Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 asm updates from Ingo Molnar:
 "This includes the following changes:

   - cpu_has() cleanups

   - sync_bitops.h modernization to the rmwcc.h facility, similarly to
     bitops.h

   - continued LTO annotations/fixes

   - misc cleanups and smaller cleanups"

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/um/vdso: Drop unnecessary cc-ldoption
  x86/vdso: Rename variable to fix -Wshadow warning
  x86/cpu/amd: Exclude 32bit only assembler from 64bit build
  x86/asm: Mark all top level asm statements as .text
  x86/build/vdso: Add FORCE to the build rule of %.so
  x86/asm: Modernize sync_bitops.h
  x86/mm: Convert some slow-path static_cpu_has() callers to boot_cpu_has()
  x86: Convert some slow-path static_cpu_has() callers to boot_cpu_has()
  x86/asm: Clarify static_cpu_has()'s intended use
  x86/uaccess: Fix implicit cast of __user pointer
  x86/cpufeature: Remove __pure attribute to _static_cpu_has()

arch/x86/entry/vdso/Makefile

@@ -116,7 +116,7 @@ $(obj)/%-x32.o: $(obj)/%.o FORCE
 targets += vdsox32.lds $(vobjx32s-y)
 
 $(obj)/%.so: OBJCOPYFLAGS := -S
-$(obj)/%.so: $(obj)/%.so.dbg
+$(obj)/%.so: $(obj)/%.so.dbg FORCE
 	$(call if_changed,objcopy)
 
 $(obj)/vdsox32.so.dbg: $(obj)/vdsox32.lds $(vobjx32s) FORCE

arch/x86/entry/vdso/vdso2c.h

@@ -7,7 +7,7 @@
 
 static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 			 void *stripped_addr, size_t stripped_len,
-			 FILE *outfile, const char *name)
+			 FILE *outfile, const char *image_name)
 {
 	int found_load = 0;
 	unsigned long load_size = -1;  /* Work around bogus warning */
@@ -93,11 +93,12 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 		int k;
 		ELF(Sym) *sym = raw_addr + GET_LE(&symtab_hdr->sh_offset) +
 			GET_LE(&symtab_hdr->sh_entsize) * i;
-		const char *name = raw_addr + GET_LE(&strtab_hdr->sh_offset) +
-			GET_LE(&sym->st_name);
+		const char *sym_name = raw_addr +
+				       GET_LE(&strtab_hdr->sh_offset) +
+				       GET_LE(&sym->st_name);
 
 		for (k = 0; k < NSYMS; k++) {
-			if (!strcmp(name, required_syms[k].name)) {
+			if (!strcmp(sym_name, required_syms[k].name)) {
 				if (syms[k]) {
 					fail("duplicate symbol %s\n",
 					     required_syms[k].name);
@@ -134,7 +135,7 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 	if (syms[sym_vvar_start] % 4096)
 		fail("vvar_begin must be a multiple of 4096\n");
 
-	if (!name) {
+	if (!image_name) {
 		fwrite(stripped_addr, stripped_len, 1, outfile);
 		return;
 	}
@@ -157,7 +158,7 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 	}
 	fprintf(outfile, "\n};\n\n");
 
-	fprintf(outfile, "const struct vdso_image %s = {\n", name);
+	fprintf(outfile, "const struct vdso_image %s = {\n", image_name);
 	fprintf(outfile, "\t.data = raw_data,\n");
 	fprintf(outfile, "\t.size = %lu,\n", mapping_size);
 	if (alt_sec) {

arch/x86/include/asm/cpufeature.h

@@ -156,11 +156,14 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
 #else
 
 /*
- * Static testing of CPU features.  Used the same as boot_cpu_has().
- * These will statically patch the target code for additional
- * performance.
+ * Static testing of CPU features. Used the same as boot_cpu_has(). It
+ * statically patches the target code for additional performance. Use
+ * static_cpu_has() only in fast paths, where every cycle counts. Which
+ * means that the boot_cpu_has() variant is already fast enough for the
+ * majority of cases and you should stick to using it as it is generally
+ * only two instructions: a RIP-relative MOV and a TEST.
  */
-static __always_inline __pure bool _static_cpu_has(u16 bit)
+static __always_inline bool _static_cpu_has(u16 bit)
 {
 	asm_volatile_goto("1: jmp 6f\n"
 		 "2:\n"

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

@@ -253,7 +253,7 @@ static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate)
 
 	WARN_ON(system_state != SYSTEM_BOOTING);
 
-	if (static_cpu_has(X86_FEATURE_XSAVES))
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
 		XSTATE_OP(XSAVES, xstate, lmask, hmask, err);
 	else
 		XSTATE_OP(XSAVE, xstate, lmask, hmask, err);
@@ -275,7 +275,7 @@ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate)
 
 	WARN_ON(system_state != SYSTEM_BOOTING);
 
-	if (static_cpu_has(X86_FEATURE_XSAVES))
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
 		XSTATE_OP(XRSTORS, xstate, lmask, hmask, err);
 	else
 		XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
@@ -497,8 +497,7 @@ static inline void fpregs_activate(struct fpu *fpu)
  *  - switch_fpu_finish() restores the new state as
  *    necessary.
  */
-static inline void
-switch_fpu_prepare(struct fpu *old_fpu, int cpu)
+static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu)
 {
 	if (static_cpu_has(X86_FEATURE_FPU) && old_fpu->initialized) {
 		if (!copy_fpregs_to_fpstate(old_fpu))

arch/x86/include/asm/sync_bitops.h

@@ -14,6 +14,8 @@
  * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1).
  */
 
+#include <asm/rmwcc.h>
+
 #define ADDR (*(volatile long *)addr)
 
 /**
@@ -29,7 +31,7 @@
  */
 static inline void sync_set_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("lock; bts %1,%0"
+	asm volatile("lock; " __ASM_SIZE(bts) " %1,%0"
 		     : "+m" (ADDR)
 		     : "Ir" (nr)
 		     : "memory");
@@ -47,7 +49,7 @@ static inline void sync_set_bit(long nr, volatile unsigned long *addr)
  */
 static inline void sync_clear_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("lock; btr %1,%0"
+	asm volatile("lock; " __ASM_SIZE(btr) " %1,%0"
 		     : "+m" (ADDR)
 		     : "Ir" (nr)
 		     : "memory");
@@ -64,7 +66,7 @@ static inline void sync_clear_bit(long nr, volatile unsigned long *addr)
  */
 static inline void sync_change_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("lock; btc %1,%0"
+	asm volatile("lock; " __ASM_SIZE(btc) " %1,%0"
 		     : "+m" (ADDR)
 		     : "Ir" (nr)
 		     : "memory");
@@ -78,14 +80,9 @@ static inline void sync_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 sync_test_and_set_bit(long nr, volatile unsigned long *addr)
+static inline bool sync_test_and_set_bit(long nr, volatile unsigned long *addr)
 {
-	unsigned char oldbit;
-
-	asm volatile("lock; bts %2,%1\n\tsetc %0"
-		     : "=qm" (oldbit), "+m" (ADDR)
-		     : "Ir" (nr) : "memory");
-	return oldbit;
+	return GEN_BINARY_RMWcc("lock; " __ASM_SIZE(bts), *addr, c, "Ir", nr);
 }
 
 /**
@@ -98,12 +95,7 @@ static inline int sync_test_and_set_bit(long nr, volatile unsigned long *addr)
  */
 static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
-	unsigned char oldbit;
-
-	asm volatile("lock; btr %2,%1\n\tsetc %0"
-		     : "=qm" (oldbit), "+m" (ADDR)
-		     : "Ir" (nr) : "memory");
-	return oldbit;
+	return GEN_BINARY_RMWcc("lock; " __ASM_SIZE(btr), *addr, c, "Ir", nr);
 }
 
 /**
@@ -116,12 +108,7 @@ static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr)
  */
 static inline int sync_test_and_change_bit(long nr, volatile unsigned long *addr)
 {
-	unsigned char oldbit;
-
-	asm volatile("lock; btc %2,%1\n\tsetc %0"
-		     : "=qm" (oldbit), "+m" (ADDR)
-		     : "Ir" (nr) : "memory");
-	return oldbit;
+	return GEN_BINARY_RMWcc("lock; " __ASM_SIZE(btc), *addr, c, "Ir", nr);
 }
 
 #define sync_test_bit(nr, addr) test_bit(nr, addr)

arch/x86/include/asm/uaccess.h

@@ -586,7 +586,6 @@ extern void __cmpxchg_wrong_size(void)
 #define __user_atomic_cmpxchg_inatomic(uval, ptr, old, new, size)	\
 ({									\
 	int __ret = 0;							\
-	__typeof__(ptr) __uval = (uval);				\
 	__typeof__(*(ptr)) __old = (old);				\
 	__typeof__(*(ptr)) __new = (new);				\
 	__uaccess_begin_nospec();					\
@@ -662,7 +661,7 @@ extern void __cmpxchg_wrong_size(void)
 		__cmpxchg_wrong_size();					\
 	}								\
 	__uaccess_end();						\
-	*__uval = __old;						\
+	*(uval) = __old;						\
 	__ret;								\
 })
 

arch/x86/kernel/apic/apic_numachip.c

@@ -175,7 +175,7 @@ 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(X86_FEATURE_NODEID_MSR)) {
+	if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) {
 		rdmsrl(MSR_FAM10H_NODE_ID, val);
 		nodes = ((val >> 3) & 7) + 1;
 	}

arch/x86/kernel/cpu/amd.c

@@ -82,11 +82,14 @@ static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
  *	performance at the same time..
  */
 
+#ifdef CONFIG_X86_32
 extern __visible void vide(void);
-__asm__(".globl vide\n"
+__asm__(".text\n"
+	".globl vide\n"
 	".type vide, @function\n"
 	".align 4\n"
 	"vide: ret\n");
+#endif
 
 static void init_amd_k5(struct cpuinfo_x86 *c)
 {

arch/x86/kernel/cpu/aperfmperf.c

@@ -83,7 +83,7 @@ unsigned int aperfmperf_get_khz(int cpu)
 	if (!cpu_khz)
 		return 0;
 
-	if (!static_cpu_has(X86_FEATURE_APERFMPERF))
+	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
 		return 0;
 
 	aperfmperf_snapshot_cpu(cpu, ktime_get(), true);
@@ -99,7 +99,7 @@ void arch_freq_prepare_all(void)
 	if (!cpu_khz)
 		return;
 
-	if (!static_cpu_has(X86_FEATURE_APERFMPERF))
+	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
 		return;
 
 	for_each_online_cpu(cpu)
@@ -115,7 +115,7 @@ unsigned int arch_freq_get_on_cpu(int cpu)
 	if (!cpu_khz)
 		return 0;
 
-	if (!static_cpu_has(X86_FEATURE_APERFMPERF))
+	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
 		return 0;
 
 	if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true))

arch/x86/kernel/cpu/common.c

@@ -1668,7 +1668,7 @@ static void setup_getcpu(int cpu)
 	unsigned long cpudata = vdso_encode_cpunode(cpu, early_cpu_to_node(cpu));
 	struct desc_struct d = { };
 
-	if (static_cpu_has(X86_FEATURE_RDTSCP))
+	if (boot_cpu_has(X86_FEATURE_RDTSCP))
 		write_rdtscp_aux(cpudata);
 
 	/* Store CPU and node number in limit. */

arch/x86/kernel/cpu/mce/inject.c

@@ -528,7 +528,7 @@ static void do_inject(void)
 	 * only on the node base core. Refer to D18F3x44[NbMcaToMstCpuEn] for
 	 * Fam10h and later BKDGs.
 	 */
-	if (static_cpu_has(X86_FEATURE_AMD_DCM) &&
+	if (boot_cpu_has(X86_FEATURE_AMD_DCM) &&
 	    b == 4 &&
 	    boot_cpu_data.x86 < 0x17) {
 		toggle_nb_mca_mst_cpu(amd_get_nb_id(cpu));

arch/x86/kernel/cpu/proc.c

@@ -35,11 +35,11 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c)
 		   "fpu_exception\t: %s\n"
 		   "cpuid level\t: %d\n"
 		   "wp\t\t: yes\n",
-		   static_cpu_has_bug(X86_BUG_FDIV) ? "yes" : "no",
-		   static_cpu_has_bug(X86_BUG_F00F) ? "yes" : "no",
-		   static_cpu_has_bug(X86_BUG_COMA) ? "yes" : "no",
-		   static_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
-		   static_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
+		   boot_cpu_has_bug(X86_BUG_FDIV) ? "yes" : "no",
+		   boot_cpu_has_bug(X86_BUG_F00F) ? "yes" : "no",
+		   boot_cpu_has_bug(X86_BUG_COMA) ? "yes" : "no",
+		   boot_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
+		   boot_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
 		   c->cpuid_level);
 }
 #else

arch/x86/kernel/kprobes/core.c

@@ -716,6 +716,7 @@ NOKPROBE_SYMBOL(kprobe_int3_handler);
  * calls trampoline_handler() runs, which calls the kretprobe's handler.
  */
 asm(
+	".text\n"
 	".global kretprobe_trampoline\n"
 	".type kretprobe_trampoline, @function\n"
 	"kretprobe_trampoline:\n"

arch/x86/kernel/ldt.c

@@ -113,7 +113,7 @@ static void do_sanity_check(struct mm_struct *mm,
 		 * tables.
 		 */
 		WARN_ON(!had_kernel_mapping);
-		if (static_cpu_has(X86_FEATURE_PTI))
+		if (boot_cpu_has(X86_FEATURE_PTI))
 			WARN_ON(!had_user_mapping);
 	} else {
 		/*
@@ -121,7 +121,7 @@ static void do_sanity_check(struct mm_struct *mm,
 		 * Sync the pgd to the usermode tables.
 		 */
 		WARN_ON(had_kernel_mapping);
-		if (static_cpu_has(X86_FEATURE_PTI))
+		if (boot_cpu_has(X86_FEATURE_PTI))
 			WARN_ON(had_user_mapping);
 	}
 }
@@ -156,7 +156,7 @@ static void map_ldt_struct_to_user(struct mm_struct *mm)
 	k_pmd = pgd_to_pmd_walk(k_pgd, LDT_BASE_ADDR);
 	u_pmd = pgd_to_pmd_walk(u_pgd, LDT_BASE_ADDR);
 
-	if (static_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
+	if (boot_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
 		set_pmd(u_pmd, *k_pmd);
 }
 
@@ -181,7 +181,7 @@ static void map_ldt_struct_to_user(struct mm_struct *mm)
 {
 	pgd_t *pgd = pgd_offset(mm, LDT_BASE_ADDR);
 
-	if (static_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
+	if (boot_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
 		set_pgd(kernel_to_user_pgdp(pgd), *pgd);
 }
 
@@ -208,7 +208,7 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 	spinlock_t *ptl;
 	int i, nr_pages;
 
-	if (!static_cpu_has(X86_FEATURE_PTI))
+	if (!boot_cpu_has(X86_FEATURE_PTI))
 		return 0;
 
 	/*
@@ -271,7 +271,7 @@ static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt)
 		return;
 
 	/* LDT map/unmap is only required for PTI */
-	if (!static_cpu_has(X86_FEATURE_PTI))
+	if (!boot_cpu_has(X86_FEATURE_PTI))
 		return;
 
 	nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE);
@@ -311,7 +311,7 @@ static void free_ldt_pgtables(struct mm_struct *mm)
 	unsigned long start = LDT_BASE_ADDR;
 	unsigned long end = LDT_END_ADDR;
 
-	if (!static_cpu_has(X86_FEATURE_PTI))
+	if (!boot_cpu_has(X86_FEATURE_PTI))
 		return;
 
 	tlb_gather_mmu(&tlb, mm, start, end);

arch/x86/kernel/paravirt.c

@@ -121,7 +121,7 @@ DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key);
 
 void __init native_pv_lock_init(void)
 {
-	if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
+	if (!boot_cpu_has(X86_FEATURE_HYPERVISOR))
 		static_branch_disable(&virt_spin_lock_key);
 }
 

arch/x86/kernel/process.c

@@ -236,7 +236,7 @@ static int get_cpuid_mode(void)
 
 static int set_cpuid_mode(struct task_struct *task, unsigned long cpuid_enabled)
 {
-	if (!static_cpu_has(X86_FEATURE_CPUID_FAULT))
+	if (!boot_cpu_has(X86_FEATURE_CPUID_FAULT))
 		return -ENODEV;
 
 	if (cpuid_enabled)
@@ -670,7 +670,7 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c)
 	if (c->x86_vendor != X86_VENDOR_INTEL)
 		return 0;
 
-	if (!cpu_has(c, X86_FEATURE_MWAIT) || static_cpu_has_bug(X86_BUG_MONITOR))
+	if (!cpu_has(c, X86_FEATURE_MWAIT) || boot_cpu_has_bug(X86_BUG_MONITOR))
 		return 0;
 
 	return 1;

arch/x86/kernel/reboot.c

@@ -121,7 +121,7 @@ void __noreturn machine_real_restart(unsigned int type)
 	write_cr3(real_mode_header->trampoline_pgd);
 
 	/* Exiting long mode will fail if CR4.PCIDE is set. */
-	if (static_cpu_has(X86_FEATURE_PCID))
+	if (boot_cpu_has(X86_FEATURE_PCID))
 		cr4_clear_bits(X86_CR4_PCIDE);
 #endif
 

arch/x86/kernel/vm86_32.c

@@ -369,7 +369,7 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus)
 	preempt_disable();
 	tsk->thread.sp0 += 16;
 
-	if (static_cpu_has(X86_FEATURE_SEP)) {
+	if (boot_cpu_has(X86_FEATURE_SEP)) {
 		tsk->thread.sysenter_cs = 0;
 		refresh_sysenter_cs(&tsk->thread);
 	}

arch/x86/lib/error-inject.c

@@ -6,6 +6,7 @@
 asmlinkage void just_return_func(void);
 
 asm(
+	".text\n"
 	".type just_return_func, @function\n"
 	".globl just_return_func\n"
 	"just_return_func:\n"

arch/x86/mm/dump_pagetables.c

@@ -578,7 +578,7 @@ void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd)
 void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user)
 {
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
-	if (user && static_cpu_has(X86_FEATURE_PTI))
+	if (user && boot_cpu_has(X86_FEATURE_PTI))
 		pgd = kernel_to_user_pgdp(pgd);
 #endif
 	ptdump_walk_pgd_level_core(m, pgd, false, false);
@@ -591,7 +591,7 @@ void ptdump_walk_user_pgd_level_checkwx(void)
 	pgd_t *pgd = INIT_PGD;
 
 	if (!(__supported_pte_mask & _PAGE_NX) ||
-	    !static_cpu_has(X86_FEATURE_PTI))
+	    !boot_cpu_has(X86_FEATURE_PTI))
 		return;
 
 	pr_info("x86/mm: Checking user space page tables\n");

arch/x86/mm/pgtable.c

@@ -190,7 +190,7 @@ static void pgd_dtor(pgd_t *pgd)
  * when PTI is enabled. We need them to map the per-process LDT into the
  * user-space page-table.
  */
-#define PREALLOCATED_USER_PMDS	 (static_cpu_has(X86_FEATURE_PTI) ? \
+#define PREALLOCATED_USER_PMDS	 (boot_cpu_has(X86_FEATURE_PTI) ? \
 					KERNEL_PGD_PTRS : 0)
 #define MAX_PREALLOCATED_USER_PMDS KERNEL_PGD_PTRS
 
@@ -292,7 +292,7 @@ static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp)
 
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
 
-	if (!static_cpu_has(X86_FEATURE_PTI))
+	if (!boot_cpu_has(X86_FEATURE_PTI))
 		return;
 
 	pgdp = kernel_to_user_pgdp(pgdp);

arch/x86/mm/pti.c

@@ -628,7 +628,7 @@ static void pti_set_kernel_image_nonglobal(void)
  */
 void __init pti_init(void)
 {
-	if (!static_cpu_has(X86_FEATURE_PTI))
+	if (!boot_cpu_has(X86_FEATURE_PTI))
 		return;
 
 	pr_info("enabled\n");

arch/x86/um/vdso/Makefile

@@ -62,7 +62,7 @@ quiet_cmd_vdso = VDSO    $@
 		       -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \
 		 sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@'
 
-VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+VDSO_LDFLAGS = -fPIC -shared -Wl,--hash-style=sysv
 GCOV_PROFILE := n
 
 #