Merge branch 'x86/vdso' of git://git.kernel.org/pub/scm/linux/kernel/…

…git/tip/tip into next

Pull x86 cdso updates from Peter Anvin:
 "Vdso cleanups and improvements largely from Andy Lutomirski.  This
  makes the vdso a lot less ''special''"

* 'x86/vdso' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/vdso, build: Make LE access macros clearer, host-safe
  x86/vdso, build: Fix cross-compilation from big-endian architectures
  x86/vdso, build: When vdso2c fails, unlink the output
  x86, vdso: Fix an OOPS accessing the HPET mapping w/o an HPET
  x86, mm: Replace arch_vma_name with vm_ops->name for vsyscalls
  x86, mm: Improve _install_special_mapping and fix x86 vdso naming
  mm, fs: Add vm_ops->name as an alternative to arch_vma_name
  x86, vdso: Fix an OOPS accessing the HPET mapping w/o an HPET
  x86, vdso: Remove vestiges of VDSO_PRELINK and some outdated comments
  x86, vdso: Move the vvar and hpet mappings next to the 64-bit vDSO
  x86, vdso: Move the 32-bit vdso special pages after the text
  x86, vdso: Reimplement vdso.so preparation in build-time C
  x86, vdso: Move syscall and sysenter setup into kernel/cpu/common.c
  x86, vdso: Clean up 32-bit vs 64-bit vdso params
  x86, mm: Ensure correct alignment of the fixmap

arch/x86/ia32/ia32_signal.c

@@ -383,8 +383,8 @@ int ia32_setup_frame(int sig, struct ksignal *ksig,
 	} else {
 		/* Return stub is in 32bit vsyscall page */
 		if (current->mm->context.vdso)
-			restorer = VDSO32_SYMBOL(current->mm->context.vdso,
-						 sigreturn);
+			restorer = current->mm->context.vdso +
+				selected_vdso32->sym___kernel_sigreturn;
 		else
 			restorer = &frame->retcode;
 	}
@@ -462,8 +462,8 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig,
 		if (ksig->ka.sa.sa_flags & SA_RESTORER)
 			restorer = ksig->ka.sa.sa_restorer;
 		else
-			restorer = VDSO32_SYMBOL(current->mm->context.vdso,
-						 rt_sigreturn);
+			restorer = current->mm->context.vdso +
+				selected_vdso32->sym___kernel_rt_sigreturn;
 		put_user_ex(ptr_to_compat(restorer), &frame->pretcode);
 
 		/*

arch/x86/include/asm/elf.h

@@ -75,7 +75,12 @@ typedef struct user_fxsr_struct elf_fpxregset_t;
 
 #include <asm/vdso.h>
 
-extern unsigned int vdso_enabled;
+#ifdef CONFIG_X86_64
+extern unsigned int vdso64_enabled;
+#endif
+#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT)
+extern unsigned int vdso32_enabled;
+#endif
 
 /*
  * This is used to ensure we don't load something for the wrong architecture.
@@ -269,9 +274,9 @@ extern int force_personality32;
 
 struct task_struct;
 
-#define	ARCH_DLINFO_IA32(vdso_enabled)					\
+#define	ARCH_DLINFO_IA32						\
 do {									\
-	if (vdso_enabled) {						\
+	if (vdso32_enabled) {						\
 		NEW_AUX_ENT(AT_SYSINFO,	VDSO_ENTRY);			\
 		NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_CURRENT_BASE);	\
 	}								\
@@ -281,7 +286,7 @@ do {									\
 
 #define STACK_RND_MASK (0x7ff)
 
-#define ARCH_DLINFO		ARCH_DLINFO_IA32(vdso_enabled)
+#define ARCH_DLINFO		ARCH_DLINFO_IA32
 
 /* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */
 
@@ -292,16 +297,17 @@ do {									\
 
 #define ARCH_DLINFO							\
 do {									\
-	if (vdso_enabled)						\
+	if (vdso64_enabled)						\
 		NEW_AUX_ENT(AT_SYSINFO_EHDR,				\
-			    (unsigned long)current->mm->context.vdso);	\
+			    (unsigned long __force)current->mm->context.vdso); \
 } while (0)
 
+/* As a historical oddity, the x32 and x86_64 vDSOs are controlled together. */
 #define ARCH_DLINFO_X32							\
 do {									\
-	if (vdso_enabled)						\
+	if (vdso64_enabled)						\
 		NEW_AUX_ENT(AT_SYSINFO_EHDR,				\
-			    (unsigned long)current->mm->context.vdso);	\
+			    (unsigned long __force)current->mm->context.vdso); \
 } while (0)
 
 #define AT_SYSINFO		32
@@ -310,7 +316,7 @@ do {									\
 if (test_thread_flag(TIF_X32))						\
 	ARCH_DLINFO_X32;						\
 else									\
-	ARCH_DLINFO_IA32(sysctl_vsyscall32)
+	ARCH_DLINFO_IA32
 
 #define COMPAT_ELF_ET_DYN_BASE	(TASK_UNMAPPED_BASE + 0x1000000)
 
@@ -319,18 +325,17 @@ else									\
 #define VDSO_CURRENT_BASE	((unsigned long)current->mm->context.vdso)
 
 #define VDSO_ENTRY							\
-	((unsigned long)VDSO32_SYMBOL(VDSO_CURRENT_BASE, vsyscall))
+	((unsigned long)current->mm->context.vdso +			\
+	 selected_vdso32->sym___kernel_vsyscall)
 
 struct linux_binprm;
 
 #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
 extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 				       int uses_interp);
-extern int x32_setup_additional_pages(struct linux_binprm *bprm,
-				      int uses_interp);
-
-extern int syscall32_setup_pages(struct linux_binprm *, int exstack);
-#define compat_arch_setup_additional_pages	syscall32_setup_pages
+extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
+					      int uses_interp);
+#define compat_arch_setup_additional_pages compat_arch_setup_additional_pages
 
 extern unsigned long arch_randomize_brk(struct mm_struct *mm);
 #define arch_randomize_brk arch_randomize_brk

arch/x86/include/asm/fixmap.h

@@ -24,7 +24,7 @@
 #include <linux/threads.h>
 #include <asm/kmap_types.h>
 #else
-#include <asm/vsyscall.h>
+#include <uapi/asm/vsyscall.h>
 #endif
 
 /*
@@ -41,7 +41,8 @@
 extern unsigned long __FIXADDR_TOP;
 #define FIXADDR_TOP	((unsigned long)__FIXADDR_TOP)
 #else
-#define FIXADDR_TOP	(VSYSCALL_END-PAGE_SIZE)
+#define FIXADDR_TOP	(round_up(VSYSCALL_ADDR + PAGE_SIZE, 1<<PMD_SHIFT) - \
+			 PAGE_SIZE)
 #endif
 
 
@@ -68,11 +69,7 @@ enum fixed_addresses {
 #ifdef CONFIG_X86_32
 	FIX_HOLE,
 #else
-	VSYSCALL_LAST_PAGE,
-	VSYSCALL_FIRST_PAGE = VSYSCALL_LAST_PAGE
-			    + ((VSYSCALL_END-VSYSCALL_START) >> PAGE_SHIFT) - 1,
-	VVAR_PAGE,
-	VSYSCALL_HPET,
+	VSYSCALL_PAGE = (FIXADDR_TOP - VSYSCALL_ADDR) >> PAGE_SHIFT,
 #ifdef CONFIG_PARAVIRT_CLOCK
 	PVCLOCK_FIXMAP_BEGIN,
 	PVCLOCK_FIXMAP_END = PVCLOCK_FIXMAP_BEGIN+PVCLOCK_VSYSCALL_NR_PAGES-1,

arch/x86/include/asm/mmu.h

@@ -18,7 +18,7 @@ typedef struct {
 #endif
 
 	struct mutex lock;
-	void *vdso;
+	void __user *vdso;
 } mm_context_t;
 
 #ifdef CONFIG_SMP

arch/x86/include/asm/proto.h

@@ -12,8 +12,6 @@ void ia32_syscall(void);
 void ia32_cstar_target(void);
 void ia32_sysenter_target(void);
 
-void syscall32_cpu_init(void);
-
 void x86_configure_nx(void);
 void x86_report_nx(void);
 

arch/x86/include/asm/vdso.h

@@ -3,63 +3,51 @@
 
 #include <asm/page_types.h>
 #include <linux/linkage.h>
+#include <linux/init.h>
 
-#ifdef __ASSEMBLER__
+#ifndef __ASSEMBLER__
 
-#define DEFINE_VDSO_IMAGE(symname, filename)				\
-__PAGE_ALIGNED_DATA ;							\
-	.globl symname##_start, symname##_end ;				\
-	.align PAGE_SIZE ;						\
-	symname##_start: ;						\
-	.incbin filename ;						\
-	symname##_end: ;						\
-	.align PAGE_SIZE /* extra data here leaks to userspace. */ ;	\
-									\
-.previous ;								\
-									\
-	.globl symname##_pages ;					\
-	.bss ;								\
-	.align 8 ;							\
-	.type symname##_pages, @object ;				\
-	symname##_pages: ;						\
-	.zero (symname##_end - symname##_start + PAGE_SIZE - 1) / PAGE_SIZE * (BITS_PER_LONG / 8) ; \
-	.size symname##_pages, .-symname##_pages
+#include <linux/mm_types.h>
 
-#else
+struct vdso_image {
+	void *data;
+	unsigned long size;   /* Always a multiple of PAGE_SIZE */
 
-#define DECLARE_VDSO_IMAGE(symname)				\
-	extern char symname##_start[], symname##_end[];		\
-	extern struct page *symname##_pages[]
+	/* text_mapping.pages is big enough for data/size page pointers */
+	struct vm_special_mapping text_mapping;
 
-#if defined CONFIG_X86_32 || defined CONFIG_COMPAT
+	unsigned long alt, alt_len;
 
-#include <asm/vdso32.h>
+	unsigned long sym_end_mapping;  /* Total size of the mapping */
 
-DECLARE_VDSO_IMAGE(vdso32_int80);
-#ifdef CONFIG_COMPAT
-DECLARE_VDSO_IMAGE(vdso32_syscall);
+	unsigned long sym_vvar_page;
+	unsigned long sym_hpet_page;
+	unsigned long sym_VDSO32_NOTE_MASK;
+	unsigned long sym___kernel_sigreturn;
+	unsigned long sym___kernel_rt_sigreturn;
+	unsigned long sym___kernel_vsyscall;
+	unsigned long sym_VDSO32_SYSENTER_RETURN;
+};
+
+#ifdef CONFIG_X86_64
+extern const struct vdso_image vdso_image_64;
+#endif
+
+#ifdef CONFIG_X86_X32
+extern const struct vdso_image vdso_image_x32;
 #endif
-DECLARE_VDSO_IMAGE(vdso32_sysenter);
 
-/*
- * Given a pointer to the vDSO image, find the pointer to VDSO32_name
- * as that symbol is defined in the vDSO sources or linker script.
- */
-#define VDSO32_SYMBOL(base, name)					\
-({									\
-	extern const char VDSO32_##name[];				\
-	(void __user *)(VDSO32_##name + (unsigned long)(base));		\
-})
+#if defined CONFIG_X86_32 || defined CONFIG_COMPAT
+extern const struct vdso_image vdso_image_32_int80;
+#ifdef CONFIG_COMPAT
+extern const struct vdso_image vdso_image_32_syscall;
 #endif
+extern const struct vdso_image vdso_image_32_sysenter;
 
-/*
- * These symbols are defined with the addresses in the vsyscall page.
- * See vsyscall-sigreturn.S.
- */
-extern void __user __kernel_sigreturn;
-extern void __user __kernel_rt_sigreturn;
+extern const struct vdso_image *selected_vdso32;
+#endif
 
-void __init patch_vdso32(void *vdso, size_t len);
+extern void __init init_vdso_image(const struct vdso_image *image);
 
 #endif /* __ASSEMBLER__ */
 

arch/x86/include/asm/vvar.h

@@ -29,31 +29,13 @@
 
 #else
 
-#ifdef BUILD_VDSO32
+extern char __vvar_page;
 
 #define DECLARE_VVAR(offset, type, name)				\
 	extern type vvar_ ## name __attribute__((visibility("hidden")));
 
 #define VVAR(name) (vvar_ ## name)
 
-#else
-
-extern char __vvar_page;
-
-/* Base address of vvars.  This is not ABI. */
-#ifdef CONFIG_X86_64
-#define VVAR_ADDRESS (-10*1024*1024 - 4096)
-#else
-#define VVAR_ADDRESS (&__vvar_page)
-#endif
-
-#define DECLARE_VVAR(offset, type, name)				\
-	static type const * const vvaraddr_ ## name =			\
-		(void *)(VVAR_ADDRESS + (offset));
-
-#define VVAR(name) (*vvaraddr_ ## name)
-#endif
-
 #define DEFINE_VVAR(type, name)						\
 	type name							\
 	__attribute__((section(".vvar_" #name), aligned(16))) __visible

arch/x86/include/uapi/asm/vsyscall.h

@@ -7,11 +7,6 @@ enum vsyscall_num {
 	__NR_vgetcpu,
 };
 
-#define VSYSCALL_START (-10UL << 20)
-#define VSYSCALL_SIZE 1024
-#define VSYSCALL_END (-2UL << 20)
-#define VSYSCALL_MAPPED_PAGES 1
-#define VSYSCALL_ADDR(vsyscall_nr) (VSYSCALL_START+VSYSCALL_SIZE*(vsyscall_nr))
-
+#define VSYSCALL_ADDR (-10UL << 20)
 
 #endif /* _UAPI_ASM_X86_VSYSCALL_H */

arch/x86/kernel/cpu/common.c

@@ -20,6 +20,7 @@
 #include <asm/processor.h>
 #include <asm/debugreg.h>
 #include <asm/sections.h>
+#include <asm/vsyscall.h>
 #include <linux/topology.h>
 #include <linux/cpumask.h>
 #include <asm/pgtable.h>
@@ -953,6 +954,38 @@ static void vgetcpu_set_mode(void)
 	else
 		vgetcpu_mode = VGETCPU_LSL;
 }
+
+/* May not be __init: called during resume */
+static void syscall32_cpu_init(void)
+{
+	/* Load these always in case some future AMD CPU supports
+	   SYSENTER from compat mode too. */
+	wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
+	wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
+	wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target);
+
+	wrmsrl(MSR_CSTAR, ia32_cstar_target);
+}
+#endif
+
+#ifdef CONFIG_X86_32
+void enable_sep_cpu(void)
+{
+	int cpu = get_cpu();
+	struct tss_struct *tss = &per_cpu(init_tss, cpu);
+
+	if (!boot_cpu_has(X86_FEATURE_SEP)) {
+		put_cpu();
+		return;
+	}
+
+	tss->x86_tss.ss1 = __KERNEL_CS;
+	tss->x86_tss.sp1 = sizeof(struct tss_struct) + (unsigned long) tss;
+	wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0);
+	wrmsr(MSR_IA32_SYSENTER_ESP, tss->x86_tss.sp1, 0);
+	wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long) ia32_sysenter_target, 0);
+	put_cpu();
+}
 #endif
 
 void __init identify_boot_cpu(void)

arch/x86/kernel/hpet.c

@@ -74,9 +74,6 @@ static inline void hpet_writel(unsigned int d, unsigned int a)
 static inline void hpet_set_mapping(void)
 {
 	hpet_virt_address = ioremap_nocache(hpet_address, HPET_MMAP_SIZE);
-#ifdef CONFIG_X86_64
-	__set_fixmap(VSYSCALL_HPET, hpet_address, PAGE_KERNEL_VVAR_NOCACHE);
-#endif
 }
 
 static inline void hpet_clear_mapping(void)

arch/x86/kernel/signal.c

@@ -298,7 +298,8 @@ __setup_frame(int sig, struct ksignal *ksig, sigset_t *set,
 	}
 
 	if (current->mm->context.vdso)
-		restorer = VDSO32_SYMBOL(current->mm->context.vdso, sigreturn);
+		restorer = current->mm->context.vdso +
+			selected_vdso32->sym___kernel_sigreturn;
 	else
 		restorer = &frame->retcode;
 	if (ksig->ka.sa.sa_flags & SA_RESTORER)
@@ -361,7 +362,8 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 		save_altstack_ex(&frame->uc.uc_stack, regs->sp);
 
 		/* Set up to return from userspace.  */
-		restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn);
+		restorer = current->mm->context.vdso +
+			selected_vdso32->sym___kernel_sigreturn;
 		if (ksig->ka.sa.sa_flags & SA_RESTORER)
 			restorer = ksig->ka.sa.sa_restorer;
 		put_user_ex(restorer, &frame->pretcode);