kernel-alx/patches-4.1/0120-4.1.21-all-fixes.patch

diff --git a/Documentation/devicetree/bindings/arm/omap/omap.txt b/Documentation/devicetree/bindings/arm/omap/omap.txt
index 4f6a82cef1d1..cbe35b3de9e9 100644
--- a/Documentation/devicetree/bindings/arm/omap/omap.txt
+++ b/Documentation/devicetree/bindings/arm/omap/omap.txt
@@ -23,6 +23,7 @@ Optional properties:
   during suspend.
 - ti,no-reset-on-init: When present, the module should not be reset at init
 - ti,no-idle-on-init: When present, the module should not be idled at init
+- ti,no-idle: When present, the module is never allowed to idle.
 
 Example:
 
diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt
index c59bd9bc41ef..4176ab076f1c 100644
--- a/Documentation/virtual/kvm/mmu.txt
+++ b/Documentation/virtual/kvm/mmu.txt
@@ -352,7 +352,8 @@ In the first case there are two additional complications:
 - if CR4.SMEP is enabled: since we've turned the page into a kernel page,
   the kernel may now execute it.  We handle this by also setting spte.nx.
   If we get a user fetch or read fault, we'll change spte.u=1 and
-  spte.nx=gpte.nx back.
+  spte.nx=gpte.nx back.  For this to work, KVM forces EFER.NX to 1 when
+  shadow paging is in use.
 - if CR4.SMAP is disabled: since the page has been changed to a kernel
   page, it can not be reused when CR4.SMAP is enabled. We set
   CR4.SMAP && !CR0.WP into shadow page's role to avoid this case. Note,
diff --git a/Makefile b/Makefile
index 39be1bbd373a..79fab0d55218 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 1
-SUBLEVEL = 20
+SUBLEVEL = 21
 EXTRAVERSION =
 NAME = Series 4800
 
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index dfcc0dd637e5..bc04b754fe36 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -1411,6 +1411,16 @@
 			       0x48485200 0x2E00>;
 			#address-cells = <1>;
 			#size-cells = <1>;
+
+			/*
+			 * Do not allow gating of cpsw clock as workaround
+			 * for errata i877. Keeping internal clock disabled
+			 * causes the device switching characteristics
+			 * to degrade over time and eventually fail to meet
+			 * the data manual delay time/skew specs.
+			 */
+			ti,no-idle;
+
 			/*
 			 * rx_thresh_pend
 			 * rx_pend
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 5286e7773ed4..9185bb958503 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -876,6 +876,36 @@ static int _init_opt_clks(struct omap_hwmod *oh)
 	return ret;
 }
 
+static void _enable_optional_clocks(struct omap_hwmod *oh)
+{
+	struct omap_hwmod_opt_clk *oc;
+	int i;
+
+	pr_debug("omap_hwmod: %s: enabling optional clocks\n", oh->name);
+
+	for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++)
+		if (oc->_clk) {
+			pr_debug("omap_hwmod: enable %s:%s\n", oc->role,
+				 __clk_get_name(oc->_clk));
+			clk_enable(oc->_clk);
+		}
+}
+
+static void _disable_optional_clocks(struct omap_hwmod *oh)
+{
+	struct omap_hwmod_opt_clk *oc;
+	int i;
+
+	pr_debug("omap_hwmod: %s: disabling optional clocks\n", oh->name);
+
+	for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++)
+		if (oc->_clk) {
+			pr_debug("omap_hwmod: disable %s:%s\n", oc->role,
+				 __clk_get_name(oc->_clk));
+			clk_disable(oc->_clk);
+		}
+}
+
 /**
  * _enable_clocks - enable hwmod main clock and interface clocks
  * @oh: struct omap_hwmod *
@@ -903,6 +933,9 @@ static int _enable_clocks(struct omap_hwmod *oh)
 			clk_enable(os->_clk);
 	}
 
+	if (oh->flags & HWMOD_OPT_CLKS_NEEDED)
+		_enable_optional_clocks(oh);
+
 	/* The opt clocks are controlled by the device driver. */
 
 	return 0;
@@ -934,41 +967,14 @@ static int _disable_clocks(struct omap_hwmod *oh)
 			clk_disable(os->_clk);
 	}
 
+	if (oh->flags & HWMOD_OPT_CLKS_NEEDED)
+		_disable_optional_clocks(oh);
+
 	/* The opt clocks are controlled by the device driver. */
 
 	return 0;
 }
 
-static void _enable_optional_clocks(struct omap_hwmod *oh)
-{
-	struct omap_hwmod_opt_clk *oc;
-	int i;
-
-	pr_debug("omap_hwmod: %s: enabling optional clocks\n", oh->name);
-
-	for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++)
-		if (oc->_clk) {
-			pr_debug("omap_hwmod: enable %s:%s\n", oc->role,
-				 __clk_get_name(oc->_clk));
-			clk_enable(oc->_clk);
-		}
-}
-
-static void _disable_optional_clocks(struct omap_hwmod *oh)
-{
-	struct omap_hwmod_opt_clk *oc;
-	int i;
-
-	pr_debug("omap_hwmod: %s: disabling optional clocks\n", oh->name);
-
-	for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++)
-		if (oc->_clk) {
-			pr_debug("omap_hwmod: disable %s:%s\n", oc->role,
-				 __clk_get_name(oc->_clk));
-			clk_disable(oc->_clk);
-		}
-}
-
 /**
  * _omap4_enable_module - enable CLKCTRL modulemode on OMAP4
  * @oh: struct omap_hwmod *
@@ -2180,6 +2186,11 @@ static int _enable(struct omap_hwmod *oh)
  */
 static int _idle(struct omap_hwmod *oh)
 {
+	if (oh->flags & HWMOD_NO_IDLE) {
+		oh->_int_flags |= _HWMOD_SKIP_ENABLE;
+		return 0;
+	}
+
 	pr_debug("omap_hwmod: %s: idling\n", oh->name);
 
 	if (oh->_state != _HWMOD_STATE_ENABLED) {
@@ -2484,6 +2495,8 @@ static int __init _init(struct omap_hwmod *oh, void *data)
 			oh->flags |= HWMOD_INIT_NO_RESET;
 		if (of_find_property(np, "ti,no-idle-on-init", NULL))
 			oh->flags |= HWMOD_INIT_NO_IDLE;
+		if (of_find_property(np, "ti,no-idle", NULL))
+			oh->flags |= HWMOD_NO_IDLE;
 	}
 
 	oh->_state = _HWMOD_STATE_INITIALIZED;
@@ -2610,7 +2623,7 @@ static void __init _setup_postsetup(struct omap_hwmod *oh)
 	 * XXX HWMOD_INIT_NO_IDLE does not belong in hwmod data -
 	 * it should be set by the core code as a runtime flag during startup
 	 */
-	if ((oh->flags & HWMOD_INIT_NO_IDLE) &&
+	if ((oh->flags & (HWMOD_INIT_NO_IDLE | HWMOD_NO_IDLE)) &&
 	    (postsetup_state == _HWMOD_STATE_IDLE)) {
 		oh->_int_flags |= _HWMOD_SKIP_ENABLE;
 		postsetup_state = _HWMOD_STATE_ENABLED;
diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h
index 9611c91d9b82..ec289c5f099a 100644
--- a/arch/arm/mach-omap2/omap_hwmod.h
+++ b/arch/arm/mach-omap2/omap_hwmod.h
@@ -517,6 +517,10 @@ struct omap_hwmod_omap4_prcm {
  * HWMOD_RECONFIG_IO_CHAIN: omap_hwmod code needs to reconfigure wake-up 
  *     events by calling _reconfigure_io_chain() when a device is enabled
  *     or idled.
+ * HWMOD_OPT_CLKS_NEEDED: The optional clocks are needed for the module to
+ *     operate and they need to be handled at the same time as the main_clk.
+ * HWMOD_NO_IDLE: Do not idle the hwmod at all. Useful to handle certain
+ *     IPs like CPSW on DRA7, where clocks to this module cannot be disabled.
  */
 #define HWMOD_SWSUP_SIDLE			(1 << 0)
 #define HWMOD_SWSUP_MSTANDBY			(1 << 1)
@@ -532,6 +536,8 @@ struct omap_hwmod_omap4_prcm {
 #define HWMOD_FORCE_MSTANDBY			(1 << 11)
 #define HWMOD_SWSUP_SIDLE_ACT			(1 << 12)
 #define HWMOD_RECONFIG_IO_CHAIN			(1 << 13)
+#define HWMOD_OPT_CLKS_NEEDED			(1 << 14)
+#define HWMOD_NO_IDLE				(1 << 15)
 
 /*
  * omap_hwmod._int_flags definitions
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index b056369fd47d..0d1d675f2cce 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -184,20 +184,21 @@ static void clear_regs_spsr_ss(struct pt_regs *regs)
 
 /* EL1 Single Step Handler hooks */
 static LIST_HEAD(step_hook);
-static DEFINE_RWLOCK(step_hook_lock);
+static DEFINE_SPINLOCK(step_hook_lock);
 
 void register_step_hook(struct step_hook *hook)
 {
-	write_lock(&step_hook_lock);
-	list_add(&hook->node, &step_hook);
-	write_unlock(&step_hook_lock);
+	spin_lock(&step_hook_lock);
+	list_add_rcu(&hook->node, &step_hook);
+	spin_unlock(&step_hook_lock);
 }
 
 void unregister_step_hook(struct step_hook *hook)
 {
-	write_lock(&step_hook_lock);
-	list_del(&hook->node);
-	write_unlock(&step_hook_lock);
+	spin_lock(&step_hook_lock);
+	list_del_rcu(&hook->node);
+	spin_unlock(&step_hook_lock);
+	synchronize_rcu();
 }
 
 /*
@@ -211,15 +212,15 @@ static int call_step_hook(struct pt_regs *regs, unsigned int esr)
 	struct step_hook *hook;
 	int retval = DBG_HOOK_ERROR;
 
-	read_lock(&step_hook_lock);
+	rcu_read_lock();
 
-	list_for_each_entry(hook, &step_hook, node)	{
+	list_for_each_entry_rcu(hook, &step_hook, node)	{
 		retval = hook->fn(regs, esr);
 		if (retval == DBG_HOOK_HANDLED)
 			break;
 	}
 
-	read_unlock(&step_hook_lock);
+	rcu_read_unlock();
 
 	return retval;
 }
@@ -271,20 +272,21 @@ static int single_step_handler(unsigned long addr, unsigned int esr,
  * Use reader/writer locks instead of plain spinlock.
  */
 static LIST_HEAD(break_hook);
-static DEFINE_RWLOCK(break_hook_lock);
+static DEFINE_SPINLOCK(break_hook_lock);
 
 void register_break_hook(struct break_hook *hook)
 {
-	write_lock(&break_hook_lock);
-	list_add(&hook->node, &break_hook);
-	write_unlock(&break_hook_lock);
+	spin_lock(&break_hook_lock);
+	list_add_rcu(&hook->node, &break_hook);
+	spin_unlock(&break_hook_lock);
 }
 
 void unregister_break_hook(struct break_hook *hook)
 {
-	write_lock(&break_hook_lock);
-	list_del(&hook->node);
-	write_unlock(&break_hook_lock);
+	spin_lock(&break_hook_lock);
+	list_del_rcu(&hook->node);
+	spin_unlock(&break_hook_lock);
+	synchronize_rcu();
 }
 
 static int call_break_hook(struct pt_regs *regs, unsigned int esr)
@@ -292,11 +294,11 @@ static int call_break_hook(struct pt_regs *regs, unsigned int esr)
 	struct break_hook *hook;
 	int (*fn)(struct pt_regs *regs, unsigned int esr) = NULL;
 
-	read_lock(&break_hook_lock);
-	list_for_each_entry(hook, &break_hook, node)
+	rcu_read_lock();
+	list_for_each_entry_rcu(hook, &break_hook, node)
 		if ((esr & hook->esr_mask) == hook->esr_val)
 			fn = hook->fn;
-	read_unlock(&break_hook_lock);
+	rcu_read_unlock();
 
 	return fn ? fn(regs, esr) : DBG_HOOK_ERROR;
 }
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index a3b1ffe50aa0..c99e8a32bea4 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2103,11 +2103,11 @@ config CPU_R4K_CACHE_TLB
 
 config MIPS_MT_SMP
 	bool "MIPS MT SMP support (1 TC on each available VPE)"
-	depends on SYS_SUPPORTS_MULTITHREADING
+	depends on SYS_SUPPORTS_MULTITHREADING && !CPU_MIPSR6
 	select CPU_MIPSR2_IRQ_VI
 	select CPU_MIPSR2_IRQ_EI
 	select SYNC_R4K
-	select MIPS_GIC_IPI
+	select MIPS_GIC_IPI if MIPS_GIC
 	select MIPS_MT
 	select SMP
 	select SMP_UP
@@ -2204,8 +2204,8 @@ config MIPS_VPE_APSP_API_MT
 
 config MIPS_CMP
 	bool "MIPS CMP framework support (DEPRECATED)"
-	depends on SYS_SUPPORTS_MIPS_CMP
-	select MIPS_GIC_IPI
+	depends on SYS_SUPPORTS_MIPS_CMP && !CPU_MIPSR6
+	select MIPS_GIC_IPI if MIPS_GIC
 	select SMP
 	select SYNC_R4K
 	select SYS_SUPPORTS_SMP
@@ -2221,11 +2221,11 @@ config MIPS_CMP
 
 config MIPS_CPS
 	bool "MIPS Coherent Processing System support"
-	depends on SYS_SUPPORTS_MIPS_CPS && !64BIT
+	depends on SYS_SUPPORTS_MIPS_CPS && !CPU_MIPSR6
 	select MIPS_CM
 	select MIPS_CPC
 	select MIPS_CPS_PM if HOTPLUG_CPU
-	select MIPS_GIC_IPI
+	select MIPS_GIC_IPI if MIPS_GIC
 	select SMP
 	select SYNC_R4K if (CEVT_R4K || CSRC_R4K)
 	select SYS_SUPPORTS_HOTPLUG_CPU
@@ -2244,6 +2244,7 @@ config MIPS_CPS_PM
 	bool
 
 config MIPS_GIC_IPI
+	depends on MIPS_GIC
 	bool
 
 config MIPS_CM
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index f8338e6d3dd7..a34e43eec658 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1273,6 +1273,20 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	std	r6, VCPU_ACOP(r9)
 	stw	r7, VCPU_GUEST_PID(r9)
 	std	r8, VCPU_WORT(r9)
+	/*
+	 * Restore various registers to 0, where non-zero values
+	 * set by the guest could disrupt the host.
+	 */
+	li	r0, 0
+	mtspr	SPRN_IAMR, r0
+	mtspr	SPRN_CIABR, r0
+	mtspr	SPRN_DAWRX, r0
+	mtspr	SPRN_TCSCR, r0
+	mtspr	SPRN_WORT, r0
+	/* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */
+	li	r0, 1
+	sldi	r0, r0, 31
+	mtspr	SPRN_MMCRS, r0
 8:
 
 	/* Save and reset AMR and UAMOR before turning on the MMU */
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index fb1b93ea3e3f..e485817f7b1a 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -15,17 +15,25 @@
 static inline int init_new_context(struct task_struct *tsk,
 				   struct mm_struct *mm)
 {
+	spin_lock_init(&mm->context.list_lock);
+	INIT_LIST_HEAD(&mm->context.pgtable_list);
+	INIT_LIST_HEAD(&mm->context.gmap_list);
 	cpumask_clear(&mm->context.cpu_attach_mask);
 	atomic_set(&mm->context.attach_count, 0);
 	mm->context.flush_mm = 0;
-	mm->context.asce_bits = _ASCE_TABLE_LENGTH | _ASCE_USER_BITS;
-	mm->context.asce_bits |= _ASCE_TYPE_REGION3;
 #ifdef CONFIG_PGSTE
 	mm->context.alloc_pgste = page_table_allocate_pgste;
 	mm->context.has_pgste = 0;
 	mm->context.use_skey = 0;
 #endif
-	mm->context.asce_limit = STACK_TOP_MAX;
+	if (mm->context.asce_limit == 0) {
+		/* context created by exec, set asce limit to 4TB */
+		mm->context.asce_bits = _ASCE_TABLE_LENGTH |
+			_ASCE_USER_BITS | _ASCE_TYPE_REGION3;
+		mm->context.asce_limit = STACK_TOP_MAX;
+	} else if (mm->context.asce_limit == (1UL << 31)) {
+		mm_inc_nr_pmds(mm);
+	}
 	crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm));
 	return 0;
 }
@@ -111,8 +119,6 @@ static inline void activate_mm(struct mm_struct *prev,
 static inline void arch_dup_mmap(struct mm_struct *oldmm,
 				 struct mm_struct *mm)
 {
-	if (oldmm->context.asce_limit < mm->context.asce_limit)
-		crst_table_downgrade(mm, oldmm->context.asce_limit);
 }
 
 static inline void arch_exit_mmap(struct mm_struct *mm)
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index 7b7858f158b4..d7cc79fb6191 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -100,12 +100,26 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	spin_lock_init(&mm->context.list_lock);
-	INIT_LIST_HEAD(&mm->context.pgtable_list);
-	INIT_LIST_HEAD(&mm->context.gmap_list);
-	return (pgd_t *) crst_table_alloc(mm);
+	unsigned long *table = crst_table_alloc(mm);
+
+	if (!table)
+		return NULL;
+	if (mm->context.asce_limit == (1UL << 31)) {
+		/* Forking a compat process with 2 page table levels */
+		if (!pgtable_pmd_page_ctor(virt_to_page(table))) {
+			crst_table_free(mm, table);
+			return NULL;
+		}
+	}
+	return (pgd_t *) table;
+}
+
+static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+	if (mm->context.asce_limit == (1UL << 31))
+		pgtable_pmd_page_dtor(virt_to_page(pgd));
+	crst_table_free(mm, (unsigned long *) pgd);
 }
-#define pgd_free(mm, pgd) crst_table_free(mm, (unsigned long *) pgd)
 
 static inline void pmd_populate(struct mm_struct *mm,
 				pmd_t *pmd, pgtable_t pte)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 945f9e13f1aa..917148620f49 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1674,6 +1674,13 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 			return;
 		}
 		break;
+	case MSR_IA32_PEBS_ENABLE:
+		/* PEBS needs a quiescent period after being disabled (to write
+		 * a record).  Disabling PEBS through VMX MSR swapping doesn't
+		 * provide that period, so a CPU could write host's record into
+		 * guest's memory.
+		 */
+		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
 	}
 
 	for (i = 0; i < m->nr; ++i)
@@ -1711,26 +1718,31 @@ static void reload_tss(void)
 
 static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
 {
-	u64 guest_efer;
-	u64 ignore_bits;
+	u64 guest_efer = vmx->vcpu.arch.efer;
+	u64 ignore_bits = 0;
 
-	guest_efer = vmx->vcpu.arch.efer;
+	if (!enable_ept) {
+		/*
+		 * NX is needed to handle CR0.WP=1, CR4.SMEP=1.  Testing
+		 * host CPUID is more efficient than testing guest CPUID
+		 * or CR4.  Host SMEP is anyway a requirement for guest SMEP.
+		 */
+		if (boot_cpu_has(X86_FEATURE_SMEP))
+			guest_efer |= EFER_NX;
+		else if (!(guest_efer & EFER_NX))
+			ignore_bits |= EFER_NX;
+	}
 
 	/*
-	 * NX is emulated; LMA and LME handled by hardware; SCE meaningless
-	 * outside long mode
+	 * LMA and LME handled by hardware; SCE meaningless outside long mode.
 	 */
-	ignore_bits = EFER_NX | EFER_SCE;
+	ignore_bits |= EFER_SCE;
 #ifdef CONFIG_X86_64
 	ignore_bits |= EFER_LMA | EFER_LME;
 	/* SCE is meaningful only in long mode on Intel */
 	if (guest_efer & EFER_LMA)
 		ignore_bits &= ~(u64)EFER_SCE;
 #endif
-	guest_efer &= ~ignore_bits;
-	guest_efer |= host_efer & ignore_bits;
-	vmx->guest_msrs[efer_offset].data = guest_efer;
-	vmx->guest_msrs[efer_offset].mask = ~ignore_bits;
 
 	clear_atomic_switch_msr(vmx, MSR_EFER);
 
@@ -1741,16 +1753,21 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
 	 */
 	if (cpu_has_load_ia32_efer ||
 	    (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) {
-		guest_efer = vmx->vcpu.arch.efer;
 		if (!(guest_efer & EFER_LMA))
 			guest_efer &= ~EFER_LME;
 		if (guest_efer != host_efer)
 			add_atomic_switch_msr(vmx, MSR_EFER,
 					      guest_efer, host_efer);
 		return false;
-	}
+	} else {
+		guest_efer &= ~ignore_bits;
+		guest_efer |= host_efer & ignore_bits;
 
-	return true;
+		vmx->guest_msrs[efer_offset].data = guest_efer;
+		vmx->guest_msrs[efer_offset].mask = ~ignore_bits;
+
+		return true;
+	}
 }
 
 static unsigned long segment_base(u16 selector)
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index 8d8c35623f2a..ffa809f30b19 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -176,6 +176,7 @@
 #define AT_XDMAC_MAX_CHAN	0x20
 #define AT_XDMAC_MAX_CSIZE	16	/* 16 data */
 #define AT_XDMAC_MAX_DWIDTH	8	/* 64 bits */
+#define AT_XDMAC_RESIDUE_MAX_RETRIES	5
 
 #define AT_XDMAC_DMA_BUSWIDTHS\
 	(BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED) |\
@@ -925,8 +926,8 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	struct at_xdmac_desc	*desc, *_desc;
 	struct list_head	*descs_list;
 	enum dma_status		ret;
-	int			residue;
-	u32			cur_nda, mask, value;
+	int			residue, retry;
+	u32			cur_nda, check_nda, cur_ubc, mask, value;
 	u8			dwidth = 0;
 	unsigned long		flags;
 
@@ -963,7 +964,42 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 			cpu_relax();
 	}
 
+	/*
+	 * When processing the residue, we need to read two registers but we
+	 * can't do it in an atomic way. AT_XDMAC_CNDA is used to find where
+	 * we stand in the descriptor list and AT_XDMAC_CUBC is used
+	 * to know how many data are remaining for the current descriptor.
+	 * Since the dma channel is not paused to not loose data, between the
+	 * AT_XDMAC_CNDA and AT_XDMAC_CUBC read, we may have change of
+	 * descriptor.
+	 * For that reason, after reading AT_XDMAC_CUBC, we check if we are
+	 * still using the same descriptor by reading a second time
+	 * AT_XDMAC_CNDA. If AT_XDMAC_CNDA has changed, it means we have to
+	 * read again AT_XDMAC_CUBC.
+	 * Memory barriers are used to ensure the read order of the registers.
+	 * A max number of retries is set because unlikely it can never ends if
+	 * we are transferring a lot of data with small buffers.
+	 */
 	cur_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc;
+	rmb();
+	cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC);
+	for (retry = 0; retry < AT_XDMAC_RESIDUE_MAX_RETRIES; retry++) {
+		rmb();
+		check_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc;
+
+		if (likely(cur_nda == check_nda))
+			break;
+
+		cur_nda = check_nda;
+		rmb();
+		cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC);
+	}
+
+	if (unlikely(retry >= AT_XDMAC_RESIDUE_MAX_RETRIES)) {
+		ret = DMA_ERROR;
+		goto spin_unlock;
+	}
+
 	/*
 	 * Remove size of all microblocks already transferred and the current
 	 * one. Then add the remaining size to transfer of the current
@@ -976,7 +1012,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 		if ((desc->lld.mbr_nda & 0xfffffffc) == cur_nda)
 			break;
 	}
-	residue += at_xdmac_chan_read(atchan, AT_XDMAC_CUBC) << dwidth;
+	residue += cur_ubc << dwidth;
 
 	dma_set_residue(txstate, residue);
 
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 447dbfa6c793..7ac42d063574 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -254,7 +254,7 @@ void radeon_dp_aux_init(struct radeon_connector *radeon_connector)
 #define DP_VOLTAGE_MAX         DP_TRAIN_VOLTAGE_SWING_LEVEL_3
 #define DP_PRE_EMPHASIS_MAX    DP_TRAIN_PRE_EMPH_LEVEL_3
 
-static void dp_get_adjust_train(u8 link_status[DP_LINK_STATUS_SIZE],
+static void dp_get_adjust_train(const u8 link_status[DP_LINK_STATUS_SIZE],
 				int lane_count,
 				u8 train_set[4])
 {
@@ -301,77 +301,43 @@ static int convert_bpc_to_bpp(int bpc)
 		return bpc * 3;
 }
 
-/* get the max pix clock supported by the link rate and lane num */
-static int dp_get_max_dp_pix_clock(int link_rate,
-				   int lane_num,
-				   int bpp)
-{
-	return (link_rate * lane_num * 8) / bpp;
-}
-
 /***** radeon specific DP functions *****/
 
-int radeon_dp_get_max_link_rate(struct drm_connector *connector,
-				u8 dpcd[DP_DPCD_SIZE])
-{
-	int max_link_rate;
-
-	if (radeon_connector_is_dp12_capable(connector))
-		max_link_rate = min(drm_dp_max_link_rate(dpcd), 540000);
-	else
-		max_link_rate = min(drm_dp_max_link_rate(dpcd), 270000);
-
-	return max_link_rate;
-}
-
-/* First get the min lane# when low rate is used according to pixel clock
- * (prefer low rate), second check max lane# supported by DP panel,
- * if the max lane# < low rate lane# then use max lane# instead.
- */
-static int radeon_dp_get_dp_lane_number(struct drm_connector *connector,
-					u8 dpcd[DP_DPCD_SIZE],
-					int pix_clock)
+int radeon_dp_get_dp_link_config(struct drm_connector *connector,
+				 const u8 dpcd[DP_DPCD_SIZE],
+				 unsigned pix_clock,
+				 unsigned *dp_lanes, unsigned *dp_rate)
 {
 	int bpp = convert_bpc_to_bpp(radeon_get_monitor_bpc(connector));
-	int max_link_rate = radeon_dp_get_max_link_rate(connector, dpcd);
-	int max_lane_num = drm_dp_max_lane_count(dpcd);
-	int lane_num;
-	int max_dp_pix_clock;
-
-	for (lane_num = 1; lane_num < max_lane_num; lane_num <<= 1) {
-		max_dp_pix_clock = dp_get_max_dp_pix_clock(max_link_rate, lane_num, bpp);
-		if (pix_clock <= max_dp_pix_clock)
-			break;
-	}
-
-	return lane_num;
-}
-
-static int radeon_dp_get_dp_link_clock(struct drm_connector *connector,
-				       u8 dpcd[DP_DPCD_SIZE],
-				       int pix_clock)
-{
-	int bpp = convert_bpc_to_bpp(radeon_get_monitor_bpc(connector));
-	int lane_num, max_pix_clock;
+	static const unsigned link_rates[3] = { 162000, 270000, 540000 };
+	unsigned max_link_rate = drm_dp_max_link_rate(dpcd);
+	unsigned max_lane_num = drm_dp_max_lane_count(dpcd);
+	unsigned lane_num, i, max_pix_clock;
 
 	if (radeon_connector_encoder_get_dp_bridge_encoder_id(connector) ==
-	    ENCODER_OBJECT_ID_NUTMEG)
-		return 270000;
-
-	lane_num = radeon_dp_get_dp_lane_number(connector, dpcd, pix_clock);
-	max_pix_clock = dp_get_max_dp_pix_clock(162000, lane_num, bpp);
-	if (pix_clock <= max_pix_clock)
-		return 162000;
-	max_pix_clock = dp_get_max_dp_pix_clock(270000, lane_num, bpp);
-	if (pix_clock <= max_pix_clock)
-		return 270000;
-	if (radeon_connector_is_dp12_capable(connector)) {
-		max_pix_clock = dp_get_max_dp_pix_clock(540000, lane_num, bpp);
-		if (pix_clock <= max_pix_clock)
-			return 540000;
+	    ENCODER_OBJECT_ID_NUTMEG) {
+		for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) {
+			max_pix_clock = (lane_num * 270000 * 8) / bpp;
+			if (max_pix_clock >= pix_clock) {
+				*dp_lanes = lane_num;
+				*dp_rate = 270000;
+				return 0;
+			}
+		}
+	} else {
+		for (lane_num = 1; lane_num <= max_lane_num; lane_num <<= 1) {
+			for (i = 0; i < ARRAY_SIZE(link_rates) && link_rates[i] <= max_link_rate; i++) {
+				max_pix_clock = (lane_num * link_rates[i] * 8) / bpp;
+				if (max_pix_clock >= pix_clock) {
+					*dp_lanes = lane_num;
+					*dp_rate = link_rates[i];
+					return 0;
+				}
+			}
+		}
 	}
 
-	return radeon_dp_get_max_link_rate(connector, dpcd);
+	return -EINVAL;
 }
 
 static u8 radeon_dp_encoder_service(struct radeon_device *rdev,
@@ -490,6 +456,7 @@ void radeon_dp_set_link_config(struct drm_connector *connector,
 {
 	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 	struct radeon_connector_atom_dig *dig_connector;
+	int ret;
 
 	if (!radeon_connector->con_priv)
 		return;
@@ -497,10 +464,14 @@ void radeon_dp_set_link_config(struct drm_connector *connector,
 
 	if ((dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT) ||
 	    (dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_eDP)) {
-		dig_connector->dp_clock =
-			radeon_dp_get_dp_link_clock(connector, dig_connector->dpcd, mode->clock);
-		dig_connector->dp_lane_count =
-			radeon_dp_get_dp_lane_number(connector, dig_connector->dpcd, mode->clock);
+		ret = radeon_dp_get_dp_link_config(connector, dig_connector->dpcd,
+						   mode->clock,
+						   &dig_connector->dp_lane_count,
+						   &dig_connector->dp_clock);
+		if (ret) {
+			dig_connector->dp_clock = 0;
+			dig_connector->dp_lane_count = 0;
+		}
 	}
 }
 
@@ -509,7 +480,8 @@ int radeon_dp_mode_valid_helper(struct drm_connector *connector,
 {
 	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 	struct radeon_connector_atom_dig *dig_connector;
-	int dp_clock;
+	unsigned dp_clock, dp_lanes;
+	int ret;
 
 	if ((mode->clock > 340000) &&
 	    (!radeon_connector_is_dp12_capable(connector)))
@@ -519,8 +491,12 @@ int radeon_dp_mode_valid_helper(struct drm_connector *connector,
 		return MODE_CLOCK_HIGH;
 	dig_connector = radeon_connector->con_priv;
 
-	dp_clock =
-		radeon_dp_get_dp_link_clock(connector, dig_connector->dpcd, mode->clock);
+	ret = radeon_dp_get_dp_link_config(connector, dig_connector->dpcd,
+					   mode->clock,
+					   &dp_lanes,
+					   &dp_clock);
+	if (ret)
+		return MODE_CLOCK_HIGH;
 
 	if ((dp_clock == 540000) &&
 	    (!radeon_connector_is_dp12_capable(connector)))
diff --git a/drivers/gpu/drm/radeon/radeon_dp_mst.c b/drivers/gpu/drm/radeon/radeon_dp_mst.c
index c9ff4cf4c4e7..c4b4c0233937 100644
--- a/drivers/gpu/drm/radeon/radeon_dp_mst.c
+++ b/drivers/gpu/drm/radeon/radeon_dp_mst.c
@@ -520,11 +520,17 @@ static bool radeon_mst_mode_fixup(struct drm_encoder *encoder,
 	drm_mode_set_crtcinfo(adjusted_mode, 0);
 	{
 	  struct radeon_connector_atom_dig *dig_connector;
+	  int ret;
 
 	  dig_connector = mst_enc->connector->con_priv;
-	  dig_connector->dp_lane_count = drm_dp_max_lane_count(dig_connector->dpcd);
-	  dig_connector->dp_clock = radeon_dp_get_max_link_rate(&mst_enc->connector->base,
-								dig_connector->dpcd);
+	  ret = radeon_dp_get_dp_link_config(&mst_enc->connector->base,
+					     dig_connector->dpcd, adjusted_mode->clock,
+					     &dig_connector->dp_lane_count,
+					     &dig_connector->dp_clock);
+	  if (ret) {
+		  dig_connector->dp_lane_count = 0;
+		  dig_connector->dp_clock = 0;
+	  }
 	  DRM_DEBUG_KMS("dig clock %p %d %d\n", dig_connector,
 			dig_connector->dp_lane_count, dig_connector->dp_clock);
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
index 9af2d8398e90..43ba333949c7 100644
--- a/drivers/gpu/drm/radeon/radeon_mode.h
+++ b/drivers/gpu/drm/radeon/radeon_mode.h
@@ -752,8 +752,10 @@ extern u8 radeon_dp_getsinktype(struct radeon_connector *radeon_connector);
 extern bool radeon_dp_getdpcd(struct radeon_connector *radeon_connector);
 extern int radeon_dp_get_panel_mode(struct drm_encoder *encoder,
 				    struct drm_connector *connector);
-int radeon_dp_get_max_link_rate(struct drm_connector *connector,
-				u8 *dpcd);
+extern int radeon_dp_get_dp_link_config(struct drm_connector *connector,
+					const u8 *dpcd,
+					unsigned pix_clock,
+					unsigned *dp_lanes, unsigned *dp_rate);
 extern void radeon_dp_set_rx_power_state(struct drm_connector *connector,
 					 u8 power_state);
 extern void radeon_dp_aux_init(struct radeon_connector *radeon_connector);
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index a56eab7f0ab1..8319eed613b0 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -1079,6 +1079,8 @@ force:
 
 	/* update display watermarks based on new power state */
 	radeon_bandwidth_update(rdev);
+	/* update displays */
+	radeon_dpm_display_configuration_changed(rdev);
 
 	/* wait for the rings to drain */
 	for (i = 0; i < RADEON_NUM_RINGS; i++) {
@@ -1095,9 +1097,6 @@ force:
 
 	radeon_dpm_post_set_power_state(rdev);
 
-	/* update displays */
-	radeon_dpm_display_configuration_changed(rdev);
-
 	rdev->pm.dpm.current_active_crtcs = rdev->pm.dpm.new_active_crtcs;
 	rdev->pm.dpm.current_active_crtc_count = rdev->pm.dpm.new_active_crtc_count;
 	rdev->pm.dpm.single_display = single_display;
diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index 8b4d3e6875eb..21924f52863f 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -826,9 +826,8 @@ static struct gs_can *gs_make_candev(unsigned int channel, struct usb_interface
 static void gs_destroy_candev(struct gs_can *dev)
 {
 	unregister_candev(dev->netdev);
-	free_candev(dev->netdev);
 	usb_kill_anchored_urbs(&dev->tx_submitted);
-	kfree(dev);
+	free_candev(dev->netdev);
 }
 
 static int gs_usb_probe(struct usb_interface *intf, const struct usb_device_id *id)
@@ -913,12 +912,15 @@ static int gs_usb_probe(struct usb_interface *intf, const struct usb_device_id *
 	for (i = 0; i < icount; i++) {
 		dev->canch[i] = gs_make_candev(i, intf);
 		if (IS_ERR_OR_NULL(dev->canch[i])) {
+			/* save error code to return later */
+			rc = PTR_ERR(dev->canch[i]);
+
 			/* on failure destroy previously created candevs */
 			icount = i;
-			for (i = 0; i < icount; i++) {
+			for (i = 0; i < icount; i++)
 				gs_destroy_candev(dev->canch[i]);
-				dev->canch[i] = NULL;
-			}
+
+			usb_kill_anchored_urbs(&dev->rx_submitted);
 			kfree(dev);
 			return rc;
 		}
@@ -939,16 +941,12 @@ static void gs_usb_disconnect(struct usb_interface *intf)
 		return;
 	}
 
-	for (i = 0; i < GS_MAX_INTF; i++) {
-		struct gs_can *can = dev->canch[i];
-
-		if (!can)
-			continue;
-
-		gs_destroy_candev(can);
-	}
+	for (i = 0; i < GS_MAX_INTF; i++)
+		if (dev->canch[i])
+			gs_destroy_candev(dev->canch[i]);
 
 	usb_kill_anchored_urbs(&dev->rx_submitted);
+	kfree(dev);
 }
 
 static const struct usb_device_id gs_usb_table[] = {
diff --git a/drivers/net/wireless/iwlwifi/mvm/tx.c b/drivers/net/wireless/iwlwifi/mvm/tx.c
index 281451c274ca..771097f2162d 100644
--- a/drivers/net/wireless/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/iwlwifi/mvm/tx.c
@@ -370,6 +370,15 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb)
 		return -1;
 	}
 
+	/*
+	 * Increase the pending frames counter, so that later when a reply comes
+	 * in and the counter is decreased - we don't start getting negative
+	 * values.
+	 * Note that we don't need to make sure it isn't agg'd, since we're
+	 * TXing non-sta
+	 */
+	atomic_inc(&mvm->pending_frames[sta_id]);
+
 	return 0;
 }
 
diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index ad48837ead42..eed7c5a31b15 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -181,7 +181,6 @@ void core_tmr_abort_task(
 
 		if (!__target_check_io_state(se_cmd, se_sess, 0)) {
 			spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
-			target_put_sess_cmd(se_cmd);
 			goto out;
 		}
 
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 9a83f149ac85..95dfff88de11 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -873,6 +873,15 @@ struct ext4_inode_info {
 	 * by other means, so we have i_data_sem.
 	 */
 	struct rw_semaphore i_data_sem;
+	/*
+	 * i_mmap_sem is for serializing page faults with truncate / punch hole
+	 * operations. We have to make sure that new page cannot be faulted in
+	 * a section of the inode that is being punched. We cannot easily use
+	 * i_data_sem for this since we need protection for the whole punch
+	 * operation and i_data_sem ranks below transaction start so we have
+	 * to occasionally drop it.
+	 */
+	struct rw_semaphore i_mmap_sem;
 	struct inode vfs_inode;
 	struct jbd2_inode *jinode;
 
@@ -2287,6 +2296,7 @@ extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
 extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
 			     loff_t lstart, loff_t lend);
 extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
+extern int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf);
 extern qsize_t *ext4_get_reserved_space(struct inode *inode);
 extern void ext4_da_update_reserve_space(struct inode *inode,
 					int used, int quota_claim);
@@ -2632,6 +2642,9 @@ static inline int ext4_update_inode_size(struct inode *inode, loff_t newsize)
 	return changed;
 }
 
+int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
+				      loff_t len);
+
 struct ext4_group_info {
 	unsigned long   bb_state;
 	struct rb_root  bb_free_root;
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 87ba10d1d3bc..ea12f565be24 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4741,7 +4741,6 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	int partial_begin, partial_end;
 	loff_t start, end;
 	ext4_lblk_t lblk;
-	struct address_space *mapping = inode->i_mapping;
 	unsigned int blkbits = inode->i_blkbits;
 
 	trace_ext4_zero_range(inode, offset, len, mode);
@@ -4757,17 +4756,6 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	}
 
 	/*
-	 * Write out all dirty pages to avoid race conditions
-	 * Then release them.
-	 */
-	if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
-		ret = filemap_write_and_wait_range(mapping, offset,
-						   offset + len - 1);
-		if (ret)
-			return ret;
-	}
-
-	/*
 	 * Round up offset. This is not fallocate, we neet to zero out
 	 * blocks, so convert interior block aligned part of the range to
 	 * unwritten and possibly manually zero out unaligned parts of the
@@ -4810,6 +4798,10 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	if (mode & FALLOC_FL_KEEP_SIZE)
 		flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
 
+	/* Wait all existing dio workers, newcomers will block on i_mutex */
+	ext4_inode_block_unlocked_dio(inode);
+	inode_dio_wait(inode);
+
 	/* Preallocate the range including the unaligned edges */
 	if (partial_begin || partial_end) {
 		ret = ext4_alloc_file_blocks(file,
@@ -4818,7 +4810,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 				 round_down(offset, 1 << blkbits)) >> blkbits,
 				new_size, flags, mode);
 		if (ret)
-			goto out_mutex;
+			goto out_dio;
 
 	}
 
@@ -4827,16 +4819,23 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 		flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN |
 			  EXT4_EX_NOCACHE);
 
-		/* Now release the pages and zero block aligned part of pages*/
+		/*
+		 * Prevent page faults from reinstantiating pages we have
+		 * released from page cache.
+		 */
+		down_write(&EXT4_I(inode)->i_mmap_sem);
+		ret = ext4_update_disksize_before_punch(inode, offset, len);
+		if (ret) {
+			up_write(&EXT4_I(inode)->i_mmap_sem);
+			goto out_dio;
+		}
+		/* Now release the pages and zero block aligned part of pages */
 		truncate_pagecache_range(inode, start, end - 1);
 		inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
 
-		/* Wait all existing dio workers, newcomers will block on i_mutex */
-		ext4_inode_block_unlocked_dio(inode);
-		inode_dio_wait(inode);
-
 		ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
 					     flags, mode);
+		up_write(&EXT4_I(inode)->i_mmap_sem);
 		if (ret)
 			goto out_dio;
 	}
@@ -4964,8 +4963,13 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 			goto out;
 	}
 
+	/* Wait all existing dio workers, newcomers will block on i_mutex */
+	ext4_inode_block_unlocked_dio(inode);
+	inode_dio_wait(inode);
+
 	ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
 				     flags, mode);
+	ext4_inode_resume_unlocked_dio(inode);
 	if (ret)
 		goto out;
 
@@ -5424,21 +5428,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 			return ret;
 	}
 
-	/*
-	 * Need to round down offset to be aligned with page size boundary
-	 * for page size > block size.
-	 */
-	ioffset = round_down(offset, PAGE_SIZE);
-
-	/* Write out all dirty pages */
-	ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
-					   LLONG_MAX);
-	if (ret)
-		return ret;
-
-	/* Take mutex lock */
 	mutex_lock(&inode->i_mutex);
-
 	/*
 	 * There is no need to overlap collapse range with EOF, in which case
 	 * it is effectively a truncate operation
@@ -5454,17 +5444,43 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 		goto out_mutex;
 	}
 
-	truncate_pagecache(inode, ioffset);
-
 	/* Wait for existing dio to complete */
 	ext4_inode_block_unlocked_dio(inode);
 	inode_dio_wait(inode);
 
+	/*
+	 * Prevent page faults from reinstantiating pages we have released from
+	 * page cache.
+	 */
+	down_write(&EXT4_I(inode)->i_mmap_sem);
+	/*
+	 * Need to round down offset to be aligned with page size boundary
+	 * for page size > block size.
+	 */
+	ioffset = round_down(offset, PAGE_SIZE);
+	/*
+	 * Write tail of the last page before removed range since it will get
+	 * removed from the page cache below.
+	 */
+	ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, offset);
+	if (ret)
+		goto out_mmap;
+	/*
+	 * Write data that will be shifted to preserve them when discarding
+	 * page cache below. We are also protected from pages becoming dirty
+	 * by i_mmap_sem.
+	 */
+	ret = filemap_write_and_wait_range(inode->i_mapping, offset + len,
+					   LLONG_MAX);
+	if (ret)
+		goto out_mmap;
+	truncate_pagecache(inode, ioffset);
+
 	credits = ext4_writepage_trans_blocks(inode);
 	handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
 	if (IS_ERR(handle)) {
 		ret = PTR_ERR(handle);
-		goto out_dio;
+		goto out_mmap;
 	}
 
 	down_write(&EXT4_I(inode)->i_data_sem);
@@ -5503,7 +5519,8 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 
 out_stop:
 	ext4_journal_stop(handle);
-out_dio:
+out_mmap:
+	up_write(&EXT4_I(inode)->i_mmap_sem);
 	ext4_inode_resume_unlocked_dio(inode);
 out_mutex:
 	mutex_unlock(&inode->i_mutex);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 0613c256c344..dd65fac5ff2f 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -213,7 +213,7 @@ static const struct vm_operations_struct ext4_dax_vm_ops = {
 #endif
 
 static const struct vm_operations_struct ext4_file_vm_ops = {
-	.fault		= filemap_fault,
+	.fault		= ext4_filemap_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite   = ext4_page_mkwrite,
 };
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 2b3a53a51582..3291e1af0e24 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3524,6 +3524,35 @@ int ext4_can_truncate(struct inode *inode)
 }
 
 /*
+ * We have to make sure i_disksize gets properly updated before we truncate
+ * page cache due to hole punching or zero range. Otherwise i_disksize update
+ * can get lost as it may have been postponed to submission of writeback but
+ * that will never happen after we truncate page cache.
+ */
+int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
+				      loff_t len)
+{
+	handle_t *handle;
+	loff_t size = i_size_read(inode);
+
+	WARN_ON(!mutex_is_locked(&inode->i_mutex));
+	if (offset > size || offset + len < size)
+		return 0;
+
+	if (EXT4_I(inode)->i_disksize >= size)
+		return 0;
+
+	handle = ext4_journal_start(inode, EXT4_HT_MISC, 1);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+	ext4_update_i_disksize(inode, size);
+	ext4_mark_inode_dirty(handle, inode);
+	ext4_journal_stop(handle);
+
+	return 0;
+}
+
+/*
  * ext4_punch_hole: punches a hole in a file by releaseing the blocks
  * associated with the given offset and length
  *
@@ -3588,17 +3617,26 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 
 	}
 
+	/* Wait all existing dio workers, newcomers will block on i_mutex */
+	ext4_inode_block_unlocked_dio(inode);
+	inode_dio_wait(inode);
+
+	/*
+	 * Prevent page faults from reinstantiating pages we have released from
+	 * page cache.
+	 */
+	down_write(&EXT4_I(inode)->i_mmap_sem);
 	first_block_offset = round_up(offset, sb->s_blocksize);
 	last_block_offset = round_down((offset + length), sb->s_blocksize) - 1;
 
 	/* Now release the pages and zero block aligned part of pages*/
-	if (last_block_offset > first_block_offset)
+	if (last_block_offset > first_block_offset) {
+		ret = ext4_update_disksize_before_punch(inode, offset, length);
+		if (ret)
+			goto out_dio;
 		truncate_pagecache_range(inode, first_block_offset,
 					 last_block_offset);
-
-	/* Wait all existing dio workers, newcomers will block on i_mutex */
-	ext4_inode_block_unlocked_dio(inode);
-	inode_dio_wait(inode);
+	}
 
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 		credits = ext4_writepage_trans_blocks(inode);
@@ -3645,16 +3683,12 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);
 
-	/* Now release the pages again to reduce race window */
-	if (last_block_offset > first_block_offset)
-		truncate_pagecache_range(inode, first_block_offset,
-					 last_block_offset);
-
 	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
 out_stop:
 	ext4_journal_stop(handle);
 out_dio:
+	up_write(&EXT4_I(inode)->i_mmap_sem);
 	ext4_inode_resume_unlocked_dio(inode);
 out_mutex:
 	mutex_unlock(&inode->i_mutex);
@@ -4775,11 +4809,13 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 			} else
 				ext4_wait_for_tail_page_commit(inode);
 		}
+		down_write(&EXT4_I(inode)->i_mmap_sem);
 		/*
 		 * Truncate pagecache after we've waited for commit
 		 * in data=journal mode to make pages freeable.
 		 */
 		truncate_pagecache(inode, inode->i_size);
+		up_write(&EXT4_I(inode)->i_mmap_sem);
 	}
 	/*
 	 * We want to call ext4_truncate() even if attr->ia_size ==
@@ -5234,6 +5270,8 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 	sb_start_pagefault(inode->i_sb);
 	file_update_time(vma->vm_file);
+
+	down_read(&EXT4_I(inode)->i_mmap_sem);
 	/* Delalloc case is easy... */
 	if (test_opt(inode->i_sb, DELALLOC) &&
 	    !ext4_should_journal_data(inode) &&
@@ -5303,6 +5341,19 @@ retry_alloc:
 out_ret:
 	ret = block_page_mkwrite_return(ret);
 out:
+	up_read(&EXT4_I(inode)->i_mmap_sem);
 	sb_end_pagefault(inode->i_sb);
 	return ret;
 }
+
+int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct inode *inode = file_inode(vma->vm_file);
+	int err;
+
+	down_read(&EXT4_I(inode)->i_mmap_sem);
+	err = filemap_fault(vma, vmf);
+	up_read(&EXT4_I(inode)->i_mmap_sem);
+
+	return err;
+}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 8a3b9f14d198..6f5ca3e92246 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -945,6 +945,7 @@ static void init_once(void *foo)
 	INIT_LIST_HEAD(&ei->i_orphan);
 	init_rwsem(&ei->xattr_sem);
 	init_rwsem(&ei->i_data_sem);
+	init_rwsem(&ei->i_mmap_sem);
 	inode_init_once(&ei->vfs_inode);
 }
 
diff --git a/fs/ext4/truncate.h b/fs/ext4/truncate.h
index 011ba6670d99..c70d06a383e2 100644
--- a/fs/ext4/truncate.h
+++ b/fs/ext4/truncate.h
@@ -10,8 +10,10 @@
  */
 static inline void ext4_truncate_failed_write(struct inode *inode)
 {
+	down_write(&EXT4_I(inode)->i_mmap_sem);
 	truncate_inode_pages(inode->i_mapping, inode->i_size);
 	ext4_truncate(inode);
+	up_write(&EXT4_I(inode)->i_mmap_sem);
 }
 
 /*
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index 1ba5c97943b8..cfbceb116356 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -845,9 +845,14 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry,
 
 		pr_notice("%s(): Link succeeded, unlink failed (err %d). You now have a hard link\n",
 			  __func__, ret);
-		/* Might as well let the VFS know */
-		d_instantiate(new_dentry, d_inode(old_dentry));
-		ihold(d_inode(old_dentry));
+		/*
+		 * We can't keep the target in dcache after that.
+		 * For one thing, we can't afford dentry aliases for directories.
+		 * For another, if there was a victim, we _can't_ set new inode
+		 * for that sucker and we have to trigger mount eviction - the
+		 * caller won't do it on its own since we are returning an error.
+		 */
+		d_invalidate(new_dentry);
 		new_dir_i->i_mtime = new_dir_i->i_ctime = ITIME(now);
 		return ret;
 	}
diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c
index 80021c709af9..0c2632386f35 100644
--- a/fs/ncpfs/dir.c
+++ b/fs/ncpfs/dir.c
@@ -633,7 +633,7 @@ ncp_fill_cache(struct file *file, struct dir_context *ctx,
 				d_rehash(newdent);
 		} else {
 			spin_lock(&dentry->d_lock);
-			NCP_FINFO(inode)->flags &= ~NCPI_DIR_CACHE;
+			NCP_FINFO(dir)->flags &= ~NCPI_DIR_CACHE;
 			spin_unlock(&dentry->d_lock);
 		}
 	} else {
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 692ceda3bc21..a2b1d7ce3e1a 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -618,7 +618,8 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir)
 	 * sole user of this dentry.  Too tricky...  Just unhash for
 	 * now.
 	 */
-	d_drop(dentry);
+	if (!err)
+		d_drop(dentry);
 	mutex_unlock(&dir->i_mutex);
 
 	return err;
@@ -903,6 +904,13 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
 	if (!overwrite && new_is_dir && !old_opaque && new_opaque)
 		ovl_remove_opaque(newdentry);
 
+	/*
+	 * Old dentry now lives in different location. Dentries in
+	 * lowerstack are stale. We cannot drop them here because
+	 * access to them is lockless. This could be only pure upper
+	 * or opaque directory - numlower is zero. Or upper non-dir
+	 * entry - its pureness is tracked by flag opaque.
+	 */
 	if (old_opaque != new_opaque) {
 		ovl_dentry_set_opaque(old, new_opaque);
 		if (!overwrite)
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index a1b069e5e363..e505b44a9184 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -66,6 +66,8 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr)
 	if (upperdentry) {
 		mutex_lock(&upperdentry->d_inode->i_mutex);
 		err = notify_change(upperdentry, attr, NULL);
+		if (!err)
+			ovl_copyattr(upperdentry->d_inode, dentry->d_inode);
 		mutex_unlock(&upperdentry->d_inode->i_mutex);
 	} else {
 		err = ovl_copy_up_last(dentry, attr, false);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index bd6d5c1e667d..39266655d2bd 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -76,12 +76,14 @@ enum ovl_path_type ovl_path_type(struct dentry *dentry)
 	if (oe->__upperdentry) {
 		type = __OVL_PATH_UPPER;
 
-		if (oe->numlower) {
-			if (S_ISDIR(dentry->d_inode->i_mode))
-				type |= __OVL_PATH_MERGE;
-		} else if (!oe->opaque) {
+		/*
+		 * Non-dir dentry can hold lower dentry from previous
+		 * location. Its purity depends only on opaque flag.
+		 */
+		if (oe->numlower && S_ISDIR(dentry->d_inode->i_mode))
+			type |= __OVL_PATH_MERGE;
+		else if (!oe->opaque)
 			type |= __OVL_PATH_PURE;
-		}
 	} else {
 		if (oe->numlower > 1)
 			type |= __OVL_PATH_MERGE;
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index a6e1bca88cc6..8454fb35fcbe 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -131,9 +131,6 @@ extern void syscall_unregfunc(void);
 		void *it_func;						\
 		void *__data;						\
 									\
-		if (!cpu_online(raw_smp_processor_id()))		\
-			return;						\
-									\
 		if (!(cond))						\
 			return;						\
 		prercu;							\
@@ -332,15 +329,19 @@ extern void syscall_unregfunc(void);
  * "void *__data, proto" as the callback prototype.
  */
 #define DECLARE_TRACE_NOARGS(name)					\
-		__DECLARE_TRACE(name, void, , 1, void *__data, __data)
+	__DECLARE_TRACE(name, void, ,					\
+			cpu_online(raw_smp_processor_id()),		\
+			void *__data, __data)
 
 #define DECLARE_TRACE(name, proto, args)				\
-		__DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), 1,	\
-				PARAMS(void *__data, proto),		\
-				PARAMS(__data, args))
+	__DECLARE_TRACE(name, PARAMS(proto), PARAMS(args),		\
+			cpu_online(raw_smp_processor_id()),		\
+			PARAMS(void *__data, proto),			\
+			PARAMS(__data, args))
 
 #define DECLARE_TRACE_CONDITION(name, proto, args, cond)		\
-	__DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), PARAMS(cond), \
+	__DECLARE_TRACE(name, PARAMS(proto), PARAMS(args),		\
+			cpu_online(raw_smp_processor_id()) && (PARAMS(cond)), \
 			PARAMS(void *__data, proto),			\
 			PARAMS(__data, args))
 
diff --git a/include/net/iw_handler.h b/include/net/iw_handler.h
index 8f81bbbc38fc..e0f4109e64c6 100644
--- a/include/net/iw_handler.h
+++ b/include/net/iw_handler.h
@@ -439,6 +439,12 @@ int dev_get_wireless_info(char *buffer, char **start, off_t offset, int length);
 /* Send a single event to user space */
 void wireless_send_event(struct net_device *dev, unsigned int cmd,
 			 union iwreq_data *wrqu, const char *extra);
+#ifdef CONFIG_WEXT_CORE
+/* flush all previous wext events - if work is done from netdev notifiers */
+void wireless_nlevent_flush(void);
+#else
+static inline void wireless_nlevent_flush(void) {}
+#endif
 
 /* We may need a function to send a stream of events to user space.
  * More on that later... */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e1af58e23bee..66e6568a4736 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1562,14 +1562,14 @@ event_sched_out(struct perf_event *event,
 
 	perf_pmu_disable(event->pmu);
 
+	event->tstamp_stopped = tstamp;
+	event->pmu->del(event, 0);
+	event->oncpu = -1;
 	event->state = PERF_EVENT_STATE_INACTIVE;
 	if (event->pending_disable) {
 		event->pending_disable = 0;
 		event->state = PERF_EVENT_STATE_OFF;
 	}
-	event->tstamp_stopped = tstamp;
-	event->pmu->del(event, 0);
-	event->oncpu = -1;
 
 	if (!is_software_event(event))
 		cpuctx->active_oncpu--;
@@ -7641,6 +7641,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		}
 	}
 
+	/* symmetric to unaccount_event() in _free_event() */
+	account_event(event);
+
 	return event;
 
 err_per_task:
@@ -8004,8 +8007,6 @@ SYSCALL_DEFINE5(perf_event_open,
 		}
 	}
 
-	account_event(event);
-
 	/*
 	 * Special case software events and allow them to be part of
 	 * any hardware group.
@@ -8221,7 +8222,12 @@ err_context:
 	perf_unpin_context(ctx);
 	put_ctx(ctx);
 err_alloc:
-	free_event(event);
+	/*
+	 * If event_file is set, the fput() above will have called ->release()
+	 * and that will take care of freeing the event.
+	 */
+	if (!event_file)
+		free_event(event);
 err_cpus:
 	put_online_cpus();
 err_task:
@@ -8265,8 +8271,6 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 	/* Mark owner so we could distinguish it from user events. */
 	event->owner = EVENT_OWNER_KERNEL;
 
-	account_event(event);
-
 	ctx = find_get_context(event->pmu, task, event);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c
index 5c564a68fb50..d71edcbd0c58 100644
--- a/net/mac80211/agg-rx.c
+++ b/net/mac80211/agg-rx.c
@@ -289,7 +289,7 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta,
 	}
 
 	/* prepare A-MPDU MLME for Rx aggregation */
-	tid_agg_rx = kmalloc(sizeof(struct tid_ampdu_rx), GFP_KERNEL);
+	tid_agg_rx = kzalloc(sizeof(*tid_agg_rx), GFP_KERNEL);
 	if (!tid_agg_rx)
 		goto end;
 
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index c0a9187bc3a9..cdf8609a6240 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -90,7 +90,7 @@ struct ieee80211_fragment_entry {
 	unsigned int last_frag;
 	unsigned int extra_len;
 	struct sk_buff_head skb_list;
-	int ccmp; /* Whether fragments were encrypted with CCMP */
+	bool check_sequential_pn; /* needed for CCMP/GCMP */
 	u8 last_pn[6]; /* PN of the last fragment if CCMP was used */
 };
 
diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c
index 3ece7d1034c8..b54f398cda5d 100644
--- a/net/mac80211/rc80211_minstrel.c
+++ b/net/mac80211/rc80211_minstrel.c
@@ -711,7 +711,7 @@ static u32 minstrel_get_expected_throughput(void *priv_sta)
 	 * computing cur_tp
 	 */
 	tmp_mrs = &mi->r[idx].stats;
-	tmp_cur_tp = minstrel_get_tp_avg(&mi->r[idx], tmp_mrs->prob_ewma);
+	tmp_cur_tp = minstrel_get_tp_avg(&mi->r[idx], tmp_mrs->prob_ewma) * 10;
 	tmp_cur_tp = tmp_cur_tp * 1200 * 8 / 1024;
 
 	return tmp_cur_tp;
diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c
index 7430a1df2ab1..1ec889dc2e46 100644
--- a/net/mac80211/rc80211_minstrel_ht.c
+++ b/net/mac80211/rc80211_minstrel_ht.c
@@ -691,7 +691,7 @@ minstrel_aggr_check(struct ieee80211_sta *pubsta, struct sk_buff *skb)
 	if (likely(sta->ampdu_mlme.tid_tx[tid]))
 		return;
 
-	ieee80211_start_tx_ba_session(pubsta, tid, 5000);
+	ieee80211_start_tx_ba_session(pubsta, tid, 0);
 }
 
 static void
@@ -1328,7 +1328,8 @@ static u32 minstrel_ht_get_expected_throughput(void *priv_sta)
 	prob = mi->groups[i].rates[j].prob_ewma;
 
 	/* convert tp_avg from pkt per second in kbps */
-	tp_avg = minstrel_ht_get_tp_avg(mi, i, j, prob) * AVG_PKT_SIZE * 8 / 1024;
+	tp_avg = minstrel_ht_get_tp_avg(mi, i, j, prob) * 10;
+	tp_avg = tp_avg * AVG_PKT_SIZE * 8 / 1024;
 
 	return tp_avg;
 }
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 5793f75c5ffd..d4b08d87537c 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1725,7 +1725,7 @@ ieee80211_reassemble_add(struct ieee80211_sub_if_data *sdata,
 	entry->seq = seq;
 	entry->rx_queue = rx_queue;
 	entry->last_frag = frag;
-	entry->ccmp = 0;
+	entry->check_sequential_pn = false;
 	entry->extra_len = 0;
 
 	return entry;
@@ -1821,15 +1821,27 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
 						 rx->seqno_idx, &(rx->skb));
 		if (rx->key &&
 		    (rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP ||
-		     rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256) &&
+		     rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256 ||
+		     rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP ||
+		     rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP_256) &&
 		    ieee80211_has_protected(fc)) {
 			int queue = rx->security_idx;
-			/* Store CCMP PN so that we can verify that the next
-			 * fragment has a sequential PN value. */
-			entry->ccmp = 1;
+
+			/* Store CCMP/GCMP PN so that we can verify that the
+			 * next fragment has a sequential PN value.
+			 */
+			entry->check_sequential_pn = true;
 			memcpy(entry->last_pn,
 			       rx->key->u.ccmp.rx_pn[queue],
 			       IEEE80211_CCMP_PN_LEN);
+			BUILD_BUG_ON(offsetof(struct ieee80211_key,
+					      u.ccmp.rx_pn) !=
+				     offsetof(struct ieee80211_key,
+					      u.gcmp.rx_pn));
+			BUILD_BUG_ON(sizeof(rx->key->u.ccmp.rx_pn[queue]) !=
+				     sizeof(rx->key->u.gcmp.rx_pn[queue]));
+			BUILD_BUG_ON(IEEE80211_CCMP_PN_LEN !=
+				     IEEE80211_GCMP_PN_LEN);
 		}
 		return RX_QUEUED;
 	}
@@ -1844,15 +1856,21 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
 		return RX_DROP_MONITOR;
 	}
 
-	/* Verify that MPDUs within one MSDU have sequential PN values.
-	 * (IEEE 802.11i, 8.3.3.4.5) */
-	if (entry->ccmp) {
+	/* "The receiver shall discard MSDUs and MMPDUs whose constituent
+	 *  MPDU PN values are not incrementing in steps of 1."
+	 * see IEEE P802.11-REVmc/D5.0, 12.5.3.4.4, item d (for CCMP)
+	 * and IEEE P802.11-REVmc/D5.0, 12.5.5.4.4, item d (for GCMP)
+	 */
+	if (entry->check_sequential_pn) {
 		int i;
 		u8 pn[IEEE80211_CCMP_PN_LEN], *rpn;
 		int queue;
+
 		if (!rx->key ||
 		    (rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP &&
-		     rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP_256))
+		     rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP_256 &&
+		     rx->key->conf.cipher != WLAN_CIPHER_SUITE_GCMP &&
+		     rx->key->conf.cipher != WLAN_CIPHER_SUITE_GCMP_256))
 			return RX_DROP_UNUSABLE;
 		memcpy(pn, entry->last_pn, IEEE80211_CCMP_PN_LEN);
 		for (i = IEEE80211_CCMP_PN_LEN - 1; i >= 0; i--) {
@@ -3359,6 +3377,7 @@ static bool prepare_for_handlers(struct ieee80211_rx_data *rx,
 				return false;
 			/* ignore action frames to TDLS-peers */
 			if (ieee80211_is_action(hdr->frame_control) &&
+			    !is_broadcast_ether_addr(bssid) &&
 			    !ether_addr_equal(bssid, hdr->addr1))
 				return false;
 		}
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 2a0bbd22854b..71e9b84847f3 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -1138,6 +1138,8 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 		return NOTIFY_DONE;
 	}
 
+	wireless_nlevent_flush();
+
 	return NOTIFY_OK;
 }
 
diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c
index c8717c1d082e..b50ee5d622e1 100644
--- a/net/wireless/wext-core.c
+++ b/net/wireless/wext-core.c
@@ -342,6 +342,40 @@ static const int compat_event_type_size[] = {
 
 /* IW event code */
 
+void wireless_nlevent_flush(void)
+{
+	struct sk_buff *skb;
+	struct net *net;
+
+	ASSERT_RTNL();
+
+	for_each_net(net) {
+		while ((skb = skb_dequeue(&net->wext_nlevents)))
+			rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL,
+				    GFP_KERNEL);
+	}
+}
+EXPORT_SYMBOL_GPL(wireless_nlevent_flush);
+
+static int wext_netdev_notifier_call(struct notifier_block *nb,
+				     unsigned long state, void *ptr)
+{
+	/*
+	 * When a netdev changes state in any way, flush all pending messages
+	 * to avoid them going out in a strange order, e.g. RTM_NEWLINK after
+	 * RTM_DELLINK, or with IFF_UP after without IFF_UP during dev_close()
+	 * or similar - all of which could otherwise happen due to delays from
+	 * schedule_work().
+	 */
+	wireless_nlevent_flush();
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block wext_netdev_notifier = {
+	.notifier_call = wext_netdev_notifier_call,
+};
+
 static int __net_init wext_pernet_init(struct net *net)
 {
 	skb_queue_head_init(&net->wext_nlevents);
@@ -360,7 +394,12 @@ static struct pernet_operations wext_pernet_ops = {
 
 static int __init wireless_nlevent_init(void)
 {
-	return register_pernet_subsys(&wext_pernet_ops);
+	int err = register_pernet_subsys(&wext_pernet_ops);
+
+	if (err)
+		return err;
+
+	return register_netdevice_notifier(&wext_netdev_notifier);
 }
 
 subsys_initcall(wireless_nlevent_init);
@@ -368,17 +407,8 @@ subsys_initcall(wireless_nlevent_init);
 /* Process events generated by the wireless layer or the driver. */
 static void wireless_nlevent_process(struct work_struct *work)
 {
-	struct sk_buff *skb;
-	struct net *net;
-
 	rtnl_lock();
-
-	for_each_net(net) {
-		while ((skb = skb_dequeue(&net->wext_nlevents)))
-			rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL,
-				    GFP_KERNEL);
-	}
-
+	wireless_nlevent_flush();
 	rtnl_unlock();
 }
 
diff --git a/scripts/ld-version.sh b/scripts/ld-version.sh
index 198580d245e0..1659b409ef10 100755
--- a/scripts/ld-version.sh
+++ b/scripts/ld-version.sh
@@ -1,7 +1,7 @@
 #!/usr/bin/awk -f
 # extract linker version number from stdin and turn into single number
 	{
-	gsub(".*)", "");
+	gsub(".*\\)", "");
 	split($1,a, ".");
 	print a[1]*10000000 + a[2]*100000 + a[3]*10000 + a[4]*100 + a[5];
 	exit
diff --git a/sound/soc/codecs/wm8958-dsp2.c b/sound/soc/codecs/wm8958-dsp2.c
index c799cca5abeb..6b864c0fc2b6 100644
--- a/sound/soc/codecs/wm8958-dsp2.c
+++ b/sound/soc/codecs/wm8958-dsp2.c
@@ -459,7 +459,7 @@ static int wm8958_put_mbc_enum(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec);
 	struct wm8994 *control = wm8994->wm8994;
-	int value = ucontrol->value.integer.value[0];
+	int value = ucontrol->value.enumerated.item[0];
 	int reg;
 
 	/* Don't allow on the fly reconfiguration */
@@ -549,7 +549,7 @@ static int wm8958_put_vss_enum(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec);
 	struct wm8994 *control = wm8994->wm8994;
-	int value = ucontrol->value.integer.value[0];
+	int value = ucontrol->value.enumerated.item[0];
 	int reg;
 
 	/* Don't allow on the fly reconfiguration */
@@ -582,7 +582,7 @@ static int wm8958_put_vss_hpf_enum(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec);
 	struct wm8994 *control = wm8994->wm8994;
-	int value = ucontrol->value.integer.value[0];
+	int value = ucontrol->value.enumerated.item[0];
 	int reg;
 
 	/* Don't allow on the fly reconfiguration */
@@ -749,7 +749,7 @@ static int wm8958_put_enh_eq_enum(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec);
 	struct wm8994 *control = wm8994->wm8994;
-	int value = ucontrol->value.integer.value[0];
+	int value = ucontrol->value.enumerated.item[0];
 	int reg;
 
 	/* Don't allow on the fly reconfiguration */
diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c
index a1c04dab6684..a484ca8421af 100644
--- a/sound/soc/codecs/wm8994.c
+++ b/sound/soc/codecs/wm8994.c
@@ -361,7 +361,7 @@ static int wm8994_put_drc_enum(struct snd_kcontrol *kcontrol,
 	struct wm8994 *control = wm8994->wm8994;
 	struct wm8994_pdata *pdata = &control->pdata;
 	int drc = wm8994_get_drc(kcontrol->id.name);
-	int value = ucontrol->value.integer.value[0];
+	int value = ucontrol->value.enumerated.item[0];
 
 	if (drc < 0)
 		return drc;
@@ -468,7 +468,7 @@ static int wm8994_put_retune_mobile_enum(struct snd_kcontrol *kcontrol,
 	struct wm8994 *control = wm8994->wm8994;
 	struct wm8994_pdata *pdata = &control->pdata;
 	int block = wm8994_get_retune_mobile_block(kcontrol->id.name);
-	int value = ucontrol->value.integer.value[0];
+	int value = ucontrol->value.enumerated.item[0];
 
 	if (block < 0)
 		return block;
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index d01c2095452f..431d94397219 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -248,7 +248,7 @@ static int wm_adsp_fw_get(struct snd_kcontrol *kcontrol,
 	struct soc_enum *e = (struct soc_enum *)kcontrol->private_value;
 	struct wm_adsp *adsp = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.integer.value[0] = adsp[e->shift_l].fw;
+	ucontrol->value.enumerated.item[0] = adsp[e->shift_l].fw;
 
 	return 0;
 }
@@ -260,16 +260,16 @@ static int wm_adsp_fw_put(struct snd_kcontrol *kcontrol,
 	struct soc_enum *e = (struct soc_enum *)kcontrol->private_value;
 	struct wm_adsp *adsp = snd_soc_codec_get_drvdata(codec);
 
-	if (ucontrol->value.integer.value[0] == adsp[e->shift_l].fw)
+	if (ucontrol->value.enumerated.item[0] == adsp[e->shift_l].fw)
 		return 0;
 
-	if (ucontrol->value.integer.value[0] >= WM_ADSP_NUM_FW)
+	if (ucontrol->value.enumerated.item[0] >= WM_ADSP_NUM_FW)
 		return -EINVAL;
 
 	if (adsp[e->shift_l].running)
 		return -EBUSY;
 
-	adsp[e->shift_l].fw = ucontrol->value.integer.value[0];
+	adsp[e->shift_l].fw = ucontrol->value.enumerated.item[0];
 
 	return 0;
 }
diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c
index b92ab40d2be6..5e8ccb0a7028 100644
--- a/sound/soc/samsung/i2s.c
+++ b/sound/soc/samsung/i2s.c
@@ -480,10 +480,11 @@ static int i2s_set_sysclk(struct snd_soc_dai *dai,
 	unsigned int cdcon_mask = 1 << i2s_regs->cdclkcon_off;
 	unsigned int rsrc_mask = 1 << i2s_regs->rclksrc_off;
 	u32 mod, mask, val = 0;
+	unsigned long flags;
 
-	spin_lock(i2s->lock);
+	spin_lock_irqsave(i2s->lock, flags);
 	mod = readl(i2s->addr + I2SMOD);
-	spin_unlock(i2s->lock);
+	spin_unlock_irqrestore(i2s->lock, flags);
 
 	switch (clk_id) {
 	case SAMSUNG_I2S_OPCLK:
@@ -574,11 +575,11 @@ static int i2s_set_sysclk(struct snd_soc_dai *dai,
 		return -EINVAL;
 	}
 
-	spin_lock(i2s->lock);
+	spin_lock_irqsave(i2s->lock, flags);
 	mod = readl(i2s->addr + I2SMOD);
 	mod = (mod & ~mask) | val;
 	writel(mod, i2s->addr + I2SMOD);
-	spin_unlock(i2s->lock);
+	spin_unlock_irqrestore(i2s->lock, flags);
 
 	return 0;
 }
@@ -589,6 +590,7 @@ static int i2s_set_fmt(struct snd_soc_dai *dai,
 	struct i2s_dai *i2s = to_info(dai);
 	int lrp_shift, sdf_shift, sdf_mask, lrp_rlow, mod_slave;
 	u32 mod, tmp = 0;
+	unsigned long flags;
 
 	lrp_shift = i2s->variant_regs->lrp_off;
 	sdf_shift = i2s->variant_regs->sdf_off;
@@ -648,7 +650,7 @@ static int i2s_set_fmt(struct snd_soc_dai *dai,
 		return -EINVAL;
 	}
 
-	spin_lock(i2s->lock);
+	spin_lock_irqsave(i2s->lock, flags);
 	mod = readl(i2s->addr + I2SMOD);
 	/*
 	 * Don't change the I2S mode if any controller is active on this
@@ -656,7 +658,7 @@ static int i2s_set_fmt(struct snd_soc_dai *dai,
 	 */
 	if (any_active(i2s) &&
 		((mod & (sdf_mask | lrp_rlow | mod_slave)) != tmp)) {
-		spin_unlock(i2s->lock);
+		spin_unlock_irqrestore(i2s->lock, flags);
 		dev_err(&i2s->pdev->dev,
 				"%s:%d Other DAI busy\n", __func__, __LINE__);
 		return -EAGAIN;
@@ -665,7 +667,7 @@ static int i2s_set_fmt(struct snd_soc_dai *dai,
 	mod &= ~(sdf_mask | lrp_rlow | mod_slave);
 	mod |= tmp;
 	writel(mod, i2s->addr + I2SMOD);
-	spin_unlock(i2s->lock);
+	spin_unlock_irqrestore(i2s->lock, flags);
 
 	return 0;
 }
@@ -675,6 +677,7 @@ static int i2s_hw_params(struct snd_pcm_substream *substream,
 {
 	struct i2s_dai *i2s = to_info(dai);
 	u32 mod, mask = 0, val = 0;
+	unsigned long flags;
 
 	if (!is_secondary(i2s))
 		mask |= (MOD_DC2_EN | MOD_DC1_EN);
@@ -743,11 +746,11 @@ static int i2s_hw_params(struct snd_pcm_substream *substream,
 		return -EINVAL;
 	}
 
-	spin_lock(i2s->lock);
+	spin_lock_irqsave(i2s->lock, flags);
 	mod = readl(i2s->addr + I2SMOD);
 	mod = (mod & ~mask) | val;
 	writel(mod, i2s->addr + I2SMOD);
-	spin_unlock(i2s->lock);
+	spin_unlock_irqrestore(i2s->lock, flags);
 
 	samsung_asoc_init_dma_data(dai, &i2s->dma_playback, &i2s->dma_capture);
 
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index b6c12dccb259..28df6adf362b 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -3324,7 +3324,7 @@ static int snd_soc_dapm_dai_link_get(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_dapm_widget *w = snd_kcontrol_chip(kcontrol);
 
-	ucontrol->value.integer.value[0] = w->params_select;
+	ucontrol->value.enumerated.item[0] = w->params_select;
 
 	return 0;
 }
@@ -3338,13 +3338,13 @@ static int snd_soc_dapm_dai_link_put(struct snd_kcontrol *kcontrol,
 	if (w->power)
 		return -EBUSY;
 
-	if (ucontrol->value.integer.value[0] == w->params_select)
+	if (ucontrol->value.enumerated.item[0] == w->params_select)
 		return 0;
 
-	if (ucontrol->value.integer.value[0] >= w->num_params)
+	if (ucontrol->value.enumerated.item[0] >= w->num_params)
 		return -EINVAL;
 
-	w->params_select = ucontrol->value.integer.value[0];
+	w->params_select = ucontrol->value.enumerated.item[0];
 
 	return 0;
 }