diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl index 7514dbf0a679..c36892c072da 100644 --- a/Documentation/DocBook/device-drivers.tmpl +++ b/Documentation/DocBook/device-drivers.tmpl @@ -227,7 +227,7 @@ X!Isound/sound_firmware.c 16x50 UART Driver !Edrivers/tty/serial/serial_core.c -!Edrivers/tty/serial/8250/8250.c +!Edrivers/tty/serial/8250/8250_core.c diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 4609e81dbc37..8ccbf27aead4 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -596,9 +596,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted. is selected automatically. Check Documentation/kdump/kdump.txt for further details. - crashkernel_low=size[KMG] - [KNL, x86] parts under 4G. - crashkernel=range1:size1[,range2:size2,...][@offset] [KNL] Same as above, but depends on the memory in the running system. The syntax of range is @@ -606,6 +603,26 @@ bytes respectively. Such letter suffixes can also be entirely omitted. a memory unit (amount[KMG]). See also Documentation/kdump/kdump.txt for an example. + crashkernel=size[KMG],high + [KNL, x86_64] range could be above 4G. Allow kernel + to allocate physical memory region from top, so could + be above 4G if system have more than 4G ram installed. + Otherwise memory region will be allocated below 4G, if + available. + It will be ignored if crashkernel=X is specified. + crashkernel=size[KMG],low + [KNL, x86_64] range under 4G. When crashkernel=X,high + is passed, kernel could allocate physical memory region + above 4G, that cause second kernel crash on system + that require some amount of low memory, e.g. swiotlb + requires at least 64M+32K low memory. Kernel would + try to allocate 72M below 4G automatically. + This one let user to specify own low range under 4G + for second kernel instead. + 0: to disable low allocation. + It will be ignored when crashkernel=X,high is not used + or memory reserved is below 4G. + cs89x0_dma= [HW,NET] Format: @@ -788,6 +805,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted. edd= [EDD] Format: {"off" | "on" | "skip[mbr]"} + efi_no_storage_paranoia [EFI; X86] + Using this parameter you can use more than 50% of + your efi variable storage. Use this parameter only if + you are really sure that your UEFI does sane gc and + fulfills the spec otherwise your board may brick. + eisa_irq_edge= [PARISC,HW] See header of drivers/parisc/eisa.c. diff --git a/Documentation/scsi/LICENSE.qla2xxx b/Documentation/scsi/LICENSE.qla2xxx index 27a91cf43d6d..5020b7b5a244 100644 --- a/Documentation/scsi/LICENSE.qla2xxx +++ b/Documentation/scsi/LICENSE.qla2xxx @@ -1,4 +1,4 @@ -Copyright (c) 2003-2012 QLogic Corporation +Copyright (c) 2003-2013 QLogic Corporation QLogic Linux FC-FCoE Driver This program includes a device driver for Linux 3.x. diff --git a/MAINTAINERS b/MAINTAINERS index c39bdc3fb425..1ee5d119831e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4941,6 +4941,12 @@ W: logfs.org S: Maintained F: fs/logfs/ +LPC32XX MACHINE SUPPORT +M: Roland Stigge +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +S: Maintained +F: arch/arm/mach-lpc32xx/ + LSILOGIC MPT FUSION DRIVERS (FC/SAS/SPI) M: Nagalakshmi Nandigama M: Sreekanth Reddy @@ -6627,7 +6633,7 @@ S: Supported F: fs/reiserfs/ REGISTER MAP ABSTRACTION -M: Mark Brown +M: Mark Brown T: git git://git.kernel.org/pub/scm/linux/kernel/git/broonie/regmap.git S: Supported F: drivers/base/regmap/ @@ -7375,7 +7381,7 @@ F: sound/ SOUND - SOC LAYER / DYNAMIC AUDIO POWER MANAGEMENT (ASoC) M: Liam Girdwood -M: Mark Brown +M: Mark Brown T: git git://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound.git L: alsa-devel@alsa-project.org (moderated for non-subscribers) W: http://alsa-project.org/main/index.php/ASoC @@ -7464,7 +7470,7 @@ F: drivers/clk/spear/ SPI SUBSYSTEM M: Grant Likely -M: Mark Brown +M: Mark Brown L: spi-devel-general@lists.sourceforge.net Q: http://patchwork.kernel.org/project/spi-devel-general/list/ T: git git://git.secretlab.ca/git/linux-2.6.git @@ -8709,7 +8715,7 @@ F: drivers/scsi/vmw_pvscsi.h VOLTAGE AND CURRENT REGULATOR FRAMEWORK M: Liam Girdwood -M: Mark Brown +M: Mark Brown W: http://opensource.wolfsonmicro.com/node/15 W: http://www.slimlogic.co.uk/?p=48 T: git git://git.kernel.org/pub/scm/linux/kernel/git/lrg/regulator.git diff --git a/Makefile b/Makefile index 58a165b02af1..46263d808876 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 3 PATCHLEVEL = 9 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc8 NAME = Unicycling Gorilla # *DOCUMENTATION* @@ -513,7 +513,8 @@ ifeq ($(KBUILD_EXTMOD),) # Carefully list dependencies so we do not try to build scripts twice # in parallel PHONY += scripts -scripts: scripts_basic include/config/auto.conf include/config/tristate.conf +scripts: scripts_basic include/config/auto.conf include/config/tristate.conf \ + asm-generic $(Q)$(MAKE) $(build)=$(@) # Objects we will link into vmlinux / subdirs we need to visit diff --git a/arch/alpha/Makefile b/arch/alpha/Makefile index 4759fe751aa1..2cc3cc519c54 100644 --- a/arch/alpha/Makefile +++ b/arch/alpha/Makefile @@ -12,7 +12,7 @@ NM := $(NM) -B LDFLAGS_vmlinux := -static -N #-relax CHECKFLAGS += -D__alpha__ -m64 -cflags-y := -pipe -mno-fp-regs -ffixed-8 -msmall-data +cflags-y := -pipe -mno-fp-regs -ffixed-8 cflags-y += $(call cc-option, -fno-jump-tables) cpuflags-$(CONFIG_ALPHA_EV4) := -mcpu=ev4 diff --git a/arch/alpha/include/asm/floppy.h b/arch/alpha/include/asm/floppy.h index 46cefbd50e73..bae97eb19d26 100644 --- a/arch/alpha/include/asm/floppy.h +++ b/arch/alpha/include/asm/floppy.h @@ -26,7 +26,7 @@ #define fd_disable_irq() disable_irq(FLOPPY_IRQ) #define fd_cacheflush(addr,size) /* nothing */ #define fd_request_irq() request_irq(FLOPPY_IRQ, floppy_interrupt,\ - IRQF_DISABLED, "floppy", NULL) + 0, "floppy", NULL) #define fd_free_irq() free_irq(FLOPPY_IRQ, NULL) #ifdef CONFIG_PCI diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c index 2872accd2215..7b2be251c30f 100644 --- a/arch/alpha/kernel/irq.c +++ b/arch/alpha/kernel/irq.c @@ -117,13 +117,6 @@ handle_irq(int irq) return; } - /* - * From here we must proceed with IPL_MAX. Note that we do not - * explicitly enable interrupts afterwards - some MILO PALcode - * (namely LX164 one) seems to have severe problems with RTI - * at IPL 0. - */ - local_irq_disable(); irq_enter(); generic_handle_irq_desc(irq, desc); irq_exit(); diff --git a/arch/alpha/kernel/irq_alpha.c b/arch/alpha/kernel/irq_alpha.c index 772ddfdb71a8..f433fc11877a 100644 --- a/arch/alpha/kernel/irq_alpha.c +++ b/arch/alpha/kernel/irq_alpha.c @@ -45,6 +45,14 @@ do_entInt(unsigned long type, unsigned long vector, unsigned long la_ptr, struct pt_regs *regs) { struct pt_regs *old_regs; + + /* + * Disable interrupts during IRQ handling. + * Note that there is no matching local_irq_enable() due to + * severe problems with RTI at IPL0 and some MILO PALcode + * (namely LX164). + */ + local_irq_disable(); switch (type) { case 0: #ifdef CONFIG_SMP @@ -62,7 +70,6 @@ do_entInt(unsigned long type, unsigned long vector, { long cpu; - local_irq_disable(); smp_percpu_timer_interrupt(regs); cpu = smp_processor_id(); if (cpu != boot_cpuid) { @@ -222,7 +229,6 @@ process_mcheck_info(unsigned long vector, unsigned long la_ptr, struct irqaction timer_irqaction = { .handler = timer_interrupt, - .flags = IRQF_DISABLED, .name = "timer", }; diff --git a/arch/alpha/kernel/sys_nautilus.c b/arch/alpha/kernel/sys_nautilus.c index 4d4c046f708d..1383f8601a93 100644 --- a/arch/alpha/kernel/sys_nautilus.c +++ b/arch/alpha/kernel/sys_nautilus.c @@ -188,6 +188,10 @@ nautilus_machine_check(unsigned long vector, unsigned long la_ptr) extern void free_reserved_mem(void *, void *); extern void pcibios_claim_one_bus(struct pci_bus *); +static struct resource irongate_io = { + .name = "Irongate PCI IO", + .flags = IORESOURCE_IO, +}; static struct resource irongate_mem = { .name = "Irongate PCI MEM", .flags = IORESOURCE_MEM, @@ -209,6 +213,7 @@ nautilus_init_pci(void) irongate = pci_get_bus_and_slot(0, 0); bus->self = irongate; + bus->resource[0] = &irongate_io; bus->resource[1] = &irongate_mem; pci_bus_size_bridges(bus); diff --git a/arch/alpha/kernel/sys_titan.c b/arch/alpha/kernel/sys_titan.c index 5cf4a481b8c5..a53cf03f49d5 100644 --- a/arch/alpha/kernel/sys_titan.c +++ b/arch/alpha/kernel/sys_titan.c @@ -280,15 +280,15 @@ titan_late_init(void) * all reported to the kernel as machine checks, so the handler * is a nop so it can be called to count the individual events. */ - titan_request_irq(63+16, titan_intr_nop, IRQF_DISABLED, + titan_request_irq(63+16, titan_intr_nop, 0, "CChip Error", NULL); - titan_request_irq(62+16, titan_intr_nop, IRQF_DISABLED, + titan_request_irq(62+16, titan_intr_nop, 0, "PChip 0 H_Error", NULL); - titan_request_irq(61+16, titan_intr_nop, IRQF_DISABLED, + titan_request_irq(61+16, titan_intr_nop, 0, "PChip 1 H_Error", NULL); - titan_request_irq(60+16, titan_intr_nop, IRQF_DISABLED, + titan_request_irq(60+16, titan_intr_nop, 0, "PChip 0 C_Error", NULL); - titan_request_irq(59+16, titan_intr_nop, IRQF_DISABLED, + titan_request_irq(59+16, titan_intr_nop, 0, "PChip 1 C_Error", NULL); /* @@ -348,9 +348,9 @@ privateer_init_pci(void) * Hook a couple of extra err interrupts that the * common titan code won't. */ - titan_request_irq(53+16, titan_intr_nop, IRQF_DISABLED, + titan_request_irq(53+16, titan_intr_nop, 0, "NMI", NULL); - titan_request_irq(50+16, titan_intr_nop, IRQF_DISABLED, + titan_request_irq(50+16, titan_intr_nop, 0, "Temperature Warning", NULL); /* diff --git a/arch/arc/include/asm/irqflags.h b/arch/arc/include/asm/irqflags.h index ccd84806b62f..eac071668201 100644 --- a/arch/arc/include/asm/irqflags.h +++ b/arch/arc/include/asm/irqflags.h @@ -39,7 +39,7 @@ static inline long arch_local_irq_save(void) " flag.nz %0 \n" : "=r"(temp), "=r"(flags) : "n"((STATUS_E1_MASK | STATUS_E2_MASK)) - : "cc"); + : "memory", "cc"); return flags; } @@ -53,7 +53,8 @@ static inline void arch_local_irq_restore(unsigned long flags) __asm__ __volatile__( " flag %0 \n" : - : "r"(flags)); + : "r"(flags) + : "memory"); } /* @@ -73,7 +74,8 @@ static inline void arch_local_irq_disable(void) " and %0, %0, %1 \n" " flag %0 \n" : "=&r"(temp) - : "n"(~(STATUS_E1_MASK | STATUS_E2_MASK))); + : "n"(~(STATUS_E1_MASK | STATUS_E2_MASK)) + : "memory"); } /* @@ -85,7 +87,9 @@ static inline long arch_local_save_flags(void) __asm__ __volatile__( " lr %0, [status32] \n" - : "=&r"(temp)); + : "=&r"(temp) + : + : "memory"); return temp; } diff --git a/arch/arm/boot/dts/imx28-m28evk.dts b/arch/arm/boot/dts/imx28-m28evk.dts index 6ce3d17c3a29..fd36e1cca104 100644 --- a/arch/arm/boot/dts/imx28-m28evk.dts +++ b/arch/arm/boot/dts/imx28-m28evk.dts @@ -152,7 +152,6 @@ i2c0: i2c@80058000 { pinctrl-names = "default"; pinctrl-0 = <&i2c0_pins_a>; - clock-frequency = <400000>; status = "okay"; sgtl5000: codec@0a { diff --git a/arch/arm/boot/dts/imx28-sps1.dts b/arch/arm/boot/dts/imx28-sps1.dts index e6cde8aa7fff..6c6a5442800a 100644 --- a/arch/arm/boot/dts/imx28-sps1.dts +++ b/arch/arm/boot/dts/imx28-sps1.dts @@ -70,7 +70,6 @@ i2c0: i2c@80058000 { pinctrl-names = "default"; pinctrl-0 = <&i2c0_pins_a>; - clock-frequency = <400000>; status = "okay"; rtc: rtc@51 { diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi index 06ec460b4581..281a223591ff 100644 --- a/arch/arm/boot/dts/imx6qdl.dtsi +++ b/arch/arm/boot/dts/imx6qdl.dtsi @@ -91,6 +91,7 @@ compatible = "arm,cortex-a9-twd-timer"; reg = <0x00a00600 0x20>; interrupts = <1 13 0xf01>; + clocks = <&clks 15>; }; L2: l2-cache@00a02000 { diff --git a/arch/arm/boot/dts/kirkwood-iomega_ix2_200.dts b/arch/arm/boot/dts/kirkwood-iomega_ix2_200.dts index 93c3afbef9ee..3694e94f6e99 100644 --- a/arch/arm/boot/dts/kirkwood-iomega_ix2_200.dts +++ b/arch/arm/boot/dts/kirkwood-iomega_ix2_200.dts @@ -96,11 +96,11 @@ marvell,function = "gpio"; }; pmx_led_rebuild_brt_ctrl_1: pmx-led-rebuild-brt-ctrl-1 { - marvell,pins = "mpp44"; + marvell,pins = "mpp46"; marvell,function = "gpio"; }; pmx_led_rebuild_brt_ctrl_2: pmx-led-rebuild-brt-ctrl-2 { - marvell,pins = "mpp45"; + marvell,pins = "mpp47"; marvell,function = "gpio"; }; @@ -157,14 +157,14 @@ gpios = <&gpio0 16 0>; linux,default-trigger = "default-on"; }; - health_led1 { + rebuild_led { + label = "status:white:rebuild_led"; + gpios = <&gpio1 4 0>; + }; + health_led { label = "status:red:health_led"; gpios = <&gpio1 5 0>; }; - health_led2 { - label = "status:white:health_led"; - gpios = <&gpio1 4 0>; - }; backup_led { label = "status:blue:backup_led"; gpios = <&gpio0 15 0>; diff --git a/arch/arm/include/asm/glue-cache.h b/arch/arm/include/asm/glue-cache.h index cca9f15704ed..ea289e1435e7 100644 --- a/arch/arm/include/asm/glue-cache.h +++ b/arch/arm/include/asm/glue-cache.h @@ -19,14 +19,6 @@ #undef _CACHE #undef MULTI_CACHE -#if defined(CONFIG_CPU_CACHE_V3) -# ifdef _CACHE -# define MULTI_CACHE 1 -# else -# define _CACHE v3 -# endif -#endif - #if defined(CONFIG_CPU_CACHE_V4) # ifdef _CACHE # define MULTI_CACHE 1 diff --git a/arch/arm/include/asm/hardware/iop3xx.h b/arch/arm/include/asm/hardware/iop3xx.h index 02fe2fbe2477..ed94b1a366ae 100644 --- a/arch/arm/include/asm/hardware/iop3xx.h +++ b/arch/arm/include/asm/hardware/iop3xx.h @@ -37,7 +37,7 @@ extern int iop3xx_get_init_atu(void); * IOP3XX processor registers */ #define IOP3XX_PERIPHERAL_PHYS_BASE 0xffffe000 -#define IOP3XX_PERIPHERAL_VIRT_BASE 0xfeffe000 +#define IOP3XX_PERIPHERAL_VIRT_BASE 0xfedfe000 #define IOP3XX_PERIPHERAL_SIZE 0x00002000 #define IOP3XX_PERIPHERAL_UPPER_PA (IOP3XX_PERIPHERAL_PHYS_BASE +\ IOP3XX_PERIPHERAL_SIZE - 1) diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index 6ef8afd1b64c..86b8fe398b95 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -111,7 +111,7 @@ #define L_PTE_S2_MT_WRITETHROUGH (_AT(pteval_t, 0xa) << 2) /* MemAttr[3:0] */ #define L_PTE_S2_MT_WRITEBACK (_AT(pteval_t, 0xf) << 2) /* MemAttr[3:0] */ #define L_PTE_S2_RDONLY (_AT(pteval_t, 1) << 6) /* HAP[1] */ -#define L_PTE_S2_RDWR (_AT(pteval_t, 2) << 6) /* HAP[2:1] */ +#define L_PTE_S2_RDWR (_AT(pteval_t, 3) << 6) /* HAP[2:1] */ /* * Hyp-mode PL2 PTE definitions for LPAE. diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h index 9e9c041358ca..ab865e65a84c 100644 --- a/arch/arm/include/asm/tlbflush.h +++ b/arch/arm/include/asm/tlbflush.h @@ -14,7 +14,6 @@ #include -#define TLB_V3_PAGE (1 << 0) #define TLB_V4_U_PAGE (1 << 1) #define TLB_V4_D_PAGE (1 << 2) #define TLB_V4_I_PAGE (1 << 3) @@ -22,7 +21,6 @@ #define TLB_V6_D_PAGE (1 << 5) #define TLB_V6_I_PAGE (1 << 6) -#define TLB_V3_FULL (1 << 8) #define TLB_V4_U_FULL (1 << 9) #define TLB_V4_D_FULL (1 << 10) #define TLB_V4_I_FULL (1 << 11) @@ -52,7 +50,6 @@ * ============= * * We have the following to choose from: - * v3 - ARMv3 * v4 - ARMv4 without write buffer * v4wb - ARMv4 with write buffer without I TLB flush entry instruction * v4wbi - ARMv4 with write buffer with I TLB flush entry instruction @@ -330,7 +327,6 @@ static inline void local_flush_tlb_all(void) if (tlb_flag(TLB_WB)) dsb(); - tlb_op(TLB_V3_FULL, "c6, c0, 0", zero); tlb_op(TLB_V4_U_FULL | TLB_V6_U_FULL, "c8, c7, 0", zero); tlb_op(TLB_V4_D_FULL | TLB_V6_D_FULL, "c8, c6, 0", zero); tlb_op(TLB_V4_I_FULL | TLB_V6_I_FULL, "c8, c5, 0", zero); @@ -351,9 +347,8 @@ static inline void local_flush_tlb_mm(struct mm_struct *mm) if (tlb_flag(TLB_WB)) dsb(); - if (possible_tlb_flags & (TLB_V3_FULL|TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) { + if (possible_tlb_flags & (TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) { if (cpumask_test_cpu(get_cpu(), mm_cpumask(mm))) { - tlb_op(TLB_V3_FULL, "c6, c0, 0", zero); tlb_op(TLB_V4_U_FULL, "c8, c7, 0", zero); tlb_op(TLB_V4_D_FULL, "c8, c6, 0", zero); tlb_op(TLB_V4_I_FULL, "c8, c5, 0", zero); @@ -385,9 +380,8 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) if (tlb_flag(TLB_WB)) dsb(); - if (possible_tlb_flags & (TLB_V3_PAGE|TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) && + if (possible_tlb_flags & (TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) && cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) { - tlb_op(TLB_V3_PAGE, "c6, c0, 0", uaddr); tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", uaddr); tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", uaddr); tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", uaddr); @@ -418,7 +412,6 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr) if (tlb_flag(TLB_WB)) dsb(); - tlb_op(TLB_V3_PAGE, "c6, c0, 0", kaddr); tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", kaddr); tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", kaddr); tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", kaddr); diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 5dc1aa6f0f7d..1fd749ee4a1b 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -1043,7 +1043,7 @@ static int dbg_cpu_pm_notify(struct notifier_block *self, unsigned long action, return NOTIFY_OK; } -static struct notifier_block __cpuinitdata dbg_cpu_pm_nb = { +static struct notifier_block dbg_cpu_pm_nb = { .notifier_call = dbg_cpu_pm_notify, }; diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 146157dfe27c..8c3094d0f7b7 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -253,7 +253,10 @@ validate_event(struct pmu_hw_events *hw_events, struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct pmu *leader_pmu = event->group_leader->pmu; - if (event->pmu != leader_pmu || event->state <= PERF_EVENT_STATE_OFF) + if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF) + return 1; + + if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec) return 1; return armpmu->get_event_idx(hw_events, event) >= 0; diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c index bd6f56b9ec21..59d2adb764a9 100644 --- a/arch/arm/kernel/sched_clock.c +++ b/arch/arm/kernel/sched_clock.c @@ -45,12 +45,12 @@ static u32 notrace jiffy_sched_clock_read(void) static u32 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read; -static inline u64 cyc_to_ns(u64 cyc, u32 mult, u32 shift) +static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift) { return (cyc * mult) >> shift; } -static unsigned long long cyc_to_sched_clock(u32 cyc, u32 mask) +static unsigned long long notrace cyc_to_sched_clock(u32 cyc, u32 mask) { u64 epoch_ns; u32 epoch_cyc; diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index d343a6c3a6d1..234e339196c0 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -56,7 +56,6 @@ #include #include "atags.h" -#include "tcm.h" #if defined(CONFIG_FPE_NWFPE) || defined(CONFIG_FPE_FASTFPE) @@ -798,8 +797,6 @@ void __init setup_arch(char **cmdline_p) reserve_crashkernel(); - tcm_init(); - #ifdef CONFIG_MULTI_IRQ_HANDLER handle_arch_irq = mdesc->handle_irq; #endif diff --git a/arch/arm/kernel/tcm.c b/arch/arm/kernel/tcm.c index 30ae6bb4a310..f50f19e5c138 100644 --- a/arch/arm/kernel/tcm.c +++ b/arch/arm/kernel/tcm.c @@ -17,7 +17,6 @@ #include #include #include -#include "tcm.h" static struct gen_pool *tcm_pool; static bool dtcm_present; diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 5a936988eb24..c1fe498983ac 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -201,6 +201,7 @@ int kvm_dev_ioctl_check_extension(long ext) break; case KVM_CAP_ARM_SET_DEVICE_ADDR: r = 1; + break; case KVM_CAP_NR_VCPUS: r = num_online_cpus(); break; diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c index 4ea9a982269c..7bed7556077a 100644 --- a/arch/arm/kvm/coproc.c +++ b/arch/arm/kvm/coproc.c @@ -79,11 +79,11 @@ static bool access_dcsw(struct kvm_vcpu *vcpu, u32 val; int cpu; - cpu = get_cpu(); - if (!p->is_write) return read_from_write_only(vcpu, p); + cpu = get_cpu(); + cpumask_setall(&vcpu->arch.require_dcache_flush); cpumask_clear_cpu(cpu, &vcpu->arch.require_dcache_flush); diff --git a/arch/arm/mach-highbank/hotplug.c b/arch/arm/mach-highbank/hotplug.c index f30c52843396..890cae23c12a 100644 --- a/arch/arm/mach-highbank/hotplug.c +++ b/arch/arm/mach-highbank/hotplug.c @@ -28,13 +28,11 @@ extern void secondary_startup(void); */ void __ref highbank_cpu_die(unsigned int cpu) { - flush_cache_all(); - highbank_set_cpu_jump(cpu, phys_to_virt(0)); + + flush_cache_louis(); highbank_set_core_pwr(); - cpu_do_idle(); - - /* We should never return from idle */ - panic("highbank: cpu %d unexpectedly exit from shutdown\n", cpu); + while (1) + cpu_do_idle(); } diff --git a/arch/arm/mach-imx/clk-imx35.c b/arch/arm/mach-imx/clk-imx35.c index e13a8fa5e62c..2193c834f55c 100644 --- a/arch/arm/mach-imx/clk-imx35.c +++ b/arch/arm/mach-imx/clk-imx35.c @@ -257,6 +257,7 @@ int __init mx35_clocks_init(void) clk_register_clkdev(clk[wdog_gate], NULL, "imx2-wdt.0"); clk_register_clkdev(clk[nfc_div], NULL, "imx25-nand.0"); clk_register_clkdev(clk[csi_gate], NULL, "mx3-camera.0"); + clk_register_clkdev(clk[admux_gate], "audmux", NULL); clk_prepare_enable(clk[spba_gate]); clk_prepare_enable(clk[gpio1_gate]); @@ -265,6 +266,7 @@ int __init mx35_clocks_init(void) clk_prepare_enable(clk[iim_gate]); clk_prepare_enable(clk[emi_gate]); clk_prepare_enable(clk[max_gate]); + clk_prepare_enable(clk[iomuxc_gate]); /* * SCC is needed to boot via mmc after a watchdog reset. The clock code diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c index 2f9ff93a4e61..d38e54f5b6d7 100644 --- a/arch/arm/mach-imx/clk-imx6q.c +++ b/arch/arm/mach-imx/clk-imx6q.c @@ -115,7 +115,7 @@ static const char *gpu2d_core_sels[] = { "axi", "pll3_usb_otg", "pll2_pfd0_352m" static const char *gpu3d_core_sels[] = { "mmdc_ch0_axi", "pll3_usb_otg", "pll2_pfd1_594m", "pll2_pfd2_396m", }; static const char *gpu3d_shader_sels[] = { "mmdc_ch0_axi", "pll3_usb_otg", "pll2_pfd1_594m", "pll2_pfd9_720m", }; static const char *ipu_sels[] = { "mmdc_ch0_axi", "pll2_pfd2_396m", "pll3_120m", "pll3_pfd1_540m", }; -static const char *ldb_di_sels[] = { "pll5_video", "pll2_pfd0_352m", "pll2_pfd2_396m", "mmdc_ch1_axi", "pll3_pfd1_540m", }; +static const char *ldb_di_sels[] = { "pll5_video", "pll2_pfd0_352m", "pll2_pfd2_396m", "mmdc_ch1_axi", "pll3_usb_otg", }; static const char *ipu_di_pre_sels[] = { "mmdc_ch0_axi", "pll3_usb_otg", "pll5_video", "pll2_pfd0_352m", "pll2_pfd2_396m", "pll3_pfd1_540m", }; static const char *ipu1_di0_sels[] = { "ipu1_di0_pre", "dummy", "dummy", "ldb_di0", "ldb_di1", }; static const char *ipu1_di1_sels[] = { "ipu1_di1_pre", "dummy", "dummy", "ldb_di0", "ldb_di1", }; @@ -443,7 +443,6 @@ int __init mx6q_clocks_init(void) clk_register_clkdev(clk[gpt_ipg], "ipg", "imx-gpt.0"); clk_register_clkdev(clk[gpt_ipg_per], "per", "imx-gpt.0"); - clk_register_clkdev(clk[twd], NULL, "smp_twd"); clk_register_clkdev(clk[cko1_sel], "cko1_sel", NULL); clk_register_clkdev(clk[ahb], "ahb", NULL); clk_register_clkdev(clk[cko1], "cko1", NULL); diff --git a/arch/arm/mach-kirkwood/board-iomega_ix2_200.c b/arch/arm/mach-kirkwood/board-iomega_ix2_200.c index f655b2637b0e..e5f70415905a 100644 --- a/arch/arm/mach-kirkwood/board-iomega_ix2_200.c +++ b/arch/arm/mach-kirkwood/board-iomega_ix2_200.c @@ -20,10 +20,15 @@ static struct mv643xx_eth_platform_data iomega_ix2_200_ge00_data = { .duplex = DUPLEX_FULL, }; +static struct mv643xx_eth_platform_data iomega_ix2_200_ge01_data = { + .phy_addr = MV643XX_ETH_PHY_ADDR(11), +}; + void __init iomega_ix2_200_init(void) { /* * Basic setup. Needs to be called early. */ - kirkwood_ge01_init(&iomega_ix2_200_ge00_data); + kirkwood_ge00_init(&iomega_ix2_200_ge00_data); + kirkwood_ge01_init(&iomega_ix2_200_ge01_data); } diff --git a/arch/arm/mach-mvebu/irq-armada-370-xp.c b/arch/arm/mach-mvebu/irq-armada-370-xp.c index 6a9195e10579..d5970f5a1e8d 100644 --- a/arch/arm/mach-mvebu/irq-armada-370-xp.c +++ b/arch/arm/mach-mvebu/irq-armada-370-xp.c @@ -61,7 +61,6 @@ static struct irq_domain *armada_370_xp_mpic_domain; */ static void armada_370_xp_irq_mask(struct irq_data *d) { -#ifdef CONFIG_SMP irq_hw_number_t hwirq = irqd_to_hwirq(d); if (hwirq != ARMADA_370_XP_TIMER0_PER_CPU_IRQ) @@ -70,15 +69,10 @@ static void armada_370_xp_irq_mask(struct irq_data *d) else writel(hwirq, per_cpu_int_base + ARMADA_370_XP_INT_SET_MASK_OFFS); -#else - writel(irqd_to_hwirq(d), - per_cpu_int_base + ARMADA_370_XP_INT_SET_MASK_OFFS); -#endif } static void armada_370_xp_irq_unmask(struct irq_data *d) { -#ifdef CONFIG_SMP irq_hw_number_t hwirq = irqd_to_hwirq(d); if (hwirq != ARMADA_370_XP_TIMER0_PER_CPU_IRQ) @@ -87,10 +81,6 @@ static void armada_370_xp_irq_unmask(struct irq_data *d) else writel(hwirq, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS); -#else - writel(irqd_to_hwirq(d), - per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS); -#endif } #ifdef CONFIG_SMP @@ -146,7 +136,11 @@ static int armada_370_xp_mpic_irq_map(struct irq_domain *h, unsigned int virq, irq_hw_number_t hw) { armada_370_xp_irq_mask(irq_get_irq_data(virq)); - writel(hw, main_int_base + ARMADA_370_XP_INT_SET_ENABLE_OFFS); + if (hw != ARMADA_370_XP_TIMER0_PER_CPU_IRQ) + writel(hw, per_cpu_int_base + + ARMADA_370_XP_INT_CLEAR_MASK_OFFS); + else + writel(hw, main_int_base + ARMADA_370_XP_INT_SET_ENABLE_OFFS); irq_set_status_flags(virq, IRQ_LEVEL); if (hw == ARMADA_370_XP_TIMER0_PER_CPU_IRQ) { diff --git a/arch/arm/mach-s3c24xx/include/mach/irqs.h b/arch/arm/mach-s3c24xx/include/mach/irqs.h index b7a9f4d469e8..1e73f5fa8659 100644 --- a/arch/arm/mach-s3c24xx/include/mach/irqs.h +++ b/arch/arm/mach-s3c24xx/include/mach/irqs.h @@ -188,10 +188,8 @@ #if defined(CONFIG_CPU_S3C2416) #define NR_IRQS (IRQ_S3C2416_I2S1 + 1) -#elif defined(CONFIG_CPU_S3C2443) -#define NR_IRQS (IRQ_S3C2443_AC97+1) #else -#define NR_IRQS (IRQ_S3C2440_AC97+1) +#define NR_IRQS (IRQ_S3C2443_AC97 + 1) #endif /* compatibility define. */ diff --git a/arch/arm/mach-s3c24xx/irq.c b/arch/arm/mach-s3c24xx/irq.c index cb9f5e011e73..d8ba9bee4c7e 100644 --- a/arch/arm/mach-s3c24xx/irq.c +++ b/arch/arm/mach-s3c24xx/irq.c @@ -500,7 +500,7 @@ struct s3c_irq_intc *s3c24xx_init_intc(struct device_node *np, base = (void *)0xfd000000; intc->reg_mask = base + 0xa4; - intc->reg_pending = base + 0x08; + intc->reg_pending = base + 0xa8; irq_num = 20; irq_start = S3C2410_IRQ(32); irq_offset = 4; diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 025d17328730..4045c4931a30 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -43,7 +43,7 @@ config CPU_ARM740T depends on !MMU select CPU_32v4T select CPU_ABRT_LV4T - select CPU_CACHE_V3 # although the core is v4t + select CPU_CACHE_V4 select CPU_CP15_MPU select CPU_PABRT_LEGACY help @@ -469,9 +469,6 @@ config CPU_PABRT_V7 bool # The cache model -config CPU_CACHE_V3 - bool - config CPU_CACHE_V4 bool diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile index 4e333fa2756f..9e51be96f635 100644 --- a/arch/arm/mm/Makefile +++ b/arch/arm/mm/Makefile @@ -33,7 +33,6 @@ obj-$(CONFIG_CPU_PABRT_LEGACY) += pabort-legacy.o obj-$(CONFIG_CPU_PABRT_V6) += pabort-v6.o obj-$(CONFIG_CPU_PABRT_V7) += pabort-v7.o -obj-$(CONFIG_CPU_CACHE_V3) += cache-v3.o obj-$(CONFIG_CPU_CACHE_V4) += cache-v4.o obj-$(CONFIG_CPU_CACHE_V4WT) += cache-v4wt.o obj-$(CONFIG_CPU_CACHE_V4WB) += cache-v4wb.o diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c index dd3d59122cc3..48bc3c0a87ce 100644 --- a/arch/arm/mm/cache-feroceon-l2.c +++ b/arch/arm/mm/cache-feroceon-l2.c @@ -343,6 +343,7 @@ void __init feroceon_l2_init(int __l2_wt_override) outer_cache.inv_range = feroceon_l2_inv_range; outer_cache.clean_range = feroceon_l2_clean_range; outer_cache.flush_range = feroceon_l2_flush_range; + outer_cache.inv_all = l2_inv_all; enable_l2(); diff --git a/arch/arm/mm/cache-v3.S b/arch/arm/mm/cache-v3.S deleted file mode 100644 index 8a3fadece8d3..000000000000 --- a/arch/arm/mm/cache-v3.S +++ /dev/null @@ -1,137 +0,0 @@ -/* - * linux/arch/arm/mm/cache-v3.S - * - * Copyright (C) 1997-2002 Russell king - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#include -#include -#include -#include "proc-macros.S" - -/* - * flush_icache_all() - * - * Unconditionally clean and invalidate the entire icache. - */ -ENTRY(v3_flush_icache_all) - mov pc, lr -ENDPROC(v3_flush_icache_all) - -/* - * flush_user_cache_all() - * - * Invalidate all cache entries in a particular address - * space. - * - * - mm - mm_struct describing address space - */ -ENTRY(v3_flush_user_cache_all) - /* FALLTHROUGH */ -/* - * flush_kern_cache_all() - * - * Clean and invalidate the entire cache. - */ -ENTRY(v3_flush_kern_cache_all) - /* FALLTHROUGH */ - -/* - * flush_user_cache_range(start, end, flags) - * - * Invalidate a range of cache entries in the specified - * address space. - * - * - start - start address (may not be aligned) - * - end - end address (exclusive, may not be aligned) - * - flags - vma_area_struct flags describing address space - */ -ENTRY(v3_flush_user_cache_range) - mov ip, #0 - mcreq p15, 0, ip, c7, c0, 0 @ flush ID cache - mov pc, lr - -/* - * coherent_kern_range(start, end) - * - * Ensure coherency between the Icache and the Dcache in the - * region described by start. If you have non-snooping - * Harvard caches, you need to implement this function. - * - * - start - virtual start address - * - end - virtual end address - */ -ENTRY(v3_coherent_kern_range) - /* FALLTHROUGH */ - -/* - * coherent_user_range(start, end) - * - * Ensure coherency between the Icache and the Dcache in the - * region described by start. If you have non-snooping - * Harvard caches, you need to implement this function. - * - * - start - virtual start address - * - end - virtual end address - */ -ENTRY(v3_coherent_user_range) - mov r0, #0 - mov pc, lr - -/* - * flush_kern_dcache_area(void *page, size_t size) - * - * Ensure no D cache aliasing occurs, either with itself or - * the I cache - * - * - addr - kernel address - * - size - region size - */ -ENTRY(v3_flush_kern_dcache_area) - /* FALLTHROUGH */ - -/* - * dma_flush_range(start, end) - * - * Clean and invalidate the specified virtual address range. - * - * - start - virtual start address - * - end - virtual end address - */ -ENTRY(v3_dma_flush_range) - mov r0, #0 - mcr p15, 0, r0, c7, c0, 0 @ flush ID cache - mov pc, lr - -/* - * dma_unmap_area(start, size, dir) - * - start - kernel virtual start address - * - size - size of region - * - dir - DMA direction - */ -ENTRY(v3_dma_unmap_area) - teq r2, #DMA_TO_DEVICE - bne v3_dma_flush_range - /* FALLTHROUGH */ - -/* - * dma_map_area(start, size, dir) - * - start - kernel virtual start address - * - size - size of region - * - dir - DMA direction - */ -ENTRY(v3_dma_map_area) - mov pc, lr -ENDPROC(v3_dma_unmap_area) -ENDPROC(v3_dma_map_area) - - .globl v3_flush_kern_cache_louis - .equ v3_flush_kern_cache_louis, v3_flush_kern_cache_all - - __INITDATA - - @ define struct cpu_cache_fns (see and proc-macros.S) - define_cache_functions v3 diff --git a/arch/arm/mm/cache-v4.S b/arch/arm/mm/cache-v4.S index 43e5d77be677..a7ba68f59f0c 100644 --- a/arch/arm/mm/cache-v4.S +++ b/arch/arm/mm/cache-v4.S @@ -58,7 +58,7 @@ ENTRY(v4_flush_kern_cache_all) ENTRY(v4_flush_user_cache_range) #ifdef CONFIG_CPU_CP15 mov ip, #0 - mcreq p15, 0, ip, c7, c7, 0 @ flush ID cache + mcr p15, 0, ip, c7, c7, 0 @ flush ID cache mov pc, lr #else /* FALLTHROUGH */ diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 78978945492a..a84ff763ac39 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -34,6 +34,7 @@ #include #include "mm.h" +#include "tcm.h" /* * empty_zero_page is a special page that is used for @@ -1277,6 +1278,7 @@ void __init paging_init(struct machine_desc *mdesc) dma_contiguous_remap(); devicemaps_init(mdesc); kmap_init(); + tcm_init(); top_pmd = pmd_off_k(0xffff0000); diff --git a/arch/arm/mm/proc-arm740.S b/arch/arm/mm/proc-arm740.S index dc5de5d53f20..fde2d2a794cf 100644 --- a/arch/arm/mm/proc-arm740.S +++ b/arch/arm/mm/proc-arm740.S @@ -77,24 +77,27 @@ __arm740_setup: mcr p15, 0, r0, c6, c0 @ set area 0, default ldr r0, =(CONFIG_DRAM_BASE & 0xFFFFF000) @ base[31:12] of RAM - ldr r1, =(CONFIG_DRAM_SIZE >> 12) @ size of RAM (must be >= 4KB) - mov r2, #10 @ 11 is the minimum (4KB) -1: add r2, r2, #1 @ area size *= 2 - mov r1, r1, lsr #1 + ldr r3, =(CONFIG_DRAM_SIZE >> 12) @ size of RAM (must be >= 4KB) + mov r4, #10 @ 11 is the minimum (4KB) +1: add r4, r4, #1 @ area size *= 2 + movs r3, r3, lsr #1 bne 1b @ count not zero r-shift - orr r0, r0, r2, lsl #1 @ the area register value + orr r0, r0, r4, lsl #1 @ the area register value orr r0, r0, #1 @ set enable bit mcr p15, 0, r0, c6, c1 @ set area 1, RAM ldr r0, =(CONFIG_FLASH_MEM_BASE & 0xFFFFF000) @ base[31:12] of FLASH - ldr r1, =(CONFIG_FLASH_SIZE >> 12) @ size of FLASH (must be >= 4KB) - mov r2, #10 @ 11 is the minimum (4KB) -1: add r2, r2, #1 @ area size *= 2 - mov r1, r1, lsr #1 + ldr r3, =(CONFIG_FLASH_SIZE >> 12) @ size of FLASH (must be >= 4KB) + cmp r3, #0 + moveq r0, #0 + beq 2f + mov r4, #10 @ 11 is the minimum (4KB) +1: add r4, r4, #1 @ area size *= 2 + movs r3, r3, lsr #1 bne 1b @ count not zero r-shift - orr r0, r0, r2, lsl #1 @ the area register value + orr r0, r0, r4, lsl #1 @ the area register value orr r0, r0, #1 @ set enable bit - mcr p15, 0, r0, c6, c2 @ set area 2, ROM/FLASH +2: mcr p15, 0, r0, c6, c2 @ set area 2, ROM/FLASH mov r0, #0x06 mcr p15, 0, r0, c2, c0 @ Region 1&2 cacheable @@ -137,13 +140,14 @@ __arm740_proc_info: .long 0x41807400 .long 0xfffffff0 .long 0 + .long 0 b __arm740_setup .long cpu_arch_name .long cpu_elf_name - .long HWCAP_SWP | HWCAP_HALF | HWCAP_26BIT + .long HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB | HWCAP_26BIT .long cpu_arm740_name .long arm740_processor_functions .long 0 .long 0 - .long v3_cache_fns @ cache model + .long v4_cache_fns @ cache model .size __arm740_proc_info, . - __arm740_proc_info diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S index 2c3b9421ab5e..2556cf1c2da1 100644 --- a/arch/arm/mm/proc-arm920.S +++ b/arch/arm/mm/proc-arm920.S @@ -387,7 +387,7 @@ ENTRY(cpu_arm920_set_pte_ext) /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */ .globl cpu_arm920_suspend_size .equ cpu_arm920_suspend_size, 4 * 3 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_arm920_do_suspend) stmfd sp!, {r4 - r6, lr} mrc p15, 0, r4, c13, c0, 0 @ PID diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S index f1803f7e2972..344c8a548cc0 100644 --- a/arch/arm/mm/proc-arm926.S +++ b/arch/arm/mm/proc-arm926.S @@ -402,7 +402,7 @@ ENTRY(cpu_arm926_set_pte_ext) /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */ .globl cpu_arm926_suspend_size .equ cpu_arm926_suspend_size, 4 * 3 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_arm926_do_suspend) stmfd sp!, {r4 - r6, lr} mrc p15, 0, r4, c13, c0, 0 @ PID diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S index 82f9cdc751d6..0b60dd3d742a 100644 --- a/arch/arm/mm/proc-mohawk.S +++ b/arch/arm/mm/proc-mohawk.S @@ -350,7 +350,7 @@ ENTRY(cpu_mohawk_set_pte_ext) .globl cpu_mohawk_suspend_size .equ cpu_mohawk_suspend_size, 4 * 6 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_mohawk_do_suspend) stmfd sp!, {r4 - r9, lr} mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S index 3aa0da11fd84..d92dfd081429 100644 --- a/arch/arm/mm/proc-sa1100.S +++ b/arch/arm/mm/proc-sa1100.S @@ -172,7 +172,7 @@ ENTRY(cpu_sa1100_set_pte_ext) .globl cpu_sa1100_suspend_size .equ cpu_sa1100_suspend_size, 4 * 3 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_sa1100_do_suspend) stmfd sp!, {r4 - r6, lr} mrc p15, 0, r4, c3, c0, 0 @ domain ID diff --git a/arch/arm/mm/proc-syms.c b/arch/arm/mm/proc-syms.c index 3e6210b4d6d4..054b491ff764 100644 --- a/arch/arm/mm/proc-syms.c +++ b/arch/arm/mm/proc-syms.c @@ -17,7 +17,9 @@ #ifndef MULTI_CPU EXPORT_SYMBOL(cpu_dcache_clean_area); +#ifdef CONFIG_MMU EXPORT_SYMBOL(cpu_set_pte_ext); +#endif #else EXPORT_SYMBOL(processor); #endif diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S index bcaaa8de9325..5c07ee4fe3eb 100644 --- a/arch/arm/mm/proc-v6.S +++ b/arch/arm/mm/proc-v6.S @@ -138,7 +138,7 @@ ENTRY(cpu_v6_set_pte_ext) /* Suspend/resume support: taken from arch/arm/mach-s3c64xx/sleep.S */ .globl cpu_v6_suspend_size .equ cpu_v6_suspend_size, 4 * 6 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_v6_do_suspend) stmfd sp!, {r4 - r9, lr} mrc p15, 0, r4, c13, c0, 0 @ FCSE/PID diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S index eb93d6487f35..e8efd83b6f25 100644 --- a/arch/arm/mm/proc-xsc3.S +++ b/arch/arm/mm/proc-xsc3.S @@ -413,7 +413,7 @@ ENTRY(cpu_xsc3_set_pte_ext) .globl cpu_xsc3_suspend_size .equ cpu_xsc3_suspend_size, 4 * 6 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_xsc3_do_suspend) stmfd sp!, {r4 - r9, lr} mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S index 25510361aa18..e766f889bfd6 100644 --- a/arch/arm/mm/proc-xscale.S +++ b/arch/arm/mm/proc-xscale.S @@ -528,7 +528,7 @@ ENTRY(cpu_xscale_set_pte_ext) .globl cpu_xscale_suspend_size .equ cpu_xscale_suspend_size, 4 * 6 -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_xscale_do_suspend) stmfd sp!, {r4 - r9, lr} mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode diff --git a/arch/arm/kernel/tcm.h b/arch/arm/mm/tcm.h similarity index 100% rename from arch/arm/kernel/tcm.h rename to arch/arm/mm/tcm.h diff --git a/arch/avr32/include/asm/io.h b/arch/avr32/include/asm/io.h index cf60d0a9f176..fc6483f83ccc 100644 --- a/arch/avr32/include/asm/io.h +++ b/arch/avr32/include/asm/io.h @@ -165,6 +165,10 @@ BUILDIO_IOPORT(l, u32) #define readw_be __raw_readw #define readl_be __raw_readl +#define writeb_relaxed writeb +#define writew_relaxed writew +#define writel_relaxed writel + #define writeb_be __raw_writeb #define writew_be __raw_writew #define writel_be __raw_writel diff --git a/arch/c6x/include/asm/irqflags.h b/arch/c6x/include/asm/irqflags.h index cf78e09e18c3..2c71d5634ec2 100644 --- a/arch/c6x/include/asm/irqflags.h +++ b/arch/c6x/include/asm/irqflags.h @@ -27,7 +27,7 @@ static inline unsigned long arch_local_save_flags(void) /* set interrupt enabled status */ static inline void arch_local_irq_restore(unsigned long flags) { - asm volatile (" mvc .s2 %0,CSR\n" : : "b"(flags)); + asm volatile (" mvc .s2 %0,CSR\n" : : "b"(flags) : "memory"); } /* unconditionally enable interrupts */ diff --git a/arch/ia64/kernel/palinfo.c b/arch/ia64/kernel/palinfo.c index 77597e5ea60a..79521d5499f9 100644 --- a/arch/ia64/kernel/palinfo.c +++ b/arch/ia64/kernel/palinfo.c @@ -849,17 +849,6 @@ static palinfo_entry_t palinfo_entries[]={ #define NR_PALINFO_ENTRIES (int) ARRAY_SIZE(palinfo_entries) -/* - * this array is used to keep track of the proc entries we create. This is - * required in the module mode when we need to remove all entries. The procfs code - * does not do recursion of deletion - * - * Notes: - * - +1 accounts for the cpuN directory entry in /proc/pal - */ -#define NR_PALINFO_PROC_ENTRIES (NR_CPUS*(NR_PALINFO_ENTRIES+1)) - -static struct proc_dir_entry *palinfo_proc_entries[NR_PALINFO_PROC_ENTRIES]; static struct proc_dir_entry *palinfo_dir; /* @@ -971,60 +960,32 @@ palinfo_read_entry(char *page, char **start, off_t off, int count, int *eof, voi static void __cpuinit create_palinfo_proc_entries(unsigned int cpu) { -# define CPUSTR "cpu%d" - pal_func_cpu_u_t f; - struct proc_dir_entry **pdir; struct proc_dir_entry *cpu_dir; int j; - char cpustr[sizeof(CPUSTR)]; - - - /* - * we keep track of created entries in a depth-first order for - * cleanup purposes. Each entry is stored into palinfo_proc_entries - */ - sprintf(cpustr,CPUSTR, cpu); + char cpustr[3+4+1]; /* cpu numbers are up to 4095 on itanic */ + sprintf(cpustr, "cpu%d", cpu); cpu_dir = proc_mkdir(cpustr, palinfo_dir); + if (!cpu_dir) + return; f.req_cpu = cpu; - /* - * Compute the location to store per cpu entries - * We dont store the top level entry in this list, but - * remove it finally after removing all cpu entries. - */ - pdir = &palinfo_proc_entries[cpu*(NR_PALINFO_ENTRIES+1)]; - *pdir++ = cpu_dir; for (j=0; j < NR_PALINFO_ENTRIES; j++) { f.func_id = j; - *pdir = create_proc_read_entry( - palinfo_entries[j].name, 0, cpu_dir, - palinfo_read_entry, (void *)f.value); - pdir++; + create_proc_read_entry( + palinfo_entries[j].name, 0, cpu_dir, + palinfo_read_entry, (void *)f.value); } } static void remove_palinfo_proc_entries(unsigned int hcpu) { - int j; - struct proc_dir_entry *cpu_dir, **pdir; - - pdir = &palinfo_proc_entries[hcpu*(NR_PALINFO_ENTRIES+1)]; - cpu_dir = *pdir; - *pdir++=NULL; - for (j=0; j < (NR_PALINFO_ENTRIES); j++) { - if ((*pdir)) { - remove_proc_entry ((*pdir)->name, cpu_dir); - *pdir ++= NULL; - } - } - - if (cpu_dir) { - remove_proc_entry(cpu_dir->name, palinfo_dir); - } + char cpustr[3+4+1]; /* cpu numbers are up to 4095 on itanic */ + sprintf(cpustr, "cpu%d", hcpu); + remove_proc_subtree(cpustr, palinfo_dir); } static int __cpuinit palinfo_cpu_callback(struct notifier_block *nfb, @@ -1058,6 +1019,8 @@ palinfo_init(void) printk(KERN_INFO "PAL Information Facility v%s\n", PALINFO_VERSION); palinfo_dir = proc_mkdir("pal", NULL); + if (!palinfo_dir) + return -ENOMEM; /* Create palinfo dirs in /proc for all online cpus */ for_each_online_cpu(i) { @@ -1073,22 +1036,8 @@ palinfo_init(void) static void __exit palinfo_exit(void) { - int i = 0; - - /* remove all nodes: depth first pass. Could optimize this */ - for_each_online_cpu(i) { - remove_palinfo_proc_entries(i); - } - - /* - * Remove the top level entry finally - */ - remove_proc_entry(palinfo_dir->name, NULL); - - /* - * Unregister from cpu notifier callbacks - */ unregister_hotcpu_notifier(&palinfo_cpu_notifier); + remove_proc_subtree("pal", NULL); } module_init(palinfo_init); diff --git a/arch/m68k/include/asm/gpio.h b/arch/m68k/include/asm/gpio.h index 4395ffc51fdb..8cc83431805b 100644 --- a/arch/m68k/include/asm/gpio.h +++ b/arch/m68k/include/asm/gpio.h @@ -86,4 +86,24 @@ static inline int gpio_cansleep(unsigned gpio) return gpio < MCFGPIO_PIN_MAX ? 0 : __gpio_cansleep(gpio); } +static inline int gpio_request_one(unsigned gpio, unsigned long flags, const char *label) +{ + int err; + + err = gpio_request(gpio, label); + if (err) + return err; + + if (flags & GPIOF_DIR_IN) + err = gpio_direction_input(gpio); + else + err = gpio_direction_output(gpio, + (flags & GPIOF_INIT_HIGH) ? 1 : 0); + + if (err) + gpio_free(gpio); + + return err; +} + #endif diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 256c5bf0adb7..04d69c4a5ac2 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -304,7 +304,7 @@ syscall_exit_work: subi r12,r12,TI_FLAGS 4: /* Anything else left to do? */ - SET_DEFAULT_THREAD_PPR(r3, r9) /* Set thread.ppr = 3 */ + SET_DEFAULT_THREAD_PPR(r3, r10) /* Set thread.ppr = 3 */ andi. r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP) beq .ret_from_except_lite @@ -657,7 +657,7 @@ resume_kernel: /* Clear _TIF_EMULATE_STACK_STORE flag */ lis r11,_TIF_EMULATE_STACK_STORE@h addi r5,r9,TI_FLAGS - ldarx r4,0,r5 +0: ldarx r4,0,r5 andc r4,r4,r11 stdcx. r4,0,r5 bne- 0b diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 59dd545fdde1..16e77a81ab4f 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -555,10 +555,12 @@ static inline void tm_recheckpoint_new_task(struct task_struct *new) new->thread.regs->msr |= (MSR_FP | new->thread.fpexc_mode); } +#ifdef CONFIG_ALTIVEC if (msr & MSR_VEC) { do_load_up_transact_altivec(&new->thread); new->thread.regs->msr |= MSR_VEC; } +#endif /* We may as well turn on VSX too since all the state is restored now */ if (msr & MSR_VSX) new->thread.regs->msr |= MSR_VSX; diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 3acb28e245b4..95068bf569ad 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -866,10 +866,12 @@ static long restore_tm_user_regs(struct pt_regs *regs, do_load_up_transact_fpu(¤t->thread); regs->msr |= (MSR_FP | current->thread.fpexc_mode); } +#ifdef CONFIG_ALTIVEC if (msr & MSR_VEC) { do_load_up_transact_altivec(¤t->thread); regs->msr |= MSR_VEC; } +#endif return 0; } diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 995f8543cb57..c1794286098c 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -522,10 +522,12 @@ static long restore_tm_sigcontexts(struct pt_regs *regs, do_load_up_transact_fpu(¤t->thread); regs->msr |= (MSR_FP | current->thread.fpexc_mode); } +#ifdef CONFIG_ALTIVEC if (msr & MSR_VEC) { do_load_up_transact_altivec(¤t->thread); regs->msr |= MSR_VEC; } +#endif return err; } diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index 84dbace657ce..2da67e7a16d5 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -309,6 +309,7 @@ _GLOBAL(tm_recheckpoint) or r5, r6, r5 /* Set MSR.FP+.VSX/.VEC */ mtmsr r5 +#ifdef CONFIG_ALTIVEC /* FP and VEC registers: These are recheckpointed from thread.fpr[] * and thread.vr[] respectively. The thread.transact_fpr[] version * is more modern, and will be loaded subsequently by any FPUnavailable @@ -323,6 +324,7 @@ _GLOBAL(tm_recheckpoint) REST_32VRS(0, r5, r3) /* r5 scratch, r3 THREAD ptr */ ld r5, THREAD_VRSAVE(r3) mtspr SPRN_VRSAVE, r5 +#endif dont_restore_vec: andi. r0, r4, MSR_FP diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h index 41cefd43655f..33db48a8ce24 100644 --- a/arch/powerpc/kvm/e500.h +++ b/arch/powerpc/kvm/e500.h @@ -26,17 +26,20 @@ #define E500_PID_NUM 3 #define E500_TLB_NUM 2 -#define E500_TLB_VALID 1 -#define E500_TLB_BITMAP 2 +/* entry is mapped somewhere in host TLB */ +#define E500_TLB_VALID (1 << 0) +/* TLB1 entry is mapped by host TLB1, tracked by bitmaps */ +#define E500_TLB_BITMAP (1 << 1) +/* TLB1 entry is mapped by host TLB0 */ #define E500_TLB_TLB0 (1 << 2) struct tlbe_ref { - pfn_t pfn; - unsigned int flags; /* E500_TLB_* */ + pfn_t pfn; /* valid only for TLB0, except briefly */ + unsigned int flags; /* E500_TLB_* */ }; struct tlbe_priv { - struct tlbe_ref ref; /* TLB0 only -- TLB1 uses tlb_refs */ + struct tlbe_ref ref; }; #ifdef CONFIG_KVM_E500V2 @@ -63,17 +66,6 @@ struct kvmppc_vcpu_e500 { unsigned int gtlb_nv[E500_TLB_NUM]; - /* - * information associated with each host TLB entry -- - * TLB1 only for now. If/when guest TLB1 entries can be - * mapped with host TLB0, this will be used for that too. - * - * We don't want to use this for guest TLB0 because then we'd - * have the overhead of doing the translation again even if - * the entry is still in the guest TLB (e.g. we swapped out - * and back, and our host TLB entries got evicted). - */ - struct tlbe_ref *tlb_refs[E500_TLB_NUM]; unsigned int host_tlb1_nv; u32 svr; diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index a222edfb9a9b..1c6a9d729df4 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -193,8 +193,11 @@ void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel, struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[tlbsel][esel].ref; /* Don't bother with unmapped entries */ - if (!(ref->flags & E500_TLB_VALID)) - return; + if (!(ref->flags & E500_TLB_VALID)) { + WARN(ref->flags & (E500_TLB_BITMAP | E500_TLB_TLB0), + "%s: flags %x\n", __func__, ref->flags); + WARN_ON(tlbsel == 1 && vcpu_e500->g2h_tlb1_map[esel]); + } if (tlbsel == 1 && ref->flags & E500_TLB_BITMAP) { u64 tmp = vcpu_e500->g2h_tlb1_map[esel]; @@ -248,7 +251,7 @@ static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref, pfn_t pfn) { ref->pfn = pfn; - ref->flags = E500_TLB_VALID; + ref->flags |= E500_TLB_VALID; if (tlbe_is_writable(gtlbe)) kvm_set_pfn_dirty(pfn); @@ -257,6 +260,7 @@ static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref, static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref) { if (ref->flags & E500_TLB_VALID) { + /* FIXME: don't log bogus pfn for TLB1 */ trace_kvm_booke206_ref_release(ref->pfn, ref->flags); ref->flags = 0; } @@ -274,36 +278,23 @@ static void clear_tlb1_bitmap(struct kvmppc_vcpu_e500 *vcpu_e500) static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500) { - int tlbsel = 0; + int tlbsel; int i; - for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) { - struct tlbe_ref *ref = - &vcpu_e500->gtlb_priv[tlbsel][i].ref; - kvmppc_e500_ref_release(ref); + for (tlbsel = 0; tlbsel <= 1; tlbsel++) { + for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) { + struct tlbe_ref *ref = + &vcpu_e500->gtlb_priv[tlbsel][i].ref; + kvmppc_e500_ref_release(ref); + } } } -static void clear_tlb_refs(struct kvmppc_vcpu_e500 *vcpu_e500) -{ - int stlbsel = 1; - int i; - - kvmppc_e500_tlbil_all(vcpu_e500); - - for (i = 0; i < host_tlb_params[stlbsel].entries; i++) { - struct tlbe_ref *ref = - &vcpu_e500->tlb_refs[stlbsel][i]; - kvmppc_e500_ref_release(ref); - } - - clear_tlb_privs(vcpu_e500); -} - void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); - clear_tlb_refs(vcpu_e500); + kvmppc_e500_tlbil_all(vcpu_e500); + clear_tlb_privs(vcpu_e500); clear_tlb1_bitmap(vcpu_e500); } @@ -458,8 +449,6 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1); } - /* Drop old ref and setup new one. */ - kvmppc_e500_ref_release(ref); kvmppc_e500_ref_setup(ref, gtlbe, pfn); kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize, @@ -507,14 +496,15 @@ static int kvmppc_e500_tlb1_map_tlb1(struct kvmppc_vcpu_e500 *vcpu_e500, if (unlikely(vcpu_e500->host_tlb1_nv >= tlb1_max_shadow_size())) vcpu_e500->host_tlb1_nv = 0; - vcpu_e500->tlb_refs[1][sesel] = *ref; - vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel; - vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP; if (vcpu_e500->h2g_tlb1_rmap[sesel]) { - unsigned int idx = vcpu_e500->h2g_tlb1_rmap[sesel]; + unsigned int idx = vcpu_e500->h2g_tlb1_rmap[sesel] - 1; vcpu_e500->g2h_tlb1_map[idx] &= ~(1ULL << sesel); } - vcpu_e500->h2g_tlb1_rmap[sesel] = esel; + + vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP; + vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel; + vcpu_e500->h2g_tlb1_rmap[sesel] = esel + 1; + WARN_ON(!(ref->flags & E500_TLB_VALID)); return sesel; } @@ -526,13 +516,12 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500, u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe, struct kvm_book3e_206_tlb_entry *stlbe, int esel) { - struct tlbe_ref ref; + struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[1][esel].ref; int sesel; int r; - ref.flags = 0; r = kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, stlbe, - &ref); + ref); if (r) return r; @@ -544,7 +533,7 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500, } /* Otherwise map into TLB1 */ - sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, &ref, esel); + sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, ref, esel); write_stlbe(vcpu_e500, gtlbe, stlbe, 1, sesel); return 0; @@ -565,7 +554,7 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr, case 0: priv = &vcpu_e500->gtlb_priv[tlbsel][esel]; - /* Triggers after clear_tlb_refs or on initial mapping */ + /* Triggers after clear_tlb_privs or on initial mapping */ if (!(priv->ref.flags & E500_TLB_VALID)) { kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe); } else { @@ -665,35 +654,16 @@ int e500_mmu_host_init(struct kvmppc_vcpu_e500 *vcpu_e500) host_tlb_params[0].entries / host_tlb_params[0].ways; host_tlb_params[1].sets = 1; - vcpu_e500->tlb_refs[0] = - kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[0].entries, - GFP_KERNEL); - if (!vcpu_e500->tlb_refs[0]) - goto err; - - vcpu_e500->tlb_refs[1] = - kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[1].entries, - GFP_KERNEL); - if (!vcpu_e500->tlb_refs[1]) - goto err; - vcpu_e500->h2g_tlb1_rmap = kzalloc(sizeof(unsigned int) * host_tlb_params[1].entries, GFP_KERNEL); if (!vcpu_e500->h2g_tlb1_rmap) - goto err; + return -EINVAL; return 0; - -err: - kfree(vcpu_e500->tlb_refs[0]); - kfree(vcpu_e500->tlb_refs[1]); - return -EINVAL; } void e500_mmu_host_uninit(struct kvmppc_vcpu_e500 *vcpu_e500) { kfree(vcpu_e500->h2g_tlb1_rmap); - kfree(vcpu_e500->tlb_refs[0]); - kfree(vcpu_e500->tlb_refs[1]); } diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c index 1f89d26e65fb..2f4baa074b2e 100644 --- a/arch/powerpc/kvm/e500mc.c +++ b/arch/powerpc/kvm/e500mc.c @@ -108,6 +108,8 @@ void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr) { } +static DEFINE_PER_CPU(struct kvm_vcpu *, last_vcpu_on_cpu); + void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu); @@ -136,8 +138,11 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) mtspr(SPRN_GDEAR, vcpu->arch.shared->dar); mtspr(SPRN_GESR, vcpu->arch.shared->esr); - if (vcpu->arch.oldpir != mfspr(SPRN_PIR)) + if (vcpu->arch.oldpir != mfspr(SPRN_PIR) || + __get_cpu_var(last_vcpu_on_cpu) != vcpu) { kvmppc_e500_tlbil_all(vcpu_e500); + __get_cpu_var(last_vcpu_on_cpu) = vcpu; + } kvmppc_load_guest_fp(vcpu); } diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 0da39fed355a..299731e9036b 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -186,7 +186,13 @@ static long pSeries_lpar_hpte_remove(unsigned long hpte_group) (0x1UL << 4), &dummy1, &dummy2); if (lpar_rc == H_SUCCESS) return i; - BUG_ON(lpar_rc != H_NOT_FOUND); + + /* + * The test for adjunct partition is performed before the + * ANDCOND test. H_RESOURCE may be returned, so we need to + * check for that as well. + */ + BUG_ON(lpar_rc != H_NOT_FOUND && lpar_rc != H_RESOURCE); slot_offset++; slot_offset &= 0x7; diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h index 27cb32185ce1..379d96e2105e 100644 --- a/arch/s390/include/asm/io.h +++ b/arch/s390/include/asm/io.h @@ -50,10 +50,6 @@ void unxlate_dev_mem_ptr(unsigned long phys, void *addr); #define ioremap_nocache(addr, size) ioremap(addr, size) #define ioremap_wc ioremap_nocache -/* TODO: s390 cannot support io_remap_pfn_range... */ -#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \ - remap_pfn_range(vma, vaddr, pfn, size, prot) - static inline void __iomem *ioremap(unsigned long offset, unsigned long size) { return (void __iomem *) offset; diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 4a5443118cfb..3cb47cf02530 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -57,6 +57,10 @@ extern unsigned long zero_page_mask; (((unsigned long)(vaddr)) &zero_page_mask)))) #define __HAVE_COLOR_ZERO_PAGE +/* TODO: s390 cannot support io_remap_pfn_range... */ +#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \ + remap_pfn_range(vma, vaddr, pfn, size, prot) + #endif /* !__ASSEMBLY__ */ /* diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index e26d430ce2fd..ff18e3cfb6b1 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -2,11 +2,16 @@ generic-y += clkdev.h +generic-y += cputime.h generic-y += div64.h +generic-y += emergency-restart.h generic-y += exec.h generic-y += local64.h +generic-y += mutex.h generic-y += irq_regs.h generic-y += local.h generic-y += module.h +generic-y += serial.h generic-y += trace_clock.h +generic-y += types.h generic-y += word-at-a-time.h diff --git a/arch/sparc/include/asm/cputime.h b/arch/sparc/include/asm/cputime.h deleted file mode 100644 index 1a642b81e019..000000000000 --- a/arch/sparc/include/asm/cputime.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __SPARC_CPUTIME_H -#define __SPARC_CPUTIME_H - -#include - -#endif /* __SPARC_CPUTIME_H */ diff --git a/arch/sparc/include/asm/emergency-restart.h b/arch/sparc/include/asm/emergency-restart.h deleted file mode 100644 index 108d8c48e42e..000000000000 --- a/arch/sparc/include/asm/emergency-restart.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _ASM_EMERGENCY_RESTART_H -#define _ASM_EMERGENCY_RESTART_H - -#include - -#endif /* _ASM_EMERGENCY_RESTART_H */ diff --git a/arch/sparc/include/asm/mutex.h b/arch/sparc/include/asm/mutex.h deleted file mode 100644 index 458c1f7fbc18..000000000000 --- a/arch/sparc/include/asm/mutex.h +++ /dev/null @@ -1,9 +0,0 @@ -/* - * Pull in the generic implementation for the mutex fastpath. - * - * TODO: implement optimized primitives instead, or leave the generic - * implementation in place, or pick the atomic_xchg() based generic - * implementation. (see asm-generic/mutex-xchg.h for details) - */ - -#include diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 08fcce90316b..7619f2f792af 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -915,6 +915,7 @@ static inline int io_remap_pfn_range(struct vm_area_struct *vma, return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, prot); } +#include #include /* We provide our own get_unmapped_area to cope with VA holes and diff --git a/arch/sparc/include/asm/serial.h b/arch/sparc/include/asm/serial.h deleted file mode 100644 index f90d61c28059..000000000000 --- a/arch/sparc/include/asm/serial.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __SPARC_SERIAL_H -#define __SPARC_SERIAL_H - -#define BASE_BAUD ( 1843200 / 16 ) - -#endif /* __SPARC_SERIAL_H */ diff --git a/arch/sparc/include/asm/smp_32.h b/arch/sparc/include/asm/smp_32.h index b73da3c5f10a..3c8917f054de 100644 --- a/arch/sparc/include/asm/smp_32.h +++ b/arch/sparc/include/asm/smp_32.h @@ -36,7 +36,6 @@ typedef void (*smpfunc_t)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); void cpu_panic(void); -extern void smp4m_irq_rotate(int cpu); /* * General functions that each host system must provide. @@ -46,7 +45,6 @@ void sun4m_init_smp(void); void sun4d_init_smp(void); void smp_callin(void); -void smp_boot_cpus(void); void smp_store_cpu_info(int); void smp_resched_interrupt(void); @@ -107,9 +105,6 @@ extern int hard_smp_processor_id(void); #define raw_smp_processor_id() (current_thread_info()->cpu) -#define prof_multiplier(__cpu) cpu_data(__cpu).multiplier -#define prof_counter(__cpu) cpu_data(__cpu).counter - void smp_setup_cpu_possible_map(void); #endif /* !(__ASSEMBLY__) */ diff --git a/arch/sparc/include/asm/switch_to_64.h b/arch/sparc/include/asm/switch_to_64.h index cad36f56fa03..c7de3323819c 100644 --- a/arch/sparc/include/asm/switch_to_64.h +++ b/arch/sparc/include/asm/switch_to_64.h @@ -18,8 +18,7 @@ do { \ * and 2 stores in this critical code path. -DaveM */ #define switch_to(prev, next, last) \ -do { flush_tlb_pending(); \ - save_and_clear_fpu(); \ +do { save_and_clear_fpu(); \ /* If you are tempted to conditionalize the following */ \ /* so that ASI is only written if it changes, think again. */ \ __asm__ __volatile__("wr %%g0, %0, %%asi" \ diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h index 2ef463494153..f0d6a9700f4c 100644 --- a/arch/sparc/include/asm/tlbflush_64.h +++ b/arch/sparc/include/asm/tlbflush_64.h @@ -11,24 +11,40 @@ struct tlb_batch { struct mm_struct *mm; unsigned long tlb_nr; + unsigned long active; unsigned long vaddrs[TLB_BATCH_NR]; }; extern void flush_tsb_kernel_range(unsigned long start, unsigned long end); extern void flush_tsb_user(struct tlb_batch *tb); +extern void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr); /* TLB flush operations. */ -extern void flush_tlb_pending(void); +static inline void flush_tlb_mm(struct mm_struct *mm) +{ +} -#define flush_tlb_range(vma,start,end) \ - do { (void)(start); flush_tlb_pending(); } while (0) -#define flush_tlb_page(vma,addr) flush_tlb_pending() -#define flush_tlb_mm(mm) flush_tlb_pending() +static inline void flush_tlb_page(struct vm_area_struct *vma, + unsigned long vmaddr) +{ +} + +static inline void flush_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ +} + +#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE + +extern void flush_tlb_pending(void); +extern void arch_enter_lazy_mmu_mode(void); +extern void arch_leave_lazy_mmu_mode(void); +#define arch_flush_lazy_mmu_mode() do {} while (0) /* Local cpu only. */ extern void __flush_tlb_all(void); - +extern void __flush_tlb_page(unsigned long context, unsigned long vaddr); extern void __flush_tlb_kernel_range(unsigned long start, unsigned long end); #ifndef CONFIG_SMP @@ -38,15 +54,24 @@ do { flush_tsb_kernel_range(start,end); \ __flush_tlb_kernel_range(start,end); \ } while (0) +static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr) +{ + __flush_tlb_page(CTX_HWBITS(mm->context), vaddr); +} + #else /* CONFIG_SMP */ extern void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end); +extern void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr); #define flush_tlb_kernel_range(start, end) \ do { flush_tsb_kernel_range(start,end); \ smp_flush_tlb_kernel_range(start, end); \ } while (0) +#define global_flush_tlb_page(mm, vaddr) \ + smp_flush_tlb_page(mm, vaddr) + #endif /* ! CONFIG_SMP */ #endif /* _SPARC64_TLBFLUSH_H */ diff --git a/arch/sparc/include/uapi/asm/Kbuild b/arch/sparc/include/uapi/asm/Kbuild index ce175aff71b7..b5843ee09fb5 100644 --- a/arch/sparc/include/uapi/asm/Kbuild +++ b/arch/sparc/include/uapi/asm/Kbuild @@ -44,7 +44,6 @@ header-y += swab.h header-y += termbits.h header-y += termios.h header-y += traps.h -header-y += types.h header-y += uctx.h header-y += unistd.h header-y += utrap.h diff --git a/arch/sparc/include/uapi/asm/types.h b/arch/sparc/include/uapi/asm/types.h deleted file mode 100644 index 383d156cde9c..000000000000 --- a/arch/sparc/include/uapi/asm/types.h +++ /dev/null @@ -1,17 +0,0 @@ -#ifndef _SPARC_TYPES_H -#define _SPARC_TYPES_H -/* - * This file is never included by application software unless - * explicitly requested (e.g., via linux/types.h) in which case the - * application is Linux specific so (user-) name space pollution is - * not a major issue. However, for interoperability, libraries still - * need to be careful to avoid a name clashes. - */ - -#if defined(__sparc__) - -#include - -#endif /* defined(__sparc__) */ - -#endif /* defined(_SPARC_TYPES_H) */ diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 537eb66abd06..ca64d2a86ec0 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -849,7 +849,7 @@ void smp_tsb_sync(struct mm_struct *mm) } extern unsigned long xcall_flush_tlb_mm; -extern unsigned long xcall_flush_tlb_pending; +extern unsigned long xcall_flush_tlb_page; extern unsigned long xcall_flush_tlb_kernel_range; extern unsigned long xcall_fetch_glob_regs; extern unsigned long xcall_fetch_glob_pmu; @@ -1074,19 +1074,52 @@ local_flush_and_out: put_cpu(); } +struct tlb_pending_info { + unsigned long ctx; + unsigned long nr; + unsigned long *vaddrs; +}; + +static void tlb_pending_func(void *info) +{ + struct tlb_pending_info *t = info; + + __flush_tlb_pending(t->ctx, t->nr, t->vaddrs); +} + void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long *vaddrs) { u32 ctx = CTX_HWBITS(mm->context); + struct tlb_pending_info info; + int cpu = get_cpu(); + + info.ctx = ctx; + info.nr = nr; + info.vaddrs = vaddrs; + + if (mm == current->mm && atomic_read(&mm->mm_users) == 1) + cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); + else + smp_call_function_many(mm_cpumask(mm), tlb_pending_func, + &info, 1); + + __flush_tlb_pending(ctx, nr, vaddrs); + + put_cpu(); +} + +void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr) +{ + unsigned long context = CTX_HWBITS(mm->context); int cpu = get_cpu(); if (mm == current->mm && atomic_read(&mm->mm_users) == 1) cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); else - smp_cross_call_masked(&xcall_flush_tlb_pending, - ctx, nr, (unsigned long) vaddrs, + smp_cross_call_masked(&xcall_flush_tlb_page, + context, vaddr, 0, mm_cpumask(mm)); - - __flush_tlb_pending(ctx, nr, vaddrs); + __flush_tlb_page(context, vaddr); put_cpu(); } diff --git a/arch/sparc/lib/bitext.c b/arch/sparc/lib/bitext.c index 48d00e72ce15..8ec4e9c0251a 100644 --- a/arch/sparc/lib/bitext.c +++ b/arch/sparc/lib/bitext.c @@ -119,11 +119,7 @@ void bit_map_clear(struct bit_map *t, int offset, int len) void bit_map_init(struct bit_map *t, unsigned long *map, int size) { - - if ((size & 07) != 0) - BUG(); - memset(map, 0, size>>3); - + bitmap_zero(map, size); memset(t, 0, sizeof *t); spin_lock_init(&t->lock); t->map = map; diff --git a/arch/sparc/mm/iommu.c b/arch/sparc/mm/iommu.c index 0f4f7191fbba..28f96f27c768 100644 --- a/arch/sparc/mm/iommu.c +++ b/arch/sparc/mm/iommu.c @@ -34,7 +34,7 @@ #define IOMMU_RNGE IOMMU_RNGE_256MB #define IOMMU_START 0xF0000000 #define IOMMU_WINSIZE (256*1024*1024U) -#define IOMMU_NPTES (IOMMU_WINSIZE/PAGE_SIZE) /* 64K PTEs, 265KB */ +#define IOMMU_NPTES (IOMMU_WINSIZE/PAGE_SIZE) /* 64K PTEs, 256KB */ #define IOMMU_ORDER 6 /* 4096 * (1<<6) */ /* srmmu.c */ diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c index c38bb72e3e80..036c2797dece 100644 --- a/arch/sparc/mm/srmmu.c +++ b/arch/sparc/mm/srmmu.c @@ -280,7 +280,9 @@ static void __init srmmu_nocache_init(void) SRMMU_NOCACHE_ALIGN_MAX, 0UL); memset(srmmu_nocache_pool, 0, srmmu_nocache_size); - srmmu_nocache_bitmap = __alloc_bootmem(bitmap_bits >> 3, SMP_CACHE_BYTES, 0UL); + srmmu_nocache_bitmap = + __alloc_bootmem(BITS_TO_LONGS(bitmap_bits) * sizeof(long), + SMP_CACHE_BYTES, 0UL); bit_map_init(&srmmu_nocache_map, srmmu_nocache_bitmap, bitmap_bits); srmmu_swapper_pg_dir = __srmmu_get_nocache(SRMMU_PGD_TABLE_SIZE, SRMMU_PGD_TABLE_SIZE); diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c index ba6ae7ffdc2c..272aa4f7657e 100644 --- a/arch/sparc/mm/tlb.c +++ b/arch/sparc/mm/tlb.c @@ -24,11 +24,17 @@ static DEFINE_PER_CPU(struct tlb_batch, tlb_batch); void flush_tlb_pending(void) { struct tlb_batch *tb = &get_cpu_var(tlb_batch); + struct mm_struct *mm = tb->mm; - if (tb->tlb_nr) { - flush_tsb_user(tb); + if (!tb->tlb_nr) + goto out; - if (CTX_VALID(tb->mm->context)) { + flush_tsb_user(tb); + + if (CTX_VALID(mm->context)) { + if (tb->tlb_nr == 1) { + global_flush_tlb_page(mm, tb->vaddrs[0]); + } else { #ifdef CONFIG_SMP smp_flush_tlb_pending(tb->mm, tb->tlb_nr, &tb->vaddrs[0]); @@ -37,12 +43,30 @@ void flush_tlb_pending(void) tb->tlb_nr, &tb->vaddrs[0]); #endif } - tb->tlb_nr = 0; } + tb->tlb_nr = 0; + +out: put_cpu_var(tlb_batch); } +void arch_enter_lazy_mmu_mode(void) +{ + struct tlb_batch *tb = &__get_cpu_var(tlb_batch); + + tb->active = 1; +} + +void arch_leave_lazy_mmu_mode(void) +{ + struct tlb_batch *tb = &__get_cpu_var(tlb_batch); + + if (tb->tlb_nr) + flush_tlb_pending(); + tb->active = 0; +} + static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr, bool exec) { @@ -60,6 +84,12 @@ static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr, nr = 0; } + if (!tb->active) { + global_flush_tlb_page(mm, vaddr); + flush_tsb_user_page(mm, vaddr); + return; + } + if (nr == 0) tb->mm = mm; diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index 428982b9becf..2cc3bce5ee91 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -7,11 +7,10 @@ #include #include #include -#include -#include -#include #include +#include #include +#include #include extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES]; @@ -46,23 +45,27 @@ void flush_tsb_kernel_range(unsigned long start, unsigned long end) } } +static void __flush_tsb_one_entry(unsigned long tsb, unsigned long v, + unsigned long hash_shift, + unsigned long nentries) +{ + unsigned long tag, ent, hash; + + v &= ~0x1UL; + hash = tsb_hash(v, hash_shift, nentries); + ent = tsb + (hash * sizeof(struct tsb)); + tag = (v >> 22UL); + + tsb_flush(ent, tag); +} + static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift, unsigned long tsb, unsigned long nentries) { unsigned long i; - for (i = 0; i < tb->tlb_nr; i++) { - unsigned long v = tb->vaddrs[i]; - unsigned long tag, ent, hash; - - v &= ~0x1UL; - - hash = tsb_hash(v, hash_shift, nentries); - ent = tsb + (hash * sizeof(struct tsb)); - tag = (v >> 22UL); - - tsb_flush(ent, tag); - } + for (i = 0; i < tb->tlb_nr; i++) + __flush_tsb_one_entry(tsb, tb->vaddrs[i], hash_shift, nentries); } void flush_tsb_user(struct tlb_batch *tb) @@ -90,6 +93,30 @@ void flush_tsb_user(struct tlb_batch *tb) spin_unlock_irqrestore(&mm->context.lock, flags); } +void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr) +{ + unsigned long nentries, base, flags; + + spin_lock_irqsave(&mm->context.lock, flags); + + base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb; + nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries; + if (tlb_type == cheetah_plus || tlb_type == hypervisor) + base = __pa(base); + __flush_tsb_one_entry(base, vaddr, PAGE_SHIFT, nentries); + +#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) + if (mm->context.tsb_block[MM_TSB_HUGE].tsb) { + base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb; + nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries; + if (tlb_type == cheetah_plus || tlb_type == hypervisor) + base = __pa(base); + __flush_tsb_one_entry(base, vaddr, HPAGE_SHIFT, nentries); + } +#endif + spin_unlock_irqrestore(&mm->context.lock, flags); +} + #define HV_PGSZ_IDX_BASE HV_PGSZ_IDX_8K #define HV_PGSZ_MASK_BASE HV_PGSZ_MASK_8K diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S index f8e13d421fcb..432aa0cb1b38 100644 --- a/arch/sparc/mm/ultra.S +++ b/arch/sparc/mm/ultra.S @@ -52,6 +52,33 @@ __flush_tlb_mm: /* 18 insns */ nop nop + .align 32 + .globl __flush_tlb_page +__flush_tlb_page: /* 22 insns */ + /* %o0 = context, %o1 = vaddr */ + rdpr %pstate, %g7 + andn %g7, PSTATE_IE, %g2 + wrpr %g2, %pstate + mov SECONDARY_CONTEXT, %o4 + ldxa [%o4] ASI_DMMU, %g2 + stxa %o0, [%o4] ASI_DMMU + andcc %o1, 1, %g0 + andn %o1, 1, %o3 + be,pn %icc, 1f + or %o3, 0x10, %o3 + stxa %g0, [%o3] ASI_IMMU_DEMAP +1: stxa %g0, [%o3] ASI_DMMU_DEMAP + membar #Sync + stxa %g2, [%o4] ASI_DMMU + sethi %hi(KERNBASE), %o4 + flush %o4 + retl + wrpr %g7, 0x0, %pstate + nop + nop + nop + nop + .align 32 .globl __flush_tlb_pending __flush_tlb_pending: /* 26 insns */ @@ -203,6 +230,31 @@ __cheetah_flush_tlb_mm: /* 19 insns */ retl wrpr %g7, 0x0, %pstate +__cheetah_flush_tlb_page: /* 22 insns */ + /* %o0 = context, %o1 = vaddr */ + rdpr %pstate, %g7 + andn %g7, PSTATE_IE, %g2 + wrpr %g2, 0x0, %pstate + wrpr %g0, 1, %tl + mov PRIMARY_CONTEXT, %o4 + ldxa [%o4] ASI_DMMU, %g2 + srlx %g2, CTX_PGSZ1_NUC_SHIFT, %o3 + sllx %o3, CTX_PGSZ1_NUC_SHIFT, %o3 + or %o0, %o3, %o0 /* Preserve nucleus page size fields */ + stxa %o0, [%o4] ASI_DMMU + andcc %o1, 1, %g0 + be,pn %icc, 1f + andn %o1, 1, %o3 + stxa %g0, [%o3] ASI_IMMU_DEMAP +1: stxa %g0, [%o3] ASI_DMMU_DEMAP + membar #Sync + stxa %g2, [%o4] ASI_DMMU + sethi %hi(KERNBASE), %o4 + flush %o4 + wrpr %g0, 0, %tl + retl + wrpr %g7, 0x0, %pstate + __cheetah_flush_tlb_pending: /* 27 insns */ /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */ rdpr %pstate, %g7 @@ -269,6 +321,20 @@ __hypervisor_flush_tlb_mm: /* 10 insns */ retl nop +__hypervisor_flush_tlb_page: /* 11 insns */ + /* %o0 = context, %o1 = vaddr */ + mov %o0, %g2 + mov %o1, %o0 /* ARG0: vaddr + IMMU-bit */ + mov %g2, %o1 /* ARG1: mmu context */ + mov HV_MMU_ALL, %o2 /* ARG2: flags */ + srlx %o0, PAGE_SHIFT, %o0 + sllx %o0, PAGE_SHIFT, %o0 + ta HV_MMU_UNMAP_ADDR_TRAP + brnz,pn %o0, __hypervisor_tlb_tl0_error + mov HV_MMU_UNMAP_ADDR_TRAP, %o1 + retl + nop + __hypervisor_flush_tlb_pending: /* 16 insns */ /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */ sllx %o1, 3, %g1 @@ -339,6 +405,13 @@ cheetah_patch_cachetlbops: call tlb_patch_one mov 19, %o2 + sethi %hi(__flush_tlb_page), %o0 + or %o0, %lo(__flush_tlb_page), %o0 + sethi %hi(__cheetah_flush_tlb_page), %o1 + or %o1, %lo(__cheetah_flush_tlb_page), %o1 + call tlb_patch_one + mov 22, %o2 + sethi %hi(__flush_tlb_pending), %o0 or %o0, %lo(__flush_tlb_pending), %o0 sethi %hi(__cheetah_flush_tlb_pending), %o1 @@ -397,10 +470,9 @@ xcall_flush_tlb_mm: /* 21 insns */ nop nop - .globl xcall_flush_tlb_pending -xcall_flush_tlb_pending: /* 21 insns */ - /* %g5=context, %g1=nr, %g7=vaddrs[] */ - sllx %g1, 3, %g1 + .globl xcall_flush_tlb_page +xcall_flush_tlb_page: /* 17 insns */ + /* %g5=context, %g1=vaddr */ mov PRIMARY_CONTEXT, %g4 ldxa [%g4] ASI_DMMU, %g2 srlx %g2, CTX_PGSZ1_NUC_SHIFT, %g4 @@ -408,20 +480,16 @@ xcall_flush_tlb_pending: /* 21 insns */ or %g5, %g4, %g5 mov PRIMARY_CONTEXT, %g4 stxa %g5, [%g4] ASI_DMMU -1: sub %g1, (1 << 3), %g1 - ldx [%g7 + %g1], %g5 - andcc %g5, 0x1, %g0 + andcc %g1, 0x1, %g0 be,pn %icc, 2f - - andn %g5, 0x1, %g5 + andn %g1, 0x1, %g5 stxa %g0, [%g5] ASI_IMMU_DEMAP 2: stxa %g0, [%g5] ASI_DMMU_DEMAP membar #Sync - brnz,pt %g1, 1b - nop stxa %g2, [%g4] ASI_DMMU retry nop + nop .globl xcall_flush_tlb_kernel_range xcall_flush_tlb_kernel_range: /* 25 insns */ @@ -656,15 +724,13 @@ __hypervisor_xcall_flush_tlb_mm: /* 21 insns */ membar #Sync retry - .globl __hypervisor_xcall_flush_tlb_pending -__hypervisor_xcall_flush_tlb_pending: /* 21 insns */ - /* %g5=ctx, %g1=nr, %g7=vaddrs[], %g2,%g3,%g4,g6=scratch */ - sllx %g1, 3, %g1 + .globl __hypervisor_xcall_flush_tlb_page +__hypervisor_xcall_flush_tlb_page: /* 17 insns */ + /* %g5=ctx, %g1=vaddr */ mov %o0, %g2 mov %o1, %g3 mov %o2, %g4 -1: sub %g1, (1 << 3), %g1 - ldx [%g7 + %g1], %o0 /* ARG0: virtual address */ + mov %g1, %o0 /* ARG0: virtual address */ mov %g5, %o1 /* ARG1: mmu context */ mov HV_MMU_ALL, %o2 /* ARG2: flags */ srlx %o0, PAGE_SHIFT, %o0 @@ -673,8 +739,6 @@ __hypervisor_xcall_flush_tlb_pending: /* 21 insns */ mov HV_MMU_UNMAP_ADDR_TRAP, %g6 brnz,a,pn %o0, __hypervisor_tlb_xcall_error mov %o0, %g5 - brnz,pt %g1, 1b - nop mov %g2, %o0 mov %g3, %o1 mov %g4, %o2 @@ -757,6 +821,13 @@ hypervisor_patch_cachetlbops: call tlb_patch_one mov 10, %o2 + sethi %hi(__flush_tlb_page), %o0 + or %o0, %lo(__flush_tlb_page), %o0 + sethi %hi(__hypervisor_flush_tlb_page), %o1 + or %o1, %lo(__hypervisor_flush_tlb_page), %o1 + call tlb_patch_one + mov 11, %o2 + sethi %hi(__flush_tlb_pending), %o0 or %o0, %lo(__flush_tlb_pending), %o0 sethi %hi(__hypervisor_flush_tlb_pending), %o1 @@ -788,12 +859,12 @@ hypervisor_patch_cachetlbops: call tlb_patch_one mov 21, %o2 - sethi %hi(xcall_flush_tlb_pending), %o0 - or %o0, %lo(xcall_flush_tlb_pending), %o0 - sethi %hi(__hypervisor_xcall_flush_tlb_pending), %o1 - or %o1, %lo(__hypervisor_xcall_flush_tlb_pending), %o1 + sethi %hi(xcall_flush_tlb_page), %o0 + or %o0, %lo(xcall_flush_tlb_page), %o0 + sethi %hi(__hypervisor_xcall_flush_tlb_page), %o1 + or %o1, %lo(__hypervisor_xcall_flush_tlb_page), %o1 call tlb_patch_one - mov 21, %o2 + mov 17, %o2 sethi %hi(xcall_flush_tlb_kernel_range), %o0 or %o0, %lo(xcall_flush_tlb_kernel_range), %o0 diff --git a/arch/tile/include/asm/irqflags.h b/arch/tile/include/asm/irqflags.h index 241c0bb60b12..c96f9bbb760d 100644 --- a/arch/tile/include/asm/irqflags.h +++ b/arch/tile/include/asm/irqflags.h @@ -40,7 +40,15 @@ #include #include -/* Set and clear kernel interrupt masks. */ +/* + * Set and clear kernel interrupt masks. + * + * NOTE: __insn_mtspr() is a compiler builtin marked as a memory + * clobber. We rely on it being equivalent to a compiler barrier in + * this code since arch_local_irq_save() and friends must act as + * compiler barriers. This compiler semantic is baked into enough + * places that the compiler will maintain it going forward. + */ #if CHIP_HAS_SPLIT_INTR_MASK() #if INT_PERF_COUNT < 32 || INT_AUX_PERF_COUNT < 32 || INT_MEM_ERROR >= 32 # error Fix assumptions about which word various interrupts are in diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 70c0f3da0476..15b5cef4aa38 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1549,6 +1549,7 @@ config X86_SMAP config EFI bool "EFI runtime service support" depends on ACPI + select UCS2_STRING ---help--- This enables the kernel to use EFI runtime services that are available (such as the EFI variable services). diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 8a84501acb1b..5ef205c5f37b 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -4,7 +4,7 @@ # create a compressed vmlinux image from the original vmlinux # -targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.xz vmlinux.bin.lzo head_$(BITS).o misc.o string.o cmdline.o early_serial_console.o piggy.o +targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.xz vmlinux.bin.lzo KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2 KBUILD_CFLAGS += -fno-strict-aliasing -fPIC @@ -29,7 +29,6 @@ VMLINUX_OBJS = $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \ $(obj)/piggy.o $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone -$(obj)/efi_stub_$(BITS).o: KBUILD_CLFAGS += -fshort-wchar -mno-red-zone ifeq ($(CONFIG_EFI_STUB), y) VMLINUX_OBJS += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o @@ -43,7 +42,7 @@ OBJCOPYFLAGS_vmlinux.bin := -R .comment -S $(obj)/vmlinux.bin: vmlinux FORCE $(call if_changed,objcopy) -targets += vmlinux.bin.all vmlinux.relocs +targets += $(patsubst $(obj)/%,%,$(VMLINUX_OBJS)) vmlinux.bin.all vmlinux.relocs CMD_RELOCS = arch/x86/tools/relocs quiet_cmd_relocs = RELOCS $@ diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index c205035a6b96..8615f7581820 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -251,6 +251,51 @@ static void find_bits(unsigned long mask, u8 *pos, u8 *size) *size = len; } +static efi_status_t setup_efi_vars(struct boot_params *params) +{ + struct setup_data *data; + struct efi_var_bootdata *efidata; + u64 store_size, remaining_size, var_size; + efi_status_t status; + + if (!sys_table->runtime->query_variable_info) + return EFI_UNSUPPORTED; + + data = (struct setup_data *)(unsigned long)params->hdr.setup_data; + + while (data && data->next) + data = (struct setup_data *)(unsigned long)data->next; + + status = efi_call_phys4(sys_table->runtime->query_variable_info, + EFI_VARIABLE_NON_VOLATILE | + EFI_VARIABLE_BOOTSERVICE_ACCESS | + EFI_VARIABLE_RUNTIME_ACCESS, &store_size, + &remaining_size, &var_size); + + if (status != EFI_SUCCESS) + return status; + + status = efi_call_phys3(sys_table->boottime->allocate_pool, + EFI_LOADER_DATA, sizeof(*efidata), &efidata); + + if (status != EFI_SUCCESS) + return status; + + efidata->data.type = SETUP_EFI_VARS; + efidata->data.len = sizeof(struct efi_var_bootdata) - + sizeof(struct setup_data); + efidata->data.next = 0; + efidata->store_size = store_size; + efidata->remaining_size = remaining_size; + efidata->max_var_size = var_size; + + if (data) + data->next = (unsigned long)efidata; + else + params->hdr.setup_data = (unsigned long)efidata; + +} + static efi_status_t setup_efi_pci(struct boot_params *params) { efi_pci_io_protocol *pci; @@ -1157,6 +1202,8 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table, setup_graphics(boot_params); + setup_efi_vars(boot_params); + setup_efi_pci(boot_params); status = efi_call_phys3(sys_table->boottime->allocate_pool, diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 60c89f30c727..2fb5d5884e23 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -102,6 +102,13 @@ extern void efi_call_phys_epilog(void); extern void efi_unmap_memmap(void); extern void efi_memory_uc(u64 addr, unsigned long size); +struct efi_var_bootdata { + struct setup_data data; + u64 store_size; + u64 remaining_size; + u64 max_var_size; +}; + #ifdef CONFIG_EFI static inline bool efi_is_native(void) diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 5edd1742cfd0..7361e47db79f 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -703,7 +703,10 @@ static inline void arch_leave_lazy_mmu_mode(void) PVOP_VCALL0(pv_mmu_ops.lazy_mode.leave); } -void arch_flush_lazy_mmu_mode(void); +static inline void arch_flush_lazy_mmu_mode(void) +{ + PVOP_VCALL0(pv_mmu_ops.lazy_mode.flush); +} static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx, phys_addr_t phys, pgprot_t flags) diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 142236ed83af..b3b0ec1dac86 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -91,6 +91,7 @@ struct pv_lazy_ops { /* Set deferred update mode, used for batching operations. */ void (*enter)(void); void (*leave)(void); + void (*flush)(void); }; struct pv_time_ops { @@ -679,6 +680,7 @@ void paravirt_end_context_switch(struct task_struct *next); void paravirt_enter_lazy_mmu(void); void paravirt_leave_lazy_mmu(void); +void paravirt_flush_lazy_mmu(void); void _paravirt_nop(void); u32 _paravirt_ident_32(u32); diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index 1ace47b62592..2e188d68397c 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -29,13 +29,13 @@ extern const unsigned long sys_call_table[]; */ static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs) { - return regs->orig_ax & __SYSCALL_MASK; + return regs->orig_ax; } static inline void syscall_rollback(struct task_struct *task, struct pt_regs *regs) { - regs->ax = regs->orig_ax & __SYSCALL_MASK; + regs->ax = regs->orig_ax; } static inline long syscall_get_error(struct task_struct *task, diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h index 4fef20773b8f..c7797307fc2b 100644 --- a/arch/x86/include/asm/tlb.h +++ b/arch/x86/include/asm/tlb.h @@ -7,7 +7,7 @@ #define tlb_flush(tlb) \ { \ - if (tlb->fullmm == 0) \ + if (!tlb->fullmm && !tlb->need_flush_all) \ flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end, 0UL); \ else \ flush_tlb_mm_range(tlb->mm, 0UL, TLB_FLUSH_ALL, 0UL); \ diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index c15ddaf90710..08744242b8d2 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -6,6 +6,7 @@ #define SETUP_E820_EXT 1 #define SETUP_DTB 2 #define SETUP_PCI 3 +#define SETUP_EFI_VARS 4 /* ram_size flags */ #define RAMDISK_IMAGE_START_MASK 0x07FF diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index a7d26d83fb70..8f4be53ea04b 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -35,13 +35,6 @@ static bool __init ms_hyperv_platform(void) if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) return false; - /* - * Xen emulates Hyper-V to support enlightened Windows. - * Check to see first if we are on a Xen Hypervisor. - */ - if (xen_cpuid_base()) - return false; - cpuid(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS, &eax, &hyp_signature[0], &hyp_signature[1], &hyp_signature[2]); @@ -82,12 +75,6 @@ static void __init ms_hyperv_init_platform(void) if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE) clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100); -#if IS_ENABLED(CONFIG_HYPERV) - /* - * Setup the IDT for hypervisor callback. - */ - alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector); -#endif } const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { @@ -103,6 +90,11 @@ static irq_handler_t vmbus_isr; void hv_register_vmbus_handler(int irq, irq_handler_t handler) { + /* + * Setup the IDT for hypervisor callback. + */ + alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector); + vmbus_irq = irq; vmbus_isr = handler; } diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index dab7580c47ae..cc45deb791b0 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -153,8 +153,14 @@ static struct event_constraint intel_gen_event_constraints[] __read_mostly = }; static struct extra_reg intel_snb_extra_regs[] __read_mostly = { - INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0), - INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1), + INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0), + INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1), + EVENT_EXTRA_END +}; + +static struct extra_reg intel_snbep_extra_regs[] __read_mostly = { + INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0), + INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1), EVENT_EXTRA_END }; @@ -2097,7 +2103,10 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_snb_event_constraints; x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints; x86_pmu.pebs_aliases = intel_pebs_aliases_snb; - x86_pmu.extra_regs = intel_snb_extra_regs; + if (boot_cpu_data.x86_model == 45) + x86_pmu.extra_regs = intel_snbep_extra_regs; + else + x86_pmu.extra_regs = intel_snb_extra_regs; /* all extra regs are per-cpu when HT is on */ x86_pmu.er_flags |= ERF_HAS_RSP_1; x86_pmu.er_flags |= ERF_NO_HT_SHARING; @@ -2123,7 +2132,10 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_ivb_event_constraints; x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints; x86_pmu.pebs_aliases = intel_pebs_aliases_snb; - x86_pmu.extra_regs = intel_snb_extra_regs; + if (boot_cpu_data.x86_model == 62) + x86_pmu.extra_regs = intel_snbep_extra_regs; + else + x86_pmu.extra_regs = intel_snb_extra_regs; /* all extra regs are per-cpu when HT is on */ x86_pmu.er_flags |= ERF_HAS_RSP_1; x86_pmu.er_flags |= ERF_NO_HT_SHARING; diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index b05a575d56f4..26830f3af0df 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -314,10 +314,11 @@ int intel_pmu_drain_bts_buffer(void) if (top <= at) return 0; + memset(®s, 0, sizeof(regs)); + ds->bts_index = ds->bts_buffer_base; perf_sample_data_init(&data, 0, event->hw.last_period); - regs.ip = 0; /* * Prepare a generic sample, i.e. fill in the invariant fields. diff --git a/arch/x86/kernel/microcode_core_early.c b/arch/x86/kernel/microcode_core_early.c index 577db8417d15..833d51d6ee06 100644 --- a/arch/x86/kernel/microcode_core_early.c +++ b/arch/x86/kernel/microcode_core_early.c @@ -45,9 +45,6 @@ static int __cpuinit x86_vendor(void) u32 eax = 0x00000000; u32 ebx, ecx = 0, edx; - if (!have_cpuid_p()) - return X86_VENDOR_UNKNOWN; - native_cpuid(&eax, &ebx, &ecx, &edx); if (CPUID_IS(CPUID_INTEL1, CPUID_INTEL2, CPUID_INTEL3, ebx, ecx, edx)) @@ -59,18 +56,45 @@ static int __cpuinit x86_vendor(void) return X86_VENDOR_UNKNOWN; } +static int __cpuinit x86_family(void) +{ + u32 eax = 0x00000001; + u32 ebx, ecx = 0, edx; + int x86; + + native_cpuid(&eax, &ebx, &ecx, &edx); + + x86 = (eax >> 8) & 0xf; + if (x86 == 15) + x86 += (eax >> 20) & 0xff; + + return x86; +} + void __init load_ucode_bsp(void) { - int vendor = x86_vendor(); + int vendor, x86; - if (vendor == X86_VENDOR_INTEL) + if (!have_cpuid_p()) + return; + + vendor = x86_vendor(); + x86 = x86_family(); + + if (vendor == X86_VENDOR_INTEL && x86 >= 6) load_ucode_intel_bsp(); } void __cpuinit load_ucode_ap(void) { - int vendor = x86_vendor(); + int vendor, x86; - if (vendor == X86_VENDOR_INTEL) + if (!have_cpuid_p()) + return; + + vendor = x86_vendor(); + x86 = x86_family(); + + if (vendor == X86_VENDOR_INTEL && x86 >= 6) load_ucode_intel_ap(); } diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 17fff18a1031..8bfb335f74bb 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -263,6 +263,18 @@ void paravirt_leave_lazy_mmu(void) leave_lazy(PARAVIRT_LAZY_MMU); } +void paravirt_flush_lazy_mmu(void) +{ + preempt_disable(); + + if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) { + arch_leave_lazy_mmu_mode(); + arch_enter_lazy_mmu_mode(); + } + + preempt_enable(); +} + void paravirt_start_context_switch(struct task_struct *prev) { BUG_ON(preemptible()); @@ -292,18 +304,6 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void) return this_cpu_read(paravirt_lazy_mode); } -void arch_flush_lazy_mmu_mode(void) -{ - preempt_disable(); - - if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) { - arch_leave_lazy_mmu_mode(); - arch_enter_lazy_mmu_mode(); - } - - preempt_enable(); -} - struct pv_info pv_info = { .name = "bare hardware", .paravirt_enabled = 0, @@ -475,6 +475,7 @@ struct pv_mmu_ops pv_mmu_ops = { .lazy_mode = { .enter = paravirt_nop, .leave = paravirt_nop, + .flush = paravirt_nop, }, .set_fixmap = native_set_fixmap, diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 90d8cc930f5e..fae9134a2de9 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -507,11 +507,14 @@ static void __init memblock_x86_reserve_range_setup_data(void) /* * Keep the crash kernel below this limit. On 32 bits earlier kernels * would limit the kernel to the low 512 MiB due to mapping restrictions. + * On 64bit, old kexec-tools need to under 896MiB. */ #ifdef CONFIG_X86_32 -# define CRASH_KERNEL_ADDR_MAX (512 << 20) +# define CRASH_KERNEL_ADDR_LOW_MAX (512 << 20) +# define CRASH_KERNEL_ADDR_HIGH_MAX (512 << 20) #else -# define CRASH_KERNEL_ADDR_MAX MAXMEM +# define CRASH_KERNEL_ADDR_LOW_MAX (896UL<<20) +# define CRASH_KERNEL_ADDR_HIGH_MAX MAXMEM #endif static void __init reserve_crashkernel_low(void) @@ -521,19 +524,35 @@ static void __init reserve_crashkernel_low(void) unsigned long long low_base = 0, low_size = 0; unsigned long total_low_mem; unsigned long long base; + bool auto_set = false; int ret; total_low_mem = memblock_mem_size(1UL<<(32-PAGE_SHIFT)); + /* crashkernel=Y,low */ ret = parse_crashkernel_low(boot_command_line, total_low_mem, &low_size, &base); - if (ret != 0 || low_size <= 0) - return; + if (ret != 0) { + /* + * two parts from lib/swiotlb.c: + * swiotlb size: user specified with swiotlb= or default. + * swiotlb overflow buffer: now is hardcoded to 32k. + * We round it to 8M for other buffers that + * may need to stay low too. + */ + low_size = swiotlb_size_or_default() + (8UL<<20); + auto_set = true; + } else { + /* passed with crashkernel=0,low ? */ + if (!low_size) + return; + } low_base = memblock_find_in_range(low_size, (1ULL<<32), low_size, alignment); if (!low_base) { - pr_info("crashkernel low reservation failed - No suitable area found.\n"); + if (!auto_set) + pr_info("crashkernel low reservation failed - No suitable area found.\n"); return; } @@ -554,14 +573,22 @@ static void __init reserve_crashkernel(void) const unsigned long long alignment = 16<<20; /* 16M */ unsigned long long total_mem; unsigned long long crash_size, crash_base; + bool high = false; int ret; total_mem = memblock_phys_mem_size(); + /* crashkernel=XM */ ret = parse_crashkernel(boot_command_line, total_mem, &crash_size, &crash_base); - if (ret != 0 || crash_size <= 0) - return; + if (ret != 0 || crash_size <= 0) { + /* crashkernel=X,high */ + ret = parse_crashkernel_high(boot_command_line, total_mem, + &crash_size, &crash_base); + if (ret != 0 || crash_size <= 0) + return; + high = true; + } /* 0 means: find the address automatically */ if (crash_base <= 0) { @@ -569,7 +596,9 @@ static void __init reserve_crashkernel(void) * kexec want bzImage is below CRASH_KERNEL_ADDR_MAX */ crash_base = memblock_find_in_range(alignment, - CRASH_KERNEL_ADDR_MAX, crash_size, alignment); + high ? CRASH_KERNEL_ADDR_HIGH_MAX : + CRASH_KERNEL_ADDR_LOW_MAX, + crash_size, alignment); if (!crash_base) { pr_info("crashkernel reservation failed - No suitable area found.\n"); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 02b51dd4e4ad..f77df1c5de6e 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1857,7 +1857,7 @@ int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data) if (!pv_eoi_enabled(vcpu)) return 0; return kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.pv_eoi.data, - addr); + addr, sizeof(u8)); } void kvm_lapic_init(void) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f19ac0aca60d..e1721324c271 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1823,7 +1823,8 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) return 0; } - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa)) + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa, + sizeof(u32))) return 1; vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS); @@ -1952,12 +1953,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) gpa_offset = data & ~(PAGE_MASK | 1); - /* Check that the address is 32-byte aligned. */ - if (gpa_offset & (sizeof(struct pvclock_vcpu_time_info) - 1)) - break; - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, - &vcpu->arch.pv_time, data & ~1ULL)) + &vcpu->arch.pv_time, data & ~1ULL, + sizeof(struct pvclock_vcpu_time_info))) vcpu->arch.pv_time_enabled = false; else vcpu->arch.pv_time_enabled = true; @@ -1977,7 +1975,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime, - data & KVM_STEAL_VALID_BITS)) + data & KVM_STEAL_VALID_BITS, + sizeof(struct kvm_steal_time))) return 1; vcpu->arch.st.msr_val = data; diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 1cbd89ca5569..7114c63f047d 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -1334,6 +1334,7 @@ __init void lguest_init(void) pv_mmu_ops.read_cr3 = lguest_read_cr3; pv_mmu_ops.lazy_mode.enter = paravirt_enter_lazy_mmu; pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mmu_mode; + pv_mmu_ops.lazy_mode.flush = paravirt_flush_lazy_mmu; pv_mmu_ops.pte_update = lguest_pte_update; pv_mmu_ops.pte_update_defer = lguest_pte_update; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 2b97525246d4..0e883364abb5 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -378,10 +378,12 @@ static noinline __kprobes int vmalloc_fault(unsigned long address) if (pgd_none(*pgd_ref)) return -1; - if (pgd_none(*pgd)) + if (pgd_none(*pgd)) { set_pgd(pgd, *pgd_ref); - else + arch_flush_lazy_mmu_mode(); + } else { BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref)); + } /* * Below here mismatches are bugs because these lower tables diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c index b0086567271c..0e38951e65eb 100644 --- a/arch/x86/mm/pageattr-test.c +++ b/arch/x86/mm/pageattr-test.c @@ -68,7 +68,7 @@ static int print_split(struct split_state *s) s->gpg++; i += GPS/PAGE_SIZE; } else if (level == PG_LEVEL_2M) { - if (!(pte_val(*pte) & _PAGE_PSE)) { + if ((pte_val(*pte) & _PAGE_PRESENT) && !(pte_val(*pte) & _PAGE_PSE)) { printk(KERN_ERR "%lx level %d but not PSE %Lx\n", addr, level, (u64)pte_val(*pte)); diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 091934e1d0d9..fb4e73ec24d8 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -467,7 +467,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * We are safe now. Check whether the new pgprot is the same: */ old_pte = *kpte; - old_prot = new_prot = req_prot = pte_pgprot(old_pte); + old_prot = req_prot = pte_pgprot(old_pte); pgprot_val(req_prot) &= ~pgprot_val(cpa->mask_clr); pgprot_val(req_prot) |= pgprot_val(cpa->mask_set); @@ -478,12 +478,12 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * a non present pmd. The canon_pgprot will clear _PAGE_GLOBAL * for the ancient hardware that doesn't support it. */ - if (pgprot_val(new_prot) & _PAGE_PRESENT) - pgprot_val(new_prot) |= _PAGE_PSE | _PAGE_GLOBAL; + if (pgprot_val(req_prot) & _PAGE_PRESENT) + pgprot_val(req_prot) |= _PAGE_PSE | _PAGE_GLOBAL; else - pgprot_val(new_prot) &= ~(_PAGE_PSE | _PAGE_GLOBAL); + pgprot_val(req_prot) &= ~(_PAGE_PSE | _PAGE_GLOBAL); - new_prot = canon_pgprot(new_prot); + req_prot = canon_pgprot(req_prot); /* * old_pte points to the large page base address. So we need @@ -1413,6 +1413,8 @@ void kernel_map_pages(struct page *page, int numpages, int enable) * but that can deadlock->flush only current cpu: */ __flush_tlb_all(); + + arch_flush_lazy_mmu_mode(); } #ifdef CONFIG_HIBERNATION diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 193350b51f90..17fda6a8b3c2 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -58,6 +58,13 @@ void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte) void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) { paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT); + /* + * NOTE! For PAE, any changes to the top page-directory-pointer-table + * entries need a full cr3 reload to flush. + */ +#ifdef CONFIG_X86_PAE + tlb->need_flush_all = 1; +#endif tlb_remove_page(tlb, virt_to_page(pmd)); } diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 5f2ecaf3f9d8..e4a86a677ce1 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -41,6 +41,7 @@ #include #include #include +#include #include #include @@ -51,6 +52,13 @@ #define EFI_DEBUG 1 +/* + * There's some additional metadata associated with each + * variable. Intel's reference implementation is 60 bytes - bump that + * to account for potential alignment constraints + */ +#define VAR_METADATA_SIZE 64 + struct efi __read_mostly efi = { .mps = EFI_INVALID_TABLE_ADDR, .acpi = EFI_INVALID_TABLE_ADDR, @@ -69,6 +77,13 @@ struct efi_memory_map memmap; static struct efi efi_phys __initdata; static efi_system_table_t efi_systab __initdata; +static u64 efi_var_store_size; +static u64 efi_var_remaining_size; +static u64 efi_var_max_var_size; +static u64 boot_used_size; +static u64 boot_var_size; +static u64 active_size; + unsigned long x86_efi_facility; /* @@ -98,6 +113,15 @@ static int __init setup_add_efi_memmap(char *arg) } early_param("add_efi_memmap", setup_add_efi_memmap); +static bool efi_no_storage_paranoia; + +static int __init setup_storage_paranoia(char *arg) +{ + efi_no_storage_paranoia = true; + return 0; +} +early_param("efi_no_storage_paranoia", setup_storage_paranoia); + static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc) { @@ -162,8 +186,53 @@ static efi_status_t virt_efi_get_next_variable(unsigned long *name_size, efi_char16_t *name, efi_guid_t *vendor) { - return efi_call_virt3(get_next_variable, - name_size, name, vendor); + efi_status_t status; + static bool finished = false; + static u64 var_size; + + status = efi_call_virt3(get_next_variable, + name_size, name, vendor); + + if (status == EFI_NOT_FOUND) { + finished = true; + if (var_size < boot_used_size) { + boot_var_size = boot_used_size - var_size; + active_size += boot_var_size; + } else { + printk(KERN_WARNING FW_BUG "efi: Inconsistent initial sizes\n"); + } + } + + if (boot_used_size && !finished) { + unsigned long size; + u32 attr; + efi_status_t s; + void *tmp; + + s = virt_efi_get_variable(name, vendor, &attr, &size, NULL); + + if (s != EFI_BUFFER_TOO_SMALL || !size) + return status; + + tmp = kmalloc(size, GFP_ATOMIC); + + if (!tmp) + return status; + + s = virt_efi_get_variable(name, vendor, &attr, &size, tmp); + + if (s == EFI_SUCCESS && (attr & EFI_VARIABLE_NON_VOLATILE)) { + var_size += size; + var_size += ucs2_strsize(name, 1024); + active_size += size; + active_size += VAR_METADATA_SIZE; + active_size += ucs2_strsize(name, 1024); + } + + kfree(tmp); + } + + return status; } static efi_status_t virt_efi_set_variable(efi_char16_t *name, @@ -172,9 +241,34 @@ static efi_status_t virt_efi_set_variable(efi_char16_t *name, unsigned long data_size, void *data) { - return efi_call_virt5(set_variable, - name, vendor, attr, - data_size, data); + efi_status_t status; + u32 orig_attr = 0; + unsigned long orig_size = 0; + + status = virt_efi_get_variable(name, vendor, &orig_attr, &orig_size, + NULL); + + if (status != EFI_BUFFER_TOO_SMALL) + orig_size = 0; + + status = efi_call_virt5(set_variable, + name, vendor, attr, + data_size, data); + + if (status == EFI_SUCCESS) { + if (orig_size) { + active_size -= orig_size; + active_size -= ucs2_strsize(name, 1024); + active_size -= VAR_METADATA_SIZE; + } + if (data_size) { + active_size += data_size; + active_size += ucs2_strsize(name, 1024); + active_size += VAR_METADATA_SIZE; + } + } + + return status; } static efi_status_t virt_efi_query_variable_info(u32 attr, @@ -682,6 +776,9 @@ void __init efi_init(void) char vendor[100] = "unknown"; int i = 0; void *tmp; + struct setup_data *data; + struct efi_var_bootdata *efi_var_data; + u64 pa_data; #ifdef CONFIG_X86_32 if (boot_params.efi_info.efi_systab_hi || @@ -699,6 +796,22 @@ void __init efi_init(void) if (efi_systab_init(efi_phys.systab)) return; + pa_data = boot_params.hdr.setup_data; + while (pa_data) { + data = early_ioremap(pa_data, sizeof(*efi_var_data)); + if (data->type == SETUP_EFI_VARS) { + efi_var_data = (struct efi_var_bootdata *)data; + + efi_var_store_size = efi_var_data->store_size; + efi_var_remaining_size = efi_var_data->remaining_size; + efi_var_max_var_size = efi_var_data->max_var_size; + } + pa_data = data->next; + early_iounmap(data, sizeof(*efi_var_data)); + } + + boot_used_size = efi_var_store_size - efi_var_remaining_size; + set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility); /* @@ -999,3 +1112,48 @@ u64 efi_mem_attributes(unsigned long phys_addr) } return 0; } + +/* + * Some firmware has serious problems when using more than 50% of the EFI + * variable store, i.e. it triggers bugs that can brick machines. Ensure that + * we never use more than this safe limit. + * + * Return EFI_SUCCESS if it is safe to write 'size' bytes to the variable + * store. + */ +efi_status_t efi_query_variable_store(u32 attributes, unsigned long size) +{ + efi_status_t status; + u64 storage_size, remaining_size, max_size; + + status = efi.query_variable_info(attributes, &storage_size, + &remaining_size, &max_size); + if (status != EFI_SUCCESS) + return status; + + if (!max_size && remaining_size > size) + printk_once(KERN_ERR FW_BUG "Broken EFI implementation" + " is returning MaxVariableSize=0\n"); + /* + * Some firmware implementations refuse to boot if there's insufficient + * space in the variable store. We account for that by refusing the + * write if permitting it would reduce the available space to under + * 50%. However, some firmware won't reclaim variable space until + * after the used (not merely the actively used) space drops below + * a threshold. We can approximate that case with the value calculated + * above. If both the firmware and our calculations indicate that the + * available space would drop below 50%, refuse the write. + */ + + if (!storage_size || size > remaining_size || + (max_size && size > max_size)) + return EFI_OUT_OF_RESOURCES; + + if (!efi_no_storage_paranoia && + ((active_size + size + VAR_METADATA_SIZE > storage_size / 2) && + (remaining_size - size < storage_size / 2))) + return EFI_OUT_OF_RESOURCES; + + return EFI_SUCCESS; +} +EXPORT_SYMBOL_GPL(efi_query_variable_store); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 6afbb2ca9a0a..e006c18d288a 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1748,14 +1748,18 @@ static void *m2v(phys_addr_t maddr) } /* Set the page permissions on an identity-mapped pages */ -static void set_page_prot(void *addr, pgprot_t prot) +static void set_page_prot_flags(void *addr, pgprot_t prot, unsigned long flags) { unsigned long pfn = __pa(addr) >> PAGE_SHIFT; pte_t pte = pfn_pte(pfn, prot); - if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, 0)) + if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, flags)) BUG(); } +static void set_page_prot(void *addr, pgprot_t prot) +{ + return set_page_prot_flags(addr, prot, UVMF_NONE); +} #ifdef CONFIG_X86_32 static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn) { @@ -1839,12 +1843,12 @@ static void __init check_pt_base(unsigned long *pt_base, unsigned long *pt_end, unsigned long addr) { if (*pt_base == PFN_DOWN(__pa(addr))) { - set_page_prot((void *)addr, PAGE_KERNEL); + set_page_prot_flags((void *)addr, PAGE_KERNEL, UVMF_INVLPG); clear_page((void *)addr); (*pt_base)++; } if (*pt_end == PFN_DOWN(__pa(addr))) { - set_page_prot((void *)addr, PAGE_KERNEL); + set_page_prot_flags((void *)addr, PAGE_KERNEL, UVMF_INVLPG); clear_page((void *)addr); (*pt_end)--; } @@ -2196,6 +2200,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { .lazy_mode = { .enter = paravirt_enter_lazy_mmu, .leave = xen_leave_lazy_mmu, + .flush = paravirt_flush_lazy_mmu, }, .set_fixmap = xen_set_fixmap, diff --git a/block/blk-core.c b/block/blk-core.c index 074b758efc42..7c288358a745 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -39,6 +39,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap); EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap); +EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete); EXPORT_TRACEPOINT_SYMBOL_GPL(block_unplug); DEFINE_IDA(blk_queue_ida); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 6206a934eb8c..5efc5a647183 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -229,6 +229,8 @@ queue_store_##name(struct request_queue *q, const char *page, size_t count) \ unsigned long val; \ ssize_t ret; \ ret = queue_var_store(&val, page, count); \ + if (ret < 0) \ + return ret; \ if (neg) \ val = !val; \ \ diff --git a/block/partition-generic.c b/block/partition-generic.c index ae95ee6a58aa..789cdea05893 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -257,7 +257,6 @@ void delete_partition(struct gendisk *disk, int partno) hd_struct_put(part); } -EXPORT_SYMBOL(delete_partition); static ssize_t whole_disk_show(struct device *dev, struct device_attribute *attr, char *buf) diff --git a/crypto/gcm.c b/crypto/gcm.c index 137ad1ec5438..13ccbda34ff9 100644 --- a/crypto/gcm.c +++ b/crypto/gcm.c @@ -44,6 +44,7 @@ struct crypto_rfc4543_ctx { struct crypto_rfc4543_req_ctx { u8 auth_tag[16]; + u8 assocbuf[32]; struct scatterlist cipher[1]; struct scatterlist payload[2]; struct scatterlist assoc[2]; @@ -1133,9 +1134,19 @@ static struct aead_request *crypto_rfc4543_crypt(struct aead_request *req, scatterwalk_crypto_chain(payload, dst, vdst == req->iv + 8, 2); assoclen += 8 + req->cryptlen - (enc ? 0 : authsize); - sg_init_table(assoc, 2); - sg_set_page(assoc, sg_page(req->assoc), req->assoc->length, - req->assoc->offset); + if (req->assoc->length == req->assoclen) { + sg_init_table(assoc, 2); + sg_set_page(assoc, sg_page(req->assoc), req->assoc->length, + req->assoc->offset); + } else { + BUG_ON(req->assoclen > sizeof(rctx->assocbuf)); + + scatterwalk_map_and_copy(rctx->assocbuf, req->assoc, 0, + req->assoclen, 0); + + sg_init_table(assoc, 2); + sg_set_buf(assoc, rctx->assocbuf, req->assoclen); + } scatterwalk_crypto_chain(assoc, payload, 0, 2); aead_request_set_tfm(subreq, ctx->child); diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c index 5ff173066127..6ae5e440436e 100644 --- a/drivers/acpi/pci_root.c +++ b/drivers/acpi/pci_root.c @@ -415,7 +415,6 @@ static int acpi_pci_root_add(struct acpi_device *device, struct acpi_pci_root *root; struct acpi_pci_driver *driver; u32 flags, base_flags; - bool is_osc_granted = false; root = kzalloc(sizeof(struct acpi_pci_root), GFP_KERNEL); if (!root) @@ -476,6 +475,30 @@ static int acpi_pci_root_add(struct acpi_device *device, flags = base_flags = OSC_PCI_SEGMENT_GROUPS_SUPPORT; acpi_pci_osc_support(root, flags); + /* + * TBD: Need PCI interface for enumeration/configuration of roots. + */ + + mutex_lock(&acpi_pci_root_lock); + list_add_tail(&root->node, &acpi_pci_roots); + mutex_unlock(&acpi_pci_root_lock); + + /* + * Scan the Root Bridge + * -------------------- + * Must do this prior to any attempt to bind the root device, as the + * PCI namespace does not get created until this call is made (and + * thus the root bridge's pci_dev does not exist). + */ + root->bus = pci_acpi_scan_root(root); + if (!root->bus) { + printk(KERN_ERR PREFIX + "Bus %04x:%02x not present in PCI namespace\n", + root->segment, (unsigned int)root->secondary.start); + result = -ENODEV; + goto out_del_root; + } + /* Indicate support for various _OSC capabilities. */ if (pci_ext_cfg_avail()) flags |= OSC_EXT_PCI_CONFIG_SUPPORT; @@ -494,6 +517,7 @@ static int acpi_pci_root_add(struct acpi_device *device, flags = base_flags; } } + if (!pcie_ports_disabled && (flags & ACPI_PCIE_REQ_SUPPORT) == ACPI_PCIE_REQ_SUPPORT) { flags = OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL @@ -514,54 +538,28 @@ static int acpi_pci_root_add(struct acpi_device *device, status = acpi_pci_osc_control_set(device->handle, &flags, OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL); if (ACPI_SUCCESS(status)) { - is_osc_granted = true; dev_info(&device->dev, "ACPI _OSC control (0x%02x) granted\n", flags); + if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_ASPM) { + /* + * We have ASPM control, but the FADT indicates + * that it's unsupported. Clear it. + */ + pcie_clear_aspm(root->bus); + } } else { - is_osc_granted = false; dev_info(&device->dev, "ACPI _OSC request failed (%s), " "returned control mask: 0x%02x\n", acpi_format_exception(status), flags); + pr_info("ACPI _OSC control for PCIe not granted, " + "disabling ASPM\n"); + pcie_no_aspm(); } } else { dev_info(&device->dev, - "Unable to request _OSC control " - "(_OSC support mask: 0x%02x)\n", flags); - } - - /* - * TBD: Need PCI interface for enumeration/configuration of roots. - */ - - mutex_lock(&acpi_pci_root_lock); - list_add_tail(&root->node, &acpi_pci_roots); - mutex_unlock(&acpi_pci_root_lock); - - /* - * Scan the Root Bridge - * -------------------- - * Must do this prior to any attempt to bind the root device, as the - * PCI namespace does not get created until this call is made (and - * thus the root bridge's pci_dev does not exist). - */ - root->bus = pci_acpi_scan_root(root); - if (!root->bus) { - printk(KERN_ERR PREFIX - "Bus %04x:%02x not present in PCI namespace\n", - root->segment, (unsigned int)root->secondary.start); - result = -ENODEV; - goto out_del_root; - } - - /* ASPM setting */ - if (is_osc_granted) { - if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_ASPM) - pcie_clear_aspm(root->bus); - } else { - pr_info("ACPI _OSC control for PCIe not granted, " - "disabling ASPM\n"); - pcie_no_aspm(); + "Unable to request _OSC control " + "(_OSC support mask: 0x%02x)\n", flags); } pci_acpi_add_bus_pm_notifier(device, root->bus); diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c index ffdd32d22602..2f48123d74c4 100644 --- a/drivers/ata/ata_piix.c +++ b/drivers/ata/ata_piix.c @@ -150,6 +150,7 @@ enum piix_controller_ids { tolapai_sata, piix_pata_vmw, /* PIIX4 for VMware, spurious DMA_ERR */ ich8_sata_snb, + ich8_2port_sata_snb, }; struct piix_map_db { @@ -304,7 +305,7 @@ static const struct pci_device_id piix_pci_tbl[] = { /* SATA Controller IDE (Lynx Point) */ { 0x8086, 0x8c01, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_snb }, /* SATA Controller IDE (Lynx Point) */ - { 0x8086, 0x8c08, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata }, + { 0x8086, 0x8c08, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata_snb }, /* SATA Controller IDE (Lynx Point) */ { 0x8086, 0x8c09, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata }, /* SATA Controller IDE (Lynx Point-LP) */ @@ -439,6 +440,7 @@ static const struct piix_map_db *piix_map_db_table[] = { [ich8m_apple_sata] = &ich8m_apple_map_db, [tolapai_sata] = &tolapai_map_db, [ich8_sata_snb] = &ich8_map_db, + [ich8_2port_sata_snb] = &ich8_2port_map_db, }; static struct pci_bits piix_enable_bits[] = { @@ -1242,6 +1244,16 @@ static struct ata_port_info piix_port_info[] = { .udma_mask = ATA_UDMA6, .port_ops = &piix_sata_ops, }, + + [ich8_2port_sata_snb] = + { + .flags = PIIX_SATA_FLAGS | PIIX_FLAG_SIDPR + | PIIX_FLAG_PIO16, + .pio_mask = ATA_PIO4, + .mwdma_mask = ATA_MWDMA2, + .udma_mask = ATA_UDMA6, + .port_ops = &piix_sata_ops, + }, }; #define AHCI_PCI_BAR 5 diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 497adea1f0d6..63c743baf920 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2329,7 +2329,7 @@ int ata_dev_configure(struct ata_device *dev) * from SATA Settings page of Identify Device Data Log. */ if (ata_id_has_devslp(dev->id)) { - u8 sata_setting[ATA_SECT_SIZE]; + u8 *sata_setting = ap->sector_buf; int i, j; dev->flags |= ATA_DFLAG_DEVSLP; @@ -2439,6 +2439,9 @@ int ata_dev_configure(struct ata_device *dev) dev->max_sectors = min_t(unsigned int, ATA_MAX_SECTORS_128, dev->max_sectors); + if (dev->horkage & ATA_HORKAGE_MAX_SEC_LBA48) + dev->max_sectors = ATA_MAX_SECTORS_LBA48; + if (ap->ops->dev_config) ap->ops->dev_config(dev); @@ -4100,6 +4103,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { /* Weird ATAPI devices */ { "TORiSAN DVD-ROM DRD-N216", NULL, ATA_HORKAGE_MAX_SEC_128 }, { "QUANTUM DAT DAT72-000", NULL, ATA_HORKAGE_ATAPI_MOD16_DMA }, + { "Slimtype DVD A DS8A8SH", NULL, ATA_HORKAGE_MAX_SEC_LBA48 }, /* Devices we expect to fail diagnostics */ diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 318b41358187..ff44787e5a45 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -532,8 +532,8 @@ int ata_cmd_ioctl(struct scsi_device *scsidev, void __user *arg) struct scsi_sense_hdr sshdr; scsi_normalize_sense(sensebuf, SCSI_SENSE_BUFFERSIZE, &sshdr); - if (sshdr.sense_key == 0 && - sshdr.asc == 0 && sshdr.ascq == 0) + if (sshdr.sense_key == RECOVERED_ERROR && + sshdr.asc == 0 && sshdr.ascq == 0x1d) cmd_result &= ~SAM_STAT_CHECK_CONDITION; } @@ -618,8 +618,8 @@ int ata_task_ioctl(struct scsi_device *scsidev, void __user *arg) struct scsi_sense_hdr sshdr; scsi_normalize_sense(sensebuf, SCSI_SENSE_BUFFERSIZE, &sshdr); - if (sshdr.sense_key == 0 && - sshdr.asc == 0 && sshdr.ascq == 0) + if (sshdr.sense_key == RECOVERED_ERROR && + sshdr.asc == 0 && sshdr.ascq == 0x1d) cmd_result &= ~SAM_STAT_CHECK_CONDITION; } diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index d34adef1e63e..58cfb3232428 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -943,7 +943,8 @@ static int _regmap_raw_write(struct regmap *map, unsigned int reg, unsigned int ival; int val_bytes = map->format.val_bytes; for (i = 0; i < val_len / val_bytes; i++) { - ival = map->format.parse_val(val + (i * val_bytes)); + memcpy(map->work_buf, val + (i * val_bytes), val_bytes); + ival = map->format.parse_val(map->work_buf); ret = regcache_write(map, reg + (i * map->reg_stride), ival); if (ret) { diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 2c127f9c3f3b..dfe758382eaf 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1051,29 +1051,12 @@ static int loop_clr_fd(struct loop_device *lo) lo->lo_state = Lo_unbound; /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); + if (lo->lo_flags & LO_FLAGS_PARTSCAN && bdev) + ioctl_by_bdev(bdev, BLKRRPART, 0); lo->lo_flags = 0; if (!part_shift) lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN; mutex_unlock(&lo->lo_ctl_mutex); - - /* - * Remove all partitions, since BLKRRPART won't remove user - * added partitions when max_part=0 - */ - if (bdev) { - struct disk_part_iter piter; - struct hd_struct *part; - - mutex_lock_nested(&bdev->bd_mutex, 1); - invalidate_partition(bdev->bd_disk, 0); - disk_part_iter_init(&piter, bdev->bd_disk, - DISK_PITER_INCL_EMPTY); - while ((part = disk_part_iter_next(&piter))) - delete_partition(bdev->bd_disk, part->partno); - disk_part_iter_exit(&piter); - mutex_unlock(&bdev->bd_mutex); - } - /* * Need not hold lo_ctl_mutex to fput backing file. * Calling fput holding lo_ctl_mutex triggers a circular diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 92250af84e7d..32c678028e53 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -81,12 +81,17 @@ /* Device instance number, incremented each time a device is probed. */ static int instance; +struct list_head online_list; +struct list_head removing_list; +spinlock_t dev_lock; + /* * Global variable used to hold the major block device number * allocated in mtip_init(). */ static int mtip_major; static struct dentry *dfs_parent; +static struct dentry *dfs_device_status; static u32 cpu_use[NR_CPUS]; @@ -243,40 +248,31 @@ static inline void release_slot(struct mtip_port *port, int tag) /* * Reset the HBA (without sleeping) * - * Just like hba_reset, except does not call sleep, so can be - * run from interrupt/tasklet context. - * * @dd Pointer to the driver data structure. * * return value * 0 The reset was successful. * -1 The HBA Reset bit did not clear. */ -static int hba_reset_nosleep(struct driver_data *dd) +static int mtip_hba_reset(struct driver_data *dd) { unsigned long timeout; - /* Chip quirk: quiesce any chip function */ - mdelay(10); - /* Set the reset bit */ writel(HOST_RESET, dd->mmio + HOST_CTL); /* Flush */ readl(dd->mmio + HOST_CTL); - /* - * Wait 10ms then spin for up to 1 second - * waiting for reset acknowledgement - */ - timeout = jiffies + msecs_to_jiffies(1000); - mdelay(10); - while ((readl(dd->mmio + HOST_CTL) & HOST_RESET) - && time_before(jiffies, timeout)) - mdelay(1); + /* Spin for up to 2 seconds, waiting for reset acknowledgement */ + timeout = jiffies + msecs_to_jiffies(2000); + do { + mdelay(10); + if (test_bit(MTIP_DDF_REMOVE_PENDING_BIT, &dd->dd_flag)) + return -1; - if (test_bit(MTIP_DDF_REMOVE_PENDING_BIT, &dd->dd_flag)) - return -1; + } while ((readl(dd->mmio + HOST_CTL) & HOST_RESET) + && time_before(jiffies, timeout)); if (readl(dd->mmio + HOST_CTL) & HOST_RESET) return -1; @@ -481,7 +477,7 @@ static void mtip_restart_port(struct mtip_port *port) dev_warn(&port->dd->pdev->dev, "PxCMD.CR not clear, escalating reset\n"); - if (hba_reset_nosleep(port->dd)) + if (mtip_hba_reset(port->dd)) dev_err(&port->dd->pdev->dev, "HBA reset escalation failed.\n"); @@ -527,6 +523,26 @@ static void mtip_restart_port(struct mtip_port *port) } +static int mtip_device_reset(struct driver_data *dd) +{ + int rv = 0; + + if (mtip_check_surprise_removal(dd->pdev)) + return 0; + + if (mtip_hba_reset(dd) < 0) + rv = -EFAULT; + + mdelay(1); + mtip_init_port(dd->port); + mtip_start_port(dd->port); + + /* Enable interrupts on the HBA. */ + writel(readl(dd->mmio + HOST_CTL) | HOST_IRQ_EN, + dd->mmio + HOST_CTL); + return rv; +} + /* * Helper function for tag logging */ @@ -632,7 +648,7 @@ static void mtip_timeout_function(unsigned long int data) if (cmdto_cnt) { print_tags(port->dd, "timed out", tagaccum, cmdto_cnt); if (!test_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags)) { - mtip_restart_port(port); + mtip_device_reset(port->dd); wake_up_interruptible(&port->svc_wait); } clear_bit(MTIP_PF_EH_ACTIVE_BIT, &port->flags); @@ -1283,11 +1299,11 @@ static int mtip_exec_internal_command(struct mtip_port *port, int rv = 0, ready2go = 1; struct mtip_cmd *int_cmd = &port->commands[MTIP_TAG_INTERNAL]; unsigned long to; + struct driver_data *dd = port->dd; /* Make sure the buffer is 8 byte aligned. This is asic specific. */ if (buffer & 0x00000007) { - dev_err(&port->dd->pdev->dev, - "SG buffer is not 8 byte aligned\n"); + dev_err(&dd->pdev->dev, "SG buffer is not 8 byte aligned\n"); return -EFAULT; } @@ -1300,23 +1316,21 @@ static int mtip_exec_internal_command(struct mtip_port *port, mdelay(100); } while (time_before(jiffies, to)); if (!ready2go) { - dev_warn(&port->dd->pdev->dev, + dev_warn(&dd->pdev->dev, "Internal cmd active. new cmd [%02X]\n", fis->command); return -EBUSY; } set_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags); port->ic_pause_timer = 0; - if (fis->command == ATA_CMD_SEC_ERASE_UNIT) - clear_bit(MTIP_PF_SE_ACTIVE_BIT, &port->flags); - else if (fis->command == ATA_CMD_DOWNLOAD_MICRO) - clear_bit(MTIP_PF_DM_ACTIVE_BIT, &port->flags); + clear_bit(MTIP_PF_SE_ACTIVE_BIT, &port->flags); + clear_bit(MTIP_PF_DM_ACTIVE_BIT, &port->flags); if (atomic == GFP_KERNEL) { if (fis->command != ATA_CMD_STANDBYNOW1) { /* wait for io to complete if non atomic */ if (mtip_quiesce_io(port, 5000) < 0) { - dev_warn(&port->dd->pdev->dev, + dev_warn(&dd->pdev->dev, "Failed to quiesce IO\n"); release_slot(port, MTIP_TAG_INTERNAL); clear_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags); @@ -1361,58 +1375,84 @@ static int mtip_exec_internal_command(struct mtip_port *port, /* Issue the command to the hardware */ mtip_issue_non_ncq_command(port, MTIP_TAG_INTERNAL); - /* Poll if atomic, wait_for_completion otherwise */ if (atomic == GFP_KERNEL) { /* Wait for the command to complete or timeout. */ - if (wait_for_completion_timeout( + if (wait_for_completion_interruptible_timeout( &wait, - msecs_to_jiffies(timeout)) == 0) { - dev_err(&port->dd->pdev->dev, - "Internal command did not complete [%d] " - "within timeout of %lu ms\n", - atomic, timeout); - if (mtip_check_surprise_removal(port->dd->pdev) || + msecs_to_jiffies(timeout)) <= 0) { + if (rv == -ERESTARTSYS) { /* interrupted */ + dev_err(&dd->pdev->dev, + "Internal command [%02X] was interrupted after %lu ms\n", + fis->command, timeout); + rv = -EINTR; + goto exec_ic_exit; + } else if (rv == 0) /* timeout */ + dev_err(&dd->pdev->dev, + "Internal command did not complete [%02X] within timeout of %lu ms\n", + fis->command, timeout); + else + dev_err(&dd->pdev->dev, + "Internal command [%02X] wait returned code [%d] after %lu ms - unhandled\n", + fis->command, rv, timeout); + + if (mtip_check_surprise_removal(dd->pdev) || test_bit(MTIP_DDF_REMOVE_PENDING_BIT, - &port->dd->dd_flag)) { + &dd->dd_flag)) { + dev_err(&dd->pdev->dev, + "Internal command [%02X] wait returned due to SR\n", + fis->command); rv = -ENXIO; goto exec_ic_exit; } + mtip_device_reset(dd); /* recover from timeout issue */ rv = -EAGAIN; + goto exec_ic_exit; } } else { + u32 hba_stat, port_stat; + /* Spin for checking if command still outstanding */ timeout = jiffies + msecs_to_jiffies(timeout); while ((readl(port->cmd_issue[MTIP_TAG_INTERNAL]) & (1 << MTIP_TAG_INTERNAL)) && time_before(jiffies, timeout)) { - if (mtip_check_surprise_removal(port->dd->pdev)) { + if (mtip_check_surprise_removal(dd->pdev)) { rv = -ENXIO; goto exec_ic_exit; } if ((fis->command != ATA_CMD_STANDBYNOW1) && test_bit(MTIP_DDF_REMOVE_PENDING_BIT, - &port->dd->dd_flag)) { + &dd->dd_flag)) { rv = -ENXIO; goto exec_ic_exit; } - if (readl(port->mmio + PORT_IRQ_STAT) & PORT_IRQ_ERR) { - atomic_inc(&int_cmd->active); /* error */ - break; + port_stat = readl(port->mmio + PORT_IRQ_STAT); + if (!port_stat) + continue; + + if (port_stat & PORT_IRQ_ERR) { + dev_err(&dd->pdev->dev, + "Internal command [%02X] failed\n", + fis->command); + mtip_device_reset(dd); + rv = -EIO; + goto exec_ic_exit; + } else { + writel(port_stat, port->mmio + PORT_IRQ_STAT); + hba_stat = readl(dd->mmio + HOST_IRQ_STAT); + if (hba_stat) + writel(hba_stat, + dd->mmio + HOST_IRQ_STAT); } + break; } } - if (atomic_read(&int_cmd->active) > 1) { - dev_err(&port->dd->pdev->dev, - "Internal command [%02X] failed\n", fis->command); - rv = -EIO; - } if (readl(port->cmd_issue[MTIP_TAG_INTERNAL]) & (1 << MTIP_TAG_INTERNAL)) { rv = -ENXIO; - if (!test_bit(MTIP_DDF_REMOVE_PENDING_BIT, - &port->dd->dd_flag)) { - mtip_restart_port(port); + if (!test_bit(MTIP_DDF_REMOVE_PENDING_BIT, &dd->dd_flag)) { + mtip_device_reset(dd); rv = -EAGAIN; } } @@ -1724,7 +1764,8 @@ static int mtip_get_smart_attr(struct mtip_port *port, unsigned int id, * -EINVAL Invalid parameters passed in, trim not supported * -EIO Error submitting trim request to hw */ -static int mtip_send_trim(struct driver_data *dd, unsigned int lba, unsigned int len) +static int mtip_send_trim(struct driver_data *dd, unsigned int lba, + unsigned int len) { int i, rv = 0; u64 tlba, tlen, sect_left; @@ -1810,45 +1851,6 @@ static bool mtip_hw_get_capacity(struct driver_data *dd, sector_t *sectors) return (bool) !!port->identify_valid; } -/* - * Reset the HBA. - * - * Resets the HBA by setting the HBA Reset bit in the Global - * HBA Control register. After setting the HBA Reset bit the - * function waits for 1 second before reading the HBA Reset - * bit to make sure it has cleared. If HBA Reset is not clear - * an error is returned. Cannot be used in non-blockable - * context. - * - * @dd Pointer to the driver data structure. - * - * return value - * 0 The reset was successful. - * -1 The HBA Reset bit did not clear. - */ -static int mtip_hba_reset(struct driver_data *dd) -{ - mtip_deinit_port(dd->port); - - /* Set the reset bit */ - writel(HOST_RESET, dd->mmio + HOST_CTL); - - /* Flush */ - readl(dd->mmio + HOST_CTL); - - /* Wait for reset to clear */ - ssleep(1); - - /* Check the bit has cleared */ - if (readl(dd->mmio + HOST_CTL) & HOST_RESET) { - dev_err(&dd->pdev->dev, - "Reset bit did not clear.\n"); - return -1; - } - - return 0; -} - /* * Display the identify command data. * @@ -2710,6 +2712,100 @@ static ssize_t mtip_hw_show_status(struct device *dev, static DEVICE_ATTR(status, S_IRUGO, mtip_hw_show_status, NULL); +/* debugsfs entries */ + +static ssize_t show_device_status(struct device_driver *drv, char *buf) +{ + int size = 0; + struct driver_data *dd, *tmp; + unsigned long flags; + char id_buf[42]; + u16 status = 0; + + spin_lock_irqsave(&dev_lock, flags); + size += sprintf(&buf[size], "Devices Present:\n"); + list_for_each_entry_safe(dd, tmp, &online_list, online_list) { + if (dd->pdev) { + if (dd->port && + dd->port->identify && + dd->port->identify_valid) { + strlcpy(id_buf, + (char *) (dd->port->identify + 10), 21); + status = *(dd->port->identify + 141); + } else { + memset(id_buf, 0, 42); + status = 0; + } + + if (dd->port && + test_bit(MTIP_PF_REBUILD_BIT, &dd->port->flags)) { + size += sprintf(&buf[size], + " device %s %s (ftl rebuild %d %%)\n", + dev_name(&dd->pdev->dev), + id_buf, + status); + } else { + size += sprintf(&buf[size], + " device %s %s\n", + dev_name(&dd->pdev->dev), + id_buf); + } + } + } + + size += sprintf(&buf[size], "Devices Being Removed:\n"); + list_for_each_entry_safe(dd, tmp, &removing_list, remove_list) { + if (dd->pdev) { + if (dd->port && + dd->port->identify && + dd->port->identify_valid) { + strlcpy(id_buf, + (char *) (dd->port->identify+10), 21); + status = *(dd->port->identify + 141); + } else { + memset(id_buf, 0, 42); + status = 0; + } + + if (dd->port && + test_bit(MTIP_PF_REBUILD_BIT, &dd->port->flags)) { + size += sprintf(&buf[size], + " device %s %s (ftl rebuild %d %%)\n", + dev_name(&dd->pdev->dev), + id_buf, + status); + } else { + size += sprintf(&buf[size], + " device %s %s\n", + dev_name(&dd->pdev->dev), + id_buf); + } + } + } + spin_unlock_irqrestore(&dev_lock, flags); + + return size; +} + +static ssize_t mtip_hw_read_device_status(struct file *f, char __user *ubuf, + size_t len, loff_t *offset) +{ + int size = *offset; + char buf[MTIP_DFS_MAX_BUF_SIZE]; + + if (!len || *offset) + return 0; + + size += show_device_status(NULL, buf); + + *offset = size <= len ? size : len; + size = copy_to_user(ubuf, buf, *offset); + if (size) + return -EFAULT; + + return *offset; +} + static ssize_t mtip_hw_read_registers(struct file *f, char __user *ubuf, size_t len, loff_t *offset) { @@ -2804,6 +2900,13 @@ static ssize_t mtip_hw_read_flags(struct file *f, char __user *ubuf, return *offset; } +static const struct file_operations mtip_device_status_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = mtip_hw_read_device_status, + .llseek = no_llseek, +}; + static const struct file_operations mtip_regs_fops = { .owner = THIS_MODULE, .open = simple_open, @@ -4161,6 +4264,7 @@ static int mtip_pci_probe(struct pci_dev *pdev, const struct cpumask *node_mask; int cpu, i = 0, j = 0; int my_node = NUMA_NO_NODE; + unsigned long flags; /* Allocate memory for this devices private data. */ my_node = pcibus_to_node(pdev->bus); @@ -4218,6 +4322,9 @@ static int mtip_pci_probe(struct pci_dev *pdev, dd->pdev = pdev; dd->numa_node = my_node; + INIT_LIST_HEAD(&dd->online_list); + INIT_LIST_HEAD(&dd->remove_list); + memset(dd->workq_name, 0, 32); snprintf(dd->workq_name, 31, "mtipq%d", dd->instance); @@ -4305,6 +4412,14 @@ static int mtip_pci_probe(struct pci_dev *pdev, instance++; if (rv != MTIP_FTL_REBUILD_MAGIC) set_bit(MTIP_DDF_INIT_DONE_BIT, &dd->dd_flag); + else + rv = 0; /* device in rebuild state, return 0 from probe */ + + /* Add to online list even if in ftl rebuild */ + spin_lock_irqsave(&dev_lock, flags); + list_add(&dd->online_list, &online_list); + spin_unlock_irqrestore(&dev_lock, flags); + goto done; block_initialize_err: @@ -4338,9 +4453,15 @@ static void mtip_pci_remove(struct pci_dev *pdev) { struct driver_data *dd = pci_get_drvdata(pdev); int counter = 0; + unsigned long flags; set_bit(MTIP_DDF_REMOVE_PENDING_BIT, &dd->dd_flag); + spin_lock_irqsave(&dev_lock, flags); + list_del_init(&dd->online_list); + list_add(&dd->remove_list, &removing_list); + spin_unlock_irqrestore(&dev_lock, flags); + if (mtip_check_surprise_removal(pdev)) { while (!test_bit(MTIP_DDF_CLEANUP_BIT, &dd->dd_flag)) { counter++; @@ -4366,6 +4487,10 @@ static void mtip_pci_remove(struct pci_dev *pdev) pci_disable_msi(pdev); + spin_lock_irqsave(&dev_lock, flags); + list_del_init(&dd->remove_list); + spin_unlock_irqrestore(&dev_lock, flags); + kfree(dd); pcim_iounmap_regions(pdev, 1 << MTIP_ABAR); } @@ -4513,6 +4638,11 @@ static int __init mtip_init(void) pr_info(MTIP_DRV_NAME " Version " MTIP_DRV_VERSION "\n"); + spin_lock_init(&dev_lock); + + INIT_LIST_HEAD(&online_list); + INIT_LIST_HEAD(&removing_list); + /* Allocate a major block device number to use with this driver. */ error = register_blkdev(0, MTIP_DRV_NAME); if (error <= 0) { @@ -4522,11 +4652,18 @@ static int __init mtip_init(void) } mtip_major = error; - if (!dfs_parent) { - dfs_parent = debugfs_create_dir("rssd", NULL); - if (IS_ERR_OR_NULL(dfs_parent)) { - pr_warn("Error creating debugfs parent\n"); - dfs_parent = NULL; + dfs_parent = debugfs_create_dir("rssd", NULL); + if (IS_ERR_OR_NULL(dfs_parent)) { + pr_warn("Error creating debugfs parent\n"); + dfs_parent = NULL; + } + if (dfs_parent) { + dfs_device_status = debugfs_create_file("device_status", + S_IRUGO, dfs_parent, NULL, + &mtip_device_status_fops); + if (IS_ERR_OR_NULL(dfs_device_status)) { + pr_err("Error creating device_status node\n"); + dfs_device_status = NULL; } } diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h index 3bffff5f670c..8e8334c9dd0f 100644 --- a/drivers/block/mtip32xx/mtip32xx.h +++ b/drivers/block/mtip32xx/mtip32xx.h @@ -129,9 +129,9 @@ enum { MTIP_PF_EH_ACTIVE_BIT = 1, /* error handling */ MTIP_PF_SE_ACTIVE_BIT = 2, /* secure erase */ MTIP_PF_DM_ACTIVE_BIT = 3, /* download microcde */ - MTIP_PF_PAUSE_IO = ((1 << MTIP_PF_IC_ACTIVE_BIT) | \ - (1 << MTIP_PF_EH_ACTIVE_BIT) | \ - (1 << MTIP_PF_SE_ACTIVE_BIT) | \ + MTIP_PF_PAUSE_IO = ((1 << MTIP_PF_IC_ACTIVE_BIT) | + (1 << MTIP_PF_EH_ACTIVE_BIT) | + (1 << MTIP_PF_SE_ACTIVE_BIT) | (1 << MTIP_PF_DM_ACTIVE_BIT)), MTIP_PF_SVC_THD_ACTIVE_BIT = 4, @@ -144,9 +144,9 @@ enum { MTIP_DDF_REMOVE_PENDING_BIT = 1, MTIP_DDF_OVER_TEMP_BIT = 2, MTIP_DDF_WRITE_PROTECT_BIT = 3, - MTIP_DDF_STOP_IO = ((1 << MTIP_DDF_REMOVE_PENDING_BIT) | \ - (1 << MTIP_DDF_SEC_LOCK_BIT) | \ - (1 << MTIP_DDF_OVER_TEMP_BIT) | \ + MTIP_DDF_STOP_IO = ((1 << MTIP_DDF_REMOVE_PENDING_BIT) | + (1 << MTIP_DDF_SEC_LOCK_BIT) | + (1 << MTIP_DDF_OVER_TEMP_BIT) | (1 << MTIP_DDF_WRITE_PROTECT_BIT)), MTIP_DDF_CLEANUP_BIT = 5, @@ -180,7 +180,7 @@ struct mtip_work { #define MTIP_TRIM_TIMEOUT_MS 240000 #define MTIP_MAX_TRIM_ENTRIES 8 -#define MTIP_MAX_TRIM_ENTRY_LEN 0xfff8 +#define MTIP_MAX_TRIM_ENTRY_LEN 0xfff8 struct mtip_trim_entry { u32 lba; /* starting lba of region */ @@ -501,6 +501,10 @@ struct driver_data { atomic_t irq_workers_active; int isr_binding; + + struct list_head online_list; /* linkage for online list */ + + struct list_head remove_list; /* linkage for removing list */ }; #endif diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index f556f8a8b3f9..b7b7a88d9f68 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -1742,9 +1742,10 @@ static int rbd_img_request_submit(struct rbd_img_request *img_request) struct rbd_device *rbd_dev = img_request->rbd_dev; struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc; struct rbd_obj_request *obj_request; + struct rbd_obj_request *next_obj_request; dout("%s: img %p\n", __func__, img_request); - for_each_obj_request(img_request, obj_request) { + for_each_obj_request_safe(img_request, obj_request, next_obj_request) { int ret; obj_request->callback = rbd_img_obj_callback; diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c index e3f9a99b8522..d784650d14f0 100644 --- a/drivers/char/hpet.c +++ b/drivers/char/hpet.c @@ -373,26 +373,14 @@ static int hpet_mmap(struct file *file, struct vm_area_struct *vma) struct hpet_dev *devp; unsigned long addr; - if (((vma->vm_end - vma->vm_start) != PAGE_SIZE) || vma->vm_pgoff) - return -EINVAL; - devp = file->private_data; addr = devp->hd_hpets->hp_hpet_phys; if (addr & (PAGE_SIZE - 1)) return -ENOSYS; - vma->vm_flags |= VM_IO; vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - - if (io_remap_pfn_range(vma, vma->vm_start, addr >> PAGE_SHIFT, - PAGE_SIZE, vma->vm_page_prot)) { - printk(KERN_ERR "%s: io_remap_pfn_range failed\n", - __func__); - return -EAGAIN; - } - - return 0; + return vm_iomap_memory(vma, addr, PAGE_SIZE); #else return -ENOSYS; #endif diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index ad72922919ed..6133ef5cf671 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -502,7 +502,6 @@ static inline void intel_pstate_set_sample_time(struct cpudata *cpu) sample_time = cpu->pstate_policy->sample_rate_ms; delay = msecs_to_jiffies(sample_time); - delay -= jiffies % delay; mod_timer_pinned(&cpu->timer, jiffies + delay); } diff --git a/drivers/crypto/ux500/cryp/cryp_core.c b/drivers/crypto/ux500/cryp/cryp_core.c index 8bc5fef07e7a..22c9063e0120 100644 --- a/drivers/crypto/ux500/cryp/cryp_core.c +++ b/drivers/crypto/ux500/cryp/cryp_core.c @@ -1750,7 +1750,7 @@ static struct platform_driver cryp_driver = { .shutdown = ux500_cryp_shutdown, .driver = { .owner = THIS_MODULE, - .name = "cryp1" + .name = "cryp1", .pm = &ux500_cryp_pm, } }; diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c index 6e13f262139a..88cfc61329d2 100644 --- a/drivers/dma/at_hdmac.c +++ b/drivers/dma/at_hdmac.c @@ -310,8 +310,6 @@ static void atc_complete_all(struct at_dma_chan *atchan) dev_vdbg(chan2dev(&atchan->chan_common), "complete all\n"); - BUG_ON(atc_chan_is_enabled(atchan)); - /* * Submit queued descriptors ASAP, i.e. before we go through * the completed ones. @@ -368,6 +366,9 @@ static void atc_advance_work(struct at_dma_chan *atchan) { dev_vdbg(chan2dev(&atchan->chan_common), "advance_work\n"); + if (atc_chan_is_enabled(atchan)) + return; + if (list_empty(&atchan->active_list) || list_is_singular(&atchan->active_list)) { atc_complete_all(atchan); @@ -1078,9 +1079,7 @@ static void atc_issue_pending(struct dma_chan *chan) return; spin_lock_irqsave(&atchan->lock, flags); - if (!atc_chan_is_enabled(atchan)) { - atc_advance_work(atchan); - } + atc_advance_work(atchan); spin_unlock_irqrestore(&atchan->lock, flags); } diff --git a/drivers/dma/omap-dma.c b/drivers/dma/omap-dma.c index c4b4fd2acc42..08b43bf37158 100644 --- a/drivers/dma/omap-dma.c +++ b/drivers/dma/omap-dma.c @@ -276,12 +276,20 @@ static void omap_dma_issue_pending(struct dma_chan *chan) spin_lock_irqsave(&c->vc.lock, flags); if (vchan_issue_pending(&c->vc) && !c->desc) { - struct omap_dmadev *d = to_omap_dma_dev(chan->device); - spin_lock(&d->lock); - if (list_empty(&c->node)) - list_add_tail(&c->node, &d->pending); - spin_unlock(&d->lock); - tasklet_schedule(&d->task); + /* + * c->cyclic is used only by audio and in this case the DMA need + * to be started without delay. + */ + if (!c->cyclic) { + struct omap_dmadev *d = to_omap_dma_dev(chan->device); + spin_lock(&d->lock); + if (list_empty(&c->node)) + list_add_tail(&c->node, &d->pending); + spin_unlock(&d->lock); + tasklet_schedule(&d->task); + } else { + omap_dma_start_desc(c); + } } spin_unlock_irqrestore(&c->vc.lock, flags); } diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index 718153122759..5dbc5946c4c3 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -2882,7 +2882,7 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id) { struct dma_pl330_platdata *pdat; struct dma_pl330_dmac *pdmac; - struct dma_pl330_chan *pch; + struct dma_pl330_chan *pch, *_p; struct pl330_info *pi; struct dma_device *pd; struct resource *res; @@ -2984,7 +2984,16 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id) ret = dma_async_device_register(pd); if (ret) { dev_err(&adev->dev, "unable to register DMAC\n"); - goto probe_err2; + goto probe_err3; + } + + if (adev->dev.of_node) { + ret = of_dma_controller_register(adev->dev.of_node, + of_dma_pl330_xlate, pdmac); + if (ret) { + dev_err(&adev->dev, + "unable to register DMA to the generic DT DMA helpers\n"); + } } dev_info(&adev->dev, @@ -2995,16 +3004,21 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id) pi->pcfg.data_bus_width / 8, pi->pcfg.num_chan, pi->pcfg.num_peri, pi->pcfg.num_events); - ret = of_dma_controller_register(adev->dev.of_node, - of_dma_pl330_xlate, pdmac); - if (ret) { - dev_err(&adev->dev, - "unable to register DMA to the generic DT DMA helpers\n"); - goto probe_err2; - } - return 0; +probe_err3: + amba_set_drvdata(adev, NULL); + /* Idle the DMAC */ + list_for_each_entry_safe(pch, _p, &pdmac->ddma.channels, + chan.device_node) { + + /* Remove the channel */ + list_del(&pch->chan.device_node); + + /* Flush the channel */ + pl330_control(&pch->chan, DMA_TERMINATE_ALL, 0); + pl330_free_chan_resources(&pch->chan); + } probe_err2: pl330_del(pi); probe_err1: @@ -3023,8 +3037,10 @@ static int pl330_remove(struct amba_device *adev) if (!pdmac) return 0; - of_dma_controller_free(adev->dev.of_node); + if (adev->dev.of_node) + of_dma_controller_free(adev->dev.of_node); + dma_async_device_unregister(&pdmac->ddma); amba_set_drvdata(adev, NULL); /* Idle the DMAC */ diff --git a/drivers/eisa/pci_eisa.c b/drivers/eisa/pci_eisa.c index cdae207028a7..6c3fca97d346 100644 --- a/drivers/eisa/pci_eisa.c +++ b/drivers/eisa/pci_eisa.c @@ -19,10 +19,10 @@ /* There is only *one* pci_eisa device per machine, right ? */ static struct eisa_root_device pci_eisa_root; -static int __init pci_eisa_init(struct pci_dev *pdev, - const struct pci_device_id *ent) +static int __init pci_eisa_init(struct pci_dev *pdev) { - int rc; + int rc, i; + struct resource *res, *bus_res = NULL; if ((rc = pci_enable_device (pdev))) { printk (KERN_ERR "pci_eisa : Could not enable device %s\n", @@ -30,9 +30,30 @@ static int __init pci_eisa_init(struct pci_dev *pdev, return rc; } + /* + * The Intel 82375 PCI-EISA bridge is a subtractive-decode PCI + * device, so the resources available on EISA are the same as those + * available on the 82375 bus. This works the same as a PCI-PCI + * bridge in subtractive-decode mode (see pci_read_bridge_bases()). + * We assume other PCI-EISA bridges are similar. + * + * eisa_root_register() can only deal with a single io port resource, + * so we use the first valid io port resource. + */ + pci_bus_for_each_resource(pdev->bus, res, i) + if (res && (res->flags & IORESOURCE_IO)) { + bus_res = res; + break; + } + + if (!bus_res) { + dev_err(&pdev->dev, "No resources available\n"); + return -1; + } + pci_eisa_root.dev = &pdev->dev; - pci_eisa_root.res = pdev->bus->resource[0]; - pci_eisa_root.bus_base_addr = pdev->bus->resource[0]->start; + pci_eisa_root.res = bus_res; + pci_eisa_root.bus_base_addr = bus_res->start; pci_eisa_root.slots = EISA_MAX_SLOTS; pci_eisa_root.dma_mask = pdev->dma_mask; dev_set_drvdata(pci_eisa_root.dev, &pci_eisa_root); @@ -45,22 +66,26 @@ static int __init pci_eisa_init(struct pci_dev *pdev, return 0; } -static struct pci_device_id pci_eisa_pci_tbl[] = { - { PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, - PCI_CLASS_BRIDGE_EISA << 8, 0xffff00, 0 }, - { 0, } -}; - -static struct pci_driver __refdata pci_eisa_driver = { - .name = "pci_eisa", - .id_table = pci_eisa_pci_tbl, - .probe = pci_eisa_init, -}; - -static int __init pci_eisa_init_module (void) +/* + * We have to call pci_eisa_init_early() before pnpacpi_init()/isapnp_init(). + * Otherwise pnp resource will get enabled early and could prevent eisa + * to be initialized. + * Also need to make sure pci_eisa_init_early() is called after + * x86/pci_subsys_init(). + * So need to use subsys_initcall_sync with it. + */ +static int __init pci_eisa_init_early(void) { - return pci_register_driver (&pci_eisa_driver); -} + struct pci_dev *dev = NULL; + int ret; -device_initcall(pci_eisa_init_module); -MODULE_DEVICE_TABLE(pci, pci_eisa_pci_tbl); + for_each_pci_dev(dev) + if ((dev->class >> 8) == PCI_CLASS_BRIDGE_EISA) { + ret = pci_eisa_init(dev); + if (ret) + return ret; + } + + return 0; +} +subsys_initcall_sync(pci_eisa_init_early); diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig index 42c759a4d047..3e532002e4d1 100644 --- a/drivers/firmware/Kconfig +++ b/drivers/firmware/Kconfig @@ -39,6 +39,7 @@ config FIRMWARE_MEMMAP config EFI_VARS tristate "EFI Variable Support via sysfs" depends on EFI + select UCS2_STRING default n help If you say Y here, you are able to get EFI (Extensible Firmware diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c index 7acafb80fd4c..182ce9471175 100644 --- a/drivers/firmware/efivars.c +++ b/drivers/firmware/efivars.c @@ -80,6 +80,7 @@ #include #include #include +#include #include #include @@ -172,51 +173,6 @@ static void efivar_update_sysfs_entries(struct work_struct *); static DECLARE_WORK(efivar_work, efivar_update_sysfs_entries); static bool efivar_wq_enabled = true; -/* Return the number of unicode characters in data */ -static unsigned long -utf16_strnlen(efi_char16_t *s, size_t maxlength) -{ - unsigned long length = 0; - - while (*s++ != 0 && length < maxlength) - length++; - return length; -} - -static inline unsigned long -utf16_strlen(efi_char16_t *s) -{ - return utf16_strnlen(s, ~0UL); -} - -/* - * Return the number of bytes is the length of this string - * Note: this is NOT the same as the number of unicode characters - */ -static inline unsigned long -utf16_strsize(efi_char16_t *data, unsigned long maxlength) -{ - return utf16_strnlen(data, maxlength/sizeof(efi_char16_t)) * sizeof(efi_char16_t); -} - -static inline int -utf16_strncmp(const efi_char16_t *a, const efi_char16_t *b, size_t len) -{ - while (1) { - if (len == 0) - return 0; - if (*a < *b) - return -1; - if (*a > *b) - return 1; - if (*a == 0) /* implies *b == 0 */ - return 0; - a++; - b++; - len--; - } -} - static bool validate_device_path(struct efi_variable *var, int match, u8 *buffer, unsigned long len) @@ -268,7 +224,7 @@ validate_load_option(struct efi_variable *var, int match, u8 *buffer, u16 filepathlength; int i, desclength = 0, namelen; - namelen = utf16_strnlen(var->VariableName, sizeof(var->VariableName)); + namelen = ucs2_strnlen(var->VariableName, sizeof(var->VariableName)); /* Either "Boot" or "Driver" followed by four digits of hex */ for (i = match; i < match+4; i++) { @@ -291,7 +247,7 @@ validate_load_option(struct efi_variable *var, int match, u8 *buffer, * There's no stored length for the description, so it has to be * found by hand */ - desclength = utf16_strsize((efi_char16_t *)(buffer + 6), len - 6) + 2; + desclength = ucs2_strsize((efi_char16_t *)(buffer + 6), len - 6) + 2; /* Each boot entry must have a descriptor */ if (!desclength) @@ -436,24 +392,12 @@ static efi_status_t check_var_size_locked(struct efivars *efivars, u32 attributes, unsigned long size) { - u64 storage_size, remaining_size, max_size; - efi_status_t status; const struct efivar_operations *fops = efivars->ops; - if (!efivars->ops->query_variable_info) + if (!efivars->ops->query_variable_store) return EFI_UNSUPPORTED; - status = fops->query_variable_info(attributes, &storage_size, - &remaining_size, &max_size); - - if (status != EFI_SUCCESS) - return status; - - if (!storage_size || size > remaining_size || size > max_size || - (remaining_size - size) < (storage_size / 2)) - return EFI_OUT_OF_RESOURCES; - - return status; + return fops->query_variable_store(attributes, size); } @@ -593,7 +537,7 @@ efivar_store_raw(struct efivar_entry *entry, const char *buf, size_t count) spin_lock_irq(&efivars->lock); status = check_var_size_locked(efivars, new_var->Attributes, - new_var->DataSize + utf16_strsize(new_var->VariableName, 1024)); + new_var->DataSize + ucs2_strsize(new_var->VariableName, 1024)); if (status == EFI_SUCCESS || status == EFI_UNSUPPORTED) status = efivars->ops->set_variable(new_var->VariableName, @@ -771,7 +715,7 @@ static ssize_t efivarfs_file_write(struct file *file, * QueryVariableInfo() isn't supported by the firmware. */ - varsize = datasize + utf16_strsize(var->var.VariableName, 1024); + varsize = datasize + ucs2_strsize(var->var.VariableName, 1024); status = check_var_size(efivars, attributes, varsize); if (status != EFI_SUCCESS) { @@ -1223,7 +1167,7 @@ static int efivarfs_fill_super(struct super_block *sb, void *data, int silent) inode = NULL; - len = utf16_strlen(entry->var.VariableName); + len = ucs2_strlen(entry->var.VariableName); /* name, plus '-', plus GUID, plus NUL*/ name = kmalloc(len + 1 + GUID_LEN + 1, GFP_ATOMIC); @@ -1481,8 +1425,8 @@ static int efi_pstore_erase(enum pstore_type_id type, u64 id, int count, if (efi_guidcmp(entry->var.VendorGuid, vendor)) continue; - if (utf16_strncmp(entry->var.VariableName, efi_name, - utf16_strlen(efi_name))) { + if (ucs2_strncmp(entry->var.VariableName, efi_name, + ucs2_strlen(efi_name))) { /* * Check if an old format, * which doesn't support holding @@ -1494,8 +1438,8 @@ static int efi_pstore_erase(enum pstore_type_id type, u64 id, int count, for (i = 0; i < DUMP_NAME_LEN; i++) efi_name_old[i] = name_old[i]; - if (utf16_strncmp(entry->var.VariableName, efi_name_old, - utf16_strlen(efi_name_old))) + if (ucs2_strncmp(entry->var.VariableName, efi_name_old, + ucs2_strlen(efi_name_old))) continue; } @@ -1573,8 +1517,8 @@ static ssize_t efivar_create(struct file *filp, struct kobject *kobj, * Does this variable already exist? */ list_for_each_entry_safe(search_efivar, n, &efivars->list, list) { - strsize1 = utf16_strsize(search_efivar->var.VariableName, 1024); - strsize2 = utf16_strsize(new_var->VariableName, 1024); + strsize1 = ucs2_strsize(search_efivar->var.VariableName, 1024); + strsize2 = ucs2_strsize(new_var->VariableName, 1024); if (strsize1 == strsize2 && !memcmp(&(search_efivar->var.VariableName), new_var->VariableName, strsize1) && @@ -1590,7 +1534,7 @@ static ssize_t efivar_create(struct file *filp, struct kobject *kobj, } status = check_var_size_locked(efivars, new_var->Attributes, - new_var->DataSize + utf16_strsize(new_var->VariableName, 1024)); + new_var->DataSize + ucs2_strsize(new_var->VariableName, 1024)); if (status && status != EFI_UNSUPPORTED) { spin_unlock_irq(&efivars->lock); @@ -1614,7 +1558,7 @@ static ssize_t efivar_create(struct file *filp, struct kobject *kobj, /* Create the entry in sysfs. Locking is not required here */ status = efivar_create_sysfs_entry(efivars, - utf16_strsize(new_var->VariableName, + ucs2_strsize(new_var->VariableName, 1024), new_var->VariableName, &new_var->VendorGuid); @@ -1644,8 +1588,8 @@ static ssize_t efivar_delete(struct file *filp, struct kobject *kobj, * Does this variable already exist? */ list_for_each_entry_safe(search_efivar, n, &efivars->list, list) { - strsize1 = utf16_strsize(search_efivar->var.VariableName, 1024); - strsize2 = utf16_strsize(del_var->VariableName, 1024); + strsize1 = ucs2_strsize(search_efivar->var.VariableName, 1024); + strsize2 = ucs2_strsize(del_var->VariableName, 1024); if (strsize1 == strsize2 && !memcmp(&(search_efivar->var.VariableName), del_var->VariableName, strsize1) && @@ -1691,9 +1635,9 @@ static bool variable_is_present(efi_char16_t *variable_name, efi_guid_t *vendor) unsigned long strsize1, strsize2; bool found = false; - strsize1 = utf16_strsize(variable_name, 1024); + strsize1 = ucs2_strsize(variable_name, 1024); list_for_each_entry_safe(entry, n, &efivars->list, list) { - strsize2 = utf16_strsize(entry->var.VariableName, 1024); + strsize2 = ucs2_strsize(entry->var.VariableName, 1024); if (strsize1 == strsize2 && !memcmp(variable_name, &(entry->var.VariableName), strsize2) && @@ -2131,7 +2075,7 @@ efivars_init(void) ops.get_variable = efi.get_variable; ops.set_variable = efi.set_variable; ops.get_next_variable = efi.get_next_variable; - ops.query_variable_info = efi.query_variable_info; + ops.query_variable_store = efi_query_variable_store; error = register_efivars(&__efivars, &ops, efi_kobj); if (error) diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index 24059462c87f..9391cf16e990 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -575,7 +575,7 @@ static int pca953x_irq_setup(struct pca953x_chip *chip, chip->gpio_chip.ngpio, irq_base, &pca953x_irq_simple_ops, - NULL); + chip); if (!chip->domain) return -ENODEV; diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 59d6b9bf204b..892ff9f95975 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -1544,10 +1544,10 @@ int drm_fb_helper_hotplug_event(struct drm_fb_helper *fb_helper) if (!fb_helper->fb) return 0; - drm_modeset_lock_all(dev); + mutex_lock(&fb_helper->dev->mode_config.mutex); if (!drm_fb_helper_is_bound(fb_helper)) { fb_helper->delayed_hotplug = true; - drm_modeset_unlock_all(dev); + mutex_unlock(&fb_helper->dev->mode_config.mutex); return 0; } DRM_DEBUG_KMS("\n"); @@ -1558,9 +1558,11 @@ int drm_fb_helper_hotplug_event(struct drm_fb_helper *fb_helper) count = drm_fb_helper_probe_connector_modes(fb_helper, max_width, max_height); + mutex_unlock(&fb_helper->dev->mode_config.mutex); + + drm_modeset_lock_all(dev); drm_setup_crtcs(fb_helper); drm_modeset_unlock_all(dev); - drm_fb_helper_set_par(fb_helper->fbdev); return 0; diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c index fe22bb780e1d..78d8e919509f 100644 --- a/drivers/gpu/drm/mgag200/mgag200_mode.c +++ b/drivers/gpu/drm/mgag200/mgag200_mode.c @@ -751,8 +751,6 @@ static int mga_crtc_mode_set(struct drm_crtc *crtc, int i; unsigned char misc = 0; unsigned char ext_vga[6]; - unsigned char ext_vga_index24; - unsigned char dac_index90 = 0; u8 bppshift; static unsigned char dacvalue[] = { @@ -803,7 +801,6 @@ static int mga_crtc_mode_set(struct drm_crtc *crtc, option2 = 0x0000b000; break; case G200_ER: - dac_index90 = 0; break; } @@ -852,10 +849,8 @@ static int mga_crtc_mode_set(struct drm_crtc *crtc, WREG_DAC(i, dacvalue[i]); } - if (mdev->type == G200_ER) { - WREG_DAC(0x90, dac_index90); - } - + if (mdev->type == G200_ER) + WREG_DAC(0x90, 0); if (option) pci_write_config_dword(dev->pdev, PCI_MGA_OPTION, option); @@ -952,8 +947,6 @@ static int mga_crtc_mode_set(struct drm_crtc *crtc, if (mdev->type == G200_WB) ext_vga[1] |= 0x88; - ext_vga_index24 = 0x05; - /* Set pixel clocks */ misc = 0x2d; WREG8(MGA_MISC_OUT, misc); @@ -965,7 +958,7 @@ static int mga_crtc_mode_set(struct drm_crtc *crtc, } if (mdev->type == G200_ER) - WREG_ECRT(24, ext_vga_index24); + WREG_ECRT(0x24, 0x5); if (mdev->type == G200_EV) { WREG_ECRT(6, 0); diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/base.c b/drivers/gpu/drm/nouveau/core/subdev/bios/base.c index e816f06637a7..0e2c1a4f1659 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/bios/base.c +++ b/drivers/gpu/drm/nouveau/core/subdev/bios/base.c @@ -248,6 +248,22 @@ nouveau_bios_shadow_pci(struct nouveau_bios *bios) } } +static void +nouveau_bios_shadow_platform(struct nouveau_bios *bios) +{ + struct pci_dev *pdev = nv_device(bios)->pdev; + size_t size; + + void __iomem *rom = pci_platform_rom(pdev, &size); + if (rom && size) { + bios->data = kmalloc(size, GFP_KERNEL); + if (bios->data) { + memcpy_fromio(bios->data, rom, size); + bios->size = size; + } + } +} + static int nouveau_bios_score(struct nouveau_bios *bios, const bool writeable) { @@ -288,6 +304,7 @@ nouveau_bios_shadow(struct nouveau_bios *bios) { "PROM", nouveau_bios_shadow_prom, false, 0, 0, NULL }, { "ACPI", nouveau_bios_shadow_acpi, true, 0, 0, NULL }, { "PCIROM", nouveau_bios_shadow_pci, true, 0, 0, NULL }, + { "PLATFORM", nouveau_bios_shadow_platform, true, 0, 0, NULL }, {} }; struct methods *mthd, *best; diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c index 7f0e6c3f37d1..1ddc03e51bf4 100644 --- a/drivers/gpu/drm/nouveau/nv50_display.c +++ b/drivers/gpu/drm/nouveau/nv50_display.c @@ -479,7 +479,7 @@ nv50_display_flip_wait(void *data) { struct nv50_display_flip *flip = data; if (nouveau_bo_rd32(flip->disp->sync, flip->chan->addr / 4) == - flip->chan->data); + flip->chan->data) return true; usleep_range(1, 2); return false; diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c index b8015913d382..fa3c56fba294 100644 --- a/drivers/gpu/drm/radeon/radeon_bios.c +++ b/drivers/gpu/drm/radeon/radeon_bios.c @@ -99,6 +99,29 @@ static bool radeon_read_bios(struct radeon_device *rdev) return true; } +static bool radeon_read_platform_bios(struct radeon_device *rdev) +{ + uint8_t __iomem *bios; + size_t size; + + rdev->bios = NULL; + + bios = pci_platform_rom(rdev->pdev, &size); + if (!bios) { + return false; + } + + if (size == 0 || bios[0] != 0x55 || bios[1] != 0xaa) { + return false; + } + rdev->bios = kmemdup(bios, size, GFP_KERNEL); + if (rdev->bios == NULL) { + return false; + } + + return true; +} + #ifdef CONFIG_ACPI /* ATRM is used to get the BIOS on the discrete cards in * dual-gpu systems. @@ -620,6 +643,9 @@ bool radeon_get_bios(struct radeon_device *rdev) if (r == false) { r = radeon_read_disabled_bios(rdev); } + if (r == false) { + r = radeon_read_platform_bios(rdev); + } if (r == false || rdev->bios == NULL) { DRM_ERROR("Unable to locate a BIOS ROM\n"); rdev->bios = NULL; diff --git a/drivers/gpu/drm/udl/udl_connector.c b/drivers/gpu/drm/udl/udl_connector.c index fe5cdbcf2636..b44d548c56f8 100644 --- a/drivers/gpu/drm/udl/udl_connector.c +++ b/drivers/gpu/drm/udl/udl_connector.c @@ -61,6 +61,10 @@ static int udl_get_modes(struct drm_connector *connector) int ret; edid = (struct edid *)udl_get_edid(udl); + if (!edid) { + drm_mode_connector_update_edid_property(connector, NULL); + return 0; + } /* * We only read the main block, but if the monitor reports extension diff --git a/drivers/hwspinlock/hwspinlock_core.c b/drivers/hwspinlock/hwspinlock_core.c index db713c0dfba4..461a0d739d75 100644 --- a/drivers/hwspinlock/hwspinlock_core.c +++ b/drivers/hwspinlock/hwspinlock_core.c @@ -416,6 +416,8 @@ static int __hwspin_lock_request(struct hwspinlock *hwlock) ret = pm_runtime_get_sync(dev); if (ret < 0) { dev_err(dev, "%s: can't power on device\n", __func__); + pm_runtime_put_noidle(dev); + module_put(dev->driver->owner); return ret; } diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 5d6675013864..1a38dd7dfe4e 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -465,6 +465,7 @@ static const struct x86_cpu_id intel_idle_ids[] = { ICPU(0x3c, idle_cpu_hsw), ICPU(0x3f, idle_cpu_hsw), ICPU(0x45, idle_cpu_hsw), + ICPU(0x46, idle_cpu_hsw), {} }; MODULE_DEVICE_TABLE(x86cpu, intel_idle_ids); diff --git a/drivers/input/tablet/wacom_wac.c b/drivers/input/tablet/wacom_wac.c index 1daa97913b7d..0bfd8cf25200 100644 --- a/drivers/input/tablet/wacom_wac.c +++ b/drivers/input/tablet/wacom_wac.c @@ -359,7 +359,7 @@ static int wacom_intuos_inout(struct wacom_wac *wacom) case 0x802: /* Intuos4 General Pen */ case 0x804: /* Intuos4 Marker Pen */ case 0x40802: /* Intuos4 Classic Pen */ - case 0x18803: /* DTH2242 Grip Pen */ + case 0x18802: /* DTH2242 Grip Pen */ case 0x022: wacom->tool[idx] = BTN_TOOL_PEN; break; @@ -1912,7 +1912,7 @@ static const struct wacom_features wacom_features_0xBB = { "Wacom Intuos4 12x19", WACOM_PKGLEN_INTUOS, 97536, 60960, 2047, 63, INTUOS4L, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES }; static const struct wacom_features wacom_features_0xBC = - { "Wacom Intuos4 WL", WACOM_PKGLEN_INTUOS, 40840, 25400, 2047, + { "Wacom Intuos4 WL", WACOM_PKGLEN_INTUOS, 40640, 25400, 2047, 63, INTUOS4, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES }; static const struct wacom_features wacom_features_0x26 = { "Wacom Intuos5 touch S", WACOM_PKGLEN_INTUOS, 31496, 19685, 2047, @@ -2144,7 +2144,7 @@ const struct usb_device_id wacom_ids[] = { { USB_DEVICE_WACOM(0x44) }, { USB_DEVICE_WACOM(0x45) }, { USB_DEVICE_WACOM(0x59) }, - { USB_DEVICE_WACOM(0x5D) }, + { USB_DEVICE_DETAILED(0x5D, USB_CLASS_HID, 0, 0) }, { USB_DEVICE_WACOM(0xB0) }, { USB_DEVICE_WACOM(0xB1) }, { USB_DEVICE_WACOM(0xB2) }, @@ -2209,7 +2209,7 @@ const struct usb_device_id wacom_ids[] = { { USB_DEVICE_WACOM(0x47) }, { USB_DEVICE_WACOM(0xF4) }, { USB_DEVICE_WACOM(0xF8) }, - { USB_DEVICE_WACOM(0xF6) }, + { USB_DEVICE_DETAILED(0xF6, USB_CLASS_HID, 0, 0) }, { USB_DEVICE_WACOM(0xFA) }, { USB_DEVICE_LENOVO(0x6004) }, { } diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index a32e0d5aa45f..fc6aebf1e4b2 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -236,7 +236,8 @@ static int gic_retrigger(struct irq_data *d) if (gic_arch_extn.irq_retrigger) return gic_arch_extn.irq_retrigger(d); - return -ENXIO; + /* the genirq layer expects 0 if we can't retrigger in hardware */ + return 0; } #ifdef CONFIG_SMP diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 66120bd46d15..10744091e6ca 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -6,6 +6,7 @@ #include "dm.h" #include "dm-bio-prison.h" +#include "dm-bio-record.h" #include "dm-cache-metadata.h" #include @@ -201,10 +202,15 @@ struct per_bio_data { unsigned req_nr:2; struct dm_deferred_entry *all_io_entry; - /* writethrough fields */ + /* + * writethrough fields. These MUST remain at the end of this + * structure and the 'cache' member must be the first as it + * is used to determine the offsetof the writethrough fields. + */ struct cache *cache; dm_cblock_t cblock; bio_end_io_t *saved_bi_end_io; + struct dm_bio_details bio_details; }; struct dm_cache_migration { @@ -513,16 +519,28 @@ static void save_stats(struct cache *cache) /*---------------------------------------------------------------- * Per bio data *--------------------------------------------------------------*/ -static struct per_bio_data *get_per_bio_data(struct bio *bio) + +/* + * If using writeback, leave out struct per_bio_data's writethrough fields. + */ +#define PB_DATA_SIZE_WB (offsetof(struct per_bio_data, cache)) +#define PB_DATA_SIZE_WT (sizeof(struct per_bio_data)) + +static size_t get_per_bio_data_size(struct cache *cache) { - struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data)); + return cache->features.write_through ? PB_DATA_SIZE_WT : PB_DATA_SIZE_WB; +} + +static struct per_bio_data *get_per_bio_data(struct bio *bio, size_t data_size) +{ + struct per_bio_data *pb = dm_per_bio_data(bio, data_size); BUG_ON(!pb); return pb; } -static struct per_bio_data *init_per_bio_data(struct bio *bio) +static struct per_bio_data *init_per_bio_data(struct bio *bio, size_t data_size) { - struct per_bio_data *pb = get_per_bio_data(bio); + struct per_bio_data *pb = get_per_bio_data(bio, data_size); pb->tick = false; pb->req_nr = dm_bio_get_target_bio_nr(bio); @@ -556,7 +574,8 @@ static void remap_to_cache(struct cache *cache, struct bio *bio, static void check_if_tick_bio_needed(struct cache *cache, struct bio *bio) { unsigned long flags; - struct per_bio_data *pb = get_per_bio_data(bio); + size_t pb_data_size = get_per_bio_data_size(cache); + struct per_bio_data *pb = get_per_bio_data(bio, pb_data_size); spin_lock_irqsave(&cache->lock, flags); if (cache->need_tick_bio && @@ -635,7 +654,7 @@ static void defer_writethrough_bio(struct cache *cache, struct bio *bio) static void writethrough_endio(struct bio *bio, int err) { - struct per_bio_data *pb = get_per_bio_data(bio); + struct per_bio_data *pb = get_per_bio_data(bio, PB_DATA_SIZE_WT); bio->bi_end_io = pb->saved_bi_end_io; if (err) { @@ -643,6 +662,7 @@ static void writethrough_endio(struct bio *bio, int err) return; } + dm_bio_restore(&pb->bio_details, bio); remap_to_cache(pb->cache, bio, pb->cblock); /* @@ -662,11 +682,12 @@ static void writethrough_endio(struct bio *bio, int err) static void remap_to_origin_then_cache(struct cache *cache, struct bio *bio, dm_oblock_t oblock, dm_cblock_t cblock) { - struct per_bio_data *pb = get_per_bio_data(bio); + struct per_bio_data *pb = get_per_bio_data(bio, PB_DATA_SIZE_WT); pb->cache = cache; pb->cblock = cblock; pb->saved_bi_end_io = bio->bi_end_io; + dm_bio_record(&pb->bio_details, bio); bio->bi_end_io = writethrough_endio; remap_to_origin_clear_discard(pb->cache, bio, oblock); @@ -1035,7 +1056,8 @@ static void defer_bio(struct cache *cache, struct bio *bio) static void process_flush_bio(struct cache *cache, struct bio *bio) { - struct per_bio_data *pb = get_per_bio_data(bio); + size_t pb_data_size = get_per_bio_data_size(cache); + struct per_bio_data *pb = get_per_bio_data(bio, pb_data_size); BUG_ON(bio->bi_size); if (!pb->req_nr) @@ -1107,7 +1129,8 @@ static void process_bio(struct cache *cache, struct prealloc *structs, dm_oblock_t block = get_bio_block(cache, bio); struct dm_bio_prison_cell *cell_prealloc, *old_ocell, *new_ocell; struct policy_result lookup_result; - struct per_bio_data *pb = get_per_bio_data(bio); + size_t pb_data_size = get_per_bio_data_size(cache); + struct per_bio_data *pb = get_per_bio_data(bio, pb_data_size); bool discarded_block = is_discarded_oblock(cache, block); bool can_migrate = discarded_block || spare_migration_bandwidth(cache); @@ -1881,7 +1904,6 @@ static int cache_create(struct cache_args *ca, struct cache **result) cache->ti = ca->ti; ti->private = cache; - ti->per_bio_data_size = sizeof(struct per_bio_data); ti->num_flush_bios = 2; ti->flush_supported = true; @@ -1890,6 +1912,7 @@ static int cache_create(struct cache_args *ca, struct cache **result) ti->discard_zeroes_data_unsupported = true; memcpy(&cache->features, &ca->features, sizeof(cache->features)); + ti->per_bio_data_size = get_per_bio_data_size(cache); cache->callbacks.congested_fn = cache_is_congested; dm_table_add_target_callbacks(ti->table, &cache->callbacks); @@ -2092,6 +2115,7 @@ static int cache_map(struct dm_target *ti, struct bio *bio) int r; dm_oblock_t block = get_bio_block(cache, bio); + size_t pb_data_size = get_per_bio_data_size(cache); bool can_migrate = false; bool discarded_block; struct dm_bio_prison_cell *cell; @@ -2108,7 +2132,7 @@ static int cache_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_REMAPPED; } - pb = init_per_bio_data(bio); + pb = init_per_bio_data(bio, pb_data_size); if (bio->bi_rw & (REQ_FLUSH | REQ_FUA | REQ_DISCARD)) { defer_bio(cache, bio); @@ -2193,7 +2217,8 @@ static int cache_end_io(struct dm_target *ti, struct bio *bio, int error) { struct cache *cache = ti->private; unsigned long flags; - struct per_bio_data *pb = get_per_bio_data(bio); + size_t pb_data_size = get_per_bio_data_size(cache); + struct per_bio_data *pb = get_per_bio_data(bio, pb_data_size); if (pb->tick) { policy_tick(cache->policy); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 7e469260fe5e..9a0bdad9ad8f 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -611,6 +611,7 @@ static void dec_pending(struct dm_io *io, int error) queue_io(md, bio); } else { /* done with normal IO or empty flush */ + trace_block_bio_complete(md->queue, bio, io_error); bio_endio(bio, io_error); } } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 24909eb13fec..f4e87bfc7567 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -184,6 +184,8 @@ static void return_io(struct bio *return_bi) return_bi = bi->bi_next; bi->bi_next = NULL; bi->bi_size = 0; + trace_block_bio_complete(bdev_get_queue(bi->bi_bdev), + bi, 0); bio_endio(bi, 0); bi = return_bi; } @@ -3914,6 +3916,8 @@ static void raid5_align_endio(struct bio *bi, int error) rdev_dec_pending(rdev, conf->mddev); if (!error && uptodate) { + trace_block_bio_complete(bdev_get_queue(raid_bi->bi_bdev), + raid_bi, 0); bio_endio(raid_bi, 0); if (atomic_dec_and_test(&conf->active_aligned_reads)) wake_up(&conf->wait_for_stripe); @@ -4382,6 +4386,8 @@ static void make_request(struct mddev *mddev, struct bio * bi) if ( rw == WRITE ) md_write_end(mddev); + trace_block_bio_complete(bdev_get_queue(bi->bi_bdev), + bi, 0); bio_endio(bi, 0); } } @@ -4758,8 +4764,11 @@ static int retry_aligned_read(struct r5conf *conf, struct bio *raid_bio) handled++; } remaining = raid5_dec_bi_active_stripes(raid_bio); - if (remaining == 0) + if (remaining == 0) { + trace_block_bio_complete(bdev_get_queue(raid_bio->bi_bdev), + raid_bio, 0); bio_endio(raid_bio, 0); + } if (atomic_dec_and_test(&conf->active_aligned_reads)) wake_up(&conf->wait_for_stripe); return handled; diff --git a/drivers/misc/vmw_vmci/Kconfig b/drivers/misc/vmw_vmci/Kconfig index 39c2ecadb273..ea98f7e9ccd1 100644 --- a/drivers/misc/vmw_vmci/Kconfig +++ b/drivers/misc/vmw_vmci/Kconfig @@ -4,7 +4,7 @@ config VMWARE_VMCI tristate "VMware VMCI Driver" - depends on X86 && PCI + depends on X86 && PCI && NET help This is VMware's Virtual Machine Communication Interface. It enables high-speed communication between host and guest in a virtual diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c index 92ab30ab00dc..dc571ebc1aa0 100644 --- a/drivers/mtd/mtdchar.c +++ b/drivers/mtd/mtdchar.c @@ -1123,33 +1123,6 @@ static unsigned long mtdchar_get_unmapped_area(struct file *file, } #endif -static inline unsigned long get_vm_size(struct vm_area_struct *vma) -{ - return vma->vm_end - vma->vm_start; -} - -static inline resource_size_t get_vm_offset(struct vm_area_struct *vma) -{ - return (resource_size_t) vma->vm_pgoff << PAGE_SHIFT; -} - -/* - * Set a new vm offset. - * - * Verify that the incoming offset really works as a page offset, - * and that the offset and size fit in a resource_size_t. - */ -static inline int set_vm_offset(struct vm_area_struct *vma, resource_size_t off) -{ - pgoff_t pgoff = off >> PAGE_SHIFT; - if (off != (resource_size_t) pgoff << PAGE_SHIFT) - return -EINVAL; - if (off + get_vm_size(vma) - 1 < off) - return -EINVAL; - vma->vm_pgoff = pgoff; - return 0; -} - /* * set up a mapping for shared memory segments */ @@ -1159,45 +1132,17 @@ static int mtdchar_mmap(struct file *file, struct vm_area_struct *vma) struct mtd_file_info *mfi = file->private_data; struct mtd_info *mtd = mfi->mtd; struct map_info *map = mtd->priv; - resource_size_t start, off; - unsigned long len, vma_len; /* This is broken because it assumes the MTD device is map-based and that mtd->priv is a valid struct map_info. It should be replaced with something that uses the mtd_get_unmapped_area() operation properly. */ if (0 /*mtd->type == MTD_RAM || mtd->type == MTD_ROM*/) { - off = get_vm_offset(vma); - start = map->phys; - len = PAGE_ALIGN((start & ~PAGE_MASK) + map->size); - start &= PAGE_MASK; - vma_len = get_vm_size(vma); - - /* Overflow in off+len? */ - if (vma_len + off < off) - return -EINVAL; - /* Does it fit in the mapping? */ - if (vma_len + off > len) - return -EINVAL; - - off += start; - /* Did that overflow? */ - if (off < start) - return -EINVAL; - if (set_vm_offset(vma, off) < 0) - return -EINVAL; - vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP; - #ifdef pgprot_noncached - if (file->f_flags & O_DSYNC || off >= __pa(high_memory)) + if (file->f_flags & O_DSYNC || map->phys >= __pa(high_memory)) vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); #endif - if (io_remap_pfn_range(vma, vma->vm_start, off >> PAGE_SHIFT, - vma->vm_end - vma->vm_start, - vma->vm_page_prot)) - return -EAGAIN; - - return 0; + return vm_iomap_memory(vma, map->phys, map->size); } return -ENOSYS; #else diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 5e22126c7a26..532153db1f9c 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -848,8 +848,10 @@ static void bond_mc_swap(struct bonding *bond, struct slave *new_active, if (bond->dev->flags & IFF_ALLMULTI) dev_set_allmulti(old_active->dev, -1); + netif_addr_lock_bh(bond->dev); netdev_for_each_mc_addr(ha, bond->dev) dev_mc_del(old_active->dev, ha->addr); + netif_addr_unlock_bh(bond->dev); } if (new_active) { @@ -860,8 +862,10 @@ static void bond_mc_swap(struct bonding *bond, struct slave *new_active, if (bond->dev->flags & IFF_ALLMULTI) dev_set_allmulti(new_active->dev, 1); + netif_addr_lock_bh(bond->dev); netdev_for_each_mc_addr(ha, bond->dev) dev_mc_add(new_active->dev, ha->addr); + netif_addr_unlock_bh(bond->dev); } } @@ -1903,11 +1907,29 @@ err_dest_symlinks: bond_destroy_slave_symlinks(bond_dev, slave_dev); err_detach: + if (!USES_PRIMARY(bond->params.mode)) { + netif_addr_lock_bh(bond_dev); + bond_mc_list_flush(bond_dev, slave_dev); + netif_addr_unlock_bh(bond_dev); + } + bond_del_vlans_from_slave(bond, slave_dev); write_lock_bh(&bond->lock); bond_detach_slave(bond, new_slave); + if (bond->primary_slave == new_slave) + bond->primary_slave = NULL; write_unlock_bh(&bond->lock); + if (bond->curr_active_slave == new_slave) { + read_lock(&bond->lock); + write_lock_bh(&bond->curr_slave_lock); + bond_change_active_slave(bond, NULL); + bond_select_active_slave(bond); + write_unlock_bh(&bond->curr_slave_lock); + read_unlock(&bond->lock); + } + slave_disable_netpoll(new_slave); err_close: + slave_dev->priv_flags &= ~IFF_BONDING; dev_close(slave_dev); err_unset_master: @@ -3172,11 +3194,20 @@ static int bond_slave_netdev_event(unsigned long event, struct net_device *slave_dev) { struct slave *slave = bond_slave_get_rtnl(slave_dev); - struct bonding *bond = slave->bond; - struct net_device *bond_dev = slave->bond->dev; + struct bonding *bond; + struct net_device *bond_dev; u32 old_speed; u8 old_duplex; + /* A netdev event can be generated while enslaving a device + * before netdev_rx_handler_register is called in which case + * slave will be NULL + */ + if (!slave) + return NOTIFY_DONE; + bond_dev = slave->bond->dev; + bond = slave->bond; + switch (event) { case NETDEV_UNREGISTER: if (bond->setup_by_slave) @@ -3290,20 +3321,22 @@ static int bond_xmit_hash_policy_l2(struct sk_buff *skb, int count) */ static int bond_xmit_hash_policy_l23(struct sk_buff *skb, int count) { - struct ethhdr *data = (struct ethhdr *)skb->data; - struct iphdr *iph; - struct ipv6hdr *ipv6h; + const struct ethhdr *data; + const struct iphdr *iph; + const struct ipv6hdr *ipv6h; u32 v6hash; - __be32 *s, *d; + const __be32 *s, *d; if (skb->protocol == htons(ETH_P_IP) && - skb_network_header_len(skb) >= sizeof(*iph)) { + pskb_network_may_pull(skb, sizeof(*iph))) { iph = ip_hdr(skb); + data = (struct ethhdr *)skb->data; return ((ntohl(iph->saddr ^ iph->daddr) & 0xffff) ^ (data->h_dest[5] ^ data->h_source[5])) % count; } else if (skb->protocol == htons(ETH_P_IPV6) && - skb_network_header_len(skb) >= sizeof(*ipv6h)) { + pskb_network_may_pull(skb, sizeof(*ipv6h))) { ipv6h = ipv6_hdr(skb); + data = (struct ethhdr *)skb->data; s = &ipv6h->saddr.s6_addr32[0]; d = &ipv6h->daddr.s6_addr32[0]; v6hash = (s[1] ^ d[1]) ^ (s[2] ^ d[2]) ^ (s[3] ^ d[3]); @@ -3322,33 +3355,36 @@ static int bond_xmit_hash_policy_l23(struct sk_buff *skb, int count) static int bond_xmit_hash_policy_l34(struct sk_buff *skb, int count) { u32 layer4_xor = 0; - struct iphdr *iph; - struct ipv6hdr *ipv6h; - __be32 *s, *d; - __be16 *layer4hdr; + const struct iphdr *iph; + const struct ipv6hdr *ipv6h; + const __be32 *s, *d; + const __be16 *l4 = NULL; + __be16 _l4[2]; + int noff = skb_network_offset(skb); + int poff; if (skb->protocol == htons(ETH_P_IP) && - skb_network_header_len(skb) >= sizeof(*iph)) { + pskb_may_pull(skb, noff + sizeof(*iph))) { iph = ip_hdr(skb); - if (!ip_is_fragment(iph) && - (iph->protocol == IPPROTO_TCP || - iph->protocol == IPPROTO_UDP) && - (skb_headlen(skb) - skb_network_offset(skb) >= - iph->ihl * sizeof(u32) + sizeof(*layer4hdr) * 2)) { - layer4hdr = (__be16 *)((u32 *)iph + iph->ihl); - layer4_xor = ntohs(*layer4hdr ^ *(layer4hdr + 1)); + poff = proto_ports_offset(iph->protocol); + + if (!ip_is_fragment(iph) && poff >= 0) { + l4 = skb_header_pointer(skb, noff + (iph->ihl << 2) + poff, + sizeof(_l4), &_l4); + if (l4) + layer4_xor = ntohs(l4[0] ^ l4[1]); } return (layer4_xor ^ ((ntohl(iph->saddr ^ iph->daddr)) & 0xffff)) % count; } else if (skb->protocol == htons(ETH_P_IPV6) && - skb_network_header_len(skb) >= sizeof(*ipv6h)) { + pskb_may_pull(skb, noff + sizeof(*ipv6h))) { ipv6h = ipv6_hdr(skb); - if ((ipv6h->nexthdr == IPPROTO_TCP || - ipv6h->nexthdr == IPPROTO_UDP) && - (skb_headlen(skb) - skb_network_offset(skb) >= - sizeof(*ipv6h) + sizeof(*layer4hdr) * 2)) { - layer4hdr = (__be16 *)(ipv6h + 1); - layer4_xor = ntohs(*layer4hdr ^ *(layer4hdr + 1)); + poff = proto_ports_offset(ipv6h->nexthdr); + if (poff >= 0) { + l4 = skb_header_pointer(skb, noff + sizeof(*ipv6h) + poff, + sizeof(_l4), &_l4); + if (l4) + layer4_xor = ntohs(l4[0] ^ l4[1]); } s = &ipv6h->saddr.s6_addr32[0]; d = &ipv6h->daddr.s6_addr32[0]; @@ -4882,9 +4918,18 @@ static int __net_init bond_net_init(struct net *net) static void __net_exit bond_net_exit(struct net *net) { struct bond_net *bn = net_generic(net, bond_net_id); + struct bonding *bond, *tmp_bond; + LIST_HEAD(list); bond_destroy_sysfs(bn); bond_destroy_proc_dir(bn); + + /* Kill off any bonds created after unregistering bond rtnl ops */ + rtnl_lock(); + list_for_each_entry_safe(bond, tmp_bond, &bn->dev_list, bond_list) + unregister_netdevice_queue(bond->dev, &list); + unregister_netdevice_many(&list); + rtnl_unlock(); } static struct pernet_operations bond_net_ops = { @@ -4938,8 +4983,8 @@ static void __exit bonding_exit(void) bond_destroy_debugfs(); - unregister_pernet_subsys(&bond_net_ops); rtnl_link_unregister(&bond_link_ops); + unregister_pernet_subsys(&bond_net_ops); #ifdef CONFIG_NET_POLL_CONTROLLER /* diff --git a/drivers/net/can/mcp251x.c b/drivers/net/can/mcp251x.c index 55033dd57afb..8cda23bf0614 100644 --- a/drivers/net/can/mcp251x.c +++ b/drivers/net/can/mcp251x.c @@ -929,6 +929,7 @@ static int mcp251x_open(struct net_device *net) struct mcp251x_priv *priv = netdev_priv(net); struct spi_device *spi = priv->spi; struct mcp251x_platform_data *pdata = spi->dev.platform_data; + unsigned long flags; int ret; ret = open_candev(net); @@ -945,9 +946,14 @@ static int mcp251x_open(struct net_device *net) priv->tx_skb = NULL; priv->tx_len = 0; + flags = IRQF_ONESHOT; + if (pdata->irq_flags) + flags |= pdata->irq_flags; + else + flags |= IRQF_TRIGGER_FALLING; + ret = request_threaded_irq(spi->irq, NULL, mcp251x_can_ist, - pdata->irq_flags ? pdata->irq_flags : IRQF_TRIGGER_FALLING, - DEVICE_NAME, priv); + flags, DEVICE_NAME, priv); if (ret) { dev_err(&spi->dev, "failed to acquire irq %d\n", spi->irq); if (pdata->transceiver_enable) diff --git a/drivers/net/can/sja1000/sja1000_of_platform.c b/drivers/net/can/sja1000/sja1000_of_platform.c index 6433b81256cd..8e0c4a001939 100644 --- a/drivers/net/can/sja1000/sja1000_of_platform.c +++ b/drivers/net/can/sja1000/sja1000_of_platform.c @@ -96,8 +96,8 @@ static int sja1000_ofp_probe(struct platform_device *ofdev) struct net_device *dev; struct sja1000_priv *priv; struct resource res; - const u32 *prop; - int err, irq, res_size, prop_size; + u32 prop; + int err, irq, res_size; void __iomem *base; err = of_address_to_resource(np, 0, &res); @@ -138,27 +138,27 @@ static int sja1000_ofp_probe(struct platform_device *ofdev) priv->read_reg = sja1000_ofp_read_reg; priv->write_reg = sja1000_ofp_write_reg; - prop = of_get_property(np, "nxp,external-clock-frequency", &prop_size); - if (prop && (prop_size == sizeof(u32))) - priv->can.clock.freq = *prop / 2; + err = of_property_read_u32(np, "nxp,external-clock-frequency", &prop); + if (!err) + priv->can.clock.freq = prop / 2; else priv->can.clock.freq = SJA1000_OFP_CAN_CLOCK; /* default */ - prop = of_get_property(np, "nxp,tx-output-mode", &prop_size); - if (prop && (prop_size == sizeof(u32))) - priv->ocr |= *prop & OCR_MODE_MASK; + err = of_property_read_u32(np, "nxp,tx-output-mode", &prop); + if (!err) + priv->ocr |= prop & OCR_MODE_MASK; else priv->ocr |= OCR_MODE_NORMAL; /* default */ - prop = of_get_property(np, "nxp,tx-output-config", &prop_size); - if (prop && (prop_size == sizeof(u32))) - priv->ocr |= (*prop << OCR_TX_SHIFT) & OCR_TX_MASK; + err = of_property_read_u32(np, "nxp,tx-output-config", &prop); + if (!err) + priv->ocr |= (prop << OCR_TX_SHIFT) & OCR_TX_MASK; else priv->ocr |= OCR_TX0_PULLDOWN; /* default */ - prop = of_get_property(np, "nxp,clock-out-frequency", &prop_size); - if (prop && (prop_size == sizeof(u32)) && *prop) { - u32 divider = priv->can.clock.freq * 2 / *prop; + err = of_property_read_u32(np, "nxp,clock-out-frequency", &prop); + if (!err && prop) { + u32 divider = priv->can.clock.freq * 2 / prop; if (divider > 1) priv->cdr |= divider / 2 - 1; @@ -168,8 +168,7 @@ static int sja1000_ofp_probe(struct platform_device *ofdev) priv->cdr |= CDR_CLK_OFF; /* default */ } - prop = of_get_property(np, "nxp,no-comparator-bypass", NULL); - if (!prop) + if (!of_property_read_bool(np, "nxp,no-comparator-bypass")) priv->cdr |= CDR_CBP; /* default */ priv->irq_flags = IRQF_SHARED; diff --git a/drivers/net/ethernet/8390/ax88796.c b/drivers/net/ethernet/8390/ax88796.c index cab306a9888e..e1d26433d619 100644 --- a/drivers/net/ethernet/8390/ax88796.c +++ b/drivers/net/ethernet/8390/ax88796.c @@ -828,7 +828,7 @@ static int ax_probe(struct platform_device *pdev) struct ei_device *ei_local; struct ax_device *ax; struct resource *irq, *mem, *mem2; - resource_size_t mem_size, mem2_size = 0; + unsigned long mem_size, mem2_size = 0; int ret = 0; dev = ax__alloc_ei_netdev(sizeof(struct ax_device)); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 6b50443d3456..d72bd8c40aa1 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -2615,6 +2615,9 @@ int bnx2x_nic_load(struct bnx2x *bp, int load_mode) } } + /* initialize FW coalescing state machines in RAM */ + bnx2x_update_coalesce(bp); + /* setup the leading queue */ rc = bnx2x_setup_leading(bp); if (rc) { @@ -4737,11 +4740,11 @@ static void storm_memset_hc_disable(struct bnx2x *bp, u8 port, u32 enable_flag = disable ? 0 : (1 << HC_INDEX_DATA_HC_ENABLED_SHIFT); u32 addr = BAR_CSTRORM_INTMEM + CSTORM_STATUS_BLOCK_DATA_FLAGS_OFFSET(fw_sb_id, sb_index); - u16 flags = REG_RD16(bp, addr); + u8 flags = REG_RD8(bp, addr); /* clear and set */ flags &= ~HC_INDEX_DATA_HC_ENABLED; flags |= enable_flag; - REG_WR16(bp, addr, flags); + REG_WR8(bp, addr, flags); DP(NETIF_MSG_IFUP, "port %x fw_sb_id %d sb_index %d disable %d\n", port, fw_sb_id, sb_index, disable); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 1e60c5d139d1..86d13870399e 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -4959,7 +4959,7 @@ static void bnx2x_after_function_update(struct bnx2x *bp) q); } - if (!NO_FCOE(bp)) { + if (!NO_FCOE(bp) && CNIC_ENABLED(bp)) { fp = &bp->fp[FCOE_IDX(bp)]; queue_params.q_obj = &bnx2x_sp_obj(bp, fp).q_obj; @@ -9946,6 +9946,10 @@ static int bnx2x_prev_unload_common(struct bnx2x *bp) REG_RD(bp, NIG_REG_NIG_INT_STS_CLR_0); } } + if (!CHIP_IS_E1x(bp)) + /* block FW from writing to host */ + REG_WR(bp, PGLUE_B_REG_INTERNAL_PFID_ENABLE_MASTER, 0); + /* wait until BRB is empty */ tmp_reg = REG_RD(bp, BRB1_REG_NUM_OF_FULL_BLOCKS); while (timer_count) { @@ -13450,6 +13454,7 @@ static int bnx2x_unregister_cnic(struct net_device *dev) RCU_INIT_POINTER(bp->cnic_ops, NULL); mutex_unlock(&bp->cnic_mutex); synchronize_rcu(); + bp->cnic_enabled = false; kfree(bp->cnic_kwq); bp->cnic_kwq = NULL; diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 21808680b91f..654e7820daa0 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -772,8 +772,9 @@ static struct sk_buff *be_insert_vlan_in_pkt(struct be_adapter *adapter, if (vlan_tx_tag_present(skb)) { vlan_tag = be_get_tx_vlan_tag(adapter, skb); - __vlan_put_tag(skb, htons(ETH_P_8021Q), vlan_tag); - skb->vlan_tci = 0; + skb = __vlan_put_tag(skb, htons(ETH_P_8021Q), vlan_tag); + if (skb) + skb->vlan_tci = 0; } return skb; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 20890874ead7..2451ab1b5a83 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -997,6 +997,7 @@ static void fec_enet_adjust_link(struct net_device *ndev) } else { if (fep->link) { fec_stop(ndev); + fep->link = phy_dev->link; status_change = 1; } } diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index ec800b093e7e..d2bea3f07c73 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -870,7 +870,7 @@ err_unlock: } static int e100_exec_cb(struct nic *nic, struct sk_buff *skb, - void (*cb_prepare)(struct nic *, struct cb *, struct sk_buff *)) + int (*cb_prepare)(struct nic *, struct cb *, struct sk_buff *)) { struct cb *cb; unsigned long flags; @@ -888,10 +888,13 @@ static int e100_exec_cb(struct nic *nic, struct sk_buff *skb, nic->cbs_avail--; cb->skb = skb; + err = cb_prepare(nic, cb, skb); + if (err) + goto err_unlock; + if (unlikely(!nic->cbs_avail)) err = -ENOSPC; - cb_prepare(nic, cb, skb); /* Order is important otherwise we'll be in a race with h/w: * set S-bit in current first, then clear S-bit in previous. */ @@ -1091,7 +1094,7 @@ static void e100_get_defaults(struct nic *nic) nic->mii.mdio_write = mdio_write; } -static void e100_configure(struct nic *nic, struct cb *cb, struct sk_buff *skb) +static int e100_configure(struct nic *nic, struct cb *cb, struct sk_buff *skb) { struct config *config = &cb->u.config; u8 *c = (u8 *)config; @@ -1181,6 +1184,7 @@ static void e100_configure(struct nic *nic, struct cb *cb, struct sk_buff *skb) netif_printk(nic, hw, KERN_DEBUG, nic->netdev, "[16-23]=%02X:%02X:%02X:%02X:%02X:%02X:%02X:%02X\n", c[16], c[17], c[18], c[19], c[20], c[21], c[22], c[23]); + return 0; } /************************************************************************* @@ -1331,7 +1335,7 @@ static const struct firmware *e100_request_firmware(struct nic *nic) return fw; } -static void e100_setup_ucode(struct nic *nic, struct cb *cb, +static int e100_setup_ucode(struct nic *nic, struct cb *cb, struct sk_buff *skb) { const struct firmware *fw = (void *)skb; @@ -1358,6 +1362,7 @@ static void e100_setup_ucode(struct nic *nic, struct cb *cb, cb->u.ucode[min_size] |= cpu_to_le32((BUNDLESMALL) ? 0xFFFF : 0xFF80); cb->command = cpu_to_le16(cb_ucode | cb_el); + return 0; } static inline int e100_load_ucode_wait(struct nic *nic) @@ -1400,18 +1405,20 @@ static inline int e100_load_ucode_wait(struct nic *nic) return err; } -static void e100_setup_iaaddr(struct nic *nic, struct cb *cb, +static int e100_setup_iaaddr(struct nic *nic, struct cb *cb, struct sk_buff *skb) { cb->command = cpu_to_le16(cb_iaaddr); memcpy(cb->u.iaaddr, nic->netdev->dev_addr, ETH_ALEN); + return 0; } -static void e100_dump(struct nic *nic, struct cb *cb, struct sk_buff *skb) +static int e100_dump(struct nic *nic, struct cb *cb, struct sk_buff *skb) { cb->command = cpu_to_le16(cb_dump); cb->u.dump_buffer_addr = cpu_to_le32(nic->dma_addr + offsetof(struct mem, dump_buf)); + return 0; } static int e100_phy_check_without_mii(struct nic *nic) @@ -1581,7 +1588,7 @@ static int e100_hw_init(struct nic *nic) return 0; } -static void e100_multi(struct nic *nic, struct cb *cb, struct sk_buff *skb) +static int e100_multi(struct nic *nic, struct cb *cb, struct sk_buff *skb) { struct net_device *netdev = nic->netdev; struct netdev_hw_addr *ha; @@ -1596,6 +1603,7 @@ static void e100_multi(struct nic *nic, struct cb *cb, struct sk_buff *skb) memcpy(&cb->u.multi.addr[i++ * ETH_ALEN], &ha->addr, ETH_ALEN); } + return 0; } static void e100_set_multicast_list(struct net_device *netdev) @@ -1756,11 +1764,18 @@ static void e100_watchdog(unsigned long data) round_jiffies(jiffies + E100_WATCHDOG_PERIOD)); } -static void e100_xmit_prepare(struct nic *nic, struct cb *cb, +static int e100_xmit_prepare(struct nic *nic, struct cb *cb, struct sk_buff *skb) { + dma_addr_t dma_addr; cb->command = nic->tx_command; + dma_addr = pci_map_single(nic->pdev, + skb->data, skb->len, PCI_DMA_TODEVICE); + /* If we can't map the skb, have the upper layer try later */ + if (pci_dma_mapping_error(nic->pdev, dma_addr)) + return -ENOMEM; + /* * Use the last 4 bytes of the SKB payload packet as the CRC, used for * testing, ie sending frames with bad CRC. @@ -1777,11 +1792,10 @@ static void e100_xmit_prepare(struct nic *nic, struct cb *cb, cb->u.tcb.tcb_byte_count = 0; cb->u.tcb.threshold = nic->tx_threshold; cb->u.tcb.tbd_count = 1; - cb->u.tcb.tbd.buf_addr = cpu_to_le32(pci_map_single(nic->pdev, - skb->data, skb->len, PCI_DMA_TODEVICE)); - /* check for mapping failure? */ + cb->u.tcb.tbd.buf_addr = cpu_to_le32(dma_addr); cb->u.tcb.tbd.size = cpu_to_le16(skb->len); skb_tx_timestamp(skb); + return 0; } static netdev_tx_t e100_xmit_frame(struct sk_buff *skb, diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index c92115e71ebe..9d6c075e232d 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -293,18 +293,10 @@ struct igb_q_vector { enum e1000_ring_flags_t { IGB_RING_FLAG_RX_SCTP_CSUM, IGB_RING_FLAG_RX_LB_VLAN_BSWAP, - IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, IGB_RING_FLAG_TX_CTX_IDX, IGB_RING_FLAG_TX_DETECT_HANG }; -#define ring_uses_build_skb(ring) \ - test_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags) -#define set_ring_build_skb_enabled(ring) \ - set_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags) -#define clear_ring_build_skb_enabled(ring) \ - clear_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags) - #define IGB_TXD_DCMD (E1000_ADVTXD_DCMD_EOP | E1000_ADVTXD_DCMD_RS) #define IGB_RX_DESC(R, i) \ diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 9bf08b977daa..dcaa35481dd7 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -3387,20 +3387,6 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, wr32(E1000_RXDCTL(reg_idx), rxdctl); } -static void igb_set_rx_buffer_len(struct igb_adapter *adapter, - struct igb_ring *rx_ring) -{ -#define IGB_MAX_BUILD_SKB_SIZE \ - (SKB_WITH_OVERHEAD(IGB_RX_BUFSZ) - \ - (NET_SKB_PAD + NET_IP_ALIGN + IGB_TS_HDR_LEN)) - - /* set build_skb flag */ - if (adapter->max_frame_size <= IGB_MAX_BUILD_SKB_SIZE) - set_ring_build_skb_enabled(rx_ring); - else - clear_ring_build_skb_enabled(rx_ring); -} - /** * igb_configure_rx - Configure receive Unit after Reset * @adapter: board private structure @@ -3421,11 +3407,8 @@ static void igb_configure_rx(struct igb_adapter *adapter) /* Setup the HW Rx Head and Tail Descriptor Pointers and * the Base and Length of the Rx Descriptor Ring */ - for (i = 0; i < adapter->num_rx_queues; i++) { - struct igb_ring *rx_ring = adapter->rx_ring[i]; - igb_set_rx_buffer_len(adapter, rx_ring); - igb_configure_rx_ring(adapter, rx_ring); - } + for (i = 0; i < adapter->num_rx_queues; i++) + igb_configure_rx_ring(adapter, adapter->rx_ring[i]); } /** @@ -6238,78 +6221,6 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring, return igb_can_reuse_rx_page(rx_buffer, page, truesize); } -static struct sk_buff *igb_build_rx_buffer(struct igb_ring *rx_ring, - union e1000_adv_rx_desc *rx_desc) -{ - struct igb_rx_buffer *rx_buffer; - struct sk_buff *skb; - struct page *page; - void *page_addr; - unsigned int size = le16_to_cpu(rx_desc->wb.upper.length); -#if (PAGE_SIZE < 8192) - unsigned int truesize = IGB_RX_BUFSZ; -#else - unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + - SKB_DATA_ALIGN(NET_SKB_PAD + - NET_IP_ALIGN + - size); -#endif - - /* If we spanned a buffer we have a huge mess so test for it */ - BUG_ON(unlikely(!igb_test_staterr(rx_desc, E1000_RXD_STAT_EOP))); - - rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; - page = rx_buffer->page; - prefetchw(page); - - page_addr = page_address(page) + rx_buffer->page_offset; - - /* prefetch first cache line of first page */ - prefetch(page_addr + NET_SKB_PAD + NET_IP_ALIGN); -#if L1_CACHE_BYTES < 128 - prefetch(page_addr + L1_CACHE_BYTES + NET_SKB_PAD + NET_IP_ALIGN); -#endif - - /* build an skb to around the page buffer */ - skb = build_skb(page_addr, truesize); - if (unlikely(!skb)) { - rx_ring->rx_stats.alloc_failed++; - return NULL; - } - - /* we are reusing so sync this buffer for CPU use */ - dma_sync_single_range_for_cpu(rx_ring->dev, - rx_buffer->dma, - rx_buffer->page_offset, - IGB_RX_BUFSZ, - DMA_FROM_DEVICE); - - /* update pointers within the skb to store the data */ - skb_reserve(skb, NET_IP_ALIGN + NET_SKB_PAD); - __skb_put(skb, size); - - /* pull timestamp out of packet data */ - if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { - igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb); - __skb_pull(skb, IGB_TS_HDR_LEN); - } - - if (igb_can_reuse_rx_page(rx_buffer, page, truesize)) { - /* hand second half of page back to the ring */ - igb_reuse_rx_page(rx_ring, rx_buffer); - } else { - /* we are not reusing the buffer so unmap it */ - dma_unmap_page(rx_ring->dev, rx_buffer->dma, - PAGE_SIZE, DMA_FROM_DEVICE); - } - - /* clear contents of buffer_info */ - rx_buffer->dma = 0; - rx_buffer->page = NULL; - - return skb; -} - static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring, union e1000_adv_rx_desc *rx_desc, struct sk_buff *skb) @@ -6719,10 +6630,7 @@ static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) rmb(); /* retrieve a buffer from the ring */ - if (ring_uses_build_skb(rx_ring)) - skb = igb_build_rx_buffer(rx_ring, rx_desc); - else - skb = igb_fetch_rx_buffer(rx_ring, rx_desc, skb); + skb = igb_fetch_rx_buffer(rx_ring, rx_desc, skb); /* exit if we failed to retrieve a buffer */ if (!skb) @@ -6808,14 +6716,6 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, return true; } -static inline unsigned int igb_rx_offset(struct igb_ring *rx_ring) -{ - if (ring_uses_build_skb(rx_ring)) - return NET_SKB_PAD + NET_IP_ALIGN; - else - return 0; -} - /** * igb_alloc_rx_buffers - Replace used receive buffers; packet split * @adapter: address of board private structure @@ -6841,9 +6741,7 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) /* Refresh the desc even if buffer_addrs didn't change * because each write-back erases this info. */ - rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + - bi->page_offset + - igb_rx_offset(rx_ring)); + rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset); rx_desc++; bi++; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index 2d4bdcc4fdbe..1e7d587c4e57 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -1052,6 +1052,12 @@ int ixgbe_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos) if ((vf >= adapter->num_vfs) || (vlan > 4095) || (qos > 7)) return -EINVAL; if (vlan || qos) { + if (adapter->vfinfo[vf].pf_vlan) + err = ixgbe_set_vf_vlan(adapter, false, + adapter->vfinfo[vf].pf_vlan, + vf); + if (err) + goto out; err = ixgbe_set_vf_vlan(adapter, true, vlan, vf); if (err) goto out; diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig index 0051f0ef3cd0..a49e81bdf8e8 100644 --- a/drivers/net/ethernet/marvell/Kconfig +++ b/drivers/net/ethernet/marvell/Kconfig @@ -33,6 +33,7 @@ config MV643XX_ETH config MVMDIO tristate "Marvell MDIO interface support" + select PHYLIB ---help--- This driver supports the MDIO interface found in the network interface units of the Marvell EBU SoCs (Kirkwood, Orion5x, @@ -43,7 +44,6 @@ config MVMDIO config MVNETA tristate "Marvell Armada 370/XP network interface support" depends on MACH_ARMADA_370_XP - select PHYLIB select MVMDIO ---help--- This driver supports the network interface units in the diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index e48261e468f3..c96678555233 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -374,7 +374,6 @@ static int rxq_number = 8; static int txq_number = 8; static int rxq_def; -static int txq_def; #define MVNETA_DRIVER_NAME "mvneta" #define MVNETA_DRIVER_VERSION "1.0" @@ -1475,7 +1474,8 @@ error: static int mvneta_tx(struct sk_buff *skb, struct net_device *dev) { struct mvneta_port *pp = netdev_priv(dev); - struct mvneta_tx_queue *txq = &pp->txqs[txq_def]; + u16 txq_id = skb_get_queue_mapping(skb); + struct mvneta_tx_queue *txq = &pp->txqs[txq_id]; struct mvneta_tx_desc *tx_desc; struct netdev_queue *nq; int frags = 0; @@ -1485,7 +1485,7 @@ static int mvneta_tx(struct sk_buff *skb, struct net_device *dev) goto out; frags = skb_shinfo(skb)->nr_frags + 1; - nq = netdev_get_tx_queue(dev, txq_def); + nq = netdev_get_tx_queue(dev, txq_id); /* Get a descriptor for the first part of the packet */ tx_desc = mvneta_txq_next_desc_get(txq); @@ -2679,7 +2679,7 @@ static int mvneta_probe(struct platform_device *pdev) return -EINVAL; } - dev = alloc_etherdev_mq(sizeof(struct mvneta_port), 8); + dev = alloc_etherdev_mqs(sizeof(struct mvneta_port), txq_number, rxq_number); if (!dev) return -ENOMEM; @@ -2761,16 +2761,17 @@ static int mvneta_probe(struct platform_device *pdev) netif_napi_add(dev, &pp->napi, mvneta_poll, pp->weight); + dev->features = NETIF_F_SG | NETIF_F_IP_CSUM; + dev->hw_features |= NETIF_F_SG | NETIF_F_IP_CSUM; + dev->vlan_features |= NETIF_F_SG | NETIF_F_IP_CSUM; + dev->priv_flags |= IFF_UNICAST_FLT; + err = register_netdev(dev); if (err < 0) { dev_err(&pdev->dev, "failed to register\n"); goto err_deinit; } - dev->features = NETIF_F_SG | NETIF_F_IP_CSUM; - dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM; - dev->priv_flags |= IFF_UNICAST_FLT; - netdev_info(dev, "mac: %pM\n", dev->dev_addr); platform_set_drvdata(pdev, pp->dev); @@ -2833,4 +2834,3 @@ module_param(rxq_number, int, S_IRUGO); module_param(txq_number, int, S_IRUGO); module_param(rxq_def, int, S_IRUGO); -module_param(txq_def, int, S_IRUGO); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c index 32a95c105e4e..fd0829c2839d 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c @@ -1619,6 +1619,12 @@ int qlcnic_83xx_loopback_test(struct net_device *netdev, u8 mode) } } while ((adapter->ahw->linkup && ahw->has_link_events) != 1); + /* Make sure carrier is off and queue is stopped during loopback */ + if (netif_running(netdev)) { + netif_carrier_off(netdev); + netif_stop_queue(netdev); + } + ret = qlcnic_do_lb_test(adapter, mode); qlcnic_83xx_clear_lb_mode(adapter, mode); @@ -2944,6 +2950,7 @@ static u64 *qlcnic_83xx_fill_stats(struct qlcnic_adapter *adapter, void qlcnic_83xx_get_stats(struct qlcnic_adapter *adapter, u64 *data) { struct qlcnic_cmd_args cmd; + struct net_device *netdev = adapter->netdev; int ret = 0; qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_GET_STATISTICS); @@ -2953,7 +2960,7 @@ void qlcnic_83xx_get_stats(struct qlcnic_adapter *adapter, u64 *data) data = qlcnic_83xx_fill_stats(adapter, &cmd, data, QLC_83XX_STAT_TX, &ret); if (ret) { - dev_info(&adapter->pdev->dev, "Error getting MAC stats\n"); + netdev_err(netdev, "Error getting Tx stats\n"); goto out; } /* Get MAC stats */ @@ -2963,8 +2970,7 @@ void qlcnic_83xx_get_stats(struct qlcnic_adapter *adapter, u64 *data) data = qlcnic_83xx_fill_stats(adapter, &cmd, data, QLC_83XX_STAT_MAC, &ret); if (ret) { - dev_info(&adapter->pdev->dev, - "Error getting Rx stats\n"); + netdev_err(netdev, "Error getting MAC stats\n"); goto out; } /* Get Rx stats */ @@ -2974,8 +2980,7 @@ void qlcnic_83xx_get_stats(struct qlcnic_adapter *adapter, u64 *data) data = qlcnic_83xx_fill_stats(adapter, &cmd, data, QLC_83XX_STAT_RX, &ret); if (ret) - dev_info(&adapter->pdev->dev, - "Error getting Tx stats\n"); + netdev_err(netdev, "Error getting Rx stats\n"); out: qlcnic_free_mbx_args(&cmd); } diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c index 356859b9f21c..d3f8797efcc3 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c @@ -362,8 +362,7 @@ set_flags: memcpy(&first_desc->eth_addr, skb->data, ETH_ALEN); } opcode = TX_ETHER_PKT; - if ((adapter->netdev->features & (NETIF_F_TSO | NETIF_F_TSO6)) && - skb_shinfo(skb)->gso_size > 0) { + if (skb_is_gso(skb)) { hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb); first_desc->mss = cpu_to_le16(skb_shinfo(skb)->gso_size); first_desc->total_hdr_length = hdr_len; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c index c77675da671f..4e22e794a186 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c @@ -198,10 +198,10 @@ beacon_err: } err = qlcnic_config_led(adapter, b_state, b_rate); - if (!err) + if (!err) { err = len; - else ahw->beacon_state = b_state; + } if (test_and_clear_bit(__QLCNIC_DIAG_RES_ALLOC, &adapter->state)) qlcnic_diag_free_res(adapter->netdev, max_sds_rings); diff --git a/drivers/net/ethernet/qlogic/qlge/qlge.h b/drivers/net/ethernet/qlogic/qlge/qlge.h index a131d7b5d2fe..7e8d68263963 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge.h +++ b/drivers/net/ethernet/qlogic/qlge/qlge.h @@ -18,7 +18,7 @@ */ #define DRV_NAME "qlge" #define DRV_STRING "QLogic 10 Gigabit PCI-E Ethernet Driver " -#define DRV_VERSION "v1.00.00.31" +#define DRV_VERSION "v1.00.00.32" #define WQ_ADDR_ALIGN 0x3 /* 4 byte alignment */ diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c b/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c index 6f316ab23257..0780e039b271 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c @@ -379,13 +379,13 @@ static int ql_get_settings(struct net_device *ndev, ecmd->supported = SUPPORTED_10000baseT_Full; ecmd->advertising = ADVERTISED_10000baseT_Full; - ecmd->autoneg = AUTONEG_ENABLE; ecmd->transceiver = XCVR_EXTERNAL; if ((qdev->link_status & STS_LINK_TYPE_MASK) == STS_LINK_TYPE_10GBASET) { ecmd->supported |= (SUPPORTED_TP | SUPPORTED_Autoneg); ecmd->advertising |= (ADVERTISED_TP | ADVERTISED_Autoneg); ecmd->port = PORT_TP; + ecmd->autoneg = AUTONEG_ENABLE; } else { ecmd->supported |= SUPPORTED_FIBRE; ecmd->advertising |= ADVERTISED_FIBRE; diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c index 44cf72ac2489..87463bc701a6 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c @@ -1432,11 +1432,13 @@ map_error: } /* Categorizing receive firmware frame errors */ -static void ql_categorize_rx_err(struct ql_adapter *qdev, u8 rx_err) +static void ql_categorize_rx_err(struct ql_adapter *qdev, u8 rx_err, + struct rx_ring *rx_ring) { struct nic_stats *stats = &qdev->nic_stats; stats->rx_err_count++; + rx_ring->rx_errors++; switch (rx_err & IB_MAC_IOCB_RSP_ERR_MASK) { case IB_MAC_IOCB_RSP_ERR_CODE_ERR: @@ -1472,6 +1474,12 @@ static void ql_process_mac_rx_gro_page(struct ql_adapter *qdev, struct bq_desc *lbq_desc = ql_get_curr_lchunk(qdev, rx_ring); struct napi_struct *napi = &rx_ring->napi; + /* Frame error, so drop the packet. */ + if (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_ERR_MASK) { + ql_categorize_rx_err(qdev, ib_mac_rsp->flags2, rx_ring); + put_page(lbq_desc->p.pg_chunk.page); + return; + } napi->dev = qdev->ndev; skb = napi_get_frags(napi); @@ -1525,6 +1533,12 @@ static void ql_process_mac_rx_page(struct ql_adapter *qdev, addr = lbq_desc->p.pg_chunk.va; prefetch(addr); + /* Frame error, so drop the packet. */ + if (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_ERR_MASK) { + ql_categorize_rx_err(qdev, ib_mac_rsp->flags2, rx_ring); + goto err_out; + } + /* The max framesize filter on this chip is set higher than * MTU since FCoE uses 2k frames. */ @@ -1608,6 +1622,13 @@ static void ql_process_mac_rx_skb(struct ql_adapter *qdev, memcpy(skb_put(new_skb, length), skb->data, length); skb = new_skb; + /* Frame error, so drop the packet. */ + if (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_ERR_MASK) { + ql_categorize_rx_err(qdev, ib_mac_rsp->flags2, rx_ring); + dev_kfree_skb_any(skb); + return; + } + /* loopback self test for ethtool */ if (test_bit(QL_SELFTEST, &qdev->flags)) { ql_check_lb_frame(qdev, skb); @@ -1913,6 +1934,13 @@ static void ql_process_mac_split_rx_intr(struct ql_adapter *qdev, return; } + /* Frame error, so drop the packet. */ + if (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_ERR_MASK) { + ql_categorize_rx_err(qdev, ib_mac_rsp->flags2, rx_ring); + dev_kfree_skb_any(skb); + return; + } + /* The max framesize filter on this chip is set higher than * MTU since FCoE uses 2k frames. */ @@ -1994,12 +2022,6 @@ static unsigned long ql_process_mac_rx_intr(struct ql_adapter *qdev, QL_DUMP_IB_MAC_RSP(ib_mac_rsp); - /* Frame error, so drop the packet. */ - if (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_ERR_MASK) { - ql_categorize_rx_err(qdev, ib_mac_rsp->flags2); - return (unsigned long)length; - } - if (ib_mac_rsp->flags4 & IB_MAC_IOCB_RSP_HV) { /* The data and headers are split into * separate buffers. diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c index 0c74a702d461..50617c5a0bdb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c @@ -149,6 +149,7 @@ void dwmac_mmc_intr_all_mask(void __iomem *ioaddr) { writel(MMC_DEFAULT_MASK, ioaddr + MMC_RX_INTR_MASK); writel(MMC_DEFAULT_MASK, ioaddr + MMC_TX_INTR_MASK); + writel(MMC_DEFAULT_MASK, ioaddr + MMC_RX_IPC_INTR_MASK); } /* This reads the MAC core counters (if actaully supported). diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 5cf8d03b8cae..25c364209a21 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -1520,7 +1520,7 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, memcpy(slave_data->mac_addr, mac_addr, ETH_ALEN); if (data->dual_emac) { - if (of_property_read_u32(node, "dual_emac_res_vlan", + if (of_property_read_u32(slave_node, "dual_emac_res_vlan", &prop)) { pr_err("Missing dual_emac_res_vlan in DT.\n"); slave_data->dual_emac_res_vlan = i+1; diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 1cd77483da50..f5f0f09e4cc5 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -470,8 +470,10 @@ static void netvsc_send_completion(struct hv_device *device, packet->trans_id; /* Notify the layer above us */ - nvsc_packet->completion.send.send_completion( - nvsc_packet->completion.send.send_completion_ctx); + if (nvsc_packet) + nvsc_packet->completion.send.send_completion( + nvsc_packet->completion.send. + send_completion_ctx); num_outstanding_sends = atomic_dec_return(&net_device->num_outstanding_sends); @@ -498,6 +500,7 @@ int netvsc_send(struct hv_device *device, int ret = 0; struct nvsp_message sendMessage; struct net_device *ndev; + u64 req_id; net_device = get_outbound_net_device(device); if (!net_device) @@ -518,20 +521,24 @@ int netvsc_send(struct hv_device *device, 0xFFFFFFFF; sendMessage.msg.v1_msg.send_rndis_pkt.send_buf_section_size = 0; + if (packet->completion.send.send_completion) + req_id = (u64)packet; + else + req_id = 0; + if (packet->page_buf_cnt) { ret = vmbus_sendpacket_pagebuffer(device->channel, packet->page_buf, packet->page_buf_cnt, &sendMessage, sizeof(struct nvsp_message), - (unsigned long)packet); + req_id); } else { ret = vmbus_sendpacket(device->channel, &sendMessage, sizeof(struct nvsp_message), - (unsigned long)packet, + req_id, VM_PKT_DATA_INBAND, VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); - } if (ret == 0) { diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 4559bb8115bf..088c55496191 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -241,13 +241,11 @@ void netvsc_linkstatus_callback(struct hv_device *device_obj, if (status == 1) { netif_carrier_on(net); - netif_wake_queue(net); ndev_ctx = netdev_priv(net); schedule_delayed_work(&ndev_ctx->dwork, 0); schedule_delayed_work(&ndev_ctx->dwork, msecs_to_jiffies(20)); } else { netif_carrier_off(net); - netif_tx_disable(net); } } diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index 2b657d4d63a8..0775f0aefd1e 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -61,9 +61,6 @@ struct rndis_request { static void rndis_filter_send_completion(void *ctx); -static void rndis_filter_send_request_completion(void *ctx); - - static struct rndis_device *get_rndis_device(void) { @@ -241,10 +238,7 @@ static int rndis_filter_send_request(struct rndis_device *dev, packet->page_buf[0].len; } - packet->completion.send.send_completion_ctx = req;/* packet; */ - packet->completion.send.send_completion = - rndis_filter_send_request_completion; - packet->completion.send.send_completion_tid = (unsigned long)dev; + packet->completion.send.send_completion = NULL; ret = netvsc_send(dev->net_dev->dev, packet); return ret; @@ -999,9 +993,3 @@ static void rndis_filter_send_completion(void *ctx) /* Pass it back to the original handler */ filter_pkt->completion(filter_pkt->completion_ctx); } - - -static void rndis_filter_send_request_completion(void *ctx) -{ - /* Noop */ -} diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 316c759bd988..66109a2ad886 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1594,7 +1594,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) if (tun->flags & TUN_TAP_MQ && (tun->numqueues + tun->numdisabled > 1)) - return err; + return -EBUSY; } else { char *name; diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c index cc6dfe4102fd..c96454434f7b 100644 --- a/drivers/net/usb/cdc_mbim.c +++ b/drivers/net/usb/cdc_mbim.c @@ -134,7 +134,7 @@ static struct sk_buff *cdc_mbim_tx_fixup(struct usbnet *dev, struct sk_buff *skb goto error; if (skb) { - if (skb->len <= sizeof(ETH_HLEN)) + if (skb->len <= ETH_HLEN) goto error; /* mapping VLANs to MBIM sessions: diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 968d5d50751d..2a3579f67910 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -52,6 +53,96 @@ struct qmi_wwan_state { struct usb_interface *data; }; +/* default ethernet address used by the modem */ +static const u8 default_modem_addr[ETH_ALEN] = {0x02, 0x50, 0xf3}; + +/* Make up an ethernet header if the packet doesn't have one. + * + * A firmware bug common among several devices cause them to send raw + * IP packets under some circumstances. There is no way for the + * driver/host to know when this will happen. And even when the bug + * hits, some packets will still arrive with an intact header. + * + * The supported devices are only capably of sending IPv4, IPv6 and + * ARP packets on a point-to-point link. Any packet with an ethernet + * header will have either our address or a broadcast/multicast + * address as destination. ARP packets will always have a header. + * + * This means that this function will reliably add the appropriate + * header iff necessary, provided our hardware address does not start + * with 4 or 6. + * + * Another common firmware bug results in all packets being addressed + * to 00:a0:c6:00:00:00 despite the host address being different. + * This function will also fixup such packets. + */ +static int qmi_wwan_rx_fixup(struct usbnet *dev, struct sk_buff *skb) +{ + __be16 proto; + + /* usbnet rx_complete guarantees that skb->len is at least + * hard_header_len, so we can inspect the dest address without + * checking skb->len + */ + switch (skb->data[0] & 0xf0) { + case 0x40: + proto = htons(ETH_P_IP); + break; + case 0x60: + proto = htons(ETH_P_IPV6); + break; + case 0x00: + if (is_multicast_ether_addr(skb->data)) + return 1; + /* possibly bogus destination - rewrite just in case */ + skb_reset_mac_header(skb); + goto fix_dest; + default: + /* pass along other packets without modifications */ + return 1; + } + if (skb_headroom(skb) < ETH_HLEN) + return 0; + skb_push(skb, ETH_HLEN); + skb_reset_mac_header(skb); + eth_hdr(skb)->h_proto = proto; + memset(eth_hdr(skb)->h_source, 0, ETH_ALEN); +fix_dest: + memcpy(eth_hdr(skb)->h_dest, dev->net->dev_addr, ETH_ALEN); + return 1; +} + +/* very simplistic detection of IPv4 or IPv6 headers */ +static bool possibly_iphdr(const char *data) +{ + return (data[0] & 0xd0) == 0x40; +} + +/* disallow addresses which may be confused with IP headers */ +static int qmi_wwan_mac_addr(struct net_device *dev, void *p) +{ + int ret; + struct sockaddr *addr = p; + + ret = eth_prepare_mac_addr_change(dev, p); + if (ret < 0) + return ret; + if (possibly_iphdr(addr->sa_data)) + return -EADDRNOTAVAIL; + eth_commit_mac_addr_change(dev, p); + return 0; +} + +static const struct net_device_ops qmi_wwan_netdev_ops = { + .ndo_open = usbnet_open, + .ndo_stop = usbnet_stop, + .ndo_start_xmit = usbnet_start_xmit, + .ndo_tx_timeout = usbnet_tx_timeout, + .ndo_change_mtu = usbnet_change_mtu, + .ndo_set_mac_address = qmi_wwan_mac_addr, + .ndo_validate_addr = eth_validate_addr, +}; + /* using a counter to merge subdriver requests with our own into a combined state */ static int qmi_wwan_manage_power(struct usbnet *dev, int on) { @@ -229,6 +320,18 @@ next_desc: usb_driver_release_interface(driver, info->data); } + /* Never use the same address on both ends of the link, even + * if the buggy firmware told us to. + */ + if (!compare_ether_addr(dev->net->dev_addr, default_modem_addr)) + eth_hw_addr_random(dev->net); + + /* make MAC addr easily distinguishable from an IP header */ + if (possibly_iphdr(dev->net->dev_addr)) { + dev->net->dev_addr[0] |= 0x02; /* set local assignment bit */ + dev->net->dev_addr[0] &= 0xbf; /* clear "IP" bit */ + } + dev->net->netdev_ops = &qmi_wwan_netdev_ops; err: return status; } @@ -307,6 +410,7 @@ static const struct driver_info qmi_wwan_info = { .bind = qmi_wwan_bind, .unbind = qmi_wwan_unbind, .manage_power = qmi_wwan_manage_power, + .rx_fixup = qmi_wwan_rx_fixup, }; #define HUAWEI_VENDOR_ID 0x12D1 diff --git a/drivers/net/wireless/ath/ath9k/ar9580_1p0_initvals.h b/drivers/net/wireless/ath/ath9k/ar9580_1p0_initvals.h index 28fd99203f64..bdee2ed67219 100644 --- a/drivers/net/wireless/ath/ath9k/ar9580_1p0_initvals.h +++ b/drivers/net/wireless/ath/ath9k/ar9580_1p0_initvals.h @@ -519,7 +519,7 @@ static const u32 ar9580_1p0_mac_core[][2] = { {0x00008258, 0x00000000}, {0x0000825c, 0x40000000}, {0x00008260, 0x00080922}, - {0x00008264, 0x9bc00010}, + {0x00008264, 0x9d400010}, {0x00008268, 0xffffffff}, {0x0000826c, 0x0000ffff}, {0x00008270, 0x00000000}, diff --git a/drivers/net/wireless/ath/ath9k/dfs_pattern_detector.c b/drivers/net/wireless/ath/ath9k/dfs_pattern_detector.c index 467b60014b7b..73fe8d6db566 100644 --- a/drivers/net/wireless/ath/ath9k/dfs_pattern_detector.c +++ b/drivers/net/wireless/ath/ath9k/dfs_pattern_detector.c @@ -143,14 +143,14 @@ channel_detector_create(struct dfs_pattern_detector *dpd, u16 freq) u32 sz, i; struct channel_detector *cd; - cd = kmalloc(sizeof(*cd), GFP_KERNEL); + cd = kmalloc(sizeof(*cd), GFP_ATOMIC); if (cd == NULL) goto fail; INIT_LIST_HEAD(&cd->head); cd->freq = freq; sz = sizeof(cd->detectors) * dpd->num_radar_types; - cd->detectors = kzalloc(sz, GFP_KERNEL); + cd->detectors = kzalloc(sz, GFP_ATOMIC); if (cd->detectors == NULL) goto fail; diff --git a/drivers/net/wireless/ath/ath9k/dfs_pri_detector.c b/drivers/net/wireless/ath/ath9k/dfs_pri_detector.c index 91b8dceeadb1..5e48c5515b8c 100644 --- a/drivers/net/wireless/ath/ath9k/dfs_pri_detector.c +++ b/drivers/net/wireless/ath/ath9k/dfs_pri_detector.c @@ -218,7 +218,7 @@ static bool pulse_queue_enqueue(struct pri_detector *pde, u64 ts) { struct pulse_elem *p = pool_get_pulse_elem(); if (p == NULL) { - p = kmalloc(sizeof(*p), GFP_KERNEL); + p = kmalloc(sizeof(*p), GFP_ATOMIC); if (p == NULL) { DFS_POOL_STAT_INC(pulse_alloc_error); return false; @@ -299,7 +299,7 @@ static bool pseq_handler_create_sequences(struct pri_detector *pde, ps.deadline_ts = ps.first_ts + ps.dur; new_ps = pool_get_pseq_elem(); if (new_ps == NULL) { - new_ps = kmalloc(sizeof(*new_ps), GFP_KERNEL); + new_ps = kmalloc(sizeof(*new_ps), GFP_ATOMIC); if (new_ps == NULL) { DFS_POOL_STAT_INC(pseq_alloc_error); return false; diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_init.c b/drivers/net/wireless/ath/ath9k/htc_drv_init.c index 716058b67557..a47f5e05fc04 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_init.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_init.c @@ -796,7 +796,7 @@ static int ath9k_init_firmware_version(struct ath9k_htc_priv *priv) * required version. */ if (priv->fw_version_major != MAJOR_VERSION_REQ || - priv->fw_version_minor != MINOR_VERSION_REQ) { + priv->fw_version_minor < MINOR_VERSION_REQ) { dev_err(priv->dev, "ath9k_htc: Please upgrade to FW version %d.%d\n", MAJOR_VERSION_REQ, MINOR_VERSION_REQ); return -EINVAL; diff --git a/drivers/net/wireless/b43/phy_n.c b/drivers/net/wireless/b43/phy_n.c index f9339e7ea6af..63cca9c2bf97 100644 --- a/drivers/net/wireless/b43/phy_n.c +++ b/drivers/net/wireless/b43/phy_n.c @@ -5161,7 +5161,8 @@ static void b43_nphy_pmu_spur_avoid(struct b43_wldev *dev, bool avoid) #endif #ifdef CONFIG_B43_SSB case B43_BUS_SSB: - /* FIXME */ + ssb_pmu_spuravoid_pllupdate(&dev->dev->sdev->bus->chipco, + avoid); break; #endif } diff --git a/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c b/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c index 62699203869d..e4f1f3c9575a 100644 --- a/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c +++ b/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c @@ -4076,10 +4076,6 @@ static const struct ieee80211_iface_limit brcmf_iface_limits[] = { BIT(NL80211_IFTYPE_ADHOC) | BIT(NL80211_IFTYPE_AP) }, - { - .max = 1, - .types = BIT(NL80211_IFTYPE_P2P_DEVICE) - }, { .max = 1, .types = BIT(NL80211_IFTYPE_P2P_CLIENT) | @@ -4142,8 +4138,7 @@ static struct wiphy *brcmf_setup_wiphy(struct device *phydev) BIT(NL80211_IFTYPE_ADHOC) | BIT(NL80211_IFTYPE_AP) | BIT(NL80211_IFTYPE_P2P_CLIENT) | - BIT(NL80211_IFTYPE_P2P_GO) | - BIT(NL80211_IFTYPE_P2P_DEVICE); + BIT(NL80211_IFTYPE_P2P_GO); wiphy->iface_combinations = brcmf_iface_combos; wiphy->n_iface_combinations = ARRAY_SIZE(brcmf_iface_combos); wiphy->bands[IEEE80211_BAND_2GHZ] = &__wl_band_2ghz; diff --git a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c index cd837860cd42..c837be242cba 100644 --- a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c +++ b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c @@ -276,6 +276,130 @@ static void brcms_set_basic_rate(struct brcm_rateset *rs, u16 rate, bool is_br) } } +/** + * This function frees the WL per-device resources. + * + * This function frees resources owned by the WL device pointed to + * by the wl parameter. + * + * precondition: can both be called locked and unlocked + * + */ +static void brcms_free(struct brcms_info *wl) +{ + struct brcms_timer *t, *next; + + /* free ucode data */ + if (wl->fw.fw_cnt) + brcms_ucode_data_free(&wl->ucode); + if (wl->irq) + free_irq(wl->irq, wl); + + /* kill dpc */ + tasklet_kill(&wl->tasklet); + + if (wl->pub) { + brcms_debugfs_detach(wl->pub); + brcms_c_module_unregister(wl->pub, "linux", wl); + } + + /* free common resources */ + if (wl->wlc) { + brcms_c_detach(wl->wlc); + wl->wlc = NULL; + wl->pub = NULL; + } + + /* virtual interface deletion is deferred so we cannot spinwait */ + + /* wait for all pending callbacks to complete */ + while (atomic_read(&wl->callbacks) > 0) + schedule(); + + /* free timers */ + for (t = wl->timers; t; t = next) { + next = t->next; +#ifdef DEBUG + kfree(t->name); +#endif + kfree(t); + } +} + +/* +* called from both kernel as from this kernel module (error flow on attach) +* precondition: perimeter lock is not acquired. +*/ +static void brcms_remove(struct bcma_device *pdev) +{ + struct ieee80211_hw *hw = bcma_get_drvdata(pdev); + struct brcms_info *wl = hw->priv; + + if (wl->wlc) { + wiphy_rfkill_set_hw_state(wl->pub->ieee_hw->wiphy, false); + wiphy_rfkill_stop_polling(wl->pub->ieee_hw->wiphy); + ieee80211_unregister_hw(hw); + } + + brcms_free(wl); + + bcma_set_drvdata(pdev, NULL); + ieee80211_free_hw(hw); +} + +/* + * Precondition: Since this function is called in brcms_pci_probe() context, + * no locking is required. + */ +static void brcms_release_fw(struct brcms_info *wl) +{ + int i; + for (i = 0; i < MAX_FW_IMAGES; i++) { + release_firmware(wl->fw.fw_bin[i]); + release_firmware(wl->fw.fw_hdr[i]); + } +} + +/* + * Precondition: Since this function is called in brcms_pci_probe() context, + * no locking is required. + */ +static int brcms_request_fw(struct brcms_info *wl, struct bcma_device *pdev) +{ + int status; + struct device *device = &pdev->dev; + char fw_name[100]; + int i; + + memset(&wl->fw, 0, sizeof(struct brcms_firmware)); + for (i = 0; i < MAX_FW_IMAGES; i++) { + if (brcms_firmwares[i] == NULL) + break; + sprintf(fw_name, "%s-%d.fw", brcms_firmwares[i], + UCODE_LOADER_API_VER); + status = request_firmware(&wl->fw.fw_bin[i], fw_name, device); + if (status) { + wiphy_err(wl->wiphy, "%s: fail to load firmware %s\n", + KBUILD_MODNAME, fw_name); + return status; + } + sprintf(fw_name, "%s_hdr-%d.fw", brcms_firmwares[i], + UCODE_LOADER_API_VER); + status = request_firmware(&wl->fw.fw_hdr[i], fw_name, device); + if (status) { + wiphy_err(wl->wiphy, "%s: fail to load firmware %s\n", + KBUILD_MODNAME, fw_name); + return status; + } + wl->fw.hdr_num_entries[i] = + wl->fw.fw_hdr[i]->size / (sizeof(struct firmware_hdr)); + } + wl->fw.fw_cnt = i; + status = brcms_ucode_data_init(wl, &wl->ucode); + brcms_release_fw(wl); + return status; +} + static void brcms_ops_tx(struct ieee80211_hw *hw, struct ieee80211_tx_control *control, struct sk_buff *skb) @@ -308,6 +432,14 @@ static int brcms_ops_start(struct ieee80211_hw *hw) if (!blocked) wiphy_rfkill_stop_polling(wl->pub->ieee_hw->wiphy); + if (!wl->ucode.bcm43xx_bomminor) { + err = brcms_request_fw(wl, wl->wlc->hw->d11core); + if (err) { + brcms_remove(wl->wlc->hw->d11core); + return -ENOENT; + } + } + spin_lock_bh(&wl->lock); /* avoid acknowledging frames before a non-monitor device is added */ wl->mute_tx = true; @@ -856,129 +988,6 @@ void brcms_dpc(unsigned long data) wake_up(&wl->tx_flush_wq); } -/* - * Precondition: Since this function is called in brcms_pci_probe() context, - * no locking is required. - */ -static int brcms_request_fw(struct brcms_info *wl, struct bcma_device *pdev) -{ - int status; - struct device *device = &pdev->dev; - char fw_name[100]; - int i; - - memset(&wl->fw, 0, sizeof(struct brcms_firmware)); - for (i = 0; i < MAX_FW_IMAGES; i++) { - if (brcms_firmwares[i] == NULL) - break; - sprintf(fw_name, "%s-%d.fw", brcms_firmwares[i], - UCODE_LOADER_API_VER); - status = request_firmware(&wl->fw.fw_bin[i], fw_name, device); - if (status) { - wiphy_err(wl->wiphy, "%s: fail to load firmware %s\n", - KBUILD_MODNAME, fw_name); - return status; - } - sprintf(fw_name, "%s_hdr-%d.fw", brcms_firmwares[i], - UCODE_LOADER_API_VER); - status = request_firmware(&wl->fw.fw_hdr[i], fw_name, device); - if (status) { - wiphy_err(wl->wiphy, "%s: fail to load firmware %s\n", - KBUILD_MODNAME, fw_name); - return status; - } - wl->fw.hdr_num_entries[i] = - wl->fw.fw_hdr[i]->size / (sizeof(struct firmware_hdr)); - } - wl->fw.fw_cnt = i; - return brcms_ucode_data_init(wl, &wl->ucode); -} - -/* - * Precondition: Since this function is called in brcms_pci_probe() context, - * no locking is required. - */ -static void brcms_release_fw(struct brcms_info *wl) -{ - int i; - for (i = 0; i < MAX_FW_IMAGES; i++) { - release_firmware(wl->fw.fw_bin[i]); - release_firmware(wl->fw.fw_hdr[i]); - } -} - -/** - * This function frees the WL per-device resources. - * - * This function frees resources owned by the WL device pointed to - * by the wl parameter. - * - * precondition: can both be called locked and unlocked - * - */ -static void brcms_free(struct brcms_info *wl) -{ - struct brcms_timer *t, *next; - - /* free ucode data */ - if (wl->fw.fw_cnt) - brcms_ucode_data_free(&wl->ucode); - if (wl->irq) - free_irq(wl->irq, wl); - - /* kill dpc */ - tasklet_kill(&wl->tasklet); - - if (wl->pub) { - brcms_debugfs_detach(wl->pub); - brcms_c_module_unregister(wl->pub, "linux", wl); - } - - /* free common resources */ - if (wl->wlc) { - brcms_c_detach(wl->wlc); - wl->wlc = NULL; - wl->pub = NULL; - } - - /* virtual interface deletion is deferred so we cannot spinwait */ - - /* wait for all pending callbacks to complete */ - while (atomic_read(&wl->callbacks) > 0) - schedule(); - - /* free timers */ - for (t = wl->timers; t; t = next) { - next = t->next; -#ifdef DEBUG - kfree(t->name); -#endif - kfree(t); - } -} - -/* -* called from both kernel as from this kernel module (error flow on attach) -* precondition: perimeter lock is not acquired. -*/ -static void brcms_remove(struct bcma_device *pdev) -{ - struct ieee80211_hw *hw = bcma_get_drvdata(pdev); - struct brcms_info *wl = hw->priv; - - if (wl->wlc) { - brcms_led_unregister(wl); - wiphy_rfkill_set_hw_state(wl->pub->ieee_hw->wiphy, false); - wiphy_rfkill_stop_polling(wl->pub->ieee_hw->wiphy); - ieee80211_unregister_hw(hw); - } - - brcms_free(wl); - - bcma_set_drvdata(pdev, NULL); - ieee80211_free_hw(hw); -} - static irqreturn_t brcms_isr(int irq, void *dev_id) { struct brcms_info *wl; @@ -1120,18 +1129,8 @@ static struct brcms_info *brcms_attach(struct bcma_device *pdev) spin_lock_init(&wl->lock); spin_lock_init(&wl->isr_lock); - /* prepare ucode */ - if (brcms_request_fw(wl, pdev) < 0) { - wiphy_err(wl->wiphy, "%s: Failed to find firmware usually in " - "%s\n", KBUILD_MODNAME, "/lib/firmware/brcm"); - brcms_release_fw(wl); - brcms_remove(pdev); - return NULL; - } - /* common load-time initialization */ wl->wlc = brcms_c_attach((void *)wl, pdev, unit, false, &err); - brcms_release_fw(wl); if (!wl->wlc) { wiphy_err(wl->wiphy, "%s: attach() failed with code %d\n", KBUILD_MODNAME, err); diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index dee5dddaa292..5147c210df52 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -53,14 +53,15 @@ static void pci_acpi_wake_dev(acpi_handle handle, u32 event, void *context) return; } - if (!pci_dev->pm_cap || !pci_dev->pme_support - || pci_check_pme_status(pci_dev)) { - if (pci_dev->pme_poll) - pci_dev->pme_poll = false; + /* Clear PME Status if set. */ + if (pci_dev->pme_support) + pci_check_pme_status(pci_dev); - pci_wakeup_event(pci_dev); - pm_runtime_resume(&pci_dev->dev); - } + if (pci_dev->pme_poll) + pci_dev->pme_poll = false; + + pci_wakeup_event(pci_dev); + pm_runtime_resume(&pci_dev->dev); if (pci_dev->subordinate) pci_pme_wakeup_bus(pci_dev->subordinate); diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 1fa1e482a999..79277fb36c6b 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -390,9 +390,10 @@ static void pci_device_shutdown(struct device *dev) /* * Turn off Bus Master bit on the device to tell it to not - * continue to do DMA + * continue to do DMA. Don't touch devices in D3cold or unknown states. */ - pci_clear_master(pci_dev); + if (pci_dev->current_state <= PCI_D3hot) + pci_clear_master(pci_dev); } #ifdef CONFIG_PM diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c index 08c243ab034e..ed4d09498337 100644 --- a/drivers/pci/pcie/portdrv_pci.c +++ b/drivers/pci/pcie/portdrv_pci.c @@ -184,14 +184,6 @@ static const struct dev_pm_ops pcie_portdrv_pm_ops = { #define PCIE_PORTDRV_PM_OPS NULL #endif /* !PM */ -/* - * PCIe port runtime suspend is broken for some chipsets, so use a - * black list to disable runtime PM for these chipsets. - */ -static const struct pci_device_id port_runtime_pm_black_list[] = { - { /* end: all zeroes */ } -}; - /* * pcie_portdrv_probe - Probe PCI-Express port devices * @dev: PCI-Express port device being probed @@ -225,16 +217,11 @@ static int pcie_portdrv_probe(struct pci_dev *dev, * it by default. */ dev->d3cold_allowed = false; - if (!pci_match_id(port_runtime_pm_black_list, dev)) - pm_runtime_put_noidle(&dev->dev); - return 0; } static void pcie_portdrv_remove(struct pci_dev *dev) { - if (!pci_match_id(port_runtime_pm_black_list, dev)) - pm_runtime_get_noresume(&dev->dev); pcie_port_device_remove(dev); pci_disable_device(dev); } diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c index b41ac7756a4b..c5d0a08a8747 100644 --- a/drivers/pci/rom.c +++ b/drivers/pci/rom.c @@ -100,27 +100,6 @@ size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size) return min((size_t)(image - rom), size); } -static loff_t pci_find_rom(struct pci_dev *pdev, size_t *size) -{ - struct resource *res = &pdev->resource[PCI_ROM_RESOURCE]; - loff_t start; - - /* assign the ROM an address if it doesn't have one */ - if (res->parent == NULL && pci_assign_resource(pdev, PCI_ROM_RESOURCE)) - return 0; - start = pci_resource_start(pdev, PCI_ROM_RESOURCE); - *size = pci_resource_len(pdev, PCI_ROM_RESOURCE); - - if (*size == 0) - return 0; - - /* Enable ROM space decodes */ - if (pci_enable_rom(pdev)) - return 0; - - return start; -} - /** * pci_map_rom - map a PCI ROM to kernel space * @pdev: pointer to pci device struct @@ -135,7 +114,7 @@ static loff_t pci_find_rom(struct pci_dev *pdev, size_t *size) void __iomem *pci_map_rom(struct pci_dev *pdev, size_t *size) { struct resource *res = &pdev->resource[PCI_ROM_RESOURCE]; - loff_t start = 0; + loff_t start; void __iomem *rom; /* @@ -154,21 +133,21 @@ void __iomem *pci_map_rom(struct pci_dev *pdev, size_t *size) return (void __iomem *)(unsigned long) pci_resource_start(pdev, PCI_ROM_RESOURCE); } else { - start = pci_find_rom(pdev, size); + /* assign the ROM an address if it doesn't have one */ + if (res->parent == NULL && + pci_assign_resource(pdev,PCI_ROM_RESOURCE)) + return NULL; + start = pci_resource_start(pdev, PCI_ROM_RESOURCE); + *size = pci_resource_len(pdev, PCI_ROM_RESOURCE); + if (*size == 0) + return NULL; + + /* Enable ROM space decodes */ + if (pci_enable_rom(pdev)) + return NULL; } } - /* - * Some devices may provide ROMs via a source other than the BAR - */ - if (!start && pdev->rom && pdev->romlen) { - *size = pdev->romlen; - return phys_to_virt(pdev->rom); - } - - if (!start) - return NULL; - rom = ioremap(start, *size); if (!rom) { /* restore enable if ioremap fails */ @@ -202,8 +181,7 @@ void pci_unmap_rom(struct pci_dev *pdev, void __iomem *rom) if (res->flags & (IORESOURCE_ROM_COPY | IORESOURCE_ROM_BIOS_COPY)) return; - if (!pdev->rom || !pdev->romlen) - iounmap(rom); + iounmap(rom); /* Disable again before continuing, leave enabled if pci=rom */ if (!(res->flags & (IORESOURCE_ROM_ENABLE | IORESOURCE_ROM_SHADOW))) @@ -227,7 +205,24 @@ void pci_cleanup_rom(struct pci_dev *pdev) } } +/** + * pci_platform_rom - provides a pointer to any ROM image provided by the + * platform + * @pdev: pointer to pci device struct + * @size: pointer to receive size of pci window over ROM + */ +void __iomem *pci_platform_rom(struct pci_dev *pdev, size_t *size) +{ + if (pdev->rom && pdev->romlen) { + *size = pdev->romlen; + return phys_to_virt((phys_addr_t)pdev->rom); + } + + return NULL; +} + EXPORT_SYMBOL(pci_map_rom); EXPORT_SYMBOL(pci_unmap_rom); EXPORT_SYMBOL_GPL(pci_enable_rom); EXPORT_SYMBOL_GPL(pci_disable_rom); +EXPORT_SYMBOL(pci_platform_rom); diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c index 45cacf79f3a7..1a779bbfb87d 100644 --- a/drivers/platform/x86/hp-wmi.c +++ b/drivers/platform/x86/hp-wmi.c @@ -134,7 +134,6 @@ static const struct key_entry hp_wmi_keymap[] = { { KE_KEY, 0x2142, { KEY_MEDIA } }, { KE_KEY, 0x213b, { KEY_INFO } }, { KE_KEY, 0x2169, { KEY_DIRECTION } }, - { KE_KEY, 0x216a, { KEY_SETUP } }, { KE_KEY, 0x231b, { KEY_HELP } }, { KE_END, 0 } }; @@ -925,9 +924,6 @@ static int __init hp_wmi_init(void) err = hp_wmi_input_setup(); if (err) return err; - - //Enable magic for hotkeys that run on the SMBus - ec_write(0xe6,0x6e); } if (bios_capable) { diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 9a907567f41e..edec135b1685 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -1964,9 +1964,6 @@ struct tp_nvram_state { /* kthread for the hotkey poller */ static struct task_struct *tpacpi_hotkey_task; -/* Acquired while the poller kthread is running, use to sync start/stop */ -static struct mutex hotkey_thread_mutex; - /* * Acquire mutex to write poller control variables as an * atomic block. @@ -2462,8 +2459,6 @@ static int hotkey_kthread(void *data) unsigned int poll_freq; bool was_frozen; - mutex_lock(&hotkey_thread_mutex); - if (tpacpi_lifecycle == TPACPI_LIFE_EXITING) goto exit; @@ -2523,7 +2518,6 @@ static int hotkey_kthread(void *data) } exit: - mutex_unlock(&hotkey_thread_mutex); return 0; } @@ -2533,9 +2527,6 @@ static void hotkey_poll_stop_sync(void) if (tpacpi_hotkey_task) { kthread_stop(tpacpi_hotkey_task); tpacpi_hotkey_task = NULL; - mutex_lock(&hotkey_thread_mutex); - /* at this point, the thread did exit */ - mutex_unlock(&hotkey_thread_mutex); } } @@ -3234,7 +3225,6 @@ static int __init hotkey_init(struct ibm_init_struct *iibm) mutex_init(&hotkey_mutex); #ifdef CONFIG_THINKPAD_ACPI_HOTKEY_POLL - mutex_init(&hotkey_thread_mutex); mutex_init(&hotkey_thread_data_mutex); #endif diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig index cc1f7bf53fd0..c6d77e20622c 100644 --- a/drivers/remoteproc/Kconfig +++ b/drivers/remoteproc/Kconfig @@ -4,7 +4,7 @@ menu "Remoteproc drivers" config REMOTEPROC tristate depends on HAS_DMA - select FW_CONFIG + select FW_LOADER select VIRTIO config OMAP_REMOTEPROC diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 29387df4bfc9..8edb4aed5d36 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -217,7 +217,7 @@ int rproc_alloc_vring(struct rproc_vdev *rvdev, int i) * TODO: support predefined notifyids (via resource table) */ ret = idr_alloc(&rproc->notifyids, rvring, 0, 0, GFP_KERNEL); - if (ret) { + if (ret < 0) { dev_err(dev, "idr_alloc failed: %d\n", ret); dma_free_coherent(dev->parent, size, va, dma); return ret; @@ -366,10 +366,12 @@ static int rproc_handle_vdev(struct rproc *rproc, struct fw_rsc_vdev *rsc, /* it is now safe to add the virtio device */ ret = rproc_add_virtio_dev(rvdev, rsc->id); if (ret) - goto free_rvdev; + goto remove_rvdev; return 0; +remove_rvdev: + list_del(&rvdev->node); free_rvdev: kfree(rvdev); return ret; diff --git a/drivers/remoteproc/ste_modem_rproc.c b/drivers/remoteproc/ste_modem_rproc.c index a7743c069339..fb95c4220052 100644 --- a/drivers/remoteproc/ste_modem_rproc.c +++ b/drivers/remoteproc/ste_modem_rproc.c @@ -240,6 +240,8 @@ static int sproc_drv_remove(struct platform_device *pdev) /* Unregister as remoteproc device */ rproc_del(sproc->rproc); + dma_free_coherent(sproc->rproc->dev.parent, SPROC_FW_SIZE, + sproc->fw_addr, sproc->fw_dma_addr); rproc_put(sproc->rproc); mdev->drv_data = NULL; @@ -297,10 +299,13 @@ static int sproc_probe(struct platform_device *pdev) /* Register as a remoteproc device */ err = rproc_add(rproc); if (err) - goto free_rproc; + goto free_mem; return 0; +free_mem: + dma_free_coherent(rproc->dev.parent, SPROC_FW_SIZE, + sproc->fw_addr, sproc->fw_dma_addr); free_rproc: /* Reset device data upon error */ mdev->drv_data = NULL; diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index ab4d2861ef3c..c4f392d5db4c 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -769,6 +769,7 @@ struct qeth_card { unsigned long thread_start_mask; unsigned long thread_allowed_mask; unsigned long thread_running_mask; + struct task_struct *recovery_task; spinlock_t ip_lock; struct list_head ip_list; struct list_head *ip_tbd_list; @@ -862,6 +863,8 @@ extern struct qeth_card_list_struct qeth_core_card_list; extern struct kmem_cache *qeth_core_header_cache; extern struct qeth_dbf_info qeth_dbf[QETH_DBF_INFOS]; +void qeth_set_recovery_task(struct qeth_card *); +void qeth_clear_recovery_task(struct qeth_card *); void qeth_set_allowed_threads(struct qeth_card *, unsigned long , int); int qeth_threads_running(struct qeth_card *, unsigned long); int qeth_wait_for_threads(struct qeth_card *, unsigned long); diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index a86ce07736ef..6cd0fc1b203a 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -177,6 +177,23 @@ const char *qeth_get_cardname_short(struct qeth_card *card) return "n/a"; } +void qeth_set_recovery_task(struct qeth_card *card) +{ + card->recovery_task = current; +} +EXPORT_SYMBOL_GPL(qeth_set_recovery_task); + +void qeth_clear_recovery_task(struct qeth_card *card) +{ + card->recovery_task = NULL; +} +EXPORT_SYMBOL_GPL(qeth_clear_recovery_task); + +static bool qeth_is_recovery_task(const struct qeth_card *card) +{ + return card->recovery_task == current; +} + void qeth_set_allowed_threads(struct qeth_card *card, unsigned long threads, int clear_start_mask) { @@ -205,6 +222,8 @@ EXPORT_SYMBOL_GPL(qeth_threads_running); int qeth_wait_for_threads(struct qeth_card *card, unsigned long threads) { + if (qeth_is_recovery_task(card)) + return 0; return wait_event_interruptible(card->wait_q, qeth_threads_running(card, threads) == 0); } diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 2d425416b0a1..ec8ccdae7aba 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -1144,6 +1144,7 @@ static int qeth_l2_recover(void *ptr) QETH_CARD_TEXT(card, 2, "recover2"); dev_warn(&card->gdev->dev, "A recovery process has been started for the device\n"); + qeth_set_recovery_task(card); __qeth_l2_set_offline(card->gdev, 1); rc = __qeth_l2_set_online(card->gdev, 1); if (!rc) @@ -1154,6 +1155,7 @@ static int qeth_l2_recover(void *ptr) dev_warn(&card->gdev->dev, "The qeth device driver " "failed to recover an error on the device\n"); } + qeth_clear_recovery_task(card); qeth_clear_thread_start_bit(card, QETH_RECOVER_THREAD); qeth_clear_thread_running_bit(card, QETH_RECOVER_THREAD); return 0; diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 449676e48fd0..c1b0b2761f8d 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -3520,6 +3520,7 @@ static int qeth_l3_recover(void *ptr) QETH_CARD_TEXT(card, 2, "recover2"); dev_warn(&card->gdev->dev, "A recovery process has been started for the device\n"); + qeth_set_recovery_task(card); __qeth_l3_set_offline(card->gdev, 1); rc = __qeth_l3_set_online(card->gdev, 1); if (!rc) @@ -3530,6 +3531,7 @@ static int qeth_l3_recover(void *ptr) dev_warn(&card->gdev->dev, "The qeth device driver " "failed to recover an error on the device\n"); } + qeth_clear_recovery_task(card); qeth_clear_thread_start_bit(card, QETH_RECOVER_THREAD); qeth_clear_thread_running_bit(card, QETH_RECOVER_THREAD); return 0; diff --git a/drivers/sbus/char/bbc_i2c.c b/drivers/sbus/char/bbc_i2c.c index 1a9d1e3ce64c..c1441ed282eb 100644 --- a/drivers/sbus/char/bbc_i2c.c +++ b/drivers/sbus/char/bbc_i2c.c @@ -282,7 +282,7 @@ static irqreturn_t bbc_i2c_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static void __init reset_one_i2c(struct bbc_i2c_bus *bp) +static void reset_one_i2c(struct bbc_i2c_bus *bp) { writeb(I2C_PCF_PIN, bp->i2c_control_regs + 0x0); writeb(bp->own, bp->i2c_control_regs + 0x1); @@ -291,7 +291,7 @@ static void __init reset_one_i2c(struct bbc_i2c_bus *bp) writeb(I2C_PCF_IDLE, bp->i2c_control_regs + 0x0); } -static struct bbc_i2c_bus * __init attach_one_i2c(struct platform_device *op, int index) +static struct bbc_i2c_bus * attach_one_i2c(struct platform_device *op, int index) { struct bbc_i2c_bus *bp; struct device_node *dp; diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c index a044f593e8b9..d0fa4b6c551f 100644 --- a/drivers/scsi/ibmvscsi/ibmvscsi.c +++ b/drivers/scsi/ibmvscsi/ibmvscsi.c @@ -1899,8 +1899,8 @@ static int ibmvscsi_slave_configure(struct scsi_device *sdev) sdev->allow_restart = 1; blk_queue_rq_timeout(sdev->request_queue, 120 * HZ); } - scsi_adjust_queue_depth(sdev, 0, shost->cmd_per_lun); spin_unlock_irqrestore(shost->host_lock, lock_flags); + scsi_adjust_queue_depth(sdev, 0, shost->cmd_per_lun); return 0; } diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index f328089a1060..2197b57fb225 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -5148,7 +5148,7 @@ static int ipr_cancel_op(struct scsi_cmnd *scsi_cmd) ipr_trace; } - list_add_tail(&ipr_cmd->queue, &hrrq->hrrq_free_q); + list_add_tail(&ipr_cmd->queue, &ipr_cmd->hrrq->hrrq_free_q); if (!ipr_is_naca_model(res)) res->needs_sync_complete = 1; @@ -9349,7 +9349,10 @@ static int ipr_test_msi(struct ipr_ioa_cfg *ioa_cfg, struct pci_dev *pdev) int_reg = readl(ioa_cfg->regs.sense_interrupt_mask_reg); spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags); - rc = request_irq(pdev->irq, ipr_test_intr, 0, IPR_NAME, ioa_cfg); + if (ioa_cfg->intr_flag == IPR_USE_MSIX) + rc = request_irq(ioa_cfg->vectors_info[0].vec, ipr_test_intr, 0, IPR_NAME, ioa_cfg); + else + rc = request_irq(pdev->irq, ipr_test_intr, 0, IPR_NAME, ioa_cfg); if (rc) { dev_err(&pdev->dev, "Can not assign irq %d\n", pdev->irq); return rc; @@ -9371,7 +9374,10 @@ static int ipr_test_msi(struct ipr_ioa_cfg *ioa_cfg, struct pci_dev *pdev) spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags); - free_irq(pdev->irq, ioa_cfg); + if (ioa_cfg->intr_flag == IPR_USE_MSIX) + free_irq(ioa_cfg->vectors_info[0].vec, ioa_cfg); + else + free_irq(pdev->irq, ioa_cfg); LEAVE; @@ -9722,6 +9728,7 @@ static void __ipr_remove(struct pci_dev *pdev) spin_unlock_irqrestore(ioa_cfg->host->host_lock, host_lock_flags); wait_event(ioa_cfg->reset_wait_q, !ioa_cfg->in_reset_reload); flush_work(&ioa_cfg->work_q); + INIT_LIST_HEAD(&ioa_cfg->used_res_q); spin_lock_irqsave(ioa_cfg->host->host_lock, host_lock_flags); spin_lock(&ipr_driver_lock); diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c index aec2e0da5016..55cbd0180159 100644 --- a/drivers/scsi/libsas/sas_expander.c +++ b/drivers/scsi/libsas/sas_expander.c @@ -235,6 +235,17 @@ static void sas_set_ex_phy(struct domain_device *dev, int phy_id, void *rsp) linkrate = phy->linkrate; memcpy(sas_addr, phy->attached_sas_addr, SAS_ADDR_SIZE); + /* Handle vacant phy - rest of dr data is not valid so skip it */ + if (phy->phy_state == PHY_VACANT) { + memset(phy->attached_sas_addr, 0, SAS_ADDR_SIZE); + phy->attached_dev_type = NO_DEVICE; + if (!test_bit(SAS_HA_ATA_EH_ACTIVE, &ha->state)) { + phy->phy_id = phy_id; + goto skip; + } else + goto out; + } + phy->attached_dev_type = to_dev_type(dr); if (test_bit(SAS_HA_ATA_EH_ACTIVE, &ha->state)) goto out; @@ -272,6 +283,7 @@ static void sas_set_ex_phy(struct domain_device *dev, int phy_id, void *rsp) phy->phy->maximum_linkrate = dr->pmax_linkrate; phy->phy->negotiated_linkrate = phy->linkrate; + skip: if (new_phy) if (sas_phy_add(phy->phy)) { sas_phy_free(phy->phy); @@ -388,7 +400,7 @@ int sas_ex_phy_discover(struct domain_device *dev, int single) if (!disc_req) return -ENOMEM; - disc_resp = alloc_smp_req(DISCOVER_RESP_SIZE); + disc_resp = alloc_smp_resp(DISCOVER_RESP_SIZE); if (!disc_resp) { kfree(disc_req); return -ENOMEM; diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 74b67d98e952..d43faf34c1e2 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -438,11 +438,12 @@ lpfc_sli4_rq_put(struct lpfc_queue *hq, struct lpfc_queue *dq, struct lpfc_rqe *temp_hrqe; struct lpfc_rqe *temp_drqe; struct lpfc_register doorbell; - int put_index = hq->host_index; + int put_index; /* sanity check on queue memory */ if (unlikely(!hq) || unlikely(!dq)) return -ENOMEM; + put_index = hq->host_index; temp_hrqe = hq->qe[hq->host_index].rqe; temp_drqe = dq->qe[dq->host_index].rqe; diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index 1d82eef4e1eb..b3db9dcc2619 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -1938,11 +1938,6 @@ qla24xx_vport_delete(struct fc_vport *fc_vport) "Timer for the VP[%d] has stopped\n", vha->vp_idx); } - /* No pending activities shall be there on the vha now */ - if (ql2xextended_error_logging & ql_dbg_user) - msleep(random32()%10); /* Just to see if something falls on - * the net we have placed below */ - BUG_ON(atomic_read(&vha->vref_count)); qla2x00_free_fcports(vha); diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c index 1626de52e32a..fbc305f1c87c 100644 --- a/drivers/scsi/qla2xxx/qla_dbg.c +++ b/drivers/scsi/qla2xxx/qla_dbg.c @@ -15,6 +15,7 @@ * | Mailbox commands | 0x115b | 0x111a-0x111b | * | | | 0x112c-0x112e | * | | | 0x113a | + * | | | 0x1155-0x1158 | * | Device Discovery | 0x2087 | 0x2020-0x2022, | * | | | 0x2016 | * | Queue Command and IO tracing | 0x3031 | 0x3006-0x300b | @@ -401,7 +402,7 @@ qla2xxx_copy_atioqueues(struct qla_hw_data *ha, void *ptr, void *ring; } aq, *aqp; - if (!ha->tgt.atio_q_length) + if (!ha->tgt.atio_ring) return ptr; num_queues = 1; diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index c6509911772b..65c5ff75936b 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -863,7 +863,6 @@ typedef struct { #define MBX_1 BIT_1 #define MBX_0 BIT_0 -#define RNID_TYPE_SET_VERSION 0x9 #define RNID_TYPE_ASIC_TEMP 0xC /* diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h index eb3ca21a7f17..b310fa97b545 100644 --- a/drivers/scsi/qla2xxx/qla_gbl.h +++ b/drivers/scsi/qla2xxx/qla_gbl.h @@ -357,9 +357,6 @@ qla2x00_enable_fce_trace(scsi_qla_host_t *, dma_addr_t, uint16_t , uint16_t *, extern int qla2x00_disable_fce_trace(scsi_qla_host_t *, uint64_t *, uint64_t *); -extern int -qla2x00_set_driver_version(scsi_qla_host_t *, char *); - extern int qla2x00_read_sfp(scsi_qla_host_t *, dma_addr_t, uint8_t *, uint16_t, uint16_t, uint16_t, uint16_t); diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index edf4d14a1335..b59203393cb2 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -619,8 +619,6 @@ qla2x00_initialize_adapter(scsi_qla_host_t *vha) if (IS_QLA24XX_TYPE(ha) || IS_QLA25XX(ha)) qla24xx_read_fcp_prio_cfg(vha); - qla2x00_set_driver_version(vha, QLA2XXX_VERSION); - return (rval); } @@ -1399,7 +1397,7 @@ qla2x00_alloc_fw_dump(scsi_qla_host_t *vha) mq_size += ha->max_rsp_queues * (rsp->length * sizeof(response_t)); } - if (ha->tgt.atio_q_length) + if (ha->tgt.atio_ring) mq_size += ha->tgt.atio_q_length * sizeof(request_t); /* Allocate memory for Fibre Channel Event Buffer. */ if (!IS_QLA25XX(ha) && !IS_QLA81XX(ha) && !IS_QLA83XX(ha)) diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 186dd59ce4fa..43345af56431 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -3866,64 +3866,6 @@ qla81xx_restart_mpi_firmware(scsi_qla_host_t *vha) return rval; } -int -qla2x00_set_driver_version(scsi_qla_host_t *vha, char *version) -{ - int rval; - mbx_cmd_t mc; - mbx_cmd_t *mcp = &mc; - int len; - uint16_t dwlen; - uint8_t *str; - dma_addr_t str_dma; - struct qla_hw_data *ha = vha->hw; - - if (!IS_FWI2_CAPABLE(ha) || IS_QLA82XX(ha)) - return QLA_FUNCTION_FAILED; - - ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x1155, - "Entered %s.\n", __func__); - - str = dma_pool_alloc(ha->s_dma_pool, GFP_KERNEL, &str_dma); - if (!str) { - ql_log(ql_log_warn, vha, 0x1156, - "Failed to allocate driver version param.\n"); - return QLA_MEMORY_ALLOC_FAILED; - } - - memcpy(str, "\x7\x3\x11\x0", 4); - dwlen = str[0]; - len = dwlen * sizeof(uint32_t) - 4; - memset(str + 4, 0, len); - if (len > strlen(version)) - len = strlen(version); - memcpy(str + 4, version, len); - - mcp->mb[0] = MBC_SET_RNID_PARAMS; - mcp->mb[1] = RNID_TYPE_SET_VERSION << 8 | dwlen; - mcp->mb[2] = MSW(LSD(str_dma)); - mcp->mb[3] = LSW(LSD(str_dma)); - mcp->mb[6] = MSW(MSD(str_dma)); - mcp->mb[7] = LSW(MSD(str_dma)); - mcp->out_mb = MBX_7|MBX_6|MBX_3|MBX_2|MBX_1|MBX_0; - mcp->in_mb = MBX_0; - mcp->tov = MBX_TOV_SECONDS; - mcp->flags = 0; - rval = qla2x00_mailbox_command(vha, mcp); - - if (rval != QLA_SUCCESS) { - ql_dbg(ql_dbg_mbx, vha, 0x1157, - "Failed=%x mb[0]=%x.\n", rval, mcp->mb[0]); - } else { - ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x1158, - "Done %s.\n", __func__); - } - - dma_pool_free(ha->s_dma_pool, str, str_dma); - - return rval; -} - static int qla2x00_read_asic_temperature(scsi_qla_host_t *vha, uint16_t *temp) { diff --git a/drivers/scsi/qla2xxx/qla_version.h b/drivers/scsi/qla2xxx/qla_version.h index 2b6e478d9e33..ec54036d1e12 100644 --- a/drivers/scsi/qla2xxx/qla_version.h +++ b/drivers/scsi/qla2xxx/qla_version.h @@ -7,7 +7,7 @@ /* * Driver version */ -#define QLA2XXX_VERSION "8.04.00.08-k" +#define QLA2XXX_VERSION "8.04.00.13-k" #define QLA_DRIVER_MAJOR_VER 8 #define QLA_DRIVER_MINOR_VER 4 diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index 86974471af68..2a32036a9404 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -4112,6 +4112,10 @@ static int st_probe(struct device *dev) tpnt->disk = disk; disk->private_data = &tpnt->driver; disk->queue = SDp->request_queue; + /* SCSI tape doesn't register this gendisk via add_disk(). Manually + * take queue reference that release_disk() expects. */ + if (!blk_get_queue(disk->queue)) + goto out_put_disk; tpnt->driver = &st_template; tpnt->device = SDp; @@ -4185,7 +4189,7 @@ static int st_probe(struct device *dev) idr_preload_end(); if (error < 0) { pr_warn("st: idr allocation failed: %d\n", error); - goto out_put_disk; + goto out_put_queue; } tpnt->index = error; sprintf(disk->disk_name, "st%d", tpnt->index); @@ -4211,6 +4215,8 @@ out_remove_devs: spin_lock(&st_index_lock); idr_remove(&st_index_idr, tpnt->index); spin_unlock(&st_index_lock); +out_put_queue: + blk_put_queue(disk->queue); out_put_disk: put_disk(disk); kfree(tpnt); diff --git a/drivers/ssb/driver_chipcommon_pmu.c b/drivers/ssb/driver_chipcommon_pmu.c index 791da2c0d8f6..23c5dbfea115 100644 --- a/drivers/ssb/driver_chipcommon_pmu.c +++ b/drivers/ssb/driver_chipcommon_pmu.c @@ -670,3 +670,32 @@ u32 ssb_pmu_get_controlclock(struct ssb_chipcommon *cc) return 0; } } + +void ssb_pmu_spuravoid_pllupdate(struct ssb_chipcommon *cc, int spuravoid) +{ + u32 pmu_ctl = 0; + + switch (cc->dev->bus->chip_id) { + case 0x4322: + ssb_chipco_pll_write(cc, SSB_PMU1_PLLCTL0, 0x11100070); + ssb_chipco_pll_write(cc, SSB_PMU1_PLLCTL1, 0x1014140a); + ssb_chipco_pll_write(cc, SSB_PMU1_PLLCTL5, 0x88888854); + if (spuravoid == 1) + ssb_chipco_pll_write(cc, SSB_PMU1_PLLCTL2, 0x05201828); + else + ssb_chipco_pll_write(cc, SSB_PMU1_PLLCTL2, 0x05001828); + pmu_ctl = SSB_CHIPCO_PMU_CTL_PLL_UPD; + break; + case 43222: + /* TODO: BCM43222 requires updating PLLs too */ + return; + default: + ssb_printk(KERN_ERR PFX + "Unknown spuravoidance settings for chip 0x%04X, not changing PLL\n", + cc->dev->bus->chip_id); + return; + } + + chipco_set32(cc, SSB_CHIPCO_PMU_CTL, pmu_ctl); +} +EXPORT_SYMBOL_GPL(ssb_pmu_spuravoid_pllupdate); diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c index ff1c5ee352cb..cbe48ab41745 100644 --- a/drivers/target/target_core_alua.c +++ b/drivers/target/target_core_alua.c @@ -409,6 +409,7 @@ static inline int core_alua_state_standby( case REPORT_LUNS: case RECEIVE_DIAGNOSTIC: case SEND_DIAGNOSTIC: + return 0; case MAINTENANCE_IN: switch (cdb[1] & 0x1f) { case MI_REPORT_TARGET_PGS: @@ -451,6 +452,7 @@ static inline int core_alua_state_unavailable( switch (cdb[0]) { case INQUIRY: case REPORT_LUNS: + return 0; case MAINTENANCE_IN: switch (cdb[1] & 0x1f) { case MI_REPORT_TARGET_PGS: @@ -491,6 +493,7 @@ static inline int core_alua_state_transition( switch (cdb[0]) { case INQUIRY: case REPORT_LUNS: + return 0; case MAINTENANCE_IN: switch (cdb[1] & 0x1f) { case MI_REPORT_TARGET_PGS: diff --git a/drivers/tty/mxser.c b/drivers/tty/mxser.c index 484b6a3c9b03..302909ccf183 100644 --- a/drivers/tty/mxser.c +++ b/drivers/tty/mxser.c @@ -2643,9 +2643,9 @@ static int mxser_probe(struct pci_dev *pdev, mxvar_sdriver, brd->idx + i, &pdev->dev); if (IS_ERR(tty_dev)) { retval = PTR_ERR(tty_dev); - for (i--; i >= 0; i--) + for (; i > 0; i--) tty_unregister_device(mxvar_sdriver, - brd->idx + i); + brd->idx + i - 1); goto err_relbrd; } } @@ -2751,9 +2751,9 @@ static int __init mxser_module_init(void) tty_dev = tty_port_register_device(&brd->ports[i].port, mxvar_sdriver, brd->idx + i, NULL); if (IS_ERR(tty_dev)) { - for (i--; i >= 0; i--) + for (; i > 0; i--) tty_unregister_device(mxvar_sdriver, - brd->idx + i); + brd->idx + i - 1); for (i = 0; i < brd->info->nports; i++) tty_port_destroy(&brd->ports[i].port); free_irq(brd->irq, brd); diff --git a/drivers/tty/serial/8250/8250_pnp.c b/drivers/tty/serial/8250/8250_pnp.c index b3455a970a1d..35d9ab95c5cb 100644 --- a/drivers/tty/serial/8250/8250_pnp.c +++ b/drivers/tty/serial/8250/8250_pnp.c @@ -429,7 +429,6 @@ serial_pnp_probe(struct pnp_dev *dev, const struct pnp_device_id *dev_id) { struct uart_8250_port uart; int ret, line, flags = dev_id->driver_data; - struct resource *res = NULL; if (flags & UNKNOWN_DEV) { ret = serial_pnp_guess_board(dev); @@ -440,12 +439,11 @@ serial_pnp_probe(struct pnp_dev *dev, const struct pnp_device_id *dev_id) memset(&uart, 0, sizeof(uart)); if (pnp_irq_valid(dev, 0)) uart.port.irq = pnp_irq(dev, 0); - if ((flags & CIR_PORT) && pnp_port_valid(dev, 2)) - res = pnp_get_resource(dev, IORESOURCE_IO, 2); - else if (pnp_port_valid(dev, 0)) - res = pnp_get_resource(dev, IORESOURCE_IO, 0); - if (pnp_resource_enabled(res)) { - uart.port.iobase = res->start; + if ((flags & CIR_PORT) && pnp_port_valid(dev, 2)) { + uart.port.iobase = pnp_port_start(dev, 2); + uart.port.iotype = UPIO_PORT; + } else if (pnp_port_valid(dev, 0)) { + uart.port.iobase = pnp_port_start(dev, 0); uart.port.iotype = UPIO_PORT; } else if (pnp_mem_valid(dev, 0)) { uart.port.mapbase = pnp_mem_start(dev, 0); diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c index 4dc41408ecb7..30d4f7a783cd 100644 --- a/drivers/tty/serial/omap-serial.c +++ b/drivers/tty/serial/omap-serial.c @@ -886,6 +886,17 @@ serial_omap_set_termios(struct uart_port *port, struct ktermios *termios, serial_out(up, UART_MCR, up->mcr | UART_MCR_TCRTLR); /* FIFO ENABLE, DMA MODE */ + up->scr |= OMAP_UART_SCR_RX_TRIG_GRANU1_MASK; + /* + * NOTE: Setting OMAP_UART_SCR_RX_TRIG_GRANU1_MASK + * sets Enables the granularity of 1 for TRIGGER RX + * level. Along with setting RX FIFO trigger level + * to 1 (as noted below, 16 characters) and TLR[3:0] + * to zero this will result RX FIFO threshold level + * to 1 character, instead of 16 as noted in comment + * below. + */ + /* Set receive FIFO threshold to 16 characters and * transmit FIFO threshold to 16 spaces */ diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 8189cb6a86af..7abc5c81af2c 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -346,6 +346,7 @@ static long vfio_pci_ioctl(void *device_data, if (!(hdr.flags & VFIO_IRQ_SET_DATA_NONE)) { size_t size; + int max = vfio_pci_get_irq_count(vdev, hdr.index); if (hdr.flags & VFIO_IRQ_SET_DATA_BOOL) size = sizeof(uint8_t); @@ -355,7 +356,7 @@ static long vfio_pci_ioctl(void *device_data, return -EINVAL; if (hdr.argsz - minsz < hdr.count * size || - hdr.count > vfio_pci_get_irq_count(vdev, hdr.index)) + hdr.start >= max || hdr.start + hdr.count > max) return -EINVAL; data = memdup_user((void __user *)(arg + minsz), diff --git a/drivers/vhost/tcm_vhost.c b/drivers/vhost/tcm_vhost.c index 2968b4934659..957a0b98a5d9 100644 --- a/drivers/vhost/tcm_vhost.c +++ b/drivers/vhost/tcm_vhost.c @@ -74,9 +74,8 @@ enum { struct vhost_scsi { /* Protected by vhost_scsi->dev.mutex */ - struct tcm_vhost_tpg *vs_tpg[VHOST_SCSI_MAX_TARGET]; + struct tcm_vhost_tpg **vs_tpg; char vs_vhost_wwpn[TRANSPORT_IQN_LEN]; - bool vs_endpoint; struct vhost_dev dev; struct vhost_virtqueue vqs[VHOST_SCSI_MAX_VQ]; @@ -579,9 +578,27 @@ static void tcm_vhost_submission_work(struct work_struct *work) } } +static void vhost_scsi_send_bad_target(struct vhost_scsi *vs, + struct vhost_virtqueue *vq, int head, unsigned out) +{ + struct virtio_scsi_cmd_resp __user *resp; + struct virtio_scsi_cmd_resp rsp; + int ret; + + memset(&rsp, 0, sizeof(rsp)); + rsp.response = VIRTIO_SCSI_S_BAD_TARGET; + resp = vq->iov[out].iov_base; + ret = __copy_to_user(resp, &rsp, sizeof(rsp)); + if (!ret) + vhost_add_used_and_signal(&vs->dev, vq, head, 0); + else + pr_err("Faulted on virtio_scsi_cmd_resp\n"); +} + static void vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) { + struct tcm_vhost_tpg **vs_tpg; struct virtio_scsi_cmd_req v_req; struct tcm_vhost_tpg *tv_tpg; struct tcm_vhost_cmd *tv_cmd; @@ -590,8 +607,16 @@ static void vhost_scsi_handle_vq(struct vhost_scsi *vs, int head, ret; u8 target; - /* Must use ioctl VHOST_SCSI_SET_ENDPOINT */ - if (unlikely(!vs->vs_endpoint)) + /* + * We can handle the vq only after the endpoint is setup by calling the + * VHOST_SCSI_SET_ENDPOINT ioctl. + * + * TODO: Check that we are running from vhost_worker which acts + * as read-side critical section for vhost kind of RCU. + * See the comments in struct vhost_virtqueue in drivers/vhost/vhost.h + */ + vs_tpg = rcu_dereference_check(vq->private_data, 1); + if (!vs_tpg) return; mutex_lock(&vq->mutex); @@ -661,23 +686,11 @@ static void vhost_scsi_handle_vq(struct vhost_scsi *vs, /* Extract the tpgt */ target = v_req.lun[1]; - tv_tpg = vs->vs_tpg[target]; + tv_tpg = ACCESS_ONCE(vs_tpg[target]); /* Target does not exist, fail the request */ if (unlikely(!tv_tpg)) { - struct virtio_scsi_cmd_resp __user *resp; - struct virtio_scsi_cmd_resp rsp; - - memset(&rsp, 0, sizeof(rsp)); - rsp.response = VIRTIO_SCSI_S_BAD_TARGET; - resp = vq->iov[out].iov_base; - ret = __copy_to_user(resp, &rsp, sizeof(rsp)); - if (!ret) - vhost_add_used_and_signal(&vs->dev, - vq, head, 0); - else - pr_err("Faulted on virtio_scsi_cmd_resp\n"); - + vhost_scsi_send_bad_target(vs, vq, head, out); continue; } @@ -690,22 +703,13 @@ static void vhost_scsi_handle_vq(struct vhost_scsi *vs, if (IS_ERR(tv_cmd)) { vq_err(vq, "vhost_scsi_allocate_cmd failed %ld\n", PTR_ERR(tv_cmd)); - break; + goto err_cmd; } pr_debug("Allocated tv_cmd: %p exp_data_len: %d, data_direction" ": %d\n", tv_cmd, exp_data_len, data_direction); tv_cmd->tvc_vhost = vs; tv_cmd->tvc_vq = vq; - - if (unlikely(vq->iov[out].iov_len != - sizeof(struct virtio_scsi_cmd_resp))) { - vq_err(vq, "Expecting virtio_scsi_cmd_resp, got %zu" - " bytes, out: %d, in: %d\n", - vq->iov[out].iov_len, out, in); - break; - } - tv_cmd->tvc_resp = vq->iov[out].iov_base; /* @@ -725,7 +729,7 @@ static void vhost_scsi_handle_vq(struct vhost_scsi *vs, " exceeds SCSI_MAX_VARLEN_CDB_SIZE: %d\n", scsi_command_size(tv_cmd->tvc_cdb), TCM_VHOST_MAX_CDB_SIZE); - break; /* TODO */ + goto err_free; } tv_cmd->tvc_lun = ((v_req.lun[2] << 8) | v_req.lun[3]) & 0x3FFF; @@ -738,7 +742,7 @@ static void vhost_scsi_handle_vq(struct vhost_scsi *vs, data_direction == DMA_TO_DEVICE); if (unlikely(ret)) { vq_err(vq, "Failed to map iov to sgl\n"); - break; /* TODO */ + goto err_free; } } @@ -759,6 +763,13 @@ static void vhost_scsi_handle_vq(struct vhost_scsi *vs, } mutex_unlock(&vq->mutex); + return; + +err_free: + vhost_scsi_free_cmd(tv_cmd); +err_cmd: + vhost_scsi_send_bad_target(vs, vq, head, out); + mutex_unlock(&vq->mutex); } static void vhost_scsi_ctl_handle_kick(struct vhost_work *work) @@ -780,6 +791,20 @@ static void vhost_scsi_handle_kick(struct vhost_work *work) vhost_scsi_handle_vq(vs, vq); } +static void vhost_scsi_flush_vq(struct vhost_scsi *vs, int index) +{ + vhost_poll_flush(&vs->dev.vqs[index].poll); +} + +static void vhost_scsi_flush(struct vhost_scsi *vs) +{ + int i; + + for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) + vhost_scsi_flush_vq(vs, i); + vhost_work_flush(&vs->dev, &vs->vs_completion_work); +} + /* * Called from vhost_scsi_ioctl() context to walk the list of available * tcm_vhost_tpg with an active struct tcm_vhost_nexus @@ -790,8 +815,10 @@ static int vhost_scsi_set_endpoint( { struct tcm_vhost_tport *tv_tport; struct tcm_vhost_tpg *tv_tpg; + struct tcm_vhost_tpg **vs_tpg; + struct vhost_virtqueue *vq; + int index, ret, i, len; bool match = false; - int index, ret; mutex_lock(&vs->dev.mutex); /* Verify that ring has been setup correctly. */ @@ -803,6 +830,15 @@ static int vhost_scsi_set_endpoint( } } + len = sizeof(vs_tpg[0]) * VHOST_SCSI_MAX_TARGET; + vs_tpg = kzalloc(len, GFP_KERNEL); + if (!vs_tpg) { + mutex_unlock(&vs->dev.mutex); + return -ENOMEM; + } + if (vs->vs_tpg) + memcpy(vs_tpg, vs->vs_tpg, len); + mutex_lock(&tcm_vhost_mutex); list_for_each_entry(tv_tpg, &tcm_vhost_list, tv_tpg_list) { mutex_lock(&tv_tpg->tv_tpg_mutex); @@ -817,14 +853,15 @@ static int vhost_scsi_set_endpoint( tv_tport = tv_tpg->tport; if (!strcmp(tv_tport->tport_name, t->vhost_wwpn)) { - if (vs->vs_tpg[tv_tpg->tport_tpgt]) { + if (vs->vs_tpg && vs->vs_tpg[tv_tpg->tport_tpgt]) { mutex_unlock(&tv_tpg->tv_tpg_mutex); mutex_unlock(&tcm_vhost_mutex); mutex_unlock(&vs->dev.mutex); + kfree(vs_tpg); return -EEXIST; } tv_tpg->tv_tpg_vhost_count++; - vs->vs_tpg[tv_tpg->tport_tpgt] = tv_tpg; + vs_tpg[tv_tpg->tport_tpgt] = tv_tpg; smp_mb__after_atomic_inc(); match = true; } @@ -835,12 +872,27 @@ static int vhost_scsi_set_endpoint( if (match) { memcpy(vs->vs_vhost_wwpn, t->vhost_wwpn, sizeof(vs->vs_vhost_wwpn)); - vs->vs_endpoint = true; + for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) { + vq = &vs->vqs[i]; + /* Flushing the vhost_work acts as synchronize_rcu */ + mutex_lock(&vq->mutex); + rcu_assign_pointer(vq->private_data, vs_tpg); + vhost_init_used(vq); + mutex_unlock(&vq->mutex); + } ret = 0; } else { ret = -EEXIST; } + /* + * Act as synchronize_rcu to make sure access to + * old vs->vs_tpg is finished. + */ + vhost_scsi_flush(vs); + kfree(vs->vs_tpg); + vs->vs_tpg = vs_tpg; + mutex_unlock(&vs->dev.mutex); return ret; } @@ -851,6 +903,8 @@ static int vhost_scsi_clear_endpoint( { struct tcm_vhost_tport *tv_tport; struct tcm_vhost_tpg *tv_tpg; + struct vhost_virtqueue *vq; + bool match = false; int index, ret, i; u8 target; @@ -862,9 +916,14 @@ static int vhost_scsi_clear_endpoint( goto err_dev; } } + + if (!vs->vs_tpg) { + mutex_unlock(&vs->dev.mutex); + return 0; + } + for (i = 0; i < VHOST_SCSI_MAX_TARGET; i++) { target = i; - tv_tpg = vs->vs_tpg[target]; if (!tv_tpg) continue; @@ -886,10 +945,27 @@ static int vhost_scsi_clear_endpoint( } tv_tpg->tv_tpg_vhost_count--; vs->vs_tpg[target] = NULL; - vs->vs_endpoint = false; + match = true; mutex_unlock(&tv_tpg->tv_tpg_mutex); } + if (match) { + for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) { + vq = &vs->vqs[i]; + /* Flushing the vhost_work acts as synchronize_rcu */ + mutex_lock(&vq->mutex); + rcu_assign_pointer(vq->private_data, NULL); + mutex_unlock(&vq->mutex); + } + } + /* + * Act as synchronize_rcu to make sure access to + * old vs->vs_tpg is finished. + */ + vhost_scsi_flush(vs); + kfree(vs->vs_tpg); + vs->vs_tpg = NULL; mutex_unlock(&vs->dev.mutex); + return 0; err_tpg: @@ -899,6 +975,24 @@ err_dev: return ret; } +static int vhost_scsi_set_features(struct vhost_scsi *vs, u64 features) +{ + if (features & ~VHOST_SCSI_FEATURES) + return -EOPNOTSUPP; + + mutex_lock(&vs->dev.mutex); + if ((features & (1 << VHOST_F_LOG_ALL)) && + !vhost_log_access_ok(&vs->dev)) { + mutex_unlock(&vs->dev.mutex); + return -EFAULT; + } + vs->dev.acked_features = features; + smp_wmb(); + vhost_scsi_flush(vs); + mutex_unlock(&vs->dev.mutex); + return 0; +} + static int vhost_scsi_open(struct inode *inode, struct file *f) { struct vhost_scsi *s; @@ -939,38 +1033,6 @@ static int vhost_scsi_release(struct inode *inode, struct file *f) return 0; } -static void vhost_scsi_flush_vq(struct vhost_scsi *vs, int index) -{ - vhost_poll_flush(&vs->dev.vqs[index].poll); -} - -static void vhost_scsi_flush(struct vhost_scsi *vs) -{ - int i; - - for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) - vhost_scsi_flush_vq(vs, i); - vhost_work_flush(&vs->dev, &vs->vs_completion_work); -} - -static int vhost_scsi_set_features(struct vhost_scsi *vs, u64 features) -{ - if (features & ~VHOST_SCSI_FEATURES) - return -EOPNOTSUPP; - - mutex_lock(&vs->dev.mutex); - if ((features & (1 << VHOST_F_LOG_ALL)) && - !vhost_log_access_ok(&vs->dev)) { - mutex_unlock(&vs->dev.mutex); - return -EFAULT; - } - vs->dev.acked_features = features; - smp_wmb(); - vhost_scsi_flush(vs); - mutex_unlock(&vs->dev.mutex); - return 0; -} - static long vhost_scsi_ioctl(struct file *f, unsigned int ioctl, unsigned long arg) { diff --git a/drivers/video/fbmem.c b/drivers/video/fbmem.c index 7c254084b6a0..86291dcd964a 100644 --- a/drivers/video/fbmem.c +++ b/drivers/video/fbmem.c @@ -1373,15 +1373,12 @@ fb_mmap(struct file *file, struct vm_area_struct * vma) { struct fb_info *info = file_fb_info(file); struct fb_ops *fb; - unsigned long off; + unsigned long mmio_pgoff; unsigned long start; u32 len; if (!info) return -ENODEV; - if (vma->vm_pgoff > (~0UL >> PAGE_SHIFT)) - return -EINVAL; - off = vma->vm_pgoff << PAGE_SHIFT; fb = info->fbops; if (!fb) return -ENODEV; @@ -1393,32 +1390,24 @@ fb_mmap(struct file *file, struct vm_area_struct * vma) return res; } - /* frame buffer memory */ + /* + * Ugh. This can be either the frame buffer mapping, or + * if pgoff points past it, the mmio mapping. + */ start = info->fix.smem_start; - len = PAGE_ALIGN((start & ~PAGE_MASK) + info->fix.smem_len); - if (off >= len) { - /* memory mapped io */ - off -= len; - if (info->var.accel_flags) { - mutex_unlock(&info->mm_lock); - return -EINVAL; - } + len = info->fix.smem_len; + mmio_pgoff = PAGE_ALIGN((start & ~PAGE_MASK) + len) >> PAGE_SHIFT; + if (vma->vm_pgoff >= mmio_pgoff) { + vma->vm_pgoff -= mmio_pgoff; start = info->fix.mmio_start; - len = PAGE_ALIGN((start & ~PAGE_MASK) + info->fix.mmio_len); + len = info->fix.mmio_len; } mutex_unlock(&info->mm_lock); - start &= PAGE_MASK; - if ((vma->vm_end - vma->vm_start + off) > len) - return -EINVAL; - off += start; - vma->vm_pgoff = off >> PAGE_SHIFT; - /* VM_IO | VM_DONTEXPAND | VM_DONTDUMP are set by io_remap_pfn_range()*/ + vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); - fb_pgprotect(file, vma, off); - if (io_remap_pfn_range(vma, vma->vm_start, off >> PAGE_SHIFT, - vma->vm_end - vma->vm_start, vma->vm_page_prot)) - return -EAGAIN; - return 0; + fb_pgprotect(file, vma, start); + + return vm_iomap_memory(vma, start, len); } static int diff --git a/drivers/video/mmp/core.c b/drivers/video/mmp/core.c index 9ed83419038b..84de2632857a 100644 --- a/drivers/video/mmp/core.c +++ b/drivers/video/mmp/core.c @@ -252,7 +252,5 @@ void mmp_unregister_path(struct mmp_path *path) kfree(path); mutex_unlock(&disp_lock); - - dev_info(path->dev, "de-register %s\n", path->name); } EXPORT_SYMBOL_GPL(mmp_unregister_path); diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index 9fcc70c11cea..e89fc3133972 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -117,7 +117,7 @@ config ARM_SP805_WATCHDOG config AT91RM9200_WATCHDOG tristate "AT91RM9200 watchdog" - depends on ARCH_AT91 + depends on ARCH_AT91RM9200 help Watchdog timer embedded into AT91RM9200 chips. This will reboot your system when the timeout is reached. diff --git a/drivers/xen/events.c b/drivers/xen/events.c index aa85881d17b2..2647ad8e1f19 100644 --- a/drivers/xen/events.c +++ b/drivers/xen/events.c @@ -1316,7 +1316,7 @@ static void __xen_evtchn_do_upcall(void) { int start_word_idx, start_bit_idx; int word_idx, bit_idx; - int i; + int i, irq; int cpu = get_cpu(); struct shared_info *s = HYPERVISOR_shared_info; struct vcpu_info *vcpu_info = __this_cpu_read(xen_vcpu); @@ -1324,6 +1324,8 @@ static void __xen_evtchn_do_upcall(void) do { xen_ulong_t pending_words; + xen_ulong_t pending_bits; + struct irq_desc *desc; vcpu_info->evtchn_upcall_pending = 0; @@ -1335,6 +1337,17 @@ static void __xen_evtchn_do_upcall(void) * selector flag. xchg_xen_ulong must contain an * appropriate barrier. */ + if ((irq = per_cpu(virq_to_irq, cpu)[VIRQ_TIMER]) != -1) { + int evtchn = evtchn_from_irq(irq); + word_idx = evtchn / BITS_PER_LONG; + pending_bits = evtchn % BITS_PER_LONG; + if (active_evtchns(cpu, s, word_idx) & (1ULL << pending_bits)) { + desc = irq_to_desc(irq); + if (desc) + generic_handle_irq_desc(irq, desc); + } + } + pending_words = xchg_xen_ulong(&vcpu_info->evtchn_pending_sel, 0); start_word_idx = __this_cpu_read(current_word_idx); @@ -1343,7 +1356,6 @@ static void __xen_evtchn_do_upcall(void) word_idx = start_word_idx; for (i = 0; pending_words != 0; i++) { - xen_ulong_t pending_bits; xen_ulong_t words; words = MASK_LSBS(pending_words, word_idx); @@ -1372,8 +1384,7 @@ static void __xen_evtchn_do_upcall(void) do { xen_ulong_t bits; - int port, irq; - struct irq_desc *desc; + int port; bits = MASK_LSBS(pending_bits, bit_idx); diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 3939829f6c5c..86af964c2425 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1137,6 +1137,7 @@ static unsigned long vma_dump_size(struct vm_area_struct *vma, goto whole; if (!(vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_PRIVATE)) goto whole; + return 0; } /* Do not dump I/O mapped devices or special mappings */ diff --git a/fs/bio.c b/fs/bio.c index bb5768f59b32..b96fc6ce4855 100644 --- a/fs/bio.c +++ b/fs/bio.c @@ -1428,8 +1428,6 @@ void bio_endio(struct bio *bio, int error) else if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) error = -EIO; - trace_block_bio_complete(bio, error); - if (bio->bi_end_io) bio->bi_end_io(bio, error); } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 451fad96ecd1..ef96381569a4 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -317,6 +317,7 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans, unsigned long src_ptr; unsigned long dst_ptr; int overwrite_root = 0; + bool inode_item = key->type == BTRFS_INODE_ITEM_KEY; if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) overwrite_root = 1; @@ -326,6 +327,9 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans, /* look for the key in the destination tree */ ret = btrfs_search_slot(NULL, root, key, path, 0, 0); + if (ret < 0) + return ret; + if (ret == 0) { char *src_copy; char *dst_copy; @@ -367,6 +371,30 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans, return 0; } + /* + * We need to load the old nbytes into the inode so when we + * replay the extents we've logged we get the right nbytes. + */ + if (inode_item) { + struct btrfs_inode_item *item; + u64 nbytes; + + item = btrfs_item_ptr(path->nodes[0], path->slots[0], + struct btrfs_inode_item); + nbytes = btrfs_inode_nbytes(path->nodes[0], item); + item = btrfs_item_ptr(eb, slot, + struct btrfs_inode_item); + btrfs_set_inode_nbytes(eb, item, nbytes); + } + } else if (inode_item) { + struct btrfs_inode_item *item; + + /* + * New inode, set nbytes to 0 so that the nbytes comes out + * properly when we replay the extents. + */ + item = btrfs_item_ptr(eb, slot, struct btrfs_inode_item); + btrfs_set_inode_nbytes(eb, item, 0); } insert: btrfs_release_path(path); @@ -486,7 +514,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, int found_type; u64 extent_end; u64 start = key->offset; - u64 saved_nbytes; + u64 nbytes = 0; struct btrfs_file_extent_item *item; struct inode *inode = NULL; unsigned long size; @@ -496,10 +524,19 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, found_type = btrfs_file_extent_type(eb, item); if (found_type == BTRFS_FILE_EXTENT_REG || - found_type == BTRFS_FILE_EXTENT_PREALLOC) - extent_end = start + btrfs_file_extent_num_bytes(eb, item); - else if (found_type == BTRFS_FILE_EXTENT_INLINE) { + found_type == BTRFS_FILE_EXTENT_PREALLOC) { + nbytes = btrfs_file_extent_num_bytes(eb, item); + extent_end = start + nbytes; + + /* + * We don't add to the inodes nbytes if we are prealloc or a + * hole. + */ + if (btrfs_file_extent_disk_bytenr(eb, item) == 0) + nbytes = 0; + } else if (found_type == BTRFS_FILE_EXTENT_INLINE) { size = btrfs_file_extent_inline_len(eb, item); + nbytes = btrfs_file_extent_ram_bytes(eb, item); extent_end = ALIGN(start + size, root->sectorsize); } else { ret = 0; @@ -548,7 +585,6 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, } btrfs_release_path(path); - saved_nbytes = inode_get_bytes(inode); /* drop any overlapping extents */ ret = btrfs_drop_extents(trans, root, inode, start, extent_end, 1); BUG_ON(ret); @@ -635,7 +671,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, BUG_ON(ret); } - inode_set_bytes(inode, saved_nbytes); + inode_add_bytes(inode, nbytes); ret = btrfs_update_inode(trans, root, inode); out: if (inode) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 991c63c6bdd0..21b3a291c327 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1575,14 +1575,24 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, } break; case Opt_blank_pass: - vol->password = NULL; - break; - case Opt_pass: /* passwords have to be handled differently * to allow the character used for deliminator * to be passed within them */ + /* + * Check if this is a case where the password + * starts with a delimiter + */ + tmp_end = strchr(data, '='); + tmp_end++; + if (!(tmp_end < end && tmp_end[1] == delim)) { + /* No it is not. Set the password to NULL */ + vol->password = NULL; + break; + } + /* Yes it is. Drop down to Opt_pass below.*/ + case Opt_pass: /* Obtain the value string */ value = strchr(data, '='); value++; diff --git a/fs/ecryptfs/miscdev.c b/fs/ecryptfs/miscdev.c index 412e6eda25f8..e4141f257495 100644 --- a/fs/ecryptfs/miscdev.c +++ b/fs/ecryptfs/miscdev.c @@ -80,13 +80,6 @@ ecryptfs_miscdev_open(struct inode *inode, struct file *file) int rc; mutex_lock(&ecryptfs_daemon_hash_mux); - rc = try_module_get(THIS_MODULE); - if (rc == 0) { - rc = -EIO; - printk(KERN_ERR "%s: Error attempting to increment module use " - "count; rc = [%d]\n", __func__, rc); - goto out_unlock_daemon_list; - } rc = ecryptfs_find_daemon_by_euid(&daemon); if (!rc) { rc = -EINVAL; @@ -96,7 +89,7 @@ ecryptfs_miscdev_open(struct inode *inode, struct file *file) if (rc) { printk(KERN_ERR "%s: Error attempting to spawn daemon; " "rc = [%d]\n", __func__, rc); - goto out_module_put_unlock_daemon_list; + goto out_unlock_daemon_list; } mutex_lock(&daemon->mux); if (daemon->flags & ECRYPTFS_DAEMON_MISCDEV_OPEN) { @@ -108,9 +101,6 @@ ecryptfs_miscdev_open(struct inode *inode, struct file *file) atomic_inc(&ecryptfs_num_miscdev_opens); out_unlock_daemon: mutex_unlock(&daemon->mux); -out_module_put_unlock_daemon_list: - if (rc) - module_put(THIS_MODULE); out_unlock_daemon_list: mutex_unlock(&ecryptfs_daemon_hash_mux); return rc; @@ -147,7 +137,6 @@ ecryptfs_miscdev_release(struct inode *inode, struct file *file) "bug.\n", __func__, rc); BUG(); } - module_put(THIS_MODULE); return rc; } @@ -471,6 +460,7 @@ out_free: static const struct file_operations ecryptfs_miscdev_fops = { + .owner = THIS_MODULE, .open = ecryptfs_miscdev_open, .poll = ecryptfs_miscdev_poll, .read = ecryptfs_miscdev_read, diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c index a94f0f779d5e..fe0a76213d9e 100644 --- a/fs/hfsplus/extents.c +++ b/fs/hfsplus/extents.c @@ -533,7 +533,7 @@ void hfsplus_file_truncate(struct inode *inode) struct address_space *mapping = inode->i_mapping; struct page *page; void *fsdata; - u32 size = inode->i_size; + loff_t size = inode->i_size; res = pagecache_write_begin(NULL, mapping, size, 0, AOP_FLAG_UNINTERRUPTIBLE, diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 84e3d856e91d..523464e62849 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -110,7 +110,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) * way when do_mmap_pgoff unwinds (may be important on powerpc * and ia64). */ - vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND | VM_DONTDUMP; + vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND; vma->vm_ops = &hugetlb_vm_ops; if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT)) diff --git a/fs/inode.c b/fs/inode.c index f5f7c06c36fb..a898b3d43ccf 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -725,7 +725,7 @@ void prune_icache_sb(struct super_block *sb, int nr_to_scan) * inode to the back of the list so we don't spin on it. */ if (!spin_trylock(&inode->i_lock)) { - list_move_tail(&inode->i_lru, &sb->s_inode_lru); + list_move(&inode->i_lru, &sb->s_inode_lru); continue; } diff --git a/fs/namespace.c b/fs/namespace.c index d581e45c0a9f..341d3f564082 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1690,7 +1690,7 @@ static int do_loopback(struct path *path, const char *old_name, if (IS_ERR(mnt)) { err = PTR_ERR(mnt); - goto out; + goto out2; } err = graft_tree(mnt, path); diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index ac4fc9a8fdbc..66b6664dcd4c 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -300,7 +300,7 @@ int nfs40_walk_client_list(struct nfs_client *new, struct rpc_cred *cred) { struct nfs_net *nn = net_generic(new->cl_net, nfs_net_id); - struct nfs_client *pos, *n, *prev = NULL; + struct nfs_client *pos, *prev = NULL; struct nfs4_setclientid_res clid = { .clientid = new->cl_clientid, .confirm = new->cl_confirm, @@ -308,10 +308,23 @@ int nfs40_walk_client_list(struct nfs_client *new, int status = -NFS4ERR_STALE_CLIENTID; spin_lock(&nn->nfs_client_lock); - list_for_each_entry_safe(pos, n, &nn->nfs_client_list, cl_share_link) { + list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) { /* If "pos" isn't marked ready, we can't trust the * remaining fields in "pos" */ - if (pos->cl_cons_state < NFS_CS_READY) + if (pos->cl_cons_state > NFS_CS_READY) { + atomic_inc(&pos->cl_count); + spin_unlock(&nn->nfs_client_lock); + + if (prev) + nfs_put_client(prev); + prev = pos; + + status = nfs_wait_client_init_complete(pos); + spin_lock(&nn->nfs_client_lock); + if (status < 0) + continue; + } + if (pos->cl_cons_state != NFS_CS_READY) continue; if (pos->rpc_ops != new->rpc_ops) @@ -423,16 +436,16 @@ int nfs41_walk_client_list(struct nfs_client *new, struct rpc_cred *cred) { struct nfs_net *nn = net_generic(new->cl_net, nfs_net_id); - struct nfs_client *pos, *n, *prev = NULL; + struct nfs_client *pos, *prev = NULL; int status = -NFS4ERR_STALE_CLIENTID; spin_lock(&nn->nfs_client_lock); - list_for_each_entry_safe(pos, n, &nn->nfs_client_list, cl_share_link) { + list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) { /* If "pos" isn't marked ready, we can't trust the * remaining fields in "pos", especially the client * ID and serverowner fields. Wait for CREATE_SESSION * to finish. */ - if (pos->cl_cons_state < NFS_CS_READY) { + if (pos->cl_cons_state > NFS_CS_READY) { atomic_inc(&pos->cl_count); spin_unlock(&nn->nfs_client_lock); @@ -440,18 +453,17 @@ int nfs41_walk_client_list(struct nfs_client *new, nfs_put_client(prev); prev = pos; - nfs4_schedule_lease_recovery(pos); status = nfs_wait_client_init_complete(pos); - if (status < 0) { - nfs_put_client(pos); - spin_lock(&nn->nfs_client_lock); - continue; + if (status == 0) { + nfs4_schedule_lease_recovery(pos); + status = nfs4_wait_clnt_recover(pos); } - status = pos->cl_cons_state; spin_lock(&nn->nfs_client_lock); if (status < 0) continue; } + if (pos->cl_cons_state != NFS_CS_READY) + continue; if (pos->rpc_ops != new->rpc_ops) continue; @@ -469,17 +481,18 @@ int nfs41_walk_client_list(struct nfs_client *new, continue; atomic_inc(&pos->cl_count); - spin_unlock(&nn->nfs_client_lock); + *result = pos; + status = 0; dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n", __func__, pos, atomic_read(&pos->cl_count)); - - *result = pos; - return 0; + break; } /* No matching nfs_client found. */ spin_unlock(&nn->nfs_client_lock); dprintk("NFS: <-- %s status = %d\n", __func__, status); + if (prev) + nfs_put_client(prev); return status; } #endif /* CONFIG_NFS_V4_1 */ diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 26431cf62ddb..0ad025eb523b 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1046,6 +1046,7 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata) /* Save the delegation */ nfs4_stateid_copy(&stateid, &delegation->stateid); rcu_read_unlock(); + nfs_release_seqid(opendata->o_arg.seqid); ret = nfs_may_open(state->inode, state->owner->so_cred, open_mode); if (ret != 0) goto out; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 6ace365c6334..d41a3518509f 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1886,7 +1886,13 @@ again: status = PTR_ERR(clnt); break; } - clp->cl_rpcclient = clnt; + /* Note: this is safe because we haven't yet marked the + * client as ready, so we are the only user of + * clp->cl_rpcclient + */ + clnt = xchg(&clp->cl_rpcclient, clnt); + rpc_shutdown_client(clnt); + clnt = clp->cl_rpcclient; goto again; case -NFS4ERR_MINOR_VERS_MISMATCH: diff --git a/fs/proc/array.c b/fs/proc/array.c index f7ed9ee46eb9..cbd0f1b324b9 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -143,6 +143,7 @@ static const char * const task_state_array[] = { "x (dead)", /* 64 */ "K (wakekill)", /* 128 */ "W (waking)", /* 256 */ + "P (parked)", /* 512 */ }; static inline const char *get_task_state(struct task_struct *tsk) diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 4b3b3ffb52f1..21e1a8f1659d 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -755,37 +755,8 @@ void pde_put(struct proc_dir_entry *pde) free_proc_entry(pde); } -/* - * Remove a /proc entry and free it if it's not currently in use. - */ -void remove_proc_entry(const char *name, struct proc_dir_entry *parent) +static void entry_rundown(struct proc_dir_entry *de) { - struct proc_dir_entry **p; - struct proc_dir_entry *de = NULL; - const char *fn = name; - unsigned int len; - - spin_lock(&proc_subdir_lock); - if (__xlate_proc_name(name, &parent, &fn) != 0) { - spin_unlock(&proc_subdir_lock); - return; - } - len = strlen(fn); - - for (p = &parent->subdir; *p; p=&(*p)->next ) { - if (proc_match(len, fn, *p)) { - de = *p; - *p = de->next; - de->next = NULL; - break; - } - } - spin_unlock(&proc_subdir_lock); - if (!de) { - WARN(1, "name '%s'\n", name); - return; - } - spin_lock(&de->pde_unload_lock); /* * Stop accepting new callers into module. If you're @@ -817,6 +788,40 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent) spin_lock(&de->pde_unload_lock); } spin_unlock(&de->pde_unload_lock); +} + +/* + * Remove a /proc entry and free it if it's not currently in use. + */ +void remove_proc_entry(const char *name, struct proc_dir_entry *parent) +{ + struct proc_dir_entry **p; + struct proc_dir_entry *de = NULL; + const char *fn = name; + unsigned int len; + + spin_lock(&proc_subdir_lock); + if (__xlate_proc_name(name, &parent, &fn) != 0) { + spin_unlock(&proc_subdir_lock); + return; + } + len = strlen(fn); + + for (p = &parent->subdir; *p; p=&(*p)->next ) { + if (proc_match(len, fn, *p)) { + de = *p; + *p = de->next; + de->next = NULL; + break; + } + } + spin_unlock(&proc_subdir_lock); + if (!de) { + WARN(1, "name '%s'\n", name); + return; + } + + entry_rundown(de); if (S_ISDIR(de->mode)) parent->nlink--; @@ -827,3 +832,57 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent) pde_put(de); } EXPORT_SYMBOL(remove_proc_entry); + +int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) +{ + struct proc_dir_entry **p; + struct proc_dir_entry *root = NULL, *de, *next; + const char *fn = name; + unsigned int len; + + spin_lock(&proc_subdir_lock); + if (__xlate_proc_name(name, &parent, &fn) != 0) { + spin_unlock(&proc_subdir_lock); + return -ENOENT; + } + len = strlen(fn); + + for (p = &parent->subdir; *p; p=&(*p)->next ) { + if (proc_match(len, fn, *p)) { + root = *p; + *p = root->next; + root->next = NULL; + break; + } + } + if (!root) { + spin_unlock(&proc_subdir_lock); + return -ENOENT; + } + de = root; + while (1) { + next = de->subdir; + if (next) { + de->subdir = next->next; + next->next = NULL; + de = next; + continue; + } + spin_unlock(&proc_subdir_lock); + + entry_rundown(de); + next = de->parent; + if (S_ISDIR(de->mode)) + next->nlink--; + de->nlink = 0; + if (de == root) + break; + pde_put(de); + + spin_lock(&proc_subdir_lock); + de = next; + } + pde_put(root); + return 0; +} +EXPORT_SYMBOL(remove_proc_subtree); diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 25f01d0bc149..b1b1fa6ffffe 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -99,7 +99,12 @@ struct mmu_gather { unsigned int need_flush : 1, /* Did free PTEs */ fast_mode : 1; /* No batching */ - unsigned int fullmm; + /* we are in the middle of an operation to clear + * a full mm and can make some optimizations */ + unsigned int fullmm : 1, + /* we have performed an operation which + * requires a complete flush of the tlb */ + need_flush_all : 1; struct mmu_gather_batch *active; struct mmu_gather_batch local; diff --git a/include/linux/ata.h b/include/linux/ata.h index 8f7a3d68371a..ee0bd9524055 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -954,7 +954,7 @@ static inline int atapi_cdb_len(const u16 *dev_id) } } -static inline bool atapi_command_packet_set(const u16 *dev_id) +static inline int atapi_command_packet_set(const u16 *dev_id) { return (dev_id[ATA_ID_CONFIG] >> 8) & 0x1f; } diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 0ea61e07a91c..7c2e030e72f1 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -12,7 +12,6 @@ struct blk_trace { int trace_state; - bool rq_based; struct rchan *rchan; unsigned long __percpu *sequence; unsigned char __percpu *msg_data; diff --git a/include/linux/capability.h b/include/linux/capability.h index 98503b792369..d9a4f7f40f32 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -35,6 +35,7 @@ struct cpu_vfs_cap_data { #define _KERNEL_CAP_T_SIZE (sizeof(kernel_cap_t)) +struct file; struct inode; struct dentry; struct user_namespace; @@ -211,6 +212,7 @@ extern bool capable(int cap); extern bool ns_capable(struct user_namespace *ns, int cap); extern bool nsown_capable(int cap); extern bool inode_capable(const struct inode *inode, int cap); +extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap); /* audit system wants to get cap info from files as well */ extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); diff --git a/include/linux/efi.h b/include/linux/efi.h index 9bf2f1fcae27..3d7df3d32c66 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -333,6 +333,7 @@ typedef efi_status_t efi_query_capsule_caps_t(efi_capsule_header_t **capsules, unsigned long count, u64 *max_size, int *reset_type); +typedef efi_status_t efi_query_variable_store_t(u32 attributes, unsigned long size); /* * EFI Configuration Table and GUID definitions @@ -575,9 +576,15 @@ extern void efi_enter_virtual_mode (void); /* switch EFI to virtual mode, if pos #ifdef CONFIG_X86 extern void efi_late_init(void); extern void efi_free_boot_services(void); +extern efi_status_t efi_query_variable_store(u32 attributes, unsigned long size); #else static inline void efi_late_init(void) {} static inline void efi_free_boot_services(void) {} + +static inline efi_status_t efi_query_variable_store(u32 attributes, unsigned long size) +{ + return EFI_SUCCESS; +} #endif extern void __iomem *efi_lookup_mapped_addr(u64 phys_addr); extern u64 efi_get_iobase (void); @@ -731,7 +738,7 @@ struct efivar_operations { efi_get_variable_t *get_variable; efi_get_next_variable_t *get_next_variable; efi_set_variable_t *set_variable; - efi_query_variable_info_t *query_variable_info; + efi_query_variable_store_t *query_variable_store; }; struct efivars { diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index e5ca8ef50e9b..52da2a250795 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -89,6 +89,7 @@ typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip, * that the call back has its own recursion protection. If it does * not set this, then the ftrace infrastructure will add recursion * protection for the caller. + * STUB - The ftrace_ops is just a place holder. */ enum { FTRACE_OPS_FL_ENABLED = 1 << 0, @@ -98,6 +99,7 @@ enum { FTRACE_OPS_FL_SAVE_REGS = 1 << 4, FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED = 1 << 5, FTRACE_OPS_FL_RECURSION_SAFE = 1 << 6, + FTRACE_OPS_FL_STUB = 1 << 7, }; struct ftrace_ops { @@ -394,7 +396,6 @@ ssize_t ftrace_filter_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos); ssize_t ftrace_notrace_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos); -loff_t ftrace_regex_lseek(struct file *file, loff_t offset, int whence); int ftrace_regex_release(struct inode *inode, struct file *file); void __init @@ -567,6 +568,8 @@ static inline int ftrace_regex_release(struct inode *inode, struct file *file) { return -ENODEV; } #endif /* CONFIG_DYNAMIC_FTRACE */ +loff_t ftrace_filter_lseek(struct file *file, loff_t offset, int whence); + /* totally disable ftrace - can not re-enable after this */ void ftrace_kill(void); diff --git a/include/linux/kexec.h b/include/linux/kexec.h index d2e6927bbaae..d78d28a733b1 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -200,6 +200,8 @@ extern size_t vmcoreinfo_max_size; int __init parse_crashkernel(char *cmdline, unsigned long long system_ram, unsigned long long *crash_size, unsigned long long *crash_base); +int parse_crashkernel_high(char *cmdline, unsigned long long system_ram, + unsigned long long *crash_size, unsigned long long *crash_base); int parse_crashkernel_low(char *cmdline, unsigned long long system_ram, unsigned long long *crash_size, unsigned long long *crash_base); int crash_shrink_memory(unsigned long new_size); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index cad77fe09d77..c13958251927 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -518,7 +518,7 @@ int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned long len); int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, - gpa_t gpa); + gpa_t gpa, unsigned long len); int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len); int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len); struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index fa7cc7244cbd..b0bcce0ddc95 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -71,6 +71,7 @@ struct gfn_to_hva_cache { u64 generation; gpa_t gpa; unsigned long hva; + unsigned long len; struct kvm_memory_slot *memslot; }; diff --git a/include/linux/libata.h b/include/linux/libata.h index 91c9d109e5f1..eae7a053dc51 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -398,6 +398,7 @@ enum { ATA_HORKAGE_NOSETXFER = (1 << 14), /* skip SETXFER, SATA only */ ATA_HORKAGE_BROKEN_FPDMA_AA = (1 << 15), /* skip AA */ ATA_HORKAGE_DUMP_ID = (1 << 16), /* dump IDENTIFY data */ + ATA_HORKAGE_MAX_SEC_LBA48 = (1 << 17), /* Set max sects to 65535 */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ diff --git a/include/linux/mm.h b/include/linux/mm.h index e19ff30ad0a2..e2091b88d24c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1611,6 +1611,8 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); +int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len); + struct page *follow_page_mask(struct vm_area_struct *vma, unsigned long address, unsigned int foll_flags, diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h index 01d25e6fc792..0214c4c146fa 100644 --- a/include/linux/netfilter/ipset/ip_set_ahash.h +++ b/include/linux/netfilter/ipset/ip_set_ahash.h @@ -291,6 +291,7 @@ ip_set_hash_destroy(struct ip_set *set) #define type_pf_data_tlist TOKEN(TYPE, PF, _data_tlist) #define type_pf_data_next TOKEN(TYPE, PF, _data_next) #define type_pf_data_flags TOKEN(TYPE, PF, _data_flags) +#define type_pf_data_reset_flags TOKEN(TYPE, PF, _data_reset_flags) #ifdef IP_SET_HASH_WITH_NETS #define type_pf_data_match TOKEN(TYPE, PF, _data_match) #else @@ -385,9 +386,9 @@ type_pf_resize(struct ip_set *set, bool retried) struct ip_set_hash *h = set->data; struct htable *t, *orig = h->table; u8 htable_bits = orig->htable_bits; - const struct type_pf_elem *data; + struct type_pf_elem *data; struct hbucket *n, *m; - u32 i, j; + u32 i, j, flags = 0; int ret; retry: @@ -412,9 +413,16 @@ retry: n = hbucket(orig, i); for (j = 0; j < n->pos; j++) { data = ahash_data(n, j); +#ifdef IP_SET_HASH_WITH_NETS + flags = 0; + type_pf_data_reset_flags(data, &flags); +#endif m = hbucket(t, HKEY(data, h->initval, htable_bits)); - ret = type_pf_elem_add(m, data, AHASH_MAX(h), 0); + ret = type_pf_elem_add(m, data, AHASH_MAX(h), flags); if (ret < 0) { +#ifdef IP_SET_HASH_WITH_NETS + type_pf_data_flags(data, flags); +#endif read_unlock_bh(&set->lock); ahash_destroy(t); if (ret == -EAGAIN) @@ -836,9 +844,9 @@ type_pf_tresize(struct ip_set *set, bool retried) struct ip_set_hash *h = set->data; struct htable *t, *orig = h->table; u8 htable_bits = orig->htable_bits; - const struct type_pf_elem *data; + struct type_pf_elem *data; struct hbucket *n, *m; - u32 i, j; + u32 i, j, flags = 0; int ret; /* Try to cleanup once */ @@ -873,10 +881,17 @@ retry: n = hbucket(orig, i); for (j = 0; j < n->pos; j++) { data = ahash_tdata(n, j); +#ifdef IP_SET_HASH_WITH_NETS + flags = 0; + type_pf_data_reset_flags(data, &flags); +#endif m = hbucket(t, HKEY(data, h->initval, htable_bits)); - ret = type_pf_elem_tadd(m, data, AHASH_MAX(h), 0, - ip_set_timeout_get(type_pf_data_timeout(data))); + ret = type_pf_elem_tadd(m, data, AHASH_MAX(h), flags, + ip_set_timeout_get(type_pf_data_timeout(data))); if (ret < 0) { +#ifdef IP_SET_HASH_WITH_NETS + type_pf_data_flags(data, flags); +#endif read_unlock_bh(&set->lock); ahash_destroy(t); if (ret == -EAGAIN) @@ -1187,6 +1202,7 @@ type_pf_gc_init(struct ip_set *set) #undef type_pf_data_tlist #undef type_pf_data_next #undef type_pf_data_flags +#undef type_pf_data_reset_flags #undef type_pf_data_match #undef type_pf_elem diff --git a/include/linux/pci.h b/include/linux/pci.h index 2461033a7987..710067f3618c 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -916,6 +916,7 @@ void pci_disable_rom(struct pci_dev *pdev); void __iomem __must_check *pci_map_rom(struct pci_dev *pdev, size_t *size); void pci_unmap_rom(struct pci_dev *pdev, void __iomem *rom); size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size); +void __iomem __must_check *pci_platform_rom(struct pci_dev *pdev, size_t *size); /* Power management related routines */ int pci_save_state(struct pci_dev *dev); diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 5a710b9c578e..87a03c746f17 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -93,14 +93,20 @@ do { \ #else /* !CONFIG_PREEMPT_COUNT */ -#define preempt_disable() do { } while (0) -#define sched_preempt_enable_no_resched() do { } while (0) -#define preempt_enable_no_resched() do { } while (0) -#define preempt_enable() do { } while (0) +/* + * Even if we don't have any preemption, we need preempt disable/enable + * to be barriers, so that we don't have things like get_user/put_user + * that can cause faults and scheduling migrate into our preempt-protected + * region. + */ +#define preempt_disable() barrier() +#define sched_preempt_enable_no_resched() barrier() +#define preempt_enable_no_resched() barrier() +#define preempt_enable() barrier() -#define preempt_disable_notrace() do { } while (0) -#define preempt_enable_no_resched_notrace() do { } while (0) -#define preempt_enable_notrace() do { } while (0) +#define preempt_disable_notrace() barrier() +#define preempt_enable_no_resched_notrace() barrier() +#define preempt_enable_notrace() barrier() #endif /* CONFIG_PREEMPT_COUNT */ diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 8307f2f94d86..94dfb2aa5533 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -117,6 +117,7 @@ struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, const struct file_operations *proc_fops, void *data); extern void remove_proc_entry(const char *name, struct proc_dir_entry *parent); +extern int remove_proc_subtree(const char *name, struct proc_dir_entry *parent); struct pid_namespace; @@ -202,6 +203,7 @@ static inline struct proc_dir_entry *proc_create_data(const char *name, return NULL; } #define remove_proc_entry(name, parent) do {} while (0) +#define remove_proc_subtree(name, parent) do {} while (0) static inline struct proc_dir_entry *proc_symlink(const char *name, struct proc_dir_entry *parent,const char *dest) {return NULL;} diff --git a/include/linux/sched.h b/include/linux/sched.h index d35d2b6ddbfb..e692a022527b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -163,9 +163,10 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) #define TASK_DEAD 64 #define TASK_WAKEKILL 128 #define TASK_WAKING 256 -#define TASK_STATE_MAX 512 +#define TASK_PARKED 512 +#define TASK_STATE_MAX 1024 -#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKW" +#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP" extern char ___assert_task_state[1 - 2*!!( sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)]; diff --git a/include/linux/security.h b/include/linux/security.h index eee7478cda70..032c366ef1c6 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1012,6 +1012,10 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * This hook can be used by the module to update any security state * associated with the TUN device's security structure. * @security pointer to the TUN devices's security structure. + * @skb_owned_by: + * This hook sets the packet's owning sock. + * @skb is the packet. + * @sk the sock which owns the packet. * * Security hooks for XFRM operations. * @@ -1638,6 +1642,7 @@ struct security_operations { int (*tun_dev_attach_queue) (void *security); int (*tun_dev_attach) (struct sock *sk, void *security); int (*tun_dev_open) (void *security); + void (*skb_owned_by) (struct sk_buff *skb, struct sock *sk); #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM @@ -2588,6 +2593,8 @@ int security_tun_dev_attach_queue(void *security); int security_tun_dev_attach(struct sock *sk, void *security); int security_tun_dev_open(void *security); +void security_skb_owned_by(struct sk_buff *skb, struct sock *sk); + #else /* CONFIG_SECURITY_NETWORK */ static inline int security_unix_stream_connect(struct sock *sock, struct sock *other, @@ -2779,6 +2786,11 @@ static inline int security_tun_dev_open(void *security) { return 0; } + +static inline void security_skb_owned_by(struct sk_buff *skb, struct sock *sk) +{ +} + #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h index a26e2fb604e6..e2369c167dbd 100644 --- a/include/linux/spinlock_up.h +++ b/include/linux/spinlock_up.h @@ -16,7 +16,10 @@ * In the debug case, 1 means unlocked, 0 means locked. (the values * are inverted, to catch initialization bugs) * - * No atomicity anywhere, we are on UP. + * No atomicity anywhere, we are on UP. However, we still need + * the compiler barriers, because we do not want the compiler to + * move potentially faulting instructions (notably user accesses) + * into the locked sequence, resulting in non-atomic execution. */ #ifdef CONFIG_DEBUG_SPINLOCK @@ -25,6 +28,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) { lock->slock = 0; + barrier(); } static inline void @@ -32,6 +36,7 @@ arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) { local_irq_save(flags); lock->slock = 0; + barrier(); } static inline int arch_spin_trylock(arch_spinlock_t *lock) @@ -39,32 +44,34 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock) char oldval = lock->slock; lock->slock = 0; + barrier(); return oldval > 0; } static inline void arch_spin_unlock(arch_spinlock_t *lock) { + barrier(); lock->slock = 1; } /* * Read-write spinlocks. No debug version. */ -#define arch_read_lock(lock) do { (void)(lock); } while (0) -#define arch_write_lock(lock) do { (void)(lock); } while (0) -#define arch_read_trylock(lock) ({ (void)(lock); 1; }) -#define arch_write_trylock(lock) ({ (void)(lock); 1; }) -#define arch_read_unlock(lock) do { (void)(lock); } while (0) -#define arch_write_unlock(lock) do { (void)(lock); } while (0) +#define arch_read_lock(lock) do { barrier(); (void)(lock); } while (0) +#define arch_write_lock(lock) do { barrier(); (void)(lock); } while (0) +#define arch_read_trylock(lock) ({ barrier(); (void)(lock); 1; }) +#define arch_write_trylock(lock) ({ barrier(); (void)(lock); 1; }) +#define arch_read_unlock(lock) do { barrier(); (void)(lock); } while (0) +#define arch_write_unlock(lock) do { barrier(); (void)(lock); } while (0) #else /* DEBUG_SPINLOCK */ #define arch_spin_is_locked(lock) ((void)(lock), 0) /* for sched.c and kernel_lock.c: */ -# define arch_spin_lock(lock) do { (void)(lock); } while (0) -# define arch_spin_lock_flags(lock, flags) do { (void)(lock); } while (0) -# define arch_spin_unlock(lock) do { (void)(lock); } while (0) -# define arch_spin_trylock(lock) ({ (void)(lock); 1; }) +# define arch_spin_lock(lock) do { barrier(); (void)(lock); } while (0) +# define arch_spin_lock_flags(lock, flags) do { barrier(); (void)(lock); } while (0) +# define arch_spin_unlock(lock) do { barrier(); (void)(lock); } while (0) +# define arch_spin_trylock(lock) ({ barrier(); (void)(lock); 1; }) #endif /* DEBUG_SPINLOCK */ #define arch_spin_is_contended(lock) (((void)(lock), 0)) diff --git a/include/linux/ssb/ssb_driver_chipcommon.h b/include/linux/ssb/ssb_driver_chipcommon.h index 9e492be5244b..6fcfe99bd999 100644 --- a/include/linux/ssb/ssb_driver_chipcommon.h +++ b/include/linux/ssb/ssb_driver_chipcommon.h @@ -219,6 +219,7 @@ #define SSB_CHIPCO_PMU_CTL 0x0600 /* PMU control */ #define SSB_CHIPCO_PMU_CTL_ILP_DIV 0xFFFF0000 /* ILP div mask */ #define SSB_CHIPCO_PMU_CTL_ILP_DIV_SHIFT 16 +#define SSB_CHIPCO_PMU_CTL_PLL_UPD 0x00000400 #define SSB_CHIPCO_PMU_CTL_NOILPONW 0x00000200 /* No ILP on wait */ #define SSB_CHIPCO_PMU_CTL_HTREQEN 0x00000100 /* HT req enable */ #define SSB_CHIPCO_PMU_CTL_ALPREQEN 0x00000080 /* ALP req enable */ @@ -667,5 +668,6 @@ enum ssb_pmu_ldo_volt_id { void ssb_pmu_set_ldo_voltage(struct ssb_chipcommon *cc, enum ssb_pmu_ldo_volt_id id, u32 voltage); void ssb_pmu_set_ldo_paref(struct ssb_chipcommon *cc, bool on); +void ssb_pmu_spuravoid_pllupdate(struct ssb_chipcommon *cc, int spuravoid); #endif /* LINUX_SSB_CHIPCO_H_ */ diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 2de42f9401d2..a5ffd32642fd 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -25,6 +25,7 @@ extern int swiotlb_force; extern void swiotlb_init(int verbose); int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose); extern unsigned long swiotlb_nr_tbl(void); +unsigned long swiotlb_size_or_default(void); extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs); /* diff --git a/include/linux/ucs2_string.h b/include/linux/ucs2_string.h new file mode 100644 index 000000000000..cbb20afdbc01 --- /dev/null +++ b/include/linux/ucs2_string.h @@ -0,0 +1,14 @@ +#ifndef _LINUX_UCS2_STRING_H_ +#define _LINUX_UCS2_STRING_H_ + +#include /* for size_t */ +#include /* for NULL */ + +typedef u16 ucs2_char_t; + +unsigned long ucs2_strnlen(const ucs2_char_t *s, size_t maxlength); +unsigned long ucs2_strlen(const ucs2_char_t *s); +unsigned long ucs2_strsize(const ucs2_char_t *data, unsigned long maxlength); +int ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len); + +#endif /* _LINUX_UCS2_STRING_H_ */ diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 40be2a0d8ae1..84a6440f1f19 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -199,6 +199,7 @@ extern bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev, /* Device notifier */ extern int register_inet6addr_notifier(struct notifier_block *nb); extern int unregister_inet6addr_notifier(struct notifier_block *nb); +extern int inet6addr_notifier_call_chain(unsigned long val, void *v); extern void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex, struct ipv6_devconf *devconf); diff --git a/include/net/irda/irlmp.h b/include/net/irda/irlmp.h index f74109144d3f..f132924cc9da 100644 --- a/include/net/irda/irlmp.h +++ b/include/net/irda/irlmp.h @@ -256,7 +256,8 @@ static inline __u32 irlmp_get_daddr(const struct lsap_cb *self) return (self && self->lap) ? self->lap->daddr : 0; } -extern const char *irlmp_reasons[]; +const char *irlmp_reason_str(LM_REASON reason); + extern int sysctl_discovery_timeout; extern int sysctl_discovery_slots; extern int sysctl_discovery; diff --git a/include/net/iucv/af_iucv.h b/include/net/iucv/af_iucv.h index cc7c19732389..714cc9a54a4c 100644 --- a/include/net/iucv/af_iucv.h +++ b/include/net/iucv/af_iucv.h @@ -130,6 +130,14 @@ struct iucv_sock { enum iucv_tx_notify n); }; +struct iucv_skb_cb { + u32 class; /* target class of message */ + u32 tag; /* tag associated with message */ + u32 offset; /* offset for skb receival */ +}; + +#define IUCV_SKB_CB(__skb) ((struct iucv_skb_cb *)&((__skb)->cb[0])) + /* iucv socket options (SOL_IUCV) */ #define SO_IPRMDATA_MSG 0x0080 /* send/recv IPRM_DATA msgs */ #define SO_MSGLIMIT 0x1000 /* get/set IUCV MSGLIMIT */ diff --git a/include/net/scm.h b/include/net/scm.h index 5a4c6a9eb122..8de2d37d2077 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -78,7 +78,7 @@ static __inline__ int scm_send(struct socket *sock, struct msghdr *msg, scm->creds.uid = INVALID_UID; scm->creds.gid = INVALID_GID; if (forcecreds) - scm_set_cred(scm, task_tgid(current), current_euid(), current_egid()); + scm_set_cred(scm, task_tgid(current), current_uid(), current_gid()); unix_get_peersec_dgram(sock, scm); if (msg->msg_controllen <= 0) return 0; diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 9961726523d0..9c1467357b03 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -257,6 +257,7 @@ TRACE_EVENT(block_bio_bounce, /** * block_bio_complete - completed all work on the block operation + * @q: queue holding the block operation * @bio: block operation completed * @error: io error value * @@ -265,9 +266,9 @@ TRACE_EVENT(block_bio_bounce, */ TRACE_EVENT(block_bio_complete, - TP_PROTO(struct bio *bio, int error), + TP_PROTO(struct request_queue *q, struct bio *bio, int error), - TP_ARGS(bio, error), + TP_ARGS(q, bio, error), TP_STRUCT__entry( __field( dev_t, dev ) @@ -278,8 +279,7 @@ TRACE_EVENT(block_bio_complete, ), TP_fast_assign( - __entry->dev = bio->bi_bdev ? - bio->bi_bdev->bd_dev : 0; + __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_sector; __entry->nr_sector = bio->bi_size >> 9; __entry->error = error; diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 5a8671e8a67f..e5586caff67a 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -147,7 +147,7 @@ TRACE_EVENT(sched_switch, __print_flags(__entry->prev_state & (TASK_STATE_MAX-1), "|", { 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" }, { 16, "Z" }, { 32, "X" }, { 64, "x" }, - { 128, "W" }) : "R", + { 128, "K" }, { 256, "W" }, { 512, "P" }) : "R", __entry->prev_state & TASK_STATE_MAX ? "+" : "", __entry->next_comm, __entry->next_pid, __entry->next_prio) ); diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 4c43b4448792..706d035fa748 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -95,15 +95,10 @@ #ifndef _LINUX_FUSE_H #define _LINUX_FUSE_H -#ifdef __linux__ +#ifdef __KERNEL__ #include #else #include -#define __u64 uint64_t -#define __s64 int64_t -#define __u32 uint32_t -#define __s32 int32_t -#define __u16 uint16_t #endif /* @@ -139,42 +134,42 @@ userspace works under 64bit kernels */ struct fuse_attr { - __u64 ino; - __u64 size; - __u64 blocks; - __u64 atime; - __u64 mtime; - __u64 ctime; - __u32 atimensec; - __u32 mtimensec; - __u32 ctimensec; - __u32 mode; - __u32 nlink; - __u32 uid; - __u32 gid; - __u32 rdev; - __u32 blksize; - __u32 padding; + uint64_t ino; + uint64_t size; + uint64_t blocks; + uint64_t atime; + uint64_t mtime; + uint64_t ctime; + uint32_t atimensec; + uint32_t mtimensec; + uint32_t ctimensec; + uint32_t mode; + uint32_t nlink; + uint32_t uid; + uint32_t gid; + uint32_t rdev; + uint32_t blksize; + uint32_t padding; }; struct fuse_kstatfs { - __u64 blocks; - __u64 bfree; - __u64 bavail; - __u64 files; - __u64 ffree; - __u32 bsize; - __u32 namelen; - __u32 frsize; - __u32 padding; - __u32 spare[6]; + uint64_t blocks; + uint64_t bfree; + uint64_t bavail; + uint64_t files; + uint64_t ffree; + uint32_t bsize; + uint32_t namelen; + uint32_t frsize; + uint32_t padding; + uint32_t spare[6]; }; struct fuse_file_lock { - __u64 start; - __u64 end; - __u32 type; - __u32 pid; /* tgid */ + uint64_t start; + uint64_t end; + uint32_t type; + uint32_t pid; /* tgid */ }; /** @@ -364,143 +359,143 @@ enum fuse_notify_code { #define FUSE_COMPAT_ENTRY_OUT_SIZE 120 struct fuse_entry_out { - __u64 nodeid; /* Inode ID */ - __u64 generation; /* Inode generation: nodeid:gen must - be unique for the fs's lifetime */ - __u64 entry_valid; /* Cache timeout for the name */ - __u64 attr_valid; /* Cache timeout for the attributes */ - __u32 entry_valid_nsec; - __u32 attr_valid_nsec; + uint64_t nodeid; /* Inode ID */ + uint64_t generation; /* Inode generation: nodeid:gen must + be unique for the fs's lifetime */ + uint64_t entry_valid; /* Cache timeout for the name */ + uint64_t attr_valid; /* Cache timeout for the attributes */ + uint32_t entry_valid_nsec; + uint32_t attr_valid_nsec; struct fuse_attr attr; }; struct fuse_forget_in { - __u64 nlookup; + uint64_t nlookup; }; struct fuse_forget_one { - __u64 nodeid; - __u64 nlookup; + uint64_t nodeid; + uint64_t nlookup; }; struct fuse_batch_forget_in { - __u32 count; - __u32 dummy; + uint32_t count; + uint32_t dummy; }; struct fuse_getattr_in { - __u32 getattr_flags; - __u32 dummy; - __u64 fh; + uint32_t getattr_flags; + uint32_t dummy; + uint64_t fh; }; #define FUSE_COMPAT_ATTR_OUT_SIZE 96 struct fuse_attr_out { - __u64 attr_valid; /* Cache timeout for the attributes */ - __u32 attr_valid_nsec; - __u32 dummy; + uint64_t attr_valid; /* Cache timeout for the attributes */ + uint32_t attr_valid_nsec; + uint32_t dummy; struct fuse_attr attr; }; #define FUSE_COMPAT_MKNOD_IN_SIZE 8 struct fuse_mknod_in { - __u32 mode; - __u32 rdev; - __u32 umask; - __u32 padding; + uint32_t mode; + uint32_t rdev; + uint32_t umask; + uint32_t padding; }; struct fuse_mkdir_in { - __u32 mode; - __u32 umask; + uint32_t mode; + uint32_t umask; }; struct fuse_rename_in { - __u64 newdir; + uint64_t newdir; }; struct fuse_link_in { - __u64 oldnodeid; + uint64_t oldnodeid; }; struct fuse_setattr_in { - __u32 valid; - __u32 padding; - __u64 fh; - __u64 size; - __u64 lock_owner; - __u64 atime; - __u64 mtime; - __u64 unused2; - __u32 atimensec; - __u32 mtimensec; - __u32 unused3; - __u32 mode; - __u32 unused4; - __u32 uid; - __u32 gid; - __u32 unused5; + uint32_t valid; + uint32_t padding; + uint64_t fh; + uint64_t size; + uint64_t lock_owner; + uint64_t atime; + uint64_t mtime; + uint64_t unused2; + uint32_t atimensec; + uint32_t mtimensec; + uint32_t unused3; + uint32_t mode; + uint32_t unused4; + uint32_t uid; + uint32_t gid; + uint32_t unused5; }; struct fuse_open_in { - __u32 flags; - __u32 unused; + uint32_t flags; + uint32_t unused; }; struct fuse_create_in { - __u32 flags; - __u32 mode; - __u32 umask; - __u32 padding; + uint32_t flags; + uint32_t mode; + uint32_t umask; + uint32_t padding; }; struct fuse_open_out { - __u64 fh; - __u32 open_flags; - __u32 padding; + uint64_t fh; + uint32_t open_flags; + uint32_t padding; }; struct fuse_release_in { - __u64 fh; - __u32 flags; - __u32 release_flags; - __u64 lock_owner; + uint64_t fh; + uint32_t flags; + uint32_t release_flags; + uint64_t lock_owner; }; struct fuse_flush_in { - __u64 fh; - __u32 unused; - __u32 padding; - __u64 lock_owner; + uint64_t fh; + uint32_t unused; + uint32_t padding; + uint64_t lock_owner; }; struct fuse_read_in { - __u64 fh; - __u64 offset; - __u32 size; - __u32 read_flags; - __u64 lock_owner; - __u32 flags; - __u32 padding; + uint64_t fh; + uint64_t offset; + uint32_t size; + uint32_t read_flags; + uint64_t lock_owner; + uint32_t flags; + uint32_t padding; }; #define FUSE_COMPAT_WRITE_IN_SIZE 24 struct fuse_write_in { - __u64 fh; - __u64 offset; - __u32 size; - __u32 write_flags; - __u64 lock_owner; - __u32 flags; - __u32 padding; + uint64_t fh; + uint64_t offset; + uint32_t size; + uint32_t write_flags; + uint64_t lock_owner; + uint32_t flags; + uint32_t padding; }; struct fuse_write_out { - __u32 size; - __u32 padding; + uint32_t size; + uint32_t padding; }; #define FUSE_COMPAT_STATFS_SIZE 48 @@ -510,32 +505,32 @@ struct fuse_statfs_out { }; struct fuse_fsync_in { - __u64 fh; - __u32 fsync_flags; - __u32 padding; + uint64_t fh; + uint32_t fsync_flags; + uint32_t padding; }; struct fuse_setxattr_in { - __u32 size; - __u32 flags; + uint32_t size; + uint32_t flags; }; struct fuse_getxattr_in { - __u32 size; - __u32 padding; + uint32_t size; + uint32_t padding; }; struct fuse_getxattr_out { - __u32 size; - __u32 padding; + uint32_t size; + uint32_t padding; }; struct fuse_lk_in { - __u64 fh; - __u64 owner; + uint64_t fh; + uint64_t owner; struct fuse_file_lock lk; - __u32 lk_flags; - __u32 padding; + uint32_t lk_flags; + uint32_t padding; }; struct fuse_lk_out { @@ -543,134 +538,135 @@ struct fuse_lk_out { }; struct fuse_access_in { - __u32 mask; - __u32 padding; + uint32_t mask; + uint32_t padding; }; struct fuse_init_in { - __u32 major; - __u32 minor; - __u32 max_readahead; - __u32 flags; + uint32_t major; + uint32_t minor; + uint32_t max_readahead; + uint32_t flags; }; struct fuse_init_out { - __u32 major; - __u32 minor; - __u32 max_readahead; - __u32 flags; - __u16 max_background; - __u16 congestion_threshold; - __u32 max_write; + uint32_t major; + uint32_t minor; + uint32_t max_readahead; + uint32_t flags; + uint16_t max_background; + uint16_t congestion_threshold; + uint32_t max_write; }; #define CUSE_INIT_INFO_MAX 4096 struct cuse_init_in { - __u32 major; - __u32 minor; - __u32 unused; - __u32 flags; + uint32_t major; + uint32_t minor; + uint32_t unused; + uint32_t flags; }; struct cuse_init_out { - __u32 major; - __u32 minor; - __u32 unused; - __u32 flags; - __u32 max_read; - __u32 max_write; - __u32 dev_major; /* chardev major */ - __u32 dev_minor; /* chardev minor */ - __u32 spare[10]; + uint32_t major; + uint32_t minor; + uint32_t unused; + uint32_t flags; + uint32_t max_read; + uint32_t max_write; + uint32_t dev_major; /* chardev major */ + uint32_t dev_minor; /* chardev minor */ + uint32_t spare[10]; }; struct fuse_interrupt_in { - __u64 unique; + uint64_t unique; }; struct fuse_bmap_in { - __u64 block; - __u32 blocksize; - __u32 padding; + uint64_t block; + uint32_t blocksize; + uint32_t padding; }; struct fuse_bmap_out { - __u64 block; + uint64_t block; }; struct fuse_ioctl_in { - __u64 fh; - __u32 flags; - __u32 cmd; - __u64 arg; - __u32 in_size; - __u32 out_size; + uint64_t fh; + uint32_t flags; + uint32_t cmd; + uint64_t arg; + uint32_t in_size; + uint32_t out_size; }; struct fuse_ioctl_iovec { - __u64 base; - __u64 len; + uint64_t base; + uint64_t len; }; struct fuse_ioctl_out { - __s32 result; - __u32 flags; - __u32 in_iovs; - __u32 out_iovs; + int32_t result; + uint32_t flags; + uint32_t in_iovs; + uint32_t out_iovs; }; struct fuse_poll_in { - __u64 fh; - __u64 kh; - __u32 flags; - __u32 events; + uint64_t fh; + uint64_t kh; + uint32_t flags; + uint32_t events; }; struct fuse_poll_out { - __u32 revents; - __u32 padding; + uint32_t revents; + uint32_t padding; }; struct fuse_notify_poll_wakeup_out { - __u64 kh; + uint64_t kh; }; struct fuse_fallocate_in { - __u64 fh; - __u64 offset; - __u64 length; - __u32 mode; - __u32 padding; + uint64_t fh; + uint64_t offset; + uint64_t length; + uint32_t mode; + uint32_t padding; }; struct fuse_in_header { - __u32 len; - __u32 opcode; - __u64 unique; - __u64 nodeid; - __u32 uid; - __u32 gid; - __u32 pid; - __u32 padding; + uint32_t len; + uint32_t opcode; + uint64_t unique; + uint64_t nodeid; + uint32_t uid; + uint32_t gid; + uint32_t pid; + uint32_t padding; }; struct fuse_out_header { - __u32 len; - __s32 error; - __u64 unique; + uint32_t len; + int32_t error; + uint64_t unique; }; struct fuse_dirent { - __u64 ino; - __u64 off; - __u32 namelen; - __u32 type; + uint64_t ino; + uint64_t off; + uint32_t namelen; + uint32_t type; char name[]; }; #define FUSE_NAME_OFFSET offsetof(struct fuse_dirent, name) -#define FUSE_DIRENT_ALIGN(x) (((x) + sizeof(__u64) - 1) & ~(sizeof(__u64) - 1)) +#define FUSE_DIRENT_ALIGN(x) \ + (((x) + sizeof(uint64_t) - 1) & ~(sizeof(uint64_t) - 1)) #define FUSE_DIRENT_SIZE(d) \ FUSE_DIRENT_ALIGN(FUSE_NAME_OFFSET + (d)->namelen) @@ -685,47 +681,47 @@ struct fuse_direntplus { FUSE_DIRENT_ALIGN(FUSE_NAME_OFFSET_DIRENTPLUS + (d)->dirent.namelen) struct fuse_notify_inval_inode_out { - __u64 ino; - __s64 off; - __s64 len; + uint64_t ino; + int64_t off; + int64_t len; }; struct fuse_notify_inval_entry_out { - __u64 parent; - __u32 namelen; - __u32 padding; + uint64_t parent; + uint32_t namelen; + uint32_t padding; }; struct fuse_notify_delete_out { - __u64 parent; - __u64 child; - __u32 namelen; - __u32 padding; + uint64_t parent; + uint64_t child; + uint32_t namelen; + uint32_t padding; }; struct fuse_notify_store_out { - __u64 nodeid; - __u64 offset; - __u32 size; - __u32 padding; + uint64_t nodeid; + uint64_t offset; + uint32_t size; + uint32_t padding; }; struct fuse_notify_retrieve_out { - __u64 notify_unique; - __u64 nodeid; - __u64 offset; - __u32 size; - __u32 padding; + uint64_t notify_unique; + uint64_t nodeid; + uint64_t offset; + uint32_t size; + uint32_t padding; }; /* Matches the size of fuse_write_in */ struct fuse_notify_retrieve_in { - __u64 dummy1; - __u64 offset; - __u32 size; - __u32 dummy2; - __u64 dummy3; - __u64 dummy4; + uint64_t dummy1; + uint64_t offset; + uint32_t size; + uint32_t dummy2; + uint64_t dummy3; + uint64_t dummy4; }; #endif /* _LINUX_FUSE_H */ diff --git a/kernel/capability.c b/kernel/capability.c index 493d97259484..f6c2ce5701e1 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -392,6 +392,30 @@ bool ns_capable(struct user_namespace *ns, int cap) } EXPORT_SYMBOL(ns_capable); +/** + * file_ns_capable - Determine if the file's opener had a capability in effect + * @file: The file we want to check + * @ns: The usernamespace we want the capability in + * @cap: The capability to be tested for + * + * Return true if task that opened the file had a capability in effect + * when the file was opened. + * + * This does not set PF_SUPERPRIV because the caller may not + * actually be privileged. + */ +bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap) +{ + if (WARN_ON_ONCE(!cap_valid(cap))) + return false; + + if (security_capable(file->f_cred, ns, cap) == 0) + return true; + + return false; +} +EXPORT_SYMBOL(file_ns_capable); + /** * capable - Determine if the current task has a superior capability in effect * @cap: The capability to be tested for diff --git a/kernel/events/core.c b/kernel/events/core.c index 59412d037eed..4d3124b39277 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4737,7 +4737,8 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event) } else { if (arch_vma_name(mmap_event->vma)) { name = strncpy(tmp, arch_vma_name(mmap_event->vma), - sizeof(tmp)); + sizeof(tmp) - 1); + tmp[sizeof(tmp) - 1] = '\0'; goto got_name; } @@ -5330,7 +5331,7 @@ static void sw_perf_event_destroy(struct perf_event *event) static int perf_swevent_init(struct perf_event *event) { - int event_id = event->attr.config; + u64 event_id = event->attr.config; if (event->attr.type != PERF_TYPE_SOFTWARE) return -ENOENT; @@ -5986,6 +5987,7 @@ skip_type: if (pmu->pmu_cpu_context) goto got_cpu_context; + ret = -ENOMEM; pmu->pmu_cpu_context = alloc_percpu(struct perf_cpu_context); if (!pmu->pmu_cpu_context) goto free_dev; diff --git a/kernel/events/internal.h b/kernel/events/internal.h index d56a64c99a8b..eb675c4d59df 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -16,7 +16,7 @@ struct ring_buffer { int page_order; /* allocation order */ #endif int nr_pages; /* nr of data pages */ - int writable; /* are we writable */ + int overwrite; /* can overwrite itself */ atomic_t poll; /* POLL_ for wakeups */ diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 23cb34ff3973..97fddb09762b 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -18,12 +18,24 @@ static bool perf_output_space(struct ring_buffer *rb, unsigned long tail, unsigned long offset, unsigned long head) { - unsigned long mask; + unsigned long sz = perf_data_size(rb); + unsigned long mask = sz - 1; - if (!rb->writable) + /* + * check if user-writable + * overwrite : over-write its own tail + * !overwrite: buffer possibly drops events. + */ + if (rb->overwrite) return true; - mask = perf_data_size(rb) - 1; + /* + * verify that payload is not bigger than buffer + * otherwise masking logic may fail to detect + * the "not enough space" condition + */ + if ((head - offset) > sz) + return false; offset = (offset - tail) & mask; head = (head - tail) & mask; @@ -212,7 +224,9 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags) rb->watermark = max_size / 2; if (flags & RING_BUFFER_WRITABLE) - rb->writable = 1; + rb->overwrite = 0; + else + rb->overwrite = 1; atomic_set(&rb->refcount, 1); diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index cc47812d3feb..14be27feda49 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -63,6 +63,7 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = { + .lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock), .clock_base = { { @@ -1642,8 +1643,6 @@ static void __cpuinit init_hrtimers_cpu(int cpu) struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu); int i; - raw_spin_lock_init(&cpu_base->lock); - for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { cpu_base->clock_base[i].cpu_base = cpu_base; timerqueue_init_head(&cpu_base->clock_base[i].active); diff --git a/kernel/kexec.c b/kernel/kexec.c index bddd3d7a74b6..ffd4e111fd67 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -55,7 +55,7 @@ struct resource crashk_res = { .flags = IORESOURCE_BUSY | IORESOURCE_MEM }; struct resource crashk_low_res = { - .name = "Crash kernel low", + .name = "Crash kernel", .start = 0, .end = 0, .flags = IORESOURCE_BUSY | IORESOURCE_MEM @@ -1368,35 +1368,114 @@ static int __init parse_crashkernel_simple(char *cmdline, return 0; } +#define SUFFIX_HIGH 0 +#define SUFFIX_LOW 1 +#define SUFFIX_NULL 2 +static __initdata char *suffix_tbl[] = { + [SUFFIX_HIGH] = ",high", + [SUFFIX_LOW] = ",low", + [SUFFIX_NULL] = NULL, +}; + /* - * That function is the entry point for command line parsing and should be - * called from the arch-specific code. + * That function parses "suffix" crashkernel command lines like + * + * crashkernel=size,[high|low] + * + * It returns 0 on success and -EINVAL on failure. */ +static int __init parse_crashkernel_suffix(char *cmdline, + unsigned long long *crash_size, + unsigned long long *crash_base, + const char *suffix) +{ + char *cur = cmdline; + + *crash_size = memparse(cmdline, &cur); + if (cmdline == cur) { + pr_warn("crashkernel: memory value expected\n"); + return -EINVAL; + } + + /* check with suffix */ + if (strncmp(cur, suffix, strlen(suffix))) { + pr_warn("crashkernel: unrecognized char\n"); + return -EINVAL; + } + cur += strlen(suffix); + if (*cur != ' ' && *cur != '\0') { + pr_warn("crashkernel: unrecognized char\n"); + return -EINVAL; + } + + return 0; +} + +static __init char *get_last_crashkernel(char *cmdline, + const char *name, + const char *suffix) +{ + char *p = cmdline, *ck_cmdline = NULL; + + /* find crashkernel and use the last one if there are more */ + p = strstr(p, name); + while (p) { + char *end_p = strchr(p, ' '); + char *q; + + if (!end_p) + end_p = p + strlen(p); + + if (!suffix) { + int i; + + /* skip the one with any known suffix */ + for (i = 0; suffix_tbl[i]; i++) { + q = end_p - strlen(suffix_tbl[i]); + if (!strncmp(q, suffix_tbl[i], + strlen(suffix_tbl[i]))) + goto next; + } + ck_cmdline = p; + } else { + q = end_p - strlen(suffix); + if (!strncmp(q, suffix, strlen(suffix))) + ck_cmdline = p; + } +next: + p = strstr(p+1, name); + } + + if (!ck_cmdline) + return NULL; + + return ck_cmdline; +} + static int __init __parse_crashkernel(char *cmdline, unsigned long long system_ram, unsigned long long *crash_size, unsigned long long *crash_base, - const char *name) + const char *name, + const char *suffix) { - char *p = cmdline, *ck_cmdline = NULL; char *first_colon, *first_space; + char *ck_cmdline; BUG_ON(!crash_size || !crash_base); *crash_size = 0; *crash_base = 0; - /* find crashkernel and use the last one if there are more */ - p = strstr(p, name); - while (p) { - ck_cmdline = p; - p = strstr(p+1, name); - } + ck_cmdline = get_last_crashkernel(cmdline, name, suffix); if (!ck_cmdline) return -EINVAL; ck_cmdline += strlen(name); + if (suffix) + return parse_crashkernel_suffix(ck_cmdline, crash_size, + crash_base, suffix); /* * if the commandline contains a ':', then that's the extended * syntax -- if not, it must be the classic syntax @@ -1413,13 +1492,26 @@ static int __init __parse_crashkernel(char *cmdline, return 0; } +/* + * That function is the entry point for command line parsing and should be + * called from the arch-specific code. + */ int __init parse_crashkernel(char *cmdline, unsigned long long system_ram, unsigned long long *crash_size, unsigned long long *crash_base) { return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base, - "crashkernel="); + "crashkernel=", NULL); +} + +int __init parse_crashkernel_high(char *cmdline, + unsigned long long system_ram, + unsigned long long *crash_size, + unsigned long long *crash_base) +{ + return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base, + "crashkernel=", suffix_tbl[SUFFIX_HIGH]); } int __init parse_crashkernel_low(char *cmdline, @@ -1428,7 +1520,7 @@ int __init parse_crashkernel_low(char *cmdline, unsigned long long *crash_base) { return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base, - "crashkernel_low="); + "crashkernel=", suffix_tbl[SUFFIX_LOW]); } static void update_vmcoreinfo_note(void) diff --git a/kernel/kprobes.c b/kernel/kprobes.c index e35be53f6613..3fed7f0cbcdf 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -794,16 +794,16 @@ out: } #ifdef CONFIG_SYSCTL -/* This should be called with kprobe_mutex locked */ static void __kprobes optimize_all_kprobes(void) { struct hlist_head *head; struct kprobe *p; unsigned int i; + mutex_lock(&kprobe_mutex); /* If optimization is already allowed, just return */ if (kprobes_allow_optimization) - return; + goto out; kprobes_allow_optimization = true; for (i = 0; i < KPROBE_TABLE_SIZE; i++) { @@ -813,18 +813,22 @@ static void __kprobes optimize_all_kprobes(void) optimize_kprobe(p); } printk(KERN_INFO "Kprobes globally optimized\n"); +out: + mutex_unlock(&kprobe_mutex); } -/* This should be called with kprobe_mutex locked */ static void __kprobes unoptimize_all_kprobes(void) { struct hlist_head *head; struct kprobe *p; unsigned int i; + mutex_lock(&kprobe_mutex); /* If optimization is already prohibited, just return */ - if (!kprobes_allow_optimization) + if (!kprobes_allow_optimization) { + mutex_unlock(&kprobe_mutex); return; + } kprobes_allow_optimization = false; for (i = 0; i < KPROBE_TABLE_SIZE; i++) { @@ -834,11 +838,14 @@ static void __kprobes unoptimize_all_kprobes(void) unoptimize_kprobe(p, false); } } + mutex_unlock(&kprobe_mutex); + /* Wait for unoptimizing completion */ wait_for_kprobe_optimizer(); printk(KERN_INFO "Kprobes globally unoptimized\n"); } +static DEFINE_MUTEX(kprobe_sysctl_mutex); int sysctl_kprobes_optimization; int proc_kprobes_optimization_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, @@ -846,7 +853,7 @@ int proc_kprobes_optimization_handler(struct ctl_table *table, int write, { int ret; - mutex_lock(&kprobe_mutex); + mutex_lock(&kprobe_sysctl_mutex); sysctl_kprobes_optimization = kprobes_allow_optimization ? 1 : 0; ret = proc_dointvec_minmax(table, write, buffer, length, ppos); @@ -854,7 +861,7 @@ int proc_kprobes_optimization_handler(struct ctl_table *table, int write, optimize_all_kprobes(); else unoptimize_all_kprobes(); - mutex_unlock(&kprobe_mutex); + mutex_unlock(&kprobe_sysctl_mutex); return ret; } diff --git a/kernel/kthread.c b/kernel/kthread.c index 691dc2ef9baf..9eb7fed0bbaa 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -124,12 +124,12 @@ void *kthread_data(struct task_struct *task) static void __kthread_parkme(struct kthread *self) { - __set_current_state(TASK_INTERRUPTIBLE); + __set_current_state(TASK_PARKED); while (test_bit(KTHREAD_SHOULD_PARK, &self->flags)) { if (!test_and_set_bit(KTHREAD_IS_PARKED, &self->flags)) complete(&self->parked); schedule(); - __set_current_state(TASK_INTERRUPTIBLE); + __set_current_state(TASK_PARKED); } clear_bit(KTHREAD_IS_PARKED, &self->flags); __set_current_state(TASK_RUNNING); @@ -256,8 +256,13 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), } EXPORT_SYMBOL(kthread_create_on_node); -static void __kthread_bind(struct task_struct *p, unsigned int cpu) +static void __kthread_bind(struct task_struct *p, unsigned int cpu, long state) { + /* Must have done schedule() in kthread() before we set_task_cpu */ + if (!wait_task_inactive(p, state)) { + WARN_ON(1); + return; + } /* It's safe because the task is inactive. */ do_set_cpus_allowed(p, cpumask_of(cpu)); p->flags |= PF_THREAD_BOUND; @@ -274,12 +279,7 @@ static void __kthread_bind(struct task_struct *p, unsigned int cpu) */ void kthread_bind(struct task_struct *p, unsigned int cpu) { - /* Must have done schedule() in kthread() before we set_task_cpu */ - if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE)) { - WARN_ON(1); - return; - } - __kthread_bind(p, cpu); + __kthread_bind(p, cpu, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(kthread_bind); @@ -324,6 +324,22 @@ static struct kthread *task_get_live_kthread(struct task_struct *k) return NULL; } +static void __kthread_unpark(struct task_struct *k, struct kthread *kthread) +{ + clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags); + /* + * We clear the IS_PARKED bit here as we don't wait + * until the task has left the park code. So if we'd + * park before that happens we'd see the IS_PARKED bit + * which might be about to be cleared. + */ + if (test_and_clear_bit(KTHREAD_IS_PARKED, &kthread->flags)) { + if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags)) + __kthread_bind(k, kthread->cpu, TASK_PARKED); + wake_up_state(k, TASK_PARKED); + } +} + /** * kthread_unpark - unpark a thread created by kthread_create(). * @k: thread created by kthread_create(). @@ -336,20 +352,8 @@ void kthread_unpark(struct task_struct *k) { struct kthread *kthread = task_get_live_kthread(k); - if (kthread) { - clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags); - /* - * We clear the IS_PARKED bit here as we don't wait - * until the task has left the park code. So if we'd - * park before that happens we'd see the IS_PARKED bit - * which might be about to be cleared. - */ - if (test_and_clear_bit(KTHREAD_IS_PARKED, &kthread->flags)) { - if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags)) - __kthread_bind(k, kthread->cpu); - wake_up_process(k); - } - } + if (kthread) + __kthread_unpark(k, kthread); put_task_struct(k); } @@ -407,7 +411,7 @@ int kthread_stop(struct task_struct *k) trace_sched_kthread_stop(k); if (kthread) { set_bit(KTHREAD_SHOULD_STOP, &kthread->flags); - clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags); + __kthread_unpark(k, kthread); wake_up_process(k); wait_for_completion(&kthread->exited); } diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index c685e31492df..c3ae1446461c 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -176,10 +176,36 @@ static u64 sched_clock_remote(struct sched_clock_data *scd) u64 this_clock, remote_clock; u64 *ptr, old_val, val; +#if BITS_PER_LONG != 64 +again: + /* + * Careful here: The local and the remote clock values need to + * be read out atomic as we need to compare the values and + * then update either the local or the remote side. So the + * cmpxchg64 below only protects one readout. + * + * We must reread via sched_clock_local() in the retry case on + * 32bit as an NMI could use sched_clock_local() via the + * tracer and hit between the readout of + * the low32bit and the high 32bit portion. + */ + this_clock = sched_clock_local(my_scd); + /* + * We must enforce atomic readout on 32bit, otherwise the + * update on the remote cpu can hit inbetween the readout of + * the low32bit and the high 32bit portion. + */ + remote_clock = cmpxchg64(&scd->clock, 0, 0); +#else + /* + * On 64bit the read of [my]scd->clock is atomic versus the + * update, so we can avoid the above 32bit dance. + */ sched_clock_local(my_scd); again: this_clock = my_scd->clock; remote_clock = scd->clock; +#endif /* * Use the opportunity that we have both locks diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 7f12624a393c..67d04651f44b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1498,8 +1498,10 @@ static void try_to_wake_up_local(struct task_struct *p) { struct rq *rq = task_rq(p); - BUG_ON(rq != this_rq()); - BUG_ON(p == current); + if (WARN_ON_ONCE(rq != this_rq()) || + WARN_ON_ONCE(p == current)) + return; + lockdep_assert_held(&rq->lock); if (!raw_spin_trylock(&p->pi_lock)) { @@ -4999,7 +5001,7 @@ static void sd_free_ctl_entry(struct ctl_table **tablep) } static int min_load_idx = 0; -static int max_load_idx = CPU_LOAD_IDX_MAX; +static int max_load_idx = CPU_LOAD_IDX_MAX-1; static void set_table_entry(struct ctl_table *entry, diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index ed12cbb135f4..e93cca92f38b 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -310,7 +310,7 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) t = tsk; do { - task_cputime(tsk, &utime, &stime); + task_cputime(t, &utime, &stime); times->utime += utime; times->stime += stime; times->sum_exec_runtime += task_sched_runtime(t); diff --git a/kernel/signal.c b/kernel/signal.c index 497330ec2ae9..06ff7764ab7c 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2950,7 +2950,7 @@ do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info) static int do_tkill(pid_t tgid, pid_t pid, int sig) { - struct siginfo info; + struct siginfo info = {}; info.si_signo = sig; info.si_errno = 0; diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 8eaed9aa9cf0..02fc5c933673 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -185,8 +185,18 @@ __smpboot_create_thread(struct smp_hotplug_thread *ht, unsigned int cpu) } get_task_struct(tsk); *per_cpu_ptr(ht->store, cpu) = tsk; - if (ht->create) - ht->create(cpu); + if (ht->create) { + /* + * Make sure that the task has actually scheduled out + * into park position, before calling the create + * callback. At least the migration thread callback + * requires that the task is off the runqueue. + */ + if (!wait_task_inactive(tsk, TASK_PARKED)) + WARN_ON(1); + else + ht->create(cpu); + } return 0; } diff --git a/kernel/sys.c b/kernel/sys.c index 39c9c4a2949f..0da73cf73e60 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -324,7 +324,6 @@ void kernel_restart_prepare(char *cmd) system_state = SYSTEM_RESTART; usermodehelper_disable(); device_shutdown(); - syscore_shutdown(); } /** @@ -370,6 +369,7 @@ void kernel_restart(char *cmd) { kernel_restart_prepare(cmd); disable_nonboot_cpus(); + syscore_shutdown(); if (!cmd) printk(KERN_EMERG "Restarting system.\n"); else @@ -395,6 +395,7 @@ static void kernel_shutdown_prepare(enum system_states state) void kernel_halt(void) { kernel_shutdown_prepare(SYSTEM_HALT); + disable_nonboot_cpus(); syscore_shutdown(); printk(KERN_EMERG "System halted.\n"); kmsg_dump(KMSG_DUMP_HALT); diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 9e5b8c272eec..5a0f781cd729 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -739,12 +739,6 @@ static void blk_add_trace_rq_complete(void *ignore, struct request_queue *q, struct request *rq) { - struct blk_trace *bt = q->blk_trace; - - /* if control ever passes through here, it's a request based driver */ - if (unlikely(bt && !bt->rq_based)) - bt->rq_based = true; - blk_add_trace_rq(q, rq, BLK_TA_COMPLETE); } @@ -780,24 +774,10 @@ static void blk_add_trace_bio_bounce(void *ignore, blk_add_trace_bio(q, bio, BLK_TA_BOUNCE, 0); } -static void blk_add_trace_bio_complete(void *ignore, struct bio *bio, int error) +static void blk_add_trace_bio_complete(void *ignore, + struct request_queue *q, struct bio *bio, + int error) { - struct request_queue *q; - struct blk_trace *bt; - - if (!bio->bi_bdev) - return; - - q = bdev_get_queue(bio->bi_bdev); - bt = q->blk_trace; - - /* - * Request based drivers will generate both rq and bio completions. - * Ignore bio ones. - */ - if (likely(!bt) || bt->rq_based) - return; - blk_add_trace_bio(q, bio, BLK_TA_COMPLETE, error); } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 6893d5a2bf08..b3fde6d7b7fc 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -66,7 +66,7 @@ static struct ftrace_ops ftrace_list_end __read_mostly = { .func = ftrace_stub, - .flags = FTRACE_OPS_FL_RECURSION_SAFE, + .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_STUB, }; /* ftrace_enabled is a method to turn ftrace on or off */ @@ -694,7 +694,6 @@ int ftrace_profile_pages_init(struct ftrace_profile_stat *stat) free_page(tmp); } - free_page((unsigned long)stat->pages); stat->pages = NULL; stat->start = NULL; @@ -1053,6 +1052,19 @@ static __init void ftrace_profile_debugfs(struct dentry *d_tracer) static struct pid * const ftrace_swapper_pid = &init_struct_pid; +loff_t +ftrace_filter_lseek(struct file *file, loff_t offset, int whence) +{ + loff_t ret; + + if (file->f_mode & FMODE_READ) + ret = seq_lseek(file, offset, whence); + else + file->f_pos = ret = 1; + + return ret; +} + #ifdef CONFIG_DYNAMIC_FTRACE #ifndef CONFIG_FTRACE_MCOUNT_RECORD @@ -2613,7 +2625,7 @@ static void ftrace_filter_reset(struct ftrace_hash *hash) * routine, you can use ftrace_filter_write() for the write * routine if @flag has FTRACE_ITER_FILTER set, or * ftrace_notrace_write() if @flag has FTRACE_ITER_NOTRACE set. - * ftrace_regex_lseek() should be used as the lseek routine, and + * ftrace_filter_lseek() should be used as the lseek routine, and * release must call ftrace_regex_release(). */ int @@ -2697,19 +2709,6 @@ ftrace_notrace_open(struct inode *inode, struct file *file) inode, file); } -loff_t -ftrace_regex_lseek(struct file *file, loff_t offset, int whence) -{ - loff_t ret; - - if (file->f_mode & FMODE_READ) - ret = seq_lseek(file, offset, whence); - else - file->f_pos = ret = 1; - - return ret; -} - static int ftrace_match(char *str, char *regex, int len, int type) { int matched = 0; @@ -3441,14 +3440,14 @@ static char ftrace_filter_buf[FTRACE_FILTER_SIZE] __initdata; static int __init set_ftrace_notrace(char *str) { - strncpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE); + strlcpy(ftrace_notrace_buf, str, FTRACE_FILTER_SIZE); return 1; } __setup("ftrace_notrace=", set_ftrace_notrace); static int __init set_ftrace_filter(char *str) { - strncpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE); + strlcpy(ftrace_filter_buf, str, FTRACE_FILTER_SIZE); return 1; } __setup("ftrace_filter=", set_ftrace_filter); @@ -3571,7 +3570,7 @@ static const struct file_operations ftrace_filter_fops = { .open = ftrace_filter_open, .read = seq_read, .write = ftrace_filter_write, - .llseek = ftrace_regex_lseek, + .llseek = ftrace_filter_lseek, .release = ftrace_regex_release, }; @@ -3579,7 +3578,7 @@ static const struct file_operations ftrace_notrace_fops = { .open = ftrace_notrace_open, .read = seq_read, .write = ftrace_notrace_write, - .llseek = ftrace_regex_lseek, + .llseek = ftrace_filter_lseek, .release = ftrace_regex_release, }; @@ -3784,8 +3783,8 @@ static const struct file_operations ftrace_graph_fops = { .open = ftrace_graph_open, .read = seq_read, .write = ftrace_graph_write, + .llseek = ftrace_filter_lseek, .release = ftrace_graph_release, - .llseek = seq_lseek, }; #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ @@ -4131,7 +4130,8 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip, preempt_disable_notrace(); trace_recursion_set(TRACE_CONTROL_BIT); do_for_each_ftrace_op(op, ftrace_control_list) { - if (!ftrace_function_local_disabled(op) && + if (!(op->flags & FTRACE_OPS_FL_STUB) && + !ftrace_function_local_disabled(op) && ftrace_ops_test(op, ip)) op->func(ip, parent_ip, op, regs); } while_for_each_ftrace_op(op); @@ -4439,7 +4439,7 @@ static const struct file_operations ftrace_pid_fops = { .open = ftrace_pid_open, .write = ftrace_pid_write, .read = seq_read, - .llseek = seq_lseek, + .llseek = ftrace_filter_lseek, .release = ftrace_pid_release, }; @@ -4555,12 +4555,8 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, ftrace_startup_sysctl(); /* we are starting ftrace again */ - if (ftrace_ops_list != &ftrace_list_end) { - if (ftrace_ops_list->next == &ftrace_list_end) - ftrace_trace_function = ftrace_ops_list->func; - else - ftrace_trace_function = ftrace_ops_list_func; - } + if (ftrace_ops_list != &ftrace_list_end) + update_ftrace_function(); } else { /* stopping ftrace calls (just send to ftrace_stub) */ diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 4f1dade56981..66338c4f7f4b 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -132,7 +132,7 @@ static char *default_bootup_tracer; static int __init set_cmdline_ftrace(char *str) { - strncpy(bootup_tracer_buf, str, MAX_TRACER_SIZE); + strlcpy(bootup_tracer_buf, str, MAX_TRACER_SIZE); default_bootup_tracer = bootup_tracer_buf; /* We are using ftrace early, expand it */ ring_buffer_expanded = 1; @@ -162,7 +162,7 @@ static char *trace_boot_options __initdata; static int __init set_trace_boot_options(char *str) { - strncpy(trace_boot_options_buf, str, MAX_TRACER_SIZE); + strlcpy(trace_boot_options_buf, str, MAX_TRACER_SIZE); trace_boot_options = trace_boot_options_buf; return 0; } @@ -744,8 +744,11 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) return; WARN_ON_ONCE(!irqs_disabled()); - if (WARN_ON_ONCE(!current_trace->allocated_snapshot)) + if (!current_trace->allocated_snapshot) { + /* Only the nop tracer should hit this when disabling */ + WARN_ON_ONCE(current_trace != &nop_trace); return; + } arch_spin_lock(&ftrace_max_lock); diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 42ca822fc701..83a8b5b7bd35 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -322,7 +322,7 @@ static const struct file_operations stack_trace_filter_fops = { .open = stack_trace_filter_open, .read = seq_read, .write = ftrace_filter_write, - .llseek = ftrace_regex_lseek, + .llseek = ftrace_filter_lseek, .release = ftrace_regex_release, }; diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index a54f26f82eb2..e134d8f365dd 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -25,7 +25,8 @@ static struct kmem_cache *user_ns_cachep __read_mostly; -static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid, +static bool new_idmap_permitted(const struct file *file, + struct user_namespace *ns, int cap_setid, struct uid_gid_map *map); static void set_cred_user_ns(struct cred *cred, struct user_namespace *user_ns) @@ -612,10 +613,10 @@ static ssize_t map_write(struct file *file, const char __user *buf, if (map->nr_extents != 0) goto out; - /* Require the appropriate privilege CAP_SETUID or CAP_SETGID - * over the user namespace in order to set the id mapping. + /* + * Adjusting namespace settings requires capabilities on the target. */ - if (cap_valid(cap_setid) && !ns_capable(ns, cap_setid)) + if (cap_valid(cap_setid) && !file_ns_capable(file, ns, CAP_SYS_ADMIN)) goto out; /* Get a buffer */ @@ -700,7 +701,7 @@ static ssize_t map_write(struct file *file, const char __user *buf, ret = -EPERM; /* Validate the user is allowed to use user id's mapped to. */ - if (!new_idmap_permitted(ns, cap_setid, &new_map)) + if (!new_idmap_permitted(file, ns, cap_setid, &new_map)) goto out; /* Map the lower ids from the parent user namespace to the @@ -787,7 +788,8 @@ ssize_t proc_projid_map_write(struct file *file, const char __user *buf, size_t &ns->projid_map, &ns->parent->projid_map); } -static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid, +static bool new_idmap_permitted(const struct file *file, + struct user_namespace *ns, int cap_setid, struct uid_gid_map *new_map) { /* Allow mapping to your own filesystem ids */ @@ -795,12 +797,12 @@ static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid, u32 id = new_map->extent[0].lower_first; if (cap_setid == CAP_SETUID) { kuid_t uid = make_kuid(ns->parent, id); - if (uid_eq(uid, current_fsuid())) + if (uid_eq(uid, file->f_cred->fsuid)) return true; } else if (cap_setid == CAP_SETGID) { kgid_t gid = make_kgid(ns->parent, id); - if (gid_eq(gid, current_fsgid())) + if (gid_eq(gid, file->f_cred->fsgid)) return true; } } @@ -811,8 +813,10 @@ static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid, /* Allow the specified ids if we have the appropriate capability * (CAP_SETUID or CAP_SETGID) over the parent user namespace. + * And the opener of the id file also had the approprpiate capability. */ - if (ns_capable(ns->parent, cap_setid)) + if (ns_capable(ns->parent, cap_setid) && + file_ns_capable(file, ns->parent, cap_setid)) return true; return false; diff --git a/lib/Kconfig b/lib/Kconfig index 3958dc4389f9..fe01d418b09a 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -404,4 +404,7 @@ config OID_REGISTRY help Enable fast lookup object identifier registry. +config UCS2_STRING + tristate + endmenu diff --git a/lib/Makefile b/lib/Makefile index d7946ff75b2e..6e2cc561f761 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -174,3 +174,5 @@ quiet_cmd_build_OID_registry = GEN $@ cmd_build_OID_registry = perl $(srctree)/$(src)/build_OID_registry $< $@ clean-files += oid_registry_data.c + +obj-$(CONFIG_UCS2_STRING) += ucs2_string.o diff --git a/lib/kobject.c b/lib/kobject.c index e07ee1fcd6f1..a65486613d79 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -529,6 +529,13 @@ struct kobject *kobject_get(struct kobject *kobj) return kobj; } +static struct kobject *kobject_get_unless_zero(struct kobject *kobj) +{ + if (!kref_get_unless_zero(&kobj->kref)) + kobj = NULL; + return kobj; +} + /* * kobject_cleanup - free kobject resources. * @kobj: object to cleanup @@ -751,7 +758,7 @@ struct kobject *kset_find_obj(struct kset *kset, const char *name) list_for_each_entry(k, &kset->list, entry) { if (kobject_name(k) && !strcmp(kobject_name(k), name)) { - ret = kobject_get(k); + ret = kobject_get_unless_zero(k); break; } } diff --git a/lib/swiotlb.c b/lib/swiotlb.c index bfe02b8fc55b..d23762e6652c 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -105,9 +105,9 @@ setup_io_tlb_npages(char *str) if (!strcmp(str, "force")) swiotlb_force = 1; - return 1; + return 0; } -__setup("swiotlb=", setup_io_tlb_npages); +early_param("swiotlb", setup_io_tlb_npages); /* make io_tlb_overflow tunable too? */ unsigned long swiotlb_nr_tbl(void) @@ -115,6 +115,18 @@ unsigned long swiotlb_nr_tbl(void) return io_tlb_nslabs; } EXPORT_SYMBOL_GPL(swiotlb_nr_tbl); + +/* default to 64MB */ +#define IO_TLB_DEFAULT_SIZE (64UL<<20) +unsigned long swiotlb_size_or_default(void) +{ + unsigned long size; + + size = io_tlb_nslabs << IO_TLB_SHIFT; + + return size ? size : (IO_TLB_DEFAULT_SIZE); +} + /* Note that this doesn't work with highmem page */ static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev, volatile void *address) @@ -188,8 +200,7 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) void __init swiotlb_init(int verbose) { - /* default to 64MB */ - size_t default_size = 64UL<<20; + size_t default_size = IO_TLB_DEFAULT_SIZE; unsigned char *vstart; unsigned long bytes; diff --git a/lib/ucs2_string.c b/lib/ucs2_string.c new file mode 100644 index 000000000000..6f500ef2301d --- /dev/null +++ b/lib/ucs2_string.c @@ -0,0 +1,51 @@ +#include +#include + +/* Return the number of unicode characters in data */ +unsigned long +ucs2_strnlen(const ucs2_char_t *s, size_t maxlength) +{ + unsigned long length = 0; + + while (*s++ != 0 && length < maxlength) + length++; + return length; +} +EXPORT_SYMBOL(ucs2_strnlen); + +unsigned long +ucs2_strlen(const ucs2_char_t *s) +{ + return ucs2_strnlen(s, ~0UL); +} +EXPORT_SYMBOL(ucs2_strlen); + +/* + * Return the number of bytes is the length of this string + * Note: this is NOT the same as the number of unicode characters + */ +unsigned long +ucs2_strsize(const ucs2_char_t *data, unsigned long maxlength) +{ + return ucs2_strnlen(data, maxlength/sizeof(ucs2_char_t)) * sizeof(ucs2_char_t); +} +EXPORT_SYMBOL(ucs2_strsize); + +int +ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len) +{ + while (1) { + if (len == 0) + return 0; + if (*a < *b) + return -1; + if (*a > *b) + return 1; + if (*a == 0) /* implies *b == 0 */ + return 0; + a++; + b++; + len--; + } +} +EXPORT_SYMBOL(ucs2_strncmp); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ca9a7c6d7e97..1a12f5b9a0ab 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2961,7 +2961,17 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, break; } - if (absent || + /* + * We need call hugetlb_fault for both hugepages under migration + * (in which case hugetlb_fault waits for the migration,) and + * hwpoisoned hugepages (in which case we need to prevent the + * caller from accessing to them.) In order to do this, we use + * here is_swap_pte instead of is_hugetlb_entry_migration and + * is_hugetlb_entry_hwpoisoned. This is because it simply covers + * both cases, and because we can't follow correct pages + * directly from any kind of swap entries. + */ + if (absent || is_swap_pte(huge_ptep_get(pte)) || ((flags & FOLL_WRITE) && !pte_write(huge_ptep_get(pte)))) { int ret; diff --git a/mm/memory.c b/mm/memory.c index 494526ae024a..ba94dec5b259 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -216,6 +216,7 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm) tlb->mm = mm; tlb->fullmm = fullmm; + tlb->need_flush_all = 0; tlb->start = -1UL; tlb->end = 0; tlb->need_flush = 0; @@ -2392,6 +2393,53 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, } EXPORT_SYMBOL(remap_pfn_range); +/** + * vm_iomap_memory - remap memory to userspace + * @vma: user vma to map to + * @start: start of area + * @len: size of area + * + * This is a simplified io_remap_pfn_range() for common driver use. The + * driver just needs to give us the physical memory range to be mapped, + * we'll figure out the rest from the vma information. + * + * NOTE! Some drivers might want to tweak vma->vm_page_prot first to get + * whatever write-combining details or similar. + */ +int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len) +{ + unsigned long vm_len, pfn, pages; + + /* Check that the physical memory area passed in looks valid */ + if (start + len < start) + return -EINVAL; + /* + * You *really* shouldn't map things that aren't page-aligned, + * but we've historically allowed it because IO memory might + * just have smaller alignment. + */ + len += start & ~PAGE_MASK; + pfn = start >> PAGE_SHIFT; + pages = (len + ~PAGE_MASK) >> PAGE_SHIFT; + if (pfn + pages < pfn) + return -EINVAL; + + /* We start the mapping 'vm_pgoff' pages into the area */ + if (vma->vm_pgoff > pages) + return -EINVAL; + pfn += vma->vm_pgoff; + pages -= vma->vm_pgoff; + + /* Can we fit all of the mapping? */ + vm_len = vma->vm_end - vma->vm_start; + if (vm_len >> PAGE_SHIFT > pages) + return -EINVAL; + + /* Ok, let it rip */ + return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot); +} +EXPORT_SYMBOL(vm_iomap_memory); + static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, pte_fn_t fn, void *data) diff --git a/mm/vmscan.c b/mm/vmscan.c index 88c5fed8b9a4..669fba39be1a 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3188,9 +3188,9 @@ int kswapd_run(int nid) if (IS_ERR(pgdat->kswapd)) { /* failure at boot is fatal */ BUG_ON(system_state == SYSTEM_BOOTING); - pgdat->kswapd = NULL; pr_err("Failed to start kswapd on node %d\n", nid); ret = PTR_ERR(pgdat->kswapd); + pgdat->kswapd = NULL; } return ret; } diff --git a/net/802/mrp.c b/net/802/mrp.c index a4cc3229952a..e085bcc754f6 100644 --- a/net/802/mrp.c +++ b/net/802/mrp.c @@ -870,8 +870,12 @@ void mrp_uninit_applicant(struct net_device *dev, struct mrp_application *appl) * all pending messages before the applicant is gone. */ del_timer_sync(&app->join_timer); + + spin_lock(&app->lock); mrp_mad_event(app, MRP_EVENT_TX); mrp_pdu_queue(app); + spin_unlock(&app->lock); + mrp_queue_xmit(app); dev_mc_del(dev, appl->group_address); diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 6277735cd89e..3e30a0f1b908 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -177,7 +177,13 @@ void batadv_mesh_free(struct net_device *soft_iface) atomic_set(&bat_priv->mesh_state, BATADV_MESH_INACTIVE); } -int batadv_is_my_mac(const uint8_t *addr) +/** + * batadv_is_my_mac - check if the given mac address belongs to any of the real + * interfaces in the current mesh + * @bat_priv: the bat priv with all the soft interface information + * @addr: the address to check + */ +int batadv_is_my_mac(struct batadv_priv *bat_priv, const uint8_t *addr) { const struct batadv_hard_iface *hard_iface; @@ -186,6 +192,9 @@ int batadv_is_my_mac(const uint8_t *addr) if (hard_iface->if_status != BATADV_IF_ACTIVE) continue; + if (hard_iface->soft_iface != bat_priv->soft_iface) + continue; + if (batadv_compare_eth(hard_iface->net_dev->dev_addr, addr)) { rcu_read_unlock(); return 1; diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index f90f5bc8e426..59a0d6af15c8 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -165,7 +165,7 @@ extern struct workqueue_struct *batadv_event_workqueue; int batadv_mesh_init(struct net_device *soft_iface); void batadv_mesh_free(struct net_device *soft_iface); -int batadv_is_my_mac(const uint8_t *addr); +int batadv_is_my_mac(struct batadv_priv *bat_priv, const uint8_t *addr); struct batadv_hard_iface * batadv_seq_print_text_primary_if_get(struct seq_file *seq); int batadv_batman_skb_recv(struct sk_buff *skb, struct net_device *dev, diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index 6b9a54485314..f7c54305a918 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -1484,7 +1484,7 @@ void batadv_nc_skb_store_sniffed_unicast(struct batadv_priv *bat_priv, { struct ethhdr *ethhdr = (struct ethhdr *)skb_mac_header(skb); - if (batadv_is_my_mac(ethhdr->h_dest)) + if (batadv_is_my_mac(bat_priv, ethhdr->h_dest)) return; /* Set data pointer to MAC header to mimic packets from our tx path */ @@ -1496,6 +1496,7 @@ void batadv_nc_skb_store_sniffed_unicast(struct batadv_priv *bat_priv, /** * batadv_nc_skb_decode_packet - decode given skb using the decode data stored * in nc_packet + * @bat_priv: the bat priv with all the soft interface information * @skb: unicast skb to decode * @nc_packet: decode data needed to decode the skb * @@ -1503,7 +1504,7 @@ void batadv_nc_skb_store_sniffed_unicast(struct batadv_priv *bat_priv, * in case of an error. */ static struct batadv_unicast_packet * -batadv_nc_skb_decode_packet(struct sk_buff *skb, +batadv_nc_skb_decode_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_nc_packet *nc_packet) { const int h_size = sizeof(struct batadv_unicast_packet); @@ -1537,7 +1538,7 @@ batadv_nc_skb_decode_packet(struct sk_buff *skb, /* Select the correct unicast header information based on the location * of our mac address in the coded_packet header */ - if (batadv_is_my_mac(coded_packet_tmp.second_dest)) { + if (batadv_is_my_mac(bat_priv, coded_packet_tmp.second_dest)) { /* If we are the second destination the packet was overheard, * so the Ethernet address must be copied to h_dest and * pkt_type changed from PACKET_OTHERHOST to PACKET_HOST @@ -1608,7 +1609,7 @@ batadv_nc_find_decoding_packet(struct batadv_priv *bat_priv, /* Select the correct packet id based on the location of our mac-addr */ dest = ethhdr->h_source; - if (!batadv_is_my_mac(coded->second_dest)) { + if (!batadv_is_my_mac(bat_priv, coded->second_dest)) { source = coded->second_source; packet_id = coded->second_crc; } else { @@ -1675,12 +1676,12 @@ static int batadv_nc_recv_coded_packet(struct sk_buff *skb, ethhdr = (struct ethhdr *)skb_mac_header(skb); /* Verify frame is destined for us */ - if (!batadv_is_my_mac(ethhdr->h_dest) && - !batadv_is_my_mac(coded_packet->second_dest)) + if (!batadv_is_my_mac(bat_priv, ethhdr->h_dest) && + !batadv_is_my_mac(bat_priv, coded_packet->second_dest)) return NET_RX_DROP; /* Update stat counter */ - if (batadv_is_my_mac(coded_packet->second_dest)) + if (batadv_is_my_mac(bat_priv, coded_packet->second_dest)) batadv_inc_counter(bat_priv, BATADV_CNT_NC_SNIFFED); nc_packet = batadv_nc_find_decoding_packet(bat_priv, ethhdr, @@ -1698,7 +1699,7 @@ static int batadv_nc_recv_coded_packet(struct sk_buff *skb, goto free_nc_packet; /* Decode the packet */ - unicast_packet = batadv_nc_skb_decode_packet(skb, nc_packet); + unicast_packet = batadv_nc_skb_decode_packet(bat_priv, skb, nc_packet); if (!unicast_packet) { batadv_inc_counter(bat_priv, BATADV_CNT_NC_DECODE_FAILED); goto free_nc_packet; diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 8f88967ff14b..2f1f88923df8 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -403,7 +403,7 @@ int batadv_recv_icmp_packet(struct sk_buff *skb, goto out; /* not for me */ - if (!batadv_is_my_mac(ethhdr->h_dest)) + if (!batadv_is_my_mac(bat_priv, ethhdr->h_dest)) goto out; icmp_packet = (struct batadv_icmp_packet_rr *)skb->data; @@ -417,7 +417,7 @@ int batadv_recv_icmp_packet(struct sk_buff *skb, } /* packet for me */ - if (batadv_is_my_mac(icmp_packet->dst)) + if (batadv_is_my_mac(bat_priv, icmp_packet->dst)) return batadv_recv_my_icmp_packet(bat_priv, skb, hdr_size); /* TTL exceeded */ @@ -551,6 +551,7 @@ batadv_find_ifalter_router(struct batadv_orig_node *primary_orig, /** * batadv_check_unicast_packet - Check for malformed unicast packets + * @bat_priv: the bat priv with all the soft interface information * @skb: packet to check * @hdr_size: size of header to pull * @@ -559,7 +560,8 @@ batadv_find_ifalter_router(struct batadv_orig_node *primary_orig, * reason: -ENODATA for bad header, -EBADR for broadcast destination or source, * and -EREMOTE for non-local (other host) destination. */ -static int batadv_check_unicast_packet(struct sk_buff *skb, int hdr_size) +static int batadv_check_unicast_packet(struct batadv_priv *bat_priv, + struct sk_buff *skb, int hdr_size) { struct ethhdr *ethhdr; @@ -578,7 +580,7 @@ static int batadv_check_unicast_packet(struct sk_buff *skb, int hdr_size) return -EBADR; /* not for me */ - if (!batadv_is_my_mac(ethhdr->h_dest)) + if (!batadv_is_my_mac(bat_priv, ethhdr->h_dest)) return -EREMOTE; return 0; @@ -593,7 +595,7 @@ int batadv_recv_tt_query(struct sk_buff *skb, struct batadv_hard_iface *recv_if) char tt_flag; size_t packet_size; - if (batadv_check_unicast_packet(skb, hdr_size) < 0) + if (batadv_check_unicast_packet(bat_priv, skb, hdr_size) < 0) return NET_RX_DROP; /* I could need to modify it */ @@ -625,7 +627,7 @@ int batadv_recv_tt_query(struct sk_buff *skb, struct batadv_hard_iface *recv_if) case BATADV_TT_RESPONSE: batadv_inc_counter(bat_priv, BATADV_CNT_TT_RESPONSE_RX); - if (batadv_is_my_mac(tt_query->dst)) { + if (batadv_is_my_mac(bat_priv, tt_query->dst)) { /* packet needs to be linearized to access the TT * changes */ @@ -668,14 +670,15 @@ int batadv_recv_roam_adv(struct sk_buff *skb, struct batadv_hard_iface *recv_if) struct batadv_roam_adv_packet *roam_adv_packet; struct batadv_orig_node *orig_node; - if (batadv_check_unicast_packet(skb, sizeof(*roam_adv_packet)) < 0) + if (batadv_check_unicast_packet(bat_priv, skb, + sizeof(*roam_adv_packet)) < 0) goto out; batadv_inc_counter(bat_priv, BATADV_CNT_TT_ROAM_ADV_RX); roam_adv_packet = (struct batadv_roam_adv_packet *)skb->data; - if (!batadv_is_my_mac(roam_adv_packet->dst)) + if (!batadv_is_my_mac(bat_priv, roam_adv_packet->dst)) return batadv_route_unicast_packet(skb, recv_if); /* check if it is a backbone gateway. we don't accept @@ -981,7 +984,7 @@ static int batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, * last time) the packet had an updated information or not */ curr_ttvn = (uint8_t)atomic_read(&bat_priv->tt.vn); - if (!batadv_is_my_mac(unicast_packet->dest)) { + if (!batadv_is_my_mac(bat_priv, unicast_packet->dest)) { orig_node = batadv_orig_hash_find(bat_priv, unicast_packet->dest); /* if it is not possible to find the orig_node representing the @@ -1059,7 +1062,7 @@ int batadv_recv_unicast_packet(struct sk_buff *skb, hdr_size = sizeof(*unicast_4addr_packet); /* function returns -EREMOTE for promiscuous packets */ - check = batadv_check_unicast_packet(skb, hdr_size); + check = batadv_check_unicast_packet(bat_priv, skb, hdr_size); /* Even though the packet is not for us, we might save it to use for * decoding a later received coded packet @@ -1074,7 +1077,7 @@ int batadv_recv_unicast_packet(struct sk_buff *skb, return NET_RX_DROP; /* packet for me */ - if (batadv_is_my_mac(unicast_packet->dest)) { + if (batadv_is_my_mac(bat_priv, unicast_packet->dest)) { if (is4addr) { batadv_dat_inc_counter(bat_priv, unicast_4addr_packet->subtype); @@ -1111,7 +1114,7 @@ int batadv_recv_ucast_frag_packet(struct sk_buff *skb, struct sk_buff *new_skb = NULL; int ret; - if (batadv_check_unicast_packet(skb, hdr_size) < 0) + if (batadv_check_unicast_packet(bat_priv, skb, hdr_size) < 0) return NET_RX_DROP; if (!batadv_check_unicast_ttvn(bat_priv, skb)) @@ -1120,7 +1123,7 @@ int batadv_recv_ucast_frag_packet(struct sk_buff *skb, unicast_packet = (struct batadv_unicast_frag_packet *)skb->data; /* packet for me */ - if (batadv_is_my_mac(unicast_packet->dest)) { + if (batadv_is_my_mac(bat_priv, unicast_packet->dest)) { ret = batadv_frag_reassemble_skb(skb, bat_priv, &new_skb); if (ret == NET_RX_DROP) @@ -1174,13 +1177,13 @@ int batadv_recv_bcast_packet(struct sk_buff *skb, goto out; /* ignore broadcasts sent by myself */ - if (batadv_is_my_mac(ethhdr->h_source)) + if (batadv_is_my_mac(bat_priv, ethhdr->h_source)) goto out; bcast_packet = (struct batadv_bcast_packet *)skb->data; /* ignore broadcasts originated by myself */ - if (batadv_is_my_mac(bcast_packet->orig)) + if (batadv_is_my_mac(bat_priv, bcast_packet->orig)) goto out; if (bcast_packet->header.ttl < 2) @@ -1266,14 +1269,14 @@ int batadv_recv_vis_packet(struct sk_buff *skb, ethhdr = (struct ethhdr *)skb_mac_header(skb); /* not for me */ - if (!batadv_is_my_mac(ethhdr->h_dest)) + if (!batadv_is_my_mac(bat_priv, ethhdr->h_dest)) return NET_RX_DROP; /* ignore own packets */ - if (batadv_is_my_mac(vis_packet->vis_orig)) + if (batadv_is_my_mac(bat_priv, vis_packet->vis_orig)) return NET_RX_DROP; - if (batadv_is_my_mac(vis_packet->sender_orig)) + if (batadv_is_my_mac(bat_priv, vis_packet->sender_orig)) return NET_RX_DROP; switch (vis_packet->vis_type) { diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 932232087449..5e89deeb9542 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1940,7 +1940,7 @@ out: bool batadv_send_tt_response(struct batadv_priv *bat_priv, struct batadv_tt_query_packet *tt_request) { - if (batadv_is_my_mac(tt_request->dst)) { + if (batadv_is_my_mac(bat_priv, tt_request->dst)) { /* don't answer backbone gws! */ if (batadv_bla_is_backbone_gw_orig(bat_priv, tt_request->src)) return true; diff --git a/net/batman-adv/vis.c b/net/batman-adv/vis.c index 962ccf3b8382..1625e5793a89 100644 --- a/net/batman-adv/vis.c +++ b/net/batman-adv/vis.c @@ -477,7 +477,7 @@ void batadv_receive_client_update_packet(struct batadv_priv *bat_priv, /* Are we the target for this VIS packet? */ if (vis_server == BATADV_VIS_TYPE_SERVER_SYNC && - batadv_is_my_mac(vis_packet->target_orig)) + batadv_is_my_mac(bat_priv, vis_packet->target_orig)) are_target = 1; spin_lock_bh(&bat_priv->vis.hash_lock); @@ -496,7 +496,7 @@ void batadv_receive_client_update_packet(struct batadv_priv *bat_priv, batadv_send_list_add(bat_priv, info); /* ... we're not the recipient (and thus need to forward). */ - } else if (!batadv_is_my_mac(packet->target_orig)) { + } else if (!batadv_is_my_mac(bat_priv, packet->target_orig)) { batadv_send_list_add(bat_priv, info); } diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index f17fcb3097c2..4cdba60926ff 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -67,7 +67,8 @@ void br_port_carrier_check(struct net_bridge_port *p) struct net_device *dev = p->dev; struct net_bridge *br = p->br; - if (netif_running(dev) && netif_oper_up(dev)) + if (!(p->flags & BR_ADMIN_COST) && + netif_running(dev) && netif_oper_up(dev)) p->path_cost = port_cost(dev); if (!netif_running(br->dev)) diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 3cbf5beb3d4b..d2c043a857b6 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -156,6 +156,7 @@ struct net_bridge_port #define BR_BPDU_GUARD 0x00000002 #define BR_ROOT_BLOCK 0x00000004 #define BR_MULTICAST_FAST_LEAVE 0x00000008 +#define BR_ADMIN_COST 0x00000010 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING u32 multicast_startup_queries_sent; diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 0bdb4ebd362b..d45e760141bb 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -288,6 +288,7 @@ int br_stp_set_path_cost(struct net_bridge_port *p, unsigned long path_cost) path_cost > BR_MAX_PATH_COST) return -ERANGE; + p->flags |= BR_ADMIN_COST; p->path_cost = path_cost; br_configuration_update(p->br); br_port_state_selection(p->br); diff --git a/net/can/gw.c b/net/can/gw.c index 2dc619db805a..3ee690e8c7d3 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -466,7 +466,7 @@ static int cgw_notifier(struct notifier_block *nb, if (gwj->src.dev == dev || gwj->dst.dev == dev) { hlist_del(&gwj->list); cgw_unregister_filter(gwj); - kfree(gwj); + kmem_cache_free(cgw_cache, gwj); } } } @@ -863,7 +863,7 @@ static void cgw_remove_all_jobs(void) hlist_for_each_entry_safe(gwj, nx, &cgw_list, list) { hlist_del(&gwj->list); cgw_unregister_filter(gwj); - kfree(gwj); + kmem_cache_free(cgw_cache, gwj); } } @@ -919,7 +919,7 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh) hlist_del(&gwj->list); cgw_unregister_filter(gwj); - kfree(gwj); + kmem_cache_free(cgw_cache, gwj); err = 0; break; } diff --git a/net/core/dev.c b/net/core/dev.c index 8a3cb2c50fbf..9e26b8d9eafe 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2146,6 +2146,9 @@ static void skb_warn_bad_offload(const struct sk_buff *skb) struct net_device *dev = skb->dev; const char *driver = ""; + if (!net_ratelimit()) + return; + if (dev && dev->dev.parent) driver = dev_driver_string(dev->dev.parent); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 589d0abb34a0..18af08a73f0a 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1046,7 +1046,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); cb->seq = net->dev_base_seq; - if (nlmsg_parse(cb->nlh, sizeof(struct rtgenmsg), tb, IFLA_MAX, + if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX, ifla_policy) >= 0) { if (tb[IFLA_EXT_MASK]) @@ -1896,7 +1896,7 @@ static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh) u32 ext_filter_mask = 0; u16 min_ifinfo_dump_size = 0; - if (nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, IFLA_MAX, + if (nlmsg_parse(nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX, ifla_policy) >= 0) { if (tb[IFLA_EXT_MASK]) ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 2759dfd576ae..dfc39d4d48b7 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -587,13 +587,16 @@ static void check_lifetime(struct work_struct *work) { unsigned long now, next, next_sec, next_sched; struct in_ifaddr *ifa; + struct hlist_node *n; int i; now = jiffies; next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY); - rcu_read_lock(); for (i = 0; i < IN4_ADDR_HSIZE; i++) { + bool change_needed = false; + + rcu_read_lock(); hlist_for_each_entry_rcu(ifa, &inet_addr_lst[i], hash) { unsigned long age; @@ -606,16 +609,7 @@ static void check_lifetime(struct work_struct *work) if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME && age >= ifa->ifa_valid_lft) { - struct in_ifaddr **ifap ; - - rtnl_lock(); - for (ifap = &ifa->ifa_dev->ifa_list; - *ifap != NULL; ifap = &ifa->ifa_next) { - if (*ifap == ifa) - inet_del_ifa(ifa->ifa_dev, - ifap, 1); - } - rtnl_unlock(); + change_needed = true; } else if (ifa->ifa_preferred_lft == INFINITY_LIFE_TIME) { continue; @@ -625,10 +619,8 @@ static void check_lifetime(struct work_struct *work) next = ifa->ifa_tstamp + ifa->ifa_valid_lft * HZ; - if (!(ifa->ifa_flags & IFA_F_DEPRECATED)) { - ifa->ifa_flags |= IFA_F_DEPRECATED; - rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0); - } + if (!(ifa->ifa_flags & IFA_F_DEPRECATED)) + change_needed = true; } else if (time_before(ifa->ifa_tstamp + ifa->ifa_preferred_lft * HZ, next)) { @@ -636,8 +628,42 @@ static void check_lifetime(struct work_struct *work) ifa->ifa_preferred_lft * HZ; } } + rcu_read_unlock(); + if (!change_needed) + continue; + rtnl_lock(); + hlist_for_each_entry_safe(ifa, n, &inet_addr_lst[i], hash) { + unsigned long age; + + if (ifa->ifa_flags & IFA_F_PERMANENT) + continue; + + /* We try to batch several events at once. */ + age = (now - ifa->ifa_tstamp + + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; + + if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME && + age >= ifa->ifa_valid_lft) { + struct in_ifaddr **ifap; + + for (ifap = &ifa->ifa_dev->ifa_list; + *ifap != NULL; ifap = &(*ifap)->ifa_next) { + if (*ifap == ifa) { + inet_del_ifa(ifa->ifa_dev, + ifap, 1); + break; + } + } + } else if (ifa->ifa_preferred_lft != + INFINITY_LIFE_TIME && + age >= ifa->ifa_preferred_lft && + !(ifa->ifa_flags & IFA_F_DEPRECATED)) { + ifa->ifa_flags |= IFA_F_DEPRECATED; + rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0); + } + } + rtnl_unlock(); } - rcu_read_unlock(); next_sec = round_jiffies_up(next); next_sched = next; @@ -804,6 +830,8 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) return -EEXIST; ifa = ifa_existing; set_ifa_lifetime(ifa, valid_lft, prefered_lft); + cancel_delayed_work(&check_lifetime_work); + schedule_delayed_work(&check_lifetime_work, 0); rtmsg_ifa(RTM_NEWADDR, ifa, nlh, NETLINK_CB(skb).portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa); } diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 3b4f0cd2e63e..4cfe34d4cc96 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -139,8 +139,6 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) /* skb is pure payload to encrypt */ - err = -ENOMEM; - esp = x->data; aead = esp->aead; alen = crypto_aead_authsize(aead); @@ -176,8 +174,10 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) } tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen); - if (!tmp) + if (!tmp) { + err = -ENOMEM; goto error; + } seqhi = esp_tmp_seqhi(tmp); iv = esp_tmp_iv(aead, tmp, seqhilen); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 938520668b2f..b66910aaef4d 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -219,8 +219,7 @@ static void ip_expire(unsigned long arg) if (!head->dev) goto out_rcu_unlock; - /* skb dst is stale, drop it, and perform route lookup again */ - skb_dst_drop(head); + /* skb has no dst, perform route lookup again */ iph = ip_hdr(head); err = ip_route_input_noref(head, iph->daddr, iph->saddr, iph->tos, head->dev); @@ -494,9 +493,16 @@ found: qp->q.max_size = skb->len + ihl; if (qp->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && - qp->q.meat == qp->q.len) - return ip_frag_reasm(qp, prev, dev); + qp->q.meat == qp->q.len) { + unsigned long orefdst = skb->_skb_refdst; + skb->_skb_refdst = 0UL; + err = ip_frag_reasm(qp, prev, dev); + skb->_skb_refdst = orefdst; + return err; + } + + skb_dst_drop(skb); inet_frag_lru_move(&qp->q); return -EINPROGRESS; diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index c30130062cd6..c49dcd0284a0 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -66,6 +66,12 @@ static bool rpfilter_lookup_reverse(struct flowi4 *fl4, return dev_match; } +static bool rpfilter_is_local(const struct sk_buff *skb) +{ + const struct rtable *rt = skb_rtable(skb); + return rt && (rt->rt_flags & RTCF_LOCAL); +} + static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_rpfilter_info *info; @@ -76,7 +82,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) info = par->matchinfo; invert = info->flags & XT_RPFILTER_INVERT; - if (par->in->flags & IFF_LOOPBACK) + if (rpfilter_is_local(skb)) return true ^ invert; iph = ip_hdr(skb); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 7f4a5cb8f8d0..b05c96e7af8b 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -348,8 +348,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, * hasn't changed since we received the original syn, but I see * no easy way to do this. */ - flowi4_init_output(&fl4, 0, sk->sk_mark, RT_CONN_FLAGS(sk), - RT_SCOPE_UNIVERSE, IPPROTO_TCP, + flowi4_init_output(&fl4, sk->sk_bound_dev_if, sk->sk_mark, + RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP, inet_sk_flowi_flags(sk), (opt && opt->srr) ? opt->faddr : ireq->rmt_addr, ireq->loc_addr, th->source, th->dest); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 6d9ca35f0c35..aafd052865ba 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -111,6 +111,7 @@ int sysctl_tcp_early_retrans __read_mostly = 3; #define FLAG_SND_UNA_ADVANCED 0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */ #define FLAG_DSACKING_ACK 0x800 /* SACK blocks contained D-SACK info */ #define FLAG_SACK_RENEGING 0x2000 /* snd_una advanced to a sacked seq */ +#define FLAG_UPDATE_TS_RECENT 0x4000 /* tcp_replace_ts_recent() */ #define FLAG_ACKED (FLAG_DATA_ACKED|FLAG_SYN_ACKED) #define FLAG_NOT_DUP (FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED) @@ -3265,6 +3266,27 @@ static void tcp_send_challenge_ack(struct sock *sk) } } +static void tcp_store_ts_recent(struct tcp_sock *tp) +{ + tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval; + tp->rx_opt.ts_recent_stamp = get_seconds(); +} + +static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq) +{ + if (tp->rx_opt.saw_tstamp && !after(seq, tp->rcv_wup)) { + /* PAWS bug workaround wrt. ACK frames, the PAWS discard + * extra check below makes sure this can only happen + * for pure ACK frames. -DaveM + * + * Not only, also it occurs for expired timestamps. + */ + + if (tcp_paws_check(&tp->rx_opt, 0)) + tcp_store_ts_recent(tp); + } +} + /* This routine deals with acks during a TLP episode. * Ref: loss detection algorithm in draft-dukkipati-tcpm-tcp-loss-probe. */ @@ -3340,6 +3362,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) prior_fackets = tp->fackets_out; prior_in_flight = tcp_packets_in_flight(tp); + /* ts_recent update must be made after we are sure that the packet + * is in window. + */ + if (flag & FLAG_UPDATE_TS_RECENT) + tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); + if (!(flag & FLAG_SLOWPATH) && after(ack, prior_snd_una)) { /* Window is constant, pure forward advance. * No more checks are required. @@ -3636,27 +3664,6 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th) EXPORT_SYMBOL(tcp_parse_md5sig_option); #endif -static inline void tcp_store_ts_recent(struct tcp_sock *tp) -{ - tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval; - tp->rx_opt.ts_recent_stamp = get_seconds(); -} - -static inline void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq) -{ - if (tp->rx_opt.saw_tstamp && !after(seq, tp->rcv_wup)) { - /* PAWS bug workaround wrt. ACK frames, the PAWS discard - * extra check below makes sure this can only happen - * for pure ACK frames. -DaveM - * - * Not only, also it occurs for expired timestamps. - */ - - if (tcp_paws_check(&tp->rx_opt, 0)) - tcp_store_ts_recent(tp); - } -} - /* Sorry, PAWS as specified is broken wrt. pure-ACKs -DaveM * * It is not fatal. If this ACK does _not_ change critical state (seqs, window) @@ -5250,14 +5257,9 @@ slow_path: return 0; step5: - if (tcp_ack(sk, skb, FLAG_SLOWPATH) < 0) + if (tcp_ack(sk, skb, FLAG_SLOWPATH | FLAG_UPDATE_TS_RECENT) < 0) goto discard; - /* ts_recent update must be made after we are sure that the packet - * is in window. - */ - tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); - tcp_rcv_rtt_measure_ts(sk, skb); /* Process urgent data. */ @@ -5666,7 +5668,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, /* step 5: check the ACK field */ if (true) { - int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH) > 0; + int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH | + FLAG_UPDATE_TS_RECENT) > 0; switch (sk->sk_state) { case TCP_SYN_RECV: @@ -5817,11 +5820,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, } } - /* ts_recent update must be made after we are sure that the packet - * is in window. - */ - tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); - /* step 6: check the URG bit */ tcp_urg(sk, skb, th); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 5f28131eb37e..b735c23a961d 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2353,8 +2353,12 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) */ TCP_SKB_CB(skb)->when = tcp_time_stamp; - /* make sure skb->data is aligned on arches that require it */ - if (unlikely(NET_IP_ALIGN && ((unsigned long)skb->data & 3))) { + /* make sure skb->data is aligned on arches that require it + * and check if ack-trimming & collapsing extended the headroom + * beyond what csum_start can cover. + */ + if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) || + skb_headroom(skb) >= 0xFFFF)) { struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); return nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : @@ -2666,6 +2670,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, skb_reserve(skb, MAX_TCP_HEADER); skb_dst_set(skb, dst); + security_skb_owned_by(skb, sk); mss = dst_metric_advmss(dst); if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 28b61e89bbb8..d1ab6ab29a55 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -169,8 +169,6 @@ static void inet6_prefix_notify(int event, struct inet6_dev *idev, static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, struct net_device *dev); -static ATOMIC_NOTIFIER_HEAD(inet6addr_chain); - static struct ipv6_devconf ipv6_devconf __read_mostly = { .forwarding = 0, .hop_limit = IPV6_DEFAULT_HOPLIMIT, @@ -910,7 +908,7 @@ out2: rcu_read_unlock_bh(); if (likely(err == 0)) - atomic_notifier_call_chain(&inet6addr_chain, NETDEV_UP, ifa); + inet6addr_notifier_call_chain(NETDEV_UP, ifa); else { kfree(ifa); ifa = ERR_PTR(err); @@ -1000,7 +998,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) ipv6_ifa_notify(RTM_DELADDR, ifp); - atomic_notifier_call_chain(&inet6addr_chain, NETDEV_DOWN, ifp); + inet6addr_notifier_call_chain(NETDEV_DOWN, ifp); /* * Purge or update corresponding prefix @@ -3087,7 +3085,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) if (state != INET6_IFADDR_STATE_DEAD) { __ipv6_ifa_notify(RTM_DELADDR, ifa); - atomic_notifier_call_chain(&inet6addr_chain, NETDEV_DOWN, ifa); + inet6addr_notifier_call_chain(NETDEV_DOWN, ifa); } in6_ifa_put(ifa); @@ -5054,22 +5052,6 @@ static struct pernet_operations addrconf_ops = { .exit = addrconf_exit_net, }; -/* - * Device notifier - */ - -int register_inet6addr_notifier(struct notifier_block *nb) -{ - return atomic_notifier_chain_register(&inet6addr_chain, nb); -} -EXPORT_SYMBOL(register_inet6addr_notifier); - -int unregister_inet6addr_notifier(struct notifier_block *nb) -{ - return atomic_notifier_chain_unregister(&inet6addr_chain, nb); -} -EXPORT_SYMBOL(unregister_inet6addr_notifier); - static struct rtnl_af_ops inet6_ops = { .family = AF_INET6, .fill_link_af = inet6_fill_link_af, diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index d051e5f4bf34..72104562c864 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -78,3 +78,22 @@ int __ipv6_addr_type(const struct in6_addr *addr) } EXPORT_SYMBOL(__ipv6_addr_type); +static ATOMIC_NOTIFIER_HEAD(inet6addr_chain); + +int register_inet6addr_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_register(&inet6addr_chain, nb); +} +EXPORT_SYMBOL(register_inet6addr_notifier); + +int unregister_inet6addr_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&inet6addr_chain, nb); +} +EXPORT_SYMBOL(unregister_inet6addr_notifier); + +int inet6addr_notifier_call_chain(unsigned long val, void *v) +{ + return atomic_notifier_call_chain(&inet6addr_chain, val, v); +} +EXPORT_SYMBOL(inet6addr_notifier_call_chain); diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c index 5060d54199ab..e0983f3648a6 100644 --- a/net/ipv6/netfilter/ip6t_rpfilter.c +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -71,6 +71,12 @@ static bool rpfilter_lookup_reverse6(const struct sk_buff *skb, return ret; } +static bool rpfilter_is_local(const struct sk_buff *skb) +{ + const struct rt6_info *rt = (const void *) skb_dst(skb); + return rt && (rt->rt6i_flags & RTF_LOCAL); +} + static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_rpfilter_info *info = par->matchinfo; @@ -78,7 +84,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) struct ipv6hdr *iph; bool invert = info->flags & XT_RPFILTER_INVERT; - if (par->in->flags & IFF_LOOPBACK) + if (rpfilter_is_local(skb)) return true ^ invert; iph = ipv6_hdr(skb); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index e6e44cef8db2..790d9f4b8b0b 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -342,9 +342,17 @@ found: } if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && - fq->q.meat == fq->q.len) - return ip6_frag_reasm(fq, prev, dev); + fq->q.meat == fq->q.len) { + int res; + unsigned long orefdst = skb->_skb_refdst; + skb->_skb_refdst = 0UL; + res = ip6_frag_reasm(fq, prev, dev); + skb->_skb_refdst = orefdst; + return res; + } + + skb_dst_drop(skb); inet_frag_lru_move(&fq->q); return -1; diff --git a/net/irda/iriap.c b/net/irda/iriap.c index 29340a9a6fb9..e1b37f5a2691 100644 --- a/net/irda/iriap.c +++ b/net/irda/iriap.c @@ -303,7 +303,8 @@ static void iriap_disconnect_indication(void *instance, void *sap, { struct iriap_cb *self; - IRDA_DEBUG(4, "%s(), reason=%s\n", __func__, irlmp_reasons[reason]); + IRDA_DEBUG(4, "%s(), reason=%s [%d]\n", __func__, + irlmp_reason_str(reason), reason); self = instance; diff --git a/net/irda/irlmp.c b/net/irda/irlmp.c index 6115a44c0a24..1064621da6f6 100644 --- a/net/irda/irlmp.c +++ b/net/irda/irlmp.c @@ -66,8 +66,15 @@ const char *irlmp_reasons[] = { "LM_LAP_RESET", "LM_INIT_DISCONNECT", "ERROR, NOT USED", + "UNKNOWN", }; +const char *irlmp_reason_str(LM_REASON reason) +{ + reason = min_t(size_t, reason, ARRAY_SIZE(irlmp_reasons) - 1); + return irlmp_reasons[reason]; +} + /* * Function irlmp_init (void) * @@ -747,7 +754,8 @@ void irlmp_disconnect_indication(struct lsap_cb *self, LM_REASON reason, { struct lsap_cb *lsap; - IRDA_DEBUG(1, "%s(), reason=%s\n", __func__, irlmp_reasons[reason]); + IRDA_DEBUG(1, "%s(), reason=%s [%d]\n", __func__, + irlmp_reason_str(reason), reason); IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return;); diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index e165e8dc962e..ae691651b721 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -49,12 +49,6 @@ static const u8 iprm_shutdown[8] = #define TRGCLS_SIZE (sizeof(((struct iucv_message *)0)->class)) -/* macros to set/get socket control buffer at correct offset */ -#define CB_TAG(skb) ((skb)->cb) /* iucv message tag */ -#define CB_TAG_LEN (sizeof(((struct iucv_message *) 0)->tag)) -#define CB_TRGCLS(skb) ((skb)->cb + CB_TAG_LEN) /* iucv msg target class */ -#define CB_TRGCLS_LEN (TRGCLS_SIZE) - #define __iucv_sock_wait(sk, condition, timeo, ret) \ do { \ DEFINE_WAIT(__wait); \ @@ -1141,7 +1135,7 @@ static int iucv_sock_sendmsg(struct kiocb *iocb, struct socket *sock, /* increment and save iucv message tag for msg_completion cbk */ txmsg.tag = iucv->send_tag++; - memcpy(CB_TAG(skb), &txmsg.tag, CB_TAG_LEN); + IUCV_SKB_CB(skb)->tag = txmsg.tag; if (iucv->transport == AF_IUCV_TRANS_HIPER) { atomic_inc(&iucv->msg_sent); @@ -1224,7 +1218,7 @@ static int iucv_fragment_skb(struct sock *sk, struct sk_buff *skb, int len) return -ENOMEM; /* copy target class to control buffer of new skb */ - memcpy(CB_TRGCLS(nskb), CB_TRGCLS(skb), CB_TRGCLS_LEN); + IUCV_SKB_CB(nskb)->class = IUCV_SKB_CB(skb)->class; /* copy data fragment */ memcpy(nskb->data, skb->data + copied, size); @@ -1256,7 +1250,7 @@ static void iucv_process_message(struct sock *sk, struct sk_buff *skb, /* store msg target class in the second 4 bytes of skb ctrl buffer */ /* Note: the first 4 bytes are reserved for msg tag */ - memcpy(CB_TRGCLS(skb), &msg->class, CB_TRGCLS_LEN); + IUCV_SKB_CB(skb)->class = msg->class; /* check for special IPRM messages (e.g. iucv_sock_shutdown) */ if ((msg->flags & IUCV_IPRMDATA) && len > 7) { @@ -1292,6 +1286,7 @@ static void iucv_process_message(struct sock *sk, struct sk_buff *skb, } } + IUCV_SKB_CB(skb)->offset = 0; if (sock_queue_rcv_skb(sk, skb)) skb_queue_head(&iucv_sk(sk)->backlog_skb_q, skb); } @@ -1327,6 +1322,7 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, unsigned int copied, rlen; struct sk_buff *skb, *rskb, *cskb; int err = 0; + u32 offset; msg->msg_namelen = 0; @@ -1348,13 +1344,14 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, return err; } - rlen = skb->len; /* real length of skb */ + offset = IUCV_SKB_CB(skb)->offset; + rlen = skb->len - offset; /* real length of skb */ copied = min_t(unsigned int, rlen, len); if (!rlen) sk->sk_shutdown = sk->sk_shutdown | RCV_SHUTDOWN; cskb = skb; - if (skb_copy_datagram_iovec(cskb, 0, msg->msg_iov, copied)) { + if (skb_copy_datagram_iovec(cskb, offset, msg->msg_iov, copied)) { if (!(flags & MSG_PEEK)) skb_queue_head(&sk->sk_receive_queue, skb); return -EFAULT; @@ -1372,7 +1369,8 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, * get the trgcls from the control buffer of the skb due to * fragmentation of original iucv message. */ err = put_cmsg(msg, SOL_IUCV, SCM_IUCV_TRGCLS, - CB_TRGCLS_LEN, CB_TRGCLS(skb)); + sizeof(IUCV_SKB_CB(skb)->class), + (void *)&IUCV_SKB_CB(skb)->class); if (err) { if (!(flags & MSG_PEEK)) skb_queue_head(&sk->sk_receive_queue, skb); @@ -1384,9 +1382,8 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, /* SOCK_STREAM: re-queue skb if it contains unreceived data */ if (sk->sk_type == SOCK_STREAM) { - skb_pull(skb, copied); - if (skb->len) { - skb_queue_head(&sk->sk_receive_queue, skb); + if (copied < rlen) { + IUCV_SKB_CB(skb)->offset = offset + copied; goto done; } } @@ -1405,6 +1402,7 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, spin_lock_bh(&iucv->message_q.lock); rskb = skb_dequeue(&iucv->backlog_skb_q); while (rskb) { + IUCV_SKB_CB(rskb)->offset = 0; if (sock_queue_rcv_skb(sk, rskb)) { skb_queue_head(&iucv->backlog_skb_q, rskb); @@ -1833,7 +1831,7 @@ static void iucv_callback_txdone(struct iucv_path *path, spin_lock_irqsave(&list->lock, flags); while (list_skb != (struct sk_buff *)list) { - if (!memcmp(&msg->tag, CB_TAG(list_skb), CB_TAG_LEN)) { + if (msg->tag != IUCV_SKB_CB(list_skb)->tag) { this = list_skb; break; } @@ -2094,6 +2092,7 @@ static int afiucv_hs_callback_rx(struct sock *sk, struct sk_buff *skb) skb_pull(skb, sizeof(struct af_iucv_trans_hdr)); skb_reset_transport_header(skb); skb_reset_network_header(skb); + IUCV_SKB_CB(skb)->offset = 0; spin_lock(&iucv->message_q.lock); if (skb_queue_empty(&iucv->backlog_skb_q)) { if (sock_queue_rcv_skb(sk, skb)) { @@ -2198,8 +2197,7 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, /* fall through and receive zero length data */ case 0: /* plain data frame */ - memcpy(CB_TRGCLS(skb), &trans_hdr->iucv_hdr.class, - CB_TRGCLS_LEN); + IUCV_SKB_CB(skb)->class = trans_hdr->iucv_hdr.class; err = afiucv_hs_callback_rx(sk, skb); break; default: diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 69aaba79a9f7..e8a260f53c16 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -78,7 +78,7 @@ void ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata) ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_TXPOWER); } -u32 ieee80211_idle_off(struct ieee80211_local *local) +static u32 __ieee80211_idle_off(struct ieee80211_local *local) { if (!(local->hw.conf.flags & IEEE80211_CONF_IDLE)) return 0; @@ -87,7 +87,7 @@ u32 ieee80211_idle_off(struct ieee80211_local *local) return IEEE80211_CONF_CHANGE_IDLE; } -static u32 ieee80211_idle_on(struct ieee80211_local *local) +static u32 __ieee80211_idle_on(struct ieee80211_local *local) { if (local->hw.conf.flags & IEEE80211_CONF_IDLE) return 0; @@ -98,16 +98,18 @@ static u32 ieee80211_idle_on(struct ieee80211_local *local) return IEEE80211_CONF_CHANGE_IDLE; } -void ieee80211_recalc_idle(struct ieee80211_local *local) +static u32 __ieee80211_recalc_idle(struct ieee80211_local *local, + bool force_active) { bool working = false, scanning, active; unsigned int led_trig_start = 0, led_trig_stop = 0; struct ieee80211_roc_work *roc; - u32 change; lockdep_assert_held(&local->mtx); - active = !list_empty(&local->chanctx_list) || local->monitors; + active = force_active || + !list_empty(&local->chanctx_list) || + local->monitors; if (!local->ops->remain_on_channel) { list_for_each_entry(roc, &local->roc_list, list) { @@ -132,9 +134,18 @@ void ieee80211_recalc_idle(struct ieee80211_local *local) ieee80211_mod_tpt_led_trig(local, led_trig_start, led_trig_stop); if (working || scanning || active) - change = ieee80211_idle_off(local); - else - change = ieee80211_idle_on(local); + return __ieee80211_idle_off(local); + return __ieee80211_idle_on(local); +} + +u32 ieee80211_idle_off(struct ieee80211_local *local) +{ + return __ieee80211_recalc_idle(local, true); +} + +void ieee80211_recalc_idle(struct ieee80211_local *local) +{ + u32 change = __ieee80211_recalc_idle(local, false); if (change) ieee80211_hw_config(local, change); } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index e06dbbf8cb4c..dec42ab1fa91 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -3887,8 +3887,16 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, /* prep auth_data so we don't go into idle on disassoc */ ifmgd->auth_data = auth_data; - if (ifmgd->associated) - ieee80211_set_disassoc(sdata, 0, 0, false, NULL); + if (ifmgd->associated) { + u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN]; + + ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, + WLAN_REASON_UNSPECIFIED, + false, frame_buf); + + __cfg80211_send_deauth(sdata->dev, frame_buf, + sizeof(frame_buf)); + } sdata_info(sdata, "authenticate with %pM\n", req->bss->bssid); @@ -3948,8 +3956,16 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, mutex_lock(&ifmgd->mtx); - if (ifmgd->associated) - ieee80211_set_disassoc(sdata, 0, 0, false, NULL); + if (ifmgd->associated) { + u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN]; + + ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, + WLAN_REASON_UNSPECIFIED, + false, frame_buf); + + __cfg80211_send_deauth(sdata->dev, frame_buf, + sizeof(frame_buf)); + } if (ifmgd->auth_data && !ifmgd->auth_data->done) { err = -EBUSY; diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index 0f92dc24cb89..d7df6ac2c6f1 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -339,7 +339,11 @@ bitmap_ipmac_tlist(const struct ip_set *set, nla_put_failure: nla_nest_cancel(skb, nested); ipset_nest_end(skb, atd); - return -EMSGSIZE; + if (unlikely(id == first)) { + cb->args[2] = 0; + return -EMSGSIZE; + } + return 0; } static int diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index f2627226a087..10a30b4fc7db 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -104,6 +104,15 @@ hash_ipportnet4_data_flags(struct hash_ipportnet4_elem *dst, u32 flags) dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); } +static inline void +hash_ipportnet4_data_reset_flags(struct hash_ipportnet4_elem *dst, u32 *flags) +{ + if (dst->nomatch) { + *flags = IPSET_FLAG_NOMATCH; + dst->nomatch = 0; + } +} + static inline int hash_ipportnet4_data_match(const struct hash_ipportnet4_elem *elem) { @@ -414,6 +423,15 @@ hash_ipportnet6_data_flags(struct hash_ipportnet6_elem *dst, u32 flags) dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); } +static inline void +hash_ipportnet6_data_reset_flags(struct hash_ipportnet6_elem *dst, u32 *flags) +{ + if (dst->nomatch) { + *flags = IPSET_FLAG_NOMATCH; + dst->nomatch = 0; + } +} + static inline int hash_ipportnet6_data_match(const struct hash_ipportnet6_elem *elem) { diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index 4b677cf6bf7d..d6a59154d710 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -87,7 +87,16 @@ hash_net4_data_copy(struct hash_net4_elem *dst, static inline void hash_net4_data_flags(struct hash_net4_elem *dst, u32 flags) { - dst->nomatch = flags & IPSET_FLAG_NOMATCH; + dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); +} + +static inline void +hash_net4_data_reset_flags(struct hash_net4_elem *dst, u32 *flags) +{ + if (dst->nomatch) { + *flags = IPSET_FLAG_NOMATCH; + dst->nomatch = 0; + } } static inline int @@ -308,7 +317,16 @@ hash_net6_data_copy(struct hash_net6_elem *dst, static inline void hash_net6_data_flags(struct hash_net6_elem *dst, u32 flags) { - dst->nomatch = flags & IPSET_FLAG_NOMATCH; + dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); +} + +static inline void +hash_net6_data_reset_flags(struct hash_net6_elem *dst, u32 *flags) +{ + if (dst->nomatch) { + *flags = IPSET_FLAG_NOMATCH; + dst->nomatch = 0; + } } static inline int diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 6ba985f1c96f..f2b0a3c30130 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -198,7 +198,16 @@ hash_netiface4_data_copy(struct hash_netiface4_elem *dst, static inline void hash_netiface4_data_flags(struct hash_netiface4_elem *dst, u32 flags) { - dst->nomatch = flags & IPSET_FLAG_NOMATCH; + dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); +} + +static inline void +hash_netiface4_data_reset_flags(struct hash_netiface4_elem *dst, u32 *flags) +{ + if (dst->nomatch) { + *flags = IPSET_FLAG_NOMATCH; + dst->nomatch = 0; + } } static inline int @@ -494,7 +503,7 @@ hash_netiface6_data_copy(struct hash_netiface6_elem *dst, static inline void hash_netiface6_data_flags(struct hash_netiface6_elem *dst, u32 flags) { - dst->nomatch = flags & IPSET_FLAG_NOMATCH; + dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); } static inline int @@ -503,6 +512,15 @@ hash_netiface6_data_match(const struct hash_netiface6_elem *elem) return elem->nomatch ? -ENOTEMPTY : 1; } +static inline void +hash_netiface6_data_reset_flags(struct hash_netiface6_elem *dst, u32 *flags) +{ + if (dst->nomatch) { + *flags = IPSET_FLAG_NOMATCH; + dst->nomatch = 0; + } +} + static inline void hash_netiface6_data_zero_out(struct hash_netiface6_elem *elem) { diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index af20c0c5ced2..349deb672a2d 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -104,6 +104,15 @@ hash_netport4_data_flags(struct hash_netport4_elem *dst, u32 flags) dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); } +static inline void +hash_netport4_data_reset_flags(struct hash_netport4_elem *dst, u32 *flags) +{ + if (dst->nomatch) { + *flags = IPSET_FLAG_NOMATCH; + dst->nomatch = 0; + } +} + static inline int hash_netport4_data_match(const struct hash_netport4_elem *elem) { @@ -375,6 +384,15 @@ hash_netport6_data_flags(struct hash_netport6_elem *dst, u32 flags) dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); } +static inline void +hash_netport6_data_reset_flags(struct hash_netport6_elem *dst, u32 *flags) +{ + if (dst->nomatch) { + *flags = IPSET_FLAG_NOMATCH; + dst->nomatch = 0; + } +} + static inline int hash_netport6_data_match(const struct hash_netport6_elem *elem) { diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 8371c2bac2e4..09c744aa8982 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -174,9 +174,13 @@ list_set_add(struct list_set *map, u32 i, ip_set_id_t id, { const struct set_elem *e = list_set_elem(map, i); - if (i == map->size - 1 && e->id != IPSET_INVALID_ID) - /* Last element replaced: e.g. add new,before,last */ - ip_set_put_byindex(e->id); + if (e->id != IPSET_INVALID_ID) { + const struct set_elem *x = list_set_elem(map, map->size - 1); + + /* Last element replaced or pushed off */ + if (x->id != IPSET_INVALID_ID) + ip_set_put_byindex(x->id); + } if (with_timeout(map->timeout)) list_elem_tadd(map, i, id, ip_set_timeout_set(timeout)); else diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 0e7d423324c3..e0c4373b4747 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1593,10 +1593,8 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff, end += strlen("\r\n\r\n") + clen; msglen = origlen = end - dptr; - if (msglen > datalen) { - nf_ct_helper_log(skb, ct, "incomplete/bad SIP message"); - return NF_DROP; - } + if (msglen > datalen) + return NF_ACCEPT; ret = process_sip_msg(skb, ct, protoff, dataoff, &dptr, &msglen); diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 346f871cf096..2e469ca2ca55 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -468,33 +468,22 @@ EXPORT_SYMBOL_GPL(nf_nat_packet); struct nf_nat_proto_clean { u8 l3proto; u8 l4proto; - bool hash; }; -/* Clear NAT section of all conntracks, in case we're loaded again. */ -static int nf_nat_proto_clean(struct nf_conn *i, void *data) +/* kill conntracks with affected NAT section */ +static int nf_nat_proto_remove(struct nf_conn *i, void *data) { const struct nf_nat_proto_clean *clean = data; struct nf_conn_nat *nat = nfct_nat(i); if (!nat) return 0; - if (!(i->status & IPS_SRC_NAT_DONE)) - return 0; + if ((clean->l3proto && nf_ct_l3num(i) != clean->l3proto) || (clean->l4proto && nf_ct_protonum(i) != clean->l4proto)) return 0; - if (clean->hash) { - spin_lock_bh(&nf_nat_lock); - hlist_del_rcu(&nat->bysource); - spin_unlock_bh(&nf_nat_lock); - } else { - memset(nat, 0, sizeof(*nat)); - i->status &= ~(IPS_NAT_MASK | IPS_NAT_DONE_MASK | - IPS_SEQ_ADJUST); - } - return 0; + return i->status & IPS_NAT_MASK ? 1 : 0; } static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto) @@ -506,16 +495,8 @@ static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto) struct net *net; rtnl_lock(); - /* Step 1 - remove from bysource hash */ - clean.hash = true; for_each_net(net) - nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); - synchronize_rcu(); - - /* Step 2 - clean NAT section */ - clean.hash = false; - for_each_net(net) - nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); + nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean); rtnl_unlock(); } @@ -527,16 +508,9 @@ static void nf_nat_l3proto_clean(u8 l3proto) struct net *net; rtnl_lock(); - /* Step 1 - remove from bysource hash */ - clean.hash = true; - for_each_net(net) - nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); - synchronize_rcu(); - /* Step 2 - clean NAT section */ - clean.hash = false; for_each_net(net) - nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); + nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean); rtnl_unlock(); } @@ -774,7 +748,7 @@ static void __net_exit nf_nat_net_exit(struct net *net) { struct nf_nat_proto_clean clean = {}; - nf_ct_iterate_cleanup(net, &nf_nat_proto_clean, &clean); + nf_ct_iterate_cleanup(net, &nf_nat_proto_remove, &clean); synchronize_rcu(); nf_ct_free_hashtable(net->ct.nat_bysource, net->ct.nat_htable_size); } diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 7fcb307dea47..103bd704b5fc 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -1173,7 +1173,7 @@ static int nr_recvmsg(struct kiocb *iocb, struct socket *sock, } if (sax != NULL) { - memset(sax, 0, sizeof(sax)); + memset(sax, 0, sizeof(*sax)); sax->sax25_family = AF_NETROM; skb_copy_from_linear_data_offset(skb, 7, sax->sax25_call.ax25_call, AX25_ADDR_LEN); diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 7bb5d4f6bb90..d2f9f2e57298 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1681,10 +1681,8 @@ struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 portid, return ERR_PTR(-ENOMEM); retval = ovs_vport_cmd_fill_info(vport, skb, portid, seq, 0, cmd); - if (retval < 0) { - kfree_skb(skb); - return ERR_PTR(retval); - } + BUG_ON(retval < 0); + return skb; } @@ -1814,25 +1812,33 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info) nla_get_u32(a[OVS_VPORT_ATTR_TYPE]) != vport->ops->type) err = -EINVAL; + reply = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!reply) { + err = -ENOMEM; + goto exit_unlock; + } + if (!err && a[OVS_VPORT_ATTR_OPTIONS]) err = ovs_vport_set_options(vport, a[OVS_VPORT_ATTR_OPTIONS]); if (err) - goto exit_unlock; + goto exit_free; + if (a[OVS_VPORT_ATTR_UPCALL_PID]) vport->upcall_portid = nla_get_u32(a[OVS_VPORT_ATTR_UPCALL_PID]); - reply = ovs_vport_cmd_build_info(vport, info->snd_portid, info->snd_seq, - OVS_VPORT_CMD_NEW); - if (IS_ERR(reply)) { - netlink_set_err(sock_net(skb->sk)->genl_sock, 0, - ovs_dp_vport_multicast_group.id, PTR_ERR(reply)); - goto exit_unlock; - } + err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid, + info->snd_seq, 0, OVS_VPORT_CMD_NEW); + BUG_ON(err < 0); ovs_unlock(); ovs_notify(reply, info, &ovs_dp_vport_multicast_group); return 0; + rtnl_unlock(); + return 0; + +exit_free: + kfree_skb(reply); exit_unlock: ovs_unlock(); return err; diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index cf9328be75e9..b15321a2228c 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -795,9 +795,9 @@ void ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow) void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow) { + BUG_ON(table->count == 0); hlist_del_rcu(&flow->hash_node[table->node_ver]); table->count--; - BUG_ON(table->count < 0); } /* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute. */ diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 1135d8227f9b..9b97172db84a 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -204,7 +204,6 @@ fw_change_attrs(struct net *net, struct tcf_proto *tp, struct fw_filter *f, if (err < 0) return err; - err = -EINVAL; if (tb[TCA_FW_CLASSID]) { f->res.classid = nla_get_u32(tb[TCA_FW_CLASSID]); tcf_bind_filter(tp, &f->res, base); @@ -218,6 +217,7 @@ fw_change_attrs(struct net *net, struct tcf_proto *tp, struct fw_filter *f, } #endif /* CONFIG_NET_CLS_IND */ + err = -EINVAL; if (tb[TCA_FW_MASK]) { mask = nla_get_u32(tb[TCA_FW_MASK]); if (mask != head->mask) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index dcc446e7fbf6..d5f35f15af98 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -304,10 +304,8 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, stru err = rpciod_up(); if (err) goto out_no_rpciod; - err = -EINVAL; - if (!xprt) - goto out_no_xprt; + err = -EINVAL; if (args->version >= program->nrvers) goto out_err; version = program->version[args->version]; @@ -382,10 +380,9 @@ out_no_principal: out_no_stats: kfree(clnt); out_err: - xprt_put(xprt); -out_no_xprt: rpciod_down(); out_no_rpciod: + xprt_put(xprt); return ERR_PTR(err); } @@ -512,7 +509,7 @@ static struct rpc_clnt *__rpc_clone_client(struct rpc_create_args *args, new = rpc_new_client(args, xprt); if (IS_ERR(new)) { err = PTR_ERR(new); - goto out_put; + goto out_err; } atomic_inc(&clnt->cl_count); @@ -525,8 +522,6 @@ static struct rpc_clnt *__rpc_clone_client(struct rpc_create_args *args, new->cl_chatty = clnt->cl_chatty; return new; -out_put: - xprt_put(xprt); out_err: dprintk("RPC: %s: returned error %d\n", __func__, err); return ERR_PTR(err); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 5ca1631de7ef..9efe01113c5c 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1414,7 +1414,7 @@ static void maybe_add_creds(struct sk_buff *skb, const struct socket *sock, !other->sk_socket || test_bit(SOCK_PASSCRED, &other->sk_socket->flags)) { UNIXCB(skb).pid = get_pid(task_tgid(current)); - current_euid_egid(&UNIXCB(skb).uid, &UNIXCB(skb).gid); + current_uid_gid(&UNIXCB(skb).uid, &UNIXCB(skb).gid); } } diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index b28cc384a5bc..4de4bc48493b 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -3016,6 +3016,7 @@ sub process { $dstat !~ /^'X'$/ && # character constants $dstat !~ /$exceptions/ && $dstat !~ /^\.$Ident\s*=/ && # .foo = + $dstat !~ /^(?:\#\s*$Ident|\#\s*$Constant)\s*$/ && # stringification #foo $dstat !~ /^do\s*$Constant\s*while\s*$Constant;?$/ && # do {...} while (...); // do {...} while (...) $dstat !~ /^for\s*$Constant$/ && # for (...) $dstat !~ /^for\s*$Constant\s+(?:$Ident|-?$Constant)$/ && # for (...) bar() diff --git a/security/capability.c b/security/capability.c index 579775088967..6783c3e6c88e 100644 --- a/security/capability.c +++ b/security/capability.c @@ -737,6 +737,11 @@ static int cap_tun_dev_open(void *security) { return 0; } + +static void cap_skb_owned_by(struct sk_buff *skb, struct sock *sk) +{ +} + #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM @@ -1071,6 +1076,7 @@ void __init security_fixup_ops(struct security_operations *ops) set_to_cap_if_null(ops, tun_dev_open); set_to_cap_if_null(ops, tun_dev_attach_queue); set_to_cap_if_null(ops, tun_dev_attach); + set_to_cap_if_null(ops, skb_owned_by); #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM set_to_cap_if_null(ops, xfrm_policy_alloc_security); diff --git a/security/security.c b/security/security.c index 7b88c6aeaed4..03f248b84e9f 100644 --- a/security/security.c +++ b/security/security.c @@ -1290,6 +1290,11 @@ int security_tun_dev_open(void *security) } EXPORT_SYMBOL(security_tun_dev_open); +void security_skb_owned_by(struct sk_buff *skb, struct sock *sk) +{ + security_ops->skb_owned_by(skb, sk); +} + #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 0a0609fce28b..bf889ee51509 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -51,6 +51,7 @@ #include #include #include /* for local_port_range[] */ +#include #include /* struct or_callable used in sock_rcv_skb */ #include #include @@ -4363,6 +4364,11 @@ static void selinux_inet_conn_established(struct sock *sk, struct sk_buff *skb) selinux_skb_peerlbl_sid(skb, family, &sksec->peer_sid); } +static void selinux_skb_owned_by(struct sk_buff *skb, struct sock *sk) +{ + skb_set_owner_w(skb, sk); +} + static int selinux_secmark_relabel_packet(u32 sid) { const struct task_security_struct *__tsec; @@ -5664,6 +5670,7 @@ static struct security_operations selinux_ops = { .tun_dev_attach_queue = selinux_tun_dev_attach_queue, .tun_dev_attach = selinux_tun_dev_attach, .tun_dev_open = selinux_tun_dev_open, + .skb_owned_by = selinux_skb_owned_by, #ifdef CONFIG_SECURITY_NETWORK_XFRM .xfrm_policy_alloc_security = selinux_xfrm_policy_alloc, diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 71ae86ca64ac..eb560fa32321 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -3222,18 +3222,10 @@ EXPORT_SYMBOL_GPL(snd_pcm_lib_default_mmap); int snd_pcm_lib_mmap_iomem(struct snd_pcm_substream *substream, struct vm_area_struct *area) { - long size; - unsigned long offset; + struct snd_pcm_runtime *runtime = substream->runtime;; area->vm_page_prot = pgprot_noncached(area->vm_page_prot); - area->vm_flags |= VM_IO; - size = area->vm_end - area->vm_start; - offset = area->vm_pgoff << PAGE_SHIFT; - if (io_remap_pfn_range(area, area->vm_start, - (substream->runtime->dma_addr + offset) >> PAGE_SHIFT, - size, area->vm_page_prot)) - return -EAGAIN; - return 0; + return vm_iomap_memory(area, runtime->dma_addr, runtime->dma_bytes); } EXPORT_SYMBOL(snd_pcm_lib_mmap_iomem); diff --git a/sound/soc/codecs/wm5102.c b/sound/soc/codecs/wm5102.c index b82bbf584146..34d0201d6a78 100644 --- a/sound/soc/codecs/wm5102.c +++ b/sound/soc/codecs/wm5102.c @@ -584,7 +584,7 @@ static int wm5102_sysclk_ev(struct snd_soc_dapm_widget *w, struct snd_kcontrol *kcontrol, int event) { struct snd_soc_codec *codec = w->codec; - struct arizona *arizona = dev_get_drvdata(codec->dev); + struct arizona *arizona = dev_get_drvdata(codec->dev->parent); struct regmap *regmap = codec->control_data; const struct reg_default *patch = NULL; int i, patch_size; diff --git a/sound/soc/codecs/wm8903.c b/sound/soc/codecs/wm8903.c index 134e41c870b9..f8a31ad0b203 100644 --- a/sound/soc/codecs/wm8903.c +++ b/sound/soc/codecs/wm8903.c @@ -1083,6 +1083,8 @@ static const struct snd_soc_dapm_route wm8903_intercon[] = { { "ROP", NULL, "Right Speaker PGA" }, { "RON", NULL, "Right Speaker PGA" }, + { "Charge Pump", NULL, "CLK_DSP" }, + { "Left Headphone Output PGA", NULL, "Charge Pump" }, { "Right Headphone Output PGA", NULL, "Charge Pump" }, { "Left Line Output PGA", NULL, "Charge Pump" }, diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c index d7231e336a7c..6bbeb0bf1a73 100644 --- a/sound/soc/samsung/i2s.c +++ b/sound/soc/samsung/i2s.c @@ -972,6 +972,7 @@ static const struct snd_soc_dai_ops samsung_i2s_dai_ops = { static struct i2s_dai *i2s_alloc_dai(struct platform_device *pdev, bool sec) { struct i2s_dai *i2s; + int ret; i2s = devm_kzalloc(&pdev->dev, sizeof(struct i2s_dai), GFP_KERNEL); if (i2s == NULL) @@ -996,15 +997,17 @@ static struct i2s_dai *i2s_alloc_dai(struct platform_device *pdev, bool sec) i2s->i2s_dai_drv.capture.channels_max = 2; i2s->i2s_dai_drv.capture.rates = SAMSUNG_I2S_RATES; i2s->i2s_dai_drv.capture.formats = SAMSUNG_I2S_FMTS; + dev_set_drvdata(&i2s->pdev->dev, i2s); } else { /* Create a new platform_device for Secondary */ - i2s->pdev = platform_device_register_resndata(NULL, - "samsung-i2s-sec", -1, NULL, 0, NULL, 0); + i2s->pdev = platform_device_alloc("samsung-i2s-sec", -1); if (IS_ERR(i2s->pdev)) return NULL; - } - /* Pre-assign snd_soc_dai_set_drvdata */ - dev_set_drvdata(&i2s->pdev->dev, i2s); + platform_set_drvdata(i2s->pdev, i2s); + ret = platform_device_add(i2s->pdev); + if (ret < 0) + return NULL; + } return i2s; } @@ -1107,6 +1110,10 @@ static int samsung_i2s_probe(struct platform_device *pdev) if (samsung_dai_type == TYPE_SEC) { sec_dai = dev_get_drvdata(&pdev->dev); + if (!sec_dai) { + dev_err(&pdev->dev, "Unable to get drvdata\n"); + return -EFAULT; + } snd_soc_register_dai(&sec_dai->pdev->dev, &sec_dai->i2s_dai_drv); asoc_dma_platform_register(&pdev->dev); diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c index b5b3db71e253..ed0bfb0ddb96 100644 --- a/sound/soc/soc-compress.c +++ b/sound/soc/soc-compress.c @@ -211,19 +211,27 @@ static int soc_compr_set_params(struct snd_compr_stream *cstream, if (platform->driver->compr_ops && platform->driver->compr_ops->set_params) { ret = platform->driver->compr_ops->set_params(cstream, params); if (ret < 0) - goto out; + goto err; } if (rtd->dai_link->compr_ops && rtd->dai_link->compr_ops->set_params) { ret = rtd->dai_link->compr_ops->set_params(cstream); if (ret < 0) - goto out; + goto err; } snd_soc_dapm_stream_event(rtd, SNDRV_PCM_STREAM_PLAYBACK, SND_SOC_DAPM_STREAM_START); -out: + /* cancel any delayed stream shutdown that is pending */ + rtd->pop_wait = 0; + mutex_unlock(&rtd->pcm_mutex); + + cancel_delayed_work_sync(&rtd->delayed_work); + + return ret; + +err: mutex_unlock(&rtd->pcm_mutex); return ret; } diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 507d251916af..ff4b45a5d796 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -2963,7 +2963,7 @@ int snd_soc_put_volsw_range(struct snd_kcontrol *kcontrol, val = val << shift; ret = snd_soc_update_bits_locked(codec, reg, val_mask, val); - if (ret != 0) + if (ret < 0) return ret; if (snd_soc_volsw_is_stereo(mc)) { diff --git a/sound/soc/tegra/tegra_pcm.c b/sound/soc/tegra/tegra_pcm.c index c925ab0adeb6..5e2c55c5b255 100644 --- a/sound/soc/tegra/tegra_pcm.c +++ b/sound/soc/tegra/tegra_pcm.c @@ -43,8 +43,6 @@ static const struct snd_pcm_hardware tegra_pcm_hardware = { .info = SNDRV_PCM_INFO_MMAP | SNDRV_PCM_INFO_MMAP_VALID | - SNDRV_PCM_INFO_PAUSE | - SNDRV_PCM_INFO_RESUME | SNDRV_PCM_INFO_INTERLEAVED, .formats = SNDRV_PCM_FMTBIT_S16_LE, .channels_min = 2, @@ -127,26 +125,6 @@ static int tegra_pcm_hw_free(struct snd_pcm_substream *substream) return 0; } -static int tegra_pcm_trigger(struct snd_pcm_substream *substream, int cmd) -{ - switch (cmd) { - case SNDRV_PCM_TRIGGER_START: - case SNDRV_PCM_TRIGGER_RESUME: - case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: - return snd_dmaengine_pcm_trigger(substream, - SNDRV_PCM_TRIGGER_START); - - case SNDRV_PCM_TRIGGER_STOP: - case SNDRV_PCM_TRIGGER_SUSPEND: - case SNDRV_PCM_TRIGGER_PAUSE_PUSH: - return snd_dmaengine_pcm_trigger(substream, - SNDRV_PCM_TRIGGER_STOP); - default: - return -EINVAL; - } - return 0; -} - static int tegra_pcm_mmap(struct snd_pcm_substream *substream, struct vm_area_struct *vma) { @@ -164,7 +142,7 @@ static struct snd_pcm_ops tegra_pcm_ops = { .ioctl = snd_pcm_lib_ioctl, .hw_params = tegra_pcm_hw_params, .hw_free = tegra_pcm_hw_free, - .trigger = tegra_pcm_trigger, + .trigger = snd_dmaengine_pcm_trigger, .pointer = snd_dmaengine_pcm_pointer, .mmap = tegra_pcm_mmap, }; diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index 497d2741d119..ebe91440a068 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -509,7 +509,7 @@ static int snd_nativeinstruments_control_get(struct snd_kcontrol *kcontrol, else ret = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), bRequest, USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_IN, - 0, cpu_to_le16(wIndex), + 0, wIndex, &tmp, sizeof(tmp), 1000); up_read(&mixer->chip->shutdown_rwsem); @@ -540,7 +540,7 @@ static int snd_nativeinstruments_control_put(struct snd_kcontrol *kcontrol, else ret = usb_control_msg(dev, usb_sndctrlpipe(dev, 0), bRequest, USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_OUT, - cpu_to_le16(wValue), cpu_to_le16(wIndex), + wValue, wIndex, NULL, 0, 1000); up_read(&mixer->chip->shutdown_rwsem); diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 5325a3869bb7..9c5ab22358b1 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -486,7 +486,7 @@ static int snd_usb_nativeinstruments_boot_quirk(struct usb_device *dev) { int ret = usb_control_msg(dev, usb_sndctrlpipe(dev, 0), 0xaf, USB_TYPE_VENDOR | USB_RECIP_DEVICE, - cpu_to_le16(1), 0, NULL, 0, 1000); + 1, 0, NULL, 0, 1000); if (ret < 0) return ret; diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 6f3214ed4444..321e066a0753 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -1421,6 +1421,7 @@ int has_nehalem_turbo_ratio_limit(unsigned int family, unsigned int model) case 0x3C: /* HSW */ case 0x3F: /* HSW */ case 0x45: /* HSW */ + case 0x46: /* HSW */ return 1; case 0x2E: /* Nehalem-EX Xeon - Beckton */ case 0x2F: /* Westmere-EX Xeon - Eagleton */ @@ -1515,6 +1516,7 @@ void rapl_probe(unsigned int family, unsigned int model) case 0x3C: /* HSW */ case 0x3F: /* HSW */ case 0x45: /* HSW */ + case 0x46: /* HSW */ do_rapl = RAPL_PKG | RAPL_CORES | RAPL_GFX; break; case 0x2D: @@ -1754,6 +1756,7 @@ int is_snb(unsigned int family, unsigned int model) case 0x3C: /* HSW */ case 0x3F: /* HSW */ case 0x45: /* HSW */ + case 0x46: /* HSW */ return 1; } return 0; @@ -2276,7 +2279,7 @@ int main(int argc, char **argv) cmdline(argc, argv); if (verbose) - fprintf(stderr, "turbostat v3.2 February 11, 2013" + fprintf(stderr, "turbostat v3.3 March 15, 2013" " - Len Brown \n"); turbostat_init(); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index adc68feb5c5a..f18013f09e68 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1541,21 +1541,38 @@ int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, } int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, - gpa_t gpa) + gpa_t gpa, unsigned long len) { struct kvm_memslots *slots = kvm_memslots(kvm); int offset = offset_in_page(gpa); - gfn_t gfn = gpa >> PAGE_SHIFT; + gfn_t start_gfn = gpa >> PAGE_SHIFT; + gfn_t end_gfn = (gpa + len - 1) >> PAGE_SHIFT; + gfn_t nr_pages_needed = end_gfn - start_gfn + 1; + gfn_t nr_pages_avail; ghc->gpa = gpa; ghc->generation = slots->generation; - ghc->memslot = gfn_to_memslot(kvm, gfn); - ghc->hva = gfn_to_hva_many(ghc->memslot, gfn, NULL); - if (!kvm_is_error_hva(ghc->hva)) + ghc->len = len; + ghc->memslot = gfn_to_memslot(kvm, start_gfn); + ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, &nr_pages_avail); + if (!kvm_is_error_hva(ghc->hva) && nr_pages_avail >= nr_pages_needed) { ghc->hva += offset; - else - return -EFAULT; - + } else { + /* + * If the requested region crosses two memslots, we still + * verify that the entire region is valid here. + */ + while (start_gfn <= end_gfn) { + ghc->memslot = gfn_to_memslot(kvm, start_gfn); + ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, + &nr_pages_avail); + if (kvm_is_error_hva(ghc->hva)) + return -EFAULT; + start_gfn += nr_pages_avail; + } + /* Use the slow path for cross page reads and writes. */ + ghc->memslot = NULL; + } return 0; } EXPORT_SYMBOL_GPL(kvm_gfn_to_hva_cache_init); @@ -1566,8 +1583,13 @@ int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, struct kvm_memslots *slots = kvm_memslots(kvm); int r; + BUG_ON(len > ghc->len); + if (slots->generation != ghc->generation) - kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa); + kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa, ghc->len); + + if (unlikely(!ghc->memslot)) + return kvm_write_guest(kvm, ghc->gpa, data, len); if (kvm_is_error_hva(ghc->hva)) return -EFAULT; @@ -1587,8 +1609,13 @@ int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, struct kvm_memslots *slots = kvm_memslots(kvm); int r; + BUG_ON(len > ghc->len); + if (slots->generation != ghc->generation) - kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa); + kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa, ghc->len); + + if (unlikely(!ghc->memslot)) + return kvm_read_guest(kvm, ghc->gpa, data, len); if (kvm_is_error_hva(ghc->hva)) return -EFAULT;