Re: Linux 3.14.47

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 6cd63a9010fb..bc6d61773ee2 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -2344,7 +2344,8 @@ should be created before this ioctl is invoked.
 
 Possible features:
 	- KVM_ARM_VCPU_POWER_OFF: Starts the CPU in a power-off state.
-	  Depends on KVM_CAP_ARM_PSCI.
+	  Depends on KVM_CAP_ARM_PSCI.  If not set, the CPU will be powered on
+	  and execute guest code when KVM_RUN is called.
 	- KVM_ARM_VCPU_EL1_32BIT: Starts the CPU in a 32bit mode.
 	  Depends on KVM_CAP_ARM_EL1_32BIT (arm64 only).
 
diff --git a/Makefile b/Makefile
index def39fdd9df4..f9041e6d4d19 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 14
-SUBLEVEL = 46
+SUBLEVEL = 47
 EXTRAVERSION =
 NAME = Remembering Coco
 
diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index 0fa90c962ac8..853e2becad18 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -33,6 +33,11 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu);
 void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr);
 void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr);
 
+static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.hcr = HCR_GUEST_MASK;
+}
+
 static inline bool vcpu_mode_is_32bit(struct kvm_vcpu *vcpu)
 {
 	return 1;
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 0cbdb8ed71cf..9f7923193cda 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -47,6 +47,7 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
 void free_boot_hyp_pgd(void);
 void free_hyp_pgds(void);
 
+void stage2_unmap_vm(struct kvm *kvm);
 int kvm_alloc_stage2_pgd(struct kvm *kvm);
 void kvm_free_stage2_pgd(struct kvm *kvm);
 int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
@@ -78,17 +79,6 @@ static inline void kvm_set_pte(pte_t *pte, pte_t new_pte)
 	flush_pmd_entry(pte);
 }
 
-static inline bool kvm_is_write_fault(unsigned long hsr)
-{
-	unsigned long hsr_ec = hsr >> HSR_EC_SHIFT;
-	if (hsr_ec == HSR_EC_IABT)
-		return false;
-	else if ((hsr & HSR_ISV) && !(hsr & HSR_WNR))
-		return false;
-	else
-		return true;
-}
-
 static inline void kvm_clean_pgd(pgd_t *pgd)
 {
 	clean_dcache_area(pgd, PTRS_PER_S2_PGD * sizeof(pgd_t));
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index df6e75e47ae0..2e74a617147d 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -220,6 +220,11 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 	int err;
 	struct kvm_vcpu *vcpu;
 
+	if (irqchip_in_kernel(kvm) && vgic_initialized(kvm)) {
+		err = -EBUSY;
+		goto out;
+	}
+
 	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
 	if (!vcpu) {
 		err = -ENOMEM;
@@ -427,9 +432,9 @@ static void update_vttbr(struct kvm *kvm)
 
 	/* update vttbr to be used with the new vmid */
 	pgd_phys = virt_to_phys(kvm->arch.pgd);
+	BUG_ON(pgd_phys & ~VTTBR_BADDR_MASK);
 	vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK;
-	kvm->arch.vttbr = pgd_phys & VTTBR_BADDR_MASK;
-	kvm->arch.vttbr |= vmid;
+	kvm->arch.vttbr = pgd_phys | vmid;
 
 	spin_unlock(&kvm_vmid_lock);
 }
@@ -676,10 +681,21 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
 		return ret;
 
 	/*
+	 * Ensure a rebooted VM will fault in RAM pages and detect if the
+	 * guest MMU is turned off and flush the caches as needed.
+	 */
+	if (vcpu->arch.has_run_once)
+		stage2_unmap_vm(vcpu->kvm);
+
+	vcpu_reset_hcr(vcpu);
+
+	/*
 	 * Handle the "start in power-off" case by marking the VCPU as paused.
 	 */
-	if (__test_and_clear_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features))
+	if (test_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features))
 		vcpu->arch.pause = true;
+	else
+		vcpu->arch.pause = false;
 
 	return 0;
 }
@@ -825,7 +841,8 @@ static int hyp_init_cpu_notify(struct notifier_block *self,
 	switch (action) {
 	case CPU_STARTING:
 	case CPU_STARTING_FROZEN:
-		cpu_init_hyp_mode(NULL);
+		if (__hyp_get_vectors() == hyp_default_vectors)
+			cpu_init_hyp_mode(NULL);
 		break;
 	}
 
diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c
index b23a59c1c522..2786eae10c0d 100644
--- a/arch/arm/kvm/guest.c
+++ b/arch/arm/kvm/guest.c
@@ -38,7 +38,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.hcr = HCR_GUEST_MASK;
 	return 0;
 }
 
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 70ed2c1f57b0..524b4b57f650 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -197,7 +197,8 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
 	pgd = pgdp + pgd_index(addr);
 	do {
 		next = kvm_pgd_addr_end(addr, end);
-		unmap_puds(kvm, pgd, addr, next);
+		if (!pgd_none(*pgd))
+			unmap_puds(kvm, pgd, addr, next);
 	} while (pgd++, addr = next, addr != end);
 }
 
@@ -555,6 +556,71 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
 	unmap_range(kvm, kvm->arch.pgd, start, size);
 }
 
+static void stage2_unmap_memslot(struct kvm *kvm,
+				 struct kvm_memory_slot *memslot)
+{
+	hva_t hva = memslot->userspace_addr;
+	phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
+	phys_addr_t size = PAGE_SIZE * memslot->npages;
+	hva_t reg_end = hva + size;
+
+	/*
+	 * A memory region could potentially cover multiple VMAs, and any holes
+	 * between them, so iterate over all of them to find out if we should
+	 * unmap any of them.
+	 *
+	 *     +--------------------------------------------+
+	 * +---------------+----------------+   +----------------+
+	 * |   : VMA 1     |      VMA 2     |   |    VMA 3  :    |
+	 * +---------------+----------------+   +----------------+
+	 *     |               memory region                |
+	 *     +--------------------------------------------+
+	 */
+	do {
+		struct vm_area_struct *vma = find_vma(current->mm, hva);
+		hva_t vm_start, vm_end;
+
+		if (!vma || vma->vm_start >= reg_end)
+			break;
+
+		/*
+		 * Take the intersection of this VMA with the memory region
+		 */
+		vm_start = max(hva, vma->vm_start);
+		vm_end = min(reg_end, vma->vm_end);
+
+		if (!(vma->vm_flags & VM_PFNMAP)) {
+			gpa_t gpa = addr + (vm_start - memslot->userspace_addr);
+			unmap_stage2_range(kvm, gpa, vm_end - vm_start);
+		}
+		hva = vm_end;
+	} while (hva < reg_end);
+}
+
+/**
+ * stage2_unmap_vm - Unmap Stage-2 RAM mappings
+ * @kvm: The struct kvm pointer
+ *
+ * Go through the memregions and unmap any reguler RAM
+ * backing memory already mapped to the VM.
+ */
+void stage2_unmap_vm(struct kvm *kvm)
+{
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
+	int idx;
+
+	idx = srcu_read_lock(&kvm->srcu);
+	spin_lock(&kvm->mmu_lock);
+
+	slots = kvm_memslots(kvm);
+	kvm_for_each_memslot(memslot, slots)
+		stage2_unmap_memslot(kvm, memslot);
+
+	spin_unlock(&kvm->mmu_lock);
+	srcu_read_unlock(&kvm->srcu, idx);
+}
+
 /**
  * kvm_free_stage2_pgd - free all stage-2 tables
  * @kvm:	The KVM struct pointer for the VM.
@@ -746,6 +812,19 @@ static bool transparent_hugepage_adjust(pfn_t *pfnp, phys_addr_t *ipap)
 	return false;
 }
 
+static bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
+{
+	if (kvm_vcpu_trap_is_iabt(vcpu))
+		return false;
+
+	return kvm_vcpu_dabt_iswrite(vcpu);
+}
+
+static bool kvm_is_device_pfn(unsigned long pfn)
+{
+	return !pfn_valid(pfn);
+}
+
 static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			  struct kvm_memory_slot *memslot,
 			  unsigned long fault_status)
@@ -761,7 +840,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	pfn_t pfn;
 	pgprot_t mem_type = PAGE_S2;
 
-	write_fault = kvm_is_write_fault(kvm_vcpu_get_hsr(vcpu));
+	write_fault = kvm_is_write_fault(vcpu);
 	if (fault_status == FSC_PERM && !write_fault) {
 		kvm_err("Unexpected L2 read permission error\n");
 		return -EFAULT;
@@ -770,6 +849,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	/* Let's check if we will get back a huge page backed by hugetlbfs */
 	down_read(&current->mm->mmap_sem);
 	vma = find_vma_intersection(current->mm, hva, hva + 1);
+	if (unlikely(!vma)) {
+		kvm_err("Failed to find VMA for hva 0x%lx\n", hva);
+		up_read(&current->mm->mmap_sem);
+		return -EFAULT;
+	}
+
 	if (is_vm_hugetlb_page(vma)) {
 		hugetlb = true;
 		gfn = (fault_ipa & PMD_MASK) >> PAGE_SHIFT;
@@ -810,7 +895,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (is_error_pfn(pfn))
 		return -EFAULT;
 
-	if (kvm_is_mmio_pfn(pfn))
+	if (kvm_is_device_pfn(pfn))
 		mem_type = PAGE_S2_DEVICE;
 
 	spin_lock(&kvm->mmu_lock);
@@ -836,7 +921,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		}
 		coherent_cache_guest_page(vcpu, hva, PAGE_SIZE);
 		ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte,
-				     mem_type == PAGE_S2_DEVICE);
+			pgprot_val(mem_type) == pgprot_val(PAGE_S2_DEVICE));
 	}
 
 
@@ -912,6 +997,9 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 	memslot = gfn_to_memslot(vcpu->kvm, gfn);
 
+	/* Userspace should not be able to register out-of-bounds IPAs */
+	VM_BUG_ON(fault_ipa >= KVM_PHYS_SIZE);
+
 	ret = user_mem_abort(vcpu, fault_ipa, memslot, fault_status);
 	if (ret == 0)
 		ret = 1;
@@ -1136,6 +1224,14 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				   struct kvm_userspace_memory_region *mem,
 				   enum kvm_mr_change change)
 {
+	/*
+	 * Prevent userspace from creating a memory region outside of the IPA
+	 * space addressable by the KVM guest IPA space.
+	 */
+	if (memslot->base_gfn + memslot->npages >=
+	    (KVM_PHYS_SIZE >> PAGE_SHIFT))
+		return -EFAULT;
+
 	return 0;
 }
 
diff --git a/arch/arm/mach-dove/board-dt.c b/arch/arm/mach-dove/board-dt.c
index 49fa9abd09da..7a7a09a5d5ff 100644
--- a/arch/arm/mach-dove/board-dt.c
+++ b/arch/arm/mach-dove/board-dt.c
@@ -26,7 +26,7 @@ static void __init dove_dt_init(void)
 #ifdef CONFIG_CACHE_TAUROS2
 	tauros2_init(0);
 #endif
-	BUG_ON(mvebu_mbus_dt_init());
+	BUG_ON(mvebu_mbus_dt_init(false));
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c
index 01a5765a8b26..b509556f6cfd 100644
--- a/arch/arm/mach-imx/clk-imx6q.c
+++ b/arch/arm/mach-imx/clk-imx6q.c
@@ -406,7 +406,7 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	clk[gpmi_io]      = imx_clk_gate2("gpmi_io",       "enfc",              base + 0x78, 28);
 	clk[gpmi_apb]     = imx_clk_gate2("gpmi_apb",      "usdhc3",            base + 0x78, 30);
 	clk[rom]          = imx_clk_gate2("rom",           "ahb",               base + 0x7c, 0);
-	clk[sata]         = imx_clk_gate2("sata",          "ipg",               base + 0x7c, 4);
+	clk[sata]         = imx_clk_gate2("sata",          "ahb",               base + 0x7c, 4);
 	clk[sdma]         = imx_clk_gate2("sdma",          "ahb",               base + 0x7c, 6);
 	clk[spba]         = imx_clk_gate2("spba",          "ipg",               base + 0x7c, 12);
 	clk[spdif]        = imx_clk_gate2("spdif",         "spdif_podf",    	base + 0x7c, 14);
diff --git a/arch/arm/mach-kirkwood/board-dt.c b/arch/arm/mach-kirkwood/board-dt.c
index 78188159484d..79e629da1c92 100644
--- a/arch/arm/mach-kirkwood/board-dt.c
+++ b/arch/arm/mach-kirkwood/board-dt.c
@@ -116,7 +116,7 @@ static void __init kirkwood_dt_init(void)
 	 */
 	writel(readl(CPU_CONFIG) & ~CPU_CONFIG_ERROR_PROP, CPU_CONFIG);
 
-	BUG_ON(mvebu_mbus_dt_init());
+	BUG_ON(mvebu_mbus_dt_init(false));
 
 	kirkwood_l2_init();
 
diff --git a/arch/arm/mach-mvebu/armada-370-xp.c b/arch/arm/mach-mvebu/armada-370-xp.c
index f6c9d1d85c14..79c3766a56fd 100644
--- a/arch/arm/mach-mvebu/armada-370-xp.c
+++ b/arch/arm/mach-mvebu/armada-370-xp.c
@@ -41,7 +41,7 @@ static void __init armada_370_xp_timer_and_clk_init(void)
 	of_clk_init(NULL);
 	clocksource_of_init();
 	coherency_init();
-	BUG_ON(mvebu_mbus_dt_init());
+	BUG_ON(mvebu_mbus_dt_init(coherency_available()));
 #ifdef CONFIG_CACHE_L2X0
 	l2x0_of_init(0, ~0UL);
 #endif
diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c
index c295c10f9217..49bad4d66fa2 100644
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -121,6 +121,20 @@ static struct notifier_block mvebu_hwcc_platform_nb = {
 	.notifier_call = mvebu_hwcc_platform_notifier,
 };
 
+/*
+ * Keep track of whether we have IO hardware coherency enabled or not.
+ * On Armada 370's we will not be using it for example. We need to make
+ * that available [through coherency_available()] so the mbus controller
+ * doesn't enable the IO coherency bit in the attribute bits of the
+ * chip selects.
+ */
+static int coherency_enabled;
+
+int coherency_available(void)
+{
+	return coherency_enabled;
+}
+
 int __init coherency_init(void)
 {
 	struct device_node *np;
@@ -164,6 +178,7 @@ int __init coherency_init(void)
 		coherency_base = of_iomap(np, 0);
 		coherency_cpu_base = of_iomap(np, 1);
 		set_cpu_coherent(cpu_logical_map(smp_processor_id()), 0);
+		coherency_enabled = 1;
 		of_node_put(np);
 	}
 
diff --git a/arch/arm/mach-mvebu/coherency.h b/arch/arm/mach-mvebu/coherency.h
index 760226c41353..63e18c64a8e3 100644
--- a/arch/arm/mach-mvebu/coherency.h
+++ b/arch/arm/mach-mvebu/coherency.h
@@ -17,6 +17,7 @@
 extern unsigned long coherency_phys_base;
 
 int set_cpu_coherent(unsigned int cpu_id, int smp_group_id);
+int coherency_available(void);
 int coherency_init(void);
 
 #endif	/* __MACH_370_XP_COHERENCY_H */
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 00fbaa75dc7b..ea68925a4480 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -18,6 +18,7 @@
 #ifndef __ARM64_KVM_ARM_H__
 #define __ARM64_KVM_ARM_H__
 
+#include <asm/memory.h>
 #include <asm/types.h>
 
 /* Hyp Configuration Register (HCR) bits */
@@ -122,6 +123,17 @@
 #define VTCR_EL2_T0SZ_MASK	0x3f
 #define VTCR_EL2_T0SZ_40B	24
 
+/*
+ * We configure the Stage-2 page tables to always restrict the IPA space to be
+ * 40 bits wide (T0SZ = 24).  Systems with a PARange smaller than 40 bits are
+ * not known to exist and will break with this configuration.
+ *
+ * Note that when using 4K pages, we concatenate two first level page tables
+ * together.
+ *
+ * The magic numbers used for VTTBR_X in this patch can be found in Tables
+ * D4-23 and D4-25 in ARM DDI 0487A.b.
+ */
 #ifdef CONFIG_ARM64_64K_PAGES
 /*
  * Stage2 translation configuration:
@@ -151,9 +163,9 @@
 #endif
 
 #define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
-#define VTTBR_BADDR_MASK  (((1LLU << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
-#define VTTBR_VMID_SHIFT  (48LLU)
-#define VTTBR_VMID_MASK	  (0xffLLU << VTTBR_VMID_SHIFT)
+#define VTTBR_BADDR_MASK  (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
+#define VTTBR_VMID_SHIFT  (UL(48))
+#define VTTBR_VMID_MASK	  (UL(0xFF) << VTTBR_VMID_SHIFT)
 
 /* Hyp System Trap Register */
 #define HSTR_EL2_TTEE	(1 << 16)
@@ -176,13 +188,13 @@
 
 /* Exception Syndrome Register (ESR) bits */
 #define ESR_EL2_EC_SHIFT	(26)
-#define ESR_EL2_EC		(0x3fU << ESR_EL2_EC_SHIFT)
-#define ESR_EL2_IL		(1U << 25)
+#define ESR_EL2_EC		(UL(0x3f) << ESR_EL2_EC_SHIFT)
+#define ESR_EL2_IL		(UL(1) << 25)
 #define ESR_EL2_ISS		(ESR_EL2_IL - 1)
 #define ESR_EL2_ISV_SHIFT	(24)
-#define ESR_EL2_ISV		(1U << ESR_EL2_ISV_SHIFT)
+#define ESR_EL2_ISV		(UL(1) << ESR_EL2_ISV_SHIFT)
 #define ESR_EL2_SAS_SHIFT	(22)
-#define ESR_EL2_SAS		(3U << ESR_EL2_SAS_SHIFT)
+#define ESR_EL2_SAS		(UL(3) << ESR_EL2_SAS_SHIFT)
 #define ESR_EL2_SSE		(1 << 21)
 #define ESR_EL2_SRT_SHIFT	(16)
 #define ESR_EL2_SRT_MASK	(0x1f << ESR_EL2_SRT_SHIFT)
@@ -196,16 +208,16 @@
 #define ESR_EL2_FSC_TYPE	(0x3c)
 
 #define ESR_EL2_CV_SHIFT	(24)
-#define ESR_EL2_CV		(1U << ESR_EL2_CV_SHIFT)
+#define ESR_EL2_CV		(UL(1) << ESR_EL2_CV_SHIFT)
 #define ESR_EL2_COND_SHIFT	(20)
-#define ESR_EL2_COND		(0xfU << ESR_EL2_COND_SHIFT)
+#define ESR_EL2_COND		(UL(0xf) << ESR_EL2_COND_SHIFT)
 
 
 #define FSC_FAULT	(0x04)
 #define FSC_PERM	(0x0c)
 
 /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
-#define HPFAR_MASK	(~0xFUL)
+#define HPFAR_MASK	(~UL(0xf))
 
 #define ESR_EL2_EC_UNKNOWN	(0x00)
 #define ESR_EL2_EC_WFI		(0x01)
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index dd8ecfc3f995..681cb9080100 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -38,6 +38,11 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu);
 void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr);
 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;
+}
+
 static inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu)
 {
 	return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pc;
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 8e138c7c53ac..0d51874c838f 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -59,10 +59,9 @@
 #define KERN_TO_HYP(kva)	((unsigned long)kva - PAGE_OFFSET + HYP_PAGE_OFFSET)
 
 /*
- * Align KVM with the kernel's view of physical memory. Should be
- * 40bit IPA, with PGD being 8kB aligned in the 4KB page configuration.
+ * We currently only support a 40bit IPA.
  */
-#define KVM_PHYS_SHIFT	PHYS_MASK_SHIFT
+#define KVM_PHYS_SHIFT	(40)
 #define KVM_PHYS_SIZE	(1UL << KVM_PHYS_SHIFT)
 #define KVM_PHYS_MASK	(KVM_PHYS_SIZE - 1UL)
 
@@ -75,6 +74,7 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
 void free_boot_hyp_pgd(void);
 void free_hyp_pgds(void);
 
+void stage2_unmap_vm(struct kvm *kvm);
 int kvm_alloc_stage2_pgd(struct kvm *kvm);
 void kvm_free_stage2_pgd(struct kvm *kvm);
 int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
@@ -93,19 +93,6 @@ void kvm_clear_hyp_idmap(void);
 #define	kvm_set_pte(ptep, pte)		set_pte(ptep, pte)
 #define	kvm_set_pmd(pmdp, pmd)		set_pmd(pmdp, pmd)
 
-static inline bool kvm_is_write_fault(unsigned long esr)
-{
-	unsigned long esr_ec = esr >> ESR_EL2_EC_SHIFT;
-
-	if (esr_ec == ESR_EL2_EC_IABT)
-		return false;
-
-	if ((esr & ESR_EL2_ISV) && !(esr & ESR_EL2_WNR))
-		return false;
-
-	return true;
-}
-
 static inline void kvm_clean_pgd(pgd_t *pgd) {}
 static inline void kvm_clean_pmd_entry(pmd_t *pmd) {}
 static inline void kvm_clean_pte(pte_t *pte) {}
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 08745578d54d..a8d81fa8c527 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -38,7 +38,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS;
 	return 0;
 }
 
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 3974881388bb..b76159a153a5 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -54,8 +54,7 @@ static void *arm64_swiotlb_alloc_coherent(struct device *dev, size_t size,
 
 		*dma_handle = phys_to_dma(dev, page_to_phys(page));
 		addr = page_address(page);
-		if (flags & __GFP_ZERO)
-			memset(addr, 0, size);
+		memset(addr, 0, size);
 		return addr;
 	} else {
 		return swiotlb_alloc_coherent(dev, size, dma_handle, flags);
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 2f645c90e4d8..5dab54accc56 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -160,7 +160,7 @@ config SBUS
 
 config NEED_DMA_MAP_STATE
 	def_bool y
-	depends on X86_64 || INTEL_IOMMU || DMA_API_DEBUG
+	depends on X86_64 || INTEL_IOMMU || DMA_API_DEBUG || SWIOTLB
 
 config NEED_SG_DMA_LENGTH
 	def_bool y
diff --git a/arch/x86/kernel/cpu/microcode/intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c
index 18f739129e72..43a07bf48dea 100644
--- a/arch/x86/kernel/cpu/microcode/intel_early.c
+++ b/arch/x86/kernel/cpu/microcode/intel_early.c
@@ -321,7 +321,7 @@ get_matching_model_microcode(int cpu, unsigned long start,
 	unsigned int mc_saved_count = mc_saved_data->mc_saved_count;
 	int i;
 
-	while (leftover) {
+	while (leftover && mc_saved_count < ARRAY_SIZE(mc_saved_tmp)) {
 		mc_header = (struct microcode_header_intel *)ucode_ptr;
 
 		mc_size = get_totalsize(mc_header);
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index a1f5b1866cbe..490fee15fea5 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -326,13 +326,16 @@ int __kprobes __copy_instruction(u8 *dest, u8 *src)
 {
 	struct insn insn;
 	kprobe_opcode_t buf[MAX_INSN_SIZE];
+	int length;
 
 	kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, (unsigned long)src));
 	insn_get_length(&insn);
+	length = insn.length;
+
 	/* Another subsystem puts a breakpoint, failed to recover */
 	if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
 		return 0;
-	memcpy(dest, insn.kaddr, insn.length);
+	memcpy(dest, insn.kaddr, length);
 
 #ifdef CONFIG_X86_64
 	if (insn_rip_relative(&insn)) {
@@ -362,7 +365,7 @@ int __kprobes __copy_instruction(u8 *dest, u8 *src)
 		*(s32 *) disp = (s32) newdisp;
 	}
 #endif
-	return insn.length;
+	return length;
 }
 
 static int __kprobes arch_copy_kprobe(struct kprobe *p)
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 9643eda60a52..074633411ea8 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -495,8 +495,10 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	if (svm->vmcb->control.next_rip != 0)
+	if (svm->vmcb->control.next_rip != 0) {
+		WARN_ON(!static_cpu_has(X86_FEATURE_NRIPS));
 		svm->next_rip = svm->vmcb->control.next_rip;
+	}
 
 	if (!svm->next_rip) {
 		if (emulate_instruction(vcpu, EMULTYPE_SKIP) !=
@@ -4246,7 +4248,9 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu,
 		break;
 	}
 
-	vmcb->control.next_rip  = info->next_rip;
+	/* TODO: Advertise NRIPS to guest hypervisor unconditionally */
+	if (static_cpu_has(X86_FEATURE_NRIPS))
+		vmcb->control.next_rip  = info->next_rip;
 	vmcb->control.exit_code = icpt_info.exit_code;
 	vmexit = nested_svm_exit_handled(svm);
 
diff --git a/drivers/bus/mvebu-mbus.c b/drivers/bus/mvebu-mbus.c
index e990deed2d33..1aa0130a63d5 100644
--- a/drivers/bus/mvebu-mbus.c
+++ b/drivers/bus/mvebu-mbus.c
@@ -701,7 +701,6 @@ static int __init mvebu_mbus_common_init(struct mvebu_mbus_state *mbus,
 					 phys_addr_t sdramwins_phys_base,
 					 size_t sdramwins_size)
 {
-	struct device_node *np;
 	int win;
 
 	mbus->mbuswins_base = ioremap(mbuswins_phys_base, mbuswins_size);
@@ -714,12 +713,6 @@ static int __init mvebu_mbus_common_init(struct mvebu_mbus_state *mbus,
 		return -ENOMEM;
 	}
 
-	np = of_find_compatible_node(NULL, NULL, "marvell,coherency-fabric");
-	if (np) {
-		mbus->hw_io_coherency = 1;
-		of_node_put(np);
-	}
-
 	for (win = 0; win < mbus->soc->num_wins; win++)
 		mvebu_mbus_disable_window(mbus, win);
 
@@ -889,7 +882,7 @@ static void __init mvebu_mbus_get_pcie_resources(struct device_node *np,
 	}
 }
 
-int __init mvebu_mbus_dt_init(void)
+int __init mvebu_mbus_dt_init(bool is_coherent)
 {
 	struct resource mbuswins_res, sdramwins_res;
 	struct device_node *np, *controller;
@@ -928,6 +921,8 @@ int __init mvebu_mbus_dt_init(void)
 		return -EINVAL;
 	}
 
+	mbus_state.hw_io_coherency = is_coherent;
+
 	/* Get optional pcie-{mem,io}-aperture properties */
 	mvebu_mbus_get_pcie_resources(np, &mbus_state.pcie_mem_aperture,
 					  &mbus_state.pcie_io_aperture);
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index c611bcc01f7e..3e623ab5e315 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -765,7 +765,7 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 	u32 reg;
 	u64 limit, prv = 0;
 	u64 tmp_mb;
-	u32 mb, kb;
+	u32 gb, mb;
 	u32 rir_way;
 
 	/*
@@ -775,15 +775,17 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 	pvt->tolm = pvt->info.get_tolm(pvt);
 	tmp_mb = (1 + pvt->tolm) >> 20;
 
-	mb = div_u64_rem(tmp_mb, 1000, &kb);
-	edac_dbg(0, "TOLM: %u.%03u GB (0x%016Lx)\n", mb, kb, (u64)pvt->tolm);
+	gb = div_u64_rem(tmp_mb, 1024, &mb);
+	edac_dbg(0, "TOLM: %u.%03u GB (0x%016Lx)\n",
+		gb, (mb*1000)/1024, (u64)pvt->tolm);
 
 	/* Address range is already 45:25 */
 	pvt->tohm = pvt->info.get_tohm(pvt);
 	tmp_mb = (1 + pvt->tohm) >> 20;
 
-	mb = div_u64_rem(tmp_mb, 1000, &kb);
-	edac_dbg(0, "TOHM: %u.%03u GB (0x%016Lx)\n", mb, kb, (u64)pvt->tohm);
+	gb = div_u64_rem(tmp_mb, 1024, &mb);
+	edac_dbg(0, "TOHM: %u.%03u GB (0x%016Lx)\n",
+		gb, (mb*1000)/1024, (u64)pvt->tohm);
 
 	/*
 	 * Step 2) Get SAD range and SAD Interleave list
@@ -805,11 +807,11 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 			break;
 
 		tmp_mb = (limit + 1) >> 20;
-		mb = div_u64_rem(tmp_mb, 1000, &kb);
+		gb = div_u64_rem(tmp_mb, 1024, &mb);
 		edac_dbg(0, "SAD#%d %s up to %u.%03u GB (0x%016Lx) Interleave: %s reg=0x%08x\n",
 			 n_sads,
 			 get_dram_attr(reg),
-			 mb, kb,
+			 gb, (mb*1000)/1024,
 			 ((u64)tmp_mb) << 20L,
 			 INTERLEAVE_MODE(reg) ? "8:6" : "[8:6]XOR[18:16]",
 			 reg);
@@ -840,9 +842,9 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 			break;
 		tmp_mb = (limit + 1) >> 20;
 
-		mb = div_u64_rem(tmp_mb, 1000, &kb);
+		gb = div_u64_rem(tmp_mb, 1024, &mb);
 		edac_dbg(0, "TAD#%d: up to %u.%03u GB (0x%016Lx), socket interleave %d, memory interleave %d, TGT: %d, %d, %d, %d, reg=0x%08x\n",
-			 n_tads, mb, kb,
+			 n_tads, gb, (mb*1000)/1024,
 			 ((u64)tmp_mb) << 20L,
 			 (u32)TAD_SOCK(reg),
 			 (u32)TAD_CH(reg),
@@ -865,10 +867,10 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 					      tad_ch_nilv_offset[j],
 					      &reg);
 			tmp_mb = TAD_OFFSET(reg) >> 20;
-			mb = div_u64_rem(tmp_mb, 1000, &kb);
+			gb = div_u64_rem(tmp_mb, 1024, &mb);
 			edac_dbg(0, "TAD CH#%d, offset #%d: %u.%03u GB (0x%016Lx), reg=0x%08x\n",
 				 i, j,
-				 mb, kb,
+				 gb, (mb*1000)/1024,
 				 ((u64)tmp_mb) << 20L,
 				 reg);
 		}
@@ -890,10 +892,10 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 
 			tmp_mb = RIR_LIMIT(reg) >> 20;
 			rir_way = 1 << RIR_WAY(reg);
-			mb = div_u64_rem(tmp_mb, 1000, &kb);
+			gb = div_u64_rem(tmp_mb, 1024, &mb);
 			edac_dbg(0, "CH#%d RIR#%d, limit: %u.%03u GB (0x%016Lx), way: %d, reg=0x%08x\n",
 				 i, j,
-				 mb, kb,
+				 gb, (mb*1000)/1024,
 				 ((u64)tmp_mb) << 20L,
 				 rir_way,
 				 reg);
@@ -904,10 +906,10 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 						      &reg);
 				tmp_mb = RIR_OFFSET(reg) << 6;
 
-				mb = div_u64_rem(tmp_mb, 1000, &kb);
+				gb = div_u64_rem(tmp_mb, 1024, &mb);
 				edac_dbg(0, "CH#%d RIR#%d INTL#%d, offset %u.%03u GB (0x%016Lx), tgt: %d, reg=0x%08x\n",
 					 i, j, k,
-					 mb, kb,
+					 gb, (mb*1000)/1024,
 					 ((u64)tmp_mb) << 20L,
 					 (u32)RIR_RNK_TGT(reg),
 					 reg);
@@ -945,7 +947,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci,
 	u8			ch_way, sck_way, pkg, sad_ha = 0;
 	u32			tad_offset;
 	u32			rir_way;
-	u32			mb, kb;
+	u32			mb, gb;
 	u64			ch_addr, offset, limit = 0, prv = 0;
 
 
@@ -1183,10 +1185,10 @@ static int get_memory_error_data(struct mem_ctl_info *mci,
 			continue;
 
 		limit = RIR_LIMIT(reg);
-		mb = div_u64_rem(limit >> 20, 1000, &kb);
+		gb = div_u64_rem(limit >> 20, 1024, &mb);
 		edac_dbg(0, "RIR#%d, limit: %u.%03u GB (0x%016Lx), way: %d\n",
 			 n_rir,
-			 mb, kb,
+			 gb, (mb*1000)/1024,
 			 limit,
 			 1 << RIR_WAY(reg));
 		if  (ch_addr <= limit)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 019a04a31384..a467261b10b9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -810,8 +810,11 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	tx_desc->ctrl.fence_size = (real_size / 16) & 0x3f;
 	tx_desc->ctrl.srcrb_flags = priv->ctrl_flags;
 	if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) {
-		tx_desc->ctrl.srcrb_flags |= cpu_to_be32(MLX4_WQE_CTRL_IP_CSUM |
-							 MLX4_WQE_CTRL_TCP_UDP_CSUM);
+		if (!skb->encapsulation)
+			tx_desc->ctrl.srcrb_flags |= cpu_to_be32(MLX4_WQE_CTRL_IP_CSUM |
+								 MLX4_WQE_CTRL_TCP_UDP_CSUM);
+		else
+			tx_desc->ctrl.srcrb_flags |= cpu_to_be32(MLX4_WQE_CTRL_IP_CSUM);
 		ring->tx_csum++;
 	}
 
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 528bff5ec91f..85d370e1ca79 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -3984,10 +3984,6 @@ static int hpsa_kdump_hard_reset_controller(struct pci_dev *pdev)
 
 	/* Save the PCI command register */
 	pci_read_config_word(pdev, 4, &command_register);
-	/* Turn the board off.  This is so that later pci_restore_state()
-	 * won't turn the board on before the rest of config space is ready.
-	 */
-	pci_disable_device(pdev);
 	pci_save_state(pdev);
 
 	/* find the first memory BAR, so we can find the cfg table */
@@ -4035,11 +4031,6 @@ static int hpsa_kdump_hard_reset_controller(struct pci_dev *pdev)
 		goto unmap_cfgtable;
 
 	pci_restore_state(pdev);
-	rc = pci_enable_device(pdev);
-	if (rc) {
-		dev_warn(&pdev->dev, "failed to enable device.\n");
-		goto unmap_cfgtable;
-	}
 	pci_write_config_word(pdev, 4, command_register);
 
 	/* Some devices (notably the HP Smart Array 5i Controller)
@@ -4525,6 +4516,23 @@ static int hpsa_init_reset_devices(struct pci_dev *pdev)
 	if (!reset_devices)
 		return 0;
 
+	/* kdump kernel is loading, we don't know in which state is
+	 * the pci interface. The dev->enable_cnt is equal zero
+	 * so we call enable+disable, wait a while and switch it on.
+	 */
+	rc = pci_enable_device(pdev);
+	if (rc) {
+		dev_warn(&pdev->dev, "Failed to enable PCI device\n");
+		return -ENODEV;
+	}
+	pci_disable_device(pdev);
+	msleep(260);			/* a randomly chosen number */
+	rc = pci_enable_device(pdev);
+	if (rc) {
+		dev_warn(&pdev->dev, "failed to enable device.\n");
+		return -ENODEV;
+	}
+	pci_set_master(pdev);
 	/* Reset the controller with a PCI power-cycle or via doorbell */
 	rc = hpsa_kdump_hard_reset_controller(pdev);
 
@@ -4533,10 +4541,11 @@ static int hpsa_init_reset_devices(struct pci_dev *pdev)
 	 * "performant mode".  Or, it might be 640x, which can't reset
 	 * due to concerns about shared bbwc between 6402/6404 pair.
 	 */
-	if (rc == -ENOTSUPP)
-		return rc; /* just try to do the kdump anyhow. */
-	if (rc)
-		return -ENODEV;
+	if (rc) {
+		if (rc != -ENOTSUPP) /* just try to do the kdump anyhow. */
+			rc = -ENODEV;
+		goto out_disable;
+	}
 
 	/* Now try to get the controller to respond to a no-op */
 	dev_warn(&pdev->dev, "Waiting for controller to respond to no-op\n");
@@ -4547,7 +4556,11 @@ static int hpsa_init_reset_devices(struct pci_dev *pdev)
 			dev_warn(&pdev->dev, "no-op failed%s\n",
 					(i < 11 ? "; re-trying" : ""));
 	}
-	return 0;
+
+out_disable:
+
+	pci_disable_device(pdev);
+	return rc;
 }
 
 static int hpsa_allocate_cmd_pool(struct ctlr_info *h)
@@ -4690,6 +4703,7 @@ static void hpsa_undo_allocations_after_kdump_soft_reset(struct ctlr_info *h)
 		iounmap(h->transtable);
 	if (h->cfgtable)
 		iounmap(h->cfgtable);
+	pci_disable_device(h->pdev);
 	pci_release_regions(h->pdev);
 	kfree(h);
 }
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 93de3ba994e7..f8ffee4562d3 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -2963,7 +2963,7 @@ done:
 	 */
 	if (!p->leave_spinning)
 		btrfs_set_path_blocking(p);
-	if (ret < 0)
+	if (ret < 0 && !p->skip_release_on_error)
 		btrfs_release_path(p);
 	return ret;
 }
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index d3511cc17091..3b39eb4cb309 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -608,6 +608,7 @@ struct btrfs_path {
 	unsigned int skip_locking:1;
 	unsigned int leave_spinning:1;
 	unsigned int search_commit_root:1;
+	unsigned int skip_release_on_error:1;
 };
 
 /*
@@ -3609,6 +3610,10 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans,
 int verify_dir_item(struct btrfs_root *root,
 		    struct extent_buffer *leaf,
 		    struct btrfs_dir_item *dir_item);
+struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root,
+						 struct btrfs_path *path,
+						 const char *name,
+						 int name_len);
 
 /* orphan.c */
 int btrfs_insert_orphan_item(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c
index a0691df5dcea..9521a93b5303 100644
--- a/fs/btrfs/dir-item.c
+++ b/fs/btrfs/dir-item.c
@@ -21,10 +21,6 @@
 #include "hash.h"
 #include "transaction.h"
 
-static struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root,
-			      struct btrfs_path *path,
-			      const char *name, int name_len);
-
 /*
  * insert a name into a directory, doing overflow properly if there is a hash
  * collision.  data_size indicates how big the item inserted should be.  On
@@ -383,9 +379,9 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans,
  * this walks through all the entries in a dir item and finds one
  * for a specific name.
  */
-static struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root,
-			      struct btrfs_path *path,
-			      const char *name, int name_len)
+struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root,
+						 struct btrfs_path *path,
+						 const char *name, int name_len)
 {
 	struct btrfs_dir_item *dir_item;
 	unsigned long name_ptr;
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 488e987c3374..618e86ceede7 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -29,6 +29,7 @@
 #include "xattr.h"
 #include "disk-io.h"
 #include "props.h"
+#include "locking.h"
 
 
 ssize_t __btrfs_getxattr(struct inode *inode, const char *name,
@@ -91,7 +92,7 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
 		       struct inode *inode, const char *name,
 		       const void *value, size_t size, int flags)
 {
-	struct btrfs_dir_item *di;
+	struct btrfs_dir_item *di = NULL;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_path *path;
 	size_t name_len = strlen(name);
@@ -103,84 +104,119 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
+	path->skip_release_on_error = 1;
+
+	if (!value) {
+		di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode),
+					name, name_len, -1);
+		if (!di && (flags & XATTR_REPLACE))
+			ret = -ENODATA;
+		else if (di)
+			ret = btrfs_delete_one_dir_name(trans, root, path, di);
+		goto out;
+	}
 
+	/*
+	 * For a replace we can't just do the insert blindly.
+	 * Do a lookup first (read-only btrfs_search_slot), and return if xattr
+	 * doesn't exist. If it exists, fall down below to the insert/replace
+	 * path - we can't race with a concurrent xattr delete, because the VFS
+	 * locks the inode's i_mutex before calling setxattr or removexattr.
+	 */
 	if (flags & XATTR_REPLACE) {
-		di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode), name,
-					name_len, -1);
-		if (IS_ERR(di)) {
-			ret = PTR_ERR(di);
-			goto out;
-		} else if (!di) {
+		ASSERT(mutex_is_locked(&inode->i_mutex));
+		di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode),
+					name, name_len, 0);
+		if (!di) {
 			ret = -ENODATA;
 			goto out;
 		}
-		ret = btrfs_delete_one_dir_name(trans, root, path, di);
-		if (ret)
-			goto out;
 		btrfs_release_path(path);
+		di = NULL;
+	}
 
+	ret = btrfs_insert_xattr_item(trans, root, path, btrfs_ino(inode),
+				      name, name_len, value, size);
+	if (ret == -EOVERFLOW) {
 		/*
-		 * remove the attribute
+		 * We have an existing item in a leaf, split_leaf couldn't
+		 * expand it. That item might have or not a dir_item that
+		 * matches our target xattr, so lets check.
 		 */
-		if (!value)
-			goto out;
-	} else {
-		di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode),
-					name, name_len, 0);
-		if (IS_ERR(di)) {
-			ret = PTR_ERR(di);
+		ret = 0;
+		btrfs_assert_tree_locked(path->nodes[0]);
+		di = btrfs_match_dir_item_name(root, path, name, name_len);
+		if (!di && !(flags & XATTR_REPLACE)) {
+			ret = -ENOSPC;
 			goto out;
 		}
-		if (!di && !value)
-			goto out;
-		btrfs_release_path(path);
+	} else if (ret == -EEXIST) {
+		ret = 0;
+		di = btrfs_match_dir_item_name(root, path, name, name_len);
+		ASSERT(di); /* logic error */
+	} else if (ret) {
+		goto out;
 	}
 
-again:
-	ret = btrfs_insert_xattr_item(trans, root, path, btrfs_ino(inode),
-				      name, name_len, value, size);
-	/*
-	 * If we're setting an xattr to a new value but the new value is say
-	 * exactly BTRFS_MAX_XATTR_SIZE, we could end up with EOVERFLOW getting
-	 * back from split_leaf.  This is because it thinks we'll be extending
-	 * the existing item size, but we're asking for enough space to add the
-	 * item itself.  So if we get EOVERFLOW just set ret to EEXIST and let
-	 * the rest of the function figure it out.
-	 */
-	if (ret == -EOVERFLOW)
+	if (di && (flags & XATTR_CREATE)) {
 		ret = -EEXIST;
+		goto out;
+	}
 
-	if (ret == -EEXIST) {
-		if (flags & XATTR_CREATE)
-			goto out;
+	if (di) {
 		/*
-		 * We can't use the path we already have since we won't have the
-		 * proper locking for a delete, so release the path and
-		 * re-lookup to delete the thing.
+		 * We're doing a replace, and it must be atomic, that is, at
+		 * any point in time we have either the old or the new xattr
+		 * value in the tree. We don't want readers (getxattr and
+		 * listxattrs) to miss a value, this is specially important
+		 * for ACLs.
 		 */
-		btrfs_release_path(path);
-		di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode),
-					name, name_len, -1);
-		if (IS_ERR(di)) {
-			ret = PTR_ERR(di);
-			goto out;
-		} else if (!di) {
-			/* Shouldn't happen but just in case... */
-			btrfs_release_path(path);
-			goto again;
+		const int slot = path->slots[0];
+		struct extent_buffer *leaf = path->nodes[0];
+		const u16 old_data_len = btrfs_dir_data_len(leaf, di);
+		const u32 item_size = btrfs_item_size_nr(leaf, slot);
+		const u32 data_size = sizeof(*di) + name_len + size;
+		struct btrfs_item *item;
+		unsigned long data_ptr;
+		char *ptr;
+
+		if (size > old_data_len) {
+			if (btrfs_leaf_free_space(root, leaf) <
+			    (size - old_data_len)) {
+				ret = -ENOSPC;
+				goto out;
+			}
 		}
 
-		ret = btrfs_delete_one_dir_name(trans, root, path, di);
-		if (ret)
-			goto out;
+		if (old_data_len + name_len + sizeof(*di) == item_size) {
+			/* No other xattrs packed in the same leaf item. */
+			if (size > old_data_len)
+				btrfs_extend_item(root, path,
+						  size - old_data_len);
+			else if (size < old_data_len)
+				btrfs_truncate_item(root, path, data_size, 1);
+		} else {
+			/* There are other xattrs packed in the same item. */
+			ret = btrfs_delete_one_dir_name(trans, root, path, di);
+			if (ret)
+				goto out;
+			btrfs_extend_item(root, path, data_size);
+		}
 
+		item = btrfs_item_nr(slot);
+		ptr = btrfs_item_ptr(leaf, slot, char);
+		ptr += btrfs_item_size(leaf, item) - data_size;
+		di = (struct btrfs_dir_item *)ptr;
+		btrfs_set_dir_data_len(leaf, di, size);
+		data_ptr = ((unsigned long)(di + 1)) + name_len;
+		write_extent_buffer(leaf, value, data_ptr, size);
+		btrfs_mark_buffer_dirty(leaf);
+	} else {
 		/*
-		 * We have a value to set, so go back and try to insert it now.
+		 * Insert, and we had space for the xattr, so path->slots[0] is
+		 * where our xattr dir_item is and btrfs_insert_xattr_item()
+		 * filled it.
 		 */
-		if (value) {
-			btrfs_release_path(path);
-			goto again;
-		}
 	}
 out:
 	btrfs_free_path(path);
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 7fe30f655aa5..35f54bc96519 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2478,9 +2478,7 @@ static ssize_t ocfs2_file_splice_write(struct pipe_inode_info *pipe,
 	struct address_space *mapping = out->f_mapping;
 	struct inode *inode = mapping->host;
 	struct splice_desc sd = {
-		.total_len = len,
 		.flags = flags,
-		.pos = *ppos,
 		.u.file = out,
 	};
 
@@ -2490,6 +2488,12 @@ static ssize_t ocfs2_file_splice_write(struct pipe_inode_info *pipe,
 			out->f_path.dentry->d_name.len,
 			out->f_path.dentry->d_name.name, len);
 
+	ret = generic_write_checks(out, ppos, &len, 0);
+	if (ret)
+		return ret;
+	sd.total_len = len;
+	sd.pos = *ppos;
+
 	pipe_lock(pipe);
 
 	splice_from_pipe_begin(&sd);
diff --git a/fs/splice.c b/fs/splice.c
index 12028fa41def..f345d53f94da 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1012,13 +1012,17 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
 	struct address_space *mapping = out->f_mapping;
 	struct inode *inode = mapping->host;
 	struct splice_desc sd = {
-		.total_len = len,
 		.flags = flags,
-		.pos = *ppos,
 		.u.file = out,
 	};
 	ssize_t ret;
 
+	ret = generic_write_checks(out, ppos, &len, S_ISBLK(inode->i_mode));
+	if (ret)
+		return ret;
+	sd.total_len = len;
+	sd.pos = *ppos;
+
 	pipe_lock(pipe);
 
 	splice_from_pipe_begin(&sd);
diff --git a/include/linux/mbus.h b/include/linux/mbus.h
index 345b8c53b897..550c88fb0267 100644
--- a/include/linux/mbus.h
+++ b/include/linux/mbus.h
@@ -73,6 +73,6 @@ int mvebu_mbus_del_window(phys_addr_t base, size_t size);
 int mvebu_mbus_init(const char *soc, phys_addr_t mbus_phys_base,
 		    size_t mbus_size, phys_addr_t sdram_phys_base,
 		    size_t sdram_size);
-int mvebu_mbus_dt_init(void);
+int mvebu_mbus_dt_init(bool is_coherent);
 
 #endif /* __LINUX_MBUS_H */
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index c68e5e0628df..99de2409f731 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -855,7 +855,10 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 
 	if (nla[NFTA_CHAIN_POLICY]) {
 		if ((chain != NULL &&
-		    !(chain->flags & NFT_BASE_CHAIN)) ||
+		    !(chain->flags & NFT_BASE_CHAIN)))
+			return -EOPNOTSUPP;
+
+		if (chain == NULL &&
 		    nla[NFTA_CHAIN_HOOK] == NULL)
 			return -EOPNOTSUPP;
 
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index 9e287cb56a04..54330fb5efaf 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -77,6 +77,9 @@ nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple,
 	if (!tb[NFCTH_TUPLE_L3PROTONUM] || !tb[NFCTH_TUPLE_L4PROTONUM])
 		return -EINVAL;
 
+	/* Not all fields are initialized so first zero the tuple */
+	memset(tuple, 0, sizeof(struct nf_conntrack_tuple));
+
 	tuple->src.l3num = ntohs(nla_get_be16(tb[NFCTH_TUPLE_L3PROTONUM]));
 	tuple->dst.protonum = nla_get_u8(tb[NFCTH_TUPLE_L4PROTONUM]);
 
@@ -86,7 +89,7 @@ nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple,
 static int
 nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct)
 {
-	const struct nf_conn_help *help = nfct_help(ct);
+	struct nf_conn_help *help = nfct_help(ct);
 
 	if (attr == NULL)
 		return -EINVAL;
@@ -94,7 +97,7 @@ nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct)
 	if (help->helper->data_len == 0)
 		return -EINVAL;
 
-	memcpy(&help->data, nla_data(attr), help->helper->data_len);
+	memcpy(help->data, nla_data(attr), help->helper->data_len);
 	return 0;
 }
 
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 7350723aeb15..969589590814 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -82,6 +82,9 @@ nft_target_set_tgchk_param(struct xt_tgchk_param *par,
 		entry->e4.ip.invflags = inv ? IPT_INV_PROTO : 0;
 		break;
 	case AF_INET6:
+		if (proto)
+			entry->e6.ipv6.flags |= IP6T_F_PROTO;
+
 		entry->e6.ipv6.proto = proto;
 		entry->e6.ipv6.invflags = inv ? IP6T_INV_PROTO : 0;
 		break;
@@ -313,6 +316,9 @@ nft_match_set_mtchk_param(struct xt_mtchk_param *par, const struct nft_ctx *ctx,
 		entry->e4.ip.invflags = inv ? IPT_INV_PROTO : 0;
 		break;
 	case AF_INET6:
+		if (proto)
+			entry->e6.ipv6.flags |= IP6T_F_PROTO;
+
 		entry->e6.ipv6.proto = proto;
 		entry->e6.ipv6.invflags = inv ? IP6T_INV_PROTO : 0;
 		break;
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 1316e558db64..c324a52bb407 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -674,7 +674,7 @@ static bool read_set_clear_sgi_pend_reg(struct kvm_vcpu *vcpu,
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 	int sgi;
-	int min_sgi = (offset & ~0x3) * 4;
+	int min_sgi = (offset & ~0x3);
 	int max_sgi = min_sgi + 3;
 	int vcpu_id = vcpu->vcpu_id;
 	u32 reg = 0;
@@ -695,7 +695,7 @@ static bool write_set_clear_sgi_pend_reg(struct kvm_vcpu *vcpu,
 {
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 	int sgi;
-	int min_sgi = (offset & ~0x3) * 4;
+	int min_sgi = (offset & ~0x3);
 	int max_sgi = min_sgi + 3;
 	int vcpu_id = vcpu->vcpu_id;
 	u32 reg;
@@ -1387,7 +1387,8 @@ out:
 int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
 			bool level)
 {
-	if (vgic_update_irq_state(kvm, cpuid, irq_num, level))
+	if (likely(vgic_initialized(kvm)) &&
+	    vgic_update_irq_state(kvm, cpuid, irq_num, level))
 		vgic_kick_vcpus(kvm);
 
 	return 0;
@@ -1610,7 +1611,7 @@ out:
 
 int kvm_vgic_create(struct kvm *kvm)
 {
-	int i, vcpu_lock_idx = -1, ret = 0;
+	int i, vcpu_lock_idx = -1, ret;
 	struct kvm_vcpu *vcpu;
 
 	mutex_lock(&kvm->lock);
@@ -1625,6 +1626,7 @@ int kvm_vgic_create(struct kvm *kvm)
 	 * vcpu->mutex.  By grabbing the vcpu->mutex of all VCPUs we ensure
 	 * that no other VCPUs are run while we create the vgic.
 	 */
+	ret = -EBUSY;
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		if (!mutex_trylock(&vcpu->mutex))
 			goto out_unlock;
@@ -1632,11 +1634,10 @@ int kvm_vgic_create(struct kvm *kvm)
 	}
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
-		if (vcpu->arch.has_run_once) {
-			ret = -EBUSY;
+		if (vcpu->arch.has_run_once)
 			goto out_unlock;
-		}
 	}
+	ret = 0;
 
 	spin_lock_init(&kvm->arch.vgic.lock);
 	kvm->arch.vgic.vctrl_base = vgic_vctrl_base;
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html



[Index of Archives]     [Linux Kernel]     [Kernel Development Newbies]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite Hiking]     [Linux Kernel]     [Linux SCSI]