Merge branch 'userns-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/luto/linux
Pull user-namespace fixes from Andy Lutomirski.
* 'userns-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/luto/linux:
userns: Changing any namespace id mappings should require privileges
userns: Check uid_map's opener's fsuid, not the current fsuid
userns: Don't let unprivileged users trick privileged users into setting the id_map
diff --git a/Makefile b/Makefile
index 6db672b..ac509b2 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
VERSION = 3
PATCHLEVEL = 9
SUBLEVEL = 0
-EXTRAVERSION = -rc6
+EXTRAVERSION = -rc7
NAME = Unicycling Gorilla
# *DOCUMENTATION*
@@ -513,7 +513,8 @@
# Carefully list dependencies so we do not try to build scripts twice
# in parallel
PHONY += scripts
-scripts: scripts_basic include/config/auto.conf include/config/tristate.conf
+scripts: scripts_basic include/config/auto.conf include/config/tristate.conf \
+ asm-generic
$(Q)$(MAKE) $(build)=$(@)
# Objects we will link into vmlinux / subdirs we need to visit
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index 6ef8afd..86b8fe3 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -111,7 +111,7 @@
#define L_PTE_S2_MT_WRITETHROUGH (_AT(pteval_t, 0xa) << 2) /* MemAttr[3:0] */
#define L_PTE_S2_MT_WRITEBACK (_AT(pteval_t, 0xf) << 2) /* MemAttr[3:0] */
#define L_PTE_S2_RDONLY (_AT(pteval_t, 1) << 6) /* HAP[1] */
-#define L_PTE_S2_RDWR (_AT(pteval_t, 2) << 6) /* HAP[2:1] */
+#define L_PTE_S2_RDWR (_AT(pteval_t, 3) << 6) /* HAP[2:1] */
/*
* Hyp-mode PL2 PTE definitions for LPAE.
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 5a93698..c1fe498 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -201,6 +201,7 @@
break;
case KVM_CAP_ARM_SET_DEVICE_ADDR:
r = 1;
+ break;
case KVM_CAP_NR_VCPUS:
r = num_online_cpus();
break;
diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c
index 4ea9a98..7bed755 100644
--- a/arch/arm/kvm/coproc.c
+++ b/arch/arm/kvm/coproc.c
@@ -79,11 +79,11 @@
u32 val;
int cpu;
- cpu = get_cpu();
-
if (!p->is_write)
return read_from_write_only(vcpu, p);
+ cpu = get_cpu();
+
cpumask_setall(&vcpu->arch.require_dcache_flush);
cpumask_clear_cpu(cpu, &vcpu->arch.require_dcache_flush);
diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S
index 2c3b942..2556cf1 100644
--- a/arch/arm/mm/proc-arm920.S
+++ b/arch/arm/mm/proc-arm920.S
@@ -387,7 +387,7 @@
/* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */
.globl cpu_arm920_suspend_size
.equ cpu_arm920_suspend_size, 4 * 3
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
ENTRY(cpu_arm920_do_suspend)
stmfd sp!, {r4 - r6, lr}
mrc p15, 0, r4, c13, c0, 0 @ PID
diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S
index f1803f7..344c8a5 100644
--- a/arch/arm/mm/proc-arm926.S
+++ b/arch/arm/mm/proc-arm926.S
@@ -402,7 +402,7 @@
/* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */
.globl cpu_arm926_suspend_size
.equ cpu_arm926_suspend_size, 4 * 3
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
ENTRY(cpu_arm926_do_suspend)
stmfd sp!, {r4 - r6, lr}
mrc p15, 0, r4, c13, c0, 0 @ PID
diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S
index 82f9cdc..0b60dd3 100644
--- a/arch/arm/mm/proc-mohawk.S
+++ b/arch/arm/mm/proc-mohawk.S
@@ -350,7 +350,7 @@
.globl cpu_mohawk_suspend_size
.equ cpu_mohawk_suspend_size, 4 * 6
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
ENTRY(cpu_mohawk_do_suspend)
stmfd sp!, {r4 - r9, lr}
mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode
diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S
index 3aa0da1..d92dfd0 100644
--- a/arch/arm/mm/proc-sa1100.S
+++ b/arch/arm/mm/proc-sa1100.S
@@ -172,7 +172,7 @@
.globl cpu_sa1100_suspend_size
.equ cpu_sa1100_suspend_size, 4 * 3
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
ENTRY(cpu_sa1100_do_suspend)
stmfd sp!, {r4 - r6, lr}
mrc p15, 0, r4, c3, c0, 0 @ domain ID
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index bcaaa8d..5c07ee4 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -138,7 +138,7 @@
/* Suspend/resume support: taken from arch/arm/mach-s3c64xx/sleep.S */
.globl cpu_v6_suspend_size
.equ cpu_v6_suspend_size, 4 * 6
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
ENTRY(cpu_v6_do_suspend)
stmfd sp!, {r4 - r9, lr}
mrc p15, 0, r4, c13, c0, 0 @ FCSE/PID
diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S
index eb93d64..e8efd83 100644
--- a/arch/arm/mm/proc-xsc3.S
+++ b/arch/arm/mm/proc-xsc3.S
@@ -413,7 +413,7 @@
.globl cpu_xsc3_suspend_size
.equ cpu_xsc3_suspend_size, 4 * 6
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
ENTRY(cpu_xsc3_do_suspend)
stmfd sp!, {r4 - r9, lr}
mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode
diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S
index 2551036..e766f88 100644
--- a/arch/arm/mm/proc-xscale.S
+++ b/arch/arm/mm/proc-xscale.S
@@ -528,7 +528,7 @@
.globl cpu_xscale_suspend_size
.equ cpu_xscale_suspend_size, 4 * 6
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
ENTRY(cpu_xscale_do_suspend)
stmfd sp!, {r4 - r9, lr}
mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode
diff --git a/arch/avr32/include/asm/io.h b/arch/avr32/include/asm/io.h
index cf60d0a..fc6483f 100644
--- a/arch/avr32/include/asm/io.h
+++ b/arch/avr32/include/asm/io.h
@@ -165,6 +165,10 @@
#define readw_be __raw_readw
#define readl_be __raw_readl
+#define writeb_relaxed writeb
+#define writew_relaxed writew
+#define writel_relaxed writel
+
#define writeb_be __raw_writeb
#define writew_be __raw_writew
#define writel_be __raw_writel
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 256c5bf..04d69c4 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -304,7 +304,7 @@
subi r12,r12,TI_FLAGS
4: /* Anything else left to do? */
- SET_DEFAULT_THREAD_PPR(r3, r9) /* Set thread.ppr = 3 */
+ SET_DEFAULT_THREAD_PPR(r3, r10) /* Set thread.ppr = 3 */
andi. r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP)
beq .ret_from_except_lite
@@ -657,7 +657,7 @@
/* Clear _TIF_EMULATE_STACK_STORE flag */
lis r11,_TIF_EMULATE_STACK_STORE@h
addi r5,r9,TI_FLAGS
- ldarx r4,0,r5
+0: ldarx r4,0,r5
andc r4,r4,r11
stdcx. r4,0,r5
bne- 0b
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 59dd545..16e77a8 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -555,10 +555,12 @@
new->thread.regs->msr |=
(MSR_FP | new->thread.fpexc_mode);
}
+#ifdef CONFIG_ALTIVEC
if (msr & MSR_VEC) {
do_load_up_transact_altivec(&new->thread);
new->thread.regs->msr |= MSR_VEC;
}
+#endif
/* We may as well turn on VSX too since all the state is restored now */
if (msr & MSR_VSX)
new->thread.regs->msr |= MSR_VSX;
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 3acb28e..95068bf 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -866,10 +866,12 @@
do_load_up_transact_fpu(¤t->thread);
regs->msr |= (MSR_FP | current->thread.fpexc_mode);
}
+#ifdef CONFIG_ALTIVEC
if (msr & MSR_VEC) {
do_load_up_transact_altivec(¤t->thread);
regs->msr |= MSR_VEC;
}
+#endif
return 0;
}
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 995f854..c179428 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -522,10 +522,12 @@
do_load_up_transact_fpu(¤t->thread);
regs->msr |= (MSR_FP | current->thread.fpexc_mode);
}
+#ifdef CONFIG_ALTIVEC
if (msr & MSR_VEC) {
do_load_up_transact_altivec(¤t->thread);
regs->msr |= MSR_VEC;
}
+#endif
return err;
}
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index 84dbace..2da67e7 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -309,6 +309,7 @@
or r5, r6, r5 /* Set MSR.FP+.VSX/.VEC */
mtmsr r5
+#ifdef CONFIG_ALTIVEC
/* FP and VEC registers: These are recheckpointed from thread.fpr[]
* and thread.vr[] respectively. The thread.transact_fpr[] version
* is more modern, and will be loaded subsequently by any FPUnavailable
@@ -323,6 +324,7 @@
REST_32VRS(0, r5, r3) /* r5 scratch, r3 THREAD ptr */
ld r5, THREAD_VRSAVE(r3)
mtspr SPRN_VRSAVE, r5
+#endif
dont_restore_vec:
andi. r0, r4, MSR_FP
diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h
index 41cefd4..33db48a 100644
--- a/arch/powerpc/kvm/e500.h
+++ b/arch/powerpc/kvm/e500.h
@@ -26,17 +26,20 @@
#define E500_PID_NUM 3
#define E500_TLB_NUM 2
-#define E500_TLB_VALID 1
-#define E500_TLB_BITMAP 2
+/* entry is mapped somewhere in host TLB */
+#define E500_TLB_VALID (1 << 0)
+/* TLB1 entry is mapped by host TLB1, tracked by bitmaps */
+#define E500_TLB_BITMAP (1 << 1)
+/* TLB1 entry is mapped by host TLB0 */
#define E500_TLB_TLB0 (1 << 2)
struct tlbe_ref {
- pfn_t pfn;
- unsigned int flags; /* E500_TLB_* */
+ pfn_t pfn; /* valid only for TLB0, except briefly */
+ unsigned int flags; /* E500_TLB_* */
};
struct tlbe_priv {
- struct tlbe_ref ref; /* TLB0 only -- TLB1 uses tlb_refs */
+ struct tlbe_ref ref;
};
#ifdef CONFIG_KVM_E500V2
@@ -63,17 +66,6 @@
unsigned int gtlb_nv[E500_TLB_NUM];
- /*
- * information associated with each host TLB entry --
- * TLB1 only for now. If/when guest TLB1 entries can be
- * mapped with host TLB0, this will be used for that too.
- *
- * We don't want to use this for guest TLB0 because then we'd
- * have the overhead of doing the translation again even if
- * the entry is still in the guest TLB (e.g. we swapped out
- * and back, and our host TLB entries got evicted).
- */
- struct tlbe_ref *tlb_refs[E500_TLB_NUM];
unsigned int host_tlb1_nv;
u32 svr;
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index a222edf..1c6a9d72 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -193,8 +193,11 @@
struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[tlbsel][esel].ref;
/* Don't bother with unmapped entries */
- if (!(ref->flags & E500_TLB_VALID))
- return;
+ if (!(ref->flags & E500_TLB_VALID)) {
+ WARN(ref->flags & (E500_TLB_BITMAP | E500_TLB_TLB0),
+ "%s: flags %x\n", __func__, ref->flags);
+ WARN_ON(tlbsel == 1 && vcpu_e500->g2h_tlb1_map[esel]);
+ }
if (tlbsel == 1 && ref->flags & E500_TLB_BITMAP) {
u64 tmp = vcpu_e500->g2h_tlb1_map[esel];
@@ -248,7 +251,7 @@
pfn_t pfn)
{
ref->pfn = pfn;
- ref->flags = E500_TLB_VALID;
+ ref->flags |= E500_TLB_VALID;
if (tlbe_is_writable(gtlbe))
kvm_set_pfn_dirty(pfn);
@@ -257,6 +260,7 @@
static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref)
{
if (ref->flags & E500_TLB_VALID) {
+ /* FIXME: don't log bogus pfn for TLB1 */
trace_kvm_booke206_ref_release(ref->pfn, ref->flags);
ref->flags = 0;
}
@@ -274,36 +278,23 @@
static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500)
{
- int tlbsel = 0;
+ int tlbsel;
int i;
- for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) {
- struct tlbe_ref *ref =
- &vcpu_e500->gtlb_priv[tlbsel][i].ref;
- kvmppc_e500_ref_release(ref);
+ for (tlbsel = 0; tlbsel <= 1; tlbsel++) {
+ for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) {
+ struct tlbe_ref *ref =
+ &vcpu_e500->gtlb_priv[tlbsel][i].ref;
+ kvmppc_e500_ref_release(ref);
+ }
}
}
-static void clear_tlb_refs(struct kvmppc_vcpu_e500 *vcpu_e500)
-{
- int stlbsel = 1;
- int i;
-
- kvmppc_e500_tlbil_all(vcpu_e500);
-
- for (i = 0; i < host_tlb_params[stlbsel].entries; i++) {
- struct tlbe_ref *ref =
- &vcpu_e500->tlb_refs[stlbsel][i];
- kvmppc_e500_ref_release(ref);
- }
-
- clear_tlb_privs(vcpu_e500);
-}
-
void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
- clear_tlb_refs(vcpu_e500);
+ kvmppc_e500_tlbil_all(vcpu_e500);
+ clear_tlb_privs(vcpu_e500);
clear_tlb1_bitmap(vcpu_e500);
}
@@ -458,8 +449,6 @@
gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
}
- /* Drop old ref and setup new one. */
- kvmppc_e500_ref_release(ref);
kvmppc_e500_ref_setup(ref, gtlbe, pfn);
kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize,
@@ -507,14 +496,15 @@
if (unlikely(vcpu_e500->host_tlb1_nv >= tlb1_max_shadow_size()))
vcpu_e500->host_tlb1_nv = 0;
- vcpu_e500->tlb_refs[1][sesel] = *ref;
- vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel;
- vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP;
if (vcpu_e500->h2g_tlb1_rmap[sesel]) {
- unsigned int idx = vcpu_e500->h2g_tlb1_rmap[sesel];
+ unsigned int idx = vcpu_e500->h2g_tlb1_rmap[sesel] - 1;
vcpu_e500->g2h_tlb1_map[idx] &= ~(1ULL << sesel);
}
- vcpu_e500->h2g_tlb1_rmap[sesel] = esel;
+
+ vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP;
+ vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel;
+ vcpu_e500->h2g_tlb1_rmap[sesel] = esel + 1;
+ WARN_ON(!(ref->flags & E500_TLB_VALID));
return sesel;
}
@@ -526,13 +516,12 @@
u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe,
struct kvm_book3e_206_tlb_entry *stlbe, int esel)
{
- struct tlbe_ref ref;
+ struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[1][esel].ref;
int sesel;
int r;
- ref.flags = 0;
r = kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, stlbe,
- &ref);
+ ref);
if (r)
return r;
@@ -544,7 +533,7 @@
}
/* Otherwise map into TLB1 */
- sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, &ref, esel);
+ sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, ref, esel);
write_stlbe(vcpu_e500, gtlbe, stlbe, 1, sesel);
return 0;
@@ -565,7 +554,7 @@
case 0:
priv = &vcpu_e500->gtlb_priv[tlbsel][esel];
- /* Triggers after clear_tlb_refs or on initial mapping */
+ /* Triggers after clear_tlb_privs or on initial mapping */
if (!(priv->ref.flags & E500_TLB_VALID)) {
kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe);
} else {
@@ -665,35 +654,16 @@
host_tlb_params[0].entries / host_tlb_params[0].ways;
host_tlb_params[1].sets = 1;
- vcpu_e500->tlb_refs[0] =
- kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[0].entries,
- GFP_KERNEL);
- if (!vcpu_e500->tlb_refs[0])
- goto err;
-
- vcpu_e500->tlb_refs[1] =
- kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[1].entries,
- GFP_KERNEL);
- if (!vcpu_e500->tlb_refs[1])
- goto err;
-
vcpu_e500->h2g_tlb1_rmap = kzalloc(sizeof(unsigned int) *
host_tlb_params[1].entries,
GFP_KERNEL);
if (!vcpu_e500->h2g_tlb1_rmap)
- goto err;
+ return -EINVAL;
return 0;
-
-err:
- kfree(vcpu_e500->tlb_refs[0]);
- kfree(vcpu_e500->tlb_refs[1]);
- return -EINVAL;
}
void e500_mmu_host_uninit(struct kvmppc_vcpu_e500 *vcpu_e500)
{
kfree(vcpu_e500->h2g_tlb1_rmap);
- kfree(vcpu_e500->tlb_refs[0]);
- kfree(vcpu_e500->tlb_refs[1]);
}
diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c
index 1f89d26..2f4baa0 100644
--- a/arch/powerpc/kvm/e500mc.c
+++ b/arch/powerpc/kvm/e500mc.c
@@ -108,6 +108,8 @@
{
}
+static DEFINE_PER_CPU(struct kvm_vcpu *, last_vcpu_on_cpu);
+
void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
@@ -136,8 +138,11 @@
mtspr(SPRN_GDEAR, vcpu->arch.shared->dar);
mtspr(SPRN_GESR, vcpu->arch.shared->esr);
- if (vcpu->arch.oldpir != mfspr(SPRN_PIR))
+ if (vcpu->arch.oldpir != mfspr(SPRN_PIR) ||
+ __get_cpu_var(last_vcpu_on_cpu) != vcpu) {
kvmppc_e500_tlbil_all(vcpu_e500);
+ __get_cpu_var(last_vcpu_on_cpu) = vcpu;
+ }
kvmppc_load_guest_fp(vcpu);
}
diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h
index 27cb321..379d96e 100644
--- a/arch/s390/include/asm/io.h
+++ b/arch/s390/include/asm/io.h
@@ -50,10 +50,6 @@
#define ioremap_nocache(addr, size) ioremap(addr, size)
#define ioremap_wc ioremap_nocache
-/* TODO: s390 cannot support io_remap_pfn_range... */
-#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \
- remap_pfn_range(vma, vaddr, pfn, size, prot)
-
static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
{
return (void __iomem *) offset;
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 4a54431..3cb47cf 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -57,6 +57,10 @@
(((unsigned long)(vaddr)) &zero_page_mask))))
#define __HAVE_COLOR_ZERO_PAGE
+/* TODO: s390 cannot support io_remap_pfn_range... */
+#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \
+ remap_pfn_range(vma, vaddr, pfn, size, prot)
+
#endif /* !__ASSEMBLY__ */
/*
diff --git a/block/blk-core.c b/block/blk-core.c
index 074b758..7c28835 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -39,6 +39,7 @@
EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
+EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_unplug);
DEFINE_IDA(blk_queue_ida);
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index f556f8a..b7b7a88 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -1742,9 +1742,10 @@
struct rbd_device *rbd_dev = img_request->rbd_dev;
struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc;
struct rbd_obj_request *obj_request;
+ struct rbd_obj_request *next_obj_request;
dout("%s: img %p\n", __func__, img_request);
- for_each_obj_request(img_request, obj_request) {
+ for_each_obj_request_safe(img_request, obj_request, next_obj_request) {
int ret;
obj_request->callback = rbd_img_obj_callback;
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index 6e13f26..88cfc61 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -310,8 +310,6 @@
dev_vdbg(chan2dev(&atchan->chan_common), "complete all\n");
- BUG_ON(atc_chan_is_enabled(atchan));
-
/*
* Submit queued descriptors ASAP, i.e. before we go through
* the completed ones.
@@ -368,6 +366,9 @@
{
dev_vdbg(chan2dev(&atchan->chan_common), "advance_work\n");
+ if (atc_chan_is_enabled(atchan))
+ return;
+
if (list_empty(&atchan->active_list) ||
list_is_singular(&atchan->active_list)) {
atc_complete_all(atchan);
@@ -1078,9 +1079,7 @@
return;
spin_lock_irqsave(&atchan->lock, flags);
- if (!atc_chan_is_enabled(atchan)) {
- atc_advance_work(atchan);
- }
+ atc_advance_work(atchan);
spin_unlock_irqrestore(&atchan->lock, flags);
}
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 5d66750..1a38dd7 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -465,6 +465,7 @@
ICPU(0x3c, idle_cpu_hsw),
ICPU(0x3f, idle_cpu_hsw),
ICPU(0x45, idle_cpu_hsw),
+ ICPU(0x46, idle_cpu_hsw),
{}
};
MODULE_DEVICE_TABLE(x86cpu, intel_idle_ids);
diff --git a/drivers/input/tablet/wacom_wac.c b/drivers/input/tablet/wacom_wac.c
index 1daa979..49fdff0 100644
--- a/drivers/input/tablet/wacom_wac.c
+++ b/drivers/input/tablet/wacom_wac.c
@@ -1912,7 +1912,7 @@
{ "Wacom Intuos4 12x19", WACOM_PKGLEN_INTUOS, 97536, 60960, 2047,
63, INTUOS4L, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES };
static const struct wacom_features wacom_features_0xBC =
- { "Wacom Intuos4 WL", WACOM_PKGLEN_INTUOS, 40840, 25400, 2047,
+ { "Wacom Intuos4 WL", WACOM_PKGLEN_INTUOS, 40640, 25400, 2047,
63, INTUOS4, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES };
static const struct wacom_features wacom_features_0x26 =
{ "Wacom Intuos5 touch S", WACOM_PKGLEN_INTUOS, 31496, 19685, 2047,
@@ -2209,7 +2209,7 @@
{ USB_DEVICE_WACOM(0x47) },
{ USB_DEVICE_WACOM(0xF4) },
{ USB_DEVICE_WACOM(0xF8) },
- { USB_DEVICE_WACOM(0xF6) },
+ { USB_DEVICE_DETAILED(0xF6, USB_CLASS_HID, 0, 0) },
{ USB_DEVICE_WACOM(0xFA) },
{ USB_DEVICE_LENOVO(0x6004) },
{ }
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index a32e0d5..fc6aebf 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -236,7 +236,8 @@
if (gic_arch_extn.irq_retrigger)
return gic_arch_extn.irq_retrigger(d);
- return -ENXIO;
+ /* the genirq layer expects 0 if we can't retrigger in hardware */
+ return 0;
}
#ifdef CONFIG_SMP
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 7e46926..9a0bdad 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -611,6 +611,7 @@
queue_io(md, bio);
} else {
/* done with normal IO or empty flush */
+ trace_block_bio_complete(md->queue, bio, io_error);
bio_endio(bio, io_error);
}
}
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 24909eb..f4e87bf 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -184,6 +184,8 @@
return_bi = bi->bi_next;
bi->bi_next = NULL;
bi->bi_size = 0;
+ trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
+ bi, 0);
bio_endio(bi, 0);
bi = return_bi;
}
@@ -3914,6 +3916,8 @@
rdev_dec_pending(rdev, conf->mddev);
if (!error && uptodate) {
+ trace_block_bio_complete(bdev_get_queue(raid_bi->bi_bdev),
+ raid_bi, 0);
bio_endio(raid_bi, 0);
if (atomic_dec_and_test(&conf->active_aligned_reads))
wake_up(&conf->wait_for_stripe);
@@ -4382,6 +4386,8 @@
if ( rw == WRITE )
md_write_end(mddev);
+ trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
+ bi, 0);
bio_endio(bi, 0);
}
}
@@ -4758,8 +4764,11 @@
handled++;
}
remaining = raid5_dec_bi_active_stripes(raid_bio);
- if (remaining == 0)
+ if (remaining == 0) {
+ trace_block_bio_complete(bdev_get_queue(raid_bio->bi_bdev),
+ raid_bio, 0);
bio_endio(raid_bio, 0);
+ }
if (atomic_dec_and_test(&conf->active_aligned_reads))
wake_up(&conf->wait_for_stripe);
return handled;
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 07401a3..a61a760 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1906,6 +1906,7 @@
write_unlock_bh(&bond->lock);
err_close:
+ slave_dev->priv_flags &= ~IFF_BONDING;
dev_close(slave_dev);
err_unset_master:
@@ -3168,11 +3169,20 @@
struct net_device *slave_dev)
{
struct slave *slave = bond_slave_get_rtnl(slave_dev);
- struct bonding *bond = slave->bond;
- struct net_device *bond_dev = slave->bond->dev;
+ struct bonding *bond;
+ struct net_device *bond_dev;
u32 old_speed;
u8 old_duplex;
+ /* A netdev event can be generated while enslaving a device
+ * before netdev_rx_handler_register is called in which case
+ * slave will be NULL
+ */
+ if (!slave)
+ return NOTIFY_DONE;
+ bond_dev = slave->bond->dev;
+ bond = slave->bond;
+
switch (event) {
case NETDEV_UNREGISTER:
if (bond->setup_by_slave)
diff --git a/drivers/net/can/mcp251x.c b/drivers/net/can/mcp251x.c
index f32b9fc..9aa0c64 100644
--- a/drivers/net/can/mcp251x.c
+++ b/drivers/net/can/mcp251x.c
@@ -929,6 +929,7 @@
struct mcp251x_priv *priv = netdev_priv(net);
struct spi_device *spi = priv->spi;
struct mcp251x_platform_data *pdata = spi->dev.platform_data;
+ unsigned long flags;
int ret;
ret = open_candev(net);
@@ -945,9 +946,14 @@
priv->tx_skb = NULL;
priv->tx_len = 0;
+ flags = IRQF_ONESHOT;
+ if (pdata->irq_flags)
+ flags |= pdata->irq_flags;
+ else
+ flags |= IRQF_TRIGGER_FALLING;
+
ret = request_threaded_irq(spi->irq, NULL, mcp251x_can_ist,
- pdata->irq_flags ? pdata->irq_flags : IRQF_TRIGGER_FALLING,
- DEVICE_NAME, priv);
+ flags, DEVICE_NAME, priv);
if (ret) {
dev_err(&spi->dev, "failed to acquire irq %d\n", spi->irq);
if (pdata->transceiver_enable)
diff --git a/drivers/net/can/sja1000/sja1000_of_platform.c b/drivers/net/can/sja1000/sja1000_of_platform.c
index 6433b81..8e0c4a0 100644
--- a/drivers/net/can/sja1000/sja1000_of_platform.c
+++ b/drivers/net/can/sja1000/sja1000_of_platform.c
@@ -96,8 +96,8 @@
struct net_device *dev;
struct sja1000_priv *priv;
struct resource res;
- const u32 *prop;
- int err, irq, res_size, prop_size;
+ u32 prop;
+ int err, irq, res_size;
void __iomem *base;
err = of_address_to_resource(np, 0, &res);
@@ -138,27 +138,27 @@
priv->read_reg = sja1000_ofp_read_reg;
priv->write_reg = sja1000_ofp_write_reg;
- prop = of_get_property(np, "nxp,external-clock-frequency", &prop_size);
- if (prop && (prop_size == sizeof(u32)))
- priv->can.clock.freq = *prop / 2;
+ err = of_property_read_u32(np, "nxp,external-clock-frequency", &prop);
+ if (!err)
+ priv->can.clock.freq = prop / 2;
else
priv->can.clock.freq = SJA1000_OFP_CAN_CLOCK; /* default */
- prop = of_get_property(np, "nxp,tx-output-mode", &prop_size);
- if (prop && (prop_size == sizeof(u32)))
- priv->ocr |= *prop & OCR_MODE_MASK;
+ err = of_property_read_u32(np, "nxp,tx-output-mode", &prop);
+ if (!err)
+ priv->ocr |= prop & OCR_MODE_MASK;
else
priv->ocr |= OCR_MODE_NORMAL; /* default */
- prop = of_get_property(np, "nxp,tx-output-config", &prop_size);
- if (prop && (prop_size == sizeof(u32)))
- priv->ocr |= (*prop << OCR_TX_SHIFT) & OCR_TX_MASK;
+ err = of_property_read_u32(np, "nxp,tx-output-config", &prop);
+ if (!err)
+ priv->ocr |= (prop << OCR_TX_SHIFT) & OCR_TX_MASK;
else
priv->ocr |= OCR_TX0_PULLDOWN; /* default */
- prop = of_get_property(np, "nxp,clock-out-frequency", &prop_size);
- if (prop && (prop_size == sizeof(u32)) && *prop) {
- u32 divider = priv->can.clock.freq * 2 / *prop;
+ err = of_property_read_u32(np, "nxp,clock-out-frequency", &prop);
+ if (!err && prop) {
+ u32 divider = priv->can.clock.freq * 2 / prop;
if (divider > 1)
priv->cdr |= divider / 2 - 1;
@@ -168,8 +168,7 @@
priv->cdr |= CDR_CLK_OFF; /* default */
}
- prop = of_get_property(np, "nxp,no-comparator-bypass", NULL);
- if (!prop)
+ if (!of_property_read_bool(np, "nxp,no-comparator-bypass"))
priv->cdr |= CDR_CBP; /* default */
priv->irq_flags = IRQF_SHARED;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 08e54f3..2886c9b 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -759,8 +759,9 @@
if (vlan_tx_tag_present(skb)) {
vlan_tag = be_get_tx_vlan_tag(adapter, skb);
- __vlan_put_tag(skb, vlan_tag);
- skb->vlan_tci = 0;
+ skb = __vlan_put_tag(skb, vlan_tag);
+ if (skb)
+ skb->vlan_tci = 0;
}
return skb;
diff --git a/drivers/net/ethernet/freescale/fec.c b/drivers/net/ethernet/freescale/fec.c
index f292c3a..73195f6 100644
--- a/drivers/net/ethernet/freescale/fec.c
+++ b/drivers/net/ethernet/freescale/fec.c
@@ -1002,6 +1002,7 @@
} else {
if (fep->link) {
fec_stop(ndev);
+ fep->link = phy_dev->link;
status_change = 1;
}
}
diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig
index edfba93..434e33c 100644
--- a/drivers/net/ethernet/marvell/Kconfig
+++ b/drivers/net/ethernet/marvell/Kconfig
@@ -33,6 +33,7 @@
config MVMDIO
tristate "Marvell MDIO interface support"
+ select PHYLIB
---help---
This driver supports the MDIO interface found in the network
interface units of the Marvell EBU SoCs (Kirkwood, Orion5x,
@@ -45,7 +46,6 @@
config MVNETA
tristate "Marvell Armada 370/XP network interface support"
depends on MACH_ARMADA_370_XP
- select PHYLIB
select MVMDIO
---help---
This driver supports the network interface units in the
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 1e628ce..a47a097 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -374,7 +374,6 @@
static int txq_number = 8;
static int rxq_def;
-static int txq_def;
#define MVNETA_DRIVER_NAME "mvneta"
#define MVNETA_DRIVER_VERSION "1.0"
@@ -1475,7 +1474,8 @@
static int mvneta_tx(struct sk_buff *skb, struct net_device *dev)
{
struct mvneta_port *pp = netdev_priv(dev);
- struct mvneta_tx_queue *txq = &pp->txqs[txq_def];
+ u16 txq_id = skb_get_queue_mapping(skb);
+ struct mvneta_tx_queue *txq = &pp->txqs[txq_id];
struct mvneta_tx_desc *tx_desc;
struct netdev_queue *nq;
int frags = 0;
@@ -1485,7 +1485,7 @@
goto out;
frags = skb_shinfo(skb)->nr_frags + 1;
- nq = netdev_get_tx_queue(dev, txq_def);
+ nq = netdev_get_tx_queue(dev, txq_id);
/* Get a descriptor for the first part of the packet */
tx_desc = mvneta_txq_next_desc_get(txq);
@@ -2689,7 +2689,7 @@
return -EINVAL;
}
- dev = alloc_etherdev_mq(sizeof(struct mvneta_port), 8);
+ dev = alloc_etherdev_mqs(sizeof(struct mvneta_port), txq_number, rxq_number);
if (!dev)
return -ENOMEM;
@@ -2844,4 +2844,3 @@
module_param(txq_number, int, S_IRUGO);
module_param(rxq_def, int, S_IRUGO);
-module_param(txq_def, int, S_IRUGO);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
index 987fb6f..5ef328a 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
@@ -200,10 +200,10 @@
}
err = qlcnic_config_led(adapter, b_state, b_rate);
- if (!err)
+ if (!err) {
err = len;
- else
ahw->beacon_state = b_state;
+ }
if (test_and_clear_bit(__QLCNIC_DIAG_RES_ALLOC, &adapter->state))
qlcnic_diag_free_res(adapter->netdev, max_sds_rings);
diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
index 0c74a70..50617c5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
@@ -149,6 +149,7 @@
{
writel(MMC_DEFAULT_MASK, ioaddr + MMC_RX_INTR_MASK);
writel(MMC_DEFAULT_MASK, ioaddr + MMC_TX_INTR_MASK);
+ writel(MMC_DEFAULT_MASK, ioaddr + MMC_RX_IPC_INTR_MASK);
}
/* This reads the MAC core counters (if actaully supported).
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 80cad06..4781d3d 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1380,7 +1380,7 @@
memcpy(slave_data->mac_addr, mac_addr, ETH_ALEN);
if (data->dual_emac) {
- if (of_property_read_u32(node, "dual_emac_res_vlan",
+ if (of_property_read_u32(slave_node, "dual_emac_res_vlan",
&prop)) {
pr_err("Missing dual_emac_res_vlan in DT.\n");
slave_data->dual_emac_res_vlan = i+1;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index b7c457a..729ed53 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1594,7 +1594,7 @@
if (tun->flags & TUN_TAP_MQ &&
(tun->numqueues + tun->numdisabled > 1))
- return err;
+ return -EBUSY;
}
else {
char *name;
diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index 16c8429..6bd91676 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -134,7 +134,7 @@
goto error;
if (skb) {
- if (skb->len <= sizeof(ETH_HLEN))
+ if (skb->len <= ETH_HLEN)
goto error;
/* mapping VLANs to MBIM sessions:
diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c
index 45cacf7..1a779bb 100644
--- a/drivers/platform/x86/hp-wmi.c
+++ b/drivers/platform/x86/hp-wmi.c
@@ -134,7 +134,6 @@
{ KE_KEY, 0x2142, { KEY_MEDIA } },
{ KE_KEY, 0x213b, { KEY_INFO } },
{ KE_KEY, 0x2169, { KEY_DIRECTION } },
- { KE_KEY, 0x216a, { KEY_SETUP } },
{ KE_KEY, 0x231b, { KEY_HELP } },
{ KE_END, 0 }
};
@@ -925,9 +924,6 @@
err = hp_wmi_input_setup();
if (err)
return err;
-
- //Enable magic for hotkeys that run on the SMBus
- ec_write(0xe6,0x6e);
}
if (bios_capable) {
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 9a90756..edec135 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -1964,9 +1964,6 @@
/* kthread for the hotkey poller */
static struct task_struct *tpacpi_hotkey_task;
-/* Acquired while the poller kthread is running, use to sync start/stop */
-static struct mutex hotkey_thread_mutex;
-
/*
* Acquire mutex to write poller control variables as an
* atomic block.
@@ -2462,8 +2459,6 @@
unsigned int poll_freq;
bool was_frozen;
- mutex_lock(&hotkey_thread_mutex);
-
if (tpacpi_lifecycle == TPACPI_LIFE_EXITING)
goto exit;
@@ -2523,7 +2518,6 @@
}
exit:
- mutex_unlock(&hotkey_thread_mutex);
return 0;
}
@@ -2533,9 +2527,6 @@
if (tpacpi_hotkey_task) {
kthread_stop(tpacpi_hotkey_task);
tpacpi_hotkey_task = NULL;
- mutex_lock(&hotkey_thread_mutex);
- /* at this point, the thread did exit */
- mutex_unlock(&hotkey_thread_mutex);
}
}
@@ -3234,7 +3225,6 @@
mutex_init(&hotkey_mutex);
#ifdef CONFIG_THINKPAD_ACPI_HOTKEY_POLL
- mutex_init(&hotkey_thread_mutex);
mutex_init(&hotkey_thread_data_mutex);
#endif
diff --git a/drivers/video/mmp/core.c b/drivers/video/mmp/core.c
index 9ed8341..84de263 100644
--- a/drivers/video/mmp/core.c
+++ b/drivers/video/mmp/core.c
@@ -252,7 +252,5 @@
kfree(path);
mutex_unlock(&disp_lock);
-
- dev_info(path->dev, "de-register %s\n", path->name);
}
EXPORT_SYMBOL_GPL(mmp_unregister_path);
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 3939829..86af964 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1137,6 +1137,7 @@
goto whole;
if (!(vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_PRIVATE))
goto whole;
+ return 0;
}
/* Do not dump I/O mapped devices or special mappings */
diff --git a/fs/bio.c b/fs/bio.c
index bb5768f..b96fc6c 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -1428,8 +1428,6 @@
else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
error = -EIO;
- trace_block_bio_complete(bio, error);
-
if (bio->bi_end_io)
bio->bi_end_io(bio, error);
}
diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c
index a94f0f7..fe0a762 100644
--- a/fs/hfsplus/extents.c
+++ b/fs/hfsplus/extents.c
@@ -533,7 +533,7 @@
struct address_space *mapping = inode->i_mapping;
struct page *page;
void *fsdata;
- u32 size = inode->i_size;
+ loff_t size = inode->i_size;
res = pagecache_write_begin(NULL, mapping, size, 0,
AOP_FLAG_UNINTERRUPTIBLE,
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 84e3d85..523464e 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -110,7 +110,7 @@
* way when do_mmap_pgoff unwinds (may be important on powerpc
* and ia64).
*/
- vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND | VM_DONTDUMP;
+ vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND;
vma->vm_ops = &hugetlb_vm_ops;
if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))
diff --git a/fs/proc/array.c b/fs/proc/array.c
index f7ed9ee..cbd0f1b 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -143,6 +143,7 @@
"x (dead)", /* 64 */
"K (wakekill)", /* 128 */
"W (waking)", /* 256 */
+ "P (parked)", /* 512 */
};
static inline const char *get_task_state(struct task_struct *tsk)
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index 0ea61e0..7c2e030 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -12,7 +12,6 @@
struct blk_trace {
int trace_state;
- bool rq_based;
struct rchan *rchan;
unsigned long __percpu *sequence;
unsigned char __percpu *msg_data;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index e19ff30..e2091b8 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1611,6 +1611,8 @@
unsigned long pfn);
int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn);
+int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len);
+
struct page *follow_page_mask(struct vm_area_struct *vma,
unsigned long address, unsigned int foll_flags,
diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h
index 01d25e6..0214c4c 100644
--- a/include/linux/netfilter/ipset/ip_set_ahash.h
+++ b/include/linux/netfilter/ipset/ip_set_ahash.h
@@ -291,6 +291,7 @@
#define type_pf_data_tlist TOKEN(TYPE, PF, _data_tlist)
#define type_pf_data_next TOKEN(TYPE, PF, _data_next)
#define type_pf_data_flags TOKEN(TYPE, PF, _data_flags)
+#define type_pf_data_reset_flags TOKEN(TYPE, PF, _data_reset_flags)
#ifdef IP_SET_HASH_WITH_NETS
#define type_pf_data_match TOKEN(TYPE, PF, _data_match)
#else
@@ -385,9 +386,9 @@
struct ip_set_hash *h = set->data;
struct htable *t, *orig = h->table;
u8 htable_bits = orig->htable_bits;
- const struct type_pf_elem *data;
+ struct type_pf_elem *data;
struct hbucket *n, *m;
- u32 i, j;
+ u32 i, j, flags = 0;
int ret;
retry:
@@ -412,9 +413,16 @@
n = hbucket(orig, i);
for (j = 0; j < n->pos; j++) {
data = ahash_data(n, j);
+#ifdef IP_SET_HASH_WITH_NETS
+ flags = 0;
+ type_pf_data_reset_flags(data, &flags);
+#endif
m = hbucket(t, HKEY(data, h->initval, htable_bits));
- ret = type_pf_elem_add(m, data, AHASH_MAX(h), 0);
+ ret = type_pf_elem_add(m, data, AHASH_MAX(h), flags);
if (ret < 0) {
+#ifdef IP_SET_HASH_WITH_NETS
+ type_pf_data_flags(data, flags);
+#endif
read_unlock_bh(&set->lock);
ahash_destroy(t);
if (ret == -EAGAIN)
@@ -836,9 +844,9 @@
struct ip_set_hash *h = set->data;
struct htable *t, *orig = h->table;
u8 htable_bits = orig->htable_bits;
- const struct type_pf_elem *data;
+ struct type_pf_elem *data;
struct hbucket *n, *m;
- u32 i, j;
+ u32 i, j, flags = 0;
int ret;
/* Try to cleanup once */
@@ -873,10 +881,17 @@
n = hbucket(orig, i);
for (j = 0; j < n->pos; j++) {
data = ahash_tdata(n, j);
+#ifdef IP_SET_HASH_WITH_NETS
+ flags = 0;
+ type_pf_data_reset_flags(data, &flags);
+#endif
m = hbucket(t, HKEY(data, h->initval, htable_bits));
- ret = type_pf_elem_tadd(m, data, AHASH_MAX(h), 0,
- ip_set_timeout_get(type_pf_data_timeout(data)));
+ ret = type_pf_elem_tadd(m, data, AHASH_MAX(h), flags,
+ ip_set_timeout_get(type_pf_data_timeout(data)));
if (ret < 0) {
+#ifdef IP_SET_HASH_WITH_NETS
+ type_pf_data_flags(data, flags);
+#endif
read_unlock_bh(&set->lock);
ahash_destroy(t);
if (ret == -EAGAIN)
@@ -1187,6 +1202,7 @@
#undef type_pf_data_tlist
#undef type_pf_data_next
#undef type_pf_data_flags
+#undef type_pf_data_reset_flags
#undef type_pf_data_match
#undef type_pf_elem
diff --git a/include/linux/sched.h b/include/linux/sched.h
index d35d2b6..e692a02 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -163,9 +163,10 @@
#define TASK_DEAD 64
#define TASK_WAKEKILL 128
#define TASK_WAKING 256
-#define TASK_STATE_MAX 512
+#define TASK_PARKED 512
+#define TASK_STATE_MAX 1024
-#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKW"
+#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP"
extern char ___assert_task_state[1 - 2*!!(
sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)];
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 40be2a0..84a6440 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -199,6 +199,7 @@
/* Device notifier */
extern int register_inet6addr_notifier(struct notifier_block *nb);
extern int unregister_inet6addr_notifier(struct notifier_block *nb);
+extern int inet6addr_notifier_call_chain(unsigned long val, void *v);
extern void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex,
struct ipv6_devconf *devconf);
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index 9961726..9c14673 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -257,6 +257,7 @@
/**
* block_bio_complete - completed all work on the block operation
+ * @q: queue holding the block operation
* @bio: block operation completed
* @error: io error value
*
@@ -265,9 +266,9 @@
*/
TRACE_EVENT(block_bio_complete,
- TP_PROTO(struct bio *bio, int error),
+ TP_PROTO(struct request_queue *q, struct bio *bio, int error),
- TP_ARGS(bio, error),
+ TP_ARGS(q, bio, error),
TP_STRUCT__entry(
__field( dev_t, dev )
@@ -278,8 +279,7 @@
),
TP_fast_assign(
- __entry->dev = bio->bi_bdev ?
- bio->bi_bdev->bd_dev : 0;
+ __entry->dev = bio->bi_bdev->bd_dev;
__entry->sector = bio->bi_sector;
__entry->nr_sector = bio->bi_size >> 9;
__entry->error = error;
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 5a8671e..e5586ca 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -147,7 +147,7 @@
__print_flags(__entry->prev_state & (TASK_STATE_MAX-1), "|",
{ 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" },
{ 16, "Z" }, { 32, "X" }, { 64, "x" },
- { 128, "W" }) : "R",
+ { 128, "K" }, { 256, "W" }, { 512, "P" }) : "R",
__entry->prev_state & TASK_STATE_MAX ? "+" : "",
__entry->next_comm, __entry->next_pid, __entry->next_prio)
);
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index cc47812..14be27f 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -63,6 +63,7 @@
DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
{
+ .lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock),
.clock_base =
{
{
@@ -1642,8 +1643,6 @@
struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu);
int i;
- raw_spin_lock_init(&cpu_base->lock);
-
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
cpu_base->clock_base[i].cpu_base = cpu_base;
timerqueue_init_head(&cpu_base->clock_base[i].active);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index e35be53..3fed7f0 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -794,16 +794,16 @@
}
#ifdef CONFIG_SYSCTL
-/* This should be called with kprobe_mutex locked */
static void __kprobes optimize_all_kprobes(void)
{
struct hlist_head *head;
struct kprobe *p;
unsigned int i;
+ mutex_lock(&kprobe_mutex);
/* If optimization is already allowed, just return */
if (kprobes_allow_optimization)
- return;
+ goto out;
kprobes_allow_optimization = true;
for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
@@ -813,18 +813,22 @@
optimize_kprobe(p);
}
printk(KERN_INFO "Kprobes globally optimized\n");
+out:
+ mutex_unlock(&kprobe_mutex);
}
-/* This should be called with kprobe_mutex locked */
static void __kprobes unoptimize_all_kprobes(void)
{
struct hlist_head *head;
struct kprobe *p;
unsigned int i;
+ mutex_lock(&kprobe_mutex);
/* If optimization is already prohibited, just return */
- if (!kprobes_allow_optimization)
+ if (!kprobes_allow_optimization) {
+ mutex_unlock(&kprobe_mutex);
return;
+ }
kprobes_allow_optimization = false;
for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
@@ -834,11 +838,14 @@
unoptimize_kprobe(p, false);
}
}
+ mutex_unlock(&kprobe_mutex);
+
/* Wait for unoptimizing completion */
wait_for_kprobe_optimizer();
printk(KERN_INFO "Kprobes globally unoptimized\n");
}
+static DEFINE_MUTEX(kprobe_sysctl_mutex);
int sysctl_kprobes_optimization;
int proc_kprobes_optimization_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length,
@@ -846,7 +853,7 @@
{
int ret;
- mutex_lock(&kprobe_mutex);
+ mutex_lock(&kprobe_sysctl_mutex);
sysctl_kprobes_optimization = kprobes_allow_optimization ? 1 : 0;
ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
@@ -854,7 +861,7 @@
optimize_all_kprobes();
else
unoptimize_all_kprobes();
- mutex_unlock(&kprobe_mutex);
+ mutex_unlock(&kprobe_sysctl_mutex);
return ret;
}
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 691dc2e..9eb7fed 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -124,12 +124,12 @@
static void __kthread_parkme(struct kthread *self)
{
- __set_current_state(TASK_INTERRUPTIBLE);
+ __set_current_state(TASK_PARKED);
while (test_bit(KTHREAD_SHOULD_PARK, &self->flags)) {
if (!test_and_set_bit(KTHREAD_IS_PARKED, &self->flags))
complete(&self->parked);
schedule();
- __set_current_state(TASK_INTERRUPTIBLE);
+ __set_current_state(TASK_PARKED);
}
clear_bit(KTHREAD_IS_PARKED, &self->flags);
__set_current_state(TASK_RUNNING);
@@ -256,8 +256,13 @@
}
EXPORT_SYMBOL(kthread_create_on_node);
-static void __kthread_bind(struct task_struct *p, unsigned int cpu)
+static void __kthread_bind(struct task_struct *p, unsigned int cpu, long state)
{
+ /* Must have done schedule() in kthread() before we set_task_cpu */
+ if (!wait_task_inactive(p, state)) {
+ WARN_ON(1);
+ return;
+ }
/* It's safe because the task is inactive. */
do_set_cpus_allowed(p, cpumask_of(cpu));
p->flags |= PF_THREAD_BOUND;
@@ -274,12 +279,7 @@
*/
void kthread_bind(struct task_struct *p, unsigned int cpu)
{
- /* Must have done schedule() in kthread() before we set_task_cpu */
- if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE)) {
- WARN_ON(1);
- return;
- }
- __kthread_bind(p, cpu);
+ __kthread_bind(p, cpu, TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(kthread_bind);
@@ -324,6 +324,22 @@
return NULL;
}
+static void __kthread_unpark(struct task_struct *k, struct kthread *kthread)
+{
+ clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+ /*
+ * We clear the IS_PARKED bit here as we don't wait
+ * until the task has left the park code. So if we'd
+ * park before that happens we'd see the IS_PARKED bit
+ * which might be about to be cleared.
+ */
+ if (test_and_clear_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
+ if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
+ __kthread_bind(k, kthread->cpu, TASK_PARKED);
+ wake_up_state(k, TASK_PARKED);
+ }
+}
+
/**
* kthread_unpark - unpark a thread created by kthread_create().
* @k: thread created by kthread_create().
@@ -336,20 +352,8 @@
{
struct kthread *kthread = task_get_live_kthread(k);
- if (kthread) {
- clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
- /*
- * We clear the IS_PARKED bit here as we don't wait
- * until the task has left the park code. So if we'd
- * park before that happens we'd see the IS_PARKED bit
- * which might be about to be cleared.
- */
- if (test_and_clear_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
- if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
- __kthread_bind(k, kthread->cpu);
- wake_up_process(k);
- }
- }
+ if (kthread)
+ __kthread_unpark(k, kthread);
put_task_struct(k);
}
@@ -407,7 +411,7 @@
trace_sched_kthread_stop(k);
if (kthread) {
set_bit(KTHREAD_SHOULD_STOP, &kthread->flags);
- clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+ __kthread_unpark(k, kthread);
wake_up_process(k);
wait_for_completion(&kthread->exited);
}
diff --git a/kernel/signal.c b/kernel/signal.c
index dd72567..598dc06 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2948,7 +2948,7 @@
static int do_tkill(pid_t tgid, pid_t pid, int sig)
{
- struct siginfo info;
+ struct siginfo info = {};
info.si_signo = sig;
info.si_errno = 0;
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index 8eaed9a..02fc5c9 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -185,8 +185,18 @@
}
get_task_struct(tsk);
*per_cpu_ptr(ht->store, cpu) = tsk;
- if (ht->create)
- ht->create(cpu);
+ if (ht->create) {
+ /*
+ * Make sure that the task has actually scheduled out
+ * into park position, before calling the create
+ * callback. At least the migration thread callback
+ * requires that the task is off the runqueue.
+ */
+ if (!wait_task_inactive(tsk, TASK_PARKED))
+ WARN_ON(1);
+ else
+ ht->create(cpu);
+ }
return 0;
}
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 9e5b8c2..5a0f781 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -739,12 +739,6 @@
struct request_queue *q,
struct request *rq)
{
- struct blk_trace *bt = q->blk_trace;
-
- /* if control ever passes through here, it's a request based driver */
- if (unlikely(bt && !bt->rq_based))
- bt->rq_based = true;
-
blk_add_trace_rq(q, rq, BLK_TA_COMPLETE);
}
@@ -780,24 +774,10 @@
blk_add_trace_bio(q, bio, BLK_TA_BOUNCE, 0);
}
-static void blk_add_trace_bio_complete(void *ignore, struct bio *bio, int error)
+static void blk_add_trace_bio_complete(void *ignore,
+ struct request_queue *q, struct bio *bio,
+ int error)
{
- struct request_queue *q;
- struct blk_trace *bt;
-
- if (!bio->bi_bdev)
- return;
-
- q = bdev_get_queue(bio->bi_bdev);
- bt = q->blk_trace;
-
- /*
- * Request based drivers will generate both rq and bio completions.
- * Ignore bio ones.
- */
- if (likely(!bt) || bt->rq_based)
- return;
-
blk_add_trace_bio(q, bio, BLK_TA_COMPLETE, error);
}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ca9a7c6..1a12f5b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2961,7 +2961,17 @@
break;
}
- if (absent ||
+ /*
+ * We need call hugetlb_fault for both hugepages under migration
+ * (in which case hugetlb_fault waits for the migration,) and
+ * hwpoisoned hugepages (in which case we need to prevent the
+ * caller from accessing to them.) In order to do this, we use
+ * here is_swap_pte instead of is_hugetlb_entry_migration and
+ * is_hugetlb_entry_hwpoisoned. This is because it simply covers
+ * both cases, and because we can't follow correct pages
+ * directly from any kind of swap entries.
+ */
+ if (absent || is_swap_pte(huge_ptep_get(pte)) ||
((flags & FOLL_WRITE) && !pte_write(huge_ptep_get(pte)))) {
int ret;
diff --git a/mm/memory.c b/mm/memory.c
index 13cbc42..ba94dec 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2393,6 +2393,53 @@
}
EXPORT_SYMBOL(remap_pfn_range);
+/**
+ * vm_iomap_memory - remap memory to userspace
+ * @vma: user vma to map to
+ * @start: start of area
+ * @len: size of area
+ *
+ * This is a simplified io_remap_pfn_range() for common driver use. The
+ * driver just needs to give us the physical memory range to be mapped,
+ * we'll figure out the rest from the vma information.
+ *
+ * NOTE! Some drivers might want to tweak vma->vm_page_prot first to get
+ * whatever write-combining details or similar.
+ */
+int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len)
+{
+ unsigned long vm_len, pfn, pages;
+
+ /* Check that the physical memory area passed in looks valid */
+ if (start + len < start)
+ return -EINVAL;
+ /*
+ * You *really* shouldn't map things that aren't page-aligned,
+ * but we've historically allowed it because IO memory might
+ * just have smaller alignment.
+ */
+ len += start & ~PAGE_MASK;
+ pfn = start >> PAGE_SHIFT;
+ pages = (len + ~PAGE_MASK) >> PAGE_SHIFT;
+ if (pfn + pages < pfn)
+ return -EINVAL;
+
+ /* We start the mapping 'vm_pgoff' pages into the area */
+ if (vma->vm_pgoff > pages)
+ return -EINVAL;
+ pfn += vma->vm_pgoff;
+ pages -= vma->vm_pgoff;
+
+ /* Can we fit all of the mapping? */
+ vm_len = vma->vm_end - vma->vm_start;
+ if (vm_len >> PAGE_SHIFT > pages)
+ return -EINVAL;
+
+ /* Ok, let it rip */
+ return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot);
+}
+EXPORT_SYMBOL(vm_iomap_memory);
+
static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
unsigned long addr, unsigned long end,
pte_fn_t fn, void *data)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 88c5fed..669fba3 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3188,9 +3188,9 @@
if (IS_ERR(pgdat->kswapd)) {
/* failure at boot is fatal */
BUG_ON(system_state == SYSTEM_BOOTING);
- pgdat->kswapd = NULL;
pr_err("Failed to start kswapd on node %d\n", nid);
ret = PTR_ERR(pgdat->kswapd);
+ pgdat->kswapd = NULL;
}
return ret;
}
diff --git a/net/802/mrp.c b/net/802/mrp.c
index a4cc322..e085bcc 100644
--- a/net/802/mrp.c
+++ b/net/802/mrp.c
@@ -870,8 +870,12 @@
* all pending messages before the applicant is gone.
*/
del_timer_sync(&app->join_timer);
+
+ spin_lock(&app->lock);
mrp_mad_event(app, MRP_EVENT_TX);
mrp_pdu_queue(app);
+ spin_unlock(&app->lock);
+
mrp_queue_xmit(app);
dev_mc_del(dev, appl->group_address);
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index ef1b914..459dab2 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -67,7 +67,8 @@
struct net_device *dev = p->dev;
struct net_bridge *br = p->br;
- if (netif_running(dev) && netif_oper_up(dev))
+ if (!(p->flags & BR_ADMIN_COST) &&
+ netif_running(dev) && netif_oper_up(dev))
p->path_cost = port_cost(dev);
if (!netif_running(br->dev))
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 3cbf5be..d2c043a 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -156,6 +156,7 @@
#define BR_BPDU_GUARD 0x00000002
#define BR_ROOT_BLOCK 0x00000004
#define BR_MULTICAST_FAST_LEAVE 0x00000008
+#define BR_ADMIN_COST 0x00000010
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
u32 multicast_startup_queries_sent;
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 0bdb4eb..d45e760 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -288,6 +288,7 @@
path_cost > BR_MAX_PATH_COST)
return -ERANGE;
+ p->flags |= BR_ADMIN_COST;
p->path_cost = path_cost;
br_configuration_update(p->br);
br_port_state_selection(p->br);
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 3b4f0cd..4cfe34d 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -139,8 +139,6 @@
/* skb is pure payload to encrypt */
- err = -ENOMEM;
-
esp = x->data;
aead = esp->aead;
alen = crypto_aead_authsize(aead);
@@ -176,8 +174,10 @@
}
tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen);
- if (!tmp)
+ if (!tmp) {
+ err = -ENOMEM;
goto error;
+ }
seqhi = esp_tmp_seqhi(tmp);
iv = esp_tmp_iv(aead, tmp, seqhilen);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index a6445b8..52c273e 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -248,8 +248,7 @@
if (!head->dev)
goto out_rcu_unlock;
- /* skb dst is stale, drop it, and perform route lookup again */
- skb_dst_drop(head);
+ /* skb has no dst, perform route lookup again */
iph = ip_hdr(head);
err = ip_route_input_noref(head, iph->daddr, iph->saddr,
iph->tos, head->dev);
@@ -523,9 +522,16 @@
qp->q.max_size = skb->len + ihl;
if (qp->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
- qp->q.meat == qp->q.len)
- return ip_frag_reasm(qp, prev, dev);
+ qp->q.meat == qp->q.len) {
+ unsigned long orefdst = skb->_skb_refdst;
+ skb->_skb_refdst = 0UL;
+ err = ip_frag_reasm(qp, prev, dev);
+ skb->_skb_refdst = orefdst;
+ return err;
+ }
+
+ skb_dst_drop(skb);
inet_frag_lru_move(&qp->q);
return -EINPROGRESS;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index ef54377..397e0f6 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -349,8 +349,8 @@
* hasn't changed since we received the original syn, but I see
* no easy way to do this.
*/
- flowi4_init_output(&fl4, 0, sk->sk_mark, RT_CONN_FLAGS(sk),
- RT_SCOPE_UNIVERSE, IPPROTO_TCP,
+ flowi4_init_output(&fl4, sk->sk_bound_dev_if, sk->sk_mark,
+ RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP,
inet_sk_flowi_flags(sk),
(opt && opt->srr) ? opt->faddr : ireq->rmt_addr,
ireq->loc_addr, th->source, th->dest);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index b44cf81..509912a 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2388,8 +2388,12 @@
*/
TCP_SKB_CB(skb)->when = tcp_time_stamp;
- /* make sure skb->data is aligned on arches that require it */
- if (unlikely(NET_IP_ALIGN && ((unsigned long)skb->data & 3))) {
+ /* make sure skb->data is aligned on arches that require it
+ * and check if ack-trimming & collapsing extended the headroom
+ * beyond what csum_start can cover.
+ */
+ if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) ||
+ skb_headroom(skb) >= 0xFFFF)) {
struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER,
GFP_ATOMIC);
return nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index a459c4f..dae802c 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -168,8 +168,6 @@
static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr,
struct net_device *dev);
-static ATOMIC_NOTIFIER_HEAD(inet6addr_chain);
-
static struct ipv6_devconf ipv6_devconf __read_mostly = {
.forwarding = 0,
.hop_limit = IPV6_DEFAULT_HOPLIMIT,
@@ -837,7 +835,7 @@
rcu_read_unlock_bh();
if (likely(err == 0))
- atomic_notifier_call_chain(&inet6addr_chain, NETDEV_UP, ifa);
+ inet6addr_notifier_call_chain(NETDEV_UP, ifa);
else {
kfree(ifa);
ifa = ERR_PTR(err);
@@ -927,7 +925,7 @@
ipv6_ifa_notify(RTM_DELADDR, ifp);
- atomic_notifier_call_chain(&inet6addr_chain, NETDEV_DOWN, ifp);
+ inet6addr_notifier_call_chain(NETDEV_DOWN, ifp);
/*
* Purge or update corresponding prefix
@@ -2988,7 +2986,7 @@
if (state != INET6_IFADDR_STATE_DEAD) {
__ipv6_ifa_notify(RTM_DELADDR, ifa);
- atomic_notifier_call_chain(&inet6addr_chain, NETDEV_DOWN, ifa);
+ inet6addr_notifier_call_chain(NETDEV_DOWN, ifa);
}
in6_ifa_put(ifa);
@@ -4869,22 +4867,6 @@
.exit = addrconf_exit_net,
};
-/*
- * Device notifier
- */
-
-int register_inet6addr_notifier(struct notifier_block *nb)
-{
- return atomic_notifier_chain_register(&inet6addr_chain, nb);
-}
-EXPORT_SYMBOL(register_inet6addr_notifier);
-
-int unregister_inet6addr_notifier(struct notifier_block *nb)
-{
- return atomic_notifier_chain_unregister(&inet6addr_chain, nb);
-}
-EXPORT_SYMBOL(unregister_inet6addr_notifier);
-
static struct rtnl_af_ops inet6_ops = {
.family = AF_INET6,
.fill_link_af = inet6_fill_link_af,
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index d051e5f..7210456 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -78,3 +78,22 @@
}
EXPORT_SYMBOL(__ipv6_addr_type);
+static ATOMIC_NOTIFIER_HEAD(inet6addr_chain);
+
+int register_inet6addr_notifier(struct notifier_block *nb)
+{
+ return atomic_notifier_chain_register(&inet6addr_chain, nb);
+}
+EXPORT_SYMBOL(register_inet6addr_notifier);
+
+int unregister_inet6addr_notifier(struct notifier_block *nb)
+{
+ return atomic_notifier_chain_unregister(&inet6addr_chain, nb);
+}
+EXPORT_SYMBOL(unregister_inet6addr_notifier);
+
+int inet6addr_notifier_call_chain(unsigned long val, void *v)
+{
+ return atomic_notifier_call_chain(&inet6addr_chain, val, v);
+}
+EXPORT_SYMBOL(inet6addr_notifier_call_chain);
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 196ab93..0ba10e5 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -330,9 +330,17 @@
}
if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
- fq->q.meat == fq->q.len)
- return ip6_frag_reasm(fq, prev, dev);
+ fq->q.meat == fq->q.len) {
+ int res;
+ unsigned long orefdst = skb->_skb_refdst;
+ skb->_skb_refdst = 0UL;
+ res = ip6_frag_reasm(fq, prev, dev);
+ skb->_skb_refdst = orefdst;
+ return res;
+ }
+
+ skb_dst_drop(skb);
inet_frag_lru_move(&fq->q);
return -1;
diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c
index f262722..10a30b4 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c
@@ -104,6 +104,15 @@
dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
}
+static inline void
+hash_ipportnet4_data_reset_flags(struct hash_ipportnet4_elem *dst, u32 *flags)
+{
+ if (dst->nomatch) {
+ *flags = IPSET_FLAG_NOMATCH;
+ dst->nomatch = 0;
+ }
+}
+
static inline int
hash_ipportnet4_data_match(const struct hash_ipportnet4_elem *elem)
{
@@ -414,6 +423,15 @@
dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
}
+static inline void
+hash_ipportnet6_data_reset_flags(struct hash_ipportnet6_elem *dst, u32 *flags)
+{
+ if (dst->nomatch) {
+ *flags = IPSET_FLAG_NOMATCH;
+ dst->nomatch = 0;
+ }
+}
+
static inline int
hash_ipportnet6_data_match(const struct hash_ipportnet6_elem *elem)
{
diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c
index 4b677cf..d6a5915 100644
--- a/net/netfilter/ipset/ip_set_hash_net.c
+++ b/net/netfilter/ipset/ip_set_hash_net.c
@@ -87,7 +87,16 @@
static inline void
hash_net4_data_flags(struct hash_net4_elem *dst, u32 flags)
{
- dst->nomatch = flags & IPSET_FLAG_NOMATCH;
+ dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
+}
+
+static inline void
+hash_net4_data_reset_flags(struct hash_net4_elem *dst, u32 *flags)
+{
+ if (dst->nomatch) {
+ *flags = IPSET_FLAG_NOMATCH;
+ dst->nomatch = 0;
+ }
}
static inline int
@@ -308,7 +317,16 @@
static inline void
hash_net6_data_flags(struct hash_net6_elem *dst, u32 flags)
{
- dst->nomatch = flags & IPSET_FLAG_NOMATCH;
+ dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
+}
+
+static inline void
+hash_net6_data_reset_flags(struct hash_net6_elem *dst, u32 *flags)
+{
+ if (dst->nomatch) {
+ *flags = IPSET_FLAG_NOMATCH;
+ dst->nomatch = 0;
+ }
}
static inline int
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index 6ba985f..f2b0a3c 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -198,7 +198,16 @@
static inline void
hash_netiface4_data_flags(struct hash_netiface4_elem *dst, u32 flags)
{
- dst->nomatch = flags & IPSET_FLAG_NOMATCH;
+ dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
+}
+
+static inline void
+hash_netiface4_data_reset_flags(struct hash_netiface4_elem *dst, u32 *flags)
+{
+ if (dst->nomatch) {
+ *flags = IPSET_FLAG_NOMATCH;
+ dst->nomatch = 0;
+ }
}
static inline int
@@ -494,7 +503,7 @@
static inline void
hash_netiface6_data_flags(struct hash_netiface6_elem *dst, u32 flags)
{
- dst->nomatch = flags & IPSET_FLAG_NOMATCH;
+ dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
}
static inline int
@@ -504,6 +513,15 @@
}
static inline void
+hash_netiface6_data_reset_flags(struct hash_netiface6_elem *dst, u32 *flags)
+{
+ if (dst->nomatch) {
+ *flags = IPSET_FLAG_NOMATCH;
+ dst->nomatch = 0;
+ }
+}
+
+static inline void
hash_netiface6_data_zero_out(struct hash_netiface6_elem *elem)
{
elem->elem = 0;
diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c
index af20c0c..349deb6 100644
--- a/net/netfilter/ipset/ip_set_hash_netport.c
+++ b/net/netfilter/ipset/ip_set_hash_netport.c
@@ -104,6 +104,15 @@
dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
}
+static inline void
+hash_netport4_data_reset_flags(struct hash_netport4_elem *dst, u32 *flags)
+{
+ if (dst->nomatch) {
+ *flags = IPSET_FLAG_NOMATCH;
+ dst->nomatch = 0;
+ }
+}
+
static inline int
hash_netport4_data_match(const struct hash_netport4_elem *elem)
{
@@ -375,6 +384,15 @@
dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
}
+static inline void
+hash_netport6_data_reset_flags(struct hash_netport6_elem *dst, u32 *flags)
+{
+ if (dst->nomatch) {
+ *flags = IPSET_FLAG_NOMATCH;
+ dst->nomatch = 0;
+ }
+}
+
static inline int
hash_netport6_data_match(const struct hash_netport6_elem *elem)
{
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index 8371c2b..09c744a 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -174,9 +174,13 @@
{
const struct set_elem *e = list_set_elem(map, i);
- if (i == map->size - 1 && e->id != IPSET_INVALID_ID)
- /* Last element replaced: e.g. add new,before,last */
- ip_set_put_byindex(e->id);
+ if (e->id != IPSET_INVALID_ID) {
+ const struct set_elem *x = list_set_elem(map, map->size - 1);
+
+ /* Last element replaced or pushed off */
+ if (x->id != IPSET_INVALID_ID)
+ ip_set_put_byindex(x->id);
+ }
if (with_timeout(map->timeout))
list_elem_tadd(map, i, id, ip_set_timeout_set(timeout));
else
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 0e7d423..e0c4373 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -1593,10 +1593,8 @@
end += strlen("\r\n\r\n") + clen;
msglen = origlen = end - dptr;
- if (msglen > datalen) {
- nf_ct_helper_log(skb, ct, "incomplete/bad SIP message");
- return NF_DROP;
- }
+ if (msglen > datalen)
+ return NF_ACCEPT;
ret = process_sip_msg(skb, ct, protoff, dataoff,
&dptr, &msglen);
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 8d5769c..ad24be0 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -467,33 +467,22 @@
struct nf_nat_proto_clean {
u8 l3proto;
u8 l4proto;
- bool hash;
};
-/* Clear NAT section of all conntracks, in case we're loaded again. */
-static int nf_nat_proto_clean(struct nf_conn *i, void *data)
+/* kill conntracks with affected NAT section */
+static int nf_nat_proto_remove(struct nf_conn *i, void *data)
{
const struct nf_nat_proto_clean *clean = data;
struct nf_conn_nat *nat = nfct_nat(i);
if (!nat)
return 0;
- if (!(i->status & IPS_SRC_NAT_DONE))
- return 0;
+
if ((clean->l3proto && nf_ct_l3num(i) != clean->l3proto) ||
(clean->l4proto && nf_ct_protonum(i) != clean->l4proto))
return 0;
- if (clean->hash) {
- spin_lock_bh(&nf_nat_lock);
- hlist_del_rcu(&nat->bysource);
- spin_unlock_bh(&nf_nat_lock);
- } else {
- memset(nat, 0, sizeof(*nat));
- i->status &= ~(IPS_NAT_MASK | IPS_NAT_DONE_MASK |
- IPS_SEQ_ADJUST);
- }
- return 0;
+ return i->status & IPS_NAT_MASK ? 1 : 0;
}
static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto)
@@ -505,16 +494,8 @@
struct net *net;
rtnl_lock();
- /* Step 1 - remove from bysource hash */
- clean.hash = true;
for_each_net(net)
- nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean);
- synchronize_rcu();
-
- /* Step 2 - clean NAT section */
- clean.hash = false;
- for_each_net(net)
- nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean);
+ nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean);
rtnl_unlock();
}
@@ -526,16 +507,9 @@
struct net *net;
rtnl_lock();
- /* Step 1 - remove from bysource hash */
- clean.hash = true;
- for_each_net(net)
- nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean);
- synchronize_rcu();
- /* Step 2 - clean NAT section */
- clean.hash = false;
for_each_net(net)
- nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean);
+ nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean);
rtnl_unlock();
}
@@ -773,7 +747,7 @@
{
struct nf_nat_proto_clean clean = {};
- nf_ct_iterate_cleanup(net, &nf_nat_proto_clean, &clean);
+ nf_ct_iterate_cleanup(net, &nf_nat_proto_remove, &clean);
synchronize_rcu();
nf_ct_free_hashtable(net->ct.nat_bysource, net->ct.nat_htable_size);
}
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index b28cc38..4de4bc4 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -3016,6 +3016,7 @@
$dstat !~ /^'X'$/ && # character constants
$dstat !~ /$exceptions/ &&
$dstat !~ /^\.$Ident\s*=/ && # .foo =
+ $dstat !~ /^(?:\#\s*$Ident|\#\s*$Constant)\s*$/ && # stringification #foo
$dstat !~ /^do\s*$Constant\s*while\s*$Constant;?$/ && # do {...} while (...); // do {...} while (...)
$dstat !~ /^for\s*$Constant$/ && # for (...)
$dstat !~ /^for\s*$Constant\s+(?:$Ident|-?$Constant)$/ && # for (...) bar()
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 6f3214e..321e066 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -1421,6 +1421,7 @@
case 0x3C: /* HSW */
case 0x3F: /* HSW */
case 0x45: /* HSW */
+ case 0x46: /* HSW */
return 1;
case 0x2E: /* Nehalem-EX Xeon - Beckton */
case 0x2F: /* Westmere-EX Xeon - Eagleton */
@@ -1515,6 +1516,7 @@
case 0x3C: /* HSW */
case 0x3F: /* HSW */
case 0x45: /* HSW */
+ case 0x46: /* HSW */
do_rapl = RAPL_PKG | RAPL_CORES | RAPL_GFX;
break;
case 0x2D:
@@ -1754,6 +1756,7 @@
case 0x3C: /* HSW */
case 0x3F: /* HSW */
case 0x45: /* HSW */
+ case 0x46: /* HSW */
return 1;
}
return 0;
@@ -2276,7 +2279,7 @@
cmdline(argc, argv);
if (verbose)
- fprintf(stderr, "turbostat v3.2 February 11, 2013"
+ fprintf(stderr, "turbostat v3.3 March 15, 2013"
" - Len Brown <lenb@kernel.org>\n");
turbostat_init();
