Re: Linux 3.14.48

From: Greg KH
Date: Fri Jul 10 2015 - 15:25:53 EST

diff --git a/Makefile b/Makefile
index f9041e6d4d19..25393e89051c 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
VERSION = 3
PATCHLEVEL = 14
-SUBLEVEL = 47
+SUBLEVEL = 48
EXTRAVERSION =
NAME = Remembering Coco

diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 9f7923193cda..7d35af3f3752 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -117,13 +117,14 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd)
(__boundary - 1 < (end) - 1)? __boundary: (end); \
})

+#define kvm_pgd_index(addr) pgd_index(addr)
+
static inline bool kvm_page_empty(void *ptr)
{
struct page *ptr_page = virt_to_page(ptr);
return page_count(ptr_page) == 1;
}

-
#define kvm_pte_table_empty(ptep) kvm_page_empty(ptep)
#define kvm_pmd_table_empty(pmdp) kvm_page_empty(pmdp)
#define kvm_pud_table_empty(pudp) (0)
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 2e74a617147d..f6a52a2a3724 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -441,6 +441,7 @@ static void update_vttbr(struct kvm *kvm)

static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
{
+ struct kvm *kvm = vcpu->kvm;
int ret;

if (likely(vcpu->arch.has_run_once))
@@ -452,12 +453,20 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
* Initialize the VGIC before running a vcpu the first time on
* this VM.
*/
- if (unlikely(!vgic_initialized(vcpu->kvm))) {
- ret = kvm_vgic_init(vcpu->kvm);
+ if (unlikely(!vgic_initialized(kvm))) {
+ ret = kvm_vgic_init(kvm);
if (ret)
return ret;
}

+ /*
+ * Enable the arch timers only if we have an in-kernel VGIC
+ * and it has been properly initialized, since we cannot handle
+ * interrupts from the virtual timer with a userspace gic.
+ */
+ if (irqchip_in_kernel(kvm) && vgic_initialized(kvm))
+ kvm_timer_enable(kvm);
+
return 0;
}

diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
index 0d68d4073068..a1467e7689f5 100644
--- a/arch/arm/kvm/interrupts.S
+++ b/arch/arm/kvm/interrupts.S
@@ -159,13 +159,9 @@ __kvm_vcpu_return:
@ Don't trap coprocessor accesses for host kernel
set_hstr vmexit
set_hdcr vmexit
- set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11))
+ set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11)), after_vfp_restore

#ifdef CONFIG_VFPv3
- @ Save floating point registers we if let guest use them.
- tst r2, #(HCPTR_TCP(10) | HCPTR_TCP(11))
- bne after_vfp_restore
-
@ Switch VFP/NEON hardware state to the host's
add r7, vcpu, #VCPU_VFP_GUEST
store_vfp_state r7
@@ -177,6 +173,8 @@ after_vfp_restore:
@ Restore FPEXC_EN which we clobbered on entry
pop {r2}
VFPFMXR FPEXC, r2
+#else
+after_vfp_restore:
#endif

@ Reset Hyp-role
@@ -467,7 +465,7 @@ switch_to_guest_vfp:
push {r3-r7}

@ NEON/VFP used. Turn on VFP access.
- set_hcptr vmexit, (HCPTR_TCP(10) | HCPTR_TCP(11))
+ set_hcptr vmtrap, (HCPTR_TCP(10) | HCPTR_TCP(11))

@ Switch VFP/NEON hardware state to the guest's
add r7, r0, #VCPU_VFP_HOST
diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S
index 76af93025574..2973b2d342fa 100644
--- a/arch/arm/kvm/interrupts_head.S
+++ b/arch/arm/kvm/interrupts_head.S
@@ -578,8 +578,13 @@ vcpu .req r0 @ vcpu pointer always in r0
.endm

/* Configures the HCPTR (Hyp Coprocessor Trap Register) on entry/return
- * (hardware reset value is 0). Keep previous value in r2. */
-.macro set_hcptr operation, mask
+ * (hardware reset value is 0). Keep previous value in r2.
+ * An ISB is emited on vmexit/vmtrap, but executed on vmexit only if
+ * VFP wasn't already enabled (always executed on vmtrap).
+ * If a label is specified with vmexit, it is branched to if VFP wasn't
+ * enabled.
+ */
+.macro set_hcptr operation, mask, label = none
mrc p15, 4, r2, c1, c1, 2
ldr r3, =\mask
.if \operation == vmentry
@@ -588,6 +593,17 @@ vcpu .req r0 @ vcpu pointer always in r0
bic r3, r2, r3 @ Don't trap defined coproc-accesses
.endif
mcr p15, 4, r3, c1, c1, 2
+ .if \operation != vmentry
+ .if \operation == vmexit
+ tst r2, #(HCPTR_TCP(10) | HCPTR_TCP(11))
+ beq 1f
+ .endif
+ isb
+ .if \label != none
+ b \label
+ .endif
+1:
+ .endif
.endm

/* Configures the HDCR (Hyp Debug Configuration Register) on entry/return
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 524b4b57f650..c612e37166ad 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -194,7 +194,7 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
phys_addr_t addr = start, end = start + size;
phys_addr_t next;

- pgd = pgdp + pgd_index(addr);
+ pgd = pgdp + kvm_pgd_index(addr);
do {
next = kvm_pgd_addr_end(addr, end);
if (!pgd_none(*pgd))
@@ -264,7 +264,7 @@ static void stage2_flush_memslot(struct kvm *kvm,
phys_addr_t next;
pgd_t *pgd;

- pgd = kvm->arch.pgd + pgd_index(addr);
+ pgd = kvm->arch.pgd + kvm_pgd_index(addr);
do {
next = kvm_pgd_addr_end(addr, end);
stage2_flush_puds(kvm, pgd, addr, next);
@@ -649,7 +649,7 @@ static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
pud_t *pud;
pmd_t *pmd;

- pgd = kvm->arch.pgd + pgd_index(addr);
+ pgd = kvm->arch.pgd + kvm_pgd_index(addr);
pud = pud_offset(pgd, addr);
if (pud_none(*pud)) {
if (!cache)
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 681cb9080100..91f33c2051f2 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -41,6 +41,8 @@ void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr);
static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
{
vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS;
+ if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features))
+ vcpu->arch.hcr_el2 &= ~HCR_RW;
}

static inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 0d51874c838f..15a8a861264a 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -69,6 +69,8 @@
#define PTRS_PER_S2_PGD (1 << (KVM_PHYS_SHIFT - PGDIR_SHIFT))
#define S2_PGD_ORDER get_order(PTRS_PER_S2_PGD * sizeof(pgd_t))

+#define kvm_pgd_index(addr) (((addr) >> PGDIR_SHIFT) & (PTRS_PER_S2_PGD - 1))
+
int create_hyp_mappings(void *from, void *to);
int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
void free_boot_hyp_pgd(void);
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 5dfc8331c385..3aaf3bc4ad8a 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -629,6 +629,7 @@ ENTRY(__kvm_tlb_flush_vmid_ipa)
* Instead, we invalidate Stage-2 for this IPA, and the
* whole of Stage-1. Weep...
*/
+ lsr x1, x1, #12
tlbi ipas2e1is, x1
/*
* We have to ensure completion of the invalidation at Stage-2,
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 70a7816535cd..0b4326578985 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -90,7 +90,6 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
if (!cpu_has_32bit_el1())
return -EINVAL;
cpu_reset = &default_regs_reset32;
- vcpu->arch.hcr_el2 &= ~HCR_RW;
} else {
cpu_reset = &default_regs_reset;
}
diff --git a/arch/mips/include/asm/mach-generic/spaces.h b/arch/mips/include/asm/mach-generic/spaces.h
index 9488fa5f8866..afc96ecb9004 100644
--- a/arch/mips/include/asm/mach-generic/spaces.h
+++ b/arch/mips/include/asm/mach-generic/spaces.h
@@ -94,7 +94,11 @@
#endif

#ifndef FIXADDR_TOP
+#ifdef CONFIG_KVM_GUEST
+#define FIXADDR_TOP ((unsigned long)(long)(int)0x7ffe0000)
+#else
#define FIXADDR_TOP ((unsigned long)(long)(int)0xfffe0000)
#endif
+#endif

#endif /* __ASM_MACH_GENERIC_SPACES_H */
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 38265dc85318..65dfbd0c196d 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -124,7 +124,16 @@ static inline void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) {}

static bool regs_use_siar(struct pt_regs *regs)
{
- return !!regs->result;
+ /*
+ * When we take a performance monitor exception the regs are setup
+ * using perf_read_regs() which overloads some fields, in particular
+ * regs->result to tell us whether to use SIAR.
+ *
+ * However if the regs are from another exception, eg. a syscall, then
+ * they have not been setup using perf_read_regs() and so regs->result
+ * is something random.
+ */
+ return ((TRAP(regs) == 0xf00) && regs->result);
}

/*
diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c
index 27bb55485472..7ef28625c199 100644
--- a/arch/sparc/kernel/ldc.c
+++ b/arch/sparc/kernel/ldc.c
@@ -2307,7 +2307,7 @@ void *ldc_alloc_exp_dring(struct ldc_channel *lp, unsigned int len,
if (len & (8UL - 1))
return ERR_PTR(-EINVAL);

- buf = kzalloc(len, GFP_KERNEL);
+ buf = kzalloc(len, GFP_ATOMIC);
if (!buf)
return ERR_PTR(-ENOMEM);

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5dab54accc56..96e743ac28f3 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2440,9 +2440,19 @@ config X86_DMA_REMAP
depends on STA2X11

config IOSF_MBI
- tristate
- default m
+ tristate "Intel System On Chip IOSF Sideband support"
depends on PCI
+ ---help---
+ Enables sideband access to mailbox registers on SoC's. The sideband is
+ available on the following platforms. This list is not meant to be
+ exclusive.
+ - BayTrail
+ - Cherryview
+ - Braswell
+ - Quark
+
+ You should say Y if you are running a kernel on one of these
+ platforms.

source "net/Kconfig"

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e9dc02968cf8..ac03bd7c8978 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -571,7 +571,7 @@ struct kvm_arch {
struct kvm_pic *vpic;
struct kvm_ioapic *vioapic;
struct kvm_pit *vpit;
- int vapics_in_nmi_mode;
+ atomic_t vapics_in_nmi_mode;
struct mutex apic_map_lock;
struct kvm_apic_map *apic_map;

diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 298781d4cfb4..1406ffde3e35 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -305,7 +305,7 @@ static void pit_do_work(struct kthread_work *work)
* LVT0 to NMI delivery. Other PIC interrupts are just sent to
* VCPU0, and only if its LVT0 is in EXTINT mode.
*/
- if (kvm->arch.vapics_in_nmi_mode > 0)
+ if (atomic_read(&kvm->arch.vapics_in_nmi_mode) > 0)
kvm_for_each_vcpu(i, vcpu, kvm)
kvm_apic_nmi_wd_deliver(vcpu);
}
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 453e5fbbb7ae..6456734a4ca6 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1109,10 +1109,10 @@ static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val)
if (!nmi_wd_enabled) {
apic_debug("Receive NMI setting on APIC_LVT0 "
"for cpu %d\n", apic->vcpu->vcpu_id);
- apic->vcpu->kvm->arch.vapics_in_nmi_mode++;
+ atomic_inc(&apic->vcpu->kvm->arch.vapics_in_nmi_mode);
}
} else if (nmi_wd_enabled)
- apic->vcpu->kvm->arch.vapics_in_nmi_mode--;
+ atomic_dec(&apic->vcpu->kvm->arch.vapics_in_nmi_mode);
}

static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 4f25ec077552..bf001382d170 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -84,6 +84,17 @@ static const struct dmi_system_id pci_crs_quirks[] __initconst = {
DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies, LTD"),
},
},
+ /* https://bugs.launchpad.net/ubuntu/+source/alsa-driver/+bug/931368 */
+ /* https://bugs.launchpad.net/ubuntu/+source/alsa-driver/+bug/1033299 */
+ {
+ .callback = set_use_crs,
+ .ident = "Foxconn K8M890-8237A",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Foxconn"),
+ DMI_MATCH(DMI_BOARD_NAME, "K8M890-8237A"),
+ DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies, LTD"),
+ },
+ },

/* Now for the blacklist.. */

@@ -124,8 +135,10 @@ void __init pci_acpi_crs_quirks(void)
{
int year;

- if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) && year < 2008)
- pci_use_crs = false;
+ if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) && year < 2008) {
+ if (iomem_resource.end <= 0xffffffff)
+ pci_use_crs = false;
+ }

dmi_check_system(pci_crs_quirks);

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 533a509439ca..fbc693b7d24f 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -417,7 +417,7 @@ static void byt_set_pstate(struct cpudata *cpudata, int pstate)

val |= vid;

- wrmsrl(MSR_IA32_PERF_CTL, val);
+ wrmsrl_on_cpu(cpudata->cpu, MSR_IA32_PERF_CTL, val);
}

#define BYT_BCLK_FREQS 5
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index 5967667e1a8f..1f354879bd06 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -927,7 +927,8 @@ static int sg_to_link_tbl(struct scatterlist *sg, int sg_count,
sg_count--;
link_tbl_ptr--;
}
- be16_add_cpu(&link_tbl_ptr->len, cryptlen);
+ link_tbl_ptr->len = cpu_to_be16(be16_to_cpu(link_tbl_ptr->len)
+ + cryptlen);

/* tag end of link table */
link_tbl_ptr->j_extent = DESC_PTR_LNKTBL_RETURN;
@@ -2563,6 +2564,7 @@ static struct talitos_crypto_alg *talitos_alg_alloc(struct device *dev,
break;
default:
dev_err(dev, "unknown algorithm type %d\n", t_alg->algt.type);
+ kfree(t_alg);
return ERR_PTR(-EINVAL);
}

diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 9cbef59d404a..935974090aa0 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -1922,9 +1922,15 @@ static void free_pt_##LVL (unsigned long __pt) \
pt = (u64 *)__pt; \
\
for (i = 0; i < 512; ++i) { \
+ /* PTE present? */ \
if (!IOMMU_PTE_PRESENT(pt[i])) \
continue; \
\
+ /* Large PTE? */ \
+ if (PM_PTE_LEVEL(pt[i]) == 0 || \
+ PM_PTE_LEVEL(pt[i]) == 7) \
+ continue; \
+ \
p = (unsigned long)IOMMU_PTE_PAGE(pt[i]); \
FN(p); \
} \
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 25f74191a788..62c3fb91e76f 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -765,10 +765,11 @@ static int genphy_config_advert(struct phy_device *phydev)
if (phydev->supported & (SUPPORTED_1000baseT_Half |
SUPPORTED_1000baseT_Full)) {
adv |= ethtool_adv_to_mii_ctrl1000_t(advertise);
- if (adv != oldadv)
- changed = 1;
}

+ if (adv != oldadv)
+ changed = 1;
+
err = phy_write(phydev, MII_CTRL1000, adv);
if (err < 0)
return err;
diff --git a/fs/dcache.c b/fs/dcache.c
index 1d7e8a3fb6cd..aa24f7de1b92 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2905,17 +2905,6 @@ restart:
vfsmnt = &mnt->mnt;
continue;
}
- /*
- * Filesystems needing to implement special "root names"
- * should do so with ->d_dname()
- */
- if (IS_ROOT(dentry) &&
- (dentry->d_name.len != 1 ||
- dentry->d_name.name[0] != '/')) {
- WARN(1, "Root dentry has weird name <%.*s>\n",
- (int) dentry->d_name.len,
- dentry->d_name.name);
- }
if (!error)
error = is_mounted(vfsmnt) ? 1 : 2;
break;
diff --git a/fs/inode.c b/fs/inode.c
index e846a32e8d6e..644875bcc846 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1631,8 +1631,8 @@ int file_remove_suid(struct file *file)
error = security_inode_killpriv(dentry);
if (!error && killsuid)
error = __remove_suid(dentry, killsuid);
- if (!error && (inode->i_sb->s_flags & MS_NOSEC))
- inode->i_flags |= S_NOSEC;
+ if (!error)
+ inode_has_no_xattr(inode);

return error;
}
diff --git a/fs/namespace.c b/fs/namespace.c
index 2faa7eacb62b..fc99d185a477 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -3031,11 +3031,15 @@ bool fs_fully_visible(struct file_system_type *type)
if (mnt->mnt.mnt_root != mnt->mnt.mnt_sb->s_root)
continue;

- /* This mount is not fully visible if there are any child mounts
- * that cover anything except for empty directories.
+ /* This mount is not fully visible if there are any
+ * locked child mounts that cover anything except for
+ * empty directories.
*/
list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
struct inode *inode = child->mnt_mountpoint->d_inode;
+ /* Only worry about locked mounts */
+ if (!(mnt->mnt.mnt_flags & MNT_LOCKED))
+ continue;
if (!S_ISDIR(inode->i_mode))
goto next;
if (inode->i_nlink > 2)
diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index 6d9aeddc09bf..327b155e7cc9 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -60,7 +60,8 @@ struct arch_timer_cpu {

#ifdef CONFIG_KVM_ARM_TIMER
int kvm_timer_hyp_init(void);
-int kvm_timer_init(struct kvm *kvm);
+void kvm_timer_enable(struct kvm *kvm);
+void kvm_timer_init(struct kvm *kvm);
void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu,
const struct kvm_irq_level *irq);
void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu);
@@ -73,11 +74,8 @@ static inline int kvm_timer_hyp_init(void)
return 0;
};

-static inline int kvm_timer_init(struct kvm *kvm)
-{
- return 0;
-}
-
+static inline void kvm_timer_enable(struct kvm *kvm) {}
+static inline void kvm_timer_init(struct kvm *kvm) {}
static inline void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu,
const struct kvm_irq_level *irq) {}
static inline void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) {}
diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h
index 3573a81815ad..8ba379f9e467 100644
--- a/include/net/netns/sctp.h
+++ b/include/net/netns/sctp.h
@@ -31,6 +31,7 @@ struct netns_sctp {
struct list_head addr_waitq;
struct timer_list addr_wq_timer;
struct list_head auto_asconf_splist;
+ /* Lock that protects both addr_waitq and auto_asconf_splist */
spinlock_t addr_wq_lock;

/* Lock that protects the local_addr_list writers */
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 0dfcc92600e8..2c2d388f884f 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -219,6 +219,10 @@ struct sctp_sock {
atomic_t pd_mode;
/* Receive to here while partial delivery is in effect. */
struct sk_buff_head pd_lobby;
+
+ /* These must be the last fields, as they will skipped on copies,
+ * like on accept and peeloff operations
+ */
struct list_head auto_asconf_list;
int do_auto_asconf;
};
diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c
index a9a4a1b7863d..8d423bc649b9 100644
--- a/net/bridge/br_ioctl.c
+++ b/net/bridge/br_ioctl.c
@@ -247,9 +247,7 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN))
return -EPERM;

- spin_lock_bh(&br->lock);
br_stp_set_bridge_priority(br, args[1]);
- spin_unlock_bh(&br->lock);
return 0;

case BRCTL_SET_PORT_PRIORITY:
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 11a2e6c8538f..7bbc8fe25261 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1086,6 +1086,9 @@ static void br_multicast_add_router(struct net_bridge *br,
struct net_bridge_port *p;
struct hlist_node *slot = NULL;

+ if (!hlist_unhashed(&port->rlist))
+ return;
+
hlist_for_each_entry(p, &br->router_list, rlist) {
if ((unsigned long) port >= (unsigned long) p)
break;
@@ -1113,12 +1116,8 @@ static void br_multicast_mark_router(struct net_bridge *br,
if (port->multicast_router != 1)
return;

- if (!hlist_unhashed(&port->rlist))
- goto timer;
-
br_multicast_add_router(br, port);

-timer:
mod_timer(&port->multicast_router_timer,
now + br->multicast_querier_interval);
}
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 189ba1e7d851..9a0005aee9ad 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -243,12 +243,13 @@ bool br_stp_recalculate_bridge_id(struct net_bridge *br)
return true;
}

-/* called under bridge lock */
+/* Acquires and releases bridge lock */
void br_stp_set_bridge_priority(struct net_bridge *br, u16 newprio)
{
struct net_bridge_port *p;
int wasroot;

+ spin_lock_bh(&br->lock);
wasroot = br_is_root_bridge(br);

list_for_each_entry(p, &br->port_list, list) {
@@ -266,6 +267,7 @@ void br_stp_set_bridge_priority(struct net_bridge *br, u16 newprio)
br_port_state_selection(br);
if (br_is_root_bridge(br) && !wasroot)
br_become_root_bridge(br);
+ spin_unlock_bh(&br->lock);
}

/* called under bridge lock */
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 7d95f69635c6..0f062c671da9 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -976,6 +976,8 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
rc = 0;
if (neigh->nud_state & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE))
goto out_unlock_bh;
+ if (neigh->dead)
+ goto out_dead;

if (!(neigh->nud_state & (NUD_STALE | NUD_INCOMPLETE))) {
if (NEIGH_VAR(neigh->parms, MCAST_PROBES) +
@@ -1032,6 +1034,13 @@ out_unlock_bh:
write_unlock(&neigh->lock);
local_bh_enable();
return rc;
+
+out_dead:
+ if (neigh->nud_state & NUD_STALE)
+ goto out_unlock_bh;
+ write_unlock_bh(&neigh->lock);
+ kfree_skb(skb);
+ return 1;
}
EXPORT_SYMBOL(__neigh_event_send);

@@ -1095,6 +1104,8 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
if (!(flags & NEIGH_UPDATE_F_ADMIN) &&
(old & (NUD_NOARP | NUD_PERMANENT)))
goto out;
+ if (neigh->dead)
+ goto out;

if (!(new & NUD_VALID)) {
neigh_del_timer(neigh);
@@ -1244,6 +1255,8 @@ EXPORT_SYMBOL(neigh_update);
*/
void __neigh_set_probe_once(struct neighbour *neigh)
{
+ if (neigh->dead)
+ return;
neigh->updated = jiffies;
if (!(neigh->nud_state & NUD_FAILED))
return;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 69ec61abfb37..8207f8d7f665 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -368,9 +368,11 @@ refill:
for (order = NETDEV_FRAG_PAGE_MAX_ORDER; ;) {
gfp_t gfp = gfp_mask;

- if (order)
+ if (order) {
gfp |= __GFP_COMP | __GFP_NOWARN |
__GFP_NOMEMALLOC;
+ gfp &= ~__GFP_WAIT;
+ }
nc->frag.page = alloc_pages(gfp, order);
if (likely(nc->frag.page))
break;
diff --git a/net/core/sock.c b/net/core/sock.c
index 650dd58ebd05..8ebfa52e5d70 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1914,8 +1914,10 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio)
do {
gfp_t gfp = prio;

- if (order)
+ if (order) {
gfp |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY;
+ gfp &= ~__GFP_WAIT;
+ }
pfrag->page = alloc_pages(gfp, order);
if (likely(pfrag->page)) {
pfrag->offset = 0;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 07bd8edef417..951fe55b1671 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -228,6 +228,8 @@ int inet_listen(struct socket *sock, int backlog)
err = 0;
if (err)
goto out;
+
+ tcp_fastopen_init_key_once(true);
}
err = inet_csk_listen_start(sk, backlog);
if (err)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 29d240b87af1..dc45221dc692 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2684,10 +2684,13 @@ static int do_tcp_setsockopt(struct sock *sk, int level,

case TCP_FASTOPEN:
if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE |
- TCPF_LISTEN)))
+ TCPF_LISTEN))) {
+ tcp_fastopen_init_key_once(true);
+
err = fastopen_init_queue(sk, val);
- else
+ } else {
err = -EINVAL;
+ }
break;
case TCP_TIMESTAMP:
if (!tp->repair)
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index f195d9316e55..ee6518d1afe5 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -84,8 +84,6 @@ void tcp_fastopen_cookie_gen(__be32 src, __be32 dst,
__be32 path[4] = { src, dst, 0, 0 };
struct tcp_fastopen_context *ctx;

- tcp_fastopen_init_key_once(true);
-
rcu_read_lock();
ctx = rcu_dereference(tcp_fastopen_ctx);
if (ctx) {
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 48b181797d7b..84a60b82e235 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1264,16 +1264,6 @@ static void packet_sock_destruct(struct sock *sk)
sk_refcnt_debug_dec(sk);
}

-static int fanout_rr_next(struct packet_fanout *f, unsigned int num)
-{
- int x = atomic_read(&f->rr_cur) + 1;
-
- if (x >= num)
- x = 0;
-
- return x;
-}
-
static unsigned int fanout_demux_hash(struct packet_fanout *f,
struct sk_buff *skb,
unsigned int num)
@@ -1285,13 +1275,9 @@ static unsigned int fanout_demux_lb(struct packet_fanout *f,
struct sk_buff *skb,
unsigned int num)
{
- int cur, old;
+ unsigned int val = atomic_inc_return(&f->rr_cur);

- cur = atomic_read(&f->rr_cur);
- while ((old = atomic_cmpxchg(&f->rr_cur, cur,
- fanout_rr_next(f, num))) != cur)
- cur = old;
- return cur;
+ return val % num;
}

static unsigned int fanout_demux_cpu(struct packet_fanout *f,
@@ -1345,7 +1331,7 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *orig_dev)
{
struct packet_fanout *f = pt->af_packet_priv;
- unsigned int num = f->num_members;
+ unsigned int num = ACCESS_ONCE(f->num_members);
struct packet_sock *po;
unsigned int idx;

diff --git a/net/sctp/output.c b/net/sctp/output.c
index 740ca5f7add0..e39e6d561592 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -599,7 +599,9 @@ out:
return err;
no_route:
kfree_skb(nskb);
- IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES);
+
+ if (asoc)
+ IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES);

/* FIXME: Returning the 'err' will effect all the associations
* associated with a socket, although only one of the paths of the
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 604a6acdf92e..f940fdc540f5 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1532,8 +1532,10 @@ static void sctp_close(struct sock *sk, long timeout)

/* Supposedly, no process has access to the socket, but
* the net layers still may.
+ * Also, sctp_destroy_sock() needs to be called with addr_wq_lock
+ * held and that should be grabbed before socket lock.
*/
- local_bh_disable();
+ spin_lock_bh(&net->sctp.addr_wq_lock);
bh_lock_sock(sk);

/* Hold the sock, since sk_common_release() will put sock_put()
@@ -1543,7 +1545,7 @@ static void sctp_close(struct sock *sk, long timeout)
sk_common_release(sk);

bh_unlock_sock(sk);
- local_bh_enable();
+ spin_unlock_bh(&net->sctp.addr_wq_lock);

sock_put(sk);

@@ -3511,6 +3513,7 @@ static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval,
if ((val && sp->do_auto_asconf) || (!val && !sp->do_auto_asconf))
return 0;

+ spin_lock_bh(&sock_net(sk)->sctp.addr_wq_lock);
if (val == 0 && sp->do_auto_asconf) {
list_del(&sp->auto_asconf_list);
sp->do_auto_asconf = 0;
@@ -3519,6 +3522,7 @@ static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval,
&sock_net(sk)->sctp.auto_asconf_splist);
sp->do_auto_asconf = 1;
}
+ spin_unlock_bh(&sock_net(sk)->sctp.addr_wq_lock);
return 0;
}

@@ -4009,18 +4013,28 @@ static int sctp_init_sock(struct sock *sk)
local_bh_disable();
percpu_counter_inc(&sctp_sockets_allocated);
sock_prot_inuse_add(net, sk->sk_prot, 1);
+
+ /* Nothing can fail after this block, otherwise
+ * sctp_destroy_sock() will be called without addr_wq_lock held
+ */
if (net->sctp.default_auto_asconf) {
+ spin_lock(&sock_net(sk)->sctp.addr_wq_lock);
list_add_tail(&sp->auto_asconf_list,
&net->sctp.auto_asconf_splist);
sp->do_auto_asconf = 1;
- } else
+ spin_unlock(&sock_net(sk)->sctp.addr_wq_lock);
+ } else {
sp->do_auto_asconf = 0;
+ }
+
local_bh_enable();

return 0;
}

-/* Cleanup any SCTP per socket resources. */
+/* Cleanup any SCTP per socket resources. Must be called with
+ * sock_net(sk)->sctp.addr_wq_lock held if sp->do_auto_asconf is true
+ */
static void sctp_destroy_sock(struct sock *sk)
{
struct sctp_sock *sp;
@@ -6973,6 +6987,19 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
newinet->mc_list = NULL;
}

+static inline void sctp_copy_descendant(struct sock *sk_to,
+ const struct sock *sk_from)
+{
+ int ancestor_size = sizeof(struct inet_sock) +
+ sizeof(struct sctp_sock) -
+ offsetof(struct sctp_sock, auto_asconf_list);
+
+ if (sk_from->sk_family == PF_INET6)
+ ancestor_size += sizeof(struct ipv6_pinfo);
+
+ __inet_sk_copy_descendant(sk_to, sk_from, ancestor_size);
+}
+
/* Populate the fields of the newsk from the oldsk and migrate the assoc
* and its messages to the newsk.
*/
@@ -6987,7 +7014,6 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
struct sk_buff *skb, *tmp;
struct sctp_ulpevent *event;
struct sctp_bind_hashbucket *head;
- struct list_head tmplist;

/* Migrate socket buffer sizes and all the socket level options to the
* new socket.
@@ -6995,12 +7021,7 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
newsk->sk_sndbuf = oldsk->sk_sndbuf;
newsk->sk_rcvbuf = oldsk->sk_rcvbuf;
/* Brute force copy old sctp opt. */
- if (oldsp->do_auto_asconf) {
- memcpy(&tmplist, &newsp->auto_asconf_list, sizeof(tmplist));
- inet_sk_copy_descendant(newsk, oldsk);
- memcpy(&newsp->auto_asconf_list, &tmplist, sizeof(tmplist));
- } else
- inet_sk_copy_descendant(newsk, oldsk);
+ sctp_copy_descendant(newsk, oldsk);

/* Restore the ep value that was overwritten with the above structure
* copy.
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index 5081e809821f..c6fe40568690 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -61,12 +61,14 @@ static void timer_disarm(struct arch_timer_cpu *timer)

static void kvm_timer_inject_irq(struct kvm_vcpu *vcpu)
{
+ int ret;
struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;

timer->cntv_ctl |= ARCH_TIMER_CTRL_IT_MASK;
- kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
- timer->irq->irq,
- timer->irq->level);
+ ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
+ timer->irq->irq,
+ timer->irq->level);
+ WARN_ON(ret);
}

static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id)
@@ -307,12 +309,24 @@ void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu)
timer_disarm(timer);
}

-int kvm_timer_init(struct kvm *kvm)
+void kvm_timer_enable(struct kvm *kvm)
{
- if (timecounter && wqueue) {
- kvm->arch.timer.cntvoff = kvm_phys_timer_read();
+ if (kvm->arch.timer.enabled)
+ return;
+
+ /*
+ * There is a potential race here between VCPUs starting for the first
+ * time, which may be enabling the timer multiple times. That doesn't
+ * hurt though, because we're just setting a variable to the same
+ * variable that it already was. The important thing is that all
+ * VCPUs have the enabled variable set, before entering the guest, if
+ * the arch timers are enabled.
+ */
+ if (timecounter && wqueue)
kvm->arch.timer.enabled = 1;
- }
+}

- return 0;
+void kvm_timer_init(struct kvm *kvm)
+{
+ kvm->arch.timer.cntvoff = kvm_phys_timer_read();
}
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index c324a52bb407..152ec76ccb42 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -1042,6 +1042,7 @@ static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
lr, irq, vgic_cpu->vgic_lr[lr]);
BUG_ON(!test_bit(lr, vgic_cpu->lr_used));
vgic_cpu->vgic_lr[lr] |= GICH_LR_PENDING_BIT;
+ __clear_bit(lr, (unsigned long *)vgic_cpu->vgic_elrsr);
return true;
}

@@ -1055,6 +1056,7 @@ static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
vgic_cpu->vgic_lr[lr] = MK_LR_PEND(sgi_source_id, irq);
vgic_cpu->vgic_irq_lr_map[irq] = lr;
set_bit(lr, vgic_cpu->lr_used);
+ __clear_bit(lr, (unsigned long *)vgic_cpu->vgic_elrsr);

if (!vgic_irq_is_edge(vcpu, irq))
vgic_cpu->vgic_lr[lr] |= GICH_LR_EOI;
@@ -1209,6 +1211,14 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
if (vgic_cpu->vgic_misr & GICH_MISR_U)
vgic_cpu->vgic_hcr &= ~GICH_HCR_UIE;

+ /*
+ * In the next iterations of the vcpu loop, if we sync the vgic state
+ * after flushing it, but before entering the guest (this happens for
+ * pending signals and vmid rollovers), then make sure we don't pick
+ * up any old maintenance interrupts here.
+ */
+ memset(vgic_cpu->vgic_eisr, 0, sizeof(vgic_cpu->vgic_eisr[0]) * 2);
+
return level_pending;
}

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/