lkml.org 
[lkml]   [2017]   [Oct]   [5]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
SubjectRe: Linux 4.9.53
diff --git a/Makefile b/Makefile
index c53de1e38c6a..98e3be659b21 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
VERSION = 4
PATCHLEVEL = 9
-SUBLEVEL = 52
+SUBLEVEL = 53
EXTRAVERSION =
NAME = Roaring Lionus

diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index d062f08f5020..4b24964a520a 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -199,6 +199,7 @@ static struct dma_map_ops xen_swiotlb_dma_ops = {
.unmap_page = xen_swiotlb_unmap_page,
.dma_supported = xen_swiotlb_dma_supported,
.set_dma_mask = xen_swiotlb_set_dma_mask,
+ .mmap = xen_swiotlb_dma_mmap,
};

int __init xen_mm_init(void)
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 332e33193ccf..539bebc1222f 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -486,6 +486,7 @@ ENTRY(kimage_vaddr)
* booted in EL1 or EL2 respectively.
*/
ENTRY(el2_setup)
+ msr SPsel, #1 // We want to use SP_EL{1,2}
mrs x0, CurrentEL
cmp x0, #CurrentEL_EL2
b.ne 1f
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index fec5b1ce97f8..403fe9e57135 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -509,7 +509,7 @@ static const struct fault_info fault_info[] = {
{ do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 0 translation fault" },
{ do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 1 translation fault" },
{ do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 2 translation fault" },
- { do_page_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" },
+ { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" },
{ do_bad, SIGBUS, 0, "unknown 8" },
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" },
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" },
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 767ef6d68c9e..caa659671599 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -1235,10 +1235,14 @@ _GLOBAL(ftrace_caller)
stdu r1,-SWITCH_FRAME_SIZE(r1)

/* Save all gprs to pt_regs */
- SAVE_8GPRS(0,r1)
- SAVE_8GPRS(8,r1)
- SAVE_8GPRS(16,r1)
- SAVE_8GPRS(24,r1)
+ SAVE_GPR(0, r1)
+ SAVE_10GPRS(2, r1)
+ SAVE_10GPRS(12, r1)
+ SAVE_10GPRS(22, r1)
+
+ /* Save previous stack pointer (r1) */
+ addi r8, r1, SWITCH_FRAME_SIZE
+ std r8, GPR1(r1)

/* Load special regs for save below */
mfmsr r8
@@ -1292,10 +1296,10 @@ ftrace_call:
#endif

/* Restore gprs */
- REST_8GPRS(0,r1)
- REST_8GPRS(8,r1)
- REST_8GPRS(16,r1)
- REST_8GPRS(24,r1)
+ REST_GPR(0,r1)
+ REST_10GPRS(2,r1)
+ REST_10GPRS(12,r1)
+ REST_10GPRS(22,r1)

/* Restore callee's TOC */
ld r2, 24(r1)
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index dcbb9144c16d..d97370866a5f 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -131,7 +131,7 @@ static void flush_tmregs_to_thread(struct task_struct *tsk)
* in the appropriate thread structures from live.
*/

- if (tsk != current)
+ if ((!cpu_has_feature(CPU_FTR_TM)) || (tsk != current))
return;

if (MSR_TM_SUSPENDED(mfmsr())) {
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index c379ff5a4438..da2a7eccb10a 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -129,8 +129,11 @@ static int kvm_spapr_tce_mmap(struct file *file, struct vm_area_struct *vma)
static int kvm_spapr_tce_release(struct inode *inode, struct file *filp)
{
struct kvmppc_spapr_tce_table *stt = filp->private_data;
+ struct kvm *kvm = stt->kvm;

+ mutex_lock(&kvm->lock);
list_del_rcu(&stt->list);
+ mutex_unlock(&kvm->lock);

kvm_put_kvm(stt->kvm);

@@ -150,6 +153,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
struct kvm_create_spapr_tce_64 *args)
{
struct kvmppc_spapr_tce_table *stt = NULL;
+ struct kvmppc_spapr_tce_table *siter;
unsigned long npages, size;
int ret = -ENOMEM;
int i;
@@ -157,24 +161,16 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
if (!args->size)
return -EINVAL;

- /* Check this LIOBN hasn't been previously allocated */
- list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
- if (stt->liobn == args->liobn)
- return -EBUSY;
- }
-
size = args->size;
npages = kvmppc_tce_pages(size);
ret = kvmppc_account_memlimit(kvmppc_stt_pages(npages), true);
- if (ret) {
- stt = NULL;
- goto fail;
- }
+ if (ret)
+ return ret;

stt = kzalloc(sizeof(*stt) + npages * sizeof(struct page *),
GFP_KERNEL);
if (!stt)
- goto fail;
+ goto fail_acct;

stt->liobn = args->liobn;
stt->page_shift = args->page_shift;
@@ -188,24 +184,39 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
goto fail;
}

- kvm_get_kvm(kvm);
-
mutex_lock(&kvm->lock);
- list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables);
+
+ /* Check this LIOBN hasn't been previously allocated */
+ ret = 0;
+ list_for_each_entry(siter, &kvm->arch.spapr_tce_tables, list) {
+ if (siter->liobn == args->liobn) {
+ ret = -EBUSY;
+ break;
+ }
+ }
+
+ if (!ret)
+ ret = anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
+ stt, O_RDWR | O_CLOEXEC);
+
+ if (ret >= 0) {
+ list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables);
+ kvm_get_kvm(kvm);
+ }

mutex_unlock(&kvm->lock);

- return anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
- stt, O_RDWR | O_CLOEXEC);
+ if (ret >= 0)
+ return ret;

-fail:
- if (stt) {
- for (i = 0; i < npages; i++)
- if (stt->pages[i])
- __free_page(stt->pages[i]);
+ fail:
+ for (i = 0; i < npages; i++)
+ if (stt->pages[i])
+ __free_page(stt->pages[i]);

- kfree(stt);
- }
+ kfree(stt);
+ fail_acct:
+ kvmppc_account_memlimit(kvmppc_stt_pages(npages), false);
return ret;
}

diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index a560a98bcf3b..6a5e7467445c 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -225,8 +225,10 @@ static int add_dt_node(__be32 parent_phandle, __be32 drc_index)
return -ENOENT;

dn = dlpar_configure_connector(drc_index, parent_dn);
- if (!dn)
+ if (!dn) {
+ of_node_put(parent_dn);
return -ENOENT;
+ }

rc = dlpar_attach_node(dn);
if (rc)
diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
index 18d4107e10ee..97fc449a7470 100644
--- a/arch/s390/mm/gup.c
+++ b/arch/s390/mm/gup.c
@@ -56,13 +56,12 @@ static inline int gup_pte_range(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
unsigned long end, int write, struct page **pages, int *nr)
{
- unsigned long mask, result;
struct page *head, *page;
+ unsigned long mask;
int refs;

- result = write ? 0 : _SEGMENT_ENTRY_PROTECT;
- mask = result | _SEGMENT_ENTRY_INVALID;
- if ((pmd_val(pmd) & mask) != result)
+ mask = (write ? _SEGMENT_ENTRY_PROTECT : 0) | _SEGMENT_ENTRY_INVALID;
+ if ((pmd_val(pmd) & mask) != 0)
return 0;
VM_BUG_ON(!pfn_valid(pmd_val(pmd) >> PAGE_SHIFT));

diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c
index c114b132d121..7052d9a65fe9 100644
--- a/arch/x86/kernel/fpu/regset.c
+++ b/arch/x86/kernel/fpu/regset.c
@@ -130,11 +130,16 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset,

fpu__activate_fpstate_write(fpu);

- if (boot_cpu_has(X86_FEATURE_XSAVES))
+ if (boot_cpu_has(X86_FEATURE_XSAVES)) {
ret = copyin_to_xsaves(kbuf, ubuf, xsave);
- else
+ } else {
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);

+ /* xcomp_bv must be 0 when using uncompacted format */
+ if (!ret && xsave->header.xcomp_bv)
+ ret = -EINVAL;
+ }
+
/*
* In case of failure, mark all states as init:
*/
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index a184c210efba..3ec0d2d64601 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -329,6 +329,10 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
} else {
err = __copy_from_user(&fpu->state.xsave,
buf_fx, state_size);
+
+ /* xcomp_bv must be 0 when using uncompacted format */
+ if (!err && state_size > offsetof(struct xregs_state, header) && fpu->state.xsave.header.xcomp_bv)
+ err = -EINVAL;
}

if (err || __copy_from_user(&env, buf, sizeof(env))) {
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 55ffd9dc2258..77f17cbfe271 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -141,7 +141,8 @@ void kvm_async_pf_task_wait(u32 token)

n.token = token;
n.cpu = smp_processor_id();
- n.halted = is_idle_task(current) || preempt_count() > 1;
+ n.halted = is_idle_task(current) || preempt_count() > 1 ||
+ rcu_preempt_depth();
init_swait_queue_head(&n.wq);
hlist_add_head(&n.link, &b->list);
raw_spin_unlock(&b->lock);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 3dc6d8017ce9..fb49212d25df 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2167,46 +2167,44 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
struct pi_desc old, new;
unsigned int dest;

- if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
- !irq_remapping_cap(IRQ_POSTING_CAP) ||
- !kvm_vcpu_apicv_active(vcpu))
+ /*
+ * In case of hot-plug or hot-unplug, we may have to undo
+ * vmx_vcpu_pi_put even if there is no assigned device. And we
+ * always keep PI.NDST up to date for simplicity: it makes the
+ * code easier, and CPU migration is not a fast path.
+ */
+ if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu)
+ return;
+
+ /*
+ * First handle the simple case where no cmpxchg is necessary; just
+ * allow posting non-urgent interrupts.
+ *
+ * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change
+ * PI.NDST: pi_post_block will do it for us and the wakeup_handler
+ * expects the VCPU to be on the blocked_vcpu_list that matches
+ * PI.NDST.
+ */
+ if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR ||
+ vcpu->cpu == cpu) {
+ pi_clear_sn(pi_desc);
return;
+ }

+ /* The full case. */
do {
old.control = new.control = pi_desc->control;

- /*
- * If 'nv' field is POSTED_INTR_WAKEUP_VECTOR, there
- * are two possible cases:
- * 1. After running 'pre_block', context switch
- * happened. For this case, 'sn' was set in
- * vmx_vcpu_put(), so we need to clear it here.
- * 2. After running 'pre_block', we were blocked,
- * and woken up by some other guy. For this case,
- * we don't need to do anything, 'pi_post_block'
- * will do everything for us. However, we cannot
- * check whether it is case #1 or case #2 here
- * (maybe, not needed), so we also clear sn here,
- * I think it is not a big deal.
- */
- if (pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR) {
- if (vcpu->cpu != cpu) {
- dest = cpu_physical_id(cpu);
-
- if (x2apic_enabled())
- new.ndst = dest;
- else
- new.ndst = (dest << 8) & 0xFF00;
- }
+ dest = cpu_physical_id(cpu);

- /* set 'NV' to 'notification vector' */
- new.nv = POSTED_INTR_VECTOR;
- }
+ if (x2apic_enabled())
+ new.ndst = dest;
+ else
+ new.ndst = (dest << 8) & 0xFF00;

- /* Allow posting non-urgent interrupts */
new.sn = 0;
- } while (cmpxchg(&pi_desc->control, old.control,
- new.control) != old.control);
+ } while (cmpxchg64(&pi_desc->control, old.control,
+ new.control) != old.control);
}

static void decache_tsc_multiplier(struct vcpu_vmx *vmx)
@@ -4761,21 +4759,30 @@ static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu)
{
#ifdef CONFIG_SMP
if (vcpu->mode == IN_GUEST_MODE) {
- struct vcpu_vmx *vmx = to_vmx(vcpu);
-
/*
- * Currently, we don't support urgent interrupt,
- * all interrupts are recognized as non-urgent
- * interrupt, so we cannot post interrupts when
- * 'SN' is set.
+ * The vector of interrupt to be delivered to vcpu had
+ * been set in PIR before this function.
*
- * If the vcpu is in guest mode, it means it is
- * running instead of being scheduled out and
- * waiting in the run queue, and that's the only
- * case when 'SN' is set currently, warning if
- * 'SN' is set.
+ * Following cases will be reached in this block, and
+ * we always send a notification event in all cases as
+ * explained below.
+ *
+ * Case 1: vcpu keeps in non-root mode. Sending a
+ * notification event posts the interrupt to vcpu.
+ *
+ * Case 2: vcpu exits to root mode and is still
+ * runnable. PIR will be synced to vIRR before the
+ * next vcpu entry. Sending a notification event in
+ * this case has no effect, as vcpu is not in root
+ * mode.
+ *
+ * Case 3: vcpu exits to root mode and is blocked.
+ * vcpu_block() has already synced PIR to vIRR and
+ * never blocks vcpu if vIRR is not cleared. Therefore,
+ * a blocked vcpu here does not wait for any requested
+ * interrupts in PIR, and sending a notification event
+ * which has no effect is safe here.
*/
- WARN_ON_ONCE(pi_test_sn(&vmx->pi_desc));

apic->send_IPI_mask(get_cpu_mask(vcpu->cpu),
POSTED_INTR_VECTOR);
@@ -9187,6 +9194,13 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)

vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED;

+ /*
+ * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR
+ * or POSTED_INTR_WAKEUP_VECTOR.
+ */
+ vmx->pi_desc.nv = POSTED_INTR_VECTOR;
+ vmx->pi_desc.sn = 1;
+
return &vmx->vcpu;

free_vmcs:
@@ -9996,6 +10010,11 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
vmcs_write64(VIRTUAL_APIC_PAGE_ADDR,
page_to_phys(vmx->nested.virtual_apic_page));
vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold);
+ } else {
+#ifdef CONFIG_X86_64
+ exec_control |= CPU_BASED_CR8_LOAD_EXITING |
+ CPU_BASED_CR8_STORE_EXITING;
+#endif
}

if (cpu_has_vmx_msr_bitmap() &&
@@ -11000,6 +11019,37 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm,
kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask);
}

+static void __pi_post_block(struct kvm_vcpu *vcpu)
+{
+ struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+ struct pi_desc old, new;
+ unsigned int dest;
+
+ do {
+ old.control = new.control = pi_desc->control;
+ WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR,
+ "Wakeup handler not enabled while the VCPU is blocked\n");
+
+ dest = cpu_physical_id(vcpu->cpu);
+
+ if (x2apic_enabled())
+ new.ndst = dest;
+ else
+ new.ndst = (dest << 8) & 0xFF00;
+
+ /* set 'NV' to 'notification vector' */
+ new.nv = POSTED_INTR_VECTOR;
+ } while (cmpxchg64(&pi_desc->control, old.control,
+ new.control) != old.control);
+
+ if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) {
+ spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+ list_del(&vcpu->blocked_vcpu_list);
+ spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+ vcpu->pre_pcpu = -1;
+ }
+}
+
/*
* This routine does the following things for vCPU which is going
* to be blocked if VT-d PI is enabled.
@@ -11015,7 +11065,6 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm,
*/
static int pi_pre_block(struct kvm_vcpu *vcpu)
{
- unsigned long flags;
unsigned int dest;
struct pi_desc old, new;
struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
@@ -11025,34 +11074,20 @@ static int pi_pre_block(struct kvm_vcpu *vcpu)
!kvm_vcpu_apicv_active(vcpu))
return 0;

- vcpu->pre_pcpu = vcpu->cpu;
- spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
- list_add_tail(&vcpu->blocked_vcpu_list,
- &per_cpu(blocked_vcpu_on_cpu,
- vcpu->pre_pcpu));
- spin_unlock_irqrestore(&per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
+ WARN_ON(irqs_disabled());
+ local_irq_disable();
+ if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) {
+ vcpu->pre_pcpu = vcpu->cpu;
+ spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+ list_add_tail(&vcpu->blocked_vcpu_list,
+ &per_cpu(blocked_vcpu_on_cpu,
+ vcpu->pre_pcpu));
+ spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+ }

do {
old.control = new.control = pi_desc->control;

- /*
- * We should not block the vCPU if
- * an interrupt is posted for it.
- */
- if (pi_test_on(pi_desc) == 1) {
- spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
- list_del(&vcpu->blocked_vcpu_list);
- spin_unlock_irqrestore(
- &per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
- vcpu->pre_pcpu = -1;
-
- return 1;
- }
-
WARN((pi_desc->sn == 1),
"Warning: SN field of posted-interrupts "
"is set before blocking\n");
@@ -11074,10 +11109,15 @@ static int pi_pre_block(struct kvm_vcpu *vcpu)

/* set 'NV' to 'wakeup vector' */
new.nv = POSTED_INTR_WAKEUP_VECTOR;
- } while (cmpxchg(&pi_desc->control, old.control,
- new.control) != old.control);
+ } while (cmpxchg64(&pi_desc->control, old.control,
+ new.control) != old.control);

- return 0;
+ /* We should not block the vCPU if an interrupt is posted for it. */
+ if (pi_test_on(pi_desc) == 1)
+ __pi_post_block(vcpu);
+
+ local_irq_enable();
+ return (vcpu->pre_pcpu == -1);
}

static int vmx_pre_block(struct kvm_vcpu *vcpu)
@@ -11093,44 +11133,13 @@ static int vmx_pre_block(struct kvm_vcpu *vcpu)

static void pi_post_block(struct kvm_vcpu *vcpu)
{
- struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
- struct pi_desc old, new;
- unsigned int dest;
- unsigned long flags;
-
- if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
- !irq_remapping_cap(IRQ_POSTING_CAP) ||
- !kvm_vcpu_apicv_active(vcpu))
+ if (vcpu->pre_pcpu == -1)
return;

- do {
- old.control = new.control = pi_desc->control;
-
- dest = cpu_physical_id(vcpu->cpu);
-
- if (x2apic_enabled())
- new.ndst = dest;
- else
- new.ndst = (dest << 8) & 0xFF00;
-
- /* Allow posting non-urgent interrupts */
- new.sn = 0;
-
- /* set 'NV' to 'notification vector' */
- new.nv = POSTED_INTR_VECTOR;
- } while (cmpxchg(&pi_desc->control, old.control,
- new.control) != old.control);
-
- if(vcpu->pre_pcpu != -1) {
- spin_lock_irqsave(
- &per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
- list_del(&vcpu->blocked_vcpu_list);
- spin_unlock_irqrestore(
- &per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
- vcpu->pre_pcpu = -1;
- }
+ WARN_ON(irqs_disabled());
+ local_irq_disable();
+ __pi_post_block(vcpu);
+ local_irq_enable();
}

static void vmx_post_block(struct kvm_vcpu *vcpu)
@@ -11158,7 +11167,7 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
struct kvm_lapic_irq irq;
struct kvm_vcpu *vcpu;
struct vcpu_data vcpu_info;
- int idx, ret = -EINVAL;
+ int idx, ret = 0;

if (!kvm_arch_has_assigned_device(kvm) ||
!irq_remapping_cap(IRQ_POSTING_CAP) ||
@@ -11167,7 +11176,12 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,

idx = srcu_read_lock(&kvm->irq_srcu);
irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
- BUG_ON(guest_irq >= irq_rt->nr_rt_entries);
+ if (guest_irq >= irq_rt->nr_rt_entries ||
+ hlist_empty(&irq_rt->map[guest_irq])) {
+ pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n",
+ guest_irq, irq_rt->nr_rt_entries);
+ goto out;
+ }

hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) {
if (e->type != KVM_IRQ_ROUTING_MSI)
@@ -11210,12 +11224,8 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,

if (set)
ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
- else {
- /* suppress notification event before unposting */
- pi_set_sn(vcpu_to_pi_desc(vcpu));
+ else
ret = irq_set_vcpu_affinity(host_irq, NULL);
- pi_clear_sn(vcpu_to_pi_desc(vcpu));
- }

if (ret < 0) {
printk(KERN_INFO "%s: failed to update PI IRTE\n",
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 9f72ca3b2669..1dd796025472 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -191,8 +191,7 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr)
* 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really
* faulted on a pte with its pkey=4.
*/
-static void fill_sig_info_pkey(int si_code, siginfo_t *info,
- struct vm_area_struct *vma)
+static void fill_sig_info_pkey(int si_code, siginfo_t *info, u32 *pkey)
{
/* This is effectively an #ifdef */
if (!boot_cpu_has(X86_FEATURE_OSPKE))
@@ -208,7 +207,7 @@ static void fill_sig_info_pkey(int si_code, siginfo_t *info,
* valid VMA, so we should never reach this without a
* valid VMA.
*/
- if (!vma) {
+ if (!pkey) {
WARN_ONCE(1, "PKU fault with no VMA passed in");
info->si_pkey = 0;
return;
@@ -218,13 +217,12 @@ static void fill_sig_info_pkey(int si_code, siginfo_t *info,
* absolutely guranteed to be 100% accurate because of
* the race explained above.
*/
- info->si_pkey = vma_pkey(vma);
+ info->si_pkey = *pkey;
}

static void
force_sig_info_fault(int si_signo, int si_code, unsigned long address,
- struct task_struct *tsk, struct vm_area_struct *vma,
- int fault)
+ struct task_struct *tsk, u32 *pkey, int fault)
{
unsigned lsb = 0;
siginfo_t info;
@@ -239,7 +237,7 @@ force_sig_info_fault(int si_signo, int si_code, unsigned long address,
lsb = PAGE_SHIFT;
info.si_addr_lsb = lsb;

- fill_sig_info_pkey(si_code, &info, vma);
+ fill_sig_info_pkey(si_code, &info, pkey);

force_sig_info(si_signo, &info, tsk);
}
@@ -718,8 +716,6 @@ no_context(struct pt_regs *regs, unsigned long error_code,
struct task_struct *tsk = current;
unsigned long flags;
int sig;
- /* No context means no VMA to pass down */
- struct vm_area_struct *vma = NULL;

/* Are we prepared to handle this kernel fault? */
if (fixup_exception(regs, X86_TRAP_PF)) {
@@ -744,7 +740,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,

/* XXX: hwpoison faults will set the wrong code. */
force_sig_info_fault(signal, si_code, address,
- tsk, vma, 0);
+ tsk, NULL, 0);
}

/*
@@ -853,8 +849,7 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code,

static void
__bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
- unsigned long address, struct vm_area_struct *vma,
- int si_code)
+ unsigned long address, u32 *pkey, int si_code)
{
struct task_struct *tsk = current;

@@ -902,7 +897,7 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
tsk->thread.error_code = error_code;
tsk->thread.trap_nr = X86_TRAP_PF;

- force_sig_info_fault(SIGSEGV, si_code, address, tsk, vma, 0);
+ force_sig_info_fault(SIGSEGV, si_code, address, tsk, pkey, 0);

return;
}
@@ -915,9 +910,9 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,

static noinline void
bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
- unsigned long address, struct vm_area_struct *vma)
+ unsigned long address, u32 *pkey)
{
- __bad_area_nosemaphore(regs, error_code, address, vma, SEGV_MAPERR);
+ __bad_area_nosemaphore(regs, error_code, address, pkey, SEGV_MAPERR);
}

static void
@@ -925,6 +920,10 @@ __bad_area(struct pt_regs *regs, unsigned long error_code,
unsigned long address, struct vm_area_struct *vma, int si_code)
{
struct mm_struct *mm = current->mm;
+ u32 pkey;
+
+ if (vma)
+ pkey = vma_pkey(vma);

/*
* Something tried to access memory that isn't in our memory map..
@@ -932,7 +931,8 @@ __bad_area(struct pt_regs *regs, unsigned long error_code,
*/
up_read(&mm->mmap_sem);

- __bad_area_nosemaphore(regs, error_code, address, vma, si_code);
+ __bad_area_nosemaphore(regs, error_code, address,
+ (vma) ? &pkey : NULL, si_code);
}

static noinline void
@@ -975,7 +975,7 @@ bad_area_access_error(struct pt_regs *regs, unsigned long error_code,

static void
do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
- struct vm_area_struct *vma, unsigned int fault)
+ u32 *pkey, unsigned int fault)
{
struct task_struct *tsk = current;
int code = BUS_ADRERR;
@@ -1002,13 +1002,12 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
code = BUS_MCEERR_AR;
}
#endif
- force_sig_info_fault(SIGBUS, code, address, tsk, vma, fault);
+ force_sig_info_fault(SIGBUS, code, address, tsk, pkey, fault);
}

static noinline void
mm_fault_error(struct pt_regs *regs, unsigned long error_code,
- unsigned long address, struct vm_area_struct *vma,
- unsigned int fault)
+ unsigned long address, u32 *pkey, unsigned int fault)
{
if (fatal_signal_pending(current) && !(error_code & PF_USER)) {
no_context(regs, error_code, address, 0, 0);
@@ -1032,9 +1031,9 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
} else {
if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
VM_FAULT_HWPOISON_LARGE))
- do_sigbus(regs, error_code, address, vma, fault);
+ do_sigbus(regs, error_code, address, pkey, fault);
else if (fault & VM_FAULT_SIGSEGV)
- bad_area_nosemaphore(regs, error_code, address, vma);
+ bad_area_nosemaphore(regs, error_code, address, pkey);
else
BUG();
}
@@ -1220,6 +1219,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
struct mm_struct *mm;
int fault, major = 0;
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+ u32 pkey;

tsk = current;
mm = tsk->mm;
@@ -1420,9 +1420,10 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
return;
}

+ pkey = vma_pkey(vma);
up_read(&mm->mmap_sem);
if (unlikely(fault & VM_FAULT_ERROR)) {
- mm_fault_error(regs, error_code, address, vma, fault);
+ mm_fault_error(regs, error_code, address, &pkey, fault);
return;
}

diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index 650f427d915b..341b8d858e67 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -147,7 +147,6 @@ static int bsg_create_job(struct device *dev, struct request *req)
failjob_rls_rqst_payload:
kfree(job->request_payload.sg_list);
failjob_rls_job:
- kfree(job);
return -ENOMEM;
}

diff --git a/crypto/drbg.c b/crypto/drbg.c
index 8cac3d31a5f8..942ddff68408 100644
--- a/crypto/drbg.c
+++ b/crypto/drbg.c
@@ -1133,10 +1133,10 @@ static inline void drbg_dealloc_state(struct drbg_state *drbg)
{
if (!drbg)
return;
- kzfree(drbg->V);
- drbg->Vbuf = NULL;
- kzfree(drbg->C);
- drbg->Cbuf = NULL;
+ kzfree(drbg->Vbuf);
+ drbg->V = NULL;
+ kzfree(drbg->Cbuf);
+ drbg->C = NULL;
kzfree(drbg->scratchpadbuf);
drbg->scratchpadbuf = NULL;
drbg->reseed_ctr = 0;
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 2932a5bd892f..dfffba39f723 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -1757,10 +1757,13 @@ void device_pm_check_callbacks(struct device *dev)
{
spin_lock_irq(&dev->power.lock);
dev->power.no_pm_callbacks =
- (!dev->bus || pm_ops_is_empty(dev->bus->pm)) &&
- (!dev->class || pm_ops_is_empty(dev->class->pm)) &&
+ (!dev->bus || (pm_ops_is_empty(dev->bus->pm) &&
+ !dev->bus->suspend && !dev->bus->resume)) &&
+ (!dev->class || (pm_ops_is_empty(dev->class->pm) &&
+ !dev->class->suspend && !dev->class->resume)) &&
(!dev->type || pm_ops_is_empty(dev->type->pm)) &&
(!dev->pm_domain || pm_ops_is_empty(&dev->pm_domain->ops)) &&
- (!dev->driver || pm_ops_is_empty(dev->driver->pm));
+ (!dev->driver || (pm_ops_is_empty(dev->driver->pm) &&
+ !dev->driver->suspend && !dev->driver->resume));
spin_unlock_irq(&dev->power.lock);
}
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index 571de2f284cf..e2d323fa2437 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -1756,9 +1756,9 @@ static int common_nonsnoop_hash(struct talitos_edesc *edesc,
req_ctx->swinit = 0;
} else {
desc->ptr[1] = zero_entry;
- /* Indicate next op is not the first. */
- req_ctx->first = 0;
}
+ /* Indicate next op is not the first. */
+ req_ctx->first = 0;

/* HMAC key */
if (ctx->keylen)
@@ -1769,7 +1769,7 @@ static int common_nonsnoop_hash(struct talitos_edesc *edesc,

sg_count = edesc->src_nents ?: 1;
if (is_sec1 && sg_count > 1)
- sg_copy_to_buffer(areq->src, sg_count, edesc->buf, length);
+ sg_copy_to_buffer(req_ctx->psrc, sg_count, edesc->buf, length);
else
sg_count = dma_map_sg(dev, req_ctx->psrc, sg_count,
DMA_TO_DEVICE);
@@ -3057,7 +3057,8 @@ static struct talitos_crypto_alg *talitos_alg_alloc(struct device *dev,
t_alg->algt.alg.hash.final = ahash_final;
t_alg->algt.alg.hash.finup = ahash_finup;
t_alg->algt.alg.hash.digest = ahash_digest;
- t_alg->algt.alg.hash.setkey = ahash_setkey;
+ if (!strncmp(alg->cra_name, "hmac", 4))
+ t_alg->algt.alg.hash.setkey = ahash_setkey;
t_alg->algt.alg.hash.import = ahash_import;
t_alg->algt.alg.hash.export = ahash_export;

diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
index 0370b842d9cc..82dd57d4843c 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
@@ -549,12 +549,15 @@ static const struct etnaviv_gem_ops etnaviv_gem_shmem_ops = {
void etnaviv_gem_free_object(struct drm_gem_object *obj)
{
struct etnaviv_gem_object *etnaviv_obj = to_etnaviv_bo(obj);
+ struct etnaviv_drm_private *priv = obj->dev->dev_private;
struct etnaviv_vram_mapping *mapping, *tmp;

/* object should not be active */
WARN_ON(is_active(etnaviv_obj));

+ mutex_lock(&priv->gem_lock);
list_del(&etnaviv_obj->gem_node);
+ mutex_unlock(&priv->gem_lock);

list_for_each_entry_safe(mapping, tmp, &etnaviv_obj->vram_list,
obj_node) {
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 3b21ca5a6c81..82b01123c386 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1674,7 +1674,7 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend,
radeon_agp_suspend(rdev);

pci_save_state(dev->pdev);
- if (freeze && rdev->family >= CHIP_CEDAR) {
+ if (freeze && rdev->family >= CHIP_CEDAR && !(rdev->flags & RADEON_IS_IGP)) {
rdev->asic->asic_reset(rdev, true);
pci_restore_state(dev->pdev);
} else if (suspend) {
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 9398143d7c5e..6512a555f7f8 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -2577,9 +2577,9 @@ static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb)
c4iw_put_ep(&child_ep->com);
reject:
reject_cr(dev, hwtid, skb);
+out:
if (parent_ep)
c4iw_put_ep(&parent_ep->com);
-out:
return 0;
}

@@ -3441,7 +3441,7 @@ int c4iw_create_listen(struct iw_cm_id *cm_id, int backlog)
cm_id->provider_data = ep;
goto out;
}
-
+ remove_handle(ep->com.dev, &ep->com.dev->stid_idr, ep->stid);
cxgb4_free_stid(ep->com.dev->rdev.lldi.tids, ep->stid,
ep->com.local_addr.ss_family);
fail2:
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 549b4afd12e1..7aea0221530c 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -829,6 +829,14 @@ static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh
spin_unlock(&head->batch_head->batch_lock);
goto unlock_out;
}
+ /*
+ * We must assign batch_head of this stripe within the
+ * batch_lock, otherwise clear_batch_ready of batch head
+ * stripe could clear BATCH_READY bit of this stripe and
+ * this stripe->batch_head doesn't get assigned, which
+ * could confuse clear_batch_ready for this stripe
+ */
+ sh->batch_head = head->batch_head;

/*
* at this point, head's BATCH_READY could be cleared, but we
@@ -836,8 +844,6 @@ static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh
*/
list_add(&sh->batch_list, &head->batch_list);
spin_unlock(&head->batch_head->batch_lock);
-
- sh->batch_head = head->batch_head;
} else {
head->batch_head = head;
sh->batch_head = head->batch_head;
@@ -4277,7 +4283,8 @@ static void break_stripe_batch_list(struct stripe_head *head_sh,

set_mask_bits(&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS |
(1 << STRIPE_PREREAD_ACTIVE) |
- (1 << STRIPE_DEGRADED)),
+ (1 << STRIPE_DEGRADED) |
+ (1 << STRIPE_ON_UNPLUG_LIST)),
head_sh->state & (1 << STRIPE_INSYNC));

sh->check_state = head_sh->check_state;
diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index 2e5233b60971..ae856161faa9 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -244,6 +244,10 @@ int cxl_start_context(struct cxl_context *ctx, u64 wed,
ctx->real_mode = false;
}

+ /*
+ * Increment driver use count. Enables global TLBIs for hash
+ * and callbacks to handle the segment table
+ */
cxl_ctx_get();

if ((rc = cxl_ops->attach_process(ctx, kernel, wed, 0))) {
diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c
index afa211397048..d3e009438991 100644
--- a/drivers/misc/cxl/file.c
+++ b/drivers/misc/cxl/file.c
@@ -91,7 +91,6 @@ static int __afu_open(struct inode *inode, struct file *file, bool master)

pr_devel("afu_open pe: %i\n", ctx->pe);
file->private_data = ctx;
- cxl_ctx_get();

/* indicate success */
rc = 0;
@@ -213,6 +212,12 @@ static long afu_ioctl_start_work(struct cxl_context *ctx,
ctx->glpid = get_task_pid(current->group_leader, PIDTYPE_PID);


+ /*
+ * Increment driver use count. Enables global TLBIs for hash
+ * and callbacks to handle the segment table
+ */
+ cxl_ctx_get();
+
trace_cxl_attach(ctx, work.work_element_descriptor, work.num_interrupts, amr);

if ((rc = cxl_ops->attach_process(ctx, false, work.work_element_descriptor,
@@ -222,6 +227,7 @@ static long afu_ioctl_start_work(struct cxl_context *ctx,
put_pid(ctx->glpid);
put_pid(ctx->pid);
ctx->glpid = ctx->pid = NULL;
+ cxl_ctx_put();
goto out;
}

diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 0fd7d7ed07ce..c06932c5ecdb 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -1357,8 +1357,6 @@ static void mac80211_hwsim_tx(struct ieee80211_hw *hw,
txi->control.rates,
ARRAY_SIZE(txi->control.rates));

- txi->rate_driver_data[0] = channel;
-
if (skb->len >= 24 + 8 &&
ieee80211_is_probe_resp(hdr->frame_control)) {
/* fake header transmission time */
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 1b0786555394..f9f4d1c18eb2 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -527,7 +527,7 @@ static ssize_t driver_override_store(struct device *dev,
const char *buf, size_t count)
{
struct pci_dev *pdev = to_pci_dev(dev);
- char *driver_override, *old = pdev->driver_override, *cp;
+ char *driver_override, *old, *cp;

/* We need to keep extra room for a newline */
if (count >= (PAGE_SIZE - 1))
@@ -541,12 +541,15 @@ static ssize_t driver_override_store(struct device *dev,
if (cp)
*cp = '\0';

+ device_lock(dev);
+ old = pdev->driver_override;
if (strlen(driver_override)) {
pdev->driver_override = driver_override;
} else {
kfree(driver_override);
pdev->driver_override = NULL;
}
+ device_unlock(dev);

kfree(old);

@@ -557,8 +560,12 @@ static ssize_t driver_override_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct pci_dev *pdev = to_pci_dev(dev);
+ ssize_t len;

- return snprintf(buf, PAGE_SIZE, "%s\n", pdev->driver_override);
+ device_lock(dev);
+ len = snprintf(buf, PAGE_SIZE, "%s\n", pdev->driver_override);
+ device_unlock(dev);
+ return len;
}
static DEVICE_ATTR_RW(driver_override);

diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index 42bca619f854..c39551b32e94 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -3696,7 +3696,7 @@ iscsi_if_rx(struct sk_buff *skb)
uint32_t group;

nlh = nlmsg_hdr(skb);
- if (nlh->nlmsg_len < sizeof(*nlh) ||
+ if (nlh->nlmsg_len < sizeof(*nlh) + sizeof(*ev) ||
skb->len < nlh->nlmsg_len) {
break;
}
diff --git a/drivers/video/fbdev/aty/atyfb_base.c b/drivers/video/fbdev/aty/atyfb_base.c
index 11026e726b68..81367cf0af77 100644
--- a/drivers/video/fbdev/aty/atyfb_base.c
+++ b/drivers/video/fbdev/aty/atyfb_base.c
@@ -1861,7 +1861,7 @@ static int atyfb_ioctl(struct fb_info *info, u_int cmd, u_long arg)
#if defined(DEBUG) && defined(CONFIG_FB_ATY_CT)
case ATYIO_CLKR:
if (M64_HAS(INTEGRATED)) {
- struct atyclk clk;
+ struct atyclk clk = { 0 };
union aty_pll *pll = &par->pll;
u32 dsp_config = pll->ct.dsp_config;
u32 dsp_on_off = pll->ct.dsp_on_off;
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 679f79f68182..b68ced5a6331 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -680,3 +680,22 @@ xen_swiotlb_set_dma_mask(struct device *dev, u64 dma_mask)
return 0;
}
EXPORT_SYMBOL_GPL(xen_swiotlb_set_dma_mask);
+
+/*
+ * Create userspace mapping for the DMA-coherent memory.
+ * This function should be called with the pages from the current domain only,
+ * passing pages mapped from other domains would lead to memory corruption.
+ */
+int
+xen_swiotlb_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ unsigned long attrs)
+{
+#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
+ if (__generic_dma_ops(dev)->mmap)
+ return __generic_dma_ops(dev)->mmap(dev, vma, cpu_addr,
+ dma_addr, size, attrs);
+#endif
+ return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_dma_mmap);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 1782804f6c26..0fe346c4bd28 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3052,7 +3052,7 @@ static int btrfs_cmp_data_prepare(struct inode *src, u64 loff,
out:
if (ret)
btrfs_cmp_data_free(cmp);
- return 0;
+ return ret;
}

static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst,
@@ -4082,6 +4082,10 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp)
ret = PTR_ERR(new_root);
goto out;
}
+ if (!is_fstree(new_root->objectid)) {
+ ret = -ENOENT;
+ goto out;
+ }

path = btrfs_alloc_path();
if (!path) {
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 2cf5e142675e..04c61bcf62e5 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2367,11 +2367,11 @@ void free_reloc_roots(struct list_head *list)
while (!list_empty(list)) {
reloc_root = list_entry(list->next, struct btrfs_root,
root_list);
+ __del_reloc_root(reloc_root);
free_extent_buffer(reloc_root->node);
free_extent_buffer(reloc_root->commit_root);
reloc_root->node = NULL;
reloc_root->commit_root = NULL;
- __del_reloc_root(reloc_root);
}
}

diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index c0c253005b76..87658f63b374 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -1360,7 +1360,7 @@ exit_cifs(void)
exit_cifs_idmap();
#endif
#ifdef CONFIG_CIFS_UPCALL
- unregister_key_type(&cifs_spnego_key_type);
+ exit_cifs_spnego();
#endif
cifs_destroy_request_bufs();
cifs_destroy_mids();
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 1a545695f547..f6712b6128d8 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -4071,6 +4071,14 @@ cifs_setup_session(const unsigned int xid, struct cifs_ses *ses,
cifs_dbg(FYI, "Security Mode: 0x%x Capabilities: 0x%x TimeAdjust: %d\n",
server->sec_mode, server->capabilities, server->timeAdj);

+ if (ses->auth_key.response) {
+ cifs_dbg(VFS, "Free previous auth_key.response = %p\n",
+ ses->auth_key.response);
+ kfree(ses->auth_key.response);
+ ses->auth_key.response = NULL;
+ ses->auth_key.len = 0;
+ }
+
if (server->ops->sess_setup)
rc = server->ops->sess_setup(xid, ses, nls_info);

diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 3925758f6dde..cf192f9ce254 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -224,6 +224,13 @@ cifs_nt_open(char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb,
if (backup_cred(cifs_sb))
create_options |= CREATE_OPEN_BACKUP_INTENT;

+ /* O_SYNC also has bit for O_DSYNC so following check picks up either */
+ if (f_flags & O_SYNC)
+ create_options |= CREATE_WRITE_THROUGH;
+
+ if (f_flags & O_DIRECT)
+ create_options |= CREATE_NO_BUFFER;
+
oparms.tcon = tcon;
oparms.cifs_sb = cifs_sb;
oparms.desired_access = desired_access;
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 0437e5fdba56..69b610ad3fdc 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -366,7 +366,7 @@ assemble_neg_contexts(struct smb2_negotiate_req *req)
build_encrypt_ctxt((struct smb2_encryption_neg_context *)pneg_ctxt);
req->NegotiateContextOffset = cpu_to_le32(OFFSET_OF_NEG_CONTEXT);
req->NegotiateContextCount = cpu_to_le16(2);
- inc_rfc1001_len(req, 4 + sizeof(struct smb2_preauth_neg_context) + 2
+ inc_rfc1001_len(req, 4 + sizeof(struct smb2_preauth_neg_context)
+ sizeof(struct smb2_encryption_neg_context)); /* calculate hash */
}
#else
@@ -531,15 +531,22 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon)

/*
* validation ioctl must be signed, so no point sending this if we
- * can not sign it. We could eventually change this to selectively
+ * can not sign it (ie are not known user). Even if signing is not
+ * required (enabled but not negotiated), in those cases we selectively
* sign just this, the first and only signed request on a connection.
- * This is good enough for now since a user who wants better security
- * would also enable signing on the mount. Having validation of
- * negotiate info for signed connections helps reduce attack vectors
+ * Having validation of negotiate info helps reduce attack vectors.
*/
- if (tcon->ses->server->sign == false)
+ if (tcon->ses->session_flags & SMB2_SESSION_FLAG_IS_GUEST)
return 0; /* validation requires signing */

+ if (tcon->ses->user_name == NULL) {
+ cifs_dbg(FYI, "Can't validate negotiate: null user mount\n");
+ return 0; /* validation requires signing */
+ }
+
+ if (tcon->ses->session_flags & SMB2_SESSION_FLAG_IS_NULL)
+ cifs_dbg(VFS, "Unexpected null user (anonymous) auth flag sent by server\n");
+
vneg_inbuf.Capabilities =
cpu_to_le32(tcon->ses->server->vals->req_capabilities);
memcpy(vneg_inbuf.Guid, tcon->ses->server->client_guid,
@@ -1010,6 +1017,8 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses,
while (sess_data->func)
sess_data->func(sess_data);

+ if ((ses->session_flags & SMB2_SESSION_FLAG_IS_GUEST) && (ses->sign))
+ cifs_dbg(VFS, "signing requested but authenticated as guest\n");
rc = sess_data->result;
out:
kfree(sess_data);
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 7bff6f46f5da..f7cae1629c6c 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1836,13 +1836,9 @@ static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos)
{
struct gfs2_glock_iter *gi = seq->private;
loff_t n = *pos;
- int ret;
-
- if (gi->last_pos <= *pos)
- n = (*pos - gi->last_pos);

- ret = rhashtable_walk_start(&gi->hti);
- if (ret)
+ rhashtable_walk_enter(&gl_hash_table, &gi->hti);
+ if (rhashtable_walk_start(&gi->hti) != 0)
return NULL;

do {
@@ -1850,6 +1846,7 @@ static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos)
} while (gi->gl && n--);

gi->last_pos = *pos;
+
return gi->gl;
}

@@ -1861,6 +1858,7 @@ static void *gfs2_glock_seq_next(struct seq_file *seq, void *iter_ptr,
(*pos)++;
gi->last_pos = *pos;
gfs2_glock_iter_next(gi);
+
return gi->gl;
}

@@ -1870,6 +1868,7 @@ static void gfs2_glock_seq_stop(struct seq_file *seq, void *iter_ptr)

gi->gl = NULL;
rhashtable_walk_stop(&gi->hti);
+ rhashtable_walk_exit(&gi->hti);
}

static int gfs2_glock_seq_show(struct seq_file *seq, void *iter_ptr)
@@ -1932,12 +1931,10 @@ static int gfs2_glocks_open(struct inode *inode, struct file *file)
struct gfs2_glock_iter *gi = seq->private;

gi->sdp = inode->i_private;
- gi->last_pos = 0;
seq->buf = kmalloc(GFS2_SEQ_GOODSIZE, GFP_KERNEL | __GFP_NOWARN);
if (seq->buf)
seq->size = GFS2_SEQ_GOODSIZE;
gi->gl = NULL;
- ret = rhashtable_walk_init(&gl_hash_table, &gi->hti, GFP_KERNEL);
}
return ret;
}
@@ -1948,7 +1945,6 @@ static int gfs2_glocks_release(struct inode *inode, struct file *file)
struct gfs2_glock_iter *gi = seq->private;

gi->gl = NULL;
- rhashtable_walk_exit(&gi->hti);
return seq_release_private(inode, file);
}

@@ -1960,12 +1956,10 @@ static int gfs2_glstats_open(struct inode *inode, struct file *file)
struct seq_file *seq = file->private_data;
struct gfs2_glock_iter *gi = seq->private;
gi->sdp = inode->i_private;
- gi->last_pos = 0;
seq->buf = kmalloc(GFS2_SEQ_GOODSIZE, GFP_KERNEL | __GFP_NOWARN);
if (seq->buf)
seq->size = GFS2_SEQ_GOODSIZE;
gi->gl = NULL;
- ret = rhashtable_walk_init(&gl_hash_table, &gi->hti, GFP_KERNEL);
}
return ret;
}
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 81818adb8e9e..c932ec454625 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -60,6 +60,7 @@
#include <linux/tty.h>
#include <linux/string.h>
#include <linux/mman.h>
+#include <linux/sched.h>
#include <linux/proc_fs.h>
#include <linux/ioport.h>
#include <linux/uaccess.h>
@@ -416,7 +417,15 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
* esp and eip are intentionally zeroed out. There is no
* non-racy way to read them without freezing the task.
* Programs that need reliable values can use ptrace(2).
+ *
+ * The only exception is if the task is core dumping because
+ * a program is not able to use ptrace(2) in that case. It is
+ * safe because the task has stopped executing permanently.
*/
+ if (permitted && (task->flags & PF_DUMPCORE)) {
+ eip = KSTK_EIP(task);
+ esp = KSTK_ESP(task);
+ }
}

get_task_comm(tcomm, task);
diff --git a/fs/read_write.c b/fs/read_write.c
index e479e24dcd4c..09a8757efd34 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -114,7 +114,7 @@ generic_file_llseek_size(struct file *file, loff_t offset, int whence,
* In the generic case the entire file is data, so as long as
* offset isn't at the end of the file then the offset is data.
*/
- if (offset >= eof)
+ if ((unsigned long long)offset >= eof)
return -ENXIO;
break;
case SEEK_HOLE:
@@ -122,7 +122,7 @@ generic_file_llseek_size(struct file *file, loff_t offset, int whence,
* There is a virtual hole at the end of the file, so as long as
* offset isn't i_size or larger, return i_size.
*/
- if (offset >= eof)
+ if ((unsigned long long)offset >= eof)
return -ENXIO;
offset = eof;
break;
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index bce2e260f55e..6c95812120eb 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1085,6 +1085,7 @@ xfs_ioctl_setattr_dax_invalidate(
int *join_flags)
{
struct inode *inode = VFS_I(ip);
+ struct super_block *sb = inode->i_sb;
int error;

*join_flags = 0;
@@ -1097,7 +1098,7 @@ xfs_ioctl_setattr_dax_invalidate(
if (fa->fsx_xflags & FS_XFLAG_DAX) {
if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)))
return -EINVAL;
- if (ip->i_mount->m_sb.sb_blocksize != PAGE_SIZE)
+ if (bdev_dax_supported(sb, sb->s_blocksize) < 0)
return -EINVAL;
}

diff --git a/include/linux/key.h b/include/linux/key.h
index 722914798f37..6a544726903e 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -176,6 +176,7 @@ struct key {
#define KEY_FLAG_BUILTIN 8 /* set if key is built in to the kernel */
#define KEY_FLAG_ROOT_CAN_INVAL 9 /* set if key can be invalidated by root without permission */
#define KEY_FLAG_KEEP 10 /* set if key should not be removed */
+#define KEY_FLAG_UID_KEYRING 11 /* set if key is a user or user session keyring */

/* the key type and key description string
* - the desc is used to match a key against search criteria
@@ -235,6 +236,7 @@ extern struct key *key_alloc(struct key_type *type,
#define KEY_ALLOC_NOT_IN_QUOTA 0x0002 /* not in quota */
#define KEY_ALLOC_BUILT_IN 0x0004 /* Key is built into kernel */
#define KEY_ALLOC_BYPASS_RESTRICTION 0x0008 /* Override the check on restricted keyrings */
+#define KEY_ALLOC_UID_KEYRING 0x0010 /* allocating a user or user session keyring */

extern void key_revoke(struct key *key);
extern void key_invalidate(struct key *key);
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index e2dba93e374f..2c7d876e2a1a 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -902,21 +902,10 @@ struct ieee80211_tx_info {
unsigned long jiffies;
};
/* NB: vif can be NULL for injected frames */
- union {
- /* NB: vif can be NULL for injected frames */
- struct ieee80211_vif *vif;
-
- /* When packets are enqueued on txq it's easy
- * to re-construct the vif pointer. There's no
- * more space in tx_info so it can be used to
- * store the necessary enqueue time for packet
- * sojourn time computation.
- */
- codel_time_t enqueue_time;
- };
+ struct ieee80211_vif *vif;
struct ieee80211_key_conf *hw_key;
u32 flags;
- /* 4 bytes free */
+ codel_time_t enqueue_time;
} control;
struct {
u64 cookie;
diff --git a/include/xen/swiotlb-xen.h b/include/xen/swiotlb-xen.h
index 7c35e279d1e3..683057f79dca 100644
--- a/include/xen/swiotlb-xen.h
+++ b/include/xen/swiotlb-xen.h
@@ -58,4 +58,9 @@ xen_swiotlb_dma_supported(struct device *hwdev, u64 mask);

extern int
xen_swiotlb_set_dma_mask(struct device *dev, u64 dma_mask);
+
+extern int
+xen_swiotlb_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ unsigned long attrs);
#endif /* __LINUX_SWIOTLB_XEN_H */
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 00bb0aeea1d0..77977f55dff7 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -405,10 +405,8 @@ static void free_desc(unsigned int irq)
* The sysfs entry must be serialized against a concurrent
* irq_sysfs_init() as well.
*/
- mutex_lock(&sparse_irq_lock);
kobject_del(&desc->kobj);
delete_irq_desc(irq);
- mutex_unlock(&sparse_irq_lock);

/*
* We free the descriptor, masks and stat fields via RCU. That
@@ -446,20 +444,15 @@ static int alloc_descs(unsigned int start, unsigned int cnt, int node,
desc = alloc_desc(start + i, node, flags, mask, owner);
if (!desc)
goto err;
- mutex_lock(&sparse_irq_lock);
irq_insert_desc(start + i, desc);
irq_sysfs_add(start + i, desc);
- mutex_unlock(&sparse_irq_lock);
}
+ bitmap_set(allocated_irqs, start, cnt);
return start;

err:
for (i--; i >= 0; i--)
free_desc(start + i);
-
- mutex_lock(&sparse_irq_lock);
- bitmap_clear(allocated_irqs, start, cnt);
- mutex_unlock(&sparse_irq_lock);
return -ENOMEM;
}

@@ -558,6 +551,7 @@ static inline int alloc_descs(unsigned int start, unsigned int cnt, int node,

desc->owner = owner;
}
+ bitmap_set(allocated_irqs, start, cnt);
return start;
}

@@ -653,10 +647,10 @@ void irq_free_descs(unsigned int from, unsigned int cnt)
if (from >= nr_irqs || (from + cnt) > nr_irqs)
return;

+ mutex_lock(&sparse_irq_lock);
for (i = 0; i < cnt; i++)
free_desc(from + i);

- mutex_lock(&sparse_irq_lock);
bitmap_clear(allocated_irqs, from, cnt);
mutex_unlock(&sparse_irq_lock);
}
@@ -703,19 +697,15 @@ __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
from, cnt, 0);
ret = -EEXIST;
if (irq >=0 && start != irq)
- goto err;
+ goto unlock;

if (start + cnt > nr_irqs) {
ret = irq_expand_nr_irqs(start + cnt);
if (ret)
- goto err;
+ goto unlock;
}
-
- bitmap_set(allocated_irqs, start, cnt);
- mutex_unlock(&sparse_irq_lock);
- return alloc_descs(start, cnt, node, affinity, owner);
-
-err:
+ ret = alloc_descs(start, cnt, node, affinity, owner);
+unlock:
mutex_unlock(&sparse_irq_lock);
return ret;
}
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 0db7c8a2afe2..af182a6df25b 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -457,14 +457,19 @@ static long seccomp_attach_filter(unsigned int flags,
return 0;
}

+void __get_seccomp_filter(struct seccomp_filter *filter)
+{
+ /* Reference count is bounded by the number of total processes. */
+ atomic_inc(&filter->usage);
+}
+
/* get_seccomp_filter - increments the reference count of the filter on @tsk */
void get_seccomp_filter(struct task_struct *tsk)
{
struct seccomp_filter *orig = tsk->seccomp.filter;
if (!orig)
return;
- /* Reference count is bounded by the number of total processes. */
- atomic_inc(&orig->usage);
+ __get_seccomp_filter(orig);
}

static inline void seccomp_filter_free(struct seccomp_filter *filter)
@@ -475,10 +480,8 @@ static inline void seccomp_filter_free(struct seccomp_filter *filter)
}
}

-/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */
-void put_seccomp_filter(struct task_struct *tsk)
+static void __put_seccomp_filter(struct seccomp_filter *orig)
{
- struct seccomp_filter *orig = tsk->seccomp.filter;
/* Clean up single-reference branches iteratively. */
while (orig && atomic_dec_and_test(&orig->usage)) {
struct seccomp_filter *freeme = orig;
@@ -487,6 +490,12 @@ void put_seccomp_filter(struct task_struct *tsk)
}
}

+/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */
+void put_seccomp_filter(struct task_struct *tsk)
+{
+ __put_seccomp_filter(tsk->seccomp.filter);
+}
+
/**
* seccomp_send_sigsys - signals the task to allow in-process syscall emulation
* @syscall: syscall number to send to userland
@@ -892,13 +901,13 @@ long seccomp_get_filter(struct task_struct *task, unsigned long filter_off,
if (!data)
goto out;

- get_seccomp_filter(task);
+ __get_seccomp_filter(filter);
spin_unlock_irq(&task->sighand->siglock);

if (copy_to_user(data, fprog->filter, bpf_classic_proglen(fprog)))
ret = -EFAULT;

- put_seccomp_filter(task);
+ __put_seccomp_filter(filter);
return ret;

out:
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 265e0d0216e3..24d603d29512 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1189,6 +1189,8 @@ static struct ctl_table kern_table[] = {
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = timer_migration_handler,
+ .extra1 = &zero,
+ .extra2 = &one,
},
#endif
#ifdef CONFIG_BPF_SYSCALL
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index df445cde8a1e..7d670362891a 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -240,7 +240,7 @@ int timer_migration_handler(struct ctl_table *table, int write,
int ret;

mutex_lock(&mutex);
- ret = proc_dointvec(table, write, buffer, lenp, ppos);
+ ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (!ret && write)
timers_update_migration(false);
mutex_unlock(&mutex);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f95bf81529f5..c1e50cc0d7b0 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3569,11 +3569,17 @@ static int tracing_open(struct inode *inode, struct file *file)
/* If this file was open for write, then erase contents */
if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
int cpu = tracing_get_cpu(inode);
+ struct trace_buffer *trace_buf = &tr->trace_buffer;
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+ if (tr->current_trace->print_max)
+ trace_buf = &tr->max_buffer;
+#endif

if (cpu == RING_BUFFER_ALL_CPUS)
- tracing_reset_online_cpus(&tr->trace_buffer);
+ tracing_reset_online_cpus(trace_buf);
else
- tracing_reset(&tr->trace_buffer, cpu);
+ tracing_reset(trace_buf, cpu);
}

if (file->f_mode & FMODE_READ) {
@@ -5128,7 +5134,7 @@ static int tracing_wait_pipe(struct file *filp)
*
* iter->pos will be 0 if we haven't read anything.
*/
- if (!tracing_is_on() && iter->pos)
+ if (!tracer_tracing_is_on(iter->tr) && iter->pos)
break;

mutex_unlock(&iter->mutex);
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 37bec0f864b7..a7aa54f45e19 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -791,6 +791,7 @@ static int ieee80211_open(struct net_device *dev)
static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
bool going_down)
{
+ struct ieee80211_sub_if_data *txq_sdata = sdata;
struct ieee80211_local *local = sdata->local;
struct fq *fq = &local->fq;
unsigned long flags;
@@ -931,6 +932,9 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,

switch (sdata->vif.type) {
case NL80211_IFTYPE_AP_VLAN:
+ txq_sdata = container_of(sdata->bss,
+ struct ieee80211_sub_if_data, u.ap);
+
mutex_lock(&local->mtx);
list_del(&sdata->u.vlan.list);
mutex_unlock(&local->mtx);
@@ -1001,8 +1005,17 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
}
spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);

- if (sdata->vif.txq) {
- struct txq_info *txqi = to_txq_info(sdata->vif.txq);
+ if (txq_sdata->vif.txq) {
+ struct txq_info *txqi = to_txq_info(txq_sdata->vif.txq);
+
+ /*
+ * FIXME FIXME
+ *
+ * We really shouldn't purge the *entire* txqi since that
+ * contains frames for the other AP_VLANs (and possibly
+ * the AP itself) as well, but there's no API in FQ now
+ * to be able to filter.
+ */

spin_lock_bh(&fq->lock);
ieee80211_txq_purge(local, txqi);
diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c
index eede5c6db8d5..30bba53c2992 100644
--- a/net/mac80211/offchannel.c
+++ b/net/mac80211/offchannel.c
@@ -707,6 +707,8 @@ static int ieee80211_cancel_roc(struct ieee80211_local *local,
if (!cookie)
return -ENOENT;

+ flush_work(&local->hw_roc_start);
+
mutex_lock(&local->mtx);
list_for_each_entry_safe(roc, tmp, &local->roc_list, list) {
if (!mgmt_tx && roc->cookie != cookie)
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index dd190ff3daea..274c564bd9af 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1277,11 +1277,6 @@ static void ieee80211_set_skb_enqueue_time(struct sk_buff *skb)
IEEE80211_SKB_CB(skb)->control.enqueue_time = codel_get_time();
}

-static void ieee80211_set_skb_vif(struct sk_buff *skb, struct txq_info *txqi)
-{
- IEEE80211_SKB_CB(skb)->control.vif = txqi->txq.vif;
-}
-
static u32 codel_skb_len_func(const struct sk_buff *skb)
{
return skb->len;
@@ -3388,6 +3383,7 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
struct ieee80211_tx_info *info;
struct ieee80211_tx_data tx;
ieee80211_tx_result r;
+ struct ieee80211_vif *vif;

spin_lock_bh(&fq->lock);

@@ -3404,8 +3400,6 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
if (!skb)
goto out;

- ieee80211_set_skb_vif(skb, txqi);
-
hdr = (struct ieee80211_hdr *)skb->data;
info = IEEE80211_SKB_CB(skb);

@@ -3462,6 +3456,34 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
}
}

+ switch (tx.sdata->vif.type) {
+ case NL80211_IFTYPE_MONITOR:
+ if (tx.sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE) {
+ vif = &tx.sdata->vif;
+ break;
+ }
+ tx.sdata = rcu_dereference(local->monitor_sdata);
+ if (tx.sdata) {
+ vif = &tx.sdata->vif;
+ info->hw_queue =
+ vif->hw_queue[skb_get_queue_mapping(skb)];
+ } else if (ieee80211_hw_check(&local->hw, QUEUE_CONTROL)) {
+ ieee80211_free_txskb(&local->hw, skb);
+ goto begin;
+ } else {
+ vif = NULL;
+ }
+ break;
+ case NL80211_IFTYPE_AP_VLAN:
+ tx.sdata = container_of(tx.sdata->bss,
+ struct ieee80211_sub_if_data, u.ap);
+ /* fall through */
+ default:
+ vif = &tx.sdata->vif;
+ break;
+ }
+
+ IEEE80211_SKB_CB(skb)->control.vif = vif;
out:
spin_unlock_bh(&fq->lock);

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index e9e9bc5c8773..ece0fbc08607 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -10385,6 +10385,9 @@ static int nl80211_set_rekey_data(struct sk_buff *skb, struct genl_info *info)
if (err)
return err;

+ if (!tb[NL80211_REKEY_DATA_REPLAY_CTR] || !tb[NL80211_REKEY_DATA_KEK] ||
+ !tb[NL80211_REKEY_DATA_KCK])
+ return -EINVAL;
if (nla_len(tb[NL80211_REKEY_DATA_REPLAY_CTR]) != NL80211_REPLAY_CTR_LEN)
return -ERANGE;
if (nla_len(tb[NL80211_REKEY_DATA_KEK]) != NL80211_KEK_LEN)
diff --git a/security/keys/Kconfig b/security/keys/Kconfig
index d942c7c2bc0a..e0a39781b10f 100644
--- a/security/keys/Kconfig
+++ b/security/keys/Kconfig
@@ -41,10 +41,8 @@ config BIG_KEYS
bool "Large payload keys"
depends on KEYS
depends on TMPFS
- depends on (CRYPTO_ANSI_CPRNG = y || CRYPTO_DRBG = y)
select CRYPTO_AES
- select CRYPTO_ECB
- select CRYPTO_RNG
+ select CRYPTO_GCM
help
This option provides support for holding large keys within the kernel
(for example Kerberos ticket caches). The data may be stored out to
diff --git a/security/keys/big_key.c b/security/keys/big_key.c
index 835c1ab30d01..47c6dcab1a8e 100644
--- a/security/keys/big_key.c
+++ b/security/keys/big_key.c
@@ -1,5 +1,6 @@
/* Large capacity key type
*
+ * Copyright (C) 2017 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
* Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*
@@ -16,10 +17,10 @@
#include <linux/shmem_fs.h>
#include <linux/err.h>
#include <linux/scatterlist.h>
+#include <linux/random.h>
#include <keys/user-type.h>
#include <keys/big_key-type.h>
-#include <crypto/rng.h>
-#include <crypto/skcipher.h>
+#include <crypto/aead.h>

/*
* Layout of key payload words.
@@ -49,7 +50,12 @@ enum big_key_op {
/*
* Key size for big_key data encryption
*/
-#define ENC_KEY_SIZE 16
+#define ENC_KEY_SIZE 32
+
+/*
+ * Authentication tag length
+ */
+#define ENC_AUTHTAG_SIZE 16

/*
* big_key defined keys take an arbitrary string as the description and an
@@ -64,57 +70,62 @@ struct key_type key_type_big_key = {
.destroy = big_key_destroy,
.describe = big_key_describe,
.read = big_key_read,
+ /* no ->update(); don't add it without changing big_key_crypt() nonce */
};

/*
- * Crypto names for big_key data encryption
+ * Crypto names for big_key data authenticated encryption
*/
-static const char big_key_rng_name[] = "stdrng";
-static const char big_key_alg_name[] = "ecb(aes)";
+static const char big_key_alg_name[] = "gcm(aes)";

/*
- * Crypto algorithms for big_key data encryption
+ * Crypto algorithms for big_key data authenticated encryption
*/
-static struct crypto_rng *big_key_rng;
-static struct crypto_skcipher *big_key_skcipher;
+static struct crypto_aead *big_key_aead;

/*
- * Generate random key to encrypt big_key data
+ * Since changing the key affects the entire object, we need a mutex.
*/
-static inline int big_key_gen_enckey(u8 *key)
-{
- return crypto_rng_get_bytes(big_key_rng, key, ENC_KEY_SIZE);
-}
+static DEFINE_MUTEX(big_key_aead_lock);

/*
* Encrypt/decrypt big_key data
*/
static int big_key_crypt(enum big_key_op op, u8 *data, size_t datalen, u8 *key)
{
- int ret = -EINVAL;
+ int ret;
struct scatterlist sgio;
- SKCIPHER_REQUEST_ON_STACK(req, big_key_skcipher);
-
- if (crypto_skcipher_setkey(big_key_skcipher, key, ENC_KEY_SIZE)) {
+ struct aead_request *aead_req;
+ /* We always use a zero nonce. The reason we can get away with this is
+ * because we're using a different randomly generated key for every
+ * different encryption. Notably, too, key_type_big_key doesn't define
+ * an .update function, so there's no chance we'll wind up reusing the
+ * key to encrypt updated data. Simply put: one key, one encryption.
+ */
+ u8 zero_nonce[crypto_aead_ivsize(big_key_aead)];
+
+ aead_req = aead_request_alloc(big_key_aead, GFP_KERNEL);
+ if (!aead_req)
+ return -ENOMEM;
+
+ memset(zero_nonce, 0, sizeof(zero_nonce));
+ sg_init_one(&sgio, data, datalen + (op == BIG_KEY_ENC ? ENC_AUTHTAG_SIZE : 0));
+ aead_request_set_crypt(aead_req, &sgio, &sgio, datalen, zero_nonce);
+ aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
+ aead_request_set_ad(aead_req, 0);
+
+ mutex_lock(&big_key_aead_lock);
+ if (crypto_aead_setkey(big_key_aead, key, ENC_KEY_SIZE)) {
ret = -EAGAIN;
goto error;
}
-
- skcipher_request_set_tfm(req, big_key_skcipher);
- skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP,
- NULL, NULL);
-
- sg_init_one(&sgio, data, datalen);
- skcipher_request_set_crypt(req, &sgio, &sgio, datalen, NULL);
-
if (op == BIG_KEY_ENC)
- ret = crypto_skcipher_encrypt(req);
+ ret = crypto_aead_encrypt(aead_req);
else
- ret = crypto_skcipher_decrypt(req);
-
- skcipher_request_zero(req);
-
+ ret = crypto_aead_decrypt(aead_req);
error:
+ mutex_unlock(&big_key_aead_lock);
+ aead_request_free(aead_req);
return ret;
}

@@ -146,15 +157,13 @@ int big_key_preparse(struct key_preparsed_payload *prep)
*
* File content is stored encrypted with randomly generated key.
*/
- size_t enclen = ALIGN(datalen, crypto_skcipher_blocksize(big_key_skcipher));
+ size_t enclen = datalen + ENC_AUTHTAG_SIZE;

- /* prepare aligned data to encrypt */
data = kmalloc(enclen, GFP_KERNEL);
if (!data)
return -ENOMEM;

memcpy(data, prep->data, datalen);
- memset(data + datalen, 0x00, enclen - datalen);

/* generate random key */
enckey = kmalloc(ENC_KEY_SIZE, GFP_KERNEL);
@@ -162,13 +171,10 @@ int big_key_preparse(struct key_preparsed_payload *prep)
ret = -ENOMEM;
goto error;
}
-
- ret = big_key_gen_enckey(enckey);
- if (ret)
- goto err_enckey;
+ get_random_bytes(enckey, ENC_KEY_SIZE);

/* encrypt aligned data */
- ret = big_key_crypt(BIG_KEY_ENC, data, enclen, enckey);
+ ret = big_key_crypt(BIG_KEY_ENC, data, datalen, enckey);
if (ret)
goto err_enckey;

@@ -194,7 +200,7 @@ int big_key_preparse(struct key_preparsed_payload *prep)
*path = file->f_path;
path_get(path);
fput(file);
- kfree(data);
+ kzfree(data);
} else {
/* Just store the data in a buffer */
void *data = kmalloc(datalen, GFP_KERNEL);
@@ -210,9 +216,9 @@ int big_key_preparse(struct key_preparsed_payload *prep)
err_fput:
fput(file);
err_enckey:
- kfree(enckey);
+ kzfree(enckey);
error:
- kfree(data);
+ kzfree(data);
return ret;
}

@@ -226,7 +232,7 @@ void big_key_free_preparse(struct key_preparsed_payload *prep)

path_put(path);
}
- kfree(prep->payload.data[big_key_data]);
+ kzfree(prep->payload.data[big_key_data]);
}

/*
@@ -258,7 +264,7 @@ void big_key_destroy(struct key *key)
path->mnt = NULL;
path->dentry = NULL;
}
- kfree(key->payload.data[big_key_data]);
+ kzfree(key->payload.data[big_key_data]);
key->payload.data[big_key_data] = NULL;
}

@@ -294,7 +300,7 @@ long big_key_read(const struct key *key, char __user *buffer, size_t buflen)
struct file *file;
u8 *data;
u8 *enckey = (u8 *)key->payload.data[big_key_data];
- size_t enclen = ALIGN(datalen, crypto_skcipher_blocksize(big_key_skcipher));
+ size_t enclen = datalen + ENC_AUTHTAG_SIZE;

data = kmalloc(enclen, GFP_KERNEL);
if (!data)
@@ -326,7 +332,7 @@ long big_key_read(const struct key *key, char __user *buffer, size_t buflen)
err_fput:
fput(file);
error:
- kfree(data);
+ kzfree(data);
} else {
ret = datalen;
if (copy_to_user(buffer, key->payload.data[big_key_data],
@@ -342,47 +348,31 @@ long big_key_read(const struct key *key, char __user *buffer, size_t buflen)
*/
static int __init big_key_init(void)
{
- struct crypto_skcipher *cipher;
- struct crypto_rng *rng;
int ret;

- rng = crypto_alloc_rng(big_key_rng_name, 0, 0);
- if (IS_ERR(rng)) {
- pr_err("Can't alloc rng: %ld\n", PTR_ERR(rng));
- return PTR_ERR(rng);
- }
-
- big_key_rng = rng;
-
- /* seed RNG */
- ret = crypto_rng_reset(rng, NULL, crypto_rng_seedsize(rng));
- if (ret) {
- pr_err("Can't reset rng: %d\n", ret);
- goto error_rng;
- }
-
/* init block cipher */
- cipher = crypto_alloc_skcipher(big_key_alg_name, 0, CRYPTO_ALG_ASYNC);
- if (IS_ERR(cipher)) {
- ret = PTR_ERR(cipher);
+ big_key_aead = crypto_alloc_aead(big_key_alg_name, 0, CRYPTO_ALG_ASYNC);
+ if (IS_ERR(big_key_aead)) {
+ ret = PTR_ERR(big_key_aead);
pr_err("Can't alloc crypto: %d\n", ret);
- goto error_rng;
+ return ret;
+ }
+ ret = crypto_aead_setauthsize(big_key_aead, ENC_AUTHTAG_SIZE);
+ if (ret < 0) {
+ pr_err("Can't set crypto auth tag len: %d\n", ret);
+ goto free_aead;
}
-
- big_key_skcipher = cipher;

ret = register_key_type(&key_type_big_key);
if (ret < 0) {
pr_err("Can't register type: %d\n", ret);
- goto error_cipher;
+ goto free_aead;
}

return 0;

-error_cipher:
- crypto_free_skcipher(big_key_skcipher);
-error_rng:
- crypto_free_rng(big_key_rng);
+free_aead:
+ crypto_free_aead(big_key_aead);
return ret;
}

diff --git a/security/keys/internal.h b/security/keys/internal.h
index a705a7d92ad7..fb0c65049c19 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -137,7 +137,7 @@ extern key_ref_t keyring_search_aux(key_ref_t keyring_ref,
extern key_ref_t search_my_process_keyrings(struct keyring_search_context *ctx);
extern key_ref_t search_process_keyrings(struct keyring_search_context *ctx);

-extern struct key *find_keyring_by_name(const char *name, bool skip_perm_check);
+extern struct key *find_keyring_by_name(const char *name, bool uid_keyring);

extern int install_user_keyrings(void);
extern int install_thread_keyring_to_cred(struct cred *);
diff --git a/security/keys/key.c b/security/keys/key.c
index 2f4ce35ae2aa..135e1eb7e468 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -301,6 +301,8 @@ struct key *key_alloc(struct key_type *type, const char *desc,
key->flags |= 1 << KEY_FLAG_IN_QUOTA;
if (flags & KEY_ALLOC_BUILT_IN)
key->flags |= 1 << KEY_FLAG_BUILTIN;
+ if (flags & KEY_ALLOC_UID_KEYRING)
+ key->flags |= 1 << KEY_FLAG_UID_KEYRING;

#ifdef KEY_DEBUGGING
key->magic = KEY_DEBUG_MAGIC;
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index ada12c3e3ac4..1302cb398346 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -766,6 +766,11 @@ long keyctl_read_key(key_serial_t keyid, char __user *buffer, size_t buflen)

key = key_ref_to_ptr(key_ref);

+ if (test_bit(KEY_FLAG_NEGATIVE, &key->flags)) {
+ ret = -ENOKEY;
+ goto error2;
+ }
+
/* see if we can read it directly */
ret = key_permission(key_ref, KEY_NEED_READ);
if (ret == 0)
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index c91e4e0cea08..a86d0ae1773c 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -416,7 +416,7 @@ static void keyring_describe(const struct key *keyring, struct seq_file *m)
}

struct keyring_read_iterator_context {
- size_t qty;
+ size_t buflen;
size_t count;
key_serial_t __user *buffer;
};
@@ -428,9 +428,9 @@ static int keyring_read_iterator(const void *object, void *data)
int ret;

kenter("{%s,%d},,{%zu/%zu}",
- key->type->name, key->serial, ctx->count, ctx->qty);
+ key->type->name, key->serial, ctx->count, ctx->buflen);

- if (ctx->count >= ctx->qty)
+ if (ctx->count >= ctx->buflen)
return 1;

ret = put_user(key->serial, ctx->buffer);
@@ -465,16 +465,12 @@ static long keyring_read(const struct key *keyring,
return 0;

/* Calculate how much data we could return */
- ctx.qty = nr_keys * sizeof(key_serial_t);
-
if (!buffer || !buflen)
- return ctx.qty;
-
- if (buflen > ctx.qty)
- ctx.qty = buflen;
+ return nr_keys * sizeof(key_serial_t);

/* Copy the IDs of the subscribed keys into the buffer */
ctx.buffer = (key_serial_t __user *)buffer;
+ ctx.buflen = buflen;
ctx.count = 0;
ret = assoc_array_iterate(&keyring->keys, keyring_read_iterator, &ctx);
if (ret < 0) {
@@ -989,15 +985,15 @@ key_ref_t find_key_to_update(key_ref_t keyring_ref,
/*
* Find a keyring with the specified name.
*
- * All named keyrings in the current user namespace are searched, provided they
- * grant Search permission directly to the caller (unless this check is
- * skipped). Keyrings whose usage points have reached zero or who have been
- * revoked are skipped.
+ * Only keyrings that have nonzero refcount, are not revoked, and are owned by a
+ * user in the current user namespace are considered. If @uid_keyring is %true,
+ * the keyring additionally must have been allocated as a user or user session
+ * keyring; otherwise, it must grant Search permission directly to the caller.
*
* Returns a pointer to the keyring with the keyring's refcount having being
* incremented on success. -ENOKEY is returned if a key could not be found.
*/
-struct key *find_keyring_by_name(const char *name, bool skip_perm_check)
+struct key *find_keyring_by_name(const char *name, bool uid_keyring)
{
struct key *keyring;
int bucket;
@@ -1025,10 +1021,15 @@ struct key *find_keyring_by_name(const char *name, bool skip_perm_check)
if (strcmp(keyring->description, name) != 0)
continue;

- if (!skip_perm_check &&
- key_permission(make_key_ref(keyring, 0),
- KEY_NEED_SEARCH) < 0)
- continue;
+ if (uid_keyring) {
+ if (!test_bit(KEY_FLAG_UID_KEYRING,
+ &keyring->flags))
+ continue;
+ } else {
+ if (key_permission(make_key_ref(keyring, 0),
+ KEY_NEED_SEARCH) < 0)
+ continue;
+ }

/* we've got a match but we might end up racing with
* key_cleanup() if the keyring is currently 'dead'
diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c
index 45536c677b05..ce45c78cf0a2 100644
--- a/security/keys/process_keys.c
+++ b/security/keys/process_keys.c
@@ -76,7 +76,8 @@ int install_user_keyrings(void)
if (IS_ERR(uid_keyring)) {
uid_keyring = keyring_alloc(buf, user->uid, INVALID_GID,
cred, user_keyring_perm,
- KEY_ALLOC_IN_QUOTA,
+ KEY_ALLOC_UID_KEYRING |
+ KEY_ALLOC_IN_QUOTA,
NULL, NULL);
if (IS_ERR(uid_keyring)) {
ret = PTR_ERR(uid_keyring);
@@ -93,7 +94,8 @@ int install_user_keyrings(void)
session_keyring =
keyring_alloc(buf, user->uid, INVALID_GID,
cred, user_keyring_perm,
- KEY_ALLOC_IN_QUOTA,
+ KEY_ALLOC_UID_KEYRING |
+ KEY_ALLOC_IN_QUOTA,
NULL, NULL);
if (IS_ERR(session_keyring)) {
ret = PTR_ERR(session_keyring);
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 03f1fa495d74..cbb0564c0ec4 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -6,10 +6,18 @@
*/

#include <sys/types.h>
-#include <asm/siginfo.h>
-#define __have_siginfo_t 1
-#define __have_sigval_t 1
-#define __have_sigevent_t 1
+
+/*
+ * glibc 2.26 and later have SIGSYS in siginfo_t. Before that,
+ * we need to use the kernel's siginfo.h file and trick glibc
+ * into accepting it.
+ */
+#if !__GLIBC_PREREQ(2, 26)
+# include <asm/siginfo.h>
+# define __have_siginfo_t 1
+# define __have_sigval_t 1
+# define __have_sigevent_t 1
+#endif

#include <errno.h>
#include <linux/filter.h>
@@ -676,7 +684,7 @@ TEST_F_SIGNAL(TRAP, ign, SIGSYS)
syscall(__NR_getpid);
}

-static struct siginfo TRAP_info;
+static siginfo_t TRAP_info;
static volatile int TRAP_nr;
static void TRAP_action(int nr, siginfo_t *info, void *void_context)
{
\
 
 \ /
  Last update: 2017-10-05 10:14    [W:0.064 / U:0.064 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site