Merge branches 'x86/fpu', 'x86/mm' and 'x86/asm' into x86/pkeys

Provide a stable basis for the pkeys patches, which touches various
x86 details.
Signed-off-by: Ingo Molnar <mingo@kernel.org>

Documentation/kernel-parameters.txt

@@ -666,7 +666,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	clearcpuid=BITNUM [X86]
 			Disable CPUID feature X for the kernel. See
-			arch/x86/include/asm/cpufeature.h for the valid bit
+			arch/x86/include/asm/cpufeatures.h for the valid bit
 			numbers. Note the Linux specific bits are not necessarily
 			stable over kernel options, but the vendor specific
 			ones should be.
@@ -2566,6 +2566,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	nointroute	[IA-64]
 
+	noinvpcid	[X86] Disable the INVPCID cpu feature.
+
 	nojitter	[IA-64] Disables jitter checking for ITC timers.
 
 	no-kvmclock	[X86,KVM] Disable paravirtualized KVM clock driver

arch/x86/Kconfig.debug

@@ -350,16 +350,6 @@ config DEBUG_IMR_SELFTEST
 
 	  If unsure say N here.
 
-config X86_DEBUG_STATIC_CPU_HAS
-	bool "Debug alternatives"
-	depends on DEBUG_KERNEL
-	---help---
-	  This option causes additional code to be generated which
-	  fails if static_cpu_has() is used before alternatives have
-	  run.
-
-	  If unsure, say N.
-
 config X86_DEBUG_FPU
 	bool "Debug the x86 FPU code"
 	depends on DEBUG_KERNEL

arch/x86/boot/cpuflags.h

 #ifndef BOOT_CPUFLAGS_H
 #define BOOT_CPUFLAGS_H
 
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/processor-flags.h>
 
 struct cpu_features {

arch/x86/boot/mkcpustr.c

@@ -17,7 +17,7 @@
 
 #include "../include/asm/required-features.h"
 #include "../include/asm/disabled-features.h"
-#include "../include/asm/cpufeature.h"
+#include "../include/asm/cpufeatures.h"
 #include "../kernel/cpu/capflags.c"
 
 int main(void)

arch/x86/crypto/crc32-pclmul_glue.c

@@ -33,7 +33,7 @@
 #include <linux/crc32.h>
 #include <crypto/internal/hash.h>
 
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/cpu_device_id.h>
 #include <asm/fpu/api.h>
 

arch/x86/crypto/crc32c-intel_glue.c

@@ -30,7 +30,7 @@
 #include <linux/kernel.h>
 #include <crypto/internal/hash.h>
 
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/cpu_device_id.h>
 #include <asm/fpu/internal.h>
 

arch/x86/crypto/crct10dif-pclmul_glue.c

@@ -30,7 +30,7 @@
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <asm/fpu/api.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/cpu_device_id.h>
 
 asmlinkage __u16 crc_t10dif_pcl(__u16 crc, const unsigned char *buf,

arch/x86/entry/calling.h

@@ -201,37 +201,6 @@ For 32-bit we have the following conventions - kernel is built with
 	.byte 0xf1
 	.endm
 
-#else /* CONFIG_X86_64 */
-
-/*
- * For 32bit only simplified versions of SAVE_ALL/RESTORE_ALL. These
- * are different from the entry_32.S versions in not changing the segment
- * registers. So only suitable for in kernel use, not when transitioning
- * from or to user space. The resulting stack frame is not a standard
- * pt_regs frame. The main use case is calling C code from assembler
- * when all the registers need to be preserved.
- */
-
-	.macro SAVE_ALL
-	pushl %eax
-	pushl %ebp
-	pushl %edi
-	pushl %esi
-	pushl %edx
-	pushl %ecx
-	pushl %ebx
-	.endm
-
-	.macro RESTORE_ALL
-	popl %ebx
-	popl %ecx
-	popl %edx
-	popl %esi
-	popl %edi
-	popl %ebp
-	popl %eax
-	.endm
-
 #endif /* CONFIG_X86_64 */
 
 /*

arch/x86/entry/common.c

@@ -26,6 +26,7 @@
 #include <asm/traps.h>
 #include <asm/vdso.h>
 #include <asm/uaccess.h>
+#include <asm/cpufeature.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
@@ -344,6 +345,32 @@ __visible inline void syscall_return_slowpath(struct pt_regs *regs)
 	prepare_exit_to_usermode(regs);
 }
 
+#ifdef CONFIG_X86_64
+__visible void do_syscall_64(struct pt_regs *regs)
+{
+	struct thread_info *ti = pt_regs_to_thread_info(regs);
+	unsigned long nr = regs->orig_ax;
+
+	local_irq_enable();
+
+	if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY)
+		nr = syscall_trace_enter(regs);
+
+	/*
+	 * NB: Native and x32 syscalls are dispatched from the same
+	 * table.  The only functional difference is the x32 bit in
+	 * regs->orig_ax, which changes the behavior of some syscalls.
+	 */
+	if (likely((nr & __SYSCALL_MASK) < NR_syscalls)) {
+		regs->ax = sys_call_table[nr & __SYSCALL_MASK](
+			regs->di, regs->si, regs->dx,
+			regs->r10, regs->r8, regs->r9);
+	}
+
+	syscall_return_slowpath(regs);
+}
+#endif
+
 #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
 /*
  * Does a 32-bit syscall.  Called with IRQs on and does all entry and

arch/x86/entry/entry_32.S

@@ -40,7 +40,7 @@
 #include <asm/processor-flags.h>
 #include <asm/ftrace.h>
 #include <asm/irq_vectors.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 #include <asm/asm.h>
 #include <asm/smap.h>

arch/x86/entry/syscall_32.c

@@ -6,17 +6,11 @@
 #include <asm/asm-offsets.h>
 #include <asm/syscall.h>
 
-#ifdef CONFIG_IA32_EMULATION
-#define SYM(sym, compat) compat
-#else
-#define SYM(sym, compat) sym
-#endif
-
-#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage long SYM(sym, compat)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ;
+#define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ;
 #include <asm/syscalls_32.h>
 #undef __SYSCALL_I386
 
-#define __SYSCALL_I386(nr, sym, compat) [nr] = SYM(sym, compat),
+#define __SYSCALL_I386(nr, sym, qual) [nr] = sym,
 
 extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
 

arch/x86/entry/syscall_64.c

@@ -6,19 +6,14 @@
 #include <asm/asm-offsets.h>
 #include <asm/syscall.h>
 
-#define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
+#define __SYSCALL_64_QUAL_(sym) sym
+#define __SYSCALL_64_QUAL_ptregs(sym) ptregs_##sym
 
-#ifdef CONFIG_X86_X32_ABI
-# define __SYSCALL_X32(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
-#else
-# define __SYSCALL_X32(nr, sym, compat) /* nothing */
-#endif
-
-#define __SYSCALL_64(nr, sym, compat) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ;
+#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long __SYSCALL_64_QUAL_##qual(sym)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
 #include <asm/syscalls_64.h>
 #undef __SYSCALL_64
 
-#define __SYSCALL_64(nr, sym, compat) [nr] = sym,
+#define __SYSCALL_64(nr, sym, qual) [nr] = __SYSCALL_64_QUAL_##qual(sym),
 
 extern long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
 

arch/x86/entry/syscalls/syscall_64.tbl

@@ -21,7 +21,7 @@
 12	common	brk			sys_brk
 13	64	rt_sigaction		sys_rt_sigaction
 14	common	rt_sigprocmask		sys_rt_sigprocmask
-15	64	rt_sigreturn		stub_rt_sigreturn
+15	64	rt_sigreturn		sys_rt_sigreturn/ptregs
 16	64	ioctl			sys_ioctl
 17	common	pread64			sys_pread64
 18	common	pwrite64		sys_pwrite64
@@ -62,10 +62,10 @@
 53	common	socketpair		sys_socketpair
 54	64	setsockopt		sys_setsockopt
 55	64	getsockopt		sys_getsockopt
-56	common	clone			stub_clone
-57	common	fork			stub_fork
-58	common	vfork			stub_vfork
-59	64	execve			stub_execve
+56	common	clone			sys_clone/ptregs
+57	common	fork			sys_fork/ptregs
+58	common	vfork			sys_vfork/ptregs
+59	64	execve			sys_execve/ptregs
 60	common	exit			sys_exit
 61	common	wait4			sys_wait4
 62	common	kill			sys_kill
@@ -178,7 +178,7 @@
 169	common	reboot			sys_reboot
 170	common	sethostname		sys_sethostname
 171	common	setdomainname		sys_setdomainname
-172	common	iopl			sys_iopl
+172	common	iopl			sys_iopl/ptregs
 173	common	ioperm			sys_ioperm
 174	64	create_module
 175	common	init_module		sys_init_module
@@ -328,7 +328,7 @@
 319	common	memfd_create		sys_memfd_create
 320	common	kexec_file_load		sys_kexec_file_load
 321	common	bpf			sys_bpf
-322	64	execveat		stub_execveat
+322	64	execveat		sys_execveat/ptregs
 323	common	userfaultfd		sys_userfaultfd
 324	common	membarrier		sys_membarrier
 325	common	mlock2			sys_mlock2
@@ -339,14 +339,14 @@
 # for native 64-bit operation.
 #
 512	x32	rt_sigaction		compat_sys_rt_sigaction
-513	x32	rt_sigreturn		stub_x32_rt_sigreturn
+513	x32	rt_sigreturn		sys32_x32_rt_sigreturn
 514	x32	ioctl			compat_sys_ioctl
 515	x32	readv			compat_sys_readv
 516	x32	writev			compat_sys_writev
 517	x32	recvfrom		compat_sys_recvfrom
 518	x32	sendmsg			compat_sys_sendmsg
 519	x32	recvmsg			compat_sys_recvmsg
-520	x32	execve			stub_x32_execve
+520	x32	execve			compat_sys_execve/ptregs
 521	x32	ptrace			compat_sys_ptrace
 522	x32	rt_sigpending		compat_sys_rt_sigpending
 523	x32	rt_sigtimedwait		compat_sys_rt_sigtimedwait
@@ -371,4 +371,4 @@
 542	x32	getsockopt		compat_sys_getsockopt
 543	x32	io_setup		compat_sys_io_setup
 544	x32	io_submit		compat_sys_io_submit
-545	x32	execveat		stub_x32_execveat
+545	x32	execveat		compat_sys_execveat/ptregs

arch/x86/entry/syscalls/syscalltbl.sh

@@ -3,13 +3,63 @@
 in="$1"
 out="$2"
 
+syscall_macro() {
+    abi="$1"
+    nr="$2"
+    entry="$3"
+
+    # Entry can be either just a function name or "function/qualifier"
+    real_entry="${entry%%/*}"
+    qualifier="${entry:${#real_entry}}"		# Strip the function name
+    qualifier="${qualifier:1}"			# Strip the slash, if any
+
+    echo "__SYSCALL_${abi}($nr, $real_entry, $qualifier)"
+}
+
+emit() {
+    abi="$1"
+    nr="$2"
+    entry="$3"
+    compat="$4"
+
+    if [ "$abi" == "64" -a -n "$compat" ]; then
+	echo "a compat entry for a 64-bit syscall makes no sense" >&2
+	exit 1
+    fi
+
+    if [ -z "$compat" ]; then
+	if [ -n "$entry" ]; then
+	    syscall_macro "$abi" "$nr" "$entry"
+	fi
+    else
+	echo "#ifdef CONFIG_X86_32"
+	if [ -n "$entry" ]; then
+	    syscall_macro "$abi" "$nr" "$entry"
+	fi
+	echo "#else"
+	syscall_macro "$abi" "$nr" "$compat"
+	echo "#endif"
+    fi
+}
+
 grep '^[0-9]' "$in" | sort -n | (
     while read nr abi name entry compat; do
 	abi=`echo "$abi" | tr '[a-z]' '[A-Z]'`
-	if [ -n "$compat" ]; then
-	    echo "__SYSCALL_${abi}($nr, $entry, $compat)"
-	elif [ -n "$entry" ]; then
-	    echo "__SYSCALL_${abi}($nr, $entry, $entry)"
+	if [ "$abi" == "COMMON" -o "$abi" == "64" ]; then
+	    # COMMON is the same as 64, except that we don't expect X32
+	    # programs to use it.  Our expectation has nothing to do with
+	    # any generated code, so treat them the same.
+	    emit 64 "$nr" "$entry" "$compat"
+	elif [ "$abi" == "X32" ]; then
+	    # X32 is equivalent to 64 on an X32-compatible kernel.
+	    echo "#ifdef CONFIG_X86_X32_ABI"
+	    emit 64 "$nr" "$entry" "$compat"
+	    echo "#endif"
+	elif [ "$abi" == "I386" ]; then
+	    emit "$abi" "$nr" "$entry" "$compat"
+	else
+	    echo "Unknown abi $abi" >&2
+	    exit 1
 	fi
     done
 ) > "$out"

arch/x86/entry/vdso/vdso2c.h

@@ -150,16 +150,9 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 	}
 	fprintf(outfile, "\n};\n\n");
 
-	fprintf(outfile, "static struct page *pages[%lu];\n\n",
-		mapping_size / 4096);
-
 	fprintf(outfile, "const struct vdso_image %s = {\n", name);
 	fprintf(outfile, "\t.data = raw_data,\n");
 	fprintf(outfile, "\t.size = %lu,\n", mapping_size);
-	fprintf(outfile, "\t.text_mapping = {\n");
-	fprintf(outfile, "\t\t.name = \"[vdso]\",\n");
-	fprintf(outfile, "\t\t.pages = pages,\n");
-	fprintf(outfile, "\t},\n");
 	if (alt_sec) {
 		fprintf(outfile, "\t.alt = %lu,\n",
 			(unsigned long)GET_LE(&alt_sec->sh_offset));

arch/x86/entry/vdso/vdso32-setup.c

@@ -11,7 +11,6 @@
 #include <linux/kernel.h>
 #include <linux/mm_types.h>
 
-#include <asm/cpufeature.h>
 #include <asm/processor.h>
 #include <asm/vdso.h>
 

arch/x86/entry/vdso/vdso32/system_call.S

@@ -3,7 +3,7 @@
 */
 
 #include <asm/dwarf2.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 
 /*

arch/x86/entry/vdso/vma.c

@@ -20,6 +20,7 @@
 #include <asm/page.h>
 #include <asm/hpet.h>
 #include <asm/desc.h>
+#include <asm/cpufeature.h>
 
 #if defined(CONFIG_X86_64)
 unsigned int __read_mostly vdso64_enabled = 1;
@@ -27,13 +28,7 @@ unsigned int __read_mostly vdso64_enabled = 1;
 
 void __init init_vdso_image(const struct vdso_image *image)
 {
-	int i;
-	int npages = (image->size) / PAGE_SIZE;
-
 	BUG_ON(image->size % PAGE_SIZE != 0);
-	for (i = 0; i < npages; i++)
-		image->text_mapping.pages[i] =
-			virt_to_page(image->data + i*PAGE_SIZE);
 
 	apply_alternatives((struct alt_instr *)(image->data + image->alt),
 			   (struct alt_instr *)(image->data + image->alt +
@@ -90,18 +85,87 @@ static unsigned long vdso_addr(unsigned long start, unsigned len)
 #endif
 }
 
+static int vdso_fault(const struct vm_special_mapping *sm,
+		      struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	const struct vdso_image *image = vma->vm_mm->context.vdso_image;
+
+	if (!image || (vmf->pgoff << PAGE_SHIFT) >= image->size)
+		return VM_FAULT_SIGBUS;
+
+	vmf->page = virt_to_page(image->data + (vmf->pgoff << PAGE_SHIFT));
+	get_page(vmf->page);
+	return 0;
+}
+
+static const struct vm_special_mapping text_mapping = {
+	.name = "[vdso]",
+	.fault = vdso_fault,
+};
+
+static int vvar_fault(const struct vm_special_mapping *sm,
+		      struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	const struct vdso_image *image = vma->vm_mm->context.vdso_image;
+	long sym_offset;
+	int ret = -EFAULT;
+
+	if (!image)
+		return VM_FAULT_SIGBUS;
+
+	sym_offset = (long)(vmf->pgoff << PAGE_SHIFT) +
+		image->sym_vvar_start;
+
+	/*
+	 * Sanity check: a symbol offset of zero means that the page
+	 * does not exist for this vdso image, not that the page is at
+	 * offset zero relative to the text mapping.  This should be
+	 * impossible here, because sym_offset should only be zero for
+	 * the page past the end of the vvar mapping.
+	 */
+	if (sym_offset == 0)
+		return VM_FAULT_SIGBUS;
+
+	if (sym_offset == image->sym_vvar_page) {
+		ret = vm_insert_pfn(vma, (unsigned long)vmf->virtual_address,
+				    __pa_symbol(&__vvar_page) >> PAGE_SHIFT);
+	} else if (sym_offset == image->sym_hpet_page) {
+#ifdef CONFIG_HPET_TIMER
+		if (hpet_address && vclock_was_used(VCLOCK_HPET)) {
+			ret = vm_insert_pfn_prot(
+				vma,
+				(unsigned long)vmf->virtual_address,
+				hpet_address >> PAGE_SHIFT,
+				pgprot_noncached(PAGE_READONLY));
+		}
+#endif
+	} else if (sym_offset == image->sym_pvclock_page) {
+		struct pvclock_vsyscall_time_info *pvti =
+			pvclock_pvti_cpu0_va();
+		if (pvti && vclock_was_used(VCLOCK_PVCLOCK)) {
+			ret = vm_insert_pfn(
+				vma,
+				(unsigned long)vmf->virtual_address,
+				__pa(pvti) >> PAGE_SHIFT);
+		}
+	}
+
+	if (ret == 0 || ret == -EBUSY)
+		return VM_FAULT_NOPAGE;
+
+	return VM_FAULT_SIGBUS;
+}
+
 static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	unsigned long addr, text_start;
 	int ret = 0;
-	static struct page *no_pages[] = {NULL};
-	static struct vm_special_mapping vvar_mapping = {
+	static const struct vm_special_mapping vvar_mapping = {
 		.name = "[vvar]",
-		.pages = no_pages,
+		.fault = vvar_fault,
 	};
-	struct pvclock_vsyscall_time_info *pvti;
 
 	if (calculate_addr) {
 		addr = vdso_addr(current->mm->start_stack,
@@ -121,6 +185,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 
 	text_start = addr - image->sym_vvar_start;
 	current->mm->context.vdso = (void __user *)text_start;
+	current->mm->context.vdso_image = image;
 
 	/*
 	 * MAYWRITE to allow gdb to COW and set breakpoints
@@ -130,7 +195,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 				       image->size,
 				       VM_READ|VM_EXEC|
 				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
-				       &image->text_mapping);
+				       &text_mapping);
 
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
@@ -140,7 +205,8 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 	vma = _install_special_mapping(mm,
 				       addr,
 				       -image->sym_vvar_start,
-				       VM_READ|VM_MAYREAD,
+				       VM_READ|VM_MAYREAD|VM_IO|VM_DONTDUMP|
+				       VM_PFNMAP,
 				       &vvar_mapping);
 
 	if (IS_ERR(vma)) {
@@ -148,41 +214,6 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 		goto up_fail;
 	}
 
-	if (image->sym_vvar_page)
-		ret = remap_pfn_range(vma,
-				      text_start + image->sym_vvar_page,
-				      __pa_symbol(&__vvar_page) >> PAGE_SHIFT,
-				      PAGE_SIZE,
-				      PAGE_READONLY);
-
-	if (ret)
-		goto up_fail;
-
-#ifdef CONFIG_HPET_TIMER
-	if (hpet_address && image->sym_hpet_page) {
-		ret = io_remap_pfn_range(vma,
-			text_start + image->sym_hpet_page,
-			hpet_address >> PAGE_SHIFT,
-			PAGE_SIZE,
-			pgprot_noncached(PAGE_READONLY));
-
-		if (ret)
-			goto up_fail;
-	}
-#endif
-
-	pvti = pvclock_pvti_cpu0_va();
-	if (pvti && image->sym_pvclock_page) {
-		ret = remap_pfn_range(vma,
-				      text_start + image->sym_pvclock_page,
-				      __pa(pvti) >> PAGE_SHIFT,
-				      PAGE_SIZE,
-				      PAGE_READONLY);
-
-		if (ret)
-			goto up_fail;
-	}
-
 up_fail:
 	if (ret)
 		current->mm->context.vdso = NULL;
@@ -254,7 +285,7 @@ static void vgetcpu_cpu_init(void *arg)
 #ifdef CONFIG_NUMA
 	node = cpu_to_node(cpu);
 #endif
-	if (cpu_has(&cpu_data(cpu), X86_FEATURE_RDTSCP))
+	if (static_cpu_has(X86_FEATURE_RDTSCP))
 		write_rdtscp_aux((node << 12) | cpu);
 
 	/*

arch/x86/entry/vsyscall/vsyscall_gtod.c

@@ -16,6 +16,8 @@
 #include <asm/vgtod.h>
 #include <asm/vvar.h>
 
+int vclocks_used __read_mostly;
+
 DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data);
 
 void update_vsyscall_tz(void)
@@ -26,12 +28,17 @@ void update_vsyscall_tz(void)
 
 void update_vsyscall(struct timekeeper *tk)
 {
+	int vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode;
 	struct vsyscall_gtod_data *vdata = &vsyscall_gtod_data;
 
+	/* Mark the new vclock used. */
+	BUILD_BUG_ON(VCLOCK_MAX >= 32);
+	WRITE_ONCE(vclocks_used, READ_ONCE(vclocks_used) | (1 << vclock_mode));
+
 	gtod_write_begin(vdata);
 
 	/* copy vsyscall data */
-	vdata->vclock_mode	= tk->tkr_mono.clock->archdata.vclock_mode;
+	vdata->vclock_mode	= vclock_mode;
 	vdata->cycle_last	= tk->tkr_mono.cycle_last;
 	vdata->mask		= tk->tkr_mono.mask;
 	vdata->mult		= tk->tkr_mono.mult;

arch/x86/include/asm/alternative.h

@@ -151,12 +151,6 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	ALTINSTR_REPLACEMENT(newinstr2, feature2, 2)			\
 	".popsection"
 
-/*
- * This must be included *after* the definition of ALTERNATIVE due to
- * <asm/arch_hweight.h>
- */
-#include <asm/cpufeature.h>
-
 /*
  * Alternative instructions for different CPU types or capabilities.
  *

arch/x86/include/asm/apic.h

@@ -6,7 +6,6 @@
 
 #include <asm/alternative.h>
 #include <asm/cpufeature.h>
-#include <asm/processor.h>
 #include <asm/apicdef.h>
 #include <linux/atomic.h>
 #include <asm/fixmap.h>

arch/x86/include/asm/arch_hweight.h

 #ifndef _ASM_X86_HWEIGHT_H
 #define _ASM_X86_HWEIGHT_H
 
+#include <asm/cpufeatures.h>
+
 #ifdef CONFIG_64BIT
 /* popcnt %edi, %eax -- redundant REX prefix for alignment */
 #define POPCNT32 ".byte 0xf3,0x40,0x0f,0xb8,0xc7"

arch/x86/include/asm/bitops.h

@@ -91,7 +91,7 @@ set_bit(long nr, volatile unsigned long *addr)
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static inline void __set_bit(long nr, volatile unsigned long *addr)
+static __always_inline void __set_bit(long nr, volatile unsigned long *addr)
 {
 	asm volatile("bts %1,%0" : ADDR : "Ir" (nr) : "memory");
 }
@@ -128,13 +128,13 @@ clear_bit(long nr, volatile unsigned long *addr)
  * clear_bit() is atomic and implies release semantics before the memory
  * operation. It can be used for an unlock.
  */
-static inline void clear_bit_unlock(long nr, volatile unsigned long *addr)
+static __always_inline void clear_bit_unlock(long nr, volatile unsigned long *addr)
 {
 	barrier();
 	clear_bit(nr, addr);
 }
 
-static inline void __clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline void __clear_bit(long nr, volatile unsigned long *addr)
 {
 	asm volatile("btr %1,%0" : ADDR : "Ir" (nr));
 }
@@ -151,7 +151,7 @@ static inline void __clear_bit(long nr, volatile unsigned long *addr)
  * No memory barrier is required here, because x86 cannot reorder stores past
  * older loads. Same principle as spin_unlock.
  */
-static inline void __clear_bit_unlock(long nr, volatile unsigned long *addr)
+static __always_inline void __clear_bit_unlock(long nr, volatile unsigned long *addr)
 {
 	barrier();
 	__clear_bit(nr, addr);
@@ -166,7 +166,7 @@ static inline void __clear_bit_unlock(long nr, volatile unsigned long *addr)
  * If it's called on the same region of memory simultaneously, the effect
  * may be that only one operation succeeds.
  */
-static inline void __change_bit(long nr, volatile unsigned long *addr)
+static __always_inline void __change_bit(long nr, volatile unsigned long *addr)
 {
 	asm volatile("btc %1,%0" : ADDR : "Ir" (nr));
 }
@@ -180,7 +180,7 @@ static inline void __change_bit(long nr, volatile unsigned long *addr)
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void change_bit(long nr, volatile unsigned long *addr)
+static __always_inline void change_bit(long nr, volatile unsigned long *addr)
 {
 	if (IS_IMMEDIATE(nr)) {
 		asm volatile(LOCK_PREFIX "xorb %1,%0"
@@ -201,7 +201,7 @@ static inline void change_bit(long nr, volatile unsigned long *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int test_and_set_bit(long nr, volatile unsigned long *addr)
+static __always_inline int test_and_set_bit(long nr, volatile unsigned long *addr)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, "Ir", nr, "%0", "c");
 }
@@ -228,7 +228,7 @@ test_and_set_bit_lock(long nr, volatile unsigned long *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static inline int __test_and_set_bit(long nr, volatile unsigned long *addr)
+static __always_inline int __test_and_set_bit(long nr, volatile unsigned long *addr)
 {
 	int oldbit;
 
@@ -247,7 +247,7 @@ static inline int __test_and_set_bit(long nr, volatile unsigned long *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int test_and_clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline int test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, "Ir", nr, "%0", "c");
 }
@@ -268,7 +268,7 @@ static inline int test_and_clear_bit(long nr, volatile unsigned long *addr)
  * accessed from a hypervisor on the same CPU if running in a VM: don't change
  * this without also updating arch/x86/kernel/kvm.c
  */
-static inline int __test_and_clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline int __test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
 	int oldbit;
 
@@ -280,7 +280,7 @@ static inline int __test_and_clear_bit(long nr, volatile unsigned long *addr)
 }
 
 /* WARNING: non atomic and it can be reordered! */
-static inline int __test_and_change_bit(long nr, volatile unsigned long *addr)
+static __always_inline int __test_and_change_bit(long nr, volatile unsigned long *addr)
 {
 	int oldbit;
 
@@ -300,7 +300,7 @@ static inline int __test_and_change_bit(long nr, volatile unsigned long *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int test_and_change_bit(long nr, volatile unsigned long *addr)
+static __always_inline int test_and_change_bit(long nr, volatile unsigned long *addr)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, "Ir", nr, "%0", "c");
 }
@@ -311,7 +311,7 @@ static __always_inline int constant_test_bit(long nr, const volatile unsigned lo
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
 
-static inline int variable_test_bit(long nr, volatile const unsigned long *addr)
+static __always_inline int variable_test_bit(long nr, volatile const unsigned long *addr)
 {
 	int oldbit;
 
@@ -343,7 +343,7 @@ static int test_bit(int nr, const volatile unsigned long *addr);
  *
  * Undefined if no bit exists, so code should check against 0 first.
  */
-static inline unsigned long __ffs(unsigned long word)
+static __always_inline unsigned long __ffs(unsigned long word)
 {
 	asm("rep; bsf %1,%0"
 		: "=r" (word)
@@ -357,7 +357,7 @@ static inline unsigned long __ffs(unsigned long word)
  *
  * Undefined if no zero exists, so code should check against ~0UL first.
  */
-static inline unsigned long ffz(unsigned long word)
+static __always_inline unsigned long ffz(unsigned long word)
 {
 	asm("rep; bsf %1,%0"
 		: "=r" (word)
@@ -371,7 +371,7 @@ static inline unsigned long ffz(unsigned long word)
  *
  * Undefined if no set bit exists, so code should check against 0 first.
  */
-static inline unsigned long __fls(unsigned long word)
+static __always_inline unsigned long __fls(unsigned long word)
 {
 	asm("bsr %1,%0"
 	    : "=r" (word)
@@ -393,7 +393,7 @@ static inline unsigned long __fls(unsigned long word)
  * set bit if value is nonzero. The first (least significant) bit
  * is at position 1.
  */
-static inline int ffs(int x)
+static __always_inline int ffs(int x)
 {
 	int r;
 
@@ -434,7 +434,7 @@ static inline int ffs(int x)
  * set bit if value is nonzero. The last (most significant) bit is
  * at position 32.
  */
-static inline int fls(int x)
+static __always_inline int fls(int x)
 {
 	int r;
 

arch/x86/include/asm/clocksource.h

@@ -7,6 +7,7 @@
 #define VCLOCK_TSC	1  /* vDSO should use vread_tsc.	*/
 #define VCLOCK_HPET	2  /* vDSO should use vread_hpet.	*/
 #define VCLOCK_PVCLOCK	3 /* vDSO should use vread_pvclock. */
+#define VCLOCK_MAX	3
 
 struct arch_clocksource_data {
 	int vclock_mode;

arch/x86/include/asm/cmpxchg.h

@@ -2,6 +2,7 @@
 #define ASM_X86_CMPXCHG_H
 
 #include <linux/compiler.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative.h> /* Provides LOCK_PREFIX */
 
 /*

arch/x86/include/asm/dmi.h

@@ -15,7 +15,7 @@ static __always_inline __init void *dmi_alloc(unsigned len)
 /* Use early IO mappings for DMI because it's initialized early */
 #define dmi_early_remap		early_ioremap
 #define dmi_early_unmap		early_iounmap
-#define dmi_remap		ioremap
+#define dmi_remap		ioremap_cache
 #define dmi_unmap		iounmap
 
 #endif /* _ASM_X86_DMI_H */

arch/x86/include/asm/fixmap.h

@@ -138,7 +138,7 @@ extern void reserve_top_address(unsigned long reserve);
 extern int fixmaps_set;
 
 extern pte_t *kmap_pte;
-extern pgprot_t kmap_prot;
+#define kmap_prot PAGE_KERNEL
 extern pte_t *pkmap_page_table;
 
 void __native_set_fixmap(enum fixed_addresses idx, pte_t pte);

arch/x86/include/asm/fpu/internal.h

@@ -17,6 +17,7 @@
 #include <asm/user.h>
 #include <asm/fpu/api.h>
 #include <asm/fpu/xstate.h>
+#include <asm/cpufeature.h>
 
 /*
  * High level FPU state handling functions:
@@ -58,22 +59,22 @@ extern u64 fpu__get_supported_xfeatures_mask(void);
  */
 static __always_inline __pure bool use_eager_fpu(void)
 {
-	return static_cpu_has_safe(X86_FEATURE_EAGER_FPU);
+	return static_cpu_has(X86_FEATURE_EAGER_FPU);
 }
 
 static __always_inline __pure bool use_xsaveopt(void)
 {
-	return static_cpu_has_safe(X86_FEATURE_XSAVEOPT);
+	return static_cpu_has(X86_FEATURE_XSAVEOPT);
 }
 
 static __always_inline __pure bool use_xsave(void)
 {
-	return static_cpu_has_safe(X86_FEATURE_XSAVE);
+	return static_cpu_has(X86_FEATURE_XSAVE);
 }
 
 static __always_inline __pure bool use_fxsr(void)
 {
-	return static_cpu_has_safe(X86_FEATURE_FXSR);
+	return static_cpu_has(X86_FEATURE_FXSR);
 }
 
 /*
@@ -300,7 +301,7 @@ static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate)
 
 	WARN_ON(system_state != SYSTEM_BOOTING);
 
-	if (static_cpu_has_safe(X86_FEATURE_XSAVES))
+	if (static_cpu_has(X86_FEATURE_XSAVES))
 		XSTATE_OP(XSAVES, xstate, lmask, hmask, err);
 	else
 		XSTATE_OP(XSAVE, xstate, lmask, hmask, err);
@@ -322,7 +323,7 @@ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate)
 
 	WARN_ON(system_state != SYSTEM_BOOTING);
 
-	if (static_cpu_has_safe(X86_FEATURE_XSAVES))
+	if (static_cpu_has(X86_FEATURE_XSAVES))
 		XSTATE_OP(XRSTORS, xstate, lmask, hmask, err);
 	else
 		XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
@@ -460,7 +461,7 @@ static inline void copy_kernel_to_fpregs(union fpregs_state *fpstate)
 	 * pending. Clear the x87 state here by setting it to fixed values.
 	 * "m" is a random variable that should be in L1.
 	 */
-	if (unlikely(static_cpu_has_bug_safe(X86_BUG_FXSAVE_LEAK))) {
+	if (unlikely(static_cpu_has_bug(X86_BUG_FXSAVE_LEAK))) {
 		asm volatile(
 			"fnclex\n\t"
 			"emms\n\t"
@@ -589,7 +590,8 @@ switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu)
 	 * If the task has used the math, pre-load the FPU on xsave processors
 	 * or if the past 5 consecutive context-switches used math.
 	 */
-	fpu.preload = new_fpu->fpstate_active &&
+	fpu.preload = static_cpu_has(X86_FEATURE_FPU) &&
+		      new_fpu->fpstate_active &&
 		      (use_eager_fpu() || new_fpu->counter > 5);
 
 	if (old_fpu->fpregs_active) {

arch/x86/include/asm/frame.h

-#ifdef __ASSEMBLY__
+#ifndef _ASM_X86_FRAME_H
+#define _ASM_X86_FRAME_H
 
 #include <asm/asm.h>
 
-/* The annotation hides the frame from the unwinder and makes it look
-   like a ordinary ebp save/restore. This avoids some special cases for
-   frame pointer later */
+/*
+ * These are stack frame creation macros.  They should be used by every
+ * callable non-leaf asm function to make kernel stack traces more reliable.
+ */
+
 #ifdef CONFIG_FRAME_POINTER
-	.macro FRAME
-	__ASM_SIZE(push,)	%__ASM_REG(bp)
-	__ASM_SIZE(mov)		%__ASM_REG(sp), %__ASM_REG(bp)
-	.endm
-	.macro ENDFRAME
-	__ASM_SIZE(pop,)	%__ASM_REG(bp)
-	.endm
-#else
-	.macro FRAME
-	.endm
-	.macro ENDFRAME
-	.endm
-#endif
+
+#ifdef __ASSEMBLY__
+
+.macro FRAME_BEGIN
+	push %_ASM_BP
+	_ASM_MOV %_ASM_SP, %_ASM_BP
+.endm
+
+.macro FRAME_END
+	pop %_ASM_BP
+.endm
+
+#else /* !__ASSEMBLY__ */
+
+#define FRAME_BEGIN				\
+	"push %" _ASM_BP "\n"			\
+	_ASM_MOV "%" _ASM_SP ", %" _ASM_BP "\n"
+
+#define FRAME_END "pop %" _ASM_BP "\n"
 
 #endif /* __ASSEMBLY__ */
+
+#define FRAME_OFFSET __ASM_SEL(4, 8)
+
+#else /* !CONFIG_FRAME_POINTER */
+
+#define FRAME_BEGIN
+#define FRAME_END
+#define FRAME_OFFSET 0
+
+#endif /* CONFIG_FRAME_POINTER */
+
+#endif /* _ASM_X86_FRAME_H */

arch/x86/include/asm/irq_work.h

 #ifndef _ASM_IRQ_WORK_H
 #define _ASM_IRQ_WORK_H
 
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 
 static inline bool arch_irq_work_has_interrupt(void)
 {

arch/x86/include/asm/mmu.h

@@ -19,7 +19,8 @@ typedef struct {
 #endif
 
 	struct mutex lock;
-	void __user *vdso;
+	void __user *vdso;			/* vdso base address */
+	const struct vdso_image *vdso_image;	/* vdso image in use */
 
 	atomic_t perf_rdpmc_allowed;	/* nonzero if rdpmc is allowed */
 } mm_context_t;

arch/x86/include/asm/mwait.h

@@ -3,6 +3,8 @@
 
 #include <linux/sched.h>
 
+#include <asm/cpufeature.h>
+
 #define MWAIT_SUBSTATE_MASK		0xf
 #define MWAIT_CSTATE_MASK		0xf
 #define MWAIT_SUBSTATE_SIZE		4

arch/x86/include/asm/processor.h

@@ -13,7 +13,7 @@ struct vm86;
 #include <asm/types.h>
 #include <uapi/asm/sigcontext.h>
 #include <asm/current.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/page.h>
 #include <asm/pgtable_types.h>
 #include <asm/percpu.h>
@@ -24,7 +24,6 @@ struct vm86;
 #include <asm/fpu/types.h>
 
 #include <linux/personality.h>
-#include <linux/cpumask.h>
 #include <linux/cache.h>
 #include <linux/threads.h>
 #include <linux/math64.h>

arch/x86/include/asm/smap.h

@@ -15,7 +15,7 @@
 
 #include <linux/stringify.h>
 #include <asm/nops.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 
 /* "Raw" instruction opcodes */
 #define __ASM_CLAC	.byte 0x0f,0x01,0xca

arch/x86/include/asm/smp.h

@@ -16,7 +16,6 @@
 #endif
 #include <asm/thread_info.h>
 #include <asm/cpumask.h>
-#include <asm/cpufeature.h>
 
 extern int smp_num_siblings;
 extern unsigned int num_processors;

arch/x86/include/asm/thread_info.h

@@ -49,7 +49,7 @@
  */
 #ifndef __ASSEMBLY__
 struct task_struct;
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <linux/atomic.h>
 
 struct thread_info {

arch/x86/include/asm/tlbflush.h

@@ -5,8 +5,57 @@
 #include <linux/sched.h>
 
 #include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <asm/special_insns.h>
 
+static inline void __invpcid(unsigned long pcid, unsigned long addr,
+			     unsigned long type)
+{
+	struct { u64 d[2]; } desc = { { pcid, addr } };
+
+	/*
+	 * The memory clobber is because the whole point is to invalidate
+	 * stale TLB entries and, especially if we're flushing global
+	 * mappings, we don't want the compiler to reorder any subsequent
+	 * memory accesses before the TLB flush.
+	 *
+	 * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and
+	 * invpcid (%rcx), %rax in long mode.
+	 */
+	asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01"
+		      : : "m" (desc), "a" (type), "c" (&desc) : "memory");
+}
+
+#define INVPCID_TYPE_INDIV_ADDR		0
+#define INVPCID_TYPE_SINGLE_CTXT	1
+#define INVPCID_TYPE_ALL_INCL_GLOBAL	2
+#define INVPCID_TYPE_ALL_NON_GLOBAL	3
+
+/* Flush all mappings for a given pcid and addr, not including globals. */
+static inline void invpcid_flush_one(unsigned long pcid,
+				     unsigned long addr)
+{
+	__invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR);
+}
+
+/* Flush all mappings for a given PCID, not including globals. */
+static inline void invpcid_flush_single_context(unsigned long pcid)
+{
+	__invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT);
+}
+
+/* Flush all mappings, including globals, for all PCIDs. */
+static inline void invpcid_flush_all(void)
+{
+	__invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL);
+}
+
+/* Flush all mappings for all PCIDs except globals. */
+static inline void invpcid_flush_all_nonglobals(void)
+{
+	__invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL);
+}
+
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else
@@ -104,6 +153,15 @@ static inline void __native_flush_tlb_global(void)
 {
 	unsigned long flags;
 
+	if (static_cpu_has(X86_FEATURE_INVPCID)) {
+		/*
+		 * Using INVPCID is considerably faster than a pair of writes
+		 * to CR4 sandwiched inside an IRQ flag save/restore.
+		 */
+		invpcid_flush_all();
+		return;
+	}
+
 	/*
 	 * Read-modify-write to CR4 - protect it from preemption and
 	 * from interrupts. (Use the raw variant because this code can

arch/x86/include/asm/uaccess_64.h

@@ -8,7 +8,7 @@
 #include <linux/errno.h>
 #include <linux/lockdep.h>
 #include <asm/alternative.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/page.h>
 
 /*

arch/x86/include/asm/vdso.h

@@ -13,9 +13,6 @@ struct vdso_image {
 	void *data;
 	unsigned long size;   /* Always a multiple of PAGE_SIZE */
 
-	/* text_mapping.pages is big enough for data/size page pointers */
-	struct vm_special_mapping text_mapping;
-
 	unsigned long alt, alt_len;
 
 	long sym_vvar_start;  /* Negative offset to the vvar area */

arch/x86/include/asm/vgtod.h

@@ -37,6 +37,12 @@ struct vsyscall_gtod_data {
 };
 extern struct vsyscall_gtod_data vsyscall_gtod_data;
 
+extern int vclocks_used;
+static inline bool vclock_was_used(int vclock)
+{
+	return READ_ONCE(vclocks_used) & (1 << vclock);
+}
+
 static inline unsigned gtod_read_begin(const struct vsyscall_gtod_data *s)
 {
 	unsigned ret;

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;
 	}

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>
 };

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>
 };

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

arch/x86/kernel/cpu/centaur.c

 #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>

arch/x86/kernel/cpu/common.c

@@ -162,6 +162,22 @@ static int __init x86_mpx_setup(char *s)
 }
 __setup("nompx", x86_mpx_setup);
 
+static int __init x86_noinvpcid_setup(char *s)
+{
+	/* noinvpcid doesn't accept parameters */
+	if (s)
+		return -EINVAL;
+
+	/* do not emit a message if the feature is not present */
+	if (!boot_cpu_has(X86_FEATURE_INVPCID))
+		return 0;
+
+	setup_clear_cpu_cap(X86_FEATURE_INVPCID);
+	pr_info("noinvpcid: INVPCID feature disabled\n");
+	return 0;
+}
+early_param("noinvpcid", x86_noinvpcid_setup);
+
 #ifdef CONFIG_X86_32
 static int cachesize_override = -1;
 static int disable_x86_serial_nr = 1;
@@ -1475,20 +1491,6 @@ 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)

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"
 

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>

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>
 

arch/x86/kernel/cpu/match.c

 #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>

arch/x86/kernel/cpu/mkcapflags.sh

 #!/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 ""
 

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>

arch/x86/kernel/cpu/transmeta.c

 #include <linux/kernel.h>
 #include <linux/mm.h>
-#include <asm/processor.h>
+#include <asm/cpufeature.h>
 #include <asm/msr.h>
 #include "cpu.h"
 

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

arch/x86/kernel/fpu/core.c

@@ -114,6 +114,10 @@ void __kernel_fpu_begin(void)
 	kernel_fpu_disable();
 
 	if (fpu->fpregs_active) {
+		/*
+		 * Ignore return value -- we don't care if reg state
+		 * is clobbered.
+		 */
 		copy_fpregs_to_fpstate(fpu);
 	} else {
 		this_cpu_write(fpu_fpregs_owner_ctx, NULL);
@@ -189,9 +193,13 @@ void fpu__save(struct fpu *fpu)
 
 	preempt_disable();
 	if (fpu->fpregs_active) {
-		if (!copy_fpregs_to_fpstate(fpu))
+		if (!copy_fpregs_to_fpstate(fpu)) {
+			if (use_eager_fpu())
+				copy_kernel_to_fpregs(&fpu->state);
+			else
 				fpregs_deactivate(fpu);
 		}
+	}
 	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(fpu__save);
@@ -223,14 +231,15 @@ void fpstate_init(union fpregs_state *state)
 }
 EXPORT_SYMBOL_GPL(fpstate_init);
 
-/*
- * Copy the current task's FPU state to a new task's FPU context.
- *
- * In both the 'eager' and the 'lazy' case we save hardware registers
- * directly to the destination buffer.
- */
-static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu)
+int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 {
+	dst_fpu->counter = 0;
+	dst_fpu->fpregs_active = 0;
+	dst_fpu->last_cpu = -1;
+
+	if (!src_fpu->fpstate_active || !cpu_has_fpu)
+		return 0;
+
 	WARN_ON_FPU(src_fpu != &current->thread.fpu);
 
 	/*
@@ -243,10 +252,9 @@ static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 	/*
 	 * Save current FPU registers directly into the child
 	 * FPU context, without any memory-to-memory copying.
-	 *
-	 * If the FPU context got destroyed in the process (FNSAVE
-	 * done on old CPUs) then copy it back into the source
-	 * context and mark the current task for lazy restore.
+	 * In lazy mode, if the FPU context isn't loaded into
+	 * fpregs, CR0.TS will be set and do_device_not_available
+	 * will load the FPU context.
 	 *
 	 * We have to do all this with preemption disabled,
 	 * mostly because of the FNSAVE case, because in that
@@ -259,19 +267,13 @@ static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 	preempt_disable();
 	if (!copy_fpregs_to_fpstate(dst_fpu)) {
 		memcpy(&src_fpu->state, &dst_fpu->state, xstate_size);
+
+		if (use_eager_fpu())
+			copy_kernel_to_fpregs(&src_fpu->state);
+		else
 			fpregs_deactivate(src_fpu);
 	}
 	preempt_enable();
-}
-
-int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
-{
-	dst_fpu->counter = 0;
-	dst_fpu->fpregs_active = 0;
-	dst_fpu->last_cpu = -1;
-
-	if (src_fpu->fpstate_active && cpu_has_fpu)
-		fpu_copy(dst_fpu, src_fpu);
 
 	return 0;
 }
@@ -423,7 +425,7 @@ void fpu__clear(struct fpu *fpu)
 {
 	WARN_ON_FPU(fpu != &current->thread.fpu); /* Almost certainly an anomaly */
 
-	if (!use_eager_fpu()) {
+	if (!use_eager_fpu() || !static_cpu_has(X86_FEATURE_FPU)) {
 		/* FPU state will be reallocated lazily at the first use. */
 		fpu__drop(fpu);
 	} else {

arch/x86/kernel/fpu/init.c

@@ -260,7 +260,10 @@ static void __init fpu__init_system_xstate_size_legacy(void)
  * not only saved the restores along the way, but we also have the
  * FPU ready to be used for the original task.
  *
- * 'eager' switching is used on modern CPUs, there we switch the FPU
+ * 'lazy' is deprecated because it's almost never a performance win
+ * and it's much more complicated than 'eager'.
+ *
+ * 'eager' switching is by default on all CPUs, there we switch the FPU
  * state during every context switch, regardless of whether the task
  * has used FPU instructions in that time slice or not. This is done
  * because modern FPU context saving instructions are able to optimize
@@ -271,7 +274,7 @@ static void __init fpu__init_system_xstate_size_legacy(void)
  *   to use 'eager' restores, if we detect that a task is using the FPU
  *   frequently. See the fpu->counter logic in fpu/internal.h for that. ]
  */
-static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO;
+static enum { ENABLE, DISABLE } eagerfpu = ENABLE;
 
 /*
  * Find supported xfeatures based on cpu features and command-line input.
@@ -348,15 +351,9 @@ static void __init fpu__init_system_ctx_switch(void)
  */
 static void __init fpu__init_parse_early_param(void)
 {
-	/*
-	 * No need to check "eagerfpu=auto" again, since it is the
-	 * initial default.
-	 */
 	if (cmdline_find_option_bool(boot_command_line, "eagerfpu=off")) {
 		eagerfpu = DISABLE;
 		fpu__clear_eager_fpu_features();
-	} else if (cmdline_find_option_bool(boot_command_line, "eagerfpu=on")) {
-		eagerfpu = ENABLE;
 	}
 
 	if (cmdline_find_option_bool(boot_command_line, "no387"))

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>
@@ -389,6 +389,12 @@ default_entry:
 	/* Make changes effective */
 	wrmsr
 
+	/*
+	 * And make sure that all the mappings we set up have NX set from
+	 * the beginning.
+	 */
+	orl $(1 << (_PAGE_BIT_NX - 32)), pa(__supported_pte_mask + 4)
+
 enable_paging:
 
 /*

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)
 

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>

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;

arch/x86/kernel/signal.c

@@ -692,12 +692,15 @@ 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
 }
 
 /*

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)) {
@@ -743,20 +734,19 @@ 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
 do_device_not_available(struct pt_regs *regs, long error_code)
 {
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
-	BUG_ON(use_eager_fpu());
 
 #ifdef CONFIG_MATH_EMULATION
-	if (read_cr0() & X86_CR0_EM) {
+	if (!boot_cpu_has(X86_FEATURE_FPU) && (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 +755,7 @@ 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);

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:

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);

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) {

arch/x86/lib/clear_page_64.S

 #include <linux/linkage.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 
 /*

arch/x86/lib/copy_page_64.S

 /* Written 2003 by Andi Kleen, based on a kernel by Evandro Menezes */
 
 #include <linux/linkage.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 
 /*

arch/x86/lib/copy_user_64.S

@@ -10,7 +10,7 @@
 #include <asm/current.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 #include <asm/asm.h>
 #include <asm/smap.h>

arch/x86/lib/memcpy_64.S

 /* Copyright 2002 Andi Kleen */
 
 #include <linux/linkage.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 
 /*

arch/x86/lib/memmove_64.S

@@ -6,7 +6,7 @@
  *	- Copyright 2011 Fenghua Yu <fenghua.yu@intel.com>
  */
 #include <linux/linkage.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 
 #undef memmove

arch/x86/lib/memset_64.S

 /* Copyright 2002 Andi Kleen, SuSE Labs */
 
 #include <linux/linkage.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 
 .weak memset

arch/x86/mm/init_32.c

@@ -388,7 +388,6 @@ kernel_physical_mapping_init(unsigned long start,
 }
 
 pte_t *kmap_pte;
-pgprot_t kmap_prot;
 
 static inline pte_t *kmap_get_fixmap_pte(unsigned long vaddr)
 {
@@ -405,8 +404,6 @@ static void __init kmap_init(void)
 	 */
 	kmap_vstart = __fix_to_virt(FIX_KMAP_BEGIN);
 	kmap_pte = kmap_get_fixmap_pte(kmap_vstart);
-
-	kmap_prot = PAGE_KERNEL;
 }
 
 #ifdef CONFIG_HIGHMEM

arch/x86/mm/init_64.c

@@ -53,6 +53,7 @@
 #include <asm/numa.h>
 #include <asm/cacheflush.h>
 #include <asm/init.h>
+#include <asm/uv/uv.h>
 #include <asm/setup.h>
 
 #include "mm_internal.h"
@@ -1206,26 +1207,13 @@ int kern_addr_valid(unsigned long addr)
 
 static unsigned long probe_memory_block_size(void)
 {
-	/* start from 2g */
-	unsigned long bz = 1UL<<31;
+	unsigned long bz = MIN_MEMORY_BLOCK_SIZE;
 
-	if (totalram_pages >= (64ULL << (30 - PAGE_SHIFT))) {
-		pr_info("Using 2GB memory block size for large-memory system\n");
-		return 2UL * 1024 * 1024 * 1024;
-	}
-
-	/* less than 64g installed */
-	if ((max_pfn << PAGE_SHIFT) < (16UL << 32))
-		return MIN_MEMORY_BLOCK_SIZE;
-
-	/* get the tail size */
-	while (bz > MIN_MEMORY_BLOCK_SIZE) {
-		if (!((max_pfn << PAGE_SHIFT) & (bz - 1)))
-			break;
-		bz >>= 1;
-	}
+	/* if system is UV or has 64GB of RAM or more, use large blocks */
+	if (is_uv_system() || ((max_pfn << PAGE_SHIFT) >= (64UL << 30)))
+		bz = 2UL << 30; /* 2GB */
 
-	printk(KERN_DEBUG "memory block size : %ldMB\n", bz >> 20);
+	pr_info("x86/mm: Memory block size: %ldMB\n", bz >> 20);
 
 	return bz;
 }

arch/x86/mm/kasan_init_64.c

@@ -120,11 +120,22 @@ void __init kasan_init(void)
 	kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END),
 			(void *)KASAN_SHADOW_END);
 
-	memset(kasan_zero_page, 0, PAGE_SIZE);
-
 	load_cr3(init_level4_pgt);
 	__flush_tlb_all();
-	init_task.kasan_depth = 0;
 
+	/*
+	 * kasan_zero_page has been used as early shadow memory, thus it may
+	 * contain some garbage. Now we can clear and write protect it, since
+	 * after the TLB flush no one should write to it.
+	 */
+	memset(kasan_zero_page, 0, PAGE_SIZE);
+	for (i = 0; i < PTRS_PER_PTE; i++) {
+		pte_t pte = __pte(__pa(kasan_zero_page) | __PAGE_KERNEL_RO);
+		set_pte(&kasan_zero_pte[i], pte);
+	}
+	/* Flush TLBs again to be sure that write protection applied. */
+	__flush_tlb_all();
+
+	init_task.kasan_depth = 0;
 	pr_info("KernelAddressSanitizer initialized\n");
 }

arch/x86/mm/numa.c

@@ -465,46 +465,67 @@ static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi)
 	return true;
 }
 
+/*
+ * Mark all currently memblock-reserved physical memory (which covers the
+ * kernel's own memory ranges) as hot-unswappable.
+ */
 static void __init numa_clear_kernel_node_hotplug(void)
 {
-	int i, nid;
-	nodemask_t numa_kernel_nodes = NODE_MASK_NONE;
-	phys_addr_t start, end;
-	struct memblock_region *r;
+	nodemask_t reserved_nodemask = NODE_MASK_NONE;
+	struct memblock_region *mb_region;
+	int i;
 
 	/*
+	 * We have to do some preprocessing of memblock regions, to
+	 * make them suitable for reservation.
+	 *
 	 * At this time, all memory regions reserved by memblock are
-	 * used by the kernel. Set the nid in memblock.reserved will
-	 * mark out all the nodes the kernel resides in.
+	 * used by the kernel, but those regions are not split up
+	 * along node boundaries yet, and don't necessarily have their
+	 * node ID set yet either.
+	 *
+	 * So iterate over all memory known to the x86 architecture,
+	 * and use those ranges to set the nid in memblock.reserved.
+	 * This will split up the memblock regions along node
+	 * boundaries and will set the node IDs as well.
 	 */
 	for (i = 0; i < numa_meminfo.nr_blks; i++) {
-		struct numa_memblk *mb = &numa_meminfo.blk[i];
+		struct numa_memblk *mb = numa_meminfo.blk + i;
+		int ret;
 
-		memblock_set_node(mb->start, mb->end - mb->start,
-				  &memblock.reserved, mb->nid);
+		ret = memblock_set_node(mb->start, mb->end - mb->start, &memblock.reserved, mb->nid);
+		WARN_ON_ONCE(ret);
 	}
 
 	/*
-	 * Mark all kernel nodes.
+	 * Now go over all reserved memblock regions, to construct a
+	 * node mask of all kernel reserved memory areas.
 	 *
-	 * When booting with mem=nn[kMG] or in a kdump kernel, numa_meminfo
-	 * may not include all the memblock.reserved memory ranges because
-	 * trim_snb_memory() reserves specific pages for Sandy Bridge graphics.
+	 * [ Note, when booting with mem=nn[kMG] or in a kdump kernel,
+	 *   numa_meminfo might not include all memblock.reserved
+	 *   memory ranges, because quirks such as trim_snb_memory()
+	 *   reserve specific pages for Sandy Bridge graphics. ]
 	 */
-	for_each_memblock(reserved, r)
-		if (r->nid != MAX_NUMNODES)
-			node_set(r->nid, numa_kernel_nodes);
+	for_each_memblock(reserved, mb_region) {
+		if (mb_region->nid != MAX_NUMNODES)
+			node_set(mb_region->nid, reserved_nodemask);
+	}
 
-	/* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */
+	/*
+	 * Finally, clear the MEMBLOCK_HOTPLUG flag for all memory
+	 * belonging to the reserved node mask.
+	 *
+	 * Note that this will include memory regions that reside
+	 * on nodes that contain kernel memory - entire nodes
+	 * become hot-unpluggable:
+	 */
 	for (i = 0; i < numa_meminfo.nr_blks; i++) {
-		nid = numa_meminfo.blk[i].nid;
-		if (!node_isset(nid, numa_kernel_nodes))
-			continue;
+		struct numa_memblk *mb = numa_meminfo.blk + i;
 
-		start = numa_meminfo.blk[i].start;
-		end = numa_meminfo.blk[i].end;
+		if (!node_isset(mb->nid, reserved_nodemask))
+			continue;
 
-		memblock_clear_hotplug(start, end - start);
+		memblock_clear_hotplug(mb->start, mb->end - mb->start);
 	}
 }
 

arch/x86/mm/pat.c

@@ -943,7 +943,7 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
 			return -EINVAL;
 	}
 
-	*prot = __pgprot((pgprot_val(vma->vm_page_prot) & (~_PAGE_CACHE_MASK)) |
+	*prot = __pgprot((pgprot_val(*prot) & (~_PAGE_CACHE_MASK)) |
 			 cachemode2protval(pcm));
 
 	return 0;
@@ -959,7 +959,7 @@ int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
 
 	/* Set prot based on lookup */
 	pcm = lookup_memtype(pfn_t_to_phys(pfn));
-	*prot = __pgprot((pgprot_val(vma->vm_page_prot) & (~_PAGE_CACHE_MASK)) |
+	*prot = __pgprot((pgprot_val(*prot) & (~_PAGE_CACHE_MASK)) |
 			 cachemode2protval(pcm));
 
 	return 0;

arch/x86/mm/setup_nx.c

@@ -4,6 +4,7 @@
 
 #include <asm/pgtable.h>
 #include <asm/proto.h>
+#include <asm/cpufeature.h>
 
 static int disable_nx;
 
@@ -31,9 +32,8 @@ early_param("noexec", noexec_setup);
 
 void x86_configure_nx(void)
 {
-	if (boot_cpu_has(X86_FEATURE_NX) && !disable_nx)
-		__supported_pte_mask |= _PAGE_NX;
-	else
+	/* If disable_nx is set, clear NX on all new mappings going forward. */
+	if (disable_nx)
 		__supported_pte_mask &= ~_PAGE_NX;
 }
 

arch/x86/oprofile/op_model_amd.c

@@ -24,7 +24,6 @@
 #include <asm/nmi.h>
 #include <asm/apic.h>
 #include <asm/processor.h>
-#include <asm/cpufeature.h>
 
 #include "op_x86_model.h"
 #include "op_counter.h"

arch/x86/um/asm/barrier.h

@@ -3,7 +3,7 @@
 
 #include <asm/asm.h>
 #include <asm/segment.h>
-#include <asm/cpufeature.h>
+#include <asm/cpufeatures.h>
 #include <asm/cmpxchg.h>
 #include <asm/nops.h>
 

arch/x86/um/sys_call_table_32.c

@@ -25,11 +25,11 @@
 
 #define old_mmap sys_old_mmap
 
-#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ;
+#define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ;
 #include <asm/syscalls_32.h>
 
 #undef __SYSCALL_I386
-#define __SYSCALL_I386(nr, sym, compat) [ nr ] = sym,
+#define __SYSCALL_I386(nr, sym, qual) [ nr ] = sym,
 
 extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
 

arch/x86/um/sys_call_table_64.c

@@ -35,14 +35,11 @@
 #define stub_execveat sys_execveat
 #define stub_rt_sigreturn sys_rt_sigreturn
 
-#define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
-#define __SYSCALL_X32(nr, sym, compat) /* Not supported */
-
-#define __SYSCALL_64(nr, sym, compat) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ;
+#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ;
 #include <asm/syscalls_64.h>
 
 #undef __SYSCALL_64
-#define __SYSCALL_64(nr, sym, compat) [ nr ] = sym,
+#define __SYSCALL_64(nr, sym, qual) [ nr ] = sym,
 
 extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
 

arch/x86/um/user-offsets.c

@@ -9,14 +9,12 @@
 #include <asm/types.h>
 
 #ifdef __i386__
-#define __SYSCALL_I386(nr, sym, compat) [nr] = 1,
+#define __SYSCALL_I386(nr, sym, qual) [nr] = 1,
 static char syscalls[] = {
 #include <asm/syscalls_32.h>
 };
 #else
-#define __SYSCALL_64(nr, sym, compat) [nr] = 1,
-#define __SYSCALL_COMMON(nr, sym, compat) [nr] = 1,
-#define __SYSCALL_X32(nr, sym, compat) /* Not supported */
+#define __SYSCALL_64(nr, sym, qual) [nr] = 1,
 static char syscalls[] = {
 #include <asm/syscalls_64.h>
 };

drivers/cpufreq/intel_pstate.c

@@ -1431,7 +1431,7 @@ static int __init intel_pstate_init(void)
 	if (!all_cpu_data)
 		return -ENOMEM;
 
-	if (static_cpu_has_safe(X86_FEATURE_HWP) && !no_hwp) {
+	if (static_cpu_has(X86_FEATURE_HWP) && !no_hwp) {
 		pr_info("intel_pstate: HWP enabled\n");
 		hwp_active++;
 	}

fs/btrfs/disk-io.c

@@ -931,7 +931,7 @@ static int check_async_write(struct inode *inode, unsigned long bio_flags)
 	if (bio_flags & EXTENT_BIO_TREE_LOG)
 		return 0;
 #ifdef CONFIG_X86
-	if (static_cpu_has_safe(X86_FEATURE_XMM4_2))
+	if (static_cpu_has(X86_FEATURE_XMM4_2))
 		return 0;
 #endif
 	return 1;

include/linux/mm.h

@@ -2138,6 +2138,8 @@ int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
 int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
 int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn);
+int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
+			unsigned long pfn, pgprot_t pgprot);
 int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
 			pfn_t pfn);
 int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len);

include/linux/mm_types.h

@@ -566,10 +566,26 @@ static inline void clear_tlb_flush_pending(struct mm_struct *mm)
 }
 #endif
 
-struct vm_special_mapping
-{
-	const char *name;
+struct vm_fault;
+
+struct vm_special_mapping {
+	const char *name;	/* The name, e.g. "[vdso]". */
+
+	/*
+	 * If .fault is not provided, this points to a
+	 * NULL-terminated array of pages that back the special mapping.
+	 *
+	 * This must not be NULL unless .fault is provided.
+	 */
 	struct page **pages;
+
+	/*
+	 * If non-NULL, then this is called to resolve page faults
+	 * on the special mapping.  If used, .pages is not checked.
+	 */
+	int (*fault)(const struct vm_special_mapping *sm,
+		     struct vm_area_struct *vma,
+		     struct vm_fault *vmf);
 };
 
 enum tlb_flush_reason {

lib/atomic64_test.c

@@ -17,7 +17,7 @@
 #include <linux/atomic.h>
 
 #ifdef CONFIG_X86
-#include <asm/processor.h>	/* for boot_cpu_has below */
+#include <asm/cpufeature.h>	/* for boot_cpu_has below */
 #endif
 
 #define TEST(bit, op, c_op, val)				\

mm/memory.c

@@ -1550,9 +1550,30 @@ static int insert_pfn(struct vm_area_struct *vma, unsigned long addr,
  */
 int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn)
+{
+	return vm_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot);
+}
+EXPORT_SYMBOL(vm_insert_pfn);
+
+/**
+ * vm_insert_pfn_prot - insert single pfn into user vma with specified pgprot
+ * @vma: user vma to map to
+ * @addr: target user address of this page
+ * @pfn: source kernel pfn
+ * @pgprot: pgprot flags for the inserted page
+ *
+ * This is exactly like vm_insert_pfn, except that it allows drivers to
+ * to override pgprot on a per-page basis.
+ *
+ * This only makes sense for IO mappings, and it makes no sense for
+ * cow mappings.  In general, using multiple vmas is preferable;
+ * vm_insert_pfn_prot should only be used if using multiple VMAs is
+ * impractical.
+ */
+int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
+			unsigned long pfn, pgprot_t pgprot)
 {
 	int ret;
-	pgprot_t pgprot = vma->vm_page_prot;
 	/*
 	 * Technically, architectures with pte_special can avoid all these
 	 * restrictions (same for remap_pfn_range).  However we would like
@@ -1574,7 +1595,7 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 
 	return ret;
 }
-EXPORT_SYMBOL(vm_insert_pfn);
+EXPORT_SYMBOL(vm_insert_pfn_prot);
 
 int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
 			pfn_t pfn)

mm/mmap.c

@@ -3042,11 +3042,16 @@ static int special_mapping_fault(struct vm_area_struct *vma,
 	pgoff_t pgoff;
 	struct page **pages;
 
-	if (vma->vm_ops == &legacy_special_mapping_vmops)
+	if (vma->vm_ops == &legacy_special_mapping_vmops) {
 		pages = vma->vm_private_data;
-	else
-		pages = ((struct vm_special_mapping *)vma->vm_private_data)->
-			pages;
+	} else {
+		struct vm_special_mapping *sm = vma->vm_private_data;
+
+		if (sm->fault)
+			return sm->fault(sm, vma, vmf);
+
+		pages = sm->pages;
+	}
 
 	for (pgoff = vmf->pgoff; pgoff && *pages; ++pages)
 		pgoff--;

tools/testing/selftests/x86/Makefile

@@ -4,15 +4,17 @@ include ../lib.mk
 
 .PHONY: all all_32 all_64 warn_32bit_failure clean
 
-TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall
+TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall \
+			check_initial_reg_state
 TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault sigreturn test_syscall_vdso unwind_vdso \
 			test_FCMOV test_FCOMI test_FISTTP \
 			ldt_gdt \
 			vdso_restorer
 
 TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY)
+TARGETS_C_64BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_64BIT_ONLY)
 BINARIES_32 := $(TARGETS_C_32BIT_ALL:%=%_32)
-BINARIES_64 := $(TARGETS_C_BOTHBITS:%=%_64)
+BINARIES_64 := $(TARGETS_C_64BIT_ALL:%=%_64)
 
 CFLAGS := -O2 -g -std=gnu99 -pthread -Wall
 
@@ -40,7 +42,7 @@ clean:
 $(TARGETS_C_32BIT_ALL:%=%_32): %_32: %.c
 	$(CC) -m32 -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl -lm
 
-$(TARGETS_C_BOTHBITS:%=%_64): %_64: %.c
+$(TARGETS_C_64BIT_ALL:%=%_64): %_64: %.c
 	$(CC) -m64 -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl
 
 # x86_64 users should be encouraged to install 32-bit libraries
@@ -65,3 +67,9 @@ endif
 sysret_ss_attrs_64: thunks.S
 ptrace_syscall_32: raw_syscall_helper_32.S
 test_syscall_vdso_32: thunks_32.S
+
+# check_initial_reg_state is special: it needs a custom entry, and it
+# needs to be static so that its interpreter doesn't destroy its initial
+# state.
+check_initial_reg_state_32: CFLAGS += -Wl,-ereal_start -static
+check_initial_reg_state_64: CFLAGS += -Wl,-ereal_start -static

tools/testing/selftests/x86/check_initial_reg_state.c

+/*
+ * check_initial_reg_state.c - check that execve sets the correct state
+ * Copyright (c) 2014-2016 Andrew Lutomirski
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#define _GNU_SOURCE
+
+#include <stdio.h>
+
+unsigned long ax, bx, cx, dx, si, di, bp, sp, flags;
+unsigned long r8, r9, r10, r11, r12, r13, r14, r15;
+
+asm (
+	".pushsection .text\n\t"
+	".type real_start, @function\n\t"
+	".global real_start\n\t"
+	"real_start:\n\t"
+#ifdef __x86_64__
+	"mov %rax, ax\n\t"
+	"mov %rbx, bx\n\t"
+	"mov %rcx, cx\n\t"
+	"mov %rdx, dx\n\t"
+	"mov %rsi, si\n\t"
+	"mov %rdi, di\n\t"
+	"mov %rbp, bp\n\t"
+	"mov %rsp, sp\n\t"
+	"mov %r8, r8\n\t"
+	"mov %r9, r9\n\t"
+	"mov %r10, r10\n\t"
+	"mov %r11, r11\n\t"
+	"mov %r12, r12\n\t"
+	"mov %r13, r13\n\t"
+	"mov %r14, r14\n\t"
+	"mov %r15, r15\n\t"
+	"pushfq\n\t"
+	"popq flags\n\t"
+#else
+	"mov %eax, ax\n\t"
+	"mov %ebx, bx\n\t"
+	"mov %ecx, cx\n\t"
+	"mov %edx, dx\n\t"
+	"mov %esi, si\n\t"
+	"mov %edi, di\n\t"
+	"mov %ebp, bp\n\t"
+	"mov %esp, sp\n\t"
+	"pushfl\n\t"
+	"popl flags\n\t"
+#endif
+	"jmp _start\n\t"
+	".size real_start, . - real_start\n\t"
+	".popsection");
+
+int main()
+{
+	int nerrs = 0;
+
+	if (sp == 0) {
+		printf("[FAIL]\tTest was built incorrectly\n");
+		return 1;
+	}
+
+	if (ax || bx || cx || dx || si || di || bp
+#ifdef __x86_64__
+	    || r8 || r9 || r10 || r11 || r12 || r13 || r14 || r15
+#endif
+		) {
+		printf("[FAIL]\tAll GPRs except SP should be 0\n");
+#define SHOW(x) printf("\t" #x " = 0x%lx\n", x);
+		SHOW(ax);
+		SHOW(bx);
+		SHOW(cx);
+		SHOW(dx);
+		SHOW(si);
+		SHOW(di);
+		SHOW(bp);
+		SHOW(sp);
+#ifdef __x86_64__
+		SHOW(r8);
+		SHOW(r9);
+		SHOW(r10);
+		SHOW(r11);
+		SHOW(r12);
+		SHOW(r13);
+		SHOW(r14);
+		SHOW(r15);
+#endif
+		nerrs++;
+	} else {
+		printf("[OK]\tAll GPRs except SP are 0\n");
+	}
+
+	if (flags != 0x202) {
+		printf("[FAIL]\tFLAGS is 0x%lx, but it should be 0x202\n", flags);
+		nerrs++;
+	} else {
+		printf("[OK]\tFLAGS is 0x202\n");
+	}
+
+	return nerrs ? 1 : 0;
+}