diff --git a/Makefile b/Makefile index 41fe3014b712..ccf2602f664d 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 9 -SUBLEVEL = 137 +SUBLEVEL = 138 EXTRAVERSION = NAME = Roaring Lionus diff --git a/arch/alpha/include/asm/termios.h b/arch/alpha/include/asm/termios.h index 7fde0f88da88..51ed90be770a 100644 --- a/arch/alpha/include/asm/termios.h +++ b/arch/alpha/include/asm/termios.h @@ -72,9 +72,15 @@ }) #define user_termios_to_kernel_termios(k, u) \ - copy_from_user(k, u, sizeof(struct termios)) + copy_from_user(k, u, sizeof(struct termios2)) #define kernel_termios_to_user_termios(u, k) \ + copy_to_user(u, k, sizeof(struct termios2)) + +#define user_termios_to_kernel_termios_1(k, u) \ + copy_from_user(k, u, sizeof(struct termios)) + +#define kernel_termios_to_user_termios_1(u, k) \ copy_to_user(u, k, sizeof(struct termios)) #endif /* _ALPHA_TERMIOS_H */ diff --git a/arch/alpha/include/uapi/asm/ioctls.h b/arch/alpha/include/uapi/asm/ioctls.h index f30c94ae1bdb..7ee8ab577e11 100644 --- a/arch/alpha/include/uapi/asm/ioctls.h +++ b/arch/alpha/include/uapi/asm/ioctls.h @@ -31,6 +31,11 @@ #define TCXONC _IO('t', 30) #define TCFLSH _IO('t', 31) +#define TCGETS2 _IOR('T', 42, struct termios2) +#define TCSETS2 _IOW('T', 43, struct termios2) +#define TCSETSW2 _IOW('T', 44, struct termios2) +#define TCSETSF2 _IOW('T', 45, struct termios2) + #define TIOCSWINSZ _IOW('t', 103, struct winsize) #define TIOCGWINSZ _IOR('t', 104, struct winsize) #define TIOCSTART _IO('t', 110) /* start output, like ^Q */ diff --git a/arch/alpha/include/uapi/asm/termbits.h b/arch/alpha/include/uapi/asm/termbits.h index 879dd3589921..483c7ec2a879 100644 --- a/arch/alpha/include/uapi/asm/termbits.h +++ b/arch/alpha/include/uapi/asm/termbits.h @@ -25,6 +25,19 @@ struct termios { speed_t c_ospeed; /* output speed */ }; +/* Alpha has identical termios and termios2 */ + +struct termios2 { + tcflag_t c_iflag; /* input mode flags */ + tcflag_t c_oflag; /* output mode flags */ + tcflag_t c_cflag; /* control mode flags */ + tcflag_t c_lflag; /* local mode flags */ + cc_t c_cc[NCCS]; /* control characters */ + cc_t c_line; /* line discipline (== c_cc[19]) */ + speed_t c_ispeed; /* input speed */ + speed_t c_ospeed; /* output speed */ +}; + /* Alpha has matching termios and ktermios */ struct ktermios { @@ -147,6 +160,7 @@ struct ktermios { #define B3000000 00034 #define B3500000 00035 #define B4000000 00036 +#define BOTHER 00037 #define CSIZE 00001400 #define CS5 00000000 @@ -164,6 +178,9 @@ struct ktermios { #define CMSPAR 010000000000 /* mark or space (stick) parity */ #define CRTSCTS 020000000000 /* flow control */ +#define CIBAUD 07600000 +#define IBSHIFT 16 + /* c_lflag bits */ #define ISIG 0x00000080 #define ICANON 0x00000100 diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig index 8ec4dbbb50b0..47c3fb8d4313 100644 --- a/arch/arm/configs/imx_v6_v7_defconfig +++ b/arch/arm/configs/imx_v6_v7_defconfig @@ -361,6 +361,7 @@ CONFIG_ZISOFS=y CONFIG_UDF_FS=m CONFIG_MSDOS_FS=m CONFIG_VFAT_FS=y +CONFIG_TMPFS_POSIX_ACL=y CONFIG_JFFS2_FS=y CONFIG_UBIFS_FS=y CONFIG_NFS_FS=y diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 20436972537f..a670c70f4def 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -1092,8 +1092,6 @@ static void cpu_init_hyp_mode(void *dummy) __cpu_init_hyp_mode(pgd_ptr, hyp_stack_ptr, vector_ptr); __cpu_init_stage2(); - - kvm_arm_init_debug(); } static void cpu_hyp_reinit(void) @@ -1108,6 +1106,8 @@ static void cpu_hyp_reinit(void) if (__hyp_get_vectors() == hyp_default_vectors) cpu_init_hyp_mode(NULL); } + + kvm_arm_init_debug(); } static void cpu_hyp_reset(void) diff --git a/arch/mips/include/asm/mach-loongson64/irq.h b/arch/mips/include/asm/mach-loongson64/irq.h index d18c45c7c394..19ff9ce46c02 100644 --- a/arch/mips/include/asm/mach-loongson64/irq.h +++ b/arch/mips/include/asm/mach-loongson64/irq.h @@ -9,7 +9,7 @@ #define MIPS_CPU_IRQ_BASE 56 #define LOONGSON_UART_IRQ (MIPS_CPU_IRQ_BASE + 2) /* UART */ -#define LOONGSON_HT1_IRQ (MIPS_CPU_IRQ_BASE + 3) /* HT1 */ +#define LOONGSON_BRIDGE_IRQ (MIPS_CPU_IRQ_BASE + 3) /* CASCADE */ #define LOONGSON_TIMER_IRQ (MIPS_CPU_IRQ_BASE + 7) /* CPU Timer */ #define LOONGSON_HT1_CFG_BASE loongson_sysconf.ht_control_base diff --git a/arch/mips/kernel/crash.c b/arch/mips/kernel/crash.c index 1723b1762297..e757f36cea6f 100644 --- a/arch/mips/kernel/crash.c +++ b/arch/mips/kernel/crash.c @@ -34,6 +34,9 @@ static void crash_shutdown_secondary(void *passed_regs) if (!cpu_online(cpu)) return; + /* We won't be sent IPIs any more. */ + set_cpu_online(cpu, false); + local_irq_disable(); if (!cpumask_test_cpu(cpu, &cpus_in_crash)) crash_save_cpu(regs, cpu); diff --git a/arch/mips/kernel/machine_kexec.c b/arch/mips/kernel/machine_kexec.c index 59725204105c..32b567e88b02 100644 --- a/arch/mips/kernel/machine_kexec.c +++ b/arch/mips/kernel/machine_kexec.c @@ -96,6 +96,9 @@ machine_kexec(struct kimage *image) *ptr = (unsigned long) phys_to_virt(*ptr); } + /* Mark offline BEFORE disabling local irq. */ + set_cpu_online(smp_processor_id(), false); + /* * we do not want to be bothered. */ diff --git a/arch/mips/loongson64/loongson-3/irq.c b/arch/mips/loongson64/loongson-3/irq.c index 8e7649088353..027f53e3bc81 100644 --- a/arch/mips/loongson64/loongson-3/irq.c +++ b/arch/mips/loongson64/loongson-3/irq.c @@ -44,51 +44,8 @@ void mach_irq_dispatch(unsigned int pending) } } -static struct irqaction cascade_irqaction = { - .handler = no_action, - .flags = IRQF_NO_SUSPEND, - .name = "cascade", -}; - -static inline void mask_loongson_irq(struct irq_data *d) -{ - clear_c0_status(0x100 << (d->irq - MIPS_CPU_IRQ_BASE)); - irq_disable_hazard(); - - /* Workaround: UART IRQ may deliver to any core */ - if (d->irq == LOONGSON_UART_IRQ) { - int cpu = smp_processor_id(); - int node_id = cpu_logical_map(cpu) / loongson_sysconf.cores_per_node; - int core_id = cpu_logical_map(cpu) % loongson_sysconf.cores_per_node; - u64 intenclr_addr = smp_group[node_id] | - (u64)(&LOONGSON_INT_ROUTER_INTENCLR); - u64 introuter_lpc_addr = smp_group[node_id] | - (u64)(&LOONGSON_INT_ROUTER_LPC); - - *(volatile u32 *)intenclr_addr = 1 << 10; - *(volatile u8 *)introuter_lpc_addr = 0x10 + (1<irq == LOONGSON_UART_IRQ) { - int cpu = smp_processor_id(); - int node_id = cpu_logical_map(cpu) / loongson_sysconf.cores_per_node; - int core_id = cpu_logical_map(cpu) % loongson_sysconf.cores_per_node; - u64 intenset_addr = smp_group[node_id] | - (u64)(&LOONGSON_INT_ROUTER_INTENSET); - u64 introuter_lpc_addr = smp_group[node_id] | - (u64)(&LOONGSON_INT_ROUTER_LPC); - - *(volatile u32 *)intenset_addr = 1 << 10; - *(volatile u8 *)introuter_lpc_addr = 0x10 + (1<irq - MIPS_CPU_IRQ_BASE)); - irq_enable_hazard(); -} +static inline void mask_loongson_irq(struct irq_data *d) { } +static inline void unmask_loongson_irq(struct irq_data *d) { } /* For MIPS IRQs which shared by all cores */ static struct irq_chip loongson_irq_chip = { @@ -126,12 +83,11 @@ void __init mach_init_irq(void) mips_cpu_irq_init(); init_i8259_irqs(); irq_set_chip_and_handler(LOONGSON_UART_IRQ, - &loongson_irq_chip, handle_level_irq); - - /* setup HT1 irq */ - setup_irq(LOONGSON_HT1_IRQ, &cascade_irqaction); + &loongson_irq_chip, handle_percpu_irq); + irq_set_chip_and_handler(LOONGSON_BRIDGE_IRQ, + &loongson_irq_chip, handle_percpu_irq); - set_c0_status(STATUSF_IP2 | STATUSF_IP6); + set_c0_status(STATUSF_IP2 | STATUSF_IP3 | STATUSF_IP6); } #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/mips/pci/pci-legacy.c b/arch/mips/pci/pci-legacy.c index 014649be158d..2d6886f09ba3 100644 --- a/arch/mips/pci/pci-legacy.c +++ b/arch/mips/pci/pci-legacy.c @@ -116,8 +116,12 @@ static void pcibios_scanbus(struct pci_controller *hose) if (pci_has_flag(PCI_PROBE_ONLY)) { pci_bus_claim_resources(bus); } else { + struct pci_bus *child; + pci_bus_size_bridges(bus); pci_bus_assign_resources(bus); + list_for_each_entry(child, &bus->children, node) + pcie_bus_configure_settings(child); } pci_bus_add_devices(bus); } diff --git a/arch/parisc/kernel/hpmc.S b/arch/parisc/kernel/hpmc.S index 0fbd0a0e1cda..e88f4e7f39f3 100644 --- a/arch/parisc/kernel/hpmc.S +++ b/arch/parisc/kernel/hpmc.S @@ -83,7 +83,8 @@ END(hpmc_pim_data) .text .import intr_save, code -ENTRY_CFI(os_hpmc) + .align 16 +ENTRY(os_hpmc) .os_hpmc: /* @@ -299,11 +300,14 @@ os_hpmc_6: b . nop -ENDPROC_CFI(os_hpmc) + .align 16 /* make function length multiple of 16 bytes */ .os_hpmc_end: __INITRODATA - .export os_hpmc_size +.globl os_hpmc_size + .align 4 + .type os_hpmc_size, @object + .size os_hpmc_size, 4 os_hpmc_size: .word .os_hpmc_end-.os_hpmc diff --git a/arch/powerpc/boot/crt0.S b/arch/powerpc/boot/crt0.S index 12866ccb5694..5c2199857aa8 100644 --- a/arch/powerpc/boot/crt0.S +++ b/arch/powerpc/boot/crt0.S @@ -47,8 +47,10 @@ p_end: .long _end p_pstack: .long _platform_stack_top #endif - .weak _zimage_start .globl _zimage_start + /* Clang appears to require the .weak directive to be after the symbol + * is defined. See https://bugs.llvm.org/show_bug.cgi?id=38921 */ + .weak _zimage_start _zimage_start: .globl _zimage_start_lib _zimage_start_lib: diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index e5bfbf62827a..8336b9016ca9 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -169,6 +169,11 @@ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len) int n = 0, l = 0; char buffer[128]; + if (!pdn) { + pr_warn("EEH: Note: No error log for absent device.\n"); + return 0; + } + n += scnprintf(buf+n, len-n, "%04x:%02x:%02x.%01x\n", edev->phb->global_number, pdn->busno, PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn)); diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c index 0b50019505a5..79cf21be8f6e 100644 --- a/arch/powerpc/mm/tlb_nohash.c +++ b/arch/powerpc/mm/tlb_nohash.c @@ -481,6 +481,9 @@ static void setup_page_sizes(void) for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) { struct mmu_psize_def *def = &mmu_psize_defs[psize]; + if (!def->shift) + continue; + if (tlb1ps & (1U << (def->shift - 10))) { def->flags |= MMU_PAGE_SIZE_DIRECT; diff --git a/arch/xtensa/boot/Makefile b/arch/xtensa/boot/Makefile index ca20a892021b..6c6877d628ef 100644 --- a/arch/xtensa/boot/Makefile +++ b/arch/xtensa/boot/Makefile @@ -31,7 +31,7 @@ $(bootdir-y): $(addprefix $(obj)/,$(subdir-y)) \ $(addprefix $(obj)/,$(host-progs)) $(Q)$(MAKE) $(build)=$(obj)/$@ $(MAKECMDGOALS) -OBJCOPYFLAGS = --strip-all -R .comment -R .note.gnu.build-id -O binary +OBJCOPYFLAGS = --strip-all -R .comment -R .notes -O binary vmlinux.bin: vmlinux FORCE $(call if_changed,objcopy) diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h index b42d68bfe3cf..521c1e789e6e 100644 --- a/arch/xtensa/include/asm/processor.h +++ b/arch/xtensa/include/asm/processor.h @@ -24,7 +24,11 @@ # error Linux requires the Xtensa Windowed Registers Option. #endif -#define ARCH_SLAB_MINALIGN XCHAL_DATA_WIDTH +/* Xtensa ABI requires stack alignment to be at least 16 */ + +#define STACK_ALIGN (XCHAL_DATA_WIDTH > 16 ? XCHAL_DATA_WIDTH : 16) + +#define ARCH_SLAB_MINALIGN STACK_ALIGN /* * User space process size: 1 GB. diff --git a/arch/xtensa/kernel/head.S b/arch/xtensa/kernel/head.S index 23ce62e60435..27c8e07ace43 100644 --- a/arch/xtensa/kernel/head.S +++ b/arch/xtensa/kernel/head.S @@ -88,9 +88,12 @@ _SetupMMU: initialize_mmu #if defined(CONFIG_MMU) && XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY rsr a2, excsave1 - movi a3, 0x08000000 + movi a3, XCHAL_KSEG_PADDR + bltu a2, a3, 1f + sub a2, a2, a3 + movi a3, XCHAL_KSEG_SIZE bgeu a2, a3, 1f - movi a3, 0xd0000000 + movi a3, XCHAL_KSEG_CACHED_VADDR add a2, a2, a3 wsr a2, excsave1 1: diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S index 31411fc82662..e8358ea0a9f9 100644 --- a/arch/xtensa/kernel/vmlinux.lds.S +++ b/arch/xtensa/kernel/vmlinux.lds.S @@ -109,6 +109,7 @@ SECTIONS .fixup : { *(.fixup) } EXCEPTION_TABLE(16) + NOTES /* Data section */ _sdata = .; diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 987e8f503522..ff4280800cd0 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -2435,7 +2435,7 @@ static int cdrom_ioctl_select_disc(struct cdrom_device_info *cdi, return -ENOSYS; if (arg != CDSL_CURRENT && arg != CDSL_NONE) { - if ((int)arg >= cdi->capacity) + if (arg >= cdi->capacity) return -EINVAL; } diff --git a/drivers/clk/at91/clk-pll.c b/drivers/clk/at91/clk-pll.c index 2bb2551c6245..a17a428fa706 100644 --- a/drivers/clk/at91/clk-pll.c +++ b/drivers/clk/at91/clk-pll.c @@ -133,6 +133,9 @@ static unsigned long clk_pll_recalc_rate(struct clk_hw *hw, { struct clk_pll *pll = to_clk_pll(hw); + if (!pll->div || !pll->mul) + return 0; + return (parent_rate / pll->div) * (pll->mul + 1); } diff --git a/drivers/clk/clk-s2mps11.c b/drivers/clk/clk-s2mps11.c index fbaa84a33c46..14071a57c926 100644 --- a/drivers/clk/clk-s2mps11.c +++ b/drivers/clk/clk-s2mps11.c @@ -245,6 +245,36 @@ static const struct platform_device_id s2mps11_clk_id[] = { }; MODULE_DEVICE_TABLE(platform, s2mps11_clk_id); +#ifdef CONFIG_OF +/* + * Device is instantiated through parent MFD device and device matching is done + * through platform_device_id. + * + * However if device's DT node contains proper clock compatible and driver is + * built as a module, then the *module* matching will be done trough DT aliases. + * This requires of_device_id table. In the same time this will not change the + * actual *device* matching so do not add .of_match_table. + */ +static const struct of_device_id s2mps11_dt_match[] = { + { + .compatible = "samsung,s2mps11-clk", + .data = (void *)S2MPS11X, + }, { + .compatible = "samsung,s2mps13-clk", + .data = (void *)S2MPS13X, + }, { + .compatible = "samsung,s2mps14-clk", + .data = (void *)S2MPS14X, + }, { + .compatible = "samsung,s5m8767-clk", + .data = (void *)S5M8767X, + }, { + /* Sentinel */ + }, +}; +MODULE_DEVICE_TABLE(of, s2mps11_dt_match); +#endif + static struct platform_driver s2mps11_clk_driver = { .driver = { .name = "s2mps11-clk", diff --git a/drivers/clk/hisilicon/reset.c b/drivers/clk/hisilicon/reset.c index 2a5015c736ce..43e82fa64422 100644 --- a/drivers/clk/hisilicon/reset.c +++ b/drivers/clk/hisilicon/reset.c @@ -109,9 +109,8 @@ struct hisi_reset_controller *hisi_reset_init(struct platform_device *pdev) return NULL; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - rstc->membase = devm_ioremap(&pdev->dev, - res->start, resource_size(res)); - if (!rstc->membase) + rstc->membase = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(rstc->membase)) return NULL; spin_lock_init(&rstc->lock); diff --git a/drivers/clk/rockchip/clk-ddr.c b/drivers/clk/rockchip/clk-ddr.c index e8075359366b..ebce5260068b 100644 --- a/drivers/clk/rockchip/clk-ddr.c +++ b/drivers/clk/rockchip/clk-ddr.c @@ -80,16 +80,12 @@ static long rockchip_ddrclk_sip_round_rate(struct clk_hw *hw, static u8 rockchip_ddrclk_get_parent(struct clk_hw *hw) { struct rockchip_ddrclk *ddrclk = to_rockchip_ddrclk_hw(hw); - int num_parents = clk_hw_get_num_parents(hw); u32 val; val = clk_readl(ddrclk->reg_base + ddrclk->mux_offset) >> ddrclk->mux_shift; val &= GENMASK(ddrclk->mux_width - 1, 0); - if (val >= num_parents) - return -EINVAL; - return val; } diff --git a/drivers/clocksource/i8253.c b/drivers/clocksource/i8253.c index 0efd36e483ab..a2b545fdee81 100644 --- a/drivers/clocksource/i8253.c +++ b/drivers/clocksource/i8253.c @@ -19,6 +19,13 @@ DEFINE_RAW_SPINLOCK(i8253_lock); EXPORT_SYMBOL(i8253_lock); +/* + * Handle PIT quirk in pit_shutdown() where zeroing the counter register + * restarts the PIT, negating the shutdown. On platforms with the quirk, + * platform specific code can set this to false. + */ +bool i8253_clear_counter_on_shutdown __ro_after_init = true; + #ifdef CONFIG_CLKSRC_I8253 /* * Since the PIT overflows every tick, its not very useful @@ -108,8 +115,11 @@ static int pit_shutdown(struct clock_event_device *evt) raw_spin_lock(&i8253_lock); outb_p(0x30, PIT_MODE); - outb_p(0, PIT_CH0); - outb_p(0, PIT_CH0); + + if (i8253_clear_counter_on_shutdown) { + outb_p(0, PIT_CH0); + outb_p(0, PIT_CH0); + } raw_spin_unlock(&i8253_lock); return 0; diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index db7890cb254e..b59441d109a5 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -1230,6 +1230,9 @@ static struct drm_dp_mst_branch *drm_dp_get_mst_branch_device(struct drm_dp_mst_ mutex_lock(&mgr->lock); mstb = mgr->mst_primary; + if (!mstb) + goto out; + for (i = 0; i < lct - 1; i++) { int shift = (i % 2) ? 0 : 4; int port_num = (rad[i / 2] >> shift) & 0xf; diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c index 6c70a5bfd7d8..840522867436 100644 --- a/drivers/gpu/drm/i915/intel_audio.c +++ b/drivers/gpu/drm/i915/intel_audio.c @@ -76,6 +76,9 @@ static const struct { /* HDMI N/CTS table */ #define TMDS_297M 297000 #define TMDS_296M 296703 +#define TMDS_594M 594000 +#define TMDS_593M 593407 + static const struct { int sample_rate; int clock; @@ -96,6 +99,20 @@ static const struct { { 176400, TMDS_297M, 18816, 247500 }, { 192000, TMDS_296M, 23296, 281250 }, { 192000, TMDS_297M, 20480, 247500 }, + { 44100, TMDS_593M, 8918, 937500 }, + { 44100, TMDS_594M, 9408, 990000 }, + { 48000, TMDS_593M, 5824, 562500 }, + { 48000, TMDS_594M, 6144, 594000 }, + { 32000, TMDS_593M, 5824, 843750 }, + { 32000, TMDS_594M, 3072, 445500 }, + { 88200, TMDS_593M, 17836, 937500 }, + { 88200, TMDS_594M, 18816, 990000 }, + { 96000, TMDS_593M, 11648, 562500 }, + { 96000, TMDS_594M, 12288, 594000 }, + { 176400, TMDS_593M, 35672, 937500 }, + { 176400, TMDS_594M, 37632, 990000 }, + { 192000, TMDS_593M, 23296, 562500 }, + { 192000, TMDS_594M, 24576, 594000 }, }; /* get AUD_CONFIG_PIXEL_CLOCK_HDMI_* value for mode */ diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 67db1577ee49..fd11be6b23b9 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -368,7 +368,8 @@ static u64 execlists_update_context(struct drm_i915_gem_request *rq) reg_state[CTX_RING_TAIL+1] = intel_ring_offset(rq->ring, rq->tail); - /* True 32b PPGTT with dynamic page allocation: update PDP + /* + * True 32b PPGTT with dynamic page allocation: update PDP * registers and point the unallocated PDPs to scratch page. * PML4 is allocated during ppgtt init, so this is not needed * in 48-bit mode. @@ -376,6 +377,17 @@ static u64 execlists_update_context(struct drm_i915_gem_request *rq) if (ppgtt && !USES_FULL_48BIT_PPGTT(ppgtt->base.dev)) execlists_update_context_pdps(ppgtt, reg_state); + /* + * Make sure the context image is complete before we submit it to HW. + * + * Ostensibly, writes (including the WCB) should be flushed prior to + * an uncached write such as our mmio register access, the empirical + * evidence (esp. on Braswell) suggests that the WC write into memory + * may not be visible to the HW prior to the completion of the UC + * register write and that we may begin execution from the context + * before its image is complete leading to invalid PD chasing. + */ + wmb(); return ce->lrc_desc; } diff --git a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c index 7def04049498..6a0b25e0823f 100644 --- a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c +++ b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c @@ -273,6 +273,17 @@ static int dmm_txn_commit(struct dmm_txn *txn, bool wait) } txn->last_pat->next_pa = 0; + /* ensure that the written descriptors are visible to DMM */ + wmb(); + + /* + * NOTE: the wmb() above should be enough, but there seems to be a bug + * in OMAP's memory barrier implementation, which in some rare cases may + * cause the writes not to be observable after wmb(). + */ + + /* read back to ensure the data is in RAM */ + readl(&txn->last_pat->next_pa); /* write to PAT_DESCR to clear out any pending transaction */ dmm_write(dmm, 0x0, reg[PAT_DESCR][engine->id]); diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c index 8c8cbe837e61..f2033ab36f37 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c @@ -478,6 +478,11 @@ static int rockchip_drm_platform_remove(struct platform_device *pdev) return 0; } +static void rockchip_drm_platform_shutdown(struct platform_device *pdev) +{ + rockchip_drm_platform_remove(pdev); +} + static const struct of_device_id rockchip_drm_dt_ids[] = { { .compatible = "rockchip,display-subsystem", }, { /* sentinel */ }, @@ -487,6 +492,7 @@ MODULE_DEVICE_TABLE(of, rockchip_drm_dt_ids); static struct platform_driver rockchip_drm_platform_driver = { .probe = rockchip_drm_platform_probe, .remove = rockchip_drm_platform_remove, + .shutdown = rockchip_drm_platform_shutdown, .driver = { .name = "rockchip-drm", .of_match_table = rockchip_drm_dt_ids, diff --git a/drivers/media/i2c/tvp5150.c b/drivers/media/i2c/tvp5150.c index 5d9c2b03d83a..e83f8111a5fb 100644 --- a/drivers/media/i2c/tvp5150.c +++ b/drivers/media/i2c/tvp5150.c @@ -897,9 +897,6 @@ static int tvp5150_set_selection(struct v4l2_subdev *sd, /* tvp5150 has some special limits */ rect.left = clamp(rect.left, 0, TVP5150_MAX_CROP_LEFT); - rect.width = clamp_t(unsigned int, rect.width, - TVP5150_H_MAX - TVP5150_MAX_CROP_LEFT - rect.left, - TVP5150_H_MAX - rect.left); rect.top = clamp(rect.top, 0, TVP5150_MAX_CROP_TOP); /* Calculate height based on current standard */ @@ -913,9 +910,16 @@ static int tvp5150_set_selection(struct v4l2_subdev *sd, else hmax = TVP5150_V_MAX_OTHERS; - rect.height = clamp_t(unsigned int, rect.height, + /* + * alignments: + * - width = 2 due to UYVY colorspace + * - height, image = no special alignment + */ + v4l_bound_align_image(&rect.width, + TVP5150_H_MAX - TVP5150_MAX_CROP_LEFT - rect.left, + TVP5150_H_MAX - rect.left, 1, &rect.height, hmax - TVP5150_MAX_CROP_TOP - rect.top, - hmax - rect.top); + hmax - rect.top, 0, 0); tvp5150_write(sd, TVP5150_VERT_BLANKING_START, rect.top); tvp5150_write(sd, TVP5150_VERT_BLANKING_STOP, diff --git a/drivers/media/pci/cx23885/altera-ci.c b/drivers/media/pci/cx23885/altera-ci.c index aaf4e46ff3e9..a0c1ff97f905 100644 --- a/drivers/media/pci/cx23885/altera-ci.c +++ b/drivers/media/pci/cx23885/altera-ci.c @@ -660,6 +660,10 @@ static int altera_hw_filt_init(struct altera_ci_config *config, int hw_filt_nr) } temp_int = append_internal(inter); + if (!temp_int) { + ret = -ENOMEM; + goto err; + } inter->filts_used = 1; inter->dev = config->dev; inter->fpga_rw = config->fpga_rw; @@ -694,6 +698,7 @@ err: __func__, ret); kfree(pid_filt); + kfree(inter); return ret; } @@ -728,6 +733,10 @@ int altera_ci_init(struct altera_ci_config *config, int ci_nr) } temp_int = append_internal(inter); + if (!temp_int) { + ret = -ENOMEM; + goto err; + } inter->cis_used = 1; inter->dev = config->dev; inter->fpga_rw = config->fpga_rw; @@ -796,6 +805,7 @@ err: ci_dbg_print("%s: Cannot initialize CI: Error %d.\n", __func__, ret); kfree(state); + kfree(inter); return ret; } diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig index 58329d2dacd1..75c816a5dded 100644 --- a/drivers/mtd/devices/Kconfig +++ b/drivers/mtd/devices/Kconfig @@ -196,7 +196,7 @@ comment "Disk-On-Chip Device Drivers" config MTD_DOCG3 tristate "M-Systems Disk-On-Chip G3" select BCH - select BCH_CONST_PARAMS + select BCH_CONST_PARAMS if !MTD_NAND_BCH select BITREVERSE ---help--- This provides an MTD device driver for the M-Systems DiskOnChip diff --git a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c index 31f61a744d66..9473d12ce239 100644 --- a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c +++ b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c @@ -541,8 +541,8 @@ bnad_get_strings(struct net_device *netdev, u32 stringset, u8 *string) for (i = 0; i < BNAD_ETHTOOL_STATS_NUM; i++) { BUG_ON(!(strlen(bnad_net_stats_strings[i]) < ETH_GSTRING_LEN)); - memcpy(string, bnad_net_stats_strings[i], - ETH_GSTRING_LEN); + strncpy(string, bnad_net_stats_strings[i], + ETH_GSTRING_LEN); string += ETH_GSTRING_LEN; } bmap = bna_tx_rid_mask(&bnad->bna); diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c index e84574b1eae7..2a81f6d72140 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c +++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c @@ -1826,11 +1826,12 @@ static void e1000_get_ethtool_stats(struct net_device *netdev, { struct e1000_adapter *adapter = netdev_priv(netdev); int i; - char *p = NULL; const struct e1000_stats *stat = e1000_gstrings_stats; e1000_update_stats(adapter); - for (i = 0; i < E1000_GLOBAL_STATS_LEN; i++) { + for (i = 0; i < E1000_GLOBAL_STATS_LEN; i++, stat++) { + char *p; + switch (stat->type) { case NETDEV_STATS: p = (char *)netdev + stat->stat_offset; @@ -1841,15 +1842,13 @@ static void e1000_get_ethtool_stats(struct net_device *netdev, default: WARN_ONCE(1, "Invalid E1000 stat type: %u index %d\n", stat->type, i); - break; + continue; } if (stat->sizeof_stat == sizeof(u64)) data[i] = *(u64 *)p; else data[i] = *(u32 *)p; - - stat++; } /* BUG_ON(i != E1000_STATS_LEN); */ } diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index dd112aa5cebb..39a09e18c1b7 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -521,8 +521,6 @@ void e1000_down(struct e1000_adapter *adapter) struct net_device *netdev = adapter->netdev; u32 rctl, tctl; - netif_carrier_off(netdev); - /* disable receives in the hardware */ rctl = er32(RCTL); ew32(RCTL, rctl & ~E1000_RCTL_EN); @@ -538,6 +536,15 @@ void e1000_down(struct e1000_adapter *adapter) E1000_WRITE_FLUSH(); msleep(10); + /* Set the carrier off after transmits have been disabled in the + * hardware, to avoid race conditions with e1000_watchdog() (which + * may be running concurrently to us, checking for the carrier + * bit to decide whether it should enable transmits again). Such + * a race condition would result into transmission being disabled + * in the hardware until the next IFF_DOWN+IFF_UP cycle. + */ + netif_carrier_off(netdev); + napi_disable(&adapter->napi); e1000_irq_disable(adapter); diff --git a/drivers/of/of_numa.c b/drivers/of/of_numa.c index 2db1f7a04baf..0b29ee9ee8c3 100644 --- a/drivers/of/of_numa.c +++ b/drivers/of/of_numa.c @@ -126,9 +126,14 @@ static int __init of_numa_parse_distance_map_v1(struct device_node *map) distance = of_read_number(matrix, 1); matrix++; + if ((nodea == nodeb && distance != LOCAL_DISTANCE) || + (nodea != nodeb && distance <= LOCAL_DISTANCE)) { + pr_err("Invalid distance[node%d -> node%d] = %d\n", + nodea, nodeb, distance); + return -EINVAL; + } + numa_set_distance(nodea, nodeb, distance); - pr_debug("distance[node%d -> node%d] = %d\n", - nodea, nodeb, distance); /* Set default distance of node B->A same as A->B */ if (nodeb > nodea) diff --git a/drivers/rtc/hctosys.c b/drivers/rtc/hctosys.c index e79f2a181ad2..b9ec4a16db1f 100644 --- a/drivers/rtc/hctosys.c +++ b/drivers/rtc/hctosys.c @@ -50,8 +50,10 @@ static int __init rtc_hctosys(void) tv64.tv_sec = rtc_tm_to_time64(&tm); #if BITS_PER_LONG == 32 - if (tv64.tv_sec > INT_MAX) + if (tv64.tv_sec > INT_MAX) { + err = -ERANGE; goto err_read; + } #endif err = do_settimeofday64(&tv64); diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index b6d9e3104b89..2e3a70a6b300 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -4894,7 +4894,7 @@ qla2x00_abort_isp(scsi_qla_host_t *vha) * The next call disables the board * completely. */ - ha->isp_ops->reset_adapter(vha); + qla2x00_abort_isp_cleanup(vha); vha->flags.online = 0; clear_bit(ISP_ABORT_RETRY, &vha->dpc_flags); diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index a1b01d66c9ab..bf29ad454118 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -3580,10 +3580,7 @@ qla2x00_set_idma_speed(scsi_qla_host_t *vha, uint16_t loop_id, mcp->mb[0] = MBC_PORT_PARAMS; mcp->mb[1] = loop_id; mcp->mb[2] = BIT_0; - if (IS_CNA_CAPABLE(vha->hw)) - mcp->mb[3] = port_speed & (BIT_5|BIT_4|BIT_3|BIT_2|BIT_1|BIT_0); - else - mcp->mb[3] = port_speed & (BIT_2|BIT_1|BIT_0); + mcp->mb[3] = port_speed & (BIT_5|BIT_4|BIT_3|BIT_2|BIT_1|BIT_0); mcp->mb[9] = vha->vp_idx; mcp->out_mb = MBX_9|MBX_3|MBX_2|MBX_1|MBX_0; mcp->in_mb = MBX_3|MBX_1|MBX_0; diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index 793395451982..ea6b62cece88 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -661,7 +661,7 @@ static void sc16is7xx_handle_tx(struct uart_port *port) uart_write_wakeup(port); } -static void sc16is7xx_port_irq(struct sc16is7xx_port *s, int portno) +static bool sc16is7xx_port_irq(struct sc16is7xx_port *s, int portno) { struct uart_port *port = &s->p[portno].port; @@ -670,7 +670,7 @@ static void sc16is7xx_port_irq(struct sc16is7xx_port *s, int portno) iir = sc16is7xx_port_read(port, SC16IS7XX_IIR_REG); if (iir & SC16IS7XX_IIR_NO_INT_BIT) - break; + return false; iir &= SC16IS7XX_IIR_ID_MASK; @@ -692,16 +692,23 @@ static void sc16is7xx_port_irq(struct sc16is7xx_port *s, int portno) port->line, iir); break; } - } while (1); + } while (0); + return true; } static void sc16is7xx_ist(struct kthread_work *ws) { struct sc16is7xx_port *s = to_sc16is7xx_port(ws, irq_work); - int i; - for (i = 0; i < s->devtype->nr_uart; ++i) - sc16is7xx_port_irq(s, i); + while (1) { + bool keep_polling = false; + int i; + + for (i = 0; i < s->devtype->nr_uart; ++i) + keep_polling |= sc16is7xx_port_irq(s, i); + if (!keep_polling) + break; + } } static irqreturn_t sc16is7xx_irq(int irq, void *dev_id) diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index e6429d419b80..e6c4321d695c 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -354,7 +354,7 @@ struct tty_driver *tty_find_polling_driver(char *name, int *line) mutex_lock(&tty_mutex); /* Search through the tty devices to look for a match */ list_for_each_entry(p, &tty_drivers, tty_drivers) { - if (strncmp(name, p->name, len) != 0) + if (!len || strncmp(name, p->name, len) != 0) continue; stp = str; if (*stp == ',') diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c index bf36ac9aee41..11bb9a5c700d 100644 --- a/drivers/tty/tty_ioctl.c +++ b/drivers/tty/tty_ioctl.c @@ -325,7 +325,7 @@ speed_t tty_termios_baud_rate(struct ktermios *termios) else cbaud += 15; } - return baud_table[cbaud]; + return cbaud >= n_baud_table ? 0 : baud_table[cbaud]; } EXPORT_SYMBOL(tty_termios_baud_rate); @@ -361,7 +361,7 @@ speed_t tty_termios_input_baud_rate(struct ktermios *termios) else cbaud += 15; } - return baud_table[cbaud]; + return cbaud >= n_baud_table ? 0 : baud_table[cbaud]; #else return tty_termios_baud_rate(termios); #endif diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 9e36632b6f0e..17f9ad6fdfa5 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -999,7 +999,8 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) prot_bytes = vhost32_to_cpu(vq, v_req_pi.pi_bytesin); } /* - * Set prot_iter to data_iter, and advance past any + * Set prot_iter to data_iter and truncate it to + * prot_bytes, and advance data_iter past any * preceeding prot_bytes that may be present. * * Also fix up the exp_data_len to reflect only the @@ -1008,6 +1009,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) if (prot_bytes) { exp_data_len -= prot_bytes; prot_iter = data_iter; + iov_iter_truncate(&prot_iter, prot_bytes); iov_iter_advance(&data_iter, prot_bytes); } tag = vhost64_to_cpu(vq, v_req_pi.tag); diff --git a/drivers/video/fbdev/aty/mach64_accel.c b/drivers/video/fbdev/aty/mach64_accel.c index 182bd680141f..e9dfe0e40b8b 100644 --- a/drivers/video/fbdev/aty/mach64_accel.c +++ b/drivers/video/fbdev/aty/mach64_accel.c @@ -126,7 +126,7 @@ void aty_init_engine(struct atyfb_par *par, struct fb_info *info) /* set host attributes */ wait_for_fifo(13, par); - aty_st_le32(HOST_CNTL, 0, par); + aty_st_le32(HOST_CNTL, HOST_BYTE_ALIGN, par); /* set pattern attributes */ aty_st_le32(PAT_REG0, 0, par); @@ -232,7 +232,8 @@ void atyfb_copyarea(struct fb_info *info, const struct fb_copyarea *area) rotation = rotation24bpp(dx, direction); } - wait_for_fifo(4, par); + wait_for_fifo(5, par); + aty_st_le32(DP_PIX_WIDTH, par->crtc.dp_pix_width, par); aty_st_le32(DP_SRC, FRGD_SRC_BLIT, par); aty_st_le32(SRC_Y_X, (sx << 16) | sy, par); aty_st_le32(SRC_HEIGHT1_WIDTH1, (width << 16) | area->height, par); @@ -268,7 +269,8 @@ void atyfb_fillrect(struct fb_info *info, const struct fb_fillrect *rect) rotation = rotation24bpp(dx, DST_X_LEFT_TO_RIGHT); } - wait_for_fifo(3, par); + wait_for_fifo(4, par); + aty_st_le32(DP_PIX_WIDTH, par->crtc.dp_pix_width, par); aty_st_le32(DP_FRGD_CLR, color, par); aty_st_le32(DP_SRC, BKGD_SRC_BKGD_CLR | FRGD_SRC_FRGD_CLR | MONO_SRC_ONE, @@ -283,7 +285,7 @@ void atyfb_imageblit(struct fb_info *info, const struct fb_image *image) { struct atyfb_par *par = (struct atyfb_par *) info->par; u32 src_bytes, dx = image->dx, dy = image->dy, width = image->width; - u32 pix_width_save, pix_width, host_cntl, rotation = 0, src, mix; + u32 pix_width, rotation = 0, src, mix; if (par->asleep) return; @@ -295,8 +297,7 @@ void atyfb_imageblit(struct fb_info *info, const struct fb_image *image) return; } - pix_width = pix_width_save = aty_ld_le32(DP_PIX_WIDTH, par); - host_cntl = aty_ld_le32(HOST_CNTL, par) | HOST_BYTE_ALIGN; + pix_width = par->crtc.dp_pix_width; switch (image->depth) { case 1: @@ -344,7 +345,7 @@ void atyfb_imageblit(struct fb_info *info, const struct fb_image *image) * since Rage 3D IIc we have DP_HOST_TRIPLE_EN bit * this hwaccelerated triple has an issue with not aligned data */ - if (M64_HAS(HW_TRIPLE) && image->width % 8 == 0) + if (image->depth == 1 && M64_HAS(HW_TRIPLE) && image->width % 8 == 0) pix_width |= DP_HOST_TRIPLE_EN; } @@ -369,19 +370,18 @@ void atyfb_imageblit(struct fb_info *info, const struct fb_image *image) mix = FRGD_MIX_D_XOR_S | BKGD_MIX_D; } - wait_for_fifo(6, par); - aty_st_le32(DP_WRITE_MASK, 0xFFFFFFFF, par); + wait_for_fifo(5, par); aty_st_le32(DP_PIX_WIDTH, pix_width, par); aty_st_le32(DP_MIX, mix, par); aty_st_le32(DP_SRC, src, par); - aty_st_le32(HOST_CNTL, host_cntl, par); + aty_st_le32(HOST_CNTL, HOST_BYTE_ALIGN, par); aty_st_le32(DST_CNTL, DST_Y_TOP_TO_BOTTOM | DST_X_LEFT_TO_RIGHT | rotation, par); draw_rect(dx, dy, width, image->height, par); src_bytes = (((image->width * image->depth) + 7) / 8) * image->height; /* manual triple each pixel */ - if (info->var.bits_per_pixel == 24 && !(pix_width & DP_HOST_TRIPLE_EN)) { + if (image->depth == 1 && info->var.bits_per_pixel == 24 && !(pix_width & DP_HOST_TRIPLE_EN)) { int inbit, outbit, mult24, byte_id_in_dword, width; u8 *pbitmapin = (u8*)image->data, *pbitmapout; u32 hostdword; @@ -414,7 +414,7 @@ void atyfb_imageblit(struct fb_info *info, const struct fb_image *image) } } wait_for_fifo(1, par); - aty_st_le32(HOST_DATA0, hostdword, par); + aty_st_le32(HOST_DATA0, le32_to_cpu(hostdword), par); } } else { u32 *pbitmap, dwords = (src_bytes + 3) / 4; @@ -423,8 +423,4 @@ void atyfb_imageblit(struct fb_info *info, const struct fb_image *image) aty_st_le32(HOST_DATA0, get_unaligned_le32(pbitmap), par); } } - - /* restore pix_width */ - wait_for_fifo(1, par); - aty_st_le32(DP_PIX_WIDTH, pix_width_save, par); } diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index d7b78d531e63..398a3eddb2df 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -204,6 +204,14 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl) break; if (schedule_timeout_interruptible(P9_LOCK_TIMEOUT) != 0) break; + /* + * p9_client_lock_dotl overwrites flock.client_id with the + * server message, free and reuse the client name + */ + if (flock.client_id != fid->clnt->name) { + kfree(flock.client_id); + flock.client_id = fid->clnt->name; + } } /* map 9p status to VFS status */ @@ -235,6 +243,8 @@ out_unlock: locks_lock_file_wait(filp, fl); fl->fl_type = fl_type; } + if (flock.client_id != fid->clnt->name) + kfree(flock.client_id); out: return res; } @@ -269,7 +279,7 @@ static int v9fs_file_getlock(struct file *filp, struct file_lock *fl) res = p9_client_getlock_dotl(fid, &glock); if (res < 0) - return res; + goto out; /* map 9p lock type to os lock type */ switch (glock.type) { case P9_LOCK_TYPE_RDLCK: @@ -290,7 +300,9 @@ static int v9fs_file_getlock(struct file *filp, struct file_lock *fl) fl->fl_end = glock.start + glock.length - 1; fl->fl_pid = glock.proc_id; } - kfree(glock.client_id); +out: + if (glock.client_id != fid->clnt->name) + kfree(glock.client_id); return res; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 17e143d91fa9..1b1a9e35e082 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1548,12 +1548,11 @@ out_check: } btrfs_release_path(path); - if (cur_offset <= end && cow_start == (u64)-1) { + if (cur_offset <= end && cow_start == (u64)-1) cow_start = cur_offset; - cur_offset = end; - } if (cow_start != (u64)-1) { + cur_offset = end; ret = cow_file_range(inode, locked_page, cow_start, end, end, page_started, nr_written, 1, NULL); if (ret) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index cbf512b64597..96ad2778405b 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3911,9 +3911,17 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src, goto out_unlock; if (len == 0) olen = len = src->i_size - off; - /* if we extend to eof, continue to block boundary */ - if (off + len == src->i_size) + /* + * If we extend to eof, continue to block boundary if and only if the + * destination end offset matches the destination file's size, otherwise + * we would be corrupting data by placing the eof block into the middle + * of a file. + */ + if (off + len == src->i_size) { + if (!IS_ALIGNED(len, bs) && destoff + len < inode->i_size) + goto out_unlock; len = ALIGN(src->i_size, bs) - off; + } if (len == 0) { ret = 0; diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 1f754336f801..30d9d9e7057d 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1077,8 +1077,12 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in) if (IS_ERR(realdn)) { pr_err("splice_dentry error %ld %p inode %p ino %llx.%llx\n", PTR_ERR(realdn), dn, in, ceph_vinop(in)); - dput(dn); - dn = realdn; /* note realdn contains the error */ + dn = realdn; + /* + * Caller should release 'dn' in the case of error. + * If 'req->r_dentry' is passed to this function, + * caller should leave 'req->r_dentry' untouched. + */ goto out; } else if (realdn) { dout("dn %p (%d) spliced with %p (%d) " diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c index 314b4edac72b..fea6db1ee065 100644 --- a/fs/configfs/symlink.c +++ b/fs/configfs/symlink.c @@ -64,7 +64,7 @@ static void fill_item_path(struct config_item * item, char * buffer, int length) /* back up enough to print this bus id with '/' */ length -= cur; - strncpy(buffer + length,config_item_name(p),cur); + memcpy(buffer + length, config_item_name(p), cur); *(buffer + --length) = '/'; } } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index bc727c393a89..3c3757ee11f0 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -124,6 +124,7 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, if (!is_dx_block && type == INDEX) { ext4_error_inode(inode, func, line, block, "directory leaf block found instead of index block"); + brelse(bh); return ERR_PTR(-EFSCORRUPTED); } if (!ext4_has_metadata_csum(inode->i_sb) || @@ -2842,7 +2843,9 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) list_del_init(&EXT4_I(inode)->i_orphan); mutex_unlock(&sbi->s_orphan_lock); } - } + } else + brelse(iloc.bh); + jbd_debug(4, "superblock will point to %lu\n", inode->i_ino); jbd_debug(4, "orphan inode %lu will point to %d\n", inode->i_ino, NEXT_ORPHAN(inode)); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 1da301ee78ce..9be605c63ae1 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -442,16 +442,18 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle, BUFFER_TRACE(bh, "get_write_access"); err = ext4_journal_get_write_access(handle, bh); - if (err) + if (err) { + brelse(bh); return err; + } ext4_debug("mark block bitmap %#04llx (+%llu/%u)\n", block, block - start, count2); ext4_set_bits(bh->b_data, block - start, count2); err = ext4_handle_dirty_metadata(handle, NULL, bh); + brelse(bh); if (unlikely(err)) return err; - brelse(bh); } return 0; @@ -588,7 +590,6 @@ handle_bb: bh = bclean(handle, sb, block); if (IS_ERR(bh)) { err = PTR_ERR(bh); - bh = NULL; goto out; } overhead = ext4_group_overhead_blocks(sb, group); @@ -600,9 +601,9 @@ handle_bb: ext4_mark_bitmap_end(group_data[i].blocks_count, sb->s_blocksize * 8, bh->b_data); err = ext4_handle_dirty_metadata(handle, NULL, bh); + brelse(bh); if (err) goto out; - brelse(bh); handle_ib: if (bg_flags[i] & EXT4_BG_INODE_UNINIT) @@ -617,18 +618,16 @@ handle_ib: bh = bclean(handle, sb, block); if (IS_ERR(bh)) { err = PTR_ERR(bh); - bh = NULL; goto out; } ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8, bh->b_data); err = ext4_handle_dirty_metadata(handle, NULL, bh); + brelse(bh); if (err) goto out; - brelse(bh); } - bh = NULL; /* Mark group tables in block bitmap */ for (j = 0; j < GROUP_TABLE_COUNT; j++) { @@ -659,7 +658,6 @@ handle_ib: } out: - brelse(bh); err2 = ext4_journal_stop(handle); if (err2 && !err) err = err2; @@ -846,6 +844,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, err = ext4_handle_dirty_metadata(handle, NULL, gdb_bh); if (unlikely(err)) { ext4_std_error(sb, err); + iloc.bh = NULL; goto exit_inode; } brelse(dind); @@ -897,6 +896,7 @@ static int add_new_gdb_meta_bg(struct super_block *sb, sizeof(struct buffer_head *), GFP_NOFS); if (!n_group_desc) { + brelse(gdb_bh); err = -ENOMEM; ext4_warning(sb, "not enough memory for %lu groups", gdb_num + 1); @@ -912,8 +912,6 @@ static int add_new_gdb_meta_bg(struct super_block *sb, kvfree(o_group_desc); BUFFER_TRACE(gdb_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, gdb_bh); - if (unlikely(err)) - brelse(gdb_bh); return err; } @@ -1095,8 +1093,10 @@ static void update_backups(struct super_block *sb, sector_t blk_off, char *data, backup_block, backup_block - ext4_group_first_block_no(sb, group)); BUFFER_TRACE(bh, "get_write_access"); - if ((err = ext4_journal_get_write_access(handle, bh))) + if ((err = ext4_journal_get_write_access(handle, bh))) { + brelse(bh); break; + } lock_buffer(bh); memcpy(bh->b_data, data, size); if (rest) @@ -1991,7 +1991,7 @@ retry: err = ext4_alloc_flex_bg_array(sb, n_group + 1); if (err) - return err; + goto out; err = ext4_mb_alloc_groupinfo(sb, n_group + 1); if (err) @@ -2027,6 +2027,10 @@ retry: n_blocks_count_retry = 0; free_flex_gd(flex_gd); flex_gd = NULL; + if (resize_inode) { + iput(resize_inode); + resize_inode = NULL; + } goto retry; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index f88d4804c3a8..75177eb498ed 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3897,6 +3897,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_groups_count = blocks_count; sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count, (EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb))); + if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) != + le32_to_cpu(es->s_inodes_count)) { + ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu", + le32_to_cpu(es->s_inodes_count), + ((u64)sbi->s_groups_count * sbi->s_inodes_per_group)); + ret = -EINVAL; + goto failed_mount; + } db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) / EXT4_DESC_PER_BLOCK(sb); if (ext4_has_feature_meta_bg(sb)) { @@ -3916,14 +3924,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) ret = -ENOMEM; goto failed_mount; } - if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) != - le32_to_cpu(es->s_inodes_count)) { - ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu", - le32_to_cpu(es->s_inodes_count), - ((u64)sbi->s_groups_count * sbi->s_inodes_per_group)); - ret = -EINVAL; - goto failed_mount; - } bgl_lock_init(sbi->s_blockgroup_lock); @@ -4305,6 +4305,7 @@ failed_mount6: percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); percpu_counter_destroy(&sbi->s_dirtyclusters_counter); + percpu_free_rwsem(&sbi->s_journal_flag_rwsem); failed_mount5: ext4_ext_release(sb); ext4_release_system_zone(sb); diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 38385bcb9148..22f765069655 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1221,6 +1221,8 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index, error = ext4_xattr_block_set(handle, inode, &i, &bs); } else if (error == -ENOSPC) { if (EXT4_I(inode)->i_file_acl && !bs.s.base) { + brelse(bs.bh); + bs.bh = NULL; error = ext4_xattr_block_find(inode, &i, &bs); if (error) goto cleanup; @@ -1391,6 +1393,8 @@ out: kfree(buffer); if (is) brelse(is->iloc.bh); + if (bs) + brelse(bs->bh); kfree(is); kfree(bs); diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index c94bab6103f5..b4253181b5d4 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -383,12 +383,19 @@ static void request_end(struct fuse_conn *fc, struct fuse_req *req) if (test_bit(FR_BACKGROUND, &req->flags)) { spin_lock(&fc->lock); clear_bit(FR_BACKGROUND, &req->flags); - if (fc->num_background == fc->max_background) + if (fc->num_background == fc->max_background) { fc->blocked = 0; - - /* Wake up next waiter, if any */ - if (!fc->blocked && waitqueue_active(&fc->blocked_waitq)) wake_up(&fc->blocked_waitq); + } else if (!fc->blocked) { + /* + * Wake up next waiter, if any. It's okay to use + * waitqueue_active(), as we've already synced up + * fc->blocked with waiters with the wake_up() call + * above. + */ + if (waitqueue_active(&fc->blocked_waitq)) + wake_up(&fc->blocked_waitq); + } if (fc->num_background == fc->congestion_threshold && fc->connected && fc->bdi_initialized) { @@ -1303,12 +1310,14 @@ static ssize_t fuse_dev_do_read(struct fuse_dev *fud, struct file *file, goto out_end; } list_move_tail(&req->list, &fpq->processing); - spin_unlock(&fpq->lock); + __fuse_get_request(req); set_bit(FR_SENT, &req->flags); + spin_unlock(&fpq->lock); /* matches barrier in request_wait_answer() */ smp_mb__after_atomic(); if (test_bit(FR_INTERRUPTED, &req->flags)) queue_interrupt(fiq, req); + fuse_put_request(fc, req); return reqsize; @@ -1706,8 +1715,10 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, req->in.args[1].size = total_len; err = fuse_request_send_notify_reply(fc, req, outarg->notify_unique); - if (err) + if (err) { fuse_retrieve_end(fc, req); + fuse_put_request(fc, req); + } return err; } @@ -1866,16 +1877,20 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud, /* Is it an interrupt reply? */ if (req->intr_unique == oh.unique) { + __fuse_get_request(req); spin_unlock(&fpq->lock); err = -EINVAL; - if (nbytes != sizeof(struct fuse_out_header)) + if (nbytes != sizeof(struct fuse_out_header)) { + fuse_put_request(fc, req); goto err_finish; + } if (oh.error == -ENOSYS) fc->no_interrupt = 1; else if (oh.error == -EAGAIN) queue_interrupt(&fc->iq, req); + fuse_put_request(fc, req); fuse_copy_finish(cs); return nbytes; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 4408abf6675b..1cd46e667e3d 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2900,10 +2900,12 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter) } if (io->async) { + bool blocking = io->blocking; + fuse_aio_complete(io, ret < 0 ? ret : 0, -1); /* we have a non-extending, async request, so return */ - if (!io->blocking) + if (!blocking) return -EIOCBQUEUED; wait_for_completion(&wait); diff --git a/fs/namespace.c b/fs/namespace.c index 0a9e766b4087..41f906a6f5d9 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1599,8 +1599,13 @@ static int do_umount(struct mount *mnt, int flags) namespace_lock(); lock_mount_hash(); - event++; + /* Recheck MNT_LOCKED with the locks held */ + retval = -EINVAL; + if (mnt->mnt.mnt_flags & MNT_LOCKED) + goto out; + + event++; if (flags & MNT_DETACH) { if (!list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE); @@ -1614,6 +1619,7 @@ static int do_umount(struct mount *mnt, int flags) retval = 0; } } +out: unlock_mount_hash(); namespace_unlock(); return retval; @@ -1704,7 +1710,7 @@ SYSCALL_DEFINE2(umount, char __user *, name, int, flags) goto dput_and_out; if (!check_mnt(mnt)) goto dput_and_out; - if (mnt->mnt.mnt_flags & MNT_LOCKED) + if (mnt->mnt.mnt_flags & MNT_LOCKED) /* Check optimistically */ goto dput_and_out; retval = -EPERM; if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN)) @@ -1782,8 +1788,14 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, for (s = r; s; s = next_mnt(s, r)) { if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(s)) { - s = skip_mnt_tree(s); - continue; + if (s->mnt.mnt_flags & MNT_LOCKED) { + /* Both unbindable and locked. */ + q = ERR_PTR(-EPERM); + goto out; + } else { + s = skip_mnt_tree(s); + continue; + } } if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(s->mnt.mnt_root)) { @@ -1836,7 +1848,7 @@ void drop_collected_mounts(struct vfsmount *mnt) { namespace_lock(); lock_mount_hash(); - umount_tree(real_mount(mnt), UMOUNT_SYNC); + umount_tree(real_mount(mnt), 0); unlock_mount_hash(); namespace_unlock(); } diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index e9495516527d..66985a6a7047 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1016,6 +1016,9 @@ nfsd4_verify_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, { __be32 status; + if (!cstate->save_fh.fh_dentry) + return nfserr_nofilehandle; + status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->save_fh, src_stateid, RD_STATE, src, NULL); if (status) { diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 3ecb9f337b7d..20e610419501 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -1896,8 +1896,7 @@ static int ocfs2_dir_foreach_blk_el(struct inode *inode, /* On error, skip the f_pos to the next block. */ ctx->pos = (ctx->pos | (sb->s_blocksize - 1)) + 1; - brelse(bh); - continue; + break; } if (le64_to_cpu(de->inode)) { unsigned char d_type = DT_UNKNOWN; diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 1816c5e26581..a8a574897d3c 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -77,7 +77,13 @@ struct ceph_options { #define CEPH_MSG_MAX_FRONT_LEN (16*1024*1024) #define CEPH_MSG_MAX_MIDDLE_LEN (16*1024*1024) -#define CEPH_MSG_MAX_DATA_LEN (16*1024*1024) + +/* + * Handle the largest possible rbd object in one message. + * There is no limit on the size of cephfs objects, but it has to obey + * rsize and wsize mount options anyway. + */ +#define CEPH_MSG_MAX_DATA_LEN (32*1024*1024) #define CEPH_AUTH_NAME_DEFAULT "guest" diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 48c76d612d40..b699d59d0f4f 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -109,6 +109,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz); pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr); int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep); +void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, + unsigned long *start, unsigned long *end); struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, int write); struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, @@ -131,6 +133,18 @@ static inline unsigned long hugetlb_total_pages(void) return 0; } +static inline int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, + pte_t *ptep) +{ + return 0; +} + +static inline void adjust_range_if_pmd_sharing_possible( + struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) +{ +} + #define follow_hugetlb_page(m,v,p,vs,a,b,i,w) ({ BUG(); 0; }) #define follow_huge_addr(mm, addr, write) ERR_PTR(-EINVAL) #define copy_hugetlb_page_range(src, dst, vma) ({ BUG(); 0; }) diff --git a/include/linux/i8253.h b/include/linux/i8253.h index e6bb36a97519..8336b2f6f834 100644 --- a/include/linux/i8253.h +++ b/include/linux/i8253.h @@ -21,6 +21,7 @@ #define PIT_LATCH ((PIT_TICK_RATE + HZ/2) / HZ) extern raw_spinlock_t i8253_lock; +extern bool i8253_clear_counter_on_shutdown; extern struct clock_event_device i8253_clockevent; extern void clockevent_i8253_init(bool oneshot); diff --git a/include/linux/mm.h b/include/linux/mm.h index 493d07931ea5..11a5a46ce72b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2187,6 +2187,12 @@ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm, return vma; } +static inline bool range_in_vma(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + return (vma && vma->vm_start <= start && end <= vma->vm_end); +} + #ifdef CONFIG_MMU pgprot_t vm_get_page_prot(unsigned long vm_flags); void vma_set_page_prot(struct vm_area_struct *vma); diff --git a/lib/ubsan.c b/lib/ubsan.c index 50d1d5c25deb..60e108c5c173 100644 --- a/lib/ubsan.c +++ b/lib/ubsan.c @@ -451,8 +451,7 @@ void __ubsan_handle_shift_out_of_bounds(struct shift_out_of_bounds_data *data, EXPORT_SYMBOL(__ubsan_handle_shift_out_of_bounds); -void __noreturn -__ubsan_handle_builtin_unreachable(struct unreachable_data *data) +void __ubsan_handle_builtin_unreachable(struct unreachable_data *data) { unsigned long flags; diff --git a/mm/gup.c b/mm/gup.c index be4ccddac26f..d71da7216c6e 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1122,8 +1122,6 @@ int __mm_populate(unsigned long start, unsigned long len, int ignore_errors) int locked = 0; long ret = 0; - VM_BUG_ON(start & ~PAGE_MASK); - VM_BUG_ON(len != PAGE_ALIGN(len)); end = start + len; for (nstart = start; nstart < end; nstart = nend) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 9c566e4b06ce..5e3a4db36310 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3220,7 +3220,7 @@ static int is_hugetlb_entry_hwpoisoned(pte_t pte) int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma) { - pte_t *src_pte, *dst_pte, entry; + pte_t *src_pte, *dst_pte, entry, dst_entry; struct page *ptepage; unsigned long addr; int cow; @@ -3248,15 +3248,30 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, break; } - /* If the pagetables are shared don't copy or take references */ - if (dst_pte == src_pte) + /* + * If the pagetables are shared don't copy or take references. + * dst_pte == src_pte is the common case of src/dest sharing. + * + * However, src could have 'unshared' and dst shares with + * another vma. If dst_pte !none, this implies sharing. + * Check here before taking page table lock, and once again + * after taking the lock below. + */ + dst_entry = huge_ptep_get(dst_pte); + if ((dst_pte == src_pte) || !huge_pte_none(dst_entry)) continue; dst_ptl = huge_pte_lock(h, dst, dst_pte); src_ptl = huge_pte_lockptr(h, src, src_pte); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); entry = huge_ptep_get(src_pte); - if (huge_pte_none(entry)) { /* skip none entry */ + dst_entry = huge_ptep_get(dst_pte); + if (huge_pte_none(entry) || !huge_pte_none(dst_entry)) { + /* + * Skip if src entry none. Also, skip in the + * unlikely case dst entry !none as this implies + * sharing with another vma. + */ ; } else if (unlikely(is_hugetlb_entry_migration(entry) || is_hugetlb_entry_hwpoisoned(entry))) { @@ -4318,12 +4333,40 @@ static bool vma_shareable(struct vm_area_struct *vma, unsigned long addr) /* * check on proper vm_flags and page table alignment */ - if (vma->vm_flags & VM_MAYSHARE && - vma->vm_start <= base && end <= vma->vm_end) + if (vma->vm_flags & VM_MAYSHARE && range_in_vma(vma, base, end)) return true; return false; } +/* + * Determine if start,end range within vma could be mapped by shared pmd. + * If yes, adjust start and end to cover range associated with possible + * shared pmd mappings. + */ +void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) +{ + unsigned long check_addr = *start; + + if (!(vma->vm_flags & VM_MAYSHARE)) + return; + + for (check_addr = *start; check_addr < *end; check_addr += PUD_SIZE) { + unsigned long a_start = check_addr & PUD_MASK; + unsigned long a_end = a_start + PUD_SIZE; + + /* + * If sharing is possible, adjust start/end if necessary. + */ + if (range_in_vma(vma, a_start, a_end)) { + if (a_start < *start) + *start = a_start; + if (a_end > *end) + *end = a_end; + } + } +} + /* * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc() * and returns the corresponding pte. While this is not necessary for the @@ -4420,6 +4463,11 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) { return 0; } + +void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) +{ +} #define want_pmd_share() (0) #endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 69c4a0c92ebb..e21d9b44247b 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2027,8 +2027,36 @@ retry_cpuset: nmask = policy_nodemask(gfp, pol); if (!nmask || node_isset(hpage_node, *nmask)) { mpol_cond_put(pol); - page = __alloc_pages_node(hpage_node, - gfp | __GFP_THISNODE, order); + /* + * We cannot invoke reclaim if __GFP_THISNODE + * is set. Invoking reclaim with + * __GFP_THISNODE set, would cause THP + * allocations to trigger heavy swapping + * despite there may be tons of free memory + * (including potentially plenty of THP + * already available in the buddy) on all the + * other NUMA nodes. + * + * At most we could invoke compaction when + * __GFP_THISNODE is set (but we would need to + * refrain from invoking reclaim even if + * compaction returned COMPACT_SKIPPED because + * there wasn't not enough memory to succeed + * compaction). For now just avoid + * __GFP_THISNODE instead of limiting the + * allocation path to a strict and single + * compaction invocation. + * + * Supposedly if direct reclaim was enabled by + * the caller, the app prefers THP regardless + * of the node it comes from so this would be + * more desiderable behavior than only + * providing THP originated from the local + * node in such case. + */ + if (!(gfp & __GFP_DIRECT_RECLAIM)) + gfp |= __GFP_THISNODE; + page = __alloc_pages_node(hpage_node, gfp, order); goto out; } } diff --git a/mm/mmap.c b/mm/mmap.c index aa97074a4a99..283755645d17 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2876,21 +2876,15 @@ static inline void verify_mm_writelocked(struct mm_struct *mm) * anonymous maps. eventually we may be able to do some * brk-specific accounting here. */ -static int do_brk(unsigned long addr, unsigned long request) +static int do_brk(unsigned long addr, unsigned long len) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; - unsigned long flags, len; + unsigned long flags; struct rb_node **rb_link, *rb_parent; pgoff_t pgoff = addr >> PAGE_SHIFT; int error; - len = PAGE_ALIGN(request); - if (len < request) - return -ENOMEM; - if (!len) - return 0; - flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags; error = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED); @@ -2959,12 +2953,19 @@ out: return 0; } -int vm_brk(unsigned long addr, unsigned long len) +int vm_brk(unsigned long addr, unsigned long request) { struct mm_struct *mm = current->mm; + unsigned long len; int ret; bool populate; + len = PAGE_ALIGN(request); + if (len < request) + return -ENOMEM; + if (!len) + return 0; + if (down_write_killable(&mm->mmap_sem)) return -EINTR; diff --git a/mm/rmap.c b/mm/rmap.c index 94488b0362f8..a7276d8c96f3 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1476,6 +1476,9 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, pte_t pteval; spinlock_t *ptl; int ret = SWAP_AGAIN; + unsigned long sh_address; + bool pmd_sharing_possible = false; + unsigned long spmd_start, spmd_end; struct rmap_private *rp = arg; enum ttu_flags flags = rp->flags; @@ -1491,6 +1494,32 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, goto out; } + /* + * Only use the range_start/end mmu notifiers if huge pmd sharing + * is possible. In the normal case, mmu_notifier_invalidate_page + * is sufficient as we only unmap a page. However, if we unshare + * a pmd, we will unmap a PUD_SIZE range. + */ + if (PageHuge(page)) { + spmd_start = address; + spmd_end = spmd_start + vma_mmu_pagesize(vma); + + /* + * Check if pmd sharing is possible. If possible, we could + * unmap a PUD_SIZE range. spmd_start/spmd_end will be + * modified if sharing is possible. + */ + adjust_range_if_pmd_sharing_possible(vma, &spmd_start, + &spmd_end); + if (spmd_end - spmd_start != vma_mmu_pagesize(vma)) { + sh_address = address; + + pmd_sharing_possible = true; + mmu_notifier_invalidate_range_start(vma->vm_mm, + spmd_start, spmd_end); + } + } + pte = page_check_address(page, mm, address, &ptl, PageTransCompound(page)); if (!pte) @@ -1524,6 +1553,30 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, } } + /* + * Call huge_pmd_unshare to potentially unshare a huge pmd. Pass + * sh_address as it will be modified if unsharing is successful. + */ + if (PageHuge(page) && huge_pmd_unshare(mm, &sh_address, pte)) { + /* + * huge_pmd_unshare unmapped an entire PMD page. There is + * no way of knowing exactly which PMDs may be cached for + * this mm, so flush them all. spmd_start/spmd_end cover + * this PUD_SIZE range. + */ + flush_cache_range(vma, spmd_start, spmd_end); + flush_tlb_range(vma, spmd_start, spmd_end); + + /* + * The ref count of the PMD page was dropped which is part + * of the way map counting is done for shared PMDs. When + * there is no other sharing, huge_pmd_unshare returns false + * and we will unmap the actual page and drop map count + * to zero. + */ + goto out_unmap; + } + /* Nuke the page table entry. */ flush_cache_page(vma, address, page_to_pfn(page)); if (should_defer_flush(mm, flags)) { @@ -1621,6 +1674,9 @@ out_unmap: if (ret != SWAP_FAIL && ret != SWAP_MLOCK && !(flags & TTU_MUNLOCK)) mmu_notifier_invalidate_page(mm, address); out: + if (pmd_sharing_possible) + mmu_notifier_invalidate_range_end(vma->vm_mm, + spmd_start, spmd_end); return ret; } diff --git a/net/9p/protocol.c b/net/9p/protocol.c index 16d287565987..145f80518064 100644 --- a/net/9p/protocol.c +++ b/net/9p/protocol.c @@ -46,10 +46,15 @@ p9pdu_writef(struct p9_fcall *pdu, int proto_version, const char *fmt, ...); void p9stat_free(struct p9_wstat *stbuf) { kfree(stbuf->name); + stbuf->name = NULL; kfree(stbuf->uid); + stbuf->uid = NULL; kfree(stbuf->gid); + stbuf->gid = NULL; kfree(stbuf->muid); + stbuf->muid = NULL; kfree(stbuf->extension); + stbuf->extension = NULL; } EXPORT_SYMBOL(p9stat_free); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index db3586ba1211..19b3f4fbea52 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -918,19 +918,22 @@ static unsigned int early_drop_list(struct net *net, return drops; } -static noinline int early_drop(struct net *net, unsigned int _hash) +static noinline int early_drop(struct net *net, unsigned int hash) { - unsigned int i; + unsigned int i, bucket; for (i = 0; i < NF_CT_EVICTION_RANGE; i++) { struct hlist_nulls_head *ct_hash; - unsigned int hash, hsize, drops; + unsigned int hsize, drops; rcu_read_lock(); nf_conntrack_get_ht(&ct_hash, &hsize); - hash = reciprocal_scale(_hash++, hsize); + if (!i) + bucket = reciprocal_scale(hash, hsize); + else + bucket = (bucket + 1) % hsize; - drops = early_drop_list(net, &ct_hash[hash]); + drops = early_drop_list(net, &ct_hash[bucket]); rcu_read_unlock(); if (drops) { diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 7f1071e103ca..1b38fc486351 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -639,11 +639,10 @@ void xdr_truncate_encode(struct xdr_stream *xdr, size_t len) WARN_ON_ONCE(xdr->iov); return; } - if (fraglen) { + if (fraglen) xdr->end = head->iov_base + head->iov_len; - xdr->page_ptr--; - } /* (otherwise assume xdr->end is already set) */ + xdr->page_ptr--; head->iov_len = len; buf->len = len; xdr->p = head->iov_base + head->iov_len; diff --git a/tools/testing/selftests/powerpc/tm/tm-tmspr.c b/tools/testing/selftests/powerpc/tm/tm-tmspr.c index 2bda81c7bf23..df1d7d4b1c89 100644 --- a/tools/testing/selftests/powerpc/tm/tm-tmspr.c +++ b/tools/testing/selftests/powerpc/tm/tm-tmspr.c @@ -98,7 +98,7 @@ void texasr(void *in) int test_tmspr() { - pthread_t thread; + pthread_t *thread; int thread_num; unsigned long i; @@ -107,21 +107,28 @@ int test_tmspr() /* To cause some context switching */ thread_num = 10 * sysconf(_SC_NPROCESSORS_ONLN); + thread = malloc(thread_num * sizeof(pthread_t)); + if (thread == NULL) + return EXIT_FAILURE; + /* Test TFIAR and TFHAR */ - for (i = 0 ; i < thread_num ; i += 2){ - if (pthread_create(&thread, NULL, (void*)tfiar_tfhar, (void *)i)) + for (i = 0; i < thread_num; i += 2) { + if (pthread_create(&thread[i], NULL, (void *)tfiar_tfhar, + (void *)i)) return EXIT_FAILURE; } - if (pthread_join(thread, NULL) != 0) - return EXIT_FAILURE; - /* Test TEXASR */ - for (i = 0 ; i < thread_num ; i++){ - if (pthread_create(&thread, NULL, (void*)texasr, (void *)i)) + for (i = 1; i < thread_num; i += 2) { + if (pthread_create(&thread[i], NULL, (void *)texasr, (void *)i)) return EXIT_FAILURE; } - if (pthread_join(thread, NULL) != 0) - return EXIT_FAILURE; + + for (i = 0; i < thread_num; i++) { + if (pthread_join(thread[i], NULL) != 0) + return EXIT_FAILURE; + } + + free(thread); if (passed) return 0;