_TX_SIZE; lnk->wr_tx_sges[i].lkey = lnk->roce_pd->local_dma_lkey; + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge[0].lkey = + lnk->roce_pd->local_dma_lkey; + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge[1].lkey = + lnk->roce_pd->local_dma_lkey; + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge[0].lkey = + lnk->roce_pd->local_dma_lkey; + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge[1].lkey = + lnk->roce_pd->local_dma_lkey; lnk->wr_tx_ibs[i].next = NULL; lnk->wr_tx_ibs[i].sg_list = &lnk->wr_tx_sges[i]; lnk->wr_tx_ibs[i].num_sge = 1; lnk->wr_tx_ibs[i].opcode = IB_WR_SEND; lnk->wr_tx_ibs[i].send_flags = IB_SEND_SIGNALED | IB_SEND_SOLICITED; + lnk->wr_tx_rdmas[i].wr_tx_rdma[0].wr.opcode = IB_WR_RDMA_WRITE; + lnk->wr_tx_rdmas[i].wr_tx_rdma[1].wr.opcode = IB_WR_RDMA_WRITE; + lnk->wr_tx_rdmas[i].wr_tx_rdma[0].wr.sg_list = + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge; + lnk->wr_tx_rdmas[i].wr_tx_rdma[1].wr.sg_list = + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge; } for (i = 0; i < lnk->wr_rx_cnt; i++) { lnk->wr_rx_sges[i].addr = @@ -521,8 +539,12 @@ void smc_wr_free_link_mem(struct smc_link *lnk) lnk->wr_tx_mask = NULL; kfree(lnk->wr_tx_sges); lnk->wr_tx_sges = NULL; + kfree(lnk->wr_tx_rdma_sges); + lnk->wr_tx_rdma_sges = NULL; kfree(lnk->wr_rx_sges); lnk->wr_rx_sges = NULL; + kfree(lnk->wr_tx_rdmas); + lnk->wr_tx_rdmas = NULL; kfree(lnk->wr_rx_ibs); lnk->wr_rx_ibs = NULL; kfree(lnk->wr_tx_ibs); @@ -552,10 +574,20 @@ int smc_wr_alloc_link_mem(struct smc_link *link) GFP_KERNEL); if (!link->wr_rx_ibs) goto no_mem_wr_tx_ibs; + link->wr_tx_rdmas = kcalloc(SMC_WR_BUF_CNT, + sizeof(link->wr_tx_rdmas[0]), + GFP_KERNEL); + if (!link->wr_tx_rdmas) + goto no_mem_wr_rx_ibs; + link->wr_tx_rdma_sges = kcalloc(SMC_WR_BUF_CNT, + sizeof(link->wr_tx_rdma_sges[0]), + GFP_KERNEL); + if (!link->wr_tx_rdma_sges) + goto no_mem_wr_tx_rdmas; link->wr_tx_sges = kcalloc(SMC_WR_BUF_CNT, sizeof(link->wr_tx_sges[0]), GFP_KERNEL); if (!link->wr_tx_sges) - goto no_mem_wr_rx_ibs; + goto no_mem_wr_tx_rdma_sges; link->wr_rx_sges = kcalloc(SMC_WR_BUF_CNT * 3, sizeof(link->wr_rx_sges[0]), GFP_KERNEL); @@ -579,6 +611,10 @@ no_mem_wr_rx_sges: kfree(link->wr_rx_sges); no_mem_wr_tx_sges: kfree(link->wr_tx_sges); +no_mem_wr_tx_rdma_sges: + kfree(link->wr_tx_rdma_sges); +no_mem_wr_tx_rdmas: + kfree(link->wr_tx_rdmas); no_mem_wr_rx_ibs: kfree(link->wr_rx_ibs); no_mem_wr_tx_ibs: diff --git a/net/smc/smc_wr.h b/net/smc/smc_wr.h index 1d85bb14fd6f..09bf32fd3959 100644 --- a/net/smc/smc_wr.h +++ b/net/smc/smc_wr.h @@ -85,6 +85,7 @@ void smc_wr_add_dev(struct smc_ib_device *smcibdev); int smc_wr_tx_get_free_slot(struct smc_link *link, smc_wr_tx_handler handler, struct smc_wr_buf **wr_buf, + struct smc_rdma_wr **wrs, struct smc_wr_tx_pend_priv **wr_pend_priv); int smc_wr_tx_put_slot(struct smc_link *link, struct smc_wr_tx_pend_priv *wr_pend_priv); From b8649efad879c69c7ab1f19ce8814fcabef1f72b Mon Sep 17 00:00:00 2001 From: Ursula Braun Date: Mon, 4 Feb 2019 13:44:45 +0100 Subject: [PATCH 419/525] net/smc: fix sender_free computation In some scenarios a separate consumer cursor update is necessary. The decision is made in smc_tx_consumer_cursor_update(). The sender_free computation could be wrong: The rx confirmed cursor is always smaller than or equal to the rx producer cursor. The parameters in the smc_curs_diff() call have to be exchanged, otherwise sender_free might even be negative. And if more data arrives local_rx_ctrl.prod might be updated, enabling a cursor difference between local_rx_ctrl.prod and rx confirmed cursor larger than the RMB size. This case is not covered by smc_curs_diff(). Thus function smc_curs_diff_large() is introduced here. If a recvmsg() is processed in parallel, local_tx_ctrl.cons might change during smc_cdc_msg_send. Make sure rx_curs_confirmed is updated with the actually sent local_tx_ctrl.cons value. Fixes: e82f2e31f559 ("net/smc: optimize consumer cursor updates") Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/smc_cdc.c | 5 +++-- net/smc/smc_cdc.h | 26 +++++++++++++++++++++++++- net/smc/smc_tx.c | 3 ++- 3 files changed, 30 insertions(+), 4 deletions(-) diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index b80ef104ab4e..a712c9f8699b 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -91,6 +91,7 @@ int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf, struct smc_cdc_tx_pend *pend) { + union smc_host_cursor cfed; struct smc_link *link; int rc; @@ -102,10 +103,10 @@ int smc_cdc_msg_send(struct smc_connection *conn, conn->local_tx_ctrl.seqno = conn->tx_cdc_seq; smc_host_msg_to_cdc((struct smc_cdc_msg *)wr_buf, &conn->local_tx_ctrl, conn); + smc_curs_copy(&cfed, &((struct smc_host_cdc_msg *)wr_buf)->cons, conn); rc = smc_wr_tx_send(link, (struct smc_wr_tx_pend_priv *)pend); if (!rc) - smc_curs_copy(&conn->rx_curs_confirmed, - &conn->local_tx_ctrl.cons, conn); + smc_curs_copy(&conn->rx_curs_confirmed, &cfed, conn); return rc; } diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h index 2148da7a26b1..271e2524dc8f 100644 --- a/net/smc/smc_cdc.h +++ b/net/smc/smc_cdc.h @@ -160,7 +160,9 @@ static inline void smcd_curs_copy(union smcd_cdc_cursor *tgt, #endif } -/* calculate cursor difference between old and new, where old <= new */ +/* calculate cursor difference between old and new, where old <= new and + * difference cannot exceed size + */ static inline int smc_curs_diff(unsigned int size, union smc_host_cursor *old, union smc_host_cursor *new) @@ -185,6 +187,28 @@ static inline int smc_curs_comp(unsigned int size, return smc_curs_diff(size, old, new); } +/* calculate cursor difference between old and new, where old <= new and + * difference may exceed size + */ +static inline int smc_curs_diff_large(unsigned int size, + union smc_host_cursor *old, + union smc_host_cursor *new) +{ + if (old->wrap < new->wrap) + return min_t(int, + (size - old->count) + new->count + + (new->wrap - old->wrap - 1) * size, + size); + + if (old->wrap > new->wrap) /* wrap has switched from 0xffff to 0x0000 */ + return min_t(int, + (size - old->count) + new->count + + (new->wrap + 0xffff - old->wrap) * size, + size); + + return max_t(int, 0, (new->count - old->count)); +} + static inline void smc_host_cursor_to_cdc(union smc_cdc_cursor *peer, union smc_host_cursor *local, struct smc_connection *conn) diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index 2fdfaff60cf9..f93f3580c100 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -595,7 +595,8 @@ void smc_tx_consumer_update(struct smc_connection *conn, bool force) if (to_confirm > conn->rmbe_update_limit) { smc_curs_copy(&prod, &conn->local_rx_ctrl.prod, conn); sender_free = conn->rmb_desc->len - - smc_curs_diff(conn->rmb_desc->len, &prod, &cfed); + smc_curs_diff_large(conn->rmb_desc->len, + &cfed, &prod); } if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req || From a5e04318c83a31925300af1ce358dbc1a708b732 Mon Sep 17 00:00:00 2001 From: Ursula Braun Date: Mon, 4 Feb 2019 13:44:46 +0100 Subject: [PATCH 420/525] net/smc: delete rkey first before switching to unused Once RMBs are flagged as unused they are candidates for reuse. Thus the LLC DELETE RKEY operaton should be made before flagging the RMB as unused. Fixes: c7674c001b11 ("net/smc: unregister rkeys of unused buffer") Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/smc_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 097c798983ca..aa1c551cee81 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -302,13 +302,13 @@ static void smc_buf_unuse(struct smc_connection *conn, conn->sndbuf_desc->used = 0; if (conn->rmb_desc) { if (!conn->rmb_desc->regerr) { - conn->rmb_desc->used = 0; if (!lgr->is_smcd) { /* unregister rmb with peer */ smc_llc_do_delete_rkey( &lgr->lnk[SMC_SINGLE_LINK], conn->rmb_desc); } + conn->rmb_desc->used = 0; } else { /* buf registration failed, reuse not possible */ write_lock_bh(&lgr->rmbs_lock); From 84b799a292ebc03de388f8573a169de6eb12c340 Mon Sep 17 00:00:00 2001 From: Ursula Braun Date: Mon, 4 Feb 2019 13:44:47 +0100 Subject: [PATCH 421/525] net/smc: correct state change for peer closing If some kind of closing is received from the peer while still in state SMC_INIT, it means the peer has had an active connection and closed the socket quickly before listen_work finished. This should not result in a shortcut from state SMC_INIT to state SMC_CLOSED. This patch adds the socket to the accept queue in state SMC_APPCLOSEWAIT1. The socket reaches state SMC_CLOSED once being accepted and closed with smc_release(). Signed-off-by: Ursula Braun Signed-off-by: David S. Miller --- net/smc/smc_close.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index ea2b87f29469..e39cadda1bf5 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -345,14 +345,7 @@ static void smc_close_passive_work(struct work_struct *work) switch (sk->sk_state) { case SMC_INIT: - if (atomic_read(&conn->bytes_to_rcv) || - (rxflags->peer_done_writing && - !smc_cdc_rxed_any_close(conn))) { - sk->sk_state = SMC_APPCLOSEWAIT1; - } else { - sk->sk_state = SMC_CLOSED; - sock_put(sk); /* passive closing */ - } + sk->sk_state = SMC_APPCLOSEWAIT1; break; case SMC_ACTIVE: sk->sk_state = SMC_APPCLOSEWAIT1; From c1f7e02979edd7a3a3e69fe04be60b1d650dc8a7 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Mon, 4 Feb 2019 14:50:38 +0000 Subject: [PATCH 422/525] net: cls_flower: Remove filter from mask before freeing it In fl_change(), when adding a new rule (i.e. fold == NULL), a driver may reject the new rule, for example due to resource exhaustion. By that point, the new rule was already assigned a mask, and it was added to that mask's hash table. The clean-up path that's invoked as a result of the rejection however neglects to undo the hash table addition, and proceeds to free the new rule, thus leaving a dangling pointer in the hash table. Fix by removing fnew from the mask's hash table before it is freed. Fixes: 35cc3cefc4de ("net/sched: cls_flower: Reject duplicated rules also under skip_sw") Signed-off-by: Petr Machata Acked-by: Jiri Pirko Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- net/sched/cls_flower.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index f6aa57fbbbaf..12ca9d13db83 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1371,7 +1371,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, if (!tc_skip_hw(fnew->flags)) { err = fl_hw_replace_filter(tp, fnew, extack); if (err) - goto errout_mask; + goto errout_mask_ht; } if (!tc_in_hw(fnew->flags)) @@ -1401,6 +1401,10 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, kfree(mask); return 0; +errout_mask_ht: + rhashtable_remove_fast(&fnew->mask->ht, &fnew->ht_node, + fnew->mask->filter_ht_params); + errout_mask: fl_mask_put(head, fnew->mask, false); From 5065b2dd3e5f9247a6c9d67974bc0472bf561b9d Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Mon, 4 Feb 2019 17:40:06 +0100 Subject: [PATCH 423/525] s390/qeth: release cmd buffer in error paths Whenever we fail before/while starting an IO, make sure to release the IO buffer. Usually qeth_irq() would do this for us, but if the IO doesn't even start we obviously won't get an interrupt for it either. Signed-off-by: Julian Wiedmann Signed-off-by: David S. Miller --- drivers/s390/net/qeth_core_main.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index e63e03143ca7..ca62e7d3ee93 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -566,6 +566,7 @@ static int __qeth_issue_next_read(struct qeth_card *card) QETH_DBF_MESSAGE(2, "error %i on device %x when starting next read ccw!\n", rc, CARD_DEVID(card)); atomic_set(&channel->irq_pending, 0); + qeth_release_buffer(channel, iob); card->read_or_write_problem = 1; qeth_schedule_recovery(card); wake_up(&card->wait_q); @@ -1127,6 +1128,8 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, rc = qeth_get_problem(card, cdev, irb); if (rc) { card->read_or_write_problem = 1; + if (iob) + qeth_release_buffer(iob->channel, iob); qeth_clear_ipacmd_list(card); qeth_schedule_recovery(card); goto out; @@ -1809,6 +1812,7 @@ static int qeth_idx_activate_get_answer(struct qeth_card *card, QETH_DBF_MESSAGE(2, "Error2 in activating channel rc=%d\n", rc); QETH_DBF_TEXT_(SETUP, 2, "2err%d", rc); atomic_set(&channel->irq_pending, 0); + qeth_release_buffer(channel, iob); wake_up(&card->wait_q); return rc; } @@ -1878,6 +1882,7 @@ static int qeth_idx_activate_channel(struct qeth_card *card, rc); QETH_DBF_TEXT_(SETUP, 2, "1err%d", rc); atomic_set(&channel->irq_pending, 0); + qeth_release_buffer(channel, iob); wake_up(&card->wait_q); return rc; } @@ -2058,6 +2063,7 @@ int qeth_send_control_data(struct qeth_card *card, int len, } reply = qeth_alloc_reply(card); if (!reply) { + qeth_release_buffer(channel, iob); return -ENOMEM; } reply->callback = reply_cb; From afa0c5904ba16d59b0454f7ee4c807dae350f432 Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Mon, 4 Feb 2019 17:40:07 +0100 Subject: [PATCH 424/525] s390/qeth: fix use-after-free in error path The error path in qeth_alloc_qdio_buffers() that takes care of cleaning up the Output Queues is buggy. It first frees the queue, but then calls qeth_clear_outq_buffers() with that very queue struct. Make the call to qeth_clear_outq_buffers() part of the free action (in the correct order), and while at it fix the naming of the helper. Fixes: 0da9581ddb0f ("qeth: exploit asynchronous delivery of storage blocks") Signed-off-by: Julian Wiedmann Reviewed-by: Alexandra Winter Signed-off-by: David S. Miller --- drivers/s390/net/qeth_core_main.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index ca62e7d3ee93..30679bfc8a1b 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -2395,11 +2395,12 @@ static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *q, int bidx) return 0; } -static void qeth_free_qdio_out_buf(struct qeth_qdio_out_q *q) +static void qeth_free_output_queue(struct qeth_qdio_out_q *q) { if (!q) return; + qeth_clear_outq_buffers(q, 1); qdio_free_buffers(q->qdio_bufs, QDIO_MAX_BUFFERS_PER_Q); kfree(q); } @@ -2473,10 +2474,8 @@ out_freeoutqbufs: card->qdio.out_qs[i]->bufs[j] = NULL; } out_freeoutq: - while (i > 0) { - qeth_free_qdio_out_buf(card->qdio.out_qs[--i]); - qeth_clear_outq_buffers(card->qdio.out_qs[i], 1); - } + while (i > 0) + qeth_free_output_queue(card->qdio.out_qs[--i]); kfree(card->qdio.out_qs); card->qdio.out_qs = NULL; out_freepool: @@ -2509,10 +2508,8 @@ static void qeth_free_qdio_buffers(struct qeth_card *card) qeth_free_buffer_pool(card); /* free outbound qdio_qs */ if (card->qdio.out_qs) { - for (i = 0; i < card->qdio.no_out_queues; ++i) { - qeth_clear_outq_buffers(card->qdio.out_qs[i], 1); - qeth_free_qdio_out_buf(card->qdio.out_qs[i]); - } + for (i = 0; i < card->qdio.no_out_queues; i++) + qeth_free_output_queue(card->qdio.out_qs[i]); kfree(card->qdio.out_qs); card->qdio.out_qs = NULL; } From c2780c1a3fb724560b1d44f7976e0de17bf153c7 Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Mon, 4 Feb 2019 17:40:08 +0100 Subject: [PATCH 425/525] s390/qeth: cancel close_dev work before removing a card A card's close_dev work is scheduled on a driver-wide workqueue. If the card is removed and freed while the work is still active, this causes a use-after-free. So make sure that the work is completed before freeing the card. Fixes: 0f54761d167f ("qeth: Support VEPA mode") Signed-off-by: Julian Wiedmann Signed-off-by: David S. Miller --- drivers/s390/net/qeth_core.h | 1 + drivers/s390/net/qeth_l2_main.c | 2 ++ drivers/s390/net/qeth_l3_main.c | 1 + 3 files changed, 4 insertions(+) diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 0ee026947f20..1cf45ace0dd0 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -22,6 +22,7 @@ #include #include #include +#include #include #include diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index f108d4b44605..9fec0117fc00 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -801,6 +801,8 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev) if (cgdev->state == CCWGROUP_ONLINE) qeth_l2_set_offline(cgdev); + + cancel_work_sync(&card->close_dev_work); if (qeth_netdev_is_registered(card->dev)) unregister_netdev(card->dev); } diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 42a7cdc59b76..5e810561cb12 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -2338,6 +2338,7 @@ static void qeth_l3_remove_device(struct ccwgroup_device *cgdev) if (cgdev->state == CCWGROUP_ONLINE) qeth_l3_set_offline(cgdev); + cancel_work_sync(&card->close_dev_work); if (qeth_netdev_is_registered(card->dev)) unregister_netdev(card->dev); qeth_l3_clear_ip_htable(card, 0); From c0a2e4d10d9366ada133a8ae4ff2f32397f8b15b Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Mon, 4 Feb 2019 17:40:09 +0100 Subject: [PATCH 426/525] s390/qeth: conclude all event processing before offlining a card Work for Bridgeport events is currently placed on a driver-wide workqueue. If the card is removed and freed while any such work is still active, this causes a use-after-free. So put the events on a per-card queue, where we can control their lifetime. As we also don't want stale events to last beyond an offline & online cycle, flush this queue when setting the card offline. Fixes: b4d72c08b358 ("qeth: bridgeport support - basic control") Signed-off-by: Julian Wiedmann Signed-off-by: David S. Miller --- drivers/s390/net/qeth_core.h | 2 +- drivers/s390/net/qeth_core_main.c | 10 ++++++++-- drivers/s390/net/qeth_l2_main.c | 6 ++++-- drivers/s390/net/qeth_l3_main.c | 2 ++ 4 files changed, 15 insertions(+), 5 deletions(-) diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 1cf45ace0dd0..122059ecad84 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -790,6 +790,7 @@ struct qeth_card { struct qeth_seqno seqno; struct qeth_card_options options; + struct workqueue_struct *event_wq; wait_queue_head_t wait_q; spinlock_t mclock; unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; @@ -963,7 +964,6 @@ extern const struct attribute_group *qeth_osn_attr_groups[]; extern const struct attribute_group qeth_device_attr_group; extern const struct attribute_group qeth_device_blkt_group; extern const struct device_type qeth_generic_devtype; -extern struct workqueue_struct *qeth_wq; int qeth_card_hw_is_reachable(struct qeth_card *); const char *qeth_get_cardname_short(struct qeth_card *); diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 30679bfc8a1b..89f912213e62 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -74,8 +74,7 @@ static void qeth_notify_skbs(struct qeth_qdio_out_q *queue, static void qeth_release_skbs(struct qeth_qdio_out_buffer *buf); static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *, int); -struct workqueue_struct *qeth_wq; -EXPORT_SYMBOL_GPL(qeth_wq); +static struct workqueue_struct *qeth_wq; int qeth_card_hw_is_reachable(struct qeth_card *card) { @@ -1469,6 +1468,10 @@ static struct qeth_card *qeth_alloc_card(struct ccwgroup_device *gdev) CARD_RDEV(card) = gdev->cdev[0]; CARD_WDEV(card) = gdev->cdev[1]; CARD_DDEV(card) = gdev->cdev[2]; + + card->event_wq = alloc_ordered_workqueue("%s", 0, dev_name(&gdev->dev)); + if (!card->event_wq) + goto out_wq; if (qeth_setup_channel(&card->read, true)) goto out_ip; if (qeth_setup_channel(&card->write, true)) @@ -1484,6 +1487,8 @@ out_data: out_channel: qeth_clean_channel(&card->read); out_ip: + destroy_workqueue(card->event_wq); +out_wq: dev_set_drvdata(&gdev->dev, NULL); kfree(card); out: @@ -5031,6 +5036,7 @@ static void qeth_core_free_card(struct qeth_card *card) qeth_clean_channel(&card->read); qeth_clean_channel(&card->write); qeth_clean_channel(&card->data); + destroy_workqueue(card->event_wq); qeth_free_qdio_buffers(card); unregister_service_level(&card->qeth_service_level); dev_set_drvdata(&card->gdev->dev, NULL); diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 9fec0117fc00..a43de2f9bcac 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -369,6 +369,8 @@ static void qeth_l2_stop_card(struct qeth_card *card, int recovery_mode) qeth_clear_cmd_buffers(&card->read); qeth_clear_cmd_buffers(&card->write); } + + flush_workqueue(card->event_wq); } static int qeth_l2_process_inbound_buffer(struct qeth_card *card, @@ -1436,7 +1438,7 @@ static void qeth_bridge_state_change(struct qeth_card *card, data->card = card; memcpy(&data->qports, qports, sizeof(struct qeth_sbp_state_change) + extrasize); - queue_work(qeth_wq, &data->worker); + queue_work(card->event_wq, &data->worker); } struct qeth_bridge_host_data { @@ -1508,7 +1510,7 @@ static void qeth_bridge_host_event(struct qeth_card *card, data->card = card; memcpy(&data->hostevs, hostevs, sizeof(struct qeth_ipacmd_addr_change) + extrasize); - queue_work(qeth_wq, &data->worker); + queue_work(card->event_wq, &data->worker); } /* SETBRIDGEPORT support; sending commands */ diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 5e810561cb12..df34bff4ac31 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -1433,6 +1433,8 @@ static void qeth_l3_stop_card(struct qeth_card *card, int recovery_mode) qeth_clear_cmd_buffers(&card->read); qeth_clear_cmd_buffers(&card->write); } + + flush_workqueue(card->event_wq); } /* From 843cf70ed29a7fb51f1e796c1d6e1ba3620250ac Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 4 Feb 2019 15:48:03 -0300 Subject: [PATCH 427/525] perf symbols: Add fallback definitions for GELF_ST_VISIBILITY() Those aren't present in Alpine Linux 3.4 to edge, so provide fallback defines to get the next patch building there keeping the build bisectable. Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Masami Hiramatsu Cc: Michael Petlan Cc: Namhyung Kim Cc: Nick Clifton Cc: Peter Zijlstra Link: https://lkml.kernel.org/n/tip-03cg3gya2ju4ba2x6ibb9fuz@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/symbol-elf.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 66a84d5846c8..695a73940329 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -19,6 +19,20 @@ #define EM_AARCH64 183 /* ARM 64 bit */ #endif +#ifndef ELF32_ST_VISIBILITY +#define ELF32_ST_VISIBILITY(o) ((o) & 0x03) +#endif + +/* For ELF64 the definitions are the same. */ +#ifndef ELF64_ST_VISIBILITY +#define ELF64_ST_VISIBILITY(o) ELF32_ST_VISIBILITY (o) +#endif + +/* How to extract information held in the st_other field. */ +#ifndef GELF_ST_VISIBILITY +#define GELF_ST_VISIBILITY(val) ELF64_ST_VISIBILITY (val) +#endif + typedef Elf64_Nhdr GElf_Nhdr; #ifdef HAVE_CPLUS_DEMANGLE_SUPPORT From 59a17706915fe5ea6f711e1f92d4fb706bce07fe Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 28 Jan 2019 14:35:26 +0100 Subject: [PATCH 428/525] perf symbols: Filter out hidden symbols from labels When perf is built with the annobin plugin (RHEL8 build) extra symbols are added to its binary: # nm perf | grep annobin | head -10 0000000000241100 t .annobin_annotate.c 0000000000326490 t .annobin_annotate.c 0000000000249255 t .annobin_annotate.c_end 00000000003283a8 t .annobin_annotate.c_end 00000000001bce18 t .annobin_annotate.c_end.hot 00000000001bce18 t .annobin_annotate.c_end.hot 00000000001bc3e2 t .annobin_annotate.c_end.unlikely 00000000001bc400 t .annobin_annotate.c_end.unlikely 00000000001bce18 t .annobin_annotate.c.hot 00000000001bce18 t .annobin_annotate.c.hot ... Those symbols have no use for report or annotation and should be skipped. Moreover they interfere with the DWARF unwind test on the PPC arch, where they are mixed with checked symbols and then the test fails: # perf test dwarf -v 59: Test dwarf unwind : --- start --- test child forked, pid 8515 unwind: .annobin_dwarf_unwind.c:ip = 0x10dba40dc (0x2740dc) ... got: .annobin_dwarf_unwind.c 0x10dba40dc, expecting test__arch_unwind_sample unwind: failed with 'no error' The annobin symbols are defined as NOTYPE/LOCAL/HIDDEN: # readelf -s ./perf | grep annobin | head -1 40: 00000000001bce4f 0 NOTYPE LOCAL HIDDEN 13 .annobin_init.c They can still pass the check for the label symbol. Adding check for HIDDEN and INTERNAL (as suggested by Nick below) visibility and filter out such symbols. > Just to be awkward, if you are going to ignore STV_HIDDEN > symbols then you should probably also ignore STV_INTERNAL ones > as well... Annobin does not generate them, but you never know, > one day some other tool might create some. Signed-off-by: Jiri Olsa Cc: Alexander Shishkin Cc: Masami Hiramatsu Cc: Michael Petlan Cc: Namhyung Kim Cc: Nick Clifton Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20190128133526.GD15461@krava Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/symbol-elf.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 695a73940329..dca7dfae69ad 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -101,6 +101,11 @@ static inline uint8_t elf_sym__type(const GElf_Sym *sym) return GELF_ST_TYPE(sym->st_info); } +static inline uint8_t elf_sym__visibility(const GElf_Sym *sym) +{ + return GELF_ST_VISIBILITY(sym->st_other); +} + #ifndef STT_GNU_IFUNC #define STT_GNU_IFUNC 10 #endif @@ -125,7 +130,9 @@ static inline int elf_sym__is_label(const GElf_Sym *sym) return elf_sym__type(sym) == STT_NOTYPE && sym->st_name != 0 && sym->st_shndx != SHN_UNDEF && - sym->st_shndx != SHN_ABS; + sym->st_shndx != SHN_ABS && + elf_sym__visibility(sym) != STV_HIDDEN && + elf_sym__visibility(sym) != STV_INTERNAL; } static bool elf_sym__filter(GElf_Sym *sym) From 6ab3bc240ade47a0f52bc16d97edd9accbe0024e Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 29 Jan 2019 15:12:34 +0100 Subject: [PATCH 429/525] perf trace: Support multiple "vfs_getname" probes With a suitably defined "probe:vfs_getname" probe, 'perf trace' can "beautify" its output, so syscalls like open() or openat() can print the "filename" argument instead of just its hex address, like: $ perf trace -e open -- touch /dev/null [...] 0.590 ( 0.014 ms): touch/18063 open(filename: /dev/null, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: IRUGO|IWUGO) = 3 [...] The output without such beautifier looks like: 0.529 ( 0.011 ms): touch/18075 open(filename: 0xc78cf288, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: IRUGO|IWUGO) = 3 However, when the vfs_getname probe expands to multiple probes and it is not the first one that is hit, the beautifier fails, as following: 0.326 ( 0.010 ms): touch/18072 open(filename: , flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: IRUGO|IWUGO) = 3 Fix it by hooking into all the expanded probes (inlines), now, for instance: [root@quaco ~]# perf probe -l probe:vfs_getname (on getname_flags:73@fs/namei.c with pathname) probe:vfs_getname_1 (on getname_flags:73@fs/namei.c with pathname) [root@quaco ~]# perf trace -e open* sleep 1 0.010 ( 0.005 ms): sleep/5588 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: RDONLY|CLOEXEC) = 3 0.029 ( 0.006 ms): sleep/5588 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: RDONLY|CLOEXEC) = 3 0.194 ( 0.008 ms): sleep/5588 openat(dfd: CWD, filename: /usr/lib/locale/locale-archive, flags: RDONLY|CLOEXEC) = 3 [root@quaco ~]# Works, further verified with: [root@quaco ~]# perf test vfs 65: Use vfs_getname probe to get syscall args filenames : Ok 66: Add vfs_getname probe to get syscall args filenames : Ok 67: Check open filename arg using perf trace + vfs_getname: Ok [root@quaco ~]# Reported-by: Michael Petlan Tested-by: Michael Petlan Cc: Adrian Hunter Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lkml.kernel.org/n/tip-mv8kolk17xla1smvmp3qabv1@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index ed4583128b9c..b36061cd1ab8 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2514,19 +2514,30 @@ static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp); static bool perf_evlist__add_vfs_getname(struct perf_evlist *evlist) { - struct perf_evsel *evsel = perf_evsel__newtp("probe", "vfs_getname"); + bool found = false; + struct perf_evsel *evsel, *tmp; + struct parse_events_error err = { .idx = 0, }; + int ret = parse_events(evlist, "probe:vfs_getname*", &err); - if (IS_ERR(evsel)) + if (ret) return false; - if (perf_evsel__field(evsel, "pathname") == NULL) { + evlist__for_each_entry_safe(evlist, evsel, tmp) { + if (!strstarts(perf_evsel__name(evsel), "probe:vfs_getname")) + continue; + + if (perf_evsel__field(evsel, "pathname")) { + evsel->handler = trace__vfs_getname; + found = true; + continue; + } + + list_del_init(&evsel->node); + evsel->evlist = NULL; perf_evsel__delete(evsel); - return false; } - evsel->handler = trace__vfs_getname; - perf_evlist__add(evlist, evsel); - return true; + return found; } static struct perf_evsel *perf_evsel__new_pgfault(u64 config) From e02e07e3127d8aec1f4bcdfb2fc52a2d99b4859e Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Tue, 15 Jan 2019 16:04:54 +0800 Subject: [PATCH 430/525] MIPS: Loongson: Introduce and use loongson_llsc_mb() On the Loongson-2G/2H/3A/3B there is a hardware flaw that ll/sc and lld/scd is very weak ordering. We should add sync instructions "before each ll/lld" and "at the branch-target between ll/sc" to workaround. Otherwise, this flaw will cause deadlock occasionally (e.g. when doing heavy load test with LTP). Below is the explaination of CPU designer: "For Loongson 3 family, when a memory access instruction (load, store, or prefetch)'s executing occurs between the execution of LL and SC, the success or failure of SC is not predictable. Although programmer would not insert memory access instructions between LL and SC, the memory instructions before LL in program-order, may dynamically executed between the execution of LL/SC, so a memory fence (SYNC) is needed before LL/LLD to avoid this situation. Since Loongson-3A R2 (3A2000), we have improved our hardware design to handle this case. But we later deduce a rarely circumstance that some speculatively executed memory instructions due to branch misprediction between LL/SC still fall into the above case, so a memory fence (SYNC) at branch-target (if its target is not between LL/SC) is needed for Loongson 3A1000, 3B1500, 3A2000 and 3A3000. Our processor is continually evolving and we aim to to remove all these workaround-SYNCs around LL/SC for new-come processor." Here is an example: Both cpu1 and cpu2 simutaneously run atomic_add by 1 on same atomic var, this bug cause both 'sc' run by two cpus (in atomic_add) succeed at same time('sc' return 1), and the variable is only *added by 1*, sometimes, which is wrong and unacceptable(it should be added by 2). Why disable fix-loongson3-llsc in compiler? Because compiler fix will cause problems in kernel's __ex_table section. This patch fix all the cases in kernel, but: +. the fix at the end of futex_atomic_cmpxchg_inatomic is for branch-target of 'bne', there other cases which smp_mb__before_llsc() and smp_llsc_mb() fix the ll and branch-target coincidently such as atomic_sub_if_positive/ cmpxchg/xchg, just like this one. +. Loongson 3 does support CONFIG_EDAC_ATOMIC_SCRUB, so no need to touch edac.h +. local_ops and cmpxchg_local should not be affected by this bug since only the owner can write. +. mips_atomic_set for syscall.c is deprecated and rarely used, just let it go Signed-off-by: Huacai Chen Signed-off-by: Huang Pei [paul.burton@mips.com: - Simplify the addition of -mno-fix-loongson3-llsc to cflags, and add a comment describing why it's there. - Make loongson_llsc_mb() a no-op when CONFIG_CPU_LOONGSON3_WORKAROUNDS=n, rather than a compiler memory barrier. - Add a comment describing the bug & how loongson_llsc_mb() helps in asm/barrier.h.] Signed-off-by: Paul Burton Cc: Ralf Baechle Cc: ambrosehua@gmail.com Cc: Steven J . Hill Cc: linux-mips@linux-mips.org Cc: Fuxin Zhang Cc: Zhangjin Wu Cc: Li Xuefeng Cc: Xu Chenghua --- arch/mips/Kconfig | 15 ++++++++++++++ arch/mips/include/asm/atomic.h | 6 ++++++ arch/mips/include/asm/barrier.h | 36 +++++++++++++++++++++++++++++++++ arch/mips/include/asm/bitops.h | 5 +++++ arch/mips/include/asm/futex.h | 3 +++ arch/mips/include/asm/pgtable.h | 2 ++ arch/mips/loongson64/Platform | 23 +++++++++++++++++++++ arch/mips/mm/tlbex.c | 10 +++++++++ 8 files changed, 100 insertions(+) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 0d14f51d0002..a84c24d894aa 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -1403,6 +1403,21 @@ config LOONGSON3_ENHANCEMENT please say 'N' here. If you want a high-performance kernel to run on new Loongson 3 machines only, please say 'Y' here. +config CPU_LOONGSON3_WORKAROUNDS + bool "Old Loongson 3 LLSC Workarounds" + default y if SMP + depends on CPU_LOONGSON3 + help + Loongson 3 processors have the llsc issues which require workarounds. + Without workarounds the system may hang unexpectedly. + + Newer Loongson 3 will fix these issues and no workarounds are needed. + The workarounds have no significant side effect on them but may + decrease the performance of the system so this option should be + disabled unless the kernel is intended to be run on old systems. + + If unsure, please say Y. + config CPU_LOONGSON2E bool "Loongson 2E" depends on SYS_HAS_CPU_LOONGSON2E diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h index 43fcd35e2957..94096299fc56 100644 --- a/arch/mips/include/asm/atomic.h +++ b/arch/mips/include/asm/atomic.h @@ -58,6 +58,7 @@ static __inline__ void atomic_##op(int i, atomic_t * v) \ if (kernel_uses_llsc) { \ int temp; \ \ + loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set "MIPS_ISA_LEVEL" \n" \ @@ -85,6 +86,7 @@ static __inline__ int atomic_##op##_return_relaxed(int i, atomic_t * v) \ if (kernel_uses_llsc) { \ int temp; \ \ + loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set "MIPS_ISA_LEVEL" \n" \ @@ -118,6 +120,7 @@ static __inline__ int atomic_fetch_##op##_relaxed(int i, atomic_t * v) \ if (kernel_uses_llsc) { \ int temp; \ \ + loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set "MIPS_ISA_LEVEL" \n" \ @@ -256,6 +259,7 @@ static __inline__ void atomic64_##op(long i, atomic64_t * v) \ if (kernel_uses_llsc) { \ long temp; \ \ + loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set "MIPS_ISA_LEVEL" \n" \ @@ -283,6 +287,7 @@ static __inline__ long atomic64_##op##_return_relaxed(long i, atomic64_t * v) \ if (kernel_uses_llsc) { \ long temp; \ \ + loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set "MIPS_ISA_LEVEL" \n" \ @@ -316,6 +321,7 @@ static __inline__ long atomic64_fetch_##op##_relaxed(long i, atomic64_t * v) \ if (kernel_uses_llsc) { \ long temp; \ \ + loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set "MIPS_ISA_LEVEL" \n" \ diff --git a/arch/mips/include/asm/barrier.h b/arch/mips/include/asm/barrier.h index a5eb1bb199a7..b7f6ac5e513c 100644 --- a/arch/mips/include/asm/barrier.h +++ b/arch/mips/include/asm/barrier.h @@ -222,6 +222,42 @@ #define __smp_mb__before_atomic() __smp_mb__before_llsc() #define __smp_mb__after_atomic() smp_llsc_mb() +/* + * Some Loongson 3 CPUs have a bug wherein execution of a memory access (load, + * store or pref) in between an ll & sc can cause the sc instruction to + * erroneously succeed, breaking atomicity. Whilst it's unusual to write code + * containing such sequences, this bug bites harder than we might otherwise + * expect due to reordering & speculation: + * + * 1) A memory access appearing prior to the ll in program order may actually + * be executed after the ll - this is the reordering case. + * + * In order to avoid this we need to place a memory barrier (ie. a sync + * instruction) prior to every ll instruction, in between it & any earlier + * memory access instructions. Many of these cases are already covered by + * smp_mb__before_llsc() but for the remaining cases, typically ones in + * which multiple CPUs may operate on a memory location but ordering is not + * usually guaranteed, we use loongson_llsc_mb() below. + * + * This reordering case is fixed by 3A R2 CPUs, ie. 3A2000 models and later. + * + * 2) If a conditional branch exists between an ll & sc with a target outside + * of the ll-sc loop, for example an exit upon value mismatch in cmpxchg() + * or similar, then misprediction of the branch may allow speculative + * execution of memory accesses from outside of the ll-sc loop. + * + * In order to avoid this we need a memory barrier (ie. a sync instruction) + * at each affected branch target, for which we also use loongson_llsc_mb() + * defined below. + * + * This case affects all current Loongson 3 CPUs. + */ +#ifdef CONFIG_CPU_LOONGSON3_WORKAROUNDS /* Loongson-3's LLSC workaround */ +#define loongson_llsc_mb() __asm__ __volatile__(__WEAK_LLSC_MB : : :"memory") +#else +#define loongson_llsc_mb() do { } while (0) +#endif + #include #endif /* __ASM_BARRIER_H */ diff --git a/arch/mips/include/asm/bitops.h b/arch/mips/include/asm/bitops.h index c4675957b21b..830c93a010c3 100644 --- a/arch/mips/include/asm/bitops.h +++ b/arch/mips/include/asm/bitops.h @@ -69,6 +69,7 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr) : "ir" (1UL << bit), GCC_OFF_SMALL_ASM() (*m)); #if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) } else if (kernel_uses_llsc && __builtin_constant_p(bit)) { + loongson_llsc_mb(); do { __asm__ __volatile__( " " __LL "%0, %1 # set_bit \n" @@ -79,6 +80,7 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr) } while (unlikely(!temp)); #endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */ } else if (kernel_uses_llsc) { + loongson_llsc_mb(); do { __asm__ __volatile__( " .set push \n" @@ -123,6 +125,7 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *addr) : "ir" (~(1UL << bit))); #if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) } else if (kernel_uses_llsc && __builtin_constant_p(bit)) { + loongson_llsc_mb(); do { __asm__ __volatile__( " " __LL "%0, %1 # clear_bit \n" @@ -133,6 +136,7 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *addr) } while (unlikely(!temp)); #endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */ } else if (kernel_uses_llsc) { + loongson_llsc_mb(); do { __asm__ __volatile__( " .set push \n" @@ -193,6 +197,7 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *addr) unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); unsigned long temp; + loongson_llsc_mb(); do { __asm__ __volatile__( " .set push \n" diff --git a/arch/mips/include/asm/futex.h b/arch/mips/include/asm/futex.h index c14d798f3888..b83b0397462d 100644 --- a/arch/mips/include/asm/futex.h +++ b/arch/mips/include/asm/futex.h @@ -50,6 +50,7 @@ "i" (-EFAULT) \ : "memory"); \ } else if (cpu_has_llsc) { \ + loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set noat \n" \ @@ -163,6 +164,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, "i" (-EFAULT) : "memory"); } else if (cpu_has_llsc) { + loongson_llsc_mb(); __asm__ __volatile__( "# futex_atomic_cmpxchg_inatomic \n" " .set push \n" @@ -192,6 +194,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, : GCC_OFF_SMALL_ASM() (*uaddr), "Jr" (oldval), "Jr" (newval), "i" (-EFAULT) : "memory"); + loongson_llsc_mb(); } else return -ENOSYS; diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index 57933fc8fd98..910851c62db3 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -228,6 +228,7 @@ static inline void set_pte(pte_t *ptep, pte_t pteval) : [buddy] "+m" (buddy->pte), [tmp] "=&r" (tmp) : [global] "r" (page_global)); } else if (kernel_uses_llsc) { + loongson_llsc_mb(); __asm__ __volatile__ ( " .set push \n" " .set "MIPS_ISA_ARCH_LEVEL" \n" @@ -242,6 +243,7 @@ static inline void set_pte(pte_t *ptep, pte_t pteval) " .set pop \n" : [buddy] "+m" (buddy->pte), [tmp] "=&r" (tmp) : [global] "r" (page_global)); + loongson_llsc_mb(); } #else /* !CONFIG_SMP */ if (pte_none(*buddy)) diff --git a/arch/mips/loongson64/Platform b/arch/mips/loongson64/Platform index 0fce4608aa88..c1a4d4dc4665 100644 --- a/arch/mips/loongson64/Platform +++ b/arch/mips/loongson64/Platform @@ -23,6 +23,29 @@ ifdef CONFIG_CPU_LOONGSON2F_WORKAROUNDS endif cflags-$(CONFIG_CPU_LOONGSON3) += -Wa,--trap + +# +# Some versions of binutils, not currently mainline as of 2019/02/04, support +# an -mfix-loongson3-llsc flag which emits a sync prior to each ll instruction +# to work around a CPU bug (see loongson_llsc_mb() in asm/barrier.h for a +# description). +# +# We disable this in order to prevent the assembler meddling with the +# instruction that labels refer to, ie. if we label an ll instruction: +# +# 1: ll v0, 0(a0) +# +# ...then with the assembler fix applied the label may actually point at a sync +# instruction inserted by the assembler, and if we were using the label in an +# exception table the table would no longer contain the address of the ll +# instruction. +# +# Avoid this by explicitly disabling that assembler behaviour. If upstream +# binutils does not merge support for the flag then we can revisit & remove +# this later - for now it ensures vendor toolchains don't cause problems. +# +cflags-$(CONFIG_CPU_LOONGSON3) += $(call as-option,-Wa$(comma)-mno-fix-loongson3-llsc,) + # # binutils from v2.25 on and gcc starting from v4.9.0 treat -march=loongson3a # as MIPS64 R2; older versions as just R1. This leaves the possibility open diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 37b1cb246332..65b6e85447b1 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -932,6 +932,8 @@ build_get_pgd_vmalloc64(u32 **p, struct uasm_label **l, struct uasm_reloc **r, * to mimic that here by taking a load/istream page * fault. */ + if (IS_ENABLED(CONFIG_CPU_LOONGSON3_WORKAROUNDS)) + uasm_i_sync(p, 0); UASM_i_LA(p, ptr, (unsigned long)tlb_do_page_fault_0); uasm_i_jr(p, ptr); @@ -1646,6 +1648,8 @@ static void iPTE_LW(u32 **p, unsigned int pte, unsigned int ptr) { #ifdef CONFIG_SMP + if (IS_ENABLED(CONFIG_CPU_LOONGSON3_WORKAROUNDS)) + uasm_i_sync(p, 0); # ifdef CONFIG_PHYS_ADDR_T_64BIT if (cpu_has_64bits) uasm_i_lld(p, pte, 0, ptr); @@ -2259,6 +2263,8 @@ static void build_r4000_tlb_load_handler(void) #endif uasm_l_nopage_tlbl(&l, p); + if (IS_ENABLED(CONFIG_CPU_LOONGSON3_WORKAROUNDS)) + uasm_i_sync(&p, 0); build_restore_work_registers(&p); #ifdef CONFIG_CPU_MICROMIPS if ((unsigned long)tlb_do_page_fault_0 & 1) { @@ -2313,6 +2319,8 @@ static void build_r4000_tlb_store_handler(void) #endif uasm_l_nopage_tlbs(&l, p); + if (IS_ENABLED(CONFIG_CPU_LOONGSON3_WORKAROUNDS)) + uasm_i_sync(&p, 0); build_restore_work_registers(&p); #ifdef CONFIG_CPU_MICROMIPS if ((unsigned long)tlb_do_page_fault_1 & 1) { @@ -2368,6 +2376,8 @@ static void build_r4000_tlb_modify_handler(void) #endif uasm_l_nopage_tlbm(&l, p); + if (IS_ENABLED(CONFIG_CPU_LOONGSON3_WORKAROUNDS)) + uasm_i_sync(&p, 0); build_restore_work_registers(&p); #ifdef CONFIG_CPU_MICROMIPS if ((unsigned long)tlb_do_page_fault_1 & 1) { From 047f2d941b8b24cadd6a4a09e606b7f41188ba3e Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Mon, 4 Feb 2019 19:53:53 +0000 Subject: [PATCH 431/525] MIPS: Use lower case for addresses in nexys4ddr.dts DTC introduced an i2c_bus_reg check in v1.4.7, used since Linux v4.20, which complains about upper case addresses used in the unit name. nexys4ddr.dts names an I2C device node "ad7420@4B", leading to: arch/mips/boot/dts/xilfpga/nexys4ddr.dts:109.16-112.8: Warning (i2c_bus_reg): /i2c@10A00000/ad7420@4B: I2C bus unit address format error, expected "4b" Fix this by switching to lower case addresses throughout the file, as is *mostly* the case in the file already & fairly standard throughout the tree. Signed-off-by: Paul Burton Cc: stable@vger.kernel.org # v4.20+ Cc: linux-mips@vger.kernel.org --- arch/mips/boot/dts/xilfpga/nexys4ddr.dts | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/mips/boot/dts/xilfpga/nexys4ddr.dts b/arch/mips/boot/dts/xilfpga/nexys4ddr.dts index 2152b7ba65fb..cc8dbea0911f 100644 --- a/arch/mips/boot/dts/xilfpga/nexys4ddr.dts +++ b/arch/mips/boot/dts/xilfpga/nexys4ddr.dts @@ -90,11 +90,11 @@ interrupts = <0>; }; - axi_i2c: i2c@10A00000 { + axi_i2c: i2c@10a00000 { compatible = "xlnx,xps-iic-2.00.a"; interrupt-parent = <&axi_intc>; interrupts = <4>; - reg = < 0x10A00000 0x10000 >; + reg = < 0x10a00000 0x10000 >; clocks = <&ext>; xlnx,clk-freq = <0x5f5e100>; xlnx,family = "Artix7"; @@ -106,9 +106,9 @@ #address-cells = <1>; #size-cells = <0>; - ad7420@4B { + ad7420@4b { compatible = "adi,adt7420"; - reg = <0x4B>; + reg = <0x4b>; }; } ; }; From 2b424cfc69728224fcb5fad138ea7260728e0901 Mon Sep 17 00:00:00 2001 From: Jun-Ru Chang Date: Tue, 29 Jan 2019 11:56:07 +0800 Subject: [PATCH 432/525] MIPS: Remove function size check in get_frame_info() Patch (b6c7a324df37b "MIPS: Fix get_frame_info() handling of microMIPS function size.") introduces additional function size check for microMIPS by only checking insn between ip and ip + func_size. However, func_size in get_frame_info() is always 0 if KALLSYMS is not enabled. This causes get_frame_info() to return immediately without calculating correct frame_size, which in turn causes "Can't analyze schedule() prologue" warning messages at boot time. This patch removes func_size check, and let the frame_size check run up to 128 insns for both MIPS and microMIPS. Signed-off-by: Jun-Ru Chang Signed-off-by: Tony Wu Signed-off-by: Paul Burton Fixes: b6c7a324df37b ("MIPS: Fix get_frame_info() handling of microMIPS function size.") Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: --- arch/mips/kernel/process.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 6829a064aac8..339870ed92f7 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -371,7 +371,7 @@ static inline int is_sp_move_ins(union mips_instruction *ip, int *frame_size) static int get_frame_info(struct mips_frame_info *info) { bool is_mmips = IS_ENABLED(CONFIG_CPU_MICROMIPS); - union mips_instruction insn, *ip, *ip_end; + union mips_instruction insn, *ip; const unsigned int max_insns = 128; unsigned int last_insn_size = 0; unsigned int i; @@ -384,10 +384,9 @@ static int get_frame_info(struct mips_frame_info *info) if (!ip) goto err; - ip_end = (void *)ip + info->func_size; - - for (i = 0; i < max_insns && ip < ip_end; i++) { + for (i = 0; i < max_insns; i++) { ip = (void *)ip + last_insn_size; + if (is_mmips && mm_insn_16bit(ip->halfword[0])) { insn.word = ip->halfword[0] << 16; last_insn_size = 2; From 17ab4f61b8cd6f9c38e9d0b935d86d73b5d0d2b5 Mon Sep 17 00:00:00 2001 From: Rundong Ge Date: Sat, 2 Feb 2019 14:29:35 +0000 Subject: [PATCH 433/525] net: dsa: slave: Don't propagate flag changes on down slave interfaces The unbalance of master's promiscuity or allmulti will happen after ifdown and ifup a slave interface which is in a bridge. When we ifdown a slave interface , both the 'dsa_slave_close' and 'dsa_slave_change_rx_flags' will clear the master's flags. The flags of master will be decrease twice. In the other hand, if we ifup the slave interface again, since the slave's flags were cleared the 'dsa_slave_open' won't set the master's flag, only 'dsa_slave_change_rx_flags' that triggered by 'br_add_if' will set the master's flags. The flags of master is increase once. Only propagating flag changes when a slave interface is up makes sure this does not happen. The 'vlan_dev_change_rx_flags' had the same problem and was fixed, and changes here follows that fix. Fixes: 91da11f870f0 ("net: Distributed Switch Architecture protocol support") Signed-off-by: Rundong Ge Signed-off-by: David S. Miller --- net/dsa/slave.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index a3fcc1d01615..b5e44825d173 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -140,11 +140,14 @@ static int dsa_slave_close(struct net_device *dev) static void dsa_slave_change_rx_flags(struct net_device *dev, int change) { struct net_device *master = dsa_slave_to_master(dev); - - if (change & IFF_ALLMULTI) - dev_set_allmulti(master, dev->flags & IFF_ALLMULTI ? 1 : -1); - if (change & IFF_PROMISC) - dev_set_promiscuity(master, dev->flags & IFF_PROMISC ? 1 : -1); + if (dev->flags & IFF_UP) { + if (change & IFF_ALLMULTI) + dev_set_allmulti(master, + dev->flags & IFF_ALLMULTI ? 1 : -1); + if (change & IFF_PROMISC) + dev_set_promiscuity(master, + dev->flags & IFF_PROMISC ? 1 : -1); + } } static void dsa_slave_set_rx_mode(struct net_device *dev) From c8101f7729daee251f4f6505f9d135ec08e1342f Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sat, 2 Feb 2019 17:53:29 +0000 Subject: [PATCH 434/525] net: dsa: Fix lockdep false positive splat Creating a macvtap on a DSA-backed interface results in the following splat when lockdep is enabled: [ 19.638080] IPv6: ADDRCONF(NETDEV_CHANGE): lan0: link becomes ready [ 23.041198] device lan0 entered promiscuous mode [ 23.043445] device eth0 entered promiscuous mode [ 23.049255] [ 23.049557] ============================================ [ 23.055021] WARNING: possible recursive locking detected [ 23.060490] 5.0.0-rc3-00013-g56c857a1b8d3 #118 Not tainted [ 23.066132] -------------------------------------------- [ 23.071598] ip/2861 is trying to acquire lock: [ 23.076171] 00000000f61990cb (_xmit_ETHER){+...}, at: dev_set_rx_mode+0x1c/0x38 [ 23.083693] [ 23.083693] but task is already holding lock: [ 23.089696] 00000000ecf0c3b4 (_xmit_ETHER){+...}, at: dev_uc_add+0x24/0x70 [ 23.096774] [ 23.096774] other info that might help us debug this: [ 23.103494] Possible unsafe locking scenario: [ 23.103494] [ 23.109584] CPU0 [ 23.112093] ---- [ 23.114601] lock(_xmit_ETHER); [ 23.117917] lock(_xmit_ETHER); [ 23.121233] [ 23.121233] *** DEADLOCK *** [ 23.121233] [ 23.127325] May be due to missing lock nesting notation [ 23.127325] [ 23.134315] 2 locks held by ip/2861: [ 23.137987] #0: 000000003b766c72 (rtnl_mutex){+.+.}, at: rtnetlink_rcv_msg+0x338/0x4e0 [ 23.146231] #1: 00000000ecf0c3b4 (_xmit_ETHER){+...}, at: dev_uc_add+0x24/0x70 [ 23.153757] [ 23.153757] stack backtrace: [ 23.158243] CPU: 0 PID: 2861 Comm: ip Not tainted 5.0.0-rc3-00013-g56c857a1b8d3 #118 [ 23.166212] Hardware name: Globalscale Marvell ESPRESSOBin Board (DT) [ 23.172843] Call trace: [ 23.175358] dump_backtrace+0x0/0x188 [ 23.179116] show_stack+0x14/0x20 [ 23.182524] dump_stack+0xb4/0xec [ 23.185928] __lock_acquire+0x123c/0x1860 [ 23.190048] lock_acquire+0xc8/0x248 [ 23.193724] _raw_spin_lock_bh+0x40/0x58 [ 23.197755] dev_set_rx_mode+0x1c/0x38 [ 23.201607] dev_set_promiscuity+0x3c/0x50 [ 23.205820] dsa_slave_change_rx_flags+0x5c/0x70 [ 23.210567] __dev_set_promiscuity+0x148/0x1e0 [ 23.215136] __dev_set_rx_mode+0x74/0x98 [ 23.219167] dev_uc_add+0x54/0x70 [ 23.222575] macvlan_open+0x170/0x1d0 [ 23.226336] __dev_open+0xe0/0x160 [ 23.229830] __dev_change_flags+0x16c/0x1b8 [ 23.234132] dev_change_flags+0x20/0x60 [ 23.238074] do_setlink+0x2d0/0xc50 [ 23.241658] __rtnl_newlink+0x5f8/0x6e8 [ 23.245601] rtnl_newlink+0x50/0x78 [ 23.249184] rtnetlink_rcv_msg+0x360/0x4e0 [ 23.253397] netlink_rcv_skb+0xe8/0x130 [ 23.257338] rtnetlink_rcv+0x14/0x20 [ 23.261012] netlink_unicast+0x190/0x210 [ 23.265043] netlink_sendmsg+0x288/0x350 [ 23.269075] sock_sendmsg+0x18/0x30 [ 23.272659] ___sys_sendmsg+0x29c/0x2c8 [ 23.276602] __sys_sendmsg+0x60/0xb8 [ 23.280276] __arm64_sys_sendmsg+0x1c/0x28 [ 23.284488] el0_svc_common+0xd8/0x138 [ 23.288340] el0_svc_handler+0x24/0x80 [ 23.292192] el0_svc+0x8/0xc This looks fairly harmless (no actual deadlock occurs), and is fixed in a similar way to c6894dec8ea9 ("bridge: fix lockdep addr_list_lock false positive splat") by putting the addr_list_lock in its own lockdep class. Signed-off-by: Marc Zyngier Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- net/dsa/master.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/dsa/master.c b/net/dsa/master.c index 71bb15f491c8..54f5551fb799 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -205,6 +205,8 @@ static void dsa_master_reset_mtu(struct net_device *dev) rtnl_unlock(); } +static struct lock_class_key dsa_master_addr_list_lock_key; + int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) { int ret; @@ -218,6 +220,8 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) wmb(); dev->dsa_ptr = cpu_dp; + lockdep_set_class(&dev->addr_list_lock, + &dsa_master_addr_list_lock_key); ret = dsa_master_ethtool_setup(dev); if (ret) From b6cd7f34ba1354498de03e6882c33f935b071e99 Mon Sep 17 00:00:00 2001 From: David Disseldorp Date: Mon, 4 Feb 2019 19:32:10 +0100 Subject: [PATCH 435/525] scsi: target: make the pi_prot_format ConfigFS path readable pi_prot_format conversion to write-only caused userspace breakage. Make the ConfigFS path readable again and hardcode the "0\n" content, matching previous output. Fixes: 6baca7601bde ("scsi: target: drop unused pi_prot_format attribute storage") Link: https://bugzilla.redhat.com/show_bug.cgi?id=1667505 Reported-by: Lee Duncan Reported-by: Laura Abbott Reviewed-by: Bart Van Assche Signed-off-by: David Disseldorp Signed-off-by: Martin K. Petersen --- drivers/target/target_core_configfs.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index 72016d0dfca5..8e7fffbb8802 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -852,6 +852,12 @@ static ssize_t pi_prot_type_store(struct config_item *item, return count; } +/* always zero, but attr needs to remain RW to avoid userspace breakage */ +static ssize_t pi_prot_format_show(struct config_item *item, char *page) +{ + return snprintf(page, PAGE_SIZE, "0\n"); +} + static ssize_t pi_prot_format_store(struct config_item *item, const char *page, size_t count) { @@ -1132,7 +1138,7 @@ CONFIGFS_ATTR(, emulate_3pc); CONFIGFS_ATTR(, emulate_pr); CONFIGFS_ATTR(, pi_prot_type); CONFIGFS_ATTR_RO(, hw_pi_prot_type); -CONFIGFS_ATTR_WO(, pi_prot_format); +CONFIGFS_ATTR(, pi_prot_format); CONFIGFS_ATTR(, pi_prot_verify); CONFIGFS_ATTR(, enforce_pr_isids); CONFIGFS_ATTR(, is_nonrot); From 88fc41c407158a7d2eaa4b2f7cfa289749d456c6 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 30 Jan 2019 15:54:58 +0900 Subject: [PATCH 436/525] scsi: sd_zbc: Fix zone information messages Commit bf5054569653 ("block: Introduce blk_revalidate_disk_zones()") inadvertently broke the message output of sd_zbc_print_zones() because the zone information initialization of the scsi disk structure was moved to the second scan run while sd_zbc_print_zones() is called on the first scan. This leads to the following incorrect message to be printed for any ZBC or ZAC zoned disks. "...[sdX] 4294967295 zones of 0 logical blocks + 1 runt zone" Fix this by initializing sdkp zone size and number of zones early on the first scan. This does not impact the execution of blk_revalidate_zones(). This functions is still called only once the block device capacity is set on the second revalidate run on boot, or if the disk zone configuration changed (i.e. the disk changed). Fixes: bf5054569653 ("block: Introduce blk_revalidate_disk_zones()") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Signed-off-by: Martin K. Petersen --- drivers/scsi/sd_zbc.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index 83365b29a4d8..fff86940388b 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -462,12 +462,16 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf) sdkp->device->use_10_for_rw = 0; /* - * If something changed, revalidate the disk zone bitmaps once we have - * the capacity, that is on the second revalidate execution during disk - * scan and always during normal revalidate. + * Revalidate the disk zone bitmaps once the block device capacity is + * set on the second revalidate execution during disk scan and if + * something changed when executing a normal revalidate. */ - if (sdkp->first_scan) + if (sdkp->first_scan) { + sdkp->zone_blocks = zone_blocks; + sdkp->nr_zones = nr_zones; return 0; + } + if (sdkp->zone_blocks != zone_blocks || sdkp->nr_zones != nr_zones || disk->queue->nr_zones != nr_zones) { From d8f6382a7d026989029e2e50c515df954488459b Mon Sep 17 00:00:00 2001 From: Ross Lagerwall Date: Fri, 1 Feb 2019 14:42:28 +0000 Subject: [PATCH 437/525] Revert "scsi: libfc: Add WARN_ON() when deleting rports" This reverts commit bbc0f8bd88abefb0f27998f40a073634a3a2db89. It added a warning whose intent was to check whether the rport was still linked into the peer list. It doesn't work as intended and gives false positive warnings for two reasons: 1) If the rport is never linked into the peer list it will not be considered empty since the list_head is never initialized. 2) If the rport is deleted from the peer list using list_del_rcu(), then the list_head is in an undefined state and it is not considered empty. Signed-off-by: Ross Lagerwall Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- drivers/scsi/libfc/fc_rport.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c index 9192a1d9dec6..dfba4921b265 100644 --- a/drivers/scsi/libfc/fc_rport.c +++ b/drivers/scsi/libfc/fc_rport.c @@ -184,7 +184,6 @@ void fc_rport_destroy(struct kref *kref) struct fc_rport_priv *rdata; rdata = container_of(kref, struct fc_rport_priv, kref); - WARN_ON(!list_empty(&rdata->peers)); kfree_rcu(rdata, rcu); } EXPORT_SYMBOL(fc_rport_destroy); From bb61b843ffd46978d7ca5095453e572714934eeb Mon Sep 17 00:00:00 2001 From: Vaibhav Jain Date: Wed, 30 Jan 2019 17:56:51 +0530 Subject: [PATCH 438/525] scsi: cxlflash: Prevent deadlock when adapter probe fails Presently when an error is encountered during probe of the cxlflash adapter, a deadlock is seen with cpu thread stuck inside cxlflash_remove(). Below is the trace of the deadlock as logged by khungtaskd: cxlflash 0006:00:00.0: cxlflash_probe: init_afu failed rc=-16 INFO: task kworker/80:1:890 blocked for more than 120 seconds. Not tainted 5.0.0-rc4-capi2-kexec+ #2 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kworker/80:1 D 0 890 2 0x00000808 Workqueue: events work_for_cpu_fn Call Trace: 0x4d72136320 (unreliable) __switch_to+0x2cc/0x460 __schedule+0x2bc/0xac0 schedule+0x40/0xb0 cxlflash_remove+0xec/0x640 [cxlflash] cxlflash_probe+0x370/0x8f0 [cxlflash] local_pci_probe+0x6c/0x140 work_for_cpu_fn+0x38/0x60 process_one_work+0x260/0x530 worker_thread+0x280/0x5d0 kthread+0x1a8/0x1b0 ret_from_kernel_thread+0x5c/0x80 INFO: task systemd-udevd:5160 blocked for more than 120 seconds. The deadlock occurs as cxlflash_remove() is called from cxlflash_probe() without setting 'cxlflash_cfg->state' to STATE_PROBED and the probe thread starts to wait on 'cxlflash_cfg->reset_waitq'. Since the device was never successfully probed the 'cxlflash_cfg->state' never changes from STATE_PROBING hence the deadlock occurs. We fix this deadlock by setting the variable 'cxlflash_cfg->state' to STATE_PROBED in case an error occurs during cxlflash_probe() and just before calling cxlflash_remove(). Cc: stable@vger.kernel.org Fixes: c21e0bbfc485("cxlflash: Base support for IBM CXL Flash Adapter") Signed-off-by: Vaibhav Jain Signed-off-by: Martin K. Petersen --- drivers/scsi/cxlflash/main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c index bfa13e3b191c..c8bad2c093b8 100644 --- a/drivers/scsi/cxlflash/main.c +++ b/drivers/scsi/cxlflash/main.c @@ -3687,6 +3687,7 @@ static int cxlflash_probe(struct pci_dev *pdev, host->max_cmd_len = CXLFLASH_MAX_CDB_LEN; cfg = shost_priv(host); + cfg->state = STATE_PROBING; cfg->host = host; rc = alloc_mem(cfg); if (rc) { @@ -3775,6 +3776,7 @@ out: return rc; out_remove: + cfg->state = STATE_PROBED; cxlflash_remove(pdev); goto out; } From ea5736805190e912903c27c9f17c7a4341a405e9 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Fri, 1 Feb 2019 16:26:08 +0000 Subject: [PATCH 439/525] arm64: kexec_file: handle empty command-line Calling strlen() on cmdline == NULL produces a kernel oops. Since having a NULL cmdline is valid, handle this case explicitly. Fixes: 52b2a8af7436 ("arm64: kexec_file: load initrd and device-tree") Signed-off-by: Jean-Philippe Brucker Signed-off-by: Will Deacon --- arch/arm64/kernel/machine_kexec_file.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index f2c211a6229b..58871333737a 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -120,10 +120,12 @@ static int create_dtb(struct kimage *image, { void *buf; size_t buf_size; + size_t cmdline_len; int ret; + cmdline_len = cmdline ? strlen(cmdline) : 0; buf_size = fdt_totalsize(initial_boot_params) - + strlen(cmdline) + DTB_EXTRA_SPACE; + + cmdline_len + DTB_EXTRA_SPACE; for (;;) { buf = vmalloc(buf_size); From c6e2bd956936d925748581e4d0294f10f1d92f2c Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Thu, 10 Jan 2019 07:59:16 -0800 Subject: [PATCH 440/525] i2c: omap: Use noirq system sleep pm ops to idle device for suspend We currently get the following error with pixcir_ts driver during a suspend resume cycle: omap_i2c 4802a000.i2c: controller timed out pixcir_ts 1-005c: pixcir_int_enable: can't read reg 0x34 : -110 pixcir_ts 1-005c: Failed to disable interrupt generation: -110 pixcir_ts 1-005c: Failed to stop dpm_run_callback(): pixcir_i2c_ts_resume+0x0/0x98 [pixcir_i2c_ts] returns -110 PM: Device 1-005c failed to resume: error -110 And at least am437x based devices with pixcir_ts will fail to resume to a touchscreen that is configured as the wakeup-source in device tree for these devices. This is because pixcir_ts tries to reconfigure it's registers for noirq suspend which fails. This also leaves i2c-omap in enabled state for suspend. Let's fix the pixcir_ts issue and make sure i2c-omap is suspended by adding SET_NOIRQ_SYSTEM_SLEEP_PM_OPS. Let's also get rid of some ifdefs while at it and replace them with __maybe_unused as SET_RUNTIME_PM_OPS and SET_NOIRQ_SYSTEM_SLEEP_PM_OPS already deal with the various PM Kconfig options. Reported-by: Keerthy Signed-off-by: Tony Lindgren Acked-by: Vignesh R Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-omap.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c index b1086bfb0465..cd9c65f3d404 100644 --- a/drivers/i2c/busses/i2c-omap.c +++ b/drivers/i2c/busses/i2c-omap.c @@ -1500,8 +1500,7 @@ static int omap_i2c_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_PM -static int omap_i2c_runtime_suspend(struct device *dev) +static int __maybe_unused omap_i2c_runtime_suspend(struct device *dev) { struct omap_i2c_dev *omap = dev_get_drvdata(dev); @@ -1527,7 +1526,7 @@ static int omap_i2c_runtime_suspend(struct device *dev) return 0; } -static int omap_i2c_runtime_resume(struct device *dev) +static int __maybe_unused omap_i2c_runtime_resume(struct device *dev) { struct omap_i2c_dev *omap = dev_get_drvdata(dev); @@ -1542,20 +1541,18 @@ static int omap_i2c_runtime_resume(struct device *dev) } static const struct dev_pm_ops omap_i2c_pm_ops = { + SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, + pm_runtime_force_resume) SET_RUNTIME_PM_OPS(omap_i2c_runtime_suspend, omap_i2c_runtime_resume, NULL) }; -#define OMAP_I2C_PM_OPS (&omap_i2c_pm_ops) -#else -#define OMAP_I2C_PM_OPS NULL -#endif /* CONFIG_PM */ static struct platform_driver omap_i2c_driver = { .probe = omap_i2c_probe, .remove = omap_i2c_remove, .driver = { .name = "omap_i2c", - .pm = OMAP_I2C_PM_OPS, + .pm = &omap_i2c_pm_ops, .of_match_table = of_match_ptr(omap_i2c_of_match), }, }; From 728354c005c36eaf44b6e5552372b67e60d17f56 Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Thu, 31 Jan 2019 10:55:37 +0100 Subject: [PATCH 441/525] drm/vmwgfx: Return error code from vmw_execbuf_copy_fence_user The function was unconditionally returning 0, and a caller would have to rely on the returned fence pointer being NULL to detect errors. However, the function vmw_execbuf_copy_fence_user() would expect a non-zero error code in that case and would BUG otherwise. So make sure we return a proper non-zero error code if the fence pointer returned is NULL. Cc: Fixes: ae2a104058e2: ("vmwgfx: Implement fence objects") Signed-off-by: Thomas Hellstrom Reviewed-by: Deepak Rawat --- drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index f2d13a72c05d..88b8178d4687 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -3570,7 +3570,7 @@ int vmw_execbuf_fence_commands(struct drm_file *file_priv, *p_fence = NULL; } - return 0; + return ret; } /** From 51fdbeb4ca1a8415c98f87cb877956ae83e71627 Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Thu, 31 Jan 2019 10:52:21 +0100 Subject: [PATCH 442/525] drm/vmwgfx: Fix an uninitialized fence handle value if vmw_execbuf_fence_commands() fails, The handle value will be uninitialized and a bogus fence handle might be copied to user-space. Cc: Fixes: 2724b2d54cda: ("drm/vmwgfx: Use new validation interface for the modesetting code v2") Reported-by: Dan Carpenter Signed-off-by: Thomas Hellstrom Reviewed-by: Brian Paul #v1 Reviewed-by: Sinclair Yeh #v1 Reviewed-by: Deepak Rawat --- drivers/gpu/drm/vmwgfx/vmwgfx_kms.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index b351fb5214d3..5e257a600cea 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -2554,8 +2554,8 @@ void vmw_kms_helper_validation_finish(struct vmw_private *dev_priv, user_fence_rep) { struct vmw_fence_obj *fence = NULL; - uint32_t handle; - int ret; + uint32_t handle = 0; + int ret = 0; if (file_priv || user_fence_rep || vmw_validation_has_bos(ctx) || out_fence) From 479d59026fe44f89fa67efa01a4d47e00808e688 Mon Sep 17 00:00:00 2001 From: Deepak Rawat Date: Fri, 21 Dec 2018 14:38:35 -0800 Subject: [PATCH 443/525] drm/vmwgfx: Also check for crtc status while checking for DU active During modeset check it is possible to have all crtc_state's in atomic state. Check for crtc enable status while checking for display unit active status. Only error if enabling a crtc while display unit is not active. Cc: Fixes: 9da6e26c0aae: ("drm/vmwgfx: Fix a layout race condition") Signed-off-by: Deepak Rawat Reviewed-by: Thomas Hellstrom Signed-off-by: Thomas Hellstrom --- drivers/gpu/drm/vmwgfx/vmwgfx_kms.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 5e257a600cea..ed2f67822f45 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -1646,7 +1646,7 @@ static int vmw_kms_check_topology(struct drm_device *dev, struct drm_connector_state *conn_state; struct vmw_connector_state *vmw_conn_state; - if (!du->pref_active) { + if (!du->pref_active && new_crtc_state->enable) { ret = -EINVAL; goto clean; } From 4cbfa1e6c09e98450aab3240e5119b0ab2c9795b Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Mon, 28 Jan 2019 10:31:33 +0100 Subject: [PATCH 444/525] drm/vmwgfx: Fix setting of dma masks Previously we set only the dma mask and not the coherent mask. Fix that. Also, for clarity, make sure both are initially set to 64 bits. Cc: Fixes: 0d00c488f3de: ("drm/vmwgfx: Fix the driver for large dma addresses") Signed-off-by: Thomas Hellstrom Reviewed-by: Deepak Rawat --- drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 3e2bcff34032..ae9df4432bfc 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -600,13 +600,16 @@ static int vmw_dma_select_mode(struct vmw_private *dev_priv) static int vmw_dma_masks(struct vmw_private *dev_priv) { struct drm_device *dev = dev_priv->dev; + int ret = 0; - if (intel_iommu_enabled && + ret = dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(64)); + if (dev_priv->map_mode != vmw_dma_phys && (sizeof(unsigned long) == 4 || vmw_restrict_dma_mask)) { DRM_INFO("Restricting DMA addresses to 44 bits.\n"); - return dma_set_mask(dev->dev, DMA_BIT_MASK(44)); + return dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(44)); } - return 0; + + return ret; } static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) From 9ddac734aa310c5fbc0ec93602335d2a39092451 Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Thu, 17 Jan 2019 14:34:52 +0100 Subject: [PATCH 445/525] drm/vmwgfx: Improve on IOMMU detection instead of relying on intel_iommu_enabled, use the fact that the dma_map_ops::map_page != dma_direct_map_page. Signed-off-by: Thomas Hellstrom Reviewed-by: Deepak Rawat --- drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index ae9df4432bfc..7ef5dcb06104 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -26,6 +26,7 @@ **************************************************************************/ #include #include +#include #include #include "vmwgfx_drv.h" @@ -34,7 +35,6 @@ #include #include #include -#include #define VMWGFX_DRIVER_DESC "Linux drm driver for VMware graphics devices" #define VMWGFX_CHIP_SVGAII 0 @@ -545,6 +545,21 @@ static void vmw_get_initial_size(struct vmw_private *dev_priv) dev_priv->initial_height = height; } +/** + * vmw_assume_iommu - Figure out whether coherent dma-remapping might be + * taking place. + * @dev: Pointer to the struct drm_device. + * + * Return: true if iommu present, false otherwise. + */ +static bool vmw_assume_iommu(struct drm_device *dev) +{ + const struct dma_map_ops *ops = get_dma_ops(dev->dev); + + return !dma_is_direct(ops) && ops && + ops->map_page != dma_direct_map_page; +} + /** * vmw_dma_select_mode - Determine how DMA mappings should be set up for this * system. @@ -568,7 +583,7 @@ static int vmw_dma_select_mode(struct vmw_private *dev_priv) if (vmw_force_coherent) dev_priv->map_mode = vmw_dma_alloc_coherent; - else if (intel_iommu_enabled) + else if (vmw_assume_iommu(dev_priv->dev)) dev_priv->map_mode = vmw_dma_map_populate; else if (!vmw_force_iommu) dev_priv->map_mode = vmw_dma_phys; From 15df03c661cb362366ecfc3a21820cb934f3e4ca Mon Sep 17 00:00:00 2001 From: Eli Cooper Date: Mon, 21 Jan 2019 18:45:27 +0800 Subject: [PATCH 446/525] netfilter: ipv6: Don't preserve original oif for loopback address Commit 508b09046c0f ("netfilter: ipv6: Preserve link scope traffic original oif") made ip6_route_me_harder() keep the original oif for link-local and multicast packets. However, it also affected packets for the loopback address because it used rt6_need_strict(). REDIRECT rules in the OUTPUT chain rewrite the destination to loopback address; thus its oif should not be preserved. This commit fixes the bug that redirected local packets are being dropped. Actually the packet was not exactly dropped; Instead it was sent out to the original oif rather than lo. When a packet with daddr ::1 is sent to the router, it is effectively dropped. Fixes: 508b09046c0f ("netfilter: ipv6: Preserve link scope traffic original oif") Signed-off-by: Eli Cooper Signed-off-by: Pablo Neira Ayuso --- net/ipv6/netfilter.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 8b075f0bc351..6d0b1f3e927b 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -23,9 +23,11 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb) struct sock *sk = sk_to_full_sk(skb->sk); unsigned int hh_len; struct dst_entry *dst; + int strict = (ipv6_addr_type(&iph->daddr) & + (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)); struct flowi6 fl6 = { .flowi6_oif = sk && sk->sk_bound_dev_if ? sk->sk_bound_dev_if : - rt6_need_strict(&iph->daddr) ? skb_dst(skb)->dev->ifindex : 0, + strict ? skb_dst(skb)->dev->ifindex : 0, .flowi6_mark = skb->mark, .flowi6_uid = sock_net_uid(net, sk), .daddr = iph->daddr, From 947e492c0fc2132ae5fca081a9c2952ccaab0404 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 5 Feb 2019 12:16:18 +0100 Subject: [PATCH 447/525] netfilter: nft_compat: don't use refcount_inc on newly allocated entry When I moved the refcount to refcount_t type I missed the fact that refcount_inc() will result in use-after-free warning with CONFIG_REFCOUNT_FULL=y builds. The correct fix would be to init the reference count to 1 at allocation time, but, unfortunately we cannot do this, as we can't undo that in case something else fails later in the batch. So only solution I see is to special-case the 'new entry' condition and replace refcount_inc() with a "delayed" refcount_set(1) in this case, as done here. The .activate callback can be removed to simplify things, we only need to make sure that deactivate() decrements/unlinks the entry from the list at end of transaction phase (commit or abort). Fixes: 12c44aba6618 ("netfilter: nft_compat: use refcnt_t type for nft_xt reference count") Reported-by: Jordan Glover Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_compat.c | 62 ++++++++++++++------------------------ 1 file changed, 23 insertions(+), 39 deletions(-) diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 0732a2fc697c..fe64df848365 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -61,6 +61,21 @@ static struct nft_compat_net *nft_compat_pernet(struct net *net) return net_generic(net, nft_compat_net_id); } +static void nft_xt_get(struct nft_xt *xt) +{ + /* refcount_inc() warns on 0 -> 1 transition, but we can't + * init the reference count to 1 in .select_ops -- we can't + * undo such an increase when another expression inside the same + * rule fails afterwards. + */ + if (xt->listcnt == 0) + refcount_set(&xt->refcnt, 1); + else + refcount_inc(&xt->refcnt); + + xt->listcnt++; +} + static bool nft_xt_put(struct nft_xt *xt) { if (refcount_dec_and_test(&xt->refcnt)) { @@ -291,7 +306,7 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return -EINVAL; nft_xt = container_of(expr->ops, struct nft_xt, ops); - refcount_inc(&nft_xt->refcnt); + nft_xt_get(nft_xt); return 0; } @@ -504,7 +519,7 @@ __nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return ret; nft_xt = container_of(expr->ops, struct nft_xt, ops); - refcount_inc(&nft_xt->refcnt); + nft_xt_get(nft_xt); return 0; } @@ -558,45 +573,16 @@ nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) __nft_match_destroy(ctx, expr, nft_expr_priv(expr)); } -static void nft_compat_activate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - struct list_head *h) -{ - struct nft_xt *xt = container_of(expr->ops, struct nft_xt, ops); - - if (xt->listcnt == 0) - list_add(&xt->head, h); - - xt->listcnt++; -} - -static void nft_compat_activate_mt(const struct nft_ctx *ctx, - const struct nft_expr *expr) -{ - struct nft_compat_net *cn = nft_compat_pernet(ctx->net); - - nft_compat_activate(ctx, expr, &cn->nft_match_list); -} - -static void nft_compat_activate_tg(const struct nft_ctx *ctx, - const struct nft_expr *expr) -{ - struct nft_compat_net *cn = nft_compat_pernet(ctx->net); - - nft_compat_activate(ctx, expr, &cn->nft_target_list); -} - static void nft_compat_deactivate(const struct nft_ctx *ctx, const struct nft_expr *expr, enum nft_trans_phase phase) { struct nft_xt *xt = container_of(expr->ops, struct nft_xt, ops); - if (phase == NFT_TRANS_COMMIT) - return; - - if (--xt->listcnt == 0) - list_del_init(&xt->head); + if (phase == NFT_TRANS_ABORT || phase == NFT_TRANS_COMMIT) { + if (--xt->listcnt == 0) + list_del_init(&xt->head); + } } static void @@ -852,7 +838,6 @@ nft_match_select_ops(const struct nft_ctx *ctx, nft_match->ops.eval = nft_match_eval; nft_match->ops.init = nft_match_init; nft_match->ops.destroy = nft_match_destroy; - nft_match->ops.activate = nft_compat_activate_mt; nft_match->ops.deactivate = nft_compat_deactivate; nft_match->ops.dump = nft_match_dump; nft_match->ops.validate = nft_match_validate; @@ -870,7 +855,7 @@ nft_match_select_ops(const struct nft_ctx *ctx, nft_match->ops.size = matchsize; - nft_match->listcnt = 1; + nft_match->listcnt = 0; list_add(&nft_match->head, &cn->nft_match_list); return &nft_match->ops; @@ -957,7 +942,6 @@ nft_target_select_ops(const struct nft_ctx *ctx, nft_target->ops.size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize)); nft_target->ops.init = nft_target_init; nft_target->ops.destroy = nft_target_destroy; - nft_target->ops.activate = nft_compat_activate_tg; nft_target->ops.deactivate = nft_compat_deactivate; nft_target->ops.dump = nft_target_dump; nft_target->ops.validate = nft_target_validate; @@ -968,7 +952,7 @@ nft_target_select_ops(const struct nft_ctx *ctx, else nft_target->ops.eval = nft_target_eval_xt; - nft_target->listcnt = 1; + nft_target->listcnt = 0; list_add(&nft_target->head, &cn->nft_target_list); return &nft_target->ops; From 3e0b69bbed7161eee8702eee5dcdc18afc1dc982 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Fri, 25 Jan 2019 20:38:46 +0200 Subject: [PATCH 448/525] drm/i915: Fix skl srckey mask bits MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We're incorrectly masking off the R/V channel enable bit from KEYMSK. Fix it up. Cc: Maarten Lankhorst Cc: Matt Roper Fixes: b20815255693 ("drm/i915: Add plane alpha blending support, v2.") Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20190125183846.28755-1-ville.syrjala@linux.intel.com Reviewed-by: Matt Roper (cherry picked from commit 968bf969b47df2481022b9a05eaab02948eec088) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_sprite.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index d2e003d8f3db..5170a0f5fe7b 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -494,7 +494,7 @@ skl_program_plane(struct intel_plane *plane, keymax = (key->max_value & 0xffffff) | PLANE_KEYMAX_ALPHA(alpha); - keymsk = key->channel_mask & 0x3ffffff; + keymsk = key->channel_mask & 0x7ffffff; if (alpha < 0xff) keymsk |= PLANE_KEYMSK_ALPHA_ENABLE; From 2a121030d4ee3f84f60c6f415f9c44bffbcde81d Mon Sep 17 00:00:00 2001 From: Lucas De Marchi Date: Fri, 25 Jan 2019 14:24:42 -0800 Subject: [PATCH 449/525] drm/i915: always return something on DDI clock selection Even if we don't have the correct clock and get a warning, we should not skip the return. v2: improve commit message (from Joonas) Fixes: 1fa11ee2d9d0 ("drm/i915/icl: start adding the TBT pll") Cc: Paulo Zanoni Cc: # v4.19+ Signed-off-by: Lucas De Marchi Reviewed-by: Mika Kahola Link: https://patchwork.freedesktop.org/patch/msgid/20190125222444.19926-3-lucas.demarchi@intel.com (cherry picked from commit 7a61a6dec3dfb9f2e8c39a337580a3c3036c5cdf) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_ddi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index f3e1d6a0b7dd..4079050f9d6c 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -1086,7 +1086,7 @@ static uint32_t icl_pll_to_ddi_pll_sel(struct intel_encoder *encoder, return DDI_CLK_SEL_TBT_810; default: MISSING_CASE(clock); - break; + return DDI_CLK_SEL_NONE; } case DPLL_ID_ICL_MGPLL1: case DPLL_ID_ICL_MGPLL2: From 8f2f350cbdb2c2fbff654cb778139144b48a59ba Mon Sep 17 00:00:00 2001 From: Tony Jones Date: Wed, 23 Jan 2019 16:52:29 -0800 Subject: [PATCH 450/525] perf script python: Add Python3 support to tests/attr.py Support both Python 2 and Python 3 in tests/attr.py The use of "except as" syntax implies the minimum supported Python2 version is now v2.6 Committer testing: $ make -C tools/perf PYTHON3=python install-bin Before: # perf test attr 16: Setup struct perf_event_attr : FAILED! 48: Synthesize attr update : Ok [root@quaco ~]# perf test -v attr 16: Setup struct perf_event_attr : --- start --- test child forked, pid 3121 File "/home/acme/libexec/perf-core/tests/attr.py", line 324 except Unsup, obj: ^ SyntaxError: invalid syntax test child finished with -1 ---- end ---- Setup struct perf_event_attr: FAILED! 48: Synthesize attr update : --- start --- test child forked, pid 3124 test child finished with 0 ---- end ---- Synthesize attr update: Ok # After: # perf test attr 16: Setup struct perf_event_attr : Ok 48: Synthesize attr update : Ok # Signed-off-by: Tony Jones Acked-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Jonathan Corbet Cc: Ravi Bangoria Cc: Seeteena Thoufeek Link: http://lkml.kernel.org/r/20190124005229.16146-7-tonyj@suse.de Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/attr.py | 32 +++++++++++++++++++------------- 1 file changed, 19 insertions(+), 13 deletions(-) diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py index 44090a9a19f3..e952127e4fb0 100644 --- a/tools/perf/tests/attr.py +++ b/tools/perf/tests/attr.py @@ -1,6 +1,8 @@ #! /usr/bin/python # SPDX-License-Identifier: GPL-2.0 +from __future__ import print_function + import os import sys import glob @@ -8,7 +10,11 @@ import optparse import tempfile import logging import shutil -import ConfigParser + +try: + import configparser +except ImportError: + import ConfigParser as configparser def data_equal(a, b): # Allow multiple values in assignment separated by '|' @@ -100,20 +106,20 @@ class Event(dict): def equal(self, other): for t in Event.terms: log.debug(" [%s] %s %s" % (t, self[t], other[t])); - if not self.has_key(t) or not other.has_key(t): + if t not in self or t not in other: return False if not data_equal(self[t], other[t]): return False return True def optional(self): - if self.has_key('optional') and self['optional'] == '1': + if 'optional' in self and self['optional'] == '1': return True return False def diff(self, other): for t in Event.terms: - if not self.has_key(t) or not other.has_key(t): + if t not in self or t not in other: continue if not data_equal(self[t], other[t]): log.warning("expected %s=%s, got %s" % (t, self[t], other[t])) @@ -134,7 +140,7 @@ class Event(dict): # - expected values assignments class Test(object): def __init__(self, path, options): - parser = ConfigParser.SafeConfigParser() + parser = configparser.SafeConfigParser() parser.read(path) log.warning("running '%s'" % path) @@ -193,7 +199,7 @@ class Test(object): return True def load_events(self, path, events): - parser_event = ConfigParser.SafeConfigParser() + parser_event = configparser.SafeConfigParser() parser_event.read(path) # The event record section header contains 'event' word, @@ -207,7 +213,7 @@ class Test(object): # Read parent event if there's any if (':' in section): base = section[section.index(':') + 1:] - parser_base = ConfigParser.SafeConfigParser() + parser_base = configparser.SafeConfigParser() parser_base.read(self.test_dir + '/' + base) base_items = parser_base.items('event') @@ -322,9 +328,9 @@ def run_tests(options): for f in glob.glob(options.test_dir + '/' + options.test): try: Test(f, options).run() - except Unsup, obj: + except Unsup as obj: log.warning("unsupp %s" % obj.getMsg()) - except Notest, obj: + except Notest as obj: log.warning("skipped %s" % obj.getMsg()) def setup_log(verbose): @@ -363,7 +369,7 @@ def main(): parser.add_option("-p", "--perf", action="store", type="string", dest="perf") parser.add_option("-v", "--verbose", - action="count", dest="verbose") + default=0, action="count", dest="verbose") options, args = parser.parse_args() if args: @@ -373,7 +379,7 @@ def main(): setup_log(options.verbose) if not options.test_dir: - print 'FAILED no -d option specified' + print('FAILED no -d option specified') sys.exit(-1) if not options.test: @@ -382,8 +388,8 @@ def main(): try: run_tests(options) - except Fail, obj: - print "FAILED %s" % obj.getMsg(); + except Fail as obj: + print("FAILED %s" % obj.getMsg()) sys.exit(-1) sys.exit(0) From a692933a87691681e880feb708081681ff32400a Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 5 Feb 2019 07:19:11 -0600 Subject: [PATCH 451/525] signal: Always attempt to allocate siginfo for SIGSTOP Since 2.5.34 the code has had the potential to not allocate siginfo for SIGSTOP signals. Except for ptrace this is perfectly fine as only ptrace can use PTRACE_PEEK_SIGINFO and see what the contents of the delivered siginfo are. Users of PTRACE_PEEK_SIGINFO that care about the contents siginfo for SIGSTOP are rare, but they do exist. A seccomp self test has cared and lldb cares. Jack Andersen writes: > The patch titled > `signal: Never allocate siginfo for SIGKILL or SIGSTOP` > created a regression for users of PTRACE_GETSIGINFO needing to > discern signals that were raised via the tgkill syscall. > > A notable user of this tgkill+ptrace combination is lldb while > debugging a multithreaded program. Without the ability to detect a > SIGSTOP originating from tgkill, lldb does not have a way to > synchronize on a per-thread basis and falls back to SIGSTOP-ing the > entire process. Everyone affected by this please note. The kernel can still fail to allocate a siginfo structure. The allocation is with GFP_KERNEL and is best effort only. If memory is tight when the signal allocation comes in this will fail to allocate a siginfo. So I strongly recommend looking at more robust solutions for synchronizing with a single thread such as PTRACE_INTERRUPT. Or if that does not work persuading your friendly local kernel developer to build the interface you need. Reported-by: Tycho Andersen Reported-by: Kees Cook Reported-by: Jack Andersen Acked-by: Linus Torvalds Reviewed-by: Christian Brauner Cc: stable@vger.kernel.org Fixes: f149b3155744 ("signal: Never allocate siginfo for SIGKILL or SIGSTOP") Fixes: 6dfc88977e42 ("[PATCH] shared thread signals") History Tree: https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git Signed-off-by: "Eric W. Biederman" --- kernel/signal.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/kernel/signal.c b/kernel/signal.c index e1d7ad8e6ab1..9ca8e5278c8e 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1057,10 +1057,9 @@ static int __send_signal(int sig, struct kernel_siginfo *info, struct task_struc result = TRACE_SIGNAL_DELIVERED; /* - * Skip useless siginfo allocation for SIGKILL SIGSTOP, - * and kernel threads. + * Skip useless siginfo allocation for SIGKILL and kernel threads. */ - if (sig_kernel_only(sig) || (t->flags & PF_KTHREAD)) + if ((sig == SIGKILL) || (t->flags & PF_KTHREAD)) goto out_set; /* From 3bff2407fbd28fd55ad5b5cccd98fc0c9598f23b Mon Sep 17 00:00:00 2001 From: Udo Eberhardt Date: Tue, 5 Feb 2019 17:20:47 +0100 Subject: [PATCH 452/525] ALSA: usb-audio: Add support for new T+A USB DAC This patch adds the T+A VID to the generic check in order to enable native DSD support for T+A devices. This works with the new T+A USB DAC model SD3100HV and will also work with future devices which support the XMOS/Thesycon style DSD format. Signed-off-by: Udo Eberhardt Cc: Signed-off-by: Takashi Iwai --- sound/usb/quirks.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index bb8372833fc2..7e65fe853ee3 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1567,6 +1567,7 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip, case 0x20b1: /* XMOS based devices */ case 0x152a: /* Thesycon devices */ case 0x25ce: /* Mytek devices */ + case 0x2ab6: /* T+A devices */ if (fp->dsd_raw) return SNDRV_PCM_FMTBIT_DSD_U32_BE; break; From 82eaa1fa0448da1852d7b80832e67e80a08dcc27 Mon Sep 17 00:00:00 2001 From: Raed Salem Date: Mon, 17 Dec 2018 11:40:06 +0200 Subject: [PATCH 453/525] net/mlx5e: FPGA, fix Innova IPsec TX offload data path performance At Innova IPsec TX offload data path a special software parser metadata is used to pass some packet attributes to the hardware, this metadata is passed using the Ethernet control segment of a WQE (a HW descriptor) header. The cited commit might nullify this header, hence the metadata is lost, this caused a significant performance drop during hw offloading operation. Fix by restoring the metadata at the Ethernet control segment in case it was nullified. Fixes: 37fdffb217a4 ("net/mlx5: WQ, fixes for fragmented WQ buffers API") Signed-off-by: Raed Salem Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 598ad7e4d5c9..0e55cd1f2e98 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -387,8 +387,14 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS); contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi); if (unlikely(contig_wqebbs_room < num_wqebbs)) { +#ifdef CONFIG_MLX5_EN_IPSEC + struct mlx5_wqe_eth_seg cur_eth = wqe->eth; +#endif mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room); mlx5e_sq_fetch_wqe(sq, &wqe, &pi); +#ifdef CONFIG_MLX5_EN_IPSEC + wqe->eth = cur_eth; +#endif } /* fill wqe */ From 6363651d6dd79694d586f4ae68967036dd14bc3a Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Thu, 10 Jan 2019 20:37:36 +0200 Subject: [PATCH 454/525] net/mlx5e: Properly set steering match levels for offloaded TC decap rules The match level computed by the driver gets to be wrong for decap rules with wildcarded inner packet match such as: tc filter add dev vxlan_sys_4789 protocol all parent ffff: prio 2 flower enc_dst_ip 192.168.0.9 enc_key_id 100 enc_dst_port 4789 action tunnel_key unset action mirred egress redirect dev eth1 The FW errs for a missing matching meta-data indicator for the outer headers (where we do have a match), and a wrong matching meta-data indicator for the inner headers (where we don't have a match). Fix that by taking into account the matching on the tunnel info and relating the match level of the encapsulated packet to the firmware inner headers indicator in case of decap. As for vxlan we mandate a match on the tunnel udp dst port, and in general we practically madndate a match on the source or dest ip for any IP tunnel, the fix was done in a minimal manner around the tunnel match parsing code. Fixes: d708f902989b ('net/mlx5e: Get the required HW match level while parsing TC flow matches') Signed-off-by: Or Gerlitz Reported-by: Slava Ovsiienko Reviewed-by: Jianbo Liu Signed-off-by: Saeed Mahameed --- .../ethernet/mellanox/mlx5/core/en/tc_tun.c | 4 +++- .../ethernet/mellanox/mlx5/core/en/tc_tun.h | 2 +- .../net/ethernet/mellanox/mlx5/core/en_tc.c | 18 ++++++++++-------- .../net/ethernet/mellanox/mlx5/core/eswitch.h | 1 + .../mellanox/mlx5/core/eswitch_offloads.c | 17 +++++++++-------- 5 files changed, 24 insertions(+), 18 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 046948ead152..a3750af074a4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -612,16 +612,18 @@ int mlx5e_tc_tun_parse(struct net_device *filter_dev, struct mlx5_flow_spec *spec, struct tc_cls_flower_offload *f, void *headers_c, - void *headers_v) + void *headers_v, u8 *match_level) { int tunnel_type; int err = 0; tunnel_type = mlx5e_tc_tun_get_type(filter_dev); if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) { + *match_level = MLX5_MATCH_L4; err = mlx5e_tc_tun_parse_vxlan(priv, spec, f, headers_c, headers_v); } else if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_GRETAP) { + *match_level = MLX5_MATCH_L3; err = mlx5e_tc_tun_parse_gretap(priv, spec, f, headers_c, headers_v); } else { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h index 706ce7bf15e7..b63f15de899d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h @@ -39,6 +39,6 @@ int mlx5e_tc_tun_parse(struct net_device *filter_dev, struct mlx5_flow_spec *spec, struct tc_cls_flower_offload *f, void *headers_c, - void *headers_v); + void *headers_v, u8 *match_level); #endif //__MLX5_EN_TC_TUNNEL_H__ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index cae6c6d48984..043896e13ffa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1302,7 +1302,7 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, static int parse_tunnel_attr(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec, struct tc_cls_flower_offload *f, - struct net_device *filter_dev) + struct net_device *filter_dev, u8 *match_level) { struct netlink_ext_ack *extack = f->common.extack; void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, @@ -1317,7 +1317,7 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, int err = 0; err = mlx5e_tc_tun_parse(filter_dev, priv, spec, f, - headers_c, headers_v); + headers_c, headers_v, match_level); if (err) { NL_SET_ERR_MSG_MOD(extack, "failed to parse tunnel attributes"); @@ -1426,7 +1426,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec, struct tc_cls_flower_offload *f, struct net_device *filter_dev, - u8 *match_level) + u8 *match_level, u8 *tunnel_match_level) { struct netlink_ext_ack *extack = f->common.extack; void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, @@ -1477,7 +1477,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, switch (key->addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: case FLOW_DISSECTOR_KEY_IPV6_ADDRS: - if (parse_tunnel_attr(priv, spec, f, filter_dev)) + if (parse_tunnel_attr(priv, spec, f, filter_dev, tunnel_match_level)) return -EOPNOTSUPP; break; default: @@ -1826,11 +1826,11 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_core_dev *dev = priv->mdev; struct mlx5_eswitch *esw = dev->priv.eswitch; struct mlx5e_rep_priv *rpriv = priv->ppriv; + u8 match_level, tunnel_match_level = MLX5_MATCH_NONE; struct mlx5_eswitch_rep *rep; - u8 match_level; int err; - err = __parse_cls_flower(priv, spec, f, filter_dev, &match_level); + err = __parse_cls_flower(priv, spec, f, filter_dev, &match_level, &tunnel_match_level); if (!err && (flow->flags & MLX5E_TC_FLOW_ESWITCH)) { rep = rpriv->rep; @@ -1846,10 +1846,12 @@ static int parse_cls_flower(struct mlx5e_priv *priv, } } - if (flow->flags & MLX5E_TC_FLOW_ESWITCH) + if (flow->flags & MLX5E_TC_FLOW_ESWITCH) { flow->esw_attr->match_level = match_level; - else + flow->esw_attr->tunnel_match_level = tunnel_match_level; + } else { flow->nic_attr->match_level = match_level; + } return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 9c89eea9b2c3..748ff178a1d6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -312,6 +312,7 @@ struct mlx5_esw_flow_attr { } dests[MLX5_MAX_FLOW_FWD_VPORTS]; u32 mod_hdr_id; u8 match_level; + u8 tunnel_match_level; struct mlx5_fc *counter; u32 chain; u16 prio; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 53065b6ae593..d4e6fe5b9300 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -160,14 +160,15 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_eswitch_owner_vhca_id); - if (attr->match_level == MLX5_MATCH_NONE) - spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS; - else - spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS | - MLX5_MATCH_MISC_PARAMETERS; - - if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DECAP) - spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS; + spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS; + if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DECAP) { + if (attr->tunnel_match_level != MLX5_MATCH_NONE) + spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS; + if (attr->match_level != MLX5_MATCH_NONE) + spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS; + } else if (attr->match_level != MLX5_MATCH_NONE) { + spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS; + } if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) flow_act.modify_id = attr->mod_hdr_id; From 1651925d403e077e3fc86f961905e27c6810e132 Mon Sep 17 00:00:00 2001 From: Guy Shattah Date: Mon, 28 Jan 2019 13:58:07 +0000 Subject: [PATCH 455/525] net/mlx5e: Use the inner headers to determine tc/pedit offload limitation on decap flows In packets that need to be decaped the internal headers have to be checked, not the external ones. Fixes: bdd66ac0aeed ("net/mlx5e: Disallow TC offloading of unsupported match/action combinations") Signed-off-by: Guy Shattah Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 043896e13ffa..1c3c9fa26b55 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -2181,6 +2181,7 @@ static bool csum_offload_supported(struct mlx5e_priv *priv, static bool modify_header_match_supported(struct mlx5_flow_spec *spec, struct tcf_exts *exts, + u32 actions, struct netlink_ext_ack *extack) { const struct tc_action *a; @@ -2190,7 +2191,11 @@ static bool modify_header_match_supported(struct mlx5_flow_spec *spec, u16 ethertype; int nkeys, i; - headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers); + if (actions & MLX5_FLOW_CONTEXT_ACTION_DECAP) + headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, inner_headers); + else + headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers); + ethertype = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ethertype); /* for non-IP we only re-write MACs, so we're okay */ @@ -2247,7 +2252,7 @@ static bool actions_match_supported(struct mlx5e_priv *priv, if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) return modify_header_match_supported(&parse_attr->spec, exts, - extack); + actions, extack); return true; } From 9c0644ee4aa8792f1e60a2b014b4710faaddafeb Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Fri, 1 Feb 2019 17:13:57 -0500 Subject: [PATCH 456/525] virtio: drop internal struct from UAPI There's no reason to expose struct vring_packed in UAPI - if we do we won't be able to change or drop it, and it's not part of any interface. Let's move it to virtio_ring.c Cc: Tiwei Bie Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio_ring.c | 7 ++++++- include/uapi/linux/virtio_ring.h | 10 ---------- 2 files changed, 6 insertions(+), 11 deletions(-) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 27d3f057493e..a0b07c331255 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -152,7 +152,12 @@ struct vring_virtqueue { /* Available for packed ring */ struct { /* Actual memory layout for this queue. */ - struct vring_packed vring; + struct { + unsigned int num; + struct vring_packed_desc *desc; + struct vring_packed_desc_event *driver; + struct vring_packed_desc_event *device; + } vring; /* Driver ring wrap counter. */ bool avail_wrap_counter; diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h index 2414f8af26b3..4c4e24c291a5 100644 --- a/include/uapi/linux/virtio_ring.h +++ b/include/uapi/linux/virtio_ring.h @@ -213,14 +213,4 @@ struct vring_packed_desc { __le16 flags; }; -struct vring_packed { - unsigned int num; - - struct vring_packed_desc *desc; - - struct vring_packed_desc_event *driver; - - struct vring_packed_desc_event *device; -}; - #endif /* _UAPI_LINUX_VIRTIO_RING_H */ From 4f2ab5e1d13d6aa77c55f4914659784efd776eb4 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Tue, 5 Feb 2019 16:29:40 +0000 Subject: [PATCH 457/525] ALSA: compress: Fix stop handling on compressed capture streams It is normal user behaviour to start, stop, then start a stream again without closing it. Currently this works for compressed playback streams but not capture ones. The states on a compressed capture stream go directly from OPEN to PREPARED, unlike a playback stream which moves to SETUP and waits for a write of data before moving to PREPARED. Currently however, when a stop is sent the state is set to SETUP for both types of streams. This leaves a capture stream in the situation where a new start can't be sent as that requires the state to be PREPARED and a new set_params can't be sent as that requires the state to be OPEN. The only option being to close the stream, and then reopen. Correct this issues by allowing snd_compr_drain_notify to set the state depending on the stream direction, as we already do in set_params. Fixes: 49bb6402f1aa ("ALSA: compress_core: Add support for capture streams") Signed-off-by: Charles Keepax Cc: Signed-off-by: Takashi Iwai --- include/sound/compress_driver.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/include/sound/compress_driver.h b/include/sound/compress_driver.h index 0cdc3999ecfa..c5188ff724d1 100644 --- a/include/sound/compress_driver.h +++ b/include/sound/compress_driver.h @@ -173,7 +173,11 @@ static inline void snd_compr_drain_notify(struct snd_compr_stream *stream) if (snd_BUG_ON(!stream)) return; - stream->runtime->state = SNDRV_PCM_STATE_SETUP; + if (stream->direction == SND_COMPRESS_PLAYBACK) + stream->runtime->state = SNDRV_PCM_STATE_SETUP; + else + stream->runtime->state = SNDRV_PCM_STATE_PREPARED; + wake_up(&stream->runtime->sleep); } From ad4635153034c20c6f6e211e2ed3fd38b658649a Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Wed, 30 Jan 2019 12:55:52 +0100 Subject: [PATCH 458/525] mtd: Make sure mtd->erasesize is valid even if the partition is of size 0 Commit 33f45c44d68b ("mtd: Do not allow MTD devices with inconsistent erase properties") introduced a check to make sure ->erasesize and ->_erase values are consistent with the MTD_NO_ERASE flag. This patch did not take the 0 bytes partition case into account which can happen when the defined partition is outside the flash device memory range. Fix that by setting the partition erasesize to the parent erasesize. Fixes: 33f45c44d68b ("mtd: Do not allow MTD devices with inconsistent erase properties") Reported-by: Geert Uytterhoeven Cc: Cc: Geert Uytterhoeven Signed-off-by: Boris Brezillon Tested-by: Geert Uytterhoeven --- drivers/mtd/mtdpart.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index e6d9467f6be0..37f174ccbcec 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -480,6 +480,10 @@ static struct mtd_part *allocate_partition(struct mtd_info *parent, /* let's register it anyway to preserve ordering */ slave->offset = 0; slave->mtd.size = 0; + + /* Initialize ->erasesize to make add_mtd_device() happy. */ + slave->mtd.erasesize = parent->erasesize; + printk(KERN_ERR"mtd: partition \"%s\" is out of reach -- disabled\n", part->name); goto out_register; From 0a5f49cbf9d6ad3721c16f8a6d823363ea7a160f Mon Sep 17 00:00:00 2001 From: Philip Yang Date: Wed, 30 Jan 2019 15:21:16 -0500 Subject: [PATCH 459/525] drm/amdgpu: use spin_lock_irqsave to protect vm_manager.pasid_idr MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit amdgpu_vm_get_task_info is called from interrupt handler and sched timeout workqueue, we should use irq version spin_lock to avoid deadlock. Signed-off-by: Philip Yang Reviewed-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index d2ea5ce2cefb..7c108e687683 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -3363,14 +3363,15 @@ void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid, struct amdgpu_task_info *task_info) { struct amdgpu_vm *vm; + unsigned long flags; - spin_lock(&adev->vm_manager.pasid_lock); + spin_lock_irqsave(&adev->vm_manager.pasid_lock, flags); vm = idr_find(&adev->vm_manager.pasid_idr, pasid); if (vm) *task_info = vm->task_info; - spin_unlock(&adev->vm_manager.pasid_lock); + spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags); } /** From 6d3d8065bb14dcd3d36b63f81fff9bc7f4388bda Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Mon, 21 Jan 2019 16:52:15 -0700 Subject: [PATCH 460/525] drm/amdkfd: Fix if preprocessor statement above kfd_fill_iolink_info_for_cpu Clang warns: drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_crat.c:866:5: warning: 'CONFIG_X86_64' is not defined, evaluates to 0 [-Wundef] ^ 1 warning generated. Fixes: d1c234e2cd10 ("drm/amdkfd: Allow building KFD on ARM64 (v2)") Signed-off-by: Nathan Chancellor Reviewed-by: Felix Kuehling Signed-off-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_crat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c index 5d85ff341385..2e7c44955f43 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c @@ -863,7 +863,7 @@ static int kfd_fill_mem_info_for_cpu(int numa_node_id, int *avail_size, return 0; } -#if CONFIG_X86_64 +#ifdef CONFIG_X86_64 static int kfd_fill_iolink_info_for_cpu(int numa_node_id, int *avail_size, uint32_t *num_entries, struct crat_subtype_iolink *sub_type_hdr) From 7fad8da1ae23171de0ea3cdb2c620f71eb2ab983 Mon Sep 17 00:00:00 2001 From: Nicholas Kazlauskas Date: Thu, 31 Jan 2019 13:58:21 -0500 Subject: [PATCH 461/525] drm/amd/display: Attach VRR properties for eDP connectors [Why] eDP was missing in the checks for supported VRR connectors. [How] Attach the properties for eDP connectors too. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202449 Signed-off-by: Nicholas Kazlauskas Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index f4fa40c387d3..0b392bfca284 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -4082,7 +4082,8 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm, } if (connector_type == DRM_MODE_CONNECTOR_HDMIA || - connector_type == DRM_MODE_CONNECTOR_DisplayPort) { + connector_type == DRM_MODE_CONNECTOR_DisplayPort || + connector_type == DRM_MODE_CONNECTOR_eDP) { drm_connector_attach_vrr_capable_property( &aconnector->base); } From 75c05a74e745ae7d663b04d75777af80ada2233c Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 6 Feb 2019 00:02:58 +0100 Subject: [PATCH 462/525] net: dsa: mv88e6xxx: Fix counting of ATU violations The ATU port vector contains a bit per port of the switch. The code wrongly used it as a port number, and incremented a port counter. This resulted in the wrong interfaces counter being incremented, and potentially going off the end of the array of ports. Fix this by using the source port ID for the violation, which really is a port number. Reported-by: Chris Healy Tested-by: Chris Healy Fixes: 65f60e4582bd ("net: dsa: mv88e6xxx: Keep ATU/VTU violation statistics") Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/global1_atu.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c index 5200e4bdce93..ea243840ee0f 100644 --- a/drivers/net/dsa/mv88e6xxx/global1_atu.c +++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c @@ -314,6 +314,7 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id) { struct mv88e6xxx_chip *chip = dev_id; struct mv88e6xxx_atu_entry entry; + int spid; int err; u16 val; @@ -336,6 +337,8 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id) if (err) goto out; + spid = entry.state; + if (val & MV88E6XXX_G1_ATU_OP_AGE_OUT_VIOLATION) { dev_err_ratelimited(chip->dev, "ATU age out violation for %pM\n", @@ -344,23 +347,23 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id) if (val & MV88E6XXX_G1_ATU_OP_MEMBER_VIOLATION) { dev_err_ratelimited(chip->dev, - "ATU member violation for %pM portvec %x\n", - entry.mac, entry.portvec); - chip->ports[entry.portvec].atu_member_violation++; + "ATU member violation for %pM portvec %x spid %d\n", + entry.mac, entry.portvec, spid); + chip->ports[spid].atu_member_violation++; } if (val & MV88E6XXX_G1_ATU_OP_MISS_VIOLATION) { dev_err_ratelimited(chip->dev, - "ATU miss violation for %pM portvec %x\n", - entry.mac, entry.portvec); - chip->ports[entry.portvec].atu_miss_violation++; + "ATU miss violation for %pM portvec %x spid %d\n", + entry.mac, entry.portvec, spid); + chip->ports[spid].atu_miss_violation++; } if (val & MV88E6XXX_G1_ATU_OP_FULL_VIOLATION) { dev_err_ratelimited(chip->dev, - "ATU full violation for %pM portvec %x\n", - entry.mac, entry.portvec); - chip->ports[entry.portvec].atu_full_violation++; + "ATU full violation for %pM portvec %x spid %d\n", + entry.mac, entry.portvec, spid); + chip->ports[spid].atu_full_violation++; } mutex_unlock(&chip->reg_lock); From bdcc5bc25548ef6b08e2e43937148f907c212292 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 5 Feb 2019 15:38:44 -0800 Subject: [PATCH 463/525] mISDN: fix a race in dev_expire_timer() Since mISDN_close() uses dev->pending to iterate over active timers, there is a chance that one timer got removed from the ->pending list in dev_expire_timer() but that the thread has not called yet wake_up_interruptible() So mISDN_close() could miss this and free dev before completion of at least one dev_expire_timer() syzbot was able to catch this race : BUG: KASAN: use-after-free in register_lock_class+0x140c/0x1bf0 kernel/locking/lockdep.c:827 Write of size 8 at addr ffff88809fc18948 by task syz-executor1/24769 CPU: 1 PID: 24769 Comm: syz-executor1 Not tainted 5.0.0-rc5 #60 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x172/0x1f0 lib/dump_stack.c:113 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:187 kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317 __asan_report_store8_noabort+0x17/0x20 mm/kasan/generic_report.c:140 register_lock_class+0x140c/0x1bf0 kernel/locking/lockdep.c:827 __lock_acquire+0x11f/0x4700 kernel/locking/lockdep.c:3224 lock_acquire+0x16f/0x3f0 kernel/locking/lockdep.c:3841 __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline] _raw_spin_lock_irqsave+0x95/0xcd kernel/locking/spinlock.c:152 __wake_up_common_lock+0xc7/0x190 kernel/sched/wait.c:120 __wake_up+0xe/0x10 kernel/sched/wait.c:145 dev_expire_timer+0xe4/0x3b0 drivers/isdn/mISDN/timerdev.c:174 call_timer_fn+0x190/0x720 kernel/time/timer.c:1325 protocol 88fb is buggy, dev hsr_slave_0 protocol 88fb is buggy, dev hsr_slave_1 expire_timers kernel/time/timer.c:1362 [inline] __run_timers kernel/time/timer.c:1681 [inline] __run_timers kernel/time/timer.c:1649 [inline] run_timer_softirq+0x652/0x1700 kernel/time/timer.c:1694 __do_softirq+0x266/0x95a kernel/softirq.c:292 invoke_softirq kernel/softirq.c:373 [inline] irq_exit+0x180/0x1d0 kernel/softirq.c:413 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0x14a/0x570 arch/x86/kernel/apic/apic.c:1062 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:807 RIP: 0010:__sanitizer_cov_trace_pc+0x26/0x50 kernel/kcov.c:101 Code: 90 90 90 90 55 48 89 e5 48 8b 75 08 65 48 8b 04 25 40 ee 01 00 65 8b 15 98 12 92 7e 81 e2 00 01 1f 00 75 2b 8b 90 d8 12 00 00 <83> fa 02 75 20 48 8b 88 e0 12 00 00 8b 80 dc 12 00 00 48 8b 11 48 RSP: 0018:ffff8880589b7a60 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffff888087ce25c0 RBX: 0000000000000001 RCX: ffffffff818f8ca3 RDX: 0000000000000000 RSI: ffffffff818f8b48 RDI: 0000000000000001 RBP: ffff8880589b7a60 R08: ffff888087ce25c0 R09: ffffed1015d25bd0 R10: ffffed1015d25bcf R11: ffff8880ae92de7b R12: ffffea0001ae4680 R13: ffffea0001ae4688 R14: 0000000000000000 R15: ffffea0001b41648 PageIdle include/linux/page-flags.h:398 [inline] page_is_idle include/linux/page_idle.h:29 [inline] mark_page_accessed+0x618/0x1140 mm/swap.c:398 touch_buffer fs/buffer.c:59 [inline] __find_get_block+0x312/0xcc0 fs/buffer.c:1298 sb_find_get_block include/linux/buffer_head.h:338 [inline] recently_deleted fs/ext4/ialloc.c:682 [inline] find_inode_bit.isra.0+0x202/0x510 fs/ext4/ialloc.c:722 __ext4_new_inode+0x14ad/0x52c0 fs/ext4/ialloc.c:914 ext4_symlink+0x3f8/0xbe0 fs/ext4/namei.c:3096 vfs_symlink fs/namei.c:4126 [inline] vfs_symlink+0x378/0x5d0 fs/namei.c:4112 do_symlinkat+0x22b/0x290 fs/namei.c:4153 __do_sys_symlink fs/namei.c:4172 [inline] __se_sys_symlink fs/namei.c:4170 [inline] __x64_sys_symlink+0x59/0x80 fs/namei.c:4170 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x457b67 Code: 0f 1f 00 b8 5c 00 00 00 0f 05 48 3d 01 f0 ff ff 0f 83 6d bb fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 b8 58 00 00 00 0f 05 <48> 3d 01 f0 ff ff 0f 83 4d bb fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fff045ce0f8 EFLAGS: 00000202 ORIG_RAX: 0000000000000058 RAX: ffffffffffffffda RBX: 0000000000000001 RCX: 0000000000457b67 RDX: 00007fff045ce173 RSI: 00000000004bd63f RDI: 00007fff045ce160 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000013 R10: 0000000000000075 R11: 0000000000000202 R12: 0000000000000000 R13: 0000000000000001 R14: 000000000000029b R15: 0000000000000001 Allocated by task 24763: save_stack+0x45/0xd0 mm/kasan/common.c:73 set_track mm/kasan/common.c:85 [inline] __kasan_kmalloc mm/kasan/common.c:496 [inline] __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:469 kasan_kmalloc+0x9/0x10 mm/kasan/common.c:504 kmem_cache_alloc_trace+0x151/0x760 mm/slab.c:3609 kmalloc include/linux/slab.h:545 [inline] mISDN_open+0x9a/0x270 drivers/isdn/mISDN/timerdev.c:59 misc_open+0x398/0x4c0 drivers/char/misc.c:141 chrdev_open+0x247/0x6b0 fs/char_dev.c:417 do_dentry_open+0x47d/0x1130 fs/open.c:771 vfs_open+0xa0/0xd0 fs/open.c:880 do_last fs/namei.c:3418 [inline] path_openat+0x10d7/0x4690 fs/namei.c:3534 do_filp_open+0x1a1/0x280 fs/namei.c:3564 do_sys_open+0x3fe/0x5d0 fs/open.c:1063 __do_sys_openat fs/open.c:1090 [inline] __se_sys_openat fs/open.c:1084 [inline] __x64_sys_openat+0x9d/0x100 fs/open.c:1084 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 24762: save_stack+0x45/0xd0 mm/kasan/common.c:73 set_track mm/kasan/common.c:85 [inline] __kasan_slab_free+0x102/0x150 mm/kasan/common.c:458 kasan_slab_free+0xe/0x10 mm/kasan/common.c:466 __cache_free mm/slab.c:3487 [inline] kfree+0xcf/0x230 mm/slab.c:3806 mISDN_close+0x2a1/0x390 drivers/isdn/mISDN/timerdev.c:97 __fput+0x2df/0x8d0 fs/file_table.c:278 ____fput+0x16/0x20 fs/file_table.c:309 task_work_run+0x14a/0x1c0 kernel/task_work.c:113 tracehook_notify_resume include/linux/tracehook.h:188 [inline] exit_to_usermode_loop+0x273/0x2c0 arch/x86/entry/common.c:166 prepare_exit_to_usermode arch/x86/entry/common.c:197 [inline] syscall_return_slowpath arch/x86/entry/common.c:268 [inline] do_syscall_64+0x52d/0x610 arch/x86/entry/common.c:293 entry_SYSCALL_64_after_hwframe+0x49/0xbe The buggy address belongs to the object at ffff88809fc18900 which belongs to the cache kmalloc-192 of size 192 The buggy address is located 72 bytes inside of 192-byte region [ffff88809fc18900, ffff88809fc189c0) The buggy address belongs to the page: page:ffffea00027f0600 count:1 mapcount:0 mapping:ffff88812c3f0040 index:0xffff88809fc18000 flags: 0x1fffc0000000200(slab) raw: 01fffc0000000200 ffffea000269f648 ffffea00029f7408 ffff88812c3f0040 raw: ffff88809fc18000 ffff88809fc18000 000000010000000b 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88809fc18800: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff88809fc18880: 00 fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffff88809fc18900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff88809fc18980: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc ffff88809fc18a00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 Signed-off-by: Eric Dumazet Cc: Karsten Keil Reported-by: syzbot Signed-off-by: David S. Miller --- drivers/isdn/mISDN/timerdev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/isdn/mISDN/timerdev.c b/drivers/isdn/mISDN/timerdev.c index 211ed6cffd10..578978711887 100644 --- a/drivers/isdn/mISDN/timerdev.c +++ b/drivers/isdn/mISDN/timerdev.c @@ -170,8 +170,8 @@ dev_expire_timer(struct timer_list *t) spin_lock_irqsave(&timer->dev->lock, flags); if (timer->id >= 0) list_move_tail(&timer->list, &timer->dev->expired); - spin_unlock_irqrestore(&timer->dev->lock, flags); wake_up_interruptible(&timer->dev->wait); + spin_unlock_irqrestore(&timer->dev->lock, flags); } static int From c97617a81a7616d49bc3700959e08c6c6f447093 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 5 Feb 2019 17:57:27 +0100 Subject: [PATCH 464/525] ALSA: hda/ca0132 - Fix build error without CONFIG_PCI A call of pci_iounmap() call without CONFIG_PCI leads to a build error on some architectures. We tried to address this and add a check of IS_ENABLED(CONFIG_PCI), but this still doesn't seem enough for sh. Ideally we should fix it globally, it's really a corner case, so let's paper over it with a simpler ifdef. Fixes: 1e73359a24fa ("ALSA: hda/ca0132 - make pci_iounmap() call conditional") Reported-by: Kuninori Morimoto Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_ca0132.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index e5bdbc245682..29882bda7632 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -8451,8 +8451,10 @@ static void ca0132_free(struct hda_codec *codec) ca0132_exit_chip(codec); snd_hda_power_down(codec); - if (IS_ENABLED(CONFIG_PCI) && spec->mem_base) +#ifdef CONFIG_PCI + if (spec->mem_base) pci_iounmap(codec->bus->pci, spec->mem_base); +#endif kfree(spec->spec_init_verbs); kfree(codec->spec); } From d028a646e84b9b131e4ff2cb5bbdd3825d141028 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Tue, 5 Feb 2019 16:18:46 +0200 Subject: [PATCH 465/525] drm/i915: Try to sanitize bogus DPLL state left over by broken SNB BIOSen MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Certain SNB machines (eg. ASUS K53SV) seem to have a broken BIOS which misprograms the hardware badly when encountering a suitably high resolution display. The programmed pipe timings are somewhat bonkers and the DPLL is totally misprogrammed (P divider == 0). That will result in atomic commit timeouts as apparently the pipe is sufficiently stuck to not signal vblank interrupts. IIRC something like this was also observed on some other SNB machine years ago (might have been a Dell XPS 8300) but a BIOS update cured it. Sadly looks like this was never fixed for the ASUS K53SV as the latest BIOS (K53SV.320 11/11/2011) is still broken. The quickest way to deal with this seems to be to shut down the pipe+ports+DPLL. Unfortunately doing this during the normal sanitization phase isn't quite soon enough as we already spew several WARNs about the bogus hardware state. But it's better than hanging the boot for a few dozen seconds. Since this is limited to a few old machines it doesn't seem entirely worthwile to try and rework the readout+sanitization code to handle it more gracefully. v2: Fix potential NULL deref (kbuild test robot) Constify has_bogus_dpll_config() Cc: stable@vger.kernel.org # v4.20+ Cc: Daniel Kamil Kozar Reported-by: Daniel Kamil Kozar Tested-by: Daniel Kamil Kozar Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=109245 Fixes: 516a49cc1946 ("drm/i915: Fix assert_plane() warning on bootup with external display") Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20190111174950.10681-1-ville.syrjala@linux.intel.com Reviewed-by: Mika Kahola (cherry picked from commit 7bed8adcd9f86231bb69bbc02f88ad89330f99e3) Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20190205141846.6053-1-ville.syrjala@linux.intel.com --- drivers/gpu/drm/i915/intel_display.c | 50 ++++++++++++++++++++++++---- 1 file changed, 44 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 3da9c0f9e948..248128126422 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -15415,16 +15415,45 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc, } } +static bool has_bogus_dpll_config(const struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev); + + /* + * Some SNB BIOSen (eg. ASUS K53SV) are known to misprogram + * the hardware when a high res displays plugged in. DPLL P + * divider is zero, and the pipe timings are bonkers. We'll + * try to disable everything in that case. + * + * FIXME would be nice to be able to sanitize this state + * without several WARNs, but for now let's take the easy + * road. + */ + return IS_GEN6(dev_priv) && + crtc_state->base.active && + crtc_state->shared_dpll && + crtc_state->port_clock == 0; +} + static void intel_sanitize_encoder(struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct intel_connector *connector; + struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc); + struct intel_crtc_state *crtc_state = crtc ? + to_intel_crtc_state(crtc->base.state) : NULL; /* We need to check both for a crtc link (meaning that the * encoder is active and trying to read from a pipe) and the * pipe itself being active. */ - bool has_active_crtc = encoder->base.crtc && - to_intel_crtc(encoder->base.crtc)->active; + bool has_active_crtc = crtc_state && + crtc_state->base.active; + + if (crtc_state && has_bogus_dpll_config(crtc_state)) { + DRM_DEBUG_KMS("BIOS has misprogrammed the hardware. Disabling pipe %c\n", + pipe_name(crtc->pipe)); + has_active_crtc = false; + } connector = intel_encoder_find_connector(encoder); if (connector && !has_active_crtc) { @@ -15435,16 +15464,25 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder) /* Connector is active, but has no active pipe. This is * fallout from our resume register restoring. Disable * the encoder manually again. */ - if (encoder->base.crtc) { - struct drm_crtc_state *crtc_state = encoder->base.crtc->state; + if (crtc_state) { + struct drm_encoder *best_encoder; DRM_DEBUG_KMS("[ENCODER:%d:%s] manually disabled\n", encoder->base.base.id, encoder->base.name); + + /* avoid oopsing in case the hooks consult best_encoder */ + best_encoder = connector->base.state->best_encoder; + connector->base.state->best_encoder = &encoder->base; + if (encoder->disable) - encoder->disable(encoder, to_intel_crtc_state(crtc_state), connector->base.state); + encoder->disable(encoder, crtc_state, + connector->base.state); if (encoder->post_disable) - encoder->post_disable(encoder, to_intel_crtc_state(crtc_state), connector->base.state); + encoder->post_disable(encoder, crtc_state, + connector->base.state); + + connector->base.state->best_encoder = best_encoder; } encoder->base.crtc = NULL; From d5d27fd9826b59979b184ec288e4812abac0e988 Mon Sep 17 00:00:00 2001 From: Martin Kepplinger Date: Tue, 5 Feb 2019 16:52:51 +0100 Subject: [PATCH 466/525] mtd: rawnand: gpmi: fix MX28 bus master lockup problem MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Disable BCH soft reset according to MX23 erratum #2847 ("BCH soft reset may cause bus master lock up") for MX28 too. It has the same problem. Observed problem: once per 100,000+ MX28 reboots NAND read failed on DMA timeout errors: [ 1.770823] UBI: attaching mtd3 to ubi0 [ 2.768088] gpmi_nand: DMA timeout, last DMA :1 [ 3.958087] gpmi_nand: BCH timeout, last DMA :1 [ 4.156033] gpmi_nand: Error in ECC-based read: -110 [ 4.161136] UBI warning: ubi_io_read: error -110 while reading 64 bytes from PEB 0:0, read only 0 bytes, retry [ 4.171283] step 1 error [ 4.173846] gpmi_nand: Chip: 0, Error -1 Without BCH soft reset we successfully executed 1,000,000 MX28 reboots. I have a quote from NXP regarding this problem, from July 18th 2016: "As the i.MX23 and i.MX28 are of the same generation, they share many characteristics. Unfortunately, also the erratas may be shared. In case of the documented erratas and the workarounds, you can also apply the workaround solution of one device on the other one. This have been reported, but I’m afraid that there are not an estimated date for updating the Errata documents. Please accept our apologies for any inconveniences this may cause." Fixes: 6f2a6a52560a ("mtd: nand: gpmi: reset BCH earlier, too, to avoid NAND startup problems") Cc: stable@vger.kernel.org Signed-off-by: Manfred Schlaegl Signed-off-by: Martin Kepplinger Reviewed-by: Miquel Raynal Reviewed-by: Fabio Estevam Acked-by: Han Xu Signed-off-by: Boris Brezillon --- drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c index bd4cfac6b5aa..a4768df5083f 100644 --- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c +++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c @@ -155,9 +155,10 @@ int gpmi_init(struct gpmi_nand_data *this) /* * Reset BCH here, too. We got failures otherwise :( - * See later BCH reset for explanation of MX23 handling + * See later BCH reset for explanation of MX23 and MX28 handling */ - ret = gpmi_reset_block(r->bch_regs, GPMI_IS_MX23(this)); + ret = gpmi_reset_block(r->bch_regs, + GPMI_IS_MX23(this) || GPMI_IS_MX28(this)); if (ret) goto err_out; @@ -263,12 +264,10 @@ int bch_set_geometry(struct gpmi_nand_data *this) /* * Due to erratum #2847 of the MX23, the BCH cannot be soft reset on this * chip, otherwise it will lock up. So we skip resetting BCH on the MX23. - * On the other hand, the MX28 needs the reset, because one case has been - * seen where the BCH produced ECC errors constantly after 10000 - * consecutive reboots. The latter case has not been seen on the MX23 - * yet, still we don't know if it could happen there as well. + * and MX28. */ - ret = gpmi_reset_block(r->bch_regs, GPMI_IS_MX23(this)); + ret = gpmi_reset_block(r->bch_regs, + GPMI_IS_MX23(this) || GPMI_IS_MX28(this)); if (ret) goto err_out; From 4df04ac9b37f278c48bb696289aff8f81226af4b Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Fri, 11 Jan 2019 05:50:33 +0200 Subject: [PATCH 467/525] drm/omap: dsi: Fix crash in DSI debug dumps Reading any of the DSI debugfs files results in a crash, as wrong pointer is passed to the dump functions, and the dump functions use a wrong pointer. This patch fixes DSI debug dumps. Fixes: f3ed97f9ae7d ("drm/omap: dsi: Simplify debugfs implementation") Signed-off-by: Tomi Valkeinen Reviewed-by: Laurent Pinchart Signed-off-by: Laurent Pinchart Signed-off-by: Tomi Valkeinen Link: https://patchwork.freedesktop.org/patch/msgid/20190111035120.20668-3-laurent.pinchart@ideasonboard.com --- drivers/gpu/drm/omapdrm/dss/dsi.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/omapdrm/dss/dsi.c b/drivers/gpu/drm/omapdrm/dss/dsi.c index 00a9c2ab9e6c..277f9dd2ec8c 100644 --- a/drivers/gpu/drm/omapdrm/dss/dsi.c +++ b/drivers/gpu/drm/omapdrm/dss/dsi.c @@ -1406,7 +1406,7 @@ static void dsi_pll_disable(struct dss_pll *pll) static int dsi_dump_dsi_clocks(struct seq_file *s, void *p) { - struct dsi_data *dsi = p; + struct dsi_data *dsi = s->private; struct dss_pll_clock_info *cinfo = &dsi->pll.cinfo; enum dss_clk_source dispc_clk_src, dsi_clk_src; int dsi_module = dsi->module_id; @@ -1467,7 +1467,7 @@ static int dsi_dump_dsi_clocks(struct seq_file *s, void *p) #ifdef CONFIG_OMAP2_DSS_COLLECT_IRQ_STATS static int dsi_dump_dsi_irqs(struct seq_file *s, void *p) { - struct dsi_data *dsi = p; + struct dsi_data *dsi = s->private; unsigned long flags; struct dsi_irq_stats stats; @@ -1558,7 +1558,7 @@ static int dsi_dump_dsi_irqs(struct seq_file *s, void *p) static int dsi_dump_dsi_regs(struct seq_file *s, void *p) { - struct dsi_data *dsi = p; + struct dsi_data *dsi = s->private; if (dsi_runtime_get(dsi)) return 0; @@ -5083,15 +5083,15 @@ static int dsi_bind(struct device *dev, struct device *master, void *data) snprintf(name, sizeof(name), "dsi%u_regs", dsi->module_id + 1); dsi->debugfs.regs = dss_debugfs_create_file(dss, name, - dsi_dump_dsi_regs, &dsi); + dsi_dump_dsi_regs, dsi); #ifdef CONFIG_OMAP2_DSS_COLLECT_IRQ_STATS snprintf(name, sizeof(name), "dsi%u_irqs", dsi->module_id + 1); dsi->debugfs.irqs = dss_debugfs_create_file(dss, name, - dsi_dump_dsi_irqs, &dsi); + dsi_dump_dsi_irqs, dsi); #endif snprintf(name, sizeof(name), "dsi%u_clks", dsi->module_id + 1); dsi->debugfs.clks = dss_debugfs_create_file(dss, name, - dsi_dump_dsi_clocks, &dsi); + dsi_dump_dsi_clocks, dsi); return 0; } From 0940c52742de0d2f70ba687bfd5fe8aa38c5f27d Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Fri, 11 Jan 2019 05:50:34 +0200 Subject: [PATCH 468/525] drm/omap: dsi: Fix OF platform depopulate Commit edb715dffdee ("drm/omap: dss: dsi: Move initialization code from bind to probe") moved the of_platform_populate() call from dsi_bind() to dsi_probe(), but failed to move the corresponding of_platform_depopulate() from dsi_unbind() to dsi_remove(). This results in OF child devices being potentially removed multiple times. Fix it by placing the of_platform_depopulate() call where it belongs. Fixes: edb715dffdee ("drm/omap: dss: dsi: Move initialization code from bind to probe") Signed-off-by: Laurent Pinchart Reviewed-by: Laurent Pinchart Signed-off-by: Tomi Valkeinen Link: https://patchwork.freedesktop.org/patch/msgid/20190111035120.20668-4-laurent.pinchart@ideasonboard.com --- drivers/gpu/drm/omapdrm/dss/dsi.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/omapdrm/dss/dsi.c b/drivers/gpu/drm/omapdrm/dss/dsi.c index 277f9dd2ec8c..b5685018d830 100644 --- a/drivers/gpu/drm/omapdrm/dss/dsi.c +++ b/drivers/gpu/drm/omapdrm/dss/dsi.c @@ -5104,8 +5104,6 @@ static void dsi_unbind(struct device *dev, struct device *master, void *data) dss_debugfs_remove_file(dsi->debugfs.irqs); dss_debugfs_remove_file(dsi->debugfs.regs); - of_platform_depopulate(dev); - WARN_ON(dsi->scp_clk_refcount > 0); dss_pll_unregister(&dsi->pll); @@ -5457,6 +5455,8 @@ static int dsi_remove(struct platform_device *pdev) dsi_uninit_output(dsi); + of_platform_depopulate(&pdev->dev); + pm_runtime_disable(&pdev->dev); if (dsi->vdds_dsi_reg != NULL && dsi->vdds_dsi_enabled) { From 6297388e1eddd2f1345cea5892156223995bcf2d Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Fri, 11 Jan 2019 05:50:35 +0200 Subject: [PATCH 469/525] drm/omap: dsi: Hack-fix DSI bus flags Since commit b4935e3a3cfa ("drm/omap: Store bus flags in the omap_dss_device structure") video mode flags are managed by the omapdss (and later omapdrm) core based on bus flags stored in omap_dss_device. This works fine for all devices whose video modes are set by the omapdss and omapdrm core, but breaks DSI operation as the DSI still uses legacy code paths and sets the DISPC timings manually. To fix the problem properly we should move the DSI encoder to the new encoder model. This will however require a considerable amount of work. Restore DSI operation by adding back video mode flags handling in the DSI encoder driver as a hack in the meantime. Fixes: b4935e3a3cfa ("drm/omap: Store bus flags in the omap_dss_device structure") Signed-off-by: Laurent Pinchart Reviewed-by: Laurent Pinchart Signed-off-by: Tomi Valkeinen Link: https://patchwork.freedesktop.org/patch/msgid/20190111035120.20668-5-laurent.pinchart@ideasonboard.com --- drivers/gpu/drm/omapdrm/dss/dsi.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/gpu/drm/omapdrm/dss/dsi.c b/drivers/gpu/drm/omapdrm/dss/dsi.c index b5685018d830..64fb788b6647 100644 --- a/drivers/gpu/drm/omapdrm/dss/dsi.c +++ b/drivers/gpu/drm/omapdrm/dss/dsi.c @@ -4751,6 +4751,17 @@ static int dsi_set_config(struct omap_dss_device *dssdev, dsi->vm.flags |= DISPLAY_FLAGS_HSYNC_HIGH; dsi->vm.flags &= ~DISPLAY_FLAGS_VSYNC_LOW; dsi->vm.flags |= DISPLAY_FLAGS_VSYNC_HIGH; + /* + * HACK: These flags should be handled through the omap_dss_device bus + * flags, but this will only be possible when the DSI encoder will be + * converted to the omapdrm-managed encoder model. + */ + dsi->vm.flags &= ~DISPLAY_FLAGS_PIXDATA_NEGEDGE; + dsi->vm.flags |= DISPLAY_FLAGS_PIXDATA_POSEDGE; + dsi->vm.flags &= ~DISPLAY_FLAGS_DE_LOW; + dsi->vm.flags |= DISPLAY_FLAGS_DE_HIGH; + dsi->vm.flags &= ~DISPLAY_FLAGS_SYNC_POSEDGE; + dsi->vm.flags |= DISPLAY_FLAGS_SYNC_NEGEDGE; dss_mgr_set_timings(&dsi->output, &dsi->vm); From ec51f8ee1e63498e9f521ec0e5a6d04622bb2c67 Mon Sep 17 00:00:00 2001 From: Mike Marshall Date: Tue, 5 Feb 2019 14:13:35 -0500 Subject: [PATCH 470/525] aio: initialize kiocb private in case any filesystems expect it. A recent optimization had left private uninitialized. Fixes: 2bc4ca9bb600 ("aio: don't zero entire aio_kiocb aio_get_req()") Reviewed-by: Christoph Hellwig Signed-off-by: Mike Marshall Signed-off-by: Jens Axboe --- fs/aio.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/aio.c b/fs/aio.c index b906ff70c90f..aaaaf4d12c73 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -1436,6 +1436,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) if (unlikely(!req->ki_filp)) return -EBADF; req->ki_complete = aio_complete_rw; + req->private = NULL; req->ki_pos = iocb->aio_offset; req->ki_flags = iocb_flags(req->ki_filp); if (iocb->aio_flags & IOCB_FLAG_RESFD) From e7ad43c3eda6a1690c4c3c341f95dc1c6898da83 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Mon, 28 Jan 2019 09:46:07 -0700 Subject: [PATCH 471/525] nvme: lock NS list changes while handling command effects If a controller supports the NS Change Notification, the namespace scan_work is automatically triggered after attaching a new namespace. Occasionally the namespace scan_work may append the new namespace to the list before the admin command effects handling is completed. The effects handling unfreezes namespaces, but if it unfreezes the newly attached namespace, its request_queue freeze depth will be off and we'll hit the warning in blk_mq_unfreeze_queue(). On the next namespace add, we will fail to freeze that queue due to the previous bad accounting and deadlock waiting for frozen. Fix that by preventing scan work from altering the namespace list while command effects handling needs to pair freeze with unfreeze. Reported-by: Wen Xiong Tested-by: Wen Xiong Signed-off-by: Keith Busch Reviewed-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 8 +++++++- drivers/nvme/host/nvme.h | 1 + 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 150e49723c15..6a9dd68c0f4f 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1253,6 +1253,7 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns, * effects say only one namespace is affected. */ if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) { + mutex_lock(&ctrl->scan_lock); nvme_start_freeze(ctrl); nvme_wait_freeze(ctrl); } @@ -1281,8 +1282,10 @@ static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects) */ if (effects & NVME_CMD_EFFECTS_LBCC) nvme_update_formats(ctrl); - if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) + if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) { nvme_unfreeze(ctrl); + mutex_unlock(&ctrl->scan_lock); + } if (effects & NVME_CMD_EFFECTS_CCC) nvme_init_identify(ctrl); if (effects & (NVME_CMD_EFFECTS_NIC | NVME_CMD_EFFECTS_NCC)) @@ -3401,6 +3404,7 @@ static void nvme_scan_work(struct work_struct *work) if (nvme_identify_ctrl(ctrl, &id)) return; + mutex_lock(&ctrl->scan_lock); nn = le32_to_cpu(id->nn); if (ctrl->vs >= NVME_VS(1, 1, 0) && !(ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)) { @@ -3409,6 +3413,7 @@ static void nvme_scan_work(struct work_struct *work) } nvme_scan_ns_sequential(ctrl, nn); out_free_id: + mutex_unlock(&ctrl->scan_lock); kfree(id); down_write(&ctrl->namespaces_rwsem); list_sort(NULL, &ctrl->namespaces, ns_cmp); @@ -3652,6 +3657,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, ctrl->state = NVME_CTRL_NEW; spin_lock_init(&ctrl->lock); + mutex_init(&ctrl->scan_lock); INIT_LIST_HEAD(&ctrl->namespaces); init_rwsem(&ctrl->namespaces_rwsem); ctrl->dev = dev; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index ab961bdeea89..c4a1bb41abf0 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -154,6 +154,7 @@ struct nvme_ctrl { enum nvme_ctrl_state state; bool identified; spinlock_t lock; + struct mutex scan_lock; const struct nvme_ctrl_ops *ops; struct request_queue *admin_q; struct request_queue *connect_q; From 5c959d73dba6495ec01d04c206ee679d61ccb2b0 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 23 Jan 2019 18:46:11 -0700 Subject: [PATCH 472/525] nvme-pci: fix rapid add remove sequence A surprise removal may fail to tear down request queues if it is racing with the initial asynchronous probe. If that happens, the remove path won't see the queue resources to tear down, and the controller reset path may create a new request queue on a removed device, but will not be able to make forward progress, deadlocking the pci removal. Protect setting up non-blocking resources from a shutdown by holding the same mutex, and transition to the CONNECTING state after these resources are initialized so the probe path may see the dead controller state before dispatching new IO. Link: https://bugzilla.kernel.org/show_bug.cgi?id=202081 Reported-by: Alex Gagniuc Signed-off-by: Keith Busch Tested-by: Alex Gagniuc Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 9bc585415d9b..022ea1ee63f8 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2557,16 +2557,7 @@ static void nvme_reset_work(struct work_struct *work) if (dev->ctrl.ctrl_config & NVME_CC_ENABLE) nvme_dev_disable(dev, false); - /* - * Introduce CONNECTING state from nvme-fc/rdma transports to mark the - * initializing procedure here. - */ - if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_CONNECTING)) { - dev_warn(dev->ctrl.device, - "failed to mark controller CONNECTING\n"); - goto out; - } - + mutex_lock(&dev->shutdown_lock); result = nvme_pci_enable(dev); if (result) goto out; @@ -2585,6 +2576,17 @@ static void nvme_reset_work(struct work_struct *work) */ dev->ctrl.max_hw_sectors = NVME_MAX_KB_SZ << 1; dev->ctrl.max_segments = NVME_MAX_SEGS; + mutex_unlock(&dev->shutdown_lock); + + /* + * Introduce CONNECTING state from nvme-fc/rdma transports to mark the + * initializing procedure here. + */ + if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_CONNECTING)) { + dev_warn(dev->ctrl.device, + "failed to mark controller CONNECTING\n"); + goto out; + } result = nvme_init_identify(&dev->ctrl); if (result) From 45b13b424faafb81c8c44541f093a682fdabdefc Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 6 Feb 2019 14:52:53 +0300 Subject: [PATCH 473/525] x86/boot/compressed/64: Do not corrupt EDX on EFER.LME=1 setting RDMSR in the trampoline code overwrites EDX but that register is used to indicate whether 5-level paging has to be enabled and if clobbered, leads to failure to boot on a 5-level paging machine. Preserve EDX on the stack while we are dealing with EFER. Fixes: b677dfae5aa1 ("x86/boot/compressed/64: Set EFER.LME=1 in 32-bit trampoline before returning to long mode") Reported-by: Kyle D Pelton Signed-off-by: Kirill A. Shutemov Signed-off-by: Borislav Petkov Cc: dave.hansen@linux.intel.com Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Wei Huang Cc: x86-ml Link: https://lkml.kernel.org/r/20190206115253.1907-1-kirill.shutemov@linux.intel.com --- arch/x86/boot/compressed/head_64.S | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index f105ae8651c9..f62e347862cc 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -602,10 +602,12 @@ ENTRY(trampoline_32bit_src) 3: /* Set EFER.LME=1 as a precaution in case hypervsior pulls the rug */ pushl %ecx + pushl %edx movl $MSR_EFER, %ecx rdmsr btsl $_EFER_LME, %eax wrmsr + popl %edx popl %ecx /* Enable PAE and LA57 (if required) paging modes */ From 6dce3c20ac429e7a651d728e375853370c796e8d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 4 Feb 2019 08:36:06 -0800 Subject: [PATCH 474/525] rxrpc: bad unlock balance in rxrpc_recvmsg When either "goto wait_interrupted;" or "goto wait_error;" paths are taken, socket lock has already been released. This patch fixes following syzbot splat : WARNING: bad unlock balance detected! 5.0.0-rc4+ #59 Not tainted ------------------------------------- syz-executor223/8256 is trying to release lock (sk_lock-AF_RXRPC) at: [] rxrpc_recvmsg+0x6d3/0x3099 net/rxrpc/recvmsg.c:598 but there are no more locks to release! other info that might help us debug this: 1 lock held by syz-executor223/8256: #0: 00000000fa9ed0f4 (slock-AF_RXRPC){+...}, at: spin_lock_bh include/linux/spinlock.h:334 [inline] #0: 00000000fa9ed0f4 (slock-AF_RXRPC){+...}, at: release_sock+0x20/0x1c0 net/core/sock.c:2798 stack backtrace: CPU: 1 PID: 8256 Comm: syz-executor223 Not tainted 5.0.0-rc4+ #59 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x172/0x1f0 lib/dump_stack.c:113 print_unlock_imbalance_bug kernel/locking/lockdep.c:3391 [inline] print_unlock_imbalance_bug.cold+0x114/0x123 kernel/locking/lockdep.c:3368 __lock_release kernel/locking/lockdep.c:3601 [inline] lock_release+0x67e/0xa00 kernel/locking/lockdep.c:3860 sock_release_ownership include/net/sock.h:1471 [inline] release_sock+0x183/0x1c0 net/core/sock.c:2808 rxrpc_recvmsg+0x6d3/0x3099 net/rxrpc/recvmsg.c:598 sock_recvmsg_nosec net/socket.c:794 [inline] sock_recvmsg net/socket.c:801 [inline] sock_recvmsg+0xd0/0x110 net/socket.c:797 __sys_recvfrom+0x1ff/0x350 net/socket.c:1845 __do_sys_recvfrom net/socket.c:1863 [inline] __se_sys_recvfrom net/socket.c:1859 [inline] __x64_sys_recvfrom+0xe1/0x1a0 net/socket.c:1859 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x446379 Code: e8 2c b3 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 2b 09 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fe5da89fd98 EFLAGS: 00000246 ORIG_RAX: 000000000000002d RAX: ffffffffffffffda RBX: 00000000006dbc28 RCX: 0000000000446379 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000003 RBP: 00000000006dbc20 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000006dbc2c R13: 0000000000000000 R14: 0000000000000000 R15: 20c49ba5e353f7cf Fixes: 248f219cb8bc ("rxrpc: Rewrite the data and ack handling code") Signed-off-by: Eric Dumazet Cc: David Howells Reported-by: syzbot Signed-off-by: David S. Miller --- net/rxrpc/recvmsg.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index eaf19ebaa964..3f7bb11f3290 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -596,6 +596,7 @@ error_requeue_call: } error_no_call: release_sock(&rx->sk); +error_trace: trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret); return ret; @@ -604,7 +605,7 @@ wait_interrupted: wait_error: finish_wait(sk_sleep(&rx->sk), &wait); call = NULL; - goto error_no_call; + goto error_trace; } /** From dd957493baa586f1431490f97f9c7c45eaf8ab10 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sun, 3 Feb 2019 10:02:07 +0100 Subject: [PATCH 475/525] libata: Add NOLPM quirk for SAMSUNG MZ7TE512HMHP-000L1 SSD We've received a bugreport that using LPM with a SAMSUNG MZ7TE512HMHP-000L1 SSD leads to system instability, we already have a quirk for the MZ7TD256HAFV-000L9, which is also a Samsun EVO 840 / PM851 OEM model, so it seems some of these models have a LPM issue. This commits adds a NOLPM quirk for the model string from the new bugeport, to avoid the reported stability issues. Cc: stable@vger.kernel.org BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=1571330 Signed-off-by: Hans de Goede Signed-off-by: Jens Axboe --- drivers/ata/libata-core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index b8c3f9e6af89..adf28788cab5 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4554,6 +4554,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "SAMSUNG MZMPC128HBFU-000MV", "CXM14M1Q", ATA_HORKAGE_NOLPM, }, { "SAMSUNG SSD PM830 mSATA *", "CXM13D1Q", ATA_HORKAGE_NOLPM, }, { "SAMSUNG MZ7TD256HAFV-000L9", NULL, ATA_HORKAGE_NOLPM, }, + { "SAMSUNG MZ7TE512HMHP-000L1", "EXT06L0Q", ATA_HORKAGE_NOLPM, }, /* devices that don't properly handle queued TRIM commands */ { "Micron_M500IT_*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | From 30363d6506d0d202bb14f4dac36d9b4b0714ad8d Mon Sep 17 00:00:00 2001 From: Chengguang Xu Date: Fri, 1 Feb 2019 11:26:02 +0800 Subject: [PATCH 476/525] m68k: set proper major_num when specifying module param major_num When calling register_blkdev() with specified major device number, the return code is 0 on success. So it seems not correct direct assign return code to variable major_num in this case. Tested-by: Michael Schmitz Reviewed-by: Geert Uytterhoeven Signed-off-by: Chengguang Xu Signed-off-by: Jens Axboe --- arch/m68k/emu/nfblock.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/arch/m68k/emu/nfblock.c b/arch/m68k/emu/nfblock.c index 38049357d6d3..40712e49381b 100644 --- a/arch/m68k/emu/nfblock.c +++ b/arch/m68k/emu/nfblock.c @@ -155,18 +155,22 @@ out: static int __init nfhd_init(void) { u32 blocks, bsize; + int ret; int i; nfhd_id = nf_get_id("XHDI"); if (!nfhd_id) return -ENODEV; - major_num = register_blkdev(major_num, "nfhd"); - if (major_num <= 0) { + ret = register_blkdev(major_num, "nfhd"); + if (ret < 0) { pr_warn("nfhd: unable to get major number\n"); - return major_num; + return ret; } + if (!major_num) + major_num = ret; + for (i = NFHD_DEV_OFFSET; i < 24; i++) { if (nfhd_get_capacity(i, 0, &blocks, &bsize)) continue; From 2b1f86bf741a3220b4471fef197631d6e2264983 Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 6 Feb 2019 10:54:54 +0000 Subject: [PATCH 477/525] MAINTAINERS: add maintainer for SFF/SFP/SFP+ support Add maintainer entry for SFF/SFP/SFP+ support. Signed-off-by: Russell King Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- MAINTAINERS | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 479b03221a4c..39168d401b26 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13708,6 +13708,15 @@ L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/sfc/ +SFF/SFP/SFP+ MODULE SUPPORT +M: Russell King +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/phy/phylink.c +F: drivers/net/phy/sfp* +F: include/linux/phylink.h +F: include/linux/sfp.h + SGI GRU DRIVER M: Dimitri Sivanich S: Maintained From 43636c804df0126da669c261fc820fb22f62bfc2 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Mon, 21 Jan 2019 22:49:37 +0900 Subject: [PATCH 478/525] fs: ratelimit __find_get_block_slow() failure message. When something let __find_get_block_slow() hit all_mapped path, it calls printk() for 100+ times per a second. But there is no need to print same message with such high frequency; it is just asking for stall warning, or at least bloating log files. [ 399.866302][T15342] __find_get_block_slow() failed. block=1, b_blocknr=8 [ 399.873324][T15342] b_state=0x00000029, b_size=512 [ 399.878403][T15342] device loop0 blocksize: 4096 [ 399.883296][T15342] __find_get_block_slow() failed. block=1, b_blocknr=8 [ 399.890400][T15342] b_state=0x00000029, b_size=512 [ 399.895595][T15342] device loop0 blocksize: 4096 [ 399.900556][T15342] __find_get_block_slow() failed. block=1, b_blocknr=8 [ 399.907471][T15342] b_state=0x00000029, b_size=512 [ 399.912506][T15342] device loop0 blocksize: 4096 This patch reduces frequency to up to once per a second, in addition to concatenating three lines into one. [ 399.866302][T15342] __find_get_block_slow() failed. block=1, b_blocknr=8, b_state=0x00000029, b_size=512, device loop0 blocksize: 4096 Signed-off-by: Tetsuo Handa Reviewed-by: Jan Kara Cc: Dmitry Vyukov Signed-off-by: Jens Axboe --- fs/buffer.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/fs/buffer.c b/fs/buffer.c index 52d024bfdbc1..48318fb74938 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -200,6 +200,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) struct buffer_head *head; struct page *page; int all_mapped = 1; + static DEFINE_RATELIMIT_STATE(last_warned, HZ, 1); index = block >> (PAGE_SHIFT - bd_inode->i_blkbits); page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED); @@ -227,15 +228,15 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) * file io on the block device and getblk. It gets dealt with * elsewhere, don't buffer_error if we had some unmapped buffers */ - if (all_mapped) { - printk("__find_get_block_slow() failed. " - "block=%llu, b_blocknr=%llu\n", - (unsigned long long)block, - (unsigned long long)bh->b_blocknr); - printk("b_state=0x%08lx, b_size=%zu\n", - bh->b_state, bh->b_size); - printk("device %pg blocksize: %d\n", bdev, - 1 << bd_inode->i_blkbits); + ratelimit_set_flags(&last_warned, RATELIMIT_MSG_ON_RELEASE); + if (all_mapped && __ratelimit(&last_warned)) { + printk("__find_get_block_slow() failed. block=%llu, " + "b_blocknr=%llu, b_state=0x%08lx, b_size=%zu, " + "device %pg blocksize: %d\n", + (unsigned long long)block, + (unsigned long long)bh->b_blocknr, + bh->b_state, bh->b_size, bdev, + 1 << bd_inode->i_blkbits); } out_unlock: spin_unlock(&bd_mapping->private_lock); From e3fdc89ca47ef34dfb6fd5101fec084c3dba5486 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 21 Jan 2019 15:58:38 -0500 Subject: [PATCH 479/525] nfsd: Fix error return values for nfsd4_clone_file_range() If the parameter 'count' is non-zero, nfsd4_clone_file_range() will currently clobber all errors returned by vfs_clone_file_range() and replace them with EINVAL. Fixes: 42ec3d4c0218 ("vfs: make remap_file_range functions take and...") Signed-off-by: Trond Myklebust Cc: stable@vger.kernel.org # v4.20+ Signed-off-by: J. Bruce Fields --- fs/nfsd/vfs.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 9824e32b2f23..7dc98e14655d 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -557,9 +557,11 @@ __be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst, loff_t cloned; cloned = vfs_clone_file_range(src, src_pos, dst, dst_pos, count, 0); + if (cloned < 0) + return nfserrno(cloned); if (count && cloned != count) - cloned = -EINVAL; - return nfserrno(cloned < 0 ? cloned : 0); + return nfserrno(-EINVAL); + return 0; } ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst, From e248aa7be86e8179f20ac0931774ecd746f3f5bf Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 25 Jan 2019 16:54:54 -0500 Subject: [PATCH 480/525] svcrdma: Remove max_sge check at connect time Two and a half years ago, the client was changed to use gathered Send for larger inline messages, in commit 655fec6987b ("xprtrdma: Use gathered Send for large inline messages"). Several fixes were required because there are a few in-kernel device drivers whose max_sge is 3, and these were broken by the change. Apparently my memory is going, because some time later, I submitted commit 25fd86eca11c ("svcrdma: Don't overrun the SGE array in svc_rdma_send_ctxt"), and after that, commit f3c1fd0ee294 ("svcrdma: Reduce max_send_sges"). These too incorrectly assumed in-kernel device drivers would have more than a few Send SGEs available. The fix for the server side is not the same. This is because the fundamental problem on the server is that, whether or not the client has provisioned a chunk for the RPC reply, the server must squeeze even the most complex RPC replies into a single RDMA Send. Failing in the send path because of Send SGE exhaustion should never be an option. Therefore, instead of failing when the send path runs out of SGEs, switch to using a bounce buffer mechanism to handle RPC replies that are too complex for the device to send directly. That allows us to remove the max_sge check to enable drivers with small max_sge to work again. Reported-by: Don Dutile Fixes: 25fd86eca11c ("svcrdma: Don't overrun the SGE array in ...") Cc: stable@vger.kernel.org Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- net/sunrpc/xprtrdma/svc_rdma_sendto.c | 105 +++++++++++++++++++++-- net/sunrpc/xprtrdma/svc_rdma_transport.c | 9 +- 2 files changed, 102 insertions(+), 12 deletions(-) diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index cf51b8f9b15f..1f200119268c 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -537,6 +537,99 @@ void svc_rdma_sync_reply_hdr(struct svcxprt_rdma *rdma, DMA_TO_DEVICE); } +/* If the xdr_buf has more elements than the device can + * transmit in a single RDMA Send, then the reply will + * have to be copied into a bounce buffer. + */ +static bool svc_rdma_pull_up_needed(struct svcxprt_rdma *rdma, + struct xdr_buf *xdr, + __be32 *wr_lst) +{ + int elements; + + /* xdr->head */ + elements = 1; + + /* xdr->pages */ + if (!wr_lst) { + unsigned int remaining; + unsigned long pageoff; + + pageoff = xdr->page_base & ~PAGE_MASK; + remaining = xdr->page_len; + while (remaining) { + ++elements; + remaining -= min_t(u32, PAGE_SIZE - pageoff, + remaining); + pageoff = 0; + } + } + + /* xdr->tail */ + if (xdr->tail[0].iov_len) + ++elements; + + /* assume 1 SGE is needed for the transport header */ + return elements >= rdma->sc_max_send_sges; +} + +/* The device is not capable of sending the reply directly. + * Assemble the elements of @xdr into the transport header + * buffer. + */ +static int svc_rdma_pull_up_reply_msg(struct svcxprt_rdma *rdma, + struct svc_rdma_send_ctxt *ctxt, + struct xdr_buf *xdr, __be32 *wr_lst) +{ + unsigned char *dst, *tailbase; + unsigned int taillen; + + dst = ctxt->sc_xprt_buf; + dst += ctxt->sc_sges[0].length; + + memcpy(dst, xdr->head[0].iov_base, xdr->head[0].iov_len); + dst += xdr->head[0].iov_len; + + tailbase = xdr->tail[0].iov_base; + taillen = xdr->tail[0].iov_len; + if (wr_lst) { + u32 xdrpad; + + xdrpad = xdr_padsize(xdr->page_len); + if (taillen && xdrpad) { + tailbase += xdrpad; + taillen -= xdrpad; + } + } else { + unsigned int len, remaining; + unsigned long pageoff; + struct page **ppages; + + ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT); + pageoff = xdr->page_base & ~PAGE_MASK; + remaining = xdr->page_len; + while (remaining) { + len = min_t(u32, PAGE_SIZE - pageoff, remaining); + + memcpy(dst, page_address(*ppages), len); + remaining -= len; + dst += len; + pageoff = 0; + } + } + + if (taillen) + memcpy(dst, tailbase, taillen); + + ctxt->sc_sges[0].length += xdr->len; + ib_dma_sync_single_for_device(rdma->sc_pd->device, + ctxt->sc_sges[0].addr, + ctxt->sc_sges[0].length, + DMA_TO_DEVICE); + + return 0; +} + /* svc_rdma_map_reply_msg - Map the buffer holding RPC message * @rdma: controlling transport * @ctxt: send_ctxt for the Send WR @@ -559,8 +652,10 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, u32 xdr_pad; int ret; - if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges) - return -EIO; + if (svc_rdma_pull_up_needed(rdma, xdr, wr_lst)) + return svc_rdma_pull_up_reply_msg(rdma, ctxt, xdr, wr_lst); + + ++ctxt->sc_cur_sge_no; ret = svc_rdma_dma_map_buf(rdma, ctxt, xdr->head[0].iov_base, xdr->head[0].iov_len); @@ -591,8 +686,7 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, while (remaining) { len = min_t(u32, PAGE_SIZE - page_off, remaining); - if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges) - return -EIO; + ++ctxt->sc_cur_sge_no; ret = svc_rdma_dma_map_page(rdma, ctxt, *ppages++, page_off, len); if (ret < 0) @@ -606,8 +700,7 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, len = xdr->tail[0].iov_len; tail: if (len) { - if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges) - return -EIO; + ++ctxt->sc_cur_sge_no; ret = svc_rdma_dma_map_buf(rdma, ctxt, base, len); if (ret < 0) return ret; diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 924c17d46903..57f86c63a463 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -419,12 +419,9 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) /* Transport header, head iovec, tail iovec */ newxprt->sc_max_send_sges = 3; /* Add one SGE per page list entry */ - newxprt->sc_max_send_sges += svcrdma_max_req_size / PAGE_SIZE; - if (newxprt->sc_max_send_sges > dev->attrs.max_send_sge) { - pr_err("svcrdma: too few Send SGEs available (%d needed)\n", - newxprt->sc_max_send_sges); - goto errout; - } + newxprt->sc_max_send_sges += (svcrdma_max_req_size / PAGE_SIZE) + 1; + if (newxprt->sc_max_send_sges > dev->attrs.max_send_sge) + newxprt->sc_max_send_sges = dev->attrs.max_send_sge; newxprt->sc_max_req_size = svcrdma_max_req_size; newxprt->sc_max_requests = svcrdma_max_requests; newxprt->sc_max_bc_requests = svcrdma_max_bc_requests; From 00670cb8a73b10b10d3c40f045c15411715e4465 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 6 Feb 2019 18:35:15 +0300 Subject: [PATCH 481/525] net: dsa: Fix NULL checking in dsa_slave_set_eee() This function can't succeed if dp->pl is NULL. It will Oops inside the call to return phylink_ethtool_get_eee(dp->pl, e); Fixes: 1be52e97ed3e ("dsa: slave: eee: Allow ports to use phylink") Signed-off-by: Dan Carpenter Reviewed-by: Florian Fainelli Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- net/dsa/slave.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index b5e44825d173..a1c9fe155057 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -642,7 +642,7 @@ static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e) int ret; /* Port's PHY and MAC both need to be EEE capable */ - if (!dev->phydev && !dp->pl) + if (!dev->phydev || !dp->pl) return -ENODEV; if (!ds->ops->set_mac_eee) @@ -662,7 +662,7 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) int ret; /* Port's PHY and MAC both need to be EEE capable */ - if (!dev->phydev && !dp->pl) + if (!dev->phydev || !dp->pl) return -ENODEV; if (!ds->ops->get_mac_eee) From 645efa84f6c7566ea863ed37a8b3247247f72e02 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Tue, 5 Feb 2019 05:09:00 -0500 Subject: [PATCH 482/525] dm: add memory barrier before waitqueue_active Block core changes to switch bio-based IO accounting to be percpu had a side-effect of altering DM core to now rely on calling waitqueue_active (in both bio-based and request-based) to check if another task is in dm_wait_for_completion(). A memory barrier is needed before calling waitqueue_active(). DM core doesn't piggyback on a preceding memory barrier so it must explicitly use its own. For more details on why using waitqueue_active() without a preceding barrier is unsafe, please see the comment before the waitqueue_active() definition in include/linux/wait.h. Add the missing memory barrier by switching to using wq_has_sleeper(). Fixes: 6f75723190d8 ("dm: remove the pending IO accounting") Fixes: c4576aed8d85 ("dm: fix request-based dm's use of dm_wait_for_completion") Signed-off-by: Mikulas Patocka Signed-off-by: Mike Snitzer --- drivers/md/dm-rq.c | 2 +- drivers/md/dm.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index 4eb5f8c56535..a20531e5f3b4 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -131,7 +131,7 @@ static void rq_end_stats(struct mapped_device *md, struct request *orig) static void rq_completed(struct mapped_device *md) { /* nudge anyone waiting on suspend queue */ - if (unlikely(waitqueue_active(&md->wait))) + if (unlikely(wq_has_sleeper(&md->wait))) wake_up(&md->wait); /* diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 2b53c3841b53..a0972a9301de 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -699,7 +699,7 @@ static void end_io_acct(struct dm_io *io) true, duration, &io->stats_aux); /* nudge anyone waiting on suspend queue */ - if (unlikely(waitqueue_active(&md->wait))) + if (unlikely(wq_has_sleeper(&md->wait))) wake_up(&md->wait); } From fa8db4948f5224dae33a0e783e7dec682e145f88 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Tue, 5 Feb 2019 17:07:58 -0500 Subject: [PATCH 483/525] dm: don't use bio_trim() afterall bio_trim() has an early return, which makes it _not_ idempotent, if the offset is 0 and the bio's bi_size already matches the requested size. Prior to DM, all users of bio_trim() were fine with this. But DM has exposed the fact that bio_trim()'s early return is incompatible with a cloned bio whose integrity payload must be trimmed via bio_integrity_trim(). Fix this by reverting DM back to doing the equivalent of bio_trim() but in an idempotent manner (so bio_integrity_trim is always performed). Follow-on work is needed to assess what benefit bio_trim()'s early return is providing to its existing callers. Reported-by: Milan Broz Fixes: 57c36519e4b94 ("dm: fix clone_bio() to trigger blk_recount_segments()") Signed-off-by: Mike Snitzer --- drivers/md/dm.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index a0972a9301de..515e6af9bed2 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1336,7 +1336,11 @@ static int clone_bio(struct dm_target_io *tio, struct bio *bio, return r; } - bio_trim(clone, sector - clone->bi_iter.bi_sector, len); + bio_advance(clone, to_bytes(sector - clone->bi_iter.bi_sector)); + clone->bi_iter.bi_size = to_bytes(len); + + if (bio_integrity(bio)) + bio_integrity_trim(clone); return 0; } From f57a98e1b71357713e44c57268a53d9c803f0626 Mon Sep 17 00:00:00 2001 From: Thinh Nguyen Date: Wed, 6 Feb 2019 17:17:27 -0600 Subject: [PATCH 484/525] PCI: Work around Synopsys duplicate Device ID (HAPS USB3, NXP i.MX) There are at least four different parts with the same Vendor and Device ID ([16c3:abcd]): 1) Synopsys HAPS USB3 controller 2) Synopsys PCIe Root Port in Freescale/NXP i.MX6Q (reported by Lucas) 3) Synopsys PCIe Root Port in Freescale/NXP i.MX6QP (reported by Lukas) 4) Synopsys PCIe Root Port in Freescale/NXP i.MX7D (reported by Trent) The HAPS USB3 controller has a Class Code of PCI_CLASS_SERIAL_USB_XHCI, which means the XHCI driver would normally claim it. Previously, quirk_synopsys_haps() changed the Class Code of all [16c3:abcd] devices, including the Root Ports, to PCI_CLASS_SERIAL_USB_DEVICE to prevent the XHCI driver from claiming them so dwc3-haps can claim them instead. Changing the Class Code of the Root Ports prevents the PCI core from handling them as bridges, so devices below them don't work. Restrict the quirk so it only changes the Class Code for devices that start with the PCI_CLASS_SERIAL_USB_XHCI Class Code, leaving the Root Ports alone. Fixes: 03e6742584af ("PCI: Override Synopsys USB 3.x HAPS device class") Reported-by: Lukas F. Hartmann Reported-by: Trent Piepho Reported-by: Lucas Stach Signed-off-by: Thinh Nguyen [bhelgaas: changelog] Signed-off-by: Bjorn Helgaas --- drivers/pci/quirks.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index b0a413f3f7ca..e2a879e93d86 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -639,8 +639,9 @@ static void quirk_synopsys_haps(struct pci_dev *pdev) break; } } -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SYNOPSYS, PCI_ANY_ID, - quirk_synopsys_haps); +DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_VENDOR_ID_SYNOPSYS, PCI_ANY_ID, + PCI_CLASS_SERIAL_USB_XHCI, 0, + quirk_synopsys_haps); /* * Let's make the southbridge information explicit instead of having to From 660492bcf4a7561b5fdc13be0ae0b0c0a8c120be Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Wed, 6 Feb 2019 14:43:42 -0800 Subject: [PATCH 485/525] qed: Fix EQ full firmware assert. When slowpath messages are sent with high rate, the resulting events can lead to a FW assert in case they are not handled fast enough (Event Queue Full assert). Attempt to send queued slowpath messages only after the newly evacuated entries in the EQ ring are indicated to FW. Signed-off-by: Manish Chopra Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_sp.h | 1 + drivers/net/ethernet/qlogic/qed/qed_spq.c | 15 +++++++-------- 2 files changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h index 4179c9013fc6..96ab77ae6af5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h @@ -382,6 +382,7 @@ void qed_consq_setup(struct qed_hwfn *p_hwfn); * @param p_hwfn */ void qed_consq_free(struct qed_hwfn *p_hwfn); +int qed_spq_pend_post(struct qed_hwfn *p_hwfn); /** * @file diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c index eb88bbc6b193..ba64ff9bedbd 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_spq.c +++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c @@ -397,6 +397,11 @@ int qed_eq_completion(struct qed_hwfn *p_hwfn, void *cookie) qed_eq_prod_update(p_hwfn, qed_chain_get_prod_idx(p_chain)); + /* Attempt to post pending requests */ + spin_lock_bh(&p_hwfn->p_spq->lock); + rc = qed_spq_pend_post(p_hwfn); + spin_unlock_bh(&p_hwfn->p_spq->lock); + return rc; } @@ -767,7 +772,7 @@ static int qed_spq_post_list(struct qed_hwfn *p_hwfn, return 0; } -static int qed_spq_pend_post(struct qed_hwfn *p_hwfn) +int qed_spq_pend_post(struct qed_hwfn *p_hwfn) { struct qed_spq *p_spq = p_hwfn->p_spq; struct qed_spq_entry *p_ent = NULL; @@ -905,7 +910,6 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn, struct qed_spq_entry *p_ent = NULL; struct qed_spq_entry *tmp; struct qed_spq_entry *found = NULL; - int rc; if (!p_hwfn) return -EINVAL; @@ -963,12 +967,7 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn, */ qed_spq_return_entry(p_hwfn, found); - /* Attempt to post pending requests */ - spin_lock_bh(&p_spq->lock); - rc = qed_spq_pend_post(p_hwfn); - spin_unlock_bh(&p_spq->lock); - - return rc; + return 0; } int qed_consq_alloc(struct qed_hwfn *p_hwfn) From ebd873a31cae778c2379959ab382b34ba3b73549 Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Wed, 6 Feb 2019 14:43:43 -0800 Subject: [PATCH 486/525] qed: Assign UFP TC value to vlan priority in UFP mode. In the case of Unified Fabric Port (UFP) mode, switch provides the traffic class (TC) value to be used for the traffic. Configure hardware to use this TC value for vlan priority. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_sp_commands.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c index 888274fa208b..5a495fda9e9d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c @@ -604,6 +604,9 @@ int qed_sp_pf_update_stag(struct qed_hwfn *p_hwfn) p_ent->ramrod.pf_update.update_mf_vlan_flag = true; p_ent->ramrod.pf_update.mf_vlan = cpu_to_le16(p_hwfn->hw_info.ovlan); + if (test_bit(QED_MF_UFP_SPECIFIC, &p_hwfn->cdev->mf_bits)) + p_ent->ramrod.pf_update.mf_vlan |= + cpu_to_le16(((u16)p_hwfn->ufp_info.tc << 13)); return qed_spq_post(p_hwfn, p_ent, NULL); } From fb1faab74ddef9ec2d841d54e5d0912a097b3abe Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Wed, 6 Feb 2019 14:43:44 -0800 Subject: [PATCH 487/525] qed: Consider TX tcs while deriving the max num_queues for PF. Max supported queues is derived incorrectly in the case of multi-CoS. Need to consider TCs while calculating num_queues for PF. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_l2.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index e68ca83ae915..64ac95ca4df2 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -2216,7 +2216,7 @@ static int qed_fill_eth_dev_info(struct qed_dev *cdev, u16 num_queues = 0; /* Since the feature controls only queue-zones, - * make sure we have the contexts [rx, tx, xdp] to + * make sure we have the contexts [rx, xdp, tcs] to * match. */ for_each_hwfn(cdev, i) { @@ -2226,7 +2226,8 @@ static int qed_fill_eth_dev_info(struct qed_dev *cdev, u16 cids; cids = hwfn->pf_params.eth_pf_params.num_cons; - num_queues += min_t(u16, l2_queues, cids / 3); + cids /= (2 + info->num_tc); + num_queues += min_t(u16, l2_queues, cids); } /* queues might theoretically be >256, but interrupts' From 0aa4febb420d91df5b56b1864a2465765da85f4b Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Wed, 6 Feb 2019 14:43:45 -0800 Subject: [PATCH 488/525] qede: Fix system crash on configuring channels. Under heavy traffic load, when changing number of channels via ethtool (ethtool -L) which will cause interface to be reloaded, it was observed that some packets gets transmitted on old TX channel/queue id which doesn't really exist after the channel configuration leads to system crash. Add a safeguard in the driver by validating queue id through ndo_select_queue() which is called before the ndo_start_xmit(). Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qede/qede.h | 3 +++ drivers/net/ethernet/qlogic/qede/qede_fp.c | 13 +++++++++++++ drivers/net/ethernet/qlogic/qede/qede_main.c | 3 +++ 3 files changed, 19 insertions(+) diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index 613249d1e967..cd404269de53 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -494,6 +494,9 @@ struct qede_reload_args { /* Datapath functions definition */ netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev); +u16 qede_select_queue(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev, + select_queue_fallback_t fallback); netdev_features_t qede_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features); diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index bdf816fe5a16..31b046e24565 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -1695,6 +1695,19 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev) return NETDEV_TX_OK; } +u16 qede_select_queue(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev, + select_queue_fallback_t fallback) +{ + struct qede_dev *edev = netdev_priv(dev); + int total_txq; + + total_txq = QEDE_TSS_COUNT(edev) * edev->dev_info.num_tc; + + return QEDE_TSS_COUNT(edev) ? + fallback(dev, skb, NULL) % total_txq : 0; +} + /* 8B udp header + 8B base tunnel header + 32B option length */ #define QEDE_MAX_TUN_HDR_LEN 48 diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 5a74fcbdbc2b..9790f26d17c4 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -631,6 +631,7 @@ static const struct net_device_ops qede_netdev_ops = { .ndo_open = qede_open, .ndo_stop = qede_close, .ndo_start_xmit = qede_start_xmit, + .ndo_select_queue = qede_select_queue, .ndo_set_rx_mode = qede_set_rx_mode, .ndo_set_mac_address = qede_set_mac_addr, .ndo_validate_addr = eth_validate_addr, @@ -666,6 +667,7 @@ static const struct net_device_ops qede_netdev_vf_ops = { .ndo_open = qede_open, .ndo_stop = qede_close, .ndo_start_xmit = qede_start_xmit, + .ndo_select_queue = qede_select_queue, .ndo_set_rx_mode = qede_set_rx_mode, .ndo_set_mac_address = qede_set_mac_addr, .ndo_validate_addr = eth_validate_addr, @@ -684,6 +686,7 @@ static const struct net_device_ops qede_netdev_vf_xdp_ops = { .ndo_open = qede_open, .ndo_stop = qede_close, .ndo_start_xmit = qede_start_xmit, + .ndo_select_queue = qede_select_queue, .ndo_set_rx_mode = qede_set_rx_mode, .ndo_set_mac_address = qede_set_mac_addr, .ndo_validate_addr = eth_validate_addr, From 8c8502532f0064d0f04335bfe0f80d9431866a73 Mon Sep 17 00:00:00 2001 From: Rahul Verma Date: Wed, 6 Feb 2019 14:43:46 -0800 Subject: [PATCH 489/525] qed: Change verbosity for coalescing message. Fix unnecessary logging of message in an expected default case where coalescing value read (via ethtool -c) migh not be valid unless they are configured explicitly in the hardware using ethtool -C. Signed-off-by: Rahul Verma Signed-off-by: Manish Chopra Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_l2.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 64ac95ca4df2..58be1c4c6668 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -2871,7 +2871,8 @@ static int qed_get_coalesce(struct qed_dev *cdev, u16 *coal, void *handle) p_hwfn = p_cid->p_owner; rc = qed_get_queue_coalesce(p_hwfn, coal, handle); if (rc) - DP_NOTICE(p_hwfn, "Unable to read queue coalescing\n"); + DP_VERBOSE(cdev, QED_MSG_DEBUG, + "Unable to read queue coalescing\n"); return rc; } From 42dbcd6b25cd6fe8b47cf838f5da8178d1cd926c Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Wed, 6 Feb 2019 14:43:47 -0800 Subject: [PATCH 490/525] qed*: Advance drivers version to 8.37.0.20 Version update for qed/qede modules. Signed-off-by: Manish Chopra Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed.h | 2 +- drivers/net/ethernet/qlogic/qede/qede.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index 24a90163775e..2d8a77cc156b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -53,7 +53,7 @@ extern const struct qed_common_ops qed_common_ops_pass; #define QED_MAJOR_VERSION 8 -#define QED_MINOR_VERSION 33 +#define QED_MINOR_VERSION 37 #define QED_REVISION_VERSION 0 #define QED_ENGINEERING_VERSION 20 diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index cd404269de53..730997b13747 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -56,7 +56,7 @@ #include #define QEDE_MAJOR_VERSION 8 -#define QEDE_MINOR_VERSION 33 +#define QEDE_MINOR_VERSION 37 #define QEDE_REVISION_VERSION 0 #define QEDE_ENGINEERING_VERSION 20 #define DRV_MODULE_VERSION __stringify(QEDE_MAJOR_VERSION) "." \ From 6707f74be8621ae067d2cf1c4485900e2742c20f Mon Sep 17 00:00:00 2001 From: Tonghao Zhang Date: Mon, 28 Jan 2019 15:28:05 -0800 Subject: [PATCH 491/525] net/mlx5e: Update hw flows when encap source mac changed When we offload tc filters to hardware, hardware flows can be updated when mac of encap destination ip is changed. But we ignore one case, that the mac of local encap ip can be changed too, so we should also update them. To fix it, add route_dev in mlx5e_encap_entry struct to save the local encap netdevice, and when mac changed, kernel will flush all the neighbour on the netdevice and send NETEVENT_NEIGH_UPDATE event. The mlx5 driver will delete the flows and add them when neighbour available again. Fixes: 232c001398ae ("net/mlx5e: Add support to neighbour update flow") Cc: Hadar Hen Zion Signed-off-by: Tonghao Zhang Reviewed-by: Or Gerlitz Acked-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c | 2 ++ drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 4 ++++ drivers/net/ethernet/mellanox/mlx5/core/en_rep.h | 1 + 3 files changed, 7 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index a3750af074a4..f3c7ab6faea5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -256,6 +256,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, e->m_neigh.family = n->ops->family; memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len); e->out_dev = out_dev; + e->route_dev = route_dev; /* It's important to add the neigh to the hash table before checking * the neigh validity state. So if we'll get a notification, in case the @@ -369,6 +370,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, e->m_neigh.family = n->ops->family; memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len); e->out_dev = out_dev; + e->route_dev = route_dev; /* It's importent to add the neigh to the hash table before checking * the neigh validity state. So if we'll get a notification, in case the diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index f2573c2d2b5c..ef9e472daffb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -596,6 +596,10 @@ static void mlx5e_rep_update_flows(struct mlx5e_priv *priv, if (neigh_connected && !(e->flags & MLX5_ENCAP_ENTRY_VALID)) { ether_addr_copy(e->h_dest, ha); ether_addr_copy(eth->h_dest, ha); + /* Update the encap source mac, in case that we delete + * the flows when encap source mac changed. + */ + ether_addr_copy(eth->h_source, e->route_dev->dev_addr); mlx5e_tc_encap_flows_add(priv, e); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index edd722824697..36eafc877e6b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -148,6 +148,7 @@ struct mlx5e_encap_entry { unsigned char h_dest[ETH_ALEN]; /* destination eth addr */ struct net_device *out_dev; + struct net_device *route_dev; int tunnel_type; int tunnel_hlen; int reformat_type; From 218d05ce326f9e1b40a56085431fa1068b43d5d9 Mon Sep 17 00:00:00 2001 From: Tonghao Zhang Date: Mon, 28 Jan 2019 15:28:06 -0800 Subject: [PATCH 492/525] net/mlx5e: Don't overwrite pedit action when multiple pedit used In some case, we may use multiple pedit actions to modify packets. The command shown as below: the last pedit action is effective. $ tc filter add dev netdev_rep parent ffff: protocol ip prio 1 \ flower skip_sw ip_proto icmp dst_ip 3.3.3.3 \ action pedit ex munge ip dst set 192.168.1.100 pipe \ action pedit ex munge eth src set 00:00:00:00:00:01 pipe \ action pedit ex munge eth dst set 00:00:00:00:00:02 pipe \ action csum ip pipe \ action tunnel_key set src_ip 1.1.1.100 dst_ip 1.1.1.200 dst_port 4789 id 100 \ action mirred egress redirect dev vxlan0 To fix it, we add max_mod_hdr_actions to mlx5e_tc_flow_parse_attr struction, max_mod_hdr_actions will store the max pedit action number we support and num_mod_hdr_actions indicates how many pedit action we used, and store all pedit action to mod_hdr_actions. Fixes: d79b6df6b10a ("net/mlx5e: Add parsing of TC pedit actions to HW format") Cc: Or Gerlitz Signed-off-by: Tonghao Zhang Reviewed-by: Or Gerlitz Acked-by: Saeed Mahameed Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlx5/core/en_tc.c | 25 +++++++++++-------- 1 file changed, 15 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 1c3c9fa26b55..b5c1b039375a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -128,6 +128,7 @@ struct mlx5e_tc_flow_parse_attr { struct net_device *filter_dev; struct mlx5_flow_spec spec; int num_mod_hdr_actions; + int max_mod_hdr_actions; void *mod_hdr_actions; int mirred_ifindex[MLX5_MAX_FLOW_FWD_VPORTS]; }; @@ -1936,9 +1937,9 @@ static struct mlx5_fields fields[] = { OFFLOAD(UDP_DPORT, 2, udp.dest, 0), }; -/* On input attr->num_mod_hdr_actions tells how many HW actions can be parsed at - * max from the SW pedit action. On success, it says how many HW actions were - * actually parsed. +/* On input attr->max_mod_hdr_actions tells how many HW actions can be parsed at + * max from the SW pedit action. On success, attr->num_mod_hdr_actions + * says how many HW actions were actually parsed. */ static int offload_pedit_fields(struct pedit_headers *masks, struct pedit_headers *vals, @@ -1962,9 +1963,11 @@ static int offload_pedit_fields(struct pedit_headers *masks, add_vals = &vals[TCA_PEDIT_KEY_EX_CMD_ADD]; action_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto); - action = parse_attr->mod_hdr_actions; - max_actions = parse_attr->num_mod_hdr_actions; - nactions = 0; + action = parse_attr->mod_hdr_actions + + parse_attr->num_mod_hdr_actions * action_size; + + max_actions = parse_attr->max_mod_hdr_actions; + nactions = parse_attr->num_mod_hdr_actions; for (i = 0; i < ARRAY_SIZE(fields); i++) { f = &fields[i]; @@ -2075,7 +2078,7 @@ static int alloc_mod_hdr_actions(struct mlx5e_priv *priv, if (!parse_attr->mod_hdr_actions) return -ENOMEM; - parse_attr->num_mod_hdr_actions = max_actions; + parse_attr->max_mod_hdr_actions = max_actions; return 0; } @@ -2121,9 +2124,11 @@ static int parse_tc_pedit_action(struct mlx5e_priv *priv, goto out_err; } - err = alloc_mod_hdr_actions(priv, a, namespace, parse_attr); - if (err) - goto out_err; + if (!parse_attr->mod_hdr_actions) { + err = alloc_mod_hdr_actions(priv, a, namespace, parse_attr); + if (err) + goto out_err; + } err = offload_pedit_fields(masks, vals, parse_attr, extack); if (err < 0) From 3703a395012b509cb2fea50958cdbe4a6a895eed Mon Sep 17 00:00:00 2001 From: Yang Wei Date: Wed, 6 Feb 2019 00:01:04 +0800 Subject: [PATCH 493/525] net: defxx: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles dev_consume_skb_irq() should be called in dfx_xmt_done() when skb xmit done. It makes drop profiles(dropwatch, perf) more friendly. Signed-off-by: Yang Wei Reviewed-by: Maciej W. Rozycki Signed-off-by: David S. Miller --- drivers/net/fddi/defxx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/fddi/defxx.c b/drivers/net/fddi/defxx.c index 38ac8ef41f5f..56b7791911bf 100644 --- a/drivers/net/fddi/defxx.c +++ b/drivers/net/fddi/defxx.c @@ -3512,7 +3512,7 @@ static int dfx_xmt_done(DFX_board_t *bp) bp->descr_block_virt->xmt_data[comp].long_1, p_xmt_drv_descr->p_skb->len, DMA_TO_DEVICE); - dev_kfree_skb_irq(p_xmt_drv_descr->p_skb); + dev_consume_skb_irq(p_xmt_drv_descr->p_skb); /* * Move to start of next packet by updating completion index From 62d1a31cfb5d9291f4dd90c1b0ef5c22f3c235bf Mon Sep 17 00:00:00 2001 From: Yang Wei Date: Wed, 6 Feb 2019 00:03:51 +0800 Subject: [PATCH 494/525] net: tulip: de2104x: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles dev_consume_skb_irq() should be called in de_tx() when skb xmit done. It makes drop profiles(dropwatch, perf) more friendly. Signed-off-by: Yang Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/dec/tulip/de2104x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c index 13430f75496c..f1a2da15dd0a 100644 --- a/drivers/net/ethernet/dec/tulip/de2104x.c +++ b/drivers/net/ethernet/dec/tulip/de2104x.c @@ -585,7 +585,7 @@ static void de_tx (struct de_private *de) netif_dbg(de, tx_done, de->dev, "tx done, slot %d\n", tx_tail); } - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); } next: From 96d26503e1deba5d12e0e4b473336479cc0965af Mon Sep 17 00:00:00 2001 From: Yang Wei Date: Wed, 6 Feb 2019 00:07:03 +0800 Subject: [PATCH 495/525] net: dscc4: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles dev_consume_skb_irq() should be called in dscc4_tx_irq() when skb xmit done. It makes drop profiles(dropwatch, perf) more friendly. Signed-off-by: Yang Wei Signed-off-by: David S. Miller --- drivers/net/wan/dscc4.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wan/dscc4.c b/drivers/net/wan/dscc4.c index c0b0f525c87c..27decf8ae840 100644 --- a/drivers/net/wan/dscc4.c +++ b/drivers/net/wan/dscc4.c @@ -1575,7 +1575,7 @@ try: dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; } - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); dpriv->tx_skbuff[cur] = NULL; ++dpriv->tx_dirty; } else { From bb6a702c6d512b16a7c16a38468a14eda72f44b5 Mon Sep 17 00:00:00 2001 From: Yang Wei Date: Wed, 6 Feb 2019 00:09:41 +0800 Subject: [PATCH 496/525] net: smsc: epic100: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles dev_consume_skb_irq() should be called in epic_tx() when skb xmit done. It makes drop profiles(dropwatch, perf) more friendly. Signed-off-by: Yang Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/smsc/epic100.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c index 15c62c160953..be47d864f8b9 100644 --- a/drivers/net/ethernet/smsc/epic100.c +++ b/drivers/net/ethernet/smsc/epic100.c @@ -1037,7 +1037,7 @@ static void epic_tx(struct net_device *dev, struct epic_private *ep) skb = ep->tx_skbuff[entry]; pci_unmap_single(ep->pci_dev, ep->tx_ring[entry].bufaddr, skb->len, PCI_DMA_TODEVICE); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); ep->tx_skbuff[entry] = NULL; } From c50e964b76903b03a1516a04463c2faf945ec140 Mon Sep 17 00:00:00 2001 From: Yang Wei Date: Wed, 6 Feb 2019 00:12:04 +0800 Subject: [PATCH 497/525] net: fec_mpc52xx: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles dev_consume_skb_irq() should be called in mpc52xx_fec_tx_interrupt() when skb xmit done. It makes drop profiles(dropwatch, perf) more friendly. Signed-off-by: Yang Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fec_mpc52xx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/fec_mpc52xx.c b/drivers/net/ethernet/freescale/fec_mpc52xx.c index b90bab72efdb..c1968b3ecec8 100644 --- a/drivers/net/ethernet/freescale/fec_mpc52xx.c +++ b/drivers/net/ethernet/freescale/fec_mpc52xx.c @@ -369,7 +369,7 @@ static irqreturn_t mpc52xx_fec_tx_interrupt(int irq, void *dev_id) dma_unmap_single(dev->dev.parent, bd->skb_pa, skb->len, DMA_TO_DEVICE); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); } spin_unlock(&priv->lock); From 7c3850adbcccc2c6c9e7ab23a7dcbc4926ee5b96 Mon Sep 17 00:00:00 2001 From: Yang Wei Date: Wed, 6 Feb 2019 00:14:51 +0800 Subject: [PATCH 498/525] net: fsl_ucc_hdlc: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles dev_consume_skb_irq() should be called in hdlc_tx_done() when skb xmit done. It makes drop profiles(dropwatch, perf) more friendly. Signed-off-by: Yang Wei Signed-off-by: David S. Miller --- drivers/net/wan/fsl_ucc_hdlc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c index 66d889d54e58..a08f04c3f644 100644 --- a/drivers/net/wan/fsl_ucc_hdlc.c +++ b/drivers/net/wan/fsl_ucc_hdlc.c @@ -482,7 +482,7 @@ static int hdlc_tx_done(struct ucc_hdlc_private *priv) memset(priv->tx_buffer + (be32_to_cpu(bd->buf) - priv->dma_tx_addr), 0, skb->len); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); priv->tx_skbuff[priv->skb_dirtytx] = NULL; priv->skb_dirtytx = From 98fcd70b642dd843f80c92eeb6f8c07886876999 Mon Sep 17 00:00:00 2001 From: Yang Wei Date: Wed, 6 Feb 2019 00:19:44 +0800 Subject: [PATCH 499/525] net: sun: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles dev_consume_skb_irq() should be called when skb xmit done. It makes drop profiles(dropwatch, perf) more friendly. Signed-off-by: Yang Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/sun/cassini.c | 2 +- drivers/net/ethernet/sun/sunbmac.c | 2 +- drivers/net/ethernet/sun/sunhme.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index 7ec4eb74fe21..6fc05c106afc 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -1898,7 +1898,7 @@ static inline void cas_tx_ringN(struct cas *cp, int ring, int limit) cp->net_stats[ring].tx_packets++; cp->net_stats[ring].tx_bytes += skb->len; spin_unlock(&cp->stat_lock[ring]); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); } cp->tx_old[ring] = entry; diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c index 720b7ac77f3b..e9b757b03b56 100644 --- a/drivers/net/ethernet/sun/sunbmac.c +++ b/drivers/net/ethernet/sun/sunbmac.c @@ -781,7 +781,7 @@ static void bigmac_tx(struct bigmac *bp) DTX(("skb(%p) ", skb)); bp->tx_skbs[elem] = NULL; - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); elem = NEXT_TX(elem); } diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c index ff641cf30a4e..d007dfeba5c3 100644 --- a/drivers/net/ethernet/sun/sunhme.c +++ b/drivers/net/ethernet/sun/sunhme.c @@ -1962,7 +1962,7 @@ static void happy_meal_tx(struct happy_meal *hp) this = &txbase[elem]; } - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); dev->stats.tx_packets++; } hp->tx_old = elem; From f4ad1a6154e305dbcde20395a6961658d1ce032b Mon Sep 17 00:00:00 2001 From: Yang Wei Date: Wed, 6 Feb 2019 00:21:31 +0800 Subject: [PATCH 500/525] net: tehuti: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles dev_consume_skb_irq() should be called in bdx_tx_cleanup() when skb xmit done. It makes drop profiles(dropwatch, perf) more friendly. Signed-off-by: Yang Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/tehuti/tehuti.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c index dc966ddb6d81..b24c11187017 100644 --- a/drivers/net/ethernet/tehuti/tehuti.c +++ b/drivers/net/ethernet/tehuti/tehuti.c @@ -1739,7 +1739,7 @@ static void bdx_tx_cleanup(struct bdx_priv *priv) tx_level -= db->rptr->len; /* '-' koz len is negative */ /* now should come skb pointer - free it */ - dev_kfree_skb_irq(db->rptr->addr.skb); + dev_consume_skb_irq(db->rptr->addr.skb); bdx_tx_db_inc_rptr(db); } From e0cbbc613175e1c67bd82721230692047923d845 Mon Sep 17 00:00:00 2001 From: Yang Wei Date: Wed, 6 Feb 2019 00:22:54 +0800 Subject: [PATCH 501/525] net: via-velocity: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles dev_consume_skb_irq() should be called in velocity_free_tx_buf() when skb xmit done. It makes drop profiles(dropwatch, perf) more friendly. Signed-off-by: Yang Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/via/via-velocity.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c index 82412691ee66..27f6cf140845 100644 --- a/drivers/net/ethernet/via/via-velocity.c +++ b/drivers/net/ethernet/via/via-velocity.c @@ -1740,7 +1740,7 @@ static void velocity_free_tx_buf(struct velocity_info *vptr, dma_unmap_single(vptr->dev, tdinfo->skb_dma[i], le16_to_cpu(pktlen), DMA_TO_DEVICE); } - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); tdinfo->skb = NULL; } From d2901b0739a42a5669ae33356206591a6bd3a64c Mon Sep 17 00:00:00 2001 From: Yang Wei Date: Wed, 6 Feb 2019 00:25:54 +0800 Subject: [PATCH 502/525] net: broadcom: replace dev_kfree_skb_irq by dev_consume_skb_irq for drop profiles dev_consume_skb_irq() should be called in sbdma_tx_process() when skb xmit done. It makes drop profiles(dropwatch, perf) more friendly. Signed-off-by: Yang Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/sb1250-mac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/sb1250-mac.c b/drivers/net/ethernet/broadcom/sb1250-mac.c index 5db9f4158e62..134ae2862efa 100644 --- a/drivers/net/ethernet/broadcom/sb1250-mac.c +++ b/drivers/net/ethernet/broadcom/sb1250-mac.c @@ -1288,7 +1288,7 @@ static void sbdma_tx_process(struct sbmac_softc *sc, struct sbmacdma *d, * for transmits, we just free buffers. */ - dev_kfree_skb_irq(sb); + dev_consume_skb_irq(sb); /* * .. and advance to the next buffer. From e8c32c32b48c2e889704d8ca0872f92eb027838e Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 5 Feb 2019 14:47:21 -0600 Subject: [PATCH 503/525] net: Don't default Cavium PTP driver to 'y' 8c56df372bc1 ("net: add support for Cavium PTP coprocessor") added the Cavium PTP coprocessor driver and enabled it by default. Remove the "default y" because the driver only applies to Cavium ThunderX processors. Fixes: 8c56df372bc1 ("net: add support for Cavium PTP coprocessor") Signed-off-by: Bjorn Helgaas Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/Kconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig index 5f03199a3acf..05f4a3b21e29 100644 --- a/drivers/net/ethernet/cavium/Kconfig +++ b/drivers/net/ethernet/cavium/Kconfig @@ -54,7 +54,6 @@ config CAVIUM_PTP tristate "Cavium PTP coprocessor as PTP clock" depends on 64BIT && PCI imply PTP_1588_CLOCK - default y ---help--- This driver adds support for the Precision Time Protocol Clocks and Timestamping coprocessor (PTP) found on Cavium processors. From ce5cbf53496bfebe1b7478a532820373342e8302 Mon Sep 17 00:00:00 2001 From: Erik Schmauss Date: Tue, 5 Feb 2019 16:14:00 -0800 Subject: [PATCH 504/525] ACPI: Set debug output flags independent of ACPICA There was a divergence between Linux and ACPICA on the definition of ACPI_DEBUG_DEFAULT. This divergence was solved by taking ACPICA's definition in 4c1379d7bb42. After resolving the divergence, it was clear that Linux users wanted to use their old set of debug flags. This change fixes the divergence by setting these debug flags during acpi_early_init() rather than during global variable initialization in acpixf.h (owned by ACPICA). Fixes: 4c1379d7bb42 ("ACPICA: Debug output: Add option to display method/object evaluation") Reported-by: Michael J Ruhl Reported-by: Alex Gagniuc Signed-off-by: Erik Schmauss Signed-off-by: Rafael J. Wysocki --- drivers/acpi/bus.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 5c093ce01bcd..147f6c7ea59c 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -1029,6 +1029,9 @@ void __init acpi_early_init(void) acpi_permanent_mmap = true; + /* Initialize debug output. Linux does not use ACPICA defaults */ + acpi_dbg_level = ACPI_LV_INFO | ACPI_LV_REPAIR; + #ifdef CONFIG_X86 /* * If the machine falls into the DMI check table, From 35634ffa1751b6efd8cf75010b509dcb0263e29b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 6 Feb 2019 18:39:40 -0600 Subject: [PATCH 505/525] signal: Always notice exiting tasks Recently syzkaller was able to create unkillablle processes by creating a timer that is delivered as a thread local signal on SIGHUP, and receiving SIGHUP SA_NODEFERER. Ultimately causing a loop failing to deliver SIGHUP but always trying. Upon examination it turns out part of the problem is actually most of the solution. Since 2.5 signal delivery has found all fatal signals, marked the signal group for death, and queued SIGKILL in every threads thread queue relying on signal->group_exit_code to preserve the information of which was the actual fatal signal. The conversion of all fatal signals to SIGKILL results in the synchronous signal heuristic in next_signal kicking in and preferring SIGHUP to SIGKILL. Which is especially problematic as all fatal signals have already been transformed into SIGKILL. Instead of dequeueing signals and depending upon SIGKILL to be the first signal dequeued, first test if the signal group has already been marked for death. This guarantees that nothing in the signal queue can prevent a process that needs to exit from exiting. Cc: stable@vger.kernel.org Tested-by: Dmitry Vyukov Reported-by: Dmitry Vyukov Ref: ebf5ebe31d2c ("[PATCH] signal-fixes-2.5.59-A4") History Tree: https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git Signed-off-by: "Eric W. Biederman" --- kernel/signal.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/kernel/signal.c b/kernel/signal.c index 9ca8e5278c8e..5424cb0006bc 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2393,6 +2393,11 @@ relock: goto relock; } + /* Has this task already been marked for death? */ + ksig->info.si_signo = signr = SIGKILL; + if (signal_group_exit(signal)) + goto fatal; + for (;;) { struct k_sigaction *ka; @@ -2488,6 +2493,7 @@ relock: continue; } + fatal: spin_unlock_irq(&sighand->siglock); /* From 7146db3317c67b517258cb5e1b08af387da0618b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 6 Feb 2019 17:51:47 -0600 Subject: [PATCH 506/525] signal: Better detection of synchronous signals Recently syzkaller was able to create unkillablle processes by creating a timer that is delivered as a thread local signal on SIGHUP, and receiving SIGHUP SA_NODEFERER. Ultimately causing a loop failing to deliver SIGHUP but always trying. When the stack overflows delivery of SIGHUP fails and force_sigsegv is called. Unfortunately because SIGSEGV is numerically higher than SIGHUP next_signal tries again to deliver a SIGHUP. From a quality of implementation standpoint attempting to deliver the timer SIGHUP signal is wrong. We should attempt to deliver the synchronous SIGSEGV signal we just forced. We can make that happening in a fairly straight forward manner by instead of just looking at the signal number we also look at the si_code. In particular for exceptions (aka synchronous signals) the si_code is always greater than 0. That still has the potential to pick up a number of asynchronous signals as in a few cases the same si_codes that are used for synchronous signals are also used for asynchronous signals, and SI_KERNEL is also included in the list of possible si_codes. Still the heuristic is much better and timer signals are definitely excluded. Which is enough to prevent all known ways for someone sending a process signals fast enough to cause unexpected and arguably incorrect behavior. Cc: stable@vger.kernel.org Fixes: a27341cd5fcb ("Prioritize synchronous signals over 'normal' signals") Tested-by: Dmitry Vyukov Reported-by: Dmitry Vyukov Signed-off-by: "Eric W. Biederman" --- kernel/signal.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 51 insertions(+), 1 deletion(-) diff --git a/kernel/signal.c b/kernel/signal.c index 5424cb0006bc..99fa8ff06fd9 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -688,6 +688,48 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, kernel_siginfo_t *in } EXPORT_SYMBOL_GPL(dequeue_signal); +static int dequeue_synchronous_signal(kernel_siginfo_t *info) +{ + struct task_struct *tsk = current; + struct sigpending *pending = &tsk->pending; + struct sigqueue *q, *sync = NULL; + + /* + * Might a synchronous signal be in the queue? + */ + if (!((pending->signal.sig[0] & ~tsk->blocked.sig[0]) & SYNCHRONOUS_MASK)) + return 0; + + /* + * Return the first synchronous signal in the queue. + */ + list_for_each_entry(q, &pending->list, list) { + /* Synchronous signals have a postive si_code */ + if ((q->info.si_code > SI_USER) && + (sigmask(q->info.si_signo) & SYNCHRONOUS_MASK)) { + sync = q; + goto next; + } + } + return 0; +next: + /* + * Check if there is another siginfo for the same signal. + */ + list_for_each_entry_continue(q, &pending->list, list) { + if (q->info.si_signo == sync->info.si_signo) + goto still_pending; + } + + sigdelset(&pending->signal, sync->info.si_signo); + recalc_sigpending(); +still_pending: + list_del_init(&sync->list); + copy_siginfo(info, &sync->info); + __sigqueue_free(sync); + return info->si_signo; +} + /* * Tell a process that it has a new active signal.. * @@ -2411,7 +2453,15 @@ relock: goto relock; } - signr = dequeue_signal(current, ¤t->blocked, &ksig->info); + /* + * Signals generated by the execution of an instruction + * need to be delivered before any other pending signals + * so that the instruction pointer in the signal stack + * frame points to the faulting instruction. + */ + signr = dequeue_synchronous_signal(&ksig->info); + if (!signr) + signr = dequeue_signal(current, ¤t->blocked, &ksig->info); if (!signr) break; /* will return 0 */ From cfa39381173d5f969daf43582c95ad679189cbc9 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Sat, 26 Jan 2019 01:54:33 +0100 Subject: [PATCH 507/525] kvm: fix kvm_ioctl_create_device() reference counting (CVE-2019-6974) kvm_ioctl_create_device() does the following: 1. creates a device that holds a reference to the VM object (with a borrowed reference, the VM's refcount has not been bumped yet) 2. initializes the device 3. transfers the reference to the device to the caller's file descriptor table 4. calls kvm_get_kvm() to turn the borrowed reference to the VM into a real reference The ownership transfer in step 3 must not happen before the reference to the VM becomes a proper, non-borrowed reference, which only happens in step 4. After step 3, an attacker can close the file descriptor and drop the borrowed reference, which can cause the refcount of the kvm object to drop to zero. This means that we need to grab a reference for the device before anon_inode_getfd(), otherwise the VM can disappear from under us. Fixes: 852b6d57dc7f ("kvm: add device control API") Cc: stable@kernel.org Signed-off-by: Jann Horn Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 5ecea812cb6a..585845203db8 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3000,8 +3000,10 @@ static int kvm_ioctl_create_device(struct kvm *kvm, if (ops->init) ops->init(dev); + kvm_get_kvm(kvm); ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC); if (ret < 0) { + kvm_put_kvm(kvm); mutex_lock(&kvm->lock); list_del(&dev->vm_node); mutex_unlock(&kvm->lock); @@ -3009,7 +3011,6 @@ static int kvm_ioctl_create_device(struct kvm *kvm, return ret; } - kvm_get_kvm(kvm); cd->fd = ret; return 0; } From 353c0956a618a07ba4bbe7ad00ff29fe70e8412a Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 29 Jan 2019 18:41:16 +0100 Subject: [PATCH 508/525] KVM: x86: work around leak of uninitialized stack contents (CVE-2019-7222) Bugzilla: 1671930 Emulation of certain instructions (VMXON, VMCLEAR, VMPTRLD, VMWRITE with memory operand, INVEPT, INVVPID) can incorrectly inject a page fault when passed an operand that points to an MMIO address. The page fault will use uninitialized kernel stack memory as the CR2 and error code. The right behavior would be to abort the VM with a KVM_EXIT_INTERNAL_ERROR exit to userspace; however, it is not an easy fix, so for now just ensure that the error code and CR2 are zero. Embargoed until Feb 7th 2019. Reported-by: Felix Wilhelm Cc: stable@kernel.org Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3d27206f6c01..e67ecf25e690 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5116,6 +5116,13 @@ int kvm_read_guest_virt(struct kvm_vcpu *vcpu, { u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + /* + * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED + * is returned, but our callers are not ready for that and they blindly + * call kvm_inject_page_fault. Ensure that they at least do not leak + * uninitialized kernel stack memory into cr2 and error code. + */ + memset(exception, 0, sizeof(*exception)); return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception); } From ecec76885bcfe3294685dc363fd1273df0d5d65f Mon Sep 17 00:00:00 2001 From: Peter Shier Date: Thu, 11 Oct 2018 11:46:46 -0700 Subject: [PATCH 509/525] KVM: nVMX: unconditionally cancel preemption timer in free_nested (CVE-2019-7221) Bugzilla: 1671904 There are multiple code paths where an hrtimer may have been started to emulate an L1 VMX preemption timer that can result in a call to free_nested without an intervening L2 exit where the hrtimer is normally cancelled. Unconditionally cancel in free_nested to cover all cases. Embargoed until Feb 7th 2019. Signed-off-by: Peter Shier Reported-by: Jim Mattson Reviewed-by: Jim Mattson Reported-by: Felix Wilhelm Cc: stable@kernel.org Message-Id: <20181011184646.154065-1-pshier@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/nested.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 8ff20523661b..d8ea4ebd79e7 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -211,6 +211,7 @@ static void free_nested(struct kvm_vcpu *vcpu) if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon) return; + hrtimer_cancel(&vmx->nested.preemption_timer); vmx->nested.vmxon = false; vmx->nested.smm.vmxon = false; free_vpid(vmx->nested.vpid02); From c0a47e44c0980b3b23ee31fa7936d70ea5dce491 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Thu, 7 Feb 2019 18:36:10 +0800 Subject: [PATCH 510/525] geneve: should not call rt6_lookup() when ipv6 was disabled When we add a new GENEVE device with IPv6 remote, checking only for IS_ENABLED(CONFIG_IPV6) is not enough as we may disable IPv6 in the kernel command line (ipv6.disable=1), and calling rt6_lookup() would cause a NULL pointer dereference. v2: - don't mix declarations and code (reported by Stefano Brivio, Eric Dumazet) - there's no need to use in6_dev_get() as we only need to check that idev exists (reported by David Ahern). This is under RTNL, so we can simply use __in6_dev_get() instead (Stefano, Eric). Reported-by: Jianlin Shi Fixes: c40e89fd358e9 ("geneve: configure MTU based on a lower device") Cc: Alexey Kodanev Signed-off-by: Hangbin Liu Reviewed-by: Stefano Brivio Signed-off-by: David S. Miller --- drivers/net/geneve.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 58bbba8582b0..3377ac66a347 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1512,9 +1512,13 @@ static void geneve_link_config(struct net_device *dev, } #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: { - struct rt6_info *rt = rt6_lookup(geneve->net, - &info->key.u.ipv6.dst, NULL, 0, - NULL, 0); + struct rt6_info *rt; + + if (!__in6_dev_get(dev)) + break; + + rt = rt6_lookup(geneve->net, &info->key.u.ipv6.dst, NULL, 0, + NULL, 0); if (rt && rt->dst.dev) ldev_mtu = rt->dst.dev->mtu - GENEVE_IPV6_HLEN; From 173656accaf583698bac3f9e269884ba60d51ef4 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Thu, 7 Feb 2019 18:36:11 +0800 Subject: [PATCH 511/525] sit: check if IPv6 enabled before calling ip6_err_gen_icmpv6_unreach() If we disabled IPv6 from the kernel command line (ipv6.disable=1), we should not call ip6_err_gen_icmpv6_unreach(). This: ip link add sit1 type sit local 192.0.2.1 remote 192.0.2.2 ttl 1 ip link set sit1 up ip addr add 198.51.100.1/24 dev sit1 ping 198.51.100.2 if IPv6 is disabled at boot time, will crash the kernel. v2: there's no need to use in6_dev_get(), use __in6_dev_get() instead, as we only need to check that idev exists and we are under rcu_read_lock() (from netif_receive_skb_internal()). Reported-by: Jianlin Shi Fixes: ca15a078bd90 ("sit: generate icmpv6 error when receiving icmpv4 error") Cc: Oussama Ghorbel Signed-off-by: Hangbin Liu Reviewed-by: Stefano Brivio Signed-off-by: David S. Miller --- net/ipv6/sit.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 1e03305c0549..e8a1dabef803 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -546,7 +546,8 @@ static int ipip6_err(struct sk_buff *skb, u32 info) } err = 0; - if (!ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len)) + if (__in6_dev_get(skb->dev) && + !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len)) goto out; if (t->parms.iph.daddr == 0) From 8a96669d77897ff3613157bf43f875739205d66d Mon Sep 17 00:00:00 2001 From: Yifeng Li Date: Wed, 6 Feb 2019 15:07:21 +0800 Subject: [PATCH 512/525] mips: loongson64: remove unreachable(), fix loongson_poweroff(). On my Yeeloong 8089, I noticed the machine fails to shutdown properly, and often, the function mach_prepare_reboot() is unexpectedly executed, thus the machine reboots instead. A wait loop is needed to ensure the system is in a well-defined state before going down. In commit 997e93d4df16 ("MIPS: Hang more efficiently on halt/powerdown/restart"), a general superset of the wait loop for all platforms is already provided, so we don't need to implement our own. This commit simply removes the unreachable() compiler marco after mach_prepare_reboot(), thus allowing the execution of machine_hang(). My test shows that the machine is now able to shutdown successfully. Please note that there are two different bugs preventing the machine from shutting down, another work-in-progress commit is needed to fix a lockup in cpufreq / i8259 driver, please read Reference, this commit does not fix that bug. Reference: https://lkml.org/lkml/2019/2/5/908 Signed-off-by: Yifeng Li Signed-off-by: Paul Burton Cc: linux-mips@vger.kernel.org Cc: Huacai Chen Cc: Ralf Baechle Cc: James Hogan Cc: linux-kernel@vger.kernel.org Cc: Aaro Koskinen Cc: stable@vger.kernel.org # v4.17+ --- arch/mips/loongson64/common/reset.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/mips/loongson64/common/reset.c b/arch/mips/loongson64/common/reset.c index a60715e11306..b26892ce871c 100644 --- a/arch/mips/loongson64/common/reset.c +++ b/arch/mips/loongson64/common/reset.c @@ -59,7 +59,12 @@ static void loongson_poweroff(void) { #ifndef CONFIG_LEFI_FIRMWARE_INTERFACE mach_prepare_shutdown(); - unreachable(); + + /* + * It needs a wait loop here, but mips/kernel/reset.c already calls + * a generic delay loop, machine_hang(), so simply return. + */ + return; #else void (*fw_poweroff)(void) = (void *)loongson_sysconf.poweroff_addr; From 05dc6001af0630e200ad5ea08707187fe5537e6d Mon Sep 17 00:00:00 2001 From: Vladimir Kondratiev Date: Wed, 6 Feb 2019 13:46:17 +0200 Subject: [PATCH 513/525] mips: cm: reprime error cause Accordingly to the documentation ---cut--- The GCR_ERROR_CAUSE.ERR_TYPE field and the GCR_ERROR_MULT.ERR_TYPE fields can be cleared by either a reset or by writing the current value of GCR_ERROR_CAUSE.ERR_TYPE to the GCR_ERROR_CAUSE.ERR_TYPE register. ---cut--- Do exactly this. Original value of cm_error may be safely written back; it clears error cause and keeps other bits untouched. Fixes: 3885c2b463f6 ("MIPS: CM: Add support for reporting CM cache errors") Signed-off-by: Vladimir Kondratiev Signed-off-by: Paul Burton Cc: Ralf Baechle Cc: James Hogan Cc: linux-mips@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v4.3+ --- arch/mips/kernel/mips-cm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c index 8f5bd04f320a..7f3f136572de 100644 --- a/arch/mips/kernel/mips-cm.c +++ b/arch/mips/kernel/mips-cm.c @@ -457,5 +457,5 @@ void mips_cm_error_report(void) } /* reprime cause register */ - write_gcr_error_cause(0); + write_gcr_error_cause(cm_error); } From 0803de78049fe1b0baf44bcddc727b036fb9139b Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 7 Feb 2019 11:55:39 +0100 Subject: [PATCH 514/525] blktrace: Show requests without sector Currently, blktrace will not show requests that don't have any data as rq->__sector is initialized to -1 which is out of device range and thus discarded by act_log_check(). This is most notably the case for cache flush requests sent to the device. Fix the problem by making blk_rq_trace_sector() return 0 for requests without initialized sector. Reviewed-by: Johannes Thumshirn Signed-off-by: Jan Kara Signed-off-by: Jens Axboe --- include/linux/blktrace_api.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 8804753805ac..7bb2d8de9f30 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -116,7 +116,13 @@ extern void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes); static inline sector_t blk_rq_trace_sector(struct request *rq) { - return blk_rq_is_passthrough(rq) ? 0 : blk_rq_pos(rq); + /* + * Tracing should ignore starting sector for passthrough requests and + * requests where starting sector didn't get set. + */ + if (blk_rq_is_passthrough(rq) || blk_rq_pos(rq) == (sector_t)-1) + return 0; + return blk_rq_pos(rq); } static inline unsigned int blk_rq_trace_nr_sectors(struct request *rq) From 39841cc1cbb69344539c98a1fa9d858ed124c7ba Mon Sep 17 00:00:00 2001 From: Arun Parameswaran Date: Thu, 7 Feb 2019 16:01:18 -0800 Subject: [PATCH 515/525] net: dsa: b53: Fix for failure when irq is not defined in dt Fixes the issues with non BCM58XX chips in the b53 driver failing, when the irq is not specified in the device tree. Removed the check for BCM58XX in b53_srab_prepare_irq(), so the 'port->irq' will be set to '-EXIO' if the irq is not specified in the device tree. Fixes: 16994374a6fc ("net: dsa: b53: Make SRAB driver manage port interrupts") Fixes: b2ddc48a81b5 ("net: dsa: b53: Do not fail when IRQ are not initialized") Signed-off-by: Arun Parameswaran Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/dsa/b53/b53_srab.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/net/dsa/b53/b53_srab.c b/drivers/net/dsa/b53/b53_srab.c index 90f514252987..d9c56a779c08 100644 --- a/drivers/net/dsa/b53/b53_srab.c +++ b/drivers/net/dsa/b53/b53_srab.c @@ -511,9 +511,6 @@ static void b53_srab_prepare_irq(struct platform_device *pdev) /* Clear all pending interrupts */ writel(0xffffffff, priv->regs + B53_SRAB_INTR); - if (dev->pdata && dev->pdata->chip_id != BCM58XX_DEVICE_ID) - return; - for (i = 0; i < B53_N_PORTS; i++) { port = &priv->port_intrs[i]; From 6f568ebe2afefdc33a6fb06ef20a94f8b96455f1 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Wed, 6 Feb 2019 10:56:02 -0800 Subject: [PATCH 516/525] futex: Fix barrier comment The current comment for the barrier that guarantees that waiter increment is always before taking the hb spinlock (barrier (A)) needs to be fixed as it is misplaced. This is obviously referring to hb_waiters_inc, which is a full barrier. Reported-by: Peter Zijlstra Signed-off-by: Davidlohr Bueso Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20190206185602.949-1-dave@stgolabs.net --- kernel/futex.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/futex.c b/kernel/futex.c index fdd312da0992..5ec2473a3497 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -2221,11 +2221,11 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q) * decrement the counter at queue_unlock() when some error has * occurred and we don't end up adding the task to the list. */ - hb_waiters_inc(hb); + hb_waiters_inc(hb); /* implies smp_mb(); (A) */ q->lock_ptr = &hb->lock; - spin_lock(&hb->lock); /* implies smp_mb(); (A) */ + spin_lock(&hb->lock); return hb; } From 1a1fb985f2e2b85ec0d3dc2e519ee48389ec2434 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 29 Jan 2019 23:15:12 +0100 Subject: [PATCH 517/525] futex: Handle early deadlock return correctly commit 56222b212e8e ("futex: Drop hb->lock before enqueueing on the rtmutex") changed the locking rules in the futex code so that the hash bucket lock is not longer held while the waiter is enqueued into the rtmutex wait list. This made the lock and the unlock path symmetric, but unfortunately the possible early exit from __rt_mutex_proxy_start() due to a detected deadlock was not updated accordingly. That allows a concurrent unlocker to observe inconsitent state which triggers the warning in the unlock path. futex_lock_pi() futex_unlock_pi() lock(hb->lock) queue(hb_waiter) lock(hb->lock) lock(rtmutex->wait_lock) unlock(hb->lock) // acquired hb->lock hb_waiter = futex_top_waiter() lock(rtmutex->wait_lock) __rt_mutex_proxy_start() ---> fail remove(rtmutex_waiter); ---> returns -EDEADLOCK unlock(rtmutex->wait_lock) // acquired wait_lock wake_futex_pi() rt_mutex_next_owner() --> returns NULL --> WARN lock(hb->lock) unqueue(hb_waiter) The problem is caused by the remove(rtmutex_waiter) in the failure case of __rt_mutex_proxy_start() as this lets the unlocker observe a waiter in the hash bucket but no waiter on the rtmutex, i.e. inconsistent state. The original commit handles this correctly for the other early return cases (timeout, signal) by delaying the removal of the rtmutex waiter until the returning task reacquired the hash bucket lock. Treat the failure case of __rt_mutex_proxy_start() in the same way and let the existing cleanup code handle the eventual handover of the rtmutex gracefully. The regular rt_mutex_proxy_start() gains the rtmutex waiter removal for the failure case, so that the other callsites are still operating correctly. Add proper comments to the code so all these details are fully documented. Thanks to Peter for helping with the analysis and writing the really valuable code comments. Fixes: 56222b212e8e ("futex: Drop hb->lock before enqueueing on the rtmutex") Reported-by: Heiko Carstens Co-developed-by: Peter Zijlstra Signed-off-by: Peter Zijlstra Signed-off-by: Thomas Gleixner Tested-by: Heiko Carstens Cc: Martin Schwidefsky Cc: linux-s390@vger.kernel.org Cc: Stefan Liebler Cc: Sebastian Sewior Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1901292311410.1950@nanos.tec.linutronix.de --- kernel/futex.c | 28 ++++++++++++++++++---------- kernel/locking/rtmutex.c | 37 ++++++++++++++++++++++++++++++++----- 2 files changed, 50 insertions(+), 15 deletions(-) diff --git a/kernel/futex.c b/kernel/futex.c index 5ec2473a3497..a0514e01c3eb 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -2861,35 +2861,39 @@ retry_private: * and BUG when futex_unlock_pi() interleaves with this. * * Therefore acquire wait_lock while holding hb->lock, but drop the - * latter before calling rt_mutex_start_proxy_lock(). This still fully - * serializes against futex_unlock_pi() as that does the exact same - * lock handoff sequence. + * latter before calling __rt_mutex_start_proxy_lock(). This + * interleaves with futex_unlock_pi() -- which does a similar lock + * handoff -- such that the latter can observe the futex_q::pi_state + * before __rt_mutex_start_proxy_lock() is done. */ raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock); spin_unlock(q.lock_ptr); + /* + * __rt_mutex_start_proxy_lock() unconditionally enqueues the @rt_waiter + * such that futex_unlock_pi() is guaranteed to observe the waiter when + * it sees the futex_q::pi_state. + */ ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current); raw_spin_unlock_irq(&q.pi_state->pi_mutex.wait_lock); if (ret) { if (ret == 1) ret = 0; - - spin_lock(q.lock_ptr); - goto no_block; + goto cleanup; } - if (unlikely(to)) hrtimer_start_expires(&to->timer, HRTIMER_MODE_ABS); ret = rt_mutex_wait_proxy_lock(&q.pi_state->pi_mutex, to, &rt_waiter); +cleanup: spin_lock(q.lock_ptr); /* - * If we failed to acquire the lock (signal/timeout), we must + * If we failed to acquire the lock (deadlock/signal/timeout), we must * first acquire the hb->lock before removing the lock from the - * rt_mutex waitqueue, such that we can keep the hb and rt_mutex - * wait lists consistent. + * rt_mutex waitqueue, such that we can keep the hb and rt_mutex wait + * lists consistent. * * In particular; it is important that futex_unlock_pi() can not * observe this inconsistency. @@ -3013,6 +3017,10 @@ retry: * there is no point where we hold neither; and therefore * wake_futex_pi() must observe a state consistent with what we * observed. + * + * In particular; this forces __rt_mutex_start_proxy() to + * complete such that we're guaranteed to observe the + * rt_waiter. Also see the WARN in wake_futex_pi(). */ raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 581edcc63c26..978d63a8261c 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1726,12 +1726,33 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock, rt_mutex_set_owner(lock, NULL); } +/** + * __rt_mutex_start_proxy_lock() - Start lock acquisition for another task + * @lock: the rt_mutex to take + * @waiter: the pre-initialized rt_mutex_waiter + * @task: the task to prepare + * + * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock + * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that. + * + * NOTE: does _NOT_ remove the @waiter on failure; must either call + * rt_mutex_wait_proxy_lock() or rt_mutex_cleanup_proxy_lock() after this. + * + * Returns: + * 0 - task blocked on lock + * 1 - acquired the lock for task, caller should wake it up + * <0 - error + * + * Special API call for PI-futex support. + */ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, struct task_struct *task) { int ret; + lockdep_assert_held(&lock->wait_lock); + if (try_to_take_rt_mutex(lock, task, NULL)) return 1; @@ -1749,9 +1770,6 @@ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, ret = 0; } - if (unlikely(ret)) - remove_waiter(lock, waiter); - debug_rt_mutex_print_deadlock(waiter); return ret; @@ -1763,12 +1781,18 @@ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, * @waiter: the pre-initialized rt_mutex_waiter * @task: the task to prepare * + * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock + * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that. + * + * NOTE: unlike __rt_mutex_start_proxy_lock this _DOES_ remove the @waiter + * on failure. + * * Returns: * 0 - task blocked on lock * 1 - acquired the lock for task, caller should wake it up * <0 - error * - * Special API call for FUTEX_REQUEUE_PI support. + * Special API call for PI-futex support. */ int rt_mutex_start_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, @@ -1778,6 +1802,8 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock, raw_spin_lock_irq(&lock->wait_lock); ret = __rt_mutex_start_proxy_lock(lock, waiter, task); + if (unlikely(ret)) + remove_waiter(lock, waiter); raw_spin_unlock_irq(&lock->wait_lock); return ret; @@ -1845,7 +1871,8 @@ int rt_mutex_wait_proxy_lock(struct rt_mutex *lock, * @lock: the rt_mutex we were woken on * @waiter: the pre-initialized rt_mutex_waiter * - * Attempt to clean up after a failed rt_mutex_wait_proxy_lock(). + * Attempt to clean up after a failed __rt_mutex_start_proxy_lock() or + * rt_mutex_wait_proxy_lock(). * * Unless we acquired the lock; we're still enqueued on the wait-list and can * in fact still be granted ownership until we're removed. Therefore we can From 0521e8be211cd20d547bff9da2534b7ed6f2c1b9 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 8 Feb 2019 13:08:59 +0100 Subject: [PATCH 518/525] x86/mm/cpa: Fix set_mce_nospec() The recent commit fe0937b24ff5 ("x86/mm/cpa: Fold cpa_flush_range() and cpa_flush_array() into a single cpa_flush() function") accidentally made the call to make_addr_canonical_again() go away, which breaks set_mce_nospec(). Re-instate the call to convert the address back into canonical form right before invoking either CLFLUSH or INVLPG. Rename the function while at it to be shorter (and less MAGA). Fixes: fe0937b24ff5 ("x86/mm/cpa: Fold cpa_flush_range() and cpa_flush_array() into a single cpa_flush() function") Reported-by: Tony Luck Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Tested-by: Tony Luck Cc: Linus Torvalds Cc: Dan Williams Cc: Dave Hansen Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Rik van Riel Link: https://lkml.kernel.org/r/20190208120859.GH32511@hirez.programming.kicks-ass.net --- arch/x86/mm/pageattr.c | 50 +++++++++++++++++++++--------------------- 1 file changed, 25 insertions(+), 25 deletions(-) diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 4f8972311a77..14e6119838a6 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -230,6 +230,29 @@ static bool __cpa_pfn_in_highmap(unsigned long pfn) #endif +/* + * See set_mce_nospec(). + * + * Machine check recovery code needs to change cache mode of poisoned pages to + * UC to avoid speculative access logging another error. But passing the + * address of the 1:1 mapping to set_memory_uc() is a fine way to encourage a + * speculative access. So we cheat and flip the top bit of the address. This + * works fine for the code that updates the page tables. But at the end of the + * process we need to flush the TLB and cache and the non-canonical address + * causes a #GP fault when used by the INVLPG and CLFLUSH instructions. + * + * But in the common case we already have a canonical address. This code + * will fix the top bit if needed and is a no-op otherwise. + */ +static inline unsigned long fix_addr(unsigned long addr) +{ +#ifdef CONFIG_X86_64 + return (long)(addr << 1) >> 1; +#else + return addr; +#endif +} + static unsigned long __cpa_addr(struct cpa_data *cpa, unsigned long idx) { if (cpa->flags & CPA_PAGES_ARRAY) { @@ -313,7 +336,7 @@ void __cpa_flush_tlb(void *data) unsigned int i; for (i = 0; i < cpa->numpages; i++) - __flush_tlb_one_kernel(__cpa_addr(cpa, i)); + __flush_tlb_one_kernel(fix_addr(__cpa_addr(cpa, i))); } static void cpa_flush(struct cpa_data *data, int cache) @@ -347,7 +370,7 @@ static void cpa_flush(struct cpa_data *data, int cache) * Only flush present addresses: */ if (pte && (pte_val(*pte) & _PAGE_PRESENT)) - clflush_cache_range_opt((void *)addr, PAGE_SIZE); + clflush_cache_range_opt((void *)fix_addr(addr), PAGE_SIZE); } mb(); } @@ -1627,29 +1650,6 @@ out: return ret; } -/* - * Machine check recovery code needs to change cache mode of poisoned - * pages to UC to avoid speculative access logging another error. But - * passing the address of the 1:1 mapping to set_memory_uc() is a fine - * way to encourage a speculative access. So we cheat and flip the top - * bit of the address. This works fine for the code that updates the - * page tables. But at the end of the process we need to flush the cache - * and the non-canonical address causes a #GP fault when used by the - * CLFLUSH instruction. - * - * But in the common case we already have a canonical address. This code - * will fix the top bit if needed and is a no-op otherwise. - */ -static inline unsigned long make_addr_canonical_again(unsigned long addr) -{ -#ifdef CONFIG_X86_64 - return (long)(addr << 1) >> 1; -#else - return addr; -#endif -} - - static int change_page_attr_set_clr(unsigned long *addr, int numpages, pgprot_t mask_set, pgprot_t mask_clr, int force_split, int in_flag, From 9ab7d228e972b50d06ee28076ab5d0f93e862463 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Sat, 12 Jan 2019 10:07:23 +0100 Subject: [PATCH 519/525] MAINTAINERS: unify reference to xen-devel list In the linux kernel MAINTAINERS file, largely "xen-devel@lists.xenproject.org (moderated for non-subscribers)" is used to refer to the xen-devel mailing list. The DRM DRIVERS FOR XEN section entry mentions xen-devel@lists.xen.org instead, but that is just the same mailing list as the mailing list above. Signed-off-by: Lukas Bulwahn Signed-off-by: Juergen Gross --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index fc9fe92bfa68..9ada1dc4fe83 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5092,7 +5092,7 @@ DRM DRIVERS FOR XEN M: Oleksandr Andrushchenko T: git git://anongit.freedesktop.org/drm/drm-misc L: dri-devel@lists.freedesktop.org -L: xen-devel@lists.xen.org +L: xen-devel@lists.xenproject.org (moderated for non-subscribers) S: Supported F: drivers/gpu/drm/xen/ F: Documentation/gpu/xen-front.rst From 8c772a9bfc7c07c76f4a58b58910452fbb20843b Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Fri, 25 Jan 2019 08:12:47 +0800 Subject: [PATCH 520/525] blk-iolatency: fix IO hang due to negative inflight counter Our test reported the following stack, and vmcore showed that ->inflight counter is -1. [ffffc9003fcc38d0] __schedule at ffffffff8173d95d [ffffc9003fcc3958] schedule at ffffffff8173de26 [ffffc9003fcc3970] io_schedule at ffffffff810bb6b6 [ffffc9003fcc3988] blkcg_iolatency_throttle at ffffffff813911cb [ffffc9003fcc3a20] rq_qos_throttle at ffffffff813847f3 [ffffc9003fcc3a48] blk_mq_make_request at ffffffff8137468a [ffffc9003fcc3b08] generic_make_request at ffffffff81368b49 [ffffc9003fcc3b68] submit_bio at ffffffff81368d7d [ffffc9003fcc3bb8] ext4_io_submit at ffffffffa031be00 [ext4] [ffffc9003fcc3c00] ext4_writepages at ffffffffa03163de [ext4] [ffffc9003fcc3d68] do_writepages at ffffffff811c49ae [ffffc9003fcc3d78] __filemap_fdatawrite_range at ffffffff811b6188 [ffffc9003fcc3e30] filemap_write_and_wait_range at ffffffff811b6301 [ffffc9003fcc3e60] ext4_sync_file at ffffffffa030cee8 [ext4] [ffffc9003fcc3ea8] vfs_fsync_range at ffffffff8128594b [ffffc9003fcc3ee8] do_fsync at ffffffff81285abd [ffffc9003fcc3f18] sys_fsync at ffffffff81285d50 [ffffc9003fcc3f28] do_syscall_64 at ffffffff81003c04 [ffffc9003fcc3f50] entry_SYSCALL_64_after_swapgs at ffffffff81742b8e The ->inflight counter may be negative (-1) if 1) blk-iolatency was disabled when the IO was issued, 2) blk-iolatency was enabled before this IO reached its endio, 3) the ->inflight counter is decreased from 0 to -1 in endio() In fact the hang can be easily reproduced by the below script, H=/sys/fs/cgroup/unified/ P=/sys/fs/cgroup/unified/test echo "+io" > $H/cgroup.subtree_control mkdir -p $P echo $$ > $P/cgroup.procs xfs_io -f -d -c "pwrite 0 4k" /dev/sdg echo "`cat /sys/block/sdg/dev` target=1000000" > $P/io.latency xfs_io -f -d -c "pwrite 0 4k" /dev/sdg This fixes the problem by freezing the queue so that while enabling/disabling iolatency, there is no inflight rq running. Note that quiesce_queue is not needed as this only updating iolatency configuration about which dispatching request_queue doesn't care. Signed-off-by: Liu Bo Signed-off-by: Jens Axboe --- block/blk-iolatency.c | 52 +++++++++++++++++++++++++++++++++++++------ 1 file changed, 45 insertions(+), 7 deletions(-) diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index fc714ef402a6..1893686a9c1f 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -72,6 +72,7 @@ #include #include #include +#include #include "blk-rq-qos.h" #include "blk-stat.h" @@ -601,6 +602,9 @@ static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio) return; enabled = blk_iolatency_enabled(iolat->blkiolat); + if (!enabled) + return; + while (blkg && blkg->parent) { iolat = blkg_to_lat(blkg); if (!iolat) { @@ -610,7 +614,7 @@ static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio) rqw = &iolat->rq_wait; atomic_dec(&rqw->inflight); - if (!enabled || iolat->min_lat_nsec == 0) + if (iolat->min_lat_nsec == 0) goto next; iolatency_record_time(iolat, &bio->bi_issue, now, issue_as_root); @@ -754,10 +758,13 @@ int blk_iolatency_init(struct request_queue *q) return 0; } -static void iolatency_set_min_lat_nsec(struct blkcg_gq *blkg, u64 val) +/* + * return 1 for enabling iolatency, return -1 for disabling iolatency, otherwise + * return 0. + */ +static int iolatency_set_min_lat_nsec(struct blkcg_gq *blkg, u64 val) { struct iolatency_grp *iolat = blkg_to_lat(blkg); - struct blk_iolatency *blkiolat = iolat->blkiolat; u64 oldval = iolat->min_lat_nsec; iolat->min_lat_nsec = val; @@ -766,9 +773,10 @@ static void iolatency_set_min_lat_nsec(struct blkcg_gq *blkg, u64 val) BLKIOLATENCY_MAX_WIN_SIZE); if (!oldval && val) - atomic_inc(&blkiolat->enabled); + return 1; if (oldval && !val) - atomic_dec(&blkiolat->enabled); + return -1; + return 0; } static void iolatency_clear_scaling(struct blkcg_gq *blkg) @@ -800,6 +808,7 @@ static ssize_t iolatency_set_limit(struct kernfs_open_file *of, char *buf, u64 lat_val = 0; u64 oldval; int ret; + int enable = 0; ret = blkg_conf_prep(blkcg, &blkcg_policy_iolatency, buf, &ctx); if (ret) @@ -834,7 +843,12 @@ static ssize_t iolatency_set_limit(struct kernfs_open_file *of, char *buf, blkg = ctx.blkg; oldval = iolat->min_lat_nsec; - iolatency_set_min_lat_nsec(blkg, lat_val); + enable = iolatency_set_min_lat_nsec(blkg, lat_val); + if (enable) { + WARN_ON_ONCE(!blk_get_queue(blkg->q)); + blkg_get(blkg); + } + if (oldval != iolat->min_lat_nsec) { iolatency_clear_scaling(blkg); } @@ -842,6 +856,24 @@ static ssize_t iolatency_set_limit(struct kernfs_open_file *of, char *buf, ret = 0; out: blkg_conf_finish(&ctx); + if (ret == 0 && enable) { + struct iolatency_grp *tmp = blkg_to_lat(blkg); + struct blk_iolatency *blkiolat = tmp->blkiolat; + + blk_mq_freeze_queue(blkg->q); + + if (enable == 1) + atomic_inc(&blkiolat->enabled); + else if (enable == -1) + atomic_dec(&blkiolat->enabled); + else + WARN_ON_ONCE(1); + + blk_mq_unfreeze_queue(blkg->q); + + blkg_put(blkg); + blk_put_queue(blkg->q); + } return ret ?: nbytes; } @@ -977,8 +1009,14 @@ static void iolatency_pd_offline(struct blkg_policy_data *pd) { struct iolatency_grp *iolat = pd_to_lat(pd); struct blkcg_gq *blkg = lat_to_blkg(iolat); + struct blk_iolatency *blkiolat = iolat->blkiolat; + int ret; - iolatency_set_min_lat_nsec(blkg, 0); + ret = iolatency_set_min_lat_nsec(blkg, 0); + if (ret == 1) + atomic_inc(&blkiolat->enabled); + if (ret == -1) + atomic_dec(&blkiolat->enabled); iolatency_clear_scaling(blkg); } From 391f552af213985d3d324c60004475759a7030c5 Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Fri, 25 Jan 2019 08:12:48 +0800 Subject: [PATCH 521/525] Blk-iolatency: warn on negative inflight IO counter This is to catch any unexpected negative value of inflight IO counter. Signed-off-by: Liu Bo Signed-off-by: Jens Axboe --- block/blk-iolatency.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index 1893686a9c1f..2620baa1f699 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -592,6 +592,7 @@ static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio) u64 now = ktime_to_ns(ktime_get()); bool issue_as_root = bio_issue_as_root_blkg(bio); bool enabled = false; + int inflight = 0; blkg = bio->bi_blkg; if (!blkg || !bio_flagged(bio, BIO_TRACKED)) @@ -613,7 +614,8 @@ static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio) } rqw = &iolat->rq_wait; - atomic_dec(&rqw->inflight); + inflight = atomic_dec_return(&rqw->inflight); + WARN_ON_ONCE(inflight < 0); if (iolat->min_lat_nsec == 0) goto next; iolatency_record_time(iolat, &bio->bi_issue, now, From 2698484178ca5cbfdde189b1d8809e1528f82a10 Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Fri, 25 Jan 2019 08:12:49 +0800 Subject: [PATCH 522/525] blk-mq: remove duplicated definition of blk_mq_freeze_queue As the prototype has been defined in "include/linux/blk-mq.h", the one in "block/blk-mq.h" can be removed then. Signed-off-by: Liu Bo Signed-off-by: Jens Axboe --- block/blk-mq.h | 1 - 1 file changed, 1 deletion(-) diff --git a/block/blk-mq.h b/block/blk-mq.h index d943d46b0785..d0b3dd54ef8d 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -36,7 +36,6 @@ struct blk_mq_ctx { struct kobject kobj; } ____cacheline_aligned_in_smp; -void blk_mq_freeze_queue(struct request_queue *q); void blk_mq_free_queue(struct request_queue *q); int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr); void blk_mq_wake_waiters(struct request_queue *q); From 13c80dda84c4c0c0f52f8dc2e8f083ca3ccc2aa0 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Fri, 8 Feb 2019 17:56:31 +0100 Subject: [PATCH 523/525] MAINTAINERS: Update the ocores i2c bus driver maintainer, etc The listed maintainer has not been responding to emails for a while. Add myself as a second maintainer. Add the platform data include file, which was not listed. Signed-off-by: Andrew Lunn Signed-off-by: Wolfram Sang --- MAINTAINERS | 2 ++ 1 file changed, 2 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 8c68de3cfd80..e832eed65767 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11307,10 +11307,12 @@ F: include/dt-bindings/ OPENCORES I2C BUS DRIVER M: Peter Korsgaard +M: Andrew Lunn L: linux-i2c@vger.kernel.org S: Maintained F: Documentation/i2c/busses/i2c-ocores F: drivers/i2c/busses/i2c-ocores.c +F: include/linux/platform_data/i2c-ocores.h OPENRISC ARCHITECTURE M: Jonas Bonn From 20e55bc17dd01f13cec0eb17e76e9511b23963ef Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Sun, 10 Feb 2019 08:40:56 +0100 Subject: [PATCH 524/525] x86/mm: Make set_pmd_at() paravirt aware set_pmd_at() calls native_set_pmd() unconditionally on x86. This was fine as long as only huge page entries were written via set_pmd_at(), as Xen pv guests don't support those. Commit 2c91bd4a4e2e53 ("mm: speed up mremap by 20x on large regions") introduced a usage of set_pmd_at() possible on pv guests, leading to failures like: BUG: unable to handle kernel paging request at ffff888023e26778 #PF error: [PROT] [WRITE] RIP: e030:move_page_tables+0x7c1/0xae0 move_vma.isra.3+0xd1/0x2d0 __se_sys_mremap+0x3c6/0x5b0 do_syscall_64+0x49/0x100 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Make set_pmd_at() paravirt aware by just letting it use set_pmd(). Fixes: 2c91bd4a4e2e53 ("mm: speed up mremap by 20x on large regions") Reported-by: Sander Eikelenboom Signed-off-by: Juergen Gross Signed-off-by: Thomas Gleixner Cc: xen-devel@lists.xenproject.org Cc: boris.ostrovsky@oracle.com Cc: sstabellini@kernel.org Cc: hpa@zytor.com Cc: bp@alien8.de Cc: torvalds@linux-foundation.org Link: https://lkml.kernel.org/r/20190210074056.11842-1-jgross@suse.com --- arch/x86/include/asm/pgtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 40616e805292..2779ace16d23 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1065,7 +1065,7 @@ static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr, static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { - native_set_pmd(pmdp, pmd); + set_pmd(pmdp, pmd); } static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, From d13937116f1e82bf508a6325111b322c30c85eb9 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 10 Feb 2019 14:42:20 -0800 Subject: [PATCH 525/525] Linux 5.0-rc6 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 3142e67d03f1..86cf35d1d79d 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 0 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Shy Crocodile # *DOCUMENTATION*