x86/asm changes for v4.5

index 3c71dd947c7b..e32206e09868 100644
@@ -1,3 +1,5 @@
+#include <linux/jump_label.h>
+
 /*
 
  x86 function call convention, 64-bit:

@@ -232,3 +234,16 @@ For 32-bit we have the following conventions - kernel is built with
 
 #endif /* CONFIG_X86_64 */
 
+/*
+ * This does 'call enter_from_user_mode' unless we can avoid it based on
+ * kernel config or using the static jump infrastructure.
+ */
+.macro CALL_enter_from_user_mode
+#ifdef CONFIG_CONTEXT_TRACKING
+#ifdef HAVE_JUMP_LABEL
+	STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_enabled, def=0
+#endif
+	call enter_from_user_mode
+.Lafter_call_\@:
+#endif
+.endm

183 lines not on this page · raw message

index 785d9922b106..491020b2826d 100644
@@ -73,6 +73,7 @@ enum {
 	sym_vvar_start,
 	sym_vvar_page,
 	sym_hpet_page,
+	sym_pvclock_page,
 	sym_VDSO_FAKE_SECTION_TABLE_START,
 	sym_VDSO_FAKE_SECTION_TABLE_END,
 };

@@ -80,6 +81,7 @@ enum {
 const int special_pages[] = {
 	sym_vvar_page,
 	sym_hpet_page,
+	sym_pvclock_page,
 };
 
 struct vdso_sym {

@@ -91,6 +93,7 @@ struct vdso_sym required_syms[] = {
 	[sym_vvar_start] = {"vvar_start", true},
 	[sym_vvar_page] = {"vvar_page", true},
 	[sym_hpet_page] = {"hpet_page", true},
+	[sym_pvclock_page] = {"pvclock_page", true},
 	[sym_VDSO_FAKE_SECTION_TABLE_START] = {
 		"VDSO_FAKE_SECTION_TABLE_START", false
 	},

index 64df47148160..b8f69e264ac4 100644
@@ -12,6 +12,7 @@
 #include <linux/random.h>
 #include <linux/elf.h>
 #include <linux/cpu.h>
+#include <asm/pvclock.h>
 #include <asm/vgtod.h>
 #include <asm/proto.h>
 #include <asm/vdso.h>

@@ -100,6 +101,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 		.name = "[vvar]",
 		.pages = no_pages,
 	};
+	struct pvclock_vsyscall_time_info *pvti;
 
 	if (calculate_addr) {
 		addr = vdso_addr(current->mm->start_stack,

@@ -169,6 +171,18 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
 	}
 #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;

index e4f8010f22e0..f7ba9fbf12ee 100644
@@ -216,6 +216,7 @@
 #define X86_FEATURE_PAUSEFILTER ( 8*32+13) /* AMD filtered pause intercept */
 #define X86_FEATURE_PFTHRESHOLD ( 8*32+14) /* AMD pause filter threshold */
 #define X86_FEATURE_VMMCALL     ( 8*32+15) /* Prefer vmmcall to vmcall */
+#define X86_FEATURE_XENPV       ( 8*32+16) /* "" Xen paravirtual guest */
 
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */

index f80d70009ff8..6d7d0e52ed5a 100644
@@ -19,7 +19,6 @@
 #include <asm/acpi.h>
 #include <asm/apicdef.h>
 #include <asm/page.h>
-#include <asm/pvclock.h>
 #ifdef CONFIG_X86_32
 #include <linux/threads.h>
 #include <asm/kmap_types.h>

@@ -72,10 +71,6 @@ enum fixed_addresses {
 #ifdef CONFIG_X86_VSYSCALL_EMULATION
 	VSYSCALL_PAGE = (FIXADDR_TOP - VSYSCALL_ADDR) >> PAGE_SHIFT,
 #endif
-#ifdef CONFIG_PARAVIRT_CLOCK
-	PVCLOCK_FIXMAP_BEGIN,
-	PVCLOCK_FIXMAP_END = PVCLOCK_FIXMAP_BEGIN+PVCLOCK_VSYSCALL_NR_PAGES-1,
-#endif
 #endif
 	FIX_DBGP_BASE,
 	FIX_EARLYCON_MEM_BASE,

79 lines not on this page · raw message

index 10d0596433f8..1b71c3aeae86 100644
@@ -922,23 +922,11 @@ extern void default_banner(void);
 		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable);	\
 		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
 
-#define USERGS_SYSRET32							\
-	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret32),	\
-		  CLBR_NONE,						\
-		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret32))
-
 #ifdef CONFIG_X86_32
 #define GET_CR0_INTO_EAX				\
 	push %ecx; push %edx;				\
 	call PARA_INDIRECT(pv_cpu_ops+PV_CPU_read_cr0);	\
 	pop %edx; pop %ecx
-
-#define ENABLE_INTERRUPTS_SYSEXIT					\
-	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_irq_enable_sysexit),	\
-		  CLBR_NONE,						\
-		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_irq_enable_sysexit))
-
-
 #else	/* !CONFIG_X86_32 */
 
 /*

index 31247b5bff7c..702c8bdf7b66 100644
@@ -157,15 +157,6 @@ struct pv_cpu_ops {
 
 	u64 (*read_pmc)(int counter);
 
-#ifdef CONFIG_X86_32
-	/*
-	 * Atomically enable interrupts and return to userspace.  This
-	 * is only used in 32-bit kernels.  64-bit kernels use
-	 * usergs_sysret32 instead.
-	 */
-	void (*irq_enable_sysexit)(void);
-#endif
-
 	/*
 	 * Switch to usermode gs and return to 64-bit usermode using
 	 * sysret.  Only used in 64-bit kernels to return to 64-bit

@@ -174,14 +165,6 @@ struct pv_cpu_ops {
 	 */
 	void (*usergs_sysret64)(void);
 
-	/*
-	 * Switch to usermode gs and return to 32-bit usermode using
-	 * sysret.  Used to return to 32-on-64 compat processes.
-	 * Other usermode register state, including %esp, must already
-	 * be restored.
-	 */
-	void (*usergs_sysret32)(void);
-
 	/* Normal iret.  Jump to this with the standard iret stack
 	   frame set up. */
 	void (*iret)(void);

index 7a6bed5c08bc..fdcc04020636 100644
@@ -4,6 +4,15 @@
 #include <linux/clocksource.h>
 #include <asm/pvclock-abi.h>
 
+#ifdef CONFIG_KVM_GUEST
+extern struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void);
+#else
+static inline struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void)
+{
+	return NULL;
+}
+#endif
+
 /* some helper functions for xen and kvm pv clock sources */
 cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src);
 u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src);

@@ -91,10 +100,5 @@ struct pvclock_vsyscall_time_info {
 } __attribute__((__aligned__(SMP_CACHE_BYTES)));
 
 #define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info)
-#define PVCLOCK_VSYSCALL_NR_PAGES (((NR_CPUS-1)/(PAGE_SIZE/PVTI_SIZE))+1)
-
-int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i,
-				 int size);
-struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu);
 
 #endif /* _ASM_X86_PVCLOCK_H */

index 756de9190aec..deabaf9759b6 100644
@@ -22,6 +22,7 @@ struct vdso_image {
 
 	long sym_vvar_page;
 	long sym_hpet_page;
+	long sym_pvclock_page;
 	long sym_VDSO32_NOTE_MASK;
 	long sym___kernel_sigreturn;
 	long sym___kernel_rt_sigreturn;

index 439df975bc7a..84a7524b202c 100644
@@ -65,9 +65,6 @@ void common(void) {
 	OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
 	OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
 	OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
-#ifdef CONFIG_X86_32
-	OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit);
-#endif
 	OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0);
 	OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2);
 #endif

index d8f42f902a0f..f2edafb5f24e 100644
@@ -23,7 +23,6 @@ int main(void)
 {
 #ifdef CONFIG_PARAVIRT
 	OFFSET(PV_IRQ_adjust_exception_frame, pv_irq_ops, adjust_exception_frame);
-	OFFSET(PV_CPU_usergs_sysret32, pv_cpu_ops, usergs_sysret32);
 	OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64);
 	OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs);
 	BLANK();

index 2bd81e302427..72cef58693c7 100644
@@ -45,6 +45,11 @@ early_param("no-kvmclock", parse_no_kvmclock);
 static struct pvclock_vsyscall_time_info *hv_clock;
 static struct pvclock_wall_clock wall_clock;
 
+struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void)
+{
+	return hv_clock;
+}
+
 /*
  * The wallclock is the time of day when we booted. Since then, some time may
  * have elapsed since the hypervisor wrote the data. So we try to account for

@@ -305,7 +310,6 @@ int __init kvm_setup_vsyscall_timeinfo(void)
 {
 #ifdef CONFIG_X86_64
 	int cpu;
-	int ret;
 	u8 flags;
 	struct pvclock_vcpu_time_info *vcpu_time;
 	unsigned int size;

@@ -325,11 +329,6 @@ int __init kvm_setup_vsyscall_timeinfo(void)
 		return 1;
 	}
 
-	if ((ret = pvclock_init_vsyscall(hv_clock, size))) {
-		put_cpu();
-		return ret;
-	}
-
 	put_cpu();
 
 	kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK;

index c2130aef3f9d..8c19b4d5e719 100644
@@ -162,10 +162,6 @@ unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf,
 		ret = paravirt_patch_ident_64(insnbuf, len);
 
 	else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) ||
-#ifdef CONFIG_X86_32
-		 type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit) ||
-#endif
-		 type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret32) ||
 		 type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret64))
 		/* If operation requires a jmp, then jmp */
 		ret = paravirt_patch_jmp(insnbuf, opfunc, addr, len);

@@ -220,8 +216,6 @@ static u64 native_steal_clock(int cpu)
 
 /* These are in entry.S */
 extern void native_iret(void);
-extern void native_irq_enable_sysexit(void);
-extern void native_usergs_sysret32(void);
 extern void native_usergs_sysret64(void);
 
 static struct resource reserve_ioports = {

@@ -379,13 +373,7 @@ __visible struct pv_cpu_ops pv_cpu_ops = {
 
 	.load_sp0 = native_load_sp0,
 
-#if defined(CONFIG_X86_32)
-	.irq_enable_sysexit = native_irq_enable_sysexit,
-#endif
 #ifdef CONFIG_X86_64
-#ifdef CONFIG_IA32_EMULATION
-	.usergs_sysret32 = native_usergs_sysret32,
-#endif
 	.usergs_sysret64 = native_usergs_sysret64,
 #endif
 	.iret = native_iret,

index c89f50a76e97..158dc0650d5d 100644
@@ -5,7 +5,6 @@ DEF_NATIVE(pv_irq_ops, irq_enable, "sti");
 DEF_NATIVE(pv_irq_ops, restore_fl, "push %eax; popf");
 DEF_NATIVE(pv_irq_ops, save_fl, "pushf; pop %eax");
 DEF_NATIVE(pv_cpu_ops, iret, "iret");
-DEF_NATIVE(pv_cpu_ops, irq_enable_sysexit, "sti; sysexit");
 DEF_NATIVE(pv_mmu_ops, read_cr2, "mov %cr2, %eax");
 DEF_NATIVE(pv_mmu_ops, write_cr3, "mov %eax, %cr3");
 DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax");

@@ -46,7 +45,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_irq_ops, restore_fl);
 		PATCH_SITE(pv_irq_ops, save_fl);
 		PATCH_SITE(pv_cpu_ops, iret);
-		PATCH_SITE(pv_cpu_ops, irq_enable_sysexit);
 		PATCH_SITE(pv_mmu_ops, read_cr2);
 		PATCH_SITE(pv_mmu_ops, read_cr3);
 		PATCH_SITE(pv_mmu_ops, write_cr3);

index 8aa05583bc42..e70087a04cc8 100644
@@ -13,9 +13,7 @@ DEF_NATIVE(pv_mmu_ops, flush_tlb_single, "invlpg (%rdi)");
 DEF_NATIVE(pv_cpu_ops, clts, "clts");
 DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd");
 
-DEF_NATIVE(pv_cpu_ops, irq_enable_sysexit, "swapgs; sti; sysexit");
 DEF_NATIVE(pv_cpu_ops, usergs_sysret64, "swapgs; sysretq");
-DEF_NATIVE(pv_cpu_ops, usergs_sysret32, "swapgs; sysretl");
 DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs");
 
 DEF_NATIVE(, mov32, "mov %edi, %eax");

@@ -55,7 +53,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_irq_ops, save_fl);
 		PATCH_SITE(pv_irq_ops, irq_enable);
 		PATCH_SITE(pv_irq_ops, irq_disable);
-		PATCH_SITE(pv_cpu_ops, usergs_sysret32);
 		PATCH_SITE(pv_cpu_ops, usergs_sysret64);
 		PATCH_SITE(pv_cpu_ops, swapgs);
 		PATCH_SITE(pv_mmu_ops, read_cr2);

index 2f355d229a58..99bfc025111d 100644
@@ -140,27 +140,3 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock,
 
 	set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
 }
-
-#ifdef CONFIG_X86_64
-/*
- * Initialize the generic pvclock vsyscall state.  This will allocate
- * a/some page(s) for the per-vcpu pvclock information, set up a
- * fixmap mapping for the page(s)
- */
-
-int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i,
-				 int size)
-{
-	int idx;
-
-	WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE);
-
-	for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) {
-		__set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx,
-			     __pa(i) + (idx*PAGE_SIZE),
-			     PAGE_KERNEL_VVAR);
-	}
-
-	return 0;
-}
-#endif

index 327f21c3bde1..8dd80050d705 100644
@@ -28,6 +28,7 @@
 #include <linux/nmi.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/clocksource.h>
 
 #include <asm/apic.h>
 #include <asm/current.h>

index 5774800ff583..a068e36382b7 100644
@@ -1229,10 +1229,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 
 	.iret = xen_iret,
 #ifdef CONFIG_X86_64
-	.usergs_sysret32 = xen_sysret32,
 	.usergs_sysret64 = xen_sysret64,
-#else
-	.irq_enable_sysexit = xen_sysexit,
 #endif
 
 	.load_tr_desc = paravirt_nop,

@@ -1886,8 +1883,10 @@ EXPORT_SYMBOL_GPL(xen_hvm_need_lapic);
 
 static void xen_set_cpu_features(struct cpuinfo_x86 *c)
 {
-	if (xen_pv_domain())
+	if (xen_pv_domain()) {
 		clear_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
+		set_cpu_cap(c, X86_FEATURE_XENPV);
+	}
 }
 
 const struct hypervisor_x86 x86_hyper_xen = {

index 1399423f3418..4140b070f2e9 100644
@@ -139,9 +139,6 @@ DECL_ASM(void, xen_restore_fl_direct, unsigned long);
 
 /* These are not functions, and cannot be called normally */
 __visible void xen_iret(void);
-#ifdef CONFIG_X86_32
-__visible void xen_sysexit(void);
-#endif
 __visible void xen_sysret32(void);
 __visible void xen_sysret64(void);
 __visible void xen_adjust_exception_frame(void);

index ee956c528fab..1d34fe68f48a 100644
@@ -22,12 +22,12 @@ struct context_tracking {
 };
 
 #ifdef CONFIG_CONTEXT_TRACKING
-extern struct static_key context_tracking_enabled;
+extern struct static_key_false context_tracking_enabled;
 DECLARE_PER_CPU(struct context_tracking, context_tracking);
 
 static inline bool context_tracking_is_enabled(void)
 {
-	return static_key_false(&context_tracking_enabled);
+	return static_branch_unlikely(&context_tracking_enabled);
 }
 
 static inline bool context_tracking_cpu_is_enabled(void)

index d8560ee3bab7..9ad37b9e44a7 100644
@@ -24,7 +24,7 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/context_tracking.h>
 
-struct static_key context_tracking_enabled = STATIC_KEY_INIT_FALSE;
+DEFINE_STATIC_KEY_FALSE(context_tracking_enabled);
 EXPORT_SYMBOL_GPL(context_tracking_enabled);
 
 DEFINE_PER_CPU(struct context_tracking, context_tracking);

@@ -191,7 +191,7 @@ void __init context_tracking_cpu_set(int cpu)
 
 	if (!per_cpu(context_tracking.active, cpu)) {
 		per_cpu(context_tracking.active, cpu) = true;
-		static_key_slow_inc(&context_tracking_enabled);
+		static_branch_inc(&context_tracking_enabled);
 	}
 
 	if (initialized)