Merge branch 'x86/debug' into core/objtool, to pick up frame pointer fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

29 files changed, 214 insertions, 136 deletions

diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index 8c35df4..169963f 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -5,6 +5,7 @@
 #include <asm/page_types.h>
 #include <asm/msr.h>
 #include <asm/asm-offsets.h>
+#include <asm/frame.h>
 
 # Copyright 2003 Pavel Machek <pavel@suse.cz>, distribute under GPLv2
 
@@ -39,6 +40,7 @@ bogus_64_magic:
 	jmp	bogus_64_magic
 
 ENTRY(do_suspend_lowlevel)
+	FRAME_BEGIN
 	subq	$8, %rsp
 	xorl	%eax, %eax
 	call	save_processor_state
@@ -109,6 +111,7 @@ ENTRY(do_suspend_lowlevel)
 
 	xorl	%eax, %eax
 	addq	$8, %rsp
+	FRAME_END
 	jmp	restore_processor_state
 ENDPROC(do_suspend_lowlevel)
 
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index c80c02c..ab5c2c6 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -30,7 +30,7 @@ static unsigned int numachip1_get_apic_id(unsigned long x)
 	unsigned long value;
 	unsigned int id = (x >> 24) & 0xff;
 
-	if (static_cpu_has_safe(X86_FEATURE_NODEID_MSR)) {
+	if (static_cpu_has(X86_FEATURE_NODEID_MSR)) {
 		rdmsrl(MSR_FAM10H_NODE_ID, value);
 		id |= (value << 2) & 0xff00;
 	}
@@ -178,7 +178,7 @@ static void fixup_cpu_id(struct cpuinfo_x86 *c, int node)
 	this_cpu_write(cpu_llc_id, node);
 
 	/* Account for nodes per socket in multi-core-module processors */
-	if (static_cpu_has_safe(X86_FEATURE_NODEID_MSR)) {
+	if (static_cpu_has(X86_FEATURE_NODEID_MSR)) {
 		rdmsrl(MSR_FAM10H_NODE_ID, val);
 		nodes = ((val >> 3) & 7) + 1;
 	}
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index 6ce3902..fdeb0ce 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -7,7 +7,7 @@
 #include <linux/lguest.h>
 #include "../../../drivers/lguest/lg.h"
 
-#define __SYSCALL_I386(nr, sym, compat) [nr] = 1,
+#define __SYSCALL_I386(nr, sym, qual) [nr] = 1,
 static char syscalls[] = {
 #include <asm/syscalls_32.h>
 };
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index f2edafb..d875f97 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -4,17 +4,11 @@
 
 #include <asm/ia32.h>
 
-#define __SYSCALL_64(nr, sym, compat) [nr] = 1,
-#define __SYSCALL_COMMON(nr, sym, compat) [nr] = 1,
-#ifdef CONFIG_X86_X32_ABI
-# define __SYSCALL_X32(nr, sym, compat) [nr] = 1,
-#else
-# define __SYSCALL_X32(nr, sym, compat) /* nothing */
-#endif
+#define __SYSCALL_64(nr, sym, qual) [nr] = 1,
 static char syscalls_64[] = {
 #include <asm/syscalls_64.h>
 };
-#define __SYSCALL_I386(nr, sym, compat) [nr] = 1,
+#define __SYSCALL_I386(nr, sym, qual) [nr] = 1,
 static char syscalls_ia32[] = {
 #include <asm/syscalls_32.h>
 };
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 5803130..faa7b52 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -64,7 +64,7 @@ ifdef CONFIG_X86_FEATURE_NAMES
 quiet_cmd_mkcapflags = MKCAP   $@
       cmd_mkcapflags = $(CONFIG_SHELL) $(srctree)/$(src)/mkcapflags.sh $< $@
 
-cpufeature = $(src)/../../include/asm/cpufeature.h
+cpufeature = $(src)/../../include/asm/cpufeatures.h
 
 targets += capflags.c
 $(obj)/capflags.c: $(cpufeature) $(src)/mkcapflags.sh FORCE
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index a07956a..fe2f089 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -75,7 +75,10 @@ static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
  */
 
 extern __visible void vide(void);
-__asm__(".globl vide\n\t.align 4\nvide: ret");
+__asm__(".globl vide\n"
+	".type vide, @function\n"
+	".align 4\n"
+	"vide: ret\n");
 
 static void init_amd_k5(struct cpuinfo_x86 *c)
 {
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index ae20be6..6608c03 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -1,7 +1,7 @@
 #include <linux/bitops.h>
 #include <linux/kernel.h>
 
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <asm/e820.h>
 #include <asm/mtrr.h>
 #include <asm/msr.h>
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 37830de..079d83f 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1475,20 +1475,6 @@ void cpu_init(void)
 }
 #endif
 
-#ifdef CONFIG_X86_DEBUG_STATIC_CPU_HAS
-void warn_pre_alternatives(void)
-{
-	WARN(1, "You're using static_cpu_has before alternatives have run!\n");
-}
-EXPORT_SYMBOL_GPL(warn_pre_alternatives);
-#endif
-
-inline bool __static_cpu_has_safe(u16 bit)
-{
-	return boot_cpu_has(bit);
-}
-EXPORT_SYMBOL_GPL(__static_cpu_has_safe);
-
 static void bsp_resume(void)
 {
 	if (this_cpu->c_bsp_resume)
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index aaf152e..15e47c1 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -8,6 +8,7 @@
 #include <linux/timer.h>
 #include <asm/pci-direct.h>
 #include <asm/tsc.h>
+#include <asm/cpufeature.h>
 
 #include "cpu.h"
 
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 565648b..9299e3b 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -8,7 +8,7 @@
 #include <linux/module.h>
 #include <linux/uaccess.h>
 
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <asm/pgtable.h>
 #include <asm/msr.h>
 #include <asm/bugs.h>
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 0b6c523..341449c 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -14,7 +14,7 @@
 #include <linux/sysfs.h>
 #include <linux/pci.h>
 
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <asm/amd_nb.h>
 #include <asm/smp.h>
 
diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c
index afa9f0d..fbb5e90 100644
--- a/arch/x86/kernel/cpu/match.c
+++ b/arch/x86/kernel/cpu/match.c
@@ -1,5 +1,5 @@
 #include <asm/cpu_device_id.h>
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <linux/cpu.h>
 #include <linux/module.h>
 #include <linux/slab.h>
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index a006f4c..b5b187c 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1576,6 +1576,17 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 
 		if (c->x86 == 6 && c->x86_model == 45)
 			quirk_no_way_out = quirk_sandybridge_ifu;
+		/*
+		 * MCG_CAP.MCG_SER_P is necessary but not sufficient to know
+		 * whether this processor will actually generate recoverable
+		 * machine checks. Check to see if this is an E7 model Xeon.
+		 * We can't do a model number check because E5 and E7 use the
+		 * same model number. E5 doesn't support recovery, E7 does.
+		 */
+		if (mca_cfg.recovery || (mca_cfg.ser &&
+			!strncmp(c->x86_model_id,
+				 "Intel(R) Xeon(R) CPU E7-", 24)))
+			set_cpu_cap(c, X86_FEATURE_MCE_RECOVERY);
 	}
 	if (cfg->monarch_timeout < 0)
 		cfg->monarch_timeout = 0;
@@ -2028,6 +2039,8 @@ static int __init mcheck_enable(char *str)
 		cfg->bootlog = (str[0] == 'b');
 	else if (!strcmp(str, "bios_cmci_threshold"))
 		cfg->bios_cmci_threshold = true;
+	else if (!strcmp(str, "recovery"))
+		cfg->recovery = true;
 	else if (isdigit(str[0])) {
 		if (get_option(&str, &cfg->tolerant) == 2)
 			get_option(&str, &(cfg->monarch_timeout));
diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh
index 3f20710..6988c74 100644
--- a/arch/x86/kernel/cpu/mkcapflags.sh
+++ b/arch/x86/kernel/cpu/mkcapflags.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 #
-# Generate the x86_cap/bug_flags[] arrays from include/asm/cpufeature.h
+# Generate the x86_cap/bug_flags[] arrays from include/asm/cpufeatures.h
 #
 
 IN=$1
@@ -49,8 +49,8 @@ dump_array()
 trap 'rm "$OUT"' EXIT
 
 (
-	echo "#ifndef _ASM_X86_CPUFEATURE_H"
-	echo "#include <asm/cpufeature.h>"
+	echo "#ifndef _ASM_X86_CPUFEATURES_H"
+	echo "#include <asm/cpufeatures.h>"
 	echo "#endif"
 	echo ""
 
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 5c3d149..74f1d90 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -47,7 +47,7 @@
 #include <linux/smp.h>
 #include <linux/syscore_ops.h>
 
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <asm/e820.h>
 #include <asm/mtrr.h>
 #include <asm/msr.h>
diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c
index 252da7a..a19a663 100644
--- a/arch/x86/kernel/cpu/transmeta.c
+++ b/arch/x86/kernel/cpu/transmeta.c
@@ -1,6 +1,6 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <asm/msr.h>
 #include "cpu.h"
 
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 569c1e4..b3c2a69 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -24,6 +24,7 @@
 #include <asm/e820.h>
 #include <asm/proto.h>
 #include <asm/setup.h>
+#include <asm/cpufeature.h>
 
 /*
  * The e820 map is the map that gets modified e.g. with command line parameters
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 29408d6..04f9641e 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -697,9 +697,8 @@ static inline void tramp_free(void *tramp) { }
 #endif
 
 /* Defined as markers to the end of the ftrace default trampolines */
-extern void ftrace_caller_end(void);
 extern void ftrace_regs_caller_end(void);
-extern void ftrace_return(void);
+extern void ftrace_epilogue(void);
 extern void ftrace_caller_op_ptr(void);
 extern void ftrace_regs_caller_op_ptr(void);
 
@@ -746,7 +745,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 		op_offset = (unsigned long)ftrace_regs_caller_op_ptr;
 	} else {
 		start_offset = (unsigned long)ftrace_caller;
-		end_offset = (unsigned long)ftrace_caller_end;
+		end_offset = (unsigned long)ftrace_epilogue;
 		op_offset = (unsigned long)ftrace_caller_op_ptr;
 	}
 
@@ -754,7 +753,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 
 	/*
 	 * Allocate enough size to store the ftrace_caller code,
-	 * the jmp to ftrace_return, as well as the address of
+	 * the jmp to ftrace_epilogue, as well as the address of
 	 * the ftrace_ops this trampoline is used for.
 	 */
 	trampoline = alloc_tramp(size + MCOUNT_INSN_SIZE + sizeof(void *));
@@ -772,8 +771,8 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 
 	ip = (unsigned long)trampoline + size;
 
-	/* The trampoline ends with a jmp to ftrace_return */
-	jmp = ftrace_jmp_replace(ip, (unsigned long)ftrace_return);
+	/* The trampoline ends with a jmp to ftrace_epilogue */
+	jmp = ftrace_jmp_replace(ip, (unsigned long)ftrace_epilogue);
 	memcpy(trampoline + size, jmp, MCOUNT_INSN_SIZE);
 
 	/*
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 6bc9ae2..af11129 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -19,7 +19,7 @@
 #include <asm/setup.h>
 #include <asm/processor-flags.h>
 #include <asm/msr-index.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/percpu.h>
 #include <asm/nops.h>
 #include <asm/bootparam.h>
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index ffdc0e8..2e97468 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -38,7 +38,6 @@
 #define pud_index(x)	(((x) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
 
 L4_PAGE_OFFSET = pgd_index(__PAGE_OFFSET)
-L3_PAGE_OFFSET = pud_index(__PAGE_OFFSET)
 L4_START_KERNEL = pgd_index(__START_KERNEL_map)
 L3_START_KERNEL = pud_index(__START_KERNEL_map)
 
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index b8e6ff5..be0ebbb 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -12,6 +12,7 @@
 #include <linux/pm.h>
 #include <linux/io.h>
 
+#include <asm/cpufeature.h>
 #include <asm/irqdomain.h>
 #include <asm/fixmap.h>
 #include <asm/hpet.h>
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 1deffe6..5b187df 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -671,38 +671,37 @@ NOKPROBE_SYMBOL(kprobe_int3_handler);
  * When a retprobed function returns, this code saves registers and
  * calls trampoline_handler() runs, which calls the kretprobe's handler.
  */
-static void __used kretprobe_trampoline_holder(void)
-{
-	asm volatile (
-			".global kretprobe_trampoline\n"
-			"kretprobe_trampoline: \n"
+asm(
+	".global kretprobe_trampoline\n"
+	".type kretprobe_trampoline, @function\n"
+	"kretprobe_trampoline:\n"
 #ifdef CONFIG_X86_64
-			/* We don't bother saving the ss register */
-			"	pushq %rsp\n"
-			"	pushfq\n"
-			SAVE_REGS_STRING
-			"	movq %rsp, %rdi\n"
-			"	call trampoline_handler\n"
-			/* Replace saved sp with true return address. */
-			"	movq %rax, 152(%rsp)\n"
-			RESTORE_REGS_STRING
-			"	popfq\n"
+	/* We don't bother saving the ss register */
+	"	pushq %rsp\n"
+	"	pushfq\n"
+	SAVE_REGS_STRING
+	"	movq %rsp, %rdi\n"
+	"	call trampoline_handler\n"
+	/* Replace saved sp with true return address. */
+	"	movq %rax, 152(%rsp)\n"
+	RESTORE_REGS_STRING
+	"	popfq\n"
 #else
-			"	pushf\n"
-			SAVE_REGS_STRING
-			"	movl %esp, %eax\n"
-			"	call trampoline_handler\n"
-			/* Move flags to cs */
-			"	movl 56(%esp), %edx\n"
-			"	movl %edx, 52(%esp)\n"
-			/* Replace saved flags with true return address. */
-			"	movl %eax, 56(%esp)\n"
-			RESTORE_REGS_STRING
-			"	popf\n"
+	"	pushf\n"
+	SAVE_REGS_STRING
+	"	movl %esp, %eax\n"
+	"	call trampoline_handler\n"
+	/* Move flags to cs */
+	"	movl 56(%esp), %edx\n"
+	"	movl %edx, 52(%esp)\n"
+	/* Replace saved flags with true return address. */
+	"	movl %eax, 56(%esp)\n"
+	RESTORE_REGS_STRING
+	"	popf\n"
 #endif
-			"	ret\n");
-}
-NOKPROBE_SYMBOL(kretprobe_trampoline_holder);
+	"	ret\n"
+	".size kretprobe_trampoline, .-kretprobe_trampoline\n"
+);
 NOKPROBE_SYMBOL(kretprobe_trampoline);
 
 /*
diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S
index 87e1762..ed48a9f 100644
--- a/arch/x86/kernel/mcount_64.S
+++ b/arch/x86/kernel/mcount_64.S
@@ -168,12 +168,14 @@ GLOBAL(ftrace_call)
 	restore_mcount_regs
 
 	/*
-	 * The copied trampoline must call ftrace_return as it
+	 * The copied trampoline must call ftrace_epilogue as it
 	 * still may need to call the function graph tracer.
+	 *
+	 * The code up to this label is copied into trampolines so
+	 * think twice before adding any new code or changing the
+	 * layout here.
 	 */
-GLOBAL(ftrace_caller_end)
-
-GLOBAL(ftrace_return)
+GLOBAL(ftrace_epilogue)
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 GLOBAL(ftrace_graph_call)
@@ -244,14 +246,14 @@ GLOBAL(ftrace_regs_call)
 	popfq
 
 	/*
-	 * As this jmp to ftrace_return can be a short jump
+	 * As this jmp to ftrace_epilogue can be a short jump
 	 * it must not be copied into the trampoline.
 	 * The trampoline will add the code to jump
 	 * to the return.
 	 */
 GLOBAL(ftrace_regs_caller_end)
 
-	jmp ftrace_return
+	jmp ftrace_epilogue
 
 END(ftrace_regs_caller)
 
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 64f9616..7f3550a 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -40,7 +40,7 @@
 #include <linux/uaccess.h>
 #include <linux/gfp.h>
 
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <asm/msr.h>
 
 static struct class *msr_class;
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index cb6282c..548ddf7 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -61,7 +61,38 @@
 	regs->seg = GET_SEG(seg) | 3;			\
 } while (0)
 
-int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
+#ifdef CONFIG_X86_64
+/*
+ * If regs->ss will cause an IRET fault, change it.  Otherwise leave it
+ * alone.  Using this generally makes no sense unless
+ * user_64bit_mode(regs) would return true.
+ */
+static void force_valid_ss(struct pt_regs *regs)
+{
+	u32 ar;
+	asm volatile ("lar %[old_ss], %[ar]\n\t"
+		      "jz 1f\n\t"		/* If invalid: */
+		      "xorl %[ar], %[ar]\n\t"	/* set ar = 0 */
+		      "1:"
+		      : [ar] "=r" (ar)
+		      : [old_ss] "rm" ((u16)regs->ss));
+
+	/*
+	 * For a valid 64-bit user context, we need DPL 3, type
+	 * read-write data or read-write exp-down data, and S and P
+	 * set.  We can't use VERW because VERW doesn't check the
+	 * P bit.
+	 */
+	ar &= AR_DPL_MASK | AR_S | AR_P | AR_TYPE_MASK;
+	if (ar != (AR_DPL3 | AR_S | AR_P | AR_TYPE_RWDATA) &&
+	    ar != (AR_DPL3 | AR_S | AR_P | AR_TYPE_RWDATA_EXPDOWN))
+		regs->ss = __USER_DS;
+}
+#endif
+
+static int restore_sigcontext(struct pt_regs *regs,
+			      struct sigcontext __user *sc,
+			      unsigned long uc_flags)
 {
 	unsigned long buf_val;
 	void __user *buf;
@@ -94,15 +125,18 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
 		COPY(r15);
 #endif /* CONFIG_X86_64 */
 
-#ifdef CONFIG_X86_32
 		COPY_SEG_CPL3(cs);
 		COPY_SEG_CPL3(ss);
-#else /* !CONFIG_X86_32 */
-		/* Kernel saves and restores only the CS segment register on signals,
-		 * which is the bare minimum needed to allow mixed 32/64-bit code.
-		 * App's signal handler can save/restore other segments if needed. */
-		COPY_SEG_CPL3(cs);
-#endif /* CONFIG_X86_32 */
+
+#ifdef CONFIG_X86_64
+		/*
+		 * Fix up SS if needed for the benefit of old DOSEMU and
+		 * CRIU.
+		 */
+		if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) &&
+			     user_64bit_mode(regs)))
+			force_valid_ss(regs);
+#endif
 
 		get_user_ex(tmpflags, &sc->flags);
 		regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
@@ -165,6 +199,7 @@ int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
 		put_user_ex(regs->cs, &sc->cs);
 		put_user_ex(0, &sc->gs);
 		put_user_ex(0, &sc->fs);
+		put_user_ex(regs->ss, &sc->ss);
 #endif /* CONFIG_X86_32 */
 
 		put_user_ex(fpstate, &sc->fpstate);
@@ -403,6 +438,21 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 	return 0;
 }
 #else /* !CONFIG_X86_32 */
+static unsigned long frame_uc_flags(struct pt_regs *regs)
+{
+	unsigned long flags;
+
+	if (cpu_has_xsave)
+		flags = UC_FP_XSTATE | UC_SIGCONTEXT_SS;
+	else
+		flags = UC_SIGCONTEXT_SS;
+
+	if (likely(user_64bit_mode(regs)))
+		flags |= UC_STRICT_RESTORE_SS;
+
+	return flags;
+}
+
 static int __setup_rt_frame(int sig, struct ksignal *ksig,
 			    sigset_t *set, struct pt_regs *regs)
 {
@@ -422,10 +472,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 
 	put_user_try {
 		/* Create the ucontext.  */
-		if (cpu_has_xsave)
-			put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
-		else
-			put_user_ex(0, &frame->uc.uc_flags);
+		put_user_ex(frame_uc_flags(regs), &frame->uc.uc_flags);
 		put_user_ex(0, &frame->uc.uc_link);
 		save_altstack_ex(&frame->uc.uc_stack, regs->sp);
 
@@ -459,10 +506,28 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 
 	regs->sp = (unsigned long)frame;
 
-	/* Set up the CS register to run signal handlers in 64-bit mode,
-	   even if the handler happens to be interrupting 32-bit code. */
+	/*
+	 * Set up the CS and SS registers to run signal handlers in
+	 * 64-bit mode, even if the handler happens to be interrupting
+	 * 32-bit or 16-bit code.
+	 *
+	 * SS is subtle.  In 64-bit mode, we don't need any particular
+	 * SS descriptor, but we do need SS to be valid.  It's possible
+	 * that the old SS is entirely bogus -- this can happen if the
+	 * signal we're trying to deliver is #GP or #SS caused by a bad
+	 * SS value.  We also have a compatbility issue here: DOSEMU
+	 * relies on the contents of the SS register indicating the
+	 * SS value at the time of the signal, even though that code in
+	 * DOSEMU predates sigreturn's ability to restore SS.  (DOSEMU
+	 * avoids relying on sigreturn to restore SS; instead it uses
+	 * a trampoline.)  So we do our best: if the old SS was valid,
+	 * we keep it.  Otherwise we replace it.
+	 */
 	regs->cs = __USER_CS;
 
+	if (unlikely(regs->ss != __USER_DS))
+		force_valid_ss(regs);
+
 	return 0;
 }
 #endif /* CONFIG_X86_32 */
@@ -489,10 +554,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig,
 
 	put_user_try {
 		/* Create the ucontext.  */
-		if (cpu_has_xsave)
-			put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
-		else
-			put_user_ex(0, &frame->uc.uc_flags);
+		put_user_ex(frame_uc_flags(regs), &frame->uc.uc_flags);
 		put_user_ex(0, &frame->uc.uc_link);
 		compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp);
 		put_user_ex(0, &frame->uc.uc__pad0);
@@ -554,7 +616,11 @@ asmlinkage unsigned long sys_sigreturn(void)
 
 	set_current_blocked(&set);
 
-	if (restore_sigcontext(regs, &frame->sc))
+	/*
+	 * x86_32 has no uc_flags bits relevant to restore_sigcontext.
+	 * Save a few cycles by skipping the __get_user.
+	 */
+	if (restore_sigcontext(regs, &frame->sc, 0))
 		goto badframe;
 	return regs->ax;
 
@@ -570,16 +636,19 @@ asmlinkage long sys_rt_sigreturn(void)
 	struct pt_regs *regs = current_pt_regs();
 	struct rt_sigframe __user *frame;
 	sigset_t set;
+	unsigned long uc_flags;
 
 	frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long));
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
 	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
 		goto badframe;
+	if (__get_user(uc_flags, &frame->uc.uc_flags))
+		goto badframe;
 
 	set_current_blocked(&set);
 
-	if (restore_sigcontext(regs, &frame->uc.uc_mcontext))
+	if (restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags))
 		goto badframe;
 
 	if (restore_altstack(&frame->uc.uc_stack))
@@ -692,12 +761,15 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 
 static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs)
 {
-#if defined(CONFIG_X86_32) || !defined(CONFIG_X86_64)
+#ifdef CONFIG_X86_64
+	if (is_ia32_task())
+		return __NR_ia32_restart_syscall;
+#endif
+#ifdef CONFIG_X86_X32_ABI
+	return __NR_restart_syscall | (regs->orig_ax & __X32_SYSCALL_BIT);
+#else
 	return __NR_restart_syscall;
-#else /* !CONFIG_X86_32 && CONFIG_X86_64 */
-	return test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall :
-		__NR_restart_syscall | (regs->orig_ax & __X32_SYSCALL_BIT);
-#endif /* CONFIG_X86_32 || !CONFIG_X86_64 */
+#endif
 }
 
 /*
@@ -763,6 +835,7 @@ asmlinkage long sys32_x32_rt_sigreturn(void)
 	struct pt_regs *regs = current_pt_regs();
 	struct rt_sigframe_x32 __user *frame;
 	sigset_t set;
+	unsigned long uc_flags;
 
 	frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8);
 
@@ -770,10 +843,12 @@ asmlinkage long sys32_x32_rt_sigreturn(void)
 		goto badframe;
 	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
 		goto badframe;
+	if (__get_user(uc_flags, &frame->uc.uc_flags))
+		goto badframe;
 
 	set_current_blocked(&set);
 
-	if (restore_sigcontext(regs, &frame->uc.uc_mcontext))
+	if (restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags))
 		goto badframe;
 
 	if (compat_restore_altstack(&frame->uc.uc_stack))
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index ade185a..410e8e2 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -83,30 +83,16 @@ gate_desc idt_table[NR_VECTORS] __page_aligned_bss;
 DECLARE_BITMAP(used_vectors, NR_VECTORS);
 EXPORT_SYMBOL_GPL(used_vectors);
 
-static inline void conditional_sti(struct pt_regs *regs)
+static inline void cond_local_irq_enable(struct pt_regs *regs)
 {
 	if (regs->flags & X86_EFLAGS_IF)
 		local_irq_enable();
 }
 
-static inline void preempt_conditional_sti(struct pt_regs *regs)
-{
-	preempt_count_inc();
-	if (regs->flags & X86_EFLAGS_IF)
-		local_irq_enable();
-}
-
-static inline void conditional_cli(struct pt_regs *regs)
-{
-	if (regs->flags & X86_EFLAGS_IF)
-		local_irq_disable();
-}
-
-static inline void preempt_conditional_cli(struct pt_regs *regs)
+static inline void cond_local_irq_disable(struct pt_regs *regs)
 {
 	if (regs->flags & X86_EFLAGS_IF)
 		local_irq_disable();
-	preempt_count_dec();
 }
 
 void ist_enter(struct pt_regs *regs)
@@ -286,7 +272,7 @@ static void do_error_trap(struct pt_regs *regs, long error_code, char *str,
 
 	if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) !=
 			NOTIFY_STOP) {
-		conditional_sti(regs);
+		cond_local_irq_enable(regs);
 		do_trap(trapnr, signr, str, regs, error_code,
 			fill_trap_info(regs, signr, trapnr, &info));
 	}
@@ -368,7 +354,7 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 	if (notify_die(DIE_TRAP, "bounds", regs, error_code,
 			X86_TRAP_BR, SIGSEGV) == NOTIFY_STOP)
 		return;
-	conditional_sti(regs);
+	cond_local_irq_enable(regs);
 
 	if (!user_mode(regs))
 		die("bounds", regs, error_code);
@@ -443,7 +429,7 @@ do_general_protection(struct pt_regs *regs, long error_code)
 	struct task_struct *tsk;
 
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
-	conditional_sti(regs);
+	cond_local_irq_enable(regs);
 
 	if (v8086_mode(regs)) {
 		local_irq_enable();
@@ -517,9 +503,11 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 	 * as we may switch to the interrupt stack.
 	 */
 	debug_stack_usage_inc();
-	preempt_conditional_sti(regs);
+	preempt_disable();
+	cond_local_irq_enable(regs);
 	do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL);
-	preempt_conditional_cli(regs);
+	cond_local_irq_disable(regs);
+	preempt_enable_no_resched();
 	debug_stack_usage_dec();
 exit:
 	ist_exit(regs);
@@ -648,12 +636,14 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
 	debug_stack_usage_inc();
 
 	/* It's safe to allow irq's after DR6 has been saved */
-	preempt_conditional_sti(regs);
+	preempt_disable();
+	cond_local_irq_enable(regs);
 
 	if (v8086_mode(regs)) {
 		handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code,
 					X86_TRAP_DB);
-		preempt_conditional_cli(regs);
+		cond_local_irq_disable(regs);
+		preempt_enable_no_resched();
 		debug_stack_usage_dec();
 		goto exit;
 	}
@@ -673,7 +663,8 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
 	si_code = get_si_code(tsk->thread.debugreg6);
 	if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp)
 		send_sigtrap(tsk, regs, error_code, si_code);
-	preempt_conditional_cli(regs);
+	cond_local_irq_disable(regs);
+	preempt_enable_no_resched();
 	debug_stack_usage_dec();
 
 exit:
@@ -696,7 +687,7 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
 
 	if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, SIGFPE) == NOTIFY_STOP)
 		return;
-	conditional_sti(regs);
+	cond_local_irq_enable(regs);
 
 	if (!user_mode(regs)) {
 		if (!fixup_exception(regs)) {
@@ -743,7 +734,7 @@ do_simd_coprocessor_error(struct pt_regs *regs, long error_code)
 dotraplinkage void
 do_spurious_interrupt_bug(struct pt_regs *regs, long error_code)
 {
-	conditional_sti(regs);
+	cond_local_irq_enable(regs);
 }
 
 dotraplinkage void
@@ -756,7 +747,7 @@ do_device_not_available(struct pt_regs *regs, long error_code)
 	if (read_cr0() & X86_CR0_EM) {
 		struct math_emu_info info = { };
 
-		conditional_sti(regs);
+		cond_local_irq_enable(regs);
 
 		info.regs = regs;
 		math_emulate(&info);
@@ -765,7 +756,7 @@ do_device_not_available(struct pt_regs *regs, long error_code)
 #endif
 	fpu__restore(&current->thread.fpu); /* interrupts still off */
 #ifdef CONFIG_X86_32
-	conditional_sti(regs);
+	cond_local_irq_enable(regs);
 #endif
 }
 NOKPROBE_SYMBOL(do_device_not_available);
diff --git a/arch/x86/kernel/verify_cpu.S b/arch/x86/kernel/verify_cpu.S
index 07efb35..014ea59 100644
--- a/arch/x86/kernel/verify_cpu.S
+++ b/arch/x86/kernel/verify_cpu.S
@@ -30,7 +30,7 @@
  * 	appropriately. Either display a message or halt.
  */
 
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/msr-index.h>
 
 verify_cpu:
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index e574b85..3dce1ca 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -362,7 +362,7 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus)
 	/* make room for real-mode segments */
 	tsk->thread.sp0 += 16;
 
-	if (static_cpu_has_safe(X86_FEATURE_SEP))
+	if (static_cpu_has(X86_FEATURE_SEP))
 		tsk->thread.sysenter_cs = 0;
 
 	load_sp0(tss, &tsk->thread);
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 74e4bf1..92dc211 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -195,6 +195,17 @@ SECTIONS
 	:init
 #endif
 
+	/*
+	 * Section for code used exclusively before alternatives are run. All
+	 * references to such code must be patched out by alternatives, normally
+	 * by using X86_FEATURE_ALWAYS CPU feature bit.
+	 *
+	 * See static_cpu_has() for an example.
+	 */
+	.altinstr_aux : AT(ADDR(.altinstr_aux) - LOAD_OFFSET) {
+		*(.altinstr_aux)
+	}
+
 	INIT_DATA_SECTION(16)
 
 	.x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) {