15 files changed, 117 insertions, 38 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6a154a91c7e7..685692c94f05 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -108,7 +108,6 @@ config X86
 	select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC)
 	select GENERIC_TIME_VSYSCALL if X86_64
 	select KTIME_SCALAR if X86_32
-	select ALWAYS_USE_PERSISTENT_CLOCK
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
 	select HAVE_CONTEXT_TRACKING if X86_64
diff --git a/arch/x86/crypto/crc32-pclmul_asm.S b/arch/x86/crypto/crc32-pclmul_asm.S
index 94c27df8a549..f247304299a2 100644
--- a/arch/x86/crypto/crc32-pclmul_asm.S
+++ b/arch/x86/crypto/crc32-pclmul_asm.S
@@ -240,7 +240,7 @@ fold_64:
 	pand    %xmm3, %xmm1
 	PCLMULQDQ 0x00, CONSTANT, %xmm1
 	pxor    %xmm2, %xmm1
-	pextrd  $0x01, %xmm1, %eax
+	PEXTRD  0x01, %xmm1, %eax
 
 	ret
 ENDPROC(crc32_pclmul_le_16)
diff --git a/arch/x86/crypto/sha256-avx-asm.S b/arch/x86/crypto/sha256-avx-asm.S
index 56610c4bf31b..642f15687a0a 100644
--- a/arch/x86/crypto/sha256-avx-asm.S
+++ b/arch/x86/crypto/sha256-avx-asm.S
@@ -118,7 +118,7 @@ y2 = %r15d
 
 _INP_END_SIZE = 8
 _INP_SIZE = 8
-_XFER_SIZE = 8
+_XFER_SIZE = 16
 _XMM_SAVE_SIZE = 0
 
 _INP_END = 0
diff --git a/arch/x86/crypto/sha256-ssse3-asm.S b/arch/x86/crypto/sha256-ssse3-asm.S
index 98d3c391da81..f833b74d902b 100644
--- a/arch/x86/crypto/sha256-ssse3-asm.S
+++ b/arch/x86/crypto/sha256-ssse3-asm.S
@@ -111,7 +111,7 @@ y2 = %r15d
 
 _INP_END_SIZE = 8
 _INP_SIZE = 8
-_XFER_SIZE = 8
+_XFER_SIZE = 16
 _XMM_SAVE_SIZE = 0
 
 _INP_END = 0
diff --git a/arch/x86/include/asm/inst.h b/arch/x86/include/asm/inst.h
index 280bf7fb6aba..3e115273ed88 100644
--- a/arch/x86/include/asm/inst.h
+++ b/arch/x86/include/asm/inst.h
@@ -9,12 +9,68 @@
 
 #define REG_NUM_INVALID		100
 
-#define REG_TYPE_R64		0
-#define REG_TYPE_XMM		1
+#define REG_TYPE_R32		0
+#define REG_TYPE_R64		1
+#define REG_TYPE_XMM		2
 #define REG_TYPE_INVALID	100
 
+	.macro R32_NUM opd r32
+	\opd = REG_NUM_INVALID
+	.ifc \r32,%eax
+	\opd = 0
+	.endif
+	.ifc \r32,%ecx
+	\opd = 1
+	.endif
+	.ifc \r32,%edx
+	\opd = 2
+	.endif
+	.ifc \r32,%ebx
+	\opd = 3
+	.endif
+	.ifc \r32,%esp
+	\opd = 4
+	.endif
+	.ifc \r32,%ebp
+	\opd = 5
+	.endif
+	.ifc \r32,%esi
+	\opd = 6
+	.endif
+	.ifc \r32,%edi
+	\opd = 7
+	.endif
+#ifdef CONFIG_X86_64
+	.ifc \r32,%r8d
+	\opd = 8
+	.endif
+	.ifc \r32,%r9d
+	\opd = 9
+	.endif
+	.ifc \r32,%r10d
+	\opd = 10
+	.endif
+	.ifc \r32,%r11d
+	\opd = 11
+	.endif
+	.ifc \r32,%r12d
+	\opd = 12
+	.endif
+	.ifc \r32,%r13d
+	\opd = 13
+	.endif
+	.ifc \r32,%r14d
+	\opd = 14
+	.endif
+	.ifc \r32,%r15d
+	\opd = 15
+	.endif
+#endif
+	.endm
+
 	.macro R64_NUM opd r64
 	\opd = REG_NUM_INVALID
+#ifdef CONFIG_X86_64
 	.ifc \r64,%rax
 	\opd = 0
 	.endif
@@ -63,6 +119,7 @@
 	.ifc \r64,%r15
 	\opd = 15
 	.endif
+#endif
 	.endm
 
 	.macro XMM_NUM opd xmm
@@ -118,10 +175,13 @@
 	.endm
 
 	.macro REG_TYPE type reg
+	R32_NUM reg_type_r32 \reg
 	R64_NUM reg_type_r64 \reg
 	XMM_NUM reg_type_xmm \reg
 	.if reg_type_r64 <> REG_NUM_INVALID
 	\type = REG_TYPE_R64
+	.elseif reg_type_r32 <> REG_NUM_INVALID
+	\type = REG_TYPE_R32
 	.elseif reg_type_xmm <> REG_NUM_INVALID
 	\type = REG_TYPE_XMM
 	.else
@@ -162,6 +222,16 @@
 	.byte \imm8
 	.endm
 
+	.macro PEXTRD imm8 xmm gpr
+	R32_NUM extrd_opd1 \gpr
+	XMM_NUM extrd_opd2 \xmm
+	PFX_OPD_SIZE
+	PFX_REX extrd_opd1 extrd_opd2
+	.byte 0x0f, 0x3a, 0x16
+	MODRM 0xc0 extrd_opd1 extrd_opd2
+	.byte \imm8
+	.endm
+
 	.macro AESKEYGENASSIST rcon xmm1 xmm2
 	XMM_NUM aeskeygen_opd1 \xmm1
 	XMM_NUM aeskeygen_opd2 \xmm2
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index dab95a85f7f8..55b67614ed94 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -34,7 +34,7 @@
 extern pgd_t early_level4_pgt[PTRS_PER_PGD];
 extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD];
 static unsigned int __initdata next_early_pgt = 2;
-pmdval_t __initdata early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX);
+pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX);
 
 /* Wipe all early page tables except for the kernel symbol map */
 static void __init reset_early_page_tables(void)
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 08f7e8039099..321d65ebaffe 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -115,8 +115,10 @@ startup_64:
 	movq	%rdi, %rax
 	shrq	$PUD_SHIFT, %rax
 	andl	$(PTRS_PER_PUD-1), %eax
-	movq	%rdx, (4096+0)(%rbx,%rax,8)
-	movq	%rdx, (4096+8)(%rbx,%rax,8)
+	movq	%rdx, 4096(%rbx,%rax,8)
+	incl	%eax
+	andl	$(PTRS_PER_PUD-1), %eax
+	movq	%rdx, 4096(%rbx,%rax,8)
 
 	addq	$8192, %rbx
 	movq	%rdi, %rax
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index 245a71db401a..cb339097b9ea 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -22,23 +22,19 @@
 /*
  * Were we in an interrupt that interrupted kernel mode?
  *
- * For now, with eagerfpu we will return interrupted kernel FPU
- * state as not-idle. TBD: Ideally we can change the return value
- * to something like __thread_has_fpu(current). But we need to
- * be careful of doing __thread_clear_has_fpu() before saving
- * the FPU etc for supporting nested uses etc. For now, take
- * the simple route!
- *
  * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that
  * pair does nothing at all: the thread must not have fpu (so
  * that we don't try to save the FPU state), and TS must
  * be set (so that the clts/stts pair does nothing that is
  * visible in the interrupted kernel thread).
+ *
+ * Except for the eagerfpu case when we return 1 unless we've already
+ * been eager and saved the state in kernel_fpu_begin().
  */
 static inline bool interrupted_kernel_fpu_idle(void)
 {
 	if (use_eager_fpu())
-		return 0;
+		return __thread_has_fpu(current);
 
 	return !__thread_has_fpu(current) &&
 		(read_cr0() & X86_CR0_TS);
@@ -78,8 +74,8 @@ void __kernel_fpu_begin(void)
 	struct task_struct *me = current;
 
 	if (__thread_has_fpu(me)) {
-		__save_init_fpu(me);
 		__thread_clear_has_fpu(me);
+		__save_init_fpu(me);
 		/* We do 'stts()' in __kernel_fpu_end() */
 	} else if (!use_eager_fpu()) {
 		this_cpu_write(fpu_owner_task, NULL);
diff --git a/arch/x86/kernel/microcode_intel_early.c b/arch/x86/kernel/microcode_intel_early.c
index d893e8ed8ac9..2e9e12871c2b 100644
--- a/arch/x86/kernel/microcode_intel_early.c
+++ b/arch/x86/kernel/microcode_intel_early.c
@@ -487,6 +487,7 @@ static inline void show_saved_mc(void)
 #endif
 
 #if defined(CONFIG_MICROCODE_INTEL_EARLY) && defined(CONFIG_HOTPLUG_CPU)
+static DEFINE_MUTEX(x86_cpu_microcode_mutex);
 /*
  * Save this mc into mc_saved_data. So it will be loaded early when a CPU is
  * hot added or resumes.
@@ -507,7 +508,7 @@ int save_mc_for_early(u8 *mc)
 	 * Hold hotplug lock so mc_saved_data is not accessed by a CPU in
 	 * hotplug.
 	 */
-	cpu_hotplug_driver_lock();
+	mutex_lock(&x86_cpu_microcode_mutex);
 
 	mc_saved_count_init = mc_saved_data.mc_saved_count;
 	mc_saved_count = mc_saved_data.mc_saved_count;
@@ -544,7 +545,7 @@ int save_mc_for_early(u8 *mc)
 	}
 
 out:
-	cpu_hotplug_driver_unlock();
+	mutex_unlock(&x86_cpu_microcode_mutex);
 
 	return ret;
 }
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 607af0d4d5ef..4e7a37ff03ab 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -312,6 +312,8 @@ void arch_cpu_idle(void)
 {
 	if (cpuidle_idle_call())
 		x86_idle();
+	else
+		local_irq_enable();
 }
 
 /*
@@ -368,9 +370,6 @@ void amd_e400_remove_cpu(int cpu)
  */
 static void amd_e400_idle(void)
 {
-	if (need_resched())
-		return;
-
 	if (!amd_e400_c1e_detected) {
 		u32 lo, hi;
 
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index fdc5dca14fb3..eaac1743def7 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -359,7 +359,17 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 }
 
 /*
- * would have hole in the middle or ends, and only ram parts will be mapped.
+ * We need to iterate through the E820 memory map and create direct mappings
+ * for only E820_RAM and E820_KERN_RESERVED regions. We cannot simply
+ * create direct mappings for all pfns from [0 to max_low_pfn) and
+ * [4GB to max_pfn) because of possible memory holes in high addresses
+ * that cannot be marked as UC by fixed/variable range MTRRs.
+ * Depending on the alignment of E820 ranges, this may possibly result
+ * in using smaller size (i.e. 4K instead of 2M or 1G) page tables.
+ *
+ * init_mem_mapping() calls init_range_memory_mapping() with big range.
+ * That range would have hole in the middle or ends, and only ram parts
+ * will be mapped in init_range_memory_mapping().
  */
 static unsigned long __init init_range_memory_mapping(
 					   unsigned long r_start,
@@ -419,6 +429,13 @@ void __init init_mem_mapping(void)
 	max_pfn_mapped = 0; /* will get exact value next */
 	min_pfn_mapped = real_end >> PAGE_SHIFT;
 	last_start = start = real_end;
+
+	/*
+	 * We start from the top (end of memory) and go to the bottom.
+	 * The memblock_find_in_range() gets us a block of RAM from the
+	 * end of RAM in [min_pfn_mapped, max_pfn_mapped) used as new pages
+	 * for page table.
+	 */
 	while (last_start > ISA_END_ADDRESS) {
 		if (last_start > step_size) {
 			start = round_down(last_start - 1, step_size);
diff --git a/arch/x86/pci/mrst.c b/arch/x86/pci/mrst.c
index 0e0fabf17342..6eb18c42a28a 100644
--- a/arch/x86/pci/mrst.c
+++ b/arch/x86/pci/mrst.c
@@ -141,11 +141,6 @@ static int pci_device_update_fixed(struct pci_bus *bus, unsigned int devfn,
  */
 static bool type1_access_ok(unsigned int bus, unsigned int devfn, int reg)
 {
-	if (bus == 0 && (devfn == PCI_DEVFN(2, 0)
-				|| devfn == PCI_DEVFN(0, 0)
-				|| devfn == PCI_DEVFN(3, 0)))
-		return 1;
-
 	/* This is a workaround for A0 LNC bug where PCI status register does
 	 * not have new CAP bit set. can not be written by SW either.
 	 *
@@ -155,7 +150,10 @@ static bool type1_access_ok(unsigned int bus, unsigned int devfn, int reg)
 	 */
 	if (reg >= 0x100 || reg == PCI_STATUS || reg == PCI_HEADER_TYPE)
 		return 0;
-
+	if (bus == 0 && (devfn == PCI_DEVFN(2, 0)
+				|| devfn == PCI_DEVFN(0, 0)
+				|| devfn == PCI_DEVFN(3, 0)))
+		return 1;
 	return 0; /* langwell on others */
 }
 
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 55856b2310d3..82089d8b1954 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -206,7 +206,7 @@ static efi_status_t virt_efi_get_next_variable(unsigned long *name_size,
 	}
 
 	if (boot_used_size && !finished) {
-		unsigned long size;
+		unsigned long size = 0;
 		u32 attr;
 		efi_status_t s;
 		void *tmp;
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 8ff37995d54e..fb44426fe931 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -576,24 +576,22 @@ void xen_send_IPI_mask_allbutself(const struct cpumask *mask,
 {
 	unsigned cpu;
 	unsigned int this_cpu = smp_processor_id();
+	int xen_vector = xen_map_vector(vector);
 
-	if (!(num_online_cpus() > 1))
+	if (!(num_online_cpus() > 1) || (xen_vector < 0))
 		return;
 
 	for_each_cpu_and(cpu, mask, cpu_online_mask) {
 		if (this_cpu == cpu)
 			continue;
 
-		xen_smp_send_call_function_single_ipi(cpu);
+		xen_send_IPI_one(cpu, xen_vector);
 	}
 }
 
 void xen_send_IPI_allbutself(int vector)
 {
-	int xen_vector = xen_map_vector(vector);
-
-	if (xen_vector >= 0)
-		xen_send_IPI_mask_allbutself(cpu_online_mask, xen_vector);
+	xen_send_IPI_mask_allbutself(cpu_online_mask, vector);
 }
 
 static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id)
diff --git a/arch/x86/xen/smp.h b/arch/x86/xen/smp.h
index 8981a76d081a..c7c2d89efd76 100644
--- a/arch/x86/xen/smp.h
+++ b/arch/x86/xen/smp.h
@@ -5,7 +5,6 @@ extern void xen_send_IPI_mask(const struct cpumask *mask,
 extern void xen_send_IPI_mask_allbutself(const struct cpumask *mask,
 				int vector);
 extern void xen_send_IPI_allbutself(int vector);
-extern void physflat_send_IPI_allbutself(int vector);
 extern void xen_send_IPI_all(int vector);
 extern void xen_send_IPI_self(int vector);