diff --git a/Makefile b/Makefile index e99e5a5d571b..8a3f507065f9 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 3 PATCHLEVEL = 4 -SUBLEVEL = 110 +SUBLEVEL = 111 EXTRAVERSION = NAME = Saber-toothed Squirrel diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index b2202a68cf0f..95bcedbdc92c 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -153,8 +153,39 @@ static inline void set_pte(pte_t *ptep, pte_t pteval) * Make sure the buddy is global too (if it's !none, * it better already be global) */ +#ifdef CONFIG_SMP + /* + * For SMP, multiple CPUs can race, so we need to do + * this atomically. + */ +#ifdef CONFIG_64BIT +#define LL_INSN "lld" +#define SC_INSN "scd" +#else /* CONFIG_32BIT */ +#define LL_INSN "ll" +#define SC_INSN "sc" +#endif + unsigned long page_global = _PAGE_GLOBAL; + unsigned long tmp; + + __asm__ __volatile__ ( + " .set push\n" + " .set noreorder\n" + "1: " LL_INSN " %[tmp], %[buddy]\n" + " bnez %[tmp], 2f\n" + " or %[tmp], %[tmp], %[global]\n" + " " SC_INSN " %[tmp], %[buddy]\n" + " beqz %[tmp], 1b\n" + " nop\n" + "2:\n" + " .set pop" + : [buddy] "+m" (buddy->pte), + [tmp] "=&r" (tmp) + : [global] "r" (page_global)); +#else /* !CONFIG_SMP */ if (pte_none(*buddy)) pte_val(*buddy) = pte_val(*buddy) | _PAGE_GLOBAL; +#endif /* CONFIG_SMP */ } #endif } diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c index 33f63bab478a..c7e2684a53c9 100644 --- a/arch/mips/kernel/mips-mt-fpaff.c +++ b/arch/mips/kernel/mips-mt-fpaff.c @@ -154,7 +154,7 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len, unsigned long __user *user_mask_ptr) { unsigned int real_len; - cpumask_t mask; + cpumask_t allowed, mask; int retval; struct task_struct *p; @@ -173,7 +173,8 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len, if (retval) goto out_unlock; - cpumask_and(&mask, &p->thread.user_cpus_allowed, cpu_possible_mask); + cpumask_or(&allowed, &p->thread.user_cpus_allowed, &p->cpus_allowed); + cpumask_and(&mask, &allowed, cpu_active_mask); out_unlock: read_unlock(&tasklist_lock); diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 60055cefdd04..5f947e531562 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -246,7 +246,7 @@ asmlinkage void execve_tail(void) { current->thread.fp_regs.fpc = 0; if (MACHINE_HAS_IEEE) - asm volatile("sfpc %0,%0" : : "d" (0)); + asm volatile("sfpc %0" : : "d" (0)); } /* diff --git a/arch/s390/kernel/sclp.S b/arch/s390/kernel/sclp.S index 95792d846bb6..51ca1c3b42db 100644 --- a/arch/s390/kernel/sclp.S +++ b/arch/s390/kernel/sclp.S @@ -270,6 +270,8 @@ ENTRY(_sclp_print_early) jno .Lesa2 ahi %r15,-80 stmh %r6,%r15,96(%r15) # store upper register halves + basr %r13,0 + lmh %r0,%r15,.Lzeroes-.(%r13) # clear upper register halves .Lesa2: #endif lr %r10,%r2 # save string pointer @@ -293,6 +295,8 @@ ENTRY(_sclp_print_early) #endif lm %r6,%r15,120(%r15) # restore registers br %r14 +.Lzeroes: + .fill 64,4,0 .LwritedataS4: .long 0x00760005 # SCLP command for write data diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c index fd107ab7dd26..c40f8062e3a9 100644 --- a/arch/tile/kernel/setup.c +++ b/arch/tile/kernel/setup.c @@ -972,7 +972,7 @@ static void __init load_hv_initrd(void) void __init free_initrd_mem(unsigned long begin, unsigned long end) { - free_bootmem(__pa(begin), end - begin); + free_bootmem_late(__pa(begin), end - begin); } #else diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index fa9c8c7bc500..d34c94fb3375 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -279,21 +279,6 @@ static inline void clear_LDT(void) set_ldt(NULL, 0); } -/* - * load one particular LDT into the current CPU - */ -static inline void load_LDT_nolock(mm_context_t *pc) -{ - set_ldt(pc->ldt, pc->size); -} - -static inline void load_LDT(mm_context_t *pc) -{ - preempt_disable(); - load_LDT_nolock(pc); - preempt_enable(); -} - static inline unsigned long get_desc_base(const struct desc_struct *desc) { return (unsigned)(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24)); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index d60facb1a9d4..493b0267f23e 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -87,6 +87,7 @@ #define GP_VECTOR 13 #define PF_VECTOR 14 #define MF_VECTOR 16 +#define AC_VECTOR 17 #define MC_VECTOR 18 #define SELECTOR_TI_MASK (1 << 2) diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index 5f55e6962769..926f67263287 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -9,8 +9,7 @@ * we put the segment information here. */ typedef struct { - void *ldt; - int size; + struct ldt_struct *ldt; #ifdef CONFIG_X86_64 /* True if mm supports a task running in 32 bit compatibility mode. */ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 69021528b43c..ce4ea94fc4be 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -16,6 +16,51 @@ static inline void paravirt_activate_mm(struct mm_struct *prev, #endif /* !CONFIG_PARAVIRT */ /* + * ldt_structs can be allocated, used, and freed, but they are never + * modified while live. + */ +struct ldt_struct { + /* + * Xen requires page-aligned LDTs with special permissions. This is + * needed to prevent us from installing evil descriptors such as + * call gates. On native, we could merge the ldt_struct and LDT + * allocations, but it's not worth trying to optimize. + */ + struct desc_struct *entries; + int size; +}; + +static inline void load_mm_ldt(struct mm_struct *mm) +{ + struct ldt_struct *ldt; + + /* smp_read_barrier_depends synchronizes with barrier in install_ldt */ + ldt = ACCESS_ONCE(mm->context.ldt); + smp_read_barrier_depends(); + + /* + * Any change to mm->context.ldt is followed by an IPI to all + * CPUs with the mm active. The LDT will not be freed until + * after the IPI is handled by all such CPUs. This means that, + * if the ldt_struct changes before we return, the values we see + * will be safe, and the new values will be loaded before we run + * any user code. + * + * NB: don't try to convert this to use RCU without extreme care. + * We would still need IRQs off, because we don't want to change + * the local LDT after an IPI loaded a newer value than the one + * that we can see. + */ + + if (unlikely(ldt)) + set_ldt(ldt->entries, ldt->size); + else + clear_LDT(); + + DEBUG_LOCKS_WARN_ON(preemptible()); +} + +/* * Used for LDT copy/destruction. */ int init_new_context(struct task_struct *tsk, struct mm_struct *mm); @@ -52,7 +97,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, * load the LDT, if the LDT is different: */ if (unlikely(prev->context.ldt != next->context.ldt)) - load_LDT_nolock(&next->context); + load_mm_ldt(next); } #ifdef CONFIG_SMP else { @@ -65,7 +110,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, * to make sure to use no freed page tables. */ load_cr3(next->pgd); - load_LDT_nolock(&next->context); + load_mm_ldt(next); } } #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 114db0fee86c..b190a620a850 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1254,7 +1254,7 @@ void __cpuinit cpu_init(void) load_sp0(t, ¤t->thread); set_tss_desc(cpu, t); load_TR_desc(); - load_LDT(&init_mm.context); + load_mm_ldt(&init_mm); clear_all_debug_regs(); dbg_restore_debug_regs(); @@ -1302,7 +1302,7 @@ void __cpuinit cpu_init(void) load_sp0(t, thread); set_tss_desc(cpu, t); load_TR_desc(); - load_LDT(&init_mm.context); + load_mm_ldt(&init_mm); t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap); diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index c37886d759cc..fba5131ce71e 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include @@ -20,82 +21,87 @@ #include #include -#ifdef CONFIG_SMP +/* context.lock is held for us, so we don't need any locking. */ static void flush_ldt(void *current_mm) { - if (current->active_mm == current_mm) - load_LDT(¤t->active_mm->context); + mm_context_t *pc; + + if (current->active_mm != current_mm) + return; + + pc = ¤t->active_mm->context; + set_ldt(pc->ldt->entries, pc->ldt->size); } -#endif -static int alloc_ldt(mm_context_t *pc, int mincount, int reload) +/* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */ +static struct ldt_struct *alloc_ldt_struct(int size) { - void *oldldt, *newldt; - int oldsize; - - if (mincount <= pc->size) - return 0; - oldsize = pc->size; - mincount = (mincount + (PAGE_SIZE / LDT_ENTRY_SIZE - 1)) & - (~(PAGE_SIZE / LDT_ENTRY_SIZE - 1)); - if (mincount * LDT_ENTRY_SIZE > PAGE_SIZE) - newldt = vmalloc(mincount * LDT_ENTRY_SIZE); + struct ldt_struct *new_ldt; + int alloc_size; + + if (size > LDT_ENTRIES) + return NULL; + + new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL); + if (!new_ldt) + return NULL; + + BUILD_BUG_ON(LDT_ENTRY_SIZE != sizeof(struct desc_struct)); + alloc_size = size * LDT_ENTRY_SIZE; + + /* + * Xen is very picky: it requires a page-aligned LDT that has no + * trailing nonzero bytes in any page that contains LDT descriptors. + * Keep it simple: zero the whole allocation and never allocate less + * than PAGE_SIZE. + */ + if (alloc_size > PAGE_SIZE) + new_ldt->entries = vzalloc(alloc_size); else - newldt = (void *)__get_free_page(GFP_KERNEL); - - if (!newldt) - return -ENOMEM; + new_ldt->entries = kzalloc(PAGE_SIZE, GFP_KERNEL); - if (oldsize) - memcpy(newldt, pc->ldt, oldsize * LDT_ENTRY_SIZE); - oldldt = pc->ldt; - memset(newldt + oldsize * LDT_ENTRY_SIZE, 0, - (mincount - oldsize) * LDT_ENTRY_SIZE); + if (!new_ldt->entries) { + kfree(new_ldt); + return NULL; + } - paravirt_alloc_ldt(newldt, mincount); + new_ldt->size = size; + return new_ldt; +} -#ifdef CONFIG_X86_64 - /* CHECKME: Do we really need this ? */ - wmb(); -#endif - pc->ldt = newldt; - wmb(); - pc->size = mincount; - wmb(); - - if (reload) { -#ifdef CONFIG_SMP - preempt_disable(); - load_LDT(pc); - if (!cpumask_equal(mm_cpumask(current->mm), - cpumask_of(smp_processor_id()))) - smp_call_function(flush_ldt, current->mm, 1); - preempt_enable(); -#else - load_LDT(pc); -#endif - } - if (oldsize) { - paravirt_free_ldt(oldldt, oldsize); - if (oldsize * LDT_ENTRY_SIZE > PAGE_SIZE) - vfree(oldldt); - else - put_page(virt_to_page(oldldt)); - } - return 0; +/* After calling this, the LDT is immutable. */ +static void finalize_ldt_struct(struct ldt_struct *ldt) +{ + paravirt_alloc_ldt(ldt->entries, ldt->size); } -static inline int copy_ldt(mm_context_t *new, mm_context_t *old) +/* context.lock is held */ +static void install_ldt(struct mm_struct *current_mm, + struct ldt_struct *ldt) { - int err = alloc_ldt(new, old->size, 0); - int i; + /* Synchronizes with smp_read_barrier_depends in load_mm_ldt. */ + barrier(); + ACCESS_ONCE(current_mm->context.ldt) = ldt; + + /* Activate the LDT for all CPUs using current_mm. */ + smp_call_function_many(mm_cpumask(current_mm), flush_ldt, current_mm, + true); + local_irq_disable(); + flush_ldt(current_mm); + local_irq_enable(); +} - if (err < 0) - return err; +static void free_ldt_struct(struct ldt_struct *ldt) +{ + if (likely(!ldt)) + return; - for (i = 0; i < old->size; i++) - write_ldt_entry(new->ldt, i, old->ldt + i * LDT_ENTRY_SIZE); - return 0; + paravirt_free_ldt(ldt->entries, ldt->size); + if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE) + vfree(ldt->entries); + else + kfree(ldt->entries); + kfree(ldt); } /* @@ -104,17 +110,37 @@ static inline int copy_ldt(mm_context_t *new, mm_context_t *old) */ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { + struct ldt_struct *new_ldt; struct mm_struct *old_mm; int retval = 0; mutex_init(&mm->context.lock); - mm->context.size = 0; old_mm = current->mm; - if (old_mm && old_mm->context.size > 0) { - mutex_lock(&old_mm->context.lock); - retval = copy_ldt(&mm->context, &old_mm->context); - mutex_unlock(&old_mm->context.lock); + if (!old_mm) { + mm->context.ldt = NULL; + return 0; + } + + mutex_lock(&old_mm->context.lock); + if (!old_mm->context.ldt) { + mm->context.ldt = NULL; + goto out_unlock; } + + new_ldt = alloc_ldt_struct(old_mm->context.ldt->size); + if (!new_ldt) { + retval = -ENOMEM; + goto out_unlock; + } + + memcpy(new_ldt->entries, old_mm->context.ldt->entries, + new_ldt->size * LDT_ENTRY_SIZE); + finalize_ldt_struct(new_ldt); + + mm->context.ldt = new_ldt; + +out_unlock: + mutex_unlock(&old_mm->context.lock); return retval; } @@ -125,53 +151,47 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) */ void destroy_context(struct mm_struct *mm) { - if (mm->context.size) { -#ifdef CONFIG_X86_32 - /* CHECKME: Can this ever happen ? */ - if (mm == current->active_mm) - clear_LDT(); -#endif - paravirt_free_ldt(mm->context.ldt, mm->context.size); - if (mm->context.size * LDT_ENTRY_SIZE > PAGE_SIZE) - vfree(mm->context.ldt); - else - put_page(virt_to_page(mm->context.ldt)); - mm->context.size = 0; - } + free_ldt_struct(mm->context.ldt); + mm->context.ldt = NULL; } static int read_ldt(void __user *ptr, unsigned long bytecount) { - int err; + int retval; unsigned long size; struct mm_struct *mm = current->mm; - if (!mm->context.size) - return 0; + mutex_lock(&mm->context.lock); + + if (!mm->context.ldt) { + retval = 0; + goto out_unlock; + } + if (bytecount > LDT_ENTRY_SIZE * LDT_ENTRIES) bytecount = LDT_ENTRY_SIZE * LDT_ENTRIES; - mutex_lock(&mm->context.lock); - size = mm->context.size * LDT_ENTRY_SIZE; + size = mm->context.ldt->size * LDT_ENTRY_SIZE; if (size > bytecount) size = bytecount; - err = 0; - if (copy_to_user(ptr, mm->context.ldt, size)) - err = -EFAULT; - mutex_unlock(&mm->context.lock); - if (err < 0) - goto error_return; + if (copy_to_user(ptr, mm->context.ldt->entries, size)) { + retval = -EFAULT; + goto out_unlock; + } + if (size != bytecount) { - /* zero-fill the rest */ - if (clear_user(ptr + size, bytecount - size) != 0) { - err = -EFAULT; - goto error_return; + /* Zero-fill the rest and pretend we read bytecount bytes. */ + if (clear_user(ptr + size, bytecount - size)) { + retval = -EFAULT; + goto out_unlock; } } - return bytecount; -error_return: - return err; + retval = bytecount; + +out_unlock: + mutex_unlock(&mm->context.lock); + return retval; } static int read_default_ldt(void __user *ptr, unsigned long bytecount) @@ -195,6 +215,8 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) struct desc_struct ldt; int error; struct user_desc ldt_info; + int oldsize, newsize; + struct ldt_struct *new_ldt, *old_ldt; error = -EINVAL; if (bytecount != sizeof(ldt_info)) @@ -213,34 +235,39 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) goto out; } - mutex_lock(&mm->context.lock); - if (ldt_info.entry_number >= mm->context.size) { - error = alloc_ldt(¤t->mm->context, - ldt_info.entry_number + 1, 1); - if (error < 0) - goto out_unlock; - } - - /* Allow LDTs to be cleared by the user. */ - if (ldt_info.base_addr == 0 && ldt_info.limit == 0) { - if (oldmode || LDT_empty(&ldt_info)) { - memset(&ldt, 0, sizeof(ldt)); - goto install; + if ((oldmode && !ldt_info.base_addr && !ldt_info.limit) || + LDT_empty(&ldt_info)) { + /* The user wants to clear the entry. */ + memset(&ldt, 0, sizeof(ldt)); + } else { + if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) { + error = -EINVAL; + goto out; } + + fill_ldt(&ldt, &ldt_info); + if (oldmode) + ldt.avl = 0; } - if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) { - error = -EINVAL; + mutex_lock(&mm->context.lock); + + old_ldt = mm->context.ldt; + oldsize = old_ldt ? old_ldt->size : 0; + newsize = max((int)(ldt_info.entry_number + 1), oldsize); + + error = -ENOMEM; + new_ldt = alloc_ldt_struct(newsize); + if (!new_ldt) goto out_unlock; - } - fill_ldt(&ldt, &ldt_info); - if (oldmode) - ldt.avl = 0; + if (old_ldt) + memcpy(new_ldt->entries, old_ldt->entries, oldsize * LDT_ENTRY_SIZE); + new_ldt->entries[ldt_info.entry_number] = ldt; + finalize_ldt_struct(new_ldt); - /* Install the new entry ... */ -install: - write_ldt_entry(mm->context.ldt, ldt_info.entry_number, &ldt); + install_ldt(mm, new_ldt); + free_ldt_struct(old_ldt); error = 0; out_unlock: diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index bb390e1ba600..d5d7313ed430 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -116,11 +116,11 @@ void __show_regs(struct pt_regs *regs, int all) void release_thread(struct task_struct *dead_task) { if (dead_task->mm) { - if (dead_task->mm->context.size) { + if (dead_task->mm->context.ldt) { printk("WARNING: dead process %8s still has LDT? <%p/%d>\n", dead_task->comm, - dead_task->mm->context.ldt, - dead_task->mm->context.size); + dead_task->mm->context.ldt->entries, + dead_task->mm->context.ldt->size); BUG(); } } diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index f89cdc6ccd5b..1565262dce89 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -5,6 +5,7 @@ #include #include #include +#include unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs) { @@ -27,13 +28,14 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re struct desc_struct *desc; unsigned long base; - seg &= ~7UL; + seg >>= 3; mutex_lock(&child->mm->context.lock); - if (unlikely((seg >> 3) >= child->mm->context.size)) + if (unlikely(!child->mm->context.ldt || + seg >= child->mm->context.ldt->size)) addr = -1L; /* bogus selector, access would fault */ else { - desc = child->mm->context.ldt + seg; + desc = &child->mm->context.ldt->entries[seg]; base = get_desc_base(desc); /* 16-bit code segment? */ diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 86c74c0cd876..6201ca0c9770 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1081,6 +1081,8 @@ static void init_vmcb(struct vcpu_svm *svm) set_exception_intercept(svm, PF_VECTOR); set_exception_intercept(svm, UD_VECTOR); set_exception_intercept(svm, MC_VECTOR); + set_exception_intercept(svm, AC_VECTOR); + set_exception_intercept(svm, DB_VECTOR); set_intercept(svm, INTERCEPT_INTR); set_intercept(svm, INTERCEPT_NMI); @@ -1636,20 +1638,13 @@ static void svm_set_segment(struct kvm_vcpu *vcpu, mark_dirty(svm->vmcb, VMCB_SEG); } -static void update_db_intercept(struct kvm_vcpu *vcpu) +static void update_bp_intercept(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - clr_exception_intercept(svm, DB_VECTOR); clr_exception_intercept(svm, BP_VECTOR); - if (svm->nmi_singlestep) - set_exception_intercept(svm, DB_VECTOR); - if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) { - if (vcpu->guest_debug & - (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) - set_exception_intercept(svm, DB_VECTOR); if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) set_exception_intercept(svm, BP_VECTOR); } else @@ -1667,7 +1662,7 @@ static void svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) mark_dirty(svm->vmcb, VMCB_DR); - update_db_intercept(vcpu); + update_bp_intercept(vcpu); } static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd) @@ -1741,7 +1736,6 @@ static int db_interception(struct vcpu_svm *svm) if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP)) svm->vmcb->save.rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); - update_db_intercept(&svm->vcpu); } if (svm->vcpu.guest_debug & @@ -1776,6 +1770,12 @@ static int ud_interception(struct vcpu_svm *svm) return 1; } +static int ac_interception(struct vcpu_svm *svm) +{ + kvm_queue_exception_e(&svm->vcpu, AC_VECTOR, 0); + return 1; +} + static void svm_fpu_activate(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -3291,6 +3291,7 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception, [SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception, [SVM_EXIT_EXCP_BASE + MC_VECTOR] = mc_interception, + [SVM_EXIT_EXCP_BASE + AC_VECTOR] = ac_interception, [SVM_EXIT_INTR] = intr_interception, [SVM_EXIT_NMI] = nmi_interception, [SVM_EXIT_SMI] = nop_on_interception, @@ -3653,7 +3654,6 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu) */ svm->nmi_singlestep = true; svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF); - update_db_intercept(vcpu); } static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr) diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 911d2641f14c..d26a7e24464e 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -244,6 +244,7 @@ TRACE_EVENT(kvm_apic, { SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" }, \ { SVM_EXIT_EXCP_BASE + PF_VECTOR, "PF excp" }, \ { SVM_EXIT_EXCP_BASE + NM_VECTOR, "NM excp" }, \ + { SVM_EXIT_EXCP_BASE + AC_VECTOR, "AC excp" }, \ { SVM_EXIT_EXCP_BASE + MC_VECTOR, "MC excp" }, \ { SVM_EXIT_INTR, "interrupt" }, \ { SVM_EXIT_NMI, "nmi" }, \ diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 4ad0d7171d6c..defd510486fd 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1169,7 +1169,7 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) u32 eb; eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) | - (1u << NM_VECTOR) | (1u << DB_VECTOR); + (1u << NM_VECTOR) | (1u << DB_VECTOR) | (1u << AC_VECTOR); if ((vcpu->guest_debug & (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) == (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) @@ -4260,6 +4260,9 @@ static int handle_exception(struct kvm_vcpu *vcpu) ex_no = intr_info & INTR_INFO_VECTOR_MASK; switch (ex_no) { + case AC_VECTOR: + kvm_queue_exception_e(vcpu, AC_VECTOR, error_code); + return 1; case DB_VECTOR: dr6 = vmcs_readl(EXIT_QUALIFICATION); if (!(vcpu->guest_debug & diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4ad2b7bb382e..9cc83e287adf 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1545,6 +1545,8 @@ static void accumulate_steal_time(struct kvm_vcpu *vcpu) static void record_steal_time(struct kvm_vcpu *vcpu) { + accumulate_steal_time(vcpu); + if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; @@ -1665,12 +1667,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) if (!(data & KVM_MSR_ENABLED)) break; - vcpu->arch.st.last_steal = current->sched_info.run_delay; - - preempt_disable(); - accumulate_steal_time(vcpu); - preempt_enable(); - kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); break; @@ -2327,7 +2323,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) vcpu->cpu = cpu; } - accumulate_steal_time(vcpu); kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); } diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c index 9b868124128d..274a52b1183e 100644 --- a/arch/x86/math-emu/fpu_entry.c +++ b/arch/x86/math-emu/fpu_entry.c @@ -29,7 +29,6 @@ #include #include -#include #include #include @@ -185,7 +184,7 @@ void math_emulate(struct math_emu_info *info) math_abort(FPU_info, SIGILL); } - code_descriptor = LDT_DESCRIPTOR(FPU_CS); + code_descriptor = FPU_get_ldt_descriptor(FPU_CS); if (SEG_D_SIZE(code_descriptor)) { /* The above test may be wrong, the book is not clear */ /* Segmented 32 bit protected mode */ diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h index 2c614410a5f3..d342fce49447 100644 --- a/arch/x86/math-emu/fpu_system.h +++ b/arch/x86/math-emu/fpu_system.h @@ -16,9 +16,24 @@ #include #include -/* s is always from a cpu register, and the cpu does bounds checking - * during register load --> no further bounds checks needed */ -#define LDT_DESCRIPTOR(s) (((struct desc_struct *)current->mm->context.ldt)[(s) >> 3]) +#include +#include + +static inline struct desc_struct FPU_get_ldt_descriptor(unsigned seg) +{ + static struct desc_struct zero_desc; + struct desc_struct ret = zero_desc; + +#ifdef CONFIG_MODIFY_LDT_SYSCALL + seg >>= 3; + mutex_lock(¤t->mm->context.lock); + if (current->mm->context.ldt && seg < current->mm->context.ldt->size) + ret = current->mm->context.ldt->entries[seg]; + mutex_unlock(¤t->mm->context.lock); +#endif + return ret; +} + #define SEG_D_SIZE(x) ((x).b & (3 << 21)) #define SEG_G_BIT(x) ((x).b & (1 << 23)) #define SEG_GRANULARITY(x) (((x).b & (1 << 23)) ? 4096 : 1) diff --git a/arch/x86/math-emu/get_address.c b/arch/x86/math-emu/get_address.c index 6ef5e99380f9..d13cab2aec45 100644 --- a/arch/x86/math-emu/get_address.c +++ b/arch/x86/math-emu/get_address.c @@ -20,7 +20,6 @@ #include #include -#include #include "fpu_system.h" #include "exception.h" @@ -158,7 +157,7 @@ static long pm_address(u_char FPU_modrm, u_char segment, addr->selector = PM_REG_(segment); } - descriptor = LDT_DESCRIPTOR(PM_REG_(segment)); + descriptor = FPU_get_ldt_descriptor(segment); base_address = SEG_BASE_ADDR(descriptor); address = base_address + offset; limit = base_address diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index fcbaac60d938..dd298e73cbb3 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -22,6 +22,7 @@ #include #include #include /* pcntxt_mask */ +#include #ifdef CONFIG_X86_32 static struct saved_context saved_context; @@ -148,7 +149,7 @@ static void fix_processor_context(void) syscall_init(); /* This sets MSR_*STAR and related */ #endif load_TR_desc(); /* This does ltr */ - load_LDT(¤t->active_mm->context); /* This does lldt */ + load_mm_ldt(current->active_mm); /* This does lldt */ } /** diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 95980387eeb5..8ade106b879b 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -413,6 +413,7 @@ static void set_aliased_prot(void *v, pgprot_t prot) pte_t pte; unsigned long pfn; struct page *page; + unsigned char dummy; ptep = lookup_address((unsigned long)v, &level); BUG_ON(ptep == NULL); @@ -422,6 +423,32 @@ static void set_aliased_prot(void *v, pgprot_t prot) pte = pfn_pte(pfn, prot); + /* + * Careful: update_va_mapping() will fail if the virtual address + * we're poking isn't populated in the page tables. We don't + * need to worry about the direct map (that's always in the page + * tables), but we need to be careful about vmap space. In + * particular, the top level page table can lazily propagate + * entries between processes, so if we've switched mms since we + * vmapped the target in the first place, we might not have the + * top-level page table entry populated. + * + * We disable preemption because we want the same mm active when + * we probe the target and when we issue the hypercall. We'll + * have the same nominal mm, but if we're a kernel thread, lazy + * mm dropping could change our pgd. + * + * Out of an abundance of caution, this uses __get_user() to fault + * in the target address just in case there's some obscure case + * in which the target address isn't readable. + */ + + preempt_disable(); + + pagefault_disable(); /* Avoid warnings due to being atomic. */ + __get_user(dummy, (unsigned char __user __force *)v); + pagefault_enable(); + if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0)) BUG(); @@ -433,6 +460,8 @@ static void set_aliased_prot(void *v, pgprot_t prot) BUG(); } else kmap_flush_unused(); + + preempt_enable(); } static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries) @@ -440,6 +469,17 @@ static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries) const unsigned entries_per_page = PAGE_SIZE / LDT_ENTRY_SIZE; int i; + /* + * We need to mark the all aliases of the LDT pages RO. We + * don't need to call vm_flush_aliases(), though, since that's + * only responsible for flushing aliases out the TLBs, not the + * page tables, and Xen will flush the TLB for us if needed. + * + * To avoid confusing future readers: none of this is necessary + * to load the LDT. The hypervisor only checks this when the + * LDT is faulted in due to subsequent descriptor access. + */ + for(i = 0; i < entries; i += entries_per_page) set_aliased_prot(ldt + i, PAGE_KERNEL_RO); } diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 0a6767b9939c..68bdd59e5e62 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4104,9 +4104,10 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "ST3320[68]13AS", "SD1[5-9]", ATA_HORKAGE_NONCQ | ATA_HORKAGE_FIRMWARE_WARN }, - /* Seagate Momentus SpinPoint M8 seem to have FPMDA_AA issues */ + /* drives which fail FPDMA_AA activation (some may freeze afterwards) */ { "ST1000LM024 HN-M101MBB", "2AR10001", ATA_HORKAGE_BROKEN_FPDMA_AA }, { "ST1000LM024 HN-M101MBB", "2BA30001", ATA_HORKAGE_BROKEN_FPDMA_AA }, + { "VB0250EAVER", "HPG7", ATA_HORKAGE_BROKEN_FPDMA_AA }, /* Blacklist entries taken from Silicon Image 3124/3132 Windows driver .inf file - also several Linux problem reports */ @@ -4143,6 +4144,9 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "WD My Book", NULL, ATA_HORKAGE_1_5_GBPS, }, { "Seagate FreeAgent GoFlex", NULL, ATA_HORKAGE_1_5_GBPS, }, + /* devices that don't properly handle TRIM commands */ + { "SuperSSpeed S238*", NULL, ATA_HORKAGE_NOTRIM, }, + /* * Devices which choke on SETXFER. Applies only if both the * device and controller are SATA. @@ -4440,7 +4444,8 @@ static unsigned int ata_dev_set_xfermode(struct ata_device *dev) else /* In the ancient relic department - skip all of this */ return 0; - err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0); + /* On some disks, this command causes spin-up, so we need longer timeout */ + err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 15000); DPRINTK("EXIT, err_mask=%x\n", err_mask); return err_mask; diff --git a/drivers/ata/libata-pmp.c b/drivers/ata/libata-pmp.c index 0ba32fe00d13..93ea33509fa8 100644 --- a/drivers/ata/libata-pmp.c +++ b/drivers/ata/libata-pmp.c @@ -460,6 +460,13 @@ static void sata_pmp_quirks(struct ata_port *ap) ATA_LFLAG_NO_SRST | ATA_LFLAG_ASSUME_ATA; } + } else if (vendor == 0x11ab && devid == 0x4140) { + /* Marvell 4140 quirks */ + ata_for_each_link(link, ap, EDGE) { + /* port 4 is for SEMB device and it doesn't like SRST */ + if (link->pmp == 4) + link->flags |= ATA_LFLAG_DISABLED; + } } } diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 15863a4b6190..94ccbc15f5fb 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -2461,7 +2461,8 @@ static unsigned int ata_scsiop_read_cap(struct ata_scsi_args *args, u8 *rbuf) rbuf[14] = (lowest_aligned >> 8) & 0x3f; rbuf[15] = lowest_aligned; - if (ata_id_has_trim(args->id)) { + if (ata_id_has_trim(args->id) && + !(dev->horkage & ATA_HORKAGE_NOTRIM)) { rbuf[14] |= 0x80; /* TPE */ if (ata_id_has_zero_after_trim(args->id)) diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c index 8f3f74ce8c7f..f731abcf3f33 100644 --- a/drivers/crypto/ixp4xx_crypto.c +++ b/drivers/crypto/ixp4xx_crypto.c @@ -915,7 +915,6 @@ static int ablk_perform(struct ablkcipher_request *req, int encrypt) crypt->mode |= NPE_OP_NOT_IN_PLACE; /* This was never tested by Intel * for more than one dst buffer, I think. */ - BUG_ON(req->dst->length < nbytes); req_ctx->dst = NULL; if (!chainup_buffers(dev, req->dst, nbytes, &dst_hook, flags, DMA_FROM_DEVICE)) diff --git a/drivers/edac/ppc4xx_edac.c b/drivers/edac/ppc4xx_edac.c index d427c69bb8b1..9212f6c7ee95 100644 --- a/drivers/edac/ppc4xx_edac.c +++ b/drivers/edac/ppc4xx_edac.c @@ -919,7 +919,7 @@ ppc4xx_edac_init_csrows(struct mem_ctl_info *mci, u32 mcopt1) */ for (row = 0; row < mci->nr_csrows; row++) { - struct csrow_info *csi = &mci->csrows[row]; + struct csrow_info *csi = mci->csrows[row]; /* * Get the configuration settings for this diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index c61e67222160..ed4b7481a865 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -1836,8 +1836,11 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, if (!drm_core_check_feature(dev, DRIVER_MODESET)) return -EINVAL; - /* For some reason crtc x/y offsets are signed internally. */ - if (crtc_req->x > INT_MAX || crtc_req->y > INT_MAX) + /* + * Universal plane src offsets are only 16.16, prevent havoc for + * drivers using universal plane code internally. + */ + if (crtc_req->x & 0xffff0000 || crtc_req->y & 0xffff0000) return -ERANGE; mutex_lock(&dev->mode_config.mutex); diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c index cf5dd63a95c3..b72eb507df64 100644 --- a/drivers/gpu/drm/radeon/radeon_combios.c +++ b/drivers/gpu/drm/radeon/radeon_combios.c @@ -1259,10 +1259,15 @@ struct radeon_encoder_lvds *radeon_combios_get_lvds_info(struct radeon_encoder if ((RBIOS16(tmp) == lvds->native_mode.hdisplay) && (RBIOS16(tmp + 2) == lvds->native_mode.vdisplay)) { + u32 hss = (RBIOS16(tmp + 21) - RBIOS16(tmp + 19) - 1) * 8; + + if (hss > lvds->native_mode.hdisplay) + hss = (10 - 1) * 8; + lvds->native_mode.htotal = lvds->native_mode.hdisplay + (RBIOS16(tmp + 17) - RBIOS16(tmp + 19)) * 8; lvds->native_mode.hsync_start = lvds->native_mode.hdisplay + - (RBIOS16(tmp + 21) - RBIOS16(tmp + 19) - 1) * 8; + hss; lvds->native_mode.hsync_end = lvds->native_mode.hsync_start + (RBIOS8(tmp + 23) * 8); diff --git a/drivers/input/touchscreen/usbtouchscreen.c b/drivers/input/touchscreen/usbtouchscreen.c index ce384a449a65..e57eaf8b23db 100644 --- a/drivers/input/touchscreen/usbtouchscreen.c +++ b/drivers/input/touchscreen/usbtouchscreen.c @@ -586,6 +586,9 @@ static int dmc_tsc10_init(struct usbtouch_usb *usbtouch) goto err_out; } + /* TSC-25 data sheet specifies a delay after the RESET command */ + msleep(150); + /* set coordinate output rate */ buf[0] = buf[1] = 0xFF; ret = usb_control_msg(dev, usb_rcvctrlpipe (dev, 0), diff --git a/drivers/isdn/i4l/isdn_ppp.c b/drivers/isdn/i4l/isdn_ppp.c index a1e760150821..7d6c170f5f68 100644 --- a/drivers/isdn/i4l/isdn_ppp.c +++ b/drivers/isdn/i4l/isdn_ppp.c @@ -301,6 +301,8 @@ isdn_ppp_open(int min, struct file *file) is->compflags = 0; is->reset = isdn_ppp_ccp_reset_alloc(is); + if (!is->reset) + return -ENOMEM; is->lp = NULL; is->mp_seqno = 0; /* MP sequence number */ @@ -320,6 +322,10 @@ isdn_ppp_open(int min, struct file *file) * VJ header compression init */ is->slcomp = slhc_init(16, 16); /* not necessary for 2. link in bundle */ + if (IS_ERR(is->slcomp)) { + isdn_ppp_ccp_reset_free(is); + return PTR_ERR(is->slcomp); + } #endif #ifdef CONFIG_IPPP_FILTER is->pass_filter = NULL; @@ -568,10 +574,8 @@ isdn_ppp_ioctl(int min, struct file *file, unsigned int cmd, unsigned long arg) is->maxcid = val; #ifdef CONFIG_ISDN_PPP_VJ sltmp = slhc_init(16, val); - if (!sltmp) { - printk(KERN_ERR "ippp, can't realloc slhc struct\n"); - return -ENOMEM; - } + if (IS_ERR(sltmp)) + return PTR_ERR(sltmp); if (is->slcomp) slhc_free(is->slcomp); is->slcomp = sltmp; diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index e811e44dfcf7..862612eebd63 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -13,6 +13,7 @@ #include #include #include +#include #define DM_MSG_PREFIX "thin" @@ -149,9 +150,7 @@ static struct bio_prison *prison_create(unsigned nr_cells) { unsigned i; uint32_t nr_buckets = calc_nr_buckets(nr_cells); - size_t len = sizeof(struct bio_prison) + - (sizeof(struct hlist_head) * nr_buckets); - struct bio_prison *prison = kmalloc(len, GFP_KERNEL); + struct bio_prison *prison = kmalloc(sizeof(*prison), GFP_KERNEL); if (!prison) return NULL; @@ -164,9 +163,15 @@ static struct bio_prison *prison_create(unsigned nr_cells) return NULL; } + prison->cells = vmalloc(sizeof(*prison->cells) * nr_buckets); + if (!prison->cells) { + mempool_destroy(prison->cell_pool); + kfree(prison); + return NULL; + } + prison->nr_buckets = nr_buckets; prison->hash_mask = nr_buckets - 1; - prison->cells = (struct hlist_head *) (prison + 1); for (i = 0; i < nr_buckets; i++) INIT_HLIST_HEAD(prison->cells + i); @@ -175,6 +180,7 @@ static struct bio_prison *prison_create(unsigned nr_cells) static void prison_destroy(struct bio_prison *prison) { + vfree(prison->cells); mempool_destroy(prison->cell_pool); kfree(prison); } diff --git a/drivers/md/md.c b/drivers/md/md.c index 83dba060525b..a875348e819e 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5120,16 +5120,30 @@ void md_stop_writes(struct mddev *mddev) } EXPORT_SYMBOL_GPL(md_stop_writes); -void md_stop(struct mddev *mddev) +static void __md_stop(struct mddev *mddev) { mddev->ready = 0; mddev->pers->stop(mddev); if (mddev->pers->sync_request && mddev->to_remove == NULL) mddev->to_remove = &md_redundancy_group; module_put(mddev->pers->owner); + /* Ensure ->event_work is done */ + flush_workqueue(md_misc_wq); mddev->pers = NULL; clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); } + +void md_stop(struct mddev *mddev) +{ + /* stop the array and free an attached data structures. + * This is called from dm-raid + */ + __md_stop(mddev); + bitmap_destroy(mddev); + if (mddev->bio_set) + bioset_free(mddev->bio_set); +} + EXPORT_SYMBOL_GPL(md_stop); static int md_set_readonly(struct mddev *mddev, struct block_device *bdev) @@ -5190,7 +5204,7 @@ static int do_md_stop(struct mddev * mddev, int mode, set_disk_ro(disk, 0); __md_stop_writes(mddev); - md_stop(mddev); + __md_stop(mddev); mddev->queue->merge_bvec_fn = NULL; mddev->queue->backing_dev_info.congested_fn = NULL; diff --git a/drivers/md/persistent-data/dm-btree-internal.h b/drivers/md/persistent-data/dm-btree-internal.h index accbb05f17b6..c2465785e44a 100644 --- a/drivers/md/persistent-data/dm-btree-internal.h +++ b/drivers/md/persistent-data/dm-btree-internal.h @@ -131,4 +131,10 @@ int lower_bound(struct btree_node *n, uint64_t key); extern struct dm_block_validator btree_node_validator; +/* + * Value type for upper levels of multi-level btrees. + */ +extern void init_le64_type(struct dm_transaction_manager *tm, + struct dm_btree_value_type *vt); + #endif /* DM_BTREE_INTERNAL_H */ diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c index b88757cd0d1d..92cd09f3c69b 100644 --- a/drivers/md/persistent-data/dm-btree-remove.c +++ b/drivers/md/persistent-data/dm-btree-remove.c @@ -301,35 +301,40 @@ static void redistribute3(struct dm_btree_info *info, struct btree_node *parent, { int s; uint32_t max_entries = le32_to_cpu(left->header.max_entries); - unsigned target = (nr_left + nr_center + nr_right) / 3; - BUG_ON(target > max_entries); + unsigned total = nr_left + nr_center + nr_right; + unsigned target_right = total / 3; + unsigned remainder = (target_right * 3) != total; + unsigned target_left = target_right + remainder; + + BUG_ON(target_left > max_entries); + BUG_ON(target_right > max_entries); if (nr_left < nr_right) { - s = nr_left - target; + s = nr_left - target_left; if (s < 0 && nr_center < -s) { /* not enough in central node */ - shift(left, center, nr_center); - s = nr_center - target; + shift(left, center, -nr_center); + s += nr_center; shift(left, right, s); nr_right += s; } else shift(left, center, s); - shift(center, right, target - nr_right); + shift(center, right, target_right - nr_right); } else { - s = target - nr_right; + s = target_right - nr_right; if (s > 0 && nr_center < s) { /* not enough in central node */ shift(center, right, nr_center); - s = target - nr_center; + s -= nr_center; shift(left, right, s); nr_left -= s; } else shift(center, right, s); - shift(left, center, nr_left - target); + shift(left, center, nr_left - target_left); } *key_ptr(parent, c->index) = center->keys[0]; @@ -544,14 +549,6 @@ static int remove_raw(struct shadow_spine *s, struct dm_btree_info *info, return r; } -static struct dm_btree_value_type le64_type = { - .context = NULL, - .size = sizeof(__le64), - .inc = NULL, - .dec = NULL, - .equal = NULL -}; - int dm_btree_remove(struct dm_btree_info *info, dm_block_t root, uint64_t *keys, dm_block_t *new_root) { @@ -559,12 +556,14 @@ int dm_btree_remove(struct dm_btree_info *info, dm_block_t root, int index = 0, r = 0; struct shadow_spine spine; struct btree_node *n; + struct dm_btree_value_type le64_vt; + init_le64_type(info->tm, &le64_vt); init_shadow_spine(&spine, info); for (level = 0; level < info->levels; level++) { r = remove_raw(&spine, info, (level == last_level ? - &info->value_type : &le64_type), + &info->value_type : &le64_vt), root, keys[level], (unsigned *)&index); if (r < 0) break; diff --git a/drivers/md/persistent-data/dm-btree-spine.c b/drivers/md/persistent-data/dm-btree-spine.c index 2f0805c3263e..f6cb762a3a17 100644 --- a/drivers/md/persistent-data/dm-btree-spine.c +++ b/drivers/md/persistent-data/dm-btree-spine.c @@ -242,3 +242,40 @@ int shadow_root(struct shadow_spine *s) { return s->root; } + +static void le64_inc(void *context, void *value_le) +{ + struct dm_transaction_manager *tm = context; + __le64 v_le; + + memcpy(&v_le, value_le, sizeof(v_le)); + dm_tm_inc(tm, le64_to_cpu(v_le)); +} + +static void le64_dec(void *context, void *value_le) +{ + struct dm_transaction_manager *tm = context; + __le64 v_le; + + memcpy(&v_le, value_le, sizeof(v_le)); + dm_tm_dec(tm, le64_to_cpu(v_le)); +} + +static int le64_equal(void *context, void *value1_le, void *value2_le) +{ + __le64 v1_le, v2_le; + + memcpy(&v1_le, value1_le, sizeof(v1_le)); + memcpy(&v2_le, value2_le, sizeof(v2_le)); + return v1_le == v2_le; +} + +void init_le64_type(struct dm_transaction_manager *tm, + struct dm_btree_value_type *vt) +{ + vt->context = tm; + vt->size = sizeof(__le64); + vt->inc = le64_inc; + vt->dec = le64_dec; + vt->equal = le64_equal; +} diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c index 371f3d49d18e..dddd5a47f97d 100644 --- a/drivers/md/persistent-data/dm-btree.c +++ b/drivers/md/persistent-data/dm-btree.c @@ -235,7 +235,7 @@ int dm_btree_del(struct dm_btree_info *info, dm_block_t root) int r; struct del_stack *s; - s = kmalloc(sizeof(*s), GFP_KERNEL); + s = kmalloc(sizeof(*s), GFP_NOIO); if (!s) return -ENOMEM; s->tm = info->tm; @@ -646,12 +646,7 @@ static int insert(struct dm_btree_info *info, dm_block_t root, struct btree_node *n; struct dm_btree_value_type le64_type; - le64_type.context = NULL; - le64_type.size = sizeof(__le64); - le64_type.inc = NULL; - le64_type.dec = NULL; - le64_type.equal = NULL; - + init_le64_type(info->tm, &le64_type); init_shadow_spine(&spine, info); for (level = 0; level < (info->levels - 1); level++) { diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 75e66c612505..189eedbc3027 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -314,7 +314,7 @@ static void raid1_end_read_request(struct bio *bio, int error) spin_lock_irqsave(&conf->device_lock, flags); if (r1_bio->mddev->degraded == conf->raid_disks || (r1_bio->mddev->degraded == conf->raid_disks-1 && - !test_bit(Faulty, &conf->mirrors[mirror].rdev->flags))) + test_bit(In_sync, &conf->mirrors[mirror].rdev->flags))) uptodate = 1; spin_unlock_irqrestore(&conf->device_lock, flags); } @@ -1250,6 +1250,7 @@ static void error(struct mddev *mddev, struct md_rdev *rdev) { char b[BDEVNAME_SIZE]; struct r1conf *conf = mddev->private; + unsigned long flags; /* * If it is not operational, then we have already marked it as dead @@ -1269,6 +1270,7 @@ static void error(struct mddev *mddev, struct md_rdev *rdev) return; } set_bit(Blocked, &rdev->flags); + spin_lock_irqsave(&conf->device_lock, flags); if (test_and_clear_bit(In_sync, &rdev->flags)) { unsigned long flags; spin_lock_irqsave(&conf->device_lock, flags); @@ -1281,6 +1283,7 @@ static void error(struct mddev *mddev, struct md_rdev *rdev) set_bit(MD_RECOVERY_INTR, &mddev->recovery); } else set_bit(Faulty, &rdev->flags); + spin_unlock_irqrestore(&conf->device_lock, flags); set_bit(MD_CHANGE_DEVS, &mddev->flags); printk(KERN_ALERT "md/raid1:%s: Disk failure on %s, disabling device.\n" @@ -1334,7 +1337,10 @@ static int raid1_spare_active(struct mddev *mddev) * Find all failed disks within the RAID1 configuration * and mark them readable. * Called under mddev lock, so rcu protection not needed. + * device_lock used to avoid races with raid1_end_read_request + * which expects 'In_sync' flags and ->degraded to be consistent. */ + spin_lock_irqsave(&conf->device_lock, flags); for (i = 0; i < conf->raid_disks; i++) { struct md_rdev *rdev = conf->mirrors[i].rdev; struct md_rdev *repl = conf->mirrors[conf->raid_disks + i].rdev; @@ -1364,7 +1370,6 @@ static int raid1_spare_active(struct mddev *mddev) sysfs_notify_dirent_safe(rdev->sysfs_state); } } - spin_lock_irqsave(&conf->device_lock, flags); mddev->degraded -= count; spin_unlock_irqrestore(&conf->device_lock, flags); diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index 47a789ea26bc..b4277ac6939f 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -182,6 +182,8 @@ static ssize_t power_ro_lock_show(struct device *dev, ret = snprintf(buf, PAGE_SIZE, "%d\n", locked); + mmc_blk_put(md); + return ret; } diff --git a/drivers/net/can/mcp251x.c b/drivers/net/can/mcp251x.c index 9d6074273caa..d07426d007d0 100644 --- a/drivers/net/can/mcp251x.c +++ b/drivers/net/can/mcp251x.c @@ -1161,18 +1161,17 @@ static int mcp251x_can_resume(struct spi_device *spi) struct mcp251x_platform_data *pdata = spi->dev.platform_data; struct mcp251x_priv *priv = dev_get_drvdata(&spi->dev); - if (priv->after_suspend & AFTER_SUSPEND_POWER) { + if (priv->after_suspend & AFTER_SUSPEND_POWER) pdata->power_enable(1); + + if (priv->after_suspend & AFTER_SUSPEND_UP) { + if (pdata->transceiver_enable) + pdata->transceiver_enable(1); queue_work(priv->wq, &priv->restart_work); } else { - if (priv->after_suspend & AFTER_SUSPEND_UP) { - if (pdata->transceiver_enable) - pdata->transceiver_enable(1); - queue_work(priv->wq, &priv->restart_work); - } else { - priv->after_suspend = 0; - } + priv->after_suspend = 0; } + priv->force_quit = 0; enable_irq(spi->irq); return 0; diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 8489d09494af..e475f8530862 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -6659,10 +6659,8 @@ static netdev_tx_t niu_start_xmit(struct sk_buff *skb, struct sk_buff *skb_new; skb_new = skb_realloc_headroom(skb, len); - if (!skb_new) { - rp->tx_errors++; + if (!skb_new) goto out_drop; - } kfree_skb(skb); skb = skb_new; } else diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 1207bb19ba58..ba4411b746a5 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -703,10 +703,8 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) val &= 0xffff; } vj = slhc_init(val2+1, val+1); - if (!vj) { - netdev_err(ppp->dev, - "PPP: no memory (VJ compressor)\n"); - err = -ENOMEM; + if (IS_ERR(vj)) { + err = PTR_ERR(vj); break; } ppp_lock(ppp); diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index 9f047a04215e..5a13ad0f2939 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -420,6 +420,9 @@ static int pptp_bind(struct socket *sock, struct sockaddr *uservaddr, struct pptp_opt *opt = &po->proto.pptp; int error = 0; + if (sockaddr_len < sizeof(struct sockaddr_pppox)) + return -EINVAL; + lock_sock(sk); opt->src_addr = sp->sa_addr.pptp; @@ -441,6 +444,9 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr, struct flowi4 fl4; int error = 0; + if (sockaddr_len < sizeof(struct sockaddr_pppox)) + return -EINVAL; + if (sp->sa_protocol != PX_PROTO_PPTP) return -EINVAL; diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c index 1252d9c726a7..b52eabc168a0 100644 --- a/drivers/net/slip/slhc.c +++ b/drivers/net/slip/slhc.c @@ -84,8 +84,9 @@ static long decode(unsigned char **cpp); static unsigned char * put16(unsigned char *cp, unsigned short x); static unsigned short pull16(unsigned char **cpp); -/* Initialize compression data structure +/* Allocate compression data structure * slots must be in range 0 to 255 (zero meaning no compression) + * Returns pointer to structure or ERR_PTR() on error. */ struct slcompress * slhc_init(int rslots, int tslots) @@ -94,11 +95,14 @@ slhc_init(int rslots, int tslots) register struct cstate *ts; struct slcompress *comp; + if (rslots < 0 || rslots > 255 || tslots < 0 || tslots > 255) + return ERR_PTR(-EINVAL); + comp = kzalloc(sizeof(struct slcompress), GFP_KERNEL); if (! comp) goto out_fail; - if ( rslots > 0 && rslots < 256 ) { + if (rslots > 0) { size_t rsize = rslots * sizeof(struct cstate); comp->rstate = kzalloc(rsize, GFP_KERNEL); if (! comp->rstate) @@ -106,7 +110,7 @@ slhc_init(int rslots, int tslots) comp->rslot_limit = rslots - 1; } - if ( tslots > 0 && tslots < 256 ) { + if (tslots > 0) { size_t tsize = tslots * sizeof(struct cstate); comp->tstate = kzalloc(tsize, GFP_KERNEL); if (! comp->tstate) @@ -141,7 +145,7 @@ out_free2: out_free: kfree(comp); out_fail: - return NULL; + return ERR_PTR(-ENOMEM); } diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c index d4c9db3da22a..1f22662648b5 100644 --- a/drivers/net/slip/slip.c +++ b/drivers/net/slip/slip.c @@ -163,7 +163,7 @@ static int sl_alloc_bufs(struct slip *sl, int mtu) if (cbuff == NULL) goto err_exit; slcomp = slhc_init(16, 16); - if (slcomp == NULL) + if (IS_ERR(slcomp)) goto err_exit; #endif spin_lock_bh(&sl->lock); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index efb50d6dfb6c..27c82eee537a 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1036,9 +1036,9 @@ static int virtnet_probe(struct virtio_device *vdev) /* Do we support "hardware" checksums? */ if (virtio_has_feature(vdev, VIRTIO_NET_F_CSUM)) { /* This opens up the world of extra features. */ - dev->hw_features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST; + dev->hw_features |= NETIF_F_HW_CSUM | NETIF_F_SG; if (csum) - dev->features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST; + dev->features |= NETIF_F_HW_CSUM | NETIF_F_SG; if (virtio_has_feature(vdev, VIRTIO_NET_F_GSO)) { dev->hw_features |= NETIF_F_TSO | NETIF_F_UFO diff --git a/drivers/scsi/libfc/fc_fcp.c b/drivers/scsi/libfc/fc_fcp.c index f7357308655a..c979fd02b515 100644 --- a/drivers/scsi/libfc/fc_fcp.c +++ b/drivers/scsi/libfc/fc_fcp.c @@ -1030,11 +1030,26 @@ restart: fc_fcp_pkt_hold(fsp); spin_unlock_irqrestore(&si->scsi_queue_lock, flags); - if (!fc_fcp_lock_pkt(fsp)) { + spin_lock_bh(&fsp->scsi_pkt_lock); + if (!(fsp->state & FC_SRB_COMPL)) { + fsp->state |= FC_SRB_COMPL; + /* + * TODO: dropping scsi_pkt_lock and then reacquiring + * again around fc_fcp_cleanup_cmd() is required, + * since fc_fcp_cleanup_cmd() calls into + * fc_seq_set_resp() and that func preempts cpu using + * schedule. May be schedule and related code should be + * removed instead of unlocking here to avoid scheduling + * while atomic bug. + */ + spin_unlock_bh(&fsp->scsi_pkt_lock); + fc_fcp_cleanup_cmd(fsp, error); + + spin_lock_bh(&fsp->scsi_pkt_lock); fc_io_compl(fsp); - fc_fcp_unlock_pkt(fsp); } + spin_unlock_bh(&fsp->scsi_pkt_lock); fc_fcp_pkt_release(fsp); spin_lock_irqsave(&si->scsi_queue_lock, flags); diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index 1243d2f5bffa..d9a898c5d242 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -2907,10 +2907,10 @@ void iscsi_conn_teardown(struct iscsi_cls_conn *cls_conn) { struct iscsi_conn *conn = cls_conn->dd_data; struct iscsi_session *session = conn->session; - unsigned long flags; del_timer_sync(&conn->transport_timer); + mutex_lock(&session->eh_mutex); spin_lock_bh(&session->lock); conn->c_stage = ISCSI_CONN_CLEANUP_WAIT; if (session->leadconn == conn) { @@ -2922,28 +2922,6 @@ void iscsi_conn_teardown(struct iscsi_cls_conn *cls_conn) } spin_unlock_bh(&session->lock); - /* - * Block until all in-progress commands for this connection - * time out or fail. - */ - for (;;) { - spin_lock_irqsave(session->host->host_lock, flags); - if (!session->host->host_busy) { /* OK for ERL == 0 */ - spin_unlock_irqrestore(session->host->host_lock, flags); - break; - } - spin_unlock_irqrestore(session->host->host_lock, flags); - msleep_interruptible(500); - iscsi_conn_printk(KERN_INFO, conn, "iscsi conn_destroy(): " - "host_busy %d host_failed %d\n", - session->host->host_busy, - session->host->host_failed); - /* - * force eh_abort() to unblock - */ - wake_up(&conn->ehwait); - } - /* flush queued up work because we free the connection below */ iscsi_suspend_tx(conn); @@ -2956,6 +2934,7 @@ void iscsi_conn_teardown(struct iscsi_cls_conn *cls_conn) if (session->leadconn == conn) session->leadconn = NULL; spin_unlock_bh(&session->lock); + mutex_unlock(&session->eh_mutex); iscsi_destroy_conn(cls_conn); } diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index fb119ce06ae5..ebe83f7f63e7 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1687,6 +1687,9 @@ static int sg_start_req(Sg_request *srp, unsigned char *cmd) md->from_user = 0; } + if (unlikely(iov_count > UIO_MAXIOV)) + return -EINVAL; + if (iov_count) { int len, size = sizeof(struct sg_iovec) * iov_count; struct iovec *iov; diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index e41998cb098e..a3eb263e0321 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -1268,9 +1268,9 @@ static int st_open(struct inode *inode, struct file *filp) err_out: normalize_buffer(STp->buffer); STp->in_use = 0; - scsi_tape_put(STp); if (resumed) scsi_autopm_put_device(STp->device); + scsi_tape_put(STp); mutex_unlock(&st_mutex); return retval; diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 56d02e071d7a..963f38312927 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -981,7 +981,7 @@ done: if (cmd->targ_xfer_tag == 0xFFFFFFFF) cmd->targ_xfer_tag = conn->sess->targ_xfer_tag++; spin_unlock_bh(&conn->sess->ttt_lock); - } else if (hdr->flags & ISCSI_FLAG_CMD_WRITE) + } else cmd->targ_xfer_tag = 0xFFFFFFFF; cmd->cmd_sn = hdr->cmdsn; cmd->exp_stat_sn = hdr->exp_statsn; @@ -4500,6 +4500,7 @@ int iscsit_release_sessions_for_tpg(struct iscsi_portal_group *tpg, int force) struct iscsi_session *sess; struct se_portal_group *se_tpg = &tpg->tpg_se_tpg; struct se_session *se_sess, *se_sess_tmp; + LIST_HEAD(free_list); int session_count = 0; spin_lock_bh(&se_tpg->session_lock); @@ -4521,14 +4522,17 @@ int iscsit_release_sessions_for_tpg(struct iscsi_portal_group *tpg, int force) } atomic_set(&sess->session_reinstatement, 1); spin_unlock(&sess->conn_lock); - spin_unlock_bh(&se_tpg->session_lock); - iscsit_free_session(sess); - spin_lock_bh(&se_tpg->session_lock); + list_move_tail(&se_sess->sess_list, &free_list); + } + spin_unlock_bh(&se_tpg->session_lock); + list_for_each_entry_safe(se_sess, se_sess_tmp, &free_list, sess_list) { + sess = (struct iscsi_session *)se_sess->fabric_sess_ptr; + + iscsit_free_session(sess); session_count++; } - spin_unlock_bh(&se_tpg->session_lock); pr_debug("Released %d iSCSI Session(s) from Target Portal" " Group: %hu\n", session_count, tpg->tpgt); diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index 194cafdac16a..97076015b41c 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -614,7 +614,6 @@ struct dwc3 { unsigned three_stage_setup:1; unsigned ep0_bounced:1; unsigned ep0_expect_in:1; - unsigned start_config_issued:1; unsigned setup_packet_pending:1; unsigned delayed_status:1; unsigned needs_fifo_resize:1; diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index a8714fd5ffe2..b6051f396015 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -442,7 +442,6 @@ static int dwc3_ep0_set_config(struct dwc3 *dwc, struct usb_ctrlrequest *ctrl) u32 cfg; int ret; - dwc->start_config_issued = false; cfg = le16_to_cpu(ctrl->wValue); switch (dwc->dev_state) { @@ -644,10 +643,6 @@ static void dwc3_ep0_xfer_complete(struct dwc3 *dwc, dev_vdbg(dwc->dev, "Status Phase\n"); dwc3_ep0_complete_req(dwc, event); break; - case USB_REQ_SET_INTERFACE: - dev_vdbg(dwc->dev, "USB_REQ_SET_INTERFACE\n"); - dwc->start_config_issued = false; - /* Fall through */ default: WARN(true, "UNKNOWN ep0state %d\n", dwc->ep0state); } diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index b43c6f90b25f..fba74f8a5b5a 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -359,24 +359,66 @@ static void dwc3_free_trb_pool(struct dwc3_ep *dep) dep->trb_pool_dma = 0; } +static int dwc3_gadget_set_xfer_resource(struct dwc3 *dwc, struct dwc3_ep *dep); + +/** + * dwc3_gadget_start_config - Configure EP resources + * @dwc: pointer to our controller context structure + * @dep: endpoint that is being enabled + * + * The assignment of transfer resources cannot perfectly follow the + * data book due to the fact that the controller driver does not have + * all knowledge of the configuration in advance. It is given this + * information piecemeal by the composite gadget framework after every + * SET_CONFIGURATION and SET_INTERFACE. Trying to follow the databook + * programming model in this scenario can cause errors. For two + * reasons: + * + * 1) The databook says to do DEPSTARTCFG for every SET_CONFIGURATION + * and SET_INTERFACE (8.1.5). This is incorrect in the scenario of + * multiple interfaces. + * + * 2) The databook does not mention doing more DEPXFERCFG for new + * endpoint on alt setting (8.1.6). + * + * The following simplified method is used instead: + * + * All hardware endpoints can be assigned a transfer resource and this + * setting will stay persistent until either a core reset or + * hibernation. So whenever we do a DEPSTARTCFG(0) we can go ahead and + * do DEPXFERCFG for every hardware endpoint as well. We are + * guaranteed that there are as many transfer resources as endpoints. + * + * This function is called for each endpoint when it is being enabled + * but is triggered only when called for EP0-out, which always happens + * first, and which should only happen in one of the above conditions. + */ static int dwc3_gadget_start_config(struct dwc3 *dwc, struct dwc3_ep *dep) { struct dwc3_gadget_ep_cmd_params params; u32 cmd; + int i; + int ret; + + if (dep->number) + return 0; memset(¶ms, 0x00, sizeof(params)); + cmd = DWC3_DEPCMD_DEPSTARTCFG; - if (dep->number != 1) { - cmd = DWC3_DEPCMD_DEPSTARTCFG; - /* XferRscIdx == 0 for ep0 and 2 for the remaining */ - if (dep->number > 1) { - if (dwc->start_config_issued) - return 0; - dwc->start_config_issued = true; - cmd |= DWC3_DEPCMD_PARAM(2); - } + ret = dwc3_send_gadget_ep_cmd(dwc, 0, cmd, ¶ms); + if (ret) + return ret; - return dwc3_send_gadget_ep_cmd(dwc, 0, cmd, ¶ms); + for (i = 0; i < DWC3_ENDPOINTS_NUM; i++) { + struct dwc3_ep *dep = dwc->eps[i]; + + if (!dep) + continue; + + ret = dwc3_gadget_set_xfer_resource(dwc, dep); + if (ret) + return ret; } return 0; @@ -471,10 +513,6 @@ static int __dwc3_gadget_ep_enable(struct dwc3_ep *dep, struct dwc3_trb *trb_st_hw; struct dwc3_trb *trb_link; - ret = dwc3_gadget_set_xfer_resource(dwc, dep); - if (ret) - return ret; - dep->desc = desc; dep->comp_desc = comp_desc; dep->type = usb_endpoint_type(desc); @@ -1375,8 +1413,6 @@ static int dwc3_gadget_start(struct usb_gadget *g, reg |= dwc->maximum_speed; dwc3_writel(dwc->regs, DWC3_DCFG, reg); - dwc->start_config_issued = false; - /* Start with SuperSpeed Default */ dwc3_gadget_ep0_desc.wMaxPacketSize = cpu_to_le16(512); @@ -1861,7 +1897,6 @@ static void dwc3_gadget_disconnect_interrupt(struct dwc3 *dwc) dwc3_stop_active_transfers(dwc); dwc3_disconnect_gadget(dwc); - dwc->start_config_issued = false; dwc->gadget.speed = USB_SPEED_UNKNOWN; dwc->setup_packet_pending = false; @@ -1949,7 +1984,6 @@ static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc) dwc3_stop_active_transfers(dwc); dwc3_clear_stall_all_ep(dwc); - dwc->start_config_issued = false; /* Reset device address to zero */ reg = dwc3_readl(dwc->regs, DWC3_DCFG); diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index a6d4393668f5..fbbb11d0f9bb 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -473,10 +473,13 @@ static void xhci_hub_report_link_state(struct xhci_hcd *xhci, u32 pls = status_reg & PORT_PLS_MASK; /* resume state is a xHCI internal state. - * Do not report it to usb core. + * Do not report it to usb core, instead, pretend to be U3, + * thus usb core knows it's not ready for transfer */ - if (pls == XDEV_RESUME) + if (pls == XDEV_RESUME) { + *status |= USB_SS_PORT_LS_U3; return; + } /* When the CAS bit is set then warm reset * should be performed on port @@ -1008,10 +1011,10 @@ int xhci_bus_suspend(struct usb_hcd *hcd) spin_lock_irqsave(&xhci->lock, flags); if (hcd->self.root_hub->do_remote_wakeup) { - if (bus_state->resuming_ports) { + if (bus_state->resuming_ports || /* USB2 */ + bus_state->port_remote_wakeup) { /* USB3 */ spin_unlock_irqrestore(&xhci->lock, flags); - xhci_dbg(xhci, "suspend failed because " - "a port is resuming\n"); + xhci_dbg(xhci, "suspend failed because a port is resuming\n"); return -EBUSY; } } diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index aa38b1ff45ae..048cc382a7a9 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -1420,10 +1420,10 @@ int xhci_endpoint_init(struct xhci_hcd *xhci, /* Attempt to use the ring cache */ if (virt_dev->num_rings_cached == 0) return -ENOMEM; + virt_dev->num_rings_cached--; virt_dev->eps[ep_index].new_ring = virt_dev->ring_cache[virt_dev->num_rings_cached]; virt_dev->ring_cache[virt_dev->num_rings_cached] = NULL; - virt_dev->num_rings_cached--; xhci_reinit_cached_ring(xhci, virt_dev->eps[ep_index].new_ring, 1, type); } diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 5e93425424f6..5623785a300c 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -85,7 +85,7 @@ dma_addr_t xhci_trb_virt_to_dma(struct xhci_segment *seg, return 0; /* offset in TRBs */ segment_offset = trb - seg->trbs; - if (segment_offset > TRBS_PER_SEGMENT) + if (segment_offset >= TRBS_PER_SEGMENT) return 0; return seg->dma + (segment_offset * sizeof(*trb)); } @@ -1667,6 +1667,9 @@ static void handle_port_status(struct xhci_hcd *xhci, usb_hcd_resume_root_hub(hcd); } + if (hcd->speed == HCD_USB3 && (temp & PORT_PLS_MASK) == XDEV_INACTIVE) + bus_state->port_remote_wakeup &= ~(1 << faked_port_index); + if ((temp & PORT_PLC) && (temp & PORT_PLS_MASK) == XDEV_RESUME) { xhci_dbg(xhci, "port resume event for port %d\n", port_id); diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index d96652d3fb54..fd52e1efd6ca 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -3368,6 +3368,9 @@ int xhci_discover_or_reset_device(struct usb_hcd *hcd, struct usb_device *udev) return -EINVAL; } + if (virt_dev->tt_info) + old_active_eps = virt_dev->tt_info->active_eps; + if (virt_dev->udev != udev) { /* If the virt_dev and the udev does not match, this virt_dev * may belong to another udev. diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 855f084a9a32..f4116fcd1cd8 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -280,6 +280,7 @@ struct xhci_op_regs { #define XDEV_U0 (0x0 << 5) #define XDEV_U2 (0x2 << 5) #define XDEV_U3 (0x3 << 5) +#define XDEV_INACTIVE (0x6 << 5) #define XDEV_RESUME (0xf << 5) /* true: port has power (see HCC_PPC) */ #define PORT_POWER (1 << 9) diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 29bf38309252..7a04e2c4e0af 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -193,6 +193,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x1FB9, 0x0602) }, /* Lake Shore Model 648 Magnet Power Supply */ { USB_DEVICE(0x1FB9, 0x0700) }, /* Lake Shore Model 737 VSM Controller */ { USB_DEVICE(0x1FB9, 0x0701) }, /* Lake Shore Model 776 Hall Matrix */ + { USB_DEVICE(0x2626, 0xEA60) }, /* Aruba Networks 7xxx USB Serial Console */ { USB_DEVICE(0x3195, 0xF190) }, /* Link Instruments MSO-19 */ { USB_DEVICE(0x3195, 0xF280) }, /* Link Instruments MSO-28 */ { USB_DEVICE(0x3195, 0xF281) }, /* Link Instruments MSO-28 */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index d8232df2c211..cb999af237dd 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1757,6 +1757,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d03, 0xff, 0x00, 0x00) }, { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */ { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */ + { USB_DEVICE_INTERFACE_CLASS(0x2020, 0x4000, 0xff) }, /* OLICARD300 - MT6225 */ { USB_DEVICE(INOVIA_VENDOR_ID, INOVIA_SEW858) }, { USB_DEVICE(VIATELECOM_VENDOR_ID, VIATELECOM_PRODUCT_CDS7) }, { } /* Terminating entry */ diff --git a/drivers/usb/serial/sierra.c b/drivers/usb/serial/sierra.c index e3ddec02f032..dd0ca846236e 100644 --- a/drivers/usb/serial/sierra.c +++ b/drivers/usb/serial/sierra.c @@ -303,6 +303,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x68AA, 0xFF, 0xFF, 0xFF), .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist }, + { USB_DEVICE(0x1199, 0x68AB) }, /* Sierra Wireless AR8550 */ /* AT&T Direct IP LTE modems */ { USB_DEVICE_AND_INTERFACE_INFO(0x0F3D, 0x68AA, 0xFF, 0xFF, 0xFF), .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist diff --git a/drivers/usb/serial/whiteheat.c b/drivers/usb/serial/whiteheat.c index bf7014d49a50..5cf9db1d5692 100644 --- a/drivers/usb/serial/whiteheat.c +++ b/drivers/usb/serial/whiteheat.c @@ -91,6 +91,8 @@ static int whiteheat_firmware_download(struct usb_serial *serial, static int whiteheat_firmware_attach(struct usb_serial *serial); /* function prototypes for the Connect Tech WhiteHEAT serial converter */ +static int whiteheat_probe(struct usb_serial *serial, + const struct usb_device_id *id); static int whiteheat_attach(struct usb_serial *serial); static void whiteheat_release(struct usb_serial *serial); static int whiteheat_open(struct tty_struct *tty, @@ -134,6 +136,7 @@ static struct usb_serial_driver whiteheat_device = { .description = "Connect Tech - WhiteHEAT", .id_table = id_table_std, .num_ports = 4, + .probe = whiteheat_probe, .attach = whiteheat_attach, .release = whiteheat_release, .open = whiteheat_open, @@ -336,6 +339,34 @@ static int whiteheat_firmware_attach(struct usb_serial *serial) /***************************************************************************** * Connect Tech's White Heat serial driver functions *****************************************************************************/ + +static int whiteheat_probe(struct usb_serial *serial, + const struct usb_device_id *id) +{ + struct usb_host_interface *iface_desc; + struct usb_endpoint_descriptor *endpoint; + size_t num_bulk_in = 0; + size_t num_bulk_out = 0; + size_t min_num_bulk; + unsigned int i; + + iface_desc = serial->interface->cur_altsetting; + + for (i = 0; i < iface_desc->desc.bNumEndpoints; i++) { + endpoint = &iface_desc->endpoint[i].desc; + if (usb_endpoint_is_bulk_in(endpoint)) + ++num_bulk_in; + if (usb_endpoint_is_bulk_out(endpoint)) + ++num_bulk_out; + } + + min_num_bulk = COMMAND_PORT + 1; + if (num_bulk_in < min_num_bulk || num_bulk_out < min_num_bulk) + return -ENODEV; + + return 0; +} + static int whiteheat_attach(struct usb_serial *serial) { struct usb_serial_port *command_port; diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index d0ecaf9ff415..61f93ea73f2c 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -2019,6 +2019,18 @@ UNUSUAL_DEV( 0x1908, 0x3335, 0x0200, 0x0200, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_NO_READ_DISC_INFO ), +/* Reported by Oliver Neukum + * This device morphes spontaneously into another device if the access + * pattern of Windows isn't followed. Thus writable media would be dirty + * if the initial instance is used. So the device is limited to its + * virtual CD. + * And yes, the concept that BCD goes up to 9 is not heeded */ +UNUSUAL_DEV( 0x19d2, 0x1225, 0x0000, 0xffff, + "ZTE,Incorporated", + "ZTE WCDMA Technologies MSM", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_SINGLE_LUN ), + /* Reported by Sven Geggus * This encrypted pen drive returns bogus data for the initial READ(10). */ diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index a50cb9c28f7d..8b2bac4c1c40 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -884,6 +884,7 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, unsigned long arg) } if (eventfp != d->log_file) { filep = d->log_file; + d->log_file = eventfp; ctx = d->log_ctx; d->log_ctx = eventfp ? eventfd_ctx_fileget(eventfp) : NULL; diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 014c8dd62962..c9b32dcf820d 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -540,8 +540,7 @@ static struct inode *v9fs_qid_iget(struct super_block *sb, unlock_new_inode(inode); return inode; error: - unlock_new_inode(inode); - iput(inode); + iget_failed(inode); return ERR_PTR(retval); } diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index a86a78d8e614..5cfbaddd3ec5 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -169,8 +169,7 @@ static struct inode *v9fs_qid_iget_dotl(struct super_block *sb, unlock_new_inode(inode); return inode; error: - unlock_new_inode(inode); - iput(inode); + iget_failed(inode); return ERR_PTR(retval); } diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index b1a1c929ba80..47abfd2b3c4c 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -283,7 +283,7 @@ void btrfs_unpin_free_ino(struct btrfs_root *root) __btrfs_add_free_space(ctl, info->offset, count); free: rb_erase(&info->offset_index, rbroot); - kfree(info); + kmem_cache_free(btrfs_free_space_cachep, info); } } diff --git a/fs/buffer.c b/fs/buffer.c index ed2dc709883a..e65a585eebc2 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -952,7 +952,7 @@ init_page_buffers(struct page *page, struct block_device *bdev, */ static int grow_dev_page(struct block_device *bdev, sector_t block, - pgoff_t index, int size, int sizebits) + pgoff_t index, int size, int sizebits, gfp_t gfp) { struct inode *inode = bdev->bd_inode; struct page *page; @@ -961,7 +961,7 @@ grow_dev_page(struct block_device *bdev, sector_t block, int ret = 0; /* Will call free_more_memory() */ page = find_or_create_page(inode->i_mapping, index, - (mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS)|__GFP_MOVABLE); + (mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS) | gfp); if (!page) return ret; @@ -1009,7 +1009,7 @@ failed: * that page was dirty, the buffers are set dirty also. */ static int -grow_buffers(struct block_device *bdev, sector_t block, int size) +grow_buffers(struct block_device *bdev, sector_t block, int size, gfp_t gfp) { pgoff_t index; int sizebits; @@ -1036,11 +1036,12 @@ grow_buffers(struct block_device *bdev, sector_t block, int size) } /* Create a page with the proper size buffers.. */ - return grow_dev_page(bdev, block, index, size, sizebits); + return grow_dev_page(bdev, block, index, size, sizebits, gfp); } -static struct buffer_head * -__getblk_slow(struct block_device *bdev, sector_t block, int size) +struct buffer_head * +__getblk_slow(struct block_device *bdev, sector_t block, + unsigned size, gfp_t gfp) { /* Size must be multiple of hard sectorsize */ if (unlikely(size & (bdev_logical_block_size(bdev)-1) || @@ -1062,13 +1063,14 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size) if (bh) return bh; - ret = grow_buffers(bdev, block, size); + ret = grow_buffers(bdev, block, size, gfp); if (ret < 0) return NULL; if (ret == 0) free_more_memory(); } } +EXPORT_SYMBOL(__getblk_slow); /* * The relationship between dirty buffers and dirty pages: @@ -1319,24 +1321,25 @@ __find_get_block(struct block_device *bdev, sector_t block, unsigned size) EXPORT_SYMBOL(__find_get_block); /* - * __getblk will locate (and, if necessary, create) the buffer_head + * __getblk_gfp() will locate (and, if necessary, create) the buffer_head * which corresponds to the passed block_device, block and size. The * returned buffer has its reference count incremented. * - * __getblk() will lock up the machine if grow_dev_page's try_to_free_buffers() - * attempt is failing. FIXME, perhaps? + * __getblk_gfp() will lock up the machine if grow_dev_page's + * try_to_free_buffers() attempt is failing. FIXME, perhaps? */ struct buffer_head * -__getblk(struct block_device *bdev, sector_t block, unsigned size) +__getblk_gfp(struct block_device *bdev, sector_t block, + unsigned size, gfp_t gfp) { struct buffer_head *bh = __find_get_block(bdev, block, size); might_sleep(); if (bh == NULL) - bh = __getblk_slow(bdev, block, size); + bh = __getblk_slow(bdev, block, size, gfp); return bh; } -EXPORT_SYMBOL(__getblk); +EXPORT_SYMBOL(__getblk_gfp); /* * Do async read-ahead on a buffer.. @@ -1352,24 +1355,28 @@ void __breadahead(struct block_device *bdev, sector_t block, unsigned size) EXPORT_SYMBOL(__breadahead); /** - * __bread() - reads a specified block and returns the bh + * __bread_gfp() - reads a specified block and returns the bh * @bdev: the block_device to read from * @block: number of block * @size: size (in bytes) to read - * + * @gfp: page allocation flag + * * Reads a specified block, and returns buffer head that contains it. + * The page cache can be allocated from non-movable area + * not to prevent page migration if you set gfp to zero. * It returns NULL if the block was unreadable. */ struct buffer_head * -__bread(struct block_device *bdev, sector_t block, unsigned size) +__bread_gfp(struct block_device *bdev, sector_t block, + unsigned size, gfp_t gfp) { - struct buffer_head *bh = __getblk(bdev, block, size); + struct buffer_head *bh = __getblk_gfp(bdev, block, size, gfp); if (likely(bh) && !buffer_uptodate(bh)) bh = __bread_slow(bh); return bh; } -EXPORT_SYMBOL(__bread); +EXPORT_SYMBOL(__bread_gfp); /* * invalidate_bh_lrus() is called rarely - but not only at unmount. diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index bbe09a975003..e05cb4c91a9b 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -699,7 +699,8 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block, path[ppos].p_depth = i; path[ppos].p_ext = NULL; - bh = sb_getblk(inode->i_sb, path[ppos].p_block); + bh = sb_getblk_gfp(inode->i_sb, path[ppos].p_block, + __GFP_MOVABLE | GFP_NOFS); if (unlikely(!bh)) { ret = -ENOMEM; goto err; @@ -904,7 +905,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, err = -EIO; goto cleanup; } - bh = sb_getblk(inode->i_sb, newblock); + bh = sb_getblk_gfp(inode->i_sb, newblock, __GFP_MOVABLE | GFP_NOFS); if (!bh) { err = -ENOMEM; goto cleanup; @@ -1088,7 +1089,7 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, if (newblock == 0) return err; - bh = sb_getblk(inode->i_sb, newblock); + bh = sb_getblk_gfp(inode->i_sb, newblock, __GFP_MOVABLE | GFP_NOFS); if (!bh) return -ENOMEM; lock_buffer(bh); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index cdfc763b313f..46e6562ae66e 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -4643,18 +4643,12 @@ do_more: /* * blocks being freed are metadata. these blocks shouldn't * be used until this transaction is committed + * + * We use __GFP_NOFAIL because ext4_free_blocks() is not allowed + * to fail. */ - retry: - new_entry = kmem_cache_alloc(ext4_free_data_cachep, GFP_NOFS); - if (!new_entry) { - /* - * We use a retry loop because - * ext4_free_blocks() is not allowed to fail. - */ - cond_resched(); - congestion_wait(BLK_RW_ASYNC, HZ/50); - goto retry; - } + new_entry = kmem_cache_alloc(ext4_free_data_cachep, + GFP_NOFS|__GFP_NOFAIL); new_entry->efd_start_cluster = bit; new_entry->efd_group = block_group; new_entry->efd_count = count_clusters; diff --git a/fs/file_table.c b/fs/file_table.c index 70f2a0fd6aec..a01710a6ff3b 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -34,9 +34,6 @@ struct files_stat_struct files_stat = { .max_files = NR_FILE }; -DECLARE_LGLOCK(files_lglock); -DEFINE_LGLOCK(files_lglock); - /* SLAB cache for file structures */ static struct kmem_cache *filp_cachep __read_mostly; @@ -129,7 +126,6 @@ struct file *get_empty_filp(void) if (security_file_alloc(f)) goto fail_sec; - INIT_LIST_HEAD(&f->f_u.fu_list); atomic_long_set(&f->f_count, 1); rwlock_init(&f->f_owner.lock); spin_lock_init(&f->f_lock); @@ -252,7 +248,6 @@ static void __fput(struct file *file) } fops_put(file->f_op); put_pid(file->f_owner.pid); - file_sb_list_del(file); if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) i_readcount_dec(inode); if (file->f_mode & FMODE_WRITE) @@ -382,134 +377,10 @@ void put_filp(struct file *file) { if (atomic_long_dec_and_test(&file->f_count)) { security_file_free(file); - file_sb_list_del(file); file_free(file); } } -static inline int file_list_cpu(struct file *file) -{ -#ifdef CONFIG_SMP - return file->f_sb_list_cpu; -#else - return smp_processor_id(); -#endif -} - -/* helper for file_sb_list_add to reduce ifdefs */ -static inline void __file_sb_list_add(struct file *file, struct super_block *sb) -{ - struct list_head *list; -#ifdef CONFIG_SMP - int cpu; - cpu = smp_processor_id(); - file->f_sb_list_cpu = cpu; - list = per_cpu_ptr(sb->s_files, cpu); -#else - list = &sb->s_files; -#endif - list_add(&file->f_u.fu_list, list); -} - -/** - * file_sb_list_add - add a file to the sb's file list - * @file: file to add - * @sb: sb to add it to - * - * Use this function to associate a file with the superblock of the inode it - * refers to. - */ -void file_sb_list_add(struct file *file, struct super_block *sb) -{ - lg_local_lock(files_lglock); - __file_sb_list_add(file, sb); - lg_local_unlock(files_lglock); -} - -/** - * file_sb_list_del - remove a file from the sb's file list - * @file: file to remove - * @sb: sb to remove it from - * - * Use this function to remove a file from its superblock. - */ -void file_sb_list_del(struct file *file) -{ - if (!list_empty(&file->f_u.fu_list)) { - lg_local_lock_cpu(files_lglock, file_list_cpu(file)); - list_del_init(&file->f_u.fu_list); - lg_local_unlock_cpu(files_lglock, file_list_cpu(file)); - } -} - -#ifdef CONFIG_SMP - -/* - * These macros iterate all files on all CPUs for a given superblock. - * files_lglock must be held globally. - */ -#define do_file_list_for_each_entry(__sb, __file) \ -{ \ - int i; \ - for_each_possible_cpu(i) { \ - struct list_head *list; \ - list = per_cpu_ptr((__sb)->s_files, i); \ - list_for_each_entry((__file), list, f_u.fu_list) - -#define while_file_list_for_each_entry \ - } \ -} - -#else - -#define do_file_list_for_each_entry(__sb, __file) \ -{ \ - struct list_head *list; \ - list = &(sb)->s_files; \ - list_for_each_entry((__file), list, f_u.fu_list) - -#define while_file_list_for_each_entry \ -} - -#endif - -/** - * mark_files_ro - mark all files read-only - * @sb: superblock in question - * - * All files are marked read-only. We don't care about pending - * delete files so this should be used in 'force' mode only. - */ -void mark_files_ro(struct super_block *sb) -{ - struct file *f; - -retry: - lg_global_lock(files_lglock); - do_file_list_for_each_entry(sb, f) { - struct vfsmount *mnt; - if (!S_ISREG(f->f_path.dentry->d_inode->i_mode)) - continue; - if (!file_count(f)) - continue; - if (!(f->f_mode & FMODE_WRITE)) - continue; - spin_lock(&f->f_lock); - f->f_mode &= ~FMODE_WRITE; - spin_unlock(&f->f_lock); - if (file_check_writeable(f) != 0) - continue; - file_release_write(f); - mnt = mntget(f->f_path.mnt); - /* This can sleep, so we can't hold the spinlock. */ - lg_global_unlock(files_lglock); - mnt_drop_write(mnt); - mntput(mnt); - goto retry; - } while_file_list_for_each_entry; - lg_global_unlock(files_lglock); -} - void __init files_init(unsigned long mempages) { unsigned long n; @@ -525,6 +396,5 @@ void __init files_init(unsigned long mempages) n = (mempages * (PAGE_SIZE / 1024)) / 10; files_stat.max_files = max_t(unsigned long, n, NR_FILE); files_defer_init(); - lg_lock_init(files_lglock); percpu_counter_init(&nr_files, 0); } diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c index 0bf578dbfce7..efc18237fbae 100644 --- a/fs/hpfs/super.c +++ b/fs/hpfs/super.c @@ -52,17 +52,20 @@ static void unmark_dirty(struct super_block *s) } /* Filesystem error... */ -static char err_buf[1024]; - void hpfs_error(struct super_block *s, const char *fmt, ...) { + struct va_format vaf; va_list args; va_start(args, fmt); - vsnprintf(err_buf, sizeof(err_buf), fmt, args); + + vaf.fmt = fmt; + vaf.va = &args; + + pr_err("filesystem error: %pV", &vaf); + va_end(args); - printk("HPFS: filesystem error: %s", err_buf); if (!hpfs_sb(s)->sb_was_error) { if (hpfs_sb(s)->sb_err == 2) { printk("; crashing the system because you wanted it\n"); @@ -385,9 +388,13 @@ static int hpfs_remount_fs(struct super_block *s, int *flags, char *data) int o; struct hpfs_sb_info *sbi = hpfs_sb(s); char *new_opts = kstrdup(data, GFP_KERNEL); - + + + if (!new_opts) + return -ENOMEM; + *flags |= MS_NOATIME; - + hpfs_lock(s); lock_super(s); uid = sbi->sb_uid; gid = sbi->sb_gid; diff --git a/fs/internal.h b/fs/internal.h index 9962c59ba280..ed005c5eef62 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -67,9 +67,6 @@ extern void chroot_fs_refs(struct path *, struct path *); /* * file_table.c */ -extern void file_sb_list_add(struct file *f, struct super_block *sb); -extern void file_sb_list_del(struct file *f); -extern void mark_files_ro(struct super_block *); extern struct file *get_empty_filp(void); /* diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 231eab2b2d07..b5e457ccfed2 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -3968,9 +3968,13 @@ static void ocfs2_downconvert_thread_do_work(struct ocfs2_super *osb) osb->dc_work_sequence = osb->dc_wake_sequence; processed = osb->blocked_lock_count; - while (processed) { - BUG_ON(list_empty(&osb->blocked_lock_list)); - + /* + * blocked lock processing in this loop might call iput which can + * remove items off osb->blocked_lock_list. Downconvert up to + * 'processed' number of locks, but stop short if we had some + * removed in ocfs2_mark_lockres_freeing when downconverting. + */ + while (processed && !list_empty(&osb->blocked_lock_list)) { lockres = list_entry(osb->blocked_lock_list.next, struct ocfs2_lock_res, l_blocked_list); list_del_init(&lockres->l_blocked_list); diff --git a/fs/open.c b/fs/open.c index cf1d34fc5e69..703b0512a714 100644 --- a/fs/open.c +++ b/fs/open.c @@ -672,7 +672,6 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt, f->f_path.dentry = dentry; f->f_path.mnt = mnt; f->f_pos = 0; - file_sb_list_add(f, inode->i_sb); if (unlikely(f->f_mode & FMODE_PATH)) { f->f_op = &empty_fops; @@ -730,7 +729,6 @@ cleanup_all: mnt_drop_write(mnt); } } - file_sb_list_del(f); f->f_path.dentry = NULL; f->f_path.mnt = NULL; cleanup_file: diff --git a/fs/super.c b/fs/super.c index d0154e52c76b..36fbe271fa41 100644 --- a/fs/super.c +++ b/fs/super.c @@ -122,22 +122,7 @@ static struct super_block *alloc_super(struct file_system_type *type) s = NULL; goto out; } -#ifdef CONFIG_SMP - s->s_files = alloc_percpu(struct list_head); - if (!s->s_files) { - security_sb_free(s); - kfree(s); - s = NULL; - goto out; - } else { - int i; - for_each_possible_cpu(i) - INIT_LIST_HEAD(per_cpu_ptr(s->s_files, i)); - } -#else - INIT_LIST_HEAD(&s->s_files); -#endif s->s_bdi = &default_backing_dev_info; INIT_HLIST_NODE(&s->s_instances); INIT_HLIST_BL_HEAD(&s->s_anon); @@ -200,9 +185,6 @@ out: */ static inline void destroy_super(struct super_block *s) { -#ifdef CONFIG_SMP - free_percpu(s->s_files); -#endif security_sb_free(s); WARN_ON(!list_empty(&s->s_mounts)); kfree(s->s_subtype); @@ -744,7 +726,8 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force) make sure there are no rw files opened */ if (remount_ro) { if (force) { - mark_files_ro(sb); + sb->s_readonly_remount = 1; + smp_wmb(); } else { retval = sb_prepare_remount_readonly(sb); if (retval) diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 458f497738a4..fed3f3ac489d 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -166,12 +166,13 @@ void __wait_on_buffer(struct buffer_head *); wait_queue_head_t *bh_waitq_head(struct buffer_head *bh); struct buffer_head *__find_get_block(struct block_device *bdev, sector_t block, unsigned size); -struct buffer_head *__getblk(struct block_device *bdev, sector_t block, - unsigned size); +struct buffer_head *__getblk_gfp(struct block_device *bdev, sector_t block, + unsigned size, gfp_t gfp); void __brelse(struct buffer_head *); void __bforget(struct buffer_head *); void __breadahead(struct block_device *, sector_t block, unsigned int size); -struct buffer_head *__bread(struct block_device *, sector_t block, unsigned size); +struct buffer_head *__bread_gfp(struct block_device *, + sector_t block, unsigned size, gfp_t gfp); void invalidate_bh_lrus(void); struct buffer_head *alloc_buffer_head(gfp_t gfp_flags); void free_buffer_head(struct buffer_head * bh); @@ -286,7 +287,13 @@ static inline void bforget(struct buffer_head *bh) static inline struct buffer_head * sb_bread(struct super_block *sb, sector_t block) { - return __bread(sb->s_bdev, block, sb->s_blocksize); + return __bread_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE); +} + +static inline struct buffer_head * +sb_bread_unmovable(struct super_block *sb, sector_t block) +{ + return __bread_gfp(sb->s_bdev, block, sb->s_blocksize, 0); } static inline void @@ -298,7 +305,14 @@ sb_breadahead(struct super_block *sb, sector_t block) static inline struct buffer_head * sb_getblk(struct super_block *sb, sector_t block) { - return __getblk(sb->s_bdev, block, sb->s_blocksize); + return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE); +} + + +static inline struct buffer_head * +sb_getblk_gfp(struct super_block *sb, sector_t block, gfp_t gfp) +{ + return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, gfp); } static inline struct buffer_head * @@ -335,6 +349,36 @@ static inline void lock_buffer(struct buffer_head *bh) __lock_buffer(bh); } +static inline struct buffer_head *getblk_unmovable(struct block_device *bdev, + sector_t block, + unsigned size) +{ + return __getblk_gfp(bdev, block, size, 0); +} + +static inline struct buffer_head *__getblk(struct block_device *bdev, + sector_t block, + unsigned size) +{ + return __getblk_gfp(bdev, block, size, __GFP_MOVABLE); +} + +/** + * __bread() - reads a specified block and returns the bh + * @bdev: the block_device to read from + * @block: number of block + * @size: size (in bytes) to read + * + * Reads a specified block, and returns buffer head that contains it. + * The page cache is allocated from movable area so that it can be migrated. + * It returns NULL if the block was unreadable. + */ +static inline struct buffer_head * +__bread(struct block_device *bdev, sector_t block, unsigned size) +{ + return __bread_gfp(bdev, block, size, __GFP_MOVABLE); +} + extern int __set_page_dirty_buffers(struct page *page); #else /* CONFIG_BLOCK */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 210c347425e8..e7bbe996ab49 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -976,12 +976,7 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) #define FILE_MNT_WRITE_RELEASED 2 struct file { - /* - * fu_list becomes invalid after file_free is called and queued via - * fu_rcuhead for RCU freeing - */ union { - struct list_head fu_list; struct rcu_head fu_rcuhead; } f_u; struct path f_path; @@ -994,9 +989,6 @@ struct file { * Must not be taken from IRQ context. */ spinlock_t f_lock; -#ifdef CONFIG_SMP - int f_sb_list_cpu; -#endif atomic_long_t f_count; unsigned int f_flags; fmode_t f_mode; @@ -1443,11 +1435,6 @@ struct super_block { struct list_head s_inodes; /* all inodes */ struct hlist_bl_head s_anon; /* anonymous dentries for (nfs) exporting */ -#ifdef CONFIG_SMP - struct list_head __percpu *s_files; -#else - struct list_head s_files; -#endif struct list_head s_mounts; /* list of mounts; _not_ for fs use */ /* s_dentry_lru, s_nr_dentry_unused protected by dcache.c lru locks */ struct list_head s_dentry_lru; /* unused dentry lru */ diff --git a/include/linux/libata.h b/include/linux/libata.h index 35e7f71cd8a5..9736dbe329e6 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -402,6 +402,8 @@ enum { ATA_HORKAGE_BROKEN_FPDMA_AA = (1 << 15), /* skip AA */ ATA_HORKAGE_DUMP_ID = (1 << 16), /* dump IDENTIFY data */ ATA_HORKAGE_MAX_SEC_LBA48 = (1 << 17), /* Set max sects to 65535 */ + ATA_HORKAGE_NOTRIM = (1 << 24), /* don't use TRIM */ + /* DMA mask for user DMA control: User visible values; DO NOT renumber */ diff --git a/include/net/af_unix.h b/include/net/af_unix.h index ca68e2cef230..d29a576e4a16 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -60,6 +60,7 @@ struct unix_sock { unsigned int gc_maybe_cycle : 1; unsigned char recursion_level; struct socket_wq peer_wq; + wait_queue_t peer_wake; }; #define unix_sk(__sk) ((struct unix_sock *)__sk) diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 0ae759a6c76e..49c4cfe810d2 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -266,7 +266,7 @@ extern void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info); extern void fib6_run_gc(unsigned long expires, - struct net *net); + struct net *net, bool force); extern void fib6_gc_cleanup(void); diff --git a/include/net/sock.h b/include/net/sock.h index f673ba5b6b1a..ddc3737b537e 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -329,6 +329,7 @@ struct sock { sk_userlocks : 4, sk_protocol : 8, sk_type : 16; +#define SK_PROTOCOL_MAX ((u8)~0U) kmemcheck_bitfield_end(flags); int sk_wmem_queued; gfp_t sk_allocation; diff --git a/include/sound/tlv.h b/include/sound/tlv.h index 7067e2dfb0b9..49e7bd68c153 100644 --- a/include/sound/tlv.h +++ b/include/sound/tlv.h @@ -38,21 +38,26 @@ #define SNDRV_CTL_TLVT_DB_MINMAX 4 /* dB scale with min/max */ #define SNDRV_CTL_TLVT_DB_MINMAX_MUTE 5 /* dB scale with min/max with mute */ +#define TLV_ITEM(type, ...) \ + (type), TLV_LENGTH(__VA_ARGS__), __VA_ARGS__ +#define TLV_LENGTH(...) \ + ((unsigned int)sizeof((const unsigned int[]) { __VA_ARGS__ })) + #define TLV_DB_SCALE_MASK 0xffff #define TLV_DB_SCALE_MUTE 0x10000 #define TLV_DB_SCALE_ITEM(min, step, mute) \ - SNDRV_CTL_TLVT_DB_SCALE, 2 * sizeof(unsigned int), \ - (min), ((step) & TLV_DB_SCALE_MASK) | ((mute) ? TLV_DB_SCALE_MUTE : 0) + TLV_ITEM(SNDRV_CTL_TLVT_DB_SCALE, \ + (min), \ + ((step) & TLV_DB_SCALE_MASK) | \ + ((mute) ? TLV_DB_SCALE_MUTE : 0)) #define DECLARE_TLV_DB_SCALE(name, min, step, mute) \ unsigned int name[] = { TLV_DB_SCALE_ITEM(min, step, mute) } /* dB scale specified with min/max values instead of step */ #define TLV_DB_MINMAX_ITEM(min_dB, max_dB) \ - SNDRV_CTL_TLVT_DB_MINMAX, 2 * sizeof(unsigned int), \ - (min_dB), (max_dB) + TLV_ITEM(SNDRV_CTL_TLVT_DB_MINMAX, (min_dB), (max_dB)) #define TLV_DB_MINMAX_MUTE_ITEM(min_dB, max_dB) \ - SNDRV_CTL_TLVT_DB_MINMAX_MUTE, 2 * sizeof(unsigned int), \ - (min_dB), (max_dB) + TLV_ITEM(SNDRV_CTL_TLVT_DB_MINMAX_MUTE, (min_dB), (max_dB)) #define DECLARE_TLV_DB_MINMAX(name, min_dB, max_dB) \ unsigned int name[] = { TLV_DB_MINMAX_ITEM(min_dB, max_dB) } #define DECLARE_TLV_DB_MINMAX_MUTE(name, min_dB, max_dB) \ @@ -60,13 +65,16 @@ /* linear volume between min_dB and max_dB (.01dB unit) */ #define TLV_DB_LINEAR_ITEM(min_dB, max_dB) \ - SNDRV_CTL_TLVT_DB_LINEAR, 2 * sizeof(unsigned int), \ - (min_dB), (max_dB) + TLV_ITEM(SNDRV_CTL_TLVT_DB_LINEAR, (min_dB), (max_dB)) #define DECLARE_TLV_DB_LINEAR(name, min_dB, max_dB) \ unsigned int name[] = { TLV_DB_LINEAR_ITEM(min_dB, max_dB) } /* dB range container */ /* Each item is: */ +#define TLV_DB_RANGE_ITEM(...) \ + TLV_ITEM(SNDRV_CTL_TLVT_DB_RANGE, __VA_ARGS__) +#define DECLARE_TLV_DB_RANGE(name, ...) \ + unsigned int name[] = { TLV_DB_RANGE_ITEM(__VA_ARGS__) } /* The below assumes that each item TLV is 4 words like DB_SCALE or LINEAR */ #define TLV_DB_RANGE_HEAD(num) \ SNDRV_CTL_TLVT_DB_RANGE, 6 * (num) * sizeof(unsigned int) diff --git a/ipc/msg.c b/ipc/msg.c index 25f1a6139584..391e3e0a44b5 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -198,6 +198,15 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params) return retval; } + msq->q_stime = msq->q_rtime = 0; + msq->q_ctime = get_seconds(); + msq->q_cbytes = msq->q_qnum = 0; + msq->q_qbytes = ns->msg_ctlmnb; + msq->q_lspid = msq->q_lrpid = 0; + INIT_LIST_HEAD(&msq->q_messages); + INIT_LIST_HEAD(&msq->q_receivers); + INIT_LIST_HEAD(&msq->q_senders); + /* * ipc_addid() locks msq */ @@ -208,15 +217,6 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params) return id; } - msq->q_stime = msq->q_rtime = 0; - msq->q_ctime = get_seconds(); - msq->q_cbytes = msq->q_qnum = 0; - msq->q_qbytes = ns->msg_ctlmnb; - msq->q_lspid = msq->q_lrpid = 0; - INIT_LIST_HEAD(&msq->q_messages); - INIT_LIST_HEAD(&msq->q_receivers); - INIT_LIST_HEAD(&msq->q_senders); - msg_unlock(msq); return msq->q_perm.id; diff --git a/ipc/sem.c b/ipc/sem.c index 5215a81420df..67f2110c8a80 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -1606,16 +1606,27 @@ void exit_sem(struct task_struct *tsk) rcu_read_lock(); un = list_entry_rcu(ulp->list_proc.next, struct sem_undo, list_proc); - if (&un->list_proc == &ulp->list_proc) - semid = -1; - else - semid = un->semid; + if (&un->list_proc == &ulp->list_proc) { + /* + * We must wait for freeary() before freeing this ulp, + * in case we raced with last sem_undo. There is a small + * possibility where we exit while freeary() didn't + * finish unlocking sem_undo_list. + */ + spin_unlock_wait(&ulp->lock); + rcu_read_unlock(); + break; + } + spin_lock(&ulp->lock); + semid = un->semid; + spin_unlock(&ulp->lock); rcu_read_unlock(); + /* exit_sem raced with IPC_RMID, nothing to do */ if (semid == -1) - break; + continue; - sma = sem_lock_check(tsk->nsproxy->ipc_ns, un->semid); + sma = sem_lock_check(tsk->nsproxy->ipc_ns, semid); /* exit_sem raced with IPC_RMID, nothing to do */ if (IS_ERR(sma)) diff --git a/ipc/shm.c b/ipc/shm.c index a02ef5781ce9..634b0ba15f49 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -500,12 +500,6 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) if (IS_ERR(file)) goto no_file; - id = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni); - if (id < 0) { - error = id; - goto no_id; - } - shp->shm_cprid = task_tgid_vnr(current); shp->shm_lprid = 0; shp->shm_atim = shp->shm_dtim = 0; @@ -514,6 +508,13 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) shp->shm_nattch = 0; shp->shm_file = file; shp->shm_creator = current; + + id = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni); + if (id < 0) { + error = id; + goto no_id; + } + /* * shmid gets reported as "inode#" in /proc/pid/maps. * proc-ps tools use this. Changing this will break them. diff --git a/ipc/util.c b/ipc/util.c index 75261a31d48d..e4c937703ade 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -264,6 +264,10 @@ int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size) rcu_read_lock(); spin_lock(&new->lock); + current_euid_egid(&euid, &egid); + new->cuid = new->uid = euid; + new->gid = new->cgid = egid; + err = idr_get_new(&ids->ipcs_idr, new, &id); if (err) { spin_unlock(&new->lock); @@ -273,10 +277,6 @@ int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size) ids->in_use++; - current_euid_egid(&euid, &egid); - new->cuid = new->uid = euid; - new->gid = new->cgid = egid; - new->seq = ids->seq++; if(ids->seq > ids->seq_max) ids->seq = 0; diff --git a/kernel/events/core.c b/kernel/events/core.c index 461b6e0007b1..2e6c24843eb6 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3863,12 +3863,20 @@ static const struct file_operations perf_fops = { * to user-space before waking everybody up. */ +static inline struct fasync_struct **perf_event_fasync(struct perf_event *event) +{ + /* only the parent has fasync state */ + if (event->parent) + event = event->parent; + return &event->fasync; +} + void perf_event_wakeup(struct perf_event *event) { ring_buffer_wakeup(event); if (event->pending_kill) { - kill_fasync(&event->fasync, SIGIO, event->pending_kill); + kill_fasync(perf_event_fasync(event), SIGIO, event->pending_kill); event->pending_kill = 0; } } @@ -4879,7 +4887,7 @@ static int __perf_event_overflow(struct perf_event *event, else perf_event_output(event, data, regs); - if (event->fasync && event->pending_kill) { + if (*perf_event_fasync(event) && event->pending_kill) { event->pending_wakeup = 1; irq_work_queue(&event->pending); } diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 991aa9381a44..8304c87cfcd9 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -154,14 +154,14 @@ void touch_all_softlockup_watchdogs(void) #ifdef CONFIG_HARDLOCKUP_DETECTOR void touch_nmi_watchdog(void) { - if (watchdog_enabled) { - unsigned cpu; - - for_each_present_cpu(cpu) { - if (per_cpu(watchdog_nmi_touch, cpu) != true) - per_cpu(watchdog_nmi_touch, cpu) = true; - } - } + /* + * Using __raw here because some code paths have + * preemption enabled. If preemption is enabled + * then interrupts should be enabled too, in which + * case we shouldn't have to worry about the watchdog + * going off. + */ + __raw_get_cpu_var(watchdog_nmi_touch) = true; touch_softlockup_watchdog(); } EXPORT_SYMBOL(touch_nmi_watchdog); diff --git a/mm/memory.c b/mm/memory.c index 02aef93416f2..4774579d8acb 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3173,6 +3173,14 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, pte_unmap(page_table); + /* File mapping without ->vm_ops ? */ + if (vma->vm_flags & VM_SHARED) + return VM_FAULT_SIGBUS; + + /* File mapping without ->vm_ops ? */ + if (vma->vm_flags & VM_SHARED) + return VM_FAULT_SIGBUS; + /* Check if we need to add a guard page to the stack */ if (check_stack_guard_page(vma, address) < 0) return VM_FAULT_SIGSEGV; @@ -3432,6 +3440,9 @@ static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma, - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; pte_unmap(page_table); + /* The VMA was not fully populated on mmap() or missing VM_DONTEXPAND */ + if (!vma->vm_ops->fault) + return VM_FAULT_SIGBUS; return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); } @@ -3490,11 +3501,9 @@ int handle_pte_fault(struct mm_struct *mm, entry = *pte; if (!pte_present(entry)) { if (pte_none(entry)) { - if (vma->vm_ops) { - if (likely(vma->vm_ops->fault)) - return do_linear_fault(mm, vma, address, + if (vma->vm_ops) + return do_linear_fault(mm, vma, address, pte, pmd, flags, entry); - } return do_anonymous_page(mm, vma, address, pte, pmd, flags); } diff --git a/net/atm/clip.c b/net/atm/clip.c index 8ae3a7879335..e55e664faca8 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -317,6 +317,9 @@ static int clip_constructor(struct neighbour *neigh) static int clip_encap(struct atm_vcc *vcc, int mode) { + if (!CLIP_VCC(vcc)) + return -EBADFD; + CLIP_VCC(vcc)->encap = mode; return 0; } diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index ca1820cf22f2..f59c8af13e57 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -811,6 +811,9 @@ static int ax25_create(struct net *net, struct socket *sock, int protocol, struct sock *sk; ax25_cb *ax25; + if (protocol < 0 || protocol > SK_PROTOCOL_MAX) + return -EINVAL; + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; diff --git a/net/core/datagram.c b/net/core/datagram.c index da7e0c867cc0..ba96ad93d136 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -127,6 +127,35 @@ out_noerr: goto out; } +static int skb_set_peeked(struct sk_buff *skb) +{ + struct sk_buff *nskb; + + if (skb->peeked) + return 0; + + /* We have to unshare an skb before modifying it. */ + if (!skb_shared(skb)) + goto done; + + nskb = skb_clone(skb, GFP_ATOMIC); + if (!nskb) + return -ENOMEM; + + skb->prev->next = nskb; + skb->next->prev = nskb; + nskb->prev = skb->prev; + nskb->next = skb->next; + + consume_skb(skb); + skb = nskb; + +done: + skb->peeked = 1; + + return 0; +} + /** * __skb_recv_datagram - Receive a datagram skbuff * @sk: socket @@ -161,7 +190,9 @@ out_noerr: struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags, int *peeked, int *off, int *err) { + struct sk_buff_head *queue = &sk->sk_receive_queue; struct sk_buff *skb; + unsigned long cpu_flags; long timeo; /* * Caller is allowed not to check sk->sk_err before skb_recv_datagram() @@ -180,8 +211,6 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags, * Look at current nfs client by the way... * However, this function was correct in any case. 8) */ - unsigned long cpu_flags; - struct sk_buff_head *queue = &sk->sk_receive_queue; spin_lock_irqsave(&queue->lock, cpu_flags); skb_queue_walk(queue, skb) { @@ -191,7 +220,11 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags, *off -= skb->len; continue; } - skb->peeked = 1; + + error = skb_set_peeked(skb); + if (error) + goto unlock_err; + atomic_inc(&skb->users); } else __skb_unlink(skb, queue); @@ -210,6 +243,8 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags, return NULL; +unlock_err: + spin_unlock_irqrestore(&queue->lock, cpu_flags); no_packet: *err = error; return NULL; diff --git a/net/core/dev.c b/net/core/dev.c index 901495216f85..4f679bf4f12e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2880,6 +2880,8 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, local_irq_save(flags); rps_lock(sd); + if (!netif_running(skb->dev)) + goto drop; if (skb_queue_len(&sd->input_pkt_queue) <= netdev_max_backlog) { if (skb_queue_len(&sd->input_pkt_queue)) { enqueue: @@ -2900,6 +2902,7 @@ enqueue: goto enqueue; } +drop: sd->dropped++; rps_unlock(sd); @@ -3188,8 +3191,6 @@ static int __netif_receive_skb(struct sk_buff *skb) pt_prev = NULL; - rcu_read_lock(); - another_round: __this_cpu_inc(softnet_data.processed); @@ -3284,7 +3285,6 @@ ncls: } out: - rcu_read_unlock(); return ret; } @@ -3305,29 +3305,30 @@ out: */ int netif_receive_skb(struct sk_buff *skb) { + int ret; + net_timestamp_check(netdev_tstamp_prequeue, skb); if (skb_defer_rx_timestamp(skb)) return NET_RX_SUCCESS; + rcu_read_lock(); + #ifdef CONFIG_RPS if (static_key_false(&rps_needed)) { struct rps_dev_flow voidflow, *rflow = &voidflow; - int cpu, ret; - - rcu_read_lock(); - - cpu = get_rps_cpu(skb->dev, skb, &rflow); + int cpu = get_rps_cpu(skb->dev, skb, &rflow); if (cpu >= 0) { ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); rcu_read_unlock(); return ret; } - rcu_read_unlock(); } #endif - return __netif_receive_skb(skb); + ret = __netif_receive_skb(skb); + rcu_read_unlock(); + return ret; } EXPORT_SYMBOL(netif_receive_skb); @@ -3718,8 +3719,10 @@ static int process_backlog(struct napi_struct *napi, int quota) unsigned int qlen; while ((skb = __skb_dequeue(&sd->process_queue))) { + rcu_read_lock(); local_irq_enable(); __netif_receive_skb(skb); + rcu_read_unlock(); local_irq_disable(); input_queue_head_incr(sd); if (++work >= quota) { @@ -5228,6 +5231,7 @@ static void rollback_registered_many(struct list_head *head) unlist_netdevice(dev); dev->reg_state = NETREG_UNREGISTERING; + on_each_cpu(flush_backlog, dev, 1); } synchronize_net(); @@ -5791,8 +5795,6 @@ void netdev_run_todo(void) dev->reg_state = NETREG_UNREGISTERED; - on_each_cpu(flush_backlog, dev, 1); - netdev_wait_allrefs(dev); /* paranoia */ diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 43c6dd8da602..8941e962a3f9 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1139,10 +1139,6 @@ static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { [IFLA_INFO_DATA] = { .type = NLA_NESTED }, }; -static const struct nla_policy ifla_vfinfo_policy[IFLA_VF_INFO_MAX+1] = { - [IFLA_VF_INFO] = { .type = NLA_NESTED }, -}; - static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = { [IFLA_VF_MAC] = { .len = sizeof(struct ifla_vf_mac) }, [IFLA_VF_VLAN] = { .len = sizeof(struct ifla_vf_vlan) }, @@ -1216,58 +1212,53 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[]) return 0; } -static int do_setvfinfo(struct net_device *dev, struct nlattr *attr) +static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) { - int rem, err = -EINVAL; - struct nlattr *vf; const struct net_device_ops *ops = dev->netdev_ops; + int err = -EINVAL; - nla_for_each_nested(vf, attr, rem) { - switch (nla_type(vf)) { - case IFLA_VF_MAC: { - struct ifla_vf_mac *ivm; - ivm = nla_data(vf); - err = -EOPNOTSUPP; - if (ops->ndo_set_vf_mac) - err = ops->ndo_set_vf_mac(dev, ivm->vf, - ivm->mac); - break; - } - case IFLA_VF_VLAN: { - struct ifla_vf_vlan *ivv; - ivv = nla_data(vf); - err = -EOPNOTSUPP; - if (ops->ndo_set_vf_vlan) - err = ops->ndo_set_vf_vlan(dev, ivv->vf, - ivv->vlan, - ivv->qos); - break; - } - case IFLA_VF_TX_RATE: { - struct ifla_vf_tx_rate *ivt; - ivt = nla_data(vf); - err = -EOPNOTSUPP; - if (ops->ndo_set_vf_tx_rate) - err = ops->ndo_set_vf_tx_rate(dev, ivt->vf, - ivt->rate); - break; - } - case IFLA_VF_SPOOFCHK: { - struct ifla_vf_spoofchk *ivs; - ivs = nla_data(vf); - err = -EOPNOTSUPP; - if (ops->ndo_set_vf_spoofchk) - err = ops->ndo_set_vf_spoofchk(dev, ivs->vf, - ivs->setting); - break; - } - default: - err = -EINVAL; - break; - } - if (err) - break; + if (tb[IFLA_VF_MAC]) { + struct ifla_vf_mac *ivm = nla_data(tb[IFLA_VF_MAC]); + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_mac) + err = ops->ndo_set_vf_mac(dev, ivm->vf, + ivm->mac); + if (err < 0) + return err; } + + if (tb[IFLA_VF_VLAN]) { + struct ifla_vf_vlan *ivv = nla_data(tb[IFLA_VF_VLAN]); + + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_vlan) + err = ops->ndo_set_vf_vlan(dev, ivv->vf, ivv->vlan, + ivv->qos); + if (err < 0) + return err; + } + + if (tb[IFLA_VF_TX_RATE]) { + struct ifla_vf_tx_rate *ivt = nla_data(tb[IFLA_VF_TX_RATE]); + + if (ops->ndo_set_vf_tx_rate) + err = ops->ndo_set_vf_tx_rate(dev, ivt->vf, + ivt->rate); + if (err < 0) + return err; + } + + if (tb[IFLA_VF_SPOOFCHK]) { + struct ifla_vf_spoofchk *ivs = nla_data(tb[IFLA_VF_SPOOFCHK]); + + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_spoofchk) + err = ops->ndo_set_vf_spoofchk(dev, ivs->vf, + ivs->setting); + if (err < 0) + return err; + } + return err; } @@ -1450,14 +1441,21 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, } if (tb[IFLA_VFINFO_LIST]) { + struct nlattr *vfinfo[IFLA_VF_MAX + 1]; struct nlattr *attr; int rem; + nla_for_each_nested(attr, tb[IFLA_VFINFO_LIST], rem) { - if (nla_type(attr) != IFLA_VF_INFO) { + if (nla_type(attr) != IFLA_VF_INFO || + nla_len(attr) < NLA_HDRLEN) { err = -EINVAL; goto errout; } - err = do_setvfinfo(dev, attr); + err = nla_parse_nested(vfinfo, IFLA_VF_MAX, attr, + ifla_vf_policy); + if (err < 0) + goto errout; + err = do_setvfinfo(dev, vfinfo); if (err < 0) goto errout; modified = 1; diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 77d1550b19fd..c04daddc4491 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -22,6 +22,8 @@ static int zero = 0; static int ushort_max = USHRT_MAX; +static int one = 1; + #ifdef CONFIG_RPS static int rps_sock_flow_sysctl(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -94,28 +96,32 @@ static struct ctl_table net_core_table[] = { .data = &sysctl_wmem_max, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "rmem_max", .data = &sysctl_rmem_max, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "wmem_default", .data = &sysctl_wmem_default, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "rmem_default", .data = &sysctl_rmem_default, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "dev_weight", diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 4136987d94da..4fa941ea4d64 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -680,6 +680,9 @@ static int dn_create(struct net *net, struct socket *sock, int protocol, { struct sock *sk; + if (protocol < 0 || protocol > SK_PROTOCOL_MAX) + return -EINVAL; + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 78ec298001c8..0a828e25b585 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -284,6 +284,9 @@ static int inet_create(struct net *net, struct socket *sock, int protocol, if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM) build_ehash_secret(); + if (protocol < 0 || protocol >= IPPROTO_MAX) + return -EINVAL; + sock->state = SS_UNCONNECTED; /* Look for the requested type/protocol pair. */ diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 4a40457d8d14..f4597939b9e9 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -384,7 +384,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) ihl = ip_hdrlen(skb); /* Determine the position of this fragment. */ - end = offset + skb->len - ihl; + end = offset + skb->len - skb_network_offset(skb) - ihl; err = -EINVAL; /* Is this the final fragment? */ @@ -414,7 +414,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) goto err; err = -ENOMEM; - if (pskb_pull(skb, ihl) == NULL) + if (!pskb_pull(skb, skb_network_offset(skb) + ihl)) goto err; err = pskb_trim_rcsum(skb, end - offset); @@ -637,6 +637,8 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, iph->frag_off = 0; iph->tot_len = htons(len); iph->tos |= ecn; + ip_send_check(iph); + IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS); qp->q.fragments = NULL; qp->q.fragments_tail = NULL; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 086c97327b9b..009e36d2ba95 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -27,6 +27,7 @@ #include static int zero; +static int one = 1; static int tcp_retr1_max = 255; static int ip_local_port_range_min[] = { 1, 1 }; static int ip_local_port_range_max[] = { 65535, 65535 }; @@ -486,14 +487,16 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_wmem, .maxlen = sizeof(sysctl_tcp_wmem), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "tcp_rmem", .data = &sysctl_tcp_rmem, .maxlen = sizeof(sysctl_tcp_rmem), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "tcp_app_win", @@ -700,7 +703,7 @@ static struct ctl_table ipv4_table[] = { .maxlen = sizeof(sysctl_udp_rmem_min), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero + .extra1 = &one }, { .procname = "udp_wmem_min", @@ -708,7 +711,7 @@ static struct ctl_table ipv4_table[] = { .maxlen = sizeof(sysctl_udp_wmem_min), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero + .extra1 = &one }, { } }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index be5876079a8e..b6c236bd2326 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4340,6 +4340,21 @@ int addrconf_sysctl_forward(ctl_table *ctl, int write, return ret; } +static +int addrconf_sysctl_mtu(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct inet6_dev *idev = ctl->extra1; + int min_mtu = IPV6_MIN_MTU; + struct ctl_table lctl; + + lctl = *ctl; + lctl.extra1 = &min_mtu; + lctl.extra2 = idev ? &idev->dev->mtu : NULL; + + return proc_dointvec_minmax(&lctl, write, buffer, lenp, ppos); +} + static void dev_disable_change(struct inet6_dev *idev) { if (!idev || !idev->dev) @@ -4449,7 +4464,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.mtu6, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = addrconf_sysctl_mtu, }, { .procname = "accept_ra", diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 8ed1b930e75f..5300ef35fd41 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -113,6 +113,9 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol, !inet_ehash_secret) build_ehash_secret(); + if (protocol < 0 || protocol >= IPPROTO_MAX) + return -EINVAL; + /* Look for the requested type/protocol pair. */ lookup_protocol: err = -ESOCKTNOSUPPORT; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 2cfcfb7efa91..fc5ce6e9dc6f 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1593,19 +1593,16 @@ static int fib6_age(struct rt6_info *rt, void *arg) static DEFINE_SPINLOCK(fib6_gc_lock); -void fib6_run_gc(unsigned long expires, struct net *net) +void fib6_run_gc(unsigned long expires, struct net *net, bool force) { - if (expires != ~0UL) { + if (force) { spin_lock_bh(&fib6_gc_lock); - gc_args.timeout = expires ? (int)expires : - net->ipv6.sysctl.ip6_rt_gc_interval; - } else { - if (!spin_trylock_bh(&fib6_gc_lock)) { - mod_timer(&net->ipv6.ip6_fib_timer, jiffies + HZ); - return; - } - gc_args.timeout = net->ipv6.sysctl.ip6_rt_gc_interval; + } else if (!spin_trylock_bh(&fib6_gc_lock)) { + mod_timer(&net->ipv6.ip6_fib_timer, jiffies + HZ); + return; } + gc_args.timeout = expires ? (int)expires : + net->ipv6.sysctl.ip6_rt_gc_interval; gc_args.more = icmp6_dst_gc(); @@ -1622,7 +1619,7 @@ void fib6_run_gc(unsigned long expires, struct net *net) static void fib6_gc_timer_cb(unsigned long arg) { - fib6_run_gc(0, (struct net *)arg); + fib6_run_gc(0, (struct net *)arg, true); } static int __net_init fib6_net_init(struct net *net) diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 5cc78e6930b5..e235b4c2b1be 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1737,11 +1737,11 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, switch (event) { case NETDEV_CHANGEADDR: neigh_changeaddr(&nd_tbl, dev); - fib6_run_gc(~0UL, net); + fib6_run_gc(0, net, false); break; case NETDEV_DOWN: neigh_ifdown(&nd_tbl, dev); - fib6_run_gc(~0UL, net); + fib6_run_gc(0, net, false); break; case NETDEV_NOTIFY_PEERS: ndisc_send_unsol_na(dev); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 23b33048ea98..7ab7f8a5ee4f 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -404,6 +404,24 @@ out: } #ifdef CONFIG_IPV6_ROUTER_PREF +struct __rt6_probe_work { + struct work_struct work; + struct in6_addr target; + struct net_device *dev; +}; + +static void rt6_probe_deferred(struct work_struct *w) +{ + struct in6_addr mcaddr; + struct __rt6_probe_work *work = + container_of(w, struct __rt6_probe_work, work); + + addrconf_addr_solict_mult(&work->target, &mcaddr); + ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL); + dev_put(work->dev); + kfree(w); +} + static void rt6_probe(struct rt6_info *rt) { struct neighbour *neigh; @@ -422,15 +440,22 @@ static void rt6_probe(struct rt6_info *rt) read_lock_bh(&neigh->lock); if (!(neigh->nud_state & NUD_VALID) && time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) { - struct in6_addr mcaddr; - struct in6_addr *target; + struct __rt6_probe_work *work; + + work = kmalloc(sizeof(*work), GFP_ATOMIC); + + if (work) + neigh->updated = jiffies; - neigh->updated = jiffies; read_unlock_bh(&neigh->lock); - target = (struct in6_addr *)&neigh->primary_key; - addrconf_addr_solict_mult(target, &mcaddr); - ndisc_send_ns(rt->dst.dev, NULL, target, &mcaddr, NULL); + if (work) { + INIT_WORK(&work->work, rt6_probe_deferred); + work->target = rt->rt6i_gateway; + dev_hold(rt->dst.dev); + work->dev = rt->dst.dev; + schedule_work(&work->work); + } } else { read_unlock_bh(&neigh->lock); } @@ -1220,7 +1245,7 @@ static int ip6_dst_gc(struct dst_ops *ops) goto out; net->ipv6.ip6_rt_gc_expire++; - fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net); + fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, entries > rt_max_size); net->ipv6.ip6_rt_last_gc = now; entries = dst_entries_get_slow(ops); if (entries < ops->gc_thresh) @@ -2815,7 +2840,7 @@ int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write, net = (struct net *)ctl->extra1; delay = net->ipv6.sysctl.flush_delay; proc_dointvec(ctl, write, buffer, lenp, ppos); - fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net); + fib6_run_gc(delay <= 0 ? 0 : (unsigned long)delay, net, delay > 0); return 0; } diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index 12218f705315..3eaf4fe85fd5 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -1106,6 +1106,9 @@ static int irda_create(struct net *net, struct socket *sock, int protocol, IRDA_DEBUG(2, "%s()\n", __func__); + if (protocol < 0 || protocol > SK_PROTOCOL_MAX) + return -EINVAL; + if (net != &init_net) return -EAFNOSUPPORT; diff --git a/net/key/af_key.c b/net/key/af_key.c index d5cd43920ccb..eb6ce3b8a8cb 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -220,7 +220,7 @@ static int pfkey_broadcast_one(struct sk_buff *skb, struct sk_buff **skb2, #define BROADCAST_ONE 1 #define BROADCAST_REGISTERED 2 #define BROADCAST_PROMISC_ONLY 4 -static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, +static int pfkey_broadcast(struct sk_buff *skb, int broadcast_flags, struct sock *one_sk, struct net *net) { @@ -246,7 +246,7 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, * socket. */ if (pfk->promisc) - pfkey_broadcast_one(skb, &skb2, allocation, sk); + pfkey_broadcast_one(skb, &skb2, GFP_ATOMIC, sk); /* the exact target will be processed later */ if (sk == one_sk) @@ -261,7 +261,7 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, continue; } - err2 = pfkey_broadcast_one(skb, &skb2, allocation, sk); + err2 = pfkey_broadcast_one(skb, &skb2, GFP_ATOMIC, sk); /* Error is cleare after succecful sending to at least one * registered KM */ @@ -271,7 +271,7 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, rcu_read_unlock(); if (one_sk != NULL) - err = pfkey_broadcast_one(skb, &skb2, allocation, one_sk); + err = pfkey_broadcast_one(skb, &skb2, GFP_KERNEL, one_sk); kfree_skb(skb2); kfree_skb(skb); @@ -294,7 +294,7 @@ static int pfkey_do_dump(struct pfkey_sock *pfk) hdr = (struct sadb_msg *) pfk->dump.skb->data; hdr->sadb_msg_seq = 0; hdr->sadb_msg_errno = rc; - pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE, + pfkey_broadcast(pfk->dump.skb, BROADCAST_ONE, &pfk->sk, sock_net(&pfk->sk)); pfk->dump.skb = NULL; } @@ -335,7 +335,7 @@ static int pfkey_error(const struct sadb_msg *orig, int err, struct sock *sk) hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); - pfkey_broadcast(skb, GFP_KERNEL, BROADCAST_ONE, sk, sock_net(sk)); + pfkey_broadcast(skb, BROADCAST_ONE, sk, sock_net(sk)); return 0; } @@ -1361,7 +1361,7 @@ static int pfkey_getspi(struct sock *sk, struct sk_buff *skb, const struct sadb_ xfrm_state_put(x); - pfkey_broadcast(resp_skb, GFP_KERNEL, BROADCAST_ONE, sk, net); + pfkey_broadcast(resp_skb, BROADCAST_ONE, sk, net); return 0; } @@ -1449,7 +1449,7 @@ static int key_notify_sa(struct xfrm_state *x, const struct km_event *c) hdr->sadb_msg_seq = c->seq; hdr->sadb_msg_pid = c->pid; - pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, xs_net(x)); + pfkey_broadcast(skb, BROADCAST_ALL, NULL, xs_net(x)); return 0; } @@ -1566,7 +1566,7 @@ static int pfkey_get(struct sock *sk, struct sk_buff *skb, const struct sadb_msg out_hdr->sadb_msg_reserved = 0; out_hdr->sadb_msg_seq = hdr->sadb_msg_seq; out_hdr->sadb_msg_pid = hdr->sadb_msg_pid; - pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ONE, sk, sock_net(sk)); + pfkey_broadcast(out_skb, BROADCAST_ONE, sk, sock_net(sk)); return 0; } @@ -1667,7 +1667,7 @@ static int pfkey_register(struct sock *sk, struct sk_buff *skb, const struct sad return -ENOBUFS; } - pfkey_broadcast(supp_skb, GFP_KERNEL, BROADCAST_REGISTERED, sk, sock_net(sk)); + pfkey_broadcast(supp_skb, BROADCAST_REGISTERED, sk, sock_net(sk)); return 0; } @@ -1686,7 +1686,7 @@ static int unicast_flush_resp(struct sock *sk, const struct sadb_msg *ihdr) hdr->sadb_msg_errno = (uint8_t) 0; hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); - return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ONE, sk, sock_net(sk)); + return pfkey_broadcast(skb, BROADCAST_ONE, sk, sock_net(sk)); } static int key_notify_sa_flush(const struct km_event *c) @@ -1707,7 +1707,7 @@ static int key_notify_sa_flush(const struct km_event *c) hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); hdr->sadb_msg_reserved = 0; - pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, c->net); + pfkey_broadcast(skb, BROADCAST_ALL, NULL, c->net); return 0; } @@ -1768,7 +1768,7 @@ static int dump_sa(struct xfrm_state *x, int count, void *ptr) out_hdr->sadb_msg_pid = pfk->dump.msg_pid; if (pfk->dump.skb) - pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE, + pfkey_broadcast(pfk->dump.skb, BROADCAST_ONE, &pfk->sk, sock_net(&pfk->sk)); pfk->dump.skb = out_skb; @@ -1829,7 +1829,7 @@ static int pfkey_promisc(struct sock *sk, struct sk_buff *skb, const struct sadb new_hdr->sadb_msg_errno = 0; } - pfkey_broadcast(skb, GFP_KERNEL, BROADCAST_ALL, NULL, sock_net(sk)); + pfkey_broadcast(skb, BROADCAST_ALL, NULL, sock_net(sk)); return 0; } @@ -2160,7 +2160,7 @@ static int key_notify_policy(struct xfrm_policy *xp, int dir, const struct km_ev out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_seq = c->seq; out_hdr->sadb_msg_pid = c->pid; - pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ALL, NULL, xp_net(xp)); + pfkey_broadcast(out_skb, BROADCAST_ALL, NULL, xp_net(xp)); return 0; } @@ -2386,7 +2386,7 @@ static int key_pol_get_resp(struct sock *sk, struct xfrm_policy *xp, const struc out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_seq = hdr->sadb_msg_seq; out_hdr->sadb_msg_pid = hdr->sadb_msg_pid; - pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ONE, sk, xp_net(xp)); + pfkey_broadcast(out_skb, BROADCAST_ONE, sk, xp_net(xp)); err = 0; out: @@ -2639,7 +2639,7 @@ static int dump_sp(struct xfrm_policy *xp, int dir, int count, void *ptr) out_hdr->sadb_msg_pid = pfk->dump.msg_pid; if (pfk->dump.skb) - pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE, + pfkey_broadcast(pfk->dump.skb, BROADCAST_ONE, &pfk->sk, sock_net(&pfk->sk)); pfk->dump.skb = out_skb; @@ -2690,7 +2690,7 @@ static int key_notify_policy_flush(const struct km_event *c) hdr->sadb_msg_satype = SADB_SATYPE_UNSPEC; hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); hdr->sadb_msg_reserved = 0; - pfkey_broadcast(skb_out, GFP_ATOMIC, BROADCAST_ALL, NULL, c->net); + pfkey_broadcast(skb_out, BROADCAST_ALL, NULL, c->net); return 0; } @@ -2756,7 +2756,7 @@ static int pfkey_process(struct sock *sk, struct sk_buff *skb, const struct sadb void *ext_hdrs[SADB_EXT_MAX]; int err; - pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL, + pfkey_broadcast(skb_clone(skb, GFP_KERNEL), BROADCAST_PROMISC_ONLY, NULL, sock_net(sk)); memset(ext_hdrs, 0, sizeof(ext_hdrs)); @@ -2962,7 +2962,7 @@ static int key_notify_sa_expire(struct xfrm_state *x, const struct km_event *c) out_hdr->sadb_msg_seq = 0; out_hdr->sadb_msg_pid = 0; - pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL, xs_net(x)); + pfkey_broadcast(out_skb, BROADCAST_REGISTERED, NULL, xs_net(x)); return 0; } @@ -3134,7 +3134,7 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_ctx->ctx_len); } - return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL, xs_net(x)); + return pfkey_broadcast(skb, BROADCAST_REGISTERED, NULL, xs_net(x)); } static struct xfrm_policy *pfkey_compile_policy(struct sock *sk, int opt, @@ -3332,7 +3332,7 @@ static int pfkey_send_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, n_port->sadb_x_nat_t_port_port = sport; n_port->sadb_x_nat_t_port_reserved = 0; - return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL, xs_net(x)); + return pfkey_broadcast(skb, BROADCAST_REGISTERED, NULL, xs_net(x)); } #ifdef CONFIG_NET_KEY_MIGRATE @@ -3524,7 +3524,7 @@ static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, } /* broadcast migrate message to sockets */ - pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, &init_net); + pfkey_broadcast(skb, BROADCAST_ALL, NULL, &init_net); return 0; diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index d5404cc0248d..fa4a68993858 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -700,6 +700,7 @@ void ieee80211_debugfs_remove_netdev(struct ieee80211_sub_if_data *sdata) debugfs_remove_recursive(sdata->debugfs.dir); sdata->debugfs.dir = NULL; + sdata->debugfs.subdir_stations = NULL; } void ieee80211_debugfs_rename_netdev(struct ieee80211_sub_if_data *sdata) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 9a171b2445b1..71935fc880cf 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -309,6 +309,21 @@ static void death_by_timeout(unsigned long ul_conntrack) nf_ct_put(ct); } +static inline bool +nf_ct_key_equal(struct nf_conntrack_tuple_hash *h, + const struct nf_conntrack_tuple *tuple, + u16 zone) +{ + struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); + + /* A conntrack can be recreated with the equal tuple, + * so we need to check that the conntrack is confirmed + */ + return nf_ct_tuple_equal(tuple, &h->tuple) && + nf_ct_zone(ct) == zone && + nf_ct_is_confirmed(ct); +} + /* * Warning : * - Caller must take a reference on returned object @@ -330,8 +345,7 @@ ____nf_conntrack_find(struct net *net, u16 zone, local_bh_disable(); begin: hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[bucket], hnnode) { - if (nf_ct_tuple_equal(tuple, &h->tuple) && - nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)) == zone) { + if (nf_ct_key_equal(h, tuple, zone)) { NF_CT_STAT_INC(net, found); local_bh_enable(); return h; @@ -378,8 +392,7 @@ begin: !atomic_inc_not_zero(&ct->ct_general.use))) h = NULL; else { - if (unlikely(!nf_ct_tuple_equal(tuple, &h->tuple) || - nf_ct_zone(ct) != zone)) { + if (unlikely(!nf_ct_key_equal(h, tuple, zone))) { nf_ct_put(ct); goto begin; } diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index e41ec849120a..6fedfb359b19 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -203,7 +203,8 @@ static inline int expect_clash(const struct nf_conntrack_expect *a, a->mask.src.u3.all[count] & b->mask.src.u3.all[count]; } - return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask); + return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask) && + nf_ct_zone(a->master) == nf_ct_zone(b->master); } static inline int expect_matches(const struct nf_conntrack_expect *a, diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index e8fdb172adbb..a985158d95d5 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -759,8 +759,10 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, } ibmr = rds_ib_alloc_fmr(rds_ibdev); - if (IS_ERR(ibmr)) + if (IS_ERR(ibmr)) { + rds_ib_dev_put(rds_ibdev); return ibmr; + } ret = rds_ib_map_fmr(rds_ibdev, ibmr, sg, nents); if (ret == 0) diff --git a/net/rds/info.c b/net/rds/info.c index 9a6b4f66187c..140a44a5f7b7 100644 --- a/net/rds/info.c +++ b/net/rds/info.c @@ -176,7 +176,7 @@ int rds_info_getsockopt(struct socket *sock, int optname, char __user *optval, /* check for all kinds of wrapping and the like */ start = (unsigned long)optval; - if (len < 0 || len + PAGE_SIZE - 1 < len || start + len < start) { + if (len < 0 || len > INT_MAX - PAGE_SIZE + 1 || start + len < start) { ret = -EINVAL; goto out; } diff --git a/net/rds/send.c b/net/rds/send.c index 88eace57dd6b..31c9fa464b11 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -955,11 +955,13 @@ int rds_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, release_sock(sk); } - /* racing with another thread binding seems ok here */ + lock_sock(sk); if (daddr == 0 || rs->rs_bound_addr == 0) { + release_sock(sk); ret = -ENOTCONN; /* XXX not a great errno */ goto out; } + release_sock(sk); /* size of rm including all sgs */ ret = rds_rm_size(msg, payload_len); diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 1ff51c9d18d5..5fa033ac59e5 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -682,7 +682,7 @@ static void sctp_cmd_transport_on(sctp_cmd_seq_t *cmds, * outstanding data and rely on the retransmission limit be reached * to shutdown the association. */ - if (t->asoc->state != SCTP_STATE_SHUTDOWN_PENDING) + if (t->asoc->state < SCTP_STATE_SHUTDOWN_PENDING) t->asoc->overall_error_count = 0; /* Clear the hb_sent flag to signal that we had a good diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index f1a63c1885dc..fe5728422667 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -66,6 +66,7 @@ static void xprt_init(struct rpc_xprt *xprt, struct net *net); static void xprt_request_init(struct rpc_task *, struct rpc_xprt *); static void xprt_connect_status(struct rpc_task *task); static int __xprt_get_cong(struct rpc_xprt *, struct rpc_task *); +static void __xprt_put_cong(struct rpc_xprt *, struct rpc_rqst *); static void xprt_destroy(struct rpc_xprt *xprt); static DEFINE_SPINLOCK(xprt_list_lock); @@ -269,6 +270,8 @@ int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task) } xprt_clear_locked(xprt); out_sleep: + if (req) + __xprt_put_cong(xprt, req); dprintk("RPC: %5u failed to lock transport %p\n", task->tk_pid, xprt); task->tk_timeout = 0; task->tk_status = -EAGAIN; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 09a84c9f2f59..de07f944e98a 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -306,6 +306,118 @@ found: return s; } +/* Support code for asymmetrically connected dgram sockets + * + * If a datagram socket is connected to a socket not itself connected + * to the first socket (eg, /dev/log), clients may only enqueue more + * messages if the present receive queue of the server socket is not + * "too large". This means there's a second writeability condition + * poll and sendmsg need to test. The dgram recv code will do a wake + * up on the peer_wait wait queue of a socket upon reception of a + * datagram which needs to be propagated to sleeping would-be writers + * since these might not have sent anything so far. This can't be + * accomplished via poll_wait because the lifetime of the server + * socket might be less than that of its clients if these break their + * association with it or if the server socket is closed while clients + * are still connected to it and there's no way to inform "a polling + * implementation" that it should let go of a certain wait queue + * + * In order to propagate a wake up, a wait_queue_t of the client + * socket is enqueued on the peer_wait queue of the server socket + * whose wake function does a wake_up on the ordinary client socket + * wait queue. This connection is established whenever a write (or + * poll for write) hit the flow control condition and broken when the + * association to the server socket is dissolved or after a wake up + * was relayed. + */ + +static int unix_dgram_peer_wake_relay(wait_queue_t *q, unsigned mode, int flags, + void *key) +{ + struct unix_sock *u; + wait_queue_head_t *u_sleep; + + u = container_of(q, struct unix_sock, peer_wake); + + __remove_wait_queue(&unix_sk(u->peer_wake.private)->peer_wait, + q); + u->peer_wake.private = NULL; + + /* relaying can only happen while the wq still exists */ + u_sleep = sk_sleep(&u->sk); + if (u_sleep) + wake_up_interruptible_poll(u_sleep, key); + + return 0; +} + +static int unix_dgram_peer_wake_connect(struct sock *sk, struct sock *other) +{ + struct unix_sock *u, *u_other; + int rc; + + u = unix_sk(sk); + u_other = unix_sk(other); + rc = 0; + spin_lock(&u_other->peer_wait.lock); + + if (!u->peer_wake.private) { + u->peer_wake.private = other; + __add_wait_queue(&u_other->peer_wait, &u->peer_wake); + + rc = 1; + } + + spin_unlock(&u_other->peer_wait.lock); + return rc; +} + +static void unix_dgram_peer_wake_disconnect(struct sock *sk, + struct sock *other) +{ + struct unix_sock *u, *u_other; + + u = unix_sk(sk); + u_other = unix_sk(other); + spin_lock(&u_other->peer_wait.lock); + + if (u->peer_wake.private == other) { + __remove_wait_queue(&u_other->peer_wait, &u->peer_wake); + u->peer_wake.private = NULL; + } + + spin_unlock(&u_other->peer_wait.lock); +} + +static void unix_dgram_peer_wake_disconnect_wakeup(struct sock *sk, + struct sock *other) +{ + unix_dgram_peer_wake_disconnect(sk, other); + wake_up_interruptible_poll(sk_sleep(sk), + POLLOUT | + POLLWRNORM | + POLLWRBAND); +} + +/* preconditions: + * - unix_peer(sk) == other + * - association is stable + */ +static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other) +{ + int connected; + + connected = unix_dgram_peer_wake_connect(sk, other); + + if (unix_recvq_full(other)) + return 1; + + if (connected) + unix_dgram_peer_wake_disconnect(sk, other); + + return 0; +} + static inline int unix_writable(struct sock *sk) { return (atomic_read(&sk->sk_wmem_alloc) << 2) <= sk->sk_sndbuf; @@ -410,6 +522,8 @@ static void unix_release_sock(struct sock *sk, int embrion) skpair->sk_state_change(skpair); sk_wake_async(skpair, SOCK_WAKE_WAITD, POLL_HUP); } + + unix_dgram_peer_wake_disconnect(sk, skpair); sock_put(skpair); /* It may now die */ unix_peer(sk) = NULL; } @@ -646,6 +760,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock) INIT_LIST_HEAD(&u->link); mutex_init(&u->readlock); /* single task reading lock */ init_waitqueue_head(&u->peer_wait); + init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay); unix_insert_socket(unix_sockets_unbound, sk); out: if (sk == NULL) @@ -1020,6 +1135,8 @@ restart: if (unix_peer(sk)) { struct sock *old_peer = unix_peer(sk); unix_peer(sk) = other; + unix_dgram_peer_wake_disconnect_wakeup(sk, old_peer); + unix_state_double_unlock(sk, other); if (other != old_peer) @@ -1459,6 +1576,7 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock, long timeo; struct scm_cookie tmp_scm; int max_level; + int sk_locked; if (NULL == siocb->scm) siocb->scm = &tmp_scm; @@ -1527,12 +1645,14 @@ restart: goto out_free; } + sk_locked = 0; unix_state_lock(other); +restart_locked: err = -EPERM; if (!unix_may_send(sk, other)) goto out_unlock; - if (sock_flag(other, SOCK_DEAD)) { + if (unlikely(sock_flag(other, SOCK_DEAD))) { /* * Check with 1003.1g - what should * datagram error @@ -1540,10 +1660,14 @@ restart: unix_state_unlock(other); sock_put(other); + if (!sk_locked) + unix_state_lock(sk); + err = 0; - unix_state_lock(sk); if (unix_peer(sk) == other) { unix_peer(sk) = NULL; + unix_dgram_peer_wake_disconnect_wakeup(sk, other); + unix_state_unlock(sk); unix_dgram_disconnected(sk, other); @@ -1569,21 +1693,43 @@ restart: goto out_unlock; } - if (unix_peer(other) != sk && unix_recvq_full(other)) { - if (!timeo) { - err = -EAGAIN; - goto out_unlock; + /* other == sk && unix_peer(other) != sk if + * - unix_peer(sk) == NULL, destination address bound to sk + * - unix_peer(sk) == sk by time of get but disconnected before lock + */ + if (other != sk && + unlikely(unix_peer(other) != sk && unix_recvq_full(other))) { + if (timeo) { + timeo = unix_wait_for_peer(other, timeo); + + err = sock_intr_errno(timeo); + if (signal_pending(current)) + goto out_free; + + goto restart; } - timeo = unix_wait_for_peer(other, timeo); + if (!sk_locked) { + unix_state_unlock(other); + unix_state_double_lock(sk, other); + } - err = sock_intr_errno(timeo); - if (signal_pending(current)) - goto out_free; + if (unix_peer(sk) != other || + unix_dgram_peer_wake_me(sk, other)) { + err = -EAGAIN; + sk_locked = 1; + goto out_unlock; + } - goto restart; + if (!sk_locked) { + sk_locked = 1; + goto restart_locked; + } } + if (unlikely(sk_locked)) + unix_state_unlock(sk); + if (sock_flag(other, SOCK_RCVTSTAMP)) __net_timestamp(skb); maybe_add_creds(skb, sock, other); @@ -1597,6 +1743,8 @@ restart: return len; out_unlock: + if (sk_locked) + unix_state_unlock(sk); unix_state_unlock(other); out_free: kfree_skb(skb); @@ -2229,14 +2377,16 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock, return mask; writable = unix_writable(sk); - other = unix_peer_get(sk); - if (other) { - if (unix_peer(other) != sk) { - sock_poll_wait(file, &unix_sk(other)->peer_wait, wait); - if (unix_recvq_full(other)) - writable = 0; - } - sock_put(other); + if (writable) { + unix_state_lock(sk); + + other = unix_peer(sk); + if (other && unix_peer(other) != sk && + unix_recvq_full(other) && + unix_dgram_peer_wake_me(sk, other)) + writable = 0; + + unix_state_unlock(sk); } if (writable) diff --git a/scripts/kconfig/streamline_config.pl b/scripts/kconfig/streamline_config.pl index 3346f4236ebe..4a19a7f3bfde 100644 --- a/scripts/kconfig/streamline_config.pl +++ b/scripts/kconfig/streamline_config.pl @@ -125,7 +125,7 @@ my $ksource = $ARGV[0]; my $kconfig = $ARGV[1]; my $lsmod_file = $ENV{'LSMOD'}; -my @makefiles = `find $ksource -name Makefile 2>/dev/null`; +my @makefiles = `find $ksource -name Makefile -or -name Kbuild 2>/dev/null`; chomp @makefiles; my %depends; diff --git a/security/keys/gc.c b/security/keys/gc.c index 87632bd17b3e..9e496adfa3db 100644 --- a/security/keys/gc.c +++ b/security/keys/gc.c @@ -174,6 +174,12 @@ static noinline void key_gc_unused_key(struct key *key) { key_check(key); + /* Throw away the key data if the key is instantiated */ + if (test_bit(KEY_FLAG_INSTANTIATED, &key->flags) && + !test_bit(KEY_FLAG_NEGATIVE, &key->flags) && + key->type->destroy) + key->type->destroy(key); + security_key_free(key); /* deal with the user's key tracking and quota */ @@ -188,10 +194,6 @@ static noinline void key_gc_unused_key(struct key *key) if (test_bit(KEY_FLAG_INSTANTIATED, &key->flags)) atomic_dec(&key->user->nikeys); - /* now throw away the key memory */ - if (key->type->destroy) - key->type->destroy(key); - key_user_put(key->user); kfree(key->description); diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index c419aa30d544..67a827df2cde 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -1211,6 +1211,8 @@ static void build_feature_ctl(struct mixer_build *state, void *raw_desc, break; } + snd_usb_mixer_fu_apply_quirk(state->mixer, cval, unitid, kctl); + range = (cval->max - cval->min) / cval->res; /* Are there devices with volume range more than 255? I use a bit more * to be sure. 384 is a resolution magic number found on Logitech diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c index 851786ffa639..cb980407a3f0 100644 --- a/sound/usb/mixer_maps.c +++ b/sound/usb/mixer_maps.c @@ -312,6 +312,13 @@ static const struct usbmix_name_map scms_usb3318_map[] = { { 0 } }; +/* Bose companion 5, the dB conversion factor is 16 instead of 256 */ +static struct usbmix_dB_map bose_companion5_dB = {-5006, -6}; +static struct usbmix_name_map bose_companion5_map[] = { + { 3, NULL, .dB = &bose_companion5_dB }, + { 0 } /* terminator */ +}; + /* * Control map entries */ @@ -394,6 +401,11 @@ static struct usbmix_ctl_map usbmix_ctl_maps[] = { .id = USB_ID(0x25c4, 0x0003), .map = scms_usb3318_map, }, + { + /* Bose Companion 5 */ + .id = USB_ID(0x05a7, 0x1020), + .map = bose_companion5_map, + }, { 0 } /* terminator */ }; diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index 040d1016fb20..21f4d448b242 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -34,6 +34,7 @@ #include #include #include +#include #include "usbaudio.h" #include "mixer.h" @@ -682,3 +683,39 @@ void snd_usb_mixer_rc_memory_change(struct usb_mixer_interface *mixer, } } +static void snd_dragonfly_quirk_db_scale(struct usb_mixer_interface *mixer, + struct snd_kcontrol *kctl) +{ + /* Approximation using 10 ranges based on output measurement on hw v1.2. + * This seems close to the cubic mapping e.g. alsamixer uses. */ + static const DECLARE_TLV_DB_RANGE(scale, + 0, 1, TLV_DB_MINMAX_ITEM(-5300, -4970), + 2, 5, TLV_DB_MINMAX_ITEM(-4710, -4160), + 6, 7, TLV_DB_MINMAX_ITEM(-3884, -3710), + 8, 14, TLV_DB_MINMAX_ITEM(-3443, -2560), + 15, 16, TLV_DB_MINMAX_ITEM(-2475, -2324), + 17, 19, TLV_DB_MINMAX_ITEM(-2228, -2031), + 20, 26, TLV_DB_MINMAX_ITEM(-1910, -1393), + 27, 31, TLV_DB_MINMAX_ITEM(-1322, -1032), + 32, 40, TLV_DB_MINMAX_ITEM(-968, -490), + 41, 50, TLV_DB_MINMAX_ITEM(-441, 0), + ); + + dev_info(&mixer->chip->dev->dev, "applying DragonFly dB scale quirk\n"); + kctl->tlv.p = scale; + kctl->vd[0].access |= SNDRV_CTL_ELEM_ACCESS_TLV_READ; + kctl->vd[0].access &= ~SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK; +} + +void snd_usb_mixer_fu_apply_quirk(struct usb_mixer_interface *mixer, + struct usb_mixer_elem_info *cval, int unitid, + struct snd_kcontrol *kctl) +{ + switch (mixer->chip->usb_id) { + case USB_ID(0x21b4, 0x0081): /* AudioQuest DragonFly */ + if (unitid == 7 && cval->min == 0 && cval->max == 50) + snd_dragonfly_quirk_db_scale(mixer, kctl); + break; + } +} + diff --git a/sound/usb/mixer_quirks.h b/sound/usb/mixer_quirks.h index bdbfab093816..177c329cd4dd 100644 --- a/sound/usb/mixer_quirks.h +++ b/sound/usb/mixer_quirks.h @@ -9,5 +9,9 @@ void snd_emuusb_set_samplerate(struct snd_usb_audio *chip, void snd_usb_mixer_rc_memory_change(struct usb_mixer_interface *mixer, int unitid); +void snd_usb_mixer_fu_apply_quirk(struct usb_mixer_interface *mixer, + struct usb_mixer_elem_info *cval, int unitid, + struct snd_kcontrol *kctl); + #endif /* SND_USB_MIXER_QUIRKS_H */ diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index 2ad5d772cd92..4cebbf7f6ad1 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -2461,6 +2461,74 @@ YAMAHA_DEVICE(0x7010, "UB99"), } }, +/* Steinberg devices */ +{ + /* Steinberg MI2 */ + USB_DEVICE_VENDOR_SPEC(0x0a4e, 0x2040), + .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_COMPOSITE, + .data = & (const struct snd_usb_audio_quirk[]) { + { + .ifnum = 0, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 1, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 2, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 3, + .type = QUIRK_MIDI_FIXED_ENDPOINT, + .data = &(const struct snd_usb_midi_endpoint_info) { + .out_cables = 0x0001, + .in_cables = 0x0001 + } + }, + { + .ifnum = -1 + } + } + } +}, +{ + /* Steinberg MI4 */ + USB_DEVICE_VENDOR_SPEC(0x0a4e, 0x4040), + .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_COMPOSITE, + .data = & (const struct snd_usb_audio_quirk[]) { + { + .ifnum = 0, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 1, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 2, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 3, + .type = QUIRK_MIDI_FIXED_ENDPOINT, + .data = &(const struct snd_usb_midi_endpoint_info) { + .out_cables = 0x0001, + .in_cables = 0x0001 + } + }, + { + .ifnum = -1 + } + } + } +}, + /* TerraTec devices */ { USB_DEVICE_VENDOR_SPEC(0x0ccd, 0x0012),