From f42259ef810ce83f3e1a8ea4ce12dfda873fbe44 Mon Sep 17 00:00:00 2001 From: Hang Yuan Date: Wed, 19 Sep 2018 14:42:09 +0800 Subject: [PATCH 001/356] drm/i915/gvt: invalidate old ggtt page when update ggtt entry Previously only cancelled dma map of a ggtt page when the ggtt entry was cleared. This patch will cancel dma map of an old ggtt page as well when the ggtt entry is updated with new page address. Fixes: 7598e8700e9a(drm/i915/gvt: Missed to cancel dma map for ggtt entries) Signed-off-by: Hang Yuan Signed-off-by: Zhenyu Wang --- drivers/gpu/drm/i915/gvt/gtt.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 00aad8164dec..c11e353ca904 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -2259,16 +2259,18 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, } else ops->set_pfn(&m, dma_addr >> PAGE_SHIFT); } else { - ggtt_get_host_entry(ggtt_mm, &m, g_gtt_index); - ggtt_invalidate_pte(vgpu, &m); ops->set_pfn(&m, gvt->gtt.scratch_mfn); ops->clear_present(&m); } out: + ggtt_set_guest_entry(ggtt_mm, &e, g_gtt_index); + + ggtt_get_host_entry(ggtt_mm, &e, g_gtt_index); + ggtt_invalidate_pte(vgpu, &e); + ggtt_set_host_entry(ggtt_mm, &m, g_gtt_index); ggtt_invalidate(gvt->dev_priv); - ggtt_set_guest_entry(ggtt_mm, &e, g_gtt_index); return 0; } From 202dc3cc10b4d37e5251431acf8d5040a8876c7d Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 9 Oct 2018 19:41:58 +0200 Subject: [PATCH 002/356] serial: sh-sci: Fix receive on SCIFA/SCIFB variants with DMA On SCIFA and SCIFB serial ports with DMA support (i.e. some ports on R-Car Gen2 and RZ/G1 SoCs), receive DMA operations are submitted before the DMA channel pointer is initialized. Hence this fails, and the driver tries to fall back to PIO. However, at this early phase in the initialization sequence, fallback to PIO does not work, leading to a serial port that cannot receive any data. Fix this by calling sci_submit_rx() after initialization of the DMA channel pointer. Reported-by: Yoshihiro Shimoda Fixes: 2c4ee23530ffc022 ("serial: sh-sci: Postpone DMA release when falling back to PIO") Signed-off-by: Geert Uytterhoeven Reviewed-by: Wolfram Sang Tested-by: Wolfram Sang Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/sh-sci.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index ab3f6e91853d..e19bfbba8a01 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -1614,10 +1614,10 @@ static void sci_request_dma(struct uart_port *port) hrtimer_init(&s->rx_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); s->rx_timer.function = rx_timer_fn; + s->chan_rx_saved = s->chan_rx = chan; + if (port->type == PORT_SCIFA || port->type == PORT_SCIFB) sci_submit_rx(s); - - s->chan_rx_saved = s->chan_rx = chan; } } From 61792b677415b77c8db04991c22966bb8de7603e Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 23 Oct 2018 16:47:16 +0200 Subject: [PATCH 003/356] netfilter: ipv6: fix oops when defragmenting locally generated fragments MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Unlike ipv4 and normal ipv6 defrag, netfilter ipv6 defragmentation did not save/restore skb->dst. This causes oops when handling locally generated ipv6 fragments, as output path needs a valid dst. Reported-by: Maciej Żenczykowski Fixes: 84379c9afe01 ("netfilter: ipv6: nf_defrag: drop skb dst before queueing") Signed-off-by: Florian Westphal Reviewed-by: Eric Dumazet Signed-off-by: Pablo Neira Ayuso --- net/ipv6/netfilter/nf_conntrack_reasm.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index b8ac369f98ad..d219979c3e52 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -587,11 +587,16 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) */ ret = -EINPROGRESS; if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && - fq->q.meat == fq->q.len && - nf_ct_frag6_reasm(fq, skb, dev)) - ret = 0; - else + fq->q.meat == fq->q.len) { + unsigned long orefdst = skb->_skb_refdst; + + skb->_skb_refdst = 0UL; + if (nf_ct_frag6_reasm(fq, skb, dev)) + ret = 0; + skb->_skb_refdst = orefdst; + } else { skb_dst_drop(skb); + } out_unlock: spin_unlock_bh(&fq->q.lock); From 5e91c9d9cd3fd557226ca75fed58816b9eee7e07 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 22 Oct 2018 21:49:45 +0200 Subject: [PATCH 004/356] netfilter: nft_osf: check if attribute is present If the attribute is not sent, eg. old libnftnl binary, then tb[NFTA_OSF_TTL] is NULL and kernel crashes from the _init path. Fixes: a218dc82f0b5 ("netfilter: nft_osf: Add ttl option support") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_osf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index ca5e5d8c5ef8..b13618c764ec 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -50,7 +50,7 @@ static int nft_osf_init(const struct nft_ctx *ctx, int err; u8 ttl; - if (nla_get_u8(tb[NFTA_OSF_TTL])) { + if (tb[NFTA_OSF_TTL]) { ttl = nla_get_u8(tb[NFTA_OSF_TTL]); if (ttl > 2) return -EINVAL; From 5a8de47b3c250521dd632cdedaac6db88367defa Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 24 Oct 2018 13:54:03 +0200 Subject: [PATCH 005/356] netfilter: bridge: define INT_MIN & INT_MAX in userspace MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With 4.19, programs like ebtables fail to build when they include "linux/netfilter_bridge.h". It is caused by commit 94276fa8a2a4 which added a use of INT_MIN and INT_MAX to the header: : In file included from /usr/include/linux/netfilter_bridge/ebtables.h:18, : from include/ebtables_u.h:28, : from communication.c:23: : /usr/include/linux/netfilter_bridge.h:30:20: error: 'INT_MIN' undeclared here (not in a function) : NF_BR_PRI_FIRST = INT_MIN, : ^~~~~~~ Define these constants by including "limits.h" when !__KERNEL__ (the same way as for other netfilter_* headers). Fixes: 94276fa8a2a4 ("netfilter: bridge: Expose nf_tables bridge hook priorities through uapi") Signed-off-by: Jiri Slaby Acked-by: Máté Eckl Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter_bridge.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/include/uapi/linux/netfilter_bridge.h b/include/uapi/linux/netfilter_bridge.h index 156ccd089df1..1610fdbab98d 100644 --- a/include/uapi/linux/netfilter_bridge.h +++ b/include/uapi/linux/netfilter_bridge.h @@ -11,6 +11,10 @@ #include #include +#ifndef __KERNEL__ +#include /* for INT_MIN, INT_MAX */ +#endif + /* Bridge Hooks */ /* After promisc drops, checksum checks. */ #define NF_BR_PRE_ROUTING 0 From 1b50bb4d36e89fd54c14722c4ab5266ef17767ff Mon Sep 17 00:00:00 2001 From: Pavel Machek Date: Wed, 24 Oct 2018 22:44:39 +0200 Subject: [PATCH 006/356] Fix pattern handling optimalization Check for zero duration before skipping step. This fixes pattern echo "0 1000 10 2550 0 1000" > pattern which should do [ .-xXx-.] but does [ Xx-.] Signed-off-by: Pavel Machek Suggested-by: Jacek Anaszewski Signed-off-by: Jacek Anaszewski --- drivers/leds/trigger/ledtrig-pattern.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/leds/trigger/ledtrig-pattern.c b/drivers/leds/trigger/ledtrig-pattern.c index ce7acd115dd8..174a298f1be0 100644 --- a/drivers/leds/trigger/ledtrig-pattern.c +++ b/drivers/leds/trigger/ledtrig-pattern.c @@ -87,9 +87,10 @@ static void pattern_trig_timer_function(struct timer_list *t) data->curr->brightness); mod_timer(&data->timer, jiffies + msecs_to_jiffies(data->curr->delta_t)); - - /* Skip the tuple with zero duration */ - pattern_trig_update_patterns(data); + if (!data->next->delta_t) { + /* Skip the tuple with zero duration */ + pattern_trig_update_patterns(data); + } /* Select next tuple */ pattern_trig_update_patterns(data); } else { From ef5febae1543f35a45f01614123e829d77326d0f Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Fri, 19 Oct 2018 13:37:46 +0200 Subject: [PATCH 007/356] s390/decompressor: add missing FORCE to build targets According to Documentation/kbuild/makefiles.txt all build targets using if_changed should use FORCE as well. Add missing FORCE to make sure vmlinux decompressor targets are rebuild properly when not just immediate prerequisites have changed but also when build command differs. Reviewed-by: Philipp Rudo Signed-off-by: Vasily Gorbik Signed-off-by: Martin Schwidefsky --- arch/s390/boot/compressed/Makefile | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile index 593039620487..92b5487b0556 100644 --- a/arch/s390/boot/compressed/Makefile +++ b/arch/s390/boot/compressed/Makefile @@ -22,7 +22,7 @@ OBJCOPYFLAGS := OBJECTS := $(addprefix $(obj)/,$(obj-y)) LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup -T -$(obj)/vmlinux: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS) +$(obj)/vmlinux: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS) FORCE $(call if_changed,ld) OBJCOPYFLAGS_info.bin := -O binary --only-section=.vmlinux.info @@ -46,17 +46,17 @@ suffix-$(CONFIG_KERNEL_LZMA) := .lzma suffix-$(CONFIG_KERNEL_LZO) := .lzo suffix-$(CONFIG_KERNEL_XZ) := .xz -$(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y) +$(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y) FORCE $(call if_changed,gzip) -$(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y) +$(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y) FORCE $(call if_changed,bzip2) -$(obj)/vmlinux.bin.lz4: $(vmlinux.bin.all-y) +$(obj)/vmlinux.bin.lz4: $(vmlinux.bin.all-y) FORCE $(call if_changed,lz4) -$(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y) +$(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y) FORCE $(call if_changed,lzma) -$(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y) +$(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y) FORCE $(call if_changed,lzo) -$(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y) +$(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y) FORCE $(call if_changed,xzkern) OBJCOPYFLAGS_piggy.o := -I binary -O elf64-s390 -B s390:64-bit --rename-section .data=.vmlinux.bin.compressed From b44b136a3773d8a9c7853f8df716bd1483613cbb Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Fri, 19 Oct 2018 15:37:01 +0200 Subject: [PATCH 008/356] s390/vdso: add missing FORCE to build targets According to Documentation/kbuild/makefiles.txt all build targets using if_changed should use FORCE as well. Add missing FORCE to make sure vdso targets are rebuild properly when not just immediate prerequisites have changed but also when build command differs. Reviewed-by: Philipp Rudo Signed-off-by: Vasily Gorbik Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/vdso32/Makefile | 6 +++--- arch/s390/kernel/vdso64/Makefile | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile index eb8aebea3ea7..e76309fbbcb3 100644 --- a/arch/s390/kernel/vdso32/Makefile +++ b/arch/s390/kernel/vdso32/Makefile @@ -37,7 +37,7 @@ KASAN_SANITIZE := n $(obj)/vdso32_wrapper.o : $(obj)/vdso32.so # link rule for the .so file, .lds has to be first -$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) +$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) FORCE $(call if_changed,vdso32ld) # strip rule for the .so file @@ -46,12 +46,12 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) # assembly rules for the .S files -$(obj-vdso32): %.o: %.S +$(obj-vdso32): %.o: %.S FORCE $(call if_changed_dep,vdso32as) # actual build commands quiet_cmd_vdso32ld = VDSO32L $@ - cmd_vdso32ld = $(CC) $(c_flags) -Wl,-T $^ -o $@ + cmd_vdso32ld = $(CC) $(c_flags) -Wl,-T $(filter %.lds %.o,$^) -o $@ quiet_cmd_vdso32as = VDSO32A $@ cmd_vdso32as = $(CC) $(a_flags) -c -o $@ $< diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile index a22b2cf86eec..f849ac61c5da 100644 --- a/arch/s390/kernel/vdso64/Makefile +++ b/arch/s390/kernel/vdso64/Makefile @@ -37,7 +37,7 @@ KASAN_SANITIZE := n $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so # link rule for the .so file, .lds has to be first -$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) +$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) FORCE $(call if_changed,vdso64ld) # strip rule for the .so file @@ -46,12 +46,12 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) # assembly rules for the .S files -$(obj-vdso64): %.o: %.S +$(obj-vdso64): %.o: %.S FORCE $(call if_changed_dep,vdso64as) # actual build commands quiet_cmd_vdso64ld = VDSO64L $@ - cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $^ -o $@ + cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $(filter %.lds %.o,$^) -o $@ quiet_cmd_vdso64as = VDSO64A $@ cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $< From 5a2e1853d68904c4b26706dba2884cbeb77bc3ee Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Wed, 17 Oct 2018 13:59:46 +0200 Subject: [PATCH 009/356] s390: avoid vmlinux segments overlap Currently .vmlinux.info section of uncompressed vmlinux elf image is included into the data segment and load address specified as 0. That extends data segment to address 0 and makes "text" and "data" segments overlap. Program Headers: Type Offset VirtAddr PhysAddr FileSiz MemSiz Flags Align LOAD 0x0000000000001000 0x0000000000100000 0x0000000000100000 0x0000000000ead03c 0x0000000000ead03c R E 0x1000 LOAD 0x0000000000eaf000 0x0000000000000000 0x0000000000000000 0x0000000001a13400 0x000000000233b520 RWE 0x1000 NOTE 0x0000000000eae000 0x0000000000fad000 0x0000000000fad000 0x000000000000003c 0x000000000000003c 0x4 Section to Segment mapping: Segment Sections... 00 .text .notes 01 .rodata __ksymtab __ksymtab_gpl __ksymtab_strings __param __modver .data..ro_after_init __ex_table .data __bug_table .init.text .exit.text .exit.data .altinstructions .altinstr_replacement .nospec_call_table .nospec_return_table .boot.data .init.data .data..percpu .bss .vmlinux.info 02 .notes Later when vmlinux.bin is produced from vmlinux, .vmlinux.info section is removed. But elf vmlinux file, even though it is not bootable anymore, used for debugging and loadable segments overlap should be avoided. Utilize special ":NONE" phdr specification to avoid adding .vmlinux.info into loadable data segment. Also set .vmlinux.info section type to INFO, which allows to get a not-loadable info CONTENTS section. Since minimal supported version of binutils 2.20 does not have --dump-section objcopy option, make .vmlinux.info section loadable during info.bin creation to get actual section contents. Reported-by: Philipp Rudo Signed-off-by: Vasily Gorbik Signed-off-by: Martin Schwidefsky --- arch/s390/boot/compressed/Makefile | 2 +- arch/s390/kernel/vmlinux.lds.S | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile index 92b5487b0556..b1bdd15e3429 100644 --- a/arch/s390/boot/compressed/Makefile +++ b/arch/s390/boot/compressed/Makefile @@ -25,7 +25,7 @@ LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup -T $(obj)/vmlinux: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS) FORCE $(call if_changed,ld) -OBJCOPYFLAGS_info.bin := -O binary --only-section=.vmlinux.info +OBJCOPYFLAGS_info.bin := -O binary --only-section=.vmlinux.info --set-section-flags .vmlinux.info=load $(obj)/info.bin: vmlinux FORCE $(call if_changed,objcopy) diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 21eb7407d51b..8429ab079715 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -154,14 +154,14 @@ SECTIONS * uncompressed image info used by the decompressor * it should match struct vmlinux_info */ - .vmlinux.info 0 : { + .vmlinux.info 0 (INFO) : { QUAD(_stext) /* default_lma */ QUAD(startup_continue) /* entry */ QUAD(__bss_start - _stext) /* image_size */ QUAD(__bss_stop - __bss_start) /* bss_size */ QUAD(__boot_data_start) /* bootdata_off */ QUAD(__boot_data_end - __boot_data_start) /* bootdata_size */ - } + } :NONE /* Debugging sections. */ STABS_DEBUG From f11274396a538b31bc010f782e05c2ce3f804c13 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Fri, 19 Oct 2018 17:01:33 -0300 Subject: [PATCH 010/356] HID: hiddev: fix potential Spectre v1 uref->usage_index can be indirectly controlled by userspace, hence leading to a potential exploitation of the Spectre variant 1 vulnerability. This field is used as an array index by the hiddev_ioctl_usage() function, when 'cmd' is either HIDIOCGCOLLECTIONINDEX, HIDIOCGUSAGES or HIDIOCSUSAGES. For cmd == HIDIOCGCOLLECTIONINDEX case, uref->usage_index is compared to field->maxusage and then used as an index to dereference field->usage array. The same thing happens to the cmd == HIDIOC{G,S}USAGES cases, where uref->usage_index is checked against an array maximum value and then it is used as an index in an array. This is a summary of the HIDIOCGCOLLECTIONINDEX case, which matches the traditional Spectre V1 first load: copy_from_user(uref, user_arg, sizeof(*uref)) if (uref->usage_index >= field->maxusage) goto inval; i = field->usage[uref->usage_index].collection_index; return i; This patch fixes this by sanitizing field uref->usage_index before using it to index field->usage (HIDIOCGCOLLECTIONINDEX) or field->value in HIDIOC{G,S}USAGES arrays, thus, avoiding speculation in the first load. Cc: Signed-off-by: Breno Leitao -- v2: Contemplate cmd == HIDIOC{G,S}USAGES case Signed-off-by: Jiri Kosina --- drivers/hid/usbhid/hiddev.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c index 23872d08308c..a746017fac17 100644 --- a/drivers/hid/usbhid/hiddev.c +++ b/drivers/hid/usbhid/hiddev.c @@ -512,14 +512,24 @@ static noinline int hiddev_ioctl_usage(struct hiddev *hiddev, unsigned int cmd, if (cmd == HIDIOCGCOLLECTIONINDEX) { if (uref->usage_index >= field->maxusage) goto inval; + uref->usage_index = + array_index_nospec(uref->usage_index, + field->maxusage); } else if (uref->usage_index >= field->report_count) goto inval; } - if ((cmd == HIDIOCGUSAGES || cmd == HIDIOCSUSAGES) && - (uref_multi->num_values > HID_MAX_MULTI_USAGES || - uref->usage_index + uref_multi->num_values > field->report_count)) - goto inval; + if (cmd == HIDIOCGUSAGES || cmd == HIDIOCSUSAGES) { + if (uref_multi->num_values > HID_MAX_MULTI_USAGES || + uref->usage_index + uref_multi->num_values > + field->report_count) + goto inval; + + uref->usage_index = + array_index_nospec(uref->usage_index, + field->report_count - + uref_multi->num_values); + } switch (cmd) { case HIDIOCGUSAGE: From 00b790ea545b6ef30221adef6e9c3707e03b82b5 Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Fri, 5 Oct 2018 12:46:29 +0800 Subject: [PATCH 011/356] HID: i2c-hid: Add a small delay after sleep command for Raydium touchpanel Raydium touchpanel (2386:4B33) sometimes does not work in desktop session although it works in display manager. During user logging, the display manager exits, close the HID device, then the device gets runtime suspended and powered off. The desktop session begins shortly after, opens the HID device, then the device gets runtime resumed and powered on. If the trasition from display manager to desktop sesesion is fast, the touchpanel cannot switch from powered off to powered on in short timeframe. So add a small delay to workaround the issue. Signed-off-by: Kai-Heng Feng Reviewed-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- drivers/hid/hid-ids.h | 3 +++ drivers/hid/i2c-hid/i2c-hid-core.c | 19 +++++++++++++++++++ 2 files changed, 22 insertions(+) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index f63489c882bb..c0d668944dbe 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -927,6 +927,9 @@ #define USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3003 0x3003 #define USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3008 0x3008 +#define I2C_VENDOR_ID_RAYDIUM 0x2386 +#define I2C_PRODUCT_ID_RAYDIUM_4B33 0x4b33 + #define USB_VENDOR_ID_RAZER 0x1532 #define USB_DEVICE_ID_RAZER_BLADE_14 0x011D diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 4aab96cf0818..3cde7c1b9c33 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -49,6 +49,7 @@ #define I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV BIT(0) #define I2C_HID_QUIRK_NO_IRQ_AFTER_RESET BIT(1) #define I2C_HID_QUIRK_NO_RUNTIME_PM BIT(2) +#define I2C_HID_QUIRK_DELAY_AFTER_SLEEP BIT(3) /* flags */ #define I2C_HID_STARTED 0 @@ -158,6 +159,8 @@ struct i2c_hid { bool irq_wake_enabled; struct mutex reset_lock; + + unsigned long sleep_delay; }; static const struct i2c_hid_quirks { @@ -172,6 +175,8 @@ static const struct i2c_hid_quirks { { I2C_VENDOR_ID_HANTICK, I2C_PRODUCT_ID_HANTICK_5288, I2C_HID_QUIRK_NO_IRQ_AFTER_RESET | I2C_HID_QUIRK_NO_RUNTIME_PM }, + { I2C_VENDOR_ID_RAYDIUM, I2C_PRODUCT_ID_RAYDIUM_4B33, + I2C_HID_QUIRK_DELAY_AFTER_SLEEP }, { 0, 0 } }; @@ -387,6 +392,7 @@ static int i2c_hid_set_power(struct i2c_client *client, int power_state) { struct i2c_hid *ihid = i2c_get_clientdata(client); int ret; + unsigned long now, delay; i2c_hid_dbg(ihid, "%s\n", __func__); @@ -404,9 +410,22 @@ static int i2c_hid_set_power(struct i2c_client *client, int power_state) goto set_pwr_exit; } + if (ihid->quirks & I2C_HID_QUIRK_DELAY_AFTER_SLEEP && + power_state == I2C_HID_PWR_ON) { + now = jiffies; + if (time_after(ihid->sleep_delay, now)) { + delay = jiffies_to_usecs(ihid->sleep_delay - now); + usleep_range(delay, delay + 1); + } + } + ret = __i2c_hid_command(client, &hid_set_power_cmd, power_state, 0, NULL, 0, NULL, 0); + if (ihid->quirks & I2C_HID_QUIRK_DELAY_AFTER_SLEEP && + power_state == I2C_HID_PWR_SLEEP) + ihid->sleep_delay = jiffies + msecs_to_jiffies(20); + if (ret) dev_err(&client->dev, "failed to change power setting.\n"); From 6298944d8f57f40ee2a3e6dcea1253e78d7a9969 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Wed, 17 Oct 2018 09:01:53 +0200 Subject: [PATCH 012/356] Revert "HID: add NOGET quirk for Eaton Ellipse MAX UPS" This reverts commit 67ddbb3e6568fb1820b2cc45b00c50702b114801. 67ddbb3e656 ("HID: add NOGET quirk for Eaton Ellipse MAX UPS") was reported by Laurent Bigonville. It turns out that a later model Laurent got doesn't need the quirk after all. My take is that Eaton upgraded their firmwares, so we don't need it anymore. The old model was from 2012, so better make sure the new line works properly by removing the quirk. This allows upower to actually fetch the current data. Reported-by: Laurent Bigonville Signed-off-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- drivers/hid/hid-quirks.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 52c3b01917e7..8237dd86fb17 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -107,7 +107,6 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOUSE_C05A), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOUSE_C06A), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_MCS, USB_DEVICE_ID_MCS_GAMEPADBLOCK), HID_QUIRK_MULTI_INPUT }, - { HID_USB_DEVICE(USB_VENDOR_ID_MGE, USB_DEVICE_ID_MGE_UPS), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_POWER_COVER), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_SURFACE_PRO_2), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TOUCH_COVER_2), HID_QUIRK_NO_INIT_REPORTS }, From 7dd8db68949a7acc5bd528ee0ecb8f8720f49921 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Fri, 12 Oct 2018 16:05:25 +0200 Subject: [PATCH 013/356] HID: alps: allow incoming reports when only the trackstick is opened If userspace only reads the trackstick node, and no one is listening to the touchpad nor the hidraw node then, the device is not powered on. Add open/close callbacks to allow users to disable the touchpad in Gnome while keeping the trackstick active. Link: https://bugzilla.redhat.com/show_bug.cgi?id=1559632 Link: https://gitlab.gnome.org/GNOME/mutter/issues/128 Signed-off-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- drivers/hid/hid-alps.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/drivers/hid/hid-alps.c b/drivers/hid/hid-alps.c index aec253b44156..3cd7229b6e54 100644 --- a/drivers/hid/hid-alps.c +++ b/drivers/hid/hid-alps.c @@ -660,6 +660,20 @@ exit: return ret; } +static int alps_sp_open(struct input_dev *dev) +{ + struct hid_device *hid = input_get_drvdata(dev); + + return hid_hw_open(hid); +} + +static void alps_sp_close(struct input_dev *dev) +{ + struct hid_device *hid = input_get_drvdata(dev); + + hid_hw_close(hid); +} + static int alps_input_configured(struct hid_device *hdev, struct hid_input *hi) { struct alps_dev *data = hid_get_drvdata(hdev); @@ -733,6 +747,10 @@ static int alps_input_configured(struct hid_device *hdev, struct hid_input *hi) input2->id.version = input->id.version; input2->dev.parent = input->dev.parent; + input_set_drvdata(input2, hdev); + input2->open = alps_sp_open; + input2->close = alps_sp_close; + __set_bit(EV_KEY, input2->evbit); data->sp_btn_cnt = (data->sp_btn_info & 0x0F); for (i = 0; i < data->sp_btn_cnt; i++) From 4269fea768a11a447d8de620ce420f2214d4685c Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 26 Oct 2018 11:14:28 +0200 Subject: [PATCH 014/356] Revert "netfilter: nft_numgen: add map lookups for numgen random operations" Laura found a better way to do this from userspace without requiring kernel infrastructure, revert this. Fixes: 978d8f9055c3 ("netfilter: nft_numgen: add map lookups for numgen random operations") Signed-off-by: Laura Garcia Liebana Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 4 +- net/netfilter/nft_numgen.c | 127 ----------------------- 2 files changed, 2 insertions(+), 129 deletions(-) diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 579974b0bf0d..7de4f1bdaf06 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1635,8 +1635,8 @@ enum nft_ng_attributes { NFTA_NG_MODULUS, NFTA_NG_TYPE, NFTA_NG_OFFSET, - NFTA_NG_SET_NAME, - NFTA_NG_SET_ID, + NFTA_NG_SET_NAME, /* deprecated */ + NFTA_NG_SET_ID, /* deprecated */ __NFTA_NG_MAX }; #define NFTA_NG_MAX (__NFTA_NG_MAX - 1) diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c index 649d1700ec5b..3cc1b3dc3c3c 100644 --- a/net/netfilter/nft_numgen.c +++ b/net/netfilter/nft_numgen.c @@ -24,7 +24,6 @@ struct nft_ng_inc { u32 modulus; atomic_t counter; u32 offset; - struct nft_set *map; }; static u32 nft_ng_inc_gen(struct nft_ng_inc *priv) @@ -48,34 +47,11 @@ static void nft_ng_inc_eval(const struct nft_expr *expr, regs->data[priv->dreg] = nft_ng_inc_gen(priv); } -static void nft_ng_inc_map_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) -{ - struct nft_ng_inc *priv = nft_expr_priv(expr); - const struct nft_set *map = priv->map; - const struct nft_set_ext *ext; - u32 result; - bool found; - - result = nft_ng_inc_gen(priv); - found = map->ops->lookup(nft_net(pkt), map, &result, &ext); - - if (!found) - return; - - nft_data_copy(®s->data[priv->dreg], - nft_set_ext_data(ext), map->dlen); -} - static const struct nla_policy nft_ng_policy[NFTA_NG_MAX + 1] = { [NFTA_NG_DREG] = { .type = NLA_U32 }, [NFTA_NG_MODULUS] = { .type = NLA_U32 }, [NFTA_NG_TYPE] = { .type = NLA_U32 }, [NFTA_NG_OFFSET] = { .type = NLA_U32 }, - [NFTA_NG_SET_NAME] = { .type = NLA_STRING, - .len = NFT_SET_MAXNAMELEN - 1 }, - [NFTA_NG_SET_ID] = { .type = NLA_U32 }, }; static int nft_ng_inc_init(const struct nft_ctx *ctx, @@ -101,22 +77,6 @@ static int nft_ng_inc_init(const struct nft_ctx *ctx, NFT_DATA_VALUE, sizeof(u32)); } -static int nft_ng_inc_map_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) -{ - struct nft_ng_inc *priv = nft_expr_priv(expr); - u8 genmask = nft_genmask_next(ctx->net); - - nft_ng_inc_init(ctx, expr, tb); - - priv->map = nft_set_lookup_global(ctx->net, ctx->table, - tb[NFTA_NG_SET_NAME], - tb[NFTA_NG_SET_ID], genmask); - - return PTR_ERR_OR_ZERO(priv->map); -} - static int nft_ng_dump(struct sk_buff *skb, enum nft_registers dreg, u32 modulus, enum nft_ng_types type, u32 offset) { @@ -143,27 +103,10 @@ static int nft_ng_inc_dump(struct sk_buff *skb, const struct nft_expr *expr) priv->offset); } -static int nft_ng_inc_map_dump(struct sk_buff *skb, - const struct nft_expr *expr) -{ - const struct nft_ng_inc *priv = nft_expr_priv(expr); - - if (nft_ng_dump(skb, priv->dreg, priv->modulus, - NFT_NG_INCREMENTAL, priv->offset) || - nla_put_string(skb, NFTA_NG_SET_NAME, priv->map->name)) - goto nla_put_failure; - - return 0; - -nla_put_failure: - return -1; -} - struct nft_ng_random { enum nft_registers dreg:8; u32 modulus; u32 offset; - struct nft_set *map; }; static u32 nft_ng_random_gen(struct nft_ng_random *priv) @@ -183,25 +126,6 @@ static void nft_ng_random_eval(const struct nft_expr *expr, regs->data[priv->dreg] = nft_ng_random_gen(priv); } -static void nft_ng_random_map_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) -{ - struct nft_ng_random *priv = nft_expr_priv(expr); - const struct nft_set *map = priv->map; - const struct nft_set_ext *ext; - u32 result; - bool found; - - result = nft_ng_random_gen(priv); - found = map->ops->lookup(nft_net(pkt), map, &result, &ext); - if (!found) - return; - - nft_data_copy(®s->data[priv->dreg], - nft_set_ext_data(ext), map->dlen); -} - static int nft_ng_random_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) @@ -226,21 +150,6 @@ static int nft_ng_random_init(const struct nft_ctx *ctx, NFT_DATA_VALUE, sizeof(u32)); } -static int nft_ng_random_map_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) -{ - struct nft_ng_random *priv = nft_expr_priv(expr); - u8 genmask = nft_genmask_next(ctx->net); - - nft_ng_random_init(ctx, expr, tb); - priv->map = nft_set_lookup_global(ctx->net, ctx->table, - tb[NFTA_NG_SET_NAME], - tb[NFTA_NG_SET_ID], genmask); - - return PTR_ERR_OR_ZERO(priv->map); -} - static int nft_ng_random_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_ng_random *priv = nft_expr_priv(expr); @@ -249,22 +158,6 @@ static int nft_ng_random_dump(struct sk_buff *skb, const struct nft_expr *expr) priv->offset); } -static int nft_ng_random_map_dump(struct sk_buff *skb, - const struct nft_expr *expr) -{ - const struct nft_ng_random *priv = nft_expr_priv(expr); - - if (nft_ng_dump(skb, priv->dreg, priv->modulus, - NFT_NG_RANDOM, priv->offset) || - nla_put_string(skb, NFTA_NG_SET_NAME, priv->map->name)) - goto nla_put_failure; - - return 0; - -nla_put_failure: - return -1; -} - static struct nft_expr_type nft_ng_type; static const struct nft_expr_ops nft_ng_inc_ops = { .type = &nft_ng_type, @@ -274,14 +167,6 @@ static const struct nft_expr_ops nft_ng_inc_ops = { .dump = nft_ng_inc_dump, }; -static const struct nft_expr_ops nft_ng_inc_map_ops = { - .type = &nft_ng_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_ng_inc)), - .eval = nft_ng_inc_map_eval, - .init = nft_ng_inc_map_init, - .dump = nft_ng_inc_map_dump, -}; - static const struct nft_expr_ops nft_ng_random_ops = { .type = &nft_ng_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_ng_random)), @@ -290,14 +175,6 @@ static const struct nft_expr_ops nft_ng_random_ops = { .dump = nft_ng_random_dump, }; -static const struct nft_expr_ops nft_ng_random_map_ops = { - .type = &nft_ng_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_ng_random)), - .eval = nft_ng_random_map_eval, - .init = nft_ng_random_map_init, - .dump = nft_ng_random_map_dump, -}; - static const struct nft_expr_ops * nft_ng_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { @@ -312,12 +189,8 @@ nft_ng_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) switch (type) { case NFT_NG_INCREMENTAL: - if (tb[NFTA_NG_SET_NAME]) - return &nft_ng_inc_map_ops; return &nft_ng_inc_ops; case NFT_NG_RANDOM: - if (tb[NFTA_NG_SET_NAME]) - return &nft_ng_random_map_ops; return &nft_ng_random_ops; } From c6e0bba4ac44fd3d116d763c834dd43f3824f635 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Sat, 27 Oct 2018 14:16:13 +0200 Subject: [PATCH 015/356] HID: moving to group maintainership model Benjamin and myself will from now on be sharing maintainership responsibilities for hid.git. Update maintainers to reflect that change, and also move a git repository to shared space at kernel.org. Signed-off-by: Jiri Kosina Signed-off-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- MAINTAINERS | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index c0c4c5003998..4715cb8d9584 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6588,9 +6588,9 @@ F: arch/*/include/asm/suspend*.h HID CORE LAYER M: Jiri Kosina -R: Benjamin Tissoires +M: Benjamin Tissoires L: linux-input@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/hid/hid.git S: Maintained F: drivers/hid/ F: include/linux/hid* @@ -15254,9 +15254,9 @@ F: include/linux/usb/gadget* USB HID/HIDBP DRIVERS (USB KEYBOARDS, MICE, REMOTE CONTROLS, ...) M: Jiri Kosina -R: Benjamin Tissoires +M: Benjamin Tissoires L: linux-usb@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/hid/hid.git S: Maintained F: Documentation/hid/hiddev.txt F: drivers/hid/usbhid/ From bc0686ff5fad7a842cc88377439e78be87fedc80 Mon Sep 17 00:00:00 2001 From: Hang Yuan Date: Wed, 19 Sep 2018 14:42:10 +0800 Subject: [PATCH 016/356] drm/i915/gvt: support inconsecutive partial gtt entry write Previously we assumed two 4-byte writes to the same PTE coming in sequence. But recently we observed inconsecutive partial write happening as well. So this patch enhances the previous solution. It now uses a list to save more partial writes. If one partial write can be combined with another one in the list to construct a full PTE, update its shadow entry. Otherwise, save the partial write in the list. v2: invalidate old entry and flush ggtt (Zhenyu) v3: split old ggtt page unmap to another patch (Zhenyu) v4: refine codes (Zhenyu) Signed-off-by: Hang Yuan Cc: Yan Zhao Cc: Xiaolin Zhang Cc: Zhenyu Wang Reviewed-by: Xiaolin Zhang Signed-off-by: Zhenyu Wang --- drivers/gpu/drm/i915/gvt/gtt.c | 99 +++++++++++++++++----------------- drivers/gpu/drm/i915/gvt/gtt.h | 9 +++- 2 files changed, 56 insertions(+), 52 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index c11e353ca904..919de5a1bafb 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -1901,7 +1901,6 @@ static struct intel_vgpu_mm *intel_vgpu_create_ggtt_mm(struct intel_vgpu *vgpu) vgpu_free_mm(mm); return ERR_PTR(-ENOMEM); } - mm->ggtt_mm.last_partial_off = -1UL; return mm; } @@ -1926,7 +1925,6 @@ void _intel_vgpu_mm_release(struct kref *mm_ref) invalidate_ppgtt_mm(mm); } else { vfree(mm->ggtt_mm.virtual_ggtt); - mm->ggtt_mm.last_partial_off = -1UL; } vgpu_free_mm(mm); @@ -2164,6 +2162,8 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, struct intel_gvt_gtt_entry e, m; dma_addr_t dma_addr; int ret; + struct intel_gvt_partial_pte *partial_pte, *pos, *n; + bool partial_update = false; if (bytes != 4 && bytes != 8) return -EINVAL; @@ -2174,68 +2174,57 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, if (!vgpu_gmadr_is_valid(vgpu, gma)) return 0; - ggtt_get_guest_entry(ggtt_mm, &e, g_gtt_index); - + e.type = GTT_TYPE_GGTT_PTE; memcpy((void *)&e.val64 + (off & (info->gtt_entry_size - 1)), p_data, bytes); /* If ggtt entry size is 8 bytes, and it's split into two 4 bytes - * write, we assume the two 4 bytes writes are consecutive. - * Otherwise, we abort and report error + * write, save the first 4 bytes in a list and update virtual + * PTE. Only update shadow PTE when the second 4 bytes comes. */ if (bytes < info->gtt_entry_size) { - if (ggtt_mm->ggtt_mm.last_partial_off == -1UL) { - /* the first partial part*/ - ggtt_mm->ggtt_mm.last_partial_off = off; - ggtt_mm->ggtt_mm.last_partial_data = e.val64; - return 0; - } else if ((g_gtt_index == - (ggtt_mm->ggtt_mm.last_partial_off >> - info->gtt_entry_size_shift)) && - (off != ggtt_mm->ggtt_mm.last_partial_off)) { - /* the second partial part */ + bool found = false; - int last_off = ggtt_mm->ggtt_mm.last_partial_off & - (info->gtt_entry_size - 1); + list_for_each_entry_safe(pos, n, + &ggtt_mm->ggtt_mm.partial_pte_list, list) { + if (g_gtt_index == pos->offset >> + info->gtt_entry_size_shift) { + if (off != pos->offset) { + /* the second partial part*/ + int last_off = pos->offset & + (info->gtt_entry_size - 1); - memcpy((void *)&e.val64 + last_off, - (void *)&ggtt_mm->ggtt_mm.last_partial_data + - last_off, bytes); + memcpy((void *)&e.val64 + last_off, + (void *)&pos->data + last_off, + bytes); - ggtt_mm->ggtt_mm.last_partial_off = -1UL; - } else { - int last_offset; + list_del(&pos->list); + kfree(pos); + found = true; + break; + } - gvt_vgpu_err("failed to populate guest ggtt entry: abnormal ggtt entry write sequence, last_partial_off=%lx, offset=%x, bytes=%d, ggtt entry size=%d\n", - ggtt_mm->ggtt_mm.last_partial_off, off, - bytes, info->gtt_entry_size); + /* update of the first partial part */ + pos->data = e.val64; + ggtt_set_guest_entry(ggtt_mm, &e, g_gtt_index); + return 0; + } + } - /* set host ggtt entry to scratch page and clear - * virtual ggtt entry as not present for last - * partially write offset - */ - last_offset = ggtt_mm->ggtt_mm.last_partial_off & - (~(info->gtt_entry_size - 1)); - - ggtt_get_host_entry(ggtt_mm, &m, last_offset); - ggtt_invalidate_pte(vgpu, &m); - ops->set_pfn(&m, gvt->gtt.scratch_mfn); - ops->clear_present(&m); - ggtt_set_host_entry(ggtt_mm, &m, last_offset); - ggtt_invalidate(gvt->dev_priv); - - ggtt_get_guest_entry(ggtt_mm, &e, last_offset); - ops->clear_present(&e); - ggtt_set_guest_entry(ggtt_mm, &e, last_offset); - - ggtt_mm->ggtt_mm.last_partial_off = off; - ggtt_mm->ggtt_mm.last_partial_data = e.val64; - - return 0; + if (!found) { + /* the first partial part */ + partial_pte = kzalloc(sizeof(*partial_pte), GFP_KERNEL); + if (!partial_pte) + return -ENOMEM; + partial_pte->offset = off; + partial_pte->data = e.val64; + list_add_tail(&partial_pte->list, + &ggtt_mm->ggtt_mm.partial_pte_list); + partial_update = true; } } - if (ops->test_present(&e)) { + if (!partial_update && (ops->test_present(&e))) { gfn = ops->get_pfn(&e); m = e; @@ -2428,6 +2417,8 @@ int intel_vgpu_init_gtt(struct intel_vgpu *vgpu) intel_vgpu_reset_ggtt(vgpu, false); + INIT_LIST_HEAD(>t->ggtt_mm->ggtt_mm.partial_pte_list); + return create_scratch_page_tree(vgpu); } @@ -2452,6 +2443,14 @@ static void intel_vgpu_destroy_all_ppgtt_mm(struct intel_vgpu *vgpu) static void intel_vgpu_destroy_ggtt_mm(struct intel_vgpu *vgpu) { + struct intel_gvt_partial_pte *pos; + + list_for_each_entry(pos, + &vgpu->gtt.ggtt_mm->ggtt_mm.partial_pte_list, list) { + gvt_dbg_mm("partial PTE update on hold 0x%lx : 0x%llx\n", + pos->offset, pos->data); + kfree(pos); + } intel_vgpu_destroy_mm(vgpu->gtt.ggtt_mm); vgpu->gtt.ggtt_mm = NULL; } diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h index 7a9b36176efb..a11bfee1e0c8 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.h +++ b/drivers/gpu/drm/i915/gvt/gtt.h @@ -133,6 +133,12 @@ enum intel_gvt_mm_type { #define GVT_RING_CTX_NR_PDPS GEN8_3LVL_PDPES +struct intel_gvt_partial_pte { + unsigned long offset; + u64 data; + struct list_head list; +}; + struct intel_vgpu_mm { enum intel_gvt_mm_type type; struct intel_vgpu *vgpu; @@ -157,8 +163,7 @@ struct intel_vgpu_mm { } ppgtt_mm; struct { void *virtual_ggtt; - unsigned long last_partial_off; - u64 last_partial_data; + struct list_head partial_pte_list; } ggtt_mm; }; }; From 606a745944bc0ebd14f77dfc61ac7d6cb685cefe Mon Sep 17 00:00:00 2001 From: Xinyun Liu Date: Wed, 19 Sep 2018 15:28:53 +0800 Subject: [PATCH 017/356] drm/i915/gvt: correct mask setting for CSFE_CHICKEN1 CSFE_CHICKEN1(0x20d4) needs access with mask. This is caught in AcrnGT conformance check test: [drm:intel_gvt_vgpu_conformance_check] *ERROR* gvt: vgpu1 unconformance mmio 0x20d4:0x40004,0x4 Signed-off-by: Xinyun Liu Signed-off-by: Zhi Wang Signed-off-by: Zhenyu Wang --- drivers/gpu/drm/i915/gvt/mmio_context.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index e872f4847fbe..088a62ab2bc8 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -144,7 +144,7 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = { {RCS, GAMT_CHKN_BIT_REG, 0x0, false}, /* 0x4ab8 */ {RCS, GEN9_GAMT_ECO_REG_RW_IA, 0x0, false}, /* 0x4ab0 */ - {RCS, GEN9_CSFE_CHICKEN1_RCS, 0x0, false}, /* 0x20d4 */ + {RCS, GEN9_CSFE_CHICKEN1_RCS, 0xffff, false}, /* 0x20d4 */ {RCS, GEN8_GARBCNTL, 0x0, false}, /* 0xb004 */ {RCS, GEN7_FF_THREAD_MODE, 0x0, false}, /* 0x20a0 */ From 5e7154ff5e8e21dc9acac4f8dba7533552365374 Mon Sep 17 00:00:00 2001 From: Longhe Zheng Date: Tue, 30 Oct 2018 16:12:10 +0800 Subject: [PATCH 018/356] drm/i915/gvt: Handle values of EDP_PSR_IMR and EDP_PSR_IIR GVT-g only simulates DP port for guest and leaves EDP_PSR_IMR and EDP_PSR_IIR registers as default MMIO read/write. So guest won't get expected initial values of these registers when initializing the gpu driver, which results in following warning and logs. -------- Interrupt register 0x64838 is not zero: 0xffffffff WARNING: CPU: 1 PID: 157 at drivers/gpu/drm/i915/i915_irq.c:177 gen3_assert_iir_is_zero+0x38/0xa0 Call Trace: gen8_de_irq_postinstall+0xa7/0x400 gen8_irq_postinstall+0x27/0x80 drm_irq_install+0xbc/0x140 i915_driver_load+0xa9d/0xd50 -------- Because GVT-g does not handle EDP(embedded DP) simulation for guests, always set EDP_PSR_IMR and EDP_PSR_IIR to value 0. Signed-off-by: Longhe Zheng Signed-off-by: Zhenyu Wang --- drivers/gpu/drm/i915/gvt/handlers.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 94c1089ecf59..f9002cb1f2a3 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -1608,7 +1608,7 @@ static int bxt_gt_disp_pwron_write(struct intel_vgpu *vgpu, return 0; } -static int bxt_edp_psr_imr_iir_write(struct intel_vgpu *vgpu, +static int edp_psr_imr_iir_write(struct intel_vgpu *vgpu, unsigned int offset, void *p_data, unsigned int bytes) { vgpu_vreg(vgpu, offset) = 0; @@ -2613,6 +2613,9 @@ static int init_generic_mmio_info(struct intel_gvt *gvt) MMIO_DFH(_MMIO(0x1a178), D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); MMIO_DFH(_MMIO(0x1a17c), D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); MMIO_DFH(_MMIO(0x2217c), D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); + + MMIO_DH(EDP_PSR_IMR, D_BDW_PLUS, NULL, edp_psr_imr_iir_write); + MMIO_DH(EDP_PSR_IIR, D_BDW_PLUS, NULL, edp_psr_imr_iir_write); return 0; } @@ -3216,9 +3219,6 @@ static int init_bxt_mmio_info(struct intel_gvt *gvt) MMIO_D(HSW_TVIDEO_DIP_GCP(TRANSCODER_B), D_BXT); MMIO_D(HSW_TVIDEO_DIP_GCP(TRANSCODER_C), D_BXT); - MMIO_DH(EDP_PSR_IMR, D_BXT, NULL, bxt_edp_psr_imr_iir_write); - MMIO_DH(EDP_PSR_IIR, D_BXT, NULL, bxt_edp_psr_imr_iir_write); - MMIO_D(RC6_CTX_BASE, D_BXT); MMIO_D(GEN8_PUSHBUS_CONTROL, D_BXT); From 399474e4c1100bca264ed14fa3ad0d68fab484d8 Mon Sep 17 00:00:00 2001 From: Julian Sax Date: Wed, 24 Oct 2018 22:40:26 +0200 Subject: [PATCH 019/356] HID: i2c-hid: add Direkt-Tek DTLAPY133-1 to descriptor override This device uses the SIPODEV SP1064 touchpad, which does not supply descriptors, so it has to be added to the override list. Reported-by: Tim Aldridge Signed-off-by: Julian Sax Signed-off-by: Jiri Kosina --- drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c index 1d645c9ab417..9ca2fcc48b5a 100644 --- a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c +++ b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c @@ -330,6 +330,14 @@ static const struct dmi_system_id i2c_hid_dmi_desc_override_table[] = { }, .driver_data = (void *)&sipodev_desc }, + { + .ident = "Direkt-Tek DTLAPY133-1", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Direkt-Tek"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "DTLAPY133-1"), + }, + .driver_data = (void *)&sipodev_desc + }, { .ident = "Mediacom Flexbook Edge 11", .matches = { From 439cd39ea136d2c026805264d58a91f36b6b64ca Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Sat, 14 Jul 2018 21:59:43 +0200 Subject: [PATCH 020/356] netfilter: ipset: list:set: Decrease refcount synchronously on deletion and replace Commit 45040978c899 ("netfilter: ipset: Fix set:list type crash when flush/dump set in parallel") postponed decreasing set reference counters to the RCU callback. An 'ipset del' command can terminate before the RCU grace period is elapsed, and if sets are listed before then, the reference counter shown in userspace will be wrong: # ipset create h hash:ip; ipset create l list:set; ipset add l # ipset del l h; ipset list h Name: h Type: hash:ip Revision: 4 Header: family inet hashsize 1024 maxelem 65536 Size in memory: 88 References: 1 Number of entries: 0 Members: # sleep 1; ipset list h Name: h Type: hash:ip Revision: 4 Header: family inet hashsize 1024 maxelem 65536 Size in memory: 88 References: 0 Number of entries: 0 Members: Fix this by making the reference count update synchronous again. As a result, when sets are listed, ip_set_name_byindex() might now fetch a set whose reference count is already zero. Instead of relying on the reference count to protect against concurrent set renaming, grab ip_set_ref_lock as reader and copy the name, while holding the same lock in ip_set_rename() as writer instead. Reported-by: Li Shuang Fixes: 45040978c899 ("netfilter: ipset: Fix set:list type crash when flush/dump set in parallel") Signed-off-by: Stefano Brivio Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 2 +- net/netfilter/ipset/ip_set_core.c | 23 +++++++++++------------ net/netfilter/ipset/ip_set_list_set.c | 17 +++++++++++------ 3 files changed, 23 insertions(+), 19 deletions(-) diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 34fc80f3eb90..1d100efe74ec 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -314,7 +314,7 @@ enum { extern ip_set_id_t ip_set_get_byname(struct net *net, const char *name, struct ip_set **set); extern void ip_set_put_byindex(struct net *net, ip_set_id_t index); -extern const char *ip_set_name_byindex(struct net *net, ip_set_id_t index); +extern void ip_set_name_byindex(struct net *net, ip_set_id_t index, char *name); extern ip_set_id_t ip_set_nfnl_get_byindex(struct net *net, ip_set_id_t index); extern void ip_set_nfnl_put(struct net *net, ip_set_id_t index); diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index bc4bd247bb7d..fa15a831aeee 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -693,21 +693,20 @@ ip_set_put_byindex(struct net *net, ip_set_id_t index) EXPORT_SYMBOL_GPL(ip_set_put_byindex); /* Get the name of a set behind a set index. - * We assume the set is referenced, so it does exist and - * can't be destroyed. The set cannot be renamed due to - * the referencing either. - * + * Set itself is protected by RCU, but its name isn't: to protect against + * renaming, grab ip_set_ref_lock as reader (see ip_set_rename()) and copy the + * name. */ -const char * -ip_set_name_byindex(struct net *net, ip_set_id_t index) +void +ip_set_name_byindex(struct net *net, ip_set_id_t index, char *name) { - const struct ip_set *set = ip_set_rcu_get(net, index); + struct ip_set *set = ip_set_rcu_get(net, index); BUG_ON(!set); - BUG_ON(set->ref == 0); - /* Referenced, so it's safe */ - return set->name; + read_lock_bh(&ip_set_ref_lock); + strncpy(name, set->name, IPSET_MAXNAMELEN); + read_unlock_bh(&ip_set_ref_lock); } EXPORT_SYMBOL_GPL(ip_set_name_byindex); @@ -1153,7 +1152,7 @@ static int ip_set_rename(struct net *net, struct sock *ctnl, if (!set) return -ENOENT; - read_lock_bh(&ip_set_ref_lock); + write_lock_bh(&ip_set_ref_lock); if (set->ref != 0) { ret = -IPSET_ERR_REFERENCED; goto out; @@ -1170,7 +1169,7 @@ static int ip_set_rename(struct net *net, struct sock *ctnl, strncpy(set->name, name2, IPSET_MAXNAMELEN); out: - read_unlock_bh(&ip_set_ref_lock); + write_unlock_bh(&ip_set_ref_lock); return ret; } diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 072a658fde04..4eef55da0878 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -148,9 +148,7 @@ __list_set_del_rcu(struct rcu_head * rcu) { struct set_elem *e = container_of(rcu, struct set_elem, rcu); struct ip_set *set = e->set; - struct list_set *map = set->data; - ip_set_put_byindex(map->net, e->id); ip_set_ext_destroy(set, e); kfree(e); } @@ -158,15 +156,21 @@ __list_set_del_rcu(struct rcu_head * rcu) static inline void list_set_del(struct ip_set *set, struct set_elem *e) { + struct list_set *map = set->data; + set->elements--; list_del_rcu(&e->list); + ip_set_put_byindex(map->net, e->id); call_rcu(&e->rcu, __list_set_del_rcu); } static inline void -list_set_replace(struct set_elem *e, struct set_elem *old) +list_set_replace(struct ip_set *set, struct set_elem *e, struct set_elem *old) { + struct list_set *map = set->data; + list_replace_rcu(&old->list, &e->list); + ip_set_put_byindex(map->net, old->id); call_rcu(&old->rcu, __list_set_del_rcu); } @@ -298,7 +302,7 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext, INIT_LIST_HEAD(&e->list); list_set_init_extensions(set, ext, e); if (n) - list_set_replace(e, n); + list_set_replace(set, e, n); else if (next) list_add_tail_rcu(&e->list, &next->list); else if (prev) @@ -486,6 +490,7 @@ list_set_list(const struct ip_set *set, const struct list_set *map = set->data; struct nlattr *atd, *nested; u32 i = 0, first = cb->args[IPSET_CB_ARG0]; + char name[IPSET_MAXNAMELEN]; struct set_elem *e; int ret = 0; @@ -504,8 +509,8 @@ list_set_list(const struct ip_set *set, nested = ipset_nest_start(skb, IPSET_ATTR_DATA); if (!nested) goto nla_put_failure; - if (nla_put_string(skb, IPSET_ATTR_NAME, - ip_set_name_byindex(map->net, e->id))) + ip_set_name_byindex(map->net, e->id, name); + if (nla_put_string(skb, IPSET_ATTR_NAME, name)) goto nla_put_failure; if (ip_set_put_extensions(skb, set, e, true)) goto nla_put_failure; From 886503f34d63e681662057448819edb5b1057a97 Mon Sep 17 00:00:00 2001 From: Eric Westbrook Date: Tue, 28 Aug 2018 15:14:42 -0600 Subject: [PATCH 021/356] netfilter: ipset: actually allow allowable CIDR 0 in hash:net,port,net Allow /0 as advertised for hash:net,port,net sets. For "hash:net,port,net", ipset(8) says that "either subnet is permitted to be a /0 should you wish to match port between all destinations." Make that statement true. Before: # ipset create cidrzero hash:net,port,net # ipset add cidrzero 0.0.0.0/0,12345,0.0.0.0/0 ipset v6.34: The value of the CIDR parameter of the IP address is invalid # ipset create cidrzero6 hash:net,port,net family inet6 # ipset add cidrzero6 ::/0,12345,::/0 ipset v6.34: The value of the CIDR parameter of the IP address is invalid After: # ipset create cidrzero hash:net,port,net # ipset add cidrzero 0.0.0.0/0,12345,0.0.0.0/0 # ipset test cidrzero 192.168.205.129,12345,172.16.205.129 192.168.205.129,tcp:12345,172.16.205.129 is in set cidrzero. # ipset create cidrzero6 hash:net,port,net family inet6 # ipset add cidrzero6 ::/0,12345,::/0 # ipset test cidrzero6 fe80::1,12345,ff00::1 fe80::1,tcp:12345,ff00::1 is in set cidrzero6. See also: https://bugzilla.kernel.org/show_bug.cgi?id=200897 https://github.com/ewestbrook/linux/commit/df7ff6efb0934ab6acc11f003ff1a7580d6c1d9c Signed-off-by: Eric Westbrook Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipset/ip_set_hash_netportnet.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index d391485a6acd..613e18e720a4 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -213,13 +213,13 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_CIDR]) { e.cidr[0] = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!e.cidr[0] || e.cidr[0] > HOST_MASK) + if (e.cidr[0] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } if (tb[IPSET_ATTR_CIDR2]) { e.cidr[1] = nla_get_u8(tb[IPSET_ATTR_CIDR2]); - if (!e.cidr[1] || e.cidr[1] > HOST_MASK) + if (e.cidr[1] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } @@ -493,13 +493,13 @@ hash_netportnet6_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_CIDR]) { e.cidr[0] = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!e.cidr[0] || e.cidr[0] > HOST_MASK) + if (e.cidr[0] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } if (tb[IPSET_ATTR_CIDR2]) { e.cidr[1] = nla_get_u8(tb[IPSET_ATTR_CIDR2]); - if (!e.cidr[1] || e.cidr[1] > HOST_MASK) + if (e.cidr[1] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } From ed956f3947a01ff9875cd908d7c1ef1fe7f47bf0 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Mon, 22 Oct 2018 23:30:40 +0200 Subject: [PATCH 022/356] netfilter: ipset: fix ip_set_list allocation failure ip_set_create() and ip_set_net_init() attempt to allocate physically contiguous memory for ip_set_list. If memory is fragmented, the allocations could easily fail: vzctl: page allocation failure: order:7, mode:0xc0d0 Call Trace: dump_stack+0x19/0x1b warn_alloc_failed+0x110/0x180 __alloc_pages_nodemask+0x7bf/0xc60 alloc_pages_current+0x98/0x110 kmalloc_order+0x18/0x40 kmalloc_order_trace+0x26/0xa0 __kmalloc+0x279/0x290 ip_set_net_init+0x4b/0x90 [ip_set] ops_init+0x3b/0xb0 setup_net+0xbb/0x170 copy_net_ns+0xf1/0x1c0 create_new_namespaces+0xf9/0x180 copy_namespaces+0x8e/0xd0 copy_process+0xb61/0x1a00 do_fork+0x91/0x320 Use kvcalloc() to fallback to 0-order allocations if high order page isn't available. Signed-off-by: Andrey Ryabinin Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipset/ip_set_core.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index fa15a831aeee..68db946df151 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -960,7 +960,7 @@ static int ip_set_create(struct net *net, struct sock *ctnl, /* Wraparound */ goto cleanup; - list = kcalloc(i, sizeof(struct ip_set *), GFP_KERNEL); + list = kvcalloc(i, sizeof(struct ip_set *), GFP_KERNEL); if (!list) goto cleanup; /* nfnl mutex is held, both lists are valid */ @@ -972,7 +972,7 @@ static int ip_set_create(struct net *net, struct sock *ctnl, /* Use new list */ index = inst->ip_set_max; inst->ip_set_max = i; - kfree(tmp); + kvfree(tmp); ret = 0; } else if (ret) { goto cleanup; @@ -2058,7 +2058,7 @@ ip_set_net_init(struct net *net) if (inst->ip_set_max >= IPSET_INVALID_ID) inst->ip_set_max = IPSET_INVALID_ID - 1; - list = kcalloc(inst->ip_set_max, sizeof(struct ip_set *), GFP_KERNEL); + list = kvcalloc(inst->ip_set_max, sizeof(struct ip_set *), GFP_KERNEL); if (!list) return -ENOMEM; inst->is_deleted = false; @@ -2086,7 +2086,7 @@ ip_set_net_exit(struct net *net) } } nfnl_unlock(NFNL_SUBSYS_IPSET); - kfree(rcu_dereference_protected(inst->ip_set_list, 1)); + kvfree(rcu_dereference_protected(inst->ip_set_list, 1)); } static struct pernet_operations ip_set_net_ops = { From 51f5fd2e4615dcdc25cd7f9d19b7b27eb9ecdac7 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 31 Oct 2018 17:44:08 +0000 Subject: [PATCH 023/356] tools headers barrier: Fix arm64 tools build failure wrt smp_load_{acquire,release} Cheers for reporting this. I managed to reproduce the build failure with gcc version 6.3.0 20170516 (Debian 6.3.0-18+deb9u1). The code in question is the arm64 versions of smp_load_acquire() and smp_store_release(). Unlike other architectures, these are not built around READ_ONCE() and WRITE_ONCE() since we have instructions we can use instead of fences. Bringing our macros up-to-date with those (i.e. tweaking the union initialisation and using the special "uXX_alias_t" types) appears to fix the issue for me. Committer notes: Testing it in the systems previously failing: # time dm android-ndk:r12b-arm \ android-ndk:r15c-arm \ debian:experimental-x-arm64 \ ubuntu:14.04.4-x-linaro-arm64 \ ubuntu:16.04-x-arm \ ubuntu:16.04-x-arm64 \ ubuntu:18.04-x-arm \ ubuntu:18.04-x-arm64 1 android-ndk:r12b-arm : Ok arm-linux-androideabi-gcc (GCC) 4.9.x 20150123 (prerelease) 2 android-ndk:r15c-arm : Ok arm-linux-androideabi-gcc (GCC) 4.9.x 20150123 (prerelease) 3 debian:experimental-x-arm64 : Ok aarch64-linux-gnu-gcc (Debian 8.2.0-7) 8.2.0 4 ubuntu:14.04.4-x-linaro-arm64 : Ok aarch64-linux-gnu-gcc (Linaro GCC 5.5-2017.10) 5.5.0 5 ubuntu:16.04-x-arm : Ok arm-linux-gnueabihf-gcc (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 6 ubuntu:16.04-x-arm64 : Ok aarch64-linux-gnu-gcc (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 7 ubuntu:18.04-x-arm : Ok arm-linux-gnueabihf-gcc (Ubuntu/Linaro 7.3.0-27ubuntu1~18.04) 7.3.0 8 ubuntu:18.04-x-arm64 : Ok aarch64-linux-gnu-gcc (Ubuntu/Linaro 7.3.0-27ubuntu1~18.04) 7.3.0 Reported-by: Arnaldo Carvalho de Melo Signed-off-by: Will Deacon Tested-by: Arnaldo Carvalho de Melo Tested-by: Daniel Borkmann Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20181031174408.GA27871@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/arm64/include/asm/barrier.h | 133 +++++++++++++------------ 1 file changed, 67 insertions(+), 66 deletions(-) diff --git a/tools/arch/arm64/include/asm/barrier.h b/tools/arch/arm64/include/asm/barrier.h index 12835ea0e417..378c051fa177 100644 --- a/tools/arch/arm64/include/asm/barrier.h +++ b/tools/arch/arm64/include/asm/barrier.h @@ -14,74 +14,75 @@ #define wmb() asm volatile("dmb ishst" ::: "memory") #define rmb() asm volatile("dmb ishld" ::: "memory") -#define smp_store_release(p, v) \ -do { \ - union { typeof(*p) __val; char __c[1]; } __u = \ - { .__val = (__force typeof(*p)) (v) }; \ - \ - switch (sizeof(*p)) { \ - case 1: \ - asm volatile ("stlrb %w1, %0" \ - : "=Q" (*p) \ - : "r" (*(__u8 *)__u.__c) \ - : "memory"); \ - break; \ - case 2: \ - asm volatile ("stlrh %w1, %0" \ - : "=Q" (*p) \ - : "r" (*(__u16 *)__u.__c) \ - : "memory"); \ - break; \ - case 4: \ - asm volatile ("stlr %w1, %0" \ - : "=Q" (*p) \ - : "r" (*(__u32 *)__u.__c) \ - : "memory"); \ - break; \ - case 8: \ - asm volatile ("stlr %1, %0" \ - : "=Q" (*p) \ - : "r" (*(__u64 *)__u.__c) \ - : "memory"); \ - break; \ - default: \ - /* Only to shut up gcc ... */ \ - mb(); \ - break; \ - } \ +#define smp_store_release(p, v) \ +do { \ + union { typeof(*p) __val; char __c[1]; } __u = \ + { .__val = (v) }; \ + \ + switch (sizeof(*p)) { \ + case 1: \ + asm volatile ("stlrb %w1, %0" \ + : "=Q" (*p) \ + : "r" (*(__u8_alias_t *)__u.__c) \ + : "memory"); \ + break; \ + case 2: \ + asm volatile ("stlrh %w1, %0" \ + : "=Q" (*p) \ + : "r" (*(__u16_alias_t *)__u.__c) \ + : "memory"); \ + break; \ + case 4: \ + asm volatile ("stlr %w1, %0" \ + : "=Q" (*p) \ + : "r" (*(__u32_alias_t *)__u.__c) \ + : "memory"); \ + break; \ + case 8: \ + asm volatile ("stlr %1, %0" \ + : "=Q" (*p) \ + : "r" (*(__u64_alias_t *)__u.__c) \ + : "memory"); \ + break; \ + default: \ + /* Only to shut up gcc ... */ \ + mb(); \ + break; \ + } \ } while (0) -#define smp_load_acquire(p) \ -({ \ - union { typeof(*p) __val; char __c[1]; } __u; \ - \ - switch (sizeof(*p)) { \ - case 1: \ - asm volatile ("ldarb %w0, %1" \ - : "=r" (*(__u8 *)__u.__c) \ - : "Q" (*p) : "memory"); \ - break; \ - case 2: \ - asm volatile ("ldarh %w0, %1" \ - : "=r" (*(__u16 *)__u.__c) \ - : "Q" (*p) : "memory"); \ - break; \ - case 4: \ - asm volatile ("ldar %w0, %1" \ - : "=r" (*(__u32 *)__u.__c) \ - : "Q" (*p) : "memory"); \ - break; \ - case 8: \ - asm volatile ("ldar %0, %1" \ - : "=r" (*(__u64 *)__u.__c) \ - : "Q" (*p) : "memory"); \ - break; \ - default: \ - /* Only to shut up gcc ... */ \ - mb(); \ - break; \ - } \ - __u.__val; \ +#define smp_load_acquire(p) \ +({ \ + union { typeof(*p) __val; char __c[1]; } __u = \ + { .__c = { 0 } }; \ + \ + switch (sizeof(*p)) { \ + case 1: \ + asm volatile ("ldarb %w0, %1" \ + : "=r" (*(__u8_alias_t *)__u.__c) \ + : "Q" (*p) : "memory"); \ + break; \ + case 2: \ + asm volatile ("ldarh %w0, %1" \ + : "=r" (*(__u16_alias_t *)__u.__c) \ + : "Q" (*p) : "memory"); \ + break; \ + case 4: \ + asm volatile ("ldar %w0, %1" \ + : "=r" (*(__u32_alias_t *)__u.__c) \ + : "Q" (*p) : "memory"); \ + break; \ + case 8: \ + asm volatile ("ldar %0, %1" \ + : "=r" (*(__u64_alias_t *)__u.__c) \ + : "Q" (*p) : "memory"); \ + break; \ + default: \ + /* Only to shut up gcc ... */ \ + mb(); \ + break; \ + } \ + __u.__val; \ }) #endif /* _TOOLS_LINUX_ASM_AARCH64_BARRIER_H */ From febf8a3712e4209b7e650b37b3b240a2b387794d Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 1 Nov 2018 10:34:34 -0300 Subject: [PATCH 024/356] perf examples bpf: Start augmenting raw_syscalls:sys_{start,exit} The previous approach of attaching to each syscall showed how it is possible to augment tracepoints and use that augmentation, pointer payloads, in the existing beautifiers in 'perf trace', but for a more general solution we now will try to augment the main raw_syscalls:sys_{enter,exit} syscalls, and then pass instructions in maps so that it knows which syscalls and which pointer contents, and how many bytes for each of the arguments should be copied. Start with just the bare minimum to collect what is provided by those two tracepoints via the __augmented_syscalls__ map + bpf-output perf event, which results in perf trace showing them without connecting enter+exit: # perf trace -e tools/perf/examples/bpf/augmented_raw_syscalls.c sleep 1 0.000 sleep/11563 raw_syscalls:sys_exit:NR 59 = 0 0.019 ( ): sleep/11563 brk() ... 0.021 sleep/11563 raw_syscalls:sys_exit:NR 12 = 94682642325504 0.033 ( ): sleep/11563 access(filename:, mode: R) ... 0.037 sleep/11563 raw_syscalls:sys_exit:NR 21 = -2 0.041 ( ): sleep/11563 openat(dfd: CWD, filename: , flags: CLOEXEC) ... 0.044 sleep/11563 raw_syscalls:sys_exit:NR 257 = 3 0.045 ( ): sleep/11563 fstat(fd: 3, statbuf: 0x7ffdbf7119b0) ... 0.046 sleep/11563 raw_syscalls:sys_exit:NR 5 = 0 0.047 ( ): sleep/11563 mmap(len: 103334, prot: READ, flags: PRIVATE, fd: 3) ... 0.049 sleep/11563 raw_syscalls:sys_exit:NR 9 = 140196285493248 0.050 ( ): sleep/11563 close(fd: 3) ... 0.051 sleep/11563 raw_syscalls:sys_exit:NR 3 = 0 0.059 ( ): sleep/11563 openat(dfd: CWD, filename: , flags: CLOEXEC) ... 0.062 sleep/11563 raw_syscalls:sys_exit:NR 257 = 3 0.063 ( ): sleep/11563 read(fd: 3, buf: 0x7ffdbf711b78, count: 832) ... 0.065 sleep/11563 raw_syscalls:sys_exit:NR 0 = 832 0.066 ( ): sleep/11563 fstat(fd: 3, statbuf: 0x7ffdbf711a10) ... 0.067 sleep/11563 raw_syscalls:sys_exit:NR 5 = 0 0.068 ( ): sleep/11563 mmap(len: 8192, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS) ... 0.070 sleep/11563 raw_syscalls:sys_exit:NR 9 = 140196285485056 0.073 ( ): sleep/11563 mmap(len: 3889792, prot: EXEC|READ, flags: PRIVATE|DENYWRITE, fd: 3) ... 0.076 sleep/11563 raw_syscalls:sys_exit:NR 9 = 140196279463936 0.077 ( ): sleep/11563 mprotect(start: 0x7f81fd8a8000, len: 2093056) ... 0.083 sleep/11563 raw_syscalls:sys_exit:NR 10 = 0 0.084 ( ): sleep/11563 mmap(addr: 0x7f81fdaa7000, len: 24576, prot: READ|WRITE, flags: PRIVATE|FIXED|DENYWRITE, fd: 3, off: 1753088) ... 0.088 sleep/11563 raw_syscalls:sys_exit:NR 9 = 140196283314176 0.091 ( ): sleep/11563 mmap(addr: 0x7f81fdaad000, len: 14976, prot: READ|WRITE, flags: PRIVATE|FIXED|ANONYMOUS) ... 0.093 sleep/11563 raw_syscalls:sys_exit:NR 9 = 140196283338752 0.097 ( ): sleep/11563 close(fd: 3) ... 0.098 sleep/11563 raw_syscalls:sys_exit:NR 3 = 0 0.107 ( ): sleep/11563 arch_prctl(option: 4098, arg2: 140196285490432) ... 0.108 sleep/11563 raw_syscalls:sys_exit:NR 158 = 0 0.143 ( ): sleep/11563 mprotect(start: 0x7f81fdaa7000, len: 16384, prot: READ) ... 0.146 sleep/11563 raw_syscalls:sys_exit:NR 10 = 0 0.157 ( ): sleep/11563 mprotect(start: 0x561d037e7000, len: 4096, prot: READ) ... 0.160 sleep/11563 raw_syscalls:sys_exit:NR 10 = 0 0.163 ( ): sleep/11563 mprotect(start: 0x7f81fdcd5000, len: 4096, prot: READ) ... 0.165 sleep/11563 raw_syscalls:sys_exit:NR 10 = 0 0.166 ( ): sleep/11563 munmap(addr: 0x7f81fdcbb000, len: 103334) ... 0.174 sleep/11563 raw_syscalls:sys_exit:NR 11 = 0 0.216 ( ): sleep/11563 brk() ... 0.217 sleep/11563 raw_syscalls:sys_exit:NR 12 = 94682642325504 0.217 ( ): sleep/11563 brk(brk: 0x561d05453000) ... 0.219 sleep/11563 raw_syscalls:sys_exit:NR 12 = 94682642460672 0.220 ( ): sleep/11563 brk() ... 0.221 sleep/11563 raw_syscalls:sys_exit:NR 12 = 94682642460672 0.224 ( ): sleep/11563 open(filename: , flags: CLOEXEC) ... 0.228 sleep/11563 raw_syscalls:sys_exit:NR 2 = 3 0.229 ( ): sleep/11563 fstat(fd: 3, statbuf: 0x7f81fdaacaa0) ... 0.230 sleep/11563 raw_syscalls:sys_exit:NR 5 = 0 0.231 ( ): sleep/11563 mmap(len: 113045344, prot: READ, flags: PRIVATE, fd: 3) ... 0.234 sleep/11563 raw_syscalls:sys_exit:NR 9 = 140196166418432 0.237 ( ): sleep/11563 close(fd: 3) ... 0.238 sleep/11563 raw_syscalls:sys_exit:NR 3 = 0 0.262 ( ): sleep/11563 nanosleep(rqtp: 0x7ffdbf7126f0) ... 1000.399 sleep/11563 raw_syscalls:sys_exit:NR 35 = 0 1000.440 ( ): sleep/11563 close(fd: 1) ... 1000.447 sleep/11563 raw_syscalls:sys_exit:NR 3 = 0 1000.454 ( ): sleep/11563 close(fd: 2) ... 1000.468 ( ): sleep/11563 exit_group( ) # In the next csets we'll connect those events to the existing enter/exit raw_syscalls handlers in 'perf trace', just like we did with the syscalls:sys_{enter,exit}_* tracepoints. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-5nl8l4hx1tl9pqdx65nkp6pw@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- .../examples/bpf/augmented_raw_syscalls.c | 59 +++++++++++++++++++ 1 file changed, 59 insertions(+) create mode 100644 tools/perf/examples/bpf/augmented_raw_syscalls.c diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c new file mode 100644 index 000000000000..cde91c34b101 --- /dev/null +++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Augment the raw_syscalls tracepoints with the contents of the pointer arguments. + * + * Test it with: + * + * perf trace -e tools/perf/examples/bpf/augmented_raw_syscalls.c cat /etc/passwd > /dev/null + * + * This exactly matches what is marshalled into the raw_syscall:sys_enter + * payload expected by the 'perf trace' beautifiers. + * + * For now it just uses the existing tracepoint augmentation code in 'perf + * trace', in the next csets we'll hook up these with the sys_enter/sys_exit + * code that will combine entry/exit in a strace like way. + */ + +#include +#include + +/* bpf-output associated map */ +struct bpf_map SEC("maps") __augmented_syscalls__ = { + .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(u32), + .max_entries = __NR_CPUS__, +}; + +struct syscall_enter_args { + unsigned long long common_tp_fields; + long syscall_nr; + unsigned long args[6]; +}; + +struct syscall_exit_args { + unsigned long long common_tp_fields; + long syscall_nr; + long ret; +}; + +SEC("raw_syscalls:sys_enter") +int sys_enter(struct syscall_enter_args *args) +{ + struct { + struct syscall_enter_args args; + } augmented_args; + unsigned int len = sizeof(augmented_args); + + probe_read(&augmented_args.args, sizeof(augmented_args.args), args); + perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len); + return 0; +} + +SEC("raw_syscalls:sys_exit") +int sys_exit(struct syscall_exit_args *args) +{ + return 1; /* 0 as soon as we start copying data returned by the kernel, e.g. 'read' */ +} + +license(GPL); From 3c5e3dabf3722a883227623a4adf61976c2224ff Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 1 Nov 2018 13:50:35 -0300 Subject: [PATCH 025/356] perf trace: When augmenting raw_syscalls plug raw_syscalls:sys_exit too With just this commit we get to support all syscalls via hooking raw_syscalls:sys_{enter,exit} to the trace__sys_{enter,exit} routines to combine, strace-like, those tracepoints. # trace -e tools/perf/examples/bpf/augmented_raw_syscalls.c sleep 1 ? ( ): sleep/31680 ... [continued]: execve()) = 0 0.043 ( 0.004 ms): sleep/31680 brk() = 0x55652a851000 0.070 ( 0.009 ms): sleep/31680 access(filename:, mode: R) = -1 ENOENT No such file or directory 0.087 ( 0.006 ms): sleep/31680 openat(dfd: CWD, filename: , flags: CLOEXEC) = 3 0.096 ( 0.003 ms): sleep/31680 fstat(fd: 3, statbuf: 0x7ffc5269e190) = 0 0.101 ( 0.005 ms): sleep/31680 mmap(len: 103334, prot: READ, flags: PRIVATE, fd: 3) = 0x7f709c239000 0.109 ( 0.002 ms): sleep/31680 close(fd: 3) = 0 0.126 ( 0.006 ms): sleep/31680 openat(dfd: CWD, filename: , flags: CLOEXEC) = 3 0.135 ( 0.003 ms): sleep/31680 read(fd: 3, buf: 0x7ffc5269e358, count: 832) = 832 0.141 ( 0.002 ms): sleep/31680 fstat(fd: 3, statbuf: 0x7ffc5269e1f0) = 0 0.146 ( 0.005 ms): sleep/31680 mmap(len: 8192, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS) = 0x7f709c237000 0.159 ( 0.007 ms): sleep/31680 mmap(len: 3889792, prot: EXEC|READ, flags: PRIVATE|DENYWRITE, fd: 3) = 0x7f709bc79000 0.168 ( 0.009 ms): sleep/31680 mprotect(start: 0x7f709be26000, len: 2093056) = 0 0.179 ( 0.010 ms): sleep/31680 mmap(addr: 0x7f709c025000, len: 24576, prot: READ|WRITE, flags: PRIVATE|FIXED|DENYWRITE, fd: 3, off: 1753088) = 0x7f709c025000 0.196 ( 0.005 ms): sleep/31680 mmap(addr: 0x7f709c02b000, len: 14976, prot: READ|WRITE, flags: PRIVATE|FIXED|ANONYMOUS) = 0x7f709c02b000 0.210 ( 0.002 ms): sleep/31680 close(fd: 3) = 0 0.230 ( 0.002 ms): sleep/31680 arch_prctl(option: 4098, arg2: 140121632638208) = 0 0.306 ( 0.009 ms): sleep/31680 mprotect(start: 0x7f709c025000, len: 16384, prot: READ) = 0 0.338 ( 0.005 ms): sleep/31680 mprotect(start: 0x556529607000, len: 4096, prot: READ) = 0 0.348 ( 0.005 ms): sleep/31680 mprotect(start: 0x7f709c253000, len: 4096, prot: READ) = 0 0.356 ( 0.019 ms): sleep/31680 munmap(addr: 0x7f709c239000, len: 103334) = 0 0.463 ( 0.002 ms): sleep/31680 brk() = 0x55652a851000 0.468 ( 0.004 ms): sleep/31680 brk(brk: 0x55652a872000) = 0x55652a872000 0.474 ( 0.002 ms): sleep/31680 brk() = 0x55652a872000 0.484 ( 0.008 ms): sleep/31680 open(filename: , flags: CLOEXEC) = 3 0.497 ( 0.002 ms): sleep/31680 fstat(fd: 3, statbuf: 0x7f709c02aaa0) = 0 0.501 ( 0.006 ms): sleep/31680 mmap(len: 113045344, prot: READ, flags: PRIVATE, fd: 3) = 0x7f70950aa000 0.514 ( 0.002 ms): sleep/31680 close(fd: 3) = 0 0.554 (1000.140 ms): sleep/31680 nanosleep(rqtp: 0x7ffc5269eed0) = 0 1000.734 ( 0.007 ms): sleep/31680 close(fd: 1) = 0 1000.748 ( 0.004 ms): sleep/31680 close(fd: 2) = 0 1000.769 ( ): sleep/31680 exit_group() # Now to allow selecting which syscalls should be traced, using a map. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-votqqmqhag8e1i9mgyzfez3o@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index dc8a6c4986ce..f582ca575883 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -3501,7 +3501,8 @@ int cmd_trace(int argc, const char **argv) evsel->handler = trace__sys_enter; evlist__for_each_entry(trace.evlist, evsel) { - if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_")) { + if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_") || + strcmp(perf_evsel__name(evsel), "raw_syscalls:sys_exit") == 0) { perf_evsel__init_augmented_syscall_tp(evsel); perf_evsel__init_augmented_syscall_tp_ret(evsel); evsel->handler = trace__sys_exit; From 7de414a9dd91426318df7b63da024b2b07e53df5 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 1 Nov 2018 12:02:37 -0700 Subject: [PATCH 026/356] net: drop skb on failure in ip_check_defrag() Most callers of pskb_trim_rcsum() simply drop the skb when it fails, however, ip_check_defrag() still continues to pass the skb up to stack. This is suspicious. In ip_check_defrag(), after we learn the skb is an IP fragment, passing the skb to callers makes no sense, because callers expect fragments are defrag'ed on success. So, dropping the skb when we can't defrag it is reasonable. Note, prior to commit 88078d98d1bb, this is not a big problem as checksum will be fixed up anyway. After it, the checksum is not correct on failure. Found this during code review. Fixes: 88078d98d1bb ("net: pskb_trim_rcsum() and CHECKSUM_COMPLETE are friends") Cc: Eric Dumazet Signed-off-by: Cong Wang Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/ip_fragment.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 9b0158fa431f..d6ee343fdb86 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -722,10 +722,14 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user) if (ip_is_fragment(&iph)) { skb = skb_share_check(skb, GFP_ATOMIC); if (skb) { - if (!pskb_may_pull(skb, netoff + iph.ihl * 4)) - return skb; - if (pskb_trim_rcsum(skb, netoff + len)) - return skb; + if (!pskb_may_pull(skb, netoff + iph.ihl * 4)) { + kfree_skb(skb); + return NULL; + } + if (pskb_trim_rcsum(skb, netoff + len)) { + kfree_skb(skb); + return NULL; + } memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); if (ip_defrag(net, skb, user)) return NULL; From a8874e7e8a8896f2b6c641f4b8e2473eafd35204 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Wed, 31 Oct 2018 12:11:48 +0100 Subject: [PATCH 027/356] mm: make the __PAGETABLE_PxD_FOLDED defines non-empty Change the currently empty defines for __PAGETABLE_PMD_FOLDED, __PAGETABLE_PUD_FOLDED and __PAGETABLE_P4D_FOLDED to return 1. This makes it possible to use __is_defined() to test if the preprocessor define exists. Acked-by: Kirill A. Shutemov Signed-off-by: Martin Schwidefsky --- arch/arm/include/asm/pgtable-2level.h | 2 +- arch/m68k/include/asm/pgtable_mm.h | 4 ++-- arch/microblaze/include/asm/pgtable.h | 2 +- arch/nds32/include/asm/pgtable.h | 2 +- arch/parisc/include/asm/pgtable.h | 2 +- include/asm-generic/4level-fixup.h | 2 +- include/asm-generic/5level-fixup.h | 2 +- include/asm-generic/pgtable-nop4d-hack.h | 2 +- include/asm-generic/pgtable-nop4d.h | 2 +- include/asm-generic/pgtable-nopmd.h | 2 +- include/asm-generic/pgtable-nopud.h | 2 +- 11 files changed, 12 insertions(+), 12 deletions(-) diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h index 92fd2c8a9af0..12659ce5c1f3 100644 --- a/arch/arm/include/asm/pgtable-2level.h +++ b/arch/arm/include/asm/pgtable-2level.h @@ -10,7 +10,7 @@ #ifndef _ASM_PGTABLE_2LEVEL_H #define _ASM_PGTABLE_2LEVEL_H -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 /* * Hardware-wise, we have a two level page table structure, where the first diff --git a/arch/m68k/include/asm/pgtable_mm.h b/arch/m68k/include/asm/pgtable_mm.h index 6181e4134483..fe3ddd73a0cc 100644 --- a/arch/m68k/include/asm/pgtable_mm.h +++ b/arch/m68k/include/asm/pgtable_mm.h @@ -55,12 +55,12 @@ */ #ifdef CONFIG_SUN3 #define PTRS_PER_PTE 16 -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 #define PTRS_PER_PMD 1 #define PTRS_PER_PGD 2048 #elif defined(CONFIG_COLDFIRE) #define PTRS_PER_PTE 512 -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 #define PTRS_PER_PMD 1 #define PTRS_PER_PGD 1024 #else diff --git a/arch/microblaze/include/asm/pgtable.h b/arch/microblaze/include/asm/pgtable.h index f64ebb9c9a41..e14b6621c933 100644 --- a/arch/microblaze/include/asm/pgtable.h +++ b/arch/microblaze/include/asm/pgtable.h @@ -63,7 +63,7 @@ extern int mem_init_done; #include -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 #ifdef __KERNEL__ #ifndef __ASSEMBLY__ diff --git a/arch/nds32/include/asm/pgtable.h b/arch/nds32/include/asm/pgtable.h index d3e19a55cf53..9f52db930c00 100644 --- a/arch/nds32/include/asm/pgtable.h +++ b/arch/nds32/include/asm/pgtable.h @@ -4,7 +4,7 @@ #ifndef _ASMNDS32_PGTABLE_H #define _ASMNDS32_PGTABLE_H -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 #include #include diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index b941ac7d4e70..c7bb74e22436 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -111,7 +111,7 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) #if CONFIG_PGTABLE_LEVELS == 3 #define BITS_PER_PMD (PAGE_SHIFT + PMD_ORDER - BITS_PER_PMD_ENTRY) #else -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 #define BITS_PER_PMD 0 #endif #define PTRS_PER_PMD (1UL << BITS_PER_PMD) diff --git a/include/asm-generic/4level-fixup.h b/include/asm-generic/4level-fixup.h index 89f3b03b1445..e3667c9a33a5 100644 --- a/include/asm-generic/4level-fixup.h +++ b/include/asm-generic/4level-fixup.h @@ -3,7 +3,7 @@ #define _4LEVEL_FIXUP_H #define __ARCH_HAS_4LEVEL_HACK -#define __PAGETABLE_PUD_FOLDED +#define __PAGETABLE_PUD_FOLDED 1 #define PUD_SHIFT PGDIR_SHIFT #define PUD_SIZE PGDIR_SIZE diff --git a/include/asm-generic/5level-fixup.h b/include/asm-generic/5level-fixup.h index 9c2e0708eb82..73474bb52344 100644 --- a/include/asm-generic/5level-fixup.h +++ b/include/asm-generic/5level-fixup.h @@ -3,7 +3,7 @@ #define _5LEVEL_FIXUP_H #define __ARCH_HAS_5LEVEL_HACK -#define __PAGETABLE_P4D_FOLDED +#define __PAGETABLE_P4D_FOLDED 1 #define P4D_SHIFT PGDIR_SHIFT #define P4D_SIZE PGDIR_SIZE diff --git a/include/asm-generic/pgtable-nop4d-hack.h b/include/asm-generic/pgtable-nop4d-hack.h index 0c34215263b8..1d6dd38c0e5e 100644 --- a/include/asm-generic/pgtable-nop4d-hack.h +++ b/include/asm-generic/pgtable-nop4d-hack.h @@ -5,7 +5,7 @@ #ifndef __ASSEMBLY__ #include -#define __PAGETABLE_PUD_FOLDED +#define __PAGETABLE_PUD_FOLDED 1 /* * Having the pud type consist of a pgd gets the size right, and allows diff --git a/include/asm-generic/pgtable-nop4d.h b/include/asm-generic/pgtable-nop4d.h index 1a29b2a0282b..04cb913797bc 100644 --- a/include/asm-generic/pgtable-nop4d.h +++ b/include/asm-generic/pgtable-nop4d.h @@ -4,7 +4,7 @@ #ifndef __ASSEMBLY__ -#define __PAGETABLE_P4D_FOLDED +#define __PAGETABLE_P4D_FOLDED 1 typedef struct { pgd_t pgd; } p4d_t; diff --git a/include/asm-generic/pgtable-nopmd.h b/include/asm-generic/pgtable-nopmd.h index f35f6e8149e4..b85b8271a73d 100644 --- a/include/asm-generic/pgtable-nopmd.h +++ b/include/asm-generic/pgtable-nopmd.h @@ -8,7 +8,7 @@ struct mm_struct; -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 /* * Having the pmd type consist of a pud gets the size right, and allows diff --git a/include/asm-generic/pgtable-nopud.h b/include/asm-generic/pgtable-nopud.h index e950b9c50f34..9bef475db6fe 100644 --- a/include/asm-generic/pgtable-nopud.h +++ b/include/asm-generic/pgtable-nopud.h @@ -9,7 +9,7 @@ #else #include -#define __PAGETABLE_PUD_FOLDED +#define __PAGETABLE_PUD_FOLDED 1 /* * Having the pud type consist of a p4d gets the size right, and allows From 1071fc5779d9846fec56a4ff6089ab08cac1ab72 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Mon, 15 Oct 2018 10:25:57 +0200 Subject: [PATCH 028/356] mm: introduce mm_[p4d|pud|pmd]_folded Add three architecture overrideable functions to test if the p4d, pud, or pmd layer of a page table is folded or not. Acked-by: Kirill A. Shutemov Signed-off-by: Martin Schwidefsky --- include/asm-generic/pgtable.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 88ebc6102c7c..15fd0277ffa6 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -1127,4 +1127,20 @@ static inline bool arch_has_pfn_modify_check(void) #endif #endif +/* + * On some architectures it depends on the mm if the p4d/pud or pmd + * layer of the page table hierarchy is folded or not. + */ +#ifndef mm_p4d_folded +#define mm_p4d_folded(mm) __is_defined(__PAGETABLE_P4D_FOLDED) +#endif + +#ifndef mm_pud_folded +#define mm_pud_folded(mm) __is_defined(__PAGETABLE_PUD_FOLDED) +#endif + +#ifndef mm_pmd_folded +#define mm_pmd_folded(mm) __is_defined(__PAGETABLE_PMD_FOLDED) +#endif + #endif /* _ASM_GENERIC_PGTABLE_H */ From 6d212db11947ae5464e4717536ed9faf61c01e86 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Mon, 15 Oct 2018 10:30:23 +0200 Subject: [PATCH 029/356] mm: add mm_pxd_folded checks to pgtable_bytes accounting functions The common mm code calls mm_dec_nr_pmds() and mm_dec_nr_puds() in free_pgtables() if the address range spans a full pud or pmd. If mm_dec_nr_puds/mm_dec_nr_pmds are non-empty due to configuration settings they blindly subtract the size of the pmd or pud table from pgtable_bytes even if the pud or pmd page table layer is folded. Add explicit mm_[pmd|pud]_folded checks to the four pgtable_bytes accounting functions mm_inc_nr_puds, mm_inc_nr_pmds, mm_dec_nr_puds and mm_dec_nr_pmds. As the check for folded page tables can be overwritten by the architecture, this allows to keep a correct pgtable_bytes value for platforms that use a dynamic number of page table levels. Acked-by: Kirill A. Shutemov Signed-off-by: Martin Schwidefsky --- include/linux/mm.h | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/include/linux/mm.h b/include/linux/mm.h index daa2b8f1e9a8..a3701e91bb57 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1742,11 +1742,15 @@ int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address); static inline void mm_inc_nr_puds(struct mm_struct *mm) { + if (mm_pud_folded(mm)) + return; atomic_long_add(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_puds(struct mm_struct *mm) { + if (mm_pud_folded(mm)) + return; atomic_long_sub(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } #endif @@ -1766,11 +1770,15 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address); static inline void mm_inc_nr_pmds(struct mm_struct *mm) { + if (mm_pmd_folded(mm)) + return; atomic_long_add(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_pmds(struct mm_struct *mm) { + if (mm_pmd_folded(mm)) + return; atomic_long_sub(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } #endif From e12e4044aede97974f2222eb7f0ed726a5179a32 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Mon, 15 Oct 2018 11:09:16 +0200 Subject: [PATCH 030/356] s390/mm: fix mis-accounting of pgtable_bytes In case a fork or a clone system fails in copy_process and the error handling does the mmput() at the bad_fork_cleanup_mm label, the following warning messages will appear on the console: BUG: non-zero pgtables_bytes on freeing mm: 16384 The reason for that is the tricks we play with mm_inc_nr_puds() and mm_inc_nr_pmds() in init_new_context(). A normal 64-bit process has 3 levels of page table, the p4d level and the pud level are folded. On process termination the free_pud_range() function in mm/memory.c will subtract 16KB from pgtable_bytes with a mm_dec_nr_puds() call, but there actually is not really a pud table. One issue with this is the fact that pgtable_bytes is usually off by a few kilobytes, but the more severe problem is that for a failed fork or clone the free_pgtables() function is not called. In this case there is no mm_dec_nr_puds() or mm_dec_nr_pmds() that go together with the mm_inc_nr_puds() and mm_inc_nr_pmds in init_new_context(). The pgtable_bytes will be off by 16384 or 32768 bytes and we get the BUG message. The message itself is purely cosmetic, but annoying. To fix this override the mm_pmd_folded, mm_pud_folded and mm_p4d_folded function to check for the true size of the address space. Reported-by: Li Wang Tested-by: Li Wang Signed-off-by: Martin Schwidefsky --- arch/s390/include/asm/mmu_context.h | 5 ----- arch/s390/include/asm/pgalloc.h | 6 +++--- arch/s390/include/asm/pgtable.h | 18 ++++++++++++++++++ arch/s390/include/asm/tlb.h | 6 +++--- arch/s390/mm/pgalloc.c | 1 + 5 files changed, 25 insertions(+), 11 deletions(-) diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index dbd689d556ce..ccbb53e22024 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -46,8 +46,6 @@ static inline int init_new_context(struct task_struct *tsk, mm->context.asce_limit = STACK_TOP_MAX; mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | _ASCE_USER_BITS | _ASCE_TYPE_REGION3; - /* pgd_alloc() did not account this pud */ - mm_inc_nr_puds(mm); break; case -PAGE_SIZE: /* forked 5-level task, set new asce with new_mm->pgd */ @@ -63,9 +61,6 @@ static inline int init_new_context(struct task_struct *tsk, /* forked 2-level compat task, set new asce with new mm->pgd */ mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT; - /* pgd_alloc() did not account this pmd */ - mm_inc_nr_pmds(mm); - mm_inc_nr_puds(mm); } crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm)); return 0; diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index f0f9bcf94c03..5ee733720a57 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -36,11 +36,11 @@ static inline void crst_table_init(unsigned long *crst, unsigned long entry) static inline unsigned long pgd_entry_type(struct mm_struct *mm) { - if (mm->context.asce_limit <= _REGION3_SIZE) + if (mm_pmd_folded(mm)) return _SEGMENT_ENTRY_EMPTY; - if (mm->context.asce_limit <= _REGION2_SIZE) + if (mm_pud_folded(mm)) return _REGION3_ENTRY_EMPTY; - if (mm->context.asce_limit <= _REGION1_SIZE) + if (mm_p4d_folded(mm)) return _REGION2_ENTRY_EMPTY; return _REGION1_ENTRY_EMPTY; } diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 411d435e7a7d..063732414dfb 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -493,6 +493,24 @@ static inline int is_module_addr(void *addr) _REGION_ENTRY_PROTECT | \ _REGION_ENTRY_NOEXEC) +static inline bool mm_p4d_folded(struct mm_struct *mm) +{ + return mm->context.asce_limit <= _REGION1_SIZE; +} +#define mm_p4d_folded(mm) mm_p4d_folded(mm) + +static inline bool mm_pud_folded(struct mm_struct *mm) +{ + return mm->context.asce_limit <= _REGION2_SIZE; +} +#define mm_pud_folded(mm) mm_pud_folded(mm) + +static inline bool mm_pmd_folded(struct mm_struct *mm) +{ + return mm->context.asce_limit <= _REGION3_SIZE; +} +#define mm_pmd_folded(mm) mm_pmd_folded(mm) + static inline int mm_has_pgste(struct mm_struct *mm) { #ifdef CONFIG_PGSTE diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index 457b7ba0fbb6..b31c779cf581 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -136,7 +136,7 @@ static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, unsigned long address) { - if (tlb->mm->context.asce_limit <= _REGION3_SIZE) + if (mm_pmd_folded(tlb->mm)) return; pgtable_pmd_page_dtor(virt_to_page(pmd)); tlb_remove_table(tlb, pmd); @@ -152,7 +152,7 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, unsigned long address) { - if (tlb->mm->context.asce_limit <= _REGION1_SIZE) + if (mm_p4d_folded(tlb->mm)) return; tlb_remove_table(tlb, p4d); } @@ -167,7 +167,7 @@ static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, unsigned long address) { - if (tlb->mm->context.asce_limit <= _REGION2_SIZE) + if (mm_pud_folded(tlb->mm)) return; tlb_remove_table(tlb, pud); } diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index 76d89ee8b428..814f26520aa2 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -101,6 +101,7 @@ int crst_table_upgrade(struct mm_struct *mm, unsigned long end) mm->context.asce_limit = _REGION1_SIZE; mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | _ASCE_USER_BITS | _ASCE_TYPE_REGION2; + mm_inc_nr_puds(mm); } else { crst_table_init(table, _REGION1_ENTRY_EMPTY); pgd_populate(mm, (pgd_t *) table, (p4d_t *) pgd); From c43e1c5a801fdde1aad0a2f9ed948753b5275d56 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Thu, 25 Oct 2018 09:04:05 +0100 Subject: [PATCH 031/356] s390/cpum_sf: Rework attribute definition for diagnostic sampling Previously, the attribute entry for diagnostic sampling was added if authorized. Otherwise, the array of struct attribute contains two NULL values. Change this logic and reserve space for the attribute for diagnostic sampling. If diagnostic sampling is authorized, add an entry in the respective position in the array of struct attribute. Signed-off-by: Thomas Richter Reviewed-by: Hendrik Brueckner Suggested-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/perf_cpum_sf.c | 33 ++++++++++++++++++++++++++++----- 1 file changed, 28 insertions(+), 5 deletions(-) diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 7bf604ff50a1..bfabeb1889cc 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -1842,10 +1842,30 @@ static void cpumsf_pmu_del(struct perf_event *event, int flags) CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC, PERF_EVENT_CPUM_SF); CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC_DIAG, PERF_EVENT_CPUM_SF_DIAG); -static struct attribute *cpumsf_pmu_events_attr[] = { - CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC), - NULL, - NULL, +/* Attribute list for CPU_SF. + * + * The availablitiy depends on the CPU_MF sampling facility authorization + * for basic + diagnositic samples. This is determined at initialization + * time by the sampling facility device driver. + * If the authorization for basic samples is turned off, it should be + * also turned off for diagnostic sampling. + * + * During initialization of the device driver, check the authorization + * level for diagnostic sampling and installs the attribute + * file for diagnostic sampling if necessary. + * + * For now install a placeholder to reference all possible attributes: + * SF_CYCLES_BASIC and SF_CYCLES_BASIC_DIAG. + * Add another entry for the final NULL pointer. + */ +enum { + SF_CYCLES_BASIC_ATTR_IDX = 0, + SF_CYCLES_BASIC_DIAG_ATTR_IDX, + SF_CYCLES_ATTR_MAX +}; + +static struct attribute *cpumsf_pmu_events_attr[SF_CYCLES_ATTR_MAX + 1] = { + [SF_CYCLES_BASIC_ATTR_IDX] = CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC) }; PMU_FORMAT_ATTR(event, "config:0-63"); @@ -2040,7 +2060,10 @@ static int __init init_cpum_sampling_pmu(void) if (si.ad) { sfb_set_limits(CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB); - cpumsf_pmu_events_attr[1] = + /* Sampling of diagnostic data authorized, + * install event into attribute list of PMU device. + */ + cpumsf_pmu_events_attr[SF_CYCLES_BASIC_DIAG_ATTR_IDX] = CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC_DIAG); } From 9fed920e6817218ad786c3f28e14b4c877cc2aed Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Fri, 26 Oct 2018 15:29:59 +0200 Subject: [PATCH 032/356] s390/kasan: increase instrumented stack size to 64k Increase kasan instrumented kernel stack size from 32k to 64k. Other architectures seems to get away with just doubling kernel stack size under kasan, but on s390 this appears to be not enough due to bigger frame size. The particular pain point is kasan inlined checks (CONFIG_KASAN_INLINE vs CONFIG_KASAN_OUTLINE). With inlined checks one particular case hitting stack overflow is fs sync on xfs filesystem: #0 [9a0681e8] 704 bytes check_usage at 34b1fc #1 [9a0684a8] 432 bytes check_usage at 34c710 #2 [9a068658] 1048 bytes validate_chain at 35044a #3 [9a068a70] 312 bytes __lock_acquire at 3559fe #4 [9a068ba8] 440 bytes lock_acquire at 3576ee #5 [9a068d60] 104 bytes _raw_spin_lock at 21b44e0 #6 [9a068dc8] 1992 bytes enqueue_entity at 2dbf72 #7 [9a069590] 1496 bytes enqueue_task_fair at 2df5f0 #8 [9a069b68] 64 bytes ttwu_do_activate at 28f438 #9 [9a069ba8] 552 bytes try_to_wake_up at 298c4c #10 [9a069dd0] 168 bytes wake_up_worker at 23f97c #11 [9a069e78] 200 bytes insert_work at 23fc2e #12 [9a069f40] 648 bytes __queue_work at 2487c0 #13 [9a06a1c8] 200 bytes __queue_delayed_work at 24db28 #14 [9a06a290] 248 bytes mod_delayed_work_on at 24de84 #15 [9a06a388] 24 bytes kblockd_mod_delayed_work_on at 153e2a0 #16 [9a06a3a0] 288 bytes __blk_mq_delay_run_hw_queue at 158168c #17 [9a06a4c0] 192 bytes blk_mq_run_hw_queue at 1581a3c #18 [9a06a580] 184 bytes blk_mq_sched_insert_requests at 15a2192 #19 [9a06a638] 1024 bytes blk_mq_flush_plug_list at 1590f3a #20 [9a06aa38] 704 bytes blk_flush_plug_list at 1555028 #21 [9a06acf8] 320 bytes schedule at 219e476 #22 [9a06ae38] 760 bytes schedule_timeout at 21b0aac #23 [9a06b130] 408 bytes wait_for_common at 21a1706 #24 [9a06b2c8] 360 bytes xfs_buf_iowait at fa1540 #25 [9a06b430] 256 bytes __xfs_buf_submit at fadae6 #26 [9a06b530] 264 bytes xfs_buf_read_map at fae3f6 #27 [9a06b638] 656 bytes xfs_trans_read_buf_map at 10ac9a8 #28 [9a06b8c8] 304 bytes xfs_btree_kill_root at e72426 #29 [9a06b9f8] 288 bytes xfs_btree_lookup_get_block at e7bc5e #30 [9a06bb18] 624 bytes xfs_btree_lookup at e7e1a6 #31 [9a06bd88] 2664 bytes xfs_alloc_ag_vextent_near at dfa070 #32 [9a06c7f0] 144 bytes xfs_alloc_ag_vextent at dff3ca #33 [9a06c880] 1128 bytes xfs_alloc_vextent at e05fce #34 [9a06cce8] 584 bytes xfs_bmap_btalloc at e58342 #35 [9a06cf30] 1336 bytes xfs_bmapi_write at e618de #36 [9a06d468] 776 bytes xfs_iomap_write_allocate at ff678e #37 [9a06d770] 720 bytes xfs_map_blocks at f82af8 #38 [9a06da40] 928 bytes xfs_writepage_map at f83cd6 #39 [9a06dde0] 320 bytes xfs_do_writepage at f85872 #40 [9a06df20] 1320 bytes write_cache_pages at 73dfe8 #41 [9a06e448] 208 bytes xfs_vm_writepages at f7f892 #42 [9a06e518] 88 bytes do_writepages at 73fe6a #43 [9a06e570] 872 bytes __writeback_single_inode at a20cb6 #44 [9a06e8d8] 664 bytes writeback_sb_inodes at a23be2 #45 [9a06eb70] 296 bytes __writeback_inodes_wb at a242e0 #46 [9a06ec98] 928 bytes wb_writeback at a2500e #47 [9a06f038] 848 bytes wb_do_writeback at a260ae #48 [9a06f388] 536 bytes wb_workfn at a28228 #49 [9a06f5a0] 1088 bytes process_one_work at 24a234 #50 [9a06f9e0] 1120 bytes worker_thread at 24ba26 #51 [9a06fe40] 104 bytes kthread at 26545a #52 [9a06fea8] kernel_thread_starter at 21b6b62 To be able to increase the stack size to 64k reuse LLILL instruction in __switch_to function to load 64k - STACK_FRAME_OVERHEAD - __PT_SIZE (65192) value as unsigned. Reported-by: Benjamin Block Reviewed-by: Heiko Carstens Signed-off-by: Vasily Gorbik Signed-off-by: Martin Schwidefsky --- arch/s390/Makefile | 2 +- arch/s390/include/asm/thread_info.h | 2 +- arch/s390/kernel/entry.S | 6 +++--- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 0b33577932c3..e21053e5e0da 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -27,7 +27,7 @@ KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-option,-ffreestanding) KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),-g) KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO_DWARF4), $(call cc-option, -gdwarf-4,)) UTS_MACHINE := s390x -STACK_SIZE := $(if $(CONFIG_KASAN),32768,16384) +STACK_SIZE := $(if $(CONFIG_KASAN),65536,16384) CHECKFLAGS += -D__s390__ -D__s390x__ export LD_BFD diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index 27248f42a03c..ce4e17c9aad6 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -14,7 +14,7 @@ * General size of kernel stacks */ #ifdef CONFIG_KASAN -#define THREAD_SIZE_ORDER 3 +#define THREAD_SIZE_ORDER 4 #else #define THREAD_SIZE_ORDER 2 #endif diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 724fba4d09d2..39191a0feed1 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -236,10 +236,10 @@ ENTRY(__switch_to) stmg %r6,%r15,__SF_GPRS(%r15) # store gprs of prev task lghi %r4,__TASK_stack lghi %r1,__TASK_thread - lg %r5,0(%r4,%r3) # start of kernel stack of next + llill %r5,STACK_INIT stg %r15,__THREAD_ksp(%r1,%r2) # store kernel stack of prev - lgr %r15,%r5 - aghi %r15,STACK_INIT # end of kernel stack of next + lg %r15,0(%r4,%r3) # start of kernel stack of next + agr %r15,%r5 # end of kernel stack of next stg %r3,__LC_CURRENT # store task struct of next stg %r15,__LC_KERNEL_STACK # store end of kernel stack lg %r15,__THREAD_ksp(%r1,%r3) # load kernel stack of next From a541f0ebcc08ed8bc0cc492eec9a86cb280a9f24 Mon Sep 17 00:00:00 2001 From: "Justin M. Forbes" Date: Wed, 31 Oct 2018 13:02:03 -0500 Subject: [PATCH 033/356] s390/mm: Fix ERROR: "__node_distance" undefined! Fixes: ERROR: "__node_distance" [drivers/nvme/host/nvme-core.ko] undefined! make[1]: *** [scripts/Makefile.modpost:92: __modpost] Error 1 make: *** [Makefile:1275: modules] Error 2 + exit 1 Signed-off-by: Justin M. Forbes Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/numa/numa.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/s390/numa/numa.c b/arch/s390/numa/numa.c index 5bd374491f94..6c151b42e65d 100644 --- a/arch/s390/numa/numa.c +++ b/arch/s390/numa/numa.c @@ -54,6 +54,7 @@ int __node_distance(int a, int b) { return mode->distance ? mode->distance(a, b) : 0; } +EXPORT_SYMBOL(__node_distance); int numa_debug_enabled; From f9005571701920551bcf54a500973fb61f2e1eda Mon Sep 17 00:00:00 2001 From: Stefano Stabellini Date: Wed, 31 Oct 2018 16:11:49 -0700 Subject: [PATCH 034/356] CONFIG_XEN_PV breaks xen_create_contiguous_region on ARM xen_create_contiguous_region has now only an implementation if CONFIG_XEN_PV is defined. However, on ARM we never set CONFIG_XEN_PV but we do have an implementation of xen_create_contiguous_region which is required for swiotlb-xen to work correctly (although it just sets *dma_handle). Cc: # 4.12 Fixes: 16624390816c ("xen: create xen_create/destroy_contiguous_region() stubs for PVHVM only builds") Signed-off-by: Stefano Stabellini Reviewed-by: Juergen Gross CC: Jeff.Kubascik@dornerworks.com CC: Jarvis.Roach@dornerworks.com CC: Nathan.Studer@dornerworks.com CC: vkuznets@redhat.com CC: boris.ostrovsky@oracle.com CC: jgross@suse.com CC: julien.grall@arm.com Signed-off-by: Juergen Gross --- include/xen/xen-ops.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index 18803ff76e27..4969817124a8 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -42,16 +42,12 @@ int xen_setup_shutdown_event(void); extern unsigned long *xen_contiguous_bitmap; -#ifdef CONFIG_XEN_PV +#if defined(CONFIG_XEN_PV) || defined(CONFIG_ARM) || defined(CONFIG_ARM64) int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, unsigned int address_bits, dma_addr_t *dma_handle); void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order); - -int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, - xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot, - unsigned int domid, bool no_translate, struct page **pages); #else static inline int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, @@ -63,7 +59,13 @@ static inline int xen_create_contiguous_region(phys_addr_t pstart, static inline void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order) { } +#endif +#if defined(CONFIG_XEN_PV) +int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, + xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot, + unsigned int domid, bool no_translate, struct page **pages); +#else static inline int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot, unsigned int domid, From df0734702a7cbba49d6765bd5ba069340bf9c5db Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 2 Nov 2018 10:16:15 -0700 Subject: [PATCH 035/356] bpf: show real jited prog address in /proc/kallsyms Currently, /proc/kallsyms shows page address of jited bpf program. The main reason here is to not expose randomized start address. However, This is not ideal for detailed profiling (find hot instructions from stack traces). This patch replaces the page address with real prog start address. This change is OK because these addresses are still protected by sysctl kptr_restrict (see kallsyms_show_value()), and only programs loaded by root are added to kallsyms (see bpf_prog_kallsyms_add()). Signed-off-by: Song Liu Signed-off-by: Daniel Borkmann --- kernel/bpf/core.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 6377225b2082..1a796e0799ec 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -553,7 +553,6 @@ bool is_bpf_text_address(unsigned long addr) int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym) { - unsigned long symbol_start, symbol_end; struct bpf_prog_aux *aux; unsigned int it = 0; int ret = -ERANGE; @@ -566,10 +565,9 @@ int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, if (it++ != symnum) continue; - bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end); bpf_get_prog_name(aux->prog, sym); - *value = symbol_start; + *value = (unsigned long)aux->prog->bpf_func; *type = BPF_SYM_ELF_TYPE; ret = 0; From de57e99ceb65d0d7775cc14a8ba5931d7de1d708 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 2 Nov 2018 10:16:16 -0700 Subject: [PATCH 036/356] bpf: show real jited address in bpf_prog_info->jited_ksyms Currently, jited_ksyms in bpf_prog_info shows page addresses of jited bpf program. The main reason here is to not expose randomized start address. However, this is not ideal for detailed profiling (find hot instructions from stack traces). This patch replaces the page address with real prog start address. This change is OK because bpf_prog_get_info_by_fd() is only available to root. Signed-off-by: Song Liu Signed-off-by: Daniel Borkmann --- kernel/bpf/syscall.c | 1 - 1 file changed, 1 deletion(-) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index ccb93277aae2..34a9eef5992c 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2172,7 +2172,6 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, user_ksyms = u64_to_user_ptr(info.jited_ksyms); for (i = 0; i < ulen; i++) { ksym_addr = (ulong) prog->aux->func[i]->bpf_func; - ksym_addr &= PAGE_MASK; if (put_user((u64) ksym_addr, &user_ksyms[i])) return -EFAULT; } From ff1889fc531f582f902175c0acc80321af540b24 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 2 Nov 2018 10:16:17 -0700 Subject: [PATCH 037/356] bpf: show main program address and length in bpf_prog_info Currently, when there is no subprog (prog->aux->func_cnt == 0), bpf_prog_info does not return any jited_ksyms or jited_func_lens. This patch adds main program address (prog->bpf_func) and main program length (prog->jited_len) to bpf_prog_info. Signed-off-by: Song Liu Signed-off-by: Daniel Borkmann --- kernel/bpf/syscall.c | 33 ++++++++++++++++++++++++--------- 1 file changed, 24 insertions(+), 9 deletions(-) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 34a9eef5992c..9418174c276c 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2158,11 +2158,11 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, } ulen = info.nr_jited_ksyms; - info.nr_jited_ksyms = prog->aux->func_cnt; + info.nr_jited_ksyms = prog->aux->func_cnt ? : 1; if (info.nr_jited_ksyms && ulen) { if (bpf_dump_raw_ok()) { + unsigned long ksym_addr; u64 __user *user_ksyms; - ulong ksym_addr; u32 i; /* copy the address of the kernel symbol @@ -2170,9 +2170,17 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, */ ulen = min_t(u32, info.nr_jited_ksyms, ulen); user_ksyms = u64_to_user_ptr(info.jited_ksyms); - for (i = 0; i < ulen; i++) { - ksym_addr = (ulong) prog->aux->func[i]->bpf_func; - if (put_user((u64) ksym_addr, &user_ksyms[i])) + if (prog->aux->func_cnt) { + for (i = 0; i < ulen; i++) { + ksym_addr = (unsigned long) + prog->aux->func[i]->bpf_func; + if (put_user((u64) ksym_addr, + &user_ksyms[i])) + return -EFAULT; + } + } else { + ksym_addr = (unsigned long) prog->bpf_func; + if (put_user((u64) ksym_addr, &user_ksyms[0])) return -EFAULT; } } else { @@ -2181,7 +2189,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, } ulen = info.nr_jited_func_lens; - info.nr_jited_func_lens = prog->aux->func_cnt; + info.nr_jited_func_lens = prog->aux->func_cnt ? : 1; if (info.nr_jited_func_lens && ulen) { if (bpf_dump_raw_ok()) { u32 __user *user_lens; @@ -2190,9 +2198,16 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, /* copy the JITed image lengths for each function */ ulen = min_t(u32, info.nr_jited_func_lens, ulen); user_lens = u64_to_user_ptr(info.jited_func_lens); - for (i = 0; i < ulen; i++) { - func_len = prog->aux->func[i]->jited_len; - if (put_user(func_len, &user_lens[i])) + if (prog->aux->func_cnt) { + for (i = 0; i < ulen; i++) { + func_len = + prog->aux->func[i]->jited_len; + if (put_user(func_len, &user_lens[i])) + return -EFAULT; + } + } else { + func_len = prog->jited_len; + if (put_user(func_len, &user_lens[0])) return -EFAULT; } } else { From 28c2fae726bf5003cd209b0d5910a642af98316f Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 2 Nov 2018 11:35:46 +0100 Subject: [PATCH 038/356] bpf: fix bpf_prog_get_info_by_fd to return 0 func_lens for unpriv While dbecd7388476 ("bpf: get kernel symbol addresses via syscall") zeroed info.nr_jited_ksyms in bpf_prog_get_info_by_fd() for queries from unprivileged users, commit 815581c11cc2 ("bpf: get JITed image lengths of functions via syscall") forgot about doing so and therefore returns the #elems of the user set up buffer which is incorrect. It also needs to indicate a info.nr_jited_func_lens of zero. Fixes: 815581c11cc2 ("bpf: get JITed image lengths of functions via syscall") Signed-off-by: Daniel Borkmann Cc: Sandipan Das Cc: Song Liu Signed-off-by: Alexei Starovoitov --- kernel/bpf/syscall.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 9418174c276c..cf5040fd5434 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2078,6 +2078,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, info.jited_prog_len = 0; info.xlated_prog_len = 0; info.nr_jited_ksyms = 0; + info.nr_jited_func_lens = 0; goto done; } From 49682bfa1e0e448a711471a5db83be0df1fb39a2 Mon Sep 17 00:00:00 2001 From: Mathieu Malaterre Date: Wed, 31 Oct 2018 13:16:58 +0100 Subject: [PATCH 039/356] net: document skb parameter in function 'skb_gso_size_check' Remove kernel-doc warning: net/core/skbuff.c:4953: warning: Function parameter or member 'skb' not described in 'skb_gso_size_check' Signed-off-by: Mathieu Malaterre Signed-off-by: David S. Miller --- net/core/skbuff.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 946de0e24c87..b4ee5c8b928f 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4944,6 +4944,8 @@ static unsigned int skb_gso_mac_seglen(const struct sk_buff *skb) * * This is a helper to do that correctly considering GSO_BY_FRAGS. * + * @skb: GSO skb + * * @seg_len: The segmented length (from skb_gso_*_seglen). In the * GSO_BY_FRAGS case this will be [header sizes + GSO_BY_FRAGS]. * From 7b900ead6cc66b2ee873cb042dfba169aa68b56c Mon Sep 17 00:00:00 2001 From: Frieder Schrempf Date: Wed, 31 Oct 2018 22:52:19 +0100 Subject: [PATCH 040/356] usbnet: smsc95xx: disable carrier check while suspending We need to make sure, that the carrier check polling is disabled while suspending. Otherwise we can end up with usbnet_read_cmd() being issued when only usbnet_read_cmd_nopm() is allowed. If this happens, read operations lock up. Fixes: d69d169493 ("usbnet: smsc95xx: fix link detection for disabled autonegotiation") Signed-off-by: Frieder Schrempf Reviewed-by: Raghuram Chary J Signed-off-by: David S. Miller --- drivers/net/usb/smsc95xx.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 262e7a3c23cb..2d17f3b9bb16 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -1598,6 +1598,8 @@ static int smsc95xx_suspend(struct usb_interface *intf, pm_message_t message) return ret; } + cancel_delayed_work_sync(&pdata->carrier_check); + if (pdata->suspend_flags) { netdev_warn(dev->net, "error during last resume\n"); pdata->suspend_flags = 0; @@ -1840,6 +1842,11 @@ done: */ if (ret && PMSG_IS_AUTO(message)) usbnet_resume(intf); + + if (ret) + schedule_delayed_work(&pdata->carrier_check, + CARRIER_CHECK_DELAY); + return ret; } From 2384d02520ff2a916169b2fd85ea50e923ed56c2 Mon Sep 17 00:00:00 2001 From: Jeff Barnhill <0xeffeff@gmail.com> Date: Fri, 2 Nov 2018 20:23:57 +0000 Subject: [PATCH 041/356] net/ipv6: Add anycast addresses to a global hashtable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit icmp6_send() function is expensive on systems with a large number of interfaces. Every time it’s called, it has to verify that the source address does not correspond to an existing anycast address by looping through every device and every anycast address on the device. This can result in significant delays for a CPU when there are a large number of neighbors and ND timers are frequently timing out and calling neigh_invalidate(). Add anycast addresses to a global hashtable to allow quick searching for matching anycast addresses. This is based on inet6_addr_lst in addrconf.c. Signed-off-by: Jeff Barnhill <0xeffeff@gmail.com> Signed-off-by: David S. Miller --- include/net/addrconf.h | 2 ++ include/net/if_inet6.h | 2 ++ net/ipv6/af_inet6.c | 5 +++ net/ipv6/anycast.c | 80 +++++++++++++++++++++++++++++++++++++++--- 4 files changed, 85 insertions(+), 4 deletions(-) diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 14b789a123e7..1656c5978498 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -317,6 +317,8 @@ bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev, const struct in6_addr *addr); bool ipv6_chk_acast_addr_src(struct net *net, struct net_device *dev, const struct in6_addr *addr); +int ipv6_anycast_init(void); +void ipv6_anycast_cleanup(void); /* Device notifier */ int register_inet6addr_notifier(struct notifier_block *nb); diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index d7578cf49c3a..c9c78c15bce0 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -146,10 +146,12 @@ struct ifacaddr6 { struct in6_addr aca_addr; struct fib6_info *aca_rt; struct ifacaddr6 *aca_next; + struct hlist_node aca_addr_lst; int aca_users; refcount_t aca_refcnt; unsigned long aca_cstamp; unsigned long aca_tstamp; + struct rcu_head rcu; }; #define IFA_HOST IPV6_ADDR_LOOPBACK diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 3f4d61017a69..f0cd291034f0 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -1001,6 +1001,9 @@ static int __init inet6_init(void) err = ip6_flowlabel_init(); if (err) goto ip6_flowlabel_fail; + err = ipv6_anycast_init(); + if (err) + goto ipv6_anycast_fail; err = addrconf_init(); if (err) goto addrconf_fail; @@ -1091,6 +1094,8 @@ ipv6_frag_fail: ipv6_exthdrs_fail: addrconf_cleanup(); addrconf_fail: + ipv6_anycast_cleanup(); +ipv6_anycast_fail: ip6_flowlabel_cleanup(); ip6_flowlabel_fail: ndisc_late_cleanup(); diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 4e0ff7031edd..7698637cf827 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -44,8 +44,22 @@ #include +#define IN6_ADDR_HSIZE_SHIFT 8 +#define IN6_ADDR_HSIZE BIT(IN6_ADDR_HSIZE_SHIFT) +/* anycast address hash table + */ +static struct hlist_head inet6_acaddr_lst[IN6_ADDR_HSIZE]; +static DEFINE_SPINLOCK(acaddr_hash_lock); + static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr); +static u32 inet6_acaddr_hash(struct net *net, const struct in6_addr *addr) +{ + u32 val = ipv6_addr_hash(addr) ^ net_hash_mix(net); + + return hash_32(val, IN6_ADDR_HSIZE_SHIFT); +} + /* * socket join an anycast group */ @@ -204,16 +218,39 @@ void ipv6_sock_ac_close(struct sock *sk) rtnl_unlock(); } +static void ipv6_add_acaddr_hash(struct net *net, struct ifacaddr6 *aca) +{ + unsigned int hash = inet6_acaddr_hash(net, &aca->aca_addr); + + spin_lock(&acaddr_hash_lock); + hlist_add_head_rcu(&aca->aca_addr_lst, &inet6_acaddr_lst[hash]); + spin_unlock(&acaddr_hash_lock); +} + +static void ipv6_del_acaddr_hash(struct ifacaddr6 *aca) +{ + spin_lock(&acaddr_hash_lock); + hlist_del_init_rcu(&aca->aca_addr_lst); + spin_unlock(&acaddr_hash_lock); +} + static void aca_get(struct ifacaddr6 *aca) { refcount_inc(&aca->aca_refcnt); } +static void aca_free_rcu(struct rcu_head *h) +{ + struct ifacaddr6 *aca = container_of(h, struct ifacaddr6, rcu); + + fib6_info_release(aca->aca_rt); + kfree(aca); +} + static void aca_put(struct ifacaddr6 *ac) { if (refcount_dec_and_test(&ac->aca_refcnt)) { - fib6_info_release(ac->aca_rt); - kfree(ac); + call_rcu(&ac->rcu, aca_free_rcu); } } @@ -229,6 +266,7 @@ static struct ifacaddr6 *aca_alloc(struct fib6_info *f6i, aca->aca_addr = *addr; fib6_info_hold(f6i); aca->aca_rt = f6i; + INIT_HLIST_NODE(&aca->aca_addr_lst); aca->aca_users = 1; /* aca_tstamp should be updated upon changes */ aca->aca_cstamp = aca->aca_tstamp = jiffies; @@ -285,6 +323,8 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr) aca_get(aca); write_unlock_bh(&idev->lock); + ipv6_add_acaddr_hash(net, aca); + ip6_ins_rt(net, f6i); addrconf_join_solict(idev->dev, &aca->aca_addr); @@ -325,6 +365,7 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr) else idev->ac_list = aca->aca_next; write_unlock_bh(&idev->lock); + ipv6_del_acaddr_hash(aca); addrconf_leave_solict(idev, &aca->aca_addr); ip6_del_rt(dev_net(idev->dev), aca->aca_rt); @@ -352,6 +393,8 @@ void ipv6_ac_destroy_dev(struct inet6_dev *idev) idev->ac_list = aca->aca_next; write_unlock_bh(&idev->lock); + ipv6_del_acaddr_hash(aca); + addrconf_leave_solict(idev, &aca->aca_addr); ip6_del_rt(dev_net(idev->dev), aca->aca_rt); @@ -390,17 +433,25 @@ static bool ipv6_chk_acast_dev(struct net_device *dev, const struct in6_addr *ad bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev, const struct in6_addr *addr) { + unsigned int hash = inet6_acaddr_hash(net, addr); + struct net_device *nh_dev; + struct ifacaddr6 *aca; bool found = false; rcu_read_lock(); if (dev) found = ipv6_chk_acast_dev(dev, addr); else - for_each_netdev_rcu(net, dev) - if (ipv6_chk_acast_dev(dev, addr)) { + hlist_for_each_entry_rcu(aca, &inet6_acaddr_lst[hash], + aca_addr_lst) { + nh_dev = fib6_info_nh_dev(aca->aca_rt); + if (!nh_dev || !net_eq(dev_net(nh_dev), net)) + continue; + if (ipv6_addr_equal(&aca->aca_addr, addr)) { found = true; break; } + } rcu_read_unlock(); return found; } @@ -539,4 +590,25 @@ void ac6_proc_exit(struct net *net) { remove_proc_entry("anycast6", net->proc_net); } + +/* Init / cleanup code + */ +int __init ipv6_anycast_init(void) +{ + int i; + + for (i = 0; i < IN6_ADDR_HSIZE; i++) + INIT_HLIST_HEAD(&inet6_acaddr_lst[i]); + return 0; +} + +void ipv6_anycast_cleanup(void) +{ + int i; + + spin_lock(&acaddr_hash_lock); + for (i = 0; i < IN6_ADDR_HSIZE; i++) + WARN_ON(!hlist_empty(&inet6_acaddr_lst[i])); + spin_unlock(&acaddr_hash_lock); +} #endif From 284fb78ed7572117846f8e1d1d8e3dbfd16880c2 Mon Sep 17 00:00:00 2001 From: Tristram Ha Date: Fri, 2 Nov 2018 19:23:41 -0700 Subject: [PATCH 042/356] net: dsa: microchip: initialize mutex before use Initialize mutex before use. Avoid kernel complaint when CONFIG_DEBUG_LOCK_ALLOC is enabled. Fixes: b987e98e50ab90e5 ("dsa: add DSA switch driver for Microchip KSZ9477") Signed-off-by: Tristram Ha Reviewed-by: Pavel Machek Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/dsa/microchip/ksz_common.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 54e0ca6ed730..86b6464b4525 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -1117,11 +1117,6 @@ static int ksz_switch_init(struct ksz_device *dev) { int i; - mutex_init(&dev->reg_mutex); - mutex_init(&dev->stats_mutex); - mutex_init(&dev->alu_mutex); - mutex_init(&dev->vlan_mutex); - dev->ds->ops = &ksz_switch_ops; for (i = 0; i < ARRAY_SIZE(ksz_switch_chips); i++) { @@ -1206,6 +1201,11 @@ int ksz_switch_register(struct ksz_device *dev) if (dev->pdata) dev->chip_id = dev->pdata->chip_id; + mutex_init(&dev->reg_mutex); + mutex_init(&dev->stats_mutex); + mutex_init(&dev->alu_mutex); + mutex_init(&dev->vlan_mutex); + if (ksz_switch_detect(dev)) return -EINVAL; From c7e86acfcee30794dc99a0759924bf7b9d43f1ca Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 1 Nov 2018 13:39:53 +0000 Subject: [PATCH 043/356] rxrpc: Fix lockup due to no error backoff after ack transmit error If the network becomes (partially) unavailable, say by disabling IPv6, the background ACK transmission routine can get itself into a tizzy by proposing immediate ACK retransmission. Since we're in the call event processor, that happens immediately without returning to the workqueue manager. The condition should clear after a while when either the network comes back or the call times out. Fix this by: (1) When re-proposing an ACK on failed Tx, don't schedule it immediately. This will allow a certain amount of time to elapse before we try again. (2) Enforce a return to the workqueue manager after a certain number of iterations of the call processing loop. (3) Add a backoff delay that increases the delay on deferred ACKs by a jiffy per failed transmission to a limit of HZ. The backoff delay is cleared on a successful return from kernel_sendmsg(). (4) Cancel calls immediately if the opening sendmsg fails. The layer above can arrange retransmission or rotate to another server. Fixes: 248f219cb8bc ("rxrpc: Rewrite the data and ack handling code") Signed-off-by: David Howells Signed-off-by: David S. Miller --- net/rxrpc/ar-internal.h | 1 + net/rxrpc/call_event.c | 18 ++++++++++++++---- net/rxrpc/output.c | 35 +++++++++++++++++++++++++++++++---- 3 files changed, 46 insertions(+), 8 deletions(-) diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 382196e57a26..bc628acf4f4f 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -611,6 +611,7 @@ struct rxrpc_call { * not hard-ACK'd packet follows this. */ rxrpc_seq_t tx_top; /* Highest Tx slot allocated. */ + u16 tx_backoff; /* Delay to insert due to Tx failure */ /* TCP-style slow-start congestion control [RFC5681]. Since the SMSS * is fixed, we keep these numbers in terms of segments (ie. DATA diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 8e7434e92097..468efc3660c0 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -123,6 +123,7 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, else ack_at = expiry; + ack_at += READ_ONCE(call->tx_backoff); ack_at += now; if (time_before(ack_at, call->ack_at)) { WRITE_ONCE(call->ack_at, ack_at); @@ -311,6 +312,7 @@ void rxrpc_process_call(struct work_struct *work) container_of(work, struct rxrpc_call, processor); rxrpc_serial_t *send_ack; unsigned long now, next, t; + unsigned int iterations = 0; rxrpc_see_call(call); @@ -319,6 +321,11 @@ void rxrpc_process_call(struct work_struct *work) call->debug_id, rxrpc_call_states[call->state], call->events); recheck_state: + /* Limit the number of times we do this before returning to the manager */ + iterations++; + if (iterations > 5) + goto requeue; + if (test_and_clear_bit(RXRPC_CALL_EV_ABORT, &call->events)) { rxrpc_send_abort_packet(call); goto recheck_state; @@ -447,13 +454,16 @@ recheck_state: rxrpc_reduce_call_timer(call, next, now, rxrpc_timer_restart); /* other events may have been raised since we started checking */ - if (call->events && call->state < RXRPC_CALL_COMPLETE) { - __rxrpc_queue_call(call); - goto out; - } + if (call->events && call->state < RXRPC_CALL_COMPLETE) + goto requeue; out_put: rxrpc_put_call(call, rxrpc_call_put); out: _leave(""); + return; + +requeue: + __rxrpc_queue_call(call); + goto out; } diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 189418888839..736aa9281100 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -34,6 +34,21 @@ struct rxrpc_abort_buffer { static const char rxrpc_keepalive_string[] = ""; +/* + * Increase Tx backoff on transmission failure and clear it on success. + */ +static void rxrpc_tx_backoff(struct rxrpc_call *call, int ret) +{ + if (ret < 0) { + u16 tx_backoff = READ_ONCE(call->tx_backoff); + + if (tx_backoff < HZ) + WRITE_ONCE(call->tx_backoff, tx_backoff + 1); + } else { + WRITE_ONCE(call->tx_backoff, 0); + } +} + /* * Arrange for a keepalive ping a certain time after we last transmitted. This * lets the far side know we're still interested in this call and helps keep @@ -210,6 +225,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, else trace_rxrpc_tx_packet(call->debug_id, &pkt->whdr, rxrpc_tx_point_call_ack); + rxrpc_tx_backoff(call, ret); if (call->state < RXRPC_CALL_COMPLETE) { if (ret < 0) { @@ -218,7 +234,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, rxrpc_propose_ACK(call, pkt->ack.reason, ntohs(pkt->ack.maxSkew), ntohl(pkt->ack.serial), - true, true, + false, true, rxrpc_propose_ack_retry_tx); } else { spin_lock_bh(&call->lock); @@ -300,7 +316,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) else trace_rxrpc_tx_packet(call->debug_id, &pkt.whdr, rxrpc_tx_point_call_abort); - + rxrpc_tx_backoff(call, ret); rxrpc_put_connection(conn); return ret; @@ -413,6 +429,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, else trace_rxrpc_tx_packet(call->debug_id, &whdr, rxrpc_tx_point_call_data_nofrag); + rxrpc_tx_backoff(call, ret); if (ret == -EMSGSIZE) goto send_fragmentable; @@ -445,9 +462,18 @@ done: rxrpc_reduce_call_timer(call, expect_rx_by, nowj, rxrpc_timer_set_for_normal); } - } - rxrpc_set_keepalive(call); + rxrpc_set_keepalive(call); + } else { + /* Cancel the call if the initial transmission fails, + * particularly if that's due to network routing issues that + * aren't going away anytime soon. The layer above can arrange + * the retransmission. + */ + if (!test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER, &call->flags)) + rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, + RX_USER_ABORT, ret); + } _leave(" = %d [%u]", ret, call->peer->maxdata); return ret; @@ -506,6 +532,7 @@ send_fragmentable: else trace_rxrpc_tx_packet(call->debug_id, &whdr, rxrpc_tx_point_call_data_frag); + rxrpc_tx_backoff(call, ret); up_write(&conn->params.local->defrag_sem); goto done; From 09e805d2570a3a94f13dd9c9ad2bcab23da76e09 Mon Sep 17 00:00:00 2001 From: Doug Berger Date: Thu, 1 Nov 2018 15:55:37 -0700 Subject: [PATCH 044/356] net: bcmgenet: protect stop from timeout A timing hazard exists when the network interface is stopped that allows a watchdog timeout to be processed by a separate core in parallel. This creates the potential for the timeout handler to wake the queues while the driver is shutting down, or access registers after their clocks have been removed. The more common case is that the watchdog timeout will produce a warning message which doesn't lead to a crash. The chances of this are greatly increased by the fact that bcmgenet_netif_stop stops the transmit queues which can easily precipitate a watchdog time- out because of stale trans_start data in the queues. This commit corrects the behavior by ensuring that the watchdog timeout is disabled before enterring bcmgenet_netif_stop. There are currently only two users of the bcmgenet_netif_stop function: close and suspend. The close case already handles the issue by exiting the RUNNING state before invoking the driver close service. The suspend case now performs the netif_device_detach to exit the PRESENT state before the call to bcmgenet_netif_stop rather than after it. These behaviors prevent any future scheduling of the driver timeout service during the window. The netif_tx_stop_all_queues function in bcmgenet_netif_stop is replaced with netif_tx_disable to ensure synchronization with any transmit or timeout threads that may already be executing on other cores. For symmetry, the netif_device_attach call upon resume is moved to after the call to bcmgenet_netif_start. Since it wakes the transmit queues it is not necessary to invoke netif_tx_start_all_queues from bcmgenet_netif_start so it is moved into the driver open service. Fixes: 1c1008c793fa ("net: bcmgenet: add main driver file") Signed-off-by: Doug Berger Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 20c1681bb1af..2d6f090bf644 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -2855,7 +2855,6 @@ static void bcmgenet_netif_start(struct net_device *dev) umac_enable_set(priv, CMD_TX_EN | CMD_RX_EN, true); - netif_tx_start_all_queues(dev); bcmgenet_enable_tx_napi(priv); /* Monitor link interrupts now */ @@ -2937,6 +2936,8 @@ static int bcmgenet_open(struct net_device *dev) bcmgenet_netif_start(dev); + netif_tx_start_all_queues(dev); + return 0; err_irq1: @@ -2958,7 +2959,7 @@ static void bcmgenet_netif_stop(struct net_device *dev) struct bcmgenet_priv *priv = netdev_priv(dev); bcmgenet_disable_tx_napi(priv); - netif_tx_stop_all_queues(dev); + netif_tx_disable(dev); /* Disable MAC receive */ umac_enable_set(priv, CMD_RX_EN, false); @@ -3620,13 +3621,13 @@ static int bcmgenet_suspend(struct device *d) if (!netif_running(dev)) return 0; + netif_device_detach(dev); + bcmgenet_netif_stop(dev); if (!device_may_wakeup(d)) phy_suspend(dev->phydev); - netif_device_detach(dev); - /* Prepare the device for Wake-on-LAN and switch to the slow clock */ if (device_may_wakeup(d) && priv->wolopts) { ret = bcmgenet_power_down(priv, GENET_POWER_WOL_MAGIC); @@ -3700,8 +3701,6 @@ static int bcmgenet_resume(struct device *d) /* Always enable ring 16 - descriptor ring */ bcmgenet_enable_dma(priv, dma_ctrl); - netif_device_attach(dev); - if (!device_may_wakeup(d)) phy_resume(dev->phydev); @@ -3710,6 +3709,8 @@ static int bcmgenet_resume(struct device *d) bcmgenet_netif_start(dev); + netif_device_attach(dev); + return 0; out_clk_disable: From 7cb6a2a2c72c1ed8f42fb01f1a661281b568dead Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 1 Nov 2018 15:55:38 -0700 Subject: [PATCH 045/356] net: systemport: Protect stop from timeout A timing hazard exists when the network interface is stopped that allows a watchdog timeout to be processed by a separate core in parallel. This creates the potential for the timeout handler to wake the queues while the driver is shutting down, or access registers after their clocks have been removed. The more common case is that the watchdog timeout will produce a warning message which doesn't lead to a crash. The chances of this are greatly increased by the fact that bcm_sysport_netif_stop stops the transmit queues which can easily precipitate a watchdog time- out because of stale trans_start data in the queues. This commit corrects the behavior by ensuring that the watchdog timeout is disabled before enterring bcm_sysport_netif_stop. There are currently only two users of the bcm_sysport_netif_stop function: close and suspend. The close case already handles the issue by exiting the RUNNING state before invoking the driver close service. The suspend case now performs the netif_device_detach to exit the PRESENT state before the call to bcm_sysport_netif_stop rather than after it. These behaviors prevent any future scheduling of the driver timeout service during the window. The netif_tx_stop_all_queues function in bcm_sysport_netif_stop is replaced with netif_tx_disable to ensure synchronization with any transmit or timeout threads that may already be executing on other cores. For symmetry, the netif_device_attach call upon resume is moved to after the call to bcm_sysport_netif_start. Since it wakes the transmit queues it is not necessary to invoke netif_tx_start_all_queues from bcm_sysport_netif_start so it is moved into the driver open service. Fixes: 40755a0fce17 ("net: systemport: add suspend and resume support") Fixes: 80105befdb4b ("net: systemport: add Broadcom SYSTEMPORT Ethernet MAC driver") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bcmsysport.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 4122553e224b..0e2d99c737e3 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1902,9 +1902,6 @@ static void bcm_sysport_netif_start(struct net_device *dev) intrl2_1_mask_clear(priv, 0xffffffff); else intrl2_0_mask_clear(priv, INTRL2_0_TDMA_MBDONE_MASK); - - /* Last call before we start the real business */ - netif_tx_start_all_queues(dev); } static void rbuf_init(struct bcm_sysport_priv *priv) @@ -2048,6 +2045,8 @@ static int bcm_sysport_open(struct net_device *dev) bcm_sysport_netif_start(dev); + netif_tx_start_all_queues(dev); + return 0; out_clear_rx_int: @@ -2071,7 +2070,7 @@ static void bcm_sysport_netif_stop(struct net_device *dev) struct bcm_sysport_priv *priv = netdev_priv(dev); /* stop all software from updating hardware */ - netif_tx_stop_all_queues(dev); + netif_tx_disable(dev); napi_disable(&priv->napi); cancel_work_sync(&priv->dim.dim.work); phy_stop(dev->phydev); @@ -2658,12 +2657,12 @@ static int __maybe_unused bcm_sysport_suspend(struct device *d) if (!netif_running(dev)) return 0; + netif_device_detach(dev); + bcm_sysport_netif_stop(dev); phy_suspend(dev->phydev); - netif_device_detach(dev); - /* Disable UniMAC RX */ umac_enable_set(priv, CMD_RX_EN, 0); @@ -2746,8 +2745,6 @@ static int __maybe_unused bcm_sysport_resume(struct device *d) goto out_free_rx_ring; } - netif_device_attach(dev); - /* RX pipe enable */ topctrl_writel(priv, 0, RX_FLUSH_CNTL); @@ -2788,6 +2785,8 @@ static int __maybe_unused bcm_sysport_resume(struct device *d) bcm_sysport_netif_start(dev); + netif_device_attach(dev); + return 0; out_free_rx_ring: From cd26ea6d50a207ee37e0364ecc2d196d6c9671e8 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sat, 3 Nov 2018 08:19:56 -0300 Subject: [PATCH 046/356] perf trace: Fix setting of augmented payload when using eBPF + raw_syscalls For now with BPF raw_augmented we hook into raw_syscalls:sys_enter and there we get all 6 syscall args plus the tracepoint common fields (sizeof(long)) and the syscall_nr (another long). So we check if that is the case and if so don't look after the sc->args_size, but always after the full raw_syscalls:sys_enter payload, which is fixed. We'll revisit this later to pass s->args_size to the BPF augmenter (now tools/perf/examples/bpf/augmented_raw_syscalls.c, so that it copies only what we need for each syscall, like what happens when we use syscalls:sys_enter_NAME, so that we reduce the kernel/userspace traffic to just what is needed for each syscall. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-nlslrg8apxdsobt4pwl3n7ur@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 37 ++++++++++++++++++++++++++++++------- 1 file changed, 30 insertions(+), 7 deletions(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index f582ca575883..835619476370 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -108,6 +108,7 @@ struct trace { } stats; unsigned int max_stack; unsigned int min_stack; + bool raw_augmented_syscalls; bool not_ev_qualifier; bool live; bool full_time; @@ -1724,13 +1725,28 @@ static int trace__fprintf_sample(struct trace *trace, struct perf_evsel *evsel, return printed; } -static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size) +static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size, bool raw_augmented) { void *augmented_args = NULL; + /* + * For now with BPF raw_augmented we hook into raw_syscalls:sys_enter + * and there we get all 6 syscall args plus the tracepoint common + * fields (sizeof(long)) and the syscall_nr (another long). So we check + * if that is the case and if so don't look after the sc->args_size, + * but always after the full raw_syscalls:sys_enter payload, which is + * fixed. + * + * We'll revisit this later to pass s->args_size to the BPF augmenter + * (now tools/perf/examples/bpf/augmented_raw_syscalls.c, so that it + * copies only what we need for each syscall, like what happens when we + * use syscalls:sys_enter_NAME, so that we reduce the kernel/userspace + * traffic to just what is needed for each syscall. + */ + int args_size = raw_augmented ? (8 * (int)sizeof(long)) : sc->args_size; - *augmented_args_size = sample->raw_size - sc->args_size; + *augmented_args_size = sample->raw_size - args_size; if (*augmented_args_size > 0) - augmented_args = sample->raw_data + sc->args_size; + augmented_args = sample->raw_data + args_size; return augmented_args; } @@ -1780,7 +1796,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, * here and avoid using augmented syscalls when the evsel is the raw_syscalls one. */ if (evsel != trace->syscalls.events.sys_enter) - augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size); + augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls); ttrace->entry_time = sample->time; msg = ttrace->entry_str; printed += scnprintf(msg + printed, trace__entry_str_size - printed, "%s(", sc->name); @@ -1833,7 +1849,7 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evse goto out_put; args = perf_evsel__sc_tp_ptr(evsel, args, sample); - augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size); + augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls); syscall__scnprintf_args(sc, msg, sizeof(msg), args, augmented_args, augmented_args_size, trace, thread); fprintf(trace->output, "%s", msg); err = 0; @@ -3501,8 +3517,15 @@ int cmd_trace(int argc, const char **argv) evsel->handler = trace__sys_enter; evlist__for_each_entry(trace.evlist, evsel) { - if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_") || - strcmp(perf_evsel__name(evsel), "raw_syscalls:sys_exit") == 0) { + bool raw_syscalls_sys_exit = strcmp(perf_evsel__name(evsel), "raw_syscalls:sys_exit") == 0; + + if (raw_syscalls_sys_exit) { + trace.raw_augmented_syscalls = true; + goto init_augmented_syscall_tp; + } + + if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_")) { +init_augmented_syscall_tp: perf_evsel__init_augmented_syscall_tp(evsel); perf_evsel__init_augmented_syscall_tp_ret(evsel); evsel->handler = trace__sys_exit; From 17b8b74c0f8dbf9b9e3301f9ca5b65dd1c079951 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Fri, 19 Oct 2018 19:35:19 +0200 Subject: [PATCH 047/356] netfilter: ipset: Correct rcu_dereference() call in ip_set_put_comment() The function is called when rcu_read_lock() is held and not when rcu_read_lock_bh() is held. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set_comment.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/netfilter/ipset/ip_set_comment.h b/include/linux/netfilter/ipset/ip_set_comment.h index 8e2bab1e8e90..70877f8de7e9 100644 --- a/include/linux/netfilter/ipset/ip_set_comment.h +++ b/include/linux/netfilter/ipset/ip_set_comment.h @@ -43,11 +43,11 @@ ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment, rcu_assign_pointer(comment->c, c); } -/* Used only when dumping a set, protected by rcu_read_lock_bh() */ +/* Used only when dumping a set, protected by rcu_read_lock() */ static inline int ip_set_put_comment(struct sk_buff *skb, const struct ip_set_comment *comment) { - struct ip_set_comment_rcu *c = rcu_dereference_bh(comment->c); + struct ip_set_comment_rcu *c = rcu_dereference(comment->c); if (!c) return 0; From 54451f60c8fa061af9051a53be9786393947367c Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Sun, 21 Oct 2018 00:00:08 +0900 Subject: [PATCH 048/356] netfilter: xt_IDLETIMER: add sysfs filename checking routine When IDLETIMER rule is added, sysfs file is created under /sys/class/xt_idletimer/timers/ But some label name shouldn't be used. ".", "..", "power", "uevent", "subsystem", etc... So that sysfs filename checking routine is needed. test commands: %iptables -I INPUT -j IDLETIMER --timeout 1 --label "power" splat looks like: [95765.423132] sysfs: cannot create duplicate filename '/devices/virtual/xt_idletimer/timers/power' [95765.433418] CPU: 0 PID: 8446 Comm: iptables Not tainted 4.19.0-rc6+ #20 [95765.449755] Call Trace: [95765.449755] dump_stack+0xc9/0x16b [95765.449755] ? show_regs_print_info+0x5/0x5 [95765.449755] sysfs_warn_dup+0x74/0x90 [95765.449755] sysfs_add_file_mode_ns+0x352/0x500 [95765.449755] sysfs_create_file_ns+0x179/0x270 [95765.449755] ? sysfs_add_file_mode_ns+0x500/0x500 [95765.449755] ? idletimer_tg_checkentry+0x3e5/0xb1b [xt_IDLETIMER] [95765.449755] ? rcu_read_lock_sched_held+0x114/0x130 [95765.449755] ? __kmalloc_track_caller+0x211/0x2b0 [95765.449755] ? memcpy+0x34/0x50 [95765.449755] idletimer_tg_checkentry+0x4e2/0xb1b [xt_IDLETIMER] [ ... ] Fixes: 0902b469bd25 ("netfilter: xtables: idletimer target implementation") Signed-off-by: Taehee Yoo Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_IDLETIMER.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index c6acfc2d9c84..eb4cbd244c3d 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -114,6 +114,22 @@ static void idletimer_tg_expired(struct timer_list *t) schedule_work(&timer->work); } +static int idletimer_check_sysfs_name(const char *name, unsigned int size) +{ + int ret; + + ret = xt_check_proc_name(name, size); + if (ret < 0) + return ret; + + if (!strcmp(name, "power") || + !strcmp(name, "subsystem") || + !strcmp(name, "uevent")) + return -EINVAL; + + return 0; +} + static int idletimer_tg_create(struct idletimer_tg_info *info) { int ret; @@ -124,6 +140,10 @@ static int idletimer_tg_create(struct idletimer_tg_info *info) goto out; } + ret = idletimer_check_sysfs_name(info->label, sizeof(info->label)); + if (ret < 0) + goto out_free_timer; + sysfs_attr_init(&info->timer->attr.attr); info->timer->attr.attr.name = kstrdup(info->label, GFP_KERNEL); if (!info->timer->attr.attr.name) { From 8a02bdd50b2ecb6d62121d2958d3ea186cc88ce7 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Tue, 30 Oct 2018 22:43:42 +0100 Subject: [PATCH 049/356] netfilter: ipset: Fix calling ip_set() macro at dumping The ip_set() macro is called when either ip_set_ref_lock held only or no lock/nfnl mutex is held at dumping. Take this into account properly. Also, use Pablo's suggestion to use rcu_dereference_raw(), the ref_netlink protects the set. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipset/ip_set_core.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 68db946df151..1577f2f76060 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -55,11 +55,15 @@ MODULE_AUTHOR("Jozsef Kadlecsik "); MODULE_DESCRIPTION("core IP set support"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET); -/* When the nfnl mutex is held: */ +/* When the nfnl mutex or ip_set_ref_lock is held: */ #define ip_set_dereference(p) \ - rcu_dereference_protected(p, lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET)) + rcu_dereference_protected(p, \ + lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET) || \ + lockdep_is_held(&ip_set_ref_lock)) #define ip_set(inst, id) \ ip_set_dereference((inst)->ip_set_list)[id] +#define ip_set_ref_netlink(inst,id) \ + rcu_dereference_raw((inst)->ip_set_list)[id] /* The set types are implemented in modules and registered set types * can be found in ip_set_type_list. Adding/deleting types is @@ -1251,7 +1255,7 @@ ip_set_dump_done(struct netlink_callback *cb) struct ip_set_net *inst = (struct ip_set_net *)cb->args[IPSET_CB_NET]; ip_set_id_t index = (ip_set_id_t)cb->args[IPSET_CB_INDEX]; - struct ip_set *set = ip_set(inst, index); + struct ip_set *set = ip_set_ref_netlink(inst, index); if (set->variant->uref) set->variant->uref(set, cb, false); @@ -1440,7 +1444,7 @@ next_set: release_refcount: /* If there was an error or set is done, release set */ if (ret || !cb->args[IPSET_CB_ARG0]) { - set = ip_set(inst, index); + set = ip_set_ref_netlink(inst, index); if (set->variant->uref) set->variant->uref(set, cb, false); pr_debug("release set %s\n", set->name); From a95a7774d51e13f9cf4b7285666829b68852f07a Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 2 Nov 2018 00:11:34 +0100 Subject: [PATCH 050/356] netfilter: conntrack: add nf_{tcp,udp,sctp,icmp,dccp,icmpv6,generic}_pernet() Expose these functions to access conntrack protocol tracker netns area, nfnetlink_cttimeout needs this. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l4proto.h | 39 ++++++++++++++++++++ net/netfilter/nf_conntrack_proto_dccp.c | 13 ++----- net/netfilter/nf_conntrack_proto_generic.c | 11 ++---- net/netfilter/nf_conntrack_proto_icmp.c | 11 ++---- net/netfilter/nf_conntrack_proto_icmpv6.c | 11 ++---- net/netfilter/nf_conntrack_proto_sctp.c | 11 ++---- net/netfilter/nf_conntrack_proto_tcp.c | 15 +++----- net/netfilter/nf_conntrack_proto_udp.c | 11 ++---- 8 files changed, 63 insertions(+), 59 deletions(-) diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index eed04af9b75e..ae7b86f587f2 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -153,4 +153,43 @@ void nf_ct_l4proto_log_invalid(const struct sk_buff *skb, const char *fmt, ...) { } #endif /* CONFIG_SYSCTL */ +static inline struct nf_generic_net *nf_generic_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.generic; +} + +static inline struct nf_tcp_net *nf_tcp_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.tcp; +} + +static inline struct nf_udp_net *nf_udp_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.udp; +} + +static inline struct nf_icmp_net *nf_icmp_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.icmp; +} + +static inline struct nf_icmp_net *nf_icmpv6_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.icmpv6; +} + +#ifdef CONFIG_NF_CT_PROTO_DCCP +static inline struct nf_dccp_net *nf_dccp_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.dccp; +} +#endif + +#ifdef CONFIG_NF_CT_PROTO_SCTP +static inline struct nf_sctp_net *nf_sctp_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.sctp; +} +#endif + #endif /*_NF_CONNTRACK_PROTOCOL_H*/ diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 171e9e122e5f..023c1445bc39 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -384,11 +384,6 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] = }, }; -static inline struct nf_dccp_net *dccp_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.dccp; -} - static noinline bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb, const struct dccp_hdr *dh) @@ -401,7 +396,7 @@ dccp_new(struct nf_conn *ct, const struct sk_buff *skb, state = dccp_state_table[CT_DCCP_ROLE_CLIENT][dh->dccph_type][CT_DCCP_NONE]; switch (state) { default: - dn = dccp_pernet(net); + dn = nf_dccp_pernet(net); if (dn->dccp_loose == 0) { msg = "not picking up existing connection "; goto out_invalid; @@ -568,7 +563,7 @@ static int dccp_packet(struct nf_conn *ct, struct sk_buff *skb, timeouts = nf_ct_timeout_lookup(ct); if (!timeouts) - timeouts = dccp_pernet(nf_ct_net(ct))->dccp_timeout; + timeouts = nf_dccp_pernet(nf_ct_net(ct))->dccp_timeout; nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]); return NF_ACCEPT; @@ -681,7 +676,7 @@ static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct) static int dccp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { - struct nf_dccp_net *dn = dccp_pernet(net); + struct nf_dccp_net *dn = nf_dccp_pernet(net); unsigned int *timeouts = data; int i; @@ -814,7 +809,7 @@ static int dccp_kmemdup_sysctl_table(struct net *net, struct nf_proto_net *pn, static int dccp_init_net(struct net *net) { - struct nf_dccp_net *dn = dccp_pernet(net); + struct nf_dccp_net *dn = nf_dccp_pernet(net); struct nf_proto_net *pn = &dn->pn; if (!pn->users) { diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index e10e867e0b55..5da19d5fbc76 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -27,11 +27,6 @@ static bool nf_generic_should_process(u8 proto) } } -static inline struct nf_generic_net *generic_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.generic; -} - static bool generic_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, struct nf_conntrack_tuple *tuple) @@ -58,7 +53,7 @@ static int generic_packet(struct nf_conn *ct, } if (!timeout) - timeout = &generic_pernet(nf_ct_net(ct))->timeout; + timeout = &nf_generic_pernet(nf_ct_net(ct))->timeout; nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); return NF_ACCEPT; @@ -72,7 +67,7 @@ static int generic_packet(struct nf_conn *ct, static int generic_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { - struct nf_generic_net *gn = generic_pernet(net); + struct nf_generic_net *gn = nf_generic_pernet(net); unsigned int *timeout = data; if (!timeout) @@ -138,7 +133,7 @@ static int generic_kmemdup_sysctl_table(struct nf_proto_net *pn, static int generic_init_net(struct net *net) { - struct nf_generic_net *gn = generic_pernet(net); + struct nf_generic_net *gn = nf_generic_pernet(net); struct nf_proto_net *pn = &gn->pn; gn->timeout = nf_ct_generic_timeout; diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c index 3598520bd19b..de64d8a5fdfd 100644 --- a/net/netfilter/nf_conntrack_proto_icmp.c +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -25,11 +25,6 @@ static const unsigned int nf_ct_icmp_timeout = 30*HZ; -static inline struct nf_icmp_net *icmp_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.icmp; -} - static bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, struct nf_conntrack_tuple *tuple) { @@ -103,7 +98,7 @@ static int icmp_packet(struct nf_conn *ct, } if (!timeout) - timeout = &icmp_pernet(nf_ct_net(ct))->timeout; + timeout = &nf_icmp_pernet(nf_ct_net(ct))->timeout; nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); return NF_ACCEPT; @@ -275,7 +270,7 @@ static int icmp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeout = data; - struct nf_icmp_net *in = icmp_pernet(net); + struct nf_icmp_net *in = nf_icmp_pernet(net); if (tb[CTA_TIMEOUT_ICMP_TIMEOUT]) { if (!timeout) @@ -337,7 +332,7 @@ static int icmp_kmemdup_sysctl_table(struct nf_proto_net *pn, static int icmp_init_net(struct net *net) { - struct nf_icmp_net *in = icmp_pernet(net); + struct nf_icmp_net *in = nf_icmp_pernet(net); struct nf_proto_net *pn = &in->pn; in->timeout = nf_ct_icmp_timeout; diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c index 378618feed5d..a15eefb8e317 100644 --- a/net/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -30,11 +30,6 @@ static const unsigned int nf_ct_icmpv6_timeout = 30*HZ; -static inline struct nf_icmp_net *icmpv6_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.icmpv6; -} - static bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, @@ -87,7 +82,7 @@ static bool icmpv6_invert_tuple(struct nf_conntrack_tuple *tuple, static unsigned int *icmpv6_get_timeouts(struct net *net) { - return &icmpv6_pernet(net)->timeout; + return &nf_icmpv6_pernet(net)->timeout; } /* Returns verdict for packet, or -1 for invalid. */ @@ -286,7 +281,7 @@ static int icmpv6_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeout = data; - struct nf_icmp_net *in = icmpv6_pernet(net); + struct nf_icmp_net *in = nf_icmpv6_pernet(net); if (!timeout) timeout = icmpv6_get_timeouts(net); @@ -348,7 +343,7 @@ static int icmpv6_kmemdup_sysctl_table(struct nf_proto_net *pn, static int icmpv6_init_net(struct net *net) { - struct nf_icmp_net *in = icmpv6_pernet(net); + struct nf_icmp_net *in = nf_icmpv6_pernet(net); struct nf_proto_net *pn = &in->pn; in->timeout = nf_ct_icmpv6_timeout; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 3d719d3eb9a3..d53e3e78f605 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -146,11 +146,6 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { } }; -static inline struct nf_sctp_net *sctp_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.sctp; -} - #ifdef CONFIG_NF_CONNTRACK_PROCFS /* Print out the private part of the conntrack. */ static void sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct) @@ -480,7 +475,7 @@ static int sctp_packet(struct nf_conn *ct, timeouts = nf_ct_timeout_lookup(ct); if (!timeouts) - timeouts = sctp_pernet(nf_ct_net(ct))->timeouts; + timeouts = nf_sctp_pernet(nf_ct_net(ct))->timeouts; nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]); @@ -599,7 +594,7 @@ static int sctp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeouts = data; - struct nf_sctp_net *sn = sctp_pernet(net); + struct nf_sctp_net *sn = nf_sctp_pernet(net); int i; /* set default SCTP timeouts. */ @@ -736,7 +731,7 @@ static int sctp_kmemdup_sysctl_table(struct nf_proto_net *pn, static int sctp_init_net(struct net *net) { - struct nf_sctp_net *sn = sctp_pernet(net); + struct nf_sctp_net *sn = nf_sctp_pernet(net); struct nf_proto_net *pn = &sn->pn; if (!pn->users) { diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 1bcf9984d45e..4dcbd51a8e97 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -272,11 +272,6 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { } }; -static inline struct nf_tcp_net *tcp_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.tcp; -} - #ifdef CONFIG_NF_CONNTRACK_PROCFS /* Print out the private part of the conntrack. */ static void tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct) @@ -475,7 +470,7 @@ static bool tcp_in_window(const struct nf_conn *ct, const struct tcphdr *tcph) { struct net *net = nf_ct_net(ct); - struct nf_tcp_net *tn = tcp_pernet(net); + struct nf_tcp_net *tn = nf_tcp_pernet(net); struct ip_ct_tcp_state *sender = &state->seen[dir]; struct ip_ct_tcp_state *receiver = &state->seen[!dir]; const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple; @@ -767,7 +762,7 @@ static noinline bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, { enum tcp_conntrack new_state; struct net *net = nf_ct_net(ct); - const struct nf_tcp_net *tn = tcp_pernet(net); + const struct nf_tcp_net *tn = nf_tcp_pernet(net); const struct ip_ct_tcp_state *sender = &ct->proto.tcp.seen[0]; const struct ip_ct_tcp_state *receiver = &ct->proto.tcp.seen[1]; @@ -841,7 +836,7 @@ static int tcp_packet(struct nf_conn *ct, const struct nf_hook_state *state) { struct net *net = nf_ct_net(ct); - struct nf_tcp_net *tn = tcp_pernet(net); + struct nf_tcp_net *tn = nf_tcp_pernet(net); struct nf_conntrack_tuple *tuple; enum tcp_conntrack new_state, old_state; unsigned int index, *timeouts; @@ -1283,7 +1278,7 @@ static unsigned int tcp_nlattr_tuple_size(void) static int tcp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { - struct nf_tcp_net *tn = tcp_pernet(net); + struct nf_tcp_net *tn = nf_tcp_pernet(net); unsigned int *timeouts = data; int i; @@ -1508,7 +1503,7 @@ static int tcp_kmemdup_sysctl_table(struct nf_proto_net *pn, static int tcp_init_net(struct net *net) { - struct nf_tcp_net *tn = tcp_pernet(net); + struct nf_tcp_net *tn = nf_tcp_pernet(net); struct nf_proto_net *pn = &tn->pn; if (!pn->users) { diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index a7aa70370913..c879d8d78cfd 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -32,14 +32,9 @@ static const unsigned int udp_timeouts[UDP_CT_MAX] = { [UDP_CT_REPLIED] = 180*HZ, }; -static inline struct nf_udp_net *udp_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.udp; -} - static unsigned int *udp_get_timeouts(struct net *net) { - return udp_pernet(net)->timeouts; + return nf_udp_pernet(net)->timeouts; } static void udp_error_log(const struct sk_buff *skb, @@ -212,7 +207,7 @@ static int udp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeouts = data; - struct nf_udp_net *un = udp_pernet(net); + struct nf_udp_net *un = nf_udp_pernet(net); if (!timeouts) timeouts = un->timeouts; @@ -292,7 +287,7 @@ static int udp_kmemdup_sysctl_table(struct nf_proto_net *pn, static int udp_init_net(struct net *net) { - struct nf_udp_net *un = udp_pernet(net); + struct nf_udp_net *un = nf_udp_pernet(net); struct nf_proto_net *pn = &un->pn; if (!pn->users) { From 8866df9264a34e675b4ee8a151db819b87cce2d3 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 2 Nov 2018 00:14:00 +0100 Subject: [PATCH 051/356] netfilter: nfnetlink_cttimeout: pass default timeout policy to obj_to_nlattr Otherwise, we hit a NULL pointer deference since handlers always assume default timeout policy is passed. netlink: 24 bytes leftover after parsing attributes in process `syz-executor2'. 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: 0 PID: 9575 Comm: syz-executor1 Not tainted 4.19.0+ #312 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:icmp_timeout_obj_to_nlattr+0x77/0x170 net/netfilter/nf_conntrack_proto_icmp.c:297 Fixes: c779e849608a ("netfilter: conntrack: remove get_timeout() indirection") Reported-by: Eric Dumazet Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_cttimeout.c | 47 ++++++++++++++++++++++++----- 1 file changed, 40 insertions(+), 7 deletions(-) diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index e7a50af1b3d6..a518eb162344 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -382,7 +382,8 @@ err: static int cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid, u32 seq, u32 type, int event, u16 l3num, - const struct nf_conntrack_l4proto *l4proto) + const struct nf_conntrack_l4proto *l4proto, + const unsigned int *timeouts) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; @@ -408,7 +409,7 @@ cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid, if (!nest_parms) goto nla_put_failure; - ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, NULL); + ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, timeouts); if (ret < 0) goto nla_put_failure; @@ -430,6 +431,7 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, struct netlink_ext_ack *extack) { const struct nf_conntrack_l4proto *l4proto; + unsigned int *timeouts = NULL; struct sk_buff *skb2; int ret, err; __u16 l3num; @@ -442,12 +444,44 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, l4num = nla_get_u8(cda[CTA_TIMEOUT_L4PROTO]); l4proto = nf_ct_l4proto_find_get(l4num); - /* This protocol is not supported, skip. */ - if (l4proto->l4proto != l4num) { - err = -EOPNOTSUPP; + err = -EOPNOTSUPP; + if (l4proto->l4proto != l4num) goto err; + + switch (l4proto->l4proto) { + case IPPROTO_ICMP: + timeouts = &nf_icmp_pernet(net)->timeout; + break; + case IPPROTO_TCP: + timeouts = nf_tcp_pernet(net)->timeouts; + break; + case IPPROTO_UDP: + timeouts = nf_udp_pernet(net)->timeouts; + break; + case IPPROTO_DCCP: +#ifdef CONFIG_NF_CT_PROTO_DCCP + timeouts = nf_dccp_pernet(net)->dccp_timeout; +#endif + break; + case IPPROTO_ICMPV6: + timeouts = &nf_icmpv6_pernet(net)->timeout; + break; + case IPPROTO_SCTP: +#ifdef CONFIG_NF_CT_PROTO_SCTP + timeouts = nf_sctp_pernet(net)->timeouts; +#endif + break; + case 255: + timeouts = &nf_generic_pernet(net)->timeout; + break; + default: + WARN_ON_ONCE(1); + break; } + if (!timeouts) + goto err; + skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (skb2 == NULL) { err = -ENOMEM; @@ -458,8 +492,7 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, nlh->nlmsg_seq, NFNL_MSG_TYPE(nlh->nlmsg_type), IPCTNL_MSG_TIMEOUT_DEFAULT_SET, - l3num, - l4proto); + l3num, l4proto, timeouts); if (ret <= 0) { kfree_skb(skb2); err = -ENOMEM; From e4844c9c62a0fe47980d6c3d4b7a096a5d755925 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 2 Nov 2018 11:33:37 +0100 Subject: [PATCH 052/356] netfilter: nft_compat: ebtables 'nat' table is normal chain type Unlike ip(6)tables, the ebtables nat table has no special properties. This bug causes 'ebtables -A' to fail when using a target such as 'snat' (ebt_snat target sets ".table = "nat"'). Targets that have no table restrictions work fine. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_compat.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 768292eac2a4..9d0ede474224 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -54,9 +54,11 @@ static bool nft_xt_put(struct nft_xt *xt) return false; } -static int nft_compat_chain_validate_dependency(const char *tablename, - const struct nft_chain *chain) +static int nft_compat_chain_validate_dependency(const struct nft_ctx *ctx, + const char *tablename) { + enum nft_chain_types type = NFT_CHAIN_T_DEFAULT; + const struct nft_chain *chain = ctx->chain; const struct nft_base_chain *basechain; if (!tablename || @@ -64,9 +66,12 @@ static int nft_compat_chain_validate_dependency(const char *tablename, return 0; basechain = nft_base_chain(chain); - if (strcmp(tablename, "nat") == 0 && - basechain->type->type != NFT_CHAIN_T_NAT) - return -EINVAL; + if (strcmp(tablename, "nat") == 0) { + if (ctx->family != NFPROTO_BRIDGE) + type = NFT_CHAIN_T_NAT; + if (basechain->type->type != type) + return -EINVAL; + } return 0; } @@ -342,8 +347,7 @@ static int nft_target_validate(const struct nft_ctx *ctx, if (target->hooks && !(hook_mask & target->hooks)) return -EINVAL; - ret = nft_compat_chain_validate_dependency(target->table, - ctx->chain); + ret = nft_compat_chain_validate_dependency(ctx, target->table); if (ret < 0) return ret; } @@ -590,8 +594,7 @@ static int nft_match_validate(const struct nft_ctx *ctx, if (match->hooks && !(hook_mask & match->hooks)) return -EINVAL; - ret = nft_compat_chain_validate_dependency(match->table, - ctx->chain); + ret = nft_compat_chain_validate_dependency(ctx, match->table); if (ret < 0) return ret; } From f393808dc64149ccd0e5a8427505ba2974a59854 Mon Sep 17 00:00:00 2001 From: Vasily Khoruzhick Date: Thu, 25 Oct 2018 12:15:43 -0700 Subject: [PATCH 053/356] netfilter: conntrack: fix calculation of next bucket number in early_drop If there's no entry to drop in bucket that corresponds to the hash, early_drop() should look for it in other buckets. But since it increments hash instead of bucket number, it actually looks in the same bucket 8 times: hsize is 16k by default (14 bits) and hash is 32-bit value, so reciprocal_scale(hash, hsize) returns the same value for hash..hash+7 in most cases. Fix it by increasing bucket number instead of hash and rename _hash to bucket to avoid future confusion. Fixes: 3e86638e9a0b ("netfilter: conntrack: consider ct netns in early_drop logic") Cc: # v4.7+ Signed-off-by: Vasily Khoruzhick Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_core.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index ca1168d67fac..e92e749aff53 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1073,19 +1073,22 @@ static unsigned int early_drop_list(struct net *net, return drops; } -static noinline int early_drop(struct net *net, unsigned int _hash) +static noinline int early_drop(struct net *net, unsigned int hash) { - unsigned int i; + unsigned int i, bucket; for (i = 0; i < NF_CT_EVICTION_RANGE; i++) { struct hlist_nulls_head *ct_hash; - unsigned int hash, hsize, drops; + unsigned int hsize, drops; rcu_read_lock(); nf_conntrack_get_ht(&ct_hash, &hsize); - hash = reciprocal_scale(_hash++, hsize); + if (!i) + bucket = reciprocal_scale(hash, hsize); + else + bucket = (bucket + 1) % hsize; - drops = early_drop_list(net, &ct_hash[hash]); + drops = early_drop_list(net, &ct_hash[bucket]); rcu_read_unlock(); if (drops) { From e19e5be8b4cafa8b3f8b0cd1b1dfe20fa0145b83 Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Fri, 2 Nov 2018 19:04:08 +0100 Subject: [PATCH 054/356] s390/qeth: sanitize strings in debug messages As Documentation/s390/s390dbf.txt states quite clearly, using any pointer in sprinf-formatted s390dbf debug entries is dangerous. The pointers are dereferenced whenever the trace file is read from. So if the referenced data has a shorter life-time than the trace file, any read operation can result in a use-after-free. So rip out all hazardous use of indirect data, and replace any usage of dev_name() and such by the Bus ID number. Signed-off-by: Julian Wiedmann Signed-off-by: David S. Miller --- drivers/s390/net/qeth_core.h | 15 +++- drivers/s390/net/qeth_core_main.c | 127 ++++++++++++++---------------- drivers/s390/net/qeth_l2_main.c | 24 +++--- drivers/s390/net/qeth_l3_main.c | 104 ++++++++---------------- 4 files changed, 119 insertions(+), 151 deletions(-) diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 6843bc7ee9f2..884ba9dfb341 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -87,6 +87,18 @@ struct qeth_dbf_info { #define SENSE_RESETTING_EVENT_BYTE 1 #define SENSE_RESETTING_EVENT_FLAG 0x80 +static inline u32 qeth_get_device_id(struct ccw_device *cdev) +{ + struct ccw_dev_id dev_id; + u32 id; + + ccw_device_get_id(cdev, &dev_id); + id = dev_id.devno; + id |= (u32) (dev_id.ssid << 16); + + return id; +} + /* * Common IO related definitions */ @@ -97,7 +109,8 @@ struct qeth_dbf_info { #define CARD_RDEV_ID(card) dev_name(&card->read.ccwdev->dev) #define CARD_WDEV_ID(card) dev_name(&card->write.ccwdev->dev) #define CARD_DDEV_ID(card) dev_name(&card->data.ccwdev->dev) -#define CHANNEL_ID(channel) dev_name(&channel->ccwdev->dev) +#define CCW_DEVID(cdev) (qeth_get_device_id(cdev)) +#define CARD_DEVID(card) (CCW_DEVID(CARD_RDEV(card))) /** * card stuff diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 3274f13aad57..639ac0aca1e9 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -554,8 +554,8 @@ static int __qeth_issue_next_read(struct qeth_card *card) if (!iob) { dev_warn(&card->gdev->dev, "The qeth device driver " "failed to recover an error on the device\n"); - QETH_DBF_MESSAGE(2, "%s issue_next_read failed: no iob " - "available\n", dev_name(&card->gdev->dev)); + QETH_DBF_MESSAGE(2, "issue_next_read on device %x failed: no iob available\n", + CARD_DEVID(card)); return -ENOMEM; } qeth_setup_ccw(channel->ccw, CCW_CMD_READ, QETH_BUFSIZE, iob->data); @@ -563,8 +563,8 @@ static int __qeth_issue_next_read(struct qeth_card *card) rc = ccw_device_start(channel->ccwdev, channel->ccw, (addr_t) iob, 0, 0); if (rc) { - QETH_DBF_MESSAGE(2, "%s error in starting next read ccw! " - "rc=%i\n", dev_name(&card->gdev->dev), rc); + 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); card->read_or_write_problem = 1; qeth_schedule_recovery(card); @@ -613,16 +613,14 @@ static void qeth_issue_ipa_msg(struct qeth_ipa_cmd *cmd, int rc, const char *ipa_name; int com = cmd->hdr.command; ipa_name = qeth_get_ipa_cmd_name(com); + if (rc) - QETH_DBF_MESSAGE(2, "IPA: %s(x%X) for %s/%s returned " - "x%X \"%s\"\n", - ipa_name, com, dev_name(&card->gdev->dev), - QETH_CARD_IFNAME(card), rc, - qeth_get_ipa_msg(rc)); + QETH_DBF_MESSAGE(2, "IPA: %s(%#x) for device %x returned %#x \"%s\"\n", + ipa_name, com, CARD_DEVID(card), rc, + qeth_get_ipa_msg(rc)); else - QETH_DBF_MESSAGE(5, "IPA: %s(x%X) for %s/%s succeeded\n", - ipa_name, com, dev_name(&card->gdev->dev), - QETH_CARD_IFNAME(card)); + QETH_DBF_MESSAGE(5, "IPA: %s(%#x) for device %x succeeded\n", + ipa_name, com, CARD_DEVID(card)); } static struct qeth_ipa_cmd *qeth_check_ipa_data(struct qeth_card *card, @@ -711,7 +709,7 @@ static int qeth_check_idx_response(struct qeth_card *card, QETH_DBF_HEX(CTRL, 2, buffer, QETH_DBF_CTRL_LEN); if ((buffer[2] & 0xc0) == 0xc0) { - QETH_DBF_MESSAGE(2, "received an IDX TERMINATE with cause code %#02x\n", + QETH_DBF_MESSAGE(2, "received an IDX TERMINATE with cause code %#04x\n", buffer[4]); QETH_CARD_TEXT(card, 2, "ckidxres"); QETH_CARD_TEXT(card, 2, " idxterm"); @@ -972,8 +970,8 @@ static int qeth_get_problem(struct qeth_card *card, struct ccw_device *cdev, QETH_CARD_TEXT(card, 2, "CGENCHK"); dev_warn(&cdev->dev, "The qeth device driver " "failed to recover an error on the device\n"); - QETH_DBF_MESSAGE(2, "%s check on device dstat=x%x, cstat=x%x\n", - dev_name(&cdev->dev), dstat, cstat); + QETH_DBF_MESSAGE(2, "check on channel %x with dstat=%#x, cstat=%#x\n", + CCW_DEVID(cdev), dstat, cstat); print_hex_dump(KERN_WARNING, "qeth: irb ", DUMP_PREFIX_OFFSET, 16, 1, irb, 64, 1); return 1; @@ -1013,8 +1011,8 @@ static long qeth_check_irb_error(struct qeth_card *card, switch (PTR_ERR(irb)) { case -EIO: - QETH_DBF_MESSAGE(2, "%s i/o-error on device\n", - dev_name(&cdev->dev)); + QETH_DBF_MESSAGE(2, "i/o-error on channel %x\n", + CCW_DEVID(cdev)); QETH_CARD_TEXT(card, 2, "ckirberr"); QETH_CARD_TEXT_(card, 2, " rc%d", -EIO); break; @@ -1031,8 +1029,8 @@ static long qeth_check_irb_error(struct qeth_card *card, } break; default: - QETH_DBF_MESSAGE(2, "%s unknown error %ld on device\n", - dev_name(&cdev->dev), PTR_ERR(irb)); + QETH_DBF_MESSAGE(2, "unknown error %ld on channel %x\n", + PTR_ERR(irb), CCW_DEVID(cdev)); QETH_CARD_TEXT(card, 2, "ckirberr"); QETH_CARD_TEXT(card, 2, " rc???"); } @@ -1114,9 +1112,9 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, dev_warn(&channel->ccwdev->dev, "The qeth device driver failed to recover " "an error on the device\n"); - QETH_DBF_MESSAGE(2, "%s sense data available. cstat " - "0x%X dstat 0x%X\n", - dev_name(&channel->ccwdev->dev), cstat, dstat); + QETH_DBF_MESSAGE(2, "sense data available on channel %x: cstat %#X dstat %#X\n", + CCW_DEVID(channel->ccwdev), cstat, + dstat); print_hex_dump(KERN_WARNING, "qeth: irb ", DUMP_PREFIX_OFFSET, 16, 1, irb, 32, 1); print_hex_dump(KERN_WARNING, "qeth: sense data ", @@ -1890,8 +1888,8 @@ static int qeth_idx_activate_channel(struct qeth_card *card, if (channel->state != CH_STATE_ACTIVATING) { dev_warn(&channel->ccwdev->dev, "The qeth device driver" " failed to recover an error on the device\n"); - QETH_DBF_MESSAGE(2, "%s IDX activate timed out\n", - dev_name(&channel->ccwdev->dev)); + QETH_DBF_MESSAGE(2, "IDX activate timed out on channel %x\n", + CCW_DEVID(channel->ccwdev)); QETH_DBF_TEXT_(SETUP, 2, "2err%d", -ETIME); return -ETIME; } @@ -1926,17 +1924,15 @@ static void qeth_idx_write_cb(struct qeth_card *card, "The adapter is used exclusively by another " "host\n"); else - QETH_DBF_MESSAGE(2, "%s IDX_ACTIVATE on write channel:" - " negative reply\n", - dev_name(&channel->ccwdev->dev)); + QETH_DBF_MESSAGE(2, "IDX_ACTIVATE on channel %x: negative reply\n", + CCW_DEVID(channel->ccwdev)); goto out; } memcpy(&temp, QETH_IDX_ACT_FUNC_LEVEL(iob->data), 2); if ((temp & ~0x0100) != qeth_peer_func_level(card->info.func_level)) { - QETH_DBF_MESSAGE(2, "%s IDX_ACTIVATE on write channel: " - "function level mismatch (sent: 0x%x, received: " - "0x%x)\n", dev_name(&channel->ccwdev->dev), - card->info.func_level, temp); + QETH_DBF_MESSAGE(2, "IDX_ACTIVATE on channel %x: function level mismatch (sent: %#x, received: %#x)\n", + CCW_DEVID(channel->ccwdev), + card->info.func_level, temp); goto out; } channel->state = CH_STATE_UP; @@ -1973,9 +1969,8 @@ static void qeth_idx_read_cb(struct qeth_card *card, "insufficient authorization\n"); break; default: - QETH_DBF_MESSAGE(2, "%s IDX_ACTIVATE on read channel:" - " negative reply\n", - dev_name(&channel->ccwdev->dev)); + QETH_DBF_MESSAGE(2, "IDX_ACTIVATE on channel %x: negative reply\n", + CCW_DEVID(channel->ccwdev)); } QETH_CARD_TEXT_(card, 2, "idxread%c", QETH_IDX_ACT_CAUSE_CODE(iob->data)); @@ -1984,10 +1979,9 @@ static void qeth_idx_read_cb(struct qeth_card *card, memcpy(&temp, QETH_IDX_ACT_FUNC_LEVEL(iob->data), 2); if (temp != qeth_peer_func_level(card->info.func_level)) { - QETH_DBF_MESSAGE(2, "%s IDX_ACTIVATE on read channel: function " - "level mismatch (sent: 0x%x, received: 0x%x)\n", - dev_name(&channel->ccwdev->dev), - card->info.func_level, temp); + QETH_DBF_MESSAGE(2, "IDX_ACTIVATE on channel %x: function level mismatch (sent: %#x, received: %#x)\n", + CCW_DEVID(channel->ccwdev), + card->info.func_level, temp); goto out; } memcpy(&card->token.issuer_rm_r, @@ -2096,9 +2090,8 @@ int qeth_send_control_data(struct qeth_card *card, int len, (addr_t) iob, 0, 0, event_timeout); spin_unlock_irq(get_ccwdev_lock(channel->ccwdev)); if (rc) { - QETH_DBF_MESSAGE(2, "%s qeth_send_control_data: " - "ccw_device_start rc = %i\n", - dev_name(&channel->ccwdev->dev), rc); + QETH_DBF_MESSAGE(2, "qeth_send_control_data on device %x: ccw_device_start rc = %i\n", + CARD_DEVID(card), rc); QETH_CARD_TEXT_(card, 2, " err%d", rc); spin_lock_irq(&card->lock); list_del_init(&reply->list); @@ -2853,8 +2846,8 @@ struct qeth_cmd_buffer *qeth_get_ipacmd_buffer(struct qeth_card *card, } else { dev_warn(&card->gdev->dev, "The qeth driver ran out of channel command buffers\n"); - QETH_DBF_MESSAGE(1, "%s The qeth driver ran out of channel command buffers", - dev_name(&card->gdev->dev)); + QETH_DBF_MESSAGE(1, "device %x ran out of channel command buffers", + CARD_DEVID(card)); } return iob; @@ -2989,10 +2982,9 @@ static int qeth_query_ipassists_cb(struct qeth_card *card, return 0; default: if (cmd->hdr.return_code) { - QETH_DBF_MESSAGE(1, "%s IPA_CMD_QIPASSIST: Unhandled " - "rc=%d\n", - dev_name(&card->gdev->dev), - cmd->hdr.return_code); + QETH_DBF_MESSAGE(1, "IPA_CMD_QIPASSIST on device %x: Unhandled rc=%#x\n", + CARD_DEVID(card), + cmd->hdr.return_code); return 0; } } @@ -3004,8 +2996,8 @@ static int qeth_query_ipassists_cb(struct qeth_card *card, card->options.ipa6.supported_funcs = cmd->hdr.ipa_supported; card->options.ipa6.enabled_funcs = cmd->hdr.ipa_enabled; } else - QETH_DBF_MESSAGE(1, "%s IPA_CMD_QIPASSIST: Flawed LIC detected" - "\n", dev_name(&card->gdev->dev)); + QETH_DBF_MESSAGE(1, "IPA_CMD_QIPASSIST on device %x: Flawed LIC detected\n", + CARD_DEVID(card)); return 0; } @@ -4297,10 +4289,9 @@ static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card, cmd->data.setadapterparms.hdr.return_code); if (cmd->data.setadapterparms.hdr.return_code != SET_ACCESS_CTRL_RC_SUCCESS) - QETH_DBF_MESSAGE(3, "ERR:SET_ACCESS_CTRL(%s,%d)==%d\n", - card->gdev->dev.kobj.name, - access_ctrl_req->subcmd_code, - cmd->data.setadapterparms.hdr.return_code); + QETH_DBF_MESSAGE(3, "ERR:SET_ACCESS_CTRL(%#x) on device %x: %#x\n", + access_ctrl_req->subcmd_code, CARD_DEVID(card), + cmd->data.setadapterparms.hdr.return_code); switch (cmd->data.setadapterparms.hdr.return_code) { case SET_ACCESS_CTRL_RC_SUCCESS: if (card->options.isolation == ISOLATION_MODE_NONE) { @@ -4312,14 +4303,14 @@ static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card, } break; case SET_ACCESS_CTRL_RC_ALREADY_NOT_ISOLATED: - QETH_DBF_MESSAGE(2, "%s QDIO data connection isolation already " - "deactivated\n", dev_name(&card->gdev->dev)); + QETH_DBF_MESSAGE(2, "QDIO data connection isolation on device %x already deactivated\n", + CARD_DEVID(card)); if (fallback) card->options.isolation = card->options.prev_isolation; break; case SET_ACCESS_CTRL_RC_ALREADY_ISOLATED: - QETH_DBF_MESSAGE(2, "%s QDIO data connection isolation already" - " activated\n", dev_name(&card->gdev->dev)); + QETH_DBF_MESSAGE(2, "QDIO data connection isolation on device %x already activated\n", + CARD_DEVID(card)); if (fallback) card->options.isolation = card->options.prev_isolation; break; @@ -4405,10 +4396,8 @@ int qeth_set_access_ctrl_online(struct qeth_card *card, int fallback) rc = qeth_setadpparms_set_access_ctrl(card, card->options.isolation, fallback); if (rc) { - QETH_DBF_MESSAGE(3, - "IPA(SET_ACCESS_CTRL,%s,%d) sent failed\n", - card->gdev->dev.kobj.name, - rc); + QETH_DBF_MESSAGE(3, "IPA(SET_ACCESS_CTRL(%d) on device %x: sent failed\n", + rc, CARD_DEVID(card)); rc = -EOPNOTSUPP; } } else if (card->options.isolation != ISOLATION_MODE_NONE) { @@ -4634,8 +4623,8 @@ static int qeth_snmp_command(struct qeth_card *card, char __user *udata) rc = qeth_send_ipa_snmp_cmd(card, iob, QETH_SETADP_BASE_LEN + req_len, qeth_snmp_command_cb, (void *)&qinfo); if (rc) - QETH_DBF_MESSAGE(2, "SNMP command failed on %s: (0x%x)\n", - QETH_CARD_IFNAME(card), rc); + QETH_DBF_MESSAGE(2, "SNMP command failed on device %x: (%#x)\n", + CARD_DEVID(card), rc); else { if (copy_to_user(udata, qinfo.udata, qinfo.udata_len)) rc = -EFAULT; @@ -4869,8 +4858,8 @@ static void qeth_determine_capabilities(struct qeth_card *card) rc = qeth_read_conf_data(card, (void **) &prcd, &length); if (rc) { - QETH_DBF_MESSAGE(2, "%s qeth_read_conf_data returned %i\n", - dev_name(&card->gdev->dev), rc); + QETH_DBF_MESSAGE(2, "qeth_read_conf_data on device %x returned %i\n", + CARD_DEVID(card), rc); QETH_DBF_TEXT_(SETUP, 2, "5err%d", rc); goto out_offline; } @@ -5096,8 +5085,8 @@ int qeth_core_hardsetup_card(struct qeth_card *card) qeth_update_from_chp_desc(card); retry: if (retries < 3) - QETH_DBF_MESSAGE(2, "%s Retrying to do IDX activates.\n", - dev_name(&card->gdev->dev)); + QETH_DBF_MESSAGE(2, "Retrying to do IDX activates on device %x.\n", + CARD_DEVID(card)); rc = qeth_qdio_clear_card(card, card->info.type != QETH_CARD_TYPE_IQD); ccw_device_set_offline(CARD_DDEV(card)); ccw_device_set_offline(CARD_WDEV(card)); @@ -5201,8 +5190,8 @@ retriable: out: dev_warn(&card->gdev->dev, "The qeth device driver failed to recover " "an error on the device\n"); - QETH_DBF_MESSAGE(2, "%s Initialization in hardsetup failed! rc=%d\n", - dev_name(&card->gdev->dev), rc); + QETH_DBF_MESSAGE(2, "Initialization for device %x failed in hardsetup! rc=%d\n", + CARD_DEVID(card), rc); return rc; } EXPORT_SYMBOL_GPL(qeth_core_hardsetup_card); diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 23aaf373f631..5b67fd1f2b77 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -146,11 +146,11 @@ static int qeth_l2_write_mac(struct qeth_card *card, u8 *mac) QETH_CARD_TEXT(card, 2, "L2Wmac"); rc = qeth_l2_send_setdelmac(card, mac, cmd); if (rc == -EEXIST) - QETH_DBF_MESSAGE(2, "MAC %pM already registered on %s\n", - mac, QETH_CARD_IFNAME(card)); + QETH_DBF_MESSAGE(2, "MAC already registered on device %x\n", + CARD_DEVID(card)); else if (rc) - QETH_DBF_MESSAGE(2, "Failed to register MAC %pM on %s: %d\n", - mac, QETH_CARD_IFNAME(card), rc); + QETH_DBF_MESSAGE(2, "Failed to register MAC on device %x: %d\n", + CARD_DEVID(card), rc); return rc; } @@ -163,8 +163,8 @@ static int qeth_l2_remove_mac(struct qeth_card *card, u8 *mac) QETH_CARD_TEXT(card, 2, "L2Rmac"); rc = qeth_l2_send_setdelmac(card, mac, cmd); if (rc) - QETH_DBF_MESSAGE(2, "Failed to delete MAC %pM on %s: %d\n", - mac, QETH_CARD_IFNAME(card), rc); + QETH_DBF_MESSAGE(2, "Failed to delete MAC on device %u: %d\n", + CARD_DEVID(card), rc); return rc; } @@ -260,9 +260,9 @@ static int qeth_l2_send_setdelvlan_cb(struct qeth_card *card, QETH_CARD_TEXT(card, 2, "L2sdvcb"); if (cmd->hdr.return_code) { - QETH_DBF_MESSAGE(2, "Error in processing VLAN %i on %s: 0x%x.\n", + QETH_DBF_MESSAGE(2, "Error in processing VLAN %u on device %x: %#x.\n", cmd->data.setdelvlan.vlan_id, - QETH_CARD_IFNAME(card), cmd->hdr.return_code); + CARD_DEVID(card), cmd->hdr.return_code); QETH_CARD_TEXT_(card, 2, "L2VL%4x", cmd->hdr.command); QETH_CARD_TEXT_(card, 2, "err%d", cmd->hdr.return_code); } @@ -455,8 +455,8 @@ static int qeth_l2_request_initial_mac(struct qeth_card *card) rc = qeth_vm_request_mac(card); if (!rc) goto out; - QETH_DBF_MESSAGE(2, "z/VM MAC Service failed on device %s: x%x\n", - CARD_BUS_ID(card), rc); + QETH_DBF_MESSAGE(2, "z/VM MAC Service failed on device %x: %#x\n", + CARD_DEVID(card), rc); QETH_DBF_TEXT_(SETUP, 2, "err%04x", rc); /* fall back to alternative mechanism: */ } @@ -468,8 +468,8 @@ static int qeth_l2_request_initial_mac(struct qeth_card *card) rc = qeth_setadpparms_change_macaddr(card); if (!rc) goto out; - QETH_DBF_MESSAGE(2, "READ_MAC Assist failed on device %s: x%x\n", - CARD_BUS_ID(card), rc); + QETH_DBF_MESSAGE(2, "READ_MAC Assist failed on device %x: %#x\n", + CARD_DEVID(card), rc); QETH_DBF_TEXT_(SETUP, 2, "1err%04x", rc); /* fall back once more: */ } diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 0b161cc1fd2e..ffa2aa1dd4c5 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -494,9 +494,8 @@ int qeth_l3_setrouting_v4(struct qeth_card *card) QETH_PROT_IPV4); if (rc) { card->options.route4.type = NO_ROUTER; - QETH_DBF_MESSAGE(2, "Error (0x%04x) while setting routing type" - " on %s. Type set to 'no router'.\n", rc, - QETH_CARD_IFNAME(card)); + QETH_DBF_MESSAGE(2, "Error (%#06x) while setting routing type on device %x. Type set to 'no router'.\n", + rc, CARD_DEVID(card)); } return rc; } @@ -518,9 +517,8 @@ int qeth_l3_setrouting_v6(struct qeth_card *card) QETH_PROT_IPV6); if (rc) { card->options.route6.type = NO_ROUTER; - QETH_DBF_MESSAGE(2, "Error (0x%04x) while setting routing type" - " on %s. Type set to 'no router'.\n", rc, - QETH_CARD_IFNAME(card)); + QETH_DBF_MESSAGE(2, "Error (%#06x) while setting routing type on device %x. Type set to 'no router'.\n", + rc, CARD_DEVID(card)); } return rc; } @@ -1070,8 +1068,8 @@ qeth_diags_trace_cb(struct qeth_card *card, struct qeth_reply *reply, } break; default: - QETH_DBF_MESSAGE(2, "Unknown sniffer action (0x%04x) on %s\n", - cmd->data.diagass.action, QETH_CARD_IFNAME(card)); + QETH_DBF_MESSAGE(2, "Unknown sniffer action (%#06x) on device %x\n", + cmd->data.diagass.action, CARD_DEVID(card)); } return 0; @@ -1517,32 +1515,25 @@ static void qeth_l3_set_rx_mode(struct net_device *dev) qeth_l3_handle_promisc_mode(card); } -static const char *qeth_l3_arp_get_error_cause(int *rc) +static int qeth_l3_arp_makerc(int rc) { - switch (*rc) { - case QETH_IPA_ARP_RC_FAILED: - *rc = -EIO; - return "operation failed"; + switch (rc) { + case IPA_RC_SUCCESS: + return 0; case QETH_IPA_ARP_RC_NOTSUPP: - *rc = -EOPNOTSUPP; - return "operation not supported"; - case QETH_IPA_ARP_RC_OUT_OF_RANGE: - *rc = -EINVAL; - return "argument out of range"; case QETH_IPA_ARP_RC_Q_NOTSUPP: - *rc = -EOPNOTSUPP; - return "query operation not supported"; + return -EOPNOTSUPP; + case QETH_IPA_ARP_RC_OUT_OF_RANGE: + return -EINVAL; case QETH_IPA_ARP_RC_Q_NO_DATA: - *rc = -ENOENT; - return "no query data available"; + return -ENOENT; default: - return "unknown error"; + return -EIO; } } static int qeth_l3_arp_set_no_entries(struct qeth_card *card, int no_entries) { - int tmp; int rc; QETH_CARD_TEXT(card, 3, "arpstnoe"); @@ -1560,13 +1551,10 @@ static int qeth_l3_arp_set_no_entries(struct qeth_card *card, int no_entries) rc = qeth_send_simple_setassparms(card, IPA_ARP_PROCESSING, IPA_CMD_ASS_ARP_SET_NO_ENTRIES, no_entries); - if (rc) { - tmp = rc; - QETH_DBF_MESSAGE(2, "Could not set number of ARP entries on " - "%s: %s (0x%x/%d)\n", QETH_CARD_IFNAME(card), - qeth_l3_arp_get_error_cause(&rc), tmp, tmp); - } - return rc; + if (rc) + QETH_DBF_MESSAGE(2, "Could not set number of ARP entries on device %x: %#x\n", + CARD_DEVID(card), rc); + return qeth_l3_arp_makerc(rc); } static __u32 get_arp_entry_size(struct qeth_card *card, @@ -1716,7 +1704,6 @@ static int qeth_l3_query_arp_cache_info(struct qeth_card *card, { struct qeth_cmd_buffer *iob; struct qeth_ipa_cmd *cmd; - int tmp; int rc; QETH_CARD_TEXT_(card, 3, "qarpipv%i", prot); @@ -1735,15 +1722,10 @@ static int qeth_l3_query_arp_cache_info(struct qeth_card *card, rc = qeth_l3_send_ipa_arp_cmd(card, iob, QETH_SETASS_BASE_LEN+QETH_ARP_CMD_LEN, qeth_l3_arp_query_cb, (void *)qinfo); - if (rc) { - tmp = rc; - QETH_DBF_MESSAGE(2, - "Error while querying ARP cache on %s: %s " - "(0x%x/%d)\n", QETH_CARD_IFNAME(card), - qeth_l3_arp_get_error_cause(&rc), tmp, tmp); - } - - return rc; + if (rc) + QETH_DBF_MESSAGE(2, "Error while querying ARP cache on device %x: %#x\n", + CARD_DEVID(card), rc); + return qeth_l3_arp_makerc(rc); } static int qeth_l3_arp_query(struct qeth_card *card, char __user *udata) @@ -1797,8 +1779,6 @@ static int qeth_l3_arp_add_entry(struct qeth_card *card, struct qeth_arp_cache_entry *entry) { struct qeth_cmd_buffer *iob; - char buf[16]; - int tmp; int rc; QETH_CARD_TEXT(card, 3, "arpadent"); @@ -1824,14 +1804,10 @@ static int qeth_l3_arp_add_entry(struct qeth_card *card, sizeof(struct qeth_arp_cache_entry), (unsigned long) entry, qeth_setassparms_cb, NULL); - if (rc) { - tmp = rc; - qeth_l3_ipaddr4_to_string((u8 *)entry->ipaddr, buf); - QETH_DBF_MESSAGE(2, "Could not add ARP entry for address %s " - "on %s: %s (0x%x/%d)\n", buf, QETH_CARD_IFNAME(card), - qeth_l3_arp_get_error_cause(&rc), tmp, tmp); - } - return rc; + if (rc) + QETH_DBF_MESSAGE(2, "Could not add ARP entry on device %x: %#x\n", + CARD_DEVID(card), rc); + return qeth_l3_arp_makerc(rc); } static int qeth_l3_arp_remove_entry(struct qeth_card *card, @@ -1839,7 +1815,6 @@ static int qeth_l3_arp_remove_entry(struct qeth_card *card, { struct qeth_cmd_buffer *iob; char buf[16] = {0, }; - int tmp; int rc; QETH_CARD_TEXT(card, 3, "arprment"); @@ -1864,21 +1839,15 @@ static int qeth_l3_arp_remove_entry(struct qeth_card *card, rc = qeth_send_setassparms(card, iob, 12, (unsigned long)buf, qeth_setassparms_cb, NULL); - if (rc) { - tmp = rc; - memset(buf, 0, 16); - qeth_l3_ipaddr4_to_string((u8 *)entry->ipaddr, buf); - QETH_DBF_MESSAGE(2, "Could not delete ARP entry for address %s" - " on %s: %s (0x%x/%d)\n", buf, QETH_CARD_IFNAME(card), - qeth_l3_arp_get_error_cause(&rc), tmp, tmp); - } - return rc; + if (rc) + QETH_DBF_MESSAGE(2, "Could not delete ARP entry on device %x: %#x\n", + CARD_DEVID(card), rc); + return qeth_l3_arp_makerc(rc); } static int qeth_l3_arp_flush_cache(struct qeth_card *card) { int rc; - int tmp; QETH_CARD_TEXT(card, 3, "arpflush"); @@ -1894,13 +1863,10 @@ static int qeth_l3_arp_flush_cache(struct qeth_card *card) } rc = qeth_send_simple_setassparms(card, IPA_ARP_PROCESSING, IPA_CMD_ASS_ARP_FLUSH_CACHE, 0); - if (rc) { - tmp = rc; - QETH_DBF_MESSAGE(2, "Could not flush ARP cache on %s: %s " - "(0x%x/%d)\n", QETH_CARD_IFNAME(card), - qeth_l3_arp_get_error_cause(&rc), tmp, tmp); - } - return rc; + if (rc) + QETH_DBF_MESSAGE(2, "Could not flush ARP cache on device %x: %#x\n", + CARD_DEVID(card), rc); + return qeth_l3_arp_makerc(rc); } static int qeth_l3_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) From bd74a7f9cc033cf4d405788f80292268987dc0c5 Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Fri, 2 Nov 2018 19:04:09 +0100 Subject: [PATCH 055/356] s390/qeth: fix HiperSockets sniffer Sniffing mode for L3 HiperSockets requires that no IP addresses are registered with the HW. The preferred way to achieve this is for userspace to delete all the IPs on the interface. But qeth is expected to also tolerate a configuration where that is not the case, by skipping the IP registration when in sniffer mode. Since commit 5f78e29ceebf ("qeth: optimize IP handling in rx_mode callback") reworked the IP registration logic in the L3 subdriver, this no longer works. When the qeth device is set online, qeth_l3_recover_ip() now unconditionally registers all unicast addresses from our internal IP table. While we could fix this particular problem by skipping qeth_l3_recover_ip() on a sniffer device, the more future-proof change is to skip the IP address registration at the lowest level. This way we a) catch any future code path that attempts to register an IP address without considering the sniffer scenario, and b) continue to build up our internal IP table, so that if sniffer mode is switched off later we can operate just like normal. Fixes: 5f78e29ceebf ("qeth: optimize IP handling in rx_mode callback") Signed-off-by: Julian Wiedmann Signed-off-by: David S. Miller --- drivers/s390/net/qeth_l3_main.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index ffa2aa1dd4c5..968e344a240b 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -278,9 +278,6 @@ static void qeth_l3_clear_ip_htable(struct qeth_card *card, int recover) QETH_CARD_TEXT(card, 4, "clearip"); - if (recover && card->options.sniffer) - return; - spin_lock_bh(&card->ip_lock); hash_for_each_safe(card->ip_htable, i, tmp, addr, hnode) { @@ -661,6 +658,8 @@ static int qeth_l3_register_addr_entry(struct qeth_card *card, int rc = 0; int cnt = 3; + if (card->options.sniffer) + return 0; if (addr->proto == QETH_PROT_IPV4) { QETH_CARD_TEXT(card, 2, "setaddr4"); @@ -695,6 +694,9 @@ static int qeth_l3_deregister_addr_entry(struct qeth_card *card, { int rc = 0; + if (card->options.sniffer) + return 0; + if (addr->proto == QETH_PROT_IPV4) { QETH_CARD_TEXT(card, 2, "deladdr4"); QETH_CARD_HEX(card, 3, &addr->u.a4.addr, sizeof(int)); From 30356d08159d7899438e94503ae322a8b881e205 Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Fri, 2 Nov 2018 19:04:10 +0100 Subject: [PATCH 056/356] s390/qeth: unregister netdevice only when registered qeth only registers its netdevice when the qeth device is first set online. Thus a device that has never been set online will trigger a WARN ("network todo 'hsi%d' but state 0") in unregister_netdev() when removed. Fix this by protecting the unregister step, just like we already protect against repeated registering of the netdevice. Fixes: d3d1b205e89f ("s390/qeth: allocate netdevice early") Reported-by: Karsten Graul Signed-off-by: Julian Wiedmann Signed-off-by: David S. Miller --- drivers/s390/net/qeth_core.h | 5 +++++ drivers/s390/net/qeth_l2_main.c | 5 +++-- drivers/s390/net/qeth_l3_main.c | 5 +++-- 3 files changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 884ba9dfb341..b3a0b8838d2f 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -843,6 +843,11 @@ struct qeth_trap_id { /*some helper functions*/ #define QETH_CARD_IFNAME(card) (((card)->dev)? (card)->dev->name : "") +static inline bool qeth_netdev_is_registered(struct net_device *dev) +{ + return dev->netdev_ops != NULL; +} + static inline void qeth_scrub_qdio_buffer(struct qdio_buffer *buf, unsigned int elements) { diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 5b67fd1f2b77..2b978eba7e30 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -826,7 +826,8 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev) if (cgdev->state == CCWGROUP_ONLINE) qeth_l2_set_offline(cgdev); - unregister_netdev(card->dev); + if (qeth_netdev_is_registered(card->dev)) + unregister_netdev(card->dev); } static const struct ethtool_ops qeth_l2_ethtool_ops = { @@ -866,7 +867,7 @@ static int qeth_l2_setup_netdev(struct qeth_card *card) { int rc; - if (card->dev->netdev_ops) + if (qeth_netdev_is_registered(card->dev)) return 0; card->dev->priv_flags |= IFF_UNICAST_FLT; diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 968e344a240b..a719c5ec4171 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -2356,7 +2356,7 @@ static int qeth_l3_setup_netdev(struct qeth_card *card) unsigned int headroom; int rc; - if (card->dev->netdev_ops) + if (qeth_netdev_is_registered(card->dev)) return 0; if (card->info.type == QETH_CARD_TYPE_OSD || @@ -2465,7 +2465,8 @@ static void qeth_l3_remove_device(struct ccwgroup_device *cgdev) if (cgdev->state == CCWGROUP_ONLINE) qeth_l3_set_offline(cgdev); - unregister_netdev(card->dev); + if (qeth_netdev_is_registered(card->dev)) + unregister_netdev(card->dev); qeth_l3_clear_ip_htable(card, 0); qeth_l3_clear_ipato_list(card); } From 9fae5c3b60396b8586881a0e7c028ae5bcaeaa3f Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Fri, 2 Nov 2018 19:04:11 +0100 Subject: [PATCH 057/356] s390/qeth: fix initial operstate Setting the carrier 'on' for an unregistered netdevice doesn't update its operstate. Fix this by delaying the update until the netdevice has been registered. Fixes: 91cc98f51e3d ("s390/qeth: remove duplicated carrier state tracking") 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 | 13 ++++++++++--- drivers/s390/net/qeth_l2_main.c | 10 +++++++--- drivers/s390/net/qeth_l3_main.c | 10 +++++++--- 4 files changed, 25 insertions(+), 10 deletions(-) diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index b3a0b8838d2f..90cb213b0d55 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -991,7 +991,7 @@ int qeth_wait_for_threads(struct qeth_card *, unsigned long); int qeth_do_run_thread(struct qeth_card *, unsigned long); void qeth_clear_thread_start_bit(struct qeth_card *, unsigned long); void qeth_clear_thread_running_bit(struct qeth_card *, unsigned long); -int qeth_core_hardsetup_card(struct qeth_card *); +int qeth_core_hardsetup_card(struct qeth_card *card, bool *carrier_ok); void qeth_print_status_message(struct qeth_card *); int qeth_init_qdio_queues(struct qeth_card *); int qeth_send_ipa_cmd(struct qeth_card *, struct qeth_cmd_buffer *, diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 639ac0aca1e9..aed1a7961553 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -5075,7 +5075,7 @@ static struct ccw_driver qeth_ccw_driver = { .remove = ccwgroup_remove_ccwdev, }; -int qeth_core_hardsetup_card(struct qeth_card *card) +int qeth_core_hardsetup_card(struct qeth_card *card, bool *carrier_ok) { int retries = 3; int rc; @@ -5150,13 +5150,20 @@ retriable: if (rc == IPA_RC_LAN_OFFLINE) { dev_warn(&card->gdev->dev, "The LAN is offline\n"); - netif_carrier_off(card->dev); + *carrier_ok = false; } else { rc = -ENODEV; goto out; } } else { - netif_carrier_on(card->dev); + *carrier_ok = true; + } + + if (qeth_netdev_is_registered(card->dev)) { + if (*carrier_ok) + netif_carrier_on(card->dev); + else + netif_carrier_off(card->dev); } card->options.ipa4.supported_funcs = 0; diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 2b978eba7e30..2914a1a69f83 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -863,7 +863,7 @@ static const struct net_device_ops qeth_l2_netdev_ops = { .ndo_set_features = qeth_set_features }; -static int qeth_l2_setup_netdev(struct qeth_card *card) +static int qeth_l2_setup_netdev(struct qeth_card *card, bool carrier_ok) { int rc; @@ -920,6 +920,9 @@ static int qeth_l2_setup_netdev(struct qeth_card *card) qeth_l2_request_initial_mac(card); netif_napi_add(card->dev, &card->napi, qeth_poll, QETH_NAPI_WEIGHT); rc = register_netdev(card->dev); + if (!rc && carrier_ok) + netif_carrier_on(card->dev); + if (rc) card->dev->netdev_ops = NULL; return rc; @@ -950,6 +953,7 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode) struct qeth_card *card = dev_get_drvdata(&gdev->dev); int rc = 0; enum qeth_card_states recover_flag; + bool carrier_ok; mutex_lock(&card->discipline_mutex); mutex_lock(&card->conf_mutex); @@ -957,7 +961,7 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode) QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *)); recover_flag = card->state; - rc = qeth_core_hardsetup_card(card); + rc = qeth_core_hardsetup_card(card, &carrier_ok); if (rc) { QETH_DBF_TEXT_(SETUP, 2, "2err%04x", rc); rc = -ENODEV; @@ -968,7 +972,7 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode) dev_info(&card->gdev->dev, "The device represents a Bridge Capable Port\n"); - rc = qeth_l2_setup_netdev(card); + rc = qeth_l2_setup_netdev(card, carrier_ok); if (rc) goto out_remove; diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index a719c5ec4171..b26f7d7a2ca0 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -2351,7 +2351,7 @@ static const struct net_device_ops qeth_l3_osa_netdev_ops = { .ndo_neigh_setup = qeth_l3_neigh_setup, }; -static int qeth_l3_setup_netdev(struct qeth_card *card) +static int qeth_l3_setup_netdev(struct qeth_card *card, bool carrier_ok) { unsigned int headroom; int rc; @@ -2425,6 +2425,9 @@ static int qeth_l3_setup_netdev(struct qeth_card *card) netif_napi_add(card->dev, &card->napi, qeth_poll, QETH_NAPI_WEIGHT); rc = register_netdev(card->dev); + if (!rc && carrier_ok) + netif_carrier_on(card->dev); + out: if (rc) card->dev->netdev_ops = NULL; @@ -2476,6 +2479,7 @@ static int __qeth_l3_set_online(struct ccwgroup_device *gdev, int recovery_mode) struct qeth_card *card = dev_get_drvdata(&gdev->dev); int rc = 0; enum qeth_card_states recover_flag; + bool carrier_ok; mutex_lock(&card->discipline_mutex); mutex_lock(&card->conf_mutex); @@ -2483,14 +2487,14 @@ static int __qeth_l3_set_online(struct ccwgroup_device *gdev, int recovery_mode) QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *)); recover_flag = card->state; - rc = qeth_core_hardsetup_card(card); + rc = qeth_core_hardsetup_card(card, &carrier_ok); if (rc) { QETH_DBF_TEXT_(SETUP, 2, "2err%04x", rc); rc = -ENODEV; goto out_remove; } - rc = qeth_l3_setup_netdev(card); + rc = qeth_l3_setup_netdev(card, carrier_ok); if (rc) goto out_remove; From 125d7d30111738a5bdafacc1ed87cd3d7f32b4ea Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Fri, 2 Nov 2018 19:04:12 +0100 Subject: [PATCH 058/356] s390/qeth: sanitize ARP requests The ARP_{ADD,REMOVE}_ENTRY cmd structs contain reserved fields. Introduce a common helper that doesn't raw-copy the user-provided data into the cmd, but only sets those fields that are strictly needed for the command. This also sets the correct command length for ARP_REMOVE_ENTRY. Signed-off-by: Julian Wiedmann Signed-off-by: David S. Miller --- drivers/s390/net/qeth_core.h | 5 -- drivers/s390/net/qeth_core_main.c | 12 ++-- drivers/s390/net/qeth_core_mpc.h | 2 +- drivers/s390/net/qeth_l3_main.c | 94 +++++++++---------------------- 4 files changed, 34 insertions(+), 79 deletions(-) diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 90cb213b0d55..04e294d1d16d 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -1046,11 +1046,6 @@ int qeth_configure_cq(struct qeth_card *, enum qeth_cq); int qeth_hw_trap(struct qeth_card *, enum qeth_diags_trap_action); void qeth_trace_features(struct qeth_card *); void qeth_close_dev(struct qeth_card *); -int qeth_send_setassparms(struct qeth_card *, struct qeth_cmd_buffer *, __u16, - long, - int (*reply_cb)(struct qeth_card *, - struct qeth_reply *, unsigned long), - void *); int qeth_setassparms_cb(struct qeth_card *, struct qeth_reply *, unsigned long); struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *, enum qeth_ipa_funcs, diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index aed1a7961553..82282b2092d8 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -5477,11 +5477,12 @@ struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *card, } EXPORT_SYMBOL_GPL(qeth_get_setassparms_cmd); -int qeth_send_setassparms(struct qeth_card *card, - struct qeth_cmd_buffer *iob, __u16 len, long data, - int (*reply_cb)(struct qeth_card *, - struct qeth_reply *, unsigned long), - void *reply_param) +static int qeth_send_setassparms(struct qeth_card *card, + struct qeth_cmd_buffer *iob, u16 len, + long data, int (*reply_cb)(struct qeth_card *, + struct qeth_reply *, + unsigned long), + void *reply_param) { int rc; struct qeth_ipa_cmd *cmd; @@ -5497,7 +5498,6 @@ int qeth_send_setassparms(struct qeth_card *card, rc = qeth_send_ipa_cmd(card, iob, reply_cb, reply_param); return rc; } -EXPORT_SYMBOL_GPL(qeth_send_setassparms); int qeth_send_simple_setassparms_prot(struct qeth_card *card, enum qeth_ipa_funcs ipa_func, diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h index e85090467afe..80c036acf563 100644 --- a/drivers/s390/net/qeth_core_mpc.h +++ b/drivers/s390/net/qeth_core_mpc.h @@ -436,7 +436,7 @@ struct qeth_ipacmd_setassparms { __u32 flags_32bit; struct qeth_ipa_caps caps; struct qeth_checksum_cmd chksum; - struct qeth_arp_cache_entry add_arp_entry; + struct qeth_arp_cache_entry arp_entry; struct qeth_arp_query_data query_arp; struct qeth_tso_start_data tso; __u8 ip[16]; diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index b26f7d7a2ca0..f08b745c2007 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -1777,13 +1777,18 @@ out: return rc; } -static int qeth_l3_arp_add_entry(struct qeth_card *card, - struct qeth_arp_cache_entry *entry) +static int qeth_l3_arp_modify_entry(struct qeth_card *card, + struct qeth_arp_cache_entry *entry, + enum qeth_arp_process_subcmds arp_cmd) { + struct qeth_arp_cache_entry *cmd_entry; struct qeth_cmd_buffer *iob; int rc; - QETH_CARD_TEXT(card, 3, "arpadent"); + if (arp_cmd == IPA_CMD_ASS_ARP_ADD_ENTRY) + QETH_CARD_TEXT(card, 3, "arpadd"); + else + QETH_CARD_TEXT(card, 3, "arpdel"); /* * currently GuestLAN only supports the ARP assist function @@ -1796,54 +1801,19 @@ static int qeth_l3_arp_add_entry(struct qeth_card *card, return -EOPNOTSUPP; } - iob = qeth_get_setassparms_cmd(card, IPA_ARP_PROCESSING, - IPA_CMD_ASS_ARP_ADD_ENTRY, - sizeof(struct qeth_arp_cache_entry), - QETH_PROT_IPV4); + iob = qeth_get_setassparms_cmd(card, IPA_ARP_PROCESSING, arp_cmd, + sizeof(*cmd_entry), QETH_PROT_IPV4); if (!iob) return -ENOMEM; - rc = qeth_send_setassparms(card, iob, - sizeof(struct qeth_arp_cache_entry), - (unsigned long) entry, - qeth_setassparms_cb, NULL); + + cmd_entry = &__ipa_cmd(iob)->data.setassparms.data.arp_entry; + ether_addr_copy(cmd_entry->macaddr, entry->macaddr); + memcpy(cmd_entry->ipaddr, entry->ipaddr, 4); + rc = qeth_send_ipa_cmd(card, iob, qeth_setassparms_cb, NULL); if (rc) - QETH_DBF_MESSAGE(2, "Could not add ARP entry on device %x: %#x\n", - CARD_DEVID(card), rc); - return qeth_l3_arp_makerc(rc); -} + QETH_DBF_MESSAGE(2, "Could not modify (cmd: %#x) ARP entry on device %x: %#x\n", + arp_cmd, CARD_DEVID(card), rc); -static int qeth_l3_arp_remove_entry(struct qeth_card *card, - struct qeth_arp_cache_entry *entry) -{ - struct qeth_cmd_buffer *iob; - char buf[16] = {0, }; - int rc; - - QETH_CARD_TEXT(card, 3, "arprment"); - - /* - * currently GuestLAN only supports the ARP assist function - * IPA_CMD_ASS_ARP_QUERY_INFO, but not IPA_CMD_ASS_ARP_REMOVE_ENTRY; - * thus we say EOPNOTSUPP for this ARP function - */ - if (card->info.guestlan) - return -EOPNOTSUPP; - if (!qeth_is_supported(card, IPA_ARP_PROCESSING)) { - return -EOPNOTSUPP; - } - memcpy(buf, entry, 12); - iob = qeth_get_setassparms_cmd(card, IPA_ARP_PROCESSING, - IPA_CMD_ASS_ARP_REMOVE_ENTRY, - 12, - QETH_PROT_IPV4); - if (!iob) - return -ENOMEM; - rc = qeth_send_setassparms(card, iob, - 12, (unsigned long)buf, - qeth_setassparms_cb, NULL); - if (rc) - QETH_DBF_MESSAGE(2, "Could not delete ARP entry on device %x: %#x\n", - CARD_DEVID(card), rc); return qeth_l3_arp_makerc(rc); } @@ -1875,6 +1845,7 @@ static int qeth_l3_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) { struct qeth_card *card = dev->ml_priv; struct qeth_arp_cache_entry arp_entry; + enum qeth_arp_process_subcmds arp_cmd; int rc = 0; switch (cmd) { @@ -1893,27 +1864,16 @@ static int qeth_l3_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) rc = qeth_l3_arp_query(card, rq->ifr_ifru.ifru_data); break; case SIOC_QETH_ARP_ADD_ENTRY: - if (!capable(CAP_NET_ADMIN)) { - rc = -EPERM; - break; - } - if (copy_from_user(&arp_entry, rq->ifr_ifru.ifru_data, - sizeof(struct qeth_arp_cache_entry))) - rc = -EFAULT; - else - rc = qeth_l3_arp_add_entry(card, &arp_entry); - break; case SIOC_QETH_ARP_REMOVE_ENTRY: - if (!capable(CAP_NET_ADMIN)) { - rc = -EPERM; - break; - } - if (copy_from_user(&arp_entry, rq->ifr_ifru.ifru_data, - sizeof(struct qeth_arp_cache_entry))) - rc = -EFAULT; - else - rc = qeth_l3_arp_remove_entry(card, &arp_entry); - break; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (copy_from_user(&arp_entry, rq->ifr_data, sizeof(arp_entry))) + return -EFAULT; + + arp_cmd = (cmd == SIOC_QETH_ARP_ADD_ENTRY) ? + IPA_CMD_ASS_ARP_ADD_ENTRY : + IPA_CMD_ASS_ARP_REMOVE_ENTRY; + return qeth_l3_arp_modify_entry(card, &arp_entry, arp_cmd); case SIOC_QETH_ARP_FLUSH_CACHE: if (!capable(CAP_NET_ADMIN)) { rc = -EPERM; From 54e049c227d9968ff6a7d80aae5fec27b54d39da Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Fri, 2 Nov 2018 19:04:13 +0100 Subject: [PATCH 059/356] s390/qeth: report 25Gbit link speed This adds the various identifiers for 25Gbit cards, and wires them up into sysfs and ethtool. Signed-off-by: Julian Wiedmann Signed-off-by: David S. Miller --- drivers/s390/net/qeth_core_main.c | 20 ++++++++++++++++++-- drivers/s390/net/qeth_core_mpc.h | 2 ++ 2 files changed, 20 insertions(+), 2 deletions(-) diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 82282b2092d8..4bce5ae65a55 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -167,6 +167,8 @@ const char *qeth_get_cardname_short(struct qeth_card *card) return "OSD_1000"; case QETH_LINK_TYPE_10GBIT_ETH: return "OSD_10GIG"; + case QETH_LINK_TYPE_25GBIT_ETH: + return "OSD_25GIG"; case QETH_LINK_TYPE_LANE_ETH100: return "OSD_FE_LANE"; case QETH_LINK_TYPE_LANE_TR: @@ -4432,7 +4434,8 @@ static int qeth_mdio_read(struct net_device *dev, int phy_id, int regnum) rc = BMCR_FULLDPLX; if ((card->info.link_type != QETH_LINK_TYPE_GBIT_ETH) && (card->info.link_type != QETH_LINK_TYPE_OSN) && - (card->info.link_type != QETH_LINK_TYPE_10GBIT_ETH)) + (card->info.link_type != QETH_LINK_TYPE_10GBIT_ETH) && + (card->info.link_type != QETH_LINK_TYPE_25GBIT_ETH)) rc |= BMCR_SPEED100; break; case MII_BMSR: /* Basic mode status register */ @@ -6166,8 +6169,14 @@ static void qeth_set_cmd_adv_sup(struct ethtool_link_ksettings *cmd, WARN_ON_ONCE(1); } - /* fallthrough from high to low, to select all legal speeds: */ + /* partially does fall through, to also select lower speeds */ switch (maxspeed) { + case SPEED_25000: + ethtool_link_ksettings_add_link_mode(cmd, supported, + 25000baseSR_Full); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + 25000baseSR_Full); + break; case SPEED_10000: ethtool_link_ksettings_add_link_mode(cmd, supported, 10000baseT_Full); @@ -6250,6 +6259,10 @@ int qeth_core_ethtool_get_link_ksettings(struct net_device *netdev, cmd->base.speed = SPEED_10000; cmd->base.port = PORT_FIBRE; break; + case QETH_LINK_TYPE_25GBIT_ETH: + cmd->base.speed = SPEED_25000; + cmd->base.port = PORT_FIBRE; + break; default: cmd->base.speed = SPEED_10; cmd->base.port = PORT_TP; @@ -6316,6 +6329,9 @@ int qeth_core_ethtool_get_link_ksettings(struct net_device *netdev, case CARD_INFO_PORTS_10G: cmd->base.speed = SPEED_10000; break; + case CARD_INFO_PORTS_25G: + cmd->base.speed = SPEED_25000; + break; } return 0; diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h index 80c036acf563..3e54be201b27 100644 --- a/drivers/s390/net/qeth_core_mpc.h +++ b/drivers/s390/net/qeth_core_mpc.h @@ -90,6 +90,7 @@ enum qeth_link_types { QETH_LINK_TYPE_GBIT_ETH = 0x03, QETH_LINK_TYPE_OSN = 0x04, QETH_LINK_TYPE_10GBIT_ETH = 0x10, + QETH_LINK_TYPE_25GBIT_ETH = 0x12, QETH_LINK_TYPE_LANE_ETH100 = 0x81, QETH_LINK_TYPE_LANE_TR = 0x82, QETH_LINK_TYPE_LANE_ETH1000 = 0x83, @@ -347,6 +348,7 @@ enum qeth_card_info_port_speed { CARD_INFO_PORTS_100M = 0x00000006, CARD_INFO_PORTS_1G = 0x00000007, CARD_INFO_PORTS_10G = 0x00000008, + CARD_INFO_PORTS_25G = 0x0000000A, }; /* (SET)DELIP(M) IPA stuff ***************************************************/ From 9e4028935cca3f9ef9b6a90df9da6f1f94853536 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Sat, 3 Nov 2018 16:13:17 -0400 Subject: [PATCH 060/356] ext4: avoid potential extra brelse in setup_new_flex_group_blocks() Currently bh is set to NULL only during first iteration of for cycle, then this pointer is not cleared after end of using. Therefore rollback after errors can lead to extra brelse(bh) call, decrements bh counter and later trigger an unexpected warning in __brelse() Patch moves brelse() calls in body of cycle to exclude requirement of brelse() call in rollback. Fixes: 33afdcc5402d ("ext4: add a function which sets up group blocks ...") Signed-off-by: Vasily Averin Signed-off-by: Theodore Ts'o Cc: stable@kernel.org # 3.3+ --- fs/ext4/resize.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index ebbc663d0798..c3fa30878ca8 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -605,7 +605,6 @@ handle_bb: bh = bclean(handle, sb, block); if (IS_ERR(bh)) { err = PTR_ERR(bh); - bh = NULL; goto out; } overhead = ext4_group_overhead_blocks(sb, group); @@ -618,9 +617,9 @@ handle_bb: ext4_mark_bitmap_end(EXT4_B2C(sbi, group_data[i].blocks_count), sb->s_blocksize * 8, bh->b_data); err = ext4_handle_dirty_metadata(handle, NULL, bh); + brelse(bh); if (err) goto out; - brelse(bh); handle_ib: if (bg_flags[i] & EXT4_BG_INODE_UNINIT) @@ -635,18 +634,16 @@ handle_ib: bh = bclean(handle, sb, block); if (IS_ERR(bh)) { err = PTR_ERR(bh); - bh = NULL; goto out; } ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8, bh->b_data); err = ext4_handle_dirty_metadata(handle, NULL, bh); + brelse(bh); if (err) goto out; - brelse(bh); } - bh = NULL; /* Mark group tables in block bitmap */ for (j = 0; j < GROUP_TABLE_COUNT; j++) { @@ -685,7 +682,6 @@ handle_ib: } out: - brelse(bh); err2 = ext4_journal_stop(handle); if (err2 && !err) err = err2; From cea5794122125bf67559906a0762186cf417099c Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Sat, 3 Nov 2018 16:22:10 -0400 Subject: [PATCH 061/356] ext4: add missing brelse() in set_flexbg_block_bitmap()'s error path Fixes: 33afdcc5402d ("ext4: add a function which sets up group blocks ...") Cc: stable@kernel.org # 3.3 Signed-off-by: Vasily Averin Signed-off-by: Theodore Ts'o --- fs/ext4/resize.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index c3fa30878ca8..0a4dc6217e78 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -459,16 +459,18 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle, BUFFER_TRACE(bh, "get_write_access"); err = ext4_journal_get_write_access(handle, bh); - if (err) + if (err) { + brelse(bh); return err; + } ext4_debug("mark block bitmap %#04llx (+%llu/%u)\n", first_cluster, first_cluster - start, count2); ext4_set_bits(bh->b_data, first_cluster - start, count2); err = ext4_handle_dirty_metadata(handle, NULL, bh); + brelse(bh); if (unlikely(err)) return err; - brelse(bh); } return 0; From 61a9c11e5e7a0dab5381afa5d9d4dd5ebf18f7a0 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Sat, 3 Nov 2018 16:50:08 -0400 Subject: [PATCH 062/356] ext4: add missing brelse() add_new_gdb_meta_bg()'s error path Fixes: 01f795f9e0d6 ("ext4: add online resizing support for meta_bg ...") Signed-off-by: Vasily Averin Signed-off-by: Theodore Ts'o Cc: stable@kernel.org # 3.7 --- fs/ext4/resize.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 0a4dc6217e78..7131f35b62d9 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -922,6 +922,7 @@ static int add_new_gdb_meta_bg(struct super_block *sb, sizeof(struct buffer_head *), GFP_NOFS); if (!n_group_desc) { + brelse(gdb_bh); err = -ENOMEM; ext4_warning(sb, "not enough memory for %lu groups", gdb_num + 1); @@ -937,8 +938,6 @@ static int add_new_gdb_meta_bg(struct super_block *sb, kvfree(o_group_desc); BUFFER_TRACE(gdb_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, gdb_bh); - if (unlikely(err)) - brelse(gdb_bh); return err; } From ea0abbb648452cdb6e1734b702b6330a7448fcf8 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Sat, 3 Nov 2018 17:11:19 -0400 Subject: [PATCH 063/356] ext4: add missing brelse() update_backups()'s error path Fixes: ac27a0ec112a ("ext4: initial copy of files from ext3") Signed-off-by: Vasily Averin Signed-off-by: Theodore Ts'o Cc: stable@kernel.org # 2.6.19 --- fs/ext4/resize.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 7131f35b62d9..3df326ee6d50 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1121,8 +1121,10 @@ static void update_backups(struct super_block *sb, sector_t blk_off, char *data, backup_block, backup_block - ext4_group_first_block_no(sb, group)); BUFFER_TRACE(bh, "get_write_access"); - if ((err = ext4_journal_get_write_access(handle, bh))) + if ((err = ext4_journal_get_write_access(handle, bh))) { + brelse(bh); break; + } lock_buffer(bh); memcpy(bh->b_data, data, size); if (rest) From 3e59020abf0f88182730527ee5b862e786eb485a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 31 Oct 2018 08:39:12 -0700 Subject: [PATCH 064/356] net: bql: add __netdev_tx_sent_queue() When qdisc_run() tries to use BQL budget to bulk-dequeue a batch of packets, GSO can later transform this list in another list of skbs, and each skb is sent to device ndo_start_xmit(), one at a time, with skb->xmit_more being set to one but for last skb. Problem is that very often, BQL limit is hit in the middle of the packet train, forcing dev_hard_start_xmit() to stop the bulk send and requeue the end of the list. BQL role is to avoid head of line blocking, making sure a qdisc can deliver high priority packets before low priority ones. But there is no way requeued packets can be bypassed by fresh packets in the qdisc. Aborting the bulk send increases TX softirqs, and hot cache lines (after skb_segment()) are wasted. Note that for TSO packets, we never split a packet in the middle because of BQL limit being hit. Drivers should be able to update BQL counters without flipping/caring about BQL status, if the current skb has xmit_more set. Upper layers are ultimately responsible to stop sending another packet train when BQL limit is hit. Code template in a driver might look like the following : send_doorbell = __netdev_tx_sent_queue(tx_queue, nr_bytes, skb->xmit_more); Note that __netdev_tx_sent_queue() use is not mandatory, since following patch will change dev_hard_start_xmit() to not care about BQL status. But it is highly recommended so that xmit_more full benefits can be reached (less doorbells sent, and less atomic operations as well) Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index dc1d9ed33b31..857f8abf7b91 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3190,6 +3190,26 @@ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue, #endif } +/* Variant of netdev_tx_sent_queue() for drivers that are aware + * that they should not test BQL status themselves. + * We do want to change __QUEUE_STATE_STACK_XOFF only for the last + * skb of a batch. + * Returns true if the doorbell must be used to kick the NIC. + */ +static inline bool __netdev_tx_sent_queue(struct netdev_queue *dev_queue, + unsigned int bytes, + bool xmit_more) +{ + if (xmit_more) { +#ifdef CONFIG_BQL + dql_queued(&dev_queue->dql, bytes); +#endif + return netif_tx_queue_stopped(dev_queue); + } + netdev_tx_sent_queue(dev_queue, bytes); + return true; +} + /** * netdev_sent_queue - report the number of bytes queued to hardware * @dev: network device From fe60faa5063822f2d555f4f326c7dd72a60929bf Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 31 Oct 2018 08:39:13 -0700 Subject: [PATCH 065/356] net: do not abort bulk send on BQL status Before calling dev_hard_start_xmit(), upper layers tried to cook optimal skb list based on BQL budget. Problem is that GSO packets can end up comsuming more than the BQL budget. Breaking the loop is not useful, since requeued packets are ahead of any packets still in the qdisc. It is also more expensive, since next TX completion will push these packets later, while skbs are not in cpu caches. It is also a behavior difference with TSO packets, that can break the BQL limit by a large amount. Note that drivers should use __netdev_tx_sent_queue() in order to have optimal xmit_more support, and avoid useless atomic operations as shown in the following patch. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/dev.c b/net/core/dev.c index 77d43ae2a7bb..0ffcbdd55fa9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3272,7 +3272,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *first, struct net_device *de } skb = next; - if (netif_xmit_stopped(txq) && skb) { + if (netif_tx_queue_stopped(txq) && skb) { rc = NETDEV_TX_BUSY; break; } From c29734443511aa3c53844e1941805fc761aa80ba Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 31 Oct 2018 08:39:14 -0700 Subject: [PATCH 066/356] net/mlx4_en: use __netdev_tx_sent_queue() doorbell only depends on xmit_more and netif_tx_queue_stopped() Using __netdev_tx_sent_queue() avoids messing with BQL stop flag, and is more generic. This patch increases performance on GSO workload by keeping doorbells to the minimum required. Signed-off-by: Eric Dumazet Cc: Tariq Toukan Reviewed-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_tx.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 1857ee0f0871..6f5153afcab4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -1006,7 +1006,6 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) ring->packets++; } ring->bytes += tx_info->nr_bytes; - netdev_tx_sent_queue(ring->tx_queue, tx_info->nr_bytes); AVG_PERF_COUNTER(priv->pstats.tx_pktsz_avg, skb->len); if (tx_info->inl) @@ -1044,7 +1043,10 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) netif_tx_stop_queue(ring->tx_queue); ring->queue_stopped++; } - send_doorbell = !skb->xmit_more || netif_xmit_stopped(ring->tx_queue); + + send_doorbell = __netdev_tx_sent_queue(ring->tx_queue, + tx_info->nr_bytes, + skb->xmit_more); real_size = (real_size / 16) & 0x3f; From e8ccbb7d2f53c62e14b889faaa3f6f809b657278 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Fri, 2 Nov 2018 17:47:48 +0800 Subject: [PATCH 067/356] net: hns3: Fix for out-of-bounds access when setting pfc back pressure The vport should be initialized to hdev->vport for each bp group, otherwise it will cause out-of-bounds access and bp setting not correct problem. [ 35.254124] BUG: KASAN: slab-out-of-bounds in hclge_pause_setup_hw+0x2a0/0x3f8 [hclge] [ 35.254126] Read of size 2 at addr ffff803b6651581a by task kworker/0:1/14 [ 35.254132] CPU: 0 PID: 14 Comm: kworker/0:1 Not tainted 4.19.0-rc7-hulk+ #85 [ 35.254133] Hardware name: Huawei D06/D06, BIOS Hisilicon D06 UEFI RC0 - B052 (V0.52) 09/14/2018 [ 35.254141] Workqueue: events work_for_cpu_fn [ 35.254144] Call trace: [ 35.254147] dump_backtrace+0x0/0x2f0 [ 35.254149] show_stack+0x24/0x30 [ 35.254154] dump_stack+0x110/0x184 [ 35.254157] print_address_description+0x168/0x2b0 [ 35.254160] kasan_report+0x184/0x310 [ 35.254162] __asan_load2+0x7c/0xa0 [ 35.254170] hclge_pause_setup_hw+0x2a0/0x3f8 [hclge] [ 35.254177] hclge_tm_init_hw+0x794/0x9f0 [hclge] [ 35.254184] hclge_tm_schd_init+0x48/0x58 [hclge] [ 35.254191] hclge_init_ae_dev+0x778/0x1168 [hclge] [ 35.254196] hnae3_register_ae_dev+0x14c/0x298 [hnae3] [ 35.254206] hns3_probe+0x88/0xa8 [hns3] [ 35.254210] local_pci_probe+0x7c/0xf0 [ 35.254212] work_for_cpu_fn+0x34/0x50 [ 35.254214] process_one_work+0x4d4/0xa38 [ 35.254216] worker_thread+0x55c/0x8d8 [ 35.254219] kthread+0x1b0/0x1b8 [ 35.254222] ret_from_fork+0x10/0x1c [ 35.254224] The buggy address belongs to the page: [ 35.254228] page:ffff7e00ed994400 count:1 mapcount:0 mapping:0000000000000000 index:0x0 compound_mapcount: 0 [ 35.273835] flags: 0xfffff8000008000(head) [ 35.282007] raw: 0fffff8000008000 dead000000000100 dead000000000200 0000000000000000 [ 35.282010] raw: 0000000000000000 0000000000000000 00000001ffffffff 0000000000000000 [ 35.282012] page dumped because: kasan: bad access detected [ 35.282014] Memory state around the buggy address: [ 35.282017] ffff803b66515700: fe fe fe fe fe fe fe fe fe fe fe fe fe fe fe fe [ 35.282019] ffff803b66515780: fe fe fe fe fe fe fe fe fe fe fe fe fe fe fe fe [ 35.282021] >ffff803b66515800: fe fe fe fe fe fe fe fe fe fe fe fe fe fe fe fe [ 35.282022] ^ [ 35.282024] ffff803b66515880: fe fe fe fe fe fe fe fe fe fe fe fe fe fe fe fe [ 35.282026] ffff803b66515900: fe fe fe fe fe fe fe fe fe fe fe fe fe fe fe fe [ 35.282028] ================================================================== [ 35.282029] Disabling lock debugging due to kernel taint [ 35.282747] hclge driver initialization finished. Fixes: 67bf2541f4b9 ("net: hns3: Fixes the back pressure setting when sriov is enabled") Signed-off-by: Yunsheng Lin Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index aa5cb9834d73..494e562fe8c7 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -1168,14 +1168,14 @@ static int hclge_pfc_setup_hw(struct hclge_dev *hdev) */ static int hclge_bp_setup_hw(struct hclge_dev *hdev, u8 tc) { - struct hclge_vport *vport = hdev->vport; - u32 i, k, qs_bitmap; - int ret; + int i; for (i = 0; i < HCLGE_BP_GRP_NUM; i++) { - qs_bitmap = 0; + u32 qs_bitmap = 0; + int k, ret; for (k = 0; k < hdev->num_alloc_vport; k++) { + struct hclge_vport *vport = &hdev->vport[k]; u16 qs_id = vport->qs_offset + tc; u8 grp, sub_grp; @@ -1185,8 +1185,6 @@ static int hclge_bp_setup_hw(struct hclge_dev *hdev, u8 tc) HCLGE_BP_SUB_GRP_ID_S); if (i == grp) qs_bitmap |= (1 << sub_grp); - - vport++; } ret = hclge_tm_qs_bp_cfg(hdev, tc, i, qs_bitmap); From b987ffc18fb3b3b76b059aa9e372dbee26f7c4f2 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 2 Nov 2018 14:26:53 +0100 Subject: [PATCH 068/356] x86/qspinlock: Fix compile error With a compiler that has asm-goto but not asm-cc-output and CONFIG_PROFILE_ALL_BRANCHES=y we get a compiler error: arch/x86/include/asm/rmwcc.h:23:17: error: jump into statement expression Fix this by writing the if() as a boolean multiplication instead. Reported-by: kbuild test robot Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Cc: linux-kernel@vger.kernel.org Fixes: 7aa54be29765 ("locking/qspinlock, x86: Provide liveness guarantee") Signed-off-by: Ingo Molnar --- arch/x86/include/asm/qspinlock.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h index 87623c6b13db..bd5ac6cc37db 100644 --- a/arch/x86/include/asm/qspinlock.h +++ b/arch/x86/include/asm/qspinlock.h @@ -13,12 +13,15 @@ #define queued_fetch_set_pending_acquire queued_fetch_set_pending_acquire static __always_inline u32 queued_fetch_set_pending_acquire(struct qspinlock *lock) { - u32 val = 0; - - if (GEN_BINARY_RMWcc(LOCK_PREFIX "btsl", lock->val.counter, c, - "I", _Q_PENDING_OFFSET)) - val |= _Q_PENDING_VAL; + u32 val; + /* + * We can't use GEN_BINARY_RMWcc() inside an if() stmt because asm goto + * and CONFIG_PROFILE_ALL_BRANCHES=y results in a label inside a + * statement expression, which GCC doesn't like. + */ + val = GEN_BINARY_RMWcc(LOCK_PREFIX "btsl", lock->val.counter, c, + "I", _Q_PENDING_OFFSET) * _Q_PENDING_VAL; val |= atomic_read(&lock->val) & ~_Q_PENDING_MASK; return val; From 40fa3780bac2b654edf23f6b13f4e2dd550aea10 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 23 Oct 2018 14:37:31 +0100 Subject: [PATCH 069/356] sched/core: Take the hotplug lock in sched_init_smp() When running on linux-next (8c60c36d0b8c ("Add linux-next specific files for 20181019")) + CONFIG_PROVE_LOCKING=y on a big.LITTLE system (e.g. Juno or HiKey960), we get the following report: [ 0.748225] Call trace: [ 0.750685] lockdep_assert_cpus_held+0x30/0x40 [ 0.755236] static_key_enable_cpuslocked+0x20/0xc8 [ 0.760137] build_sched_domains+0x1034/0x1108 [ 0.764601] sched_init_domains+0x68/0x90 [ 0.768628] sched_init_smp+0x30/0x80 [ 0.772309] kernel_init_freeable+0x278/0x51c [ 0.776685] kernel_init+0x10/0x108 [ 0.780190] ret_from_fork+0x10/0x18 The static_key in question is 'sched_asym_cpucapacity' introduced by commit: df054e8445a4 ("sched/topology: Add static_key for asymmetric CPU capacity optimizations") In this particular case, we enable it because smp_prepare_cpus() will end up fetching the capacity-dmips-mhz entry from the devicetree, so we already have some asymmetry detected when entering sched_init_smp(). This didn't get detected in tip/sched/core because we were missing: commit cb538267ea1e ("jump_label/lockdep: Assert we hold the hotplug lock for _cpuslocked() operations") Calls to build_sched_domains() post sched_init_smp() will hold the hotplug lock, it just so happens that this very first call is a special case. As stated by a comment in sched_init_smp(), "There's no userspace yet to cause hotplug operations" so this is a harmless warning. However, to both respect the semantics of underlying callees and make lockdep happy, take the hotplug lock in sched_init_smp(). This also satisfies the comment atop sched_init_domains() that says "Callers must hold the hotplug lock". Reported-by: Sudeep Holla Tested-by: Sudeep Holla Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Cc: Dietmar.Eggemann@arm.com Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: morten.rasmussen@arm.com Cc: quentin.perret@arm.com Link: http://lkml.kernel.org/r/1540301851-3048-1-git-send-email-valentin.schneider@arm.com Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index fd2fce8a001b..02a20ef196a6 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5859,11 +5859,14 @@ void __init sched_init_smp(void) /* * There's no userspace yet to cause hotplug operations; hence all the * CPU masks are stable and all blatant races in the below code cannot - * happen. + * happen. The hotplug lock is nevertheless taken to satisfy lockdep, + * but there won't be any contention on it. */ + cpus_read_lock(); mutex_lock(&sched_domains_mutex); sched_init_domains(cpu_active_mask); mutex_unlock(&sched_domains_mutex); + cpus_read_unlock(); /* Move init over to a non-isolated CPU */ if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0) From 92619210529a6b77b2cbedbadba3ff5eaa6e28ed Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 2 Nov 2018 16:36:24 +0100 Subject: [PATCH 070/356] qed: fix link config error handling gcc-8 notices that qed_mcp_get_transceiver_data() may fail to return a result to the caller: drivers/net/ethernet/qlogic/qed/qed_mcp.c: In function 'qed_mcp_trans_speed_mask': drivers/net/ethernet/qlogic/qed/qed_mcp.c:1955:2: error: 'transceiver_type' may be used uninitialized in this function [-Werror=maybe-uninitialized] When an error is returned by qed_mcp_get_transceiver_data(), we should propagate that to the caller of qed_mcp_trans_speed_mask() rather than continuing with uninitialized data. Fixes: c56a8be7e7aa ("qed: Add supported link and advertise link to display in ethtool.") Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_mcp.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index f40f654398a0..a96364df4320 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -1944,9 +1944,12 @@ int qed_mcp_trans_speed_mask(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *p_speed_mask) { u32 transceiver_type, transceiver_state; + int ret; - qed_mcp_get_transceiver_data(p_hwfn, p_ptt, &transceiver_state, - &transceiver_type); + ret = qed_mcp_get_transceiver_data(p_hwfn, p_ptt, &transceiver_state, + &transceiver_type); + if (ret) + return ret; if (qed_is_transceiver_ready(transceiver_state, transceiver_type) == false) From a277d516de5f498c91d91189717ef7e01102ad27 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 2 Nov 2018 16:36:55 +0100 Subject: [PATCH 071/356] openvswitch: fix linking without CONFIG_NF_CONNTRACK_LABELS When CONFIG_CC_OPTIMIZE_FOR_DEBUGGING is enabled, the compiler fails to optimize out a dead code path, which leads to a link failure: net/openvswitch/conntrack.o: In function `ovs_ct_set_labels': conntrack.c:(.text+0x2e60): undefined reference to `nf_connlabels_replace' In this configuration, we can take a shortcut, and completely remove the contrack label code. This may also help the regular optimization. Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- net/openvswitch/conntrack.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 6bec37ab4472..a4660c48ff01 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1203,7 +1203,8 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, &info->labels.mask); if (err) return err; - } else if (labels_nonzero(&info->labels.mask)) { + } else if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && + labels_nonzero(&info->labels.mask)) { err = ovs_ct_set_labels(ct, key, &info->labels.value, &info->labels.mask); if (err) From 96801552f846460fe9ac10f1b189602992f004e1 Mon Sep 17 00:00:00 2001 From: Shalom Toledo Date: Fri, 2 Nov 2018 19:49:15 +0000 Subject: [PATCH 072/356] mlxsw: spectrum: Fix IP2ME CPU policer configuration The CPU policer used to police packets being trapped via a local route (IP2ME) was incorrectly configured to police based on bytes per second instead of packets per second. Change the policer to police based on packets per second and avoid packet loss under certain circumstances. Fixes: 9148e7cf73ce ("mlxsw: spectrum: Add policers for trap groups") Signed-off-by: Shalom Toledo Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index a2df12b79f8e..9bec940330a4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -3568,7 +3568,6 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core) burst_size = 7; break; case MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME: - is_bytes = true; rate = 4 * 1024; burst_size = 4; break; From fd82d61ba142f0b83463e47064bf5460aac57b6e Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 3 Nov 2018 13:59:45 +0800 Subject: [PATCH 073/356] sctp: fix strchange_flags name for Stream Change Event As defined in rfc6525#section-6.1.3, SCTP_STREAM_CHANGE_DENIED and SCTP_STREAM_CHANGE_FAILED should be used instead of SCTP_ASSOC_CHANGE_DENIED and SCTP_ASSOC_CHANGE_FAILED. To keep the compatibility, fix it by adding two macros. Fixes: b444153fb5a6 ("sctp: add support for generating add stream change event notification") Reported-by: Jianwen Ji Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/uapi/linux/sctp.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 34dd3d497f2c..680ecc3bf2a9 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -568,6 +568,8 @@ struct sctp_assoc_reset_event { #define SCTP_ASSOC_CHANGE_DENIED 0x0004 #define SCTP_ASSOC_CHANGE_FAILED 0x0008 +#define SCTP_STREAM_CHANGE_DENIED SCTP_ASSOC_CHANGE_DENIED +#define SCTP_STREAM_CHANGE_FAILED SCTP_ASSOC_CHANGE_FAILED struct sctp_stream_change_event { __u16 strchange_type; __u16 strchange_flags; From 12480e3b16982c4026de10dd8155823219cd6391 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 3 Nov 2018 14:01:31 +0800 Subject: [PATCH 074/356] sctp: define SCTP_SS_DEFAULT for Stream schedulers According to rfc8260#section-4.3.2, SCTP_SS_DEFAULT is required to defined as SCTP_SS_FCFS or SCTP_SS_RR. SCTP_SS_FCFS is used for SCTP_SS_DEFAULT's value in this patch. Fixes: 5bbbbe32a431 ("sctp: introduce stream scheduler foundations") Reported-by: Jianwen Ji Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/uapi/linux/sctp.h | 1 + net/sctp/outqueue.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 680ecc3bf2a9..c81feb373d3e 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -1153,6 +1153,7 @@ struct sctp_add_streams { /* SCTP Stream schedulers */ enum sctp_sched_type { SCTP_SS_FCFS, + SCTP_SS_DEFAULT = SCTP_SS_FCFS, SCTP_SS_PRIO, SCTP_SS_RR, SCTP_SS_MAX = SCTP_SS_RR diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 9cb854b05342..c37e1c2dec9d 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -212,7 +212,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q) INIT_LIST_HEAD(&q->retransmit); INIT_LIST_HEAD(&q->sacked); INIT_LIST_HEAD(&q->abandoned); - sctp_sched_set_sched(asoc, SCTP_SS_FCFS); + sctp_sched_set_sched(asoc, SCTP_SS_DEFAULT); } /* Free the outqueue structure and any related pending chunks. From 35b69a420bfb56b7b74cb635ea903db05e357bec Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Sun, 4 Nov 2018 03:48:54 +0000 Subject: [PATCH 075/356] clockevents/drivers/i8253: Add support for PIT shutdown quirk Add support for platforms where pit_shutdown() doesn't work because of a quirk in the PIT emulation. On these platforms setting the counter register to zero causes the PIT to start running again, negating the shutdown. Provide a global variable that controls whether the counter register is zero'ed, which platform specific code can override. Signed-off-by: Michael Kelley Signed-off-by: Thomas Gleixner Cc: "gregkh@linuxfoundation.org" Cc: "devel@linuxdriverproject.org" Cc: "daniel.lezcano@linaro.org" Cc: "virtualization@lists.linux-foundation.org" Cc: "jgross@suse.com" Cc: "akataria@vmware.com" Cc: "olaf@aepfle.de" Cc: "apw@canonical.com" Cc: vkuznets Cc: "jasowang@redhat.com" Cc: "marcelo.cerri@canonical.com" Cc: KY Srinivasan Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/1541303219-11142-2-git-send-email-mikelley@microsoft.com --- drivers/clocksource/i8253.c | 14 ++++++++++++-- include/linux/i8253.h | 1 + 2 files changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/clocksource/i8253.c b/drivers/clocksource/i8253.c index 9c38895542f4..d4350bb10b83 100644 --- a/drivers/clocksource/i8253.c +++ b/drivers/clocksource/i8253.c @@ -20,6 +20,13 @@ DEFINE_RAW_SPINLOCK(i8253_lock); EXPORT_SYMBOL(i8253_lock); +/* + * Handle PIT quirk in pit_shutdown() where zeroing the counter register + * restarts the PIT, negating the shutdown. On platforms with the quirk, + * platform specific code can set this to false. + */ +bool i8253_clear_counter_on_shutdown __ro_after_init = true; + #ifdef CONFIG_CLKSRC_I8253 /* * Since the PIT overflows every tick, its not very useful @@ -109,8 +116,11 @@ static int pit_shutdown(struct clock_event_device *evt) raw_spin_lock(&i8253_lock); outb_p(0x30, PIT_MODE); - outb_p(0, PIT_CH0); - outb_p(0, PIT_CH0); + + if (i8253_clear_counter_on_shutdown) { + outb_p(0, PIT_CH0); + outb_p(0, PIT_CH0); + } raw_spin_unlock(&i8253_lock); return 0; diff --git a/include/linux/i8253.h b/include/linux/i8253.h index e6bb36a97519..8336b2f6f834 100644 --- a/include/linux/i8253.h +++ b/include/linux/i8253.h @@ -21,6 +21,7 @@ #define PIT_LATCH ((PIT_TICK_RATE + HZ/2) / HZ) extern raw_spinlock_t i8253_lock; +extern bool i8253_clear_counter_on_shutdown; extern struct clock_event_device i8253_clockevent; extern void clockevent_i8253_init(bool oneshot); From 1de72c706488b7be664a601cf3843bd01e327e58 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Sun, 4 Nov 2018 03:48:57 +0000 Subject: [PATCH 076/356] x86/hyper-v: Enable PIT shutdown quirk Hyper-V emulation of the PIT has a quirk such that the normal PIT shutdown path doesn't work, because clearing the counter register restarts the timer. Disable the counter clearing on PIT shutdown. Signed-off-by: Michael Kelley Signed-off-by: Thomas Gleixner Cc: "gregkh@linuxfoundation.org" Cc: "devel@linuxdriverproject.org" Cc: "daniel.lezcano@linaro.org" Cc: "virtualization@lists.linux-foundation.org" Cc: "jgross@suse.com" Cc: "akataria@vmware.com" Cc: "olaf@aepfle.de" Cc: "apw@canonical.com" Cc: vkuznets Cc: "jasowang@redhat.com" Cc: "marcelo.cerri@canonical.com" Cc: KY Srinivasan Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/1541303219-11142-3-git-send-email-mikelley@microsoft.com --- arch/x86/kernel/cpu/mshyperv.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 1c72f3819eb1..e81a2db42df7 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -295,6 +296,16 @@ static void __init ms_hyperv_init_platform(void) if (efi_enabled(EFI_BOOT)) x86_platform.get_nmi_reason = hv_get_nmi_reason; + /* + * Hyper-V VMs have a PIT emulation quirk such that zeroing the + * counter register during PIT shutdown restarts the PIT. So it + * continues to interrupt @18.2 HZ. Setting i8253_clear_counter + * to false tells pit_shutdown() not to zero the counter so that + * the PIT really is shutdown. Generation 2 VMs don't have a PIT, + * and setting this value has no effect. + */ + i8253_clear_counter_on_shutdown = false; + #if IS_ENABLED(CONFIG_HYPERV) /* * Setup the hook to get control post apic initialization. From 74e3512731bd5c9673176425a76a7cc5efa8ddb6 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Wed, 24 Oct 2018 22:37:13 +0300 Subject: [PATCH 077/356] hwmon: (core) Fix double-free in __hwmon_device_register() Fix double-free that happens when thermal zone setup fails, see KASAN log below. ================================================================== BUG: KASAN: double-free or invalid-free in __hwmon_device_register+0x5dc/0xa7c CPU: 0 PID: 132 Comm: kworker/0:2 Tainted: G B 4.19.0-rc8-next-20181016-00042-gb52cd80401e9-dirty #41 Hardware name: NVIDIA Tegra SoC (Flattened Device Tree) Workqueue: events deferred_probe_work_func Backtrace: [] (dump_backtrace) from [] (show_stack+0x20/0x24) [] (show_stack) from [] (dump_stack+0x9c/0xb0) [] (dump_stack) from [] (print_address_description+0x68/0x250) [] (print_address_description) from [] (kasan_report_invalid_free+0x68/0x88) [] (kasan_report_invalid_free) from [] (__kasan_slab_free+0x1f4/0x200) [] (__kasan_slab_free) from [] (kasan_slab_free+0x14/0x18) [] (kasan_slab_free) from [] (kfree+0x90/0x294) [] (kfree) from [] (__hwmon_device_register+0x5dc/0xa7c) [] (__hwmon_device_register) from [] (hwmon_device_register_with_info+0xa0/0xa8) [] (hwmon_device_register_with_info) from [] (devm_hwmon_device_register_with_info+0x74/0xb4) [] (devm_hwmon_device_register_with_info) from [] (lm90_probe+0x414/0x578) [] (lm90_probe) from [] (i2c_device_probe+0x35c/0x384) [] (i2c_device_probe) from [] (really_probe+0x290/0x3e4) [] (really_probe) from [] (driver_probe_device+0x80/0x1c4) [] (driver_probe_device) from [] (__device_attach_driver+0x104/0x11c) [] (__device_attach_driver) from [] (bus_for_each_drv+0xa4/0xc8) [] (bus_for_each_drv) from [] (__device_attach+0xf0/0x15c) [] (__device_attach) from [] (device_initial_probe+0x1c/0x20) [] (device_initial_probe) from [] (bus_probe_device+0xdc/0xec) [] (bus_probe_device) from [] (deferred_probe_work_func+0xa8/0xd4) [] (deferred_probe_work_func) from [] (process_one_work+0x3dc/0x96c) [] (process_one_work) from [] (worker_thread+0x4ec/0x8bc) [] (worker_thread) from [] (kthread+0x230/0x240) [] (kthread) from [] (ret_from_fork+0x14/0x38) Exception stack(0xcf743fb0 to 0xcf743ff8) 3fa0: 00000000 00000000 00000000 00000000 3fc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 3fe0: 00000000 00000000 00000000 00000000 00000013 00000000 Allocated by task 132: kasan_kmalloc.part.1+0x58/0xf4 kasan_kmalloc+0x90/0xa4 kmem_cache_alloc_trace+0x90/0x2a0 __hwmon_device_register+0xbc/0xa7c hwmon_device_register_with_info+0xa0/0xa8 devm_hwmon_device_register_with_info+0x74/0xb4 lm90_probe+0x414/0x578 i2c_device_probe+0x35c/0x384 really_probe+0x290/0x3e4 driver_probe_device+0x80/0x1c4 __device_attach_driver+0x104/0x11c bus_for_each_drv+0xa4/0xc8 __device_attach+0xf0/0x15c device_initial_probe+0x1c/0x20 bus_probe_device+0xdc/0xec deferred_probe_work_func+0xa8/0xd4 process_one_work+0x3dc/0x96c worker_thread+0x4ec/0x8bc kthread+0x230/0x240 ret_from_fork+0x14/0x38 (null) Freed by task 132: __kasan_slab_free+0x12c/0x200 kasan_slab_free+0x14/0x18 kfree+0x90/0x294 hwmon_dev_release+0x1c/0x20 device_release+0x4c/0xe8 kobject_put+0xac/0x11c device_unregister+0x2c/0x30 __hwmon_device_register+0xa58/0xa7c hwmon_device_register_with_info+0xa0/0xa8 devm_hwmon_device_register_with_info+0x74/0xb4 lm90_probe+0x414/0x578 i2c_device_probe+0x35c/0x384 really_probe+0x290/0x3e4 driver_probe_device+0x80/0x1c4 __device_attach_driver+0x104/0x11c bus_for_each_drv+0xa4/0xc8 __device_attach+0xf0/0x15c device_initial_probe+0x1c/0x20 bus_probe_device+0xdc/0xec deferred_probe_work_func+0xa8/0xd4 process_one_work+0x3dc/0x96c worker_thread+0x4ec/0x8bc kthread+0x230/0x240 ret_from_fork+0x14/0x38 (null) Cc: # v4.15+ Fixes: 47c332deb8e8 ("hwmon: Deal with errors from the thermal subsystem") Signed-off-by: Dmitry Osipenko Signed-off-by: Guenter Roeck --- drivers/hwmon/hwmon.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c index 975c95169884..84f61cec6319 100644 --- a/drivers/hwmon/hwmon.c +++ b/drivers/hwmon/hwmon.c @@ -649,8 +649,10 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata, if (info[i]->config[j] & HWMON_T_INPUT) { err = hwmon_thermal_add_sensor(dev, hwdev, j); - if (err) - goto free_device; + if (err) { + device_unregister(hdev); + goto ida_remove; + } } } } @@ -658,8 +660,6 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata, return hdev; -free_device: - device_unregister(hdev); free_hwmon: kfree(hwdev); ida_remove: From e3e61f01d755188cb6c2dcf5a244b9c0937c258e Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Sun, 28 Oct 2018 18:16:51 +0100 Subject: [PATCH 078/356] hwmon: (ibmpowernv) Remove bogus __init annotations If gcc decides not to inline make_sensor_label(): WARNING: vmlinux.o(.text+0x4df549c): Section mismatch in reference from the function .create_device_attrs() to the function .init.text:.make_sensor_label() The function .create_device_attrs() references the function __init .make_sensor_label(). This is often because .create_device_attrs lacks a __init annotation or the annotation of .make_sensor_label is wrong. As .probe() can be called after freeing of __init memory, all __init annotiations in the driver are bogus, and should be removed. Signed-off-by: Geert Uytterhoeven Signed-off-by: Guenter Roeck --- drivers/hwmon/ibmpowernv.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/hwmon/ibmpowernv.c b/drivers/hwmon/ibmpowernv.c index 0ccca87f5271..293dd1c6c7b3 100644 --- a/drivers/hwmon/ibmpowernv.c +++ b/drivers/hwmon/ibmpowernv.c @@ -181,7 +181,7 @@ static ssize_t show_label(struct device *dev, struct device_attribute *devattr, return sprintf(buf, "%s\n", sdata->label); } -static int __init get_logical_cpu(int hwcpu) +static int get_logical_cpu(int hwcpu) { int cpu; @@ -192,9 +192,8 @@ static int __init get_logical_cpu(int hwcpu) return -ENOENT; } -static void __init make_sensor_label(struct device_node *np, - struct sensor_data *sdata, - const char *label) +static void make_sensor_label(struct device_node *np, + struct sensor_data *sdata, const char *label) { u32 id; size_t n; From 0432e833191ad4d17b7fc2364941f91dad51db1a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Holger=20Hoffst=C3=A4tte?= Date: Sun, 4 Nov 2018 19:02:42 +0100 Subject: [PATCH 079/356] net: phy: realtek: fix RTL8201F sysfs name MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since 4.19 the following error in sysfs has appeared when using the r8169 NIC driver: $cd /sys/module/realtek/drivers $ls -l ls: cannot access 'mdio_bus:RTL8201F 10/100Mbps Ethernet': No such file or directory [..garbled dir entries follow..] Apparently the forward slash in "10/100Mbps Ethernet" is interpreted as directory separator that leads nowhere, and was introduced in commit 513588dd44b ("net: phy: realtek: add RTL8201F phy-id and functions"). Fix this by removing the offending slash in the driver name. Other drivers in net/phy seem to have the same problem, but I cannot test/verify them. Fixes: 513588dd44b ("net: phy: realtek: add RTL8201F phy-id and functions") Signed-off-by: Holger Hoffstätte Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/realtek.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index 7fc8508b5231..271e8adc39f1 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -220,7 +220,7 @@ static struct phy_driver realtek_drvs[] = { .flags = PHY_HAS_INTERRUPT, }, { .phy_id = 0x001cc816, - .name = "RTL8201F 10/100Mbps Ethernet", + .name = "RTL8201F Fast Ethernet", .phy_id_mask = 0x001fffff, .features = PHY_BASIC_FEATURES, .flags = PHY_HAS_INTERRUPT, From ea53abfab960909d622ca37bcfb8e1c5378d21cc Mon Sep 17 00:00:00 2001 From: Jarod Wilson Date: Sun, 4 Nov 2018 14:59:46 -0500 Subject: [PATCH 080/356] bonding/802.3ad: fix link_failure_count tracking Commit 4d2c0cda07448ea6980f00102dc3964eb25e241c set slave->link to BOND_LINK_DOWN for 802.3ad bonds whenever invalid speed/duplex values were read, to fix a problem with slaves getting into weird states, but in the process, broke tracking of link failures, as going straight to BOND_LINK_DOWN when a link is indeed down (cable pulled, switch rebooted) means we broke out of bond_miimon_inspect()'s BOND_LINK_DOWN case because !link_state was already true, we never incremented commit, and never got a chance to call bond_miimon_commit(), where slave->link_failure_count would be incremented. I believe the simple fix here is to mark the slave as BOND_LINK_FAIL, and let bond_miimon_inspect() transition the link from _FAIL to either _UP or _DOWN, and in the latter case, we now get proper incrementing of link_failure_count again. Fixes: 4d2c0cda0744 ("bonding: speed/duplex update at NETDEV_UP event") CC: Mahesh Bandewar CC: David S. Miller CC: netdev@vger.kernel.org CC: stable@vger.kernel.org Signed-off-by: Jarod Wilson Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index ffa37adb7681..333387f1f1fe 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3112,13 +3112,13 @@ static int bond_slave_netdev_event(unsigned long event, case NETDEV_CHANGE: /* For 802.3ad mode only: * Getting invalid Speed/Duplex values here will put slave - * in weird state. So mark it as link-down for the time + * in weird state. So mark it as link-fail for the time * being and let link-monitoring (miimon) set it right when * correct speeds/duplex are available. */ if (bond_update_speed_duplex(slave) && BOND_MODE(bond) == BOND_MODE_8023AD) - slave->link = BOND_LINK_DOWN; + slave->link = BOND_LINK_FAIL; if (BOND_MODE(bond) == BOND_MODE_8023AD) bond_3ad_adapter_speed_duplex_changed(slave); From 438ad09af5581b7024850b5dbb6353c7f2f7d8a9 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Thu, 18 Oct 2018 13:26:13 +0200 Subject: [PATCH 081/356] ARM: dts: imx6sll: fix typo for fsl,imx6sll-i2c node MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix the type of compatible string "fs,imx6sll-i2c" which should be "fsl,imx6sll-i2c". Signed-off-by: Oleksij Rempel Acked-by: Uwe Kleine-König Signed-off-by: Shawn Guo --- arch/arm/boot/dts/imx6sll.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/imx6sll.dtsi b/arch/arm/boot/dts/imx6sll.dtsi index ed9a980bce85..beefa1b2049d 100644 --- a/arch/arm/boot/dts/imx6sll.dtsi +++ b/arch/arm/boot/dts/imx6sll.dtsi @@ -740,7 +740,7 @@ i2c1: i2c@21a0000 { #address-cells = <1>; #size-cells = <0>; - compatible = "fs,imx6sll-i2c", "fsl,imx21-i2c"; + compatible = "fsl,imx6sll-i2c", "fsl,imx21-i2c"; reg = <0x021a0000 0x4000>; interrupts = ; clocks = <&clks IMX6SLL_CLK_I2C1>; From 1af6ab3bac8458fc2e92ad7bb97b62de4a1fddef Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 30 Oct 2018 20:02:30 -0500 Subject: [PATCH 082/356] ARM: dts: fsl: Fix improperly quoted stdout-path values A quoted label reference doesn't expand to the node path and is taken as a literal string. Dropping the quotes can fix this unless the baudrate string is appended in which case we have to use the alias. At least on VF610, the problem was masked by setting the console in bootargs. Use the alias syntax with baudrate parameter so we can drop setting the console in bootargs. Cc: Shawn Guo Cc: Sascha Hauer Cc: Pengutronix Kernel Team Cc: NXP Linux Team Cc: Mark Rutland Reviewed-by: Fabio Estevam Reviewed-by: Stefan Agner Signed-off-by: Rob Herring Signed-off-by: Shawn Guo --- arch/arm/boot/dts/imx53-ppd.dts | 2 +- arch/arm/boot/dts/vf610m4-colibri.dts | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm/boot/dts/imx53-ppd.dts b/arch/arm/boot/dts/imx53-ppd.dts index b560ff88459b..5ff9a179c83c 100644 --- a/arch/arm/boot/dts/imx53-ppd.dts +++ b/arch/arm/boot/dts/imx53-ppd.dts @@ -55,7 +55,7 @@ }; chosen { - stdout-path = "&uart1:115200n8"; + stdout-path = "serial0:115200n8"; }; memory@70000000 { diff --git a/arch/arm/boot/dts/vf610m4-colibri.dts b/arch/arm/boot/dts/vf610m4-colibri.dts index 41ec66a96990..ca6249558760 100644 --- a/arch/arm/boot/dts/vf610m4-colibri.dts +++ b/arch/arm/boot/dts/vf610m4-colibri.dts @@ -50,8 +50,8 @@ compatible = "fsl,vf610m4"; chosen { - bootargs = "console=ttyLP2,115200 clk_ignore_unused init=/linuxrc rw"; - stdout-path = "&uart2"; + bootargs = "clk_ignore_unused init=/linuxrc rw"; + stdout-path = "serial2:115200"; }; memory@8c000000 { From 1ad9fb750a104f51851c092edd7b3553f0218428 Mon Sep 17 00:00:00 2001 From: Leonard Crestez Date: Mon, 8 Oct 2018 15:28:01 +0000 Subject: [PATCH 083/356] ARM: dts: imx6sx-sdb: Fix enet phy regulator Bindings for "fixed-regulator" only explicitly support "gpio" property, not "gpios". Fix by correcting the property name. The enet PHYs on imx6sx-sdb needs to be explicitly reset after a power cycle, this can be handled by the phy-reset-gpios property. Sadly this is not handled on suspend: the fec driver turns phy-supply off but doesn't assert phy-reset-gpios again on resume. Since additional phy-level work is required to support powering off the phy in suspend fix the problem by just marking the regulator as "boot-on" "always-on" so that it's never turned off. This behavior is equivalent to older releases. Keep the phy-reset-gpios property on fec anyway because it is a correct description of board design. This issue was exposed by commit efdfeb079cc3 ("regulator: fixed: Convert to use GPIO descriptor only") which causes the "gpios" property to also be parsed. Before that commit the "gpios" property had no effect, PHY reset was only handled in the the bootloader. This fixes linux-next boot failures previously reported here: https://lore.kernel.org/patchwork/patch/982437/#1177900 https://lore.kernel.org/patchwork/patch/994091/#1178304 Signed-off-by: Leonard Crestez Signed-off-by: Shawn Guo --- arch/arm/boot/dts/imx6sx-sdb.dtsi | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/imx6sx-sdb.dtsi b/arch/arm/boot/dts/imx6sx-sdb.dtsi index 53b3408b5fab..7d7d679945d2 100644 --- a/arch/arm/boot/dts/imx6sx-sdb.dtsi +++ b/arch/arm/boot/dts/imx6sx-sdb.dtsi @@ -117,7 +117,9 @@ regulator-name = "enet_3v3"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; - gpios = <&gpio2 6 GPIO_ACTIVE_LOW>; + gpio = <&gpio2 6 GPIO_ACTIVE_LOW>; + regulator-boot-on; + regulator-always-on; }; reg_pcie_gpio: regulator-pcie-gpio { @@ -180,6 +182,7 @@ phy-supply = <®_enet_3v3>; phy-mode = "rgmii"; phy-handle = <ðphy1>; + phy-reset-gpios = <&gpio2 7 GPIO_ACTIVE_LOW>; status = "okay"; mdio { @@ -373,6 +376,8 @@ MX6SX_PAD_RGMII1_RD3__ENET1_RX_DATA_3 0x3081 MX6SX_PAD_RGMII1_RX_CTL__ENET1_RX_EN 0x3081 MX6SX_PAD_ENET2_RX_CLK__ENET2_REF_CLK_25M 0x91 + /* phy reset */ + MX6SX_PAD_ENET2_CRS__GPIO2_IO_7 0x10b0 >; }; From e1ff516a56ad56c476b47795d3811eef79d25fbe Mon Sep 17 00:00:00 2001 From: Yi Wang Date: Mon, 5 Nov 2018 08:50:13 +0800 Subject: [PATCH 084/356] sched/fair: Fix a comment in task_numa_fault() Duplicated 'case it'. Signed-off-by: Yi Wang Reviewed-by: Xi Xu Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: zhong.weidong@zte.com.cn Link: http://lkml.kernel.org/r/1541379013-11352-1-git-send-email-wang.yi59@zte.com.cn Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index ee271bb661cc..3648d0300fdf 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2400,8 +2400,8 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) local = 1; /* - * Retry task to preferred node migration periodically, in case it - * case it previously failed, or the scheduler moved us. + * Retry to migrate task to preferred node periodically, in case it + * previously failed, or the scheduler moved us. */ if (time_after(jiffies, p->numa_migrate_retry)) { task_numa_placement(p); From f75d651587f719a813ebbbfeee570e6570731d55 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 4 Nov 2018 18:40:14 -0800 Subject: [PATCH 085/356] resource/docs: Fix new kernel-doc warnings The first group of warnings is caused by a "/**" kernel-doc notation marker but the function comments are not in kernel-doc format. Also add another error return value here. ../kernel/resource.c:337: warning: Function parameter or member 'start' not described in 'find_next_iomem_res' ../kernel/resource.c:337: warning: Function parameter or member 'end' not described in 'find_next_iomem_res' ../kernel/resource.c:337: warning: Function parameter or member 'flags' not described in 'find_next_iomem_res' ../kernel/resource.c:337: warning: Function parameter or member 'desc' not described in 'find_next_iomem_res' ../kernel/resource.c:337: warning: Function parameter or member 'first_lvl' not described in 'find_next_iomem_res' ../kernel/resource.c:337: warning: Function parameter or member 'res' not described in 'find_next_iomem_res' Add the missing function parameter documentation for the other warnings: ../kernel/resource.c:409: warning: Function parameter or member 'arg' not described in 'walk_iomem_res_desc' ../kernel/resource.c:409: warning: Function parameter or member 'func' not described in 'walk_iomem_res_desc' Signed-off-by: Randy Dunlap Cc: Andrew Morton Cc: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: b69c2e20f6e4 ("resource: Clean it up a bit") Link: http://lkml.kernel.org/r/dda2e4d8-bedd-3167-20fe-8c7d2d35b354@infradead.org Signed-off-by: Ingo Molnar --- kernel/resource.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/kernel/resource.c b/kernel/resource.c index b3a3a1fc499e..17bcb189d530 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -318,14 +318,14 @@ int release_resource(struct resource *old) EXPORT_SYMBOL(release_resource); -/** +/* * Finds the lowest iomem resource that covers part of [start..end]. The * caller must specify start, end, flags, and desc (which may be * IORES_DESC_NONE). * * If a resource is found, returns 0 and *res is overwritten with the part * of the resource that's within [start..end]; if none is found, returns - * -1. + * -1. Returns -EINVAL for other invalid parameters. * * This function walks the whole tree and not just first level children * unless @first_lvl is true. @@ -390,7 +390,9 @@ static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end, } /** - * Walks through iomem resources and calls func() with matching resource + * walk_iomem_res_desc - walk through iomem resources + * + * Walks through iomem resources and calls @func() with matching resource * ranges. This walks through whole tree and not just first level children. * All the memory ranges which overlap start,end and also match flags and * desc are valid candidates. @@ -399,6 +401,8 @@ static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end, * @flags: I/O resource flags * @start: start addr * @end: end addr + * @arg: function argument for the callback @func + * @func: callback function that is called for each qualifying resource area * * NOTE: For a new descriptor search, define a new IORES_DESC in * and set it in 'desc' of a target resource entry. From b068621a53f92f42400581d69ad0e84c56620b0a Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 4 Nov 2018 14:03:56 -0800 Subject: [PATCH 086/356] Documentation/x86: Fix typo in zero-page.txt Signed-off-by: Randy Dunlap Cc: Jonathan Corbet Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-doc@vger.kernel.org Link: http://lkml.kernel.org/r/f259b21b-1f2b-f215-00d2-23388bed2530@infradead.org Signed-off-by: Ingo Molnar --- Documentation/x86/zero-page.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/x86/zero-page.txt b/Documentation/x86/zero-page.txt index 97b7adbceda4..68aed077f7b6 100644 --- a/Documentation/x86/zero-page.txt +++ b/Documentation/x86/zero-page.txt @@ -25,7 +25,7 @@ Offset Proto Name Meaning 0C8/004 ALL ext_cmd_line_ptr cmd_line_ptr high 32bits 140/080 ALL edid_info Video mode setup (struct edid_info) 1C0/020 ALL efi_info EFI 32 information (struct efi_info) -1E0/004 ALL alk_mem_k Alternative mem check, in KB +1E0/004 ALL alt_mem_k Alternative mem check, in KB 1E4/004 ALL scratch Scratch field for the kernel setup code 1E8/001 ALL e820_entries Number of entries in e820_table (below) 1E9/001 ALL eddbuf_entries Number of entries in eddbuf (below) From 8727b230f665cadb9349a915c60e6abb18fb083c Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Sat, 13 Oct 2018 13:21:40 +0300 Subject: [PATCH 087/356] drm/exynos: checking for NULL instead of IS_ERR() The of_drm_find_panel() function returns error pointers and never NULL but we the driver assumes that ->panel is NULL when it's not present. Fixes: 6afb7721e2a0 ("drm/exynos: move connector creation to attach callback") Signed-off-by: Dan Carpenter Signed-off-by: Inki Dae --- drivers/gpu/drm/exynos/exynos_drm_dsi.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c index 07af7758066d..32f256749789 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c @@ -1527,7 +1527,9 @@ static int exynos_dsi_host_attach(struct mipi_dsi_host *host, } dsi->panel = of_drm_find_panel(device->dev.of_node); - if (dsi->panel) { + if (IS_ERR(dsi->panel)) { + dsi->panel = NULL; + } else { drm_panel_attach(dsi->panel, &dsi->connector); dsi->connector.status = connector_status_connected; } From 6ca469e22a30992b4478d2ab88737c70667c1e00 Mon Sep 17 00:00:00 2001 From: Inki Dae Date: Fri, 5 Oct 2018 11:50:20 +0900 Subject: [PATCH 088/356] Revert "drm/exynos/decon5433: implement frame counter" This reverts commit 0586feba322e1de05075700eb4b835c8b683e62b This patch makes it to need get_vblank_counter callback in crtc to get frame counter from decon driver. However, drm_dev->max_vblank_count is a member unique to vendor's DRM driver but in case of ARM DRM, some CRTC devices don't provide the frame counter value. As a result, this patch made extension and clone mode not working. Instead of this patch, we may need separated max_vblank_count which belongs to each CRTC device, or need to implement frame counter emulation for them who don't support HW frame counter. Signed-off-by: Inki Dae --- drivers/gpu/drm/exynos/exynos5433_drm_decon.c | 9 --------- drivers/gpu/drm/exynos/exynos_drm_crtc.c | 11 ----------- drivers/gpu/drm/exynos/exynos_drm_drv.h | 1 - 3 files changed, 21 deletions(-) diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c index 94529aa82339..aef487dd8731 100644 --- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c @@ -164,13 +164,6 @@ static u32 decon_get_frame_count(struct decon_context *ctx, bool end) return frm; } -static u32 decon_get_vblank_counter(struct exynos_drm_crtc *crtc) -{ - struct decon_context *ctx = crtc->ctx; - - return decon_get_frame_count(ctx, false); -} - static void decon_setup_trigger(struct decon_context *ctx) { if (!ctx->crtc->i80_mode && !(ctx->out_type & I80_HW_TRG)) @@ -536,7 +529,6 @@ static const struct exynos_drm_crtc_ops decon_crtc_ops = { .disable = decon_disable, .enable_vblank = decon_enable_vblank, .disable_vblank = decon_disable_vblank, - .get_vblank_counter = decon_get_vblank_counter, .atomic_begin = decon_atomic_begin, .update_plane = decon_update_plane, .disable_plane = decon_disable_plane, @@ -554,7 +546,6 @@ static int decon_bind(struct device *dev, struct device *master, void *data) int ret; ctx->drm_dev = drm_dev; - drm_dev->max_vblank_count = 0xffffffff; for (win = ctx->first_win; win < WINDOWS_NR; win++) { ctx->configs[win].pixel_formats = decon_formats; diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c index eea90251808f..2696289ecc78 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c @@ -162,16 +162,6 @@ static void exynos_drm_crtc_disable_vblank(struct drm_crtc *crtc) exynos_crtc->ops->disable_vblank(exynos_crtc); } -static u32 exynos_drm_crtc_get_vblank_counter(struct drm_crtc *crtc) -{ - struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc); - - if (exynos_crtc->ops->get_vblank_counter) - return exynos_crtc->ops->get_vblank_counter(exynos_crtc); - - return 0; -} - static const struct drm_crtc_funcs exynos_crtc_funcs = { .set_config = drm_atomic_helper_set_config, .page_flip = drm_atomic_helper_page_flip, @@ -181,7 +171,6 @@ static const struct drm_crtc_funcs exynos_crtc_funcs = { .atomic_destroy_state = drm_atomic_helper_crtc_destroy_state, .enable_vblank = exynos_drm_crtc_enable_vblank, .disable_vblank = exynos_drm_crtc_disable_vblank, - .get_vblank_counter = exynos_drm_crtc_get_vblank_counter, }; struct exynos_drm_crtc *exynos_drm_crtc_create(struct drm_device *drm_dev, diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h index ec9604f1272b..5e61e707f955 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.h +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h @@ -135,7 +135,6 @@ struct exynos_drm_crtc_ops { void (*disable)(struct exynos_drm_crtc *crtc); int (*enable_vblank)(struct exynos_drm_crtc *crtc); void (*disable_vblank)(struct exynos_drm_crtc *crtc); - u32 (*get_vblank_counter)(struct exynos_drm_crtc *crtc); enum drm_mode_status (*mode_valid)(struct exynos_drm_crtc *crtc, const struct drm_display_mode *mode); bool (*mode_fixup)(struct exynos_drm_crtc *crtc, From deee3284cba3145a4ee03cbe8541d7a3bfc499e2 Mon Sep 17 00:00:00 2001 From: Andrzej Hajda Date: Fri, 26 Oct 2018 12:40:03 +0200 Subject: [PATCH 089/356] drm/exynos/dsi: register connector if it is created after drm bind DSI device can be attached after DRM device is registered. In such case newly created connector must be registered by exynos_dsi. The patch fixes exynos_drm on rinato and trats boards. Fixes: 6afb7721e2a0 ("drm/exynos: move connector creation to attach callback") Reported-by: Marek Szyprowski Signed-off-by: Andrzej Hajda Tested-by: Marek Szyprowski Signed-off-by: Inki Dae --- drivers/gpu/drm/exynos/exynos_drm_dsi.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c index 32f256749789..d81e62ae286a 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c @@ -14,6 +14,7 @@ #include #include +#include #include #include #include @@ -1474,12 +1475,12 @@ static int exynos_dsi_create_connector(struct drm_encoder *encoder) { struct exynos_dsi *dsi = encoder_to_dsi(encoder); struct drm_connector *connector = &dsi->connector; + struct drm_device *drm = encoder->dev; int ret; connector->polled = DRM_CONNECTOR_POLL_HPD; - ret = drm_connector_init(encoder->dev, connector, - &exynos_dsi_connector_funcs, + ret = drm_connector_init(drm, connector, &exynos_dsi_connector_funcs, DRM_MODE_CONNECTOR_DSI); if (ret) { DRM_ERROR("Failed to initialize connector with drm\n"); @@ -1489,7 +1490,12 @@ static int exynos_dsi_create_connector(struct drm_encoder *encoder) connector->status = connector_status_disconnected; drm_connector_helper_add(connector, &exynos_dsi_connector_helper_funcs); drm_connector_attach_encoder(connector, encoder); + if (!drm->registered) + return 0; + connector->funcs->reset(connector); + drm_fb_helper_add_one_connector(drm->fb_helper, connector); + drm_connector_register(connector); return 0; } From 989534cfcac89f927fa46b1e0861d92ffbd2c7e4 Mon Sep 17 00:00:00 2001 From: Andrzej Hajda Date: Fri, 26 Oct 2018 12:13:28 +0200 Subject: [PATCH 090/356] drm/exynos/fbdev: do not skip fbdev init if there are no connectors Since connectors can be created dynamically, fbdev should be initialized even if there are no connectors at the moment. Otherwise fbdev will not be created even after connector's appearance. The patch fixes lack of fbdev on rinato and trats boards. Fixes: 6afb7721e2a0 ("drm/exynos: move connector creation to attach callback") Reported-by: Marek Szyprowski Signed-off-by: Andrzej Hajda Tested-by: Marek Szyprowski Signed-off-by: Inki Dae --- drivers/gpu/drm/exynos/exynos_drm_fbdev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c index 918dd2c82209..01d182289efa 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c @@ -192,7 +192,7 @@ int exynos_drm_fbdev_init(struct drm_device *dev) struct drm_fb_helper *helper; int ret; - if (!dev->mode_config.num_crtc || !dev->mode_config.num_connector) + if (!dev->mode_config.num_crtc) return 0; fbdev = kzalloc(sizeof(*fbdev), GFP_KERNEL); From be2e1c9dcf76886a83fb1c433a316e26d4ca2550 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 11 Oct 2018 13:06:16 +0200 Subject: [PATCH 091/356] mtd: docg3: don't set conflicting BCH_CONST_PARAMS option I noticed during the creation of another bugfix that the BCH_CONST_PARAMS option that is set by DOCG3 breaks setting variable parameters for any other users of the BCH library code. The only other user we have today is the MTD_NAND software BCH implementation (most flash controllers use hardware BCH these days and are not affected). I considered removing BCH_CONST_PARAMS entirely because of the inherent conflict, but according to the description in lib/bch.c there is a significant performance benefit in keeping it. To avoid the immediate problem of the conflict between MTD_NAND_BCH and DOCG3, this only sets the constant parameters if MTD_NAND_BCH is disabled, which should fix the problem for all cases that are affected. This should also work for all stable kernels. Note that there is only one machine that actually seems to use the DOCG3 driver (arch/arm/mach-pxa/mioa701.c), so most users should have the driver disabled, but it almost certainly shows up if we wanted to test random kernels on machines that use software BCH in MTD. Fixes: d13d19ece39f ("mtd: docg3: add ECC correction code") Cc: stable@vger.kernel.org Cc: Robert Jarzmik Signed-off-by: Arnd Bergmann Signed-off-by: Boris Brezillon --- drivers/mtd/devices/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig index e514d57a0419..aa983422aa97 100644 --- a/drivers/mtd/devices/Kconfig +++ b/drivers/mtd/devices/Kconfig @@ -207,7 +207,7 @@ comment "Disk-On-Chip Device Drivers" config MTD_DOCG3 tristate "M-Systems Disk-On-Chip G3" select BCH - select BCH_CONST_PARAMS + select BCH_CONST_PARAMS if !MTD_NAND_BCH select BITREVERSE help This provides an MTD device driver for the M-Systems DiskOnChip From ce97e2bb6687d3af675ecf2e836a9122def53578 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 4 Nov 2018 18:38:35 -0800 Subject: [PATCH 092/356] mtd: nand: drop kernel-doc notation for a deleted function parameter Remove kernel-doc notation for a deleted function parameter to prevent a kernel-doc warning: ../drivers/mtd/nand/raw/nand_base.c:603: warning: Excess function parameter 'mtd' description in 'panic_nand_wait' Fixes: f1d46942e823 ("mtd: rawnand: Pass a nand_chip object to chip->waitfunc()") Signed-off-by: Randy Dunlap Cc: Boris Brezillon Cc: Miquel Raynal Cc: Richard Weinberger Reviewed-by: Miquel Raynal Signed-off-by: Boris Brezillon --- drivers/mtd/nand/raw/nand_base.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 05bd0779fe9b..71050a0b31df 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -590,7 +590,6 @@ retry: /** * panic_nand_wait - [GENERIC] wait until the command is done - * @mtd: MTD device structure * @chip: NAND chip structure * @timeo: timeout * From d098093ba06eb032057d1aca1c2e45889e099d00 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 28 Oct 2018 12:29:55 +0100 Subject: [PATCH 093/356] mtd: nand: Fix nanddev_neraseblocks() nanddev_neraseblocks() currently returns the number pages per LUN instead of the total number of eraseblocks. Fixes: 9c3736a3de21 ("mtd: nand: Add core infrastructure to deal with NAND devices") Cc: Signed-off-by: Boris Brezillon Reviewed-by: Miquel Raynal --- include/linux/mtd/nand.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index abe975c87b90..78b86dea2f29 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -324,9 +324,8 @@ static inline unsigned int nanddev_ntargets(const struct nand_device *nand) */ static inline unsigned int nanddev_neraseblocks(const struct nand_device *nand) { - return (u64)nand->memorg.luns_per_target * - nand->memorg.eraseblocks_per_lun * - nand->memorg.pages_per_eraseblock; + return nand->memorg.ntargets * nand->memorg.luns_per_target * + nand->memorg.eraseblocks_per_lun; } /** From 9a4d83074769d6ecf1f5c3fef0f183b09abf3726 Mon Sep 17 00:00:00 2001 From: Robert Marko Date: Sat, 6 Oct 2018 17:36:42 +0200 Subject: [PATCH 094/356] mtd: spinand: winbond: Add support for W25N01GV W25N01GV is a single die version of the already supported W25M02GV with half the capacity. Everything else is the same so introduce support for W25N01GV. Datasheet:http://www.winbond.com/resource-files/w25n01gv%20revl%20050918%20unsecured.pdf Tested on 8devices Jalapeno dev board under OpenWrt running 4.19-rc5. Signed-off-by: Robert Marko Reviewed-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/spi/winbond.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c index 67baa1b32c00..5d944580b898 100644 --- a/drivers/mtd/nand/spi/winbond.c +++ b/drivers/mtd/nand/spi/winbond.c @@ -84,6 +84,14 @@ static const struct spinand_info winbond_spinand_table[] = { 0, SPINAND_ECCINFO(&w25m02gv_ooblayout, NULL), SPINAND_SELECT_TARGET(w25m02gv_select_target)), + SPINAND_INFO("W25N01GV", 0xAA, + NAND_MEMORG(1, 2048, 64, 64, 1024, 1, 1, 1), + NAND_ECCREQ(1, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants, + &write_cache_variants, + &update_cache_variants), + 0, + SPINAND_ECCINFO(&w25m02gv_ooblayout, NULL)), }; /** From 41d6f0d07d76257cf2d39071a439c7dd1da7271e Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Wed, 10 Oct 2018 17:58:58 +0200 Subject: [PATCH 095/356] mtd: rawnand: fsmc: Fix unchecked return value in fsmc_read_page_hwecc Check return value of nand_read_data_op. Notice that, currently, all instances of nand_read_data_op() are being checked, with the exception of two of them in marvell_nand driver, in which the caller function explicitly returns 0 every time. Also, notice that I moved the declaration of *ret* to the top of fsmc_read_page_hwecc(). Addresses-Coverity-ID: 1471968 ("Unchecked return value") Signed-off-by: Gustavo A. R. Silva Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/fsmc_nand.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c index 70ac8d875218..41ba76efd6c8 100644 --- a/drivers/mtd/nand/raw/fsmc_nand.c +++ b/drivers/mtd/nand/raw/fsmc_nand.c @@ -727,7 +727,7 @@ static int fsmc_read_page_hwecc(struct nand_chip *chip, uint8_t *buf, uint8_t *p = buf; uint8_t *ecc_calc = chip->ecc.calc_buf; uint8_t *ecc_code = chip->ecc.code_buf; - int off, len, group = 0; + int off, len, ret, group = 0; /* * ecc_oob is intentionally taken as uint16_t. In 16bit devices, we * end up reading 14 bytes (7 words) from oob. The local array is @@ -740,11 +740,12 @@ static int fsmc_read_page_hwecc(struct nand_chip *chip, uint8_t *buf, for (i = 0, s = 0; s < eccsteps; s++, i += eccbytes, p += eccsize) { nand_read_page_op(chip, page, s * eccsize, NULL, 0); chip->ecc.hwctl(chip, NAND_ECC_READ); - nand_read_data_op(chip, p, eccsize, false); + ret = nand_read_data_op(chip, p, eccsize, false); + if (ret) + return ret; for (j = 0; j < eccbytes;) { struct mtd_oob_region oobregion; - int ret; ret = mtd_ooblayout_ecc(mtd, group++, &oobregion); if (ret) From b0e137ad24b6cc36a4ab09558a401e124163eefb Mon Sep 17 00:00:00 2001 From: Janusz Krzysztofik Date: Mon, 15 Oct 2018 21:41:28 +0200 Subject: [PATCH 096/356] mtd: rawnand: Provide helper for polling GPIO R/B pin Each controller driver having access to NAND R/B pin over GPIO would have to reimplement the polling loop otherwise. Suggested-by: Boris Brezillon Signed-off-by: Janusz Krzysztofik Reviewed-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/nand_base.c | 31 +++++++++++++++++++++++++++++++ include/linux/mtd/rawnand.h | 4 ++++ 2 files changed, 35 insertions(+) diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 05bd0779fe9b..0d5a2dc59b8d 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -45,6 +45,7 @@ #include #include #include +#include #include "internals.h" @@ -531,6 +532,36 @@ int nand_soft_waitrdy(struct nand_chip *chip, unsigned long timeout_ms) }; EXPORT_SYMBOL_GPL(nand_soft_waitrdy); +/** + * nand_gpio_waitrdy - Poll R/B GPIO pin until ready + * @chip: NAND chip structure + * @gpiod: GPIO descriptor of R/B pin + * @timeout_ms: Timeout in ms + * + * Poll the R/B GPIO pin until it becomes ready. If that does not happen + * whitin the specified timeout, -ETIMEDOUT is returned. + * + * This helper is intended to be used when the controller has access to the + * NAND R/B pin over GPIO. + * + * Return 0 if the R/B pin indicates chip is ready, a negative error otherwise. + */ +int nand_gpio_waitrdy(struct nand_chip *chip, struct gpio_desc *gpiod, + unsigned long timeout_ms) +{ + /* Wait until R/B pin indicates chip is ready or timeout occurs */ + timeout_ms = jiffies + msecs_to_jiffies(timeout_ms); + do { + if (gpiod_get_value_cansleep(gpiod)) + return 0; + + cond_resched(); + } while (time_before(jiffies, timeout_ms)); + + return gpiod_get_value_cansleep(gpiod) ? 0 : -ETIMEDOUT; +}; +EXPORT_SYMBOL_GPL(nand_gpio_waitrdy); + /** * panic_nand_get_device - [GENERIC] Get chip for selected access * @chip: the nand chip descriptor diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index e10b126e148f..4e91a70ede10 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1346,4 +1346,8 @@ void nand_release(struct nand_chip *chip); */ int nand_soft_waitrdy(struct nand_chip *chip, unsigned long timeout_ms); +struct gpio_desc; +int nand_gpio_waitrdy(struct nand_chip *chip, struct gpio_desc *gpiod, + unsigned long timeout_ms); + #endif /* __LINUX_MTD_RAWNAND_H */ From 3bd647ee7abcffd98a7d8446b96c8da72591b454 Mon Sep 17 00:00:00 2001 From: Janusz Krzysztofik Date: Mon, 15 Oct 2018 21:41:29 +0200 Subject: [PATCH 097/356] mtd: rawnand: ams-delta: Stop using legacy .IOADDR_R/W Replace use of legacy .IOADDR_R/W with runtime calculations based on priv->io_base. Suggested-by: Boris Brezillon Signed-off-by: Janusz Krzysztofik Reviewed-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/ams-delta.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/mtd/nand/raw/ams-delta.c b/drivers/mtd/nand/raw/ams-delta.c index 5ba180a291eb..46193db6d368 100644 --- a/drivers/mtd/nand/raw/ams-delta.c +++ b/drivers/mtd/nand/raw/ams-delta.c @@ -75,7 +75,7 @@ static const struct mtd_partition partition_info[] = { static void ams_delta_io_write(struct ams_delta_nand *priv, u_char byte) { - writew(byte, priv->nand_chip.legacy.IO_ADDR_W); + writew(byte, priv->io_base + OMAP_MPUIO_OUTPUT); gpiod_set_value(priv->gpiod_nwe, 0); ndelay(40); gpiod_set_value(priv->gpiod_nwe, 1); @@ -87,7 +87,7 @@ static u_char ams_delta_io_read(struct ams_delta_nand *priv) gpiod_set_value(priv->gpiod_nre, 0); ndelay(40); - res = readw(priv->nand_chip.legacy.IO_ADDR_R); + res = readw(priv->io_base + OMAP_MPUIO_INPUT_LATCH); gpiod_set_value(priv->gpiod_nre, 1); return res; @@ -211,8 +211,6 @@ static int ams_delta_init(struct platform_device *pdev) nand_set_controller_data(this, priv); /* Set address of NAND IO lines */ - this->legacy.IO_ADDR_R = io_base + OMAP_MPUIO_INPUT_LATCH; - this->legacy.IO_ADDR_W = io_base + OMAP_MPUIO_OUTPUT; this->legacy.read_byte = ams_delta_read_byte; this->legacy.write_buf = ams_delta_write_buf; this->legacy.read_buf = ams_delta_read_buf; From 861fbd6e808eb2a0b0d99f7a6467a7dc4ae9fb19 Mon Sep 17 00:00:00 2001 From: Janusz Krzysztofik Date: Mon, 15 Oct 2018 21:41:30 +0200 Subject: [PATCH 098/356] mtd: rawnand: ams-delta: Convert the driver to ->exec_op() Replace legacy callbacks with ->select_chip() and ->exec_op(). Suggested-by: Boris Brezillon Signed-off-by: Janusz Krzysztofik Reviewed-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/ams-delta.c | 100 +++++++++++++++++-------------- 1 file changed, 56 insertions(+), 44 deletions(-) diff --git a/drivers/mtd/nand/raw/ams-delta.c b/drivers/mtd/nand/raw/ams-delta.c index 46193db6d368..9ca70aab199d 100644 --- a/drivers/mtd/nand/raw/ams-delta.c +++ b/drivers/mtd/nand/raw/ams-delta.c @@ -99,10 +99,9 @@ static void ams_delta_dir_input(struct ams_delta_nand *priv, bool in) priv->data_in = in; } -static void ams_delta_write_buf(struct nand_chip *this, const u_char *buf, +static void ams_delta_write_buf(struct ams_delta_nand *priv, const u_char *buf, int len) { - struct ams_delta_nand *priv = nand_get_controller_data(this); int i; if (priv->data_in) @@ -112,9 +111,9 @@ static void ams_delta_write_buf(struct nand_chip *this, const u_char *buf, ams_delta_io_write(priv, buf[i]); } -static void ams_delta_read_buf(struct nand_chip *this, u_char *buf, int len) +static void ams_delta_read_buf(struct ams_delta_nand *priv, u_char *buf, + int len) { - struct ams_delta_nand *priv = nand_get_controller_data(this); int i; if (!priv->data_in) @@ -124,46 +123,66 @@ static void ams_delta_read_buf(struct nand_chip *this, u_char *buf, int len) buf[i] = ams_delta_io_read(priv); } -static u_char ams_delta_read_byte(struct nand_chip *this) -{ - u_char res; - - ams_delta_read_buf(this, &res, 1); - - return res; -} - -/* - * Command control function - * - * ctrl: - * NAND_NCE: bit 0 -> bit 2 - * NAND_CLE: bit 1 -> bit 7 - * NAND_ALE: bit 2 -> bit 6 - */ -static void ams_delta_hwcontrol(struct nand_chip *this, int cmd, - unsigned int ctrl) +static void ams_delta_select_chip(struct nand_chip *this, int n) { struct ams_delta_nand *priv = nand_get_controller_data(this); - if (ctrl & NAND_CTRL_CHANGE) { - gpiod_set_value(priv->gpiod_nce, !(ctrl & NAND_NCE)); - gpiod_set_value(priv->gpiod_cle, !!(ctrl & NAND_CLE)); - gpiod_set_value(priv->gpiod_ale, !!(ctrl & NAND_ALE)); - } + if (n > 0) + return; - if (cmd != NAND_CMD_NONE) { - u_char byte = cmd; - - ams_delta_write_buf(this, &byte, 1); - } + gpiod_set_value(priv->gpiod_nce, n < 0); } -static int ams_delta_nand_ready(struct nand_chip *this) +static int ams_delta_exec_op(struct nand_chip *this, + const struct nand_operation *op, bool check_only) { struct ams_delta_nand *priv = nand_get_controller_data(this); + const struct nand_op_instr *instr; + int ret = 0; - return gpiod_get_value(priv->gpiod_rdy); + if (check_only) + return 0; + + for (instr = op->instrs; instr < op->instrs + op->ninstrs; instr++) { + + switch (instr->type) { + case NAND_OP_CMD_INSTR: + gpiod_set_value(priv->gpiod_cle, 1); + ams_delta_write_buf(priv, &instr->ctx.cmd.opcode, 1); + gpiod_set_value(priv->gpiod_cle, 0); + break; + + case NAND_OP_ADDR_INSTR: + gpiod_set_value(priv->gpiod_ale, 1); + ams_delta_write_buf(priv, instr->ctx.addr.addrs, + instr->ctx.addr.naddrs); + gpiod_set_value(priv->gpiod_ale, 0); + break; + + case NAND_OP_DATA_IN_INSTR: + ams_delta_read_buf(priv, instr->ctx.data.buf.in, + instr->ctx.data.len); + break; + + case NAND_OP_DATA_OUT_INSTR: + ams_delta_write_buf(priv, instr->ctx.data.buf.out, + instr->ctx.data.len); + break; + + case NAND_OP_WAITRDY_INSTR: + ret = priv->gpiod_rdy ? + nand_gpio_waitrdy(this, priv->gpiod_rdy, + instr->ctx.waitrdy.timeout_ms) : + nand_soft_waitrdy(this, + instr->ctx.waitrdy.timeout_ms); + break; + } + + if (ret) + break; + } + + return ret; } @@ -211,10 +230,8 @@ static int ams_delta_init(struct platform_device *pdev) nand_set_controller_data(this, priv); /* Set address of NAND IO lines */ - this->legacy.read_byte = ams_delta_read_byte; - this->legacy.write_buf = ams_delta_write_buf; - this->legacy.read_buf = ams_delta_read_buf; - this->legacy.cmd_ctrl = ams_delta_hwcontrol; + this->select_chip = ams_delta_select_chip; + this->exec_op = ams_delta_exec_op; priv->gpiod_rdy = devm_gpiod_get_optional(&pdev->dev, "rdy", GPIOD_IN); if (IS_ERR(priv->gpiod_rdy)) { @@ -223,11 +240,6 @@ static int ams_delta_init(struct platform_device *pdev) goto out_mtd; } - if (priv->gpiod_rdy) - this->legacy.dev_ready = ams_delta_nand_ready; - - /* 25 us command delay time */ - this->legacy.chip_delay = 30; this->ecc.mode = NAND_ECC_SOFT; this->ecc.algo = NAND_ECC_HAMMING; From 321e54047b611a07e4d4478f28f636fd4dd6e744 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 16 Oct 2018 13:33:21 +0900 Subject: [PATCH 099/356] mtd: rawnand: denali: include instead of The reason of including here is just for BIT() and GENMASK macros. Since commit 8bd9cb51daac8 ("locking/atomics, asm-generic: Move some macros from to a new file"), is enough for such compile-time macros. Signed-off-by: Masahiro Yamada Reviewed-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/denali.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/nand/raw/denali.h b/drivers/mtd/nand/raw/denali.h index 57a5498f58bb..25c00601b8b3 100644 --- a/drivers/mtd/nand/raw/denali.h +++ b/drivers/mtd/nand/raw/denali.h @@ -7,7 +7,7 @@ #ifndef __DENALI_H__ #define __DENALI_H__ -#include +#include #include #include #include From 0282fefb1a29d60d6c51ff62bda5ccdc7ab48993 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 18 Oct 2018 14:59:35 +0200 Subject: [PATCH 100/356] mtd: rawnand: r852: use generic DMA API Use the generic DMA API instead of the legacy PCI DMA API. Signed-off-by: Christoph Hellwig Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/r852.c | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) diff --git a/drivers/mtd/nand/raw/r852.c b/drivers/mtd/nand/raw/r852.c index 39be65b35ac2..35f0b343cf90 100644 --- a/drivers/mtd/nand/raw/r852.c +++ b/drivers/mtd/nand/raw/r852.c @@ -151,8 +151,9 @@ static void r852_dma_done(struct r852_device *dev, int error) dev->dma_stage = 0; if (dev->phys_dma_addr && dev->phys_dma_addr != dev->phys_bounce_buffer) - pci_unmap_single(dev->pci_dev, dev->phys_dma_addr, R852_DMA_LEN, - dev->dma_dir ? PCI_DMA_FROMDEVICE : PCI_DMA_TODEVICE); + dma_unmap_single(&dev->pci_dev->dev, dev->phys_dma_addr, + R852_DMA_LEN, + dev->dma_dir ? DMA_FROM_DEVICE : DMA_TO_DEVICE); } /* @@ -197,11 +198,10 @@ static void r852_do_dma(struct r852_device *dev, uint8_t *buf, int do_read) bounce = 1; if (!bounce) { - dev->phys_dma_addr = pci_map_single(dev->pci_dev, (void *)buf, + dev->phys_dma_addr = dma_map_single(&dev->pci_dev->dev, buf, R852_DMA_LEN, - (do_read ? PCI_DMA_FROMDEVICE : PCI_DMA_TODEVICE)); - - if (pci_dma_mapping_error(dev->pci_dev, dev->phys_dma_addr)) + do_read ? DMA_FROM_DEVICE : DMA_TO_DEVICE); + if (dma_mapping_error(&dev->pci_dev->dev, dev->phys_dma_addr)) bounce = 1; } @@ -835,7 +835,7 @@ static int r852_probe(struct pci_dev *pci_dev, const struct pci_device_id *id) pci_set_master(pci_dev); - error = pci_set_dma_mask(pci_dev, DMA_BIT_MASK(32)); + error = dma_set_mask(&pci_dev->dev, DMA_BIT_MASK(32)); if (error) goto error2; @@ -885,8 +885,8 @@ static int r852_probe(struct pci_dev *pci_dev, const struct pci_device_id *id) dev->pci_dev = pci_dev; pci_set_drvdata(pci_dev, dev); - dev->bounce_buffer = pci_alloc_consistent(pci_dev, R852_DMA_LEN, - &dev->phys_bounce_buffer); + dev->bounce_buffer = dma_alloc_coherent(&pci_dev->dev, R852_DMA_LEN, + &dev->phys_bounce_buffer, GFP_KERNEL); if (!dev->bounce_buffer) goto error6; @@ -946,8 +946,8 @@ error9: error8: pci_iounmap(pci_dev, dev->mmio); error7: - pci_free_consistent(pci_dev, R852_DMA_LEN, - dev->bounce_buffer, dev->phys_bounce_buffer); + dma_free_coherent(&pci_dev->dev, R852_DMA_LEN, dev->bounce_buffer, + dev->phys_bounce_buffer); error6: kfree(dev); error5: @@ -980,8 +980,8 @@ static void r852_remove(struct pci_dev *pci_dev) /* Cleanup */ kfree(dev->tmp_buffer); pci_iounmap(pci_dev, dev->mmio); - pci_free_consistent(pci_dev, R852_DMA_LEN, - dev->bounce_buffer, dev->phys_bounce_buffer); + dma_free_coherent(&pci_dev->dev, R852_DMA_LEN, dev->bounce_buffer, + dev->phys_bounce_buffer); kfree(dev->chip); kfree(dev); From 4920b1f7676d55dcebdf55f2b0431a328acb4abe Mon Sep 17 00:00:00 2001 From: Punit Agrawal Date: Fri, 2 Nov 2018 16:57:52 +0000 Subject: [PATCH 101/356] mailmap: Update email for Punit Agrawal As I'll no longer be working with Arm, add a mailmap entry so any mail directed towards me reaches the appropriate mailbox. Acked-by: Will Deacon Signed-off-by: Punit Agrawal Signed-off-by: Catalin Marinas --- .mailmap | 1 + 1 file changed, 1 insertion(+) diff --git a/.mailmap b/.mailmap index a76be45fef6c..28fecafa6506 100644 --- a/.mailmap +++ b/.mailmap @@ -159,6 +159,7 @@ Peter Oruba Peter Oruba Pratyush Anand Praveen BP +Punit Agrawal Qais Yousef Oleksij Rempel Oleksij Rempel From fc09ab7a767394f9ecdad84ea6e85d68b83c8e21 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 5 Nov 2018 11:52:50 +0100 Subject: [PATCH 102/356] vga_switcheroo: Fix missing gpu_bound call at audio client registration The commit 37a3a98ef601 ("ALSA: hda - Enable runtime PM only for discrete GPU") added a new ops gpu_bound to be called when GPU gets bound. The patch overlooked, however, that vga_switcheroo_enable() is called only once at GPU is bound. When an audio client is registered after that point, it would miss the gpu_bound call. This leads to the unexpected lack of runtime PM in HD-audio side. For addressing that regression, just call gpu_bound callback manually at vga_switcheroo_register_audio_client() when the GPU was already bound. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=201615 Fixes: 37a3a98ef601 ("ALSA: hda - Enable runtime PM only for discrete GPU") Cc: Reviewed-by: Lukas Wunner Signed-off-by: Takashi Iwai --- drivers/gpu/vga/vga_switcheroo.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/vga/vga_switcheroo.c b/drivers/gpu/vga/vga_switcheroo.c index cf2a18571d48..a132c37d7334 100644 --- a/drivers/gpu/vga/vga_switcheroo.c +++ b/drivers/gpu/vga/vga_switcheroo.c @@ -380,6 +380,9 @@ int vga_switcheroo_register_audio_client(struct pci_dev *pdev, mutex_unlock(&vgasr_mutex); return -EINVAL; } + /* notify if GPU has been already bound */ + if (ops->gpu_bound) + ops->gpu_bound(pdev, id); } mutex_unlock(&vgasr_mutex); From aab7a2414ba0d5c3d0571a90031b535adba7146a Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Fri, 28 Sep 2018 02:38:36 +0000 Subject: [PATCH 103/356] arm64: dts: renesas: r8a7795: add missing dma-names on hscif2 hscif2 has 4 dmas, but has only 2 dma-names. This patch add missing dma-names. Signed-off-by: Kuninori Morimoto Reviewed-by: Geert Uytterhoeven Fixes: e0f0bda79337701a ("arm64: dts: renesas: r8a7795: sort subnodes of the soc node") Signed-off-by: Simon Horman --- arch/arm64/boot/dts/renesas/r8a7795.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/renesas/r8a7795.dtsi b/arch/arm64/boot/dts/renesas/r8a7795.dtsi index b5f2273caca4..a79c8d369e0b 100644 --- a/arch/arm64/boot/dts/renesas/r8a7795.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a7795.dtsi @@ -652,7 +652,7 @@ clock-names = "fck", "brg_int", "scif_clk"; dmas = <&dmac1 0x35>, <&dmac1 0x34>, <&dmac2 0x35>, <&dmac2 0x34>; - dma-names = "tx", "rx"; + dma-names = "tx", "rx", "tx", "rx"; power-domains = <&sysc R8A7795_PD_ALWAYS_ON>; resets = <&cpg 518>; status = "disabled"; From 058ad7b6aa5204d3af878415c7b946748ab34f7a Mon Sep 17 00:00:00 2001 From: Fabrizio Castro Date: Thu, 4 Oct 2018 09:53:10 +0100 Subject: [PATCH 104/356] dt-bindings: arm: Fix RZ/G2E part number Fix RZ/G2E part number from its description. Signed-off-by: Fabrizio Castro Reviewed-by: Biju Das Reviewed-by: Rob Herring Signed-off-by: Simon Horman --- Documentation/devicetree/bindings/arm/shmobile.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/arm/shmobile.txt b/Documentation/devicetree/bindings/arm/shmobile.txt index f5e0f82fd503..58c4256d37a3 100644 --- a/Documentation/devicetree/bindings/arm/shmobile.txt +++ b/Documentation/devicetree/bindings/arm/shmobile.txt @@ -27,7 +27,7 @@ SoCs: compatible = "renesas,r8a77470" - RZ/G2M (R8A774A1) compatible = "renesas,r8a774a1" - - RZ/G2E (RA8774C0) + - RZ/G2E (R8A774C0) compatible = "renesas,r8a774c0" - R-Car M1A (R8A77781) compatible = "renesas,r8a7778" From eab53fdfd60a84b0cc514d4f1f5d79226c76df01 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Thu, 18 Oct 2018 19:48:53 +0300 Subject: [PATCH 105/356] arm64: dts: renesas: condor: switch from EtherAVB to GEther The "official" Condor boards have always been wired to mount NFS via GEther, not EtherAVB -- the boards resoldered for EtherAVB were local to Cogent Embedded, so we've been having an unpleasant situation where a "normal" Condor board still can't mount NFS (unless an EtherAVB PHY extension board is plugged in). Switch from EtherAVB to GEther at last! Fixes: 8091788f3d38 ("arm64: dts: renesas: condor: add EtherAVB support") Signed-off-by: Sergei Shtylyov Signed-off-by: Simon Horman --- .../boot/dts/renesas/r8a77980-condor.dts | 47 ++++++++++--------- 1 file changed, 24 insertions(+), 23 deletions(-) diff --git a/arch/arm64/boot/dts/renesas/r8a77980-condor.dts b/arch/arm64/boot/dts/renesas/r8a77980-condor.dts index fe2e2c051cc9..5a7012be0d6a 100644 --- a/arch/arm64/boot/dts/renesas/r8a77980-condor.dts +++ b/arch/arm64/boot/dts/renesas/r8a77980-condor.dts @@ -15,7 +15,7 @@ aliases { serial0 = &scif0; - ethernet0 = &avb; + ethernet0 = &gether; }; chosen { @@ -97,23 +97,6 @@ }; }; -&avb { - pinctrl-0 = <&avb_pins>; - pinctrl-names = "default"; - - phy-mode = "rgmii-id"; - phy-handle = <&phy0>; - renesas,no-ether-link; - status = "okay"; - - phy0: ethernet-phy@0 { - rxc-skew-ps = <1500>; - reg = <0>; - interrupt-parent = <&gpio1>; - interrupts = <17 IRQ_TYPE_LEVEL_LOW>; - }; -}; - &canfd { pinctrl-0 = <&canfd0_pins>; pinctrl-names = "default"; @@ -139,6 +122,23 @@ clock-frequency = <32768>; }; +&gether { + pinctrl-0 = <&gether_pins>; + pinctrl-names = "default"; + + phy-mode = "rgmii-id"; + phy-handle = <&phy0>; + renesas,no-ether-link; + status = "okay"; + + phy0: ethernet-phy@0 { + rxc-skew-ps = <1500>; + reg = <0>; + interrupt-parent = <&gpio4>; + interrupts = <23 IRQ_TYPE_LEVEL_LOW>; + }; +}; + &i2c0 { pinctrl-0 = <&i2c0_pins>; pinctrl-names = "default"; @@ -236,16 +236,17 @@ }; &pfc { - avb_pins: avb { - groups = "avb_mdio", "avb_rgmii"; - function = "avb"; - }; - canfd0_pins: canfd0 { groups = "canfd0_data_a"; function = "canfd0"; }; + gether_pins: gether { + groups = "gether_mdio_a", "gether_rgmii", + "gether_txcrefclk", "gether_txcrefclk_mega"; + function = "gether"; + }; + i2c0_pins: i2c0 { groups = "i2c0"; function = "i2c0"; From 02522ad77fb7619615720147dc5da18024cad577 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 2 Nov 2018 13:09:08 +0100 Subject: [PATCH 106/356] s390: update defconfigs Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/configs/debug_defconfig | 14 ++++- arch/s390/configs/performance_defconfig | 13 +++- arch/s390/defconfig | 79 +++++++++++++------------ 3 files changed, 63 insertions(+), 43 deletions(-) diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 259d1698ac50..c69cb04b7a59 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -64,6 +64,8 @@ CONFIG_NUMA=y CONFIG_PREEMPT=y CONFIG_HZ_100=y CONFIG_KEXEC_FILE=y +CONFIG_EXPOLINE=y +CONFIG_EXPOLINE_AUTO=y CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y @@ -84,9 +86,11 @@ CONFIG_PCI_DEBUG=y CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y CONFIG_CHSC_SCH=y +CONFIG_VFIO_AP=m CONFIG_CRASH_DUMP=y CONFIG_BINFMT_MISC=m CONFIG_HIBERNATION=y +CONFIG_PM_DEBUG=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_PACKET_DIAG=m @@ -161,8 +165,6 @@ CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_CT_NETLINK=m CONFIG_NF_CT_NETLINK_TIMEOUT=m CONFIG_NF_TABLES=m -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m CONFIG_NFT_CT=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m @@ -365,6 +367,8 @@ CONFIG_NET_ACT_SKBEDIT=m CONFIG_NET_ACT_CSUM=m CONFIG_DNS_RESOLVER=y CONFIG_OPENVSWITCH=m +CONFIG_VSOCKETS=m +CONFIG_VIRTIO_VSOCKETS=m CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y @@ -461,6 +465,7 @@ CONFIG_PPTP=m CONFIG_PPPOL2TP=m CONFIG_PPP_ASYNC=m CONFIG_PPP_SYNC_TTY=m +CONFIG_ISM=m CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set @@ -486,9 +491,12 @@ CONFIG_MLX4_INFINIBAND=m CONFIG_MLX5_INFINIBAND=m CONFIG_VFIO=m CONFIG_VFIO_PCI=m +CONFIG_VFIO_MDEV=m +CONFIG_VFIO_MDEV_DEVICE=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y +CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -615,7 +623,6 @@ CONFIG_DEBUG_CREDENTIALS=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=300 CONFIG_NOTIFIER_ERROR_INJECTION=m -CONFIG_PM_NOTIFIER_ERROR_INJECT=m CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m CONFIG_FAULT_INJECTION=y CONFIG_FAILSLAB=y @@ -727,3 +734,4 @@ CONFIG_APPLDATA_BASE=y CONFIG_KVM=m CONFIG_KVM_S390_UCONTROL=y CONFIG_VHOST_NET=m +CONFIG_VHOST_VSOCK=m diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig index 37fd60c20e22..32f539dc9c19 100644 --- a/arch/s390/configs/performance_defconfig +++ b/arch/s390/configs/performance_defconfig @@ -65,6 +65,8 @@ CONFIG_NR_CPUS=512 CONFIG_NUMA=y CONFIG_HZ_100=y CONFIG_KEXEC_FILE=y +CONFIG_EXPOLINE=y +CONFIG_EXPOLINE_AUTO=y CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y @@ -82,9 +84,11 @@ CONFIG_PCI=y CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y CONFIG_CHSC_SCH=y +CONFIG_VFIO_AP=m CONFIG_CRASH_DUMP=y CONFIG_BINFMT_MISC=m CONFIG_HIBERNATION=y +CONFIG_PM_DEBUG=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_PACKET_DIAG=m @@ -159,8 +163,6 @@ CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_CT_NETLINK=m CONFIG_NF_CT_NETLINK_TIMEOUT=m CONFIG_NF_TABLES=m -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m CONFIG_NFT_CT=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m @@ -362,6 +364,8 @@ CONFIG_NET_ACT_SKBEDIT=m CONFIG_NET_ACT_CSUM=m CONFIG_DNS_RESOLVER=y CONFIG_OPENVSWITCH=m +CONFIG_VSOCKETS=m +CONFIG_VIRTIO_VSOCKETS=m CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y @@ -458,6 +462,7 @@ CONFIG_PPTP=m CONFIG_PPPOL2TP=m CONFIG_PPP_ASYNC=m CONFIG_PPP_SYNC_TTY=m +CONFIG_ISM=m CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set @@ -483,9 +488,12 @@ CONFIG_MLX4_INFINIBAND=m CONFIG_MLX5_INFINIBAND=m CONFIG_VFIO=m CONFIG_VFIO_PCI=m +CONFIG_VFIO_MDEV=m +CONFIG_VFIO_MDEV_DEVICE=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y +CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -666,3 +674,4 @@ CONFIG_APPLDATA_BASE=y CONFIG_KVM=m CONFIG_KVM_S390_UCONTROL=y CONFIG_VHOST_NET=m +CONFIG_VHOST_VSOCK=m diff --git a/arch/s390/defconfig b/arch/s390/defconfig index 7cb6a52f727d..4d58a92b5d97 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -26,14 +26,23 @@ CONFIG_CGROUP_CPUACCT=y CONFIG_CGROUP_PERF=y CONFIG_NAMESPACES=y CONFIG_USER_NS=y +CONFIG_CHECKPOINT_RESTORE=y CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set -CONFIG_CHECKPOINT_RESTORE=y CONFIG_BPF_SYSCALL=y CONFIG_USERFAULTFD=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y +CONFIG_LIVEPATCH=y +CONFIG_NR_CPUS=256 +CONFIG_NUMA=y +CONFIG_HZ_100=y +CONFIG_KEXEC_FILE=y +CONFIG_CRASH_DUMP=y +CONFIG_HIBERNATION=y +CONFIG_PM_DEBUG=y +CONFIG_CMM=m CONFIG_OPROFILE=y CONFIG_KPROBES=y CONFIG_JUMP_LABEL=y @@ -44,11 +53,7 @@ CONFIG_BLK_DEV_INTEGRITY=y CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y CONFIG_DEFAULT_DEADLINE=y -CONFIG_LIVEPATCH=y -CONFIG_NR_CPUS=256 -CONFIG_NUMA=y -CONFIG_HZ_100=y -CONFIG_KEXEC_FILE=y +CONFIG_BINFMT_MISC=m CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y @@ -60,9 +65,6 @@ CONFIG_ZBUD=m CONFIG_ZSMALLOC=m CONFIG_ZSMALLOC_STAT=y CONFIG_IDLE_PAGE_TRACKING=y -CONFIG_CRASH_DUMP=y -CONFIG_BINFMT_MISC=m -CONFIG_HIBERNATION=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -98,6 +100,7 @@ CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y CONFIG_VIRTIO_BLK=y CONFIG_SCSI=y +# CONFIG_SCSI_MQ_DEFAULT is not set CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_BLK_DEV_SR=y @@ -131,6 +134,7 @@ CONFIG_EQUALIZER=m CONFIG_TUN=m CONFIG_VIRTIO_NET=y # CONFIG_NET_VENDOR_ALACRITECH is not set +# CONFIG_NET_VENDOR_AURORA is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_SOLARFLARE is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set @@ -157,33 +161,6 @@ CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_HUGETLBFS=y # CONFIG_NETWORK_FILESYSTEMS is not set -CONFIG_DEBUG_INFO=y -CONFIG_DEBUG_INFO_DWARF4=y -CONFIG_GDB_SCRIPTS=y -CONFIG_UNUSED_SYMBOLS=y -CONFIG_DEBUG_SECTION_MISMATCH=y -CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y -CONFIG_MAGIC_SYSRQ=y -CONFIG_DEBUG_PAGEALLOC=y -CONFIG_DETECT_HUNG_TASK=y -CONFIG_PANIC_ON_OOPS=y -CONFIG_PROVE_LOCKING=y -CONFIG_LOCK_STAT=y -CONFIG_DEBUG_LOCKDEP=y -CONFIG_DEBUG_ATOMIC_SLEEP=y -CONFIG_DEBUG_LIST=y -CONFIG_DEBUG_SG=y -CONFIG_DEBUG_NOTIFIERS=y -CONFIG_RCU_CPU_STALL_TIMEOUT=60 -CONFIG_LATENCYTOP=y -CONFIG_SCHED_TRACER=y -CONFIG_FTRACE_SYSCALLS=y -CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y -CONFIG_STACK_TRACER=y -CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_FUNCTION_PROFILER=y -# CONFIG_RUNTIME_TESTING_MENU is not set -CONFIG_S390_PTDUMP=y CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_AUTHENC=m CONFIG_CRYPTO_TEST=m @@ -193,6 +170,7 @@ CONFIG_CRYPTO_CBC=y CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m +CONFIG_CRYPTO_OFB=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m CONFIG_CRYPTO_CMAC=m @@ -231,7 +209,6 @@ CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_ZCRYPT=m -CONFIG_ZCRYPT_MULTIDEVNODES=y CONFIG_PKEY=m CONFIG_CRYPTO_PAES_S390=m CONFIG_CRYPTO_SHA1_S390=m @@ -247,4 +224,30 @@ CONFIG_CRC7=m # CONFIG_XZ_DEC_ARM is not set # CONFIG_XZ_DEC_ARMTHUMB is not set # CONFIG_XZ_DEC_SPARC is not set -CONFIG_CMM=m +CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF4=y +CONFIG_GDB_SCRIPTS=y +CONFIG_UNUSED_SYMBOLS=y +CONFIG_DEBUG_SECTION_MISMATCH=y +CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_PAGEALLOC=y +CONFIG_DETECT_HUNG_TASK=y +CONFIG_PANIC_ON_OOPS=y +CONFIG_PROVE_LOCKING=y +CONFIG_LOCK_STAT=y +CONFIG_DEBUG_LOCKDEP=y +CONFIG_DEBUG_ATOMIC_SLEEP=y +CONFIG_DEBUG_LIST=y +CONFIG_DEBUG_SG=y +CONFIG_DEBUG_NOTIFIERS=y +CONFIG_RCU_CPU_STALL_TIMEOUT=60 +CONFIG_LATENCYTOP=y +CONFIG_SCHED_TRACER=y +CONFIG_FTRACE_SYSCALLS=y +CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y +CONFIG_STACK_TRACER=y +CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_FUNCTION_PROFILER=y +# CONFIG_RUNTIME_TESTING_MENU is not set +CONFIG_S390_PTDUMP=y From f55275bcc72948056387041abe9fce1c54300adc Mon Sep 17 00:00:00 2001 From: Olof Johansson Date: Mon, 5 Nov 2018 06:34:09 -0800 Subject: [PATCH 107/356] ARM: defconfig: Disable PREEMPT again on multi_v7 I should have let this soak for a while in linux-next, since we have at least one board that hit a regression from it. Revert from 4.20-rc, and we'll queue it for next merge window once regression is fixed. This reverts commit 513eb98595522bc0cb83831a9daee1d5738e66f1. Signed-off-by: Olof Johansson --- arch/arm/configs/multi_v7_defconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 1c7616815a86..63af6234c1b6 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -1,7 +1,6 @@ CONFIG_SYSVIPC=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y -CONFIG_PREEMPT=y CONFIG_CGROUPS=y CONFIG_BLK_DEV_INITRD=y CONFIG_EMBEDDED=y From ee474b81fe5aa5dc0faae920bf66240fbf55f891 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 1 Nov 2018 23:29:28 +0900 Subject: [PATCH 108/356] tracing/kprobes: Fix strpbrk() argument order Fix strpbrk()'s argument order, it must pass acceptable string in 2nd argument. Note that this can cause a kernel panic where it recovers backup character to code->data. Link: http://lkml.kernel.org/r/154108256792.2604.1816052586385217811.stgit@devbox Fixes: a6682814f371 ("tracing/kprobes: Allow kprobe-events to record module symbol") Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_probe.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 3ef15a6683c0..bd30e9398d2a 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -535,7 +535,7 @@ int traceprobe_update_arg(struct probe_arg *arg) if (code[1].op != FETCH_OP_IMM) return -EINVAL; - tmp = strpbrk("+-", code->data); + tmp = strpbrk(code->data, "+-"); if (tmp) c = *tmp; ret = traceprobe_split_symbol_offset(code->data, From 79ef68c7e1f665578e005b454480b6eca60edabe Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 5 Nov 2018 12:23:40 -0300 Subject: [PATCH 109/356] perf augmented_syscalls: Start collecting pathnames in the BPF program This is the start of having the raw_syscalls:sys_enter BPF handler collecting pointer arguments, namely pathnames, and with two syscalls that have that pointer in different arguments, "open" as it as its first argument, "openat" as the second. With this in place the existing beautifiers in 'perf trace' works, those args are shown instead of just the pointer that comes with the syscalls tracepoints. This also serves to show and document pitfalls in the process of using just that place in the kernel (raw_syscalls:sys_enter) plus tables provided by userspace to collect syscall pointer arguments. One is the need to use a barrier, as suggested by Edward, to avoid clang optimizations that make the kernel BPF verifier to refuse loading our pointer contents collector. The end result should be a generic eBPF program that works in all architectures, with the differences amongst archs resolved by the userspace component, 'perf trace', that should get all its tables created automatically from the kernel components where they are defined, via string table constructors for things not expressed in BTF/DWARF (enums, structs, etc), and otherwise using those observability files (BTF). Cc: Adrian Hunter Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: David Ahern Cc: Edward Cree Cc: Jiri Olsa Cc: Martin KaFai Lau Cc: Namhyung Kim Cc: Wang Nan Cc: Yonghong Song Link: https://lkml.kernel.org/n/tip-37dz54pmotgpnwg9tb6zuk9j@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- .../examples/bpf/augmented_raw_syscalls.c | 72 +++++++++++++++++++ 1 file changed, 72 insertions(+) diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c index cde91c34b101..90a19336310b 100644 --- a/tools/perf/examples/bpf/augmented_raw_syscalls.c +++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c @@ -37,15 +37,87 @@ struct syscall_exit_args { long ret; }; +struct augmented_filename { + unsigned int size; + int reserved; + char value[256]; +}; + +#define SYS_OPEN 2 +#define SYS_OPENAT 257 + SEC("raw_syscalls:sys_enter") int sys_enter(struct syscall_enter_args *args) { struct { struct syscall_enter_args args; + struct augmented_filename filename; } augmented_args; unsigned int len = sizeof(augmented_args); + const void *filename_arg = NULL; probe_read(&augmented_args.args, sizeof(augmented_args.args), args); + /* + * Yonghong and Edward Cree sayz: + * + * https://www.spinics.net/lists/netdev/msg531645.html + * + * >> R0=inv(id=0) R1=inv2 R6=ctx(id=0,off=0,imm=0) R7=inv64 R10=fp0,call_-1 + * >> 10: (bf) r1 = r6 + * >> 11: (07) r1 += 16 + * >> 12: (05) goto pc+2 + * >> 15: (79) r3 = *(u64 *)(r1 +0) + * >> dereference of modified ctx ptr R1 off=16 disallowed + * > Aha, we at least got a different error message this time. + * > And indeed llvm has done that optimisation, rather than the more obvious + * > 11: r3 = *(u64 *)(r1 +16) + * > because it wants to have lots of reads share a single insn. You may be able + * > to defeat that optimisation by adding compiler barriers, idk. Maybe someone + * > with llvm knowledge can figure out how to stop it (ideally, llvm would know + * > when it's generating for bpf backend and not do that). -O0? ¯\_(ツ)_/¯ + * + * The optimization mostly likes below: + * + * br1: + * ... + * r1 += 16 + * goto merge + * br2: + * ... + * r1 += 20 + * goto merge + * merge: + * *(u64 *)(r1 + 0) + * + * The compiler tries to merge common loads. There is no easy way to + * stop this compiler optimization without turning off a lot of other + * optimizations. The easiest way is to add barriers: + * + * __asm__ __volatile__("": : :"memory") + * + * after the ctx memory access to prevent their down stream merging. + */ + switch (augmented_args.args.syscall_nr) { + case SYS_OPEN: filename_arg = (const void *)args->args[0]; + __asm__ __volatile__("": : :"memory"); + break; + case SYS_OPENAT: filename_arg = (const void *)args->args[1]; + break; + } + + if (filename_arg != NULL) { + augmented_args.filename.reserved = 0; + augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, + sizeof(augmented_args.filename.value), + filename_arg); + if (augmented_args.filename.size < sizeof(augmented_args.filename.value)) { + len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size; + len &= sizeof(augmented_args.filename.value) - 1; + } + } else { + len = sizeof(augmented_args.args); + } + perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len); return 0; } From b42967dcac1d4f5b059ec25568136462bcb051fe Mon Sep 17 00:00:00 2001 From: Yi Wang Date: Mon, 29 Oct 2018 15:17:31 +0800 Subject: [PATCH 110/356] x86/hyper-v: Fix indentation in hv_do_fast_hypercall16() Remove the surplus TAB in hv_do_fast_hypercall16(). Signed-off-by: Yi Wang Signed-off-by: Thomas Gleixner Cc: kys@microsoft.com Cc: haiyangz@microsoft.com Cc: sthemmin@microsoft.com Cc: bp@alien8.de Cc: hpa@zytor.com Cc: devel@linuxdriverproject.org Cc: zhong.weidong@zte.com.cn Link: https://lkml.kernel.org/r/1540797451-2792-1-git-send-email-wang.yi59@zte.com.cn --- arch/x86/include/asm/mshyperv.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 0d6271cce198..1d0a7778e163 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -232,7 +232,7 @@ static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2) : "cc"); } #endif - return hv_status; + return hv_status; } /* From 437e88ab8f9e2ad90576ab74c4cf8f527bbf51cd Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Tue, 23 Oct 2018 16:11:25 -0700 Subject: [PATCH 111/356] x86/build: Remove -pipe from KBUILD_CFLAGS Commit 77b0bf55bc67 ("kbuild/Makefile: Prepare for using macros in inline assembly code to work around asm() related GCC inlining bugs") added -Wa,- to KBUILD_CFLAGS, which breaks compiling with Clang (hangs indefinitely at compiling init/main.o). This happens because while Clang accepts -pipe (and has it documented in its list of supported flags), it silently ignores it after this 2010 commit (thanks to Nick Desaulniers for tracking this down), meaning that gas just infinitely waits for stdin and never receives it. https://github.com/llvm-mirror/clang/commit/c19a12dc3d441bec62eed55e312b76c12d6d9022 Initially, I had suggested just add -Wa,- to KBUILD_CFLAGS when GCC was being used but that was before realizing it is because Clang doesn't do anything with -pipe. H. Peter Anvin suggested checking to see if -pipe gives us any gains out of GCC. Turns out it might actually be hurting: With -pipe: real 3m40.813s real 3m44.449s real 3m39.648s Without -pipe: real 3m38.492s real 3m38.335s real 3m38.975s The issue of -Wa,- being passed along to gas without -pipe being supported should still probably be fixed on the LLVM side (open issue: https://bugs.llvm.org/show_bug.cgi?id=39410) but this is not as much of a workaround anymore since it helps both GCC and Clang. Suggested-by: H. Peter Anvin Signed-off-by: Nathan Chancellor Signed-off-by: Thomas Gleixner Tested-by: Nick Desaulniers Reviewed-by: Nadav Amit Reviewed-by: Nick Desaulniers Cc: Borislav Petkov Cc: Kees Cook Cc: Masahiro Yamada Link: https://github.com/ClangBuiltLinux/linux/issues/213 Link: https://lkml.kernel.org/r/20181023231125.27976-1-natechancellor@gmail.com --- arch/x86/Makefile | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 5b562e464009..88398fdf8129 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -213,8 +213,6 @@ ifdef CONFIG_X86_64 KBUILD_LDFLAGS += $(call ld-option, -z max-page-size=0x200000) endif -# Speed up the build -KBUILD_CFLAGS += -pipe # Workaround for a gcc prelease that unfortunately was shipped in a suse release KBUILD_CFLAGS += -Wno-sign-compare # @@ -239,7 +237,7 @@ archheaders: archmacros: $(Q)$(MAKE) $(build)=arch/x86/kernel arch/x86/kernel/macros.s -ASM_MACRO_FLAGS = -Wa,arch/x86/kernel/macros.s -Wa,- +ASM_MACRO_FLAGS = -Wa,arch/x86/kernel/macros.s export ASM_MACRO_FLAGS KBUILD_CFLAGS += $(ASM_MACRO_FLAGS) From 163c8d54a997153ee1a1e07fcac087492ad85b37 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Mon, 5 Nov 2018 07:36:28 +0100 Subject: [PATCH 112/356] compiler: remove __no_sanitize_address_or_inline again The __no_sanitize_address_or_inline and __no_kasan_or_inline defines are almost identical. The only difference is that __no_kasan_or_inline does not have the 'notrace' attribute. To be able to replace __no_sanitize_address_or_inline with the older definition, add 'notrace' to __no_kasan_or_inline and change to two users of __no_sanitize_address_or_inline in the s390 code. The 'notrace' option is necessary for e.g. the __load_psw_mask function in arch/s390/include/asm/processor.h. Without the option it is possible to trace __load_psw_mask which leads to kernel stack overflow. Signed-off-by: Martin Schwidefsky Pointed-out-by: Andrey Ryabinin Acked-by: Steven Rostedt (VMware) Signed-off-by: Linus Torvalds --- arch/s390/include/asm/processor.h | 4 ++-- include/linux/compiler-gcc.h | 12 ------------ include/linux/compiler.h | 2 +- 3 files changed, 3 insertions(+), 15 deletions(-) diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 302795c47c06..81038ab357ce 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -236,7 +236,7 @@ static inline unsigned long current_stack_pointer(void) return sp; } -static __no_sanitize_address_or_inline unsigned short stap(void) +static __no_kasan_or_inline unsigned short stap(void) { unsigned short cpu_address; @@ -330,7 +330,7 @@ static inline void __load_psw(psw_t psw) * Set PSW mask to specified value, while leaving the * PSW addr pointing to the next instruction. */ -static __no_sanitize_address_or_inline void __load_psw_mask(unsigned long mask) +static __no_kasan_or_inline void __load_psw_mask(unsigned long mask) { unsigned long addr; psw_t psw; diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index c0f5db3a9621..2010493e1040 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -143,18 +143,6 @@ #define KASAN_ABI_VERSION 3 #endif -/* - * Because __no_sanitize_address conflicts with inlining: - * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 - * we do one or the other. - */ -#ifdef CONFIG_KASAN -#define __no_sanitize_address_or_inline \ - __no_sanitize_address __maybe_unused notrace -#else -#define __no_sanitize_address_or_inline inline -#endif - #if GCC_VERSION >= 50100 #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 #endif diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 18c80cfa4fc4..06396c1cf127 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -189,7 +189,7 @@ void __read_once_size(const volatile void *p, void *res, int size) * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 * '__maybe_unused' allows us to avoid defined-but-not-used warnings. */ -# define __no_kasan_or_inline __no_sanitize_address __maybe_unused +# define __no_kasan_or_inline __no_sanitize_address notrace __maybe_unused #else # define __no_kasan_or_inline __always_inline #endif From 21b42eb46834f6245a55ac77bdf3e14c034e2864 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 5 Nov 2018 16:51:49 +0900 Subject: [PATCH 113/356] kbuild: rpm-pkg: fix binrpm-pkg breakage when O= is used Zhenzhong Duan reported that running 'make O=/build/kernel binrpm-pkg' failed with the following errors: Running 'make O=/build/kernel binrpm-pkg' failed with below two errors. Makefile:600: include/config/auto.conf: No such file or directory + cp make -C /mnt/root/kernel O=/build/kernel image_name make -f /mnt/root/kernel/Makefile ... cp: invalid option -- 'C' Try 'cp --help' for more information. Prior to commit 80463f1b7bf9 ("kbuild: add --include-dir flag only for out-of-tree build"), both srctree and objtree were added to --include-dir redundantly, and the wrong code 'make image_name' was working by relying on that. Now, the potential issue that had previously been hidden just showed up. 'make image_name' recurses to the generated $(objtree)/Makefile and ends up with running in srctree, which is incorrect. It should be invoked with '-f $srctree/Makefile' (or KBUILD_SRC=) to be executed in objtree. Fixes: 80463f1b7bf9 ("kbuild: add --include-dir flag only for out-of-tree build") Reported-by: Zhenzhong Duan Signed-off-by: Masahiro Yamada --- scripts/package/mkspec | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/scripts/package/mkspec b/scripts/package/mkspec index e05646dc24dc..009147d4718e 100755 --- a/scripts/package/mkspec +++ b/scripts/package/mkspec @@ -12,6 +12,7 @@ # how we were called determines which rpms we build and how we build them if [ "$1" = prebuilt ]; then S=DEL + MAKE="$MAKE -f $srctree/Makefile" else S= fi @@ -78,19 +79,19 @@ $S %prep $S %setup -q $S $S %build -$S make %{?_smp_mflags} KBUILD_BUILD_VERSION=%{release} +$S $MAKE %{?_smp_mflags} KBUILD_BUILD_VERSION=%{release} $S %install mkdir -p %{buildroot}/boot %ifarch ia64 mkdir -p %{buildroot}/boot/efi - cp \$(make image_name) %{buildroot}/boot/efi/vmlinuz-$KERNELRELEASE + cp \$($MAKE image_name) %{buildroot}/boot/efi/vmlinuz-$KERNELRELEASE ln -s efi/vmlinuz-$KERNELRELEASE %{buildroot}/boot/ %else - cp \$(make image_name) %{buildroot}/boot/vmlinuz-$KERNELRELEASE + cp \$($MAKE image_name) %{buildroot}/boot/vmlinuz-$KERNELRELEASE %endif -$M make %{?_smp_mflags} INSTALL_MOD_PATH=%{buildroot} KBUILD_SRC= modules_install - make %{?_smp_mflags} INSTALL_HDR_PATH=%{buildroot}/usr KBUILD_SRC= headers_install +$M $MAKE %{?_smp_mflags} INSTALL_MOD_PATH=%{buildroot} modules_install + $MAKE %{?_smp_mflags} INSTALL_HDR_PATH=%{buildroot}/usr headers_install cp System.map %{buildroot}/boot/System.map-$KERNELRELEASE cp .config %{buildroot}/boot/config-$KERNELRELEASE bzip2 -9 --keep vmlinux From 02826a6ba301b72461c3706e1cc66d5571cd327e Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 5 Nov 2018 16:52:34 +0900 Subject: [PATCH 114/356] kbuild: deb-pkg: fix bindeb-pkg breakage when O= is used Ard Biesheuvel reports bindeb-pkg with O= option is broken in the following way: ... LD [M] sound/soc/rockchip/snd-soc-rk3399-gru-sound.ko LD [M] sound/soc/rockchip/snd-soc-rockchip-pcm.ko LD [M] sound/soc/rockchip/snd-soc-rockchip-rt5645.ko LD [M] sound/soc/rockchip/snd-soc-rockchip-spdif.ko LD [M] sound/soc/sh/rcar/snd-soc-rcar.ko fakeroot -u debian/rules binary make KERNELRELEASE=4.19.0-12677-g19beffaf7a99-dirty ARCH=arm64 KBUILD_SRC= intdeb-pkg /bin/bash /home/ard/linux/scripts/package/builddeb Makefile:600: include/config/auto.conf: No such file or directory *** *** Configuration file ".config" not found! *** *** Please run some configurator (e.g. "make oldconfig" or *** "make menuconfig" or "make xconfig"). *** make[12]: *** [syncconfig] Error 1 make[11]: *** [syncconfig] Error 2 make[10]: *** [include/config/auto.conf] Error 2 make[9]: *** [__sub-make] Error 2 ... Prior to commit 80463f1b7bf9 ("kbuild: add --include-dir flag only for out-of-tree build"), both srctree and objtree were added to --include-dir redundantly, and the wrong code '$MAKE image_name' was working by relying on that. Now, the potential issue that had previously been hidden just showed up. '$MAKE image_name' recurses to the generated $(objtree)/Makefile and ends up with running in srctree, which is incorrect. It should be invoked with '-f $srctree/Makefile' (or KBUILD_SRC=) to be executed in objtree. Fixes: 80463f1b7bf9 ("kbuild: add --include-dir flag only for out-of-tree build") Reported-by: Ard Biesheuvel Signed-off-by: Masahiro Yamada Tested-by: Ard Biesheuvel --- scripts/package/builddeb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/package/builddeb b/scripts/package/builddeb index 90c9a8ac7adb..0b31f4f1f92c 100755 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -81,7 +81,7 @@ else cp System.map "$tmpdir/boot/System.map-$version" cp $KCONFIG_CONFIG "$tmpdir/boot/config-$version" fi -cp "$($MAKE -s image_name)" "$tmpdir/$installed_image_path" +cp "$($MAKE -s -f $srctree/Makefile image_name)" "$tmpdir/$installed_image_path" if grep -q "^CONFIG_OF=y" $KCONFIG_CONFIG ; then # Only some architectures with OF support have this target From 6fce3a406108ee6c8a61e2a33e52e9198a626ea0 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Thu, 4 Oct 2018 11:37:00 +0200 Subject: [PATCH 115/356] drm/etnaviv: fix bogus fence complete check in timeout handler The GPU hardware fences and the job out-fences are on different timelines so it's wrong to compare them. Fix this by only looking at the out-fence. Cc: Fixes: 2c83a726d6fb (drm/etnaviv: bring back progress check in job timeout handler) Signed-off-by: Lucas Stach --- drivers/gpu/drm/etnaviv/etnaviv_sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c index 69e9b431bf1f..e5a9fae31ab7 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c @@ -93,7 +93,7 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job) * If the GPU managed to complete this jobs fence, the timout is * spurious. Bail out. */ - if (fence_completed(gpu, submit->out_fence->seqno)) + if (dma_fence_is_signaled(submit->out_fence)) return; /* From c3537fc251503af18085b8f84126d13743663970 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 1 Oct 2018 12:59:26 -0700 Subject: [PATCH 116/356] perf evlist: Move perf_evsel__reset_weak_group into evlist - Move the function from builtin-stat to evlist for reuse - Rename to evlist to match purpose better - Pass the evlist as first argument. - No functional changes Signed-off-by: Andi Kleen Acked-by: Jiri Olsa Link: http://lkml.kernel.org/r/20181001195927.14211-1-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 28 +--------------------------- tools/perf/util/evlist.c | 27 +++++++++++++++++++++++++++ tools/perf/util/evlist.h | 3 +++ 3 files changed, 31 insertions(+), 27 deletions(-) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index d1028d7755bb..a635abfa77b6 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -383,32 +383,6 @@ static bool perf_evsel__should_store_id(struct perf_evsel *counter) return STAT_RECORD || counter->attr.read_format & PERF_FORMAT_ID; } -static struct perf_evsel *perf_evsel__reset_weak_group(struct perf_evsel *evsel) -{ - struct perf_evsel *c2, *leader; - bool is_open = true; - - leader = evsel->leader; - pr_debug("Weak group for %s/%d failed\n", - leader->name, leader->nr_members); - - /* - * for_each_group_member doesn't work here because it doesn't - * include the first entry. - */ - evlist__for_each_entry(evsel_list, c2) { - if (c2 == evsel) - is_open = false; - if (c2->leader == leader) { - if (is_open) - perf_evsel__close(c2); - c2->leader = c2; - c2->nr_members = 0; - } - } - return leader; -} - static bool is_target_alive(struct target *_target, struct thread_map *threads) { @@ -477,7 +451,7 @@ try_again: if ((errno == EINVAL || errno == EBADF) && counter->leader != counter && counter->weak_group) { - counter = perf_evsel__reset_weak_group(counter); + counter = perf_evlist__reset_weak_group(evsel_list, counter); goto try_again; } diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index e88e6f9b1463..668d2a9ef0f4 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1810,3 +1810,30 @@ void perf_evlist__force_leader(struct perf_evlist *evlist) leader->forced_leader = true; } } + +struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evsel_list, + struct perf_evsel *evsel) +{ + struct perf_evsel *c2, *leader; + bool is_open = true; + + leader = evsel->leader; + pr_debug("Weak group for %s/%d failed\n", + leader->name, leader->nr_members); + + /* + * for_each_group_member doesn't work here because it doesn't + * include the first entry. + */ + evlist__for_each_entry(evsel_list, c2) { + if (c2 == evsel) + is_open = false; + if (c2->leader == leader) { + if (is_open) + perf_evsel__close(c2); + c2->leader = c2; + c2->nr_members = 0; + } + } + return leader; +} diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index dc66436add98..9919eed6d15b 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -312,4 +312,7 @@ bool perf_evlist__exclude_kernel(struct perf_evlist *evlist); void perf_evlist__force_leader(struct perf_evlist *evlist); +struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evlist, + struct perf_evsel *evsel); + #endif /* __PERF_EVLIST_H */ From cf99ad1424c54fc84b84d3a3deb57a48c340c30a Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 1 Oct 2018 12:59:27 -0700 Subject: [PATCH 117/356] perf record: Support weak groups Implement a weak group fallback for 'perf record', similar to the existing 'perf stat' support. This allows to use groups that might be longer than the available counters without failing. Before: $ perf record -e '{cycles,cache-misses,cache-references,cpu_clk_unhalted.thread,cycles,cycles,cycles}' -a sleep 1 Error: The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (cycles). /bin/dmesg | grep -i perf may provide additional information. After: $ ./perf record -e '{cycles,cache-misses,cache-references,cpu_clk_unhalted.thread,cycles,cycles,cycles}:W' -a sleep 1 WARNING: No sample_id_all support, falling back to unordered processing [ perf record: Woken up 3 times to write data ] [ perf record: Captured and wrote 8.136 MB perf.data (134069 samples) ] Signed-off-by: Andi Kleen Acked-by: Jiri Olsa Link: http://lkml.kernel.org/r/20181001195927.14211-2-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-list.txt | 1 - tools/perf/builtin-record.c | 7 ++++++- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index 236b9b97dfdb..667c14e56031 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -55,7 +55,6 @@ counted. The following modifiers exist: S - read sample value (PERF_SAMPLE_READ) D - pin the event to the PMU W - group is weak and will fallback to non-group if not schedulable, - only supported in 'perf stat' for now. The 'p' modifier can be used for specifying how precise the instruction address should be. The 'p' modifier can be specified multiple times: diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 10cf889c6d75..488779bc4c8d 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -391,7 +391,12 @@ try_again: ui__warning("%s\n", msg); goto try_again; } - + if ((errno == EINVAL || errno == EBADF) && + pos->leader != pos && + pos->weak_group) { + pos = perf_evlist__reset_weak_group(evlist, pos); + goto try_again; + } rc = -errno; perf_evsel__open_strerror(pos, &opts->target, errno, msg, sizeof(msg)); From ea1fa48c055f833eb25f0c33188feecb7002ada5 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Tue, 23 Oct 2018 17:16:16 +0200 Subject: [PATCH 118/356] perf stat: Handle different PMU names with common prefix On s390 the CPU Measurement Facility for counters now supports 2 PMUs named cpum_cf (CPU Measurement Facility for counters) and cpum_cf_diag (CPU Measurement Facility for diagnostic counters) for one and the same CPU. Running command [root@s35lp76 perf]# ./perf stat -e tx_c_tend \ -- ~/mytests/cf-tx-events 1 Measuring transactions TX_C_TABORT_NO_SPECIAL: 0 expected:0 TX_C_TABORT_SPECIAL: 0 expected:0 TX_C_TEND: 1 expected:1 TX_NC_TABORT: 11 expected:11 TX_NC_TEND: 1 expected:1 Performance counter stats for '/root/mytests/cf-tx-events 1': 2 tx_c_tend 0.002120091 seconds time elapsed 0.000121000 seconds user 0.002127000 seconds sys [root@s35lp76 perf]# displays output which is unexpected (and wrong): 2 tx_c_tend The test program definitely triggers only one transaction, as shown in line 'TX_C_TEND: 1 expected:1'. This is caused by the following call sequence: pmu_lookup() scans and installs a PMU. +--> pmu_aliases() parses all aliases in directory ...//events/* which are file names. +--> pmu_aliases_parse() Read each file in directory and create an new alias entry. This is done with +--> perf_pmu__new_alias() and +--> __perf_pmu__new_alias() which also check for identical alias names. After pmu_aliases() returns, a complete list of event names for this pmu has been created. Now function pmu_add_cpu_aliases() is called to add the events listed in the json | files to the alias list of the cpu. +--> perf_pmu__find_map() Returns a pointer to the json events. Now function pmu_add_cpu_aliases() scans through all events listed in the JSON files for this CPU. Each json event pmu name is compared with the current PMU being built up and if they mismatch, the json event is added to the current PMUs alias list. To avoid duplicate entries the following comparison is done: if (!is_arm_pmu_core(name)) { pname = pe->pmu ? pe->pmu : "cpu"; if (strncmp(pname, name, strlen(pname))) continue; } The culprit is the strncmp() function. Using current s390 PMU naming, the first PMU is 'cpum_cf' and a long list of events is added, among them 'tx_c_tend' When the second PMU named 'cpum_cf_diag' is added, only one event named 'CF_DIAG' is added by the pmu_aliases() function. Now function pmu_add_cpu_aliases() is invoked for PMU 'cpum_cf_diag'. Since the CPUID string is the same for both PMUs, json file events for PMU named 'cpum_cf' are added to the PMU 'cpm_cf_diag' This happens because the strncmp() actually compares: strncmp("cpum_cf", "cpum_cf_diag", 6); The first parameter is the pmu name taken from the event in the json file. The second parameter is the pmu name of the PMU currently being built. They are different, but the length of the compare only tests the common prefix and this returns 0(true) when it should return false. Now all events for PMU cpum_cf are added to the alias list for pmu cpum_cf_diag. Later on in function parse_events_add_pmu() the event 'tx_c_end' is searched in all available PMUs and found twice, adding it two times to the evsel_list global variable which is the root of all events. This results in a counter value of 2 instead of 1. Output with this patch: [root@s35lp76 perf]# ./perf stat -e tx_c_tend \ -- ~/mytests/cf-tx-events 1 Measuring transactions TX_C_TABORT_NO_SPECIAL: 0 expected:0 TX_C_TABORT_SPECIAL: 0 expected:0 TX_C_TEND: 1 expected:1 TX_NC_TABORT: 11 expected:11 TX_NC_TEND: 1 expected:1 Performance counter stats for '/root/mytests/cf-tx-events 1': 1 tx_c_tend 0.001815365 seconds time elapsed 0.000123000 seconds user 0.001756000 seconds sys [root@s35lp76 perf]# Signed-off-by: Thomas Richter Reviewed-by: Hendrik Brueckner Reviewed-by: Sebastien Boisvert Cc: Heiko Carstens Cc: Kan Liang Cc: Martin Schwidefsky Cc: stable@vger.kernel.org Fixes: 292c34c10249 ("perf pmu: Fix core PMU alias list for X86 platform") Link: http://lkml.kernel.org/r/20181023151616.78193-1-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/pmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 7799788f662f..7e49baad304d 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -773,7 +773,7 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu) if (!is_arm_pmu_core(name)) { pname = pe->pmu ? pe->pmu : "cpu"; - if (strncmp(pname, name, strlen(pname))) + if (strcmp(pname, name)) continue; } From 590ac60d8aa929bd21e35cd95a7d8720d00eb4f3 Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Wed, 31 Oct 2018 19:06:35 +0800 Subject: [PATCH 119/356] perf top: Display the LBR stats in callchain entry 'perf report' has supported the displaying of LBR stats (such as cycles, predicted%) in callchain entry. For example: $ perf report --branch-history --stdio --1.01%--intel_idle mwait.h:29 intel_idle cpufeature.h:164 (cycles:5) intel_idle cpufeature.h:164 (predicted:76.4%) intel_idle mwait.h:102 (cycles:41) intel_idle current.h:15 While 'perf top' doesn't support that. For example: $ perf top -a -b --call-graph branch - 13.86% 0.23% [kernel] [k] __x86_indirect_thunk_rax - 13.65% __x86_indirect_thunk_rax + 1.69% do_syscall_64 + 1.68% do_select + 1.41% ktime_get + 0.70% __schedule + 0.62% do_sys_poll 0.58% __x86_indirect_thunk_rax Actually it's very easy to enable this feature in 'perf top'. With this patch, the result is: $ perf top -a -b --call-graph branch $ - 13.58% 0.00% [kernel] [k] __x86_indirect_thunk_rax $ - 13.57% __x86_indirect_thunk_rax (predicted:93.9%) $ + 1.78% do_select (cycles:2) $ + 1.68% perf_pmu_disable.part.99 (cycles:1) $ + 1.45% ___sys_recvmsg (cycles:25) $ + 0.81% unix_stream_sendmsg (cycles:18) $ + 0.80% ktime_get (cycles:400) $ 0.58% pick_next_task_fair (cycles:47) $ + 0.56% i915_request_retire (cycles:2) $ + 0.52% do_sys_poll (cycles:4) Signed-off-by: Jin Yao Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jiri Olsa Cc: Kan Liang Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1540983995-20462-1-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index b2838de13de0..aa0c73e57924 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1429,6 +1429,9 @@ int cmd_top(int argc, const char **argv) } } + if (opts->branch_stack && callchain_param.enabled) + symbol_conf.show_branchflag_count = true; + sort__mode = SORT_MODE__TOP; /* display thread wants entries to be collapsed in a different tree */ perf_hpp_list.need_collapse = 1; From 5ed4419d47f8ba6bbccd8e3203276b3c39a792b7 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Sun, 4 Nov 2018 17:12:35 +0200 Subject: [PATCH 120/356] perf scripts python: exported-sql-viewer.py: Fall back to /usr/local/lib/libxed.so Fall back to /usr/local/lib/libxed.so to cater for distributions that do not have /usr/local/lib in the library path by default. Signed-off-by: Adrian Hunter Cc: Andi Kleen Cc: Jiri Olsa Link: http://lkml.kernel.org/r/20181104151238.15947-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/scripts/python/exported-sql-viewer.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index 24cb0bd56afa..20cc8e7879b9 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -1929,7 +1929,12 @@ class XEDInstruction(): class LibXED(): def __init__(self): - self.libxed = CDLL("libxed.so") + try: + self.libxed = CDLL("libxed.so") + except: + self.libxed = None + if not self.libxed: + self.libxed = CDLL("/usr/local/lib/libxed.so") self.xed_tables_init = self.libxed.xed_tables_init self.xed_tables_init.restype = None From 210cf1f96185f0c6383df8b6030e3d2945e1b41a Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Sun, 4 Nov 2018 17:12:36 +0200 Subject: [PATCH 121/356] perf scripts python: exported-sql-viewer.py: Add Selected branches report Fetching data from the database can be slow. Add a report that provides the ability to select a subset of branches. Signed-off-by: Adrian Hunter Cc: Andi Kleen Cc: Jiri Olsa Link: http://lkml.kernel.org/r/20181104151238.15947-3-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- .../scripts/python/exported-sql-viewer.py | 327 ++++++++++++++++++ 1 file changed, 327 insertions(+) diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index 20cc8e7879b9..a9d2b3170141 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -119,6 +119,14 @@ def dsoname(name): return "[kernel]" return name +def findnth(s, sub, n, offs=0): + pos = s.find(sub) + if pos < 0: + return pos + if n <= 1: + return offs + pos + return findnth(s[pos + 1:], sub, n - 1, offs + pos + 1) + # Percent to one decimal place def PercentToOneDP(n, d): @@ -1464,6 +1472,317 @@ class BranchWindow(QMdiSubWindow): else: self.find_bar.NotFound() +# Dialog data item converted and validated using a SQL table + +class SQLTableDialogDataItem(): + + def __init__(self, glb, label, placeholder_text, table_name, match_column, column_name1, column_name2, parent): + self.glb = glb + self.label = label + self.placeholder_text = placeholder_text + self.table_name = table_name + self.match_column = match_column + self.column_name1 = column_name1 + self.column_name2 = column_name2 + self.parent = parent + + self.value = "" + + self.widget = QLineEdit() + self.widget.editingFinished.connect(self.Validate) + self.widget.textChanged.connect(self.Invalidate) + self.red = False + self.error = "" + self.validated = True + + self.last_id = 0 + self.first_time = 0 + self.last_time = 2 ** 64 + if self.table_name == "": + query = QSqlQuery(self.glb.db) + QueryExec(query, "SELECT id, time FROM samples ORDER BY id DESC LIMIT 1") + if query.next(): + self.last_id = int(query.value(0)) + self.last_time = int(query.value(1)) + QueryExec(query, "SELECT time FROM samples WHERE time != 0 ORDER BY id LIMIT 1") + if query.next(): + self.first_time = int(query.value(0)) + if placeholder_text: + placeholder_text += ", between " + str(self.first_time) + " and " + str(self.last_time) + + if placeholder_text: + self.widget.setPlaceholderText(placeholder_text) + + def ValueToIds(self, value): + ids = [] + query = QSqlQuery(self.glb.db) + stmt = "SELECT id FROM " + self.table_name + " WHERE " + self.match_column + " = '" + value + "'" + ret = query.exec_(stmt) + if ret: + while query.next(): + ids.append(str(query.value(0))) + return ids + + def IdBetween(self, query, lower_id, higher_id, order): + QueryExec(query, "SELECT id FROM samples WHERE id > " + str(lower_id) + " AND id < " + str(higher_id) + " ORDER BY id " + order + " LIMIT 1") + if query.next(): + return True, int(query.value(0)) + else: + return False, 0 + + def BinarySearchTime(self, lower_id, higher_id, target_time, get_floor): + query = QSqlQuery(self.glb.db) + while True: + next_id = int((lower_id + higher_id) / 2) + QueryExec(query, "SELECT time FROM samples WHERE id = " + str(next_id)) + if not query.next(): + ok, dbid = self.IdBetween(query, lower_id, next_id, "DESC") + if not ok: + ok, dbid = self.IdBetween(query, next_id, higher_id, "") + if not ok: + return str(higher_id) + next_id = dbid + QueryExec(query, "SELECT time FROM samples WHERE id = " + str(next_id)) + next_time = int(query.value(0)) + if get_floor: + if target_time > next_time: + lower_id = next_id + else: + higher_id = next_id + if higher_id <= lower_id + 1: + return str(higher_id) + else: + if target_time >= next_time: + lower_id = next_id + else: + higher_id = next_id + if higher_id <= lower_id + 1: + return str(lower_id) + + def ConvertRelativeTime(self, val): + print "val ", val + mult = 1 + suffix = val[-2:] + if suffix == "ms": + mult = 1000000 + elif suffix == "us": + mult = 1000 + elif suffix == "ns": + mult = 1 + else: + return val + val = val[:-2].strip() + if not self.IsNumber(val): + return val + val = int(val) * mult + if val >= 0: + val += self.first_time + else: + val += self.last_time + return str(val) + + def ConvertTimeRange(self, vrange): + print "vrange ", vrange + if vrange[0] == "": + vrange[0] = str(self.first_time) + if vrange[1] == "": + vrange[1] = str(self.last_time) + vrange[0] = self.ConvertRelativeTime(vrange[0]) + vrange[1] = self.ConvertRelativeTime(vrange[1]) + print "vrange2 ", vrange + if not self.IsNumber(vrange[0]) or not self.IsNumber(vrange[1]): + return False + print "ok1" + beg_range = max(int(vrange[0]), self.first_time) + end_range = min(int(vrange[1]), self.last_time) + if beg_range > self.last_time or end_range < self.first_time: + return False + print "ok2" + vrange[0] = self.BinarySearchTime(0, self.last_id, beg_range, True) + vrange[1] = self.BinarySearchTime(1, self.last_id + 1, end_range, False) + print "vrange3 ", vrange + return True + + def AddTimeRange(self, value, ranges): + print "value ", value + n = value.count("-") + if n == 1: + pass + elif n == 2: + if value.split("-")[1].strip() == "": + n = 1 + elif n == 3: + n = 2 + else: + return False + pos = findnth(value, "-", n) + vrange = [value[:pos].strip() ,value[pos+1:].strip()] + if self.ConvertTimeRange(vrange): + ranges.append(vrange) + return True + return False + + def InvalidValue(self, value): + self.value = "" + palette = QPalette() + palette.setColor(QPalette.Text,Qt.red) + self.widget.setPalette(palette) + self.red = True + self.error = self.label + " invalid value '" + value + "'" + self.parent.ShowMessage(self.error) + + def IsNumber(self, value): + try: + x = int(value) + except: + x = 0 + return str(x) == value + + def Invalidate(self): + self.validated = False + + def Validate(self): + input_string = self.widget.text() + self.validated = True + if self.red: + palette = QPalette() + self.widget.setPalette(palette) + self.red = False + if not len(input_string.strip()): + self.error = "" + self.value = "" + return + if self.table_name == "": + ranges = [] + for value in [x.strip() for x in input_string.split(",")]: + if not self.AddTimeRange(value, ranges): + return self.InvalidValue(value) + ranges = [("(" + self.column_name1 + " >= " + r[0] + " AND " + self.column_name1 + " <= " + r[1] + ")") for r in ranges] + self.value = " OR ".join(ranges) + elif self.table_name == "": + singles = [] + ranges = [] + for value in [x.strip() for x in input_string.split(",")]: + if "-" in value: + vrange = value.split("-") + if len(vrange) != 2 or not self.IsNumber(vrange[0]) or not self.IsNumber(vrange[1]): + return self.InvalidValue(value) + ranges.append(vrange) + else: + if not self.IsNumber(value): + return self.InvalidValue(value) + singles.append(value) + ranges = [("(" + self.column_name1 + " >= " + r[0] + " AND " + self.column_name1 + " <= " + r[1] + ")") for r in ranges] + if len(singles): + ranges.append(self.column_name1 + " IN (" + ",".join(singles) + ")") + self.value = " OR ".join(ranges) + elif self.table_name: + all_ids = [] + for value in [x.strip() for x in input_string.split(",")]: + ids = self.ValueToIds(value) + if len(ids): + all_ids.extend(ids) + else: + return self.InvalidValue(value) + self.value = self.column_name1 + " IN (" + ",".join(all_ids) + ")" + if self.column_name2: + self.value = "( " + self.value + " OR " + self.column_name2 + " IN (" + ",".join(all_ids) + ") )" + else: + self.value = input_string.strip() + self.error = "" + self.parent.ClearMessage() + + def IsValid(self): + if not self.validated: + self.Validate() + if len(self.error): + self.parent.ShowMessage(self.error) + return False + return True + +# Selected branch report creation dialog + +class SelectedBranchDialog(QDialog): + + def __init__(self, glb, parent=None): + super(SelectedBranchDialog, self).__init__(parent) + + self.glb = glb + + self.name = "" + self.where_clause = "" + + self.setWindowTitle("Selected Branches") + self.setMinimumWidth(600) + + items = ( + ("Report name:", "Enter a name to appear in the window title bar", "", "", "", ""), + ("Time ranges:", "Enter time ranges", "", "", "samples.id", ""), + ("CPUs:", "Enter CPUs or ranges e.g. 0,5-6", "", "", "cpu", ""), + ("Commands:", "Only branches with these commands will be included", "comms", "comm", "comm_id", ""), + ("PIDs:", "Only branches with these process IDs will be included", "threads", "pid", "thread_id", ""), + ("TIDs:", "Only branches with these thread IDs will be included", "threads", "tid", "thread_id", ""), + ("DSOs:", "Only branches with these DSOs will be included", "dsos", "short_name", "samples.dso_id", "to_dso_id"), + ("Symbols:", "Only branches with these symbols will be included", "symbols", "name", "symbol_id", "to_symbol_id"), + ("Raw SQL clause: ", "Enter a raw SQL WHERE clause", "", "", "", ""), + ) + self.data_items = [SQLTableDialogDataItem(glb, *x, parent=self) for x in items] + + self.grid = QGridLayout() + + for row in xrange(len(self.data_items)): + self.grid.addWidget(QLabel(self.data_items[row].label), row, 0) + self.grid.addWidget(self.data_items[row].widget, row, 1) + + self.status = QLabel() + + self.ok_button = QPushButton("Ok", self) + self.ok_button.setDefault(True) + self.ok_button.released.connect(self.Ok) + self.ok_button.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed) + + self.cancel_button = QPushButton("Cancel", self) + self.cancel_button.released.connect(self.reject) + self.cancel_button.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed) + + self.hbox = QHBoxLayout() + #self.hbox.addStretch() + self.hbox.addWidget(self.status) + self.hbox.addWidget(self.ok_button) + self.hbox.addWidget(self.cancel_button) + + self.vbox = QVBoxLayout() + self.vbox.addLayout(self.grid) + self.vbox.addLayout(self.hbox) + + self.setLayout(self.vbox); + + def Ok(self): + self.name = self.data_items[0].value + if not self.name: + self.ShowMessage("Report name is required") + return + for d in self.data_items: + if not d.IsValid(): + return + for d in self.data_items[1:]: + if len(d.value): + if len(self.where_clause): + self.where_clause += " AND " + self.where_clause += d.value + if len(self.where_clause): + self.where_clause = " AND ( " + self.where_clause + " ) " + else: + self.ShowMessage("No selection") + return + self.accept() + + def ShowMessage(self, msg): + self.status.setText("" + msg) + + def ClearMessage(self): + self.status.setText("") + # Event list def GetEventList(db): @@ -1888,6 +2207,8 @@ class MainWindow(QMainWindow): if event == "branches": label = "All branches" if branches_events == 1 else "All branches " + "(id=" + dbid + ")" reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda x=dbid: self.NewBranchView(x), self)) + label = "Selected branches" if branches_events == 1 else "Selected branches " + "(id=" + dbid + ")" + reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda x=dbid: self.NewSelectedBranchView(x), self)) def TableMenu(self, tables, menu): table_menu = menu.addMenu("&Tables") @@ -1900,6 +2221,12 @@ class MainWindow(QMainWindow): def NewBranchView(self, event_id): BranchWindow(self.glb, event_id, "", "", self) + def NewSelectedBranchView(self, event_id): + dialog = SelectedBranchDialog(self.glb, self) + ret = dialog.exec_() + if ret: + BranchWindow(self.glb, event_id, dialog.name, dialog.where_clause, self) + def NewTableView(self, table_name): TableWindow(self.glb, table_name, self) From 65b24292e8f34df22a16bf7c47823325ac247572 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Sun, 4 Nov 2018 17:12:37 +0200 Subject: [PATCH 122/356] perf scripts python: exported-sql-viewer.py: Add help window Add a window to display help. It is also possible to display the help only, by using the option "--help-only" instead of a database name. Signed-off-by: Adrian Hunter Cc: Andi Kleen Cc: Jiri Olsa Link: http://lkml.kernel.org/r/20181104151238.15947-4-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- .../scripts/python/exported-sql-viewer.py | 155 +++++++++++++++++- 1 file changed, 154 insertions(+), 1 deletion(-) diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index a9d2b3170141..c2fcf6c5237a 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -2084,6 +2084,147 @@ class WindowMenu(): def setActiveSubWindow(self, nr): self.mdi_area.setActiveSubWindow(self.mdi_area.subWindowList()[nr - 1]) +# Help text + +glb_help_text = """ +

Contents

+ +

1. Reports

+

1.1 Context-Sensitive Call Graph

+

1.2 All branches

+

1.3 Selected branches

+

2. Tables

+

1. Reports

+

1.1 Context-Sensitive Call Graph

+The result is a GUI window with a tree representing a context-sensitive +call-graph. Expanding a couple of levels of the tree and adjusting column +widths to suit will display something like: +
+                                         Call Graph: pt_example
+Call Path                          Object      Count   Time(ns)  Time(%)  Branch Count   Branch Count(%)
+v- ls
+    v- 2638:2638
+        v- _start                  ld-2.19.so    1     10074071   100.0         211135            100.0
+          |- unknown               unknown       1        13198     0.1              1              0.0
+          >- _dl_start             ld-2.19.so    1      1400980    13.9          19637              9.3
+          >- _d_linit_internal     ld-2.19.so    1       448152     4.4          11094              5.3
+          v-__libc_start_main@plt  ls            1      8211741    81.5         180397             85.4
+             >- _dl_fixup          ld-2.19.so    1         7607     0.1            108              0.1
+             >- __cxa_atexit       libc-2.19.so  1        11737     0.1             10              0.0
+             >- __libc_csu_init    ls            1        10354     0.1             10              0.0
+             |- _setjmp            libc-2.19.so  1            0     0.0              4              0.0
+             v- main               ls            1      8182043    99.6         180254             99.9
+
+

Points to note:

+
    +
  • The top level is a command name (comm)
    • +
  • The next level is a thread (pid:tid)
    • +
  • Subsequent levels are functions
    • +
  • 'Count' is the number of calls
    • +
  • 'Time' is the elapsed time until the function returns
    • +
  • Percentages are relative to the level above
    • +
  • 'Branch Count' is the total number of branches for that function and all functions that it calls +
+

Find

+Ctrl-F displays a Find bar which finds function names by either an exact match or a pattern match. +The pattern matching symbols are ? for any character and * for zero or more characters. +

1.2 All branches

+The All branches report displays all branches in chronological order. +Not all data is fetched immediately. More records can be fetched using the Fetch bar provided. +

Disassembly

+Open a branch to display disassembly. This only works if: +
    +
  1. The disassembler is available. Currently, only Intel XED is supported - see Intel XED Setup
    2. +
  2. The object code is available. Currently, only the perf build ID cache is searched for object code. +The default directory ~/.debug can be overridden by setting environment variable PERF_BUILDID_DIR. +One exception is kcore where the DSO long name is used (refer dsos_view on the Tables menu), +or alternatively, set environment variable PERF_KCORE to the kcore file name.
    3. +
+

Intel XED Setup

+To use Intel XED, libxed.so must be present. To build and install libxed.so: +
+git clone https://github.com/intelxed/mbuild.git mbuild
+git clone https://github.com/intelxed/xed
+cd xed
+./mfile.py --share
+sudo ./mfile.py --prefix=/usr/local install
+sudo ldconfig
+
+

Find

+Ctrl-F displays a Find bar which finds substrings by either an exact match or a regular expression match. +Refer to Python documentation for the regular expression syntax. +All columns are searched, but only currently fetched rows are searched. +

1.3 Selected branches

+This is the same as the All branches report but with the data reduced +by various selection criteria. A dialog box displays available criteria which are AND'ed together. +

1.3.1 Time ranges

+The time ranges hint text shows the total time range. Relative time ranges can also be entered in +ms, us or ns. Also, negative values are relative to the end of trace. Examples: +
+	81073085947329-81073085958238	From 81073085947329 to 81073085958238
+	100us-200us		From 100us to 200us
+	10ms-			From 10ms to the end
+	-100ns			The first 100ns
+	-10ms-			The last 10ms
+
+N.B. Due to the granularity of timestamps, there could be no branches in any given time range. +

2. Tables

+The Tables menu shows all tables and views in the database. Most tables have an associated view +which displays the information in a more friendly way. Not all data for large tables is fetched +immediately. More records can be fetched using the Fetch bar provided. Columns can be sorted, +but that can be slow for large tables. +

There are also tables of database meta-information. +For SQLite3 databases, the sqlite_master table is included. +For PostgreSQL databases, information_schema.tables/views/columns are included. +

Find

+Ctrl-F displays a Find bar which finds substrings by either an exact match or a regular expression match. +Refer to Python documentation for the regular expression syntax. +All columns are searched, but only currently fetched rows are searched. +""" + +# Help window + +class HelpWindow(QMdiSubWindow): + + def __init__(self, glb, parent=None): + super(HelpWindow, self).__init__(parent) + + self.text = QTextBrowser() + self.text.setHtml(glb_help_text) + self.text.setReadOnly(True) + self.text.setOpenExternalLinks(True) + + self.setWidget(self.text) + + AddSubWindow(glb.mainwindow.mdi_area, self, "Exported SQL Viewer Help") + +# Main window that only displays the help text + +class HelpOnlyWindow(QMainWindow): + + def __init__(self, parent=None): + super(HelpOnlyWindow, self).__init__(parent) + + self.setMinimumSize(200, 100) + self.resize(800, 600) + self.setWindowTitle("Exported SQL Viewer Help") + self.setWindowIcon(self.style().standardIcon(QStyle.SP_MessageBoxInformation)) + + self.text = QTextBrowser() + self.text.setHtml(glb_help_text) + self.text.setReadOnly(True) + self.text.setOpenExternalLinks(True) + + self.setCentralWidget(self.text) + # Font resize def ResizeFont(widget, diff): @@ -2170,6 +2311,9 @@ class MainWindow(QMainWindow): self.window_menu = WindowMenu(self.mdi_area, menu) + help_menu = menu.addMenu("&Help") + help_menu.addAction(CreateAction("&Exported SQL Viewer Help", "Helpful information", self.Help, self, QKeySequence.HelpContents)) + def Find(self): win = self.mdi_area.activeSubWindow() if win: @@ -2230,6 +2374,9 @@ class MainWindow(QMainWindow): def NewTableView(self, table_name): TableWindow(self.glb, table_name, self) + def Help(self): + HelpWindow(self.glb, self) + # XED Disassembler class xed_state_t(Structure): @@ -2429,10 +2576,16 @@ class DBRef(): def Main(): if (len(sys.argv) < 2): - print >> sys.stderr, "Usage is: exported-sql-viewer.py " + print >> sys.stderr, "Usage is: exported-sql-viewer.py { | --help-only}" raise Exception("Too few arguments") dbname = sys.argv[1] + if dbname == "--help-only": + app = QApplication(sys.argv) + mainwindow = HelpOnlyWindow() + mainwindow.show() + err = app.exec_() + sys.exit(err) is_sqlite3 = False try: From 35fa1cee21e34f43db928d022610707d5a234faf Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Sun, 4 Nov 2018 17:12:38 +0200 Subject: [PATCH 123/356] perf scripts python: exported-sql-viewer.py: Fix table find when table re-ordered Table rows can be re-ordered by selecting a column to sort by. After re-ordering, the "find" operation was highlighting the wrong row, fix it. Signed-off-by: Adrian Hunter Cc: Andi Kleen Cc: Jiri Olsa Link: http://lkml.kernel.org/r/20181104151238.15947-5-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/scripts/python/exported-sql-viewer.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index c2fcf6c5237a..f278ce5ebab7 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -1975,7 +1975,7 @@ class TableWindow(QMdiSubWindow, ResizeColumnsToContentsBase): def FindDone(self, row): self.find_bar.Idle() if row >= 0: - self.view.setCurrentIndex(self.model.index(row, 0, QModelIndex())) + self.view.setCurrentIndex(self.model.mapFromSource(self.data_model.index(row, 0, QModelIndex()))) else: self.find_bar.NotFound() @@ -2188,6 +2188,8 @@ For PostgreSQL databases, information_schema.tables/views/columns are included. Ctrl-F displays a Find bar which finds substrings by either an exact match or a regular expression match. Refer to Python documentation for the regular expression syntax. All columns are searched, but only currently fetched rows are searched. +

N.B. Results are found in id order, so if the table is re-ordered, find-next and find-previous +will go to the next/previous result in id order, instead of display order. """ # Help window From 93f8be2799515e01647c5a9b0d17a90a00ebcf82 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 5 Nov 2018 09:35:04 +0200 Subject: [PATCH 124/356] perf intel-pt: Add more event information to debug log More event information is useful for debugging, especially MMAP events. Signed-off-by: Adrian Hunter Link: http://lkml.kernel.org/r/20181105073505.8129-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/intel-pt-decoder/intel-pt-log.c | 5 +++++ tools/perf/util/intel-pt-decoder/intel-pt-log.h | 1 + tools/perf/util/intel-pt.c | 16 +++++++++++++--- 3 files changed, 19 insertions(+), 3 deletions(-) diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.c b/tools/perf/util/intel-pt-decoder/intel-pt-log.c index e02bc7b166a0..5e64da270f97 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-log.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.c @@ -31,6 +31,11 @@ static FILE *f; static char log_name[MAX_LOG_NAME]; bool intel_pt_enable_logging; +void *intel_pt_log_fp(void) +{ + return f; +} + void intel_pt_log_enable(void) { intel_pt_enable_logging = true; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.h b/tools/perf/util/intel-pt-decoder/intel-pt-log.h index 45b64f93f358..cc084937f701 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-log.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.h @@ -22,6 +22,7 @@ struct intel_pt_pkt; +void *intel_pt_log_fp(void); void intel_pt_log_enable(void); void intel_pt_log_disable(void); void intel_pt_log_set_name(const char *name); diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 86cc9a64e982..149ff361ca78 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -206,6 +206,16 @@ static void intel_pt_dump_event(struct intel_pt *pt, unsigned char *buf, intel_pt_dump(pt, buf, len); } +static void intel_pt_log_event(union perf_event *event) +{ + FILE *f = intel_pt_log_fp(); + + if (!intel_pt_enable_logging || !f) + return; + + perf_event__fprintf(event, f); +} + static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *a, struct auxtrace_buffer *b) { @@ -2010,9 +2020,9 @@ static int intel_pt_process_event(struct perf_session *session, event->header.type == PERF_RECORD_SWITCH_CPU_WIDE) err = intel_pt_context_switch(pt, event, sample); - intel_pt_log("event %s (%u): cpu %d time %"PRIu64" tsc %#"PRIx64"\n", - perf_event__name(event->header.type), event->header.type, - sample->cpu, sample->time, timestamp); + intel_pt_log("event %u: cpu %d time %"PRIu64" tsc %#"PRIx64" ", + event->header.type, sample->cpu, sample->time, timestamp); + intel_pt_log_event(event); return err; } From f6c23e3b55cb93f32a724f41af8d38888bc2ab6b Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 5 Nov 2018 09:35:05 +0200 Subject: [PATCH 125/356] perf intel-pt: Add MTC and CYC timestamps to debug log One cause of decoding errors is un-synchronized side-band data. Timestamps are needed to debug such cases. TSC packet timestamps are logged. Log also MTC and CYC timestamps. Signed-off-by: Adrian Hunter Link: http://lkml.kernel.org/r/20181105073505.8129-3-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/intel-pt-decoder/intel-pt-decoder.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 58f6a9ceb590..4503f3ca45ab 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -1474,6 +1474,8 @@ static void intel_pt_calc_mtc_timestamp(struct intel_pt_decoder *decoder) decoder->have_calc_cyc_to_tsc = false; intel_pt_calc_cyc_to_tsc(decoder, true); } + + intel_pt_log_to("Setting timestamp", decoder->timestamp); } static void intel_pt_calc_cbr(struct intel_pt_decoder *decoder) @@ -1514,6 +1516,8 @@ static void intel_pt_calc_cyc_timestamp(struct intel_pt_decoder *decoder) decoder->timestamp = timestamp; decoder->timestamp_insn_cnt = 0; + + intel_pt_log_to("Setting timestamp", decoder->timestamp); } /* Walk PSB+ packets when already in sync. */ From c0fae7e2452b90c31edd2d25eb3baf0c76b400ca Mon Sep 17 00:00:00 2001 From: Aaro Koskinen Date: Sat, 27 Oct 2018 01:46:34 +0300 Subject: [PATCH 126/356] MIPS: OCTEON: fix out of bounds array access on CN68XX The maximum number of interfaces is returned by cvmx_helper_get_number_of_interfaces(), and the value is used to access interface_port_count[]. When CN68XX support was added, we forgot to increase the array size. Fix that. Fixes: 2c8c3f0201333 ("MIPS: Octeon: Support additional interfaces on CN68XX") Signed-off-by: Aaro Koskinen Signed-off-by: Paul Burton Patchwork: https://patchwork.linux-mips.org/patch/20949/ Cc: Ralf Baechle Cc: linux-mips@linux-mips.org Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v4.3+ --- arch/mips/cavium-octeon/executive/cvmx-helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper.c b/arch/mips/cavium-octeon/executive/cvmx-helper.c index 75108ec669eb..6c79e8a16a26 100644 --- a/arch/mips/cavium-octeon/executive/cvmx-helper.c +++ b/arch/mips/cavium-octeon/executive/cvmx-helper.c @@ -67,7 +67,7 @@ void (*cvmx_override_pko_queue_priority) (int pko_port, void (*cvmx_override_ipd_port_setup) (int ipd_port); /* Port count per interface */ -static int interface_port_count[5]; +static int interface_port_count[9]; /** * Return the number of interfaces the chip has. Each interface From d01501f85249848a2497968d46dd46d5c6fe32e6 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Thu, 1 Nov 2018 07:54:24 +0000 Subject: [PATCH 127/356] MIPS: Fix `dma_alloc_coherent' returning a non-coherent allocation Fix a MIPS `dma_alloc_coherent' regression from commit bc3ec75de545 ("dma-mapping: merge direct and noncoherent ops") that causes a cached allocation to be returned on noncoherent cache systems. This is due to an inverted check now used in the MIPS implementation of `arch_dma_alloc' on the result from `dma_direct_alloc_pages' before doing the cached-to-uncached mapping of the allocation address obtained. The mapping has to be done for a non-NULL rather than NULL result, because a NULL result means the allocation has failed. Invert the check for correct operation then. Signed-off-by: Maciej W. Rozycki Signed-off-by: Paul Burton Reviewed-by: Christoph Hellwig Fixes: bc3ec75de545 ("dma-mapping: merge direct and noncoherent ops") Patchwork: https://patchwork.linux-mips.org/patch/20965/ --- arch/mips/mm/dma-noncoherent.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c index e6c9485cadcf..cb38461391cb 100644 --- a/arch/mips/mm/dma-noncoherent.c +++ b/arch/mips/mm/dma-noncoherent.c @@ -50,7 +50,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, void *ret; ret = dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs); - if (!ret && !(attrs & DMA_ATTR_NON_CONSISTENT)) { + if (ret && !(attrs & DMA_ATTR_NON_CONSISTENT)) { dma_cache_wback_inv((unsigned long) ret, size); ret = (void *)UNCAC_ADDR(ret); } From e2c39f36c354a06c6e9d32d4fdf8660b41803d82 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 5 Nov 2018 15:46:51 -0300 Subject: [PATCH 128/356] perf beauty: Use SRCARCH, ARCH=x86_64 must map to "x86" to find the headers Guenter reported that using ARCH=x86_64 to build perf has regressed: $ make -C tools/perf O=/tmp/build/perf ARCH=x86_64 make: Entering directory '/home/acme/git/perf/tools/perf' BUILD: Doing 'make -j4' parallel build HOSTCC /tmp/build/perf/fixdep.o HOSTLD /tmp/build/perf/fixdep-in.o LINK /tmp/build/perf/fixdep Auto-detecting system features: ... dwarf: [ on ] ... bpf: [ on ] GEN /tmp/build/perf/common-cmds.h make[2]: *** No rule to make target '/home/acme/git/perf/tools/arch/x86_64/include/uapi/asm//mman.h', needed by '/tmp/build/perf/trace/beauty/generated/mmap_flags_array.c'. Stop. make[2]: *** Waiting for unfinished jobs.... PERF_VERSION = 4.19.gf6c23e3 make[1]: *** [Makefile.perf:207: sub-make] Error 2 make: *** [Makefile:70: all] Error 2 make: Leaving directory '/home/acme/git/perf/tools/perf' $ This is because we must use $(SRCARCH) where we were using $(ARCH), so that, just like the top level Makefile, we get this done: # Additional ARCH settings for x86 ifeq ($(ARCH),i386) SRCARCH := x86 endif ifeq ($(ARCH),x86_64) SRCARCH := x86 endif Which is done in tools/scripts/Makefile.arch, so switch to use $(SRCARCH). Reported-by: Guenter Roeck Cc: Adrian Hunter Cc: Clark Williams Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Fixes: fbd7458db757 ("perf beauty: Wire up the mmap flags table generator to the Makefile") Link: https://lkml.kernel.org/r/20181105184612.GD7077@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.perf | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 3ccb4f0bf088..d95655489f7e 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -387,7 +387,7 @@ SHELL = $(SHELL_PATH) linux_uapi_dir := $(srctree)/tools/include/uapi/linux asm_generic_uapi_dir := $(srctree)/tools/include/uapi/asm-generic -arch_asm_uapi_dir := $(srctree)/tools/arch/$(ARCH)/include/uapi/asm/ +arch_asm_uapi_dir := $(srctree)/tools/arch/$(SRCARCH)/include/uapi/asm/ beauty_outdir := $(OUTPUT)trace/beauty/generated beauty_ioctl_outdir := $(beauty_outdir)/ioctl From fd5ba6ee3187617287fb9cb187e3d6b3631210a3 Mon Sep 17 00:00:00 2001 From: Aaro Koskinen Date: Fri, 2 Nov 2018 21:10:48 +0200 Subject: [PATCH 129/356] arm64: dts: stratix10: fix multicast filtering On Stratix 10, the EMAC has 256 hash buckets for multicast filtering. This needs to be specified in DTS, otherwise the stmmac driver defaults to 64 buckets and initializes the filter incorrectly. As a result, e.g. valid IPv6 multicast traffic ends up being dropped. Fixes: 78cd6a9d8e15 ("arm64: dts: Add base stratix 10 dtsi") Cc: stable@vger.kernel.org Signed-off-by: Aaro Koskinen Signed-off-by: Dinh Nguyen --- arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi index 8253a1a9e985..fef7351e9f67 100644 --- a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi +++ b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi @@ -139,6 +139,7 @@ clock-names = "stmmaceth"; tx-fifo-depth = <16384>; rx-fifo-depth = <16384>; + snps,multicast-filter-bins = <256>; status = "disabled"; }; @@ -154,6 +155,7 @@ clock-names = "stmmaceth"; tx-fifo-depth = <16384>; rx-fifo-depth = <16384>; + snps,multicast-filter-bins = <256>; status = "disabled"; }; @@ -169,6 +171,7 @@ clock-names = "stmmaceth"; tx-fifo-depth = <16384>; rx-fifo-depth = <16384>; + snps,multicast-filter-bins = <256>; status = "disabled"; }; From 6ac2226229d931153331a93d90655a3de05b9290 Mon Sep 17 00:00:00 2001 From: Gustavo Romero Date: Thu, 1 Nov 2018 20:13:21 -0400 Subject: [PATCH 130/356] perf tools: Fix undefined symbol scnprintf in libperf-jvmti.so Currently jvmti agent can not be used because function scnprintf is not present in the agent libperf-jvmti.so. As a result the JVM when using such agent to record JITed code profiling information will fail on looking up scnprintf: java: symbol lookup error: lib/libperf-jvmti.so: undefined symbol: scnprintf This commit fixes that by reverting to the use of snprintf, that can be looked up, instead of scnprintf, adding a proper check for the returned value in order to print a better error message when the jitdump file pathname is too long. Checking the returned value also helps to comply with some recent gcc versions, like gcc8, which will fail due to truncated writing checks related to the -Werror=format-truncation= flag. Signed-off-by: Gustavo Romero Acked-by: Jiri Olsa LPU-Reference: 1541117601-18937-2-git-send-email-gromero@linux.vnet.ibm.com Link: https://lkml.kernel.org/n/tip-mvpxxxy7wnzaj74cq75muw3f@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/jvmti/jvmti_agent.c | 49 ++++++++++++++++++++++++++-------- 1 file changed, 38 insertions(+), 11 deletions(-) diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c index ac1bcdc17dae..f7eb63cbbc65 100644 --- a/tools/perf/jvmti/jvmti_agent.c +++ b/tools/perf/jvmti/jvmti_agent.c @@ -125,7 +125,7 @@ perf_get_timestamp(void) } static int -debug_cache_init(void) +create_jit_cache_dir(void) { char str[32]; char *base, *p; @@ -144,8 +144,13 @@ debug_cache_init(void) strftime(str, sizeof(str), JIT_LANG"-jit-%Y%m%d", &tm); - snprintf(jit_path, PATH_MAX - 1, "%s/.debug/", base); - + ret = snprintf(jit_path, PATH_MAX, "%s/.debug/", base); + if (ret >= PATH_MAX) { + warnx("jvmti: cannot generate jit cache dir because %s/.debug/" + " is too long, please check the cwd, JITDUMPDIR, and" + " HOME variables", base); + return -1; + } ret = mkdir(jit_path, 0755); if (ret == -1) { if (errno != EEXIST) { @@ -154,20 +159,32 @@ debug_cache_init(void) } } - snprintf(jit_path, PATH_MAX - 1, "%s/.debug/jit", base); + ret = snprintf(jit_path, PATH_MAX, "%s/.debug/jit", base); + if (ret >= PATH_MAX) { + warnx("jvmti: cannot generate jit cache dir because" + " %s/.debug/jit is too long, please check the cwd," + " JITDUMPDIR, and HOME variables", base); + return -1; + } ret = mkdir(jit_path, 0755); if (ret == -1) { if (errno != EEXIST) { - warn("cannot create jit cache dir %s", jit_path); + warn("jvmti: cannot create jit cache dir %s", jit_path); return -1; } } - snprintf(jit_path, PATH_MAX - 1, "%s/.debug/jit/%s.XXXXXXXX", base, str); - + ret = snprintf(jit_path, PATH_MAX, "%s/.debug/jit/%s.XXXXXXXX", base, str); + if (ret >= PATH_MAX) { + warnx("jvmti: cannot generate jit cache dir because" + " %s/.debug/jit/%s.XXXXXXXX is too long, please check" + " the cwd, JITDUMPDIR, and HOME variables", + base, str); + return -1; + } p = mkdtemp(jit_path); if (p != jit_path) { - warn("cannot create jit cache dir %s", jit_path); + warn("jvmti: cannot create jit cache dir %s", jit_path); return -1; } @@ -228,7 +245,7 @@ void *jvmti_open(void) { char dump_path[PATH_MAX]; struct jitheader header; - int fd; + int fd, ret; FILE *fp; init_arch_timestamp(); @@ -245,12 +262,22 @@ void *jvmti_open(void) memset(&header, 0, sizeof(header)); - debug_cache_init(); + /* + * jitdump file dir + */ + if (create_jit_cache_dir() < 0) + return NULL; /* * jitdump file name */ - scnprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid()); + ret = snprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid()); + if (ret >= PATH_MAX) { + warnx("jvmti: cannot generate jitdump file full path because" + " %s/jit-%i.dump is too long, please check the cwd," + " JITDUMPDIR, and HOME variables", jit_path, getpid()); + return NULL; + } fd = open(dump_path, O_CREAT|O_TRUNC|O_RDWR, 0666); if (fd == -1) From aba118389a6fb2ad7958de0f37b5869852bd38cf Mon Sep 17 00:00:00 2001 From: "Dmitry V. Levin" Date: Thu, 1 Nov 2018 14:03:08 +0300 Subject: [PATCH 131/356] uapi: fix linux/kfd_ioctl.h userspace compilation errors Consistently use types provided by via to fix the following linux/kfd_ioctl.h userspace compilation errors: /usr/include/linux/kfd_ioctl.h:250:2: error: unknown type name 'uint32_t' uint32_t reset_type; /usr/include/linux/kfd_ioctl.h:251:2: error: unknown type name 'uint32_t' uint32_t reset_cause; /usr/include/linux/kfd_ioctl.h:252:2: error: unknown type name 'uint32_t' uint32_t memory_lost; /usr/include/linux/kfd_ioctl.h:253:2: error: unknown type name 'uint32_t' uint32_t gpu_id; Fixes: 0c119abad7f0d ("drm/amd: Add kfd ioctl defines for hw_exception event") Cc: # v4.19 Signed-off-by: Dmitry V. Levin Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index f5ff8a76e208..dae897f38e59 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -255,10 +255,10 @@ struct kfd_hsa_memory_exception_data { /* hw exception data */ struct kfd_hsa_hw_exception_data { - uint32_t reset_type; - uint32_t reset_cause; - uint32_t memory_lost; - uint32_t gpu_id; + __u32 reset_type; + __u32 reset_cause; + __u32 memory_lost; + __u32 gpu_id; }; /* Event data */ From 8e7f91719db36440d63de37331367be9700ca0c7 Mon Sep 17 00:00:00 2001 From: "Dmitry V. Levin" Date: Thu, 1 Nov 2018 14:03:28 +0300 Subject: [PATCH 132/356] uapi: fix more linux/kfd_ioctl.h userspace compilation errors Consistently use types provided by via to fix struct kfd_ioctl_get_queue_wave_state_args userspace compilation errors. Fixes: 5df099e8bc83f ("drm/amdkfd: Add wavefront context save state retrieval ioctl") Signed-off-by: Dmitry V. Levin Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index dae897f38e59..b01eb502d49c 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -83,11 +83,11 @@ struct kfd_ioctl_set_cu_mask_args { }; struct kfd_ioctl_get_queue_wave_state_args { - uint64_t ctl_stack_address; /* to KFD */ - uint32_t ctl_stack_used_size; /* from KFD */ - uint32_t save_area_used_size; /* from KFD */ - uint32_t queue_id; /* to KFD */ - uint32_t pad; + __u64 ctl_stack_address; /* to KFD */ + __u32 ctl_stack_used_size; /* from KFD */ + __u32 save_area_used_size; /* from KFD */ + __u32 queue_id; /* to KFD */ + __u32 pad; }; /* For kfd_ioctl_set_memory_policy_args.default_policy and alternate_policy */ From 6915ed86cca6a0b422e8ada05ec7009d2074b88a Mon Sep 17 00:00:00 2001 From: Jeff Barnhill <0xeffeff@gmail.com> Date: Mon, 5 Nov 2018 20:36:45 +0000 Subject: [PATCH 133/356] net/ipv6: Move anycast init/cleanup functions out of CONFIG_PROC_FS Move the anycast.c init and cleanup functions which were inadvertently added inside the CONFIG_PROC_FS definition. Fixes: 2384d02520ff ("net/ipv6: Add anycast addresses to a global hashtable") Signed-off-by: Jeff Barnhill <0xeffeff@gmail.com> Signed-off-by: David S. Miller --- net/ipv6/anycast.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 7698637cf827..94999058e110 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -590,6 +590,7 @@ void ac6_proc_exit(struct net *net) { remove_proc_entry("anycast6", net->proc_net); } +#endif /* Init / cleanup code */ @@ -611,4 +612,3 @@ void ipv6_anycast_cleanup(void) WARN_ON(!hlist_empty(&inet6_acaddr_lst[i])); spin_unlock(&acaddr_hash_lock); } -#endif From 91d7b67000c6e9bd605624079fee5a084238ad92 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Tue, 16 Oct 2018 09:13:46 +0200 Subject: [PATCH 134/356] mtd: spi-nor: cadence-quadspi: Return error code in cqspi_direct_read_execute() We return 0 unconditionally in 'cqspi_direct_read_execute()'. However, 'ret' is set to some error codes in several error handling paths. Return 'ret' instead to propagate the error code. Fixes: ffa639e069fb ("mtd: spi-nor: cadence-quadspi: Add DMA support for direct mode reads") Cc: Signed-off-by: Christophe JAILLET Signed-off-by: Boris Brezillon --- drivers/mtd/spi-nor/cadence-quadspi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c index e24db817154e..d846428ef038 100644 --- a/drivers/mtd/spi-nor/cadence-quadspi.c +++ b/drivers/mtd/spi-nor/cadence-quadspi.c @@ -996,7 +996,7 @@ static int cqspi_direct_read_execute(struct spi_nor *nor, u_char *buf, err_unmap: dma_unmap_single(nor->dev, dma_dst, len, DMA_FROM_DEVICE); - return 0; + return ret; } static ssize_t cqspi_read(struct spi_nor *nor, loff_t from, From 90c31cb9a8115a1183daed9a714eea4be0687931 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 19 Oct 2018 11:02:22 +0200 Subject: [PATCH 135/356] mtd: spi-nor: Reset nor->addr_width when SFDP parsing failed Commit 5390a8df769e ("mtd: spi-nor: add support to non-uniform SFDP SPI NOR flash memories") removed the 'nor->addr_width = 0;' statement when spi_nor_parse_sfdp() returns an error, thus leaving ->addr_width in an undefined state which can cause trouble when spi_nor_scan() checks its value. Reported-by: Cyrille Pitchen Fixes: 5390a8df769e ("mtd: spi-nor: add support to non-uniform SFDP SPI NOR flash memories") Signed-off-by: Boris Brezillon Reviewed-by: Tudor Ambarus --- drivers/mtd/spi-nor/spi-nor.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 9407ca5f9443..3e54e31889c7 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -3250,12 +3250,14 @@ static int spi_nor_init_params(struct spi_nor *nor, memcpy(&sfdp_params, params, sizeof(sfdp_params)); memcpy(&prev_map, &nor->erase_map, sizeof(prev_map)); - if (spi_nor_parse_sfdp(nor, &sfdp_params)) + if (spi_nor_parse_sfdp(nor, &sfdp_params)) { + nor->addr_width = 0; /* restore previous erase map */ memcpy(&nor->erase_map, &prev_map, sizeof(nor->erase_map)); - else + } else { memcpy(params, &sfdp_params, sizeof(*params)); + } } return 0; From 5e1acb4afacc6229946c3d2b7ffc422b53fb2448 Mon Sep 17 00:00:00 2001 From: Alexey Kodanev Date: Fri, 2 Nov 2018 19:11:04 +0300 Subject: [PATCH 136/356] rtnetlink: restore handling of dumpit return value in rtnl_dump_all() For non-zero return from dumpit() we should break the loop in rtnl_dump_all() and return the result. Otherwise, e.g., we could get the memory leak in inet6_dump_fib() [1]. The pointer to the allocated struct fib6_walker there (saved in cb->args) can be lost, reset on the next iteration. Fix it by partially restoring the previous behavior before commit c63586dc9b3e ("net: rtnl_dump_all needs to propagate error from dumpit function"). The returned error from dumpit() is still passed further. [1]: unreferenced object 0xffff88001322a200 (size 96): comm "sshd", pid 1484, jiffies 4296032768 (age 1432.542s) hex dump (first 32 bytes): 00 01 00 00 00 00 ad de 00 02 00 00 00 00 ad de ................ 18 09 41 36 00 88 ff ff 18 09 41 36 00 88 ff ff ..A6......A6.... backtrace: [<0000000095846b39>] kmem_cache_alloc_trace+0x151/0x220 [<000000007d12709f>] inet6_dump_fib+0x68d/0x940 [<000000002775a316>] rtnl_dump_all+0x1d9/0x2d0 [<00000000d7cd302b>] netlink_dump+0x945/0x11a0 [<000000002f43485f>] __netlink_dump_start+0x55d/0x800 [<00000000f76bbeec>] rtnetlink_rcv_msg+0x4fa/0xa00 [<000000009b5761f3>] netlink_rcv_skb+0x29c/0x420 [<0000000087a1dae1>] rtnetlink_rcv+0x15/0x20 [<00000000691b703b>] netlink_unicast+0x4e3/0x6c0 [<00000000b5be0204>] netlink_sendmsg+0x7f2/0xba0 [<0000000096d2aa60>] sock_sendmsg+0xba/0xf0 [<000000008c1b786f>] __sys_sendto+0x1e4/0x330 [<0000000019587b3f>] __x64_sys_sendto+0xe1/0x1a0 [<00000000071f4d56>] do_syscall_64+0x9f/0x300 [<000000002737577f>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [<0000000057587684>] 0xffffffffffffffff Fixes: c63586dc9b3e ("net: rtnl_dump_all needs to propagate error from dumpit function") Signed-off-by: Alexey Kodanev Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index e01274bd5e3e..33d9227a8b80 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3367,7 +3367,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) cb->seq = 0; } ret = dumpit(skb, cb); - if (ret < 0) + if (ret) break; } cb->family = idx; From e22d0bfa09a56e427a1a950ccb85621c86b343a4 Mon Sep 17 00:00:00 2001 From: Alexey Kodanev Date: Fri, 2 Nov 2018 19:11:05 +0300 Subject: [PATCH 137/356] ipv6: properly check return value in inet6_dump_all() Make sure we call fib6_dump_end() if it happens that skb->len is zero. rtnl_dump_all() can reset cb->args on the next loop iteration there. Fixes: 08e814c9e8eb ("net/ipv6: Bail early if user only wants cloned entries") Fixes: ae677bbb4441 ("net: Don't return invalid table id error when dumping all families") Signed-off-by: Alexey Kodanev Signed-off-by: David S. Miller --- net/ipv6/ip6_fib.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 1b8bc008b53b..ae3786132c23 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -591,7 +591,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) /* fib entries are never clones */ if (arg.filter.flags & RTM_F_CLONED) - return skb->len; + goto out; w = (void *)cb->args[2]; if (!w) { @@ -621,7 +621,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) tb = fib6_get_table(net, arg.filter.table_id); if (!tb) { if (arg.filter.dump_all_families) - return skb->len; + goto out; NL_SET_ERR_MSG_MOD(cb->extack, "FIB table does not exist"); return -ENOENT; From d016b4a3562b745fd9fa387a47d8de62ccd7e241 Mon Sep 17 00:00:00 2001 From: "Matwey V. Kornilov" Date: Fri, 2 Nov 2018 21:19:36 +0300 Subject: [PATCH 138/356] net: core: netpoll: Enable netconsole IPv6 link local address There is no reason to discard using source link local address when remote netconsole IPv6 address is set to be link local one. The patch allows administrators to use IPv6 netconsole without explicitly configuring source address: netconsole=@/,@fe80::5054:ff:fe2f:6012/ Signed-off-by: Matwey V. Kornilov Signed-off-by: David S. Miller --- net/core/netpoll.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 5da9552b186b..2b9fdbc43205 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -717,7 +717,8 @@ int netpoll_setup(struct netpoll *np) read_lock_bh(&idev->lock); list_for_each_entry(ifp, &idev->addr_list, if_list) { - if (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL) + if (!!(ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL) != + !!(ipv6_addr_type(&np->remote_ip.in6) & IPV6_ADDR_LINKLOCAL)) continue; np->local_ip.in6 = ifp->addr; err = 0; From c34c1287778b080ed692c0a46a8e345206cc29e6 Mon Sep 17 00:00:00 2001 From: Andrei Vagin Date: Sun, 4 Nov 2018 22:37:15 -0800 Subject: [PATCH 139/356] sock_diag: fix autoloading of the raw_diag module IPPROTO_RAW isn't registred as an inet protocol, so inet_protos[protocol] is always NULL for it. Cc: Cyrill Gorcunov Cc: Xin Long Fixes: bf2ae2e4bf93 ("sock_diag: request _diag module only when the family or proto has been registered") Signed-off-by: Andrei Vagin Reviewed-by: Cyrill Gorcunov Signed-off-by: David S. Miller --- net/core/sock.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/core/sock.c b/net/core/sock.c index 6fcc4bc07d19..080a880a1761 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3279,6 +3279,7 @@ int sock_load_diag_module(int family, int protocol) #ifdef CONFIG_INET if (family == AF_INET && + protocol != IPPROTO_RAW && !rcu_access_pointer(inet_protos[protocol])) return -ENOENT; #endif From 97adaddaa6db7a8af81b9b11e30cbe3628cd6700 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 5 Nov 2018 22:31:41 +0900 Subject: [PATCH 140/356] net: bpfilter: fix iptables failure if bpfilter_umh is disabled When iptables command is executed, ip_{set/get}sockopt() try to upload bpfilter.ko if bpfilter is enabled. if it couldn't find bpfilter.ko, command is failed. bpfilter.ko is generated if CONFIG_BPFILTER_UMH is enabled. ip_{set/get}sockopt() only checks CONFIG_BPFILTER. So that if CONFIG_BPFILTER is enabled and CONFIG_BPFILTER_UMH is disabled, iptables command is always failed. test config: CONFIG_BPFILTER=y # CONFIG_BPFILTER_UMH is not set test command: %iptables -L iptables: No chain/target/match by that name. Fixes: d2ba09c17a06 ("net: add skeleton of bpfilter kernel module") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- net/ipv4/ip_sockglue.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 26c36cccabdc..fffcc130900e 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -1246,7 +1246,7 @@ int ip_setsockopt(struct sock *sk, int level, return -ENOPROTOOPT; err = do_ip_setsockopt(sk, level, optname, optval, optlen); -#ifdef CONFIG_BPFILTER +#if IS_ENABLED(CONFIG_BPFILTER_UMH) if (optname >= BPFILTER_IPT_SO_SET_REPLACE && optname < BPFILTER_IPT_SET_MAX) err = bpfilter_ip_set_sockopt(sk, optname, optval, optlen); @@ -1559,7 +1559,7 @@ int ip_getsockopt(struct sock *sk, int level, int err; err = do_ip_getsockopt(sk, level, optname, optval, optlen, 0); -#ifdef CONFIG_BPFILTER +#if IS_ENABLED(CONFIG_BPFILTER_UMH) if (optname >= BPFILTER_IPT_SO_GET_INFO && optname < BPFILTER_IPT_GET_MAX) err = bpfilter_ip_get_sockopt(sk, optname, optval, optlen); @@ -1596,7 +1596,7 @@ int compat_ip_getsockopt(struct sock *sk, int level, int optname, err = do_ip_getsockopt(sk, level, optname, optval, optlen, MSG_CMSG_COMPAT); -#ifdef CONFIG_BPFILTER +#if IS_ENABLED(CONFIG_BPFILTER_UMH) if (optname >= BPFILTER_IPT_SO_GET_INFO && optname < BPFILTER_IPT_GET_MAX) err = bpfilter_ip_get_sockopt(sk, optname, optval, optlen); From 7131193157414ac3167d7b2f2feb4c42b415d6c5 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Mon, 5 Nov 2018 18:52:21 +0100 Subject: [PATCH 141/356] net: alx: make alx_drv_name static alx_drv_name is not used outside main.c, so there's no reason for it to have external linkage. Signed-off-by: Rasmus Villemoes Signed-off-by: David S. Miller --- drivers/net/ethernet/atheros/alx/alx.h | 1 - drivers/net/ethernet/atheros/alx/main.c | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/atheros/alx/alx.h b/drivers/net/ethernet/atheros/alx/alx.h index 78c5de467426..9d0e74f6b089 100644 --- a/drivers/net/ethernet/atheros/alx/alx.h +++ b/drivers/net/ethernet/atheros/alx/alx.h @@ -140,6 +140,5 @@ struct alx_priv { }; extern const struct ethtool_ops alx_ethtool_ops; -extern const char alx_drv_name[]; #endif diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index 7968c644ad86..c131cfc1b79d 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -49,7 +49,7 @@ #include "hw.h" #include "reg.h" -const char alx_drv_name[] = "alx"; +static const char alx_drv_name[] = "alx"; static void alx_free_txbuf(struct alx_tx_queue *txq, int entry) { From d9cccfa7c4d1d9ef967ec9308df7304a18609b30 Mon Sep 17 00:00:00 2001 From: Liam Merwick Date: Fri, 2 Nov 2018 14:04:23 +0000 Subject: [PATCH 142/356] xen/grant-table: Fix incorrect gnttab_dma_free_pages() pr_debug message If a call to xenmem_reservation_increase() in gnttab_dma_free_pages() fails it triggers a message "Failed to decrease reservation..." which should be "Failed to increase reservation..." Fixes: 9bdc7304f536 ('xen/grant-table: Allow allocating buffers suitable for DMA') Reported-by: Ross Philipson Signed-off-by: Liam Merwick Reviewed-by: Mark Kanda Reviewed-by: Juergen Gross Signed-off-by: Juergen Gross --- drivers/xen/grant-table.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 84575baceebc..97341fa75458 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -914,7 +914,7 @@ int gnttab_dma_free_pages(struct gnttab_dma_alloc_args *args) ret = xenmem_reservation_increase(args->nr_pages, args->frames); if (ret != args->nr_pages) { - pr_debug("Failed to decrease reservation for DMA buffer\n"); + pr_debug("Failed to increase reservation for DMA buffer\n"); ret = -EFAULT; } else { ret = 0; From acc9d62b68728ada7356e348f3c68f20a5cbd2a1 Mon Sep 17 00:00:00 2001 From: Mason Yang Date: Thu, 25 Oct 2018 14:44:31 +0800 Subject: [PATCH 143/356] mtd: rawnand: Flag 1.8V AC chips with a broken GET_FEATURES(TIMINGS) Make sure we flag all 1.8V broken chips as not supporting this feature. Signed-off-by: Mason Yang Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/nand_macronix.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/mtd/nand/raw/nand_macronix.c b/drivers/mtd/nand/raw/nand_macronix.c index 358dcc957bb2..47d8cda547cf 100644 --- a/drivers/mtd/nand/raw/nand_macronix.c +++ b/drivers/mtd/nand/raw/nand_macronix.c @@ -33,6 +33,13 @@ static void macronix_nand_fix_broken_get_timings(struct nand_chip *chip) "MX30LF4G18AC", "MX30LF4G28AC", "MX60LF8G18AC", + "MX30UF1G18AC", + "MX30UF1G16AC", + "MX30UF2G18AC", + "MX30UF2G16AC", + "MX30UF4G18AC", + "MX30UF4G16AC", + "MX30UF4G28AC", }; if (!chip->parameters.supports_set_get_features) From 647ad49ca672b80a3fbf8396bd453ef68ba4916c Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Mon, 22 Oct 2018 22:10:59 +0200 Subject: [PATCH 144/356] staging: Remove the mt29f_spinand driver A new SPI NAND subsystem has been added in drivers/mtd/nand/spi/ and Micron's MT29F devices are now supported in drivers/mtd/nand/spi/micron.c. Remove the old driver. Signed-off-by: Boris Brezillon Acked-by: Greg Kroah-Hartman Signed-off-by: Miquel Raynal --- drivers/staging/Kconfig | 2 - drivers/staging/Makefile | 1 - drivers/staging/mt29f_spinand/Kconfig | 16 - drivers/staging/mt29f_spinand/Makefile | 1 - drivers/staging/mt29f_spinand/TODO | 13 - drivers/staging/mt29f_spinand/mt29f_spinand.c | 980 ------------------ drivers/staging/mt29f_spinand/mt29f_spinand.h | 106 -- 7 files changed, 1119 deletions(-) delete mode 100644 drivers/staging/mt29f_spinand/Kconfig delete mode 100644 drivers/staging/mt29f_spinand/Makefile delete mode 100644 drivers/staging/mt29f_spinand/TODO delete mode 100644 drivers/staging/mt29f_spinand/mt29f_spinand.c delete mode 100644 drivers/staging/mt29f_spinand/mt29f_spinand.h diff --git a/drivers/staging/Kconfig b/drivers/staging/Kconfig index 7c015536360d..e4f608815c05 100644 --- a/drivers/staging/Kconfig +++ b/drivers/staging/Kconfig @@ -78,8 +78,6 @@ source "drivers/staging/goldfish/Kconfig" source "drivers/staging/netlogic/Kconfig" -source "drivers/staging/mt29f_spinand/Kconfig" - source "drivers/staging/gs_fpgaboot/Kconfig" source "drivers/staging/unisys/Kconfig" diff --git a/drivers/staging/Makefile b/drivers/staging/Makefile index a79b3fe20cf0..5868631e8f1b 100644 --- a/drivers/staging/Makefile +++ b/drivers/staging/Makefile @@ -29,7 +29,6 @@ obj-$(CONFIG_STAGING_BOARD) += board/ obj-$(CONFIG_LTE_GDM724X) += gdm724x/ obj-$(CONFIG_FIREWIRE_SERIAL) += fwserial/ obj-$(CONFIG_GOLDFISH) += goldfish/ -obj-$(CONFIG_MTD_SPINAND_MT29F) += mt29f_spinand/ obj-$(CONFIG_GS_FPGABOOT) += gs_fpgaboot/ obj-$(CONFIG_UNISYSSPAR) += unisys/ obj-$(CONFIG_COMMON_CLK_XLNX_CLKWZRD) += clocking-wizard/ diff --git a/drivers/staging/mt29f_spinand/Kconfig b/drivers/staging/mt29f_spinand/Kconfig deleted file mode 100644 index f3f9cb3b5c35..000000000000 --- a/drivers/staging/mt29f_spinand/Kconfig +++ /dev/null @@ -1,16 +0,0 @@ -config MTD_SPINAND_MT29F - tristate "SPINAND Device Support for Micron" - depends on MTD_NAND && SPI - help - This enables support for accessing Micron SPI NAND flash - devices. - If you have Micron SPI NAND chip say yes. - - If unsure, say no here. - -config MTD_SPINAND_ONDIEECC - bool "Use SPINAND internal ECC" - depends on MTD_SPINAND_MT29F - help - Internal ECC. - Enables Hardware ECC support for Micron SPI NAND. diff --git a/drivers/staging/mt29f_spinand/Makefile b/drivers/staging/mt29f_spinand/Makefile deleted file mode 100644 index e47af0f7fda9..000000000000 --- a/drivers/staging/mt29f_spinand/Makefile +++ /dev/null @@ -1 +0,0 @@ -obj-$(CONFIG_MTD_SPINAND_MT29F) += mt29f_spinand.o diff --git a/drivers/staging/mt29f_spinand/TODO b/drivers/staging/mt29f_spinand/TODO deleted file mode 100644 index a2209b72d371..000000000000 --- a/drivers/staging/mt29f_spinand/TODO +++ /dev/null @@ -1,13 +0,0 @@ -TODO: - - Tested on XLP platform, needs to be tested on other platforms. - - Checkpatch.pl cleanups - - Sparce fixes. - - Clean up coding style to meet kernel standard. - -Please send patches -To: -Kamlakant Patel -Cc: -Greg Kroah-Hartman -Mona Anonuevo -linux-mtd@lists.infradead.org diff --git a/drivers/staging/mt29f_spinand/mt29f_spinand.c b/drivers/staging/mt29f_spinand/mt29f_spinand.c deleted file mode 100644 index def8a1f57d1c..000000000000 --- a/drivers/staging/mt29f_spinand/mt29f_spinand.c +++ /dev/null @@ -1,980 +0,0 @@ -/* - * Copyright (c) 2003-2013 Broadcom Corporation - * - * Copyright (c) 2009-2010 Micron Technology, Inc. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * 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 -#include -#include -#include -#include -#include - -#include "mt29f_spinand.h" - -#define BUFSIZE (10 * 64 * 2048) -#define CACHE_BUF 2112 -/* - * OOB area specification layout: Total 32 available free bytes. - */ - -static inline struct spinand_state *mtd_to_state(struct mtd_info *mtd) -{ - struct nand_chip *chip = mtd_to_nand(mtd); - struct spinand_info *info = nand_get_controller_data(chip); - struct spinand_state *state = info->priv; - - return state; -} - -#ifdef CONFIG_MTD_SPINAND_ONDIEECC -static int enable_hw_ecc; -static int enable_read_hw_ecc; - -static int spinand_ooblayout_64_ecc(struct mtd_info *mtd, int section, - struct mtd_oob_region *oobregion) -{ - if (section > 3) - return -ERANGE; - - oobregion->offset = (section * 16) + 1; - oobregion->length = 6; - - return 0; -} - -static int spinand_ooblayout_64_free(struct mtd_info *mtd, int section, - struct mtd_oob_region *oobregion) -{ - if (section > 3) - return -ERANGE; - - oobregion->offset = (section * 16) + 8; - oobregion->length = 8; - - return 0; -} - -static const struct mtd_ooblayout_ops spinand_oob_64_ops = { - .ecc = spinand_ooblayout_64_ecc, - .free = spinand_ooblayout_64_free, -}; -#endif - -/** - * spinand_cmd - process a command to send to the SPI Nand - * Description: - * Set up the command buffer to send to the SPI controller. - * The command buffer has to initialized to 0. - */ - -static int spinand_cmd(struct spi_device *spi, struct spinand_cmd *cmd) -{ - struct spi_message message; - struct spi_transfer x[4]; - u8 dummy = 0xff; - - spi_message_init(&message); - memset(x, 0, sizeof(x)); - - x[0].len = 1; - x[0].tx_buf = &cmd->cmd; - spi_message_add_tail(&x[0], &message); - - if (cmd->n_addr) { - x[1].len = cmd->n_addr; - x[1].tx_buf = cmd->addr; - spi_message_add_tail(&x[1], &message); - } - - if (cmd->n_dummy) { - x[2].len = cmd->n_dummy; - x[2].tx_buf = &dummy; - spi_message_add_tail(&x[2], &message); - } - - if (cmd->n_tx) { - x[3].len = cmd->n_tx; - x[3].tx_buf = cmd->tx_buf; - spi_message_add_tail(&x[3], &message); - } - - if (cmd->n_rx) { - x[3].len = cmd->n_rx; - x[3].rx_buf = cmd->rx_buf; - spi_message_add_tail(&x[3], &message); - } - - return spi_sync(spi, &message); -} - -/** - * spinand_read_id - Read SPI Nand ID - * Description: - * read two ID bytes from the SPI Nand device - */ -static int spinand_read_id(struct spi_device *spi_nand, u8 *id) -{ - int retval; - u8 nand_id[3]; - struct spinand_cmd cmd = {0}; - - cmd.cmd = CMD_READ_ID; - cmd.n_rx = 3; - cmd.rx_buf = &nand_id[0]; - - retval = spinand_cmd(spi_nand, &cmd); - if (retval < 0) { - dev_err(&spi_nand->dev, "error %d reading id\n", retval); - return retval; - } - id[0] = nand_id[1]; - id[1] = nand_id[2]; - return retval; -} - -/** - * spinand_read_status - send command 0xf to the SPI Nand status register - * Description: - * After read, write, or erase, the Nand device is expected to set the - * busy status. - * This function is to allow reading the status of the command: read, - * write, and erase. - * Once the status turns to be ready, the other status bits also are - * valid status bits. - */ -static int spinand_read_status(struct spi_device *spi_nand, u8 *status) -{ - struct spinand_cmd cmd = {0}; - int ret; - - cmd.cmd = CMD_READ_REG; - cmd.n_addr = 1; - cmd.addr[0] = REG_STATUS; - cmd.n_rx = 1; - cmd.rx_buf = status; - - ret = spinand_cmd(spi_nand, &cmd); - if (ret < 0) - dev_err(&spi_nand->dev, "err: %d read status register\n", ret); - - return ret; -} - -#define MAX_WAIT_JIFFIES (40 * HZ) -static int wait_till_ready(struct spi_device *spi_nand) -{ - unsigned long deadline; - int retval; - u8 stat = 0; - - deadline = jiffies + MAX_WAIT_JIFFIES; - do { - retval = spinand_read_status(spi_nand, &stat); - if (retval < 0) - return -1; - if (!(stat & 0x1)) - break; - - cond_resched(); - } while (!time_after_eq(jiffies, deadline)); - - if ((stat & 0x1) == 0) - return 0; - - return -1; -} - -/** - * spinand_get_otp - send command 0xf to read the SPI Nand OTP register - * Description: - * There is one bit( bit 0x10 ) to set or to clear the internal ECC. - * Enable chip internal ECC, set the bit to 1 - * Disable chip internal ECC, clear the bit to 0 - */ -static int spinand_get_otp(struct spi_device *spi_nand, u8 *otp) -{ - struct spinand_cmd cmd = {0}; - int retval; - - cmd.cmd = CMD_READ_REG; - cmd.n_addr = 1; - cmd.addr[0] = REG_OTP; - cmd.n_rx = 1; - cmd.rx_buf = otp; - - retval = spinand_cmd(spi_nand, &cmd); - if (retval < 0) - dev_err(&spi_nand->dev, "error %d get otp\n", retval); - return retval; -} - -/** - * spinand_set_otp - send command 0x1f to write the SPI Nand OTP register - * Description: - * There is one bit( bit 0x10 ) to set or to clear the internal ECC. - * Enable chip internal ECC, set the bit to 1 - * Disable chip internal ECC, clear the bit to 0 - */ -static int spinand_set_otp(struct spi_device *spi_nand, u8 *otp) -{ - int retval; - struct spinand_cmd cmd = {0}; - - cmd.cmd = CMD_WRITE_REG; - cmd.n_addr = 1; - cmd.addr[0] = REG_OTP; - cmd.n_tx = 1; - cmd.tx_buf = otp; - - retval = spinand_cmd(spi_nand, &cmd); - if (retval < 0) - dev_err(&spi_nand->dev, "error %d set otp\n", retval); - - return retval; -} - -#ifdef CONFIG_MTD_SPINAND_ONDIEECC -/** - * spinand_enable_ecc - send command 0x1f to write the SPI Nand OTP register - * Description: - * There is one bit( bit 0x10 ) to set or to clear the internal ECC. - * Enable chip internal ECC, set the bit to 1 - * Disable chip internal ECC, clear the bit to 0 - */ -static int spinand_enable_ecc(struct spi_device *spi_nand) -{ - int retval; - u8 otp = 0; - - retval = spinand_get_otp(spi_nand, &otp); - if (retval < 0) - return retval; - - if ((otp & OTP_ECC_MASK) == OTP_ECC_MASK) - return 0; - otp |= OTP_ECC_MASK; - retval = spinand_set_otp(spi_nand, &otp); - if (retval < 0) - return retval; - return spinand_get_otp(spi_nand, &otp); -} -#endif - -static int spinand_disable_ecc(struct spi_device *spi_nand) -{ - int retval; - u8 otp = 0; - - retval = spinand_get_otp(spi_nand, &otp); - if (retval < 0) - return retval; - - if ((otp & OTP_ECC_MASK) == OTP_ECC_MASK) { - otp &= ~OTP_ECC_MASK; - retval = spinand_set_otp(spi_nand, &otp); - if (retval < 0) - return retval; - return spinand_get_otp(spi_nand, &otp); - } - return 0; -} - -/** - * spinand_write_enable - send command 0x06 to enable write or erase the - * Nand cells - * Description: - * Before write and erase the Nand cells, the write enable has to be set. - * After the write or erase, the write enable bit is automatically - * cleared (status register bit 2) - * Set the bit 2 of the status register has the same effect - */ -static int spinand_write_enable(struct spi_device *spi_nand) -{ - struct spinand_cmd cmd = {0}; - - cmd.cmd = CMD_WR_ENABLE; - return spinand_cmd(spi_nand, &cmd); -} - -static int spinand_read_page_to_cache(struct spi_device *spi_nand, u16 page_id) -{ - struct spinand_cmd cmd = {0}; - u16 row; - - row = page_id; - cmd.cmd = CMD_READ; - cmd.n_addr = 3; - cmd.addr[0] = (u8)((row & 0xff0000) >> 16); - cmd.addr[1] = (u8)((row & 0xff00) >> 8); - cmd.addr[2] = (u8)(row & 0x00ff); - - return spinand_cmd(spi_nand, &cmd); -} - -/** - * spinand_read_from_cache - send command 0x03 to read out the data from the - * cache register (2112 bytes max) - * Description: - * The read can specify 1 to 2112 bytes of data read at the corresponding - * locations. - * No tRd delay. - */ -static int spinand_read_from_cache(struct spi_device *spi_nand, u16 page_id, - u16 byte_id, u16 len, u8 *rbuf) -{ - struct spinand_cmd cmd = {0}; - u16 column; - - column = byte_id; - cmd.cmd = CMD_READ_RDM; - cmd.n_addr = 3; - cmd.addr[0] = (u8)((column & 0xff00) >> 8); - cmd.addr[0] |= (u8)(((page_id >> 6) & 0x1) << 4); - cmd.addr[1] = (u8)(column & 0x00ff); - cmd.addr[2] = (u8)(0xff); - cmd.n_dummy = 0; - cmd.n_rx = len; - cmd.rx_buf = rbuf; - - return spinand_cmd(spi_nand, &cmd); -} - -/** - * spinand_read_page - read a page - * @page_id: the physical page number - * @offset: the location from 0 to 2111 - * @len: number of bytes to read - * @rbuf: read buffer to hold @len bytes - * - * Description: - * The read includes two commands to the Nand - 0x13 and 0x03 commands - * Poll to read status to wait for tRD time. - */ -static int spinand_read_page(struct spi_device *spi_nand, u16 page_id, - u16 offset, u16 len, u8 *rbuf) -{ - int ret; - u8 status = 0; - -#ifdef CONFIG_MTD_SPINAND_ONDIEECC - if (enable_read_hw_ecc) { - if (spinand_enable_ecc(spi_nand) < 0) - dev_err(&spi_nand->dev, "enable HW ECC failed!"); - } -#endif - ret = spinand_read_page_to_cache(spi_nand, page_id); - if (ret < 0) - return ret; - - if (wait_till_ready(spi_nand)) - dev_err(&spi_nand->dev, "WAIT timedout!!!\n"); - - while (1) { - ret = spinand_read_status(spi_nand, &status); - if (ret < 0) { - dev_err(&spi_nand->dev, - "err %d read status register\n", ret); - return ret; - } - - if ((status & STATUS_OIP_MASK) == STATUS_READY) { - if ((status & STATUS_ECC_MASK) == STATUS_ECC_ERROR) { - dev_err(&spi_nand->dev, "ecc error, page=%d\n", - page_id); - return 0; - } - break; - } - } - - ret = spinand_read_from_cache(spi_nand, page_id, offset, len, rbuf); - if (ret < 0) { - dev_err(&spi_nand->dev, "read from cache failed!!\n"); - return ret; - } - -#ifdef CONFIG_MTD_SPINAND_ONDIEECC - if (enable_read_hw_ecc) { - ret = spinand_disable_ecc(spi_nand); - if (ret < 0) { - dev_err(&spi_nand->dev, "disable ecc failed!!\n"); - return ret; - } - enable_read_hw_ecc = 0; - } -#endif - return ret; -} - -/** - * spinand_program_data_to_cache - write a page to cache - * @byte_id: the location to write to the cache - * @len: number of bytes to write - * @wbuf: write buffer holding @len bytes - * - * Description: - * The write command used here is 0x84--indicating that the cache is - * not cleared first. - * Since it is writing the data to cache, there is no tPROG time. - */ -static int spinand_program_data_to_cache(struct spi_device *spi_nand, - u16 page_id, u16 byte_id, - u16 len, u8 *wbuf) -{ - struct spinand_cmd cmd = {0}; - u16 column; - - column = byte_id; - cmd.cmd = CMD_PROG_PAGE_CLRCACHE; - cmd.n_addr = 2; - cmd.addr[0] = (u8)((column & 0xff00) >> 8); - cmd.addr[0] |= (u8)(((page_id >> 6) & 0x1) << 4); - cmd.addr[1] = (u8)(column & 0x00ff); - cmd.n_tx = len; - cmd.tx_buf = wbuf; - - return spinand_cmd(spi_nand, &cmd); -} - -/** - * spinand_program_execute - write a page from cache to the Nand array - * @page_id: the physical page location to write the page. - * - * Description: - * The write command used here is 0x10--indicating the cache is writing to - * the Nand array. - * Need to wait for tPROG time to finish the transaction. - */ -static int spinand_program_execute(struct spi_device *spi_nand, u16 page_id) -{ - struct spinand_cmd cmd = {0}; - u16 row; - - row = page_id; - cmd.cmd = CMD_PROG_PAGE_EXC; - cmd.n_addr = 3; - cmd.addr[0] = (u8)((row & 0xff0000) >> 16); - cmd.addr[1] = (u8)((row & 0xff00) >> 8); - cmd.addr[2] = (u8)(row & 0x00ff); - - return spinand_cmd(spi_nand, &cmd); -} - -/** - * spinand_program_page - write a page - * @page_id: the physical page location to write the page. - * @offset: the location from the cache starting from 0 to 2111 - * @len: the number of bytes to write - * @buf: the buffer holding @len bytes - * - * Description: - * The commands used here are 0x06, 0x84, and 0x10--indicating that - * the write enable is first sent, the write cache command, and the - * write execute command. - * Poll to wait for the tPROG time to finish the transaction. - */ -static int spinand_program_page(struct spi_device *spi_nand, - u16 page_id, u16 offset, u16 len, u8 *buf) -{ - int retval; - u8 status = 0; - u8 *wbuf; -#ifdef CONFIG_MTD_SPINAND_ONDIEECC - unsigned int i, j; - - wbuf = devm_kzalloc(&spi_nand->dev, CACHE_BUF, GFP_KERNEL); - if (!wbuf) - return -ENOMEM; - - enable_read_hw_ecc = 1; - retval = spinand_read_page(spi_nand, page_id, 0, CACHE_BUF, wbuf); - if (retval < 0) { - dev_err(&spi_nand->dev, "ecc error on read page!!!\n"); - return retval; - } - - for (i = offset, j = 0; i < len; i++, j++) - wbuf[i] &= buf[j]; - - if (enable_hw_ecc) { - retval = spinand_enable_ecc(spi_nand); - if (retval < 0) { - dev_err(&spi_nand->dev, "enable ecc failed!!\n"); - return retval; - } - } -#else - wbuf = buf; -#endif - retval = spinand_write_enable(spi_nand); - if (retval < 0) { - dev_err(&spi_nand->dev, "write enable failed!!\n"); - return retval; - } - if (wait_till_ready(spi_nand)) - dev_err(&spi_nand->dev, "wait timedout!!!\n"); - - retval = spinand_program_data_to_cache(spi_nand, page_id, - offset, len, wbuf); - if (retval < 0) - return retval; - retval = spinand_program_execute(spi_nand, page_id); - if (retval < 0) - return retval; - while (1) { - retval = spinand_read_status(spi_nand, &status); - if (retval < 0) { - dev_err(&spi_nand->dev, - "error %d reading status register\n", retval); - return retval; - } - - if ((status & STATUS_OIP_MASK) == STATUS_READY) { - if ((status & STATUS_P_FAIL_MASK) == STATUS_P_FAIL) { - dev_err(&spi_nand->dev, - "program error, page %d\n", page_id); - return -1; - } - break; - } - } -#ifdef CONFIG_MTD_SPINAND_ONDIEECC - if (enable_hw_ecc) { - retval = spinand_disable_ecc(spi_nand); - if (retval < 0) { - dev_err(&spi_nand->dev, "disable ecc failed!!\n"); - return retval; - } - enable_hw_ecc = 0; - } -#endif - - return 0; -} - -/** - * spinand_erase_block_erase - erase a page - * @block_id: the physical block location to erase. - * - * Description: - * The command used here is 0xd8--indicating an erase command to erase - * one block--64 pages - * Need to wait for tERS. - */ -static int spinand_erase_block_erase(struct spi_device *spi_nand, u16 block_id) -{ - struct spinand_cmd cmd = {0}; - u16 row; - - row = block_id; - cmd.cmd = CMD_ERASE_BLK; - cmd.n_addr = 3; - cmd.addr[0] = (u8)((row & 0xff0000) >> 16); - cmd.addr[1] = (u8)((row & 0xff00) >> 8); - cmd.addr[2] = (u8)(row & 0x00ff); - - return spinand_cmd(spi_nand, &cmd); -} - -/** - * spinand_erase_block - erase a page - * @block_id: the physical block location to erase. - * - * Description: - * The commands used here are 0x06 and 0xd8--indicating an erase - * command to erase one block--64 pages - * It will first to enable the write enable bit (0x06 command), - * and then send the 0xd8 erase command - * Poll to wait for the tERS time to complete the tranaction. - */ -static int spinand_erase_block(struct spi_device *spi_nand, u16 block_id) -{ - int retval; - u8 status = 0; - - retval = spinand_write_enable(spi_nand); - if (wait_till_ready(spi_nand)) - dev_err(&spi_nand->dev, "wait timedout!!!\n"); - - retval = spinand_erase_block_erase(spi_nand, block_id); - while (1) { - retval = spinand_read_status(spi_nand, &status); - if (retval < 0) { - dev_err(&spi_nand->dev, - "error %d reading status register\n", retval); - return retval; - } - - if ((status & STATUS_OIP_MASK) == STATUS_READY) { - if ((status & STATUS_E_FAIL_MASK) == STATUS_E_FAIL) { - dev_err(&spi_nand->dev, - "erase error, block %d\n", block_id); - return -1; - } - break; - } - } - return 0; -} - -#ifdef CONFIG_MTD_SPINAND_ONDIEECC -static int spinand_write_page_hwecc(struct nand_chip *chip, - const u8 *buf, int oob_required, - int page) -{ - const u8 *p = buf; - int eccsize = chip->ecc.size; - int eccsteps = chip->ecc.steps; - - enable_hw_ecc = 1; - return nand_prog_page_op(chip, page, 0, p, eccsize * eccsteps); -} - -static int spinand_read_page_hwecc(struct nand_chip *chip, u8 *buf, - int oob_required, int page) -{ - int retval; - u8 status; - u8 *p = buf; - int eccsize = chip->ecc.size; - int eccsteps = chip->ecc.steps; - struct mtd_info *mtd = nand_to_mtd(chip); - struct spinand_info *info = nand_get_controller_data(chip); - - enable_read_hw_ecc = 1; - - nand_read_page_op(chip, page, 0, p, eccsize * eccsteps); - if (oob_required) - chip->legacy.read_buf(chip, chip->oob_poi, mtd->oobsize); - - while (1) { - retval = spinand_read_status(info->spi, &status); - if (retval < 0) { - dev_err(&mtd->dev, - "error %d reading status register\n", retval); - return retval; - } - - if ((status & STATUS_OIP_MASK) == STATUS_READY) { - if ((status & STATUS_ECC_MASK) == STATUS_ECC_ERROR) { - pr_info("spinand: ECC error\n"); - mtd->ecc_stats.failed++; - } else if ((status & STATUS_ECC_MASK) == - STATUS_ECC_1BIT_CORRECTED) - mtd->ecc_stats.corrected++; - break; - } - } - return 0; -} -#endif - -static void spinand_select_chip(struct nand_chip *chip, int dev) -{ -} - -static u8 spinand_read_byte(struct nand_chip *chip) -{ - struct spinand_state *state = mtd_to_state(nand_to_mtd(chip)); - u8 data; - - data = state->buf[state->buf_ptr]; - state->buf_ptr++; - return data; -} - -static int spinand_wait(struct nand_chip *chip) -{ - struct mtd_info *mtd = nand_to_mtd(chip); - struct spinand_info *info = nand_get_controller_data(chip); - - unsigned long timeo = jiffies; - int retval, state = chip->state; - u8 status; - - if (state == FL_ERASING) - timeo += (HZ * 400) / 1000; - else - timeo += (HZ * 20) / 1000; - - while (time_before(jiffies, timeo)) { - retval = spinand_read_status(info->spi, &status); - if (retval < 0) { - dev_err(&mtd->dev, - "error %d reading status register\n", retval); - return retval; - } - - if ((status & STATUS_OIP_MASK) == STATUS_READY) - return 0; - - cond_resched(); - } - return 0; -} - -static void spinand_write_buf(struct nand_chip *chip, const u8 *buf, int len) -{ - struct spinand_state *state = mtd_to_state(nand_to_mtd(chip)); - - memcpy(state->buf + state->buf_ptr, buf, len); - state->buf_ptr += len; -} - -static void spinand_read_buf(struct nand_chip *chip, u8 *buf, int len) -{ - struct spinand_state *state = mtd_to_state(nand_to_mtd(chip)); - - memcpy(buf, state->buf + state->buf_ptr, len); - state->buf_ptr += len; -} - -/* - * spinand_reset- send RESET command "0xff" to the Nand device. - */ -static void spinand_reset(struct spi_device *spi_nand) -{ - struct spinand_cmd cmd = {0}; - - cmd.cmd = CMD_RESET; - - if (spinand_cmd(spi_nand, &cmd) < 0) - pr_info("spinand reset failed!\n"); - - /* elapse 1ms before issuing any other command */ - usleep_range(1000, 2000); - - if (wait_till_ready(spi_nand)) - dev_err(&spi_nand->dev, "wait timedout!\n"); -} - -static void spinand_cmdfunc(struct nand_chip *chip, unsigned int command, - int column, int page) -{ - struct mtd_info *mtd = nand_to_mtd(chip); - struct spinand_info *info = nand_get_controller_data(chip); - struct spinand_state *state = info->priv; - - switch (command) { - /* - * READ0 - read in first 0x800 bytes - */ - case NAND_CMD_READ1: - case NAND_CMD_READ0: - state->buf_ptr = 0; - spinand_read_page(info->spi, page, 0x0, 0x840, state->buf); - break; - /* READOOB reads only the OOB because no ECC is performed. */ - case NAND_CMD_READOOB: - state->buf_ptr = 0; - spinand_read_page(info->spi, page, 0x800, 0x40, state->buf); - break; - case NAND_CMD_RNDOUT: - state->buf_ptr = column; - break; - case NAND_CMD_READID: - state->buf_ptr = 0; - spinand_read_id(info->spi, state->buf); - break; - case NAND_CMD_PARAM: - state->buf_ptr = 0; - break; - /* ERASE1 stores the block and page address */ - case NAND_CMD_ERASE1: - spinand_erase_block(info->spi, page); - break; - /* ERASE2 uses the block and page address from ERASE1 */ - case NAND_CMD_ERASE2: - break; - /* SEQIN sets up the addr buffer and all registers except the length */ - case NAND_CMD_SEQIN: - state->col = column; - state->row = page; - state->buf_ptr = 0; - break; - /* PAGEPROG reuses all of the setup from SEQIN and adds the length */ - case NAND_CMD_PAGEPROG: - spinand_program_page(info->spi, state->row, state->col, - state->buf_ptr, state->buf); - break; - case NAND_CMD_STATUS: - spinand_get_otp(info->spi, state->buf); - if (!(state->buf[0] & 0x80)) - state->buf[0] = 0x80; - state->buf_ptr = 0; - break; - /* RESET command */ - case NAND_CMD_RESET: - if (wait_till_ready(info->spi)) - dev_err(&info->spi->dev, "WAIT timedout!!!\n"); - /* a minimum of 250us must elapse before issuing RESET cmd*/ - usleep_range(250, 1000); - spinand_reset(info->spi); - break; - default: - dev_err(&mtd->dev, "Unknown CMD: 0x%x\n", command); - } -} - -/** - * spinand_lock_block - send write register 0x1f command to the Nand device - * - * Description: - * After power up, all the Nand blocks are locked. This function allows - * one to unlock the blocks, and so it can be written or erased. - */ -static int spinand_lock_block(struct spi_device *spi_nand, u8 lock) -{ - struct spinand_cmd cmd = {0}; - int ret; - u8 otp = 0; - - ret = spinand_get_otp(spi_nand, &otp); - - cmd.cmd = CMD_WRITE_REG; - cmd.n_addr = 1; - cmd.addr[0] = REG_BLOCK_LOCK; - cmd.n_tx = 1; - cmd.tx_buf = &lock; - - ret = spinand_cmd(spi_nand, &cmd); - if (ret < 0) - dev_err(&spi_nand->dev, "error %d lock block\n", ret); - - return ret; -} - -/** - * spinand_probe - [spinand Interface] - * @spi_nand: registered device driver. - * - * Description: - * Set up the device driver parameters to make the device available. - */ -static int spinand_probe(struct spi_device *spi_nand) -{ - struct mtd_info *mtd; - struct nand_chip *chip; - struct spinand_info *info; - struct spinand_state *state; - - info = devm_kzalloc(&spi_nand->dev, sizeof(struct spinand_info), - GFP_KERNEL); - if (!info) - return -ENOMEM; - - info->spi = spi_nand; - - spinand_lock_block(spi_nand, BL_ALL_UNLOCKED); - - state = devm_kzalloc(&spi_nand->dev, sizeof(struct spinand_state), - GFP_KERNEL); - if (!state) - return -ENOMEM; - - info->priv = state; - state->buf_ptr = 0; - state->buf = devm_kzalloc(&spi_nand->dev, BUFSIZE, GFP_KERNEL); - if (!state->buf) - return -ENOMEM; - - chip = devm_kzalloc(&spi_nand->dev, sizeof(struct nand_chip), - GFP_KERNEL); - if (!chip) - return -ENOMEM; - -#ifdef CONFIG_MTD_SPINAND_ONDIEECC - chip->ecc.mode = NAND_ECC_HW; - chip->ecc.size = 0x200; - chip->ecc.bytes = 0x6; - chip->ecc.steps = 0x4; - - chip->ecc.strength = 1; - chip->ecc.total = chip->ecc.steps * chip->ecc.bytes; - chip->ecc.read_page = spinand_read_page_hwecc; - chip->ecc.write_page = spinand_write_page_hwecc; -#else - chip->ecc.mode = NAND_ECC_SOFT; - chip->ecc.algo = NAND_ECC_HAMMING; - if (spinand_disable_ecc(spi_nand) < 0) - dev_info(&spi_nand->dev, "%s: disable ecc failed!\n", - __func__); -#endif - - nand_set_flash_node(chip, spi_nand->dev.of_node); - nand_set_controller_data(chip, info); - chip->legacy.read_buf = spinand_read_buf; - chip->legacy.write_buf = spinand_write_buf; - chip->legacy.read_byte = spinand_read_byte; - chip->legacy.cmdfunc = spinand_cmdfunc; - chip->legacy.waitfunc = spinand_wait; - chip->options |= NAND_CACHEPRG; - chip->select_chip = spinand_select_chip; - chip->legacy.set_features = nand_get_set_features_notsupp; - chip->legacy.get_features = nand_get_set_features_notsupp; - - mtd = nand_to_mtd(chip); - - dev_set_drvdata(&spi_nand->dev, mtd); - - mtd->dev.parent = &spi_nand->dev; - mtd->oobsize = 64; -#ifdef CONFIG_MTD_SPINAND_ONDIEECC - mtd_set_ooblayout(mtd, &spinand_oob_64_ops); -#endif - - if (nand_scan(chip, 1)) - return -ENXIO; - - return mtd_device_register(mtd, NULL, 0); -} - -/** - * spinand_remove - remove the device driver - * @spi: the spi device. - * - * Description: - * Remove the device driver parameters and free up allocated memories. - */ -static int spinand_remove(struct spi_device *spi) -{ - mtd_device_unregister(dev_get_drvdata(&spi->dev)); - - return 0; -} - -static const struct of_device_id spinand_dt[] = { - { .compatible = "spinand,mt29f", }, - {} -}; -MODULE_DEVICE_TABLE(of, spinand_dt); - -/* - * Device name structure description - */ -static struct spi_driver spinand_driver = { - .driver = { - .name = "mt29f", - .of_match_table = spinand_dt, - }, - .probe = spinand_probe, - .remove = spinand_remove, -}; - -module_spi_driver(spinand_driver); - -MODULE_DESCRIPTION("SPI NAND driver for Micron"); -MODULE_AUTHOR("Henry Pan , Kamlakant Patel "); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/staging/mt29f_spinand/mt29f_spinand.h b/drivers/staging/mt29f_spinand/mt29f_spinand.h deleted file mode 100644 index 457dc7ffdaf1..000000000000 --- a/drivers/staging/mt29f_spinand/mt29f_spinand.h +++ /dev/null @@ -1,106 +0,0 @@ -/*- - * Copyright 2013 Broadcom Corporation - * - * Copyright (c) 2009-2010 Micron Technology, Inc. - * - * 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. - * - * Henry Pan - * - * based on nand.h - */ -#ifndef __LINUX_MTD_SPI_NAND_H -#define __LINUX_MTD_SPI_NAND_H - -#include -#include -#include - -/* cmd */ -#define CMD_READ 0x13 -#define CMD_READ_RDM 0x03 -#define CMD_PROG_PAGE_CLRCACHE 0x02 -#define CMD_PROG_PAGE 0x84 -#define CMD_PROG_PAGE_EXC 0x10 -#define CMD_ERASE_BLK 0xd8 -#define CMD_WR_ENABLE 0x06 -#define CMD_WR_DISABLE 0x04 -#define CMD_READ_ID 0x9f -#define CMD_RESET 0xff -#define CMD_READ_REG 0x0f -#define CMD_WRITE_REG 0x1f - -/* feature/ status reg */ -#define REG_BLOCK_LOCK 0xa0 -#define REG_OTP 0xb0 -#define REG_STATUS 0xc0/* timing */ - -/* status */ -#define STATUS_OIP_MASK 0x01 -#define STATUS_READY 0 -#define STATUS_BUSY BIT(0) - -#define STATUS_E_FAIL_MASK 0x04 -#define STATUS_E_FAIL BIT(2) - -#define STATUS_P_FAIL_MASK 0x08 -#define STATUS_P_FAIL BIT(3) - -#define STATUS_ECC_MASK 0x30 -#define STATUS_ECC_1BIT_CORRECTED BIT(4) -#define STATUS_ECC_ERROR BIT(5) -#define STATUS_ECC_RESERVED (BIT(5) | BIT(4)) - -/*ECC enable defines*/ -#define OTP_ECC_MASK 0x10 -#define OTP_ECC_OFF 0 -#define OTP_ECC_ON 1 - -#define ECC_DISABLED -#define ECC_IN_NAND -#define ECC_SOFT - -/* block lock */ -#define BL_ALL_LOCKED 0x38 -#define BL_1_2_LOCKED 0x30 -#define BL_1_4_LOCKED 0x28 -#define BL_1_8_LOCKED 0x20 -#define BL_1_16_LOCKED 0x18 -#define BL_1_32_LOCKED 0x10 -#define BL_1_64_LOCKED 0x08 -#define BL_ALL_UNLOCKED 0 - -struct spinand_info { - struct spi_device *spi; - void *priv; -}; - -struct spinand_state { - u32 col; - u32 row; - int buf_ptr; - u8 *buf; -}; - -struct spinand_cmd { - u8 cmd; - u32 n_addr; /* Number of address */ - u8 addr[3]; /* Reg Offset */ - u32 n_dummy; /* Dummy use */ - u32 n_tx; /* Number of tx bytes */ - u8 *tx_buf; /* Tx buf */ - u32 n_rx; /* Number of rx bytes */ - u8 *rx_buf; /* Rx buf */ -}; - -int spinand_mtd(struct mtd_info *mtd); -void spinand_mtd_release(struct mtd_info *mtd); - -#endif /* __LINUX_MTD_SPI_NAND_H */ From 6cc4a0863c9709c512280c64e698d68443ac8053 Mon Sep 17 00:00:00 2001 From: Manjunath Patil Date: Tue, 30 Oct 2018 09:49:21 -0700 Subject: [PATCH 145/356] xen-blkfront: fix kernel panic with negotiate_mq error path MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit info->nr_rings isn't adjusted in case of ENOMEM error from negotiate_mq(). This leads to kernel panic in error path. Typical call stack involving panic - #8 page_fault at ffffffff8175936f [exception RIP: blkif_free_ring+33] RIP: ffffffffa0149491 RSP: ffff8804f7673c08 RFLAGS: 00010292 ... #9 blkif_free at ffffffffa0149aaa [xen_blkfront] #10 talk_to_blkback at ffffffffa014c8cd [xen_blkfront] #11 blkback_changed at ffffffffa014ea8b [xen_blkfront] #12 xenbus_otherend_changed at ffffffff81424670 #13 backend_changed at ffffffff81426dc3 #14 xenwatch_thread at ffffffff81422f29 #15 kthread at ffffffff810abe6a #16 ret_from_fork at ffffffff81754078 Cc: stable@vger.kernel.org Fixes: 7ed8ce1c5fc7 ("xen-blkfront: move negotiate_mq to cover all cases of new VBDs") Signed-off-by: Manjunath Patil Acked-by: Roger Pau Monné Signed-off-by: Juergen Gross --- drivers/block/xen-blkfront.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 9eea83ae01c6..9ac3999a55b7 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -1919,6 +1919,7 @@ static int negotiate_mq(struct blkfront_info *info) GFP_KERNEL); if (!info->rinfo) { xenbus_dev_fatal(info->xbdev, -ENOMEM, "allocating ring_info structure"); + info->nr_rings = 0; return -ENOMEM; } From ba26cd7d58dcc50e25c8f02b5376c05046b181dc Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Mon, 5 Nov 2018 08:58:35 +0100 Subject: [PATCH 146/356] mtd: sa1100: avoid VLA in sa1100_setup_mtd Enabling -Wvla found another variable-length array with randconfig testing: drivers/mtd/maps/sa1100-flash.c: In function 'sa1100_setup_mtd': drivers/mtd/maps/sa1100-flash.c:224:10: error: ISO C90 forbids variable length array 'cdev' [-Werror=vla] Dynamically allocate the cdev array passed to mtd_concat_create() instead of using a VLA. Reported-by: Arnd Bergmann Signed-off-by: Boris Brezillon Cc: Kees Cook Cc: Olof Johansson --- drivers/mtd/maps/sa1100-flash.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/maps/sa1100-flash.c b/drivers/mtd/maps/sa1100-flash.c index 784c6e1a0391..fd5fe12d7461 100644 --- a/drivers/mtd/maps/sa1100-flash.c +++ b/drivers/mtd/maps/sa1100-flash.c @@ -221,7 +221,14 @@ static struct sa_info *sa1100_setup_mtd(struct platform_device *pdev, info->mtd = info->subdev[0].mtd; ret = 0; } else if (info->num_subdev > 1) { - struct mtd_info *cdev[nr]; + struct mtd_info **cdev; + + cdev = kmalloc_array(nr, sizeof(*cdev), GFP_KERNEL); + if (!cdev) { + ret = -ENOMEM; + goto err; + } + /* * We detected multiple devices. Concatenate them together. */ @@ -230,6 +237,7 @@ static struct sa_info *sa1100_setup_mtd(struct platform_device *pdev, info->mtd = mtd_concat_create(cdev, info->num_subdev, plat->name); + kfree(cdev); if (info->mtd == NULL) { ret = -ENXIO; goto err; From 6282e916f774e37845c65d1eae9f8c649004f033 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 5 Nov 2018 14:54:56 +0100 Subject: [PATCH 147/356] ARM: 8809/1: proc-v7: fix Thumb annotation of cpu_v7_hvc_switch_mm Due to what appears to be a copy/paste error, the opening ENTRY() of cpu_v7_hvc_switch_mm() lacks a matching ENDPROC(), and instead, the one for cpu_v7_smc_switch_mm() is duplicated. Given that it is ENDPROC() that emits the Thumb annotation, the cpu_v7_hvc_switch_mm() routine will be called in ARM mode on a Thumb2 kernel, resulting in the following splat: Internal error: Oops - undefined instruction: 0 [#1] SMP THUMB2 Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.18.0-rc1-00030-g4d28ad89189d-dirty #488 Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015 PC is at cpu_v7_hvc_switch_mm+0x12/0x18 LR is at flush_old_exec+0x31b/0x570 pc : [] lr : [] psr: 00000013 sp : ee899e50 ip : 00000000 fp : 00000001 r10: eda28f34 r9 : eda31800 r8 : c12470e0 r7 : eda1fc00 r6 : eda53000 r5 : 00000000 r4 : ee88c000 r3 : c0316eec r2 : 00000001 r1 : eda53000 r0 : 6da6c000 Flags: nzcv IRQs on FIQs on Mode SVC_32 ISA ARM Segment none Note the 'ISA ARM' in the last line. Fix this by using the correct name in ENDPROC(). Cc: Fixes: 10115105cb3a ("ARM: spectre-v2: add firmware based hardening") Reviewed-by: Dave Martin Acked-by: Marc Zyngier Signed-off-by: Ard Biesheuvel Signed-off-by: Russell King --- arch/arm/mm/proc-v7.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index b78d59a1cc05..fccd4d99f505 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -112,7 +112,7 @@ ENTRY(cpu_v7_hvc_switch_mm) hvc #0 ldmfd sp!, {r0 - r3} b cpu_v7_switch_mm -ENDPROC(cpu_v7_smc_switch_mm) +ENDPROC(cpu_v7_hvc_switch_mm) #endif ENTRY(cpu_v7_iciallu_switch_mm) mov r3, #0 From 8e88c29b351ed4e09dd63f825f1c8260b0cb0ab3 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sun, 23 Sep 2018 17:04:20 +0200 Subject: [PATCH 148/356] perf tools: Do not zero sample_id_all for group members Andi reported following malfunction: # perf record -e '{ref-cycles,cycles}:S' -a sleep 1 # perf script non matching sample_id_all That's because we disable sample_id_all bit for non-sampling group members. We can't do that, because it needs to be the same over the whole event list. This patch keeps it untouched again. Reported-by: Andi Kleen Tested-by: Andi Kleen Signed-off-by: Jiri Olsa Cc: Alexander Shishkin Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20180923150420.27327-1-jolsa@kernel.org Fixes: e9add8bac6c6 ("perf evsel: Disable write_backward for leader sampling group events") Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/attr/test-record-group-sampling | 1 - tools/perf/util/evsel.c | 1 - 2 files changed, 2 deletions(-) diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling index 8a33ca4f9e1f..f0729c454f16 100644 --- a/tools/perf/tests/attr/test-record-group-sampling +++ b/tools/perf/tests/attr/test-record-group-sampling @@ -37,4 +37,3 @@ sample_freq=0 sample_period=0 freq=0 write_backward=0 -sample_id_all=0 diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 6d187059a373..d37bb1566cd9 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -956,7 +956,6 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, attr->sample_freq = 0; attr->sample_period = 0; attr->write_backward = 0; - attr->sample_id_all = 0; } if (opts->no_samples) From 3fc202e81db70bf60beb9296eefd4e48d6304607 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 2 Nov 2018 16:14:32 +0100 Subject: [PATCH 149/356] HID: asus: fix build warning wiht CONFIG_ASUS_WMI disabled asus_wmi_evaluate_method() is an empty dummy function when CONFIG_ASUS_WMI is disabled, or not reachable from a built-in device driver. This leads to a theoretical evaluation of an uninitialized variable that the compiler complains about, failing to check that the hardcoded return value makes this an unreachable code path: In file included from include/linux/printk.h:336, from include/linux/kernel.h:14, from include/linux/list.h:9, from include/linux/dmi.h:5, from drivers/hid/hid-asus.c:29: drivers/hid/hid-asus.c: In function 'asus_input_configured': include/linux/dynamic_debug.h:135:3: error: 'value' may be used uninitialized in this function [-Werror=maybe-uninitialized] __dynamic_dev_dbg(&descriptor, dev, fmt, \ ^~~~~~~~~~~~~~~~~ drivers/hid/hid-asus.c:359:6: note: 'value' was declared here u32 value; ^~~~~ With an extra IS_ENABLED() check, the warning goes away. Fixes: 3b692c55e58d ("HID: asus: only support backlight when it's not driven by WMI") Signed-off-by: Arnd Bergmann Acked-by: Geert Uytterhoeven Signed-off-by: Jiri Kosina --- drivers/hid/hid-asus.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index dc6d6477e961..a1fa2fc8c9b5 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -359,6 +359,9 @@ static bool asus_kbd_wmi_led_control_present(struct hid_device *hdev) u32 value; int ret; + if (!IS_ENABLED(CONFIG_ASUS_WMI)) + return false; + ret = asus_wmi_evaluate_method(ASUS_WMI_METHODID_DSTS2, ASUS_WMI_DEVID_KBD_BACKLIGHT, 0, &value); hid_dbg(hdev, "WMI backlight check: rc %d value %x", ret, value); From aa9b760cec2385ad408bb2e346c7f6dc1be69a79 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sun, 4 Nov 2018 11:32:47 +0100 Subject: [PATCH 150/356] HID: fix up .raw_event() documentation The documentation for the .raw_event() callback says that if the driver return 1, there will be no further processing of the event, but this is not true, the actual code in hid-core.c looks like this: if (hdrv && hdrv->raw_event && hid_match_report(hid, report)) { ret = hdrv->raw_event(hid, report, data, size); if (ret < 0) goto unlock; } ret = hid_report_raw_event(hid, type, data, size, interrupt); The only return value that has any effect on the processing is a negative error. Correct this as it seems to confuse people: I found bogus code in the Razer out-of-tree driver attempting to return 1 here. Signed-off-by: Linus Walleij Signed-off-by: Jiri Kosina --- include/linux/hid.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/hid.h b/include/linux/hid.h index 2827b87590d8..387c70df6f29 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -722,8 +722,8 @@ struct hid_usage_id { * input will not be passed to raw_event unless hid_device_io_start is * called. * - * raw_event and event should return 0 on no action performed, 1 when no - * further processing should be done and negative on error + * raw_event and event should return negative on error, any other value will + * pass the event on to .event() typically return 0 for success. * * input_mapping shall return a negative value to completely ignore this usage * (e.g. doubled or invalid usage), zero to continue with parsing of this From 8bd66d147c88bd441178c7b4c774ae5a185f19b8 Mon Sep 17 00:00:00 2001 From: "ndesaulniers@google.com" Date: Wed, 31 Oct 2018 12:39:01 -0700 Subject: [PATCH 151/356] include/linux/compiler*.h: define asm_volatile_goto asm_volatile_goto should also be defined for other compilers that support asm goto. Fixes commit 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive"). Signed-off-by: Nick Desaulniers Signed-off-by: Miguel Ojeda --- include/linux/compiler_types.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 3439d7d0249a..4a3f9c09c92d 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -130,6 +130,10 @@ struct ftrace_likely_data { # define randomized_struct_fields_end #endif +#ifndef asm_volatile_goto +#define asm_volatile_goto(x...) asm goto(x) +#endif + /* Are two types/vars the same type (ignoring qualifiers)? */ #define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) From 18354b422ce4ce1124277dfe8f4f094bae0102ad Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Tue, 23 Oct 2018 21:21:02 +0300 Subject: [PATCH 152/356] drm/i915: Don't apply the 16Gb DIMM wm latency w/a to BXT/GLK MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The 16Gb DIMM w/a is not applicable to BXT or GLK. Limit it to the appropriate platforms. This was especially harsh on GLK since we don't even try to read the DIMM information on that platforms, hence valid_dimm was always false and thus we always tried to apply the w/a. Furthermore the w/a pushed the level 0 latency above the level 1 latency, which doesn't really make sense. v2: Do the check when populating is_16gb_dimm (Mahesh) Cc: Mahesh Kumar Cc: Maarten Lankhorst Fixes: 86b592876cb6 ("drm/i915: Implement 16GB dimm wa for latency level-0") Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20181023182102.31549-1-ville.syrjala@linux.intel.com Reviewed-by: Rodrigo Vivi Reviewed-by: Mahesh Kumar (cherry picked from commit 5d6f36b27d2764f3dc940606ee6b7ec5c669af3e) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/i915_drv.c | 15 ++++++++------- drivers/gpu/drm/i915/i915_drv.h | 1 - drivers/gpu/drm/i915/intel_pm.c | 3 +-- 3 files changed, 9 insertions(+), 10 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 44e2c0f5ec50..ffdbbac4400e 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -1175,8 +1175,6 @@ skl_dram_get_channels_info(struct drm_i915_private *dev_priv) return -EINVAL; } - dram_info->valid_dimm = true; - /* * If any of the channel is single rank channel, worst case output * will be same as if single rank memory, so consider single rank @@ -1193,8 +1191,7 @@ skl_dram_get_channels_info(struct drm_i915_private *dev_priv) return -EINVAL; } - if (ch0.is_16gb_dimm || ch1.is_16gb_dimm) - dram_info->is_16gb_dimm = true; + dram_info->is_16gb_dimm = ch0.is_16gb_dimm || ch1.is_16gb_dimm; dev_priv->dram_info.symmetric_memory = intel_is_dram_symmetric(val_ch0, val_ch1, @@ -1314,7 +1311,6 @@ bxt_get_dram_info(struct drm_i915_private *dev_priv) return -EINVAL; } - dram_info->valid_dimm = true; dram_info->valid = true; return 0; } @@ -1327,12 +1323,17 @@ intel_get_dram_info(struct drm_i915_private *dev_priv) int ret; dram_info->valid = false; - dram_info->valid_dimm = false; - dram_info->is_16gb_dimm = false; dram_info->rank = I915_DRAM_RANK_INVALID; dram_info->bandwidth_kbps = 0; dram_info->num_channels = 0; + /* + * Assume 16Gb DIMMs are present until proven otherwise. + * This is only used for the level 0 watermark latency + * w/a which does not apply to bxt/glk. + */ + dram_info->is_16gb_dimm = !IS_GEN9_LP(dev_priv); + if (INTEL_GEN(dev_priv) < 9 || IS_GEMINILAKE(dev_priv)) return; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 8624b4bdc242..9102571e9692 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1948,7 +1948,6 @@ struct drm_i915_private { struct dram_info { bool valid; - bool valid_dimm; bool is_16gb_dimm; u8 num_channels; enum dram_rank { diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 1db9b8328275..245f0022bcfd 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -2881,8 +2881,7 @@ static void intel_read_wm_latency(struct drm_i915_private *dev_priv, * any underrun. If not able to get Dimm info assume 16GB dimm * to avoid any underrun. */ - if (!dev_priv->dram_info.valid_dimm || - dev_priv->dram_info.is_16gb_dimm) + if (dev_priv->dram_info.is_16gb_dimm) wm[0] += 1; } else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) { From 6503493145cba4413ecd3d4d153faeef4a1e9b85 Mon Sep 17 00:00:00 2001 From: Clint Taylor Date: Thu, 25 Oct 2018 11:52:00 -0700 Subject: [PATCH 153/356] drm/i915/hdmi: Add HDMI 2.0 audio clock recovery N values HDMI 2.0 594Mhz modes were incorrectly selecting 25.200Mhz Automatic N value mode instead of HDMI specification values. V2: Fix 88.2 Hz N value Cc: Jani Nikula Cc: stable@vger.kernel.org Signed-off-by: Clint Taylor Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/1540493521-1746-2-git-send-email-clinton.a.taylor@intel.com (cherry picked from commit 5a400aa3c562c4a726b4da286e63c96db905ade1) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/intel_audio.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c index 769f3f586661..ee3ca2de983b 100644 --- a/drivers/gpu/drm/i915/intel_audio.c +++ b/drivers/gpu/drm/i915/intel_audio.c @@ -144,6 +144,9 @@ static const struct { /* HDMI N/CTS table */ #define TMDS_297M 297000 #define TMDS_296M 296703 +#define TMDS_594M 594000 +#define TMDS_593M 593407 + static const struct { int sample_rate; int clock; @@ -164,6 +167,20 @@ static const struct { { 176400, TMDS_297M, 18816, 247500 }, { 192000, TMDS_296M, 23296, 281250 }, { 192000, TMDS_297M, 20480, 247500 }, + { 44100, TMDS_593M, 8918, 937500 }, + { 44100, TMDS_594M, 9408, 990000 }, + { 48000, TMDS_593M, 5824, 562500 }, + { 48000, TMDS_594M, 6144, 594000 }, + { 32000, TMDS_593M, 5824, 843750 }, + { 32000, TMDS_594M, 3072, 445500 }, + { 88200, TMDS_593M, 17836, 937500 }, + { 88200, TMDS_594M, 18816, 990000 }, + { 96000, TMDS_593M, 11648, 562500 }, + { 96000, TMDS_594M, 12288, 594000 }, + { 176400, TMDS_593M, 35672, 937500 }, + { 176400, TMDS_594M, 37632, 990000 }, + { 192000, TMDS_593M, 23296, 562500 }, + { 192000, TMDS_594M, 24576, 594000 }, }; /* get AUD_CONFIG_PIXEL_CLOCK_HDMI_* value for mode */ From c58281056a8b26d5d9dc15c19859a7880835ef44 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 25 Oct 2018 10:18:22 +0100 Subject: [PATCH 154/356] drm/i915: Mark up GTT sizes as u64 Since we use a 64b virtual GTT irrespective of the system, we want to ensure that the GTT computations remains 64b even on 32b systems, including treatment of huge virtual pages. No code generation changes on 64b: Reported-by: Sergii Romantsov Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108282 Signed-off-by: Chris Wilson Cc: Joonas Lahtinen Cc: stable@vger.kernel.org Reviewed-by: Matthew Auld Link: https://patchwork.freedesktop.org/patch/msgid/20181025091823.20571-1-chris@chris-wilson.co.uk (cherry picked from commit 9125963a9494253fa5a29cc1b4169885d2be7042) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/i915_gem_gtt.c | 2 +- drivers/gpu/drm/i915/i915_gem_gtt.h | 6 +++--- drivers/gpu/drm/i915/selftests/huge_pages.c | 2 +- drivers/gpu/drm/i915/selftests/i915_gem_gtt.c | 6 +++--- 4 files changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 56c7f8637311..47c302543799 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -1757,7 +1757,7 @@ static void gen6_dump_ppgtt(struct i915_hw_ppgtt *base, struct seq_file *m) if (i == 4) continue; - seq_printf(m, "\t\t(%03d, %04d) %08lx: ", + seq_printf(m, "\t\t(%03d, %04d) %08llx: ", pde, pte, (pde * GEN6_PTES + pte) * I915_GTT_PAGE_SIZE); for (i = 0; i < 4; i++) { diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h index 7e2af5f4f39b..aa8307043036 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.h +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h @@ -42,9 +42,9 @@ #include "i915_selftest.h" #include "i915_timeline.h" -#define I915_GTT_PAGE_SIZE_4K BIT(12) -#define I915_GTT_PAGE_SIZE_64K BIT(16) -#define I915_GTT_PAGE_SIZE_2M BIT(21) +#define I915_GTT_PAGE_SIZE_4K BIT_ULL(12) +#define I915_GTT_PAGE_SIZE_64K BIT_ULL(16) +#define I915_GTT_PAGE_SIZE_2M BIT_ULL(21) #define I915_GTT_PAGE_SIZE I915_GTT_PAGE_SIZE_4K #define I915_GTT_MAX_PAGE_SIZE I915_GTT_PAGE_SIZE_2M diff --git a/drivers/gpu/drm/i915/selftests/huge_pages.c b/drivers/gpu/drm/i915/selftests/huge_pages.c index 8d03f64eabd7..5c22f2c8d4cf 100644 --- a/drivers/gpu/drm/i915/selftests/huge_pages.c +++ b/drivers/gpu/drm/i915/selftests/huge_pages.c @@ -551,7 +551,7 @@ static int igt_mock_ppgtt_misaligned_dma(void *arg) err = igt_check_page_sizes(vma); if (vma->page_sizes.gtt != I915_GTT_PAGE_SIZE_4K) { - pr_err("page_sizes.gtt=%u, expected %lu\n", + pr_err("page_sizes.gtt=%u, expected %llu\n", vma->page_sizes.gtt, I915_GTT_PAGE_SIZE_4K); err = -EINVAL; } diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c index 8e2e269db97e..127d81513671 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c @@ -1337,7 +1337,7 @@ static int igt_gtt_reserve(void *arg) GEM_BUG_ON(!drm_mm_node_allocated(&vma->node)); if (vma->node.start != total || vma->node.size != 2*I915_GTT_PAGE_SIZE) { - pr_err("i915_gem_gtt_reserve (pass 1) placement failed, found (%llx + %llx), expected (%llx + %lx)\n", + pr_err("i915_gem_gtt_reserve (pass 1) placement failed, found (%llx + %llx), expected (%llx + %llx)\n", vma->node.start, vma->node.size, total, 2*I915_GTT_PAGE_SIZE); err = -EINVAL; @@ -1386,7 +1386,7 @@ static int igt_gtt_reserve(void *arg) GEM_BUG_ON(!drm_mm_node_allocated(&vma->node)); if (vma->node.start != total || vma->node.size != 2*I915_GTT_PAGE_SIZE) { - pr_err("i915_gem_gtt_reserve (pass 2) placement failed, found (%llx + %llx), expected (%llx + %lx)\n", + pr_err("i915_gem_gtt_reserve (pass 2) placement failed, found (%llx + %llx), expected (%llx + %llx)\n", vma->node.start, vma->node.size, total, 2*I915_GTT_PAGE_SIZE); err = -EINVAL; @@ -1430,7 +1430,7 @@ static int igt_gtt_reserve(void *arg) GEM_BUG_ON(!drm_mm_node_allocated(&vma->node)); if (vma->node.start != offset || vma->node.size != 2*I915_GTT_PAGE_SIZE) { - pr_err("i915_gem_gtt_reserve (pass 3) placement failed, found (%llx + %llx), expected (%llx + %lx)\n", + pr_err("i915_gem_gtt_reserve (pass 3) placement failed, found (%llx + %llx), expected (%llx + %llx)\n", vma->node.start, vma->node.size, offset, 2*I915_GTT_PAGE_SIZE); err = -EINVAL; From 085603287452fc96376ed4888bf29f8c095d2b40 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 25 Oct 2018 10:18:23 +0100 Subject: [PATCH 155/356] drm/i915: Compare user's 64b GTT offset even on 32b Beware mixing unsigned long constants and 64b values, as on 32b the constant will be zero extended and discard the high 32b when used as a mask! Reported-by: Sergii Romantsov Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108282 Signed-off-by: Chris Wilson Cc: Joonas Lahtinen Cc: stable@vger.kernel.org Reviewed-by: Matthew Auld Link: https://patchwork.freedesktop.org/patch/msgid/20181025091823.20571-2-chris@chris-wilson.co.uk (cherry picked from commit 6fc4e48f9ed46e9adff236a0c350074aafa3b7fa) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/gvt/gtt.h | 1 - drivers/gpu/drm/i915/i915_gem_execbuffer.c | 2 +- drivers/gpu/drm/i915/i915_gem_gtt.h | 2 ++ 3 files changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h index 7a9b36176efb..bfb6f652b09f 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.h +++ b/drivers/gpu/drm/i915/gvt/gtt.h @@ -35,7 +35,6 @@ #define _GVT_GTT_H_ #define I915_GTT_PAGE_SHIFT 12 -#define I915_GTT_PAGE_MASK (~(I915_GTT_PAGE_SIZE - 1)) struct intel_vgpu_mm; diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 09187286d346..1aaccbe7e1de 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -460,7 +460,7 @@ eb_validate_vma(struct i915_execbuffer *eb, * any non-page-aligned or non-canonical addresses. */ if (unlikely(entry->flags & EXEC_OBJECT_PINNED && - entry->offset != gen8_canonical_addr(entry->offset & PAGE_MASK))) + entry->offset != gen8_canonical_addr(entry->offset & I915_GTT_PAGE_MASK))) return -EINVAL; /* pad_to_size was once a reserved field, so sanitize it */ diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h index aa8307043036..5d2c5ba55ad8 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.h +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h @@ -49,6 +49,8 @@ #define I915_GTT_PAGE_SIZE I915_GTT_PAGE_SIZE_4K #define I915_GTT_MAX_PAGE_SIZE I915_GTT_PAGE_SIZE_2M +#define I915_GTT_PAGE_MASK -I915_GTT_PAGE_SIZE + #define I915_GTT_MIN_ALIGNMENT I915_GTT_PAGE_SIZE #define I915_FENCE_REG_NONE -1 From 2c2f6e30d5f29691e3563d334ce208d3a1907f49 Mon Sep 17 00:00:00 2001 From: Rodrigo Vivi Date: Thu, 25 Oct 2018 17:56:36 -0700 Subject: [PATCH 156/356] drm/i915/glk: Remove 99% limitation. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit While checking the opportunity to add a display_gen check to allow glk and cnl to be on same bucket I noticed these FIXME cases here. So I got the confirmation from HW architect that we actually never needed this workaround. "GLK supports 2 pixel per clock, so pixel clock can be up to 2 * cdclk." So, this reverts commit 97f55ca5b662 ("drm/i915/glk: limit pixel clock to 99% of cdclk workaround") Fixes: 97f55ca5b662 ("drm/i915/glk: limit pixel clock to 99% of cdclk workaround") Cc: Ville Syrjälä Cc: Madhav Chauhan Cc: Jani Nikula Cc: Clinton Taylor Cc: Arthur J Runyan Signed-off-by: Rodrigo Vivi Reviewed-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20181026005636.22274-1-rodrigo.vivi@intel.com (cherry picked from commit 42882336e62aab00278114392a16374f272a0c99) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/intel_cdclk.c | 18 ++---------------- 1 file changed, 2 insertions(+), 16 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c index 29075c763428..8d74276029e6 100644 --- a/drivers/gpu/drm/i915/intel_cdclk.c +++ b/drivers/gpu/drm/i915/intel_cdclk.c @@ -2138,16 +2138,8 @@ void intel_set_cdclk(struct drm_i915_private *dev_priv, static int intel_pixel_rate_to_cdclk(struct drm_i915_private *dev_priv, int pixel_rate) { - if (INTEL_GEN(dev_priv) >= 10) + if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) return DIV_ROUND_UP(pixel_rate, 2); - else if (IS_GEMINILAKE(dev_priv)) - /* - * FIXME: Avoid using a pixel clock that is more than 99% of the cdclk - * as a temporary workaround. Use a higher cdclk instead. (Note that - * intel_compute_max_dotclk() limits the max pixel clock to 99% of max - * cdclk.) - */ - return DIV_ROUND_UP(pixel_rate * 100, 2 * 99); else if (IS_GEN9(dev_priv) || IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv)) return pixel_rate; @@ -2543,14 +2535,8 @@ static int intel_compute_max_dotclk(struct drm_i915_private *dev_priv) { int max_cdclk_freq = dev_priv->max_cdclk_freq; - if (INTEL_GEN(dev_priv) >= 10) + if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) return 2 * max_cdclk_freq; - else if (IS_GEMINILAKE(dev_priv)) - /* - * FIXME: Limiting to 99% as a temporary workaround. See - * intel_min_cdclk() for details. - */ - return 2 * max_cdclk_freq * 99 / 100; else if (IS_GEN9(dev_priv) || IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv)) return max_cdclk_freq; From 76271ef2638ca8e4bf2884cad664a34be0d5a42b Mon Sep 17 00:00:00 2001 From: Dhinakaran Pandiyan Date: Fri, 5 Oct 2018 11:56:42 -0700 Subject: [PATCH 157/356] drm/i915: Fix VIDEO_DIP_CTL bit shifts The shifts for VSC_SELECT bits are wrong, fix it. Good thing is the definitions are unused. v2: Moves definitions in another patch (Manasi) Cc: Manasi Navare Cc: Anusha Srivatsa Cc: Rodrigo Vivi Fixes: 7af2be6d54d4 ("drm/i915/icl: Add VIDEO_DIP registers") Signed-off-by: Dhinakaran Pandiyan Reviewed-by: Manasi Navare Link: https://patchwork.freedesktop.org/patch/msgid/20181005185643.31660-1-dhinakaran.pandiyan@intel.com (cherry picked from commit 09209662618f9fdc38b8d4da39040c8829fd2d57) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/i915_reg.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 7c491ea3d052..f2d92aee721b 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -4593,12 +4593,12 @@ enum { #define DRM_DIP_ENABLE (1 << 28) #define PSR_VSC_BIT_7_SET (1 << 27) -#define VSC_SELECT_MASK (0x3 << 26) -#define VSC_SELECT_SHIFT 26 -#define VSC_DIP_HW_HEA_DATA (0 << 26) -#define VSC_DIP_HW_HEA_SW_DATA (1 << 26) -#define VSC_DIP_HW_DATA_SW_HEA (2 << 26) -#define VSC_DIP_SW_HEA_DATA (3 << 26) +#define VSC_SELECT_MASK (0x3 << 25) +#define VSC_SELECT_SHIFT 25 +#define VSC_DIP_HW_HEA_DATA (0 << 25) +#define VSC_DIP_HW_HEA_SW_DATA (1 << 25) +#define VSC_DIP_HW_DATA_SW_HEA (2 << 25) +#define VSC_DIP_SW_HEA_DATA (3 << 25) #define VDIP_ENABLE_PPS (1 << 24) /* Panel power sequencing */ From f42f343887016330b321dd40eebc68c7292e4f1b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Mon, 29 Oct 2018 16:00:31 +0200 Subject: [PATCH 158/356] drm/i915: Fix error handling for the NV12 fb dimensions check MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Let's not leak obj->framebuffer_references when we decide that the framebuffer domensions are not suitable for NV12. Cc: stable@vger.kernel.org Cc: Maarten Lankhorst Cc: Vidya Srinivas Fixes: e44134f2673c ("drm/i915: Add NV12 support to intel_framebuffer_init") Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20181029140031.11765-1-ville.syrjala@linux.intel.com Reviewed-by: Matt Roper (cherry picked from commit 3b90946fcb6f13b65888c380461793a9dea9d1f4) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/intel_display.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 9741cc419e1b..b8dfdbc9ca1f 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -14646,7 +14646,7 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb, fb->height < SKL_MIN_YUV_420_SRC_H || (fb->width % 4) != 0 || (fb->height % 4) != 0)) { DRM_DEBUG_KMS("src dimensions not correct for NV12\n"); - return -EINVAL; + goto err; } for (i = 0; i < fb->format->num_planes; i++) { From e528c2affcf216b3d02b22004895cb678769629b Mon Sep 17 00:00:00 2001 From: Manasi Navare Date: Tue, 23 Oct 2018 12:12:47 -0700 Subject: [PATCH 159/356] drm/i915/icl: Fix the macros for DFLEXDPMLE register bits MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch fixes the macros used for defining the DFLEXDPMLE register bit fields. This accounts for changes in the spec. Fixes: a2bc69a1a9d6 ("drm/i915/icl: Add register definition for DFLEXDPMLE") Cc: Animesh Manna Cc: Paulo Zanoni Cc: Jose Roberto de Souza Cc: # v4.19+ Signed-off-by: Manasi Navare Reviewed-by: José Roberto de Souza Link: https://patchwork.freedesktop.org/patch/msgid/20181023191248.26418-1-manasi.d.navare@intel.com (cherry picked from commit b4335ec0a3ee6229a570755f8fb95dc8a7c694f2) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/i915_reg.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index f2d92aee721b..e31c27e45734 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -2095,8 +2095,12 @@ enum i915_power_well_id { /* ICL PHY DFLEX registers */ #define PORT_TX_DFLEXDPMLE1 _MMIO(0x1638C0) -#define DFLEXDPMLE1_DPMLETC_MASK(n) (0xf << (4 * (n))) -#define DFLEXDPMLE1_DPMLETC(n, x) ((x) << (4 * (n))) +#define DFLEXDPMLE1_DPMLETC_MASK(tc_port) (0xf << (4 * (tc_port))) +#define DFLEXDPMLE1_DPMLETC_ML0(tc_port) (1 << (4 * (tc_port))) +#define DFLEXDPMLE1_DPMLETC_ML1_0(tc_port) (3 << (4 * (tc_port))) +#define DFLEXDPMLE1_DPMLETC_ML3(tc_port) (8 << (4 * (tc_port))) +#define DFLEXDPMLE1_DPMLETC_ML3_2(tc_port) (12 << (4 * (tc_port))) +#define DFLEXDPMLE1_DPMLETC_ML3_0(tc_port) (15 << (4 * (tc_port))) /* BXT PHY Ref registers */ #define _PORT_REF_DW3_A 0x16218C From 0014868b9c3c1dda1de6711cf58c3486fb422d07 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 2 Nov 2018 16:12:09 +0000 Subject: [PATCH 160/356] drm/i915: Mark pin flags as u64 Since the flags are being used to operate on a u64 variable, they too need to be marked as such so that the inverses are full width (and not zero extended on 32b kernels and bdw+). Reported-by: Sergii Romantsov Signed-off-by: Chris Wilson Cc: stable@vger.kernel.org Reviewed-by: Lionel Landwerlin Reviewed-by: Michal Wajdeczko Link: https://patchwork.freedesktop.org/patch/msgid/20181102161232.17742-2-chris@chris-wilson.co.uk (cherry picked from commit 83b466b1dc5f0b4d33f0a901e8b00197a8f3582d) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/i915_gem_gtt.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h index 5d2c5ba55ad8..28039290655c 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.h +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h @@ -661,20 +661,20 @@ int i915_gem_gtt_insert(struct i915_address_space *vm, u64 start, u64 end, unsigned int flags); /* Flags used by pin/bind&friends. */ -#define PIN_NONBLOCK BIT(0) -#define PIN_MAPPABLE BIT(1) -#define PIN_ZONE_4G BIT(2) -#define PIN_NONFAULT BIT(3) -#define PIN_NOEVICT BIT(4) +#define PIN_NONBLOCK BIT_ULL(0) +#define PIN_MAPPABLE BIT_ULL(1) +#define PIN_ZONE_4G BIT_ULL(2) +#define PIN_NONFAULT BIT_ULL(3) +#define PIN_NOEVICT BIT_ULL(4) -#define PIN_MBZ BIT(5) /* I915_VMA_PIN_OVERFLOW */ -#define PIN_GLOBAL BIT(6) /* I915_VMA_GLOBAL_BIND */ -#define PIN_USER BIT(7) /* I915_VMA_LOCAL_BIND */ -#define PIN_UPDATE BIT(8) +#define PIN_MBZ BIT_ULL(5) /* I915_VMA_PIN_OVERFLOW */ +#define PIN_GLOBAL BIT_ULL(6) /* I915_VMA_GLOBAL_BIND */ +#define PIN_USER BIT_ULL(7) /* I915_VMA_LOCAL_BIND */ +#define PIN_UPDATE BIT_ULL(8) -#define PIN_HIGH BIT(9) -#define PIN_OFFSET_BIAS BIT(10) -#define PIN_OFFSET_FIXED BIT(11) +#define PIN_HIGH BIT_ULL(9) +#define PIN_OFFSET_BIAS BIT_ULL(10) +#define PIN_OFFSET_FIXED BIT_ULL(11) #define PIN_OFFSET_MASK (-I915_GTT_PAGE_SIZE) #endif From 6a8915d0f8cf323e1beb792a33095cf652db4056 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Mon, 5 Nov 2018 21:46:04 +0200 Subject: [PATCH 161/356] drm/i915: Don't oops during modeset shutdown after lpe audio deinit MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We deinit the lpe audio device before we call drm_atomic_helper_shutdown(), which means the platform device may already be gone when it comes time to shut down the crtc. As we don't know when the last reference to the platform device gets dropped by the audio driver we can't assume that the device and its data are still around when turning off the crtc. Mark the platform device as gone as soon as we do the audio deinit. Cc: stable@vger.kernel.org Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20181105194604.6994-1-ville.syrjala@linux.intel.com Reviewed-by: Chris Wilson (cherry picked from commit f45a7977d1140c11f334e01a9f77177ed68e3bfa) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/intel_lpe_audio.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/intel_lpe_audio.c b/drivers/gpu/drm/i915/intel_lpe_audio.c index cdf19553ffac..5d5336fbe7b0 100644 --- a/drivers/gpu/drm/i915/intel_lpe_audio.c +++ b/drivers/gpu/drm/i915/intel_lpe_audio.c @@ -297,8 +297,10 @@ void intel_lpe_audio_teardown(struct drm_i915_private *dev_priv) lpe_audio_platdev_destroy(dev_priv); irq_free_desc(dev_priv->lpe_audio.irq); -} + dev_priv->lpe_audio.irq = -1; + dev_priv->lpe_audio.platdev = NULL; +} /** * intel_lpe_audio_notify() - notify lpe audio event From 5e93a125f521efd00d71af31c2a301f3d46af48c Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 5 Nov 2018 12:28:07 +0100 Subject: [PATCH 162/356] ALSA: hda - Fix incorrect clearance of thinkpad_acpi hooks Since the commit c647f806b8c2 ("ALSA: hda - Allow multiple ADCs for mic mute LED controls") we allow enabling the mic mute LED with multiple ADCs. The commit changed the function return value to be zero or a negative error, while this change was overlooked in the thinkpad_acpi helper code where it still expects a positive return value for success. This eventually leads to a NULL dereference on a system that has only a mic mute LED. This patch corrects the return value check in the corresponding code as well. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=201621 Fixes: c647f806b8c2 ("ALSA: hda - Allow multiple ADCs for mic mute LED controls") Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/thinkpad_helper.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/pci/hda/thinkpad_helper.c b/sound/pci/hda/thinkpad_helper.c index 97f49b751e6e..568575b72f2f 100644 --- a/sound/pci/hda/thinkpad_helper.c +++ b/sound/pci/hda/thinkpad_helper.c @@ -58,8 +58,8 @@ static void hda_fixup_thinkpad_acpi(struct hda_codec *codec, removefunc = false; } if (led_set_func(TPACPI_LED_MICMUTE, false) >= 0 && - snd_hda_gen_add_micmute_led(codec, - update_tpacpi_micmute) > 0) + !snd_hda_gen_add_micmute_led(codec, + update_tpacpi_micmute)) removefunc = false; } From 506481b20e818db40b6198815904ecd2d6daee64 Mon Sep 17 00:00:00 2001 From: Robbie Ko Date: Tue, 30 Oct 2018 18:04:04 +0800 Subject: [PATCH 163/356] Btrfs: fix cur_offset in the error case for nocow When the cow_file_range fails, the related resources are unlocked according to the range [start..end), so the unlock cannot be repeated in run_delalloc_nocow. In some cases (e.g. cur_offset <= end && cow_start != -1), cur_offset is not updated correctly, so move the cur_offset update before cow_file_range. kernel BUG at mm/page-writeback.c:2663! Internal error: Oops - BUG: 0 [#1] SMP CPU: 3 PID: 31525 Comm: kworker/u8:7 Tainted: P O Hardware name: Realtek_RTD1296 (DT) Workqueue: writeback wb_workfn (flush-btrfs-1) task: ffffffc076db3380 ti: ffffffc02e9ac000 task.ti: ffffffc02e9ac000 PC is at clear_page_dirty_for_io+0x1bc/0x1e8 LR is at clear_page_dirty_for_io+0x14/0x1e8 pc : [] lr : [] pstate: 40000145 sp : ffffffc02e9af4f0 Process kworker/u8:7 (pid: 31525, stack limit = 0xffffffc02e9ac020) Call trace: [] clear_page_dirty_for_io+0x1bc/0x1e8 [] extent_clear_unlock_delalloc+0x1e4/0x210 [btrfs] [] run_delalloc_nocow+0x3b8/0x948 [btrfs] [] run_delalloc_range+0x250/0x3a8 [btrfs] [] writepage_delalloc.isra.21+0xbc/0x1d8 [btrfs] [] __extent_writepage+0xe8/0x248 [btrfs] [] extent_write_cache_pages.isra.17+0x164/0x378 [btrfs] [] extent_writepages+0x48/0x68 [btrfs] [] btrfs_writepages+0x20/0x30 [btrfs] [] do_writepages+0x30/0x88 [] __writeback_single_inode+0x34/0x198 [] writeback_sb_inodes+0x184/0x3c0 [] __writeback_inodes_wb+0x6c/0xc0 [] wb_writeback+0x1b8/0x1c0 [] wb_workfn+0x150/0x250 [] process_one_work+0x1dc/0x388 [] worker_thread+0x130/0x500 [] kthread+0x10c/0x110 [] ret_from_fork+0x10/0x40 Code: d503201f a9025bb5 a90363b7 f90023b9 (d4210000) CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Filipe Manana Signed-off-by: Robbie Ko Signed-off-by: David Sterba --- fs/btrfs/inode.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index f4d31fd62eed..55761b1519f5 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1531,12 +1531,11 @@ out_check: } btrfs_release_path(path); - if (cur_offset <= end && cow_start == (u64)-1) { + if (cur_offset <= end && cow_start == (u64)-1) cow_start = cur_offset; - cur_offset = end; - } if (cow_start != (u64)-1) { + cur_offset = end; ret = cow_file_range(inode, locked_page, cow_start, end, end, page_started, nr_written, 1, NULL); if (ret) From fcd5e74288f7d36991b1f0fb96b8c57079645e38 Mon Sep 17 00:00:00 2001 From: Lu Fengqi Date: Wed, 24 Oct 2018 20:24:03 +0800 Subject: [PATCH 164/356] btrfs: fix pinned underflow after transaction aborted When running generic/475, we may get the following warning in dmesg: [ 6902.102154] WARNING: CPU: 3 PID: 18013 at fs/btrfs/extent-tree.c:9776 btrfs_free_block_groups+0x2af/0x3b0 [btrfs] [ 6902.109160] CPU: 3 PID: 18013 Comm: umount Tainted: G W O 4.19.0-rc8+ #8 [ 6902.110971] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 [ 6902.112857] RIP: 0010:btrfs_free_block_groups+0x2af/0x3b0 [btrfs] [ 6902.118921] RSP: 0018:ffffc9000459bdb0 EFLAGS: 00010286 [ 6902.120315] RAX: ffff880175050bb0 RBX: ffff8801124a8000 RCX: 0000000000170007 [ 6902.121969] RDX: 0000000000000002 RSI: 0000000000170007 RDI: ffffffff8125fb74 [ 6902.123716] RBP: ffff880175055d10 R08: 0000000000000000 R09: 0000000000000000 [ 6902.125417] R10: 0000000000000000 R11: 0000000000000000 R12: ffff880175055d88 [ 6902.127129] R13: ffff880175050bb0 R14: 0000000000000000 R15: dead000000000100 [ 6902.129060] FS: 00007f4507223780(0000) GS:ffff88017ba00000(0000) knlGS:0000000000000000 [ 6902.130996] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 6902.132558] CR2: 00005623599cac78 CR3: 000000014b700001 CR4: 00000000003606e0 [ 6902.134270] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 6902.135981] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 6902.137836] Call Trace: [ 6902.138939] close_ctree+0x171/0x330 [btrfs] [ 6902.140181] ? kthread_stop+0x146/0x1f0 [ 6902.141277] generic_shutdown_super+0x6c/0x100 [ 6902.142517] kill_anon_super+0x14/0x30 [ 6902.143554] btrfs_kill_super+0x13/0x100 [btrfs] [ 6902.144790] deactivate_locked_super+0x2f/0x70 [ 6902.146014] cleanup_mnt+0x3b/0x70 [ 6902.147020] task_work_run+0x9e/0xd0 [ 6902.148036] do_syscall_64+0x470/0x600 [ 6902.149142] ? trace_hardirqs_off_thunk+0x1a/0x1c [ 6902.150375] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 6902.151640] RIP: 0033:0x7f45077a6a7b [ 6902.157324] RSP: 002b:00007ffd589f3e68 EFLAGS: 00000246 ORIG_RAX: 00000000000000a6 [ 6902.159187] RAX: 0000000000000000 RBX: 000055e8eec732b0 RCX: 00007f45077a6a7b [ 6902.160834] RDX: 0000000000000001 RSI: 0000000000000000 RDI: 000055e8eec73490 [ 6902.162526] RBP: 0000000000000000 R08: 000055e8eec734b0 R09: 00007ffd589f26c0 [ 6902.164141] R10: 0000000000000000 R11: 0000000000000246 R12: 000055e8eec73490 [ 6902.165815] R13: 00007f4507ac61a4 R14: 0000000000000000 R15: 00007ffd589f40d8 [ 6902.167553] irq event stamp: 0 [ 6902.168998] hardirqs last enabled at (0): [<0000000000000000>] (null) [ 6902.170731] hardirqs last disabled at (0): [] copy_process.part.55+0x3b0/0x1f00 [ 6902.172773] softirqs last enabled at (0): [] copy_process.part.55+0x3b0/0x1f00 [ 6902.174671] softirqs last disabled at (0): [<0000000000000000>] (null) [ 6902.176407] ---[ end trace 463138c2986b275c ]--- [ 6902.177636] BTRFS info (device dm-3): space_info 4 has 273465344 free, is not full [ 6902.179453] BTRFS info (device dm-3): space_info total=276824064, used=4685824, pinned=18446744073708158976, reserved=0, may_use=0, readonly=65536 In the above line there's "pinned=18446744073708158976" which is an unsigned u64 value of -1392640, an obvious underflow. When transaction_kthread is running cleanup_transaction(), another fsstress is running btrfs_commit_transaction(). The btrfs_finish_extent_commit() may get the same range as btrfs_destroy_pinned_extent() got, which causes the pinned underflow. Fixes: d4b450cd4b33 ("Btrfs: fix race between transaction commit and empty block group removal") CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Josef Bacik Signed-off-by: Lu Fengqi Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b0ab41da91d1..00ee5e37e989 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4359,13 +4359,23 @@ static int btrfs_destroy_pinned_extent(struct btrfs_fs_info *fs_info, unpin = pinned_extents; again: while (1) { + /* + * The btrfs_finish_extent_commit() may get the same range as + * ours between find_first_extent_bit and clear_extent_dirty. + * Hence, hold the unused_bg_unpin_mutex to avoid double unpin + * the same extent range. + */ + mutex_lock(&fs_info->unused_bg_unpin_mutex); ret = find_first_extent_bit(unpin, 0, &start, &end, EXTENT_DIRTY, NULL); - if (ret) + if (ret) { + mutex_unlock(&fs_info->unused_bg_unpin_mutex); break; + } clear_extent_dirty(unpin, start, end); btrfs_error_unpin_extent_range(fs_info, start, end); + mutex_unlock(&fs_info->unused_bg_unpin_mutex); cond_resched(); } From 008c6753f7e070c77c70d708a6bf0255b4381763 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 29 Oct 2018 09:42:06 +0000 Subject: [PATCH 165/356] Btrfs: fix missing data checksums after a ranged fsync (msync) Recently we got a massive simplification for fsync, where for the fast path we no longer log new extents while their respective ordered extents are still running. However that simplification introduced a subtle regression for the case where we use a ranged fsync (msync). Consider the following example: CPU 0 CPU 1 mmap write to range [2Mb, 4Mb[ mmap write to range [512Kb, 1Mb[ msync range [512K, 1Mb[ --> triggers fast fsync (BTRFS_INODE_NEEDS_FULL_SYNC not set) --> creates extent map A for this range and adds it to list of modified extents --> starts ordered extent A for this range --> waits for it to complete writeback triggered for range [2Mb, 4Mb[ --> create extent map B and adds it to the list of modified extents --> creates ordered extent B --> start looking for and logging modified extents --> logs extent maps A and B --> finds checksums for extent A in the csum tree, but not for extent B fsync (msync) finishes --> ordered extent B finishes and its checksums are added to the csum tree After replaying the log, we have the extent covering the range [2Mb, 4Mb[ but do not have the data checksum items covering that file range. This happens because at the very beginning of an fsync (btrfs_sync_file()) we start and wait for IO in the given range [512Kb, 1Mb[ and therefore wait for any ordered extents in that range to complete before we start logging the extents. However if right before we start logging the extent in our range [512Kb, 1Mb[, writeback is started for any other dirty range, such as the range [2Mb, 4Mb[ due to memory pressure or a concurrent fsync or msync (btrfs_sync_file() starts writeback before acquiring the inode's lock), an ordered extent is created for that other range and a new extent map is created to represent that range and added to the inode's list of modified extents. That means that we will see that other extent in that list when collecting extents for logging (done at btrfs_log_changed_extents()) and log the extent before the respective ordered extent finishes - namely before the checksum items are added to the checksums tree, which is where log_extent_csums() looks for the checksums, therefore making us log an extent without logging its checksums. Before that massive simplification of fsync, this wasn't a problem because besides looking for checkums in the checksums tree, we also looked for them in any ordered extent still running. The consequence of data checksums missing for a file range is that users attempting to read the affected file range will get -EIO errors and dmesg reports the following: [10188.358136] BTRFS info (device sdc): no csum found for inode 297 start 57344 [10188.359278] BTRFS warning (device sdc): csum failed root 5 ino 297 off 57344 csum 0x98f94189 expected csum 0x00000000 mirror 1 So fix this by skipping extents outside of our logging range at btrfs_log_changed_extents() and leaving them on the list of modified extents so that any subsequent ranged fsync may collect them if needed. Also, if we find a hole extent outside of the range still log it, just to prevent having gaps between extent items after replaying the log, otherwise fsck will complain when we are not using the NO_HOLES feature (fstest btrfs/056 triggers such case). Fixes: e7175a692765 ("btrfs: remove the wait ordered logic in the log_one_extent path") CC: stable@vger.kernel.org # 4.19+ Reviewed-by: Josef Bacik Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/tree-log.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index e07f3376b7df..a5ce99a6c936 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4396,6 +4396,23 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, logged_end = end; list_for_each_entry_safe(em, n, &tree->modified_extents, list) { + /* + * Skip extents outside our logging range. It's important to do + * it for correctness because if we don't ignore them, we may + * log them before their ordered extent completes, and therefore + * we could log them without logging their respective checksums + * (the checksum items are added to the csum tree at the very + * end of btrfs_finish_ordered_io()). Also leave such extents + * outside of our range in the list, since we may have another + * ranged fsync in the near future that needs them. If an extent + * outside our range corresponds to a hole, log it to avoid + * leaving gaps between extents (fsck will complain when we are + * not using the NO_HOLES feature). + */ + if ((em->start > end || em->start + em->len <= start) && + em->block_start != EXTENT_MAP_HOLE) + continue; + list_del_init(&em->list); /* * Just an arbitrary number, this can be really CPU intensive From 761333f2f50ccc887aa9957ae829300262c0d15b Mon Sep 17 00:00:00 2001 From: Shaokun Zhang Date: Mon, 5 Nov 2018 18:49:09 +0800 Subject: [PATCH 166/356] btrfs: tree-checker: Fix misleading group system information block_group_err shows the group system as a decimal value with a '0x' prefix, which is somewhat misleading. Fix it to print hexadecimal, as was intended. Fixes: fce466eab7ac6 ("btrfs: tree-checker: Verify block_group_item") CC: stable@vger.kernel.org # 4.19+ Reviewed-by: Nikolay Borisov Reviewed-by: Qu Wenruo Signed-off-by: Shaokun Zhang Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/tree-checker.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index cab0b1f1f741..efcf89a8ba44 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -440,7 +440,7 @@ static int check_block_group_item(struct btrfs_fs_info *fs_info, type != (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA)) { block_group_err(fs_info, leaf, slot, -"invalid type, have 0x%llx (%lu bits set) expect either 0x%llx, 0x%llx, 0x%llu or 0x%llx", +"invalid type, have 0x%llx (%lu bits set) expect either 0x%llx, 0x%llx, 0x%llx or 0x%llx", type, hweight64(type), BTRFS_BLOCK_GROUP_DATA, BTRFS_BLOCK_GROUP_METADATA, BTRFS_BLOCK_GROUP_SYSTEM, From 7e17916b35797396f681a3270245fd29c1e4c250 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 3 Nov 2018 16:39:28 +0100 Subject: [PATCH 167/356] btrfs: avoid link error with CONFIG_NO_AUTO_INLINE Note: this patch fixes a problem in a feature outside of btrfs ("kernel hacking: add a config option to disable compiler auto-inlining") and is applied ahead of time due to cross-subsystem dependencies. On 32-bit ARM with gcc-8, I see a link error with the addition of the CONFIG_NO_AUTO_INLINE option: fs/btrfs/super.o: In function `btrfs_statfs': super.c:(.text+0x67b8): undefined reference to `__aeabi_uldivmod' super.c:(.text+0x67fc): undefined reference to `__aeabi_uldivmod' super.c:(.text+0x6858): undefined reference to `__aeabi_uldivmod' super.c:(.text+0x6920): undefined reference to `__aeabi_uldivmod' super.c:(.text+0x693c): undefined reference to `__aeabi_uldivmod' fs/btrfs/super.o:super.c:(.text+0x6958): more undefined references to `__aeabi_uldivmod' follow So far this is the only file that shows the behavior, so I'd propose to just work around it by marking the functions as 'static inline' that normally get inlined here. The reference to __aeabi_uldivmod comes from a div_u64() which has an optimization for a constant division that uses a straight '/' operator when the result should be known to the compiler. My interpretation is that as we turn off inlining, gcc still expects the result to be constant but fails to use that constant value. Link: https://lkml.kernel.org/r/20181103153941.1881966-1-arnd@arndb.de Reviewed-by: Nikolay Borisov Reviewed-by: Changbin Du Signed-off-by: Arnd Bergmann [ add the note ] Signed-off-by: David Sterba --- fs/btrfs/super.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index b362b45dd757..cbc9d0d2c12d 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1916,7 +1916,7 @@ restore: } /* Used to sort the devices by max_avail(descending sort) */ -static int btrfs_cmp_device_free_bytes(const void *dev_info1, +static inline int btrfs_cmp_device_free_bytes(const void *dev_info1, const void *dev_info2) { if (((struct btrfs_device_info *)dev_info1)->max_avail > @@ -1945,8 +1945,8 @@ static inline void btrfs_descending_sort_devices( * The helper to calc the free space on the devices that can be used to store * file data. */ -static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info, - u64 *free_bytes) +static inline int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info, + u64 *free_bytes) { struct btrfs_device_info *devices_info; struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; From 4222ea7100c0e37adace2790c8822758bbeee179 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 24 Oct 2018 10:13:03 +0100 Subject: [PATCH 168/356] Btrfs: fix deadlock on tree root leaf when finding free extent When we are writing out a free space cache, during the transaction commit phase, we can end up in a deadlock which results in a stack trace like the following: schedule+0x28/0x80 btrfs_tree_read_lock+0x8e/0x120 [btrfs] ? finish_wait+0x80/0x80 btrfs_read_lock_root_node+0x2f/0x40 [btrfs] btrfs_search_slot+0xf6/0x9f0 [btrfs] ? evict_refill_and_join+0xd0/0xd0 [btrfs] ? inode_insert5+0x119/0x190 btrfs_lookup_inode+0x3a/0xc0 [btrfs] ? kmem_cache_alloc+0x166/0x1d0 btrfs_iget+0x113/0x690 [btrfs] __lookup_free_space_inode+0xd8/0x150 [btrfs] lookup_free_space_inode+0x5b/0xb0 [btrfs] load_free_space_cache+0x7c/0x170 [btrfs] ? cache_block_group+0x72/0x3b0 [btrfs] cache_block_group+0x1b3/0x3b0 [btrfs] ? finish_wait+0x80/0x80 find_free_extent+0x799/0x1010 [btrfs] btrfs_reserve_extent+0x9b/0x180 [btrfs] btrfs_alloc_tree_block+0x1b3/0x4f0 [btrfs] __btrfs_cow_block+0x11d/0x500 [btrfs] btrfs_cow_block+0xdc/0x180 [btrfs] btrfs_search_slot+0x3bd/0x9f0 [btrfs] btrfs_lookup_inode+0x3a/0xc0 [btrfs] ? kmem_cache_alloc+0x166/0x1d0 btrfs_update_inode_item+0x46/0x100 [btrfs] cache_save_setup+0xe4/0x3a0 [btrfs] btrfs_start_dirty_block_groups+0x1be/0x480 [btrfs] btrfs_commit_transaction+0xcb/0x8b0 [btrfs] At cache_save_setup() we need to update the inode item of a block group's cache which is located in the tree root (fs_info->tree_root), which means that it may result in COWing a leaf from that tree. If that happens we need to find a free metadata extent and while looking for one, if we find a block group which was not cached yet we attempt to load its cache by calling cache_block_group(). However this function will try to load the inode of the free space cache, which requires finding the matching inode item in the tree root - if that inode item is located in the same leaf as the inode item of the space cache we are updating at cache_save_setup(), we end up in a deadlock, since we try to obtain a read lock on the same extent buffer that we previously write locked. So fix this by using the tree root's commit root when searching for a block group's free space cache inode item when we are attempting to load a free space cache. This is safe since block groups once loaded stay in memory forever, as well as their caches, so after they are first loaded we will never need to read their inode items again. For new block groups, once they are created they get their ->cached field set to BTRFS_CACHE_FINISHED meaning we will not need to read their inode item. Reported-by: Andrew Nelson Link: https://lore.kernel.org/linux-btrfs/CAPTELenq9x5KOWuQ+fa7h1r3nsJG8vyiTH8+ifjURc_duHh2Wg@mail.gmail.com/ Fixes: 9d66e233c704 ("Btrfs: load free space cache if it exists") Tested-by: Andrew Nelson Reviewed-by: Josef Bacik Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 3 +++ fs/btrfs/free-space-cache.c | 22 +++++++++++++++++++++- fs/btrfs/inode.c | 32 ++++++++++++++++++++++---------- 3 files changed, 46 insertions(+), 11 deletions(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 68ca41dbbef3..f7f955109d8b 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3163,6 +3163,9 @@ void btrfs_destroy_inode(struct inode *inode); int btrfs_drop_inode(struct inode *inode); int __init btrfs_init_cachep(void); void __cold btrfs_destroy_cachep(void); +struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location, + struct btrfs_root *root, int *new, + struct btrfs_path *path); struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, struct btrfs_root *root, int *was_new); struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 4ba0aedc878b..74aa552f4793 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -75,7 +75,8 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root, * sure NOFS is set to keep us from deadlocking. */ nofs_flag = memalloc_nofs_save(); - inode = btrfs_iget(fs_info->sb, &location, root, NULL); + inode = btrfs_iget_path(fs_info->sb, &location, root, NULL, path); + btrfs_release_path(path); memalloc_nofs_restore(nofs_flag); if (IS_ERR(inode)) return inode; @@ -838,6 +839,25 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info, path->search_commit_root = 1; path->skip_locking = 1; + /* + * We must pass a path with search_commit_root set to btrfs_iget in + * order to avoid a deadlock when allocating extents for the tree root. + * + * When we are COWing an extent buffer from the tree root, when looking + * for a free extent, at extent-tree.c:find_free_extent(), we can find + * block group without its free space cache loaded. When we find one + * we must load its space cache which requires reading its free space + * cache's inode item from the root tree. If this inode item is located + * in the same leaf that we started COWing before, then we end up in + * deadlock on the extent buffer (trying to read lock it when we + * previously write locked it). + * + * It's safe to read the inode item using the commit root because + * block groups, once loaded, stay in memory forever (until they are + * removed) as well as their space caches once loaded. New block groups + * once created get their ->cached field set to BTRFS_CACHE_FINISHED so + * we will never try to read their inode item while the fs is mounted. + */ inode = lookup_free_space_inode(fs_info, block_group, path); if (IS_ERR(inode)) { btrfs_free_path(path); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 55761b1519f5..e71daadd2f75 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3569,10 +3569,11 @@ static noinline int acls_after_inode_item(struct extent_buffer *leaf, /* * read an inode from the btree into the in-memory inode */ -static int btrfs_read_locked_inode(struct inode *inode) +static int btrfs_read_locked_inode(struct inode *inode, + struct btrfs_path *in_path) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_path *path; + struct btrfs_path *path = in_path; struct extent_buffer *leaf; struct btrfs_inode_item *inode_item; struct btrfs_root *root = BTRFS_I(inode)->root; @@ -3588,15 +3589,18 @@ static int btrfs_read_locked_inode(struct inode *inode) if (!ret) filled = true; - path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; + if (!path) { + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + } memcpy(&location, &BTRFS_I(inode)->location, sizeof(location)); ret = btrfs_lookup_inode(NULL, root, path, &location, 0); if (ret) { - btrfs_free_path(path); + if (path != in_path) + btrfs_free_path(path); return ret; } @@ -3721,7 +3725,8 @@ cache_acl: btrfs_ino(BTRFS_I(inode)), root->root_key.objectid, ret); } - btrfs_free_path(path); + if (path != in_path) + btrfs_free_path(path); if (!maybe_acls) cache_no_acl(inode); @@ -5643,8 +5648,9 @@ static struct inode *btrfs_iget_locked(struct super_block *s, /* Get an inode object given its location and corresponding root. * Returns in *is_new if the inode was read from disk */ -struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, - struct btrfs_root *root, int *new) +struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location, + struct btrfs_root *root, int *new, + struct btrfs_path *path) { struct inode *inode; @@ -5655,7 +5661,7 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, if (inode->i_state & I_NEW) { int ret; - ret = btrfs_read_locked_inode(inode); + ret = btrfs_read_locked_inode(inode, path); if (!ret) { inode_tree_add(inode); unlock_new_inode(inode); @@ -5677,6 +5683,12 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, return inode; } +struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, + struct btrfs_root *root, int *new) +{ + return btrfs_iget_path(s, location, root, new, NULL); +} + static struct inode *new_simple_dir(struct super_block *s, struct btrfs_key *key, struct btrfs_root *root) From 11023d3f5fdf89bba5e1142127701ca6e6014587 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 5 Nov 2018 11:14:05 +0000 Subject: [PATCH 169/356] Btrfs: fix infinite loop on inode eviction after deduplication of eof block If we attempt to deduplicate the last block of a file A into the middle of a file B, and file A's size is not a multiple of the block size, we end rounding the deduplication length to 0 bytes, to avoid the data corruption issue fixed by commit de02b9f6bb65 ("Btrfs: fix data corruption when deduplicating between different files"). However a length of zero will cause the insertion of an extent state with a start value greater (by 1) then the end value, leading to a corrupt extent state that will trigger a warning and cause chaos such as an infinite loop during inode eviction. Example trace: [96049.833585] ------------[ cut here ]------------ [96049.833714] WARNING: CPU: 0 PID: 24448 at fs/btrfs/extent_io.c:436 insert_state+0x101/0x120 [btrfs] [96049.833767] CPU: 0 PID: 24448 Comm: xfs_io Not tainted 4.19.0-rc7-btrfs-next-39 #1 [96049.833768] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.2-0-gf9626ccb91-prebuilt.qemu-project.org 04/01/2014 [96049.833780] RIP: 0010:insert_state+0x101/0x120 [btrfs] [96049.833783] RSP: 0018:ffffafd2c3707af0 EFLAGS: 00010282 [96049.833785] RAX: 0000000000000000 RBX: 000000000004dfff RCX: 0000000000000006 [96049.833786] RDX: 0000000000000007 RSI: ffff99045c143230 RDI: ffff99047b2168a0 [96049.833787] RBP: ffff990457851cd0 R08: 0000000000000001 R09: 0000000000000000 [96049.833787] R10: ffffafd2c3707ab8 R11: 0000000000000000 R12: ffff9903b93b12c8 [96049.833788] R13: 000000000004e000 R14: ffffafd2c3707b80 R15: ffffafd2c3707b78 [96049.833790] FS: 00007f5c14e7d700(0000) GS:ffff99047b200000(0000) knlGS:0000000000000000 [96049.833791] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [96049.833792] CR2: 00007f5c146abff8 CR3: 0000000115f4c004 CR4: 00000000003606f0 [96049.833795] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [96049.833796] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [96049.833796] Call Trace: [96049.833809] __set_extent_bit+0x46c/0x6a0 [btrfs] [96049.833823] lock_extent_bits+0x6b/0x210 [btrfs] [96049.833831] ? _raw_spin_unlock+0x24/0x30 [96049.833841] ? test_range_bit+0xdf/0x130 [btrfs] [96049.833853] lock_extent_range+0x8e/0x150 [btrfs] [96049.833864] btrfs_double_extent_lock+0x78/0xb0 [btrfs] [96049.833875] btrfs_extent_same_range+0x14e/0x550 [btrfs] [96049.833885] ? rcu_read_lock_sched_held+0x3f/0x70 [96049.833890] ? __kmalloc_node+0x2b0/0x2f0 [96049.833899] ? btrfs_dedupe_file_range+0x19a/0x280 [btrfs] [96049.833909] btrfs_dedupe_file_range+0x270/0x280 [btrfs] [96049.833916] vfs_dedupe_file_range_one+0xd9/0xe0 [96049.833919] vfs_dedupe_file_range+0x131/0x1b0 [96049.833924] do_vfs_ioctl+0x272/0x6e0 [96049.833927] ? __fget+0x113/0x200 [96049.833931] ksys_ioctl+0x70/0x80 [96049.833933] __x64_sys_ioctl+0x16/0x20 [96049.833937] do_syscall_64+0x60/0x1b0 [96049.833939] entry_SYSCALL_64_after_hwframe+0x49/0xbe [96049.833941] RIP: 0033:0x7f5c1478ddd7 [96049.833943] RSP: 002b:00007ffe15b196a8 EFLAGS: 00000202 ORIG_RAX: 0000000000000010 [96049.833945] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f5c1478ddd7 [96049.833946] RDX: 00005625ece322d0 RSI: 00000000c0189436 RDI: 0000000000000004 [96049.833947] RBP: 0000000000000000 R08: 00007f5c14a46f48 R09: 0000000000000040 [96049.833948] R10: 0000000000000541 R11: 0000000000000202 R12: 0000000000000000 [96049.833949] R13: 0000000000000000 R14: 0000000000000004 R15: 00005625ece322d0 [96049.833954] irq event stamp: 6196 [96049.833956] hardirqs last enabled at (6195): [] console_unlock+0x503/0x640 [96049.833958] hardirqs last disabled at (6196): [] trace_hardirqs_off_thunk+0x1a/0x1c [96049.833959] softirqs last enabled at (6114): [] __do_softirq+0x370/0x421 [96049.833964] softirqs last disabled at (6095): [] irq_exit+0xcd/0xe0 [96049.833965] ---[ end trace db7b05f01b7fa10c ]--- [96049.935816] R13: 0000000000000000 R14: 00005562e5259240 R15: 00007ffff092b910 [96049.935822] irq event stamp: 6584 [96049.935823] hardirqs last enabled at (6583): [] console_unlock+0x503/0x640 [96049.935825] hardirqs last disabled at (6584): [] trace_hardirqs_off_thunk+0x1a/0x1c [96049.935827] softirqs last enabled at (6328): [] __do_softirq+0x370/0x421 [96049.935828] softirqs last disabled at (6313): [] irq_exit+0xcd/0xe0 [96049.935829] ---[ end trace db7b05f01b7fa123 ]--- [96049.935840] ------------[ cut here ]------------ [96049.936065] WARNING: CPU: 1 PID: 24463 at fs/btrfs/extent_io.c:436 insert_state+0x101/0x120 [btrfs] [96049.936107] CPU: 1 PID: 24463 Comm: umount Tainted: G W 4.19.0-rc7-btrfs-next-39 #1 [96049.936108] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.2-0-gf9626ccb91-prebuilt.qemu-project.org 04/01/2014 [96049.936117] RIP: 0010:insert_state+0x101/0x120 [btrfs] [96049.936119] RSP: 0018:ffffafd2c3637bc0 EFLAGS: 00010282 [96049.936120] RAX: 0000000000000000 RBX: 000000000004dfff RCX: 0000000000000006 [96049.936121] RDX: 0000000000000007 RSI: ffff990445cf88e0 RDI: ffff99047b2968a0 [96049.936122] RBP: ffff990457851cd0 R08: 0000000000000001 R09: 0000000000000000 [96049.936123] R10: ffffafd2c3637b88 R11: 0000000000000000 R12: ffff9904574301e8 [96049.936124] R13: 000000000004e000 R14: ffffafd2c3637c50 R15: ffffafd2c3637c48 [96049.936125] FS: 00007fe4b87e72c0(0000) GS:ffff99047b280000(0000) knlGS:0000000000000000 [96049.936126] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [96049.936128] CR2: 00005562e52618d8 CR3: 00000001151c8005 CR4: 00000000003606e0 [96049.936129] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [96049.936131] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [96049.936131] Call Trace: [96049.936141] __set_extent_bit+0x46c/0x6a0 [btrfs] [96049.936154] lock_extent_bits+0x6b/0x210 [btrfs] [96049.936167] btrfs_evict_inode+0x1e1/0x5a0 [btrfs] [96049.936172] evict+0xbf/0x1c0 [96049.936174] dispose_list+0x51/0x80 [96049.936176] evict_inodes+0x193/0x1c0 [96049.936180] generic_shutdown_super+0x3f/0x110 [96049.936182] kill_anon_super+0xe/0x30 [96049.936189] btrfs_kill_super+0x13/0x100 [btrfs] [96049.936191] deactivate_locked_super+0x3a/0x70 [96049.936193] cleanup_mnt+0x3b/0x80 [96049.936195] task_work_run+0x93/0xc0 [96049.936198] exit_to_usermode_loop+0xfa/0x100 [96049.936201] do_syscall_64+0x17f/0x1b0 [96049.936202] entry_SYSCALL_64_after_hwframe+0x49/0xbe [96049.936204] RIP: 0033:0x7fe4b80cfb37 [96049.936206] RSP: 002b:00007ffff092b688 EFLAGS: 00000246 ORIG_RAX: 00000000000000a6 [96049.936207] RAX: 0000000000000000 RBX: 00005562e5259060 RCX: 00007fe4b80cfb37 [96049.936208] RDX: 0000000000000001 RSI: 0000000000000000 RDI: 00005562e525faa0 [96049.936209] RBP: 00005562e525faa0 R08: 00005562e525f770 R09: 0000000000000015 [96049.936210] R10: 00000000000006b4 R11: 0000000000000246 R12: 00007fe4b85d1e64 [96049.936211] R13: 0000000000000000 R14: 00005562e5259240 R15: 00007ffff092b910 [96049.936211] R13: 0000000000000000 R14: 00005562e5259240 R15: 00007ffff092b910 [96049.936216] irq event stamp: 6616 [96049.936219] hardirqs last enabled at (6615): [] console_unlock+0x503/0x640 [96049.936219] hardirqs last disabled at (6616): [] trace_hardirqs_off_thunk+0x1a/0x1c [96049.936222] softirqs last enabled at (6328): [] __do_softirq+0x370/0x421 [96049.936222] softirqs last disabled at (6313): [] irq_exit+0xcd/0xe0 [96049.936223] ---[ end trace db7b05f01b7fa124 ]--- The second stack trace, from inode eviction, is repeated forever due to the infinite loop during eviction. This is the same type of problem fixed way back in 2015 by commit 113e8283869b ("Btrfs: fix inode eviction infinite loop after extent_same ioctl") and commit ccccf3d67294 ("Btrfs: fix inode eviction infinite loop after cloning into it"). So fix this by returning immediately if the deduplication range length gets rounded down to 0 bytes, as there is nothing that needs to be done in such case. Example reproducer: $ mkfs.btrfs -f /dev/sdb $ mount /dev/sdb /mnt $ xfs_io -f -c "pwrite -S 0xe6 0 100" /mnt/foo $ xfs_io -f -c "pwrite -S 0xe6 0 1M" /mnt/bar # Unmount the filesystem and mount it again so that we start without any # extent state records when we ask for the deduplication. $ umount /mnt $ mount /dev/sdb /mnt $ xfs_io -c "dedupe /mnt/foo 0 500K 100" /mnt/bar # This unmount triggers the infinite loop. $ umount /mnt A test case for fstests will follow soon. Fixes: de02b9f6bb65 ("Btrfs: fix data corruption when deduplicating between different files") CC: # 4.19+ Reviewed-by: Nikolay Borisov Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index a990a9045139..ed3ba55f65ac 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3488,6 +3488,8 @@ static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 olen, const u64 sz = BTRFS_I(src)->root->fs_info->sectorsize; len = round_down(i_size_read(src), sz) - loff; + if (len == 0) + return 0; olen = len; } } From ac765f83f1397646c11092a032d4f62c3d478b81 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 5 Nov 2018 11:14:17 +0000 Subject: [PATCH 170/356] Btrfs: fix data corruption due to cloning of eof block We currently allow cloning a range from a file which includes the last block of the file even if the file's size is not aligned to the block size. This is fine and useful when the destination file has the same size, but when it does not and the range ends somewhere in the middle of the destination file, it leads to corruption because the bytes between the EOF and the end of the block have undefined data (when there is support for discard/trimming they have a value of 0x00). Example: $ mkfs.btrfs -f /dev/sdb $ mount /dev/sdb /mnt $ export foo_size=$((256 * 1024 + 100)) $ xfs_io -f -c "pwrite -S 0x3c 0 $foo_size" /mnt/foo $ xfs_io -f -c "pwrite -S 0xb5 0 1M" /mnt/bar $ xfs_io -c "reflink /mnt/foo 0 512K $foo_size" /mnt/bar $ od -A d -t x1 /mnt/bar 0000000 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 * 0524288 3c 3c 3c 3c 3c 3c 3c 3c 3c 3c 3c 3c 3c 3c 3c 3c * 0786528 3c 3c 3c 3c 00 00 00 00 00 00 00 00 00 00 00 00 0786544 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 * 0790528 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 * 1048576 The bytes in the range from 786532 (512Kb + 256Kb + 100 bytes) to 790527 (512Kb + 256Kb + 4Kb - 1) got corrupted, having now a value of 0x00 instead of 0xb5. This is similar to the problem we had for deduplication that got recently fixed by commit de02b9f6bb65 ("Btrfs: fix data corruption when deduplicating between different files"). Fix this by not allowing such operations to be performed and return the errno -EINVAL to user space. This is what XFS is doing as well at the VFS level. This change however now makes us return -EINVAL instead of -EOPNOTSUPP for cases where the source range maps to an inline extent and the destination range's end is smaller then the destination file's size, since the detection of inline extents is done during the actual process of dropping file extent items (at __btrfs_drop_extents()). Returning the -EINVAL error is done early on and solely based on the input parameters (offsets and length) and destination file's size. This makes us consistent with XFS and anyone else supporting cloning since this case is now checked at a higher level in the VFS and is where the -EINVAL will be returned from starting with kernel 4.20 (the VFS changed was introduced in 4.20-rc1 by commit 07d19dc9fbe9 ("vfs: avoid problematic remapping requests into partial EOF block"). So this change is more geared towards stable kernels, as it's unlikely the new VFS checks get removed intentionally. A test case for fstests follows soon, as well as an update to filter existing tests that expect -EOPNOTSUPP to accept -EINVAL as well. CC: # 4.4+ Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index ed3ba55f65ac..95f9625dccc4 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4279,9 +4279,17 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src, goto out_unlock; if (len == 0) olen = len = src->i_size - off; - /* if we extend to eof, continue to block boundary */ - if (off + len == src->i_size) + /* + * If we extend to eof, continue to block boundary if and only if the + * destination end offset matches the destination file's size, otherwise + * we would be corrupting data by placing the eof block into the middle + * of a file. + */ + if (off + len == src->i_size) { + if (!IS_ALIGNED(len, bs) && destoff + len < inode->i_size) + goto out_unlock; len = ALIGN(src->i_size, bs) - off; + } if (len == 0) { ret = 0; From 132bf6723749f7219c399831eeb286dbbb985429 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Tue, 6 Nov 2018 07:50:50 -0800 Subject: [PATCH 171/356] xfs: Fix error code in 'xfs_ioc_getbmap()' In this function, once 'buf' has been allocated, we unconditionally return 0. However, 'error' is set to some error codes in several error handling paths. Before commit 232b51948b99 ("xfs: simplify the xfs_getbmap interface") this was not an issue because all error paths were returning directly, but now that some cleanup at the end may be needed, we must propagate the error code. Fixes: 232b51948b99 ("xfs: simplify the xfs_getbmap interface") Signed-off-by: Christophe JAILLET Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 6e2c08f30f60..6ecdbb3af7de 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1608,7 +1608,7 @@ xfs_ioc_getbmap( error = 0; out_free_buf: kmem_free(buf); - return 0; + return error; } struct getfsmap_info { From bdec055bb9f262964c4f5cb330dab26646c345c6 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 6 Nov 2018 07:50:50 -0800 Subject: [PATCH 172/356] xfs: print buffer offsets when dumping corrupt buffers Use DUMP_PREFIX_OFFSET when printing hex dumps of corrupt buffers because modern Linux now prints a 32-bit hash of our 64-bit pointer when using DUMP_PREFIX_ADDRESS: 00000000b4bb4297: 00 00 00 00 00 00 00 00 3b ee 00 00 00 00 00 00 ........;....... 00000005ec77e26: 00 00 00 00 02 d0 5a 00 00 00 00 00 00 00 00 00 ......Z......... 000000015938018: 21 98 e8 b4 fd de 4c 07 bc ea 3c e5 ae b4 7c 48 !.....L...<...|H This is totally worthless for a sequential dump since we probably only care about tracking the buffer offsets and afaik there's no way to recover the actual pointer from the hashed value. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/xfs_message.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/xfs_message.c b/fs/xfs/xfs_message.c index 576c375ce12a..6b736ea58d35 100644 --- a/fs/xfs/xfs_message.c +++ b/fs/xfs/xfs_message.c @@ -107,5 +107,5 @@ assfail(char *expr, char *file, int line) void xfs_hex_dump(void *p, int length) { - print_hex_dump(KERN_ALERT, "", DUMP_PREFIX_ADDRESS, 16, 1, p, length, 1); + print_hex_dump(KERN_ALERT, "", DUMP_PREFIX_OFFSET, 16, 1, p, length, 1); } From 837514f7a4ca4aca06aec5caa5ff56d33ef06976 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 6 Nov 2018 07:50:50 -0800 Subject: [PATCH 173/356] xfs: fix overflow in xfs_attr3_leaf_verify generic/070 on 64k block size filesystems is failing with a verifier corruption on writeback or an attribute leaf block: [ 94.973083] XFS (pmem0): Metadata corruption detected at xfs_attr3_leaf_verify+0x246/0x260, xfs_attr3_leaf block 0x811480 [ 94.975623] XFS (pmem0): Unmount and run xfs_repair [ 94.976720] XFS (pmem0): First 128 bytes of corrupted metadata buffer: [ 94.978270] 000000004b2e7b45: 00 00 00 00 00 00 00 00 3b ee 00 00 00 00 00 00 ........;....... [ 94.980268] 000000006b1db90b: 00 00 00 00 00 81 14 80 00 00 00 00 00 00 00 00 ................ [ 94.982251] 00000000433f2407: 22 7b 5c 82 2d 5c 47 4c bb 31 1c 37 fa a9 ce d6 "{\.-\GL.1.7.... [ 94.984157] 0000000010dc7dfb: 00 00 00 00 00 81 04 8a 00 0a 18 e8 dd 94 01 00 ................ [ 94.986215] 00000000d5a19229: 00 a0 dc f4 fe 98 01 68 f0 d8 07 e0 00 00 00 00 .......h........ [ 94.988171] 00000000521df36c: 0c 2d 32 e2 fe 20 01 00 0c 2d 58 65 fe 0c 01 00 .-2.. ...-Xe.... [ 94.990162] 000000008477ae06: 0c 2d 5b 66 fe 8c 01 00 0c 2d 71 35 fe 7c 01 00 .-[f.....-q5.|.. [ 94.992139] 00000000a4a6bca6: 0c 2d 72 37 fc d4 01 00 0c 2d d8 b8 f0 90 01 00 .-r7.....-...... [ 94.994789] XFS (pmem0): xfs_do_force_shutdown(0x8) called from line 1453 of file fs/xfs/xfs_buf.c. Return address = ffffffff815365f3 This is failing this check: end = ichdr.freemap[i].base + ichdr.freemap[i].size; if (end < ichdr.freemap[i].base) >>>>> return __this_address; if (end > mp->m_attr_geo->blksize) return __this_address; And from the buffer output above, the freemap array is: freemap[0].base = 0x00a0 freemap[0].size = 0xdcf4 end = 0xdd94 freemap[1].base = 0xfe98 freemap[1].size = 0x0168 end = 0x10000 freemap[2].base = 0xf0d8 freemap[2].size = 0x07e0 end = 0xf8b8 These all look valid - the block size is 0x10000 and so from the last check in the above verifier fragment we know that the end of freemap[1] is valid. The problem is that end is declared as: uint16_t end; And (uint16_t)0x10000 = 0. So we have a verifier bug here, not a corruption. Fix the verifier to use uint32_t types for the check and hence avoid the overflow. Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=201577 Signed-off-by: Dave Chinner Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/libxfs/xfs_attr_leaf.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 6fc5425b1474..2652d00842d6 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -243,7 +243,7 @@ xfs_attr3_leaf_verify( struct xfs_mount *mp = bp->b_target->bt_mount; struct xfs_attr_leafblock *leaf = bp->b_addr; struct xfs_attr_leaf_entry *entries; - uint16_t end; + uint32_t end; /* must be 32bit - see below */ int i; xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, leaf); @@ -293,6 +293,11 @@ xfs_attr3_leaf_verify( /* * Quickly check the freemap information. Attribute data has to be * aligned to 4-byte boundaries, and likewise for the free space. + * + * Note that for 64k block size filesystems, the freemap entries cannot + * overflow as they are only be16 fields. However, when checking end + * pointer of the freemap, we have to be careful to detect overflows and + * so use uint32_t for those checks. */ for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) { if (ichdr.freemap[i].base > mp->m_attr_geo->blksize) @@ -303,7 +308,9 @@ xfs_attr3_leaf_verify( return __this_address; if (ichdr.freemap[i].size & 0x3) return __this_address; - end = ichdr.freemap[i].base + ichdr.freemap[i].size; + + /* be care of 16 bit overflows here */ + end = (uint32_t)ichdr.freemap[i].base + ichdr.freemap[i].size; if (end < ichdr.freemap[i].base) return __this_address; if (end > mp->m_attr_geo->blksize) From 7f4cedd882f7cae83177066c2b239ef457ce4a42 Mon Sep 17 00:00:00 2001 From: Giulio Benetti Date: Fri, 5 Oct 2018 23:59:50 +0200 Subject: [PATCH 174/356] drm/sun4i: tcon: fix check of tcon->panel null pointer Since tcon->panel is a pointer returned by of_drm_find_panel() need to check if it is not NULL, hence a valid pointer. IS_ERR() instead checks return error values, not NULL pointers. Substitute "if (!IS_ERR(tcon->panel))" with "if (tcon->panel)". Signed-off-by: Giulio Benetti Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20181005215951.99003-1-giulio.benetti@micronovasrl.com --- drivers/gpu/drm/sun4i/sun4i_lvds.c | 4 ++-- drivers/gpu/drm/sun4i/sun4i_rgb.c | 4 ++-- drivers/gpu/drm/sun4i/sun4i_tcon.c | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/sun4i/sun4i_lvds.c b/drivers/gpu/drm/sun4i/sun4i_lvds.c index af7dcb6da351..e7eb0d1e17be 100644 --- a/drivers/gpu/drm/sun4i/sun4i_lvds.c +++ b/drivers/gpu/drm/sun4i/sun4i_lvds.c @@ -75,7 +75,7 @@ static void sun4i_lvds_encoder_enable(struct drm_encoder *encoder) DRM_DEBUG_DRIVER("Enabling LVDS output\n"); - if (!IS_ERR(tcon->panel)) { + if (tcon->panel) { drm_panel_prepare(tcon->panel); drm_panel_enable(tcon->panel); } @@ -88,7 +88,7 @@ static void sun4i_lvds_encoder_disable(struct drm_encoder *encoder) DRM_DEBUG_DRIVER("Disabling LVDS output\n"); - if (!IS_ERR(tcon->panel)) { + if (tcon->panel) { drm_panel_disable(tcon->panel); drm_panel_unprepare(tcon->panel); } diff --git a/drivers/gpu/drm/sun4i/sun4i_rgb.c b/drivers/gpu/drm/sun4i/sun4i_rgb.c index bf068da6b12e..f4a22689eb54 100644 --- a/drivers/gpu/drm/sun4i/sun4i_rgb.c +++ b/drivers/gpu/drm/sun4i/sun4i_rgb.c @@ -135,7 +135,7 @@ static void sun4i_rgb_encoder_enable(struct drm_encoder *encoder) DRM_DEBUG_DRIVER("Enabling RGB output\n"); - if (!IS_ERR(tcon->panel)) { + if (tcon->panel) { drm_panel_prepare(tcon->panel); drm_panel_enable(tcon->panel); } @@ -148,7 +148,7 @@ static void sun4i_rgb_encoder_disable(struct drm_encoder *encoder) DRM_DEBUG_DRIVER("Disabling RGB output\n"); - if (!IS_ERR(tcon->panel)) { + if (tcon->panel) { drm_panel_disable(tcon->panel); drm_panel_unprepare(tcon->panel); } diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c index c78cd35a1294..e4b3bd0307ef 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.c +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c @@ -555,7 +555,7 @@ static void sun4i_tcon0_mode_set_rgb(struct sun4i_tcon *tcon, * Following code is a way to avoid quirks all around TCON * and DOTCLOCK drivers. */ - if (!IS_ERR(tcon->panel)) { + if (tcon->panel) { struct drm_panel *panel = tcon->panel; struct drm_connector *connector = panel->connector; struct drm_display_info display_info = connector->display_info; From a8939766c75c06b5a0ab691ecbba9347e4e520cf Mon Sep 17 00:00:00 2001 From: Giulio Benetti Date: Fri, 5 Oct 2018 23:59:51 +0200 Subject: [PATCH 175/356] drm/sun4i: tcon: prevent tcon->panel dereference if NULL If tcon->panel pointer is NULL, trying to dereference from it (i.e. tcon->panel->connector) will cause a null pointer dereference. Add tcon->panel null pointer check before calling sun4i_tcon0_mode_set_dithering(). Signed-off-by: Giulio Benetti Fixes: f11adcecbd5f ("drm/sun4i: tcon: Add dithering support for RGB565/RGB666 LCD panels") Reviewed-by: Chen-Yu Tsai Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20181005215951.99003-2-giulio.benetti@micronovasrl.com --- drivers/gpu/drm/sun4i/sun4i_tcon.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c index e4b3bd0307ef..f949287d926c 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.c +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c @@ -491,7 +491,8 @@ static void sun4i_tcon0_mode_set_rgb(struct sun4i_tcon *tcon, sun4i_tcon0_mode_set_common(tcon, mode); /* Set dithering if needed */ - sun4i_tcon0_mode_set_dithering(tcon, tcon->panel->connector); + if (tcon->panel) + sun4i_tcon0_mode_set_dithering(tcon, tcon->panel->connector); /* Adjust clock delay */ clk_delay = sun4i_tcon_get_clk_delay(mode, 0); From df5e31c204b34e8d9e5ec33f5b28e960c4f25e14 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Thu, 25 Oct 2018 16:05:36 +0300 Subject: [PATCH 176/356] drm/i915: Fix ilk+ watermarks when disabling pipes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We're no longer programming any watermarks when we're disabling a pipe. That means ilk_wm_merge() & co. will keep considering the any pipe that is getting disabled as still enabled. Thus we either get no LP1+ watermakrs (ilk-ivb), or we get suboptimal ones (hsw-bdw). This seems to have been broken by commit b6b178a77210 ("drm/i915: Calculate ironlake intermediate watermarks correctly, v2."). Before that we apparently had some difference between the intermediate and optimal watermarks and so we would program the optiomal ones. Now intermediate and optimal are identical for disabled pipes and so we don't program either. Fix this by programming the intermediate watermarks even for disabled pipes. We were already doing that for skl+. We'll leave out gmch platforms for now since those do the merging in a different manner and should work as is. We'll want to unify this eventually, but play it safe for now and just put in a FIXME. Cc: stable@vger.kernel.org Cc: Matt Roper Cc: Maarten Lankhorst Fixes: b6b178a77210 ("drm/i915: Calculate ironlake intermediate watermarks correctly, v2.") Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20181025130536.29024-1-ville.syrjala@linux.intel.com Reviewed-by: Maarten Lankhorst #irc (cherry picked from commit a748faea3bfd7fd1d1485bc1c426c7d460cc6503) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/intel_display.c | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index b8dfdbc9ca1f..23d8008a93bb 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -12768,17 +12768,12 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state) intel_check_cpu_fifo_underruns(dev_priv); intel_check_pch_fifo_underruns(dev_priv); - if (!new_crtc_state->active) { - /* - * Make sure we don't call initial_watermarks - * for ILK-style watermark updates. - * - * No clue what this is supposed to achieve. - */ - if (INTEL_GEN(dev_priv) >= 9) - dev_priv->display.initial_watermarks(intel_state, - to_intel_crtc_state(new_crtc_state)); - } + /* FIXME unify this for all platforms */ + if (!new_crtc_state->active && + !HAS_GMCH_DISPLAY(dev_priv) && + dev_priv->display.initial_watermarks) + dev_priv->display.initial_watermarks(intel_state, + to_intel_crtc_state(new_crtc_state)); } } From f98e8a572bddbf27032114127d2fcc78fa5e6a9d Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Delgado Date: Thu, 1 Nov 2018 14:15:49 +0100 Subject: [PATCH 177/356] clk: fixed-factor: fix of_node_get-put imbalance When the fixed factor clock is created by devicetree, of_clk_add_provider is called. Add a call to of_clk_del_provider in the remove function to balance it out. Reported-by: Alan Tull Fixes: 971451b3b15d ("clk: fixed-factor: Convert into a module platform driver") Signed-off-by: Ricardo Ribalda Delgado Signed-off-by: Stephen Boyd --- drivers/clk/clk-fixed-factor.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/clk/clk-fixed-factor.c b/drivers/clk/clk-fixed-factor.c index ef0ca9414f37..ff83e899df71 100644 --- a/drivers/clk/clk-fixed-factor.c +++ b/drivers/clk/clk-fixed-factor.c @@ -210,6 +210,7 @@ static int of_fixed_factor_clk_remove(struct platform_device *pdev) { struct clk *clk = platform_get_drvdata(pdev); + of_clk_del_provider(pdev->dev.of_node); clk_unregister_fixed_factor(clk); return 0; From 98ee3fc7ef8395f8b7a379e6608aee91efc66d48 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 6 Nov 2018 17:25:37 +0100 Subject: [PATCH 178/356] mtd: nand: Fix nanddev_pos_next_page() kernel-doc header Function name is wrong in the kernel-doc header. Fixes: 9c3736a3de21 ("mtd: nand: Add core infrastructure to deal with NAND devices") Signed-off-by: Boris Brezillon Reviewed-by: Miquel Raynal --- include/linux/mtd/nand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 78b86dea2f29..7f53ece2c039 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -568,7 +568,7 @@ static inline void nanddev_pos_next_eraseblock(struct nand_device *nand, } /** - * nanddev_pos_next_eraseblock() - Move a position to the next page + * nanddev_pos_next_page() - Move a position to the next page * @nand: NAND device * @pos: the position to update * From 313a06e636808387822af24c507cba92703568b1 Mon Sep 17 00:00:00 2001 From: Jeremy Linton Date: Mon, 5 Nov 2018 18:14:41 -0600 Subject: [PATCH 179/356] lib/raid6: Fix arm64 test build The lib/raid6/test fails to build the neon objects on arm64 because the correct machine type is 'aarch64'. Once this is correctly enabled, the neon recovery objects need to be added to the build. Reviewed-by: Ard Biesheuvel Signed-off-by: Jeremy Linton Signed-off-by: Catalin Marinas --- lib/raid6/test/Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/lib/raid6/test/Makefile b/lib/raid6/test/Makefile index 5d73f5cb4d8a..79777645cac9 100644 --- a/lib/raid6/test/Makefile +++ b/lib/raid6/test/Makefile @@ -27,7 +27,7 @@ ifeq ($(ARCH),arm) CFLAGS += -I../../../arch/arm/include -mfpu=neon HAS_NEON = yes endif -ifeq ($(ARCH),arm64) +ifeq ($(ARCH),aarch64) CFLAGS += -I../../../arch/arm64/include HAS_NEON = yes endif @@ -41,7 +41,7 @@ ifeq ($(IS_X86),yes) gcc -c -x assembler - >&/dev/null && \ rm ./-.o && echo -DCONFIG_AS_AVX512=1) else ifeq ($(HAS_NEON),yes) - OBJS += neon.o neon1.o neon2.o neon4.o neon8.o + OBJS += neon.o neon1.o neon2.o neon4.o neon8.o recov_neon.o recov_neon_inner.o CFLAGS += -DCONFIG_KERNEL_MODE_NEON=1 else HAS_ALTIVEC := $(shell printf '\#include \nvector int a;\n' |\ From 5d96c9342c23ee1d084802dcf064caa67ecaa45b Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Thu, 25 Oct 2018 18:37:28 -0600 Subject: [PATCH 180/356] acpi/nfit, x86/mce: Handle only uncorrectable machine checks The MCE handler for nfit devices is called for memory errors on a Non-Volatile DIMM and adds the error location to a 'badblocks' list. This list is used by the various NVDIMM drivers to avoid consuming known poison locations during IO. The MCE handler gets called for both corrected and uncorrectable errors. Until now, both kinds of errors have been added to the badblocks list. However, corrected memory errors indicate that the problem has already been fixed by hardware, and the resulting interrupt is merely a notification to Linux. As far as future accesses to that location are concerned, it is perfectly fine to use, and thus doesn't need to be included in the above badblocks list. Add a check in the nfit MCE handler to filter out corrected mce events, and only process uncorrectable errors. Fixes: 6839a6d96f4e ("nfit: do an ARS scrub on hitting a latent media error") Reported-by: Omar Avelar Signed-off-by: Vishal Verma Signed-off-by: Borislav Petkov CC: Arnd Bergmann CC: Dan Williams CC: Dave Jiang CC: elliott@hpe.com CC: "H. Peter Anvin" CC: Ingo Molnar CC: Len Brown CC: linux-acpi@vger.kernel.org CC: linux-edac CC: linux-nvdimm@lists.01.org CC: Qiuxu Zhuo CC: "Rafael J. Wysocki" CC: Ross Zwisler CC: stable CC: Thomas Gleixner CC: Tony Luck CC: x86-ml CC: Yazen Ghannam Link: http://lkml.kernel.org/r/20181026003729.8420-1-vishal.l.verma@intel.com --- arch/x86/include/asm/mce.h | 1 + arch/x86/kernel/cpu/mcheck/mce.c | 3 ++- drivers/acpi/nfit/mce.c | 4 ++-- 3 files changed, 5 insertions(+), 3 deletions(-) diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 4da9b1c58d28..dbd9fe2f6163 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -221,6 +221,7 @@ static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c) { return mce_am int mce_available(struct cpuinfo_x86 *c); bool mce_is_memory_error(struct mce *m); +bool mce_is_correctable(struct mce *m); DECLARE_PER_CPU(unsigned, mce_exception_count); DECLARE_PER_CPU(unsigned, mce_poll_count); diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 8c66d2fc8f81..77527b8ea982 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -534,7 +534,7 @@ bool mce_is_memory_error(struct mce *m) } EXPORT_SYMBOL_GPL(mce_is_memory_error); -static bool mce_is_correctable(struct mce *m) +bool mce_is_correctable(struct mce *m) { if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED) return false; @@ -547,6 +547,7 @@ static bool mce_is_correctable(struct mce *m) return true; } +EXPORT_SYMBOL_GPL(mce_is_correctable); static bool cec_add_mce(struct mce *m) { diff --git a/drivers/acpi/nfit/mce.c b/drivers/acpi/nfit/mce.c index e9626bf6ca29..7a51707f87e9 100644 --- a/drivers/acpi/nfit/mce.c +++ b/drivers/acpi/nfit/mce.c @@ -25,8 +25,8 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val, struct acpi_nfit_desc *acpi_desc; struct nfit_spa *nfit_spa; - /* We only care about memory errors */ - if (!mce_is_memory_error(mce)) + /* We only care about uncorrectable memory errors */ + if (!mce_is_memory_error(mce) || mce_is_correctable(mce)) return NOTIFY_DONE; /* From e8a308e5f47e545e0d41d0686c00f5f5217c5f61 Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Thu, 25 Oct 2018 18:37:29 -0600 Subject: [PATCH 181/356] acpi/nfit, x86/mce: Validate a MCE's address before using it The NFIT machine check handler uses the physical address from the mce structure, and compares it against information in the ACPI NFIT table to determine whether that location lies on an NVDIMM. The mce->addr field however may not always be valid, and this is indicated by the MCI_STATUS_ADDRV bit in the status field. Export mce_usable_address() which already performs validation for the address, and use it in the NFIT handler. Fixes: 6839a6d96f4e ("nfit: do an ARS scrub on hitting a latent media error") Reported-by: Robert Elliott Signed-off-by: Vishal Verma Signed-off-by: Borislav Petkov CC: Arnd Bergmann Cc: Dan Williams CC: Dave Jiang CC: elliott@hpe.com CC: "H. Peter Anvin" CC: Ingo Molnar CC: Len Brown CC: linux-acpi@vger.kernel.org CC: linux-edac CC: linux-nvdimm@lists.01.org CC: Qiuxu Zhuo CC: "Rafael J. Wysocki" CC: Ross Zwisler CC: stable CC: Thomas Gleixner CC: Tony Luck CC: x86-ml CC: Yazen Ghannam Link: http://lkml.kernel.org/r/20181026003729.8420-2-vishal.l.verma@intel.com --- arch/x86/include/asm/mce.h | 1 + arch/x86/kernel/cpu/mcheck/mce.c | 3 ++- drivers/acpi/nfit/mce.c | 4 ++++ 3 files changed, 7 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index dbd9fe2f6163..c1a812bd5a27 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -222,6 +222,7 @@ static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c) { return mce_am int mce_available(struct cpuinfo_x86 *c); bool mce_is_memory_error(struct mce *m); bool mce_is_correctable(struct mce *m); +int mce_usable_address(struct mce *m); DECLARE_PER_CPU(unsigned, mce_exception_count); DECLARE_PER_CPU(unsigned, mce_poll_count); diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 77527b8ea982..36d2696c9563 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -485,7 +485,7 @@ static void mce_report_event(struct pt_regs *regs) * be somewhat complicated (e.g. segment offset would require an instruction * parser). So only support physical addresses up to page granuality for now. */ -static int mce_usable_address(struct mce *m) +int mce_usable_address(struct mce *m) { if (!(m->status & MCI_STATUS_ADDRV)) return 0; @@ -505,6 +505,7 @@ static int mce_usable_address(struct mce *m) return 1; } +EXPORT_SYMBOL_GPL(mce_usable_address); bool mce_is_memory_error(struct mce *m) { diff --git a/drivers/acpi/nfit/mce.c b/drivers/acpi/nfit/mce.c index 7a51707f87e9..d6c1b10f6c25 100644 --- a/drivers/acpi/nfit/mce.c +++ b/drivers/acpi/nfit/mce.c @@ -29,6 +29,10 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val, if (!mce_is_memory_error(mce) || mce_is_correctable(mce)) return NOTIFY_DONE; + /* Verify the address reported in the MCE is valid. */ + if (!mce_usable_address(mce)) + return NOTIFY_DONE; + /* * mce->addr contains the physical addr accessed that caused the * machine check. We need to walk through the list of NFITs, and see From 042cb56478152b31c50bea8a784fc826891eb38e Mon Sep 17 00:00:00 2001 From: Tao Ren Date: Mon, 5 Nov 2018 14:35:40 -0800 Subject: [PATCH 182/356] net: phy: Allow BCM54616S PHY to setup internal TX/RX clock delay This patch allows users to enable/disable internal TX and/or RX clock delay for BCM54616S PHYs so as to satisfy RGMII timing specifications. On a particular platform, whether TX and/or RX clock delay is required depends on how PHY connected to the MAC IP. This requirement can be specified through "phy-mode" property in the platform device tree. The patch is inspired by commit 733336262b28 ("net: phy: Allow BCM5481x PHYs to setup internal TX/RX clock delay"). Signed-off-by: Tao Ren Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/broadcom.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index e86ea105c802..704537010453 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -92,7 +92,7 @@ static int bcm54612e_config_init(struct phy_device *phydev) return 0; } -static int bcm5481x_config(struct phy_device *phydev) +static int bcm54xx_config_clock_delay(struct phy_device *phydev) { int rc, val; @@ -429,7 +429,7 @@ static int bcm5481_config_aneg(struct phy_device *phydev) ret = genphy_config_aneg(phydev); /* Then we can set up the delay. */ - bcm5481x_config(phydev); + bcm54xx_config_clock_delay(phydev); if (of_property_read_bool(np, "enet-phy-lane-swap")) { /* Lane Swap - Undocumented register...magic! */ @@ -442,6 +442,19 @@ static int bcm5481_config_aneg(struct phy_device *phydev) return ret; } +static int bcm54616s_config_aneg(struct phy_device *phydev) +{ + int ret; + + /* Aneg firsly. */ + ret = genphy_config_aneg(phydev); + + /* Then we can set up the delay. */ + bcm54xx_config_clock_delay(phydev); + + return ret; +} + static int brcm_phy_setbits(struct phy_device *phydev, int reg, int set) { int val; @@ -636,6 +649,7 @@ static struct phy_driver broadcom_drivers[] = { .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, .config_init = bcm54xx_config_init, + .config_aneg = bcm54616s_config_aneg, .ack_interrupt = bcm_phy_ack_intr, .config_intr = bcm_phy_config_intr, }, { From d52888aa2753e3063a9d3a0c9f72f94aa9809c15 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 26 Oct 2018 15:28:54 +0300 Subject: [PATCH 183/356] x86/mm: Move LDT remap out of KASLR region on 5-level paging On 5-level paging the LDT remap area is placed in the middle of the KASLR randomization region and it can overlap with the direct mapping, the vmalloc or the vmap area. The LDT mapping is per mm, so it cannot be moved into the P4D page table next to the CPU_ENTRY_AREA without complicating PGD table allocation for 5-level paging. The 4 PGD slot gap just before the direct mapping is reserved for hypervisors, so it cannot be used. Move the direct mapping one slot deeper and use the resulting gap for the LDT remap area. The resulting layout is the same for 4 and 5 level paging. [ tglx: Massaged changelog ] Fixes: f55f0501cbf6 ("x86/pti: Put the LDT in its own PGD if PTI is on") Signed-off-by: Kirill A. Shutemov Signed-off-by: Thomas Gleixner Reviewed-by: Andy Lutomirski Cc: bp@alien8.de Cc: hpa@zytor.com Cc: dave.hansen@linux.intel.com Cc: peterz@infradead.org Cc: boris.ostrovsky@oracle.com Cc: jgross@suse.com Cc: bhe@redhat.com Cc: willy@infradead.org Cc: linux-mm@kvack.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20181026122856.66224-2-kirill.shutemov@linux.intel.com --- Documentation/x86/x86_64/mm.txt | 34 +++++++++++++------------ arch/x86/include/asm/page_64_types.h | 12 +++++---- arch/x86/include/asm/pgtable_64_types.h | 4 +-- arch/x86/xen/mmu_pv.c | 6 ++--- 4 files changed, 29 insertions(+), 27 deletions(-) diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt index 73aaaa3da436..804f9426ed17 100644 --- a/Documentation/x86/x86_64/mm.txt +++ b/Documentation/x86/x86_64/mm.txt @@ -34,23 +34,24 @@ __________________|____________|__________________|_________|___________________ ____________________________________________________________|___________________________________________________________ | | | | ffff800000000000 | -128 TB | ffff87ffffffffff | 8 TB | ... guard hole, also reserved for hypervisor - ffff880000000000 | -120 TB | ffffc7ffffffffff | 64 TB | direct mapping of all physical memory (page_offset_base) - ffffc80000000000 | -56 TB | ffffc8ffffffffff | 1 TB | ... unused hole + ffff880000000000 | -120 TB | ffff887fffffffff | 0.5 TB | LDT remap for PTI + ffff888000000000 | -119.5 TB | ffffc87fffffffff | 64 TB | direct mapping of all physical memory (page_offset_base) + ffffc88000000000 | -55.5 TB | ffffc8ffffffffff | 0.5 TB | ... unused hole ffffc90000000000 | -55 TB | ffffe8ffffffffff | 32 TB | vmalloc/ioremap space (vmalloc_base) ffffe90000000000 | -23 TB | ffffe9ffffffffff | 1 TB | ... unused hole ffffea0000000000 | -22 TB | ffffeaffffffffff | 1 TB | virtual memory map (vmemmap_base) ffffeb0000000000 | -21 TB | ffffebffffffffff | 1 TB | ... unused hole ffffec0000000000 | -20 TB | fffffbffffffffff | 16 TB | KASAN shadow memory +__________________|____________|__________________|_________|____________________________________________________________ + | + | Identical layout to the 56-bit one from here on: +____________________________________________________________|____________________________________________________________ + | | | | fffffc0000000000 | -4 TB | fffffdffffffffff | 2 TB | ... unused hole | | | | vaddr_end for KASLR fffffe0000000000 | -2 TB | fffffe7fffffffff | 0.5 TB | cpu_entry_area mapping - fffffe8000000000 | -1.5 TB | fffffeffffffffff | 0.5 TB | LDT remap for PTI + fffffe8000000000 | -1.5 TB | fffffeffffffffff | 0.5 TB | ... unused hole ffffff0000000000 | -1 TB | ffffff7fffffffff | 0.5 TB | %esp fixup stacks -__________________|____________|__________________|_________|____________________________________________________________ - | - | Identical layout to the 47-bit one from here on: -____________________________________________________________|____________________________________________________________ - | | | | ffffff8000000000 | -512 GB | ffffffeeffffffff | 444 GB | ... unused hole ffffffef00000000 | -68 GB | fffffffeffffffff | 64 GB | EFI region mapping space ffffffff00000000 | -4 GB | ffffffff7fffffff | 2 GB | ... unused hole @@ -83,7 +84,7 @@ Notes: __________________|____________|__________________|_________|___________________________________________________________ | | | | 0000800000000000 | +64 PB | ffff7fffffffffff | ~16K PB | ... huge, still almost 64 bits wide hole of non-canonical - | | | | virtual memory addresses up to the -128 TB + | | | | virtual memory addresses up to the -64 PB | | | | starting offset of kernel mappings. __________________|____________|__________________|_________|___________________________________________________________ | @@ -91,23 +92,24 @@ __________________|____________|__________________|_________|___________________ ____________________________________________________________|___________________________________________________________ | | | | ff00000000000000 | -64 PB | ff0fffffffffffff | 4 PB | ... guard hole, also reserved for hypervisor - ff10000000000000 | -60 PB | ff8fffffffffffff | 32 PB | direct mapping of all physical memory (page_offset_base) - ff90000000000000 | -28 PB | ff9fffffffffffff | 4 PB | LDT remap for PTI + ff10000000000000 | -60 PB | ff10ffffffffffff | 0.25 PB | LDT remap for PTI + ff11000000000000 | -59.75 PB | ff90ffffffffffff | 32 PB | direct mapping of all physical memory (page_offset_base) + ff91000000000000 | -27.75 PB | ff9fffffffffffff | 3.75 PB | ... unused hole ffa0000000000000 | -24 PB | ffd1ffffffffffff | 12.5 PB | vmalloc/ioremap space (vmalloc_base) ffd2000000000000 | -11.5 PB | ffd3ffffffffffff | 0.5 PB | ... unused hole ffd4000000000000 | -11 PB | ffd5ffffffffffff | 0.5 PB | virtual memory map (vmemmap_base) ffd6000000000000 | -10.5 PB | ffdeffffffffffff | 2.25 PB | ... unused hole ffdf000000000000 | -8.25 PB | fffffdffffffffff | ~8 PB | KASAN shadow memory - fffffc0000000000 | -4 TB | fffffdffffffffff | 2 TB | ... unused hole - | | | | vaddr_end for KASLR - fffffe0000000000 | -2 TB | fffffe7fffffffff | 0.5 TB | cpu_entry_area mapping - fffffe8000000000 | -1.5 TB | fffffeffffffffff | 0.5 TB | ... unused hole - ffffff0000000000 | -1 TB | ffffff7fffffffff | 0.5 TB | %esp fixup stacks __________________|____________|__________________|_________|____________________________________________________________ | | Identical layout to the 47-bit one from here on: ____________________________________________________________|____________________________________________________________ | | | | + fffffc0000000000 | -4 TB | fffffdffffffffff | 2 TB | ... unused hole + | | | | vaddr_end for KASLR + fffffe0000000000 | -2 TB | fffffe7fffffffff | 0.5 TB | cpu_entry_area mapping + fffffe8000000000 | -1.5 TB | fffffeffffffffff | 0.5 TB | ... unused hole + ffffff0000000000 | -1 TB | ffffff7fffffffff | 0.5 TB | %esp fixup stacks ffffff8000000000 | -512 GB | ffffffeeffffffff | 444 GB | ... unused hole ffffffef00000000 | -68 GB | fffffffeffffffff | 64 GB | EFI region mapping space ffffffff00000000 | -4 GB | ffffffff7fffffff | 2 GB | ... unused hole diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index cd0cf1c568b4..8f657286d599 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -33,12 +33,14 @@ /* * Set __PAGE_OFFSET to the most negative possible address + - * PGDIR_SIZE*16 (pgd slot 272). The gap is to allow a space for a - * hypervisor to fit. Choosing 16 slots here is arbitrary, but it's - * what Xen requires. + * PGDIR_SIZE*17 (pgd slot 273). + * + * The gap is to allow a space for LDT remap for PTI (1 pgd slot) and space for + * a hypervisor (16 slots). Choosing 16 slots for a hypervisor is arbitrary, + * but it's what Xen requires. */ -#define __PAGE_OFFSET_BASE_L5 _AC(0xff10000000000000, UL) -#define __PAGE_OFFSET_BASE_L4 _AC(0xffff880000000000, UL) +#define __PAGE_OFFSET_BASE_L5 _AC(0xff11000000000000, UL) +#define __PAGE_OFFSET_BASE_L4 _AC(0xffff888000000000, UL) #ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT #define __PAGE_OFFSET page_offset_base diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 04edd2d58211..84bd9bdc1987 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -111,9 +111,7 @@ extern unsigned int ptrs_per_p4d; */ #define MAXMEM (1UL << MAX_PHYSMEM_BITS) -#define LDT_PGD_ENTRY_L4 -3UL -#define LDT_PGD_ENTRY_L5 -112UL -#define LDT_PGD_ENTRY (pgtable_l5_enabled() ? LDT_PGD_ENTRY_L5 : LDT_PGD_ENTRY_L4) +#define LDT_PGD_ENTRY -240UL #define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT) #define LDT_END_ADDR (LDT_BASE_ADDR + PGDIR_SIZE) diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 0d7b3ae4960b..a5d7ed125337 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1905,7 +1905,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) init_top_pgt[0] = __pgd(0); /* Pre-constructed entries are in pfn, so convert to mfn */ - /* L4[272] -> level3_ident_pgt */ + /* L4[273] -> level3_ident_pgt */ /* L4[511] -> level3_kernel_pgt */ convert_pfn_mfn(init_top_pgt); @@ -1925,8 +1925,8 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) addr[0] = (unsigned long)pgd; addr[1] = (unsigned long)l3; addr[2] = (unsigned long)l2; - /* Graft it onto L4[272][0]. Note that we creating an aliasing problem: - * Both L4[272][0] and L4[511][510] have entries that point to the same + /* Graft it onto L4[273][0]. Note that we creating an aliasing problem: + * Both L4[273][0] and L4[511][510] have entries that point to the same * L2 (PMD) tables. Meaning that if you modify it in __va space * it will be also modified in the __ka space! (But if you just * modify the PMD table to point to other PTE's or none, then you From a0e6e0831c516860fc7f9be1db6c081fe902ebcf Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 26 Oct 2018 15:28:55 +0300 Subject: [PATCH 184/356] x86/ldt: Unmap PTEs for the slot before freeing LDT pages modify_ldt(2) leaves the old LDT mapped after switching over to the new one. The old LDT gets freed and the pages can be re-used. Leaving the mapping in place can have security implications. The mapping is present in the userspace page tables and Meltdown-like attacks can read these freed and possibly reused pages. It's relatively simple to fix: unmap the old LDT and flush TLB before freeing the old LDT memory. This further allows to avoid flushing the TLB in map_ldt_struct() as the slot is unmapped and flushed by unmap_ldt_struct() or has never been mapped at all. [ tglx: Massaged changelog and removed the needless line breaks ] Fixes: f55f0501cbf6 ("x86/pti: Put the LDT in its own PGD if PTI is on") Signed-off-by: Kirill A. Shutemov Signed-off-by: Thomas Gleixner Cc: bp@alien8.de Cc: hpa@zytor.com Cc: dave.hansen@linux.intel.com Cc: luto@kernel.org Cc: peterz@infradead.org Cc: boris.ostrovsky@oracle.com Cc: jgross@suse.com Cc: bhe@redhat.com Cc: willy@infradead.org Cc: linux-mm@kvack.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20181026122856.66224-3-kirill.shutemov@linux.intel.com --- arch/x86/kernel/ldt.c | 51 ++++++++++++++++++++++++++++++++----------- 1 file changed, 38 insertions(+), 13 deletions(-) diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index ab18e0884dc6..18e4525c5933 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -199,14 +199,6 @@ static void sanity_check_ldt_mapping(struct mm_struct *mm) /* * If PTI is enabled, this maps the LDT into the kernelmode and * usermode tables for the given mm. - * - * There is no corresponding unmap function. Even if the LDT is freed, we - * leave the PTEs around until the slot is reused or the mm is destroyed. - * This is harmless: the LDT is always in ordinary memory, and no one will - * access the freed slot. - * - * If we wanted to unmap freed LDTs, we'd also need to do a flush to make - * it useful, and the flush would slow down modify_ldt(). */ static int map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) @@ -214,8 +206,8 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) unsigned long va; bool is_vmalloc; spinlock_t *ptl; + int i, nr_pages; pgd_t *pgd; - int i; if (!static_cpu_has(X86_FEATURE_PTI)) return 0; @@ -238,7 +230,9 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) is_vmalloc = is_vmalloc_addr(ldt->entries); - for (i = 0; i * PAGE_SIZE < ldt->nr_entries * LDT_ENTRY_SIZE; i++) { + nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE); + + for (i = 0; i < nr_pages; i++) { unsigned long offset = i << PAGE_SHIFT; const void *src = (char *)ldt->entries + offset; unsigned long pfn; @@ -272,13 +266,39 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) /* Propagate LDT mapping to the user page-table */ map_ldt_struct_to_user(mm); - va = (unsigned long)ldt_slot_va(slot); - flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, PAGE_SHIFT, false); - ldt->slot = slot; return 0; } +static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt) +{ + unsigned long va; + int i, nr_pages; + + if (!ldt) + return; + + /* LDT map/unmap is only required for PTI */ + if (!static_cpu_has(X86_FEATURE_PTI)) + return; + + nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE); + + for (i = 0; i < nr_pages; i++) { + unsigned long offset = i << PAGE_SHIFT; + spinlock_t *ptl; + pte_t *ptep; + + va = (unsigned long)ldt_slot_va(ldt->slot) + offset; + ptep = get_locked_pte(mm, va, &ptl); + pte_clear(mm, va, ptep); + pte_unmap_unlock(ptep, ptl); + } + + va = (unsigned long)ldt_slot_va(ldt->slot); + flush_tlb_mm_range(mm, va, va + nr_pages * PAGE_SIZE, PAGE_SHIFT, false); +} + #else /* !CONFIG_PAGE_TABLE_ISOLATION */ static int @@ -286,6 +306,10 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) { return 0; } + +static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt) +{ +} #endif /* CONFIG_PAGE_TABLE_ISOLATION */ static void free_ldt_pgtables(struct mm_struct *mm) @@ -524,6 +548,7 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) } install_ldt(mm, new_ldt); + unmap_ldt_struct(mm, old_ldt); free_ldt_struct(old_ldt); error = 0; From b082f2dd80612015cd6d9d84e52099734ec9a0e1 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 26 Oct 2018 15:28:56 +0300 Subject: [PATCH 185/356] x86/ldt: Remove unused variable in map_ldt_struct() Splitting out the sanity check in map_ldt_struct() moved page table syncing into a separate function, which made the pgd variable unused. Remove it. [ tglx: Massaged changelog ] Fixes: 9bae3197e15d ("x86/ldt: Split out sanity check in map_ldt_struct()") Signed-off-by: Kirill A. Shutemov Signed-off-by: Thomas Gleixner Reviewed-by: Andy Lutomirski Cc: bp@alien8.de Cc: hpa@zytor.com Cc: dave.hansen@linux.intel.com Cc: peterz@infradead.org Cc: boris.ostrovsky@oracle.com Cc: jgross@suse.com Cc: bhe@redhat.com Cc: willy@infradead.org Cc: linux-mm@kvack.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20181026122856.66224-4-kirill.shutemov@linux.intel.com --- arch/x86/kernel/ldt.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index 18e4525c5933..6135ae8ce036 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -207,7 +207,6 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) bool is_vmalloc; spinlock_t *ptl; int i, nr_pages; - pgd_t *pgd; if (!static_cpu_has(X86_FEATURE_PTI)) return 0; @@ -221,13 +220,6 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) /* Check if the current mappings are sane */ sanity_check_ldt_mapping(mm); - /* - * Did we already have the top level entry allocated? We can't - * use pgd_none() for this because it doens't do anything on - * 4-level page table kernels. - */ - pgd = pgd_offset(mm, LDT_BASE_ADDR); - is_vmalloc = is_vmalloc_addr(ldt->entries); nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE); From a48777fdda7d13179979a889e1fb87655a783cc0 Mon Sep 17 00:00:00 2001 From: Eial Czerwacki Date: Mon, 5 Nov 2018 19:31:54 +0200 Subject: [PATCH 186/356] x86/vsmp: Remove dependency on pv_irq_ops vSMP dependency on pv_irq_ops has been removed some years ago, but the code still deals with pv_irq_ops. In short, "cap & ctl & (1 << 4)" is always returning 0, so all PARAVIRT/PARAVIRT_XXL code related to that can be removed. However, the rest of the code depends on CONFIG_PCI, so fix it accordingly. Rename set_vsmp_pv_ops to set_vsmp_ctl as the original name does not make sense anymore. Signed-off-by: Eial Czerwacki Signed-off-by: Thomas Gleixner Acked-by: Shai Fultheim Cc: Juergen Gross Link: https://lkml.kernel.org/r/1541439114-28297-1-git-send-email-eial@scalemp.com --- arch/x86/Kconfig | 1 - arch/x86/kernel/vsmp_64.c | 84 ++++----------------------------------- 2 files changed, 7 insertions(+), 78 deletions(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ba7e3464ee92..9d734f3c8234 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -525,7 +525,6 @@ config X86_VSMP bool "ScaleMP vSMP" select HYPERVISOR_GUEST select PARAVIRT - select PARAVIRT_XXL depends on X86_64 && PCI depends on X86_EXTENDED_PLATFORM depends on SMP diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c index 1eae5af491c2..891a75dbc131 100644 --- a/arch/x86/kernel/vsmp_64.c +++ b/arch/x86/kernel/vsmp_64.c @@ -26,65 +26,8 @@ #define TOPOLOGY_REGISTER_OFFSET 0x10 -#if defined CONFIG_PCI && defined CONFIG_PARAVIRT_XXL -/* - * Interrupt control on vSMPowered systems: - * ~AC is a shadow of IF. If IF is 'on' AC should be 'off' - * and vice versa. - */ - -asmlinkage __visible unsigned long vsmp_save_fl(void) -{ - unsigned long flags = native_save_fl(); - - if (!(flags & X86_EFLAGS_IF) || (flags & X86_EFLAGS_AC)) - flags &= ~X86_EFLAGS_IF; - return flags; -} -PV_CALLEE_SAVE_REGS_THUNK(vsmp_save_fl); - -__visible void vsmp_restore_fl(unsigned long flags) -{ - if (flags & X86_EFLAGS_IF) - flags &= ~X86_EFLAGS_AC; - else - flags |= X86_EFLAGS_AC; - native_restore_fl(flags); -} -PV_CALLEE_SAVE_REGS_THUNK(vsmp_restore_fl); - -asmlinkage __visible void vsmp_irq_disable(void) -{ - unsigned long flags = native_save_fl(); - - native_restore_fl((flags & ~X86_EFLAGS_IF) | X86_EFLAGS_AC); -} -PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_disable); - -asmlinkage __visible void vsmp_irq_enable(void) -{ - unsigned long flags = native_save_fl(); - - native_restore_fl((flags | X86_EFLAGS_IF) & (~X86_EFLAGS_AC)); -} -PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_enable); - -static unsigned __init vsmp_patch(u8 type, void *ibuf, - unsigned long addr, unsigned len) -{ - switch (type) { - case PARAVIRT_PATCH(irq.irq_enable): - case PARAVIRT_PATCH(irq.irq_disable): - case PARAVIRT_PATCH(irq.save_fl): - case PARAVIRT_PATCH(irq.restore_fl): - return paravirt_patch_default(type, ibuf, addr, len); - default: - return native_patch(type, ibuf, addr, len); - } - -} - -static void __init set_vsmp_pv_ops(void) +#ifdef CONFIG_PCI +static void __init set_vsmp_ctl(void) { void __iomem *address; unsigned int cap, ctl, cfg; @@ -109,28 +52,12 @@ static void __init set_vsmp_pv_ops(void) } #endif - if (cap & ctl & (1 << 4)) { - /* Setup irq ops and turn on vSMP IRQ fastpath handling */ - pv_ops.irq.irq_disable = PV_CALLEE_SAVE(vsmp_irq_disable); - pv_ops.irq.irq_enable = PV_CALLEE_SAVE(vsmp_irq_enable); - pv_ops.irq.save_fl = PV_CALLEE_SAVE(vsmp_save_fl); - pv_ops.irq.restore_fl = PV_CALLEE_SAVE(vsmp_restore_fl); - pv_ops.init.patch = vsmp_patch; - ctl &= ~(1 << 4); - } writel(ctl, address + 4); ctl = readl(address + 4); pr_info("vSMP CTL: control set to:0x%08x\n", ctl); early_iounmap(address, 8); } -#else -static void __init set_vsmp_pv_ops(void) -{ -} -#endif - -#ifdef CONFIG_PCI static int is_vsmp = -1; static void __init detect_vsmp_box(void) @@ -164,11 +91,14 @@ static int is_vsmp_box(void) { return 0; } +static void __init set_vsmp_ctl(void) +{ +} #endif static void __init vsmp_cap_cpus(void) { -#if !defined(CONFIG_X86_VSMP) && defined(CONFIG_SMP) +#if !defined(CONFIG_X86_VSMP) && defined(CONFIG_SMP) && defined(CONFIG_PCI) void __iomem *address; unsigned int cfg, topology, node_shift, maxcpus; @@ -221,6 +151,6 @@ void __init vsmp_init(void) vsmp_cap_cpus(); - set_vsmp_pv_ops(); + set_vsmp_ctl(); return; } From 86a484bda787d542d4a968bd7742bcf844c8adb2 Mon Sep 17 00:00:00 2001 From: Leo Li Date: Tue, 30 Oct 2018 15:09:08 -0400 Subject: [PATCH 187/356] drm/amd: Update atom_smu_info_v3_3 structure Mainly adding the WAFL spread spectrum info, for adjusting display clocks when XGMI is enabled. Signed-off-by: Leo Li Acked-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/include/atomfirmware.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h index d2e7c0fa96c2..8eb0bb241210 100644 --- a/drivers/gpu/drm/amd/include/atomfirmware.h +++ b/drivers/gpu/drm/amd/include/atomfirmware.h @@ -1325,7 +1325,7 @@ struct atom_smu_info_v3_3 { struct atom_common_table_header table_header; uint8_t smuip_min_ver; uint8_t smuip_max_ver; - uint8_t smu_rsd1; + uint8_t waflclk_ss_mode; uint8_t gpuclk_ss_mode; uint16_t sclk_ss_percentage; uint16_t sclk_ss_rate_10hz; @@ -1355,7 +1355,10 @@ struct atom_smu_info_v3_3 { uint32_t syspll3_1_vco_freq_10khz; uint32_t bootup_fclk_10khz; uint32_t bootup_waflclk_10khz; - uint32_t reserved[3]; + uint32_t smu_info_caps; + uint16_t waflclk_ss_percentage; // in unit of 0.001% + uint16_t smuinitoffset; + uint32_t reserved; }; /* From ce317dd9f809c8da9656c88761e30f0a82a8c2e6 Mon Sep 17 00:00:00 2001 From: Anirudh Venkataramanan Date: Fri, 26 Oct 2018 10:40:50 -0700 Subject: [PATCH 188/356] ice: Set carrier state and start/stop queues in rebuild Set the carrier state post rebuild by querying the link status. Also start/stop queues based on link status. Signed-off-by: Anirudh Venkataramanan Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ice/ice_main.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 05993451147a..6d31ffb64940 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3296,7 +3296,7 @@ static void ice_rebuild(struct ice_pf *pf) struct device *dev = &pf->pdev->dev; struct ice_hw *hw = &pf->hw; enum ice_status ret; - int err; + int err, i; if (test_bit(__ICE_DOWN, pf->state)) goto clear_recovery; @@ -3370,6 +3370,22 @@ static void ice_rebuild(struct ice_pf *pf) } ice_reset_all_vfs(pf, true); + + for (i = 0; i < pf->num_alloc_vsi; i++) { + bool link_up; + + if (!pf->vsi[i] || pf->vsi[i]->type != ICE_VSI_PF) + continue; + ice_get_link_status(pf->vsi[i]->port_info, &link_up); + if (link_up) { + netif_carrier_on(pf->vsi[i]->netdev); + netif_tx_wake_all_queues(pf->vsi[i]->netdev); + } else { + netif_carrier_off(pf->vsi[i]->netdev); + netif_tx_stop_all_queues(pf->vsi[i]->netdev); + } + } + /* if we get here, reset flow is successful */ clear_bit(__ICE_RESET_FAILED, pf->state); return; From afd9d4ab58db20029a75cf82f23b6a5641cd7d6f Mon Sep 17 00:00:00 2001 From: Anirudh Venkataramanan Date: Fri, 26 Oct 2018 10:40:51 -0700 Subject: [PATCH 189/356] ice: Check for reset in progress during remove The remove path does not currently check to see if a reset is in progress before proceeding. This can cause a resource collision resulting in various types of errors. Check for reset in progress and wait for a reasonable amount of time before allowing the remove to progress. Signed-off-by: Dave Ertman Signed-off-by: Anirudh Venkataramanan Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ice/ice.h | 2 ++ drivers/net/ethernet/intel/ice/ice_main.c | 6 ++++++ 2 files changed, 8 insertions(+) diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 4c4b5717a627..e5b37fa60884 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -76,6 +76,8 @@ extern const char ice_drv_ver[]; #define ICE_MIN_INTR_PER_VF (ICE_MIN_QS_PER_VF + 1) #define ICE_DFLT_INTR_PER_VF (ICE_DFLT_QS_PER_VF + 1) +#define ICE_MAX_RESET_WAIT 20 + #define ICE_VSIQF_HKEY_ARRAY_SIZE ((VSIQF_HKEY_MAX_INDEX + 1) * 4) #define ICE_DFLT_NETIF_M (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 6d31ffb64940..aee22f11a41a 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2182,6 +2182,12 @@ static void ice_remove(struct pci_dev *pdev) if (!pf) return; + for (i = 0; i < ICE_MAX_RESET_WAIT; i++) { + if (!ice_is_reset_in_progress(pf->state)) + break; + msleep(100); + } + set_bit(__ICE_DOWN, pf->state); ice_service_task_stop(pf); From 0f5d4c21a50716f8bd4e220544b82dca7408d113 Mon Sep 17 00:00:00 2001 From: Akeem G Abodunrin Date: Fri, 26 Oct 2018 10:40:52 -0700 Subject: [PATCH 190/356] ice: Fix dead device link issue with flow control Setting Rx or Tx pause parameter currently results in link loss on the interface, requiring the platform/host to be cold power cycled. Fix it. Signed-off-by: Akeem G Abodunrin Signed-off-by: Anirudh Venkataramanan Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ice/ice_ethtool.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 96923580f2a6..648acdb4c644 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -1517,10 +1517,15 @@ ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) } if (!test_bit(__ICE_DOWN, pf->state)) { - /* Give it a little more time to try to come back */ + /* Give it a little more time to try to come back. If still + * down, restart autoneg link or reinitialize the interface. + */ msleep(75); if (!test_bit(__ICE_DOWN, pf->state)) return ice_nway_reset(netdev); + + ice_down(vsi); + ice_up(vsi); } return err; From 33e055fcc26909b1d66b5d1f334aee38356068d7 Mon Sep 17 00:00:00 2001 From: Victor Raj Date: Fri, 26 Oct 2018 10:40:53 -0700 Subject: [PATCH 191/356] ice: Free VSI contexts during for unload In the unload path, all VSIs are freed. Also free the related VSI contexts to prevent memory leaks. Signed-off-by: Victor Raj Signed-off-by: Anirudh Venkataramanan Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ice/ice_common.c | 3 +++ drivers/net/ethernet/intel/ice/ice_switch.c | 12 ++++++++++++ drivers/net/ethernet/intel/ice/ice_switch.h | 2 ++ 3 files changed, 17 insertions(+) diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 8cd6a2401fd9..554fd707a6d6 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -811,6 +811,9 @@ void ice_deinit_hw(struct ice_hw *hw) /* Attempt to disable FW logging before shutting down control queues */ ice_cfg_fw_log(hw, false); ice_shutdown_all_ctrlq(hw); + + /* Clear VSI contexts if not already cleared */ + ice_clear_all_vsi_ctx(hw); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 33403f39f1b3..40c9c6558956 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -347,6 +347,18 @@ static void ice_clear_vsi_ctx(struct ice_hw *hw, u16 vsi_handle) } } +/** + * ice_clear_all_vsi_ctx - clear all the VSI context entries + * @hw: pointer to the hw struct + */ +void ice_clear_all_vsi_ctx(struct ice_hw *hw) +{ + u16 i; + + for (i = 0; i < ICE_MAX_VSI; i++) + ice_clear_vsi_ctx(hw, i); +} + /** * ice_add_vsi - add VSI context to the hardware and VSI handle list * @hw: pointer to the hw struct diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index b88d96a1ef69..d5ef0bd58bf9 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -190,6 +190,8 @@ ice_update_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, struct ice_sq_cd *cd); bool ice_is_vsi_valid(struct ice_hw *hw, u16 vsi_handle); struct ice_vsi_ctx *ice_get_vsi_ctx(struct ice_hw *hw, u16 vsi_handle); +void ice_clear_all_vsi_ctx(struct ice_hw *hw); +/* Switch config */ enum ice_status ice_get_initial_sw_cfg(struct ice_hw *hw); /* Switch/bridge related commands */ From 9ecd25c26810a61b9c3abc6c73de32dca6da96e1 Mon Sep 17 00:00:00 2001 From: Anirudh Venkataramanan Date: Fri, 26 Oct 2018 10:40:54 -0700 Subject: [PATCH 192/356] ice: Remove duplicate addition of VLANs in replay path ice_restore_vlan and active_vlans were originally put in place to reprogram VLAN filters in the replay path. This is now done as part of the much broader VSI rebuild/replay framework. So remove both ice_restore_vlan and active_vlans Signed-off-by: Anirudh Venkataramanan Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ice/ice.h | 1 - drivers/net/ethernet/intel/ice/ice_main.c | 42 +++---------------- .../net/ethernet/intel/ice/ice_virtchnl_pf.c | 2 - 3 files changed, 6 insertions(+), 39 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index e5b37fa60884..1639e955f158 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -191,7 +191,6 @@ struct ice_vsi { u64 tx_linearize; DECLARE_BITMAP(state, __ICE_STATE_NBITS); DECLARE_BITMAP(flags, ICE_VSI_FLAG_NBITS); - unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; unsigned int current_netdev_flags; u32 tx_restart; u32 tx_busy; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index aee22f11a41a..338abb1b9233 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -1622,7 +1622,6 @@ static int ice_vlan_rx_add_vid(struct net_device *netdev, { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; - int ret; if (vid >= VLAN_N_VID) { netdev_err(netdev, "VLAN id requested %d is out of range %d\n", @@ -1635,7 +1634,8 @@ static int ice_vlan_rx_add_vid(struct net_device *netdev, /* Enable VLAN pruning when VLAN 0 is added */ if (unlikely(!vid)) { - ret = ice_cfg_vlan_pruning(vsi, true); + int ret = ice_cfg_vlan_pruning(vsi, true); + if (ret) return ret; } @@ -1644,12 +1644,7 @@ static int ice_vlan_rx_add_vid(struct net_device *netdev, * needed to continue allowing all untagged packets since VLAN prune * list is applied to all packets by the switch */ - ret = ice_vsi_add_vlan(vsi, vid); - - if (!ret) - set_bit(vid, vsi->active_vlans); - - return ret; + return ice_vsi_add_vlan(vsi, vid); } /** @@ -1677,8 +1672,6 @@ static int ice_vlan_rx_kill_vid(struct net_device *netdev, if (status) return status; - clear_bit(vid, vsi->active_vlans); - /* Disable VLAN pruning when VLAN 0 is removed */ if (unlikely(!vid)) status = ice_cfg_vlan_pruning(vsi, false); @@ -2515,31 +2508,6 @@ static int ice_vsi_vlan_setup(struct ice_vsi *vsi) return ret; } -/** - * ice_restore_vlan - Reinstate VLANs when vsi/netdev comes back up - * @vsi: the VSI being brought back up - */ -static int ice_restore_vlan(struct ice_vsi *vsi) -{ - int err; - u16 vid; - - if (!vsi->netdev) - return -EINVAL; - - err = ice_vsi_vlan_setup(vsi); - if (err) - return err; - - for_each_set_bit(vid, vsi->active_vlans, VLAN_N_VID) { - err = ice_vlan_rx_add_vid(vsi->netdev, htons(ETH_P_8021Q), vid); - if (err) - break; - } - - return err; -} - /** * ice_vsi_cfg - Setup the VSI * @vsi: the VSI being configured @@ -2552,7 +2520,9 @@ static int ice_vsi_cfg(struct ice_vsi *vsi) if (vsi->netdev) { ice_set_rx_mode(vsi->netdev); - err = ice_restore_vlan(vsi); + + err = ice_vsi_vlan_setup(vsi); + if (err) return err; } diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index 45f10f8f01dc..9576b958622b 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -2171,7 +2171,6 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) if (!ice_vsi_add_vlan(vsi, vid)) { vf->num_vlan++; - set_bit(vid, vsi->active_vlans); /* Enable VLAN pruning when VLAN 0 is added */ if (unlikely(!vid)) @@ -2190,7 +2189,6 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) */ if (!ice_vsi_kill_vlan(vsi, vid)) { vf->num_vlan--; - clear_bit(vid, vsi->active_vlans); /* Disable VLAN pruning when removing VLAN 0 */ if (unlikely(!vid)) From 58297dd133f64ea028e7d52dd00cd9ff8aa4479f Mon Sep 17 00:00:00 2001 From: Md Fahad Iqbal Polash Date: Fri, 26 Oct 2018 10:40:55 -0700 Subject: [PATCH 193/356] ice: Fix flags for port VLAN According to the spec, whenever insert PVID field is set, the VLAN driver insertion mode should be set to 01b which isn't done currently. Fix it. Signed-off-by: Md Fahad Iqbal Polash Signed-off-by: Anirudh Venkataramanan Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index 9576b958622b..e71065f9d391 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -348,7 +348,7 @@ static int ice_vsi_set_pvid(struct ice_vsi *vsi, u16 vid) struct ice_vsi_ctx ctxt = { 0 }; enum ice_status status; - ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_TAGGED | + ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_UNTAGGED | ICE_AQ_VSI_PVLAN_INSERT_PVID | ICE_AQ_VSI_VLAN_EMOD_STR; ctxt.info.pvid = cpu_to_le16(vid); From 31082519c11b01fe1fb6dd512055f252812c1508 Mon Sep 17 00:00:00 2001 From: Anirudh Venkataramanan Date: Fri, 26 Oct 2018 10:40:56 -0700 Subject: [PATCH 194/356] ice: Fix typo in error message Print should say "Enabling" instead of "Enaabling" Signed-off-by: Akeem G Abodunrin Signed-off-by: Anirudh Venkataramanan Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ice/ice_lib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 5bacad01f0c9..c604a44c8cfb 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -1997,7 +1997,7 @@ int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena) status = ice_update_vsi(&vsi->back->hw, vsi->idx, ctxt, NULL); if (status) { netdev_err(vsi->netdev, "%sabling VLAN pruning on VSI handle: %d, VSI HW ID: %d failed, err = %d, aq_err = %d\n", - ena ? "Ena" : "Dis", vsi->idx, vsi->vsi_num, status, + ena ? "En" : "Dis", vsi->idx, vsi->vsi_num, status, vsi->back->hw.adminq.sq_last_status); goto err_out; } From 25525b69bb44a628841492f44a5a8e74f34724f4 Mon Sep 17 00:00:00 2001 From: Dave Ertman Date: Fri, 26 Oct 2018 10:40:57 -0700 Subject: [PATCH 195/356] ice: Fix napi delete calls for remove In the remove path, the vsi->netdev is being set to NULL before the call to free vectors. This is causing the netif_napi_del call to never be made. Add a call to ice_napi_del to the same location as the calls to unregister_netdev and just prior to them. This will use the reverse flow as the register and netif_napi_add calls. Signed-off-by: Dave Ertman Signed-off-by: Anirudh Venkataramanan Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ice/ice.h | 1 + drivers/net/ethernet/intel/ice/ice_lib.c | 1 + drivers/net/ethernet/intel/ice/ice_main.c | 2 +- 3 files changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 1639e955f158..b8548370f1c7 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -370,5 +370,6 @@ int ice_set_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size); int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size); void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size); void ice_print_link_msg(struct ice_vsi *vsi, bool isup); +void ice_napi_del(struct ice_vsi *vsi); #endif /* _ICE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index c604a44c8cfb..1041fa2a7767 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -2458,6 +2458,7 @@ int ice_vsi_release(struct ice_vsi *vsi) * on this wq */ if (vsi->netdev && !ice_is_reset_in_progress(pf->state)) { + ice_napi_del(vsi); unregister_netdev(vsi->netdev); free_netdev(vsi->netdev); vsi->netdev = NULL; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 338abb1b9233..82f49dbd762c 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -1465,7 +1465,7 @@ skip_req_irq: * ice_napi_del - Remove NAPI handler for the VSI * @vsi: VSI for which NAPI handler is to be removed */ -static void ice_napi_del(struct ice_vsi *vsi) +void ice_napi_del(struct ice_vsi *vsi) { int v_idx; From c585ea42ec75e8d3afa278b7095d9f0dd6ee515b Mon Sep 17 00:00:00 2001 From: Brett Creeley Date: Fri, 26 Oct 2018 10:40:58 -0700 Subject: [PATCH 196/356] ice: Fix tx_timeout in PF driver Prior to this commit the driver was running into tx_timeouts when a queue was stressed enough. This was happening because the HW tail and SW tail (NTU) were incorrectly out of sync. Consequently this was causing the HW head to collide with the HW tail, which to the hardware means that all descriptors posted for Tx have been processed. Due to the Tx logic used in the driver SW tail and HW tail are allowed to be out of sync. This is done as an optimization because it allows the driver to write HW tail as infrequently as possible, while still updating the SW tail index to keep track. However, there are situations where this results in the tail never getting updated, resulting in Tx timeouts. Tx HW tail write condition: if (netif_xmit_stopped(txring_txq(tx_ring) || !skb->xmit_more) writel(sw_tail, tx_ring->tail); An issue was found in the Tx logic that was causing the afore mentioned condition for updating HW tail to never happen, causing tx_timeouts. In ice_xmit_frame_ring we calculate how many descriptors we need for the Tx transaction based on the skb the kernel hands us. This is then passed into ice_maybe_stop_tx along with some extra padding to determine if we have enough descriptors available for this transaction. If we don't then we return -EBUSY to the stack, otherwise we move on and eventually prepare the Tx descriptors accordingly in ice_tx_map and set next_to_watch. In ice_tx_map we make another call to ice_maybe_stop_tx with a value of MAX_SKB_FRAGS + 4. The key here is that this value is possibly less than the value we sent in the first call to ice_maybe_stop_tx in ice_xmit_frame_ring. Now, if the number of unused descriptors is between MAX_SKB_FRAGS + 4 and the value used in the first call to ice_maybe_stop_tx in ice_xmit_frame_ring then we do not update the HW tail because of the "Tx HW tail write condition" above. This is because in ice_maybe_stop_tx we return success from ice_maybe_stop_tx instead of calling __ice_maybe_stop_tx and subsequently calling netif_stop_subqueue, which sets the __QUEUE_STATE_DEV_XOFF bit. This bit is then checked in the "Tx HW tail write condition" by calling netif_xmit_stopped and subsequently updating HW tail if the afore mentioned bit is set. In ice_clean_tx_irq, if next_to_watch is not NULL, we end up cleaning the descriptors that HW sets the DD bit on and we have the budget. The HW head will eventually run into the HW tail in response to the description in the paragraph above. The next time through ice_xmit_frame_ring we make the initial call to ice_maybe_stop_tx with another skb from the stack. This time we do not have enough descriptors available and we return NETDEV_TX_BUSY to the stack and end up setting next_to_watch to NULL. This is where we are stuck. In ice_clean_tx_irq we never clean anything because next_to_watch is always NULL and in ice_xmit_frame_ring we never update HW tail because we already return NETDEV_TX_BUSY to the stack and eventually we hit a tx_timeout. This issue was fixed by making sure that the second call to ice_maybe_stop_tx in ice_tx_map is passed a value that is >= the value that was used on the initial call to ice_maybe_stop_tx in ice_xmit_frame_ring. This was done by adding the following defines to make the logic more clear and to reduce the chance of mucking this up again: ICE_CACHE_LINE_BYTES 64 ICE_DESCS_PER_CACHE_LINE (ICE_CACHE_LINE_BYTES / \ sizeof(struct ice_tx_desc)) ICE_DESCS_FOR_CTX_DESC 1 ICE_DESCS_FOR_SKB_DATA_PTR 1 The ICE_CACHE_LINE_BYTES being 64 is an assumption being made so we don't have to figure this out on every pass through the Tx path. Instead I added a sanity check in ice_probe to verify cache line size and print a message if it's not 64 Bytes. This will make it easier to file issues if they are seen when the cache line size is not 64 Bytes when reading from the GLPCI_CNF2 register. Signed-off-by: Brett Creeley Signed-off-by: Anirudh Venkataramanan Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- .../net/ethernet/intel/ice/ice_hw_autogen.h | 2 ++ drivers/net/ethernet/intel/ice/ice_main.c | 18 ++++++++++++++++++ drivers/net/ethernet/intel/ice/ice_txrx.c | 9 +++++---- drivers/net/ethernet/intel/ice/ice_txrx.h | 17 +++++++++++++++-- 4 files changed, 40 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index 5fdea6ec7675..596b9fb1c510 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -242,6 +242,8 @@ #define GLNVM_ULD 0x000B6008 #define GLNVM_ULD_CORER_DONE_M BIT(3) #define GLNVM_ULD_GLOBR_DONE_M BIT(4) +#define GLPCI_CNF2 0x000BE004 +#define GLPCI_CNF2_CACHELINE_SIZE_M BIT(1) #define PF_FUNC_RID 0x0009E880 #define PF_FUNC_RID_FUNC_NUM_S 0 #define PF_FUNC_RID_FUNC_NUM_M ICE_M(0x7, 0) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 82f49dbd762c..333312a1d595 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -1994,6 +1994,22 @@ static int ice_init_interrupt_scheme(struct ice_pf *pf) return 0; } +/** + * ice_verify_cacheline_size - verify driver's assumption of 64 Byte cache lines + * @pf: pointer to the PF structure + * + * There is no error returned here because the driver should be able to handle + * 128 Byte cache lines, so we only print a warning in case issues are seen, + * specifically with Tx. + */ +static void ice_verify_cacheline_size(struct ice_pf *pf) +{ + if (rd32(&pf->hw, GLPCI_CNF2) & GLPCI_CNF2_CACHELINE_SIZE_M) + dev_warn(&pf->pdev->dev, + "%d Byte cache line assumption is invalid, driver may have Tx timeouts!\n", + ICE_CACHE_LINE_BYTES); +} + /** * ice_probe - Device initialization routine * @pdev: PCI device information struct @@ -2144,6 +2160,8 @@ static int ice_probe(struct pci_dev *pdev, /* since everything is good, start the service timer */ mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period)); + ice_verify_cacheline_size(pf); + return 0; err_alloc_sw_unroll: diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 5dae968d853e..3387c67c848d 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -1556,15 +1556,15 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off) * magnitude greater than our largest possible GSO size. * * This would then be implemented as: - * return (((size >> 12) * 85) >> 8) + 1; + * return (((size >> 12) * 85) >> 8) + ICE_DESCS_FOR_SKB_DATA_PTR; * * Since multiplication and division are commutative, we can reorder * operations into: - * return ((size * 85) >> 20) + 1; + * return ((size * 85) >> 20) + ICE_DESCS_FOR_SKB_DATA_PTR; */ static unsigned int ice_txd_use_count(unsigned int size) { - return ((size * 85) >> 20) + 1; + return ((size * 85) >> 20) + ICE_DESCS_FOR_SKB_DATA_PTR; } /** @@ -1706,7 +1706,8 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring) * + 1 desc for context descriptor, * otherwise try next time */ - if (ice_maybe_stop_tx(tx_ring, count + 4 + 1)) { + if (ice_maybe_stop_tx(tx_ring, count + ICE_DESCS_PER_CACHE_LINE + + ICE_DESCS_FOR_CTX_DESC)) { tx_ring->tx_stats.tx_busy++; return NETDEV_TX_BUSY; } diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index 1d0f58bd389b..75d0eaf6c9dd 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -22,8 +22,21 @@ #define ICE_RX_BUF_WRITE 16 /* Must be power of 2 */ #define ICE_MAX_TXQ_PER_TXQG 128 -/* Tx Descriptors needed, worst case */ -#define DESC_NEEDED (MAX_SKB_FRAGS + 4) +/* We are assuming that the cache line is always 64 Bytes here for ice. + * In order to make sure that is a correct assumption there is a check in probe + * to print a warning if the read from GLPCI_CNF2 tells us that the cache line + * size is 128 bytes. We do it this way because we do not want to read the + * GLPCI_CNF2 register or a variable containing the value on every pass through + * the Tx path. + */ +#define ICE_CACHE_LINE_BYTES 64 +#define ICE_DESCS_PER_CACHE_LINE (ICE_CACHE_LINE_BYTES / \ + sizeof(struct ice_tx_desc)) +#define ICE_DESCS_FOR_CTX_DESC 1 +#define ICE_DESCS_FOR_SKB_DATA_PTR 1 +/* Tx descriptors needed, worst case */ +#define DESC_NEEDED (MAX_SKB_FRAGS + ICE_DESCS_FOR_CTX_DESC + \ + ICE_DESCS_PER_CACHE_LINE + ICE_DESCS_FOR_SKB_DATA_PTR) #define ICE_DESC_UNUSED(R) \ ((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \ (R)->next_to_clean - (R)->next_to_use - 1) From d944b46992f8e99b6bdc721e44b02e5ca294fa2b Mon Sep 17 00:00:00 2001 From: Brett Creeley Date: Fri, 26 Oct 2018 10:40:59 -0700 Subject: [PATCH 197/356] ice: Fix the bytecount sent to netdev_tx_sent_queue Currently if the driver does a TSO offload the bytecount sent to netdev_tx_sent_queue will be incorrect. This is because in ice_tso we overwrite the initial value that we set in ice_tx_map. This creates a mismatch between the Tx and Tx clean flow. In the Tx clean flow we calculate the bytecount (called total_bytes) as we clean the descriptors so the value used in the Tx clean path is correct. Fix this by using += in ice_tso instead of =. This fixes the mismatch in bytecount mentioned above. Signed-off-by: Brett Creeley Signed-off-by: Anirudh Venkataramanan Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ice/ice_txrx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 3387c67c848d..fe5bbabbb41e 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -1520,7 +1520,7 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off) /* update gso_segs and bytecount */ first->gso_segs = skb_shinfo(skb)->gso_segs; - first->bytecount = (first->gso_segs - 1) * off->header_len; + first->bytecount += (first->gso_segs - 1) * off->header_len; cd_tso_len = skb->len - off->header_len; cd_mss = skb_shinfo(skb)->gso_size; From 4c9b658eeaefedd402a59e858d8ac3bfdf6153e3 Mon Sep 17 00:00:00 2001 From: Miroslav Lichvar Date: Fri, 26 Oct 2018 19:13:00 +0200 Subject: [PATCH 198/356] igb: shorten maximum PHC timecounter update interval The timecounter needs to be updated at least once per ~550 seconds in order to avoid a 40-bit SYSTIM timestamp to be misinterpreted as an old timestamp. Since commit 500462a9de65 ("timers: Switch to a non-cascading wheel"), scheduling of delayed work seems to be less accurate and a requested delay of 540 seconds may actually be longer than 550 seconds. Also, the PHC may be adjusted to run up to 6% faster than real time and the system clock up to 10% slower. Shorten the delay to 360 seconds to be sure the timecounter is updated in time. This fixes an issue with HW timestamps on 82580/I350/I354 being off by ~1100 seconds for few seconds every ~9 minutes. Cc: Thomas Gleixner Signed-off-by: Miroslav Lichvar Acked-by: Jacob Keller Acked-by: Richard Cochran Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb_ptp.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 29ced6b74d36..2b95dc9c7a6a 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -53,13 +53,15 @@ * 2^40 * 10^-9 / 60 = 18.3 minutes. * * SYSTIM is converted to real time using a timecounter. As - * timecounter_cyc2time() allows old timestamps, the timecounter - * needs to be updated at least once per half of the SYSTIM interval. - * Scheduling of delayed work is not very accurate, so we aim for 8 - * minutes to be sure the actual interval is shorter than 9.16 minutes. + * timecounter_cyc2time() allows old timestamps, the timecounter needs + * to be updated at least once per half of the SYSTIM interval. + * Scheduling of delayed work is not very accurate, and also the NIC + * clock can be adjusted to run up to 6% faster and the system clock + * up to 10% slower, so we aim for 6 minutes to be sure the actual + * interval in the NIC time is shorter than 9.16 minutes. */ -#define IGB_SYSTIM_OVERFLOW_PERIOD (HZ * 60 * 8) +#define IGB_SYSTIM_OVERFLOW_PERIOD (HZ * 60 * 6) #define IGB_PTP_TX_TIMEOUT (HZ * 15) #define INCPERIOD_82576 BIT(E1000_TIMINCA_16NS_SHIFT) #define INCVALUE_82576_MASK GENMASK(E1000_TIMINCA_16NS_SHIFT - 1, 0) From 81bd415c91eb966118d773dddf254aebf3022411 Mon Sep 17 00:00:00 2001 From: Mathieu Malaterre Date: Wed, 6 Jun 2018 21:42:32 +0200 Subject: [PATCH 199/356] watchdog/core: Add missing prototypes for weak functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The split out of the hard lockup detector exposed two new weak functions, but no prototypes for them, which triggers the build warning: kernel/watchdog.c:109:12: warning: no previous prototype for ‘watchdog_nmi_enable’ [-Wmissing-prototypes] kernel/watchdog.c:115:13: warning: no previous prototype for ‘watchdog_nmi_disable’ [-Wmissing-prototypes] Add the prototypes. Fixes: 73ce0511c436 ("kernel/watchdog.c: move hardlockup detector to separate file") Signed-off-by: Mathieu Malaterre Signed-off-by: Thomas Gleixner Cc: Babu Moger Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20180606194232.17653-1-malat@debian.org --- include/linux/nmi.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 08f9247e9827..9003e29cde46 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -119,6 +119,8 @@ static inline int hardlockup_detector_perf_init(void) { return 0; } void watchdog_nmi_stop(void); void watchdog_nmi_start(void); int watchdog_nmi_probe(void); +int watchdog_nmi_enable(unsigned int cpu); +void watchdog_nmi_disable(unsigned int cpu); /** * touch_nmi_watchdog - restart NMI watchdog timeout. From f348e2241fb73515d65b5d77dd9c174128a7fbf2 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Tue, 6 Nov 2018 16:16:01 -0500 Subject: [PATCH 200/356] ext4: fix missing cleanup if ext4_alloc_flex_bg_array() fails while resizing Fixes: 117fff10d7f1 ("ext4: grow the s_flex_groups array as needed ...") Signed-off-by: Vasily Averin Signed-off-by: Theodore Ts'o Cc: stable@kernel.org # 3.7 --- fs/ext4/resize.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 3df326ee6d50..5fee65afd58b 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -2022,7 +2022,7 @@ retry: err = ext4_alloc_flex_bg_array(sb, n_group + 1); if (err) - return err; + goto out; err = ext4_mb_alloc_groupinfo(sb, n_group + 1); if (err) From db6aee62406d9fbb53315fcddd81f1dc271d49fa Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Tue, 6 Nov 2018 16:20:40 -0500 Subject: [PATCH 201/356] ext4: fix possible inode leak in the retry loop of ext4_resize_fs() Fixes: 1c6bd7173d66 ("ext4: convert file system to meta_bg if needed ...") Signed-off-by: Vasily Averin Signed-off-by: Theodore Ts'o Cc: stable@kernel.org # 3.7 --- fs/ext4/resize.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 5fee65afd58b..85158e9de7c2 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -2058,6 +2058,10 @@ retry: n_blocks_count_retry = 0; free_flex_gd(flex_gd); flex_gd = NULL; + if (resize_inode) { + iput(resize_inode); + resize_inode = NULL; + } goto retry; } From 63088da9472854408ae5d7c47bd011daf9e1a81b Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Tue, 6 Nov 2018 16:06:32 -0500 Subject: [PATCH 202/356] Revert "drm/amd/display: set backlight level limit to 1" This reverts commit 0cafc82fae41531b0162150f9a97f2c74f97118f. This breaks some apps that assume 0 is minimum brightness. Revert for 4.20. This is fixed properly for drm-next/4.21 in: "drm/amd: Don't fail on backlight = 0" However, that patch depends on more extensive changes to the backlight interface which are too invasive for -fixes. Fixes: Bugzilla: https://bugs.freedesktop.org/108668 Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 7 ------- 1 file changed, 7 deletions(-) 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 b0df6dc9a775..e224f23e2215 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1524,13 +1524,6 @@ static int amdgpu_dm_backlight_update_status(struct backlight_device *bd) { struct amdgpu_display_manager *dm = bl_get_data(bd); - /* - * PWM interperts 0 as 100% rather than 0% because of HW - * limitation for level 0.So limiting minimum brightness level - * to 1. - */ - if (bd->props.brightness < 1) - return 1; if (dc_link_set_backlight_level(dm->backlight_link, bd->props.brightness, 0, 0)) return 0; From 8ed4ec32d5b1f04a641978322a38a8d7089553bb Mon Sep 17 00:00:00 2001 From: Shaokun Zhang Date: Mon, 5 Nov 2018 18:33:35 +0800 Subject: [PATCH 203/356] drm/amd/display: Fix misleading buffer information RETIMER_REDRIVER_INFO shows the buffer as a decimal value with a '0x' prefix, which is somewhat misleading. Fix it to print hexadecimal, as was intended. Fixes: 2f14bc89("drm/amd/display: add retimer log for HWQ tuning use.") Cc: Charlene Liu Cc: Dmytro Laktyushkin Signed-off-by: Shaokun Zhang Reviewed-by: Leo Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_link.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index fb04a4ad141f..5da2186b3615 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -1722,7 +1722,7 @@ static void write_i2c_retimer_setting( i2c_success = i2c_write(pipe_ctx, slave_address, buffer, sizeof(buffer)); RETIMER_REDRIVER_INFO("retimer write to slave_address = 0x%x,\ - offset = 0x%d, reg_val = 0x%d, i2c_success = %d\n", + offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) /* Write failure */ @@ -1734,7 +1734,7 @@ static void write_i2c_retimer_setting( i2c_success = i2c_write(pipe_ctx, slave_address, buffer, sizeof(buffer)); RETIMER_REDRIVER_INFO("retimer write to slave_address = 0x%x,\ - offset = 0x%d, reg_val = 0x%d, i2c_success = %d\n", + offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) /* Write failure */ From 02680efbb10be0d2c867fe722ae23d588f6bebef Mon Sep 17 00:00:00 2001 From: Harry Wentland Date: Sun, 7 Oct 2018 10:01:23 -0400 Subject: [PATCH 204/356] drm/amd/display: Stop leaking planes [Why] drm_plane_cleanup does not free the plane. [How] Call drm_primary_helper_destroy which will also free the plane. Signed-off-by: Harry Wentland Acked-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 +- 1 file changed, 1 insertion(+), 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 e224f23e2215..289ddd52cac4 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -3301,7 +3301,7 @@ void dm_drm_plane_destroy_state(struct drm_plane *plane, static const struct drm_plane_funcs dm_plane_funcs = { .update_plane = drm_atomic_helper_update_plane, .disable_plane = drm_atomic_helper_disable_plane, - .destroy = drm_plane_cleanup, + .destroy = drm_primary_helper_destroy, .reset = dm_drm_plane_reset, .atomic_duplicate_state = dm_drm_plane_duplicate_state, .atomic_destroy_state = dm_drm_plane_destroy_state, From 3426d66d3e74ab0ab264a85e0795a17e3dde1e71 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Tue, 6 Nov 2018 11:19:00 -0500 Subject: [PATCH 205/356] drm/amdgpu/vega20: add CLK base offset In case we need to access CLK registers. Acked-by: Harry Wentland Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c b/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c index 2d4473557b0d..d13fc4fcb517 100644 --- a/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c +++ b/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c @@ -49,6 +49,7 @@ int vega20_reg_base_init(struct amdgpu_device *adev) adev->reg_offset[SMUIO_HWIP][i] = (uint32_t *)(&(SMUIO_BASE.instance[i])); adev->reg_offset[NBIF_HWIP][i] = (uint32_t *)(&(NBIO_BASE.instance[i])); adev->reg_offset[THM_HWIP][i] = (uint32_t *)(&(THM_BASE.instance[i])); + adev->reg_offset[CLK_HWIP][i] = (uint32_t *)(&(CLK_BASE.instance[i])); } return 0; } From 689e7b34234e29e5168894b27b752a4e16ef08c4 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 2 Nov 2018 10:51:50 -0500 Subject: [PATCH 206/356] drm/amdgpu/display: check if fbc is available in set_static_screen_control (v2) The value is dependent on whether fbc is available. v2: only check if num_pipes is valid Reviewed-by: Harry Wentland Signed-off-by: Alex Deucher --- .../gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index b75ede5f84f7..b459867a05b2 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -1736,7 +1736,12 @@ static void set_static_screen_control(struct pipe_ctx **pipe_ctx, if (events->force_trigger) value |= 0x1; - value |= 0x84; + if (num_pipes) { + struct dc *dc = pipe_ctx[0]->stream->ctx->dc; + + if (dc->fbc_compressor) + value |= 0x84; + } for (i = 0; i < num_pipes; i++) pipe_ctx[i]->stream_res.tg->funcs-> From 7875a22625aa7f11befba84bd1e669201032947d Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Tue, 6 Nov 2018 14:44:29 -0500 Subject: [PATCH 207/356] drm/amdgpu: add DC feature mask module parameter Similar to ppfeaturemask. Allows you to selectively enable/disable DC features. Reviewed-by: Harry Wentland Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 + drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 11 +++++++++++ drivers/gpu/drm/amd/include/amd_shared.h | 4 ++++ 3 files changed, 16 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index d0102cfc8efb..104b2e0d893b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -151,6 +151,7 @@ extern int amdgpu_compute_multipipe; extern int amdgpu_gpu_recovery; extern int amdgpu_emu_mode; extern uint amdgpu_smu_memory_pool_size; +extern uint amdgpu_dc_feature_mask; extern struct amdgpu_mgpu_info mgpu_info; #ifdef CONFIG_DRM_AMDGPU_SI diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 943dbf3c5da1..8de55f7f1a3a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -127,6 +127,9 @@ int amdgpu_compute_multipipe = -1; int amdgpu_gpu_recovery = -1; /* auto */ int amdgpu_emu_mode = 0; uint amdgpu_smu_memory_pool_size = 0; +/* FBC (bit 0) disabled by default*/ +uint amdgpu_dc_feature_mask = 0; + struct amdgpu_mgpu_info mgpu_info = { .mutex = __MUTEX_INITIALIZER(mgpu_info.mutex), }; @@ -631,6 +634,14 @@ module_param(halt_if_hws_hang, int, 0644); MODULE_PARM_DESC(halt_if_hws_hang, "Halt if HWS hang is detected (0 = off (default), 1 = on)"); #endif +/** + * DOC: dcfeaturemask (uint) + * Override display features enabled. See enum DC_FEATURE_MASK in drivers/gpu/drm/amd/include/amd_shared.h. + * The default is the current set of stable display features. + */ +MODULE_PARM_DESC(dcfeaturemask, "all stable DC features enabled (default))"); +module_param_named(dcfeaturemask, amdgpu_dc_feature_mask, uint, 0444); + static const struct pci_device_id pciidlist[] = { #ifdef CONFIG_DRM_AMDGPU_SI {0x1002, 0x6780, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI}, diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h index 2083c308007c..470d7b89071a 100644 --- a/drivers/gpu/drm/amd/include/amd_shared.h +++ b/drivers/gpu/drm/amd/include/amd_shared.h @@ -133,6 +133,10 @@ enum PP_FEATURE_MASK { PP_AVFS_MASK = 0x40000, }; +enum DC_FEATURE_MASK { + DC_FBC_MASK = 0x1, +}; + /** * struct amd_ip_funcs - general hooks for managing amdgpu IP Blocks */ From ce2127c462d9d1c0832f088b23158420e87e71a0 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Tue, 6 Nov 2018 15:10:37 -0500 Subject: [PATCH 208/356] drm/amdgpu/display/dc: add FBC to dc_config Add FBC to the list of features that can be enabled from the DM. Reviewed-by: Harry Wentland Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dc.h | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 199527171100..b57fa61b3034 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -169,6 +169,7 @@ struct link_training_settings; struct dc_config { bool gpu_vm_support; bool disable_disp_pll_sharing; + bool fbc_support; }; enum visual_confirm { From 04b94af4e348acc52546b9b19c933575f26589a1 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Tue, 6 Nov 2018 15:19:49 -0500 Subject: [PATCH 209/356] drm/amdgpu/display/dm: handle FBC dc feature parameter Set the dc_config properly when the option is enabled. Reviewed-by: Harry Wentland Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 3 +++ 1 file changed, 3 insertions(+) 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 289ddd52cac4..d3f5cb1795bf 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -429,6 +429,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) adev->asic_type < CHIP_RAVEN) init_data.flags.gpu_vm_support = true; + if (amdgpu_dc_feature_mask & DC_FBC_MASK) + init_data.flags.fbc_support = true; + /* Display Core create. */ adev->dm.dc = dc_create(&init_data); From 5822e9539dc11721b53d74accd4c091b982011d0 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 2 Nov 2018 10:54:27 -0500 Subject: [PATCH 210/356] drm/amdgpu/display/dce11: only enable FBC when selected Causes a black screen on a Stoney laptop. Bug: https://bugs.freedesktop.org/show_bug.cgi?id=108577 Reviewed-by: Harry Wentland Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c index e3624ca24574..7c9fd9052ee2 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c @@ -1362,7 +1362,8 @@ static bool construct( pool->base.sw_i2cs[i] = NULL; } - dc->fbc_compressor = dce110_compressor_create(ctx); + if (dc->config.fbc_support) + dc->fbc_compressor = dce110_compressor_create(ctx); if (!underlay_create(ctx, &pool->base)) goto res_create_fail; From a6758309a005060b8297a538a457c88699cb2520 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Tue, 6 Nov 2018 16:49:50 -0500 Subject: [PATCH 211/356] ext4: avoid buffer leak on shutdown in ext4_mark_iloc_dirty() ext4_mark_iloc_dirty() callers expect that it releases iloc->bh even if it returns an error. Fixes: 0db1ff222d40 ("ext4: add shutdown bit and check for it") Signed-off-by: Vasily Averin Signed-off-by: Theodore Ts'o Cc: stable@kernel.org # 4.11 --- fs/ext4/inode.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index c3d9a42c561e..55c8fca76daf 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5835,9 +5835,10 @@ int ext4_mark_iloc_dirty(handle_t *handle, { int err = 0; - if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) + if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) { + put_bh(iloc->bh); return -EIO; - + } if (IS_I_VERSION(inode)) inode_inc_iversion(inode); From feaf264ce7f8d54582e2f66eb82dd9dd124c94f3 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Tue, 6 Nov 2018 17:01:36 -0500 Subject: [PATCH 212/356] ext4: avoid buffer leak in ext4_orphan_add() after prior errors Fixes: d745a8c20c1f ("ext4: reduce contention on s_orphan_lock") Fixes: 6e3617e579e0 ("ext4: Handle non empty on-disk orphan link") Cc: Dmitry Monakhov Signed-off-by: Vasily Averin Signed-off-by: Theodore Ts'o Cc: stable@kernel.org # 2.6.34 --- fs/ext4/namei.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 67a38532032a..d388cce72db2 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2811,7 +2811,9 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) list_del_init(&EXT4_I(inode)->i_orphan); mutex_unlock(&sbi->s_orphan_lock); } - } + } else + brelse(iloc.bh); + jbd_debug(4, "superblock will point to %lu\n", inode->i_ino); jbd_debug(4, "orphan inode %lu will point to %d\n", inode->i_ino, NEXT_ORPHAN(inode)); From 4f32c38b4662312dd3c5f113d8bdd459887fb773 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 6 Nov 2018 17:18:17 -0500 Subject: [PATCH 213/356] ext4: avoid possible double brelse() in add_new_gdb() on error path Fixes: b40971426a83 ("ext4: add error checking to calls to ...") Reported-by: Vasily Averin Signed-off-by: Theodore Ts'o Cc: stable@kernel.org # 2.6.38 --- fs/ext4/resize.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 85158e9de7c2..a5efee34415f 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -871,6 +871,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, err = ext4_handle_dirty_metadata(handle, NULL, gdb_bh); if (unlikely(err)) { ext4_std_error(sb, err); + iloc.bh = NULL; goto exit_inode; } brelse(dind); From 1bfc204dc0e7a690ab8440e91bb7d1a324320fdc Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Tue, 6 Nov 2018 17:45:02 -0500 Subject: [PATCH 214/356] ext4: remove unneeded brelse call in ext4_xattr_inode_update_ref() Signed-off-by: Vasily Averin Signed-off-by: Theodore Ts'o --- fs/ext4/xattr.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index f36fc5d5b257..dc1aeab06dba 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1031,10 +1031,8 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, inode_lock(ea_inode); ret = ext4_reserve_inode_write(handle, ea_inode, &iloc); - if (ret) { - iloc.bh = NULL; + if (ret) goto out; - } ref_count = ext4_xattr_inode_get_ref(ea_inode); ref_count += ref_change; @@ -1080,12 +1078,10 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, } ret = ext4_mark_iloc_dirty(handle, ea_inode, &iloc); - iloc.bh = NULL; if (ret) ext4_warning_inode(ea_inode, "ext4_mark_iloc_dirty() failed ret=%d", ret); out: - brelse(iloc.bh); inode_unlock(ea_inode); return ret; } From 9e463084cdb22e0b56b2dfbc50461020409a5fd3 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 7 Nov 2018 10:32:53 -0500 Subject: [PATCH 215/356] ext4: fix possible leak of sbi->s_group_desc_leak in error path Fixes: bfe0a5f47ada ("ext4: add more mount time checks of the superblock") Reported-by: Vasily Averin Signed-off-by: Theodore Ts'o Cc: stable@kernel.org # 4.18 --- fs/ext4/super.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index a221f1cdf704..92092b55db1e 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4075,6 +4075,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_groups_count = blocks_count; sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count, (EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb))); + if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) != + le32_to_cpu(es->s_inodes_count)) { + ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu", + le32_to_cpu(es->s_inodes_count), + ((u64)sbi->s_groups_count * sbi->s_inodes_per_group)); + ret = -EINVAL; + goto failed_mount; + } db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) / EXT4_DESC_PER_BLOCK(sb); if (ext4_has_feature_meta_bg(sb)) { @@ -4094,14 +4102,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) ret = -ENOMEM; goto failed_mount; } - if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) != - le32_to_cpu(es->s_inodes_count)) { - ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu", - le32_to_cpu(es->s_inodes_count), - ((u64)sbi->s_groups_count * sbi->s_inodes_per_group)); - ret = -EINVAL; - goto failed_mount; - } bgl_lock_init(sbi->s_blockgroup_lock); From f26621e60b35369bca9228bc936dc723b3e421af Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Mon, 5 Nov 2018 10:33:07 +0100 Subject: [PATCH 216/356] resource/docs: Complete kernel-doc style function documentation Add the missing kernel-doc style function parameters documentation. Signed-off-by: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: akpm@linux-foundation.org Cc: linux-tip-commits@vger.kernel.org Cc: rdunlap@infradead.org Fixes: b69c2e20f6e4 ("resource: Clean it up a bit") Link: http://lkml.kernel.org/r/20181105093307.GA12445@zn.tnic Signed-off-by: Ingo Molnar --- kernel/resource.c | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) diff --git a/kernel/resource.c b/kernel/resource.c index 17bcb189d530..b0fbf685c77a 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -318,17 +318,24 @@ int release_resource(struct resource *old) EXPORT_SYMBOL(release_resource); -/* - * Finds the lowest iomem resource that covers part of [start..end]. The - * caller must specify start, end, flags, and desc (which may be +/** + * Finds the lowest iomem resource that covers part of [@start..@end]. The + * caller must specify @start, @end, @flags, and @desc (which may be * IORES_DESC_NONE). * - * If a resource is found, returns 0 and *res is overwritten with the part - * of the resource that's within [start..end]; if none is found, returns - * -1. Returns -EINVAL for other invalid parameters. + * If a resource is found, returns 0 and @*res is overwritten with the part + * of the resource that's within [@start..@end]; if none is found, returns + * -1 or -EINVAL for other invalid parameters. * * This function walks the whole tree and not just first level children * unless @first_lvl is true. + * + * @start: start address of the resource searched for + * @end: end address of same resource + * @flags: flags which the resource must have + * @desc: descriptor the resource must have + * @first_lvl: walk only the first level children, if set + * @res: return ptr, if resource found */ static int find_next_iomem_res(resource_size_t start, resource_size_t end, unsigned long flags, unsigned long desc, @@ -390,9 +397,7 @@ static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end, } /** - * walk_iomem_res_desc - walk through iomem resources - * - * Walks through iomem resources and calls @func() with matching resource + * Walks through iomem resources and calls func() with matching resource * ranges. This walks through whole tree and not just first level children. * All the memory ranges which overlap start,end and also match flags and * desc are valid candidates. From af18e35bfd01e6d65a5e3ef84ffe8b252d1628c5 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Wed, 7 Nov 2018 10:56:28 -0500 Subject: [PATCH 217/356] ext4: fix possible leak of s_journal_flag_rwsem in error path Fixes: c8585c6fcaf2 ("ext4: fix races between changing inode journal ...") Signed-off-by: Vasily Averin Signed-off-by: Theodore Ts'o Cc: stable@kernel.org # 4.7 --- fs/ext4/super.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 92092b55db1e..53ff6c2a26ed 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4510,6 +4510,7 @@ failed_mount6: percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); percpu_counter_destroy(&sbi->s_dirtyclusters_counter); + percpu_free_rwsem(&sbi->s_journal_flag_rwsem); failed_mount5: ext4_ext_release(sb); ext4_release_system_zone(sb); From ecaaf408478b6fb4d9986f9b6652f3824e374f4c Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Wed, 7 Nov 2018 11:01:33 -0500 Subject: [PATCH 218/356] ext4: fix buffer leak in ext4_xattr_get_block() on error path Fixes: dec214d00e0d ("ext4: xattr inode deduplication") Signed-off-by: Vasily Averin Signed-off-by: Theodore Ts'o Cc: stable@kernel.org # 4.13 --- fs/ext4/xattr.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index dc1aeab06dba..07c3a115f7ae 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -2272,8 +2272,10 @@ static struct buffer_head *ext4_xattr_get_block(struct inode *inode) if (!bh) return ERR_PTR(-EIO); error = ext4_xattr_check_block(inode, bh); - if (error) + if (error) { + brelse(bh); return ERR_PTR(error); + } return bh; } From 45ae932d246f721e6584430017176cbcadfde610 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Wed, 7 Nov 2018 11:07:01 -0500 Subject: [PATCH 219/356] ext4: release bs.bh before re-using in ext4_xattr_block_find() bs.bh was taken in previous ext4_xattr_block_find() call, it should be released before re-using Fixes: 7e01c8e5420b ("ext3/4: fix uninitialized bs in ...") Signed-off-by: Vasily Averin Signed-off-by: Theodore Ts'o Cc: stable@kernel.org # 2.6.26 --- fs/ext4/xattr.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 07c3a115f7ae..07b9a335c8eb 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -2395,6 +2395,8 @@ retry_inode: error = ext4_xattr_block_set(handle, inode, &i, &bs); } else if (error == -ENOSPC) { if (EXT4_I(inode)->i_file_acl && !bs.s.base) { + brelse(bs.bh); + bs.bh = NULL; error = ext4_xattr_block_find(inode, &i, &bs); if (error) goto cleanup; From 6bdc9977fcdedf47118d2caf7270a19f4b6d8a8f Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Wed, 7 Nov 2018 11:10:21 -0500 Subject: [PATCH 220/356] ext4: fix buffer leak in ext4_xattr_move_to_block() on error path Fixes: 3f2571c1f91f ("ext4: factor out xattr moving") Fixes: 6dd4ee7cab7e ("ext4: Expand extra_inodes space per ...") Reviewed-by: Jan Kara Signed-off-by: Vasily Averin Signed-off-by: Theodore Ts'o Cc: stable@kernel.org # 2.6.23 --- fs/ext4/xattr.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 07b9a335c8eb..5c9bc0d85cc0 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -2617,6 +2617,8 @@ out: kfree(buffer); if (is) brelse(is->iloc.bh); + if (bs) + brelse(bs->bh); kfree(is); kfree(bs); From 53692ec074d00589c2cf1d6d17ca76ad0adce6ec Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Wed, 7 Nov 2018 11:14:35 -0500 Subject: [PATCH 221/356] ext4: fix buffer leak in ext4_expand_extra_isize_ea() on error path Fixes: de05ca852679 ("ext4: move call to ext4_error() into ...") Signed-off-by: Vasily Averin Signed-off-by: Theodore Ts'o Cc: stable@kernel.org # 4.17 --- fs/ext4/xattr.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 5c9bc0d85cc0..0b9688683526 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -2698,7 +2698,6 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, struct ext4_inode *raw_inode, handle_t *handle) { struct ext4_xattr_ibody_header *header; - struct buffer_head *bh; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); static unsigned int mnt_count; size_t min_offs; @@ -2739,13 +2738,17 @@ retry: * EA block can hold new_extra_isize bytes. */ if (EXT4_I(inode)->i_file_acl) { + struct buffer_head *bh; + bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl); error = -EIO; if (!bh) goto cleanup; error = ext4_xattr_check_block(inode, bh); - if (error) + if (error) { + brelse(bh); goto cleanup; + } base = BHDR(bh); end = bh->b_data + bh->b_size; min_offs = end - base; From ffe498237b36ee42624e139b21efa05da4ff1f48 Mon Sep 17 00:00:00 2001 From: Chinh T Cao Date: Mon, 5 Nov 2018 12:18:35 -0800 Subject: [PATCH 222/356] ice: Change req_speeds to be u16 Since the req_speeds field in struct ice_link_status is a u8, req_speeds & ICE_AQ_LINK_SPEED_40GB always returns 0. This was caught by a coverity scan. Fix this by changing req_speeds to be u16. Reported-by: Bruce Allan Signed-off-by: Chinh T Cao Signed-off-by: Anirudh Venkataramanan Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ice/ice_type.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index 12f9432abf11..f4dbc81c1988 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -92,12 +92,12 @@ struct ice_link_status { u64 phy_type_low; u16 max_frame_size; u16 link_speed; + u16 req_speeds; u8 lse_ena; /* Link Status Event notification */ u8 link_info; u8 an_info; u8 ext_info; u8 pacing; - u8 req_speeds; /* Refer to #define from module_type[ICE_MODULE_TYPE_TOTAL_BYTE] of * ice_aqc_get_phy_caps structure */ From ba766b8b99c30ad3c55ed8cf224d1185ecff1476 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 29 Oct 2018 10:52:42 -0700 Subject: [PATCH 223/356] i40e: restore NETIF_F_GSO_IPXIP[46] to netdev features Since commit bacd75cfac8a ("i40e/i40evf: Add capability exchange for outer checksum", 2017-04-06) the i40e driver has not reported support for IP-in-IP offloads. This likely occurred due to a bad rebase, as the commit extracts hw_enc_features into its own variable. As part of this change, it dropped the NETIF_F_FSO_IPXIP flags from the netdev->hw_enc_features. This was unfortunately not caught during code review. Fix this by adding back the missing feature flags. For reference, NETIF_F_GSO_IPXIP4 was added in commit 7e13318daa4a ("net: define gso types for IPx over IPv4 and IPv6", 2016-05-20), replacing NETIF_F_GSO_IPIP and NETIF_F_GSO_SIT. NETIF_F_GSO_IPXIP6 was added in commit bf2d1df39502 ("intel: Add support for IPv6 IP-in-IP offload", 2016-05-20). Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index bc71a21c1dc2..3ff5ee49818b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -12249,6 +12249,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) NETIF_F_GSO_GRE | NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_PARTIAL | + NETIF_F_GSO_IPXIP4 | + NETIF_F_GSO_IPXIP6 | NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_SCTP_CRC | From d5596fd46770550873ab4c02bcb69f83d3d63f63 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 29 Oct 2018 10:52:43 -0700 Subject: [PATCH 224/356] i40e: enable NETIF_F_NTUPLE and NETIF_F_HW_TC at driver load The assignment of the feature flag NETIF_F_NTUPLE and NETIF_F_HW_TC occurs prior to the initial setup of the local hw_features variable. This means the features are set as user-changeable, but are not set in the currently active feature list. This results in the features being disabled at the driver's initial load. Move the assignment after the initial assignment of hw_features, and assign to the local variable. This ensures that NETIF_F_NTUPLE and NETIF_F_HW_TC are marked as user-changeable, and also enables them by default when the driver loads. Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 3ff5ee49818b..21c2688d6308 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -12268,13 +12268,13 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) /* record features VLANs can make use of */ netdev->vlan_features |= hw_enc_features | NETIF_F_TSO_MANGLEID; - if (!(pf->flags & I40E_FLAG_MFP_ENABLED)) - netdev->hw_features |= NETIF_F_NTUPLE | NETIF_F_HW_TC; - hw_features = hw_enc_features | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; + if (!(pf->flags & I40E_FLAG_MFP_ENABLED)) + hw_features |= NETIF_F_NTUPLE | NETIF_F_HW_TC; + netdev->hw_features |= hw_features; netdev->features |= hw_features | NETIF_F_HW_VLAN_CTAG_FILTER; From d6fd0ae25c6495674dc5a41a8d16bc8e0073276d Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Wed, 31 Oct 2018 10:06:08 -0700 Subject: [PATCH 225/356] Btrfs: fix missing delayed iputs on unmount There's a race between close_ctree() and cleaner_kthread(). close_ctree() sets btrfs_fs_closing(), and the cleaner stops when it sees it set, but this is racy; the cleaner might have already checked the bit and could be cleaning stuff. In particular, if it deletes unused block groups, it will create delayed iputs for the free space cache inodes. As of "btrfs: don't run delayed_iputs in commit", we're no longer running delayed iputs after a commit. Therefore, if the cleaner creates more delayed iputs after delayed iputs are run in btrfs_commit_super(), we will leak inodes on unmount and get a busy inode crash from the VFS. Fix it by parking the cleaner before we actually close anything. Then, any remaining delayed iputs will always be handled in btrfs_commit_super(). This also ensures that the commit in close_ctree() is really the last commit, so we can get rid of the commit in cleaner_kthread(). The fstest/generic/475 followed by 476 can trigger a crash that manifests as a slab corruption caused by accessing the freed kthread structure by a wake up function. Sample trace: [ 5657.077612] BUG: unable to handle kernel NULL pointer dereference at 00000000000000cc [ 5657.079432] PGD 1c57a067 P4D 1c57a067 PUD da10067 PMD 0 [ 5657.080661] Oops: 0000 [#1] PREEMPT SMP [ 5657.081592] CPU: 1 PID: 5157 Comm: fsstress Tainted: G W 4.19.0-rc8-default+ #323 [ 5657.083703] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.2-0-gf9626cc-prebuilt.qemu-project.org 04/01/2014 [ 5657.086577] RIP: 0010:shrink_page_list+0x2f9/0xe90 [ 5657.091937] RSP: 0018:ffffb5c745c8f728 EFLAGS: 00010287 [ 5657.092953] RAX: 0000000000000074 RBX: ffffb5c745c8f830 RCX: 0000000000000000 [ 5657.094590] RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff9a8747fdf3d0 [ 5657.095987] RBP: ffffb5c745c8f9e0 R08: 0000000000000000 R09: 0000000000000000 [ 5657.097159] R10: ffff9a8747fdf5e8 R11: 0000000000000000 R12: ffffb5c745c8f788 [ 5657.098513] R13: ffff9a877f6ff2c0 R14: ffff9a877f6ff2c8 R15: dead000000000200 [ 5657.099689] FS: 00007f948d853b80(0000) GS:ffff9a877d600000(0000) knlGS:0000000000000000 [ 5657.101032] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 5657.101953] CR2: 00000000000000cc CR3: 00000000684bd000 CR4: 00000000000006e0 [ 5657.103159] Call Trace: [ 5657.103776] shrink_inactive_list+0x194/0x410 [ 5657.104671] shrink_node_memcg.constprop.84+0x39a/0x6a0 [ 5657.105750] shrink_node+0x62/0x1c0 [ 5657.106529] try_to_free_pages+0x1a4/0x500 [ 5657.107408] __alloc_pages_slowpath+0x2c9/0xb20 [ 5657.108418] __alloc_pages_nodemask+0x268/0x2b0 [ 5657.109348] kmalloc_large_node+0x37/0x90 [ 5657.110205] __kmalloc_node+0x236/0x310 [ 5657.111014] kvmalloc_node+0x3e/0x70 Fixes: 30928e9baac2 ("btrfs: don't run delayed_iputs in commit") Signed-off-by: Omar Sandoval Reviewed-by: David Sterba [ add trace ] Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 51 ++++++++++++++-------------------------------- 1 file changed, 15 insertions(+), 36 deletions(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 00ee5e37e989..3f0b6d1936e8 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1664,9 +1664,8 @@ static int cleaner_kthread(void *arg) struct btrfs_root *root = arg; struct btrfs_fs_info *fs_info = root->fs_info; int again; - struct btrfs_trans_handle *trans; - do { + while (1) { again = 0; /* Make the cleaner go to sleep early. */ @@ -1715,42 +1714,16 @@ static int cleaner_kthread(void *arg) */ btrfs_delete_unused_bgs(fs_info); sleep: + if (kthread_should_park()) + kthread_parkme(); + if (kthread_should_stop()) + return 0; if (!again) { set_current_state(TASK_INTERRUPTIBLE); - if (!kthread_should_stop()) - schedule(); + schedule(); __set_current_state(TASK_RUNNING); } - } while (!kthread_should_stop()); - - /* - * Transaction kthread is stopped before us and wakes us up. - * However we might have started a new transaction and COWed some - * tree blocks when deleting unused block groups for example. So - * make sure we commit the transaction we started to have a clean - * shutdown when evicting the btree inode - if it has dirty pages - * when we do the final iput() on it, eviction will trigger a - * writeback for it which will fail with null pointer dereferences - * since work queues and other resources were already released and - * destroyed by the time the iput/eviction/writeback is made. - */ - trans = btrfs_attach_transaction(root); - if (IS_ERR(trans)) { - if (PTR_ERR(trans) != -ENOENT) - btrfs_err(fs_info, - "cleaner transaction attach returned %ld", - PTR_ERR(trans)); - } else { - int ret; - - ret = btrfs_commit_transaction(trans); - if (ret) - btrfs_err(fs_info, - "cleaner open transaction commit returned %d", - ret); } - - return 0; } static int transaction_kthread(void *arg) @@ -3931,6 +3904,13 @@ void close_ctree(struct btrfs_fs_info *fs_info) int ret; set_bit(BTRFS_FS_CLOSING_START, &fs_info->flags); + /* + * We don't want the cleaner to start new transactions, add more delayed + * iputs, etc. while we're closing. We can't use kthread_stop() yet + * because that frees the task_struct, and the transaction kthread might + * still try to wake up the cleaner. + */ + kthread_park(fs_info->cleaner_kthread); /* wait for the qgroup rescan worker to stop */ btrfs_qgroup_wait_for_completion(fs_info, false); @@ -3958,9 +3938,8 @@ void close_ctree(struct btrfs_fs_info *fs_info) if (!sb_rdonly(fs_info->sb)) { /* - * If the cleaner thread is stopped and there are - * block groups queued for removal, the deletion will be - * skipped when we quit the cleaner thread. + * The cleaner kthread is stopped, so do one final pass over + * unused block groups. */ btrfs_delete_unused_bgs(fs_info); From df376b2ed51a2777c3398e038992f62523c0f932 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Wed, 7 Nov 2018 14:58:14 +0100 Subject: [PATCH 226/356] block: respect virtual boundary mask in bvecs With drivers that are settting a virtual boundary constrain, we are seeing a lot of bio splitting and smaller I/Os being submitted to the driver. This happens because the bio gap detection code does not account cases where PAGE_SIZE - 1 is bigger than queue_virt_boundary() and thus will split the bio unnecessarily. Cc: Jan Kara Cc: Bart Van Assche Cc: Ming Lei Reviewed-by: Sagi Grimberg Signed-off-by: Johannes Thumshirn Acked-by: Keith Busch Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-merge.c | 2 +- block/blk.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/block/blk-merge.c b/block/blk-merge.c index 6b5ad275ed56..208658a901c6 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -46,7 +46,7 @@ static inline bool bio_will_gap(struct request_queue *q, bio_get_first_bvec(prev_rq->bio, &pb); else bio_get_first_bvec(prev, &pb); - if (pb.bv_offset) + if (pb.bv_offset & queue_virt_boundary(q)) return true; /* diff --git a/block/blk.h b/block/blk.h index a1841b8ff129..c85e53f21cdd 100644 --- a/block/blk.h +++ b/block/blk.h @@ -169,7 +169,7 @@ static inline bool biovec_phys_mergeable(struct request_queue *q, static inline bool __bvec_gap_to_prev(struct request_queue *q, struct bio_vec *bprv, unsigned int offset) { - return offset || + return (offset & queue_virt_boundary(q)) || ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); } From 3a40cfe8ba3abba57af2c7e26aad2c6dd1681864 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Wed, 7 Nov 2018 13:42:58 +0800 Subject: [PATCH 227/356] leds: trigger: Fix sleeping function called from invalid context We will meet below issue due to mutex_lock() is called in interrupt context. The mutex lock is used to protect the pattern trigger data, but before changing new pattern trigger data (pattern values or repeat value) by users, we always cancel the timer firstly to clear previous patterns' performance. That means there is no race in pattern_trig_timer_function(), so we can drop the mutex lock in pattern_trig_timer_function() to avoid this issue. Moreover we can move the timer cancelling into mutex protection, since there is no deadlock risk if we remove the mutex lock in pattern_trig_timer_function(). BUG: sleeping function called from invalid context at kernel/locking/mutex.c:254 in_atomic(): 1, irqs_disabled(): 0, pid: 0, name: swapper/1 CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.20.0-rc1-koelsch-00841-ga338c8181013c1a9 #171 Hardware name: Generic R-Car Gen2 (Flattened Device Tree) [] (unwind_backtrace) from [] (show_stack+0x10/0x14) [] (show_stack) from [] (dump_stack+0x7c/0x9c) [] (dump_stack) from [] (___might_sleep+0xf4/0x158) [] (___might_sleep) from [] (mutex_lock+0x18/0x60) [] (mutex_lock) from [] (pattern_trig_timer_function+0x1c/0x11c) [] (pattern_trig_timer_function) from [] (call_timer_fn+0x1c/0x90) [] (call_timer_fn) from [] (expire_timers+0x94/0xa4) [] (expire_timers) from [] (run_timer_softirq+0x108/0x15c) [] (run_timer_softirq) from [] (__do_softirq+0x1d4/0x258) [] (__do_softirq) from [] (irq_exit+0x64/0xc4) [] (irq_exit) from [] (__handle_domain_irq+0x80/0xb4) [] (__handle_domain_irq) from [] (gic_handle_irq+0x58/0x90) [] (gic_handle_irq) from [] (__irq_svc+0x58/0x74) Exception stack(0xeb483f60 to 0xeb483fa8) 3f60: 00000000 00000000 eb9afaa0 c0217e80 00000000 ffffe000 00000000 c0e06408 3f80: 00000002 c0e0647c c0c6a5f0 00000000 c0e04900 eb483fb0 c0207ea8 c0207e98 3fa0: 60020013 ffffffff [] (__irq_svc) from [] (arch_cpu_idle+0x1c/0x38) [] (arch_cpu_idle) from [] (do_idle+0x138/0x268) [] (do_idle) from [] (cpu_startup_entry+0x18/0x1c) [] (cpu_startup_entry) from [<402022ec>] (0x402022ec) Fixes: 5fd752b6b3a2 ("leds: core: Introduce LED pattern trigger") Signed-off-by: Baolin Wang Reported-by: Geert Uytterhoeven Tested-by: Geert Uytterhoeven Signed-off-by: Jacek Anaszewski --- drivers/leds/trigger/ledtrig-pattern.c | 20 ++++---------------- 1 file changed, 4 insertions(+), 16 deletions(-) diff --git a/drivers/leds/trigger/ledtrig-pattern.c b/drivers/leds/trigger/ledtrig-pattern.c index 174a298f1be0..1870cf87afe1 100644 --- a/drivers/leds/trigger/ledtrig-pattern.c +++ b/drivers/leds/trigger/ledtrig-pattern.c @@ -75,8 +75,6 @@ static void pattern_trig_timer_function(struct timer_list *t) { struct pattern_trig_data *data = from_timer(data, t, timer); - mutex_lock(&data->lock); - for (;;) { if (!data->is_indefinite && !data->repeat) break; @@ -117,8 +115,6 @@ static void pattern_trig_timer_function(struct timer_list *t) break; } - - mutex_unlock(&data->lock); } static int pattern_trig_start_pattern(struct led_classdev *led_cdev) @@ -177,14 +173,10 @@ static ssize_t repeat_store(struct device *dev, struct device_attribute *attr, if (res < -1 || res == 0) return -EINVAL; - /* - * Clear previous patterns' performence firstly, and remove the timer - * without mutex lock to avoid dead lock. - */ - del_timer_sync(&data->timer); - mutex_lock(&data->lock); + del_timer_sync(&data->timer); + if (data->is_hw_pattern) led_cdev->pattern_clear(led_cdev); @@ -235,14 +227,10 @@ static ssize_t pattern_trig_store_patterns(struct led_classdev *led_cdev, struct pattern_trig_data *data = led_cdev->trigger_data; int ccount, cr, offset = 0, err = 0; - /* - * Clear previous patterns' performence firstly, and remove the timer - * without mutex lock to avoid dead lock. - */ - del_timer_sync(&data->timer); - mutex_lock(&data->lock); + del_timer_sync(&data->timer); + if (data->is_hw_pattern) led_cdev->pattern_clear(led_cdev); From 406e7f986b2e4499295351bcfff5c93b0d34022a Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 7 Nov 2018 14:45:24 +0100 Subject: [PATCH 228/356] Documentation: ABI: led-trigger-pattern: Fix typos - Spelling s/brigntess/brightness/, - Double "use". Signed-off-by: Geert Uytterhoeven Acked-by: Pavel Machek Signed-off-by: Jacek Anaszewski --- Documentation/ABI/testing/sysfs-class-led-trigger-pattern | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-class-led-trigger-pattern b/Documentation/ABI/testing/sysfs-class-led-trigger-pattern index fb3d1e03b881..1e5d172e0646 100644 --- a/Documentation/ABI/testing/sysfs-class-led-trigger-pattern +++ b/Documentation/ABI/testing/sysfs-class-led-trigger-pattern @@ -37,8 +37,8 @@ Description: 0-| / \/ \/ +---0----1----2----3----4----5----6------------> time (s) - 2. To make the LED go instantly from one brigntess value to another, - we should use use zero-time lengths (the brightness must be same as + 2. To make the LED go instantly from one brightness value to another, + we should use zero-time lengths (the brightness must be same as the previous tuple's). So the format should be: "brightness_1 duration_1 brightness_1 0 brightness_2 duration_2 brightness_2 0 ...". For example: From 6961cd4d0fde97f1cdb798ba21cf124ecfa0bf95 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 7 Nov 2018 14:34:05 -0700 Subject: [PATCH 229/356] ubd: fix missing lock around request issue We need to hold the device lock (and disable interrupts) while writing new commands, or we could be interrupted while that is happening and read invalid requests in the completion path. Fixes: 4e6da0fe8058 ("um: Convert ubd driver to blk-mq") Tested-by: Richard Weinberger Signed-off-by: Jens Axboe --- arch/um/drivers/ubd_kern.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 74c002ddc0ce..08831f5d83db 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -1341,11 +1341,14 @@ static int ubd_queue_one_vec(struct blk_mq_hw_ctx *hctx, struct request *req, static blk_status_t ubd_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { + struct ubd *ubd_dev = hctx->queue->queuedata; struct request *req = bd->rq; int ret = 0; blk_mq_start_request(req); + spin_lock_irq(&ubd_dev->lock); + if (req_op(req) == REQ_OP_FLUSH) { ret = ubd_queue_one_vec(hctx, req, 0, NULL); } else { @@ -1361,9 +1364,11 @@ static blk_status_t ubd_queue_rq(struct blk_mq_hw_ctx *hctx, } } out: - if (ret < 0) { + spin_unlock_irq(&ubd_dev->lock); + + if (ret < 0) blk_mq_requeue_request(req, true); - } + return BLK_STS_OK; } From e31d36b0a453d581fb077fce6883811c5e14874d Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 7 Nov 2018 10:47:57 +0100 Subject: [PATCH 230/356] MAINTAINERS: Fix remaining pointers to obsolete libata.git libata.git no longer exists. Replace the remaining pointers to it by pointers to the block tree, which is where all libata development happens now. Signed-off-by: Geert Uytterhoeven Signed-off-by: Jens Axboe --- MAINTAINERS | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 2b928aa857ce..262ece39cc47 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8343,7 +8343,7 @@ F: drivers/media/dvb-frontends/lgdt3305.* LIBATA PATA ARASAN COMPACT FLASH CONTROLLER M: Viresh Kumar L: linux-ide@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git S: Maintained F: include/linux/pata_arasan_cf_data.h F: drivers/ata/pata_arasan_cf.c @@ -8360,7 +8360,7 @@ F: drivers/ata/ata_generic.c LIBATA PATA FARADAY FTIDE010 AND GEMINI SATA BRIDGE DRIVERS M: Linus Walleij L: linux-ide@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git S: Maintained F: drivers/ata/pata_ftide010.c F: drivers/ata/sata_gemini.c @@ -8379,7 +8379,7 @@ F: include/linux/ahci_platform.h LIBATA SATA PROMISE TX2/TX4 CONTROLLER DRIVER M: Mikael Pettersson L: linux-ide@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git S: Maintained F: drivers/ata/sata_promise.* From f3587d76da05f68098ddb1cb3c98cc6a9e8a402c Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 7 Nov 2018 07:37:45 -0700 Subject: [PATCH 231/356] block: Clear kernel memory before copying to user If the kernel allocates a bounce buffer for user read data, this memory needs to be cleared before copying it to the user, otherwise it may leak kernel memory to user space. Laurence Oberman Signed-off-by: Keith Busch Signed-off-by: Jens Axboe --- block/bio.c | 1 + 1 file changed, 1 insertion(+) diff --git a/block/bio.c b/block/bio.c index 4a5a036268fb..9a9c59067521 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1260,6 +1260,7 @@ struct bio *bio_copy_user_iov(struct request_queue *q, if (ret) goto cleanup; } else { + zero_fill_bio(bio); iov_iter_advance(iter, bio->bi_iter.bi_size); } From 3c7eda0b65ad279dd2f26908d2f4bd088da93996 Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Wed, 24 Oct 2018 12:11:35 +0800 Subject: [PATCH 232/356] drm/amd/powerplay: set a default fclk/gfxclk ratio Otherwise big gap between these two clocks may causes some hangs. Signed-off-by: Evan Quan Reviewed-by: Feifei Xu Signed-off-by: Alex Deucher --- .../gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c | 16 ++++++++++++++++ .../gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h | 1 + drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h | 3 ++- 3 files changed, 19 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c index 57143d51e3ee..8bf76108cf39 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c @@ -120,6 +120,7 @@ static void vega20_set_default_registry_data(struct pp_hwmgr *hwmgr) data->registry_data.disable_auto_wattman = 1; data->registry_data.auto_wattman_debug = 0; data->registry_data.auto_wattman_sample_period = 100; + data->registry_data.fclk_gfxclk_ratio = 0x3F6CCCCD; data->registry_data.auto_wattman_threshold = 50; data->registry_data.gfxoff_controlled_by_driver = 1; data->gfxoff_allowed = false; @@ -829,6 +830,16 @@ static int vega20_enable_all_smu_features(struct pp_hwmgr *hwmgr) return 0; } +static int vega20_send_clock_ratio(struct pp_hwmgr *hwmgr) +{ + struct vega20_hwmgr *data = + (struct vega20_hwmgr *)(hwmgr->backend); + + return smum_send_msg_to_smc_with_parameter(hwmgr, + PPSMC_MSG_SetFclkGfxClkRatio, + data->registry_data.fclk_gfxclk_ratio); +} + static int vega20_disable_all_smu_features(struct pp_hwmgr *hwmgr) { struct vega20_hwmgr *data = @@ -1532,6 +1543,11 @@ static int vega20_enable_dpm_tasks(struct pp_hwmgr *hwmgr) "[EnableDPMTasks] Failed to enable all smu features!", return result); + result = vega20_send_clock_ratio(hwmgr); + PP_ASSERT_WITH_CODE(!result, + "[EnableDPMTasks] Failed to send clock ratio!", + return result); + /* Initialize UVD/VCE powergating state */ vega20_init_powergate_state(hwmgr); diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h index 56fe6a0d42e8..25faaa5c5b10 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h @@ -328,6 +328,7 @@ struct vega20_registry_data { uint8_t disable_auto_wattman; uint32_t auto_wattman_debug; uint32_t auto_wattman_sample_period; + uint32_t fclk_gfxclk_ratio; uint8_t auto_wattman_threshold; uint8_t log_avfs_param; uint8_t enable_enginess; diff --git a/drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h b/drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h index 45d64a81e945..4f63a736ea0e 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h +++ b/drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h @@ -105,7 +105,8 @@ #define PPSMC_MSG_SetSystemVirtualDramAddrHigh 0x4B #define PPSMC_MSG_SetSystemVirtualDramAddrLow 0x4C #define PPSMC_MSG_WaflTest 0x4D -// Unused ID 0x4E to 0x50 +#define PPSMC_MSG_SetFclkGfxClkRatio 0x4E +// Unused ID 0x4F to 0x50 #define PPSMC_MSG_AllowGfxOff 0x51 #define PPSMC_MSG_DisallowGfxOff 0x52 #define PPSMC_MSG_GetPptLimit 0x53 From 108110a3ffa3483d743f3bff93917ba64dc8edd0 Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Wed, 7 Nov 2018 09:16:07 +0800 Subject: [PATCH 233/356] drm/amd/powerplay: always use fast UCLK switching when UCLK DPM enabled With UCLK DPM enabled, slow switching is not supported any more. Signed-off-by: Evan Quan Reviewed-by: Feifei Xu Signed-off-by: Alex Deucher --- .../drm/amd/powerplay/hwmgr/vega20_hwmgr.c | 37 +++++++++---------- 1 file changed, 17 insertions(+), 20 deletions(-) diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c index 8bf76108cf39..99861f32b1f9 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c @@ -830,6 +830,18 @@ static int vega20_enable_all_smu_features(struct pp_hwmgr *hwmgr) return 0; } +static int vega20_notify_smc_display_change(struct pp_hwmgr *hwmgr) +{ + struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend); + + if (data->smu_features[GNLD_DPM_UCLK].enabled) + return smum_send_msg_to_smc_with_parameter(hwmgr, + PPSMC_MSG_SetUclkFastSwitch, + 1); + + return 0; +} + static int vega20_send_clock_ratio(struct pp_hwmgr *hwmgr) { struct vega20_hwmgr *data = @@ -1543,6 +1555,11 @@ static int vega20_enable_dpm_tasks(struct pp_hwmgr *hwmgr) "[EnableDPMTasks] Failed to enable all smu features!", return result); + result = vega20_notify_smc_display_change(hwmgr); + PP_ASSERT_WITH_CODE(!result, + "[EnableDPMTasks] Failed to notify smc display change!", + return result); + result = vega20_send_clock_ratio(hwmgr); PP_ASSERT_WITH_CODE(!result, "[EnableDPMTasks] Failed to send clock ratio!", @@ -1988,19 +2005,6 @@ static int vega20_read_sensor(struct pp_hwmgr *hwmgr, int idx, return ret; } -static int vega20_notify_smc_display_change(struct pp_hwmgr *hwmgr, - bool has_disp) -{ - struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend); - - if (data->smu_features[GNLD_DPM_UCLK].enabled) - return smum_send_msg_to_smc_with_parameter(hwmgr, - PPSMC_MSG_SetUclkFastSwitch, - has_disp ? 1 : 0); - - return 0; -} - int vega20_display_clock_voltage_request(struct pp_hwmgr *hwmgr, struct pp_display_clock_request *clock_req) { @@ -2060,13 +2064,6 @@ static int vega20_notify_smc_display_config_after_ps_adjustment( struct pp_display_clock_request clock_req; int ret = 0; - if ((hwmgr->display_config->num_display > 1) && - !hwmgr->display_config->multi_monitor_in_sync && - !hwmgr->display_config->nb_pstate_switch_disable) - vega20_notify_smc_display_change(hwmgr, false); - else - vega20_notify_smc_display_change(hwmgr, true); - min_clocks.dcefClock = hwmgr->display_config->min_dcef_set_clk; min_clocks.dcefClockInSR = hwmgr->display_config->min_dcef_deep_sleep_set_clk; min_clocks.memoryClock = hwmgr->display_config->min_mem_set_clock; From 8be17ac95f8451b51f636622d8d4b8674334f468 Mon Sep 17 00:00:00 2001 From: "Jerry (Fangzhi) Zuo" Date: Tue, 30 Oct 2018 14:28:49 -0400 Subject: [PATCH 234/356] drm/amd/display: Cleanup MST non-atomic code workaround [why] It is not correct to touch aconnector within atomic_check. [How] It was added as workaround before, and no longer needed. Signed-off-by: Jerry (Fangzhi) Zuo Reviewed-by: Harry Wentland Reviewed-by: Lyude Paul Signed-off-by: Alex Deucher --- .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 15 +++----- .../display/amdgpu_dm/amdgpu_dm_mst_types.c | 34 ------------------- .../display/amdgpu_dm/amdgpu_dm_mst_types.h | 1 - 3 files changed, 4 insertions(+), 46 deletions(-) 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 d3f5cb1795bf..c1262f62cd9f 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2703,18 +2703,11 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, drm_connector = &aconnector->base; if (!aconnector->dc_sink) { - /* - * Create dc_sink when necessary to MST - * Don't apply fake_sink to MST - */ - if (aconnector->mst_port) { - dm_dp_mst_dc_sink_create(drm_connector); - return stream; + if (!aconnector->mst_port) { + sink = create_fake_sink(aconnector); + if (!sink) + return stream; } - - sink = create_fake_sink(aconnector); - if (!sink) - return stream; } else { sink = aconnector->dc_sink; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 03601d717fed..03e98967d6c2 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -205,40 +205,6 @@ static const struct drm_connector_funcs dm_dp_mst_connector_funcs = { .atomic_get_property = amdgpu_dm_connector_atomic_get_property }; -void dm_dp_mst_dc_sink_create(struct drm_connector *connector) -{ - struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); - struct dc_sink *dc_sink; - struct dc_sink_init_data init_params = { - .link = aconnector->dc_link, - .sink_signal = SIGNAL_TYPE_DISPLAY_PORT_MST }; - - /* FIXME none of this is safe. we shouldn't touch aconnector here in - * atomic_check - */ - - /* - * TODO: Need to further figure out why ddc.algo is NULL while MST port exists - */ - if (!aconnector->port || !aconnector->port->aux.ddc.algo) - return; - - ASSERT(aconnector->edid); - - dc_sink = dc_link_add_remote_sink( - aconnector->dc_link, - (uint8_t *)aconnector->edid, - (aconnector->edid->extensions + 1) * EDID_LENGTH, - &init_params); - - dc_sink->priv = aconnector; - aconnector->dc_sink = dc_sink; - - if (aconnector->dc_sink) - amdgpu_dm_update_freesync_caps( - connector, aconnector->edid); -} - static int dm_dp_mst_get_modes(struct drm_connector *connector) { struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h index 8cf51da26657..2da851b40042 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h @@ -31,6 +31,5 @@ struct amdgpu_dm_connector; void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm, struct amdgpu_dm_connector *aconnector); -void dm_dp_mst_dc_sink_create(struct drm_connector *connector); #endif From 0e6613e46fed29316f33acf86e1d1568288638b5 Mon Sep 17 00:00:00 2001 From: "Jerry (Fangzhi) Zuo" Date: Tue, 30 Oct 2018 14:37:16 -0400 Subject: [PATCH 235/356] drm/amd/display: Drop reusing drm connector for MST [why] It is not safe to keep existing connector while entire topology has been removed. Could lead potential impact to uapi. Entirely unregister all the connectors on the topology, and use a new set of connectors when the topology is plugged back on. [How] Remove the drm connector entirely each time when the corresponding MST topology is gone. When hotunplug a connector (e.g., DP2) 1. Remove connector from userspace. 2. Drop it's reference. When hotplug back on: 1. Detect new topology, and create new connectors. 2. Notify userspace with sysfs hotplug event. 3. Reprobe new connectors, and reassign CRTC from old (e.g., DP2) to new (e.g., DP3) connector. Signed-off-by: Jerry (Fangzhi) Zuo Reviewed-by: Harry Wentland Reviewed-by: Lyude Paul Signed-off-by: Alex Deucher --- .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h | 2 - .../display/amdgpu_dm/amdgpu_dm_mst_types.c | 40 ++++--------------- 2 files changed, 7 insertions(+), 35 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index 978b34a5011c..924a38a1fc44 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -160,8 +160,6 @@ struct amdgpu_dm_connector { struct mutex hpd_lock; bool fake_enable; - - bool mst_connected; }; #define to_amdgpu_dm_connector(x) container_of(x, struct amdgpu_dm_connector, base) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 03e98967d6c2..31126eb23a74 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -320,25 +320,6 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr, struct amdgpu_device *adev = dev->dev_private; struct amdgpu_dm_connector *aconnector; struct drm_connector *connector; - struct drm_connector_list_iter conn_iter; - - drm_connector_list_iter_begin(dev, &conn_iter); - drm_for_each_connector_iter(connector, &conn_iter) { - aconnector = to_amdgpu_dm_connector(connector); - if (aconnector->mst_port == master - && !aconnector->port) { - DRM_INFO("DM_MST: reusing connector: %p [id: %d] [master: %p]\n", - aconnector, connector->base.id, aconnector->mst_port); - - aconnector->port = port; - drm_connector_set_path_property(connector, pathprop); - - drm_connector_list_iter_end(&conn_iter); - aconnector->mst_connected = true; - return &aconnector->base; - } - } - drm_connector_list_iter_end(&conn_iter); aconnector = kzalloc(sizeof(*aconnector), GFP_KERNEL); if (!aconnector) @@ -387,8 +368,6 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr, */ amdgpu_dm_connector_funcs_reset(connector); - aconnector->mst_connected = true; - DRM_INFO("DM_MST: added connector: %p [id: %d] [master: %p]\n", aconnector, connector->base.id, aconnector->mst_port); @@ -400,6 +379,9 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr, static void dm_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr, struct drm_connector *connector) { + struct amdgpu_dm_connector *master = container_of(mgr, struct amdgpu_dm_connector, mst_mgr); + struct drm_device *dev = master->base.dev; + struct amdgpu_device *adev = dev->dev_private; struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); DRM_INFO("DM_MST: Disabling connector: %p [id: %d] [master: %p]\n", @@ -413,7 +395,10 @@ static void dm_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr, aconnector->dc_sink = NULL; } - aconnector->mst_connected = false; + drm_connector_unregister(connector); + if (adev->mode_info.rfbdev) + drm_fb_helper_remove_one_connector(&adev->mode_info.rfbdev->helper, connector); + drm_connector_put(connector); } static void dm_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr) @@ -424,18 +409,10 @@ static void dm_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr) drm_kms_helper_hotplug_event(dev); } -static void dm_dp_mst_link_status_reset(struct drm_connector *connector) -{ - mutex_lock(&connector->dev->mode_config.mutex); - drm_connector_set_link_status_property(connector, DRM_MODE_LINK_STATUS_BAD); - mutex_unlock(&connector->dev->mode_config.mutex); -} - static void dm_dp_mst_register_connector(struct drm_connector *connector) { struct drm_device *dev = connector->dev; struct amdgpu_device *adev = dev->dev_private; - struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); if (adev->mode_info.rfbdev) drm_fb_helper_add_one_connector(&adev->mode_info.rfbdev->helper, connector); @@ -443,9 +420,6 @@ static void dm_dp_mst_register_connector(struct drm_connector *connector) DRM_ERROR("adev->mode_info.rfbdev is NULL\n"); drm_connector_register(connector); - - if (aconnector->mst_connected) - dm_dp_mst_link_status_reset(connector); } static const struct drm_dp_mst_topology_cbs dm_mst_cbs = { From 63237f8748bdf46dccf79ef8f98f05e9fe799162 Mon Sep 17 00:00:00 2001 From: Lyude Paul Date: Thu, 1 Nov 2018 21:51:49 -0400 Subject: [PATCH 236/356] drm/amd/amdgpu/dm: Fix dm_dp_create_fake_mst_encoder() [why] Removing connector reusage from DM to match the rest of the tree ended up revealing an issue that was surprisingly subtle. The original amdgpu code for DC that was submitted appears to have left a chunk in dm_dp_create_fake_mst_encoder() that tries to find a "master encoder", the likes of which isn't actually used or stored anywhere. It does so at the wrong time as well by trying to access parts of the drm_connector from the encoder init before it's actually been initialized. This results in a NULL pointer deref on MST hotplugs: [ 160.696613] BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 [ 160.697234] PGD 0 P4D 0 [ 160.697814] Oops: 0010 [#1] SMP PTI [ 160.698430] CPU: 2 PID: 64 Comm: kworker/2:1 Kdump: loaded Tainted: G O 4.19.0Lyude-Test+ #2 [ 160.699020] Hardware name: HP HP ZBook 15 G4/8275, BIOS P70 Ver. 01.22 05/17/2018 [ 160.699672] Workqueue: events_long drm_dp_mst_link_probe_work [drm_kms_helper] [ 160.700322] RIP: 0010: (null) [ 160.700920] Code: Bad RIP value. [ 160.701541] RSP: 0018:ffffc9000029fc78 EFLAGS: 00010206 [ 160.702183] RAX: 0000000000000000 RBX: ffff8804440ed468 RCX: ffff8804440e9158 [ 160.702778] RDX: 0000000000000000 RSI: ffff8804556c5700 RDI: ffff8804440ed000 [ 160.703408] RBP: ffff880458e21800 R08: 0000000000000002 R09: 000000005fca0a25 [ 160.704002] R10: ffff88045a077a3d R11: ffff88045a077a3c R12: ffff8804440ed000 [ 160.704614] R13: ffff880458e21800 R14: ffff8804440e9000 R15: ffff8804440e9000 [ 160.705260] FS: 0000000000000000(0000) GS:ffff88045f280000(0000) knlGS:0000000000000000 [ 160.705854] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 160.706478] CR2: ffffffffffffffd6 CR3: 000000000200a001 CR4: 00000000003606e0 [ 160.707124] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 160.707724] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 160.708372] Call Trace: [ 160.708998] ? dm_dp_add_mst_connector+0xed/0x1d0 [amdgpu] [ 160.709625] ? drm_dp_add_port+0x2fa/0x470 [drm_kms_helper] [ 160.710284] ? wake_up_q+0x54/0x70 [ 160.710877] ? __mutex_unlock_slowpath.isra.18+0xb3/0x110 [ 160.711512] ? drm_dp_dpcd_access+0xe7/0x110 [drm_kms_helper] [ 160.712161] ? drm_dp_send_link_address+0x155/0x1e0 [drm_kms_helper] [ 160.712762] ? drm_dp_check_and_send_link_address+0xa3/0xd0 [drm_kms_helper] [ 160.713408] ? drm_dp_mst_link_probe_work+0x4b/0x80 [drm_kms_helper] [ 160.714013] ? process_one_work+0x1a1/0x3a0 [ 160.714667] ? worker_thread+0x30/0x380 [ 160.715326] ? wq_update_unbound_numa+0x10/0x10 [ 160.715939] ? kthread+0x112/0x130 [ 160.716591] ? kthread_create_worker_on_cpu+0x70/0x70 [ 160.717262] ? ret_from_fork+0x35/0x40 [ 160.717886] Modules linked in: amdgpu(O) vfat fat snd_hda_codec_generic joydev i915 chash gpu_sched ttm i2c_algo_bit drm_kms_helper snd_hda_codec_hdmi hp_wmi syscopyarea iTCO_wdt sysfillrect sparse_keymap sysimgblt fb_sys_fops snd_hda_intel usbhid wmi_bmof drm snd_hda_codec btusb snd_hda_core intel_rapl btrtl x86_pkg_temp_thermal btbcm btintel coretemp snd_pcm crc32_pclmul bluetooth psmouse snd_timer snd pcspkr i2c_i801 mei_me i2c_core soundcore mei tpm_tis wmi tpm_tis_core hp_accel ecdh_generic lis3lv02d tpm video rfkill acpi_pad input_polldev hp_wireless pcc_cpufreq crc32c_intel serio_raw tg3 xhci_pci xhci_hcd [last unloaded: amdgpu] [ 160.720141] CR2: 0000000000000000 Somehow the connector reusage DM was using for MST connectors managed to paper over this issue entirely; hence why this was never caught until now. [how] Since this code isn't used anywhere and seems useless anyway, we can just drop it entirely. This appears to fix the issue on my HP ZBook with an AMD WX4150. Signed-off-by: Lyude Paul Reviewed-by: Harry Wentland Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 31126eb23a74..d02c32a1039c 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -285,12 +285,7 @@ dm_dp_create_fake_mst_encoder(struct amdgpu_dm_connector *connector) struct amdgpu_device *adev = dev->dev_private; struct amdgpu_encoder *amdgpu_encoder; struct drm_encoder *encoder; - const struct drm_connector_helper_funcs *connector_funcs = - connector->base.helper_private; - struct drm_encoder *enc_master = - connector_funcs->best_encoder(&connector->base); - DRM_DEBUG_KMS("enc master is %p\n", enc_master); amdgpu_encoder = kzalloc(sizeof(*amdgpu_encoder), GFP_KERNEL); if (!amdgpu_encoder) return NULL; From de59fae0043f07de5d25e02ca360f7d57bfa5866 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Wed, 7 Nov 2018 22:36:23 -0500 Subject: [PATCH 237/356] ext4: fix buffer leak in __ext4_read_dirblock() on error path Fixes: dc6982ff4db1 ("ext4: refactor code to read directory blocks ...") Signed-off-by: Vasily Averin Signed-off-by: Theodore Ts'o Cc: stable@kernel.org # 3.9 --- fs/ext4/namei.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index d388cce72db2..6a6b90363ef1 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -126,6 +126,7 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, if (!is_dx_block && type == INDEX) { ext4_error_inode(inode, func, line, block, "directory leaf block found instead of index block"); + brelse(bh); return ERR_PTR(-EFSCORRUPTED); } if (!ext4_has_metadata_csum(inode->i_sb) || From d2f007dbe7e4c9583eea6eb04d60001e85c6f1bd Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Mon, 5 Nov 2018 20:55:09 +0100 Subject: [PATCH 238/356] userns: also map extents in the reverse map to kernel IDs The current logic first clones the extent array and sorts both copies, then maps the lower IDs of the forward mapping into the lower namespace, but doesn't map the lower IDs of the reverse mapping. This means that code in a nested user namespace with >5 extents will see incorrect IDs. It also breaks some access checks, like inode_owner_or_capable() and privileged_wrt_inode_uidgid(), so a process can incorrectly appear to be capable relative to an inode. To fix it, we have to make sure that the "lower_first" members of extents in both arrays are translated; and we have to make sure that the reverse map is sorted *after* the translation (since otherwise the translation can break the sorting). This is CVE-2018-18955. Fixes: 6397fac4915a ("userns: bump idmap limits to 340") Cc: stable@vger.kernel.org Signed-off-by: Jann Horn Tested-by: Eric W. Biederman Reviewed-by: Eric W. Biederman Signed-off-by: Eric W. Biederman --- kernel/user_namespace.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index e5222b5fb4fe..923414a246e9 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -974,10 +974,6 @@ static ssize_t map_write(struct file *file, const char __user *buf, if (!new_idmap_permitted(file, ns, cap_setid, &new_map)) goto out; - ret = sort_idmaps(&new_map); - if (ret < 0) - goto out; - ret = -EPERM; /* Map the lower ids from the parent user namespace to the * kernel global id space. @@ -1004,6 +1000,14 @@ static ssize_t map_write(struct file *file, const char __user *buf, e->lower_first = lower_first; } + /* + * If we want to use binary search for lookup, this clones the extent + * array and sorts both copies. + */ + ret = sort_idmaps(&new_map); + if (ret < 0) + goto out; + /* Install the map */ if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) { memcpy(map->extent, new_map.extent, From 96ed82cc1f515a2329f93506129ab1de35429b89 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Wed, 7 Nov 2018 12:06:52 +0000 Subject: [PATCH 239/356] FDDI: defza: Fix SPDX annotation The SPDX annotation for this driver does not match the license text, which specifies GNU GPL 2 or later. Make the two match by correcting the SPDX tag. Signed-off-by: Maciej W. Rozycki Signed-off-by: David S. Miller --- drivers/net/fddi/defza.c | 2 +- drivers/net/fddi/defza.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/fddi/defza.c b/drivers/net/fddi/defza.c index 3b7f10a5f06a..79980eeb0e43 100644 --- a/drivers/net/fddi/defza.c +++ b/drivers/net/fddi/defza.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +// SPDX-License-Identifier: GPL-2.0+ /* FDDI network adapter driver for DEC FDDIcontroller 700/700-C devices. * * Copyright (c) 2018 Maciej W. Rozycki diff --git a/drivers/net/fddi/defza.h b/drivers/net/fddi/defza.h index b06acf32738e..ed659ed17215 100644 --- a/drivers/net/fddi/defza.h +++ b/drivers/net/fddi/defza.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0+ */ /* FDDI network adapter driver for DEC FDDIcontroller 700/700-C devices. * * Copyright (c) 2018 Maciej W. Rozycki From 5f5fae37dbcf37feae48c40d2580dbd67c5df131 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Wed, 7 Nov 2018 12:06:59 +0000 Subject: [PATCH 240/356] FDDI: defza: Add missing comment closing Fix: drivers/net/fddi/defza.h:238:1: warning: "/*" within comment [-Wcomment] by adding a missing comment closing. Signed-off-by: Maciej W. Rozycki Signed-off-by: David S. Miller --- drivers/net/fddi/defza.h | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/fddi/defza.h b/drivers/net/fddi/defza.h index ed659ed17215..93bda61be8e3 100644 --- a/drivers/net/fddi/defza.h +++ b/drivers/net/fddi/defza.h @@ -235,6 +235,7 @@ struct fza_ring_cmd { #define FZA_RING_CMD 0x200400 /* command ring address */ #define FZA_RING_CMD_SIZE 0x40 /* command descriptor ring * size + */ /* Command constants. */ #define FZA_RING_CMD_MASK 0x7fffffff #define FZA_RING_CMD_NOP 0x00000000 /* nop */ From 04453b6b241913f85af013eec187bab776428af5 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Wed, 7 Nov 2018 12:07:05 +0000 Subject: [PATCH 241/356] FDDI: defza: Move SMT Tx data buffer declaration next to its skb Move the temporary data buffer used when tapping into the SMT Tx queue from the outer function level into the conditional block it's actually used in and its containing skb is also declared, making the structure of code better. Signed-off-by: Maciej W. Rozycki Signed-off-by: David S. Miller --- drivers/net/fddi/defza.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/fddi/defza.c b/drivers/net/fddi/defza.c index 79980eeb0e43..bebd0d6d2320 100644 --- a/drivers/net/fddi/defza.c +++ b/drivers/net/fddi/defza.c @@ -784,7 +784,7 @@ err_rx: static void fza_tx_smt(struct net_device *dev) { struct fza_private *fp = netdev_priv(dev); - struct fza_buffer_tx __iomem *smt_tx_ptr, *skb_data_ptr; + struct fza_buffer_tx __iomem *smt_tx_ptr; int i, len; u32 own; @@ -799,6 +799,7 @@ static void fza_tx_smt(struct net_device *dev) if (!netif_queue_stopped(dev)) { if (dev_nit_active(dev)) { + struct fza_buffer_tx *skb_data_ptr; struct sk_buff *skb; /* Length must be a multiple of 4 as only word From 8f5365ebf7b17c35dddbb694b4f0ffd1293a947f Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Wed, 7 Nov 2018 12:07:10 +0000 Subject: [PATCH 242/356] FDDI: defza: Make the driver version string constant The driver version string is obviously not meant to be changed at run time, so mark it `const'. Signed-off-by: Maciej W. Rozycki Signed-off-by: David S. Miller --- drivers/net/fddi/defza.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/fddi/defza.c b/drivers/net/fddi/defza.c index bebd0d6d2320..c5cae8e74dc4 100644 --- a/drivers/net/fddi/defza.c +++ b/drivers/net/fddi/defza.c @@ -56,7 +56,7 @@ #define DRV_VERSION "v.1.1.4" #define DRV_RELDATE "Oct 6 2018" -static char version[] = +static const char version[] = DRV_NAME ": " DRV_VERSION " " DRV_RELDATE " Maciej W. Rozycki\n"; MODULE_AUTHOR("Maciej W. Rozycki "); From 25d202ed820ee347edec0bf3bf553544556bf64b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 22 Oct 2018 10:21:38 -0500 Subject: [PATCH 243/356] mount: Retest MNT_LOCKED in do_umount It was recently pointed out that the one instance of testing MNT_LOCKED outside of the namespace_sem is in ksys_umount. Fix that by adding a test inside of do_umount with namespace_sem and the mount_lock held. As it helps to fail fails the existing test is maintained with an additional comment pointing out that it may be racy because the locks are not held. Cc: stable@vger.kernel.org Reported-by: Al Viro Fixes: 5ff9d8a65ce8 ("vfs: Lock in place mounts from more privileged users") Signed-off-by: "Eric W. Biederman" --- fs/namespace.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/fs/namespace.c b/fs/namespace.c index 98d27da43304..72f10c40fe3f 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1540,8 +1540,13 @@ static int do_umount(struct mount *mnt, int flags) namespace_lock(); lock_mount_hash(); - event++; + /* Recheck MNT_LOCKED with the locks held */ + retval = -EINVAL; + if (mnt->mnt.mnt_flags & MNT_LOCKED) + goto out; + + event++; if (flags & MNT_DETACH) { if (!list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE); @@ -1555,6 +1560,7 @@ static int do_umount(struct mount *mnt, int flags) retval = 0; } } +out: unlock_mount_hash(); namespace_unlock(); return retval; @@ -1645,7 +1651,7 @@ int ksys_umount(char __user *name, int flags) goto dput_and_out; if (!check_mnt(mnt)) goto dput_and_out; - if (mnt->mnt.mnt_flags & MNT_LOCKED) + if (mnt->mnt.mnt_flags & MNT_LOCKED) /* Check optimistically */ goto dput_and_out; retval = -EPERM; if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN)) From df7342b240185d58d3d9665c0bbf0a0f5570ec29 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 25 Oct 2018 09:04:18 -0500 Subject: [PATCH 244/356] mount: Don't allow copying MNT_UNBINDABLE|MNT_LOCKED mounts Jonathan Calmels from NVIDIA reported that he's able to bypass the mount visibility security check in place in the Linux kernel by using a combination of the unbindable property along with the private mount propagation option to allow a unprivileged user to see a path which was purposefully hidden by the root user. Reproducer: # Hide a path to all users using a tmpfs root@castiana:~# mount -t tmpfs tmpfs /sys/devices/ root@castiana:~# # As an unprivileged user, unshare user namespace and mount namespace stgraber@castiana:~$ unshare -U -m -r # Confirm the path is still not accessible root@castiana:~# ls /sys/devices/ # Make /sys recursively unbindable and private root@castiana:~# mount --make-runbindable /sys root@castiana:~# mount --make-private /sys # Recursively bind-mount the rest of /sys over to /mnnt root@castiana:~# mount --rbind /sys/ /mnt # Access our hidden /sys/device as an unprivileged user root@castiana:~# ls /mnt/devices/ breakpoint cpu cstate_core cstate_pkg i915 intel_pt isa kprobe LNXSYSTM:00 msr pci0000:00 platform pnp0 power software system tracepoint uncore_arb uncore_cbox_0 uncore_cbox_1 uprobe virtual Solve this by teaching copy_tree to fail if a mount turns out to be both unbindable and locked. Cc: stable@vger.kernel.org Fixes: 5ff9d8a65ce8 ("vfs: Lock in place mounts from more privileged users") Reported-by: Jonathan Calmels Signed-off-by: "Eric W. Biederman" --- fs/namespace.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/fs/namespace.c b/fs/namespace.c index 72f10c40fe3f..e0e0f9cf6c30 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1734,8 +1734,14 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, for (s = r; s; s = next_mnt(s, r)) { if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(s)) { - s = skip_mnt_tree(s); - continue; + if (s->mnt.mnt_flags & MNT_LOCKED) { + /* Both unbindable and locked. */ + q = ERR_PTR(-EPERM); + goto out; + } else { + s = skip_mnt_tree(s); + continue; + } } if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(s->mnt.mnt_root)) { From e84b47941e15e6666afb8ee8b21d1c3fc1a013af Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= Date: Wed, 7 Nov 2018 17:50:52 +0100 Subject: [PATCH 245/356] ibmvnic: fix accelerated VLAN handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Don't request tag insertion when it isn't present in outgoing skb. Signed-off-by: Michał Mirosław Signed-off-by: David S. Miller --- drivers/net/ethernet/ibm/ibmvnic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 7893beffcc71..c9d5d0a7fbf1 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1545,7 +1545,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_crq.v1.sge_len = cpu_to_be32(skb->len); tx_crq.v1.ioba = cpu_to_be64(data_dma_addr); - if (adapter->vlan_header_insertion) { + if (adapter->vlan_header_insertion && skb_vlan_tag_present(skb)) { tx_crq.v1.flags2 |= IBMVNIC_TX_VLAN_INSERT; tx_crq.v1.vlan_id = cpu_to_be16(skb->vlan_tci); } From b25ddb00bc1b96613edcb525f19203a7d1405fce Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= Date: Wed, 7 Nov 2018 17:50:53 +0100 Subject: [PATCH 246/356] qlcnic: remove assumption that vlan_tci != 0 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit VLAN.TCI == 0 is perfectly valid (802.1p), so allow it to be accelerated. Signed-off-by: Michał Mirosław Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c index 9647578cbe6a..14f26bf3b388 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c @@ -459,7 +459,7 @@ static int qlcnic_tx_pkt(struct qlcnic_adapter *adapter, struct cmd_desc_type0 *first_desc, struct sk_buff *skb, struct qlcnic_host_tx_ring *tx_ring) { - u8 l4proto, opcode = 0, hdr_len = 0; + u8 l4proto, opcode = 0, hdr_len = 0, tag_vlan = 0; u16 flags = 0, vlan_tci = 0; int copied, offset, copy_len, size; struct cmd_desc_type0 *hwdesc; @@ -472,14 +472,16 @@ static int qlcnic_tx_pkt(struct qlcnic_adapter *adapter, flags = QLCNIC_FLAGS_VLAN_TAGGED; vlan_tci = ntohs(vh->h_vlan_TCI); protocol = ntohs(vh->h_vlan_encapsulated_proto); + tag_vlan = 1; } else if (skb_vlan_tag_present(skb)) { flags = QLCNIC_FLAGS_VLAN_OOB; vlan_tci = skb_vlan_tag_get(skb); + tag_vlan = 1; } if (unlikely(adapter->tx_pvid)) { - if (vlan_tci && !(adapter->flags & QLCNIC_TAGGING_ENABLED)) + if (tag_vlan && !(adapter->flags & QLCNIC_TAGGING_ENABLED)) return -EIO; - if (vlan_tci && (adapter->flags & QLCNIC_TAGGING_ENABLED)) + if (tag_vlan && (adapter->flags & QLCNIC_TAGGING_ENABLED)) goto set_flags; flags = QLCNIC_FLAGS_VLAN_OOB; From e6a2d72c10405b30ddba5af2e44a9d3d925a56d3 Mon Sep 17 00:00:00 2001 From: Juri Lelli Date: Wed, 7 Nov 2018 12:10:32 +0100 Subject: [PATCH 247/356] posix-cpu-timers: Remove useless call to check_dl_overrun() check_dl_overrun() is used to send a SIGXCPU to users that asked to be informed when a SCHED_DEADLINE runtime overruns occur. The function is called by check_thread_timers() already, so the call in check_process_timers() is redundant/wrong (even though harmless). Remove it. Fixes: 34be39305a77 ("sched/deadline: Implement "runtime overrun signal" support") Signed-off-by: Juri Lelli Signed-off-by: Thomas Gleixner Reviewed-by: Daniel Bristot de Oliveira Reviewed-by: Steven Rostedt (VMware) Cc: linux-rt-users@vger.kernel.org Cc: mtk.manpages@gmail.com Cc: Mathieu Poirier Cc: Peter Zijlstra Cc: Luca Abeni Cc: Claudio Scordino Link: https://lkml.kernel.org/r/20181107111032.32291-1-juri.lelli@redhat.com --- kernel/time/posix-cpu-timers.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index ce32cf741b25..8f0644af40be 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -917,9 +917,6 @@ static void check_process_timers(struct task_struct *tsk, struct task_cputime cputime; unsigned long soft; - if (dl_task(tsk)) - check_dl_overrun(tsk); - /* * If cputimer is not running, then there are no active * process wide timers (POSIX 1.b, itimers, RLIMIT_CPU). From 0bb2ae1b26e1fb7543ec7474cdd374ac4b88c4da Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Mon, 29 Oct 2018 08:11:33 +0000 Subject: [PATCH 248/356] s390/perf: Change CPUM_CF return code in event init function The function perf_init_event() creates a new event and assignes it to a PMU. This a done in a loop over all existing PMUs. For each listed PMU the event init function is called and if this function does return any other error than -ENOENT, the loop is terminated the creation of the event fails. If the event is invalid, return -ENOENT to try other PMUs. Signed-off-by: Thomas Richter Reviewed-by: Hendrik Brueckner Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/perf_cpum_cf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index cc085e2d2ce9..74091fd3101e 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -373,7 +373,7 @@ static int __hw_perf_event_init(struct perf_event *event) return -ENOENT; if (ev > PERF_CPUM_CF_MAX_CTR) - return -EINVAL; + return -ENOENT; /* Obtain the counter set to which the specified counter belongs */ set = get_counter_set(ev); From 9c8e0a1b683525464a2abe9fb4b54404a50ed2b4 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 25 Oct 2018 12:05:11 -0500 Subject: [PATCH 249/356] mount: Prevent MNT_DETACH from disconnecting locked mounts Timothy Baldwin wrote: > As per mount_namespaces(7) unprivileged users should not be able to look under mount points: > > Mounts that come as a single unit from more privileged mount are locked > together and may not be separated in a less privileged mount namespace. > > However they can: > > 1. Create a mount namespace. > 2. In the mount namespace open a file descriptor to the parent of a mount point. > 3. Destroy the mount namespace. > 4. Use the file descriptor to look under the mount point. > > I have reproduced this with Linux 4.16.18 and Linux 4.18-rc8. > > The setup: > > $ sudo sysctl kernel.unprivileged_userns_clone=1 > kernel.unprivileged_userns_clone = 1 > $ mkdir -p A/B/Secret > $ sudo mount -t tmpfs hide A/B > > > "Secret" is indeed hidden as expected: > > $ ls -lR A > A: > total 0 > drwxrwxrwt 2 root root 40 Feb 12 21:08 B > > A/B: > total 0 > > > The attack revealing "Secret": > > $ unshare -Umr sh -c "exec unshare -m ls -lR /proc/self/fd/4/ 4 /proc/self/fd/4/: > total 0 > drwxr-xr-x 3 root root 60 Feb 12 21:08 B > > /proc/self/fd/4/B: > total 0 > drwxr-xr-x 2 root root 40 Feb 12 21:08 Secret > > /proc/self/fd/4/B/Secret: > total 0 I tracked this down to put_mnt_ns running passing UMOUNT_SYNC and disconnecting all of the mounts in a mount namespace. Fix this by factoring drop_mounts out of drop_collected_mounts and passing 0 instead of UMOUNT_SYNC. There are two possible behavior differences that result from this. - No longer setting UMOUNT_SYNC will no longer set MNT_SYNC_UMOUNT on the vfsmounts being unmounted. This effects the lazy rcu walk by kicking the walk out of rcu mode and forcing it to be a non-lazy walk. - No longer disconnecting locked mounts will keep some mounts around longer as they stay because the are locked to other mounts. There are only two users of drop_collected mounts: audit_tree.c and put_mnt_ns. In audit_tree.c the mounts are private and there are no rcu lazy walks only calls to iterate_mounts. So the changes should have no effect except for a small timing effect as the connected mounts are disconnected. In put_mnt_ns there may be references from process outside the mount namespace to the mounts. So the mounts remaining connected will be the bug fix that is needed. That rcu walks are allowed to continue appears not to be a problem especially as the rcu walk change was about an implementation detail not about semantics. Cc: stable@vger.kernel.org Fixes: 5ff9d8a65ce8 ("vfs: Lock in place mounts from more privileged users") Reported-by: Timothy Baldwin Tested-by: Timothy Baldwin Signed-off-by: "Eric W. Biederman" --- fs/namespace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/namespace.c b/fs/namespace.c index e0e0f9cf6c30..74f64294a410 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1794,7 +1794,7 @@ void drop_collected_mounts(struct vfsmount *mnt) { namespace_lock(); lock_mount_hash(); - umount_tree(real_mount(mnt), UMOUNT_SYNC); + umount_tree(real_mount(mnt), 0); unlock_mount_hash(); namespace_unlock(); } From 24efee412c75843755da0ddd7bbc2db2ce9129f5 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Tue, 6 Nov 2018 22:52:11 +0100 Subject: [PATCH 250/356] Compiler Attributes: improve explanation of header Explain better what "optional" attributes are, and avoid calling them so to avoid confusion. Simply retain "Optional" as a word to look for in the comments. Moreover, add a couple sentences to explain a bit more the intention and the documentation links. Signed-off-by: Miguel Ojeda --- include/linux/compiler_attributes.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 6b28c1b7310c..f8c400ba1929 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -4,22 +4,26 @@ /* * The attributes in this file are unconditionally defined and they directly - * map to compiler attribute(s) -- except those that are optional. + * map to compiler attribute(s), unless one of the compilers does not support + * the attribute. In that case, __has_attribute is used to check for support + * and the reason is stated in its comment ("Optional: ..."). * * Any other "attributes" (i.e. those that depend on a configuration option, * on a compiler, on an architecture, on plugins, on other attributes...) * should be defined elsewhere (e.g. compiler_types.h or compiler-*.h). + * The intention is to keep this file as simple as possible, as well as + * compiler- and version-agnostic (e.g. avoiding GCC_VERSION checks). * * This file is meant to be sorted (by actual attribute name, * not by #define identifier). Use the __attribute__((__name__)) syntax * (i.e. with underscores) to avoid future collisions with other macros. - * If an attribute is optional, state the reason in the comment. + * Provide links to the documentation of each supported compiler, if it exists. */ /* - * To check for optional attributes, we use __has_attribute, which is supported - * on gcc >= 5, clang >= 2.9 and icc >= 17. In the meantime, to support - * 4.6 <= gcc < 5, we implement __has_attribute by hand. + * __has_attribute is supported on gcc >= 5, clang >= 2.9 and icc >= 17. + * In the meantime, to support 4.6 <= gcc < 5, we implement __has_attribute + * by hand. * * sparse does not support __has_attribute (yet) and defines __GNUC_MINOR__ * depending on the compiler used to build it; however, these attributes have From 943210ba807ec50aafa2fa7b13bd6d36a478969b Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Tue, 23 Oct 2018 11:28:28 -0400 Subject: [PATCH 251/356] vt: fix broken display when running aptitude If you run aptitude on framebuffer console, the display is corrupted. The corruption is caused by the commit d8ae7242. The patch adds "offset" to "start" when calling scr_memsetw, but it forgets to do the same addition on a subsequent call to do_update_region. Signed-off-by: Mikulas Patocka Fixes: d8ae72427187 ("vt: preserve unicode values corresponding to screen characters") Reviewed-by: Nicolas Pitre Cc: stable@vger.kernel.org # 4.19 Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/vt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 5f1183b0b89d..476ec4b1b86c 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -1551,7 +1551,7 @@ static void csi_K(struct vc_data *vc, int vpar) scr_memsetw(start + offset, vc->vc_video_erase_char, 2 * count); vc->vc_need_wrap = 0; if (con_should_update(vc)) - do_update_region(vc, (unsigned long) start, count); + do_update_region(vc, (unsigned long)(start + offset), count); } static void csi_X(struct vc_data *vc, int vpar) /* erase the following vpar positions */ From 991a25194097006ec1e0d2e0814ff920e59e3465 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Mon, 22 Oct 2018 09:19:04 -0700 Subject: [PATCH 252/356] termios, tty/tty_baudrate.c: fix buffer overrun On architectures with CBAUDEX == 0 (Alpha and PowerPC), the code in tty_baudrate.c does not do any limit checking on the tty_baudrate[] array, and in fact a buffer overrun is possible on both architectures. Add a limit check to prevent that situation. This will be followed by a much bigger cleanup/simplification patch. Signed-off-by: H. Peter Anvin (Intel) Requested-by: Cc: Johan Hovold Cc: Jiri Slaby Cc: Al Viro Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Thomas Gleixner Cc: Kate Stewart Cc: Philippe Ombredanne Cc: Eugene Syromiatnikov Cc: Alan Cox Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_baudrate.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/tty/tty_baudrate.c b/drivers/tty/tty_baudrate.c index 7576ceace571..f438eaa68246 100644 --- a/drivers/tty/tty_baudrate.c +++ b/drivers/tty/tty_baudrate.c @@ -77,7 +77,7 @@ speed_t tty_termios_baud_rate(struct ktermios *termios) else cbaud += 15; } - return baud_table[cbaud]; + return cbaud >= n_baud_table ? 0 : baud_table[cbaud]; } EXPORT_SYMBOL(tty_termios_baud_rate); @@ -113,7 +113,7 @@ speed_t tty_termios_input_baud_rate(struct ktermios *termios) else cbaud += 15; } - return baud_table[cbaud]; + return cbaud >= n_baud_table ? 0 : baud_table[cbaud]; #else /* IBSHIFT */ return tty_termios_baud_rate(termios); #endif /* IBSHIFT */ From d0ffb805b729322626639336986bc83fc2e60871 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin (Intel)" Date: Mon, 22 Oct 2018 09:19:05 -0700 Subject: [PATCH 253/356] arch/alpha, termios: implement BOTHER, IBSHIFT and termios2 Alpha has had c_ispeed and c_ospeed, but still set speeds in c_cflags using arbitrary flags. Because BOTHER is not defined, the general Linux code doesn't allow setting arbitrary baud rates, and because CBAUDEX == 0, we can have an array overrun of the baud_rate[] table in drivers/tty/tty_baudrate.c if (c_cflags & CBAUD) == 037. Resolve both problems by #defining BOTHER to 037 on Alpha. However, userspace still needs to know if setting BOTHER is actually safe given legacy kernels (does anyone actually care about that on Alpha anymore?), so enable the TCGETS2/TCSETS*2 ioctls on Alpha, even though they use the same structure. Define struct termios2 just for compatibility; it is the exact same structure as struct termios. In a future patchset, this will be cleaned up so the uapi headers are usable from libc. Signed-off-by: H. Peter Anvin (Intel) Cc: Jiri Slaby Cc: Al Viro Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Thomas Gleixner Cc: Kate Stewart Cc: Philippe Ombredanne Cc: Eugene Syromiatnikov Cc: Cc: Cc: Johan Hovold Cc: Alan Cox Cc: Signed-off-by: Greg Kroah-Hartman --- arch/alpha/include/asm/termios.h | 8 +++++++- arch/alpha/include/uapi/asm/ioctls.h | 5 +++++ arch/alpha/include/uapi/asm/termbits.h | 17 +++++++++++++++++ 3 files changed, 29 insertions(+), 1 deletion(-) diff --git a/arch/alpha/include/asm/termios.h b/arch/alpha/include/asm/termios.h index 6a8c53dec57e..b7c77bb1bfd2 100644 --- a/arch/alpha/include/asm/termios.h +++ b/arch/alpha/include/asm/termios.h @@ -73,9 +73,15 @@ }) #define user_termios_to_kernel_termios(k, u) \ - copy_from_user(k, u, sizeof(struct termios)) + copy_from_user(k, u, sizeof(struct termios2)) #define kernel_termios_to_user_termios(u, k) \ + copy_to_user(u, k, sizeof(struct termios2)) + +#define user_termios_to_kernel_termios_1(k, u) \ + copy_from_user(k, u, sizeof(struct termios)) + +#define kernel_termios_to_user_termios_1(u, k) \ copy_to_user(u, k, sizeof(struct termios)) #endif /* _ALPHA_TERMIOS_H */ diff --git a/arch/alpha/include/uapi/asm/ioctls.h b/arch/alpha/include/uapi/asm/ioctls.h index 3729d92d3fa8..dc8c20ac7191 100644 --- a/arch/alpha/include/uapi/asm/ioctls.h +++ b/arch/alpha/include/uapi/asm/ioctls.h @@ -32,6 +32,11 @@ #define TCXONC _IO('t', 30) #define TCFLSH _IO('t', 31) +#define TCGETS2 _IOR('T', 42, struct termios2) +#define TCSETS2 _IOW('T', 43, struct termios2) +#define TCSETSW2 _IOW('T', 44, struct termios2) +#define TCSETSF2 _IOW('T', 45, struct termios2) + #define TIOCSWINSZ _IOW('t', 103, struct winsize) #define TIOCGWINSZ _IOR('t', 104, struct winsize) #define TIOCSTART _IO('t', 110) /* start output, like ^Q */ diff --git a/arch/alpha/include/uapi/asm/termbits.h b/arch/alpha/include/uapi/asm/termbits.h index de6c8360fbe3..4575ba34a0ea 100644 --- a/arch/alpha/include/uapi/asm/termbits.h +++ b/arch/alpha/include/uapi/asm/termbits.h @@ -26,6 +26,19 @@ struct termios { speed_t c_ospeed; /* output speed */ }; +/* Alpha has identical termios and termios2 */ + +struct termios2 { + tcflag_t c_iflag; /* input mode flags */ + tcflag_t c_oflag; /* output mode flags */ + tcflag_t c_cflag; /* control mode flags */ + tcflag_t c_lflag; /* local mode flags */ + cc_t c_cc[NCCS]; /* control characters */ + cc_t c_line; /* line discipline (== c_cc[19]) */ + speed_t c_ispeed; /* input speed */ + speed_t c_ospeed; /* output speed */ +}; + /* Alpha has matching termios and ktermios */ struct ktermios { @@ -152,6 +165,7 @@ struct ktermios { #define B3000000 00034 #define B3500000 00035 #define B4000000 00036 +#define BOTHER 00037 #define CSIZE 00001400 #define CS5 00000000 @@ -169,6 +183,9 @@ struct ktermios { #define CMSPAR 010000000000 /* mark or space (stick) parity */ #define CRTSCTS 020000000000 /* flow control */ +#define CIBAUD 07600000 +#define IBSHIFT 16 + /* c_lflag bits */ #define ISIG 0x00000080 #define ICANON 0x00000100 From 0033dfd92a5646a78025e86f8df4d5b18181ba2c Mon Sep 17 00:00:00 2001 From: Anton Ivanov Date: Thu, 8 Nov 2018 13:07:23 +0000 Subject: [PATCH 254/356] ubd: fix missing initialization of io_req The SYNC path doesn't initialize io_req->error, which can cause random errors. Before the conversion to blk-mq, we always completed requests with BLK_STS_OK status, but now we actually look at the error field and this issue becomes apparent. Signed-off-by: Anton Ivanov [axboe: fixed up commit message to explain what is actually going on] Signed-off-by: Jens Axboe --- arch/um/drivers/ubd_kern.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 08831f5d83db..28c40624bcb6 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -1305,6 +1305,7 @@ static int ubd_queue_one_vec(struct blk_mq_hw_ctx *hctx, struct request *req, io_req->fds[0] = dev->cow.fd; else io_req->fds[0] = dev->fd; + io_req->error = 0; if (req_op(req) == REQ_OP_FLUSH) { io_req->op = UBD_FLUSH; @@ -1313,9 +1314,7 @@ static int ubd_queue_one_vec(struct blk_mq_hw_ctx *hctx, struct request *req, io_req->cow_offset = -1; io_req->offset = off; io_req->length = bvec->bv_len; - io_req->error = 0; io_req->sector_mask = 0; - io_req->op = rq_data_dir(req) == READ ? UBD_READ : UBD_WRITE; io_req->offsets[0] = 0; io_req->offsets[1] = dev->cow.data_offset; From bb39ba6a8deab70752b836a36c62205b1c65b559 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Thu, 8 Nov 2018 06:34:34 +0000 Subject: [PATCH 255/356] sata_rcar: convert to SPDX identifiers This patch updates license to use SPDX-License-Identifier instead of verbose license text. Signed-off-by: Kuninori Morimoto Signed-off-by: Jens Axboe --- drivers/ata/sata_rcar.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c index 10ecb232245d..4b1ff5bc256a 100644 --- a/drivers/ata/sata_rcar.c +++ b/drivers/ata/sata_rcar.c @@ -1,14 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * Renesas R-Car SATA driver * * Author: Vladimir Barinov * Copyright (C) 2013-2015 Cogent Embedded, Inc. * Copyright (C) 2013-2015 Renesas Solutions Corp. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. */ #include From c2c6d3ce0d9a1fae4472fc10755372d022a487a4 Mon Sep 17 00:00:00 2001 From: Luis Henriques Date: Tue, 23 Oct 2018 16:53:14 +0000 Subject: [PATCH 256/356] ceph: add destination file data sync before doing any remote copy MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If we try to copy into a file that was just written, any data that is remote copied will be overwritten by our buffered writes once they are flushed.  When this happens, the call to invalidate_inode_pages2_range will also return a -EBUSY error. This patch fixes this by also sync'ing the destination file before starting any copy. Fixes: 503f82a9932d ("ceph: support copy_file_range file operation") Signed-off-by: Luis Henriques Reviewed-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- fs/ceph/file.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 27cad84dab23..189df668b6a0 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1931,10 +1931,17 @@ static ssize_t ceph_copy_file_range(struct file *src_file, loff_t src_off, if (!prealloc_cf) return -ENOMEM; - /* Start by sync'ing the source file */ + /* Start by sync'ing the source and destination files */ ret = file_write_and_wait_range(src_file, src_off, (src_off + len)); - if (ret < 0) + if (ret < 0) { + dout("failed to write src file (%zd)\n", ret); goto out; + } + ret = file_write_and_wait_range(dst_file, dst_off, (dst_off + len)); + if (ret < 0) { + dout("failed to write dst file (%zd)\n", ret); + goto out; + } /* * We need FILE_WR caps for dst_ci and FILE_RD for src_ci as other From 71f2cc64d027d712f29bf8d09d3e123302d5f245 Mon Sep 17 00:00:00 2001 From: Luis Henriques Date: Mon, 5 Nov 2018 19:00:52 +0000 Subject: [PATCH 257/356] ceph: quota: fix null pointer dereference in quota check MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch fixes a possible null pointer dereference in check_quota_exceeded, detected by the static checker smatch, with the following warning:    fs/ceph/quota.c:240 check_quota_exceeded()     error: we previously assumed 'realm' could be null (see line 188) Fixes: b7a2921765cf ("ceph: quota: support for ceph.quota.max_files") Reported-by: Dan Carpenter Signed-off-by: Luis Henriques Reviewed-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- fs/ceph/quota.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c index 32d4f13784ba..03f4d24db8fe 100644 --- a/fs/ceph/quota.c +++ b/fs/ceph/quota.c @@ -237,7 +237,8 @@ static bool check_quota_exceeded(struct inode *inode, enum quota_check_op op, ceph_put_snap_realm(mdsc, realm); realm = next; } - ceph_put_snap_realm(mdsc, realm); + if (realm) + ceph_put_snap_realm(mdsc, realm); up_read(&mdsc->snap_rwsem); return exceeded; From 23c625ce3065e40c933a4239efb9b11f1194a343 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Thu, 8 Nov 2018 14:55:21 +0100 Subject: [PATCH 258/356] libceph: assume argonaut on the server side No one is running pre-argonaut. In addition one of the argonaut features (NOSRCADDR) has been required since day one (and a half, 2.6.34 vs 2.6.35) of the kernel client. Allow for the possibility of reusing these feature bits later. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- fs/ceph/mds_client.c | 12 +++--------- include/linux/ceph/ceph_features.h | 8 +------- 2 files changed, 4 insertions(+), 16 deletions(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 67a9aeb2f4ec..bd13a3267ae0 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -80,12 +80,8 @@ static int parse_reply_info_in(void **p, void *end, info->symlink = *p; *p += info->symlink_len; - if (features & CEPH_FEATURE_DIRLAYOUTHASH) - ceph_decode_copy_safe(p, end, &info->dir_layout, - sizeof(info->dir_layout), bad); - else - memset(&info->dir_layout, 0, sizeof(info->dir_layout)); - + ceph_decode_copy_safe(p, end, &info->dir_layout, + sizeof(info->dir_layout), bad); ceph_decode_32_safe(p, end, info->xattr_len, bad); ceph_decode_need(p, end, info->xattr_len, bad); info->xattr_data = *p; @@ -3182,10 +3178,8 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc, recon_state.pagelist = pagelist; if (session->s_con.peer_features & CEPH_FEATURE_MDSENC) recon_state.msg_version = 3; - else if (session->s_con.peer_features & CEPH_FEATURE_FLOCK) - recon_state.msg_version = 2; else - recon_state.msg_version = 1; + recon_state.msg_version = 2; err = iterate_session_caps(session, encode_caps_cb, &recon_state); if (err < 0) goto fail; diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index 6b92b3395fa9..65a38c4a02a1 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -213,12 +213,6 @@ DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facin CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING | \ CEPH_FEATURE_CEPHX_V2) -#define CEPH_FEATURES_REQUIRED_DEFAULT \ - (CEPH_FEATURE_NOSRCADDR | \ - CEPH_FEATURE_SUBSCRIBE2 | \ - CEPH_FEATURE_RECONNECT_SEQ | \ - CEPH_FEATURE_PGID64 | \ - CEPH_FEATURE_PGPOOL3 | \ - CEPH_FEATURE_OSDENC) +#define CEPH_FEATURES_REQUIRED_DEFAULT 0 #endif From 26a4676faa1ad5d99317e0cd701e5d6f3e716b77 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 7 Nov 2018 18:10:38 +0100 Subject: [PATCH 259/356] arm64: mm: define NET_IP_ALIGN to 0 On arm64, there is no need to add 2 bytes of padding to the start of each network buffer just to make the IP header appear 32-bit aligned. Since this might actually adversely affect DMA performance some platforms, let's override NET_IP_ALIGN to 0 to get rid of this padding. Acked-by: Ilias Apalodimas Tested-by: Ilias Apalodimas Acked-by: Mark Rutland Acked-by: Will Deacon Signed-off-by: Ard Biesheuvel Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/processor.h | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 3e2091708b8e..6b0d4dff5012 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -24,6 +24,14 @@ #define KERNEL_DS UL(-1) #define USER_DS (TASK_SIZE_64 - 1) +/* + * On arm64 systems, unaligned accesses by the CPU are cheap, and so there is + * no point in shifting all network buffers by 2 bytes just to make some IP + * header fields appear aligned in memory, potentially sacrificing some DMA + * performance on some platforms. + */ +#define NET_IP_ALIGN 0 + #ifndef __ASSEMBLY__ #ifdef __KERNEL__ From 24cc61d8cb5a9232fadf21a830061853c1268fdd Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 7 Nov 2018 15:16:06 +0100 Subject: [PATCH 260/356] arm64: memblock: don't permit memblock resizing until linear mapping is up Bhupesh reports that having numerous memblock reservations at early boot may result in the following crash: Unable to handle kernel paging request at virtual address ffff80003ffe0000 ... Call trace: __memcpy+0x110/0x180 memblock_add_range+0x134/0x2e8 memblock_reserve+0x70/0xb8 memblock_alloc_base_nid+0x6c/0x88 __memblock_alloc_base+0x3c/0x4c memblock_alloc_base+0x28/0x4c memblock_alloc+0x2c/0x38 early_pgtable_alloc+0x20/0xb0 paging_init+0x28/0x7f8 This is caused by the fact that we permit memblock resizing before the linear mapping is up, and so the memblock_reserved() array is moved into memory that is not mapped yet. So let's ensure that this crash can no longer occur, by deferring to call to memblock_allow_resize() to after the linear mapping has been created. Reported-by: Bhupesh Sharma Acked-by: Will Deacon Tested-by: Marc Zyngier Signed-off-by: Ard Biesheuvel Signed-off-by: Catalin Marinas --- arch/arm64/mm/init.c | 2 -- arch/arm64/mm/mmu.c | 2 ++ 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 9d9582cac6c4..9b432d9fcada 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -483,8 +483,6 @@ void __init arm64_memblock_init(void) high_memory = __va(memblock_end_of_DRAM() - 1) + 1; dma_contiguous_reserve(arm64_dma_phys_limit); - - memblock_allow_resize(); } void __init bootmem_init(void) diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 394b8d554def..d1d6601b385d 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -659,6 +659,8 @@ void __init paging_init(void) memblock_free(__pa_symbol(init_pg_dir), __pa_symbol(init_pg_end) - __pa_symbol(init_pg_dir)); + + memblock_allow_resize(); } /* From e2576c8bdfd462c34b8a46c0084e7c30b0851bf4 Mon Sep 17 00:00:00 2001 From: Christian Hewitt Date: Tue, 6 Nov 2018 00:08:20 +0100 Subject: [PATCH 261/356] clk: meson-gxbb: set fclk_div3 as CLK_IS_CRITICAL On the Khadas VIM2 (GXM) and LePotato (GXL) board there are problems with reboot; e.g. a ~60 second delay between issuing reboot and the board power cycling (and in some OS configurations reboot will fail and require manual power cycling). Similar to 'commit c987ac6f1f088663b6dad39281071aeb31d450a8 ("clk: meson-gxbb: set fclk_div2 as CLK_IS_CRITICAL")' the SCPI Cortex-M4 Co-Processor seems to depend on FCLK_DIV3 being operational. Until commit 05f814402d6174369b3b29832cbb5eb5ed287059 ("clk: meson: add fdiv clock gates"), this clock was modeled and left on by the bootloader. We don't have precise documentation about the SCPI Co-Processor and its clock requirement so we are learning things the hard way. Marking this clock as critical solves the problem but it should not be viewed as final solution. Ideally, the SCPI driver should claim these clocks. We also depends on some clock hand-off mechanism making its way to CCF, to make sure the clock stays on between its registration and the SCPI driver probe. Fixes: 05f814402d61 ("clk: meson: add fdiv clock gates") Signed-off-by: Christian Hewitt Signed-off-by: Jerome Brunet Signed-off-by: Stephen Boyd --- drivers/clk/meson/gxbb.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c index 9309cfaaa464..4ada9668fd49 100644 --- a/drivers/clk/meson/gxbb.c +++ b/drivers/clk/meson/gxbb.c @@ -506,6 +506,18 @@ static struct clk_regmap gxbb_fclk_div3 = { .ops = &clk_regmap_gate_ops, .parent_names = (const char *[]){ "fclk_div3_div" }, .num_parents = 1, + /* + * FIXME: + * This clock, as fdiv2, is used by the SCPI FW and is required + * by the platform to operate correctly. + * Until the following condition are met, we need this clock to + * be marked as critical: + * a) The SCPI generic driver claims and enable all the clocks + * it needs + * b) CCF has a clock hand-off mechanism to make the sure the + * clock stays on until the proper driver comes along + */ + .flags = CLK_IS_CRITICAL, }, }; From d6ee1e7e9004d3d246cdfa14196989e0a9466c16 Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Thu, 8 Nov 2018 10:31:23 +0100 Subject: [PATCH 262/356] clk: meson: axg: mark fdiv2 and fdiv3 as critical Similar to gxbb and gxl platforms, axg SCPI Cortex-M co-processor uses the fdiv2 and fdiv3 to, among other things, provide the cpu clock. Until clock hand-off mechanism makes its way to CCF and the generic SCPI claims platform specific clocks, these clocks must be marked as critical to make sure they are never disabled when needed by the co-processor. Fixes: 05f814402d61 ("clk: meson: add fdiv clock gates") Signed-off-by: Jerome Brunet Acked-by: Neil Armstrong Signed-off-by: Stephen Boyd --- drivers/clk/meson/axg.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/clk/meson/axg.c b/drivers/clk/meson/axg.c index c981159b02c0..792735d7e46e 100644 --- a/drivers/clk/meson/axg.c +++ b/drivers/clk/meson/axg.c @@ -325,6 +325,7 @@ static struct clk_regmap axg_fclk_div2 = { .ops = &clk_regmap_gate_ops, .parent_names = (const char *[]){ "fclk_div2_div" }, .num_parents = 1, + .flags = CLK_IS_CRITICAL, }, }; @@ -349,6 +350,18 @@ static struct clk_regmap axg_fclk_div3 = { .ops = &clk_regmap_gate_ops, .parent_names = (const char *[]){ "fclk_div3_div" }, .num_parents = 1, + /* + * FIXME: + * This clock, as fdiv2, is used by the SCPI FW and is required + * by the platform to operate correctly. + * Until the following condition are met, we need this clock to + * be marked as critical: + * a) The SCPI generic driver claims and enable all the clocks + * it needs + * b) CCF has a clock hand-off mechanism to make the sure the + * clock stays on until the proper driver comes along + */ + .flags = CLK_IS_CRITICAL, }, }; From 6778be4e520959659b27a441c06a84c9cb009085 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 7 Nov 2018 16:30:32 +0000 Subject: [PATCH 263/356] of/device: Really only set bus DMA mask when appropriate of_dma_configure() was *supposed* to be following the same logic as acpi_dma_configure() and only setting bus_dma_mask if some range was specified by the firmware. However, it seems that subtlety got lost in the process of fitting it into the differently-shaped control flow, and as a result the force_dma==true case ends up always setting the bus mask to the 32-bit default, which is not what anyone wants. Make sure we only touch it if the DT actually said so. Fixes: 6c2fb2ea7636 ("of/device: Set bus DMA mask as appropriate") Reported-by: Aaro Koskinen Reported-by: Jean-Philippe Brucker Tested-by: Aaro Koskinen Tested-by: John Stultz Tested-by: Geert Uytterhoeven Tested-by: Robert Richter Signed-off-by: Robin Murphy Signed-off-by: Rob Herring --- drivers/of/device.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/of/device.c b/drivers/of/device.c index 84e810421418..258742830e36 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -149,9 +149,11 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma) * set by the driver. */ mask = DMA_BIT_MASK(ilog2(dma_addr + size - 1) + 1); - dev->bus_dma_mask = mask; dev->coherent_dma_mask &= mask; *dev->dma_mask &= mask; + /* ...but only set bus mask if we found valid dma-ranges earlier */ + if (!ret) + dev->bus_dma_mask = mask; coherent = of_dma_is_coherent(np); dev_dbg(dev, "device is%sdma coherent\n", From 89c38422e072bb453e3045b8f1b962a344c3edea Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 8 Nov 2018 18:17:03 +0800 Subject: [PATCH 264/356] of, numa: Validate some distance map rules Currently the NUMA distance map parsing does not validate the distance table for the distance-matrix rules 1-2 in [1]. However the arch NUMA code may enforce some of these rules, but not all. Such is the case for the arm64 port, which does not enforce the rule that the distance between separates nodes cannot equal LOCAL_DISTANCE. The patch adds the following rules validation: - distance of node to self equals LOCAL_DISTANCE - distance of separate nodes > LOCAL_DISTANCE This change avoids a yet-unresolved crash reported in [2]. A note on dealing with symmetrical distances between nodes: Validating symmetrical distances between nodes is difficult. If it were mandated in the bindings that every distance must be recorded in the table, then it would be easy. However, it isn't. In addition to this, it is also possible to record [b, a] distance only (and not [a, b]). So, when processing the table for [b, a], we cannot assert that current distance of [a, b] != [b, a] as invalid, as [a, b] distance may not be present in the table and current distance would be default at REMOTE_DISTANCE. As such, we maintain the policy that we overwrite distance [a, b] = [b, a] for b > a. This policy is different to kernel ACPI SLIT validation, which allows non-symmetrical distances (ACPI spec SLIT rules allow it). However, the distance debug message is dropped as it may be misleading (for a distance which is later overwritten). Some final notes on semantics: - It is implied that it is the responsibility of the arch NUMA code to reset the NUMA distance map for an error in distance map parsing. - It is the responsibility of the FW NUMA topology parsing (whether OF or ACPI) to enforce NUMA distance rules, and not arch NUMA code. [1] Documents/devicetree/bindings/numa.txt [2] https://www.spinics.net/lists/arm-kernel/msg683304.html Cc: stable@vger.kernel.org # 4.7 Signed-off-by: John Garry Acked-by: Will Deacon Signed-off-by: Rob Herring --- drivers/of/of_numa.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/of/of_numa.c b/drivers/of/of_numa.c index 35c64a4295e0..fe6b13608e51 100644 --- a/drivers/of/of_numa.c +++ b/drivers/of/of_numa.c @@ -104,9 +104,14 @@ static int __init of_numa_parse_distance_map_v1(struct device_node *map) distance = of_read_number(matrix, 1); matrix++; + if ((nodea == nodeb && distance != LOCAL_DISTANCE) || + (nodea != nodeb && distance <= LOCAL_DISTANCE)) { + pr_err("Invalid distance[node%d -> node%d] = %d\n", + nodea, nodeb, distance); + return -EINVAL; + } + numa_set_distance(nodea, nodeb, distance); - pr_debug("distance[node%d -> node%d] = %d\n", - nodea, nodeb, distance); /* Set default distance of node B->A same as A->B */ if (nodeb > nodea) From e12c225258f2584906765234ca6db4ad4c618192 Mon Sep 17 00:00:00 2001 From: Huazhong Tan Date: Thu, 8 Nov 2018 10:13:19 +0800 Subject: [PATCH 265/356] net: hns3: bugfix for not checking return value hns3_reset_notify_init_enet() only return error early if the return value of hns3_restore_vlan() is not 0. This patch adds checking for the return value of hns3_restore_vlan. Fixes: 7fa6be4fd2f6 ("net: hns3: fix incorrect return value/type of some functions") Signed-off-by: Huazhong Tan Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 3f96aa30068e..20fcf0d1c2ce 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -3760,7 +3760,8 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle) /* Hardware table is only clear when pf resets */ if (!(handle->flags & HNAE3_SUPPORT_VF)) { ret = hns3_restore_vlan(netdev); - return ret; + if (ret) + return ret; } ret = hns3_restore_fd_rules(netdev); From 0d5b9311baf27bb545f187f12ecfd558220c607d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 8 Nov 2018 17:34:27 -0800 Subject: [PATCH 266/356] inet: frags: better deal with smp races MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Multiple cpus might attempt to insert a new fragment in rhashtable, if for example RPS is buggy, as reported by 배석진 in https://patchwork.ozlabs.org/patch/994601/ We use rhashtable_lookup_get_insert_key() instead of rhashtable_insert_fast() to let cpus losing the race free their own inet_frag_queue and use the one that was inserted by another cpu. Fixes: 648700f76b03 ("inet: frags: use rhashtables for reassembly units") Signed-off-by: Eric Dumazet Reported-by: 배석진 Signed-off-by: David S. Miller --- net/ipv4/inet_fragment.c | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-) diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index bcb11f3a27c0..760a9e52e02b 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -178,21 +178,22 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, } static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf, - void *arg) + void *arg, + struct inet_frag_queue **prev) { struct inet_frags *f = nf->f; struct inet_frag_queue *q; - int err; q = inet_frag_alloc(nf, f, arg); - if (!q) + if (!q) { + *prev = ERR_PTR(-ENOMEM); return NULL; - + } mod_timer(&q->timer, jiffies + nf->timeout); - err = rhashtable_insert_fast(&nf->rhashtable, &q->node, - f->rhash_params); - if (err < 0) { + *prev = rhashtable_lookup_get_insert_key(&nf->rhashtable, &q->key, + &q->node, f->rhash_params); + if (*prev) { q->flags |= INET_FRAG_COMPLETE; inet_frag_kill(q); inet_frag_destroy(q); @@ -204,22 +205,22 @@ static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf, /* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key) { - struct inet_frag_queue *fq; + struct inet_frag_queue *fq = NULL, *prev; if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) return NULL; rcu_read_lock(); - fq = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params); - if (fq) { + prev = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params); + if (!prev) + fq = inet_frag_create(nf, key, &prev); + if (prev && !IS_ERR(prev)) { + fq = prev; if (!refcount_inc_not_zero(&fq->refcnt)) fq = NULL; - rcu_read_unlock(); - return fq; } rcu_read_unlock(); - - return inet_frag_create(nf, key); + return fq; } EXPORT_SYMBOL(inet_frag_find); From 39477551df940ddb1339203817de04f5caaacf7a Mon Sep 17 00:00:00 2001 From: Denis Bolotin Date: Thu, 8 Nov 2018 16:46:08 +0200 Subject: [PATCH 267/356] qed: Fix memory/entry leak in qed_init_sp_request() Free the allocated SPQ entry or return the acquired SPQ entry to the free list in error flows. Signed-off-by: Denis Bolotin Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- .../net/ethernet/qlogic/qed/qed_sp_commands.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c index 77b6248ad3b9..e86a1ea23613 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c @@ -80,7 +80,7 @@ int qed_sp_init_request(struct qed_hwfn *p_hwfn, case QED_SPQ_MODE_BLOCK: if (!p_data->p_comp_data) - return -EINVAL; + goto err; p_ent->comp_cb.cookie = p_data->p_comp_data->cookie; break; @@ -95,7 +95,7 @@ int qed_sp_init_request(struct qed_hwfn *p_hwfn, default: DP_NOTICE(p_hwfn, "Unknown SPQE completion mode %d\n", p_ent->comp_mode); - return -EINVAL; + goto err; } DP_VERBOSE(p_hwfn, QED_MSG_SPQ, @@ -109,6 +109,18 @@ int qed_sp_init_request(struct qed_hwfn *p_hwfn, memset(&p_ent->ramrod, 0, sizeof(p_ent->ramrod)); return 0; + +err: + /* qed_spq_get_entry() can either get an entry from the free_pool, + * or, if no entries are left, allocate a new entry and add it to + * the unlimited_pending list. + */ + if (p_ent->queue == &p_hwfn->p_spq->unlimited_pending) + kfree(p_ent); + else + qed_spq_return_entry(p_hwfn, p_ent); + + return -EINVAL; } static enum tunnel_clss qed_tunn_clss_to_fw_clss(u8 type) From 2632f22ebd08da249c2017962a199a0cfb2324bf Mon Sep 17 00:00:00 2001 From: Denis Bolotin Date: Thu, 8 Nov 2018 16:46:09 +0200 Subject: [PATCH 268/356] qed: Fix blocking/unlimited SPQ entries leak When there are no SPQ entries left in the free_pool, new entries are allocated and are added to the unlimited list. When an entry in the pool is available, the content is copied from the original entry, and the new entry is sent to the device. qed_spq_post() is not aware of that, so the additional entry is stored in the original entry as p_post_ent, which can later be returned to the pool. Signed-off-by: Denis Bolotin Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_sp.h | 3 ++ drivers/net/ethernet/qlogic/qed/qed_spq.c | 57 ++++++++++++----------- 2 files changed, 33 insertions(+), 27 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h index e95431f6acd4..04259df8a5c2 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h @@ -167,6 +167,9 @@ struct qed_spq_entry { enum spq_mode comp_mode; struct qed_spq_comp_cb comp_cb; struct qed_spq_comp_done comp_done; /* SPQ_MODE_EBLOCK */ + + /* Posted entry for unlimited list entry in EBLOCK mode */ + struct qed_spq_entry *post_ent; }; struct qed_eq { diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c index c4a6274dd625..c1a81ec0524b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_spq.c +++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c @@ -685,6 +685,8 @@ static int qed_spq_add_entry(struct qed_hwfn *p_hwfn, /* EBLOCK responsible to free the allocated p_ent */ if (p_ent->comp_mode != QED_SPQ_MODE_EBLOCK) kfree(p_ent); + else + p_ent->post_ent = p_en2; p_ent = p_en2; } @@ -767,6 +769,25 @@ static int qed_spq_pend_post(struct qed_hwfn *p_hwfn) SPQ_HIGH_PRI_RESERVE_DEFAULT); } +/* Avoid overriding of SPQ entries when getting out-of-order completions, by + * marking the completions in a bitmap and increasing the chain consumer only + * for the first successive completed entries. + */ +static void qed_spq_comp_bmap_update(struct qed_hwfn *p_hwfn, __le16 echo) +{ + u16 pos = le16_to_cpu(echo) % SPQ_RING_SIZE; + struct qed_spq *p_spq = p_hwfn->p_spq; + + __set_bit(pos, p_spq->p_comp_bitmap); + while (test_bit(p_spq->comp_bitmap_idx, + p_spq->p_comp_bitmap)) { + __clear_bit(p_spq->comp_bitmap_idx, + p_spq->p_comp_bitmap); + p_spq->comp_bitmap_idx++; + qed_chain_return_produced(&p_spq->chain); + } +} + int qed_spq_post(struct qed_hwfn *p_hwfn, struct qed_spq_entry *p_ent, u8 *fw_return_code) { @@ -824,11 +845,12 @@ int qed_spq_post(struct qed_hwfn *p_hwfn, p_ent->queue == &p_spq->unlimited_pending); if (p_ent->queue == &p_spq->unlimited_pending) { - /* This is an allocated p_ent which does not need to - * return to pool. - */ + struct qed_spq_entry *p_post_ent = p_ent->post_ent; + kfree(p_ent); - return rc; + + /* Return the entry which was actually posted */ + p_ent = p_post_ent; } if (rc) @@ -842,7 +864,7 @@ int qed_spq_post(struct qed_hwfn *p_hwfn, spq_post_fail2: spin_lock_bh(&p_spq->lock); list_del(&p_ent->list); - qed_chain_return_produced(&p_spq->chain); + qed_spq_comp_bmap_update(p_hwfn, p_ent->elem.hdr.echo); spq_post_fail: /* return to the free pool */ @@ -874,25 +896,8 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn, spin_lock_bh(&p_spq->lock); list_for_each_entry_safe(p_ent, tmp, &p_spq->completion_pending, list) { if (p_ent->elem.hdr.echo == echo) { - u16 pos = le16_to_cpu(echo) % SPQ_RING_SIZE; - list_del(&p_ent->list); - - /* Avoid overriding of SPQ entries when getting - * out-of-order completions, by marking the completions - * in a bitmap and increasing the chain consumer only - * for the first successive completed entries. - */ - __set_bit(pos, p_spq->p_comp_bitmap); - - while (test_bit(p_spq->comp_bitmap_idx, - p_spq->p_comp_bitmap)) { - __clear_bit(p_spq->comp_bitmap_idx, - p_spq->p_comp_bitmap); - p_spq->comp_bitmap_idx++; - qed_chain_return_produced(&p_spq->chain); - } - + qed_spq_comp_bmap_update(p_hwfn, echo); p_spq->comp_count++; found = p_ent; break; @@ -931,11 +936,9 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn, QED_MSG_SPQ, "Got a completion without a callback function\n"); - if ((found->comp_mode != QED_SPQ_MODE_EBLOCK) || - (found->queue == &p_spq->unlimited_pending)) + if (found->comp_mode != QED_SPQ_MODE_EBLOCK) /* EBLOCK is responsible for returning its own entry into the - * free list, unless it originally added the entry into the - * unlimited pending list. + * free list. */ qed_spq_return_entry(p_hwfn, found); From fb5e7438e7a3c8966e04ccb0760170e9e06f3699 Mon Sep 17 00:00:00 2001 From: Denis Bolotin Date: Thu, 8 Nov 2018 16:46:10 +0200 Subject: [PATCH 269/356] qed: Fix SPQ entries not returned to pool in error flows qed_sp_destroy_request() API was added for SPQ users that need to free/return the entry they acquired in their error flows. Signed-off-by: Denis Bolotin Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_fcoe.c | 11 +++++++--- drivers/net/ethernet/qlogic/qed/qed_iscsi.c | 1 + drivers/net/ethernet/qlogic/qed/qed_l2.c | 12 ++++++---- drivers/net/ethernet/qlogic/qed/qed_rdma.c | 1 + drivers/net/ethernet/qlogic/qed/qed_roce.c | 1 + drivers/net/ethernet/qlogic/qed/qed_sp.h | 11 ++++++++++ .../net/ethernet/qlogic/qed/qed_sp_commands.c | 22 ++++++++++++------- drivers/net/ethernet/qlogic/qed/qed_sriov.c | 1 + 8 files changed, 45 insertions(+), 15 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c index cc1b373c0ace..46dc93d3b9b5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c +++ b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c @@ -147,7 +147,8 @@ qed_sp_fcoe_func_start(struct qed_hwfn *p_hwfn, "Cannot satisfy CQ amount. CQs requested %d, CQs available %d. Aborting function start\n", fcoe_pf_params->num_cqs, p_hwfn->hw_info.feat_num[QED_FCOE_CQ]); - return -EINVAL; + rc = -EINVAL; + goto err; } p_data->mtu = cpu_to_le16(fcoe_pf_params->mtu); @@ -156,14 +157,14 @@ qed_sp_fcoe_func_start(struct qed_hwfn *p_hwfn, rc = qed_cxt_acquire_cid(p_hwfn, PROTOCOLID_FCOE, &dummy_cid); if (rc) - return rc; + goto err; cxt_info.iid = dummy_cid; rc = qed_cxt_get_cid_info(p_hwfn, &cxt_info); if (rc) { DP_NOTICE(p_hwfn, "Cannot find context info for dummy cid=%d\n", dummy_cid); - return rc; + goto err; } p_cxt = cxt_info.p_cxt; SET_FIELD(p_cxt->tstorm_ag_context.flags3, @@ -240,6 +241,10 @@ qed_sp_fcoe_func_start(struct qed_hwfn *p_hwfn, rc = qed_spq_post(p_hwfn, p_ent, NULL); return rc; + +err: + qed_sp_destroy_request(p_hwfn, p_ent); + return rc; } static int diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c index 1135387bd99d..4f8a685d1a55 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c @@ -200,6 +200,7 @@ qed_sp_iscsi_func_start(struct qed_hwfn *p_hwfn, "Cannot satisfy CQ amount. Queues requested %d, CQs available %d. Aborting function start\n", p_params->num_queues, p_hwfn->hw_info.feat_num[QED_ISCSI_CQ]); + qed_sp_destroy_request(p_hwfn, p_ent); return -EINVAL; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 82a1bd1f8a8c..67c02ea93906 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -740,8 +740,7 @@ int qed_sp_vport_update(struct qed_hwfn *p_hwfn, rc = qed_sp_vport_update_rss(p_hwfn, p_ramrod, p_rss_params); if (rc) { - /* Return spq entry which is taken in qed_sp_init_request()*/ - qed_spq_return_entry(p_hwfn, p_ent); + qed_sp_destroy_request(p_hwfn, p_ent); return rc; } @@ -1355,6 +1354,7 @@ qed_filter_ucast_common(struct qed_hwfn *p_hwfn, DP_NOTICE(p_hwfn, "%d is not supported yet\n", p_filter_cmd->opcode); + qed_sp_destroy_request(p_hwfn, *pp_ent); return -EINVAL; } @@ -2056,13 +2056,13 @@ qed_configure_rfs_ntuple_filter(struct qed_hwfn *p_hwfn, } else { rc = qed_fw_vport(p_hwfn, p_params->vport_id, &abs_vport_id); if (rc) - return rc; + goto err; if (p_params->qid != QED_RFS_NTUPLE_QID_RSS) { rc = qed_fw_l2_queue(p_hwfn, p_params->qid, &abs_rx_q_id); if (rc) - return rc; + goto err; p_ramrod->rx_qid_valid = 1; p_ramrod->rx_qid = cpu_to_le16(abs_rx_q_id); @@ -2083,6 +2083,10 @@ qed_configure_rfs_ntuple_filter(struct qed_hwfn *p_hwfn, (u64)p_params->addr, p_params->length); return qed_spq_post(p_hwfn, p_ent, NULL); + +err: + qed_sp_destroy_request(p_hwfn, p_ent); + return rc; } int qed_get_rxq_coalesce(struct qed_hwfn *p_hwfn, diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c index c71391b9c757..62113438c880 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c +++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c @@ -1514,6 +1514,7 @@ qed_rdma_register_tid(void *rdma_cxt, default: rc = -EINVAL; DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "rc = %d\n", rc); + qed_sp_destroy_request(p_hwfn, p_ent); return rc; } SET_FIELD(p_ramrod->flags1, diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c index f9167d1354bb..e49fada85410 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_roce.c +++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c @@ -745,6 +745,7 @@ static int qed_roce_sp_destroy_qp_responder(struct qed_hwfn *p_hwfn, DP_NOTICE(p_hwfn, "qed destroy responder failed: cannot allocate memory (ramrod). rc = %d\n", rc); + qed_sp_destroy_request(p_hwfn, p_ent); return rc; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h index 04259df8a5c2..3157c0d99441 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h @@ -399,6 +399,17 @@ struct qed_sp_init_data { struct qed_spq_comp_cb *p_comp_data; }; +/** + * @brief Returns a SPQ entry to the pool / frees the entry if allocated. + * Should be called on in error flows after initializing the SPQ entry + * and before posting it. + * + * @param p_hwfn + * @param p_ent + */ +void qed_sp_destroy_request(struct qed_hwfn *p_hwfn, + struct qed_spq_entry *p_ent); + int qed_sp_init_request(struct qed_hwfn *p_hwfn, struct qed_spq_entry **pp_ent, u8 cmd, diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c index e86a1ea23613..888274fa208b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c @@ -47,6 +47,19 @@ #include "qed_sp.h" #include "qed_sriov.h" +void qed_sp_destroy_request(struct qed_hwfn *p_hwfn, + struct qed_spq_entry *p_ent) +{ + /* qed_spq_get_entry() can either get an entry from the free_pool, + * or, if no entries are left, allocate a new entry and add it to + * the unlimited_pending list. + */ + if (p_ent->queue == &p_hwfn->p_spq->unlimited_pending) + kfree(p_ent); + else + qed_spq_return_entry(p_hwfn, p_ent); +} + int qed_sp_init_request(struct qed_hwfn *p_hwfn, struct qed_spq_entry **pp_ent, u8 cmd, u8 protocol, struct qed_sp_init_data *p_data) @@ -111,14 +124,7 @@ int qed_sp_init_request(struct qed_hwfn *p_hwfn, return 0; err: - /* qed_spq_get_entry() can either get an entry from the free_pool, - * or, if no entries are left, allocate a new entry and add it to - * the unlimited_pending list. - */ - if (p_ent->queue == &p_hwfn->p_spq->unlimited_pending) - kfree(p_ent); - else - qed_spq_return_entry(p_hwfn, p_ent); + qed_sp_destroy_request(p_hwfn, p_ent); return -EINVAL; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index 9b08a9d9e151..ca6290fa0f30 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -101,6 +101,7 @@ static int qed_sp_vf_start(struct qed_hwfn *p_hwfn, struct qed_vf_info *p_vf) default: DP_NOTICE(p_hwfn, "Unknown VF personality %d\n", p_hwfn->hw_info.personality); + qed_sp_destroy_request(p_hwfn, p_ent); return -EINVAL; } From fa5c448d98f0df660bfcad3dd5facc027ef84cd3 Mon Sep 17 00:00:00 2001 From: Sagiv Ozeri Date: Thu, 8 Nov 2018 16:46:11 +0200 Subject: [PATCH 270/356] qed: Fix potential memory corruption A stuck ramrod should be deleted from the completion_pending list, otherwise it will be added again in the future and corrupt the list. Return error value to inform that ramrod is stuck and should be deleted. Signed-off-by: Sagiv Ozeri Signed-off-by: Denis Bolotin Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_spq.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c index c1a81ec0524b..0a9c5bb0fa48 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_spq.c +++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c @@ -142,6 +142,7 @@ static int qed_spq_block(struct qed_hwfn *p_hwfn, DP_INFO(p_hwfn, "Ramrod is stuck, requesting MCP drain\n"); rc = qed_mcp_drain(p_hwfn, p_ptt); + qed_ptt_release(p_hwfn, p_ptt); if (rc) { DP_NOTICE(p_hwfn, "MCP drain failed\n"); goto err; @@ -150,18 +151,15 @@ static int qed_spq_block(struct qed_hwfn *p_hwfn, /* Retry after drain */ rc = __qed_spq_block(p_hwfn, p_ent, p_fw_ret, true); if (!rc) - goto out; + return 0; comp_done = (struct qed_spq_comp_done *)p_ent->comp_cb.cookie; - if (comp_done->done == 1) + if (comp_done->done == 1) { if (p_fw_ret) *p_fw_ret = comp_done->fw_return_code; -out: - qed_ptt_release(p_hwfn, p_ptt); - return 0; - + return 0; + } err: - qed_ptt_release(p_hwfn, p_ptt); DP_NOTICE(p_hwfn, "Ramrod is stuck [CID %08x cmd %02x protocol %02x echo %04x]\n", le32_to_cpu(p_ent->elem.hdr.cid), From 8137b6ef0ce469154e5cf19f8e7fe04d9a72ac5e Mon Sep 17 00:00:00 2001 From: Thor Thayer Date: Thu, 8 Nov 2018 11:42:14 -0600 Subject: [PATCH 271/356] net: stmmac: Fix RX packet size > 8191 Ping problems with packets > 8191 as shown: PING 192.168.1.99 (192.168.1.99) 8150(8178) bytes of data. 8158 bytes from 192.168.1.99: icmp_seq=1 ttl=64 time=0.669 ms wrong data byte 8144 should be 0xd0 but was 0x0 16 10 11 12 13 14 15 16 17 18 19 1a 1b 1c 1d 1e 1f 20 21 22 23 24 25 26 27 28 29 2a 2b 2c 2d 2e 2f %< ---------------snip-------------------------------------- 8112 b0 b1 b2 b3 b4 b5 b6 b7 b8 b9 ba bb bc bd be bf c0 c1 c2 c3 c4 c5 c6 c7 c8 c9 ca cb cc cd ce cf 8144 0 0 0 0 d0 d1 ^^^^^^^ Notice the 4 bytes of 0 before the expected byte of d0. Databook notes that the RX buffer must be a multiple of 4/8/16 bytes [1]. Update the DMA Buffer size define to 8188 instead of 8192. Remove the -1 from the RX buffer size allocations and use the new DMA Buffer size directly. [1] Synopsys DesignWare Cores Ethernet MAC Universal v3.70a [section 8.4.2 - Table 8-24] Tested on SoCFPGA Stratix10 with ping sweep from 100 to 8300 byte packets. Fixes: 286a83721720 ("stmmac: add CHAINED descriptor mode support (V4)") Suggested-by: Jose Abreu Signed-off-by: Thor Thayer Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 3 ++- drivers/net/ethernet/stmicro/stmmac/descs_com.h | 2 +- drivers/net/ethernet/stmicro/stmmac/enh_desc.c | 2 +- drivers/net/ethernet/stmicro/stmmac/ring_mode.c | 2 +- 4 files changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index b1b305f8f414..272b9ca66314 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -365,7 +365,8 @@ struct dma_features { /* GMAC TX FIFO is 8K, Rx FIFO is 16K */ #define BUF_SIZE_16KiB 16384 -#define BUF_SIZE_8KiB 8192 +/* RX Buffer size must be < 8191 and multiple of 4/8/16 bytes */ +#define BUF_SIZE_8KiB 8188 #define BUF_SIZE_4KiB 4096 #define BUF_SIZE_2KiB 2048 diff --git a/drivers/net/ethernet/stmicro/stmmac/descs_com.h b/drivers/net/ethernet/stmicro/stmmac/descs_com.h index ca9d7e48034c..40d6356a7e73 100644 --- a/drivers/net/ethernet/stmicro/stmmac/descs_com.h +++ b/drivers/net/ethernet/stmicro/stmmac/descs_com.h @@ -31,7 +31,7 @@ /* Enhanced descriptors */ static inline void ehn_desc_rx_set_on_ring(struct dma_desc *p, int end) { - p->des1 |= cpu_to_le32(((BUF_SIZE_8KiB - 1) + p->des1 |= cpu_to_le32((BUF_SIZE_8KiB << ERDES1_BUFFER2_SIZE_SHIFT) & ERDES1_BUFFER2_SIZE_MASK); diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c index 77914c89d749..5ef91a790f9d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c +++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c @@ -262,7 +262,7 @@ static void enh_desc_init_rx_desc(struct dma_desc *p, int disable_rx_ic, int mode, int end) { p->des0 |= cpu_to_le32(RDES0_OWN); - p->des1 |= cpu_to_le32((BUF_SIZE_8KiB - 1) & ERDES1_BUFFER1_SIZE_MASK); + p->des1 |= cpu_to_le32(BUF_SIZE_8KiB & ERDES1_BUFFER1_SIZE_MASK); if (mode == STMMAC_CHAIN_MODE) ehn_desc_rx_set_on_chain(p); diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c index abc3f85270cd..d8c5bc412219 100644 --- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c +++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c @@ -140,7 +140,7 @@ static void clean_desc3(void *priv_ptr, struct dma_desc *p) static int set_16kib_bfsize(int mtu) { int ret = 0; - if (unlikely(mtu >= BUF_SIZE_8KiB)) + if (unlikely(mtu > BUF_SIZE_8KiB)) ret = BUF_SIZE_16KiB; return ret; } From 85b18b0237ce9986a81a1b9534b5e2ee116f5504 Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Thu, 8 Nov 2018 20:38:26 +0100 Subject: [PATCH 272/356] net: smsc95xx: Fix MTU range The commit f77f0aee4da4 ("net: use core MTU range checking in USB NIC drivers") introduce a common MTU handling for usbnet. But it's missing the necessary changes for smsc95xx. So set the MTU range accordingly. This patch has been tested on a Raspberry Pi 3. Fixes: f77f0aee4da4 ("net: use core MTU range checking in USB NIC drivers") Signed-off-by: Stefan Wahren Signed-off-by: David S. Miller --- drivers/net/usb/smsc95xx.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 2d17f3b9bb16..f2d01cb6f958 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -1321,6 +1321,8 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf) dev->net->ethtool_ops = &smsc95xx_ethtool_ops; dev->net->flags |= IFF_MULTICAST; dev->net->hard_header_len += SMSC95XX_TX_OVERHEAD_CSUM; + dev->net->min_mtu = ETH_MIN_MTU; + dev->net->max_mtu = ETH_DATA_LEN; dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len; pdata->dev = dev; From 1457d8cf7664f34c4ba534c1073821a559a2f6f9 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Wed, 7 Nov 2018 18:01:00 +0100 Subject: [PATCH 273/356] x86/xen: fix pv boot Commit 9da3f2b7405440 ("x86/fault: BUG() when uaccess helpers fault on kernel addresses") introduced a regression for booting Xen PV guests. Xen PV guests are using __put_user() and __get_user() for accessing the p2m map (physical to machine frame number map) as accesses might fail in case of not populated areas of the map. With above commit using __put_user() and __get_user() for accessing kernel pages is no longer valid. So replace the Xen hack by adding appropriate p2m access functions using the default fixup handler. Fixes: 9da3f2b7405440 ("x86/fault: BUG() when uaccess helpers fault on kernel addresses") Signed-off-by: Juergen Gross Reviewed-by: Andrew Cooper Signed-off-by: Juergen Gross --- arch/x86/include/asm/xen/page.h | 35 +++++++++++++++++++++++++++++---- arch/x86/xen/p2m.c | 3 +-- 2 files changed, 32 insertions(+), 6 deletions(-) diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 123e669bf363..790ce08e41f2 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -9,7 +9,7 @@ #include #include -#include +#include #include #include @@ -93,12 +93,39 @@ clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, */ static inline int xen_safe_write_ulong(unsigned long *addr, unsigned long val) { - return __put_user(val, (unsigned long __user *)addr); + int ret = 0; + + asm volatile("1: mov %[val], %[ptr]\n" + "2:\n" + ".section .fixup, \"ax\"\n" + "3: sub $1, %[ret]\n" + " jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + : [ret] "+r" (ret), [ptr] "=m" (*addr) + : [val] "r" (val)); + + return ret; } -static inline int xen_safe_read_ulong(unsigned long *addr, unsigned long *val) +static inline int xen_safe_read_ulong(const unsigned long *addr, + unsigned long *val) { - return __get_user(*val, (unsigned long __user *)addr); + int ret = 0; + unsigned long rval = ~0ul; + + asm volatile("1: mov %[ptr], %[rval]\n" + "2:\n" + ".section .fixup, \"ax\"\n" + "3: sub $1, %[ret]\n" + " jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + : [ret] "+r" (ret), [rval] "+r" (rval) + : [ptr] "m" (*addr)); + *val = rval; + + return ret; } #ifdef CONFIG_XEN_PV diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index d6d74efd8912..4fe84436d5a7 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -656,8 +656,7 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) /* * The interface requires atomic updates on p2m elements. - * xen_safe_write_ulong() is using __put_user which does an atomic - * store via asm(). + * xen_safe_write_ulong() is using an atomic store via asm(). */ if (likely(!xen_safe_write_ulong(xen_p2m_addr + pfn, mfn))) return true; From 21d3bbdd4c342f16eac8d70893e45cdfa3381a1e Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Fri, 2 Nov 2018 16:12:21 -0700 Subject: [PATCH 274/356] nvmet: don't try to add ns to p2p map unless it actually uses it Even without CONFIG_P2PDMA this results in a error print: nvmet: no peer-to-peer memory is available that's supported by rxe0 and /dev/nullb0 Fixes: c6925093d0b2 ("nvmet: Optionally use PCI P2P memory") Signed-off-by: Sagi Grimberg Reviewed-by: Logan Gunthorpe Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/target/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index f4efe289dc7b..a5f9bbce863f 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -420,7 +420,7 @@ static void nvmet_p2pmem_ns_add_p2p(struct nvmet_ctrl *ctrl, struct pci_dev *p2p_dev; int ret; - if (!ctrl->p2p_client) + if (!ctrl->p2p_client || !ns->use_p2pmem) return; if (ns->p2p_dev) { From 8f676b8508c250bbe255096522fdefb73f1ea0b9 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Fri, 2 Nov 2018 11:22:13 -0700 Subject: [PATCH 275/356] nvme: make sure ns head inherits underlying device limits Whenever we update ns_head info, we need to make sure it is still compatible with all underlying backing devices because although nvme multipath doesn't have any explicit use of these limits, other devices can still be stacked on top of it which may rely on the underlying limits. Start with unlimited stacking limits, and every info update iterate over siblings and adjust queue limits. Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/host/core.c | 4 +++- drivers/nvme/host/multipath.c | 1 + 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 2e65be8b1387..559d567693b8 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1519,8 +1519,10 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id) if (ns->ndev) nvme_nvm_update_nvm_info(ns); #ifdef CONFIG_NVME_MULTIPATH - if (ns->head->disk) + if (ns->head->disk) { nvme_update_disk_info(ns->head->disk, ns, id); + blk_queue_stack_limits(ns->head->disk->queue, ns->queue); + } #endif } diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 5e3cc8c59a39..9901afd804ce 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -285,6 +285,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) blk_queue_flag_set(QUEUE_FLAG_NONROT, q); /* set to a default value for 512 until disk is validated */ blk_queue_logical_block_size(q, 512); + blk_set_stacking_limits(&q->limits); /* we need to propagate up the VMC settings */ if (ctrl->vwc & NVME_CTRL_VWC_PRESENT) From d39aa4979219ca3d61c492f7460f1032b97b9ef2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 7 Nov 2018 09:20:25 +0100 Subject: [PATCH 276/356] Revert "nvmet-rdma: use a private workqueue for delete" This reverts commit 2acf70ade79d26b97611a8df52eb22aa33814cd4. The commit never really fixed the intended issue and caused all kinds of other issues, including a use before initialization. Suggested-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/target/rdma.c | 19 ++++--------------- 1 file changed, 4 insertions(+), 15 deletions(-) diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index ddce100be57a..3f7971d3706d 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -122,7 +122,6 @@ struct nvmet_rdma_device { int inline_page_count; }; -static struct workqueue_struct *nvmet_rdma_delete_wq; static bool nvmet_rdma_use_srq; module_param_named(use_srq, nvmet_rdma_use_srq, bool, 0444); MODULE_PARM_DESC(use_srq, "Use shared receive queue."); @@ -1274,12 +1273,12 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id, if (queue->host_qid == 0) { /* Let inflight controller teardown complete */ - flush_workqueue(nvmet_rdma_delete_wq); + flush_scheduled_work(); } ret = nvmet_rdma_cm_accept(cm_id, queue, &event->param.conn); if (ret) { - queue_work(nvmet_rdma_delete_wq, &queue->release_work); + schedule_work(&queue->release_work); /* Destroying rdma_cm id is not needed here */ return 0; } @@ -1344,7 +1343,7 @@ static void __nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue) if (disconnect) { rdma_disconnect(queue->cm_id); - queue_work(nvmet_rdma_delete_wq, &queue->release_work); + schedule_work(&queue->release_work); } } @@ -1374,7 +1373,7 @@ static void nvmet_rdma_queue_connect_fail(struct rdma_cm_id *cm_id, mutex_unlock(&nvmet_rdma_queue_mutex); pr_err("failed to connect queue %d\n", queue->idx); - queue_work(nvmet_rdma_delete_wq, &queue->release_work); + schedule_work(&queue->release_work); } /** @@ -1656,17 +1655,8 @@ static int __init nvmet_rdma_init(void) if (ret) goto err_ib_client; - nvmet_rdma_delete_wq = alloc_workqueue("nvmet-rdma-delete-wq", - WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0); - if (!nvmet_rdma_delete_wq) { - ret = -ENOMEM; - goto err_unreg_transport; - } - return 0; -err_unreg_transport: - nvmet_unregister_transport(&nvmet_rdma_ops); err_ib_client: ib_unregister_client(&nvmet_rdma_ib_client); return ret; @@ -1674,7 +1664,6 @@ err_ib_client: static void __exit nvmet_rdma_exit(void) { - destroy_workqueue(nvmet_rdma_delete_wq); nvmet_unregister_transport(&nvmet_rdma_ops); ib_unregister_client(&nvmet_rdma_ib_client); WARN_ON_ONCE(!list_empty(&nvmet_rdma_queue_list)); From 1adfc5e4136f5967d591c399aff95b3b035f16b7 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 29 Oct 2018 20:57:17 +0800 Subject: [PATCH 277/356] block: make sure discard bio is aligned with logical block size Obviously the created discard bio has to be aligned with logical block size. This patch introduces the helper of bio_allowed_max_sectors() for this purpose. Cc: stable@vger.kernel.org Cc: Mike Snitzer Cc: Christoph Hellwig Cc: Xiao Ni Cc: Mariusz Dabrowski Fixes: 744889b7cbb56a6 ("block: don't deal with discard limit in blkdev_issue_discard()") Fixes: a22c4d7e34402cc ("block: re-add discard_granularity and alignment checks") Reported-by: Rui Salvaterra Tested-by: Rui Salvaterra Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-lib.c | 3 +-- block/blk-merge.c | 3 ++- block/blk.h | 10 ++++++++++ 3 files changed, 13 insertions(+), 3 deletions(-) diff --git a/block/blk-lib.c b/block/blk-lib.c index 76f867ea9a9b..d56fd159d2e8 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -57,8 +57,7 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, if (!req_sects) goto fail; - if (req_sects > UINT_MAX >> 9) - req_sects = UINT_MAX >> 9; + req_sects = min(req_sects, bio_allowed_max_sectors(q)); end_sect = sector + req_sects; diff --git a/block/blk-merge.c b/block/blk-merge.c index 208658a901c6..e7696c47489a 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -90,7 +90,8 @@ static struct bio *blk_bio_discard_split(struct request_queue *q, /* Zero-sector (unknown) and one-sector granularities are the same. */ granularity = max(q->limits.discard_granularity >> 9, 1U); - max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9); + max_discard_sectors = min(q->limits.max_discard_sectors, + bio_allowed_max_sectors(q)); max_discard_sectors -= max_discard_sectors % granularity; if (unlikely(!max_discard_sectors)) { diff --git a/block/blk.h b/block/blk.h index c85e53f21cdd..0089fefdf771 100644 --- a/block/blk.h +++ b/block/blk.h @@ -395,6 +395,16 @@ static inline unsigned long blk_rq_deadline(struct request *rq) return rq->__deadline & ~0x1UL; } +/* + * The max size one bio can handle is UINT_MAX becasue bvec_iter.bi_size + * is defined as 'unsigned int', meantime it has to aligned to with logical + * block size which is the minimum accepted unit by hardware. + */ +static inline unsigned int bio_allowed_max_sectors(struct request_queue *q) +{ + return round_down(UINT_MAX, queue_logical_block_size(q)) >> 9; +} + /* * Internal io_context interface */ From ba5d73851e71847ba7f7f4c27a1a6e1f5ab91c79 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 29 Oct 2018 20:57:18 +0800 Subject: [PATCH 278/356] block: cleanup __blkdev_issue_discard() Cleanup __blkdev_issue_discard() a bit: - remove local variable of 'end_sect' - remove code block of 'fail' Cc: Mike Snitzer Cc: Christoph Hellwig Cc: Xiao Ni Cc: Mariusz Dabrowski Tested-by: Rui Salvaterra Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-lib.c | 23 ++++++----------------- 1 file changed, 6 insertions(+), 17 deletions(-) diff --git a/block/blk-lib.c b/block/blk-lib.c index d56fd159d2e8..d58d5d87dd88 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -51,15 +51,12 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, if ((sector | nr_sects) & bs_mask) return -EINVAL; + if (!nr_sects) + return -EINVAL; + while (nr_sects) { - unsigned int req_sects = nr_sects; - sector_t end_sect; - - if (!req_sects) - goto fail; - req_sects = min(req_sects, bio_allowed_max_sectors(q)); - - end_sect = sector + req_sects; + unsigned int req_sects = min_t(unsigned int, nr_sects, + bio_allowed_max_sectors(q)); bio = blk_next_bio(bio, 0, gfp_mask); bio->bi_iter.bi_sector = sector; @@ -67,8 +64,8 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, bio_set_op_attrs(bio, op, 0); bio->bi_iter.bi_size = req_sects << 9; + sector += req_sects; nr_sects -= req_sects; - sector = end_sect; /* * We can loop for a long time in here, if someone does @@ -81,14 +78,6 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, *biop = bio; return 0; - -fail: - if (bio) { - submit_bio_wait(bio); - bio_put(bio); - } - *biop = NULL; - return -EOPNOTSUPP; } EXPORT_SYMBOL(__blkdev_issue_discard); From 34ffec60b27aa81d04e274e71e4c6ef740f75fc7 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 29 Oct 2018 20:57:19 +0800 Subject: [PATCH 279/356] block: make sure writesame bio is aligned with logical block size Obviously the created writesame bio has to be aligned with logical block size, and use bio_allowed_max_sectors() to retrieve this number. Cc: stable@vger.kernel.org Cc: Mike Snitzer Cc: Christoph Hellwig Cc: Xiao Ni Cc: Mariusz Dabrowski Fixes: b49a0871be31a745b2ef ("block: remove split code in blkdev_issue_{discard,write_same}") Tested-by: Rui Salvaterra Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-lib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/blk-lib.c b/block/blk-lib.c index d58d5d87dd88..e8b3bb9bf375 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -149,7 +149,7 @@ static int __blkdev_issue_write_same(struct block_device *bdev, sector_t sector, return -EOPNOTSUPP; /* Ensure that max_write_same_sectors doesn't overflow bi_size */ - max_write_same_sectors = UINT_MAX >> 9; + max_write_same_sectors = bio_allowed_max_sectors(q); while (nr_sects) { bio = blk_next_bio(bio, 1, gfp_mask); From d3132b3860f6cf35ff7609a76bbcdbb814bd027c Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 8 Nov 2018 08:35:06 +0100 Subject: [PATCH 280/356] xen: fix xen_qlock_wait() Commit a856531951dc80 ("xen: make xen_qlock_wait() nestable") introduced a regression for Xen guests running fully virtualized (HVM or PVH mode). The Xen hypervisor wouldn't return from the poll hypercall with interrupts disabled in case of an interrupt (for PV guests it does). So instead of disabling interrupts in xen_qlock_wait() use a nesting counter to avoid calling xen_clear_irq_pending() in case xen_qlock_wait() is nested. Fixes: a856531951dc80 ("xen: make xen_qlock_wait() nestable") Cc: stable@vger.kernel.org Reported-by: Sander Eikelenboom Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Tested-by: Sander Eikelenboom Signed-off-by: Juergen Gross --- arch/x86/xen/spinlock.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 441c88262169..1c8a8816a402 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include @@ -21,6 +22,7 @@ static DEFINE_PER_CPU(int, lock_kicker_irq) = -1; static DEFINE_PER_CPU(char *, irq_name); +static DEFINE_PER_CPU(atomic_t, xen_qlock_wait_nest); static bool xen_pvspin = true; static void xen_qlock_kick(int cpu) @@ -39,25 +41,25 @@ static void xen_qlock_kick(int cpu) */ static void xen_qlock_wait(u8 *byte, u8 val) { - unsigned long flags; int irq = __this_cpu_read(lock_kicker_irq); + atomic_t *nest_cnt = this_cpu_ptr(&xen_qlock_wait_nest); /* If kicker interrupts not initialized yet, just spin */ if (irq == -1 || in_nmi()) return; - /* Guard against reentry. */ - local_irq_save(flags); + /* Detect reentry. */ + atomic_inc(nest_cnt); - /* If irq pending already clear it. */ - if (xen_test_irq_pending(irq)) { + /* If irq pending already and no nested call clear it. */ + if (atomic_read(nest_cnt) == 1 && xen_test_irq_pending(irq)) { xen_clear_irq_pending(irq); } else if (READ_ONCE(*byte) == val) { /* Block until irq becomes pending (or a spurious wakeup) */ xen_poll_irq(irq); } - local_irq_restore(flags); + atomic_dec(nest_cnt); } static irqreturn_t dummy_handler(int irq, void *dev_id) From 3941552aec1e04d63999988a057ae09a1c56ebeb Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 1 Nov 2018 13:33:07 +0100 Subject: [PATCH 281/356] xen: remove size limit of privcmd-buf mapping interface Currently the size of hypercall buffers allocated via /dev/xen/hypercall is limited to a default of 64 memory pages. For live migration of guests this might be too small as the page dirty bitmask needs to be sized according to the size of the guest. This means migrating a 8GB sized guest is already exhausting the default buffer size for the dirty bitmap. There is no sensible way to set a sane limit, so just remove it completely. The device node's usage is limited to root anyway, so there is no additional DOS scenario added by allowing unlimited buffers. While at it make the error path for the -ENOMEM case a little bit cleaner by setting n_pages to the number of successfully allocated pages instead of the target size. Fixes: c51b3c639e01f2 ("xen: add new hypercall buffer mapping device") Cc: #4.18 Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Signed-off-by: Juergen Gross --- drivers/xen/privcmd-buf.c | 22 ++++------------------ 1 file changed, 4 insertions(+), 18 deletions(-) diff --git a/drivers/xen/privcmd-buf.c b/drivers/xen/privcmd-buf.c index df1ed37c3269..de01a6d0059d 100644 --- a/drivers/xen/privcmd-buf.c +++ b/drivers/xen/privcmd-buf.c @@ -21,15 +21,9 @@ MODULE_LICENSE("GPL"); -static unsigned int limit = 64; -module_param(limit, uint, 0644); -MODULE_PARM_DESC(limit, "Maximum number of pages that may be allocated by " - "the privcmd-buf device per open file"); - struct privcmd_buf_private { struct mutex lock; struct list_head list; - unsigned int allocated; }; struct privcmd_buf_vma_private { @@ -60,13 +54,10 @@ static void privcmd_buf_vmapriv_free(struct privcmd_buf_vma_private *vma_priv) { unsigned int i; - vma_priv->file_priv->allocated -= vma_priv->n_pages; - list_del(&vma_priv->list); for (i = 0; i < vma_priv->n_pages; i++) - if (vma_priv->pages[i]) - __free_page(vma_priv->pages[i]); + __free_page(vma_priv->pages[i]); kfree(vma_priv); } @@ -146,8 +137,7 @@ static int privcmd_buf_mmap(struct file *file, struct vm_area_struct *vma) unsigned int i; int ret = 0; - if (!(vma->vm_flags & VM_SHARED) || count > limit || - file_priv->allocated + count > limit) + if (!(vma->vm_flags & VM_SHARED)) return -EINVAL; vma_priv = kzalloc(sizeof(*vma_priv) + count * sizeof(void *), @@ -155,19 +145,15 @@ static int privcmd_buf_mmap(struct file *file, struct vm_area_struct *vma) if (!vma_priv) return -ENOMEM; - vma_priv->n_pages = count; - count = 0; - for (i = 0; i < vma_priv->n_pages; i++) { + for (i = 0; i < count; i++) { vma_priv->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!vma_priv->pages[i]) break; - count++; + vma_priv->n_pages++; } mutex_lock(&file_priv->lock); - file_priv->allocated += count; - vma_priv->file_priv = file_priv; vma_priv->users = 1; From ab214c48387aaaadcf8246b4b00d8b78286fde1b Mon Sep 17 00:00:00 2001 From: Vignesh R Date: Fri, 9 Nov 2018 16:44:10 +0530 Subject: [PATCH 282/356] dt-bindings: i2c: omap: Add new compatible for AM654 SoCs AM654 SoCs have same I2C IP as OMAP SoCs. Add new compatible to handle AM654 SoCs. While at that reformat the existing compatible list for older SoCs to list one valid compatible per line. Signed-off-by: Vignesh R Reviewed-by: Rob Herring Reviewed-by: Grygorii Strashko Signed-off-by: Wolfram Sang --- Documentation/devicetree/bindings/i2c/i2c-omap.txt | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/i2c/i2c-omap.txt b/Documentation/devicetree/bindings/i2c/i2c-omap.txt index 7e49839d4124..4b90ba9f31b7 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-omap.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-omap.txt @@ -1,8 +1,12 @@ I2C for OMAP platforms Required properties : -- compatible : Must be "ti,omap2420-i2c", "ti,omap2430-i2c", "ti,omap3-i2c" - or "ti,omap4-i2c" +- compatible : Must be + "ti,omap2420-i2c" for OMAP2420 SoCs + "ti,omap2430-i2c" for OMAP2430 SoCs + "ti,omap3-i2c" for OMAP3 SoCs + "ti,omap4-i2c" for OMAP4+ SoCs + "ti,am654-i2c", "ti,omap4-i2c" for AM654 SoCs - ti,hwmods : Must be "i2c", n being the instance number (1-based) - #address-cells = <1>; - #size-cells = <0>; From 5b277402deac0691226a947df71c581686bd4020 Mon Sep 17 00:00:00 2001 From: Vignesh R Date: Fri, 9 Nov 2018 16:44:11 +0530 Subject: [PATCH 283/356] i2c: omap: Enable for ARCH_K3 Allow I2C_OMAP to be built for K3 platforms. Signed-off-by: Vignesh R Reviewed-by: Grygorii Strashko Signed-off-by: Wolfram Sang --- drivers/i2c/busses/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index 56ccb1ea7da5..77dc94b44011 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -752,7 +752,7 @@ config I2C_OCORES config I2C_OMAP tristate "OMAP I2C adapter" - depends on ARCH_OMAP + depends on ARCH_OMAP || ARCH_K3 default y if MACH_OMAP_H3 || MACH_OMAP_OSK help If you say yes to this option, support will be included for the From 350784e79230f85e9007c4c7d8b2259717d67a4d Mon Sep 17 00:00:00 2001 From: Vignesh R Date: Fri, 9 Nov 2018 16:44:12 +0530 Subject: [PATCH 284/356] MAINTAINERS: Add entry for i2c-omap driver Add separate entry for i2c-omap and add my name as maintainer for this driver. Signed-off-by: Vignesh R Acked-by: Tony Lindgren Signed-off-by: Wolfram Sang --- MAINTAINERS | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index f4855974f325..259fe9445d2f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10784,6 +10784,14 @@ L: linux-omap@vger.kernel.org S: Maintained F: arch/arm/mach-omap2/omap_hwmod.* +OMAP I2C DRIVER +M: Vignesh R +L: linux-omap@vger.kernel.org +L: linux-i2c@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/i2c/i2c-omap.txt +F: drivers/i2c/busses/i2c-omap.c + OMAP IMAGING SUBSYSTEM (OMAP3 ISP and OMAP4 ISS) M: Laurent Pinchart L: linux-media@vger.kernel.org From 848bd3f3de9d44950c00eda6c115e8e9785440da Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Fri, 2 Nov 2018 13:57:32 -0700 Subject: [PATCH 285/356] i2c: qcom-geni: Fix runtime PM mismatch with child devices We need to enable runtime PM on this i2c controller before populating child devices with i2c_add_adapter(). Otherwise, if a child device uses runtime PM and stays runtime PM enabled we'll get the following warning at boot. Enabling runtime PM for inactive device (a98000.i2c) with active children [...] Call trace: pm_runtime_enable+0xd8/0xf8 geni_i2c_probe+0x440/0x460 platform_drv_probe+0x74/0xc8 [...] Let's move the runtime PM enabling and setup to before we add the adapter, so that this device can respond to runtime PM requests from children. Fixes: 37692de5d523 ("i2c: i2c-qcom-geni: Add bus driver for the Qualcomm GENI I2C controller") Signed-off-by: Stephen Boyd Reviewed-by: Douglas Anderson Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-qcom-geni.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index 527f55c8c4c7..db075bc0d952 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -571,18 +571,19 @@ static int geni_i2c_probe(struct platform_device *pdev) dev_dbg(&pdev->dev, "i2c fifo/se-dma mode. fifo depth:%d\n", tx_depth); - ret = i2c_add_adapter(&gi2c->adap); - if (ret) { - dev_err(&pdev->dev, "Error adding i2c adapter %d\n", ret); - return ret; - } - gi2c->suspended = 1; pm_runtime_set_suspended(gi2c->se.dev); pm_runtime_set_autosuspend_delay(gi2c->se.dev, I2C_AUTO_SUSPEND_DELAY); pm_runtime_use_autosuspend(gi2c->se.dev); pm_runtime_enable(gi2c->se.dev); + ret = i2c_add_adapter(&gi2c->adap); + if (ret) { + dev_err(&pdev->dev, "Error adding i2c adapter %d\n", ret); + pm_runtime_disable(gi2c->se.dev); + return ret; + } + return 0; } @@ -590,8 +591,8 @@ static int geni_i2c_remove(struct platform_device *pdev) { struct geni_i2c_dev *gi2c = platform_get_drvdata(pdev); - pm_runtime_disable(gi2c->se.dev); i2c_del_adapter(&gi2c->adap); + pm_runtime_disable(gi2c->se.dev); return 0; } From eb6984fa4ce2837dcb1f66720a600f31b0bb3739 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Fri, 9 Nov 2018 11:34:40 -0500 Subject: [PATCH 286/356] ext4: missing !bh check in ext4_xattr_inode_write() According to Ted Ts'o ext4_getblk() called in ext4_xattr_inode_write() should not return bh = NULL The only time that bh could be NULL, then, would be in the case of something really going wrong; a programming error elsewhere (perhaps a wild pointer dereference) or I/O error causing on-disk file system corruption (although that would be highly unlikely given that we had *just* allocated the blocks and so the metadata blocks in question probably would still be in the cache). Fixes: e50e5129f384 ("ext4: xattr-in-inode support") Signed-off-by: Vasily Averin Signed-off-by: Theodore Ts'o Cc: stable@kernel.org # 4.13 --- fs/ext4/xattr.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 0b9688683526..7643d52c776c 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1384,6 +1384,12 @@ retry: bh = ext4_getblk(handle, ea_inode, block, 0); if (IS_ERR(bh)) return PTR_ERR(bh); + if (!bh) { + WARN_ON_ONCE(1); + EXT4_ERROR_INODE(ea_inode, + "ext4_getblk() return bh = NULL"); + return -EFSCORRUPTED; + } ret = ext4_journal_get_write_access(handle, bh); if (ret) goto out; From c71bcdcb42a7493348d3b45dee8139843bf45efc Mon Sep 17 00:00:00 2001 From: Ajay Gupta Date: Fri, 26 Oct 2018 09:36:58 -0700 Subject: [PATCH 287/356] i2c: add i2c bus driver for NVIDIA GPU Latest NVIDIA GPU card has USB Type-C interface. There is a Type-C controller which can be accessed over I2C. This driver adds I2C bus driver to communicate with Type-C controller. I2C client driver will be part of USB Type-C UCSI driver. Signed-off-by: Ajay Gupta Reviewed-by: Andy Shevchenko [wsa: kept Makefile sorting] Signed-off-by: Wolfram Sang --- Documentation/i2c/busses/i2c-nvidia-gpu | 18 ++ MAINTAINERS | 7 + drivers/i2c/busses/Kconfig | 9 + drivers/i2c/busses/Makefile | 1 + drivers/i2c/busses/i2c-nvidia-gpu.c | 368 ++++++++++++++++++++++++ 5 files changed, 403 insertions(+) create mode 100644 Documentation/i2c/busses/i2c-nvidia-gpu create mode 100644 drivers/i2c/busses/i2c-nvidia-gpu.c diff --git a/Documentation/i2c/busses/i2c-nvidia-gpu b/Documentation/i2c/busses/i2c-nvidia-gpu new file mode 100644 index 000000000000..31884d2b2eb5 --- /dev/null +++ b/Documentation/i2c/busses/i2c-nvidia-gpu @@ -0,0 +1,18 @@ +Kernel driver i2c-nvidia-gpu + +Datasheet: not publicly available. + +Authors: + Ajay Gupta + +Description +----------- + +i2c-nvidia-gpu is a driver for I2C controller included in NVIDIA Turing +and later GPUs and it is used to communicate with Type-C controller on GPUs. + +If your 'lspci -v' listing shows something like the following, + +01:00.3 Serial bus controller [0c80]: NVIDIA Corporation Device 1ad9 (rev a1) + +then this driver should support the I2C controller of your GPU. diff --git a/MAINTAINERS b/MAINTAINERS index 259fe9445d2f..1835d3ffd7ea 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6861,6 +6861,13 @@ L: linux-acpi@vger.kernel.org S: Maintained F: drivers/i2c/i2c-core-acpi.c +I2C CONTROLLER DRIVER FOR NVIDIA GPU +M: Ajay Gupta +L: linux-i2c@vger.kernel.org +S: Maintained +F: Documentation/i2c/busses/i2c-nvidia-gpu +F: drivers/i2c/busses/i2c-nvidia-gpu.c + I2C MUXES M: Peter Rosin L: linux-i2c@vger.kernel.org diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index 77dc94b44011..f2c681971201 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -224,6 +224,15 @@ config I2C_NFORCE2_S4985 This driver can also be built as a module. If so, the module will be called i2c-nforce2-s4985. +config I2C_NVIDIA_GPU + tristate "NVIDIA GPU I2C controller" + depends on PCI + help + If you say yes to this option, support will be included for the + NVIDIA GPU I2C controller which is used to communicate with the GPU's + Type-C controller. This driver can also be built as a module called + i2c-nvidia-gpu. + config I2C_SIS5595 tristate "SiS 5595" depends on PCI diff --git a/drivers/i2c/busses/Makefile b/drivers/i2c/busses/Makefile index 18b26af82b1c..5f0cb6915969 100644 --- a/drivers/i2c/busses/Makefile +++ b/drivers/i2c/busses/Makefile @@ -19,6 +19,7 @@ obj-$(CONFIG_I2C_ISCH) += i2c-isch.o obj-$(CONFIG_I2C_ISMT) += i2c-ismt.o obj-$(CONFIG_I2C_NFORCE2) += i2c-nforce2.o obj-$(CONFIG_I2C_NFORCE2_S4985) += i2c-nforce2-s4985.o +obj-$(CONFIG_I2C_NVIDIA_GPU) += i2c-nvidia-gpu.o obj-$(CONFIG_I2C_PIIX4) += i2c-piix4.o obj-$(CONFIG_I2C_SIS5595) += i2c-sis5595.o obj-$(CONFIG_I2C_SIS630) += i2c-sis630.o diff --git a/drivers/i2c/busses/i2c-nvidia-gpu.c b/drivers/i2c/busses/i2c-nvidia-gpu.c new file mode 100644 index 000000000000..744f5e42636b --- /dev/null +++ b/drivers/i2c/busses/i2c-nvidia-gpu.c @@ -0,0 +1,368 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Nvidia GPU I2C controller Driver + * + * Copyright (C) 2018 NVIDIA Corporation. All rights reserved. + * Author: Ajay Gupta + */ +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +/* I2C definitions */ +#define I2C_MST_CNTL 0x00 +#define I2C_MST_CNTL_GEN_START BIT(0) +#define I2C_MST_CNTL_GEN_STOP BIT(1) +#define I2C_MST_CNTL_CMD_READ (1 << 2) +#define I2C_MST_CNTL_CMD_WRITE (2 << 2) +#define I2C_MST_CNTL_BURST_SIZE_SHIFT 6 +#define I2C_MST_CNTL_GEN_NACK BIT(28) +#define I2C_MST_CNTL_STATUS GENMASK(30, 29) +#define I2C_MST_CNTL_STATUS_OKAY (0 << 29) +#define I2C_MST_CNTL_STATUS_NO_ACK (1 << 29) +#define I2C_MST_CNTL_STATUS_TIMEOUT (2 << 29) +#define I2C_MST_CNTL_STATUS_BUS_BUSY (3 << 29) +#define I2C_MST_CNTL_CYCLE_TRIGGER BIT(31) + +#define I2C_MST_ADDR 0x04 + +#define I2C_MST_I2C0_TIMING 0x08 +#define I2C_MST_I2C0_TIMING_SCL_PERIOD_100KHZ 0x10e +#define I2C_MST_I2C0_TIMING_TIMEOUT_CLK_CNT 16 +#define I2C_MST_I2C0_TIMING_TIMEOUT_CLK_CNT_MAX 255 +#define I2C_MST_I2C0_TIMING_TIMEOUT_CHECK BIT(24) + +#define I2C_MST_DATA 0x0c + +#define I2C_MST_HYBRID_PADCTL 0x20 +#define I2C_MST_HYBRID_PADCTL_MODE_I2C BIT(0) +#define I2C_MST_HYBRID_PADCTL_I2C_SCL_INPUT_RCV BIT(14) +#define I2C_MST_HYBRID_PADCTL_I2C_SDA_INPUT_RCV BIT(15) + +struct gpu_i2c_dev { + struct device *dev; + void __iomem *regs; + struct i2c_adapter adapter; + struct i2c_board_info *gpu_ccgx_ucsi; +}; + +static void gpu_enable_i2c_bus(struct gpu_i2c_dev *i2cd) +{ + u32 val; + + /* enable I2C */ + val = readl(i2cd->regs + I2C_MST_HYBRID_PADCTL); + val |= I2C_MST_HYBRID_PADCTL_MODE_I2C | + I2C_MST_HYBRID_PADCTL_I2C_SCL_INPUT_RCV | + I2C_MST_HYBRID_PADCTL_I2C_SDA_INPUT_RCV; + writel(val, i2cd->regs + I2C_MST_HYBRID_PADCTL); + + /* enable 100KHZ mode */ + val = I2C_MST_I2C0_TIMING_SCL_PERIOD_100KHZ; + val |= (I2C_MST_I2C0_TIMING_TIMEOUT_CLK_CNT_MAX + << I2C_MST_I2C0_TIMING_TIMEOUT_CLK_CNT); + val |= I2C_MST_I2C0_TIMING_TIMEOUT_CHECK; + writel(val, i2cd->regs + I2C_MST_I2C0_TIMING); +} + +static int gpu_i2c_check_status(struct gpu_i2c_dev *i2cd) +{ + unsigned long target = jiffies + msecs_to_jiffies(1000); + u32 val; + + do { + val = readl(i2cd->regs + I2C_MST_CNTL); + if (!(val & I2C_MST_CNTL_CYCLE_TRIGGER)) + break; + if ((val & I2C_MST_CNTL_STATUS) != + I2C_MST_CNTL_STATUS_BUS_BUSY) + break; + usleep_range(500, 600); + } while (time_is_after_jiffies(target)); + + if (time_is_before_jiffies(target)) { + dev_err(i2cd->dev, "i2c timeout error %x\n", val); + return -ETIME; + } + + val = readl(i2cd->regs + I2C_MST_CNTL); + switch (val & I2C_MST_CNTL_STATUS) { + case I2C_MST_CNTL_STATUS_OKAY: + return 0; + case I2C_MST_CNTL_STATUS_NO_ACK: + return -EIO; + case I2C_MST_CNTL_STATUS_TIMEOUT: + return -ETIME; + default: + return 0; + } +} + +static int gpu_i2c_read(struct gpu_i2c_dev *i2cd, u8 *data, u16 len) +{ + int status; + u32 val; + + val = I2C_MST_CNTL_GEN_START | I2C_MST_CNTL_CMD_READ | + (len << I2C_MST_CNTL_BURST_SIZE_SHIFT) | + I2C_MST_CNTL_CYCLE_TRIGGER | I2C_MST_CNTL_GEN_NACK; + writel(val, i2cd->regs + I2C_MST_CNTL); + + status = gpu_i2c_check_status(i2cd); + if (status < 0) + return status; + + val = readl(i2cd->regs + I2C_MST_DATA); + switch (len) { + case 1: + data[0] = val; + break; + case 2: + put_unaligned_be16(val, data); + break; + case 3: + put_unaligned_be16(val >> 8, data); + data[2] = val; + break; + case 4: + put_unaligned_be32(val, data); + break; + default: + break; + } + return status; +} + +static int gpu_i2c_start(struct gpu_i2c_dev *i2cd) +{ + writel(I2C_MST_CNTL_GEN_START, i2cd->regs + I2C_MST_CNTL); + return gpu_i2c_check_status(i2cd); +} + +static int gpu_i2c_stop(struct gpu_i2c_dev *i2cd) +{ + writel(I2C_MST_CNTL_GEN_STOP, i2cd->regs + I2C_MST_CNTL); + return gpu_i2c_check_status(i2cd); +} + +static int gpu_i2c_write(struct gpu_i2c_dev *i2cd, u8 data) +{ + u32 val; + + writel(data, i2cd->regs + I2C_MST_DATA); + + val = I2C_MST_CNTL_CMD_WRITE | (1 << I2C_MST_CNTL_BURST_SIZE_SHIFT); + writel(val, i2cd->regs + I2C_MST_CNTL); + + return gpu_i2c_check_status(i2cd); +} + +static int gpu_i2c_master_xfer(struct i2c_adapter *adap, + struct i2c_msg *msgs, int num) +{ + struct gpu_i2c_dev *i2cd = i2c_get_adapdata(adap); + int status, status2; + int i, j; + + /* + * The controller supports maximum 4 byte read due to known + * limitation of sending STOP after every read. + */ + for (i = 0; i < num; i++) { + if (msgs[i].flags & I2C_M_RD) { + /* program client address before starting read */ + writel(msgs[i].addr, i2cd->regs + I2C_MST_ADDR); + /* gpu_i2c_read has implicit start */ + status = gpu_i2c_read(i2cd, msgs[i].buf, msgs[i].len); + if (status < 0) + goto stop; + } else { + u8 addr = i2c_8bit_addr_from_msg(msgs + i); + + status = gpu_i2c_start(i2cd); + if (status < 0) { + if (i == 0) + return status; + goto stop; + } + + status = gpu_i2c_write(i2cd, addr); + if (status < 0) + goto stop; + + for (j = 0; j < msgs[i].len; j++) { + status = gpu_i2c_write(i2cd, msgs[i].buf[j]); + if (status < 0) + goto stop; + } + } + } + status = gpu_i2c_stop(i2cd); + if (status < 0) + return status; + + return i; +stop: + status2 = gpu_i2c_stop(i2cd); + if (status2 < 0) + dev_err(i2cd->dev, "i2c stop failed %d\n", status2); + return status; +} + +static const struct i2c_adapter_quirks gpu_i2c_quirks = { + .max_read_len = 4, + .flags = I2C_AQ_COMB_WRITE_THEN_READ, +}; + +static u32 gpu_i2c_functionality(struct i2c_adapter *adap) +{ + return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL; +} + +static const struct i2c_algorithm gpu_i2c_algorithm = { + .master_xfer = gpu_i2c_master_xfer, + .functionality = gpu_i2c_functionality, +}; + +/* + * This driver is for Nvidia GPU cards with USB Type-C interface. + * We want to identify the cards using vendor ID and class code only + * to avoid dependency of adding product id for any new card which + * requires this driver. + * Currently there is no class code defined for UCSI device over PCI + * so using UNKNOWN class for now and it will be updated when UCSI + * over PCI gets a class code. + * There is no other NVIDIA cards with UNKNOWN class code. Even if the + * driver gets loaded for an undesired card then eventually i2c_read() + * (initiated from UCSI i2c_client) will timeout or UCSI commands will + * timeout. + */ +#define PCI_CLASS_SERIAL_UNKNOWN 0x0c80 +static const struct pci_device_id gpu_i2c_ids[] = { + { PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_SERIAL_UNKNOWN << 8, 0xffffff00}, + { } +}; +MODULE_DEVICE_TABLE(pci, gpu_i2c_ids); + +static int gpu_populate_client(struct gpu_i2c_dev *i2cd, int irq) +{ + struct i2c_client *ccgx_client; + + i2cd->gpu_ccgx_ucsi = devm_kzalloc(i2cd->dev, + sizeof(*i2cd->gpu_ccgx_ucsi), + GFP_KERNEL); + if (!i2cd->gpu_ccgx_ucsi) + return -ENOMEM; + + strlcpy(i2cd->gpu_ccgx_ucsi->type, "ccgx-ucsi", + sizeof(i2cd->gpu_ccgx_ucsi->type)); + i2cd->gpu_ccgx_ucsi->addr = 0x8; + i2cd->gpu_ccgx_ucsi->irq = irq; + ccgx_client = i2c_new_device(&i2cd->adapter, i2cd->gpu_ccgx_ucsi); + if (!ccgx_client) + return -ENODEV; + + return 0; +} + +static int gpu_i2c_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct gpu_i2c_dev *i2cd; + int status; + + i2cd = devm_kzalloc(&pdev->dev, sizeof(*i2cd), GFP_KERNEL); + if (!i2cd) + return -ENOMEM; + + i2cd->dev = &pdev->dev; + dev_set_drvdata(&pdev->dev, i2cd); + + status = pcim_enable_device(pdev); + if (status < 0) { + dev_err(&pdev->dev, "pcim_enable_device failed %d\n", status); + return status; + } + + pci_set_master(pdev); + + i2cd->regs = pcim_iomap(pdev, 0, 0); + if (!i2cd->regs) { + dev_err(&pdev->dev, "pcim_iomap failed\n"); + return -ENOMEM; + } + + status = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI); + if (status < 0) { + dev_err(&pdev->dev, "pci_alloc_irq_vectors err %d\n", status); + return status; + } + + gpu_enable_i2c_bus(i2cd); + + i2c_set_adapdata(&i2cd->adapter, i2cd); + i2cd->adapter.owner = THIS_MODULE; + strlcpy(i2cd->adapter.name, "NVIDIA GPU I2C adapter", + sizeof(i2cd->adapter.name)); + i2cd->adapter.algo = &gpu_i2c_algorithm; + i2cd->adapter.quirks = &gpu_i2c_quirks; + i2cd->adapter.dev.parent = &pdev->dev; + status = i2c_add_adapter(&i2cd->adapter); + if (status < 0) + goto free_irq_vectors; + + status = gpu_populate_client(i2cd, pdev->irq); + if (status < 0) { + dev_err(&pdev->dev, "gpu_populate_client failed %d\n", status); + goto del_adapter; + } + + return 0; + +del_adapter: + i2c_del_adapter(&i2cd->adapter); +free_irq_vectors: + pci_free_irq_vectors(pdev); + return status; +} + +static void gpu_i2c_remove(struct pci_dev *pdev) +{ + struct gpu_i2c_dev *i2cd = dev_get_drvdata(&pdev->dev); + + i2c_del_adapter(&i2cd->adapter); + pci_free_irq_vectors(pdev); +} + +static int gpu_i2c_resume(struct device *dev) +{ + struct gpu_i2c_dev *i2cd = dev_get_drvdata(dev); + + gpu_enable_i2c_bus(i2cd); + return 0; +} + +UNIVERSAL_DEV_PM_OPS(gpu_i2c_driver_pm, NULL, gpu_i2c_resume, NULL); + +static struct pci_driver gpu_i2c_driver = { + .name = "nvidia-gpu", + .id_table = gpu_i2c_ids, + .probe = gpu_i2c_probe, + .remove = gpu_i2c_remove, + .driver = { + .pm = &gpu_i2c_driver_pm, + }, +}; + +module_pci_driver(gpu_i2c_driver); + +MODULE_AUTHOR("Ajay Gupta "); +MODULE_DESCRIPTION("Nvidia GPU I2C controller Driver"); +MODULE_LICENSE("GPL v2"); From caccdcc5dbec0dd9643fe1667893e78631a4d38e Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Fri, 9 Nov 2018 17:54:38 +0100 Subject: [PATCH 288/356] i2c: nvidia-gpu: make pm_ops static sparse rightfully says: warning: symbol 'gpu_i2c_driver_pm' was not declared. Should it be static? Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-nvidia-gpu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-nvidia-gpu.c b/drivers/i2c/busses/i2c-nvidia-gpu.c index 744f5e42636b..8822357bca0c 100644 --- a/drivers/i2c/busses/i2c-nvidia-gpu.c +++ b/drivers/i2c/busses/i2c-nvidia-gpu.c @@ -349,7 +349,7 @@ static int gpu_i2c_resume(struct device *dev) return 0; } -UNIVERSAL_DEV_PM_OPS(gpu_i2c_driver_pm, NULL, gpu_i2c_resume, NULL); +static UNIVERSAL_DEV_PM_OPS(gpu_i2c_driver_pm, NULL, gpu_i2c_resume, NULL); static struct pci_driver gpu_i2c_driver = { .name = "nvidia-gpu", From 641a41dbba217ee5bd26abe6be77f8cead9cd00e Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Tue, 30 Oct 2018 15:13:35 +0900 Subject: [PATCH 289/356] serial: sh-sci: Fix could not remove dev_attr_rx_fifo_timeout This patch fixes an issue that the sci_remove() could not remove dev_attr_rx_fifo_timeout because uart_remove_one_port() set the port->port.type to PORT_UNKNOWN. Reported-by: Hiromitsu Yamasaki Fixes: 5d23188a473d ("serial: sh-sci: make RX FIFO parameters tunable via sysfs") Cc: # v4.11+ Signed-off-by: Yoshihiro Shimoda Reviewed-by: Ulrich Hecht Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/sh-sci.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index e19bfbba8a01..effba6ce0caa 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -3102,6 +3102,7 @@ static struct uart_driver sci_uart_driver = { static int sci_remove(struct platform_device *dev) { struct sci_port *port = platform_get_drvdata(dev); + unsigned int type = port->port.type; /* uart_remove_... clears it */ sci_ports_in_use &= ~BIT(port->port.line); uart_remove_one_port(&sci_uart_driver, &port->port); @@ -3112,8 +3113,7 @@ static int sci_remove(struct platform_device *dev) sysfs_remove_file(&dev->dev.kobj, &dev_attr_rx_fifo_trigger.attr); } - if (port->port.type == PORT_SCIFA || port->port.type == PORT_SCIFB || - port->port.type == PORT_HSCIF) { + if (type == PORT_SCIFA || type == PORT_SCIFB || type == PORT_HSCIF) { sysfs_remove_file(&dev->dev.kobj, &dev_attr_rx_fifo_timeout.attr); } From 247c554a14aa16ca08f4ed4d9eb39a2389f69d1d Mon Sep 17 00:00:00 2001 From: Ajay Gupta Date: Fri, 26 Oct 2018 09:36:59 -0700 Subject: [PATCH 290/356] usb: typec: ucsi: add support for Cypress CCGx Latest NVIDIA GPU cards have a Cypress CCGx Type-C controller over I2C interface. This UCSI I2C driver uses I2C bus driver interface for communicating with Type-C controller. Signed-off-by: Ajay Gupta Acked-by: Heikki Krogerus Signed-off-by: Wolfram Sang --- drivers/usb/typec/ucsi/Kconfig | 10 + drivers/usb/typec/ucsi/Makefile | 2 + drivers/usb/typec/ucsi/ucsi_ccg.c | 307 ++++++++++++++++++++++++++++++ 3 files changed, 319 insertions(+) create mode 100644 drivers/usb/typec/ucsi/ucsi_ccg.c diff --git a/drivers/usb/typec/ucsi/Kconfig b/drivers/usb/typec/ucsi/Kconfig index e36d6c73c4a4..78118883f96c 100644 --- a/drivers/usb/typec/ucsi/Kconfig +++ b/drivers/usb/typec/ucsi/Kconfig @@ -23,6 +23,16 @@ config TYPEC_UCSI if TYPEC_UCSI +config UCSI_CCG + tristate "UCSI Interface Driver for Cypress CCGx" + depends on I2C + help + This driver enables UCSI support on platforms that expose a + Cypress CCGx Type-C controller over I2C interface. + + To compile the driver as a module, choose M here: the module will be + called ucsi_ccg. + config UCSI_ACPI tristate "UCSI ACPI Interface Driver" depends on ACPI diff --git a/drivers/usb/typec/ucsi/Makefile b/drivers/usb/typec/ucsi/Makefile index 7afbea512207..2f4900b26210 100644 --- a/drivers/usb/typec/ucsi/Makefile +++ b/drivers/usb/typec/ucsi/Makefile @@ -8,3 +8,5 @@ typec_ucsi-y := ucsi.o typec_ucsi-$(CONFIG_TRACING) += trace.o obj-$(CONFIG_UCSI_ACPI) += ucsi_acpi.o + +obj-$(CONFIG_UCSI_CCG) += ucsi_ccg.o diff --git a/drivers/usb/typec/ucsi/ucsi_ccg.c b/drivers/usb/typec/ucsi/ucsi_ccg.c new file mode 100644 index 000000000000..de8a43bdff68 --- /dev/null +++ b/drivers/usb/typec/ucsi/ucsi_ccg.c @@ -0,0 +1,307 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * UCSI driver for Cypress CCGx Type-C controller + * + * Copyright (C) 2017-2018 NVIDIA Corporation. All rights reserved. + * Author: Ajay Gupta + * + * Some code borrowed from drivers/usb/typec/ucsi/ucsi_acpi.c + */ +#include +#include +#include +#include +#include +#include + +#include +#include "ucsi.h" + +struct ucsi_ccg { + struct device *dev; + struct ucsi *ucsi; + struct ucsi_ppm ppm; + struct i2c_client *client; +}; + +#define CCGX_RAB_INTR_REG 0x06 +#define CCGX_RAB_UCSI_CONTROL 0x39 +#define CCGX_RAB_UCSI_CONTROL_START BIT(0) +#define CCGX_RAB_UCSI_CONTROL_STOP BIT(1) +#define CCGX_RAB_UCSI_DATA_BLOCK(offset) (0xf000 | ((offset) & 0xff)) + +static int ccg_read(struct ucsi_ccg *uc, u16 rab, u8 *data, u32 len) +{ + struct i2c_client *client = uc->client; + const struct i2c_adapter_quirks *quirks = client->adapter->quirks; + unsigned char buf[2]; + struct i2c_msg msgs[] = { + { + .addr = client->addr, + .flags = 0x0, + .len = sizeof(buf), + .buf = buf, + }, + { + .addr = client->addr, + .flags = I2C_M_RD, + .buf = data, + }, + }; + u32 rlen, rem_len = len, max_read_len = len; + int status; + + /* check any max_read_len limitation on i2c adapter */ + if (quirks && quirks->max_read_len) + max_read_len = quirks->max_read_len; + + while (rem_len > 0) { + msgs[1].buf = &data[len - rem_len]; + rlen = min_t(u16, rem_len, max_read_len); + msgs[1].len = rlen; + put_unaligned_le16(rab, buf); + status = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs)); + if (status < 0) { + dev_err(uc->dev, "i2c_transfer failed %d\n", status); + return status; + } + rab += rlen; + rem_len -= rlen; + } + + return 0; +} + +static int ccg_write(struct ucsi_ccg *uc, u16 rab, u8 *data, u32 len) +{ + struct i2c_client *client = uc->client; + unsigned char *buf; + struct i2c_msg msgs[] = { + { + .addr = client->addr, + .flags = 0x0, + } + }; + int status; + + buf = kzalloc(len + sizeof(rab), GFP_KERNEL); + if (!buf) + return -ENOMEM; + + put_unaligned_le16(rab, buf); + memcpy(buf + sizeof(rab), data, len); + + msgs[0].len = len + sizeof(rab); + msgs[0].buf = buf; + + status = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs)); + if (status < 0) { + dev_err(uc->dev, "i2c_transfer failed %d\n", status); + kfree(buf); + return status; + } + + kfree(buf); + return 0; +} + +static int ucsi_ccg_init(struct ucsi_ccg *uc) +{ + unsigned int count = 10; + u8 data; + int status; + + data = CCGX_RAB_UCSI_CONTROL_STOP; + status = ccg_write(uc, CCGX_RAB_UCSI_CONTROL, &data, sizeof(data)); + if (status < 0) + return status; + + data = CCGX_RAB_UCSI_CONTROL_START; + status = ccg_write(uc, CCGX_RAB_UCSI_CONTROL, &data, sizeof(data)); + if (status < 0) + return status; + + /* + * Flush CCGx RESPONSE queue by acking interrupts. Above ucsi control + * register write will push response which must be cleared. + */ + do { + status = ccg_read(uc, CCGX_RAB_INTR_REG, &data, sizeof(data)); + if (status < 0) + return status; + + if (!data) + return 0; + + status = ccg_write(uc, CCGX_RAB_INTR_REG, &data, sizeof(data)); + if (status < 0) + return status; + + usleep_range(10000, 11000); + } while (--count); + + return -ETIMEDOUT; +} + +static int ucsi_ccg_send_data(struct ucsi_ccg *uc) +{ + u8 *ppm = (u8 *)uc->ppm.data; + int status; + u16 rab; + + rab = CCGX_RAB_UCSI_DATA_BLOCK(offsetof(struct ucsi_data, message_out)); + status = ccg_write(uc, rab, ppm + + offsetof(struct ucsi_data, message_out), + sizeof(uc->ppm.data->message_out)); + if (status < 0) + return status; + + rab = CCGX_RAB_UCSI_DATA_BLOCK(offsetof(struct ucsi_data, ctrl)); + return ccg_write(uc, rab, ppm + offsetof(struct ucsi_data, ctrl), + sizeof(uc->ppm.data->ctrl)); +} + +static int ucsi_ccg_recv_data(struct ucsi_ccg *uc) +{ + u8 *ppm = (u8 *)uc->ppm.data; + int status; + u16 rab; + + rab = CCGX_RAB_UCSI_DATA_BLOCK(offsetof(struct ucsi_data, cci)); + status = ccg_read(uc, rab, ppm + offsetof(struct ucsi_data, cci), + sizeof(uc->ppm.data->cci)); + if (status < 0) + return status; + + rab = CCGX_RAB_UCSI_DATA_BLOCK(offsetof(struct ucsi_data, message_in)); + return ccg_read(uc, rab, ppm + offsetof(struct ucsi_data, message_in), + sizeof(uc->ppm.data->message_in)); +} + +static int ucsi_ccg_ack_interrupt(struct ucsi_ccg *uc) +{ + int status; + unsigned char data; + + status = ccg_read(uc, CCGX_RAB_INTR_REG, &data, sizeof(data)); + if (status < 0) + return status; + + return ccg_write(uc, CCGX_RAB_INTR_REG, &data, sizeof(data)); +} + +static int ucsi_ccg_sync(struct ucsi_ppm *ppm) +{ + struct ucsi_ccg *uc = container_of(ppm, struct ucsi_ccg, ppm); + int status; + + status = ucsi_ccg_recv_data(uc); + if (status < 0) + return status; + + /* ack interrupt to allow next command to run */ + return ucsi_ccg_ack_interrupt(uc); +} + +static int ucsi_ccg_cmd(struct ucsi_ppm *ppm, struct ucsi_control *ctrl) +{ + struct ucsi_ccg *uc = container_of(ppm, struct ucsi_ccg, ppm); + + ppm->data->ctrl.raw_cmd = ctrl->raw_cmd; + return ucsi_ccg_send_data(uc); +} + +static irqreturn_t ccg_irq_handler(int irq, void *data) +{ + struct ucsi_ccg *uc = data; + + ucsi_notify(uc->ucsi); + + return IRQ_HANDLED; +} + +static int ucsi_ccg_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct device *dev = &client->dev; + struct ucsi_ccg *uc; + int status; + u16 rab; + + uc = devm_kzalloc(dev, sizeof(*uc), GFP_KERNEL); + if (!uc) + return -ENOMEM; + + uc->ppm.data = devm_kzalloc(dev, sizeof(struct ucsi_data), GFP_KERNEL); + if (!uc->ppm.data) + return -ENOMEM; + + uc->ppm.cmd = ucsi_ccg_cmd; + uc->ppm.sync = ucsi_ccg_sync; + uc->dev = dev; + uc->client = client; + + /* reset ccg device and initialize ucsi */ + status = ucsi_ccg_init(uc); + if (status < 0) { + dev_err(uc->dev, "ucsi_ccg_init failed - %d\n", status); + return status; + } + + status = devm_request_threaded_irq(dev, client->irq, NULL, + ccg_irq_handler, + IRQF_ONESHOT | IRQF_TRIGGER_HIGH, + dev_name(dev), uc); + if (status < 0) { + dev_err(uc->dev, "request_threaded_irq failed - %d\n", status); + return status; + } + + uc->ucsi = ucsi_register_ppm(dev, &uc->ppm); + if (IS_ERR(uc->ucsi)) { + dev_err(uc->dev, "ucsi_register_ppm failed\n"); + return PTR_ERR(uc->ucsi); + } + + rab = CCGX_RAB_UCSI_DATA_BLOCK(offsetof(struct ucsi_data, version)); + status = ccg_read(uc, rab, (u8 *)(uc->ppm.data) + + offsetof(struct ucsi_data, version), + sizeof(uc->ppm.data->version)); + if (status < 0) { + ucsi_unregister_ppm(uc->ucsi); + return status; + } + + i2c_set_clientdata(client, uc); + return 0; +} + +static int ucsi_ccg_remove(struct i2c_client *client) +{ + struct ucsi_ccg *uc = i2c_get_clientdata(client); + + ucsi_unregister_ppm(uc->ucsi); + + return 0; +} + +static const struct i2c_device_id ucsi_ccg_device_id[] = { + {"ccgx-ucsi", 0}, + {} +}; +MODULE_DEVICE_TABLE(i2c, ucsi_ccg_device_id); + +static struct i2c_driver ucsi_ccg_driver = { + .driver = { + .name = "ucsi_ccg", + }, + .probe = ucsi_ccg_probe, + .remove = ucsi_ccg_remove, + .id_table = ucsi_ccg_device_id, +}; + +module_i2c_driver(ucsi_ccg_driver); + +MODULE_AUTHOR("Ajay Gupta "); +MODULE_DESCRIPTION("UCSI driver for Cypress CCGx Type-C controller"); +MODULE_LICENSE("GPL v2"); From 15035388439f892017d38b05214d3cda6578af64 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 9 Nov 2018 15:22:07 -0500 Subject: [PATCH 291/356] x86/cpu/vmware: Do not trace vmware_sched_clock() When running function tracing on a Linux guest running on VMware Workstation, the guest would crash. This is due to tracing of the sched_clock internal call of the VMware vmware_sched_clock(), which causes an infinite recursion within the tracing code (clock calls must not be traced). Make vmware_sched_clock() not traced by ftrace. Fixes: 80e9a4f21fd7c ("x86/vmware: Add paravirt sched clock") Reported-by: GwanYeong Kim Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Borislav Petkov CC: Alok Kataria CC: GwanYeong Kim CC: "H. Peter Anvin" CC: Ingo Molnar Cc: stable@vger.kernel.org CC: Thomas Gleixner CC: virtualization@lists.linux-foundation.org CC: x86-ml Link: http://lkml.kernel.org/r/20181109152207.4d3e7d70@gandalf.local.home --- arch/x86/kernel/cpu/vmware.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index d9ab49bed8af..0eda91f8eeac 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -77,7 +77,7 @@ static __init int setup_vmw_sched_clock(char *s) } early_param("no-vmw-sched-clock", setup_vmw_sched_clock); -static unsigned long long vmware_sched_clock(void) +static unsigned long long notrace vmware_sched_clock(void) { unsigned long long ns; From 1aefa98b010e9cc7a07046cbcb1237ddad85b708 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Fri, 9 Nov 2018 15:20:54 +0530 Subject: [PATCH 292/356] clk: qcom: gcc: Fix board clock node name Device tree node name are not supposed to have "_" in them so fix the node name use of xo_board to xo-board Fixes: 652f1813c113 ("clk: qcom: gcc: Add global clock controller driver for QCS404") Signed-off-by: Vinod Koul Signed-off-by: Stephen Boyd --- drivers/clk/qcom/gcc-qcs404.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/qcom/gcc-qcs404.c b/drivers/clk/qcom/gcc-qcs404.c index e4ca6a45f313..ef1b267cb058 100644 --- a/drivers/clk/qcom/gcc-qcs404.c +++ b/drivers/clk/qcom/gcc-qcs404.c @@ -265,7 +265,7 @@ static struct clk_fixed_factor cxo = { .div = 1, .hw.init = &(struct clk_init_data){ .name = "cxo", - .parent_names = (const char *[]){ "xo_board" }, + .parent_names = (const char *[]){ "xo-board" }, .num_parents = 1, .ops = &clk_fixed_factor_ops, }, From 35e8e8b45d31bec34379dd36e7b71448e003efb2 Mon Sep 17 00:00:00 2001 From: Igor Russkikh Date: Fri, 9 Nov 2018 11:53:56 +0000 Subject: [PATCH 293/356] net: aquantia: synchronized flow control between mac/phy Flow control statuses were not synchronized between blocks, that caused packets/link drop on some corner cases, when MAC sent PFC although Phy was not expecting these to come. Driver should readout the negotiated FC from phy and configure RX block accordigly. This is done on each link change event with information from FW. Fixes: 288551de45aa ("net: aquantia: Implement rx/tx flow control ethtools callback") Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- .../ethernet/aquantia/atlantic/aq_ethtool.c | 8 +++---- .../net/ethernet/aquantia/atlantic/aq_hw.h | 3 +++ .../net/ethernet/aquantia/atlantic/aq_nic.c | 14 ++++++++++++- .../aquantia/atlantic/hw_atl/hw_atl_b0.c | 12 ++++++++--- .../atlantic/hw_atl/hw_atl_utils_fw2x.c | 21 +++++++++++++++++++ 5 files changed, 50 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c index 6a633c70f603..99ef1daaa4d8 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c @@ -407,13 +407,13 @@ static void aq_ethtool_get_pauseparam(struct net_device *ndev, struct ethtool_pauseparam *pause) { struct aq_nic_s *aq_nic = netdev_priv(ndev); + u32 fc = aq_nic->aq_nic_cfg.flow_control; pause->autoneg = 0; - if (aq_nic->aq_hw->aq_nic_cfg->flow_control & AQ_NIC_FC_RX) - pause->rx_pause = 1; - if (aq_nic->aq_hw->aq_nic_cfg->flow_control & AQ_NIC_FC_TX) - pause->tx_pause = 1; + pause->rx_pause = !!(fc & AQ_NIC_FC_RX); + pause->tx_pause = !!(fc & AQ_NIC_FC_TX); + } static int aq_ethtool_set_pauseparam(struct net_device *ndev, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h index e8689241204e..7ec8d24b2b0b 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h @@ -204,6 +204,7 @@ struct aq_hw_ops { int (*hw_get_fw_version)(struct aq_hw_s *self, u32 *fw_version); + int (*hw_set_fc)(struct aq_hw_s *self, u32 fc, u32 tc); }; struct aq_fw_ops { @@ -226,6 +227,8 @@ struct aq_fw_ops { int (*update_stats)(struct aq_hw_s *self); + u32 (*get_flow_control)(struct aq_hw_s *self, u32 *fcmode); + int (*set_flow_control)(struct aq_hw_s *self); int (*set_power)(struct aq_hw_s *self, unsigned int power_state, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 5fed24446687..0011a3f2f672 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -124,6 +124,7 @@ void aq_nic_cfg_start(struct aq_nic_s *self) static int aq_nic_update_link_status(struct aq_nic_s *self) { int err = self->aq_fw_ops->update_link_status(self->aq_hw); + u32 fc = 0; if (err) return err; @@ -133,6 +134,15 @@ static int aq_nic_update_link_status(struct aq_nic_s *self) AQ_CFG_DRV_NAME, self->link_status.mbps, self->aq_hw->aq_link_status.mbps); aq_nic_update_interrupt_moderation_settings(self); + + /* Driver has to update flow control settings on RX block + * on any link event. + * We should query FW whether it negotiated FC. + */ + if (self->aq_fw_ops->get_flow_control) + self->aq_fw_ops->get_flow_control(self->aq_hw, &fc); + if (self->aq_hw_ops->hw_set_fc) + self->aq_hw_ops->hw_set_fc(self->aq_hw, fc, 0); } self->link_status = self->aq_hw->aq_link_status; @@ -772,7 +782,9 @@ void aq_nic_get_link_ksettings(struct aq_nic_s *self, ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause); - if (self->aq_nic_cfg.flow_control & AQ_NIC_FC_TX) + /* Asym is when either RX or TX, but not both */ + if (!!(self->aq_nic_cfg.flow_control & AQ_NIC_FC_TX) ^ + !!(self->aq_nic_cfg.flow_control & AQ_NIC_FC_RX)) ethtool_link_ksettings_add_link_mode(cmd, advertising, Asym_Pause); diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index 76d25d594a0f..119265762b0c 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -100,12 +100,17 @@ static int hw_atl_b0_hw_reset(struct aq_hw_s *self) return err; } +static int hw_atl_b0_set_fc(struct aq_hw_s *self, u32 fc, u32 tc) +{ + hw_atl_rpb_rx_xoff_en_per_tc_set(self, !!(fc & AQ_NIC_FC_RX), tc); + return 0; +} + static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self) { u32 tc = 0U; u32 buff_size = 0U; unsigned int i_priority = 0U; - bool is_rx_flow_control = false; /* TPS Descriptor rate init */ hw_atl_tps_tx_pkt_shed_desc_rate_curr_time_res_set(self, 0x0U); @@ -138,7 +143,6 @@ static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self) /* QoS Rx buf size per TC */ tc = 0; - is_rx_flow_control = (AQ_NIC_FC_RX & self->aq_nic_cfg->flow_control); buff_size = HW_ATL_B0_RXBUF_MAX; hw_atl_rpb_rx_pkt_buff_size_per_tc_set(self, buff_size, tc); @@ -150,7 +154,8 @@ static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self) (buff_size * (1024U / 32U) * 50U) / 100U, tc); - hw_atl_rpb_rx_xoff_en_per_tc_set(self, is_rx_flow_control ? 1U : 0U, tc); + + hw_atl_b0_set_fc(self, self->aq_nic_cfg->flow_control, tc); /* QoS 802.1p priority -> TC mapping */ for (i_priority = 8U; i_priority--;) @@ -963,4 +968,5 @@ const struct aq_hw_ops hw_atl_ops_b0 = { .hw_get_regs = hw_atl_utils_hw_get_regs, .hw_get_hw_stats = hw_atl_utils_get_hw_stats, .hw_get_fw_version = hw_atl_utils_get_fw_version, + .hw_set_fc = hw_atl_b0_set_fc, }; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c index 096ca5730887..7de3220d9cab 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c @@ -30,6 +30,8 @@ #define HW_ATL_FW2X_MPI_STATE_ADDR 0x370 #define HW_ATL_FW2X_MPI_STATE2_ADDR 0x374 +#define HW_ATL_FW2X_CAP_PAUSE BIT(CAPS_HI_PAUSE) +#define HW_ATL_FW2X_CAP_ASYM_PAUSE BIT(CAPS_HI_ASYMMETRIC_PAUSE) #define HW_ATL_FW2X_CAP_SLEEP_PROXY BIT(CAPS_HI_SLEEP_PROXY) #define HW_ATL_FW2X_CAP_WOL BIT(CAPS_HI_WOL) @@ -451,6 +453,24 @@ static int aq_fw2x_set_flow_control(struct aq_hw_s *self) return 0; } +static u32 aq_fw2x_get_flow_control(struct aq_hw_s *self, u32 *fcmode) +{ + u32 mpi_state = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_STATE2_ADDR); + + if (mpi_state & HW_ATL_FW2X_CAP_PAUSE) + if (mpi_state & HW_ATL_FW2X_CAP_ASYM_PAUSE) + *fcmode = AQ_NIC_FC_RX; + else + *fcmode = AQ_NIC_FC_RX | AQ_NIC_FC_TX; + else + if (mpi_state & HW_ATL_FW2X_CAP_ASYM_PAUSE) + *fcmode = AQ_NIC_FC_TX; + else + *fcmode = 0; + + return 0; +} + const struct aq_fw_ops aq_fw_2x_ops = { .init = aq_fw2x_init, .deinit = aq_fw2x_deinit, @@ -465,4 +485,5 @@ const struct aq_fw_ops aq_fw_2x_ops = { .set_eee_rate = aq_fw2x_set_eee_rate, .get_eee_rate = aq_fw2x_get_eee_rate, .set_flow_control = aq_fw2x_set_flow_control, + .get_flow_control = aq_fw2x_get_flow_control }; From 7a1bb49461b12b2e6332a4d054256835f45203f3 Mon Sep 17 00:00:00 2001 From: Dmitry Bogdanov Date: Fri, 9 Nov 2018 11:53:57 +0000 Subject: [PATCH 294/356] net: aquantia: fix potential IOMMU fault after driver unbind IOMMU fault may occurr on unbind/bind or if_down/if_up sequence. Although driver disables the rings on down, this is not enough. Due to internal HW design, during subsequent initialization NIC sometimes may reuse RX descriptors cache and write to the host memory from the descriptor cache. That's get catched by IOMMU on host. This patch invalidates the descriptor cache in NIC on interface down to prevent writing to the cached descriptors and to the memory pointed in those descriptors. Signed-off-by: Dmitry Bogdanov Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- .../aquantia/atlantic/hw_atl/hw_atl_b0.c | 6 ++++++ .../aquantia/atlantic/hw_atl/hw_atl_llh.c | 8 ++++++++ .../aquantia/atlantic/hw_atl/hw_atl_llh.h | 3 +++ .../atlantic/hw_atl/hw_atl_llh_internal.h | 18 ++++++++++++++++++ 4 files changed, 35 insertions(+) diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index 119265762b0c..3aec56623bf5 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -920,6 +920,12 @@ static int hw_atl_b0_hw_interrupt_moderation_set(struct aq_hw_s *self) static int hw_atl_b0_hw_stop(struct aq_hw_s *self) { hw_atl_b0_hw_irq_disable(self, HW_ATL_B0_INT_MASK); + + /* Invalidate Descriptor Cache to prevent writing to the cached + * descriptors and to the data pointer of those descriptors + */ + hw_atl_rdm_rx_dma_desc_cache_init_set(self, 1); + return aq_hw_err_from_flags(self); } diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c index be0a3a90dfad..5502ec5f0f69 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c @@ -619,6 +619,14 @@ void hw_atl_rpb_rx_flow_ctl_mode_set(struct aq_hw_s *aq_hw, u32 rx_flow_ctl_mode HW_ATL_RPB_RX_FC_MODE_SHIFT, rx_flow_ctl_mode); } +void hw_atl_rdm_rx_dma_desc_cache_init_set(struct aq_hw_s *aq_hw, u32 init) +{ + aq_hw_write_reg_bit(aq_hw, HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_ADR, + HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_MSK, + HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_SHIFT, + init); +} + void hw_atl_rpb_rx_pkt_buff_size_per_tc_set(struct aq_hw_s *aq_hw, u32 rx_pkt_buff_size_per_tc, u32 buffer) { diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h index 7056c7342afc..41f239928c15 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h @@ -325,6 +325,9 @@ void hw_atl_rpb_rx_pkt_buff_size_per_tc_set(struct aq_hw_s *aq_hw, u32 rx_pkt_buff_size_per_tc, u32 buffer); +/* set rdm rx dma descriptor cache init */ +void hw_atl_rdm_rx_dma_desc_cache_init_set(struct aq_hw_s *aq_hw, u32 init); + /* set rx xoff enable (per tc) */ void hw_atl_rpb_rx_xoff_en_per_tc_set(struct aq_hw_s *aq_hw, u32 rx_xoff_en_per_tc, u32 buffer); diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h index 716674a9b729..a715fa317b1c 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h @@ -293,6 +293,24 @@ /* default value of bitfield desc{d}_reset */ #define HW_ATL_RDM_DESCDRESET_DEFAULT 0x0 +/* rdm_desc_init_i bitfield definitions + * preprocessor definitions for the bitfield rdm_desc_init_i. + * port="pif_rdm_desc_init_i" + */ + +/* register address for bitfield rdm_desc_init_i */ +#define HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_ADR 0x00005a00 +/* bitmask for bitfield rdm_desc_init_i */ +#define HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_MSK 0xffffffff +/* inverted bitmask for bitfield rdm_desc_init_i */ +#define HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_MSKN 0x00000000 +/* lower bit position of bitfield rdm_desc_init_i */ +#define HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_SHIFT 0 +/* width of bitfield rdm_desc_init_i */ +#define HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_WIDTH 32 +/* default value of bitfield rdm_desc_init_i */ +#define HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_DEFAULT 0x0 + /* rx int_desc_wrb_en bitfield definitions * preprocessor definitions for the bitfield "int_desc_wrb_en". * port="pif_rdm_int_desc_wrb_en_i" From bfaa9f8553d5c20703781e63f4fc8cb4792f18fd Mon Sep 17 00:00:00 2001 From: Igor Russkikh Date: Fri, 9 Nov 2018 11:53:59 +0000 Subject: [PATCH 295/356] net: aquantia: fixed enable unicast on 32 macvlan Fixed a condition mistake due to which macvlans unicast item number 32 was not added in the unicast filter. The consequence is that when exactly 32 macvlans are created on NIC, the last created macvlan receives no traffic because its MAC was not registered in HW. Fixes: 94b3b542303f ("net: aquantia: vlan unicast address list correct handling") Signed-off-by: Igor Russkikh Tested-by: Nikita Danilov Signed-off-by: David S. Miller --- drivers/net/ethernet/aquantia/atlantic/aq_nic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 0011a3f2f672..b5e7c98f424c 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -600,7 +600,7 @@ int aq_nic_set_multicast_list(struct aq_nic_s *self, struct net_device *ndev) } } - if (i > 0 && i < AQ_HW_MULTICAST_ADDRESS_MAX) { + if (i > 0 && i <= AQ_HW_MULTICAST_ADDRESS_MAX) { packet_filter |= IFF_MULTICAST; self->mc_list.count = i; self->aq_hw_ops->hw_multicast_list_set(self->aq_hw, From ad703c2b9127f9acdef697ec4755f6da4beaa266 Mon Sep 17 00:00:00 2001 From: Dmitry Bogdanov Date: Fri, 9 Nov 2018 11:54:01 +0000 Subject: [PATCH 296/356] net: aquantia: invalid checksumm offload implementation Packets with marked invalid IP/UDP/TCP checksums were considered as good by the driver. The error was in a logic, processing offload bits in RX descriptor. Signed-off-by: Igor Russkikh Signed-off-by: Dmitry Bogdanov Signed-off-by: David S. Miller --- .../net/ethernet/aquantia/atlantic/aq_ring.c | 35 +++++++++++------- .../aquantia/atlantic/hw_atl/hw_atl_b0.c | 36 +++++++++---------- 2 files changed, 41 insertions(+), 30 deletions(-) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 3db91446cc67..74550ccc7a20 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -172,6 +172,27 @@ bool aq_ring_tx_clean(struct aq_ring_s *self) return !!budget; } +static void aq_rx_checksum(struct aq_ring_s *self, + struct aq_ring_buff_s *buff, + struct sk_buff *skb) +{ + if (!(self->aq_nic->ndev->features & NETIF_F_RXCSUM)) + return; + + if (unlikely(buff->is_cso_err)) { + ++self->stats.rx.errors; + skb->ip_summed = CHECKSUM_NONE; + return; + } + if (buff->is_ip_cso) { + __skb_incr_checksum_unnecessary(skb); + if (buff->is_udp_cso || buff->is_tcp_cso) + __skb_incr_checksum_unnecessary(skb); + } else { + skb->ip_summed = CHECKSUM_NONE; + } +} + #define AQ_SKB_ALIGN SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) int aq_ring_rx_clean(struct aq_ring_s *self, struct napi_struct *napi, @@ -267,18 +288,8 @@ int aq_ring_rx_clean(struct aq_ring_s *self, } skb->protocol = eth_type_trans(skb, ndev); - if (unlikely(buff->is_cso_err)) { - ++self->stats.rx.errors; - skb->ip_summed = CHECKSUM_NONE; - } else { - if (buff->is_ip_cso) { - __skb_incr_checksum_unnecessary(skb); - if (buff->is_udp_cso || buff->is_tcp_cso) - __skb_incr_checksum_unnecessary(skb); - } else { - skb->ip_summed = CHECKSUM_NONE; - } - } + + aq_rx_checksum(self, buff, skb); skb_set_hash(skb, buff->rss_hash, buff->is_hash_l4 ? PKT_HASH_TYPE_L4 : diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index 3aec56623bf5..179ce12fe4d8 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -660,9 +660,9 @@ static int hw_atl_b0_hw_ring_rx_receive(struct aq_hw_s *self, struct hw_atl_rxd_wb_s *rxd_wb = (struct hw_atl_rxd_wb_s *) &ring->dx_ring[ring->hw_head * HW_ATL_B0_RXD_SIZE]; - unsigned int is_err = 1U; unsigned int is_rx_check_sum_enabled = 0U; unsigned int pkt_type = 0U; + u8 rx_stat = 0U; if (!(rxd_wb->status & 0x1U)) { /* RxD is not done */ break; @@ -670,35 +670,35 @@ static int hw_atl_b0_hw_ring_rx_receive(struct aq_hw_s *self, buff = &ring->buff_ring[ring->hw_head]; - is_err = (0x0000003CU & rxd_wb->status); + rx_stat = (0x0000003CU & rxd_wb->status) >> 2; is_rx_check_sum_enabled = (rxd_wb->type) & (0x3U << 19); - is_err &= ~0x20U; /* exclude validity bit */ pkt_type = 0xFFU & (rxd_wb->type >> 4); - if (is_rx_check_sum_enabled) { - if (0x0U == (pkt_type & 0x3U)) - buff->is_ip_cso = (is_err & 0x08U) ? 0U : 1U; + if (is_rx_check_sum_enabled & BIT(0) && + (0x0U == (pkt_type & 0x3U))) + buff->is_ip_cso = (rx_stat & BIT(1)) ? 0U : 1U; + if (is_rx_check_sum_enabled & BIT(1)) { if (0x4U == (pkt_type & 0x1CU)) - buff->is_udp_cso = buff->is_cso_err ? 0U : 1U; + buff->is_udp_cso = (rx_stat & BIT(2)) ? 0U : + !!(rx_stat & BIT(3)); else if (0x0U == (pkt_type & 0x1CU)) - buff->is_tcp_cso = buff->is_cso_err ? 0U : 1U; - - /* Checksum offload workaround for small packets */ - if (rxd_wb->pkt_len <= 60) { - buff->is_ip_cso = 0U; - buff->is_cso_err = 0U; - } + buff->is_tcp_cso = (rx_stat & BIT(2)) ? 0U : + !!(rx_stat & BIT(3)); + } + buff->is_cso_err = !!(rx_stat & 0x6); + /* Checksum offload workaround for small packets */ + if (unlikely(rxd_wb->pkt_len <= 60)) { + buff->is_ip_cso = 0U; + buff->is_cso_err = 0U; } - - is_err &= ~0x18U; dma_unmap_page(ndev, buff->pa, buff->len, DMA_FROM_DEVICE); - if (is_err || rxd_wb->type & 0x1000U) { - /* status error or DMA error */ + if ((rx_stat & BIT(0)) || rxd_wb->type & 0x1000U) { + /* MAC error or DMA error */ buff->is_error = 1U; } else { if (self->aq_nic_cfg->is_rss) { From bbb67a44baf973da734b9fd61cba4211da240751 Mon Sep 17 00:00:00 2001 From: Dmitry Bogdanov Date: Fri, 9 Nov 2018 11:54:03 +0000 Subject: [PATCH 297/356] net: aquantia: allow rx checksum offload configuration RX Checksum offloads could not be configured and ignored netdev features flag for checksumming. Signed-off-by: Igor Russkikh Signed-off-by: Dmitry Bogdanov Signed-off-by: David S. Miller --- drivers/net/ethernet/aquantia/atlantic/aq_hw.h | 3 +++ drivers/net/ethernet/aquantia/atlantic/aq_main.c | 10 ++++++++-- drivers/net/ethernet/aquantia/atlantic/aq_nic.c | 2 +- drivers/net/ethernet/aquantia/atlantic/aq_nic.h | 2 +- .../net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c | 7 +++++-- 5 files changed, 18 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h index 7ec8d24b2b0b..a1e70da358ca 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h @@ -204,6 +204,9 @@ struct aq_hw_ops { int (*hw_get_fw_version)(struct aq_hw_s *self, u32 *fw_version); + int (*hw_set_offload)(struct aq_hw_s *self, + struct aq_nic_cfg_s *aq_nic_cfg); + int (*hw_set_fc)(struct aq_hw_s *self, u32 fc, u32 tc); }; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c index e3ae29e523f0..7c07eef275eb 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c @@ -99,8 +99,11 @@ static int aq_ndev_set_features(struct net_device *ndev, struct aq_nic_s *aq_nic = netdev_priv(ndev); struct aq_nic_cfg_s *aq_cfg = aq_nic_get_cfg(aq_nic); bool is_lro = false; + int err = 0; - if (aq_cfg->hw_features & NETIF_F_LRO) { + aq_cfg->features = features; + + if (aq_cfg->aq_hw_caps->hw_features & NETIF_F_LRO) { is_lro = features & NETIF_F_LRO; if (aq_cfg->is_lro != is_lro) { @@ -112,8 +115,11 @@ static int aq_ndev_set_features(struct net_device *ndev, } } } + if ((aq_nic->ndev->features ^ features) & NETIF_F_RXCSUM) + err = aq_nic->aq_hw_ops->hw_set_offload(aq_nic->aq_hw, + aq_cfg); - return 0; + return err; } static int aq_ndev_set_mac_address(struct net_device *ndev, void *addr) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index b5e7c98f424c..7abdc0952425 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -118,7 +118,7 @@ void aq_nic_cfg_start(struct aq_nic_s *self) } cfg->link_speed_msk &= cfg->aq_hw_caps->link_speed_msk; - cfg->hw_features = cfg->aq_hw_caps->hw_features; + cfg->features = cfg->aq_hw_caps->hw_features; } static int aq_nic_update_link_status(struct aq_nic_s *self) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h index c1582f4e8e1b..44ec47a3d60a 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h @@ -23,7 +23,7 @@ struct aq_vec_s; struct aq_nic_cfg_s { const struct aq_hw_caps_s *aq_hw_caps; - u64 hw_features; + u64 features; u32 rxds; /* rx ring size, descriptors # */ u32 txds; /* tx ring size, descriptors # */ u32 vecs; /* vecs==allocated irqs */ diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index 179ce12fe4d8..f02592f43fe3 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -234,8 +234,10 @@ static int hw_atl_b0_hw_offload_set(struct aq_hw_s *self, hw_atl_tpo_tcp_udp_crc_offload_en_set(self, 1); /* RX checksums offloads*/ - hw_atl_rpo_ipv4header_crc_offload_en_set(self, 1); - hw_atl_rpo_tcp_udp_crc_offload_en_set(self, 1); + hw_atl_rpo_ipv4header_crc_offload_en_set(self, !!(aq_nic_cfg->features & + NETIF_F_RXCSUM)); + hw_atl_rpo_tcp_udp_crc_offload_en_set(self, !!(aq_nic_cfg->features & + NETIF_F_RXCSUM)); /* LSO offloads*/ hw_atl_tdm_large_send_offload_en_set(self, 0xFFFFFFFFU); @@ -974,5 +976,6 @@ const struct aq_hw_ops hw_atl_ops_b0 = { .hw_get_regs = hw_atl_utils_hw_get_regs, .hw_get_hw_stats = hw_atl_utils_get_hw_stats, .hw_get_fw_version = hw_atl_utils_get_fw_version, + .hw_set_offload = hw_atl_b0_hw_offload_set, .hw_set_fc = hw_atl_b0_set_fc, }; From d02854dc1999ed3e7fd79ec700c64ac23ac0c458 Mon Sep 17 00:00:00 2001 From: Subash Abhinov Kasiviswanathan Date: Fri, 9 Nov 2018 18:56:27 -0700 Subject: [PATCH 298/356] net: qualcomm: rmnet: Fix incorrect assignment of real_dev A null dereference was observed when a sysctl was being set from userspace and rmnet was stuck trying to complete some actions in the NETDEV_REGISTER callback. This is because the real_dev is set only after the device registration handler completes. sysctl call stack - <6> Unable to handle kernel NULL pointer dereference at virtual address 00000108 <2> pc : rmnet_vnd_get_iflink+0x1c/0x28 <2> lr : dev_get_iflink+0x2c/0x40 <2> rmnet_vnd_get_iflink+0x1c/0x28 <2> inet6_fill_ifinfo+0x15c/0x234 <2> inet6_ifinfo_notify+0x68/0xd4 <2> ndisc_ifinfo_sysctl_change+0x1b8/0x234 <2> proc_sys_call_handler+0xac/0x100 <2> proc_sys_write+0x3c/0x4c <2> __vfs_write+0x54/0x14c <2> vfs_write+0xcc/0x188 <2> SyS_write+0x60/0xc0 <2> el0_svc_naked+0x34/0x38 device register call stack - <2> notifier_call_chain+0x84/0xbc <2> raw_notifier_call_chain+0x38/0x48 <2> call_netdevice_notifiers_info+0x40/0x70 <2> call_netdevice_notifiers+0x38/0x60 <2> register_netdevice+0x29c/0x3d8 <2> rmnet_vnd_newlink+0x68/0xe8 <2> rmnet_newlink+0xa0/0x160 <2> rtnl_newlink+0x57c/0x6c8 <2> rtnetlink_rcv_msg+0x1dc/0x328 <2> netlink_rcv_skb+0xac/0x118 <2> rtnetlink_rcv+0x24/0x30 <2> netlink_unicast+0x158/0x1f0 <2> netlink_sendmsg+0x32c/0x338 <2> sock_sendmsg+0x44/0x60 <2> SyS_sendto+0x150/0x1ac <2> el0_svc_naked+0x34/0x38 Fixes: b752eff5be24 ("net: qualcomm: rmnet: Implement ndo_get_iflink") Signed-off-by: Sean Tranchetti Signed-off-by: Subash Abhinov Kasiviswanathan Signed-off-by: David S. Miller --- drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c index 0afc3d335d56..d11c16aeb19a 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c @@ -234,7 +234,7 @@ int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev, struct net_device *real_dev, struct rmnet_endpoint *ep) { - struct rmnet_priv *priv; + struct rmnet_priv *priv = netdev_priv(rmnet_dev); int rc; if (ep->egress_dev) @@ -247,6 +247,8 @@ int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev, rmnet_dev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; rmnet_dev->hw_features |= NETIF_F_SG; + priv->real_dev = real_dev; + rc = register_netdevice(rmnet_dev); if (!rc) { ep->egress_dev = rmnet_dev; @@ -255,9 +257,7 @@ int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev, rmnet_dev->rtnl_link_ops = &rmnet_link_ops; - priv = netdev_priv(rmnet_dev); priv->mux_id = id; - priv->real_dev = real_dev; netdev_dbg(rmnet_dev, "rmnet dev created\n"); } From 62230715fd2453b3ba948c9d83cfb3ada9169169 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=EB=B0=B0=EC=84=9D=EC=A7=84?= Date: Fri, 9 Nov 2018 16:53:06 -0800 Subject: [PATCH 299/356] flow_dissector: do not dissect l4 ports for fragments MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Only first fragment has the sport/dport information, not the following ones. If we want consistent hash for all fragments, we need to ignore ports even for first fragment. This bug is visible for IPv6 traffic, if incoming fragments do not have a flow label, since skb_get_hash() will give different results for first fragment and following ones. It is also visible if any routing rule wants dissection and sport or dport. See commit 5e5d6fed3741 ("ipv6: route: dissect flow in input path if fib rules need it") for details. [edumazet] rewrote the changelog completely. Fixes: 06635a35d13d ("flow_dissect: use programable dissector in skb_flow_dissect and friends") Signed-off-by: 배석진 Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/flow_dissector.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 676f3ad629f9..588f475019d4 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1166,8 +1166,8 @@ ip_proto_again: break; } - if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_PORTS)) { + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS) && + !(key_control->flags & FLOW_DIS_IS_FRAGMENT)) { key_ports = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS, target_container); From fbd1d5245372e48b494120a30fe0b34b304576c4 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Fri, 9 Nov 2018 17:37:20 +0100 Subject: [PATCH 300/356] net: mvneta: correct typo The reserved variable should be named reserved1. Signed-off-by: Alexandre Belloni Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvneta.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 5bfd349bf41a..3ba672e9e353 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -494,7 +494,7 @@ struct mvneta_port { #if defined(__LITTLE_ENDIAN) struct mvneta_tx_desc { u32 command; /* Options used by HW for packet transmitting.*/ - u16 reserverd1; /* csum_l4 (for future use) */ + u16 reserved1; /* csum_l4 (for future use) */ u16 data_size; /* Data size of transmitted packet in bytes */ u32 buf_phys_addr; /* Physical addr of transmitted buffer */ u32 reserved2; /* hw_cmd - (for future use, PMT) */ @@ -519,7 +519,7 @@ struct mvneta_rx_desc { #else struct mvneta_tx_desc { u16 data_size; /* Data size of transmitted packet in bytes */ - u16 reserverd1; /* csum_l4 (for future use) */ + u16 reserved1; /* csum_l4 (for future use) */ u32 command; /* Options used by HW for packet transmitting.*/ u32 reserved2; /* hw_cmd - (for future use, PMT) */ u32 buf_phys_addr; /* Physical addr of transmitted buffer */ From 63c82997f5c0f3e1b914af43d82f712a86bc5f3a Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 9 Nov 2018 21:06:26 -0800 Subject: [PATCH 301/356] net: sched: cls_flower: validate nested enc_opts_policy to avoid warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit TCA_FLOWER_KEY_ENC_OPTS and TCA_FLOWER_KEY_ENC_OPTS_MASK can only currently contain further nested attributes, which are parsed by hand, so the policy is never actually used resulting in a W=1 build warning: net/sched/cls_flower.c:492:1: warning: ‘enc_opts_policy’ defined but not used [-Wunused-const-variable=] enc_opts_policy[TCA_FLOWER_KEY_ENC_OPTS_MAX + 1] = { Add the validation anyway to avoid potential bugs when other attributes are added and to make the attribute structure slightly more clear. Validation will also set extact to point to bad attribute on error. Fixes: 0a6e77784f49 ("net/sched: allow flower to match tunnel options") Signed-off-by: Jakub Kicinski Acked-by: Simon Horman Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- net/sched/cls_flower.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 9aada2d0ef06..c6c327874abc 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -709,11 +709,23 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, struct netlink_ext_ack *extack) { const struct nlattr *nla_enc_key, *nla_opt_key, *nla_opt_msk = NULL; - int option_len, key_depth, msk_depth = 0; + int err, option_len, key_depth, msk_depth = 0; + + err = nla_validate_nested(tb[TCA_FLOWER_KEY_ENC_OPTS], + TCA_FLOWER_KEY_ENC_OPTS_MAX, + enc_opts_policy, extack); + if (err) + return err; nla_enc_key = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS]); if (tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]) { + err = nla_validate_nested(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK], + TCA_FLOWER_KEY_ENC_OPTS_MAX, + enc_opts_policy, extack); + if (err) + return err; + nla_opt_msk = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]); msk_depth = nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]); } From 6bbe4385d035c6fac56f840a59861a0310ce137b Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 5 Nov 2018 17:19:36 +0900 Subject: [PATCH 302/356] kconfig: merge_config: avoid false positive matches from comment lines The current SED_CONFIG_EXP could match to comment lines in config fragment files, especially when CONFIG_PREFIX_ is empty. For example, Buildroot uses empty prefixing; starting symbols with BR2_ is just convention. Make the sed expression more robust against false positives from comment lines. The new sed expression matches to only valid patterns. Signed-off-by: Masahiro Yamada Reviewed-by: Petr Vorel Reviewed-by: Arnout Vandecappelle (Essensium/Mind) --- scripts/kconfig/merge_config.sh | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/scripts/kconfig/merge_config.sh b/scripts/kconfig/merge_config.sh index da66e7742282..0ef906499646 100755 --- a/scripts/kconfig/merge_config.sh +++ b/scripts/kconfig/merge_config.sh @@ -102,7 +102,8 @@ if [ ! -r "$INITFILE" ]; then fi MERGE_LIST=$* -SED_CONFIG_EXP="s/^\(# \)\{0,1\}\(${CONFIG_PREFIX}[a-zA-Z0-9_]*\)[= ].*/\2/p" +SED_CONFIG_EXP1="s/^\(${CONFIG_PREFIX}[a-zA-Z0-9_]*\)=.*/\1/p" +SED_CONFIG_EXP2="s/^# \(${CONFIG_PREFIX}[a-zA-Z0-9_]*\) is not set$/\1/p" TMP_FILE=$(mktemp ./.tmp.config.XXXXXXXXXX) @@ -116,7 +117,7 @@ for MERGE_FILE in $MERGE_LIST ; do echo "The merge file '$MERGE_FILE' does not exist. Exit." >&2 exit 1 fi - CFG_LIST=$(sed -n "$SED_CONFIG_EXP" $MERGE_FILE) + CFG_LIST=$(sed -n -e "$SED_CONFIG_EXP1" -e "$SED_CONFIG_EXP2" $MERGE_FILE) for CFG in $CFG_LIST ; do grep -q -w $CFG $TMP_FILE || continue @@ -159,7 +160,7 @@ make KCONFIG_ALLCONFIG=$TMP_FILE $OUTPUT_ARG $ALLTARGET # Check all specified config values took (might have missed-dependency issues) -for CFG in $(sed -n "$SED_CONFIG_EXP" $TMP_FILE); do +for CFG in $(sed -n -e "$SED_CONFIG_EXP1" -e "$SED_CONFIG_EXP2" $TMP_FILE); do REQUESTED_VAL=$(grep -w -e "$CFG" $TMP_FILE) ACTUAL_VAL=$(grep -w -e "$CFG" "$KCONFIG_CONFIG") From bbcde0a7241261cd0ca8d8e6b94a4113a4b71443 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 6 Nov 2018 13:18:05 +0900 Subject: [PATCH 303/356] kbuild: deb-pkg: fix too low build version number Since commit b41d920acff8 ("kbuild: deb-pkg: split generating packaging and build"), the build version of the kernel contained in a deb package is too low by 1. Prior to the bad commit, the kernel was built first, then the number in .version file was read out, and written into the debian control file. Now, the debian control file is created before the kernel is actually compiled, which is causing the version number mismatch. Let the mkdebian script pass KBUILD_BUILD_VERSION=${revision} to require the build system to use the specified version number. Fixes: b41d920acff8 ("kbuild: deb-pkg: split generating packaging and build") Reported-by: Doug Smythies Signed-off-by: Masahiro Yamada Tested-by: Doug Smythies --- scripts/package/mkdebian | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian index 663a7f343b42..edcad61fe3cd 100755 --- a/scripts/package/mkdebian +++ b/scripts/package/mkdebian @@ -88,6 +88,7 @@ set_debarch() { version=$KERNELRELEASE if [ -n "$KDEB_PKGVERSION" ]; then packageversion=$KDEB_PKGVERSION + revision=${packageversion##*-} else revision=$(cat .version 2>/dev/null||echo 1) packageversion=$version-$revision @@ -205,10 +206,12 @@ cat < debian/rules #!$(command -v $MAKE) -f build: - \$(MAKE) KERNELRELEASE=${version} ARCH=${ARCH} KBUILD_SRC= + \$(MAKE) KERNELRELEASE=${version} ARCH=${ARCH} \ + KBUILD_BUILD_VERSION=${revision} KBUILD_SRC= binary-arch: - \$(MAKE) KERNELRELEASE=${version} ARCH=${ARCH} KBUILD_SRC= intdeb-pkg + \$(MAKE) KERNELRELEASE=${version} ARCH=${ARCH} \ + KBUILD_BUILD_VERSION=${revision} KBUILD_SRC= intdeb-pkg clean: rm -rf debian/*tmp debian/files From 8ef14c2c41d962756d314f1d7dc972b0ea7a180f Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Tue, 6 Nov 2018 10:10:38 -0800 Subject: [PATCH 304/356] Revert "scripts/setlocalversion: git: Make -dirty check more robust" This reverts commit 6147b1cf19651c7de297e69108b141fb30aa2349. The reverted patch results in attempted write access to the source repository, even if that repository is mounted read-only. Output from "strace git status -uno --porcelain": getcwd("/tmp/linux-test", 129) = 16 open("/tmp/linux-test/.git/index.lock", O_RDWR|O_CREAT|O_EXCL|O_CLOEXEC, 0666) = -1 EROFS (Read-only file system) While git appears to be able to handle this situation, a monitored build environment (such as the one used for Chrome OS kernel builds) may detect it and bail out with an access violation error. On top of that, the attempted write access suggests that git _will_ write to the file even if a build output directory is specified. Users may have the reasonable expectation that the source repository remains untouched in that situation. Fixes: 6147b1cf19651 ("scripts/setlocalversion: git: Make -dirty check more robust" Cc: Genki Sky Signed-off-by: Guenter Roeck Reviewed-by: Brian Norris Signed-off-by: Masahiro Yamada --- scripts/setlocalversion | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/setlocalversion b/scripts/setlocalversion index 79f7dd57d571..71f39410691b 100755 --- a/scripts/setlocalversion +++ b/scripts/setlocalversion @@ -74,7 +74,7 @@ scm_version() fi # Check for uncommitted changes - if git status -uno --porcelain | grep -qv '^.. scripts/package'; then + if git diff-index --name-only HEAD | grep -qv "^scripts/package"; then printf '%s' -dirty fi From d5615e472d23e854e96192103b6ae7977e705f01 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 7 Nov 2018 08:36:46 -0600 Subject: [PATCH 305/356] builddeb: Fix inclusion of dtbs in debian package MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 37c8a5fafa3b ("kbuild: consolidate Devicetree dtb build rules") moved the location of 'dtbs_install' target which caused dtbs to not be installed when building debian package with 'bindeb-pkg' target. Update the builddeb script to use the same logic that determines if there's a 'dtbs_install' target which is presence of the arch dts directory. Also, use CONFIG_OF_EARLY_FLATTREE instead of CONFIG_OF as that's a better indication of whether we are building dtbs. This commit will also have the side effect of installing dtbs on any arch that has dts files. Previously, it was dependent on whether the arch defined 'dtbs_install'. Fixes: 37c8a5fafa3b ("kbuild: consolidate Devicetree dtb build rules") Reported-by: Nuno Gonçalves Signed-off-by: Rob Herring Signed-off-by: Masahiro Yamada --- scripts/package/builddeb | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/scripts/package/builddeb b/scripts/package/builddeb index 0b31f4f1f92c..f43a274f4f1d 100755 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -83,9 +83,9 @@ else fi cp "$($MAKE -s -f $srctree/Makefile image_name)" "$tmpdir/$installed_image_path" -if grep -q "^CONFIG_OF=y" $KCONFIG_CONFIG ; then +if grep -q "^CONFIG_OF_EARLY_FLATTREE=y" $KCONFIG_CONFIG ; then # Only some architectures with OF support have this target - if grep -q dtbs_install "${srctree}/arch/$SRCARCH/Makefile"; then + if [ -d "${srctree}/arch/$SRCARCH/boot/dts" ]; then $MAKE KBUILD_SRC= INSTALL_DTBS_PATH="$tmpdir/usr/lib/$packagename" dtbs_install fi fi From 7ab412d33b4c7ff3e0148d3db25dd861edd1283d Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Sat, 10 Nov 2018 17:30:24 -0500 Subject: [PATCH 306/356] tipc: fix link re-establish failure When a link failure is detected locally, the link is reset, the flag link->in_session is set to false, and a RESET_MSG with the 'stopping' bit set is sent to the peer. The purpose of this bit is to inform the peer that this endpoint just is going down, and that the peer should handle the reception of this particular RESET message as a local failure. This forces the peer to accept another RESET or ACTIVATE message from this endpoint before it can re-establish the link. This again is necessary to ensure that link session numbers are properly exchanged before the link comes up again. If a failure is detected locally at the same time at the peer endpoint this will do the same, which is also a correct behavior. However, when receiving such messages, the endpoints will not distinguish between 'stopping' RESETs and ordinary ones when it comes to updating session numbers. Both endpoints will copy the received session number and set their 'in_session' flags to true at the reception, while they are still expecting another RESET from the peer before they can go ahead and re-establish. This is contradictory, since, after applying the validation check referred to below, the 'in_session' flag will cause rejection of all such messages, and the link will never come up again. We now fix this by not only handling received RESET/STOPPING messages as a local failure, but also by omitting to set a new session number and the 'in_session' flag in such cases. Fixes: 7ea817f4e832 ("tipc: check session number before accepting link protocol messages") Signed-off-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/link.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/net/tipc/link.c b/net/tipc/link.c index 201c3b5bc96b..836727e363c4 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1594,14 +1594,17 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, if (in_range(peers_prio, l->priority + 1, TIPC_MAX_LINK_PRI)) l->priority = peers_prio; - /* ACTIVATE_MSG serves as PEER_RESET if link is already down */ - if (msg_peer_stopping(hdr)) + /* If peer is going down we want full re-establish cycle */ + if (msg_peer_stopping(hdr)) { rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT); - else if ((mtyp == RESET_MSG) || !link_is_up(l)) + break; + } + /* ACTIVATE_MSG serves as PEER_RESET if link is already down */ + if (mtyp == RESET_MSG || !link_is_up(l)) rc = tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT); /* ACTIVATE_MSG takes up link if it was already locally reset */ - if ((mtyp == ACTIVATE_MSG) && (l->state == LINK_ESTABLISHING)) + if (mtyp == ACTIVATE_MSG && l->state == LINK_ESTABLISHING) rc = TIPC_LINK_UP_EVT; l->peer_session = msg_session(hdr); From a9049ff9214da68df1179a7d5e36b43479abc9b8 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 11 Nov 2018 00:41:10 +0100 Subject: [PATCH 307/356] net: dsa: mv88e6xxx: Fix clearing of stats counters The mv88e6161 would sometime fail to probe with a timeout waiting for the switch to complete an operation. This operation is supposed to clear the statistics counters. However, due to a read/modify/write, without the needed mask, the operation actually carried out was more random, with invalid parameters, resulting in the switch not responding. We need to preserve the histogram mode bits, so apply a mask to keep them. Reported-by: Chris Healy Fixes: 40cff8fca9e3 ("net: dsa: mv88e6xxx: Fix stats histogram mode") Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/global1.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c index d721ccf7d8be..38e399e0f30e 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.c +++ b/drivers/net/dsa/mv88e6xxx/global1.c @@ -567,6 +567,8 @@ int mv88e6xxx_g1_stats_clear(struct mv88e6xxx_chip *chip) if (err) return err; + /* Keep the histogram mode bits */ + val &= MV88E6XXX_G1_STATS_OP_HIST_RX_TX; val |= MV88E6XXX_G1_STATS_OP_BUSY | MV88E6XXX_G1_STATS_OP_FLUSH_ALL; err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_STATS_OP, val); From 7236ead1b14923f3ba35cd29cce13246be83f451 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 10 Nov 2018 16:22:29 -0800 Subject: [PATCH 308/356] act_mirred: clear skb->tstamp on redirect If sch_fq is used at ingress, skbs that might have been timestamped by net_timestamp_set() if a packet capture is requesting timestamps could be delayed by arbitrary amount of time, since sch_fq time base is MONOTONIC. Fix this problem by moving code from sch_netem.c to act_mirred.c. Fixes: fb420d5d91c1 ("tcp/fq: move back to CLOCK_MONOTONIC") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/sched/act_mirred.c | 3 ++- net/sched/sch_netem.c | 9 --------- 2 files changed, 2 insertions(+), 10 deletions(-) diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 1dae5f2b358f..c8cf4d10c435 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -258,7 +258,8 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, if (is_redirect) { skb2->tc_redirected = 1; skb2->tc_from_ingress = skb2->tc_at_ingress; - + if (skb2->tc_from_ingress) + skb2->tstamp = 0; /* let's the caller reinsert the packet, if possible */ if (use_reinsert) { res->ingress = want_ingress; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 57b3ad9394ad..2c38e3d07924 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -648,15 +648,6 @@ deliver: */ skb->dev = qdisc_dev(sch); -#ifdef CONFIG_NET_CLS_ACT - /* - * If it's at ingress let's pretend the delay is - * from the network (tstamp will be updated). - */ - if (skb->tc_redirected && skb->tc_from_ingress) - skb->tstamp = 0; -#endif - if (q->slot.slot_next) { q->slot.packets_left--; q->slot.bytes_left -= qdisc_pkt_len(skb); From ccda4af0f4b92f7b4c308d3acc262f4a7e3affad Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 11 Nov 2018 17:12:31 -0600 Subject: [PATCH 309/356] Linux 4.20-rc2 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 9fce8b91c15f..2f36db897895 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 20 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = "People's Front" # *DOCUMENTATION* From cfd74017191036871af68368559330507209777c Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Thu, 8 Nov 2018 06:39:20 +0000 Subject: [PATCH 310/356] mtd: rawnand: sh_flctl: convert to SPDX identifiers This patch updates license to use SPDX-License-Identifier instead of verbose license text. As original license mentioned, it is GPL-2.0 in SPDX. Then, MODULE_LICENSE() should be "GPL v2" instead of "GPL". See ${LINUX}/include/linux/module.h "GPL" [GNU Public License v2 or later] "GPL v2" [GNU Public License v2] Signed-off-by: Kuninori Morimoto Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/sh_flctl.c | 17 ++--------------- include/linux/mtd/sh_flctl.h | 16 ++-------------- 2 files changed, 4 insertions(+), 29 deletions(-) diff --git a/drivers/mtd/nand/raw/sh_flctl.c b/drivers/mtd/nand/raw/sh_flctl.c index 4d20d033de7b..30edcc77b111 100644 --- a/drivers/mtd/nand/raw/sh_flctl.c +++ b/drivers/mtd/nand/raw/sh_flctl.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * SuperH FLCTL nand controller * @@ -5,20 +6,6 @@ * Copyright (c) 2008 Atom Create Engineering Co., Ltd. * * Based on fsl_elbc_nand.c, Copyright (c) 2006-2007 Freescale Semiconductor - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - * - * 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. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * */ #include @@ -1236,7 +1223,7 @@ static struct platform_driver flctl_driver = { module_platform_driver_probe(flctl_driver, flctl_probe); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Yoshihiro Shimoda"); MODULE_DESCRIPTION("SuperH FLCTL driver"); MODULE_ALIAS("platform:sh_flctl"); diff --git a/include/linux/mtd/sh_flctl.h b/include/linux/mtd/sh_flctl.h index c759d403cbc0..78fc2d4218c8 100644 --- a/include/linux/mtd/sh_flctl.h +++ b/include/linux/mtd/sh_flctl.h @@ -1,20 +1,8 @@ -/* +/* SPDX-License-Identifier: GPL-2.0 + * * SuperH FLCTL nand controller * * Copyright © 2008 Renesas Solutions Corp. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - * - * 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. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */ #ifndef __SH_FLCTL_H__ From 10949af1681d5bb5cdbcc012815c6e40eec17d02 Mon Sep 17 00:00:00 2001 From: Schrempf Frieder Date: Thu, 8 Nov 2018 08:32:11 +0000 Subject: [PATCH 311/356] mtd: spinand: Add initial support for Toshiba TC58CVG2S0H MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add minimal support for the Toshiba TC58CVG2S0H SPI NAND chip. Signed-off-by: Frieder Schrempf Acked-by: Clément Péron Signed-off-by: Miquel Raynal --- drivers/mtd/nand/spi/Makefile | 2 +- drivers/mtd/nand/spi/core.c | 1 + drivers/mtd/nand/spi/toshiba.c | 137 +++++++++++++++++++++++++++++++++ include/linux/mtd/spinand.h | 1 + 4 files changed, 140 insertions(+), 1 deletion(-) create mode 100644 drivers/mtd/nand/spi/toshiba.c diff --git a/drivers/mtd/nand/spi/Makefile b/drivers/mtd/nand/spi/Makefile index b74e074b363a..be5f73512ece 100644 --- a/drivers/mtd/nand/spi/Makefile +++ b/drivers/mtd/nand/spi/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 -spinand-objs := core.o macronix.o micron.o winbond.o +spinand-objs := core.o macronix.o micron.o toshiba.o winbond.o obj-$(CONFIG_MTD_SPI_NAND) += spinand.o diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c index 30f83649c481..87bdf2a7b724 100644 --- a/drivers/mtd/nand/spi/core.c +++ b/drivers/mtd/nand/spi/core.c @@ -766,6 +766,7 @@ static const struct nand_ops spinand_ops = { static const struct spinand_manufacturer *spinand_manufacturers[] = { ¯onix_spinand_manufacturer, µn_spinand_manufacturer, + &toshiba_spinand_manufacturer, &winbond_spinand_manufacturer, }; diff --git a/drivers/mtd/nand/spi/toshiba.c b/drivers/mtd/nand/spi/toshiba.c new file mode 100644 index 000000000000..081265557e70 --- /dev/null +++ b/drivers/mtd/nand/spi/toshiba.c @@ -0,0 +1,137 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2018 exceet electronics GmbH + * Copyright (c) 2018 Kontron Electronics GmbH + * + * Author: Frieder Schrempf + */ + +#include +#include +#include + +#define SPINAND_MFR_TOSHIBA 0x98 +#define TOSH_STATUS_ECC_HAS_BITFLIPS_T (3 << 4) + +static SPINAND_OP_VARIANTS(read_cache_variants, + SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0)); + +static SPINAND_OP_VARIANTS(write_cache_variants, + SPINAND_PROG_LOAD(true, 0, NULL, 0)); + +static SPINAND_OP_VARIANTS(update_cache_variants, + SPINAND_PROG_LOAD(false, 0, NULL, 0)); + +static int tc58cvg2s0h_ooblayout_ecc(struct mtd_info *mtd, int section, + struct mtd_oob_region *region) +{ + if (section > 7) + return -ERANGE; + + region->offset = 128 + 16 * section; + region->length = 16; + + return 0; +} + +static int tc58cvg2s0h_ooblayout_free(struct mtd_info *mtd, int section, + struct mtd_oob_region *region) +{ + if (section > 0) + return -ERANGE; + + /* 2 bytes reserved for BBM */ + region->offset = 2; + region->length = 126; + + return 0; +} + +static const struct mtd_ooblayout_ops tc58cvg2s0h_ooblayout = { + .ecc = tc58cvg2s0h_ooblayout_ecc, + .free = tc58cvg2s0h_ooblayout_free, +}; + +static int tc58cvg2s0h_ecc_get_status(struct spinand_device *spinand, + u8 status) +{ + struct nand_device *nand = spinand_to_nand(spinand); + u8 mbf = 0; + struct spi_mem_op op = SPINAND_GET_FEATURE_OP(0x30, &mbf); + + switch (status & STATUS_ECC_MASK) { + case STATUS_ECC_NO_BITFLIPS: + return 0; + + case STATUS_ECC_UNCOR_ERROR: + return -EBADMSG; + + case STATUS_ECC_HAS_BITFLIPS: + case TOSH_STATUS_ECC_HAS_BITFLIPS_T: + /* + * Let's try to retrieve the real maximum number of bitflips + * in order to avoid forcing the wear-leveling layer to move + * data around if it's not necessary. + */ + if (spi_mem_exec_op(spinand->spimem, &op)) + return nand->eccreq.strength; + + mbf >>= 4; + + if (WARN_ON(mbf > nand->eccreq.strength || !mbf)) + return nand->eccreq.strength; + + return mbf; + + default: + break; + } + + return -EINVAL; +} + +static const struct spinand_info toshiba_spinand_table[] = { + SPINAND_INFO("TC58CVG2S0H", 0xCD, + NAND_MEMORG(1, 4096, 256, 64, 2048, 1, 1, 1), + NAND_ECCREQ(8, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants, + &write_cache_variants, + &update_cache_variants), + SPINAND_HAS_QE_BIT, + SPINAND_ECCINFO(&tc58cvg2s0h_ooblayout, + tc58cvg2s0h_ecc_get_status)), +}; + +static int toshiba_spinand_detect(struct spinand_device *spinand) +{ + u8 *id = spinand->id.data; + int ret; + + /* + * Toshiba SPI NAND read ID needs a dummy byte, + * so the first byte in id is garbage. + */ + if (id[1] != SPINAND_MFR_TOSHIBA) + return 0; + + ret = spinand_match_and_init(spinand, toshiba_spinand_table, + ARRAY_SIZE(toshiba_spinand_table), + id[2]); + if (ret) + return ret; + + return 1; +} + +static const struct spinand_manufacturer_ops toshiba_spinand_manuf_ops = { + .detect = toshiba_spinand_detect, +}; + +const struct spinand_manufacturer toshiba_spinand_manufacturer = { + .id = SPINAND_MFR_TOSHIBA, + .name = "Toshiba", + .ops = &toshiba_spinand_manuf_ops, +}; diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 088ff96c3eb6..816c4b00abca 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -196,6 +196,7 @@ struct spinand_manufacturer { /* SPI NAND manufacturers */ extern const struct spinand_manufacturer macronix_spinand_manufacturer; extern const struct spinand_manufacturer micron_spinand_manufacturer; +extern const struct spinand_manufacturer toshiba_spinand_manufacturer; extern const struct spinand_manufacturer winbond_spinand_manufacturer; /** From 0813621ba898aa91984d2713251970feeca93777 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:03 +0100 Subject: [PATCH 312/356] mtd: rawnand: Stop passing mtd_info objects to internal functions After having reworked the rawnand API to avoid passing mtd_info objects around, let's do the same for internal functions. Signed-off-by: Boris Brezillon Tested-by: Janusz Krzysztofik Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/nand_base.c | 171 +++++++++++++------------- drivers/mtd/nand/raw/nand_bbt.c | 185 +++++++++++++++-------------- drivers/mtd/nand/raw/nand_legacy.c | 18 ++- 3 files changed, 184 insertions(+), 190 deletions(-) diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 4bc89c959f23..2a50afbdeeeb 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -49,9 +49,9 @@ #include "internals.h" -static int nand_get_device(struct mtd_info *mtd, int new_state); +static int nand_get_device(struct nand_chip *chip, int new_state); -static int nand_do_write_oob(struct mtd_info *mtd, loff_t to, +static int nand_do_write_oob(struct nand_chip *chip, loff_t to, struct mtd_oob_ops *ops); /* Define default oob placement schemes for large and small page devices */ @@ -214,10 +214,8 @@ static const struct mtd_ooblayout_ops nand_ooblayout_lp_hamming_ops = { .free = nand_ooblayout_free_lp_hamming, }; -static int check_offs_len(struct mtd_info *mtd, - loff_t ofs, uint64_t len) +static int check_offs_len(struct nand_chip *chip, loff_t ofs, uint64_t len) { - struct nand_chip *chip = mtd_to_nand(mtd); int ret = 0; /* Start address must align on block boundary */ @@ -237,14 +235,12 @@ static int check_offs_len(struct mtd_info *mtd, /** * nand_release_device - [GENERIC] release chip - * @mtd: MTD device structure + * @chip: NAND chip object * * Release chip lock and wake up anyone waiting on the device. */ -static void nand_release_device(struct mtd_info *mtd) +static void nand_release_device(struct nand_chip *chip) { - struct nand_chip *chip = mtd_to_nand(mtd); - /* Release the controller and the chip */ spin_lock(&chip->controller->lock); chip->controller->active = NULL; @@ -321,7 +317,7 @@ static int nand_default_block_markbad(struct nand_chip *chip, loff_t ofs) if (chip->bbt_options & NAND_BBT_SCANLASTPAGE) ofs += mtd->erasesize - mtd->writesize; do { - res = nand_do_write_oob(mtd, ofs, &ops); + res = nand_do_write_oob(chip, ofs, &ops); if (!ret) ret = res; @@ -355,7 +351,7 @@ static int nand_isbad_bbm(struct nand_chip *chip, loff_t ofs) /** * nand_block_markbad_lowlevel - mark a block bad - * @mtd: MTD device structure + * @chip: NAND chip object * @ofs: offset from device start * * This function performs the generic NAND bad block marking steps (i.e., bad @@ -372,9 +368,9 @@ static int nand_isbad_bbm(struct nand_chip *chip, loff_t ofs) * Note that we retain the first error encountered in (2) or (3), finish the * procedures, and dump the error in the end. */ -static int nand_block_markbad_lowlevel(struct mtd_info *mtd, loff_t ofs) +static int nand_block_markbad_lowlevel(struct nand_chip *chip, loff_t ofs) { - struct nand_chip *chip = mtd_to_nand(mtd); + struct mtd_info *mtd = nand_to_mtd(chip); int res, ret = 0; if (!(chip->bbt_options & NAND_BBT_NO_OOB_BBM)) { @@ -387,9 +383,9 @@ static int nand_block_markbad_lowlevel(struct mtd_info *mtd, loff_t ofs) nand_erase_nand(chip, &einfo, 0); /* Write bad block marker to OOB */ - nand_get_device(mtd, FL_WRITING); + nand_get_device(chip, FL_WRITING); ret = nand_markbad_bbm(chip, ofs); - nand_release_device(mtd); + nand_release_device(chip); } /* Mark block bad in BBT */ @@ -407,14 +403,13 @@ static int nand_block_markbad_lowlevel(struct mtd_info *mtd, loff_t ofs) /** * nand_check_wp - [GENERIC] check if the chip is write protected - * @mtd: MTD device structure + * @chip: NAND chip object * * Check, if the device is write protected. The function expects, that the * device is already selected. */ -static int nand_check_wp(struct mtd_info *mtd) +static int nand_check_wp(struct nand_chip *chip) { - struct nand_chip *chip = mtd_to_nand(mtd); u8 status; int ret; @@ -449,17 +444,15 @@ static int nand_block_isreserved(struct mtd_info *mtd, loff_t ofs) /** * nand_block_checkbad - [GENERIC] Check if a block is marked bad - * @mtd: MTD device structure + * @chip: NAND chip object * @ofs: offset from device start * @allowbbt: 1, if its allowed to access the bbt area * * Check, if the block is bad. Either by reading the bad block table or * calling of the scan function. */ -static int nand_block_checkbad(struct mtd_info *mtd, loff_t ofs, int allowbbt) +static int nand_block_checkbad(struct nand_chip *chip, loff_t ofs, int allowbbt) { - struct nand_chip *chip = mtd_to_nand(mtd); - /* Return info from the table */ if (chip->bbt) return nand_isbad_bbt(chip, ofs, allowbbt); @@ -565,13 +558,11 @@ EXPORT_SYMBOL_GPL(nand_gpio_waitrdy); /** * panic_nand_get_device - [GENERIC] Get chip for selected access * @chip: the nand chip descriptor - * @mtd: MTD device structure * @new_state: the state which is requested * * Used when in panic, no locks are taken. */ -static void panic_nand_get_device(struct nand_chip *chip, - struct mtd_info *mtd, int new_state) +static void panic_nand_get_device(struct nand_chip *chip, int new_state) { /* Hardware controller shared among independent devices */ chip->controller->active = chip; @@ -580,15 +571,14 @@ static void panic_nand_get_device(struct nand_chip *chip, /** * nand_get_device - [GENERIC] Get chip for selected access - * @mtd: MTD device structure + * @chip: NAND chip structure * @new_state: the state which is requested * * Get the device and lock it for exclusive access */ static int -nand_get_device(struct mtd_info *mtd, int new_state) +nand_get_device(struct nand_chip *chip, int new_state) { - struct nand_chip *chip = mtd_to_nand(mtd); spinlock_t *lock = &chip->controller->lock; wait_queue_head_t *wq = &chip->controller->wq; DECLARE_WAITQUEUE(wait, current); @@ -2955,15 +2945,15 @@ static int nand_read_page_syndrome(struct nand_chip *chip, uint8_t *buf, /** * nand_transfer_oob - [INTERN] Transfer oob to client buffer - * @mtd: mtd info structure + * @chip: NAND chip object * @oob: oob destination address * @ops: oob ops structure * @len: size of oob to transfer */ -static uint8_t *nand_transfer_oob(struct mtd_info *mtd, uint8_t *oob, +static uint8_t *nand_transfer_oob(struct nand_chip *chip, uint8_t *oob, struct mtd_oob_ops *ops, size_t len) { - struct nand_chip *chip = mtd_to_nand(mtd); + struct mtd_info *mtd = nand_to_mtd(chip); int ret; switch (ops->mode) { @@ -3020,17 +3010,17 @@ static void nand_wait_readrdy(struct nand_chip *chip) /** * nand_do_read_ops - [INTERN] Read data with ECC - * @mtd: MTD device structure + * @chip: NAND chip object * @from: offset to read from * @ops: oob ops structure * * Internal function. Called with chip held. */ -static int nand_do_read_ops(struct mtd_info *mtd, loff_t from, +static int nand_do_read_ops(struct nand_chip *chip, loff_t from, struct mtd_oob_ops *ops) { int chipnr, page, realpage, col, bytes, aligned, oob_required; - struct nand_chip *chip = mtd_to_nand(mtd); + struct mtd_info *mtd = nand_to_mtd(chip); int ret = 0; uint32_t readlen = ops->len; uint32_t oobreadlen = ops->ooblen; @@ -3118,8 +3108,8 @@ read_retry: int toread = min(oobreadlen, max_oobsize); if (toread) { - oob = nand_transfer_oob(mtd, - oob, ops, toread); + oob = nand_transfer_oob(chip, oob, ops, + toread); oobreadlen -= toread; } } @@ -3349,18 +3339,18 @@ static int nand_write_oob_syndrome(struct nand_chip *chip, int page) /** * nand_do_read_oob - [INTERN] NAND read out-of-band - * @mtd: MTD device structure + * @chip: NAND chip object * @from: offset to read from * @ops: oob operations description structure * * NAND read out-of-band data from the spare area. */ -static int nand_do_read_oob(struct mtd_info *mtd, loff_t from, +static int nand_do_read_oob(struct nand_chip *chip, loff_t from, struct mtd_oob_ops *ops) { + struct mtd_info *mtd = nand_to_mtd(chip); unsigned int max_bitflips = 0; int page, realpage, chipnr; - struct nand_chip *chip = mtd_to_nand(mtd); struct mtd_ecc_stats stats; int readlen = ops->ooblen; int len; @@ -3391,7 +3381,7 @@ static int nand_do_read_oob(struct mtd_info *mtd, loff_t from, break; len = min(len, readlen); - buf = nand_transfer_oob(mtd, buf, ops, len); + buf = nand_transfer_oob(chip, buf, ops, len); nand_wait_readrdy(chip); @@ -3436,6 +3426,7 @@ static int nand_do_read_oob(struct mtd_info *mtd, loff_t from, static int nand_read_oob(struct mtd_info *mtd, loff_t from, struct mtd_oob_ops *ops) { + struct nand_chip *chip = mtd_to_nand(mtd); int ret; ops->retlen = 0; @@ -3445,14 +3436,14 @@ static int nand_read_oob(struct mtd_info *mtd, loff_t from, ops->mode != MTD_OPS_RAW) return -ENOTSUPP; - nand_get_device(mtd, FL_READING); + nand_get_device(chip, FL_READING); if (!ops->datbuf) - ret = nand_do_read_oob(mtd, from, ops); + ret = nand_do_read_oob(chip, from, ops); else - ret = nand_do_read_ops(mtd, from, ops); + ret = nand_do_read_ops(chip, from, ops); - nand_release_device(mtd); + nand_release_device(chip); return ret; } @@ -3780,7 +3771,6 @@ static int nand_write_page_syndrome(struct nand_chip *chip, const uint8_t *buf, /** * nand_write_page - write one page - * @mtd: MTD device structure * @chip: NAND chip descriptor * @offset: address offset within the page * @data_len: length of actual data to be written @@ -3789,10 +3779,11 @@ static int nand_write_page_syndrome(struct nand_chip *chip, const uint8_t *buf, * @page: page number to write * @raw: use _raw version of write_page */ -static int nand_write_page(struct mtd_info *mtd, struct nand_chip *chip, - uint32_t offset, int data_len, const uint8_t *buf, - int oob_required, int page, int raw) +static int nand_write_page(struct nand_chip *chip, uint32_t offset, + int data_len, const uint8_t *buf, int oob_required, + int page, int raw) { + struct mtd_info *mtd = nand_to_mtd(chip); int status, subpage; if (!(chip->options & NAND_NO_SUBPAGE_WRITE) && @@ -3818,15 +3809,15 @@ static int nand_write_page(struct mtd_info *mtd, struct nand_chip *chip, /** * nand_fill_oob - [INTERN] Transfer client buffer to oob - * @mtd: MTD device structure + * @chip: NAND chip object * @oob: oob data buffer * @len: oob data write length * @ops: oob ops structure */ -static uint8_t *nand_fill_oob(struct mtd_info *mtd, uint8_t *oob, size_t len, +static uint8_t *nand_fill_oob(struct nand_chip *chip, uint8_t *oob, size_t len, struct mtd_oob_ops *ops) { - struct nand_chip *chip = mtd_to_nand(mtd); + struct mtd_info *mtd = nand_to_mtd(chip); int ret; /* @@ -3858,17 +3849,17 @@ static uint8_t *nand_fill_oob(struct mtd_info *mtd, uint8_t *oob, size_t len, /** * nand_do_write_ops - [INTERN] NAND write with ECC - * @mtd: MTD device structure + * @chip: NAND chip object * @to: offset to write to * @ops: oob operations description structure * * NAND write with ECC. */ -static int nand_do_write_ops(struct mtd_info *mtd, loff_t to, +static int nand_do_write_ops(struct nand_chip *chip, loff_t to, struct mtd_oob_ops *ops) { + struct mtd_info *mtd = nand_to_mtd(chip); int chipnr, realpage, page, column; - struct nand_chip *chip = mtd_to_nand(mtd); uint32_t writelen = ops->len; uint32_t oobwritelen = ops->ooblen; @@ -3896,7 +3887,7 @@ static int nand_do_write_ops(struct mtd_info *mtd, loff_t to, chip->select_chip(chip, chipnr); /* Check, if it is write protected */ - if (nand_check_wp(mtd)) { + if (nand_check_wp(chip)) { ret = -EIO; goto err_out; } @@ -3944,14 +3935,14 @@ static int nand_do_write_ops(struct mtd_info *mtd, loff_t to, if (unlikely(oob)) { size_t len = min(oobwritelen, oobmaxlen); - oob = nand_fill_oob(mtd, oob, len, ops); + oob = nand_fill_oob(chip, oob, len, ops); oobwritelen -= len; } else { /* We still need to erase leftover OOB data */ memset(chip->oob_poi, 0xff, mtd->oobsize); } - ret = nand_write_page(mtd, chip, column, bytes, wbuf, + ret = nand_write_page(chip, column, bytes, wbuf, oob_required, page, (ops->mode == MTD_OPS_RAW)); if (ret) @@ -4003,7 +3994,7 @@ static int panic_nand_write(struct mtd_info *mtd, loff_t to, size_t len, int ret; /* Grab the device */ - panic_nand_get_device(chip, mtd, FL_WRITING); + panic_nand_get_device(chip, FL_WRITING); chip->select_chip(chip, chipnr); @@ -4015,7 +4006,7 @@ static int panic_nand_write(struct mtd_info *mtd, loff_t to, size_t len, ops.datbuf = (uint8_t *)buf; ops.mode = MTD_OPS_PLACE_OOB; - ret = nand_do_write_ops(mtd, to, &ops); + ret = nand_do_write_ops(chip, to, &ops); *retlen = ops.retlen; return ret; @@ -4023,17 +4014,17 @@ static int panic_nand_write(struct mtd_info *mtd, loff_t to, size_t len, /** * nand_do_write_oob - [MTD Interface] NAND write out-of-band - * @mtd: MTD device structure + * @chip: NAND chip object * @to: offset to write to * @ops: oob operation description structure * * NAND write out-of-band. */ -static int nand_do_write_oob(struct mtd_info *mtd, loff_t to, +static int nand_do_write_oob(struct nand_chip *chip, loff_t to, struct mtd_oob_ops *ops) { + struct mtd_info *mtd = nand_to_mtd(chip); int chipnr, page, status, len; - struct nand_chip *chip = mtd_to_nand(mtd); pr_debug("%s: to = 0x%08x, len = %i\n", __func__, (unsigned int)to, (int)ops->ooblen); @@ -4063,7 +4054,7 @@ static int nand_do_write_oob(struct mtd_info *mtd, loff_t to, page = (int)(to >> chip->page_shift); /* Check, if it is write protected */ - if (nand_check_wp(mtd)) { + if (nand_check_wp(chip)) { chip->select_chip(chip, -1); return -EROFS; } @@ -4072,7 +4063,7 @@ static int nand_do_write_oob(struct mtd_info *mtd, loff_t to, if (page == chip->pagebuf) chip->pagebuf = -1; - nand_fill_oob(mtd, ops->oobbuf, ops->ooblen, ops); + nand_fill_oob(chip, ops->oobbuf, ops->ooblen, ops); if (ops->mode == MTD_OPS_RAW) status = chip->ecc.write_oob_raw(chip, page & chip->pagemask); @@ -4098,11 +4089,12 @@ static int nand_do_write_oob(struct mtd_info *mtd, loff_t to, static int nand_write_oob(struct mtd_info *mtd, loff_t to, struct mtd_oob_ops *ops) { + struct nand_chip *chip = mtd_to_nand(mtd); int ret = -ENOTSUPP; ops->retlen = 0; - nand_get_device(mtd, FL_WRITING); + nand_get_device(chip, FL_WRITING); switch (ops->mode) { case MTD_OPS_PLACE_OOB: @@ -4115,12 +4107,12 @@ static int nand_write_oob(struct mtd_info *mtd, loff_t to, } if (!ops->datbuf) - ret = nand_do_write_oob(mtd, to, ops); + ret = nand_do_write_oob(chip, to, ops); else - ret = nand_do_write_ops(mtd, to, ops); + ret = nand_do_write_ops(chip, to, ops); out: - nand_release_device(mtd); + nand_release_device(chip); return ret; } @@ -4164,7 +4156,6 @@ static int nand_erase(struct mtd_info *mtd, struct erase_info *instr) int nand_erase_nand(struct nand_chip *chip, struct erase_info *instr, int allowbbt) { - struct mtd_info *mtd = nand_to_mtd(chip); int page, status, pages_per_block, ret, chipnr; loff_t len; @@ -4172,11 +4163,11 @@ int nand_erase_nand(struct nand_chip *chip, struct erase_info *instr, __func__, (unsigned long long)instr->addr, (unsigned long long)instr->len); - if (check_offs_len(mtd, instr->addr, instr->len)) + if (check_offs_len(chip, instr->addr, instr->len)) return -EINVAL; /* Grab the lock and see if the device is available */ - nand_get_device(mtd, FL_ERASING); + nand_get_device(chip, FL_ERASING); /* Shift to get first page */ page = (int)(instr->addr >> chip->page_shift); @@ -4189,7 +4180,7 @@ int nand_erase_nand(struct nand_chip *chip, struct erase_info *instr, chip->select_chip(chip, chipnr); /* Check, if it is write protected */ - if (nand_check_wp(mtd)) { + if (nand_check_wp(chip)) { pr_debug("%s: device is write protected!\n", __func__); ret = -EIO; @@ -4201,7 +4192,7 @@ int nand_erase_nand(struct nand_chip *chip, struct erase_info *instr, while (len) { /* Check if we have a bad block, we do not erase bad blocks! */ - if (nand_block_checkbad(mtd, ((loff_t) page) << + if (nand_block_checkbad(chip, ((loff_t) page) << chip->page_shift, allowbbt)) { pr_warn("%s: attempt to erase a bad block at page 0x%08x\n", __func__, page); @@ -4250,7 +4241,7 @@ erase_exit: /* Deselect and wake up anyone waiting on the device */ chip->select_chip(chip, -1); - nand_release_device(mtd); + nand_release_device(chip); /* Return more or less happy */ return ret; @@ -4264,12 +4255,14 @@ erase_exit: */ static void nand_sync(struct mtd_info *mtd) { + struct nand_chip *chip = mtd_to_nand(mtd); + pr_debug("%s: called\n", __func__); /* Grab the lock and see if the device is available */ - nand_get_device(mtd, FL_SYNCING); + nand_get_device(chip, FL_SYNCING); /* Release it and go back */ - nand_release_device(mtd); + nand_release_device(chip); } /** @@ -4284,13 +4277,13 @@ static int nand_block_isbad(struct mtd_info *mtd, loff_t offs) int ret; /* Select the NAND device */ - nand_get_device(mtd, FL_READING); + nand_get_device(chip, FL_READING); chip->select_chip(chip, chipnr); - ret = nand_block_checkbad(mtd, offs, 0); + ret = nand_block_checkbad(chip, offs, 0); chip->select_chip(chip, -1); - nand_release_device(mtd); + nand_release_device(chip); return ret; } @@ -4312,7 +4305,7 @@ static int nand_block_markbad(struct mtd_info *mtd, loff_t ofs) return ret; } - return nand_block_markbad_lowlevel(mtd, ofs); + return nand_block_markbad_lowlevel(mtd_to_nand(mtd), ofs); } /** @@ -4357,7 +4350,7 @@ static int nand_max_bad_blocks(struct mtd_info *mtd, loff_t ofs, size_t len) */ static int nand_suspend(struct mtd_info *mtd) { - return nand_get_device(mtd, FL_PM_SUSPENDED); + return nand_get_device(mtd_to_nand(mtd), FL_PM_SUSPENDED); } /** @@ -4369,7 +4362,7 @@ static void nand_resume(struct mtd_info *mtd) struct nand_chip *chip = mtd_to_nand(mtd); if (chip->state == FL_PM_SUSPENDED) - nand_release_device(mtd); + nand_release_device(chip); else pr_err("%s called for a chip which is not in suspended state\n", __func__); @@ -4382,7 +4375,7 @@ static void nand_resume(struct mtd_info *mtd) */ static void nand_shutdown(struct mtd_info *mtd) { - nand_get_device(mtd, FL_PM_SUSPENDED); + nand_get_device(mtd_to_nand(mtd), FL_PM_SUSPENDED); } /* Set default functions */ @@ -5052,9 +5045,9 @@ static void nand_scan_ident_cleanup(struct nand_chip *chip) kfree(chip->parameters.onfi); } -static int nand_set_ecc_soft_ops(struct mtd_info *mtd) +static int nand_set_ecc_soft_ops(struct nand_chip *chip) { - struct nand_chip *chip = mtd_to_nand(mtd); + struct mtd_info *mtd = nand_to_mtd(chip); struct nand_ecc_ctrl *ecc = &chip->ecc; if (WARN_ON(ecc->mode != NAND_ECC_SOFT)) @@ -5410,9 +5403,9 @@ EXPORT_SYMBOL_GPL(nand_ecc_choose_conf); * Requirement (2) ensures we can correct even when all bitflips are clumped * in the same sector. */ -static bool nand_ecc_strength_good(struct mtd_info *mtd) +static bool nand_ecc_strength_good(struct nand_chip *chip) { - struct nand_chip *chip = mtd_to_nand(mtd); + struct mtd_info *mtd = nand_to_mtd(chip); struct nand_ecc_ctrl *ecc = &chip->ecc; int corr, ds_corr; @@ -5577,7 +5570,7 @@ static int nand_scan_tail(struct nand_chip *chip) ecc->algo = NAND_ECC_HAMMING; case NAND_ECC_SOFT: - ret = nand_set_ecc_soft_ops(mtd); + ret = nand_set_ecc_soft_ops(chip); if (ret) { ret = -EINVAL; goto err_nand_manuf_cleanup; @@ -5662,7 +5655,7 @@ static int nand_scan_tail(struct nand_chip *chip) mtd->oobavail = ret; /* ECC sanity check: warn if it's too weak */ - if (!nand_ecc_strength_good(mtd)) + if (!nand_ecc_strength_good(chip)) pr_warn("WARNING: %s: the ECC used on your system is too weak compared to the one required by the NAND chip\n", mtd->name); diff --git a/drivers/mtd/nand/raw/nand_bbt.c b/drivers/mtd/nand/raw/nand_bbt.c index 98a826838b60..b5e3b54cc767 100644 --- a/drivers/mtd/nand/raw/nand_bbt.c +++ b/drivers/mtd/nand/raw/nand_bbt.c @@ -77,7 +77,7 @@ #define BBT_ENTRY_MASK 0x03 #define BBT_ENTRY_SHIFT 2 -static int nand_update_bbt(struct mtd_info *mtd, loff_t offs); +static int nand_update_bbt(struct nand_chip *chip, loff_t offs); static inline uint8_t bbt_get_entry(struct nand_chip *chip, int block) { @@ -160,7 +160,7 @@ static u32 add_marker_len(struct nand_bbt_descr *td) /** * read_bbt - [GENERIC] Read the bad block table starting from page - * @mtd: MTD device structure + * @chip: NAND chip object * @buf: temporary buffer * @page: the starting page * @num: the number of bbt descriptors to read @@ -169,11 +169,11 @@ static u32 add_marker_len(struct nand_bbt_descr *td) * * Read the bad block table starting from page. */ -static int read_bbt(struct mtd_info *mtd, uint8_t *buf, int page, int num, - struct nand_bbt_descr *td, int offs) +static int read_bbt(struct nand_chip *this, uint8_t *buf, int page, int num, + struct nand_bbt_descr *td, int offs) { + struct mtd_info *mtd = nand_to_mtd(this); int res, ret = 0, i, j, act = 0; - struct nand_chip *this = mtd_to_nand(mtd); size_t retlen, len, totlen; loff_t from; int bits = td->options & NAND_BBT_NRBITS_MSK; @@ -253,7 +253,7 @@ static int read_bbt(struct mtd_info *mtd, uint8_t *buf, int page, int num, /** * read_abs_bbt - [GENERIC] Read the bad block table starting at a given page - * @mtd: MTD device structure + * @this: NAND chip object * @buf: temporary buffer * @td: descriptor for the bad block table * @chip: read the table for a specific chip, -1 read all chips; applies only if @@ -262,16 +262,17 @@ static int read_bbt(struct mtd_info *mtd, uint8_t *buf, int page, int num, * Read the bad block table for all chips starting at a given page. We assume * that the bbt bits are in consecutive order. */ -static int read_abs_bbt(struct mtd_info *mtd, uint8_t *buf, struct nand_bbt_descr *td, int chip) +static int read_abs_bbt(struct nand_chip *this, uint8_t *buf, + struct nand_bbt_descr *td, int chip) { - struct nand_chip *this = mtd_to_nand(mtd); + struct mtd_info *mtd = nand_to_mtd(this); int res = 0, i; if (td->options & NAND_BBT_PERCHIP) { int offs = 0; for (i = 0; i < this->numchips; i++) { if (chip == -1 || chip == i) - res = read_bbt(mtd, buf, td->pages[i], + res = read_bbt(this, buf, td->pages[i], this->chipsize >> this->bbt_erase_shift, td, offs); if (res) @@ -279,7 +280,7 @@ static int read_abs_bbt(struct mtd_info *mtd, uint8_t *buf, struct nand_bbt_desc offs += this->chipsize >> this->bbt_erase_shift; } } else { - res = read_bbt(mtd, buf, td->pages[0], + res = read_bbt(this, buf, td->pages[0], mtd->size >> this->bbt_erase_shift, td, 0); if (res) return res; @@ -288,9 +289,10 @@ static int read_abs_bbt(struct mtd_info *mtd, uint8_t *buf, struct nand_bbt_desc } /* BBT marker is in the first page, no OOB */ -static int scan_read_data(struct mtd_info *mtd, uint8_t *buf, loff_t offs, - struct nand_bbt_descr *td) +static int scan_read_data(struct nand_chip *this, uint8_t *buf, loff_t offs, + struct nand_bbt_descr *td) { + struct mtd_info *mtd = nand_to_mtd(this); size_t retlen; size_t len; @@ -303,7 +305,7 @@ static int scan_read_data(struct mtd_info *mtd, uint8_t *buf, loff_t offs, /** * scan_read_oob - [GENERIC] Scan data+OOB region to buffer - * @mtd: MTD device structure + * @this: NAND chip object * @buf: temporary buffer * @offs: offset at which to scan * @len: length of data region to read @@ -312,9 +314,10 @@ static int scan_read_data(struct mtd_info *mtd, uint8_t *buf, loff_t offs, * page,OOB,page,OOB,... in buf. Completes transfer and returns the "strongest" * ECC condition (error or bitflip). May quit on the first (non-ECC) error. */ -static int scan_read_oob(struct mtd_info *mtd, uint8_t *buf, loff_t offs, +static int scan_read_oob(struct nand_chip *this, uint8_t *buf, loff_t offs, size_t len) { + struct mtd_info *mtd = nand_to_mtd(this); struct mtd_oob_ops ops; int res, ret = 0; @@ -342,19 +345,20 @@ static int scan_read_oob(struct mtd_info *mtd, uint8_t *buf, loff_t offs, return ret; } -static int scan_read(struct mtd_info *mtd, uint8_t *buf, loff_t offs, - size_t len, struct nand_bbt_descr *td) +static int scan_read(struct nand_chip *this, uint8_t *buf, loff_t offs, + size_t len, struct nand_bbt_descr *td) { if (td->options & NAND_BBT_NO_OOB) - return scan_read_data(mtd, buf, offs, td); + return scan_read_data(this, buf, offs, td); else - return scan_read_oob(mtd, buf, offs, len); + return scan_read_oob(this, buf, offs, len); } /* Scan write data with oob to flash */ -static int scan_write_bbt(struct mtd_info *mtd, loff_t offs, size_t len, +static int scan_write_bbt(struct nand_chip *this, loff_t offs, size_t len, uint8_t *buf, uint8_t *oob) { + struct mtd_info *mtd = nand_to_mtd(this); struct mtd_oob_ops ops; ops.mode = MTD_OPS_PLACE_OOB; @@ -367,8 +371,9 @@ static int scan_write_bbt(struct mtd_info *mtd, loff_t offs, size_t len, return mtd_write_oob(mtd, offs, &ops); } -static u32 bbt_get_ver_offs(struct mtd_info *mtd, struct nand_bbt_descr *td) +static u32 bbt_get_ver_offs(struct nand_chip *this, struct nand_bbt_descr *td) { + struct mtd_info *mtd = nand_to_mtd(this); u32 ver_offs = td->veroffs; if (!(td->options & NAND_BBT_NO_OOB)) @@ -378,7 +383,7 @@ static u32 bbt_get_ver_offs(struct mtd_info *mtd, struct nand_bbt_descr *td) /** * read_abs_bbts - [GENERIC] Read the bad block table(s) for all chips starting at a given page - * @mtd: MTD device structure + * @this: NAND chip object * @buf: temporary buffer * @td: descriptor for the bad block table * @md: descriptor for the bad block table mirror @@ -386,34 +391,35 @@ static u32 bbt_get_ver_offs(struct mtd_info *mtd, struct nand_bbt_descr *td) * Read the bad block table(s) for all chips starting at a given page. We * assume that the bbt bits are in consecutive order. */ -static void read_abs_bbts(struct mtd_info *mtd, uint8_t *buf, +static void read_abs_bbts(struct nand_chip *this, uint8_t *buf, struct nand_bbt_descr *td, struct nand_bbt_descr *md) { - struct nand_chip *this = mtd_to_nand(mtd); + struct mtd_info *mtd = nand_to_mtd(this); /* Read the primary version, if available */ if (td->options & NAND_BBT_VERSION) { - scan_read(mtd, buf, (loff_t)td->pages[0] << this->page_shift, - mtd->writesize, td); - td->version[0] = buf[bbt_get_ver_offs(mtd, td)]; + scan_read(this, buf, (loff_t)td->pages[0] << this->page_shift, + mtd->writesize, td); + td->version[0] = buf[bbt_get_ver_offs(this, td)]; pr_info("Bad block table at page %d, version 0x%02X\n", td->pages[0], td->version[0]); } /* Read the mirror version, if available */ if (md && (md->options & NAND_BBT_VERSION)) { - scan_read(mtd, buf, (loff_t)md->pages[0] << this->page_shift, - mtd->writesize, md); - md->version[0] = buf[bbt_get_ver_offs(mtd, md)]; + scan_read(this, buf, (loff_t)md->pages[0] << this->page_shift, + mtd->writesize, md); + md->version[0] = buf[bbt_get_ver_offs(this, md)]; pr_info("Bad block table at page %d, version 0x%02X\n", md->pages[0], md->version[0]); } } /* Scan a given block partially */ -static int scan_block_fast(struct mtd_info *mtd, struct nand_bbt_descr *bd, +static int scan_block_fast(struct nand_chip *this, struct nand_bbt_descr *bd, loff_t offs, uint8_t *buf, int numpages) { + struct mtd_info *mtd = nand_to_mtd(this); struct mtd_oob_ops ops; int j, ret; @@ -443,7 +449,7 @@ static int scan_block_fast(struct mtd_info *mtd, struct nand_bbt_descr *bd, /** * create_bbt - [GENERIC] Create a bad block table by scanning the device - * @mtd: MTD device structure + * @this: NAND chip object * @buf: temporary buffer * @bd: descriptor for the good/bad block search pattern * @chip: create the table for a specific chip, -1 read all chips; applies only @@ -452,10 +458,10 @@ static int scan_block_fast(struct mtd_info *mtd, struct nand_bbt_descr *bd, * Create a bad block table by scanning the device for the given good/bad block * identify pattern. */ -static int create_bbt(struct mtd_info *mtd, uint8_t *buf, - struct nand_bbt_descr *bd, int chip) +static int create_bbt(struct nand_chip *this, uint8_t *buf, + struct nand_bbt_descr *bd, int chip) { - struct nand_chip *this = mtd_to_nand(mtd); + struct mtd_info *mtd = nand_to_mtd(this); int i, numblocks, numpages; int startblock; loff_t from; @@ -491,7 +497,7 @@ static int create_bbt(struct mtd_info *mtd, uint8_t *buf, BUG_ON(bd->options & NAND_BBT_NO_OOB); - ret = scan_block_fast(mtd, bd, from, buf, numpages); + ret = scan_block_fast(this, bd, from, buf, numpages); if (ret < 0) return ret; @@ -509,7 +515,7 @@ static int create_bbt(struct mtd_info *mtd, uint8_t *buf, /** * search_bbt - [GENERIC] scan the device for a specific bad block table - * @mtd: MTD device structure + * @this: NAND chip object * @buf: temporary buffer * @td: descriptor for the bad block table * @@ -522,9 +528,10 @@ static int create_bbt(struct mtd_info *mtd, uint8_t *buf, * * The bbt ident pattern resides in the oob area of the first page in a block. */ -static int search_bbt(struct mtd_info *mtd, uint8_t *buf, struct nand_bbt_descr *td) +static int search_bbt(struct nand_chip *this, uint8_t *buf, + struct nand_bbt_descr *td) { - struct nand_chip *this = mtd_to_nand(mtd); + struct mtd_info *mtd = nand_to_mtd(this); int i, chips; int startblock, block, dir; int scanlen = mtd->writesize + mtd->oobsize; @@ -561,11 +568,11 @@ static int search_bbt(struct mtd_info *mtd, uint8_t *buf, struct nand_bbt_descr loff_t offs = (loff_t)actblock << this->bbt_erase_shift; /* Read first page */ - scan_read(mtd, buf, offs, mtd->writesize, td); + scan_read(this, buf, offs, mtd->writesize, td); if (!check_pattern(buf, scanlen, mtd->writesize, td)) { td->pages[i] = actblock << blocktopage; if (td->options & NAND_BBT_VERSION) { - offs = bbt_get_ver_offs(mtd, td); + offs = bbt_get_ver_offs(this, td); td->version[i] = buf[offs]; } break; @@ -586,23 +593,23 @@ static int search_bbt(struct mtd_info *mtd, uint8_t *buf, struct nand_bbt_descr /** * search_read_bbts - [GENERIC] scan the device for bad block table(s) - * @mtd: MTD device structure + * @this: NAND chip object * @buf: temporary buffer * @td: descriptor for the bad block table * @md: descriptor for the bad block table mirror * * Search and read the bad block table(s). */ -static void search_read_bbts(struct mtd_info *mtd, uint8_t *buf, +static void search_read_bbts(struct nand_chip *this, uint8_t *buf, struct nand_bbt_descr *td, struct nand_bbt_descr *md) { /* Search the primary table */ - search_bbt(mtd, buf, td); + search_bbt(this, buf, td); /* Search the mirror table */ if (md) - search_bbt(mtd, buf, md); + search_bbt(this, buf, md); } /** @@ -700,7 +707,7 @@ static void mark_bbt_block_bad(struct nand_chip *this, /** * write_bbt - [GENERIC] (Re)write the bad block table - * @mtd: MTD device structure + * @this: NAND chip object * @buf: temporary buffer * @td: descriptor for the bad block table * @md: descriptor for the bad block table mirror @@ -708,11 +715,11 @@ static void mark_bbt_block_bad(struct nand_chip *this, * * (Re)write the bad block table. */ -static int write_bbt(struct mtd_info *mtd, uint8_t *buf, +static int write_bbt(struct nand_chip *this, uint8_t *buf, struct nand_bbt_descr *td, struct nand_bbt_descr *md, int chipsel) { - struct nand_chip *this = mtd_to_nand(mtd); + struct mtd_info *mtd = nand_to_mtd(this); struct erase_info einfo; int i, res, chip = 0; int bits, page, offs, numblocks, sft, sftmsk; @@ -862,9 +869,9 @@ static int write_bbt(struct mtd_info *mtd, uint8_t *buf, continue; } - res = scan_write_bbt(mtd, to, len, buf, - td->options & NAND_BBT_NO_OOB ? NULL : - &buf[len]); + res = scan_write_bbt(this, to, len, buf, + td->options & NAND_BBT_NO_OOB ? + NULL : &buf[len]); if (res < 0) { pr_warn("nand_bbt: error while writing BBT block %d\n", res); @@ -887,22 +894,21 @@ static int write_bbt(struct mtd_info *mtd, uint8_t *buf, /** * nand_memory_bbt - [GENERIC] create a memory based bad block table - * @mtd: MTD device structure + * @this: NAND chip object * @bd: descriptor for the good/bad block search pattern * * The function creates a memory based bbt by scanning the device for * manufacturer / software marked good / bad blocks. */ -static inline int nand_memory_bbt(struct mtd_info *mtd, struct nand_bbt_descr *bd) +static inline int nand_memory_bbt(struct nand_chip *this, + struct nand_bbt_descr *bd) { - struct nand_chip *this = mtd_to_nand(mtd); - - return create_bbt(mtd, this->data_buf, bd, -1); + return create_bbt(this, this->data_buf, bd, -1); } /** * check_create - [GENERIC] create and write bbt(s) if necessary - * @mtd: MTD device structure + * @this: the NAND device * @buf: temporary buffer * @bd: descriptor for the good/bad block search pattern * @@ -911,10 +917,10 @@ static inline int nand_memory_bbt(struct mtd_info *mtd, struct nand_bbt_descr *b * for the chip/device. Update is necessary if one of the tables is missing or * the version nr. of one table is less than the other. */ -static int check_create(struct mtd_info *mtd, uint8_t *buf, struct nand_bbt_descr *bd) +static int check_create(struct nand_chip *this, uint8_t *buf, + struct nand_bbt_descr *bd) { int i, chips, writeops, create, chipsel, res, res2; - struct nand_chip *this = mtd_to_nand(mtd); struct nand_bbt_descr *td = this->bbt_td; struct nand_bbt_descr *md = this->bbt_md; struct nand_bbt_descr *rd, *rd2; @@ -971,7 +977,7 @@ static int check_create(struct mtd_info *mtd, uint8_t *buf, struct nand_bbt_desc /* Create the table in memory by scanning the chip(s) */ if (!(this->bbt_options & NAND_BBT_CREATE_EMPTY)) - create_bbt(mtd, buf, bd, chipsel); + create_bbt(this, buf, bd, chipsel); td->version[i] = 1; if (md) @@ -980,7 +986,7 @@ static int check_create(struct mtd_info *mtd, uint8_t *buf, struct nand_bbt_desc /* Read back first? */ if (rd) { - res = read_abs_bbt(mtd, buf, rd, chipsel); + res = read_abs_bbt(this, buf, rd, chipsel); if (mtd_is_eccerr(res)) { /* Mark table as invalid */ rd->pages[i] = -1; @@ -991,7 +997,7 @@ static int check_create(struct mtd_info *mtd, uint8_t *buf, struct nand_bbt_desc } /* If they weren't versioned, read both */ if (rd2) { - res2 = read_abs_bbt(mtd, buf, rd2, chipsel); + res2 = read_abs_bbt(this, buf, rd2, chipsel); if (mtd_is_eccerr(res2)) { /* Mark table as invalid */ rd2->pages[i] = -1; @@ -1013,14 +1019,14 @@ static int check_create(struct mtd_info *mtd, uint8_t *buf, struct nand_bbt_desc /* Write the bad block table to the device? */ if ((writeops & 0x01) && (td->options & NAND_BBT_WRITE)) { - res = write_bbt(mtd, buf, td, md, chipsel); + res = write_bbt(this, buf, td, md, chipsel); if (res < 0) return res; } /* Write the mirror bad block table to the device? */ if ((writeops & 0x02) && md && (md->options & NAND_BBT_WRITE)) { - res = write_bbt(mtd, buf, md, td, chipsel); + res = write_bbt(this, buf, md, td, chipsel); if (res < 0) return res; } @@ -1030,15 +1036,15 @@ static int check_create(struct mtd_info *mtd, uint8_t *buf, struct nand_bbt_desc /** * mark_bbt_regions - [GENERIC] mark the bad block table regions - * @mtd: MTD device structure + * @this: the NAND device * @td: bad block table descriptor * * The bad block table regions are marked as "bad" to prevent accidental * erasures / writes. The regions are identified by the mark 0x02. */ -static void mark_bbt_region(struct mtd_info *mtd, struct nand_bbt_descr *td) +static void mark_bbt_region(struct nand_chip *this, struct nand_bbt_descr *td) { - struct nand_chip *this = mtd_to_nand(mtd); + struct mtd_info *mtd = nand_to_mtd(this); int i, j, chips, block, nrblocks, update; uint8_t oldval; @@ -1061,7 +1067,7 @@ static void mark_bbt_region(struct mtd_info *mtd, struct nand_bbt_descr *td) bbt_mark_entry(this, block, BBT_BLOCK_RESERVED); if ((oldval != BBT_BLOCK_RESERVED) && td->reserved_block_code) - nand_update_bbt(mtd, (loff_t)block << + nand_update_bbt(this, (loff_t)block << this->bbt_erase_shift); continue; } @@ -1083,22 +1089,22 @@ static void mark_bbt_region(struct mtd_info *mtd, struct nand_bbt_descr *td) * bbts. This should only happen once. */ if (update && td->reserved_block_code) - nand_update_bbt(mtd, (loff_t)(block - 1) << + nand_update_bbt(this, (loff_t)(block - 1) << this->bbt_erase_shift); } } /** * verify_bbt_descr - verify the bad block description - * @mtd: MTD device structure + * @this: the NAND device * @bd: the table to verify * * This functions performs a few sanity checks on the bad block description * table. */ -static void verify_bbt_descr(struct mtd_info *mtd, struct nand_bbt_descr *bd) +static void verify_bbt_descr(struct nand_chip *this, struct nand_bbt_descr *bd) { - struct nand_chip *this = mtd_to_nand(mtd); + struct mtd_info *mtd = nand_to_mtd(this); u32 pattern_len; u32 bits; u32 table_size; @@ -1138,7 +1144,7 @@ static void verify_bbt_descr(struct mtd_info *mtd, struct nand_bbt_descr *bd) /** * nand_scan_bbt - [NAND Interface] scan, find, read and maybe create bad block table(s) - * @mtd: MTD device structure + * @this: the NAND device * @bd: descriptor for the good/bad block search pattern * * The function checks, if a bad block table(s) is/are already available. If @@ -1148,9 +1154,9 @@ static void verify_bbt_descr(struct mtd_info *mtd, struct nand_bbt_descr *bd) * The bad block table memory is allocated here. It must be freed by calling * the nand_free_bbt function. */ -static int nand_scan_bbt(struct mtd_info *mtd, struct nand_bbt_descr *bd) +static int nand_scan_bbt(struct nand_chip *this, struct nand_bbt_descr *bd) { - struct nand_chip *this = mtd_to_nand(mtd); + struct mtd_info *mtd = nand_to_mtd(this); int len, res; uint8_t *buf; struct nand_bbt_descr *td = this->bbt_td; @@ -1170,14 +1176,14 @@ static int nand_scan_bbt(struct mtd_info *mtd, struct nand_bbt_descr *bd) * memory based bad block table. */ if (!td) { - if ((res = nand_memory_bbt(mtd, bd))) { + if ((res = nand_memory_bbt(this, bd))) { pr_err("nand_bbt: can't scan flash and build the RAM-based BBT\n"); goto err; } return 0; } - verify_bbt_descr(mtd, td); - verify_bbt_descr(mtd, md); + verify_bbt_descr(this, td); + verify_bbt_descr(this, md); /* Allocate a temporary buffer for one eraseblock incl. oob */ len = (1 << this->bbt_erase_shift); @@ -1190,20 +1196,20 @@ static int nand_scan_bbt(struct mtd_info *mtd, struct nand_bbt_descr *bd) /* Is the bbt at a given page? */ if (td->options & NAND_BBT_ABSPAGE) { - read_abs_bbts(mtd, buf, td, md); + read_abs_bbts(this, buf, td, md); } else { /* Search the bad block table using a pattern in oob */ - search_read_bbts(mtd, buf, td, md); + search_read_bbts(this, buf, td, md); } - res = check_create(mtd, buf, bd); + res = check_create(this, buf, bd); if (res) goto err; /* Prevent the bbt regions from erasing / writing */ - mark_bbt_region(mtd, td); + mark_bbt_region(this, td); if (md) - mark_bbt_region(mtd, md); + mark_bbt_region(this, md); vfree(buf); return 0; @@ -1216,14 +1222,14 @@ err: /** * nand_update_bbt - update bad block table(s) - * @mtd: MTD device structure + * @this: the NAND device * @offs: the offset of the newly marked block * * The function updates the bad block table(s). */ -static int nand_update_bbt(struct mtd_info *mtd, loff_t offs) +static int nand_update_bbt(struct nand_chip *this, loff_t offs) { - struct nand_chip *this = mtd_to_nand(mtd); + struct mtd_info *mtd = nand_to_mtd(this); int len, res = 0; int chip, chipsel; uint8_t *buf; @@ -1255,13 +1261,13 @@ static int nand_update_bbt(struct mtd_info *mtd, loff_t offs) /* Write the bad block table to the device? */ if (td->options & NAND_BBT_WRITE) { - res = write_bbt(mtd, buf, td, md, chipsel); + res = write_bbt(this, buf, td, md, chipsel); if (res < 0) goto out; } /* Write the mirror bad block table to the device? */ if (md && (md->options & NAND_BBT_WRITE)) { - res = write_bbt(mtd, buf, md, td, chipsel); + res = write_bbt(this, buf, md, td, chipsel); } out: @@ -1382,7 +1388,7 @@ int nand_create_bbt(struct nand_chip *this) return ret; } - return nand_scan_bbt(nand_to_mtd(this), this->badblock_pattern); + return nand_scan_bbt(this, this->badblock_pattern); } EXPORT_SYMBOL(nand_create_bbt); @@ -1433,7 +1439,6 @@ int nand_isbad_bbt(struct nand_chip *this, loff_t offs, int allowbbt) */ int nand_markbad_bbt(struct nand_chip *this, loff_t offs) { - struct mtd_info *mtd = nand_to_mtd(this); int block, ret = 0; block = (int)(offs >> this->bbt_erase_shift); @@ -1443,7 +1448,7 @@ int nand_markbad_bbt(struct nand_chip *this, loff_t offs) /* Update flash-based bad block table */ if (this->bbt_options & NAND_BBT_USE_FLASH) - ret = nand_update_bbt(mtd, offs); + ret = nand_update_bbt(this, offs); return ret; } diff --git a/drivers/mtd/nand/raw/nand_legacy.c b/drivers/mtd/nand/raw/nand_legacy.c index c5ddc86cd98c..bf0304c4a640 100644 --- a/drivers/mtd/nand/raw/nand_legacy.c +++ b/drivers/mtd/nand/raw/nand_legacy.c @@ -165,15 +165,14 @@ static void nand_read_buf16(struct nand_chip *chip, uint8_t *buf, int len) /** * panic_nand_wait_ready - [GENERIC] Wait for the ready pin after commands. - * @mtd: MTD device structure + * @chip: NAND chip object * @timeo: Timeout * * Helper function for nand_wait_ready used when needing to wait in interrupt * context. */ -static void panic_nand_wait_ready(struct mtd_info *mtd, unsigned long timeo) +static void panic_nand_wait_ready(struct nand_chip *chip, unsigned long timeo) { - struct nand_chip *chip = mtd_to_nand(mtd); int i; /* Wait for the device to get ready */ @@ -193,11 +192,10 @@ static void panic_nand_wait_ready(struct mtd_info *mtd, unsigned long timeo) */ void nand_wait_ready(struct nand_chip *chip) { - struct mtd_info *mtd = nand_to_mtd(chip); unsigned long timeo = 400; if (in_interrupt() || oops_in_progress) - return panic_nand_wait_ready(mtd, timeo); + return panic_nand_wait_ready(chip, timeo); /* Wait until command is processed or timeout occurs */ timeo = jiffies + msecs_to_jiffies(timeo); @@ -214,14 +212,13 @@ EXPORT_SYMBOL_GPL(nand_wait_ready); /** * nand_wait_status_ready - [GENERIC] Wait for the ready status after commands. - * @mtd: MTD device structure + * @chip: NAND chip object * @timeo: Timeout in ms * * Wait for status ready (i.e. command done) or timeout. */ -static void nand_wait_status_ready(struct mtd_info *mtd, unsigned long timeo) +static void nand_wait_status_ready(struct nand_chip *chip, unsigned long timeo) { - register struct nand_chip *chip = mtd_to_nand(mtd); int ret; timeo = jiffies + msecs_to_jiffies(timeo); @@ -321,7 +318,7 @@ static void nand_command(struct nand_chip *chip, unsigned int command, chip->legacy.cmd_ctrl(chip, NAND_CMD_NONE, NAND_NCE | NAND_CTRL_CHANGE); /* EZ-NAND can take upto 250ms as per ONFi v4.0 */ - nand_wait_status_ready(mtd, 250); + nand_wait_status_ready(chip, 250); return; /* This applies to read commands */ @@ -458,7 +455,7 @@ static void nand_command_lp(struct nand_chip *chip, unsigned int command, chip->legacy.cmd_ctrl(chip, NAND_CMD_NONE, NAND_NCE | NAND_CTRL_CHANGE); /* EZ-NAND can take upto 250ms as per ONFi v4.0 */ - nand_wait_status_ready(mtd, 250); + nand_wait_status_ready(chip, 250); return; case NAND_CMD_RNDOUT: @@ -525,7 +522,6 @@ EXPORT_SYMBOL(nand_get_set_features_notsupp); /** * nand_wait - [DEFAULT] wait until the command is done - * @mtd: MTD device structure * @chip: NAND chip structure * * Wait for command done. This applies to erase and program only. From 99f3351a6d6e03a9d307bba6797150a30e2e9d2e Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:04 +0100 Subject: [PATCH 313/356] mtd: rawnand: Reorganize code to avoid forward declarations Avoid forward declaration of nand_get_device(), nand_do_write_oob() and nand_update_bbt() by moving functions around. Signed-off-by: Boris Brezillon Tested-by: Janusz Krzysztofik Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/nand_base.c | 388 +++++++++++++++---------------- drivers/mtd/nand/raw/nand_bbt.c | 112 +++++---- 2 files changed, 246 insertions(+), 254 deletions(-) diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 2a50afbdeeeb..6d9de6949366 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -49,11 +49,6 @@ #include "internals.h" -static int nand_get_device(struct nand_chip *chip, int new_state); - -static int nand_do_write_oob(struct nand_chip *chip, loff_t to, - struct mtd_oob_ops *ops); - /* Define default oob placement schemes for large and small page devices */ static int nand_ooblayout_ecc_sp(struct mtd_info *mtd, int section, struct mtd_oob_region *oobregion) @@ -286,6 +281,197 @@ static int nand_block_bad(struct nand_chip *chip, loff_t ofs) return 0; } +static int nand_isbad_bbm(struct nand_chip *chip, loff_t ofs) +{ + if (chip->legacy.block_bad) + return chip->legacy.block_bad(chip, ofs); + + return nand_block_bad(chip, ofs); +} + +/** + * panic_nand_get_device - [GENERIC] Get chip for selected access + * @chip: the nand chip descriptor + * @new_state: the state which is requested + * + * Used when in panic, no locks are taken. + */ +static void panic_nand_get_device(struct nand_chip *chip, int new_state) +{ + /* Hardware controller shared among independent devices */ + chip->controller->active = chip; + chip->state = new_state; +} + +/** + * nand_get_device - [GENERIC] Get chip for selected access + * @chip: NAND chip structure + * @new_state: the state which is requested + * + * Get the device and lock it for exclusive access + */ +static int +nand_get_device(struct nand_chip *chip, int new_state) +{ + spinlock_t *lock = &chip->controller->lock; + wait_queue_head_t *wq = &chip->controller->wq; + DECLARE_WAITQUEUE(wait, current); +retry: + spin_lock(lock); + + /* Hardware controller shared among independent devices */ + if (!chip->controller->active) + chip->controller->active = chip; + + if (chip->controller->active == chip && chip->state == FL_READY) { + chip->state = new_state; + spin_unlock(lock); + return 0; + } + if (new_state == FL_PM_SUSPENDED) { + if (chip->controller->active->state == FL_PM_SUSPENDED) { + chip->state = FL_PM_SUSPENDED; + spin_unlock(lock); + return 0; + } + } + set_current_state(TASK_UNINTERRUPTIBLE); + add_wait_queue(wq, &wait); + spin_unlock(lock); + schedule(); + remove_wait_queue(wq, &wait); + goto retry; +} + +/** + * nand_check_wp - [GENERIC] check if the chip is write protected + * @chip: NAND chip object + * + * Check, if the device is write protected. The function expects, that the + * device is already selected. + */ +static int nand_check_wp(struct nand_chip *chip) +{ + u8 status; + int ret; + + /* Broken xD cards report WP despite being writable */ + if (chip->options & NAND_BROKEN_XD) + return 0; + + /* Check the WP bit */ + ret = nand_status_op(chip, &status); + if (ret) + return ret; + + return status & NAND_STATUS_WP ? 0 : 1; +} + +/** + * nand_fill_oob - [INTERN] Transfer client buffer to oob + * @oob: oob data buffer + * @len: oob data write length + * @ops: oob ops structure + */ +static uint8_t *nand_fill_oob(struct nand_chip *chip, uint8_t *oob, size_t len, + struct mtd_oob_ops *ops) +{ + struct mtd_info *mtd = nand_to_mtd(chip); + int ret; + + /* + * Initialise to all 0xFF, to avoid the possibility of left over OOB + * data from a previous OOB read. + */ + memset(chip->oob_poi, 0xff, mtd->oobsize); + + switch (ops->mode) { + + case MTD_OPS_PLACE_OOB: + case MTD_OPS_RAW: + memcpy(chip->oob_poi + ops->ooboffs, oob, len); + return oob + len; + + case MTD_OPS_AUTO_OOB: + ret = mtd_ooblayout_set_databytes(mtd, oob, chip->oob_poi, + ops->ooboffs, len); + BUG_ON(ret); + return oob + len; + + default: + BUG(); + } + return NULL; +} + +/** + * nand_do_write_oob - [MTD Interface] NAND write out-of-band + * @chip: NAND chip object + * @to: offset to write to + * @ops: oob operation description structure + * + * NAND write out-of-band. + */ +static int nand_do_write_oob(struct nand_chip *chip, loff_t to, + struct mtd_oob_ops *ops) +{ + struct mtd_info *mtd = nand_to_mtd(chip); + int chipnr, page, status, len; + + pr_debug("%s: to = 0x%08x, len = %i\n", + __func__, (unsigned int)to, (int)ops->ooblen); + + len = mtd_oobavail(mtd, ops); + + /* Do not allow write past end of page */ + if ((ops->ooboffs + ops->ooblen) > len) { + pr_debug("%s: attempt to write past end of page\n", + __func__); + return -EINVAL; + } + + chipnr = (int)(to >> chip->chip_shift); + + /* + * Reset the chip. Some chips (like the Toshiba TC5832DC found in one + * of my DiskOnChip 2000 test units) will clear the whole data page too + * if we don't do this. I have no clue why, but I seem to have 'fixed' + * it in the doc2000 driver in August 1999. dwmw2. + */ + nand_reset(chip, chipnr); + + chip->select_chip(chip, chipnr); + + /* Shift to get page */ + page = (int)(to >> chip->page_shift); + + /* Check, if it is write protected */ + if (nand_check_wp(chip)) { + chip->select_chip(chip, -1); + return -EROFS; + } + + /* Invalidate the page cache, if we write to the cached page */ + if (page == chip->pagebuf) + chip->pagebuf = -1; + + nand_fill_oob(chip, ops->oobbuf, ops->ooblen, ops); + + if (ops->mode == MTD_OPS_RAW) + status = chip->ecc.write_oob_raw(chip, page & chip->pagemask); + else + status = chip->ecc.write_oob(chip, page & chip->pagemask); + + chip->select_chip(chip, -1); + + if (status) + return status; + + ops->oobretlen = ops->ooblen; + + return 0; +} + /** * nand_default_block_markbad - [DEFAULT] mark a block bad via bad block marker * @chip: NAND chip object @@ -341,14 +527,6 @@ int nand_markbad_bbm(struct nand_chip *chip, loff_t ofs) return nand_default_block_markbad(chip, ofs); } -static int nand_isbad_bbm(struct nand_chip *chip, loff_t ofs) -{ - if (chip->legacy.block_bad) - return chip->legacy.block_bad(chip, ofs); - - return nand_block_bad(chip, ofs); -} - /** * nand_block_markbad_lowlevel - mark a block bad * @chip: NAND chip object @@ -401,30 +579,6 @@ static int nand_block_markbad_lowlevel(struct nand_chip *chip, loff_t ofs) return ret; } -/** - * nand_check_wp - [GENERIC] check if the chip is write protected - * @chip: NAND chip object - * - * Check, if the device is write protected. The function expects, that the - * device is already selected. - */ -static int nand_check_wp(struct nand_chip *chip) -{ - u8 status; - int ret; - - /* Broken xD cards report WP despite being writable */ - if (chip->options & NAND_BROKEN_XD) - return 0; - - /* Check the WP bit */ - ret = nand_status_op(chip, &status); - if (ret) - return ret; - - return status & NAND_STATUS_WP ? 0 : 1; -} - /** * nand_block_isreserved - [GENERIC] Check if a block is marked reserved. * @mtd: MTD device structure @@ -555,60 +709,6 @@ int nand_gpio_waitrdy(struct nand_chip *chip, struct gpio_desc *gpiod, }; EXPORT_SYMBOL_GPL(nand_gpio_waitrdy); -/** - * panic_nand_get_device - [GENERIC] Get chip for selected access - * @chip: the nand chip descriptor - * @new_state: the state which is requested - * - * Used when in panic, no locks are taken. - */ -static void panic_nand_get_device(struct nand_chip *chip, int new_state) -{ - /* Hardware controller shared among independent devices */ - chip->controller->active = chip; - chip->state = new_state; -} - -/** - * nand_get_device - [GENERIC] Get chip for selected access - * @chip: NAND chip structure - * @new_state: the state which is requested - * - * Get the device and lock it for exclusive access - */ -static int -nand_get_device(struct nand_chip *chip, int new_state) -{ - spinlock_t *lock = &chip->controller->lock; - wait_queue_head_t *wq = &chip->controller->wq; - DECLARE_WAITQUEUE(wait, current); -retry: - spin_lock(lock); - - /* Hardware controller shared among independent devices */ - if (!chip->controller->active) - chip->controller->active = chip; - - if (chip->controller->active == chip && chip->state == FL_READY) { - chip->state = new_state; - spin_unlock(lock); - return 0; - } - if (new_state == FL_PM_SUSPENDED) { - if (chip->controller->active->state == FL_PM_SUSPENDED) { - chip->state = FL_PM_SUSPENDED; - spin_unlock(lock); - return 0; - } - } - set_current_state(TASK_UNINTERRUPTIBLE); - add_wait_queue(wq, &wait); - spin_unlock(lock); - schedule(); - remove_wait_queue(wq, &wait); - goto retry; -} - /** * panic_nand_wait - [GENERIC] wait until the command is done * @chip: NAND chip structure @@ -3807,44 +3907,6 @@ static int nand_write_page(struct nand_chip *chip, uint32_t offset, return 0; } -/** - * 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 - */ -static uint8_t *nand_fill_oob(struct nand_chip *chip, uint8_t *oob, size_t len, - struct mtd_oob_ops *ops) -{ - struct mtd_info *mtd = nand_to_mtd(chip); - int ret; - - /* - * Initialise to all 0xFF, to avoid the possibility of left over OOB - * data from a previous OOB read. - */ - memset(chip->oob_poi, 0xff, mtd->oobsize); - - switch (ops->mode) { - - case MTD_OPS_PLACE_OOB: - case MTD_OPS_RAW: - memcpy(chip->oob_poi + ops->ooboffs, oob, len); - return oob + len; - - case MTD_OPS_AUTO_OOB: - ret = mtd_ooblayout_set_databytes(mtd, oob, chip->oob_poi, - ops->ooboffs, len); - BUG_ON(ret); - return oob + len; - - default: - BUG(); - } - return NULL; -} - #define NOTALIGNED(x) ((x & (chip->subpagesize - 1)) != 0) /** @@ -4012,74 +4074,6 @@ static int panic_nand_write(struct mtd_info *mtd, loff_t to, size_t len, return ret; } -/** - * nand_do_write_oob - [MTD Interface] NAND write out-of-band - * @chip: NAND chip object - * @to: offset to write to - * @ops: oob operation description structure - * - * NAND write out-of-band. - */ -static int nand_do_write_oob(struct nand_chip *chip, loff_t to, - struct mtd_oob_ops *ops) -{ - struct mtd_info *mtd = nand_to_mtd(chip); - int chipnr, page, status, len; - - pr_debug("%s: to = 0x%08x, len = %i\n", - __func__, (unsigned int)to, (int)ops->ooblen); - - len = mtd_oobavail(mtd, ops); - - /* Do not allow write past end of page */ - if ((ops->ooboffs + ops->ooblen) > len) { - pr_debug("%s: attempt to write past end of page\n", - __func__); - return -EINVAL; - } - - chipnr = (int)(to >> chip->chip_shift); - - /* - * Reset the chip. Some chips (like the Toshiba TC5832DC found in one - * of my DiskOnChip 2000 test units) will clear the whole data page too - * if we don't do this. I have no clue why, but I seem to have 'fixed' - * it in the doc2000 driver in August 1999. dwmw2. - */ - nand_reset(chip, chipnr); - - chip->select_chip(chip, chipnr); - - /* Shift to get page */ - page = (int)(to >> chip->page_shift); - - /* Check, if it is write protected */ - if (nand_check_wp(chip)) { - chip->select_chip(chip, -1); - return -EROFS; - } - - /* Invalidate the page cache, if we write to the cached page */ - if (page == chip->pagebuf) - chip->pagebuf = -1; - - nand_fill_oob(chip, ops->oobbuf, ops->ooblen, ops); - - if (ops->mode == MTD_OPS_RAW) - status = chip->ecc.write_oob_raw(chip, page & chip->pagemask); - else - status = chip->ecc.write_oob(chip, page & chip->pagemask); - - chip->select_chip(chip, -1); - - if (status) - return status; - - ops->oobretlen = ops->ooblen; - - return 0; -} - /** * nand_write_oob - [MTD Interface] NAND write data and/or out-of-band * @mtd: MTD device structure diff --git a/drivers/mtd/nand/raw/nand_bbt.c b/drivers/mtd/nand/raw/nand_bbt.c index b5e3b54cc767..1b722fe9213c 100644 --- a/drivers/mtd/nand/raw/nand_bbt.c +++ b/drivers/mtd/nand/raw/nand_bbt.c @@ -77,8 +77,6 @@ #define BBT_ENTRY_MASK 0x03 #define BBT_ENTRY_SHIFT 2 -static int nand_update_bbt(struct nand_chip *chip, loff_t offs); - static inline uint8_t bbt_get_entry(struct nand_chip *chip, int block) { uint8_t entry = chip->bbt[block >> BBT_ENTRY_SHIFT]; @@ -1034,6 +1032,61 @@ static int check_create(struct nand_chip *this, uint8_t *buf, return 0; } +/** + * nand_update_bbt - update bad block table(s) + * @this: the NAND device + * @offs: the offset of the newly marked block + * + * The function updates the bad block table(s). + */ +static int nand_update_bbt(struct nand_chip *this, loff_t offs) +{ + struct mtd_info *mtd = nand_to_mtd(this); + int len, res = 0; + int chip, chipsel; + uint8_t *buf; + struct nand_bbt_descr *td = this->bbt_td; + struct nand_bbt_descr *md = this->bbt_md; + + if (!this->bbt || !td) + return -EINVAL; + + /* Allocate a temporary buffer for one eraseblock incl. oob */ + len = (1 << this->bbt_erase_shift); + len += (len >> this->page_shift) * mtd->oobsize; + buf = kmalloc(len, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + /* Do we have a bbt per chip? */ + if (td->options & NAND_BBT_PERCHIP) { + chip = (int)(offs >> this->chip_shift); + chipsel = chip; + } else { + chip = 0; + chipsel = -1; + } + + td->version[chip]++; + if (md) + md->version[chip]++; + + /* Write the bad block table to the device? */ + if (td->options & NAND_BBT_WRITE) { + res = write_bbt(this, buf, td, md, chipsel); + if (res < 0) + goto out; + } + /* Write the mirror bad block table to the device? */ + if (md && (md->options & NAND_BBT_WRITE)) { + res = write_bbt(this, buf, md, td, chipsel); + } + + out: + kfree(buf); + return res; +} + /** * mark_bbt_regions - [GENERIC] mark the bad block table regions * @this: the NAND device @@ -1220,61 +1273,6 @@ err: return res; } -/** - * nand_update_bbt - update bad block table(s) - * @this: the NAND device - * @offs: the offset of the newly marked block - * - * The function updates the bad block table(s). - */ -static int nand_update_bbt(struct nand_chip *this, loff_t offs) -{ - struct mtd_info *mtd = nand_to_mtd(this); - int len, res = 0; - int chip, chipsel; - uint8_t *buf; - struct nand_bbt_descr *td = this->bbt_td; - struct nand_bbt_descr *md = this->bbt_md; - - if (!this->bbt || !td) - return -EINVAL; - - /* Allocate a temporary buffer for one eraseblock incl. oob */ - len = (1 << this->bbt_erase_shift); - len += (len >> this->page_shift) * mtd->oobsize; - buf = kmalloc(len, GFP_KERNEL); - if (!buf) - return -ENOMEM; - - /* Do we have a bbt per chip? */ - if (td->options & NAND_BBT_PERCHIP) { - chip = (int)(offs >> this->chip_shift); - chipsel = chip; - } else { - chip = 0; - chipsel = -1; - } - - td->version[chip]++; - if (md) - md->version[chip]++; - - /* Write the bad block table to the device? */ - if (td->options & NAND_BBT_WRITE) { - res = write_bbt(this, buf, td, md, chipsel); - if (res < 0) - goto out; - } - /* Write the mirror bad block table to the device? */ - if (md && (md->options & NAND_BBT_WRITE)) { - res = write_bbt(this, buf, md, td, chipsel); - } - - out: - kfree(buf); - return res; -} - /* * Define some generic bad / good block scan pattern which are used * while scanning a device for factory marked good / bad blocks. From 996852a97bc684d7771c692364705f0aaf423ba9 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:05 +0100 Subject: [PATCH 314/356] mtd: rawnand: legacy: Drop useless test in nand_legacy_set_defaults() nand_legacy_set_defaults() returns directly if chip->exec_op != NULL, no need to test !chip->exec_op after that. Signed-off-by: Boris Brezillon Tested-by: Janusz Krzysztofik Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/nand_legacy.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/nand/raw/nand_legacy.c b/drivers/mtd/nand/raw/nand_legacy.c index bf0304c4a640..f76b9356ba9c 100644 --- a/drivers/mtd/nand/raw/nand_legacy.c +++ b/drivers/mtd/nand/raw/nand_legacy.c @@ -585,7 +585,7 @@ void nand_legacy_set_defaults(struct nand_chip *chip) chip->legacy.chip_delay = 20; /* check, if a user supplied command function given */ - if (!chip->legacy.cmdfunc && !chip->exec_op) + if (!chip->legacy.cmdfunc) chip->legacy.cmdfunc = nand_command; /* check, if a user supplied wait function given */ From 1f2d29e634b3e7abc7b62adf6bb4a676615c02ef Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:06 +0100 Subject: [PATCH 315/356] mtd: rawnand: Move nand_exec_op() to internal.h nand_exec_op() is only used by core code (nand_xxx.c files). Let's move this inline function in drivers/mtd/nand/raw/internals.h. Signed-off-by: Boris Brezillon Tested-by: Janusz Krzysztofik Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/internals.h | 9 +++++++++ include/linux/mtd/rawnand.h | 9 --------- 2 files changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/mtd/nand/raw/internals.h b/drivers/mtd/nand/raw/internals.h index 04c2cf74eff3..6e2f61fbc5f0 100644 --- a/drivers/mtd/nand/raw/internals.h +++ b/drivers/mtd/nand/raw/internals.h @@ -95,6 +95,15 @@ void nand_decode_ext_id(struct nand_chip *chip); void panic_nand_wait(struct nand_chip *chip, unsigned long timeo); void sanitize_string(uint8_t *s, size_t len); +static inline int nand_exec_op(struct nand_chip *chip, + const struct nand_operation *op) +{ + if (!chip->exec_op) + return -ENOTSUPP; + + return chip->exec_op(chip, op, false); +} + /* BBT functions */ int nand_markbad_bbt(struct nand_chip *chip, loff_t offs); int nand_isreserved_bbt(struct nand_chip *chip, loff_t offs); diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 4e91a70ede10..85dd89abcd22 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1098,15 +1098,6 @@ struct nand_chip { } manufacturer; }; -static inline int nand_exec_op(struct nand_chip *chip, - const struct nand_operation *op) -{ - if (!chip->exec_op) - return -ENOTSUPP; - - return chip->exec_op(chip, op, false); -} - extern const struct mtd_ooblayout_ops nand_ooblayout_sp_ops; extern const struct mtd_ooblayout_ops nand_ooblayout_lp_ops; From 336058c8f4c2c7991427304c8bde05acef156054 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:07 +0100 Subject: [PATCH 316/356] mtd: rawnand: Remove unused NAND_CONTROLLER_ALLOC flag Looks like NAND_CONTROLLER_ALLOC has been introduced a long time ago back when the dummy nand_hw_ctrl object was dynamically allocated instead of being embedded in nand_chip. We can safely get rid of this unused flag. Signed-off-by: Boris Brezillon Tested-by: Janusz Krzysztofik Signed-off-by: Miquel Raynal --- include/linux/mtd/rawnand.h | 4 ---- 1 file changed, 4 deletions(-) diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 85dd89abcd22..2a3dd3e633f1 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -203,10 +203,6 @@ enum nand_ecc_algo { */ #define NAND_IS_BOOT_MEDIUM 0x00400000 -/* Options set by nand scan */ -/* Nand scan has allocated controller struct */ -#define NAND_CONTROLLER_ALLOC 0x80000000 - /* Cell info constants */ #define NAND_CI_CHIPNR_MSK 0x03 #define NAND_CI_CELLTYPE_MSK 0x0C From fbb080a1fcad340a6337d850ce4ff21f84635b03 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:08 +0100 Subject: [PATCH 317/356] mtd: rawnand: ams-delta: Allow this driver to be compiled when COMPILE_TEST=y Drop the asm and mach headers inclusion and allow this driver to be compiled when COMPILE_TEST=y in order to increase compile-test coverage. Signed-off-by: Boris Brezillon Tested-by: Janusz Krzysztofik Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/Kconfig | 2 +- drivers/mtd/nand/raw/ams-delta.c | 7 ++----- 2 files changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig index c7efc31384d5..1a55d3e3d4c5 100644 --- a/drivers/mtd/nand/raw/Kconfig +++ b/drivers/mtd/nand/raw/Kconfig @@ -70,7 +70,7 @@ config MTD_NAND_GPIO config MTD_NAND_AMS_DELTA tristate "NAND Flash device on Amstrad E3" - depends on MACH_AMS_DELTA + depends on MACH_AMS_DELTA || COMPILE_TEST default y help Support for NAND flash on Amstrad E3 (Delta). diff --git a/drivers/mtd/nand/raw/ams-delta.c b/drivers/mtd/nand/raw/ams-delta.c index 9ca70aab199d..a7c0e3af3b11 100644 --- a/drivers/mtd/nand/raw/ams-delta.c +++ b/drivers/mtd/nand/raw/ams-delta.c @@ -21,15 +21,12 @@ #include #include #include +#include #include #include #include #include - -#include -#include - -#include +#include /* * MTD structure for E3 (Delta) From 4857393d5655b93e0e7368c12bbcf1d79883155c Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:09 +0100 Subject: [PATCH 318/356] mtd: rawnand: ams-delta: Add an SPDX tag to replace the license text Add an SPDX GPL-2.0 tag and update MODULE_LICENSE() to match the license text. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/ams-delta.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/mtd/nand/raw/ams-delta.c b/drivers/mtd/nand/raw/ams-delta.c index a7c0e3af3b11..4862d4df1a15 100644 --- a/drivers/mtd/nand/raw/ams-delta.c +++ b/drivers/mtd/nand/raw/ams-delta.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2006 Jonathan McDowell * @@ -8,10 +9,6 @@ * Converted to platform driver by Janusz Krzysztofik * Partially stolen from plat_nand.c * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * Overview: * This is a device driver for the NAND flash device found on the * Amstrad E3 (Delta). @@ -332,6 +329,6 @@ static struct platform_driver ams_delta_nand_driver = { module_platform_driver(ams_delta_nand_driver); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Jonathan McDowell "); MODULE_DESCRIPTION("Glue layer for NAND flash on Amstrad E3 (Delta)"); From d54445d664a1324785f40f6fd4240b7a024f4b19 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:10 +0100 Subject: [PATCH 319/356] mtd: rawnand: ams-delta: Fix various coding style issues Most of them were reported by checkpatch: * s/u_char/u8/ * remove unneeded blank lines * don't print warning messages when devm_kzalloc() fails * Use ! instead of == NULL * Remove invalid comment Signed-off-by: Boris Brezillon Tested-by: Janusz Krzysztofik Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/ams-delta.c | 23 ++++++++--------------- 1 file changed, 8 insertions(+), 15 deletions(-) diff --git a/drivers/mtd/nand/raw/ams-delta.c b/drivers/mtd/nand/raw/ams-delta.c index 4862d4df1a15..07ee513318ec 100644 --- a/drivers/mtd/nand/raw/ams-delta.c +++ b/drivers/mtd/nand/raw/ams-delta.c @@ -28,7 +28,6 @@ /* * MTD structure for E3 (Delta) */ - struct ams_delta_nand { struct nand_chip nand_chip; struct gpio_desc *gpiod_rdy; @@ -67,7 +66,7 @@ static const struct mtd_partition partition_info[] = { .size = 3 * SZ_256K }, }; -static void ams_delta_io_write(struct ams_delta_nand *priv, u_char byte) +static void ams_delta_io_write(struct ams_delta_nand *priv, u8 byte) { writew(byte, priv->io_base + OMAP_MPUIO_OUTPUT); gpiod_set_value(priv->gpiod_nwe, 0); @@ -75,9 +74,9 @@ static void ams_delta_io_write(struct ams_delta_nand *priv, u_char byte) gpiod_set_value(priv->gpiod_nwe, 1); } -static u_char ams_delta_io_read(struct ams_delta_nand *priv) +static u8 ams_delta_io_read(struct ams_delta_nand *priv) { - u_char res; + u8 res; gpiod_set_value(priv->gpiod_nre, 0); ndelay(40); @@ -93,7 +92,7 @@ static void ams_delta_dir_input(struct ams_delta_nand *priv, bool in) priv->data_in = in; } -static void ams_delta_write_buf(struct ams_delta_nand *priv, const u_char *buf, +static void ams_delta_write_buf(struct ams_delta_nand *priv, const u8 *buf, int len) { int i; @@ -105,8 +104,7 @@ static void ams_delta_write_buf(struct ams_delta_nand *priv, const u_char *buf, ams_delta_io_write(priv, buf[i]); } -static void ams_delta_read_buf(struct ams_delta_nand *priv, u_char *buf, - int len) +static void ams_delta_read_buf(struct ams_delta_nand *priv, u8 *buf, int len) { int i; @@ -138,7 +136,6 @@ static int ams_delta_exec_op(struct nand_chip *this, return 0; for (instr = op->instrs; instr < op->instrs + op->ninstrs; instr++) { - switch (instr->type) { case NAND_OP_CMD_INSTR: gpiod_set_value(priv->gpiod_cle, 1); @@ -179,7 +176,6 @@ static int ams_delta_exec_op(struct nand_chip *this, return ret; } - /* * Main initialization routine */ @@ -198,10 +194,9 @@ static int ams_delta_init(struct platform_device *pdev) /* Allocate memory for MTD device structure and private data */ priv = devm_kzalloc(&pdev->dev, sizeof(struct ams_delta_nand), GFP_KERNEL); - if (!priv) { - pr_warn("Unable to allocate E3 NAND MTD device structure.\n"); + if (!priv) return -ENOMEM; - } + this = &priv->nand_chip; mtd = nand_to_mtd(this); @@ -212,9 +207,8 @@ static int ams_delta_init(struct platform_device *pdev) * it should have been already requested from the * gpio-omap driver and requesting it again would fail. */ - io_base = ioremap(res->start, resource_size(res)); - if (io_base == NULL) { + if (!io_base) { dev_err(&pdev->dev, "ioremap failed\n"); err = -EIO; goto out_free; @@ -223,7 +217,6 @@ static int ams_delta_init(struct platform_device *pdev) priv->io_base = io_base; nand_set_controller_data(this, priv); - /* Set address of NAND IO lines */ this->select_chip = ams_delta_select_chip; this->exec_op = ams_delta_exec_op; From 8bbc3c0850d0668ac7cf0f5b129ffae8c810247f Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:11 +0100 Subject: [PATCH 320/356] mtd: rawnand: ams-delta: cleanup ams_delta_init() error path Remove unused labels, rename out_mtd into err_unmap to make it clearer and return 0 instead of using a goto out at the end of the registration procedure. Signed-off-by: Boris Brezillon Tested-by: Janusz Krzysztofik Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/ams-delta.c | 26 ++++++++++++-------------- 1 file changed, 12 insertions(+), 14 deletions(-) diff --git a/drivers/mtd/nand/raw/ams-delta.c b/drivers/mtd/nand/raw/ams-delta.c index 07ee513318ec..0fc7563fba10 100644 --- a/drivers/mtd/nand/raw/ams-delta.c +++ b/drivers/mtd/nand/raw/ams-delta.c @@ -210,8 +210,7 @@ static int ams_delta_init(struct platform_device *pdev) io_base = ioremap(res->start, resource_size(res)); if (!io_base) { dev_err(&pdev->dev, "ioremap failed\n"); - err = -EIO; - goto out_free; + return -EIO; } priv->io_base = io_base; @@ -224,7 +223,7 @@ static int ams_delta_init(struct platform_device *pdev) if (IS_ERR(priv->gpiod_rdy)) { err = PTR_ERR(priv->gpiod_rdy); dev_warn(&pdev->dev, "RDY GPIO request failed (%d)\n", err); - goto out_mtd; + goto err_unmap; } this->ecc.mode = NAND_ECC_SOFT; @@ -237,42 +236,42 @@ static int ams_delta_init(struct platform_device *pdev) if (IS_ERR(priv->gpiod_nwp)) { err = PTR_ERR(priv->gpiod_nwp); dev_err(&pdev->dev, "NWP GPIO request failed (%d)\n", err); - goto out_mtd; + goto err_unmap; } priv->gpiod_nce = devm_gpiod_get(&pdev->dev, "nce", GPIOD_OUT_HIGH); if (IS_ERR(priv->gpiod_nce)) { err = PTR_ERR(priv->gpiod_nce); dev_err(&pdev->dev, "NCE GPIO request failed (%d)\n", err); - goto out_mtd; + goto err_unmap; } priv->gpiod_nre = devm_gpiod_get(&pdev->dev, "nre", GPIOD_OUT_HIGH); if (IS_ERR(priv->gpiod_nre)) { err = PTR_ERR(priv->gpiod_nre); dev_err(&pdev->dev, "NRE GPIO request failed (%d)\n", err); - goto out_mtd; + goto err_unmap; } priv->gpiod_nwe = devm_gpiod_get(&pdev->dev, "nwe", GPIOD_OUT_HIGH); if (IS_ERR(priv->gpiod_nwe)) { err = PTR_ERR(priv->gpiod_nwe); dev_err(&pdev->dev, "NWE GPIO request failed (%d)\n", err); - goto out_mtd; + goto err_unmap; } priv->gpiod_ale = devm_gpiod_get(&pdev->dev, "ale", GPIOD_OUT_LOW); if (IS_ERR(priv->gpiod_ale)) { err = PTR_ERR(priv->gpiod_ale); dev_err(&pdev->dev, "ALE GPIO request failed (%d)\n", err); - goto out_mtd; + goto err_unmap; } priv->gpiod_cle = devm_gpiod_get(&pdev->dev, "cle", GPIOD_OUT_LOW); if (IS_ERR(priv->gpiod_cle)) { err = PTR_ERR(priv->gpiod_cle); dev_err(&pdev->dev, "CLE GPIO request failed (%d)\n", err); - goto out_mtd; + goto err_unmap; } /* Initialize data port direction to a known state */ @@ -281,17 +280,16 @@ static int ams_delta_init(struct platform_device *pdev) /* Scan to find existence of the device */ err = nand_scan(this, 1); if (err) - goto out_mtd; + goto err_unmap; /* Register the partitions */ mtd_device_register(mtd, partition_info, ARRAY_SIZE(partition_info)); - goto out; + return 0; - out_mtd: +err_unmap: iounmap(io_base); -out_free: - out: + return err; } From 876ba603c9e0fa7885f89a35ed221792caea8034 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:12 +0100 Subject: [PATCH 321/356] mtd: rawnand: ams-delta: Check mtd_device_register() return code mtd_device_register() can fail, and when it does we should propagate the error and cleanup what has been done before. Signed-off-by: Boris Brezillon Tested-by: Janusz Krzysztofik Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/ams-delta.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/nand/raw/ams-delta.c b/drivers/mtd/nand/raw/ams-delta.c index 0fc7563fba10..c59672a92832 100644 --- a/drivers/mtd/nand/raw/ams-delta.c +++ b/drivers/mtd/nand/raw/ams-delta.c @@ -283,10 +283,16 @@ static int ams_delta_init(struct platform_device *pdev) goto err_unmap; /* Register the partitions */ - mtd_device_register(mtd, partition_info, ARRAY_SIZE(partition_info)); + err = mtd_device_register(mtd, partition_info, + ARRAY_SIZE(partition_info)); + if (err) + goto err_nand_cleanup; return 0; +err_nand_cleanup: + nand_cleanup(this); + err_unmap: iounmap(io_base); From 9fd6bcffe741cfd237bb4a310e8cc82457a6c541 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:13 +0100 Subject: [PATCH 322/356] mtd: rawnand: ams-delta: Explicitly inherit from nand_controller All NAND objects are supposed to inherit from nand_controller. The framework is providing a dummy controller object, but we're moving away from this approach in favor of explicit inheritance. Signed-off-by: Boris Brezillon Tested-by: Janusz Krzysztofik Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/ams-delta.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/mtd/nand/raw/ams-delta.c b/drivers/mtd/nand/raw/ams-delta.c index c59672a92832..34b83edb965c 100644 --- a/drivers/mtd/nand/raw/ams-delta.c +++ b/drivers/mtd/nand/raw/ams-delta.c @@ -29,6 +29,7 @@ * MTD structure for E3 (Delta) */ struct ams_delta_nand { + struct nand_controller base; struct nand_chip nand_chip; struct gpio_desc *gpiod_rdy; struct gpio_desc *gpiod_nce; @@ -277,6 +278,10 @@ static int ams_delta_init(struct platform_device *pdev) /* Initialize data port direction to a known state */ ams_delta_dir_input(priv, true); + /* Initialize the NAND controller object embedded in ams_delta_nand. */ + nand_controller_init(&priv->base); + this->controller = &priv->base; + /* Scan to find existence of the device */ err = nand_scan(this, 1); if (err) From 1d0178593d148e88d2ac1e3f09c7f7eb1c20796b Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:14 +0100 Subject: [PATCH 323/356] mtd: rawnand: Add nand_[de]select_target() helpers Add a wrapper to prevent drivers and core code from directly calling the ->select_chip hook which we are about to deprecate. Signed-off-by: Boris Brezillon Tested-by: Janusz Krzysztofik Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c | 23 ++-- drivers/mtd/nand/raw/jz4740_nand.c | 4 +- drivers/mtd/nand/raw/nand_base.c | 120 ++++++++++++++------- drivers/mtd/nand/raw/r852.c | 4 +- include/linux/mtd/rawnand.h | 5 +- 5 files changed, 104 insertions(+), 52 deletions(-) diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c index 94c2b7525c85..302ddd3d4a5f 100644 --- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c +++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c @@ -1549,7 +1549,7 @@ static int gpmi_block_markbad(struct nand_chip *chip, loff_t ofs) int column, page, chipnr; chipnr = (int)(ofs >> chip->chip_shift); - chip->select_chip(chip, chipnr); + nand_select_target(chip, chipnr); column = !GPMI_IS_MX23(this) ? mtd->writesize : 0; @@ -1562,7 +1562,7 @@ static int gpmi_block_markbad(struct nand_chip *chip, loff_t ofs) ret = nand_prog_page_op(chip, page, column, block_mark, 1); - chip->select_chip(chip, -1); + nand_deselect_target(chip); return ret; } @@ -1610,7 +1610,7 @@ static int mx23_check_transcription_stamp(struct gpmi_nand_data *this) search_area_size_in_strides = 1 << rom_geo->search_area_stride_exponent; saved_chip_number = this->current_chip; - chip->select_chip(chip, 0); + nand_select_target(chip, 0); /* * Loop through the first search area, looking for the NCB fingerprint. @@ -1638,7 +1638,10 @@ static int mx23_check_transcription_stamp(struct gpmi_nand_data *this) } - chip->select_chip(chip, saved_chip_number); + if (saved_chip_number >= 0) + nand_select_target(chip, saved_chip_number); + else + nand_deselect_target(chip); if (found_an_ncb_fingerprint) dev_dbg(dev, "\tFound a fingerprint\n"); @@ -1681,7 +1684,7 @@ static int mx23_write_transcription_stamp(struct gpmi_nand_data *this) /* Select chip 0. */ saved_chip_number = this->current_chip; - chip->select_chip(chip, 0); + nand_select_target(chip, 0); /* Loop over blocks in the first search area, erasing them. */ dev_dbg(dev, "Erasing the search area...\n"); @@ -1713,7 +1716,11 @@ static int mx23_write_transcription_stamp(struct gpmi_nand_data *this) } /* Deselect chip 0. */ - chip->select_chip(chip, saved_chip_number); + if (saved_chip_number >= 0) + nand_select_target(chip, saved_chip_number); + else + nand_deselect_target(chip); + return 0; } @@ -1762,10 +1769,10 @@ static int mx23_boot_init(struct gpmi_nand_data *this) byte = block << chip->phys_erase_shift; /* Send the command to read the conventional block mark. */ - chip->select_chip(chip, chipnr); + nand_select_target(chip, chipnr); nand_read_page_op(chip, page, mtd->writesize, NULL, 0); block_mark = chip->legacy.read_byte(chip); - chip->select_chip(chip, -1); + nand_deselect_target(chip); /* * Check if the block is marked bad. If so, we need to mark it diff --git a/drivers/mtd/nand/raw/jz4740_nand.c b/drivers/mtd/nand/raw/jz4740_nand.c index fb59cfca11a7..d271004f16b0 100644 --- a/drivers/mtd/nand/raw/jz4740_nand.c +++ b/drivers/mtd/nand/raw/jz4740_nand.c @@ -335,14 +335,14 @@ static int jz_nand_detect_bank(struct platform_device *pdev, goto notfound_id; /* Retrieve the IDs from the first chip. */ - chip->select_chip(chip, 0); + nand_select_target(chip, 0); nand_reset_op(chip); nand_readid_op(chip, 0, id, sizeof(id)); *nand_maf_id = id[0]; *nand_dev_id = id[1]; } else { /* Detect additional chip. */ - chip->select_chip(chip, chipnr); + nand_select_target(chip, chipnr); nand_reset_op(chip); nand_readid_op(chip, 0, id, sizeof(id)); if (*nand_maf_id != id[0] || *nand_dev_id != id[1]) { diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 6d9de6949366..f85e6f3b1b2f 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -228,6 +228,41 @@ static int check_offs_len(struct nand_chip *chip, loff_t ofs, uint64_t len) return ret; } +/** + * nand_select_target() - Select a NAND target (A.K.A. die) + * @chip: NAND chip object + * @cs: the CS line to select. Note that this CS id is always from the chip + * PoV, not the controller one + * + * Select a NAND target so that further operations executed on @chip go to the + * selected NAND target. + */ +void nand_select_target(struct nand_chip *chip, unsigned int cs) +{ + /* + * cs should always lie between 0 and chip->numchips, when that's not + * the case it's a bug and the caller should be fixed. + */ + if (WARN_ON(cs > chip->numchips)) + return; + + chip->select_chip(chip, cs); +} +EXPORT_SYMBOL_GPL(nand_select_target); + +/** + * nand_deselect_target() - Deselect the currently selected target + * @chip: NAND chip object + * + * Deselect the currently selected NAND target. The result of operations + * executed on @chip after the target has been deselected is undefined. + */ +void nand_deselect_target(struct nand_chip *chip) +{ + chip->select_chip(chip, -1); +} +EXPORT_SYMBOL_GPL(nand_deselect_target); + /** * nand_release_device - [GENERIC] release chip * @chip: NAND chip object @@ -440,14 +475,14 @@ static int nand_do_write_oob(struct nand_chip *chip, loff_t to, */ nand_reset(chip, chipnr); - chip->select_chip(chip, chipnr); + nand_select_target(chip, chipnr); /* Shift to get page */ page = (int)(to >> chip->page_shift); /* Check, if it is write protected */ if (nand_check_wp(chip)) { - chip->select_chip(chip, -1); + nand_deselect_target(chip); return -EROFS; } @@ -462,7 +497,7 @@ static int nand_do_write_oob(struct nand_chip *chip, loff_t to, else status = chip->ecc.write_oob(chip, page & chip->pagemask); - chip->select_chip(chip, -1); + nand_deselect_target(chip); if (status) return status; @@ -816,10 +851,10 @@ static int nand_setup_data_interface(struct nand_chip *chip, int chipnr) /* Change the mode on the chip side (if supported by the NAND chip) */ if (nand_supports_set_features(chip, ONFI_FEATURE_ADDR_TIMING_MODE)) { - chip->select_chip(chip, chipnr); + nand_select_target(chip, chipnr); ret = nand_set_features(chip, ONFI_FEATURE_ADDR_TIMING_MODE, tmode_param); - chip->select_chip(chip, -1); + nand_deselect_target(chip); if (ret) return ret; } @@ -834,10 +869,10 @@ static int nand_setup_data_interface(struct nand_chip *chip, int chipnr) return 0; memset(tmode_param, 0, ONFI_SUBFEATURE_PARAM_LEN); - chip->select_chip(chip, chipnr); + nand_select_target(chip, chipnr); ret = nand_get_features(chip, ONFI_FEATURE_ADDR_TIMING_MODE, tmode_param); - chip->select_chip(chip, -1); + nand_deselect_target(chip); if (ret) goto err_reset_chip; @@ -855,9 +890,9 @@ err_reset_chip: * timing mode. */ nand_reset_data_interface(chip, chipnr); - chip->select_chip(chip, chipnr); + nand_select_target(chip, chipnr); nand_reset_op(chip); - chip->select_chip(chip, -1); + nand_deselect_target(chip); return ret; } @@ -2345,11 +2380,12 @@ int nand_reset(struct nand_chip *chip, int chipnr) /* * The CS line has to be released before we can apply the new NAND - * interface settings, hence this weird ->select_chip() dance. + * interface settings, hence this weird nand_select_target() + * nand_deselect_target() dance. */ - chip->select_chip(chip, chipnr); + nand_select_target(chip, chipnr); ret = nand_reset_op(chip); - chip->select_chip(chip, -1); + nand_deselect_target(chip); if (ret) return ret; @@ -3133,7 +3169,7 @@ static int nand_do_read_ops(struct nand_chip *chip, loff_t from, bool ecc_fail = false; chipnr = (int)(from >> chip->chip_shift); - chip->select_chip(chip, chipnr); + nand_select_target(chip, chipnr); realpage = (int)(from >> chip->page_shift); page = realpage & chip->pagemask; @@ -3264,11 +3300,11 @@ read_retry: /* Check, if we cross a chip boundary */ if (!page) { chipnr++; - chip->select_chip(chip, -1); - chip->select_chip(chip, chipnr); + nand_deselect_target(chip); + nand_select_target(chip, chipnr); } } - chip->select_chip(chip, -1); + nand_deselect_target(chip); ops->retlen = ops->len - (size_t) readlen; if (oob) @@ -3465,7 +3501,7 @@ static int nand_do_read_oob(struct nand_chip *chip, loff_t from, len = mtd_oobavail(mtd, ops); chipnr = (int)(from >> chip->chip_shift); - chip->select_chip(chip, chipnr); + nand_select_target(chip, chipnr); /* Shift to get page */ realpage = (int)(from >> chip->page_shift); @@ -3498,11 +3534,11 @@ static int nand_do_read_oob(struct nand_chip *chip, loff_t from, /* Check, if we cross a chip boundary */ if (!page) { chipnr++; - chip->select_chip(chip, -1); - chip->select_chip(chip, chipnr); + nand_deselect_target(chip); + nand_select_target(chip, chipnr); } } - chip->select_chip(chip, -1); + nand_deselect_target(chip); ops->oobretlen = ops->ooblen - readlen; @@ -3946,7 +3982,7 @@ static int nand_do_write_ops(struct nand_chip *chip, loff_t to, column = to & (mtd->writesize - 1); chipnr = (int)(to >> chip->chip_shift); - chip->select_chip(chip, chipnr); + nand_select_target(chip, chipnr); /* Check, if it is write protected */ if (nand_check_wp(chip)) { @@ -4022,8 +4058,8 @@ static int nand_do_write_ops(struct nand_chip *chip, loff_t to, /* Check, if we cross a chip boundary */ if (!page) { chipnr++; - chip->select_chip(chip, -1); - chip->select_chip(chip, chipnr); + nand_deselect_target(chip); + nand_select_target(chip, chipnr); } } @@ -4032,7 +4068,7 @@ static int nand_do_write_ops(struct nand_chip *chip, loff_t to, ops->oobretlen = ops->ooblen; err_out: - chip->select_chip(chip, -1); + nand_deselect_target(chip); return ret; } @@ -4058,7 +4094,7 @@ static int panic_nand_write(struct mtd_info *mtd, loff_t to, size_t len, /* Grab the device */ panic_nand_get_device(chip, FL_WRITING); - chip->select_chip(chip, chipnr); + nand_select_target(chip, chipnr); /* Wait for the device to get ready */ panic_nand_wait(chip, 400); @@ -4171,7 +4207,7 @@ int nand_erase_nand(struct nand_chip *chip, struct erase_info *instr, pages_per_block = 1 << (chip->phys_erase_shift - chip->page_shift); /* Select the NAND device */ - chip->select_chip(chip, chipnr); + nand_select_target(chip, chipnr); /* Check, if it is write protected */ if (nand_check_wp(chip)) { @@ -4225,8 +4261,8 @@ int nand_erase_nand(struct nand_chip *chip, struct erase_info *instr, /* Check, if we cross a chip boundary */ if (len && !(page & chip->pagemask)) { chipnr++; - chip->select_chip(chip, -1); - chip->select_chip(chip, chipnr); + nand_deselect_target(chip); + nand_select_target(chip, chipnr); } } @@ -4234,7 +4270,7 @@ int nand_erase_nand(struct nand_chip *chip, struct erase_info *instr, erase_exit: /* Deselect and wake up anyone waiting on the device */ - chip->select_chip(chip, -1); + nand_deselect_target(chip); nand_release_device(chip); /* Return more or less happy */ @@ -4272,11 +4308,11 @@ static int nand_block_isbad(struct mtd_info *mtd, loff_t offs) /* Select the NAND device */ nand_get_device(chip, FL_READING); - chip->select_chip(chip, chipnr); + nand_select_target(chip, chipnr); ret = nand_block_checkbad(chip, offs, 0); - chip->select_chip(chip, -1); + nand_deselect_target(chip); nand_release_device(chip); return ret; @@ -4645,7 +4681,7 @@ static int nand_detect(struct nand_chip *chip, struct nand_flash_dev *type) return ret; /* Select the device */ - chip->select_chip(chip, 0); + nand_select_target(chip, 0); /* Send the command for reading device ID */ ret = nand_readid_op(chip, 0, id_data, 2); @@ -4989,6 +5025,12 @@ static int nand_scan_ident(struct nand_chip *chip, unsigned int maxchips, if (ret) return ret; + /* + * Start with chips->numchips = maxchips to let nand_select_target() do + * its job. chip->numchips will be adjusted after. + */ + chip->numchips = maxchips; + /* Set the default functions */ nand_set_defaults(chip); @@ -4997,14 +5039,14 @@ static int nand_scan_ident(struct nand_chip *chip, unsigned int maxchips, if (ret) { if (!(chip->options & NAND_SCAN_SILENT_NODEV)) pr_warn("No NAND device found\n"); - chip->select_chip(chip, -1); + nand_deselect_target(chip); return ret; } nand_maf_id = chip->id.data[0]; nand_dev_id = chip->id.data[1]; - chip->select_chip(chip, -1); + nand_deselect_target(chip); /* Check for a chip array */ for (i = 1; i < maxchips; i++) { @@ -5013,15 +5055,15 @@ static int nand_scan_ident(struct nand_chip *chip, unsigned int maxchips, /* See comment in nand_get_flash_type for reset */ nand_reset(chip, i); - chip->select_chip(chip, i); + nand_select_target(chip, i); /* Send the command for reading device ID */ nand_readid_op(chip, 0, id, sizeof(id)); /* Read manufacturer and device IDs */ if (nand_maf_id != id[0] || nand_dev_id != id[1]) { - chip->select_chip(chip, -1); + nand_deselect_target(chip); break; } - chip->select_chip(chip, -1); + nand_deselect_target(chip); } if (i > 1) pr_info("%d chips detected\n", i); @@ -5447,9 +5489,9 @@ static int nand_scan_tail(struct nand_chip *chip) * to explictly select the relevant die when interacting with the NAND * chip. */ - chip->select_chip(chip, 0); + nand_select_target(chip, 0); ret = nand_manufacturer_init(chip); - chip->select_chip(chip, -1); + nand_deselect_target(chip); if (ret) goto err_free_buf; diff --git a/drivers/mtd/nand/raw/r852.c b/drivers/mtd/nand/raw/r852.c index 35f0b343cf90..c01422d953dd 100644 --- a/drivers/mtd/nand/raw/r852.c +++ b/drivers/mtd/nand/raw/r852.c @@ -1045,9 +1045,9 @@ static int r852_resume(struct device *device) /* Otherwise, initialize the card */ if (dev->card_registered) { r852_engine_enable(dev); - dev->chip->select_chip(dev->chip, 0); + nand_select_target(dev->chip, 0); nand_reset_op(dev->chip); - dev->chip->select_chip(dev->chip, -1); + nand_deselect_target(dev->chip); } /* Program card detection IRQ */ diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 2a3dd3e633f1..def6dff11e8b 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1332,9 +1332,12 @@ void nand_release(struct nand_chip *chip); * instruction and have no physical pin to check it. */ int nand_soft_waitrdy(struct nand_chip *chip, unsigned long timeout_ms); - struct gpio_desc; int nand_gpio_waitrdy(struct nand_chip *chip, struct gpio_desc *gpiod, unsigned long timeout_ms); +/* Select/deselect a NAND target. */ +void nand_select_target(struct nand_chip *chip, unsigned int cs); +void nand_deselect_target(struct nand_chip *chip); + #endif /* __LINUX_MTD_RAWNAND_H */ From ae2294b10b0f066ef500954b36c94ee11c4ef20f Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:15 +0100 Subject: [PATCH 324/356] mtd: rawnand: Pass the CS line to be selected in struct nand_operation In order to deprecate the ->select_chip hook we need to pass the CS line a NAND operations are targeting. This is done through the addition of a cs field to the nand_operation struct. We also need to keep track of the currently selected target to properly initialize op->cs, hence the ->cur_cs field addition to the nand_chip struct. Note that op->cs is not assigned in nand_exec_op() because we might rework the way we execute NAND operations in the future (adopt a queuing mechanism instead of the serialization we have right now). Signed-off-by: Boris Brezillon Tested-by: Janusz Krzysztofik Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/internals.h | 3 +++ drivers/mtd/nand/raw/nand_base.c | 39 +++++++++++++++++-------------- drivers/mtd/nand/raw/nand_hynix.c | 4 ++-- include/linux/mtd/rawnand.h | 11 ++++++++- 4 files changed, 37 insertions(+), 20 deletions(-) diff --git a/drivers/mtd/nand/raw/internals.h b/drivers/mtd/nand/raw/internals.h index 6e2f61fbc5f0..b62728d5884b 100644 --- a/drivers/mtd/nand/raw/internals.h +++ b/drivers/mtd/nand/raw/internals.h @@ -101,6 +101,9 @@ static inline int nand_exec_op(struct nand_chip *chip, if (!chip->exec_op) return -ENOTSUPP; + if (WARN_ON(op->cs >= chip->numchips)) + return -EINVAL; + return chip->exec_op(chip, op, false); } diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index f85e6f3b1b2f..7aa661f76891 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -246,6 +246,7 @@ void nand_select_target(struct nand_chip *chip, unsigned int cs) if (WARN_ON(cs > chip->numchips)) return; + chip->cur_cs = cs; chip->select_chip(chip, cs); } EXPORT_SYMBOL_GPL(nand_select_target); @@ -260,6 +261,7 @@ EXPORT_SYMBOL_GPL(nand_select_target); void nand_deselect_target(struct nand_chip *chip) { chip->select_chip(chip, -1); + chip->cur_cs = -1; } EXPORT_SYMBOL_GPL(nand_deselect_target); @@ -1022,7 +1024,7 @@ static int nand_sp_exec_read_page_op(struct nand_chip *chip, unsigned int page, PSEC_TO_NSEC(sdr->tRR_min)), NAND_OP_DATA_IN(len, buf, 0), }; - struct nand_operation op = NAND_OPERATION(instrs); + struct nand_operation op = NAND_OPERATION(chip->cur_cs, instrs); int ret; /* Drop the DATA_IN instruction if len is set to 0. */ @@ -1065,7 +1067,7 @@ static int nand_lp_exec_read_page_op(struct nand_chip *chip, unsigned int page, PSEC_TO_NSEC(sdr->tRR_min)), NAND_OP_DATA_IN(len, buf, 0), }; - struct nand_operation op = NAND_OPERATION(instrs); + struct nand_operation op = NAND_OPERATION(chip->cur_cs, instrs); int ret; /* Drop the DATA_IN instruction if len is set to 0. */ @@ -1160,7 +1162,7 @@ int nand_read_param_page_op(struct nand_chip *chip, u8 page, void *buf, PSEC_TO_NSEC(sdr->tRR_min)), NAND_OP_8BIT_DATA_IN(len, buf, 0), }; - struct nand_operation op = NAND_OPERATION(instrs); + struct nand_operation op = NAND_OPERATION(chip->cur_cs, instrs); /* Drop the DATA_IN instruction if len is set to 0. */ if (!len) @@ -1216,7 +1218,7 @@ int nand_change_read_column_op(struct nand_chip *chip, PSEC_TO_NSEC(sdr->tCCS_min)), NAND_OP_DATA_IN(len, buf, 0), }; - struct nand_operation op = NAND_OPERATION(instrs); + struct nand_operation op = NAND_OPERATION(chip->cur_cs, instrs); int ret; ret = nand_fill_column_cycles(chip, addrs, offset_in_page); @@ -1298,7 +1300,7 @@ static int nand_exec_prog_page_op(struct nand_chip *chip, unsigned int page, NAND_OP_CMD(NAND_CMD_PAGEPROG, PSEC_TO_NSEC(sdr->tWB_max)), NAND_OP_WAIT_RDY(PSEC_TO_MSEC(sdr->tPROG_max), 0), }; - struct nand_operation op = NAND_OPERATION(instrs); + struct nand_operation op = NAND_OPERATION(chip->cur_cs, instrs); int naddrs = nand_fill_column_cycles(chip, addrs, offset_in_page); int ret; u8 status; @@ -1412,7 +1414,7 @@ int nand_prog_page_end_op(struct nand_chip *chip) PSEC_TO_NSEC(sdr->tWB_max)), NAND_OP_WAIT_RDY(PSEC_TO_MSEC(sdr->tPROG_max), 0), }; - struct nand_operation op = NAND_OPERATION(instrs); + struct nand_operation op = NAND_OPERATION(chip->cur_cs, instrs); ret = nand_exec_op(chip, &op); if (ret) @@ -1520,7 +1522,7 @@ int nand_change_write_column_op(struct nand_chip *chip, NAND_OP_ADDR(2, addrs, PSEC_TO_NSEC(sdr->tCCS_min)), NAND_OP_DATA_OUT(len, buf, 0), }; - struct nand_operation op = NAND_OPERATION(instrs); + struct nand_operation op = NAND_OPERATION(chip->cur_cs, instrs); int ret; ret = nand_fill_column_cycles(chip, addrs, offset_in_page); @@ -1574,7 +1576,7 @@ int nand_readid_op(struct nand_chip *chip, u8 addr, void *buf, NAND_OP_ADDR(1, &addr, PSEC_TO_NSEC(sdr->tADL_min)), NAND_OP_8BIT_DATA_IN(len, buf, 0), }; - struct nand_operation op = NAND_OPERATION(instrs); + struct nand_operation op = NAND_OPERATION(chip->cur_cs, instrs); /* Drop the DATA_IN instruction if len is set to 0. */ if (!len) @@ -1613,7 +1615,7 @@ int nand_status_op(struct nand_chip *chip, u8 *status) PSEC_TO_NSEC(sdr->tADL_min)), NAND_OP_8BIT_DATA_IN(1, status, 0), }; - struct nand_operation op = NAND_OPERATION(instrs); + struct nand_operation op = NAND_OPERATION(chip->cur_cs, instrs); if (!status) op.ninstrs--; @@ -1646,7 +1648,7 @@ int nand_exit_status_op(struct nand_chip *chip) struct nand_op_instr instrs[] = { NAND_OP_CMD(NAND_CMD_READ0, 0), }; - struct nand_operation op = NAND_OPERATION(instrs); + struct nand_operation op = NAND_OPERATION(chip->cur_cs, instrs); return nand_exec_op(chip, &op); } @@ -1685,7 +1687,7 @@ int nand_erase_op(struct nand_chip *chip, unsigned int eraseblock) PSEC_TO_MSEC(sdr->tWB_max)), NAND_OP_WAIT_RDY(PSEC_TO_MSEC(sdr->tBERS_max), 0), }; - struct nand_operation op = NAND_OPERATION(instrs); + struct nand_operation op = NAND_OPERATION(chip->cur_cs, instrs); if (chip->options & NAND_ROW_ADDR_3) instrs[1].ctx.addr.naddrs++; @@ -1743,7 +1745,7 @@ static int nand_set_features_op(struct nand_chip *chip, u8 feature, PSEC_TO_NSEC(sdr->tWB_max)), NAND_OP_WAIT_RDY(PSEC_TO_MSEC(sdr->tFEAT_max), 0), }; - struct nand_operation op = NAND_OPERATION(instrs); + struct nand_operation op = NAND_OPERATION(chip->cur_cs, instrs); return nand_exec_op(chip, &op); } @@ -1791,7 +1793,7 @@ static int nand_get_features_op(struct nand_chip *chip, u8 feature, NAND_OP_8BIT_DATA_IN(ONFI_SUBFEATURE_PARAM_LEN, data, 0), }; - struct nand_operation op = NAND_OPERATION(instrs); + struct nand_operation op = NAND_OPERATION(chip->cur_cs, instrs); return nand_exec_op(chip, &op); } @@ -1811,7 +1813,7 @@ static int nand_wait_rdy_op(struct nand_chip *chip, unsigned int timeout_ms, NAND_OP_WAIT_RDY(PSEC_TO_MSEC(timeout_ms), PSEC_TO_NSEC(delay_ns)), }; - struct nand_operation op = NAND_OPERATION(instrs); + struct nand_operation op = NAND_OPERATION(chip->cur_cs, instrs); return nand_exec_op(chip, &op); } @@ -1844,7 +1846,7 @@ int nand_reset_op(struct nand_chip *chip) NAND_OP_CMD(NAND_CMD_RESET, PSEC_TO_NSEC(sdr->tWB_max)), NAND_OP_WAIT_RDY(PSEC_TO_MSEC(sdr->tRST_max), 0), }; - struct nand_operation op = NAND_OPERATION(instrs); + struct nand_operation op = NAND_OPERATION(chip->cur_cs, instrs); return nand_exec_op(chip, &op); } @@ -1878,7 +1880,7 @@ int nand_read_data_op(struct nand_chip *chip, void *buf, unsigned int len, struct nand_op_instr instrs[] = { NAND_OP_DATA_IN(len, buf, 0), }; - struct nand_operation op = NAND_OPERATION(instrs); + struct nand_operation op = NAND_OPERATION(chip->cur_cs, instrs); instrs[0].ctx.data.force_8bit = force_8bit; @@ -1922,7 +1924,7 @@ int nand_write_data_op(struct nand_chip *chip, const void *buf, struct nand_op_instr instrs[] = { NAND_OP_DATA_OUT(len, buf, 0), }; - struct nand_operation op = NAND_OPERATION(instrs); + struct nand_operation op = NAND_OPERATION(chip->cur_cs, instrs); instrs[0].ctx.data.force_8bit = force_8bit; @@ -5006,6 +5008,9 @@ static int nand_scan_ident(struct nand_chip *chip, unsigned int maxchips, unsigned int i; int ret; + /* Assume all dies are deselected when we enter nand_scan_ident(). */ + chip->cur_cs = -1; + /* Enforce the right timings for reset/detection */ onfi_fill_data_interface(chip, NAND_SDR_IFACE, 0); diff --git a/drivers/mtd/nand/raw/nand_hynix.c b/drivers/mtd/nand/raw/nand_hynix.c index ac1b5c103968..1e4499d01e14 100644 --- a/drivers/mtd/nand/raw/nand_hynix.c +++ b/drivers/mtd/nand/raw/nand_hynix.c @@ -84,7 +84,7 @@ static int hynix_nand_cmd_op(struct nand_chip *chip, u8 cmd) struct nand_op_instr instrs[] = { NAND_OP_CMD(cmd, 0), }; - struct nand_operation op = NAND_OPERATION(instrs); + struct nand_operation op = NAND_OPERATION(chip->cur_cs, instrs); return nand_exec_op(chip, &op); } @@ -103,7 +103,7 @@ static int hynix_nand_reg_write_op(struct nand_chip *chip, u8 addr, u8 val) NAND_OP_ADDR(1, &addr, 0), NAND_OP_8BIT_DATA_OUT(1, &val, 0), }; - struct nand_operation op = NAND_OPERATION(instrs); + struct nand_operation op = NAND_OPERATION(chip->cur_cs, instrs); return nand_exec_op(chip, &op); } diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index def6dff11e8b..aa1512df38a9 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -875,18 +875,21 @@ struct nand_op_parser { /** * struct nand_operation - NAND operation descriptor + * @cs: the CS line to select for this NAND operation * @instrs: array of instructions to execute * @ninstrs: length of the @instrs array * * The actual operation structure that will be passed to chip->exec_op(). */ struct nand_operation { + unsigned int cs; const struct nand_op_instr *instrs; unsigned int ninstrs; }; -#define NAND_OPERATION(_instrs) \ +#define NAND_OPERATION(_cs, _instrs) \ { \ + .cs = _cs, \ .instrs = _instrs, \ .ninstrs = ARRAY_SIZE(_instrs), \ } @@ -1008,6 +1011,10 @@ struct nand_legacy { * this nand device will encounter their life times. * @blocks_per_die: [INTERN] The number of PEBs in a die * @data_interface: [INTERN] NAND interface timing information + * @cur_cs: currently selected target. -1 means no target selected, + * otherwise we should always have cur_cs >= 0 && + * cur_cs < numchips. NAND Controller drivers should not + * modify this value, but they're allowed to read it. * @read_retries: [INTERN] the number of read retry modes supported * @setup_data_interface: [OPTIONAL] setup the data interface and timing. If * chipnr is set to %NAND_DATA_IFACE_CHECK_ONLY this @@ -1069,6 +1076,8 @@ struct nand_chip { struct nand_data_interface data_interface; + int cur_cs; + int read_retries; flstate_t state; From 02b4a52604a4d1734a666ed11f9fb43afff10656 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:16 +0100 Subject: [PATCH 325/356] mtd: rawnand: Make ->select_chip() optional when ->exec_op() is implemented Now that the CS to be selected on a nand_operation is passed in nand_operation->cs we can make the ->select_chip() hook optional for drivers implementing ->exec_op(). When not implemented, the core is assuming the CS line is automatically asserted/deasserted by the driver ->exec_op() implementation. Signed-off-by: Boris Brezillon Tested-by: Janusz Krzysztofik Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/nand_base.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 7aa661f76891..93a19f551796 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -247,7 +247,9 @@ void nand_select_target(struct nand_chip *chip, unsigned int cs) return; chip->cur_cs = cs; - chip->select_chip(chip, cs); + + if (chip->select_chip) + chip->select_chip(chip, cs); } EXPORT_SYMBOL_GPL(nand_select_target); @@ -260,7 +262,9 @@ EXPORT_SYMBOL_GPL(nand_select_target); */ void nand_deselect_target(struct nand_chip *chip) { - chip->select_chip(chip, -1); + if (chip->select_chip) + chip->select_chip(chip, -1); + chip->cur_cs = -1; } EXPORT_SYMBOL_GPL(nand_deselect_target); @@ -5021,11 +5025,6 @@ static int nand_scan_ident(struct nand_chip *chip, unsigned int maxchips, if (!mtd->name && mtd->dev.parent) mtd->name = dev_name(mtd->dev.parent); - if (chip->exec_op && !chip->select_chip) { - pr_err("->select_chip() is mandatory when implementing ->exec_op()\n"); - return -EINVAL; - } - ret = nand_legacy_check_hooks(chip); if (ret) return ret; From 550b9fc4e3af5f0af687d9e7bf168c8b48cf5495 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:17 +0100 Subject: [PATCH 326/356] mtd: rawnand: fsmc: Stop implementing ->select_chip() Now that the CS line to assert is directly passed through the nand_operation struct we can replace the fsmc_select_chip() implementation by an internal fsmc_ce_ctrl() function which is directly called from fsmc_exec_op() Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/fsmc_nand.c | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c index 41ba76efd6c8..ea69ac6e6d7a 100644 --- a/drivers/mtd/nand/raw/fsmc_nand.c +++ b/drivers/mtd/nand/raw/fsmc_nand.c @@ -609,22 +609,19 @@ static void fsmc_write_buf_dma(struct mtd_info *mtd, const uint8_t *buf, } /* fsmc_select_chip - assert or deassert nCE */ -static void fsmc_select_chip(struct nand_chip *chip, int chipnr) +static void fsmc_ce_ctrl(struct fsmc_nand_data *host, bool assert) { - struct fsmc_nand_data *host = mtd_to_fsmc(nand_to_mtd(chip)); - u32 pc; + u32 pc = readl(host->regs_va + FSMC_PC); - /* Support only one CS */ - if (chipnr > 0) - return; - - pc = readl(host->regs_va + FSMC_PC); - if (chipnr < 0) + if (!assert) writel_relaxed(pc & ~FSMC_ENABLE, host->regs_va + FSMC_PC); else writel_relaxed(pc | FSMC_ENABLE, host->regs_va + FSMC_PC); - /* nCE line must be asserted before starting any operation */ + /* + * nCE line changes must be applied before returning from this + * function. + */ mb(); } @@ -645,6 +642,9 @@ static int fsmc_exec_op(struct nand_chip *chip, const struct nand_operation *op, int i; pr_debug("Executing operation [%d instructions]:\n", op->ninstrs); + + fsmc_ce_ctrl(host, true); + for (op_id = 0; op_id < op->ninstrs; op_id++) { instr = &op->instrs[op_id]; @@ -701,6 +701,8 @@ static int fsmc_exec_op(struct nand_chip *chip, const struct nand_operation *op, } } + fsmc_ce_ctrl(host, false); + return ret; } @@ -1081,7 +1083,6 @@ static int __init fsmc_nand_probe(struct platform_device *pdev) mtd->dev.parent = &pdev->dev; nand->exec_op = fsmc_exec_op; - nand->select_chip = fsmc_select_chip; /* * Setup default ECC mode. nand_dt_init() called from nand_scan_ident() From b25251414f6e007c6ce7a0f6b96542bce728ffd9 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:18 +0100 Subject: [PATCH 327/356] mtd: rawnand: marvell: Stop implementing ->select_chip() Now that the CS to be selected is kept in chip->cur_cs and passed in nand_operation->cs, we can get rid of the ->select_chip() implementation and replace it by an internal function which is called from the chip->exec_op() and chip->ecc.read/write_xxx() hooks. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/marvell_nand.c | 27 ++++++++++++++++++--------- 1 file changed, 18 insertions(+), 9 deletions(-) diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c index 650f2b490a05..ba7a45fb1905 100644 --- a/drivers/mtd/nand/raw/marvell_nand.c +++ b/drivers/mtd/nand/raw/marvell_nand.c @@ -704,7 +704,8 @@ static int marvell_nfc_wait_op(struct nand_chip *chip, unsigned int timeout_ms) return 0; } -static void marvell_nfc_select_chip(struct nand_chip *chip, int die_nr) +static void marvell_nfc_select_target(struct nand_chip *chip, + unsigned int die_nr) { struct marvell_nand_chip *marvell_nand = to_marvell_nand(chip); struct marvell_nfc *nfc = to_marvell_nfc(chip->controller); @@ -713,12 +714,6 @@ static void marvell_nfc_select_chip(struct nand_chip *chip, int die_nr) if (chip == nfc->selected_chip && die_nr == marvell_nand->selected_die) return; - if (die_nr < 0 || die_nr >= marvell_nand->nsels) { - nfc->selected_chip = NULL; - marvell_nand->selected_die = -1; - return; - } - writel_relaxed(marvell_nand->ndtr0, nfc->regs + NDTR0); writel_relaxed(marvell_nand->ndtr1, nfc->regs + NDTR1); @@ -1024,13 +1019,13 @@ static int marvell_nfc_hw_ecc_hmg_do_read_page(struct nand_chip *chip, } ret = marvell_nfc_wait_cmdd(chip); - return ret; } static int marvell_nfc_hw_ecc_hmg_read_page_raw(struct nand_chip *chip, u8 *buf, int oob_required, int page) { + marvell_nfc_select_target(chip, chip->cur_cs); return marvell_nfc_hw_ecc_hmg_do_read_page(chip, buf, chip->oob_poi, true, page); } @@ -1043,6 +1038,7 @@ static int marvell_nfc_hw_ecc_hmg_read_page(struct nand_chip *chip, u8 *buf, int max_bitflips = 0, ret; u8 *raw_buf; + marvell_nfc_select_target(chip, chip->cur_cs); marvell_nfc_enable_hw_ecc(chip); marvell_nfc_hw_ecc_hmg_do_read_page(chip, buf, chip->oob_poi, false, page); @@ -1079,6 +1075,7 @@ static int marvell_nfc_hw_ecc_hmg_read_oob_raw(struct nand_chip *chip, int page) /* Invalidate page cache */ chip->pagebuf = -1; + marvell_nfc_select_target(chip, chip->cur_cs); return marvell_nfc_hw_ecc_hmg_do_read_page(chip, chip->data_buf, chip->oob_poi, true, page); } @@ -1142,6 +1139,7 @@ static int marvell_nfc_hw_ecc_hmg_write_page_raw(struct nand_chip *chip, const u8 *buf, int oob_required, int page) { + marvell_nfc_select_target(chip, chip->cur_cs); return marvell_nfc_hw_ecc_hmg_do_write_page(chip, buf, chip->oob_poi, true, page); } @@ -1152,6 +1150,7 @@ static int marvell_nfc_hw_ecc_hmg_write_page(struct nand_chip *chip, { int ret; + marvell_nfc_select_target(chip, chip->cur_cs); marvell_nfc_enable_hw_ecc(chip); ret = marvell_nfc_hw_ecc_hmg_do_write_page(chip, buf, chip->oob_poi, false, page); @@ -1175,6 +1174,7 @@ static int marvell_nfc_hw_ecc_hmg_write_oob_raw(struct nand_chip *chip, memset(chip->data_buf, 0xFF, mtd->writesize); + marvell_nfc_select_target(chip, chip->cur_cs); return marvell_nfc_hw_ecc_hmg_do_write_page(chip, chip->data_buf, chip->oob_poi, true, page); } @@ -1194,6 +1194,8 @@ static int marvell_nfc_hw_ecc_bch_read_page_raw(struct nand_chip *chip, u8 *buf, int ecc_len = lt->ecc_bytes; int chunk; + marvell_nfc_select_target(chip, chip->cur_cs); + if (oob_required) memset(chip->oob_poi, 0xFF, mtd->oobsize); @@ -1304,6 +1306,8 @@ static int marvell_nfc_hw_ecc_bch_read_page(struct nand_chip *chip, u32 failure_mask = 0; int chunk, ret; + marvell_nfc_select_target(chip, chip->cur_cs); + /* * With BCH, OOB is not fully used (and thus not read entirely), not * expected bytes could show up at the end of the OOB buffer if not @@ -1448,6 +1452,8 @@ static int marvell_nfc_hw_ecc_bch_write_page_raw(struct nand_chip *chip, lt->last_spare_bytes; int chunk; + marvell_nfc_select_target(chip, chip->cur_cs); + nand_prog_page_begin_op(chip, page, 0, NULL, 0); for (chunk = 0; chunk < lt->nchunks; chunk++) { @@ -1559,6 +1565,8 @@ static int marvell_nfc_hw_ecc_bch_write_page(struct nand_chip *chip, int spare_len = lt->spare_bytes; int chunk, ret; + marvell_nfc_select_target(chip, chip->cur_cs); + /* Spare data will be written anyway, so clear it to avoid garbage */ if (!oob_required) memset(chip->oob_poi, 0xFF, mtd->oobsize); @@ -2097,6 +2105,8 @@ static int marvell_nfc_exec_op(struct nand_chip *chip, { struct marvell_nfc *nfc = to_marvell_nfc(chip->controller); + marvell_nfc_select_target(chip, op->cs); + if (nfc->caps->is_nfcv2) return nand_op_parser_exec_op(chip, &marvell_nfcv2_op_parser, op, check_only); @@ -2618,7 +2628,6 @@ static int marvell_nand_chip_init(struct device *dev, struct marvell_nfc *nfc, nand_set_flash_node(chip, np); chip->exec_op = marvell_nfc_exec_op; - chip->select_chip = marvell_nfc_select_chip; if (!of_property_read_bool(np, "marvell,nand-keep-config")) chip->setup_data_interface = marvell_nfc_setup_data_interface; From 2ace451cae226da8cbf9b2af28f1458e4edaa31a Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:19 +0100 Subject: [PATCH 328/356] mtd: rawnand: tegra: Stop implementing ->select_chip() Now that the CS to be selected is kept in chip->cur_cs and passed in nand_operation->cs, we can get rid of the ->select_chip() implementation and replace it by an internal function which is called from the chip->exec_op() and chip->ecc.read/write_xxx() hooks. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/tegra_nand.c | 30 +++++++++++++----------------- 1 file changed, 13 insertions(+), 17 deletions(-) diff --git a/drivers/mtd/nand/raw/tegra_nand.c b/drivers/mtd/nand/raw/tegra_nand.c index 9767e29d74e2..590393d93ffc 100644 --- a/drivers/mtd/nand/raw/tegra_nand.c +++ b/drivers/mtd/nand/raw/tegra_nand.c @@ -454,29 +454,24 @@ static const struct nand_op_parser tegra_nand_op_parser = NAND_OP_PARSER( NAND_OP_PARSER_PAT_DATA_IN_ELEM(true, 4)), ); -static int tegra_nand_exec_op(struct nand_chip *chip, - const struct nand_operation *op, - bool check_only) -{ - return nand_op_parser_exec_op(chip, &tegra_nand_op_parser, op, - check_only); -} - -static void tegra_nand_select_chip(struct nand_chip *chip, int die_nr) +static void tegra_nand_select_target(struct nand_chip *chip, + unsigned int die_nr) { struct tegra_nand_chip *nand = to_tegra_chip(chip); struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller); - WARN_ON(die_nr >= (int)ARRAY_SIZE(nand->cs)); - - if (die_nr < 0 || die_nr > 0) { - ctrl->cur_cs = -1; - return; - } - ctrl->cur_cs = nand->cs[die_nr]; } +static int tegra_nand_exec_op(struct nand_chip *chip, + const struct nand_operation *op, + bool check_only) +{ + tegra_nand_select_target(chip, op->cs); + return nand_op_parser_exec_op(chip, &tegra_nand_op_parser, op, + check_only); +} + static void tegra_nand_hw_ecc(struct tegra_nand_controller *ctrl, struct nand_chip *chip, bool enable) { @@ -503,6 +498,8 @@ static int tegra_nand_page_xfer(struct mtd_info *mtd, struct nand_chip *chip, u32 addr1, cmd, dma_ctrl; int ret; + tegra_nand_select_target(chip, chip->cur_cs); + if (read) { writel_relaxed(NAND_CMD_READ0, ctrl->regs + CMD_REG1); writel_relaxed(NAND_CMD_READSTART, ctrl->regs + CMD_REG2); @@ -1116,7 +1113,6 @@ static int tegra_nand_chips_init(struct device *dev, chip->options = NAND_NO_SUBPAGE_WRITE | NAND_USE_BOUNCE_BUFFER; chip->exec_op = tegra_nand_exec_op; - chip->select_chip = tegra_nand_select_chip; chip->setup_data_interface = tegra_nand_setup_data_interface; ret = nand_scan(chip, 1); From 653c57c7da087be6448f63430e077dd9eae06188 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:20 +0100 Subject: [PATCH 329/356] mtd: rawnand: vf610: Stop implementing ->select_chip() Now that the CS to be selected is kept in chip->cur_cs and passed in nand_operation->cs, we can get rid of the ->select_chip() implementation and replace it by an internal function which is called from the chip->exec_op() and chip->ecc.read/write_xxx() hooks. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/vf610_nfc.c | 34 +++++++++++++++++--------------- 1 file changed, 18 insertions(+), 16 deletions(-) diff --git a/drivers/mtd/nand/raw/vf610_nfc.c b/drivers/mtd/nand/raw/vf610_nfc.c index 9814fd4a84cf..49a174e30211 100644 --- a/drivers/mtd/nand/raw/vf610_nfc.c +++ b/drivers/mtd/nand/raw/vf610_nfc.c @@ -487,36 +487,35 @@ static const struct nand_op_parser vf610_nfc_op_parser = NAND_OP_PARSER( NAND_OP_PARSER_PAT_DATA_IN_ELEM(true, PAGE_2K + OOB_MAX)), ); -static int vf610_nfc_exec_op(struct nand_chip *chip, - const struct nand_operation *op, - bool check_only) -{ - return nand_op_parser_exec_op(chip, &vf610_nfc_op_parser, op, - check_only); -} - /* * This function supports Vybrid only (MPC5125 would have full RB and four CS) */ -static void vf610_nfc_select_chip(struct nand_chip *chip, int cs) +static void vf610_nfc_select_target(struct nand_chip *chip, unsigned int cs) { struct vf610_nfc *nfc = mtd_to_nfc(nand_to_mtd(chip)); - u32 tmp = vf610_nfc_read(nfc, NFC_ROW_ADDR); + u32 tmp; /* Vybrid only (MPC5125 would have full RB and four CS) */ if (nfc->variant != NFC_VFC610) return; + tmp = vf610_nfc_read(nfc, NFC_ROW_ADDR); tmp &= ~(ROW_ADDR_CHIP_SEL_RB_MASK | ROW_ADDR_CHIP_SEL_MASK); - - if (cs >= 0) { - tmp |= 1 << ROW_ADDR_CHIP_SEL_RB_SHIFT; - tmp |= BIT(cs) << ROW_ADDR_CHIP_SEL_SHIFT; - } + tmp |= 1 << ROW_ADDR_CHIP_SEL_RB_SHIFT; + tmp |= BIT(cs) << ROW_ADDR_CHIP_SEL_SHIFT; vf610_nfc_write(nfc, NFC_ROW_ADDR, tmp); } +static int vf610_nfc_exec_op(struct nand_chip *chip, + const struct nand_operation *op, + bool check_only) +{ + vf610_nfc_select_target(chip, op->cs); + return nand_op_parser_exec_op(chip, &vf610_nfc_op_parser, op, + check_only); +} + static inline int vf610_nfc_correct_data(struct mtd_info *mtd, uint8_t *dat, uint8_t *oob, int page) { @@ -566,6 +565,8 @@ static int vf610_nfc_read_page(struct nand_chip *chip, uint8_t *buf, u32 row = 0, cmd1 = 0, cmd2 = 0, code = 0; int stat; + vf610_nfc_select_target(chip, chip->cur_cs); + cmd2 |= NAND_CMD_READ0 << CMD_BYTE1_SHIFT; code |= COMMAND_CMD_BYTE1 | COMMAND_CAR_BYTE1 | COMMAND_CAR_BYTE2; @@ -613,6 +614,8 @@ static int vf610_nfc_write_page(struct nand_chip *chip, const uint8_t *buf, u8 status; int ret; + vf610_nfc_select_target(chip, chip->cur_cs); + cmd2 |= NAND_CMD_SEQIN << CMD_BYTE1_SHIFT; code |= COMMAND_CMD_BYTE1 | COMMAND_CAR_BYTE1 | COMMAND_CAR_BYTE2; @@ -877,7 +880,6 @@ static int vf610_nfc_probe(struct platform_device *pdev) } chip->exec_op = vf610_nfc_exec_op; - chip->select_chip = vf610_nfc_select_chip; chip->options |= NAND_NO_SUBPAGE_WRITE; From 1770022ffa85e1cdba88e311493cc16d52340a59 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:21 +0100 Subject: [PATCH 330/356] mtd: rawnand: ams-delta: Stop implementing ->select_chip() Now that the CS to be selected is passed in nand_operation->cs, we can get rid of the ->select_chip() implementation and replace it by an internal function which is called from the chip->exec_op() hook. Signed-off-by: Boris Brezillon Tested-by: Janusz Krzysztofik Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/ams-delta.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/drivers/mtd/nand/raw/ams-delta.c b/drivers/mtd/nand/raw/ams-delta.c index 34b83edb965c..611c822e967f 100644 --- a/drivers/mtd/nand/raw/ams-delta.c +++ b/drivers/mtd/nand/raw/ams-delta.c @@ -116,14 +116,9 @@ static void ams_delta_read_buf(struct ams_delta_nand *priv, u8 *buf, int len) buf[i] = ams_delta_io_read(priv); } -static void ams_delta_select_chip(struct nand_chip *this, int n) +static void ams_delta_ctrl_cs(struct ams_delta_nand *priv, bool assert) { - struct ams_delta_nand *priv = nand_get_controller_data(this); - - if (n > 0) - return; - - gpiod_set_value(priv->gpiod_nce, n < 0); + gpiod_set_value(priv->gpiod_nce, assert ? 0 : 1); } static int ams_delta_exec_op(struct nand_chip *this, @@ -136,6 +131,8 @@ static int ams_delta_exec_op(struct nand_chip *this, if (check_only) return 0; + ams_delta_ctrl_cs(priv, 1); + for (instr = op->instrs; instr < op->instrs + op->ninstrs; instr++) { switch (instr->type) { case NAND_OP_CMD_INSTR: @@ -174,6 +171,8 @@ static int ams_delta_exec_op(struct nand_chip *this, break; } + ams_delta_ctrl_cs(priv, 0); + return ret; } @@ -217,7 +216,6 @@ static int ams_delta_init(struct platform_device *pdev) priv->io_base = io_base; nand_set_controller_data(this, priv); - this->select_chip = ams_delta_select_chip; this->exec_op = ams_delta_exec_op; priv->gpiod_rdy = devm_gpiod_get_optional(&pdev->dev, "rdy", GPIOD_IN); From 7d6c37e90cf9013bd18240cd861b9ae7b006f91f Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:22 +0100 Subject: [PATCH 331/356] mtd: rawnand: Deprecate the ->select_chip() hook Now that the CS line to be selected is passed to ->exec_op() and stored in chip->cur_cs and after patching all drivers implementing ->exec_op() to stop implementing this method, we can deprecate it by moving it to the nand_legacy structure. Signed-off-by: Boris Brezillon Tested-by: Janusz Krzysztofik Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/atmel/nand-controller.c | 4 ++-- drivers/mtd/nand/raw/au1550nd.c | 2 +- drivers/mtd/nand/raw/bcm47xxnflash/ops_bcm4706.c | 2 +- drivers/mtd/nand/raw/cafe_nand.c | 2 +- drivers/mtd/nand/raw/davinci_nand.c | 2 +- drivers/mtd/nand/raw/denali.c | 2 +- drivers/mtd/nand/raw/diskonchip.c | 4 ++-- drivers/mtd/nand/raw/fsl_elbc_nand.c | 2 +- drivers/mtd/nand/raw/fsl_ifc_nand.c | 2 +- drivers/mtd/nand/raw/fsl_upm.c | 2 +- drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c | 2 +- drivers/mtd/nand/raw/hisi504_nand.c | 2 +- drivers/mtd/nand/raw/jz4740_nand.c | 2 +- drivers/mtd/nand/raw/jz4780_nand.c | 2 +- drivers/mtd/nand/raw/mpc5121_nfc.c | 4 ++-- drivers/mtd/nand/raw/mtk_nand.c | 2 +- drivers/mtd/nand/raw/mxc_nand.c | 2 +- drivers/mtd/nand/raw/nand_base.c | 8 ++++---- drivers/mtd/nand/raw/nand_legacy.c | 9 +++++---- drivers/mtd/nand/raw/ndfc.c | 2 +- drivers/mtd/nand/raw/plat_nand.c | 2 +- drivers/mtd/nand/raw/qcom_nandc.c | 2 +- drivers/mtd/nand/raw/s3c2410.c | 2 +- drivers/mtd/nand/raw/sh_flctl.c | 2 +- drivers/mtd/nand/raw/sunxi_nand.c | 2 +- drivers/mtd/nand/raw/tango_nand.c | 2 +- drivers/mtd/nand/raw/xway_nand.c | 2 +- include/linux/mtd/rawnand.h | 4 ++-- 28 files changed, 39 insertions(+), 38 deletions(-) diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c index fb33f6be7c4f..d5c58eb040d8 100644 --- a/drivers/mtd/nand/raw/atmel/nand-controller.c +++ b/drivers/mtd/nand/raw/atmel/nand-controller.c @@ -1477,7 +1477,7 @@ static void atmel_nand_init(struct atmel_nand_controller *nc, chip->legacy.write_byte = atmel_nand_write_byte; chip->legacy.read_buf = atmel_nand_read_buf; chip->legacy.write_buf = atmel_nand_write_buf; - chip->select_chip = atmel_nand_select_chip; + chip->legacy.select_chip = atmel_nand_select_chip; if (nc->mck && nc->caps->ops->setup_data_interface) chip->setup_data_interface = atmel_nand_setup_data_interface; @@ -1525,7 +1525,7 @@ static void atmel_hsmc_nand_init(struct atmel_nand_controller *nc, /* Overload some methods for the HSMC controller. */ chip->legacy.cmd_ctrl = atmel_hsmc_nand_cmd_ctrl; - chip->select_chip = atmel_hsmc_nand_select_chip; + chip->legacy.select_chip = atmel_hsmc_nand_select_chip; } static int atmel_nand_controller_remove_nand(struct atmel_nand *nand) diff --git a/drivers/mtd/nand/raw/au1550nd.c b/drivers/mtd/nand/raw/au1550nd.c index 9731c1c487f6..a963002663ed 100644 --- a/drivers/mtd/nand/raw/au1550nd.c +++ b/drivers/mtd/nand/raw/au1550nd.c @@ -430,7 +430,7 @@ static int au1550nd_probe(struct platform_device *pdev) ctx->cs = cs; this->legacy.dev_ready = au1550_device_ready; - this->select_chip = au1550_select_chip; + this->legacy.select_chip = au1550_select_chip; this->legacy.cmdfunc = au1550_command; /* 30 us command delay time */ diff --git a/drivers/mtd/nand/raw/bcm47xxnflash/ops_bcm4706.c b/drivers/mtd/nand/raw/bcm47xxnflash/ops_bcm4706.c index 9095a79ebc7d..a37cbfe56567 100644 --- a/drivers/mtd/nand/raw/bcm47xxnflash/ops_bcm4706.c +++ b/drivers/mtd/nand/raw/bcm47xxnflash/ops_bcm4706.c @@ -383,7 +383,7 @@ int bcm47xxnflash_ops_bcm4706_init(struct bcm47xxnflash *b47n) u8 tbits, col_bits, col_size, row_bits, row_bsize; u32 val; - b47n->nand_chip.select_chip = bcm47xxnflash_ops_bcm4706_select_chip; + nand_chip->legacy.select_chip = bcm47xxnflash_ops_bcm4706_select_chip; nand_chip->legacy.cmd_ctrl = bcm47xxnflash_ops_bcm4706_cmd_ctrl; nand_chip->legacy.dev_ready = bcm47xxnflash_ops_bcm4706_dev_ready; b47n->nand_chip.legacy.cmdfunc = bcm47xxnflash_ops_bcm4706_cmdfunc; diff --git a/drivers/mtd/nand/raw/cafe_nand.c b/drivers/mtd/nand/raw/cafe_nand.c index c1a745940d12..a85f5fa5c66d 100644 --- a/drivers/mtd/nand/raw/cafe_nand.c +++ b/drivers/mtd/nand/raw/cafe_nand.c @@ -708,7 +708,7 @@ static int cafe_nand_probe(struct pci_dev *pdev, cafe->nand.legacy.read_byte = cafe_read_byte; cafe->nand.legacy.read_buf = cafe_read_buf; cafe->nand.legacy.write_buf = cafe_write_buf; - cafe->nand.select_chip = cafe_select_chip; + cafe->nand.legacy.select_chip = cafe_select_chip; cafe->nand.legacy.set_features = nand_get_set_features_notsupp; cafe->nand.legacy.get_features = nand_get_set_features_notsupp; diff --git a/drivers/mtd/nand/raw/davinci_nand.c b/drivers/mtd/nand/raw/davinci_nand.c index 80f228d23cd2..f430aeb917e8 100644 --- a/drivers/mtd/nand/raw/davinci_nand.c +++ b/drivers/mtd/nand/raw/davinci_nand.c @@ -762,7 +762,7 @@ static int nand_davinci_probe(struct platform_device *pdev) info->chip.legacy.IO_ADDR_R = vaddr; info->chip.legacy.IO_ADDR_W = vaddr; info->chip.legacy.chip_delay = 0; - info->chip.select_chip = nand_davinci_select_chip; + info->chip.legacy.select_chip = nand_davinci_select_chip; /* options such as NAND_BBT_USE_FLASH */ info->chip.bbt_options = pdata->bbt_options; diff --git a/drivers/mtd/nand/raw/denali.c b/drivers/mtd/nand/raw/denali.c index 830ea247277b..64895ca68c8d 100644 --- a/drivers/mtd/nand/raw/denali.c +++ b/drivers/mtd/nand/raw/denali.c @@ -1355,7 +1355,7 @@ int denali_init(struct denali_nand_info *denali) if (!mtd->name) mtd->name = "denali-nand"; - chip->select_chip = denali_select_chip; + chip->legacy.select_chip = denali_select_chip; chip->legacy.read_byte = denali_read_byte; chip->legacy.write_byte = denali_write_byte; chip->legacy.cmd_ctrl = denali_cmd_ctrl; diff --git a/drivers/mtd/nand/raw/diskonchip.c b/drivers/mtd/nand/raw/diskonchip.c index 3a4c373affab..53f57e0f007e 100644 --- a/drivers/mtd/nand/raw/diskonchip.c +++ b/drivers/mtd/nand/raw/diskonchip.c @@ -1390,7 +1390,7 @@ static inline int __init doc2001plus_init(struct mtd_info *mtd) this->legacy.read_buf = doc2001plus_readbuf; doc->late_init = inftl_scan_bbt; this->legacy.cmd_ctrl = NULL; - this->select_chip = doc2001plus_select_chip; + this->legacy.select_chip = doc2001plus_select_chip; this->legacy.cmdfunc = doc2001plus_command; this->ecc.hwctl = doc2001plus_enable_hwecc; @@ -1568,7 +1568,7 @@ static int __init doc_probe(unsigned long physadr) mtd_set_ooblayout(mtd, &doc200x_ooblayout_ops); nand_set_controller_data(nand, doc); - nand->select_chip = doc200x_select_chip; + nand->legacy.select_chip = doc200x_select_chip; nand->legacy.cmd_ctrl = doc200x_hwcontrol; nand->legacy.dev_ready = doc200x_dev_ready; nand->legacy.waitfunc = doc200x_wait; diff --git a/drivers/mtd/nand/raw/fsl_elbc_nand.c b/drivers/mtd/nand/raw/fsl_elbc_nand.c index d6ed697fcfe6..70f0d2b450ea 100644 --- a/drivers/mtd/nand/raw/fsl_elbc_nand.c +++ b/drivers/mtd/nand/raw/fsl_elbc_nand.c @@ -779,7 +779,7 @@ static int fsl_elbc_chip_init(struct fsl_elbc_mtd *priv) chip->legacy.read_byte = fsl_elbc_read_byte; chip->legacy.write_buf = fsl_elbc_write_buf; chip->legacy.read_buf = fsl_elbc_read_buf; - chip->select_chip = fsl_elbc_select_chip; + chip->legacy.select_chip = fsl_elbc_select_chip; chip->legacy.cmdfunc = fsl_elbc_cmdfunc; chip->legacy.waitfunc = fsl_elbc_wait; chip->legacy.set_features = nand_get_set_features_notsupp; diff --git a/drivers/mtd/nand/raw/fsl_ifc_nand.c b/drivers/mtd/nand/raw/fsl_ifc_nand.c index 6f4afc44381a..e65d274399f9 100644 --- a/drivers/mtd/nand/raw/fsl_ifc_nand.c +++ b/drivers/mtd/nand/raw/fsl_ifc_nand.c @@ -864,7 +864,7 @@ static int fsl_ifc_chip_init(struct fsl_ifc_mtd *priv) chip->legacy.write_buf = fsl_ifc_write_buf; chip->legacy.read_buf = fsl_ifc_read_buf; - chip->select_chip = fsl_ifc_select_chip; + chip->legacy.select_chip = fsl_ifc_select_chip; chip->legacy.cmdfunc = fsl_ifc_cmdfunc; chip->legacy.waitfunc = fsl_ifc_wait; chip->legacy.set_features = nand_get_set_features_notsupp; diff --git a/drivers/mtd/nand/raw/fsl_upm.c b/drivers/mtd/nand/raw/fsl_upm.c index 673c5a0c9345..5ccc28ec0985 100644 --- a/drivers/mtd/nand/raw/fsl_upm.c +++ b/drivers/mtd/nand/raw/fsl_upm.c @@ -170,7 +170,7 @@ static int fun_chip_init(struct fsl_upm_nand *fun, fun->chip.ecc.mode = NAND_ECC_SOFT; fun->chip.ecc.algo = NAND_ECC_HAMMING; if (fun->mchip_count > 1) - fun->chip.select_chip = fun_select_chip; + fun->chip.legacy.select_chip = fun_select_chip; if (fun->rnb_gpio[0] >= 0) fun->chip.legacy.dev_ready = fun_chip_ready; diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c index 302ddd3d4a5f..c461d5efabc0 100644 --- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c +++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c @@ -1907,7 +1907,7 @@ static int gpmi_nand_init(struct gpmi_nand_data *this) /* init the nand_chip{}, we don't support a 16-bit NAND Flash bus. */ nand_set_controller_data(chip, this); nand_set_flash_node(chip, this->pdev->dev.of_node); - chip->select_chip = gpmi_select_chip; + chip->legacy.select_chip = gpmi_select_chip; chip->setup_data_interface = gpmi_setup_data_interface; chip->legacy.cmd_ctrl = gpmi_cmd_ctrl; chip->legacy.dev_ready = gpmi_dev_ready; diff --git a/drivers/mtd/nand/raw/hisi504_nand.c b/drivers/mtd/nand/raw/hisi504_nand.c index f043938ee36b..e41c13499fd5 100644 --- a/drivers/mtd/nand/raw/hisi504_nand.c +++ b/drivers/mtd/nand/raw/hisi504_nand.c @@ -783,7 +783,7 @@ static int hisi_nfc_probe(struct platform_device *pdev) nand_set_controller_data(chip, host); nand_set_flash_node(chip, np); chip->legacy.cmdfunc = hisi_nfc_cmdfunc; - chip->select_chip = hisi_nfc_select_chip; + chip->legacy.select_chip = hisi_nfc_select_chip; chip->legacy.read_byte = hisi_nfc_read_byte; chip->legacy.write_buf = hisi_nfc_write_buf; chip->legacy.read_buf = hisi_nfc_read_buf; diff --git a/drivers/mtd/nand/raw/jz4740_nand.c b/drivers/mtd/nand/raw/jz4740_nand.c index d271004f16b0..0bcfdd3d66a8 100644 --- a/drivers/mtd/nand/raw/jz4740_nand.c +++ b/drivers/mtd/nand/raw/jz4740_nand.c @@ -427,7 +427,7 @@ static int jz_nand_probe(struct platform_device *pdev) chip->legacy.chip_delay = 50; chip->legacy.cmd_ctrl = jz_nand_cmd_ctrl; - chip->select_chip = jz_nand_select_chip; + chip->legacy.select_chip = jz_nand_select_chip; chip->dummy_controller.ops = &jz_nand_controller_ops; if (nand->busy_gpio) diff --git a/drivers/mtd/nand/raw/jz4780_nand.c b/drivers/mtd/nand/raw/jz4780_nand.c index cdf22100ab77..22e58975f0d5 100644 --- a/drivers/mtd/nand/raw/jz4780_nand.c +++ b/drivers/mtd/nand/raw/jz4780_nand.c @@ -279,7 +279,7 @@ static int jz4780_nand_init_chip(struct platform_device *pdev, chip->legacy.IO_ADDR_W = cs->base + OFFSET_DATA; chip->legacy.chip_delay = RB_DELAY_US; chip->options = NAND_NO_SUBPAGE_WRITE; - chip->select_chip = jz4780_nand_select_chip; + chip->legacy.select_chip = jz4780_nand_select_chip; chip->legacy.cmd_ctrl = jz4780_nand_cmd_ctrl; chip->ecc.mode = NAND_ECC_HW; chip->controller = &nfc->controller; diff --git a/drivers/mtd/nand/raw/mpc5121_nfc.c b/drivers/mtd/nand/raw/mpc5121_nfc.c index 86a0aabe08df..062cd1eb2861 100644 --- a/drivers/mtd/nand/raw/mpc5121_nfc.c +++ b/drivers/mtd/nand/raw/mpc5121_nfc.c @@ -697,7 +697,7 @@ static int mpc5121_nfc_probe(struct platform_device *op) chip->legacy.read_byte = mpc5121_nfc_read_byte; chip->legacy.read_buf = mpc5121_nfc_read_buf; chip->legacy.write_buf = mpc5121_nfc_write_buf; - chip->select_chip = mpc5121_nfc_select_chip; + chip->legacy.select_chip = mpc5121_nfc_select_chip; chip->legacy.set_features = nand_get_set_features_notsupp; chip->legacy.get_features = nand_get_set_features_notsupp; chip->bbt_options = NAND_BBT_USE_FLASH; @@ -712,7 +712,7 @@ static int mpc5121_nfc_probe(struct platform_device *op) return retval; } - chip->select_chip = ads5121_select_chip; + chip->legacy.select_chip = ads5121_select_chip; } /* Enable NFC clock */ diff --git a/drivers/mtd/nand/raw/mtk_nand.c b/drivers/mtd/nand/raw/mtk_nand.c index 2bb0df1b7244..ce124f8c02cd 100644 --- a/drivers/mtd/nand/raw/mtk_nand.c +++ b/drivers/mtd/nand/raw/mtk_nand.c @@ -1333,7 +1333,7 @@ static int mtk_nfc_nand_chip_init(struct device *dev, struct mtk_nfc *nfc, nand->options |= NAND_USE_BOUNCE_BUFFER | NAND_SUBPAGE_READ; nand->legacy.dev_ready = mtk_nfc_dev_ready; - nand->select_chip = mtk_nfc_select_chip; + nand->legacy.select_chip = mtk_nfc_select_chip; nand->legacy.write_byte = mtk_nfc_write_byte; nand->legacy.write_buf = mtk_nfc_write_buf; nand->legacy.read_byte = mtk_nfc_read_byte; diff --git a/drivers/mtd/nand/raw/mxc_nand.c b/drivers/mtd/nand/raw/mxc_nand.c index 88bd3f6a499c..c00b1d408a04 100644 --- a/drivers/mtd/nand/raw/mxc_nand.c +++ b/drivers/mtd/nand/raw/mxc_nand.c @@ -1828,7 +1828,7 @@ static int mxcnd_probe(struct platform_device *pdev) this->ecc.bytes = host->devtype_data->eccbytes; host->eccsize = host->devtype_data->eccsize; - this->select_chip = host->devtype_data->select_chip; + this->legacy.select_chip = host->devtype_data->select_chip; this->ecc.size = 512; mtd_set_ooblayout(mtd, host->devtype_data->ooblayout); diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 93a19f551796..cef6633fdce9 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -248,8 +248,8 @@ void nand_select_target(struct nand_chip *chip, unsigned int cs) chip->cur_cs = cs; - if (chip->select_chip) - chip->select_chip(chip, cs); + if (chip->legacy.select_chip) + chip->legacy.select_chip(chip, cs); } EXPORT_SYMBOL_GPL(nand_select_target); @@ -262,8 +262,8 @@ EXPORT_SYMBOL_GPL(nand_select_target); */ void nand_deselect_target(struct nand_chip *chip) { - if (chip->select_chip) - chip->select_chip(chip, -1); + if (chip->legacy.select_chip) + chip->legacy.select_chip(chip, -1); chip->cur_cs = -1; } diff --git a/drivers/mtd/nand/raw/nand_legacy.c b/drivers/mtd/nand/raw/nand_legacy.c index f76b9356ba9c..4596a538b967 100644 --- a/drivers/mtd/nand/raw/nand_legacy.c +++ b/drivers/mtd/nand/raw/nand_legacy.c @@ -592,8 +592,8 @@ void nand_legacy_set_defaults(struct nand_chip *chip) if (chip->legacy.waitfunc == NULL) chip->legacy.waitfunc = nand_wait; - if (!chip->select_chip) - chip->select_chip = nand_select_chip; + if (!chip->legacy.select_chip) + chip->legacy.select_chip = nand_select_chip; /* If called twice, pointers that depend on busw may need to be reset */ if (!chip->legacy.read_byte || chip->legacy.read_byte == nand_read_byte) @@ -626,9 +626,10 @@ int nand_legacy_check_hooks(struct nand_chip *chip) /* * Default functions assigned for ->legacy.cmdfunc() and - * ->select_chip() both expect ->legacy.cmd_ctrl() to be populated. + * ->legacy.select_chip() both expect ->legacy.cmd_ctrl() to be + * populated. */ - if ((!chip->legacy.cmdfunc || !chip->select_chip) && + if ((!chip->legacy.cmdfunc || !chip->legacy.select_chip) && !chip->legacy.cmd_ctrl) { pr_err("->legacy.cmd_ctrl() should be provided\n"); return -EINVAL; diff --git a/drivers/mtd/nand/raw/ndfc.c b/drivers/mtd/nand/raw/ndfc.c index d49a7a17146c..9857e0e5acd4 100644 --- a/drivers/mtd/nand/raw/ndfc.c +++ b/drivers/mtd/nand/raw/ndfc.c @@ -146,7 +146,7 @@ static int ndfc_chip_init(struct ndfc_controller *ndfc, chip->legacy.IO_ADDR_W = ndfc->ndfcbase + NDFC_DATA; chip->legacy.cmd_ctrl = ndfc_hwcontrol; chip->legacy.dev_ready = ndfc_ready; - chip->select_chip = ndfc_select_chip; + chip->legacy.select_chip = ndfc_select_chip; chip->legacy.chip_delay = 50; chip->controller = &ndfc->ndfc_control; chip->legacy.read_buf = ndfc_read_buf; diff --git a/drivers/mtd/nand/raw/plat_nand.c b/drivers/mtd/nand/raw/plat_nand.c index 86c536ddaf24..a994b76daa50 100644 --- a/drivers/mtd/nand/raw/plat_nand.c +++ b/drivers/mtd/nand/raw/plat_nand.c @@ -63,7 +63,7 @@ static int plat_nand_probe(struct platform_device *pdev) data->chip.legacy.IO_ADDR_W = data->io_base; data->chip.legacy.cmd_ctrl = pdata->ctrl.cmd_ctrl; data->chip.legacy.dev_ready = pdata->ctrl.dev_ready; - data->chip.select_chip = pdata->ctrl.select_chip; + data->chip.legacy.select_chip = pdata->ctrl.select_chip; data->chip.legacy.write_buf = pdata->ctrl.write_buf; data->chip.legacy.read_buf = pdata->ctrl.read_buf; data->chip.legacy.chip_delay = pdata->chip.chip_delay; diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c index ef75dfa62a4f..6b76fb5c0aed 100644 --- a/drivers/mtd/nand/raw/qcom_nandc.c +++ b/drivers/mtd/nand/raw/qcom_nandc.c @@ -2804,7 +2804,7 @@ static int qcom_nand_host_init_and_register(struct qcom_nand_controller *nandc, mtd->dev.parent = dev; chip->legacy.cmdfunc = qcom_nandc_command; - chip->select_chip = qcom_nandc_select_chip; + chip->legacy.select_chip = qcom_nandc_select_chip; chip->legacy.read_byte = qcom_nandc_read_byte; chip->legacy.read_buf = qcom_nandc_read_buf; chip->legacy.write_buf = qcom_nandc_write_buf; diff --git a/drivers/mtd/nand/raw/s3c2410.c b/drivers/mtd/nand/raw/s3c2410.c index d2e42e9d0e8c..a8905463701a 100644 --- a/drivers/mtd/nand/raw/s3c2410.c +++ b/drivers/mtd/nand/raw/s3c2410.c @@ -866,7 +866,7 @@ static void s3c2410_nand_init_chip(struct s3c2410_nand_info *info, chip->legacy.write_buf = s3c2410_nand_write_buf; chip->legacy.read_buf = s3c2410_nand_read_buf; - chip->select_chip = s3c2410_nand_select_chip; + chip->legacy.select_chip = s3c2410_nand_select_chip; chip->legacy.chip_delay = 50; nand_set_controller_data(chip, nmtd); chip->options = set->options; diff --git a/drivers/mtd/nand/raw/sh_flctl.c b/drivers/mtd/nand/raw/sh_flctl.c index 30edcc77b111..7ab50bc6ad3a 100644 --- a/drivers/mtd/nand/raw/sh_flctl.c +++ b/drivers/mtd/nand/raw/sh_flctl.c @@ -1170,7 +1170,7 @@ static int flctl_probe(struct platform_device *pdev) nand->legacy.read_byte = flctl_read_byte; nand->legacy.write_buf = flctl_write_buf; nand->legacy.read_buf = flctl_read_buf; - nand->select_chip = flctl_select_chip; + nand->legacy.select_chip = flctl_select_chip; nand->legacy.cmdfunc = flctl_cmdfunc; nand->legacy.set_features = nand_get_set_features_notsupp; nand->legacy.get_features = nand_get_set_features_notsupp; diff --git a/drivers/mtd/nand/raw/sunxi_nand.c b/drivers/mtd/nand/raw/sunxi_nand.c index 51b1a548064b..e489a6ff57d7 100644 --- a/drivers/mtd/nand/raw/sunxi_nand.c +++ b/drivers/mtd/nand/raw/sunxi_nand.c @@ -1922,7 +1922,7 @@ static int sunxi_nand_chip_init(struct device *dev, struct sunxi_nfc *nfc, */ nand->ecc.mode = NAND_ECC_HW; nand_set_flash_node(nand, np); - nand->select_chip = sunxi_nfc_select_chip; + nand->legacy.select_chip = sunxi_nfc_select_chip; nand->legacy.cmd_ctrl = sunxi_nfc_cmd_ctrl; nand->legacy.read_buf = sunxi_nfc_read_buf; nand->legacy.write_buf = sunxi_nfc_write_buf; diff --git a/drivers/mtd/nand/raw/tango_nand.c b/drivers/mtd/nand/raw/tango_nand.c index 8818f893f300..ebca4579c033 100644 --- a/drivers/mtd/nand/raw/tango_nand.c +++ b/drivers/mtd/nand/raw/tango_nand.c @@ -567,7 +567,7 @@ static int chip_init(struct device *dev, struct device_node *np) chip->legacy.read_byte = tango_read_byte; chip->legacy.write_buf = tango_write_buf; chip->legacy.read_buf = tango_read_buf; - chip->select_chip = tango_select_chip; + chip->legacy.select_chip = tango_select_chip; chip->legacy.cmd_ctrl = tango_cmd_ctrl; chip->legacy.dev_ready = tango_dev_ready; chip->setup_data_interface = tango_set_timings; diff --git a/drivers/mtd/nand/raw/xway_nand.c b/drivers/mtd/nand/raw/xway_nand.c index a234a5cb4868..4cb78106af14 100644 --- a/drivers/mtd/nand/raw/xway_nand.c +++ b/drivers/mtd/nand/raw/xway_nand.c @@ -176,7 +176,7 @@ static int xway_nand_probe(struct platform_device *pdev) data->chip.legacy.cmd_ctrl = xway_cmd_ctrl; data->chip.legacy.dev_ready = xway_dev_ready; - data->chip.select_chip = xway_select_chip; + data->chip.legacy.select_chip = xway_select_chip; data->chip.legacy.write_buf = xway_write_buf; data->chip.legacy.read_buf = xway_read_buf; data->chip.legacy.read_byte = xway_read_byte; diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index aa1512df38a9..40b74fb1792d 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -902,6 +902,7 @@ int nand_op_parser_exec_op(struct nand_chip *chip, * struct nand_legacy - NAND chip legacy fields/hooks * @IO_ADDR_R: address to read the 8 I/O lines of the flash device * @IO_ADDR_W: address to write the 8 I/O lines of the flash device + * @select_chip: select/deselect a specific target/die * @read_byte: read one byte from the chip * @write_byte: write a single byte to the chip on the low 8 I/O lines * @write_buf: write data from the buffer to the chip @@ -927,6 +928,7 @@ int nand_op_parser_exec_op(struct nand_chip *chip, struct nand_legacy { void __iomem *IO_ADDR_R; void __iomem *IO_ADDR_W; + void (*select_chip)(struct nand_chip *chip, int cs); u8 (*read_byte)(struct nand_chip *chip); void (*write_byte)(struct nand_chip *chip, u8 byte); void (*write_buf)(struct nand_chip *chip, const u8 *buf, int len); @@ -954,7 +956,6 @@ struct nand_legacy { * you're modifying an existing driver that is using those * fields/hooks, you should consider reworking the driver * avoid using them. - * @select_chip: [REPLACEABLE] select chip nr * @exec_op: controller specific method to execute NAND operations. * This method replaces ->cmdfunc(), * ->legacy.{read,write}_{buf,byte,word}(), @@ -1040,7 +1041,6 @@ struct nand_chip { struct nand_legacy legacy; - void (*select_chip)(struct nand_chip *chip, int cs); int (*exec_op)(struct nand_chip *chip, const struct nand_operation *op, bool check_only); From f2abfeb2078b9682bfeb77f91816fcf2177b3051 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:23 +0100 Subject: [PATCH 332/356] mtd: rawnand: Move the ->exec_op() method to nand_controller_ops ->exec_op() is a controller method and has nothing to do in the nand_chip struct. Let's move it to the nand_controller_ops struct and adjust the core and drivers accordingly. Signed-off-by: Boris Brezillon Tested-by: Janusz Krzysztofik Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/ams-delta.c | 7 +- drivers/mtd/nand/raw/fsmc_nand.c | 2 +- drivers/mtd/nand/raw/internals.h | 13 +++- drivers/mtd/nand/raw/marvell_nand.c | 2 +- drivers/mtd/nand/raw/nand_base.c | 51 +++++++-------- drivers/mtd/nand/raw/nand_hynix.c | 4 +- drivers/mtd/nand/raw/nand_legacy.c | 4 +- drivers/mtd/nand/raw/tegra_nand.c | 2 +- drivers/mtd/nand/raw/vf610_nfc.c | 4 +- include/linux/mtd/rawnand.h | 99 ++++++++++++++--------------- 10 files changed, 100 insertions(+), 88 deletions(-) diff --git a/drivers/mtd/nand/raw/ams-delta.c b/drivers/mtd/nand/raw/ams-delta.c index 611c822e967f..f8eb4a419e77 100644 --- a/drivers/mtd/nand/raw/ams-delta.c +++ b/drivers/mtd/nand/raw/ams-delta.c @@ -176,6 +176,10 @@ static int ams_delta_exec_op(struct nand_chip *this, return ret; } +static const struct nand_controller_ops ams_delta_ops = { + .exec_op = ams_delta_exec_op, +}; + /* * Main initialization routine */ @@ -216,8 +220,6 @@ static int ams_delta_init(struct platform_device *pdev) priv->io_base = io_base; nand_set_controller_data(this, priv); - this->exec_op = ams_delta_exec_op; - priv->gpiod_rdy = devm_gpiod_get_optional(&pdev->dev, "rdy", GPIOD_IN); if (IS_ERR(priv->gpiod_rdy)) { err = PTR_ERR(priv->gpiod_rdy); @@ -277,6 +279,7 @@ static int ams_delta_init(struct platform_device *pdev) ams_delta_dir_input(priv, true); /* Initialize the NAND controller object embedded in ams_delta_nand. */ + priv->base.ops = &ams_delta_ops; nand_controller_init(&priv->base); this->controller = &priv->base; diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c index ea69ac6e6d7a..1eb5008e7453 100644 --- a/drivers/mtd/nand/raw/fsmc_nand.c +++ b/drivers/mtd/nand/raw/fsmc_nand.c @@ -995,6 +995,7 @@ static int fsmc_nand_attach_chip(struct nand_chip *nand) static const struct nand_controller_ops fsmc_nand_controller_ops = { .attach_chip = fsmc_nand_attach_chip, + .exec_op = fsmc_exec_op, }; /* @@ -1082,7 +1083,6 @@ static int __init fsmc_nand_probe(struct platform_device *pdev) nand_set_flash_node(nand, pdev->dev.of_node); mtd->dev.parent = &pdev->dev; - nand->exec_op = fsmc_exec_op; /* * Setup default ECC mode. nand_dt_init() called from nand_scan_ident() diff --git a/drivers/mtd/nand/raw/internals.h b/drivers/mtd/nand/raw/internals.h index b62728d5884b..ac66b458566f 100644 --- a/drivers/mtd/nand/raw/internals.h +++ b/drivers/mtd/nand/raw/internals.h @@ -95,16 +95,25 @@ void nand_decode_ext_id(struct nand_chip *chip); void panic_nand_wait(struct nand_chip *chip, unsigned long timeo); void sanitize_string(uint8_t *s, size_t len); +static inline bool nand_has_exec_op(struct nand_chip *chip) +{ + if (!chip->controller || !chip->controller->ops || + !chip->controller->ops->exec_op) + return false; + + return true; +} + static inline int nand_exec_op(struct nand_chip *chip, const struct nand_operation *op) { - if (!chip->exec_op) + if (!nand_has_exec_op(chip)) return -ENOTSUPP; if (WARN_ON(op->cs >= chip->numchips)) return -EINVAL; - return chip->exec_op(chip, op, false); + return chip->controller->ops->exec_op(chip, op, false); } /* BBT functions */ diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c index ba7a45fb1905..2e8257fe7d00 100644 --- a/drivers/mtd/nand/raw/marvell_nand.c +++ b/drivers/mtd/nand/raw/marvell_nand.c @@ -2505,6 +2505,7 @@ static int marvell_nand_attach_chip(struct nand_chip *chip) static const struct nand_controller_ops marvell_nand_controller_ops = { .attach_chip = marvell_nand_attach_chip, + .exec_op = marvell_nfc_exec_op, }; static int marvell_nand_chip_init(struct device *dev, struct marvell_nfc *nfc, @@ -2627,7 +2628,6 @@ static int marvell_nand_chip_init(struct device *dev, struct marvell_nfc *nfc, chip->controller = &nfc->controller; nand_set_flash_node(chip, np); - chip->exec_op = marvell_nfc_exec_op; if (!of_property_read_bool(np, "marvell,nand-keep-config")) chip->setup_data_interface = marvell_nfc_setup_data_interface; diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index cef6633fdce9..eabef6a3857e 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -678,7 +678,7 @@ int nand_soft_waitrdy(struct nand_chip *chip, unsigned long timeout_ms) u8 status = 0; int ret; - if (!chip->exec_op) + if (!nand_has_exec_op(chip)) return -ENOTSUPP; /* Wait tWB before polling the STATUS reg. */ @@ -1117,7 +1117,7 @@ int nand_read_page_op(struct nand_chip *chip, unsigned int page, if (offset_in_page + len > mtd->writesize + mtd->oobsize) return -EINVAL; - if (chip->exec_op) { + if (nand_has_exec_op(chip)) { if (mtd->writesize > 512) return nand_lp_exec_read_page_op(chip, page, offset_in_page, buf, @@ -1156,7 +1156,7 @@ int nand_read_param_page_op(struct nand_chip *chip, u8 page, void *buf, if (len && !buf) return -EINVAL; - if (chip->exec_op) { + if (nand_has_exec_op(chip)) { const struct nand_sdr_timings *sdr = nand_get_sdr_timings(&chip->data_interface); struct nand_op_instr instrs[] = { @@ -1211,7 +1211,7 @@ int nand_change_read_column_op(struct nand_chip *chip, if (mtd->writesize <= 512) return -ENOTSUPP; - if (chip->exec_op) { + if (nand_has_exec_op(chip)) { const struct nand_sdr_timings *sdr = nand_get_sdr_timings(&chip->data_interface); u8 addrs[2] = {}; @@ -1270,7 +1270,7 @@ int nand_read_oob_op(struct nand_chip *chip, unsigned int page, if (offset_in_oob + len > mtd->oobsize) return -EINVAL; - if (chip->exec_op) + if (nand_has_exec_op(chip)) return nand_read_page_op(chip, page, mtd->writesize + offset_in_oob, buf, len); @@ -1383,7 +1383,7 @@ int nand_prog_page_begin_op(struct nand_chip *chip, unsigned int page, if (offset_in_page + len > mtd->writesize + mtd->oobsize) return -EINVAL; - if (chip->exec_op) + if (nand_has_exec_op(chip)) return nand_exec_prog_page_op(chip, page, offset_in_page, buf, len, false); @@ -1410,7 +1410,7 @@ int nand_prog_page_end_op(struct nand_chip *chip) int ret; u8 status; - if (chip->exec_op) { + if (nand_has_exec_op(chip)) { const struct nand_sdr_timings *sdr = nand_get_sdr_timings(&chip->data_interface); struct nand_op_instr instrs[] = { @@ -1469,7 +1469,7 @@ int nand_prog_page_op(struct nand_chip *chip, unsigned int page, if (offset_in_page + len > mtd->writesize + mtd->oobsize) return -EINVAL; - if (chip->exec_op) { + if (nand_has_exec_op(chip)) { status = nand_exec_prog_page_op(chip, page, offset_in_page, buf, len, true); } else { @@ -1517,7 +1517,7 @@ int nand_change_write_column_op(struct nand_chip *chip, if (mtd->writesize <= 512) return -ENOTSUPP; - if (chip->exec_op) { + if (nand_has_exec_op(chip)) { const struct nand_sdr_timings *sdr = nand_get_sdr_timings(&chip->data_interface); u8 addrs[2]; @@ -1572,7 +1572,7 @@ int nand_readid_op(struct nand_chip *chip, u8 addr, void *buf, if (len && !buf) return -EINVAL; - if (chip->exec_op) { + if (nand_has_exec_op(chip)) { const struct nand_sdr_timings *sdr = nand_get_sdr_timings(&chip->data_interface); struct nand_op_instr instrs[] = { @@ -1611,7 +1611,7 @@ EXPORT_SYMBOL_GPL(nand_readid_op); */ int nand_status_op(struct nand_chip *chip, u8 *status) { - if (chip->exec_op) { + if (nand_has_exec_op(chip)) { const struct nand_sdr_timings *sdr = nand_get_sdr_timings(&chip->data_interface); struct nand_op_instr instrs[] = { @@ -1648,7 +1648,7 @@ EXPORT_SYMBOL_GPL(nand_status_op); */ int nand_exit_status_op(struct nand_chip *chip) { - if (chip->exec_op) { + if (nand_has_exec_op(chip)) { struct nand_op_instr instrs[] = { NAND_OP_CMD(NAND_CMD_READ0, 0), }; @@ -1680,7 +1680,7 @@ int nand_erase_op(struct nand_chip *chip, unsigned int eraseblock) int ret; u8 status; - if (chip->exec_op) { + if (nand_has_exec_op(chip)) { const struct nand_sdr_timings *sdr = nand_get_sdr_timings(&chip->data_interface); u8 addrs[3] = { page, page >> 8, page >> 16 }; @@ -1739,7 +1739,7 @@ static int nand_set_features_op(struct nand_chip *chip, u8 feature, const u8 *params = data; int i, ret; - if (chip->exec_op) { + if (nand_has_exec_op(chip)) { const struct nand_sdr_timings *sdr = nand_get_sdr_timings(&chip->data_interface); struct nand_op_instr instrs[] = { @@ -1786,7 +1786,7 @@ static int nand_get_features_op(struct nand_chip *chip, u8 feature, u8 *params = data; int i; - if (chip->exec_op) { + if (nand_has_exec_op(chip)) { const struct nand_sdr_timings *sdr = nand_get_sdr_timings(&chip->data_interface); struct nand_op_instr instrs[] = { @@ -1812,7 +1812,7 @@ static int nand_get_features_op(struct nand_chip *chip, u8 feature, static int nand_wait_rdy_op(struct nand_chip *chip, unsigned int timeout_ms, unsigned int delay_ns) { - if (chip->exec_op) { + if (nand_has_exec_op(chip)) { struct nand_op_instr instrs[] = { NAND_OP_WAIT_RDY(PSEC_TO_MSEC(timeout_ms), PSEC_TO_NSEC(delay_ns)), @@ -1843,7 +1843,7 @@ static int nand_wait_rdy_op(struct nand_chip *chip, unsigned int timeout_ms, */ int nand_reset_op(struct nand_chip *chip) { - if (chip->exec_op) { + if (nand_has_exec_op(chip)) { const struct nand_sdr_timings *sdr = nand_get_sdr_timings(&chip->data_interface); struct nand_op_instr instrs[] = { @@ -1880,7 +1880,7 @@ int nand_read_data_op(struct nand_chip *chip, void *buf, unsigned int len, if (!len || !buf) return -EINVAL; - if (chip->exec_op) { + if (nand_has_exec_op(chip)) { struct nand_op_instr instrs[] = { NAND_OP_DATA_IN(len, buf, 0), }; @@ -1924,7 +1924,7 @@ int nand_write_data_op(struct nand_chip *chip, const void *buf, if (!len || !buf) return -EINVAL; - if (chip->exec_op) { + if (nand_has_exec_op(chip)) { struct nand_op_instr instrs[] = { NAND_OP_DATA_OUT(len, buf, 0), }; @@ -4417,13 +4417,14 @@ static void nand_shutdown(struct mtd_info *mtd) /* Set default functions */ static void nand_set_defaults(struct nand_chip *chip) { - nand_legacy_set_defaults(chip); - + /* If no controller is provided, use the dummy one. */ if (!chip->controller) { chip->controller = &chip->dummy_controller; nand_controller_init(chip->controller); } + nand_legacy_set_defaults(chip); + if (!chip->buf_align) chip->buf_align = 1; } @@ -5025,10 +5026,6 @@ static int nand_scan_ident(struct nand_chip *chip, unsigned int maxchips, if (!mtd->name && mtd->dev.parent) mtd->name = dev_name(mtd->dev.parent); - ret = nand_legacy_check_hooks(chip); - if (ret) - return ret; - /* * Start with chips->numchips = maxchips to let nand_select_target() do * its job. chip->numchips will be adjusted after. @@ -5038,6 +5035,10 @@ static int nand_scan_ident(struct nand_chip *chip, unsigned int maxchips, /* Set the default functions */ nand_set_defaults(chip); + ret = nand_legacy_check_hooks(chip); + if (ret) + return ret; + /* Read the flash type */ ret = nand_detect(chip, table); if (ret) { diff --git a/drivers/mtd/nand/raw/nand_hynix.c b/drivers/mtd/nand/raw/nand_hynix.c index 1e4499d01e14..343f477362d1 100644 --- a/drivers/mtd/nand/raw/nand_hynix.c +++ b/drivers/mtd/nand/raw/nand_hynix.c @@ -80,7 +80,7 @@ static bool hynix_nand_has_valid_jedecid(struct nand_chip *chip) static int hynix_nand_cmd_op(struct nand_chip *chip, u8 cmd) { - if (chip->exec_op) { + if (nand_has_exec_op(chip)) { struct nand_op_instr instrs[] = { NAND_OP_CMD(cmd, 0), }; @@ -98,7 +98,7 @@ static int hynix_nand_reg_write_op(struct nand_chip *chip, u8 addr, u8 val) { u16 column = ((u16)addr << 8) | addr; - if (chip->exec_op) { + if (nand_has_exec_op(chip)) { struct nand_op_instr instrs[] = { NAND_OP_ADDR(1, &addr, 0), NAND_OP_8BIT_DATA_OUT(1, &val, 0), diff --git a/drivers/mtd/nand/raw/nand_legacy.c b/drivers/mtd/nand/raw/nand_legacy.c index 4596a538b967..47364237861e 100644 --- a/drivers/mtd/nand/raw/nand_legacy.c +++ b/drivers/mtd/nand/raw/nand_legacy.c @@ -577,7 +577,7 @@ void nand_legacy_set_defaults(struct nand_chip *chip) { unsigned int busw = chip->options & NAND_BUSWIDTH_16; - if (chip->exec_op) + if (nand_has_exec_op(chip)) return; /* check for proper chip_delay setup, set 20us if not */ @@ -621,7 +621,7 @@ int nand_legacy_check_hooks(struct nand_chip *chip) * ->legacy.cmdfunc() is legacy and will only be used if ->exec_op() is * not populated. */ - if (chip->exec_op) + if (nand_has_exec_op(chip)) return 0; /* diff --git a/drivers/mtd/nand/raw/tegra_nand.c b/drivers/mtd/nand/raw/tegra_nand.c index 590393d93ffc..2fe6de09f4ff 100644 --- a/drivers/mtd/nand/raw/tegra_nand.c +++ b/drivers/mtd/nand/raw/tegra_nand.c @@ -1050,6 +1050,7 @@ static int tegra_nand_attach_chip(struct nand_chip *chip) static const struct nand_controller_ops tegra_nand_controller_ops = { .attach_chip = &tegra_nand_attach_chip, + .exec_op = tegra_nand_exec_op, }; static int tegra_nand_chips_init(struct device *dev, @@ -1112,7 +1113,6 @@ static int tegra_nand_chips_init(struct device *dev, mtd->name = "tegra_nand"; chip->options = NAND_NO_SUBPAGE_WRITE | NAND_USE_BOUNCE_BUFFER; - chip->exec_op = tegra_nand_exec_op; chip->setup_data_interface = tegra_nand_setup_data_interface; ret = nand_scan(chip, 1); diff --git a/drivers/mtd/nand/raw/vf610_nfc.c b/drivers/mtd/nand/raw/vf610_nfc.c index 49a174e30211..0fa7cac4ce14 100644 --- a/drivers/mtd/nand/raw/vf610_nfc.c +++ b/drivers/mtd/nand/raw/vf610_nfc.c @@ -812,6 +812,8 @@ static int vf610_nfc_attach_chip(struct nand_chip *chip) static const struct nand_controller_ops vf610_nfc_controller_ops = { .attach_chip = vf610_nfc_attach_chip, + .exec_op = vf610_nfc_exec_op, + }; static int vf610_nfc_probe(struct platform_device *pdev) @@ -879,8 +881,6 @@ static int vf610_nfc_probe(struct platform_device *pdev) goto err_disable_clk; } - chip->exec_op = vf610_nfc_exec_op; - chip->options |= NAND_NO_SUBPAGE_WRITE; init_completion(&nfc->cmd_done); diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 40b74fb1792d..297b40c56403 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -240,49 +240,6 @@ struct nand_id { int len; }; -/** - * struct nand_controller_ops - Controller operations - * - * @attach_chip: this method is called after the NAND detection phase after - * flash ID and MTD fields such as erase size, page size and OOB - * size have been set up. ECC requirements are available if - * provided by the NAND chip or device tree. Typically used to - * choose the appropriate ECC configuration and allocate - * associated resources. - * This hook is optional. - * @detach_chip: free all resources allocated/claimed in - * nand_controller_ops->attach_chip(). - * This hook is optional. - */ -struct nand_controller_ops { - int (*attach_chip)(struct nand_chip *chip); - void (*detach_chip)(struct nand_chip *chip); -}; - -/** - * struct nand_controller - Structure used to describe a NAND controller - * - * @lock: protection lock - * @active: the mtd device which holds the controller currently - * @wq: wait queue to sleep on if a NAND operation is in - * progress used instead of the per chip wait queue - * when a hw controller is available. - * @ops: NAND controller operations. - */ -struct nand_controller { - spinlock_t lock; - struct nand_chip *active; - wait_queue_head_t wq; - const struct nand_controller_ops *ops; -}; - -static inline void nand_controller_init(struct nand_controller *nfc) -{ - nfc->active = NULL; - spin_lock_init(&nfc->lock); - init_waitqueue_head(&nfc->wq); -} - /** * struct nand_ecc_step_info - ECC step information of ECC engine * @stepsize: data bytes per ECC step @@ -897,6 +854,55 @@ struct nand_operation { int nand_op_parser_exec_op(struct nand_chip *chip, const struct nand_op_parser *parser, const struct nand_operation *op, bool check_only); +/** + * struct nand_controller_ops - Controller operations + * + * @attach_chip: this method is called after the NAND detection phase after + * flash ID and MTD fields such as erase size, page size and OOB + * size have been set up. ECC requirements are available if + * provided by the NAND chip or device tree. Typically used to + * choose the appropriate ECC configuration and allocate + * associated resources. + * This hook is optional. + * @detach_chip: free all resources allocated/claimed in + * nand_controller_ops->attach_chip(). + * This hook is optional. + * @exec_op: controller specific method to execute NAND operations. + * This method replaces chip->legacy.cmdfunc(), + * chip->legacy.{read,write}_{buf,byte,word}(), + * chip->legacy.dev_ready() and chip->legacy.waifunc(). + */ +struct nand_controller_ops { + int (*attach_chip)(struct nand_chip *chip); + void (*detach_chip)(struct nand_chip *chip); + int (*exec_op)(struct nand_chip *chip, + const struct nand_operation *op, + bool check_only); +}; + +/** + * struct nand_controller - Structure used to describe a NAND controller + * + * @lock: protection lock + * @active: the mtd device which holds the controller currently + * @wq: wait queue to sleep on if a NAND operation is in + * progress used instead of the per chip wait queue + * when a hw controller is available. + * @ops: NAND controller operations. + */ +struct nand_controller { + spinlock_t lock; + struct nand_chip *active; + wait_queue_head_t wq; + const struct nand_controller_ops *ops; +}; + +static inline void nand_controller_init(struct nand_controller *nfc) +{ + nfc->active = NULL; + spin_lock_init(&nfc->lock); + init_waitqueue_head(&nfc->wq); +} /** * struct nand_legacy - NAND chip legacy fields/hooks @@ -956,10 +962,6 @@ struct nand_legacy { * you're modifying an existing driver that is using those * fields/hooks, you should consider reworking the driver * avoid using them. - * @exec_op: controller specific method to execute NAND operations. - * This method replaces ->cmdfunc(), - * ->legacy.{read,write}_{buf,byte,word}(), - * ->legacy.dev_ready() and ->waifunc(). * @setup_read_retry: [FLASHSPECIFIC] flash (vendor) specific function for * setting the read-retry mode. Mostly needed for MLC NAND. * @ecc: [BOARDSPECIFIC] ECC control structure @@ -1041,9 +1043,6 @@ struct nand_chip { struct nand_legacy legacy; - int (*exec_op)(struct nand_chip *chip, - const struct nand_operation *op, - bool check_only); int (*setup_read_retry)(struct nand_chip *chip, int retry_mode); int (*setup_data_interface)(struct nand_chip *chip, int chipnr, const struct nand_data_interface *conf); From 7a08dbaedd365fa4eb7c9cd504c075e3336eb0c6 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 11 Nov 2018 08:55:24 +0100 Subject: [PATCH 333/356] mtd: rawnand: Move ->setup_data_interface() to nand_controller_ops ->setup_data_interface() is a controller specific method and should thus be placed in nand_controller_ops. In order to make that work with controllers that support keeping pre-configured timings we need to add a new NAND_KEEP_TIMINGS flag to inform the core it should skip the timings selection step. Signed-off-by: Boris Brezillon Tested-by: Janusz Krzysztofik Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/atmel/nand-controller.c | 5 +++-- drivers/mtd/nand/raw/denali.c | 3 ++- drivers/mtd/nand/raw/fsmc_nand.c | 7 ++++--- drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c | 2 +- drivers/mtd/nand/raw/internals.h | 12 ++++++++++++ drivers/mtd/nand/raw/marvell_nand.c | 3 ++- drivers/mtd/nand/raw/mtk_nand.c | 2 +- drivers/mtd/nand/raw/mxc_nand.c | 12 +++++++++++- drivers/mtd/nand/raw/nand_base.c | 14 ++++++++------ drivers/mtd/nand/raw/nand_legacy.c | 2 +- drivers/mtd/nand/raw/s3c2410.c | 5 +++-- drivers/mtd/nand/raw/sunxi_nand.c | 2 +- drivers/mtd/nand/raw/tango_nand.c | 2 +- drivers/mtd/nand/raw/tegra_nand.c | 2 +- include/linux/mtd/rawnand.h | 20 ++++++++++++++------ 15 files changed, 65 insertions(+), 28 deletions(-) diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c index d5c58eb040d8..dcd3bd73e549 100644 --- a/drivers/mtd/nand/raw/atmel/nand-controller.c +++ b/drivers/mtd/nand/raw/atmel/nand-controller.c @@ -1479,8 +1479,8 @@ static void atmel_nand_init(struct atmel_nand_controller *nc, chip->legacy.write_buf = atmel_nand_write_buf; chip->legacy.select_chip = atmel_nand_select_chip; - if (nc->mck && nc->caps->ops->setup_data_interface) - chip->setup_data_interface = atmel_nand_setup_data_interface; + if (!nc->mck || !nc->caps->ops->setup_data_interface) + chip->options |= NAND_KEEP_TIMINGS; /* Some NANDs require a longer delay than the default one (20us). */ chip->legacy.chip_delay = 40; @@ -1908,6 +1908,7 @@ static int atmel_nand_attach_chip(struct nand_chip *chip) static const struct nand_controller_ops atmel_nand_controller_ops = { .attach_chip = atmel_nand_attach_chip, + .setup_data_interface = atmel_nand_setup_data_interface, }; static int atmel_nand_controller_init(struct atmel_nand_controller *nc, diff --git a/drivers/mtd/nand/raw/denali.c b/drivers/mtd/nand/raw/denali.c index 64895ca68c8d..bad3b8ad5e0a 100644 --- a/drivers/mtd/nand/raw/denali.c +++ b/drivers/mtd/nand/raw/denali.c @@ -1316,6 +1316,7 @@ static void denali_detach_chip(struct nand_chip *chip) static const struct nand_controller_ops denali_controller_ops = { .attach_chip = denali_attach_chip, .detach_chip = denali_detach_chip, + .setup_data_interface = denali_setup_data_interface, }; int denali_init(struct denali_nand_info *denali) @@ -1372,7 +1373,7 @@ int denali_init(struct denali_nand_info *denali) /* clk rate info is needed for setup_data_interface */ if (denali->clk_rate && denali->clk_x_rate) - chip->setup_data_interface = denali_setup_data_interface; + chip->options |= NAND_KEEP_TIMINGS; chip->dummy_controller.ops = &denali_controller_ops; ret = nand_scan(chip, denali->max_banks); diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c index 1eb5008e7453..61927c4c2650 100644 --- a/drivers/mtd/nand/raw/fsmc_nand.c +++ b/drivers/mtd/nand/raw/fsmc_nand.c @@ -996,6 +996,7 @@ static int fsmc_nand_attach_chip(struct nand_chip *nand) static const struct nand_controller_ops fsmc_nand_controller_ops = { .attach_chip = fsmc_nand_attach_chip, .exec_op = fsmc_exec_op, + .setup_data_interface = fsmc_setup_data_interface, }; /* @@ -1108,10 +1109,10 @@ static int __init fsmc_nand_probe(struct platform_device *pdev) } } - if (host->dev_timings) + if (host->dev_timings) { fsmc_nand_setup(host, host->dev_timings); - else - nand->setup_data_interface = fsmc_setup_data_interface; + nand->options |= NAND_KEEP_TIMINGS; + } if (AMBA_REV_BITS(host->pid) >= 8) { nand->ecc.read_page = fsmc_read_page_hwecc; diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c index c461d5efabc0..25f9fe79796a 100644 --- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c +++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c @@ -1889,6 +1889,7 @@ static int gpmi_nand_attach_chip(struct nand_chip *chip) static const struct nand_controller_ops gpmi_nand_controller_ops = { .attach_chip = gpmi_nand_attach_chip, + .setup_data_interface = gpmi_setup_data_interface, }; static int gpmi_nand_init(struct gpmi_nand_data *this) @@ -1908,7 +1909,6 @@ static int gpmi_nand_init(struct gpmi_nand_data *this) nand_set_controller_data(chip, this); nand_set_flash_node(chip, this->pdev->dev.of_node); chip->legacy.select_chip = gpmi_select_chip; - chip->setup_data_interface = gpmi_setup_data_interface; chip->legacy.cmd_ctrl = gpmi_cmd_ctrl; chip->legacy.dev_ready = gpmi_dev_ready; chip->legacy.read_byte = gpmi_read_byte; diff --git a/drivers/mtd/nand/raw/internals.h b/drivers/mtd/nand/raw/internals.h index ac66b458566f..fbf6ca015cd7 100644 --- a/drivers/mtd/nand/raw/internals.h +++ b/drivers/mtd/nand/raw/internals.h @@ -116,6 +116,18 @@ static inline int nand_exec_op(struct nand_chip *chip, return chip->controller->ops->exec_op(chip, op, false); } +static inline bool nand_has_setup_data_iface(struct nand_chip *chip) +{ + if (!chip->controller || !chip->controller->ops || + !chip->controller->ops->setup_data_interface) + return false; + + if (chip->options & NAND_KEEP_TIMINGS) + return false; + + return true; +} + /* BBT functions */ int nand_markbad_bbt(struct nand_chip *chip, loff_t offs); int nand_isreserved_bbt(struct nand_chip *chip, loff_t offs); diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c index 2e8257fe7d00..b7b4d9b14da1 100644 --- a/drivers/mtd/nand/raw/marvell_nand.c +++ b/drivers/mtd/nand/raw/marvell_nand.c @@ -2506,6 +2506,7 @@ static int marvell_nand_attach_chip(struct nand_chip *chip) static const struct nand_controller_ops marvell_nand_controller_ops = { .attach_chip = marvell_nand_attach_chip, .exec_op = marvell_nfc_exec_op, + .setup_data_interface = marvell_nfc_setup_data_interface, }; static int marvell_nand_chip_init(struct device *dev, struct marvell_nfc *nfc, @@ -2629,7 +2630,7 @@ static int marvell_nand_chip_init(struct device *dev, struct marvell_nfc *nfc, nand_set_flash_node(chip, np); if (!of_property_read_bool(np, "marvell,nand-keep-config")) - chip->setup_data_interface = marvell_nfc_setup_data_interface; + chip->options |= NAND_KEEP_TIMINGS; mtd = nand_to_mtd(chip); mtd->dev.parent = dev; diff --git a/drivers/mtd/nand/raw/mtk_nand.c b/drivers/mtd/nand/raw/mtk_nand.c index ce124f8c02cd..b6b4602f5132 100644 --- a/drivers/mtd/nand/raw/mtk_nand.c +++ b/drivers/mtd/nand/raw/mtk_nand.c @@ -1288,6 +1288,7 @@ static int mtk_nfc_attach_chip(struct nand_chip *chip) static const struct nand_controller_ops mtk_nfc_controller_ops = { .attach_chip = mtk_nfc_attach_chip, + .setup_data_interface = mtk_nfc_setup_data_interface, }; static int mtk_nfc_nand_chip_init(struct device *dev, struct mtk_nfc *nfc, @@ -1339,7 +1340,6 @@ static int mtk_nfc_nand_chip_init(struct device *dev, struct mtk_nfc *nfc, nand->legacy.read_byte = mtk_nfc_read_byte; nand->legacy.read_buf = mtk_nfc_read_buf; nand->legacy.cmd_ctrl = mtk_nfc_cmd_ctrl; - nand->setup_data_interface = mtk_nfc_setup_data_interface; /* set default mode in case dt entry is missing */ nand->ecc.mode = NAND_ECC_HW; diff --git a/drivers/mtd/nand/raw/mxc_nand.c b/drivers/mtd/nand/raw/mxc_nand.c index c00b1d408a04..9b75d894cb74 100644 --- a/drivers/mtd/nand/raw/mxc_nand.c +++ b/drivers/mtd/nand/raw/mxc_nand.c @@ -1738,8 +1738,17 @@ static int mxcnd_attach_chip(struct nand_chip *chip) return 0; } +static int mxcnd_setup_data_interface(struct nand_chip *chip, int chipnr, + const struct nand_data_interface *conf) +{ + struct mxc_nand_host *host = nand_get_controller_data(chip); + + return host->devtype_data->setup_data_interface(chip, chipnr, conf); +} + static const struct nand_controller_ops mxcnd_controller_ops = { .attach_chip = mxcnd_attach_chip, + .setup_data_interface = mxcnd_setup_data_interface, }; static int mxcnd_probe(struct platform_device *pdev) @@ -1800,7 +1809,8 @@ static int mxcnd_probe(struct platform_device *pdev) if (err < 0) return err; - this->setup_data_interface = host->devtype_data->setup_data_interface; + if (!host->devtype_data->setup_data_interface) + this->options |= NAND_KEEP_TIMINGS; if (host->devtype_data->needs_ip) { res = platform_get_resource(pdev, IORESOURCE_MEM, 0); diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index eabef6a3857e..3fc5c00f8dba 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -807,7 +807,7 @@ static int nand_reset_data_interface(struct nand_chip *chip, int chipnr) { int ret; - if (!chip->setup_data_interface) + if (!nand_has_setup_data_iface(chip)) return 0; /* @@ -825,7 +825,8 @@ static int nand_reset_data_interface(struct nand_chip *chip, int chipnr) */ onfi_fill_data_interface(chip, NAND_SDR_IFACE, 0); - ret = chip->setup_data_interface(chip, chipnr, &chip->data_interface); + ret = chip->controller->ops->setup_data_interface(chip, chipnr, + &chip->data_interface); if (ret) pr_err("Failed to configure data interface to SDR timing mode 0\n"); @@ -852,7 +853,7 @@ static int nand_setup_data_interface(struct nand_chip *chip, int chipnr) }; int ret; - if (!chip->setup_data_interface) + if (!nand_has_setup_data_iface(chip)) return 0; /* Change the mode on the chip side (if supported by the NAND chip) */ @@ -866,7 +867,8 @@ static int nand_setup_data_interface(struct nand_chip *chip, int chipnr) } /* Change the mode on the controller side */ - ret = chip->setup_data_interface(chip, chipnr, &chip->data_interface); + ret = chip->controller->ops->setup_data_interface(chip, chipnr, + &chip->data_interface); if (ret) return ret; @@ -921,7 +923,7 @@ static int nand_init_data_interface(struct nand_chip *chip) { int modes, mode, ret; - if (!chip->setup_data_interface) + if (!nand_has_setup_data_iface(chip)) return 0; /* @@ -947,7 +949,7 @@ static int nand_init_data_interface(struct nand_chip *chip) * Pass NAND_DATA_IFACE_CHECK_ONLY to only check if the * controller supports the requested timings. */ - ret = chip->setup_data_interface(chip, + ret = chip->controller->ops->setup_data_interface(chip, NAND_DATA_IFACE_CHECK_ONLY, &chip->data_interface); if (!ret) { diff --git a/drivers/mtd/nand/raw/nand_legacy.c b/drivers/mtd/nand/raw/nand_legacy.c index 47364237861e..43575943f13b 100644 --- a/drivers/mtd/nand/raw/nand_legacy.c +++ b/drivers/mtd/nand/raw/nand_legacy.c @@ -364,7 +364,7 @@ static void nand_ccs_delay(struct nand_chip *chip) * Wait tCCS_min if it is correctly defined, otherwise wait 500ns * (which should be safe for all NANDs). */ - if (chip->setup_data_interface) + if (nand_has_setup_data_iface(chip)) ndelay(chip->data_interface.timings.sdr.tCCS_min / 1000); else ndelay(500); diff --git a/drivers/mtd/nand/raw/s3c2410.c b/drivers/mtd/nand/raw/s3c2410.c index a8905463701a..adc7a196e383 100644 --- a/drivers/mtd/nand/raw/s3c2410.c +++ b/drivers/mtd/nand/raw/s3c2410.c @@ -876,8 +876,8 @@ static void s3c2410_nand_init_chip(struct s3c2410_nand_info *info, * let's keep behavior unchanged for legacy boards booting via pdata and * auto-detect timings only when booting with a device tree. */ - if (np) - chip->setup_data_interface = s3c2410_nand_setup_data_interface; + if (!np) + chip->options |= NAND_KEEP_TIMINGS; switch (info->cpu_type) { case TYPE_S3C2410: @@ -1011,6 +1011,7 @@ static int s3c2410_nand_attach_chip(struct nand_chip *chip) static const struct nand_controller_ops s3c24xx_nand_controller_ops = { .attach_chip = s3c2410_nand_attach_chip, + .setup_data_interface = s3c2410_nand_setup_data_interface, }; static const struct of_device_id s3c24xx_nand_dt_ids[] = { diff --git a/drivers/mtd/nand/raw/sunxi_nand.c b/drivers/mtd/nand/raw/sunxi_nand.c index e489a6ff57d7..a5c83cbe4897 100644 --- a/drivers/mtd/nand/raw/sunxi_nand.c +++ b/drivers/mtd/nand/raw/sunxi_nand.c @@ -1847,6 +1847,7 @@ static int sunxi_nand_attach_chip(struct nand_chip *nand) static const struct nand_controller_ops sunxi_nand_controller_ops = { .attach_chip = sunxi_nand_attach_chip, + .setup_data_interface = sunxi_nfc_setup_data_interface, }; static int sunxi_nand_chip_init(struct device *dev, struct sunxi_nfc *nfc, @@ -1927,7 +1928,6 @@ static int sunxi_nand_chip_init(struct device *dev, struct sunxi_nfc *nfc, nand->legacy.read_buf = sunxi_nfc_read_buf; nand->legacy.write_buf = sunxi_nfc_write_buf; nand->legacy.read_byte = sunxi_nfc_read_byte; - nand->setup_data_interface = sunxi_nfc_setup_data_interface; mtd = nand_to_mtd(nand); mtd->dev.parent = dev; diff --git a/drivers/mtd/nand/raw/tango_nand.c b/drivers/mtd/nand/raw/tango_nand.c index ebca4579c033..cb3beda88789 100644 --- a/drivers/mtd/nand/raw/tango_nand.c +++ b/drivers/mtd/nand/raw/tango_nand.c @@ -530,6 +530,7 @@ static int tango_attach_chip(struct nand_chip *chip) static const struct nand_controller_ops tango_controller_ops = { .attach_chip = tango_attach_chip, + .setup_data_interface = tango_set_timings, }; static int chip_init(struct device *dev, struct device_node *np) @@ -570,7 +571,6 @@ static int chip_init(struct device *dev, struct device_node *np) chip->legacy.select_chip = tango_select_chip; chip->legacy.cmd_ctrl = tango_cmd_ctrl; chip->legacy.dev_ready = tango_dev_ready; - chip->setup_data_interface = tango_set_timings; chip->options = NAND_USE_BOUNCE_BUFFER | NAND_NO_SUBPAGE_WRITE | NAND_WAIT_TCCS; diff --git a/drivers/mtd/nand/raw/tegra_nand.c b/drivers/mtd/nand/raw/tegra_nand.c index 2fe6de09f4ff..13be32c38194 100644 --- a/drivers/mtd/nand/raw/tegra_nand.c +++ b/drivers/mtd/nand/raw/tegra_nand.c @@ -1051,6 +1051,7 @@ static int tegra_nand_attach_chip(struct nand_chip *chip) static const struct nand_controller_ops tegra_nand_controller_ops = { .attach_chip = &tegra_nand_attach_chip, .exec_op = tegra_nand_exec_op, + .setup_data_interface = tegra_nand_setup_data_interface, }; static int tegra_nand_chips_init(struct device *dev, @@ -1113,7 +1114,6 @@ static int tegra_nand_chips_init(struct device *dev, mtd->name = "tegra_nand"; chip->options = NAND_NO_SUBPAGE_WRITE | NAND_USE_BOUNCE_BUFFER; - chip->setup_data_interface = tegra_nand_setup_data_interface; ret = nand_scan(chip, 1); if (ret) diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 297b40c56403..f50f40643895 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -203,6 +203,13 @@ enum nand_ecc_algo { */ #define NAND_IS_BOOT_MEDIUM 0x00400000 +/* + * Do not try to tweak the timings at runtime. This is needed when the + * controller initializes the timings on itself or when it relies on + * configuration done by the bootloader. + */ +#define NAND_KEEP_TIMINGS 0x00800000 + /* Cell info constants */ #define NAND_CI_CHIPNR_MSK 0x03 #define NAND_CI_CELLTYPE_MSK 0x0C @@ -871,6 +878,11 @@ int nand_op_parser_exec_op(struct nand_chip *chip, * This method replaces chip->legacy.cmdfunc(), * chip->legacy.{read,write}_{buf,byte,word}(), * chip->legacy.dev_ready() and chip->legacy.waifunc(). + * @setup_data_interface: setup the data interface and timing. If + * chipnr is set to %NAND_DATA_IFACE_CHECK_ONLY this + * means the configuration should not be applied but + * only checked. + * This hook is optional. */ struct nand_controller_ops { int (*attach_chip)(struct nand_chip *chip); @@ -878,6 +890,8 @@ struct nand_controller_ops { int (*exec_op)(struct nand_chip *chip, const struct nand_operation *op, bool check_only); + int (*setup_data_interface)(struct nand_chip *chip, int chipnr, + const struct nand_data_interface *conf); }; /** @@ -1019,10 +1033,6 @@ struct nand_legacy { * cur_cs < numchips. NAND Controller drivers should not * modify this value, but they're allowed to read it. * @read_retries: [INTERN] the number of read retry modes supported - * @setup_data_interface: [OPTIONAL] setup the data interface and timing. If - * chipnr is set to %NAND_DATA_IFACE_CHECK_ONLY this - * means the configuration should not be applied but - * only checked. * @bbt: [INTERN] bad block table pointer * @bbt_td: [REPLACEABLE] bad block table descriptor for flash * lookup. @@ -1044,8 +1054,6 @@ struct nand_chip { struct nand_legacy legacy; int (*setup_read_retry)(struct nand_chip *chip, int retry_mode); - int (*setup_data_interface)(struct nand_chip *chip, int chipnr, - const struct nand_data_interface *conf); unsigned int options; unsigned int bbt_options; From 02e1ca60f4c36c0f9635f79e172b72d811b8a627 Mon Sep 17 00:00:00 2001 From: Janusz Krzysztofik Date: Wed, 21 Nov 2018 12:08:03 +0100 Subject: [PATCH 334/356] ARM: OMAP1: ams-delta: Provide GPIO lookup table for NAND data port Data port used by Amstrad Delta NAND driver is actually an OMAP MPUIO device, already under control of gpio-omap driver. The NAND driver gets access to the port by ioremapping it and performs read/write operations. That is done without any proteciton from other users legally manipulating the port pins over GPIO API. The plan is to convert the driver to access the port over GPIO consumer API. Before that is implemented, the driver can already obtain exclusive access to the port by requesting an array of its GPIO descriptors. Add respective entries to the NAND GPIO lookup table. Signed-off-by: Janusz Krzysztofik Reviewed-by: Boris Brezillon Reviewed-by: Linus Walleij Acked-by: Tony Lindgren Signed-off-by: Miquel Raynal --- arch/arm/mach-omap1/board-ams-delta.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/arch/arm/mach-omap1/board-ams-delta.c b/arch/arm/mach-omap1/board-ams-delta.c index 3d191fd52910..30c0d18f372e 100644 --- a/arch/arm/mach-omap1/board-ams-delta.c +++ b/arch/arm/mach-omap1/board-ams-delta.c @@ -312,7 +312,8 @@ static struct platform_device ams_delta_nand_device = { .resource = ams_delta_nand_resources, }; -#define OMAP_GPIO_LABEL "gpio-0-15" +#define OMAP_GPIO_LABEL "gpio-0-15" +#define OMAP_MPUIO_LABEL "mpuio" static struct gpiod_lookup_table ams_delta_nand_gpio_table = { .table = { @@ -324,6 +325,14 @@ static struct gpiod_lookup_table ams_delta_nand_gpio_table = { GPIO_LOOKUP(LATCH2_LABEL, LATCH2_PIN_NAND_NWE, "nwe", 0), GPIO_LOOKUP(LATCH2_LABEL, LATCH2_PIN_NAND_ALE, "ale", 0), GPIO_LOOKUP(LATCH2_LABEL, LATCH2_PIN_NAND_CLE, "cle", 0), + GPIO_LOOKUP_IDX(OMAP_MPUIO_LABEL, 0, "data", 0, 0), + GPIO_LOOKUP_IDX(OMAP_MPUIO_LABEL, 1, "data", 1, 0), + GPIO_LOOKUP_IDX(OMAP_MPUIO_LABEL, 2, "data", 2, 0), + GPIO_LOOKUP_IDX(OMAP_MPUIO_LABEL, 3, "data", 3, 0), + GPIO_LOOKUP_IDX(OMAP_MPUIO_LABEL, 4, "data", 4, 0), + GPIO_LOOKUP_IDX(OMAP_MPUIO_LABEL, 5, "data", 5, 0), + GPIO_LOOKUP_IDX(OMAP_MPUIO_LABEL, 6, "data", 6, 0), + GPIO_LOOKUP_IDX(OMAP_MPUIO_LABEL, 7, "data", 7, 0), { }, }, }; From 9773861304f15bec54b55ff1b6e6e6a7f99ebe5b Mon Sep 17 00:00:00 2001 From: Janusz Krzysztofik Date: Wed, 21 Nov 2018 12:08:04 +0100 Subject: [PATCH 335/356] mtd: rawnand: ams-delta: Request data port GPIO resource Data port used by the driver is actually an OMAP MPUIO device, already under control of gpio-omap driver. For that reason we used to not request the memory region of the port as that would fail because the region is already busy. Despite that, we are still accessing the port by just ioremapping it and performing read/write operations. Moreover, we are doing that without any proteciton from other users legally manipulating the port pins over GPIO API. The plan is to convert the driver to access the port over GPIO consumer API. Before that happens, already prevent from other users accessing the port pins by requesting an array of its GPIO descriptors. Signed-off-by: Janusz Krzysztofik Reviewed-by: Boris Brezillon Reviewed-by: Linus Walleij Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/ams-delta.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/nand/raw/ams-delta.c b/drivers/mtd/nand/raw/ams-delta.c index f8eb4a419e77..bb50dda05654 100644 --- a/drivers/mtd/nand/raw/ams-delta.c +++ b/drivers/mtd/nand/raw/ams-delta.c @@ -190,6 +190,7 @@ static int ams_delta_init(struct platform_device *pdev) struct mtd_info *mtd; struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); void __iomem *io_base; + struct gpio_descs *data_gpiods; int err = 0; if (!res) @@ -275,8 +276,14 @@ static int ams_delta_init(struct platform_device *pdev) goto err_unmap; } - /* Initialize data port direction to a known state */ - ams_delta_dir_input(priv, true); + /* Request array of data pins, initialize them as input */ + data_gpiods = devm_gpiod_get_array(&pdev->dev, "data", GPIOD_IN); + if (IS_ERR(data_gpiods)) { + err = PTR_ERR(data_gpiods); + dev_err(&pdev->dev, "data GPIO request failed: %d\n", err); + goto err_unmap; + } + priv->data_in = true; /* Initialize the NAND controller object embedded in ams_delta_nand. */ priv->base.ops = &ams_delta_ops; From 7416bd35008c0fbd4aff9fdb267ff67b7bc4ea77 Mon Sep 17 00:00:00 2001 From: Janusz Krzysztofik Date: Wed, 21 Nov 2018 12:08:05 +0100 Subject: [PATCH 336/356] mtd: rawnand: ams-delta: Use GPIO API for data I/O Don't readw()/writew() data directly from/to GPIO port which is under control of gpio-omap driver, use GPIO consumer API instead. The driver should now work with any 8-bit bidirectional GPIO port, not only OMAP. Signed-off-by: Janusz Krzysztofik Reviewed-by: Linus Walleij Reviewed-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/ams-delta.c | 109 +++++++++++++++++-------------- 1 file changed, 61 insertions(+), 48 deletions(-) diff --git a/drivers/mtd/nand/raw/ams-delta.c b/drivers/mtd/nand/raw/ams-delta.c index bb50dda05654..8312182088c1 100644 --- a/drivers/mtd/nand/raw/ams-delta.c +++ b/drivers/mtd/nand/raw/ams-delta.c @@ -18,11 +18,10 @@ #include #include #include -#include #include #include #include -#include +#include #include /* @@ -38,7 +37,7 @@ struct ams_delta_nand { struct gpio_desc *gpiod_nwe; struct gpio_desc *gpiod_ale; struct gpio_desc *gpiod_cle; - void __iomem *io_base; + struct gpio_descs *data_gpiods; bool data_in; }; @@ -67,42 +66,78 @@ static const struct mtd_partition partition_info[] = { .size = 3 * SZ_256K }, }; -static void ams_delta_io_write(struct ams_delta_nand *priv, u8 byte) +static void ams_delta_write_commit(struct ams_delta_nand *priv) { - writew(byte, priv->io_base + OMAP_MPUIO_OUTPUT); gpiod_set_value(priv->gpiod_nwe, 0); ndelay(40); gpiod_set_value(priv->gpiod_nwe, 1); } +static void ams_delta_io_write(struct ams_delta_nand *priv, u8 byte) +{ + struct gpio_descs *data_gpiods = priv->data_gpiods; + DECLARE_BITMAP(values, BITS_PER_TYPE(byte)) = { byte, }; + + gpiod_set_raw_array_value(data_gpiods->ndescs, data_gpiods->desc, + data_gpiods->info, values); + + ams_delta_write_commit(priv); +} + +static void ams_delta_dir_output(struct ams_delta_nand *priv, u8 byte) +{ + struct gpio_descs *data_gpiods = priv->data_gpiods; + DECLARE_BITMAP(values, BITS_PER_TYPE(byte)) = { byte, }; + int i; + + for (i = 0; i < data_gpiods->ndescs; i++) + gpiod_direction_output_raw(data_gpiods->desc[i], + test_bit(i, values)); + + ams_delta_write_commit(priv); + + priv->data_in = false; +} + static u8 ams_delta_io_read(struct ams_delta_nand *priv) { u8 res; + struct gpio_descs *data_gpiods = priv->data_gpiods; + DECLARE_BITMAP(values, BITS_PER_TYPE(res)) = { 0, }; gpiod_set_value(priv->gpiod_nre, 0); ndelay(40); - res = readw(priv->io_base + OMAP_MPUIO_INPUT_LATCH); + + gpiod_get_raw_array_value(data_gpiods->ndescs, data_gpiods->desc, + data_gpiods->info, values); + gpiod_set_value(priv->gpiod_nre, 1); + res = values[0]; return res; } -static void ams_delta_dir_input(struct ams_delta_nand *priv, bool in) +static void ams_delta_dir_input(struct ams_delta_nand *priv) { - writew(in ? ~0 : 0, priv->io_base + OMAP_MPUIO_IO_CNTL); - priv->data_in = in; + struct gpio_descs *data_gpiods = priv->data_gpiods; + int i; + + for (i = 0; i < data_gpiods->ndescs; i++) + gpiod_direction_input(data_gpiods->desc[i]); + + priv->data_in = true; } static void ams_delta_write_buf(struct ams_delta_nand *priv, const u8 *buf, int len) { - int i; + int i = 0; - if (priv->data_in) - ams_delta_dir_input(priv, false); + if (len > 0 && priv->data_in) + ams_delta_dir_output(priv, buf[i++]); - for (i = 0; i < len; i++) - ams_delta_io_write(priv, buf[i]); + while (i < len) + ams_delta_io_write(priv, buf[i++]); } static void ams_delta_read_buf(struct ams_delta_nand *priv, u8 *buf, int len) @@ -110,7 +145,7 @@ static void ams_delta_read_buf(struct ams_delta_nand *priv, u8 *buf, int len) int i; if (!priv->data_in) - ams_delta_dir_input(priv, true); + ams_delta_dir_input(priv); for (i = 0; i < len; i++) buf[i] = ams_delta_io_read(priv); @@ -188,14 +223,9 @@ static int ams_delta_init(struct platform_device *pdev) struct ams_delta_nand *priv; struct nand_chip *this; struct mtd_info *mtd; - struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - void __iomem *io_base; struct gpio_descs *data_gpiods; int err = 0; - if (!res) - return -ENXIO; - /* Allocate memory for MTD device structure and private data */ priv = devm_kzalloc(&pdev->dev, sizeof(struct ams_delta_nand), GFP_KERNEL); @@ -207,25 +237,13 @@ static int ams_delta_init(struct platform_device *pdev) mtd = nand_to_mtd(this); mtd->dev.parent = &pdev->dev; - /* - * Don't try to request the memory region from here, - * it should have been already requested from the - * gpio-omap driver and requesting it again would fail. - */ - io_base = ioremap(res->start, resource_size(res)); - if (!io_base) { - dev_err(&pdev->dev, "ioremap failed\n"); - return -EIO; - } - - priv->io_base = io_base; nand_set_controller_data(this, priv); priv->gpiod_rdy = devm_gpiod_get_optional(&pdev->dev, "rdy", GPIOD_IN); if (IS_ERR(priv->gpiod_rdy)) { err = PTR_ERR(priv->gpiod_rdy); dev_warn(&pdev->dev, "RDY GPIO request failed (%d)\n", err); - goto err_unmap; + return err; } this->ecc.mode = NAND_ECC_SOFT; @@ -238,42 +256,42 @@ static int ams_delta_init(struct platform_device *pdev) if (IS_ERR(priv->gpiod_nwp)) { err = PTR_ERR(priv->gpiod_nwp); dev_err(&pdev->dev, "NWP GPIO request failed (%d)\n", err); - goto err_unmap; + return err; } priv->gpiod_nce = devm_gpiod_get(&pdev->dev, "nce", GPIOD_OUT_HIGH); if (IS_ERR(priv->gpiod_nce)) { err = PTR_ERR(priv->gpiod_nce); dev_err(&pdev->dev, "NCE GPIO request failed (%d)\n", err); - goto err_unmap; + return err; } priv->gpiod_nre = devm_gpiod_get(&pdev->dev, "nre", GPIOD_OUT_HIGH); if (IS_ERR(priv->gpiod_nre)) { err = PTR_ERR(priv->gpiod_nre); dev_err(&pdev->dev, "NRE GPIO request failed (%d)\n", err); - goto err_unmap; + return err; } priv->gpiod_nwe = devm_gpiod_get(&pdev->dev, "nwe", GPIOD_OUT_HIGH); if (IS_ERR(priv->gpiod_nwe)) { err = PTR_ERR(priv->gpiod_nwe); dev_err(&pdev->dev, "NWE GPIO request failed (%d)\n", err); - goto err_unmap; + return err; } priv->gpiod_ale = devm_gpiod_get(&pdev->dev, "ale", GPIOD_OUT_LOW); if (IS_ERR(priv->gpiod_ale)) { err = PTR_ERR(priv->gpiod_ale); dev_err(&pdev->dev, "ALE GPIO request failed (%d)\n", err); - goto err_unmap; + return err; } priv->gpiod_cle = devm_gpiod_get(&pdev->dev, "cle", GPIOD_OUT_LOW); if (IS_ERR(priv->gpiod_cle)) { err = PTR_ERR(priv->gpiod_cle); dev_err(&pdev->dev, "CLE GPIO request failed (%d)\n", err); - goto err_unmap; + return err; } /* Request array of data pins, initialize them as input */ @@ -281,8 +299,9 @@ static int ams_delta_init(struct platform_device *pdev) if (IS_ERR(data_gpiods)) { err = PTR_ERR(data_gpiods); dev_err(&pdev->dev, "data GPIO request failed: %d\n", err); - goto err_unmap; + return err; } + priv->data_gpiods = data_gpiods; priv->data_in = true; /* Initialize the NAND controller object embedded in ams_delta_nand. */ @@ -293,7 +312,7 @@ static int ams_delta_init(struct platform_device *pdev) /* Scan to find existence of the device */ err = nand_scan(this, 1); if (err) - goto err_unmap; + return err; /* Register the partitions */ err = mtd_device_register(mtd, partition_info, @@ -306,9 +325,6 @@ static int ams_delta_init(struct platform_device *pdev) err_nand_cleanup: nand_cleanup(this); -err_unmap: - iounmap(io_base); - return err; } @@ -319,13 +335,10 @@ static int ams_delta_cleanup(struct platform_device *pdev) { struct ams_delta_nand *priv = platform_get_drvdata(pdev); struct mtd_info *mtd = nand_to_mtd(&priv->nand_chip); - void __iomem *io_base = priv->io_base; - /* Release resources, unregister device */ + /* Unregister device */ nand_release(mtd_to_nand(mtd)); - iounmap(io_base); - return 0; } From 48fa2f58a5d6449dc0231a994ff4f62eed86380b Mon Sep 17 00:00:00 2001 From: Janusz Krzysztofik Date: Wed, 21 Nov 2018 12:08:06 +0100 Subject: [PATCH 337/356] ARM: OMAP1: ams-delta: Drop obsolete NAND resources Amstrad Delta NAND driver now uses GPIO API for data I/O so there is no need to assign memory I/O resource to the device any longer. Drop it. Signed-off-by: Janusz Krzysztofik Acked-by: Tony Lindgren Signed-off-by: Miquel Raynal --- arch/arm/mach-omap1/board-ams-delta.c | 11 ----------- 1 file changed, 11 deletions(-) diff --git a/arch/arm/mach-omap1/board-ams-delta.c b/arch/arm/mach-omap1/board-ams-delta.c index 30c0d18f372e..d594f60c3224 100644 --- a/arch/arm/mach-omap1/board-ams-delta.c +++ b/arch/arm/mach-omap1/board-ams-delta.c @@ -296,20 +296,9 @@ struct modem_private_data { static struct modem_private_data modem_priv; -static struct resource ams_delta_nand_resources[] = { - [0] = { - .start = OMAP1_MPUIO_BASE, - .end = OMAP1_MPUIO_BASE + - OMAP_MPUIO_IO_CNTL + sizeof(u32) - 1, - .flags = IORESOURCE_MEM, - }, -}; - static struct platform_device ams_delta_nand_device = { .name = "ams-delta-nand", .id = -1, - .num_resources = ARRAY_SIZE(ams_delta_nand_resources), - .resource = ams_delta_nand_resources, }; #define OMAP_GPIO_LABEL "gpio-0-15" From 1b489effdb6dc16f63f254ee4c0d579929089e1d Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 22 Nov 2018 16:58:59 +0100 Subject: [PATCH 338/356] mtd: rawnand: marvell: fix spelling mistake in kernel doc Correct the spelling mistake 'Regiters' -> 'Registers'. Fixes: 961ba15c48dd ("mtd: rawnand: marvell: Fix clock resource by adding a register clock") Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon --- drivers/mtd/nand/raw/marvell_nand.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c index b7b4d9b14da1..e6c3739cea73 100644 --- a/drivers/mtd/nand/raw/marvell_nand.c +++ b/drivers/mtd/nand/raw/marvell_nand.c @@ -378,7 +378,7 @@ struct marvell_nfc_caps { * @dev: Parent device (used to print error messages) * @regs: NAND controller registers * @core_clk: Core clock - * @reg_clk: Regiters clock + * @reg_clk: Registers clock * @complete: Completion object to wait for NAND controller events * @assigned_cs: Bitmask describing already assigned CS lines * @chips: List containing all the NAND chips attached to From a2a05c2f530c663f6f23cee1e57dc6d45a11a9e9 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 28 Nov 2018 14:27:36 +0900 Subject: [PATCH 339/356] mtd: rawnand: denali: remove ->dev_ready() hook The Denali NAND IP has no way to read out the current signal level of the R/B# pin. Instead, denali_dev_ready() checks if the R/B# transition has already happened. (The INTR__INT_ACT interrupt is asserted at the rising edge of the R/B# pin.) It is not a correct way to implement the ->dev_ready() hook. In fact, it has a drawback; in the nand_scan_ident phase, the chip detection iterates over maxchips until it fails to find a homogeneous chip. For the last loop, nand_reset() fails if no chip is there. If ->dev_ready hook exists, nand_command(_lp) calls nand_wait_ready() after NAND_CMD_RESET. However, we know denali_dev_ready() never returns 1 unless there exists a chip that toggles R/B# in that chip select. Then, nand_wait_ready() just ends up with wasting 400 msec, in the end, shows the "timeout while waiting for chip to become ready" warning. Let's remove the mis-implemented dev_ready hook, and fallback to sending the NAND_CMD_STATUS and nand_wait_status_ready(), which bails out more quickly. Signed-off-by: Masahiro Yamada Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/denali.c | 23 +---------------------- 1 file changed, 1 insertion(+), 22 deletions(-) diff --git a/drivers/mtd/nand/raw/denali.c b/drivers/mtd/nand/raw/denali.c index bad3b8ad5e0a..3f8ee9245adb 100644 --- a/drivers/mtd/nand/raw/denali.c +++ b/drivers/mtd/nand/raw/denali.c @@ -204,18 +204,6 @@ static uint32_t denali_wait_for_irq(struct denali_nand_info *denali, return denali->irq_status; } -static uint32_t denali_check_irq(struct denali_nand_info *denali) -{ - unsigned long flags; - uint32_t irq_status; - - spin_lock_irqsave(&denali->irq_lock, flags); - irq_status = denali->irq_status; - spin_unlock_irqrestore(&denali->irq_lock, flags); - - return irq_status; -} - static void denali_read_buf(struct nand_chip *chip, uint8_t *buf, int len) { struct mtd_info *mtd = nand_to_mtd(chip); @@ -288,8 +276,7 @@ static void denali_cmd_ctrl(struct nand_chip *chip, int dat, unsigned int ctrl) return; /* - * Some commands are followed by chip->legacy.dev_ready or - * chip->legacy.waitfunc. + * Some commands are followed by chip->legacy.waitfunc. * irq_status must be cleared here to catch the R/B# interrupt later. */ if (ctrl & NAND_CTRL_CHANGE) @@ -298,13 +285,6 @@ static void denali_cmd_ctrl(struct nand_chip *chip, int dat, unsigned int ctrl) denali->host_write(denali, DENALI_BANK(denali) | type, dat); } -static int denali_dev_ready(struct nand_chip *chip) -{ - struct denali_nand_info *denali = mtd_to_denali(nand_to_mtd(chip)); - - return !!(denali_check_irq(denali) & INTR__INT_ACT); -} - static int denali_check_erased_page(struct mtd_info *mtd, struct nand_chip *chip, uint8_t *buf, unsigned long uncor_ecc_flags, @@ -1360,7 +1340,6 @@ int denali_init(struct denali_nand_info *denali) chip->legacy.read_byte = denali_read_byte; chip->legacy.write_byte = denali_write_byte; chip->legacy.cmd_ctrl = denali_cmd_ctrl; - chip->legacy.dev_ready = denali_dev_ready; chip->legacy.waitfunc = denali_waitfunc; if (features & FEATURES__INDEX_ADDR) { From 5fb3dc114706b557c3f6c385640f8fc1a03c2889 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 28 Nov 2018 14:27:37 +0900 Subject: [PATCH 340/356] mtd: rawnand: denali: remove denali_reset_banks() In nand_scan_ident(), the controller driver resets every NAND chip. This is done by sending NAND_CMD_RESET. The Denali IP provides another way to do the equivalent thing; if a bit is set in the DEVICE_RESET register, the controller sends the RESET command to the corresponding device. denali_reset_banks() uses it to reset all devices beforehand. This redundant reset sequence was needed to know the actual number of chips before calling nand_scan_ident(); if DEVICE_RESET fails, there is no chip in that chip select. Then, denali_reset_banks() sets denali->max_banks to the number of detected chips. As commit f486287d2372 ("mtd: nand: denali: fix bank reset function to detect the number of chips") explained, nand_scan_ident() issued Set Features (0xEF) command to all CS lines, some of which may not be connected with a chip. Then, the driver would wait for R/B# response, which never happens. This problem was solved by commit 107b7d6a7ad4 ("mtd: rawnand: avoid setting again the timings to mode 0 after a reset"). In the current code, nand_setup_data_interface() is called from nand_scan_tail(), which is invoked after the chip detection. Now, we can really remove the redundant denali_nand_banks() by simply passing the maximum number of chip selects supported by this IP (typically 4 or 8) to nand_scan(). Let's leave all the chip detection process to nand_scan_ident(). Signed-off-by: Masahiro Yamada Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/denali.c | 29 ----------------------------- 1 file changed, 29 deletions(-) diff --git a/drivers/mtd/nand/raw/denali.c b/drivers/mtd/nand/raw/denali.c index 3f8ee9245adb..e1c3099d705a 100644 --- a/drivers/mtd/nand/raw/denali.c +++ b/drivers/mtd/nand/raw/denali.c @@ -1045,29 +1045,6 @@ static int denali_setup_data_interface(struct nand_chip *chip, int chipnr, return 0; } -static void denali_reset_banks(struct denali_nand_info *denali) -{ - u32 irq_status; - int i; - - for (i = 0; i < denali->max_banks; i++) { - denali->active_bank = i; - - denali_reset_irq(denali); - - iowrite32(DEVICE_RESET__BANK(i), - denali->reg + DEVICE_RESET); - - irq_status = denali_wait_for_irq(denali, - INTR__RST_COMP | INTR__INT_ACT | INTR__TIME_OUT); - if (!(irq_status & INTR__INT_ACT)) - break; - } - - dev_dbg(denali->dev, "%d chips connected\n", i); - denali->max_banks = i; -} - static void denali_hw_init(struct denali_nand_info *denali) { /* @@ -1322,12 +1299,6 @@ int denali_init(struct denali_nand_info *denali) } denali_enable_irq(denali); - denali_reset_banks(denali); - if (!denali->max_banks) { - /* Error out earlier if no chip is found for some reasons. */ - ret = -ENODEV; - goto disable_irq; - } denali->active_bank = DENALI_INVALID_BANK; From bfc535f44089d6574ee4fba1c7683980020c24fb Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 20 Nov 2018 10:02:30 +0100 Subject: [PATCH 341/356] mtd: rawnand: fsmc: Stop passing mtd_info objects to internal functions Mimic what has been done in the core and stop passing mtd_info objects to internal functions. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/fsmc_nand.c | 51 ++++++++++++++------------------ 1 file changed, 23 insertions(+), 28 deletions(-) diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c index 61927c4c2650..54c854451493 100644 --- a/drivers/mtd/nand/raw/fsmc_nand.c +++ b/drivers/mtd/nand/raw/fsmc_nand.c @@ -248,9 +248,9 @@ static const struct mtd_ooblayout_ops fsmc_ecc4_ooblayout_ops = { .free = fsmc_ecc4_ooblayout_free, }; -static inline struct fsmc_nand_data *mtd_to_fsmc(struct mtd_info *mtd) +static inline struct fsmc_nand_data *nand_to_fsmc(struct nand_chip *chip) { - return container_of(mtd_to_nand(mtd), struct fsmc_nand_data, nand); + return container_of(chip, struct fsmc_nand_data, nand); } /* @@ -369,7 +369,7 @@ static int fsmc_setup_data_interface(struct nand_chip *nand, int csline, */ static void fsmc_enable_hwecc(struct nand_chip *chip, int mode) { - struct fsmc_nand_data *host = mtd_to_fsmc(nand_to_mtd(chip)); + struct fsmc_nand_data *host = nand_to_fsmc(chip); writel_relaxed(readl(host->regs_va + FSMC_PC) & ~FSMC_ECCPLEN_256, host->regs_va + FSMC_PC); @@ -387,7 +387,7 @@ static void fsmc_enable_hwecc(struct nand_chip *chip, int mode) static int fsmc_read_hwecc_ecc4(struct nand_chip *chip, const uint8_t *data, uint8_t *ecc) { - struct fsmc_nand_data *host = mtd_to_fsmc(nand_to_mtd(chip)); + struct fsmc_nand_data *host = nand_to_fsmc(chip); uint32_t ecc_tmp; unsigned long deadline = jiffies + FSMC_BUSY_WAIT_TIMEOUT; @@ -435,7 +435,7 @@ static int fsmc_read_hwecc_ecc4(struct nand_chip *chip, const uint8_t *data, static int fsmc_read_hwecc_ecc1(struct nand_chip *chip, const uint8_t *data, uint8_t *ecc) { - struct fsmc_nand_data *host = mtd_to_fsmc(nand_to_mtd(chip)); + struct fsmc_nand_data *host = nand_to_fsmc(chip); uint32_t ecc_tmp; ecc_tmp = readl_relaxed(host->regs_va + ECC1); @@ -537,13 +537,13 @@ unmap_dma: /* * fsmc_write_buf - write buffer to chip - * @mtd: MTD device structure + * @host: FSMC NAND controller * @buf: data buffer * @len: number of bytes to write */ -static void fsmc_write_buf(struct mtd_info *mtd, const uint8_t *buf, int len) +static void fsmc_write_buf(struct fsmc_nand_data *host, const uint8_t *buf, + int len) { - struct fsmc_nand_data *host = mtd_to_fsmc(mtd); int i; if (IS_ALIGNED((uintptr_t)buf, sizeof(uint32_t)) && @@ -560,13 +560,12 @@ static void fsmc_write_buf(struct mtd_info *mtd, const uint8_t *buf, int len) /* * fsmc_read_buf - read chip data into buffer - * @mtd: MTD device structure + * @host: FSMC NAND controller * @buf: buffer to store date * @len: number of bytes to read */ -static void fsmc_read_buf(struct mtd_info *mtd, uint8_t *buf, int len) +static void fsmc_read_buf(struct fsmc_nand_data *host, uint8_t *buf, int len) { - struct fsmc_nand_data *host = mtd_to_fsmc(mtd); int i; if (IS_ALIGNED((uintptr_t)buf, sizeof(uint32_t)) && @@ -583,28 +582,25 @@ static void fsmc_read_buf(struct mtd_info *mtd, uint8_t *buf, int len) /* * fsmc_read_buf_dma - read chip data into buffer - * @mtd: MTD device structure + * @host: FSMC NAND controller * @buf: buffer to store date * @len: number of bytes to read */ -static void fsmc_read_buf_dma(struct mtd_info *mtd, uint8_t *buf, int len) +static void fsmc_read_buf_dma(struct fsmc_nand_data *host, uint8_t *buf, + int len) { - struct fsmc_nand_data *host = mtd_to_fsmc(mtd); - dma_xfer(host, buf, len, DMA_FROM_DEVICE); } /* * fsmc_write_buf_dma - write buffer to chip - * @mtd: MTD device structure + * @host: FSMC NAND controller * @buf: data buffer * @len: number of bytes to write */ -static void fsmc_write_buf_dma(struct mtd_info *mtd, const uint8_t *buf, - int len) +static void fsmc_write_buf_dma(struct fsmc_nand_data *host, const uint8_t *buf, + int len) { - struct fsmc_nand_data *host = mtd_to_fsmc(mtd); - dma_xfer(host, (void *)buf, len, DMA_TO_DEVICE); } @@ -634,8 +630,7 @@ static void fsmc_ce_ctrl(struct fsmc_nand_data *host, bool assert) static int fsmc_exec_op(struct nand_chip *chip, const struct nand_operation *op, bool check_only) { - struct mtd_info *mtd = nand_to_mtd(chip); - struct fsmc_nand_data *host = mtd_to_fsmc(mtd); + struct fsmc_nand_data *host = nand_to_fsmc(chip); const struct nand_op_instr *instr = NULL; int ret = 0; unsigned int op_id; @@ -671,10 +666,10 @@ static int fsmc_exec_op(struct nand_chip *chip, const struct nand_operation *op, ", force 8-bit" : ""); if (host->mode == USE_DMA_ACCESS) - fsmc_read_buf_dma(mtd, instr->ctx.data.buf.in, + fsmc_read_buf_dma(host, instr->ctx.data.buf.in, instr->ctx.data.len); else - fsmc_read_buf(mtd, instr->ctx.data.buf.in, + fsmc_read_buf(host, instr->ctx.data.buf.in, instr->ctx.data.len); break; @@ -684,10 +679,10 @@ static int fsmc_exec_op(struct nand_chip *chip, const struct nand_operation *op, ", force 8-bit" : ""); if (host->mode == USE_DMA_ACCESS) - fsmc_write_buf_dma(mtd, instr->ctx.data.buf.out, + fsmc_write_buf_dma(host, instr->ctx.data.buf.out, instr->ctx.data.len); else - fsmc_write_buf(mtd, instr->ctx.data.buf.out, + fsmc_write_buf(host, instr->ctx.data.buf.out, instr->ctx.data.len); break; @@ -796,7 +791,7 @@ static int fsmc_read_page_hwecc(struct nand_chip *chip, uint8_t *buf, static int fsmc_bch8_correct_data(struct nand_chip *chip, uint8_t *dat, uint8_t *read_ecc, uint8_t *calc_ecc) { - struct fsmc_nand_data *host = mtd_to_fsmc(nand_to_mtd(chip)); + struct fsmc_nand_data *host = nand_to_fsmc(chip); uint32_t err_idx[8]; uint32_t num_err, i; uint32_t ecc1, ecc2, ecc3, ecc4; @@ -923,7 +918,7 @@ static int fsmc_nand_probe_config_dt(struct platform_device *pdev, static int fsmc_nand_attach_chip(struct nand_chip *nand) { struct mtd_info *mtd = nand_to_mtd(nand); - struct fsmc_nand_data *host = mtd_to_fsmc(mtd); + struct fsmc_nand_data *host = nand_to_fsmc(nand); if (AMBA_REV_BITS(host->pid) >= 8) { switch (mtd->oobsize) { From 5b47f407810369e21f2c3123c13e29ff8609a7e4 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 20 Nov 2018 10:02:31 +0100 Subject: [PATCH 342/356] mtd: rawnand: fsmc: Fix the fsmc_nand_data kernel-doc The kernel-doc describing struct fsmc_nand_data is not in sync with the struct itself. Add missing entries and drop invalid ones. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/fsmc_nand.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c index 54c854451493..01044b858a93 100644 --- a/drivers/mtd/nand/raw/fsmc_nand.c +++ b/drivers/mtd/nand/raw/fsmc_nand.c @@ -123,18 +123,19 @@ enum access_mode { * struct fsmc_nand_data - structure for FSMC NAND device state * * @pid: Part ID on the AMBA PrimeCell format - * @mtd: MTD info for a NAND flash. * @nand: Chip related info for a NAND flash. - * @partitions: Partition info for a NAND Flash. - * @nr_partitions: Total number of partition of a NAND flash. * * @bank: Bank number for probed device. + * @dev: Parent device + * @mode: Access mode * @clk: Clock structure for FSMC. * * @read_dma_chan: DMA channel for read access * @write_dma_chan: DMA channel for write access to NAND * @dma_access_complete: Completion structure * + * @dev_timings: NAND timings + * * @data_pa: NAND Physical port for Data. * @data_va: NAND port for Data. * @cmd_va: NAND port for Command. From 1e809f7ef4d2402e31e4bc2f76753b9d3b1e0b6c Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 20 Nov 2018 10:02:32 +0100 Subject: [PATCH 343/356] mtd: rawnand: fsmc: Make conversion from chip to fsmc consistent nand_to_fsmc() is used almost everywhere except in fsmc_setup_data_interface() where nand_get_controller_data() is used instead. Make that consistent and drop the nand_set_controller_data() call in the probe path. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/fsmc_nand.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c index 01044b858a93..23d00a2c926f 100644 --- a/drivers/mtd/nand/raw/fsmc_nand.c +++ b/drivers/mtd/nand/raw/fsmc_nand.c @@ -344,7 +344,7 @@ static int fsmc_calc_timings(struct fsmc_nand_data *host, static int fsmc_setup_data_interface(struct nand_chip *nand, int csline, const struct nand_data_interface *conf) { - struct fsmc_nand_data *host = nand_get_controller_data(nand); + struct fsmc_nand_data *host = nand_to_fsmc(nand); struct fsmc_nand_timings tims; const struct nand_sdr_timings *sdrt; int ret; @@ -1076,7 +1076,6 @@ static int __init fsmc_nand_probe(struct platform_device *pdev) /* Link all private pointers */ mtd = nand_to_mtd(&host->nand); - nand_set_controller_data(nand, host); nand_set_flash_node(nand, pdev->dev.of_node); mtd->dev.parent = &pdev->dev; From ad71148c1804c334544068514bc318bfd3490334 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 20 Nov 2018 10:02:33 +0100 Subject: [PATCH 344/356] mtd: rawnand: fsmc: Stop using the dummy controller obj The dummy controller is kept around to support old drivers. Let's patch this one and declare our own nand_controller instance. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/fsmc_nand.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c index 23d00a2c926f..db5174c336d4 100644 --- a/drivers/mtd/nand/raw/fsmc_nand.c +++ b/drivers/mtd/nand/raw/fsmc_nand.c @@ -122,6 +122,7 @@ enum access_mode { /** * struct fsmc_nand_data - structure for FSMC NAND device state * + * @base: Inherit from the nand_controller struct * @pid: Part ID on the AMBA PrimeCell format * @nand: Chip related info for a NAND flash. * @@ -143,6 +144,7 @@ enum access_mode { * @regs_va: Registers base address for a given bank. */ struct fsmc_nand_data { + struct nand_controller base; u32 pid; struct nand_chip nand; @@ -1117,10 +1119,13 @@ static int __init fsmc_nand_probe(struct platform_device *pdev) nand->ecc.strength = 8; } + nand_controller_init(&host->base); + host->base.ops = &fsmc_nand_controller_ops; + nand->controller = &host->base; + /* * Scan to find existence of the device */ - nand->dummy_controller.ops = &fsmc_nand_controller_ops; ret = nand_scan(nand, 1); if (ret) goto release_dma_write_chan; From bb6963449f3d43e1162359895005ada3db02c9de Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 20 Nov 2018 10:02:34 +0100 Subject: [PATCH 345/356] mtd: rawnand: fsmc: Add an SPDX tag to replace the license text Add an SPDX GPL-2.0 tag and update MODULE_LICENSE() to match the license text. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/fsmc_nand.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c index db5174c336d4..3a4b80a121ad 100644 --- a/drivers/mtd/nand/raw/fsmc_nand.c +++ b/drivers/mtd/nand/raw/fsmc_nand.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * ST Microelectronics * Flexible Static Memory Controller (FSMC) @@ -10,10 +11,6 @@ * Based on drivers/mtd/nand/nomadik_nand.c (removed in v3.8) * Copyright © 2007 STMicroelectronics Pvt. Ltd. * Copyright © 2009 Alessandro Rubini - * - * This file is licensed under the terms of the GNU General Public - * License version 2. This program is licensed "as is" without any - * warranty of any kind, whether express or implied. */ #include @@ -1215,6 +1212,6 @@ static struct platform_driver fsmc_nand_driver = { module_platform_driver_probe(fsmc_nand_driver, fsmc_nand_probe); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Vipin Kumar , Ashish Priyadarshi"); MODULE_DESCRIPTION("NAND driver for SPEAr Platforms"); From fc43f45ed563f517e9bd1ddc9d0a2fecf3cd2808 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 20 Nov 2018 10:02:35 +0100 Subject: [PATCH 346/356] mtd: rawnand: fsmc: Fix all coding style issues reported by checkpatch checkpatch reports a bunch of coding style issues. Let's fix them all in one step. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/fsmc_nand.c | 199 +++++++++++++++---------------- 1 file changed, 99 insertions(+), 100 deletions(-) diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c index 3a4b80a121ad..325b4414dccc 100644 --- a/drivers/mtd/nand/raw/fsmc_nand.c +++ b/drivers/mtd/nand/raw/fsmc_nand.c @@ -38,15 +38,14 @@ /* fsmc controller registers for NOR flash */ #define CTRL 0x0 /* ctrl register definitions */ - #define BANK_ENABLE (1 << 0) - #define MUXED (1 << 1) + #define BANK_ENABLE BIT(0) + #define MUXED BIT(1) #define NOR_DEV (2 << 2) - #define WIDTH_8 (0 << 4) - #define WIDTH_16 (1 << 4) - #define RSTPWRDWN (1 << 6) - #define WPROT (1 << 7) - #define WRT_ENABLE (1 << 12) - #define WAIT_ENB (1 << 13) + #define WIDTH_16 BIT(4) + #define RSTPWRDWN BIT(6) + #define WPROT BIT(7) + #define WRT_ENABLE BIT(12) + #define WAIT_ENB BIT(13) #define CTRL_TIM 0x4 /* ctrl_tim register definitions */ @@ -54,43 +53,35 @@ #define FSMC_NOR_BANK_SZ 0x8 #define FSMC_NOR_REG_SIZE 0x40 -#define FSMC_NOR_REG(base, bank, reg) (base + \ - FSMC_NOR_BANK_SZ * (bank) + \ - reg) +#define FSMC_NOR_REG(base, bank, reg) ((base) + \ + (FSMC_NOR_BANK_SZ * (bank)) + \ + (reg)) /* fsmc controller registers for NAND flash */ #define FSMC_PC 0x00 /* pc register definitions */ - #define FSMC_RESET (1 << 0) - #define FSMC_WAITON (1 << 1) - #define FSMC_ENABLE (1 << 2) - #define FSMC_DEVTYPE_NAND (1 << 3) - #define FSMC_DEVWID_8 (0 << 4) - #define FSMC_DEVWID_16 (1 << 4) - #define FSMC_ECCEN (1 << 6) - #define FSMC_ECCPLEN_512 (0 << 7) - #define FSMC_ECCPLEN_256 (1 << 7) - #define FSMC_TCLR_1 (1) + #define FSMC_RESET BIT(0) + #define FSMC_WAITON BIT(1) + #define FSMC_ENABLE BIT(2) + #define FSMC_DEVTYPE_NAND BIT(3) + #define FSMC_DEVWID_16 BIT(4) + #define FSMC_ECCEN BIT(6) + #define FSMC_ECCPLEN_256 BIT(7) #define FSMC_TCLR_SHIFT (9) #define FSMC_TCLR_MASK (0xF) - #define FSMC_TAR_1 (1) #define FSMC_TAR_SHIFT (13) #define FSMC_TAR_MASK (0xF) #define STS 0x04 /* sts register definitions */ - #define FSMC_CODE_RDY (1 << 15) + #define FSMC_CODE_RDY BIT(15) #define COMM 0x08 /* comm register definitions */ - #define FSMC_TSET_0 0 #define FSMC_TSET_SHIFT 0 #define FSMC_TSET_MASK 0xFF - #define FSMC_TWAIT_6 6 #define FSMC_TWAIT_SHIFT 8 #define FSMC_TWAIT_MASK 0xFF - #define FSMC_THOLD_4 4 #define FSMC_THOLD_SHIFT 16 #define FSMC_THOLD_MASK 0xFF - #define FSMC_THIZ_1 1 #define FSMC_THIZ_SHIFT 24 #define FSMC_THIZ_MASK 0xFF #define ATTRIB 0x0C @@ -103,12 +94,12 @@ #define FSMC_BUSY_WAIT_TIMEOUT (1 * HZ) struct fsmc_nand_timings { - uint8_t tclr; - uint8_t tar; - uint8_t thiz; - uint8_t thold; - uint8_t twait; - uint8_t tset; + u8 tclr; + u8 tar; + u8 thiz; + u8 thold; + u8 twait; + u8 tset; }; enum access_mode { @@ -262,8 +253,8 @@ static inline struct fsmc_nand_data *nand_to_fsmc(struct nand_chip *chip) static void fsmc_nand_setup(struct fsmc_nand_data *host, struct fsmc_nand_timings *tims) { - uint32_t value = FSMC_DEVTYPE_NAND | FSMC_ENABLE | FSMC_WAITON; - uint32_t tclr, tar, thiz, thold, twait, tset; + u32 value = FSMC_DEVTYPE_NAND | FSMC_ENABLE | FSMC_WAITON; + u32 tclr, tar, thiz, thold, twait, tset; tclr = (tims->tclr & FSMC_TCLR_MASK) << FSMC_TCLR_SHIFT; tar = (tims->tar & FSMC_TAR_MASK) << FSMC_TAR_SHIFT; @@ -273,13 +264,9 @@ static void fsmc_nand_setup(struct fsmc_nand_data *host, tset = (tims->tset & FSMC_TSET_MASK) << FSMC_TSET_SHIFT; if (host->nand.options & NAND_BUSWIDTH_16) - writel_relaxed(value | FSMC_DEVWID_16, - host->regs_va + FSMC_PC); - else - writel_relaxed(value | FSMC_DEVWID_8, host->regs_va + FSMC_PC); + value |= FSMC_DEVWID_16; - writel_relaxed(readl(host->regs_va + FSMC_PC) | tclr | tar, - host->regs_va + FSMC_PC); + writel_relaxed(value | tclr | tar, host->regs_va + FSMC_PC); writel_relaxed(thiz | thold | twait | tset, host->regs_va + COMM); writel_relaxed(thiz | thold | twait | tset, host->regs_va + ATTRIB); } @@ -290,7 +277,7 @@ static int fsmc_calc_timings(struct fsmc_nand_data *host, { unsigned long hclk = clk_get_rate(host->clk); unsigned long hclkn = NSEC_PER_SEC / hclk; - uint32_t thiz, thold, twait, tset; + u32 thiz, thold, twait, tset; if (sdrt->tRC_min < 30000) return -EOPNOTSUPP; @@ -384,18 +371,18 @@ static void fsmc_enable_hwecc(struct nand_chip *chip, int mode) * FSMC. ECC is 13 bytes for 512 bytes of data (supports error correction up to * max of 8-bits) */ -static int fsmc_read_hwecc_ecc4(struct nand_chip *chip, const uint8_t *data, - uint8_t *ecc) +static int fsmc_read_hwecc_ecc4(struct nand_chip *chip, const u8 *data, + u8 *ecc) { struct fsmc_nand_data *host = nand_to_fsmc(chip); - uint32_t ecc_tmp; + u32 ecc_tmp; unsigned long deadline = jiffies + FSMC_BUSY_WAIT_TIMEOUT; do { if (readl_relaxed(host->regs_va + STS) & FSMC_CODE_RDY) break; - else - cond_resched(); + + cond_resched(); } while (!time_after_eq(jiffies, deadline)); if (time_after_eq(jiffies, deadline)) { @@ -404,25 +391,25 @@ static int fsmc_read_hwecc_ecc4(struct nand_chip *chip, const uint8_t *data, } ecc_tmp = readl_relaxed(host->regs_va + ECC1); - ecc[0] = (uint8_t) (ecc_tmp >> 0); - ecc[1] = (uint8_t) (ecc_tmp >> 8); - ecc[2] = (uint8_t) (ecc_tmp >> 16); - ecc[3] = (uint8_t) (ecc_tmp >> 24); + ecc[0] = ecc_tmp; + ecc[1] = ecc_tmp >> 8; + ecc[2] = ecc_tmp >> 16; + ecc[3] = ecc_tmp >> 24; ecc_tmp = readl_relaxed(host->regs_va + ECC2); - ecc[4] = (uint8_t) (ecc_tmp >> 0); - ecc[5] = (uint8_t) (ecc_tmp >> 8); - ecc[6] = (uint8_t) (ecc_tmp >> 16); - ecc[7] = (uint8_t) (ecc_tmp >> 24); + ecc[4] = ecc_tmp; + ecc[5] = ecc_tmp >> 8; + ecc[6] = ecc_tmp >> 16; + ecc[7] = ecc_tmp >> 24; ecc_tmp = readl_relaxed(host->regs_va + ECC3); - ecc[8] = (uint8_t) (ecc_tmp >> 0); - ecc[9] = (uint8_t) (ecc_tmp >> 8); - ecc[10] = (uint8_t) (ecc_tmp >> 16); - ecc[11] = (uint8_t) (ecc_tmp >> 24); + ecc[8] = ecc_tmp; + ecc[9] = ecc_tmp >> 8; + ecc[10] = ecc_tmp >> 16; + ecc[11] = ecc_tmp >> 24; ecc_tmp = readl_relaxed(host->regs_va + STS); - ecc[12] = (uint8_t) (ecc_tmp >> 16); + ecc[12] = ecc_tmp >> 16; return 0; } @@ -432,22 +419,22 @@ static int fsmc_read_hwecc_ecc4(struct nand_chip *chip, const uint8_t *data, * FSMC. ECC is 3 bytes for 512 bytes of data (supports error correction up to * max of 1-bit) */ -static int fsmc_read_hwecc_ecc1(struct nand_chip *chip, const uint8_t *data, - uint8_t *ecc) +static int fsmc_read_hwecc_ecc1(struct nand_chip *chip, const u8 *data, + u8 *ecc) { struct fsmc_nand_data *host = nand_to_fsmc(chip); - uint32_t ecc_tmp; + u32 ecc_tmp; ecc_tmp = readl_relaxed(host->regs_va + ECC1); - ecc[0] = (uint8_t) (ecc_tmp >> 0); - ecc[1] = (uint8_t) (ecc_tmp >> 8); - ecc[2] = (uint8_t) (ecc_tmp >> 16); + ecc[0] = ecc_tmp; + ecc[1] = ecc_tmp >> 8; + ecc[2] = ecc_tmp >> 16; return 0; } /* Count the number of 0's in buff upto a max of max_bits */ -static int count_written_bits(uint8_t *buff, int size, int max_bits) +static int count_written_bits(u8 *buff, int size, int max_bits) { int k, written_bits = 0; @@ -468,7 +455,7 @@ static void dma_complete(void *param) } static int dma_xfer(struct fsmc_nand_data *host, void *buffer, int len, - enum dma_data_direction direction) + enum dma_data_direction direction) { struct dma_chan *chan; struct dma_device *dma_dev; @@ -519,7 +506,7 @@ static int dma_xfer(struct fsmc_nand_data *host, void *buffer, int len, time_left = wait_for_completion_timeout(&host->dma_access_complete, - msecs_to_jiffies(3000)); + msecs_to_jiffies(3000)); if (time_left == 0) { dmaengine_terminate_all(chan); dev_err(host->dev, "wait_for_completion_timeout\n"); @@ -541,14 +528,15 @@ unmap_dma: * @buf: data buffer * @len: number of bytes to write */ -static void fsmc_write_buf(struct fsmc_nand_data *host, const uint8_t *buf, +static void fsmc_write_buf(struct fsmc_nand_data *host, const u8 *buf, int len) { int i; - if (IS_ALIGNED((uintptr_t)buf, sizeof(uint32_t)) && - IS_ALIGNED(len, sizeof(uint32_t))) { - uint32_t *p = (uint32_t *)buf; + if (IS_ALIGNED((uintptr_t)buf, sizeof(u32)) && + IS_ALIGNED(len, sizeof(u32))) { + u32 *p = (u32 *)buf; + len = len >> 2; for (i = 0; i < len; i++) writel_relaxed(p[i], host->data_va); @@ -564,13 +552,14 @@ static void fsmc_write_buf(struct fsmc_nand_data *host, const uint8_t *buf, * @buf: buffer to store date * @len: number of bytes to read */ -static void fsmc_read_buf(struct fsmc_nand_data *host, uint8_t *buf, int len) +static void fsmc_read_buf(struct fsmc_nand_data *host, u8 *buf, int len) { int i; - if (IS_ALIGNED((uintptr_t)buf, sizeof(uint32_t)) && - IS_ALIGNED(len, sizeof(uint32_t))) { - uint32_t *p = (uint32_t *)buf; + if (IS_ALIGNED((uintptr_t)buf, sizeof(u32)) && + IS_ALIGNED(len, sizeof(u32))) { + u32 *p = (u32 *)buf; + len = len >> 2; for (i = 0; i < len; i++) p[i] = readl_relaxed(host->data_va); @@ -586,7 +575,7 @@ static void fsmc_read_buf(struct fsmc_nand_data *host, uint8_t *buf, int len) * @buf: buffer to store date * @len: number of bytes to read */ -static void fsmc_read_buf_dma(struct fsmc_nand_data *host, uint8_t *buf, +static void fsmc_read_buf_dma(struct fsmc_nand_data *host, u8 *buf, int len) { dma_xfer(host, buf, len, DMA_FROM_DEVICE); @@ -598,7 +587,7 @@ static void fsmc_read_buf_dma(struct fsmc_nand_data *host, uint8_t *buf, * @buf: data buffer * @len: number of bytes to write */ -static void fsmc_write_buf_dma(struct fsmc_nand_data *host, const uint8_t *buf, +static void fsmc_write_buf_dma(struct fsmc_nand_data *host, const u8 *buf, int len) { dma_xfer(host, (void *)buf, len, DMA_TO_DEVICE); @@ -679,7 +668,8 @@ static int fsmc_exec_op(struct nand_chip *chip, const struct nand_operation *op, ", force 8-bit" : ""); if (host->mode == USE_DMA_ACCESS) - fsmc_write_buf_dma(host, instr->ctx.data.buf.out, + fsmc_write_buf_dma(host, + instr->ctx.data.buf.out, instr->ctx.data.len); else fsmc_write_buf(host, instr->ctx.data.buf.out, @@ -714,24 +704,24 @@ static int fsmc_exec_op(struct nand_chip *chip, const struct nand_operation *op, * After this read, fsmc hardware generates and reports error data bits(up to a * max of 8 bits) */ -static int fsmc_read_page_hwecc(struct nand_chip *chip, uint8_t *buf, +static int fsmc_read_page_hwecc(struct nand_chip *chip, u8 *buf, int oob_required, int page) { struct mtd_info *mtd = nand_to_mtd(chip); int i, j, s, stat, eccsize = chip->ecc.size; int eccbytes = chip->ecc.bytes; int eccsteps = chip->ecc.steps; - uint8_t *p = buf; - uint8_t *ecc_calc = chip->ecc.calc_buf; - uint8_t *ecc_code = chip->ecc.code_buf; + u8 *p = buf; + u8 *ecc_calc = chip->ecc.calc_buf; + u8 *ecc_code = chip->ecc.code_buf; int off, len, ret, group = 0; /* - * ecc_oob is intentionally taken as uint16_t. In 16bit devices, we + * ecc_oob is intentionally taken as u16. In 16bit devices, we * end up reading 14 bytes (7 words) from oob. The local array is * to maintain word alignment */ - uint16_t ecc_oob[7]; - uint8_t *oob = (uint8_t *)&ecc_oob[0]; + u16 ecc_oob[7]; + u8 *oob = (u8 *)&ecc_oob[0]; unsigned int max_bitflips = 0; for (i = 0, s = 0; s < eccsteps; s++, i += eccbytes, p += eccsize) { @@ -786,15 +776,15 @@ static int fsmc_read_page_hwecc(struct nand_chip *chip, uint8_t *buf, * @calc_ecc: ecc calculated from read data * * calc_ecc is a 104 bit information containing maximum of 8 error - * offset informations of 13 bits each in 512 bytes of read data. + * offset information of 13 bits each in 512 bytes of read data. */ -static int fsmc_bch8_correct_data(struct nand_chip *chip, uint8_t *dat, - uint8_t *read_ecc, uint8_t *calc_ecc) +static int fsmc_bch8_correct_data(struct nand_chip *chip, u8 *dat, + u8 *read_ecc, u8 *calc_ecc) { struct fsmc_nand_data *host = nand_to_fsmc(chip); - uint32_t err_idx[8]; - uint32_t num_err, i; - uint32_t ecc1, ecc2, ecc3, ecc4; + u32 err_idx[8]; + u32 num_err, i; + u32 ecc1, ecc2, ecc3, ecc4; num_err = (readl_relaxed(host->regs_va + STS) >> 10) & 0xF; @@ -835,8 +825,8 @@ static int fsmc_bch8_correct_data(struct nand_chip *chip, uint8_t *dat, * |---idx[7]--|--.....-----|---idx[2]--||---idx[1]--||---idx[0]--| * * calc_ecc is a 104 bit information containing maximum of 8 error - * offset informations of 13 bits each. calc_ecc is copied into a - * uint64_t array and error offset indexes are populated in err_idx + * offset information of 13 bits each. calc_ecc is copied into a + * u64 array and error offset indexes are populated in err_idx * array */ ecc1 = readl_relaxed(host->regs_va + ECC1); @@ -895,11 +885,13 @@ static int fsmc_nand_probe_config_dt(struct platform_device *pdev, nand->options |= NAND_SKIP_BBTSCAN; host->dev_timings = devm_kzalloc(&pdev->dev, - sizeof(*host->dev_timings), GFP_KERNEL); + sizeof(*host->dev_timings), + GFP_KERNEL); if (!host->dev_timings) return -ENOMEM; + ret = of_property_read_u8_array(np, "timings", (u8 *)host->dev_timings, - sizeof(*host->dev_timings)); + sizeof(*host->dev_timings)); if (ret) host->dev_timings = NULL; @@ -1061,10 +1053,13 @@ static int __init fsmc_nand_probe(struct platform_device *pdev) * AMBA PrimeCell bus. However it is not a PrimeCell. */ for (pid = 0, i = 0; i < 4; i++) - pid |= (readl(base + resource_size(res) - 0x20 + 4 * i) & 255) << (i * 8); + pid |= (readl(base + resource_size(res) - 0x20 + 4 * i) & + 255) << (i * 8); + host->pid = pid; - dev_info(&pdev->dev, "FSMC device partno %03x, manufacturer %02x, " - "revision %02x, config %02x\n", + + dev_info(&pdev->dev, + "FSMC device partno %03x, manufacturer %02x, revision %02x, config %02x\n", AMBA_PART_BITS(pid), AMBA_MANF_BITS(pid), AMBA_REV_BITS(pid), AMBA_CONFIG_BITS(pid)); @@ -1175,19 +1170,23 @@ static int fsmc_nand_remove(struct platform_device *pdev) static int fsmc_nand_suspend(struct device *dev) { struct fsmc_nand_data *host = dev_get_drvdata(dev); + if (host) clk_disable_unprepare(host->clk); + return 0; } static int fsmc_nand_resume(struct device *dev) { struct fsmc_nand_data *host = dev_get_drvdata(dev); + if (host) { clk_prepare_enable(host->clk); if (host->dev_timings) fsmc_nand_setup(host, host->dev_timings); } + return 0; } #endif From 4440f781969dcc28d8af0e66a6d6d741845bb67b Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 20 Nov 2018 10:02:36 +0100 Subject: [PATCH 347/356] mtd: rawnand: vf610: Stop passing mtd_info to internal functions Mimic what has been done in the core and avoid passing mtd_info object internally. Signed-off-by: Boris Brezillon Reviewed-by: Stefan Agner Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/vf610_nfc.c | 48 +++++++++++++------------------- 1 file changed, 19 insertions(+), 29 deletions(-) diff --git a/drivers/mtd/nand/raw/vf610_nfc.c b/drivers/mtd/nand/raw/vf610_nfc.c index 0fa7cac4ce14..845a639b0595 100644 --- a/drivers/mtd/nand/raw/vf610_nfc.c +++ b/drivers/mtd/nand/raw/vf610_nfc.c @@ -168,11 +168,6 @@ struct vf610_nfc { u32 ecc_mode; }; -static inline struct vf610_nfc *mtd_to_nfc(struct mtd_info *mtd) -{ - return container_of(mtd_to_nand(mtd), struct vf610_nfc, chip); -} - static inline struct vf610_nfc *chip_to_nfc(struct nand_chip *chip) { return container_of(chip, struct vf610_nfc, chip); @@ -316,8 +311,7 @@ static void vf610_nfc_done(struct vf610_nfc *nfc) static irqreturn_t vf610_nfc_irq(int irq, void *data) { - struct mtd_info *mtd = data; - struct vf610_nfc *nfc = mtd_to_nfc(mtd); + struct vf610_nfc *nfc = data; vf610_nfc_clear(nfc, NFC_IRQ_STATUS, IDLE_EN_BIT); complete(&nfc->cmd_done); @@ -492,7 +486,7 @@ static const struct nand_op_parser vf610_nfc_op_parser = NAND_OP_PARSER( */ static void vf610_nfc_select_target(struct nand_chip *chip, unsigned int cs) { - struct vf610_nfc *nfc = mtd_to_nfc(nand_to_mtd(chip)); + struct vf610_nfc *nfc = chip_to_nfc(chip); u32 tmp; /* Vybrid only (MPC5125 would have full RB and four CS) */ @@ -516,10 +510,11 @@ static int vf610_nfc_exec_op(struct nand_chip *chip, check_only); } -static inline int vf610_nfc_correct_data(struct mtd_info *mtd, uint8_t *dat, +static inline int vf610_nfc_correct_data(struct nand_chip *chip, uint8_t *dat, uint8_t *oob, int page) { - struct vf610_nfc *nfc = mtd_to_nfc(mtd); + struct vf610_nfc *nfc = chip_to_nfc(chip); + struct mtd_info *mtd = nand_to_mtd(chip); u32 ecc_status_off = NFC_MAIN_AREA(0) + ECC_SRAM_ADDR + ECC_STATUS; u8 ecc_status; u8 ecc_count; @@ -559,8 +554,8 @@ static void vf610_nfc_fill_row(struct nand_chip *chip, int page, u32 *code, static int vf610_nfc_read_page(struct nand_chip *chip, uint8_t *buf, int oob_required, int page) { + struct vf610_nfc *nfc = chip_to_nfc(chip); struct mtd_info *mtd = nand_to_mtd(chip); - struct vf610_nfc *nfc = mtd_to_nfc(mtd); int trfr_sz = mtd->writesize + mtd->oobsize; u32 row = 0, cmd1 = 0, cmd2 = 0, code = 0; int stat; @@ -593,7 +588,7 @@ static int vf610_nfc_read_page(struct nand_chip *chip, uint8_t *buf, mtd->writesize, mtd->oobsize, false); - stat = vf610_nfc_correct_data(mtd, buf, chip->oob_poi, page); + stat = vf610_nfc_correct_data(chip, buf, chip->oob_poi, page); if (stat < 0) { mtd->ecc_stats.failed++; @@ -607,8 +602,8 @@ static int vf610_nfc_read_page(struct nand_chip *chip, uint8_t *buf, static int vf610_nfc_write_page(struct nand_chip *chip, const uint8_t *buf, int oob_required, int page) { + struct vf610_nfc *nfc = chip_to_nfc(chip); struct mtd_info *mtd = nand_to_mtd(chip); - struct vf610_nfc *nfc = mtd_to_nfc(mtd); int trfr_sz = mtd->writesize + mtd->oobsize; u32 row = 0, cmd1 = 0, cmd2 = 0, code = 0; u8 status; @@ -651,8 +646,7 @@ static int vf610_nfc_write_page(struct nand_chip *chip, const uint8_t *buf, static int vf610_nfc_read_page_raw(struct nand_chip *chip, u8 *buf, int oob_required, int page) { - struct mtd_info *mtd = nand_to_mtd(chip); - struct vf610_nfc *nfc = mtd_to_nfc(mtd); + struct vf610_nfc *nfc = chip_to_nfc(chip); int ret; nfc->data_access = true; @@ -665,8 +659,8 @@ static int vf610_nfc_read_page_raw(struct nand_chip *chip, u8 *buf, static int vf610_nfc_write_page_raw(struct nand_chip *chip, const u8 *buf, int oob_required, int page) { + struct vf610_nfc *nfc = chip_to_nfc(chip); struct mtd_info *mtd = nand_to_mtd(chip); - struct vf610_nfc *nfc = mtd_to_nfc(mtd); int ret; nfc->data_access = true; @@ -684,7 +678,7 @@ static int vf610_nfc_write_page_raw(struct nand_chip *chip, const u8 *buf, static int vf610_nfc_read_oob(struct nand_chip *chip, int page) { - struct vf610_nfc *nfc = mtd_to_nfc(nand_to_mtd(chip)); + struct vf610_nfc *nfc = chip_to_nfc(chip); int ret; nfc->data_access = true; @@ -697,7 +691,7 @@ static int vf610_nfc_read_oob(struct nand_chip *chip, int page) static int vf610_nfc_write_oob(struct nand_chip *chip, int page) { struct mtd_info *mtd = nand_to_mtd(chip); - struct vf610_nfc *nfc = mtd_to_nfc(mtd); + struct vf610_nfc *nfc = chip_to_nfc(chip); int ret; nfc->data_access = true; @@ -754,7 +748,7 @@ static void vf610_nfc_init_controller(struct vf610_nfc *nfc) static int vf610_nfc_attach_chip(struct nand_chip *chip) { struct mtd_info *mtd = nand_to_mtd(chip); - struct vf610_nfc *nfc = mtd_to_nfc(mtd); + struct vf610_nfc *nfc = chip_to_nfc(chip); vf610_nfc_init_controller(nfc); @@ -885,7 +879,7 @@ static int vf610_nfc_probe(struct platform_device *pdev) init_completion(&nfc->cmd_done); - err = devm_request_irq(nfc->dev, irq, vf610_nfc_irq, 0, DRV_NAME, mtd); + err = devm_request_irq(nfc->dev, irq, vf610_nfc_irq, 0, DRV_NAME, nfc); if (err) { dev_err(nfc->dev, "Error requesting IRQ!\n"); goto err_disable_clk; @@ -899,7 +893,7 @@ static int vf610_nfc_probe(struct platform_device *pdev) if (err) goto err_disable_clk; - platform_set_drvdata(pdev, mtd); + platform_set_drvdata(pdev, nfc); /* Register device in MTD */ err = mtd_device_register(mtd, NULL, 0); @@ -916,10 +910,9 @@ err_disable_clk: static int vf610_nfc_remove(struct platform_device *pdev) { - struct mtd_info *mtd = platform_get_drvdata(pdev); - struct vf610_nfc *nfc = mtd_to_nfc(mtd); + struct vf610_nfc *nfc = platform_get_drvdata(pdev); - nand_release(mtd_to_nand(mtd)); + nand_release(&nfc->chip); clk_disable_unprepare(nfc->clk); return 0; } @@ -927,8 +920,7 @@ static int vf610_nfc_remove(struct platform_device *pdev) #ifdef CONFIG_PM_SLEEP static int vf610_nfc_suspend(struct device *dev) { - struct mtd_info *mtd = dev_get_drvdata(dev); - struct vf610_nfc *nfc = mtd_to_nfc(mtd); + struct vf610_nfc *nfc = dev_get_drvdata(dev); clk_disable_unprepare(nfc->clk); return 0; @@ -936,11 +928,9 @@ static int vf610_nfc_suspend(struct device *dev) static int vf610_nfc_resume(struct device *dev) { + struct vf610_nfc *nfc = dev_get_drvdata(dev); int err; - struct mtd_info *mtd = dev_get_drvdata(dev); - struct vf610_nfc *nfc = mtd_to_nfc(mtd); - err = clk_prepare_enable(nfc->clk); if (err) return err; From da59b4538c4cddfcd77e1c3e45e087d6b757729b Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 20 Nov 2018 10:02:37 +0100 Subject: [PATCH 348/356] mtd: rawnand: vf610: Stop using the dummy controller obj The dummy controller is kept around to support old drivers. Let's patch this one and declare our own nand_controller instance. Signed-off-by: Boris Brezillon Reviewed-by: Stefan Agner Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/vf610_nfc.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/mtd/nand/raw/vf610_nfc.c b/drivers/mtd/nand/raw/vf610_nfc.c index 845a639b0595..2e8b7e9314a3 100644 --- a/drivers/mtd/nand/raw/vf610_nfc.c +++ b/drivers/mtd/nand/raw/vf610_nfc.c @@ -152,6 +152,7 @@ enum vf610_nfc_variant { }; struct vf610_nfc { + struct nand_controller base; struct nand_chip chip; struct device *dev; void __iomem *regs; @@ -887,8 +888,11 @@ static int vf610_nfc_probe(struct platform_device *pdev) vf610_nfc_preinit_controller(nfc); + nand_controller_init(&nfc->base); + nfc->base.ops = &vf610_nfc_controller_ops; + chip->controller = &nfc->base; + /* Scan the NAND chip */ - chip->dummy_controller.ops = &vf610_nfc_controller_ops; err = nand_scan(chip, 1); if (err) goto err_disable_clk; From 419e5b84a4be6c796e421b82e9673e2fa1ec1b07 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 20 Nov 2018 10:02:38 +0100 Subject: [PATCH 349/356] mtd: rawnand: vf610: Add an SPDX tag to replace the license text Replace the license text by an SPDX tag. Signed-off-by: Boris Brezillon Reviewed-by: Stefan Agner Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/vf610_nfc.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/mtd/nand/raw/vf610_nfc.c b/drivers/mtd/nand/raw/vf610_nfc.c index 2e8b7e9314a3..a662ca1970e5 100644 --- a/drivers/mtd/nand/raw/vf610_nfc.c +++ b/drivers/mtd/nand/raw/vf610_nfc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * Copyright 2009-2015 Freescale Semiconductor, Inc. and others * @@ -10,11 +11,6 @@ * * Based on original driver mpc5121_nfc.c. * - * This is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * * Limitations: * - Untested on MPC5125 and M54418. * - DMA and pipelining not used. From 7b6a9b28ecf2fd2e2f5dcdb6d4fa8044b48bdb74 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 20 Nov 2018 10:02:39 +0100 Subject: [PATCH 350/356] mtd: rawnand: Deprecate the dummy_controller field We try to force NAND controller drivers to properly separate the NAND controller object from the NAND chip one, so let's deprecate the dummy controller object embedded in nand_chip to encourage them to create their own instance. Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/cafe_nand.c | 2 +- drivers/mtd/nand/raw/davinci_nand.c | 2 +- drivers/mtd/nand/raw/denali.c | 2 +- drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c | 2 +- drivers/mtd/nand/raw/hisi504_nand.c | 2 +- drivers/mtd/nand/raw/jz4740_nand.c | 2 +- drivers/mtd/nand/raw/lpc32xx_mlc.c | 2 +- drivers/mtd/nand/raw/lpc32xx_slc.c | 2 +- drivers/mtd/nand/raw/mxc_nand.c | 2 +- drivers/mtd/nand/raw/nand_base.c | 4 ++-- drivers/mtd/nand/raw/nandsim.c | 2 +- drivers/mtd/nand/raw/sh_flctl.c | 2 +- drivers/mtd/nand/raw/sm_common.c | 2 +- include/linux/mtd/rawnand.h | 6 +++--- 14 files changed, 17 insertions(+), 17 deletions(-) diff --git a/drivers/mtd/nand/raw/cafe_nand.c b/drivers/mtd/nand/raw/cafe_nand.c index a85f5fa5c66d..b1c0cd6b49da 100644 --- a/drivers/mtd/nand/raw/cafe_nand.c +++ b/drivers/mtd/nand/raw/cafe_nand.c @@ -780,7 +780,7 @@ static int cafe_nand_probe(struct pci_dev *pdev, cafe->usedma = 0; /* Scan to find existence of the device */ - cafe->nand.dummy_controller.ops = &cafe_nand_controller_ops; + cafe->nand.legacy.dummy_controller.ops = &cafe_nand_controller_ops; err = nand_scan(&cafe->nand, 2); if (err) goto out_irq; diff --git a/drivers/mtd/nand/raw/davinci_nand.c b/drivers/mtd/nand/raw/davinci_nand.c index f430aeb917e8..27bafa5e1ca1 100644 --- a/drivers/mtd/nand/raw/davinci_nand.c +++ b/drivers/mtd/nand/raw/davinci_nand.c @@ -801,7 +801,7 @@ static int nand_davinci_probe(struct platform_device *pdev) spin_unlock_irq(&davinci_nand_lock); /* Scan to find existence of the device(s) */ - info->chip.dummy_controller.ops = &davinci_nand_controller_ops; + info->chip.legacy.dummy_controller.ops = &davinci_nand_controller_ops; ret = nand_scan(&info->chip, pdata->mask_chipsel ? 2 : 1); if (ret < 0) { dev_dbg(&pdev->dev, "no NAND chip(s) found\n"); diff --git a/drivers/mtd/nand/raw/denali.c b/drivers/mtd/nand/raw/denali.c index e1c3099d705a..eebac35304c6 100644 --- a/drivers/mtd/nand/raw/denali.c +++ b/drivers/mtd/nand/raw/denali.c @@ -1325,7 +1325,7 @@ int denali_init(struct denali_nand_info *denali) if (denali->clk_rate && denali->clk_x_rate) chip->options |= NAND_KEEP_TIMINGS; - chip->dummy_controller.ops = &denali_controller_ops; + chip->legacy.dummy_controller.ops = &denali_controller_ops; ret = nand_scan(chip, denali->max_banks); if (ret) goto disable_irq; diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c index 25f9fe79796a..ed405c9434fe 100644 --- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c +++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c @@ -1931,7 +1931,7 @@ static int gpmi_nand_init(struct gpmi_nand_data *this) if (ret) goto err_out; - chip->dummy_controller.ops = &gpmi_nand_controller_ops; + chip->legacy.dummy_controller.ops = &gpmi_nand_controller_ops; ret = nand_scan(chip, GPMI_IS_MX6(this) ? 2 : 1); if (ret) goto err_out; diff --git a/drivers/mtd/nand/raw/hisi504_nand.c b/drivers/mtd/nand/raw/hisi504_nand.c index e41c13499fd5..f3f9aa160cff 100644 --- a/drivers/mtd/nand/raw/hisi504_nand.c +++ b/drivers/mtd/nand/raw/hisi504_nand.c @@ -799,7 +799,7 @@ static int hisi_nfc_probe(struct platform_device *pdev) return ret; } - chip->dummy_controller.ops = &hisi_nfc_controller_ops; + chip->legacy.dummy_controller.ops = &hisi_nfc_controller_ops; ret = nand_scan(chip, max_chips); if (ret) return ret; diff --git a/drivers/mtd/nand/raw/jz4740_nand.c b/drivers/mtd/nand/raw/jz4740_nand.c index 0bcfdd3d66a8..f92ae5aa2a54 100644 --- a/drivers/mtd/nand/raw/jz4740_nand.c +++ b/drivers/mtd/nand/raw/jz4740_nand.c @@ -428,7 +428,7 @@ static int jz_nand_probe(struct platform_device *pdev) chip->legacy.chip_delay = 50; chip->legacy.cmd_ctrl = jz_nand_cmd_ctrl; chip->legacy.select_chip = jz_nand_select_chip; - chip->dummy_controller.ops = &jz_nand_controller_ops; + chip->legacy.dummy_controller.ops = &jz_nand_controller_ops; if (nand->busy_gpio) chip->legacy.dev_ready = jz_nand_dev_ready; diff --git a/drivers/mtd/nand/raw/lpc32xx_mlc.c b/drivers/mtd/nand/raw/lpc32xx_mlc.c index abbb655fe154..086964f8d424 100644 --- a/drivers/mtd/nand/raw/lpc32xx_mlc.c +++ b/drivers/mtd/nand/raw/lpc32xx_mlc.c @@ -799,7 +799,7 @@ static int lpc32xx_nand_probe(struct platform_device *pdev) * Scan to find existence of the device and get the type of NAND device: * SMALL block or LARGE block. */ - nand_chip->dummy_controller.ops = &lpc32xx_nand_controller_ops; + nand_chip->legacy.dummy_controller.ops = &lpc32xx_nand_controller_ops; res = nand_scan(nand_chip, 1); if (res) goto free_irq; diff --git a/drivers/mtd/nand/raw/lpc32xx_slc.c b/drivers/mtd/nand/raw/lpc32xx_slc.c index f2f2cdbb9d04..a2c5fdc875bd 100644 --- a/drivers/mtd/nand/raw/lpc32xx_slc.c +++ b/drivers/mtd/nand/raw/lpc32xx_slc.c @@ -924,7 +924,7 @@ static int lpc32xx_nand_probe(struct platform_device *pdev) } /* Find NAND device */ - chip->dummy_controller.ops = &lpc32xx_nand_controller_ops; + chip->legacy.dummy_controller.ops = &lpc32xx_nand_controller_ops; res = nand_scan(chip, 1); if (res) goto release_dma; diff --git a/drivers/mtd/nand/raw/mxc_nand.c b/drivers/mtd/nand/raw/mxc_nand.c index 9b75d894cb74..59554c187e01 100644 --- a/drivers/mtd/nand/raw/mxc_nand.c +++ b/drivers/mtd/nand/raw/mxc_nand.c @@ -1891,7 +1891,7 @@ static int mxcnd_probe(struct platform_device *pdev) } /* Scan the NAND device */ - this->dummy_controller.ops = &mxcnd_controller_ops; + this->legacy.dummy_controller.ops = &mxcnd_controller_ops; err = nand_scan(this, is_imx25_nfc(host) ? 4 : 1); if (err) goto escan; diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 3fc5c00f8dba..cca4b24d2ffa 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -4419,9 +4419,9 @@ static void nand_shutdown(struct mtd_info *mtd) /* Set default functions */ static void nand_set_defaults(struct nand_chip *chip) { - /* If no controller is provided, use the dummy one. */ + /* If no controller is provided, use the dummy, legacy one. */ if (!chip->controller) { - chip->controller = &chip->dummy_controller; + chip->controller = &chip->legacy.dummy_controller; nand_controller_init(chip->controller); } diff --git a/drivers/mtd/nand/raw/nandsim.c b/drivers/mtd/nand/raw/nandsim.c index c452819f6123..2b3047d53558 100644 --- a/drivers/mtd/nand/raw/nandsim.c +++ b/drivers/mtd/nand/raw/nandsim.c @@ -2304,7 +2304,7 @@ static int __init ns_init_module(void) if ((retval = parse_gravepages()) != 0) goto error; - chip->dummy_controller.ops = &ns_controller_ops; + chip->legacy.dummy_controller.ops = &ns_controller_ops; retval = nand_scan(chip, 1); if (retval) { NS_ERR("Could not scan NAND Simulator device\n"); diff --git a/drivers/mtd/nand/raw/sh_flctl.c b/drivers/mtd/nand/raw/sh_flctl.c index 7ab50bc6ad3a..cf6b1be1cf9c 100644 --- a/drivers/mtd/nand/raw/sh_flctl.c +++ b/drivers/mtd/nand/raw/sh_flctl.c @@ -1183,7 +1183,7 @@ static int flctl_probe(struct platform_device *pdev) flctl_setup_dma(flctl); - nand->dummy_controller.ops = &flctl_nand_controller_ops; + nand->legacy.dummy_controller.ops = &flctl_nand_controller_ops; ret = nand_scan(nand, 1); if (ret) goto err_chip; diff --git a/drivers/mtd/nand/raw/sm_common.c b/drivers/mtd/nand/raw/sm_common.c index 6f063ef57640..409d036858dc 100644 --- a/drivers/mtd/nand/raw/sm_common.c +++ b/drivers/mtd/nand/raw/sm_common.c @@ -194,7 +194,7 @@ int sm_register_device(struct mtd_info *mtd, int smartmedia) chip->options |= NAND_SKIP_BBTSCAN; /* Scan for card properties */ - chip->dummy_controller.ops = &sm_controller_ops; + chip->legacy.dummy_controller.ops = &sm_controller_ops; flash_ids = smartmedia ? nand_smartmedia_flash_ids : nand_xd_flash_ids; ret = nand_scan_with_ids(chip, 1, flash_ids); if (ret) diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index f50f40643895..33e240acdc6d 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -941,6 +941,8 @@ static inline void nand_controller_init(struct nand_controller *nfc) * @get_features: get the NAND chip features * @chip_delay: chip dependent delay for transferring data from array to read * regs (tR). + * @dummy_controller: dummy controller implementation for drivers that can + * only control a single chip * * If you look at this structure you're already wrong. These fields/hooks are * all deprecated. @@ -966,6 +968,7 @@ struct nand_legacy { int (*get_features)(struct nand_chip *chip, int feature_addr, u8 *subfeature_para); int chip_delay; + struct nand_controller dummy_controller; }; /** @@ -980,8 +983,6 @@ struct nand_legacy { * setting the read-retry mode. Mostly needed for MLC NAND. * @ecc: [BOARDSPECIFIC] ECC control structure * @buf_align: minimum buffer alignment required by a platform - * @dummy_controller: dummy controller implementation for drivers that can - * only control a single chip * @state: [INTERN] the current state of the NAND device * @oob_poi: "poison value buffer," used for laying out OOB data * before writing @@ -1094,7 +1095,6 @@ struct nand_chip { struct nand_ecc_ctrl ecc; unsigned long buf_align; - struct nand_controller dummy_controller; uint8_t *bbt; struct nand_bbt_descr *bbt_td; From c93c613214ac70c87beab5422a60077bf126b855 Mon Sep 17 00:00:00 2001 From: Chuanhong Guo Date: Wed, 28 Nov 2018 21:07:25 +0800 Subject: [PATCH 351/356] mtd: spinand: add support for GigaDevice GD5FxGQ4xA Add support for GigaDevice GD5F1G/2G/4GQ4xA SPI NAND. Signed-off-by: Chuanhong Guo Reviewed-by: Frieder Schrempf Signed-off-by: Miquel Raynal --- drivers/mtd/nand/spi/Makefile | 2 +- drivers/mtd/nand/spi/core.c | 1 + drivers/mtd/nand/spi/gigadevice.c | 148 ++++++++++++++++++++++++++++++ include/linux/mtd/spinand.h | 1 + 4 files changed, 151 insertions(+), 1 deletion(-) create mode 100644 drivers/mtd/nand/spi/gigadevice.c diff --git a/drivers/mtd/nand/spi/Makefile b/drivers/mtd/nand/spi/Makefile index be5f73512ece..753125082640 100644 --- a/drivers/mtd/nand/spi/Makefile +++ b/drivers/mtd/nand/spi/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 -spinand-objs := core.o macronix.o micron.o toshiba.o winbond.o +spinand-objs := core.o gigadevice.o macronix.o micron.o toshiba.o winbond.o obj-$(CONFIG_MTD_SPI_NAND) += spinand.o diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c index 87bdf2a7b724..479c2f2cf17f 100644 --- a/drivers/mtd/nand/spi/core.c +++ b/drivers/mtd/nand/spi/core.c @@ -764,6 +764,7 @@ static const struct nand_ops spinand_ops = { }; static const struct spinand_manufacturer *spinand_manufacturers[] = { + &gigadevice_spinand_manufacturer, ¯onix_spinand_manufacturer, µn_spinand_manufacturer, &toshiba_spinand_manufacturer, diff --git a/drivers/mtd/nand/spi/gigadevice.c b/drivers/mtd/nand/spi/gigadevice.c new file mode 100644 index 000000000000..e4141c20947a --- /dev/null +++ b/drivers/mtd/nand/spi/gigadevice.c @@ -0,0 +1,148 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Author: + * Chuanhong Guo + */ + +#include +#include +#include + +#define SPINAND_MFR_GIGADEVICE 0xC8 +#define GD5FXGQ4XA_STATUS_ECC_1_7_BITFLIPS (1 << 4) +#define GD5FXGQ4XA_STATUS_ECC_8_BITFLIPS (3 << 4) + +static SPINAND_OP_VARIANTS(read_cache_variants, + SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 2, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0), + SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0)); + +static SPINAND_OP_VARIANTS(write_cache_variants, + SPINAND_PROG_LOAD_X4(true, 0, NULL, 0), + SPINAND_PROG_LOAD(true, 0, NULL, 0)); + +static SPINAND_OP_VARIANTS(update_cache_variants, + SPINAND_PROG_LOAD_X4(false, 0, NULL, 0), + SPINAND_PROG_LOAD(false, 0, NULL, 0)); + +static int gd5fxgq4xa_ooblayout_ecc(struct mtd_info *mtd, int section, + struct mtd_oob_region *region) +{ + if (section > 3) + return -ERANGE; + + region->offset = (16 * section) + 8; + region->length = 8; + + return 0; +} + +static int gd5fxgq4xa_ooblayout_free(struct mtd_info *mtd, int section, + struct mtd_oob_region *region) +{ + if (section > 3) + return -ERANGE; + + if (section) { + region->offset = 16 * section; + region->length = 8; + } else { + /* section 0 has one byte reserved for bad block mark */ + region->offset = 1; + region->length = 7; + } + return 0; +} + +static int gd5fxgq4xa_ecc_get_status(struct spinand_device *spinand, + u8 status) +{ + switch (status & STATUS_ECC_MASK) { + case STATUS_ECC_NO_BITFLIPS: + return 0; + + case GD5FXGQ4XA_STATUS_ECC_1_7_BITFLIPS: + /* 1-7 bits are flipped. return the maximum. */ + return 7; + + case GD5FXGQ4XA_STATUS_ECC_8_BITFLIPS: + return 8; + + case STATUS_ECC_UNCOR_ERROR: + return -EBADMSG; + + default: + break; + } + + return -EINVAL; +} + +static const struct mtd_ooblayout_ops gd5fxgq4xa_ooblayout = { + .ecc = gd5fxgq4xa_ooblayout_ecc, + .free = gd5fxgq4xa_ooblayout_free, +}; + +static const struct spinand_info gigadevice_spinand_table[] = { + SPINAND_INFO("GD5F1GQ4xA", 0xF1, + NAND_MEMORG(1, 2048, 64, 64, 1024, 1, 1, 1), + NAND_ECCREQ(8, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants, + &write_cache_variants, + &update_cache_variants), + 0, + SPINAND_ECCINFO(&gd5fxgq4xa_ooblayout, + gd5fxgq4xa_ecc_get_status)), + SPINAND_INFO("GD5F2GQ4xA", 0xF2, + NAND_MEMORG(1, 2048, 64, 64, 2048, 1, 1, 1), + NAND_ECCREQ(8, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants, + &write_cache_variants, + &update_cache_variants), + 0, + SPINAND_ECCINFO(&gd5fxgq4xa_ooblayout, + gd5fxgq4xa_ecc_get_status)), + SPINAND_INFO("GD5F4GQ4xA", 0xF4, + NAND_MEMORG(1, 2048, 64, 64, 4096, 1, 1, 1), + NAND_ECCREQ(8, 512), + SPINAND_INFO_OP_VARIANTS(&read_cache_variants, + &write_cache_variants, + &update_cache_variants), + 0, + SPINAND_ECCINFO(&gd5fxgq4xa_ooblayout, + gd5fxgq4xa_ecc_get_status)), +}; + +static int gigadevice_spinand_detect(struct spinand_device *spinand) +{ + u8 *id = spinand->id.data; + int ret; + + /* + * For GD NANDs, There is an address byte needed to shift in before IDs + * are read out, so the first byte in raw_id is dummy. + */ + if (id[1] != SPINAND_MFR_GIGADEVICE) + return 0; + + ret = spinand_match_and_init(spinand, gigadevice_spinand_table, + ARRAY_SIZE(gigadevice_spinand_table), + id[2]); + if (ret) + return ret; + + return 1; +} + +static const struct spinand_manufacturer_ops gigadevice_spinand_manuf_ops = { + .detect = gigadevice_spinand_detect, +}; + +const struct spinand_manufacturer gigadevice_spinand_manufacturer = { + .id = SPINAND_MFR_GIGADEVICE, + .name = "GigaDevice", + .ops = &gigadevice_spinand_manuf_ops, +}; diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 816c4b00abca..b92e2aa955b6 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -194,6 +194,7 @@ struct spinand_manufacturer { }; /* SPI NAND manufacturers */ +extern const struct spinand_manufacturer gigadevice_spinand_manufacturer; extern const struct spinand_manufacturer macronix_spinand_manufacturer; extern const struct spinand_manufacturer micron_spinand_manufacturer; extern const struct spinand_manufacturer toshiba_spinand_manufacturer; From 38842572df1c79213b99e0c3472ce95aa5d152cf Mon Sep 17 00:00:00 2001 From: Mathieu Malaterre Date: Tue, 4 Dec 2018 21:10:57 +0100 Subject: [PATCH 352/356] mtd: rawnand: jz4780: annotate implicit fall throughs There is a plan to build the kernel with -Wimplicit-fallthrough and these places in the code produced warnings. Fix them up. Signed-off-by: Mathieu Malaterre Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/jz4780_bch.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/mtd/nand/raw/jz4780_bch.c b/drivers/mtd/nand/raw/jz4780_bch.c index 731c6051d91e..7201827809e9 100644 --- a/drivers/mtd/nand/raw/jz4780_bch.c +++ b/drivers/mtd/nand/raw/jz4780_bch.c @@ -136,8 +136,10 @@ static void jz4780_bch_read_parity(struct jz4780_bch *bch, void *buf, switch (size8) { case 3: dest8[2] = (val >> 16) & 0xff; + /* fall through */ case 2: dest8[1] = (val >> 8) & 0xff; + /* fall through */ case 1: dest8[0] = val & 0xff; break; From b637ef779575a977068025f842ecd480a9671f3f Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 13 Dec 2018 11:55:26 +0100 Subject: [PATCH 353/356] mtd: rawnand: Fix JEDEC detection nand_jedec_detect() should return 1 when the PARAM page parsing succeeds, otherwise the core considers JEDEC detection failed and falls back to ID-based detection. Fixes: 480139d9229e ("mtd: rawnand: get rid of the JEDEC parameter page in nand_chip") Cc: Signed-off-by: Boris Brezillon Acked-by: Miquel Raynal Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/nand_jedec.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/mtd/nand/raw/nand_jedec.c b/drivers/mtd/nand/raw/nand_jedec.c index 5c26492c841d..38b5dc22cb30 100644 --- a/drivers/mtd/nand/raw/nand_jedec.c +++ b/drivers/mtd/nand/raw/nand_jedec.c @@ -107,6 +107,8 @@ int nand_jedec_detect(struct nand_chip *chip) pr_warn("Invalid codeword size\n"); } + ret = 1; + free_jedec_param_page: kfree(p); return ret; From 9b432630e0150b777c423fdef6a7b8d17dfa70b6 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 13 Dec 2018 20:22:27 +0100 Subject: [PATCH 354/356] mtd: rawnand: omap2: Pass the parent of pdev to dma_request_chan() Commit e1e6255c311b ("mtd: rawnand: omap2: convert driver to nand_scan()") moved part of the init code in the ->attach_chip hook and at the same time changed the struct device object passed to dma_request_chan() (&pdev->dev instead of pdev->dev.parent). Fixes: e1e6255c311b ("mtd: rawnand: omap2: convert driver to nand_scan()") Reported-by: Alexander Sverdlin Cc: Signed-off-by: Boris Brezillon Tested-by: Alexander Sverdlin Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/omap2.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/nand/raw/omap2.c b/drivers/mtd/nand/raw/omap2.c index 886d05c391ef..68e8b9f7f372 100644 --- a/drivers/mtd/nand/raw/omap2.c +++ b/drivers/mtd/nand/raw/omap2.c @@ -1944,7 +1944,7 @@ static int omap_nand_attach_chip(struct nand_chip *chip) case NAND_OMAP_PREFETCH_DMA: dma_cap_zero(mask); dma_cap_set(DMA_SLAVE, mask); - info->dma = dma_request_chan(dev, "rxtx"); + info->dma = dma_request_chan(dev->parent, "rxtx"); if (IS_ERR(info->dma)) { dev_err(dev, "DMA engine request failed\n"); From cafb56dd741e61c99709bcd2b193a9a1d36def3b Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 11 Dec 2018 18:38:28 +0100 Subject: [PATCH 355/356] mtd: rawnand: marvell: prevent timeouts on a loaded machine marvell_nfc_wait_op() waits for completion during 'timeout_ms' milliseconds before throwing an error. While the logic is fine, the value of 'timeout_ms' is given by the core and actually correspond to the maximum time the NAND chip will take to complete the operation. Assuming there is no overhead in the propagation of the interrupt signal to the the NAND controller (through the Ready/Busy line), this delay does not take into account the latency of the operating system. For instance, for a page write, the delay given by the core is rounded up to 1ms. Hence, when the machine is over loaded, there is chances that this timeout will be reached. There are two ways to solve this issue that are not incompatible: 1/ Enlarge the timeout value (if so, how much?). 2/ Check after the waiting method if we did not miss any interrupt because of the OS latency (an interrupt is still pending). In this case, we assume the operation exited successfully. We choose the second approach that is a must in all cases, with the possibility to also modify the timeout value to be, e.g. at least 1 second in all cases. Fixes: 02f26ecf8c77 ("mtd: nand: add reworked Marvell NAND controller driver") Cc: stable@vger.kernel.org Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon --- drivers/mtd/nand/raw/marvell_nand.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c index e6c3739cea73..84283c6bb0ff 100644 --- a/drivers/mtd/nand/raw/marvell_nand.c +++ b/drivers/mtd/nand/raw/marvell_nand.c @@ -514,9 +514,14 @@ static void marvell_nfc_enable_int(struct marvell_nfc *nfc, u32 int_mask) writel_relaxed(reg & ~int_mask, nfc->regs + NDCR); } -static void marvell_nfc_clear_int(struct marvell_nfc *nfc, u32 int_mask) +static u32 marvell_nfc_clear_int(struct marvell_nfc *nfc, u32 int_mask) { + u32 reg; + + reg = readl_relaxed(nfc->regs + NDSR); writel_relaxed(int_mask, nfc->regs + NDSR); + + return reg & int_mask; } static void marvell_nfc_force_byte_access(struct nand_chip *chip, @@ -683,6 +688,7 @@ static int marvell_nfc_wait_cmdd(struct nand_chip *chip) static int marvell_nfc_wait_op(struct nand_chip *chip, unsigned int timeout_ms) { struct marvell_nfc *nfc = to_marvell_nfc(chip->controller); + u32 pending; int ret; /* Timeout is expressed in ms */ @@ -695,8 +701,13 @@ static int marvell_nfc_wait_op(struct nand_chip *chip, unsigned int timeout_ms) ret = wait_for_completion_timeout(&nfc->complete, msecs_to_jiffies(timeout_ms)); marvell_nfc_disable_int(nfc, NDCR_RDYM); - marvell_nfc_clear_int(nfc, NDSR_RDY(0) | NDSR_RDY(1)); - if (!ret) { + pending = marvell_nfc_clear_int(nfc, NDSR_RDY(0) | NDSR_RDY(1)); + + /* + * In case the interrupt was not served in the required time frame, + * check if the ISR was not served or if something went actually wrong. + */ + if (ret && !pending) { dev_err(nfc->dev, "Timeout waiting for RB signal\n"); return -ETIMEDOUT; } From 732774437ae01d9882e60314e303898e63c7f038 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 16 Dec 2018 09:34:17 +0100 Subject: [PATCH 356/356] mtd: rawnand: sunxi: Write pageprog related opcodes to WCMD_SET The opcodes used by the controller when doing batched page prog should be written in NFC_REG_WCMD_SET not FC_REG_RCMD_SET. Luckily, the default NFC_REG_WCMD_SET value matches the one we set in the driver which explains why we didn't notice the problem. Fixes: 614049a8d904 ("mtd: nand: sunxi: add support for DMA assisted operations") Signed-off-by: Boris Brezillon Signed-off-by: Miquel Raynal --- drivers/mtd/nand/raw/sunxi_nand.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/nand/raw/sunxi_nand.c b/drivers/mtd/nand/raw/sunxi_nand.c index a5c83cbe4897..e828ee50a201 100644 --- a/drivers/mtd/nand/raw/sunxi_nand.c +++ b/drivers/mtd/nand/raw/sunxi_nand.c @@ -1393,7 +1393,7 @@ static int sunxi_nfc_hw_ecc_write_page_dma(struct nand_chip *chip, sunxi_nfc_randomizer_enable(mtd); writel((NAND_CMD_RNDIN << 8) | NAND_CMD_PAGEPROG, - nfc->regs + NFC_REG_RCMD_SET); + nfc->regs + NFC_REG_WCMD_SET); dma_async_issue_pending(nfc->dmac);