diff options
162 files changed, 2041 insertions, 1045 deletions
diff --git a/Documentation/stable_kernel_rules.txt b/Documentation/stable_kernel_rules.txt index e1f856b..22bf11b 100644 --- a/Documentation/stable_kernel_rules.txt +++ b/Documentation/stable_kernel_rules.txt @@ -1,4 +1,4 @@ -Everything you ever wanted to know about Linux 2.6 -stable releases. +Everything you ever wanted to know about Linux -stable releases. Rules on what kind of patches are accepted, and which ones are not, into the "-stable" tree: @@ -41,10 +41,10 @@ Procedure for submitting patches to the -stable tree: cherry-picked than this can be specified in the following format in the sign-off area: - Cc: <stable@vger.kernel.org> # .32.x: a1f84a3: sched: Check for idle - Cc: <stable@vger.kernel.org> # .32.x: 1b9508f: sched: Rate-limit newidle - Cc: <stable@vger.kernel.org> # .32.x: fd21073: sched: Fix affinity logic - Cc: <stable@vger.kernel.org> # .32.x + Cc: <stable@vger.kernel.org> # 3.3.x: a1f84a3: sched: Check for idle + Cc: <stable@vger.kernel.org> # 3.3.x: 1b9508f: sched: Rate-limit newidle + Cc: <stable@vger.kernel.org> # 3.3.x: fd21073: sched: Fix affinity logic + Cc: <stable@vger.kernel.org> # 3.3.x Signed-off-by: Ingo Molnar <mingo@elte.hu> The tag sequence has the meaning of: @@ -78,6 +78,15 @@ Review cycle: security kernel team, and not go through the normal review cycle. Contact the kernel security team for more details on this procedure. +Trees: + + - The queues of patches, for both completed versions and in progress + versions can be found at: + http://git.kernel.org/?p=linux/kernel/git/stable/stable-queue.git + - The finalized and tagged releases of all stable kernels can be found + in separate branches per version at: + http://git.kernel.org/?p=linux/kernel/git/stable/linux-stable.git + Review committee: diff --git a/Documentation/trace/postprocess/trace-vmscan-postprocess.pl b/Documentation/trace/postprocess/trace-vmscan-postprocess.pl index 12cecc8..4a37c47 100644 --- a/Documentation/trace/postprocess/trace-vmscan-postprocess.pl +++ b/Documentation/trace/postprocess/trace-vmscan-postprocess.pl @@ -379,10 +379,10 @@ EVENT_PROCESS: # To closer match vmstat scanning statistics, only count isolate_both # and isolate_inactive as scanning. isolate_active is rotation - # isolate_inactive == 0 - # isolate_active == 1 - # isolate_both == 2 - if ($isolate_mode != 1) { + # isolate_inactive == 1 + # isolate_active == 2 + # isolate_both == 3 + if ($isolate_mode != 2) { $perprocesspid{$process_pid}->{HIGH_NR_SCANNED} += $nr_scanned; } $perprocesspid{$process_pid}->{HIGH_NR_CONTIG_DIRTY} += $nr_contig_dirty; diff --git a/MAINTAINERS b/MAINTAINERS index b0209fb..74c8e4b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5247,7 +5247,7 @@ F: Documentation/blockdev/ramdisk.txt F: drivers/block/brd.c RANDOM NUMBER DRIVER -M: Matt Mackall <mpm@selenic.com> +M: Theodore Ts'o" <tytso@mit.edu> S: Maintained F: drivers/char/random.c @@ -1,6 +1,6 @@ VERSION = 3 PATCHLEVEL = 0 -SUBLEVEL = 38 +SUBLEVEL = 42 EXTRAVERSION = NAME = Sneaky Weasel diff --git a/arch/arm/configs/mxs_defconfig b/arch/arm/configs/mxs_defconfig index 2bf2243..166d6aa 100644 --- a/arch/arm/configs/mxs_defconfig +++ b/arch/arm/configs/mxs_defconfig @@ -29,7 +29,6 @@ CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_PREEMPT_VOLUNTARY=y CONFIG_AEABI=y -CONFIG_DEFAULT_MMAP_MIN_ADDR=65536 CONFIG_AUTO_ZRELADDR=y CONFIG_FPE_NWFPE=y CONFIG_NET=y diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index 1252a26..42dec04 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -215,7 +215,9 @@ static inline void vivt_flush_cache_mm(struct mm_struct *mm) static inline void vivt_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) + struct mm_struct *mm = vma->vm_mm; + + if (!mm || cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm))) __cpuc_flush_user_range(start & PAGE_MASK, PAGE_ALIGN(end), vma->vm_flags); } @@ -223,7 +225,9 @@ vivt_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned static inline void vivt_flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsigned long pfn) { - if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) { + struct mm_struct *mm = vma->vm_mm; + + if (!mm || cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm))) { unsigned long addr = user_addr & PAGE_MASK; __cpuc_flush_user_range(addr, addr + PAGE_SIZE, vma->vm_flags); } diff --git a/arch/arm/mach-omap2/opp.c b/arch/arm/mach-omap2/opp.c index ab8b35b..0627494 100644 --- a/arch/arm/mach-omap2/opp.c +++ b/arch/arm/mach-omap2/opp.c @@ -53,7 +53,7 @@ int __init omap_init_opp_table(struct omap_opp_def *opp_def, omap_table_init = 1; /* Lets now register with OPP library */ - for (i = 0; i < opp_def_size; i++) { + for (i = 0; i < opp_def_size; i++, opp_def++) { struct omap_hwmod *oh; struct device *dev; @@ -86,7 +86,6 @@ int __init omap_init_opp_table(struct omap_opp_def *opp_def, __func__, opp_def->freq, opp_def->hwmod_name, i, r); } - opp_def++; } return 0; diff --git a/arch/arm/mm/tlb-v7.S b/arch/arm/mm/tlb-v7.S index 53cd5b4..875634a 100644 --- a/arch/arm/mm/tlb-v7.S +++ b/arch/arm/mm/tlb-v7.S @@ -38,11 +38,19 @@ ENTRY(v7wbi_flush_user_tlb_range) dsb mov r0, r0, lsr #PAGE_SHIFT @ align address mov r1, r1, lsr #PAGE_SHIFT +#ifdef CONFIG_ARM_ERRATA_720789 + mov r3, #0 +#else asid r3, r3 @ mask ASID +#endif orr r0, r3, r0, lsl #PAGE_SHIFT @ Create initial MVA mov r1, r1, lsl #PAGE_SHIFT 1: +#ifdef CONFIG_ARM_ERRATA_720789 + ALT_SMP(mcr p15, 0, r0, c8, c3, 3) @ TLB invalidate U MVA all ASID (shareable) +#else ALT_SMP(mcr p15, 0, r0, c8, c3, 1) @ TLB invalidate U MVA (shareable) +#endif ALT_UP(mcr p15, 0, r0, c8, c7, 1) @ TLB invalidate U MVA add r0, r0, #PAGE_SZ @@ -70,7 +78,11 @@ ENTRY(v7wbi_flush_kern_tlb_range) mov r0, r0, lsl #PAGE_SHIFT mov r1, r1, lsl #PAGE_SHIFT 1: +#ifdef CONFIG_ARM_ERRATA_720789 + ALT_SMP(mcr p15, 0, r0, c8, c3, 3) @ TLB invalidate U MVA all ASID (shareable) +#else ALT_SMP(mcr p15, 0, r0, c8, c3, 1) @ TLB invalidate U MVA (shareable) +#endif ALT_UP(mcr p15, 0, r0, c8, c7, 1) @ TLB invalidate U MVA add r0, r0, #PAGE_SZ cmp r0, r1 diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h index 4468814..6fcc9a0 100644 --- a/arch/ia64/include/asm/atomic.h +++ b/arch/ia64/include/asm/atomic.h @@ -18,8 +18,8 @@ #include <asm/system.h> -#define ATOMIC_INIT(i) ((atomic_t) { (i) }) -#define ATOMIC64_INIT(i) ((atomic64_t) { (i) }) +#define ATOMIC_INIT(i) { (i) } +#define ATOMIC64_INIT(i) { (i) } #define atomic_read(v) (*(volatile int *)&(v)->counter) #define atomic64_read(v) (*(volatile long *)&(v)->counter) diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c index 782c3a35..3540c5e 100644 --- a/arch/ia64/kernel/irq_ia64.c +++ b/arch/ia64/kernel/irq_ia64.c @@ -23,7 +23,6 @@ #include <linux/ioport.h> #include <linux/kernel_stat.h> #include <linux/ptrace.h> -#include <linux/random.h> /* for rand_initialize_irq() */ #include <linux/signal.h> #include <linux/smp.h> #include <linux/threads.h> diff --git a/arch/m68k/include/asm/entry_mm.h b/arch/m68k/include/asm/entry_mm.h index 73b8c8f..bdace4b 100644 --- a/arch/m68k/include/asm/entry_mm.h +++ b/arch/m68k/include/asm/entry_mm.h @@ -35,8 +35,8 @@ /* the following macro is used when enabling interrupts */ #if defined(MACH_ATARI_ONLY) - /* block out HSYNC on the atari */ -#define ALLOWINT (~0x400) + /* block out HSYNC = ipl 2 on the atari */ +#define ALLOWINT (~0x500) #define MAX_NOINT_IPL 3 #else /* portable version */ diff --git a/arch/m68k/kernel/sys_m68k.c b/arch/m68k/kernel/sys_m68k.c index 8623f8d..9a5932e 100644 --- a/arch/m68k/kernel/sys_m68k.c +++ b/arch/m68k/kernel/sys_m68k.c @@ -479,9 +479,13 @@ sys_atomic_cmpxchg_32(unsigned long newval, int oldval, int d3, int d4, int d5, goto bad_access; } - mem_value = *mem; + /* + * No need to check for EFAULT; we know that the page is + * present and writable. + */ + __get_user(mem_value, mem); if (mem_value == oldval) - *mem = newval; + __put_user(newval, mem); pte_unmap_unlock(pte, ptl); up_read(&mm->mmap_sem); diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h index 97f8bf6..adda036 100644 --- a/arch/mips/include/asm/thread_info.h +++ b/arch/mips/include/asm/thread_info.h @@ -60,6 +60,8 @@ struct thread_info { register struct thread_info *__current_thread_info __asm__("$28"); #define current_thread_info() __current_thread_info +#endif /* !__ASSEMBLY__ */ + /* thread information allocation */ #if defined(CONFIG_PAGE_SIZE_4KB) && defined(CONFIG_32BIT) #define THREAD_SIZE_ORDER (1) @@ -97,8 +99,6 @@ register struct thread_info *__current_thread_info __asm__("$28"); #define free_thread_info(info) kfree(info) -#endif /* !__ASSEMBLY__ */ - #define PREEMPT_ACTIVE 0x10000000 /* diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S index a81176f..be281c6 100644 --- a/arch/mips/kernel/vmlinux.lds.S +++ b/arch/mips/kernel/vmlinux.lds.S @@ -1,5 +1,6 @@ #include <asm/asm-offsets.h> #include <asm/page.h> +#include <asm/thread_info.h> #include <asm-generic/vmlinux.lds.h> #undef mips @@ -73,7 +74,7 @@ SECTIONS .data : { /* Data */ . = . + DATAOFFSET; /* for CONFIG_MAPPED_KERNEL */ - INIT_TASK_DATA(PAGE_SIZE) + INIT_TASK_DATA(THREAD_SIZE) NOSAVE_DATA CACHELINE_ALIGNED_DATA(1 << CONFIG_MIPS_L1_CACHE_SHIFT) READ_MOSTLY_DATA(1 << CONFIG_MIPS_L1_CACHE_SHIFT) diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h index 1cf20bd..33a3580 100644 --- a/arch/powerpc/include/asm/cputime.h +++ b/arch/powerpc/include/asm/cputime.h @@ -126,11 +126,11 @@ static inline u64 cputime64_to_jiffies64(const cputime_t ct) /* * Convert cputime <-> microseconds */ -extern u64 __cputime_msec_factor; +extern u64 __cputime_usec_factor; static inline unsigned long cputime_to_usecs(const cputime_t ct) { - return mulhdu(ct, __cputime_msec_factor) * USEC_PER_MSEC; + return mulhdu(ct, __cputime_usec_factor); } static inline cputime_t usecs_to_cputime(const unsigned long us) @@ -143,7 +143,7 @@ static inline cputime_t usecs_to_cputime(const unsigned long us) sec = us / 1000000; if (ct) { ct *= tb_ticks_per_sec; - do_div(ct, 1000); + do_div(ct, 1000000); } if (sec) ct += (cputime_t) sec * tb_ticks_per_sec; diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index c5cae0d..764e99c 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -1000,7 +1000,8 @@ /* Macros for setting and retrieving special purpose registers */ #ifndef __ASSEMBLY__ #define mfmsr() ({unsigned long rval; \ - asm volatile("mfmsr %0" : "=r" (rval)); rval;}) + asm volatile("mfmsr %0" : "=r" (rval) : \ + : "memory"); rval;}) #ifdef CONFIG_PPC_BOOK3S_64 #define __mtmsrd(v, l) asm volatile("mtmsrd %0," __stringify(l) \ : : "r" (v) : "memory") diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index bf99cfa..6324008 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -245,9 +245,9 @@ __ftrace_make_nop(struct module *mod, /* * On PPC32 the trampoline looks like: - * 0x3d, 0x60, 0x00, 0x00 lis r11,sym@ha - * 0x39, 0x6b, 0x00, 0x00 addi r11,r11,sym@l - * 0x7d, 0x69, 0x03, 0xa6 mtctr r11 + * 0x3d, 0x80, 0x00, 0x00 lis r12,sym@ha + * 0x39, 0x8c, 0x00, 0x00 addi r12,r12,sym@l + * 0x7d, 0x89, 0x03, 0xa6 mtctr r12 * 0x4e, 0x80, 0x04, 0x20 bctr */ @@ -262,9 +262,9 @@ __ftrace_make_nop(struct module *mod, pr_devel(" %08x %08x ", jmp[0], jmp[1]); /* verify that this is what we expect it to be */ - if (((jmp[0] & 0xffff0000) != 0x3d600000) || - ((jmp[1] & 0xffff0000) != 0x396b0000) || - (jmp[2] != 0x7d6903a6) || + if (((jmp[0] & 0xffff0000) != 0x3d800000) || + ((jmp[1] & 0xffff0000) != 0x398c0000) || + (jmp[2] != 0x7d8903a6) || (jmp[3] != 0x4e800420)) { printk(KERN_ERR "Not a trampoline\n"); return -EINVAL; diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 2de304a..1becd7b 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -168,13 +168,13 @@ EXPORT_SYMBOL_GPL(ppc_tb_freq); #ifdef CONFIG_VIRT_CPU_ACCOUNTING /* * Factors for converting from cputime_t (timebase ticks) to - * jiffies, milliseconds, seconds, and clock_t (1/USER_HZ seconds). + * jiffies, microseconds, seconds, and clock_t (1/USER_HZ seconds). * These are all stored as 0.64 fixed-point binary fractions. */ u64 __cputime_jiffies_factor; EXPORT_SYMBOL(__cputime_jiffies_factor); -u64 __cputime_msec_factor; -EXPORT_SYMBOL(__cputime_msec_factor); +u64 __cputime_usec_factor; +EXPORT_SYMBOL(__cputime_usec_factor); u64 __cputime_sec_factor; EXPORT_SYMBOL(__cputime_sec_factor); u64 __cputime_clockt_factor; @@ -192,8 +192,8 @@ static void calc_cputime_factors(void) div128_by_32(HZ, 0, tb_ticks_per_sec, &res); __cputime_jiffies_factor = res.result_low; - div128_by_32(1000, 0, tb_ticks_per_sec, &res); - __cputime_msec_factor = res.result_low; + div128_by_32(1000000, 0, tb_ticks_per_sec, &res); + __cputime_usec_factor = res.result_low; div128_by_32(1, 0, tb_ticks_per_sec, &res); __cputime_sec_factor = res.result_low; div128_by_32(USER_HZ, 0, tb_ticks_per_sec, &res); diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 53acaa8..f98af03 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -631,7 +631,6 @@ asmlinkage unsigned long old32_mmap(struct mmap_arg_struct_emu31 __user *arg) return -EFAULT; if (a.offset & ~PAGE_MASK) return -EINVAL; - a.addr = (unsigned long) compat_ptr(a.addr); return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset >> PAGE_SHIFT); } @@ -642,7 +641,6 @@ asmlinkage long sys32_mmap2(struct mmap_arg_struct_emu31 __user *arg) if (copy_from_user(&a, arg, sizeof(a))) return -EFAULT; - a.addr = (unsigned long) compat_ptr(a.addr); return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset); } diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 5d9c61d..e5f7248 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -99,7 +99,6 @@ struct cpuinfo_x86 { u16 apicid; u16 initial_apicid; u16 x86_clflush_size; -#ifdef CONFIG_SMP /* number of cores as seen by the OS: */ u16 booted_cores; /* Physical processor id: */ @@ -110,7 +109,6 @@ struct cpuinfo_x86 { u8 compute_unit_id; /* Index into per_cpu list: */ u16 cpu_index; -#endif } __attribute__((__aligned__(SMP_CACHE_BYTES))); #define X86_VENDOR_INTEL 0 diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index a81f2d5..dfabea4 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -220,7 +220,7 @@ void __init arch_init_ideal_nops(void) ideal_nops = intel_nops; #endif } - + break; default: #ifdef CONFIG_X86_64 ideal_nops = k8_nops; diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index bae1efe..be16854 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -154,16 +154,14 @@ int amd_get_subcaches(int cpu) { struct pci_dev *link = node_to_amd_nb(amd_get_nb_id(cpu))->link; unsigned int mask; - int cuid = 0; + int cuid; if (!amd_nb_has_feature(AMD_NB_L3_PARTITIONING)) return 0; pci_read_config_dword(link, 0x1d4, &mask); -#ifdef CONFIG_SMP cuid = cpu_data(cpu).compute_unit_id; -#endif return (mask >> (4 * cuid)) & 0xf; } @@ -172,7 +170,7 @@ int amd_set_subcaches(int cpu, int mask) static unsigned int reset, ban; struct amd_northbridge *nb = node_to_amd_nb(amd_get_nb_id(cpu)); unsigned int reg; - int cuid = 0; + int cuid; if (!amd_nb_has_feature(AMD_NB_L3_PARTITIONING) || mask > 0xf) return -EINVAL; @@ -190,9 +188,7 @@ int amd_set_subcaches(int cpu, int mask) pci_write_config_dword(nb->misc, 0x1b8, reg & ~0x180000); } -#ifdef CONFIG_SMP cuid = cpu_data(cpu).compute_unit_id; -#endif mask <<= 4 * cuid; mask |= (0xf ^ (1 << cuid)) << 26; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index b13ed39..8115040 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -146,7 +146,6 @@ static void __cpuinit init_amd_k6(struct cpuinfo_x86 *c) static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c) { -#ifdef CONFIG_SMP /* calling is from identify_secondary_cpu() ? */ if (!c->cpu_index) return; @@ -190,7 +189,6 @@ static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c) valid_k7: ; -#endif } static void __cpuinit init_amd_k7(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 22a073d..0cb2883 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -675,9 +675,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) if (this_cpu->c_early_init) this_cpu->c_early_init(c); -#ifdef CONFIG_SMP c->cpu_index = 0; -#endif filter_cpuid_features(c, false); setup_smep(c); @@ -760,10 +758,7 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 *c) c->apicid = c->initial_apicid; # endif #endif - -#ifdef CONFIG_X86_HT c->phys_proc_id = c->initial_apicid; -#endif } setup_smep(c); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index ed6086e..e0dc000 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -179,7 +179,6 @@ static void __cpuinit trap_init_f00f_bug(void) static void __cpuinit intel_smp_check(struct cpuinfo_x86 *c) { -#ifdef CONFIG_SMP /* calling is from identify_secondary_cpu() ? */ if (!c->cpu_index) return; @@ -196,7 +195,6 @@ static void __cpuinit intel_smp_check(struct cpuinfo_x86 *c) WARN_ONCE(1, "WARNING: SMP operation may be unreliable" "with B stepping processors.\n"); } -#endif } static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index ff1ae9b..942bda2 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -122,9 +122,7 @@ void mce_setup(struct mce *m) m->time = get_seconds(); m->cpuvendor = boot_cpu_data.x86_vendor; m->cpuid = cpuid_eax(1); -#ifdef CONFIG_SMP m->socketid = cpu_data(m->extcpu).phys_proc_id; -#endif m->apicid = cpu_data(m->extcpu).initial_apicid; rdmsrl(MSR_IA32_MCG_CAP, m->mcgcap); } diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index dc4fb77..b97aa72 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -65,11 +65,9 @@ struct threshold_bank { }; static DEFINE_PER_CPU(struct threshold_bank * [NR_BANKS], threshold_banks); -#ifdef CONFIG_SMP static unsigned char shared_bank[NR_BANKS] = { 0, 0, 0, 0, 1 }; -#endif static DEFINE_PER_CPU(unsigned char, bank_map); /* see which banks are on */ @@ -227,10 +225,9 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) if (!block) per_cpu(bank_map, cpu) |= (1 << bank); -#ifdef CONFIG_SMP + if (shared_bank[bank] && c->cpu_core_id) break; -#endif memset(&b, 0, sizeof(b)); b.cpu = cpu; diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 62ac8cb..72c365a 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -64,12 +64,10 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c) static int show_cpuinfo(struct seq_file *m, void *v) { struct cpuinfo_x86 *c = v; - unsigned int cpu = 0; + unsigned int cpu; int i; -#ifdef CONFIG_SMP cpu = c->cpu_index; -#endif seq_printf(m, "processor\t: %u\n" "vendor_id\t: %s\n" "cpu family\t: %d\n" diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index f924280..c4e2465 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -297,20 +297,31 @@ static ssize_t reload_store(struct sys_device *dev, const char *buf, size_t size) { unsigned long val; - int cpu = dev->id; - int ret = 0; - char *end; + int cpu; + ssize_t ret = 0, tmp_ret; - val = simple_strtoul(buf, &end, 0); - if (end == buf) + /* allow reload only from the BSP */ + if (boot_cpu_data.cpu_index != dev->id) return -EINVAL; - if (val == 1) { - get_online_cpus(); - if (cpu_online(cpu)) - ret = reload_for_cpu(cpu); - put_online_cpus(); + ret = kstrtoul(buf, 0, &val); + if (ret) + return ret; + + if (val != 1) + return size; + + get_online_cpus(); + for_each_online_cpu(cpu) { + tmp_ret = reload_for_cpu(cpu); + if (tmp_ret != 0) + pr_warn("Error reloading microcode on CPU %d\n", cpu); + + /* save retval of the first encountered reload error */ + if (!ret) + ret = tmp_ret; } + put_online_cpus(); if (!ret) ret = size; diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 58efeb9..2f7847d 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -683,6 +683,7 @@ int m2p_add_override(unsigned long mfn, struct page *page, bool clear_pte) unsigned long uninitialized_var(address); unsigned level; pte_t *ptep = NULL; + int ret = 0; pfn = page_to_pfn(page); if (!PageHighMem(page)) { @@ -706,6 +707,24 @@ int m2p_add_override(unsigned long mfn, struct page *page, bool clear_pte) list_add(&page->lru, &m2p_overrides[mfn_hash(mfn)]); spin_unlock_irqrestore(&m2p_override_lock, flags); + /* p2m(m2p(mfn)) == mfn: the mfn is already present somewhere in + * this domain. Set the FOREIGN_FRAME_BIT in the p2m for the other + * pfn so that the following mfn_to_pfn(mfn) calls will return the + * pfn from the m2p_override (the backend pfn) instead. + * We need to do this because the pages shared by the frontend + * (xen-blkfront) can be already locked (lock_page, called by + * do_read_cache_page); when the userspace backend tries to use them + * with direct_IO, mfn_to_pfn returns the pfn of the frontend, so + * do_blockdev_direct_IO is going to try to lock the same pages + * again resulting in a deadlock. + * As a side effect get_user_pages_fast might not be safe on the + * frontend pages while they are being shared with the backend, + * because mfn_to_pfn (that ends up being called by GUPF) will + * return the backend pfn rather than the frontend pfn. */ + ret = __get_user(pfn, &machine_to_phys_mapping[mfn]); + if (ret == 0 && get_phys_to_machine(pfn) == mfn) + set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)); + return 0; } EXPORT_SYMBOL_GPL(m2p_add_override); @@ -717,6 +736,7 @@ int m2p_remove_override(struct page *page, bool clear_pte) unsigned long uninitialized_var(address); unsigned level; pte_t *ptep = NULL; + int ret = 0; pfn = page_to_pfn(page); mfn = get_phys_to_machine(pfn); @@ -743,6 +763,22 @@ int m2p_remove_override(struct page *page, bool clear_pte) /* No tlb flush necessary because the caller already * left the pte unmapped. */ + /* p2m(m2p(mfn)) == FOREIGN_FRAME(mfn): the mfn is already present + * somewhere in this domain, even before being added to the + * m2p_override (see comment above in m2p_add_override). + * If there are no other entries in the m2p_override corresponding + * to this mfn, then remove the FOREIGN_FRAME_BIT from the p2m for + * the original pfn (the one shared by the frontend): the backend + * cannot do any IO on this page anymore because it has been + * unshared. Removing the FOREIGN_FRAME_BIT from the p2m entry of + * the original pfn causes mfn_to_pfn(mfn) to return the frontend + * pfn again. */ + mfn &= ~FOREIGN_FRAME_BIT; + ret = __get_user(pfn, &machine_to_phys_mapping[mfn]); + if (ret == 0 && get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) && + m2p_find_override(mfn) == NULL) + set_phys_to_machine(pfn, mfn); + return 0; } EXPORT_SYMBOL_GPL(m2p_remove_override); diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c index 58c3f74..9582050 100644 --- a/drivers/acpi/ac.c +++ b/drivers/acpi/ac.c @@ -292,7 +292,9 @@ static int acpi_ac_add(struct acpi_device *device) ac->charger.properties = ac_props; ac->charger.num_properties = ARRAY_SIZE(ac_props); ac->charger.get_property = get_ac_property; - power_supply_register(&ac->device->dev, &ac->charger); + result = power_supply_register(&ac->device->dev, &ac->charger); + if (result) + goto end; printk(KERN_INFO PREFIX "%s [%s] (%s)\n", acpi_device_name(device), acpi_device_bid(device), diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 45d7c8f..5fb6aae 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -224,13 +224,48 @@ int memory_isolate_notify(unsigned long val, void *v) } /* + * The probe routines leave the pages reserved, just as the bootmem code does. + * Make sure they're still that way. + */ +static bool pages_correctly_reserved(unsigned long start_pfn, + unsigned long nr_pages) +{ + int i, j; + struct page *page; + unsigned long pfn = start_pfn; + + /* + * memmap between sections is not contiguous except with + * SPARSEMEM_VMEMMAP. We lookup the page once per section + * and assume memmap is contiguous within each section + */ + for (i = 0; i < sections_per_block; i++, pfn += PAGES_PER_SECTION) { + if (WARN_ON_ONCE(!pfn_valid(pfn))) + return false; + page = pfn_to_page(pfn); + + for (j = 0; j < PAGES_PER_SECTION; j++) { + if (PageReserved(page + j)) + continue; + + printk(KERN_WARNING "section number %ld page number %d " + "not reserved, was it already online?\n", + pfn_to_section_nr(pfn), j); + + return false; + } + } + + return true; +} + +/* * MEMORY_HOTPLUG depends on SPARSEMEM in mm/Kconfig, so it is * OK to have direct references to sparsemem variables in here. */ static int memory_block_action(unsigned long phys_index, unsigned long action) { - int i; unsigned long start_pfn, start_paddr; unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block; struct page *first_page; @@ -238,26 +273,13 @@ memory_block_action(unsigned long phys_index, unsigned long action) first_page = pfn_to_page(phys_index << PFN_SECTION_SHIFT); - /* - * The probe routines leave the pages reserved, just - * as the bootmem code does. Make sure they're still - * that way. - */ - if (action == MEM_ONLINE) { - for (i = 0; i < nr_pages; i++) { - if (PageReserved(first_page+i)) - continue; - - printk(KERN_WARNING "section number %ld page number %d " - "not reserved, was it already online?\n", - phys_index, i); - return -EBUSY; - } - } - switch (action) { case MEM_ONLINE: start_pfn = page_to_pfn(first_page); + + if (!pages_correctly_reserved(start_pfn, nr_pages)) + return -EBUSY; + ret = online_pages(start_pfn, nr_pages); break; case MEM_OFFLINE: diff --git a/drivers/char/mspec.c b/drivers/char/mspec.c index 25d139c..579051c 100644 --- a/drivers/char/mspec.c +++ b/drivers/char/mspec.c @@ -284,7 +284,7 @@ mspec_mmap(struct file *file, struct vm_area_struct *vma, vdata->flags = flags; vdata->type = type; spin_lock_init(&vdata->lock); - vdata->refcnt = ATOMIC_INIT(1); + atomic_set(&vdata->refcnt, 1); vma->vm_private_data = vdata; vma->vm_flags |= (VM_IO | VM_RESERVED | VM_PFNMAP | VM_DONTEXPAND); diff --git a/drivers/char/random.c b/drivers/char/random.c index c35a785..fceac95 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -125,21 +125,26 @@ * The current exported interfaces for gathering environmental noise * from the devices are: * + * void add_device_randomness(const void *buf, unsigned int size); * void add_input_randomness(unsigned int type, unsigned int code, * unsigned int value); - * void add_interrupt_randomness(int irq); + * void add_interrupt_randomness(int irq, int irq_flags); * void add_disk_randomness(struct gendisk *disk); * + * add_device_randomness() is for adding data to the random pool that + * is likely to differ between two devices (or possibly even per boot). + * This would be things like MAC addresses or serial numbers, or the + * read-out of the RTC. This does *not* add any actual entropy to the + * pool, but it initializes the pool to different values for devices + * that might otherwise be identical and have very little entropy + * available to them (particularly common in the embedded world). + * * add_input_randomness() uses the input layer interrupt timing, as well as * the event type information from the hardware. * - * add_interrupt_randomness() uses the inter-interrupt timing as random - * inputs to the entropy pool. Note that not all interrupts are good - * sources of randomness! For example, the timer interrupts is not a - * good choice, because the periodicity of the interrupts is too - * regular, and hence predictable to an attacker. Network Interface - * Controller interrupts are a better measure, since the timing of the - * NIC interrupts are more unpredictable. + * add_interrupt_randomness() uses the interrupt timing as random + * inputs to the entropy pool. Using the cycle counters and the irq source + * as inputs, it feeds the randomness roughly once a second. * * add_disk_randomness() uses what amounts to the seek time of block * layer request events, on a per-disk_devt basis, as input to the @@ -248,6 +253,8 @@ #include <linux/percpu.h> #include <linux/cryptohash.h> #include <linux/fips.h> +#include <linux/ptrace.h> +#include <linux/kmemcheck.h> #ifdef CONFIG_GENERIC_HARDIRQS # include <linux/irq.h> @@ -256,8 +263,12 @@ #include <asm/processor.h> #include <asm/uaccess.h> #include <asm/irq.h> +#include <asm/irq_regs.h> #include <asm/io.h> +#define CREATE_TRACE_POINTS +#include <trace/events/random.h> + /* * Configuration information */ @@ -266,6 +277,8 @@ #define SEC_XFER_SIZE 512 #define EXTRACT_SIZE 10 +#define LONGS(x) (((x) + sizeof(unsigned long) - 1)/sizeof(unsigned long)) + /* * The minimum number of bits of entropy before we wake up a read on * /dev/random. Should be enough to do a significant reseed. @@ -420,8 +433,10 @@ struct entropy_store { /* read-write data: */ spinlock_t lock; unsigned add_ptr; + unsigned input_rotate; int entropy_count; - int input_rotate; + int entropy_total; + unsigned int initialized:1; __u8 last_data[EXTRACT_SIZE]; }; @@ -454,6 +469,10 @@ static struct entropy_store nonblocking_pool = { .pool = nonblocking_pool_data }; +static __u32 const twist_table[8] = { + 0x00000000, 0x3b6e20c8, 0x76dc4190, 0x4db26158, + 0xedb88320, 0xd6d6a3e8, 0x9b64c2b0, 0xa00ae278 }; + /* * This function adds bytes into the entropy "pool". It does not * update the entropy estimate. The caller should call @@ -464,29 +483,24 @@ static struct entropy_store nonblocking_pool = { * it's cheap to do so and helps slightly in the expected case where * the entropy is concentrated in the low-order bits. */ -static void mix_pool_bytes_extract(struct entropy_store *r, const void *in, - int nbytes, __u8 out[64]) +static void _mix_pool_bytes(struct entropy_store *r, const void *in, + int nbytes, __u8 out[64]) { - static __u32 const twist_table[8] = { - 0x00000000, 0x3b6e20c8, 0x76dc4190, 0x4db26158, - 0xedb88320, 0xd6d6a3e8, 0x9b64c2b0, 0xa00ae278 }; unsigned long i, j, tap1, tap2, tap3, tap4, tap5; int input_rotate; int wordmask = r->poolinfo->poolwords - 1; const char *bytes = in; __u32 w; - unsigned long flags; - /* Taps are constant, so we can load them without holding r->lock. */ tap1 = r->poolinfo->tap1; tap2 = r->poolinfo->tap2; tap3 = r->poolinfo->tap3; tap4 = r->poolinfo->tap4; tap5 = r->poolinfo->tap5; - spin_lock_irqsave(&r->lock, flags); - input_rotate = r->input_rotate; - i = r->add_ptr; + smp_rmb(); + input_rotate = ACCESS_ONCE(r->input_rotate); + i = ACCESS_ONCE(r->add_ptr); /* mix one byte at a time to simplify size handling and churn faster */ while (nbytes--) { @@ -513,19 +527,61 @@ static void mix_pool_bytes_extract(struct entropy_store *r, const void *in, input_rotate += i ? 7 : 14; } - r->input_rotate = input_rotate; - r->add_ptr = i; + ACCESS_ONCE(r->input_rotate) = input_rotate; + ACCESS_ONCE(r->add_ptr) = i; + smp_wmb(); if (out) for (j = 0; j < 16; j++) ((__u32 *)out)[j] = r->pool[(i - j) & wordmask]; +} +static void __mix_pool_bytes(struct entropy_store *r, const void *in, + int nbytes, __u8 out[64]) +{ + trace_mix_pool_bytes_nolock(r->name, nbytes, _RET_IP_); + _mix_pool_bytes(r, in, nbytes, out); +} + +static void mix_pool_bytes(struct entropy_store *r, const void *in, + int nbytes, __u8 out[64]) +{ + unsigned long flags; + + trace_mix_pool_bytes(r->name, nbytes, _RET_IP_); + spin_lock_irqsave(&r->lock, flags); + _mix_pool_bytes(r, in, nbytes, out); spin_unlock_irqrestore(&r->lock, flags); } -static void mix_pool_bytes(struct entropy_store *r, const void *in, int bytes) +struct fast_pool { + __u32 pool[4]; + unsigned long last; + unsigned short count; + unsigned char rotate; + unsigned char last_timer_intr; +}; + +/* + * This is a fast mixing routine used by the interrupt randomness + * collector. It's hardcoded for an 128 bit pool and assumes that any + * locks that might be needed are taken by the caller. + */ +static void fast_mix(struct fast_pool *f, const void *in, int nbytes) { - mix_pool_bytes_extract(r, in, bytes, NULL); + const char *bytes = in; + __u32 w; + unsigned i = f->count; + unsigned input_rotate = f->rotate; + + while (nbytes--) { + w = rol32(*bytes++, input_rotate & 31) ^ f->pool[i & 3] ^ + f->pool[(i + 1) & 3]; + f->pool[i & 3] = (w >> 3) ^ twist_table[w & 7]; + input_rotate += (i++ & 3) ? 7 : 14; + } + f->count = i; + f->rotate = input_rotate; } /* @@ -533,30 +589,38 @@ static void mix_pool_bytes(struct entropy_store *r, const void *in, int bytes) */ static void credit_entropy_bits(struct entropy_store *r, int nbits) { - unsigned long flags; - int entropy_count; + int entropy_count, orig; if (!nbits) return; - spin_lock_irqsave(&r->lock, flags); - DEBUG_ENT("added %d entropy credits to %s\n", nbits, r->name); - entropy_count = r->entropy_count; +retry: + entropy_count = orig = ACCESS_ONCE(r->entropy_count); entropy_count += nbits; + if (entropy_count < 0) { DEBUG_ENT("negative entropy/overflow\n"); entropy_count = 0; } else if (entropy_count > r->poolinfo->POOLBITS) entropy_count = r->poolinfo->POOLBITS; - r->entropy_count = entropy_count; + if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig) + goto retry; + + if (!r->initialized && nbits > 0) { + r->entropy_total += nbits; + if (r->entropy_total > 128) + r->initialized = 1; + } + + trace_credit_entropy_bits(r->name, nbits, entropy_count, + r->entropy_total, _RET_IP_); /* should we wake readers? */ if (r == &input_pool && entropy_count >= random_read_wakeup_thresh) { wake_up_interruptible(&random_read_wait); kill_fasync(&fasync, SIGIO, POLL_IN); } - spin_unlock_irqrestore(&r->lock, flags); } /********************************************************************* @@ -572,42 +636,24 @@ struct timer_rand_state { unsigned dont_count_entropy:1; }; -#ifndef CONFIG_GENERIC_HARDIRQS - -static struct timer_rand_state *irq_timer_state[NR_IRQS]; - -static struct timer_rand_state *get_timer_rand_state(unsigned int irq) -{ - return irq_timer_state[irq]; -} - -static void set_timer_rand_state(unsigned int irq, - struct timer_rand_state *state) -{ - irq_timer_state[irq] = state; -} - -#else - -static struct timer_rand_state *get_timer_rand_state(unsigned int irq) -{ - struct irq_desc *desc; - - desc = irq_to_desc(irq); - - return desc->timer_rand_state; -} - -static void set_timer_rand_state(unsigned int irq, - struct timer_rand_state *state) +/* + * Add device- or boot-specific data to the input and nonblocking + * pools to help initialize them to unique values. + * + * None of this adds any entropy, it is meant to avoid the + * problem of the nonblocking pool having similar initial state + * across largely identical devices. + */ +void add_device_randomness(const void *buf, unsigned int size) { - struct irq_desc *desc; - - desc = irq_to_desc(irq); + unsigned long time = get_cycles() ^ jiffies; - desc->timer_rand_state = state; + mix_pool_bytes(&input_pool, buf, size, NULL); + mix_pool_bytes(&input_pool, &time, sizeof(time), NULL); + mix_pool_bytes(&nonblocking_pool, buf, size, NULL); + mix_pool_bytes(&nonblocking_pool, &time, sizeof(time), NULL); } -#endif +EXPORT_SYMBOL(add_device_randomness); static struct timer_rand_state input_timer_state; @@ -624,8 +670,8 @@ static struct timer_rand_state input_timer_state; static void add_timer_randomness(struct timer_rand_state *state, unsigned num) { struct { - cycles_t cycles; long jiffies; + unsigned cycles; unsigned num; } sample; long delta, delta2, delta3; @@ -639,7 +685,7 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num) sample.jiffies = jiffies; sample.cycles = get_cycles(); sample.num = num; - mix_pool_bytes(&input_pool, &sample, sizeof(sample)); + mix_pool_bytes(&input_pool, &sample, sizeof(sample), NULL); /* * Calculate number of bits of randomness we probably added. @@ -696,17 +742,48 @@ void add_input_randomness(unsigned int type, unsigned int code, } EXPORT_SYMBOL_GPL(add_input_randomness); -void add_interrupt_randomness(int irq) +static DEFINE_PER_CPU(struct fast_pool, irq_randomness); + +void add_interrupt_randomness(int irq, int irq_flags) { - struct timer_rand_state *state; + struct entropy_store *r; + struct fast_pool *fast_pool = &__get_cpu_var(irq_randomness); + struct pt_regs *regs = get_irq_regs(); + unsigned long now = jiffies; + __u32 input[4], cycles = get_cycles(); + + input[0] = cycles ^ jiffies; + input[1] = irq; + if (regs) { + __u64 ip = instruction_pointer(regs); + input[2] = ip; + input[3] = ip >> 32; + } - state = get_timer_rand_state(irq); + fast_mix(fast_pool, input, sizeof(input)); - if (state == NULL) + if ((fast_pool->count & 1023) && + !time_after(now, fast_pool->last + HZ)) return; - DEBUG_ENT("irq event %d\n", irq); - add_timer_randomness(state, 0x100 + irq); + fast_pool->last = now; + + r = nonblocking_pool.initialized ? &input_pool : &nonblocking_pool; + __mix_pool_bytes(r, &fast_pool->pool, sizeof(fast_pool->pool), NULL); + /* + * If we don't have a valid cycle counter, and we see + * back-to-back timer interrupts, then skip giving credit for + * any entropy. + */ + if (cycles == 0) { + if (irq_flags & __IRQF_TIMER) { + if (fast_pool->last_timer_intr) + return; + fast_pool->last_timer_intr = 1; + } else + fast_pool->last_timer_intr = 0; + } + credit_entropy_bits(r, 1); } #ifdef CONFIG_BLOCK @@ -738,7 +815,7 @@ static ssize_t extract_entropy(struct entropy_store *r, void *buf, */ static void xfer_secondary_pool(struct entropy_store *r, size_t nbytes) { - __u32 tmp[OUTPUT_POOL_WORDS]; + __u32 tmp[OUTPUT_POOL_WORDS]; if (r->pull && r->entropy_count < nbytes * 8 && r->entropy_count < r->poolinfo->POOLBITS) { @@ -757,7 +834,7 @@ static void xfer_secondary_pool(struct entropy_store *r, size_t nbytes) bytes = extract_entropy(r->pull, tmp, bytes, random_read_wakeup_thresh / 8, rsvd); - mix_pool_bytes(r, tmp, bytes); + mix_pool_bytes(r, tmp, bytes, NULL); credit_entropy_bits(r, bytes*8); } } @@ -816,13 +893,19 @@ static size_t account(struct entropy_store *r, size_t nbytes, int min, static void extract_buf(struct entropy_store *r, __u8 *out) { int i; - __u32 hash[5], workspace[SHA_WORKSPACE_WORDS]; + union { + __u32 w[5]; + unsigned long l[LONGS(EXTRACT_SIZE)]; + } hash; + __u32 workspace[SHA_WORKSPACE_WORDS]; __u8 extract[64]; + unsigned long flags; /* Generate a hash across the pool, 16 words (512 bits) at a time */ - sha_init(hash); + sha_init(hash.w); + spin_lock_irqsave(&r->lock, flags); for (i = 0; i < r->poolinfo->poolwords; i += 16) - sha_transform(hash, (__u8 *)(r->pool + i), workspace); + sha_transform(hash.w, (__u8 *)(r->pool + i), workspace); /* * We mix the hash back into the pool to prevent backtracking @@ -833,13 +916,14 @@ static void extract_buf(struct entropy_store *r, __u8 *out) * brute-forcing the feedback as hard as brute-forcing the * hash. */ - mix_pool_bytes_extract(r, hash, sizeof(hash), extract); + __mix_pool_bytes(r, hash.w, sizeof(hash.w), extract); + spin_unlock_irqrestore(&r->lock, flags); /* * To avoid duplicates, we atomically extract a portion of the * pool while mixing, and hash one final time. */ - sha_transform(hash, extract, workspace); + sha_transform(hash.w, extract, workspace); memset(extract, 0, sizeof(extract)); memset(workspace, 0, sizeof(workspace)); @@ -848,20 +932,32 @@ static void extract_buf(struct entropy_store *r, __u8 *out) * pattern, we fold it in half. Thus, we always feed back * twice as much data as we output. */ - hash[0] ^= hash[3]; - hash[1] ^= hash[4]; - hash[2] ^= rol32(hash[2], 16); - memcpy(out, hash, EXTRACT_SIZE); - memset(hash, 0, sizeof(hash)); + hash.w[0] ^= hash.w[3]; + hash.w[1] ^= hash.w[4]; + hash.w[2] ^= rol32(hash.w[2], 16); + + /* + * If we have a architectural hardware random number + * generator, mix that in, too. + */ + for (i = 0; i < LONGS(EXTRACT_SIZE); i++) { + unsigned long v; + if (!arch_get_random_long(&v)) + break; + hash.l[i] ^= v; + } + + memcpy(out, &hash, EXTRACT_SIZE); + memset(&hash, 0, sizeof(hash)); } static ssize_t extract_entropy(struct entropy_store *r, void *buf, - size_t nbytes, int min, int reserved) + size_t nbytes, int min, int reserved) { ssize_t ret = 0, i; __u8 tmp[EXTRACT_SIZE]; - unsigned long flags; + trace_extract_entropy(r->name, nbytes, r->entropy_count, _RET_IP_); xfer_secondary_pool(r, nbytes); nbytes = account(r, nbytes, min, reserved); @@ -869,6 +965,8 @@ static ssize_t extract_entropy(struct entropy_store *r, void *buf, extract_buf(r, tmp); if (fips_enabled) { + unsigned long flags; + spin_lock_irqsave(&r->lock, flags); if (!memcmp(tmp, r->last_data, EXTRACT_SIZE)) panic("Hardware RNG duplicated output!\n"); @@ -894,6 +992,7 @@ static ssize_t extract_entropy_user(struct entropy_store *r, void __user *buf, ssize_t ret = 0, i; __u8 tmp[EXTRACT_SIZE]; + trace_extract_entropy_user(r->name, nbytes, r->entropy_count, _RET_IP_); xfer_secondary_pool(r, nbytes); nbytes = account(r, nbytes, 0, 0); @@ -927,8 +1026,9 @@ static ssize_t extract_entropy_user(struct entropy_store *r, void __user *buf, /* * This function is the exported kernel interface. It returns some - * number of good random numbers, suitable for seeding TCP sequence - * numbers, etc. + * number of good random numbers, suitable for key generation, seeding + * TCP sequence numbers, etc. It does not use the hw random number + * generator, if available; use get_random_bytes_arch() for that. */ void get_random_bytes(void *buf, int nbytes) { @@ -937,6 +1037,39 @@ void get_random_bytes(void *buf, int nbytes) EXPORT_SYMBOL(get_random_bytes); /* + * This function will use the architecture-specific hardware random + * number generator if it is available. The arch-specific hw RNG will + * almost certainly be faster than what we can do in software, but it + * is impossible to verify that it is implemented securely (as + * opposed, to, say, the AES encryption of a sequence number using a + * key known by the NSA). So it's useful if we need the speed, but + * only if we're willing to trust the hardware manufacturer not to + * have put in a back door. + */ +void get_random_bytes_arch(void *buf, int nbytes) +{ + char *p = buf; + + trace_get_random_bytes(nbytes, _RET_IP_); + while (nbytes) { + unsigned long v; + int chunk = min(nbytes, (int)sizeof(unsigned long)); + + if (!arch_get_random_long(&v)) + break; + + memcpy(p, &v, chunk); + p += chunk; + nbytes -= chunk; + } + + if (nbytes) + extract_entropy(&nonblocking_pool, p, nbytes, 0, 0); +} +EXPORT_SYMBOL(get_random_bytes_arch); + + +/* * init_std_data - initialize pool with system data * * @r: pool to initialize @@ -947,18 +1080,31 @@ EXPORT_SYMBOL(get_random_bytes); */ static void init_std_data(struct entropy_store *r) { - ktime_t now; - unsigned long flags; + int i; + ktime_t now = ktime_get_real(); + unsigned long rv; - spin_lock_irqsave(&r->lock, flags); r->entropy_count = 0; - spin_unlock_irqrestore(&r->lock, flags); - - now = ktime_get_real(); - mix_pool_bytes(r, &now, sizeof(now)); - mix_pool_bytes(r, utsname(), sizeof(*(utsname()))); + r->entropy_total = 0; + mix_pool_bytes(r, &now, sizeof(now), NULL); + for (i = r->poolinfo->POOLBYTES; i > 0; i -= sizeof(rv)) { + if (!arch_get_random_long(&rv)) + break; + mix_pool_bytes(r, &rv, sizeof(rv), NULL); + } + mix_pool_bytes(r, utsname(), sizeof(*(utsname())), NULL); } +/* + * Note that setup_arch() may call add_device_randomness() + * long before we get here. This allows seeding of the pools + * with some platform dependent data very early in the boot + * process. But it limits our options here. We must use + * statically allocated structures that already have all + * initializations complete at compile time. We should also + * take care not to overwrite the precious per platform data + * we were given. + */ static int rand_initialize(void) { init_std_data(&input_pool); @@ -968,24 +1114,6 @@ static int rand_initialize(void) } module_init(rand_initialize); -void rand_initialize_irq(int irq) -{ - struct timer_rand_state *state; - - state = get_timer_rand_state(irq); - - if (state) - return; - - /* - * If kzalloc returns null, we just won't use that entropy - * source. - */ - state = kzalloc(sizeof(struct timer_rand_state), GFP_KERNEL); - if (state) - set_timer_rand_state(irq, state); -} - #ifdef CONFIG_BLOCK void rand_initialize_disk(struct gendisk *disk) { @@ -1093,7 +1221,7 @@ write_pool(struct entropy_store *r, const char __user *buffer, size_t count) count -= bytes; p += bytes; - mix_pool_bytes(r, buf, bytes); + mix_pool_bytes(r, buf, bytes, NULL); cond_resched(); } @@ -1236,10 +1364,15 @@ static int proc_do_uuid(ctl_table *table, int write, uuid = table->data; if (!uuid) { uuid = tmp_uuid; - uuid[8] = 0; - } - if (uuid[8] == 0) generate_random_uuid(uuid); + } else { + static DEFINE_SPINLOCK(bootid_spinlock); + + spin_lock(&bootid_spinlock); + if (!uuid[8]) + generate_random_uuid(uuid); + spin_unlock(&bootid_spinlock); + } sprintf(buf, "%pU", uuid); @@ -1318,9 +1451,14 @@ late_initcall(random_int_secret_init); DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash); unsigned int get_random_int(void) { - __u32 *hash = get_cpu_var(get_random_int_hash); + __u32 *hash; unsigned int ret; + if (arch_get_random_int(&ret)) + return ret; + + hash = get_cpu_var(get_random_int_hash); + hash[0] += current->pid + jiffies + get_cycles(); md5_transform(hash, random_int_secret); ret = hash[0]; diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c index f6cf448..240966b 100644 --- a/drivers/edac/i7core_edac.c +++ b/drivers/edac/i7core_edac.c @@ -1842,11 +1842,9 @@ static int i7core_mce_check_error(void *priv, struct mce *mce) if (mce->bank != 8) return 0; -#ifdef CONFIG_SMP /* Only handle if it is the right mc controller */ if (cpu_data(mce->cpu).phys_proc_id != pvt->i7core_dev->socket) return 0; -#endif smp_rmb(); if ((pvt->mce_out + 1) % MCE_LOG_LEN == pvt->mce_in) { diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index bcb1126..02a52d1 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -6,6 +6,7 @@ #include <linux/dmi.h> #include <linux/efi.h> #include <linux/bootmem.h> +#include <linux/random.h> #include <asm/dmi.h> /* @@ -111,6 +112,8 @@ static int __init dmi_walk_early(void (*decode)(const struct dmi_header *, dmi_table(buf, dmi_len, dmi_num, decode, NULL); + add_device_randomness(buf, dmi_len); + dmi_iounmap(buf, dmi_len); return 0; } diff --git a/drivers/firmware/pcdp.c b/drivers/firmware/pcdp.c index 51e0e2d..a330492 100644 --- a/drivers/firmware/pcdp.c +++ b/drivers/firmware/pcdp.c @@ -95,7 +95,7 @@ efi_setup_pcdp_console(char *cmdline) if (efi.hcdp == EFI_INVALID_TABLE_ADDR) return -ENODEV; - pcdp = ioremap(efi.hcdp, 4096); + pcdp = early_ioremap(efi.hcdp, 4096); printk(KERN_INFO "PCDP: v%d at 0x%lx\n", pcdp->rev, efi.hcdp); if (strstr(cmdline, "console=hcdp")) { @@ -131,6 +131,6 @@ efi_setup_pcdp_console(char *cmdline) } out: - iounmap(pcdp); + early_iounmap(pcdp, 4096); return rc; } diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 2d6039b..3bd85f7 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -150,8 +150,6 @@ static int init_ring_common(struct intel_ring_buffer *ring) I915_WRITE_HEAD(ring, 0); ring->write_tail(ring, 0); - /* Initialize the ring. */ - I915_WRITE_START(ring, obj->gtt_offset); head = I915_READ_HEAD(ring) & HEAD_ADDR; /* G45 ring initialization fails to reset head to zero */ @@ -177,6 +175,11 @@ static int init_ring_common(struct intel_ring_buffer *ring) } } + /* Initialize the ring. This must happen _after_ we've cleared the ring + * registers with the above sequence (the readback of the HEAD registers + * also enforces ordering), otherwise the hw might lose the new ring + * register values. */ + I915_WRITE_START(ring, obj->gtt_offset); I915_WRITE_CTL(ring, ((ring->size - PAGE_SIZE) & RING_NR_PAGES) | RING_REPORT_64K | RING_VALID); diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c index 3b77ad6..efc2b21 100644 --- a/drivers/gpu/drm/radeon/atombios_dp.c +++ b/drivers/gpu/drm/radeon/atombios_dp.c @@ -22,6 +22,7 @@ * * Authors: Dave Airlie * Alex Deucher + * Jerome Glisse */ #include "drmP.h" #include "radeon_drm.h" @@ -624,7 +625,6 @@ static bool radeon_dp_get_link_status(struct radeon_connector *radeon_connector, ret = radeon_dp_aux_native_read(radeon_connector, DP_LANE0_1_STATUS, link_status, DP_LINK_STATUS_SIZE, 100); if (ret <= 0) { - DRM_ERROR("displayport link status failed\n"); return false; } @@ -797,8 +797,10 @@ static int radeon_dp_link_train_cr(struct radeon_dp_link_train_info *dp_info) else mdelay(dp_info->rd_interval * 4); - if (!radeon_dp_get_link_status(dp_info->radeon_connector, dp_info->link_status)) + if (!radeon_dp_get_link_status(dp_info->radeon_connector, dp_info->link_status)) { + DRM_ERROR("displayport link status failed\n"); break; + } if (dp_clock_recovery_ok(dp_info->link_status, dp_info->dp_lane_count)) { clock_recovery = true; @@ -860,8 +862,10 @@ static int radeon_dp_link_train_ce(struct radeon_dp_link_train_info *dp_info) else mdelay(dp_info->rd_interval * 4); - if (!radeon_dp_get_link_status(dp_info->radeon_connector, dp_info->link_status)) + if (!radeon_dp_get_link_status(dp_info->radeon_connector, dp_info->link_status)) { + DRM_ERROR("displayport link status failed\n"); break; + } if (dp_channel_eq_ok(dp_info->link_status, dp_info->dp_lane_count)) { channel_eq = true; diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 8846bad..314e217 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -1019,24 +1019,8 @@ void evergreen_agp_enable(struct radeon_device *rdev) void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *save) { - save->vga_control[0] = RREG32(D1VGA_CONTROL); - save->vga_control[1] = RREG32(D2VGA_CONTROL); save->vga_render_control = RREG32(VGA_RENDER_CONTROL); save->vga_hdp_control = RREG32(VGA_HDP_CONTROL); - save->crtc_control[0] = RREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET); - save->crtc_control[1] = RREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET); - if (rdev->num_crtc >= 4) { - save->vga_control[2] = RREG32(EVERGREEN_D3VGA_CONTROL); - save->vga_control[3] = RREG32(EVERGREEN_D4VGA_CONTROL); - save->crtc_control[2] = RREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET); - save->crtc_control[3] = RREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET); - } - if (rdev->num_crtc >= 6) { - save->vga_control[4] = RREG32(EVERGREEN_D5VGA_CONTROL); - save->vga_control[5] = RREG32(EVERGREEN_D6VGA_CONTROL); - save->crtc_control[4] = RREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET); - save->crtc_control[5] = RREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET); - } /* Stop all video */ WREG32(VGA_RENDER_CONTROL, 0); @@ -1147,47 +1131,6 @@ void evergreen_mc_resume(struct radeon_device *rdev, struct evergreen_mc_save *s /* Unlock host access */ WREG32(VGA_HDP_CONTROL, save->vga_hdp_control); mdelay(1); - /* Restore video state */ - WREG32(D1VGA_CONTROL, save->vga_control[0]); - WREG32(D2VGA_CONTROL, save->vga_control[1]); - if (rdev->num_crtc >= 4) { - WREG32(EVERGREEN_D3VGA_CONTROL, save->vga_control[2]); - WREG32(EVERGREEN_D4VGA_CONTROL, save->vga_control[3]); - } - if (rdev->num_crtc >= 6) { - WREG32(EVERGREEN_D5VGA_CONTROL, save->vga_control[4]); - WREG32(EVERGREEN_D6VGA_CONTROL, save->vga_control[5]); - } - WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC0_REGISTER_OFFSET, 1); - WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC1_REGISTER_OFFSET, 1); - if (rdev->num_crtc >= 4) { - WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC2_REGISTER_OFFSET, 1); - WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC3_REGISTER_OFFSET, 1); - } - if (rdev->num_crtc >= 6) { - WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC4_REGISTER_OFFSET, 1); - WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC5_REGISTER_OFFSET, 1); - } - WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET, save->crtc_control[0]); - WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET, save->crtc_control[1]); - if (rdev->num_crtc >= 4) { - WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET, save->crtc_control[2]); - WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET, save->crtc_control[3]); - } - if (rdev->num_crtc >= 6) { - WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, save->crtc_control[4]); - WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, save->crtc_control[5]); - } - WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC0_REGISTER_OFFSET, 0); - WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC1_REGISTER_OFFSET, 0); - if (rdev->num_crtc >= 4) { - WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC2_REGISTER_OFFSET, 0); - WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC3_REGISTER_OFFSET, 0); - } - if (rdev->num_crtc >= 6) { - WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC4_REGISTER_OFFSET, 0); - WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC5_REGISTER_OFFSET, 0); - } WREG32(VGA_RENDER_CONTROL, save->vga_render_control); } diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h index 3dedaa0..4d81e96 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.h +++ b/drivers/gpu/drm/radeon/radeon_asic.h @@ -253,13 +253,10 @@ void rs690_line_buffer_adjust(struct radeon_device *rdev, * rv515 */ struct rv515_mc_save { - u32 d1vga_control; - u32 d2vga_control; u32 vga_render_control; u32 vga_hdp_control; - u32 d1crtc_control; - u32 d2crtc_control; }; + int rv515_init(struct radeon_device *rdev); void rv515_fini(struct radeon_device *rdev); uint32_t rv515_mc_rreg(struct radeon_device *rdev, uint32_t reg); @@ -387,11 +384,10 @@ void r700_cp_fini(struct radeon_device *rdev); * evergreen */ struct evergreen_mc_save { - u32 vga_control[6]; u32 vga_render_control; u32 vga_hdp_control; - u32 crtc_control[6]; }; + void evergreen_pcie_gart_tlb_flush(struct radeon_device *rdev); int evergreen_init(struct radeon_device *rdev); void evergreen_fini(struct radeon_device *rdev); diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c index 1f6a0f5..f1a1e8a 100644 --- a/drivers/gpu/drm/radeon/radeon_connectors.c +++ b/drivers/gpu/drm/radeon/radeon_connectors.c @@ -66,14 +66,33 @@ void radeon_connector_hotplug(struct drm_connector *connector) /* just deal with DP (not eDP) here. */ if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort) { - int saved_dpms = connector->dpms; - - /* Only turn off the display it it's physically disconnected */ - if (!radeon_hpd_sense(rdev, radeon_connector->hpd.hpd)) - drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF); - else if (radeon_dp_needs_link_train(radeon_connector)) - drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON); - connector->dpms = saved_dpms; + struct radeon_connector_atom_dig *dig_connector = + radeon_connector->con_priv; + + /* if existing sink type was not DP no need to retrain */ + if (dig_connector->dp_sink_type != CONNECTOR_OBJECT_ID_DISPLAYPORT) + return; + + /* first get sink type as it may be reset after (un)plug */ + dig_connector->dp_sink_type = radeon_dp_getsinktype(radeon_connector); + /* don't do anything if sink is not display port, i.e., + * passive dp->(dvi|hdmi) adaptor + */ + if (dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT) { + int saved_dpms = connector->dpms; + /* Only turn off the display if it's physically disconnected */ + if (!radeon_hpd_sense(rdev, radeon_connector->hpd.hpd)) { + drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF); + } else if (radeon_dp_needs_link_train(radeon_connector)) { + /* set it to OFF so that drm_helper_connector_dpms() + * won't return immediately since the current state + * is ON at this point. + */ + connector->dpms = DRM_MODE_DPMS_OFF; + drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON); + } + connector->dpms = saved_dpms; + } } } diff --git a/drivers/gpu/drm/radeon/radeon_cursor.c b/drivers/gpu/drm/radeon/radeon_cursor.c index 3fb2226..72f749d 100644 --- a/drivers/gpu/drm/radeon/radeon_cursor.c +++ b/drivers/gpu/drm/radeon/radeon_cursor.c @@ -257,8 +257,14 @@ int radeon_crtc_cursor_move(struct drm_crtc *crtc, if (!(cursor_end & 0x7f)) w--; } - if (w <= 0) + if (w <= 0) { w = 1; + cursor_end = x - xorigin + w; + if (!(cursor_end & 0x7f)) { + x--; + WARN_ON_ONCE(x < 0); + } + } } } diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c index 6613ee9..d5f45b4 100644 --- a/drivers/gpu/drm/radeon/rv515.c +++ b/drivers/gpu/drm/radeon/rv515.c @@ -281,12 +281,8 @@ int rv515_debugfs_ga_info_init(struct radeon_device *rdev) void rv515_mc_stop(struct radeon_device *rdev, struct rv515_mc_save *save) { - save->d1vga_control = RREG32(R_000330_D1VGA_CONTROL); - save->d2vga_control = RREG32(R_000338_D2VGA_CONTROL); save->vga_render_control = RREG32(R_000300_VGA_RENDER_CONTROL); save->vga_hdp_control = RREG32(R_000328_VGA_HDP_CONTROL); - save->d1crtc_control = RREG32(R_006080_D1CRTC_CONTROL); - save->d2crtc_control = RREG32(R_006880_D2CRTC_CONTROL); /* Stop all video */ WREG32(R_0068E8_D2CRTC_UPDATE_LOCK, 0); @@ -311,15 +307,6 @@ void rv515_mc_resume(struct radeon_device *rdev, struct rv515_mc_save *save) /* Unlock host access */ WREG32(R_000328_VGA_HDP_CONTROL, save->vga_hdp_control); mdelay(1); - /* Restore video state */ - WREG32(R_000330_D1VGA_CONTROL, save->d1vga_control); - WREG32(R_000338_D2VGA_CONTROL, save->d2vga_control); - WREG32(R_0060E8_D1CRTC_UPDATE_LOCK, 1); - WREG32(R_0068E8_D2CRTC_UPDATE_LOCK, 1); - WREG32(R_006080_D1CRTC_CONTROL, save->d1crtc_control); - WREG32(R_006880_D2CRTC_CONTROL, save->d2crtc_control); - WREG32(R_0060E8_D1CRTC_UPDATE_LOCK, 0); - WREG32(R_0068E8_D2CRTC_UPDATE_LOCK, 0); WREG32(R_000300_VGA_RENDER_CONTROL, save->vga_render_control); } diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index 252defd..87fd034 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -47,16 +47,15 @@ #define MAX_ATTRS 5 /* Maximum no of per-core attrs */ #define MAX_CORE_DATA (NUM_REAL_CORES + BASE_SYSFS_ATTR_NO) -#ifdef CONFIG_SMP #define TO_PHYS_ID(cpu) cpu_data(cpu).phys_proc_id #define TO_CORE_ID(cpu) cpu_data(cpu).cpu_core_id +#define TO_ATTR_NO(cpu) (TO_CORE_ID(cpu) + BASE_SYSFS_ATTR_NO) + +#ifdef CONFIG_SMP #define for_each_sibling(i, cpu) for_each_cpu(i, cpu_sibling_mask(cpu)) #else -#define TO_PHYS_ID(cpu) (cpu) -#define TO_CORE_ID(cpu) (cpu) #define for_each_sibling(i, cpu) for (i = 0; false; ) #endif -#define TO_ATTR_NO(cpu) (TO_CORE_ID(cpu) + BASE_SYSFS_ATTR_NO) /* * Per-Core Temperature Data diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index 7d5109b..e763e30 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -568,24 +568,62 @@ static void srp_unmap_data(struct scsi_cmnd *scmnd, scmnd->sc_data_direction); } -static void srp_remove_req(struct srp_target_port *target, - struct srp_request *req, s32 req_lim_delta) +/** + * srp_claim_req - Take ownership of the scmnd associated with a request. + * @target: SRP target port. + * @req: SRP request. + * @scmnd: If NULL, take ownership of @req->scmnd. If not NULL, only take + * ownership of @req->scmnd if it equals @scmnd. + * + * Return value: + * Either NULL or a pointer to the SCSI command the caller became owner of. + */ +static struct scsi_cmnd *srp_claim_req(struct srp_target_port *target, + struct srp_request *req, + struct scsi_cmnd *scmnd) { unsigned long flags; - srp_unmap_data(req->scmnd, target, req); + spin_lock_irqsave(&target->lock, flags); + if (!scmnd) { + scmnd = req->scmnd; + req->scmnd = NULL; + } else if (req->scmnd == scmnd) { + req->scmnd = NULL; + } else { + scmnd = NULL; + } + spin_unlock_irqrestore(&target->lock, flags); + + return scmnd; +} + +/** + * srp_free_req() - Unmap data and add request to the free request list. + */ +static void srp_free_req(struct srp_target_port *target, + struct srp_request *req, struct scsi_cmnd *scmnd, + s32 req_lim_delta) +{ + unsigned long flags; + + srp_unmap_data(scmnd, target, req); + spin_lock_irqsave(&target->lock, flags); target->req_lim += req_lim_delta; - req->scmnd = NULL; list_add_tail(&req->list, &target->free_reqs); spin_unlock_irqrestore(&target->lock, flags); } static void srp_reset_req(struct srp_target_port *target, struct srp_request *req) { - req->scmnd->result = DID_RESET << 16; - req->scmnd->scsi_done(req->scmnd); - srp_remove_req(target, req, 0); + struct scsi_cmnd *scmnd = srp_claim_req(target, req, NULL); + + if (scmnd) { + scmnd->result = DID_RESET << 16; + scmnd->scsi_done(scmnd); + srp_free_req(target, req, scmnd, 0); + } } static int srp_reconnect_target(struct srp_target_port *target) @@ -1055,11 +1093,18 @@ static void srp_process_rsp(struct srp_target_port *target, struct srp_rsp *rsp) complete(&target->tsk_mgmt_done); } else { req = &target->req_ring[rsp->tag]; - scmnd = req->scmnd; - if (!scmnd) + scmnd = srp_claim_req(target, req, NULL); + if (!scmnd) { shost_printk(KERN_ERR, target->scsi_host, "Null scmnd for RSP w/tag %016llx\n", (unsigned long long) rsp->tag); + + spin_lock_irqsave(&target->lock, flags); + target->req_lim += be32_to_cpu(rsp->req_lim_delta); + spin_unlock_irqrestore(&target->lock, flags); + + return; + } scmnd->result = rsp->status; if (rsp->flags & SRP_RSP_FLAG_SNSVALID) { @@ -1074,7 +1119,9 @@ static void srp_process_rsp(struct srp_target_port *target, struct srp_rsp *rsp) else if (rsp->flags & (SRP_RSP_FLAG_DIOVER | SRP_RSP_FLAG_DIUNDER)) scsi_set_resid(scmnd, be32_to_cpu(rsp->data_in_res_cnt)); - srp_remove_req(target, req, be32_to_cpu(rsp->req_lim_delta)); + srp_free_req(target, req, scmnd, + be32_to_cpu(rsp->req_lim_delta)); + scmnd->host_scribble = NULL; scmnd->scsi_done(scmnd); } @@ -1613,25 +1660,17 @@ static int srp_abort(struct scsi_cmnd *scmnd) { struct srp_target_port *target = host_to_target(scmnd->device->host); struct srp_request *req = (struct srp_request *) scmnd->host_scribble; - int ret = SUCCESS; shost_printk(KERN_ERR, target->scsi_host, "SRP abort called\n"); - if (!req || target->qp_in_error) - return FAILED; - if (srp_send_tsk_mgmt(target, req->index, scmnd->device->lun, - SRP_TSK_ABORT_TASK)) + if (!req || target->qp_in_error || !srp_claim_req(target, req, scmnd)) return FAILED; + srp_send_tsk_mgmt(target, req->index, scmnd->device->lun, + SRP_TSK_ABORT_TASK); + srp_free_req(target, req, scmnd, 0); + scmnd->result = DID_ABORT << 16; - if (req->scmnd) { - if (!target->tsk_mgmt_status) { - srp_remove_req(target, req, 0); - scmnd->result = DID_ABORT << 16; - } else - ret = FAILED; - } - - return ret; + return SUCCESS; } static int srp_reset_device(struct scsi_cmnd *scmnd) diff --git a/drivers/input/tablet/wacom_wac.c b/drivers/input/tablet/wacom_wac.c index 08ba5ad..a28ebf0 100644 --- a/drivers/input/tablet/wacom_wac.c +++ b/drivers/input/tablet/wacom_wac.c @@ -242,7 +242,7 @@ static int wacom_graphire_irq(struct wacom_wac *wacom) input_report_abs(input, ABS_X, le16_to_cpup((__le16 *)&data[2])); input_report_abs(input, ABS_Y, le16_to_cpup((__le16 *)&data[4])); if (wacom->tool[0] != BTN_TOOL_MOUSE) { - input_report_abs(input, ABS_PRESSURE, data[6] | ((data[7] & 0x01) << 8)); + input_report_abs(input, ABS_PRESSURE, data[6] | ((data[7] & 0x03) << 8)); input_report_key(input, BTN_TOUCH, data[1] & 0x01); input_report_key(input, BTN_STYLUS, data[1] & 0x02); input_report_key(input, BTN_STYLUS2, data[1] & 0x04); diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index 9bfd057..42ef54f 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -1210,7 +1210,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, * We need to dec pending if this was a write. */ if (rw == WRITE) { - if (!(bio->bi_rw & REQ_FLUSH)) + if (!(bio->bi_rw & (REQ_FLUSH | REQ_DISCARD))) dm_rh_dec(ms->rh, map_context->ll); return error; } diff --git a/drivers/md/dm-region-hash.c b/drivers/md/dm-region-hash.c index 7771ed2..69732e0 100644 --- a/drivers/md/dm-region-hash.c +++ b/drivers/md/dm-region-hash.c @@ -404,6 +404,9 @@ void dm_rh_mark_nosync(struct dm_region_hash *rh, struct bio *bio) return; } + if (bio->bi_rw & REQ_DISCARD) + return; + /* We must inform the log that the sync count has changed. */ log->type->set_region_sync(log, region, 0); @@ -524,7 +527,7 @@ void dm_rh_inc_pending(struct dm_region_hash *rh, struct bio_list *bios) struct bio *bio; for (bio = bios->head; bio; bio = bio->bi_next) { - if (bio->bi_rw & REQ_FLUSH) + if (bio->bi_rw & (REQ_FLUSH | REQ_DISCARD)) continue; rh_inc(rh, dm_rh_bio_to_region(rh, bio)); } diff --git a/drivers/mfd/ab3100-core.c b/drivers/mfd/ab3100-core.c index a20e1c4..ccd81b1 100644 --- a/drivers/mfd/ab3100-core.c +++ b/drivers/mfd/ab3100-core.c @@ -408,8 +408,6 @@ static irqreturn_t ab3100_irq_handler(int irq, void *data) u32 fatevent; int err; - add_interrupt_randomness(irq); - err = ab3100_get_register_page_interruptible(ab3100, AB3100_EVENTA1, event_regs, 3); if (err) @@ -938,9 +936,6 @@ static int __devinit ab3100_probe(struct i2c_client *client, err = request_threaded_irq(client->irq, NULL, ab3100_irq_handler, IRQF_ONESHOT, "ab3100-core", ab3100); - /* This real unpredictable IRQ is of course sampled for entropy */ - rand_initialize_irq(client->irq); - if (err) goto exit_no_irq; diff --git a/drivers/mfd/ab3550-core.c b/drivers/mfd/ab3550-core.c index 3d7dce6..d69dc4b 100644 --- a/drivers/mfd/ab3550-core.c +++ b/drivers/mfd/ab3550-core.c @@ -1309,8 +1309,6 @@ static int __init ab3550_probe(struct i2c_client *client, err = request_threaded_irq(client->irq, NULL, ab3550_irq_handler, IRQF_ONESHOT, "ab3550-core", ab); - /* This real unpredictable IRQ is of course sampled for entropy */ - rand_initialize_irq(client->irq); if (err) goto exit_no_irq; diff --git a/drivers/mfd/ezx-pcap.c b/drivers/mfd/ezx-pcap.c index 43a76c4..db662e2 100644 --- a/drivers/mfd/ezx-pcap.c +++ b/drivers/mfd/ezx-pcap.c @@ -202,7 +202,7 @@ static void pcap_isr_work(struct work_struct *work) } local_irq_enable(); ezx_pcap_write(pcap, PCAP_REG_MSR, pcap->msr); - } while (gpio_get_value(irq_to_gpio(pcap->spi->irq))); + } while (gpio_get_value(pdata->gpio)); } static void pcap_irq_handler(unsigned int irq, struct irq_desc *desc) diff --git a/drivers/mfd/wm831x-otp.c b/drivers/mfd/wm831x-otp.c index f742745..b90f3e0 100644 --- a/drivers/mfd/wm831x-otp.c +++ b/drivers/mfd/wm831x-otp.c @@ -18,6 +18,7 @@ #include <linux/bcd.h> #include <linux/delay.h> #include <linux/mfd/core.h> +#include <linux/random.h> #include <linux/mfd/wm831x/core.h> #include <linux/mfd/wm831x/otp.h> @@ -66,6 +67,7 @@ static DEVICE_ATTR(unique_id, 0444, wm831x_unique_id_show, NULL); int wm831x_otp_init(struct wm831x *wm831x) { + char uuid[WM831X_UNIQUE_ID_LEN]; int ret; ret = device_create_file(wm831x->dev, &dev_attr_unique_id); @@ -73,6 +75,12 @@ int wm831x_otp_init(struct wm831x *wm831x) dev_err(wm831x->dev, "Unique ID attribute not created: %d\n", ret); + ret = wm831x_unique_id_read(wm831x, uuid); + if (ret == 0) + add_device_randomness(uuid, sizeof(uuid)); + else + dev_err(wm831x->dev, "Failed to read UUID: %d\n", ret); + return ret; } diff --git a/drivers/mmc/host/sdhci-pci.c b/drivers/mmc/host/sdhci-pci.c index 936bbca..d3b3115 100644 --- a/drivers/mmc/host/sdhci-pci.c +++ b/drivers/mmc/host/sdhci-pci.c @@ -140,6 +140,7 @@ static const struct sdhci_pci_fixes sdhci_ene_714 = { static const struct sdhci_pci_fixes sdhci_cafe = { .quirks = SDHCI_QUIRK_NO_SIMULT_VDD_AND_POWER | SDHCI_QUIRK_NO_BUSY_IRQ | + SDHCI_QUIRK_BROKEN_CARD_DETECTION | SDHCI_QUIRK_BROKEN_TIMEOUT_VAL, }; diff --git a/drivers/net/bnx2.c b/drivers/net/bnx2.c index 74580bb..c9b123c 100644 --- a/drivers/net/bnx2.c +++ b/drivers/net/bnx2.c @@ -5310,7 +5310,7 @@ bnx2_free_tx_skbs(struct bnx2 *bp) int k, last; if (skb == NULL) { - j++; + j = NEXT_TX_BD(j); continue; } @@ -5322,8 +5322,8 @@ bnx2_free_tx_skbs(struct bnx2 *bp) tx_buf->skb = NULL; last = tx_buf->nr_frags; - j++; - for (k = 0; k < last; k++, j++) { + j = NEXT_TX_BD(j); + for (k = 0; k < last; k++, j = NEXT_TX_BD(j)) { tx_buf = &txr->tx_buf_ring[TX_RING_IDX(j)]; dma_unmap_page(&bp->pdev->dev, dma_unmap_addr(tx_buf, mapping), diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c index 3df0c0f..82b1802 100644 --- a/drivers/net/caif/caif_serial.c +++ b/drivers/net/caif/caif_serial.c @@ -325,6 +325,9 @@ static int ldisc_open(struct tty_struct *tty) sprintf(name, "cf%s", tty->name); dev = alloc_netdev(sizeof(*ser), name, caifdev_setup); + if (!dev) + return -ENOMEM; + ser = netdev_priv(dev); ser->tty = tty_kref_get(tty); ser->dev = dev; diff --git a/drivers/net/e1000e/82571.c b/drivers/net/e1000e/82571.c index 5278e84..0d0ee55 100644 --- a/drivers/net/e1000e/82571.c +++ b/drivers/net/e1000e/82571.c @@ -1602,10 +1602,8 @@ static s32 e1000_check_for_serdes_link_82571(struct e1000_hw *hw) * auto-negotiation in the TXCW register and disable * forced link in the Device Control register in an * attempt to auto-negotiate with our link partner. - * If the partner code word is null, stop forcing - * and restart auto negotiation. */ - if ((rxcw & E1000_RXCW_C) || !(rxcw & E1000_RXCW_CW)) { + if (rxcw & E1000_RXCW_C) { /* Enable autoneg, and unforce link up */ ew32(TXCW, mac->txcw); ew32(CTRL, (ctrl & ~E1000_CTRL_SLU)); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 76b8650..3cc22b9 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1245,10 +1245,12 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, } #endif - if (cmd == TUNSETIFF || _IOC_TYPE(cmd) == 0x89) + if (cmd == TUNSETIFF || _IOC_TYPE(cmd) == 0x89) { if (copy_from_user(&ifr, argp, ifreq_len)) return -EFAULT; - + } else { + memset(&ifr, 0, sizeof(ifr)); + } if (cmd == TUNGETFEATURES) { /* Currently this just means: "what IFF flags are valid?". * This is needed because we never checked for invalid flags on diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c index ad0298f..3362449 100644 --- a/drivers/net/usb/kaweth.c +++ b/drivers/net/usb/kaweth.c @@ -1308,7 +1308,7 @@ static int kaweth_internal_control_msg(struct usb_device *usb_dev, int retv; int length = 0; /* shut up GCC */ - urb = usb_alloc_urb(0, GFP_NOIO); + urb = usb_alloc_urb(0, GFP_ATOMIC); if (!urb) return -ENOMEM; diff --git a/drivers/net/wireless/rt2x00/rt2800usb.c b/drivers/net/wireless/rt2x00/rt2800usb.c index 0781fb0..39ebf9f 100644 --- a/drivers/net/wireless/rt2x00/rt2800usb.c +++ b/drivers/net/wireless/rt2x00/rt2800usb.c @@ -829,6 +829,7 @@ static struct usb_device_id rt2800usb_device_table[] = { { USB_DEVICE(0x0411, 0x015d) }, { USB_DEVICE(0x0411, 0x016f) }, { USB_DEVICE(0x0411, 0x01a2) }, + { USB_DEVICE(0x0411, 0x01ee) }, /* Corega */ { USB_DEVICE(0x07aa, 0x002f) }, { USB_DEVICE(0x07aa, 0x003c) }, diff --git a/drivers/net/wireless/rt2x00/rt61pci.c b/drivers/net/wireless/rt2x00/rt61pci.c index 9d35ec1..9e5fd45 100644 --- a/drivers/net/wireless/rt2x00/rt61pci.c +++ b/drivers/net/wireless/rt2x00/rt61pci.c @@ -2254,8 +2254,7 @@ static void rt61pci_txdone(struct rt2x00_dev *rt2x00dev) static void rt61pci_wakeup(struct rt2x00_dev *rt2x00dev) { - struct ieee80211_conf conf = { .flags = 0 }; - struct rt2x00lib_conf libconf = { .conf = &conf }; + struct rt2x00lib_conf libconf = { .conf = &rt2x00dev->hw->conf }; rt61pci_config(rt2x00dev, &libconf, IEEE80211_CONF_CHANGE_PS); } diff --git a/drivers/rtc/rtc-wm831x.c b/drivers/rtc/rtc-wm831x.c index bdc909b..f3c2110 100644 --- a/drivers/rtc/rtc-wm831x.c +++ b/drivers/rtc/rtc-wm831x.c @@ -24,7 +24,7 @@ #include <linux/mfd/wm831x/core.h> #include <linux/delay.h> #include <linux/platform_device.h> - +#include <linux/random.h> /* * R16416 (0x4020) - RTC Write Counter @@ -96,6 +96,26 @@ struct wm831x_rtc { unsigned int alarm_enabled:1; }; +static void wm831x_rtc_add_randomness(struct wm831x *wm831x) +{ + int ret; + u16 reg; + + /* + * The write counter contains a pseudo-random number which is + * regenerated every time we set the RTC so it should be a + * useful per-system source of entropy. + */ + ret = wm831x_reg_read(wm831x, WM831X_RTC_WRITE_COUNTER); + if (ret >= 0) { + reg = ret; + add_device_randomness(®, sizeof(reg)); + } else { + dev_warn(wm831x->dev, "Failed to read RTC write counter: %d\n", + ret); + } +} + /* * Read current time and date in RTC */ @@ -449,6 +469,8 @@ static int wm831x_rtc_probe(struct platform_device *pdev) alm_irq, ret); } + wm831x_rtc_add_randomness(wm831x); + return 0; err: diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c index e68fac6..d2f9576 100644 --- a/drivers/scsi/libsas/sas_expander.c +++ b/drivers/scsi/libsas/sas_expander.c @@ -770,7 +770,7 @@ static struct domain_device *sas_ex_discover_end_dev( } /* See if this phy is part of a wide port */ -static int sas_ex_join_wide_port(struct domain_device *parent, int phy_id) +static bool sas_ex_join_wide_port(struct domain_device *parent, int phy_id) { struct ex_phy *phy = &parent->ex_dev.ex_phy[phy_id]; int i; @@ -786,11 +786,11 @@ static int sas_ex_join_wide_port(struct domain_device *parent, int phy_id) sas_port_add_phy(ephy->port, phy->phy); phy->port = ephy->port; phy->phy_state = PHY_DEVICE_DISCOVERED; - return 0; + return true; } } - return -ENODEV; + return false; } static struct domain_device *sas_ex_discover_expander( @@ -928,8 +928,7 @@ static int sas_ex_discover_dev(struct domain_device *dev, int phy_id) return res; } - res = sas_ex_join_wide_port(dev, phy_id); - if (!res) { + if (sas_ex_join_wide_port(dev, phy_id)) { SAS_DPRINTK("Attaching ex phy%d to wide port %016llx\n", phy_id, SAS_ADDR(ex_phy->attached_sas_addr)); return res; @@ -974,8 +973,7 @@ static int sas_ex_discover_dev(struct domain_device *dev, int phy_id) if (SAS_ADDR(ex->ex_phy[i].attached_sas_addr) == SAS_ADDR(child->sas_addr)) { ex->ex_phy[i].phy_state= PHY_DEVICE_DISCOVERED; - res = sas_ex_join_wide_port(dev, i); - if (!res) + if (sas_ex_join_wide_port(dev, i)) SAS_DPRINTK("Attaching ex phy%d to wide port %016llx\n", i, SAS_ADDR(ex->ex_phy[i].attached_sas_addr)); @@ -1838,32 +1836,20 @@ static int sas_discover_new(struct domain_device *dev, int phy_id) { struct ex_phy *ex_phy = &dev->ex_dev.ex_phy[phy_id]; struct domain_device *child; - bool found = false; - int res, i; + int res; SAS_DPRINTK("ex %016llx phy%d new device attached\n", SAS_ADDR(dev->sas_addr), phy_id); res = sas_ex_phy_discover(dev, phy_id); if (res) - goto out; - /* to support the wide port inserted */ - for (i = 0; i < dev->ex_dev.num_phys; i++) { - struct ex_phy *ex_phy_temp = &dev->ex_dev.ex_phy[i]; - if (i == phy_id) - continue; - if (SAS_ADDR(ex_phy_temp->attached_sas_addr) == - SAS_ADDR(ex_phy->attached_sas_addr)) { - found = true; - break; - } - } - if (found) { - sas_ex_join_wide_port(dev, phy_id); + return res; + + if (sas_ex_join_wide_port(dev, phy_id)) return 0; - } + res = sas_ex_discover_devices(dev, phy_id); - if (!res) - goto out; + if (res) + return res; list_for_each_entry(child, &dev->ex_dev.children, siblings) { if (SAS_ADDR(child->sas_addr) == SAS_ADDR(ex_phy->attached_sas_addr)) { @@ -1873,7 +1859,6 @@ static int sas_discover_new(struct domain_device *dev, int phy_id) break; } } -out: return res; } @@ -1972,9 +1957,7 @@ int sas_ex_revalidate_domain(struct domain_device *port_dev) struct domain_device *dev = NULL; res = sas_find_bcast_dev(port_dev, &dev); - if (res) - goto out; - if (dev) { + while (res == 0 && dev) { struct expander_device *ex = &dev->ex_dev; int i = 0, phy_id; @@ -1986,8 +1969,10 @@ int sas_ex_revalidate_domain(struct domain_device *port_dev) res = sas_rediscover(dev, phy_id); i = phy_id + 1; } while (i < ex->num_phys); + + dev = NULL; + res = sas_find_bcast_dev(port_dev, &dev); } -out: return res; } diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index a4b9cdb..7f1afde 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -1665,6 +1665,20 @@ static void scsi_restart_operations(struct Scsi_Host *shost) * requests are started. */ scsi_run_host_queues(shost); + + /* + * if eh is active and host_eh_scheduled is pending we need to re-run + * recovery. we do this check after scsi_run_host_queues() to allow + * everything pent up since the last eh run a chance to make forward + * progress before we sync again. Either we'll immediately re-run + * recovery or scsi_device_unbusy() will wake us again when these + * pending commands complete. + */ + spin_lock_irqsave(shost->host_lock, flags); + if (shost->host_eh_scheduled) + if (scsi_host_set_state(shost, SHOST_RECOVERY)) + WARN_ON(scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY)); + spin_unlock_irqrestore(shost->host_lock, flags); } /** diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 99fc45b..dd454c4 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -481,15 +481,26 @@ void scsi_requeue_run_queue(struct work_struct *work) */ static void scsi_requeue_command(struct request_queue *q, struct scsi_cmnd *cmd) { + struct scsi_device *sdev = cmd->device; struct request *req = cmd->request; unsigned long flags; + /* + * We need to hold a reference on the device to avoid the queue being + * killed after the unlock and before scsi_run_queue is invoked which + * may happen because scsi_unprep_request() puts the command which + * releases its reference on the device. + */ + get_device(&sdev->sdev_gendev); + spin_lock_irqsave(q->queue_lock, flags); scsi_unprep_request(req); blk_requeue_request(q, req); spin_unlock_irqrestore(q->queue_lock, flags); scsi_run_queue(q); + + put_device(&sdev->sdev_gendev); } void scsi_next_command(struct scsi_cmnd *cmd) diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 6e7ea4a..a48b59c 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -1710,6 +1710,9 @@ static void scsi_sysfs_add_devices(struct Scsi_Host *shost) { struct scsi_device *sdev; shost_for_each_device(sdev, shost) { + /* target removed before the device could be added */ + if (sdev->sdev_state == SDEV_DEL) + continue; if (!scsi_host_scan_allowed(shost) || scsi_sysfs_add_sdev(sdev) != 0) __scsi_remove_device(sdev); diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index e0bd3f7..de21547 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -962,7 +962,6 @@ static void __scsi_remove_target(struct scsi_target *starget) struct scsi_device *sdev; spin_lock_irqsave(shost->host_lock, flags); - starget->reap_ref++; restart: list_for_each_entry(sdev, &shost->__devices, siblings) { if (sdev->channel != starget->channel || @@ -976,14 +975,6 @@ static void __scsi_remove_target(struct scsi_target *starget) goto restart; } spin_unlock_irqrestore(shost->host_lock, flags); - scsi_target_reap(starget); -} - -static int __remove_child (struct device * dev, void * data) -{ - if (scsi_is_target_device(dev)) - __scsi_remove_target(to_scsi_target(dev)); - return 0; } /** @@ -996,14 +987,34 @@ static int __remove_child (struct device * dev, void * data) */ void scsi_remove_target(struct device *dev) { - if (scsi_is_target_device(dev)) { - __scsi_remove_target(to_scsi_target(dev)); - return; + struct Scsi_Host *shost = dev_to_shost(dev->parent); + struct scsi_target *starget, *found; + unsigned long flags; + + restart: + found = NULL; + spin_lock_irqsave(shost->host_lock, flags); + list_for_each_entry(starget, &shost->__targets, siblings) { + if (starget->state == STARGET_DEL) + continue; + if (starget->dev.parent == dev || &starget->dev == dev) { + found = starget; + found->reap_ref++; + break; + } } + spin_unlock_irqrestore(shost->host_lock, flags); - get_device(dev); - device_for_each_child(dev, NULL, __remove_child); - put_device(dev); + if (found) { + __scsi_remove_target(found); + scsi_target_reap(found); + /* in the case where @dev has multiple starget children, + * continue removing. + * + * FIXME: does such a case exist? + */ + goto restart; + } } EXPORT_SYMBOL(scsi_remove_target); diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index ca3c303..4d1f996 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -1557,10 +1557,14 @@ static int processcompl_compat(struct async *as, void __user * __user *arg) void __user *addr = as->userurb; unsigned int i; - if (as->userbuffer && urb->actual_length) - if (copy_to_user(as->userbuffer, urb->transfer_buffer, - urb->actual_length)) + if (as->userbuffer && urb->actual_length) { + if (urb->number_of_packets > 0) /* Isochronous */ + i = urb->transfer_buffer_length; + else /* Non-Isoc */ + i = urb->actual_length; + if (copy_to_user(as->userbuffer, urb->transfer_buffer, i)) return -EFAULT; + } if (put_user(as->status, &userurb->status)) return -EFAULT; if (put_user(urb->actual_length, &userurb->actual_length)) diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 34bb059..3c0aa02 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -24,6 +24,7 @@ #include <linux/kthread.h> #include <linux/mutex.h> #include <linux/freezer.h> +#include <linux/random.h> #include <asm/uaccess.h> #include <asm/byteorder.h> @@ -1902,6 +1903,14 @@ int usb_new_device(struct usb_device *udev) /* Tell the world! */ announce_device(udev); + if (udev->serial) + add_device_randomness(udev->serial, strlen(udev->serial)); + if (udev->product) + add_device_randomness(udev->product, strlen(udev->product)); + if (udev->manufacturer) + add_device_randomness(udev->manufacturer, + strlen(udev->manufacturer)); + device_enable_async_suspend(&udev->dev); /* Register the device. The device driver is responsible * for configuring the device and invoking the add-device diff --git a/drivers/usb/early/ehci-dbgp.c b/drivers/usb/early/ehci-dbgp.c index 1fc8f12..347bb05 100644 --- a/drivers/usb/early/ehci-dbgp.c +++ b/drivers/usb/early/ehci-dbgp.c @@ -450,7 +450,7 @@ static int dbgp_ehci_startup(void) writel(FLAG_CF, &ehci_regs->configured_flag); /* Wait until the controller is no longer halted */ - loop = 10; + loop = 1000; do { status = readl(&ehci_regs->status); if (!(status & STS_HALT)) diff --git a/drivers/usb/gadget/u_ether.c b/drivers/usb/gadget/u_ether.c index 4690980..f30c307 100644 --- a/drivers/usb/gadget/u_ether.c +++ b/drivers/usb/gadget/u_ether.c @@ -846,12 +846,6 @@ int gether_setup_name(struct usb_gadget *g, u8 ethaddr[ETH_ALEN], SET_ETHTOOL_OPS(net, &ops); - /* two kinds of host-initiated state changes: - * - iff DATA transfer is active, carrier is "on" - * - tx queueing enabled if open *and* carrier is "on" - */ - netif_carrier_off(net); - dev->gadget = g; SET_NETDEV_DEV(net, &g->dev); SET_NETDEV_DEVTYPE(net, &gadget_type); @@ -865,6 +859,12 @@ int gether_setup_name(struct usb_gadget *g, u8 ethaddr[ETH_ALEN], INFO(dev, "HOST MAC %pM\n", dev->host_mac); the_dev = dev; + + /* two kinds of host-initiated state changes: + * - iff DATA transfer is active, carrier is "on" + * - tx queueing enabled if open *and* carrier is "on" + */ + netif_carrier_off(net); } return status; diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index 9ab094c..efba0188 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -798,6 +798,13 @@ void usb_enable_xhci_ports(struct pci_dev *xhci_pdev) } EXPORT_SYMBOL_GPL(usb_enable_xhci_ports); +void usb_disable_xhci_ports(struct pci_dev *xhci_pdev) +{ + pci_write_config_dword(xhci_pdev, USB_INTEL_USB3_PSSEN, 0x0); + pci_write_config_dword(xhci_pdev, USB_INTEL_XUSB2PR, 0x0); +} +EXPORT_SYMBOL_GPL(usb_disable_xhci_ports); + /** * PCI Quirks for xHCI. * diff --git a/drivers/usb/host/pci-quirks.h b/drivers/usb/host/pci-quirks.h index b1002a8..ef004a5 100644 --- a/drivers/usb/host/pci-quirks.h +++ b/drivers/usb/host/pci-quirks.h @@ -10,6 +10,7 @@ void usb_amd_quirk_pll_disable(void); void usb_amd_quirk_pll_enable(void); bool usb_is_intel_switchable_xhci(struct pci_dev *pdev); void usb_enable_xhci_ports(struct pci_dev *xhci_pdev); +void usb_disable_xhci_ports(struct pci_dev *xhci_pdev); #else static inline void usb_amd_quirk_pll_disable(void) {} static inline void usb_amd_quirk_pll_enable(void) {} diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 39e230f..b047458 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -140,11 +140,21 @@ static int xhci_pci_setup(struct usb_hcd *hcd) xhci->quirks |= XHCI_SPURIOUS_SUCCESS; xhci->quirks |= XHCI_EP_LIMIT_QUIRK; xhci->limit_active_eps = 64; + /* + * PPT desktop boards DH77EB and DH77DF will power back on after + * a few seconds of being shutdown. The fix for this is to + * switch the ports from xHCI to EHCI on shutdown. We can't use + * DMI information to find those particular boards (since each + * vendor will change the board name), so we have to key off all + * PPT chipsets. + */ + xhci->quirks |= XHCI_SPURIOUS_REBOOT; } if (pdev->vendor == PCI_VENDOR_ID_ETRON && pdev->device == PCI_DEVICE_ID_ASROCK_P67) { xhci->quirks |= XHCI_RESET_ON_RESUME; xhci_dbg(xhci, "QUIRK: Resetting on resume\n"); + xhci->quirks |= XHCI_TRUST_TX_LENGTH; } if (pdev->vendor == PCI_VENDOR_ID_VIA) xhci->quirks |= XHCI_RESET_ON_RESUME; diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 16ec4d3..1f9602a 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -163,7 +163,7 @@ int xhci_reset(struct xhci_hcd *xhci) xhci_writel(xhci, command, &xhci->op_regs->command); ret = handshake(xhci, &xhci->op_regs->command, - CMD_RESET, 0, 250 * 1000); + CMD_RESET, 0, 10 * 1000 * 1000); if (ret) return ret; @@ -172,7 +172,8 @@ int xhci_reset(struct xhci_hcd *xhci) * xHCI cannot write to any doorbells or operational registers other * than status until the "Controller Not Ready" flag is cleared. */ - return handshake(xhci, &xhci->op_regs->status, STS_CNR, 0, 250 * 1000); + return handshake(xhci, &xhci->op_regs->status, + STS_CNR, 0, 10 * 1000 * 1000); } /* @@ -593,6 +594,9 @@ void xhci_shutdown(struct usb_hcd *hcd) { struct xhci_hcd *xhci = hcd_to_xhci(hcd); + if (xhci->quirks && XHCI_SPURIOUS_REBOOT) + usb_disable_xhci_ports(to_pci_dev(hcd->self.controller)); + spin_lock_irq(&xhci->lock); xhci_halt(xhci); spin_unlock_irq(&xhci->lock); diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 25c3e26..d88644d 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1316,6 +1316,7 @@ struct xhci_hcd { #define XHCI_RESET_ON_RESUME (1 << 7) #define XHCI_AMD_0x96_HOST (1 << 9) #define XHCI_TRUST_TX_LENGTH (1 << 10) +#define XHCI_SPURIOUS_REBOOT (1 << 13) unsigned int num_active_eps; unsigned int limit_active_eps; /* There are two roothubs to keep track of bus suspend info for */ diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 86fc8fc..535a307 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -809,6 +809,7 @@ static struct usb_device_id id_table_combined [] = { { USB_DEVICE(LARSENBRUSGAARD_VID, LB_ALTITRACK_PID) }, { USB_DEVICE(GN_OTOMETRICS_VID, AURICAL_USB_PID) }, { USB_DEVICE(PI_VID, PI_E861_PID) }, + { USB_DEVICE(KONDO_VID, KONDO_USB_SERIAL_PID) }, { USB_DEVICE(BAYER_VID, BAYER_CONTOUR_CABLE_PID) }, { USB_DEVICE(FTDI_VID, MARVELL_OPENRD_PID), .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index d27d7d7..54b4258 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -795,6 +795,13 @@ #define PI_E861_PID 0x1008 /* E-861 piezo controller USB connection */ /* + * Kondo Kagaku Co.Ltd. + * http://www.kondo-robot.com/EN + */ +#define KONDO_VID 0x165c +#define KONDO_USB_SERIAL_PID 0x0002 + +/* * Bayer Ascensia Contour blood glucose meter USB-converter cable. * http://winglucofacts.com/cables/ */ diff --git a/drivers/usb/serial/mos7840.c b/drivers/usb/serial/mos7840.c index fdbeb6a..fd2463e 100644 --- a/drivers/usb/serial/mos7840.c +++ b/drivers/usb/serial/mos7840.c @@ -1191,9 +1191,12 @@ static int mos7840_chars_in_buffer(struct tty_struct *tty) } spin_lock_irqsave(&mos7840_port->pool_lock, flags); - for (i = 0; i < NUM_URBS; ++i) - if (mos7840_port->busy[i]) - chars += URB_TRANSFER_BUFFER_SIZE; + for (i = 0; i < NUM_URBS; ++i) { + if (mos7840_port->busy[i]) { + struct urb *urb = mos7840_port->write_urb_pool[i]; + chars += urb->transfer_buffer_length; + } + } spin_unlock_irqrestore(&mos7840_port->pool_lock, flags); dbg("%s - returns %d", __func__, chars); return chars; diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index d232623..d8851d0 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -80,85 +80,9 @@ static void option_instat_callback(struct urb *urb); #define OPTION_PRODUCT_GTM380_MODEM 0x7201 #define HUAWEI_VENDOR_ID 0x12D1 -#define HUAWEI_PRODUCT_E600 0x1001 -#define HUAWEI_PRODUCT_E220 0x1003 -#define HUAWEI_PRODUCT_E220BIS 0x1004 -#define HUAWEI_PRODUCT_E1401 0x1401 -#define HUAWEI_PRODUCT_E1402 0x1402 -#define HUAWEI_PRODUCT_E1403 0x1403 -#define HUAWEI_PRODUCT_E1404 0x1404 -#define HUAWEI_PRODUCT_E1405 0x1405 -#define HUAWEI_PRODUCT_E1406 0x1406 -#define HUAWEI_PRODUCT_E1407 0x1407 -#define HUAWEI_PRODUCT_E1408 0x1408 -#define HUAWEI_PRODUCT_E1409 0x1409 -#define HUAWEI_PRODUCT_E140A 0x140A -#define HUAWEI_PRODUCT_E140B 0x140B -#define HUAWEI_PRODUCT_E140C 0x140C -#define HUAWEI_PRODUCT_E140D 0x140D -#define HUAWEI_PRODUCT_E140E 0x140E -#define HUAWEI_PRODUCT_E140F 0x140F -#define HUAWEI_PRODUCT_E1410 0x1410 -#define HUAWEI_PRODUCT_E1411 0x1411 -#define HUAWEI_PRODUCT_E1412 0x1412 -#define HUAWEI_PRODUCT_E1413 0x1413 -#define HUAWEI_PRODUCT_E1414 0x1414 -#define HUAWEI_PRODUCT_E1415 0x1415 -#define HUAWEI_PRODUCT_E1416 0x1416 -#define HUAWEI_PRODUCT_E1417 0x1417 -#define HUAWEI_PRODUCT_E1418 0x1418 -#define HUAWEI_PRODUCT_E1419 0x1419 -#define HUAWEI_PRODUCT_E141A 0x141A -#define HUAWEI_PRODUCT_E141B 0x141B -#define HUAWEI_PRODUCT_E141C 0x141C -#define HUAWEI_PRODUCT_E141D 0x141D -#define HUAWEI_PRODUCT_E141E 0x141E -#define HUAWEI_PRODUCT_E141F 0x141F -#define HUAWEI_PRODUCT_E1420 0x1420 -#define HUAWEI_PRODUCT_E1421 0x1421 -#define HUAWEI_PRODUCT_E1422 0x1422 -#define HUAWEI_PRODUCT_E1423 0x1423 -#define HUAWEI_PRODUCT_E1424 0x1424 -#define HUAWEI_PRODUCT_E1425 0x1425 -#define HUAWEI_PRODUCT_E1426 0x1426 -#define HUAWEI_PRODUCT_E1427 0x1427 -#define HUAWEI_PRODUCT_E1428 0x1428 -#define HUAWEI_PRODUCT_E1429 0x1429 -#define HUAWEI_PRODUCT_E142A 0x142A -#define HUAWEI_PRODUCT_E142B 0x142B -#define HUAWEI_PRODUCT_E142C 0x142C -#define HUAWEI_PRODUCT_E142D 0x142D -#define HUAWEI_PRODUCT_E142E 0x142E -#define HUAWEI_PRODUCT_E142F 0x142F -#define HUAWEI_PRODUCT_E1430 0x1430 -#define HUAWEI_PRODUCT_E1431 0x1431 -#define HUAWEI_PRODUCT_E1432 0x1432 -#define HUAWEI_PRODUCT_E1433 0x1433 -#define HUAWEI_PRODUCT_E1434 0x1434 -#define HUAWEI_PRODUCT_E1435 0x1435 -#define HUAWEI_PRODUCT_E1436 0x1436 -#define HUAWEI_PRODUCT_E1437 0x1437 -#define HUAWEI_PRODUCT_E1438 0x1438 -#define HUAWEI_PRODUCT_E1439 0x1439 -#define HUAWEI_PRODUCT_E143A 0x143A -#define HUAWEI_PRODUCT_E143B 0x143B -#define HUAWEI_PRODUCT_E143C 0x143C -#define HUAWEI_PRODUCT_E143D 0x143D -#define HUAWEI_PRODUCT_E143E 0x143E -#define HUAWEI_PRODUCT_E143F 0x143F #define HUAWEI_PRODUCT_K4505 0x1464 #define HUAWEI_PRODUCT_K3765 0x1465 -#define HUAWEI_PRODUCT_E14AC 0x14AC -#define HUAWEI_PRODUCT_K3806 0x14AE #define HUAWEI_PRODUCT_K4605 0x14C6 -#define HUAWEI_PRODUCT_K5005 0x14C8 -#define HUAWEI_PRODUCT_K3770 0x14C9 -#define HUAWEI_PRODUCT_K3771 0x14CA -#define HUAWEI_PRODUCT_K4510 0x14CB -#define HUAWEI_PRODUCT_K4511 0x14CC -#define HUAWEI_PRODUCT_ETS1220 0x1803 -#define HUAWEI_PRODUCT_E353 0x1506 -#define HUAWEI_PRODUCT_E173S 0x1C05 #define QUANTA_VENDOR_ID 0x0408 #define QUANTA_PRODUCT_Q101 0xEA02 @@ -615,104 +539,123 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(QUANTA_VENDOR_ID, QUANTA_PRODUCT_GLX) }, { USB_DEVICE(QUANTA_VENDOR_ID, QUANTA_PRODUCT_GKE) }, { USB_DEVICE(QUANTA_VENDOR_ID, QUANTA_PRODUCT_GLE) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E600, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E220, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E220BIS, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1401, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1402, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1403, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1404, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1405, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1406, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1407, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1408, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1409, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E140A, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E140B, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E140C, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E140D, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E140E, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E140F, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1410, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1411, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1412, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1413, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1414, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1415, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1416, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1417, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1418, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1419, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E141A, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E141B, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E141C, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E141D, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E141E, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E141F, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1420, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1421, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1422, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1423, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1424, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1425, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1426, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1427, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1428, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1429, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E142A, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E142B, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E142C, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E142D, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E142E, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E142F, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1430, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1431, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1432, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1433, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1434, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1435, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1436, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1437, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1438, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1439, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E143A, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E143B, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E143C, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E143D, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E143E, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E143F, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E173S, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K4505, 0xff, 0xff, 0xff), .driver_info = (kernel_ulong_t) &huawei_cdc12_blacklist }, { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K3765, 0xff, 0xff, 0xff), .driver_info = (kernel_ulong_t) &huawei_cdc12_blacklist }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_ETS1220, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E14AC, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K3806, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K4605, 0xff, 0xff, 0xff), .driver_info = (kernel_ulong_t) &huawei_cdc12_blacklist }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K4605, 0xff, 0x01, 0x31) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K4605, 0xff, 0x01, 0x32) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K5005, 0xff, 0x01, 0x31) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K5005, 0xff, 0x01, 0x32) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K5005, 0xff, 0x01, 0x33) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K3770, 0xff, 0x02, 0x31) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K3770, 0xff, 0x02, 0x32) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K3771, 0xff, 0x02, 0x31) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K3771, 0xff, 0x02, 0x32) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K4510, 0xff, 0x01, 0x31) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K4510, 0xff, 0x01, 0x32) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K4511, 0xff, 0x01, 0x31) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K4511, 0xff, 0x01, 0x32) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x01) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x02) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x03) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x10) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x12) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x13) }, - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x02, 0x01) }, /* E398 3G Modem */ - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x02, 0x02) }, /* E398 3G PC UI Interface */ - { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x02, 0x03) }, /* E398 3G Application Interface */ + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0xff, 0xff) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x01) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x02) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x03) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x04) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x05) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x06) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x0A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x0B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x0D) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x0E) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x0F) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x10) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x12) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x13) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x14) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x15) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x17) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x18) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x19) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x1A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x1B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x1C) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x31) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x32) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x33) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x34) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x35) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x36) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x3A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x3B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x3D) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x3E) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x3F) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x48) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x49) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x4A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x4B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x4C) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x61) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x62) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x63) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x64) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x65) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x66) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x6A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x6B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x6D) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x6E) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x6F) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x78) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x79) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x7A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x7B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x7C) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x01) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x02) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x03) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x04) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x05) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x06) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x0A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x0B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x0D) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x0E) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x0F) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x10) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x12) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x13) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x14) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x15) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x17) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x18) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x19) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x1A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x1B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x1C) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x31) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x32) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x33) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x34) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x35) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x36) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x3A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x3B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x3D) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x3E) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x3F) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x48) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x49) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x4A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x4B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x4C) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x61) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x62) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x63) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x64) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x65) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x66) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x6A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x6B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x6D) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x6E) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x6F) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x78) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x79) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x7A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x7B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x7C) }, + + { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_V640) }, { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_V620) }, { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_V740) }, @@ -939,6 +882,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1008, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1010, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1012, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1018, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&net_intf3_blacklist }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1057, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1058, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1059, 0xff, 0xff, 0xff) }, diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index 7ec1409..8006a28 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -212,10 +212,17 @@ static noinline int run_ordered_completions(struct btrfs_workers *workers, work->ordered_func(work); - /* now take the lock again and call the freeing code */ + /* now take the lock again and drop our item from the list */ spin_lock(&workers->order_lock); list_del(&work->order_list); + spin_unlock(&workers->order_lock); + + /* + * we don't want to call the ordered free functions + * with the lock held though + */ work->ordered_free(work); + spin_lock(&workers->order_lock); } spin_unlock(&workers->order_lock); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 1ac8db5d..57106a9 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -801,7 +801,8 @@ static int btree_submit_bio_hook(struct inode *inode, int rw, struct bio *bio, #ifdef CONFIG_MIGRATION static int btree_migratepage(struct address_space *mapping, - struct page *newpage, struct page *page) + struct page *newpage, struct page *page, + enum migrate_mode mode) { /* * we can't safely write a btree page from here, @@ -816,7 +817,7 @@ static int btree_migratepage(struct address_space *mapping, if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL)) return -EAGAIN; - return migrate_page(mapping, newpage, page); + return migrate_page(mapping, newpage, page, mode); } #endif diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 6751e74..c71032b 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -85,9 +85,12 @@ cifs_readdir_lookup(struct dentry *parent, struct qstr *name, dentry = d_lookup(parent, name); if (dentry) { - /* FIXME: check for inode number changes? */ - if (dentry->d_inode != NULL) + inode = dentry->d_inode; + /* update inode in place if i_ino didn't change */ + if (inode && CIFS_I(inode)->uniqueid == fattr->cf_uniqueid) { + cifs_fattr_to_inode(inode, fattr); return dentry; + } d_drop(dentry); dput(dentry); } diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 264f694..ebe95f5 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -514,7 +514,8 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb) if (bitmap_bh == NULL) continue; - x = ext4_count_free(bitmap_bh, sb->s_blocksize); + x = ext4_count_free(bitmap_bh->b_data, + EXT4_BLOCKS_PER_GROUP(sb) / 8); printk(KERN_DEBUG "group %u: stored = %d, counted = %u\n", i, ext4_free_blks_count(sb, gdp), x); bitmap_count += x; diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c index fa3af81..012faaa 100644 --- a/fs/ext4/bitmap.c +++ b/fs/ext4/bitmap.c @@ -15,15 +15,13 @@ static const int nibblemap[] = {4, 3, 3, 2, 3, 2, 2, 1, 3, 2, 2, 1, 2, 1, 1, 0}; -unsigned int ext4_count_free(struct buffer_head *map, unsigned int numchars) +unsigned int ext4_count_free(char *bitmap, unsigned int numchars) { unsigned int i, sum = 0; - if (!map) - return 0; for (i = 0; i < numchars; i++) - sum += nibblemap[map->b_data[i] & 0xf] + - nibblemap[(map->b_data[i] >> 4) & 0xf]; + sum += nibblemap[bitmap[i] & 0xf] + + nibblemap[(bitmap[i] >> 4) & 0xf]; return sum; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 1a34c1c..e0113aa 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1713,7 +1713,7 @@ struct mmpd_data { # define NORET_AND noreturn, /* bitmap.c */ -extern unsigned int ext4_count_free(struct buffer_head *, unsigned); +extern unsigned int ext4_count_free(char *bitmap, unsigned numchars); /* balloc.c */ extern unsigned int ext4_block_group(struct super_block *sb, diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 412469b..29272de 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -1193,7 +1193,8 @@ unsigned long ext4_count_free_inodes(struct super_block *sb) if (!bitmap_bh) continue; - x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8); + x = ext4_count_free(bitmap_bh->b_data, + EXT4_INODES_PER_GROUP(sb) / 8); printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n", (unsigned long) i, ext4_free_inodes_count(sb, gdp), x); bitmap_count += x; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index c1e6a72..18fee6d 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1134,6 +1134,15 @@ void ext4_da_update_reserve_space(struct inode *inode, used = ei->i_reserved_data_blocks; } + if (unlikely(ei->i_allocated_meta_blocks > ei->i_reserved_meta_blocks)) { + ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, allocated %d " + "with only %d reserved metadata blocks\n", __func__, + inode->i_ino, ei->i_allocated_meta_blocks, + ei->i_reserved_meta_blocks); + WARN_ON(1); + ei->i_allocated_meta_blocks = ei->i_reserved_meta_blocks; + } + /* Update per-inode reservations */ ei->i_reserved_data_blocks -= used; ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 113b107..489d406 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -860,6 +860,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) ei->i_reserved_meta_blocks = 0; ei->i_allocated_meta_blocks = 0; ei->i_da_metadata_calc_len = 0; + ei->i_da_metadata_calc_last_lblock = 0; spin_lock_init(&(ei->i_block_reservation_lock)); #ifdef CONFIG_QUOTA ei->i_reserved_quota = 0; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 82a6646..79fca8d 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1710,7 +1710,7 @@ static int fuse_verify_ioctl_iov(struct iovec *iov, size_t count) size_t n; u32 max = FUSE_MAX_PAGES_PER_REQ << PAGE_SHIFT; - for (n = 0; n < count; n++) { + for (n = 0; n < count; n++, iov++) { if (iov->iov_len > (size_t) max) return -ENOMEM; max -= iov->iov_len; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 8b0c875..6327a06 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -568,7 +568,8 @@ static int hugetlbfs_set_page_dirty(struct page *page) } static int hugetlbfs_migrate_page(struct address_space *mapping, - struct page *newpage, struct page *page) + struct page *newpage, struct page *page, + enum migrate_mode mode) { int rc; @@ -315,7 +315,7 @@ static int flock_make_lock(struct file *filp, struct file_lock **lock, return 0; } -static int assign_type(struct file_lock *fl, int type) +static int assign_type(struct file_lock *fl, long type) { switch (type) { case F_RDLCK: @@ -452,7 +452,7 @@ static const struct lock_manager_operations lease_manager_ops = { /* * Initialize a lease, use the default lock manager operations */ -static int lease_init(struct file *filp, int type, struct file_lock *fl) +static int lease_init(struct file *filp, long type, struct file_lock *fl) { if (assign_type(fl, type) != 0) return -EINVAL; @@ -470,7 +470,7 @@ static int lease_init(struct file *filp, int type, struct file_lock *fl) } /* Allocate a file_lock initialised to this type of lease */ -static struct file_lock *lease_alloc(struct file *filp, int type) +static struct file_lock *lease_alloc(struct file *filp, long type) { struct file_lock *fl = locks_alloc_lock(); int error = -ENOMEM; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index dd2f130..6c6e2c4 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -493,8 +493,11 @@ static int nfs_release_page(struct page *page, gfp_t gfp) dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page); - /* Only do I/O if gfp is a superset of GFP_KERNEL */ - if (mapping && (gfp & GFP_KERNEL) == GFP_KERNEL) { + /* Only do I/O if gfp is a superset of GFP_KERNEL, and we're not + * doing this memory reclaim for a fs-related allocation. + */ + if (mapping && (gfp & GFP_KERNEL) == GFP_KERNEL && + !(current->flags & PF_FSTRANS)) { int how = FLUSH_SYNC; /* Don't let kswapd deadlock waiting for OOM RPC calls */ diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 2a55347..4f10d81 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -315,7 +315,7 @@ void nfs_commit_release_pages(struct nfs_write_data *data); #ifdef CONFIG_MIGRATION extern int nfs_migrate_page(struct address_space *, - struct page *, struct page *); + struct page *, struct page *, enum migrate_mode); #else #define nfs_migrate_page NULL #endif diff --git a/fs/nfs/write.c b/fs/nfs/write.c index f2f80c0..58bb999 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1662,7 +1662,7 @@ out_error: #ifdef CONFIG_MIGRATION int nfs_migrate_page(struct address_space *mapping, struct page *newpage, - struct page *page) + struct page *page, enum migrate_mode mode) { /* * If PagePrivate is set, then the page is currently associated with @@ -1677,7 +1677,7 @@ int nfs_migrate_page(struct address_space *mapping, struct page *newpage, nfs_fscache_release_page(page, GFP_KERNEL); - return migrate_page(mapping, newpage, page); + return migrate_page(mapping, newpage, page, mode); } #endif diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 6c74097..f91d589 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2010,7 +2010,7 @@ out_acl: if (bmval0 & FATTR4_WORD0_CASE_INSENSITIVE) { if ((buflen -= 4) < 0) goto out_resource; - WRITE32(1); + WRITE32(0); } if (bmval0 & FATTR4_WORD0_CASE_PRESERVING) { if ((buflen -= 4) < 0) diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index 3e65427..0d1c9bd 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -182,7 +182,7 @@ static int nilfs_ioctl_change_cpmode(struct inode *inode, struct file *filp, if (copy_from_user(&cpmode, argp, sizeof(cpmode))) goto out; - down_read(&inode->i_sb->s_umount); + mutex_lock(&nilfs->ns_snapshot_mount_mutex); nilfs_transaction_begin(inode->i_sb, &ti, 0); ret = nilfs_cpfile_change_cpmode( @@ -192,7 +192,7 @@ static int nilfs_ioctl_change_cpmode(struct inode *inode, struct file *filp, else nilfs_transaction_commit(inode->i_sb); /* never fails */ - up_read(&inode->i_sb->s_umount); + mutex_unlock(&nilfs->ns_snapshot_mount_mutex); out: mnt_drop_write(filp->f_path.mnt); return ret; diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 8351c44..97bfbdd 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -951,6 +951,8 @@ static int nilfs_attach_snapshot(struct super_block *s, __u64 cno, struct nilfs_root *root; int ret; + mutex_lock(&nilfs->ns_snapshot_mount_mutex); + down_read(&nilfs->ns_segctor_sem); ret = nilfs_cpfile_is_snapshot(nilfs->ns_cpfile, cno); up_read(&nilfs->ns_segctor_sem); @@ -975,6 +977,7 @@ static int nilfs_attach_snapshot(struct super_block *s, __u64 cno, ret = nilfs_get_root_dentry(s, root, root_dentry); nilfs_put_root(root); out: + mutex_unlock(&nilfs->ns_snapshot_mount_mutex); return ret; } diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 35a8970..1c98f53 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -76,6 +76,7 @@ struct the_nilfs *alloc_nilfs(struct block_device *bdev) nilfs->ns_bdev = bdev; atomic_set(&nilfs->ns_ndirtyblks, 0); init_rwsem(&nilfs->ns_sem); + mutex_init(&nilfs->ns_snapshot_mount_mutex); INIT_LIST_HEAD(&nilfs->ns_dirty_files); INIT_LIST_HEAD(&nilfs->ns_gc_inodes); spin_lock_init(&nilfs->ns_inode_lock); diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h index 9992b11..de7435f 100644 --- a/fs/nilfs2/the_nilfs.h +++ b/fs/nilfs2/the_nilfs.h @@ -47,6 +47,7 @@ enum { * @ns_flags: flags * @ns_bdev: block device * @ns_sem: semaphore for shared states + * @ns_snapshot_mount_mutex: mutex to protect snapshot mounts * @ns_sbh: buffer heads of on-disk super blocks * @ns_sbp: pointers to super block data * @ns_sbwtime: previous write time of super block @@ -99,6 +100,7 @@ struct the_nilfs { struct block_device *ns_bdev; struct rw_semaphore ns_sem; + struct mutex ns_snapshot_mount_mutex; /* * used for diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c index c606f01..1250016 100644 --- a/fs/ubifs/sb.c +++ b/fs/ubifs/sb.c @@ -715,8 +715,12 @@ static int fixup_free_space(struct ubifs_info *c) lnum = ubifs_next_log_lnum(c, lnum); } - /* Fixup the current log head */ - err = fixup_leb(c, c->lhead_lnum, c->lhead_offs); + /* + * Fixup the log head which contains the only a CS node at the + * beginning. + */ + err = fixup_leb(c, c->lhead_lnum, + ALIGN(UBIFS_CS_NODE_SZ, c->min_io_size)); if (err) goto out; diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 97f1ca7..111797a 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -66,8 +66,9 @@ enum { /* migration should happen before other stuff but after perf */ CPU_PRI_PERF = 20, CPU_PRI_MIGRATION = 10, - /* prepare workqueues for other notifiers */ - CPU_PRI_WORKQUEUE = 5, + /* bring up workqueues before normal notifiers and down after */ + CPU_PRI_WORKQUEUE_UP = 5, + CPU_PRI_WORKQUEUE_DOWN = -5, }; #ifdef CONFIG_SMP diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index e9eaec5..7a7e5fd 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -89,42 +89,33 @@ extern void rebuild_sched_domains(void); extern void cpuset_print_task_mems_allowed(struct task_struct *p); /* - * reading current mems_allowed and mempolicy in the fastpath must protected - * by get_mems_allowed() + * get_mems_allowed is required when making decisions involving mems_allowed + * such as during page allocation. mems_allowed can be updated in parallel + * and depending on the new value an operation can fail potentially causing + * process failure. A retry loop with get_mems_allowed and put_mems_allowed + * prevents these artificial failures. */ -static inline void get_mems_allowed(void) +static inline unsigned int get_mems_allowed(void) { - current->mems_allowed_change_disable++; - - /* - * ensure that reading mems_allowed and mempolicy happens after the - * update of ->mems_allowed_change_disable. - * - * the write-side task finds ->mems_allowed_change_disable is not 0, - * and knows the read-side task is reading mems_allowed or mempolicy, - * so it will clear old bits lazily. - */ - smp_mb(); + return read_seqcount_begin(¤t->mems_allowed_seq); } -static inline void put_mems_allowed(void) +/* + * If this returns false, the operation that took place after get_mems_allowed + * may have failed. It is up to the caller to retry the operation if + * appropriate. + */ +static inline bool put_mems_allowed(unsigned int seq) { - /* - * ensure that reading mems_allowed and mempolicy before reducing - * mems_allowed_change_disable. - * - * the write-side task will know that the read-side task is still - * reading mems_allowed or mempolicy, don't clears old bits in the - * nodemask. - */ - smp_mb(); - --ACCESS_ONCE(current->mems_allowed_change_disable); + return !read_seqcount_retry(¤t->mems_allowed_seq, seq); } static inline void set_mems_allowed(nodemask_t nodemask) { task_lock(current); + write_seqcount_begin(¤t->mems_allowed_seq); current->mems_allowed = nodemask; + write_seqcount_end(¤t->mems_allowed_seq); task_unlock(current); } @@ -234,12 +225,14 @@ static inline void set_mems_allowed(nodemask_t nodemask) { } -static inline void get_mems_allowed(void) +static inline unsigned int get_mems_allowed(void) { + return 0; } -static inline void put_mems_allowed(void) +static inline bool put_mems_allowed(unsigned int seq) { + return true; } #endif /* !CONFIG_CPUSETS */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 96b1035..212ea7b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -523,6 +523,7 @@ enum positive_aop_returns { struct page; struct address_space; struct writeback_control; +enum migrate_mode; struct iov_iter { const struct iovec *iov; @@ -607,9 +608,12 @@ struct address_space_operations { loff_t offset, unsigned long nr_segs); int (*get_xip_mem)(struct address_space *, pgoff_t, int, void **, unsigned long *); - /* migrate the contents of a page to the specified target */ + /* + * migrate the contents of a page to the specified target. If sync + * is false, it must not block. + */ int (*migratepage) (struct address_space *, - struct page *, struct page *); + struct page *, struct page *, enum migrate_mode); int (*launder_page) (struct page *); int (*is_partially_uptodate) (struct page *, read_descriptor_t *, unsigned long); @@ -2478,7 +2482,8 @@ extern int generic_check_addressable(unsigned, u64); #ifdef CONFIG_MIGRATION extern int buffer_migrate_page(struct address_space *, - struct page *, struct page *); + struct page *, struct page *, + enum migrate_mode); #else #define buffer_migrate_page NULL #endif diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 580f70c..5e41a8e 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -30,6 +30,13 @@ extern struct fs_struct init_fs; #define INIT_THREADGROUP_FORK_LOCK(sig) #endif +#ifdef CONFIG_CPUSETS +#define INIT_CPUSET_SEQ \ + .mems_allowed_seq = SEQCNT_ZERO, +#else +#define INIT_CPUSET_SEQ +#endif + #define INIT_SIGNALS(sig) { \ .nr_threads = 1, \ .wait_chldexit = __WAIT_QUEUE_HEAD_INITIALIZER(sig.wait_chldexit),\ @@ -193,6 +200,7 @@ extern struct cred init_cred; INIT_FTRACE_GRAPH \ INIT_TRACE_RECURSION \ INIT_TASK_RCU_PREEMPT(tsk) \ + INIT_CPUSET_SEQ \ } diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 2d921b3..d0a3100 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -38,7 +38,6 @@ struct timer_rand_state; */ struct irq_desc { struct irq_data irq_data; - struct timer_rand_state *timer_rand_state; unsigned int __percpu *kstat_irqs; irq_flow_handler_t handle_irq; #ifdef CONFIG_IRQ_PREFLOW_FASTEOI diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 313a00e..4a8da84 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -35,7 +35,8 @@ enum mem_cgroup_page_stat_item { extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, struct list_head *dst, unsigned long *scanned, int order, - int mode, struct zone *z, + isolate_mode_t mode, + struct zone *z, struct mem_cgroup *mem_cont, int active, int file); diff --git a/include/linux/mfd/ezx-pcap.h b/include/linux/mfd/ezx-pcap.h index 40c37216..32a1b5c 100644 --- a/include/linux/mfd/ezx-pcap.h +++ b/include/linux/mfd/ezx-pcap.h @@ -16,6 +16,7 @@ struct pcap_subdev { struct pcap_platform_data { unsigned int irq_base; unsigned int config; + int gpio; void (*init) (void *); /* board specific init */ int num_subdevs; struct pcap_subdev *subdevs; diff --git a/include/linux/migrate.h b/include/linux/migrate.h index e39aeec..eaf8674 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -6,18 +6,31 @@ typedef struct page *new_page_t(struct page *, unsigned long private, int **); +/* + * MIGRATE_ASYNC means never block + * MIGRATE_SYNC_LIGHT in the current implementation means to allow blocking + * on most operations but not ->writepage as the potential stall time + * is too significant + * MIGRATE_SYNC will block when migrating pages + */ +enum migrate_mode { + MIGRATE_ASYNC, + MIGRATE_SYNC_LIGHT, + MIGRATE_SYNC, +}; + #ifdef CONFIG_MIGRATION #define PAGE_MIGRATION 1 extern void putback_lru_pages(struct list_head *l); extern int migrate_page(struct address_space *, - struct page *, struct page *); + struct page *, struct page *, enum migrate_mode); extern int migrate_pages(struct list_head *l, new_page_t x, unsigned long private, bool offlining, - bool sync); + enum migrate_mode mode); extern int migrate_huge_pages(struct list_head *l, new_page_t x, unsigned long private, bool offlining, - bool sync); + enum migrate_mode mode); extern int fail_migrate_page(struct address_space *, struct page *, struct page *); @@ -36,10 +49,10 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, static inline void putback_lru_pages(struct list_head *l) {} static inline int migrate_pages(struct list_head *l, new_page_t x, unsigned long private, bool offlining, - bool sync) { return -ENOSYS; } + enum migrate_mode mode) { return -ENOSYS; } static inline int migrate_huge_pages(struct list_head *l, new_page_t x, unsigned long private, bool offlining, - bool sync) { return -ENOSYS; } + enum migrate_mode mode) { return -ENOSYS; } static inline int migrate_prep(void) { return -ENOSYS; } static inline int migrate_prep_local(void) { return -ENOSYS; } diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index aa2d80b..b32f3f9 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -158,6 +158,20 @@ static inline int is_unevictable_lru(enum lru_list l) return (l == LRU_UNEVICTABLE); } +/* Isolate inactive pages */ +#define ISOLATE_INACTIVE ((__force isolate_mode_t)0x1) +/* Isolate active pages */ +#define ISOLATE_ACTIVE ((__force isolate_mode_t)0x2) +/* Isolate clean file */ +#define ISOLATE_CLEAN ((__force isolate_mode_t)0x4) +/* Isolate unmapped file */ +#define ISOLATE_UNMAPPED ((__force isolate_mode_t)0x8) +/* Isolate for asynchronous migration */ +#define ISOLATE_ASYNC_MIGRATE ((__force isolate_mode_t)0x10) + +/* LRU Isolation modes. */ +typedef unsigned __bitwise__ isolate_mode_t; + enum zone_watermarks { WMARK_MIN, WMARK_LOW, diff --git a/include/linux/random.h b/include/linux/random.h index d13059f..ac621ce 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -48,13 +48,13 @@ struct rnd_state { #ifdef __KERNEL__ -extern void rand_initialize_irq(int irq); - +extern void add_device_randomness(const void *, unsigned int); extern void add_input_randomness(unsigned int type, unsigned int code, unsigned int value); -extern void add_interrupt_randomness(int irq); +extern void add_interrupt_randomness(int irq, int irq_flags); extern void get_random_bytes(void *buf, int nbytes); +extern void get_random_bytes_arch(void *buf, int nbytes); void generate_random_uuid(unsigned char uuid_out[16]); #ifndef MODULE @@ -91,6 +91,19 @@ static inline void prandom32_seed(struct rnd_state *state, u64 seed) state->s3 = __seed(i, 15); } +#ifdef CONFIG_ARCH_RANDOM +# include <asm/archrandom.h> +#else +static inline int arch_get_random_long(unsigned long *v) +{ + return 0; +} +static inline int arch_get_random_int(unsigned int *v) +{ + return 0; +} +#endif + #endif /* __KERNEL___ */ #endif /* _LINUX_RANDOM_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 35895e3..189b442 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1484,7 +1484,7 @@ struct task_struct { #endif #ifdef CONFIG_CPUSETS nodemask_t mems_allowed; /* Protected by alloc_lock */ - int mems_allowed_change_disable; + seqcount_t mems_allowed_seq; /* Seqence no to catch updates */ int cpuset_mem_spread_rotor; int cpuset_slab_spread_rotor; #endif diff --git a/include/linux/swap.h b/include/linux/swap.h index a273468..e73799d 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -243,11 +243,6 @@ static inline void lru_cache_add_file(struct page *page) __lru_cache_add(page, LRU_INACTIVE_FILE); } -/* LRU Isolation modes. */ -#define ISOLATE_INACTIVE 0 /* Isolate inactive pages. */ -#define ISOLATE_ACTIVE 1 /* Isolate active pages. */ -#define ISOLATE_BOTH 2 /* Isolate both active and inactive pages. */ - /* linux/mm/vmscan.c */ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); @@ -259,7 +254,7 @@ extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem, unsigned int swappiness, struct zone *zone, unsigned long *nr_scanned); -extern int __isolate_lru_page(struct page *page, int mode, int file); +extern int __isolate_lru_page(struct page *page, isolate_mode_t mode, int file); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; extern int remove_mapping(struct address_space *mapping, struct page *page); diff --git a/include/linux/usb.h b/include/linux/usb.h index b08e04c..6cd1576 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -757,6 +757,27 @@ static inline int usb_make_path(struct usb_device *dev, char *buf, size_t size) .bInterfaceSubClass = (sc), \ .bInterfaceProtocol = (pr) +/** + * USB_VENDOR_AND_INTERFACE_INFO - describe a specific usb vendor with a class of usb interfaces + * @vend: the 16 bit USB Vendor ID + * @cl: bInterfaceClass value + * @sc: bInterfaceSubClass value + * @pr: bInterfaceProtocol value + * + * This macro is used to create a struct usb_device_id that matches a + * specific vendor with a specific class of interfaces. + * + * This is especially useful when explicitly matching devices that have + * vendor specific bDeviceClass values, but standards-compliant interfaces. + */ +#define USB_VENDOR_AND_INTERFACE_INFO(vend, cl, sc, pr) \ + .match_flags = USB_DEVICE_ID_MATCH_INT_INFO \ + | USB_DEVICE_ID_MATCH_VENDOR, \ + .idVendor = (vend), \ + .bInterfaceClass = (cl), \ + .bInterfaceSubClass = (sc), \ + .bInterfaceProtocol = (pr) + /* ----------------------------------------------------------------------- */ /* Stuff for dynamic usb ids */ diff --git a/include/trace/events/random.h b/include/trace/events/random.h new file mode 100644 index 0000000..422df19 --- /dev/null +++ b/include/trace/events/random.h @@ -0,0 +1,134 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM random + +#if !defined(_TRACE_RANDOM_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_RANDOM_H + +#include <linux/writeback.h> +#include <linux/tracepoint.h> + +DECLARE_EVENT_CLASS(random__mix_pool_bytes, + TP_PROTO(const char *pool_name, int bytes, unsigned long IP), + + TP_ARGS(pool_name, bytes, IP), + + TP_STRUCT__entry( + __field( const char *, pool_name ) + __field( int, bytes ) + __field(unsigned long, IP ) + ), + + TP_fast_assign( + __entry->pool_name = pool_name; + __entry->bytes = bytes; + __entry->IP = IP; + ), + + TP_printk("%s pool: bytes %d caller %pF", + __entry->pool_name, __entry->bytes, (void *)__entry->IP) +); + +DEFINE_EVENT(random__mix_pool_bytes, mix_pool_bytes, + TP_PROTO(const char *pool_name, int bytes, unsigned long IP), + + TP_ARGS(pool_name, bytes, IP) +); + +DEFINE_EVENT(random__mix_pool_bytes, mix_pool_bytes_nolock, + TP_PROTO(const char *pool_name, int bytes, unsigned long IP), + + TP_ARGS(pool_name, bytes, IP) +); + +TRACE_EVENT(credit_entropy_bits, + TP_PROTO(const char *pool_name, int bits, int entropy_count, + int entropy_total, unsigned long IP), + + TP_ARGS(pool_name, bits, entropy_count, entropy_total, IP), + + TP_STRUCT__entry( + __field( const char *, pool_name ) + __field( int, bits ) + __field( int, entropy_count ) + __field( int, entropy_total ) + __field(unsigned long, IP ) + ), + + TP_fast_assign( + __entry->pool_name = pool_name; + __entry->bits = bits; + __entry->entropy_count = entropy_count; + __entry->entropy_total = entropy_total; + __entry->IP = IP; + ), + + TP_printk("%s pool: bits %d entropy_count %d entropy_total %d " + "caller %pF", __entry->pool_name, __entry->bits, + __entry->entropy_count, __entry->entropy_total, + (void *)__entry->IP) +); + +TRACE_EVENT(get_random_bytes, + TP_PROTO(int nbytes, unsigned long IP), + + TP_ARGS(nbytes, IP), + + TP_STRUCT__entry( + __field( int, nbytes ) + __field(unsigned long, IP ) + ), + + TP_fast_assign( + __entry->nbytes = nbytes; + __entry->IP = IP; + ), + + TP_printk("nbytes %d caller %pF", __entry->nbytes, (void *)__entry->IP) +); + +DECLARE_EVENT_CLASS(random__extract_entropy, + TP_PROTO(const char *pool_name, int nbytes, int entropy_count, + unsigned long IP), + + TP_ARGS(pool_name, nbytes, entropy_count, IP), + + TP_STRUCT__entry( + __field( const char *, pool_name ) + __field( int, nbytes ) + __field( int, entropy_count ) + __field(unsigned long, IP ) + ), + + TP_fast_assign( + __entry->pool_name = pool_name; + __entry->nbytes = nbytes; + __entry->entropy_count = entropy_count; + __entry->IP = IP; + ), + + TP_printk("%s pool: nbytes %d entropy_count %d caller %pF", + __entry->pool_name, __entry->nbytes, __entry->entropy_count, + (void *)__entry->IP) +); + + +DEFINE_EVENT(random__extract_entropy, extract_entropy, + TP_PROTO(const char *pool_name, int nbytes, int entropy_count, + unsigned long IP), + + TP_ARGS(pool_name, nbytes, entropy_count, IP) +); + +DEFINE_EVENT(random__extract_entropy, extract_entropy_user, + TP_PROTO(const char *pool_name, int nbytes, int entropy_count, + unsigned long IP), + + TP_ARGS(pool_name, nbytes, entropy_count, IP) +); + + + +#endif /* _TRACE_RANDOM_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index b2c33bd..edc4b3d 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -179,6 +179,83 @@ DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_softlimit_re TP_ARGS(nr_reclaimed) ); +TRACE_EVENT(mm_shrink_slab_start, + TP_PROTO(struct shrinker *shr, struct shrink_control *sc, + long nr_objects_to_shrink, unsigned long pgs_scanned, + unsigned long lru_pgs, unsigned long cache_items, + unsigned long long delta, unsigned long total_scan), + + TP_ARGS(shr, sc, nr_objects_to_shrink, pgs_scanned, lru_pgs, + cache_items, delta, total_scan), + + TP_STRUCT__entry( + __field(struct shrinker *, shr) + __field(void *, shrink) + __field(long, nr_objects_to_shrink) + __field(gfp_t, gfp_flags) + __field(unsigned long, pgs_scanned) + __field(unsigned long, lru_pgs) + __field(unsigned long, cache_items) + __field(unsigned long long, delta) + __field(unsigned long, total_scan) + ), + + TP_fast_assign( + __entry->shr = shr; + __entry->shrink = shr->shrink; + __entry->nr_objects_to_shrink = nr_objects_to_shrink; + __entry->gfp_flags = sc->gfp_mask; + __entry->pgs_scanned = pgs_scanned; + __entry->lru_pgs = lru_pgs; + __entry->cache_items = cache_items; + __entry->delta = delta; + __entry->total_scan = total_scan; + ), + + TP_printk("%pF %p: objects to shrink %ld gfp_flags %s pgs_scanned %ld lru_pgs %ld cache items %ld delta %lld total_scan %ld", + __entry->shrink, + __entry->shr, + __entry->nr_objects_to_shrink, + show_gfp_flags(__entry->gfp_flags), + __entry->pgs_scanned, + __entry->lru_pgs, + __entry->cache_items, + __entry->delta, + __entry->total_scan) +); + +TRACE_EVENT(mm_shrink_slab_end, + TP_PROTO(struct shrinker *shr, int shrinker_retval, + long unused_scan_cnt, long new_scan_cnt), + + TP_ARGS(shr, shrinker_retval, unused_scan_cnt, new_scan_cnt), + + TP_STRUCT__entry( + __field(struct shrinker *, shr) + __field(void *, shrink) + __field(long, unused_scan) + __field(long, new_scan) + __field(int, retval) + __field(long, total_scan) + ), + + TP_fast_assign( + __entry->shr = shr; + __entry->shrink = shr->shrink; + __entry->unused_scan = unused_scan_cnt; + __entry->new_scan = new_scan_cnt; + __entry->retval = shrinker_retval; + __entry->total_scan = new_scan_cnt - unused_scan_cnt; + ), + + TP_printk("%pF %p: unused scan count %ld new scan count %ld total_scan %ld last shrinker return val %d", + __entry->shrink, + __entry->shr, + __entry->unused_scan, + __entry->new_scan, + __entry->total_scan, + __entry->retval) +); DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template, @@ -189,7 +266,7 @@ DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template, unsigned long nr_lumpy_taken, unsigned long nr_lumpy_dirty, unsigned long nr_lumpy_failed, - int isolate_mode), + isolate_mode_t isolate_mode), TP_ARGS(order, nr_requested, nr_scanned, nr_taken, nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed, isolate_mode), @@ -201,7 +278,7 @@ DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template, __field(unsigned long, nr_lumpy_taken) __field(unsigned long, nr_lumpy_dirty) __field(unsigned long, nr_lumpy_failed) - __field(int, isolate_mode) + __field(isolate_mode_t, isolate_mode) ), TP_fast_assign( @@ -235,7 +312,7 @@ DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_lru_isolate, unsigned long nr_lumpy_taken, unsigned long nr_lumpy_dirty, unsigned long nr_lumpy_failed, - int isolate_mode), + isolate_mode_t isolate_mode), TP_ARGS(order, nr_requested, nr_scanned, nr_taken, nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed, isolate_mode) @@ -250,7 +327,7 @@ DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_memcg_isolate, unsigned long nr_lumpy_taken, unsigned long nr_lumpy_dirty, unsigned long nr_lumpy_failed, - int isolate_mode), + isolate_mode_t isolate_mode), TP_ARGS(order, nr_requested, nr_scanned, nr_taken, nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed, isolate_mode) diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 9c9b754..b2e84bd 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -123,6 +123,19 @@ static inline struct cpuset *task_cs(struct task_struct *task) struct cpuset, css); } +#ifdef CONFIG_NUMA +static inline bool task_has_mempolicy(struct task_struct *task) +{ + return task->mempolicy; +} +#else +static inline bool task_has_mempolicy(struct task_struct *task) +{ + return false; +} +#endif + + /* bits in struct cpuset flags field */ typedef enum { CS_CPU_EXCLUSIVE, @@ -949,7 +962,8 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, static void cpuset_change_task_nodemask(struct task_struct *tsk, nodemask_t *newmems) { -repeat: + bool need_loop; + /* * Allow tasks that have access to memory reserves because they have * been OOM killed to get memory anywhere. @@ -960,46 +974,27 @@ repeat: return; task_lock(tsk); - nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems); - mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1); - - /* - * ensure checking ->mems_allowed_change_disable after setting all new - * allowed nodes. - * - * the read-side task can see an nodemask with new allowed nodes and - * old allowed nodes. and if it allocates page when cpuset clears newly - * disallowed ones continuous, it can see the new allowed bits. - * - * And if setting all new allowed nodes is after the checking, setting - * all new allowed nodes and clearing newly disallowed ones will be done - * continuous, and the read-side task may find no node to alloc page. + * Determine if a loop is necessary if another thread is doing + * get_mems_allowed(). If at least one node remains unchanged and + * tsk does not have a mempolicy, then an empty nodemask will not be + * possible when mems_allowed is larger than a word. */ - smp_mb(); + need_loop = task_has_mempolicy(tsk) || + !nodes_intersects(*newmems, tsk->mems_allowed); - /* - * Allocation of memory is very fast, we needn't sleep when waiting - * for the read-side. - */ - while (ACCESS_ONCE(tsk->mems_allowed_change_disable)) { - task_unlock(tsk); - if (!task_curr(tsk)) - yield(); - goto repeat; - } + if (need_loop) + write_seqcount_begin(&tsk->mems_allowed_seq); - /* - * ensure checking ->mems_allowed_change_disable before clearing all new - * disallowed nodes. - * - * if clearing newly disallowed bits before the checking, the read-side - * task may find no node to alloc page. - */ - smp_mb(); + nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems); + mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1); mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP2); tsk->mems_allowed = *newmems; + + if (need_loop) + write_seqcount_end(&tsk->mems_allowed_seq); + task_unlock(tsk); } diff --git a/kernel/fork.c b/kernel/fork.c index fa6030d..158ca4f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1001,6 +1001,9 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) #ifdef CONFIG_CGROUPS init_rwsem(&sig->threadgroup_fork_lock); #endif +#ifdef CONFIG_CPUSETS + seqcount_init(&tsk->mems_allowed_seq); +#endif sig->oom_adj = current->signal->oom_adj; sig->oom_score_adj = current->signal->oom_score_adj; diff --git a/kernel/futex.c b/kernel/futex.c index b2d51a7..e45efe7 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -2231,11 +2231,11 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb, * @uaddr2: the pi futex we will take prior to returning to user-space * * The caller will wait on uaddr and will be requeued by futex_requeue() to - * uaddr2 which must be PI aware. Normal wakeup will wake on uaddr2 and - * complete the acquisition of the rt_mutex prior to returning to userspace. - * This ensures the rt_mutex maintains an owner when it has waiters; without - * one, the pi logic wouldn't know which task to boost/deboost, if there was a - * need to. + * uaddr2 which must be PI aware and unique from uaddr. Normal wakeup will wake + * on uaddr2 and complete the acquisition of the rt_mutex prior to returning to + * userspace. This ensures the rt_mutex maintains an owner when it has waiters; + * without one, the pi logic would not know which task to boost/deboost, if + * there was a need to. * * We call schedule in futex_wait_queue_me() when we enqueue and return there * via the following: @@ -2272,6 +2272,9 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, struct futex_q q = futex_q_init; int res, ret; + if (uaddr == uaddr2) + return -EINVAL; + if (!bitset) return -EINVAL; @@ -2343,7 +2346,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, * signal. futex_unlock_pi() will not destroy the lock_ptr nor * the pi_state. */ - WARN_ON(!&q.pi_state); + WARN_ON(!q.pi_state); pi_mutex = &q.pi_state->pi_mutex; ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter, 1); debug_rt_mutex_free_waiter(&rt_waiter); @@ -2370,7 +2373,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, * fault, unlock the rt_mutex and return the fault to userspace. */ if (ret == -EFAULT) { - if (rt_mutex_owner(pi_mutex) == current) + if (pi_mutex && rt_mutex_owner(pi_mutex) == current) rt_mutex_unlock(pi_mutex); } else if (ret == -EINTR) { /* diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 470d08c..10e0772 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -117,7 +117,7 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action) { irqreturn_t retval = IRQ_NONE; - unsigned int random = 0, irq = desc->irq_data.irq; + unsigned int flags = 0, irq = desc->irq_data.irq; do { irqreturn_t res; @@ -145,7 +145,7 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action) /* Fall through to add to randomness */ case IRQ_HANDLED: - random |= action->flags; + flags |= action->flags; break; default: @@ -156,8 +156,7 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action) action = action->next; } while (action); - if (random & IRQF_SAMPLE_RANDOM) - add_interrupt_randomness(irq); + add_interrupt_randomness(irq, flags); if (!noirqdebug) note_interrupt(irq, desc, retval); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index df8136f..fa4a70e 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -886,22 +886,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) if (desc->irq_data.chip == &no_irq_chip) return -ENOSYS; - /* - * Some drivers like serial.c use request_irq() heavily, - * so we have to be careful not to interfere with a - * running system. - */ - if (new->flags & IRQF_SAMPLE_RANDOM) { - /* - * This function might sleep, we want to call it first, - * outside of the atomic block. - * Yes, this might clear the entropy pool if the wrong - * driver is attempted to be loaded, without actually - * installing a new handler, but is this really a problem, - * only the sysadmin is able to do this. - */ - rand_initialize_irq(irq); - } /* * Check whether the interrupt nests into another interrupt @@ -1325,7 +1309,6 @@ EXPORT_SYMBOL(free_irq); * Flags: * * IRQF_SHARED Interrupt is shared - * IRQF_SAMPLE_RANDOM The interrupt can be used for entropy * IRQF_TRIGGER_* Specify active edge(s) or level * */ diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 8884c27..32f1590 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -344,6 +344,7 @@ int hibernation_snapshot(int platform_mode) goto Complete_devices; suspend_console(); + ftrace_stop(); pm_restrict_gfp_mask(); error = dpm_suspend(PMSG_FREEZE); if (error) @@ -369,6 +370,7 @@ int hibernation_snapshot(int platform_mode) if (error || !in_suspend) pm_restore_gfp_mask(); + ftrace_start(); resume_console(); Complete_devices: @@ -471,6 +473,7 @@ int hibernation_restore(int platform_mode) pm_prepare_console(); suspend_console(); + ftrace_stop(); pm_restrict_gfp_mask(); error = dpm_suspend_start(PMSG_QUIESCE); if (!error) { @@ -478,6 +481,7 @@ int hibernation_restore(int platform_mode) dpm_resume_end(PMSG_RECOVER); } pm_restore_gfp_mask(); + ftrace_start(); resume_console(); pm_restore_console(); return error; @@ -504,6 +508,7 @@ int hibernation_platform_enter(void) entering_platform_hibernation = true; suspend_console(); + ftrace_stop(); error = dpm_suspend_start(PMSG_HIBERNATE); if (error) { if (hibernation_ops->recover) @@ -547,6 +552,7 @@ int hibernation_platform_enter(void) Resume_devices: entering_platform_hibernation = false; dpm_resume_end(PMSG_RESTORE); + ftrace_start(); resume_console(); Close: diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index a8bf2e6..44c78d5 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -23,6 +23,7 @@ #include <linux/slab.h> #include <linux/suspend.h> #include <linux/syscore_ops.h> +#include <linux/ftrace.h> #include <trace/events/power.h> #include "power.h" @@ -213,6 +214,7 @@ int suspend_devices_and_enter(suspend_state_t state) goto Close; } suspend_console(); + ftrace_stop(); suspend_test_start(); error = dpm_suspend_start(PMSG_SUSPEND); if (error) { @@ -229,6 +231,7 @@ int suspend_devices_and_enter(suspend_state_t state) suspend_test_start(); dpm_resume_end(PMSG_RESUME); suspend_test_finish("resume devices"); + ftrace_start(); resume_console(); Close: if (suspend_ops->end) diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index f1eb182..61fc450 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -375,7 +375,9 @@ int second_overflow(unsigned long secs) time_state = TIME_DEL; break; case TIME_INS: - if (secs % 86400 == 0) { + if (!(time_status & STA_INS)) + time_state = TIME_OK; + else if (secs % 86400 == 0) { leap = -1; time_state = TIME_OOP; time_tai++; @@ -384,7 +386,9 @@ int second_overflow(unsigned long secs) } break; case TIME_DEL: - if ((secs + 1) % 86400 == 0) { + if (!(time_status & STA_DEL)) + time_state = TIME_OK; + else if ((secs + 1) % 86400 == 0) { leap = 1; time_tai--; time_state = TIME_WAIT; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index ee1845b..e88c924 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3561,6 +3561,41 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb, return notifier_from_errno(0); } +/* + * Workqueues should be brought up before normal priority CPU notifiers. + * This will be registered high priority CPU notifier. + */ +static int __devinit workqueue_cpu_up_callback(struct notifier_block *nfb, + unsigned long action, + void *hcpu) +{ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_UP_PREPARE: + case CPU_UP_CANCELED: + case CPU_DOWN_FAILED: + case CPU_ONLINE: + return workqueue_cpu_callback(nfb, action, hcpu); + } + return NOTIFY_OK; +} + +/* + * Workqueues should be brought down after normal priority CPU notifiers. + * This will be registered as low priority CPU notifier. + */ +static int __devinit workqueue_cpu_down_callback(struct notifier_block *nfb, + unsigned long action, + void *hcpu) +{ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_DOWN_PREPARE: + case CPU_DYING: + case CPU_POST_DEAD: + return workqueue_cpu_callback(nfb, action, hcpu); + } + return NOTIFY_OK; +} + #ifdef CONFIG_SMP struct work_for_cpu { @@ -3754,7 +3789,8 @@ static int __init init_workqueues(void) unsigned int cpu; int i; - cpu_notifier(workqueue_cpu_callback, CPU_PRI_WORKQUEUE); + cpu_notifier(workqueue_cpu_up_callback, CPU_PRI_WORKQUEUE_UP); + cpu_notifier(workqueue_cpu_down_callback, CPU_PRI_WORKQUEUE_DOWN); /* initialize gcwqs */ for_each_gcwq_cpu(cpu) { diff --git a/mm/compaction.c b/mm/compaction.c index 9cec4f2..88d55f4 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -35,10 +35,6 @@ struct compact_control { unsigned long migrate_pfn; /* isolate_migratepages search base */ bool sync; /* Synchronous migration */ - /* Account for isolated anon and file pages */ - unsigned long nr_anon; - unsigned long nr_file; - unsigned int order; /* order a direct compactor needs */ int migratetype; /* MOVABLE, RECLAIMABLE etc */ struct zone *zone; @@ -233,17 +229,13 @@ static void isolate_freepages(struct zone *zone, static void acct_isolated(struct zone *zone, struct compact_control *cc) { struct page *page; - unsigned int count[NR_LRU_LISTS] = { 0, }; + unsigned int count[2] = { 0, }; - list_for_each_entry(page, &cc->migratepages, lru) { - int lru = page_lru_base_type(page); - count[lru]++; - } + list_for_each_entry(page, &cc->migratepages, lru) + count[!!page_is_file_cache(page)]++; - cc->nr_anon = count[LRU_ACTIVE_ANON] + count[LRU_INACTIVE_ANON]; - cc->nr_file = count[LRU_ACTIVE_FILE] + count[LRU_INACTIVE_FILE]; - __mod_zone_page_state(zone, NR_ISOLATED_ANON, cc->nr_anon); - __mod_zone_page_state(zone, NR_ISOLATED_FILE, cc->nr_file); + __mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]); + __mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]); } /* Similar to reclaim, but different enough that they don't share logic */ @@ -279,6 +271,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, unsigned long last_pageblock_nr = 0, pageblock_nr; unsigned long nr_scanned = 0, nr_isolated = 0; struct list_head *migratelist = &cc->migratepages; + isolate_mode_t mode = ISOLATE_ACTIVE|ISOLATE_INACTIVE; /* Do not scan outside zone boundaries */ low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn); @@ -393,8 +386,11 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, continue; } + if (!cc->sync) + mode |= ISOLATE_ASYNC_MIGRATE; + /* Try isolate the page */ - if (__isolate_lru_page(page, ISOLATE_BOTH, 0) != 0) + if (__isolate_lru_page(page, mode, 0) != 0) continue; VM_BUG_ON(PageTransCompound(page)); @@ -596,7 +592,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) nr_migrate = cc->nr_migratepages; err = migrate_pages(&cc->migratepages, compaction_alloc, (unsigned long)cc, false, - cc->sync); + cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC); update_nr_listpages(cc); nr_remaining = cc->nr_migratepages; diff --git a/mm/filemap.c b/mm/filemap.c index b7d8603..10481eb 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -516,10 +516,13 @@ struct page *__page_cache_alloc(gfp_t gfp) struct page *page; if (cpuset_do_page_mem_spread()) { - get_mems_allowed(); - n = cpuset_mem_spread_node(); - page = alloc_pages_exact_node(n, gfp, 0); - put_mems_allowed(); + unsigned int cpuset_mems_cookie; + do { + cpuset_mems_cookie = get_mems_allowed(); + n = cpuset_mem_spread_node(); + page = alloc_pages_exact_node(n, gfp, 0); + } while (!put_mems_allowed(cpuset_mems_cookie) && !page); + return page; } return alloc_pages(gfp, 0); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 05f8fd4..037f077 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -460,8 +460,10 @@ static struct page *dequeue_huge_page_vma(struct hstate *h, struct zonelist *zonelist; struct zone *zone; struct zoneref *z; + unsigned int cpuset_mems_cookie; - get_mems_allowed(); +retry_cpuset: + cpuset_mems_cookie = get_mems_allowed(); zonelist = huge_zonelist(vma, address, htlb_alloc_mask, &mpol, &nodemask); /* @@ -488,10 +490,15 @@ static struct page *dequeue_huge_page_vma(struct hstate *h, } } } -err: + mpol_cond_put(mpol); - put_mems_allowed(); + if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + goto retry_cpuset; return page; + +err: + mpol_cond_put(mpol); + return NULL; } static void update_and_free_page(struct hstate *h, struct page *page) @@ -2294,6 +2301,22 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, { mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex); __unmap_hugepage_range(vma, start, end, ref_page); + /* + * Clear this flag so that x86's huge_pmd_share page_table_shareable + * test will fail on a vma being torn down, and not grab a page table + * on its way out. We're lucky that the flag has such an appropriate + * name, and can in fact be safely cleared here. We could clear it + * before the __unmap_hugepage_range above, but all that's necessary + * is to clear it before releasing the i_mmap_mutex below. + * + * This works because in the contexts this is called, the VMA is + * going to be destroyed. It is not vunerable to madvise(DONTNEED) + * because madvise is not supported on hugetlbfs. The same applies + * for direct IO. unmap_hugepage_range() is only being called just + * before free_pgtables() so clearing VM_MAYSHARE will not cause + * surprises later. + */ + vma->vm_flags &= ~VM_MAYSHARE; mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex); } @@ -2846,9 +2869,14 @@ void hugetlb_change_protection(struct vm_area_struct *vma, } } spin_unlock(&mm->page_table_lock); - mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex); - + /* + * Must flush TLB before releasing i_mmap_mutex: x86's huge_pmd_unshare + * may have cleared our pud entry and done put_page on the page table: + * once we release i_mmap_mutex, another task can do the final put_page + * and that page table be reused and filled with junk. + */ flush_tlb_range(vma, start, end); + mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex); } int hugetlb_reserve_pages(struct inode *inode, diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ffb99b4..57cdf5a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1251,7 +1251,8 @@ mem_cgroup_get_reclaim_stat_from_page(struct page *page) unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, struct list_head *dst, unsigned long *scanned, int order, - int mode, struct zone *z, + isolate_mode_t mode, + struct zone *z, struct mem_cgroup *mem_cont, int active, int file) { diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 740c4f5..2f49dcf 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1334,8 +1334,8 @@ static int soft_offline_huge_page(struct page *page, int flags) /* Keep page count to indicate a given hugepage is isolated. */ list_add(&hpage->lru, &pagelist); - ret = migrate_huge_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, 0, - true); + ret = migrate_huge_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, false, + MIGRATE_SYNC); if (ret) { struct page *page1, *page2; list_for_each_entry_safe(page1, page2, &pagelist, lru) @@ -1464,7 +1464,7 @@ int soft_offline_page(struct page *page, int flags) page_is_file_cache(page)); list_add(&page->lru, &pagelist); ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, - 0, true); + false, MIGRATE_SYNC); if (ret) { putback_lru_pages(&pagelist); pr_info("soft offline: %#lx: migration failed %d, type %lx\n", diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index c46887b..ae5a3f2 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -747,7 +747,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) } /* this function returns # of failed pages */ ret = migrate_pages(&source, hotremove_migrate_alloc, 0, - true, true); + true, MIGRATE_SYNC); if (ret) putback_lru_pages(&source); } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 3dac2d1..cff919f 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -926,7 +926,7 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest, if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, new_node_page, dest, - false, true); + false, MIGRATE_SYNC); if (err) putback_lru_pages(&pagelist); } @@ -1810,18 +1810,24 @@ struct page * alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr, int node) { - struct mempolicy *pol = get_vma_policy(current, vma, addr); + struct mempolicy *pol; struct zonelist *zl; struct page *page; + unsigned int cpuset_mems_cookie; + +retry_cpuset: + pol = get_vma_policy(current, vma, addr); + cpuset_mems_cookie = get_mems_allowed(); - get_mems_allowed(); if (unlikely(pol->mode == MPOL_INTERLEAVE)) { unsigned nid; nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order); mpol_cond_put(pol); page = alloc_page_interleave(gfp, order, nid); - put_mems_allowed(); + if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + goto retry_cpuset; + return page; } zl = policy_zonelist(gfp, pol, node); @@ -1832,7 +1838,8 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, struct page *page = __alloc_pages_nodemask(gfp, order, zl, policy_nodemask(gfp, pol)); __mpol_put(pol); - put_mems_allowed(); + if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + goto retry_cpuset; return page; } /* @@ -1840,7 +1847,8 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, */ page = __alloc_pages_nodemask(gfp, order, zl, policy_nodemask(gfp, pol)); - put_mems_allowed(); + if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + goto retry_cpuset; return page; } @@ -1867,11 +1875,14 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order) { struct mempolicy *pol = current->mempolicy; struct page *page; + unsigned int cpuset_mems_cookie; if (!pol || in_interrupt() || (gfp & __GFP_THISNODE)) pol = &default_policy; - get_mems_allowed(); +retry_cpuset: + cpuset_mems_cookie = get_mems_allowed(); + /* * No reference counting needed for current->mempolicy * nor system default_policy @@ -1882,7 +1893,10 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order) page = __alloc_pages_nodemask(gfp, order, policy_zonelist(gfp, pol, numa_node_id()), policy_nodemask(gfp, pol)); - put_mems_allowed(); + + if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + goto retry_cpuset; + return page; } EXPORT_SYMBOL(alloc_pages_current); diff --git a/mm/migrate.c b/mm/migrate.c index 14d0a6a..480714b 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -220,6 +220,56 @@ out: pte_unmap_unlock(ptep, ptl); } +#ifdef CONFIG_BLOCK +/* Returns true if all buffers are successfully locked */ +static bool buffer_migrate_lock_buffers(struct buffer_head *head, + enum migrate_mode mode) +{ + struct buffer_head *bh = head; + + /* Simple case, sync compaction */ + if (mode != MIGRATE_ASYNC) { + do { + get_bh(bh); + lock_buffer(bh); + bh = bh->b_this_page; + + } while (bh != head); + + return true; + } + + /* async case, we cannot block on lock_buffer so use trylock_buffer */ + do { + get_bh(bh); + if (!trylock_buffer(bh)) { + /* + * We failed to lock the buffer and cannot stall in + * async migration. Release the taken locks + */ + struct buffer_head *failed_bh = bh; + put_bh(failed_bh); + bh = head; + while (bh != failed_bh) { + unlock_buffer(bh); + put_bh(bh); + bh = bh->b_this_page; + } + return false; + } + + bh = bh->b_this_page; + } while (bh != head); + return true; +} +#else +static inline bool buffer_migrate_lock_buffers(struct buffer_head *head, + enum migrate_mode mode) +{ + return true; +} +#endif /* CONFIG_BLOCK */ + /* * Replace the page in the mapping. * @@ -229,7 +279,8 @@ out: * 3 for pages with a mapping and PagePrivate/PagePrivate2 set. */ static int migrate_page_move_mapping(struct address_space *mapping, - struct page *newpage, struct page *page) + struct page *newpage, struct page *page, + struct buffer_head *head, enum migrate_mode mode) { int expected_count; void **pslot; @@ -259,6 +310,20 @@ static int migrate_page_move_mapping(struct address_space *mapping, } /* + * In the async migration case of moving a page with buffers, lock the + * buffers using trylock before the mapping is moved. If the mapping + * was moved, we later failed to lock the buffers and could not move + * the mapping back due to an elevated page count, we would have to + * block waiting on other references to be dropped. + */ + if (mode == MIGRATE_ASYNC && head && + !buffer_migrate_lock_buffers(head, mode)) { + page_unfreeze_refs(page, expected_count); + spin_unlock_irq(&mapping->tree_lock); + return -EAGAIN; + } + + /* * Now we know that no one else is looking at the page. */ get_page(newpage); /* add cache reference */ @@ -415,13 +480,14 @@ EXPORT_SYMBOL(fail_migrate_page); * Pages are locked upon entry and exit. */ int migrate_page(struct address_space *mapping, - struct page *newpage, struct page *page) + struct page *newpage, struct page *page, + enum migrate_mode mode) { int rc; BUG_ON(PageWriteback(page)); /* Writeback must be complete */ - rc = migrate_page_move_mapping(mapping, newpage, page); + rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode); if (rc) return rc; @@ -438,28 +504,28 @@ EXPORT_SYMBOL(migrate_page); * exist. */ int buffer_migrate_page(struct address_space *mapping, - struct page *newpage, struct page *page) + struct page *newpage, struct page *page, enum migrate_mode mode) { struct buffer_head *bh, *head; int rc; if (!page_has_buffers(page)) - return migrate_page(mapping, newpage, page); + return migrate_page(mapping, newpage, page, mode); head = page_buffers(page); - rc = migrate_page_move_mapping(mapping, newpage, page); + rc = migrate_page_move_mapping(mapping, newpage, page, head, mode); if (rc) return rc; - bh = head; - do { - get_bh(bh); - lock_buffer(bh); - bh = bh->b_this_page; - - } while (bh != head); + /* + * In the async case, migrate_page_move_mapping locked the buffers + * with an IRQ-safe spinlock held. In the sync case, the buffers + * need to be locked now + */ + if (mode != MIGRATE_ASYNC) + BUG_ON(!buffer_migrate_lock_buffers(head, mode)); ClearPagePrivate(page); set_page_private(newpage, page_private(page)); @@ -536,10 +602,14 @@ static int writeout(struct address_space *mapping, struct page *page) * Default handling if a filesystem does not provide a migration function. */ static int fallback_migrate_page(struct address_space *mapping, - struct page *newpage, struct page *page) + struct page *newpage, struct page *page, enum migrate_mode mode) { - if (PageDirty(page)) + if (PageDirty(page)) { + /* Only writeback pages in full synchronous migration */ + if (mode != MIGRATE_SYNC) + return -EBUSY; return writeout(mapping, page); + } /* * Buffers may be managed in a filesystem specific way. @@ -549,7 +619,7 @@ static int fallback_migrate_page(struct address_space *mapping, !try_to_release_page(page, GFP_KERNEL)) return -EAGAIN; - return migrate_page(mapping, newpage, page); + return migrate_page(mapping, newpage, page, mode); } /* @@ -564,7 +634,7 @@ static int fallback_migrate_page(struct address_space *mapping, * == 0 - success */ static int move_to_new_page(struct page *newpage, struct page *page, - int remap_swapcache, bool sync) + int remap_swapcache, enum migrate_mode mode) { struct address_space *mapping; int rc; @@ -585,29 +655,18 @@ static int move_to_new_page(struct page *newpage, struct page *page, mapping = page_mapping(page); if (!mapping) - rc = migrate_page(mapping, newpage, page); - else { + rc = migrate_page(mapping, newpage, page, mode); + else if (mapping->a_ops->migratepage) /* - * Do not writeback pages if !sync and migratepage is - * not pointing to migrate_page() which is nonblocking - * (swapcache/tmpfs uses migratepage = migrate_page). + * Most pages have a mapping and most filesystems provide a + * migratepage callback. Anonymous pages are part of swap + * space which also has its own migratepage callback. This + * is the most common path for page migration. */ - if (PageDirty(page) && !sync && - mapping->a_ops->migratepage != migrate_page) - rc = -EBUSY; - else if (mapping->a_ops->migratepage) - /* - * Most pages have a mapping and most filesystems - * should provide a migration function. Anonymous - * pages are part of swap space which also has its - * own migration function. This is the most common - * path for page migration. - */ - rc = mapping->a_ops->migratepage(mapping, - newpage, page); - else - rc = fallback_migrate_page(mapping, newpage, page); - } + rc = mapping->a_ops->migratepage(mapping, + newpage, page, mode); + else + rc = fallback_migrate_page(mapping, newpage, page, mode); if (rc) { newpage->mapping = NULL; @@ -621,38 +680,18 @@ static int move_to_new_page(struct page *newpage, struct page *page, return rc; } -/* - * Obtain the lock on page, remove all ptes and migrate the page - * to the newly allocated page in newpage. - */ -static int unmap_and_move(new_page_t get_new_page, unsigned long private, - struct page *page, int force, bool offlining, bool sync) +static int __unmap_and_move(struct page *page, struct page *newpage, + int force, bool offlining, enum migrate_mode mode) { - int rc = 0; - int *result = NULL; - struct page *newpage = get_new_page(page, private, &result); + int rc = -EAGAIN; int remap_swapcache = 1; int charge = 0; struct mem_cgroup *mem; struct anon_vma *anon_vma = NULL; - if (!newpage) - return -ENOMEM; - - if (page_count(page) == 1) { - /* page was freed from under us. So we are done. */ - goto move_newpage; - } - if (unlikely(PageTransHuge(page))) - if (unlikely(split_huge_page(page))) - goto move_newpage; - - /* prepare cgroup just returns 0 or -ENOMEM */ - rc = -EAGAIN; - if (!trylock_page(page)) { - if (!force || !sync) - goto move_newpage; + if (!force || mode == MIGRATE_ASYNC) + goto out; /* * It's not safe for direct compaction to call lock_page. @@ -668,7 +707,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private, * altogether. */ if (current->flags & PF_MEMALLOC) - goto move_newpage; + goto out; lock_page(page); } @@ -697,10 +736,12 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private, if (PageWriteback(page)) { /* - * For !sync, there is no point retrying as the retry loop - * is expected to be too short for PageWriteback to be cleared + * Only in the case of a full syncronous migration is it + * necessary to wait for PageWriteback. In the async case, + * the retry loop is too short and in the sync-light case, + * the overhead of stalling is too much */ - if (!sync) { + if (mode != MIGRATE_SYNC) { rc = -EBUSY; goto uncharge; } @@ -771,7 +812,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private, skip_unmap: if (!page_mapped(page)) - rc = move_to_new_page(newpage, page, remap_swapcache, sync); + rc = move_to_new_page(newpage, page, remap_swapcache, mode); if (rc && remap_swapcache) remove_migration_ptes(page, page); @@ -785,27 +826,53 @@ uncharge: mem_cgroup_end_migration(mem, page, newpage, rc == 0); unlock: unlock_page(page); +out: + return rc; +} -move_newpage: +/* + * Obtain the lock on page, remove all ptes and migrate the page + * to the newly allocated page in newpage. + */ +static int unmap_and_move(new_page_t get_new_page, unsigned long private, + struct page *page, int force, bool offlining, + enum migrate_mode mode) +{ + int rc = 0; + int *result = NULL; + struct page *newpage = get_new_page(page, private, &result); + + if (!newpage) + return -ENOMEM; + + if (page_count(page) == 1) { + /* page was freed from under us. So we are done. */ + goto out; + } + + if (unlikely(PageTransHuge(page))) + if (unlikely(split_huge_page(page))) + goto out; + + rc = __unmap_and_move(page, newpage, force, offlining, mode); +out: if (rc != -EAGAIN) { - /* - * A page that has been migrated has all references - * removed and will be freed. A page that has not been - * migrated will have kepts its references and be - * restored. - */ - list_del(&page->lru); + /* + * A page that has been migrated has all references + * removed and will be freed. A page that has not been + * migrated will have kepts its references and be + * restored. + */ + list_del(&page->lru); dec_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); putback_lru_page(page); } - /* * Move the new page to the LRU. If migration was not successful * then this will free the page. */ putback_lru_page(newpage); - if (result) { if (rc) *result = rc; @@ -835,7 +902,8 @@ move_newpage: */ static int unmap_and_move_huge_page(new_page_t get_new_page, unsigned long private, struct page *hpage, - int force, bool offlining, bool sync) + int force, bool offlining, + enum migrate_mode mode) { int rc = 0; int *result = NULL; @@ -848,7 +916,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, rc = -EAGAIN; if (!trylock_page(hpage)) { - if (!force || !sync) + if (!force || mode != MIGRATE_SYNC) goto out; lock_page(hpage); } @@ -859,7 +927,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, try_to_unmap(hpage, TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS); if (!page_mapped(hpage)) - rc = move_to_new_page(new_hpage, hpage, 1, sync); + rc = move_to_new_page(new_hpage, hpage, 1, mode); if (rc) remove_migration_ptes(hpage, hpage); @@ -902,7 +970,7 @@ out: */ int migrate_pages(struct list_head *from, new_page_t get_new_page, unsigned long private, bool offlining, - bool sync) + enum migrate_mode mode) { int retry = 1; int nr_failed = 0; @@ -923,7 +991,7 @@ int migrate_pages(struct list_head *from, rc = unmap_and_move(get_new_page, private, page, pass > 2, offlining, - sync); + mode); switch(rc) { case -ENOMEM: @@ -953,7 +1021,7 @@ out: int migrate_huge_pages(struct list_head *from, new_page_t get_new_page, unsigned long private, bool offlining, - bool sync) + enum migrate_mode mode) { int retry = 1; int nr_failed = 0; @@ -970,7 +1038,7 @@ int migrate_huge_pages(struct list_head *from, rc = unmap_and_move_huge_page(get_new_page, private, page, pass > 2, offlining, - sync); + mode); switch(rc) { case -ENOMEM: @@ -1099,7 +1167,7 @@ set_status: err = 0; if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, new_page_node, - (unsigned long)pm, 0, true); + (unsigned long)pm, 0, MIGRATE_SYNC); if (err) putback_lru_pages(&pagelist); } diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index 8d032de..71c7811 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -33,6 +33,24 @@ void __mmu_notifier_release(struct mm_struct *mm) { struct mmu_notifier *mn; + struct hlist_node *n; + + /* + * RCU here will block mmu_notifier_unregister until + * ->release returns. + */ + rcu_read_lock(); + hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) + /* + * if ->release runs before mmu_notifier_unregister it + * must be handled as it's the only way for the driver + * to flush all existing sptes and stop the driver + * from establishing any more sptes before all the + * pages in the mm are freed. + */ + if (mn->ops->release) + mn->ops->release(mn, mm); + rcu_read_unlock(); spin_lock(&mm->mmu_notifier_mm->lock); while (unlikely(!hlist_empty(&mm->mmu_notifier_mm->list))) { @@ -46,23 +64,6 @@ void __mmu_notifier_release(struct mm_struct *mm) * mmu_notifier_unregister to return. */ hlist_del_init_rcu(&mn->hlist); - /* - * RCU here will block mmu_notifier_unregister until - * ->release returns. - */ - rcu_read_lock(); - spin_unlock(&mm->mmu_notifier_mm->lock); - /* - * if ->release runs before mmu_notifier_unregister it - * must be handled as it's the only way for the driver - * to flush all existing sptes and stop the driver - * from establishing any more sptes before all the - * pages in the mm are freed. - */ - if (mn->ops->release) - mn->ops->release(mn, mm); - rcu_read_unlock(); - spin_lock(&mm->mmu_notifier_mm->lock); } spin_unlock(&mm->mmu_notifier_mm->lock); @@ -284,16 +285,13 @@ void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm) { BUG_ON(atomic_read(&mm->mm_count) <= 0); - spin_lock(&mm->mmu_notifier_mm->lock); if (!hlist_unhashed(&mn->hlist)) { - hlist_del_rcu(&mn->hlist); - /* * RCU here will force exit_mmap to wait ->release to finish * before freeing the pages. */ rcu_read_lock(); - spin_unlock(&mm->mmu_notifier_mm->lock); + /* * exit_mmap will block in mmu_notifier_release to * guarantee ->release is called before freeing the @@ -302,8 +300,11 @@ void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm) if (mn->ops->release) mn->ops->release(mn, mm); rcu_read_unlock(); - } else + + spin_lock(&mm->mmu_notifier_mm->lock); + hlist_del_rcu(&mn->hlist); spin_unlock(&mm->mmu_notifier_mm->lock); + } /* * Wait any running method to finish, of course including diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e2f474d..87b0a3f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1912,14 +1912,20 @@ static struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, unsigned long *did_some_progress, - bool sync_migration) + int migratetype, bool sync_migration, + bool *deferred_compaction, + unsigned long *did_some_progress) { struct page *page; - if (!order || compaction_deferred(preferred_zone)) + if (!order) return NULL; + if (compaction_deferred(preferred_zone)) { + *deferred_compaction = true; + return NULL; + } + current->flags |= PF_MEMALLOC; *did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask, nodemask, sync_migration); @@ -1947,7 +1953,13 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, * but not enough to satisfy watermarks. */ count_vm_event(COMPACTFAIL); - defer_compaction(preferred_zone); + + /* + * As async compaction considers a subset of pageblocks, only + * defer if the failure was a sync compaction failure. + */ + if (sync_migration) + defer_compaction(preferred_zone); cond_resched(); } @@ -1959,8 +1971,9 @@ static inline struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, unsigned long *did_some_progress, - bool sync_migration) + int migratetype, bool sync_migration, + bool *deferred_compaction, + unsigned long *did_some_progress) { return NULL; } @@ -2110,6 +2123,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, unsigned long pages_reclaimed = 0; unsigned long did_some_progress; bool sync_migration = false; + bool deferred_compaction = false; /* * In the slowpath, we sanity check order to avoid ever trying to @@ -2190,12 +2204,22 @@ rebalance: zonelist, high_zoneidx, nodemask, alloc_flags, preferred_zone, - migratetype, &did_some_progress, - sync_migration); + migratetype, sync_migration, + &deferred_compaction, + &did_some_progress); if (page) goto got_pg; sync_migration = true; + /* + * If compaction is deferred for high-order allocations, it is because + * sync compaction recently failed. In this is the case and the caller + * has requested the system not be heavily disrupted, fail the + * allocation now instead of entering direct reclaim + */ + if (deferred_compaction && (gfp_mask & __GFP_NO_KSWAPD)) + goto nopage; + /* Try direct reclaim and then allocating */ page = __alloc_pages_direct_reclaim(gfp_mask, order, zonelist, high_zoneidx, @@ -2266,8 +2290,9 @@ rebalance: zonelist, high_zoneidx, nodemask, alloc_flags, preferred_zone, - migratetype, &did_some_progress, - sync_migration); + migratetype, sync_migration, + &deferred_compaction, + &did_some_progress); if (page) goto got_pg; } @@ -2291,8 +2316,9 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, { enum zone_type high_zoneidx = gfp_zone(gfp_mask); struct zone *preferred_zone; - struct page *page; + struct page *page = NULL; int migratetype = allocflags_to_migratetype(gfp_mask); + unsigned int cpuset_mems_cookie; gfp_mask &= gfp_allowed_mask; @@ -2311,15 +2337,15 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, if (unlikely(!zonelist->_zonerefs->zone)) return NULL; - get_mems_allowed(); +retry_cpuset: + cpuset_mems_cookie = get_mems_allowed(); + /* The preferred zone is used for statistics later */ first_zones_zonelist(zonelist, high_zoneidx, nodemask ? : &cpuset_current_mems_allowed, &preferred_zone); - if (!preferred_zone) { - put_mems_allowed(); - return NULL; - } + if (!preferred_zone) + goto out; /* First allocation attempt */ page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order, @@ -2329,9 +2355,19 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, page = __alloc_pages_slowpath(gfp_mask, order, zonelist, high_zoneidx, nodemask, preferred_zone, migratetype); - put_mems_allowed(); trace_mm_page_alloc(page, order, gfp_mask, migratetype); + +out: + /* + * When updating a task's mems_allowed, it is possible to race with + * parallel threads in such a way that an allocation can fail while + * the mask is being updated. If a page allocation is about to fail, + * check if the cpuset changed during allocation and if so, retry. + */ + if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + goto retry_cpuset; + return page; } EXPORT_SYMBOL(__alloc_pages_nodemask); @@ -2555,13 +2591,15 @@ void si_meminfo_node(struct sysinfo *val, int nid) bool skip_free_areas_node(unsigned int flags, int nid) { bool ret = false; + unsigned int cpuset_mems_cookie; if (!(flags & SHOW_MEM_FILTER_NODES)) goto out; - get_mems_allowed(); - ret = !node_isset(nid, cpuset_current_mems_allowed); - put_mems_allowed(); + do { + cpuset_mems_cookie = get_mems_allowed(); + ret = !node_isset(nid, cpuset_current_mems_allowed); + } while (!put_mems_allowed(cpuset_mems_cookie)); out: return ret; } @@ -3441,25 +3479,33 @@ static void setup_zone_migrate_reserve(struct zone *zone) if (page_to_nid(page) != zone_to_nid(zone)) continue; - /* Blocks with reserved pages will never free, skip them. */ - block_end_pfn = min(pfn + pageblock_nr_pages, end_pfn); - if (pageblock_is_reserved(pfn, block_end_pfn)) - continue; - block_migratetype = get_pageblock_migratetype(page); - /* If this block is reserved, account for it */ - if (reserve > 0 && block_migratetype == MIGRATE_RESERVE) { - reserve--; - continue; - } + /* Only test what is necessary when the reserves are not met */ + if (reserve > 0) { + /* + * Blocks with reserved pages will never free, skip + * them. + */ + block_end_pfn = min(pfn + pageblock_nr_pages, end_pfn); + if (pageblock_is_reserved(pfn, block_end_pfn)) + continue; - /* Suitable for reserving if this block is movable */ - if (reserve > 0 && block_migratetype == MIGRATE_MOVABLE) { - set_pageblock_migratetype(page, MIGRATE_RESERVE); - move_freepages_block(zone, page, MIGRATE_RESERVE); - reserve--; - continue; + /* If this block is reserved, account for it */ + if (block_migratetype == MIGRATE_RESERVE) { + reserve--; + continue; + } + + /* Suitable for reserving if this block is movable */ + if (block_migratetype == MIGRATE_MOVABLE) { + set_pageblock_migratetype(page, + MIGRATE_RESERVE); + move_freepages_block(zone, page, + MIGRATE_RESERVE); + reserve--; + continue; + } } /* @@ -3218,12 +3218,10 @@ static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags) if (in_interrupt() || (flags & __GFP_THISNODE)) return NULL; nid_alloc = nid_here = numa_mem_id(); - get_mems_allowed(); if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD)) nid_alloc = cpuset_slab_spread_node(); else if (current->mempolicy) nid_alloc = slab_node(current->mempolicy); - put_mems_allowed(); if (nid_alloc != nid_here) return ____cache_alloc_node(cachep, flags, nid_alloc); return NULL; @@ -3246,14 +3244,17 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags) enum zone_type high_zoneidx = gfp_zone(flags); void *obj = NULL; int nid; + unsigned int cpuset_mems_cookie; if (flags & __GFP_THISNODE) return NULL; - get_mems_allowed(); - zonelist = node_zonelist(slab_node(current->mempolicy), flags); local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK); +retry_cpuset: + cpuset_mems_cookie = get_mems_allowed(); + zonelist = node_zonelist(slab_node(current->mempolicy), flags); + retry: /* * Look through allowed nodes for objects available @@ -3306,7 +3307,9 @@ retry: } } } - put_mems_allowed(); + + if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !obj)) + goto retry_cpuset; return obj; } @@ -1457,6 +1457,7 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags) struct zone *zone; enum zone_type high_zoneidx = gfp_zone(flags); struct page *page; + unsigned int cpuset_mems_cookie; /* * The defrag ratio allows a configuration of the tradeoffs between @@ -1480,23 +1481,32 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags) get_cycles() % 1024 > s->remote_node_defrag_ratio) return NULL; - get_mems_allowed(); - zonelist = node_zonelist(slab_node(current->mempolicy), flags); - for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { - struct kmem_cache_node *n; - - n = get_node(s, zone_to_nid(zone)); - - if (n && cpuset_zone_allowed_hardwall(zone, flags) && - n->nr_partial > s->min_partial) { - page = get_partial_node(n); - if (page) { - put_mems_allowed(); - return page; + do { + cpuset_mems_cookie = get_mems_allowed(); + zonelist = node_zonelist(slab_node(current->mempolicy), flags); + for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { + struct kmem_cache_node *n; + + n = get_node(s, zone_to_nid(zone)); + + if (n && cpuset_zone_allowed_hardwall(zone, flags) && + n->nr_partial > s->min_partial) { + page = get_partial_node(n); + if (page) { + /* + * Return the object even if + * put_mems_allowed indicated that + * the cpuset mems_allowed was + * updated in parallel. It's a + * harmless race between the alloc + * and the cpuset update. + */ + put_mems_allowed(cpuset_mems_cookie); + return page; + } } } - } - put_mems_allowed(); + } while (!put_mems_allowed(cpuset_mems_cookie)); #endif return NULL; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 1b0ed36..5326f98 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -248,35 +248,66 @@ unsigned long shrink_slab(struct shrink_control *shrink, list_for_each_entry(shrinker, &shrinker_list, list) { unsigned long long delta; - unsigned long total_scan; - unsigned long max_pass; + long total_scan; + long max_pass; + int shrink_ret = 0; + long nr; + long new_nr; max_pass = do_shrinker_shrink(shrinker, shrink, 0); + if (max_pass <= 0) + continue; + + /* + * copy the current shrinker scan count into a local variable + * and zero it so that other concurrent shrinker invocations + * don't also do this scanning work. + */ + do { + nr = shrinker->nr; + } while (cmpxchg(&shrinker->nr, nr, 0) != nr); + + total_scan = nr; delta = (4 * nr_pages_scanned) / shrinker->seeks; delta *= max_pass; do_div(delta, lru_pages + 1); - shrinker->nr += delta; - if (shrinker->nr < 0) { + total_scan += delta; + if (total_scan < 0) { printk(KERN_ERR "shrink_slab: %pF negative objects to " "delete nr=%ld\n", - shrinker->shrink, shrinker->nr); - shrinker->nr = max_pass; + shrinker->shrink, total_scan); + total_scan = max_pass; } /* + * We need to avoid excessive windup on filesystem shrinkers + * due to large numbers of GFP_NOFS allocations causing the + * shrinkers to return -1 all the time. This results in a large + * nr being built up so when a shrink that can do some work + * comes along it empties the entire cache due to nr >>> + * max_pass. This is bad for sustaining a working set in + * memory. + * + * Hence only allow the shrinker to scan the entire cache when + * a large delta change is calculated directly. + */ + if (delta < max_pass / 4) + total_scan = min(total_scan, max_pass / 2); + + /* * Avoid risking looping forever due to too large nr value: * never try to free more than twice the estimate number of * freeable entries. */ - if (shrinker->nr > max_pass * 2) - shrinker->nr = max_pass * 2; + if (total_scan > max_pass * 2) + total_scan = max_pass * 2; - total_scan = shrinker->nr; - shrinker->nr = 0; + trace_mm_shrink_slab_start(shrinker, shrink, nr, + nr_pages_scanned, lru_pages, + max_pass, delta, total_scan); while (total_scan >= SHRINK_BATCH) { long this_scan = SHRINK_BATCH; - int shrink_ret; int nr_before; nr_before = do_shrinker_shrink(shrinker, shrink, 0); @@ -292,7 +323,19 @@ unsigned long shrink_slab(struct shrink_control *shrink, cond_resched(); } - shrinker->nr += total_scan; + /* + * move the unused scan count back into the shrinker in a + * manner that handles concurrent updates. If we exhausted the + * scan, there is no need to do an update. + */ + do { + nr = shrinker->nr; + new_nr = total_scan + nr; + if (total_scan <= 0) + break; + } while (cmpxchg(&shrinker->nr, nr, new_nr) != nr); + + trace_mm_shrink_slab_end(shrinker, shrink_ret, nr, new_nr); } up_read(&shrinker_rwsem); out: @@ -683,7 +726,13 @@ static enum page_references page_check_references(struct page *page, */ SetPageReferenced(page); - if (referenced_page) + if (referenced_page || referenced_ptes > 1) + return PAGEREF_ACTIVATE; + + /* + * Activate file-backed executable pages after first usage. + */ + if (vm_flags & VM_EXEC) return PAGEREF_ACTIVATE; return PAGEREF_KEEP; @@ -972,23 +1021,27 @@ keep_lumpy: * * returns 0 on success, -ve errno on failure. */ -int __isolate_lru_page(struct page *page, int mode, int file) +int __isolate_lru_page(struct page *page, isolate_mode_t mode, int file) { + bool all_lru_mode; int ret = -EINVAL; /* Only take pages on the LRU. */ if (!PageLRU(page)) return ret; + all_lru_mode = (mode & (ISOLATE_ACTIVE|ISOLATE_INACTIVE)) == + (ISOLATE_ACTIVE|ISOLATE_INACTIVE); + /* * When checking the active state, we need to be sure we are * dealing with comparible boolean values. Take the logical not * of each. */ - if (mode != ISOLATE_BOTH && (!PageActive(page) != !mode)) + if (!all_lru_mode && !PageActive(page) != !(mode & ISOLATE_ACTIVE)) return ret; - if (mode != ISOLATE_BOTH && page_is_file_cache(page) != file) + if (!all_lru_mode && !!page_is_file_cache(page) != file) return ret; /* @@ -1001,6 +1054,43 @@ int __isolate_lru_page(struct page *page, int mode, int file) ret = -EBUSY; + /* + * To minimise LRU disruption, the caller can indicate that it only + * wants to isolate pages it will be able to operate on without + * blocking - clean pages for the most part. + * + * ISOLATE_CLEAN means that only clean pages should be isolated. This + * is used by reclaim when it is cannot write to backing storage + * + * ISOLATE_ASYNC_MIGRATE is used to indicate that it only wants to pages + * that it is possible to migrate without blocking + */ + if (mode & (ISOLATE_CLEAN|ISOLATE_ASYNC_MIGRATE)) { + /* All the caller can do on PageWriteback is block */ + if (PageWriteback(page)) + return ret; + + if (PageDirty(page)) { + struct address_space *mapping; + + /* ISOLATE_CLEAN means only clean pages */ + if (mode & ISOLATE_CLEAN) + return ret; + + /* + * Only pages without mappings or that have a + * ->migratepage callback are possible to migrate + * without blocking + */ + mapping = page_mapping(page); + if (mapping && !mapping->a_ops->migratepage) + return ret; + } + } + + if ((mode & ISOLATE_UNMAPPED) && page_mapped(page)) + return ret; + if (likely(get_page_unless_zero(page))) { /* * Be careful not to clear PageLRU until after we're @@ -1036,7 +1126,8 @@ int __isolate_lru_page(struct page *page, int mode, int file) */ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, struct list_head *src, struct list_head *dst, - unsigned long *scanned, int order, int mode, int file) + unsigned long *scanned, int order, isolate_mode_t mode, + int file) { unsigned long nr_taken = 0; unsigned long nr_lumpy_taken = 0; @@ -1111,7 +1202,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, * anon page which don't already have a swap slot is * pointless. */ - if (nr_swap_pages <= 0 && PageAnon(cursor_page) && + if (nr_swap_pages <= 0 && PageSwapBacked(cursor_page) && !PageSwapCache(cursor_page)) break; @@ -1161,8 +1252,8 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, static unsigned long isolate_pages_global(unsigned long nr, struct list_head *dst, unsigned long *scanned, int order, - int mode, struct zone *z, - int active, int file) + isolate_mode_t mode, + struct zone *z, int active, int file) { int lru = LRU_BASE; if (active) @@ -1408,6 +1499,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, unsigned long nr_taken; unsigned long nr_anon; unsigned long nr_file; + isolate_mode_t reclaim_mode = ISOLATE_INACTIVE; while (unlikely(too_many_isolated(zone, file, sc))) { congestion_wait(BLK_RW_ASYNC, HZ/10); @@ -1418,15 +1510,21 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, } set_reclaim_mode(priority, sc, false); + if (sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM) + reclaim_mode |= ISOLATE_ACTIVE; + lru_add_drain(); + + if (!sc->may_unmap) + reclaim_mode |= ISOLATE_UNMAPPED; + if (!sc->may_writepage) + reclaim_mode |= ISOLATE_CLEAN; + spin_lock_irq(&zone->lru_lock); if (scanning_global_lru(sc)) { - nr_taken = isolate_pages_global(nr_to_scan, - &page_list, &nr_scanned, sc->order, - sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM ? - ISOLATE_BOTH : ISOLATE_INACTIVE, - zone, 0, file); + nr_taken = isolate_pages_global(nr_to_scan, &page_list, + &nr_scanned, sc->order, reclaim_mode, zone, 0, file); zone->pages_scanned += nr_scanned; if (current_is_kswapd()) __count_zone_vm_events(PGSCAN_KSWAPD, zone, @@ -1435,12 +1533,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, __count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scanned); } else { - nr_taken = mem_cgroup_isolate_pages(nr_to_scan, - &page_list, &nr_scanned, sc->order, - sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM ? - ISOLATE_BOTH : ISOLATE_INACTIVE, - zone, sc->mem_cgroup, - 0, file); + nr_taken = mem_cgroup_isolate_pages(nr_to_scan, &page_list, + &nr_scanned, sc->order, reclaim_mode, zone, + sc->mem_cgroup, 0, file); /* * mem_cgroup_isolate_pages() keeps track of * scanned pages on its own. @@ -1542,19 +1637,26 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, struct page *page; struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc); unsigned long nr_rotated = 0; + isolate_mode_t reclaim_mode = ISOLATE_ACTIVE; lru_add_drain(); + + if (!sc->may_unmap) + reclaim_mode |= ISOLATE_UNMAPPED; + if (!sc->may_writepage) + reclaim_mode |= ISOLATE_CLEAN; + spin_lock_irq(&zone->lru_lock); if (scanning_global_lru(sc)) { nr_taken = isolate_pages_global(nr_pages, &l_hold, &pgscanned, sc->order, - ISOLATE_ACTIVE, zone, + reclaim_mode, zone, 1, file); zone->pages_scanned += pgscanned; } else { nr_taken = mem_cgroup_isolate_pages(nr_pages, &l_hold, &pgscanned, sc->order, - ISOLATE_ACTIVE, zone, + reclaim_mode, zone, sc->mem_cgroup, 1, file); /* * mem_cgroup_isolate_pages() keeps track of @@ -1747,23 +1849,16 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc, u64 fraction[2], denominator; enum lru_list l; int noswap = 0; - int force_scan = 0; + bool force_scan = false; unsigned long nr_force_scan[2]; - - anon = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_ANON) + - zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON); - file = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_FILE) + - zone_nr_lru_pages(zone, sc, LRU_INACTIVE_FILE); - - if (((anon + file) >> priority) < SWAP_CLUSTER_MAX) { - /* kswapd does zone balancing and need to scan this zone */ - if (scanning_global_lru(sc) && current_is_kswapd()) - force_scan = 1; - /* memcg may have small limit and need to avoid priority drop */ - if (!scanning_global_lru(sc)) - force_scan = 1; - } + /* kswapd does zone balancing and needs to scan this zone */ + if (scanning_global_lru(sc) && current_is_kswapd() && + zone->all_unreclaimable) + force_scan = true; + /* memcg may have small limit and need to avoid priority drop */ + if (!scanning_global_lru(sc)) + force_scan = true; /* If we have no swap space, do not bother scanning anon pages. */ if (!sc->may_swap || (nr_swap_pages <= 0)) { @@ -1776,6 +1871,11 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc, goto out; } + anon = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_ANON) + + zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON); + file = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_FILE) + + zone_nr_lru_pages(zone, sc, LRU_INACTIVE_FILE); + if (scanning_global_lru(sc)) { free = zone_page_state(zone, NR_FREE_PAGES); /* If we have very few page cache pages, @@ -1912,8 +2012,9 @@ static inline bool should_continue_reclaim(struct zone *zone, * inactive lists are large enough, continue reclaiming */ pages_for_compaction = (2UL << sc->order); - inactive_lru_pages = zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON) + - zone_nr_lru_pages(zone, sc, LRU_INACTIVE_FILE); + inactive_lru_pages = zone_nr_lru_pages(zone, sc, LRU_INACTIVE_FILE); + if (nr_swap_pages > 0) + inactive_lru_pages += zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON); if (sc->nr_reclaimed < pages_for_compaction && inactive_lru_pages > pages_for_compaction) return true; @@ -1985,6 +2086,42 @@ restart: throttle_vm_writeout(sc->gfp_mask); } +/* Returns true if compaction should go ahead for a high-order request */ +static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) +{ + unsigned long balance_gap, watermark; + bool watermark_ok; + + /* Do not consider compaction for orders reclaim is meant to satisfy */ + if (sc->order <= PAGE_ALLOC_COSTLY_ORDER) + return false; + + /* + * Compaction takes time to run and there are potentially other + * callers using the pages just freed. Continue reclaiming until + * there is a buffer of free pages available to give compaction + * a reasonable chance of completing and allocating the page + */ + balance_gap = min(low_wmark_pages(zone), + (zone->present_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1) / + KSWAPD_ZONE_BALANCE_GAP_RATIO); + watermark = high_wmark_pages(zone) + balance_gap + (2UL << sc->order); + watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, 0, 0); + + /* + * If compaction is deferred, reclaim up to a point where + * compaction will have a chance of success when re-enabled + */ + if (compaction_deferred(zone)) + return watermark_ok; + + /* If compaction is not ready to start, keep reclaiming */ + if (!compaction_suitable(zone, sc->order)) + return false; + + return watermark_ok; +} + /* * This is the direct reclaim path, for page-allocating processes. We only * try to reclaim pages from zones which will satisfy the caller's allocation @@ -2000,14 +2137,20 @@ restart: * * If a zone is deemed to be full of pinned pages then just give it a light * scan then give up on it. + * + * This function returns true if a zone is being reclaimed for a costly + * high-order allocation and compaction is ready to begin. This indicates to + * the caller that it should consider retrying the allocation instead of + * further reclaim. */ -static void shrink_zones(int priority, struct zonelist *zonelist, +static bool shrink_zones(int priority, struct zonelist *zonelist, struct scan_control *sc) { struct zoneref *z; struct zone *zone; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; + bool aborted_reclaim = false; for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(sc->gfp_mask), sc->nodemask) { @@ -2022,6 +2165,21 @@ static void shrink_zones(int priority, struct zonelist *zonelist, continue; if (zone->all_unreclaimable && priority != DEF_PRIORITY) continue; /* Let kswapd poll it */ + if (COMPACTION_BUILD) { + /* + * If we already have plenty of memory free for + * compaction in this zone, don't free any more. + * Even though compaction is invoked for any + * non-zero order, only frequent costly order + * reclamation is disruptive enough to become a + * noticable problem, like transparent huge page + * allocations. + */ + if (compaction_ready(zone, sc)) { + aborted_reclaim = true; + continue; + } + } /* * This steals pages from memory cgroups over softlimit * and returns the number of reclaimed pages and @@ -2039,6 +2197,8 @@ static void shrink_zones(int priority, struct zonelist *zonelist, shrink_zone(priority, zone, sc); } + + return aborted_reclaim; } static bool zone_reclaimable(struct zone *zone) @@ -2092,8 +2252,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, struct zoneref *z; struct zone *zone; unsigned long writeback_threshold; + bool aborted_reclaim; - get_mems_allowed(); delayacct_freepages_start(); if (scanning_global_lru(sc)) @@ -2103,7 +2263,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, sc->nr_scanned = 0; if (!priority) disable_swap_token(sc->mem_cgroup); - shrink_zones(priority, zonelist, sc); + aborted_reclaim = shrink_zones(priority, zonelist, sc); + /* * Don't shrink slabs when reclaiming memory from * over limit cgroups @@ -2155,7 +2316,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, out: delayacct_freepages_end(); - put_mems_allowed(); if (sc->nr_reclaimed) return sc->nr_reclaimed; @@ -2168,6 +2328,10 @@ out: if (oom_killer_disabled) return 0; + /* Aborted reclaim to try compaction? don't OOM, then */ + if (aborted_reclaim) + return 1; + /* top priority shrink_zones still had more to do? don't OOM, then */ if (scanning_global_lru(sc) && !all_unreclaimable(zonelist, sc)) return 1; @@ -2459,6 +2623,9 @@ loop_again: high_wmark_pages(zone), 0, 0)) { end_zone = i; break; + } else { + /* If balanced, clear the congested flag */ + zone_clear_flag(zone, ZONE_CONGESTED); } } if (i < 0) @@ -2695,7 +2862,10 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx) * them before going back to sleep. */ set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold); - schedule(); + + if (!kthread_should_stop()) + schedule(); + set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold); } else { if (remaining) @@ -2722,7 +2892,9 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx) static int kswapd(void *p) { unsigned long order, new_order; + unsigned balanced_order; int classzone_idx, new_classzone_idx; + int balanced_classzone_idx; pg_data_t *pgdat = (pg_data_t*)p; struct task_struct *tsk = current; @@ -2753,7 +2925,9 @@ static int kswapd(void *p) set_freezable(); order = new_order = 0; + balanced_order = 0; classzone_idx = new_classzone_idx = pgdat->nr_zones - 1; + balanced_classzone_idx = classzone_idx; for ( ; ; ) { int ret; @@ -2762,7 +2936,8 @@ static int kswapd(void *p) * new request of a similar or harder type will succeed soon * so consider going to sleep on the basis we reclaimed at */ - if (classzone_idx >= new_classzone_idx && order == new_order) { + if (balanced_classzone_idx >= new_classzone_idx && + balanced_order == new_order) { new_order = pgdat->kswapd_max_order; new_classzone_idx = pgdat->classzone_idx; pgdat->kswapd_max_order = 0; @@ -2777,9 +2952,12 @@ static int kswapd(void *p) order = new_order; classzone_idx = new_classzone_idx; } else { - kswapd_try_to_sleep(pgdat, order, classzone_idx); + kswapd_try_to_sleep(pgdat, balanced_order, + balanced_classzone_idx); order = pgdat->kswapd_max_order; classzone_idx = pgdat->classzone_idx; + new_order = order; + new_classzone_idx = classzone_idx; pgdat->kswapd_max_order = 0; pgdat->classzone_idx = pgdat->nr_zones - 1; } @@ -2794,7 +2972,9 @@ static int kswapd(void *p) */ if (!ret) { trace_mm_vmscan_kswapd_wake(pgdat->node_id, order); - order = balance_pgdat(pgdat, order, &classzone_idx); + balanced_classzone_idx = classzone_idx; + balanced_order = balance_pgdat(pgdat, order, + &balanced_classzone_idx); } } return 0; diff --git a/mm/vmstat.c b/mm/vmstat.c index 20c18b7..6559013 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -78,7 +78,7 @@ void vm_events_fold_cpu(int cpu) * * vm_stat contains the global counters */ -atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; +atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp; EXPORT_SYMBOL(vm_stat); #ifdef CONFIG_SMP diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index 5ba4366..804e50f 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -424,9 +424,9 @@ static int __init caif_device_init(void) static void __exit caif_device_exit(void) { - unregister_pernet_subsys(&caif_net_ops); unregister_netdevice_notifier(&caif_device_notifier); dev_remove_pack(&caif_packet_type); + unregister_pernet_subsys(&caif_net_ops); } module_init(caif_device_init); diff --git a/net/core/dev.c b/net/core/dev.c index a71eafc..8235b81 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1163,6 +1163,7 @@ static int __dev_open(struct net_device *dev) net_dmaengine_get(); dev_set_rx_mode(dev); dev_activate(dev); + add_device_randomness(dev->dev_addr, dev->addr_len); } return ret; @@ -4730,6 +4731,7 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa) err = ops->ndo_set_mac_address(dev, sa); if (!err) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + add_device_randomness(dev->dev_addr, dev->addr_len); return err; } EXPORT_SYMBOL(dev_set_mac_address); @@ -5507,6 +5509,7 @@ int register_netdevice(struct net_device *dev) dev_init_scheduler(dev); dev_hold(dev); list_netdevice(dev); + add_device_randomness(dev->dev_addr, dev->addr_len); /* Notify protocols, that a new device appeared. */ ret = call_netdevice_notifiers(NETDEV_REGISTER, dev); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index abd936d..ac49ad5 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -647,6 +647,12 @@ static void set_operstate(struct net_device *dev, unsigned char transition) } } +static unsigned int rtnl_dev_get_flags(const struct net_device *dev) +{ + return (dev->flags & ~(IFF_PROMISC | IFF_ALLMULTI)) | + (dev->gflags & (IFF_PROMISC | IFF_ALLMULTI)); +} + static unsigned int rtnl_dev_combine_flags(const struct net_device *dev, const struct ifinfomsg *ifm) { @@ -655,7 +661,7 @@ static unsigned int rtnl_dev_combine_flags(const struct net_device *dev, /* bugwards compatibility: ifi_change == 0 is treated as ~0 */ if (ifm->ifi_change) flags = (flags & ifm->ifi_change) | - (dev->flags & ~ifm->ifi_change); + (rtnl_dev_get_flags(dev) & ~ifm->ifi_change); return flags; } @@ -1298,6 +1304,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, goto errout; send_addr_notify = 1; modified = 1; + add_device_randomness(dev->dev_addr, dev->addr_len); } if (tb[IFLA_MTU]) { diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 2b3c23c..062876b 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1725,8 +1725,10 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option) case CIPSO_V4_TAG_LOCAL: /* This is a non-standard tag that we only allow for * local connections, so if the incoming interface is - * not the loopback device drop the packet. */ - if (!(skb->dev->flags & IFF_LOOPBACK)) { + * not the loopback device drop the packet. Further, + * there is no legitimate reason for setting this from + * userspace so reject it if skb is NULL. */ + if (skb == NULL || !(skb->dev->flags & IFF_LOOPBACK)) { err_offset = opt_iter; goto validate_return_locked; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 58a944f..31741cf 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2409,7 +2409,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level, /* Cap the max timeout in ms TCP will retry/retrans * before giving up and aborting (ETIMEDOUT) a connection. */ - icsk->icsk_user_timeout = msecs_to_jiffies(val); + if (val < 0) + err = -EINVAL; + else + icsk->icsk_user_timeout = msecs_to_jiffies(val); break; default: err = -ENOPROTOOPT; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 6e33b79c..b76aa2d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5340,7 +5340,9 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, if (tp->copied_seq == tp->rcv_nxt && len - tcp_header_len <= tp->ucopy.len) { #ifdef CONFIG_NET_DMA - if (tcp_dma_try_early_copy(sk, skb, tcp_header_len)) { + if (tp->ucopy.task == current && + sock_owned_by_user(sk) && + tcp_dma_try_early_copy(sk, skb, tcp_header_len)) { copied_early = 1; eaten = 1; } diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 29e9980..370aa94 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -490,6 +490,7 @@ void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata) del_timer_sync(&sdata->u.mesh.housekeeping_timer); del_timer_sync(&sdata->u.mesh.mesh_path_root_timer); + del_timer_sync(&sdata->u.mesh.mesh_path_timer); /* * If the timer fired while we waited for it, it will have * requeued the work. Now the work will be running again diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 47ee29f..e85b2487 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -556,6 +556,8 @@ static int sfb_dump(struct Qdisc *sch, struct sk_buff *skb) sch->qstats.backlog = q->qdisc->qstats.backlog; opts = nla_nest_start(skb, TCA_OPTIONS); + if (opts == NULL) + goto nla_put_failure; NLA_PUT(skb, TCA_SFB_PARMS, sizeof(opt), &opt); return nla_nest_end(skb, opts); diff --git a/net/sctp/input.c b/net/sctp/input.c index 741ed16..cd9eded 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -737,15 +737,12 @@ static void __sctp_unhash_endpoint(struct sctp_endpoint *ep) epb = &ep->base; - if (hlist_unhashed(&epb->node)) - return; - epb->hashent = sctp_ep_hashfn(epb->bind_addr.port); head = &sctp_ep_hashtable[epb->hashent]; sctp_write_lock(&head->lock); - __hlist_del(&epb->node); + hlist_del_init(&epb->node); sctp_write_unlock(&head->lock); } @@ -826,7 +823,7 @@ static void __sctp_unhash_established(struct sctp_association *asoc) head = &sctp_assoc_hashtable[epb->hashent]; sctp_write_lock(&head->lock); - __hlist_del(&epb->node); + hlist_del_init(&epb->node); sctp_write_unlock(&head->lock); } diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 4434853..b70a3ee 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1160,8 +1160,14 @@ out_free: SCTP_DEBUG_PRINTK("About to exit __sctp_connect() free asoc: %p" " kaddrs: %p err: %d\n", asoc, kaddrs, err); - if (asoc) + if (asoc) { + /* sctp_primitive_ASSOCIATE may have added this association + * To the hash table, try to unhash it, just in case, its a noop + * if it wasn't hashed so we're safe + */ + sctp_unhash_established(asoc); sctp_association_free(asoc); + } return err; } @@ -1871,8 +1877,10 @@ SCTP_STATIC int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, goto out_unlock; out_free: - if (new_asoc) + if (new_asoc) { + sctp_unhash_established(asoc); sctp_association_free(asoc); + } out_unlock: sctp_release_sock(sk); diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index e45d2fb..bf0a7f6 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -193,7 +193,7 @@ static int rpcb_create_local_unix(void) if (IS_ERR(clnt)) { dprintk("RPC: failed to create AF_LOCAL rpcbind " "client (errno %ld).\n", PTR_ERR(clnt)); - result = -PTR_ERR(clnt); + result = PTR_ERR(clnt); goto out; } @@ -242,7 +242,7 @@ static int rpcb_create_local_net(void) if (IS_ERR(clnt)) { dprintk("RPC: failed to create local rpcbind " "client (errno %ld).\n", PTR_ERR(clnt)); - result = -PTR_ERR(clnt); + result = PTR_ERR(clnt); goto out; } diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index b6bb225..c57f97f 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -713,7 +713,9 @@ void rpc_execute(struct rpc_task *task) static void rpc_async_schedule(struct work_struct *work) { + current->flags |= PF_FSTRANS; __rpc_execute(container_of(work, struct rpc_task, u.tk_work)); + current->flags &= ~PF_FSTRANS; } /** diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 0867070..d0b5210 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -200,6 +200,7 @@ xprt_rdma_connect_worker(struct work_struct *work) int rc = 0; if (!xprt->shutdown) { + current->flags |= PF_FSTRANS; xprt_clear_connected(xprt); dprintk("RPC: %s: %sconnect\n", __func__, @@ -212,10 +213,10 @@ xprt_rdma_connect_worker(struct work_struct *work) out: xprt_wake_pending_tasks(xprt, rc); - out_clear: dprintk("RPC: %s: exit\n", __func__); xprt_clear_connecting(xprt); + current->flags &= ~PF_FSTRANS; } /* diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index ea75079..554111f 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1882,6 +1882,8 @@ static void xs_local_setup_socket(struct work_struct *work) if (xprt->shutdown) goto out; + current->flags |= PF_FSTRANS; + clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); status = __sock_create(xprt->xprt_net, AF_LOCAL, SOCK_STREAM, 0, &sock, 1); @@ -1915,6 +1917,7 @@ static void xs_local_setup_socket(struct work_struct *work) out: xprt_clear_connecting(xprt); xprt_wake_pending_tasks(xprt, status); + current->flags &= ~PF_FSTRANS; } static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) @@ -1957,6 +1960,8 @@ static void xs_udp_setup_socket(struct work_struct *work) if (xprt->shutdown) goto out; + current->flags |= PF_FSTRANS; + /* Start by resetting any existing state */ xs_reset_transport(transport); sock = xs_create_sock(xprt, transport, @@ -1975,6 +1980,7 @@ static void xs_udp_setup_socket(struct work_struct *work) out: xprt_clear_connecting(xprt); xprt_wake_pending_tasks(xprt, status); + current->flags &= ~PF_FSTRANS; } /* @@ -2100,6 +2106,8 @@ static void xs_tcp_setup_socket(struct work_struct *work) if (xprt->shutdown) goto out; + current->flags |= PF_FSTRANS; + if (!sock) { clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); sock = xs_create_sock(xprt, transport, @@ -2149,6 +2157,7 @@ static void xs_tcp_setup_socket(struct work_struct *work) case -EINPROGRESS: case -EALREADY: xprt_clear_connecting(xprt); + current->flags &= ~PF_FSTRANS; return; case -EINVAL: /* Happens, for instance, if the user specified a link @@ -2161,6 +2170,7 @@ out_eagain: out: xprt_clear_connecting(xprt); xprt_wake_pending_tasks(xprt, status); + current->flags &= ~PF_FSTRANS; } /** diff --git a/net/wanrouter/wanmain.c b/net/wanrouter/wanmain.c index 788a12c..2ab7850 100644 --- a/net/wanrouter/wanmain.c +++ b/net/wanrouter/wanmain.c @@ -602,36 +602,31 @@ static int wanrouter_device_new_if(struct wan_device *wandev, * successfully, add it to the interface list. */ - if (dev->name == NULL) { - err = -EINVAL; - } else { +#ifdef WANDEBUG + printk(KERN_INFO "%s: registering interface %s...\n", + wanrouter_modname, dev->name); +#endif - #ifdef WANDEBUG - printk(KERN_INFO "%s: registering interface %s...\n", - wanrouter_modname, dev->name); - #endif - - err = register_netdev(dev); - if (!err) { - struct net_device *slave = NULL; - unsigned long smp_flags=0; - - lock_adapter_irq(&wandev->lock, &smp_flags); - - if (wandev->dev == NULL) { - wandev->dev = dev; - } else { - for (slave=wandev->dev; - DEV_TO_SLAVE(slave); - slave = DEV_TO_SLAVE(slave)) - DEV_TO_SLAVE(slave) = dev; - } - ++wandev->ndev; - - unlock_adapter_irq(&wandev->lock, &smp_flags); - err = 0; /* done !!! */ - goto out; + err = register_netdev(dev); + if (!err) { + struct net_device *slave = NULL; + unsigned long smp_flags=0; + + lock_adapter_irq(&wandev->lock, &smp_flags); + + if (wandev->dev == NULL) { + wandev->dev = dev; + } else { + for (slave=wandev->dev; + DEV_TO_SLAVE(slave); + slave = DEV_TO_SLAVE(slave)) + DEV_TO_SLAVE(slave) = dev; } + ++wandev->ndev; + + unlock_adapter_irq(&wandev->lock, &smp_flags); + err = 0; /* done !!! */ + goto out; } if (wandev->del_if) wandev->del_if(wandev, dev); diff --git a/net/wireless/core.c b/net/wireless/core.c index 880dbe2..498c760 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -959,6 +959,11 @@ static int cfg80211_netdev_notifier_call(struct notifier_block * nb, */ synchronize_rcu(); INIT_LIST_HEAD(&wdev->list); + /* + * Ensure that all events have been processed and + * freed. + */ + cfg80211_process_wdev_events(wdev); break; case NETDEV_PRE_UP: if (!(wdev->wiphy->interface_modes & BIT(wdev->iftype))) diff --git a/net/wireless/core.h b/net/wireless/core.h index a570ff9..8351645 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -426,6 +426,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, struct net_device *dev, enum nl80211_iftype ntype, u32 *flags, struct vif_params *params); void cfg80211_process_rdev_events(struct cfg80211_registered_device *rdev); +void cfg80211_process_wdev_events(struct wireless_dev *wdev); int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, diff --git a/net/wireless/util.c b/net/wireless/util.c index bbcb58e..18e22be 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -719,7 +719,7 @@ void cfg80211_upload_connect_keys(struct wireless_dev *wdev) wdev->connect_keys = NULL; } -static void cfg80211_process_wdev_events(struct wireless_dev *wdev) +void cfg80211_process_wdev_events(struct wireless_dev *wdev) { struct cfg80211_event *ev; unsigned long flags; @@ -975,6 +975,9 @@ int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, } mutex_unlock(&rdev->devlist_mtx); + if (total == 1) + return 0; + for (i = 0; i < rdev->wiphy.n_iface_combinations; i++) { const struct ieee80211_iface_combination *c; struct ieee80211_iface_limit *limits; diff --git a/sound/drivers/mpu401/mpu401_uart.c b/sound/drivers/mpu401/mpu401_uart.c index 2af0999..74f5a3d 100644 --- a/sound/drivers/mpu401/mpu401_uart.c +++ b/sound/drivers/mpu401/mpu401_uart.c @@ -554,6 +554,7 @@ int snd_mpu401_uart_new(struct snd_card *card, int device, spin_lock_init(&mpu->output_lock); spin_lock_init(&mpu->timer_lock); mpu->hardware = hardware; + mpu->irq = -1; if (! (info_flags & MPU401_INFO_INTEGRATED)) { int res_size = hardware == MPU401_HW_PC98II ? 4 : 2; mpu->res = request_region(port, res_size, "MPU401 UART"); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index baa7a49..8d288a7 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -20133,6 +20133,7 @@ static const struct hda_codec_preset snd_hda_preset_realtek[] = { { .id = 0x10ec0275, .name = "ALC275", .patch = patch_alc269 }, { .id = 0x10ec0276, .name = "ALC276", .patch = patch_alc269 }, { .id = 0x10ec0280, .name = "ALC280", .patch = patch_alc269 }, + { .id = 0x10ec0282, .name = "ALC282", .patch = patch_alc269 }, { .id = 0x10ec0861, .rev = 0x100340, .name = "ALC660", .patch = patch_alc861 }, { .id = 0x10ec0660, .name = "ALC660-VD", .patch = patch_alc861vd }, diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c index c850e3d..f16f587 100644 --- a/sound/soc/codecs/wm8962.c +++ b/sound/soc/codecs/wm8962.c @@ -2890,6 +2890,9 @@ static int wm8962_set_bias_level(struct snd_soc_codec *codec, /* VMID 2*250k */ snd_soc_update_bits(codec, WM8962_PWR_MGMT_1, WM8962_VMID_SEL_MASK, 0x100); + + if (codec->dapm.bias_level == SND_SOC_BIAS_OFF) + msleep(100); break; case SND_SOC_BIAS_OFF: diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c index 2194912..1f7616d 100644 --- a/sound/soc/codecs/wm8994.c +++ b/sound/soc/codecs/wm8994.c @@ -2127,7 +2127,7 @@ static int wm8994_hw_params(struct snd_pcm_substream *substream, return -EINVAL; } - bclk_rate = params_rate(params) * 2; + bclk_rate = params_rate(params) * 4; switch (params_format(params)) { case SNDRV_PCM_FORMAT_S16_LE: bclk_rate *= 16; diff --git a/sound/usb/clock.c b/sound/usb/clock.c index 075195e..f0ff776 100644 --- a/sound/usb/clock.c +++ b/sound/usb/clock.c @@ -111,7 +111,8 @@ static bool uac_clock_source_is_valid(struct snd_usb_audio *chip, int source_id) return 0; /* If a clock source can't tell us whether it's valid, we assume it is */ - if (!uac2_control_is_readable(cs_desc->bmControls, UAC2_CS_CONTROL_CLOCK_VALID)) + if (!uac2_control_is_readable(cs_desc->bmControls, + UAC2_CS_CONTROL_CLOCK_VALID - 1)) return 1; err = snd_usb_ctl_msg(dev, usb_rcvctrlpipe(dev, 0), UAC2_CS_CUR, |