diff options
114 files changed, 1218 insertions, 556 deletions
diff --git a/Documentation/x86/pat.txt b/Documentation/x86/pat.txt index 54944c71b819..2a4ee6302122 100644 --- a/Documentation/x86/pat.txt +++ b/Documentation/x86/pat.txt @@ -196,3 +196,35 @@ Another, more verbose way of getting PAT related debug messages is with "debugpat" boot parameter. With this parameter, various debug messages are printed to dmesg log. +PAT Initialization +------------------ + +The following table describes how PAT is initialized under various +configurations. The PAT MSR must be updated by Linux in order to support WC +and WT attributes. Otherwise, the PAT MSR has the value programmed in it +by the firmware. Note, Xen enables WC attribute in the PAT MSR for guests. + + MTRR PAT Call Sequence PAT State PAT MSR + ========================================================= + E E MTRR -> PAT init Enabled OS + E D MTRR -> PAT init Disabled - + D E MTRR -> PAT disable Disabled BIOS + D D MTRR -> PAT disable Disabled - + - np/E PAT -> PAT disable Disabled BIOS + - np/D PAT -> PAT disable Disabled - + E !P/E MTRR -> PAT init Disabled BIOS + D !P/E MTRR -> PAT disable Disabled BIOS + !M !P/E MTRR stub -> PAT disable Disabled BIOS + + Legend + ------------------------------------------------ + E Feature enabled in CPU + D Feature disabled/unsupported in CPU + np "nopat" boot option specified + !P CONFIG_X86_PAT option unset + !M CONFIG_MTRR option unset + Enabled PAT state set to enabled + Disabled PAT state set to disabled + OS PAT initializes PAT MSR with OS setting + BIOS PAT keeps PAT MSR with BIOS setting + @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 4 -SUBLEVEL = 16 +SUBLEVEL = 18 EXTRAVERSION = NAME = Blurry Fish Butt diff --git a/arch/arc/Makefile b/arch/arc/Makefile index aeb19021099e..209d8451e23d 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -48,8 +48,6 @@ endif endif -cflags-$(CONFIG_ARC_DW2_UNWIND) += -fasynchronous-unwind-tables - # By default gcc 4.8 generates dwarf4 which kernel unwinder can't grok ifeq ($(atleast_gcc48),y) cflags-$(CONFIG_ARC_DW2_UNWIND) += -gdwarf-2 diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c index 001de4ce711e..11b50959f20e 100644 --- a/arch/arc/kernel/stacktrace.c +++ b/arch/arc/kernel/stacktrace.c @@ -142,7 +142,7 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, * prelogue is setup (callee regs saved and then fp set and not other * way around */ - pr_warn("CONFIG_ARC_DW2_UNWIND needs to be enabled\n"); + pr_warn_once("CONFIG_ARC_DW2_UNWIND needs to be enabled\n"); return 0; #endif diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c index 087acb569b63..5f221acd21ae 100644 --- a/arch/arm/kernel/sys_oabi-compat.c +++ b/arch/arm/kernel/sys_oabi-compat.c @@ -279,8 +279,12 @@ asmlinkage long sys_oabi_epoll_wait(int epfd, mm_segment_t fs; long ret, err, i; - if (maxevents <= 0 || maxevents > (INT_MAX/sizeof(struct epoll_event))) + if (maxevents <= 0 || + maxevents > (INT_MAX/sizeof(*kbuf)) || + maxevents > (INT_MAX/sizeof(*events))) return -EINVAL; + if (!access_ok(VERIFY_WRITE, events, sizeof(*events) * maxevents)) + return -EFAULT; kbuf = kmalloc(sizeof(*kbuf) * maxevents, GFP_KERNEL); if (!kbuf) return -ENOMEM; @@ -317,6 +321,8 @@ asmlinkage long sys_oabi_semtimedop(int semid, if (nsops < 1 || nsops > SEMOPM) return -EINVAL; + if (!access_ok(VERIFY_READ, tsops, sizeof(*tsops) * nsops)) + return -EFAULT; sops = kmalloc(sizeof(*sops) * nsops, GFP_KERNEL); if (!sops) return -ENOMEM; diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index 5a69eb48d0a8..ee93d5fe61d7 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -344,7 +344,7 @@ EXPORT(sysn32_call_table) PTR sys_ni_syscall /* available, was setaltroot */ PTR sys_add_key PTR sys_request_key - PTR sys_keyctl /* 6245 */ + PTR compat_sys_keyctl /* 6245 */ PTR sys_set_thread_area PTR sys_inotify_init PTR sys_inotify_add_watch diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index e4b6d7c97822..b77052ec6fb2 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -500,7 +500,7 @@ EXPORT(sys32_call_table) PTR sys_ni_syscall /* available, was setaltroot */ PTR sys_add_key /* 4280 */ PTR sys_request_key - PTR sys_keyctl + PTR compat_sys_keyctl PTR sys_set_thread_area PTR sys_inotify_init PTR sys_inotify_add_watch /* 4285 */ diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index b1f0a90f933b..42570d8fb265 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -2070,13 +2070,6 @@ void s390_reset_system(void (*fn_pre)(void), S390_lowcore.program_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) s390_base_pgm_handler; - /* - * Clear subchannel ID and number to signal new kernel that no CCW or - * SCSI IPL has been done (for kexec and kdump) - */ - S390_lowcore.subchannel_id = 0; - S390_lowcore.subchannel_nr = 0; - /* Store status at absolute zero */ store_status(); diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index f17705e1332c..e62f4401e792 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -294,7 +294,7 @@ # 285 sys_setaltroot 286 i386 add_key sys_add_key 287 i386 request_key sys_request_key -288 i386 keyctl sys_keyctl +288 i386 keyctl sys_keyctl compat_sys_keyctl 289 i386 ioprio_set sys_ioprio_set 290 i386 ioprio_get sys_ioprio_get 291 i386 inotify_init sys_inotify_init diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h index b94f6f64e23d..dbff1456d215 100644 --- a/arch/x86/include/asm/mtrr.h +++ b/arch/x86/include/asm/mtrr.h @@ -24,6 +24,7 @@ #define _ASM_X86_MTRR_H #include <uapi/asm/mtrr.h> +#include <asm/pat.h> /* @@ -83,9 +84,12 @@ static inline int mtrr_trim_uncached_memory(unsigned long end_pfn) static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi) { } +static inline void mtrr_bp_init(void) +{ + pat_disable("MTRRs disabled, skipping PAT initialization too."); +} #define mtrr_ap_init() do {} while (0) -#define mtrr_bp_init() do {} while (0) #define set_mtrr_aps_delayed_init() do {} while (0) #define mtrr_aps_init() do {} while (0) #define mtrr_bp_restore() do {} while (0) diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h index ca6c228d5e62..0b1ff4c1c14e 100644 --- a/arch/x86/include/asm/pat.h +++ b/arch/x86/include/asm/pat.h @@ -5,8 +5,8 @@ #include <asm/pgtable_types.h> bool pat_enabled(void); +void pat_disable(const char *reason); extern void pat_init(void); -void pat_init_cache_modes(u64); extern int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm); diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 7a6bed5c08bc..baad72e4c100 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -76,6 +76,8 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, u8 ret_flags; version = src->version; + /* Make the latest version visible */ + smp_rmb(); offset = pvclock_get_nsec_offset(src); ret = src->system_time + offset; diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 3b533cf37c74..b5624fafa44a 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -444,11 +444,24 @@ static void __init print_mtrr_state(void) pr_debug("TOM2: %016llx aka %lldM\n", mtrr_tom2, mtrr_tom2>>20); } +/* PAT setup for BP. We need to go through sync steps here */ +void __init mtrr_bp_pat_init(void) +{ + unsigned long flags; + + local_irq_save(flags); + prepare_set(); + + pat_init(); + + post_set(); + local_irq_restore(flags); +} + /* Grab all of the MTRR state for this CPU into *state */ bool __init get_mtrr_state(void) { struct mtrr_var_range *vrs; - unsigned long flags; unsigned lo, dummy; unsigned int i; @@ -481,15 +494,6 @@ bool __init get_mtrr_state(void) mtrr_state_set = 1; - /* PAT setup for BP. We need to go through sync steps here */ - local_irq_save(flags); - prepare_set(); - - pat_init(); - - post_set(); - local_irq_restore(flags); - return !!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED); } diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index f891b4750f04..fa77ac8291f0 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -752,6 +752,9 @@ void __init mtrr_bp_init(void) /* BIOS may override */ __mtrr_enabled = get_mtrr_state(); + if (mtrr_enabled()) + mtrr_bp_pat_init(); + if (mtrr_cleanup(phys_addr)) { changed_by_mtrr_cleanup = 1; mtrr_if->set_all(); @@ -759,8 +762,16 @@ void __init mtrr_bp_init(void) } } - if (!mtrr_enabled()) + if (!mtrr_enabled()) { pr_info("MTRR: Disabled\n"); + + /* + * PAT initialization relies on MTRR's rendezvous handler. + * Skip PAT init until the handler can initialize both + * features independently. + */ + pat_disable("MTRRs disabled, skipping PAT initialization too."); + } } void mtrr_ap_init(void) diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h index 951884dcc433..6c7ced07d16d 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.h +++ b/arch/x86/kernel/cpu/mtrr/mtrr.h @@ -52,6 +52,7 @@ void set_mtrr_prepare_save(struct set_mtrr_context *ctxt); void fill_mtrr_var_range(unsigned int index, u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi); bool get_mtrr_state(void); +void mtrr_bp_pat_init(void); extern void set_mtrr_ops(const struct mtrr_ops *ops); diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 7abb2b88572e..1e7de3cefc9c 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -1110,6 +1110,13 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit) void *at; u64 pebs_status; + /* + * fmt0 does not have a status bitfield (does not use + * perf_record_nhm format) + */ + if (x86_pmu.intel_cap.pebs_format < 1) + return base; + if (base == NULL) return NULL; @@ -1195,7 +1202,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) if (!event->attr.precise_ip) return; - n = (top - at) / x86_pmu.pebs_record_size; + n = top - at; if (n <= 0) return; diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index db9a675e751b..9fdf1d330727 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -11,7 +11,11 @@ #include <linux/pci.h> #include <linux/acpi.h> +#include <linux/delay.h> +#include <linux/dmi.h> #include <linux/pci_ids.h> +#include <linux/bcma/bcma.h> +#include <linux/bcma/bcma_regs.h> #include <drm/i915_drm.h> #include <asm/pci-direct.h> #include <asm/dma.h> @@ -21,6 +25,9 @@ #include <asm/iommu.h> #include <asm/gart.h> #include <asm/irq_remapping.h> +#include <asm/early_ioremap.h> + +#define dev_err(msg) pr_err("pci 0000:%02x:%02x.%d: %s", bus, slot, func, msg) static void __init fix_hypertransport_config(int num, int slot, int func) { @@ -76,6 +83,13 @@ static void __init nvidia_bugs(int num, int slot, int func) #ifdef CONFIG_ACPI #ifdef CONFIG_X86_IO_APIC /* + * Only applies to Nvidia root ports (bus 0) and not to + * Nvidia graphics cards with PCI ports on secondary buses. + */ + if (num) + return; + + /* * All timer overrides on Nvidia are * wrong unless HPET is enabled. * Unfortunately that's not true on many Asus boards. @@ -589,6 +603,61 @@ static void __init force_disable_hpet(int num, int slot, int func) #endif } +#define BCM4331_MMIO_SIZE 16384 +#define BCM4331_PM_CAP 0x40 +#define bcma_aread32(reg) ioread32(mmio + 1 * BCMA_CORE_SIZE + reg) +#define bcma_awrite32(reg, val) iowrite32(val, mmio + 1 * BCMA_CORE_SIZE + reg) + +static void __init apple_airport_reset(int bus, int slot, int func) +{ + void __iomem *mmio; + u16 pmcsr; + u64 addr; + int i; + + if (!dmi_match(DMI_SYS_VENDOR, "Apple Inc.")) + return; + + /* Card may have been put into PCI_D3hot by grub quirk */ + pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL); + + if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) { + pmcsr &= ~PCI_PM_CTRL_STATE_MASK; + write_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL, pmcsr); + mdelay(10); + + pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL); + if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) { + dev_err("Cannot power up Apple AirPort card\n"); + return; + } + } + + addr = read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_0); + addr |= (u64)read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_1) << 32; + addr &= PCI_BASE_ADDRESS_MEM_MASK; + + mmio = early_ioremap(addr, BCM4331_MMIO_SIZE); + if (!mmio) { + dev_err("Cannot iomap Apple AirPort card\n"); + return; + } + + pr_info("Resetting Apple AirPort card (left enabled by EFI)\n"); + + for (i = 0; bcma_aread32(BCMA_RESET_ST) && i < 30; i++) + udelay(10); + + bcma_awrite32(BCMA_RESET_CTL, BCMA_RESET_CTL_RESET); + bcma_aread32(BCMA_RESET_CTL); + udelay(1); + + bcma_awrite32(BCMA_RESET_CTL, 0); + bcma_aread32(BCMA_RESET_CTL); + udelay(10); + + early_iounmap(mmio, BCM4331_MMIO_SIZE); +} #define QFLAG_APPLY_ONCE 0x1 #define QFLAG_APPLIED 0x2 @@ -602,12 +671,6 @@ struct chipset { void (*f)(int num, int slot, int func); }; -/* - * Only works for devices on the root bus. If you add any devices - * not on bus 0 readd another loop level in early_quirks(). But - * be careful because at least the Nvidia quirk here relies on - * only matching on bus 0. - */ static struct chipset early_qrk[] __initdata = { { PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, nvidia_bugs }, @@ -637,9 +700,13 @@ static struct chipset early_qrk[] __initdata = { */ { PCI_VENDOR_ID_INTEL, 0x0f00, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, + { PCI_VENDOR_ID_BROADCOM, 0x4331, + PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset}, {} }; +static void __init early_pci_scan_bus(int bus); + /** * check_dev_quirk - apply early quirks to a given PCI device * @num: bus number @@ -648,7 +715,7 @@ static struct chipset early_qrk[] __initdata = { * * Check the vendor & device ID against the early quirks table. * - * If the device is single function, let early_quirks() know so we don't + * If the device is single function, let early_pci_scan_bus() know so we don't * poke at this device again. */ static int __init check_dev_quirk(int num, int slot, int func) @@ -657,6 +724,7 @@ static int __init check_dev_quirk(int num, int slot, int func) u16 vendor; u16 device; u8 type; + u8 sec; int i; class = read_pci_config_16(num, slot, func, PCI_CLASS_DEVICE); @@ -684,25 +752,36 @@ static int __init check_dev_quirk(int num, int slot, int func) type = read_pci_config_byte(num, slot, func, PCI_HEADER_TYPE); + + if ((type & 0x7f) == PCI_HEADER_TYPE_BRIDGE) { + sec = read_pci_config_byte(num, slot, func, PCI_SECONDARY_BUS); + if (sec > num) + early_pci_scan_bus(sec); + } + if (!(type & 0x80)) return -1; return 0; } -void __init early_quirks(void) +static void __init early_pci_scan_bus(int bus) { int slot, func; - if (!early_pci_allowed()) - return; - /* Poor man's PCI discovery */ - /* Only scan the root bus */ for (slot = 0; slot < 32; slot++) for (func = 0; func < 8; func++) { /* Only probe function 0 on single fn devices */ - if (check_dev_quirk(0, slot, func)) + if (check_dev_quirk(bus, slot, func)) break; } } + +void __init early_quirks(void) +{ + if (!early_pci_allowed()) + return; + + early_pci_scan_bus(0); +} diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 2f355d229a58..bf0ce75735b0 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -66,6 +66,8 @@ u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src) do { version = __pvclock_read_cycles(src, &ret, &flags); + /* Make sure that the version double-check is last. */ + smp_rmb(); } while ((src->version & 1) || version != src->version); return flags & valid_flags; @@ -80,6 +82,8 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) do { version = __pvclock_read_cycles(src, &ret, &flags); + /* Make sure that the version double-check is last. */ + smp_rmb(); } while ((src->version & 1) || version != src->version); if (unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) { diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 844b06d67df4..307f60ecfc6d 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -94,18 +94,6 @@ static unsigned long mmap_base(unsigned long rnd) } /* - * Bottom-up (legacy) layout on X86_32 did not support randomization, X86_64 - * does, but not when emulating X86_32 - */ -static unsigned long mmap_legacy_base(unsigned long rnd) -{ - if (mmap_is_ia32()) - return TASK_UNMAPPED_BASE; - else - return TASK_UNMAPPED_BASE + rnd; -} - -/* * This function, called very early during the creation of a new * process VM image, sets up which VM layout function to use: */ @@ -116,7 +104,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (current->flags & PF_RANDOMIZE) random_factor = arch_mmap_rnd(); - mm->mmap_legacy_base = mmap_legacy_base(random_factor); + mm->mmap_legacy_base = TASK_UNMAPPED_BASE + random_factor; if (mmap_is_legacy()) { mm->mmap_base = mm->mmap_legacy_base; diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 188e3e07eeeb..6ad687d104ca 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -39,11 +39,22 @@ static bool boot_cpu_done; static int __read_mostly __pat_enabled = IS_ENABLED(CONFIG_X86_PAT); +static void init_cache_modes(void); -static inline void pat_disable(const char *reason) +void pat_disable(const char *reason) { + if (!__pat_enabled) + return; + + if (boot_cpu_done) { + WARN_ONCE(1, "x86/PAT: PAT cannot be disabled after initialization\n"); + return; + } + __pat_enabled = 0; pr_info("x86/PAT: %s\n", reason); + + init_cache_modes(); } static int __init nopat(char *str) @@ -180,7 +191,7 @@ static enum page_cache_mode pat_get_cache_mode(unsigned pat_val, char *msg) * configuration. * Using lower indices is preferred, so we start with highest index. */ -void pat_init_cache_modes(u64 pat) +static void __init_cache_modes(u64 pat) { enum page_cache_mode cache; char pat_msg[33]; @@ -201,14 +212,11 @@ static void pat_bsp_init(u64 pat) { u64 tmp_pat; - if (!cpu_has_pat) { + if (!boot_cpu_has(X86_FEATURE_PAT)) { pat_disable("PAT not supported by CPU."); return; } - if (!pat_enabled()) - goto done; - rdmsrl(MSR_IA32_CR_PAT, tmp_pat); if (!tmp_pat) { pat_disable("PAT MSR is 0, disabled."); @@ -217,16 +225,12 @@ static void pat_bsp_init(u64 pat) wrmsrl(MSR_IA32_CR_PAT, pat); -done: - pat_init_cache_modes(pat); + __init_cache_modes(pat); } static void pat_ap_init(u64 pat) { - if (!pat_enabled()) - return; - - if (!cpu_has_pat) { + if (!boot_cpu_has(X86_FEATURE_PAT)) { /* * If this happens we are on a secondary CPU, but switched to * PAT on the boot CPU. We have no way to undo PAT. @@ -237,18 +241,32 @@ static void pat_ap_init(u64 pat) wrmsrl(MSR_IA32_CR_PAT, pat); } -void pat_init(void) +static void init_cache_modes(void) { - u64 pat; - struct cpuinfo_x86 *c = &boot_cpu_data; + u64 pat = 0; + static int init_cm_done; - if (!pat_enabled()) { + if (init_cm_done) + return; + + if (boot_cpu_has(X86_FEATURE_PAT)) { + /* + * CPU supports PAT. Set PAT table to be consistent with + * PAT MSR. This case supports "nopat" boot option, and + * virtual machine environments which support PAT without + * MTRRs. In specific, Xen has unique setup to PAT MSR. + * + * If PAT MSR returns 0, it is considered invalid and emulates + * as No PAT. + */ + rdmsrl(MSR_IA32_CR_PAT, pat); + } + + if (!pat) { /* * No PAT. Emulate the PAT table that corresponds to the two - * cache bits, PWT (Write Through) and PCD (Cache Disable). This - * setup is the same as the BIOS default setup when the system - * has PAT but the "nopat" boot option has been specified. This - * emulated PAT table is used when MSR_IA32_CR_PAT returns 0. + * cache bits, PWT (Write Through) and PCD (Cache Disable). + * This setup is also the same as the BIOS default setup. * * PTE encoding: * @@ -265,10 +283,36 @@ void pat_init(void) */ pat = PAT(0, WB) | PAT(1, WT) | PAT(2, UC_MINUS) | PAT(3, UC) | PAT(4, WB) | PAT(5, WT) | PAT(6, UC_MINUS) | PAT(7, UC); + } + + __init_cache_modes(pat); + + init_cm_done = 1; +} + +/** + * pat_init - Initialize PAT MSR and PAT table + * + * This function initializes PAT MSR and PAT table with an OS-defined value + * to enable additional cache attributes, WC and WT. + * + * This function must be called on all CPUs using the specific sequence of + * operations defined in Intel SDM. mtrr_rendezvous_handler() provides this + * procedure for PAT. + */ +void pat_init(void) +{ + u64 pat; + struct cpuinfo_x86 *c = &boot_cpu_data; + + if (!pat_enabled()) { + init_cache_modes(); + return; + } - } else if ((c->x86_vendor == X86_VENDOR_INTEL) && - (((c->x86 == 0x6) && (c->x86_model <= 0xd)) || - ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) { + if ((c->x86_vendor == X86_VENDOR_INTEL) && + (((c->x86 == 0x6) && (c->x86_model <= 0xd)) || + ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) { /* * PAT support with the lower four entries. Intel Pentium 2, * 3, M, and 4 are affected by PAT errata, which makes the @@ -733,25 +777,6 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, if (file->f_flags & O_DSYNC) pcm = _PAGE_CACHE_MODE_UC_MINUS; -#ifdef CONFIG_X86_32 - /* - * On the PPro and successors, the MTRRs are used to set - * memory types for physical addresses outside main memory, - * so blindly setting UC or PWT on those pages is wrong. - * For Pentiums and earlier, the surround logic should disable - * caching for the high addresses through the KEN pin, but - * we maintain the tradition of paranoia in this code. - */ - if (!pat_enabled() && - !(boot_cpu_has(X86_FEATURE_MTRR) || - boot_cpu_has(X86_FEATURE_K6_MTRR) || - boot_cpu_has(X86_FEATURE_CYRIX_ARR) || - boot_cpu_has(X86_FEATURE_CENTAUR_MCR)) && - (pfn << PAGE_SHIFT) >= __pa(high_memory)) { - pcm = _PAGE_CACHE_MODE_UC; - } -#endif - *vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) | cachemode2protval(pcm)); return 1; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index beab8c706ac9..ffa41591bff9 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -74,7 +74,6 @@ #include <asm/mach_traps.h> #include <asm/mwait.h> #include <asm/pci_x86.h> -#include <asm/pat.h> #include <asm/cpu.h> #ifdef CONFIG_ACPI @@ -1519,7 +1518,6 @@ asmlinkage __visible void __init xen_start_kernel(void) { struct physdev_set_iopl set_iopl; unsigned long initrd_start = 0; - u64 pat; int rc; if (!xen_start_info) @@ -1627,13 +1625,6 @@ asmlinkage __visible void __init xen_start_kernel(void) xen_start_info->nr_pages); xen_reserve_special_pages(); - /* - * Modify the cache mode translation tables to match Xen's PAT - * configuration. - */ - rdmsrl(MSR_IA32_CR_PAT, pat); - pat_init_cache_modes(pat); - /* keep using Xen gdt for now; no urgent need to change it */ #ifdef CONFIG_X86_32 diff --git a/block/genhd.c b/block/genhd.c index e5cafa51567c..d2a1d43bf9fa 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -831,6 +831,7 @@ static void disk_seqf_stop(struct seq_file *seqf, void *v) if (iter) { class_dev_iter_exit(iter); kfree(iter); + seqf->private = NULL; } } diff --git a/block/ioprio.c b/block/ioprio.c index cc7800e9eb44..01b8116298a1 100644 --- a/block/ioprio.c +++ b/block/ioprio.c @@ -150,8 +150,10 @@ static int get_task_ioprio(struct task_struct *p) if (ret) goto out; ret = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, IOPRIO_NORM); + task_lock(p); if (p->io_context) ret = p->io_context->ioprio; + task_unlock(p); out: return ret; } diff --git a/crypto/gcm.c b/crypto/gcm.c index bec329b3de8d..d9ea5f9c0574 100644 --- a/crypto/gcm.c +++ b/crypto/gcm.c @@ -639,7 +639,9 @@ static int crypto_gcm_create_common(struct crypto_template *tmpl, ghash_alg = crypto_find_alg(ghash_name, &crypto_ahash_type, CRYPTO_ALG_TYPE_HASH, - CRYPTO_ALG_TYPE_AHASH_MASK); + CRYPTO_ALG_TYPE_AHASH_MASK | + crypto_requires_sync(algt->type, + algt->mask)); if (IS_ERR(ghash_alg)) return PTR_ERR(ghash_alg); diff --git a/crypto/scatterwalk.c b/crypto/scatterwalk.c index ea5815c5e128..bc769c448d4a 100644 --- a/crypto/scatterwalk.c +++ b/crypto/scatterwalk.c @@ -72,7 +72,8 @@ static void scatterwalk_pagedone(struct scatter_walk *walk, int out, void scatterwalk_done(struct scatter_walk *walk, int out, int more) { - if (!(scatterwalk_pagelen(walk) & (PAGE_SIZE - 1)) || !more) + if (!more || walk->offset >= walk->sg->offset + walk->sg->length || + !(walk->offset & (PAGE_SIZE - 1))) scatterwalk_pagedone(walk, out, more); } EXPORT_SYMBOL_GPL(scatterwalk_done); diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index b79cb10e289e..bd370c98f77d 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4138,6 +4138,12 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { */ { "ST380013AS", "3.20", ATA_HORKAGE_MAX_SEC_1024 }, + /* + * Device times out with higher max sects. + * https://bugzilla.kernel.org/show_bug.cgi?id=121671 + */ + { "LITEON CX1-JB256-HP", NULL, ATA_HORKAGE_MAX_SEC_1024 }, + /* Devices we expect to fail diagnostics */ /* Devices where NCQ should be avoided */ diff --git a/drivers/bcma/bcma_private.h b/drivers/bcma/bcma_private.h index 38f156745d53..71df8f2afc6c 100644 --- a/drivers/bcma/bcma_private.h +++ b/drivers/bcma/bcma_private.h @@ -8,8 +8,6 @@ #include <linux/bcma/bcma.h> #include <linux/delay.h> -#define BCMA_CORE_SIZE 0x1000 - #define bcma_err(bus, fmt, ...) \ pr_err("bus%d: " fmt, (bus)->num, ##__VA_ARGS__) #define bcma_warn(bus, fmt, ...) \ diff --git a/drivers/char/random.c b/drivers/char/random.c index d0da5d852d41..0227b0465b40 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -722,15 +722,18 @@ retry: } } -static void credit_entropy_bits_safe(struct entropy_store *r, int nbits) +static int credit_entropy_bits_safe(struct entropy_store *r, int nbits) { const int nbits_max = (int)(~0U >> (ENTROPY_SHIFT + 1)); + if (nbits < 0) + return -EINVAL; + /* Cap the value to avoid overflows */ nbits = min(nbits, nbits_max); - nbits = max(nbits, -nbits_max); credit_entropy_bits(r, nbits); + return 0; } /********************************************************************* @@ -1542,8 +1545,7 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg) return -EPERM; if (get_user(ent_count, p)) return -EFAULT; - credit_entropy_bits_safe(&input_pool, ent_count); - return 0; + return credit_entropy_bits_safe(&input_pool, ent_count); case RNDADDENTROPY: if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -1557,8 +1559,7 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg) size); if (retval < 0) return retval; - credit_entropy_bits_safe(&input_pool, ent_count); - return 0; + return credit_entropy_bits_safe(&input_pool, ent_count); case RNDZAPENTCNT: case RNDCLEARPOOL: /* diff --git a/drivers/clk/rockchip/clk-mmc-phase.c b/drivers/clk/rockchip/clk-mmc-phase.c index 2685644826a0..33c20c6b45af 100644 --- a/drivers/clk/rockchip/clk-mmc-phase.c +++ b/drivers/clk/rockchip/clk-mmc-phase.c @@ -153,6 +153,7 @@ struct clk *rockchip_clk_register_mmc(const char *name, return NULL; init.name = name; + init.flags = 0; init.num_parents = num_parents; init.parent_names = parent_names; init.ops = &rockchip_mmc_clk_ops; diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 02f9aa4ebe05..e44a1bfb0250 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -242,7 +242,7 @@ struct at_xdmac_lld { u32 mbr_dus; /* Destination Microblock Stride Register */ }; - +/* 64-bit alignment needed to update CNDA and CUBC registers in an atomic way. */ struct at_xdmac_desc { struct at_xdmac_lld lld; enum dma_transfer_direction direction; @@ -253,7 +253,7 @@ struct at_xdmac_desc { unsigned int xfer_size; struct list_head descs_list; struct list_head xfer_node; -}; +} __aligned(sizeof(u64)); static inline void __iomem *at_xdmac_chan_reg_base(struct at_xdmac *atxdmac, unsigned int chan_nb) { @@ -1388,6 +1388,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, u32 cur_nda, check_nda, cur_ubc, mask, value; u8 dwidth = 0; unsigned long flags; + bool initd; ret = dma_cookie_status(chan, cookie, txstate); if (ret == DMA_COMPLETE) @@ -1412,7 +1413,16 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, residue = desc->xfer_size; /* * Flush FIFO: only relevant when the transfer is source peripheral - * synchronized. + * synchronized. Flush is needed before reading CUBC because data in + * the FIFO are not reported by CUBC. Reporting a residue of the + * transfer length while we have data in FIFO can cause issue. + * Usecase: atmel USART has a timeout which means I have received + * characters but there is no more character received for a while. On + * timeout, it requests the residue. If the data are in the DMA FIFO, + * we will return a residue of the transfer length. It means no data + * received. If an application is waiting for these data, it will hang + * since we won't have another USART timeout without receiving new + * data. */ mask = AT_XDMAC_CC_TYPE | AT_XDMAC_CC_DSYNC; value = AT_XDMAC_CC_TYPE_PER_TRAN | AT_XDMAC_CC_DSYNC_PER2MEM; @@ -1423,34 +1433,43 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, } /* - * When processing the residue, we need to read two registers but we - * can't do it in an atomic way. AT_XDMAC_CNDA is used to find where - * we stand in the descriptor list and AT_XDMAC_CUBC is used - * to know how many data are remaining for the current descriptor. - * Since the dma channel is not paused to not loose data, between the - * AT_XDMAC_CNDA and AT_XDMAC_CUBC read, we may have change of - * descriptor. - * For that reason, after reading AT_XDMAC_CUBC, we check if we are - * still using the same descriptor by reading a second time - * AT_XDMAC_CNDA. If AT_XDMAC_CNDA has changed, it means we have to - * read again AT_XDMAC_CUBC. + * The easiest way to compute the residue should be to pause the DMA + * but doing this can lead to miss some data as some devices don't + * have FIFO. + * We need to read several registers because: + * - DMA is running therefore a descriptor change is possible while + * reading these registers + * - When the block transfer is done, the value of the CUBC register + * is set to its initial value until the fetch of the next descriptor. + * This value will corrupt the residue calculation so we have to skip + * it. + * + * INITD -------- ------------ + * |____________________| + * _______________________ _______________ + * NDA @desc2 \/ @desc3 + * _______________________/\_______________ + * __________ ___________ _______________ + * CUBC 0 \/ MAX desc1 \/ MAX desc2 + * __________/\___________/\_______________ + * + * Since descriptors are aligned on 64 bits, we can assume that + * the update of NDA and CUBC is atomic. * Memory barriers are used to ensure the read order of the registers. - * A max number of retries is set because unlikely it can never ends if - * we are transferring a lot of data with small buffers. + * A max number of retries is set because unlikely it could never ends. */ - cur_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc; - rmb(); - cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC); for (retry = 0; retry < AT_XDMAC_RESIDUE_MAX_RETRIES; retry++) { - rmb(); check_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc; - - if (likely(cur_nda == check_nda)) - break; - - cur_nda = check_nda; + rmb(); + initd = !!(at_xdmac_chan_read(atchan, AT_XDMAC_CC) & AT_XDMAC_CC_INITD); rmb(); cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC); + rmb(); + cur_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc; + rmb(); + + if ((check_nda == cur_nda) && initd) + break; } if (unlikely(retry >= AT_XDMAC_RESIDUE_MAX_RETRIES)) { @@ -1459,6 +1478,19 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, } /* + * Flush FIFO: only relevant when the transfer is source peripheral + * synchronized. Another flush is needed here because CUBC is updated + * when the controller sends the data write command. It can lead to + * report data that are not written in the memory or the device. The + * FIFO flush ensures that data are really written. + */ + if ((desc->lld.mbr_cfg & mask) == value) { + at_xdmac_write(atxdmac, AT_XDMAC_GSWF, atchan->mask); + while (!(at_xdmac_chan_read(atchan, AT_XDMAC_CIS) & AT_XDMAC_CIS_FIS)) + cpu_relax(); + } + + /* * Remove size of all microblocks already transferred and the current * one. Then add the remaining size to transfer of the current * microblock. diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 62284e45d531..eb434881ddbc 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -1789,16 +1789,20 @@ static uint32_t ilk_compute_cur_wm(const struct intel_crtc_state *cstate, const struct intel_plane_state *pstate, uint32_t mem_value) { - int bpp = pstate->base.fb ? pstate->base.fb->bits_per_pixel / 8 : 0; + /* + * We treat the cursor plane as always-on for the purposes of watermark + * calculation. Until we have two-stage watermark programming merged, + * this is necessary to avoid flickering. + */ + int cpp = 4; + int width = pstate->visible ? pstate->base.crtc_w : 64; - if (!cstate->base.active || !pstate->visible) + if (!cstate->base.active) return 0; return ilk_wm_method2(ilk_pipe_pixel_rate(cstate), cstate->base.adjusted_mode.crtc_htotal, - drm_rect_width(&pstate->dst), - bpp, - mem_value); + width, cpp, mem_value); } /* Only for WM_LP. */ diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c index 774cd2210566..21febbb0d84e 100644 --- a/drivers/hid/hid-sony.c +++ b/drivers/hid/hid-sony.c @@ -1418,8 +1418,10 @@ static int sixaxis_set_operational_usb(struct hid_device *hdev) } ret = hid_hw_output_report(hdev, buf, 1); - if (ret < 0) - hid_err(hdev, "can't set operational mode: step 3\n"); + if (ret < 0) { + hid_info(hdev, "can't set operational mode: step 3, ignoring\n"); + ret = 0; + } out: kfree(buf); diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c index 165d3001c301..c6ec5c62b7a9 100644 --- a/drivers/hwtracing/intel_th/core.c +++ b/drivers/hwtracing/intel_th/core.c @@ -419,6 +419,38 @@ static struct intel_th_subdevice { }, }; +#ifdef CONFIG_MODULES +static void __intel_th_request_hub_module(struct work_struct *work) +{ + struct intel_th *th = container_of(work, struct intel_th, + request_module_work); + + request_module("intel_th_%s", th->hub->name); +} + +static int intel_th_request_hub_module(struct intel_th *th) +{ + INIT_WORK(&th->request_module_work, __intel_th_request_hub_module); + schedule_work(&th->request_module_work); + + return 0; +} + +static void intel_th_request_hub_module_flush(struct intel_th *th) +{ + flush_work(&th->request_module_work); +} +#else +static inline int intel_th_request_hub_module(struct intel_th *th) +{ + return -EINVAL; +} + +static inline void intel_th_request_hub_module_flush(struct intel_th *th) +{ +} +#endif /* CONFIG_MODULES */ + static int intel_th_populate(struct intel_th *th, struct resource *devres, unsigned int ndevres, int irq) { @@ -488,7 +520,7 @@ static int intel_th_populate(struct intel_th *th, struct resource *devres, /* need switch driver to be loaded to enumerate the rest */ if (subdev->type == INTEL_TH_SWITCH && !req) { th->hub = thdev; - err = request_module("intel_th_%s", subdev->name); + err = intel_th_request_hub_module(th); if (!err) req++; } @@ -603,6 +635,7 @@ void intel_th_free(struct intel_th *th) { int i; + intel_th_request_hub_module_flush(th); for (i = 0; i < TH_SUBDEVICE_MAX; i++) if (th->thdev[i] != th->hub) intel_th_device_remove(th->thdev[i]); diff --git a/drivers/hwtracing/intel_th/intel_th.h b/drivers/hwtracing/intel_th/intel_th.h index 57fd72b20fae..d03a6cd1c65d 100644 --- a/drivers/hwtracing/intel_th/intel_th.h +++ b/drivers/hwtracing/intel_th/intel_th.h @@ -197,6 +197,9 @@ struct intel_th { int id; int major; +#ifdef CONFIG_MODULES + struct work_struct request_module_work; +#endif /* CONFIG_MODULES */ #ifdef CONFIG_INTEL_TH_DEBUG struct dentry *dbg; #endif diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c index 641e87936064..d57a2f75dccf 100644 --- a/drivers/hwtracing/intel_th/pci.c +++ b/drivers/hwtracing/intel_th/pci.c @@ -67,6 +67,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa126), .driver_data = (kernel_ulong_t)0, }, + { + /* Kaby Lake PCH-H */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa2a6), + .driver_data = (kernel_ulong_t)0, + }, { 0 }, }; diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 27fa0cb09538..85f39cc3e276 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -244,6 +244,13 @@ struct i801_priv { struct platform_device *mux_pdev; #endif struct platform_device *tco_pdev; + + /* + * If set to true the host controller registers are reserved for + * ACPI AML use. Protected by acpi_lock. + */ + bool acpi_reserved; + struct mutex acpi_lock; }; #define FEATURE_SMBUS_PEC (1 << 0) @@ -714,9 +721,15 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr, { int hwpec; int block = 0; - int ret, xact = 0; + int ret = 0, xact = 0; struct i801_priv *priv = i2c_get_adapdata(adap); + mutex_lock(&priv->acpi_lock); + if (priv->acpi_reserved) { + mutex_unlock(&priv->acpi_lock); + return -EBUSY; + } + hwpec = (priv->features & FEATURE_SMBUS_PEC) && (flags & I2C_CLIENT_PEC) && size != I2C_SMBUS_QUICK && size != I2C_SMBUS_I2C_BLOCK_DATA; @@ -773,7 +786,8 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr, default: dev_err(&priv->pci_dev->dev, "Unsupported transaction %d\n", size); - return -EOPNOTSUPP; + ret = -EOPNOTSUPP; + goto out; } if (hwpec) /* enable/disable hardware PEC */ @@ -796,11 +810,11 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr, ~(SMBAUXCTL_CRC | SMBAUXCTL_E32B), SMBAUXCTL(priv)); if (block) - return ret; + goto out; if (ret) - return ret; + goto out; if ((read_write == I2C_SMBUS_WRITE) || (xact == I801_QUICK)) - return 0; + goto out; switch (xact & 0x7f) { case I801_BYTE: /* Result put in SMBHSTDAT0 */ @@ -812,7 +826,10 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr, (inb_p(SMBHSTDAT1(priv)) << 8); break; } - return 0; + +out: + mutex_unlock(&priv->acpi_lock); + return ret; } @@ -1249,6 +1266,72 @@ static void i801_add_tco(struct i801_priv *priv) priv->tco_pdev = pdev; } +#ifdef CONFIG_ACPI +static acpi_status +i801_acpi_io_handler(u32 function, acpi_physical_address address, u32 bits, + u64 *value, void *handler_context, void *region_context) +{ + struct i801_priv *priv = handler_context; + struct pci_dev *pdev = priv->pci_dev; + acpi_status status; + + /* + * Once BIOS AML code touches the OpRegion we warn and inhibit any + * further access from the driver itself. This device is now owned + * by the system firmware. + */ + mutex_lock(&priv->acpi_lock); + + if (!priv->acpi_reserved) { + priv->acpi_reserved = true; + + dev_warn(&pdev->dev, "BIOS is accessing SMBus registers\n"); + dev_warn(&pdev->dev, "Driver SMBus register access inhibited\n"); + } + + if ((function & ACPI_IO_MASK) == ACPI_READ) + status = acpi_os_read_port(address, (u32 *)value, bits); + else + status = acpi_os_write_port(address, (u32)*value, bits); + + mutex_unlock(&priv->acpi_lock); + + return status; +} + +static int i801_acpi_probe(struct i801_priv *priv) +{ + struct acpi_device *adev; + acpi_status status; + + adev = ACPI_COMPANION(&priv->pci_dev->dev); + if (adev) { + status = acpi_install_address_space_handler(adev->handle, + ACPI_ADR_SPACE_SYSTEM_IO, i801_acpi_io_handler, + NULL, priv); + if (ACPI_SUCCESS(status)) + return 0; + } + + return acpi_check_resource_conflict(&priv->pci_dev->resource[SMBBAR]); +} + +static void i801_acpi_remove(struct i801_priv *priv) +{ + struct acpi_device *adev; + + adev = ACPI_COMPANION(&priv->pci_dev->dev); + if (!adev) + return; + + acpi_remove_address_space_handler(adev->handle, + ACPI_ADR_SPACE_SYSTEM_IO, i801_acpi_io_handler); +} +#else +static inline int i801_acpi_probe(struct i801_priv *priv) { return 0; } +static inline void i801_acpi_remove(struct i801_priv *priv) { } +#endif + static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) { unsigned char temp; @@ -1266,6 +1349,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) priv->adapter.dev.parent = &dev->dev; ACPI_COMPANION_SET(&priv->adapter.dev, ACPI_COMPANION(&dev->dev)); priv->adapter.retries = 3; + mutex_init(&priv->acpi_lock); priv->pci_dev = dev; switch (dev->device) { @@ -1328,10 +1412,8 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) return -ENODEV; } - err = acpi_check_resource_conflict(&dev->resource[SMBBAR]); - if (err) { + if (i801_acpi_probe(priv)) return -ENODEV; - } err = pcim_iomap_regions(dev, 1 << SMBBAR, dev_driver_string(&dev->dev)); @@ -1340,6 +1422,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) "Failed to request SMBus region 0x%lx-0x%Lx\n", priv->smba, (unsigned long long)pci_resource_end(dev, SMBBAR)); + i801_acpi_remove(priv); return err; } @@ -1404,6 +1487,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) err = i2c_add_adapter(&priv->adapter); if (err) { dev_err(&dev->dev, "Failed to add SMBus adapter\n"); + i801_acpi_remove(priv); return err; } @@ -1422,6 +1506,7 @@ static void i801_remove(struct pci_dev *dev) i801_del_mux(priv); i2c_del_adapter(&priv->adapter); + i801_acpi_remove(priv); pci_write_config_byte(dev, SMBHSTCFG, priv->original_hstcfg); platform_device_unregister(priv->tco_pdev); diff --git a/drivers/i2c/muxes/i2c-mux-reg.c b/drivers/i2c/muxes/i2c-mux-reg.c index 5fbd5bd0878f..49fc2c7e560a 100644 --- a/drivers/i2c/muxes/i2c-mux-reg.c +++ b/drivers/i2c/muxes/i2c-mux-reg.c @@ -150,7 +150,7 @@ static int i2c_mux_reg_probe_dt(struct regmux *mux, mux->data.idle_in_use = true; /* map address from "reg" if exists */ - if (of_address_to_resource(np, 0, &res)) { + if (of_address_to_resource(np, 0, &res) == 0) { mux->data.reg_size = resource_size(&res); mux->data.reg = devm_ioremap_resource(&pdev->dev, &res); if (IS_ERR(mux->data.reg)) diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index fd4100d56d8c..2b2f9d66c2c7 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -1200,22 +1200,15 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id int ep_irq_in_idx; int i, error; + if (intf->cur_altsetting->desc.bNumEndpoints != 2) + return -ENODEV; + for (i = 0; xpad_device[i].idVendor; i++) { if ((le16_to_cpu(udev->descriptor.idVendor) == xpad_device[i].idVendor) && (le16_to_cpu(udev->descriptor.idProduct) == xpad_device[i].idProduct)) break; } - if (xpad_device[i].xtype == XTYPE_XBOXONE && - intf->cur_altsetting->desc.bInterfaceNumber != 0) { - /* - * The Xbox One controller lists three interfaces all with the - * same interface class, subclass and protocol. Differentiate by - * interface number. - */ - return -ENODEV; - } - xpad = kzalloc(sizeof(struct usb_xpad), GFP_KERNEL); if (!xpad) return -ENOMEM; @@ -1246,6 +1239,8 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id if (intf->cur_altsetting->desc.bInterfaceClass == USB_CLASS_VENDOR_SPEC) { if (intf->cur_altsetting->desc.bInterfaceProtocol == 129) xpad->xtype = XTYPE_XBOX360W; + else if (intf->cur_altsetting->desc.bInterfaceProtocol == 208) + xpad->xtype = XTYPE_XBOXONE; else xpad->xtype = XTYPE_XBOX360; } else { @@ -1260,6 +1255,17 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id xpad->mapping |= MAP_STICKS_TO_NULL; } + if (xpad->xtype == XTYPE_XBOXONE && + intf->cur_altsetting->desc.bInterfaceNumber != 0) { + /* + * The Xbox One controller lists three interfaces all with the + * same interface class, subclass and protocol. Differentiate by + * interface number. + */ + error = -ENODEV; + goto err_free_in_urb; + } + error = xpad_init_output(intf, xpad); if (error) goto err_free_in_urb; diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c index 78f93cf68840..be5b399da5d3 100644 --- a/drivers/input/mouse/elantech.c +++ b/drivers/input/mouse/elantech.c @@ -1568,13 +1568,7 @@ static int elantech_set_properties(struct elantech_data *etd) case 5: etd->hw_version = 3; break; - case 6: - case 7: - case 8: - case 9: - case 10: - case 13: - case 14: + case 6 ... 14: etd->hw_version = 4; break; default: diff --git a/drivers/input/mouse/vmmouse.c b/drivers/input/mouse/vmmouse.c index a3f0f5a47490..0f586780ceb4 100644 --- a/drivers/input/mouse/vmmouse.c +++ b/drivers/input/mouse/vmmouse.c @@ -355,18 +355,11 @@ int vmmouse_detect(struct psmouse *psmouse, bool set_properties) return -ENXIO; } - if (!request_region(VMMOUSE_PROTO_PORT, 4, "vmmouse")) { - psmouse_dbg(psmouse, "VMMouse port in use.\n"); - return -EBUSY; - } - /* Check if the device is present */ response = ~VMMOUSE_PROTO_MAGIC; VMMOUSE_CMD(GETVERSION, 0, version, response, dummy1, dummy2); - if (response != VMMOUSE_PROTO_MAGIC || version == 0xffffffffU) { - release_region(VMMOUSE_PROTO_PORT, 4); + if (response != VMMOUSE_PROTO_MAGIC || version == 0xffffffffU) return -ENXIO; - } if (set_properties) { psmouse->vendor = VMMOUSE_VENDOR; @@ -374,8 +367,6 @@ int vmmouse_detect(struct psmouse *psmouse, bool set_properties) psmouse->model = version; } - release_region(VMMOUSE_PROTO_PORT, 4); - return 0; } @@ -394,7 +385,6 @@ static void vmmouse_disconnect(struct psmouse *psmouse) psmouse_reset(psmouse); input_unregister_device(priv->abs_dev); kfree(priv); - release_region(VMMOUSE_PROTO_PORT, 4); } /** @@ -438,15 +428,10 @@ int vmmouse_init(struct psmouse *psmouse) struct input_dev *rel_dev = psmouse->dev, *abs_dev; int error; - if (!request_region(VMMOUSE_PROTO_PORT, 4, "vmmouse")) { - psmouse_dbg(psmouse, "VMMouse port in use.\n"); - return -EBUSY; - } - psmouse_reset(psmouse); error = vmmouse_enable(psmouse); if (error) - goto release_region; + return error; priv = kzalloc(sizeof(*priv), GFP_KERNEL); abs_dev = input_allocate_device(); @@ -502,8 +487,5 @@ init_fail: kfree(priv); psmouse->private = NULL; -release_region: - release_region(VMMOUSE_PROTO_PORT, 4); - return error; } diff --git a/drivers/input/touchscreen/tsc2004.c b/drivers/input/touchscreen/tsc2004.c index 7295c198aa08..6fe55d598fac 100644 --- a/drivers/input/touchscreen/tsc2004.c +++ b/drivers/input/touchscreen/tsc2004.c @@ -22,6 +22,11 @@ #include <linux/regmap.h> #include "tsc200x-core.h" +static const struct input_id tsc2004_input_id = { + .bustype = BUS_I2C, + .product = 2004, +}; + static int tsc2004_cmd(struct device *dev, u8 cmd) { u8 tx = TSC200X_CMD | TSC200X_CMD_12BIT | cmd; @@ -42,7 +47,7 @@ static int tsc2004_probe(struct i2c_client *i2c, const struct i2c_device_id *id) { - return tsc200x_probe(&i2c->dev, i2c->irq, BUS_I2C, + return tsc200x_probe(&i2c->dev, i2c->irq, &tsc2004_input_id, devm_regmap_init_i2c(i2c, &tsc200x_regmap_config), tsc2004_cmd); } diff --git a/drivers/input/touchscreen/tsc2005.c b/drivers/input/touchscreen/tsc2005.c index b9f593dfd2ef..f2c5f0e47f77 100644 --- a/drivers/input/touchscreen/tsc2005.c +++ b/drivers/input/touchscreen/tsc2005.c @@ -24,6 +24,11 @@ #include <linux/regmap.h> #include "tsc200x-core.h" +static const struct input_id tsc2005_input_id = { + .bustype = BUS_SPI, + .product = 2005, +}; + static int tsc2005_cmd(struct device *dev, u8 cmd) { u8 tx = TSC200X_CMD | TSC200X_CMD_12BIT | cmd; @@ -62,7 +67,7 @@ static int tsc2005_probe(struct spi_device *spi) if (error) return error; - return tsc200x_probe(&spi->dev, spi->irq, BUS_SPI, + return tsc200x_probe(&spi->dev, spi->irq, &tsc2005_input_id, devm_regmap_init_spi(spi, &tsc200x_regmap_config), tsc2005_cmd); } diff --git a/drivers/input/touchscreen/tsc200x-core.c b/drivers/input/touchscreen/tsc200x-core.c index 15240c1ee850..dfa7f1c4f545 100644 --- a/drivers/input/touchscreen/tsc200x-core.c +++ b/drivers/input/touchscreen/tsc200x-core.c @@ -450,7 +450,7 @@ static void tsc200x_close(struct input_dev *input) mutex_unlock(&ts->mutex); } -int tsc200x_probe(struct device *dev, int irq, __u16 bustype, +int tsc200x_probe(struct device *dev, int irq, const struct input_id *tsc_id, struct regmap *regmap, int (*tsc200x_cmd)(struct device *dev, u8 cmd)) { @@ -547,9 +547,18 @@ int tsc200x_probe(struct device *dev, int irq, __u16 bustype, snprintf(ts->phys, sizeof(ts->phys), "%s/input-ts", dev_name(dev)); - input_dev->name = "TSC200X touchscreen"; + if (tsc_id->product == 2004) { + input_dev->name = "TSC200X touchscreen"; + } else { + input_dev->name = devm_kasprintf(dev, GFP_KERNEL, + "TSC%04d touchscreen", + tsc_id->product); + if (!input_dev->name) + return -ENOMEM; + } + input_dev->phys = ts->phys; - input_dev->id.bustype = bustype; + input_dev->id = *tsc_id; input_dev->dev.parent = dev; input_dev->evbit[0] = BIT(EV_ABS) | BIT(EV_KEY); input_dev->keybit[BIT_WORD(BTN_TOUCH)] = BIT_MASK(BTN_TOUCH); diff --git a/drivers/input/touchscreen/tsc200x-core.h b/drivers/input/touchscreen/tsc200x-core.h index 7a482d102614..49a63a3c6840 100644 --- a/drivers/input/touchscreen/tsc200x-core.h +++ b/drivers/input/touchscreen/tsc200x-core.h @@ -70,7 +70,7 @@ extern const struct regmap_config tsc200x_regmap_config; extern const struct dev_pm_ops tsc200x_pm_ops; -int tsc200x_probe(struct device *dev, int irq, __u16 bustype, +int tsc200x_probe(struct device *dev, int irq, const struct input_id *tsc_id, struct regmap *regmap, int (*tsc200x_cmd)(struct device *dev, u8 cmd)); int tsc200x_remove(struct device *dev); diff --git a/drivers/input/touchscreen/wacom_w8001.c b/drivers/input/touchscreen/wacom_w8001.c index 2792ca397dd0..3ed0ce1e4dcb 100644 --- a/drivers/input/touchscreen/wacom_w8001.c +++ b/drivers/input/touchscreen/wacom_w8001.c @@ -27,7 +27,7 @@ MODULE_AUTHOR("Jaya Kumar <jayakumar.lkml@gmail.com>"); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_LICENSE("GPL"); -#define W8001_MAX_LENGTH 11 +#define W8001_MAX_LENGTH 13 #define W8001_LEAD_MASK 0x80 #define W8001_LEAD_BYTE 0x80 #define W8001_TAB_MASK 0x40 diff --git a/drivers/media/usb/airspy/airspy.c b/drivers/media/usb/airspy/airspy.c index 565a59310747..34b35ebd60ac 100644 --- a/drivers/media/usb/airspy/airspy.c +++ b/drivers/media/usb/airspy/airspy.c @@ -1073,7 +1073,7 @@ static int airspy_probe(struct usb_interface *intf, if (ret) { dev_err(s->dev, "Failed to register as video device (%d)\n", ret); - goto err_unregister_v4l2_dev; + goto err_free_controls; } dev_info(s->dev, "Registered as %s\n", video_device_node_name(&s->vdev)); @@ -1082,7 +1082,6 @@ static int airspy_probe(struct usb_interface *intf, err_free_controls: v4l2_ctrl_handler_free(&s->hdl); -err_unregister_v4l2_dev: v4l2_device_unregister(&s->v4l2_dev); err_free_mem: kfree(s); diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index c641c202fe7e..64950035613b 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -1767,8 +1767,8 @@ static void mmc_blk_packed_hdr_wrq_prep(struct mmc_queue_req *mqrq, packed_cmd_hdr = packed->cmd_hdr; memset(packed_cmd_hdr, 0, sizeof(packed->cmd_hdr)); - packed_cmd_hdr[0] = (packed->nr_entries << 16) | - (PACKED_CMD_WR << 8) | PACKED_CMD_VER; + packed_cmd_hdr[0] = cpu_to_le32((packed->nr_entries << 16) | + (PACKED_CMD_WR << 8) | PACKED_CMD_VER); hdr_blocks = mmc_large_sector(card) ? 8 : 1; /* @@ -1782,14 +1782,14 @@ static void mmc_blk_packed_hdr_wrq_prep(struct mmc_queue_req *mqrq, ((brq->data.blocks * brq->data.blksz) >= card->ext_csd.data_tag_unit_size); /* Argument of CMD23 */ - packed_cmd_hdr[(i * 2)] = + packed_cmd_hdr[(i * 2)] = cpu_to_le32( (do_rel_wr ? MMC_CMD23_ARG_REL_WR : 0) | (do_data_tag ? MMC_CMD23_ARG_TAG_REQ : 0) | - blk_rq_sectors(prq); + blk_rq_sectors(prq)); /* Argument of CMD18 or CMD25 */ - packed_cmd_hdr[((i * 2)) + 1] = + packed_cmd_hdr[((i * 2)) + 1] = cpu_to_le32( mmc_card_blockaddr(card) ? - blk_rq_pos(prq) : blk_rq_pos(prq) << 9; + blk_rq_pos(prq) : blk_rq_pos(prq) << 9); packed->blocks += blk_rq_sectors(prq); i++; } diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index db760e84119f..b8df0f5e8c25 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -446,7 +446,11 @@ static int bond_newlink(struct net *src_net, struct net_device *bond_dev, if (err < 0) return err; - return register_netdevice(bond_dev); + err = register_netdevice(bond_dev); + + netif_carrier_off(bond_dev); + + return err; } static size_t bond_get_size(const struct net_device *bond_dev) diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c index 8b3275d7792a..8f5e93cb7975 100644 --- a/drivers/net/can/at91_can.c +++ b/drivers/net/can/at91_can.c @@ -712,9 +712,10 @@ static int at91_poll_rx(struct net_device *dev, int quota) /* upper group completed, look again in lower */ if (priv->rx_next > get_mb_rx_low_last(priv) && - quota > 0 && mb > get_mb_rx_last(priv)) { + mb > get_mb_rx_last(priv)) { priv->rx_next = get_mb_rx_first(priv); - goto again; + if (quota > 0) + goto again; } return received; diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c index f91b094288da..e3dccd3200d5 100644 --- a/drivers/net/can/c_can/c_can.c +++ b/drivers/net/can/c_can/c_can.c @@ -332,9 +332,23 @@ static void c_can_setup_tx_object(struct net_device *dev, int iface, priv->write_reg(priv, C_CAN_IFACE(MSGCTRL_REG, iface), ctrl); - for (i = 0; i < frame->can_dlc; i += 2) { - priv->write_reg(priv, C_CAN_IFACE(DATA1_REG, iface) + i / 2, - frame->data[i] | (frame->data[i + 1] << 8)); + if (priv->type == BOSCH_D_CAN) { + u32 data = 0, dreg = C_CAN_IFACE(DATA1_REG, iface); + + for (i = 0; i < frame->can_dlc; i += 4, dreg += 2) { + data = (u32)frame->data[i]; + data |= (u32)frame->data[i + 1] << 8; + data |= (u32)frame->data[i + 2] << 16; + data |= (u32)frame->data[i + 3] << 24; + priv->write_reg32(priv, dreg, data); + } + } else { + for (i = 0; i < frame->can_dlc; i += 2) { + priv->write_reg(priv, + C_CAN_IFACE(DATA1_REG, iface) + i / 2, + frame->data[i] | + (frame->data[i + 1] << 8)); + } } } @@ -402,10 +416,20 @@ static int c_can_read_msg_object(struct net_device *dev, int iface, u32 ctrl) } else { int i, dreg = C_CAN_IFACE(DATA1_REG, iface); - for (i = 0; i < frame->can_dlc; i += 2, dreg ++) { - data = priv->read_reg(priv, dreg); - frame->data[i] = data; - frame->data[i + 1] = data >> 8; + if (priv->type == BOSCH_D_CAN) { + for (i = 0; i < frame->can_dlc; i += 4, dreg += 2) { + data = priv->read_reg32(priv, dreg); + frame->data[i] = data; + frame->data[i + 1] = data >> 8; + frame->data[i + 2] = data >> 16; + frame->data[i + 3] = data >> 24; + } + } else { + for (i = 0; i < frame->can_dlc; i += 2, dreg++) { + data = priv->read_reg(priv, dreg); + frame->data[i] = data; + frame->data[i + 1] = data >> 8; + } } } diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index 910c12e2638e..ad535a854e5c 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -798,6 +798,9 @@ static int can_validate(struct nlattr *tb[], struct nlattr *data[]) * - control mode with CAN_CTRLMODE_FD set */ + if (!data) + return 0; + if (data[IFLA_CAN_CTRLMODE]) { struct can_ctrlmode *cm = nla_data(data[IFLA_CAN_CTRLMODE]); @@ -1008,6 +1011,11 @@ static int can_newlink(struct net *src_net, struct net_device *dev, return -EOPNOTSUPP; } +static void can_dellink(struct net_device *dev, struct list_head *head) +{ + return; +} + static struct rtnl_link_ops can_link_ops __read_mostly = { .kind = "can", .maxtype = IFLA_CAN_MAX, @@ -1016,6 +1024,7 @@ static struct rtnl_link_ops can_link_ops __read_mostly = { .validate = can_validate, .newlink = can_newlink, .changelink = can_changelink, + .dellink = can_dellink, .get_size = can_get_size, .fill_info = can_fill_info, .get_xstats_size = can_get_xstats_size, diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index 28f7610b03fe..c32f5d32f811 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -219,7 +219,7 @@ err_dma: dma_unmap_single(dma_dev, slot->dma_addr, skb_headlen(skb), DMA_TO_DEVICE); - while (i > 0) { + while (i-- > 0) { int index = (ring->end + i) % BGMAC_TX_RING_SLOTS; struct bgmac_slot_info *slot = &ring->slots[index]; u32 ctl1 = le32_to_cpu(ring->cpu_base[index].ctl1); diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index a4ac6fedac75..71ec9cb08e06 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -226,7 +226,7 @@ /* Various constants */ /* Coalescing */ -#define MVNETA_TXDONE_COAL_PKTS 1 +#define MVNETA_TXDONE_COAL_PKTS 0 /* interrupt per packet */ #define MVNETA_RX_COAL_PKTS 32 #define MVNETA_RX_COAL_USEC 100 diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c index 3dd548ab8df1..40365cb1abe6 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_spq.c +++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c @@ -794,13 +794,12 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn, * in a bitmap and increasing the chain consumer only * for the first successive completed entries. */ - bitmap_set(p_spq->p_comp_bitmap, pos, SPQ_RING_SIZE); + __set_bit(pos, p_spq->p_comp_bitmap); while (test_bit(p_spq->comp_bitmap_idx, p_spq->p_comp_bitmap)) { - bitmap_clear(p_spq->p_comp_bitmap, - p_spq->comp_bitmap_idx, - SPQ_RING_SIZE); + __clear_bit(p_spq->comp_bitmap_idx, + p_spq->p_comp_bitmap); p_spq->comp_bitmap_idx++; qed_chain_return_produced(&p_spq->chain); } diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index a790d5f90b83..e0e94b855bbe 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -952,8 +952,6 @@ EXPORT_SYMBOL_GPL(cdc_ncm_select_altsetting); static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf) { - int ret; - /* MBIM backwards compatible function? */ if (cdc_ncm_select_altsetting(intf) != CDC_NCM_COMM_ALTSETTING_NCM) return -ENODEV; @@ -962,16 +960,7 @@ static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf) * Additionally, generic NCM devices are assumed to accept arbitrarily * placed NDP. */ - ret = cdc_ncm_bind_common(dev, intf, CDC_NCM_DATA_ALTSETTING_NCM, 0); - - /* - * We should get an event when network connection is "connected" or - * "disconnected". Set network connection in "disconnected" state - * (carrier is OFF) during attach, so the IP network stack does not - * start IPv6 negotiation and more. - */ - usbnet_link_change(dev, 0, 0); - return ret; + return cdc_ncm_bind_common(dev, intf, CDC_NCM_DATA_ALTSETTING_NCM, 0); } static void cdc_ncm_align_tail(struct sk_buff *skb, size_t modulus, size_t remainder, size_t max) @@ -1554,7 +1543,8 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb) static const struct driver_info cdc_ncm_info = { .description = "CDC NCM", - .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET, + .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET + | FLAG_LINK_INTR, .bind = cdc_ncm_bind, .unbind = cdc_ncm_unbind, .manage_power = usbnet_manage_power, @@ -1567,7 +1557,7 @@ static const struct driver_info cdc_ncm_info = { static const struct driver_info wwan_info = { .description = "Mobile Broadband Network Device", .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET - | FLAG_WWAN, + | FLAG_LINK_INTR | FLAG_WWAN, .bind = cdc_ncm_bind, .unbind = cdc_ncm_unbind, .manage_power = usbnet_manage_power, @@ -1580,7 +1570,7 @@ static const struct driver_info wwan_info = { static const struct driver_info wwan_noarp_info = { .description = "Mobile Broadband Network Device (NO ARP)", .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET - | FLAG_WWAN | FLAG_NOARP, + | FLAG_LINK_INTR | FLAG_WWAN | FLAG_NOARP, .bind = cdc_ncm_bind, .unbind = cdc_ncm_unbind, .manage_power = usbnet_manage_power, diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c index 1029aa7889b5..398ec45aadef 100644 --- a/drivers/pinctrl/freescale/pinctrl-imx.c +++ b/drivers/pinctrl/freescale/pinctrl-imx.c @@ -207,9 +207,9 @@ static int imx_pmx_set(struct pinctrl_dev *pctldev, unsigned selector, pin_reg = &info->pin_regs[pin_id]; if (pin_reg->mux_reg == -1) { - dev_err(ipctl->dev, "Pin(%s) does not support mux function\n", + dev_dbg(ipctl->dev, "Pin(%s) does not support mux function\n", info->pins[pin_id].name); - return -EINVAL; + continue; } if (info->flags & SHARE_MUX_CONF_REG) { diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c index 23b6b8c29a99..73d8d47ea465 100644 --- a/drivers/pinctrl/pinctrl-single.c +++ b/drivers/pinctrl/pinctrl-single.c @@ -1576,6 +1576,9 @@ static inline void pcs_irq_set(struct pcs_soc_data *pcs_soc, else mask &= ~soc_mask; pcs->write(mask, pcswi->reg); + + /* flush posted write */ + mask = pcs->read(pcswi->reg); raw_spin_unlock(&pcs->lock); } diff --git a/drivers/platform/chrome/cros_ec_dev.c b/drivers/platform/chrome/cros_ec_dev.c index d45cd254ed1c..2b331d5b9e79 100644 --- a/drivers/platform/chrome/cros_ec_dev.c +++ b/drivers/platform/chrome/cros_ec_dev.c @@ -147,13 +147,19 @@ static long ec_device_ioctl_xcmd(struct cros_ec_dev *ec, void __user *arg) goto exit; } + if (u_cmd.outsize != s_cmd->outsize || + u_cmd.insize != s_cmd->insize) { + ret = -EINVAL; + goto exit; + } + s_cmd->command += ec->cmd_offset; ret = cros_ec_cmd_xfer(ec->ec_dev, s_cmd); /* Only copy data to userland if data was received. */ if (ret < 0) goto exit; - if (copy_to_user(arg, s_cmd, sizeof(*s_cmd) + u_cmd.insize)) + if (copy_to_user(arg, s_cmd, sizeof(*s_cmd) + s_cmd->insize)) ret = -EFAULT; exit: kfree(s_cmd); diff --git a/drivers/pnp/quirks.c b/drivers/pnp/quirks.c index 943c1cb9566c..d28e3ab9479c 100644 --- a/drivers/pnp/quirks.c +++ b/drivers/pnp/quirks.c @@ -342,7 +342,9 @@ static void quirk_amd_mmconfig_area(struct pnp_dev *dev) /* Device IDs of parts that have 32KB MCH space */ static const unsigned int mch_quirk_devices[] = { 0x0154, /* Ivy Bridge */ + 0x0a04, /* Haswell-ULT */ 0x0c00, /* Haswell */ + 0x1604, /* Broadwell */ }; static struct pci_dev *get_intel_host(void) diff --git a/drivers/power/power_supply_core.c b/drivers/power/power_supply_core.c index 456987c88baa..b13cd074c52a 100644 --- a/drivers/power/power_supply_core.c +++ b/drivers/power/power_supply_core.c @@ -565,11 +565,12 @@ static int power_supply_read_temp(struct thermal_zone_device *tzd, WARN_ON(tzd == NULL); psy = tzd->devdata; - ret = psy->desc->get_property(psy, POWER_SUPPLY_PROP_TEMP, &val); + ret = power_supply_get_property(psy, POWER_SUPPLY_PROP_TEMP, &val); + if (ret) + return ret; /* Convert tenths of degree Celsius to milli degree Celsius. */ - if (!ret) - *temp = val.intval * 100; + *temp = val.intval * 100; return ret; } @@ -612,10 +613,12 @@ static int ps_get_max_charge_cntl_limit(struct thermal_cooling_device *tcd, int ret; psy = tcd->devdata; - ret = psy->desc->get_property(psy, - POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT_MAX, &val); - if (!ret) - *state = val.intval; + ret = power_supply_get_property(psy, + POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT_MAX, &val); + if (ret) + return ret; + + *state = val.intval; return ret; } @@ -628,10 +631,12 @@ static int ps_get_cur_chrage_cntl_limit(struct thermal_cooling_device *tcd, int ret; psy = tcd->devdata; - ret = psy->desc->get_property(psy, - POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT, &val); - if (!ret) - *state = val.intval; + ret = power_supply_get_property(psy, + POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT, &val); + if (ret) + return ret; + + *state = val.intval; return ret; } diff --git a/drivers/pps/clients/pps_parport.c b/drivers/pps/clients/pps_parport.c index 38a8bbe74810..83797d89c30f 100644 --- a/drivers/pps/clients/pps_parport.c +++ b/drivers/pps/clients/pps_parport.c @@ -195,7 +195,7 @@ static void parport_detach(struct parport *port) struct pps_client_pp *device; /* FIXME: oooh, this is ugly! */ - if (strcmp(pardev->name, KBUILD_MODNAME)) + if (!pardev || strcmp(pardev->name, KBUILD_MODNAME)) /* not our port */ return; diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 8f1b091e1732..12b2cb7769f9 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -1051,6 +1051,7 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev) qeth_l2_set_offline(cgdev); if (card->dev) { + netif_napi_del(&card->napi); unregister_netdev(card->dev); card->dev = NULL; } diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 543960e96b42..50cec6b13d27 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -3246,6 +3246,7 @@ static void qeth_l3_remove_device(struct ccwgroup_device *cgdev) qeth_l3_set_offline(cgdev); if (card->dev) { + netif_napi_del(&card->napi); unregister_netdev(card->dev); card->dev = NULL; } diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index 43ac62623bf2..7a58128a0000 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -10095,6 +10095,7 @@ static int ipr_probe_ioa(struct pci_dev *pdev, ioa_cfg->intr_flag = IPR_USE_MSI; else { ioa_cfg->intr_flag = IPR_USE_LSI; + ioa_cfg->clear_isr = 1; ioa_cfg->nvectors = 1; dev_info(&pdev->dev, "Cannot enable MSI.\n"); } diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c index 93cbefa75b26..11cdb172cfaf 100644 --- a/drivers/scsi/scsi_devinfo.c +++ b/drivers/scsi/scsi_devinfo.c @@ -426,7 +426,7 @@ static struct scsi_dev_info_list *scsi_dev_info_list_find(const char *vendor, * here, and we don't know what device it is * trying to work with, leave it as-is. */ - vmax = 8; /* max length of vendor */ + vmax = sizeof(devinfo->vendor); vskip = vendor; while (vmax > 0 && *vskip == ' ') { vmax--; @@ -436,7 +436,7 @@ static struct scsi_dev_info_list *scsi_dev_info_list_find(const char *vendor, while (vmax > 0 && vskip[vmax - 1] == ' ') --vmax; - mmax = 16; /* max length of model */ + mmax = sizeof(devinfo->model); mskip = model; while (mmax > 0 && *mskip == ' ') { mmax--; @@ -452,10 +452,12 @@ static struct scsi_dev_info_list *scsi_dev_info_list_find(const char *vendor, * Behave like the older version of get_device_flags. */ if (memcmp(devinfo->vendor, vskip, vmax) || - devinfo->vendor[vmax]) + (vmax < sizeof(devinfo->vendor) && + devinfo->vendor[vmax])) continue; if (memcmp(devinfo->model, mskip, mmax) || - devinfo->model[mmax]) + (mmax < sizeof(devinfo->model) && + devinfo->model[mmax])) continue; return devinfo; } else { diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index f7ae898833dd..7232d43e2207 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -1058,11 +1058,12 @@ int scsi_sysfs_add_sdev(struct scsi_device *sdev) } error = scsi_dh_add_device(sdev); - if (error) { + if (error) + /* + * device_handler is optional, so any error can be ignored + */ sdev_printk(KERN_INFO, sdev, "failed to add device handler: %d\n", error); - return error; - } device_enable_async_suspend(&sdev->sdev_dev); error = device_add(&sdev->sdev_dev); diff --git a/drivers/spi/spi-sun4i.c b/drivers/spi/spi-sun4i.c index fbb0a4d74e91..39d7c7c70112 100644 --- a/drivers/spi/spi-sun4i.c +++ b/drivers/spi/spi-sun4i.c @@ -170,13 +170,17 @@ static int sun4i_spi_transfer_one(struct spi_master *master, { struct sun4i_spi *sspi = spi_master_get_devdata(master); unsigned int mclk_rate, div, timeout; + unsigned int start, end, tx_time; unsigned int tx_len = 0; int ret = 0; u32 reg; /* We don't support transfer larger than the FIFO */ if (tfr->len > SUN4I_FIFO_DEPTH) - return -EINVAL; + return -EMSGSIZE; + + if (tfr->tx_buf && tfr->len >= SUN4I_FIFO_DEPTH) + return -EMSGSIZE; reinit_completion(&sspi->done); sspi->tx_buf = tfr->tx_buf; @@ -269,8 +273,12 @@ static int sun4i_spi_transfer_one(struct spi_master *master, sun4i_spi_write(sspi, SUN4I_BURST_CNT_REG, SUN4I_BURST_CNT(tfr->len)); sun4i_spi_write(sspi, SUN4I_XMIT_CNT_REG, SUN4I_XMIT_CNT(tx_len)); - /* Fill the TX FIFO */ - sun4i_spi_fill_fifo(sspi, SUN4I_FIFO_DEPTH); + /* + * Fill the TX FIFO + * Filling the FIFO fully causes timeout for some reason + * at least on spi2 on A10s + */ + sun4i_spi_fill_fifo(sspi, SUN4I_FIFO_DEPTH - 1); /* Enable the interrupts */ sun4i_spi_write(sspi, SUN4I_INT_CTL_REG, SUN4I_INT_CTL_TC); @@ -279,9 +287,16 @@ static int sun4i_spi_transfer_one(struct spi_master *master, reg = sun4i_spi_read(sspi, SUN4I_CTL_REG); sun4i_spi_write(sspi, SUN4I_CTL_REG, reg | SUN4I_CTL_XCH); + tx_time = max(tfr->len * 8 * 2 / (tfr->speed_hz / 1000), 100U); + start = jiffies; timeout = wait_for_completion_timeout(&sspi->done, - msecs_to_jiffies(1000)); + msecs_to_jiffies(tx_time)); + end = jiffies; if (!timeout) { + dev_warn(&master->dev, + "%s: timeout transferring %u bytes@%iHz for %i(%i)ms", + dev_name(&spi->dev), tfr->len, tfr->speed_hz, + jiffies_to_msecs(end - start), tx_time); ret = -ETIMEDOUT; goto out; } diff --git a/drivers/spi/spi-sun6i.c b/drivers/spi/spi-sun6i.c index ac48f59705a8..e77add01b0e9 100644 --- a/drivers/spi/spi-sun6i.c +++ b/drivers/spi/spi-sun6i.c @@ -160,6 +160,7 @@ static int sun6i_spi_transfer_one(struct spi_master *master, { struct sun6i_spi *sspi = spi_master_get_devdata(master); unsigned int mclk_rate, div, timeout; + unsigned int start, end, tx_time; unsigned int tx_len = 0; int ret = 0; u32 reg; @@ -269,9 +270,16 @@ static int sun6i_spi_transfer_one(struct spi_master *master, reg = sun6i_spi_read(sspi, SUN6I_TFR_CTL_REG); sun6i_spi_write(sspi, SUN6I_TFR_CTL_REG, reg | SUN6I_TFR_CTL_XCH); + tx_time = max(tfr->len * 8 * 2 / (tfr->speed_hz / 1000), 100U); + start = jiffies; timeout = wait_for_completion_timeout(&sspi->done, - msecs_to_jiffies(1000)); + msecs_to_jiffies(tx_time)); + end = jiffies; if (!timeout) { + dev_warn(&master->dev, + "%s: timeout transferring %u bytes@%iHz for %i(%i)ms", + dev_name(&spi->dev), tfr->len, tfr->speed_hz, + jiffies_to_msecs(end - start), tx_time); ret = -ETIMEDOUT; goto out; } diff --git a/drivers/staging/rdma/ipath/ipath_file_ops.c b/drivers/staging/rdma/ipath/ipath_file_ops.c index 13c3cd11ab92..05d30f433b19 100644 --- a/drivers/staging/rdma/ipath/ipath_file_ops.c +++ b/drivers/staging/rdma/ipath/ipath_file_ops.c @@ -45,6 +45,8 @@ #include <linux/uio.h> #include <asm/pgtable.h> +#include <rdma/ib.h> + #include "ipath_kernel.h" #include "ipath_common.h" #include "ipath_user_sdma.h" @@ -2243,6 +2245,9 @@ static ssize_t ipath_write(struct file *fp, const char __user *data, ssize_t ret = 0; void *dest; + if (WARN_ON_ONCE(!ib_safe_file_access(fp))) + return -EACCES; + if (count < sizeof(cmd.type)) { ret = -EINVAL; goto bail; diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index 7865228f664f..807d80145686 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -679,14 +679,14 @@ static void pty_unix98_remove(struct tty_driver *driver, struct tty_struct *tty) /* this is called once with whichever end is closed last */ static void pty_unix98_shutdown(struct tty_struct *tty) { - struct inode *ptmx_inode; + struct pts_fs_info *fsi; if (tty->driver->subtype == PTY_TYPE_MASTER) - ptmx_inode = tty->driver_data; + fsi = tty->driver_data; else - ptmx_inode = tty->link->driver_data; - devpts_kill_index(ptmx_inode, tty->index); - devpts_del_ref(ptmx_inode); + fsi = tty->link->driver_data; + devpts_kill_index(fsi, tty->index); + devpts_put_ref(fsi); } static const struct tty_operations ptm_unix98_ops = { @@ -738,6 +738,7 @@ static const struct tty_operations pty_unix98_ops = { static int ptmx_open(struct inode *inode, struct file *filp) { + struct pts_fs_info *fsi; struct tty_struct *tty; struct inode *slave_inode; int retval; @@ -752,47 +753,41 @@ static int ptmx_open(struct inode *inode, struct file *filp) if (retval) return retval; + fsi = devpts_get_ref(inode, filp); + retval = -ENODEV; + if (!fsi) + goto out_free_file; + /* find a device that is not in use. */ mutex_lock(&devpts_mutex); - index = devpts_new_index(inode); - if (index < 0) { - retval = index; - mutex_unlock(&devpts_mutex); - goto err_file; - } - + index = devpts_new_index(fsi); mutex_unlock(&devpts_mutex); - mutex_lock(&tty_mutex); - tty = tty_init_dev(ptm_driver, index); + retval = index; + if (index < 0) + goto out_put_ref; - if (IS_ERR(tty)) { - retval = PTR_ERR(tty); - goto out; - } + mutex_lock(&tty_mutex); + tty = tty_init_dev(ptm_driver, index); /* The tty returned here is locked so we can safely drop the mutex */ mutex_unlock(&tty_mutex); - set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */ - tty->driver_data = inode; + retval = PTR_ERR(tty); + if (IS_ERR(tty)) + goto out; /* - * In the case where all references to ptmx inode are dropped and we - * still have /dev/tty opened pointing to the master/slave pair (ptmx - * is closed/released before /dev/tty), we must make sure that the inode - * is still valid when we call the final pty_unix98_shutdown, thus we - * hold an additional reference to the ptmx inode. For the same /dev/tty - * last close case, we also need to make sure the super_block isn't - * destroyed (devpts instance unmounted), before /dev/tty is closed and - * on its release devpts_kill_index is called. + * From here on out, the tty is "live", and the index and + * fsi will be killed/put by the tty_release() */ - devpts_add_ref(inode); + set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */ + tty->driver_data = fsi; tty_add_file(tty, filp); - slave_inode = devpts_pty_new(inode, + slave_inode = devpts_pty_new(fsi, MKDEV(UNIX98_PTY_SLAVE_MAJOR, index), index, tty->link); if (IS_ERR(slave_inode)) { @@ -811,12 +806,14 @@ static int ptmx_open(struct inode *inode, struct file *filp) return 0; err_release: tty_unlock(tty); + // This will also put-ref the fsi tty_release(inode, filp); return retval; out: - mutex_unlock(&tty_mutex); - devpts_kill_index(inode, index); -err_file: + devpts_kill_index(fsi, index); +out_put_ref: + devpts_put_ref(fsi); +out_free_file: tty_free_file(filp); return retval; } diff --git a/drivers/usb/host/ohci-q.c b/drivers/usb/host/ohci-q.c index d029bbe9eb36..641fed609911 100644 --- a/drivers/usb/host/ohci-q.c +++ b/drivers/usb/host/ohci-q.c @@ -183,7 +183,6 @@ static int ed_schedule (struct ohci_hcd *ohci, struct ed *ed) { int branch; - ed->state = ED_OPER; ed->ed_prev = NULL; ed->ed_next = NULL; ed->hwNextED = 0; @@ -259,6 +258,8 @@ static int ed_schedule (struct ohci_hcd *ohci, struct ed *ed) /* the HC may not see the schedule updates yet, but if it does * then they'll be properly ordered. */ + + ed->state = ED_OPER; return 0; } diff --git a/drivers/xen/xen-pciback/conf_space.c b/drivers/xen/xen-pciback/conf_space.c index 9c234209d8b5..47a4177b16d2 100644 --- a/drivers/xen/xen-pciback/conf_space.c +++ b/drivers/xen/xen-pciback/conf_space.c @@ -183,8 +183,7 @@ int xen_pcibk_config_read(struct pci_dev *dev, int offset, int size, field_start = OFFSET(cfg_entry); field_end = OFFSET(cfg_entry) + field->size; - if ((req_start >= field_start && req_start < field_end) - || (req_end > field_start && req_end <= field_end)) { + if (req_end > field_start && field_end > req_start) { err = conf_space_read(dev, cfg_entry, field_start, &tmp_val); if (err) @@ -230,8 +229,7 @@ int xen_pcibk_config_write(struct pci_dev *dev, int offset, int size, u32 value) field_start = OFFSET(cfg_entry); field_end = OFFSET(cfg_entry) + field->size; - if ((req_start >= field_start && req_start < field_end) - || (req_end > field_start && req_end <= field_end)) { + if (req_end > field_start && field_end > req_start) { tmp_val = 0; err = xen_pcibk_config_read(dev, field_start, diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index 9433e46518c8..531e76474983 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -316,11 +316,18 @@ static int xenbus_write_transaction(unsigned msg_type, rc = -ENOMEM; goto out; } + } else { + list_for_each_entry(trans, &u->transactions, list) + if (trans->handle.id == u->u.msg.tx_id) + break; + if (&trans->list == &u->transactions) + return -ESRCH; } reply = xenbus_dev_request_and_reply(&u->u.msg); if (IS_ERR(reply)) { - kfree(trans); + if (msg_type == XS_TRANSACTION_START) + kfree(trans); rc = PTR_ERR(reply); goto out; } @@ -333,12 +340,7 @@ static int xenbus_write_transaction(unsigned msg_type, list_add(&trans->list, &u->transactions); } } else if (u->u.msg.type == XS_TRANSACTION_END) { - list_for_each_entry(trans, &u->transactions, list) - if (trans->handle.id == u->u.msg.tx_id) - break; - BUG_ON(&trans->list == &u->transactions); list_del(&trans->list); - kfree(trans); } diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c index ba804f3d8278..ce65591b4168 100644 --- a/drivers/xen/xenbus/xenbus_xs.c +++ b/drivers/xen/xenbus/xenbus_xs.c @@ -250,9 +250,6 @@ void *xenbus_dev_request_and_reply(struct xsd_sockmsg *msg) mutex_unlock(&xs_state.request_mutex); - if (IS_ERR(ret)) - return ret; - if ((msg->type == XS_TRANSACTION_END) || ((req_msg.type == XS_TRANSACTION_START) && (msg->type == XS_ERROR))) diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 7bf835f85bc8..12ceaf52dae6 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -74,7 +74,7 @@ int v9fs_file_open(struct inode *inode, struct file *file) v9fs_proto_dotu(v9ses)); fid = file->private_data; if (!fid) { - fid = v9fs_fid_clone(file->f_path.dentry); + fid = v9fs_fid_clone(file_dentry(file)); if (IS_ERR(fid)) return PTR_ERR(fid); @@ -100,7 +100,7 @@ int v9fs_file_open(struct inode *inode, struct file *file) * because we want write after unlink usecase * to work. */ - fid = v9fs_writeback_fid(file->f_path.dentry); + fid = v9fs_writeback_fid(file_dentry(file)); if (IS_ERR(fid)) { err = PTR_ERR(fid); mutex_unlock(&v9inode->v_mutex); @@ -516,7 +516,7 @@ v9fs_mmap_file_mmap(struct file *filp, struct vm_area_struct *vma) * because we want write after unlink usecase * to work. */ - fid = v9fs_writeback_fid(filp->f_path.dentry); + fid = v9fs_writeback_fid(file_dentry(filp)); if (IS_ERR(fid)) { retval = PTR_ERR(fid); mutex_unlock(&v9inode->v_mutex); diff --git a/fs/dcache.c b/fs/dcache.c index 108d7d810be3..71b6056ad35d 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -578,7 +578,6 @@ static struct dentry *dentry_kill(struct dentry *dentry) failed: spin_unlock(&dentry->d_lock); - cpu_relax(); return dentry; /* try again with same dentry */ } @@ -752,6 +751,8 @@ void dput(struct dentry *dentry) return; repeat: + might_sleep(); + rcu_read_lock(); if (likely(fast_dput(dentry))) { rcu_read_unlock(); @@ -783,8 +784,10 @@ repeat: kill_it: dentry = dentry_kill(dentry); - if (dentry) + if (dentry) { + cond_resched(); goto repeat; + } } EXPORT_SYMBOL(dput); diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 706de324f2a6..c82edb049117 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -128,6 +128,7 @@ static const match_table_t tokens = { struct pts_fs_info { struct ida allocated_ptys; struct pts_mount_opts mount_opts; + struct super_block *sb; struct dentry *ptmx_dentry; }; @@ -358,7 +359,7 @@ static const struct super_operations devpts_sops = { .show_options = devpts_show_options, }; -static void *new_pts_fs_info(void) +static void *new_pts_fs_info(struct super_block *sb) { struct pts_fs_info *fsi; @@ -369,6 +370,7 @@ static void *new_pts_fs_info(void) ida_init(&fsi->allocated_ptys); fsi->mount_opts.mode = DEVPTS_DEFAULT_MODE; fsi->mount_opts.ptmxmode = DEVPTS_DEFAULT_PTMX_MODE; + fsi->sb = sb; return fsi; } @@ -384,7 +386,7 @@ devpts_fill_super(struct super_block *s, void *data, int silent) s->s_op = &devpts_sops; s->s_time_gran = 1; - s->s_fs_info = new_pts_fs_info(); + s->s_fs_info = new_pts_fs_info(s); if (!s->s_fs_info) goto fail; @@ -524,17 +526,14 @@ static struct file_system_type devpts_fs_type = { * to the System V naming convention */ -int devpts_new_index(struct inode *ptmx_inode) +int devpts_new_index(struct pts_fs_info *fsi) { - struct super_block *sb = pts_sb_from_inode(ptmx_inode); - struct pts_fs_info *fsi; int index; int ida_ret; - if (!sb) + if (!fsi) return -ENODEV; - fsi = DEVPTS_SB(sb); retry: if (!ida_pre_get(&fsi->allocated_ptys, GFP_KERNEL)) return -ENOMEM; @@ -564,11 +563,8 @@ retry: return index; } -void devpts_kill_index(struct inode *ptmx_inode, int idx) +void devpts_kill_index(struct pts_fs_info *fsi, int idx) { - struct super_block *sb = pts_sb_from_inode(ptmx_inode); - struct pts_fs_info *fsi = DEVPTS_SB(sb); - mutex_lock(&allocated_ptys_lock); ida_remove(&fsi->allocated_ptys, idx); pty_count--; @@ -578,21 +574,25 @@ void devpts_kill_index(struct inode *ptmx_inode, int idx) /* * pty code needs to hold extra references in case of last /dev/tty close */ - -void devpts_add_ref(struct inode *ptmx_inode) +struct pts_fs_info *devpts_get_ref(struct inode *ptmx_inode, struct file *file) { - struct super_block *sb = pts_sb_from_inode(ptmx_inode); + struct super_block *sb; + struct pts_fs_info *fsi; + + sb = pts_sb_from_inode(ptmx_inode); + if (!sb) + return NULL; + fsi = DEVPTS_SB(sb); + if (!fsi) + return NULL; atomic_inc(&sb->s_active); - ihold(ptmx_inode); + return fsi; } -void devpts_del_ref(struct inode *ptmx_inode) +void devpts_put_ref(struct pts_fs_info *fsi) { - struct super_block *sb = pts_sb_from_inode(ptmx_inode); - - iput(ptmx_inode); - deactivate_super(sb); + deactivate_super(fsi->sb); } /** @@ -604,22 +604,21 @@ void devpts_del_ref(struct inode *ptmx_inode) * * The created inode is returned. Remove it from /dev/pts/ by devpts_pty_kill. */ -struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index, +struct inode *devpts_pty_new(struct pts_fs_info *fsi, dev_t device, int index, void *priv) { struct dentry *dentry; - struct super_block *sb = pts_sb_from_inode(ptmx_inode); + struct super_block *sb; struct inode *inode; struct dentry *root; - struct pts_fs_info *fsi; struct pts_mount_opts *opts; char s[12]; - if (!sb) + if (!fsi) return ERR_PTR(-ENODEV); + sb = fsi->sb; root = sb->s_root; - fsi = DEVPTS_SB(sb); opts = &fsi->mount_opts; inode = new_inode(sb); diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index feef8a9c4de7..11309683d65f 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -170,6 +170,19 @@ out: return rc; } +static int ecryptfs_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct file *lower_file = ecryptfs_file_to_lower(file); + /* + * Don't allow mmap on top of file systems that don't support it + * natively. If FILESYSTEM_MAX_STACK_DEPTH > 2 or ecryptfs + * allows recursive mounting, this will need to be extended. + */ + if (!lower_file->f_op->mmap) + return -ENODEV; + return generic_file_mmap(file, vma); +} + /** * ecryptfs_open * @inode: inode speciying file to open @@ -364,7 +377,7 @@ const struct file_operations ecryptfs_main_fops = { #ifdef CONFIG_COMPAT .compat_ioctl = ecryptfs_compat_ioctl, #endif - .mmap = generic_file_mmap, + .mmap = ecryptfs_mmap, .open = ecryptfs_open, .flush = ecryptfs_flush, .release = ecryptfs_release, diff --git a/fs/ecryptfs/kthread.c b/fs/ecryptfs/kthread.c index e818f5ac7a26..866bb18efefe 100644 --- a/fs/ecryptfs/kthread.c +++ b/fs/ecryptfs/kthread.c @@ -25,7 +25,6 @@ #include <linux/slab.h> #include <linux/wait.h> #include <linux/mount.h> -#include <linux/file.h> #include "ecryptfs_kernel.h" struct ecryptfs_open_req { @@ -148,7 +147,7 @@ int ecryptfs_privileged_open(struct file **lower_file, flags |= IS_RDONLY(d_inode(lower_dentry)) ? O_RDONLY : O_RDWR; (*lower_file) = dentry_open(&req.path, flags, cred); if (!IS_ERR(*lower_file)) - goto have_file; + goto out; if ((flags & O_ACCMODE) == O_RDONLY) { rc = PTR_ERR((*lower_file)); goto out; @@ -166,16 +165,8 @@ int ecryptfs_privileged_open(struct file **lower_file, mutex_unlock(&ecryptfs_kthread_ctl.mux); wake_up(&ecryptfs_kthread_ctl.wait); wait_for_completion(&req.done); - if (IS_ERR(*lower_file)) { + if (IS_ERR(*lower_file)) rc = PTR_ERR(*lower_file); - goto out; - } -have_file: - if ((*lower_file)->f_op->mmap == NULL) { - fput(*lower_file); - *lower_file = NULL; - rc = -EMEDIUMTYPE; - } out: return rc; } diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index fe1f50fe764f..f97110461c19 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -208,6 +208,9 @@ static int ext4_init_block_bitmap(struct super_block *sb, memset(bh->b_data, 0, sb->s_blocksize); bit_max = ext4_num_base_meta_clusters(sb, block_group); + if ((bit_max >> 3) >= bh->b_size) + return -EFSCORRUPTED; + for (bit = 0; bit < bit_max; bit++) ext4_set_bit(bit, bh->b_data); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 3578b25fccfd..8eac7d586997 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -376,9 +376,13 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext) ext4_fsblk_t block = ext4_ext_pblock(ext); int len = ext4_ext_get_actual_len(ext); ext4_lblk_t lblock = le32_to_cpu(ext->ee_block); - ext4_lblk_t last = lblock + len - 1; - if (len == 0 || lblock > last) + /* + * We allow neither: + * - zero length + * - overflow/wrap-around + */ + if (lblock + len <= lblock) return 0; return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len); } @@ -469,6 +473,10 @@ static int __ext4_ext_check(const char *function, unsigned int line, error_msg = "invalid extent entries"; goto corrupted; } + if (unlikely(depth > 32)) { + error_msg = "too large eh_depth"; + goto corrupted; + } /* Verify checksum on non-root extent tree nodes */ if (ext_depth(inode) != depth && !ext4_extent_block_csum_verify(inode, eh)) { diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index e31d762eedce..9a5ad0f0d3ed 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -205,9 +205,9 @@ void ext4_evict_inode(struct inode *inode) * Note that directories do not have this problem because they * don't use page cache. */ - if (ext4_should_journal_data(inode) && - (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) && - inode->i_ino != EXT4_JOURNAL_INO) { + if (inode->i_ino != EXT4_JOURNAL_INO && + ext4_should_journal_data(inode) && + (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) { journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; tid_t commit_tid = EXT4_I(inode)->i_datasync_tid; @@ -2589,13 +2589,36 @@ retry: done = true; } } - ext4_journal_stop(handle); + /* + * Caution: If the handle is synchronous, + * ext4_journal_stop() can wait for transaction commit + * to finish which may depend on writeback of pages to + * complete or on page lock to be released. In that + * case, we have to wait until after after we have + * submitted all the IO, released page locks we hold, + * and dropped io_end reference (for extent conversion + * to be able to complete) before stopping the handle. + */ + if (!ext4_handle_valid(handle) || handle->h_sync == 0) { + ext4_journal_stop(handle); + handle = NULL; + } /* Submit prepared bio */ ext4_io_submit(&mpd.io_submit); /* Unlock pages we didn't use */ mpage_release_unused_pages(&mpd, give_up_on_write); - /* Drop our io_end reference we got from init */ - ext4_put_io_end(mpd.io_submit.io_end); + /* + * Drop our io_end reference we got from init. We have + * to be careful and use deferred io_end finishing if + * we are still holding the transaction as we can + * release the last reference to io_end which may end + * up doing unwritten extent conversion. + */ + if (handle) { + ext4_put_io_end_defer(mpd.io_submit.io_end); + ext4_journal_stop(handle); + } else + ext4_put_io_end(mpd.io_submit.io_end); if (ret == -ENOSPC && sbi->s_journal) { /* diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index cf734170daa9..c4dcac8a018d 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2932,7 +2932,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, ext4_error(sb, "Allocating blocks %llu-%llu which overlap " "fs metadata", block, block+len); /* File system mounted not to panic on error - * Fix the bitmap and repeat the block allocation + * Fix the bitmap and return EFSCORRUPTED * We leak some of the blocks here. */ ext4_lock_group(sb, ac->ac_b_ex.fe_group); @@ -2941,7 +2941,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, ext4_unlock_group(sb, ac->ac_b_ex.fe_group); err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); if (!err) - err = -EAGAIN; + err = -EFSCORRUPTED; goto out_err; } @@ -4506,18 +4506,7 @@ repeat: } if (likely(ac->ac_status == AC_STATUS_FOUND)) { *errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_clstrs); - if (*errp == -EAGAIN) { - /* - * drop the reference that we took - * in ext4_mb_use_best_found - */ - ext4_mb_release_context(ac); - ac->ac_b_ex.fe_group = 0; - ac->ac_b_ex.fe_start = 0; - ac->ac_b_ex.fe_len = 0; - ac->ac_status = AC_STATUS_CONTINUE; - goto repeat; - } else if (*errp) { + if (*errp) { ext4_discard_allocated_blocks(ac); goto errout; } else { diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 852c26806af2..c542ebcf7a92 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2240,6 +2240,16 @@ static void ext4_orphan_cleanup(struct super_block *sb, while (es->s_last_orphan) { struct inode *inode; + /* + * We may have encountered an error during cleanup; if + * so, skip the rest. + */ + if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) { + jbd_debug(1, "Skipping orphan recovery on fs with errors.\n"); + es->s_last_orphan = 0; + break; + } + inode = ext4_orphan_get(sb, le32_to_cpu(es->s_last_orphan)); if (IS_ERR(inode)) { es->s_last_orphan = 0; @@ -3372,6 +3382,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } + if (le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) > (blocksize / 4)) { + ext4_msg(sb, KERN_ERR, + "Number of reserved GDT blocks insanely large: %d", + le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks)); + goto failed_mount; + } + if (sbi->s_mount_opt & EXT4_MOUNT_DAX) { if (blocksize != PAGE_SIZE) { ext4_msg(sb, KERN_ERR, diff --git a/fs/fuse/file.c b/fs/fuse/file.c index c2e340d6ec6e..d58d4c0af0ce 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -417,6 +417,15 @@ static int fuse_flush(struct file *file, fl_owner_t id) fuse_sync_writes(inode); mutex_unlock(&inode->i_mutex); + if (test_bit(AS_ENOSPC, &file->f_mapping->flags) && + test_and_clear_bit(AS_ENOSPC, &file->f_mapping->flags)) + err = -ENOSPC; + if (test_bit(AS_EIO, &file->f_mapping->flags) && + test_and_clear_bit(AS_EIO, &file->f_mapping->flags)) + err = -EIO; + if (err) + return err; + req = fuse_get_req_nofail_nopages(fc, file); memset(&inarg, 0, sizeof(inarg)); inarg.fh = ff->fh; @@ -462,6 +471,21 @@ int fuse_fsync_common(struct file *file, loff_t start, loff_t end, goto out; fuse_sync_writes(inode); + + /* + * Due to implementation of fuse writeback + * filemap_write_and_wait_range() does not catch errors. + * We have to do this directly after fuse_sync_writes() + */ + if (test_bit(AS_ENOSPC, &file->f_mapping->flags) && + test_and_clear_bit(AS_ENOSPC, &file->f_mapping->flags)) + err = -ENOSPC; + if (test_bit(AS_EIO, &file->f_mapping->flags) && + test_and_clear_bit(AS_EIO, &file->f_mapping->flags)) + err = -EIO; + if (err) + goto out; + err = sync_inode_metadata(inode, 1); if (err) goto out; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 2913db2a5b99..0d5e8e59b390 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -926,7 +926,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req) arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC | FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK | FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ | - FUSE_FLOCK_LOCKS | FUSE_IOCTL_DIR | FUSE_AUTO_INVAL_DATA | + FUSE_FLOCK_LOCKS | FUSE_HAS_IOCTL_DIR | FUSE_AUTO_INVAL_DATA | FUSE_DO_READDIRPLUS | FUSE_READDIRPLUS_AUTO | FUSE_ASYNC_DIO | FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT; req->in.h.opcode = FUSE_INIT; diff --git a/fs/inode.c b/fs/inode.c index 1be5f9003eb3..b0edef500590 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1733,8 +1733,8 @@ static int __remove_privs(struct dentry *dentry, int kill) */ int file_remove_privs(struct file *file) { - struct dentry *dentry = file->f_path.dentry; - struct inode *inode = d_inode(dentry); + struct dentry *dentry = file_dentry(file); + struct inode *inode = file_inode(file); int kill; int error = 0; @@ -1742,7 +1742,7 @@ int file_remove_privs(struct file *file) if (IS_NOSEC(inode)) return 0; - kill = file_needs_remove_privs(file); + kill = dentry_needs_remove_privs(dentry); if (kill < 0) return kill; if (kill) diff --git a/fs/locks.c b/fs/locks.c index 6333263b7bc8..8eddae23e10b 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1602,7 +1602,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr { struct file_lock *fl, *my_fl = NULL, *lease; struct dentry *dentry = filp->f_path.dentry; - struct inode *inode = dentry->d_inode; + struct inode *inode = file_inode(filp); struct file_lock_context *ctx; bool is_deleg = (*flp)->fl_flags & FL_DELEG; int error; diff --git a/fs/namespace.c b/fs/namespace.c index 33064fcbfff9..5be02a0635be 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1562,6 +1562,7 @@ void __detach_mounts(struct dentry *dentry) goto out_unlock; lock_mount_hash(); + event++; while (!hlist_empty(&mp->m_list)) { mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list); if (mnt->mnt.mnt_flags & MNT_UMOUNT) { diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 69bd801afb53..37e49cb2ac4c 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -443,7 +443,7 @@ static int nilfs_valid_sb(struct nilfs_super_block *sbp) if (!sbp || le16_to_cpu(sbp->s_magic) != NILFS_SUPER_MAGIC) return 0; bytes = le16_to_cpu(sbp->s_bytes); - if (bytes > BLOCK_SIZE) + if (bytes < sumoff + 4 || bytes > BLOCK_SIZE) return 0; crc = crc32_le(le32_to_cpu(sbp->s_crc_seed), (unsigned char *)sbp, sumoff); diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 0597820f5d9d..4f729ffff75d 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -63,6 +63,9 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr) if (!err) { upperdentry = ovl_dentry_upper(dentry); + if (attr->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) + attr->ia_valid &= ~ATTR_MODE; + mutex_lock(&upperdentry->d_inode->i_mutex); err = notify_change(upperdentry, attr, NULL); if (!err) diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index c4bd0e2c173c..ef2e8c97e183 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -531,15 +531,19 @@ #define INIT_TEXT \ *(.init.text) \ + *(.text.startup) \ MEM_DISCARD(init.text) #define EXIT_DATA \ *(.exit.data) \ + *(.fini_array) \ + *(.dtors) \ MEM_DISCARD(exit.data) \ MEM_DISCARD(exit.rodata) #define EXIT_TEXT \ *(.exit.text) \ + *(.text.exit) \ MEM_DISCARD(exit.text) #define EXIT_CALL \ diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 3feb1b2d75d8..14cd6f77e284 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -156,6 +156,7 @@ struct bcma_host_ops { #define BCMA_CORE_DEFAULT 0xFFF #define BCMA_MAX_NR_CORES 16 +#define BCMA_CORE_SIZE 0x1000 /* Chip IDs of PCIe devices */ #define BCMA_CHIP_ID_BCM4313 0x4313 diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h index e0ee0b3000b2..358a4db72a27 100644 --- a/include/linux/devpts_fs.h +++ b/include/linux/devpts_fs.h @@ -15,38 +15,24 @@ #include <linux/errno.h> +struct pts_fs_info; + #ifdef CONFIG_UNIX98_PTYS -int devpts_new_index(struct inode *ptmx_inode); -void devpts_kill_index(struct inode *ptmx_inode, int idx); -void devpts_add_ref(struct inode *ptmx_inode); -void devpts_del_ref(struct inode *ptmx_inode); +/* Look up a pts fs info and get a ref to it */ +struct pts_fs_info *devpts_get_ref(struct inode *, struct file *); +void devpts_put_ref(struct pts_fs_info *); + +int devpts_new_index(struct pts_fs_info *); +void devpts_kill_index(struct pts_fs_info *, int); + /* mknod in devpts */ -struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index, - void *priv); +struct inode *devpts_pty_new(struct pts_fs_info *, dev_t, int, void *); /* get private structure */ void *devpts_get_priv(struct inode *pts_inode); /* unlink */ void devpts_pty_kill(struct inode *inode); -#else - -/* Dummy stubs in the no-pty case */ -static inline int devpts_new_index(struct inode *ptmx_inode) { return -EINVAL; } -static inline void devpts_kill_index(struct inode *ptmx_inode, int idx) { } -static inline void devpts_add_ref(struct inode *ptmx_inode) { } -static inline void devpts_del_ref(struct inode *ptmx_inode) { } -static inline struct inode *devpts_pty_new(struct inode *ptmx_inode, - dev_t device, int index, void *priv) -{ - return ERR_PTR(-EINVAL); -} -static inline void *devpts_get_priv(struct inode *pts_inode) -{ - return NULL; -} -static inline void devpts_pty_kill(struct inode *inode) { } - #endif diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index cd0e2413c358..435fd8426b8a 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -174,6 +174,11 @@ struct mem_cgroup_thresholds { struct mem_cgroup_threshold_ary *spare; }; +struct mem_cgroup_id { + int id; + atomic_t ref; +}; + /* * The memory controller data structure. The memory controller controls both * page cache and RSS per cgroup. We would eventually like to provide @@ -183,6 +188,9 @@ struct mem_cgroup_thresholds { struct mem_cgroup { struct cgroup_subsys_state css; + /* Private memcg ID. Used to ID objects that outlive the cgroup */ + struct mem_cgroup_id id; + /* Accounted resources */ struct page_counter memory; struct page_counter memsw; diff --git a/ipc/msg.c b/ipc/msg.c index 1471db9a7e61..c6521c205cb4 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -680,7 +680,7 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext, rcu_read_lock(); ipc_lock_object(&msq->q_perm); - ipc_rcu_putref(msq, ipc_rcu_free); + ipc_rcu_putref(msq, msg_rcu_free); /* raced with RMID? */ if (!ipc_valid_object(&msq->q_perm)) { err = -EIDRM; diff --git a/ipc/sem.c b/ipc/sem.c index b471e5a3863d..20d07008ad5e 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -442,7 +442,7 @@ static inline struct sem_array *sem_obtain_object_check(struct ipc_namespace *ns static inline void sem_lock_and_putref(struct sem_array *sma) { sem_lock(sma, NULL, -1); - ipc_rcu_putref(sma, ipc_rcu_free); + ipc_rcu_putref(sma, sem_rcu_free); } static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s) @@ -1385,7 +1385,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, rcu_read_unlock(); sem_io = ipc_alloc(sizeof(ushort)*nsems); if (sem_io == NULL) { - ipc_rcu_putref(sma, ipc_rcu_free); + ipc_rcu_putref(sma, sem_rcu_free); return -ENOMEM; } @@ -1419,20 +1419,20 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, if (nsems > SEMMSL_FAST) { sem_io = ipc_alloc(sizeof(ushort)*nsems); if (sem_io == NULL) { - ipc_rcu_putref(sma, ipc_rcu_free); + ipc_rcu_putref(sma, sem_rcu_free); return -ENOMEM; } } if (copy_from_user(sem_io, p, nsems*sizeof(ushort))) { - ipc_rcu_putref(sma, ipc_rcu_free); + ipc_rcu_putref(sma, sem_rcu_free); err = -EFAULT; goto out_free; } for (i = 0; i < nsems; i++) { if (sem_io[i] > SEMVMX) { - ipc_rcu_putref(sma, ipc_rcu_free); + ipc_rcu_putref(sma, sem_rcu_free); err = -ERANGE; goto out_free; } @@ -1722,7 +1722,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid) /* step 2: allocate new undo structure */ new = kzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL); if (!new) { - ipc_rcu_putref(sma, ipc_rcu_free); + ipc_rcu_putref(sma, sem_rcu_free); return ERR_PTR(-ENOMEM); } diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 1c9d701f7a72..a3424f28aaf4 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -4793,6 +4793,7 @@ static void init_and_link_css(struct cgroup_subsys_state *css, memset(css, 0, sizeof(*css)); css->cgroup = cgrp; css->ss = ss; + css->id = -1; INIT_LIST_HEAD(&css->sibling); INIT_LIST_HEAD(&css->children); css->serial_nr = css_serial_nr_next++; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 6c0cdb5a73f8..67d1e1597d9c 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4951,14 +4951,16 @@ void show_state_filter(unsigned long state_filter) /* * reset the NMI-timeout, listing all files on a slow * console might take a lot of time: + * Also, reset softlockup watchdogs on all CPUs, because + * another CPU might be blocked waiting for us to process + * an IPI. */ touch_nmi_watchdog(); + touch_all_softlockup_watchdogs(); if (!state_filter || (p->state & state_filter)) sched_show_task(p); } - touch_all_softlockup_watchdogs(); - #ifdef CONFIG_SCHED_DEBUG sysrq_sched_debug_show(); #endif diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 51c615279b23..b8b516c37bf1 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -687,8 +687,6 @@ void init_entity_runnable_average(struct sched_entity *se) /* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */ } -static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq); -static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq); #else void init_entity_runnable_average(struct sched_entity *se) { @@ -4594,19 +4592,24 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg) return wl; for_each_sched_entity(se) { - long w, W; + struct cfs_rq *cfs_rq = se->my_q; + long W, w = cfs_rq_load_avg(cfs_rq); - tg = se->my_q->tg; + tg = cfs_rq->tg; /* * W = @wg + \Sum rw_j */ - W = wg + calc_tg_weight(tg, se->my_q); + W = wg + atomic_long_read(&tg->load_avg); + + /* Ensure \Sum rw_j >= rw_i */ + W -= cfs_rq->tg_load_avg_contrib; + W += w; /* * w = rw_i + @wl */ - w = cfs_rq_load_avg(se->my_q) + wl; + w += wl; /* * wl = S * s'_i; see (2) diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index f5e86d282d52..80016b329d94 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -808,6 +808,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp) timer->it.cpu.expires = 0; sample_to_timespec(timer->it_clock, timer->it.cpu.expires, &itp->it_value); + return; } else { cpu_timer_sample_group(timer->it_clock, p, &now); unlock_task_sighand(p, &flags); diff --git a/mm/compaction.c b/mm/compaction.c index 7881e072dc33..dba02dec7195 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -475,25 +475,23 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, /* Found a free page, break it into order-0 pages */ isolated = split_free_page(page); + if (!isolated) + break; + total_isolated += isolated; + cc->nr_freepages += isolated; for (i = 0; i < isolated; i++) { list_add(&page->lru, freelist); page++; } - - /* If a page was split, advance to the end of it */ - if (isolated) { - cc->nr_freepages += isolated; - if (!strict && - cc->nr_migratepages <= cc->nr_freepages) { - blockpfn += isolated; - break; - } - - blockpfn += isolated - 1; - cursor += isolated - 1; - continue; + if (!strict && cc->nr_migratepages <= cc->nr_freepages) { + blockpfn += isolated; + break; } + /* Advance to the end of split page */ + blockpfn += isolated - 1; + cursor += isolated - 1; + continue; isolate_fail: if (strict) @@ -503,6 +501,9 @@ isolate_fail: } + if (locked) + spin_unlock_irqrestore(&cc->zone->lock, flags); + /* * There is a tiny chance that we have read bogus compound_order(), * so be careful to not go outside of the pageblock. @@ -524,9 +525,6 @@ isolate_fail: if (strict && blockpfn < end_pfn) total_isolated = 0; - if (locked) - spin_unlock_irqrestore(&cc->zone->lock, flags); - /* Update the pageblock-skip if the whole pageblock was scanned */ if (blockpfn == end_pfn) update_pageblock_skip(cc, valid_page, total_isolated, false); @@ -966,7 +964,6 @@ static void isolate_freepages(struct compact_control *cc) block_end_pfn = block_start_pfn, block_start_pfn -= pageblock_nr_pages, isolate_start_pfn = block_start_pfn) { - /* * This can iterate a massively long zone without finding any * suitable migration targets, so periodically check if we need @@ -990,32 +987,30 @@ static void isolate_freepages(struct compact_control *cc) continue; /* Found a block suitable for isolating free pages from. */ - isolate_freepages_block(cc, &isolate_start_pfn, - block_end_pfn, freelist, false); + isolate_freepages_block(cc, &isolate_start_pfn, block_end_pfn, + freelist, false); /* - * If we isolated enough freepages, or aborted due to async - * compaction being contended, terminate the loop. - * Remember where the free scanner should restart next time, - * which is where isolate_freepages_block() left off. - * But if it scanned the whole pageblock, isolate_start_pfn - * now points at block_end_pfn, which is the start of the next - * pageblock. - * In that case we will however want to restart at the start - * of the previous pageblock. + * If we isolated enough freepages, or aborted due to lock + * contention, terminate. */ if ((cc->nr_freepages >= cc->nr_migratepages) || cc->contended) { - if (isolate_start_pfn >= block_end_pfn) + if (isolate_start_pfn >= block_end_pfn) { + /* + * Restart at previous pageblock if more + * freepages can be isolated next time. + */ isolate_start_pfn = block_start_pfn - pageblock_nr_pages; + } break; - } else { + } else if (isolate_start_pfn < block_end_pfn) { /* - * isolate_freepages_block() should not terminate - * prematurely unless contended, or isolated enough + * If isolation failed early, do not continue + * needlessly. */ - VM_BUG_ON(isolate_start_pfn < block_end_pfn); + break; } } diff --git a/mm/internal.h b/mm/internal.h index 38e24b89e4c4..6979b2bd3227 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -22,7 +22,8 @@ */ #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\ __GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|\ - __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC) + __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\ + __GFP_ATOMIC) /* The GFP flags allowed during early boot */ #define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS)) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 67648e6b2ac8..6b90d184e9c0 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -272,21 +272,7 @@ static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) { - return memcg->css.id; -} - -/* - * A helper function to get mem_cgroup from ID. must be called under - * rcu_read_lock(). The caller is responsible for calling - * css_tryget_online() if the mem_cgroup is used for charging. (dropping - * refcnt from swap can be called against removed memcg.) - */ -static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) -{ - struct cgroup_subsys_state *css; - - css = css_from_id(id, &memory_cgrp_subsys); - return mem_cgroup_from_css(css); + return memcg->id.id; } /* Writing them here to avoid exposing memcg's inner layout */ @@ -4124,6 +4110,88 @@ static struct cftype mem_cgroup_legacy_files[] = { { }, /* terminate */ }; +/* + * Private memory cgroup IDR + * + * Swap-out records and page cache shadow entries need to store memcg + * references in constrained space, so we maintain an ID space that is + * limited to 16 bit (MEM_CGROUP_ID_MAX), limiting the total number of + * memory-controlled cgroups to 64k. + * + * However, there usually are many references to the oflline CSS after + * the cgroup has been destroyed, such as page cache or reclaimable + * slab objects, that don't need to hang on to the ID. We want to keep + * those dead CSS from occupying IDs, or we might quickly exhaust the + * relatively small ID space and prevent the creation of new cgroups + * even when there are much fewer than 64k cgroups - possibly none. + * + * Maintain a private 16-bit ID space for memcg, and allow the ID to + * be freed and recycled when it's no longer needed, which is usually + * when the CSS is offlined. + * + * The only exception to that are records of swapped out tmpfs/shmem + * pages that need to be attributed to live ancestors on swapin. But + * those references are manageable from userspace. + */ + +static DEFINE_IDR(mem_cgroup_idr); + +static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n) +{ + atomic_add(n, &memcg->id.ref); +} + +static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg) +{ + while (!atomic_inc_not_zero(&memcg->id.ref)) { + /* + * The root cgroup cannot be destroyed, so it's refcount must + * always be >= 1. + */ + if (WARN_ON_ONCE(memcg == root_mem_cgroup)) { + VM_BUG_ON(1); + break; + } + memcg = parent_mem_cgroup(memcg); + if (!memcg) + memcg = root_mem_cgroup; + } + return memcg; +} + +static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n) +{ + if (atomic_sub_and_test(n, &memcg->id.ref)) { + idr_remove(&mem_cgroup_idr, memcg->id.id); + memcg->id.id = 0; + + /* Memcg ID pins CSS */ + css_put(&memcg->css); + } +} + +static inline void mem_cgroup_id_get(struct mem_cgroup *memcg) +{ + mem_cgroup_id_get_many(memcg, 1); +} + +static inline void mem_cgroup_id_put(struct mem_cgroup *memcg) +{ + mem_cgroup_id_put_many(memcg, 1); +} + +/** + * mem_cgroup_from_id - look up a memcg from a memcg id + * @id: the memcg id to look up + * + * Caller must hold rcu_read_lock(). + */ +struct mem_cgroup *mem_cgroup_from_id(unsigned short id) +{ + WARN_ON_ONCE(!rcu_read_lock_held()); + return idr_find(&mem_cgroup_idr, id); +} + static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) { struct mem_cgroup_per_node *pn; @@ -4178,6 +4246,12 @@ static struct mem_cgroup *mem_cgroup_alloc(void) if (memcg_wb_domain_init(memcg, GFP_KERNEL)) goto out_free_stat; + memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL, + 1, MEM_CGROUP_ID_MAX, + GFP_KERNEL); + if (memcg->id.id < 0) + goto out_free_stat; + return memcg; out_free_stat: @@ -4263,9 +4337,11 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) #ifdef CONFIG_CGROUP_WRITEBACK INIT_LIST_HEAD(&memcg->cgwb_list); #endif + idr_replace(&mem_cgroup_idr, memcg, memcg->id.id); return &memcg->css; free_out: + idr_remove(&mem_cgroup_idr, memcg->id.id); __mem_cgroup_free(memcg); return ERR_PTR(error); } @@ -4277,8 +4353,9 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) struct mem_cgroup *parent = mem_cgroup_from_css(css->parent); int ret; - if (css->id > MEM_CGROUP_ID_MAX) - return -ENOSPC; + /* Online state pins memcg ID, memcg ID pins CSS */ + mem_cgroup_id_get(mem_cgroup_from_css(css)); + css_get(css); if (!parent) return 0; @@ -4352,6 +4429,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) memcg_deactivate_kmem(memcg); wb_memcg_offline(memcg); + + mem_cgroup_id_put(memcg); } static void mem_cgroup_css_released(struct cgroup_subsys_state *css) @@ -4785,6 +4864,8 @@ static void __mem_cgroup_clear_mc(void) if (!mem_cgroup_is_root(mc.from)) page_counter_uncharge(&mc.from->memsw, mc.moved_swap); + mem_cgroup_id_put_many(mc.from, mc.moved_swap); + /* * we charged both to->memory and to->memsw, so we * should uncharge to->memory. @@ -4792,9 +4873,9 @@ static void __mem_cgroup_clear_mc(void) if (!mem_cgroup_is_root(mc.to)) page_counter_uncharge(&mc.to->memory, mc.moved_swap); - css_put_many(&mc.from->css, mc.moved_swap); + mem_cgroup_id_get_many(mc.to, mc.moved_swap); + css_put_many(&mc.to->css, mc.moved_swap); - /* we've already done css_get(mc.to) */ mc.moved_swap = 0; } memcg_oom_recover(from); @@ -5670,7 +5751,7 @@ subsys_initcall(mem_cgroup_init); */ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) { - struct mem_cgroup *memcg; + struct mem_cgroup *memcg, *swap_memcg; unsigned short oldid; VM_BUG_ON_PAGE(PageLRU(page), page); @@ -5685,15 +5766,27 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) if (!memcg) return; - oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg)); + /* + * In case the memcg owning these pages has been offlined and doesn't + * have an ID allocated to it anymore, charge the closest online + * ancestor for the swap instead and transfer the memory+swap charge. + */ + swap_memcg = mem_cgroup_id_get_online(memcg); + oldid = swap_cgroup_record(entry, mem_cgroup_id(swap_memcg)); VM_BUG_ON_PAGE(oldid, page); - mem_cgroup_swap_statistics(memcg, true); + mem_cgroup_swap_statistics(swap_memcg, true); page->mem_cgroup = NULL; if (!mem_cgroup_is_root(memcg)) page_counter_uncharge(&memcg->memory, 1); + if (memcg != swap_memcg) { + if (!mem_cgroup_is_root(swap_memcg)) + page_counter_charge(&swap_memcg->memsw, 1); + page_counter_uncharge(&memcg->memsw, 1); + } + /* * Interrupts should be disabled here because the caller holds the * mapping->tree_lock lock which is taken with interrupts-off. It is @@ -5703,6 +5796,9 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) VM_BUG_ON(!irqs_disabled()); mem_cgroup_charge_statistics(memcg, page, -1); memcg_check_events(memcg, page); + + if (!mem_cgroup_is_root(memcg)) + css_put(&memcg->css); } /** @@ -5726,7 +5822,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t entry) if (!mem_cgroup_is_root(memcg)) page_counter_uncharge(&memcg->memsw, 1); mem_cgroup_swap_statistics(memcg, false); - css_put(&memcg->css); + mem_cgroup_id_put(memcg); } rcu_read_unlock(); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 99c1738684ec..2bcdfbf8c36d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -275,7 +275,9 @@ static inline void reset_deferred_meminit(pg_data_t *pgdat) /* Returns true if the struct page for the pfn is uninitialised */ static inline bool __meminit early_page_uninitialised(unsigned long pfn) { - if (pfn >= NODE_DATA(early_pfn_to_nid(pfn))->first_deferred_pfn) + int nid = early_pfn_to_nid(pfn); + + if (node_online(nid) && pfn >= NODE_DATA(nid)->first_deferred_pfn) return true; return false; @@ -1057,7 +1059,7 @@ int __meminit early_pfn_to_nid(unsigned long pfn) spin_lock(&early_pfn_lock); nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache); if (nid < 0) - nid = 0; + nid = first_online_node; spin_unlock(&early_pfn_lock); return nid; diff --git a/mm/slab_common.c b/mm/slab_common.c index 3c6a86b4ec25..bec2fce9fafc 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -521,8 +521,8 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg, goto out_unlock; cgroup_name(css->cgroup, memcg_name_buf, sizeof(memcg_name_buf)); - cache_name = kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name, - css->id, memcg_name_buf); + cache_name = kasprintf(GFP_KERNEL, "%s(%llu:%s)", root_cache->name, + css->serial_nr, memcg_name_buf); if (!cache_name) goto out_unlock; diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 7d8f581d9f1f..ddc3573894b0 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -1192,6 +1192,115 @@ struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end) } /* + * Encoding order is (new_up_client, new_state, new_weight). Need to + * apply in the (new_weight, new_state, new_up_client) order, because + * an incremental map may look like e.g. + * + * new_up_client: { osd=6, addr=... } # set osd_state and addr + * new_state: { osd=6, xorstate=EXISTS } # clear osd_state + */ +static int decode_new_up_state_weight(void **p, void *end, + struct ceph_osdmap *map) +{ + void *new_up_client; + void *new_state; + void *new_weight_end; + u32 len; + + new_up_client = *p; + ceph_decode_32_safe(p, end, len, e_inval); + len *= sizeof(u32) + sizeof(struct ceph_entity_addr); + ceph_decode_need(p, end, len, e_inval); + *p += len; + + new_state = *p; + ceph_decode_32_safe(p, end, len, e_inval); + len *= sizeof(u32) + sizeof(u8); + ceph_decode_need(p, end, len, e_inval); + *p += len; + + /* new_weight */ + ceph_decode_32_safe(p, end, len, e_inval); + while (len--) { + s32 osd; + u32 w; + + ceph_decode_need(p, end, 2*sizeof(u32), e_inval); + osd = ceph_decode_32(p); + w = ceph_decode_32(p); + BUG_ON(osd >= map->max_osd); + pr_info("osd%d weight 0x%x %s\n", osd, w, + w == CEPH_OSD_IN ? "(in)" : + (w == CEPH_OSD_OUT ? "(out)" : "")); + map->osd_weight[osd] = w; + + /* + * If we are marking in, set the EXISTS, and clear the + * AUTOOUT and NEW bits. + */ + if (w) { + map->osd_state[osd] |= CEPH_OSD_EXISTS; + map->osd_state[osd] &= ~(CEPH_OSD_AUTOOUT | + CEPH_OSD_NEW); + } + } + new_weight_end = *p; + + /* new_state (up/down) */ + *p = new_state; + len = ceph_decode_32(p); + while (len--) { + s32 osd; + u8 xorstate; + int ret; + + osd = ceph_decode_32(p); + xorstate = ceph_decode_8(p); + if (xorstate == 0) + xorstate = CEPH_OSD_UP; + BUG_ON(osd >= map->max_osd); + if ((map->osd_state[osd] & CEPH_OSD_UP) && + (xorstate & CEPH_OSD_UP)) + pr_info("osd%d down\n", osd); + if ((map->osd_state[osd] & CEPH_OSD_EXISTS) && + (xorstate & CEPH_OSD_EXISTS)) { + pr_info("osd%d does not exist\n", osd); + map->osd_weight[osd] = CEPH_OSD_IN; + ret = set_primary_affinity(map, osd, + CEPH_OSD_DEFAULT_PRIMARY_AFFINITY); + if (ret) + return ret; + memset(map->osd_addr + osd, 0, sizeof(*map->osd_addr)); + map->osd_state[osd] = 0; + } else { + map->osd_state[osd] ^= xorstate; + } + } + + /* new_up_client */ + *p = new_up_client; + len = ceph_decode_32(p); + while (len--) { + s32 osd; + struct ceph_entity_addr addr; + + osd = ceph_decode_32(p); + ceph_decode_copy(p, &addr, sizeof(addr)); + ceph_decode_addr(&addr); + BUG_ON(osd >= map->max_osd); + pr_info("osd%d up\n", osd); + map->osd_state[osd] |= CEPH_OSD_EXISTS | CEPH_OSD_UP; + map->osd_addr[osd] = addr; + } + + *p = new_weight_end; + return 0; + +e_inval: + return -EINVAL; +} + +/* * decode and apply an incremental map update. */ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, @@ -1290,49 +1399,10 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, __remove_pg_pool(&map->pg_pools, pi); } - /* new_up */ - ceph_decode_32_safe(p, end, len, e_inval); - while (len--) { - u32 osd; - struct ceph_entity_addr addr; - ceph_decode_32_safe(p, end, osd, e_inval); - ceph_decode_copy_safe(p, end, &addr, sizeof(addr), e_inval); - ceph_decode_addr(&addr); - pr_info("osd%d up\n", osd); - BUG_ON(osd >= map->max_osd); - map->osd_state[osd] |= CEPH_OSD_UP | CEPH_OSD_EXISTS; - map->osd_addr[osd] = addr; - } - - /* new_state */ - ceph_decode_32_safe(p, end, len, e_inval); - while (len--) { - u32 osd; - u8 xorstate; - ceph_decode_32_safe(p, end, osd, e_inval); - xorstate = **(u8 **)p; - (*p)++; /* clean flag */ - if (xorstate == 0) - xorstate = CEPH_OSD_UP; - if (xorstate & CEPH_OSD_UP) - pr_info("osd%d down\n", osd); - if (osd < map->max_osd) - map->osd_state[osd] ^= xorstate; - } - - /* new_weight */ - ceph_decode_32_safe(p, end, len, e_inval); - while (len--) { - u32 osd, off; - ceph_decode_need(p, end, sizeof(u32)*2, e_inval); - osd = ceph_decode_32(p); - off = ceph_decode_32(p); - pr_info("osd%d weight 0x%x %s\n", osd, off, - off == CEPH_OSD_IN ? "(in)" : - (off == CEPH_OSD_OUT ? "(out)" : "")); - if (osd < map->max_osd) - map->osd_weight[osd] = off; - } + /* new_up_client, new_state, new_weight */ + err = decode_new_up_state_weight(p, end, map); + if (err) + goto bad; /* new_pg_temp */ err = decode_new_pg_temp(p, end, map); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 2b68418c7198..ffe95d954007 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -479,6 +479,9 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, if (!rtnh_ok(rtnh, remaining)) return -EINVAL; + if (rtnh->rtnh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) + return -EINVAL; + nexthop_nh->nh_flags = (cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags; nexthop_nh->nh_oif = rtnh->rtnh_ifindex; @@ -1003,6 +1006,9 @@ struct fib_info *fib_create_info(struct fib_config *cfg) if (fib_props[cfg->fc_type].scope > cfg->fc_scope) goto err_inval; + if (cfg->fc_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) + goto err_inval; + #ifdef CONFIG_IP_ROUTE_MULTIPATH if (cfg->fc_mp) { nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index d4c51158470f..12b98e257c5f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -89,7 +89,7 @@ int sysctl_tcp_adv_win_scale __read_mostly = 1; EXPORT_SYMBOL(sysctl_tcp_adv_win_scale); /* rfc5961 challenge ack rate limiting */ -int sysctl_tcp_challenge_ack_limit = 100; +int sysctl_tcp_challenge_ack_limit = 1000; int sysctl_tcp_stdurg __read_mostly; int sysctl_tcp_rfc1337 __read_mostly; @@ -3390,6 +3390,23 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 return flag; } +static bool __tcp_oow_rate_limited(struct net *net, int mib_idx, + u32 *last_oow_ack_time) +{ + if (*last_oow_ack_time) { + s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time); + + if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { + NET_INC_STATS_BH(net, mib_idx); + return true; /* rate-limited: don't send yet! */ + } + } + + *last_oow_ack_time = tcp_time_stamp; + + return false; /* not rate-limited: go ahead, send dupack now! */ +} + /* Return true if we're currently rate-limiting out-of-window ACKs and * thus shouldn't send a dupack right now. We rate-limit dupacks in * response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS @@ -3403,21 +3420,9 @@ bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, /* Data packets without SYNs are not likely part of an ACK loop. */ if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) && !tcp_hdr(skb)->syn) - goto not_rate_limited; - - if (*last_oow_ack_time) { - s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time); - - if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { - NET_INC_STATS_BH(net, mib_idx); - return true; /* rate-limited: don't send yet! */ - } - } - - *last_oow_ack_time = tcp_time_stamp; + return false; -not_rate_limited: - return false; /* not rate-limited: go ahead, send dupack now! */ + return __tcp_oow_rate_limited(net, mib_idx, last_oow_ack_time); } /* RFC 5961 7 [ACK Throttling] */ @@ -3427,21 +3432,26 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb) static u32 challenge_timestamp; static unsigned int challenge_count; struct tcp_sock *tp = tcp_sk(sk); - u32 now; + u32 count, now; /* First check our per-socket dupack rate limit. */ - if (tcp_oow_rate_limited(sock_net(sk), skb, - LINUX_MIB_TCPACKSKIPPEDCHALLENGE, - &tp->last_oow_ack_time)) + if (__tcp_oow_rate_limited(sock_net(sk), + LINUX_MIB_TCPACKSKIPPEDCHALLENGE, + &tp->last_oow_ack_time)) return; - /* Then check the check host-wide RFC 5961 rate limit. */ + /* Then check host-wide RFC 5961 rate limit. */ now = jiffies / HZ; if (now != challenge_timestamp) { + u32 half = (sysctl_tcp_challenge_ack_limit + 1) >> 1; + challenge_timestamp = now; - challenge_count = 0; + WRITE_ONCE(challenge_count, half + + prandom_u32_max(sysctl_tcp_challenge_ack_limit)); } - if (++challenge_count <= sysctl_tcp_challenge_ack_limit) { + count = READ_ONCE(challenge_count); + if (count > 0) { + WRITE_ONCE(challenge_count, count - 1); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK); tcp_send_ack(sk); } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 7c9883ab56e5..660c967ba84a 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -239,7 +239,8 @@ void tcp_select_initial_window(int __space, __u32 mss, /* Set window scaling on max possible window * See RFC1323 for an explanation of the limit to 14 */ - space = max_t(u32, sysctl_tcp_rmem[2], sysctl_rmem_max); + space = max_t(u32, space, sysctl_tcp_rmem[2]); + space = max_t(u32, space, sysctl_rmem_max); space = min_t(u32, space, *window_clamp); while (space > 65535 && (*rcv_wscale) < 14) { space >>= 1; diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index 923abd6b3064..8d2f7c9b491d 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -1024,8 +1024,11 @@ static int irda_connect(struct socket *sock, struct sockaddr *uaddr, } /* Check if we have opened a local TSAP */ - if (!self->tsap) - irda_open_tsap(self, LSAP_ANY, addr->sir_name); + if (!self->tsap) { + err = irda_open_tsap(self, LSAP_ANY, addr->sir_name); + if (err) + goto out; + } /* Move to connecting socket, start sending Connect Requests */ sock->state = SS_CONNECTING; diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 9d6ddbacd875..18e50a8fc05f 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -421,7 +421,7 @@ static int rds_tcp_init(void) ret = rds_tcp_recv_init(); if (ret) - goto out_slab; + goto out_pernet; ret = rds_trans_register(&rds_tcp_transport); if (ret) @@ -433,8 +433,9 @@ static int rds_tcp_init(void) out_recv: rds_tcp_recv_exit(); -out_slab: +out_pernet: unregister_pernet_subsys(&rds_tcp_net_ops); +out_slab: kmem_cache_destroy(rds_tcp_conn_slab); out: return ret; diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index ad4fa49ad1db..9068369f8a1b 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -331,6 +331,7 @@ static int aa_fs_seq_hash_show(struct seq_file *seq, void *v) seq_printf(seq, "%.2x", profile->hash[i]); seq_puts(seq, "\n"); } + aa_put_profile(profile); return 0; } diff --git a/sound/core/timer.c b/sound/core/timer.c index 7c6155f5865b..637d034bb084 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -1247,6 +1247,7 @@ static void snd_timer_user_ccallback(struct snd_timer_instance *timeri, tu->tstamp = *tstamp; if ((tu->filter & (1 << event)) == 0 || !tu->tread) return; + memset(&r1, 0, sizeof(r1)); r1.event = event; r1.tstamp = *tstamp; r1.val = resolution; @@ -1281,6 +1282,7 @@ static void snd_timer_user_tinterrupt(struct snd_timer_instance *timeri, } if ((tu->filter & (1 << SNDRV_TIMER_EVENT_RESOLUTION)) && tu->last_resolution != resolution) { + memset(&r1, 0, sizeof(r1)); r1.event = SNDRV_TIMER_EVENT_RESOLUTION; r1.tstamp = tstamp; r1.val = resolution; @@ -1746,6 +1748,7 @@ static int snd_timer_user_params(struct file *file, if (tu->timeri->flags & SNDRV_TIMER_IFLG_EARLY_EVENT) { if (tu->tread) { struct snd_timer_tread tread; + memset(&tread, 0, sizeof(tread)); tread.event = SNDRV_TIMER_EVENT_EARLY; tread.tstamp.tv_sec = 0; tread.tstamp.tv_nsec = 0; |