diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 4f7c57cb6022..789b8941a0c6 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -343,6 +343,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted. no: ACPI OperationRegions are not marked as reserved, no further checks are performed. + acpi_no_memhotplug [ACPI] Disable memory hotplug. Useful for kdump + kernels. + add_efi_memmap [EFI; X86] Include EFI memory map in kernel's map of available physical RAM. diff --git a/Documentation/vm/hwpoison.txt b/Documentation/vm/hwpoison.txt index 550068466605..6ae89a9edf2a 100644 --- a/Documentation/vm/hwpoison.txt +++ b/Documentation/vm/hwpoison.txt @@ -84,6 +84,11 @@ PR_MCE_KILL PR_MCE_KILL_EARLY: Early kill PR_MCE_KILL_LATE: Late kill PR_MCE_KILL_DEFAULT: Use system global default + Note that if you want to have a dedicated thread which handles + the SIGBUS(BUS_MCEERR_AO) on behalf of the process, you should + call prctl(PR_MCE_KILL_EARLY) on the designated thread. Otherwise, + the SIGBUS is sent to the main thread. + PR_MCE_KILL_GET return current mode diff --git a/Makefile b/Makefile index 350d9caf71d0..b887aa84c80d 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 3 PATCHLEVEL = 12 -SUBLEVEL = 23 +SUBLEVEL = 24 EXTRAVERSION = NAME = One Giant Leap for Frogkind diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c index af4e8c8a5422..6582c4adc182 100644 --- a/arch/arm/kernel/stacktrace.c +++ b/arch/arm/kernel/stacktrace.c @@ -83,13 +83,16 @@ static int save_trace(struct stackframe *frame, void *d) return trace->nr_entries >= trace->max_entries; } -void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) +/* This must be noinline to so that our skip calculation works correctly */ +static noinline void __save_stack_trace(struct task_struct *tsk, + struct stack_trace *trace, unsigned int nosched) { struct stack_trace_data data; struct stackframe frame; data.trace = trace; data.skip = trace->skip; + data.no_sched_functions = nosched; if (tsk != current) { #ifdef CONFIG_SMP @@ -102,7 +105,6 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) trace->entries[trace->nr_entries++] = ULONG_MAX; return; #else - data.no_sched_functions = 1; frame.fp = thread_saved_fp(tsk); frame.sp = thread_saved_sp(tsk); frame.lr = 0; /* recovered from the stack */ @@ -111,11 +113,12 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) } else { register unsigned long current_sp asm ("sp"); - data.no_sched_functions = 0; + /* We don't want this function nor the caller */ + data.skip += 2; frame.fp = (unsigned long)__builtin_frame_address(0); frame.sp = current_sp; frame.lr = (unsigned long)__builtin_return_address(0); - frame.pc = (unsigned long)save_stack_trace_tsk; + frame.pc = (unsigned long)__save_stack_trace; } walk_stackframe(&frame, save_trace, &data); @@ -123,9 +126,14 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) trace->entries[trace->nr_entries++] = ULONG_MAX; } +void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) +{ + __save_stack_trace(tsk, trace, 1); +} + void save_stack_trace(struct stack_trace *trace) { - save_stack_trace_tsk(current, trace); + __save_stack_trace(current, trace, 0); } EXPORT_SYMBOL_GPL(save_stack_trace); #endif diff --git a/arch/arm/mach-omap1/board-h2.c b/arch/arm/mach-omap1/board-h2.c index fd90cafc2e36..db57072aeed3 100644 --- a/arch/arm/mach-omap1/board-h2.c +++ b/arch/arm/mach-omap1/board-h2.c @@ -343,7 +343,7 @@ static struct omap_usb_config h2_usb_config __initdata = { /* usb1 has a Mini-AB port and external isp1301 transceiver */ .otg = 2, -#ifdef CONFIG_USB_GADGET_OMAP +#if IS_ENABLED(CONFIG_USB_OMAP) .hmc_mode = 19, /* 0:host(off) 1:dev|otg 2:disabled */ /* .hmc_mode = 21,*/ /* 0:host(off) 1:dev(loopback) 2:host(loopback) */ #elif defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE) diff --git a/arch/arm/mach-omap1/board-h3.c b/arch/arm/mach-omap1/board-h3.c index 816ecd13f81e..bfed4f928663 100644 --- a/arch/arm/mach-omap1/board-h3.c +++ b/arch/arm/mach-omap1/board-h3.c @@ -366,7 +366,7 @@ static struct omap_usb_config h3_usb_config __initdata = { /* usb1 has a Mini-AB port and external isp1301 transceiver */ .otg = 2, -#ifdef CONFIG_USB_GADGET_OMAP +#if IS_ENABLED(CONFIG_USB_OMAP) .hmc_mode = 19, /* 0:host(off) 1:dev|otg 2:disabled */ #elif defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE) /* NONSTANDARD CABLE NEEDED (B-to-Mini-B) */ diff --git a/arch/arm/mach-omap1/board-innovator.c b/arch/arm/mach-omap1/board-innovator.c index bd5f02e9c354..c49ce83cc1eb 100644 --- a/arch/arm/mach-omap1/board-innovator.c +++ b/arch/arm/mach-omap1/board-innovator.c @@ -312,7 +312,7 @@ static struct omap_usb_config h2_usb_config __initdata = { /* usb1 has a Mini-AB port and external isp1301 transceiver */ .otg = 2, -#ifdef CONFIG_USB_GADGET_OMAP +#if IS_ENABLED(CONFIG_USB_OMAP) .hmc_mode = 19, /* 0:host(off) 1:dev|otg 2:disabled */ /* .hmc_mode = 21,*/ /* 0:host(off) 1:dev(loopback) 2:host(loopback) */ #elif defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE) diff --git a/arch/arm/mach-omap1/board-osk.c b/arch/arm/mach-omap1/board-osk.c index a7ce69286688..006fbb5f9654 100644 --- a/arch/arm/mach-omap1/board-osk.c +++ b/arch/arm/mach-omap1/board-osk.c @@ -280,7 +280,7 @@ static struct omap_usb_config osk_usb_config __initdata = { * be used, with a NONSTANDARD gender-bending cable/dongle, as * a peripheral. */ -#ifdef CONFIG_USB_GADGET_OMAP +#if IS_ENABLED(CONFIG_USB_OMAP) .register_dev = 1, .hmc_mode = 0, #else diff --git a/arch/arm/mm/hugetlbpage.c b/arch/arm/mm/hugetlbpage.c index 54ee6163c181..66781bf34077 100644 --- a/arch/arm/mm/hugetlbpage.c +++ b/arch/arm/mm/hugetlbpage.c @@ -56,8 +56,3 @@ int pmd_huge(pmd_t pmd) { return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT); } - -int pmd_huge_support(void) -{ - return 1; -} diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S index 01a719e18bb0..22e3ad63500c 100644 --- a/arch/arm/mm/proc-v7-3level.S +++ b/arch/arm/mm/proc-v7-3level.S @@ -64,6 +64,14 @@ ENTRY(cpu_v7_switch_mm) mov pc, lr ENDPROC(cpu_v7_switch_mm) +#ifdef __ARMEB__ +#define rl r3 +#define rh r2 +#else +#define rl r2 +#define rh r3 +#endif + /* * cpu_v7_set_pte_ext(ptep, pte) * @@ -73,13 +81,13 @@ ENDPROC(cpu_v7_switch_mm) */ ENTRY(cpu_v7_set_pte_ext) #ifdef CONFIG_MMU - tst r2, #L_PTE_VALID + tst rl, #L_PTE_VALID beq 1f - tst r3, #1 << (57 - 32) @ L_PTE_NONE - bicne r2, #L_PTE_VALID + tst rh, #1 << (57 - 32) @ L_PTE_NONE + bicne rl, #L_PTE_VALID bne 1f - tst r3, #1 << (55 - 32) @ L_PTE_DIRTY - orreq r2, #L_PTE_RDONLY + tst rh, #1 << (55 - 32) @ L_PTE_DIRTY + orreq rl, #L_PTE_RDONLY 1: strd r2, r3, [r0] ALT_SMP(W(nop)) ALT_UP (mcr p15, 0, r0, c7, c10, 1) @ flush_pte diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index c484d5625ffb..9fa78cd0f092 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -823,6 +823,7 @@ static int compat_ptrace_write_user(struct task_struct *tsk, compat_ulong_t off, compat_ulong_t val) { int ret; + mm_segment_t old_fs = get_fs(); if (off & 3 || off >= COMPAT_USER_SZ) return -EIO; @@ -830,10 +831,13 @@ static int compat_ptrace_write_user(struct task_struct *tsk, compat_ulong_t off, if (off >= sizeof(compat_elf_gregset_t)) return 0; + set_fs(KERNEL_DS); ret = copy_regset_from_user(tsk, &user_aarch32_view, REGSET_COMPAT_GPR, off, sizeof(compat_ulong_t), &val); + set_fs(old_fs); + return ret; } diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 31eb959e9aa8..023747bf4dd7 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -58,11 +58,6 @@ int pud_huge(pud_t pud) #endif } -int pmd_huge_support(void) -{ - return 1; -} - static __init int setup_hugepagesz(char *opt) { unsigned long ps = memparse(opt, &opt); diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c index 68232db98baa..76069c18ee42 100644 --- a/arch/ia64/mm/hugetlbpage.c +++ b/arch/ia64/mm/hugetlbpage.c @@ -114,11 +114,6 @@ int pud_huge(pud_t pud) return 0; } -int pmd_huge_support(void) -{ - return 0; -} - struct page * follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) { diff --git a/arch/metag/mm/hugetlbpage.c b/arch/metag/mm/hugetlbpage.c index 042431509b56..3c52fa6d0f8e 100644 --- a/arch/metag/mm/hugetlbpage.c +++ b/arch/metag/mm/hugetlbpage.c @@ -110,11 +110,6 @@ int pud_huge(pud_t pud) return 0; } -int pmd_huge_support(void) -{ - return 1; -} - struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) { diff --git a/arch/mips/kvm/kvm_mips.c b/arch/mips/kvm/kvm_mips.c index a7b044536de4..b31153969946 100644 --- a/arch/mips/kvm/kvm_mips.c +++ b/arch/mips/kvm/kvm_mips.c @@ -303,7 +303,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) if (cpu_has_veic || cpu_has_vint) { size = 0x200 + VECTORSPACING * 64; } else { - size = 0x200; + size = 0x4000; } /* Save Linux EBASE */ diff --git a/arch/mips/mm/hugetlbpage.c b/arch/mips/mm/hugetlbpage.c index 01fda4419ed0..a7fee0dfb7a9 100644 --- a/arch/mips/mm/hugetlbpage.c +++ b/arch/mips/mm/hugetlbpage.c @@ -85,11 +85,6 @@ int pud_huge(pud_t pud) return (pud_val(pud) & _PAGE_HUGE) != 0; } -int pmd_huge_support(void) -{ - return 1; -} - struct page * follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index e1ab62e0d548..211974a386d6 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -82,7 +82,7 @@ void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu) /* CPU points to the first thread of the core */ if (cpu != me && cpu >= 0 && cpu < nr_cpu_ids) { -#ifdef CONFIG_KVM_XICS +#ifdef CONFIG_PPC_ICP_NATIVE int real_cpu = cpu + vcpu->arch.ptid; if (paca[real_cpu].kvm_hstate.xics_phys) xics_wake_cpu(real_cpu); @@ -1092,9 +1092,7 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu) smp_wmb(); #if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP) if (vcpu->arch.ptid) { -#ifdef CONFIG_KVM_XICS xics_wake_cpu(cpu); -#endif ++vc->n_woken; } #endif diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index d67db4bd672d..834ca8eb38f2 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -86,11 +86,6 @@ int pgd_huge(pgd_t pgd) */ return ((pgd_val(pgd) & 0x3) != 0x0); } - -int pmd_huge_support(void) -{ - return 1; -} #else int pmd_huge(pmd_t pmd) { @@ -106,11 +101,6 @@ int pgd_huge(pgd_t pgd) { return 0; } - -int pmd_huge_support(void) -{ - return 0; -} #endif pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 4788ea2b343a..14c05547bd74 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -232,6 +232,7 @@ int __node_distance(int a, int b) return distance; } +EXPORT_SYMBOL(__node_distance); static void initialize_distance_lookup_table(int nid, const __be32 *associativity) diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 0ea99e3d4815..2d6fe89ff89d 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -88,13 +88,14 @@ void set_default_offline_state(int cpu) static void rtas_stop_self(void) { - struct rtas_args args = { - .token = cpu_to_be32(rtas_stop_self_token), + static struct rtas_args args = { .nargs = 0, .nret = 1, .rets = &args.args[0], }; + args.token = cpu_to_be32(rtas_stop_self_token); + local_irq_disable(); BUG_ON(rtas_stop_self_token == RTAS_UNKNOWN_SERVICE); diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h index bbf8141408cd..2bed4f02a558 100644 --- a/arch/s390/include/asm/lowcore.h +++ b/arch/s390/include/asm/lowcore.h @@ -142,9 +142,9 @@ struct _lowcore { __u8 pad_0x02fc[0x0300-0x02fc]; /* 0x02fc */ /* Interrupt response block */ - __u8 irb[64]; /* 0x0300 */ + __u8 irb[96]; /* 0x0300 */ - __u8 pad_0x0340[0x0e00-0x0340]; /* 0x0340 */ + __u8 pad_0x0360[0x0e00-0x0360]; /* 0x0360 */ /* * 0xe00 contains the address of the IPL Parameter Information @@ -288,12 +288,13 @@ struct _lowcore { __u8 pad_0x03a0[0x0400-0x03a0]; /* 0x03a0 */ /* Interrupt response block. */ - __u8 irb[64]; /* 0x0400 */ + __u8 irb[96]; /* 0x0400 */ + __u8 pad_0x0460[0x0480-0x0460]; /* 0x0460 */ /* Per cpu primary space access list */ - __u32 paste[16]; /* 0x0440 */ + __u32 paste[16]; /* 0x0480 */ - __u8 pad_0x0480[0x0e00-0x0480]; /* 0x0480 */ + __u8 pad_0x04c0[0x0e00-0x04c0]; /* 0x04c0 */ /* * 0xe00 contains the address of the IPL Parameter Information diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index d261c62e40a6..248445f92604 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -223,11 +223,6 @@ int pud_huge(pud_t pud) return 0; } -int pmd_huge_support(void) -{ - return 1; -} - struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmdp, int write) { diff --git a/arch/sh/mm/hugetlbpage.c b/arch/sh/mm/hugetlbpage.c index 0d676a41081e..d7762349ea48 100644 --- a/arch/sh/mm/hugetlbpage.c +++ b/arch/sh/mm/hugetlbpage.c @@ -83,11 +83,6 @@ int pud_huge(pud_t pud) return 0; } -int pmd_huge_support(void) -{ - return 0; -} - struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) { diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c index 96399646570a..d2b59441ebdd 100644 --- a/arch/sparc/mm/hugetlbpage.c +++ b/arch/sparc/mm/hugetlbpage.c @@ -234,11 +234,6 @@ int pud_huge(pud_t pud) return 0; } -int pmd_huge_support(void) -{ - return 0; -} - struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) { diff --git a/arch/tile/mm/hugetlbpage.c b/arch/tile/mm/hugetlbpage.c index 0cb3bbaa580c..e514899e1100 100644 --- a/arch/tile/mm/hugetlbpage.c +++ b/arch/tile/mm/hugetlbpage.c @@ -166,11 +166,6 @@ int pud_huge(pud_t pud) return !!(pud_val(pud) & _PAGE_HUGE_PAGE); } -int pmd_huge_support(void) -{ - return 1; -} - struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) { diff --git a/arch/unicore32/mm/alignment.c b/arch/unicore32/mm/alignment.c index de7dc5fdd58b..24e836023e6c 100644 --- a/arch/unicore32/mm/alignment.c +++ b/arch/unicore32/mm/alignment.c @@ -21,6 +21,7 @@ #include #include +#include #include #include diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index f67e839f06c8..eb2dfa61eabe 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1881,6 +1881,10 @@ config USE_PERCPU_NUMA_NODE_ID def_bool y depends on NUMA +config ARCH_ENABLE_HUGEPAGE_MIGRATION + def_bool y + depends on X86_64 && HUGETLB_PAGE && MIGRATION + menu "Power management and ACPI options" config ARCH_HIBERNATION_HEADER diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 15a569a47b4d..3308125c90aa 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -434,9 +434,10 @@ sysenter_past_esp: jnz sysenter_audit sysenter_do_call: cmpl $(NR_syscalls), %eax - jae syscall_badsys + jae sysenter_badsys call *sys_call_table(,%eax,4) movl %eax,PT_EAX(%esp) +sysenter_after_call: LOCKDEP_SYS_EXIT DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF @@ -554,11 +555,6 @@ ENTRY(iret_exc) CFI_RESTORE_STATE ldt_ss: - larl PT_OLDSS(%esp), %eax - jnz restore_nocheck - testl $0x00400000, %eax # returning to 32bit stack? - jnz restore_nocheck # allright, normal return - #ifdef CONFIG_PARAVIRT /* * The kernel can't run on a non-flat stack if paravirt mode @@ -691,7 +687,12 @@ END(syscall_fault) syscall_badsys: movl $-ENOSYS,PT_EAX(%esp) - jmp resume_userspace + jmp syscall_exit +END(syscall_badsys) + +sysenter_badsys: + movl $-ENOSYS,PT_EAX(%esp) + jmp sysenter_after_call END(syscall_badsys) CFI_ENDPROC /* diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 1ffc32dbe450..f8ab203fb676 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -297,16 +297,7 @@ int ftrace_int3_handler(struct pt_regs *regs) static int ftrace_write(unsigned long ip, const char *val, int size) { - /* - * On x86_64, kernel text mappings are mapped read-only with - * CONFIG_DEBUG_RODATA. So we use the kernel identity mapping instead - * of the kernel text mapping to modify the kernel text. - * - * For 32bit kernels, these mappings are same and we can use - * kernel identity mapping to modify code. - */ - if (within(ip, (unsigned long)_text, (unsigned long)_etext)) - ip = (unsigned long)__va(__pa_symbol(ip)); + ip = text_ip_addr(ip); return probe_kernel_write((void *)ip, val, size); } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index d86ff15fc89f..92bbb397f59d 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -360,6 +360,8 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) static inline void apic_set_isr(int vec, struct kvm_lapic *apic) { + /* Note that we never get here with APIC virtualization enabled. */ + if (!__apic_test_and_set_vector(vec, apic->regs + APIC_ISR)) ++apic->isr_count; BUG_ON(apic->isr_count > MAX_APIC_VECTOR); @@ -371,12 +373,48 @@ static inline void apic_set_isr(int vec, struct kvm_lapic *apic) apic->highest_isr_cache = vec; } +static inline int apic_find_highest_isr(struct kvm_lapic *apic) +{ + int result; + + /* + * Note that isr_count is always 1, and highest_isr_cache + * is always -1, with APIC virtualization enabled. + */ + if (!apic->isr_count) + return -1; + if (likely(apic->highest_isr_cache != -1)) + return apic->highest_isr_cache; + + result = find_highest_vector(apic->regs + APIC_ISR); + ASSERT(result == -1 || result >= 16); + + return result; +} + static inline void apic_clear_isr(int vec, struct kvm_lapic *apic) { - if (__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR)) + struct kvm_vcpu *vcpu; + if (!__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR)) + return; + + vcpu = apic->vcpu; + + /* + * We do get here for APIC virtualization enabled if the guest + * uses the Hyper-V APIC enlightenment. In this case we may need + * to trigger a new interrupt delivery by writing the SVI field; + * on the other hand isr_count and highest_isr_cache are unused + * and must be left alone. + */ + if (unlikely(kvm_apic_vid_enabled(vcpu->kvm))) + kvm_x86_ops->hwapic_isr_update(vcpu->kvm, + apic_find_highest_isr(apic)); + else { --apic->isr_count; - BUG_ON(apic->isr_count < 0); - apic->highest_isr_cache = -1; + BUG_ON(apic->isr_count < 0); + apic->highest_isr_cache = -1; + } } int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu) @@ -456,22 +494,6 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu) __clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); } -static inline int apic_find_highest_isr(struct kvm_lapic *apic) -{ - int result; - - /* Note that isr_count is always 1 with vid enabled */ - if (!apic->isr_count) - return -1; - if (likely(apic->highest_isr_cache != -1)) - return apic->highest_isr_cache; - - result = find_highest_vector(apic->regs + APIC_ISR); - ASSERT(result == -1 || result >= 16); - - return result; -} - void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr) { struct kvm_lapic *apic = vcpu->arch.apic; @@ -1605,6 +1627,8 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) int vector = kvm_apic_has_interrupt(vcpu); struct kvm_lapic *apic = vcpu->arch.apic; + /* Note that we never get here with APIC virtualization enabled. */ + if (vector == -1) return -1; diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 9d980d88b747..fa029fb2afae 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -58,11 +58,6 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, { return NULL; } - -int pmd_huge_support(void) -{ - return 0; -} #else struct page * @@ -80,11 +75,6 @@ int pud_huge(pud_t pud) { return !!(pud_val(pud) & _PAGE_PSE); } - -int pmd_huge_support(void) -{ - return 1; -} #endif /* x86_64 also uses this file */ diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl index 38ae65dfd14f..63a899304d27 100644 --- a/arch/x86/syscalls/syscall_64.tbl +++ b/arch/x86/syscalls/syscall_64.tbl @@ -212,10 +212,10 @@ 203 common sched_setaffinity sys_sched_setaffinity 204 common sched_getaffinity sys_sched_getaffinity 205 64 set_thread_area -206 common io_setup sys_io_setup +206 64 io_setup sys_io_setup 207 common io_destroy sys_io_destroy 208 common io_getevents sys_io_getevents -209 common io_submit sys_io_submit +209 64 io_submit sys_io_submit 210 common io_cancel sys_io_cancel 211 64 get_thread_area 212 common lookup_dcookie sys_lookup_dcookie @@ -356,3 +356,5 @@ 540 x32 process_vm_writev compat_sys_process_vm_writev 541 x32 setsockopt compat_sys_setsockopt 542 x32 getsockopt compat_sys_getsockopt +543 x32 io_setup compat_sys_io_setup +544 x32 io_submit compat_sys_io_submit diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c index 999adb5499c7..1a8cdf9f94c3 100644 --- a/drivers/acpi/acpi_memhotplug.c +++ b/drivers/acpi/acpi_memhotplug.c @@ -360,7 +360,19 @@ static void acpi_memory_device_remove(struct acpi_device *device) acpi_memory_device_free(mem_device); } +static bool __initdata acpi_no_memhotplug; + void __init acpi_memory_hotplug_init(void) { + if (acpi_no_memhotplug) + return; + acpi_scan_add_handler_with_hotplug(&memory_device_handler, "memory"); } + +static int __init disable_acpi_memory_hotplug(char *str) +{ + acpi_no_memhotplug = true; + return 1; +} +__setup("acpi_no_memhotplug", disable_acpi_memory_hotplug); diff --git a/drivers/acpi/acpica/utstring.c b/drivers/acpi/acpica/utstring.c index cb1e9cc32d5f..3d8748ae488f 100644 --- a/drivers/acpi/acpica/utstring.c +++ b/drivers/acpi/acpica/utstring.c @@ -353,7 +353,7 @@ void acpi_ut_print_string(char *string, u16 max_length) } acpi_os_printf("\""); - for (i = 0; string[i] && (i < max_length); i++) { + for (i = 0; (i < max_length) && string[i]; i++) { /* Escape sequences */ diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 7d83ef13186f..17c12ac42b5b 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -57,6 +57,12 @@ EXPORT_SYMBOL(acpi_root_dir); #ifdef CONFIG_X86 +#ifdef CONFIG_ACPI_CUSTOM_DSDT +static inline int set_copy_dsdt(const struct dmi_system_id *id) +{ + return 0; +} +#else static int set_copy_dsdt(const struct dmi_system_id *id) { printk(KERN_NOTICE "%s detected - " @@ -64,6 +70,7 @@ static int set_copy_dsdt(const struct dmi_system_id *id) acpi_gbl_copy_dsdt_locally = 1; return 0; } +#endif static struct dmi_system_id dsdt_dmi_table[] __initdata = { /* diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c index d2e069044a0f..47e4deb9dfcd 100644 --- a/drivers/acpi/video.c +++ b/drivers/acpi/video.c @@ -81,13 +81,6 @@ module_param(brightness_switch_enabled, bool, 0644); static bool allow_duplicates; module_param(allow_duplicates, bool, 0644); -/* - * Some BIOSes claim they use minimum backlight at boot, - * and this may bring dimming screen after boot - */ -static bool use_bios_initial_backlight = 1; -module_param(use_bios_initial_backlight, bool, 0644); - static int register_count; static int acpi_video_bus_add(struct acpi_device *device); static int acpi_video_bus_remove(struct acpi_device *device); @@ -388,12 +381,6 @@ static int __init video_set_bqc_offset(const struct dmi_system_id *d) return 0; } -static int video_ignore_initial_backlight(const struct dmi_system_id *d) -{ - use_bios_initial_backlight = 0; - return 0; -} - static struct dmi_system_id video_dmi_table[] __initdata = { /* * Broken _BQC workaround http://bugzilla.kernel.org/show_bug.cgi?id=13121 @@ -438,54 +425,6 @@ static struct dmi_system_id video_dmi_table[] __initdata = { DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 7720"), }, }, - { - .callback = video_ignore_initial_backlight, - .ident = "HP Folio 13-2000", - .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "HP Folio 13 - 2000 Notebook PC"), - }, - }, - { - .callback = video_ignore_initial_backlight, - .ident = "Fujitsu E753", - .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "FUJITSU"), - DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E753"), - }, - }, - { - .callback = video_ignore_initial_backlight, - .ident = "HP Pavilion dm4", - .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dm4 Notebook PC"), - }, - }, - { - .callback = video_ignore_initial_backlight, - .ident = "HP Pavilion g6 Notebook PC", - .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion g6 Notebook PC"), - }, - }, - { - .callback = video_ignore_initial_backlight, - .ident = "HP 1000 Notebook PC", - .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "HP 1000 Notebook PC"), - }, - }, - { - .callback = video_ignore_initial_backlight, - .ident = "HP Pavilion m4", - .matches = { - DMI_MATCH(DMI_BOARD_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion m4 Notebook PC"), - }, - }, {} }; @@ -827,20 +766,18 @@ acpi_video_init_brightness(struct acpi_video_device *device) if (!device->cap._BQC) goto set_level; - if (use_bios_initial_backlight) { - level = acpi_video_bqc_value_to_level(device, level_old); - /* - * On some buggy laptops, _BQC returns an uninitialized - * value when invoked for the first time, i.e. - * level_old is invalid (no matter whether it's a level - * or an index). Set the backlight to max_level in this case. - */ - for (i = 2; i < br->count; i++) - if (level == br->levels[i]) - break; - if (i == br->count || !level) - level = max_level; - } + level = acpi_video_bqc_value_to_level(device, level_old); + /* + * On some buggy laptops, _BQC returns an uninitialized + * value when invoked for the first time, i.e. + * level_old is invalid (no matter whether it's a level + * or an index). Set the backlight to max_level in this case. + */ + for (i = 2; i < br->count; i++) + if (level == br->levels[i]) + break; + if (i == br->count || !level) + level = max_level; set_level: result = acpi_video_device_lcd_set_level(device, level); diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index bc68a440d432..c4d2f0e48685 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -118,10 +118,6 @@ static inline struct sk_buff *hci_uart_dequeue(struct hci_uart *hu) int hci_uart_tx_wakeup(struct hci_uart *hu) { - struct tty_struct *tty = hu->tty; - struct hci_dev *hdev = hu->hdev; - struct sk_buff *skb; - if (test_and_set_bit(HCI_UART_SENDING, &hu->tx_state)) { set_bit(HCI_UART_TX_WAKEUP, &hu->tx_state); return 0; @@ -129,6 +125,22 @@ int hci_uart_tx_wakeup(struct hci_uart *hu) BT_DBG(""); + schedule_work(&hu->write_work); + + return 0; +} + +static void hci_uart_write_work(struct work_struct *work) +{ + struct hci_uart *hu = container_of(work, struct hci_uart, write_work); + struct tty_struct *tty = hu->tty; + struct hci_dev *hdev = hu->hdev; + struct sk_buff *skb; + + /* REVISIT: should we cope with bad skbs or ->write() returning + * and error value ? + */ + restart: clear_bit(HCI_UART_TX_WAKEUP, &hu->tx_state); @@ -153,7 +165,6 @@ restart: goto restart; clear_bit(HCI_UART_SENDING, &hu->tx_state); - return 0; } static void hci_uart_init_work(struct work_struct *work) @@ -289,6 +300,7 @@ static int hci_uart_tty_open(struct tty_struct *tty) tty->receive_room = 65536; INIT_WORK(&hu->init_ready, hci_uart_init_work); + INIT_WORK(&hu->write_work, hci_uart_write_work); spin_lock_init(&hu->rx_lock); @@ -326,6 +338,8 @@ static void hci_uart_tty_close(struct tty_struct *tty) if (hdev) hci_uart_close(hdev); + cancel_work_sync(&hu->write_work); + if (test_and_clear_bit(HCI_UART_PROTO_SET, &hu->flags)) { if (hdev) { if (test_bit(HCI_UART_REGISTERED, &hu->flags)) diff --git a/drivers/bluetooth/hci_uart.h b/drivers/bluetooth/hci_uart.h index fffa61ff5cb1..12df101ca942 100644 --- a/drivers/bluetooth/hci_uart.h +++ b/drivers/bluetooth/hci_uart.h @@ -68,6 +68,7 @@ struct hci_uart { unsigned long hdev_flags; struct work_struct init_ready; + struct work_struct write_work; struct hci_uart_proto *proto; void *priv; diff --git a/drivers/char/applicom.c b/drivers/char/applicom.c index 974321a2508d..14790304b84b 100644 --- a/drivers/char/applicom.c +++ b/drivers/char/applicom.c @@ -345,7 +345,6 @@ out: free_irq(apbs[i].irq, &dummy); iounmap(apbs[i].RamIO); } - pci_disable_device(dev); return ret; } diff --git a/drivers/extcon/extcon-max77693.c b/drivers/extcon/extcon-max77693.c index b56bdaa27d4b..9966fc0a527f 100644 --- a/drivers/extcon/extcon-max77693.c +++ b/drivers/extcon/extcon-max77693.c @@ -1180,7 +1180,7 @@ static int max77693_muic_probe(struct platform_device *pdev) /* Initialize MUIC register by using platform data or default data */ - if (pdata->muic_data) { + if (pdata && pdata->muic_data) { init_data = pdata->muic_data->init_data; num_init_data = pdata->muic_data->num_init_data; } else { @@ -1213,7 +1213,7 @@ static int max77693_muic_probe(struct platform_device *pdev) = init_data[i].data; } - if (pdata->muic_data) { + if (pdata && pdata->muic_data) { struct max77693_muic_platform_data *muic_pdata = pdata->muic_data; /* diff --git a/drivers/extcon/extcon-max8997.c b/drivers/extcon/extcon-max8997.c index 67d6738d85a0..09f4a9374cf5 100644 --- a/drivers/extcon/extcon-max8997.c +++ b/drivers/extcon/extcon-max8997.c @@ -712,7 +712,7 @@ static int max8997_muic_probe(struct platform_device *pdev) goto err_irq; } - if (pdata->muic_pdata) { + if (pdata && pdata->muic_pdata) { struct max8997_muic_platform_data *muic_pdata = pdata->muic_pdata; diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c index 743fd426f21b..b1b82e1dfb6b 100644 --- a/drivers/firmware/efi/efi-pstore.c +++ b/drivers/firmware/efi/efi-pstore.c @@ -40,7 +40,7 @@ struct pstore_read_data { static inline u64 generic_id(unsigned long timestamp, unsigned int part, int count) { - return (timestamp * 100 + part) * 1000 + count; + return ((u64) timestamp * 100 + part) * 1000 + count; } static int efi_pstore_read_func(struct efivar_entry *entry, void *data) diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index 7456ce186f29..a134e8bf53f5 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -501,8 +501,11 @@ int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv) radeon_vm_init(rdev, &fpriv->vm); r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false); - if (r) + if (r) { + radeon_vm_fini(rdev, &fpriv->vm); + kfree(fpriv); return r; + } /* map the ib pool buffer read only into * virtual address space */ diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 0335f86502c2..245f8922f813 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -842,7 +842,17 @@ struct hid_report *hid_validate_values(struct hid_device *hid, * ->numbered being checked, which may not always be the case when * drivers go to access report values. */ - report = hid->report_enum[type].report_id_hash[id]; + if (id == 0) { + /* + * Validating on id 0 means we should examine the first + * report in the list. + */ + report = list_entry( + hid->report_enum[type].report_list.next, + struct hid_report, list); + } else { + report = hid->report_enum[type].report_id_hash[id]; + } if (!report) { hid_err(hid, "missing %s %u\n", hid_report_names[type], id); return NULL; diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index 7e17a5495e02..393fd8a98735 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -19,6 +19,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include +#include #include #include #include @@ -459,6 +460,11 @@ static bool do_hot_add; */ static uint pressure_report_delay = 45; +/* + * The last time we posted a pressure report to host. + */ +static unsigned long last_post_time; + module_param(hot_add, bool, (S_IRUGO | S_IWUSR)); MODULE_PARM_DESC(hot_add, "If set attempt memory hot_add"); @@ -542,6 +548,7 @@ struct hv_dynmem_device { static struct hv_dynmem_device dm_device; +static void post_status(struct hv_dynmem_device *dm); #ifdef CONFIG_MEMORY_HOTPLUG static void hv_bring_pgs_online(unsigned long start_pfn, unsigned long size) @@ -612,7 +619,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size, * have not been "onlined" within the allowed time. */ wait_for_completion_timeout(&dm_device.ol_waitevent, 5*HZ); - + post_status(&dm_device); } return; @@ -951,11 +958,17 @@ static void post_status(struct hv_dynmem_device *dm) { struct dm_status status; struct sysinfo val; + unsigned long now = jiffies; + unsigned long last_post = last_post_time; if (pressure_report_delay > 0) { --pressure_report_delay; return; } + + if (!time_after(now, (last_post_time + HZ))) + return; + si_meminfo(&val); memset(&status, 0, sizeof(struct dm_status)); status.hdr.type = DM_STATUS_REPORT; @@ -983,6 +996,14 @@ static void post_status(struct hv_dynmem_device *dm) if (status.hdr.trans_id != atomic_read(&trans_id)) return; + /* + * If the last post time that we sampled has changed, + * we have raced, don't post the status. + */ + if (last_post != last_post_time) + return; + + last_post_time = jiffies; vmbus_sendpacket(dm->dev->channel, &status, sizeof(struct dm_status), (unsigned long)NULL, @@ -1117,7 +1138,7 @@ static void balloon_up(struct work_struct *dummy) if (ret == -EAGAIN) msleep(20); - + post_status(&dm_device); } while (ret == -EAGAIN); if (ret) { @@ -1144,8 +1165,10 @@ static void balloon_down(struct hv_dynmem_device *dm, struct dm_unballoon_response resp; int i; - for (i = 0; i < range_count; i++) + for (i = 0; i < range_count; i++) { free_balloon_pages(dm, &range_array[i]); + post_status(&dm_device); + } if (req->more_pages == 1) return; diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 53235814ea0f..97f4e807c862 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -329,7 +329,7 @@ static struct cpuidle_state atom_cstates[CPUIDLE_STATE_MAX] = { { .enter = NULL } }; -static struct cpuidle_state avn_cstates[] __initdata = { +static struct cpuidle_state avn_cstates[] = { { .name = "C1-AVN", .desc = "MWAIT 0x00", @@ -344,6 +344,8 @@ static struct cpuidle_state avn_cstates[] __initdata = { .exit_latency = 15, .target_residency = 45, .enter = &intel_idle }, + { + .enter = NULL } }; /** diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c index 0f16b553e063..b023cd3fe4f1 100644 --- a/drivers/iio/adc/at91_adc.c +++ b/drivers/iio/adc/at91_adc.c @@ -166,12 +166,11 @@ static int at91_adc_channel_init(struct iio_dev *idev) return idev->num_channels; } -static u8 at91_adc_get_trigger_value_by_name(struct iio_dev *idev, +static int at91_adc_get_trigger_value_by_name(struct iio_dev *idev, struct at91_adc_trigger *triggers, const char *trigger_name) { struct at91_adc_state *st = iio_priv(idev); - u8 value = 0; int i; for (i = 0; i < st->trigger_number; i++) { @@ -184,15 +183,16 @@ static u8 at91_adc_get_trigger_value_by_name(struct iio_dev *idev, return -ENOMEM; if (strcmp(trigger_name, name) == 0) { - value = triggers[i].value; kfree(name); - break; + if (triggers[i].value == 0) + return -EINVAL; + return triggers[i].value; } kfree(name); } - return value; + return -EINVAL; } static int at91_adc_configure_trigger(struct iio_trigger *trig, bool state) @@ -202,14 +202,14 @@ static int at91_adc_configure_trigger(struct iio_trigger *trig, bool state) struct iio_buffer *buffer = idev->buffer; struct at91_adc_reg_desc *reg = st->registers; u32 status = at91_adc_readl(st, reg->trigger_register); - u8 value; + int value; u8 bit; value = at91_adc_get_trigger_value_by_name(idev, st->trigger_list, idev->trig->name); - if (value == 0) - return -EINVAL; + if (value < 0) + return value; if (state) { st->buffer = kmalloc(idev->scan_bytes, GFP_KERNEL); diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c index 9edf4c935fd7..aeba3bbdadb0 100644 --- a/drivers/iio/magnetometer/ak8975.c +++ b/drivers/iio/magnetometer/ak8975.c @@ -352,8 +352,6 @@ static int ak8975_read_axis(struct iio_dev *indio_dev, int index, int *val) { struct ak8975_data *data = iio_priv(indio_dev); struct i2c_client *client = data->client; - u16 meas_reg; - s16 raw; int ret; mutex_lock(&data->lock); @@ -401,16 +399,11 @@ static int ak8975_read_axis(struct iio_dev *indio_dev, int index, int *val) dev_err(&client->dev, "Read axis data fails\n"); goto exit; } - meas_reg = ret; mutex_unlock(&data->lock); - /* Endian conversion of the measured values. */ - raw = (s16) (le16_to_cpu(meas_reg)); - /* Clamp to valid range. */ - raw = clamp_t(s16, raw, -4096, 4095); - *val = raw; + *val = clamp_t(s16, ret, -4096, 4095); return IIO_VAL_INT; exit: diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index 8645d19f7710..548d86847d18 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -688,14 +688,12 @@ isert_disconnect_work(struct work_struct *work) isert_put_conn(isert_conn); return; } - if (!isert_conn->logout_posted) { - pr_debug("Calling rdma_disconnect for !logout_posted from" - " isert_disconnect_work\n"); + + if (isert_conn->disconnect) { + /* Send DREQ/DREP towards our initiator */ rdma_disconnect(isert_conn->conn_cm_id); - mutex_unlock(&isert_conn->conn_mutex); - iscsit_cause_connection_reinstatement(isert_conn->conn, 0); - goto wake_up; } + mutex_unlock(&isert_conn->conn_mutex); wake_up: @@ -704,10 +702,11 @@ wake_up: } static void -isert_disconnected_handler(struct rdma_cm_id *cma_id) +isert_disconnected_handler(struct rdma_cm_id *cma_id, bool disconnect) { struct isert_conn *isert_conn = (struct isert_conn *)cma_id->context; + isert_conn->disconnect = disconnect; INIT_WORK(&isert_conn->conn_logout_work, isert_disconnect_work); schedule_work(&isert_conn->conn_logout_work); } @@ -716,29 +715,28 @@ static int isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) { int ret = 0; + bool disconnect = false; pr_debug("isert_cma_handler: event %d status %d conn %p id %p\n", event->event, event->status, cma_id->context, cma_id); switch (event->event) { case RDMA_CM_EVENT_CONNECT_REQUEST: - pr_debug("RDMA_CM_EVENT_CONNECT_REQUEST: >>>>>>>>>>>>>>>\n"); ret = isert_connect_request(cma_id, event); break; case RDMA_CM_EVENT_ESTABLISHED: - pr_debug("RDMA_CM_EVENT_ESTABLISHED >>>>>>>>>>>>>>\n"); isert_connected_handler(cma_id); break; - case RDMA_CM_EVENT_DISCONNECTED: - pr_debug("RDMA_CM_EVENT_DISCONNECTED: >>>>>>>>>>>>>>\n"); - isert_disconnected_handler(cma_id); - break; - case RDMA_CM_EVENT_DEVICE_REMOVAL: - case RDMA_CM_EVENT_ADDR_CHANGE: + case RDMA_CM_EVENT_ADDR_CHANGE: /* FALLTHRU */ + case RDMA_CM_EVENT_DISCONNECTED: /* FALLTHRU */ + case RDMA_CM_EVENT_DEVICE_REMOVAL: /* FALLTHRU */ + disconnect = true; + case RDMA_CM_EVENT_TIMEWAIT_EXIT: /* FALLTHRU */ + isert_disconnected_handler(cma_id, disconnect); break; case RDMA_CM_EVENT_CONNECT_ERROR: default: - pr_err("Unknown RDMA CMA event: %d\n", event->event); + pr_err("Unhandled RDMA CMA event: %d\n", event->event); break; } @@ -1581,11 +1579,8 @@ isert_do_control_comp(struct work_struct *work) break; case ISTATE_SEND_LOGOUTRSP: pr_debug("Calling iscsit_logout_post_handler >>>>>>>>>>>>>>\n"); - /* - * Call atomic_dec(&isert_conn->post_send_buf_count) - * from isert_wait_conn() - */ - isert_conn->logout_posted = true; + + atomic_dec(&isert_conn->post_send_buf_count); iscsit_logout_post_handler(cmd, cmd->conn); break; case ISTATE_SEND_TEXTRSP: @@ -1699,6 +1694,8 @@ isert_cq_rx_comp_err(struct isert_conn *isert_conn) isert_conn->state = ISER_CONN_DOWN; mutex_unlock(&isert_conn->conn_mutex); + iscsit_cause_connection_reinstatement(isert_conn->conn, 0); + complete(&isert_conn->conn_wait_comp_err); } @@ -1952,7 +1949,7 @@ isert_put_text_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn) int rc; isert_create_send_desc(isert_conn, isert_cmd, &isert_cmd->tx_desc); - rc = iscsit_build_text_rsp(cmd, conn, hdr); + rc = iscsit_build_text_rsp(cmd, conn, hdr, ISCSI_INFINIBAND); if (rc < 0) return rc; @@ -2633,9 +2630,14 @@ accept_wait: return -ENODEV; spin_lock_bh(&np->np_thread_lock); - if (np->np_thread_state == ISCSI_NP_THREAD_RESET) { + if (np->np_thread_state >= ISCSI_NP_THREAD_RESET) { spin_unlock_bh(&np->np_thread_lock); - pr_debug("ISCSI_NP_THREAD_RESET for isert_accept_np\n"); + pr_debug("np_thread_state %d for isert_accept_np\n", + np->np_thread_state); + /** + * No point in stalling here when np_thread + * is in state RESET/SHUTDOWN/EXIT - bail + **/ return -ENODEV; } spin_unlock_bh(&np->np_thread_lock); @@ -2685,15 +2687,9 @@ static void isert_wait_conn(struct iscsi_conn *conn) struct isert_conn *isert_conn = conn->context; pr_debug("isert_wait_conn: Starting \n"); - /* - * Decrement post_send_buf_count for special case when called - * from isert_do_control_comp() -> iscsit_logout_post_handler() - */ - mutex_lock(&isert_conn->conn_mutex); - if (isert_conn->logout_posted) - atomic_dec(&isert_conn->post_send_buf_count); - if (isert_conn->conn_cm_id && isert_conn->state != ISER_CONN_DOWN) { + mutex_lock(&isert_conn->conn_mutex); + if (isert_conn->conn_cm_id) { pr_debug("Calling rdma_disconnect from isert_wait_conn\n"); rdma_disconnect(isert_conn->conn_cm_id); } @@ -2768,6 +2764,7 @@ destroy_rx_wq: static void __exit isert_exit(void) { + flush_scheduled_work(); destroy_workqueue(isert_comp_wq); destroy_workqueue(isert_rx_wq); iscsit_unregister_transport(&iser_target_transport); diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h index ba695c33a2df..90e6aa3c25d2 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.h +++ b/drivers/infiniband/ulp/isert/ib_isert.h @@ -90,7 +90,6 @@ struct isert_device; struct isert_conn { enum iser_conn_state state; - bool logout_posted; int post_recv_buf_count; atomic_t post_send_buf_count; u32 responder_resources; @@ -122,6 +121,7 @@ struct isert_conn { int conn_frwr_pool_size; /* lock to protect frwr_pool */ spinlock_t conn_lock; + bool disconnect; }; #define ISERT_MAX_CQ 64 diff --git a/drivers/media/pci/ivtv/ivtv-alsa-pcm.c b/drivers/media/pci/ivtv/ivtv-alsa-pcm.c index e1863dbf4edc..7a9b98bc208b 100644 --- a/drivers/media/pci/ivtv/ivtv-alsa-pcm.c +++ b/drivers/media/pci/ivtv/ivtv-alsa-pcm.c @@ -159,6 +159,12 @@ static int snd_ivtv_pcm_capture_open(struct snd_pcm_substream *substream) /* Instruct the CX2341[56] to start sending packets */ snd_ivtv_lock(itvsc); + + if (ivtv_init_on_first_open(itv)) { + snd_ivtv_unlock(itvsc); + return -ENXIO; + } + s = &itv->streams[IVTV_ENC_STREAM_TYPE_PCM]; v4l2_fh_init(&item.fh, s->vdev); diff --git a/drivers/media/usb/stk1160/stk1160-core.c b/drivers/media/usb/stk1160/stk1160-core.c index 34a26e0cfe77..03504dcf3c52 100644 --- a/drivers/media/usb/stk1160/stk1160-core.c +++ b/drivers/media/usb/stk1160/stk1160-core.c @@ -67,17 +67,25 @@ int stk1160_read_reg(struct stk1160 *dev, u16 reg, u8 *value) { int ret; int pipe = usb_rcvctrlpipe(dev->udev, 0); + u8 *buf; *value = 0; + + buf = kmalloc(sizeof(u8), GFP_KERNEL); + if (!buf) + return -ENOMEM; ret = usb_control_msg(dev->udev, pipe, 0x00, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, - 0x00, reg, value, sizeof(u8), HZ); + 0x00, reg, buf, sizeof(u8), HZ); if (ret < 0) { stk1160_err("read failed on reg 0x%x (%d)\n", reg, ret); + kfree(buf); return ret; } + *value = *buf; + kfree(buf); return 0; } diff --git a/drivers/media/usb/stk1160/stk1160.h b/drivers/media/usb/stk1160/stk1160.h index 05b05b160e1e..abdea484c998 100644 --- a/drivers/media/usb/stk1160/stk1160.h +++ b/drivers/media/usb/stk1160/stk1160.h @@ -143,7 +143,6 @@ struct stk1160 { int num_alt; struct stk1160_isoc_ctl isoc_ctl; - char urb_buf[255]; /* urb control msg buffer */ /* frame properties */ int width; /* current frame width */ diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c index e1c5bf3ea112..c081812ac5c0 100644 --- a/drivers/media/usb/uvc/uvc_video.c +++ b/drivers/media/usb/uvc/uvc_video.c @@ -361,6 +361,14 @@ static int uvc_commit_video(struct uvc_streaming *stream, * Clocks and timestamps */ +static inline void uvc_video_get_ts(struct timespec *ts) +{ + if (uvc_clock_param == CLOCK_MONOTONIC) + ktime_get_ts(ts); + else + ktime_get_real_ts(ts); +} + static void uvc_video_clock_decode(struct uvc_streaming *stream, struct uvc_buffer *buf, const __u8 *data, int len) @@ -420,7 +428,7 @@ uvc_video_clock_decode(struct uvc_streaming *stream, struct uvc_buffer *buf, stream->clock.last_sof = dev_sof; host_sof = usb_get_current_frame_number(stream->dev->udev); - ktime_get_ts(&ts); + uvc_video_get_ts(&ts); /* The UVC specification allows device implementations that can't obtain * the USB frame number to keep their own frame counters as long as they @@ -1010,10 +1018,7 @@ static int uvc_video_decode_start(struct uvc_streaming *stream, return -ENODATA; } - if (uvc_clock_param == CLOCK_MONOTONIC) - ktime_get_ts(&ts); - else - ktime_get_real_ts(&ts); + uvc_video_get_ts(&ts); buf->buf.v4l2_buf.sequence = stream->sequence; buf->buf.v4l2_buf.timestamp.tv_sec = ts.tv_sec; diff --git a/drivers/mfd/sm501.c b/drivers/mfd/sm501.c index 33f040c558d0..3799a3d64415 100644 --- a/drivers/mfd/sm501.c +++ b/drivers/mfd/sm501.c @@ -1232,7 +1232,7 @@ static ssize_t sm501_dbg_regs(struct device *dev, } -static DEVICE_ATTR(dbg_regs, 0666, sm501_dbg_regs, NULL); +static DEVICE_ATTR(dbg_regs, 0444, sm501_dbg_regs, NULL); /* sm501_init_reg * diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c index 6cba26d9465f..e513354f20a7 100644 --- a/drivers/misc/mei/hw-me.c +++ b/drivers/misc/mei/hw-me.c @@ -164,6 +164,9 @@ static void mei_me_hw_reset_release(struct mei_device *dev) hcsr |= H_IG; hcsr &= ~H_RST; mei_hcsr_set(hw, hcsr); + + /* complete this write before we set host ready on another CPU */ + mmiowb(); } /** * mei_me_hw_reset - resets fw via mei csr register. @@ -186,7 +189,19 @@ static int mei_me_hw_reset(struct mei_device *dev, bool intr_enable) dev->recvd_hw_ready = false; mei_me_reg_write(hw, H_CSR, hcsr); - if (dev->dev_state == MEI_DEV_POWER_DOWN) + /* + * Host reads the H_CSR once to ensure that the + * posted write to H_CSR completes. + */ + hcsr = mei_hcsr_read(hw); + + if ((hcsr & H_RST) == 0) + dev_warn(&dev->pdev->dev, "H_RST is not set = 0x%08X", hcsr); + + if ((hcsr & H_RDY) == H_RDY) + dev_warn(&dev->pdev->dev, "H_RDY is not cleared 0x%08X", hcsr); + + if (intr_enable == false) mei_me_hw_reset_release(dev); return 0; @@ -202,6 +217,7 @@ static int mei_me_hw_reset(struct mei_device *dev, bool intr_enable) static void mei_me_host_set_ready(struct mei_device *dev) { struct mei_me_hw *hw = to_me_hw(dev); + hw->host_hw_state = mei_hcsr_read(hw); hw->host_hw_state |= H_IE | H_IG | H_RDY; mei_hcsr_set(hw, hw->host_hw_state); } @@ -494,19 +510,15 @@ irqreturn_t mei_me_irq_thread_handler(int irq, void *dev_id) /* check if we need to start the dev */ if (!mei_host_is_ready(dev)) { if (mei_hw_is_ready(dev)) { + mei_me_hw_reset_release(dev); dev_dbg(&dev->pdev->dev, "we need to start the dev.\n"); dev->recvd_hw_ready = true; wake_up_interruptible(&dev->wait_hw_ready); - - mutex_unlock(&dev->device_lock); - return IRQ_HANDLED; } else { - dev_dbg(&dev->pdev->dev, "Reset Completed.\n"); - mei_me_hw_reset_release(dev); - mutex_unlock(&dev->device_lock); - return IRQ_HANDLED; + dev_dbg(&dev->pdev->dev, "Spurious Interrupt\n"); } + goto end; } /* check slots available for reading */ slots = mei_count_full_read_slots(dev); diff --git a/drivers/net/can/sja1000/peak_pci.c b/drivers/net/can/sja1000/peak_pci.c index 6b6f0ad75090..7042f5faddd7 100644 --- a/drivers/net/can/sja1000/peak_pci.c +++ b/drivers/net/can/sja1000/peak_pci.c @@ -551,7 +551,7 @@ static int peak_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct sja1000_priv *priv; struct peak_pci_chan *chan; - struct net_device *dev; + struct net_device *dev, *prev_dev; void __iomem *cfg_base, *reg_base; u16 sub_sys_id, icr; int i, err, channels; @@ -687,11 +687,13 @@ failure_remove_channels: writew(0x0, cfg_base + PITA_ICR + 2); chan = NULL; - for (dev = pci_get_drvdata(pdev); dev; dev = chan->prev_dev) { - unregister_sja1000dev(dev); - free_sja1000dev(dev); + for (dev = pci_get_drvdata(pdev); dev; dev = prev_dev) { priv = netdev_priv(dev); chan = priv->priv; + prev_dev = chan->prev_dev; + + unregister_sja1000dev(dev); + free_sja1000dev(dev); } /* free any PCIeC resources too */ @@ -725,10 +727,12 @@ static void peak_pci_remove(struct pci_dev *pdev) /* Loop over all registered devices */ while (1) { + struct net_device *prev_dev = chan->prev_dev; + dev_info(&pdev->dev, "removing device %s\n", dev->name); unregister_sja1000dev(dev); free_sja1000dev(dev); - dev = chan->prev_dev; + dev = prev_dev; if (!dev) { /* do that only for first channel */ diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index cc3ce557e4aa..498e808391a9 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -1797,6 +1797,10 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, mdio_node = of_find_node_by_phandle(be32_to_cpup(parp)); phyid = be32_to_cpup(parp+1); mdio = of_find_device_by_node(mdio_node); + if (!mdio) { + pr_err("Missing mdio platform device\n"); + return -EINVAL; + } snprintf(slave_data->phy_id, sizeof(slave_data->phy_id), PHY_ID_FMT, mdio->name, phyid); diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index 573f4128b6b6..074f278f7dab 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -10005,6 +10005,12 @@ static struct pci_device_id ipr_pci_table[] = { PCI_VENDOR_ID_IBM, IPR_SUBS_DEV_ID_57EF, 0, 0, 0 }, { PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_CROCODILE, PCI_VENDOR_ID_IBM, IPR_SUBS_DEV_ID_57F0, 0, 0, 0 }, + { PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_CROCODILE, + PCI_VENDOR_ID_IBM, IPR_SUBS_DEV_ID_2CCA, 0, 0, 0 }, + { PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_CROCODILE, + PCI_VENDOR_ID_IBM, IPR_SUBS_DEV_ID_2CD2, 0, 0, 0 }, + { PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_CROCODILE, + PCI_VENDOR_ID_IBM, IPR_SUBS_DEV_ID_2CCD, 0, 0, 0 }, { } }; MODULE_DEVICE_TABLE(pci, ipr_pci_table); diff --git a/drivers/scsi/ipr.h b/drivers/scsi/ipr.h index cad1483f05da..58c6630fe3e2 100644 --- a/drivers/scsi/ipr.h +++ b/drivers/scsi/ipr.h @@ -107,6 +107,9 @@ #define IPR_SUBS_DEV_ID_57EE 0x049A #define IPR_SUBS_DEV_ID_57EF 0x049B #define IPR_SUBS_DEV_ID_57F0 0x049C +#define IPR_SUBS_DEV_ID_2CCA 0x04C7 +#define IPR_SUBS_DEV_ID_2CD2 0x04C8 +#define IPR_SUBS_DEV_ID_2CCD 0x04C9 #define IPR_NAME "ipr" /* diff --git a/drivers/staging/iio/light/tsl2x7x_core.c b/drivers/staging/iio/light/tsl2x7x_core.c index c99f890cc6c6..64c73adfa3b0 100644 --- a/drivers/staging/iio/light/tsl2x7x_core.c +++ b/drivers/staging/iio/light/tsl2x7x_core.c @@ -672,9 +672,13 @@ static int tsl2x7x_chip_on(struct iio_dev *indio_dev) chip->tsl2x7x_config[TSL2X7X_PRX_COUNT] = chip->tsl2x7x_settings.prox_pulse_count; chip->tsl2x7x_config[TSL2X7X_PRX_MINTHRESHLO] = - chip->tsl2x7x_settings.prox_thres_low; + (chip->tsl2x7x_settings.prox_thres_low) & 0xFF; + chip->tsl2x7x_config[TSL2X7X_PRX_MINTHRESHHI] = + (chip->tsl2x7x_settings.prox_thres_low >> 8) & 0xFF; chip->tsl2x7x_config[TSL2X7X_PRX_MAXTHRESHLO] = - chip->tsl2x7x_settings.prox_thres_high; + (chip->tsl2x7x_settings.prox_thres_high) & 0xFF; + chip->tsl2x7x_config[TSL2X7X_PRX_MAXTHRESHHI] = + (chip->tsl2x7x_settings.prox_thres_high >> 8) & 0xFF; /* and make sure we're not already on */ if (chip->tsl2x7x_chip_status == TSL2X7X_CHIP_WORKING) { diff --git a/drivers/staging/rtl8188eu/core/rtw_wlan_util.c b/drivers/staging/rtl8188eu/core/rtw_wlan_util.c index 8018edd3d42e..ce638d1723e3 100644 --- a/drivers/staging/rtl8188eu/core/rtw_wlan_util.c +++ b/drivers/staging/rtl8188eu/core/rtw_wlan_util.c @@ -1607,13 +1607,18 @@ int update_sta_support_rate(struct adapter *padapter, u8 *pvar_ie, uint var_ie_l pIE = (struct ndis_802_11_var_ie *)rtw_get_ie(pvar_ie, _SUPPORTEDRATES_IE_, &ie_len, var_ie_len); if (pIE == NULL) return _FAIL; + if (ie_len > NDIS_802_11_LENGTH_RATES_EX) + return _FAIL; memcpy(pmlmeinfo->FW_sta_info[cam_idx].SupportedRates, pIE->data, ie_len); supportRateNum = ie_len; pIE = (struct ndis_802_11_var_ie *)rtw_get_ie(pvar_ie, _EXT_SUPPORTEDRATES_IE_, &ie_len, var_ie_len); - if (pIE) + if (pIE) { + if (supportRateNum + ie_len > NDIS_802_11_LENGTH_RATES_EX) + return _FAIL; memcpy((pmlmeinfo->FW_sta_info[cam_idx].SupportedRates + supportRateNum), pIE->data, ie_len); + } return _SUCCESS; } diff --git a/drivers/staging/tidspbridge/core/dsp-clock.c b/drivers/staging/tidspbridge/core/dsp-clock.c index 2f084e181d39..a1aca4416ca7 100644 --- a/drivers/staging/tidspbridge/core/dsp-clock.c +++ b/drivers/staging/tidspbridge/core/dsp-clock.c @@ -226,7 +226,7 @@ int dsp_clk_enable(enum dsp_clk_id clk_id) case GPT_CLK: status = omap_dm_timer_start(timer[clk_id - 1]); break; -#ifdef CONFIG_OMAP_MCBSP +#ifdef CONFIG_SND_OMAP_SOC_MCBSP case MCBSP_CLK: omap_mcbsp_request(MCBSP_ID(clk_id)); omap2_mcbsp_set_clks_src(MCBSP_ID(clk_id), MCBSP_CLKS_PAD_SRC); @@ -302,7 +302,7 @@ int dsp_clk_disable(enum dsp_clk_id clk_id) case GPT_CLK: status = omap_dm_timer_stop(timer[clk_id - 1]); break; -#ifdef CONFIG_OMAP_MCBSP +#ifdef CONFIG_SND_OMAP_SOC_MCBSP case MCBSP_CLK: omap2_mcbsp_set_clks_src(MCBSP_ID(clk_id), MCBSP_CLKS_PRCM_SRC); omap_mcbsp_free(MCBSP_ID(clk_id)); diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 6f69e4e3af8c..f99162542df2 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -3378,7 +3378,9 @@ static bool iscsit_check_inaddr_any(struct iscsi_np *np) #define SENDTARGETS_BUF_LIMIT 32768U -static int iscsit_build_sendtargets_response(struct iscsi_cmd *cmd) +static int +iscsit_build_sendtargets_response(struct iscsi_cmd *cmd, + enum iscsit_transport_type network_transport) { char *payload = NULL; struct iscsi_conn *conn = cmd->conn; @@ -3450,6 +3452,9 @@ static int iscsit_build_sendtargets_response(struct iscsi_cmd *cmd) struct iscsi_np *np = tpg_np->tpg_np; bool inaddr_any = iscsit_check_inaddr_any(np); + if (np->np_network_transport != network_transport) + continue; + len = sprintf(buf, "TargetAddress=" "%s:%hu,%hu", (inaddr_any == false) ? @@ -3487,11 +3492,12 @@ eob: int iscsit_build_text_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn, - struct iscsi_text_rsp *hdr) + struct iscsi_text_rsp *hdr, + enum iscsit_transport_type network_transport) { int text_length, padding; - text_length = iscsit_build_sendtargets_response(cmd); + text_length = iscsit_build_sendtargets_response(cmd, network_transport); if (text_length < 0) return text_length; @@ -3529,7 +3535,7 @@ static int iscsit_send_text_rsp( u32 tx_size = 0; int text_length, iov_count = 0, rc; - rc = iscsit_build_text_rsp(cmd, conn, hdr); + rc = iscsit_build_text_rsp(cmd, conn, hdr, ISCSI_TCP); if (rc < 0) return rc; @@ -4203,8 +4209,6 @@ int iscsit_close_connection( if (conn->conn_transport->iscsit_wait_conn) conn->conn_transport->iscsit_wait_conn(conn); - iscsit_free_queue_reqs_for_conn(conn); - /* * During Connection recovery drop unacknowledged out of order * commands for this connection, and prepare the other commands @@ -4221,6 +4225,7 @@ int iscsit_close_connection( iscsit_clear_ooo_cmdsns_for_conn(conn); iscsit_release_commands_from_conn(conn); } + iscsit_free_queue_reqs_for_conn(conn); /* * Handle decrementing session or connection usage count if diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c index 131327ac7f5b..9f6bedecda6e 100644 --- a/drivers/target/target_core_rd.c +++ b/drivers/target/target_core_rd.c @@ -179,7 +179,7 @@ static int rd_build_device_space(struct rd_dev *rd_dev) - 1; for (j = 0; j < sg_per_table; j++) { - pg = alloc_pages(GFP_KERNEL, 0); + pg = alloc_pages(GFP_KERNEL | __GFP_ZERO, 0); if (!pg) { pr_err("Unable to allocate scatterlist" " pages for struct rd_dev_sg_table\n"); diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c index e84149895af2..214522282c19 100644 --- a/drivers/target/target_core_sbc.c +++ b/drivers/target/target_core_sbc.c @@ -80,7 +80,7 @@ sbc_emulate_readcapacity(struct se_cmd *cmd) transport_kunmap_data_sg(cmd); } - target_complete_cmd(cmd, GOOD); + target_complete_cmd_with_length(cmd, GOOD, 8); return 0; } @@ -118,7 +118,7 @@ sbc_emulate_readcapacity_16(struct se_cmd *cmd) transport_kunmap_data_sg(cmd); } - target_complete_cmd(cmd, GOOD); + target_complete_cmd_with_length(cmd, GOOD, 32); return 0; } diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c index 074539558a54..ee400df1fea2 100644 --- a/drivers/target/target_core_spc.c +++ b/drivers/target/target_core_spc.c @@ -639,6 +639,7 @@ spc_emulate_inquiry(struct se_cmd *cmd) unsigned char buf[SE_INQUIRY_BUF]; sense_reason_t ret; int p; + int len = 0; memset(buf, 0, SE_INQUIRY_BUF); @@ -656,6 +657,7 @@ spc_emulate_inquiry(struct se_cmd *cmd) } ret = spc_emulate_inquiry_std(cmd, buf); + len = buf[4] + 5; goto out; } @@ -663,6 +665,7 @@ spc_emulate_inquiry(struct se_cmd *cmd) if (cdb[2] == evpd_handlers[p].page) { buf[1] = cdb[2]; ret = evpd_handlers[p].emulate(cmd, buf); + len = get_unaligned_be16(&buf[2]) + 4; goto out; } } @@ -678,7 +681,7 @@ out: } if (!ret) - target_complete_cmd(cmd, GOOD); + target_complete_cmd_with_length(cmd, GOOD, len); return ret; } @@ -996,7 +999,7 @@ set_length: transport_kunmap_data_sg(cmd); } - target_complete_cmd(cmd, GOOD); + target_complete_cmd_with_length(cmd, GOOD, length); return 0; } @@ -1173,7 +1176,7 @@ done: buf[3] = (lun_count & 0xff); transport_kunmap_data_sg(cmd); - target_complete_cmd(cmd, GOOD); + target_complete_cmd_with_length(cmd, GOOD, 8 + lun_count * 8); return 0; } EXPORT_SYMBOL(spc_emulate_report_luns); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index edacb8d0d6b8..334c3364837d 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -552,7 +552,7 @@ static int transport_cmd_check_stop(struct se_cmd *cmd, bool remove_from_lists, spin_unlock_irqrestore(&cmd->t_state_lock, flags); - complete(&cmd->t_transport_stop_comp); + complete_all(&cmd->t_transport_stop_comp); return 1; } @@ -674,7 +674,7 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status) if (cmd->transport_state & CMD_T_ABORTED && cmd->transport_state & CMD_T_STOP) { spin_unlock_irqrestore(&cmd->t_state_lock, flags); - complete(&cmd->t_transport_stop_comp); + complete_all(&cmd->t_transport_stop_comp); return; } else if (cmd->transport_state & CMD_T_FAILED) { INIT_WORK(&cmd->work, target_complete_failure_work); @@ -690,6 +690,23 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status) } EXPORT_SYMBOL(target_complete_cmd); +void target_complete_cmd_with_length(struct se_cmd *cmd, u8 scsi_status, int length) +{ + if (scsi_status == SAM_STAT_GOOD && length < cmd->data_length) { + if (cmd->se_cmd_flags & SCF_UNDERFLOW_BIT) { + cmd->residual_count += cmd->data_length - length; + } else { + cmd->se_cmd_flags |= SCF_UNDERFLOW_BIT; + cmd->residual_count = cmd->data_length - length; + } + + cmd->data_length = length; + } + + target_complete_cmd(cmd, scsi_status); +} +EXPORT_SYMBOL(target_complete_cmd_with_length); + static void target_add_to_state_list(struct se_cmd *cmd) { struct se_device *dev = cmd->se_dev; @@ -1749,7 +1766,7 @@ void target_execute_cmd(struct se_cmd *cmd) cmd->se_tfo->get_task_tag(cmd)); spin_unlock_irq(&cmd->t_state_lock); - complete(&cmd->t_transport_stop_comp); + complete_all(&cmd->t_transport_stop_comp); return; } @@ -3001,6 +3018,12 @@ static void target_tmr_work(struct work_struct *work) int transport_generic_handle_tmr( struct se_cmd *cmd) { + unsigned long flags; + + spin_lock_irqsave(&cmd->t_state_lock, flags); + cmd->transport_state |= CMD_T_ACTIVE; + spin_unlock_irqrestore(&cmd->t_state_lock, flags); + INIT_WORK(&cmd->work, target_tmr_work); queue_work(cmd->se_dev->tmr_wq, &cmd->work); return 0; diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c index 8b2accbad3d1..70ecf541b77a 100644 --- a/drivers/tty/serial/8250/8250_dw.c +++ b/drivers/tty/serial/8250/8250_dw.c @@ -56,7 +56,6 @@ struct dw8250_data { - int last_lcr; int last_mcr; int line; struct clk *clk; @@ -76,17 +75,34 @@ static inline int dw8250_modify_msr(struct uart_port *p, int offset, int value) return value; } +static void dw8250_force_idle(struct uart_port *p) +{ + serial8250_clear_and_reinit_fifos(container_of + (p, struct uart_8250_port, port)); + (void)p->serial_in(p, UART_RX); +} + static void dw8250_serial_out(struct uart_port *p, int offset, int value) { struct dw8250_data *d = p->private_data; - if (offset == UART_LCR) - d->last_lcr = value; - if (offset == UART_MCR) d->last_mcr = value; writeb(value, p->membase + (offset << p->regshift)); + + /* Make sure LCR write wasn't ignored */ + if (offset == UART_LCR) { + int tries = 1000; + while (tries--) { + unsigned int lcr = p->serial_in(p, UART_LCR); + if ((value & ~UART_LCR_SPAR) == (lcr & ~UART_LCR_SPAR)) + return; + dw8250_force_idle(p); + writeb(value, p->membase + (UART_LCR << p->regshift)); + } + dev_err(p->dev, "Couldn't set LCR to %d\n", value); + } } static unsigned int dw8250_serial_in(struct uart_port *p, int offset) @@ -107,13 +123,23 @@ static void dw8250_serial_out32(struct uart_port *p, int offset, int value) { struct dw8250_data *d = p->private_data; - if (offset == UART_LCR) - d->last_lcr = value; - if (offset == UART_MCR) d->last_mcr = value; writel(value, p->membase + (offset << p->regshift)); + + /* Make sure LCR write wasn't ignored */ + if (offset == UART_LCR) { + int tries = 1000; + while (tries--) { + unsigned int lcr = p->serial_in(p, UART_LCR); + if ((value & ~UART_LCR_SPAR) == (lcr & ~UART_LCR_SPAR)) + return; + dw8250_force_idle(p); + writel(value, p->membase + (UART_LCR << p->regshift)); + } + dev_err(p->dev, "Couldn't set LCR to %d\n", value); + } } static unsigned int dw8250_serial_in32(struct uart_port *p, int offset) @@ -131,9 +157,8 @@ static int dw8250_handle_irq(struct uart_port *p) if (serial8250_handle_irq(p, iir)) { return 1; } else if ((iir & UART_IIR_BUSY) == UART_IIR_BUSY) { - /* Clear the USR and write the LCR again. */ + /* Clear the USR */ (void)p->serial_in(p, d->usr_reg); - p->serial_out(p, UART_LCR, d->last_lcr); return 1; } diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 0b5e381bcbe6..669836ae53e0 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -122,13 +122,23 @@ static void acm_release_minor(struct acm *acm) static int acm_ctrl_msg(struct acm *acm, int request, int value, void *buf, int len) { - int retval = usb_control_msg(acm->dev, usb_sndctrlpipe(acm->dev, 0), + int retval; + + retval = usb_autopm_get_interface(acm->control); + if (retval) + return retval; + + retval = usb_control_msg(acm->dev, usb_sndctrlpipe(acm->dev, 0), request, USB_RT_ACM, value, acm->control->altsetting[0].desc.bInterfaceNumber, buf, len, 5000); + dev_dbg(&acm->control->dev, "%s - rq 0x%02x, val %#x, len %#x, result %d\n", __func__, request, value, len, retval); + + usb_autopm_put_interface(acm->control); + return retval < 0 ? retval : 0; } @@ -484,6 +494,7 @@ static int acm_port_activate(struct tty_port *port, struct tty_struct *tty) { struct acm *acm = container_of(port, struct acm, port); int retval = -ENODEV; + int i; dev_dbg(&acm->control->dev, "%s\n", __func__); @@ -532,6 +543,8 @@ static int acm_port_activate(struct tty_port *port, struct tty_struct *tty) return 0; error_submit_read_urbs: + for (i = 0; i < acm->rx_buflimit; i++) + usb_kill_urb(acm->read_urbs[i]); acm->ctrlout = 0; acm_set_control(acm, acm->ctrlout); error_set_control: @@ -559,21 +572,35 @@ static void acm_port_destruct(struct tty_port *port) static void acm_port_shutdown(struct tty_port *port) { struct acm *acm = container_of(port, struct acm, port); + struct urb *urb; + struct acm_wb *wb; int i; + int pm_err; dev_dbg(&acm->control->dev, "%s\n", __func__); mutex_lock(&acm->mutex); if (!acm->disconnected) { - usb_autopm_get_interface(acm->control); + pm_err = usb_autopm_get_interface(acm->control); acm_set_control(acm, acm->ctrlout = 0); + + for (;;) { + urb = usb_get_from_anchor(&acm->delayed); + if (!urb) + break; + wb = urb->context; + wb->use = 0; + usb_autopm_put_interface_async(acm->control); + } + usb_kill_urb(acm->ctrlurb); for (i = 0; i < ACM_NW; i++) usb_kill_urb(acm->wb[i].urb); for (i = 0; i < acm->rx_buflimit; i++) usb_kill_urb(acm->read_urbs[i]); acm->control->needs_remote_wakeup = 0; - usb_autopm_put_interface(acm->control); + if (!pm_err) + usb_autopm_put_interface(acm->control); } mutex_unlock(&acm->mutex); } @@ -632,14 +659,17 @@ static int acm_tty_write(struct tty_struct *tty, memcpy(wb->buf, buf, count); wb->len = count; - usb_autopm_get_interface_async(acm->control); + stat = usb_autopm_get_interface_async(acm->control); + if (stat) { + wb->use = 0; + spin_unlock_irqrestore(&acm->write_lock, flags); + return stat; + } + if (acm->susp_count) { - if (!acm->delayed_wb) - acm->delayed_wb = wb; - else - usb_autopm_put_interface_async(acm->control); + usb_anchor_urb(wb->urb, &acm->delayed); spin_unlock_irqrestore(&acm->write_lock, flags); - return count; /* A white lie */ + return count; } usb_mark_last_busy(acm->dev); @@ -1176,6 +1206,7 @@ made_compressed_probe: acm->bInterval = epread->bInterval; tty_port_init(&acm->port); acm->port.ops = &acm_port_ops; + init_usb_anchor(&acm->delayed); buf = usb_alloc_coherent(usb_dev, ctrlsize, GFP_KERNEL, &acm->ctrl_dma); if (!buf) { @@ -1420,18 +1451,15 @@ static int acm_suspend(struct usb_interface *intf, pm_message_t message) struct acm *acm = usb_get_intfdata(intf); int cnt; + spin_lock_irq(&acm->read_lock); + spin_lock(&acm->write_lock); if (PMSG_IS_AUTO(message)) { - int b; - - spin_lock_irq(&acm->write_lock); - b = acm->transmitting; - spin_unlock_irq(&acm->write_lock); - if (b) + if (acm->transmitting) { + spin_unlock(&acm->write_lock); + spin_unlock_irq(&acm->read_lock); return -EBUSY; + } } - - spin_lock_irq(&acm->read_lock); - spin_lock(&acm->write_lock); cnt = acm->susp_count++; spin_unlock(&acm->write_lock); spin_unlock_irq(&acm->read_lock); @@ -1439,8 +1467,7 @@ static int acm_suspend(struct usb_interface *intf, pm_message_t message) if (cnt) return 0; - if (test_bit(ASYNCB_INITIALIZED, &acm->port.flags)) - stop_data_traffic(acm); + stop_data_traffic(acm); return 0; } @@ -1448,29 +1475,24 @@ static int acm_suspend(struct usb_interface *intf, pm_message_t message) static int acm_resume(struct usb_interface *intf) { struct acm *acm = usb_get_intfdata(intf); - struct acm_wb *wb; + struct urb *urb; int rv = 0; - int cnt; spin_lock_irq(&acm->read_lock); - acm->susp_count -= 1; - cnt = acm->susp_count; - spin_unlock_irq(&acm->read_lock); + spin_lock(&acm->write_lock); - if (cnt) - return 0; + if (--acm->susp_count) + goto out; if (test_bit(ASYNCB_INITIALIZED, &acm->port.flags)) { - rv = usb_submit_urb(acm->ctrlurb, GFP_NOIO); - - spin_lock_irq(&acm->write_lock); - if (acm->delayed_wb) { - wb = acm->delayed_wb; - acm->delayed_wb = NULL; - spin_unlock_irq(&acm->write_lock); - acm_start_wb(acm, wb); - } else { - spin_unlock_irq(&acm->write_lock); + rv = usb_submit_urb(acm->ctrlurb, GFP_ATOMIC); + + for (;;) { + urb = usb_get_from_anchor(&acm->delayed); + if (!urb) + break; + + acm_start_wb(acm, urb->context); } /* @@ -1478,12 +1500,14 @@ static int acm_resume(struct usb_interface *intf) * do the write path at all cost */ if (rv < 0) - goto err_out; + goto out; - rv = acm_submit_read_urbs(acm, GFP_NOIO); + rv = acm_submit_read_urbs(acm, GFP_ATOMIC); } +out: + spin_unlock(&acm->write_lock); + spin_unlock_irq(&acm->read_lock); -err_out: return rv; } diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h index 0f76e4af600e..1683ac161cf6 100644 --- a/drivers/usb/class/cdc-acm.h +++ b/drivers/usb/class/cdc-acm.h @@ -117,7 +117,7 @@ struct acm { unsigned int throttled:1; /* actually throttled */ unsigned int throttle_req:1; /* throttle requested */ u8 bInterval; - struct acm_wb *delayed_wb; /* write queued for a device about to be woken */ + struct usb_anchor delayed; /* writes queued for a device about to be woken */ }; #define CDC_DATA_INTERFACE_TYPE 0x0a diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 02e44fcaf205..c37da0c9a076 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -586,6 +586,10 @@ static int __dwc3_gadget_ep_disable(struct dwc3_ep *dep) dwc3_remove_requests(dwc, dep); + /* make sure HW endpoint isn't stalled */ + if (dep->flags & DWC3_EP_STALL) + __dwc3_gadget_ep_set_halt(dep, 0); + reg = dwc3_readl(dwc->regs, DWC3_DALEPENA); reg &= ~DWC3_DALEPENA_EP(dep->number); dwc3_writel(dwc->regs, DWC3_DALEPENA, reg); diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c index b94c049ab0d0..4ac9e9928d67 100644 --- a/drivers/usb/gadget/inode.c +++ b/drivers/usb/gadget/inode.c @@ -1504,7 +1504,7 @@ gadgetfs_setup (struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) } break; -#ifndef CONFIG_USB_GADGET_PXA25X +#ifndef CONFIG_USB_PXA25X /* PXA automagically handles this request too */ case USB_REQ_GET_CONFIGURATION: if (ctrl->bRequestType != 0x80) diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index f8763cc9d301..877f87f9513b 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -645,6 +645,14 @@ static const struct dmi_system_id ehci_dmi_nohandoff_table[] = { DMI_MATCH(DMI_BIOS_VERSION, "Lucid-"), }, }, + { + /* HASEE E200 */ + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "HASEE"), + DMI_MATCH(DMI_BOARD_NAME, "E210"), + DMI_MATCH(DMI_BIOS_VERSION, "6.00"), + }, + }, { } }; @@ -654,9 +662,14 @@ static void ehci_bios_handoff(struct pci_dev *pdev, { int try_handoff = 1, tried_handoff = 0; - /* The Pegatron Lucid tablet sporadically waits for 98 seconds trying - * the handoff on its unused controller. Skip it. */ - if (pdev->vendor == 0x8086 && pdev->device == 0x283a) { + /* + * The Pegatron Lucid tablet sporadically waits for 98 seconds trying + * the handoff on its unused controller. Skip it. + * + * The HASEE E200 hangs when the semaphore is set (bugzilla #77021). + */ + if (pdev->vendor == 0x8086 && (pdev->device == 0x283a || + pdev->device == 0x27cc)) { if (dmi_check_system(ehci_dmi_nohandoff_table)) try_handoff = 0; } diff --git a/drivers/usb/misc/usbtest.c b/drivers/usb/misc/usbtest.c index aa28ac8c7607..9a1297eb1abc 100644 --- a/drivers/usb/misc/usbtest.c +++ b/drivers/usb/misc/usbtest.c @@ -7,9 +7,10 @@ #include #include #include - +#include #include +#define SIMPLE_IO_TIMEOUT 10000 /* in milliseconds */ /*-------------------------------------------------------------------------*/ @@ -366,6 +367,7 @@ static int simple_io( int max = urb->transfer_buffer_length; struct completion completion; int retval = 0; + unsigned long expire; urb->context = &completion; while (retval == 0 && iterations-- > 0) { @@ -378,9 +380,15 @@ static int simple_io( if (retval != 0) break; - /* NOTE: no timeouts; can't be broken out of by interrupt */ - wait_for_completion(&completion); - retval = urb->status; + expire = msecs_to_jiffies(SIMPLE_IO_TIMEOUT); + if (!wait_for_completion_timeout(&completion, expire)) { + usb_kill_urb(urb); + retval = (urb->status == -ENOENT ? + -ETIMEDOUT : urb->status); + } else { + retval = urb->status; + } + urb->dev = udev; if (retval == 0 && usb_pipein(urb->pipe)) retval = simple_check_buf(tdev, urb); @@ -476,6 +484,14 @@ alloc_sglist(int nents, int max, int vary) return sg; } +static void sg_timeout(unsigned long _req) +{ + struct usb_sg_request *req = (struct usb_sg_request *) _req; + + req->status = -ETIMEDOUT; + usb_sg_cancel(req); +} + static int perform_sglist( struct usbtest_dev *tdev, unsigned iterations, @@ -487,6 +503,9 @@ static int perform_sglist( { struct usb_device *udev = testdev_to_usbdev(tdev); int retval = 0; + struct timer_list sg_timer; + + setup_timer_on_stack(&sg_timer, sg_timeout, (unsigned long) req); while (retval == 0 && iterations-- > 0) { retval = usb_sg_init(req, udev, pipe, @@ -497,7 +516,10 @@ static int perform_sglist( if (retval) break; + mod_timer(&sg_timer, jiffies + + msecs_to_jiffies(SIMPLE_IO_TIMEOUT)); usb_sg_wait(req); + del_timer_sync(&sg_timer); retval = req->status; /* FIXME check resulting data pattern */ @@ -1149,6 +1171,11 @@ static int unlink1(struct usbtest_dev *dev, int pipe, int size, int async) urb->context = &completion; urb->complete = unlink1_callback; + if (usb_pipeout(urb->pipe)) { + simple_fill_buf(urb); + urb->transfer_flags |= URB_ZERO_PACKET; + } + /* keep the endpoint busy. there are lots of hc/hcd-internal * states, and testing should get to all of them over time. * @@ -1279,6 +1306,11 @@ static int unlink_queued(struct usbtest_dev *dev, int pipe, unsigned num, unlink_queued_callback, &ctx); ctx.urbs[i]->transfer_dma = buf_dma; ctx.urbs[i]->transfer_flags = URB_NO_TRANSFER_DMA_MAP; + + if (usb_pipeout(ctx.urbs[i]->pipe)) { + simple_fill_buf(ctx.urbs[i]); + ctx.urbs[i]->transfer_flags |= URB_ZERO_PACKET; + } } /* Submit all the URBs and then unlink URBs num - 4 and num - 2. */ diff --git a/drivers/usb/phy/phy-isp1301-omap.c b/drivers/usb/phy/phy-isp1301-omap.c index d3a5160e4cc7..4a2ced057b40 100644 --- a/drivers/usb/phy/phy-isp1301-omap.c +++ b/drivers/usb/phy/phy-isp1301-omap.c @@ -1295,7 +1295,7 @@ isp1301_set_host(struct usb_otg *otg, struct usb_bus *host) return isp1301_otg_enable(isp); return 0; -#elif !defined(CONFIG_USB_GADGET_OMAP) +#elif !IS_ENABLED(CONFIG_USB_OMAP) // FIXME update its refcount otg->host = host; diff --git a/drivers/usb/serial/bus.c b/drivers/usb/serial/bus.c index 6335490d5760..74fc63b2e7fc 100644 --- a/drivers/usb/serial/bus.c +++ b/drivers/usb/serial/bus.c @@ -97,13 +97,19 @@ static int usb_serial_device_remove(struct device *dev) struct usb_serial_port *port; int retval = 0; int minor; + int autopm_err; port = to_usb_serial_port(dev); if (!port) return -ENODEV; - /* make sure suspend/resume doesn't race against port_remove */ - usb_autopm_get_interface(port->serial->interface); + /* + * Make sure suspend/resume doesn't race against port_remove. + * + * Note that no further runtime PM callbacks will be made if + * autopm_get fails. + */ + autopm_err = usb_autopm_get_interface(port->serial->interface); minor = port->minor; tty_unregister_device(usb_serial_tty_driver, minor); @@ -117,7 +123,9 @@ static int usb_serial_device_remove(struct device *dev) dev_info(dev, "%s converter now disconnected from ttyUSB%d\n", driver->description, minor); - usb_autopm_put_interface(port->serial->interface); + if (!autopm_err) + usb_autopm_put_interface(port->serial->interface); + return retval; } diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 948a19f0cdf7..70ede84f4f6b 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1925,6 +1925,7 @@ static int option_send_setup(struct usb_serial_port *port) struct option_private *priv = intfdata->private; struct usb_wwan_port_private *portdata; int val = 0; + int res; portdata = usb_get_serial_port_data(port); @@ -1933,9 +1934,17 @@ static int option_send_setup(struct usb_serial_port *port) if (portdata->rts_state) val |= 0x02; - return usb_control_msg(serial->dev, usb_rcvctrlpipe(serial->dev, 0), + res = usb_autopm_get_interface(serial->interface); + if (res) + return res; + + res = usb_control_msg(serial->dev, usb_rcvctrlpipe(serial->dev, 0), 0x22, 0x21, val, priv->bInterfaceNumber, NULL, 0, USB_CTRL_SET_TIMEOUT); + + usb_autopm_put_interface(serial->interface); + + return res; } MODULE_AUTHOR(DRIVER_AUTHOR); diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index 6c0a542e8ec1..3e96d1a9cbdb 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -22,8 +22,17 @@ #define DRIVER_AUTHOR "Qualcomm Inc" #define DRIVER_DESC "Qualcomm USB Serial driver" +/* standard device layouts supported by this driver */ +enum qcserial_layouts { + QCSERIAL_G2K = 0, /* Gobi 2000 */ + QCSERIAL_G1K = 1, /* Gobi 1000 */ + QCSERIAL_SWI = 2, /* Sierra Wireless */ +}; + #define DEVICE_G1K(v, p) \ - USB_DEVICE(v, p), .driver_info = 1 + USB_DEVICE(v, p), .driver_info = QCSERIAL_G1K +#define DEVICE_SWI(v, p) \ + USB_DEVICE(v, p), .driver_info = QCSERIAL_SWI static const struct usb_device_id id_table[] = { /* Gobi 1000 devices */ @@ -126,46 +135,27 @@ static const struct usb_device_id id_table[] = { {USB_DEVICE(0x12D1, 0x14F1)}, /* Sony Gobi 3000 Composite */ {USB_DEVICE(0x0AF0, 0x8120)}, /* Option GTM681W */ - /* non Gobi Qualcomm serial devices */ - {USB_DEVICE_INTERFACE_NUMBER(0x0f3d, 0x68a2, 0)}, /* Sierra Wireless MC7700 Device Management */ - {USB_DEVICE_INTERFACE_NUMBER(0x0f3d, 0x68a2, 2)}, /* Sierra Wireless MC7700 NMEA */ - {USB_DEVICE_INTERFACE_NUMBER(0x0f3d, 0x68a2, 3)}, /* Sierra Wireless MC7700 Modem */ - {USB_DEVICE_INTERFACE_NUMBER(0x114f, 0x68a2, 0)}, /* Sierra Wireless MC7750 Device Management */ - {USB_DEVICE_INTERFACE_NUMBER(0x114f, 0x68a2, 2)}, /* Sierra Wireless MC7750 NMEA */ - {USB_DEVICE_INTERFACE_NUMBER(0x114f, 0x68a2, 3)}, /* Sierra Wireless MC7750 Modem */ - {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68a2, 0)}, /* Sierra Wireless MC7710 Device Management */ - {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68a2, 2)}, /* Sierra Wireless MC7710 NMEA */ - {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68a2, 3)}, /* Sierra Wireless MC7710 Modem */ - {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68c0, 0)}, /* Sierra Wireless MC73xx Device Management */ - {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68c0, 2)}, /* Sierra Wireless MC73xx NMEA */ - {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68c0, 3)}, /* Sierra Wireless MC73xx Modem */ - {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901c, 0)}, /* Sierra Wireless EM7700 Device Management */ - {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901c, 2)}, /* Sierra Wireless EM7700 NMEA */ - {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901c, 3)}, /* Sierra Wireless EM7700 Modem */ - {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901f, 0)}, /* Sierra Wireless EM7355 Device Management */ - {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901f, 2)}, /* Sierra Wireless EM7355 NMEA */ - {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901f, 3)}, /* Sierra Wireless EM7355 Modem */ - {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9041, 0)}, /* Sierra Wireless MC7305/MC7355 Device Management */ - {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9041, 2)}, /* Sierra Wireless MC7305/MC7355 NMEA */ - {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9041, 3)}, /* Sierra Wireless MC7305/MC7355 Modem */ - {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 0)}, /* Netgear AirCard 340U Device Management */ - {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 2)}, /* Netgear AirCard 340U NMEA */ - {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 3)}, /* Netgear AirCard 340U Modem */ - {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a2, 0)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card Device Management */ - {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a2, 2)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card NMEA */ - {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a2, 3)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card Modem */ - {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a3, 0)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card Device Management */ - {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a3, 2)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card NMEA */ - {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a3, 3)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card Modem */ - {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a4, 0)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card Device Management */ - {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a4, 2)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card NMEA */ - {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a4, 3)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card Modem */ - {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a8, 0)}, /* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card Device Management */ - {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a8, 2)}, /* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card NMEA */ - {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a8, 3)}, /* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card Modem */ - {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a9, 0)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card Device Management */ - {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a9, 2)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card NMEA */ - {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a9, 3)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card Modem */ + /* non-Gobi Sierra Wireless devices */ + {DEVICE_SWI(0x0f3d, 0x68a2)}, /* Sierra Wireless MC7700 */ + {DEVICE_SWI(0x114f, 0x68a2)}, /* Sierra Wireless MC7750 */ + {DEVICE_SWI(0x1199, 0x68a2)}, /* Sierra Wireless MC7710 */ + {DEVICE_SWI(0x1199, 0x68c0)}, /* Sierra Wireless MC73xx */ + {DEVICE_SWI(0x1199, 0x901c)}, /* Sierra Wireless EM7700 */ + {DEVICE_SWI(0x1199, 0x901f)}, /* Sierra Wireless EM7355 */ + {DEVICE_SWI(0x1199, 0x9040)}, /* Sierra Wireless Modem */ + {DEVICE_SWI(0x1199, 0x9041)}, /* Sierra Wireless MC7305/MC7355 */ + {DEVICE_SWI(0x1199, 0x9051)}, /* Netgear AirCard 340U */ + {DEVICE_SWI(0x1199, 0x9053)}, /* Sierra Wireless Modem */ + {DEVICE_SWI(0x1199, 0x9054)}, /* Sierra Wireless Modem */ + {DEVICE_SWI(0x1199, 0x9055)}, /* Netgear AirCard 341U */ + {DEVICE_SWI(0x1199, 0x9056)}, /* Sierra Wireless Modem */ + {DEVICE_SWI(0x1199, 0x9060)}, /* Sierra Wireless Modem */ + {DEVICE_SWI(0x1199, 0x9061)}, /* Sierra Wireless Modem */ + {DEVICE_SWI(0x413c, 0x81a2)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */ + {DEVICE_SWI(0x413c, 0x81a3)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */ + {DEVICE_SWI(0x413c, 0x81a4)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */ + {DEVICE_SWI(0x413c, 0x81a8)}, /* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card */ + {DEVICE_SWI(0x413c, 0x81a9)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */ { } /* Terminating entry */ }; @@ -178,11 +168,8 @@ static int qcprobe(struct usb_serial *serial, const struct usb_device_id *id) int retval = -ENODEV; __u8 nintf; __u8 ifnum; - bool is_gobi1k = id->driver_info ? true : false; int altsetting = -1; - dev_dbg(dev, "Is Gobi 1000 = %d\n", is_gobi1k); - nintf = serial->dev->actconfig->desc.bNumInterfaces; dev_dbg(dev, "Num Interfaces = %d\n", nintf); ifnum = intf->desc.bInterfaceNumber; @@ -217,25 +204,29 @@ static int qcprobe(struct usb_serial *serial, const struct usb_device_id *id) goto done; } - if (nintf < 3 || nintf > 4) { - dev_err(dev, "unknown number of interfaces: %d\n", nintf); - goto done; - } - /* default to enabling interface */ altsetting = 0; - /* Composite mode; don't bind to the QMI/net interface as that + /* + * Composite mode; don't bind to the QMI/net interface as that * gets handled by other drivers. */ - if (is_gobi1k) { - /* Gobi 1K USB layout: + switch (id->driver_info) { + case QCSERIAL_G1K: + /* + * Gobi 1K USB layout: * 0: DM/DIAG (use libqcdm from ModemManager for communication) * 1: serial port (doesn't respond) * 2: AT-capable modem port * 3: QMI/net */ + if (nintf < 3 || nintf > 4) { + dev_err(dev, "unknown number of interfaces: %d\n", nintf); + altsetting = -1; + goto done; + } + if (ifnum == 0) { dev_dbg(dev, "Gobi 1K DM/DIAG interface found\n"); altsetting = 1; @@ -243,13 +234,21 @@ static int qcprobe(struct usb_serial *serial, const struct usb_device_id *id) dev_dbg(dev, "Modem port found\n"); else altsetting = -1; - } else { - /* Gobi 2K+ USB layout: + break; + case QCSERIAL_G2K: + /* + * Gobi 2K+ USB layout: * 0: QMI/net * 1: DM/DIAG (use libqcdm from ModemManager for communication) * 2: AT-capable modem port * 3: NMEA */ + if (nintf < 3 || nintf > 4) { + dev_err(dev, "unknown number of interfaces: %d\n", nintf); + altsetting = -1; + goto done; + } + switch (ifnum) { case 0: /* Don't claim the QMI/net interface */ @@ -270,6 +269,35 @@ static int qcprobe(struct usb_serial *serial, const struct usb_device_id *id) dev_dbg(dev, "Gobi 2K+ NMEA GPS interface found\n"); break; } + break; + case QCSERIAL_SWI: + /* + * Sierra Wireless layout: + * 0: DM/DIAG (use libqcdm from ModemManager for communication) + * 2: NMEA + * 3: AT-capable modem port + * 8: QMI/net + */ + switch (ifnum) { + case 0: + dev_dbg(dev, "DM/DIAG interface found\n"); + break; + case 2: + dev_dbg(dev, "NMEA GPS interface found\n"); + break; + case 3: + dev_dbg(dev, "Modem port found\n"); + break; + default: + /* don't claim any unsupported interface */ + altsetting = -1; + break; + } + break; + default: + dev_err(dev, "unsupported device layout type: %lu\n", + id->driver_info); + break; } done: diff --git a/drivers/usb/serial/sierra.c b/drivers/usb/serial/sierra.c index b6910b7ab7e2..d84a3f31ae2d 100644 --- a/drivers/usb/serial/sierra.c +++ b/drivers/usb/serial/sierra.c @@ -58,6 +58,7 @@ struct sierra_intf_private { spinlock_t susp_lock; unsigned int suspended:1; int in_flight; + unsigned int open_ports; }; static int sierra_set_power_state(struct usb_device *udev, __u16 swiState) @@ -767,6 +768,7 @@ static void sierra_close(struct usb_serial_port *port) struct usb_serial *serial = port->serial; struct sierra_port_private *portdata; struct sierra_intf_private *intfdata = port->serial->private; + struct urb *urb; portdata = usb_get_serial_port_data(port); @@ -775,7 +777,6 @@ static void sierra_close(struct usb_serial_port *port) mutex_lock(&serial->disc_mutex); if (!serial->disconnected) { - serial->interface->needs_remote_wakeup = 0; /* odd error handling due to pm counters */ if (!usb_autopm_get_interface(serial->interface)) sierra_send_setup(port); @@ -786,8 +787,22 @@ static void sierra_close(struct usb_serial_port *port) mutex_unlock(&serial->disc_mutex); spin_lock_irq(&intfdata->susp_lock); portdata->opened = 0; + if (--intfdata->open_ports == 0) + serial->interface->needs_remote_wakeup = 0; spin_unlock_irq(&intfdata->susp_lock); + for (;;) { + urb = usb_get_from_anchor(&portdata->delayed); + if (!urb) + break; + kfree(urb->transfer_buffer); + usb_free_urb(urb); + usb_autopm_put_interface_async(serial->interface); + spin_lock(&portdata->lock); + portdata->outstanding_urbs--; + spin_unlock(&portdata->lock); + } + sierra_stop_rx_urbs(port); for (i = 0; i < portdata->num_in_urbs; i++) { sierra_release_urb(portdata->in_urbs[i]); @@ -824,23 +839,29 @@ static int sierra_open(struct tty_struct *tty, struct usb_serial_port *port) usb_sndbulkpipe(serial->dev, endpoint) | USB_DIR_IN); err = sierra_submit_rx_urbs(port, GFP_KERNEL); - if (err) { - /* get rid of everything as in close */ - sierra_close(port); - /* restore balance for autopm */ - if (!serial->disconnected) - usb_autopm_put_interface(serial->interface); - return err; - } + if (err) + goto err_submit; + sierra_send_setup(port); - serial->interface->needs_remote_wakeup = 1; spin_lock_irq(&intfdata->susp_lock); portdata->opened = 1; + if (++intfdata->open_ports == 1) + serial->interface->needs_remote_wakeup = 1; spin_unlock_irq(&intfdata->susp_lock); usb_autopm_put_interface(serial->interface); return 0; + +err_submit: + sierra_stop_rx_urbs(port); + + for (i = 0; i < portdata->num_in_urbs; i++) { + sierra_release_urb(portdata->in_urbs[i]); + portdata->in_urbs[i] = NULL; + } + + return err; } @@ -936,6 +957,7 @@ static int sierra_port_remove(struct usb_serial_port *port) struct sierra_port_private *portdata; portdata = usb_get_serial_port_data(port); + usb_set_serial_port_data(port, NULL); kfree(portdata); return 0; @@ -952,6 +974,8 @@ static void stop_read_write_urbs(struct usb_serial *serial) for (i = 0; i < serial->num_ports; ++i) { port = serial->port[i]; portdata = usb_get_serial_port_data(port); + if (!portdata) + continue; sierra_stop_rx_urbs(port); usb_kill_anchored_urbs(&portdata->active); } @@ -994,6 +1018,9 @@ static int sierra_resume(struct usb_serial *serial) port = serial->port[i]; portdata = usb_get_serial_port_data(port); + if (!portdata) + continue; + while ((urb = usb_get_from_anchor(&portdata->delayed))) { usb_anchor_urb(urb, &portdata->active); intfdata->in_flight++; @@ -1001,8 +1028,12 @@ static int sierra_resume(struct usb_serial *serial) if (err < 0) { intfdata->in_flight--; usb_unanchor_urb(urb); - usb_scuttle_anchored_urbs(&portdata->delayed); - break; + kfree(urb->transfer_buffer); + usb_free_urb(urb); + spin_lock(&portdata->lock); + portdata->outstanding_urbs--; + spin_unlock(&portdata->lock); + continue; } } diff --git a/drivers/usb/serial/usb_wwan.c b/drivers/usb/serial/usb_wwan.c index 6fa78361be56..ad5fff4399d7 100644 --- a/drivers/usb/serial/usb_wwan.c +++ b/drivers/usb/serial/usb_wwan.c @@ -228,8 +228,10 @@ int usb_wwan_write(struct tty_struct *tty, struct usb_serial_port *port, usb_pipeendpoint(this_urb->pipe), i); err = usb_autopm_get_interface_async(port->serial->interface); - if (err < 0) + if (err < 0) { + clear_bit(i, &portdata->out_busy); break; + } /* send the data */ memcpy(this_urb->transfer_buffer, buf, todo); @@ -386,6 +388,14 @@ int usb_wwan_open(struct tty_struct *tty, struct usb_serial_port *port) portdata = usb_get_serial_port_data(port); intfdata = serial->private; + if (port->interrupt_in_urb) { + err = usb_submit_urb(port->interrupt_in_urb, GFP_KERNEL); + if (err) { + dev_dbg(&port->dev, "%s: submit int urb failed: %d\n", + __func__, err); + } + } + /* Start reading from the IN endpoint */ for (i = 0; i < N_IN_URB; i++) { urb = portdata->in_urbs[i]; @@ -412,12 +422,26 @@ int usb_wwan_open(struct tty_struct *tty, struct usb_serial_port *port) } EXPORT_SYMBOL(usb_wwan_open); +static void unbusy_queued_urb(struct urb *urb, + struct usb_wwan_port_private *portdata) +{ + int i; + + for (i = 0; i < N_OUT_URB; i++) { + if (urb == portdata->out_urbs[i]) { + clear_bit(i, &portdata->out_busy); + break; + } + } +} + void usb_wwan_close(struct usb_serial_port *port) { int i; struct usb_serial *serial = port->serial; struct usb_wwan_port_private *portdata; struct usb_wwan_intf_private *intfdata = port->serial->private; + struct urb *urb; portdata = usb_get_serial_port_data(port); @@ -426,10 +450,19 @@ void usb_wwan_close(struct usb_serial_port *port) portdata->opened = 0; spin_unlock_irq(&intfdata->susp_lock); + for (;;) { + urb = usb_get_from_anchor(&portdata->delayed); + if (!urb) + break; + unbusy_queued_urb(urb, portdata); + usb_autopm_put_interface_async(serial->interface); + } + for (i = 0; i < N_IN_URB; i++) usb_kill_urb(portdata->in_urbs[i]); for (i = 0; i < N_OUT_URB; i++) usb_kill_urb(portdata->out_urbs[i]); + usb_kill_urb(port->interrupt_in_urb); /* balancing - important as an error cannot be handled*/ usb_autopm_get_interface_no_resume(serial->interface); @@ -467,7 +500,6 @@ int usb_wwan_port_probe(struct usb_serial_port *port) struct usb_wwan_port_private *portdata; struct urb *urb; u8 *buffer; - int err; int i; if (!port->bulk_in_size || !port->bulk_out_size) @@ -507,13 +539,6 @@ int usb_wwan_port_probe(struct usb_serial_port *port) usb_set_serial_port_data(port, portdata); - if (port->interrupt_in_urb) { - err = usb_submit_urb(port->interrupt_in_urb, GFP_KERNEL); - if (err) - dev_dbg(&port->dev, "%s: submit irq_in urb failed %d\n", - __func__, err); - } - return 0; bail_out_error2: @@ -581,44 +606,29 @@ static void stop_read_write_urbs(struct usb_serial *serial) int usb_wwan_suspend(struct usb_serial *serial, pm_message_t message) { struct usb_wwan_intf_private *intfdata = serial->private; - int b; + spin_lock_irq(&intfdata->susp_lock); if (PMSG_IS_AUTO(message)) { - spin_lock_irq(&intfdata->susp_lock); - b = intfdata->in_flight; - spin_unlock_irq(&intfdata->susp_lock); - - if (b) + if (intfdata->in_flight) { + spin_unlock_irq(&intfdata->susp_lock); return -EBUSY; + } } - - spin_lock_irq(&intfdata->susp_lock); intfdata->suspended = 1; spin_unlock_irq(&intfdata->susp_lock); + stop_read_write_urbs(serial); return 0; } EXPORT_SYMBOL(usb_wwan_suspend); -static void unbusy_queued_urb(struct urb *urb, struct usb_wwan_port_private *portdata) -{ - int i; - - for (i = 0; i < N_OUT_URB; i++) { - if (urb == portdata->out_urbs[i]) { - clear_bit(i, &portdata->out_busy); - break; - } - } -} - -static void play_delayed(struct usb_serial_port *port) +static int play_delayed(struct usb_serial_port *port) { struct usb_wwan_intf_private *data; struct usb_wwan_port_private *portdata; struct urb *urb; - int err; + int err = 0; portdata = usb_get_serial_port_data(port); data = port->serial->private; @@ -635,6 +645,8 @@ static void play_delayed(struct usb_serial_port *port) break; } } + + return err; } int usb_wwan_resume(struct usb_serial *serial) @@ -644,54 +656,51 @@ int usb_wwan_resume(struct usb_serial *serial) struct usb_wwan_intf_private *intfdata = serial->private; struct usb_wwan_port_private *portdata; struct urb *urb; - int err = 0; - - /* get the interrupt URBs resubmitted unconditionally */ - for (i = 0; i < serial->num_ports; i++) { - port = serial->port[i]; - if (!port->interrupt_in_urb) { - dev_dbg(&port->dev, "%s: No interrupt URB for port\n", __func__); - continue; - } - err = usb_submit_urb(port->interrupt_in_urb, GFP_NOIO); - dev_dbg(&port->dev, "Submitted interrupt URB for port (result %d)\n", err); - if (err < 0) { - dev_err(&port->dev, "%s: Error %d for interrupt URB\n", - __func__, err); - goto err_out; - } - } + int err; + int err_count = 0; + spin_lock_irq(&intfdata->susp_lock); for (i = 0; i < serial->num_ports; i++) { /* walk all ports */ port = serial->port[i]; portdata = usb_get_serial_port_data(port); /* skip closed ports */ - spin_lock_irq(&intfdata->susp_lock); - if (!portdata || !portdata->opened) { - spin_unlock_irq(&intfdata->susp_lock); + if (!portdata || !portdata->opened) continue; + + if (port->interrupt_in_urb) { + err = usb_submit_urb(port->interrupt_in_urb, + GFP_ATOMIC); + if (err) { + dev_err(&port->dev, + "%s: submit int urb failed: %d\n", + __func__, err); + err_count++; + } } + err = play_delayed(port); + if (err) + err_count++; + for (j = 0; j < N_IN_URB; j++) { urb = portdata->in_urbs[j]; err = usb_submit_urb(urb, GFP_ATOMIC); if (err < 0) { dev_err(&port->dev, "%s: Error %d for bulk URB %d\n", __func__, err, i); - spin_unlock_irq(&intfdata->susp_lock); - goto err_out; + err_count++; } } - play_delayed(port); - spin_unlock_irq(&intfdata->susp_lock); } - spin_lock_irq(&intfdata->susp_lock); intfdata->suspended = 0; spin_unlock_irq(&intfdata->susp_lock); -err_out: - return err; + + if (err_count) + return -EIO; + + return 0; } EXPORT_SYMBOL(usb_wwan_resume); #endif diff --git a/drivers/video/fb-puv3.c b/drivers/video/fb-puv3.c index 27fc956166fa..520112531eb0 100644 --- a/drivers/video/fb-puv3.c +++ b/drivers/video/fb-puv3.c @@ -18,8 +18,10 @@ #include #include #include +#include #include +#include #include /* Platform_data reserved for unifb registers. */ diff --git a/drivers/video/matrox/matroxfb_base.h b/drivers/video/matrox/matroxfb_base.h index 556d96ce40bf..89a8a89a5eb2 100644 --- a/drivers/video/matrox/matroxfb_base.h +++ b/drivers/video/matrox/matroxfb_base.h @@ -698,7 +698,7 @@ void matroxfb_unregister_driver(struct matroxfb_driver* drv); #define mga_fifo(n) do {} while ((mga_inl(M_FIFOSTATUS) & 0xFF) < (n)) -#define WaitTillIdle() do {} while (mga_inl(M_STATUS) & 0x10000) +#define WaitTillIdle() do { mga_inl(M_STATUS); do {} while (mga_inl(M_STATUS) & 0x10000); } while (0) /* code speedup */ #ifdef CONFIG_FB_MATROX_MILLENIUM diff --git a/fs/aio.c b/fs/aio.c index 04cd7686555d..0abde33de70e 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -112,6 +112,11 @@ struct kioctx { struct work_struct free_work; + /* + * signals when all in-flight requests are done + */ + struct completion *requests_done; + struct { /* * This counts the number of available slots in the ringbuffer, @@ -508,6 +513,10 @@ static void free_ioctx_reqs(struct percpu_ref *ref) { struct kioctx *ctx = container_of(ref, struct kioctx, reqs); + /* At this point we know that there are no any in-flight requests */ + if (ctx->requests_done) + complete(ctx->requests_done); + INIT_WORK(&ctx->free_work, free_ioctx); schedule_work(&ctx->free_work); } @@ -718,7 +727,8 @@ err: * when the processes owning a context have all exited to encourage * the rapid destruction of the kioctx. */ -static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx) +static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx, + struct completion *requests_done) { if (!atomic_xchg(&ctx->dead, 1)) { struct kioctx_table *table; @@ -747,7 +757,11 @@ static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx) if (ctx->mmap_size) vm_munmap(ctx->mmap_base, ctx->mmap_size); + ctx->requests_done = requests_done; percpu_ref_kill(&ctx->users); + } else { + if (requests_done) + complete(requests_done); } } @@ -809,7 +823,7 @@ void exit_aio(struct mm_struct *mm) */ ctx->mmap_size = 0; - kill_ioctx(mm, ctx); + kill_ioctx(mm, ctx, NULL); } } @@ -1007,6 +1021,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2) /* everything turned out well, dispose of the aiocb. */ kiocb_free(iocb); + put_reqs_available(ctx, 1); /* * We have to order our ring_info tail store above and test @@ -1048,6 +1063,12 @@ static long aio_read_events_ring(struct kioctx *ctx, if (head == tail) goto out; + head %= ctx->nr_events; + tail %= ctx->nr_events; + + head %= ctx->nr_events; + tail %= ctx->nr_events; + while (ret < nr) { long avail; struct io_event *ev; @@ -1086,8 +1107,6 @@ static long aio_read_events_ring(struct kioctx *ctx, flush_dcache_page(ctx->ring_pages[0]); pr_debug("%li h%u t%u\n", ret, head, tail); - - put_reqs_available(ctx, ret); out: mutex_unlock(&ctx->ring_lock); @@ -1185,7 +1204,7 @@ SYSCALL_DEFINE2(io_setup, unsigned, nr_events, aio_context_t __user *, ctxp) if (!IS_ERR(ioctx)) { ret = put_user(ioctx->user_id, ctxp); if (ret) - kill_ioctx(current->mm, ioctx); + kill_ioctx(current->mm, ioctx, NULL); percpu_ref_put(&ioctx->users); } @@ -1203,8 +1222,22 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx) { struct kioctx *ioctx = lookup_ioctx(ctx); if (likely(NULL != ioctx)) { - kill_ioctx(current->mm, ioctx); + struct completion requests_done = + COMPLETION_INITIALIZER_ONSTACK(requests_done); + + /* Pass requests_done to kill_ioctx() where it can be set + * in a thread-safe way. If we try to set it here then we have + * a race condition if two io_destroy() called simultaneously. + */ + kill_ioctx(current->mm, ioctx, &requests_done); percpu_ref_put(&ioctx->users); + + /* Wait until all IO for the context are done. Otherwise kernel + * keep using user-space buffers even if user thinks the context + * is destroyed. + */ + wait_for_completion(&requests_done); + return 0; } pr_debug("EINVAL: io_destroy: invalid context id\n"); diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c index b5ee393e2e8d..76273c1d26a6 100644 --- a/fs/bio-integrity.c +++ b/fs/bio-integrity.c @@ -316,7 +316,7 @@ static void bio_integrity_generate(struct bio *bio) bix.disk_name = bio->bi_bdev->bd_disk->disk_name; bix.sector_size = bi->sector_size; - bio_for_each_segment_all(bv, bio, i) { + bio_for_each_segment(bv, bio, i) { void *kaddr = kmap_atomic(bv->bv_page); bix.data_buf = kaddr + bv->bv_offset; bix.data_size = bv->bv_len; diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 5eb50b5df777..1f4ce7ac144d 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1390,9 +1390,10 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical, * returns <0 on error */ static int __get_extent_inline_ref(unsigned long *ptr, struct extent_buffer *eb, - struct btrfs_extent_item *ei, u32 item_size, - struct btrfs_extent_inline_ref **out_eiref, - int *out_type) + struct btrfs_key *key, + struct btrfs_extent_item *ei, u32 item_size, + struct btrfs_extent_inline_ref **out_eiref, + int *out_type) { unsigned long end; u64 flags; @@ -1402,19 +1403,26 @@ static int __get_extent_inline_ref(unsigned long *ptr, struct extent_buffer *eb, /* first call */ flags = btrfs_extent_flags(eb, ei); if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) { - info = (struct btrfs_tree_block_info *)(ei + 1); - *out_eiref = - (struct btrfs_extent_inline_ref *)(info + 1); + if (key->type == BTRFS_METADATA_ITEM_KEY) { + /* a skinny metadata extent */ + *out_eiref = + (struct btrfs_extent_inline_ref *)(ei + 1); + } else { + WARN_ON(key->type != BTRFS_EXTENT_ITEM_KEY); + info = (struct btrfs_tree_block_info *)(ei + 1); + *out_eiref = + (struct btrfs_extent_inline_ref *)(info + 1); + } } else { *out_eiref = (struct btrfs_extent_inline_ref *)(ei + 1); } *ptr = (unsigned long)*out_eiref; - if ((void *)*ptr >= (void *)ei + item_size) + if ((unsigned long)(*ptr) >= (unsigned long)ei + item_size) return -ENOENT; } end = (unsigned long)ei + item_size; - *out_eiref = (struct btrfs_extent_inline_ref *)*ptr; + *out_eiref = (struct btrfs_extent_inline_ref *)(*ptr); *out_type = btrfs_extent_inline_ref_type(eb, *out_eiref); *ptr += btrfs_extent_inline_ref_size(*out_type); @@ -1433,8 +1441,8 @@ static int __get_extent_inline_ref(unsigned long *ptr, struct extent_buffer *eb, * <0 on error. */ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb, - struct btrfs_extent_item *ei, u32 item_size, - u64 *out_root, u8 *out_level) + struct btrfs_key *key, struct btrfs_extent_item *ei, + u32 item_size, u64 *out_root, u8 *out_level) { int ret; int type; @@ -1445,8 +1453,8 @@ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb, return 1; while (1) { - ret = __get_extent_inline_ref(ptr, eb, ei, item_size, - &eiref, &type); + ret = __get_extent_inline_ref(ptr, eb, key, ei, item_size, + &eiref, &type); if (ret < 0) return ret; diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h index a910b27a8ad9..519b49e51f57 100644 --- a/fs/btrfs/backref.h +++ b/fs/btrfs/backref.h @@ -40,8 +40,8 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical, u64 *flags); int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb, - struct btrfs_extent_item *ei, u32 item_size, - u64 *out_root, u8 *out_level); + struct btrfs_key *key, struct btrfs_extent_item *ei, + u32 item_size, u64 *out_root, u8 *out_level); int iterate_extent_inodes(struct btrfs_fs_info *fs_info, u64 extent_item_objectid, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 84d590a9e4ad..8964b59fee92 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -64,7 +64,6 @@ static void btrfs_destroy_ordered_operations(struct btrfs_transaction *t, static void btrfs_destroy_ordered_extents(struct btrfs_root *root); static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, struct btrfs_root *root); -static void btrfs_evict_pending_snapshots(struct btrfs_transaction *t); static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root); static int btrfs_destroy_marked_extents(struct btrfs_root *root, struct extent_io_tree *dirty_pages, @@ -1780,6 +1779,9 @@ sleep: wake_up_process(root->fs_info->cleaner_kthread); mutex_unlock(&root->fs_info->transaction_kthread_mutex); + if (unlikely(test_bit(BTRFS_FS_STATE_ERROR, + &root->fs_info->fs_state))) + btrfs_cleanup_transaction(root); if (!try_to_freeze()) { set_current_state(TASK_INTERRUPTIBLE); if (!kthread_should_stop() && @@ -3620,6 +3622,11 @@ int close_ctree(struct btrfs_root *root) btrfs_free_block_groups(fs_info); + /* + * we must make sure there is not any read request to + * submit after we stopping all workers. + */ + invalidate_inode_pages2(fs_info->btree_inode->i_mapping); btrfs_stop_all_workers(fs_info); del_fs_roots(fs_info); @@ -3806,7 +3813,8 @@ static void btrfs_destroy_all_ordered_extents(struct btrfs_fs_info *fs_info) while (!list_empty(&splice)) { root = list_first_entry(&splice, struct btrfs_root, ordered_root); - list_del_init(&root->ordered_root); + list_move_tail(&root->ordered_root, + &fs_info->ordered_roots); btrfs_destroy_ordered_extents(root); @@ -3884,24 +3892,6 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, return ret; } -static void btrfs_evict_pending_snapshots(struct btrfs_transaction *t) -{ - struct btrfs_pending_snapshot *snapshot; - struct list_head splice; - - INIT_LIST_HEAD(&splice); - - list_splice_init(&t->pending_snapshots, &splice); - - while (!list_empty(&splice)) { - snapshot = list_entry(splice.next, - struct btrfs_pending_snapshot, - list); - snapshot->error = -ECANCELED; - list_del_init(&snapshot->list); - } -} - static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root) { struct btrfs_inode *btrfs_inode; @@ -4031,6 +4021,8 @@ again: void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, struct btrfs_root *root) { + btrfs_destroy_ordered_operations(cur_trans, root); + btrfs_destroy_delayed_refs(cur_trans, root); btrfs_block_rsv_release(root, &root->fs_info->trans_block_rsv, cur_trans->dirty_pages.dirty_bytes); @@ -4038,8 +4030,6 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, cur_trans->state = TRANS_STATE_COMMIT_START; wake_up(&root->fs_info->transaction_blocked_wait); - btrfs_evict_pending_snapshots(cur_trans); - cur_trans->state = TRANS_STATE_UNBLOCKED; wake_up(&root->fs_info->transaction_wait); @@ -4063,63 +4053,51 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, static int btrfs_cleanup_transaction(struct btrfs_root *root) { struct btrfs_transaction *t; - LIST_HEAD(list); mutex_lock(&root->fs_info->transaction_kthread_mutex); spin_lock(&root->fs_info->trans_lock); - list_splice_init(&root->fs_info->trans_list, &list); - root->fs_info->running_transaction = NULL; - spin_unlock(&root->fs_info->trans_lock); - - while (!list_empty(&list)) { - t = list_entry(list.next, struct btrfs_transaction, list); - - btrfs_destroy_ordered_operations(t, root); - - btrfs_destroy_all_ordered_extents(root->fs_info); - - btrfs_destroy_delayed_refs(t, root); - - /* - * FIXME: cleanup wait for commit - * We needn't acquire the lock here, because we are during - * the umount, there is no other task which will change it. - */ - t->state = TRANS_STATE_COMMIT_START; - smp_mb(); - if (waitqueue_active(&root->fs_info->transaction_blocked_wait)) - wake_up(&root->fs_info->transaction_blocked_wait); - - btrfs_evict_pending_snapshots(t); - - t->state = TRANS_STATE_UNBLOCKED; - smp_mb(); - if (waitqueue_active(&root->fs_info->transaction_wait)) - wake_up(&root->fs_info->transaction_wait); - - btrfs_destroy_delayed_inodes(root); - btrfs_assert_delayed_root_empty(root); - - btrfs_destroy_all_delalloc_inodes(root->fs_info); - - btrfs_destroy_marked_extents(root, &t->dirty_pages, - EXTENT_DIRTY); - - btrfs_destroy_pinned_extent(root, - root->fs_info->pinned_extents); - - t->state = TRANS_STATE_COMPLETED; - smp_mb(); - if (waitqueue_active(&t->commit_wait)) - wake_up(&t->commit_wait); + while (!list_empty(&root->fs_info->trans_list)) { + t = list_first_entry(&root->fs_info->trans_list, + struct btrfs_transaction, list); + if (t->state >= TRANS_STATE_COMMIT_START) { + atomic_inc(&t->use_count); + spin_unlock(&root->fs_info->trans_lock); + btrfs_wait_for_commit(root, t->transid); + btrfs_put_transaction(t); + spin_lock(&root->fs_info->trans_lock); + continue; + } + if (t == root->fs_info->running_transaction) { + t->state = TRANS_STATE_COMMIT_DOING; + spin_unlock(&root->fs_info->trans_lock); + /* + * We wait for 0 num_writers since we don't hold a trans + * handle open currently for this transaction. + */ + wait_event(t->writer_wait, + atomic_read(&t->num_writers) == 0); + } else { + spin_unlock(&root->fs_info->trans_lock); + } + btrfs_cleanup_one_transaction(t, root); - atomic_set(&t->use_count, 0); + spin_lock(&root->fs_info->trans_lock); + if (t == root->fs_info->running_transaction) + root->fs_info->running_transaction = NULL; list_del_init(&t->list); - memset(t, 0, sizeof(*t)); - kmem_cache_free(btrfs_transaction_cachep, t); - } + spin_unlock(&root->fs_info->trans_lock); + btrfs_put_transaction(t); + trace_btrfs_transaction_commit(root); + spin_lock(&root->fs_info->trans_lock); + } + spin_unlock(&root->fs_info->trans_lock); + btrfs_destroy_all_ordered_extents(root->fs_info); + btrfs_destroy_delayed_inodes(root); + btrfs_assert_delayed_root_empty(root); + btrfs_destroy_pinned_extent(root, root->fs_info->pinned_extents); + btrfs_destroy_all_delalloc_inodes(root->fs_info); mutex_unlock(&root->fs_info->transaction_kthread_mutex); return 0; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index b256ddc1cb53..63ee604efa6c 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3318,10 +3318,9 @@ again: last = cache->key.objectid + cache->key.offset; err = write_one_cache_group(trans, root, path, cache); + btrfs_put_block_group(cache); if (err) /* File system offline */ goto out; - - btrfs_put_block_group(cache); } while (1) { diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 51731b76900d..b395791dd923 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1645,6 +1645,7 @@ again: * shortening the size of the delalloc range we're searching */ free_extent_state(cached_state); + cached_state = NULL; if (!loops) { max_bytes = PAGE_CACHE_SIZE; loops = 1; @@ -2311,7 +2312,7 @@ int end_extent_writepage(struct page *page, int err, u64 start, u64 end) { int uptodate = (err == 0); struct extent_io_tree *tree; - int ret; + int ret = 0; tree = &BTRFS_I(page->mapping->host)->io_tree; @@ -2325,6 +2326,8 @@ int end_extent_writepage(struct page *page, int err, u64 start, u64 end) if (!uptodate) { ClearPageUptodate(page); SetPageError(page); + ret = ret < 0 ? ret : -EIO; + mapping_set_error(page->mapping, ret); } return 0; } diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index b4f9904c4c6b..5467f84560fe 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -832,7 +832,7 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info, if (!matched) { __btrfs_remove_free_space_cache(ctl); - btrfs_err(fs_info, "block group %llu has wrong amount of free space", + btrfs_warn(fs_info, "block group %llu has wrong amount of free space", block_group->key.objectid); ret = -1; } @@ -844,7 +844,7 @@ out: spin_unlock(&block_group->lock); ret = 0; - btrfs_err(fs_info, "failed to load free space cache for block group %llu", + btrfs_warn(fs_info, "failed to load free space cache for block group %llu, rebuild it now", block_group->key.objectid); } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 3d03d2e0849c..fa8010c1b628 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1551,7 +1551,13 @@ static void btrfs_clear_bit_hook(struct inode *inode, spin_unlock(&BTRFS_I(inode)->lock); } - if (*bits & EXTENT_DO_ACCOUNTING) + /* + * We don't reserve metadata space for space cache inodes so we + * don't need to call dellalloc_release_metadata if there is an + * error. + */ + if (*bits & EXTENT_DO_ACCOUNTING && + root != root->fs_info->tree_root) btrfs_delalloc_release_metadata(inode, len); if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID @@ -2978,6 +2984,7 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode) if (insert >= 1) { ret = btrfs_insert_orphan_item(trans, root, btrfs_ino(inode)); if (ret) { + atomic_dec(&root->orphan_inodes); if (reserve) { clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED, &BTRFS_I(inode)->runtime_flags); @@ -3027,14 +3034,16 @@ static int btrfs_orphan_del(struct btrfs_trans_handle *trans, release_rsv = 1; spin_unlock(&root->orphan_lock); - if (trans && delete_item) - ret = btrfs_del_orphan_item(trans, root, btrfs_ino(inode)); - - if (release_rsv) { - btrfs_orphan_release_metadata(inode); + if (delete_item) { atomic_dec(&root->orphan_inodes); + if (trans) + ret = btrfs_del_orphan_item(trans, root, + btrfs_ino(inode)); } + if (release_rsv) + btrfs_orphan_release_metadata(inode); + return ret; } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 45301541349e..ad6a08c5801e 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4564,9 +4564,15 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_logical_to_ino(root, argp); case BTRFS_IOC_SPACE_INFO: return btrfs_ioctl_space_info(root, argp); - case BTRFS_IOC_SYNC: - btrfs_sync_fs(file->f_dentry->d_sb, 1); - return 0; + case BTRFS_IOC_SYNC: { + int ret; + + ret = btrfs_start_all_delalloc_inodes(root->fs_info, 0); + if (ret) + return ret; + ret = btrfs_sync_fs(file->f_dentry->d_sb, 1); + return ret; + } case BTRFS_IOC_START_SYNC: return btrfs_ioctl_start_sync(root, argp); case BTRFS_IOC_WAIT_SYNC: diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 26450d850f14..225c5b2e748f 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1383,6 +1383,7 @@ int btrfs_init_reloc_root(struct btrfs_trans_handle *trans, { struct btrfs_root *reloc_root; struct reloc_control *rc = root->fs_info->reloc_ctl; + struct btrfs_block_rsv *rsv; int clear_rsv = 0; int ret; @@ -1396,13 +1397,14 @@ int btrfs_init_reloc_root(struct btrfs_trans_handle *trans, root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) return 0; - if (!trans->block_rsv) { + if (!trans->reloc_reserved) { + rsv = trans->block_rsv; trans->block_rsv = rc->block_rsv; clear_rsv = 1; } reloc_root = create_reloc_root(trans, root, root->root_key.objectid); if (clear_rsv) - trans->block_rsv = NULL; + trans->block_rsv = rsv; ret = __add_reloc_root(reloc_root); BUG_ON(ret < 0); diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index a18e0e23f6a6..0b23100dd8ab 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -553,8 +553,9 @@ static void scrub_print_warning(const char *errstr, struct scrub_block *sblock) if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) { do { - ret = tree_backref_for_extent(&ptr, eb, ei, item_size, - &ref_root, &ref_level); + ret = tree_backref_for_extent(&ptr, eb, &found_key, ei, + item_size, &ref_root, + &ref_level); printk_in_rcu(KERN_WARNING "btrfs: %s at logical %llu on dev %s, " "sector %llu: metadata %s (level %d) in tree " diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 741c839fa46a..76736b57de5e 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1547,6 +1547,10 @@ static int lookup_dir_item_inode(struct btrfs_root *root, goto out; } btrfs_dir_item_key_to_cpu(path->nodes[0], di, &key); + if (key.type == BTRFS_ROOT_ITEM_KEY) { + ret = -ENOENT; + goto out; + } *found_inode = key.objectid; *found_type = btrfs_dir_type(path->nodes[0], di); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 25d64e8e8e47..977314e2d078 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -57,7 +57,7 @@ static unsigned int btrfs_blocked_trans_types[TRANS_STATE_MAX] = { __TRANS_JOIN_NOLOCK), }; -static void put_transaction(struct btrfs_transaction *transaction) +void btrfs_put_transaction(struct btrfs_transaction *transaction) { WARN_ON(atomic_read(&transaction->use_count) == 0); if (atomic_dec_and_test(&transaction->use_count)) { @@ -332,7 +332,7 @@ static void wait_current_trans(struct btrfs_root *root) wait_event(root->fs_info->transaction_wait, cur_trans->state >= TRANS_STATE_UNBLOCKED || cur_trans->aborted); - put_transaction(cur_trans); + btrfs_put_transaction(cur_trans); } else { spin_unlock(&root->fs_info->trans_lock); } @@ -353,6 +353,17 @@ static int may_wait_transaction(struct btrfs_root *root, int type) return 0; } +static inline bool need_reserve_reloc_root(struct btrfs_root *root) +{ + if (!root->fs_info->reloc_ctl || + !root->ref_cows || + root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID || + root->reloc_root) + return false; + + return true; +} + static struct btrfs_trans_handle * start_transaction(struct btrfs_root *root, u64 num_items, unsigned int type, enum btrfs_reserve_flush_enum flush) @@ -360,8 +371,9 @@ start_transaction(struct btrfs_root *root, u64 num_items, unsigned int type, struct btrfs_trans_handle *h; struct btrfs_transaction *cur_trans; u64 num_bytes = 0; - int ret; u64 qgroup_reserved = 0; + bool reloc_reserved = false; + int ret; if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state)) return ERR_PTR(-EROFS); @@ -390,6 +402,14 @@ start_transaction(struct btrfs_root *root, u64 num_items, unsigned int type, } num_bytes = btrfs_calc_trans_metadata_size(root, num_items); + /* + * Do the reservation for the relocation root creation + */ + if (unlikely(need_reserve_reloc_root(root))) { + num_bytes += root->nodesize; + reloc_reserved = true; + } + ret = btrfs_block_rsv_add(root, &root->fs_info->trans_block_rsv, num_bytes, flush); @@ -451,6 +471,7 @@ again: h->delayed_ref_elem.seq = 0; h->type = type; h->allocating_chunk = false; + h->reloc_reserved = false; INIT_LIST_HEAD(&h->qgroup_ref_list); INIT_LIST_HEAD(&h->new_bgs); @@ -466,6 +487,7 @@ again: h->transid, num_bytes, 1); h->block_rsv = &root->fs_info->trans_block_rsv; h->bytes_reserved = num_bytes; + h->reloc_reserved = reloc_reserved; } h->qgroup_reserved = qgroup_reserved; @@ -610,7 +632,7 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid) } wait_for_commit(root, cur_trans); - put_transaction(cur_trans); + btrfs_put_transaction(cur_trans); out: return ret; } @@ -729,7 +751,7 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, smp_mb(); if (waitqueue_active(&cur_trans->writer_wait)) wake_up(&cur_trans->writer_wait); - put_transaction(cur_trans); + btrfs_put_transaction(cur_trans); if (current->journal_info == trans) current->journal_info = NULL; @@ -738,8 +760,10 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, btrfs_run_delayed_iputs(root); if (trans->aborted || - test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state)) + test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state)) { + wake_up_process(info->transaction_kthread); err = -EIO; + } assert_qgroups_uptodate(trans); kmem_cache_free(btrfs_trans_handle_cachep, trans); @@ -1504,7 +1528,7 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans, if (current->journal_info == trans) current->journal_info = NULL; - put_transaction(cur_trans); + btrfs_put_transaction(cur_trans); return 0; } @@ -1548,8 +1572,8 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans, if (trans->type & __TRANS_FREEZABLE) sb_end_intwrite(root->fs_info->sb); - put_transaction(cur_trans); - put_transaction(cur_trans); + btrfs_put_transaction(cur_trans); + btrfs_put_transaction(cur_trans); trace_btrfs_transaction_commit(root); @@ -1665,7 +1689,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, wait_for_commit(root, cur_trans); - put_transaction(cur_trans); + btrfs_put_transaction(cur_trans); return ret; } @@ -1682,7 +1706,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, wait_for_commit(root, prev_trans); - put_transaction(prev_trans); + btrfs_put_transaction(prev_trans); } else { spin_unlock(&root->fs_info->trans_lock); } @@ -1881,8 +1905,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, list_del_init(&cur_trans->list); spin_unlock(&root->fs_info->trans_lock); - put_transaction(cur_trans); - put_transaction(cur_trans); + btrfs_put_transaction(cur_trans); + btrfs_put_transaction(cur_trans); if (trans->type & __TRANS_FREEZABLE) sb_end_intwrite(root->fs_info->sb); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 5c2af8491621..7657d115067d 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -92,6 +92,7 @@ struct btrfs_trans_handle { short aborted; short adding_csums; bool allocating_chunk; + bool reloc_reserved; unsigned int type; /* * this root is only needed to validate that the root passed to @@ -166,4 +167,5 @@ int btrfs_wait_marked_extents(struct btrfs_root *root, struct extent_io_tree *dirty_pages, int mark); int btrfs_transaction_blocked(struct btrfs_fs_info *info); int btrfs_transaction_in_commit(struct btrfs_fs_info *info); +void btrfs_put_transaction(struct btrfs_transaction *transaction); #endif diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index b691f375d837..7fae00b72283 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1438,6 +1438,22 @@ out: return ret; } +/* + * Function to update ctime/mtime for a given device path. + * Mainly used for ctime/mtime based probe like libblkid. + */ +static void update_dev_time(char *path_name) +{ + struct file *filp; + + filp = filp_open(path_name, O_RDWR, 0); + if (!filp) + return; + file_update_time(filp); + filp_close(filp, NULL); + return; +} + static int btrfs_rm_dev_item(struct btrfs_root *root, struct btrfs_device *device) { @@ -1660,11 +1676,12 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path) struct btrfs_fs_devices *fs_devices; fs_devices = root->fs_info->fs_devices; while (fs_devices) { - if (fs_devices->seed == cur_devices) + if (fs_devices->seed == cur_devices) { + fs_devices->seed = cur_devices->seed; break; + } fs_devices = fs_devices->seed; } - fs_devices->seed = cur_devices->seed; cur_devices->seed = NULL; lock_chunks(root); __btrfs_close_devices(cur_devices); @@ -1690,10 +1707,14 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path) ret = 0; - /* Notify udev that device has changed */ - if (bdev) + if (bdev) { + /* Notify udev that device has changed */ btrfs_kobject_uevent(bdev, KOBJ_CHANGE); + /* Update ctime/mtime for device path for libblkid */ + update_dev_time(device_path); + } + error_brelse: brelse(bh); if (bdev) @@ -1869,7 +1890,6 @@ static int btrfs_prepare_sprout(struct btrfs_root *root) fs_devices->seeding = 0; fs_devices->num_devices = 0; fs_devices->open_devices = 0; - fs_devices->total_devices = 0; fs_devices->seed = seed_devices; generate_random_uuid(fs_devices->fsid); @@ -2131,6 +2151,8 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) ret = btrfs_commit_transaction(trans, root); } + /* Update ctime/mtime for libblkid */ + update_dev_time(device_path); return ret; error_trans: @@ -6029,10 +6051,14 @@ void btrfs_init_devices_late(struct btrfs_fs_info *fs_info) struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; struct btrfs_device *device; - mutex_lock(&fs_devices->device_list_mutex); - list_for_each_entry(device, &fs_devices->devices, dev_list) - device->dev_root = fs_info->dev_root; - mutex_unlock(&fs_devices->device_list_mutex); + while (fs_devices) { + mutex_lock(&fs_devices->device_list_mutex); + list_for_each_entry(device, &fs_devices->devices, dev_list) + device->dev_root = fs_info->dev_root; + mutex_unlock(&fs_devices->device_list_mutex); + + fs_devices = fs_devices->seed; + } } static void __btrfs_reset_dev_stats(struct btrfs_device *dev) diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index b38bd052ce6d..b9f5709b54ca 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -87,10 +87,6 @@ extern mempool_t *cifs_mid_poolp; struct workqueue_struct *cifsiod_wq; -#ifdef CONFIG_CIFS_SMB2 -__u8 cifs_client_guid[SMB2_CLIENT_GUID_SIZE]; -#endif - /* * Bumps refcount for cifs super block. * Note that it should be only called if a referece to VFS super block is @@ -1192,10 +1188,6 @@ init_cifs(void) spin_lock_init(&cifs_file_list_lock); spin_lock_init(&GlobalMid_Lock); -#ifdef CONFIG_CIFS_SMB2 - get_random_bytes(cifs_client_guid, SMB2_CLIENT_GUID_SIZE); -#endif - if (cifs_max_pending < 2) { cifs_max_pending = 2; cifs_dbg(FYI, "cifs_max_pending set to min of 2\n"); diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 2f6f1ac52d3f..465b65488b27 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -391,6 +391,7 @@ struct smb_version_operations { const char *, u32 *); int (*set_acl)(struct cifs_ntsd *, __u32, struct inode *, const char *, int); + int (*validate_negotiate)(const unsigned int, struct cifs_tcon *); }; struct smb_version_values { @@ -546,6 +547,7 @@ struct TCP_Server_Info { int echo_credits; /* echo reserved slots */ int oplock_credits; /* oplock break reserved slots */ bool echoes:1; /* enable echoes */ + __u8 client_guid[SMB2_CLIENT_GUID_SIZE]; /* Client GUID */ #endif u16 dialect; /* dialect index that server chose */ bool oplocks:1; /* enable oplocks */ diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index a279ffc0bc29..89b5519085c2 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -2144,6 +2144,9 @@ cifs_get_tcp_session(struct smb_vol *volume_info) sizeof(tcp_ses->srcaddr)); memcpy(&tcp_ses->dstaddr, &volume_info->dstaddr, sizeof(tcp_ses->dstaddr)); +#ifdef CONFIG_CIFS_SMB2 + get_random_bytes(tcp_ses->client_guid, SMB2_CLIENT_GUID_SIZE); +#endif /* * at this point we are the only ones with the pointer * to the struct since the kernel thread not created yet diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 13e505191364..4ac88f89a5e5 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -1059,6 +1059,7 @@ struct smb_version_operations smb30_operations = { .set_oplock_level = smb3_set_oplock_level, .create_lease_buf = smb3_create_lease_buf, .parse_lease_buf = smb3_parse_lease_buf, + .validate_negotiate = smb3_validate_negotiate, }; struct smb_version_values smb20_values = { diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 06d29e3f5d10..829ad35f98d4 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -375,7 +375,12 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) req->Capabilities = cpu_to_le32(ses->server->vals->req_capabilities); - memcpy(req->ClientGUID, cifs_client_guid, SMB2_CLIENT_GUID_SIZE); + /* ClientGUID must be zero for SMB2.02 dialect */ + if (ses->server->vals->protocol_id == SMB20_PROT_ID) + memset(req->ClientGUID, 0, SMB2_CLIENT_GUID_SIZE); + else + memcpy(req->ClientGUID, server->client_guid, + SMB2_CLIENT_GUID_SIZE); iov[0].iov_base = (char *)req; /* 4 for rfc1002 length field */ @@ -456,6 +461,82 @@ neg_exit: return rc; } +int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon) +{ + int rc = 0; + struct validate_negotiate_info_req vneg_inbuf; + struct validate_negotiate_info_rsp *pneg_rsp; + u32 rsplen; + + cifs_dbg(FYI, "validate negotiate\n"); + + /* + * validation ioctl must be signed, so no point sending this if we + * can not sign it. We could eventually change this to selectively + * sign just this, the first and only signed request on a connection. + * This is good enough for now since a user who wants better security + * would also enable signing on the mount. Having validation of + * negotiate info for signed connections helps reduce attack vectors + */ + if (tcon->ses->server->sign == false) + return 0; /* validation requires signing */ + + vneg_inbuf.Capabilities = + cpu_to_le32(tcon->ses->server->vals->req_capabilities); + memcpy(vneg_inbuf.Guid, tcon->ses->server->client_guid, + SMB2_CLIENT_GUID_SIZE); + + if (tcon->ses->sign) + vneg_inbuf.SecurityMode = + cpu_to_le16(SMB2_NEGOTIATE_SIGNING_REQUIRED); + else if (global_secflags & CIFSSEC_MAY_SIGN) + vneg_inbuf.SecurityMode = + cpu_to_le16(SMB2_NEGOTIATE_SIGNING_ENABLED); + else + vneg_inbuf.SecurityMode = 0; + + vneg_inbuf.DialectCount = cpu_to_le16(1); + vneg_inbuf.Dialects[0] = + cpu_to_le16(tcon->ses->server->vals->protocol_id); + + rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID, + FSCTL_VALIDATE_NEGOTIATE_INFO, true /* is_fsctl */, + (char *)&vneg_inbuf, sizeof(struct validate_negotiate_info_req), + (char **)&pneg_rsp, &rsplen); + + if (rc != 0) { + cifs_dbg(VFS, "validate protocol negotiate failed: %d\n", rc); + return -EIO; + } + + if (rsplen != sizeof(struct validate_negotiate_info_rsp)) { + cifs_dbg(VFS, "invalid size of protocol negotiate response\n"); + return -EIO; + } + + /* check validate negotiate info response matches what we got earlier */ + if (pneg_rsp->Dialect != + cpu_to_le16(tcon->ses->server->vals->protocol_id)) + goto vneg_out; + + if (pneg_rsp->SecurityMode != cpu_to_le16(tcon->ses->server->sec_mode)) + goto vneg_out; + + /* do not validate server guid because not saved at negprot time yet */ + + if ((le32_to_cpu(pneg_rsp->Capabilities) | SMB2_NT_FIND | + SMB2_LARGE_FILES) != tcon->ses->server->capabilities) + goto vneg_out; + + /* validate negotiate successful */ + cifs_dbg(FYI, "validate negotiate info successful\n"); + return 0; + +vneg_out: + cifs_dbg(VFS, "protocol revalidation - security settings mismatch\n"); + return -EIO; +} + int SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses, const struct nls_table *nls_cp) @@ -821,6 +902,8 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, ((tcon->share_flags & SHI1005_FLAGS_DFS) == 0)) cifs_dbg(VFS, "DFS capability contradicts DFS flag\n"); + if (tcon->ses->server->ops->validate_negotiate) + rc = tcon->ses->server->ops->validate_negotiate(xid, tcon); tcon_exit: free_rsp_buf(resp_buftype, rsp); kfree(unc_path); @@ -1002,6 +1085,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, int rc = 0; unsigned int num_iovecs = 2; __u32 file_attributes = 0; + char *dhc_buf = NULL, *lc_buf = NULL; cifs_dbg(FYI, "create/open\n"); @@ -1068,6 +1152,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, kfree(copy_path); return rc; } + lc_buf = iov[num_iovecs-1].iov_base; } if (*oplock == SMB2_OPLOCK_LEVEL_BATCH) { @@ -1082,9 +1167,10 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, if (rc) { cifs_small_buf_release(req); kfree(copy_path); - kfree(iov[num_iovecs-1].iov_base); + kfree(lc_buf); return rc; } + dhc_buf = iov[num_iovecs-1].iov_base; } rc = SendReceive2(xid, ses, iov, num_iovecs, &resp_buftype, 0); @@ -1116,6 +1202,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, *oplock = rsp->OplockLevel; creat_exit: kfree(copy_path); + kfree(lc_buf); + kfree(dhc_buf); free_rsp_buf(resp_buftype, rsp); return rc; } diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index b83d0118a757..6133a4e45c6e 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -166,8 +166,6 @@ struct smb2_symlink_err_rsp { #define SMB2_CLIENT_GUID_SIZE 16 -extern __u8 cifs_client_guid[SMB2_CLIENT_GUID_SIZE]; - struct smb2_negotiate_req { struct smb2_hdr hdr; __le16 StructureSize; /* Must be 36 */ @@ -546,13 +544,19 @@ struct copychunk_ioctl { __u32 Reserved2; } __packed; -/* Response and Request are the same format */ -struct validate_negotiate_info { +struct validate_negotiate_info_req { __le32 Capabilities; __u8 Guid[SMB2_CLIENT_GUID_SIZE]; __le16 SecurityMode; __le16 DialectCount; - __le16 Dialect[1]; + __le16 Dialects[1]; /* dialect (someday maybe list) client asked for */ +} __packed; + +struct validate_negotiate_info_rsp { + __le32 Capabilities; + __u8 Guid[SMB2_CLIENT_GUID_SIZE]; + __le16 SecurityMode; + __le16 Dialect; /* Dialect in use for the connection */ } __packed; #define RSS_CAPABLE 0x00000001 diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 7db5db0eef18..d18b19ec1145 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -158,5 +158,6 @@ extern int smb2_lockv(const unsigned int xid, struct cifs_tcon *tcon, struct smb2_lock_element *buf); extern int SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon, __u8 *lease_key, const __le32 lease_state); +extern int smb3_validate_negotiate(const unsigned int, struct cifs_tcon *); #endif /* _SMB2PROTO_H */ diff --git a/fs/cifs/smbfsctl.h b/fs/cifs/smbfsctl.h index a4b2391fe66e..0e538b5c9622 100644 --- a/fs/cifs/smbfsctl.h +++ b/fs/cifs/smbfsctl.h @@ -90,7 +90,7 @@ #define FSCTL_LMR_REQUEST_RESILIENCY 0x001401D4 /* BB add struct */ #define FSCTL_LMR_GET_LINK_TRACK_INF 0x001400E8 /* BB add struct */ #define FSCTL_LMR_SET_LINK_TRACK_INF 0x001400EC /* BB add struct */ -#define FSCTL_VALIDATE_NEGOTIATE_INFO 0x00140204 /* BB add struct */ +#define FSCTL_VALIDATE_NEGOTIATE_INFO 0x00140204 /* Perform server-side data movement */ #define FSCTL_SRV_COPYCHUNK 0x001440F2 #define FSCTL_SRV_COPYCHUNK_WRITE 0x001480F2 diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index a5e34dd6a32c..1381d3fb3738 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -617,6 +617,11 @@ static void retry_failed_sctp_send(struct connection *recv_con, int nodeid = sn_send_failed->ssf_info.sinfo_ppid; log_print("Retry sending %d bytes to node id %d", len, nodeid); + + if (!nodeid) { + log_print("Shouldn't resend data via listening connection."); + return; + } con = nodeid2con(nodeid, 0); if (!con) { diff --git a/fs/eventpoll.c b/fs/eventpoll.c index d76c9744c774..55ebb8886014 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -910,7 +910,7 @@ static const struct file_operations eventpoll_fops = { void eventpoll_release_file(struct file *file) { struct eventpoll *ep; - struct epitem *epi; + struct epitem *epi, *next; /* * We don't want to get "file->f_lock" because it is not @@ -926,7 +926,7 @@ void eventpoll_release_file(struct file *file) * Besides, ep_remove() acquires the lock, so we can't hold it here. */ mutex_lock(&epmutex); - list_for_each_entry_rcu(epi, &file->f_ep_links, fllink) { + list_for_each_entry_safe(epi, next, &file->f_ep_links, fllink) { ep = epi->ep; mutex_lock_nested(&ep->mtx, 0); ep_remove(ep, epi); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 1e25d6b57bc5..54d94db2cf03 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2749,7 +2749,8 @@ extern void ext4_io_submit(struct ext4_io_submit *io); extern int ext4_bio_write_page(struct ext4_io_submit *io, struct page *page, int len, - struct writeback_control *wbc); + struct writeback_control *wbc, + bool keep_towrite); /* mmp.c */ extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index ea9793d8a77f..e5d9908c0bc3 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1835,6 +1835,7 @@ static int ext4_writepage(struct page *page, struct buffer_head *page_bufs = NULL; struct inode *inode = page->mapping->host; struct ext4_io_submit io_submit; + bool keep_towrite = false; trace_ext4_writepage(page); size = i_size_read(inode); @@ -1865,6 +1866,7 @@ static int ext4_writepage(struct page *page, unlock_page(page); return 0; } + keep_towrite = true; } if (PageChecked(page) && ext4_should_journal_data(inode)) @@ -1881,7 +1883,7 @@ static int ext4_writepage(struct page *page, unlock_page(page); return -ENOMEM; } - ret = ext4_bio_write_page(&io_submit, page, len, wbc); + ret = ext4_bio_write_page(&io_submit, page, len, wbc, keep_towrite); ext4_io_submit(&io_submit); /* Drop io_end reference we got from init */ ext4_put_io_end_defer(io_submit.io_end); @@ -1900,7 +1902,7 @@ static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page) else len = PAGE_CACHE_SIZE; clear_page_dirty_for_io(page); - err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc); + err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc, false); if (!err) mpd->wbc->nr_to_write--; mpd->first_page++; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 04a5c7504be9..08ddfdac955c 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -3135,7 +3135,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, } BUG_ON(start + size <= ac->ac_o_ex.fe_logical && start > ac->ac_o_ex.fe_logical); - BUG_ON(size <= 0 || size > EXT4_CLUSTERS_PER_GROUP(ac->ac_sb)); + BUG_ON(size <= 0 || size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb)); /* now prepare goal request */ diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 02e94ef1489b..f1ecd138d3ee 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -400,7 +400,8 @@ submit_and_retry: int ext4_bio_write_page(struct ext4_io_submit *io, struct page *page, int len, - struct writeback_control *wbc) + struct writeback_control *wbc, + bool keep_towrite) { struct inode *inode = page->mapping->host; unsigned block_start, blocksize; @@ -413,10 +414,24 @@ int ext4_bio_write_page(struct ext4_io_submit *io, BUG_ON(!PageLocked(page)); BUG_ON(PageWriteback(page)); - set_page_writeback(page); + if (keep_towrite) + set_page_writeback_keepwrite(page); + else + set_page_writeback(page); ClearPageError(page); /* + * Comments copied from block_write_full_page_endio: + * + * The page straddles i_size. It must be zeroed out on each and every + * writepage invocation because it may be mmapped. "A file is mapped + * in multiples of the page size. For a file that is not a multiple of + * the page size, the remaining memory is zeroed when mapped, and + * writes to that region are not written out to the file." + */ + if (len < PAGE_CACHE_SIZE) + zero_user_segment(page, len, PAGE_CACHE_SIZE); + /* * In the first loop we prepare and mark buffers to submit. We have to * mark all buffers in the page before submitting so that * end_page_writeback() cannot be called from ext4_bio_end_io() when IO @@ -427,19 +442,6 @@ int ext4_bio_write_page(struct ext4_io_submit *io, do { block_start = bh_offset(bh); if (block_start >= len) { - /* - * Comments copied from block_write_full_page_endio: - * - * The page straddles i_size. It must be zeroed out on - * each and every writepage invocation because it may - * be mmapped. "A file is mapped in multiples of the - * page size. For a file that is not a multiple of - * the page size, the remaining memory is zeroed when - * mapped, and writes to that region are not written - * out to the file." - */ - zero_user_segment(page, block_start, - block_start + blocksize); clear_buffer_dirty(bh); set_buffer_uptodate(bh); continue; diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 630db362a2d1..e803e3cafc53 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -583,6 +583,9 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error = PTR_ERR(inode); if (!IS_ERR(inode)) { d = d_splice_alias(inode, dentry); + error = PTR_ERR(d); + if (IS_ERR(d)) + goto fail_gunlock; error = 0; if (file) { if (S_ISREG(inode->i_mode)) { @@ -777,6 +780,11 @@ static struct dentry *__gfs2_lookup(struct inode *dir, struct dentry *dentry, } d = d_splice_alias(inode, dentry); + if (IS_ERR(d)) { + iput(inode); + gfs2_glock_dq_uninit(&gh); + return d; + } if (file && S_ISREG(inode->i_mode)) error = finish_open(file, dentry, gfs2_open_common, opened); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index ded7af3c45e1..5ae1dd340073 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -3705,7 +3705,7 @@ nfsd4_free_lock_stateid(struct nfs4_ol_stateid *stp) * correspondance, and we have to delete the lockowner when we * delete the lock stateid: */ - unhash_lockowner(lo); + release_lockowner(lo); return nfs_ok; } diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index b6af150c96b8..6040da8830ff 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -132,13 +132,6 @@ nfsd_reply_cache_alloc(void) } static void -nfsd_reply_cache_unhash(struct svc_cacherep *rp) -{ - hlist_del_init(&rp->c_hash); - list_del_init(&rp->c_lru); -} - -static void nfsd_reply_cache_free_locked(struct svc_cacherep *rp) { if (rp->c_type == RC_REPLBUFF && rp->c_replvec.iov_base) { @@ -231,13 +224,6 @@ hash_refile(struct svc_cacherep *rp) hlist_add_head(&rp->c_hash, cache_hash + hash_32(rp->c_xid, maskbits)); } -static inline bool -nfsd_cache_entry_expired(struct svc_cacherep *rp) -{ - return rp->c_state != RC_INPROG && - time_after(jiffies, rp->c_timestamp + RC_EXPIRE); -} - /* * Walk the LRU list and prune off entries that are older than RC_EXPIRE. * Also prune the oldest ones when the total exceeds the max number of entries. @@ -249,8 +235,14 @@ prune_cache_entries(void) long freed = 0; list_for_each_entry_safe(rp, tmp, &lru_head, c_lru) { - if (!nfsd_cache_entry_expired(rp) && - num_drc_entries <= max_drc_entries) + /* + * Don't free entries attached to calls that are still + * in-progress, but do keep scanning the list. + */ + if (rp->c_state == RC_INPROG) + continue; + if (num_drc_entries <= max_drc_entries && + time_before(jiffies, rp->c_timestamp + RC_EXPIRE)) break; nfsd_reply_cache_free_locked(rp); freed++; @@ -416,22 +408,8 @@ nfsd_cache_lookup(struct svc_rqst *rqstp) /* * Since the common case is a cache miss followed by an insert, - * preallocate an entry. First, try to reuse the first entry on the LRU - * if it works, then go ahead and prune the LRU list. + * preallocate an entry. */ - spin_lock(&cache_lock); - if (!list_empty(&lru_head)) { - rp = list_first_entry(&lru_head, struct svc_cacherep, c_lru); - if (nfsd_cache_entry_expired(rp) || - num_drc_entries >= max_drc_entries) { - nfsd_reply_cache_unhash(rp); - prune_cache_entries(); - goto search_cache; - } - } - - /* No expired ones available, allocate a new one. */ - spin_unlock(&cache_lock); rp = nfsd_reply_cache_alloc(); spin_lock(&cache_lock); if (likely(rp)) { @@ -439,7 +417,9 @@ nfsd_cache_lookup(struct svc_rqst *rqstp) drc_mem_usage += sizeof(*rp); } -search_cache: + /* go ahead and prune the cache */ + prune_cache_entries(); + found = nfsd_cache_search(rqstp, csum); if (found) { if (likely(rp)) @@ -453,15 +433,6 @@ search_cache: goto out; } - /* - * We're keeping the one we just allocated. Are we now over the - * limit? Prune one off the tip of the LRU in trade for the one we - * just allocated if so. - */ - if (num_drc_entries >= max_drc_entries) - nfsd_reply_cache_free_locked(list_first_entry(&lru_head, - struct svc_cacherep, c_lru)); - nfsdstats.rcmisses++; rqstp->rq_cacherep = rp; rp->c_state = RC_INPROG; diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c index 0d3a97d2d5f6..e2e05a106beb 100644 --- a/fs/ocfs2/dcache.c +++ b/fs/ocfs2/dcache.c @@ -37,7 +37,6 @@ #include "dlmglue.h" #include "file.h" #include "inode.h" -#include "super.h" #include "ocfs2_trace.h" void ocfs2_dentry_attach_gen(struct dentry *dentry) @@ -346,52 +345,6 @@ out_attach: return ret; } -DEFINE_SPINLOCK(dentry_list_lock); - -/* We limit the number of dentry locks to drop in one go. We have - * this limit so that we don't starve other users of ocfs2_wq. */ -#define DL_INODE_DROP_COUNT 64 - -/* Drop inode references from dentry locks */ -static void __ocfs2_drop_dl_inodes(struct ocfs2_super *osb, int drop_count) -{ - struct ocfs2_dentry_lock *dl; - - spin_lock(&dentry_list_lock); - while (osb->dentry_lock_list && (drop_count < 0 || drop_count--)) { - dl = osb->dentry_lock_list; - osb->dentry_lock_list = dl->dl_next; - spin_unlock(&dentry_list_lock); - iput(dl->dl_inode); - kfree(dl); - spin_lock(&dentry_list_lock); - } - spin_unlock(&dentry_list_lock); -} - -void ocfs2_drop_dl_inodes(struct work_struct *work) -{ - struct ocfs2_super *osb = container_of(work, struct ocfs2_super, - dentry_lock_work); - - __ocfs2_drop_dl_inodes(osb, DL_INODE_DROP_COUNT); - /* - * Don't queue dropping if umount is in progress. We flush the - * list in ocfs2_dismount_volume - */ - spin_lock(&dentry_list_lock); - if (osb->dentry_lock_list && - !ocfs2_test_osb_flag(osb, OCFS2_OSB_DROP_DENTRY_LOCK_IMMED)) - queue_work(ocfs2_wq, &osb->dentry_lock_work); - spin_unlock(&dentry_list_lock); -} - -/* Flush the whole work queue */ -void ocfs2_drop_all_dl_inodes(struct ocfs2_super *osb) -{ - __ocfs2_drop_dl_inodes(osb, -1); -} - /* * ocfs2_dentry_iput() and friends. * @@ -416,24 +369,16 @@ void ocfs2_drop_all_dl_inodes(struct ocfs2_super *osb) static void ocfs2_drop_dentry_lock(struct ocfs2_super *osb, struct ocfs2_dentry_lock *dl) { + iput(dl->dl_inode); ocfs2_simple_drop_lockres(osb, &dl->dl_lockres); ocfs2_lock_res_free(&dl->dl_lockres); - - /* We leave dropping of inode reference to ocfs2_wq as that can - * possibly lead to inode deletion which gets tricky */ - spin_lock(&dentry_list_lock); - if (!osb->dentry_lock_list && - !ocfs2_test_osb_flag(osb, OCFS2_OSB_DROP_DENTRY_LOCK_IMMED)) - queue_work(ocfs2_wq, &osb->dentry_lock_work); - dl->dl_next = osb->dentry_lock_list; - osb->dentry_lock_list = dl; - spin_unlock(&dentry_list_lock); + kfree(dl); } void ocfs2_dentry_lock_put(struct ocfs2_super *osb, struct ocfs2_dentry_lock *dl) { - int unlock; + int unlock = 0; BUG_ON(dl->dl_count == 0); diff --git a/fs/ocfs2/dcache.h b/fs/ocfs2/dcache.h index b79eff709958..55f58892b153 100644 --- a/fs/ocfs2/dcache.h +++ b/fs/ocfs2/dcache.h @@ -29,13 +29,8 @@ extern const struct dentry_operations ocfs2_dentry_ops; struct ocfs2_dentry_lock { - /* Use count of dentry lock */ unsigned int dl_count; - union { - /* Linked list of dentry locks to release */ - struct ocfs2_dentry_lock *dl_next; - u64 dl_parent_blkno; - }; + u64 dl_parent_blkno; /* * The ocfs2_dentry_lock keeps an inode reference until @@ -49,14 +44,9 @@ struct ocfs2_dentry_lock { int ocfs2_dentry_attach_lock(struct dentry *dentry, struct inode *inode, u64 parent_blkno); -extern spinlock_t dentry_list_lock; - void ocfs2_dentry_lock_put(struct ocfs2_super *osb, struct ocfs2_dentry_lock *dl); -void ocfs2_drop_dl_inodes(struct work_struct *work); -void ocfs2_drop_all_dl_inodes(struct ocfs2_super *osb); - struct dentry *ocfs2_find_local_alias(struct inode *inode, u64 parent_blkno, int skip_unhashed); diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 3a44a648dae7..3988d0aeb72c 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -3142,22 +3142,60 @@ out: return 0; } +static void ocfs2_process_blocked_lock(struct ocfs2_super *osb, + struct ocfs2_lock_res *lockres); + /* Mark the lockres as being dropped. It will no longer be * queued if blocking, but we still may have to wait on it * being dequeued from the downconvert thread before we can consider * it safe to drop. * * You can *not* attempt to call cluster_lock on this lockres anymore. */ -void ocfs2_mark_lockres_freeing(struct ocfs2_lock_res *lockres) +void ocfs2_mark_lockres_freeing(struct ocfs2_super *osb, + struct ocfs2_lock_res *lockres) { int status; struct ocfs2_mask_waiter mw; - unsigned long flags; + unsigned long flags, flags2; ocfs2_init_mask_waiter(&mw); spin_lock_irqsave(&lockres->l_lock, flags); lockres->l_flags |= OCFS2_LOCK_FREEING; + if (lockres->l_flags & OCFS2_LOCK_QUEUED && current == osb->dc_task) { + /* + * We know the downconvert is queued but not in progress + * because we are the downconvert thread and processing + * different lock. So we can just remove the lock from the + * queue. This is not only an optimization but also a way + * to avoid the following deadlock: + * ocfs2_dentry_post_unlock() + * ocfs2_dentry_lock_put() + * ocfs2_drop_dentry_lock() + * iput() + * ocfs2_evict_inode() + * ocfs2_clear_inode() + * ocfs2_mark_lockres_freeing() + * ... blocks waiting for OCFS2_LOCK_QUEUED + * since we are the downconvert thread which + * should clear the flag. + */ + spin_unlock_irqrestore(&lockres->l_lock, flags); + spin_lock_irqsave(&osb->dc_task_lock, flags2); + list_del_init(&lockres->l_blocked_list); + osb->blocked_lock_count--; + spin_unlock_irqrestore(&osb->dc_task_lock, flags2); + /* + * Warn if we recurse into another post_unlock call. Strictly + * speaking it isn't a problem but we need to be careful if + * that happens (stack overflow, deadlocks, ...) so warn if + * ocfs2 grows a path for which this can happen. + */ + WARN_ON_ONCE(lockres->l_ops->post_unlock); + /* Since the lock is freeing we don't do much in the fn below */ + ocfs2_process_blocked_lock(osb, lockres); + return; + } while (lockres->l_flags & OCFS2_LOCK_QUEUED) { lockres_add_mask_waiter(lockres, &mw, OCFS2_LOCK_QUEUED, 0); spin_unlock_irqrestore(&lockres->l_lock, flags); @@ -3178,7 +3216,7 @@ void ocfs2_simple_drop_lockres(struct ocfs2_super *osb, { int ret; - ocfs2_mark_lockres_freeing(lockres); + ocfs2_mark_lockres_freeing(osb, lockres); ret = ocfs2_drop_lock(osb, lockres); if (ret) mlog_errno(ret); diff --git a/fs/ocfs2/dlmglue.h b/fs/ocfs2/dlmglue.h index 1d596d8c4a4a..d293a22c32c5 100644 --- a/fs/ocfs2/dlmglue.h +++ b/fs/ocfs2/dlmglue.h @@ -157,7 +157,8 @@ int ocfs2_refcount_lock(struct ocfs2_refcount_tree *ref_tree, int ex); void ocfs2_refcount_unlock(struct ocfs2_refcount_tree *ref_tree, int ex); -void ocfs2_mark_lockres_freeing(struct ocfs2_lock_res *lockres); +void ocfs2_mark_lockres_freeing(struct ocfs2_super *osb, + struct ocfs2_lock_res *lockres); void ocfs2_simple_drop_lockres(struct ocfs2_super *osb, struct ocfs2_lock_res *lockres); diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index f87f9bd1edff..e37a59a28644 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -814,11 +814,13 @@ static int ocfs2_inode_is_valid_to_delete(struct inode *inode) goto bail; } - /* If we're coming from downconvert_thread we can't go into our own - * voting [hello, deadlock city!], so unforuntately we just - * have to skip deleting this guy. That's OK though because - * the node who's doing the actual deleting should handle it - * anyway. */ + /* + * If we're coming from downconvert_thread we can't go into our own + * voting [hello, deadlock city!] so we cannot delete the inode. But + * since we dropped last inode ref when downconverting dentry lock, + * we cannot have the file open and thus the node doing unlink will + * take care of deleting the inode. + */ if (current == osb->dc_task) goto bail; @@ -970,8 +972,6 @@ static void ocfs2_delete_inode(struct inode *inode) if (is_bad_inode(inode) || !OCFS2_I(inode)->ip_blkno) goto bail; - dquot_initialize(inode); - if (!ocfs2_inode_is_valid_to_delete(inode)) { /* It's probably not necessary to truncate_inode_pages * here but we do it for safety anyway (it will most @@ -980,6 +980,8 @@ static void ocfs2_delete_inode(struct inode *inode) goto bail; } + dquot_initialize(inode); + /* We want to block signals in delete_inode as the lock and * messaging paths may return us -ERESTARTSYS. Which would * cause us to exit early, resulting in inodes being orphaned @@ -1067,6 +1069,7 @@ static void ocfs2_clear_inode(struct inode *inode) { int status; struct ocfs2_inode_info *oi = OCFS2_I(inode); + struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); clear_inode(inode); trace_ocfs2_clear_inode((unsigned long long)oi->ip_blkno, @@ -1083,9 +1086,9 @@ static void ocfs2_clear_inode(struct inode *inode) /* Do these before all the other work so that we don't bounce * the downconvert thread while waiting to destroy the locks. */ - ocfs2_mark_lockres_freeing(&oi->ip_rw_lockres); - ocfs2_mark_lockres_freeing(&oi->ip_inode_lockres); - ocfs2_mark_lockres_freeing(&oi->ip_open_lockres); + ocfs2_mark_lockres_freeing(osb, &oi->ip_rw_lockres); + ocfs2_mark_lockres_freeing(osb, &oi->ip_inode_lockres); + ocfs2_mark_lockres_freeing(osb, &oi->ip_open_lockres); ocfs2_resv_discard(&OCFS2_SB(inode->i_sb)->osb_la_resmap, &oi->ip_la_data_resv); diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 3a903470c794..f6134345fe42 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -30,6 +30,7 @@ #include #include #include +#include #include #include #include @@ -274,19 +275,16 @@ enum ocfs2_mount_options OCFS2_MOUNT_HB_GLOBAL = 1 << 14, /* Global heartbeat */ }; -#define OCFS2_OSB_SOFT_RO 0x0001 -#define OCFS2_OSB_HARD_RO 0x0002 -#define OCFS2_OSB_ERROR_FS 0x0004 -#define OCFS2_OSB_DROP_DENTRY_LOCK_IMMED 0x0008 - -#define OCFS2_DEFAULT_ATIME_QUANTUM 60 +#define OCFS2_OSB_SOFT_RO 0x0001 +#define OCFS2_OSB_HARD_RO 0x0002 +#define OCFS2_OSB_ERROR_FS 0x0004 +#define OCFS2_DEFAULT_ATIME_QUANTUM 60 struct ocfs2_journal; struct ocfs2_slot_info; struct ocfs2_recovery_map; struct ocfs2_replay_map; struct ocfs2_quota_recovery; -struct ocfs2_dentry_lock; struct ocfs2_super { struct task_struct *commit_task; @@ -413,10 +411,9 @@ struct ocfs2_super struct list_head blocked_lock_list; unsigned long blocked_lock_count; - /* List of dentry locks to release. Anyone can add locks to - * the list, ocfs2_wq processes the list */ - struct ocfs2_dentry_lock *dentry_lock_list; - struct work_struct dentry_lock_work; + /* List of dquot structures to drop last reference to */ + struct llist_head dquot_drop_list; + struct work_struct dquot_drop_work; wait_queue_head_t osb_mount_event; @@ -578,18 +575,6 @@ static inline void ocfs2_set_osb_flag(struct ocfs2_super *osb, spin_unlock(&osb->osb_lock); } - -static inline unsigned long ocfs2_test_osb_flag(struct ocfs2_super *osb, - unsigned long flag) -{ - unsigned long ret; - - spin_lock(&osb->osb_lock); - ret = osb->osb_flags & flag; - spin_unlock(&osb->osb_lock); - return ret; -} - static inline void ocfs2_set_ro_flag(struct ocfs2_super *osb, int hard) { diff --git a/fs/ocfs2/quota.h b/fs/ocfs2/quota.h index d5ab56cbe5c5..f266d67df3c6 100644 --- a/fs/ocfs2/quota.h +++ b/fs/ocfs2/quota.h @@ -28,6 +28,7 @@ struct ocfs2_dquot { unsigned int dq_use_count; /* Number of nodes having reference to this entry in global quota file */ s64 dq_origspace; /* Last globally synced space usage */ s64 dq_originodes; /* Last globally synced inode usage */ + struct llist_node list; /* Member of list of dquots to drop */ }; /* Description of one chunk to recover in memory */ @@ -110,6 +111,7 @@ int ocfs2_read_quota_phys_block(struct inode *inode, u64 p_block, int ocfs2_create_local_dquot(struct dquot *dquot); int ocfs2_local_release_dquot(handle_t *handle, struct dquot *dquot); int ocfs2_local_write_dquot(struct dquot *dquot); +void ocfs2_drop_dquot_refs(struct work_struct *work); extern const struct dquot_operations ocfs2_quota_operations; extern struct quota_format_type ocfs2_quota_format; diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index d7b5108789e2..b990a62cff50 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -10,6 +10,7 @@ #include #include #include +#include #include @@ -679,6 +680,27 @@ static int ocfs2_calc_qdel_credits(struct super_block *sb, int type) OCFS2_INODE_UPDATE_CREDITS; } +void ocfs2_drop_dquot_refs(struct work_struct *work) +{ + struct ocfs2_super *osb = container_of(work, struct ocfs2_super, + dquot_drop_work); + struct llist_node *list; + struct ocfs2_dquot *odquot, *next_odquot; + + list = llist_del_all(&osb->dquot_drop_list); + llist_for_each_entry_safe(odquot, next_odquot, list, list) { + /* Drop the reference we acquired in ocfs2_dquot_release() */ + dqput(&odquot->dq_dquot); + } +} + +/* + * Called when the last reference to dquot is dropped. If we are called from + * downconvert thread, we cannot do all the handling here because grabbing + * quota lock could deadlock (the node holding the quota lock could need some + * other cluster lock to proceed but with blocked downconvert thread we cannot + * release any lock). + */ static int ocfs2_release_dquot(struct dquot *dquot) { handle_t *handle; @@ -694,6 +716,19 @@ static int ocfs2_release_dquot(struct dquot *dquot) /* Check whether we are not racing with some other dqget() */ if (atomic_read(&dquot->dq_count) > 1) goto out; + /* Running from downconvert thread? Postpone quota processing to wq */ + if (current == osb->dc_task) { + /* + * Grab our own reference to dquot and queue it for delayed + * dropping. Quota code rechecks after calling + * ->release_dquot() and won't free dquot structure. + */ + dqgrab(dquot); + /* First entry on list -> queue work */ + if (llist_add(&OCFS2_DQUOT(dquot)->list, &osb->dquot_drop_list)) + queue_work(ocfs2_wq, &osb->dquot_drop_work); + goto out; + } status = ocfs2_lock_global_qf(oinfo, 1); if (status < 0) goto out; diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index d4e81e4a9b04..4d13bf18af22 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1238,30 +1238,11 @@ static struct dentry *ocfs2_mount(struct file_system_type *fs_type, return mount_bdev(fs_type, flags, dev_name, data, ocfs2_fill_super); } -static void ocfs2_kill_sb(struct super_block *sb) -{ - struct ocfs2_super *osb = OCFS2_SB(sb); - - /* Failed mount? */ - if (!osb || atomic_read(&osb->vol_state) == VOLUME_DISABLED) - goto out; - - /* Prevent further queueing of inode drop events */ - spin_lock(&dentry_list_lock); - ocfs2_set_osb_flag(osb, OCFS2_OSB_DROP_DENTRY_LOCK_IMMED); - spin_unlock(&dentry_list_lock); - /* Wait for work to finish and/or remove it */ - cancel_work_sync(&osb->dentry_lock_work); -out: - kill_block_super(sb); -} - static struct file_system_type ocfs2_fs_type = { .owner = THIS_MODULE, .name = "ocfs2", .mount = ocfs2_mount, - .kill_sb = ocfs2_kill_sb, - + .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV|FS_RENAME_DOES_D_MOVE, .next = NULL }; @@ -1934,17 +1915,16 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err) debugfs_remove(osb->osb_ctxt); - /* - * Flush inode dropping work queue so that deletes are - * performed while the filesystem is still working - */ - ocfs2_drop_all_dl_inodes(osb); - /* Orphan scan should be stopped as early as possible */ ocfs2_orphan_scan_stop(osb); ocfs2_disable_quotas(osb); + /* All dquots should be freed by now */ + WARN_ON(!llist_empty(&osb->dquot_drop_list)); + /* Wait for worker to be done with the work structure in osb */ + cancel_work_sync(&osb->dquot_drop_work); + ocfs2_shutdown_local_alloc(osb); ocfs2_truncate_log_shutdown(osb); @@ -2272,8 +2252,8 @@ static int ocfs2_initialize_super(struct super_block *sb, INIT_WORK(&journal->j_recovery_work, ocfs2_complete_recovery); journal->j_state = OCFS2_JOURNAL_FREE; - INIT_WORK(&osb->dentry_lock_work, ocfs2_drop_dl_inodes); - osb->dentry_lock_list = NULL; + INIT_WORK(&osb->dquot_drop_work, ocfs2_drop_dquot_refs); + init_llist_head(&osb->dquot_drop_list); /* get some pseudo constants for clustersize bits */ osb->s_clustersize_bits = diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 390bdab01c3c..ad4df869c907 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1353,7 +1353,7 @@ static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask, struct numa_maps *md; struct page *page; - if (pte_none(*pte)) + if (!pte_present(*pte)) return 0; page = pte_page(*pte); diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index cfc8dcc16043..9cd5f63715c0 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -528,7 +528,7 @@ restart: if (atomic_read(&dquot->dq_count)) { DEFINE_WAIT(wait); - atomic_inc(&dquot->dq_count); + dqgrab(dquot); prepare_to_wait(&dquot->dq_wait_unused, &wait, TASK_UNINTERRUPTIBLE); spin_unlock(&dq_list_lock); @@ -632,7 +632,7 @@ int dquot_writeback_dquots(struct super_block *sb, int type) /* Now we have active dquot from which someone is * holding reference so we can safely just increase * use count */ - atomic_inc(&dquot->dq_count); + dqgrab(dquot); spin_unlock(&dq_list_lock); dqstats_inc(DQST_LOOKUPS); err = sb->dq_op->write_dquot(dquot); diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index e51e581454e9..be9a1fa2721b 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -1569,8 +1569,7 @@ xfs_vm_write_begin( ASSERT(len <= PAGE_CACHE_SIZE); - page = grab_cache_page_write_begin(mapping, index, - flags | AOP_FLAG_NOFS); + page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c index 45560ee1a4ba..19d9fd6caf8c 100644 --- a/fs/xfs/xfs_discard.c +++ b/fs/xfs/xfs_discard.c @@ -158,7 +158,7 @@ xfs_ioc_trim( struct xfs_mount *mp, struct fstrim_range __user *urange) { - struct request_queue *q = mp->m_ddev_targp->bt_bdev->bd_disk->queue; + struct request_queue *q = bdev_get_queue(mp->m_ddev_targp->bt_bdev); unsigned int granularity = q->limits.discard_granularity; struct fstrim_range range; xfs_daddr_t start, end, minlen; @@ -181,7 +181,8 @@ xfs_ioc_trim( * matter as trimming blocks is an advisory interface. */ if (range.start >= XFS_FSB_TO_B(mp, mp->m_sb.sb_dblocks) || - range.minlen > XFS_FSB_TO_B(mp, XFS_ALLOC_AG_MAX_USABLE(mp))) + range.minlen > XFS_FSB_TO_B(mp, XFS_ALLOC_AG_MAX_USABLE(mp)) || + range.len < mp->m_sb.sb_blocksize) return -XFS_ERROR(EINVAL); start = BTOBB(range.start); diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index c888040a1e93..20ccca12a11d 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -153,7 +153,7 @@ xfs_growfs_data_private( xfs_buf_t *bp; int bucket; int dpct; - int error; + int error, saved_error = 0; xfs_agnumber_t nagcount; xfs_agnumber_t nagimax = 0; xfs_rfsblock_t nb, nb_mod; @@ -500,29 +500,33 @@ xfs_growfs_data_private( error = ENOMEM; } + /* + * If we get an error reading or writing alternate superblocks, + * continue. xfs_repair chooses the "best" superblock based + * on most matches; if we break early, we'll leave more + * superblocks un-updated than updated, and xfs_repair may + * pick them over the properly-updated primary. + */ if (error) { xfs_warn(mp, "error %d reading secondary superblock for ag %d", error, agno); - break; + saved_error = error; + continue; } xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb, XFS_SB_ALL_BITS); - /* - * If we get an error writing out the alternate superblocks, - * just issue a warning and continue. The real work is - * already done and committed. - */ error = xfs_bwrite(bp); xfs_buf_relse(bp); if (error) { xfs_warn(mp, "write error %d updating secondary superblock for ag %d", error, agno); - break; /* no point in continuing */ + saved_error = error; + continue; } } - return error; + return saved_error ? saved_error : error; error0: xfs_trans_cancel(tp, XFS_TRANS_ABORT); diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index e3d75385aa76..7a460d8ad06e 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -2370,6 +2370,33 @@ xfs_iunpin_wait( __xfs_iunpin_wait(ip); } +/* + * Removing an inode from the namespace involves removing the directory entry + * and dropping the link count on the inode. Removing the directory entry can + * result in locking an AGF (directory blocks were freed) and removing a link + * count can result in placing the inode on an unlinked list which results in + * locking an AGI. + * + * The big problem here is that we have an ordering constraint on AGF and AGI + * locking - inode allocation locks the AGI, then can allocate a new extent for + * new inodes, locking the AGF after the AGI. Similarly, freeing the inode + * removes the inode from the unlinked list, requiring that we lock the AGI + * first, and then freeing the inode can result in an inode chunk being freed + * and hence freeing disk space requiring that we lock an AGF. + * + * Hence the ordering that is imposed by other parts of the code is AGI before + * AGF. This means we cannot remove the directory entry before we drop the inode + * reference count and put it on the unlinked list as this results in a lock + * order of AGF then AGI, and this can deadlock against inode allocation and + * freeing. Therefore we must drop the link counts before we remove the + * directory entry. + * + * This is still safe from a transactional point of view - it is not until we + * get to xfs_bmap_finish() that we have the possibility of multiple + * transactions in this operation. Hence as long as we remove the directory + * entry and drop the link count in the first transaction of the remove + * operation, there are no transactional constraints on the ordering here. + */ int xfs_remove( xfs_inode_t *dp, @@ -2439,6 +2466,7 @@ xfs_remove( /* * If we're removing a directory perform some additional validation. */ + cancel_flags |= XFS_TRANS_ABORT; if (is_dir) { ASSERT(ip->i_d.di_nlink >= 2); if (ip->i_d.di_nlink != 2) { @@ -2449,31 +2477,16 @@ xfs_remove( error = XFS_ERROR(ENOTEMPTY); goto out_trans_cancel; } - } - xfs_bmap_init(&free_list, &first_block); - error = xfs_dir_removename(tp, dp, name, ip->i_ino, - &first_block, &free_list, resblks); - if (error) { - ASSERT(error != ENOENT); - goto out_bmap_cancel; - } - xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); - - if (is_dir) { - /* - * Drop the link from ip's "..". - */ + /* Drop the link from ip's "..". */ error = xfs_droplink(tp, dp); if (error) - goto out_bmap_cancel; + goto out_trans_cancel; - /* - * Drop the "." link from ip to self. - */ + /* Drop the "." link from ip to self. */ error = xfs_droplink(tp, ip); if (error) - goto out_bmap_cancel; + goto out_trans_cancel; } else { /* * When removing a non-directory we need to log the parent @@ -2482,20 +2495,24 @@ xfs_remove( */ xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE); } + xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); - /* - * Drop the link from dp to ip. - */ + /* Drop the link from dp to ip. */ error = xfs_droplink(tp, ip); if (error) - goto out_bmap_cancel; + goto out_trans_cancel; - /* - * Determine if this is the last link while - * we are in the transaction. - */ + /* Determine if this is the last link while the inode is locked */ link_zero = (ip->i_d.di_nlink == 0); + xfs_bmap_init(&free_list, &first_block); + error = xfs_dir_removename(tp, dp, name, ip->i_ino, + &first_block, &free_list, resblks); + if (error) { + ASSERT(error != ENOENT); + goto out_bmap_cancel; + } + /* * If this is a synchronous mount, make sure that the * remove transaction goes to disk before returning to @@ -2525,7 +2542,6 @@ xfs_remove( out_bmap_cancel: xfs_bmap_cancel(&free_list); - cancel_flags |= XFS_TRANS_ABORT; out_trans_cancel: xfs_trans_cancel(tp, cancel_flags); std_return: diff --git a/fs/xfs/xfs_inode_fork.c b/fs/xfs/xfs_inode_fork.c index 02f1083955bb..6829134de253 100644 --- a/fs/xfs/xfs_inode_fork.c +++ b/fs/xfs/xfs_inode_fork.c @@ -1031,15 +1031,14 @@ xfs_iext_add( * the next index needed in the indirection array. */ else { - int count = ext_diff; + uint count = ext_diff; while (count) { erp = xfs_iext_irec_new(ifp, erp_idx); - erp->er_extcount = count; - count -= MIN(count, (int)XFS_LINEAR_EXTS); - if (count) { + erp->er_extcount = min(count, XFS_LINEAR_EXTS); + count -= erp->er_extcount; + if (count) erp_idx++; - } } } } @@ -1359,7 +1358,7 @@ xfs_iext_remove_indirect( void xfs_iext_realloc_direct( xfs_ifork_t *ifp, /* inode fork pointer */ - int new_size) /* new size of extents */ + int new_size) /* new size of extents after adding */ { int rnew_size; /* real new size of extents */ @@ -1397,13 +1396,8 @@ xfs_iext_realloc_direct( rnew_size - ifp->if_real_bytes); } } - /* - * Switch from the inline extent buffer to a direct - * extent list. Be sure to include the inline extent - * bytes in new_size. - */ + /* Switch from the inline extent buffer to a direct extent list */ else { - new_size += ifp->if_bytes; if (!is_power_of_2(new_size)) { rnew_size = roundup_pow_of_two(new_size); } diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 2b8952d9199b..584996c1bea7 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -1169,6 +1169,7 @@ xfs_setup_inode( struct xfs_inode *ip) { struct inode *inode = &ip->i_vnode; + gfp_t gfp_mask; inode->i_ino = ip->i_ino; inode->i_state = I_NEW; @@ -1229,6 +1230,14 @@ xfs_setup_inode( } /* + * Ensure all page cache allocations are done from GFP_NOFS context to + * prevent direct reclaim recursion back into the filesystem and blowing + * stacks or deadlocking. + */ + gfp_mask = mapping_gfp_mask(inode->i_mapping); + mapping_set_gfp_mask(inode->i_mapping, (gfp_mask & ~(__GFP_FS))); + + /* * If there is no attribute fork no ACL can exist on this inode, * and it can't have any file capabilities attached to it either. */ diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index a2dea108071a..3c4ddc1c79a4 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -1000,27 +1000,34 @@ xfs_log_space_wake( } /* - * Determine if we have a transaction that has gone to disk - * that needs to be covered. To begin the transition to the idle state - * firstly the log needs to be idle (no AIL and nothing in the iclogs). - * If we are then in a state where covering is needed, the caller is informed - * that dummy transactions are required to move the log into the idle state. + * Determine if we have a transaction that has gone to disk that needs to be + * covered. To begin the transition to the idle state firstly the log needs to + * be idle. That means the CIL, the AIL and the iclogs needs to be empty before + * we start attempting to cover the log. * - * Because this is called as part of the sync process, we should also indicate - * that dummy transactions should be issued in anything but the covered or - * idle states. This ensures that the log tail is accurately reflected in - * the log at the end of the sync, hence if a crash occurrs avoids replay - * of transactions where the metadata is already on disk. + * Only if we are then in a state where covering is needed, the caller is + * informed that dummy transactions are required to move the log into the idle + * state. + * + * If there are any items in the AIl or CIL, then we do not want to attempt to + * cover the log as we may be in a situation where there isn't log space + * available to run a dummy transaction and this can lead to deadlocks when the + * tail of the log is pinned by an item that is modified in the CIL. Hence + * there's no point in running a dummy transaction at this point because we + * can't start trying to idle the log until both the CIL and AIL are empty. */ int xfs_log_need_covered(xfs_mount_t *mp) { - int needed = 0; struct xlog *log = mp->m_log; + int needed = 0; if (!xfs_fs_writable(mp)) return 0; + if (!xlog_cil_empty(log)) + return 0; + spin_lock(&log->l_icloglock); switch (log->l_covered_state) { case XLOG_STATE_COVER_DONE: @@ -1029,14 +1036,17 @@ xfs_log_need_covered(xfs_mount_t *mp) break; case XLOG_STATE_COVER_NEED: case XLOG_STATE_COVER_NEED2: - if (!xfs_ail_min_lsn(log->l_ailp) && - xlog_iclogs_empty(log)) { - if (log->l_covered_state == XLOG_STATE_COVER_NEED) - log->l_covered_state = XLOG_STATE_COVER_DONE; - else - log->l_covered_state = XLOG_STATE_COVER_DONE2; - } - /* FALLTHRU */ + if (xfs_ail_min_lsn(log->l_ailp)) + break; + if (!xlog_iclogs_empty(log)) + break; + + needed = 1; + if (log->l_covered_state == XLOG_STATE_COVER_NEED) + log->l_covered_state = XLOG_STATE_COVER_DONE; + else + log->l_covered_state = XLOG_STATE_COVER_DONE2; + break; default: needed = 1; break; @@ -3702,11 +3712,9 @@ xlog_verify_iclog( /* check validity of iclog pointers */ spin_lock(&log->l_icloglock); icptr = log->l_iclog; - for (i=0; i < log->l_iclog_bufs; i++) { - if (icptr == NULL) - xfs_emerg(log->l_mp, "%s: invalid ptr", __func__); - icptr = icptr->ic_next; - } + for (i = 0; i < log->l_iclog_bufs; i++, icptr = icptr->ic_next) + ASSERT(icptr); + if (icptr != log->l_iclog) xfs_emerg(log->l_mp, "%s: corrupt iclog ring", __func__); spin_unlock(&log->l_icloglock); diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index cfe97973ba36..da8524e779b6 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -711,6 +711,20 @@ xlog_cil_push_foreground( xlog_cil_push(log); } +bool +xlog_cil_empty( + struct xlog *log) +{ + struct xfs_cil *cil = log->l_cilp; + bool empty = false; + + spin_lock(&cil->xc_push_lock); + if (list_empty(&cil->xc_cil)) + empty = true; + spin_unlock(&cil->xc_push_lock); + return empty; +} + /* * Commit a transaction with the given vector to the Committed Item List. * diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index 136654b9400d..f80cff26fda9 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -514,12 +514,10 @@ xlog_assign_grant_head(atomic64_t *head, int cycle, int space) /* * Committed Item List interfaces */ -int -xlog_cil_init(struct xlog *log); -void -xlog_cil_init_post_recovery(struct xlog *log); -void -xlog_cil_destroy(struct xlog *log); +int xlog_cil_init(struct xlog *log); +void xlog_cil_init_post_recovery(struct xlog *log); +void xlog_cil_destroy(struct xlog *log); +bool xlog_cil_empty(struct xlog *log); /* * CIL force routines diff --git a/fs/xfs/xfs_sb.c b/fs/xfs/xfs_sb.c index 039708122038..38b7df67ba7c 100644 --- a/fs/xfs/xfs_sb.c +++ b/fs/xfs/xfs_sb.c @@ -633,8 +633,9 @@ xfs_sb_read_verify( out_error: if (error) { - XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, - mp, bp->b_addr); + if (error != EWRONGFS) + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, + mp, bp->b_addr); xfs_buf_ioerror(bp, error); } } diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 6125579b5207..5214ff63c351 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -387,15 +387,13 @@ static inline pgoff_t basepage_index(struct page *page) extern void dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn); -int pmd_huge_support(void); -/* - * Currently hugepage migration is enabled only for pmd-based hugepage. - * This function will be updated when hugepage migration is more widely - * supported. - */ static inline int hugepage_migration_support(struct hstate *h) { - return pmd_huge_support() && (huge_page_shift(h) == PMD_SHIFT); +#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION + return huge_page_shift(h) == PMD_SHIFT; +#else + return 0; +#endif } #else /* CONFIG_HUGETLB_PAGE */ @@ -425,7 +423,6 @@ static inline pgoff_t basepage_index(struct page *page) return page->index; } #define dissolve_free_huge_pages(s, e) do {} while (0) -#define pmd_huge_support() 0 #define hugepage_migration_support(h) 0 #endif /* CONFIG_HUGETLB_PAGE */ diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 56fb646909dc..a7b4b61fc026 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -27,6 +27,8 @@ struct irq_desc; * @irq_count: stats field to detect stalled irqs * @last_unhandled: aging timer for unhandled count * @irqs_unhandled: stats field for spurious unhandled interrupts + * @threads_handled: stats field for deferred spurious detection of threaded handlers + * @threads_handled_last: comparator field for deferred spurious detection of theraded handlers * @lock: locking for SMP * @affinity_hint: hint to user space for preferred irq affinity * @affinity_notify: context for notification of affinity changes @@ -52,6 +54,8 @@ struct irq_desc { unsigned int irq_count; /* For detecting broken IRQs */ unsigned long last_unhandled; /* Aging timer for unhandled count */ unsigned int irqs_unhandled; + atomic_t threads_handled; + int threads_handled_last; raw_spinlock_t lock; struct cpumask *percpu_enabled; #ifdef CONFIG_SMP diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index da6716b9e3fe..ccc1b718c8f3 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -175,6 +175,12 @@ static inline int vma_migratable(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_IO | VM_PFNMAP)) return 0; + +#ifndef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION + if (vma->vm_flags & VM_HUGETLB) + return 0; +#endif + /* * Migration allocates pages in the highest zone. If we cannot * do so then migration (at least from node to node) is not diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index bd791e452ad7..56482904a676 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -75,9 +75,13 @@ enum { extern int page_group_by_mobility_disabled; +#define NR_MIGRATETYPE_BITS (PB_migrate_end - PB_migrate + 1) +#define MIGRATETYPE_MASK ((1UL << NR_MIGRATETYPE_BITS) - 1) + static inline int get_pageblock_migratetype(struct page *page) { - return get_pageblock_flags_group(page, PB_migrate, PB_migrate_end); + BUILD_BUG_ON(PB_migrate_end - PB_migrate != 2); + return get_pageblock_flags_mask(page, PB_migrate_end, MIGRATETYPE_MASK); } struct free_area { diff --git a/include/linux/module.h b/include/linux/module.h index 05f2447f8c15..54aef1b38463 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -143,7 +143,7 @@ extern const struct gtype##_id __mod_##gtype##_table \ #define MODULE_DESCRIPTION(_description) MODULE_INFO(description, _description) #define MODULE_DEVICE_TABLE(type,name) \ - MODULE_GENERIC_TABLE(type##_device,name) + MODULE_GENERIC_TABLE(type##__##name##_device, name) /* Version of form [:][-]. Or for CVS/RCS ID version, everything but the number is stripped. diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9f2a0cbc7d06..51bfd7a68272 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2892,6 +2892,20 @@ extern const char *netdev_drivername(const struct net_device *dev); extern void linkwatch_run_queue(void); +static inline netdev_features_t netdev_intersect_features(netdev_features_t f1, + netdev_features_t f2) +{ + if (f1 & NETIF_F_GEN_CSUM) + f1 |= (NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); + if (f2 & NETIF_F_GEN_CSUM) + f2 |= (NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); + f1 &= f2; + if (f1 & NETIF_F_GEN_CSUM) + f1 &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); + + return f1; +} + static inline netdev_features_t netdev_get_wanted_features( struct net_device *dev) { diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 6d53675c2b54..dd7d45b5c496 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -317,13 +317,23 @@ CLEARPAGEFLAG(Uptodate, uptodate) extern void cancel_dirty_page(struct page *page, unsigned int account_size); int test_clear_page_writeback(struct page *page); -int test_set_page_writeback(struct page *page); +int __test_set_page_writeback(struct page *page, bool keep_write); + +#define test_set_page_writeback(page) \ + __test_set_page_writeback(page, false) +#define test_set_page_writeback_keepwrite(page) \ + __test_set_page_writeback(page, true) static inline void set_page_writeback(struct page *page) { test_set_page_writeback(page); } +static inline void set_page_writeback_keepwrite(struct page *page) +{ + test_set_page_writeback_keepwrite(page); +} + #ifdef CONFIG_PAGEFLAGS_EXTENDED /* * System with lots of page flags available. This allows separate diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index 2ee8cd2466b5..c08730c10c7a 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -30,9 +30,12 @@ enum pageblock_bits { PB_migrate, PB_migrate_end = PB_migrate + 3 - 1, /* 3 bits required for migrate types */ -#ifdef CONFIG_COMPACTION PB_migrate_skip,/* If set the block is skipped by compaction */ -#endif /* CONFIG_COMPACTION */ + + /* + * Assume the bits will always align on a word. If this assumption + * changes then get/set pageblock needs updating. + */ NR_PAGEBLOCK_BITS }; @@ -62,11 +65,33 @@ extern int pageblock_order; /* Forward declaration */ struct page; +unsigned long get_pageblock_flags_mask(struct page *page, + unsigned long end_bitidx, + unsigned long mask); +void set_pageblock_flags_mask(struct page *page, + unsigned long flags, + unsigned long end_bitidx, + unsigned long mask); + /* Declarations for getting and setting flags. See mm/page_alloc.c */ -unsigned long get_pageblock_flags_group(struct page *page, - int start_bitidx, int end_bitidx); -void set_pageblock_flags_group(struct page *page, unsigned long flags, - int start_bitidx, int end_bitidx); +static inline unsigned long get_pageblock_flags_group(struct page *page, + int start_bitidx, int end_bitidx) +{ + unsigned long nr_flag_bits = end_bitidx - start_bitidx + 1; + unsigned long mask = (1 << nr_flag_bits) - 1; + + return get_pageblock_flags_mask(page, end_bitidx, mask); +} + +static inline void set_pageblock_flags_group(struct page *page, + unsigned long flags, + int start_bitidx, int end_bitidx) +{ + unsigned long nr_flag_bits = end_bitidx - start_bitidx + 1; + unsigned long mask = (1 << nr_flag_bits) - 1; + + set_pageblock_flags_mask(page, flags, end_bitidx, mask); +} #ifdef CONFIG_COMPACTION #define get_pageblock_skip(page) \ diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 07d0df6bf768..077904c8b70d 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -5,6 +5,7 @@ #include /* For struct task_struct. */ #include /* for IS_ERR_VALUE */ #include /* For BUG_ON. */ +#include /* For task_active_pid_ns. */ #include /* @@ -129,6 +130,37 @@ static inline void ptrace_event(int event, unsigned long message) } /** + * ptrace_event_pid - possibly stop for a ptrace event notification + * @event: %PTRACE_EVENT_* value to report + * @pid: process identifier for %PTRACE_GETEVENTMSG to return + * + * Check whether @event is enabled and, if so, report @event and @pid + * to the ptrace parent. @pid is reported as the pid_t seen from the + * the ptrace parent's pid namespace. + * + * Called without locks. + */ +static inline void ptrace_event_pid(int event, struct pid *pid) +{ + /* + * FIXME: There's a potential race if a ptracer in a different pid + * namespace than parent attaches between computing message below and + * when we acquire tasklist_lock in ptrace_stop(). If this happens, + * the ptracer will get a bogus pid from PTRACE_GETEVENTMSG. + */ + unsigned long message = 0; + struct pid_namespace *ns; + + rcu_read_lock(); + ns = task_active_pid_ns(rcu_dereference(current->parent)); + if (ns) + message = pid_nr_ns(pid, ns); + rcu_read_unlock(); + + ptrace_event(event, message); +} + +/** * ptrace_init_task - initialize ptrace state for a new child * @child: new child task * @ptrace: true if child should be ptrace'd by parent's tracer diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 6965fe394c3b..1d3eee594cd6 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -46,6 +46,14 @@ void inode_reclaim_rsv_space(struct inode *inode, qsize_t number); void dquot_initialize(struct inode *inode); void dquot_drop(struct inode *inode); struct dquot *dqget(struct super_block *sb, struct kqid qid); +static inline struct dquot *dqgrab(struct dquot *dquot) +{ + /* Make sure someone else has active reference to dquot */ + WARN_ON_ONCE(!atomic_read(&dquot->dq_count)); + WARN_ON_ONCE(!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)); + atomic_inc(&dquot->dq_count); + return dquot; +} void dqput(struct dquot *dquot); int dquot_scan_active(struct super_block *sb, int (*fn)(struct dquot *dquot, unsigned long priv), diff --git a/include/sound/core.h b/include/sound/core.h index 2a14f1f02d4f..d6bc9616058b 100644 --- a/include/sound/core.h +++ b/include/sound/core.h @@ -121,6 +121,8 @@ struct snd_card { int user_ctl_count; /* count of all user controls */ struct list_head controls; /* all controls for this card */ struct list_head ctl_files; /* active control files */ + struct mutex user_ctl_lock; /* protects user controls against + concurrent access */ struct snd_info_entry *proc_root; /* root for soundcard specific files */ struct snd_info_entry *proc_id; /* the card id */ diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h index 361bd0f04018..78edd7895c7f 100644 --- a/include/target/iscsi/iscsi_transport.h +++ b/include/target/iscsi/iscsi_transport.h @@ -68,7 +68,8 @@ extern void iscsit_build_nopin_rsp(struct iscsi_cmd *, struct iscsi_conn *, extern void iscsit_build_task_mgt_rsp(struct iscsi_cmd *, struct iscsi_conn *, struct iscsi_tm_rsp *); extern int iscsit_build_text_rsp(struct iscsi_cmd *, struct iscsi_conn *, - struct iscsi_text_rsp *); + struct iscsi_text_rsp *, + enum iscsit_transport_type); extern void iscsit_build_reject(struct iscsi_cmd *, struct iscsi_conn *, struct iscsi_reject *); extern int iscsit_build_logout_rsp(struct iscsi_cmd *, struct iscsi_conn *, diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index 5ebe21cd5d1c..7eb689ad52a2 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -51,6 +51,7 @@ int transport_subsystem_register(struct se_subsystem_api *); void transport_subsystem_release(struct se_subsystem_api *); void target_complete_cmd(struct se_cmd *, u8); +void target_complete_cmd_with_length(struct se_cmd *, u8, int); sense_reason_t spc_parse_cdb(struct se_cmd *cmd, unsigned int *size); sense_reason_t spc_emulate_report_luns(struct se_cmd *cmd); diff --git a/include/uapi/sound/compress_offload.h b/include/uapi/sound/compress_offload.h index 5759810e1c1b..21eed488783f 100644 --- a/include/uapi/sound/compress_offload.h +++ b/include/uapi/sound/compress_offload.h @@ -80,7 +80,7 @@ struct snd_compr_tstamp { struct snd_compr_avail { __u64 avail; struct snd_compr_tstamp tstamp; -}; +} __attribute__((packed)); enum snd_compr_direction { SND_COMPRESS_PLAYBACK = 0, diff --git a/kernel/fork.c b/kernel/fork.c index 11a23afc6ee5..c873bd081e09 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1609,10 +1609,12 @@ long do_fork(unsigned long clone_flags, */ if (!IS_ERR(p)) { struct completion vfork; + struct pid *pid; trace_sched_process_fork(current, p); - nr = task_pid_vnr(p); + pid = get_task_pid(p, PIDTYPE_PID); + nr = pid_vnr(pid); if (clone_flags & CLONE_PARENT_SETTID) put_user(nr, parent_tidptr); @@ -1627,12 +1629,14 @@ long do_fork(unsigned long clone_flags, /* forking complete and child started to run, tell ptracer */ if (unlikely(trace)) - ptrace_event(trace, nr); + ptrace_event_pid(trace, pid); if (clone_flags & CLONE_VFORK) { if (!wait_for_vfork_done(p, &vfork)) - ptrace_event(PTRACE_EVENT_VFORK_DONE, nr); + ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid); } + + put_pid(pid); } else { nr = PTR_ERR(p); } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 9e31fa71908d..75a976a8ed58 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -856,8 +856,8 @@ static int irq_thread(void *data) irq_thread_check_affinity(desc, action); action_ret = handler_fn(desc, action); - if (!noirqdebug) - note_interrupt(action->irq, desc, action_ret); + if (action_ret == IRQ_HANDLED) + atomic_inc(&desc->threads_handled); wake_threads_waitq(desc); } diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index 7b5f012bde9d..febcee3c2aa9 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -265,21 +265,119 @@ try_misrouted_irq(unsigned int irq, struct irq_desc *desc, return action && (action->flags & IRQF_IRQPOLL); } +#define SPURIOUS_DEFERRED 0x80000000 + void note_interrupt(unsigned int irq, struct irq_desc *desc, irqreturn_t action_ret) { if (desc->istate & IRQS_POLL_INPROGRESS) return; - /* we get here again via the threaded handler */ - if (action_ret == IRQ_WAKE_THREAD) - return; - if (bad_action_ret(action_ret)) { report_bad_irq(irq, desc, action_ret); return; } + /* + * We cannot call note_interrupt from the threaded handler + * because we need to look at the compound of all handlers + * (primary and threaded). Aside of that in the threaded + * shared case we have no serialization against an incoming + * hardware interrupt while we are dealing with a threaded + * result. + * + * So in case a thread is woken, we just note the fact and + * defer the analysis to the next hardware interrupt. + * + * The threaded handlers store whether they sucessfully + * handled an interrupt and we check whether that number + * changed versus the last invocation. + * + * We could handle all interrupts with the delayed by one + * mechanism, but for the non forced threaded case we'd just + * add pointless overhead to the straight hardirq interrupts + * for the sake of a few lines less code. + */ + if (action_ret & IRQ_WAKE_THREAD) { + /* + * There is a thread woken. Check whether one of the + * shared primary handlers returned IRQ_HANDLED. If + * not we defer the spurious detection to the next + * interrupt. + */ + if (action_ret == IRQ_WAKE_THREAD) { + int handled; + /* + * We use bit 31 of thread_handled_last to + * denote the deferred spurious detection + * active. No locking necessary as + * thread_handled_last is only accessed here + * and we have the guarantee that hard + * interrupts are not reentrant. + */ + if (!(desc->threads_handled_last & SPURIOUS_DEFERRED)) { + desc->threads_handled_last |= SPURIOUS_DEFERRED; + return; + } + /* + * Check whether one of the threaded handlers + * returned IRQ_HANDLED since the last + * interrupt happened. + * + * For simplicity we just set bit 31, as it is + * set in threads_handled_last as well. So we + * avoid extra masking. And we really do not + * care about the high bits of the handled + * count. We just care about the count being + * different than the one we saw before. + */ + handled = atomic_read(&desc->threads_handled); + handled |= SPURIOUS_DEFERRED; + if (handled != desc->threads_handled_last) { + action_ret = IRQ_HANDLED; + /* + * Note: We keep the SPURIOUS_DEFERRED + * bit set. We are handling the + * previous invocation right now. + * Keep it for the current one, so the + * next hardware interrupt will + * account for it. + */ + desc->threads_handled_last = handled; + } else { + /* + * None of the threaded handlers felt + * responsible for the last interrupt + * + * We keep the SPURIOUS_DEFERRED bit + * set in threads_handled_last as we + * need to account for the current + * interrupt as well. + */ + action_ret = IRQ_NONE; + } + } else { + /* + * One of the primary handlers returned + * IRQ_HANDLED. So we don't care about the + * threaded handlers on the same line. Clear + * the deferred detection bit. + * + * In theory we could/should check whether the + * deferred bit is set and take the result of + * the previous run into account here as + * well. But it's really not worth the + * trouble. If every other interrupt is + * handled we never trigger the spurious + * detector. And if this is just the one out + * of 100k unhandled ones which is handled + * then we merily delay the spurious detection + * by one hard interrupt. Not a real problem. + */ + desc->threads_handled_last &= ~SPURIOUS_DEFERRED; + } + } + if (unlikely(action_ret == IRQ_NONE)) { /* * If we are seeing only the odd spurious IRQ caused by diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 790e2fc808da..898622244bdf 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1579,13 +1579,7 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq, } wakeup = 0; } else { - /* - * Task re-woke on same cpu (or else migrate_task_rq_fair() - * would have made count negative); we must be careful to avoid - * double-accounting blocked time after synchronizing decays. - */ - se->avg.last_runnable_update += __synchronize_entity_decay(se) - << 20; + __synchronize_entity_decay(se); } /* migrated tasks did not contribute to our blocked load */ @@ -4410,6 +4404,7 @@ static unsigned long scale_rt_power(int cpu) { struct rq *rq = cpu_rq(cpu); u64 total, available, age_stamp, avg; + s64 delta; /* * Since we're reading these variables without serialization make sure @@ -4418,7 +4413,11 @@ static unsigned long scale_rt_power(int cpu) age_stamp = ACCESS_ONCE(rq->age_stamp); avg = ACCESS_ONCE(rq->rt_avg); - total = sched_avg_period() + (rq_clock(rq) - age_stamp); + delta = rq_clock(rq) - age_stamp; + if (unlikely(delta < 0)) + delta = 0; + + total = sched_avg_period() + delta; if (unlikely(total < avg)) { /* Ensures that power won't end up being negative */ diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index ea20f7d1ac2c..29b063b32ff0 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -970,7 +970,7 @@ static void tick_nohz_switch_to_nohz(void) struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched); ktime_t next; - if (!tick_nohz_active) + if (!tick_nohz_enabled) return; local_irq_disable(); diff --git a/lib/idr.c b/lib/idr.c index bfe4db4e165f..674c30bc2ed0 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -250,7 +250,7 @@ static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa, id = (id | ((1 << (IDR_BITS * l)) - 1)) + 1; /* if already at the top layer, we need to grow */ - if (id >= 1 << (idp->layers * IDR_BITS)) { + if (id > idr_max(idp->layers)) { *starting_id = id; return -EAGAIN; } @@ -827,12 +827,10 @@ void *idr_replace(struct idr *idp, void *ptr, int id) if (!p) return ERR_PTR(-EINVAL); - n = (p->layer+1) * IDR_BITS; - - if (id >= (1 << n)) + if (id > idr_max(p->layer + 1)) return ERR_PTR(-EINVAL); - n -= IDR_BITS; + n = p->layer * IDR_BITS; while ((n > 0) && p) { p = p->ary[(id >> n) & IDR_MASK]; n -= IDR_BITS; diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c index df6839e3ce08..b74da447e81e 100644 --- a/lib/lz4/lz4_decompress.c +++ b/lib/lz4/lz4_decompress.c @@ -72,6 +72,8 @@ static int lz4_uncompress(const char *source, char *dest, int osize) len = *ip++; for (; len == 255; length += 255) len = *ip++; + if (unlikely(length > (size_t)(length + len))) + goto _output_error; length += len; } @@ -106,6 +108,8 @@ static int lz4_uncompress(const char *source, char *dest, int osize) if (length == ML_MASK) { for (; *ip == 255; length += 255) ip++; + if (unlikely(length > (size_t)(length + *ip))) + goto _output_error; length += *ip++; } @@ -155,7 +159,7 @@ static int lz4_uncompress(const char *source, char *dest, int osize) /* write overflow error detected */ _output_error: - return (int) (-(((char *)ip) - source)); + return -1; } static int lz4_uncompress_unknownoutputsize(const char *source, char *dest, diff --git a/lib/lzo/lzo1x_decompress_safe.c b/lib/lzo/lzo1x_decompress_safe.c index 569985d522d5..8563081e8da3 100644 --- a/lib/lzo/lzo1x_decompress_safe.c +++ b/lib/lzo/lzo1x_decompress_safe.c @@ -19,11 +19,31 @@ #include #include "lzodefs.h" -#define HAVE_IP(x) ((size_t)(ip_end - ip) >= (size_t)(x)) -#define HAVE_OP(x) ((size_t)(op_end - op) >= (size_t)(x)) -#define NEED_IP(x) if (!HAVE_IP(x)) goto input_overrun -#define NEED_OP(x) if (!HAVE_OP(x)) goto output_overrun -#define TEST_LB(m_pos) if ((m_pos) < out) goto lookbehind_overrun +#define HAVE_IP(t, x) \ + (((size_t)(ip_end - ip) >= (size_t)(t + x)) && \ + (((t + x) >= t) && ((t + x) >= x))) + +#define HAVE_OP(t, x) \ + (((size_t)(op_end - op) >= (size_t)(t + x)) && \ + (((t + x) >= t) && ((t + x) >= x))) + +#define NEED_IP(t, x) \ + do { \ + if (!HAVE_IP(t, x)) \ + goto input_overrun; \ + } while (0) + +#define NEED_OP(t, x) \ + do { \ + if (!HAVE_OP(t, x)) \ + goto output_overrun; \ + } while (0) + +#define TEST_LB(m_pos) \ + do { \ + if ((m_pos) < out) \ + goto lookbehind_overrun; \ + } while (0) int lzo1x_decompress_safe(const unsigned char *in, size_t in_len, unsigned char *out, size_t *out_len) @@ -58,14 +78,14 @@ int lzo1x_decompress_safe(const unsigned char *in, size_t in_len, while (unlikely(*ip == 0)) { t += 255; ip++; - NEED_IP(1); + NEED_IP(1, 0); } t += 15 + *ip++; } t += 3; copy_literal_run: #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) - if (likely(HAVE_IP(t + 15) && HAVE_OP(t + 15))) { + if (likely(HAVE_IP(t, 15) && HAVE_OP(t, 15))) { const unsigned char *ie = ip + t; unsigned char *oe = op + t; do { @@ -81,8 +101,8 @@ copy_literal_run: } else #endif { - NEED_OP(t); - NEED_IP(t + 3); + NEED_OP(t, 0); + NEED_IP(t, 3); do { *op++ = *ip++; } while (--t > 0); @@ -95,7 +115,7 @@ copy_literal_run: m_pos -= t >> 2; m_pos -= *ip++ << 2; TEST_LB(m_pos); - NEED_OP(2); + NEED_OP(2, 0); op[0] = m_pos[0]; op[1] = m_pos[1]; op += 2; @@ -119,10 +139,10 @@ copy_literal_run: while (unlikely(*ip == 0)) { t += 255; ip++; - NEED_IP(1); + NEED_IP(1, 0); } t += 31 + *ip++; - NEED_IP(2); + NEED_IP(2, 0); } m_pos = op - 1; next = get_unaligned_le16(ip); @@ -137,10 +157,10 @@ copy_literal_run: while (unlikely(*ip == 0)) { t += 255; ip++; - NEED_IP(1); + NEED_IP(1, 0); } t += 7 + *ip++; - NEED_IP(2); + NEED_IP(2, 0); } next = get_unaligned_le16(ip); ip += 2; @@ -154,7 +174,7 @@ copy_literal_run: #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) if (op - m_pos >= 8) { unsigned char *oe = op + t; - if (likely(HAVE_OP(t + 15))) { + if (likely(HAVE_OP(t, 15))) { do { COPY8(op, m_pos); op += 8; @@ -164,7 +184,7 @@ copy_literal_run: m_pos += 8; } while (op < oe); op = oe; - if (HAVE_IP(6)) { + if (HAVE_IP(6, 0)) { state = next; COPY4(op, ip); op += next; @@ -172,7 +192,7 @@ copy_literal_run: continue; } } else { - NEED_OP(t); + NEED_OP(t, 0); do { *op++ = *m_pos++; } while (op < oe); @@ -181,7 +201,7 @@ copy_literal_run: #endif { unsigned char *oe = op + t; - NEED_OP(t); + NEED_OP(t, 0); op[0] = m_pos[0]; op[1] = m_pos[1]; op += 2; @@ -194,15 +214,15 @@ match_next: state = next; t = next; #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) - if (likely(HAVE_IP(6) && HAVE_OP(4))) { + if (likely(HAVE_IP(6, 0) && HAVE_OP(4, 0))) { COPY4(op, ip); op += t; ip += t; } else #endif { - NEED_IP(t + 3); - NEED_OP(t); + NEED_IP(t, 3); + NEED_OP(t, 0); while (t > 0) { *op++ = *ip++; t--; diff --git a/mm/Kconfig b/mm/Kconfig index 394838f489eb..2a092f5fa95a 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -254,6 +254,9 @@ config MIGRATION pages as migration can relocate pages to satisfy a huge page allocation instead of reclaiming. +config ARCH_ENABLE_HUGEPAGE_MIGRATION + boolean + config PHYS_ADDR_T_64BIT def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT diff --git a/mm/memory-failure.c b/mm/memory-failure.c index ecfbfe520342..6e3f9c39bc22 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -208,9 +208,9 @@ static int kill_proc(struct task_struct *t, unsigned long addr, int trapno, #endif si.si_addr_lsb = compound_order(compound_head(page)) + PAGE_SHIFT; - if ((flags & MF_ACTION_REQUIRED) && t == current) { + if ((flags & MF_ACTION_REQUIRED) && t->mm == current->mm) { si.si_code = BUS_MCEERR_AR; - ret = force_sig_info(SIGBUS, &si, t); + ret = force_sig_info(SIGBUS, &si, current); } else { /* * Don't use force here, it's convenient if the signal @@ -384,20 +384,51 @@ static void kill_procs(struct list_head *to_kill, int forcekill, int trapno, } } -static int task_early_kill(struct task_struct *tsk) +/* + * Find a dedicated thread which is supposed to handle SIGBUS(BUS_MCEERR_AO) + * on behalf of the thread group. Return task_struct of the (first found) + * dedicated thread if found, and return NULL otherwise. + * + * We already hold read_lock(&tasklist_lock) in the caller, so we don't + * have to call rcu_read_lock/unlock() in this function. + */ +static struct task_struct *find_early_kill_thread(struct task_struct *tsk) { + struct task_struct *t; + + for_each_thread(tsk, t) + if ((t->flags & PF_MCE_PROCESS) && (t->flags & PF_MCE_EARLY)) + return t; + return NULL; +} + +/* + * Determine whether a given process is "early kill" process which expects + * to be signaled when some page under the process is hwpoisoned. + * Return task_struct of the dedicated thread (main thread unless explicitly + * specified) if the process is "early kill," and otherwise returns NULL. + */ +static struct task_struct *task_early_kill(struct task_struct *tsk, + int force_early) +{ + struct task_struct *t; if (!tsk->mm) - return 0; - if (tsk->flags & PF_MCE_PROCESS) - return !!(tsk->flags & PF_MCE_EARLY); - return sysctl_memory_failure_early_kill; + return NULL; + if (force_early) + return tsk; + t = find_early_kill_thread(tsk); + if (t) + return t; + if (sysctl_memory_failure_early_kill) + return tsk; + return NULL; } /* * Collect processes when the error hit an anonymous page. */ static void collect_procs_anon(struct page *page, struct list_head *to_kill, - struct to_kill **tkc) + struct to_kill **tkc, int force_early) { struct vm_area_struct *vma; struct task_struct *tsk; @@ -412,16 +443,17 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, read_lock(&tasklist_lock); for_each_process (tsk) { struct anon_vma_chain *vmac; + struct task_struct *t = task_early_kill(tsk, force_early); - if (!task_early_kill(tsk)) + if (!t) continue; anon_vma_interval_tree_foreach(vmac, &av->rb_root, pgoff, pgoff) { vma = vmac->vma; if (!page_mapped_in_vma(page, vma)) continue; - if (vma->vm_mm == tsk->mm) - add_to_kill(tsk, page, vma, to_kill, tkc); + if (vma->vm_mm == t->mm) + add_to_kill(t, page, vma, to_kill, tkc); } } read_unlock(&tasklist_lock); @@ -432,7 +464,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, * Collect processes when the error hit a file mapped page. */ static void collect_procs_file(struct page *page, struct list_head *to_kill, - struct to_kill **tkc) + struct to_kill **tkc, int force_early) { struct vm_area_struct *vma; struct task_struct *tsk; @@ -442,10 +474,10 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, read_lock(&tasklist_lock); for_each_process(tsk) { pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + struct task_struct *t = task_early_kill(tsk, force_early); - if (!task_early_kill(tsk)) + if (!t) continue; - vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { /* @@ -455,8 +487,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, * Assume applications who requested early kill want * to be informed of all such data corruptions. */ - if (vma->vm_mm == tsk->mm) - add_to_kill(tsk, page, vma, to_kill, tkc); + if (vma->vm_mm == t->mm) + add_to_kill(t, page, vma, to_kill, tkc); } } read_unlock(&tasklist_lock); @@ -469,7 +501,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, * First preallocate one tokill structure outside the spin locks, * so that we can kill at least one process reasonably reliable. */ -static void collect_procs(struct page *page, struct list_head *tokill) +static void collect_procs(struct page *page, struct list_head *tokill, + int force_early) { struct to_kill *tk; @@ -480,9 +513,9 @@ static void collect_procs(struct page *page, struct list_head *tokill) if (!tk) return; if (PageAnon(page)) - collect_procs_anon(page, tokill, &tk); + collect_procs_anon(page, tokill, &tk, force_early); else - collect_procs_file(page, tokill, &tk); + collect_procs_file(page, tokill, &tk, force_early); kfree(tk); } @@ -967,7 +1000,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, * there's nothing that can be done. */ if (kill) - collect_procs(ppage, &tokill); + collect_procs(ppage, &tokill, flags & MF_ACTION_REQUIRED); ret = try_to_unmap(ppage, ttu); if (ret != SWAP_SUCCESS) diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 927a69cf354a..a005cc9f6f18 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -525,9 +525,13 @@ static void queue_pages_hugetlb_pmd_range(struct vm_area_struct *vma, #ifdef CONFIG_HUGETLB_PAGE int nid; struct page *page; + pte_t entry; spin_lock(&vma->vm_mm->page_table_lock); - page = pte_page(huge_ptep_get((pte_t *)pmd)); + entry = huge_ptep_get((pte_t *)pmd); + if (!pte_present(entry)) + goto unlock; + page = pte_page(entry); nid = page_to_nid(page); if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT)) goto unlock; diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 8f6daa62206d..d013dba21429 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2398,7 +2398,7 @@ int test_clear_page_writeback(struct page *page) return ret; } -int test_set_page_writeback(struct page *page) +int __test_set_page_writeback(struct page *page, bool keep_write) { struct address_space *mapping = page_mapping(page); int ret; @@ -2423,9 +2423,10 @@ int test_set_page_writeback(struct page *page) radix_tree_tag_clear(&mapping->page_tree, page_index(page), PAGECACHE_TAG_DIRTY); - radix_tree_tag_clear(&mapping->page_tree, - page_index(page), - PAGECACHE_TAG_TOWRITE); + if (!keep_write) + radix_tree_tag_clear(&mapping->page_tree, + page_index(page), + PAGECACHE_TAG_TOWRITE); spin_unlock_irqrestore(&mapping->tree_lock, flags); } else { ret = TestSetPageWriteback(page); @@ -2436,7 +2437,7 @@ int test_set_page_writeback(struct page *page) return ret; } -EXPORT_SYMBOL(test_set_page_writeback); +EXPORT_SYMBOL(__test_set_page_writeback); /* * Return true if any of the pages in the mapping are marked with the diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 09459deb0b51..a6bf980f5dd0 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5948,53 +5948,65 @@ static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn) * @end_bitidx: The last bit of interest * returns pageblock_bits flags */ -unsigned long get_pageblock_flags_group(struct page *page, - int start_bitidx, int end_bitidx) +unsigned long get_pageblock_flags_mask(struct page *page, + unsigned long end_bitidx, + unsigned long mask) { struct zone *zone; unsigned long *bitmap; - unsigned long pfn, bitidx; - unsigned long flags = 0; - unsigned long value = 1; + unsigned long pfn, bitidx, word_bitidx; + unsigned long word; zone = page_zone(page); pfn = page_to_pfn(page); bitmap = get_pageblock_bitmap(zone, pfn); bitidx = pfn_to_bitidx(zone, pfn); + word_bitidx = bitidx / BITS_PER_LONG; + bitidx &= (BITS_PER_LONG-1); - for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1) - if (test_bit(bitidx + start_bitidx, bitmap)) - flags |= value; - - return flags; + word = bitmap[word_bitidx]; + bitidx += end_bitidx; + return (word >> (BITS_PER_LONG - bitidx - 1)) & mask; } /** - * set_pageblock_flags_group - Set the requested group of flags for a pageblock_nr_pages block of pages + * set_pageblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages * @page: The page within the block of interest * @start_bitidx: The first bit of interest * @end_bitidx: The last bit of interest * @flags: The flags to set */ -void set_pageblock_flags_group(struct page *page, unsigned long flags, - int start_bitidx, int end_bitidx) +void set_pageblock_flags_mask(struct page *page, unsigned long flags, + unsigned long end_bitidx, + unsigned long mask) { struct zone *zone; unsigned long *bitmap; - unsigned long pfn, bitidx; - unsigned long value = 1; + unsigned long pfn, bitidx, word_bitidx; + unsigned long old_word, word; + + BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4); zone = page_zone(page); pfn = page_to_pfn(page); bitmap = get_pageblock_bitmap(zone, pfn); bitidx = pfn_to_bitidx(zone, pfn); + word_bitidx = bitidx / BITS_PER_LONG; + bitidx &= (BITS_PER_LONG-1); + VM_BUG_ON(!zone_spans_pfn(zone, pfn)); - for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1) - if (flags & value) - __set_bit(bitidx + start_bitidx, bitmap); - else - __clear_bit(bitidx + start_bitidx, bitmap); + bitidx += end_bitidx; + mask <<= (BITS_PER_LONG - bitidx - 1); + flags <<= (BITS_PER_LONG - bitidx - 1); + + word = ACCESS_ONCE(bitmap[word_bitidx]); + for (;;) { + old_word = cmpxchg(&bitmap[word_bitidx], word, (word & ~mask) | flags); + if (word == old_word) + break; + word = old_word; + } } /* diff --git a/mm/rmap.c b/mm/rmap.c index 91ab22878103..4271107aa46e 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -103,6 +103,7 @@ static inline void anon_vma_free(struct anon_vma *anon_vma) * LOCK should suffice since the actual taking of the lock must * happen _before_ what follows. */ + might_sleep(); if (rwsem_is_locked(&anon_vma->root->rwsem)) { anon_vma_lock_write(anon_vma); anon_vma_unlock_write(anon_vma); @@ -426,8 +427,9 @@ struct anon_vma *page_get_anon_vma(struct page *page) * above cannot corrupt). */ if (!page_mapped(page)) { + rcu_read_unlock(); put_anon_vma(anon_vma); - anon_vma = NULL; + return NULL; } out: rcu_read_unlock(); @@ -477,9 +479,9 @@ struct anon_vma *page_lock_anon_vma_read(struct page *page) } if (!page_mapped(page)) { + rcu_read_unlock(); put_anon_vma(anon_vma); - anon_vma = NULL; - goto out; + return NULL; } /* we pinned the anon_vma, its safe to sleep */ diff --git a/mm/vmscan.c b/mm/vmscan.c index 05e6095159dc..1d891f49587b 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2484,10 +2484,17 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat) for (i = 0; i <= ZONE_NORMAL; i++) { zone = &pgdat->node_zones[i]; + if (!populated_zone(zone)) + continue; + pfmemalloc_reserve += min_wmark_pages(zone); free_pages += zone_page_state(zone, NR_FREE_PAGES); } + /* If there are no reserves (unexpected config) then do not throttle */ + if (!pfmemalloc_reserve) + return true; + wmark_ok = free_pages > pfmemalloc_reserve / 2; /* kswapd must be awake if processes are being throttled */ @@ -2512,9 +2519,9 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat) static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, nodemask_t *nodemask) { + struct zoneref *z; struct zone *zone; - int high_zoneidx = gfp_zone(gfp_mask); - pg_data_t *pgdat; + pg_data_t *pgdat = NULL; /* * Kernel threads should not be throttled as they may be indirectly @@ -2533,10 +2540,34 @@ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, if (fatal_signal_pending(current)) goto out; - /* Check if the pfmemalloc reserves are ok */ - first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone); - pgdat = zone->zone_pgdat; - if (pfmemalloc_watermark_ok(pgdat)) + /* + * Check if the pfmemalloc reserves are ok by finding the first node + * with a usable ZONE_NORMAL or lower zone. The expectation is that + * GFP_KERNEL will be required for allocating network buffers when + * swapping over the network so ZONE_HIGHMEM is unusable. + * + * Throttling is based on the first usable node and throttled processes + * wait on a queue until kswapd makes progress and wakes them. There + * is an affinity then between processes waking up and where reclaim + * progress has been made assuming the process wakes on the same node. + * More importantly, processes running on remote nodes will not compete + * for remote pfmemalloc reserves and processes on different nodes + * should make reasonable progress. + */ + for_each_zone_zonelist_nodemask(zone, z, zonelist, + gfp_mask, nodemask) { + if (zone_idx(zone) > ZONE_NORMAL) + continue; + + /* Throttle based on the first usable node */ + pgdat = zone->zone_pgdat; + if (pfmemalloc_watermark_ok(pgdat)) + goto out; + break; + } + + /* If no zone was usable by the allocation flags then do not throttle */ + if (!pgdat) goto out; /* Account for the throttling */ @@ -3267,7 +3298,10 @@ static int kswapd(void *p) } } + tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD); current->reclaim_state = NULL; + lockdep_clear_current_reclaim_state(); + return 0; } diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 1b89bc7468de..0c21361fab30 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -694,9 +694,9 @@ static netdev_features_t vlan_dev_fix_features(struct net_device *dev, struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; netdev_features_t old_features = features; - features &= real_dev->vlan_features; + features = netdev_intersect_features(features, real_dev->vlan_features); features |= NETIF_F_RXCSUM; - features &= real_dev->features; + features = netdev_intersect_features(features, real_dev->features); features |= old_features & NETIF_F_SOFT_FEATURES; features |= NETIF_F_LLTX; diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index f0817121ec5e..3d339414dc9e 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -690,14 +690,17 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) if (!test_and_set_bit(HCI_CONN_AUTH_PEND, &conn->flags)) { struct hci_cp_auth_requested cp; - /* encrypt must be pending if auth is also pending */ - set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); - cp.handle = cpu_to_le16(conn->handle); hci_send_cmd(conn->hdev, HCI_OP_AUTH_REQUESTED, sizeof(cp), &cp); - if (conn->key_type != 0xff) + + /* If we're already encrypted set the REAUTH_PEND flag, + * otherwise set the ENCRYPT_PEND. + */ + if (conn->link_mode & HCI_LM_ENCRYPT) set_bit(HCI_CONN_REAUTH_PEND, &conn->flags); + else + set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); } return 0; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 0098af80b213..07c9aea21244 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -949,13 +949,16 @@ static struct l2cap_chan *l2cap_sock_new_connection_cb(struct l2cap_chan *chan) /* Check for backlog size */ if (sk_acceptq_is_full(parent)) { BT_DBG("backlog full %d", parent->sk_ack_backlog); + release_sock(parent); return NULL; } sk = l2cap_sock_alloc(sock_net(parent), NULL, BTPROTO_L2CAP, GFP_ATOMIC); - if (!sk) + if (!sk) { + release_sock(parent); return NULL; + } bt_sock_reclassify_lock(sk, BTPROTO_L2CAP); diff --git a/net/core/dev.c b/net/core/dev.c index 58990d60e65b..704c0c5bed1f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5636,13 +5636,8 @@ int register_netdevice(struct net_device *dev) dev->features |= NETIF_F_SOFT_FEATURES; dev->wanted_features = dev->features & dev->hw_features; - /* Turn on no cache copy if HW is doing checksum */ if (!(dev->flags & IFF_LOOPBACK)) { dev->hw_features |= NETIF_F_NOCACHE_COPY; - if (dev->features & NETIF_F_ALL_CSUM) { - dev->wanted_features |= NETIF_F_NOCACHE_COPY; - dev->features |= NETIF_F_NOCACHE_COPY; - } } /* Make NETIF_F_HIGHDMA inheritable to VLAN devices. diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index cbc22158af49..9cb993cd224b 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -220,6 +220,7 @@ static void ipt_ulog_packet(struct net *net, ub->qlen++; pm = nlmsg_data(nlh); + memset(pm, 0, sizeof(*pm)); /* We might not have a timestamp, get one */ if (skb->tstamp.tv64 == 0) @@ -238,8 +239,6 @@ static void ipt_ulog_packet(struct net *net, } else if (loginfo->prefix[0] != '\0') strncpy(pm->prefix, loginfo->prefix, sizeof(pm->prefix)); - else - *(pm->prefix) = '\0'; if (in && in->hard_header_len > 0 && skb->mac_header != skb->network_header && @@ -251,13 +250,9 @@ static void ipt_ulog_packet(struct net *net, if (in) strncpy(pm->indev_name, in->name, sizeof(pm->indev_name)); - else - pm->indev_name[0] = '\0'; if (out) strncpy(pm->outdev_name, out->name, sizeof(pm->outdev_name)); - else - pm->outdev_name[0] = '\0'; /* copy_len <= skb->len, so can't fail. */ if (skb_copy_bits(skb, 0, pm->payload, copy_len) < 0) diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index c4b7218058b6..1465363a452b 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1829,7 +1829,7 @@ static void iucv_callback_txdone(struct iucv_path *path, spin_lock_irqsave(&list->lock, flags); while (list_skb != (struct sk_buff *)list) { - if (msg->tag != IUCV_SKB_CB(list_skb)->tag) { + if (msg->tag == IUCV_SKB_CB(list_skb)->tag) { this = list_skb; break; } diff --git a/net/socket.c b/net/socket.c index dc57dae20a9a..c8ca896a9a5a 100644 --- a/net/socket.c +++ b/net/socket.c @@ -3023,19 +3023,16 @@ static int siocdevprivate_ioctl(struct net *net, unsigned int cmd, if (copy_from_user(&tmp_buf[0], &(u_ifreq32->ifr_ifrn.ifrn_name[0]), IFNAMSIZ)) return -EFAULT; - if (__get_user(data32, &u_ifreq32->ifr_ifru.ifru_data)) + if (get_user(data32, &u_ifreq32->ifr_ifru.ifru_data)) return -EFAULT; data64 = compat_ptr(data32); u_ifreq64 = compat_alloc_user_space(sizeof(*u_ifreq64)); - /* Don't check these user accesses, just let that get trapped - * in the ioctl handler instead. - */ if (copy_to_user(&u_ifreq64->ifr_ifrn.ifrn_name[0], &tmp_buf[0], IFNAMSIZ)) return -EFAULT; - if (__put_user(data64, &u_ifreq64->ifr_ifru.ifru_data)) + if (put_user(data64, &u_ifreq64->ifr_ifru.ifru_data)) return -EFAULT; return dev_ioctl(net, cmd, u_ifreq64); diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 299e45af7e4e..ec2ecbd515ae 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -962,6 +962,7 @@ static void tipc_purge_publications(struct name_seq *seq) list_for_each_entry_safe(publ, safe, &info->zone_list, zone_list) { tipc_nametbl_remove_publ(publ->type, publ->lower, publ->node, publ->ref, publ->key); + kfree(publ); } } @@ -986,7 +987,6 @@ void tipc_nametbl_stop(void) hlist_for_each_entry_safe(seq, safe, seq_head, ns_list) { tipc_purge_publications(seq); } - continue; } kfree(table.types); table.types = NULL; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 352dfa4c39ee..32a2dd39b785 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -930,6 +930,20 @@ static struct sk_buff *xfrm_state_netlink(struct sk_buff *in_skb, return skb; } +/* A wrapper for nlmsg_multicast() checking that nlsk is still available. + * Must be called with RCU read lock. + */ +static inline int xfrm_nlmsg_multicast(struct net *net, struct sk_buff *skb, + u32 pid, unsigned int group) +{ + struct sock *nlsk = rcu_dereference(net->xfrm.nlsk); + + if (nlsk) + return nlmsg_multicast(nlsk, skb, pid, group, GFP_ATOMIC); + else + return -1; +} + static inline size_t xfrm_spdinfo_msgsize(void) { return NLMSG_ALIGN(4) @@ -2253,7 +2267,7 @@ static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, if (build_migrate(skb, m, num_migrate, k, sel, dir, type) < 0) BUG(); - return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_MIGRATE, GFP_ATOMIC); + return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_MIGRATE); } #else static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, @@ -2440,7 +2454,7 @@ static int xfrm_exp_state_notify(struct xfrm_state *x, const struct km_event *c) return -EMSGSIZE; } - return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_EXPIRE, GFP_ATOMIC); + return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_EXPIRE); } static int xfrm_aevent_state_notify(struct xfrm_state *x, const struct km_event *c) @@ -2455,7 +2469,7 @@ static int xfrm_aevent_state_notify(struct xfrm_state *x, const struct km_event if (build_aevent(skb, x, c) < 0) BUG(); - return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_AEVENTS, GFP_ATOMIC); + return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_AEVENTS); } static int xfrm_notify_sa_flush(const struct km_event *c) @@ -2481,7 +2495,7 @@ static int xfrm_notify_sa_flush(const struct km_event *c) nlmsg_end(skb, nlh); - return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_SA, GFP_ATOMIC); + return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_SA); } static inline size_t xfrm_sa_len(struct xfrm_state *x) @@ -2568,7 +2582,7 @@ static int xfrm_notify_sa(struct xfrm_state *x, const struct km_event *c) nlmsg_end(skb, nlh); - return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_SA, GFP_ATOMIC); + return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_SA); out_free_skb: kfree_skb(skb); @@ -2659,7 +2673,7 @@ static int xfrm_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *xt, if (build_acquire(skb, x, xt, xp) < 0) BUG(); - return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_ACQUIRE, GFP_ATOMIC); + return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_ACQUIRE); } /* User gives us xfrm_user_policy_info followed by an array of 0 @@ -2773,7 +2787,7 @@ static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, const struct if (build_polexpire(skb, xp, dir, c) < 0) BUG(); - return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_EXPIRE, GFP_ATOMIC); + return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_EXPIRE); } static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_event *c) @@ -2835,7 +2849,7 @@ static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_e nlmsg_end(skb, nlh); - return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_POLICY, GFP_ATOMIC); + return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_POLICY); out_free_skb: kfree_skb(skb); @@ -2863,7 +2877,7 @@ static int xfrm_notify_policy_flush(const struct km_event *c) nlmsg_end(skb, nlh); - return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_POLICY, GFP_ATOMIC); + return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_POLICY); out_free_skb: kfree_skb(skb); @@ -2932,7 +2946,7 @@ static int xfrm_send_report(struct net *net, u8 proto, if (build_report(skb, proto, sel, addr) < 0) BUG(); - return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_REPORT, GFP_ATOMIC); + return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_REPORT); } static inline size_t xfrm_mapping_msgsize(void) @@ -2984,7 +2998,7 @@ static int xfrm_send_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, if (build_mapping(skb, x, ipaddr, sport) < 0) BUG(); - return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_MAPPING, GFP_ATOMIC); + return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_MAPPING); } static struct xfrm_mgr netlink_mgr = { diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 25e5cb0aaef6..ce164044f0cc 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -42,7 +42,7 @@ typedef unsigned char __u8; /* This array collects all instances that use the generic do_table */ struct devtable { - const char *device_id; /* name of table, __mod__device_table. */ + const char *device_id; /* name of table, __mod___*_device_table. */ unsigned long id_size; void *function; }; @@ -146,7 +146,8 @@ static void device_id_check(const char *modname, const char *device_id, if (size % id_size || size < id_size) { fatal("%s: sizeof(struct %s_device_id)=%lu is not a modulo " - "of the size of section __mod_%s_device_table=%lu.\n" + "of the size of " + "section __mod_%s___device_table=%lu.\n" "Fix definition of struct %s_device_id " "in mod_devicetable.h\n", modname, device_id, id_size, device_id, size, device_id); @@ -1206,7 +1207,7 @@ void handle_moddevtable(struct module *mod, struct elf_info *info, { void *symval; char *zeros = NULL; - const char *name; + const char *name, *identifier; unsigned int namelen; /* We're looking for a section relative symbol */ @@ -1217,7 +1218,7 @@ void handle_moddevtable(struct module *mod, struct elf_info *info, if (ELF_ST_TYPE(sym->st_info) != STT_OBJECT) return; - /* All our symbols are of form __mod_XXX_device_table. */ + /* All our symbols are of form __mod____device_table. */ name = strstr(symname, "__mod_"); if (!name) return; @@ -1227,7 +1228,10 @@ void handle_moddevtable(struct module *mod, struct elf_info *info, return; if (strcmp(name + namelen - strlen("_device_table"), "_device_table")) return; - namelen -= strlen("_device_table"); + identifier = strstr(name, "__"); + if (!identifier) + return; + namelen = identifier - name; /* Handle all-NULL symbols allocated into .bss */ if (info->sechdrs[get_secindex(info, sym)].sh_type & SHT_NOBITS) { diff --git a/scripts/package/builddeb b/scripts/package/builddeb index c1bb9be00fa0..6d02fd5d59bd 100644 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -155,11 +155,11 @@ if grep -q '^CONFIG_MODULES=y' $KCONFIG_CONFIG ; then for module in $(find lib/modules/ -name *.ko); do mkdir -p $(dirname $dbg_dir/usr/lib/debug/$module) # only keep debug symbols in the debug file - objcopy --only-keep-debug $module $dbg_dir/usr/lib/debug/$module + $OBJCOPY --only-keep-debug $module $dbg_dir/usr/lib/debug/$module # strip original module from debug symbols - objcopy --strip-debug $module + $OBJCOPY --strip-debug $module # then add a link to those - objcopy --add-gnu-debuglink=$dbg_dir/usr/lib/debug/$module $module + $OBJCOPY --add-gnu-debuglink=$dbg_dir/usr/lib/debug/$module $module done ) fi diff --git a/sound/core/control.c b/sound/core/control.c index d8aa206e8bde..98a29b26c5f4 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -289,6 +289,10 @@ static bool snd_ctl_remove_numid_conflict(struct snd_card *card, { struct snd_kcontrol *kctl; + /* Make sure that the ids assigned to the control do not wrap around */ + if (card->last_numid >= UINT_MAX - count) + card->last_numid = 0; + list_for_each_entry(kctl, &card->controls, list) { if (kctl->id.numid < card->last_numid + 1 + count && kctl->id.numid + kctl->count > card->last_numid + 1) { @@ -331,6 +335,7 @@ int snd_ctl_add(struct snd_card *card, struct snd_kcontrol *kcontrol) { struct snd_ctl_elem_id id; unsigned int idx; + unsigned int count; int err = -EINVAL; if (! kcontrol) @@ -338,6 +343,9 @@ int snd_ctl_add(struct snd_card *card, struct snd_kcontrol *kcontrol) if (snd_BUG_ON(!card || !kcontrol->info)) goto error; id = kcontrol->id; + if (id.index > UINT_MAX - kcontrol->count) + goto error; + down_write(&card->controls_rwsem); if (snd_ctl_find_id(card, &id)) { up_write(&card->controls_rwsem); @@ -359,8 +367,9 @@ int snd_ctl_add(struct snd_card *card, struct snd_kcontrol *kcontrol) card->controls_count += kcontrol->count; kcontrol->id.numid = card->last_numid + 1; card->last_numid += kcontrol->count; + count = kcontrol->count; up_write(&card->controls_rwsem); - for (idx = 0; idx < kcontrol->count; idx++, id.index++, id.numid++) + for (idx = 0; idx < count; idx++, id.index++, id.numid++) snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_ADD, &id); return 0; @@ -389,6 +398,7 @@ int snd_ctl_replace(struct snd_card *card, struct snd_kcontrol *kcontrol, bool add_on_replace) { struct snd_ctl_elem_id id; + unsigned int count; unsigned int idx; struct snd_kcontrol *old; int ret; @@ -424,8 +434,9 @@ add: card->controls_count += kcontrol->count; kcontrol->id.numid = card->last_numid + 1; card->last_numid += kcontrol->count; + count = kcontrol->count; up_write(&card->controls_rwsem); - for (idx = 0; idx < kcontrol->count; idx++, id.index++, id.numid++) + for (idx = 0; idx < count; idx++, id.index++, id.numid++) snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_ADD, &id); return 0; @@ -898,9 +909,9 @@ static int snd_ctl_elem_write(struct snd_card *card, struct snd_ctl_file *file, result = kctl->put(kctl, control); } if (result > 0) { + struct snd_ctl_elem_id id = control->id; up_read(&card->controls_rwsem); - snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE, - &control->id); + snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE, &id); return 0; } } @@ -992,6 +1003,7 @@ static int snd_ctl_elem_unlock(struct snd_ctl_file *file, struct user_element { struct snd_ctl_elem_info info; + struct snd_card *card; void *elem_data; /* element data */ unsigned long elem_data_size; /* size of element data in bytes */ void *tlv_data; /* TLV data */ @@ -1035,7 +1047,9 @@ static int snd_ctl_elem_user_get(struct snd_kcontrol *kcontrol, { struct user_element *ue = kcontrol->private_data; + mutex_lock(&ue->card->user_ctl_lock); memcpy(&ucontrol->value, ue->elem_data, ue->elem_data_size); + mutex_unlock(&ue->card->user_ctl_lock); return 0; } @@ -1044,10 +1058,12 @@ static int snd_ctl_elem_user_put(struct snd_kcontrol *kcontrol, { int change; struct user_element *ue = kcontrol->private_data; - + + mutex_lock(&ue->card->user_ctl_lock); change = memcmp(&ucontrol->value, ue->elem_data, ue->elem_data_size) != 0; if (change) memcpy(ue->elem_data, &ucontrol->value, ue->elem_data_size); + mutex_unlock(&ue->card->user_ctl_lock); return change; } @@ -1067,19 +1083,32 @@ static int snd_ctl_elem_user_tlv(struct snd_kcontrol *kcontrol, new_data = memdup_user(tlv, size); if (IS_ERR(new_data)) return PTR_ERR(new_data); + mutex_lock(&ue->card->user_ctl_lock); change = ue->tlv_data_size != size; if (!change) change = memcmp(ue->tlv_data, new_data, size); kfree(ue->tlv_data); ue->tlv_data = new_data; ue->tlv_data_size = size; + mutex_unlock(&ue->card->user_ctl_lock); } else { - if (! ue->tlv_data_size || ! ue->tlv_data) - return -ENXIO; - if (size < ue->tlv_data_size) - return -ENOSPC; + int ret = 0; + + mutex_lock(&ue->card->user_ctl_lock); + if (!ue->tlv_data_size || !ue->tlv_data) { + ret = -ENXIO; + goto err_unlock; + } + if (size < ue->tlv_data_size) { + ret = -ENOSPC; + goto err_unlock; + } if (copy_to_user(tlv, ue->tlv_data, ue->tlv_data_size)) - return -EFAULT; + ret = -EFAULT; +err_unlock: + mutex_unlock(&ue->card->user_ctl_lock); + if (ret) + return ret; } return change; } @@ -1137,8 +1166,6 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file, struct user_element *ue; int idx, err; - if (!replace && card->user_ctl_count >= MAX_USER_CONTROLS) - return -ENOMEM; if (info->count < 1) return -EINVAL; access = info->access == 0 ? SNDRV_CTL_ELEM_ACCESS_READWRITE : @@ -1147,21 +1174,16 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file, SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE)); info->id.numid = 0; memset(&kctl, 0, sizeof(kctl)); - down_write(&card->controls_rwsem); - _kctl = snd_ctl_find_id(card, &info->id); - err = 0; - if (_kctl) { - if (replace) - err = snd_ctl_remove(card, _kctl); - else - err = -EBUSY; - } else { - if (replace) - err = -ENOENT; + + if (replace) { + err = snd_ctl_remove_user_ctl(file, &info->id); + if (err) + return err; } - up_write(&card->controls_rwsem); - if (err < 0) - return err; + + if (card->user_ctl_count >= MAX_USER_CONTROLS) + return -ENOMEM; + memcpy(&kctl.id, &info->id, sizeof(info->id)); kctl.count = info->owner ? info->owner : 1; access |= SNDRV_CTL_ELEM_ACCESS_USER; @@ -1211,6 +1233,7 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file, ue = kzalloc(sizeof(struct user_element) + private_size, GFP_KERNEL); if (ue == NULL) return -ENOMEM; + ue->card = card; ue->info = *info; ue->info.access = 0; ue->elem_data = (char *)ue + sizeof(*ue); @@ -1322,8 +1345,9 @@ static int snd_ctl_tlv_ioctl(struct snd_ctl_file *file, } err = kctl->tlv.c(kctl, op_flag, tlv.length, _tlv->tlv); if (err > 0) { + struct snd_ctl_elem_id id = kctl->id; up_read(&card->controls_rwsem); - snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_TLV, &kctl->id); + snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_TLV, &id); return 0; } } else { diff --git a/sound/core/init.c b/sound/core/init.c index d04785144601..b9268a55126b 100644 --- a/sound/core/init.c +++ b/sound/core/init.c @@ -215,6 +215,7 @@ int snd_card_create(int idx, const char *xid, INIT_LIST_HEAD(&card->devices); init_rwsem(&card->controls_rwsem); rwlock_init(&card->ctl_files_rwlock); + mutex_init(&card->user_ctl_lock); INIT_LIST_HEAD(&card->controls); INIT_LIST_HEAD(&card->ctl_files); spin_lock_init(&card->files_lock); diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 2949c8d34d33..9d1a53f2a510 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -743,12 +743,12 @@ static struct channel_map_table map_tables[] = { { SNDRV_CHMAP_RC, RC }, { SNDRV_CHMAP_FLC, FLC }, { SNDRV_CHMAP_FRC, FRC }, - { SNDRV_CHMAP_FLH, FLH }, - { SNDRV_CHMAP_FRH, FRH }, + { SNDRV_CHMAP_TFL, FLH }, + { SNDRV_CHMAP_TFR, FRH }, { SNDRV_CHMAP_FLW, FLW }, { SNDRV_CHMAP_FRW, FRW }, { SNDRV_CHMAP_TC, TC }, - { SNDRV_CHMAP_FCH, FCH }, + { SNDRV_CHMAP_TFC, FCH }, {} /* terminator */ }; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 23971aa25fef..b8a5f1d02b18 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -3689,6 +3689,7 @@ enum { ALC269_FIXUP_HEADSET_MIC, ALC269_FIXUP_QUANTA_MUTE, ALC269_FIXUP_LIFEBOOK, + ALC269_FIXUP_LIFEBOOK_EXTMIC, ALC269_FIXUP_AMIC, ALC269_FIXUP_DMIC, ALC269VB_FIXUP_AMIC, @@ -3806,6 +3807,13 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_QUANTA_MUTE }, + [ALC269_FIXUP_LIFEBOOK_EXTMIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x01a1903c }, /* headset mic, with jack detect */ + { } + }, + }, [ALC269_FIXUP_AMIC] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -4105,6 +4113,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x104d, 0x9084, "Sony VAIO", ALC275_FIXUP_SONY_HWEQ), SND_PCI_QUIRK_VENDOR(0x104d, "Sony VAIO", ALC269_FIXUP_SONY_VAIO), SND_PCI_QUIRK(0x10cf, 0x1475, "Lifebook", ALC269_FIXUP_LIFEBOOK), + SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC), SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x21b8, "Thinkpad Edge 14", ALC269_FIXUP_SKU_IGNORE), @@ -5134,6 +5143,7 @@ static const struct hda_codec_preset snd_hda_preset_realtek[] = { { .id = 0x10ec0670, .name = "ALC670", .patch = patch_alc662 }, { .id = 0x10ec0671, .name = "ALC671", .patch = patch_alc662 }, { .id = 0x10ec0680, .name = "ALC680", .patch = patch_alc680 }, + { .id = 0x10ec0867, .name = "ALC891", .patch = patch_alc882 }, { .id = 0x10ec0880, .name = "ALC880", .patch = patch_alc880 }, { .id = 0x10ec0882, .name = "ALC882", .patch = patch_alc882 }, { .id = 0x10ec0883, .name = "ALC883", .patch = patch_alc882 }, diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c index 8bddf3f20a5e..9ad8f019adcd 100644 --- a/sound/soc/codecs/max98090.c +++ b/sound/soc/codecs/max98090.c @@ -255,6 +255,7 @@ static struct reg_default max98090_reg[] = { static bool max98090_volatile_register(struct device *dev, unsigned int reg) { switch (reg) { + case M98090_REG_SOFTWARE_RESET: case M98090_REG_DEVICE_STATUS: case M98090_REG_JACK_STATUS: case M98090_REG_REVISION_ID: @@ -2360,6 +2361,8 @@ static int max98090_runtime_resume(struct device *dev) regcache_cache_only(max98090->regmap, false); + max98090_reset(max98090); + regcache_sync(max98090->regmap); return 0; diff --git a/sound/soc/codecs/tlv320aic3x.c b/sound/soc/codecs/tlv320aic3x.c index 64ad84d8a306..11c8d1fe9222 100644 --- a/sound/soc/codecs/tlv320aic3x.c +++ b/sound/soc/codecs/tlv320aic3x.c @@ -164,7 +164,7 @@ static int snd_soc_dapm_put_volsw_aic3x(struct snd_kcontrol *kcontrol, mask <<= shift; val <<= shift; - change = snd_soc_test_bits(codec, val, mask, reg); + change = snd_soc_test_bits(codec, reg, mask, val); if (change) { update.kcontrol = kcontrol; update.reg = reg;