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()

12 files changed, 28 insertions, 24 deletions

diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index 78778b54f904..a5464b8b6c46 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/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;
 	}
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 01004bfb1a1b..fb6a64bd765f 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/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)
 {
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index 804c49493938..64d5aec24203 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/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))
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index cb28e98a0659..95a5faf3a6a0 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/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. */
diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c
index 8492ef7d9015..3da9a8823e47 100644
--- a/arch/x86/kernel/cpu/mce/inject.c
+++ b/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));
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index 2c8522a39ed5..cb2e49810d68 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/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
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index fed46ddb1eef..122548ad5c2e 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/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"
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 6135ae8ce036..b2463fcb20a8 100644
--- a/arch/x86/kernel/ldt.c
+++ b/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);
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index c0e0101133f3..7bbaa6baf37f 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/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);
 }
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 957eae13b370..d1d312d012a6 100644
--- a/arch/x86/kernel/process.c
+++ b/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;
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 8fd3cedd9acc..09d6bded3c1e 100644
--- a/arch/x86/kernel/reboot.c
+++ b/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
 
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index a092b6b40c6b..6a38717d179c 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/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);
 	}