diff --git a/Documentation/devicetree/bindings/ipmi/aspeed,ast2400-bt-bmc.txt b/Documentation/devicetree/bindings/ipmi/aspeed,ast2400-ibt-bmc.txt similarity index 85% rename from Documentation/devicetree/bindings/ipmi/aspeed,ast2400-bt-bmc.txt rename to Documentation/devicetree/bindings/ipmi/aspeed,ast2400-ibt-bmc.txt index fbbacd958240..6f28969af9dc 100644 --- a/Documentation/devicetree/bindings/ipmi/aspeed,ast2400-bt-bmc.txt +++ b/Documentation/devicetree/bindings/ipmi/aspeed,ast2400-ibt-bmc.txt @@ -6,7 +6,7 @@ perform in-band IPMI communication with their host. Required properties: -- compatible : should be "aspeed,ast2400-bt-bmc" +- compatible : should be "aspeed,ast2400-ibt-bmc" - reg: physical address and size of the registers Optional properties: @@ -17,7 +17,7 @@ Optional properties: Example: ibt@1e789140 { - compatible = "aspeed,ast2400-bt-bmc"; + compatible = "aspeed,ast2400-ibt-bmc"; reg = <0x1e789140 0x18>; interrupts = <8>; }; diff --git a/Documentation/devicetree/bindings/sound/omap-abe-twl6040.txt b/Documentation/devicetree/bindings/sound/omap-abe-twl6040.txt index fd40c852d7c7..462b04e8209f 100644 --- a/Documentation/devicetree/bindings/sound/omap-abe-twl6040.txt +++ b/Documentation/devicetree/bindings/sound/omap-abe-twl6040.txt @@ -12,7 +12,7 @@ Required properties: Optional properties: - ti,dmic: phandle for the OMAP dmic node if the machine have it connected -- ti,jack_detection: Need to be present if the board capable to detect jack +- ti,jack-detection: Need to be present if the board capable to detect jack insertion, removal. Available audio endpoints for the audio-routing table: diff --git a/Documentation/i2c/i2c-topology b/Documentation/i2c/i2c-topology index e0aefeece551..1a014fede0b7 100644 --- a/Documentation/i2c/i2c-topology +++ b/Documentation/i2c/i2c-topology @@ -326,7 +326,7 @@ Two parent-locked sibling muxes This is a good topology. - .--------. + .--------. .----------. .--| dev D1 | | parent- |--' '--------' .--| locked | .--------. @@ -350,7 +350,7 @@ Mux-locked and parent-locked sibling muxes This is a good topology. - .--------. + .--------. .----------. .--| dev D1 | | mux- |--' '--------' .--| locked | .--------. diff --git a/Documentation/networking/dsa/dsa.txt b/Documentation/networking/dsa/dsa.txt index 6d6c07cf1a9a..63912ef34606 100644 --- a/Documentation/networking/dsa/dsa.txt +++ b/Documentation/networking/dsa/dsa.txt @@ -67,13 +67,14 @@ Note that DSA does not currently create network interfaces for the "cpu" and Switch tagging protocols ------------------------ -DSA currently supports 4 different tagging protocols, and a tag-less mode as +DSA currently supports 5 different tagging protocols, and a tag-less mode as well. The different protocols are implemented in: net/dsa/tag_trailer.c: Marvell's 4 trailer tag mode (legacy) net/dsa/tag_dsa.c: Marvell's original DSA tag net/dsa/tag_edsa.c: Marvell's enhanced DSA tag net/dsa/tag_brcm.c: Broadcom's 4 bytes tag +net/dsa/tag_qca.c: Qualcomm's 2 bytes tag The exact format of the tag protocol is vendor specific, but in general, they all contain something which: diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 739db9ab16b2..6bbceb9a3a19 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -777,6 +777,17 @@ Gets the current timestamp of kvmclock as seen by the current guest. In conjunction with KVM_SET_CLOCK, it is used to ensure monotonicity on scenarios such as migration. +When KVM_CAP_ADJUST_CLOCK is passed to KVM_CHECK_EXTENSION, it returns the +set of bits that KVM can return in struct kvm_clock_data's flag member. + +The only flag defined now is KVM_CLOCK_TSC_STABLE. If set, the returned +value is the exact kvmclock value seen by all VCPUs at the instant +when KVM_GET_CLOCK was called. If clear, the returned value is simply +CLOCK_MONOTONIC plus a constant offset; the offset can be modified +with KVM_SET_CLOCK. KVM will try to make all VCPUs follow this clock, +but the exact value read by each VCPU could differ, because the host +TSC is not stable. + struct kvm_clock_data { __u64 clock; /* kvmclock current value */ __u32 flags; diff --git a/MAINTAINERS b/MAINTAINERS index 7db3f7ae6558..3db2078e0e47 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7084,6 +7084,7 @@ F: drivers/scsi/53c700* LED SUBSYSTEM M: Richard Purdie M: Jacek Anaszewski +M: Pavel Machek L: linux-leds@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/j.anaszewski/linux-leds.git S: Maintained @@ -8084,6 +8085,7 @@ F: drivers/infiniband/hw/mlx4/ F: include/linux/mlx4/ MELLANOX MLX5 core VPI driver +M: Saeed Mahameed M: Matan Barak M: Leon Romanovsky L: netdev@vger.kernel.org diff --git a/Makefile b/Makefile index 247430abfc73..0ede48ba5aaf 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 9 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Psychotic Stoned Sheep # *DOCUMENTATION* @@ -399,11 +399,12 @@ KBUILD_CFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -fno-strict-aliasing -fno-common \ -Werror-implicit-function-declaration \ -Wno-format-security \ - -std=gnu89 + -std=gnu89 $(call cc-option,-fno-PIE) + KBUILD_AFLAGS_KERNEL := KBUILD_CFLAGS_KERNEL := -KBUILD_AFLAGS := -D__ASSEMBLY__ +KBUILD_AFLAGS := -D__ASSEMBLY__ $(call cc-option,-fno-PIE) KBUILD_AFLAGS_MODULE := -DMODULE KBUILD_CFLAGS_MODULE := -DMODULE KBUILD_LDFLAGS_MODULE := -T $(srctree)/scripts/module-common.lds diff --git a/arch/arm/boot/dts/imx53-qsb.dts b/arch/arm/boot/dts/imx53-qsb.dts index dec4b073ceb1..379939699164 100644 --- a/arch/arm/boot/dts/imx53-qsb.dts +++ b/arch/arm/boot/dts/imx53-qsb.dts @@ -64,8 +64,8 @@ }; ldo3_reg: ldo3 { - regulator-min-microvolt = <600000>; - regulator-max-microvolt = <1800000>; + regulator-min-microvolt = <1725000>; + regulator-max-microvolt = <3300000>; regulator-always-on; }; @@ -76,8 +76,8 @@ }; ldo5_reg: ldo5 { - regulator-min-microvolt = <1725000>; - regulator-max-microvolt = <3300000>; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <3600000>; regulator-always-on; }; @@ -100,14 +100,14 @@ }; ldo9_reg: ldo9 { - regulator-min-microvolt = <1200000>; + regulator-min-microvolt = <1250000>; regulator-max-microvolt = <3600000>; regulator-always-on; }; ldo10_reg: ldo10 { - regulator-min-microvolt = <1250000>; - regulator-max-microvolt = <3650000>; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <3600000>; regulator-always-on; }; }; diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi index 0ff1c2de95bf..26cce4d18405 100644 --- a/arch/arm/boot/dts/logicpd-som-lv.dtsi +++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi @@ -13,6 +13,11 @@ }; }; + memory@80000000 { + device_type = "memory"; + reg = <0x80000000 0>; + }; + wl12xx_vmmc: wl12xx_vmmc { compatible = "regulator-fixed"; regulator-name = "vwl1271"; diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi index 731ec37aed5b..8f9a69ca818c 100644 --- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi +++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi @@ -13,9 +13,9 @@ }; }; - memory@0 { + memory@80000000 { device_type = "memory"; - reg = <0 0>; + reg = <0x80000000 0>; }; leds { diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi index 6365635fea5c..4caadb253249 100644 --- a/arch/arm/boot/dts/omap5-board-common.dtsi +++ b/arch/arm/boot/dts/omap5-board-common.dtsi @@ -124,6 +124,7 @@ compatible = "ti,abe-twl6040"; ti,model = "omap5-uevm"; + ti,jack-detection; ti,mclk-freq = <19200000>; ti,mcpdm = <&mcpdm>; @@ -415,7 +416,7 @@ ti,backup-battery-charge-high-current; }; - gpadc { + gpadc: gpadc { compatible = "ti,palmas-gpadc"; interrupts = <18 0 16 0 @@ -475,8 +476,8 @@ smps6_reg: smps6 { /* VDD_DDR3 - over VDD_SMPS6 */ regulator-name = "smps6"; - regulator-min-microvolt = <1200000>; - regulator-max-microvolt = <1200000>; + regulator-min-microvolt = <1350000>; + regulator-max-microvolt = <1350000>; regulator-always-on; regulator-boot-on; }; diff --git a/arch/arm/boot/dts/stih410-b2260.dts b/arch/arm/boot/dts/stih410-b2260.dts index ef2ff2f518f6..7fb507fcba7e 100644 --- a/arch/arm/boot/dts/stih410-b2260.dts +++ b/arch/arm/boot/dts/stih410-b2260.dts @@ -74,7 +74,7 @@ /* Low speed expansion connector */ spi0: spi@9844000 { label = "LS-SPI0"; - cs-gpio = <&pio30 3 0>; + cs-gpios = <&pio30 3 0>; status = "okay"; }; diff --git a/arch/arm/boot/dts/sun8i-a23-a33.dtsi b/arch/arm/boot/dts/sun8i-a23-a33.dtsi index 48fc24f36fcb..300a1bd5a6ec 100644 --- a/arch/arm/boot/dts/sun8i-a23-a33.dtsi +++ b/arch/arm/boot/dts/sun8i-a23-a33.dtsi @@ -282,11 +282,15 @@ uart1_pins_a: uart1@0 { allwinner,pins = "PG6", "PG7"; allwinner,function = "uart1"; + allwinner,drive = ; + allwinner,pull = ; }; uart1_pins_cts_rts_a: uart1-cts-rts@0 { allwinner,pins = "PG8", "PG9"; allwinner,function = "uart1"; + allwinner,drive = ; + allwinner,pull = ; }; mmc0_pins_a: mmc0@0 { diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index bc698383e822..9688ec0c6ef4 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -74,6 +74,26 @@ void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long dump_mem("", "Exception stack", frame + 4, frame + 4 + sizeof(struct pt_regs)); } +void dump_backtrace_stm(u32 *stack, u32 instruction) +{ + char str[80], *p; + unsigned int x; + int reg; + + for (reg = 10, x = 0, p = str; reg >= 0; reg--) { + if (instruction & BIT(reg)) { + p += sprintf(p, " r%d:%08x", reg, *stack--); + if (++x == 6) { + x = 0; + p = str; + printk("%s\n", str); + } + } + } + if (p != str) + printk("%s\n", str); +} + #ifndef CONFIG_ARM_UNWIND /* * Stack pointers should always be within the kernels view of diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S index 7fa487ef7e2f..37b2a11af345 100644 --- a/arch/arm/kernel/vmlinux-xip.lds.S +++ b/arch/arm/kernel/vmlinux-xip.lds.S @@ -3,6 +3,9 @@ * Written by Martin Mares */ +/* No __ro_after_init data in the .rodata section - which will always be ro */ +#define RO_AFTER_INIT_DATA + #include #include #include @@ -223,6 +226,8 @@ SECTIONS . = ALIGN(PAGE_SIZE); __init_end = .; + *(.data..ro_after_init) + NOSAVE_DATA CACHELINE_ALIGNED_DATA(L1_CACHE_BYTES) READ_MOSTLY_DATA(L1_CACHE_BYTES) diff --git a/arch/arm/lib/backtrace.S b/arch/arm/lib/backtrace.S index fab5a50503ae..7d7952e5a3b1 100644 --- a/arch/arm/lib/backtrace.S +++ b/arch/arm/lib/backtrace.S @@ -10,6 +10,7 @@ * 27/03/03 Ian Molton Clean up CONFIG_CPU * */ +#include #include #include .text @@ -83,13 +84,13 @@ for_each_frame: tst frame, mask @ Check for address exceptions teq r3, r1, lsr #11 ldreq r0, [frame, #-8] @ get sp subeq r0, r0, #4 @ point at the last arg - bleq .Ldumpstm @ dump saved registers + bleq dump_backtrace_stm @ dump saved registers 1004: ldr r1, [sv_pc, #0] @ if stmfd sp!, {..., fp, ip, lr, pc} ldr r3, .Ldsi @ instruction exists, teq r3, r1, lsr #11 subeq r0, frame, #16 - bleq .Ldumpstm @ dump saved registers + bleq dump_backtrace_stm @ dump saved registers teq sv_fp, #0 @ zero saved fp means beq no_frame @ no further frames @@ -112,38 +113,6 @@ ENDPROC(c_backtrace) .long 1004b, 1006b .popsection -#define instr r4 -#define reg r5 -#define stack r6 - -.Ldumpstm: stmfd sp!, {instr, reg, stack, r7, lr} - mov stack, r0 - mov instr, r1 - mov reg, #10 - mov r7, #0 -1: mov r3, #1 - ARM( tst instr, r3, lsl reg ) - THUMB( lsl r3, reg ) - THUMB( tst instr, r3 ) - beq 2f - add r7, r7, #1 - teq r7, #6 - moveq r7, #0 - adr r3, .Lcr - addne r3, r3, #1 @ skip newline - ldr r2, [stack], #-4 - mov r1, reg - adr r0, .Lfp - bl printk -2: subs reg, reg, #1 - bpl 1b - teq r7, #0 - adrne r0, .Lcr - blne printk - ldmfd sp!, {instr, reg, stack, r7, pc} - -.Lfp: .asciz " r%d:%08x%s" -.Lcr: .asciz "\n" .Lbad: .asciz "Backtrace aborted due to bad frame pointer <%p>\n" .align .Ldsi: .word 0xe92dd800 >> 11 @ stmfd sp!, {... fp, ip, lr, pc} diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig index a9afeebd59f2..0465338183c7 100644 --- a/arch/arm/mach-omap2/Kconfig +++ b/arch/arm/mach-omap2/Kconfig @@ -71,6 +71,7 @@ config SOC_AM43XX select HAVE_ARM_TWD select ARM_ERRATA_754322 select ARM_ERRATA_775420 + select OMAP_INTERCONNECT config SOC_DRA7XX bool "TI DRA7XX" diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c index 2abd53ae3e7a..cc6d9fa60924 100644 --- a/arch/arm/mach-omap2/id.c +++ b/arch/arm/mach-omap2/id.c @@ -205,11 +205,15 @@ void __init omap2xxx_check_revision(void) #define OMAP3_SHOW_FEATURE(feat) \ if (omap3_has_ ##feat()) \ - printk(#feat" "); + n += scnprintf(buf + n, sizeof(buf) - n, #feat " "); static void __init omap3_cpuinfo(void) { const char *cpu_name; + char buf[64]; + int n = 0; + + memset(buf, 0, sizeof(buf)); /* * OMAP3430 and OMAP3530 are assumed to be same. @@ -241,10 +245,10 @@ static void __init omap3_cpuinfo(void) cpu_name = "OMAP3503"; } - sprintf(soc_name, "%s", cpu_name); + scnprintf(soc_name, sizeof(soc_name), "%s", cpu_name); /* Print verbose information */ - pr_info("%s %s (", soc_name, soc_rev); + n += scnprintf(buf, sizeof(buf) - n, "%s %s (", soc_name, soc_rev); OMAP3_SHOW_FEATURE(l2cache); OMAP3_SHOW_FEATURE(iva); @@ -252,8 +256,10 @@ static void __init omap3_cpuinfo(void) OMAP3_SHOW_FEATURE(neon); OMAP3_SHOW_FEATURE(isp); OMAP3_SHOW_FEATURE(192mhz_clk); - - printk(")\n"); + if (*(buf + n - 1) == ' ') + n--; + n += scnprintf(buf + n, sizeof(buf) - n, ")\n"); + pr_info("%s", buf); } #define OMAP3_CHECK_FEATURE(status,feat) \ diff --git a/arch/arm/mach-omap2/prm3xxx.c b/arch/arm/mach-omap2/prm3xxx.c index 62680aad2126..718981bb80cd 100644 --- a/arch/arm/mach-omap2/prm3xxx.c +++ b/arch/arm/mach-omap2/prm3xxx.c @@ -319,6 +319,9 @@ void __init omap3_prm_init_pm(bool has_uart4, bool has_iva) if (has_uart4) { en_uart4_mask = OMAP3630_EN_UART4_MASK; grpsel_uart4_mask = OMAP3630_GRPSEL_UART4_MASK; + } else { + en_uart4_mask = 0; + grpsel_uart4_mask = 0; } /* Enable wakeups in PER */ diff --git a/arch/arm/mach-omap2/voltage.c b/arch/arm/mach-omap2/voltage.c index cba8cada8c81..cd15dbd62671 100644 --- a/arch/arm/mach-omap2/voltage.c +++ b/arch/arm/mach-omap2/voltage.c @@ -87,6 +87,12 @@ int voltdm_scale(struct voltagedomain *voltdm, return -ENODATA; } + if (!voltdm->volt_data) { + pr_err("%s: No voltage data defined for vdd_%s\n", + __func__, voltdm->name); + return -ENODATA; + } + /* Adjust voltage to the exact voltage from the OPP table */ for (i = 0; voltdm->volt_data[i].volt_nominal != 0; i++) { if (voltdm->volt_data[i].volt_nominal >= target_volt) { diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index ab4f74536057..ab7710002ba6 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -1167,7 +1167,7 @@ static int __init dma_debug_do_init(void) dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES); return 0; } -fs_initcall(dma_debug_do_init); +core_initcall(dma_debug_do_init); #ifdef CONFIG_ARM_DMA_USE_IOMMU diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S index f6d333f09bfe..8dea61640cc1 100644 --- a/arch/arm/mm/proc-v7m.S +++ b/arch/arm/mm/proc-v7m.S @@ -96,7 +96,7 @@ ENTRY(cpu_cm7_proc_fin) ret lr ENDPROC(cpu_cm7_proc_fin) - .section ".text.init", #alloc, #execinstr + .section ".init.text", #alloc, #execinstr __v7m_cm7_setup: mov r8, #(V7M_SCB_CCR_DC | V7M_SCB_CCR_IC| V7M_SCB_CCR_BP) diff --git a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi index c4762538ec01..e9bd58793464 100644 --- a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi @@ -105,7 +105,7 @@ status = "disabled"; }; - nb_perih_clk: nb-periph-clk@13000{ + nb_periph_clk: nb-periph-clk@13000 { compatible = "marvell,armada-3700-periph-clock-nb"; reg = <0x13000 0x100>; clocks = <&tbg 0>, <&tbg 1>, <&tbg 2>, @@ -113,7 +113,7 @@ #clock-cells = <1>; }; - sb_perih_clk: sb-periph-clk@18000{ + sb_periph_clk: sb-periph-clk@18000 { compatible = "marvell,armada-3700-periph-clock-sb"; reg = <0x18000 0x100>; clocks = <&tbg 0>, <&tbg 1>, <&tbg 2>, diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi index 842fb333285c..6bf9e241179b 100644 --- a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi @@ -130,8 +130,8 @@ reg = <0x700600 0x50>; #address-cells = <0x1>; #size-cells = <0x0>; - cell-index = <1>; - clocks = <&cps_syscon0 0 3>; + cell-index = <3>; + clocks = <&cps_syscon0 1 21>; status = "disabled"; }; @@ -140,7 +140,7 @@ reg = <0x700680 0x50>; #address-cells = <1>; #size-cells = <0>; - cell-index = <2>; + cell-index = <4>; clocks = <&cps_syscon0 1 21>; status = "disabled"; }; diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h index 2065f46fa740..38b6a2b49d68 100644 --- a/arch/arm64/include/asm/perf_event.h +++ b/arch/arm64/include/asm/perf_event.h @@ -46,7 +46,15 @@ #define ARMV8_PMU_EVTYPE_MASK 0xc800ffff /* Mask for writable bits */ #define ARMV8_PMU_EVTYPE_EVENT 0xffff /* Mask for EVENT bits */ -#define ARMV8_PMU_EVTYPE_EVENT_SW_INCR 0 /* Software increment event */ +/* + * PMUv3 event types: required events + */ +#define ARMV8_PMUV3_PERFCTR_SW_INCR 0x00 +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL 0x03 +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE 0x04 +#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED 0x10 +#define ARMV8_PMUV3_PERFCTR_CPU_CYCLES 0x11 +#define ARMV8_PMUV3_PERFCTR_BR_PRED 0x12 /* * Event filters for PMUv3 diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index a9310a69fffd..57ae9d9ed9bb 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -31,17 +31,9 @@ /* * ARMv8 PMUv3 Performance Events handling code. - * Common event types. + * Common event types (some are defined in asm/perf_event.h). */ -/* Required events. */ -#define ARMV8_PMUV3_PERFCTR_SW_INCR 0x00 -#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL 0x03 -#define ARMV8_PMUV3_PERFCTR_L1D_CACHE 0x04 -#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED 0x10 -#define ARMV8_PMUV3_PERFCTR_CPU_CYCLES 0x11 -#define ARMV8_PMUV3_PERFCTR_BR_PRED 0x12 - /* At least one of the following is required. */ #define ARMV8_PMUV3_PERFCTR_INST_RETIRED 0x08 #define ARMV8_PMUV3_PERFCTR_INST_SPEC 0x1B diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index f302fdb3a030..87e7e6608cd8 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -597,8 +597,14 @@ static bool access_pmu_evcntr(struct kvm_vcpu *vcpu, idx = ARMV8_PMU_CYCLE_IDX; } else { - BUG(); + return false; } + } else if (r->CRn == 0 && r->CRm == 9) { + /* PMCCNTR */ + if (pmu_access_event_counter_el0_disabled(vcpu)) + return false; + + idx = ARMV8_PMU_CYCLE_IDX; } else if (r->CRn == 14 && (r->CRm & 12) == 8) { /* PMEVCNTRn_EL0 */ if (pmu_access_event_counter_el0_disabled(vcpu)) @@ -606,7 +612,7 @@ static bool access_pmu_evcntr(struct kvm_vcpu *vcpu, idx = ((r->CRm & 3) << 3) | (r->Op2 & 7); } else { - BUG(); + return false; } if (!pmu_counter_idx_valid(vcpu, idx)) diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 84d49b197c32..9a3eee661297 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -91,7 +91,7 @@ */ #define LOAD_HANDLER(reg, label) \ ld reg,PACAKBASE(r13); /* get high part of &label */ \ - ori reg,reg,(FIXED_SYMBOL_ABS_ADDR(label))@l; + ori reg,reg,FIXED_SYMBOL_ABS_ADDR(label); #define __LOAD_HANDLER(reg, label) \ ld reg,PACAKBASE(r13); \ @@ -158,14 +158,17 @@ BEGIN_FTR_SECTION_NESTED(943) \ std ra,offset(r13); \ END_FTR_SECTION_NESTED(ftr,ftr,943) -#define EXCEPTION_PROLOG_0(area) \ - GET_PACA(r13); \ +#define EXCEPTION_PROLOG_0_PACA(area) \ std r9,area+EX_R9(r13); /* save r9 */ \ OPT_GET_SPR(r9, SPRN_PPR, CPU_FTR_HAS_PPR); \ HMT_MEDIUM; \ std r10,area+EX_R10(r13); /* save r10 - r12 */ \ OPT_GET_SPR(r10, SPRN_CFAR, CPU_FTR_CFAR) +#define EXCEPTION_PROLOG_0(area) \ + GET_PACA(r13); \ + EXCEPTION_PROLOG_0_PACA(area) + #define __EXCEPTION_PROLOG_1(area, extra, vec) \ OPT_SAVE_REG_TO_PACA(area+EX_PPR, r9, CPU_FTR_HAS_PPR); \ OPT_SAVE_REG_TO_PACA(area+EX_CFAR, r10, CPU_FTR_CFAR); \ @@ -196,6 +199,12 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) EXCEPTION_PROLOG_1(area, extra, vec); \ EXCEPTION_PROLOG_PSERIES_1(label, h); +/* Have the PACA in r13 already */ +#define EXCEPTION_PROLOG_PSERIES_PACA(area, label, h, extra, vec) \ + EXCEPTION_PROLOG_0_PACA(area); \ + EXCEPTION_PROLOG_1(area, extra, vec); \ + EXCEPTION_PROLOG_PSERIES_1(label, h); + #define __KVMTEST(h, n) \ lbz r10,HSTATE_IN_GUEST(r13); \ cmpwi r10,0; \ diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 0132831b3081..c56ea8c84abb 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -460,5 +460,6 @@ #define PPC_SLBIA(IH) stringify_in_c(.long PPC_INST_SLBIA | \ ((IH & 0x7) << 21)) +#define PPC_INVALIDATE_ERAT PPC_SLBIA(7) #endif /* _ASM_POWERPC_PPC_OPCODE_H */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 08ba447a4b3d..1ba82ea90230 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -116,7 +116,9 @@ EXC_VIRT_NONE(0x4000, 0x4100) EXC_REAL_BEGIN(system_reset, 0x100, 0x200) SET_SCRATCH0(r13) - EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD, + GET_PACA(r13) + clrrdi r13,r13,1 /* Last bit of HSPRG0 is set if waking from winkle */ + EXCEPTION_PROLOG_PSERIES_PACA(PACA_EXGEN, system_reset_common, EXC_STD, IDLETEST, 0x100) EXC_REAL_END(system_reset, 0x100, 0x200) @@ -124,6 +126,9 @@ EXC_VIRT_NONE(0x4100, 0x4200) #ifdef CONFIG_PPC_P7_NAP EXC_COMMON_BEGIN(system_reset_idle_common) +BEGIN_FTR_SECTION + GET_PACA(r13) /* Restore HSPRG0 to get the winkle bit in r13 */ +END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300) bl pnv_restore_hyp_resource li r0,PNV_THREAD_RUNNING @@ -169,7 +174,7 @@ EXC_REAL_BEGIN(machine_check, 0x200, 0x300) SET_SCRATCH0(r13) /* save r13 */ /* * Running native on arch 2.06 or later, we may wakeup from winkle - * inside machine check. If yes, then last bit of HSPGR0 would be set + * inside machine check. If yes, then last bit of HSPRG0 would be set * to 1. Hence clear it unconditionally. */ GET_PACA(r13) @@ -388,7 +393,7 @@ EXC_COMMON_BEGIN(machine_check_handle_early) /* * Go back to winkle. Please note that this thread was woken up in * machine check from winkle and have not restored the per-subcore - * state. Hence before going back to winkle, set last bit of HSPGR0 + * state. Hence before going back to winkle, set last bit of HSPRG0 * to 1. This will make sure that if this thread gets woken up * again at reset vector 0x100 then it will get chance to restore * the subcore state. diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index ce6dc61b15b2..49a680d5ae37 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1215,7 +1215,7 @@ static void show_instructions(struct pt_regs *regs) int instr; if (!(i % 8)) - printk("\n"); + pr_cont("\n"); #if !defined(CONFIG_BOOKE) /* If executing with the IMMU off, adjust pc rather @@ -1227,18 +1227,18 @@ static void show_instructions(struct pt_regs *regs) if (!__kernel_text_address(pc) || probe_kernel_address((unsigned int __user *)pc, instr)) { - printk(KERN_CONT "XXXXXXXX "); + pr_cont("XXXXXXXX "); } else { if (regs->nip == pc) - printk(KERN_CONT "<%08x> ", instr); + pr_cont("<%08x> ", instr); else - printk(KERN_CONT "%08x ", instr); + pr_cont("%08x ", instr); } pc += sizeof(int); } - printk("\n"); + pr_cont("\n"); } struct regbit { @@ -1282,7 +1282,7 @@ static void print_bits(unsigned long val, struct regbit *bits, const char *sep) for (; bits->bit; ++bits) if (val & bits->bit) { - printk("%s%s", s, bits->name); + pr_cont("%s%s", s, bits->name); s = sep; } } @@ -1305,9 +1305,9 @@ static void print_tm_bits(unsigned long val) * T: Transactional (bit 34) */ if (val & (MSR_TM | MSR_TS_S | MSR_TS_T)) { - printk(",TM["); + pr_cont(",TM["); print_bits(val, msr_tm_bits, ""); - printk("]"); + pr_cont("]"); } } #else @@ -1316,10 +1316,10 @@ static void print_tm_bits(unsigned long val) {} static void print_msr_bits(unsigned long val) { - printk("<"); + pr_cont("<"); print_bits(val, msr_bits, ","); print_tm_bits(val); - printk(">"); + pr_cont(">"); } #ifdef CONFIG_PPC64 @@ -1347,29 +1347,29 @@ void show_regs(struct pt_regs * regs) printk(" CR: %08lx XER: %08lx\n", regs->ccr, regs->xer); trap = TRAP(regs); if ((regs->trap != 0xc00) && cpu_has_feature(CPU_FTR_CFAR)) - printk("CFAR: "REG" ", regs->orig_gpr3); + pr_cont("CFAR: "REG" ", regs->orig_gpr3); if (trap == 0x200 || trap == 0x300 || trap == 0x600) #if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) - printk("DEAR: "REG" ESR: "REG" ", regs->dar, regs->dsisr); + pr_cont("DEAR: "REG" ESR: "REG" ", regs->dar, regs->dsisr); #else - printk("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr); + pr_cont("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr); #endif #ifdef CONFIG_PPC64 - printk("SOFTE: %ld ", regs->softe); + pr_cont("SOFTE: %ld ", regs->softe); #endif #ifdef CONFIG_PPC_TRANSACTIONAL_MEM if (MSR_TM_ACTIVE(regs->msr)) - printk("\nPACATMSCRATCH: %016llx ", get_paca()->tm_scratch); + pr_cont("\nPACATMSCRATCH: %016llx ", get_paca()->tm_scratch); #endif for (i = 0; i < 32; i++) { if ((i % REGS_PER_LINE) == 0) - printk("\nGPR%02d: ", i); - printk(REG " ", regs->gpr[i]); + pr_cont("\nGPR%02d: ", i); + pr_cont(REG " ", regs->gpr[i]); if (i == LAST_VOLATILE && !FULL_REGS(regs)) break; } - printk("\n"); + pr_cont("\n"); #ifdef CONFIG_KALLSYMS /* * Lookup NIP late so we have the best change of getting the @@ -1900,14 +1900,14 @@ void show_stack(struct task_struct *tsk, unsigned long *stack) printk("["REG"] ["REG"] %pS", sp, ip, (void *)ip); #ifdef CONFIG_FUNCTION_GRAPH_TRACER if ((ip == rth) && curr_frame >= 0) { - printk(" (%pS)", + pr_cont(" (%pS)", (void *)current->ret_stack[curr_frame].ret); curr_frame--; } #endif if (firstframe) - printk(" (unreliable)"); - printk("\n"); + pr_cont(" (unreliable)"); + pr_cont("\n"); } firstframe = 0; diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 7ac8e6eaab5b..8d586cff8a41 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -226,17 +226,25 @@ static void __init configure_exceptions(void) if (firmware_has_feature(FW_FEATURE_OPAL)) opal_configure_cores(); - /* Enable AIL if supported, and we are in hypervisor mode */ - if (early_cpu_has_feature(CPU_FTR_HVMODE) && - early_cpu_has_feature(CPU_FTR_ARCH_207S)) { - unsigned long lpcr = mfspr(SPRN_LPCR); - mtspr(SPRN_LPCR, lpcr | LPCR_AIL_3); - } + /* AIL on native is done in cpu_ready_for_interrupts() */ } } static void cpu_ready_for_interrupts(void) { + /* + * Enable AIL if supported, and we are in hypervisor mode. This + * is called once for every processor. + * + * If we are not in hypervisor mode the job is done once for + * the whole partition in configure_exceptions(). + */ + if (early_cpu_has_feature(CPU_FTR_HVMODE) && + early_cpu_has_feature(CPU_FTR_ARCH_207S)) { + unsigned long lpcr = mfspr(SPRN_LPCR); + mtspr(SPRN_LPCR, lpcr | LPCR_AIL_3); + } + /* Set IR and DR in PACA MSR */ get_paca()->kernel_msr = MSR_KERNEL; } diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 44d3c3a38e3e..5503078090cd 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -1029,6 +1029,10 @@ void hash__early_init_mmu_secondary(void) { /* Initialize hash table for that CPU */ if (!firmware_has_feature(FW_FEATURE_LPAR)) { + + if (cpu_has_feature(CPU_FTR_POWER9_DD1)) + update_hid_for_hash(); + if (!cpu_has_feature(CPU_FTR_ARCH_300)) mtspr(SPRN_SDR1, _SDR1); else diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index ed7bddc456b7..688b54517655 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -388,6 +388,10 @@ void radix__early_init_mmu_secondary(void) * update partition table control register and UPRT */ if (!firmware_has_feature(FW_FEATURE_LPAR)) { + + if (cpu_has_feature(CPU_FTR_POWER9_DD1)) + update_hid_for_radix(); + lpcr = mfspr(SPRN_LPCR); mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR); diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c index bda8c43be78a..3493cf4e0452 100644 --- a/arch/powerpc/mm/tlb-radix.c +++ b/arch/powerpc/mm/tlb-radix.c @@ -50,6 +50,8 @@ static inline void _tlbiel_pid(unsigned long pid, unsigned long ric) for (set = 0; set < POWER9_TLB_SETS_RADIX ; set++) { __tlbiel_pid(pid, set, ric); } + if (cpu_has_feature(CPU_FTR_POWER9_DD1)) + asm volatile(PPC_INVALIDATE_ERAT : : :"memory"); return; } @@ -83,6 +85,8 @@ static inline void _tlbiel_va(unsigned long va, unsigned long pid, asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); asm volatile("ptesync": : :"memory"); + if (cpu_has_feature(CPU_FTR_POWER9_DD1)) + asm volatile(PPC_INVALIDATE_ERAT : : :"memory"); } static inline void _tlbie_va(unsigned long va, unsigned long pid, diff --git a/arch/tile/include/asm/cache.h b/arch/tile/include/asm/cache.h index 6160761d5f61..4810e48dbbbf 100644 --- a/arch/tile/include/asm/cache.h +++ b/arch/tile/include/asm/cache.h @@ -61,4 +61,7 @@ */ #define __write_once __read_mostly +/* __ro_after_init is the generic name for the tile arch __write_once. */ +#define __ro_after_init __read_mostly + #endif /* _ASM_TILE_CACHE_H */ diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 5f845eef9a4d..81195cca7eae 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -8,8 +8,12 @@ #define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00 #define PCI_DEVICE_ID_INTEL_HSW_U_IMC 0x0a04 #define PCI_DEVICE_ID_INTEL_BDW_IMC 0x1604 -#define PCI_DEVICE_ID_INTEL_SKL_IMC 0x191f -#define PCI_DEVICE_ID_INTEL_SKL_U_IMC 0x190c +#define PCI_DEVICE_ID_INTEL_SKL_U_IMC 0x1904 +#define PCI_DEVICE_ID_INTEL_SKL_Y_IMC 0x190c +#define PCI_DEVICE_ID_INTEL_SKL_HD_IMC 0x1900 +#define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC 0x1910 +#define PCI_DEVICE_ID_INTEL_SKL_SD_IMC 0x190f +#define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC 0x191f /* SNB event control */ #define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff @@ -616,13 +620,29 @@ static const struct pci_device_id bdw_uncore_pci_ids[] = { static const struct pci_device_id skl_uncore_pci_ids[] = { { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_IMC), + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_Y_IMC), .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), }, { /* IMC */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_U_IMC), .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_HD_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_HQ_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_SD_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_SQ_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, { /* end: all zeroes */ }, }; @@ -666,8 +686,12 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = { IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core Processor */ IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core ULT Mobile Processor */ IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver), /* 5th Gen Core U */ - IMC_DEV(SKL_IMC, &skl_uncore_pci_driver), /* 6th Gen Core */ + IMC_DEV(SKL_Y_IMC, &skl_uncore_pci_driver), /* 6th Gen Core Y */ IMC_DEV(SKL_U_IMC, &skl_uncore_pci_driver), /* 6th Gen Core U */ + IMC_DEV(SKL_HD_IMC, &skl_uncore_pci_driver), /* 6th Gen Core H Dual Core */ + IMC_DEV(SKL_HQ_IMC, &skl_uncore_pci_driver), /* 6th Gen Core H Quad Core */ + IMC_DEV(SKL_SD_IMC, &skl_uncore_pci_driver), /* 6th Gen Core S Dual Core */ + IMC_DEV(SKL_SQ_IMC, &skl_uncore_pci_driver), /* 6th Gen Core S Quad Core */ { /* end marker */ } }; diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h index 5b6753d1f7f4..49da9f497b90 100644 --- a/arch/x86/include/asm/intel-mid.h +++ b/arch/x86/include/asm/intel-mid.h @@ -17,6 +17,7 @@ extern int intel_mid_pci_init(void); extern int intel_mid_pci_set_power_state(struct pci_dev *pdev, pci_power_t state); +extern pci_power_t intel_mid_pci_get_power_state(struct pci_dev *pdev); extern void intel_mid_pwr_power_off(void); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index b81fe2d63e15..1e81a37c034e 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -347,7 +347,6 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c) #ifdef CONFIG_SMP unsigned bits; int cpu = smp_processor_id(); - unsigned int socket_id, core_complex_id; bits = c->x86_coreid_bits; /* Low order bits define the core id (index of core in socket) */ @@ -365,10 +364,7 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c) if (c->x86 != 0x17 || !cpuid_edx(0x80000006)) return; - socket_id = (c->apicid >> bits) - 1; - core_complex_id = (c->apicid & ((1 << bits) - 1)) >> 3; - - per_cpu(cpu_llc_id, cpu) = (socket_id << 3) | core_complex_id; + per_cpu(cpu_llc_id, cpu) = c->apicid >> 3; #endif } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 9bd910a7dd0a..cc9e980c68ec 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -978,6 +978,35 @@ static void x86_init_cache_qos(struct cpuinfo_x86 *c) } } +/* + * The physical to logical package id mapping is initialized from the + * acpi/mptables information. Make sure that CPUID actually agrees with + * that. + */ +static void sanitize_package_id(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_SMP + unsigned int pkg, apicid, cpu = smp_processor_id(); + + apicid = apic->cpu_present_to_apicid(cpu); + pkg = apicid >> boot_cpu_data.x86_coreid_bits; + + if (apicid != c->initial_apicid) { + pr_err(FW_BUG "CPU%u: APIC id mismatch. Firmware: %x CPUID: %x\n", + cpu, apicid, c->initial_apicid); + c->initial_apicid = apicid; + } + if (pkg != c->phys_proc_id) { + pr_err(FW_BUG "CPU%u: Using firmware package id %u instead of %u\n", + cpu, pkg, c->phys_proc_id); + c->phys_proc_id = pkg; + } + c->logical_proc_id = topology_phys_to_logical_pkg(pkg); +#else + c->logical_proc_id = 0; +#endif +} + /* * This does the hard work of actually picking apart the CPU stuff... */ @@ -1103,8 +1132,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) #ifdef CONFIG_NUMA numa_add_cpu(smp_processor_id()); #endif - /* The boot/hotplug time assigment got cleared, restore it */ - c->logical_proc_id = topology_phys_to_logical_pkg(c->phys_proc_id); + sanitize_package_id(c); } /* diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 25810b144b58..4da03030d5a7 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -156,6 +156,16 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, } +static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int irq_source_id, int level, + bool line_status) +{ + if (!level) + return -1; + + return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint); +} + int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status) @@ -163,18 +173,26 @@ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, struct kvm_lapic_irq irq; int r; - if (unlikely(e->type != KVM_IRQ_ROUTING_MSI)) - return -EWOULDBLOCK; + switch (e->type) { + case KVM_IRQ_ROUTING_HV_SINT: + return kvm_hv_set_sint(e, kvm, irq_source_id, level, + line_status); - if (kvm_msi_route_invalid(kvm, e)) - return -EINVAL; + case KVM_IRQ_ROUTING_MSI: + if (kvm_msi_route_invalid(kvm, e)) + return -EINVAL; - kvm_set_msi_irq(kvm, e, &irq); + kvm_set_msi_irq(kvm, e, &irq); - if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL)) - return r; - else - return -EWOULDBLOCK; + if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL)) + return r; + break; + + default: + break; + } + + return -EWOULDBLOCK; } int kvm_request_irq_source_id(struct kvm *kvm) @@ -254,16 +272,6 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin, srcu_read_unlock(&kvm->irq_srcu, idx); } -static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int irq_source_id, int level, - bool line_status) -{ - if (!level) - return -1; - - return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint); -} - int kvm_set_routing_entry(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue) @@ -423,18 +431,6 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, srcu_read_unlock(&kvm->irq_srcu, idx); } -int kvm_arch_set_irq(struct kvm_kernel_irq_routing_entry *irq, struct kvm *kvm, - int irq_source_id, int level, bool line_status) -{ - switch (irq->type) { - case KVM_IRQ_ROUTING_HV_SINT: - return kvm_hv_set_sint(irq, kvm, irq_source_id, level, - line_status); - default: - return -EWOULDBLOCK; - } -} - void kvm_arch_irq_routing_update(struct kvm *kvm) { kvm_hv_irq_routing_update(kvm); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3017de0431bd..04c5d96b1d67 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -210,7 +210,18 @@ static void kvm_on_user_return(struct user_return_notifier *urn) struct kvm_shared_msrs *locals = container_of(urn, struct kvm_shared_msrs, urn); struct kvm_shared_msr_values *values; + unsigned long flags; + /* + * Disabling irqs at this point since the following code could be + * interrupted and executed through kvm_arch_hardware_disable() + */ + local_irq_save(flags); + if (locals->registered) { + locals->registered = false; + user_return_notifier_unregister(urn); + } + local_irq_restore(flags); for (slot = 0; slot < shared_msrs_global.nr; ++slot) { values = &locals->values[slot]; if (values->host != values->curr) { @@ -218,8 +229,6 @@ static void kvm_on_user_return(struct user_return_notifier *urn) values->curr = values->host; } } - locals->registered = false; - user_return_notifier_unregister(urn); } static void shared_msr_update(unsigned slot, u32 msr) @@ -1724,18 +1733,23 @@ static void kvm_gen_update_masterclock(struct kvm *kvm) static u64 __get_kvmclock_ns(struct kvm *kvm) { - struct kvm_vcpu *vcpu = kvm_get_vcpu(kvm, 0); struct kvm_arch *ka = &kvm->arch; - s64 ns; + struct pvclock_vcpu_time_info hv_clock; - if (vcpu->arch.hv_clock.flags & PVCLOCK_TSC_STABLE_BIT) { - u64 tsc = kvm_read_l1_tsc(vcpu, rdtsc()); - ns = __pvclock_read_cycles(&vcpu->arch.hv_clock, tsc); - } else { - ns = ktime_get_boot_ns() + ka->kvmclock_offset; + spin_lock(&ka->pvclock_gtod_sync_lock); + if (!ka->use_master_clock) { + spin_unlock(&ka->pvclock_gtod_sync_lock); + return ktime_get_boot_ns() + ka->kvmclock_offset; } - return ns; + hv_clock.tsc_timestamp = ka->master_cycle_now; + hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset; + spin_unlock(&ka->pvclock_gtod_sync_lock); + + kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL, + &hv_clock.tsc_shift, + &hv_clock.tsc_to_system_mul); + return __pvclock_read_cycles(&hv_clock, rdtsc()); } u64 get_kvmclock_ns(struct kvm *kvm) @@ -2596,7 +2610,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_PIT_STATE2: case KVM_CAP_SET_IDENTITY_MAP_ADDR: case KVM_CAP_XEN_HVM: - case KVM_CAP_ADJUST_CLOCK: case KVM_CAP_VCPU_EVENTS: case KVM_CAP_HYPERV: case KVM_CAP_HYPERV_VAPIC: @@ -2623,6 +2636,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) #endif r = 1; break; + case KVM_CAP_ADJUST_CLOCK: + r = KVM_CLOCK_TSC_STABLE; + break; case KVM_CAP_X86_SMM: /* SMBASE is usually relocated above 1M on modern chipsets, * and SMM handlers might indeed rely on 4G segment limits, @@ -3415,6 +3431,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, }; case KVM_SET_VAPIC_ADDR: { struct kvm_vapic_addr va; + int idx; r = -EINVAL; if (!lapic_in_kernel(vcpu)) @@ -3422,7 +3439,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&va, argp, sizeof va)) goto out; + idx = srcu_read_lock(&vcpu->kvm->srcu); r = kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr); + srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } case KVM_X86_SETUP_MCE: { @@ -4103,9 +4122,11 @@ long kvm_arch_vm_ioctl(struct file *filp, struct kvm_clock_data user_ns; u64 now_ns; - now_ns = get_kvmclock_ns(kvm); + local_irq_disable(); + now_ns = __get_kvmclock_ns(kvm); user_ns.clock = now_ns; - user_ns.flags = 0; + user_ns.flags = kvm->arch.use_master_clock ? KVM_CLOCK_TSC_STABLE : 0; + local_irq_enable(); memset(&user_ns.pad, 0, sizeof(user_ns.pad)); r = -EFAULT; diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index bf99aa7005eb..936a488d6cf6 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -861,7 +861,7 @@ static void __init __efi_enter_virtual_mode(void) int count = 0, pg_shift = 0; void *new_memmap = NULL; efi_status_t status; - phys_addr_t pa; + unsigned long pa; efi.systab = NULL; diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 58b0f801f66f..319148bd4b05 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include @@ -211,6 +212,35 @@ void efi_sync_low_kernel_mappings(void) memcpy(pud_efi, pud_k, sizeof(pud_t) * num_entries); } +/* + * Wrapper for slow_virt_to_phys() that handles NULL addresses. + */ +static inline phys_addr_t +virt_to_phys_or_null_size(void *va, unsigned long size) +{ + bool bad_size; + + if (!va) + return 0; + + if (virt_addr_valid(va)) + return virt_to_phys(va); + + /* + * A fully aligned variable on the stack is guaranteed not to + * cross a page bounary. Try to catch strings on the stack by + * checking that 'size' is a power of two. + */ + bad_size = size > PAGE_SIZE || !is_power_of_2(size); + + WARN_ON(!IS_ALIGNED((unsigned long)va, size) || bad_size); + + return slow_virt_to_phys(va); +} + +#define virt_to_phys_or_null(addr) \ + virt_to_phys_or_null_size((addr), sizeof(*(addr))) + int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) { unsigned long pfn, text; @@ -494,8 +524,8 @@ static efi_status_t efi_thunk_get_time(efi_time_t *tm, efi_time_cap_t *tc) spin_lock(&rtc_lock); - phys_tm = virt_to_phys(tm); - phys_tc = virt_to_phys(tc); + phys_tm = virt_to_phys_or_null(tm); + phys_tc = virt_to_phys_or_null(tc); status = efi_thunk(get_time, phys_tm, phys_tc); @@ -511,7 +541,7 @@ static efi_status_t efi_thunk_set_time(efi_time_t *tm) spin_lock(&rtc_lock); - phys_tm = virt_to_phys(tm); + phys_tm = virt_to_phys_or_null(tm); status = efi_thunk(set_time, phys_tm); @@ -529,9 +559,9 @@ efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending, spin_lock(&rtc_lock); - phys_enabled = virt_to_phys(enabled); - phys_pending = virt_to_phys(pending); - phys_tm = virt_to_phys(tm); + phys_enabled = virt_to_phys_or_null(enabled); + phys_pending = virt_to_phys_or_null(pending); + phys_tm = virt_to_phys_or_null(tm); status = efi_thunk(get_wakeup_time, phys_enabled, phys_pending, phys_tm); @@ -549,7 +579,7 @@ efi_thunk_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) spin_lock(&rtc_lock); - phys_tm = virt_to_phys(tm); + phys_tm = virt_to_phys_or_null(tm); status = efi_thunk(set_wakeup_time, enabled, phys_tm); @@ -558,6 +588,10 @@ efi_thunk_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) return status; } +static unsigned long efi_name_size(efi_char16_t *name) +{ + return ucs2_strsize(name, EFI_VAR_NAME_LEN) + 1; +} static efi_status_t efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor, @@ -567,11 +601,11 @@ efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor, u32 phys_name, phys_vendor, phys_attr; u32 phys_data_size, phys_data; - phys_data_size = virt_to_phys(data_size); - phys_vendor = virt_to_phys(vendor); - phys_name = virt_to_phys(name); - phys_attr = virt_to_phys(attr); - phys_data = virt_to_phys(data); + phys_data_size = virt_to_phys_or_null(data_size); + phys_vendor = virt_to_phys_or_null(vendor); + phys_name = virt_to_phys_or_null_size(name, efi_name_size(name)); + phys_attr = virt_to_phys_or_null(attr); + phys_data = virt_to_phys_or_null_size(data, *data_size); status = efi_thunk(get_variable, phys_name, phys_vendor, phys_attr, phys_data_size, phys_data); @@ -586,9 +620,9 @@ efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor, u32 phys_name, phys_vendor, phys_data; efi_status_t status; - phys_name = virt_to_phys(name); - phys_vendor = virt_to_phys(vendor); - phys_data = virt_to_phys(data); + phys_name = virt_to_phys_or_null_size(name, efi_name_size(name)); + phys_vendor = virt_to_phys_or_null(vendor); + phys_data = virt_to_phys_or_null_size(data, data_size); /* If data_size is > sizeof(u32) we've got problems */ status = efi_thunk(set_variable, phys_name, phys_vendor, @@ -605,9 +639,9 @@ efi_thunk_get_next_variable(unsigned long *name_size, efi_status_t status; u32 phys_name_size, phys_name, phys_vendor; - phys_name_size = virt_to_phys(name_size); - phys_vendor = virt_to_phys(vendor); - phys_name = virt_to_phys(name); + phys_name_size = virt_to_phys_or_null(name_size); + phys_vendor = virt_to_phys_or_null(vendor); + phys_name = virt_to_phys_or_null_size(name, *name_size); status = efi_thunk(get_next_variable, phys_name_size, phys_name, phys_vendor); @@ -621,7 +655,7 @@ efi_thunk_get_next_high_mono_count(u32 *count) efi_status_t status; u32 phys_count; - phys_count = virt_to_phys(count); + phys_count = virt_to_phys_or_null(count); status = efi_thunk(get_next_high_mono_count, phys_count); return status; @@ -633,7 +667,7 @@ efi_thunk_reset_system(int reset_type, efi_status_t status, { u32 phys_data; - phys_data = virt_to_phys(data); + phys_data = virt_to_phys_or_null_size(data, data_size); efi_thunk(reset_system, reset_type, status, data_size, phys_data); } @@ -661,9 +695,9 @@ efi_thunk_query_variable_info(u32 attr, u64 *storage_space, if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION) return EFI_UNSUPPORTED; - phys_storage = virt_to_phys(storage_space); - phys_remaining = virt_to_phys(remaining_space); - phys_max = virt_to_phys(max_variable_size); + phys_storage = virt_to_phys_or_null(storage_space); + phys_remaining = virt_to_phys_or_null(remaining_space); + phys_max = virt_to_phys_or_null(max_variable_size); status = efi_thunk(query_variable_info, attr, phys_storage, phys_remaining, phys_max); diff --git a/arch/x86/platform/intel-mid/pwr.c b/arch/x86/platform/intel-mid/pwr.c index 5d3b45ad1c03..67375dda451c 100644 --- a/arch/x86/platform/intel-mid/pwr.c +++ b/arch/x86/platform/intel-mid/pwr.c @@ -272,6 +272,25 @@ int intel_mid_pci_set_power_state(struct pci_dev *pdev, pci_power_t state) } EXPORT_SYMBOL_GPL(intel_mid_pci_set_power_state); +pci_power_t intel_mid_pci_get_power_state(struct pci_dev *pdev) +{ + struct mid_pwr *pwr = midpwr; + int id, reg, bit; + u32 power; + + if (!pwr || !pwr->available) + return PCI_UNKNOWN; + + id = intel_mid_pwr_get_lss_id(pdev); + if (id < 0) + return PCI_UNKNOWN; + + reg = (id * LSS_PWS_BITS) / 32; + bit = (id * LSS_PWS_BITS) % 32; + power = mid_pwr_get_state(pwr, reg); + return (__force pci_power_t)((power >> bit) & 3); +} + void intel_mid_pwr_power_off(void) { struct mid_pwr *pwr = midpwr; diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index ac58c1616408..555b9fa0ad43 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -16,6 +16,7 @@ KCOV_INSTRUMENT := n KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes -fno-zero-initialized-in-bss -fno-builtin -ffreestanding -c -MD -Os -mcmodel=large KBUILD_CFLAGS += -m$(BITS) +KBUILD_CFLAGS += $(call cc-option,-fno-PIE) $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE $(call if_changed,ld) diff --git a/arch/xtensa/include/uapi/asm/unistd.h b/arch/xtensa/include/uapi/asm/unistd.h index de9b14b2d348..cd400af4a6b2 100644 --- a/arch/xtensa/include/uapi/asm/unistd.h +++ b/arch/xtensa/include/uapi/asm/unistd.h @@ -767,7 +767,14 @@ __SYSCALL(346, sys_preadv2, 6) #define __NR_pwritev2 347 __SYSCALL(347, sys_pwritev2, 6) -#define __NR_syscall_count 348 +#define __NR_pkey_mprotect 348 +__SYSCALL(348, sys_pkey_mprotect, 4) +#define __NR_pkey_alloc 349 +__SYSCALL(349, sys_pkey_alloc, 2) +#define __NR_pkey_free 350 +__SYSCALL(350, sys_pkey_free, 1) + +#define __NR_syscall_count 351 /* * sysxtensa syscall handler diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c index 9a5bcd0381a7..be81e69b25bc 100644 --- a/arch/xtensa/kernel/time.c +++ b/arch/xtensa/kernel/time.c @@ -172,10 +172,11 @@ void __init time_init(void) { of_clk_init(NULL); #ifdef CONFIG_XTENSA_CALIBRATE_CCOUNT - printk("Calibrating CPU frequency "); + pr_info("Calibrating CPU frequency "); calibrate_ccount(); - printk("%d.%02d MHz\n", (int)ccount_freq/1000000, - (int)(ccount_freq/10000)%100); + pr_cont("%d.%02d MHz\n", + (int)ccount_freq / 1000000, + (int)(ccount_freq / 10000) % 100); #else ccount_freq = CONFIG_XTENSA_CPU_CLOCK*1000000UL; #endif @@ -210,9 +211,8 @@ irqreturn_t timer_interrupt(int irq, void *dev_id) void calibrate_delay(void) { loops_per_jiffy = ccount_freq / HZ; - printk("Calibrating delay loop (skipped)... " - "%lu.%02lu BogoMIPS preset\n", - loops_per_jiffy/(1000000/HZ), - (loops_per_jiffy/(10000/HZ)) % 100); + pr_info("Calibrating delay loop (skipped)... %lu.%02lu BogoMIPS preset\n", + loops_per_jiffy / (1000000 / HZ), + (loops_per_jiffy / (10000 / HZ)) % 100); } #endif diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c index d02fc304b31c..ce37d5b899fe 100644 --- a/arch/xtensa/kernel/traps.c +++ b/arch/xtensa/kernel/traps.c @@ -465,26 +465,25 @@ void show_regs(struct pt_regs * regs) for (i = 0; i < 16; i++) { if ((i % 8) == 0) - printk(KERN_INFO "a%02d:", i); - printk(KERN_CONT " %08lx", regs->areg[i]); + pr_info("a%02d:", i); + pr_cont(" %08lx", regs->areg[i]); } - printk(KERN_CONT "\n"); - - printk("pc: %08lx, ps: %08lx, depc: %08lx, excvaddr: %08lx\n", - regs->pc, regs->ps, regs->depc, regs->excvaddr); - printk("lbeg: %08lx, lend: %08lx lcount: %08lx, sar: %08lx\n", - regs->lbeg, regs->lend, regs->lcount, regs->sar); + pr_cont("\n"); + pr_info("pc: %08lx, ps: %08lx, depc: %08lx, excvaddr: %08lx\n", + regs->pc, regs->ps, regs->depc, regs->excvaddr); + pr_info("lbeg: %08lx, lend: %08lx lcount: %08lx, sar: %08lx\n", + regs->lbeg, regs->lend, regs->lcount, regs->sar); if (user_mode(regs)) - printk("wb: %08lx, ws: %08lx, wmask: %08lx, syscall: %ld\n", - regs->windowbase, regs->windowstart, regs->wmask, - regs->syscall); + pr_cont("wb: %08lx, ws: %08lx, wmask: %08lx, syscall: %ld\n", + regs->windowbase, regs->windowstart, regs->wmask, + regs->syscall); } static int show_trace_cb(struct stackframe *frame, void *data) { if (kernel_text_address(frame->pc)) { - printk(" [<%08lx>] ", frame->pc); - print_symbol("%s\n", frame->pc); + pr_cont(" [<%08lx>]", frame->pc); + print_symbol(" %s\n", frame->pc); } return 0; } @@ -494,19 +493,13 @@ void show_trace(struct task_struct *task, unsigned long *sp) if (!sp) sp = stack_pointer(task); - printk("Call Trace:"); -#ifdef CONFIG_KALLSYMS - printk("\n"); -#endif + pr_info("Call Trace:\n"); walk_stackframe(sp, show_trace_cb, NULL); - printk("\n"); +#ifndef CONFIG_KALLSYMS + pr_cont("\n"); +#endif } -/* - * This routine abuses get_user()/put_user() to reference pointers - * with at least a bit of error checking ... - */ - static int kstack_depth_to_print = 24; void show_stack(struct task_struct *task, unsigned long *sp) @@ -518,52 +511,29 @@ void show_stack(struct task_struct *task, unsigned long *sp) sp = stack_pointer(task); stack = sp; - printk("\nStack: "); + pr_info("Stack:\n"); for (i = 0; i < kstack_depth_to_print; i++) { if (kstack_end(sp)) break; - if (i && ((i % 8) == 0)) - printk("\n "); - printk("%08lx ", *sp++); + pr_cont(" %08lx", *sp++); + if (i % 8 == 7) + pr_cont("\n"); } - printk("\n"); show_trace(task, stack); } -void show_code(unsigned int *pc) -{ - long i; - - printk("\nCode:"); - - for(i = -3 ; i < 6 ; i++) { - unsigned long insn; - if (__get_user(insn, pc + i)) { - printk(" (Bad address in pc)\n"); - break; - } - printk("%c%08lx%c",(i?' ':'<'),insn,(i?' ':'>')); - } -} - DEFINE_SPINLOCK(die_lock); void die(const char * str, struct pt_regs * regs, long err) { static int die_counter; - int nl = 0; console_verbose(); spin_lock_irq(&die_lock); - printk("%s: sig: %ld [#%d]\n", str, err, ++die_counter); -#ifdef CONFIG_PREEMPT - printk("PREEMPT "); - nl = 1; -#endif - if (nl) - printk("\n"); + pr_info("%s: sig: %ld [#%d]%s\n", str, err, ++die_counter, + IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : ""); show_regs(regs); if (!user_mode(regs)) show_stack(NULL, (unsigned long*)regs->areg[1]); diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c index 2d8466f9e49b..05e21b464433 100644 --- a/crypto/algif_hash.c +++ b/crypto/algif_hash.c @@ -214,23 +214,26 @@ static int hash_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, ahash_request_set_crypt(&ctx->req, NULL, ctx->result, 0); - if (ctx->more) { + if (!result) { + err = af_alg_wait_for_completion( + crypto_ahash_init(&ctx->req), + &ctx->completion); + if (err) + goto unlock; + } + + if (!result || ctx->more) { ctx->more = 0; err = af_alg_wait_for_completion(crypto_ahash_final(&ctx->req), &ctx->completion); if (err) goto unlock; - } else if (!result) { - err = af_alg_wait_for_completion( - crypto_ahash_digest(&ctx->req), - &ctx->completion); } err = memcpy_to_msg(msg, ctx->result, len); - hash_free_result(sk, ctx); - unlock: + hash_free_result(sk, ctx); release_sock(sk); return err ?: len; diff --git a/drivers/acpi/acpica/tbfadt.c b/drivers/acpi/acpica/tbfadt.c index 046c4d0394ee..5fb838e592dc 100644 --- a/drivers/acpi/acpica/tbfadt.c +++ b/drivers/acpi/acpica/tbfadt.c @@ -480,19 +480,17 @@ static void acpi_tb_convert_fadt(void) u32 i; /* - * For ACPI 1.0 FADTs (revision 1), ensure that reserved fields which + * For ACPI 1.0 FADTs (revision 1 or 2), ensure that reserved fields which * should be zero are indeed zero. This will workaround BIOSs that * inadvertently place values in these fields. * * The ACPI 1.0 reserved fields that will be zeroed are the bytes located * at offset 45, 55, 95, and the word located at offset 109, 110. * - * Note: The FADT revision value is unreliable because of BIOS errors. - * The table length is instead used as the final word on the version. - * - * Note: FADT revision 3 is the ACPI 2.0 version of the FADT. + * Note: The FADT revision value is unreliable. Only the length can be + * trusted. */ - if (acpi_gbl_FADT.header.length <= ACPI_FADT_V3_SIZE) { + if (acpi_gbl_FADT.header.length <= ACPI_FADT_V2_SIZE) { acpi_gbl_FADT.preferred_profile = 0; acpi_gbl_FADT.pstate_control = 0; acpi_gbl_FADT.cst_control = 0; diff --git a/drivers/char/ipmi/bt-bmc.c b/drivers/char/ipmi/bt-bmc.c index b49e61320952..fc9e8891eae3 100644 --- a/drivers/char/ipmi/bt-bmc.c +++ b/drivers/char/ipmi/bt-bmc.c @@ -484,7 +484,7 @@ static int bt_bmc_remove(struct platform_device *pdev) } static const struct of_device_id bt_bmc_match[] = { - { .compatible = "aspeed,ast2400-bt-bmc" }, + { .compatible = "aspeed,ast2400-ibt-bmc" }, { }, }; @@ -502,4 +502,4 @@ module_platform_driver(bt_bmc_driver); MODULE_DEVICE_TABLE(of, bt_bmc_match); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Alistair Popple "); -MODULE_DESCRIPTION("Linux device interface to the BT interface"); +MODULE_DESCRIPTION("Linux device interface to the IPMI BT interface"); diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c index 156aad167cd6..954a64c7757b 100644 --- a/drivers/crypto/caam/caamalg.c +++ b/drivers/crypto/caam/caamalg.c @@ -137,7 +137,7 @@ static void dbg_dump_sg(const char *level, const char *prefix_str, } buf = it_page + it->offset; - len = min(tlen, it->length); + len = min_t(size_t, tlen, it->length); print_hex_dump(level, prefix_str, prefix_type, rowsize, groupsize, buf, len, ascii); tlen -= len; @@ -4583,6 +4583,15 @@ static int __init caam_algapi_init(void) if (!aes_inst && (alg_sel == OP_ALG_ALGSEL_AES)) continue; + /* + * Check support for AES modes not available + * on LP devices. + */ + if ((cha_vid & CHA_ID_LS_AES_MASK) == CHA_ID_LS_AES_LP) + if ((alg->class1_alg_type & OP_ALG_AAI_MASK) == + OP_ALG_AAI_XTS) + continue; + t_alg = caam_alg_alloc(alg); if (IS_ERR(t_alg)) { err = PTR_ERR(t_alg); diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index af63a6bcf564..141aefbe37ec 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -306,6 +306,7 @@ config MMP_TDMA depends on ARCH_MMP || COMPILE_TEST select DMA_ENGINE select MMP_SRAM if ARCH_MMP + select GENERIC_ALLOCATOR help Support the MMP Two-Channel DMA engine. This engine used for MMP Audio DMA and pxa910 SQU. diff --git a/drivers/dma/cppi41.c b/drivers/dma/cppi41.c index bac5f023013b..d5ba43a87a68 100644 --- a/drivers/dma/cppi41.c +++ b/drivers/dma/cppi41.c @@ -317,6 +317,12 @@ static irqreturn_t cppi41_irq(int irq, void *data) while (val) { u32 desc, len; + int error; + + error = pm_runtime_get(cdd->ddev.dev); + if (error < 0) + dev_err(cdd->ddev.dev, "%s pm runtime get: %i\n", + __func__, error); q_num = __fls(val); val &= ~(1 << q_num); @@ -338,7 +344,6 @@ static irqreturn_t cppi41_irq(int irq, void *data) dma_cookie_complete(&c->txd); dmaengine_desc_get_callback_invoke(&c->txd, NULL); - /* Paired with cppi41_dma_issue_pending */ pm_runtime_mark_last_busy(cdd->ddev.dev); pm_runtime_put_autosuspend(cdd->ddev.dev); } @@ -362,8 +367,13 @@ static int cppi41_dma_alloc_chan_resources(struct dma_chan *chan) int error; error = pm_runtime_get_sync(cdd->ddev.dev); - if (error < 0) + if (error < 0) { + dev_err(cdd->ddev.dev, "%s pm runtime get: %i\n", + __func__, error); + pm_runtime_put_noidle(cdd->ddev.dev); + return error; + } dma_cookie_init(chan); dma_async_tx_descriptor_init(&c->txd, chan); @@ -385,8 +395,11 @@ static void cppi41_dma_free_chan_resources(struct dma_chan *chan) int error; error = pm_runtime_get_sync(cdd->ddev.dev); - if (error < 0) + if (error < 0) { + pm_runtime_put_noidle(cdd->ddev.dev); + return; + } WARN_ON(!list_empty(&cdd->pending)); @@ -460,9 +473,9 @@ static void cppi41_dma_issue_pending(struct dma_chan *chan) struct cppi41_dd *cdd = c->cdd; int error; - /* PM runtime paired with dmaengine_desc_get_callback_invoke */ error = pm_runtime_get(cdd->ddev.dev); if ((error != -EINPROGRESS) && error < 0) { + pm_runtime_put_noidle(cdd->ddev.dev); dev_err(cdd->ddev.dev, "Failed to pm_runtime_get: %i\n", error); @@ -473,6 +486,9 @@ static void cppi41_dma_issue_pending(struct dma_chan *chan) push_desc_queue(c); else pending_desc(c); + + pm_runtime_mark_last_busy(cdd->ddev.dev); + pm_runtime_put_autosuspend(cdd->ddev.dev); } static u32 get_host_pd0(u32 length) @@ -1059,8 +1075,8 @@ err_chans: deinit_cppi41(dev, cdd); err_init_cppi: pm_runtime_dont_use_autosuspend(dev); - pm_runtime_put_sync(dev); err_get_sync: + pm_runtime_put_sync(dev); pm_runtime_disable(dev); iounmap(cdd->usbss_mem); iounmap(cdd->ctrl_mem); @@ -1072,7 +1088,12 @@ err_get_sync: static int cppi41_dma_remove(struct platform_device *pdev) { struct cppi41_dd *cdd = platform_get_drvdata(pdev); + int error; + error = pm_runtime_get_sync(&pdev->dev); + if (error < 0) + dev_err(&pdev->dev, "%s could not pm_runtime_get: %i\n", + __func__, error); of_dma_controller_free(pdev->dev.of_node); dma_async_device_unregister(&cdd->ddev); diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c index e18a58068bca..77242b37ef87 100644 --- a/drivers/dma/edma.c +++ b/drivers/dma/edma.c @@ -1628,6 +1628,7 @@ static int edma_alloc_chan_resources(struct dma_chan *chan) if (echan->slot[0] < 0) { dev_err(dev, "Entry slot allocation failed for channel %u\n", EDMA_CHAN_SLOT(echan->ch_num)); + ret = echan->slot[0]; goto err_slot; } diff --git a/drivers/dma/sun6i-dma.c b/drivers/dma/sun6i-dma.c index 83461994e418..a2358780ab2c 100644 --- a/drivers/dma/sun6i-dma.c +++ b/drivers/dma/sun6i-dma.c @@ -578,7 +578,7 @@ static struct dma_async_tx_descriptor *sun6i_dma_prep_dma_memcpy( burst = convert_burst(8); width = convert_buswidth(DMA_SLAVE_BUSWIDTH_4_BYTES); - v_lli->cfg |= DMA_CHAN_CFG_SRC_DRQ(DRQ_SDRAM) | + v_lli->cfg = DMA_CHAN_CFG_SRC_DRQ(DRQ_SDRAM) | DMA_CHAN_CFG_DST_DRQ(DRQ_SDRAM) | DMA_CHAN_CFG_DST_LINEAR_MODE | DMA_CHAN_CFG_SRC_LINEAR_MODE | diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index d011cb89d25e..ed37e5908b91 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -22,10 +22,6 @@ menuconfig GPIOLIB if GPIOLIB -config GPIO_DEVRES - def_bool y - depends on HAS_IOMEM - config OF_GPIO def_bool y depends on OF diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile index ab28a2daeacc..d074c2299393 100644 --- a/drivers/gpio/Makefile +++ b/drivers/gpio/Makefile @@ -2,7 +2,7 @@ ccflags-$(CONFIG_DEBUG_GPIO) += -DDEBUG -obj-$(CONFIG_GPIO_DEVRES) += devres.o +obj-$(CONFIG_GPIOLIB) += devres.o obj-$(CONFIG_GPIOLIB) += gpiolib.o obj-$(CONFIG_GPIOLIB) += gpiolib-legacy.o obj-$(CONFIG_OF_GPIO) += gpiolib-of.o diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index e422568e14ad..fe731f094257 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -372,14 +372,15 @@ static void pca953x_gpio_set_multiple(struct gpio_chip *gc, bank_shift = fls((chip->gpio_chip.ngpio - 1) / BANK_SZ); - memcpy(reg_val, chip->reg_output, NBANK(chip)); mutex_lock(&chip->i2c_lock); + memcpy(reg_val, chip->reg_output, NBANK(chip)); for (bank = 0; bank < NBANK(chip); bank++) { bank_mask = mask[bank / sizeof(*mask)] >> ((bank % sizeof(*mask)) * 8); if (bank_mask) { bank_val = bits[bank / sizeof(*bits)] >> ((bank % sizeof(*bits)) * 8); + bank_val &= bank_mask; reg_val[bank] = (reg_val[bank] & ~bank_mask) | bank_val; } } @@ -607,7 +608,6 @@ static int pca953x_irq_setup(struct pca953x_chip *chip, if (client->irq && irq_base != -1 && (chip->driver_data & PCA_INT)) { - ret = pca953x_read_regs(chip, chip->regs->input, chip->irq_stat); if (ret) diff --git a/drivers/gpio/gpio-tc3589x.c b/drivers/gpio/gpio-tc3589x.c index 5a5a6cb00eea..d6e21f1a70a9 100644 --- a/drivers/gpio/gpio-tc3589x.c +++ b/drivers/gpio/gpio-tc3589x.c @@ -97,7 +97,7 @@ static int tc3589x_gpio_get_direction(struct gpio_chip *chip, if (ret < 0) return ret; - return !!(ret & BIT(pos)); + return !(ret & BIT(pos)); } static int tc3589x_gpio_set_single_ended(struct gpio_chip *chip, diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 93ed0e00c578..868128a676ba 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -2737,8 +2737,11 @@ int gpiochip_lock_as_irq(struct gpio_chip *chip, unsigned int offset) if (IS_ERR(desc)) return PTR_ERR(desc); - /* Flush direction if something changed behind our back */ - if (chip->get_direction) { + /* + * If it's fast: flush the direction setting if something changed + * behind our back + */ + if (!chip->can_sleep && chip->get_direction) { int dir = chip->get_direction(chip, offset); if (dir) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 039b57e4644c..496f72b134eb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -459,6 +459,7 @@ struct amdgpu_bo { u64 metadata_flags; void *metadata; u32 metadata_size; + unsigned prime_shared_count; /* list of all virtual address to which this bo * is associated to */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c index 651115dcce12..c02db01f6583 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c @@ -132,7 +132,7 @@ static int amdgpu_bo_list_set(struct amdgpu_device *adev, entry->priority = min(info[i].bo_priority, AMDGPU_BO_LIST_MAX_PRIORITY); entry->tv.bo = &entry->robj->tbo; - entry->tv.shared = true; + entry->tv.shared = !entry->robj->prime_shared_count; if (entry->robj->prefered_domains == AMDGPU_GEM_DOMAIN_GDS) gds_obj = entry->robj; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 7ca07e7b25c1..3161d77bf299 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -658,12 +658,10 @@ static bool amdgpu_vpost_needed(struct amdgpu_device *adev) return false; if (amdgpu_passthrough(adev)) { - /* for FIJI: In whole GPU pass-through virtualization case - * old smc fw won't clear some registers (e.g. MEM_SIZE, BIOS_SCRATCH) - * so amdgpu_card_posted return false and driver will incorrectly skip vPost. - * but if we force vPost do in pass-through case, the driver reload will hang. - * whether doing vPost depends on amdgpu_card_posted if smc version is above - * 00160e00 for FIJI. + /* for FIJI: In whole GPU pass-through virtualization case, after VM reboot + * some old smc fw still need driver do vPost otherwise gpu hang, while + * those smc fw version above 22.15 doesn't have this flaw, so we force + * vpost executed for smc version below 22.15 */ if (adev->asic_type == CHIP_FIJI) { int err; @@ -674,22 +672,11 @@ static bool amdgpu_vpost_needed(struct amdgpu_device *adev) return true; fw_ver = *((uint32_t *)adev->pm.fw->data + 69); - if (fw_ver >= 0x00160e00) - return !amdgpu_card_posted(adev); + if (fw_ver < 0x00160e00) + return true; } - } else { - /* in bare-metal case, amdgpu_card_posted return false - * after system reboot/boot, and return true if driver - * reloaded. - * we shouldn't do vPost after driver reload otherwise GPU - * could hang. - */ - if (amdgpu_card_posted(adev)) - return false; } - - /* we assume vPost is neede for all other cases */ - return true; + return !amdgpu_card_posted(adev); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c index 7700dc22f243..3826d5aea0a6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c @@ -74,20 +74,36 @@ amdgpu_gem_prime_import_sg_table(struct drm_device *dev, if (ret) return ERR_PTR(ret); + bo->prime_shared_count = 1; return &bo->gem_base; } int amdgpu_gem_prime_pin(struct drm_gem_object *obj) { struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); - int ret = 0; + long ret = 0; ret = amdgpu_bo_reserve(bo, false); if (unlikely(ret != 0)) return ret; + /* + * Wait for all shared fences to complete before we switch to future + * use of exclusive fence on this prime shared bo. + */ + ret = reservation_object_wait_timeout_rcu(bo->tbo.resv, true, false, + MAX_SCHEDULE_TIMEOUT); + if (unlikely(ret < 0)) { + DRM_DEBUG_PRIME("Fence wait failed: %li\n", ret); + amdgpu_bo_unreserve(bo); + return ret; + } + /* pin buffer into GTT */ ret = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT, NULL); + if (likely(ret == 0)) + bo->prime_shared_count++; + amdgpu_bo_unreserve(bo); return ret; } @@ -102,6 +118,8 @@ void amdgpu_gem_prime_unpin(struct drm_gem_object *obj) return; amdgpu_bo_unpin(bo); + if (bo->prime_shared_count) + bo->prime_shared_count--; amdgpu_bo_unreserve(bo); } diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c index b0c929dd8beb..13f2b705ea49 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c @@ -1469,8 +1469,6 @@ static int smu7_get_evv_voltages(struct pp_hwmgr *hwmgr) table_info->vddgfx_lookup_table, vv_id, &sclk)) { if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_ClockStretcher)) { - if (table_info == NULL) - return -EINVAL; sclk_table = table_info->vdd_dep_on_sclk; for (j = 1; j < sclk_table->count; j++) { diff --git a/drivers/gpu/drm/arc/arcpgu_hdmi.c b/drivers/gpu/drm/arc/arcpgu_hdmi.c index b7a8b2ac4055..b69c66b4897e 100644 --- a/drivers/gpu/drm/arc/arcpgu_hdmi.c +++ b/drivers/gpu/drm/arc/arcpgu_hdmi.c @@ -14,170 +14,45 @@ * */ -#include +#include #include -#include #include "arcpgu.h" -struct arcpgu_drm_connector { - struct drm_connector connector; - struct drm_encoder_slave *encoder_slave; -}; - -static int arcpgu_drm_connector_get_modes(struct drm_connector *connector) -{ - const struct drm_encoder_slave_funcs *sfuncs; - struct drm_encoder_slave *slave; - struct arcpgu_drm_connector *con = - container_of(connector, struct arcpgu_drm_connector, connector); - - slave = con->encoder_slave; - if (slave == NULL) { - dev_err(connector->dev->dev, - "connector_get_modes: cannot find slave encoder for connector\n"); - return 0; - } - - sfuncs = slave->slave_funcs; - if (sfuncs->get_modes == NULL) - return 0; - - return sfuncs->get_modes(&slave->base, connector); -} - -static enum drm_connector_status -arcpgu_drm_connector_detect(struct drm_connector *connector, bool force) -{ - enum drm_connector_status status = connector_status_unknown; - const struct drm_encoder_slave_funcs *sfuncs; - struct drm_encoder_slave *slave; - - struct arcpgu_drm_connector *con = - container_of(connector, struct arcpgu_drm_connector, connector); - - slave = con->encoder_slave; - if (slave == NULL) { - dev_err(connector->dev->dev, - "connector_detect: cannot find slave encoder for connector\n"); - return status; - } - - sfuncs = slave->slave_funcs; - if (sfuncs && sfuncs->detect) - return sfuncs->detect(&slave->base, connector); - - dev_err(connector->dev->dev, "connector_detect: could not detect slave funcs\n"); - return status; -} - -static void arcpgu_drm_connector_destroy(struct drm_connector *connector) -{ - drm_connector_unregister(connector); - drm_connector_cleanup(connector); -} - -static const struct drm_connector_helper_funcs -arcpgu_drm_connector_helper_funcs = { - .get_modes = arcpgu_drm_connector_get_modes, -}; - -static const struct drm_connector_funcs arcpgu_drm_connector_funcs = { - .dpms = drm_helper_connector_dpms, - .reset = drm_atomic_helper_connector_reset, - .detect = arcpgu_drm_connector_detect, - .fill_modes = drm_helper_probe_single_connector_modes, - .destroy = arcpgu_drm_connector_destroy, - .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, - .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, -}; - -static struct drm_encoder_helper_funcs arcpgu_drm_encoder_helper_funcs = { - .dpms = drm_i2c_encoder_dpms, - .mode_fixup = drm_i2c_encoder_mode_fixup, - .mode_set = drm_i2c_encoder_mode_set, - .prepare = drm_i2c_encoder_prepare, - .commit = drm_i2c_encoder_commit, - .detect = drm_i2c_encoder_detect, -}; - static struct drm_encoder_funcs arcpgu_drm_encoder_funcs = { .destroy = drm_encoder_cleanup, }; int arcpgu_drm_hdmi_init(struct drm_device *drm, struct device_node *np) { - struct arcpgu_drm_connector *arcpgu_connector; - struct drm_i2c_encoder_driver *driver; - struct drm_encoder_slave *encoder; - struct drm_connector *connector; - struct i2c_client *i2c_slave; - int ret; + struct drm_encoder *encoder; + struct drm_bridge *bridge; + + int ret = 0; encoder = devm_kzalloc(drm->dev, sizeof(*encoder), GFP_KERNEL); if (encoder == NULL) return -ENOMEM; - i2c_slave = of_find_i2c_device_by_node(np); - if (!i2c_slave || !i2c_get_clientdata(i2c_slave)) { - dev_err(drm->dev, "failed to find i2c slave encoder\n"); + /* Locate drm bridge from the hdmi encoder DT node */ + bridge = of_drm_find_bridge(np); + if (!bridge) return -EPROBE_DEFER; - } - if (i2c_slave->dev.driver == NULL) { - dev_err(drm->dev, "failed to find i2c slave driver\n"); - return -EPROBE_DEFER; - } - - driver = - to_drm_i2c_encoder_driver(to_i2c_driver(i2c_slave->dev.driver)); - ret = driver->encoder_init(i2c_slave, drm, encoder); - if (ret) { - dev_err(drm->dev, "failed to initialize i2c encoder slave\n"); - return ret; - } - - encoder->base.possible_crtcs = 1; - encoder->base.possible_clones = 0; - ret = drm_encoder_init(drm, &encoder->base, &arcpgu_drm_encoder_funcs, + encoder->possible_crtcs = 1; + encoder->possible_clones = 0; + ret = drm_encoder_init(drm, encoder, &arcpgu_drm_encoder_funcs, DRM_MODE_ENCODER_TMDS, NULL); if (ret) return ret; - drm_encoder_helper_add(&encoder->base, - &arcpgu_drm_encoder_helper_funcs); + /* Link drm_bridge to encoder */ + bridge->encoder = encoder; + encoder->bridge = bridge; - arcpgu_connector = devm_kzalloc(drm->dev, sizeof(*arcpgu_connector), - GFP_KERNEL); - if (!arcpgu_connector) { - ret = -ENOMEM; - goto error_encoder_cleanup; - } + ret = drm_bridge_attach(drm, bridge); + if (ret) + drm_encoder_cleanup(encoder); - connector = &arcpgu_connector->connector; - drm_connector_helper_add(connector, &arcpgu_drm_connector_helper_funcs); - ret = drm_connector_init(drm, connector, &arcpgu_drm_connector_funcs, - DRM_MODE_CONNECTOR_HDMIA); - if (ret < 0) { - dev_err(drm->dev, "failed to initialize drm connector\n"); - goto error_encoder_cleanup; - } - - ret = drm_mode_connector_attach_encoder(connector, &encoder->base); - if (ret < 0) { - dev_err(drm->dev, "could not attach connector to encoder\n"); - drm_connector_unregister(connector); - goto error_connector_cleanup; - } - - arcpgu_connector->encoder_slave = encoder; - - return 0; - -error_connector_cleanup: - drm_connector_cleanup(connector); - -error_encoder_cleanup: - drm_encoder_cleanup(&encoder->base); return ret; } diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_crtc.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_crtc.c index b2d5e188b1b8..deb57435cc89 100644 --- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_crtc.c +++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_crtc.c @@ -25,8 +25,13 @@ static void fsl_dcu_drm_crtc_atomic_flush(struct drm_crtc *crtc, struct drm_crtc_state *old_crtc_state) { + struct drm_device *dev = crtc->dev; + struct fsl_dcu_drm_device *fsl_dev = dev->dev_private; struct drm_pending_vblank_event *event = crtc->state->event; + regmap_write(fsl_dev->regmap, + DCU_UPDATE_MODE, DCU_UPDATE_MODE_READREG); + if (event) { crtc->state->event = NULL; @@ -39,11 +44,15 @@ static void fsl_dcu_drm_crtc_atomic_flush(struct drm_crtc *crtc, } } -static void fsl_dcu_drm_disable_crtc(struct drm_crtc *crtc) +static void fsl_dcu_drm_crtc_atomic_disable(struct drm_crtc *crtc, + struct drm_crtc_state *old_crtc_state) { struct drm_device *dev = crtc->dev; struct fsl_dcu_drm_device *fsl_dev = dev->dev_private; + /* always disable planes on the CRTC */ + drm_atomic_helper_disable_planes_on_crtc(old_crtc_state, true); + drm_crtc_vblank_off(crtc); regmap_update_bits(fsl_dev->regmap, DCU_DCU_MODE, @@ -122,8 +131,8 @@ static void fsl_dcu_drm_crtc_mode_set_nofb(struct drm_crtc *crtc) } static const struct drm_crtc_helper_funcs fsl_dcu_drm_crtc_helper_funcs = { + .atomic_disable = fsl_dcu_drm_crtc_atomic_disable, .atomic_flush = fsl_dcu_drm_crtc_atomic_flush, - .disable = fsl_dcu_drm_disable_crtc, .enable = fsl_dcu_drm_crtc_enable, .mode_set_nofb = fsl_dcu_drm_crtc_mode_set_nofb, }; diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c index e04efbed1a54..cc2fde2ae5ef 100644 --- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c +++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c @@ -59,8 +59,6 @@ static int fsl_dcu_drm_irq_init(struct drm_device *dev) regmap_write(fsl_dev->regmap, DCU_INT_STATUS, 0); regmap_write(fsl_dev->regmap, DCU_INT_MASK, ~0); - regmap_write(fsl_dev->regmap, DCU_UPDATE_MODE, - DCU_UPDATE_MODE_READREG); return ret; } @@ -139,8 +137,6 @@ static irqreturn_t fsl_dcu_drm_irq(int irq, void *arg) drm_handle_vblank(dev, 0); regmap_write(fsl_dev->regmap, DCU_INT_STATUS, int_status); - regmap_write(fsl_dev->regmap, DCU_UPDATE_MODE, - DCU_UPDATE_MODE_READREG); return IRQ_HANDLED; } diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c index 9e6f7d8112b3..a99f48847420 100644 --- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c +++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c @@ -160,11 +160,6 @@ static void fsl_dcu_drm_plane_atomic_update(struct drm_plane *plane, DCU_LAYER_POST_SKIP(0) | DCU_LAYER_PRE_SKIP(0)); } - regmap_update_bits(fsl_dev->regmap, DCU_DCU_MODE, - DCU_MODE_DCU_MODE_MASK, - DCU_MODE_DCU_MODE(DCU_MODE_NORMAL)); - regmap_write(fsl_dev->regmap, - DCU_UPDATE_MODE, DCU_UPDATE_MODE_READREG); return; } diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 7adb4c77cc7f..a218c2e395e7 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -1281,6 +1281,12 @@ i915_gem_validate_context(struct drm_device *dev, struct drm_file *file, return ctx; } +static bool gpu_write_needs_clflush(struct drm_i915_gem_object *obj) +{ + return !(obj->cache_level == I915_CACHE_NONE || + obj->cache_level == I915_CACHE_WT); +} + void i915_vma_move_to_active(struct i915_vma *vma, struct drm_i915_gem_request *req, unsigned int flags) @@ -1311,6 +1317,8 @@ void i915_vma_move_to_active(struct i915_vma *vma, /* update for the implicit flush after a batch */ obj->base.write_domain &= ~I915_GEM_GPU_DOMAINS; + if (!obj->cache_dirty && gpu_write_needs_clflush(obj)) + obj->cache_dirty = true; } if (flags & EXEC_OBJECT_NEEDS_FENCE) diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index 1f8af87c6294..cf2560708e03 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -1143,7 +1143,7 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port, if (!child) return; - aux_channel = child->raw[25]; + aux_channel = child->common.aux_channel; ddc_pin = child->common.ddc_pin; is_dvi = child->common.device_type & DEVICE_TYPE_TMDS_DVI_SIGNALING; @@ -1673,7 +1673,8 @@ bool intel_bios_is_port_edp(struct drm_i915_private *dev_priv, enum port port) return false; } -bool intel_bios_is_port_dp_dual_mode(struct drm_i915_private *dev_priv, enum port port) +static bool child_dev_is_dp_dual_mode(const union child_device_config *p_child, + enum port port) { static const struct { u16 dp, hdmi; @@ -1687,22 +1688,35 @@ bool intel_bios_is_port_dp_dual_mode(struct drm_i915_private *dev_priv, enum por [PORT_D] = { DVO_PORT_DPD, DVO_PORT_HDMID, }, [PORT_E] = { DVO_PORT_DPE, DVO_PORT_HDMIE, }, }; - int i; if (port == PORT_A || port >= ARRAY_SIZE(port_mapping)) return false; - if (!dev_priv->vbt.child_dev_num) + if ((p_child->common.device_type & DEVICE_TYPE_DP_DUAL_MODE_BITS) != + (DEVICE_TYPE_DP_DUAL_MODE & DEVICE_TYPE_DP_DUAL_MODE_BITS)) return false; + if (p_child->common.dvo_port == port_mapping[port].dp) + return true; + + /* Only accept a HDMI dvo_port as DP++ if it has an AUX channel */ + if (p_child->common.dvo_port == port_mapping[port].hdmi && + p_child->common.aux_channel != 0) + return true; + + return false; +} + +bool intel_bios_is_port_dp_dual_mode(struct drm_i915_private *dev_priv, + enum port port) +{ + int i; + for (i = 0; i < dev_priv->vbt.child_dev_num; i++) { const union child_device_config *p_child = &dev_priv->vbt.child_dev[i]; - if ((p_child->common.dvo_port == port_mapping[port].dp || - p_child->common.dvo_port == port_mapping[port].hdmi) && - (p_child->common.device_type & DEVICE_TYPE_DP_DUAL_MODE_BITS) == - (DEVICE_TYPE_DP_DUAL_MODE & DEVICE_TYPE_DP_DUAL_MODE_BITS)) + if (child_dev_is_dp_dual_mode(p_child, port)) return true; } diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 3581b5a7f716..bf344d08356a 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -4463,21 +4463,11 @@ static enum drm_connector_status intel_dp_detect(struct drm_connector *connector, bool force) { struct intel_dp *intel_dp = intel_attached_dp(connector); - struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp); - struct intel_encoder *intel_encoder = &intel_dig_port->base; enum drm_connector_status status = connector->status; DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", connector->base.id, connector->name); - if (intel_dp->is_mst) { - /* MST devices are disconnected from a monitor POV */ - intel_dp_unset_edid(intel_dp); - if (intel_encoder->type != INTEL_OUTPUT_EDP) - intel_encoder->type = INTEL_OUTPUT_DP; - return connector_status_disconnected; - } - /* If full detect is not performed yet, do a full detect */ if (!intel_dp->detect_done) status = intel_dp_long_pulse(intel_dp->attached_connector); diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index 73a521fdf1bd..dbed12c484c9 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -358,7 +358,7 @@ vlv_update_plane(struct drm_plane *dplane, int plane = intel_plane->plane; u32 sprctl; u32 sprsurf_offset, linear_offset; - unsigned int rotation = dplane->state->rotation; + unsigned int rotation = plane_state->base.rotation; const struct drm_intel_sprite_colorkey *key = &plane_state->ckey; int crtc_x = plane_state->base.dst.x1; int crtc_y = plane_state->base.dst.y1; diff --git a/drivers/gpu/drm/i915/intel_vbt_defs.h b/drivers/gpu/drm/i915/intel_vbt_defs.h index 68db9621f1f0..8886cab19f98 100644 --- a/drivers/gpu/drm/i915/intel_vbt_defs.h +++ b/drivers/gpu/drm/i915/intel_vbt_defs.h @@ -280,7 +280,8 @@ struct common_child_dev_config { u8 dp_support:1; u8 tmds_support:1; u8 support_reserved:5; - u8 not_common3[12]; + u8 aux_channel; + u8 not_common3[11]; u8 iboost_level; } __packed; diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c index 019b7ca392d7..f75c5b5a536c 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c @@ -80,6 +80,7 @@ static void mtk_ovl_enable_vblank(struct mtk_ddp_comp *comp, ddp_comp); priv->crtc = crtc; + writel(0x0, comp->regs + DISP_REG_OVL_INTSTA); writel_relaxed(OVL_FME_CPL_INT, comp->regs + DISP_REG_OVL_INTEN); } diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c index 0186e500d2a5..90fb831ef031 100644 --- a/drivers/gpu/drm/mediatek/mtk_dpi.c +++ b/drivers/gpu/drm/mediatek/mtk_dpi.c @@ -432,11 +432,16 @@ static int mtk_dpi_set_display_mode(struct mtk_dpi *dpi, unsigned long pll_rate; unsigned int factor; + /* let pll_rate can fix the valid range of tvdpll (1G~2GHz) */ pix_rate = 1000UL * mode->clock; - if (mode->clock <= 74000) + if (mode->clock <= 27000) + factor = 16 * 3; + else if (mode->clock <= 84000) factor = 8 * 3; - else + else if (mode->clock <= 167000) factor = 4 * 3; + else + factor = 2 * 3; pll_rate = pix_rate * factor; dev_dbg(dpi->dev, "Want PLL %lu Hz, pixel clock %lu Hz\n", diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c index 71227deef21b..0e8c4d9af340 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c @@ -1133,12 +1133,6 @@ static int mtk_hdmi_output_set_display_mode(struct mtk_hdmi *hdmi, phy_power_on(hdmi->phy); mtk_hdmi_aud_output_config(hdmi, mode); - mtk_hdmi_setup_audio_infoframe(hdmi); - mtk_hdmi_setup_avi_infoframe(hdmi, mode); - mtk_hdmi_setup_spd_infoframe(hdmi, "mediatek", "On-chip HDMI"); - if (mode->flags & DRM_MODE_FLAG_3D_MASK) - mtk_hdmi_setup_vendor_specific_infoframe(hdmi, mode); - mtk_hdmi_hw_vid_black(hdmi, false); mtk_hdmi_hw_aud_unmute(hdmi); mtk_hdmi_hw_send_av_unmute(hdmi); @@ -1401,6 +1395,16 @@ static void mtk_hdmi_bridge_pre_enable(struct drm_bridge *bridge) hdmi->powered = true; } +static void mtk_hdmi_send_infoframe(struct mtk_hdmi *hdmi, + struct drm_display_mode *mode) +{ + mtk_hdmi_setup_audio_infoframe(hdmi); + mtk_hdmi_setup_avi_infoframe(hdmi, mode); + mtk_hdmi_setup_spd_infoframe(hdmi, "mediatek", "On-chip HDMI"); + if (mode->flags & DRM_MODE_FLAG_3D_MASK) + mtk_hdmi_setup_vendor_specific_infoframe(hdmi, mode); +} + static void mtk_hdmi_bridge_enable(struct drm_bridge *bridge) { struct mtk_hdmi *hdmi = hdmi_ctx_from_bridge(bridge); @@ -1409,6 +1413,7 @@ static void mtk_hdmi_bridge_enable(struct drm_bridge *bridge) clk_prepare_enable(hdmi->clk[MTK_HDMI_CLK_HDMI_PLL]); clk_prepare_enable(hdmi->clk[MTK_HDMI_CLK_HDMI_PIXEL]); phy_power_on(hdmi->phy); + mtk_hdmi_send_infoframe(hdmi, &hdmi->mode); hdmi->enabled = true; } diff --git a/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c b/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c index 8a24754b440f..51cb9cfb6646 100644 --- a/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c +++ b/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c @@ -265,6 +265,9 @@ static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate, struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw); unsigned int pre_div; unsigned int div; + unsigned int pre_ibias; + unsigned int hdmi_ibias; + unsigned int imp_en; dev_dbg(hdmi_phy->dev, "%s: %lu Hz, parent: %lu Hz\n", __func__, rate, parent_rate); @@ -298,18 +301,31 @@ static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate, (0x1 << PLL_BR_SHIFT), RG_HDMITX_PLL_BP | RG_HDMITX_PLL_BC | RG_HDMITX_PLL_BR); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON3, RG_HDMITX_PRD_IMP_EN); + if (rate < 165000000) { + mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON3, + RG_HDMITX_PRD_IMP_EN); + pre_ibias = 0x3; + imp_en = 0x0; + hdmi_ibias = hdmi_phy->ibias; + } else { + mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON3, + RG_HDMITX_PRD_IMP_EN); + pre_ibias = 0x6; + imp_en = 0xf; + hdmi_ibias = hdmi_phy->ibias_up; + } mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON4, - (0x3 << PRD_IBIAS_CLK_SHIFT) | - (0x3 << PRD_IBIAS_D2_SHIFT) | - (0x3 << PRD_IBIAS_D1_SHIFT) | - (0x3 << PRD_IBIAS_D0_SHIFT), + (pre_ibias << PRD_IBIAS_CLK_SHIFT) | + (pre_ibias << PRD_IBIAS_D2_SHIFT) | + (pre_ibias << PRD_IBIAS_D1_SHIFT) | + (pre_ibias << PRD_IBIAS_D0_SHIFT), RG_HDMITX_PRD_IBIAS_CLK | RG_HDMITX_PRD_IBIAS_D2 | RG_HDMITX_PRD_IBIAS_D1 | RG_HDMITX_PRD_IBIAS_D0); mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON3, - (0x0 << DRV_IMP_EN_SHIFT), RG_HDMITX_DRV_IMP_EN); + (imp_en << DRV_IMP_EN_SHIFT), + RG_HDMITX_DRV_IMP_EN); mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON6, (hdmi_phy->drv_imp_clk << DRV_IMP_CLK_SHIFT) | (hdmi_phy->drv_imp_d2 << DRV_IMP_D2_SHIFT) | @@ -318,12 +334,14 @@ static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate, RG_HDMITX_DRV_IMP_CLK | RG_HDMITX_DRV_IMP_D2 | RG_HDMITX_DRV_IMP_D1 | RG_HDMITX_DRV_IMP_D0); mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON5, - (hdmi_phy->ibias << DRV_IBIAS_CLK_SHIFT) | - (hdmi_phy->ibias << DRV_IBIAS_D2_SHIFT) | - (hdmi_phy->ibias << DRV_IBIAS_D1_SHIFT) | - (hdmi_phy->ibias << DRV_IBIAS_D0_SHIFT), - RG_HDMITX_DRV_IBIAS_CLK | RG_HDMITX_DRV_IBIAS_D2 | - RG_HDMITX_DRV_IBIAS_D1 | RG_HDMITX_DRV_IBIAS_D0); + (hdmi_ibias << DRV_IBIAS_CLK_SHIFT) | + (hdmi_ibias << DRV_IBIAS_D2_SHIFT) | + (hdmi_ibias << DRV_IBIAS_D1_SHIFT) | + (hdmi_ibias << DRV_IBIAS_D0_SHIFT), + RG_HDMITX_DRV_IBIAS_CLK | + RG_HDMITX_DRV_IBIAS_D2 | + RG_HDMITX_DRV_IBIAS_D1 | + RG_HDMITX_DRV_IBIAS_D0); return 0; } diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c index 0da9862ad8ed..70e9fd59c5a2 100644 --- a/drivers/gpu/drm/sun4i/sun4i_drv.c +++ b/drivers/gpu/drm/sun4i/sun4i_drv.c @@ -142,9 +142,9 @@ static int sun4i_drv_bind(struct device *dev) /* Create our layers */ drv->layers = sun4i_layers_init(drm); - if (!drv->layers) { + if (IS_ERR(drv->layers)) { dev_err(drm->dev, "Couldn't create the planes\n"); - ret = -EINVAL; + ret = PTR_ERR(drv->layers); goto free_drm; } diff --git a/drivers/gpu/drm/sun4i/sun4i_rgb.c b/drivers/gpu/drm/sun4i/sun4i_rgb.c index c3ff10f559cc..d198ad7e5323 100644 --- a/drivers/gpu/drm/sun4i/sun4i_rgb.c +++ b/drivers/gpu/drm/sun4i/sun4i_rgb.c @@ -152,15 +152,13 @@ static void sun4i_rgb_encoder_enable(struct drm_encoder *encoder) DRM_DEBUG_DRIVER("Enabling RGB output\n"); - if (!IS_ERR(tcon->panel)) { + if (!IS_ERR(tcon->panel)) drm_panel_prepare(tcon->panel); - drm_panel_enable(tcon->panel); - } - - /* encoder->bridge can be NULL; drm_bridge_enable checks for it */ - drm_bridge_enable(encoder->bridge); sun4i_tcon_channel_enable(tcon, 0); + + if (!IS_ERR(tcon->panel)) + drm_panel_enable(tcon->panel); } static void sun4i_rgb_encoder_disable(struct drm_encoder *encoder) @@ -171,15 +169,13 @@ static void sun4i_rgb_encoder_disable(struct drm_encoder *encoder) DRM_DEBUG_DRIVER("Disabling RGB output\n"); + if (!IS_ERR(tcon->panel)) + drm_panel_disable(tcon->panel); + sun4i_tcon_channel_disable(tcon, 0); - /* encoder->bridge can be NULL; drm_bridge_disable checks for it */ - drm_bridge_disable(encoder->bridge); - - if (!IS_ERR(tcon->panel)) { - drm_panel_disable(tcon->panel); + if (!IS_ERR(tcon->panel)) drm_panel_unprepare(tcon->panel); - } } static void sun4i_rgb_encoder_mode_set(struct drm_encoder *encoder, diff --git a/drivers/i2c/Kconfig b/drivers/i2c/Kconfig index d223650a97e4..11edabf425ae 100644 --- a/drivers/i2c/Kconfig +++ b/drivers/i2c/Kconfig @@ -59,7 +59,6 @@ config I2C_CHARDEV config I2C_MUX tristate "I2C bus multiplexing support" - depends on HAS_IOMEM help Say Y here if you want the I2C core to support the ability to handle multiplexed I2C bus topologies, by presenting each diff --git a/drivers/i2c/busses/i2c-digicolor.c b/drivers/i2c/busses/i2c-digicolor.c index 49f2084f7bb5..50813a24c541 100644 --- a/drivers/i2c/busses/i2c-digicolor.c +++ b/drivers/i2c/busses/i2c-digicolor.c @@ -347,7 +347,7 @@ static int dc_i2c_probe(struct platform_device *pdev) ret = i2c_add_adapter(&i2c->adap); if (ret < 0) { - clk_unprepare(i2c->clk); + clk_disable_unprepare(i2c->clk); return ret; } diff --git a/drivers/i2c/muxes/Kconfig b/drivers/i2c/muxes/Kconfig index e280c8ecc0b5..96de9ce5669b 100644 --- a/drivers/i2c/muxes/Kconfig +++ b/drivers/i2c/muxes/Kconfig @@ -63,6 +63,7 @@ config I2C_MUX_PINCTRL config I2C_MUX_REG tristate "Register-based I2C multiplexer" + depends on HAS_IOMEM help If you say yes to this option, support will be included for a register based I2C multiplexer. This driver provides access to diff --git a/drivers/i2c/muxes/i2c-demux-pinctrl.c b/drivers/i2c/muxes/i2c-demux-pinctrl.c index b3893f6282ba..3e6fe1760d82 100644 --- a/drivers/i2c/muxes/i2c-demux-pinctrl.c +++ b/drivers/i2c/muxes/i2c-demux-pinctrl.c @@ -69,10 +69,28 @@ static int i2c_demux_activate_master(struct i2c_demux_pinctrl_priv *priv, u32 ne goto err_with_revert; } - p = devm_pinctrl_get_select(adap->dev.parent, priv->bus_name); + /* + * Check if there are pinctrl states at all. Note: we cant' use + * devm_pinctrl_get_select() because we need to distinguish between + * the -ENODEV from devm_pinctrl_get() and pinctrl_lookup_state(). + */ + p = devm_pinctrl_get(adap->dev.parent); if (IS_ERR(p)) { ret = PTR_ERR(p); - goto err_with_put; + /* continue if just no pinctrl states (e.g. i2c-gpio), otherwise exit */ + if (ret != -ENODEV) + goto err_with_put; + } else { + /* there are states. check and use them */ + struct pinctrl_state *s = pinctrl_lookup_state(p, priv->bus_name); + + if (IS_ERR(s)) { + ret = PTR_ERR(s); + goto err_with_put; + } + ret = pinctrl_select_state(p, s); + if (ret < 0) + goto err_with_put; } priv->chan[new_chan].parent_adap = adap; diff --git a/drivers/i2c/muxes/i2c-mux-pca954x.c b/drivers/i2c/muxes/i2c-mux-pca954x.c index 1091346f2480..8bc3d36d2837 100644 --- a/drivers/i2c/muxes/i2c-mux-pca954x.c +++ b/drivers/i2c/muxes/i2c-mux-pca954x.c @@ -268,9 +268,9 @@ static int pca954x_probe(struct i2c_client *client, /* discard unconfigured channels */ break; idle_disconnect_pd = pdata->modes[num].deselect_on_exit; - data->deselect |= (idle_disconnect_pd - || idle_disconnect_dt) << num; } + data->deselect |= (idle_disconnect_pd || + idle_disconnect_dt) << num; ret = i2c_mux_add_adapter(muxc, force, num, class); diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index b136d3acc5bd..0f58f46dbad7 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -699,13 +699,16 @@ EXPORT_SYMBOL(rdma_addr_cancel); struct resolve_cb_context { struct rdma_dev_addr *addr; struct completion comp; + int status; }; static void resolve_cb(int status, struct sockaddr *src_addr, struct rdma_dev_addr *addr, void *context) { - memcpy(((struct resolve_cb_context *)context)->addr, addr, sizeof(struct - rdma_dev_addr)); + if (!status) + memcpy(((struct resolve_cb_context *)context)->addr, + addr, sizeof(struct rdma_dev_addr)); + ((struct resolve_cb_context *)context)->status = status; complete(&((struct resolve_cb_context *)context)->comp); } @@ -743,6 +746,10 @@ int rdma_addr_find_l2_eth_by_grh(const union ib_gid *sgid, wait_for_completion(&ctx.comp); + ret = ctx.status; + if (ret) + return ret; + memcpy(dmac, dev_addr.dst_dev_addr, ETH_ALEN); dev = dev_get_by_index(&init_net, dev_addr.bound_dev_if); if (!dev) diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index c99525512b34..71c7c4c328ef 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -80,6 +80,8 @@ static struct ib_cm { __be32 random_id_operand; struct list_head timewait_list; struct workqueue_struct *wq; + /* Sync on cm change port state */ + spinlock_t state_lock; } cm; /* Counter indexes ordered by attribute ID */ @@ -161,6 +163,8 @@ struct cm_port { struct ib_mad_agent *mad_agent; struct kobject port_obj; u8 port_num; + struct list_head cm_priv_prim_list; + struct list_head cm_priv_altr_list; struct cm_counter_group counter_group[CM_COUNTER_GROUPS]; }; @@ -241,6 +245,12 @@ struct cm_id_private { u8 service_timeout; u8 target_ack_delay; + struct list_head prim_list; + struct list_head altr_list; + /* Indicates that the send port mad is registered and av is set */ + int prim_send_port_not_ready; + int altr_send_port_not_ready; + struct list_head work_list; atomic_t work_count; }; @@ -259,20 +269,47 @@ static int cm_alloc_msg(struct cm_id_private *cm_id_priv, struct ib_mad_agent *mad_agent; struct ib_mad_send_buf *m; struct ib_ah *ah; + struct cm_av *av; + unsigned long flags, flags2; + int ret = 0; + /* don't let the port to be released till the agent is down */ + spin_lock_irqsave(&cm.state_lock, flags2); + spin_lock_irqsave(&cm.lock, flags); + if (!cm_id_priv->prim_send_port_not_ready) + av = &cm_id_priv->av; + else if (!cm_id_priv->altr_send_port_not_ready && + (cm_id_priv->alt_av.port)) + av = &cm_id_priv->alt_av; + else { + pr_info("%s: not valid CM id\n", __func__); + ret = -ENODEV; + spin_unlock_irqrestore(&cm.lock, flags); + goto out; + } + spin_unlock_irqrestore(&cm.lock, flags); + /* Make sure the port haven't released the mad yet */ mad_agent = cm_id_priv->av.port->mad_agent; - ah = ib_create_ah(mad_agent->qp->pd, &cm_id_priv->av.ah_attr); - if (IS_ERR(ah)) - return PTR_ERR(ah); + if (!mad_agent) { + pr_info("%s: not a valid MAD agent\n", __func__); + ret = -ENODEV; + goto out; + } + ah = ib_create_ah(mad_agent->qp->pd, &av->ah_attr); + if (IS_ERR(ah)) { + ret = PTR_ERR(ah); + goto out; + } m = ib_create_send_mad(mad_agent, cm_id_priv->id.remote_cm_qpn, - cm_id_priv->av.pkey_index, + av->pkey_index, 0, IB_MGMT_MAD_HDR, IB_MGMT_MAD_DATA, GFP_ATOMIC, IB_MGMT_BASE_VERSION); if (IS_ERR(m)) { ib_destroy_ah(ah); - return PTR_ERR(m); + ret = PTR_ERR(m); + goto out; } /* Timeout set by caller if response is expected. */ @@ -282,7 +319,10 @@ static int cm_alloc_msg(struct cm_id_private *cm_id_priv, atomic_inc(&cm_id_priv->refcount); m->context[0] = cm_id_priv; *msg = m; - return 0; + +out: + spin_unlock_irqrestore(&cm.state_lock, flags2); + return ret; } static int cm_alloc_response_msg(struct cm_port *port, @@ -352,7 +392,8 @@ static void cm_init_av_for_response(struct cm_port *port, struct ib_wc *wc, grh, &av->ah_attr); } -static int cm_init_av_by_path(struct ib_sa_path_rec *path, struct cm_av *av) +static int cm_init_av_by_path(struct ib_sa_path_rec *path, struct cm_av *av, + struct cm_id_private *cm_id_priv) { struct cm_device *cm_dev; struct cm_port *port = NULL; @@ -387,7 +428,17 @@ static int cm_init_av_by_path(struct ib_sa_path_rec *path, struct cm_av *av) &av->ah_attr); av->timeout = path->packet_life_time + 1; - return 0; + spin_lock_irqsave(&cm.lock, flags); + if (&cm_id_priv->av == av) + list_add_tail(&cm_id_priv->prim_list, &port->cm_priv_prim_list); + else if (&cm_id_priv->alt_av == av) + list_add_tail(&cm_id_priv->altr_list, &port->cm_priv_altr_list); + else + ret = -EINVAL; + + spin_unlock_irqrestore(&cm.lock, flags); + + return ret; } static int cm_alloc_id(struct cm_id_private *cm_id_priv) @@ -677,6 +728,8 @@ struct ib_cm_id *ib_create_cm_id(struct ib_device *device, spin_lock_init(&cm_id_priv->lock); init_completion(&cm_id_priv->comp); INIT_LIST_HEAD(&cm_id_priv->work_list); + INIT_LIST_HEAD(&cm_id_priv->prim_list); + INIT_LIST_HEAD(&cm_id_priv->altr_list); atomic_set(&cm_id_priv->work_count, -1); atomic_set(&cm_id_priv->refcount, 1); return &cm_id_priv->id; @@ -892,6 +945,15 @@ retest: break; } + spin_lock_irq(&cm.lock); + if (!list_empty(&cm_id_priv->altr_list) && + (!cm_id_priv->altr_send_port_not_ready)) + list_del(&cm_id_priv->altr_list); + if (!list_empty(&cm_id_priv->prim_list) && + (!cm_id_priv->prim_send_port_not_ready)) + list_del(&cm_id_priv->prim_list); + spin_unlock_irq(&cm.lock); + cm_free_id(cm_id->local_id); cm_deref_id(cm_id_priv); wait_for_completion(&cm_id_priv->comp); @@ -1192,12 +1254,13 @@ int ib_send_cm_req(struct ib_cm_id *cm_id, goto out; } - ret = cm_init_av_by_path(param->primary_path, &cm_id_priv->av); + ret = cm_init_av_by_path(param->primary_path, &cm_id_priv->av, + cm_id_priv); if (ret) goto error1; if (param->alternate_path) { ret = cm_init_av_by_path(param->alternate_path, - &cm_id_priv->alt_av); + &cm_id_priv->alt_av, cm_id_priv); if (ret) goto error1; } @@ -1653,7 +1716,8 @@ static int cm_req_handler(struct cm_work *work) dev_put(gid_attr.ndev); } work->path[0].gid_type = gid_attr.gid_type; - ret = cm_init_av_by_path(&work->path[0], &cm_id_priv->av); + ret = cm_init_av_by_path(&work->path[0], &cm_id_priv->av, + cm_id_priv); } if (ret) { int err = ib_get_cached_gid(work->port->cm_dev->ib_device, @@ -1672,7 +1736,8 @@ static int cm_req_handler(struct cm_work *work) goto rejected; } if (req_msg->alt_local_lid) { - ret = cm_init_av_by_path(&work->path[1], &cm_id_priv->alt_av); + ret = cm_init_av_by_path(&work->path[1], &cm_id_priv->alt_av, + cm_id_priv); if (ret) { ib_send_cm_rej(cm_id, IB_CM_REJ_INVALID_ALT_GID, &work->path[0].sgid, @@ -2727,7 +2792,8 @@ int ib_send_cm_lap(struct ib_cm_id *cm_id, goto out; } - ret = cm_init_av_by_path(alternate_path, &cm_id_priv->alt_av); + ret = cm_init_av_by_path(alternate_path, &cm_id_priv->alt_av, + cm_id_priv); if (ret) goto out; cm_id_priv->alt_av.timeout = @@ -2839,7 +2905,8 @@ static int cm_lap_handler(struct cm_work *work) cm_init_av_for_response(work->port, work->mad_recv_wc->wc, work->mad_recv_wc->recv_buf.grh, &cm_id_priv->av); - cm_init_av_by_path(param->alternate_path, &cm_id_priv->alt_av); + cm_init_av_by_path(param->alternate_path, &cm_id_priv->alt_av, + cm_id_priv); ret = atomic_inc_and_test(&cm_id_priv->work_count); if (!ret) list_add_tail(&work->list, &cm_id_priv->work_list); @@ -3031,7 +3098,7 @@ int ib_send_cm_sidr_req(struct ib_cm_id *cm_id, return -EINVAL; cm_id_priv = container_of(cm_id, struct cm_id_private, id); - ret = cm_init_av_by_path(param->path, &cm_id_priv->av); + ret = cm_init_av_by_path(param->path, &cm_id_priv->av, cm_id_priv); if (ret) goto out; @@ -3468,7 +3535,9 @@ out: static int cm_migrate(struct ib_cm_id *cm_id) { struct cm_id_private *cm_id_priv; + struct cm_av tmp_av; unsigned long flags; + int tmp_send_port_not_ready; int ret = 0; cm_id_priv = container_of(cm_id, struct cm_id_private, id); @@ -3477,7 +3546,14 @@ static int cm_migrate(struct ib_cm_id *cm_id) (cm_id->lap_state == IB_CM_LAP_UNINIT || cm_id->lap_state == IB_CM_LAP_IDLE)) { cm_id->lap_state = IB_CM_LAP_IDLE; + /* Swap address vector */ + tmp_av = cm_id_priv->av; cm_id_priv->av = cm_id_priv->alt_av; + cm_id_priv->alt_av = tmp_av; + /* Swap port send ready state */ + tmp_send_port_not_ready = cm_id_priv->prim_send_port_not_ready; + cm_id_priv->prim_send_port_not_ready = cm_id_priv->altr_send_port_not_ready; + cm_id_priv->altr_send_port_not_ready = tmp_send_port_not_ready; } else ret = -EINVAL; spin_unlock_irqrestore(&cm_id_priv->lock, flags); @@ -3888,6 +3964,9 @@ static void cm_add_one(struct ib_device *ib_device) port->cm_dev = cm_dev; port->port_num = i; + INIT_LIST_HEAD(&port->cm_priv_prim_list); + INIT_LIST_HEAD(&port->cm_priv_altr_list); + ret = cm_create_port_fs(port); if (ret) goto error1; @@ -3945,6 +4024,8 @@ static void cm_remove_one(struct ib_device *ib_device, void *client_data) { struct cm_device *cm_dev = client_data; struct cm_port *port; + struct cm_id_private *cm_id_priv; + struct ib_mad_agent *cur_mad_agent; struct ib_port_modify port_modify = { .clr_port_cap_mask = IB_PORT_CM_SUP }; @@ -3968,15 +4049,27 @@ static void cm_remove_one(struct ib_device *ib_device, void *client_data) port = cm_dev->port[i-1]; ib_modify_port(ib_device, port->port_num, 0, &port_modify); + /* Mark all the cm_id's as not valid */ + spin_lock_irq(&cm.lock); + list_for_each_entry(cm_id_priv, &port->cm_priv_altr_list, altr_list) + cm_id_priv->altr_send_port_not_ready = 1; + list_for_each_entry(cm_id_priv, &port->cm_priv_prim_list, prim_list) + cm_id_priv->prim_send_port_not_ready = 1; + spin_unlock_irq(&cm.lock); /* * We flush the queue here after the going_down set, this * verify that no new works will be queued in the recv handler, * after that we can call the unregister_mad_agent */ flush_workqueue(cm.wq); - ib_unregister_mad_agent(port->mad_agent); + spin_lock_irq(&cm.state_lock); + cur_mad_agent = port->mad_agent; + port->mad_agent = NULL; + spin_unlock_irq(&cm.state_lock); + ib_unregister_mad_agent(cur_mad_agent); cm_remove_port_fs(port); } + device_unregister(cm_dev->device); kfree(cm_dev); } @@ -3989,6 +4082,7 @@ static int __init ib_cm_init(void) INIT_LIST_HEAD(&cm.device_list); rwlock_init(&cm.device_lock); spin_lock_init(&cm.lock); + spin_lock_init(&cm.state_lock); cm.listen_service_table = RB_ROOT; cm.listen_service_id = be64_to_cpu(IB_CM_ASSIGN_SERVICE_ID); cm.remote_id_table = RB_ROOT; diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 89a6b0546804..2a6fc47a1dfb 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -2438,6 +2438,18 @@ static int iboe_tos_to_sl(struct net_device *ndev, int tos) return 0; } +static enum ib_gid_type cma_route_gid_type(enum rdma_network_type network_type, + unsigned long supported_gids, + enum ib_gid_type default_gid) +{ + if ((network_type == RDMA_NETWORK_IPV4 || + network_type == RDMA_NETWORK_IPV6) && + test_bit(IB_GID_TYPE_ROCE_UDP_ENCAP, &supported_gids)) + return IB_GID_TYPE_ROCE_UDP_ENCAP; + + return default_gid; +} + static int cma_resolve_iboe_route(struct rdma_id_private *id_priv) { struct rdma_route *route = &id_priv->id.route; @@ -2463,6 +2475,8 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv) route->num_paths = 1; if (addr->dev_addr.bound_dev_if) { + unsigned long supported_gids; + ndev = dev_get_by_index(&init_net, addr->dev_addr.bound_dev_if); if (!ndev) { ret = -ENODEV; @@ -2486,7 +2500,12 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv) route->path_rec->net = &init_net; route->path_rec->ifindex = ndev->ifindex; - route->path_rec->gid_type = id_priv->gid_type; + supported_gids = roce_gid_type_mask_support(id_priv->id.device, + id_priv->id.port_num); + route->path_rec->gid_type = + cma_route_gid_type(addr->dev_addr.network, + supported_gids, + id_priv->gid_type); } if (!ndev) { ret = -ENODEV; diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index 224ad274ea0b..84b4eff90395 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -175,7 +175,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, cur_base = addr & PAGE_MASK; - if (npages == 0) { + if (npages == 0 || npages > UINT_MAX) { ret = -EINVAL; goto out; } diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 0012fa58c105..44b1104eb168 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -262,12 +262,9 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file, container_of(uobj, struct ib_uqp_object, uevent.uobject); idr_remove_uobj(&ib_uverbs_qp_idr, uobj); - if (qp != qp->real_qp) { - ib_close_qp(qp); - } else { + if (qp == qp->real_qp) ib_uverbs_detach_umcast(qp, uqp); - ib_destroy_qp(qp); - } + ib_destroy_qp(qp); ib_uverbs_release_uevent(file, &uqp->uevent); kfree(uqp); } diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c index 867b8cf82be8..19c6477af19f 100644 --- a/drivers/infiniband/hw/cxgb4/cq.c +++ b/drivers/infiniband/hw/cxgb4/cq.c @@ -666,18 +666,6 @@ skip_cqe: return ret; } -static void invalidate_mr(struct c4iw_dev *rhp, u32 rkey) -{ - struct c4iw_mr *mhp; - unsigned long flags; - - spin_lock_irqsave(&rhp->lock, flags); - mhp = get_mhp(rhp, rkey >> 8); - if (mhp) - mhp->attr.state = 0; - spin_unlock_irqrestore(&rhp->lock, flags); -} - /* * Get one cq entry from c4iw and map it to openib. * @@ -733,7 +721,7 @@ static int c4iw_poll_cq_one(struct c4iw_cq *chp, struct ib_wc *wc) CQE_OPCODE(&cqe) == FW_RI_SEND_WITH_SE_INV) { wc->ex.invalidate_rkey = CQE_WRID_STAG(&cqe); wc->wc_flags |= IB_WC_WITH_INVALIDATE; - invalidate_mr(qhp->rhp, wc->ex.invalidate_rkey); + c4iw_invalidate_mr(qhp->rhp, wc->ex.invalidate_rkey); } } else { switch (CQE_OPCODE(&cqe)) { @@ -762,7 +750,8 @@ static int c4iw_poll_cq_one(struct c4iw_cq *chp, struct ib_wc *wc) /* Invalidate the MR if the fastreg failed */ if (CQE_STATUS(&cqe) != T4_ERR_SUCCESS) - invalidate_mr(qhp->rhp, CQE_WRID_FR_STAG(&cqe)); + c4iw_invalidate_mr(qhp->rhp, + CQE_WRID_FR_STAG(&cqe)); break; default: printk(KERN_ERR MOD "Unexpected opcode %d " diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h index 7e7f79e55006..4788e1a46fde 100644 --- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h +++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h @@ -999,6 +999,6 @@ extern int db_coalescing_threshold; extern int use_dsgl; void c4iw_drain_rq(struct ib_qp *qp); void c4iw_drain_sq(struct ib_qp *qp); - +void c4iw_invalidate_mr(struct c4iw_dev *rhp, u32 rkey); #endif diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c index 80e27749420a..410408f886c1 100644 --- a/drivers/infiniband/hw/cxgb4/mem.c +++ b/drivers/infiniband/hw/cxgb4/mem.c @@ -770,3 +770,15 @@ int c4iw_dereg_mr(struct ib_mr *ib_mr) kfree(mhp); return 0; } + +void c4iw_invalidate_mr(struct c4iw_dev *rhp, u32 rkey) +{ + struct c4iw_mr *mhp; + unsigned long flags; + + spin_lock_irqsave(&rhp->lock, flags); + mhp = get_mhp(rhp, rkey >> 8); + if (mhp) + mhp->attr.state = 0; + spin_unlock_irqrestore(&rhp->lock, flags); +} diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c index f57deba6717c..b7ac97b27c88 100644 --- a/drivers/infiniband/hw/cxgb4/qp.c +++ b/drivers/infiniband/hw/cxgb4/qp.c @@ -706,12 +706,8 @@ static int build_memreg(struct t4_sq *sq, union t4_wr *wqe, return 0; } -static int build_inv_stag(struct c4iw_dev *dev, union t4_wr *wqe, - struct ib_send_wr *wr, u8 *len16) +static int build_inv_stag(union t4_wr *wqe, struct ib_send_wr *wr, u8 *len16) { - struct c4iw_mr *mhp = get_mhp(dev, wr->ex.invalidate_rkey >> 8); - - mhp->attr.state = 0; wqe->inv.stag_inv = cpu_to_be32(wr->ex.invalidate_rkey); wqe->inv.r2 = 0; *len16 = DIV_ROUND_UP(sizeof wqe->inv, 16); @@ -797,11 +793,13 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, spin_lock_irqsave(&qhp->lock, flag); if (t4_wq_in_error(&qhp->wq)) { spin_unlock_irqrestore(&qhp->lock, flag); + *bad_wr = wr; return -EINVAL; } num_wrs = t4_sq_avail(&qhp->wq); if (num_wrs == 0) { spin_unlock_irqrestore(&qhp->lock, flag); + *bad_wr = wr; return -ENOMEM; } while (wr) { @@ -840,10 +838,13 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, case IB_WR_RDMA_READ_WITH_INV: fw_opcode = FW_RI_RDMA_READ_WR; swsqe->opcode = FW_RI_READ_REQ; - if (wr->opcode == IB_WR_RDMA_READ_WITH_INV) + if (wr->opcode == IB_WR_RDMA_READ_WITH_INV) { + c4iw_invalidate_mr(qhp->rhp, + wr->sg_list[0].lkey); fw_flags = FW_RI_RDMA_READ_INVALIDATE; - else + } else { fw_flags = 0; + } err = build_rdma_read(wqe, wr, &len16); if (err) break; @@ -876,7 +877,8 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, fw_flags |= FW_RI_LOCAL_FENCE_FLAG; fw_opcode = FW_RI_INV_LSTAG_WR; swsqe->opcode = FW_RI_LOCAL_INV; - err = build_inv_stag(qhp->rhp, wqe, wr, &len16); + err = build_inv_stag(wqe, wr, &len16); + c4iw_invalidate_mr(qhp->rhp, wr->ex.invalidate_rkey); break; default: PDBG("%s post of type=%d TBD!\n", __func__, @@ -934,11 +936,13 @@ int c4iw_post_receive(struct ib_qp *ibqp, struct ib_recv_wr *wr, spin_lock_irqsave(&qhp->lock, flag); if (t4_wq_in_error(&qhp->wq)) { spin_unlock_irqrestore(&qhp->lock, flag); + *bad_wr = wr; return -EINVAL; } num_wrs = t4_rq_avail(&qhp->wq); if (num_wrs == 0) { spin_unlock_irqrestore(&qhp->lock, flag); + *bad_wr = wr; return -ENOMEM; } while (wr) { diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c index a26a9a0bfc41..67ea85a56945 100644 --- a/drivers/infiniband/hw/hfi1/affinity.c +++ b/drivers/infiniband/hw/hfi1/affinity.c @@ -775,75 +775,3 @@ void hfi1_put_proc_affinity(int cpu) } mutex_unlock(&affinity->lock); } - -int hfi1_set_sdma_affinity(struct hfi1_devdata *dd, const char *buf, - size_t count) -{ - struct hfi1_affinity_node *entry; - cpumask_var_t mask; - int ret, i; - - mutex_lock(&node_affinity.lock); - entry = node_affinity_lookup(dd->node); - - if (!entry) { - ret = -EINVAL; - goto unlock; - } - - ret = zalloc_cpumask_var(&mask, GFP_KERNEL); - if (!ret) { - ret = -ENOMEM; - goto unlock; - } - - ret = cpulist_parse(buf, mask); - if (ret) - goto out; - - if (!cpumask_subset(mask, cpu_online_mask) || cpumask_empty(mask)) { - dd_dev_warn(dd, "Invalid CPU mask\n"); - ret = -EINVAL; - goto out; - } - - /* reset the SDMA interrupt affinity details */ - init_cpu_mask_set(&entry->def_intr); - cpumask_copy(&entry->def_intr.mask, mask); - - /* Reassign the affinity for each SDMA interrupt. */ - for (i = 0; i < dd->num_msix_entries; i++) { - struct hfi1_msix_entry *msix; - - msix = &dd->msix_entries[i]; - if (msix->type != IRQ_SDMA) - continue; - - ret = get_irq_affinity(dd, msix); - - if (ret) - break; - } -out: - free_cpumask_var(mask); -unlock: - mutex_unlock(&node_affinity.lock); - return ret ? ret : strnlen(buf, PAGE_SIZE); -} - -int hfi1_get_sdma_affinity(struct hfi1_devdata *dd, char *buf) -{ - struct hfi1_affinity_node *entry; - - mutex_lock(&node_affinity.lock); - entry = node_affinity_lookup(dd->node); - - if (!entry) { - mutex_unlock(&node_affinity.lock); - return -EINVAL; - } - - cpumap_print_to_pagebuf(true, buf, &entry->def_intr.mask); - mutex_unlock(&node_affinity.lock); - return strnlen(buf, PAGE_SIZE); -} diff --git a/drivers/infiniband/hw/hfi1/affinity.h b/drivers/infiniband/hw/hfi1/affinity.h index b89ea3c0ee1a..42e63316afd1 100644 --- a/drivers/infiniband/hw/hfi1/affinity.h +++ b/drivers/infiniband/hw/hfi1/affinity.h @@ -102,10 +102,6 @@ int hfi1_get_proc_affinity(int); /* Release a CPU used by a user process. */ void hfi1_put_proc_affinity(int); -int hfi1_get_sdma_affinity(struct hfi1_devdata *dd, char *buf); -int hfi1_set_sdma_affinity(struct hfi1_devdata *dd, const char *buf, - size_t count); - struct hfi1_affinity_node { int node; struct cpu_mask_set def_intr; diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 9bf5f23544d4..24d0820873cf 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -6301,19 +6301,8 @@ void set_up_vl15(struct hfi1_devdata *dd, u8 vau, u16 vl15buf) /* leave shared count at zero for both global and VL15 */ write_global_credit(dd, vau, vl15buf, 0); - /* We may need some credits for another VL when sending packets - * with the snoop interface. Dividing it down the middle for VL15 - * and VL0 should suffice. - */ - if (unlikely(dd->hfi1_snoop.mode_flag == HFI1_PORT_SNOOP_MODE)) { - write_csr(dd, SEND_CM_CREDIT_VL15, (u64)(vl15buf >> 1) - << SEND_CM_CREDIT_VL15_DEDICATED_LIMIT_VL_SHIFT); - write_csr(dd, SEND_CM_CREDIT_VL, (u64)(vl15buf >> 1) - << SEND_CM_CREDIT_VL_DEDICATED_LIMIT_VL_SHIFT); - } else { - write_csr(dd, SEND_CM_CREDIT_VL15, (u64)vl15buf - << SEND_CM_CREDIT_VL15_DEDICATED_LIMIT_VL_SHIFT); - } + write_csr(dd, SEND_CM_CREDIT_VL15, (u64)vl15buf + << SEND_CM_CREDIT_VL15_DEDICATED_LIMIT_VL_SHIFT); } /* @@ -9915,9 +9904,6 @@ static void set_lidlmc(struct hfi1_pportdata *ppd) u32 mask = ~((1U << ppd->lmc) - 1); u64 c1 = read_csr(ppd->dd, DCC_CFG_PORT_CONFIG1); - if (dd->hfi1_snoop.mode_flag) - dd_dev_info(dd, "Set lid/lmc while snooping"); - c1 &= ~(DCC_CFG_PORT_CONFIG1_TARGET_DLID_SMASK | DCC_CFG_PORT_CONFIG1_DLID_MASK_SMASK); c1 |= ((ppd->lid & DCC_CFG_PORT_CONFIG1_TARGET_DLID_MASK) @@ -12112,7 +12098,7 @@ static void update_synth_timer(unsigned long opaque) mod_timer(&dd->synth_stats_timer, jiffies + HZ * SYNTH_CNT_TIME); } -#define C_MAX_NAME 13 /* 12 chars + one for /0 */ +#define C_MAX_NAME 16 /* 15 chars + one for /0 */ static int init_cntrs(struct hfi1_devdata *dd) { int i, rcv_ctxts, j; @@ -14463,7 +14449,7 @@ struct hfi1_devdata *hfi1_init_dd(struct pci_dev *pdev, * Any error printing is already done by the init code. * On return, we have the chip mapped. */ - ret = hfi1_pcie_ddinit(dd, pdev, ent); + ret = hfi1_pcie_ddinit(dd, pdev); if (ret < 0) goto bail_free; @@ -14691,6 +14677,11 @@ struct hfi1_devdata *hfi1_init_dd(struct pci_dev *pdev, if (ret) goto bail_free_cntrs; + init_completion(&dd->user_comp); + + /* The user refcount starts with one to inidicate an active device */ + atomic_set(&dd->user_refcount, 1); + goto bail; bail_free_rcverr: diff --git a/drivers/infiniband/hw/hfi1/chip.h b/drivers/infiniband/hw/hfi1/chip.h index 92345259a8f4..043fd21dc5f3 100644 --- a/drivers/infiniband/hw/hfi1/chip.h +++ b/drivers/infiniband/hw/hfi1/chip.h @@ -320,6 +320,9 @@ /* DC_DC8051_CFG_MODE.GENERAL bits */ #define DISABLE_SELF_GUID_CHECK 0x2 +/* Bad L2 frame error code */ +#define BAD_L2_ERR 0x6 + /* * Eager buffer minimum and maximum sizes supported by the hardware. * All power-of-two sizes in between are supported as well. diff --git a/drivers/infiniband/hw/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c index 6563e4d38b80..c5efff29c147 100644 --- a/drivers/infiniband/hw/hfi1/driver.c +++ b/drivers/infiniband/hw/hfi1/driver.c @@ -599,7 +599,6 @@ static void __prescan_rxq(struct hfi1_packet *packet) dd->rhf_offset; struct rvt_qp *qp; struct ib_header *hdr; - struct ib_other_headers *ohdr; struct rvt_dev_info *rdi = &dd->verbs_dev.rdi; u64 rhf = rhf_to_cpu(rhf_addr); u32 etype = rhf_rcv_type(rhf), qpn, bth1; @@ -615,18 +614,21 @@ static void __prescan_rxq(struct hfi1_packet *packet) if (etype != RHF_RCV_TYPE_IB) goto next; - hdr = hfi1_get_msgheader(dd, rhf_addr); + packet->hdr = hfi1_get_msgheader(dd, rhf_addr); + hdr = packet->hdr; lnh = be16_to_cpu(hdr->lrh[0]) & 3; - if (lnh == HFI1_LRH_BTH) - ohdr = &hdr->u.oth; - else if (lnh == HFI1_LRH_GRH) - ohdr = &hdr->u.l.oth; - else + if (lnh == HFI1_LRH_BTH) { + packet->ohdr = &hdr->u.oth; + } else if (lnh == HFI1_LRH_GRH) { + packet->ohdr = &hdr->u.l.oth; + packet->rcv_flags |= HFI1_HAS_GRH; + } else { goto next; /* just in case */ + } - bth1 = be32_to_cpu(ohdr->bth[1]); + bth1 = be32_to_cpu(packet->ohdr->bth[1]); is_ecn = !!(bth1 & (HFI1_FECN_SMASK | HFI1_BECN_SMASK)); if (!is_ecn) @@ -646,7 +648,7 @@ static void __prescan_rxq(struct hfi1_packet *packet) /* turn off BECN, FECN */ bth1 &= ~(HFI1_FECN_SMASK | HFI1_BECN_SMASK); - ohdr->bth[1] = cpu_to_be32(bth1); + packet->ohdr->bth[1] = cpu_to_be32(bth1); next: update_ps_mdata(&mdata, rcd); } @@ -1360,12 +1362,25 @@ int process_receive_ib(struct hfi1_packet *packet) int process_receive_bypass(struct hfi1_packet *packet) { + struct hfi1_devdata *dd = packet->rcd->dd; + if (unlikely(rhf_err_flags(packet->rhf))) handle_eflags(packet); - dd_dev_err(packet->rcd->dd, + dd_dev_err(dd, "Bypass packets are not supported in normal operation. Dropping\n"); - incr_cntr64(&packet->rcd->dd->sw_rcv_bypass_packet_errors); + incr_cntr64(&dd->sw_rcv_bypass_packet_errors); + if (!(dd->err_info_rcvport.status_and_code & OPA_EI_STATUS_SMASK)) { + u64 *flits = packet->ebuf; + + if (flits && !(packet->rhf & RHF_LEN_ERR)) { + dd->err_info_rcvport.packet_flit1 = flits[0]; + dd->err_info_rcvport.packet_flit2 = + packet->tlen > sizeof(flits[0]) ? flits[1] : 0; + } + dd->err_info_rcvport.status_and_code |= + (OPA_EI_STATUS_SMASK | BAD_L2_ERR); + } return RHF_RCV_CONTINUE; } diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index 677efa0e8cd6..bd786b7bd30b 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -172,6 +172,9 @@ static int hfi1_file_open(struct inode *inode, struct file *fp) struct hfi1_devdata, user_cdev); + if (!atomic_inc_not_zero(&dd->user_refcount)) + return -ENXIO; + /* Just take a ref now. Not all opens result in a context assign */ kobject_get(&dd->kobj); @@ -183,11 +186,17 @@ static int hfi1_file_open(struct inode *inode, struct file *fp) fd->rec_cpu_num = -1; /* no cpu affinity by default */ fd->mm = current->mm; atomic_inc(&fd->mm->mm_count); + fp->private_data = fd; + } else { + fp->private_data = NULL; + + if (atomic_dec_and_test(&dd->user_refcount)) + complete(&dd->user_comp); + + return -ENOMEM; } - fp->private_data = fd; - - return fd ? 0 : -ENOMEM; + return 0; } static long hfi1_file_ioctl(struct file *fp, unsigned int cmd, @@ -798,6 +807,10 @@ static int hfi1_file_close(struct inode *inode, struct file *fp) done: mmdrop(fdata->mm); kobject_put(&dd->kobj); + + if (atomic_dec_and_test(&dd->user_refcount)) + complete(&dd->user_comp); + kfree(fdata); return 0; } diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h index 7eef11b316ff..cc87fd4e534b 100644 --- a/drivers/infiniband/hw/hfi1/hfi.h +++ b/drivers/infiniband/hw/hfi1/hfi.h @@ -367,26 +367,6 @@ struct hfi1_packet { u8 etype; }; -/* - * Private data for snoop/capture support. - */ -struct hfi1_snoop_data { - int mode_flag; - struct cdev cdev; - struct device *class_dev; - /* protect snoop data */ - spinlock_t snoop_lock; - struct list_head queue; - wait_queue_head_t waitq; - void *filter_value; - int (*filter_callback)(void *hdr, void *data, void *value); - u64 dcc_cfg; /* saved value of DCC Cfg register */ -}; - -/* snoop mode_flag values */ -#define HFI1_PORT_SNOOP_MODE 1U -#define HFI1_PORT_CAPTURE_MODE 2U - struct rvt_sge_state; /* @@ -613,8 +593,6 @@ struct hfi1_pportdata { struct mutex hls_lock; u32 host_link_state; - spinlock_t sdma_alllock ____cacheline_aligned_in_smp; - u32 lstate; /* logical link state */ /* these are the "32 bit" regs */ @@ -1104,8 +1082,6 @@ struct hfi1_devdata { char *portcntrnames; size_t portcntrnameslen; - struct hfi1_snoop_data hfi1_snoop; - struct err_info_rcvport err_info_rcvport; struct err_info_constraint err_info_rcv_constraint; struct err_info_constraint err_info_xmit_constraint; @@ -1141,8 +1117,8 @@ struct hfi1_devdata { rhf_rcv_function_ptr normal_rhf_rcv_functions[8]; /* - * Handlers for outgoing data so that snoop/capture does not - * have to have its hooks in the send path + * Capability to have different send engines simply by changing a + * pointer value. */ send_routine process_pio_send; send_routine process_dma_send; @@ -1174,6 +1150,10 @@ struct hfi1_devdata { spinlock_t aspm_lock; /* Number of verbs contexts which have disabled ASPM */ atomic_t aspm_disabled_cnt; + /* Keeps track of user space clients */ + atomic_t user_refcount; + /* Used to wait for outstanding user space clients before dev removal */ + struct completion user_comp; struct hfi1_affinity *affinity; struct rhashtable sdma_rht; @@ -1221,8 +1201,6 @@ struct hfi1_devdata *hfi1_lookup(int unit); extern u32 hfi1_cpulist_count; extern unsigned long *hfi1_cpulist; -extern unsigned int snoop_drop_send; -extern unsigned int snoop_force_capture; int hfi1_init(struct hfi1_devdata *, int); int hfi1_count_units(int *npresentp, int *nupp); int hfi1_count_active_units(void); @@ -1557,13 +1535,6 @@ void set_up_vl15(struct hfi1_devdata *dd, u8 vau, u16 vl15buf); void reset_link_credits(struct hfi1_devdata *dd); void assign_remote_cm_au_table(struct hfi1_devdata *dd, u8 vcu); -int snoop_recv_handler(struct hfi1_packet *packet); -int snoop_send_dma_handler(struct rvt_qp *qp, struct hfi1_pkt_state *ps, - u64 pbc); -int snoop_send_pio_handler(struct rvt_qp *qp, struct hfi1_pkt_state *ps, - u64 pbc); -void snoop_inline_pio_send(struct hfi1_devdata *dd, struct pio_buf *pbuf, - u64 pbc, const void *from, size_t count); int set_buffer_control(struct hfi1_pportdata *ppd, struct buffer_control *bc); static inline struct hfi1_devdata *dd_from_ppd(struct hfi1_pportdata *ppd) @@ -1763,8 +1734,7 @@ int qsfp_dump(struct hfi1_pportdata *ppd, char *buf, int len); int hfi1_pcie_init(struct pci_dev *, const struct pci_device_id *); void hfi1_pcie_cleanup(struct pci_dev *); -int hfi1_pcie_ddinit(struct hfi1_devdata *, struct pci_dev *, - const struct pci_device_id *); +int hfi1_pcie_ddinit(struct hfi1_devdata *, struct pci_dev *); void hfi1_pcie_ddcleanup(struct hfi1_devdata *); void hfi1_pcie_flr(struct hfi1_devdata *); int pcie_speeds(struct hfi1_devdata *); @@ -1799,8 +1769,6 @@ int kdeth_process_expected(struct hfi1_packet *packet); int kdeth_process_eager(struct hfi1_packet *packet); int process_receive_invalid(struct hfi1_packet *packet); -extern rhf_rcv_function_ptr snoop_rhf_rcv_functions[8]; - void update_sge(struct rvt_sge_state *ss, u32 length); /* global module parameter variables */ @@ -1827,9 +1795,6 @@ extern struct mutex hfi1_mutex; #define DRIVER_NAME "hfi1" #define HFI1_USER_MINOR_BASE 0 #define HFI1_TRACE_MINOR 127 -#define HFI1_DIAGPKT_MINOR 128 -#define HFI1_DIAG_MINOR_BASE 129 -#define HFI1_SNOOP_CAPTURE_BASE 200 #define HFI1_NMINORS 255 #define PCI_VENDOR_ID_INTEL 0x8086 @@ -1848,7 +1813,13 @@ extern struct mutex hfi1_mutex; static inline u64 hfi1_pkt_default_send_ctxt_mask(struct hfi1_devdata *dd, u16 ctxt_type) { - u64 base_sc_integrity = + u64 base_sc_integrity; + + /* No integrity checks if HFI1_CAP_NO_INTEGRITY is set */ + if (HFI1_CAP_IS_KSET(NO_INTEGRITY)) + return 0; + + base_sc_integrity = SEND_CTXT_CHECK_ENABLE_DISALLOW_BYPASS_BAD_PKT_LEN_SMASK | SEND_CTXT_CHECK_ENABLE_DISALLOW_PBC_STATIC_RATE_CONTROL_SMASK | SEND_CTXT_CHECK_ENABLE_DISALLOW_TOO_LONG_BYPASS_PACKETS_SMASK @@ -1863,7 +1834,6 @@ static inline u64 hfi1_pkt_default_send_ctxt_mask(struct hfi1_devdata *dd, | SEND_CTXT_CHECK_ENABLE_CHECK_VL_MAPPING_SMASK | SEND_CTXT_CHECK_ENABLE_CHECK_OPCODE_SMASK | SEND_CTXT_CHECK_ENABLE_CHECK_SLID_SMASK - | SEND_CTXT_CHECK_ENABLE_CHECK_JOB_KEY_SMASK | SEND_CTXT_CHECK_ENABLE_CHECK_VL_SMASK | SEND_CTXT_CHECK_ENABLE_CHECK_ENABLE_SMASK; @@ -1872,18 +1842,23 @@ static inline u64 hfi1_pkt_default_send_ctxt_mask(struct hfi1_devdata *dd, else base_sc_integrity |= HFI1_PKT_KERNEL_SC_INTEGRITY; - if (is_ax(dd)) - /* turn off send-side job key checks - A0 */ - return base_sc_integrity & - ~SEND_CTXT_CHECK_ENABLE_CHECK_JOB_KEY_SMASK; + /* turn on send-side job key checks if !A0 */ + if (!is_ax(dd)) + base_sc_integrity |= SEND_CTXT_CHECK_ENABLE_CHECK_JOB_KEY_SMASK; + return base_sc_integrity; } static inline u64 hfi1_pkt_base_sdma_integrity(struct hfi1_devdata *dd) { - u64 base_sdma_integrity = + u64 base_sdma_integrity; + + /* No integrity checks if HFI1_CAP_NO_INTEGRITY is set */ + if (HFI1_CAP_IS_KSET(NO_INTEGRITY)) + return 0; + + base_sdma_integrity = SEND_DMA_CHECK_ENABLE_DISALLOW_BYPASS_BAD_PKT_LEN_SMASK - | SEND_DMA_CHECK_ENABLE_DISALLOW_PBC_STATIC_RATE_CONTROL_SMASK | SEND_DMA_CHECK_ENABLE_DISALLOW_TOO_LONG_BYPASS_PACKETS_SMASK | SEND_DMA_CHECK_ENABLE_DISALLOW_TOO_LONG_IB_PACKETS_SMASK | SEND_DMA_CHECK_ENABLE_DISALLOW_BAD_PKT_LEN_SMASK @@ -1895,14 +1870,18 @@ static inline u64 hfi1_pkt_base_sdma_integrity(struct hfi1_devdata *dd) | SEND_DMA_CHECK_ENABLE_CHECK_VL_MAPPING_SMASK | SEND_DMA_CHECK_ENABLE_CHECK_OPCODE_SMASK | SEND_DMA_CHECK_ENABLE_CHECK_SLID_SMASK - | SEND_DMA_CHECK_ENABLE_CHECK_JOB_KEY_SMASK | SEND_DMA_CHECK_ENABLE_CHECK_VL_SMASK | SEND_DMA_CHECK_ENABLE_CHECK_ENABLE_SMASK; - if (is_ax(dd)) - /* turn off send-side job key checks - A0 */ - return base_sdma_integrity & - ~SEND_DMA_CHECK_ENABLE_CHECK_JOB_KEY_SMASK; + if (!HFI1_CAP_IS_KSET(STATIC_RATE_CTRL)) + base_sdma_integrity |= + SEND_DMA_CHECK_ENABLE_DISALLOW_PBC_STATIC_RATE_CONTROL_SMASK; + + /* turn on send-side job key checks if !A0 */ + if (!is_ax(dd)) + base_sdma_integrity |= + SEND_DMA_CHECK_ENABLE_CHECK_JOB_KEY_SMASK; + return base_sdma_integrity; } diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c index 60db61536fed..e3b5bc93bc70 100644 --- a/drivers/infiniband/hw/hfi1/init.c +++ b/drivers/infiniband/hw/hfi1/init.c @@ -144,6 +144,8 @@ int hfi1_create_ctxts(struct hfi1_devdata *dd) struct hfi1_ctxtdata *rcd; ppd = dd->pport + (i % dd->num_pports); + + /* dd->rcd[i] gets assigned inside the callee */ rcd = hfi1_create_ctxtdata(ppd, i, dd->node); if (!rcd) { dd_dev_err(dd, @@ -169,8 +171,6 @@ int hfi1_create_ctxts(struct hfi1_devdata *dd) if (!rcd->sc) { dd_dev_err(dd, "Unable to allocate kernel send context, failing\n"); - dd->rcd[rcd->ctxt] = NULL; - hfi1_free_ctxtdata(dd, rcd); goto nomem; } @@ -178,9 +178,6 @@ int hfi1_create_ctxts(struct hfi1_devdata *dd) if (ret < 0) { dd_dev_err(dd, "Failed to setup kernel receive context, failing\n"); - sc_free(rcd->sc); - dd->rcd[rcd->ctxt] = NULL; - hfi1_free_ctxtdata(dd, rcd); ret = -EFAULT; goto bail; } @@ -196,6 +193,10 @@ int hfi1_create_ctxts(struct hfi1_devdata *dd) nomem: ret = -ENOMEM; bail: + if (dd->rcd) { + for (i = 0; i < dd->num_rcv_contexts; ++i) + hfi1_free_ctxtdata(dd, dd->rcd[i]); + } kfree(dd->rcd); dd->rcd = NULL; return ret; @@ -216,7 +217,7 @@ struct hfi1_ctxtdata *hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, u32 ctxt, dd->num_rcv_contexts - dd->first_user_ctxt) kctxt_ngroups = (dd->rcv_entries.nctxt_extra - (dd->num_rcv_contexts - dd->first_user_ctxt)); - rcd = kzalloc(sizeof(*rcd), GFP_KERNEL); + rcd = kzalloc_node(sizeof(*rcd), GFP_KERNEL, numa); if (rcd) { u32 rcvtids, max_entries; @@ -261,13 +262,6 @@ struct hfi1_ctxtdata *hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, u32 ctxt, } rcd->eager_base = base * dd->rcv_entries.group_size; - /* Validate and initialize Rcv Hdr Q variables */ - if (rcvhdrcnt % HDRQ_INCREMENT) { - dd_dev_err(dd, - "ctxt%u: header queue count %d must be divisible by %lu\n", - rcd->ctxt, rcvhdrcnt, HDRQ_INCREMENT); - goto bail; - } rcd->rcvhdrq_cnt = rcvhdrcnt; rcd->rcvhdrqentsize = hfi1_hdrq_entsize; /* @@ -506,7 +500,6 @@ void hfi1_init_pportdata(struct pci_dev *pdev, struct hfi1_pportdata *ppd, INIT_WORK(&ppd->qsfp_info.qsfp_work, qsfp_event); mutex_init(&ppd->hls_lock); - spin_lock_init(&ppd->sdma_alllock); spin_lock_init(&ppd->qsfp_info.qsfp_lock); ppd->qsfp_info.ppd = ppd; @@ -1399,28 +1392,43 @@ static void postinit_cleanup(struct hfi1_devdata *dd) hfi1_free_devdata(dd); } +static int init_validate_rcvhdrcnt(struct device *dev, uint thecnt) +{ + if (thecnt <= HFI1_MIN_HDRQ_EGRBUF_CNT) { + hfi1_early_err(dev, "Receive header queue count too small\n"); + return -EINVAL; + } + + if (thecnt > HFI1_MAX_HDRQ_EGRBUF_CNT) { + hfi1_early_err(dev, + "Receive header queue count cannot be greater than %u\n", + HFI1_MAX_HDRQ_EGRBUF_CNT); + return -EINVAL; + } + + if (thecnt % HDRQ_INCREMENT) { + hfi1_early_err(dev, "Receive header queue count %d must be divisible by %lu\n", + thecnt, HDRQ_INCREMENT); + return -EINVAL; + } + + return 0; +} + static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) { int ret = 0, j, pidx, initfail; - struct hfi1_devdata *dd = ERR_PTR(-EINVAL); + struct hfi1_devdata *dd; struct hfi1_pportdata *ppd; /* First, lock the non-writable module parameters */ HFI1_CAP_LOCK(); /* Validate some global module parameters */ - if (rcvhdrcnt <= HFI1_MIN_HDRQ_EGRBUF_CNT) { - hfi1_early_err(&pdev->dev, "Header queue count too small\n"); - ret = -EINVAL; + ret = init_validate_rcvhdrcnt(&pdev->dev, rcvhdrcnt); + if (ret) goto bail; - } - if (rcvhdrcnt > HFI1_MAX_HDRQ_EGRBUF_CNT) { - hfi1_early_err(&pdev->dev, - "Receive header queue count cannot be greater than %u\n", - HFI1_MAX_HDRQ_EGRBUF_CNT); - ret = -EINVAL; - goto bail; - } + /* use the encoding function as a sanitization check */ if (!encode_rcv_header_entry_size(hfi1_hdrq_entsize)) { hfi1_early_err(&pdev->dev, "Invalid HdrQ Entry size %u\n", @@ -1461,26 +1469,25 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (ret) goto bail; - /* - * Do device-specific initialization, function table setup, dd - * allocation, etc. - */ - switch (ent->device) { - case PCI_DEVICE_ID_INTEL0: - case PCI_DEVICE_ID_INTEL1: - dd = hfi1_init_dd(pdev, ent); - break; - default: + if (!(ent->device == PCI_DEVICE_ID_INTEL0 || + ent->device == PCI_DEVICE_ID_INTEL1)) { hfi1_early_err(&pdev->dev, "Failing on unknown Intel deviceid 0x%x\n", ent->device); ret = -ENODEV; + goto clean_bail; } - if (IS_ERR(dd)) + /* + * Do device-specific initialization, function table setup, dd + * allocation, etc. + */ + dd = hfi1_init_dd(pdev, ent); + + if (IS_ERR(dd)) { ret = PTR_ERR(dd); - if (ret) goto clean_bail; /* error already printed */ + } ret = create_workqueues(dd); if (ret) @@ -1538,12 +1545,31 @@ bail: return ret; } +static void wait_for_clients(struct hfi1_devdata *dd) +{ + /* + * Remove the device init value and complete the device if there is + * no clients or wait for active clients to finish. + */ + if (atomic_dec_and_test(&dd->user_refcount)) + complete(&dd->user_comp); + + wait_for_completion(&dd->user_comp); +} + static void remove_one(struct pci_dev *pdev) { struct hfi1_devdata *dd = pci_get_drvdata(pdev); /* close debugfs files before ib unregister */ hfi1_dbg_ibdev_exit(&dd->verbs_dev); + + /* remove the /dev hfi1 interface */ + hfi1_device_remove(dd); + + /* wait for existing user space clients to finish */ + wait_for_clients(dd); + /* unregister from IB core */ hfi1_unregister_ib_device(dd); @@ -1558,8 +1584,6 @@ static void remove_one(struct pci_dev *pdev) /* wait until all of our (qsfp) queue_work() calls complete */ flush_workqueue(ib_wq); - hfi1_device_remove(dd); - postinit_cleanup(dd); } diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c index 89c68da1c273..4ac8f330c5cb 100644 --- a/drivers/infiniband/hw/hfi1/pcie.c +++ b/drivers/infiniband/hw/hfi1/pcie.c @@ -157,8 +157,7 @@ void hfi1_pcie_cleanup(struct pci_dev *pdev) * fields required to re-initialize after a chip reset, or for * various other purposes */ -int hfi1_pcie_ddinit(struct hfi1_devdata *dd, struct pci_dev *pdev, - const struct pci_device_id *ent) +int hfi1_pcie_ddinit(struct hfi1_devdata *dd, struct pci_dev *pdev) { unsigned long len; resource_size_t addr; diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c index 50a3a36d9363..d89b8745d4c1 100644 --- a/drivers/infiniband/hw/hfi1/pio.c +++ b/drivers/infiniband/hw/hfi1/pio.c @@ -668,19 +668,12 @@ void sc_set_cr_threshold(struct send_context *sc, u32 new_threshold) void set_pio_integrity(struct send_context *sc) { struct hfi1_devdata *dd = sc->dd; - u64 reg = 0; u32 hw_context = sc->hw_context; int type = sc->type; - /* - * No integrity checks if HFI1_CAP_NO_INTEGRITY is set, or if - * we're snooping. - */ - if (likely(!HFI1_CAP_IS_KSET(NO_INTEGRITY)) && - dd->hfi1_snoop.mode_flag != HFI1_PORT_SNOOP_MODE) - reg = hfi1_pkt_default_send_ctxt_mask(dd, type); - - write_kctxt_csr(dd, hw_context, SC(CHECK_ENABLE), reg); + write_kctxt_csr(dd, hw_context, + SC(CHECK_ENABLE), + hfi1_pkt_default_send_ctxt_mask(dd, type)); } static u32 get_buffers_allocated(struct send_context *sc) diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c index 8bc5013f39a1..83198a8a8797 100644 --- a/drivers/infiniband/hw/hfi1/rc.c +++ b/drivers/infiniband/hw/hfi1/rc.c @@ -89,7 +89,7 @@ void hfi1_add_rnr_timer(struct rvt_qp *qp, u32 to) lockdep_assert_held(&qp->s_lock); qp->s_flags |= RVT_S_WAIT_RNR; - qp->s_timer.expires = jiffies + usecs_to_jiffies(to); + priv->s_rnr_timer.expires = jiffies + usecs_to_jiffies(to); add_timer(&priv->s_rnr_timer); } diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index fd39bcaa062d..9cbe52d21077 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -2009,11 +2009,6 @@ static void sdma_hw_start_up(struct sdma_engine *sde) write_sde_csr(sde, SD(ENG_ERR_CLEAR), reg); } -#define CLEAR_STATIC_RATE_CONTROL_SMASK(r) \ -(r &= ~SEND_DMA_CHECK_ENABLE_DISALLOW_PBC_STATIC_RATE_CONTROL_SMASK) - -#define SET_STATIC_RATE_CONTROL_SMASK(r) \ -(r |= SEND_DMA_CHECK_ENABLE_DISALLOW_PBC_STATIC_RATE_CONTROL_SMASK) /* * set_sdma_integrity * @@ -2022,19 +2017,9 @@ static void sdma_hw_start_up(struct sdma_engine *sde) static void set_sdma_integrity(struct sdma_engine *sde) { struct hfi1_devdata *dd = sde->dd; - u64 reg; - if (unlikely(HFI1_CAP_IS_KSET(NO_INTEGRITY))) - return; - - reg = hfi1_pkt_base_sdma_integrity(dd); - - if (HFI1_CAP_IS_KSET(STATIC_RATE_CTRL)) - CLEAR_STATIC_RATE_CONTROL_SMASK(reg); - else - SET_STATIC_RATE_CONTROL_SMASK(reg); - - write_sde_csr(sde, SD(CHECK_ENABLE), reg); + write_sde_csr(sde, SD(CHECK_ENABLE), + hfi1_pkt_base_sdma_integrity(dd)); } static void init_sdma_regs( diff --git a/drivers/infiniband/hw/hfi1/sysfs.c b/drivers/infiniband/hw/hfi1/sysfs.c index edba22461a9c..919a5474e651 100644 --- a/drivers/infiniband/hw/hfi1/sysfs.c +++ b/drivers/infiniband/hw/hfi1/sysfs.c @@ -49,7 +49,6 @@ #include "hfi.h" #include "mad.h" #include "trace.h" -#include "affinity.h" /* * Start of per-port congestion control structures and support code @@ -623,27 +622,6 @@ static ssize_t show_tempsense(struct device *device, return ret; } -static ssize_t show_sdma_affinity(struct device *device, - struct device_attribute *attr, char *buf) -{ - struct hfi1_ibdev *dev = - container_of(device, struct hfi1_ibdev, rdi.ibdev.dev); - struct hfi1_devdata *dd = dd_from_dev(dev); - - return hfi1_get_sdma_affinity(dd, buf); -} - -static ssize_t store_sdma_affinity(struct device *device, - struct device_attribute *attr, - const char *buf, size_t count) -{ - struct hfi1_ibdev *dev = - container_of(device, struct hfi1_ibdev, rdi.ibdev.dev); - struct hfi1_devdata *dd = dd_from_dev(dev); - - return hfi1_set_sdma_affinity(dd, buf, count); -} - /* * end of per-unit (or driver, in some cases, but replicated * per unit) functions @@ -658,8 +636,6 @@ static DEVICE_ATTR(serial, S_IRUGO, show_serial, NULL); static DEVICE_ATTR(boardversion, S_IRUGO, show_boardversion, NULL); static DEVICE_ATTR(tempsense, S_IRUGO, show_tempsense, NULL); static DEVICE_ATTR(chip_reset, S_IWUSR, NULL, store_chip_reset); -static DEVICE_ATTR(sdma_affinity, S_IWUSR | S_IRUGO, show_sdma_affinity, - store_sdma_affinity); static struct device_attribute *hfi1_attributes[] = { &dev_attr_hw_rev, @@ -670,7 +646,6 @@ static struct device_attribute *hfi1_attributes[] = { &dev_attr_boardversion, &dev_attr_tempsense, &dev_attr_chip_reset, - &dev_attr_sdma_affinity, }; int hfi1_create_port_files(struct ib_device *ibdev, u8 port_num, diff --git a/drivers/infiniband/hw/hfi1/trace_rx.h b/drivers/infiniband/hw/hfi1/trace_rx.h index 11e02b228922..f77e59fb43fe 100644 --- a/drivers/infiniband/hw/hfi1/trace_rx.h +++ b/drivers/infiniband/hw/hfi1/trace_rx.h @@ -253,66 +253,6 @@ TRACE_EVENT(hfi1_mmu_invalidate, ) ); -#define SNOOP_PRN \ - "slid %.4x dlid %.4x qpn 0x%.6x opcode 0x%.2x,%s " \ - "svc lvl %d pkey 0x%.4x [header = %d bytes] [data = %d bytes]" - -TRACE_EVENT(snoop_capture, - TP_PROTO(struct hfi1_devdata *dd, - int hdr_len, - struct ib_header *hdr, - int data_len, - void *data), - TP_ARGS(dd, hdr_len, hdr, data_len, data), - TP_STRUCT__entry( - DD_DEV_ENTRY(dd) - __field(u16, slid) - __field(u16, dlid) - __field(u32, qpn) - __field(u8, opcode) - __field(u8, sl) - __field(u16, pkey) - __field(u32, hdr_len) - __field(u32, data_len) - __field(u8, lnh) - __dynamic_array(u8, raw_hdr, hdr_len) - __dynamic_array(u8, raw_pkt, data_len) - ), - TP_fast_assign( - struct ib_other_headers *ohdr; - - __entry->lnh = (u8)(be16_to_cpu(hdr->lrh[0]) & 3); - if (__entry->lnh == HFI1_LRH_BTH) - ohdr = &hdr->u.oth; - else - ohdr = &hdr->u.l.oth; - DD_DEV_ASSIGN(dd); - __entry->slid = be16_to_cpu(hdr->lrh[3]); - __entry->dlid = be16_to_cpu(hdr->lrh[1]); - __entry->qpn = be32_to_cpu(ohdr->bth[1]) & RVT_QPN_MASK; - __entry->opcode = (be32_to_cpu(ohdr->bth[0]) >> 24) & 0xff; - __entry->sl = (u8)(be16_to_cpu(hdr->lrh[0]) >> 4) & 0xf; - __entry->pkey = be32_to_cpu(ohdr->bth[0]) & 0xffff; - __entry->hdr_len = hdr_len; - __entry->data_len = data_len; - memcpy(__get_dynamic_array(raw_hdr), hdr, hdr_len); - memcpy(__get_dynamic_array(raw_pkt), data, data_len); - ), - TP_printk( - "[%s] " SNOOP_PRN, - __get_str(dev), - __entry->slid, - __entry->dlid, - __entry->qpn, - __entry->opcode, - show_ib_opcode(__entry->opcode), - __entry->sl, - __entry->pkey, - __entry->hdr_len, - __entry->data_len - ) -); - #endif /* __HFI1_TRACE_RX_H */ #undef TRACE_INCLUDE_PATH diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c index a761f804111e..77697d690f3e 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.c +++ b/drivers/infiniband/hw/hfi1/user_sdma.c @@ -1144,7 +1144,7 @@ static int pin_vector_pages(struct user_sdma_request *req, rb_node = hfi1_mmu_rb_extract(pq->handler, (unsigned long)iovec->iov.iov_base, iovec->iov.iov_len); - if (rb_node && !IS_ERR(rb_node)) + if (rb_node) node = container_of(rb_node, struct sdma_mmu_node, rb); else rb_node = NULL; diff --git a/drivers/infiniband/hw/mlx4/ah.c b/drivers/infiniband/hw/mlx4/ah.c index 5fc623362731..b9bf0759f10a 100644 --- a/drivers/infiniband/hw/mlx4/ah.c +++ b/drivers/infiniband/hw/mlx4/ah.c @@ -102,7 +102,10 @@ static struct ib_ah *create_iboe_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr if (vlan_tag < 0x1000) vlan_tag |= (ah_attr->sl & 7) << 13; ah->av.eth.port_pd = cpu_to_be32(to_mpd(pd)->pdn | (ah_attr->port_num << 24)); - ah->av.eth.gid_index = mlx4_ib_gid_index_to_real_index(ibdev, ah_attr->port_num, ah_attr->grh.sgid_index); + ret = mlx4_ib_gid_index_to_real_index(ibdev, ah_attr->port_num, ah_attr->grh.sgid_index); + if (ret < 0) + return ERR_PTR(ret); + ah->av.eth.gid_index = ret; ah->av.eth.vlan = cpu_to_be16(vlan_tag); ah->av.eth.hop_limit = ah_attr->grh.hop_limit; if (ah_attr->static_rate) { diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c index 1ea686b9e0f9..6a0fec357dae 100644 --- a/drivers/infiniband/hw/mlx4/cq.c +++ b/drivers/infiniband/hw/mlx4/cq.c @@ -253,11 +253,14 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, if (context) if (ib_copy_to_udata(udata, &cq->mcq.cqn, sizeof (__u32))) { err = -EFAULT; - goto err_dbmap; + goto err_cq_free; } return &cq->ibcq; +err_cq_free: + mlx4_cq_free(dev->dev, &cq->mcq); + err_dbmap: if (context) mlx4_ib_db_unmap_user(to_mucontext(context), &cq->db); diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index 79d017baf6f4..fcd04b881ec1 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -932,8 +932,7 @@ struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev, if (err) goto err_create; } else { - /* for now choose 64 bytes till we have a proper interface */ - cqe_size = 64; + cqe_size = cache_line_size() == 128 ? 128 : 64; err = create_cq_kernel(dev, cq, entries, cqe_size, &cqb, &index, &inlen); if (err) diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 63036c731626..32b09f059c84 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -2311,14 +2311,14 @@ static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context, { struct mlx5_ib_dev *ibdev = (struct mlx5_ib_dev *)context; struct ib_event ibev; - + bool fatal = false; u8 port = 0; switch (event) { case MLX5_DEV_EVENT_SYS_ERROR: - ibdev->ib_active = false; ibev.event = IB_EVENT_DEVICE_FATAL; mlx5_ib_handle_internal_error(ibdev); + fatal = true; break; case MLX5_DEV_EVENT_PORT_UP: @@ -2370,6 +2370,9 @@ static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context, if (ibdev->ib_active) ib_dispatch_event(&ibev); + + if (fatal) + ibdev->ib_active = false; } static void get_ext_port_caps(struct mlx5_ib_dev *dev) @@ -3115,7 +3118,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) } err = init_node_data(dev); if (err) - goto err_dealloc; + goto err_free_port; mutex_init(&dev->flow_db.lock); mutex_init(&dev->cap_mask_mutex); @@ -3125,7 +3128,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) if (ll == IB_LINK_LAYER_ETHERNET) { err = mlx5_enable_roce(dev); if (err) - goto err_dealloc; + goto err_free_port; } err = create_dev_resources(&dev->devr); diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index dcdcd195fe53..7d689903c87c 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -626,6 +626,8 @@ struct mlx5_ib_dev { struct mlx5_ib_resources devr; struct mlx5_mr_cache cache; struct timer_list delay_timer; + /* Prevents soft lock on massive reg MRs */ + struct mutex slow_path_mutex; int fill_delay; #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING struct ib_odp_caps odp_caps; diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index d4ad672b905b..4e9012463c37 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -610,6 +610,7 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev) int err; int i; + mutex_init(&dev->slow_path_mutex); cache->wq = alloc_ordered_workqueue("mkey_cache", WQ_MEM_RECLAIM); if (!cache->wq) { mlx5_ib_warn(dev, "failed to create work queue\n"); @@ -1182,9 +1183,12 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, goto error; } - if (!mr) + if (!mr) { + mutex_lock(&dev->slow_path_mutex); mr = reg_create(NULL, pd, virt_addr, length, umem, ncont, page_shift, access_flags); + mutex_unlock(&dev->slow_path_mutex); + } if (IS_ERR(mr)) { err = PTR_ERR(mr); diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 7ce97daf26c6..d1e921816bfe 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -2051,8 +2051,8 @@ struct ib_qp *mlx5_ib_create_qp(struct ib_pd *pd, mlx5_ib_dbg(dev, "ib qpnum 0x%x, mlx qpn 0x%x, rcqn 0x%x, scqn 0x%x\n", qp->ibqp.qp_num, qp->trans_qp.base.mqp.qpn, - to_mcq(init_attr->recv_cq)->mcq.cqn, - to_mcq(init_attr->send_cq)->mcq.cqn); + init_attr->recv_cq ? to_mcq(init_attr->recv_cq)->mcq.cqn : -1, + init_attr->send_cq ? to_mcq(init_attr->send_cq)->mcq.cqn : -1); qp->trans_qp.xrcdn = xrcdn; @@ -4814,6 +4814,14 @@ struct ib_rwq_ind_table *mlx5_ib_create_rwq_ind_table(struct ib_device *device, udata->inlen)) return ERR_PTR(-EOPNOTSUPP); + if (init_attr->log_ind_tbl_size > + MLX5_CAP_GEN(dev->mdev, log_max_rqt_size)) { + mlx5_ib_dbg(dev, "log_ind_tbl_size = %d is bigger than supported = %d\n", + init_attr->log_ind_tbl_size, + MLX5_CAP_GEN(dev->mdev, log_max_rqt_size)); + return ERR_PTR(-EINVAL); + } + min_resp_len = offsetof(typeof(resp), reserved) + sizeof(resp.reserved); if (udata->outlen && udata->outlen < min_resp_len) return ERR_PTR(-EINVAL); diff --git a/drivers/infiniband/sw/rdmavt/dma.c b/drivers/infiniband/sw/rdmavt/dma.c index 01f71caa3ac4..f2cefb0d9180 100644 --- a/drivers/infiniband/sw/rdmavt/dma.c +++ b/drivers/infiniband/sw/rdmavt/dma.c @@ -90,9 +90,6 @@ static u64 rvt_dma_map_page(struct ib_device *dev, struct page *page, if (WARN_ON(!valid_dma_direction(direction))) return BAD_DMA_ADDRESS; - if (offset + size > PAGE_SIZE) - return BAD_DMA_ADDRESS; - addr = (u64)page_address(page); if (addr) addr += offset; diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index b8258e4f0aea..ffff5a54cb34 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -243,10 +243,8 @@ static struct socket *rxe_setup_udp_tunnel(struct net *net, __be16 port, { int err; struct socket *sock; - struct udp_port_cfg udp_cfg; - struct udp_tunnel_sock_cfg tnl_cfg; - - memset(&udp_cfg, 0, sizeof(udp_cfg)); + struct udp_port_cfg udp_cfg = {0}; + struct udp_tunnel_sock_cfg tnl_cfg = {0}; if (ipv6) { udp_cfg.family = AF_INET6; @@ -264,10 +262,8 @@ static struct socket *rxe_setup_udp_tunnel(struct net *net, __be16 port, return ERR_PTR(err); } - tnl_cfg.sk_user_data = NULL; tnl_cfg.encap_type = 1; tnl_cfg.encap_rcv = rxe_udp_encap_recv; - tnl_cfg.encap_destroy = NULL; /* Setup UDP tunnel */ setup_udp_tunnel_sock(net, sock, &tnl_cfg); diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index b8036cfbce04..c3e60e4bde6e 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -522,6 +522,7 @@ static void rxe_qp_reset(struct rxe_qp *qp) if (qp->sq.queue) { __rxe_do_task(&qp->comp.task); __rxe_do_task(&qp->req.task); + rxe_queue_reset(qp->sq.queue); } /* cleanup attributes */ @@ -573,6 +574,7 @@ void rxe_qp_error(struct rxe_qp *qp) { qp->req.state = QP_STATE_ERROR; qp->resp.state = QP_STATE_ERROR; + qp->attr.qp_state = IB_QPS_ERR; /* drain work and packet queues */ rxe_run_task(&qp->resp.task, 1); diff --git a/drivers/infiniband/sw/rxe/rxe_queue.c b/drivers/infiniband/sw/rxe/rxe_queue.c index 08274254eb88..d14bf496d62d 100644 --- a/drivers/infiniband/sw/rxe/rxe_queue.c +++ b/drivers/infiniband/sw/rxe/rxe_queue.c @@ -84,6 +84,15 @@ err1: return -EINVAL; } +inline void rxe_queue_reset(struct rxe_queue *q) +{ + /* queue is comprised from header and the memory + * of the actual queue. See "struct rxe_queue_buf" in rxe_queue.h + * reset only the queue itself and not the management header + */ + memset(q->buf->data, 0, q->buf_size - sizeof(struct rxe_queue_buf)); +} + struct rxe_queue *rxe_queue_init(struct rxe_dev *rxe, int *num_elem, unsigned int elem_size) diff --git a/drivers/infiniband/sw/rxe/rxe_queue.h b/drivers/infiniband/sw/rxe/rxe_queue.h index 239fd609c31e..8c8641c87817 100644 --- a/drivers/infiniband/sw/rxe/rxe_queue.h +++ b/drivers/infiniband/sw/rxe/rxe_queue.h @@ -84,6 +84,8 @@ int do_mmap_info(struct rxe_dev *rxe, size_t buf_size, struct rxe_mmap_info **ip_p); +void rxe_queue_reset(struct rxe_queue *q); + struct rxe_queue *rxe_queue_init(struct rxe_dev *rxe, int *num_elem, unsigned int elem_size); diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c index 832846b73ea0..22bd9630dcd9 100644 --- a/drivers/infiniband/sw/rxe/rxe_req.c +++ b/drivers/infiniband/sw/rxe/rxe_req.c @@ -696,7 +696,8 @@ next_wqe: qp->req.wqe_index); wqe->state = wqe_state_done; wqe->status = IB_WC_SUCCESS; - goto complete; + __rxe_do_task(&qp->comp.task); + return 0; } payload = mtu; } @@ -745,13 +746,17 @@ err: wqe->status = IB_WC_LOC_PROT_ERR; wqe->state = wqe_state_error; -complete: - if (qp_type(qp) != IB_QPT_RC) { - while (rxe_completer(qp) == 0) - ; - } - - return 0; + /* + * IBA Spec. Section 10.7.3.1 SIGNALED COMPLETIONS + * ---------8<---------8<------------- + * ...Note that if a completion error occurs, a Work Completion + * will always be generated, even if the signaling + * indicator requests an Unsignaled Completion. + * ---------8<---------8<------------- + */ + wqe->wr.send_flags |= IB_SEND_SIGNALED; + __rxe_do_task(&qp->comp.task); + return -EAGAIN; exit: return -EAGAIN; diff --git a/drivers/mailbox/pcc.c b/drivers/mailbox/pcc.c index 08c87fadca8c..1f32688c312d 100644 --- a/drivers/mailbox/pcc.c +++ b/drivers/mailbox/pcc.c @@ -65,6 +65,7 @@ #include #include #include +#include #include "mailbox.h" @@ -267,6 +268,8 @@ struct mbox_chan *pcc_mbox_request_channel(struct mbox_client *cl, if (chan->txdone_method == TXDONE_BY_POLL && cl->knows_txdone) chan->txdone_method |= TXDONE_BY_ACK; + spin_unlock_irqrestore(&chan->lock, flags); + if (pcc_doorbell_irq[subspace_id] > 0) { int rc; @@ -275,12 +278,11 @@ struct mbox_chan *pcc_mbox_request_channel(struct mbox_client *cl, if (unlikely(rc)) { dev_err(dev, "failed to register PCC interrupt %d\n", pcc_doorbell_irq[subspace_id]); + pcc_mbox_free_channel(chan); chan = ERR_PTR(rc); } } - spin_unlock_irqrestore(&chan->lock, flags); - return chan; } EXPORT_SYMBOL_GPL(pcc_mbox_request_channel); @@ -304,20 +306,19 @@ void pcc_mbox_free_channel(struct mbox_chan *chan) return; } + if (pcc_doorbell_irq[id] > 0) + devm_free_irq(chan->mbox->dev, pcc_doorbell_irq[id], chan); + spin_lock_irqsave(&chan->lock, flags); chan->cl = NULL; chan->active_req = NULL; if (chan->txdone_method == (TXDONE_BY_POLL | TXDONE_BY_ACK)) chan->txdone_method = TXDONE_BY_POLL; - if (pcc_doorbell_irq[id] > 0) - devm_free_irq(chan->mbox->dev, pcc_doorbell_irq[id], chan); - spin_unlock_irqrestore(&chan->lock, flags); } EXPORT_SYMBOL_GPL(pcc_mbox_free_channel); - /** * pcc_send_data - Called from Mailbox Controller code. Used * here only to ring the channel doorbell. The PCC client diff --git a/drivers/mfd/intel-lpss-pci.c b/drivers/mfd/intel-lpss-pci.c index 3228fd182a99..9ff243970e93 100644 --- a/drivers/mfd/intel-lpss-pci.c +++ b/drivers/mfd/intel-lpss-pci.c @@ -123,19 +123,6 @@ static const struct intel_lpss_platform_info apl_i2c_info = { .properties = apl_i2c_properties, }; -static const struct intel_lpss_platform_info kbl_info = { - .clk_rate = 120000000, -}; - -static const struct intel_lpss_platform_info kbl_uart_info = { - .clk_rate = 120000000, - .clk_con_id = "baudclk", -}; - -static const struct intel_lpss_platform_info kbl_i2c_info = { - .clk_rate = 133000000, -}; - static const struct pci_device_id intel_lpss_pci_ids[] = { /* BXT A-Step */ { PCI_VDEVICE(INTEL, 0x0aac), (kernel_ulong_t)&bxt_i2c_info }, @@ -207,15 +194,15 @@ static const struct pci_device_id intel_lpss_pci_ids[] = { { PCI_VDEVICE(INTEL, 0xa161), (kernel_ulong_t)&spt_i2c_info }, { PCI_VDEVICE(INTEL, 0xa166), (kernel_ulong_t)&spt_uart_info }, /* KBL-H */ - { PCI_VDEVICE(INTEL, 0xa2a7), (kernel_ulong_t)&kbl_uart_info }, - { PCI_VDEVICE(INTEL, 0xa2a8), (kernel_ulong_t)&kbl_uart_info }, - { PCI_VDEVICE(INTEL, 0xa2a9), (kernel_ulong_t)&kbl_info }, - { PCI_VDEVICE(INTEL, 0xa2aa), (kernel_ulong_t)&kbl_info }, - { PCI_VDEVICE(INTEL, 0xa2e0), (kernel_ulong_t)&kbl_i2c_info }, - { PCI_VDEVICE(INTEL, 0xa2e1), (kernel_ulong_t)&kbl_i2c_info }, - { PCI_VDEVICE(INTEL, 0xa2e2), (kernel_ulong_t)&kbl_i2c_info }, - { PCI_VDEVICE(INTEL, 0xa2e3), (kernel_ulong_t)&kbl_i2c_info }, - { PCI_VDEVICE(INTEL, 0xa2e6), (kernel_ulong_t)&kbl_uart_info }, + { PCI_VDEVICE(INTEL, 0xa2a7), (kernel_ulong_t)&spt_uart_info }, + { PCI_VDEVICE(INTEL, 0xa2a8), (kernel_ulong_t)&spt_uart_info }, + { PCI_VDEVICE(INTEL, 0xa2a9), (kernel_ulong_t)&spt_info }, + { PCI_VDEVICE(INTEL, 0xa2aa), (kernel_ulong_t)&spt_info }, + { PCI_VDEVICE(INTEL, 0xa2e0), (kernel_ulong_t)&spt_i2c_info }, + { PCI_VDEVICE(INTEL, 0xa2e1), (kernel_ulong_t)&spt_i2c_info }, + { PCI_VDEVICE(INTEL, 0xa2e2), (kernel_ulong_t)&spt_i2c_info }, + { PCI_VDEVICE(INTEL, 0xa2e3), (kernel_ulong_t)&spt_i2c_info }, + { PCI_VDEVICE(INTEL, 0xa2e6), (kernel_ulong_t)&spt_uart_info }, { } }; MODULE_DEVICE_TABLE(pci, intel_lpss_pci_ids); diff --git a/drivers/mfd/intel-lpss.c b/drivers/mfd/intel-lpss.c index 41b113875d64..70c646b0097d 100644 --- a/drivers/mfd/intel-lpss.c +++ b/drivers/mfd/intel-lpss.c @@ -502,9 +502,6 @@ int intel_lpss_suspend(struct device *dev) for (i = 0; i < LPSS_PRIV_REG_COUNT; i++) lpss->priv_ctx[i] = readl(lpss->priv + i * 4); - /* Put the device into reset state */ - writel(0, lpss->priv + LPSS_PRIV_RESETS); - return 0; } EXPORT_SYMBOL_GPL(intel_lpss_suspend); diff --git a/drivers/mfd/intel_soc_pmic_bxtwc.c b/drivers/mfd/intel_soc_pmic_bxtwc.c index 43e54b7e908f..f9a8c5203873 100644 --- a/drivers/mfd/intel_soc_pmic_bxtwc.c +++ b/drivers/mfd/intel_soc_pmic_bxtwc.c @@ -86,6 +86,7 @@ enum bxtwc_irqs_level2 { BXTWC_THRM2_IRQ, BXTWC_BCU_IRQ, BXTWC_ADC_IRQ, + BXTWC_USBC_IRQ, BXTWC_CHGR0_IRQ, BXTWC_CHGR1_IRQ, BXTWC_GPIO0_IRQ, @@ -111,7 +112,8 @@ static const struct regmap_irq bxtwc_regmap_irqs_level2[] = { REGMAP_IRQ_REG(BXTWC_THRM2_IRQ, 2, 0xff), REGMAP_IRQ_REG(BXTWC_BCU_IRQ, 3, 0x1f), REGMAP_IRQ_REG(BXTWC_ADC_IRQ, 4, 0xff), - REGMAP_IRQ_REG(BXTWC_CHGR0_IRQ, 5, 0x3f), + REGMAP_IRQ_REG(BXTWC_USBC_IRQ, 5, BIT(5)), + REGMAP_IRQ_REG(BXTWC_CHGR0_IRQ, 5, 0x1f), REGMAP_IRQ_REG(BXTWC_CHGR1_IRQ, 6, 0x1f), REGMAP_IRQ_REG(BXTWC_GPIO0_IRQ, 7, 0xff), REGMAP_IRQ_REG(BXTWC_GPIO1_IRQ, 8, 0x3f), @@ -146,7 +148,7 @@ static struct resource adc_resources[] = { }; static struct resource usbc_resources[] = { - DEFINE_RES_IRQ_NAMED(BXTWC_CHGR0_IRQ, "USBC"), + DEFINE_RES_IRQ(BXTWC_USBC_IRQ), }; static struct resource charger_resources[] = { diff --git a/drivers/mfd/mfd-core.c b/drivers/mfd/mfd-core.c index 3ac486a597f3..c57e407020f1 100644 --- a/drivers/mfd/mfd-core.c +++ b/drivers/mfd/mfd-core.c @@ -399,6 +399,8 @@ int mfd_clone_cell(const char *cell, const char **clones, size_t n_clones) clones[i]); } + put_device(dev); + return 0; } EXPORT_SYMBOL(mfd_clone_cell); diff --git a/drivers/mfd/stmpe.c b/drivers/mfd/stmpe.c index cfdae8a3d779..b0c7bcdaf5df 100644 --- a/drivers/mfd/stmpe.c +++ b/drivers/mfd/stmpe.c @@ -851,6 +851,8 @@ static int stmpe_reset(struct stmpe *stmpe) if (ret < 0) return ret; + msleep(10); + timeout = jiffies + msecs_to_jiffies(100); while (time_before(jiffies, timeout)) { ret = __stmpe_reg_read(stmpe, stmpe->regs[STMPE_IDX_SYS_CTRL]); diff --git a/drivers/net/can/sja1000/plx_pci.c b/drivers/net/can/sja1000/plx_pci.c index 3eb7430dffbf..f8ff25c8ee2e 100644 --- a/drivers/net/can/sja1000/plx_pci.c +++ b/drivers/net/can/sja1000/plx_pci.c @@ -142,6 +142,9 @@ struct plx_pci_card { #define CTI_PCI_VENDOR_ID 0x12c4 #define CTI_PCI_DEVICE_ID_CRG001 0x0900 +#define MOXA_PCI_VENDOR_ID 0x1393 +#define MOXA_PCI_DEVICE_ID 0x0100 + static void plx_pci_reset_common(struct pci_dev *pdev); static void plx9056_pci_reset_common(struct pci_dev *pdev); static void plx_pci_reset_marathon_pci(struct pci_dev *pdev); @@ -258,6 +261,14 @@ static struct plx_pci_card_info plx_pci_card_info_elcus = { /* based on PLX9030 */ }; +static struct plx_pci_card_info plx_pci_card_info_moxa = { + "MOXA", 2, + PLX_PCI_CAN_CLOCK, PLX_PCI_OCR, PLX_PCI_CDR, + {0, 0x00, 0x00}, { {0, 0x00, 0x80}, {1, 0x00, 0x80} }, + &plx_pci_reset_common + /* based on PLX9052 */ +}; + static const struct pci_device_id plx_pci_tbl[] = { { /* Adlink PCI-7841/cPCI-7841 */ @@ -357,6 +368,13 @@ static const struct pci_device_id plx_pci_tbl[] = { 0, 0, (kernel_ulong_t)&plx_pci_card_info_elcus }, + { + /* moxa */ + MOXA_PCI_VENDOR_ID, MOXA_PCI_DEVICE_ID, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + (kernel_ulong_t)&plx_pci_card_info_moxa + }, { 0,} }; MODULE_DEVICE_TABLE(pci, plx_pci_tbl); diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c index c481f104a8fe..5390ae89136c 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c @@ -204,17 +204,6 @@ static u32 xgene_enet_ring_len(struct xgene_enet_desc_ring *ring) return num_msgs; } -static void xgene_enet_setup_coalescing(struct xgene_enet_desc_ring *ring) -{ - u32 data = 0x7777; - - xgene_enet_ring_wr32(ring, CSR_PBM_COAL, 0x8e); - xgene_enet_ring_wr32(ring, CSR_PBM_CTICK1, data); - xgene_enet_ring_wr32(ring, CSR_PBM_CTICK2, data << 16); - xgene_enet_ring_wr32(ring, CSR_THRESHOLD0_SET1, 0x40); - xgene_enet_ring_wr32(ring, CSR_THRESHOLD1_SET1, 0x80); -} - void xgene_enet_parse_error(struct xgene_enet_desc_ring *ring, struct xgene_enet_pdata *pdata, enum xgene_enet_err_code status) @@ -929,5 +918,4 @@ struct xgene_ring_ops xgene_ring1_ops = { .clear = xgene_enet_clear_ring, .wr_cmd = xgene_enet_wr_cmd, .len = xgene_enet_ring_len, - .coalesce = xgene_enet_setup_coalescing, }; diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h index 8456337a237d..06e598c8bc16 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h @@ -55,8 +55,10 @@ enum xgene_enet_rm { #define PREFETCH_BUF_EN BIT(21) #define CSR_RING_ID_BUF 0x000c #define CSR_PBM_COAL 0x0014 +#define CSR_PBM_CTICK0 0x0018 #define CSR_PBM_CTICK1 0x001c #define CSR_PBM_CTICK2 0x0020 +#define CSR_PBM_CTICK3 0x0024 #define CSR_THRESHOLD0_SET1 0x0030 #define CSR_THRESHOLD1_SET1 0x0034 #define CSR_RING_NE_INT_MODE 0x017c diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index 429f18fc5503..8158d4698734 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -1188,7 +1188,8 @@ static int xgene_enet_create_desc_rings(struct net_device *ndev) tx_ring->dst_ring_num = xgene_enet_dst_ring_num(cp_ring); } - pdata->ring_ops->coalesce(pdata->tx_ring[0]); + if (pdata->ring_ops->coalesce) + pdata->ring_ops->coalesce(pdata->tx_ring[0]); pdata->tx_qcnt_hi = pdata->tx_ring[0]->slots - 128; return 0; diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_ring2.c b/drivers/net/ethernet/apm/xgene/xgene_enet_ring2.c index 2b76732add5d..af51dd5844ce 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_ring2.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_ring2.c @@ -30,7 +30,7 @@ static void xgene_enet_ring_init(struct xgene_enet_desc_ring *ring) ring_cfg[0] |= SET_VAL(X2_INTLINE, ring->id & RING_BUFNUM_MASK); ring_cfg[3] |= SET_BIT(X2_DEQINTEN); } - ring_cfg[0] |= SET_VAL(X2_CFGCRID, 1); + ring_cfg[0] |= SET_VAL(X2_CFGCRID, 2); addr >>= 8; ring_cfg[2] |= QCOHERENT | SET_VAL(RINGADDRL, addr); @@ -192,13 +192,15 @@ static u32 xgene_enet_ring_len(struct xgene_enet_desc_ring *ring) static void xgene_enet_setup_coalescing(struct xgene_enet_desc_ring *ring) { - u32 data = 0x7777; + u32 data = 0x77777777; xgene_enet_ring_wr32(ring, CSR_PBM_COAL, 0x8e); + xgene_enet_ring_wr32(ring, CSR_PBM_CTICK0, data); xgene_enet_ring_wr32(ring, CSR_PBM_CTICK1, data); - xgene_enet_ring_wr32(ring, CSR_PBM_CTICK2, data << 16); - xgene_enet_ring_wr32(ring, CSR_THRESHOLD0_SET1, 0x40); - xgene_enet_ring_wr32(ring, CSR_THRESHOLD1_SET1, 0x80); + xgene_enet_ring_wr32(ring, CSR_PBM_CTICK2, data); + xgene_enet_ring_wr32(ring, CSR_PBM_CTICK3, data); + xgene_enet_ring_wr32(ring, CSR_THRESHOLD0_SET1, 0x08); + xgene_enet_ring_wr32(ring, CSR_THRESHOLD1_SET1, 0x10); } struct xgene_ring_ops xgene_ring2_ops = { diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index 31ca204b38d2..49f4cafe5438 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -307,6 +307,10 @@ static void bgmac_dma_rx_enable(struct bgmac *bgmac, u32 ctl; ctl = bgmac_read(bgmac, ring->mmio_base + BGMAC_DMA_RX_CTL); + + /* preserve ONLY bits 16-17 from current hardware value */ + ctl &= BGMAC_DMA_RX_ADDREXT_MASK; + if (bgmac->feature_flags & BGMAC_FEAT_RX_MASK_SETUP) { ctl &= ~BGMAC_DMA_RX_BL_MASK; ctl |= BGMAC_DMA_RX_BL_128 << BGMAC_DMA_RX_BL_SHIFT; @@ -317,7 +321,6 @@ static void bgmac_dma_rx_enable(struct bgmac *bgmac, ctl &= ~BGMAC_DMA_RX_PT_MASK; ctl |= BGMAC_DMA_RX_PT_1 << BGMAC_DMA_RX_PT_SHIFT; } - ctl &= BGMAC_DMA_RX_ADDREXT_MASK; ctl |= BGMAC_DMA_RX_ENABLE; ctl |= BGMAC_DMA_RX_PARITY_DISABLE; ctl |= BGMAC_DMA_RX_OVERFLOW_CONT; @@ -1046,9 +1049,9 @@ static void bgmac_enable(struct bgmac *bgmac) mode = (bgmac_read(bgmac, BGMAC_DEV_STATUS) & BGMAC_DS_MM_MASK) >> BGMAC_DS_MM_SHIFT; - if (!(bgmac->feature_flags & BGMAC_FEAT_CLKCTLST) || mode != 0) + if (bgmac->feature_flags & BGMAC_FEAT_CLKCTLST || mode != 0) bgmac_set(bgmac, BCMA_CLKCTLST, BCMA_CLKCTLST_FORCEHT); - if (bgmac->feature_flags & BGMAC_FEAT_CLKCTLST && mode == 2) + if (!(bgmac->feature_flags & BGMAC_FEAT_CLKCTLST) && mode == 2) bgmac_cco_ctl_maskset(bgmac, 1, ~0, BGMAC_CHIPCTL_1_RXC_DLL_BYPASS); diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index b3791b394715..1f7034d739b0 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -49,6 +49,7 @@ #include #include #include +#include #if IS_ENABLED(CONFIG_CNIC) #define BCM_CNIC 1 @@ -4764,15 +4765,16 @@ bnx2_setup_msix_tbl(struct bnx2 *bp) BNX2_WR(bp, BNX2_PCI_GRC_WINDOW3_ADDR, BNX2_MSIX_PBA_ADDR); } -static int -bnx2_reset_chip(struct bnx2 *bp, u32 reset_code) +static void +bnx2_wait_dma_complete(struct bnx2 *bp) { u32 val; - int i, rc = 0; - u8 old_port; + int i; - /* Wait for the current PCI transaction to complete before - * issuing a reset. */ + /* + * Wait for the current PCI transaction to complete before + * issuing a reset. + */ if ((BNX2_CHIP(bp) == BNX2_CHIP_5706) || (BNX2_CHIP(bp) == BNX2_CHIP_5708)) { BNX2_WR(bp, BNX2_MISC_ENABLE_CLR_BITS, @@ -4796,6 +4798,21 @@ bnx2_reset_chip(struct bnx2 *bp, u32 reset_code) } } + return; +} + + +static int +bnx2_reset_chip(struct bnx2 *bp, u32 reset_code) +{ + u32 val; + int i, rc = 0; + u8 old_port; + + /* Wait for the current PCI transaction to complete before + * issuing a reset. */ + bnx2_wait_dma_complete(bp); + /* Wait for the firmware to tell us it is ok to issue a reset. */ bnx2_fw_sync(bp, BNX2_DRV_MSG_DATA_WAIT0 | reset_code, 1, 1); @@ -6361,6 +6378,10 @@ bnx2_open(struct net_device *dev) struct bnx2 *bp = netdev_priv(dev); int rc; + rc = bnx2_request_firmware(bp); + if (rc < 0) + goto out; + netif_carrier_off(dev); bnx2_disable_int(bp); @@ -6429,6 +6450,7 @@ open_err: bnx2_free_irq(bp); bnx2_free_mem(bp); bnx2_del_napi(bp); + bnx2_release_firmware(bp); goto out; } @@ -8575,12 +8597,15 @@ bnx2_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_drvdata(pdev, dev); - rc = bnx2_request_firmware(bp); - if (rc < 0) - goto error; + /* + * In-flight DMA from 1st kernel could continue going in kdump kernel. + * New io-page table has been created before bnx2 does reset at open stage. + * We have to wait for the in-flight DMA to complete to avoid it look up + * into the newly created io-page table. + */ + if (is_kdump_kernel()) + bnx2_wait_dma_complete(bp); - - bnx2_reset_chip(bp, BNX2_DRV_MSG_CODE_RESET); memcpy(dev->dev_addr, bp->mac_addr, ETH_ALEN); dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_SG | @@ -8613,7 +8638,6 @@ bnx2_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) return 0; error: - bnx2_release_firmware(bp); pci_iounmap(pdev, bp->regview); pci_release_regions(pdev); pci_disable_device(pdev); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index a9f9f3738022..c6909660e097 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -6309,6 +6309,7 @@ static int bnxt_setup_tc(struct net_device *dev, u32 handle, __be16 proto, struct tc_to_netdev *ntc) { struct bnxt *bp = netdev_priv(dev); + bool sh = false; u8 tc; if (ntc->type != TC_SETUP_MQPRIO) @@ -6325,12 +6326,11 @@ static int bnxt_setup_tc(struct net_device *dev, u32 handle, __be16 proto, if (netdev_get_num_tc(dev) == tc) return 0; + if (bp->flags & BNXT_FLAG_SHARED_RINGS) + sh = true; + if (tc) { int max_rx_rings, max_tx_rings, rc; - bool sh = false; - - if (bp->flags & BNXT_FLAG_SHARED_RINGS) - sh = true; rc = bnxt_get_max_rings(bp, &max_rx_rings, &max_tx_rings, sh); if (rc || bp->tx_nr_rings_per_tc * tc > max_tx_rings) @@ -6348,7 +6348,8 @@ static int bnxt_setup_tc(struct net_device *dev, u32 handle, __be16 proto, bp->tx_nr_rings = bp->tx_nr_rings_per_tc; netdev_reset_tc(dev); } - bp->cp_nr_rings = max_t(int, bp->tx_nr_rings, bp->rx_nr_rings); + bp->cp_nr_rings = sh ? max_t(int, bp->tx_nr_rings, bp->rx_nr_rings) : + bp->tx_nr_rings + bp->rx_nr_rings; bp->num_stat_ctxs = bp->cp_nr_rings; if (netif_running(bp->dev)) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index ec6cd18842c3..60e2af8678bd 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -774,8 +774,8 @@ static int bnxt_vf_set_link(struct bnxt *bp, struct bnxt_vf_info *vf) if (vf->flags & BNXT_VF_LINK_UP) { /* if physical link is down, force link up on VF */ - if (phy_qcfg_resp.link == - PORT_PHY_QCFG_RESP_LINK_NO_LINK) { + if (phy_qcfg_resp.link != + PORT_PHY_QCFG_RESP_LINK_LINK) { phy_qcfg_resp.link = PORT_PHY_QCFG_RESP_LINK_LINK; phy_qcfg_resp.link_speed = cpu_to_le16( diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c index f9df4b5ae90e..f42f672b0e7e 100644 --- a/drivers/net/ethernet/brocade/bna/bnad.c +++ b/drivers/net/ethernet/brocade/bna/bnad.c @@ -177,6 +177,7 @@ bnad_txcmpl_process(struct bnad *bnad, struct bna_tcb *tcb) return 0; hw_cons = *(tcb->hw_consumer_index); + rmb(); cons = tcb->consumer_index; q_depth = tcb->q_depth; @@ -3094,7 +3095,7 @@ bnad_start_xmit(struct sk_buff *skb, struct net_device *netdev) BNA_QE_INDX_INC(prod, q_depth); tcb->producer_index = prod; - smp_mb(); + wmb(); if (unlikely(!test_bit(BNAD_TXQ_TX_STARTED, &tcb->flags))) return NETDEV_TX_OK; @@ -3102,7 +3103,6 @@ bnad_start_xmit(struct sk_buff *skb, struct net_device *netdev) skb_tx_timestamp(skb); bna_txq_prod_indx_doorbell(tcb); - smp_mb(); return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h index 50812a1d67bd..df1573c4a659 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h @@ -178,9 +178,9 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN CH_PCI_ID_TABLE_FENTRY(0x6005), CH_PCI_ID_TABLE_FENTRY(0x6006), CH_PCI_ID_TABLE_FENTRY(0x6007), + CH_PCI_ID_TABLE_FENTRY(0x6008), CH_PCI_ID_TABLE_FENTRY(0x6009), CH_PCI_ID_TABLE_FENTRY(0x600d), - CH_PCI_ID_TABLE_FENTRY(0x6010), CH_PCI_ID_TABLE_FENTRY(0x6011), CH_PCI_ID_TABLE_FENTRY(0x6014), CH_PCI_ID_TABLE_FENTRY(0x6015), diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c index c54c6fac0d1d..b6ed818f78ff 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.c +++ b/drivers/net/ethernet/hisilicon/hns/hnae.c @@ -332,8 +332,10 @@ struct hnae_handle *hnae_get_handle(struct device *owner_dev, return ERR_PTR(-ENODEV); handle = dev->ops->get_handle(dev, port_id); - if (IS_ERR(handle)) + if (IS_ERR(handle)) { + put_device(&dev->cls_dev); return handle; + } handle->dev = dev; handle->owner_dev = owner_dev; @@ -356,6 +358,8 @@ out_when_init_queue: for (j = i - 1; j >= 0; j--) hnae_fini_queue(handle->qs[j]); + put_device(&dev->cls_dev); + return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL(hnae_get_handle); @@ -377,6 +381,8 @@ void hnae_put_handle(struct hnae_handle *h) dev->ops->put_handle(h); module_put(dev->owner); + + put_device(&dev->cls_dev); } EXPORT_SYMBOL(hnae_put_handle); diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c index 54efa9a5167b..bd719e25dd76 100644 --- a/drivers/net/ethernet/ibm/ehea/ehea_main.c +++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c @@ -2446,6 +2446,8 @@ static int ehea_open(struct net_device *dev) netif_info(port, ifup, dev, "enabling port\n"); + netif_carrier_off(dev); + ret = ehea_up(dev); if (!ret) { port_napi_enable(port); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 5f44c5520fbc..4f3281a03e7e 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1505,9 +1505,8 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry) adapter->max_rx_add_entries_per_subcrq > entries_page ? entries_page : adapter->max_rx_add_entries_per_subcrq; - /* Choosing the maximum number of queues supported by firmware*/ - adapter->req_tx_queues = adapter->max_tx_queues; - adapter->req_rx_queues = adapter->max_rx_queues; + adapter->req_tx_queues = adapter->opt_tx_comp_sub_queues; + adapter->req_rx_queues = adapter->opt_rx_comp_queues; adapter->req_rx_add_queues = adapter->max_rx_add_queues; adapter->req_mtu = adapter->max_mtu; @@ -3706,7 +3705,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) struct net_device *netdev; unsigned char *mac_addr_p; struct dentry *ent; - char buf[16]; /* debugfs name buf */ + char buf[17]; /* debugfs name buf */ int rc; dev_dbg(&dev->dev, "entering ibmvnic_probe for UA 0x%x\n", @@ -3845,6 +3844,9 @@ static int ibmvnic_remove(struct vio_dev *dev) if (adapter->debugfs_dir && !IS_ERR(adapter->debugfs_dir)) debugfs_remove_recursive(adapter->debugfs_dir); + dma_unmap_single(&dev->dev, adapter->stats_token, + sizeof(struct ibmvnic_statistics), DMA_FROM_DEVICE); + if (adapter->ras_comps) dma_free_coherent(&dev->dev, adapter->ras_comp_num * diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index bf5cc55ba24c..5b12022adf1f 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -1381,6 +1381,7 @@ static unsigned int get_rx_coal(struct mv643xx_eth_private *mp) temp = (val & 0x003fff00) >> 8; temp *= 64000000; + temp += mp->t_clk / 2; do_div(temp, mp->t_clk); return (unsigned int)temp; @@ -1417,6 +1418,7 @@ static unsigned int get_tx_coal(struct mv643xx_eth_private *mp) temp = (rdlp(mp, TX_FIFO_URGENT_THRESHOLD) & 0x3fff0) >> 4; temp *= 64000000; + temp += mp->t_clk / 2; do_div(temp, mp->t_clk); return (unsigned int)temp; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 12c99a2655f2..3a47e83d3e07 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2202,7 +2202,6 @@ void mlx4_en_destroy_netdev(struct net_device *dev) if (!shutdown) free_netdev(dev); - dev->ethtool_ops = NULL; } static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index f4c687ce4c59..84e8b250e2af 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1445,6 +1445,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, c->netdev = priv->netdev; c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key); c->num_tc = priv->params.num_tc; + c->xdp = !!priv->xdp_prog; if (priv->params.rx_am_enabled) rx_cq_profile = mlx5e_am_get_def_profile(priv->params.rx_cq_period_mode); @@ -1468,6 +1469,12 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, if (err) goto err_close_tx_cqs; + /* XDP SQ CQ params are same as normal TXQ sq CQ params */ + err = c->xdp ? mlx5e_open_cq(c, &cparam->tx_cq, &c->xdp_sq.cq, + priv->params.tx_cq_moderation) : 0; + if (err) + goto err_close_rx_cq; + napi_enable(&c->napi); err = mlx5e_open_sq(c, 0, &cparam->icosq, &c->icosq); @@ -1488,21 +1495,10 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, } } - if (priv->xdp_prog) { - /* XDP SQ CQ params are same as normal TXQ sq CQ params */ - err = mlx5e_open_cq(c, &cparam->tx_cq, &c->xdp_sq.cq, - priv->params.tx_cq_moderation); - if (err) - goto err_close_sqs; + err = c->xdp ? mlx5e_open_sq(c, 0, &cparam->xdp_sq, &c->xdp_sq) : 0; + if (err) + goto err_close_sqs; - err = mlx5e_open_sq(c, 0, &cparam->xdp_sq, &c->xdp_sq); - if (err) { - mlx5e_close_cq(&c->xdp_sq.cq); - goto err_close_sqs; - } - } - - c->xdp = !!priv->xdp_prog; err = mlx5e_open_rq(c, &cparam->rq, &c->rq); if (err) goto err_close_xdp_sq; @@ -1512,7 +1508,8 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, return 0; err_close_xdp_sq: - mlx5e_close_sq(&c->xdp_sq); + if (c->xdp) + mlx5e_close_sq(&c->xdp_sq); err_close_sqs: mlx5e_close_sqs(c); @@ -1522,6 +1519,10 @@ err_close_icosq: err_disable_napi: napi_disable(&c->napi); + if (c->xdp) + mlx5e_close_cq(&c->xdp_sq.cq); + +err_close_rx_cq: mlx5e_close_cq(&c->rq.cq); err_close_tx_cqs: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 7fe6559e4ab3..bf1c09ca73c0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -308,7 +308,7 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev) netdev->switchdev_ops = &mlx5e_rep_switchdev_ops; #endif - netdev->features |= NETIF_F_VLAN_CHALLENGED | NETIF_F_HW_TC; + netdev->features |= NETIF_F_VLAN_CHALLENGED | NETIF_F_HW_TC | NETIF_F_NETNS_LOCAL; netdev->hw_features |= NETIF_F_HW_TC; eth_hw_addr_random(netdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index ce8c54d18906..6bb21b31cfeb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -237,12 +237,15 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec skb_flow_dissector_target(f->dissector, FLOW_DISSECTOR_KEY_VLAN, f->mask); - if (mask->vlan_id) { + if (mask->vlan_id || mask->vlan_priority) { MLX5_SET(fte_match_set_lyr_2_4, headers_c, vlan_tag, 1); MLX5_SET(fte_match_set_lyr_2_4, headers_v, vlan_tag, 1); MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_vid, mask->vlan_id); MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_vid, key->vlan_id); + + MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_prio, mask->vlan_priority); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_prio, key->vlan_priority); } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index c55ad8d00c05..d239f5d0ea36 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -57,7 +57,8 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, if (esw->mode != SRIOV_OFFLOADS) return ERR_PTR(-EOPNOTSUPP); - action = attr->action; + /* per flow vlan pop/push is emulated, don't set that into the firmware */ + action = attr->action & ~(MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH | MLX5_FLOW_CONTEXT_ACTION_VLAN_POP); if (action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) { dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 89696048b045..914e5466f729 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1690,7 +1690,7 @@ static int init_root_ns(struct mlx5_flow_steering *steering) { steering->root_ns = create_root_ns(steering, FS_FT_NIC_RX); - if (IS_ERR_OR_NULL(steering->root_ns)) + if (!steering->root_ns) goto cleanup; if (init_root_tree(steering, &root_fs, &steering->root_ns->ns.node)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index d5433c49b2b0..3eb931585b3e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1226,6 +1226,9 @@ static int init_one(struct pci_dev *pdev, pci_set_drvdata(pdev, dev); + dev->pdev = pdev; + dev->event = mlx5_core_event; + if (prof_sel < 0 || prof_sel >= ARRAY_SIZE(profile)) { mlx5_core_warn(dev, "selected profile out of range, selecting default (%d)\n", @@ -1233,8 +1236,6 @@ static int init_one(struct pci_dev *pdev, prof_sel = MLX5_DEFAULT_PROF; } dev->profile = &profile[prof_sel]; - dev->pdev = pdev; - dev->event = mlx5_core_event; INIT_LIST_HEAD(&priv->ctx_list); spin_lock_init(&priv->ctx_lock); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 1ec0a4ce3c46..dda5761e91bc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -231,7 +231,7 @@ mlxsw_sp_span_entry_create(struct mlxsw_sp_port *port) span_entry->used = true; span_entry->id = index; - span_entry->ref_count = 0; + span_entry->ref_count = 1; span_entry->local_port = local_port; return span_entry; } @@ -270,6 +270,7 @@ static struct mlxsw_sp_span_entry span_entry = mlxsw_sp_span_entry_find(port); if (span_entry) { + /* Already exists, just take a reference */ span_entry->ref_count++; return span_entry; } @@ -280,6 +281,7 @@ static struct mlxsw_sp_span_entry static int mlxsw_sp_span_entry_put(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_span_entry *span_entry) { + WARN_ON(!span_entry->ref_count); if (--span_entry->ref_count == 0) mlxsw_sp_span_entry_destroy(mlxsw_sp, span_entry); return 0; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 9b22863a924b..97bbc1d21df8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -115,7 +115,7 @@ struct mlxsw_sp_rif { struct mlxsw_sp_mid { struct list_head list; unsigned char addr[ETH_ALEN]; - u16 vid; + u16 fid; u16 mid; unsigned int ref_count; }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 4573da2c5560..e83072da6272 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -594,21 +594,22 @@ static int mlxsw_sp_vrs_init(struct mlxsw_sp *mlxsw_sp) return 0; } +static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp); + static void mlxsw_sp_vrs_fini(struct mlxsw_sp *mlxsw_sp) { + mlxsw_sp_router_fib_flush(mlxsw_sp); kfree(mlxsw_sp->router.vrs); } struct mlxsw_sp_neigh_key { - unsigned char addr[sizeof(struct in6_addr)]; - struct net_device *dev; + struct neighbour *n; }; struct mlxsw_sp_neigh_entry { struct rhash_head ht_node; struct mlxsw_sp_neigh_key key; u16 rif; - struct neighbour *n; bool offloaded; struct delayed_work dw; struct mlxsw_sp_port *mlxsw_sp_port; @@ -646,19 +647,15 @@ mlxsw_sp_neigh_entry_remove(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp_router_neigh_update_hw(struct work_struct *work); static struct mlxsw_sp_neigh_entry * -mlxsw_sp_neigh_entry_create(const void *addr, size_t addr_len, - struct net_device *dev, u16 rif, - struct neighbour *n) +mlxsw_sp_neigh_entry_create(struct neighbour *n, u16 rif) { struct mlxsw_sp_neigh_entry *neigh_entry; neigh_entry = kzalloc(sizeof(*neigh_entry), GFP_ATOMIC); if (!neigh_entry) return NULL; - memcpy(neigh_entry->key.addr, addr, addr_len); - neigh_entry->key.dev = dev; + neigh_entry->key.n = n; neigh_entry->rif = rif; - neigh_entry->n = n; INIT_DELAYED_WORK(&neigh_entry->dw, mlxsw_sp_router_neigh_update_hw); INIT_LIST_HEAD(&neigh_entry->nexthop_list); return neigh_entry; @@ -671,13 +668,11 @@ mlxsw_sp_neigh_entry_destroy(struct mlxsw_sp_neigh_entry *neigh_entry) } static struct mlxsw_sp_neigh_entry * -mlxsw_sp_neigh_entry_lookup(struct mlxsw_sp *mlxsw_sp, const void *addr, - size_t addr_len, struct net_device *dev) +mlxsw_sp_neigh_entry_lookup(struct mlxsw_sp *mlxsw_sp, struct neighbour *n) { - struct mlxsw_sp_neigh_key key = {{ 0 } }; + struct mlxsw_sp_neigh_key key; - memcpy(key.addr, addr, addr_len); - key.dev = dev; + key.n = n; return rhashtable_lookup_fast(&mlxsw_sp->router.neigh_ht, &key, mlxsw_sp_neigh_ht_params); } @@ -689,26 +684,20 @@ int mlxsw_sp_router_neigh_construct(struct net_device *dev, struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; struct mlxsw_sp_neigh_entry *neigh_entry; struct mlxsw_sp_rif *r; - u32 dip; int err; if (n->tbl != &arp_tbl) return 0; - dip = ntohl(*((__be32 *) n->primary_key)); - neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, &dip, sizeof(dip), - n->dev); - if (neigh_entry) { - WARN_ON(neigh_entry->n != n); + neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, n); + if (neigh_entry) return 0; - } r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, n->dev); if (WARN_ON(!r)) return -EINVAL; - neigh_entry = mlxsw_sp_neigh_entry_create(&dip, sizeof(dip), n->dev, - r->rif, n); + neigh_entry = mlxsw_sp_neigh_entry_create(n, r->rif); if (!neigh_entry) return -ENOMEM; err = mlxsw_sp_neigh_entry_insert(mlxsw_sp, neigh_entry); @@ -727,14 +716,11 @@ void mlxsw_sp_router_neigh_destroy(struct net_device *dev, struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; struct mlxsw_sp_neigh_entry *neigh_entry; - u32 dip; if (n->tbl != &arp_tbl) return; - dip = ntohl(*((__be32 *) n->primary_key)); - neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, &dip, sizeof(dip), - n->dev); + neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, n); if (!neigh_entry) return; mlxsw_sp_neigh_entry_remove(mlxsw_sp, neigh_entry); @@ -817,6 +803,26 @@ static void mlxsw_sp_router_neigh_rec_process(struct mlxsw_sp *mlxsw_sp, } } +static bool mlxsw_sp_router_rauhtd_is_full(char *rauhtd_pl) +{ + u8 num_rec, last_rec_index, num_entries; + + num_rec = mlxsw_reg_rauhtd_num_rec_get(rauhtd_pl); + last_rec_index = num_rec - 1; + + if (num_rec < MLXSW_REG_RAUHTD_REC_MAX_NUM) + return false; + if (mlxsw_reg_rauhtd_rec_type_get(rauhtd_pl, last_rec_index) == + MLXSW_REG_RAUHTD_TYPE_IPV6) + return true; + + num_entries = mlxsw_reg_rauhtd_ipv4_rec_num_entries_get(rauhtd_pl, + last_rec_index); + if (++num_entries == MLXSW_REG_RAUHTD_IPV4_ENT_PER_REC) + return true; + return false; +} + static int mlxsw_sp_router_neighs_update_rauhtd(struct mlxsw_sp *mlxsw_sp) { char *rauhtd_pl; @@ -843,7 +849,7 @@ static int mlxsw_sp_router_neighs_update_rauhtd(struct mlxsw_sp *mlxsw_sp) for (i = 0; i < num_rec; i++) mlxsw_sp_router_neigh_rec_process(mlxsw_sp, rauhtd_pl, i); - } while (num_rec); + } while (mlxsw_sp_router_rauhtd_is_full(rauhtd_pl)); rtnl_unlock(); kfree(rauhtd_pl); @@ -862,7 +868,7 @@ static void mlxsw_sp_router_neighs_update_nh(struct mlxsw_sp *mlxsw_sp) * is active regardless of the traffic. */ if (!list_empty(&neigh_entry->nexthop_list)) - neigh_event_send(neigh_entry->n, NULL); + neigh_event_send(neigh_entry->key.n, NULL); } rtnl_unlock(); } @@ -908,9 +914,9 @@ static void mlxsw_sp_router_probe_unresolved_nexthops(struct work_struct *work) rtnl_lock(); list_for_each_entry(neigh_entry, &mlxsw_sp->router.nexthop_neighs_list, nexthop_neighs_list_node) { - if (!(neigh_entry->n->nud_state & NUD_VALID) && + if (!(neigh_entry->key.n->nud_state & NUD_VALID) && !list_empty(&neigh_entry->nexthop_list)) - neigh_event_send(neigh_entry->n, NULL); + neigh_event_send(neigh_entry->key.n, NULL); } rtnl_unlock(); @@ -927,7 +933,7 @@ static void mlxsw_sp_router_neigh_update_hw(struct work_struct *work) { struct mlxsw_sp_neigh_entry *neigh_entry = container_of(work, struct mlxsw_sp_neigh_entry, dw.work); - struct neighbour *n = neigh_entry->n; + struct neighbour *n = neigh_entry->key.n; struct mlxsw_sp_port *mlxsw_sp_port = neigh_entry->mlxsw_sp_port; struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; char rauht_pl[MLXSW_REG_RAUHT_LEN]; @@ -1030,11 +1036,8 @@ int mlxsw_sp_router_netevent_event(struct notifier_block *unused, mlxsw_sp = mlxsw_sp_port->mlxsw_sp; dip = ntohl(*((__be32 *) n->primary_key)); - neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, - &dip, - sizeof(__be32), - dev); - if (WARN_ON(!neigh_entry) || WARN_ON(neigh_entry->n != n)) { + neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, n); + if (WARN_ON(!neigh_entry)) { mlxsw_sp_port_dev_put(mlxsw_sp_port); return NOTIFY_DONE; } @@ -1343,33 +1346,26 @@ static int mlxsw_sp_nexthop_init(struct mlxsw_sp *mlxsw_sp, struct fib_nh *fib_nh) { struct mlxsw_sp_neigh_entry *neigh_entry; - u32 gwip = ntohl(fib_nh->nh_gw); struct net_device *dev = fib_nh->nh_dev; struct neighbour *n; u8 nud_state; - neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, &gwip, - sizeof(gwip), dev); - if (!neigh_entry) { - __be32 gwipn = htonl(gwip); - - n = neigh_create(&arp_tbl, &gwipn, dev); + /* Take a reference of neigh here ensuring that neigh would + * not be detructed before the nexthop entry is finished. + * The reference is taken either in neigh_lookup() or + * in neith_create() in case n is not found. + */ + n = neigh_lookup(&arp_tbl, &fib_nh->nh_gw, dev); + if (!n) { + n = neigh_create(&arp_tbl, &fib_nh->nh_gw, dev); if (IS_ERR(n)) return PTR_ERR(n); neigh_event_send(n, NULL); - neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, &gwip, - sizeof(gwip), dev); - if (!neigh_entry) { - neigh_release(n); - return -EINVAL; - } - } else { - /* Take a reference of neigh here ensuring that neigh would - * not be detructed before the nexthop entry is finished. - * The second branch takes the reference in neith_create() - */ - n = neigh_entry->n; - neigh_clone(n); + } + neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, n); + if (!neigh_entry) { + neigh_release(n); + return -EINVAL; } /* If that is the first nexthop connected to that neigh, add to @@ -1403,7 +1399,7 @@ static void mlxsw_sp_nexthop_fini(struct mlxsw_sp *mlxsw_sp, if (list_empty(&nh->neigh_entry->nexthop_list)) list_del(&nh->neigh_entry->nexthop_neighs_list_node); - neigh_release(neigh_entry->n); + neigh_release(neigh_entry->key.n); } static struct mlxsw_sp_nexthop_group * @@ -1463,11 +1459,11 @@ static bool mlxsw_sp_nexthop_match(struct mlxsw_sp_nexthop *nh, for (i = 0; i < fi->fib_nhs; i++) { struct fib_nh *fib_nh = &fi->fib_nh[i]; - u32 gwip = ntohl(fib_nh->nh_gw); + struct neighbour *n = nh->neigh_entry->key.n; - if (memcmp(nh->neigh_entry->key.addr, - &gwip, sizeof(u32)) == 0 && - nh->neigh_entry->key.dev == fib_nh->nh_dev) + if (memcmp(n->primary_key, &fib_nh->nh_gw, + sizeof(fib_nh->nh_gw)) == 0 && + n->dev == fib_nh->nh_dev) return true; } return false; @@ -1874,18 +1870,18 @@ static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp) return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); } -static void mlxsw_sp_router_fib4_abort(struct mlxsw_sp *mlxsw_sp) +static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp) { struct mlxsw_resources *resources; struct mlxsw_sp_fib_entry *fib_entry; struct mlxsw_sp_fib_entry *tmp; struct mlxsw_sp_vr *vr; int i; - int err; resources = mlxsw_core_resources_get(mlxsw_sp->core); for (i = 0; i < resources->max_virtual_routers; i++) { vr = &mlxsw_sp->router.vrs[i]; + if (!vr->used) continue; @@ -1901,6 +1897,13 @@ static void mlxsw_sp_router_fib4_abort(struct mlxsw_sp *mlxsw_sp) break; } } +} + +static void mlxsw_sp_router_fib4_abort(struct mlxsw_sp *mlxsw_sp) +{ + int err; + + mlxsw_sp_router_fib_flush(mlxsw_sp); mlxsw_sp->router.aborted = true; err = mlxsw_sp_router_set_abort_trap(mlxsw_sp); if (err) @@ -1958,6 +1961,9 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, struct fib_entry_notifier_info *fen_info = ptr; int err; + if (!net_eq(fen_info->info.net, &init_net)) + return NOTIFY_DONE; + switch (event) { case FIB_EVENT_ENTRY_ADD: err = mlxsw_sp_router_fib4_add(mlxsw_sp, fen_info); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 5e00c79e8133..1e2c8eca3af1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -929,12 +929,12 @@ static int mlxsw_sp_port_smid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 mid, static struct mlxsw_sp_mid *__mlxsw_sp_mc_get(struct mlxsw_sp *mlxsw_sp, const unsigned char *addr, - u16 vid) + u16 fid) { struct mlxsw_sp_mid *mid; list_for_each_entry(mid, &mlxsw_sp->br_mids.list, list) { - if (ether_addr_equal(mid->addr, addr) && mid->vid == vid) + if (ether_addr_equal(mid->addr, addr) && mid->fid == fid) return mid; } return NULL; @@ -942,7 +942,7 @@ static struct mlxsw_sp_mid *__mlxsw_sp_mc_get(struct mlxsw_sp *mlxsw_sp, static struct mlxsw_sp_mid *__mlxsw_sp_mc_alloc(struct mlxsw_sp *mlxsw_sp, const unsigned char *addr, - u16 vid) + u16 fid) { struct mlxsw_sp_mid *mid; u16 mid_idx; @@ -958,7 +958,7 @@ static struct mlxsw_sp_mid *__mlxsw_sp_mc_alloc(struct mlxsw_sp *mlxsw_sp, set_bit(mid_idx, mlxsw_sp->br_mids.mapped); ether_addr_copy(mid->addr, addr); - mid->vid = vid; + mid->fid = fid; mid->mid = mid_idx; mid->ref_count = 0; list_add_tail(&mid->list, &mlxsw_sp->br_mids.list); @@ -991,9 +991,9 @@ static int mlxsw_sp_port_mdb_add(struct mlxsw_sp_port *mlxsw_sp_port, if (switchdev_trans_ph_prepare(trans)) return 0; - mid = __mlxsw_sp_mc_get(mlxsw_sp, mdb->addr, mdb->vid); + mid = __mlxsw_sp_mc_get(mlxsw_sp, mdb->addr, fid); if (!mid) { - mid = __mlxsw_sp_mc_alloc(mlxsw_sp, mdb->addr, mdb->vid); + mid = __mlxsw_sp_mc_alloc(mlxsw_sp, mdb->addr, fid); if (!mid) { netdev_err(dev, "Unable to allocate MC group\n"); return -ENOMEM; @@ -1137,7 +1137,7 @@ static int mlxsw_sp_port_mdb_del(struct mlxsw_sp_port *mlxsw_sp_port, u16 mid_idx; int err = 0; - mid = __mlxsw_sp_mc_get(mlxsw_sp, mdb->addr, mdb->vid); + mid = __mlxsw_sp_mc_get(mlxsw_sp, mdb->addr, fid); if (!mid) { netdev_err(dev, "Unable to remove port from MC DB\n"); return -EINVAL; diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 72eee29c677f..2777d5bb4380 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -727,9 +727,6 @@ struct core_tx_bd_flags { #define CORE_TX_BD_FLAGS_L4_PROTOCOL_SHIFT 6 #define CORE_TX_BD_FLAGS_L4_PSEUDO_CSUM_MODE_MASK 0x1 #define CORE_TX_BD_FLAGS_L4_PSEUDO_CSUM_MODE_SHIFT 7 -#define CORE_TX_BD_FLAGS_ROCE_FLAV_MASK 0x1 -#define CORE_TX_BD_FLAGS_ROCE_FLAV_SHIFT 12 - }; struct core_tx_bd { diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index 63e1a1b0ef8e..f95385cbbd40 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -1119,6 +1119,7 @@ static void qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn, start_bd->bd_flags.as_bitfield |= CORE_TX_BD_FLAGS_START_BD_MASK << CORE_TX_BD_FLAGS_START_BD_SHIFT; SET_FIELD(start_bd->bitfield0, CORE_TX_BD_NBDS, num_of_bds); + SET_FIELD(start_bd->bitfield0, CORE_TX_BD_ROCE_FLAV, type); DMA_REGPAIR_LE(start_bd->addr, first_frag); start_bd->nbytes = cpu_to_le16(first_frag_len); diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index c418360ba02a..333c7442e48a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -839,20 +839,19 @@ static void qed_update_pf_params(struct qed_dev *cdev, { int i; + if (IS_ENABLED(CONFIG_QED_RDMA)) { + params->rdma_pf_params.num_qps = QED_ROCE_QPS; + params->rdma_pf_params.min_dpis = QED_ROCE_DPIS; + /* divide by 3 the MRs to avoid MF ILT overflow */ + params->rdma_pf_params.num_mrs = RDMA_MAX_TIDS; + params->rdma_pf_params.gl_pi = QED_ROCE_PROTOCOL_INDEX; + } + for (i = 0; i < cdev->num_hwfns; i++) { struct qed_hwfn *p_hwfn = &cdev->hwfns[i]; p_hwfn->pf_params = *params; } - - if (!IS_ENABLED(CONFIG_QED_RDMA)) - return; - - params->rdma_pf_params.num_qps = QED_ROCE_QPS; - params->rdma_pf_params.min_dpis = QED_ROCE_DPIS; - /* divide by 3 the MRs to avoid MF ILT overflow */ - params->rdma_pf_params.num_mrs = RDMA_MAX_TIDS; - params->rdma_pf_params.gl_pi = QED_ROCE_PROTOCOL_INDEX; } static int qed_slowpath_start(struct qed_dev *cdev, diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index 12251a1032d1..7567cc464b88 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -175,16 +175,23 @@ static void qede_get_strings_stats(struct qede_dev *edev, u8 *buf) for (i = 0, k = 0; i < QEDE_QUEUE_CNT(edev); i++) { int tc; - for (j = 0; j < QEDE_NUM_RQSTATS; j++) - sprintf(buf + (k + j) * ETH_GSTRING_LEN, - "%d: %s", i, qede_rqstats_arr[j].string); - k += QEDE_NUM_RQSTATS; - for (tc = 0; tc < edev->num_tc; tc++) { - for (j = 0; j < QEDE_NUM_TQSTATS; j++) + if (edev->fp_array[i].type & QEDE_FASTPATH_RX) { + for (j = 0; j < QEDE_NUM_RQSTATS; j++) sprintf(buf + (k + j) * ETH_GSTRING_LEN, - "%d.%d: %s", i, tc, - qede_tqstats_arr[j].string); - k += QEDE_NUM_TQSTATS; + "%d: %s", i, + qede_rqstats_arr[j].string); + k += QEDE_NUM_RQSTATS; + } + + if (edev->fp_array[i].type & QEDE_FASTPATH_TX) { + for (tc = 0; tc < edev->num_tc; tc++) { + for (j = 0; j < QEDE_NUM_TQSTATS; j++) + sprintf(buf + (k + j) * + ETH_GSTRING_LEN, + "%d.%d: %s", i, tc, + qede_tqstats_arr[j].string); + k += QEDE_NUM_TQSTATS; + } } } diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 7def29aaf65c..85f46dbecd5b 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -2839,7 +2839,7 @@ static int qede_alloc_sge_mem(struct qede_dev *edev, struct qede_rx_queue *rxq) } mapping = dma_map_page(&edev->pdev->dev, replace_buf->data, 0, - rxq->rx_buf_size, DMA_FROM_DEVICE); + PAGE_SIZE, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(&edev->pdev->dev, mapping))) { DP_NOTICE(edev, "Failed to map TPA replacement buffer\n"); diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c index 6fb3bee904d3..0b4deb31e742 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c @@ -575,10 +575,11 @@ void emac_mac_start(struct emac_adapter *adpt) mac |= TXEN | RXEN; /* enable RX/TX */ - /* We don't have ethtool support yet, so force flow-control mode - * to 'full' always. - */ - mac |= TXFC | RXFC; + /* Configure MAC flow control to match the PHY's settings. */ + if (phydev->pause) + mac |= RXFC; + if (phydev->pause != phydev->asym_pause) + mac |= TXFC; /* setup link speed */ mac &= ~SPEED_MASK; @@ -1003,6 +1004,12 @@ int emac_mac_up(struct emac_adapter *adpt) writel((u32)~DIS_INT, adpt->base + EMAC_INT_STATUS); writel(adpt->irq.mask, adpt->base + EMAC_INT_MASK); + /* Enable pause frames. Without this feature, the EMAC has been shown + * to receive (and drop) frames with FCS errors at gigabit connections. + */ + adpt->phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; + adpt->phydev->advertising |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; + adpt->phydev->irq = PHY_IGNORE_INTERRUPT; phy_start(adpt->phydev); diff --git a/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c b/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c index 75c1b530e39e..72fe343c7a36 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c @@ -421,7 +421,7 @@ static const struct emac_reg_write sgmii_v2_laned[] = { /* CDR Settings */ {EMAC_SGMII_LN_UCDR_FO_GAIN_MODE0, UCDR_STEP_BY_TWO_MODE0 | UCDR_xO_GAIN_MODE(10)}, - {EMAC_SGMII_LN_UCDR_SO_GAIN_MODE0, UCDR_xO_GAIN_MODE(6)}, + {EMAC_SGMII_LN_UCDR_SO_GAIN_MODE0, UCDR_xO_GAIN_MODE(0)}, {EMAC_SGMII_LN_UCDR_SO_CONFIG, UCDR_ENABLE | UCDR_SO_SATURATION(12)}, /* TX/RX Settings */ diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 3cf3557106c2..6b89e4a7b164 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -485,6 +485,9 @@ efx_copy_channel(const struct efx_channel *old_channel) *channel = *old_channel; channel->napi_dev = NULL; + INIT_HLIST_NODE(&channel->napi_str.napi_hash_node); + channel->napi_str.napi_id = 0; + channel->napi_str.state = 0; memset(&channel->eventq, 0, sizeof(channel->eventq)); for (j = 0; j < EFX_TXQ_TYPES; j++) { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 48e71fad4210..e2c94ec4edd0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -880,6 +880,13 @@ static int stmmac_init_phy(struct net_device *dev) return -ENODEV; } + /* stmmac_adjust_link will change this to PHY_IGNORE_INTERRUPT to avoid + * subsequent PHY polling, make sure we force a link transition if + * we have a UP/DOWN/UP transition + */ + if (phydev->is_pseudo_fixed_link) + phydev->irq = PHY_POLL; + pr_debug("stmmac_init_phy: %s: attached to PHY (UID 0x%x)" " Link = %d\n", dev->name, phydev->phy_id, phydev->link); diff --git a/drivers/net/ethernet/ti/cpsw-phy-sel.c b/drivers/net/ethernet/ti/cpsw-phy-sel.c index 054a8dd23dae..ba1e45ff6aae 100644 --- a/drivers/net/ethernet/ti/cpsw-phy-sel.c +++ b/drivers/net/ethernet/ti/cpsw-phy-sel.c @@ -176,9 +176,12 @@ void cpsw_phy_sel(struct device *dev, phy_interface_t phy_mode, int slave) } dev = bus_find_device(&platform_bus_type, NULL, node, match); + of_node_put(node); priv = dev_get_drvdata(dev); priv->cpsw_phy_sel(priv, phy_mode, slave); + + put_device(dev); } EXPORT_SYMBOL_GPL(cpsw_phy_sel); diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c index 2fd94a5bc1f3..84fbe5714f8b 100644 --- a/drivers/net/ethernet/ti/davinci_emac.c +++ b/drivers/net/ethernet/ti/davinci_emac.c @@ -1410,6 +1410,7 @@ static int emac_dev_open(struct net_device *ndev) int i = 0; struct emac_priv *priv = netdev_priv(ndev); struct phy_device *phydev = NULL; + struct device *phy = NULL; ret = pm_runtime_get_sync(&priv->pdev->dev); if (ret < 0) { @@ -1488,19 +1489,20 @@ static int emac_dev_open(struct net_device *ndev) /* use the first phy on the bus if pdata did not give us a phy id */ if (!phydev && !priv->phy_id) { - struct device *phy; - phy = bus_find_device(&mdio_bus_type, NULL, NULL, match_first_device); - if (phy) + if (phy) { priv->phy_id = dev_name(phy); + if (!priv->phy_id || !*priv->phy_id) + put_device(phy); + } } if (!phydev && priv->phy_id && *priv->phy_id) { phydev = phy_connect(ndev, priv->phy_id, &emac_adjust_link, PHY_INTERFACE_MODE_MII); - + put_device(phy); /* reference taken by bus_find_device */ if (IS_ERR(phydev)) { dev_err(emac_dev, "could not connect to phy %s\n", priv->phy_id); diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c b/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c index 446ea580ad42..928c1dca2673 100644 --- a/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c +++ b/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c @@ -1694,7 +1694,7 @@ struct gelic_wl_scan_info *gelic_wl_find_best_bss(struct gelic_wl_info *wl) pr_debug("%s: bssid matched\n", __func__); break; } else { - pr_debug("%s: bssid unmached\n", __func__); + pr_debug("%s: bssid unmatched\n", __func__); continue; } } diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c index 7f127dc1b7ba..fa32391720fe 100644 --- a/drivers/net/ethernet/xscale/ixp4xx_eth.c +++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c @@ -708,8 +708,7 @@ static int eth_poll(struct napi_struct *napi, int budget) if (!qmgr_stat_below_low_watermark(rxq) && napi_reschedule(napi)) { /* not empty again */ #if DEBUG_RX - printk(KERN_DEBUG "%s: eth_poll" - " napi_reschedule successed\n", + printk(KERN_DEBUG "%s: eth_poll napi_reschedule succeeded\n", dev->name); #endif qmgr_disable_irq(rxq); diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 3234fcdea317..d2d6f12a112f 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1278,6 +1278,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, struct net_device *lowerdev; int err; int macmode; + bool create = false; if (!tb[IFLA_LINK]) return -EINVAL; @@ -1304,12 +1305,18 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, err = macvlan_port_create(lowerdev); if (err < 0) return err; + create = true; } port = macvlan_port_get_rtnl(lowerdev); /* Only 1 macvlan device can be created in passthru mode */ - if (port->passthru) - return -EINVAL; + if (port->passthru) { + /* The macvlan port must be not created this time, + * still goto destroy_macvlan_port for readability. + */ + err = -EINVAL; + goto destroy_macvlan_port; + } vlan->lowerdev = lowerdev; vlan->dev = dev; @@ -1325,24 +1332,28 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, vlan->flags = nla_get_u16(data[IFLA_MACVLAN_FLAGS]); if (vlan->mode == MACVLAN_MODE_PASSTHRU) { - if (port->count) - return -EINVAL; + if (port->count) { + err = -EINVAL; + goto destroy_macvlan_port; + } port->passthru = true; eth_hw_addr_inherit(dev, lowerdev); } if (data && data[IFLA_MACVLAN_MACADDR_MODE]) { - if (vlan->mode != MACVLAN_MODE_SOURCE) - return -EINVAL; + if (vlan->mode != MACVLAN_MODE_SOURCE) { + err = -EINVAL; + goto destroy_macvlan_port; + } macmode = nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE]); err = macvlan_changelink_sources(vlan, macmode, data); if (err) - return err; + goto destroy_macvlan_port; } err = register_netdevice(dev); if (err < 0) - return err; + goto destroy_macvlan_port; dev->priv_flags |= IFF_MACVLAN; err = netdev_upper_dev_link(lowerdev, dev); @@ -1357,7 +1368,9 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, unregister_netdev: unregister_netdevice(dev); - +destroy_macvlan_port: + if (create) + macvlan_port_destroy(port->dev); return err; } EXPORT_SYMBOL_GPL(macvlan_common_newlink); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index e977ba931878..1a4bf8acad78 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -723,6 +723,7 @@ struct phy_device *phy_connect(struct net_device *dev, const char *bus_id, phydev = to_phy_device(d); rc = phy_connect_direct(dev, phydev, handler, interface); + put_device(d); if (rc) return ERR_PTR(rc); @@ -953,6 +954,7 @@ struct phy_device *phy_attach(struct net_device *dev, const char *bus_id, phydev = to_phy_device(d); rc = phy_attach_direct(dev, phydev, phydev->dev_flags, interface); + put_device(d); if (rc) return ERR_PTR(rc); diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index e6338c16081a..8a6675d92b98 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -1656,6 +1656,19 @@ static const struct driver_info ax88178a_info = { .tx_fixup = ax88179_tx_fixup, }; +static const struct driver_info cypress_GX3_info = { + .description = "Cypress GX3 SuperSpeed to Gigabit Ethernet Controller", + .bind = ax88179_bind, + .unbind = ax88179_unbind, + .status = ax88179_status, + .link_reset = ax88179_link_reset, + .reset = ax88179_reset, + .stop = ax88179_stop, + .flags = FLAG_ETHER | FLAG_FRAMING_AX, + .rx_fixup = ax88179_rx_fixup, + .tx_fixup = ax88179_tx_fixup, +}; + static const struct driver_info dlink_dub1312_info = { .description = "D-Link DUB-1312 USB 3.0 to Gigabit Ethernet Adapter", .bind = ax88179_bind, @@ -1717,6 +1730,10 @@ static const struct usb_device_id products[] = { /* ASIX AX88178A 10/100/1000 */ USB_DEVICE(0x0b95, 0x178a), .driver_info = (unsigned long)&ax88178a_info, +}, { + /* Cypress GX3 SuperSpeed to Gigabit Ethernet Bridge Controller */ + USB_DEVICE(0x04b4, 0x3610), + .driver_info = (unsigned long)&cypress_GX3_info, }, { /* D-Link DUB-1312 USB 3.0 to Gigabit Ethernet Adapter */ USB_DEVICE(0x2001, 0x4a00), diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 44d439f50961..efb84f092492 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -1730,7 +1730,7 @@ static u8 r8152_rx_csum(struct r8152 *tp, struct rx_desc *rx_desc) u8 checksum = CHECKSUM_NONE; u32 opts2, opts3; - if (tp->version == RTL_VER_01) + if (tp->version == RTL_VER_01 || tp->version == RTL_VER_02) goto return_result; opts2 = le32_to_cpu(rx_desc->opts2); @@ -1745,7 +1745,7 @@ static u8 r8152_rx_csum(struct r8152 *tp, struct rx_desc *rx_desc) checksum = CHECKSUM_NONE; else checksum = CHECKSUM_UNNECESSARY; - } else if (RD_IPV6_CS) { + } else if (opts2 & RD_IPV6_CS) { if ((opts2 & RD_UDP_CS) && !(opts3 & UDPF)) checksum = CHECKSUM_UNNECESSARY; else if ((opts2 & RD_TCP_CS) && !(opts3 & TCPF)) @@ -3266,10 +3266,8 @@ static int rtl8152_open(struct net_device *netdev) goto out; res = usb_autopm_get_interface(tp->intf); - if (res < 0) { - free_all_mem(tp); - goto out; - } + if (res < 0) + goto out_free; mutex_lock(&tp->control); @@ -3285,10 +3283,9 @@ static int rtl8152_open(struct net_device *netdev) netif_device_detach(tp->netdev); netif_warn(tp, ifup, netdev, "intr_urb submit failed: %d\n", res); - free_all_mem(tp); - } else { - napi_enable(&tp->napi); + goto out_unlock; } + napi_enable(&tp->napi); mutex_unlock(&tp->control); @@ -3297,7 +3294,13 @@ static int rtl8152_open(struct net_device *netdev) tp->pm_notifier.notifier_call = rtl_notifier; register_pm_notifier(&tp->pm_notifier); #endif + return 0; +out_unlock: + mutex_unlock(&tp->control); + usb_autopm_put_interface(tp->intf); +out_free: + free_all_mem(tp); out: return res; } diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index fad84f3f4109..fd8b1e62301f 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2038,23 +2038,33 @@ static struct virtio_device_id id_table[] = { { 0 }, }; +#define VIRTNET_FEATURES \ + VIRTIO_NET_F_CSUM, VIRTIO_NET_F_GUEST_CSUM, \ + VIRTIO_NET_F_MAC, \ + VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_UFO, VIRTIO_NET_F_HOST_TSO6, \ + VIRTIO_NET_F_HOST_ECN, VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6, \ + VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_UFO, \ + VIRTIO_NET_F_MRG_RXBUF, VIRTIO_NET_F_STATUS, VIRTIO_NET_F_CTRL_VQ, \ + VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN, \ + VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ, \ + VIRTIO_NET_F_CTRL_MAC_ADDR, \ + VIRTIO_NET_F_MTU + static unsigned int features[] = { - VIRTIO_NET_F_CSUM, VIRTIO_NET_F_GUEST_CSUM, - VIRTIO_NET_F_GSO, VIRTIO_NET_F_MAC, - VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_UFO, VIRTIO_NET_F_HOST_TSO6, - VIRTIO_NET_F_HOST_ECN, VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6, - VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_UFO, - VIRTIO_NET_F_MRG_RXBUF, VIRTIO_NET_F_STATUS, VIRTIO_NET_F_CTRL_VQ, - VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN, - VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ, - VIRTIO_NET_F_CTRL_MAC_ADDR, + VIRTNET_FEATURES, +}; + +static unsigned int features_legacy[] = { + VIRTNET_FEATURES, + VIRTIO_NET_F_GSO, VIRTIO_F_ANY_LAYOUT, - VIRTIO_NET_F_MTU, }; static struct virtio_driver virtio_net_driver = { .feature_table = features, .feature_table_size = ARRAY_SIZE(features), + .feature_table_legacy = features_legacy, + .feature_table_size_legacy = ARRAY_SIZE(features_legacy), .driver.name = KBUILD_MODNAME, .driver.owner = THIS_MODULE, .id_table = id_table, diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index f3c2fa3ab0d5..24532cdebb00 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -944,7 +944,9 @@ static bool vxlan_group_used(struct vxlan_net *vn, struct vxlan_dev *dev) { struct vxlan_dev *vxlan; struct vxlan_sock *sock4; - struct vxlan_sock *sock6 = NULL; +#if IS_ENABLED(CONFIG_IPV6) + struct vxlan_sock *sock6; +#endif unsigned short family = dev->default_dst.remote_ip.sa.sa_family; sock4 = rtnl_dereference(dev->vn4_sock); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index b777e1b2f87a..78d9966a3957 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -4516,7 +4516,7 @@ brcmf_cfg80211_start_ap(struct wiphy *wiphy, struct net_device *ndev, /* store current 11d setting */ if (brcmf_fil_cmd_int_get(ifp, BRCMF_C_GET_REGULATORY, &ifp->vif->is_11d)) { - supports_11d = false; + is_11d = supports_11d = false; } else { country_ie = brcmf_parse_tlvs((u8 *)settings->beacon.tail, settings->beacon.tail_len, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c index 4fdc3dad3e85..b88e2048ae0b 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c @@ -1087,6 +1087,15 @@ iwl_mvm_netdetect_config(struct iwl_mvm *mvm, ret = iwl_mvm_switch_to_d3(mvm); if (ret) return ret; + } else { + /* In theory, we wouldn't have to stop a running sched + * scan in order to start another one (for + * net-detect). But in practice this doesn't seem to + * work properly, so stop any running sched_scan now. + */ + ret = iwl_mvm_scan_stop(mvm, IWL_MVM_SCAN_SCHED, true); + if (ret) + return ret; } /* rfkill release can be either for wowlan or netdetect */ @@ -1254,7 +1263,10 @@ static int __iwl_mvm_suspend(struct ieee80211_hw *hw, out: if (ret < 0) { iwl_mvm_ref(mvm, IWL_MVM_REF_UCODE_DOWN); - ieee80211_restart_hw(mvm->hw); + if (mvm->restart_fw > 0) { + mvm->restart_fw--; + ieee80211_restart_hw(mvm->hw); + } iwl_mvm_free_nd(mvm); } out_noreset: @@ -2088,6 +2100,16 @@ static int __iwl_mvm_resume(struct iwl_mvm *mvm, bool test) iwl_mvm_update_changed_regdom(mvm); if (mvm->net_detect) { + /* If this is a non-unified image, we restart the FW, + * so no need to stop the netdetect scan. If that + * fails, continue and try to get the wake-up reasons, + * but trigger a HW restart by keeping a failure code + * in ret. + */ + if (unified_image) + ret = iwl_mvm_scan_stop(mvm, IWL_MVM_SCAN_NETDETECT, + false); + iwl_mvm_query_netdetect_reasons(mvm, vif); /* has unlocked the mutex, so skip that */ goto out; @@ -2271,7 +2293,8 @@ static void iwl_mvm_d3_test_disconn_work_iter(void *_data, u8 *mac, static int iwl_mvm_d3_test_release(struct inode *inode, struct file *file) { struct iwl_mvm *mvm = inode->i_private; - int remaining_time = 10; + bool unified_image = fw_has_capa(&mvm->fw->ucode_capa, + IWL_UCODE_TLV_CAPA_CNSLDTD_D3_D0_IMG); mvm->d3_test_active = false; @@ -2282,18 +2305,22 @@ static int iwl_mvm_d3_test_release(struct inode *inode, struct file *file) mvm->trans->system_pm_mode = IWL_PLAT_PM_MODE_DISABLED; iwl_abort_notification_waits(&mvm->notif_wait); - ieee80211_restart_hw(mvm->hw); + if (!unified_image) { + int remaining_time = 10; - /* wait for restart and disconnect all interfaces */ - while (test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status) && - remaining_time > 0) { - remaining_time--; - msleep(1000); + ieee80211_restart_hw(mvm->hw); + + /* wait for restart and disconnect all interfaces */ + while (test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status) && + remaining_time > 0) { + remaining_time--; + msleep(1000); + } + + if (remaining_time == 0) + IWL_ERR(mvm, "Timed out waiting for HW restart!\n"); } - if (remaining_time == 0) - IWL_ERR(mvm, "Timed out waiting for HW restart to finish!\n"); - ieee80211_iterate_active_interfaces_atomic( mvm->hw, IEEE80211_IFACE_ITER_NORMAL, iwl_mvm_d3_test_disconn_work_iter, mvm->keep_vif); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c index 07da4efe8458..7b7d2a146e30 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c @@ -1529,8 +1529,8 @@ static ssize_t iwl_dbgfs_mem_read(struct file *file, char __user *user_buf, .data = { &cmd, }, .len = { sizeof(cmd) }, }; - size_t delta, len; - ssize_t ret; + size_t delta; + ssize_t ret, len; hcmd.id = iwl_cmd_id(*ppos >> 24 ? UMAC_RD_WR : LMAC_RD_WR, DEBUG_GROUP, 0); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 318efd814037..1db1dc13e988 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -4121,7 +4121,6 @@ void iwl_mvm_sync_rx_queues_internal(struct iwl_mvm *mvm, struct iwl_mvm_internal_rxq_notif *notif, u32 size) { - DECLARE_WAIT_QUEUE_HEAD_ONSTACK(notif_waitq); u32 qmask = BIT(mvm->trans->num_rx_queues) - 1; int ret; @@ -4143,7 +4142,7 @@ void iwl_mvm_sync_rx_queues_internal(struct iwl_mvm *mvm, } if (notif->sync) - ret = wait_event_timeout(notif_waitq, + ret = wait_event_timeout(mvm->rx_sync_waitq, atomic_read(&mvm->queue_sync_counter) == 0, HZ); WARN_ON_ONCE(!ret); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index d17cbf603f7c..c60703e0c246 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -937,6 +937,7 @@ struct iwl_mvm { /* sync d0i3_tx queue and IWL_MVM_STATUS_IN_D0I3 status flag */ spinlock_t d0i3_tx_lock; wait_queue_head_t d0i3_exit_waitq; + wait_queue_head_t rx_sync_waitq; /* BT-Coex */ struct iwl_bt_coex_profile_notif last_bt_notif; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c index 05fe6dd1a2c8..4d35deb628bc 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c @@ -619,6 +619,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg, spin_lock_init(&mvm->refs_lock); skb_queue_head_init(&mvm->d0i3_tx); init_waitqueue_head(&mvm->d0i3_exit_waitq); + init_waitqueue_head(&mvm->rx_sync_waitq); atomic_set(&mvm->queue_sync_counter, 0); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index a57c6ef5bc14..6c802cee900c 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -547,7 +547,8 @@ void iwl_mvm_rx_queue_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb, "Received expired RX queue sync message\n"); return; } - atomic_dec(&mvm->queue_sync_counter); + if (!atomic_dec_return(&mvm->queue_sync_counter)) + wake_up(&mvm->rx_sync_waitq); } switch (internal_notif->type) { diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c index f279fdd6eb44..fa9743205491 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c @@ -1199,6 +1199,9 @@ static int iwl_mvm_num_scans(struct iwl_mvm *mvm) static int iwl_mvm_check_running_scans(struct iwl_mvm *mvm, int type) { + bool unified_image = fw_has_capa(&mvm->fw->ucode_capa, + IWL_UCODE_TLV_CAPA_CNSLDTD_D3_D0_IMG); + /* This looks a bit arbitrary, but the idea is that if we run * out of possible simultaneous scans and the userspace is * trying to run a scan type that is already running, we @@ -1225,12 +1228,30 @@ static int iwl_mvm_check_running_scans(struct iwl_mvm *mvm, int type) return -EBUSY; return iwl_mvm_scan_stop(mvm, IWL_MVM_SCAN_REGULAR, true); case IWL_MVM_SCAN_NETDETECT: - /* No need to stop anything for net-detect since the - * firmware is restarted anyway. This way, any sched - * scans that were running will be restarted when we - * resume. - */ - return 0; + /* For non-unified images, there's no need to stop + * anything for net-detect since the firmware is + * restarted anyway. This way, any sched scans that + * were running will be restarted when we resume. + */ + if (!unified_image) + return 0; + + /* If this is a unified image and we ran out of scans, + * we need to stop something. Prefer stopping regular + * scans, because the results are useless at this + * point, and we should be able to keep running + * another scheduled scan while suspended. + */ + if (mvm->scan_status & IWL_MVM_SCAN_REGULAR_MASK) + return iwl_mvm_scan_stop(mvm, IWL_MVM_SCAN_REGULAR, + true); + if (mvm->scan_status & IWL_MVM_SCAN_SCHED_MASK) + return iwl_mvm_scan_stop(mvm, IWL_MVM_SCAN_SCHED, + true); + + /* fall through, something is wrong if no scan was + * running but we ran out of scans. + */ default: WARN_ON(1); break; diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 001be406a3d3..2f8134b2a504 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -541,48 +541,64 @@ static const struct pci_device_id iwl_hw_card_ids[] = { MODULE_DEVICE_TABLE(pci, iwl_hw_card_ids); #ifdef CONFIG_ACPI -#define SPL_METHOD "SPLC" -#define SPL_DOMAINTYPE_MODULE BIT(0) -#define SPL_DOMAINTYPE_WIFI BIT(1) -#define SPL_DOMAINTYPE_WIGIG BIT(2) -#define SPL_DOMAINTYPE_RFEM BIT(3) +#define ACPI_SPLC_METHOD "SPLC" +#define ACPI_SPLC_DOMAIN_WIFI (0x07) -static u64 splx_get_pwr_limit(struct iwl_trans *trans, union acpi_object *splx) +static u64 splc_get_pwr_limit(struct iwl_trans *trans, union acpi_object *splc) { - union acpi_object *limits, *domain_type, *power_limit; + union acpi_object *data_pkg, *dflt_pwr_limit; + int i; - if (splx->type != ACPI_TYPE_PACKAGE || - splx->package.count != 2 || - splx->package.elements[0].type != ACPI_TYPE_INTEGER || - splx->package.elements[0].integer.value != 0) { - IWL_ERR(trans, "Unsupported splx structure\n"); + /* We need at least two elements, one for the revision and one + * for the data itself. Also check that the revision is + * supported (currently only revision 0). + */ + if (splc->type != ACPI_TYPE_PACKAGE || + splc->package.count < 2 || + splc->package.elements[0].type != ACPI_TYPE_INTEGER || + splc->package.elements[0].integer.value != 0) { + IWL_DEBUG_INFO(trans, + "Unsupported structure returned by the SPLC method. Ignoring.\n"); return 0; } - limits = &splx->package.elements[1]; - if (limits->type != ACPI_TYPE_PACKAGE || - limits->package.count < 2 || - limits->package.elements[0].type != ACPI_TYPE_INTEGER || - limits->package.elements[1].type != ACPI_TYPE_INTEGER) { - IWL_ERR(trans, "Invalid limits element\n"); + /* loop through all the packages to find the one for WiFi */ + for (i = 1; i < splc->package.count; i++) { + union acpi_object *domain; + + data_pkg = &splc->package.elements[i]; + + /* Skip anything that is not a package with the right + * amount of elements (i.e. at least 2 integers). + */ + if (data_pkg->type != ACPI_TYPE_PACKAGE || + data_pkg->package.count < 2 || + data_pkg->package.elements[0].type != ACPI_TYPE_INTEGER || + data_pkg->package.elements[1].type != ACPI_TYPE_INTEGER) + continue; + + domain = &data_pkg->package.elements[0]; + if (domain->integer.value == ACPI_SPLC_DOMAIN_WIFI) + break; + + data_pkg = NULL; + } + + if (!data_pkg) { + IWL_DEBUG_INFO(trans, + "No element for the WiFi domain returned by the SPLC method.\n"); return 0; } - domain_type = &limits->package.elements[0]; - power_limit = &limits->package.elements[1]; - if (!(domain_type->integer.value & SPL_DOMAINTYPE_WIFI)) { - IWL_DEBUG_INFO(trans, "WiFi power is not limited\n"); - return 0; - } - - return power_limit->integer.value; + dflt_pwr_limit = &data_pkg->package.elements[1]; + return dflt_pwr_limit->integer.value; } static void set_dflt_pwr_limit(struct iwl_trans *trans, struct pci_dev *pdev) { acpi_handle pxsx_handle; acpi_handle handle; - struct acpi_buffer splx = {ACPI_ALLOCATE_BUFFER, NULL}; + struct acpi_buffer splc = {ACPI_ALLOCATE_BUFFER, NULL}; acpi_status status; pxsx_handle = ACPI_HANDLE(&pdev->dev); @@ -593,23 +609,24 @@ static void set_dflt_pwr_limit(struct iwl_trans *trans, struct pci_dev *pdev) } /* Get the method's handle */ - status = acpi_get_handle(pxsx_handle, (acpi_string)SPL_METHOD, &handle); + status = acpi_get_handle(pxsx_handle, (acpi_string)ACPI_SPLC_METHOD, + &handle); if (ACPI_FAILURE(status)) { - IWL_DEBUG_INFO(trans, "SPL method not found\n"); + IWL_DEBUG_INFO(trans, "SPLC method not found\n"); return; } /* Call SPLC with no arguments */ - status = acpi_evaluate_object(handle, NULL, NULL, &splx); + status = acpi_evaluate_object(handle, NULL, NULL, &splc); if (ACPI_FAILURE(status)) { IWL_ERR(trans, "SPLC invocation failed (0x%x)\n", status); return; } - trans->dflt_pwr_limit = splx_get_pwr_limit(trans, splx.pointer); + trans->dflt_pwr_limit = splc_get_pwr_limit(trans, splc.pointer); IWL_DEBUG_INFO(trans, "Default power limit set to %lld\n", trans->dflt_pwr_limit); - kfree(splx.pointer); + kfree(splc.pointer); } #else /* CONFIG_ACPI */ diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c index e9a278b60dfd..5f840f16f40b 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c @@ -592,6 +592,7 @@ error: static int iwl_pcie_txq_init(struct iwl_trans *trans, struct iwl_txq *txq, int slots_num, u32 txq_id) { + struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); int ret; txq->need_update = false; @@ -606,6 +607,13 @@ static int iwl_pcie_txq_init(struct iwl_trans *trans, struct iwl_txq *txq, return ret; spin_lock_init(&txq->lock); + + if (txq_id == trans_pcie->cmd_queue) { + static struct lock_class_key iwl_pcie_cmd_queue_lock_class; + + lockdep_set_class(&txq->lock, &iwl_pcie_cmd_queue_lock_class); + } + __skb_queue_head_init(&txq->overflow_q); /* diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index e17879dd5d5a..bf2744e1e3db 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -304,7 +304,7 @@ static void xennet_alloc_rx_buffers(struct netfront_queue *queue) queue->rx_skbs[id] = skb; ref = gnttab_claim_grant_reference(&queue->gref_rx_head); - BUG_ON((signed short)ref < 0); + WARN_ON_ONCE(IS_ERR_VALUE((unsigned long)(int)ref)); queue->grant_rx_ref[id] = ref; page = skb_frag_page(&skb_shinfo(skb)->frags[0]); @@ -428,7 +428,7 @@ static void xennet_tx_setup_grant(unsigned long gfn, unsigned int offset, id = get_id_from_freelist(&queue->tx_skb_freelist, queue->tx_skbs); tx = RING_GET_REQUEST(&queue->tx, queue->tx.req_prod_pvt++); ref = gnttab_claim_grant_reference(&queue->gref_tx_head); - BUG_ON((signed short)ref < 0); + WARN_ON_ONCE(IS_ERR_VALUE((unsigned long)(int)ref)); gnttab_grant_foreign_access_ref(ref, queue->info->xbdev->otherend_id, gfn, GNTMAP_readonly); diff --git a/drivers/ntb/hw/intel/ntb_hw_intel.c b/drivers/ntb/hw/intel/ntb_hw_intel.c index 0d5c29ae51de..7310a261c858 100644 --- a/drivers/ntb/hw/intel/ntb_hw_intel.c +++ b/drivers/ntb/hw/intel/ntb_hw_intel.c @@ -112,17 +112,17 @@ MODULE_PARM_DESC(xeon_b2b_usd_bar2_addr64, module_param_named(xeon_b2b_usd_bar4_addr64, xeon_b2b_usd_addr.bar4_addr64, ullong, 0644); -MODULE_PARM_DESC(xeon_b2b_usd_bar2_addr64, +MODULE_PARM_DESC(xeon_b2b_usd_bar4_addr64, "XEON B2B USD BAR 4 64-bit address"); module_param_named(xeon_b2b_usd_bar4_addr32, xeon_b2b_usd_addr.bar4_addr32, ullong, 0644); -MODULE_PARM_DESC(xeon_b2b_usd_bar2_addr64, +MODULE_PARM_DESC(xeon_b2b_usd_bar4_addr32, "XEON B2B USD split-BAR 4 32-bit address"); module_param_named(xeon_b2b_usd_bar5_addr32, xeon_b2b_usd_addr.bar5_addr32, ullong, 0644); -MODULE_PARM_DESC(xeon_b2b_usd_bar2_addr64, +MODULE_PARM_DESC(xeon_b2b_usd_bar5_addr32, "XEON B2B USD split-BAR 5 32-bit address"); module_param_named(xeon_b2b_dsd_bar2_addr64, @@ -132,17 +132,17 @@ MODULE_PARM_DESC(xeon_b2b_dsd_bar2_addr64, module_param_named(xeon_b2b_dsd_bar4_addr64, xeon_b2b_dsd_addr.bar4_addr64, ullong, 0644); -MODULE_PARM_DESC(xeon_b2b_dsd_bar2_addr64, +MODULE_PARM_DESC(xeon_b2b_dsd_bar4_addr64, "XEON B2B DSD BAR 4 64-bit address"); module_param_named(xeon_b2b_dsd_bar4_addr32, xeon_b2b_dsd_addr.bar4_addr32, ullong, 0644); -MODULE_PARM_DESC(xeon_b2b_dsd_bar2_addr64, +MODULE_PARM_DESC(xeon_b2b_dsd_bar4_addr32, "XEON B2B DSD split-BAR 4 32-bit address"); module_param_named(xeon_b2b_dsd_bar5_addr32, xeon_b2b_dsd_addr.bar5_addr32, ullong, 0644); -MODULE_PARM_DESC(xeon_b2b_dsd_bar2_addr64, +MODULE_PARM_DESC(xeon_b2b_dsd_bar5_addr32, "XEON B2B DSD split-BAR 5 32-bit address"); #ifndef ioread64 @@ -1755,6 +1755,8 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev, XEON_B2B_MIN_SIZE); if (!ndev->peer_mmio) return -EIO; + + ndev->peer_addr = pci_resource_start(pdev, b2b_bar); } return 0; @@ -2019,6 +2021,7 @@ static int intel_ntb_init_pci(struct intel_ntb_dev *ndev, struct pci_dev *pdev) goto err_mmio; } ndev->peer_mmio = ndev->self_mmio; + ndev->peer_addr = pci_resource_start(pdev, 0); return 0; diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index 8601c10acf74..4eb8adb34508 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -257,7 +257,7 @@ enum { #define NTB_QP_DEF_NUM_ENTRIES 100 #define NTB_LINK_DOWN_TIMEOUT 10 #define DMA_RETRIES 20 -#define DMA_OUT_RESOURCE_TO 50 +#define DMA_OUT_RESOURCE_TO msecs_to_jiffies(50) static void ntb_transport_rxc_db(unsigned long data); static const struct ntb_ctx_ops ntb_transport_ops; diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c index 6a50f20bf1cd..e75d4fdc0866 100644 --- a/drivers/ntb/test/ntb_perf.c +++ b/drivers/ntb/test/ntb_perf.c @@ -72,7 +72,7 @@ #define MAX_THREADS 32 #define MAX_TEST_SIZE SZ_1M #define MAX_SRCS 32 -#define DMA_OUT_RESOURCE_TO 50 +#define DMA_OUT_RESOURCE_TO msecs_to_jiffies(50) #define DMA_RETRIES 20 #define SZ_4G (1ULL << 32) #define MAX_SEG_ORDER 20 /* no larger than 1M for kmalloc buffer */ @@ -589,7 +589,7 @@ static ssize_t debugfs_run_read(struct file *filp, char __user *ubuf, return -ENOMEM; if (mutex_is_locked(&perf->run_mutex)) { - out_off = snprintf(buf, 64, "running\n"); + out_off = scnprintf(buf, 64, "running\n"); goto read_from_buf; } @@ -600,14 +600,14 @@ static ssize_t debugfs_run_read(struct file *filp, char __user *ubuf, break; if (pctx->status) { - out_off += snprintf(buf + out_off, 1024 - out_off, + out_off += scnprintf(buf + out_off, 1024 - out_off, "%d: error %d\n", i, pctx->status); continue; } rate = div64_u64(pctx->copied, pctx->diff_us); - out_off += snprintf(buf + out_off, 1024 - out_off, + out_off += scnprintf(buf + out_off, 1024 - out_off, "%d: copied %llu bytes in %llu usecs, %llu MBytes/s\n", i, pctx->copied, pctx->diff_us, rate); } diff --git a/drivers/ntb/test/ntb_pingpong.c b/drivers/ntb/test/ntb_pingpong.c index 7d311799fca1..435861189d97 100644 --- a/drivers/ntb/test/ntb_pingpong.c +++ b/drivers/ntb/test/ntb_pingpong.c @@ -88,7 +88,7 @@ MODULE_PARM_DESC(delay_ms, "Milliseconds to delay the response to peer"); static unsigned long db_init = 0x7; module_param(db_init, ulong, 0644); -MODULE_PARM_DESC(delay_ms, "Initial doorbell bits to ring on the peer"); +MODULE_PARM_DESC(db_init, "Initial doorbell bits to ring on the peer"); struct pp_ctx { struct ntb_dev *ntb; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 0248d0e21fee..5e52034ab010 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1242,20 +1242,16 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev) result = nvme_enable_ctrl(&dev->ctrl, cap); if (result) - goto free_nvmeq; + return result; nvmeq->cq_vector = 0; result = queue_request_irq(nvmeq); if (result) { nvmeq->cq_vector = -1; - goto free_nvmeq; + return result; } return result; - - free_nvmeq: - nvme_free_queues(dev, 0); - return result; } static bool nvme_should_reset(struct nvme_dev *dev, u32 csts) @@ -1317,10 +1313,8 @@ static int nvme_create_io_queues(struct nvme_dev *dev) max = min(dev->max_qid, dev->queue_count - 1); for (i = dev->online_queues; i <= max; i++) { ret = nvme_create_queue(dev->queues[i], i); - if (ret) { - nvme_free_queues(dev, i); + if (ret) break; - } } /* @@ -1460,13 +1454,9 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) result = queue_request_irq(adminq); if (result) { adminq->cq_vector = -1; - goto free_queues; + return result; } return nvme_create_io_queues(dev); - - free_queues: - nvme_free_queues(dev, 1); - return result; } static void nvme_del_queue_end(struct request *req, int error) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 5a8388177959..3d25add36d91 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -83,6 +83,7 @@ enum nvme_rdma_queue_flags { NVME_RDMA_Q_CONNECTED = (1 << 0), NVME_RDMA_IB_QUEUE_ALLOCATED = (1 << 1), NVME_RDMA_Q_DELETING = (1 << 2), + NVME_RDMA_Q_LIVE = (1 << 3), }; struct nvme_rdma_queue { @@ -624,10 +625,18 @@ static int nvme_rdma_connect_io_queues(struct nvme_rdma_ctrl *ctrl) for (i = 1; i < ctrl->queue_count; i++) { ret = nvmf_connect_io_queue(&ctrl->ctrl, i); - if (ret) - break; + if (ret) { + dev_info(ctrl->ctrl.device, + "failed to connect i/o queue: %d\n", ret); + goto out_free_queues; + } + set_bit(NVME_RDMA_Q_LIVE, &ctrl->queues[i].flags); } + return 0; + +out_free_queues: + nvme_rdma_free_io_queues(ctrl); return ret; } @@ -712,6 +721,8 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work) if (ret) goto stop_admin_q; + set_bit(NVME_RDMA_Q_LIVE, &ctrl->queues[0].flags); + ret = nvme_enable_ctrl(&ctrl->ctrl, ctrl->cap); if (ret) goto stop_admin_q; @@ -761,8 +772,10 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work) nvme_stop_keep_alive(&ctrl->ctrl); - for (i = 0; i < ctrl->queue_count; i++) + for (i = 0; i < ctrl->queue_count; i++) { clear_bit(NVME_RDMA_Q_CONNECTED, &ctrl->queues[i].flags); + clear_bit(NVME_RDMA_Q_LIVE, &ctrl->queues[i].flags); + } if (ctrl->queue_count > 1) nvme_stop_queues(&ctrl->ctrl); @@ -1378,6 +1391,24 @@ nvme_rdma_timeout(struct request *rq, bool reserved) return BLK_EH_HANDLED; } +/* + * We cannot accept any other command until the Connect command has completed. + */ +static inline bool nvme_rdma_queue_is_ready(struct nvme_rdma_queue *queue, + struct request *rq) +{ + if (unlikely(!test_bit(NVME_RDMA_Q_LIVE, &queue->flags))) { + struct nvme_command *cmd = (struct nvme_command *)rq->cmd; + + if (rq->cmd_type != REQ_TYPE_DRV_PRIV || + cmd->common.opcode != nvme_fabrics_command || + cmd->fabrics.fctype != nvme_fabrics_type_connect) + return false; + } + + return true; +} + static int nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { @@ -1394,6 +1425,9 @@ static int nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, WARN_ON_ONCE(rq->tag < 0); + if (!nvme_rdma_queue_is_ready(queue, rq)) + return BLK_MQ_RQ_QUEUE_BUSY; + dev = queue->device->dev; ib_dma_sync_single_for_cpu(dev, sqe->dma, sizeof(struct nvme_command), DMA_TO_DEVICE); @@ -1544,6 +1578,8 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl) if (error) goto out_cleanup_queue; + set_bit(NVME_RDMA_Q_LIVE, &ctrl->queues[0].flags); + error = nvmf_reg_read64(&ctrl->ctrl, NVME_REG_CAP, &ctrl->cap); if (error) { dev_err(ctrl->ctrl.device, diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index b4cacb6f0258..a21437a33adb 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -838,9 +838,13 @@ static void nvmet_fatal_error_handler(struct work_struct *work) void nvmet_ctrl_fatal_error(struct nvmet_ctrl *ctrl) { - ctrl->csts |= NVME_CSTS_CFS; - INIT_WORK(&ctrl->fatal_err_work, nvmet_fatal_error_handler); - schedule_work(&ctrl->fatal_err_work); + mutex_lock(&ctrl->lock); + if (!(ctrl->csts & NVME_CSTS_CFS)) { + ctrl->csts |= NVME_CSTS_CFS; + INIT_WORK(&ctrl->fatal_err_work, nvmet_fatal_error_handler); + schedule_work(&ctrl->fatal_err_work); + } + mutex_unlock(&ctrl->lock); } EXPORT_SYMBOL_GPL(nvmet_ctrl_fatal_error); diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index f8d23999e0f2..005ef5d17a19 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -951,6 +951,7 @@ err_destroy_cq: static void nvmet_rdma_destroy_queue_ib(struct nvmet_rdma_queue *queue) { + ib_drain_qp(queue->cm_id->qp); rdma_destroy_qp(queue->cm_id); ib_free_cq(queue->cq); } @@ -1066,6 +1067,7 @@ nvmet_rdma_alloc_queue(struct nvmet_rdma_device *ndev, spin_lock_init(&queue->rsp_wr_wait_lock); INIT_LIST_HEAD(&queue->free_rsps); spin_lock_init(&queue->rsps_lock); + INIT_LIST_HEAD(&queue->queue_list); queue->idx = ida_simple_get(&nvmet_rdma_queue_ida, 0, 0, GFP_KERNEL); if (queue->idx < 0) { @@ -1244,7 +1246,6 @@ static void __nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue) if (disconnect) { rdma_disconnect(queue->cm_id); - ib_drain_qp(queue->cm_id->qp); schedule_work(&queue->release_work); } } @@ -1269,7 +1270,12 @@ static void nvmet_rdma_queue_connect_fail(struct rdma_cm_id *cm_id, { WARN_ON_ONCE(queue->state != NVMET_RDMA_Q_CONNECTING); - pr_err("failed to connect queue\n"); + mutex_lock(&nvmet_rdma_queue_mutex); + if (!list_empty(&queue->queue_list)) + list_del_init(&queue->queue_list); + mutex_unlock(&nvmet_rdma_queue_mutex); + + pr_err("failed to connect queue %d\n", queue->idx); schedule_work(&queue->release_work); } @@ -1352,7 +1358,13 @@ static int nvmet_rdma_cm_handler(struct rdma_cm_id *cm_id, case RDMA_CM_EVENT_ADDR_CHANGE: case RDMA_CM_EVENT_DISCONNECTED: case RDMA_CM_EVENT_TIMEWAIT_EXIT: - nvmet_rdma_queue_disconnect(queue); + /* + * We might end up here when we already freed the qp + * which means queue release sequence is in progress, + * so don't get in the way... + */ + if (queue) + nvmet_rdma_queue_disconnect(queue); break; case RDMA_CM_EVENT_DEVICE_REMOVAL: ret = nvmet_rdma_device_removal(cm_id, queue); diff --git a/drivers/pci/pci-mid.c b/drivers/pci/pci-mid.c index 55f453de562e..c7f3408e3148 100644 --- a/drivers/pci/pci-mid.c +++ b/drivers/pci/pci-mid.c @@ -29,6 +29,11 @@ static int mid_pci_set_power_state(struct pci_dev *pdev, pci_power_t state) return intel_mid_pci_set_power_state(pdev, state); } +static pci_power_t mid_pci_get_power_state(struct pci_dev *pdev) +{ + return intel_mid_pci_get_power_state(pdev); +} + static pci_power_t mid_pci_choose_state(struct pci_dev *pdev) { return PCI_D3hot; @@ -52,6 +57,7 @@ static bool mid_pci_need_resume(struct pci_dev *dev) static struct pci_platform_pm_ops mid_pci_platform_pm = { .is_manageable = mid_pci_power_manageable, .set_state = mid_pci_set_power_state, + .get_state = mid_pci_get_power_state, .choose_state = mid_pci_choose_state, .sleep_wake = mid_pci_sleep_wake, .run_wake = mid_pci_run_wake, diff --git a/drivers/rtc/rtc-asm9260.c b/drivers/rtc/rtc-asm9260.c index 18a93d3e3f93..d36534965635 100644 --- a/drivers/rtc/rtc-asm9260.c +++ b/drivers/rtc/rtc-asm9260.c @@ -327,6 +327,7 @@ static const struct of_device_id asm9260_dt_ids[] = { { .compatible = "alphascale,asm9260-rtc", }, {} }; +MODULE_DEVICE_TABLE(of, asm9260_dt_ids); static struct platform_driver asm9260_rtc_driver = { .probe = asm9260_rtc_probe, diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index dd3d59806ffa..7030d7cd3861 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -776,7 +776,7 @@ static void cmos_do_shutdown(int rtc_irq) spin_unlock_irq(&rtc_lock); } -static void __exit cmos_do_remove(struct device *dev) +static void cmos_do_remove(struct device *dev) { struct cmos_rtc *cmos = dev_get_drvdata(dev); struct resource *ports; @@ -996,8 +996,9 @@ static u32 rtc_handler(void *context) struct cmos_rtc *cmos = dev_get_drvdata(dev); unsigned char rtc_control = 0; unsigned char rtc_intr; + unsigned long flags; - spin_lock_irq(&rtc_lock); + spin_lock_irqsave(&rtc_lock, flags); if (cmos_rtc.suspend_ctrl) rtc_control = CMOS_READ(RTC_CONTROL); if (rtc_control & RTC_AIE) { @@ -1006,7 +1007,7 @@ static u32 rtc_handler(void *context) rtc_intr = CMOS_READ(RTC_INTR_FLAGS); rtc_update_irq(cmos->rtc, 1, rtc_intr); } - spin_unlock_irq(&rtc_lock); + spin_unlock_irqrestore(&rtc_lock, flags); pm_wakeup_event(dev, 0); acpi_clear_event(ACPI_EVENT_RTC); @@ -1129,7 +1130,7 @@ static int cmos_pnp_probe(struct pnp_dev *pnp, const struct pnp_device_id *id) pnp_irq(pnp, 0)); } -static void __exit cmos_pnp_remove(struct pnp_dev *pnp) +static void cmos_pnp_remove(struct pnp_dev *pnp) { cmos_do_remove(&pnp->dev); } @@ -1161,7 +1162,7 @@ static struct pnp_driver cmos_pnp_driver = { .name = (char *) driver_name, .id_table = rtc_ids, .probe = cmos_pnp_probe, - .remove = __exit_p(cmos_pnp_remove), + .remove = cmos_pnp_remove, .shutdown = cmos_pnp_shutdown, /* flag ensures resume() gets called, and stops syslog spam */ @@ -1238,7 +1239,7 @@ static int __init cmos_platform_probe(struct platform_device *pdev) return cmos_do_probe(&pdev->dev, resource, irq); } -static int __exit cmos_platform_remove(struct platform_device *pdev) +static int cmos_platform_remove(struct platform_device *pdev) { cmos_do_remove(&pdev->dev); return 0; @@ -1263,7 +1264,7 @@ static void cmos_platform_shutdown(struct platform_device *pdev) MODULE_ALIAS("platform:rtc_cmos"); static struct platform_driver cmos_platform_driver = { - .remove = __exit_p(cmos_platform_remove), + .remove = cmos_platform_remove, .shutdown = cmos_platform_shutdown, .driver = { .name = driver_name, diff --git a/drivers/rtc/rtc-omap.c b/drivers/rtc/rtc-omap.c index b04ea9b5ae67..51e52446eacb 100644 --- a/drivers/rtc/rtc-omap.c +++ b/drivers/rtc/rtc-omap.c @@ -113,6 +113,7 @@ /* OMAP_RTC_OSC_REG bit fields: */ #define OMAP_RTC_OSC_32KCLK_EN BIT(6) #define OMAP_RTC_OSC_SEL_32KCLK_SRC BIT(3) +#define OMAP_RTC_OSC_OSC32K_GZ_DISABLE BIT(4) /* OMAP_RTC_IRQWAKEEN bit fields: */ #define OMAP_RTC_IRQWAKEEN_ALARM_WAKEEN BIT(1) @@ -146,6 +147,7 @@ struct omap_rtc { u8 interrupts_reg; bool is_pmic_controller; bool has_ext_clk; + bool is_suspending; const struct omap_rtc_device_type *type; struct pinctrl_dev *pctldev; }; @@ -786,8 +788,9 @@ static int omap_rtc_probe(struct platform_device *pdev) */ if (rtc->has_ext_clk) { reg = rtc_read(rtc, OMAP_RTC_OSC_REG); - rtc_write(rtc, OMAP_RTC_OSC_REG, - reg | OMAP_RTC_OSC_SEL_32KCLK_SRC); + reg &= ~OMAP_RTC_OSC_OSC32K_GZ_DISABLE; + reg |= OMAP_RTC_OSC_32KCLK_EN | OMAP_RTC_OSC_SEL_32KCLK_SRC; + rtc_writel(rtc, OMAP_RTC_OSC_REG, reg); } rtc->type->lock(rtc); @@ -898,8 +901,7 @@ static int omap_rtc_suspend(struct device *dev) rtc_write(rtc, OMAP_RTC_INTERRUPTS_REG, 0); rtc->type->lock(rtc); - /* Disable the clock/module */ - pm_runtime_put_sync(dev); + rtc->is_suspending = true; return 0; } @@ -908,9 +910,6 @@ static int omap_rtc_resume(struct device *dev) { struct omap_rtc *rtc = dev_get_drvdata(dev); - /* Enable the clock/module so that we can access the registers */ - pm_runtime_get_sync(dev); - rtc->type->unlock(rtc); if (device_may_wakeup(dev)) disable_irq_wake(rtc->irq_alarm); @@ -918,11 +917,34 @@ static int omap_rtc_resume(struct device *dev) rtc_write(rtc, OMAP_RTC_INTERRUPTS_REG, rtc->interrupts_reg); rtc->type->lock(rtc); + rtc->is_suspending = false; + return 0; } #endif -static SIMPLE_DEV_PM_OPS(omap_rtc_pm_ops, omap_rtc_suspend, omap_rtc_resume); +#ifdef CONFIG_PM +static int omap_rtc_runtime_suspend(struct device *dev) +{ + struct omap_rtc *rtc = dev_get_drvdata(dev); + + if (rtc->is_suspending && !rtc->has_ext_clk) + return -EBUSY; + + return 0; +} + +static int omap_rtc_runtime_resume(struct device *dev) +{ + return 0; +} +#endif + +static const struct dev_pm_ops omap_rtc_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(omap_rtc_suspend, omap_rtc_resume) + SET_RUNTIME_PM_OPS(omap_rtc_runtime_suspend, + omap_rtc_runtime_resume, NULL) +}; static void omap_rtc_shutdown(struct platform_device *pdev) { diff --git a/drivers/video/fbdev/amba-clcd-versatile.c b/drivers/video/fbdev/amba-clcd-versatile.c index 19ad8645d93c..e5d9bfc1703a 100644 --- a/drivers/video/fbdev/amba-clcd-versatile.c +++ b/drivers/video/fbdev/amba-clcd-versatile.c @@ -526,8 +526,8 @@ int versatile_clcd_init_panel(struct clcd_fb *fb, np = of_find_matching_node_and_match(NULL, versatile_clcd_of_match, &clcd_id); if (!np) { - dev_err(dev, "no Versatile syscon node\n"); - return -ENODEV; + /* Vexpress does not have this */ + return 0; } versatile_clcd_type = (enum versatile_clcd)clcd_id->data; diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c index 9a28133ac3b8..9b774f4b50c8 100644 --- a/fs/crypto/fname.c +++ b/fs/crypto/fname.c @@ -39,65 +39,54 @@ static void fname_crypt_complete(struct crypto_async_request *req, int res) static int fname_encrypt(struct inode *inode, const struct qstr *iname, struct fscrypt_str *oname) { - u32 ciphertext_len; struct skcipher_request *req = NULL; DECLARE_FS_COMPLETION_RESULT(ecr); struct fscrypt_info *ci = inode->i_crypt_info; struct crypto_skcipher *tfm = ci->ci_ctfm; int res = 0; char iv[FS_CRYPTO_BLOCK_SIZE]; - struct scatterlist src_sg, dst_sg; + struct scatterlist sg; int padding = 4 << (ci->ci_flags & FS_POLICY_FLAGS_PAD_MASK); - char *workbuf, buf[32], *alloc_buf = NULL; - unsigned lim; + unsigned int lim; + unsigned int cryptlen; lim = inode->i_sb->s_cop->max_namelen(inode); if (iname->len <= 0 || iname->len > lim) return -EIO; - ciphertext_len = max(iname->len, (u32)FS_CRYPTO_BLOCK_SIZE); - ciphertext_len = round_up(ciphertext_len, padding); - ciphertext_len = min(ciphertext_len, lim); + /* + * Copy the filename to the output buffer for encrypting in-place and + * pad it with the needed number of NUL bytes. + */ + cryptlen = max_t(unsigned int, iname->len, FS_CRYPTO_BLOCK_SIZE); + cryptlen = round_up(cryptlen, padding); + cryptlen = min(cryptlen, lim); + memcpy(oname->name, iname->name, iname->len); + memset(oname->name + iname->len, 0, cryptlen - iname->len); - if (ciphertext_len <= sizeof(buf)) { - workbuf = buf; - } else { - alloc_buf = kmalloc(ciphertext_len, GFP_NOFS); - if (!alloc_buf) - return -ENOMEM; - workbuf = alloc_buf; - } + /* Initialize the IV */ + memset(iv, 0, FS_CRYPTO_BLOCK_SIZE); - /* Allocate request */ + /* Set up the encryption request */ req = skcipher_request_alloc(tfm, GFP_NOFS); if (!req) { printk_ratelimited(KERN_ERR - "%s: crypto_request_alloc() failed\n", __func__); - kfree(alloc_buf); + "%s: skcipher_request_alloc() failed\n", __func__); return -ENOMEM; } skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, fname_crypt_complete, &ecr); + sg_init_one(&sg, oname->name, cryptlen); + skcipher_request_set_crypt(req, &sg, &sg, cryptlen, iv); - /* Copy the input */ - memcpy(workbuf, iname->name, iname->len); - if (iname->len < ciphertext_len) - memset(workbuf + iname->len, 0, ciphertext_len - iname->len); - - /* Initialize IV */ - memset(iv, 0, FS_CRYPTO_BLOCK_SIZE); - - /* Create encryption request */ - sg_init_one(&src_sg, workbuf, ciphertext_len); - sg_init_one(&dst_sg, oname->name, ciphertext_len); - skcipher_request_set_crypt(req, &src_sg, &dst_sg, ciphertext_len, iv); + /* Do the encryption */ res = crypto_skcipher_encrypt(req); if (res == -EINPROGRESS || res == -EBUSY) { + /* Request is being completed asynchronously; wait for it */ wait_for_completion(&ecr.completion); res = ecr.res; } - kfree(alloc_buf); skcipher_request_free(req); if (res < 0) { printk_ratelimited(KERN_ERR @@ -105,7 +94,7 @@ static int fname_encrypt(struct inode *inode, return res; } - oname->len = ciphertext_len; + oname->len = cryptlen; return 0; } diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c index 82f0285f5d08..67fb6d8876d0 100644 --- a/fs/crypto/keyinfo.c +++ b/fs/crypto/keyinfo.c @@ -185,7 +185,7 @@ int get_crypt_info(struct inode *inode) struct crypto_skcipher *ctfm; const char *cipher_str; int keysize; - u8 raw_key[FS_MAX_KEY_SIZE]; + u8 *raw_key = NULL; int res; res = fscrypt_initialize(); @@ -238,6 +238,15 @@ retry: if (res) goto out; + /* + * This cannot be a stack buffer because it is passed to the scatterlist + * crypto API as part of key derivation. + */ + res = -ENOMEM; + raw_key = kmalloc(FS_MAX_KEY_SIZE, GFP_NOFS); + if (!raw_key) + goto out; + if (fscrypt_dummy_context_enabled(inode)) { memset(raw_key, 0x42, FS_AES_256_XTS_KEY_SIZE); goto got_key; @@ -276,7 +285,8 @@ got_key: if (res) goto out; - memzero_explicit(raw_key, sizeof(raw_key)); + kzfree(raw_key); + raw_key = NULL; if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) != NULL) { put_crypt_info(crypt_info); goto retry; @@ -287,7 +297,7 @@ out: if (res == -ENOKEY) res = 0; put_crypt_info(crypt_info); - memzero_explicit(raw_key, sizeof(raw_key)); + kzfree(raw_key); return res; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 282a51b07c57..a8a750f59621 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -235,6 +235,7 @@ struct ext4_io_submit { #define EXT4_MAX_BLOCK_SIZE 65536 #define EXT4_MIN_BLOCK_LOG_SIZE 10 #define EXT4_MAX_BLOCK_LOG_SIZE 16 +#define EXT4_MAX_CLUSTER_LOG_SIZE 30 #ifdef __KERNEL__ # define EXT4_BLOCK_SIZE(s) ((s)->s_blocksize) #else diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 20da99da0a34..52b0530c5d65 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3565,7 +3565,15 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (blocksize < EXT4_MIN_BLOCK_SIZE || blocksize > EXT4_MAX_BLOCK_SIZE) { ext4_msg(sb, KERN_ERR, - "Unsupported filesystem blocksize %d", blocksize); + "Unsupported filesystem blocksize %d (%d log_block_size)", + blocksize, le32_to_cpu(es->s_log_block_size)); + goto failed_mount; + } + if (le32_to_cpu(es->s_log_block_size) > + (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { + ext4_msg(sb, KERN_ERR, + "Invalid log block size: %u", + le32_to_cpu(es->s_log_block_size)); goto failed_mount; } @@ -3697,6 +3705,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) "block size (%d)", clustersize, blocksize); goto failed_mount; } + if (le32_to_cpu(es->s_log_cluster_size) > + (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { + ext4_msg(sb, KERN_ERR, + "Invalid log cluster size: %u", + le32_to_cpu(es->s_log_cluster_size)); + goto failed_mount; + } sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) - le32_to_cpu(es->s_log_block_size); sbi->s_clusters_per_group = diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 6a4d0e5418a1..b3ebe512d64c 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -286,6 +286,11 @@ const struct dentry_operations fuse_dentry_operations = { .d_release = fuse_dentry_release, }; +const struct dentry_operations fuse_root_dentry_operations = { + .d_init = fuse_dentry_init, + .d_release = fuse_dentry_release, +}; + int fuse_valid_type(int m) { return S_ISREG(m) || S_ISDIR(m) || S_ISLNK(m) || S_ISCHR(m) || diff --git a/fs/fuse/file.c b/fs/fuse/file.c index abc66a6237fd..2401c5dabb2a 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1985,6 +1985,10 @@ static int fuse_write_end(struct file *file, struct address_space *mapping, { struct inode *inode = page->mapping->host; + /* Haven't copied anything? Skip zeroing, size extending, dirtying. */ + if (!copied) + goto unlock; + if (!PageUptodate(page)) { /* Zero any unwritten bytes at the end of the page */ size_t endoff = (pos + copied) & ~PAGE_MASK; @@ -1995,6 +1999,8 @@ static int fuse_write_end(struct file *file, struct address_space *mapping, fuse_write_update_size(inode, pos + copied); set_page_dirty(page); + +unlock: unlock_page(page); put_page(page); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 0dfbb136e59a..91307940c8ac 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -692,6 +692,7 @@ static inline u64 get_node_id(struct inode *inode) extern const struct file_operations fuse_dev_operations; extern const struct dentry_operations fuse_dentry_operations; +extern const struct dentry_operations fuse_root_dentry_operations; /** * Inode to nodeid comparison. diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 17141099f2e7..6fe6a88ecb4a 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1131,10 +1131,11 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) err = -ENOMEM; root = fuse_get_root_inode(sb, d.rootmode); + sb->s_d_op = &fuse_root_dentry_operations; root_dentry = d_make_root(root); if (!root_dentry) goto err_dev_free; - /* only now - we want root dentry with NULL ->d_op */ + /* Root dentry doesn't have .d_revalidate */ sb->s_d_op = &fuse_dentry_operations; init_req = fuse_request_alloc(0); diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c index d484068ca716..38887cc5577f 100644 --- a/fs/orangefs/orangefs-debugfs.c +++ b/fs/orangefs/orangefs-debugfs.c @@ -114,6 +114,7 @@ static const struct seq_operations help_debug_ops = { }; const struct file_operations debug_help_fops = { + .owner = THIS_MODULE, .open = orangefs_debug_help_open, .read = seq_read, .release = seq_release, @@ -121,6 +122,7 @@ const struct file_operations debug_help_fops = { }; static const struct file_operations kernel_debug_fops = { + .owner = THIS_MODULE, .open = orangefs_debug_open, .read = orangefs_debug_read, .write = orangefs_debug_write, diff --git a/fs/xattr.c b/fs/xattr.c index 3368659c471e..2d13b4e62fae 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -170,7 +170,7 @@ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = dentry->d_inode; - int error = -EOPNOTSUPP; + int error = -EAGAIN; int issec = !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN); @@ -183,15 +183,21 @@ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name, security_inode_post_setxattr(dentry, name, value, size, flags); } - } else if (issec) { - const char *suffix = name + XATTR_SECURITY_PREFIX_LEN; - + } else { if (unlikely(is_bad_inode(inode))) return -EIO; - error = security_inode_setsecurity(inode, suffix, value, - size, flags); - if (!error) - fsnotify_xattr(dentry); + } + if (error == -EAGAIN) { + error = -EOPNOTSUPP; + + if (issec) { + const char *suffix = name + XATTR_SECURITY_PREFIX_LEN; + + error = security_inode_setsecurity(inode, suffix, value, + size, flags); + if (!error) + fsnotify_xattr(dentry); + } } return error; diff --git a/include/acpi/actbl.h b/include/acpi/actbl.h index 1b949e08015c..c19700e2a2fe 100644 --- a/include/acpi/actbl.h +++ b/include/acpi/actbl.h @@ -230,72 +230,62 @@ struct acpi_table_facs { /* Fields common to all versions of the FADT */ struct acpi_table_fadt { - struct acpi_table_header header; /* [V1] Common ACPI table header */ - u32 facs; /* [V1] 32-bit physical address of FACS */ - u32 dsdt; /* [V1] 32-bit physical address of DSDT */ - u8 model; /* [V1] System Interrupt Model (ACPI 1.0) - not used in ACPI 2.0+ */ - u8 preferred_profile; /* [V1] Conveys preferred power management profile to OSPM. */ - u16 sci_interrupt; /* [V1] System vector of SCI interrupt */ - u32 smi_command; /* [V1] 32-bit Port address of SMI command port */ - u8 acpi_enable; /* [V1] Value to write to SMI_CMD to enable ACPI */ - u8 acpi_disable; /* [V1] Value to write to SMI_CMD to disable ACPI */ - u8 s4_bios_request; /* [V1] Value to write to SMI_CMD to enter S4BIOS state */ - u8 pstate_control; /* [V1] Processor performance state control */ - u32 pm1a_event_block; /* [V1] 32-bit port address of Power Mgt 1a Event Reg Blk */ - u32 pm1b_event_block; /* [V1] 32-bit port address of Power Mgt 1b Event Reg Blk */ - u32 pm1a_control_block; /* [V1] 32-bit port address of Power Mgt 1a Control Reg Blk */ - u32 pm1b_control_block; /* [V1] 32-bit port address of Power Mgt 1b Control Reg Blk */ - u32 pm2_control_block; /* [V1] 32-bit port address of Power Mgt 2 Control Reg Blk */ - u32 pm_timer_block; /* [V1] 32-bit port address of Power Mgt Timer Ctrl Reg Blk */ - u32 gpe0_block; /* [V1] 32-bit port address of General Purpose Event 0 Reg Blk */ - u32 gpe1_block; /* [V1] 32-bit port address of General Purpose Event 1 Reg Blk */ - u8 pm1_event_length; /* [V1] Byte Length of ports at pm1x_event_block */ - u8 pm1_control_length; /* [V1] Byte Length of ports at pm1x_control_block */ - u8 pm2_control_length; /* [V1] Byte Length of ports at pm2_control_block */ - u8 pm_timer_length; /* [V1] Byte Length of ports at pm_timer_block */ - u8 gpe0_block_length; /* [V1] Byte Length of ports at gpe0_block */ - u8 gpe1_block_length; /* [V1] Byte Length of ports at gpe1_block */ - u8 gpe1_base; /* [V1] Offset in GPE number space where GPE1 events start */ - u8 cst_control; /* [V1] Support for the _CST object and C-States change notification */ - u16 c2_latency; /* [V1] Worst case HW latency to enter/exit C2 state */ - u16 c3_latency; /* [V1] Worst case HW latency to enter/exit C3 state */ - u16 flush_size; /* [V1] Processor memory cache line width, in bytes */ - u16 flush_stride; /* [V1] Number of flush strides that need to be read */ - u8 duty_offset; /* [V1] Processor duty cycle index in processor P_CNT reg */ - u8 duty_width; /* [V1] Processor duty cycle value bit width in P_CNT register */ - u8 day_alarm; /* [V1] Index to day-of-month alarm in RTC CMOS RAM */ - u8 month_alarm; /* [V1] Index to month-of-year alarm in RTC CMOS RAM */ - u8 century; /* [V1] Index to century in RTC CMOS RAM */ - u16 boot_flags; /* [V3] IA-PC Boot Architecture Flags (see below for individual flags) */ - u8 reserved; /* [V1] Reserved, must be zero */ - u32 flags; /* [V1] Miscellaneous flag bits (see below for individual flags) */ - /* End of Version 1 FADT fields (ACPI 1.0) */ - - struct acpi_generic_address reset_register; /* [V3] 64-bit address of the Reset register */ - u8 reset_value; /* [V3] Value to write to the reset_register port to reset the system */ - u16 arm_boot_flags; /* [V5] ARM-Specific Boot Flags (see below for individual flags) (ACPI 5.1) */ - u8 minor_revision; /* [V5] FADT Minor Revision (ACPI 5.1) */ - u64 Xfacs; /* [V3] 64-bit physical address of FACS */ - u64 Xdsdt; /* [V3] 64-bit physical address of DSDT */ - struct acpi_generic_address xpm1a_event_block; /* [V3] 64-bit Extended Power Mgt 1a Event Reg Blk address */ - struct acpi_generic_address xpm1b_event_block; /* [V3] 64-bit Extended Power Mgt 1b Event Reg Blk address */ - struct acpi_generic_address xpm1a_control_block; /* [V3] 64-bit Extended Power Mgt 1a Control Reg Blk address */ - struct acpi_generic_address xpm1b_control_block; /* [V3] 64-bit Extended Power Mgt 1b Control Reg Blk address */ - struct acpi_generic_address xpm2_control_block; /* [V3] 64-bit Extended Power Mgt 2 Control Reg Blk address */ - struct acpi_generic_address xpm_timer_block; /* [V3] 64-bit Extended Power Mgt Timer Ctrl Reg Blk address */ - struct acpi_generic_address xgpe0_block; /* [V3] 64-bit Extended General Purpose Event 0 Reg Blk address */ - struct acpi_generic_address xgpe1_block; /* [V3] 64-bit Extended General Purpose Event 1 Reg Blk address */ - /* End of Version 3 FADT fields (ACPI 2.0) */ - - struct acpi_generic_address sleep_control; /* [V4] 64-bit Sleep Control register (ACPI 5.0) */ - /* End of Version 4 FADT fields (ACPI 3.0 and ACPI 4.0) (Field was originally reserved in ACPI 3.0) */ - - struct acpi_generic_address sleep_status; /* [V5] 64-bit Sleep Status register (ACPI 5.0) */ - /* End of Version 5 FADT fields (ACPI 5.0) */ - - u64 hypervisor_id; /* [V6] Hypervisor Vendor ID (ACPI 6.0) */ - /* End of Version 6 FADT fields (ACPI 6.0) */ - + struct acpi_table_header header; /* Common ACPI table header */ + u32 facs; /* 32-bit physical address of FACS */ + u32 dsdt; /* 32-bit physical address of DSDT */ + u8 model; /* System Interrupt Model (ACPI 1.0) - not used in ACPI 2.0+ */ + u8 preferred_profile; /* Conveys preferred power management profile to OSPM. */ + u16 sci_interrupt; /* System vector of SCI interrupt */ + u32 smi_command; /* 32-bit Port address of SMI command port */ + u8 acpi_enable; /* Value to write to SMI_CMD to enable ACPI */ + u8 acpi_disable; /* Value to write to SMI_CMD to disable ACPI */ + u8 s4_bios_request; /* Value to write to SMI_CMD to enter S4BIOS state */ + u8 pstate_control; /* Processor performance state control */ + u32 pm1a_event_block; /* 32-bit port address of Power Mgt 1a Event Reg Blk */ + u32 pm1b_event_block; /* 32-bit port address of Power Mgt 1b Event Reg Blk */ + u32 pm1a_control_block; /* 32-bit port address of Power Mgt 1a Control Reg Blk */ + u32 pm1b_control_block; /* 32-bit port address of Power Mgt 1b Control Reg Blk */ + u32 pm2_control_block; /* 32-bit port address of Power Mgt 2 Control Reg Blk */ + u32 pm_timer_block; /* 32-bit port address of Power Mgt Timer Ctrl Reg Blk */ + u32 gpe0_block; /* 32-bit port address of General Purpose Event 0 Reg Blk */ + u32 gpe1_block; /* 32-bit port address of General Purpose Event 1 Reg Blk */ + u8 pm1_event_length; /* Byte Length of ports at pm1x_event_block */ + u8 pm1_control_length; /* Byte Length of ports at pm1x_control_block */ + u8 pm2_control_length; /* Byte Length of ports at pm2_control_block */ + u8 pm_timer_length; /* Byte Length of ports at pm_timer_block */ + u8 gpe0_block_length; /* Byte Length of ports at gpe0_block */ + u8 gpe1_block_length; /* Byte Length of ports at gpe1_block */ + u8 gpe1_base; /* Offset in GPE number space where GPE1 events start */ + u8 cst_control; /* Support for the _CST object and C-States change notification */ + u16 c2_latency; /* Worst case HW latency to enter/exit C2 state */ + u16 c3_latency; /* Worst case HW latency to enter/exit C3 state */ + u16 flush_size; /* Processor memory cache line width, in bytes */ + u16 flush_stride; /* Number of flush strides that need to be read */ + u8 duty_offset; /* Processor duty cycle index in processor P_CNT reg */ + u8 duty_width; /* Processor duty cycle value bit width in P_CNT register */ + u8 day_alarm; /* Index to day-of-month alarm in RTC CMOS RAM */ + u8 month_alarm; /* Index to month-of-year alarm in RTC CMOS RAM */ + u8 century; /* Index to century in RTC CMOS RAM */ + u16 boot_flags; /* IA-PC Boot Architecture Flags (see below for individual flags) */ + u8 reserved; /* Reserved, must be zero */ + u32 flags; /* Miscellaneous flag bits (see below for individual flags) */ + struct acpi_generic_address reset_register; /* 64-bit address of the Reset register */ + u8 reset_value; /* Value to write to the reset_register port to reset the system */ + u16 arm_boot_flags; /* ARM-Specific Boot Flags (see below for individual flags) (ACPI 5.1) */ + u8 minor_revision; /* FADT Minor Revision (ACPI 5.1) */ + u64 Xfacs; /* 64-bit physical address of FACS */ + u64 Xdsdt; /* 64-bit physical address of DSDT */ + struct acpi_generic_address xpm1a_event_block; /* 64-bit Extended Power Mgt 1a Event Reg Blk address */ + struct acpi_generic_address xpm1b_event_block; /* 64-bit Extended Power Mgt 1b Event Reg Blk address */ + struct acpi_generic_address xpm1a_control_block; /* 64-bit Extended Power Mgt 1a Control Reg Blk address */ + struct acpi_generic_address xpm1b_control_block; /* 64-bit Extended Power Mgt 1b Control Reg Blk address */ + struct acpi_generic_address xpm2_control_block; /* 64-bit Extended Power Mgt 2 Control Reg Blk address */ + struct acpi_generic_address xpm_timer_block; /* 64-bit Extended Power Mgt Timer Ctrl Reg Blk address */ + struct acpi_generic_address xgpe0_block; /* 64-bit Extended General Purpose Event 0 Reg Blk address */ + struct acpi_generic_address xgpe1_block; /* 64-bit Extended General Purpose Event 1 Reg Blk address */ + struct acpi_generic_address sleep_control; /* 64-bit Sleep Control register (ACPI 5.0) */ + struct acpi_generic_address sleep_status; /* 64-bit Sleep Status register (ACPI 5.0) */ + u64 hypervisor_id; /* Hypervisor Vendor ID (ACPI 6.0) */ }; /* Masks for FADT IA-PC Boot Architecture Flags (boot_flags) [Vx]=Introduced in this FADT revision */ @@ -311,8 +301,8 @@ struct acpi_table_fadt { /* Masks for FADT ARM Boot Architecture Flags (arm_boot_flags) ACPI 5.1 */ -#define ACPI_FADT_PSCI_COMPLIANT (1) /* 00: [V5] PSCI 0.2+ is implemented */ -#define ACPI_FADT_PSCI_USE_HVC (1<<1) /* 01: [V5] HVC must be used instead of SMC as the PSCI conduit */ +#define ACPI_FADT_PSCI_COMPLIANT (1) /* 00: [V5+] PSCI 0.2+ is implemented */ +#define ACPI_FADT_PSCI_USE_HVC (1<<1) /* 01: [V5+] HVC must be used instead of SMC as the PSCI conduit */ /* Masks for FADT flags */ @@ -409,34 +399,20 @@ struct acpi_table_desc { * match the expected length. In other words, the length of the * FADT is the bottom line as to what the version really is. * - * NOTE: There is no officialy released V2 of the FADT. This - * version was used only for prototyping and testing during the - * 32-bit to 64-bit transition. V3 was the first official 64-bit - * version of the FADT. - * - * Update this list of defines when a new version of the FADT is - * added to the ACPI specification. Note that the FADT version is - * only incremented when new fields are appended to the existing - * version. Therefore, the FADT version is competely independent - * from the version of the ACPI specification where it is - * defined. - * - * For reference, the various FADT lengths are as follows: - * FADT V1 size: 0x074 ACPI 1.0 - * FADT V3 size: 0x0F4 ACPI 2.0 - * FADT V4 size: 0x100 ACPI 3.0 and ACPI 4.0 - * FADT V5 size: 0x10C ACPI 5.0 - * FADT V6 size: 0x114 ACPI 6.0 + * For reference, the values below are as follows: + * FADT V1 size: 0x074 + * FADT V2 size: 0x084 + * FADT V3 size: 0x0F4 + * FADT V4 size: 0x0F4 + * FADT V5 size: 0x10C + * FADT V6 size: 0x114 */ -#define ACPI_FADT_V1_SIZE (u32) (ACPI_FADT_OFFSET (flags) + 4) /* ACPI 1.0 */ -#define ACPI_FADT_V3_SIZE (u32) (ACPI_FADT_OFFSET (sleep_control)) /* ACPI 2.0 */ -#define ACPI_FADT_V4_SIZE (u32) (ACPI_FADT_OFFSET (sleep_status)) /* ACPI 3.0 and ACPI 4.0 */ -#define ACPI_FADT_V5_SIZE (u32) (ACPI_FADT_OFFSET (hypervisor_id)) /* ACPI 5.0 */ -#define ACPI_FADT_V6_SIZE (u32) (sizeof (struct acpi_table_fadt)) /* ACPI 6.0 */ +#define ACPI_FADT_V1_SIZE (u32) (ACPI_FADT_OFFSET (flags) + 4) +#define ACPI_FADT_V2_SIZE (u32) (ACPI_FADT_OFFSET (minor_revision) + 1) +#define ACPI_FADT_V3_SIZE (u32) (ACPI_FADT_OFFSET (sleep_control)) +#define ACPI_FADT_V5_SIZE (u32) (ACPI_FADT_OFFSET (hypervisor_id)) +#define ACPI_FADT_V6_SIZE (u32) (sizeof (struct acpi_table_fadt)) -/* Update these when new FADT versions are added */ - -#define ACPI_FADT_MAX_VERSION 6 #define ACPI_FADT_CONFORMANCE "ACPI 6.1 (FADT version 6)" #endif /* __ACTBL_H__ */ diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h index a5d98d171866..e861a24f06f2 100644 --- a/include/acpi/platform/aclinux.h +++ b/include/acpi/platform/aclinux.h @@ -191,6 +191,9 @@ #ifndef __init #define __init #endif +#ifndef __iomem +#define __iomem +#endif /* Host-dependent types and defines for user-space ACPICA */ diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 9b9f65d99873..e35e6de633b9 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -22,7 +22,7 @@ extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned char *vec); extern bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, unsigned long old_end, - pmd_t *old_pmd, pmd_t *new_pmd); + pmd_t *old_pmd, pmd_t *new_pmd, bool *need_flush); extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, int prot_numa); diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index ca1ad9ebbc92..a0649973ee5b 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -149,7 +149,7 @@ static inline bool inet6_exact_dif_match(struct net *net, struct sk_buff *skb) { #if defined(CONFIG_NET_L3_MASTER_DEV) if (!net->ipv4.sysctl_tcp_l3mdev_accept && - ipv6_l3mdev_skb(IP6CB(skb)->flags)) + skb && ipv6_l3mdev_skb(IP6CB(skb)->flags)) return true; #endif return false; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 91ee3643ccc8..bf04a46f6d5b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3354,6 +3354,21 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb); +static __always_inline int ____dev_forward_skb(struct net_device *dev, + struct sk_buff *skb) +{ + if (skb_orphan_frags(skb, GFP_ATOMIC) || + unlikely(!is_skb_forwardable(dev, skb))) { + atomic_long_inc(&dev->rx_dropped); + kfree_skb(skb); + return NET_RX_DROP; + } + + skb_scrub_packet(skb, true); + skb->priority = 0; + return 0; +} + void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev); extern int netdev_budget; diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index ab02a457da1f..e5d193440374 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -25,6 +25,7 @@ struct svc_xprt_ops { void (*xpo_detach)(struct svc_xprt *); void (*xpo_free)(struct svc_xprt *); int (*xpo_secure_port)(struct svc_rqst *); + void (*xpo_kill_temp_xprt)(struct svc_xprt *); }; struct svc_xprt_class { diff --git a/include/net/ip.h b/include/net/ip.h index 5413883ac47f..d3a107850a41 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -47,8 +47,7 @@ struct inet_skb_parm { #define IPSKB_REROUTED BIT(4) #define IPSKB_DOREDIRECT BIT(5) #define IPSKB_FRAG_PMTU BIT(6) -#define IPSKB_FRAG_SEGS BIT(7) -#define IPSKB_L3SLAVE BIT(8) +#define IPSKB_L3SLAVE BIT(7) u16 frag_max_size; }; diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 20ed9699fcd4..1b1cf33cbfb0 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -146,6 +146,7 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, { int pkt_len, err; + memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); pkt_len = skb->len - skb_inner_network_offset(skb); err = ip6_local_out(dev_net(skb_dst(skb)->dev), sk, skb); if (unlikely(net_xmit_eval(err))) diff --git a/include/net/netfilter/nf_conntrack_labels.h b/include/net/netfilter/nf_conntrack_labels.h index 498814626e28..1723a67c0b0a 100644 --- a/include/net/netfilter/nf_conntrack_labels.h +++ b/include/net/netfilter/nf_conntrack_labels.h @@ -30,8 +30,7 @@ static inline struct nf_conn_labels *nf_ct_labels_ext_add(struct nf_conn *ct) if (net->ct.labels_used == 0) return NULL; - return nf_ct_ext_add_length(ct, NF_CT_EXT_LABELS, - sizeof(struct nf_conn_labels), GFP_ATOMIC); + return nf_ct_ext_add(ct, NF_CT_EXT_LABELS, GFP_ATOMIC); #else return NULL; #endif diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 5031e072567b..d79d1e9b9546 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -145,7 +145,7 @@ static inline enum nft_registers nft_type_to_reg(enum nft_data_types type) return type == NFT_DATA_VERDICT ? NFT_REG_VERDICT : NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE; } -unsigned int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest); +int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest); unsigned int nft_parse_register(const struct nlattr *attr); int nft_dump_register(struct sk_buff *skb, unsigned int attr, unsigned int reg); @@ -542,7 +542,8 @@ void *nft_set_elem_init(const struct nft_set *set, const struct nft_set_ext_tmpl *tmpl, const u32 *key, const u32 *data, u64 timeout, gfp_t gfp); -void nft_set_elem_destroy(const struct nft_set *set, void *elem); +void nft_set_elem_destroy(const struct nft_set *set, void *elem, + bool destroy_expr); /** * struct nft_set_gc_batch_head - nf_tables set garbage collection batch @@ -693,7 +694,6 @@ static inline int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src) { int err; - __module_get(src->ops->type->owner); if (src->ops->clone) { dst->ops = src->ops; err = src->ops->clone(dst, src); @@ -702,6 +702,8 @@ static inline int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src) } else { memcpy(dst, src, src->ops->size); } + + __module_get(src->ops->type->owner); return 0; } diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 87a7f42e7639..31acc3f4f132 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -152,7 +152,7 @@ void sctp_unhash_endpoint(struct sctp_endpoint *); struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *, struct sctphdr *, struct sctp_association **, struct sctp_transport **); -void sctp_err_finish(struct sock *, struct sctp_association *); +void sctp_err_finish(struct sock *, struct sctp_transport *); void sctp_icmp_frag_needed(struct sock *, struct sctp_association *, struct sctp_transport *t, __u32 pmtu); void sctp_icmp_redirect(struct sock *, struct sctp_transport *, diff --git a/include/net/sock.h b/include/net/sock.h index 73c6b008f1b7..92b269709b9a 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1596,11 +1596,11 @@ static inline void sock_put(struct sock *sk) void sock_gen_put(struct sock *sk); int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested, - unsigned int trim_cap); + unsigned int trim_cap, bool refcounted); static inline int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested) { - return __sk_receive_skb(sk, skb, nested, 1); + return __sk_receive_skb(sk, skb, nested, 1, true); } static inline void sk_tx_queue_set(struct sock *sk, int tx_queue) diff --git a/include/net/tcp.h b/include/net/tcp.h index 5b82d4d94834..123979fe12bf 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -805,7 +805,7 @@ static inline bool inet_exact_dif_match(struct net *net, struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) if (!net->ipv4.sysctl_tcp_l3mdev_accept && - ipv4_l3mdev_skb(TCP_SKB_CB(skb)->header.h4.flags)) + skb && ipv4_l3mdev_skb(TCP_SKB_CB(skb)->header.h4.flags)) return true; #endif return false; @@ -1220,6 +1220,7 @@ static inline void tcp_prequeue_init(struct tcp_sock *tp) bool tcp_prequeue(struct sock *sk, struct sk_buff *skb); bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb); +int tcp_filter(struct sock *sk, struct sk_buff *skb); #undef STATE_TRACE diff --git a/include/uapi/linux/atm_zatm.h b/include/uapi/linux/atm_zatm.h index 5cd4d4d2dd1d..9c9c6ad55f14 100644 --- a/include/uapi/linux/atm_zatm.h +++ b/include/uapi/linux/atm_zatm.h @@ -14,7 +14,6 @@ #include #include -#include #define ZATM_GETPOOL _IOW('a',ATMIOC_SARPRV+1,struct atmif_sioc) /* get pool statistics */ diff --git a/include/uapi/linux/bpqether.h b/include/uapi/linux/bpqether.h index a6c35e1a89ad..05865edaefda 100644 --- a/include/uapi/linux/bpqether.h +++ b/include/uapi/linux/bpqether.h @@ -5,9 +5,7 @@ * Defines for the BPQETHER pseudo device driver */ -#ifndef __LINUX_IF_ETHER_H #include -#endif #define SIOCSBPQETHOPT (SIOCDEVPRIVATE+0) /* reserved */ #define SIOCSBPQETHADDR (SIOCDEVPRIVATE+1) diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 300ef255d1e0..4ee67cb99143 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -972,12 +972,19 @@ struct kvm_irqfd { __u8 pad[16]; }; +/* For KVM_CAP_ADJUST_CLOCK */ + +/* Do not use 1, KVM_CHECK_EXTENSION returned it before we had flags. */ +#define KVM_CLOCK_TSC_STABLE 2 + struct kvm_clock_data { __u64 clock; __u32 flags; __u32 pad[9]; }; +/* For KVM_CAP_SW_TLB */ + #define KVM_MMU_FSL_BOOKE_NOHV 0 #define KVM_MMU_FSL_BOOKE_HV 1 diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 570eeca7bdfa..ad1bc67aff1b 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -687,7 +687,8 @@ static void delete_all_elements(struct bpf_htab *htab) hlist_for_each_entry_safe(l, n, head, hash_node) { hlist_del_rcu(&l->hash_node); - htab_elem_free(htab, l); + if (l->state != HTAB_EXTRA_ELEM_USED) + htab_elem_free(htab, l); } } } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 228f962447a5..237f3d6a7ddc 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -194,7 +194,7 @@ static int map_create(union bpf_attr *attr) err = bpf_map_charge_memlock(map); if (err) - goto free_map; + goto free_map_nouncharge; err = bpf_map_new_fd(map); if (err < 0) @@ -204,6 +204,8 @@ static int map_create(union bpf_attr *attr) return err; free_map: + bpf_map_uncharge_memlock(map); +free_map_nouncharge: map->ops->map_free(map); return err; } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 9c4d30483264..6b669593e7eb 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1341,12 +1341,12 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) } else if (new->flags & IRQF_TRIGGER_MASK) { unsigned int nmsk = new->flags & IRQF_TRIGGER_MASK; - unsigned int omsk = irq_settings_get_trigger_mask(desc); + unsigned int omsk = irqd_get_trigger_type(&desc->irq_data); if (nmsk != omsk) /* hope the handler works with current trigger mode */ pr_warn("irq %d uses trigger mode %u; requested %u\n", - irq, nmsk, omsk); + irq, omsk, nmsk); } *old_ptr = new; diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 5028f4fd504a..f7a55e9ff2f7 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -783,8 +783,6 @@ static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from) return ret; } -static void cont_flush(void); - static ssize_t devkmsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -800,7 +798,6 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf, if (ret) return ret; raw_spin_lock_irq(&logbuf_lock); - cont_flush(); while (user->seq == log_next_seq) { if (file->f_flags & O_NONBLOCK) { ret = -EAGAIN; @@ -863,7 +860,6 @@ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence) return -ESPIPE; raw_spin_lock_irq(&logbuf_lock); - cont_flush(); switch (whence) { case SEEK_SET: /* the first record */ @@ -902,7 +898,6 @@ static unsigned int devkmsg_poll(struct file *file, poll_table *wait) poll_wait(file, &log_wait, wait); raw_spin_lock_irq(&logbuf_lock); - cont_flush(); if (user->seq < log_next_seq) { /* return error when data has vanished underneath us */ if (user->seq < log_first_seq) @@ -1289,7 +1284,6 @@ static int syslog_print(char __user *buf, int size) size_t skip; raw_spin_lock_irq(&logbuf_lock); - cont_flush(); if (syslog_seq < log_first_seq) { /* messages are gone, move to first one */ syslog_seq = log_first_seq; @@ -1349,7 +1343,6 @@ static int syslog_print_all(char __user *buf, int size, bool clear) return -ENOMEM; raw_spin_lock_irq(&logbuf_lock); - cont_flush(); if (buf) { u64 next_seq; u64 seq; @@ -1511,7 +1504,6 @@ int do_syslog(int type, char __user *buf, int len, int source) /* Number of chars in the log buffer */ case SYSLOG_ACTION_SIZE_UNREAD: raw_spin_lock_irq(&logbuf_lock); - cont_flush(); if (syslog_seq < log_first_seq) { /* messages are gone, move to first one */ syslog_seq = log_first_seq; @@ -3028,7 +3020,6 @@ void kmsg_dump(enum kmsg_dump_reason reason) dumper->active = true; raw_spin_lock_irqsave(&logbuf_lock, flags); - cont_flush(); dumper->cur_seq = clear_seq; dumper->cur_idx = clear_idx; dumper->next_seq = log_next_seq; @@ -3119,7 +3110,6 @@ bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, bool ret; raw_spin_lock_irqsave(&logbuf_lock, flags); - cont_flush(); ret = kmsg_dump_get_line_nolock(dumper, syslog, line, size, len); raw_spin_unlock_irqrestore(&logbuf_lock, flags); @@ -3162,7 +3152,6 @@ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, goto out; raw_spin_lock_irqsave(&logbuf_lock, flags); - cont_flush(); if (dumper->cur_seq < log_first_seq) { /* messages are gone, move to first available one */ dumper->cur_seq = log_first_seq; diff --git a/kernel/taskstats.c b/kernel/taskstats.c index b3f05ee20d18..cbb387a265db 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -54,7 +54,11 @@ static const struct nla_policy taskstats_cmd_get_policy[TASKSTATS_CMD_ATTR_MAX+1 [TASKSTATS_CMD_ATTR_REGISTER_CPUMASK] = { .type = NLA_STRING }, [TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK] = { .type = NLA_STRING },}; -static const struct nla_policy cgroupstats_cmd_get_policy[CGROUPSTATS_CMD_ATTR_MAX+1] = { +/* + * We have to use TASKSTATS_CMD_ATTR_MAX here, it is the maxattr in the family. + * Make sure they are always aligned. + */ +static const struct nla_policy cgroupstats_cmd_get_policy[TASKSTATS_CMD_ATTR_MAX+1] = { [CGROUPSTATS_CMD_ATTR_FD] = { .type = NLA_U32 }, }; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 2050a7652a86..da87b3cba5b3 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1862,6 +1862,10 @@ static int __ftrace_hash_update_ipmodify(struct ftrace_ops *ops, /* Update rec->flags */ do_for_each_ftrace_rec(pg, rec) { + + if (rec->flags & FTRACE_FL_DISABLED) + continue; + /* We need to update only differences of filter_hash */ in_old = !!ftrace_lookup_ip(old_hash, rec->ip); in_new = !!ftrace_lookup_ip(new_hash, rec->ip); @@ -1884,6 +1888,10 @@ rollback: /* Roll back what we did above */ do_for_each_ftrace_rec(pg, rec) { + + if (rec->flags & FTRACE_FL_DISABLED) + continue; + if (rec == end) goto err_out; @@ -2397,6 +2405,10 @@ void __weak ftrace_replace_code(int enable) return; do_for_each_ftrace_rec(pg, rec) { + + if (rec->flags & FTRACE_FL_DISABLED) + continue; + failed = __ftrace_replace_code(rec, enable); if (failed) { ftrace_bug(failed, rec); @@ -2763,7 +2775,7 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command) struct dyn_ftrace *rec; do_for_each_ftrace_rec(pg, rec) { - if (FTRACE_WARN_ON_ONCE(rec->flags)) + if (FTRACE_WARN_ON_ONCE(rec->flags & ~FTRACE_FL_DISABLED)) pr_warn(" %pS flags:%lx\n", (void *)rec->ip, rec->flags); } while_for_each_ftrace_rec(); @@ -3598,6 +3610,10 @@ match_records(struct ftrace_hash *hash, char *func, int len, char *mod) goto out_unlock; do_for_each_ftrace_rec(pg, rec) { + + if (rec->flags & FTRACE_FL_DISABLED) + continue; + if (ftrace_match_record(rec, &func_g, mod_match, exclude_mod)) { ret = enter_record(hash, rec, clear_filter); if (ret < 0) { @@ -3793,6 +3809,9 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, do_for_each_ftrace_rec(pg, rec) { + if (rec->flags & FTRACE_FL_DISABLED) + continue; + if (!ftrace_match_record(rec, &func_g, NULL, 0)) continue; @@ -4685,6 +4704,9 @@ ftrace_set_func(unsigned long *array, int *idx, int size, char *buffer) do_for_each_ftrace_rec(pg, rec) { + if (rec->flags & FTRACE_FL_DISABLED) + continue; + if (ftrace_match_record(rec, &func_g, NULL, 0)) { /* if it is in the array */ exists = false; diff --git a/lib/iov_iter.c b/lib/iov_iter.c index f0c7f1481bae..f2bd21b93dfc 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -683,10 +683,11 @@ static void pipe_advance(struct iov_iter *i, size_t size) struct pipe_inode_info *pipe = i->pipe; struct pipe_buffer *buf; int idx = i->idx; - size_t off = i->iov_offset; + size_t off = i->iov_offset, orig_sz; if (unlikely(i->count < size)) size = i->count; + orig_sz = size; if (size) { if (off) /* make it relative to the beginning of buffer */ @@ -713,6 +714,7 @@ static void pipe_advance(struct iov_iter *i, size_t size) pipe->nrbufs--; } } + i->count -= orig_sz; } void iov_iter_advance(struct iov_iter *i, size_t size) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index cdcd25cb30fe..eff3de359d50 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1426,11 +1426,12 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, unsigned long old_end, - pmd_t *old_pmd, pmd_t *new_pmd) + pmd_t *old_pmd, pmd_t *new_pmd, bool *need_flush) { spinlock_t *old_ptl, *new_ptl; pmd_t pmd; struct mm_struct *mm = vma->vm_mm; + bool force_flush = false; if ((old_addr & ~HPAGE_PMD_MASK) || (new_addr & ~HPAGE_PMD_MASK) || @@ -1455,6 +1456,8 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, new_ptl = pmd_lockptr(mm, new_pmd); if (new_ptl != old_ptl) spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); + if (pmd_present(*old_pmd) && pmd_dirty(*old_pmd)) + force_flush = true; pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd); VM_BUG_ON(!pmd_none(*new_pmd)); @@ -1467,6 +1470,10 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, set_pmd_at(mm, new_addr, new_pmd, pmd_mksoft_dirty(pmd)); if (new_ptl != old_ptl) spin_unlock(new_ptl); + if (force_flush) + flush_tlb_range(vma, old_addr, old_addr + PMD_SIZE); + else + *need_flush = true; spin_unlock(old_ptl); return true; } diff --git a/mm/mremap.c b/mm/mremap.c index da22ad2a5678..6ccecc03f56a 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -104,11 +104,13 @@ static pte_t move_soft_dirty_pte(pte_t pte) static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, unsigned long old_addr, unsigned long old_end, struct vm_area_struct *new_vma, pmd_t *new_pmd, - unsigned long new_addr, bool need_rmap_locks) + unsigned long new_addr, bool need_rmap_locks, bool *need_flush) { struct mm_struct *mm = vma->vm_mm; pte_t *old_pte, *new_pte, pte; spinlock_t *old_ptl, *new_ptl; + bool force_flush = false; + unsigned long len = old_end - old_addr; /* * When need_rmap_locks is true, we take the i_mmap_rwsem and anon_vma @@ -146,6 +148,14 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, new_pte++, new_addr += PAGE_SIZE) { if (pte_none(*old_pte)) continue; + + /* + * We are remapping a dirty PTE, make sure to + * flush TLB before we drop the PTL for the + * old PTE or we may race with page_mkclean(). + */ + if (pte_present(*old_pte) && pte_dirty(*old_pte)) + force_flush = true; pte = ptep_get_and_clear(mm, old_addr, old_pte); pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr); pte = move_soft_dirty_pte(pte); @@ -156,6 +166,10 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, if (new_ptl != old_ptl) spin_unlock(new_ptl); pte_unmap(new_pte - 1); + if (force_flush) + flush_tlb_range(vma, old_end - len, old_end); + else + *need_flush = true; pte_unmap_unlock(old_pte - 1, old_ptl); if (need_rmap_locks) drop_rmap_locks(vma); @@ -201,13 +215,12 @@ unsigned long move_page_tables(struct vm_area_struct *vma, if (need_rmap_locks) take_rmap_locks(vma); moved = move_huge_pmd(vma, old_addr, new_addr, - old_end, old_pmd, new_pmd); + old_end, old_pmd, new_pmd, + &need_flush); if (need_rmap_locks) drop_rmap_locks(vma); - if (moved) { - need_flush = true; + if (moved) continue; - } } split_huge_pmd(vma, old_pmd, old_addr); if (pmd_trans_unstable(old_pmd)) @@ -220,11 +233,10 @@ unsigned long move_page_tables(struct vm_area_struct *vma, extent = next - new_addr; if (extent > LATENCY_LIMIT) extent = LATENCY_LIMIT; - move_ptes(vma, old_pmd, old_addr, old_addr + extent, - new_vma, new_pmd, new_addr, need_rmap_locks); - need_flush = true; + move_ptes(vma, old_pmd, old_addr, old_addr + extent, new_vma, + new_pmd, new_addr, need_rmap_locks, &need_flush); } - if (likely(need_flush)) + if (need_flush) flush_tlb_range(vma, old_end-len, old_addr); mmu_notifier_invalidate_range_end(vma->vm_mm, mmun_start, mmun_end); diff --git a/net/can/bcm.c b/net/can/bcm.c index 8e999ffdf28b..8af9d25ff988 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1549,24 +1549,31 @@ static int bcm_connect(struct socket *sock, struct sockaddr *uaddr, int len, struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; struct bcm_sock *bo = bcm_sk(sk); + int ret = 0; if (len < sizeof(*addr)) return -EINVAL; - if (bo->bound) - return -EISCONN; + lock_sock(sk); + + if (bo->bound) { + ret = -EISCONN; + goto fail; + } /* bind a device to this socket */ if (addr->can_ifindex) { struct net_device *dev; dev = dev_get_by_index(&init_net, addr->can_ifindex); - if (!dev) - return -ENODEV; - + if (!dev) { + ret = -ENODEV; + goto fail; + } if (dev->type != ARPHRD_CAN) { dev_put(dev); - return -ENODEV; + ret = -ENODEV; + goto fail; } bo->ifindex = dev->ifindex; @@ -1577,17 +1584,24 @@ static int bcm_connect(struct socket *sock, struct sockaddr *uaddr, int len, bo->ifindex = 0; } - bo->bound = 1; - if (proc_dir) { /* unique socket address as filename */ sprintf(bo->procname, "%lu", sock_i_ino(sk)); bo->bcm_proc_read = proc_create_data(bo->procname, 0644, proc_dir, &bcm_proc_fops, sk); + if (!bo->bcm_proc_read) { + ret = -ENOMEM; + goto fail; + } } - return 0; + bo->bound = 1; + +fail: + release_sock(sk); + + return ret; } static int bcm_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, diff --git a/net/core/dev.c b/net/core/dev.c index 820bac239738..6666b28b6815 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1766,19 +1766,14 @@ EXPORT_SYMBOL_GPL(is_skb_forwardable); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb) { - if (skb_orphan_frags(skb, GFP_ATOMIC) || - unlikely(!is_skb_forwardable(dev, skb))) { - atomic_long_inc(&dev->rx_dropped); - kfree_skb(skb); - return NET_RX_DROP; + int ret = ____dev_forward_skb(dev, skb); + + if (likely(!ret)) { + skb->protocol = eth_type_trans(skb, dev); + skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } - skb_scrub_packet(skb, true); - skb->priority = 0; - skb->protocol = eth_type_trans(skb, dev); - skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); - - return 0; + return ret; } EXPORT_SYMBOL_GPL(__dev_forward_skb); @@ -2484,7 +2479,7 @@ int skb_checksum_help(struct sk_buff *skb) goto out; } - *(__sum16 *)(skb->data + offset) = csum_fold(csum); + *(__sum16 *)(skb->data + offset) = csum_fold(csum) ?: CSUM_MANGLED_0; out_set_summed: skb->ip_summed = CHECKSUM_NONE; out: diff --git a/net/core/filter.c b/net/core/filter.c index 00351cdf7d0c..b391209838ef 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1628,6 +1628,19 @@ static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb) return dev_forward_skb(dev, skb); } +static inline int __bpf_rx_skb_no_mac(struct net_device *dev, + struct sk_buff *skb) +{ + int ret = ____dev_forward_skb(dev, skb); + + if (likely(!ret)) { + skb->dev = dev; + ret = netif_rx(skb); + } + + return ret; +} + static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) { int ret; @@ -1647,6 +1660,51 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) return ret; } +static int __bpf_redirect_no_mac(struct sk_buff *skb, struct net_device *dev, + u32 flags) +{ + /* skb->mac_len is not set on normal egress */ + unsigned int mlen = skb->network_header - skb->mac_header; + + __skb_pull(skb, mlen); + + /* At ingress, the mac header has already been pulled once. + * At egress, skb_pospull_rcsum has to be done in case that + * the skb is originated from ingress (i.e. a forwarded skb) + * to ensure that rcsum starts at net header. + */ + if (!skb_at_tc_ingress(skb)) + skb_postpull_rcsum(skb, skb_mac_header(skb), mlen); + skb_pop_mac_header(skb); + skb_reset_mac_len(skb); + return flags & BPF_F_INGRESS ? + __bpf_rx_skb_no_mac(dev, skb) : __bpf_tx_skb(dev, skb); +} + +static int __bpf_redirect_common(struct sk_buff *skb, struct net_device *dev, + u32 flags) +{ + bpf_push_mac_rcsum(skb); + return flags & BPF_F_INGRESS ? + __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb); +} + +static int __bpf_redirect(struct sk_buff *skb, struct net_device *dev, + u32 flags) +{ + switch (dev->type) { + case ARPHRD_TUNNEL: + case ARPHRD_TUNNEL6: + case ARPHRD_SIT: + case ARPHRD_IPGRE: + case ARPHRD_VOID: + case ARPHRD_NONE: + return __bpf_redirect_no_mac(skb, dev, flags); + default: + return __bpf_redirect_common(skb, dev, flags); + } +} + BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags) { struct net_device *dev; @@ -1675,10 +1733,7 @@ BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags) return -ENOMEM; } - bpf_push_mac_rcsum(clone); - - return flags & BPF_F_INGRESS ? - __bpf_rx_skb(dev, clone) : __bpf_tx_skb(dev, clone); + return __bpf_redirect(clone, dev, flags); } static const struct bpf_func_proto bpf_clone_redirect_proto = { @@ -1722,10 +1777,7 @@ int skb_do_redirect(struct sk_buff *skb) return -EINVAL; } - bpf_push_mac_rcsum(skb); - - return ri->flags & BPF_F_INGRESS ? - __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb); + return __bpf_redirect(skb, dev, ri->flags); } static const struct bpf_func_proto bpf_redirect_proto = { diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index ab193e5def07..69e4463a4b1b 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -122,7 +122,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector_key_keyid *key_keyid; bool skip_vlan = false; u8 ip_proto = 0; - bool ret = false; + bool ret; if (!data) { data = skb->data; @@ -549,12 +549,17 @@ ip_proto_again: out_good: ret = true; -out_bad: + key_control->thoff = (u16)nhoff; +out: key_basic->n_proto = proto; key_basic->ip_proto = ip_proto; - key_control->thoff = (u16)nhoff; return ret; + +out_bad: + ret = false; + key_control->thoff = min_t(u16, nhoff, skb ? skb->len : hlen); + goto out; } EXPORT_SYMBOL(__skb_flow_dissect); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index fb7348f13501..db313ec7af32 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -275,6 +275,7 @@ int rtnl_unregister(int protocol, int msgtype) rtnl_msg_handlers[protocol][msgindex].doit = NULL; rtnl_msg_handlers[protocol][msgindex].dumpit = NULL; + rtnl_msg_handlers[protocol][msgindex].calcit = NULL; return 0; } diff --git a/net/core/sock.c b/net/core/sock.c index c73e28fc9c2a..5e3ca414357e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -453,7 +453,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) EXPORT_SYMBOL(sock_queue_rcv_skb); int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, - const int nested, unsigned int trim_cap) + const int nested, unsigned int trim_cap, bool refcounted) { int rc = NET_RX_SUCCESS; @@ -487,7 +487,8 @@ int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, bh_unlock_sock(sk); out: - sock_put(sk); + if (refcounted) + sock_put(sk); return rc; discard_and_relse: kfree_skb(skb); @@ -1543,6 +1544,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL); newsk->sk_err = 0; + newsk->sk_err_soft = 0; newsk->sk_priority = 0; newsk->sk_incoming_cpu = raw_smp_processor_id(); atomic64_set(&newsk->sk_cookie, 0); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 345a3aeb8c7e..b567c8725aea 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -235,7 +235,7 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) { const struct iphdr *iph = (struct iphdr *)skb->data; const u8 offset = iph->ihl << 2; - const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset); + const struct dccp_hdr *dh; struct dccp_sock *dp; struct inet_sock *inet; const int type = icmp_hdr(skb)->type; @@ -245,11 +245,13 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) int err; struct net *net = dev_net(skb->dev); - if (skb->len < offset + sizeof(*dh) || - skb->len < offset + __dccp_basic_hdr_len(dh)) { - __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); - return; - } + /* Only need dccph_dport & dccph_sport which are the first + * 4 bytes in dccp header. + * Our caller (icmp_socket_deliver()) already pulled 8 bytes for us. + */ + BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8); + BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8); + dh = (struct dccp_hdr *)(skb->data + offset); sk = __inet_lookup_established(net, &dccp_hashinfo, iph->daddr, dh->dccph_dport, @@ -868,7 +870,7 @@ lookup: goto discard_and_relse; nf_reset(skb); - return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4); + return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4, refcounted); no_dccp_socket: if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 3828f94b234c..715e5d1dc107 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -70,7 +70,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; - const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset); + const struct dccp_hdr *dh; struct dccp_sock *dp; struct ipv6_pinfo *np; struct sock *sk; @@ -78,12 +78,13 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, __u64 seq; struct net *net = dev_net(skb->dev); - if (skb->len < offset + sizeof(*dh) || - skb->len < offset + __dccp_basic_hdr_len(dh)) { - __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), - ICMP6_MIB_INERRORS); - return; - } + /* Only need dccph_dport & dccph_sport which are the first + * 4 bytes in dccp header. + * Our caller (icmpv6_notify()) already pulled 8 bytes for us. + */ + BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8); + BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8); + dh = (struct dccp_hdr *)(skb->data + offset); sk = __inet6_lookup_established(net, &dccp_hashinfo, &hdr->daddr, dh->dccph_dport, @@ -738,7 +739,8 @@ lookup: if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; - return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4) ? -1 : 0; + return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4, + refcounted) ? -1 : 0; no_dccp_socket: if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) @@ -956,6 +958,7 @@ static const struct inet_connection_sock_af_ops dccp_ipv6_mapped = { .getsockopt = ipv6_getsockopt, .addr2sockaddr = inet6_csk_addr2sockaddr, .sockaddr_len = sizeof(struct sockaddr_in6), + .bind_conflict = inet6_csk_bind_conflict, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_ipv6_setsockopt, .compat_getsockopt = compat_ipv6_getsockopt, diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 41e65804ddf5..9fe25bf63296 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -1009,6 +1009,10 @@ void dccp_close(struct sock *sk, long timeout) __kfree_skb(skb); } + /* If socket has been already reset kill it. */ + if (sk->sk_state == DCCP_CLOSED) + goto adjudge_to_death; + if (data_was_unread) { /* Unread data was tossed, send an appropriate Reset Code */ DCCP_WARN("ABORT with %u bytes unread\n", data_was_unread); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 9648c97e541f..5ddf5cda07f4 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -533,9 +533,9 @@ EXPORT_SYMBOL(inet_dgram_connect); static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) { - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, woken_wake_function); - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + add_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending += writebias; /* Basic assumption: if someone sets sk->sk_err, he _must_ @@ -545,13 +545,12 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) */ while ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { release_sock(sk); - timeo = schedule_timeout(timeo); + timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); lock_sock(sk); if (signal_pending(current) || !timeo) break; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } - finish_wait(sk_sleep(sk), &wait); + remove_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending -= writebias; return timeo; } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 31cef3602585..4cff74d4133f 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2413,22 +2413,19 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter, struct key_vector *l, **tp = &iter->tnode; t_key key; - /* use cache location of next-to-find key */ + /* use cached location of previously found key */ if (iter->pos > 0 && pos >= iter->pos) { - pos -= iter->pos; key = iter->key; } else { - iter->pos = 0; + iter->pos = 1; key = 0; } - while ((l = leaf_walk_rcu(tp, key)) != NULL) { + pos -= iter->pos; + + while ((l = leaf_walk_rcu(tp, key)) && (pos-- > 0)) { key = l->key + 1; iter->pos++; - - if (--pos <= 0) - break; - l = NULL; /* handle unlikely case of a key wrap */ @@ -2437,7 +2434,7 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter, } if (l) - iter->key = key; /* remember it */ + iter->key = l->key; /* remember it */ else iter->pos = 0; /* forget it */ @@ -2465,7 +2462,7 @@ static void *fib_route_seq_start(struct seq_file *seq, loff_t *pos) return fib_route_get_idx(iter, *pos); iter->pos = 0; - iter->key = 0; + iter->key = KEY_MAX; return SEQ_START_TOKEN; } @@ -2474,7 +2471,7 @@ static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct fib_route_iter *iter = seq->private; struct key_vector *l = NULL; - t_key key = iter->key; + t_key key = iter->key + 1; ++*pos; @@ -2483,7 +2480,7 @@ static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) l = leaf_walk_rcu(&iter->tnode, key); if (l) { - iter->key = l->key + 1; + iter->key = l->key; iter->pos++; } else { iter->pos = 0; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 38abe70e595f..48734ee6293f 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -477,7 +477,7 @@ static struct rtable *icmp_route_lookup(struct net *net, fl4->flowi4_proto = IPPROTO_ICMP; fl4->fl4_icmp_type = type; fl4->fl4_icmp_code = code; - fl4->flowi4_oif = l3mdev_master_ifindex(skb_in->dev); + fl4->flowi4_oif = l3mdev_master_ifindex(skb_dst(skb_in)->dev); security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4)); rt = __ip_route_output_key_hash(net, fl4, @@ -502,7 +502,7 @@ static struct rtable *icmp_route_lookup(struct net *net, if (err) goto relookup_failed; - if (inet_addr_type_dev_table(net, skb_in->dev, + if (inet_addr_type_dev_table(net, skb_dst(skb_in)->dev, fl4_dec.saddr) == RTN_LOCAL) { rt2 = __ip_route_output_key(net, &fl4_dec); if (IS_ERR(rt2)) diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 8b4ffd216839..9f0a7b96646f 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -117,7 +117,7 @@ int ip_forward(struct sk_buff *skb) if (opt->is_strictroute && rt->rt_uses_gateway) goto sr_failed; - IPCB(skb)->flags |= IPSKB_FORWARDED | IPSKB_FRAG_SEGS; + IPCB(skb)->flags |= IPSKB_FORWARDED; mtu = ip_dst_mtu_maybe_forward(&rt->dst, true); if (ip_exceeds_mtu(skb, mtu)) { IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 03e7f7310423..105908d841a3 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -239,19 +239,23 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, struct sk_buff *segs; int ret = 0; - /* common case: fragmentation of segments is not allowed, - * or seglen is <= mtu + /* common case: seglen is <= mtu */ - if (((IPCB(skb)->flags & IPSKB_FRAG_SEGS) == 0) || - skb_gso_validate_mtu(skb, mtu)) + if (skb_gso_validate_mtu(skb, mtu)) return ip_finish_output2(net, sk, skb); - /* Slowpath - GSO segment length is exceeding the dst MTU. + /* Slowpath - GSO segment length exceeds the egress MTU. * - * This can happen in two cases: - * 1) TCP GRO packet, DF bit not set - * 2) skb arrived via virtio-net, we thus get TSO/GSO skbs directly - * from host network stack. + * This can happen in several cases: + * - Forwarding of a TCP GRO skb, when DF flag is not set. + * - Forwarding of an skb that arrived on a virtualization interface + * (virtio-net/vhost/tap) with TSO/GSO size set by other network + * stack. + * - Local GSO skb transmitted on an NETIF_F_TSO tunnel stacked over an + * interface with a smaller MTU. + * - Arriving GRO skb (or GSO skb in a virtualized environment) that is + * bridged to a NETIF_F_TSO tunnel stacked over an interface with an + * insufficent MTU. */ features = netif_skb_features(skb); BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET); @@ -1579,7 +1583,8 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, } oif = arg->bound_dev_if; - oif = oif ? : skb->skb_iif; + if (!oif && netif_index_is_l3_master(net, skb->skb_iif)) + oif = skb->skb_iif; flowi4_init_output(&fl4, oif, IP4_REPLY_MARK(net, skb->mark), diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 777bc1883870..fed3d29f9eb3 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -63,7 +63,6 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, int pkt_len = skb->len - skb_inner_network_offset(skb); struct net *net = dev_net(rt->dst.dev); struct net_device *dev = skb->dev; - int skb_iif = skb->skb_iif; struct iphdr *iph; int err; @@ -73,16 +72,6 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, skb_dst_set(skb, &rt->dst); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); - if (skb_iif && !(df & htons(IP_DF))) { - /* Arrived from an ingress interface, got encapsulated, with - * fragmentation of encapulating frames allowed. - * If skb is gso, the resulting encapsulated network segments - * may exceed dst mtu. - * Allow IP Fragmentation of segments. - */ - IPCB(skb)->flags |= IPSKB_FRAG_SEGS; - } - /* Push down and install the IP header. */ skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 5f006e13de56..27089f5ebbb1 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1749,7 +1749,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, vif->dev->stats.tx_bytes += skb->len; } - IPCB(skb)->flags |= IPSKB_FORWARDED | IPSKB_FRAG_SEGS; + IPCB(skb)->flags |= IPSKB_FORWARDED; /* RFC1584 teaches, that DVMRP/PIM router must deliver packets locally * not only before forwarding, but after forwarding on all output diff --git a/net/ipv4/netfilter/nft_dup_ipv4.c b/net/ipv4/netfilter/nft_dup_ipv4.c index bf855e64fc45..0c01a270bf9f 100644 --- a/net/ipv4/netfilter/nft_dup_ipv4.c +++ b/net/ipv4/netfilter/nft_dup_ipv4.c @@ -28,7 +28,7 @@ static void nft_dup_ipv4_eval(const struct nft_expr *expr, struct in_addr gw = { .s_addr = (__force __be32)regs->data[priv->sreg_addr], }; - int oif = regs->data[priv->sreg_dev]; + int oif = priv->sreg_dev ? regs->data[priv->sreg_dev] : -1; nf_dup_ipv4(pkt->net, pkt->skb, pkt->hook, &gw, oif); } @@ -59,7 +59,9 @@ static int nft_dup_ipv4_dump(struct sk_buff *skb, const struct nft_expr *expr) { struct nft_dup_ipv4 *priv = nft_expr_priv(expr); - if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr) || + if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr)) + goto nla_put_failure; + if (priv->sreg_dev && nft_dump_register(skb, NFTA_DUP_SREG_DEV, priv->sreg_dev)) goto nla_put_failure; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 62d4d90c1389..2a57566e6e91 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -753,7 +753,9 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow goto reject_redirect; } - n = ipv4_neigh_lookup(&rt->dst, NULL, &new_gw); + n = __ipv4_neigh_lookup(rt->dst.dev, new_gw); + if (!n) + n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev); if (!IS_ERR(n)) { if (!(n->nud_state & NUD_VALID)) { neigh_event_send(n, NULL); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3251fe71f39f..814af89c1bd3 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1164,7 +1164,7 @@ restart: err = -EPIPE; if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) - goto out_err; + goto do_error; sg = !!(sk->sk_route_caps & NETIF_F_SG); @@ -1241,7 +1241,7 @@ new_segment: if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { - if (i == sysctl_max_skb_frags || !sg) { + if (i >= sysctl_max_skb_frags || !sg) { tcp_mark_push(tp, skb); goto new_segment; } diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 10d728b6804c..ab37c6775630 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -56,6 +56,7 @@ struct dctcp { u32 next_seq; u32 ce_state; u32 delayed_ack_reserved; + u32 loss_cwnd; }; static unsigned int dctcp_shift_g __read_mostly = 4; /* g = 1/2^4 */ @@ -96,6 +97,7 @@ static void dctcp_init(struct sock *sk) ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA); ca->delayed_ack_reserved = 0; + ca->loss_cwnd = 0; ca->ce_state = 0; dctcp_reset(tp, ca); @@ -111,9 +113,10 @@ static void dctcp_init(struct sock *sk) static u32 dctcp_ssthresh(struct sock *sk) { - const struct dctcp *ca = inet_csk_ca(sk); + struct dctcp *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); + ca->loss_cwnd = tp->snd_cwnd; return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->dctcp_alpha) >> 11U), 2U); } @@ -308,12 +311,20 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr, return 0; } +static u32 dctcp_cwnd_undo(struct sock *sk) +{ + const struct dctcp *ca = inet_csk_ca(sk); + + return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd); +} + static struct tcp_congestion_ops dctcp __read_mostly = { .init = dctcp_init, .in_ack_event = dctcp_update_alpha, .cwnd_event = dctcp_cwnd_event, .ssthresh = dctcp_ssthresh, .cong_avoid = tcp_reno_cong_avoid, + .undo_cwnd = dctcp_cwnd_undo, .set_state = dctcp_state, .get_info = dctcp_get_info, .flags = TCP_CONG_NEEDS_ECN, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 61b7be303eec..2259114c7242 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1564,6 +1564,21 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(tcp_add_backlog); +int tcp_filter(struct sock *sk, struct sk_buff *skb) +{ + struct tcphdr *th = (struct tcphdr *)skb->data; + unsigned int eaten = skb->len; + int err; + + err = sk_filter_trim_cap(sk, skb, th->doff * 4); + if (!err) { + eaten -= skb->len; + TCP_SKB_CB(skb)->end_seq -= eaten; + } + return err; +} +EXPORT_SYMBOL(tcp_filter); + /* * From tcp_input.c */ @@ -1676,8 +1691,10 @@ process: nf_reset(skb); - if (sk_filter(sk, skb)) + if (tcp_filter(sk, skb)) goto discard_and_relse; + th = (const struct tcphdr *)skb->data; + iph = ip_hdr(skb); skb->dev = NULL; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index bd59c343d35f..7370ad2e693a 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -448,7 +448,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, if (__ipv6_addr_needs_scope_id(addr_type)) iif = skb->dev->ifindex; else - iif = l3mdev_master_ifindex(skb->dev); + iif = l3mdev_master_ifindex(skb_dst(skb)->dev); /* * Must not send error if the source does not uniquely diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 6001e781164e..59eb4ed99ce8 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1366,7 +1366,7 @@ emsgsize: if (((length > mtu) || (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && - (rt->dst.dev->features & NETIF_F_UFO) && + (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len && (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) { err = ip6_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, exthdrlen, diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c index a7520528ecd2..b283f293ee4a 100644 --- a/net/ipv6/ip6_udp_tunnel.c +++ b/net/ipv6/ip6_udp_tunnel.c @@ -88,9 +88,6 @@ int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, uh->len = htons(skb->len); - memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); - IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED - | IPSKB_REROUTED); skb_dst_set(skb, dst); udp6_set_csum(nocheck, skb, saddr, daddr, skb->len); diff --git a/net/ipv6/netfilter/nft_dup_ipv6.c b/net/ipv6/netfilter/nft_dup_ipv6.c index 8bfd470cbe72..831f86e1ec08 100644 --- a/net/ipv6/netfilter/nft_dup_ipv6.c +++ b/net/ipv6/netfilter/nft_dup_ipv6.c @@ -26,7 +26,7 @@ static void nft_dup_ipv6_eval(const struct nft_expr *expr, { struct nft_dup_ipv6 *priv = nft_expr_priv(expr); struct in6_addr *gw = (struct in6_addr *)®s->data[priv->sreg_addr]; - int oif = regs->data[priv->sreg_dev]; + int oif = priv->sreg_dev ? regs->data[priv->sreg_dev] : -1; nf_dup_ipv6(pkt->net, pkt->skb, pkt->hook, gw, oif); } @@ -57,7 +57,9 @@ static int nft_dup_ipv6_dump(struct sk_buff *skb, const struct nft_expr *expr) { struct nft_dup_ipv6 *priv = nft_expr_priv(expr); - if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr) || + if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr)) + goto nla_put_failure; + if (priv->sreg_dev && nft_dump_register(skb, NFTA_DUP_SREG_DEV, priv->sreg_dev)) goto nla_put_failure; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 947ed1ded026..1b57e11e6e0d 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1364,6 +1364,9 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, if (rt6->rt6i_flags & RTF_LOCAL) return; + if (dst_metric_locked(dst, RTAX_MTU)) + return; + dst_confirm(dst); mtu = max_t(u32, mtu, IPV6_MIN_MTU); if (mtu >= dst_mtu(dst)) @@ -2758,6 +2761,7 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) PMTU discouvery. */ if (rt->dst.dev == arg->dev && + dst_metric_raw(&rt->dst, RTAX_MTU) && !dst_metric_locked(&rt->dst, RTAX_MTU)) { if (rt->rt6i_flags & RTF_CACHE) { /* For RTF_CACHE with rt6i_pmtu == 0 diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 5a27ab4eab39..b9f1fee9a886 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -818,8 +818,12 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 fl6.flowi6_proto = IPPROTO_TCP; if (rt6_need_strict(&fl6.daddr) && !oif) fl6.flowi6_oif = tcp_v6_iif(skb); - else - fl6.flowi6_oif = oif ? : skb->skb_iif; + else { + if (!oif && netif_index_is_l3_master(net, skb->skb_iif)) + oif = skb->skb_iif; + + fl6.flowi6_oif = oif; + } fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark); fl6.fl6_dport = t1->dest; @@ -1225,7 +1229,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) if (skb->protocol == htons(ETH_P_IP)) return tcp_v4_do_rcv(sk, skb); - if (sk_filter(sk, skb)) + if (tcp_filter(sk, skb)) goto discard; /* @@ -1453,8 +1457,10 @@ process: if (tcp_v6_inbound_md5_hash(sk, skb)) goto discard_and_relse; - if (sk_filter(sk, skb)) + if (tcp_filter(sk, skb)) goto discard_and_relse; + th = (const struct tcphdr *)skb->data; + hdr = ipv6_hdr(skb); skb->dev = NULL; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index c3c809b2e712..a6e44ef2ec9a 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2845,7 +2845,7 @@ static struct genl_family ip_vs_genl_family = { .hdrsize = 0, .name = IPVS_GENL_NAME, .version = IPVS_GENL_VERSION, - .maxattr = IPVS_CMD_MAX, + .maxattr = IPVS_CMD_ATTR_MAX, .netnsok = true, /* Make ipvsadm to work on netns */ }; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 1b07578bedf3..9350530c16c1 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -283,6 +283,7 @@ struct ip_vs_sync_buff { */ static void ntoh_seq(struct ip_vs_seq *no, struct ip_vs_seq *ho) { + memset(ho, 0, sizeof(*ho)); ho->init_seq = get_unaligned_be32(&no->init_seq); ho->delta = get_unaligned_be32(&no->delta); ho->previous_delta = get_unaligned_be32(&no->previous_delta); @@ -917,8 +918,10 @@ static void ip_vs_proc_conn(struct netns_ipvs *ipvs, struct ip_vs_conn_param *pa kfree(param->pe_data); } - if (opt) - memcpy(&cp->in_seq, opt, sizeof(*opt)); + if (opt) { + cp->in_seq = opt->in_seq; + cp->out_seq = opt->out_seq; + } atomic_set(&cp->in_pkts, sysctl_sync_threshold(ipvs)); cp->state = state; cp->old_state = cp->state; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index df2f5a3901df..0f87e5d21be7 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -76,6 +76,7 @@ struct conntrack_gc_work { struct delayed_work dwork; u32 last_bucket; bool exiting; + long next_gc_run; }; static __read_mostly struct kmem_cache *nf_conntrack_cachep; @@ -83,9 +84,11 @@ static __read_mostly spinlock_t nf_conntrack_locks_all_lock; static __read_mostly DEFINE_SPINLOCK(nf_conntrack_locks_all_lock); static __read_mostly bool nf_conntrack_locks_all; +/* every gc cycle scans at most 1/GC_MAX_BUCKETS_DIV part of table */ #define GC_MAX_BUCKETS_DIV 64u -#define GC_MAX_BUCKETS 8192u -#define GC_INTERVAL (5 * HZ) +/* upper bound of scan intervals */ +#define GC_INTERVAL_MAX (2 * HZ) +/* maximum conntracks to evict per gc run */ #define GC_MAX_EVICTS 256u static struct conntrack_gc_work conntrack_gc_work; @@ -936,13 +939,13 @@ static noinline int early_drop(struct net *net, unsigned int _hash) static void gc_worker(struct work_struct *work) { unsigned int i, goal, buckets = 0, expired_count = 0; - unsigned long next_run = GC_INTERVAL; - unsigned int ratio, scanned = 0; struct conntrack_gc_work *gc_work; + unsigned int ratio, scanned = 0; + unsigned long next_run; gc_work = container_of(work, struct conntrack_gc_work, dwork.work); - goal = min(nf_conntrack_htable_size / GC_MAX_BUCKETS_DIV, GC_MAX_BUCKETS); + goal = nf_conntrack_htable_size / GC_MAX_BUCKETS_DIV; i = gc_work->last_bucket; do { @@ -982,17 +985,47 @@ static void gc_worker(struct work_struct *work) if (gc_work->exiting) return; + /* + * Eviction will normally happen from the packet path, and not + * from this gc worker. + * + * This worker is only here to reap expired entries when system went + * idle after a busy period. + * + * The heuristics below are supposed to balance conflicting goals: + * + * 1. Minimize time until we notice a stale entry + * 2. Maximize scan intervals to not waste cycles + * + * Normally, expired_count will be 0, this increases the next_run time + * to priorize 2) above. + * + * As soon as a timed-out entry is found, move towards 1) and increase + * the scan frequency. + * In case we have lots of evictions next scan is done immediately. + */ ratio = scanned ? expired_count * 100 / scanned : 0; - if (ratio >= 90 || expired_count == GC_MAX_EVICTS) + if (ratio >= 90 || expired_count == GC_MAX_EVICTS) { + gc_work->next_gc_run = 0; next_run = 0; + } else if (expired_count) { + gc_work->next_gc_run /= 2U; + next_run = msecs_to_jiffies(1); + } else { + if (gc_work->next_gc_run < GC_INTERVAL_MAX) + gc_work->next_gc_run += msecs_to_jiffies(1); + + next_run = gc_work->next_gc_run; + } gc_work->last_bucket = i; - schedule_delayed_work(&gc_work->dwork, next_run); + queue_delayed_work(system_long_wq, &gc_work->dwork, next_run); } static void conntrack_gc_work_init(struct conntrack_gc_work *gc_work) { INIT_DELAYED_WORK(&gc_work->dwork, gc_worker); + gc_work->next_gc_run = GC_INTERVAL_MAX; gc_work->exiting = false; } @@ -1885,7 +1918,7 @@ int nf_conntrack_init_start(void) nf_ct_untracked_status_or(IPS_CONFIRMED | IPS_UNTRACKED); conntrack_gc_work_init(&conntrack_gc_work); - schedule_delayed_work(&conntrack_gc_work.dwork, GC_INTERVAL); + queue_delayed_work(system_long_wq, &conntrack_gc_work.dwork, GC_INTERVAL_MAX); return 0; diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 336e21559e01..7341adf7059d 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -138,9 +138,14 @@ __nf_conntrack_helper_find(const char *name, u16 l3num, u8 protonum) for (i = 0; i < nf_ct_helper_hsize; i++) { hlist_for_each_entry_rcu(h, &nf_ct_helper_hash[i], hnode) { - if (!strcmp(h->name, name) && - h->tuple.src.l3num == l3num && - h->tuple.dst.protonum == protonum) + if (strcmp(h->name, name)) + continue; + + if (h->tuple.src.l3num != NFPROTO_UNSPEC && + h->tuple.src.l3num != l3num) + continue; + + if (h->tuple.dst.protonum == protonum) return h; } } diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 621b81c7bddc..c3fc14e021ec 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1436,9 +1436,12 @@ static int process_sip_request(struct sk_buff *skb, unsigned int protoff, handler = &sip_handlers[i]; if (handler->request == NULL) continue; - if (*datalen < handler->len || + if (*datalen < handler->len + 2 || strncasecmp(*dptr, handler->method, handler->len)) continue; + if ((*dptr)[handler->len] != ' ' || + !isalpha((*dptr)[handler->len+1])) + continue; if (ct_sip_get_header(ct, *dptr, 0, *datalen, SIP_HDR_CSEQ, &matchoff, &matchlen) <= 0) { diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 24db22257586..026581b04ea8 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2956,12 +2956,14 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set); if (err < 0) - goto err2; + goto err3; list_add_tail_rcu(&set->list, &table->sets); table->use++; return 0; +err3: + ops->destroy(set); err2: kfree(set); err1: @@ -3452,14 +3454,15 @@ void *nft_set_elem_init(const struct nft_set *set, return elem; } -void nft_set_elem_destroy(const struct nft_set *set, void *elem) +void nft_set_elem_destroy(const struct nft_set *set, void *elem, + bool destroy_expr) { struct nft_set_ext *ext = nft_set_elem_ext(set, elem); nft_data_uninit(nft_set_ext_key(ext), NFT_DATA_VALUE); if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_uninit(nft_set_ext_data(ext), set->dtype); - if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPR)) + if (destroy_expr && nft_set_ext_exists(ext, NFT_SET_EXT_EXPR)) nf_tables_expr_destroy(NULL, nft_set_ext_expr(ext)); kfree(elem); @@ -3565,6 +3568,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, dreg = nft_type_to_reg(set->dtype); list_for_each_entry(binding, &set->bindings, list) { struct nft_ctx bind_ctx = { + .net = ctx->net, .afi = ctx->afi, .table = ctx->table, .chain = (struct nft_chain *)binding->chain, @@ -3812,7 +3816,7 @@ void nft_set_gc_batch_release(struct rcu_head *rcu) gcb = container_of(rcu, struct nft_set_gc_batch, head.rcu); for (i = 0; i < gcb->head.cnt; i++) - nft_set_elem_destroy(gcb->head.set, gcb->elems[i]); + nft_set_elem_destroy(gcb->head.set, gcb->elems[i], true); kfree(gcb); } EXPORT_SYMBOL_GPL(nft_set_gc_batch_release); @@ -4030,7 +4034,7 @@ static void nf_tables_commit_release(struct nft_trans *trans) break; case NFT_MSG_DELSETELEM: nft_set_elem_destroy(nft_trans_elem_set(trans), - nft_trans_elem(trans).priv); + nft_trans_elem(trans).priv, true); break; } kfree(trans); @@ -4171,7 +4175,7 @@ static void nf_tables_abort_release(struct nft_trans *trans) break; case NFT_MSG_NEWSETELEM: nft_set_elem_destroy(nft_trans_elem_set(trans), - nft_trans_elem(trans).priv); + nft_trans_elem(trans).priv, true); break; } kfree(trans); @@ -4421,7 +4425,7 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, * Otherwise a 0 is returned and the attribute value is stored in the * destination variable. */ -unsigned int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest) +int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest) { u32 val; diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 517f08767a3c..31ca94793aa9 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -44,18 +44,22 @@ static void *nft_dynset_new(struct nft_set *set, const struct nft_expr *expr, ®s->data[priv->sreg_key], ®s->data[priv->sreg_data], timeout, GFP_ATOMIC); - if (elem == NULL) { - if (set->size) - atomic_dec(&set->nelems); - return NULL; - } + if (elem == NULL) + goto err1; ext = nft_set_elem_ext(set, elem); if (priv->expr != NULL && nft_expr_clone(nft_set_ext_expr(ext), priv->expr) < 0) - return NULL; + goto err2; return elem; + +err2: + nft_set_elem_destroy(set, elem, false); +err1: + if (set->size) + atomic_dec(&set->nelems); + return NULL; } static void nft_dynset_eval(const struct nft_expr *expr, @@ -139,6 +143,9 @@ static int nft_dynset_init(const struct nft_ctx *ctx, return PTR_ERR(set); } + if (set->ops->update == NULL) + return -EOPNOTSUPP; + if (set->flags & NFT_SET_CONSTANT) return -EBUSY; diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 3794cb2fc788..a3dface3e6e6 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -98,7 +98,7 @@ static bool nft_hash_update(struct nft_set *set, const u32 *key, const struct nft_set_ext **ext) { struct nft_hash *priv = nft_set_priv(set); - struct nft_hash_elem *he; + struct nft_hash_elem *he, *prev; struct nft_hash_cmp_arg arg = { .genmask = NFT_GENMASK_ANY, .set = set, @@ -112,15 +112,24 @@ static bool nft_hash_update(struct nft_set *set, const u32 *key, he = new(set, expr, regs); if (he == NULL) goto err1; - if (rhashtable_lookup_insert_key(&priv->ht, &arg, &he->node, - nft_hash_params)) + + prev = rhashtable_lookup_get_insert_key(&priv->ht, &arg, &he->node, + nft_hash_params); + if (IS_ERR(prev)) goto err2; + + /* Another cpu may race to insert the element with the same key */ + if (prev) { + nft_set_elem_destroy(set, he, true); + he = prev; + } + out: *ext = &he->ext; return true; err2: - nft_set_elem_destroy(set, he); + nft_set_elem_destroy(set, he, true); err1: return false; } @@ -332,7 +341,7 @@ static int nft_hash_init(const struct nft_set *set, static void nft_hash_elem_destroy(void *ptr, void *arg) { - nft_set_elem_destroy((const struct nft_set *)arg, ptr); + nft_set_elem_destroy((const struct nft_set *)arg, ptr, true); } static void nft_hash_destroy(const struct nft_set *set) diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 38b5bda242f8..36493a7cae88 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -266,7 +266,7 @@ static void nft_rbtree_destroy(const struct nft_set *set) while ((node = priv->root.rb_node) != NULL) { rb_erase(node, &priv->root); rbe = rb_entry(node, struct nft_rbtree_elem, node); - nft_set_elem_destroy(set, rbe); + nft_set_elem_destroy(set, rbe, true); } } diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c index 69f78e96fdb4..b83e158e116a 100644 --- a/net/netfilter/xt_connmark.c +++ b/net/netfilter/xt_connmark.c @@ -44,7 +44,7 @@ connmark_tg(struct sk_buff *skb, const struct xt_action_param *par) u_int32_t newmark; ct = nf_ct_get(skb, &ctinfo); - if (ct == NULL) + if (ct == NULL || nf_ct_is_untracked(ct)) return XT_CONTINUE; switch (info->mode) { @@ -97,7 +97,7 @@ connmark_mt(const struct sk_buff *skb, struct xt_action_param *par) const struct nf_conn *ct; ct = nf_ct_get(skb, &ctinfo); - if (ct == NULL) + if (ct == NULL || nf_ct_is_untracked(ct)) return false; return ((ct->mark & info->mask) == info->mark) ^ info->invert; diff --git a/net/netlink/diag.c b/net/netlink/diag.c index b2f0e986a6f4..a5546249fb10 100644 --- a/net/netlink/diag.c +++ b/net/netlink/diag.c @@ -178,11 +178,8 @@ static int netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) } cb->args[1] = i; } else { - if (req->sdiag_protocol >= MAX_LINKS) { - read_unlock(&nl_table_lock); - rcu_read_unlock(); + if (req->sdiag_protocol >= MAX_LINKS) return -ENOENT; - } err = __netlink_diag_dump(skb, cb, req->sdiag_protocol, s_num); } diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 23cc12639ba7..49c28e8ef01b 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -404,7 +404,7 @@ int __genl_register_family(struct genl_family *family) err = genl_validate_assign_mc_groups(family); if (err) - goto errout_locked; + goto errout_free; list_add_tail(&family->family_list, genl_family_chain(family->id)); genl_unlock_all(); @@ -417,6 +417,8 @@ int __genl_register_family(struct genl_family *family) return 0; +errout_free: + kfree(family->attrbuf); errout_locked: genl_unlock_all(); errout: diff --git a/net/sctp/input.c b/net/sctp/input.c index a2ea1d1cc06a..a01a56ec8b8c 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -181,9 +181,10 @@ int sctp_rcv(struct sk_buff *skb) * bound to another interface, via SO_BINDTODEVICE, treat it as OOTB */ if (sk->sk_bound_dev_if && (sk->sk_bound_dev_if != af->skb_iif(skb))) { - if (asoc) { - sctp_association_put(asoc); + if (transport) { + sctp_transport_put(transport); asoc = NULL; + transport = NULL; } else { sctp_endpoint_put(ep); ep = NULL; @@ -269,8 +270,8 @@ int sctp_rcv(struct sk_buff *skb) bh_unlock_sock(sk); /* Release the asoc/ep ref we took in the lookup calls. */ - if (asoc) - sctp_association_put(asoc); + if (transport) + sctp_transport_put(transport); else sctp_endpoint_put(ep); @@ -283,8 +284,8 @@ discard_it: discard_release: /* Release the asoc/ep ref we took in the lookup calls. */ - if (asoc) - sctp_association_put(asoc); + if (transport) + sctp_transport_put(transport); else sctp_endpoint_put(ep); @@ -300,6 +301,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb) { struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk; struct sctp_inq *inqueue = &chunk->rcvr->inqueue; + struct sctp_transport *t = chunk->transport; struct sctp_ep_common *rcvr = NULL; int backloged = 0; @@ -351,7 +353,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb) done: /* Release the refs we took in sctp_add_backlog */ if (SCTP_EP_TYPE_ASSOCIATION == rcvr->type) - sctp_association_put(sctp_assoc(rcvr)); + sctp_transport_put(t); else if (SCTP_EP_TYPE_SOCKET == rcvr->type) sctp_endpoint_put(sctp_ep(rcvr)); else @@ -363,6 +365,7 @@ done: static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb) { struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk; + struct sctp_transport *t = chunk->transport; struct sctp_ep_common *rcvr = chunk->rcvr; int ret; @@ -373,7 +376,7 @@ static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb) * from us */ if (SCTP_EP_TYPE_ASSOCIATION == rcvr->type) - sctp_association_hold(sctp_assoc(rcvr)); + sctp_transport_hold(t); else if (SCTP_EP_TYPE_SOCKET == rcvr->type) sctp_endpoint_hold(sctp_ep(rcvr)); else @@ -537,15 +540,15 @@ struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *skb, return sk; out: - sctp_association_put(asoc); + sctp_transport_put(transport); return NULL; } /* Common cleanup code for icmp/icmpv6 error handler. */ -void sctp_err_finish(struct sock *sk, struct sctp_association *asoc) +void sctp_err_finish(struct sock *sk, struct sctp_transport *t) { bh_unlock_sock(sk); - sctp_association_put(asoc); + sctp_transport_put(t); } /* @@ -641,7 +644,7 @@ void sctp_v4_err(struct sk_buff *skb, __u32 info) } out_unlock: - sctp_err_finish(sk, asoc); + sctp_err_finish(sk, transport); } /* @@ -952,11 +955,8 @@ static struct sctp_association *__sctp_lookup_association( goto out; asoc = t->asoc; - sctp_association_hold(asoc); *pt = t; - sctp_transport_put(t); - out: return asoc; } @@ -986,7 +986,7 @@ int sctp_has_association(struct net *net, struct sctp_transport *transport; if ((asoc = sctp_lookup_association(net, laddr, paddr, &transport))) { - sctp_association_put(asoc); + sctp_transport_put(transport); return 1; } @@ -1021,7 +1021,6 @@ static struct sctp_association *__sctp_rcv_init_lookup(struct net *net, struct sctphdr *sh = sctp_hdr(skb); union sctp_params params; sctp_init_chunk_t *init; - struct sctp_transport *transport; struct sctp_af *af; /* @@ -1052,7 +1051,7 @@ static struct sctp_association *__sctp_rcv_init_lookup(struct net *net, af->from_addr_param(paddr, params.addr, sh->source, 0); - asoc = __sctp_lookup_association(net, laddr, paddr, &transport); + asoc = __sctp_lookup_association(net, laddr, paddr, transportp); if (asoc) return asoc; } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index f473779e8b1c..176af3080a2b 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -198,7 +198,7 @@ static void sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } out_unlock: - sctp_err_finish(sk, asoc); + sctp_err_finish(sk, transport); out: if (likely(idev != NULL)) in6_dev_put(idev); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 9fbb6feb8c27..f23ad913dc7a 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1214,9 +1214,12 @@ static int __sctp_connect(struct sock *sk, timeo = sock_sndtimeo(sk, f_flags & O_NONBLOCK); - err = sctp_wait_for_connect(asoc, &timeo); - if ((err == 0 || err == -EINPROGRESS) && assoc_id) + if (assoc_id) *assoc_id = asoc->assoc_id; + err = sctp_wait_for_connect(asoc, &timeo); + /* Note: the asoc may be freed after the return of + * sctp_wait_for_connect. + */ /* Don't free association on exit. */ asoc = NULL; @@ -4282,19 +4285,18 @@ static void sctp_shutdown(struct sock *sk, int how) { struct net *net = sock_net(sk); struct sctp_endpoint *ep; - struct sctp_association *asoc; if (!sctp_style(sk, TCP)) return; - if (how & SEND_SHUTDOWN) { + ep = sctp_sk(sk)->ep; + if (how & SEND_SHUTDOWN && !list_empty(&ep->asocs)) { + struct sctp_association *asoc; + sk->sk_state = SCTP_SS_CLOSING; - ep = sctp_sk(sk)->ep; - if (!list_empty(&ep->asocs)) { - asoc = list_entry(ep->asocs.next, - struct sctp_association, asocs); - sctp_primitive_SHUTDOWN(net, asoc, NULL); - } + asoc = list_entry(ep->asocs.next, + struct sctp_association, asocs); + sctp_primitive_SHUTDOWN(net, asoc, NULL); } } @@ -4480,12 +4482,9 @@ int sctp_transport_lookup_process(int (*cb)(struct sctp_transport *, void *), if (!transport || !sctp_transport_hold(transport)) goto out; - sctp_association_hold(transport->asoc); - sctp_transport_put(transport); - rcu_read_unlock(); err = cb(transport, p); - sctp_association_put(transport->asoc); + sctp_transport_put(transport); out: return err; diff --git a/net/socket.c b/net/socket.c index 5a9bf5ee2464..73dc69f9681e 100644 --- a/net/socket.c +++ b/net/socket.c @@ -341,8 +341,23 @@ static const struct xattr_handler sockfs_xattr_handler = { .get = sockfs_xattr_get, }; +static int sockfs_security_xattr_set(const struct xattr_handler *handler, + struct dentry *dentry, struct inode *inode, + const char *suffix, const void *value, + size_t size, int flags) +{ + /* Handled by LSM. */ + return -EAGAIN; +} + +static const struct xattr_handler sockfs_security_xattr_handler = { + .prefix = XATTR_SECURITY_PREFIX, + .set = sockfs_security_xattr_set, +}; + static const struct xattr_handler *sockfs_xattr_handlers[] = { &sockfs_xattr_handler, + &sockfs_security_xattr_handler, NULL }; @@ -2038,6 +2053,8 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, if (err) break; ++datagrams; + if (msg_data_left(&msg_sys)) + break; cond_resched(); } diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index c3f652395a80..3bc1d61694cb 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -1002,14 +1002,8 @@ static void svc_age_temp_xprts(unsigned long closure) void svc_age_temp_xprts_now(struct svc_serv *serv, struct sockaddr *server_addr) { struct svc_xprt *xprt; - struct svc_sock *svsk; - struct socket *sock; struct list_head *le, *next; LIST_HEAD(to_be_closed); - struct linger no_linger = { - .l_onoff = 1, - .l_linger = 0, - }; spin_lock_bh(&serv->sv_lock); list_for_each_safe(le, next, &serv->sv_tempsocks) { @@ -1027,10 +1021,7 @@ void svc_age_temp_xprts_now(struct svc_serv *serv, struct sockaddr *server_addr) list_del_init(le); xprt = list_entry(le, struct svc_xprt, xpt_list); dprintk("svc_age_temp_xprts_now: closing %p\n", xprt); - svsk = container_of(xprt, struct svc_sock, sk_xprt); - sock = svsk->sk_sock; - kernel_setsockopt(sock, SOL_SOCKET, SO_LINGER, - (char *)&no_linger, sizeof(no_linger)); + xprt->xpt_ops->xpo_kill_temp_xprt(xprt); svc_close_xprt(xprt); } } diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 57625f64efd5..a4bc98265d88 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -438,6 +438,21 @@ static int svc_tcp_has_wspace(struct svc_xprt *xprt) return !test_bit(SOCK_NOSPACE, &svsk->sk_sock->flags); } +static void svc_tcp_kill_temp_xprt(struct svc_xprt *xprt) +{ + struct svc_sock *svsk; + struct socket *sock; + struct linger no_linger = { + .l_onoff = 1, + .l_linger = 0, + }; + + svsk = container_of(xprt, struct svc_sock, sk_xprt); + sock = svsk->sk_sock; + kernel_setsockopt(sock, SOL_SOCKET, SO_LINGER, + (char *)&no_linger, sizeof(no_linger)); +} + /* * See net/ipv6/ip_sockglue.c : ip_cmsg_recv_pktinfo */ @@ -648,6 +663,10 @@ static struct svc_xprt *svc_udp_accept(struct svc_xprt *xprt) return NULL; } +static void svc_udp_kill_temp_xprt(struct svc_xprt *xprt) +{ +} + static struct svc_xprt *svc_udp_create(struct svc_serv *serv, struct net *net, struct sockaddr *sa, int salen, @@ -667,6 +686,7 @@ static struct svc_xprt_ops svc_udp_ops = { .xpo_has_wspace = svc_udp_has_wspace, .xpo_accept = svc_udp_accept, .xpo_secure_port = svc_sock_secure_port, + .xpo_kill_temp_xprt = svc_udp_kill_temp_xprt, }; static struct svc_xprt_class svc_udp_class = { @@ -1242,6 +1262,7 @@ static struct svc_xprt_ops svc_tcp_ops = { .xpo_has_wspace = svc_tcp_has_wspace, .xpo_accept = svc_tcp_accept, .xpo_secure_port = svc_sock_secure_port, + .xpo_kill_temp_xprt = svc_tcp_kill_temp_xprt, }; static struct svc_xprt_class svc_tcp_class = { diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 6864fb967038..1334de2715c2 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -67,6 +67,7 @@ static void svc_rdma_detach(struct svc_xprt *xprt); static void svc_rdma_free(struct svc_xprt *xprt); static int svc_rdma_has_wspace(struct svc_xprt *xprt); static int svc_rdma_secure_port(struct svc_rqst *); +static void svc_rdma_kill_temp_xprt(struct svc_xprt *); static struct svc_xprt_ops svc_rdma_ops = { .xpo_create = svc_rdma_create, @@ -79,6 +80,7 @@ static struct svc_xprt_ops svc_rdma_ops = { .xpo_has_wspace = svc_rdma_has_wspace, .xpo_accept = svc_rdma_accept, .xpo_secure_port = svc_rdma_secure_port, + .xpo_kill_temp_xprt = svc_rdma_kill_temp_xprt, }; struct svc_xprt_class svc_rdma_class = { @@ -1317,6 +1319,10 @@ static int svc_rdma_secure_port(struct svc_rqst *rqstp) return 1; } +static void svc_rdma_kill_temp_xprt(struct svc_xprt *xprt) +{ +} + int svc_rdma_send(struct svcxprt_rdma *xprt, struct ib_send_wr *wr) { struct ib_send_wr *bad_wr, *n_wr; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 145082e2ba36..5d1c14a2f268 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2812,7 +2812,8 @@ static int unix_seq_show(struct seq_file *seq, void *v) i++; } for ( ; i < len; i++) - seq_putc(seq, u->addr->name->sun_path[i]); + seq_putc(seq, u->addr->name->sun_path[i] ?: + '@'); } unix_state_unlock(s); seq_putc(seq, '\n'); diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 12b7304d55dc..72c58675973e 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -27,6 +27,7 @@ hostprogs-y += xdp2 hostprogs-y += test_current_task_under_cgroup hostprogs-y += trace_event hostprogs-y += sampleip +hostprogs-y += tc_l2_redirect test_verifier-objs := test_verifier.o libbpf.o test_maps-objs := test_maps.o libbpf.o @@ -56,6 +57,7 @@ test_current_task_under_cgroup-objs := bpf_load.o libbpf.o \ test_current_task_under_cgroup_user.o trace_event-objs := bpf_load.o libbpf.o trace_event_user.o sampleip-objs := bpf_load.o libbpf.o sampleip_user.o +tc_l2_redirect-objs := bpf_load.o libbpf.o tc_l2_redirect_user.o # Tell kbuild to always build the programs always := $(hostprogs-y) @@ -72,6 +74,7 @@ always += test_probe_write_user_kern.o always += trace_output_kern.o always += tcbpf1_kern.o always += tcbpf2_kern.o +always += tc_l2_redirect_kern.o always += lathist_kern.o always += offwaketime_kern.o always += spintest_kern.o @@ -111,6 +114,7 @@ HOSTLOADLIBES_xdp2 += -lelf HOSTLOADLIBES_test_current_task_under_cgroup += -lelf HOSTLOADLIBES_trace_event += -lelf HOSTLOADLIBES_sampleip += -lelf +HOSTLOADLIBES_tc_l2_redirect += -l elf # Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline: # make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang diff --git a/samples/bpf/tc_l2_redirect.sh b/samples/bpf/tc_l2_redirect.sh new file mode 100755 index 000000000000..80a05591a140 --- /dev/null +++ b/samples/bpf/tc_l2_redirect.sh @@ -0,0 +1,173 @@ +#!/bin/bash + +[[ -z $TC ]] && TC='tc' +[[ -z $IP ]] && IP='ip' + +REDIRECT_USER='./tc_l2_redirect' +REDIRECT_BPF='./tc_l2_redirect_kern.o' + +RP_FILTER=$(< /proc/sys/net/ipv4/conf/all/rp_filter) +IPV6_FORWARDING=$(< /proc/sys/net/ipv6/conf/all/forwarding) + +function config_common { + local tun_type=$1 + + $IP netns add ns1 + $IP netns add ns2 + $IP link add ve1 type veth peer name vens1 + $IP link add ve2 type veth peer name vens2 + $IP link set dev ve1 up + $IP link set dev ve2 up + $IP link set dev ve1 mtu 1500 + $IP link set dev ve2 mtu 1500 + $IP link set dev vens1 netns ns1 + $IP link set dev vens2 netns ns2 + + $IP -n ns1 link set dev lo up + $IP -n ns1 link set dev vens1 up + $IP -n ns1 addr add 10.1.1.101/24 dev vens1 + $IP -n ns1 addr add 2401:db01::65/64 dev vens1 nodad + $IP -n ns1 route add default via 10.1.1.1 dev vens1 + $IP -n ns1 route add default via 2401:db01::1 dev vens1 + + $IP -n ns2 link set dev lo up + $IP -n ns2 link set dev vens2 up + $IP -n ns2 addr add 10.2.1.102/24 dev vens2 + $IP -n ns2 addr add 2401:db02::66/64 dev vens2 nodad + $IP -n ns2 addr add 10.10.1.102 dev lo + $IP -n ns2 addr add 2401:face::66/64 dev lo nodad + $IP -n ns2 link add ipt2 type ipip local 10.2.1.102 remote 10.2.1.1 + $IP -n ns2 link add ip6t2 type ip6tnl mode any local 2401:db02::66 remote 2401:db02::1 + $IP -n ns2 link set dev ipt2 up + $IP -n ns2 link set dev ip6t2 up + $IP netns exec ns2 $TC qdisc add dev vens2 clsact + $IP netns exec ns2 $TC filter add dev vens2 ingress bpf da obj $REDIRECT_BPF sec drop_non_tun_vip + if [[ $tun_type == "ipip" ]]; then + $IP -n ns2 route add 10.1.1.0/24 dev ipt2 + $IP netns exec ns2 sysctl -q -w net.ipv4.conf.all.rp_filter=0 + $IP netns exec ns2 sysctl -q -w net.ipv4.conf.ipt2.rp_filter=0 + else + $IP -n ns2 route add 10.1.1.0/24 dev ip6t2 + $IP -n ns2 route add 2401:db01::/64 dev ip6t2 + $IP netns exec ns2 sysctl -q -w net.ipv4.conf.all.rp_filter=0 + $IP netns exec ns2 sysctl -q -w net.ipv4.conf.ip6t2.rp_filter=0 + fi + + $IP addr add 10.1.1.1/24 dev ve1 + $IP addr add 2401:db01::1/64 dev ve1 nodad + $IP addr add 10.2.1.1/24 dev ve2 + $IP addr add 2401:db02::1/64 dev ve2 nodad + + $TC qdisc add dev ve2 clsact + $TC filter add dev ve2 ingress bpf da obj $REDIRECT_BPF sec l2_to_iptun_ingress_forward + + sysctl -q -w net.ipv4.conf.all.rp_filter=0 + sysctl -q -w net.ipv6.conf.all.forwarding=1 +} + +function cleanup { + set +e + [[ -z $DEBUG ]] || set +x + $IP netns delete ns1 >& /dev/null + $IP netns delete ns2 >& /dev/null + $IP link del ve1 >& /dev/null + $IP link del ve2 >& /dev/null + $IP link del ipt >& /dev/null + $IP link del ip6t >& /dev/null + sysctl -q -w net.ipv4.conf.all.rp_filter=$RP_FILTER + sysctl -q -w net.ipv6.conf.all.forwarding=$IPV6_FORWARDING + rm -f /sys/fs/bpf/tc/globals/tun_iface + [[ -z $DEBUG ]] || set -x + set -e +} + +function l2_to_ipip { + echo -n "l2_to_ipip $1: " + + local dir=$1 + + config_common ipip + + $IP link add ipt type ipip external + $IP link set dev ipt up + sysctl -q -w net.ipv4.conf.ipt.rp_filter=0 + sysctl -q -w net.ipv4.conf.ipt.forwarding=1 + + if [[ $dir == "egress" ]]; then + $IP route add 10.10.1.0/24 via 10.2.1.102 dev ve2 + $TC filter add dev ve2 egress bpf da obj $REDIRECT_BPF sec l2_to_iptun_ingress_redirect + sysctl -q -w net.ipv4.conf.ve1.forwarding=1 + else + $TC qdisc add dev ve1 clsact + $TC filter add dev ve1 ingress bpf da obj $REDIRECT_BPF sec l2_to_iptun_ingress_redirect + fi + + $REDIRECT_USER -U /sys/fs/bpf/tc/globals/tun_iface -i $(< /sys/class/net/ipt/ifindex) + + $IP netns exec ns1 ping -c1 10.10.1.102 >& /dev/null + + if [[ $dir == "egress" ]]; then + # test direct egress to ve2 (i.e. not forwarding from + # ve1 to ve2). + ping -c1 10.10.1.102 >& /dev/null + fi + + cleanup + + echo "OK" +} + +function l2_to_ip6tnl { + echo -n "l2_to_ip6tnl $1: " + + local dir=$1 + + config_common ip6tnl + + $IP link add ip6t type ip6tnl mode any external + $IP link set dev ip6t up + sysctl -q -w net.ipv4.conf.ip6t.rp_filter=0 + sysctl -q -w net.ipv4.conf.ip6t.forwarding=1 + + if [[ $dir == "egress" ]]; then + $IP route add 10.10.1.0/24 via 10.2.1.102 dev ve2 + $IP route add 2401:face::/64 via 2401:db02::66 dev ve2 + $TC filter add dev ve2 egress bpf da obj $REDIRECT_BPF sec l2_to_ip6tun_ingress_redirect + sysctl -q -w net.ipv4.conf.ve1.forwarding=1 + else + $TC qdisc add dev ve1 clsact + $TC filter add dev ve1 ingress bpf da obj $REDIRECT_BPF sec l2_to_ip6tun_ingress_redirect + fi + + $REDIRECT_USER -U /sys/fs/bpf/tc/globals/tun_iface -i $(< /sys/class/net/ip6t/ifindex) + + $IP netns exec ns1 ping -c1 10.10.1.102 >& /dev/null + $IP netns exec ns1 ping -6 -c1 2401:face::66 >& /dev/null + + if [[ $dir == "egress" ]]; then + # test direct egress to ve2 (i.e. not forwarding from + # ve1 to ve2). + ping -c1 10.10.1.102 >& /dev/null + ping -6 -c1 2401:face::66 >& /dev/null + fi + + cleanup + + echo "OK" +} + +cleanup +test_names="l2_to_ipip l2_to_ip6tnl" +test_dirs="ingress egress" +if [[ $# -ge 2 ]]; then + test_names=$1 + test_dirs=$2 +elif [[ $# -ge 1 ]]; then + test_names=$1 +fi + +for t in $test_names; do + for d in $test_dirs; do + $t $d + done +done diff --git a/samples/bpf/tc_l2_redirect_kern.c b/samples/bpf/tc_l2_redirect_kern.c new file mode 100644 index 000000000000..92a44729dbe4 --- /dev/null +++ b/samples/bpf/tc_l2_redirect_kern.c @@ -0,0 +1,236 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "bpf_helpers.h" + +#define _htonl __builtin_bswap32 + +#define PIN_GLOBAL_NS 2 +struct bpf_elf_map { + __u32 type; + __u32 size_key; + __u32 size_value; + __u32 max_elem; + __u32 flags; + __u32 id; + __u32 pinning; +}; + +/* copy of 'struct ethhdr' without __packed */ +struct eth_hdr { + unsigned char h_dest[ETH_ALEN]; + unsigned char h_source[ETH_ALEN]; + unsigned short h_proto; +}; + +struct bpf_elf_map SEC("maps") tun_iface = { + .type = BPF_MAP_TYPE_ARRAY, + .size_key = sizeof(int), + .size_value = sizeof(int), + .pinning = PIN_GLOBAL_NS, + .max_elem = 1, +}; + +static __always_inline bool is_vip_addr(__be16 eth_proto, __be32 daddr) +{ + if (eth_proto == htons(ETH_P_IP)) + return (_htonl(0xffffff00) & daddr) == _htonl(0x0a0a0100); + else if (eth_proto == htons(ETH_P_IPV6)) + return (daddr == _htonl(0x2401face)); + + return false; +} + +SEC("l2_to_iptun_ingress_forward") +int _l2_to_iptun_ingress_forward(struct __sk_buff *skb) +{ + struct bpf_tunnel_key tkey = {}; + void *data = (void *)(long)skb->data; + struct eth_hdr *eth = data; + void *data_end = (void *)(long)skb->data_end; + int key = 0, *ifindex; + + int ret; + + if (data + sizeof(*eth) > data_end) + return TC_ACT_OK; + + ifindex = bpf_map_lookup_elem(&tun_iface, &key); + if (!ifindex) + return TC_ACT_OK; + + if (eth->h_proto == htons(ETH_P_IP)) { + char fmt4[] = "ingress forward to ifindex:%d daddr4:%x\n"; + struct iphdr *iph = data + sizeof(*eth); + + if (data + sizeof(*eth) + sizeof(*iph) > data_end) + return TC_ACT_OK; + + if (iph->protocol != IPPROTO_IPIP) + return TC_ACT_OK; + + bpf_trace_printk(fmt4, sizeof(fmt4), *ifindex, + _htonl(iph->daddr)); + return bpf_redirect(*ifindex, BPF_F_INGRESS); + } else if (eth->h_proto == htons(ETH_P_IPV6)) { + char fmt6[] = "ingress forward to ifindex:%d daddr6:%x::%x\n"; + struct ipv6hdr *ip6h = data + sizeof(*eth); + + if (data + sizeof(*eth) + sizeof(*ip6h) > data_end) + return TC_ACT_OK; + + if (ip6h->nexthdr != IPPROTO_IPIP && + ip6h->nexthdr != IPPROTO_IPV6) + return TC_ACT_OK; + + bpf_trace_printk(fmt6, sizeof(fmt6), *ifindex, + _htonl(ip6h->daddr.s6_addr32[0]), + _htonl(ip6h->daddr.s6_addr32[3])); + return bpf_redirect(*ifindex, BPF_F_INGRESS); + } + + return TC_ACT_OK; +} + +SEC("l2_to_iptun_ingress_redirect") +int _l2_to_iptun_ingress_redirect(struct __sk_buff *skb) +{ + struct bpf_tunnel_key tkey = {}; + void *data = (void *)(long)skb->data; + struct eth_hdr *eth = data; + void *data_end = (void *)(long)skb->data_end; + int key = 0, *ifindex; + + int ret; + + if (data + sizeof(*eth) > data_end) + return TC_ACT_OK; + + ifindex = bpf_map_lookup_elem(&tun_iface, &key); + if (!ifindex) + return TC_ACT_OK; + + if (eth->h_proto == htons(ETH_P_IP)) { + char fmt4[] = "e/ingress redirect daddr4:%x to ifindex:%d\n"; + struct iphdr *iph = data + sizeof(*eth); + __be32 daddr = iph->daddr; + + if (data + sizeof(*eth) + sizeof(*iph) > data_end) + return TC_ACT_OK; + + if (!is_vip_addr(eth->h_proto, daddr)) + return TC_ACT_OK; + + bpf_trace_printk(fmt4, sizeof(fmt4), _htonl(daddr), *ifindex); + } else { + return TC_ACT_OK; + } + + tkey.tunnel_id = 10000; + tkey.tunnel_ttl = 64; + tkey.remote_ipv4 = 0x0a020166; /* 10.2.1.102 */ + bpf_skb_set_tunnel_key(skb, &tkey, sizeof(tkey), 0); + return bpf_redirect(*ifindex, 0); +} + +SEC("l2_to_ip6tun_ingress_redirect") +int _l2_to_ip6tun_ingress_redirect(struct __sk_buff *skb) +{ + struct bpf_tunnel_key tkey = {}; + void *data = (void *)(long)skb->data; + struct eth_hdr *eth = data; + void *data_end = (void *)(long)skb->data_end; + int key = 0, *ifindex; + + if (data + sizeof(*eth) > data_end) + return TC_ACT_OK; + + ifindex = bpf_map_lookup_elem(&tun_iface, &key); + if (!ifindex) + return TC_ACT_OK; + + if (eth->h_proto == htons(ETH_P_IP)) { + char fmt4[] = "e/ingress redirect daddr4:%x to ifindex:%d\n"; + struct iphdr *iph = data + sizeof(*eth); + + if (data + sizeof(*eth) + sizeof(*iph) > data_end) + return TC_ACT_OK; + + if (!is_vip_addr(eth->h_proto, iph->daddr)) + return TC_ACT_OK; + + bpf_trace_printk(fmt4, sizeof(fmt4), _htonl(iph->daddr), + *ifindex); + } else if (eth->h_proto == htons(ETH_P_IPV6)) { + char fmt6[] = "e/ingress redirect daddr6:%x to ifindex:%d\n"; + struct ipv6hdr *ip6h = data + sizeof(*eth); + + if (data + sizeof(*eth) + sizeof(*ip6h) > data_end) + return TC_ACT_OK; + + if (!is_vip_addr(eth->h_proto, ip6h->daddr.s6_addr32[0])) + return TC_ACT_OK; + + bpf_trace_printk(fmt6, sizeof(fmt6), + _htonl(ip6h->daddr.s6_addr32[0]), *ifindex); + } else { + return TC_ACT_OK; + } + + tkey.tunnel_id = 10000; + tkey.tunnel_ttl = 64; + /* 2401:db02:0:0:0:0:0:66 */ + tkey.remote_ipv6[0] = _htonl(0x2401db02); + tkey.remote_ipv6[1] = 0; + tkey.remote_ipv6[2] = 0; + tkey.remote_ipv6[3] = _htonl(0x00000066); + bpf_skb_set_tunnel_key(skb, &tkey, sizeof(tkey), BPF_F_TUNINFO_IPV6); + return bpf_redirect(*ifindex, 0); +} + +SEC("drop_non_tun_vip") +int _drop_non_tun_vip(struct __sk_buff *skb) +{ + struct bpf_tunnel_key tkey = {}; + void *data = (void *)(long)skb->data; + struct eth_hdr *eth = data; + void *data_end = (void *)(long)skb->data_end; + + if (data + sizeof(*eth) > data_end) + return TC_ACT_OK; + + if (eth->h_proto == htons(ETH_P_IP)) { + struct iphdr *iph = data + sizeof(*eth); + + if (data + sizeof(*eth) + sizeof(*iph) > data_end) + return TC_ACT_OK; + + if (is_vip_addr(eth->h_proto, iph->daddr)) + return TC_ACT_SHOT; + } else if (eth->h_proto == htons(ETH_P_IPV6)) { + struct ipv6hdr *ip6h = data + sizeof(*eth); + + if (data + sizeof(*eth) + sizeof(*ip6h) > data_end) + return TC_ACT_OK; + + if (is_vip_addr(eth->h_proto, ip6h->daddr.s6_addr32[0])) + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/tc_l2_redirect_user.c b/samples/bpf/tc_l2_redirect_user.c new file mode 100644 index 000000000000..4013c5337b91 --- /dev/null +++ b/samples/bpf/tc_l2_redirect_user.c @@ -0,0 +1,73 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include +#include + +#include +#include +#include +#include +#include + +#include "libbpf.h" + +static void usage(void) +{ + printf("Usage: tc_l2_ipip_redirect [...]\n"); + printf(" -U Update an already pinned BPF array\n"); + printf(" -i Interface index\n"); + printf(" -h Display this help\n"); +} + +int main(int argc, char **argv) +{ + const char *pinned_file = NULL; + int ifindex = -1; + int array_key = 0; + int array_fd = -1; + int ret = -1; + int opt; + + while ((opt = getopt(argc, argv, "F:U:i:")) != -1) { + switch (opt) { + /* General args */ + case 'U': + pinned_file = optarg; + break; + case 'i': + ifindex = atoi(optarg); + break; + default: + usage(); + goto out; + } + } + + if (ifindex < 0 || !pinned_file) { + usage(); + goto out; + } + + array_fd = bpf_obj_get(pinned_file); + if (array_fd < 0) { + fprintf(stderr, "bpf_obj_get(%s): %s(%d)\n", + pinned_file, strerror(errno), errno); + goto out; + } + + /* bpf_tunnel_key.remote_ipv4 expects host byte orders */ + ret = bpf_update_elem(array_fd, &array_key, &ifindex, 0); + if (ret) { + perror("bpf_update_elem"); + goto out; + } + +out: + if (array_fd != -1) + close(array_fd); + return ret; +} diff --git a/scripts/Makefile.build b/scripts/Makefile.build index de46ab03f063..7675d11ee65e 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -159,7 +159,8 @@ cmd_cpp_i_c = $(CPP) $(c_flags) -o $@ $< $(obj)/%.i: $(src)/%.c FORCE $(call if_changed_dep,cpp_i_c) -cmd_gensymtypes = \ +# These mirror gensymtypes_S and co below, keep them in synch. +cmd_gensymtypes_c = \ $(CPP) -D__GENKSYMS__ $(c_flags) $< | \ $(GENKSYMS) $(if $(1), -T $(2)) \ $(patsubst y,-s _,$(CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX)) \ @@ -169,7 +170,7 @@ cmd_gensymtypes = \ quiet_cmd_cc_symtypes_c = SYM $(quiet_modtag) $@ cmd_cc_symtypes_c = \ set -e; \ - $(call cmd_gensymtypes,true,$@) >/dev/null; \ + $(call cmd_gensymtypes_c,true,$@) >/dev/null; \ test -s $@ || rm -f $@ $(obj)/%.symtypes : $(src)/%.c FORCE @@ -198,9 +199,10 @@ else # the actual value of the checksum generated by genksyms cmd_cc_o_c = $(CC) $(c_flags) -c -o $(@D)/.tmp_$(@F) $< -cmd_modversions = \ + +cmd_modversions_c = \ if $(OBJDUMP) -h $(@D)/.tmp_$(@F) | grep -q __ksymtab; then \ - $(call cmd_gensymtypes,$(KBUILD_SYMTYPES),$(@:.o=.symtypes)) \ + $(call cmd_gensymtypes_c,$(KBUILD_SYMTYPES),$(@:.o=.symtypes)) \ > $(@D)/.tmp_$(@F:.o=.ver); \ \ $(LD) $(LDFLAGS) -r -o $@ $(@D)/.tmp_$(@F) \ @@ -268,13 +270,14 @@ endif # CONFIG_STACK_VALIDATION define rule_cc_o_c $(call echo-cmd,checksrc) $(cmd_checksrc) \ $(call cmd_and_fixdep,cc_o_c) \ - $(cmd_modversions) \ + $(cmd_modversions_c) \ $(cmd_objtool) \ $(call echo-cmd,record_mcount) $(cmd_record_mcount) endef define rule_as_o_S $(call cmd_and_fixdep,as_o_S) \ + $(cmd_modversions_S) \ $(cmd_objtool) endef @@ -314,6 +317,39 @@ modkern_aflags := $(KBUILD_AFLAGS_KERNEL) $(AFLAGS_KERNEL) $(real-objs-m) : modkern_aflags := $(KBUILD_AFLAGS_MODULE) $(AFLAGS_MODULE) $(real-objs-m:.o=.s): modkern_aflags := $(KBUILD_AFLAGS_MODULE) $(AFLAGS_MODULE) +# .S file exports must have their C prototypes defined in asm/asm-prototypes.h +# or a file that it includes, in order to get versioned symbols. We build a +# dummy C file that includes asm-prototypes and the EXPORT_SYMBOL lines from +# the .S file (with trailing ';'), and run genksyms on that, to extract vers. +# +# This is convoluted. The .S file must first be preprocessed to run guards and +# expand names, then the resulting exports must be constructed into plain +# EXPORT_SYMBOL(symbol); to build our dummy C file, and that gets preprocessed +# to make the genksyms input. +# +# These mirror gensymtypes_c and co above, keep them in synch. +cmd_gensymtypes_S = \ + (echo "\#include " ; \ + echo "\#include " ; \ + $(CPP) $(a_flags) $< | \ + grep "\<___EXPORT_SYMBOL\>" | \ + sed 's/.*___EXPORT_SYMBOL[[:space:]]*\([a-zA-Z0-9_]*\)[[:space:]]*,.*/EXPORT_SYMBOL(\1);/' ) | \ + $(CPP) -D__GENKSYMS__ $(c_flags) -xc - | \ + $(GENKSYMS) $(if $(1), -T $(2)) \ + $(patsubst y,-s _,$(CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX)) \ + $(if $(KBUILD_PRESERVE),-p) \ + -r $(firstword $(wildcard $(2:.symtypes=.symref) /dev/null)) + +quiet_cmd_cc_symtypes_S = SYM $(quiet_modtag) $@ +cmd_cc_symtypes_S = \ + set -e; \ + $(call cmd_gensymtypes_S,true,$@) >/dev/null; \ + test -s $@ || rm -f $@ + +$(obj)/%.symtypes : $(src)/%.S FORCE + $(call cmd,cc_symtypes_S) + + quiet_cmd_cpp_s_S = CPP $(quiet_modtag) $@ cmd_cpp_s_S = $(CPP) $(a_flags) -o $@ $< @@ -321,7 +357,37 @@ $(obj)/%.s: $(src)/%.S FORCE $(call if_changed_dep,cpp_s_S) quiet_cmd_as_o_S = AS $(quiet_modtag) $@ -cmd_as_o_S = $(CC) $(a_flags) -c -o $@ $< + +ifndef CONFIG_MODVERSIONS +cmd_as_o_S = $(CC) $(a_flags) -c -o $@ $< + +else + +ASM_PROTOTYPES := $(wildcard $(srctree)/arch/$(SRCARCH)/include/asm/asm-prototypes.h) + +ifeq ($(ASM_PROTOTYPES),) +cmd_as_o_S = $(CC) $(a_flags) -c -o $@ $< + +else + +# versioning matches the C process described above, with difference that +# we parse asm-prototypes.h C header to get function definitions. + +cmd_as_o_S = $(CC) $(a_flags) -c -o $(@D)/.tmp_$(@F) $< + +cmd_modversions_S = \ + if $(OBJDUMP) -h $(@D)/.tmp_$(@F) | grep -q __ksymtab; then \ + $(call cmd_gensymtypes_S,$(KBUILD_SYMTYPES),$(@:.o=.symtypes)) \ + > $(@D)/.tmp_$(@F:.o=.ver); \ + \ + $(LD) $(LDFLAGS) -r -o $@ $(@D)/.tmp_$(@F) \ + -T $(@D)/.tmp_$(@F:.o=.ver); \ + rm -f $(@D)/.tmp_$(@F) $(@D)/.tmp_$(@F:.o=.ver); \ + else \ + mv -f $(@D)/.tmp_$(@F) $@; \ + fi; +endif +endif $(obj)/%.o: $(src)/%.S $(objtool_obj) FORCE $(call if_changed_rule,as_o_S) @@ -430,6 +496,9 @@ cmd_export_list = $(OBJDUMP) -h $< | \ $(obj)/lib-ksyms.o: $(lib-target) FORCE $(call if_changed,export_list) + +targets += $(obj)/lib-ksyms.o + endif # diff --git a/scripts/gcc-x86_64-has-stack-protector.sh b/scripts/gcc-x86_64-has-stack-protector.sh index 973e8c141567..17867e723a51 100755 --- a/scripts/gcc-x86_64-has-stack-protector.sh +++ b/scripts/gcc-x86_64-has-stack-protector.sh @@ -1,6 +1,6 @@ #!/bin/sh -echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -c -O0 -mcmodel=kernel -fstack-protector - -o - 2> /dev/null | grep -q "%gs" +echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -c -O0 -mcmodel=kernel -fno-PIE -fstack-protector - -o - 2> /dev/null | grep -q "%gs" if [ "$?" -eq "0" ] ; then echo y else diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 2f909dd8b7b8..ea81c08ddc7a 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6907,8 +6907,6 @@ static const struct hda_fixup alc662_fixups[] = { .v.pins = (const struct hda_pintbl[]) { { 0x15, 0x40f000f0 }, /* disabled */ { 0x16, 0x40f000f0 }, /* disabled */ - { 0x18, 0x01014011 }, /* LO */ - { 0x1a, 0x01014012 }, /* LO */ { } } }, diff --git a/sound/pci/hda/thinkpad_helper.c b/sound/pci/hda/thinkpad_helper.c index 6a23302297c9..4d9d320a7971 100644 --- a/sound/pci/hda/thinkpad_helper.c +++ b/sound/pci/hda/thinkpad_helper.c @@ -13,7 +13,8 @@ static void (*old_vmaster_hook)(void *, int); static bool is_thinkpad(struct hda_codec *codec) { return (codec->core.subsystem_id >> 16 == 0x17aa) && - (acpi_dev_found("LEN0068") || acpi_dev_found("IBM0068")); + (acpi_dev_found("LEN0068") || acpi_dev_found("LEN0268") || + acpi_dev_found("IBM0068")); } static void update_tpacpi_mute_led(void *private_data, int enabled) diff --git a/sound/soc/qcom/lpass-platform.c b/sound/soc/qcom/lpass-platform.c index 07000f53db44..b392e51de94d 100644 --- a/sound/soc/qcom/lpass-platform.c +++ b/sound/soc/qcom/lpass-platform.c @@ -75,6 +75,7 @@ static int lpass_platform_pcmops_open(struct snd_pcm_substream *substream) data->i2s_port = cpu_dai->driver->id; runtime->private_data = data; + dma_ch = 0; if (v->alloc_dma_channel) dma_ch = v->alloc_dma_channel(drvdata, dir); if (dma_ch < 0) diff --git a/sound/usb/card.c b/sound/usb/card.c index 9e5276d6dda0..2ddc034673a8 100644 --- a/sound/usb/card.c +++ b/sound/usb/card.c @@ -315,7 +315,8 @@ static int snd_usb_audio_free(struct snd_usb_audio *chip) snd_usb_endpoint_free(ep); mutex_destroy(&chip->mutex); - dev_set_drvdata(&chip->dev->dev, NULL); + if (!atomic_read(&chip->shutdown)) + dev_set_drvdata(&chip->dev->dev, NULL); kfree(chip); return 0; } diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 4ffff7be9299..a53fef0c673b 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -1337,8 +1337,8 @@ static int hist_browser__show_hierarchy_entry(struct hist_browser *browser, } if (first) { - ui_browser__printf(&browser->b, "%c", folded_sign); - width--; + ui_browser__printf(&browser->b, "%c ", folded_sign); + width -= 2; first = false; } else { ui_browser__printf(&browser->b, " "); @@ -1361,8 +1361,10 @@ static int hist_browser__show_hierarchy_entry(struct hist_browser *browser, width -= hpp.buf - s; } - ui_browser__write_nstring(&browser->b, "", hierarchy_indent); - width -= hierarchy_indent; + if (!first) { + ui_browser__write_nstring(&browser->b, "", hierarchy_indent); + width -= hierarchy_indent; + } if (column >= browser->b.horiz_scroll) { char s[2048]; @@ -1381,7 +1383,13 @@ static int hist_browser__show_hierarchy_entry(struct hist_browser *browser, } perf_hpp_list__for_each_format(entry->hpp_list, fmt) { - ui_browser__write_nstring(&browser->b, "", 2); + if (first) { + ui_browser__printf(&browser->b, "%c ", folded_sign); + first = false; + } else { + ui_browser__write_nstring(&browser->b, "", 2); + } + width -= 2; /* @@ -1555,10 +1563,11 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows int indent = hists->nr_hpp_node - 2; bool first_node, first_col; - ret = scnprintf(buf, size, " "); + ret = scnprintf(buf, size, " "); if (advance_hpp_check(&dummy_hpp, ret)) return ret; + first_node = true; /* the first hpp_list_node is for overhead columns */ fmt_node = list_first_entry(&hists->hpp_formats, struct perf_hpp_list_node, list); @@ -1573,12 +1582,16 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, " "); if (advance_hpp_check(&dummy_hpp, ret)) break; + + first_node = false; } - ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "%*s", - indent * HIERARCHY_INDENT, ""); - if (advance_hpp_check(&dummy_hpp, ret)) - return ret; + if (!first_node) { + ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "%*s", + indent * HIERARCHY_INDENT, ""); + if (advance_hpp_check(&dummy_hpp, ret)) + return ret; + } first_node = true; list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) { @@ -2076,8 +2089,21 @@ void hist_browser__init(struct hist_browser *browser, browser->b.use_navkeypressed = true; browser->show_headers = symbol_conf.show_hist_headers; - hists__for_each_format(hists, fmt) + if (symbol_conf.report_hierarchy) { + struct perf_hpp_list_node *fmt_node; + + /* count overhead columns (in the first node) */ + fmt_node = list_first_entry(&hists->hpp_formats, + struct perf_hpp_list_node, list); + perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) + ++browser->b.columns; + + /* add a single column for whole hierarchy sort keys*/ ++browser->b.columns; + } else { + hists__for_each_format(hists, fmt) + ++browser->b.columns; + } hists__reset_column_width(hists); } diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index b02992efb513..a69f027368ef 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -1600,18 +1600,18 @@ static void hists__hierarchy_output_resort(struct hists *hists, if (prog) ui_progress__update(prog, 1); + hists->nr_entries++; + if (!he->filtered) { + hists->nr_non_filtered_entries++; + hists__calc_col_len(hists, he); + } + if (!he->leaf) { hists__hierarchy_output_resort(hists, prog, &he->hroot_in, &he->hroot_out, min_callchain_hits, use_callchain); - hists->nr_entries++; - if (!he->filtered) { - hists->nr_non_filtered_entries++; - hists__calc_col_len(hists, he); - } - continue; } diff --git a/tools/power/acpi/Makefile.config b/tools/power/acpi/Makefile.config index a538ff44b108..a1883bbb0144 100644 --- a/tools/power/acpi/Makefile.config +++ b/tools/power/acpi/Makefile.config @@ -8,18 +8,19 @@ # as published by the Free Software Foundation; version 2 # of the License. -include ../../../../scripts/Makefile.include +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(shell pwd))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +#$(info Determined 'srctree' to be $(srctree)) +endif -OUTPUT=./ +include $(srctree)/../../scripts/Makefile.include + +OUTPUT=$(srctree)/ ifeq ("$(origin O)", "command line") - OUTPUT := $(O)/ -endif - -ifneq ($(OUTPUT),) -# check that the output directory actually exists -OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd) -$(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist)) + OUTPUT := $(O)/power/acpi/ endif +#$(info Determined 'OUTPUT' to be $(OUTPUT)) # --- CONFIGURATION BEGIN --- @@ -70,8 +71,8 @@ WARNINGS := -Wall WARNINGS += $(call cc-supports,-Wstrict-prototypes) WARNINGS += $(call cc-supports,-Wdeclaration-after-statement) -KERNEL_INCLUDE := ../../../include -ACPICA_INCLUDE := ../../../drivers/acpi/acpica +KERNEL_INCLUDE := $(OUTPUT)include +ACPICA_INCLUDE := $(srctree)/../../../drivers/acpi/acpica CFLAGS += -D_LINUX -I$(KERNEL_INCLUDE) -I$(ACPICA_INCLUDE) CFLAGS += $(WARNINGS) diff --git a/tools/power/acpi/Makefile.rules b/tools/power/acpi/Makefile.rules index ec87a9e562c0..373738338f51 100644 --- a/tools/power/acpi/Makefile.rules +++ b/tools/power/acpi/Makefile.rules @@ -8,28 +8,42 @@ # as published by the Free Software Foundation; version 2 # of the License. -$(OUTPUT)$(TOOL): $(TOOL_OBJS) FORCE - $(ECHO) " LD " $@ - $(QUIET) $(LD) $(CFLAGS) $(LDFLAGS) $(TOOL_OBJS) -L$(OUTPUT) -o $@ +objdir := $(OUTPUT)tools/$(TOOL)/ +toolobjs := $(addprefix $(objdir),$(TOOL_OBJS)) +$(OUTPUT)$(TOOL): $(toolobjs) FORCE + $(ECHO) " LD " $(subst $(OUTPUT),,$@) + $(QUIET) $(LD) $(CFLAGS) $(LDFLAGS) $(toolobjs) -L$(OUTPUT) -o $@ + $(ECHO) " STRIP " $(subst $(OUTPUT),,$@) $(QUIET) $(STRIPCMD) $@ -$(OUTPUT)%.o: %.c - $(ECHO) " CC " $@ +$(KERNEL_INCLUDE): + $(ECHO) " MKDIR " $(subst $(OUTPUT),,$@) + $(QUIET) mkdir -p $(KERNEL_INCLUDE) + $(ECHO) " CP " $(subst $(OUTPUT),,$@) + $(QUIET) cp -rf $(srctree)/../../../include/acpi $(KERNEL_INCLUDE)/ + +$(objdir)%.o: %.c $(KERNEL_INCLUDE) + $(ECHO) " CC " $(subst $(OUTPUT),,$@) $(QUIET) $(CC) -c $(CFLAGS) -o $@ $< all: $(OUTPUT)$(TOOL) clean: - -find $(OUTPUT) \( -not -type d \) \ - -and \( -name '*~' -o -name '*.[oas]' \) \ - -type f -print \ - | xargs rm -f - -rm -f $(OUTPUT)$(TOOL) + $(ECHO) " RMOBJ " $(subst $(OUTPUT),,$(objdir)) + $(QUIET) find $(objdir) \( -not -type d \)\ + -and \( -name '*~' -o -name '*.[oas]' \)\ + -type f -print | xargs rm -f + $(ECHO) " RM " $(TOOL) + $(QUIET) rm -f $(OUTPUT)$(TOOL) + $(ECHO) " RMINC " $(subst $(OUTPUT),,$(KERNEL_INCLUDE)) + $(QUIET) rm -rf $(KERNEL_INCLUDE) install-tools: - $(INSTALL) -d $(DESTDIR)${sbindir} - $(INSTALL_PROGRAM) $(OUTPUT)$(TOOL) $(DESTDIR)${sbindir} + $(ECHO) " INST " $(TOOL) + $(QUIET) $(INSTALL) -d $(DESTDIR)$(sbindir) + $(QUIET) $(INSTALL_PROGRAM) $(OUTPUT)$(TOOL) $(DESTDIR)$(sbindir) uninstall-tools: - - rm -f $(DESTDIR)${sbindir}/$(TOOL) + $(ECHO) " UNINST " $(TOOL) + $(QUIET) rm -f $(DESTDIR)$(sbindir)/$(TOOL) install: all install-tools $(EXTRA_INSTALL) uninstall: uninstall-tools $(EXTRA_UNINSTALL) diff --git a/tools/power/acpi/tools/acpidbg/Makefile b/tools/power/acpi/tools/acpidbg/Makefile index 352df4b41ae9..f2d06e773eb4 100644 --- a/tools/power/acpi/tools/acpidbg/Makefile +++ b/tools/power/acpi/tools/acpidbg/Makefile @@ -17,9 +17,7 @@ vpath %.c \ ../../os_specific/service_layers\ . CFLAGS += -DACPI_APPLICATION -DACPI_SINGLE_THREAD -DACPI_DEBUGGER\ - -I.\ - -I../../../../../drivers/acpi/acpica\ - -I../../../../../include + -I. LDFLAGS += -lpthread TOOL_OBJS = \ acpidbg.o diff --git a/tools/power/acpi/tools/acpidbg/acpidbg.c b/tools/power/acpi/tools/acpidbg/acpidbg.c index a88ac45b7756..4308362d7068 100644 --- a/tools/power/acpi/tools/acpidbg/acpidbg.c +++ b/tools/power/acpi/tools/acpidbg/acpidbg.c @@ -12,10 +12,16 @@ #include /* Headers not included by include/acpi/platform/aclinux.h */ +#include +#include +#include +#include +#include #include #include #include -#include +#include +#include "../../../../../include/linux/circ_buf.h" #define ACPI_AML_FILE "/sys/kernel/debug/acpi/acpidbg" #define ACPI_AML_SEC_TICK 1 diff --git a/tools/power/acpi/tools/acpidump/Makefile b/tools/power/acpi/tools/acpidump/Makefile index 04b5db7c7c0b..f7c7af1f9258 100644 --- a/tools/power/acpi/tools/acpidump/Makefile +++ b/tools/power/acpi/tools/acpidump/Makefile @@ -19,9 +19,7 @@ vpath %.c \ ./\ ../../common\ ../../os_specific/service_layers -CFLAGS += -DACPI_DUMP_APP -I.\ - -I../../../../../drivers/acpi/acpica\ - -I../../../../../include +CFLAGS += -DACPI_DUMP_APP -I. TOOL_OBJS = \ apdump.o\ apfiles.o\ @@ -49,7 +47,9 @@ TOOL_OBJS = \ include ../../Makefile.rules -install-man: ../../man/acpidump.8 - $(INSTALL_DATA) -D $< $(DESTDIR)${mandir}/man8/acpidump.8 +install-man: $(srctree)/man/acpidump.8 + $(ECHO) " INST " acpidump.8 + $(QUIET) $(INSTALL_DATA) -D $< $(DESTDIR)$(mandir)/man8/acpidump.8 uninstall-man: - - rm -f $(DESTDIR)${mandir}/man8/acpidump.8 + $(ECHO) " UNINST " acpidump.8 + $(QUIET) rm -f $(DESTDIR)$(mandir)/man8/acpidump.8 diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c index 6e9c40eea208..69ccce308458 100644 --- a/virt/kvm/arm/pmu.c +++ b/virt/kvm/arm/pmu.c @@ -305,7 +305,7 @@ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val) continue; type = vcpu_sys_reg(vcpu, PMEVTYPER0_EL0 + i) & ARMV8_PMU_EVTYPE_EVENT; - if ((type == ARMV8_PMU_EVTYPE_EVENT_SW_INCR) + if ((type == ARMV8_PMUV3_PERFCTR_SW_INCR) && (enable & BIT(i))) { reg = vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) + 1; reg = lower_32_bits(reg); @@ -379,7 +379,8 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data, eventsel = data & ARMV8_PMU_EVTYPE_EVENT; /* Software increment event does't need to be backed by a perf event */ - if (eventsel == ARMV8_PMU_EVTYPE_EVENT_SW_INCR) + if (eventsel == ARMV8_PMUV3_PERFCTR_SW_INCR && + select_idx != ARMV8_PMU_CYCLE_IDX) return; memset(&attr, 0, sizeof(struct perf_event_attr)); @@ -391,7 +392,8 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data, attr.exclude_kernel = data & ARMV8_PMU_EXCLUDE_EL1 ? 1 : 0; attr.exclude_hv = 1; /* Don't count EL2 events */ attr.exclude_host = 1; /* Don't count host events */ - attr.config = eventsel; + attr.config = (select_idx == ARMV8_PMU_CYCLE_IDX) ? + ARMV8_PMUV3_PERFCTR_CPU_CYCLES : eventsel; counter = kvm_pmu_get_counter_value(vcpu, select_idx); /* The initial sample period (overflow count) of an event. */ diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index 8035cc1eb955..efeceb0a222d 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -91,6 +91,7 @@ static void async_pf_execute(struct work_struct *work) spin_lock(&vcpu->async_pf.lock); list_add_tail(&apf->link, &vcpu->async_pf.done); + apf->vcpu = NULL; spin_unlock(&vcpu->async_pf.lock); /* @@ -113,6 +114,8 @@ static void async_pf_execute(struct work_struct *work) void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu) { + spin_lock(&vcpu->async_pf.lock); + /* cancel outstanding work queue item */ while (!list_empty(&vcpu->async_pf.queue)) { struct kvm_async_pf *work = @@ -120,6 +123,14 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu) typeof(*work), queue); list_del(&work->queue); + /* + * We know it's present in vcpu->async_pf.done, do + * nothing here. + */ + if (!work->vcpu) + continue; + + spin_unlock(&vcpu->async_pf.lock); #ifdef CONFIG_KVM_ASYNC_PF_SYNC flush_work(&work->work); #else @@ -129,9 +140,9 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu) kmem_cache_free(async_pf_cache, work); } #endif + spin_lock(&vcpu->async_pf.lock); } - spin_lock(&vcpu->async_pf.lock); while (!list_empty(&vcpu->async_pf.done)) { struct kvm_async_pf *work = list_first_entry(&vcpu->async_pf.done,