Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Conflicts:
	drivers/net/xen-netfront.c

Minor overlapping changes in xen-netfront.c, mostly to do
with some buffer management changes alongside the split
of stats into TX and RX.

Signed-off-by: David S. Miller <davem@davemloft.net>

49 files changed, 420 insertions, 150 deletions

diff --git a/arch/arm/boot/dts/imx6sx-sdb.dts b/arch/arm/boot/dts/imx6sx-sdb.dts
index 1e6e5cc1c14c..8c1febd7e3f2 100644
--- a/arch/arm/boot/dts/imx6sx-sdb.dts
+++ b/arch/arm/boot/dts/imx6sx-sdb.dts
@@ -159,13 +159,28 @@
 	pinctrl-0 = <&pinctrl_enet1>;
 	phy-supply = <&reg_enet_3v3>;
 	phy-mode = "rgmii";
+	phy-handle = <&ethphy1>;
 	status = "okay";
+
+	mdio {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		ethphy1: ethernet-phy@0 {
+			reg = <0>;
+		};
+
+		ethphy2: ethernet-phy@1 {
+			reg = <1>;
+		};
+	};
 };
 
 &fec2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_enet2>;
 	phy-mode = "rgmii";
+	phy-handle = <&ethphy2>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/vf610-twr.dts b/arch/arm/boot/dts/vf610-twr.dts
index a0f762159cb2..f2b64b1b00fa 100644
--- a/arch/arm/boot/dts/vf610-twr.dts
+++ b/arch/arm/boot/dts/vf610-twr.dts
@@ -129,13 +129,28 @@
 
 &fec0 {
 	phy-mode = "rmii";
+	phy-handle = <&ethphy0>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_fec0>;
 	status = "okay";
+
+	mdio {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		ethphy0: ethernet-phy@0 {
+			reg = <0>;
+		};
+
+		ethphy1: ethernet-phy@1 {
+			reg = <1>;
+		};
+	};
 };
 
 &fec1 {
 	phy-mode = "rmii";
+	phy-handle = <&ethphy1>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_fec1>;
 	status = "okay";
diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h
index 705bb7620673..0c3f5a0dafd3 100644
--- a/arch/arm/include/uapi/asm/unistd.h
+++ b/arch/arm/include/uapi/asm/unistd.h
@@ -413,6 +413,7 @@
 #define __NR_getrandom			(__NR_SYSCALL_BASE+384)
 #define __NR_memfd_create		(__NR_SYSCALL_BASE+385)
 #define __NR_bpf			(__NR_SYSCALL_BASE+386)
+#define __NR_execveat			(__NR_SYSCALL_BASE+387)
 
 /*
  * The following SWIs are ARM private.
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index e51833f8cc38..05745eb838c5 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -396,6 +396,7 @@
 		CALL(sys_getrandom)
 /* 385 */	CALL(sys_memfd_create)
 		CALL(sys_bpf)
+		CALL(sys_execveat)
 #ifndef syscalls_counted
 .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
 #define syscalls_counted
diff --git a/arch/arm/kernel/perf_regs.c b/arch/arm/kernel/perf_regs.c
index 6e4379c67cbc..592dda3f21ff 100644
--- a/arch/arm/kernel/perf_regs.c
+++ b/arch/arm/kernel/perf_regs.c
@@ -28,3 +28,11 @@ u64 perf_reg_abi(struct task_struct *task)
 {
 	return PERF_SAMPLE_REGS_ABI_32;
 }
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs,
+			struct pt_regs *regs_user_copy)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}
diff --git a/arch/arm/mm/dump.c b/arch/arm/mm/dump.c
index 59424937e52b..9fe8e241335c 100644
--- a/arch/arm/mm/dump.c
+++ b/arch/arm/mm/dump.c
@@ -220,9 +220,6 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level, u
 	static const char units[] = "KMGTPE";
 	u64 prot = val & pg_level[level].mask;
 
-	if (addr < USER_PGTABLES_CEILING)
-		return;
-
 	if (!st->level) {
 		st->level = level;
 		st->current_prot = prot;
@@ -308,15 +305,13 @@ static void walk_pgd(struct seq_file *m)
 	pgd_t *pgd = swapper_pg_dir;
 	struct pg_state st;
 	unsigned long addr;
-	unsigned i, pgdoff = USER_PGTABLES_CEILING / PGDIR_SIZE;
+	unsigned i;
 
 	memset(&st, 0, sizeof(st));
 	st.seq = m;
 	st.marker = address_markers;
 
-	pgd += pgdoff;
-
-	for (i = pgdoff; i < PTRS_PER_PGD; i++, pgd++) {
+	for (i = 0; i < PTRS_PER_PGD; i++, pgd++) {
 		addr = i * PGDIR_SIZE;
 		if (!pgd_none(*pgd)) {
 			walk_pud(&st, pgd, addr);
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 98ad9c79ea0e..2495c8cb47ba 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -658,8 +658,8 @@ static struct section_perm ro_perms[] = {
 		.start  = (unsigned long)_stext,
 		.end    = (unsigned long)__init_begin,
 #ifdef CONFIG_ARM_LPAE
-		.mask   = ~PMD_SECT_RDONLY,
-		.prot   = PMD_SECT_RDONLY,
+		.mask   = ~L_PMD_SECT_RDONLY,
+		.prot   = L_PMD_SECT_RDONLY,
 #else
 		.mask   = ~(PMD_SECT_APX | PMD_SECT_AP_WRITE),
 		.prot   = PMD_SECT_APX | PMD_SECT_AP_WRITE,
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index cda7c40999b6..4e6ef896c619 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -1329,8 +1329,8 @@ static void __init kmap_init(void)
 static void __init map_lowmem(void)
 {
 	struct memblock_region *reg;
-	unsigned long kernel_x_start = round_down(__pa(_stext), SECTION_SIZE);
-	unsigned long kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE);
+	phys_addr_t kernel_x_start = round_down(__pa(_stext), SECTION_SIZE);
+	phys_addr_t kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE);
 
 	/* Map all the lowmem memory banks. */
 	for_each_memblock(memory, reg) {
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index b1fa4e614718..fbe0ca31a99c 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -21,6 +21,7 @@
 
 #include <asm/barrier.h>
 
+#include <linux/bug.h>
 #include <linux/init.h>
 #include <linux/types.h>
 
diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h
index ace70682499b..8e797b2fcc01 100644
--- a/arch/arm64/include/asm/cpu.h
+++ b/arch/arm64/include/asm/cpu.h
@@ -39,6 +39,7 @@ struct cpuinfo_arm64 {
 	u64		reg_id_aa64pfr0;
 	u64		reg_id_aa64pfr1;
 
+	u32		reg_id_dfr0;
 	u32		reg_id_isar0;
 	u32		reg_id_isar1;
 	u32		reg_id_isar2;
@@ -51,6 +52,10 @@ struct cpuinfo_arm64 {
 	u32		reg_id_mmfr3;
 	u32		reg_id_pfr0;
 	u32		reg_id_pfr1;
+
+	u32		reg_mvfr0;
+	u32		reg_mvfr1;
+	u32		reg_mvfr2;
 };
 
 DECLARE_PER_CPU(struct cpuinfo_arm64, cpu_data);
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 8127e45e2637..865a7e28ea2d 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -41,6 +41,8 @@ void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr);
 static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS;
+	if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features))
+		vcpu->arch.hcr_el2 &= ~HCR_RW;
 }
 
 static inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 286b1bec547c..f9be30ea1cbd 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -31,6 +31,7 @@
 
 #include <asm/fpsimd.h>
 #include <asm/hw_breakpoint.h>
+#include <asm/pgtable-hwdef.h>
 #include <asm/ptrace.h>
 #include <asm/types.h>
 
@@ -123,9 +124,6 @@ struct task_struct;
 /* Free all resources held by a thread. */
 extern void release_thread(struct task_struct *);
 
-/* Prepare to copy thread state - unlazy all lazy status */
-#define prepare_to_copy(tsk)	do { } while (0)
-
 unsigned long get_wchan(struct task_struct *p);
 
 #define cpu_relax()			barrier()
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 49c9aefd24a5..b780c6c76eec 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -44,7 +44,7 @@
 #define __ARM_NR_compat_cacheflush	(__ARM_NR_COMPAT_BASE+2)
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE+5)
 
-#define __NR_compat_syscalls		386
+#define __NR_compat_syscalls		387
 #endif
 
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 57b641747534..07d435cf2eea 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -147,6 +147,7 @@ static void cpuinfo_sanity_check(struct cpuinfo_arm64 *cur)
 	 * If we have AArch32, we care about 32-bit features for compat. These
 	 * registers should be RES0 otherwise.
 	 */
+	diff |= CHECK(id_dfr0, boot, cur, cpu);
 	diff |= CHECK(id_isar0, boot, cur, cpu);
 	diff |= CHECK(id_isar1, boot, cur, cpu);
 	diff |= CHECK(id_isar2, boot, cur, cpu);
@@ -165,6 +166,10 @@ static void cpuinfo_sanity_check(struct cpuinfo_arm64 *cur)
 	diff |= CHECK(id_pfr0, boot, cur, cpu);
 	diff |= CHECK(id_pfr1, boot, cur, cpu);
 
+	diff |= CHECK(mvfr0, boot, cur, cpu);
+	diff |= CHECK(mvfr1, boot, cur, cpu);
+	diff |= CHECK(mvfr2, boot, cur, cpu);
+
 	/*
 	 * Mismatched CPU features are a recipe for disaster. Don't even
 	 * pretend to support them.
@@ -189,6 +194,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 	info->reg_id_aa64pfr0 = read_cpuid(ID_AA64PFR0_EL1);
 	info->reg_id_aa64pfr1 = read_cpuid(ID_AA64PFR1_EL1);
 
+	info->reg_id_dfr0 = read_cpuid(ID_DFR0_EL1);
 	info->reg_id_isar0 = read_cpuid(ID_ISAR0_EL1);
 	info->reg_id_isar1 = read_cpuid(ID_ISAR1_EL1);
 	info->reg_id_isar2 = read_cpuid(ID_ISAR2_EL1);
@@ -202,6 +208,10 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 	info->reg_id_pfr0 = read_cpuid(ID_PFR0_EL1);
 	info->reg_id_pfr1 = read_cpuid(ID_PFR1_EL1);
 
+	info->reg_mvfr0 = read_cpuid(MVFR0_EL1);
+	info->reg_mvfr1 = read_cpuid(MVFR1_EL1);
+	info->reg_mvfr2 = read_cpuid(MVFR2_EL1);
+
 	cpuinfo_detect_icache_policy(info);
 
 	check_local_cpu_errata();
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index 6fac253bc783..2bb4347d0edf 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -326,6 +326,7 @@ void __init efi_idmap_init(void)
 
 	/* boot time idmap_pg_dir is incomplete, so fill in missing parts */
 	efi_setup_idmap();
+	early_memunmap(memmap.map, memmap.map_end - memmap.map);
 }
 
 static int __init remap_region(efi_memory_desc_t *md, void **new)
@@ -380,7 +381,6 @@ static int __init arm64_enter_virtual_mode(void)
 	}
 
 	mapsize = memmap.map_end - memmap.map;
-	early_memunmap(memmap.map, mapsize);
 
 	if (efi_runtime_disabled()) {
 		pr_info("EFI runtime services will be disabled.\n");
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index fd027b101de5..9b6f71db2709 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -25,6 +25,7 @@
 #include <linux/mm.h>
 #include <linux/moduleloader.h>
 #include <linux/vmalloc.h>
+#include <asm/alternative.h>
 #include <asm/insn.h>
 #include <asm/sections.h>
 
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
index 6762ad705587..3f62b35fb6f1 100644
--- a/arch/arm64/kernel/perf_regs.c
+++ b/arch/arm64/kernel/perf_regs.c
@@ -50,3 +50,11 @@ u64 perf_reg_abi(struct task_struct *task)
 	else
 		return PERF_SAMPLE_REGS_ABI_64;
 }
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs,
+			struct pt_regs *regs_user_copy)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index b80991166754..20fe2932ad0c 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -402,6 +402,7 @@ void __init setup_arch(char **cmdline_p)
 	request_standard_resources();
 
 	efi_idmap_init();
+	early_ioremap_reset();
 
 	unflatten_device_tree();
 
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index 4f93c67e63de..14944e5b28da 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -25,6 +25,7 @@
 #include <asm/cacheflush.h>
 #include <asm/cpu_ops.h>
 #include <asm/cputype.h>
+#include <asm/io.h>
 #include <asm/smp_plat.h>
 
 extern void secondary_holding_pen(void);
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index fbe909fb0a1a..c3ca89c27c6b 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -1014,6 +1014,7 @@ ENTRY(__kvm_tlb_flush_vmid_ipa)
 	 * Instead, we invalidate Stage-2 for this IPA, and the
 	 * whole of Stage-1. Weep...
 	 */
+	lsr	x1, x1, #12
 	tlbi	ipas2e1is, x1
 	/*
 	 * We have to ensure completion of the invalidation at Stage-2,
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 70a7816535cd..0b4326578985 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -90,7 +90,6 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 			if (!cpu_has_32bit_el1())
 				return -EINVAL;
 			cpu_reset = &default_regs_reset32;
-			vcpu->arch.hcr_el2 &= ~HCR_RW;
 		} else {
 			cpu_reset = &default_regs_reset;
 		}
diff --git a/arch/blackfin/mach-bf533/boards/stamp.c b/arch/blackfin/mach-bf533/boards/stamp.c
index 6f4bac969bf7..23eada79439c 100644
--- a/arch/blackfin/mach-bf533/boards/stamp.c
+++ b/arch/blackfin/mach-bf533/boards/stamp.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/device.h>
+#include <linux/delay.h>
 #include <linux/platform_device.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index 615ef81def49..e795cb848154 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -893,13 +893,13 @@ static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu)
 }
 
 /* wrapper to silence section mismatch warning */
-int __ref acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu)
+int __ref acpi_map_cpu(acpi_handle handle, int physid, int *pcpu)
 {
 	return _acpi_map_lsapic(handle, physid, pcpu);
 }
-EXPORT_SYMBOL(acpi_map_lsapic);
+EXPORT_SYMBOL(acpi_map_cpu);
 
-int acpi_unmap_lsapic(int cpu)
+int acpi_unmap_cpu(int cpu)
 {
 	ia64_cpu_to_sapicid[cpu] = -1;
 	set_cpu_present(cpu, false);
@@ -910,8 +910,7 @@ int acpi_unmap_lsapic(int cpu)
 
 	return (0);
 }
-
-EXPORT_SYMBOL(acpi_unmap_lsapic);
+EXPORT_SYMBOL(acpi_unmap_cpu);
 #endif				/* CONFIG_ACPI_HOTPLUG_CPU */
 
 #ifdef CONFIG_ACPI_NUMA
diff --git a/arch/s390/hypfs/hypfs_vm.c b/arch/s390/hypfs/hypfs_vm.c
index 32040ace00ea..afbe07907c10 100644
--- a/arch/s390/hypfs/hypfs_vm.c
+++ b/arch/s390/hypfs/hypfs_vm.c
@@ -231,7 +231,7 @@ failed:
 struct dbfs_d2fc_hdr {
 	u64	len;		/* Length of d2fc buffer without header */
 	u16	version;	/* Version of header */
-	char	tod_ext[16];	/* TOD clock for d2fc */
+	char	tod_ext[STORE_CLOCK_EXT_SIZE]; /* TOD clock for d2fc */
 	u64	count;		/* Number of VM guests in d2fc buffer */
 	char	reserved[30];
 } __attribute__ ((packed));
diff --git a/arch/s390/include/asm/irqflags.h b/arch/s390/include/asm/irqflags.h
index 37b9091ab8c0..16aa0c779e07 100644
--- a/arch/s390/include/asm/irqflags.h
+++ b/arch/s390/include/asm/irqflags.h
@@ -36,7 +36,7 @@ static inline notrace void __arch_local_irq_ssm(unsigned long flags)
 
 static inline notrace unsigned long arch_local_save_flags(void)
 {
-	return __arch_local_irq_stosm(0x00);
+	return __arch_local_irq_stnsm(0xff);
 }
 
 static inline notrace unsigned long arch_local_irq_save(void)
diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index 8beee1cceba4..98eb2a579223 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -67,20 +67,22 @@ static inline void local_tick_enable(unsigned long long comp)
 	set_clock_comparator(S390_lowcore.clock_comparator);
 }
 
-#define CLOCK_TICK_RATE	1193180 /* Underlying HZ */
+#define CLOCK_TICK_RATE		1193180 /* Underlying HZ */
+#define STORE_CLOCK_EXT_SIZE	16	/* stcke writes 16 bytes */
 
 typedef unsigned long long cycles_t;
 
-static inline void get_tod_clock_ext(char clk[16])
+static inline void get_tod_clock_ext(char *clk)
 {
-	typedef struct { char _[sizeof(clk)]; } addrtype;
+	typedef struct { char _[STORE_CLOCK_EXT_SIZE]; } addrtype;
 
 	asm volatile("stcke %0" : "=Q" (*(addrtype *) clk) : : "cc");
 }
 
 static inline unsigned long long get_tod_clock(void)
 {
-	unsigned char clk[16];
+	unsigned char clk[STORE_CLOCK_EXT_SIZE];
+
 	get_tod_clock_ext(clk);
 	return *((unsigned long long *)&clk[1]);
 }
diff --git a/arch/s390/include/uapi/asm/unistd.h b/arch/s390/include/uapi/asm/unistd.h
index 2b446cf0cc65..67878af257a0 100644
--- a/arch/s390/include/uapi/asm/unistd.h
+++ b/arch/s390/include/uapi/asm/unistd.h
@@ -289,7 +289,8 @@
 #define __NR_bpf		351
 #define __NR_s390_pci_mmio_write	352
 #define __NR_s390_pci_mmio_read		353
-#define NR_syscalls 354
+#define __NR_execveat		354
+#define NR_syscalls 355
 
 /* 
  * There are some system calls that are not present on 64 bit, some
diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S
index a2987243bc76..939ec474b1dd 100644
--- a/arch/s390/kernel/syscalls.S
+++ b/arch/s390/kernel/syscalls.S
@@ -362,3 +362,4 @@ SYSCALL(sys_memfd_create,sys_memfd_create,compat_sys_memfd_create) /* 350 */
 SYSCALL(sys_bpf,sys_bpf,compat_sys_bpf)
 SYSCALL(sys_ni_syscall,sys_s390_pci_mmio_write,compat_sys_s390_pci_mmio_write)
 SYSCALL(sys_ni_syscall,sys_s390_pci_mmio_read,compat_sys_s390_pci_mmio_read)
+SYSCALL(sys_execveat,sys_execveat,compat_sys_execveat)
diff --git a/arch/s390/kernel/uprobes.c b/arch/s390/kernel/uprobes.c
index f6b3cd056ec2..cc7328080b60 100644
--- a/arch/s390/kernel/uprobes.c
+++ b/arch/s390/kernel/uprobes.c
@@ -48,6 +48,30 @@ bool arch_uprobe_xol_was_trapped(struct task_struct *tsk)
 	return false;
 }
 
+static int check_per_event(unsigned short cause, unsigned long control,
+			   struct pt_regs *regs)
+{
+	if (!(regs->psw.mask & PSW_MASK_PER))
+		return 0;
+	/* user space single step */
+	if (control == 0)
+		return 1;
+	/* over indication for storage alteration */
+	if ((control & 0x20200000) && (cause & 0x2000))
+		return 1;
+	if (cause & 0x8000) {
+		/* all branches */
+		if ((control & 0x80800000) == 0x80000000)
+			return 1;
+		/* branch into selected range */
+		if (((control & 0x80800000) == 0x80800000) &&
+		    regs->psw.addr >= current->thread.per_user.start &&
+		    regs->psw.addr <= current->thread.per_user.end)
+			return 1;
+	}
+	return 0;
+}
+
 int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 {
 	int fixup = probe_get_fixup_type(auprobe->insn);
@@ -71,9 +95,13 @@ int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 		if (regs->psw.addr - utask->xol_vaddr == ilen)
 			regs->psw.addr = utask->vaddr + ilen;
 	}
-	/* If per tracing was active generate trap */
-	if (regs->psw.mask & PSW_MASK_PER)
-		do_per_trap(regs);
+	if (check_per_event(current->thread.per_event.cause,
+			    current->thread.per_user.control, regs)) {
+		/* fix per address */
+		current->thread.per_event.address = utask->vaddr;
+		/* trigger per event */
+		set_pt_regs_flag(regs, PIF_PER_TRAP);
+	}
 	return 0;
 }
 
@@ -106,6 +134,7 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 	clear_thread_flag(TIF_UPROBE_SINGLESTEP);
 	regs->int_code = auprobe->saved_int_code;
 	regs->psw.addr = current->utask->vaddr;
+	current->thread.per_event.address = current->utask->vaddr;
 }
 
 unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline,
@@ -146,17 +175,20 @@ static void adjust_psw_addr(psw_t *psw, unsigned long len)
 	__rc;						\
 })
 
-#define emu_store_ril(ptr, input)			\
+#define emu_store_ril(regs, ptr, input)			\
 ({							\
 	unsigned int mask = sizeof(*(ptr)) - 1;		\
+	__typeof__(ptr) __ptr = (ptr);			\
 	int __rc = 0;					\
 							\
 	if (!test_facility(34))				\
 		__rc = EMU_ILLEGAL_OP;			\
-	else if ((u64 __force)ptr & mask)		\
+	else if ((u64 __force)__ptr & mask)		\
 		__rc = EMU_SPECIFICATION;		\
-	else if (put_user(*(input), ptr))		\
+	else if (put_user(*(input), __ptr))		\
 		__rc = EMU_ADDRESSING;			\
+	if (__rc == 0)					\
+		sim_stor_event(regs, __ptr, mask + 1);	\
 	__rc;						\
 })
 
@@ -198,6 +230,25 @@ union split_register {
 };
 
 /*
+ * If user per registers are setup to trace storage alterations and an
+ * emulated store took place on a fitting address a user trap is generated.
+ */
+static void sim_stor_event(struct pt_regs *regs, void *addr, int len)
+{
+	if (!(regs->psw.mask & PSW_MASK_PER))
+		return;
+	if (!(current->thread.per_user.control & PER_EVENT_STORE))
+		return;
+	if ((void *)current->thread.per_user.start > (addr + len))
+		return;
+	if ((void *)current->thread.per_user.end < addr)
+		return;
+	current->thread.per_event.address = regs->psw.addr;
+	current->thread.per_event.cause = PER_EVENT_STORE >> 16;
+	set_pt_regs_flag(regs, PIF_PER_TRAP);
+}
+
+/*
  * pc relative instructions are emulated, since parameters may not be
  * accessible from the xol area due to range limitations.
  */
@@ -249,13 +300,13 @@ static void handle_insn_ril(struct arch_uprobe *auprobe, struct pt_regs *regs)
 			rc = emu_load_ril((u32 __user *)uptr, &rx->u64);
 			break;
 		case 0x07: /* sthrl */
-			rc = emu_store_ril((u16 __user *)uptr, &rx->u16[3]);
+			rc = emu_store_ril(regs, (u16 __user *)uptr, &rx->u16[3]);
 			break;
 		case 0x0b: /* stgrl */
-			rc = emu_store_ril((u64 __user *)uptr, &rx->u64);
+			rc = emu_store_ril(regs, (u64 __user *)uptr, &rx->u64);
 			break;
 		case 0x0f: /* strl */
-			rc = emu_store_ril((u32 __user *)uptr, &rx->u32[1]);
+			rc = emu_store_ril(regs, (u32 __user *)uptr, &rx->u32[1]);
 			break;
 		}
 		break;
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 7f0089d9a4aa..e34122e539a1 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -128,8 +128,6 @@ void vtime_account_irq_enter(struct task_struct *tsk)
 	struct thread_info *ti = task_thread_info(tsk);
 	u64 timer, system;
 
-	WARN_ON_ONCE(!irqs_disabled());
-
 	timer = S390_lowcore.last_update_timer;
 	S390_lowcore.last_update_timer = get_vtimer();
 	S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer;
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index be99357d238c..3cf8cc03fff6 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -322,11 +322,12 @@ static int gmap_alloc_table(struct gmap *gmap, unsigned long *table,
 static unsigned long __gmap_segment_gaddr(unsigned long *entry)
 {
 	struct page *page;
-	unsigned long offset;
+	unsigned long offset, mask;
 
 	offset = (unsigned long) entry / sizeof(unsigned long);
 	offset = (offset & (PTRS_PER_PMD - 1)) * PMD_SIZE;
-	page = pmd_to_page((pmd_t *) entry);
+	mask = ~(PTRS_PER_PMD * sizeof(pmd_t) - 1);
+	page = virt_to_page((void *)((unsigned long) entry & mask));
 	return page->index + offset;
 }
 
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index c52ac77408ca..524496d47ef5 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -431,8 +431,8 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 		EMIT4_DISP(0x88500000, K);
 		break;
 	case BPF_ALU | BPF_NEG: /* A = -A */
-		/* lnr %r5,%r5 */
-		EMIT2(0x1155);
+		/* lcr %r5,%r5 */
+		EMIT2(0x1355);
 		break;
 	case BPF_JMP | BPF_JA: /* ip += K */
 		offset = addrs[i + K] + jit->start - jit->prg;
@@ -502,8 +502,8 @@ branch:		if (filter->jt == filter->jf) {
 xbranch:	/* Emit compare if the branch targets are different */
 		if (filter->jt != filter->jf) {
 			jit->seen |= SEEN_XREG;
-			/* cr %r5,%r12 */
-			EMIT2(0x195c);
+			/* clr %r5,%r12 */
+			EMIT2(0x155c);
 		}
 		goto branch;
 	case BPF_JMP | BPF_JSET | BPF_X: /* ip += (A & X) ? jt : jf */
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 5b016e2498f3..3db07f30636f 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -51,6 +51,7 @@ targets += cpustr.h
 $(obj)/cpustr.h: $(obj)/mkcpustr FORCE
 	$(call if_changed,cpustr)
 endif
+clean-files += cpustr.h
 
 # ---------------------------------------------------------------------------
 
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index fd0f848938cc..5a4a089e8b1f 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -26,7 +26,6 @@ obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o
 
 obj-$(CONFIG_CRYPTO_CRC32C_INTEL) += crc32c-intel.o
 obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o
-obj-$(CONFIG_CRYPTO_SHA1_MB) += sha-mb/
 obj-$(CONFIG_CRYPTO_CRC32_PCLMUL) += crc32-pclmul.o
 obj-$(CONFIG_CRYPTO_SHA256_SSSE3) += sha256-ssse3.o
 obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o
@@ -46,6 +45,7 @@ endif
 ifeq ($(avx2_supported),yes)
 	obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX2_X86_64) += camellia-aesni-avx2.o
 	obj-$(CONFIG_CRYPTO_SERPENT_AVX2_X86_64) += serpent-avx2.o
+	obj-$(CONFIG_CRYPTO_SHA1_MB) += sha-mb/
 endif
 
 aes-i586-y := aes-i586-asm_32.o aes_glue.o
diff --git a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
index 2df2a0298f5a..a916c4a61165 100644
--- a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
+++ b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
@@ -208,7 +208,7 @@ ddq_add_8:
 
 	.if (klen == KEY_128)
 		.if (load_keys)
-			vmovdqa	3*16(p_keys), xkeyA
+			vmovdqa	3*16(p_keys), xkey4
 		.endif
 	.else
 		vmovdqa	3*16(p_keys), xkeyA
@@ -224,7 +224,7 @@ ddq_add_8:
 	add	$(16*by), p_in
 
 	.if (klen == KEY_128)
-		vmovdqa	4*16(p_keys), xkey4
+		vmovdqa	4*16(p_keys), xkeyB
 	.else
 		.if (load_keys)
 			vmovdqa	4*16(p_keys), xkey4
@@ -234,7 +234,12 @@ ddq_add_8:
 	.set i, 0
 	.rept by
 		club XDATA, i
-		vaesenc	xkeyA, var_xdata, var_xdata		/* key 3 */
+		/* key 3 */
+		.if (klen == KEY_128)
+			vaesenc	xkey4, var_xdata, var_xdata
+		.else
+			vaesenc	xkeyA, var_xdata, var_xdata
+		.endif
 		.set i, (i +1)
 	.endr
 
@@ -243,13 +248,18 @@ ddq_add_8:
 	.set i, 0
 	.rept by
 		club XDATA, i
-		vaesenc	xkey4, var_xdata, var_xdata		/* key 4 */
+		/* key 4 */
+		.if (klen == KEY_128)
+			vaesenc	xkeyB, var_xdata, var_xdata
+		.else
+			vaesenc	xkey4, var_xdata, var_xdata
+		.endif
 		.set i, (i +1)
 	.endr
 
 	.if (klen == KEY_128)
 		.if (load_keys)
-			vmovdqa	6*16(p_keys), xkeyB
+			vmovdqa	6*16(p_keys), xkey8
 		.endif
 	.else
 		vmovdqa	6*16(p_keys), xkeyB
@@ -267,12 +277,17 @@ ddq_add_8:
 	.set i, 0
 	.rept by
 		club XDATA, i
-		vaesenc	xkeyB, var_xdata, var_xdata		/* key 6 */
+		/* key 6 */
+		.if (klen == KEY_128)
+			vaesenc	xkey8, var_xdata, var_xdata
+		.else
+			vaesenc	xkeyB, var_xdata, var_xdata
+		.endif
 		.set i, (i +1)
 	.endr
 
 	.if (klen == KEY_128)
-		vmovdqa	8*16(p_keys), xkey8
+		vmovdqa	8*16(p_keys), xkeyB
 	.else
 		.if (load_keys)
 			vmovdqa	8*16(p_keys), xkey8
@@ -288,7 +303,7 @@ ddq_add_8:
 
 	.if (klen == KEY_128)
 		.if (load_keys)
-			vmovdqa	9*16(p_keys), xkeyA
+			vmovdqa	9*16(p_keys), xkey12
 		.endif
 	.else
 		vmovdqa	9*16(p_keys), xkeyA
@@ -297,7 +312,12 @@ ddq_add_8:
 	.set i, 0
 	.rept by
 		club XDATA, i
-		vaesenc	xkey8, var_xdata, var_xdata		/* key 8 */
+		/* key 8 */
+		.if (klen == KEY_128)
+			vaesenc	xkeyB, var_xdata, var_xdata
+		.else
+			vaesenc	xkey8, var_xdata, var_xdata
+		.endif
 		.set i, (i +1)
 	.endr
 
@@ -306,7 +326,12 @@ ddq_add_8:
 	.set i, 0
 	.rept by
 		club XDATA, i
-		vaesenc	xkeyA, var_xdata, var_xdata		/* key 9 */
+		/* key 9 */
+		.if (klen == KEY_128)
+			vaesenc	xkey12, var_xdata, var_xdata
+		.else
+			vaesenc	xkeyA, var_xdata, var_xdata
+		.endif
 		.set i, (i +1)
 	.endr
 
@@ -412,7 +437,6 @@ ddq_add_8:
 /* main body of aes ctr load */
 
 .macro do_aes_ctrmain key_len
-
 	cmp	$16, num_bytes
 	jb	.Ldo_return2\key_len
 
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index e7e9682a33e9..f556c4843aa1 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -80,9 +80,11 @@ static inline unsigned int __getcpu(void)
 
 	/*
 	 * Load per CPU data from GDT.  LSL is faster than RDTSCP and
-	 * works on all CPUs.
+	 * works on all CPUs.  This is volatile so that it orders
+	 * correctly wrt barrier() and to keep gcc from cleverly
+	 * hoisting it out of the calling function.
 	 */
-	asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
+	asm volatile ("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
 
 	return p;
 }
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 4433a4be8171..d1626364a28a 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -750,13 +750,13 @@ static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu)
 }
 
 /* wrapper to silence section mismatch warning */
-int __ref acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu)
+int __ref acpi_map_cpu(acpi_handle handle, int physid, int *pcpu)
 {
 	return _acpi_map_lsapic(handle, physid, pcpu);
 }
-EXPORT_SYMBOL(acpi_map_lsapic);
+EXPORT_SYMBOL(acpi_map_cpu);
 
-int acpi_unmap_lsapic(int cpu)
+int acpi_unmap_cpu(int cpu)
 {
 #ifdef CONFIG_ACPI_NUMA
 	set_apicid_to_node(per_cpu(x86_cpu_to_apicid, cpu), NUMA_NO_NODE);
@@ -768,8 +768,7 @@ int acpi_unmap_lsapic(int cpu)
 
 	return (0);
 }
-
-EXPORT_SYMBOL(acpi_unmap_lsapic);
+EXPORT_SYMBOL(acpi_unmap_cpu);
 #endif				/* CONFIG_ACPI_HOTPLUG_CPU */
 
 int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base)
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index e27b49d7c922..80091ae54c2b 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -66,3 +66,4 @@ targets += capflags.c
 $(obj)/capflags.c: $(cpufeature) $(src)/mkcapflags.sh FORCE
 	$(call if_changed,mkcapflags)
 endif
+clean-files += capflags.c
diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh
index e2b22df964cd..36d99a337b49 100644
--- a/arch/x86/kernel/cpu/mkcapflags.sh
+++ b/arch/x86/kernel/cpu/mkcapflags.sh
@@ -28,7 +28,7 @@ function dump_array()
 		# If the /* comment */ starts with a quote string, grab that.
 		VALUE="$(echo "$i" | sed -n 's@.*/\* *\("[^"]*"\).*\*/@\1@p')"
 		[ -z "$VALUE" ] && VALUE="\"$NAME\""
-		[ "$VALUE" == '""' ] && continue
+		[ "$VALUE" = '""' ] && continue
 
 		# Name is uppercase, VALUE is all lowercase
 		VALUE="$(echo "$VALUE" | tr A-Z a-z)"
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 18eb78bbdd10..863d9b02563e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -17,7 +17,7 @@
 #define UNCORE_PCI_DEV_TYPE(data)	((data >> 8) & 0xff)
 #define UNCORE_PCI_DEV_IDX(data)	(data & 0xff)
 #define UNCORE_EXTRA_PCI_DEV		0xff
-#define UNCORE_EXTRA_PCI_DEV_MAX	2
+#define UNCORE_EXTRA_PCI_DEV_MAX	3
 
 /* support up to 8 sockets */
 #define UNCORE_SOCKET_MAX		8
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
index 745b158e9a65..21af6149edf2 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
@@ -891,6 +891,7 @@ void snbep_uncore_cpu_init(void)
 enum {
 	SNBEP_PCI_QPI_PORT0_FILTER,
 	SNBEP_PCI_QPI_PORT1_FILTER,
+	HSWEP_PCI_PCU_3,
 };
 
 static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event)
@@ -2026,6 +2027,17 @@ void hswep_uncore_cpu_init(void)
 {
 	if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
 		hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+
+	/* Detect 6-8 core systems with only two SBOXes */
+	if (uncore_extra_pci_dev[0][HSWEP_PCI_PCU_3]) {
+		u32 capid4;
+
+		pci_read_config_dword(uncore_extra_pci_dev[0][HSWEP_PCI_PCU_3],
+				      0x94, &capid4);
+		if (((capid4 >> 6) & 0x3) == 0)
+			hswep_uncore_sbox.num_boxes = 2;
+	}
+
 	uncore_msr_uncores = hswep_msr_uncores;
 }
 
@@ -2287,6 +2299,11 @@ static DEFINE_PCI_DEVICE_TABLE(hswep_uncore_pci_ids) = {
 		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
 						   SNBEP_PCI_QPI_PORT1_FILTER),
 	},
+	{ /* PCU.3 (for Capability registers) */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fc0),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   HSWEP_PCI_PCU_3),
+	},
 	{ /* end: all zeroes */ }
 };
 
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index e309cc5c276e..781861cc5ee8 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -78,6 +78,14 @@ u64 perf_reg_abi(struct task_struct *task)
 {
 	return PERF_SAMPLE_REGS_ABI_32;
 }
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs,
+			struct pt_regs *regs_user_copy)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}
 #else /* CONFIG_X86_64 */
 #define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
 		       (1ULL << PERF_REG_X86_ES) | \
@@ -102,4 +110,86 @@ u64 perf_reg_abi(struct task_struct *task)
 	else
 		return PERF_SAMPLE_REGS_ABI_64;
 }
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs,
+			struct pt_regs *regs_user_copy)
+{
+	struct pt_regs *user_regs = task_pt_regs(current);
+
+	/*
+	 * If we're in an NMI that interrupted task_pt_regs setup, then
+	 * we can't sample user regs at all.  This check isn't really
+	 * sufficient, though, as we could be in an NMI inside an interrupt
+	 * that happened during task_pt_regs setup.
+	 */
+	if (regs->sp > (unsigned long)&user_regs->r11 &&
+	    regs->sp <= (unsigned long)(user_regs + 1)) {
+		regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
+		regs_user->regs = NULL;
+		return;
+	}
+
+	/*
+	 * RIP, flags, and the argument registers are usually saved.
+	 * orig_ax is probably okay, too.
+	 */
+	regs_user_copy->ip = user_regs->ip;
+	regs_user_copy->cx = user_regs->cx;
+	regs_user_copy->dx = user_regs->dx;
+	regs_user_copy->si = user_regs->si;
+	regs_user_copy->di = user_regs->di;
+	regs_user_copy->r8 = user_regs->r8;
+	regs_user_copy->r9 = user_regs->r9;
+	regs_user_copy->r10 = user_regs->r10;
+	regs_user_copy->r11 = user_regs->r11;
+	regs_user_copy->orig_ax = user_regs->orig_ax;
+	regs_user_copy->flags = user_regs->flags;
+
+	/*
+	 * Don't even try to report the "rest" regs.
+	 */
+	regs_user_copy->bx = -1;
+	regs_user_copy->bp = -1;
+	regs_user_copy->r12 = -1;
+	regs_user_copy->r13 = -1;
+	regs_user_copy->r14 = -1;
+	regs_user_copy->r15 = -1;
+
+	/*
+	 * For this to be at all useful, we need a reasonable guess for
+	 * sp and the ABI.  Be careful: we're in NMI context, and we're
+	 * considering current to be the current task, so we should
+	 * be careful not to look at any other percpu variables that might
+	 * change during context switches.
+	 */
+	if (IS_ENABLED(CONFIG_IA32_EMULATION) &&
+	    task_thread_info(current)->status & TS_COMPAT) {
+		/* Easy case: we're in a compat syscall. */
+		regs_user->abi = PERF_SAMPLE_REGS_ABI_32;
+		regs_user_copy->sp = user_regs->sp;
+		regs_user_copy->cs = user_regs->cs;
+		regs_user_copy->ss = user_regs->ss;
+	} else if (user_regs->orig_ax != -1) {
+		/*
+		 * We're probably in a 64-bit syscall.
+		 * Warning: this code is severely racy.  At least it's better
+		 * than just blindly copying user_regs.
+		 */
+		regs_user->abi = PERF_SAMPLE_REGS_ABI_64;
+		regs_user_copy->sp = this_cpu_read(old_rsp);
+		regs_user_copy->cs = __USER_CS;
+		regs_user_copy->ss = __USER_DS;
+		regs_user_copy->cx = -1;  /* usually contains garbage */
+	} else {
+		/* We're probably in an interrupt or exception. */
+		regs_user->abi = user_64bit_mode(user_regs) ?
+			PERF_SAMPLE_REGS_ABI_64 : PERF_SAMPLE_REGS_ABI_32;
+		regs_user_copy->sp = user_regs->sp;
+		regs_user_copy->cs = user_regs->cs;
+		regs_user_copy->ss = user_regs->ss;
+	}
+
+	regs_user->regs = regs_user_copy;
+}
 #endif /* CONFIG_X86_32 */
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 2480978b31cc..1313ae6b478b 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -28,7 +28,7 @@
 
 /* Verify next sizeof(t) bytes can be on the same instruction */
 #define validate_next(t, insn, n)	\
-	((insn)->next_byte + sizeof(t) + n < (insn)->end_kaddr)
+	((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr)
 
 #define __get_next(t, insn)	\
 	({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); r; })
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index a97ee0801475..08a7d313538a 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -438,20 +438,20 @@ static unsigned long __init init_range_memory_mapping(
 static unsigned long __init get_new_step_size(unsigned long step_size)
 {
 	/*
-	 * Explain why we shift by 5 and why we don't have to worry about
-	 * 'step_size << 5' overflowing:
-	 *
-	 * initial mapped size is PMD_SIZE (2M).
+	 * Initial mapped size is PMD_SIZE (2M).
 	 * We can not set step_size to be PUD_SIZE (1G) yet.
 	 * In worse case, when we cross the 1G boundary, and
 	 * PG_LEVEL_2M is not set, we will need 1+1+512 pages (2M + 8k)
-	 * to map 1G range with PTE. Use 5 as shift for now.
+	 * to map 1G range with PTE. Hence we use one less than the
+	 * difference of page table level shifts.
 	 *
-	 * Don't need to worry about overflow, on 32bit, when step_size
-	 * is 0, round_down() returns 0 for start, and that turns it
-	 * into 0x100000000ULL.
+	 * Don't need to worry about overflow in the top-down case, on 32bit,
+	 * when step_size is 0, round_down() returns 0 for start, and that
+	 * turns it into 0x100000000ULL.
+	 * In the bottom-up case, round_up(x, 0) returns 0 though too, which
+	 * needs to be taken into consideration by the code below.
 	 */
-	return step_size << 5;
+	return step_size << (PMD_SHIFT - PAGE_SHIFT - 1);
 }
 
 /**
@@ -471,7 +471,6 @@ static void __init memory_map_top_down(unsigned long map_start,
 	unsigned long step_size;
 	unsigned long addr;
 	unsigned long mapped_ram_size = 0;
-	unsigned long new_mapped_ram_size;
 
 	/* xen has big range in reserved near end of ram, skip it at first.*/
 	addr = memblock_find_in_range(map_start, map_end, PMD_SIZE, PMD_SIZE);
@@ -496,14 +495,12 @@ static void __init memory_map_top_down(unsigned long map_start,
 				start = map_start;
 		} else
 			start = map_start;
-		new_mapped_ram_size = init_range_memory_mapping(start,
+		mapped_ram_size += init_range_memory_mapping(start,
 							last_start);
 		last_start = start;
 		min_pfn_mapped = last_start >> PAGE_SHIFT;
-		/* only increase step_size after big range get mapped */
-		if (new_mapped_ram_size > mapped_ram_size)
+		if (mapped_ram_size >= step_size)
 			step_size = get_new_step_size(step_size);
-		mapped_ram_size += new_mapped_ram_size;
 	}
 
 	if (real_end < map_end)
@@ -524,7 +521,7 @@ static void __init memory_map_top_down(unsigned long map_start,
 static void __init memory_map_bottom_up(unsigned long map_start,
 					unsigned long map_end)
 {
-	unsigned long next, new_mapped_ram_size, start;
+	unsigned long next, start;
 	unsigned long mapped_ram_size = 0;
 	/* step_size need to be small so pgt_buf from BRK could cover it */
 	unsigned long step_size = PMD_SIZE;
@@ -539,19 +536,19 @@ static void __init memory_map_bottom_up(unsigned long map_start,
 	 * for page table.
 	 */
 	while (start < map_end) {
-		if (map_end - start > step_size) {
+		if (step_size && map_end - start > step_size) {
 			next = round_up(start + 1, step_size);
 			if (next > map_end)
 				next = map_end;
-		} else
+		} else {
 			next = map_end;
+		}
 
-		new_mapped_ram_size = init_range_memory_mapping(start, next);
+		mapped_ram_size += init_range_memory_mapping(start, next);
 		start = next;
 
-		if (new_mapped_ram_size > mapped_ram_size)
+		if (mapped_ram_size >= step_size)
 			step_size = get_new_step_size(step_size);
-		mapped_ram_size += new_mapped_ram_size;
 	}
 }
 
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 009495b9ab4b..1c9f750c3859 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -41,12 +41,17 @@ void __init init_vdso_image(const struct vdso_image *image)
 
 struct linux_binprm;
 
-/* Put the vdso above the (randomized) stack with another randomized offset.
-   This way there is no hole in the middle of address space.
-   To save memory make sure it is still in the same PTE as the stack top.
-   This doesn't give that many random bits.
-
-   Only used for the 64-bit and x32 vdsos. */
+/*
+ * Put the vdso above the (randomized) stack with another randomized
+ * offset.  This way there is no hole in the middle of address space.
+ * To save memory make sure it is still in the same PTE as the stack
+ * top.  This doesn't give that many random bits.
+ *
+ * Note that this algorithm is imperfect: the distribution of the vdso
+ * start address within a PMD is biased toward the end.
+ *
+ * Only used for the 64-bit and x32 vdsos.
+ */
 static unsigned long vdso_addr(unsigned long start, unsigned len)
 {
 #ifdef CONFIG_X86_32
@@ -54,22 +59,30 @@ static unsigned long vdso_addr(unsigned long start, unsigned len)
 #else
 	unsigned long addr, end;
 	unsigned offset;
-	end = (start + PMD_SIZE - 1) & PMD_MASK;
+
+	/*
+	 * Round up the start address.  It can start out unaligned as a result
+	 * of stack start randomization.
+	 */
+	start = PAGE_ALIGN(start);
+
+	/* Round the lowest possible end address up to a PMD boundary. */
+	end = (start + len + PMD_SIZE - 1) & PMD_MASK;
 	if (end >= TASK_SIZE_MAX)
 		end = TASK_SIZE_MAX;
 	end -= len;
-	/* This loses some more bits than a modulo, but is cheaper */
-	offset = get_random_int() & (PTRS_PER_PTE - 1);
-	addr = start + (offset << PAGE_SHIFT);
-	if (addr >= end)
-		addr = end;
+
+	if (end > start) {
+		offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1);
+		addr = start + (offset << PAGE_SHIFT);
+	} else {
+		addr = start;
+	}
 
 	/*
-	 * page-align it here so that get_unmapped_area doesn't
-	 * align it wrongfully again to the next page. addr can come in 4K
-	 * unaligned here as a result of stack start randomization.
+	 * Forcibly align the final address in case we have a hardware
+	 * issue that requires alignment for performance reasons.
 	 */
-	addr = PAGE_ALIGN(addr);
 	addr = align_vdso_addr(addr);
 
 	return addr;
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 6bf3a13e3e0f..78a881b7fc41 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -40,6 +40,7 @@
 #include <xen/interface/physdev.h>
 #include <xen/interface/vcpu.h>
 #include <xen/interface/memory.h>
+#include <xen/interface/nmi.h>
 #include <xen/interface/xen-mca.h>
 #include <xen/features.h>
 #include <xen/page.h>
@@ -66,6 +67,7 @@
 #include <asm/reboot.h>
 #include <asm/stackprotector.h>
 #include <asm/hypervisor.h>
+#include <asm/mach_traps.h>
 #include <asm/mwait.h>
 #include <asm/pci_x86.h>
 #include <asm/pat.h>
@@ -1351,6 +1353,21 @@ static const struct machine_ops xen_machine_ops __initconst = {
 	.emergency_restart = xen_emergency_restart,
 };
 
+static unsigned char xen_get_nmi_reason(void)
+{
+	unsigned char reason = 0;
+
+	/* Construct a value which looks like it came from port 0x61. */
+	if (test_bit(_XEN_NMIREASON_io_error,
+		     &HYPERVISOR_shared_info->arch.nmi_reason))
+		reason |= NMI_REASON_IOCHK;
+	if (test_bit(_XEN_NMIREASON_pci_serr,
+		     &HYPERVISOR_shared_info->arch.nmi_reason))
+		reason |= NMI_REASON_SERR;
+
+	return reason;
+}
+
 static void __init xen_boot_params_init_edd(void)
 {
 #if IS_ENABLED(CONFIG_EDD)
@@ -1535,9 +1552,12 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	pv_info = xen_info;
 	pv_init_ops = xen_init_ops;
 	pv_apic_ops = xen_apic_ops;
-	if (!xen_pvh_domain())
+	if (!xen_pvh_domain()) {
 		pv_cpu_ops = xen_cpu_ops;
 
+		x86_platform.get_nmi_reason = xen_get_nmi_reason;
+	}
+
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		x86_init.resources.memory_setup = xen_auto_xlated_memory_setup;
 	else
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index edbc7a63fd73..70fb5075c901 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -167,10 +167,13 @@ static void * __ref alloc_p2m_page(void)
 	return (void *)__get_free_page(GFP_KERNEL | __GFP_REPEAT);
 }
 
-/* Only to be called in case of a race for a page just allocated! */
-static void free_p2m_page(void *p)
+static void __ref free_p2m_page(void *p)
 {
-	BUG_ON(!slab_is_available());
+	if (unlikely(!slab_is_available())) {
+		free_bootmem((unsigned long)p, PAGE_SIZE);
+		return;
+	}
+
 	free_page((unsigned long)p);
 }
 
@@ -375,7 +378,7 @@ static void __init xen_rebuild_p2m_list(unsigned long *p2m)
 			p2m_missing_pte : p2m_identity_pte;
 		for (i = 0; i < PMDS_PER_MID_PAGE; i++) {
 			pmdp = populate_extra_pmd(
-				(unsigned long)(p2m + pfn + i * PTRS_PER_PTE));
+				(unsigned long)(p2m + pfn) + i * PMD_SIZE);
 			set_pmd(pmdp, __pmd(__pa(ptep) | _KERNPG_TABLE));
 		}
 	}
@@ -436,10 +439,9 @@ EXPORT_SYMBOL_GPL(get_phys_to_machine);
  * a new pmd is to replace p2m_missing_pte or p2m_identity_pte by a individual
  * pmd. In case of PAE/x86-32 there are multiple pmds to allocate!
  */
-static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *ptep, pte_t *pte_pg)
+static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *pte_pg)
 {
 	pte_t *ptechk;
-	pte_t *pteret = ptep;
 	pte_t *pte_newpg[PMDS_PER_MID_PAGE];
 	pmd_t *pmdp;
 	unsigned int level;
@@ -473,8 +475,6 @@ static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *ptep, pte_t *pte_pg)
 		if (ptechk == pte_pg) {
 			set_pmd(pmdp,
 				__pmd(__pa(pte_newpg[i]) | _KERNPG_TABLE));
-			if (vaddr == (addr & ~(PMD_SIZE - 1)))
-				pteret = pte_offset_kernel(pmdp, addr);
 			pte_newpg[i] = NULL;
 		}
 
@@ -488,7 +488,7 @@ static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *ptep, pte_t *pte_pg)
 		vaddr += PMD_SIZE;
 	}
 
-	return pteret;
+	return lookup_address(addr, &level);
 }
 
 /*
@@ -517,7 +517,7 @@ static bool alloc_p2m(unsigned long pfn)
 
 	if (pte_pg == p2m_missing_pte || pte_pg == p2m_identity_pte) {
 		/* PMD level is missing, allocate a new one */
-		ptep = alloc_p2m_pmd(addr, ptep, pte_pg);
+		ptep = alloc_p2m_pmd(addr, pte_pg);
 		if (!ptep)
 			return false;
 	}
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index dfd77dec8e2b..865e56cea7a0 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -140,7 +140,7 @@ static void __init xen_del_extra_mem(u64 start, u64 size)
 unsigned long __ref xen_chk_extra_mem(unsigned long pfn)
 {
 	int i;
-	unsigned long addr = PFN_PHYS(pfn);
+	phys_addr_t addr = PFN_PHYS(pfn);
 
 	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
 		if (addr >= xen_extra_mem[i].start &&
@@ -160,6 +160,8 @@ void __init xen_inv_extra_mem(void)
 	int i;
 
 	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
+		if (!xen_extra_mem[i].size)
+			continue;
 		pfn_s = PFN_DOWN(xen_extra_mem[i].start);
 		pfn_e = PFN_UP(xen_extra_mem[i].start + xen_extra_mem[i].size);
 		for (pfn = pfn_s; pfn < pfn_e; pfn++)
@@ -229,15 +231,14 @@ static int __init xen_free_mfn(unsigned long mfn)
  * as a fallback if the remapping fails.
  */
 static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn,
-	unsigned long end_pfn, unsigned long nr_pages, unsigned long *identity,
-	unsigned long *released)
+	unsigned long end_pfn, unsigned long nr_pages, unsigned long *released)
 {
-	unsigned long len = 0;
 	unsigned long pfn, end;
 	int ret;
 
 	WARN_ON(start_pfn > end_pfn);
 
+	/* Release pages first. */
 	end = min(end_pfn, nr_pages);
 	for (pfn = start_pfn; pfn < end; pfn++) {
 		unsigned long mfn = pfn_to_mfn(pfn);
@@ -250,16 +251,14 @@ static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn,
 		WARN(ret != 1, "Failed to release pfn %lx err=%d\n", pfn, ret);
 
 		if (ret == 1) {
+			(*released)++;
 			if (!__set_phys_to_machine(pfn, INVALID_P2M_ENTRY))
 				break;
-			len++;
 		} else
 			break;
 	}
 
-	/* Need to release pages first */
-	*released += len;
-	*identity += set_phys_range_identity(start_pfn, end_pfn);
+	set_phys_range_identity(start_pfn, end_pfn);
 }
 
 /*
@@ -287,7 +286,7 @@ static void __init xen_update_mem_tables(unsigned long pfn, unsigned long mfn)
 	}
 
 	/* Update kernel mapping, but not for highmem. */
-	if ((pfn << PAGE_SHIFT) >= __pa(high_memory))
+	if (pfn >= PFN_UP(__pa(high_memory - 1)))
 		return;
 
 	if (HYPERVISOR_update_va_mapping((unsigned long)__va(pfn << PAGE_SHIFT),
@@ -318,7 +317,6 @@ static void __init xen_do_set_identity_and_remap_chunk(
 	unsigned long ident_pfn_iter, remap_pfn_iter;
 	unsigned long ident_end_pfn = start_pfn + size;
 	unsigned long left = size;
-	unsigned long ident_cnt = 0;
 	unsigned int i, chunk;
 
 	WARN_ON(size == 0);
@@ -347,8 +345,7 @@ static void __init xen_do_set_identity_and_remap_chunk(
 		xen_remap_mfn = mfn;
 
 		/* Set identity map */
-		ident_cnt += set_phys_range_identity(ident_pfn_iter,
-			ident_pfn_iter + chunk);
+		set_phys_range_identity(ident_pfn_iter, ident_pfn_iter + chunk);
 
 		left -= chunk;
 	}
@@ -371,7 +368,7 @@ static void __init xen_do_set_identity_and_remap_chunk(
 static unsigned long __init xen_set_identity_and_remap_chunk(
         const struct e820entry *list, size_t map_size, unsigned long start_pfn,
 	unsigned long end_pfn, unsigned long nr_pages, unsigned long remap_pfn,
-	unsigned long *identity, unsigned long *released)
+	unsigned long *released, unsigned long *remapped)
 {
 	unsigned long pfn;
 	unsigned long i = 0;
@@ -386,8 +383,7 @@ static unsigned long __init xen_set_identity_and_remap_chunk(
 		/* Do not remap pages beyond the current allocation */
 		if (cur_pfn >= nr_pages) {
 			/* Identity map remaining pages */
-			*identity += set_phys_range_identity(cur_pfn,
-				cur_pfn + size);
+			set_phys_range_identity(cur_pfn, cur_pfn + size);
 			break;
 		}
 		if (cur_pfn + size > nr_pages)
@@ -398,7 +394,7 @@ static unsigned long __init xen_set_identity_and_remap_chunk(
 		if (!remap_range_size) {
 			pr_warning("Unable to find available pfn range, not remapping identity pages\n");
 			xen_set_identity_and_release_chunk(cur_pfn,
-				cur_pfn + left, nr_pages, identity, released);
+				cur_pfn + left, nr_pages, released);
 			break;
 		}
 		/* Adjust size to fit in current e820 RAM region */
@@ -410,7 +406,7 @@ static unsigned long __init xen_set_identity_and_remap_chunk(
 		/* Update variables to reflect new mappings. */
 		i += size;
 		remap_pfn += size;
-		*identity += size;
+		*remapped += size;
 	}
 
 	/*
@@ -427,13 +423,13 @@ static unsigned long __init xen_set_identity_and_remap_chunk(
 
 static void __init xen_set_identity_and_remap(
 	const struct e820entry *list, size_t map_size, unsigned long nr_pages,
-	unsigned long *released)
+	unsigned long *released, unsigned long *remapped)
 {
 	phys_addr_t start = 0;
-	unsigned long identity = 0;
 	unsigned long last_pfn = nr_pages;
 	const struct e820entry *entry;
 	unsigned long num_released = 0;
+	unsigned long num_remapped = 0;
 	int i;
 
 	/*
@@ -460,14 +456,14 @@ static void __init xen_set_identity_and_remap(
 				last_pfn = xen_set_identity_and_remap_chunk(
 						list, map_size, start_pfn,
 						end_pfn, nr_pages, last_pfn,
-						&identity, &num_released);
+						&num_released, &num_remapped);
 			start = end;
 		}
 	}
 
 	*released = num_released;
+	*remapped = num_remapped;
 
-	pr_info("Set %ld page(s) to 1-1 mapping\n", identity);
 	pr_info("Released %ld page(s)\n", num_released);
 }
 
@@ -586,6 +582,7 @@ char * __init xen_memory_setup(void)
 	struct xen_memory_map memmap;
 	unsigned long max_pages;
 	unsigned long extra_pages = 0;
+	unsigned long remapped_pages;
 	int i;
 	int op;
 
@@ -635,9 +632,10 @@ char * __init xen_memory_setup(void)
 	 * underlying RAM.
 	 */
 	xen_set_identity_and_remap(map, memmap.nr_entries, max_pfn,
-				   &xen_released_pages);
+				   &xen_released_pages, &remapped_pages);
 
 	extra_pages += xen_released_pages;
+	extra_pages += remapped_pages;
 
 	/*
 	 * Clamp the amount of extra memory to a EXTRA_MEM_RATIO
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index f473d268d387..69087341d9ae 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -391,7 +391,7 @@ static const struct clock_event_device *xen_clockevent =
 
 struct xen_clock_event_device {
 	struct clock_event_device evt;
-	char *name;
+	char name[16];
 };
 static DEFINE_PER_CPU(struct xen_clock_event_device, xen_clock_events) = { .evt.irq = -1 };
 
@@ -420,46 +420,38 @@ void xen_teardown_timer(int cpu)
 	if (evt->irq >= 0) {
 		unbind_from_irqhandler(evt->irq, NULL);
 		evt->irq = -1;
-		kfree(per_cpu(xen_clock_events, cpu).name);
-		per_cpu(xen_clock_events, cpu).name = NULL;
 	}
 }
 
 void xen_setup_timer(int cpu)
 {
-	char *name;
-	struct clock_event_device *evt;
+	struct xen_clock_event_device *xevt = &per_cpu(xen_clock_events, cpu);
+	struct clock_event_device *evt = &xevt->evt;
 	int irq;
 
-	evt = &per_cpu(xen_clock_events, cpu).evt;
 	WARN(evt->irq >= 0, "IRQ%d for CPU%d is already allocated\n", evt->irq, cpu);
 	if (evt->irq >= 0)
 		xen_teardown_timer(cpu);
 
 	printk(KERN_INFO "installing Xen timer for CPU %d\n", cpu);
 
-	name = kasprintf(GFP_KERNEL, "timer%d", cpu);
-	if (!name)
-		name = "<timer kasprintf failed>";
+	snprintf(xevt->name, sizeof(xevt->name), "timer%d", cpu);
 
 	irq = bind_virq_to_irqhandler(VIRQ_TIMER, cpu, xen_timer_interrupt,
 				      IRQF_PERCPU|IRQF_NOBALANCING|IRQF_TIMER|
 				      IRQF_FORCE_RESUME|IRQF_EARLY_RESUME,
-				      name, NULL);
+				      xevt->name, NULL);
 	(void)xen_set_irq_priority(irq, XEN_IRQ_PRIORITY_MAX);
 
 	memcpy(evt, xen_clockevent, sizeof(*evt));
 
 	evt->cpumask = cpumask_of(cpu);
 	evt->irq = irq;
-	per_cpu(xen_clock_events, cpu).name = name;
 }
 
 
 void xen_setup_cpu_clockevents(void)
 {
-	BUG_ON(preemptible());
-
 	clockevents_register_device(this_cpu_ptr(&xen_clock_events.evt));
 }