Clean up and unify the vDSO

index 597ac15..6ef98c5 100644
@@ -355,6 +355,12 @@ void __init early_ioremap_init(void)
 {
 	pmd_t *pmd;
 
+#ifdef CONFIG_X86_64
+	BUILD_BUG_ON((fix_to_virt(0) + PAGE_SIZE) & ((1 << PMD_SHIFT) - 1));
+#else
+	WARN_ON((fix_to_virt(0) + PAGE_SIZE) & ((1 << PMD_SHIFT) - 1));
+#endif
+
 	early_ioremap_setup();
 
 	pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN));

index c96314a..5f8bdda 100644
@@ -449,9 +449,9 @@ void __init reserve_top_address(unsigned long reserve)
 {
 #ifdef CONFIG_X86_32
 	BUG_ON(fixmaps_set > 0);
-	printk(KERN_INFO "Reserving virtual address space above 0x%08x\n",
-	       (int)-reserve);
-	__FIXADDR_TOP = -reserve - PAGE_SIZE;
+	__FIXADDR_TOP = round_down(-reserve, 1 << PMD_SHIFT) - PAGE_SIZE;
+	printk(KERN_INFO "Reserving virtual address space above 0x%08lx (rounded to 0x%08lx)\n",
+	       -reserve, __FIXADDR_TOP + PAGE_SIZE);
 #endif
 }
 

index 2c71182..e96df2c 100644
@@ -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 */
 

@@ -292,14 +297,15 @@ do {									\
 
 #define ARCH_DLINFO							\
 do {									\
-	if (vdso_enabled)						\
+	if (vdso64_enabled)						\
 		NEW_AUX_ENT(AT_SYSINFO_EHDR,				\
 			    (unsigned long)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);	\
 } while (0)

@@ -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)
 

index af91901..916cda4 100644
@@ -12,7 +12,7 @@
 #include <asm/page.h>
 #include <linux/init.h>
 
-unsigned int __read_mostly vdso_enabled = 1;
+static unsigned int __read_mostly vdso_enabled = 1;
 unsigned long um_vdso_addr;
 
 extern unsigned long task_size;

index 0034898..5a657d9 100644
@@ -37,7 +37,6 @@
 #endif
 
 #ifdef CONFIG_X86_64
-#define vdso_enabled			sysctl_vsyscall32
 #define arch_setup_additional_pages	syscall32_setup_pages
 #endif
 

@@ -45,13 +44,13 @@
  * Should the kernel map a VDSO page into processes and pass its
  * address down to glibc upon exec()?
  */
-unsigned int __read_mostly vdso_enabled = VDSO_DEFAULT;
+unsigned int __read_mostly vdso32_enabled = VDSO_DEFAULT;
 
-static int __init vdso_setup(char *s)
+static int __init vdso32_setup(char *s)
 {
-	vdso_enabled = simple_strtoul(s, NULL, 0);
+	vdso32_enabled = simple_strtoul(s, NULL, 0);
 
-	if (vdso_enabled > 1)
+	if (vdso32_enabled > 1)
 		pr_warn("vdso32 values other than 0 and 1 are no longer allowed; vdso disabled\n");
 
 	return 1;

@@ -62,12 +61,10 @@ static int __init vdso_setup(char *s)
  * behavior on both 64-bit and 32-bit kernels.
  * On 32-bit kernels, vdso=[012] means the same thing.
  */
-__setup("vdso32=", vdso_setup);
+__setup("vdso32=", vdso32_setup);
 
 #ifdef CONFIG_X86_32
-__setup_param("vdso=", vdso32_setup, vdso_setup, 0);
-
-EXPORT_SYMBOL_GPL(vdso_enabled);
+__setup_param("vdso=", vdso_setup, vdso32_setup, 0);
 #endif
 
 static struct page **vdso32_pages;

@@ -160,7 +157,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 		return x32_setup_additional_pages(bprm, uses_interp);
 #endif
 
-	if (vdso_enabled != 1)  /* Other values all mean "disabled" */
+	if (vdso32_enabled != 1)  /* Other values all mean "disabled" */
 		return 0;
 
 	down_write(&mm->mmap_sem);

@@ -244,7 +241,7 @@ subsys_initcall(sysenter_setup);
 static struct ctl_table abi_table2[] = {
 	{
 		.procname	= "vsyscall32",
-		.data		= &sysctl_vsyscall32,
+		.data		= &vdso32_enabled,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec

index 1ad1026..8b79039 100644
@@ -17,7 +17,7 @@
 #include <asm/page.h>
 
 #if defined(CONFIG_X86_64)
-unsigned int __read_mostly vdso_enabled = 1;
+unsigned int __read_mostly vdso64_enabled = 1;
 
 DECLARE_VDSO_IMAGE(vdso);
 extern unsigned short vdso_sync_cpuid;

@@ -160,7 +160,7 @@ static int setup_additional_pages(struct linux_binprm *bprm,
 	unsigned long addr;
 	int ret;
 
-	if (!vdso_enabled)
+	if (!vdso64_enabled)
 		return 0;
 
 	down_write(&mm->mmap_sem);

@@ -203,7 +203,7 @@ int x32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 
 static __init int vdso_setup(char *s)
 {
-	vdso_enabled = simple_strtoul(s, NULL, 0);
+	vdso64_enabled = simple_strtoul(s, NULL, 0);
 	return 0;
 }
 __setup("vdso=", vdso_setup);

index 74f5b58..420d77a 100644
@@ -1418,8 +1418,13 @@ static struct ctl_table vm_table[] = {
    (defined(CONFIG_SUPERH) && defined(CONFIG_VSYSCALL))
 	{
 		.procname	= "vdso_enabled",
+#ifdef CONFIG_X86_32
+		.data		= &vdso32_enabled,
+		.maxlen		= sizeof(vdso32_enabled),
+#else
 		.data		= &vdso_enabled,
 		.maxlen		= sizeof(vdso_enabled),
+#endif
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 		.extra1		= &zero,

index 6fd3fd7..a90f897 100644
@@ -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);
 

index a135239..7c65b46 100644
@@ -953,6 +953,38 @@ 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)

index 5a657d9..9c78d5b 100644
@@ -75,41 +75,11 @@ static unsigned vdso32_size;
 #define	vdso32_sysenter()	(boot_cpu_has(X86_FEATURE_SYSENTER32))
 #define	vdso32_syscall()	(boot_cpu_has(X86_FEATURE_SYSCALL32))
 
-/* May not be __init: called during resume */
-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);
-}
-
 #else  /* CONFIG_X86_32 */
 
 #define vdso32_sysenter()	(boot_cpu_has(X86_FEATURE_SEP))
 #define vdso32_syscall()	(0)
 
-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	/* CONFIG_X86_64 */
 
 int __init sysenter_setup(void)

index 2206757..f9e181a 100644
@@ -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);
 
 		/*

index e96df2c..65b21bc 100644
@@ -299,7 +299,7 @@ do {									\
 do {									\
 	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. */

@@ -307,7 +307,7 @@ do {									\
 do {									\
 	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

@@ -325,7 +325,8 @@ 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;
 

index 5f55e69..876e74e 100644
@@ -18,7 +18,7 @@ typedef struct {
 #endif
 
 	struct mutex lock;
-	void *vdso;
+	void __user *vdso;
 } mm_context_t;
 
 #ifdef CONFIG_SMP

88 lines not on this page · raw message

index 9e5de68..a0da58d 100644
@@ -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);

index f35c66c..5638496 100644
@@ -1223,7 +1223,8 @@ int in_gate_area_no_mm(unsigned long addr)
 
 const char *arch_vma_name(struct vm_area_struct *vma)
 {
-	if (vma->vm_mm && vma->vm_start == (long)vma->vm_mm->context.vdso)
+	if (vma->vm_mm && vma->vm_start ==
+	    (long __force)vma->vm_mm->context.vdso)
 		return "[vdso]";
 	if (vma == &gate_vma)
 		return "[vsyscall]";

index 16d6861..091554c 100644
@@ -154,7 +154,7 @@ notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
 	asm(
 		"mov %%ebx, %%edx \n"
 		"mov %2, %%ebx \n"
-		"call VDSO32_vsyscall \n"
+		"call __kernel_vsyscall \n"
 		"mov %%edx, %%ebx \n"
 		: "=a" (ret)
 		: "0" (__NR_clock_gettime), "g" (clock), "c" (ts)

@@ -169,7 +169,7 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
 	asm(
 		"mov %%ebx, %%edx \n"
 		"mov %2, %%ebx \n"
-		"call VDSO32_vsyscall \n"
+		"call __kernel_vsyscall \n"
 		"mov %%edx, %%ebx \n"
 		: "=a" (ret)
 		: "0" (__NR_gettimeofday), "g" (tv), "c" (tz)

142 lines not on this page · raw message

137 lines not on this page · raw message

97 lines not on this page · raw message

137 lines not on this page · raw message

index 0982233..7225a95 100644
@@ -516,10 +516,17 @@ char * __init xen_memory_setup(void)
 static void __init fiddle_vdso(void)
 {
 #ifdef CONFIG_X86_32
+	/*
+	 * This could be called before selected_vdso32 is initialized, so
+	 * just fiddle with both possible images.  vdso_image_32_syscall
+	 * can't be selected, since it only exists on 64-bit systems.
+	 */
 	u32 *mask;
-	mask = VDSO32_SYMBOL(&vdso32_int80_start, NOTE_MASK);
+	mask = vdso_image_32_int80.data +
+		vdso_image_32_int80.sym_VDSO32_NOTE_MASK;
 	*mask |= 1 << VDSO_NOTE_NONEGSEG_BIT;
-	mask = VDSO32_SYMBOL(&vdso32_sysenter_start, NOTE_MASK);
+	mask = vdso_image_32_sysenter.data +
+		vdso_image_32_sysenter.sym_VDSO32_NOTE_MASK;
 	*mask |= 1 << VDSO_NOTE_NONEGSEG_BIT;
 #endif
 }

index 81edd1e..fe8bfbf 100644
@@ -14,6 +14,8 @@
 #include <linux/elf.h>
 #include <linux/types.h>
 
+const char *outfilename;
+
 /* Symbols that we need in vdso2c. */
 enum {
 	sym_vvar_page,

@@ -44,6 +46,7 @@ static void fail(const char *format, ...)
 	va_start(ap, format);
 	fprintf(stderr, "Error: ");
 	vfprintf(stderr, format, ap);
+	unlink(outfilename);
 	exit(1);
 	va_end(ap);
 }

@@ -82,17 +85,16 @@ static void fail(const char *format, ...)
 #undef Elf_Sym
 #undef Elf_Dyn
 
-static int go(void *addr, size_t len, FILE *outfile, const char *name)
+static void go(void *addr, size_t len, FILE *outfile, const char *name)
 {
 	Elf64_Ehdr *hdr = (Elf64_Ehdr *)addr;
 
 	if (hdr->e_ident[EI_CLASS] == ELFCLASS64) {
-		return go64(addr, len, outfile, name);
+		go64(addr, len, outfile, name);
 	} else if (hdr->e_ident[EI_CLASS] == ELFCLASS32) {
-		return go32(addr, len, outfile, name);
+		go32(addr, len, outfile, name);
 	} else {
-		fprintf(stderr, "Error: unknown ELF class\n");
-		return 1;
+		fail("unknown ELF class\n");
 	}
 }
 

@@ -102,7 +104,6 @@ int main(int argc, char **argv)
 	off_t len;
 	void *addr;
 	FILE *outfile;
-	int ret;
 	char *name, *tmp;
 	int namelen;
 

@@ -143,14 +144,15 @@ int main(int argc, char **argv)
 	if (addr == MAP_FAILED)
 		err(1, "mmap");
 
-	outfile = fopen(argv[2], "w");
+	outfilename = argv[2];
+	outfile = fopen(outfilename, "w");
 	if (!outfile)
 		err(1, "%s", argv[2]);
 
-	ret = go(addr, (size_t)len, outfile, name);
+	go(addr, (size_t)len, outfile, name);
 
 	munmap(addr, len);
 	fclose(outfile);
 
-	return ret;
+	return 0;
 }

index 3dcc61e..26a7c1f 100644
@@ -4,7 +4,7 @@
  * are built for 32-bit userspace.
  */
 
-static int GOFUNC(void *addr, size_t len, FILE *outfile, const char *name)
+static void GOFUNC(void *addr, size_t len, FILE *outfile, const char *name)
 {
 	int found_load = 0;
 	unsigned long load_size = -1;  /* Work around bogus warning */

@@ -62,10 +62,8 @@ static int GOFUNC(void *addr, size_t len, FILE *outfile, const char *name)
 			alt_sec = sh;
 	}
 
-	if (!symtab_hdr) {
+	if (!symtab_hdr)
 		fail("no symbol table\n");
-		return 1;
-	}
 
 	strtab_hdr = addr + hdr->e_shoff +
 		hdr->e_shentsize * symtab_hdr->sh_link;

@@ -112,7 +110,7 @@ static int GOFUNC(void *addr, size_t len, FILE *outfile, const char *name)
 
 	if (!name) {
 		fwrite(addr, load_size, 1, outfile);
-		return 0;
+		return;
 	}
 
 	fprintf(outfile, "/* AUTOMATICALLY GENERATED -- DO NOT EDIT */\n\n");

@@ -152,6 +150,4 @@ static int GOFUNC(void *addr, size_t len, FILE *outfile, const char *name)
 				required_syms[i], syms[i]);
 	}
 	fprintf(outfile, "};\n");
-
-	return 0;
 }

index fe8bfbf..de19ced 100644
@@ -51,6 +51,21 @@ static void fail(const char *format, ...)
 	va_end(ap);
 }
 
+/*
+ * Evil macros to do a little-endian read.
+ */
+#define __GET_TYPE(x, type, bits, ifnot)				\
+	__builtin_choose_expr(						\
+		__builtin_types_compatible_p(typeof(x), type),		\
+		le##bits##toh((x)), ifnot)
+
+extern void bad_get(uint64_t);
+
+#define GET(x)								\
+	__GET_TYPE((x), __u32, 32, __GET_TYPE((x), __u64, 64,		\
+	__GET_TYPE((x), __s32, 32, __GET_TYPE((x), __s64, 64,		\
+	__GET_TYPE((x), __u16, 16, bad_get(x))))))
+
 #define NSYMS (sizeof(required_syms) / sizeof(required_syms[0]))
 
 #define BITS 64

108 lines not on this page · raw message

index 81edd1e..fe8bfbf 100644
@@ -14,6 +14,8 @@
 #include <linux/elf.h>
 #include <linux/types.h>
 
+const char *outfilename;
+
 /* Symbols that we need in vdso2c. */
 enum {
 	sym_vvar_page,

@@ -44,6 +46,7 @@ static void fail(const char *format, ...)
 	va_start(ap, format);
 	fprintf(stderr, "Error: ");
 	vfprintf(stderr, format, ap);
+	unlink(outfilename);
 	exit(1);
 	va_end(ap);
 }

@@ -82,17 +85,16 @@ static void fail(const char *format, ...)
 #undef Elf_Sym
 #undef Elf_Dyn
 
-static int go(void *addr, size_t len, FILE *outfile, const char *name)
+static void go(void *addr, size_t len, FILE *outfile, const char *name)
 {
 	Elf64_Ehdr *hdr = (Elf64_Ehdr *)addr;
 
 	if (hdr->e_ident[EI_CLASS] == ELFCLASS64) {
-		return go64(addr, len, outfile, name);
+		go64(addr, len, outfile, name);
 	} else if (hdr->e_ident[EI_CLASS] == ELFCLASS32) {
-		return go32(addr, len, outfile, name);
+		go32(addr, len, outfile, name);
 	} else {
-		fprintf(stderr, "Error: unknown ELF class\n");
-		return 1;
+		fail("unknown ELF class\n");
 	}
 }
 

@@ -102,7 +104,6 @@ int main(int argc, char **argv)
 	off_t len;
 	void *addr;
 	FILE *outfile;
-	int ret;
 	char *name, *tmp;
 	int namelen;
 

@@ -143,14 +144,15 @@ int main(int argc, char **argv)
 	if (addr == MAP_FAILED)
 		err(1, "mmap");
 
-	outfile = fopen(argv[2], "w");
+	outfilename = argv[2];
+	outfile = fopen(outfilename, "w");
 	if (!outfile)
 		err(1, "%s", argv[2]);
 
-	ret = go(addr, (size_t)len, outfile, name);
+	go(addr, (size_t)len, outfile, name);
 
 	munmap(addr, len);
 	fclose(outfile);
 
-	return ret;
+	return 0;
 }

index 3dcc61e..26a7c1f 100644
@@ -4,7 +4,7 @@
  * are built for 32-bit userspace.
  */
 
-static int GOFUNC(void *addr, size_t len, FILE *outfile, const char *name)
+static void GOFUNC(void *addr, size_t len, FILE *outfile, const char *name)
 {
 	int found_load = 0;
 	unsigned long load_size = -1;  /* Work around bogus warning */

@@ -62,10 +62,8 @@ static int GOFUNC(void *addr, size_t len, FILE *outfile, const char *name)
 			alt_sec = sh;
 	}
 
-	if (!symtab_hdr) {
+	if (!symtab_hdr)
 		fail("no symbol table\n");
-		return 1;
-	}
 
 	strtab_hdr = addr + hdr->e_shoff +
 		hdr->e_shentsize * symtab_hdr->sh_link;

@@ -112,7 +110,7 @@ static int GOFUNC(void *addr, size_t len, FILE *outfile, const char *name)
 
 	if (!name) {
 		fwrite(addr, load_size, 1, outfile);
-		return 0;
+		return;
 	}
 
 	fprintf(outfile, "/* AUTOMATICALLY GENERATED -- DO NOT EDIT */\n\n");

@@ -152,6 +150,4 @@ static int GOFUNC(void *addr, size_t len, FILE *outfile, const char *name)
 				required_syms[i], syms[i]);
 	}
 	fprintf(outfile, "};\n");
-
-	return 0;
 }

index fe8bfbf..de19ced 100644
@@ -51,6 +51,21 @@ static void fail(const char *format, ...)
 	va_end(ap);
 }
 
+/*
+ * Evil macros to do a little-endian read.
+ */
+#define __GET_TYPE(x, type, bits, ifnot)				\
+	__builtin_choose_expr(						\
+		__builtin_types_compatible_p(typeof(x), type),		\
+		le##bits##toh((x)), ifnot)
+
+extern void bad_get(uint64_t);
+
+#define GET(x)								\
+	__GET_TYPE((x), __u32, 32, __GET_TYPE((x), __u64, 64,		\
+	__GET_TYPE((x), __s32, 32, __GET_TYPE((x), __s64, 64,		\
+	__GET_TYPE((x), __u16, 16, bad_get(x))))))
+
 #define NSYMS (sizeof(required_syms) / sizeof(required_syms[0]))
 
 #define BITS 64

119 lines not on this page · raw message

index 65b21bc..1a055c8 100644
@@ -333,11 +333,9 @@ 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

index 389fe2c..d0a2c90 100644
@@ -14,6 +14,10 @@ struct vdso_image {
 
 	unsigned long alt, alt_len;
 
+	unsigned long sym_end_mapping;  /* Total size of the mapping */
+
+	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;

deleted file mode 100644
index 7efb701..0000000
@@ -1,11 +0,0 @@
-#ifndef _ASM_X86_VDSO32_H
-#define _ASM_X86_VDSO32_H
-
-#define VDSO_BASE_PAGE	0
-#define VDSO_VVAR_PAGE	1
-#define VDSO_HPET_PAGE	2
-#define VDSO_PAGES	3
-#define VDSO_PREV_PAGES	2
-#define VDSO_OFFSET(x)	((x) * PAGE_SIZE)
-
-#endif

index 976e8e4..81edd1e 100644
@@ -15,7 +15,21 @@
 #include <linux/types.h>
 
 /* Symbols that we need in vdso2c. */
+enum {
+	sym_vvar_page,
+	sym_hpet_page,
+	sym_end_mapping,
+};
+
+const int special_pages[] = {
+	sym_vvar_page,
+	sym_hpet_page,
+};
+
 char const * const required_syms[] = {
+	[sym_vvar_page] = "vvar_page",
+	[sym_hpet_page] = "hpet_page",
+	[sym_end_mapping] = "end_mapping",
 	"VDSO32_NOTE_MASK",
 	"VDSO32_SYSENTER_RETURN",
 	"__kernel_vsyscall",

index 9276e52..ed2e894 100644
@@ -87,6 +87,23 @@ static int GOFUNC(void *addr, size_t len, FILE *outfile, const char *name)
 		}
 	}
 
+	/* Validate mapping addresses. */
+	for (i = 0; i < sizeof(special_pages) / sizeof(special_pages[0]); i++) {
+		if (!syms[i])
+			continue;  /* The mapping isn't used; ignore it. */
+
+		if (syms[i] % 4096)
+			fail("%s must be a multiple of 4096\n",
+			     required_syms[i]);
+		if (syms[i] < data_size)
+			fail("%s must be after the text mapping\n",
+			     required_syms[i]);
+		if (syms[sym_end_mapping] < syms[i] + 4096)
+			fail("%s overruns end_mapping\n", required_syms[i]);
+	}
+	if (syms[sym_end_mapping] % 4096)
+		fail("end_mapping must be a multiple of 4096\n");
+
 	/* Remove sections. */
 	hdr->e_shoff = 0;
 	hdr->e_shentsize = 0;

136 lines not on this page · raw message

189 lines not on this page · raw message

index 43f482a..b0910f9 100644
@@ -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,

index 081d909..5d2b9ad 100644
@@ -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

index 85dc1b3..b97dd6e 100644
@@ -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 */

index 7c65b46..2cbbf88 100644
@@ -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>

index 8d80ae0..bbc15a0 100644
@@ -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)

index 8b3b3eb..ea5b570 100644
@@ -91,7 +91,7 @@ static int addr_to_vsyscall_nr(unsigned long addr)
 {
 	int nr;
 
-	if ((addr & ~0xC00UL) != VSYSCALL_START)
+	if ((addr & ~0xC00UL) != VSYSCALL_ADDR)
 		return -EINVAL;
 
 	nr = (addr & 0xC00UL) >> 10;

@@ -330,24 +330,17 @@ void __init map_vsyscall(void)
 {
 	extern char __vsyscall_page;
 	unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
-	unsigned long physaddr_vvar_page = __pa_symbol(&__vvar_page);
 
-	__set_fixmap(VSYSCALL_FIRST_PAGE, physaddr_vsyscall,
+	__set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
 		     vsyscall_mode == NATIVE
 		     ? PAGE_KERNEL_VSYSCALL
 		     : PAGE_KERNEL_VVAR);
-	BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_FIRST_PAGE) !=
-		     (unsigned long)VSYSCALL_START);
-
-	__set_fixmap(VVAR_PAGE, physaddr_vvar_page, PAGE_KERNEL_VVAR);
-	BUILD_BUG_ON((unsigned long)__fix_to_virt(VVAR_PAGE) !=
-		     (unsigned long)VVAR_ADDRESS);
+	BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) !=
+		     (unsigned long)VSYSCALL_ADDR);
 }
 
 static int __init vsyscall_init(void)
 {
-	BUG_ON(VSYSCALL_ADDR(0) != __fix_to_virt(VSYSCALL_FIRST_PAGE));
-
 	cpu_notifier_register_begin();
 
 	on_each_cpu(cpu_vsyscall_init, NULL, 1);

index 8e57229..858b47b 100644
@@ -18,7 +18,8 @@
 #include <asm/traps.h>			/* dotraplinkage, ...		*/
 #include <asm/pgalloc.h>		/* pgd_*(), ...			*/
 #include <asm/kmemcheck.h>		/* kmemcheck_*(), ...		*/
-#include <asm/fixmap.h>			/* VSYSCALL_START		*/
+#include <asm/fixmap.h>			/* VSYSCALL_ADDR		*/
+#include <asm/vsyscall.h>		/* emulate_vsyscall		*/
 
 #define CREATE_TRACE_POINTS
 #include <asm/trace/exceptions.h>

@@ -771,7 +772,7 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
 		 * emulation.
 		 */
 		if (unlikely((error_code & PF_INSTR) &&
-			     ((address & ~0xfff) == VSYSCALL_START))) {
+			     ((address & ~0xfff) == VSYSCALL_ADDR))) {
 			if (emulate_vsyscall(regs, address))
 				return;
 		}

index 5638496..6f88184 100644
@@ -1055,8 +1055,8 @@ void __init mem_init(void)
 	after_bootmem = 1;
 
 	/* Register memory areas for /proc/kcore */
-	kclist_add(&kcore_vsyscall, (void *)VSYSCALL_START,
-			 VSYSCALL_END - VSYSCALL_START, KCORE_OTHER);
+	kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR,
+			 PAGE_SIZE, KCORE_OTHER);
 
 	mem_init_print_info(NULL);
 }

@@ -1186,8 +1186,8 @@ int kern_addr_valid(unsigned long addr)
  * not need special handling anymore:
  */
 static struct vm_area_struct gate_vma = {
-	.vm_start	= VSYSCALL_START,
-	.vm_end		= VSYSCALL_START + (VSYSCALL_MAPPED_PAGES * PAGE_SIZE),
+	.vm_start	= VSYSCALL_ADDR,
+	.vm_end		= VSYSCALL_ADDR + PAGE_SIZE,
 	.vm_page_prot	= PAGE_READONLY_EXEC,
 	.vm_flags	= VM_READ | VM_EXEC
 };

@@ -1218,7 +1218,7 @@ int in_gate_area(struct mm_struct *mm, unsigned long addr)
  */
 int in_gate_area_no_mm(unsigned long addr)
 {
-	return (addr >= VSYSCALL_START) && (addr < VSYSCALL_END);
+	return (addr & PAGE_MASK) == VSYSCALL_ADDR;
 }
 
 const char *arch_vma_name(struct vm_area_struct *vma)

index 091554c..b2e4f49 100644
@@ -30,9 +30,12 @@ extern int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz);
 extern time_t __vdso_time(time_t *t);
 
 #ifdef CONFIG_HPET_TIMER
-static inline u32 read_hpet_counter(const volatile void *addr)
+extern u8 hpet_page
+	__attribute__((visibility("hidden")));
+
+static notrace cycle_t vread_hpet(void)
 {
-	return *(const volatile u32 *) (addr + HPET_COUNTER);
+	return *(const volatile u32 *)(&hpet_page + HPET_COUNTER);
 }
 #endif
 

@@ -43,11 +46,6 @@ static inline u32 read_hpet_counter(const volatile void *addr)
 #include <asm/fixmap.h>
 #include <asm/pvclock.h>
 
-static notrace cycle_t vread_hpet(void)
-{
-	return read_hpet_counter((const void *)fix_to_virt(VSYSCALL_HPET));
-}
-
 notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
 {
 	long ret;

@@ -137,16 +135,6 @@ static notrace cycle_t vread_pvclock(int *mode)
 
 #else
 
-extern u8 hpet_page
-	__attribute__((visibility("hidden")));
-
-#ifdef CONFIG_HPET_TIMER
-static notrace cycle_t vread_hpet(void)
-{
-	return read_hpet_counter((const void *)(&hpet_page));
-}
-#endif
-
 notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
 {
 	long ret;

index 86e02ea..3060568 100644
@@ -1494,7 +1494,7 @@ static int xen_pgd_alloc(struct mm_struct *mm)
 		page->private = (unsigned long)user_pgd;
 
 		if (user_pgd != NULL) {
-			user_pgd[pgd_index(VSYSCALL_START)] =
+			user_pgd[pgd_index(VSYSCALL_ADDR)] =
 				__pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE);
 			ret = 0;
 		}

@@ -2062,8 +2062,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 	case FIX_KMAP_BEGIN ... FIX_KMAP_END:
 # endif
 #else
-	case VSYSCALL_LAST_PAGE ... VSYSCALL_FIRST_PAGE:
-	case VVAR_PAGE:
+	case VSYSCALL_PAGE:
 #endif
 	case FIX_TEXT_POKE0:
 	case FIX_TEXT_POKE1:

@@ -2104,8 +2103,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 #ifdef CONFIG_X86_64
 	/* Replicate changes to map the vsyscall page into the user
 	   pagetable vsyscall mapping. */
-	if ((idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) ||
-	    idx == VVAR_PAGE) {
+	if (idx == VSYSCALL_PAGE) {
 		unsigned long vaddr = __fix_to_virt(idx);
 		set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte);
 	}