diff --git a/Makefile b/Makefile index ad91a79aed51..94d663c935c0 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 4 -SUBLEVEL = 71 +SUBLEVEL = 72 EXTRAVERSION = NAME = Blurry Fish Butt diff --git a/arch/arm/kvm/init.S b/arch/arm/kvm/init.S index 3988e72d16ff..bfc5aae0c280 100644 --- a/arch/arm/kvm/init.S +++ b/arch/arm/kvm/init.S @@ -110,7 +110,6 @@ __do_hyp_init: @ - Write permission implies XN: disabled @ - Instruction cache: enabled @ - Data/Unified cache: enabled - @ - Memory alignment checks: enabled @ - MMU: enabled (this code must be run from an identity mapping) mrc p15, 4, r0, c1, c0, 0 @ HSCR ldr r2, =HSCTLR_MASK @@ -118,8 +117,8 @@ __do_hyp_init: mrc p15, 0, r1, c1, c0, 0 @ SCTLR ldr r2, =(HSCTLR_EE | HSCTLR_FI | HSCTLR_I | HSCTLR_C) and r1, r1, r2 - ARM( ldr r2, =(HSCTLR_M | HSCTLR_A) ) - THUMB( ldr r2, =(HSCTLR_M | HSCTLR_A | HSCTLR_TE) ) + ARM( ldr r2, =(HSCTLR_M) ) + THUMB( ldr r2, =(HSCTLR_M | HSCTLR_TE) ) orr r1, r1, r2 orr r0, r0, r1 isb diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 01cf10556081..1f1ff7e7b9cf 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -869,6 +869,9 @@ static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache pmd_t *pmd; pud = stage2_get_pud(kvm, cache, addr); + if (!pud) + return NULL; + if (pud_none(*pud)) { if (!cache) return NULL; diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h new file mode 100644 index 000000000000..be2d2347d995 --- /dev/null +++ b/arch/arm64/include/asm/asm-uaccess.h @@ -0,0 +1,13 @@ +#ifndef __ASM_ASM_UACCESS_H +#define __ASM_ASM_UACCESS_H + +/* + * Remove the address tag from a virtual address, if present. + */ + .macro clear_address_tag, dst, addr + tst \addr, #(1 << 55) + bic \dst, \addr, #(0xff << 56) + csel \dst, \dst, \addr, eq + .endm + +#endif diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index 9622eb48f894..f2d2c0bbe21b 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -41,23 +41,33 @@ #define smp_store_release(p, v) \ do { \ + union { typeof(*p) __val; char __c[1]; } __u = \ + { .__val = (__force typeof(*p)) (v) }; \ compiletime_assert_atomic_type(*p); \ switch (sizeof(*p)) { \ case 1: \ asm volatile ("stlrb %w1, %0" \ - : "=Q" (*p) : "r" (v) : "memory"); \ + : "=Q" (*p) \ + : "r" (*(__u8 *)__u.__c) \ + : "memory"); \ break; \ case 2: \ asm volatile ("stlrh %w1, %0" \ - : "=Q" (*p) : "r" (v) : "memory"); \ + : "=Q" (*p) \ + : "r" (*(__u16 *)__u.__c) \ + : "memory"); \ break; \ case 4: \ asm volatile ("stlr %w1, %0" \ - : "=Q" (*p) : "r" (v) : "memory"); \ + : "=Q" (*p) \ + : "r" (*(__u32 *)__u.__c) \ + : "memory"); \ break; \ case 8: \ asm volatile ("stlr %1, %0" \ - : "=Q" (*p) : "r" (v) : "memory"); \ + : "=Q" (*p) \ + : "r" (*(__u64 *)__u.__c) \ + : "memory"); \ break; \ } \ } while (0) diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index d9ca1f2c0ea8..829fa6d3e561 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -21,6 +21,7 @@ /* * User space memory access functions */ +#include #include #include @@ -103,6 +104,13 @@ static inline void set_fs(mm_segment_t fs) flag; \ }) +/* + * When dealing with data aborts, watchpoints, or instruction traps we may end + * up with a tagged userland pointer. Clear the tag to get a sane pointer to + * pass on to access_ok(), for instance. + */ +#define untagged_addr(addr) sign_extend64(addr, 55) + #define access_ok(type, addr, size) __range_ok(addr, size) #define user_addr_max get_fs diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index 937f5e58a4d3..478a00b9732b 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -305,7 +305,8 @@ static void register_insn_emulation_sysctl(struct ctl_table *table) ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, \ CONFIG_ARM64_PAN) \ : "=&r" (res), "+r" (data), "=&r" (temp) \ - : "r" (addr), "i" (-EAGAIN), "i" (-EFAULT) \ + : "r" ((unsigned long)addr), "i" (-EAGAIN), \ + "i" (-EFAULT) \ : "memory") #define __user_swp_asm(data, addr, res, temp) \ diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index bd14849beb73..dccd0c2e9023 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -29,6 +29,7 @@ #include #include #include +#include #include /* @@ -316,12 +317,13 @@ el1_da: /* * Data abort handling */ - mrs x0, far_el1 + mrs x3, far_el1 enable_dbg // re-enable interrupts if they were enabled in the aborted context tbnz x23, #7, 1f // PSR_I_BIT enable_irq 1: + clear_address_tag x0, x3 mov x2, sp // struct pt_regs bl do_mem_abort @@ -483,7 +485,7 @@ el0_da: // enable interrupts before calling the main handler enable_dbg_and_irq ct_user_exit - bic x0, x26, #(0xff << 56) + clear_address_tag x0, x26 mov x1, x25 mov x2, sp bl do_mem_abort diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index b45c95d34b83..eeebfc315526 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -35,6 +35,7 @@ #include #include #include +#include /* Breakpoint currently in use for each BRP. */ static DEFINE_PER_CPU(struct perf_event *, bp_on_reg[ARM_MAX_BRP]); @@ -690,7 +691,7 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, /* Check if the watchpoint value matches. */ val = read_wb_reg(AARCH64_DBG_REG_WVR, i); - if (val != (addr & ~alignment_mask)) + if (val != (untagged_addr(addr) & ~alignment_mask)) goto unlock; /* Possible match, check the byte address select to confirm. */ diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 8b3b46b7b0f2..329771559cbb 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -44,8 +44,22 @@ extern void __init dump_numa_cpu_topology(void); extern int sysfs_add_device_to_node(struct device *dev, int nid); extern void sysfs_remove_device_from_node(struct device *dev, int nid); +static inline int early_cpu_to_node(int cpu) +{ + int nid; + + nid = numa_cpu_lookup_table[cpu]; + + /* + * Fall back to node 0 if nid is unset (it should be, except bugs). + * This allows callers to safely do NODE_DATA(early_cpu_to_node(cpu)). + */ + return (nid < 0) ? 0 : nid; +} #else +static inline int early_cpu_to_node(int cpu) { return 0; } + static inline void dump_numa_cpu_topology(void) {} static inline int sysfs_add_device_to_node(struct device *dev, int nid) diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index c314db8b798c..9837c98caabe 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -655,7 +655,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) */ #define MAX_WAIT_FOR_RECOVERY 300 -static void eeh_handle_normal_event(struct eeh_pe *pe) +static bool eeh_handle_normal_event(struct eeh_pe *pe) { struct pci_bus *frozen_bus; int rc = 0; @@ -665,7 +665,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe) if (!frozen_bus) { pr_err("%s: Cannot find PCI bus for PHB#%d-PE#%x\n", __func__, pe->phb->global_number, pe->addr); - return; + return false; } eeh_pe_update_time_stamp(pe); @@ -790,7 +790,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe) pr_info("EEH: Notify device driver to resume\n"); eeh_pe_dev_traverse(pe, eeh_report_resume, NULL); - return; + return false; excess_failures: /* @@ -831,7 +831,11 @@ perm_error: pci_lock_rescan_remove(); pcibios_remove_pci_devices(frozen_bus); pci_unlock_rescan_remove(); + + /* The passed PE should no longer be used */ + return true; } + return false; } static void eeh_handle_special_event(void) @@ -897,7 +901,14 @@ static void eeh_handle_special_event(void) */ if (rc == EEH_NEXT_ERR_FROZEN_PE || rc == EEH_NEXT_ERR_FENCED_PHB) { - eeh_handle_normal_event(pe); + /* + * eeh_handle_normal_event() can make the PE stale if it + * determines that the PE cannot possibly be recovered. + * Don't modify the PE state if that's the case. + */ + if (eeh_handle_normal_event(pe)) + continue; + eeh_pe_state_clear(pe, EEH_PE_RECOVERING); } else { pci_lock_rescan_remove(); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index a20823210ac0..fe6e800c1357 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -751,7 +751,7 @@ void __init setup_arch(char **cmdline_p) static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align) { - return __alloc_bootmem_node(NODE_DATA(cpu_to_node(cpu)), size, align, + return __alloc_bootmem_node(NODE_DATA(early_cpu_to_node(cpu)), size, align, __pa(MAX_DMA_ADDRESS)); } @@ -762,7 +762,7 @@ static void __init pcpu_fc_free(void *ptr, size_t size) static int pcpu_cpu_distance(unsigned int from, unsigned int to) { - if (cpu_to_node(from) == cpu_to_node(to)) + if (early_cpu_to_node(from) == early_cpu_to_node(to)) return LOCAL_DISTANCE; else return REMOTE_DISTANCE; diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index e9ff44cd5d86..e8b1027e1b5b 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -110,6 +110,7 @@ static struct property *dlpar_clone_drconf_property(struct device_node *dn) for (i = 0; i < num_lmbs; i++) { lmbs[i].base_addr = be64_to_cpu(lmbs[i].base_addr); lmbs[i].drc_index = be32_to_cpu(lmbs[i].drc_index); + lmbs[i].aa_index = be32_to_cpu(lmbs[i].aa_index); lmbs[i].flags = be32_to_cpu(lmbs[i].flags); } @@ -553,6 +554,7 @@ static void dlpar_update_drconf_property(struct device_node *dn, for (i = 0; i < num_lmbs; i++) { lmbs[i].base_addr = cpu_to_be64(lmbs[i].base_addr); lmbs[i].drc_index = cpu_to_be32(lmbs[i].drc_index); + lmbs[i].aa_index = cpu_to_be32(lmbs[i].aa_index); lmbs[i].flags = cpu_to_be32(lmbs[i].flags); } diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 56442d2d7bbc..eb9487470141 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -182,9 +182,9 @@ config NR_CPUS int "Maximum number of CPUs" depends on SMP range 2 32 if SPARC32 - range 2 1024 if SPARC64 + range 2 4096 if SPARC64 default 32 if SPARC32 - default 64 if SPARC64 + default 4096 if SPARC64 source kernel/Kconfig.hz diff --git a/arch/sparc/include/asm/mmu_64.h b/arch/sparc/include/asm/mmu_64.h index f7de0dbc38af..83b36a5371ff 100644 --- a/arch/sparc/include/asm/mmu_64.h +++ b/arch/sparc/include/asm/mmu_64.h @@ -52,7 +52,7 @@ #define CTX_NR_MASK TAG_CONTEXT_BITS #define CTX_HW_MASK (CTX_NR_MASK | CTX_PGSZ_MASK) -#define CTX_FIRST_VERSION ((_AC(1,UL) << CTX_VERSION_SHIFT) + _AC(1,UL)) +#define CTX_FIRST_VERSION BIT(CTX_VERSION_SHIFT) #define CTX_VALID(__ctx) \ (!(((__ctx.sparc64_ctx_val) ^ tlb_context_cache) & CTX_VERSION_MASK)) #define CTX_HWBITS(__ctx) ((__ctx.sparc64_ctx_val) & CTX_HW_MASK) diff --git a/arch/sparc/include/asm/mmu_context_64.h b/arch/sparc/include/asm/mmu_context_64.h index b84be675e507..349dd23e2876 100644 --- a/arch/sparc/include/asm/mmu_context_64.h +++ b/arch/sparc/include/asm/mmu_context_64.h @@ -17,13 +17,8 @@ extern spinlock_t ctx_alloc_lock; extern unsigned long tlb_context_cache; extern unsigned long mmu_context_bmap[]; +DECLARE_PER_CPU(struct mm_struct *, per_cpu_secondary_mm); void get_new_mmu_context(struct mm_struct *mm); -#ifdef CONFIG_SMP -void smp_new_mmu_context_version(void); -#else -#define smp_new_mmu_context_version() do { } while (0) -#endif - int init_new_context(struct task_struct *tsk, struct mm_struct *mm); void destroy_context(struct mm_struct *mm); @@ -74,8 +69,9 @@ void __flush_tlb_mm(unsigned long, unsigned long); static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, struct task_struct *tsk) { unsigned long ctx_valid, flags; - int cpu; + int cpu = smp_processor_id(); + per_cpu(per_cpu_secondary_mm, cpu) = mm; if (unlikely(mm == &init_mm)) return; @@ -121,7 +117,6 @@ static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, str * for the first time, we must flush that context out of the * local TLB. */ - cpu = smp_processor_id(); if (!ctx_valid || !cpumask_test_cpu(cpu, mm_cpumask(mm))) { cpumask_set_cpu(cpu, mm_cpumask(mm)); __flush_tlb_mm(CTX_HWBITS(mm->context), @@ -131,26 +126,7 @@ static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, str } #define deactivate_mm(tsk,mm) do { } while (0) - -/* Activate a new MM instance for the current task. */ -static inline void activate_mm(struct mm_struct *active_mm, struct mm_struct *mm) -{ - unsigned long flags; - int cpu; - - spin_lock_irqsave(&mm->context.lock, flags); - if (!CTX_VALID(mm->context)) - get_new_mmu_context(mm); - cpu = smp_processor_id(); - if (!cpumask_test_cpu(cpu, mm_cpumask(mm))) - cpumask_set_cpu(cpu, mm_cpumask(mm)); - - load_secondary_context(mm); - __flush_tlb_mm(CTX_HWBITS(mm->context), SECONDARY_CONTEXT); - tsb_context_switch(mm); - spin_unlock_irqrestore(&mm->context.lock, flags); -} - +#define activate_mm(active_mm, mm) switch_mm(active_mm, mm, NULL) #endif /* !(__ASSEMBLY__) */ #endif /* !(__SPARC64_MMU_CONTEXT_H) */ diff --git a/arch/sparc/include/asm/pil.h b/arch/sparc/include/asm/pil.h index 266937030546..522b43db2ed3 100644 --- a/arch/sparc/include/asm/pil.h +++ b/arch/sparc/include/asm/pil.h @@ -20,7 +20,6 @@ #define PIL_SMP_CALL_FUNC 1 #define PIL_SMP_RECEIVE_SIGNAL 2 #define PIL_SMP_CAPTURE 3 -#define PIL_SMP_CTX_NEW_VERSION 4 #define PIL_DEVICE_IRQ 5 #define PIL_SMP_CALL_FUNC_SNGL 6 #define PIL_DEFERRED_PCR_WORK 7 diff --git a/arch/sparc/include/asm/vio.h b/arch/sparc/include/asm/vio.h index 8174f6cdbbbb..9dca7a892978 100644 --- a/arch/sparc/include/asm/vio.h +++ b/arch/sparc/include/asm/vio.h @@ -327,6 +327,7 @@ struct vio_dev { int compat_len; u64 dev_no; + u64 id; unsigned long channel_id; diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c index e22416ce56ea..bfbde8c4ffb2 100644 --- a/arch/sparc/kernel/irq_64.c +++ b/arch/sparc/kernel/irq_64.c @@ -1034,17 +1034,26 @@ static void __init init_cpu_send_mondo_info(struct trap_per_cpu *tb) { #ifdef CONFIG_SMP unsigned long page; + void *mondo, *p; - BUILD_BUG_ON((NR_CPUS * sizeof(u16)) > (PAGE_SIZE - 64)); + BUILD_BUG_ON((NR_CPUS * sizeof(u16)) > PAGE_SIZE); + + /* Make sure mondo block is 64byte aligned */ + p = kzalloc(127, GFP_KERNEL); + if (!p) { + prom_printf("SUN4V: Error, cannot allocate mondo block.\n"); + prom_halt(); + } + mondo = (void *)(((unsigned long)p + 63) & ~0x3f); + tb->cpu_mondo_block_pa = __pa(mondo); page = get_zeroed_page(GFP_KERNEL); if (!page) { - prom_printf("SUN4V: Error, cannot allocate cpu mondo page.\n"); + prom_printf("SUN4V: Error, cannot allocate cpu list page.\n"); prom_halt(); } - tb->cpu_mondo_block_pa = __pa(page); - tb->cpu_list_pa = __pa(page + 64); + tb->cpu_list_pa = __pa(page); #endif } diff --git a/arch/sparc/kernel/kernel.h b/arch/sparc/kernel/kernel.h index e7f652be9e61..44f32dd4477f 100644 --- a/arch/sparc/kernel/kernel.h +++ b/arch/sparc/kernel/kernel.h @@ -37,7 +37,6 @@ void handle_stdfmna(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr /* smp_64.c */ void __irq_entry smp_call_function_client(int irq, struct pt_regs *regs); void __irq_entry smp_call_function_single_client(int irq, struct pt_regs *regs); -void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs); void __irq_entry smp_penguin_jailcell(int irq, struct pt_regs *regs); void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs); diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 19cd08d18672..95a9fa0d2195 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -959,37 +959,6 @@ void flush_dcache_page_all(struct mm_struct *mm, struct page *page) preempt_enable(); } -void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs) -{ - struct mm_struct *mm; - unsigned long flags; - - clear_softint(1 << irq); - - /* See if we need to allocate a new TLB context because - * the version of the one we are using is now out of date. - */ - mm = current->active_mm; - if (unlikely(!mm || (mm == &init_mm))) - return; - - spin_lock_irqsave(&mm->context.lock, flags); - - if (unlikely(!CTX_VALID(mm->context))) - get_new_mmu_context(mm); - - spin_unlock_irqrestore(&mm->context.lock, flags); - - load_secondary_context(mm); - __flush_tlb_mm(CTX_HWBITS(mm->context), - SECONDARY_CONTEXT); -} - -void smp_new_mmu_context_version(void) -{ - smp_cross_call(&xcall_new_mmu_context_version, 0, 0, 0); -} - #ifdef CONFIG_KGDB void kgdb_roundup_cpus(unsigned long flags) { diff --git a/arch/sparc/kernel/tsb.S b/arch/sparc/kernel/tsb.S index d568c8207af7..395ec1800530 100644 --- a/arch/sparc/kernel/tsb.S +++ b/arch/sparc/kernel/tsb.S @@ -470,13 +470,16 @@ __tsb_context_switch: .type copy_tsb,#function copy_tsb: /* %o0=old_tsb_base, %o1=old_tsb_size * %o2=new_tsb_base, %o3=new_tsb_size + * %o4=page_size_shift */ sethi %uhi(TSB_PASS_BITS), %g7 srlx %o3, 4, %o3 - add %o0, %o1, %g1 /* end of old tsb */ + add %o0, %o1, %o1 /* end of old tsb */ sllx %g7, 32, %g7 sub %o3, 1, %o3 /* %o3 == new tsb hash mask */ + mov %o4, %g1 /* page_size_shift */ + 661: prefetcha [%o0] ASI_N, #one_read .section .tsb_phys_patch, "ax" .word 661b @@ -501,9 +504,9 @@ copy_tsb: /* %o0=old_tsb_base, %o1=old_tsb_size /* This can definitely be computed faster... */ srlx %o0, 4, %o5 /* Build index */ and %o5, 511, %o5 /* Mask index */ - sllx %o5, PAGE_SHIFT, %o5 /* Put into vaddr position */ + sllx %o5, %g1, %o5 /* Put into vaddr position */ or %o4, %o5, %o4 /* Full VADDR. */ - srlx %o4, PAGE_SHIFT, %o4 /* Shift down to create index */ + srlx %o4, %g1, %o4 /* Shift down to create index */ and %o4, %o3, %o4 /* Mask with new_tsb_nents-1 */ sllx %o4, 4, %o4 /* Shift back up into tsb ent offset */ TSB_STORE(%o2 + %o4, %g2) /* Store TAG */ @@ -511,7 +514,7 @@ copy_tsb: /* %o0=old_tsb_base, %o1=old_tsb_size TSB_STORE(%o2 + %o4, %g3) /* Store TTE */ 80: add %o0, 16, %o0 - cmp %o0, %g1 + cmp %o0, %o1 bne,pt %xcc, 90b nop diff --git a/arch/sparc/kernel/ttable_64.S b/arch/sparc/kernel/ttable_64.S index c6dfdaa29e20..170ead662f2a 100644 --- a/arch/sparc/kernel/ttable_64.S +++ b/arch/sparc/kernel/ttable_64.S @@ -50,7 +50,7 @@ tl0_resv03e: BTRAP(0x3e) BTRAP(0x3f) BTRAP(0x40) tl0_irq1: TRAP_IRQ(smp_call_function_client, 1) tl0_irq2: TRAP_IRQ(smp_receive_signal_client, 2) tl0_irq3: TRAP_IRQ(smp_penguin_jailcell, 3) -tl0_irq4: TRAP_IRQ(smp_new_mmu_context_version_client, 4) +tl0_irq4: BTRAP(0x44) #else tl0_irq1: BTRAP(0x41) tl0_irq2: BTRAP(0x42) diff --git a/arch/sparc/kernel/vio.c b/arch/sparc/kernel/vio.c index cb5789c9f961..34824ca396f0 100644 --- a/arch/sparc/kernel/vio.c +++ b/arch/sparc/kernel/vio.c @@ -284,13 +284,16 @@ static struct vio_dev *vio_create_one(struct mdesc_handle *hp, u64 mp, if (!id) { dev_set_name(&vdev->dev, "%s", bus_id_name); vdev->dev_no = ~(u64)0; + vdev->id = ~(u64)0; } else if (!cfg_handle) { dev_set_name(&vdev->dev, "%s-%llu", bus_id_name, *id); vdev->dev_no = *id; + vdev->id = ~(u64)0; } else { dev_set_name(&vdev->dev, "%s-%llu-%llu", bus_id_name, *cfg_handle, *id); vdev->dev_no = *cfg_handle; + vdev->id = *id; } vdev->dev.parent = parent; @@ -333,27 +336,84 @@ static void vio_add(struct mdesc_handle *hp, u64 node) (void) vio_create_one(hp, node, &root_vdev->dev); } +struct vio_md_node_query { + const char *type; + u64 dev_no; + u64 id; +}; + static int vio_md_node_match(struct device *dev, void *arg) { + struct vio_md_node_query *query = (struct vio_md_node_query *) arg; struct vio_dev *vdev = to_vio_dev(dev); - if (vdev->mp == (u64) arg) - return 1; + if (vdev->dev_no != query->dev_no) + return 0; + if (vdev->id != query->id) + return 0; + if (strcmp(vdev->type, query->type)) + return 0; - return 0; + return 1; } static void vio_remove(struct mdesc_handle *hp, u64 node) { + const char *type; + const u64 *id, *cfg_handle; + u64 a; + struct vio_md_node_query query; struct device *dev; - dev = device_find_child(&root_vdev->dev, (void *) node, + type = mdesc_get_property(hp, node, "device-type", NULL); + if (!type) { + type = mdesc_get_property(hp, node, "name", NULL); + if (!type) + type = mdesc_node_name(hp, node); + } + + query.type = type; + + id = mdesc_get_property(hp, node, "id", NULL); + cfg_handle = NULL; + mdesc_for_each_arc(a, hp, node, MDESC_ARC_TYPE_BACK) { + u64 target; + + target = mdesc_arc_target(hp, a); + cfg_handle = mdesc_get_property(hp, target, + "cfg-handle", NULL); + if (cfg_handle) + break; + } + + if (!id) { + query.dev_no = ~(u64)0; + query.id = ~(u64)0; + } else if (!cfg_handle) { + query.dev_no = *id; + query.id = ~(u64)0; + } else { + query.dev_no = *cfg_handle; + query.id = *id; + } + + dev = device_find_child(&root_vdev->dev, &query, vio_md_node_match); if (dev) { printk(KERN_INFO "VIO: Removing device %s\n", dev_name(dev)); device_unregister(dev); put_device(dev); + } else { + if (!id) + printk(KERN_ERR "VIO: Removed unknown %s node.\n", + type); + else if (!cfg_handle) + printk(KERN_ERR "VIO: Removed unknown %s node %llu.\n", + type, *id); + else + printk(KERN_ERR "VIO: Removed unknown %s node %llu-%llu.\n", + type, *cfg_handle, *id); } } diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 965655afdbb6..384aba109d7c 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -656,10 +656,58 @@ EXPORT_SYMBOL(__flush_dcache_range); /* get_new_mmu_context() uses "cache + 1". */ DEFINE_SPINLOCK(ctx_alloc_lock); -unsigned long tlb_context_cache = CTX_FIRST_VERSION - 1; +unsigned long tlb_context_cache = CTX_FIRST_VERSION; #define MAX_CTX_NR (1UL << CTX_NR_BITS) #define CTX_BMAP_SLOTS BITS_TO_LONGS(MAX_CTX_NR) DECLARE_BITMAP(mmu_context_bmap, MAX_CTX_NR); +DEFINE_PER_CPU(struct mm_struct *, per_cpu_secondary_mm) = {0}; + +static void mmu_context_wrap(void) +{ + unsigned long old_ver = tlb_context_cache & CTX_VERSION_MASK; + unsigned long new_ver, new_ctx, old_ctx; + struct mm_struct *mm; + int cpu; + + bitmap_zero(mmu_context_bmap, 1 << CTX_NR_BITS); + + /* Reserve kernel context */ + set_bit(0, mmu_context_bmap); + + new_ver = (tlb_context_cache & CTX_VERSION_MASK) + CTX_FIRST_VERSION; + if (unlikely(new_ver == 0)) + new_ver = CTX_FIRST_VERSION; + tlb_context_cache = new_ver; + + /* + * Make sure that any new mm that are added into per_cpu_secondary_mm, + * are going to go through get_new_mmu_context() path. + */ + mb(); + + /* + * Updated versions to current on those CPUs that had valid secondary + * contexts + */ + for_each_online_cpu(cpu) { + /* + * If a new mm is stored after we took this mm from the array, + * it will go into get_new_mmu_context() path, because we + * already bumped the version in tlb_context_cache. + */ + mm = per_cpu(per_cpu_secondary_mm, cpu); + + if (unlikely(!mm || mm == &init_mm)) + continue; + + old_ctx = mm->context.sparc64_ctx_val; + if (likely((old_ctx & CTX_VERSION_MASK) == old_ver)) { + new_ctx = (old_ctx & ~CTX_VERSION_MASK) | new_ver; + set_bit(new_ctx & CTX_NR_MASK, mmu_context_bmap); + mm->context.sparc64_ctx_val = new_ctx; + } + } +} /* Caller does TLB context flushing on local CPU if necessary. * The caller also ensures that CTX_VALID(mm->context) is false. @@ -675,48 +723,30 @@ void get_new_mmu_context(struct mm_struct *mm) { unsigned long ctx, new_ctx; unsigned long orig_pgsz_bits; - int new_version; spin_lock(&ctx_alloc_lock); +retry: + /* wrap might have happened, test again if our context became valid */ + if (unlikely(CTX_VALID(mm->context))) + goto out; orig_pgsz_bits = (mm->context.sparc64_ctx_val & CTX_PGSZ_MASK); ctx = (tlb_context_cache + 1) & CTX_NR_MASK; new_ctx = find_next_zero_bit(mmu_context_bmap, 1 << CTX_NR_BITS, ctx); - new_version = 0; if (new_ctx >= (1 << CTX_NR_BITS)) { new_ctx = find_next_zero_bit(mmu_context_bmap, ctx, 1); if (new_ctx >= ctx) { - int i; - new_ctx = (tlb_context_cache & CTX_VERSION_MASK) + - CTX_FIRST_VERSION; - if (new_ctx == 1) - new_ctx = CTX_FIRST_VERSION; - - /* Don't call memset, for 16 entries that's just - * plain silly... - */ - mmu_context_bmap[0] = 3; - mmu_context_bmap[1] = 0; - mmu_context_bmap[2] = 0; - mmu_context_bmap[3] = 0; - for (i = 4; i < CTX_BMAP_SLOTS; i += 4) { - mmu_context_bmap[i + 0] = 0; - mmu_context_bmap[i + 1] = 0; - mmu_context_bmap[i + 2] = 0; - mmu_context_bmap[i + 3] = 0; - } - new_version = 1; - goto out; + mmu_context_wrap(); + goto retry; } } + if (mm->context.sparc64_ctx_val) + cpumask_clear(mm_cpumask(mm)); mmu_context_bmap[new_ctx>>6] |= (1UL << (new_ctx & 63)); new_ctx |= (tlb_context_cache & CTX_VERSION_MASK); -out: tlb_context_cache = new_ctx; mm->context.sparc64_ctx_val = new_ctx | orig_pgsz_bits; +out: spin_unlock(&ctx_alloc_lock); - - if (unlikely(new_version)) - smp_new_mmu_context_version(); } static int numa_enabled = 1; diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index 9cdeca0fa955..266411291634 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -451,7 +451,8 @@ retry_tsb_alloc: extern void copy_tsb(unsigned long old_tsb_base, unsigned long old_tsb_size, unsigned long new_tsb_base, - unsigned long new_tsb_size); + unsigned long new_tsb_size, + unsigned long page_size_shift); unsigned long old_tsb_base = (unsigned long) old_tsb; unsigned long new_tsb_base = (unsigned long) new_tsb; @@ -459,7 +460,9 @@ retry_tsb_alloc: old_tsb_base = __pa(old_tsb_base); new_tsb_base = __pa(new_tsb_base); } - copy_tsb(old_tsb_base, old_size, new_tsb_base, new_size); + copy_tsb(old_tsb_base, old_size, new_tsb_base, new_size, + tsb_index == MM_TSB_BASE ? + PAGE_SHIFT : REAL_HPAGE_SHIFT); } mm->context.tsb_block[tsb_index].tsb = new_tsb; diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S index 5d2fd6cd3189..fcf4d27a38fb 100644 --- a/arch/sparc/mm/ultra.S +++ b/arch/sparc/mm/ultra.S @@ -971,11 +971,6 @@ xcall_capture: wr %g0, (1 << PIL_SMP_CAPTURE), %set_softint retry - .globl xcall_new_mmu_context_version -xcall_new_mmu_context_version: - wr %g0, (1 << PIL_SMP_CTX_NEW_VERSION), %set_softint - retry - #ifdef CONFIG_KGDB .globl xcall_kgdb_capture xcall_kgdb_capture: diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 47190bd399e7..cec49ecf5f31 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -161,8 +161,8 @@ void kvm_async_pf_task_wait(u32 token) */ rcu_irq_exit(); native_safe_halt(); - rcu_irq_enter(); local_irq_disable(); + rcu_irq_enter(); } } if (!n.halted) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 642e9c93a097..9357b29de9bc 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -737,18 +737,20 @@ out: static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i) { struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i]; - int j, nent = vcpu->arch.cpuid_nent; + struct kvm_cpuid_entry2 *ej; + int j = i; + int nent = vcpu->arch.cpuid_nent; e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT; /* when no next entry is found, the current entry[i] is reselected */ - for (j = i + 1; ; j = (j + 1) % nent) { - struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j]; - if (ej->function == e->function) { - ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT; - return j; - } - } - return 0; /* silence gcc, even though control never reaches here */ + do { + j = (j + 1) % nent; + ej = &vcpu->arch.cpuid_entries[j]; + } while (ej->function != e->function); + + ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT; + + return j; } /* find an entry with matching function, matching index (if needed), and that diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 8eb8a934b531..1049c3c9b877 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3433,12 +3433,15 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); } -static bool can_do_async_pf(struct kvm_vcpu *vcpu) +bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu) { if (unlikely(!lapic_in_kernel(vcpu) || kvm_event_needs_reinjection(vcpu))) return false; + if (is_guest_mode(vcpu)) + return false; + return kvm_x86_ops->interrupt_allowed(vcpu); } @@ -3454,7 +3457,7 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, if (!async) return false; /* *pfn has correct page already */ - if (!prefault && can_do_async_pf(vcpu)) { + if (!prefault && kvm_can_do_async_pf(vcpu)) { trace_kvm_try_async_get_page(gva, gfn); if (kvm_find_async_pf_gfn(vcpu, gfn)) { trace_kvm_async_pf_doublefault(gva, gfn); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 55ffb7b0f95e..e60fc80f8a9c 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -74,6 +74,7 @@ enum { int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct); void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu); void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly); +bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu); static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm) { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ae2b9cd358f2..6c82792487e9 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8245,8 +8245,7 @@ bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu) if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED)) return true; else - return !kvm_event_needs_reinjection(vcpu) && - kvm_x86_ops->interrupt_allowed(vcpu); + return kvm_can_do_async_pf(vcpu); } void kvm_arch_start_assignment(struct kvm *kvm) diff --git a/crypto/gcm.c b/crypto/gcm.c index 1238b3c5a321..0a12c09d7cb2 100644 --- a/crypto/gcm.c +++ b/crypto/gcm.c @@ -152,10 +152,8 @@ static int crypto_gcm_setkey(struct crypto_aead *aead, const u8 *key, err = crypto_ablkcipher_encrypt(&data->req); if (err == -EINPROGRESS || err == -EBUSY) { - err = wait_for_completion_interruptible( - &data->result.completion); - if (!err) - err = data->result.err; + wait_for_completion(&data->result.completion); + err = data->result.err; } if (err) diff --git a/drivers/char/mem.c b/drivers/char/mem.c index 0975d23031ea..2898d19fadf5 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -346,7 +346,7 @@ static int mmap_mem(struct file *file, struct vm_area_struct *vma) phys_addr_t offset = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT; /* It's illegal to wrap around the end of the physical address space. */ - if (offset + (phys_addr_t)size < offset) + if (offset + (phys_addr_t)size - 1 < offset) return -EINVAL; if (!valid_mmap_phys_addr_range(vma->vm_pgoff, size)) diff --git a/drivers/char/random.c b/drivers/char/random.c index 491a4dce13fe..1822472dffab 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1798,13 +1798,15 @@ int random_int_secret_init(void) return 0; } +static DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash) + __aligned(sizeof(unsigned long)); + /* * Get a random word for internal kernel use only. Similar to urandom but * with the goal of minimal entropy pool depletion. As a result, the random * value is not cryptographically secure but for several uses the cost of * depleting entropy is too high */ -static DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash); unsigned int get_random_int(void) { __u32 *hash; @@ -1825,6 +1827,28 @@ unsigned int get_random_int(void) EXPORT_SYMBOL(get_random_int); /* + * Same as get_random_int(), but returns unsigned long. + */ +unsigned long get_random_long(void) +{ + __u32 *hash; + unsigned long ret; + + if (arch_get_random_long(&ret)) + return ret; + + hash = get_cpu_var(get_random_int_hash); + + hash[0] += current->pid + jiffies + random_get_entropy(); + md5_transform(hash, random_int_secret); + ret = *(unsigned long *)hash; + put_cpu_var(get_random_int_hash); + + return ret; +} +EXPORT_SYMBOL(get_random_long); + +/* * randomize_range() returns a start address such that * * [...... .....] diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 38b363f4316b..ebed319657e7 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -2451,6 +2451,7 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) if (!(cpufreq_driver->flags & CPUFREQ_STICKY) && list_empty(&cpufreq_policy_list)) { /* if all ->init() calls failed, unregister */ + ret = -ENODEV; pr_debug("%s: No CPU initialized for driver %s\n", __func__, driver_data->name); goto err_if_unreg; diff --git a/drivers/dma/ep93xx_dma.c b/drivers/dma/ep93xx_dma.c index 57ff46284f15..c97336a2ba92 100644 --- a/drivers/dma/ep93xx_dma.c +++ b/drivers/dma/ep93xx_dma.c @@ -325,6 +325,8 @@ static int m2p_hw_setup(struct ep93xx_dma_chan *edmac) | M2P_CONTROL_ENABLE; m2p_set_control(edmac, control); + edmac->buffer = 0; + return 0; } diff --git a/drivers/dma/sh/usb-dmac.c b/drivers/dma/sh/usb-dmac.c index b1bc945f008f..56410ea75ac5 100644 --- a/drivers/dma/sh/usb-dmac.c +++ b/drivers/dma/sh/usb-dmac.c @@ -117,7 +117,7 @@ struct usb_dmac { #define USB_DMASWR 0x0008 #define USB_DMASWR_SWR (1 << 0) #define USB_DMAOR 0x0060 -#define USB_DMAOR_AE (1 << 2) +#define USB_DMAOR_AE (1 << 1) #define USB_DMAOR_DME (1 << 0) #define USB_DMASAR 0x0000 diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c index 57a2e347f04d..0f0094b58d1f 100644 --- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c @@ -893,6 +893,12 @@ static bool ci_dpm_vblank_too_short(struct amdgpu_device *adev) u32 vblank_time = amdgpu_dpm_get_vblank_time(adev); u32 switch_limit = adev->mc.vram_type == AMDGPU_VRAM_TYPE_GDDR5 ? 450 : 300; + /* disable mclk switching if the refresh is >120Hz, even if the + * blanking period would allow it + */ + if (amdgpu_dpm_get_vrefresh(adev) > 120) + return true; + if (vblank_time < switch_limit) return true; else diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index b88ce514eb8e..24d45fc7716c 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -986,6 +986,7 @@ static struct drm_driver msm_driver = { .prime_fd_to_handle = drm_gem_prime_fd_to_handle, .gem_prime_export = drm_gem_prime_export, .gem_prime_import = drm_gem_prime_import, + .gem_prime_res_obj = msm_gem_prime_res_obj, .gem_prime_pin = msm_gem_prime_pin, .gem_prime_unpin = msm_gem_prime_unpin, .gem_prime_get_sg_table = msm_gem_prime_get_sg_table, diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index 3be7a56b14f1..026e156e519c 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -212,6 +212,7 @@ struct sg_table *msm_gem_prime_get_sg_table(struct drm_gem_object *obj); void *msm_gem_prime_vmap(struct drm_gem_object *obj); void msm_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr); int msm_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma); +struct reservation_object *msm_gem_prime_res_obj(struct drm_gem_object *obj); struct drm_gem_object *msm_gem_prime_import_sg_table(struct drm_device *dev, struct dma_buf_attachment *attach, struct sg_table *sg); int msm_gem_prime_pin(struct drm_gem_object *obj); diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c index 121975b07cd4..1fbddc5c7281 100644 --- a/drivers/gpu/drm/msm/msm_gem_prime.c +++ b/drivers/gpu/drm/msm/msm_gem_prime.c @@ -70,3 +70,10 @@ void msm_gem_prime_unpin(struct drm_gem_object *obj) if (!obj->import_attach) msm_gem_put_pages(obj); } + +struct reservation_object *msm_gem_prime_res_obj(struct drm_gem_object *obj) +{ + struct msm_gem_object *msm_obj = to_msm_bo(obj); + + return msm_obj->resv; +} diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/timer.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/timer.h index 82d3e28918fd..7e4f24ae7de8 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/timer.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/timer.h @@ -4,6 +4,7 @@ struct nvkm_alarm { struct list_head head; + struct list_head exec; u64 timestamp; void (*func)(struct nvkm_alarm *); }; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c index 79fcdb43e174..46033909d950 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c @@ -50,7 +50,8 @@ nvkm_timer_alarm_trigger(struct nvkm_timer *tmr) /* Move to completed list. We'll drop the lock before * executing the callback so it can reschedule itself. */ - list_move_tail(&alarm->head, &exec); + list_del_init(&alarm->head); + list_add(&alarm->exec, &exec); } /* Shut down interrupt if no more pending alarms. */ @@ -59,8 +60,8 @@ nvkm_timer_alarm_trigger(struct nvkm_timer *tmr) spin_unlock_irqrestore(&tmr->lock, flags); /* Execute completed callbacks. */ - list_for_each_entry_safe(alarm, atemp, &exec, head) { - list_del_init(&alarm->head); + list_for_each_entry_safe(alarm, atemp, &exec, exec) { + list_del(&alarm->exec); alarm->func(alarm); } } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c index b6a0806b06bf..a1c68e6a689e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c @@ -368,6 +368,8 @@ static void *vmw_local_fifo_reserve(struct vmw_private *dev_priv, return fifo_state->static_buffer; else { fifo_state->dynamic_buffer = vmalloc(bytes); + if (!fifo_state->dynamic_buffer) + goto out_err; return fifo_state->dynamic_buffer; } } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c index c9c04ccccdd9..027987023400 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c @@ -1288,11 +1288,14 @@ int vmw_gb_surface_define_ioctl(struct drm_device *dev, void *data, struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile; int ret; uint32_t size; - uint32_t backup_handle; + uint32_t backup_handle = 0; if (req->multisample_count != 0) return -EINVAL; + if (req->mip_levels > DRM_VMW_MAX_MIP_LEVELS) + return -EINVAL; + if (unlikely(vmw_user_surface_size == 0)) vmw_user_surface_size = ttm_round_pot(sizeof(*user_srf)) + 128; @@ -1328,12 +1331,16 @@ int vmw_gb_surface_define_ioctl(struct drm_device *dev, void *data, ret = vmw_user_dmabuf_lookup(tfile, req->buffer_handle, &res->backup, &user_srf->backup_base); - if (ret == 0 && res->backup->base.num_pages * PAGE_SIZE < - res->backup_size) { - DRM_ERROR("Surface backup buffer is too small.\n"); - vmw_dmabuf_unreference(&res->backup); - ret = -EINVAL; - goto out_unlock; + if (ret == 0) { + if (res->backup->base.num_pages * PAGE_SIZE < + res->backup_size) { + DRM_ERROR("Surface backup buffer is too small.\n"); + vmw_dmabuf_unreference(&res->backup); + ret = -EINVAL; + goto out_unlock; + } else { + backup_handle = req->buffer_handle; + } } } else if (req->drm_surface_flags & drm_vmw_surface_flag_create_buffer) ret = vmw_user_dmabuf_alloc(dev_priv, tfile, diff --git a/drivers/iio/light/ltr501.c b/drivers/iio/light/ltr501.c index 6bf89d8f3741..b9d1e5c58ec5 100644 --- a/drivers/iio/light/ltr501.c +++ b/drivers/iio/light/ltr501.c @@ -74,9 +74,9 @@ static const int int_time_mapping[] = {100000, 50000, 200000, 400000}; static const struct reg_field reg_field_it = REG_FIELD(LTR501_ALS_MEAS_RATE, 3, 4); static const struct reg_field reg_field_als_intr = - REG_FIELD(LTR501_INTR, 0, 0); -static const struct reg_field reg_field_ps_intr = REG_FIELD(LTR501_INTR, 1, 1); +static const struct reg_field reg_field_ps_intr = + REG_FIELD(LTR501_INTR, 0, 0); static const struct reg_field reg_field_als_rate = REG_FIELD(LTR501_ALS_MEAS_RATE, 0, 2); static const struct reg_field reg_field_ps_rate = diff --git a/drivers/iio/proximity/as3935.c b/drivers/iio/proximity/as3935.c index bf0bd7e03aff..9e6d1cdb7fcd 100644 --- a/drivers/iio/proximity/as3935.c +++ b/drivers/iio/proximity/as3935.c @@ -40,9 +40,9 @@ #define AS3935_AFE_PWR_BIT BIT(0) #define AS3935_INT 0x03 -#define AS3935_INT_MASK 0x07 +#define AS3935_INT_MASK 0x0f #define AS3935_EVENT_INT BIT(3) -#define AS3935_NOISE_INT BIT(1) +#define AS3935_NOISE_INT BIT(0) #define AS3935_DATA 0x07 #define AS3935_DATA_MASK 0x3F diff --git a/drivers/infiniband/hw/qib/qib_rc.c b/drivers/infiniband/hw/qib/qib_rc.c index e6b7556d5221..cbc4216091c9 100644 --- a/drivers/infiniband/hw/qib/qib_rc.c +++ b/drivers/infiniband/hw/qib/qib_rc.c @@ -2088,8 +2088,10 @@ send_last: ret = qib_get_rwqe(qp, 1); if (ret < 0) goto nack_op_err; - if (!ret) + if (!ret) { + qib_put_ss(&qp->r_sge); goto rnr_nak; + } wc.ex.imm_data = ohdr->u.rc.imm_data; hdrsize += 4; wc.wc_flags = IB_WC_WITH_IMM; diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c index 1a2b2620421e..6f4dc0fd2ca3 100644 --- a/drivers/input/mouse/elantech.c +++ b/drivers/input/mouse/elantech.c @@ -1122,8 +1122,10 @@ static int elantech_get_resolution_v4(struct psmouse *psmouse, * Asus UX32VD 0x361f02 00, 15, 0e clickpad * Avatar AVIU-145A2 0x361f00 ? clickpad * Fujitsu LIFEBOOK E544 0x470f00 d0, 12, 09 2 hw buttons + * Fujitsu LIFEBOOK E546 0x470f00 50, 12, 09 2 hw buttons * Fujitsu LIFEBOOK E547 0x470f00 50, 12, 09 2 hw buttons * Fujitsu LIFEBOOK E554 0x570f01 40, 14, 0c 2 hw buttons + * Fujitsu LIFEBOOK E557 0x570f01 40, 14, 0c 2 hw buttons * Fujitsu T725 0x470f01 05, 12, 09 2 hw buttons * Fujitsu H730 0x570f00 c0, 14, 0c 3 hw buttons (**) * Gigabyte U2442 0x450f01 58, 17, 0c 2 hw buttons @@ -1529,6 +1531,13 @@ static const struct dmi_system_id elantech_dmi_force_crc_enabled[] = { }, }, { + /* Fujitsu LIFEBOOK E546 does not work with crc_enabled == 0 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E546"), + }, + }, + { /* Fujitsu LIFEBOOK E547 does not work with crc_enabled == 0 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), @@ -1550,6 +1559,13 @@ static const struct dmi_system_id elantech_dmi_force_crc_enabled[] = { }, }, { + /* Fujitsu LIFEBOOK E557 does not work with crc_enabled == 0 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E557"), + }, + }, + { /* Fujitsu LIFEBOOK U745 does not work with crc_enabled == 0 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c index 783337d22f36..10a02934bfc0 100644 --- a/drivers/misc/cxl/file.c +++ b/drivers/misc/cxl/file.c @@ -158,11 +158,8 @@ static long afu_ioctl_start_work(struct cxl_context *ctx, /* Do this outside the status_mutex to avoid a circular dependency with * the locking in cxl_mmap_fault() */ - if (copy_from_user(&work, uwork, - sizeof(struct cxl_ioctl_start_work))) { - rc = -EFAULT; - goto out; - } + if (copy_from_user(&work, uwork, sizeof(work))) + return -EFAULT; mutex_lock(&ctx->status_mutex); if (ctx->status != OPENED) { diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index c82ab87fcbe8..e5911ccb2148 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -1949,7 +1949,7 @@ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, } /* select a non-FCoE queue */ - return fallback(dev, skb) % BNX2X_NUM_ETH_QUEUES(bp); + return fallback(dev, skb) % (BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos); } void bnx2x_set_num_queues(struct bnx2x *bp) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 0d147610a06f..090e00650601 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -2714,10 +2714,14 @@ static int cxgb_up(struct adapter *adap) if (err) goto irq_err; } + + mutex_lock(&uld_mutex); enable_rx(adap); t4_sge_start(adap); t4_intr_enable(adap); adap->flags |= FULL_INIT_DONE; + mutex_unlock(&uld_mutex); + notify_ulds(adap, CXGB4_STATE_UP); #if IS_ENABLED(CONFIG_IPV6) update_clip(adap); diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c index ff665493ca97..52f2230062e7 100644 --- a/drivers/net/ethernet/ethoc.c +++ b/drivers/net/ethernet/ethoc.c @@ -713,6 +713,8 @@ static int ethoc_open(struct net_device *dev) if (ret) return ret; + napi_enable(&priv->napi); + ethoc_init_ring(priv, dev->mem_start); ethoc_reset(priv); @@ -725,7 +727,6 @@ static int ethoc_open(struct net_device *dev) } phy_start(priv->phy); - napi_enable(&priv->napi); if (netif_msg_ifup(priv)) { dev_info(&dev->dev, "I/O: %08lx Memory: %08lx-%08lx\n", diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 590750ab6564..9a986ccd42e5 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -77,6 +77,8 @@ static const u8 all_zeros_mac[ETH_ALEN]; static int vxlan_sock_add(struct vxlan_dev *vxlan); +static void vxlan_vs_del_dev(struct vxlan_dev *vxlan); + /* per-network namespace private data for this module */ struct vxlan_net { struct list_head vxlan_list; @@ -1052,6 +1054,8 @@ static void __vxlan_sock_release(struct vxlan_sock *vs) static void vxlan_sock_release(struct vxlan_dev *vxlan) { + vxlan_vs_del_dev(vxlan); + __vxlan_sock_release(vxlan->vn4_sock); #if IS_ENABLED(CONFIG_IPV6) __vxlan_sock_release(vxlan->vn6_sock); @@ -2255,6 +2259,15 @@ static void vxlan_cleanup(unsigned long arg) mod_timer(&vxlan->age_timer, next_timer); } +static void vxlan_vs_del_dev(struct vxlan_dev *vxlan) +{ + struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); + + spin_lock(&vn->sock_lock); + hlist_del_init_rcu(&vxlan->hlist); + spin_unlock(&vn->sock_lock); +} + static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan) { struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); @@ -3028,12 +3041,6 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev, static void vxlan_dellink(struct net_device *dev, struct list_head *head) { struct vxlan_dev *vxlan = netdev_priv(dev); - struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); - - spin_lock(&vn->sock_lock); - if (!hlist_unhashed(&vxlan->hlist)) - hlist_del_rcu(&vxlan->hlist); - spin_unlock(&vn->sock_lock); gro_cells_destroy(&vxlan->gro_cells); list_del(&vxlan->next); diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 1f445f357da1..888e9cfef51a 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -304,7 +304,7 @@ static void xennet_alloc_rx_buffers(struct netfront_queue *queue) queue->rx_skbs[id] = skb; ref = gnttab_claim_grant_reference(&queue->gref_rx_head); - BUG_ON((signed short)ref < 0); + WARN_ON_ONCE(IS_ERR_VALUE((unsigned long)(int)ref)); queue->grant_rx_ref[id] = ref; page = skb_frag_page(&skb_shinfo(skb)->frags[0]); @@ -437,7 +437,7 @@ static void xennet_tx_setup_grant(unsigned long gfn, unsigned int offset, id = get_id_from_freelist(&queue->tx_skb_freelist, queue->tx_skbs); tx = RING_GET_REQUEST(&queue->tx, queue->tx.req_prod_pvt++); ref = gnttab_claim_grant_reference(&queue->gref_tx_head); - BUG_ON((signed short)ref < 0); + WARN_ON_ONCE(IS_ERR_VALUE((unsigned long)(int)ref)); gnttab_grant_foreign_access_ref(ref, queue->info->xbdev->otherend_id, gfn, GNTMAP_readonly); diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 3588a56aabb4..5cbf20ab94aa 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -2311,10 +2311,10 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) if (mem_only) { if (pci_enable_device_mem(pdev)) - goto probe_out; + return ret; } else { if (pci_enable_device(pdev)) - goto probe_out; + return ret; } /* This may fail but that's ok */ @@ -2324,7 +2324,7 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) if (!ha) { ql_log_pci(ql_log_fatal, pdev, 0x0009, "Unable to allocate memory for ha.\n"); - goto probe_out; + goto disable_device; } ql_dbg_pci(ql_dbg_init, pdev, 0x000a, "Memory allocated for ha=%p.\n", ha); @@ -2923,7 +2923,7 @@ iospace_config_failed: kfree(ha); ha = NULL; -probe_out: +disable_device: pci_disable_device(pdev); return ret; } diff --git a/drivers/staging/lustre/lustre/lov/lov_pack.c b/drivers/staging/lustre/lustre/lov/lov_pack.c index 2fb1e974cc70..e11b1001d1f6 100644 --- a/drivers/staging/lustre/lustre/lov/lov_pack.c +++ b/drivers/staging/lustre/lustre/lov/lov_pack.c @@ -399,18 +399,10 @@ int lov_getstripe(struct obd_export *exp, struct lov_stripe_md *lsm, struct lov_mds_md *lmmk = NULL; int rc, lmm_size; int lum_size; - mm_segment_t seg; if (!lsm) return -ENODATA; - /* - * "Switch to kernel segment" to allow copying from kernel space by - * copy_{to,from}_user(). - */ - seg = get_fs(); - set_fs(KERNEL_DS); - /* we only need the header part from user space to get lmm_magic and * lmm_stripe_count, (the header part is common to v1 and v3) */ lum_size = sizeof(struct lov_user_md_v1); @@ -485,6 +477,5 @@ int lov_getstripe(struct obd_export *exp, struct lov_stripe_md *lsm, obd_free_diskmd(exp, &lmmk); out_set: - set_fs(seg); return rc; } diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index af301414a9f3..60743bf27f37 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -1154,15 +1154,28 @@ target_cmd_size_check(struct se_cmd *cmd, unsigned int size) if (cmd->unknown_data_length) { cmd->data_length = size; } else if (size != cmd->data_length) { - pr_warn("TARGET_CORE[%s]: Expected Transfer Length:" + pr_warn_ratelimited("TARGET_CORE[%s]: Expected Transfer Length:" " %u does not match SCSI CDB Length: %u for SAM Opcode:" " 0x%02x\n", cmd->se_tfo->get_fabric_name(), cmd->data_length, size, cmd->t_task_cdb[0]); - if (cmd->data_direction == DMA_TO_DEVICE && - cmd->se_cmd_flags & SCF_SCSI_DATA_CDB) { - pr_err("Rejecting underflow/overflow WRITE data\n"); - return TCM_INVALID_CDB_FIELD; + if (cmd->data_direction == DMA_TO_DEVICE) { + if (cmd->se_cmd_flags & SCF_SCSI_DATA_CDB) { + pr_err_ratelimited("Rejecting underflow/overflow" + " for WRITE data CDB\n"); + return TCM_INVALID_CDB_FIELD; + } + /* + * Some fabric drivers like iscsi-target still expect to + * always reject overflow writes. Reject this case until + * full fabric driver level support for overflow writes + * is introduced tree-wide. + */ + if (size > cmd->data_length) { + pr_err_ratelimited("Rejecting overflow for" + " WRITE control CDB\n"); + return TCM_INVALID_CDB_FIELD; + } } /* * Reject READ_* or WRITE_* with overflow/underflow for diff --git a/drivers/tty/serial/ifx6x60.c b/drivers/tty/serial/ifx6x60.c index 88246f7e435a..0f23dda60011 100644 --- a/drivers/tty/serial/ifx6x60.c +++ b/drivers/tty/serial/ifx6x60.c @@ -1378,9 +1378,9 @@ static struct spi_driver ifx_spi_driver = { static void __exit ifx_spi_exit(void) { /* unregister */ + spi_unregister_driver(&ifx_spi_driver); tty_unregister_driver(tty_drv); put_tty_driver(tty_drv); - spi_unregister_driver(&ifx_spi_driver); unregister_reboot_notifier(&ifx_modem_reboot_notifier_block); } diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 63a06ab6ba03..235e150d7b81 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -1800,11 +1800,13 @@ static int sci_startup(struct uart_port *port) dev_dbg(port->dev, "%s(%d)\n", __func__, port->line); + sci_request_dma(port); + ret = sci_request_irq(s); - if (unlikely(ret < 0)) + if (unlikely(ret < 0)) { + sci_free_dma(port); return ret; - - sci_request_dma(port); + } spin_lock_irqsave(&port->lock, flags); sci_start_tx(port); @@ -1834,8 +1836,8 @@ static void sci_shutdown(struct uart_port *port) } #endif - sci_free_dma(port); sci_free_irq(s); + sci_free_dma(port); } static unsigned int sci_scbrr_calc(struct sci_port *s, unsigned int bps, diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 7cef54334b12..1bb629ab8ecc 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -2070,13 +2070,12 @@ retry_open: if (tty) { mutex_unlock(&tty_mutex); retval = tty_lock_interruptible(tty); + tty_kref_put(tty); /* drop kref from tty_driver_lookup_tty() */ if (retval) { if (retval == -EINTR) retval = -ERESTARTSYS; goto err_unref; } - /* safe to drop the kref from tty_driver_lookup_tty() */ - tty_kref_put(tty); retval = tty_reopen(tty); if (retval < 0) { tty_unlock(tty); diff --git a/drivers/tty/tty_mutex.c b/drivers/tty/tty_mutex.c index d09293bc0e04..cff304abb619 100644 --- a/drivers/tty/tty_mutex.c +++ b/drivers/tty/tty_mutex.c @@ -24,10 +24,15 @@ EXPORT_SYMBOL(tty_lock); int tty_lock_interruptible(struct tty_struct *tty) { + int ret; + if (WARN(tty->magic != TTY_MAGIC, "L Bad %p\n", tty)) return -EIO; tty_kref_get(tty); - return mutex_lock_interruptible(&tty->legacy_mutex); + ret = mutex_lock_interruptible(&tty->legacy_mutex); + if (ret) + tty_kref_put(tty); + return ret; } void __lockfunc tty_unlock(struct tty_struct *tty) diff --git a/drivers/usb/chipidea/debug.c b/drivers/usb/chipidea/debug.c index 58c8485a0715..923379972707 100644 --- a/drivers/usb/chipidea/debug.c +++ b/drivers/usb/chipidea/debug.c @@ -295,7 +295,8 @@ static int ci_role_show(struct seq_file *s, void *data) { struct ci_hdrc *ci = s->private; - seq_printf(s, "%s\n", ci_role(ci)->name); + if (ci->role != CI_ROLE_END) + seq_printf(s, "%s\n", ci_role(ci)->name); return 0; } diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c index d8a045fc1fdb..aff086ca97e4 100644 --- a/drivers/usb/chipidea/udc.c +++ b/drivers/usb/chipidea/udc.c @@ -1982,6 +1982,7 @@ static void udc_id_switch_for_host(struct ci_hdrc *ci) int ci_hdrc_gadget_init(struct ci_hdrc *ci) { struct ci_role_driver *rdrv; + int ret; if (!hw_read(ci, CAP_DCCPARAMS, DCCPARAMS_DC)) return -ENXIO; @@ -1994,7 +1995,10 @@ int ci_hdrc_gadget_init(struct ci_hdrc *ci) rdrv->stop = udc_id_switch_for_host; rdrv->irq = udc_irq; rdrv->name = "gadget"; - ci->roles[CI_ROLE_GADGET] = rdrv; - return udc_start(ci); + ret = udc_start(ci); + if (!ret) + ci->roles[CI_ROLE_GADGET] = rdrv; + + return ret; } diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c index a4f664062e0c..a069726da72a 100644 --- a/drivers/usb/gadget/function/f_mass_storage.c +++ b/drivers/usb/gadget/function/f_mass_storage.c @@ -399,7 +399,11 @@ static int fsg_set_halt(struct fsg_dev *fsg, struct usb_ep *ep) /* Caller must hold fsg->lock */ static void wakeup_thread(struct fsg_common *common) { - smp_wmb(); /* ensure the write of bh->state is complete */ + /* + * Ensure the reading of thread_wakeup_needed + * and the writing of bh->state are completed + */ + smp_mb(); /* Tell the main thread that something has happened */ common->thread_wakeup_needed = 1; if (common->thread_task) @@ -630,7 +634,12 @@ static int sleep_thread(struct fsg_common *common, bool can_freeze) } __set_current_state(TASK_RUNNING); common->thread_wakeup_needed = 0; - smp_rmb(); /* ensure the latest bh->state is visible */ + + /* + * Ensure the writing of thread_wakeup_needed + * and the reading of bh->state are completed + */ + smp_mb(); return rc; } diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c index df2e6f783318..527de56f832f 100644 --- a/drivers/xen/privcmd.c +++ b/drivers/xen/privcmd.c @@ -335,8 +335,8 @@ static int mmap_batch_fn(void *data, int nr, void *state) st->global_error = 1; } } - st->va += PAGE_SIZE * nr; - st->index += nr; + st->va += XEN_PAGE_SIZE * nr; + st->index += nr / XEN_PFN_PER_PAGE; return 0; } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 2a2e370399ba..c36a03fa7678 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3854,6 +3854,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags, info->space_info_kobj, "%s", alloc_name(found->flags)); if (ret) { + percpu_counter_destroy(&found->total_bytes_pinned); kfree(found); return ret; } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 353f4bae658c..d4a6eef31854 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2771,7 +2771,7 @@ static long btrfs_fallocate(struct file *file, int mode, if (!ret) ret = btrfs_prealloc_file_range(inode, mode, range->start, - range->len, 1 << inode->i_blkbits, + range->len, i_blocksize(inode), offset + len, &alloc_hint); list_del(&range->list); kfree(range); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 3cff6523f27d..863fa0f1972b 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7318,8 +7318,8 @@ bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end) int found = false; void **pagep = NULL; struct page *page = NULL; - int start_idx; - int end_idx; + unsigned long start_idx; + unsigned long end_idx; start_idx = start >> PAGE_CACHE_SHIFT; diff --git a/fs/buffer.c b/fs/buffer.c index 4f4cd959da7c..6f7d519a093b 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2298,7 +2298,7 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping, loff_t pos, loff_t *bytes) { struct inode *inode = mapping->host; - unsigned blocksize = 1 << inode->i_blkbits; + unsigned int blocksize = i_blocksize(inode); struct page *page; void *fsdata; pgoff_t index, curidx; @@ -2378,8 +2378,8 @@ int cont_write_begin(struct file *file, struct address_space *mapping, get_block_t *get_block, loff_t *bytes) { struct inode *inode = mapping->host; - unsigned blocksize = 1 << inode->i_blkbits; - unsigned zerofrom; + unsigned int blocksize = i_blocksize(inode); + unsigned int zerofrom; int err; err = cont_expand_zero(file, mapping, pos, bytes); @@ -2741,7 +2741,7 @@ int nobh_truncate_page(struct address_space *mapping, struct buffer_head map_bh; int err; - blocksize = 1 << inode->i_blkbits; + blocksize = i_blocksize(inode); length = offset & (blocksize - 1); /* Block boundary? Nothing to do */ @@ -2819,7 +2819,7 @@ int block_truncate_page(struct address_space *mapping, struct buffer_head *bh; int err; - blocksize = 1 << inode->i_blkbits; + blocksize = i_blocksize(inode); length = offset & (blocksize - 1); /* Block boundary? Nothing to do */ @@ -2931,7 +2931,7 @@ sector_t generic_block_bmap(struct address_space *mapping, sector_t block, struct inode *inode = mapping->host; tmp.b_state = 0; tmp.b_blocknr = 0; - tmp.b_size = 1 << inode->i_blkbits; + tmp.b_size = i_blocksize(inode); get_block(inode, block, &tmp, 0); return tmp.b_blocknr; } diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index b7d218a168fb..c6a1ec110c01 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -697,7 +697,7 @@ static int ceph_writepages_start(struct address_space *mapping, struct pagevec pvec; int done = 0; int rc = 0; - unsigned wsize = 1 << inode->i_blkbits; + unsigned int wsize = i_blocksize(inode); struct ceph_osd_request *req = NULL; int do_sync = 0; loff_t snap_size, i_size; diff --git a/fs/direct-io.c b/fs/direct-io.c index 01171d8a6ee9..c772fdf36cd9 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -575,7 +575,7 @@ static int dio_set_defer_completion(struct dio *dio) /* * Call into the fs to map some more disk blocks. We record the current number * of available blocks at sdio->blocks_available. These are in units of the - * fs blocksize, (1 << inode->i_blkbits). + * fs blocksize, i_blocksize(inode). * * The fs is allowed to map lots of blocks at once. If it wants to do that, * it uses the passed inode-relative block number as the file offset, as usual. diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 8a456f9b8a44..61d5bfc7318c 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4902,6 +4902,8 @@ static long ext4_zero_range(struct file *file, loff_t offset, /* Zero out partial block at the edges of the range */ ret = ext4_zero_partial_blocks(handle, inode, offset, len); + if (ret >= 0) + ext4_update_inode_fsync_trans(handle, inode, 1); if (file->f_flags & O_SYNC) ext4_handle_sync(handle); @@ -5597,6 +5599,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) ext4_handle_sync(handle); inode->i_mtime = inode->i_ctime = ext4_current_time(inode); ext4_mark_inode_dirty(handle, inode); + ext4_update_inode_fsync_trans(handle, inode, 1); out_stop: ext4_journal_stop(handle); @@ -5770,6 +5773,8 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) up_write(&EXT4_I(inode)->i_data_sem); if (IS_SYNC(inode)) ext4_handle_sync(handle); + if (ret >= 0) + ext4_update_inode_fsync_trans(handle, inode, 1); out_stop: ext4_journal_stop(handle); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 0d24ebcd7c9e..8772bfc3415b 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -463,47 +463,27 @@ static int ext4_find_unwritten_pgoff(struct inode *inode, num = min_t(pgoff_t, end - index, PAGEVEC_SIZE); nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index, (pgoff_t)num); - if (nr_pages == 0) { - if (whence == SEEK_DATA) - break; - - BUG_ON(whence != SEEK_HOLE); - /* - * If this is the first time to go into the loop and - * offset is not beyond the end offset, it will be a - * hole at this offset - */ - if (lastoff == startoff || lastoff < endoff) - found = 1; + if (nr_pages == 0) break; - } - - /* - * If this is the first time to go into the loop and - * offset is smaller than the first page offset, it will be a - * hole at this offset. - */ - if (lastoff == startoff && whence == SEEK_HOLE && - lastoff < page_offset(pvec.pages[0])) { - found = 1; - break; - } for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; struct buffer_head *bh, *head; /* - * If the current offset is not beyond the end of given - * range, it will be a hole. + * If current offset is smaller than the page offset, + * there is a hole at this offset. */ - if (lastoff < endoff && whence == SEEK_HOLE && - page->index > end) { + if (whence == SEEK_HOLE && lastoff < endoff && + lastoff < page_offset(pvec.pages[i])) { found = 1; *offset = lastoff; goto out; } + if (page->index > end) + goto out; + lock_page(page); if (unlikely(page->mapping != inode->i_mapping)) { @@ -543,20 +523,18 @@ static int ext4_find_unwritten_pgoff(struct inode *inode, unlock_page(page); } - /* - * The no. of pages is less than our desired, that would be a - * hole in there. - */ - if (nr_pages < num && whence == SEEK_HOLE) { - found = 1; - *offset = lastoff; + /* The no. of pages is less than our desired, we are done. */ + if (nr_pages < num) break; - } index = pvec.pages[i - 1]->index + 1; pagevec_release(&pvec); } while (index <= end); + if (whence == SEEK_HOLE && lastoff < endoff) { + found = 1; + *offset = lastoff; + } out: pagevec_release(&pvec); return found; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index ccae64dad40c..1796d1bd9a1d 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2044,7 +2044,7 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd, { struct inode *inode = mpd->inode; int err; - ext4_lblk_t blocks = (i_size_read(inode) + (1 << inode->i_blkbits) - 1) + ext4_lblk_t blocks = (i_size_read(inode) + i_blocksize(inode) - 1) >> inode->i_blkbits; do { @@ -3793,6 +3793,8 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) inode->i_mtime = inode->i_ctime = ext4_current_time(inode); ext4_mark_inode_dirty(handle, inode); + if (ret >= 0) + ext4_update_inode_fsync_trans(handle, inode, 1); out_stop: ext4_journal_stop(handle); out_dio: @@ -5162,8 +5164,9 @@ static int ext4_expand_extra_isize(struct inode *inode, /* No extended attributes present */ if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR) || header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) { - memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE, 0, - new_extra_isize); + memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE + + EXT4_I(inode)->i_extra_isize, 0, + new_extra_isize - EXT4_I(inode)->i_extra_isize); EXT4_I(inode)->i_extra_isize = new_extra_isize; return 0; } diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 7861d801b048..05048fcfd602 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -187,7 +187,7 @@ mext_page_mkuptodate(struct page *page, unsigned from, unsigned to) if (PageUptodate(page)) return 0; - blocksize = 1 << inode->i_blkbits; + blocksize = i_blocksize(inode); if (!page_has_buffers(page)) create_empty_buffers(page, blocksize, 0); diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 8f9176caf098..c8d58c5ac8ae 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -758,7 +758,7 @@ static ssize_t jfs_quota_read(struct super_block *sb, int type, char *data, sb->s_blocksize - offset : toread; tmp_bh.b_state = 0; - tmp_bh.b_size = 1 << inode->i_blkbits; + tmp_bh.b_size = i_blocksize(inode); err = jfs_get_block(inode, blk, &tmp_bh, 0); if (err) return err; @@ -798,7 +798,7 @@ static ssize_t jfs_quota_write(struct super_block *sb, int type, sb->s_blocksize - offset : towrite; tmp_bh.b_state = 0; - tmp_bh.b_size = 1 << inode->i_blkbits; + tmp_bh.b_size = i_blocksize(inode); err = jfs_get_block(inode, blk, &tmp_bh, 1); if (err) goto out; diff --git a/fs/mpage.c b/fs/mpage.c index 1480d3a18037..6ade29b19494 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -111,7 +111,7 @@ map_buffer_to_page(struct page *page, struct buffer_head *bh, int page_block) SetPageUptodate(page); return; } - create_empty_buffers(page, 1 << inode->i_blkbits, 0); + create_empty_buffers(page, i_blocksize(inode), 0); } head = page_buffers(page); page_bh = head; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 52ee0b73ab4a..5b21b1ca2341 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2421,6 +2421,20 @@ int nfs_may_open(struct inode *inode, struct rpc_cred *cred, int openflags) } EXPORT_SYMBOL_GPL(nfs_may_open); +static int nfs_execute_ok(struct inode *inode, int mask) +{ + struct nfs_server *server = NFS_SERVER(inode); + int ret; + + if (mask & MAY_NOT_BLOCK) + ret = nfs_revalidate_inode_rcu(server, inode); + else + ret = nfs_revalidate_inode(server, inode); + if (ret == 0 && !execute_ok(inode)) + ret = -EACCES; + return ret; +} + int nfs_permission(struct inode *inode, int mask) { struct rpc_cred *cred; @@ -2438,6 +2452,9 @@ int nfs_permission(struct inode *inode, int mask) case S_IFLNK: goto out; case S_IFREG: + if ((mask & MAY_OPEN) && + nfs_server_capable(inode, NFS_CAP_ATOMIC_OPEN)) + return 0; break; case S_IFDIR: /* @@ -2470,8 +2487,8 @@ force_lookup: res = PTR_ERR(cred); } out: - if (!res && (mask & MAY_EXEC) && !execute_ok(inode)) - res = -EACCES; + if (!res && (mask & MAY_EXEC)) + res = nfs_execute_ok(inode, mask); dfprintk(VFS, "NFS: permission(%s/%lu), mask=0x%x, res=%d\n", inode->i_sb->s_id, inode->i_ino, mask, res); diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index c29d9421bd5e..0976f8dad4ce 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -50,7 +50,7 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp, { struct nfsd4_layout_seg *seg = &args->lg_seg; struct super_block *sb = inode->i_sb; - u32 block_size = (1 << inode->i_blkbits); + u32 block_size = i_blocksize(inode); struct pnfs_block_extent *bex; struct iomap iomap; u32 device_generation = 0; @@ -151,7 +151,7 @@ nfsd4_block_proc_layoutcommit(struct inode *inode, int error; nr_iomaps = nfsd4_block_decode_layoutupdate(lcp->lc_up_layout, - lcp->lc_up_len, &iomaps, 1 << inode->i_blkbits); + lcp->lc_up_len, &iomaps, i_blocksize(inode)); if (nr_iomaps < 0) return nfserrno(nr_iomaps); diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 7d5351cd67fb..209dbfc50cd4 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1690,6 +1690,12 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, opdesc->op_get_currentstateid(cstate, &op->u); op->status = opdesc->op_func(rqstp, cstate, &op->u); + /* Only from SEQUENCE */ + if (cstate->status == nfserr_replay_cache) { + dprintk("%s NFS4.1 replay from cache\n", __func__); + status = op->status; + goto out; + } if (!op->status) { if (opdesc->op_set_currentstateid) opdesc->op_set_currentstateid(cstate, &op->u); @@ -1700,14 +1706,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, if (need_wrongsec_check(rqstp)) op->status = check_nfsd_access(current_fh->fh_export, rqstp); } - encode_op: - /* Only from SEQUENCE */ - if (cstate->status == nfserr_replay_cache) { - dprintk("%s NFS4.1 replay from cache\n", __func__); - status = op->status; - goto out; - } if (op->status == nfserr_replay_me) { op->replay = &cstate->replay_owner->so_replay; nfsd4_encode_replay(&resp->xdr, op); diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index c3e1cb481fe0..3f68a25f2169 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2753,9 +2753,16 @@ out_acl: } #endif /* CONFIG_NFSD_PNFS */ if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) { - status = nfsd4_encode_bitmap(xdr, NFSD_SUPPATTR_EXCLCREAT_WORD0, - NFSD_SUPPATTR_EXCLCREAT_WORD1, - NFSD_SUPPATTR_EXCLCREAT_WORD2); + u32 supp[3]; + + supp[0] = nfsd_suppattrs0(minorversion); + supp[1] = nfsd_suppattrs1(minorversion); + supp[2] = nfsd_suppattrs2(minorversion); + supp[0] &= NFSD_SUPPATTR_EXCLCREAT_WORD0; + supp[1] &= NFSD_SUPPATTR_EXCLCREAT_WORD1; + supp[2] &= NFSD_SUPPATTR_EXCLCREAT_WORD2; + + status = nfsd4_encode_bitmap(xdr, supp[0], supp[1], supp[2]); if (status) goto out; } diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index a35ae35e6932..cd39b57288c2 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -55,7 +55,7 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr) brelse(bh); BUG(); } - memset(bh->b_data, 0, 1 << inode->i_blkbits); + memset(bh->b_data, 0, i_blocksize(inode)); bh->b_bdev = inode->i_sb->s_bdev; bh->b_blocknr = blocknr; set_buffer_mapped(bh); diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index ac2f64943ff4..00877ef0b120 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -55,7 +55,7 @@ void nilfs_inode_add_blocks(struct inode *inode, int n) { struct nilfs_root *root = NILFS_I(inode)->i_root; - inode_add_bytes(inode, (1 << inode->i_blkbits) * n); + inode_add_bytes(inode, i_blocksize(inode) * n); if (root) atomic64_add(n, &root->blocks_count); } @@ -64,7 +64,7 @@ void nilfs_inode_sub_blocks(struct inode *inode, int n) { struct nilfs_root *root = NILFS_I(inode)->i_root; - inode_sub_bytes(inode, (1 << inode->i_blkbits) * n); + inode_sub_bytes(inode, i_blocksize(inode) * n); if (root) atomic64_sub(n, &root->blocks_count); } diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index 1125f40233ff..612a2457243d 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -60,7 +60,7 @@ nilfs_mdt_insert_new_block(struct inode *inode, unsigned long block, set_buffer_mapped(bh); kaddr = kmap_atomic(bh->b_page); - memset(kaddr + bh_offset(bh), 0, 1 << inode->i_blkbits); + memset(kaddr + bh_offset(bh), 0, i_blocksize(inode)); if (init_block) init_block(inode, bh, kaddr); flush_dcache_page(bh->b_page); @@ -503,7 +503,7 @@ void nilfs_mdt_set_entry_size(struct inode *inode, unsigned entry_size, struct nilfs_mdt_info *mi = NILFS_MDT(inode); mi->mi_entry_size = entry_size; - mi->mi_entries_per_block = (1 << inode->i_blkbits) / entry_size; + mi->mi_entries_per_block = i_blocksize(inode) / entry_size; mi->mi_first_entry_offset = DIV_ROUND_UP(header_size, entry_size); } diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 3b65adaae7e4..2f27c935bd57 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -719,7 +719,7 @@ static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode, lock_page(page); if (!page_has_buffers(page)) - create_empty_buffers(page, 1 << inode->i_blkbits, 0); + create_empty_buffers(page, i_blocksize(inode), 0); unlock_page(page); bh = head = page_buffers(page); diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index e6795c7c76a8..e4184bd2a954 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -1103,7 +1103,7 @@ int ocfs2_map_page_blocks(struct page *page, u64 *p_blkno, int ret = 0; struct buffer_head *head, *bh, *wait[2], **wait_bh = wait; unsigned int block_end, block_start; - unsigned int bsize = 1 << inode->i_blkbits; + unsigned int bsize = i_blocksize(inode); if (!page_has_buffers(page)) create_empty_buffers(page, bsize, 0); diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 56dd3957cc91..1d738723a41a 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -808,7 +808,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, /* We know that zero_from is block aligned */ for (block_start = zero_from; block_start < zero_to; block_start = block_end) { - block_end = block_start + (1 << inode->i_blkbits); + block_end = block_start + i_blocksize(inode); /* * block_start is block-aligned. Bump it by one to force diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index 8f5ccdf81c25..38187300a2b4 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -189,7 +189,7 @@ int reiserfs_commit_page(struct inode *inode, struct page *page, int ret = 0; th.t_trans_id = 0; - blocksize = 1 << inode->i_blkbits; + blocksize = i_blocksize(inode); if (logit) { reiserfs_write_lock(s); diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 3d8e7e671d5b..60ba35087d12 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -524,7 +524,7 @@ static int reiserfs_get_blocks_direct_io(struct inode *inode, * referenced in convert_tail_for_hole() that may be called from * reiserfs_get_block() */ - bh_result->b_size = (1 << inode->i_blkbits); + bh_result->b_size = i_blocksize(inode); ret = reiserfs_get_block(inode, iblock, bh_result, create | GET_BLOCK_NO_DANGLE); diff --git a/fs/stat.c b/fs/stat.c index d4a61d8dc021..004dd77c3b93 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -31,7 +31,7 @@ void generic_fillattr(struct inode *inode, struct kstat *stat) stat->atime = inode->i_atime; stat->mtime = inode->i_mtime; stat->ctime = inode->i_ctime; - stat->blksize = (1 << inode->i_blkbits); + stat->blksize = i_blocksize(inode); stat->blocks = inode->i_blocks; } @@ -454,6 +454,7 @@ void __inode_add_bytes(struct inode *inode, loff_t bytes) inode->i_bytes -= 512; } } +EXPORT_SYMBOL(__inode_add_bytes); void inode_add_bytes(struct inode *inode, loff_t bytes) { diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 566df9b5a6cb..7be3166ba553 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1206,7 +1206,7 @@ int udf_setsize(struct inode *inode, loff_t newsize) { int err; struct udf_inode_info *iinfo; - int bsize = 1 << inode->i_blkbits; + int bsize = i_blocksize(inode); if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))) diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c index dc5fae601c24..637e17cb0edd 100644 --- a/fs/ufs/balloc.c +++ b/fs/ufs/balloc.c @@ -81,7 +81,8 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count) ufs_error (sb, "ufs_free_fragments", "bit already cleared for fragment %u", i); } - + + inode_sub_bytes(inode, count << uspi->s_fshift); fs32_add(sb, &ucg->cg_cs.cs_nffree, count); uspi->cs_total.cs_nffree += count; fs32_add(sb, &UFS_SB(sb)->fs_cs(cgno).cs_nffree, count); @@ -183,6 +184,7 @@ do_more: ufs_error(sb, "ufs_free_blocks", "freeing free fragment"); } ubh_setblock(UCPI_UBH(ucpi), ucpi->c_freeoff, blkno); + inode_sub_bytes(inode, uspi->s_fpb << uspi->s_fshift); if ((UFS_SB(sb)->s_flags & UFS_CG_MASK) == UFS_CG_44BSD) ufs_clusteracct (sb, ucpi, blkno, 1); @@ -494,6 +496,20 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, return 0; } +static bool try_add_frags(struct inode *inode, unsigned frags) +{ + unsigned size = frags * i_blocksize(inode); + spin_lock(&inode->i_lock); + __inode_add_bytes(inode, size); + if (unlikely((u32)inode->i_blocks != inode->i_blocks)) { + __inode_sub_bytes(inode, size); + spin_unlock(&inode->i_lock); + return false; + } + spin_unlock(&inode->i_lock); + return true; +} + static u64 ufs_add_fragments(struct inode *inode, u64 fragment, unsigned oldcount, unsigned newcount) { @@ -530,6 +546,9 @@ static u64 ufs_add_fragments(struct inode *inode, u64 fragment, for (i = oldcount; i < newcount; i++) if (ubh_isclr (UCPI_UBH(ucpi), ucpi->c_freeoff, fragno + i)) return 0; + + if (!try_add_frags(inode, count)) + return 0; /* * Block can be extended */ @@ -647,6 +666,7 @@ cg_found: ubh_setbit (UCPI_UBH(ucpi), ucpi->c_freeoff, goal + i); i = uspi->s_fpb - count; + inode_sub_bytes(inode, i << uspi->s_fshift); fs32_add(sb, &ucg->cg_cs.cs_nffree, i); uspi->cs_total.cs_nffree += i; fs32_add(sb, &UFS_SB(sb)->fs_cs(cgno).cs_nffree, i); @@ -657,6 +677,8 @@ cg_found: result = ufs_bitmap_search (sb, ucpi, goal, allocsize); if (result == INVBLOCK) return 0; + if (!try_add_frags(inode, count)) + return 0; for (i = 0; i < count; i++) ubh_clrbit (UCPI_UBH(ucpi), ucpi->c_freeoff, result + i); @@ -716,6 +738,8 @@ norot: return INVBLOCK; ucpi->c_rotor = result; gotit: + if (!try_add_frags(inode, uspi->s_fpb)) + return 0; blkno = ufs_fragstoblks(result); ubh_clrblock (UCPI_UBH(ucpi), ucpi->c_freeoff, blkno); if ((UFS_SB(sb)->s_flags & UFS_CG_MASK) == UFS_CG_44BSD) diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index a064cf44b143..1f69bb9b1e9d 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -235,7 +235,8 @@ ufs_extend_tail(struct inode *inode, u64 writes_to, p = ufs_get_direct_data_ptr(uspi, ufsi, block); tmp = ufs_new_fragments(inode, p, lastfrag, ufs_data_ptr_to_cpu(sb, p), - new_size, err, locked_page); + new_size - (lastfrag & uspi->s_fpbmask), err, + locked_page); return tmp != 0; } @@ -284,7 +285,7 @@ ufs_inode_getfrag(struct inode *inode, unsigned index, goal += uspi->s_fpb; } tmp = ufs_new_fragments(inode, p, ufs_blknum(new_fragment), - goal, uspi->s_fpb, err, locked_page); + goal, nfrags, err, locked_page); if (!tmp) { *err = -ENOSPC; @@ -402,7 +403,9 @@ static int ufs_getfrag_block(struct inode *inode, sector_t fragment, struct buff if (!create) { phys64 = ufs_frag_map(inode, offsets, depth); - goto out; + if (phys64) + map_bh(bh_result, sb, phys64 + frag); + return 0; } /* This code entered only while writing ....? */ diff --git a/fs/ufs/super.c b/fs/ufs/super.c index f6390eec02ca..10f364490833 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -746,6 +746,23 @@ static void ufs_put_super(struct super_block *sb) return; } +static u64 ufs_max_bytes(struct super_block *sb) +{ + struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi; + int bits = uspi->s_apbshift; + u64 res; + + if (bits > 21) + res = ~0ULL; + else + res = UFS_NDADDR + (1LL << bits) + (1LL << (2*bits)) + + (1LL << (3*bits)); + + if (res >= (MAX_LFS_FILESIZE >> uspi->s_bshift)) + return MAX_LFS_FILESIZE; + return res << uspi->s_bshift; +} + static int ufs_fill_super(struct super_block *sb, void *data, int silent) { struct ufs_sb_info * sbi; @@ -1212,6 +1229,7 @@ magic_found: "fast symlink size (%u)\n", uspi->s_maxsymlinklen); uspi->s_maxsymlinklen = maxsymlen; } + sb->s_maxbytes = ufs_max_bytes(sb); sb->s_max_links = UFS_LINK_MAX; inode = ufs_iget(sb, UFS_ROOTINO); diff --git a/fs/ufs/util.h b/fs/ufs/util.h index 954175928240..3f9463f8cf2f 100644 --- a/fs/ufs/util.h +++ b/fs/ufs/util.h @@ -473,15 +473,19 @@ static inline unsigned _ubh_find_last_zero_bit_( static inline int _ubh_isblockset_(struct ufs_sb_private_info * uspi, struct ufs_buffer_head * ubh, unsigned begin, unsigned block) { + u8 mask; switch (uspi->s_fpb) { case 8: return (*ubh_get_addr (ubh, begin + block) == 0xff); case 4: - return (*ubh_get_addr (ubh, begin + (block >> 1)) == (0x0f << ((block & 0x01) << 2))); + mask = 0x0f << ((block & 0x01) << 2); + return (*ubh_get_addr (ubh, begin + (block >> 1)) & mask) == mask; case 2: - return (*ubh_get_addr (ubh, begin + (block >> 2)) == (0x03 << ((block & 0x03) << 1))); + mask = 0x03 << ((block & 0x03) << 1); + return (*ubh_get_addr (ubh, begin + (block >> 2)) & mask) == mask; case 1: - return (*ubh_get_addr (ubh, begin + (block >> 3)) == (0x01 << (block & 0x07))); + mask = 0x01 << (block & 0x07); + return (*ubh_get_addr (ubh, begin + (block >> 3)) & mask) == mask; } return 0; } diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 29e7e5dd5178..187b80267ff9 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -288,7 +288,7 @@ xfs_map_blocks( { struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; - ssize_t count = 1 << inode->i_blkbits; + ssize_t count = i_blocksize(inode); xfs_fileoff_t offset_fsb, end_fsb; int error = 0; int bmapi_flags = XFS_BMAPI_ENTIRE; @@ -921,7 +921,7 @@ xfs_aops_discard_page( break; } next_buffer: - offset += 1 << inode->i_blkbits; + offset += i_blocksize(inode); } while ((bh = bh->b_this_page) != head); @@ -1363,7 +1363,7 @@ xfs_map_trim_size( offset + mapping_size >= i_size_read(inode)) { /* limit mapping to block that spans EOF */ mapping_size = roundup_64(i_size_read(inode) - offset, - 1 << inode->i_blkbits); + i_blocksize(inode)); } if (mapping_size > LONG_MAX) mapping_size = LONG_MAX; @@ -1395,7 +1395,7 @@ __xfs_get_blocks( return -EIO; offset = (xfs_off_t)iblock << inode->i_blkbits; - ASSERT(bh_result->b_size >= (1 << inode->i_blkbits)); + ASSERT(bh_result->b_size >= i_blocksize(inode)); size = bh_result->b_size; if (!create && direct && offset >= i_size_read(inode)) @@ -1968,7 +1968,7 @@ xfs_vm_set_page_dirty( if (offset < end_offset) set_buffer_dirty(bh); bh = bh->b_this_page; - offset += 1 << inode->i_blkbits; + offset += i_blocksize(inode); } while (bh != head); } /* diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index ceea444dafb4..3dd47307363f 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -947,7 +947,7 @@ xfs_file_fallocate( if (error) goto out_unlock; } else if (mode & FALLOC_FL_COLLAPSE_RANGE) { - unsigned blksize_mask = (1 << inode->i_blkbits) - 1; + unsigned int blksize_mask = i_blocksize(inode) - 1; if (offset & blksize_mask || len & blksize_mask) { error = -EINVAL; @@ -969,7 +969,7 @@ xfs_file_fallocate( if (error) goto out_unlock; } else if (mode & FALLOC_FL_INSERT_RANGE) { - unsigned blksize_mask = (1 << inode->i_blkbits) - 1; + unsigned int blksize_mask = i_blocksize(inode) - 1; new_size = i_size_read(inode) + len; if (offset & blksize_mask || len & blksize_mask) { diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c index e6dae28dfa1a..9beaf192b4bb 100644 --- a/fs/xfs/xfs_xattr.c +++ b/fs/xfs/xfs_xattr.c @@ -180,6 +180,7 @@ xfs_xattr_put_listent( arraytop = context->count + prefix_len + namelen + 1; if (arraytop > context->firstu) { context->count = -1; /* insufficient space */ + context->seen_enough = 1; return 0; } offset = (char *)context->alist + context->count; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index ad2bcf647b9a..210ccc4ea44b 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -340,6 +340,26 @@ static inline bool css_tryget_online(struct cgroup_subsys_state *css) } /** + * css_is_dying - test whether the specified css is dying + * @css: target css + * + * Test whether @css is in the process of offlining or already offline. In + * most cases, ->css_online() and ->css_offline() callbacks should be + * enough; however, the actual offline operations are RCU delayed and this + * test returns %true also when @css is scheduled to be offlined. + * + * This is useful, for example, when the use case requires synchronous + * behavior with respect to cgroup removal. cgroup removal schedules css + * offlining but the css can seem alive while the operation is being + * delayed. If the delay affects user visible semantics, this test can be + * used to resolve the situation. + */ +static inline bool css_is_dying(struct cgroup_subsys_state *css) +{ + return !(css->flags & CSS_NO_REF) && percpu_ref_is_dying(&css->refcnt); +} + +/** * css_put - put a css reference * @css: target css * diff --git a/include/linux/fs.h b/include/linux/fs.h index e1a123760dbf..c8decb7075d6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -680,6 +680,11 @@ struct inode { void *i_private; /* fs or device private pointer */ }; +static inline unsigned int i_blocksize(const struct inode *node) +{ + return (1 << node->i_blkbits); +} + static inline int inode_unhashed(struct inode *inode) { return hlist_unhashed(&inode->i_hash); diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 24daf8fc4d7c..76b502c6258f 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -408,12 +408,20 @@ static inline void early_memtest(phys_addr_t start, phys_addr_t end) } #endif +extern unsigned long memblock_reserved_memory_within(phys_addr_t start_addr, + phys_addr_t end_addr); #else static inline phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align) { return 0; } +static inline unsigned long memblock_reserved_memory_within(phys_addr_t start_addr, + phys_addr_t end_addr) +{ + return 0; +} + #endif /* CONFIG_HAVE_MEMBLOCK */ #endif /* __KERNEL__ */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index e23a9e704536..5b609a3ce3d7 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -688,6 +688,7 @@ typedef struct pglist_data { * is the first PFN that needs to be initialised. */ unsigned long first_deferred_pfn; + unsigned long static_init_size; #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ } pg_data_t; diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index e13bfdf7f314..81fdf4b8aba4 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -50,7 +50,8 @@ extern int ptrace_request(struct task_struct *child, long request, unsigned long addr, unsigned long data); extern void ptrace_notify(int exit_code); extern void __ptrace_link(struct task_struct *child, - struct task_struct *new_parent); + struct task_struct *new_parent, + const struct cred *ptracer_cred); extern void __ptrace_unlink(struct task_struct *child); extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); #define PTRACE_MODE_READ 0x01 @@ -202,7 +203,7 @@ static inline void ptrace_init_task(struct task_struct *child, bool ptrace) if (unlikely(ptrace) && current->ptrace) { child->ptrace = current->ptrace; - __ptrace_link(child, current->parent); + __ptrace_link(child, current->parent, current->ptracer_cred); if (child->ptrace & PT_SEIZED) task_set_jobctl_pending(child, JOBCTL_TRAP_STOP); @@ -211,6 +212,8 @@ static inline void ptrace_init_task(struct task_struct *child, bool ptrace) set_tsk_thread_flag(child, TIF_SIGPENDING); } + else + child->ptracer_cred = NULL; } /** diff --git a/include/linux/random.h b/include/linux/random.h index a75840c1aa71..9c29122037f9 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -34,6 +34,7 @@ extern const struct file_operations random_fops, urandom_fops; #endif unsigned int get_random_int(void); +unsigned long get_random_long(void); unsigned long randomize_range(unsigned long start, unsigned long end, unsigned long len); u32 prandom_u32(void); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d443d9ab0236..3f61c647fc5c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1084,9 +1084,6 @@ static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) static inline void skb_sender_cpu_clear(struct sk_buff *skb) { -#ifdef CONFIG_XPS - skb->sender_cpu = 0; -#endif } #ifdef NET_SKBUFF_DATA_USES_OFFSET diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 9a5c9f013784..ad1d6039185d 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -958,6 +958,7 @@ int inet6_hash_connect(struct inet_timewait_death_row *death_row, */ extern const struct proto_ops inet6_stream_ops; extern const struct proto_ops inet6_dgram_ops; +extern const struct proto_ops inet6_sockraw_ops; struct group_source_req; struct group_filter; diff --git a/kernel/cpuset.c b/kernel/cpuset.c index b271353d5202..3b5e5430f5d0 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -173,9 +173,9 @@ typedef enum { } cpuset_flagbits_t; /* convenient tests for these bits */ -static inline bool is_cpuset_online(const struct cpuset *cs) +static inline bool is_cpuset_online(struct cpuset *cs) { - return test_bit(CS_ONLINE, &cs->flags); + return test_bit(CS_ONLINE, &cs->flags) && !css_is_dying(&cs->css); } static inline int is_cpu_exclusive(const struct cpuset *cs) diff --git a/kernel/events/core.c b/kernel/events/core.c index 784ab8fe8714..22350b15b4e7 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6410,6 +6410,21 @@ static void perf_log_itrace_start(struct perf_event *event) perf_output_end(&handle); } +static bool sample_is_allowed(struct perf_event *event, struct pt_regs *regs) +{ + /* + * Due to interrupt latency (AKA "skid"), we may enter the + * kernel before taking an overflow, even if the PMU is only + * counting user events. + * To avoid leaking information to userspace, we must always + * reject kernel samples when exclude_kernel is set. + */ + if (event->attr.exclude_kernel && !user_mode(regs)) + return false; + + return true; +} + /* * Generic event overflow handling, sampling. */ @@ -6457,6 +6472,12 @@ static int __perf_event_overflow(struct perf_event *event, } /* + * For security, drop the skid kernel samples if necessary. + */ + if (!sample_is_allowed(event, regs)) + return ret; + + /* * XXX event_limit might not quite work as expected on inherited * events */ diff --git a/kernel/fork.c b/kernel/fork.c index 0ee630f3ad4b..68cfda1c1800 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -368,7 +368,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) set_task_stack_end_magic(tsk); #ifdef CONFIG_CC_STACKPROTECTOR - tsk->stack_canary = get_random_int(); + tsk->stack_canary = get_random_long(); #endif /* diff --git a/kernel/ptrace.c b/kernel/ptrace.c index c7e8ed99c953..5e2cd1030702 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -28,19 +28,25 @@ #include +void __ptrace_link(struct task_struct *child, struct task_struct *new_parent, + const struct cred *ptracer_cred) +{ + BUG_ON(!list_empty(&child->ptrace_entry)); + list_add(&child->ptrace_entry, &new_parent->ptraced); + child->parent = new_parent; + child->ptracer_cred = get_cred(ptracer_cred); +} + /* * ptrace a task: make the debugger its new parent and * move it to the ptrace list. * * Must be called with the tasklist lock write-held. */ -void __ptrace_link(struct task_struct *child, struct task_struct *new_parent) +static void ptrace_link(struct task_struct *child, struct task_struct *new_parent) { - BUG_ON(!list_empty(&child->ptrace_entry)); - list_add(&child->ptrace_entry, &new_parent->ptraced); - child->parent = new_parent; rcu_read_lock(); - child->ptracer_cred = get_cred(__task_cred(new_parent)); + __ptrace_link(child, new_parent, __task_cred(new_parent)); rcu_read_unlock(); } @@ -353,7 +359,7 @@ static int ptrace_attach(struct task_struct *task, long request, flags |= PT_SEIZED; task->ptrace = flags; - __ptrace_link(task, current); + ptrace_link(task, current); /* SEIZE doesn't trap tracee on attach */ if (!seize) @@ -420,7 +426,7 @@ static int ptrace_traceme(void) */ if (!ret && !(current->real_parent->flags & PF_EXITING)) { current->ptrace = PT_PTRACED; - __ptrace_link(current, current->real_parent); + ptrace_link(current, current->real_parent); } } write_unlock_irq(&tasklist_lock); diff --git a/lib/test_user_copy.c b/lib/test_user_copy.c index 0ecef3e4690e..5e6db6b1e3bd 100644 --- a/lib/test_user_copy.c +++ b/lib/test_user_copy.c @@ -58,7 +58,9 @@ static int __init test_user_copy_init(void) usermem = (char __user *)user_addr; bad_usermem = (char *)user_addr; - /* Legitimate usage: none of these should fail. */ + /* + * Legitimate usage: none of these copies should fail. + */ ret |= test(copy_from_user(kmem, usermem, PAGE_SIZE), "legitimate copy_from_user failed"); ret |= test(copy_to_user(usermem, kmem, PAGE_SIZE), @@ -68,19 +70,33 @@ static int __init test_user_copy_init(void) ret |= test(put_user(value, (unsigned long __user *)usermem), "legitimate put_user failed"); - /* Invalid usage: none of these should succeed. */ + /* + * Invalid usage: none of these copies should succeed. + */ + + /* Reject kernel-to-kernel copies through copy_from_user(). */ ret |= test(!copy_from_user(kmem, (char __user *)(kmem + PAGE_SIZE), PAGE_SIZE), "illegal all-kernel copy_from_user passed"); + +#if 0 + /* + * When running with SMAP/PAN/etc, this will Oops the kernel + * due to the zeroing of userspace memory on failure. This needs + * to be tested in LKDTM instead, since this test module does not + * expect to explode. + */ ret |= test(!copy_from_user(bad_usermem, (char __user *)kmem, PAGE_SIZE), "illegal reversed copy_from_user passed"); +#endif ret |= test(!copy_to_user((char __user *)kmem, kmem + PAGE_SIZE, PAGE_SIZE), "illegal all-kernel copy_to_user passed"); ret |= test(!copy_to_user((char __user *)kmem, bad_usermem, PAGE_SIZE), "illegal reversed copy_to_user passed"); + ret |= test(!get_user(value, (unsigned long __user *)kmem), "illegal get_user passed"); ret |= test(!put_user(value, (unsigned long __user *)kmem), diff --git a/mm/memblock.c b/mm/memblock.c index d300f1329814..f8fab45bfdb7 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1634,6 +1634,30 @@ static void __init_memblock memblock_dump(struct memblock_type *type, char *name } } +extern unsigned long __init_memblock +memblock_reserved_memory_within(phys_addr_t start_addr, phys_addr_t end_addr) +{ + struct memblock_type *type = &memblock.reserved; + unsigned long size = 0; + int idx; + + for (idx = 0; idx < type->cnt; idx++) { + struct memblock_region *rgn = &type->regions[idx]; + phys_addr_t start, end; + + if (rgn->base + rgn->size < start_addr) + continue; + if (rgn->base > end_addr) + continue; + + start = rgn->base; + end = start + rgn->size; + size += end - start; + } + + return size; +} + void __init_memblock __memblock_dump_all(void) { pr_info("MEMBLOCK configuration:\n"); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6f9005dcca2e..bd17a6bdf131 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -269,6 +269,26 @@ int page_group_by_mobility_disabled __read_mostly; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT static inline void reset_deferred_meminit(pg_data_t *pgdat) { + unsigned long max_initialise; + unsigned long reserved_lowmem; + + /* + * Initialise at least 2G of a node but also take into account that + * two large system hashes that can take up 1GB for 0.25TB/node. + */ + max_initialise = max(2UL << (30 - PAGE_SHIFT), + (pgdat->node_spanned_pages >> 8)); + + /* + * Compensate the all the memblock reservations (e.g. crash kernel) + * from the initial estimation to make sure we will initialize enough + * memory to boot. + */ + reserved_lowmem = memblock_reserved_memory_within(pgdat->node_start_pfn, + pgdat->node_start_pfn + max_initialise); + max_initialise += reserved_lowmem; + + pgdat->static_init_size = min(max_initialise, pgdat->node_spanned_pages); pgdat->first_deferred_pfn = ULONG_MAX; } @@ -302,10 +322,9 @@ static inline bool update_defer_init(pg_data_t *pgdat, /* Always populate low zones for address-contrained allocations */ if (zone_end < pgdat_end_pfn(pgdat)) return true; - /* Initialise at least 2G of the highest zone */ (*nr_initialised)++; - if (*nr_initialised > (2UL << (30 - PAGE_SHIFT)) && + if ((*nr_initialised > pgdat->static_init_size) && (pfn & (PAGES_PER_SECTION - 1)) == 0) { pgdat->first_deferred_pfn = pfn; return false; @@ -5343,7 +5362,6 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, /* pg_data_t should be reset to zero when it's allocated */ WARN_ON(pgdat->nr_zones || pgdat->classzone_idx); - reset_deferred_meminit(pgdat); pgdat->node_id = nid; pgdat->node_start_pfn = node_start_pfn; #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP @@ -5362,6 +5380,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, (unsigned long)pgdat->node_mem_map); #endif + reset_deferred_meminit(pgdat); free_area_init_core(pgdat); } diff --git a/mm/truncate.c b/mm/truncate.c index 76e35ad97102..f4c8270f7b84 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -732,7 +732,7 @@ EXPORT_SYMBOL(truncate_setsize); */ void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to) { - int bsize = 1 << inode->i_blkbits; + int bsize = i_blocksize(inode); loff_t rounded_from; struct page *page; pgoff_t index; diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 57be733a99bc..bcb4559e735d 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -166,7 +166,8 @@ static void br_stp_start(struct net_bridge *br) br_debug(br, "using kernel STP\n"); /* To start timers on any ports left in blocking */ - mod_timer(&br->hello_timer, jiffies + br->hello_time); + if (br->dev->flags & IFF_UP) + mod_timer(&br->hello_timer, jiffies + br->hello_time); br_port_state_selection(br); } diff --git a/net/core/dev.c b/net/core/dev.c index 48399d8ce614..87b8754f34ac 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -182,7 +182,7 @@ EXPORT_SYMBOL(dev_base_lock); /* protects napi_hash addition/deletion and napi_gen_id */ static DEFINE_SPINLOCK(napi_hash_lock); -static unsigned int napi_gen_id; +static unsigned int napi_gen_id = NR_CPUS; static DEFINE_HASHTABLE(napi_hash, 8); static seqcount_t devnet_rename_seq; @@ -3049,7 +3049,9 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, int queue_index = 0; #ifdef CONFIG_XPS - if (skb->sender_cpu == 0) + u32 sender_cpu = skb->sender_cpu - 1; + + if (sender_cpu >= (u32)NR_CPUS) skb->sender_cpu = raw_smp_processor_id() + 1; #endif @@ -4726,25 +4728,22 @@ EXPORT_SYMBOL_GPL(napi_by_id); void napi_hash_add(struct napi_struct *napi) { - if (!test_and_set_bit(NAPI_STATE_HASHED, &napi->state)) { + if (test_and_set_bit(NAPI_STATE_HASHED, &napi->state)) + return; - spin_lock(&napi_hash_lock); + spin_lock(&napi_hash_lock); - /* 0 is not a valid id, we also skip an id that is taken - * we expect both events to be extremely rare - */ - napi->napi_id = 0; - while (!napi->napi_id) { - napi->napi_id = ++napi_gen_id; - if (napi_by_id(napi->napi_id)) - napi->napi_id = 0; - } + /* 0..NR_CPUS+1 range is reserved for sender_cpu use */ + do { + if (unlikely(++napi_gen_id < NR_CPUS + 1)) + napi_gen_id = NR_CPUS + 1; + } while (napi_by_id(napi_gen_id)); + napi->napi_id = napi_gen_id; - hlist_add_head_rcu(&napi->napi_hash_node, - &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]); + hlist_add_head_rcu(&napi->napi_hash_node, + &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]); - spin_unlock(&napi_hash_lock); - } + spin_unlock(&napi_hash_lock); } EXPORT_SYMBOL_GPL(napi_hash_add); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index afc18e9ca94a..967a47ff78a4 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1014,7 +1014,7 @@ static struct inet_protosw inetsw_array[] = .type = SOCK_DGRAM, .protocol = IPPROTO_ICMP, .prot = &ping_prot, - .ops = &inet_dgram_ops, + .ops = &inet_sockraw_ops, .flags = INET_PROTOSW_REUSE, }, diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 882caa4e72bc..aafe68134763 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -183,6 +183,7 @@ void tcp_init_congestion_control(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); + tcp_sk(sk)->prior_ssthresh = 0; if (icsk->icsk_ca_ops->init) icsk->icsk_ca_ops->init(sk); if (tcp_ca_needs_ecn(sk)) diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 568bc0a52ca1..9e2ea4ae840d 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -121,8 +121,10 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, if (udpfrag) { int err = ip6_find_1stfragopt(skb, &prevhdr); - if (err < 0) + if (err < 0) { + kfree_skb_list(segs); return ERR_PTR(err); + } fptr = (struct frag_hdr *)((u8 *)ipv6h + err); fptr->frag_off = htons(offset); if (skb->next) diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 3e55447b63a4..a830b68e63c9 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -50,7 +50,7 @@ static struct inet_protosw pingv6_protosw = { .type = SOCK_DGRAM, .protocol = IPPROTO_ICMPV6, .prot = &pingv6_prot, - .ops = &inet6_dgram_ops, + .ops = &inet6_sockraw_ops, .flags = INET_PROTOSW_REUSE, }; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index c93ede16795d..4d52a0e2f60d 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1303,7 +1303,7 @@ void raw6_proc_exit(void) #endif /* CONFIG_PROC_FS */ /* Same as inet6_dgram_ops, sans udp_poll. */ -static const struct proto_ops inet6_sockraw_ops = { +const struct proto_ops inet6_sockraw_ops = { .family = PF_INET6, .owner = THIS_MODULE, .release = inet6_release, diff --git a/net/ipv6/xfrm6_mode_ro.c b/net/ipv6/xfrm6_mode_ro.c index 0e015906f9ca..07d36573f50b 100644 --- a/net/ipv6/xfrm6_mode_ro.c +++ b/net/ipv6/xfrm6_mode_ro.c @@ -47,6 +47,8 @@ static int xfrm6_ro_output(struct xfrm_state *x, struct sk_buff *skb) iph = ipv6_hdr(skb); hdr_len = x->type->hdr_offset(x, skb, &prevhdr); + if (hdr_len < 0) + return hdr_len; skb_set_mac_header(skb, (prevhdr - x->props.header_len) - skb->data); skb_set_network_header(skb, -x->props.header_len); skb->transport_header = skb->network_header + hdr_len; diff --git a/net/ipv6/xfrm6_mode_transport.c b/net/ipv6/xfrm6_mode_transport.c index 4e344105b3fd..1d3bbe6e1183 100644 --- a/net/ipv6/xfrm6_mode_transport.c +++ b/net/ipv6/xfrm6_mode_transport.c @@ -28,6 +28,8 @@ static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb) iph = ipv6_hdr(skb); hdr_len = x->type->hdr_offset(x, skb, &prevhdr); + if (hdr_len < 0) + return hdr_len; skb_set_mac_header(skb, (prevhdr - x->props.header_len) - skb->data); skb_set_network_header(skb, -x->props.header_len); skb->transport_header = skb->network_header + hdr_len; diff --git a/security/keys/key.c b/security/keys/key.c index 534808915371..09c10b181881 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -934,12 +934,11 @@ int key_update(key_ref_t key_ref, const void *payload, size_t plen) /* the key must be writable */ ret = key_permission(key_ref, KEY_NEED_WRITE); if (ret < 0) - goto error; + return ret; /* attempt to update it if supported */ - ret = -EOPNOTSUPP; if (!key->type->update) - goto error; + return -EOPNOTSUPP; memset(&prep, 0, sizeof(prep)); prep.data = payload; diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index 442e350c209d..671709d8610d 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -97,7 +97,7 @@ SYSCALL_DEFINE5(add_key, const char __user *, _type, /* pull the payload in if one was supplied */ payload = NULL; - if (_payload) { + if (plen) { ret = -ENOMEM; payload = kmalloc(plen, GFP_KERNEL | __GFP_NOWARN); if (!payload) { @@ -327,7 +327,7 @@ long keyctl_update_key(key_serial_t id, /* pull the payload in if one was supplied */ payload = NULL; - if (_payload) { + if (plen) { ret = -ENOMEM; payload = kmalloc(plen, GFP_KERNEL); if (!payload) diff --git a/sound/core/timer.c b/sound/core/timer.c index 278a332f97bd..48eaccba82a3 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -1621,6 +1621,7 @@ static int snd_timer_user_tselect(struct file *file, if (err < 0) goto __err; + tu->qhead = tu->qtail = tu->qused = 0; kfree(tu->queue); tu->queue = NULL; kfree(tu->tqueue); @@ -1958,6 +1959,7 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer, tu = file->private_data; unit = tu->tread ? sizeof(struct snd_timer_tread) : sizeof(struct snd_timer_read); + mutex_lock(&tu->ioctl_lock); spin_lock_irq(&tu->qlock); while ((long)count - result >= unit) { while (!tu->qused) { @@ -1973,7 +1975,9 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer, add_wait_queue(&tu->qchange_sleep, &wait); spin_unlock_irq(&tu->qlock); + mutex_unlock(&tu->ioctl_lock); schedule(); + mutex_lock(&tu->ioctl_lock); spin_lock_irq(&tu->qlock); remove_wait_queue(&tu->qchange_sleep, &wait); @@ -1993,7 +1997,6 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer, tu->qused--; spin_unlock_irq(&tu->qlock); - mutex_lock(&tu->ioctl_lock); if (tu->tread) { if (copy_to_user(buffer, &tu->tqueue[qhead], sizeof(struct snd_timer_tread))) @@ -2003,7 +2006,6 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer, sizeof(struct snd_timer_read))) err = -EFAULT; } - mutex_unlock(&tu->ioctl_lock); spin_lock_irq(&tu->qlock); if (err < 0) @@ -2013,6 +2015,7 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer, } _error: spin_unlock_irq(&tu->qlock); + mutex_unlock(&tu->ioctl_lock); return result > 0 ? result : err; } diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index a1305f827a98..fa6b74a304a7 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -1775,6 +1775,9 @@ static int soc_cleanup_card_resources(struct snd_soc_card *card) for (i = 0; i < card->num_aux_devs; i++) soc_remove_aux_dev(card, i); + /* free the ALSA card at first; this syncs with pending operations */ + snd_card_free(card->snd_card); + /* remove and free each DAI */ soc_remove_dai_links(card); @@ -1786,9 +1789,7 @@ static int soc_cleanup_card_resources(struct snd_soc_card *card) snd_soc_dapm_free(&card->dapm); - snd_card_free(card->snd_card); return 0; - } /* removes a socdev */