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

Pull x86 vdso changes from Peter Anvin:
 "This is the revamp of the 32-bit vdso and the associated cleanups.

  This adds timekeeping support to the 32-bit vdso that we already have
  in the 64-bit vdso.  Although 32-bit x86 is legacy, it is likely to
  remain in the embedded space for a very long time to come.

  This removes the traditional COMPAT_VDSO support; the configuration
  variable is reused for simply removing the 32-bit vdso, which will
  produce correct results but obviously suffer a performance penalty.
  Only one beta version of glibc was affected, but that version was
  unfortunately included in one OpenSUSE release.

  This is not the end of the vdso cleanups.  Stefani and Andy have
  agreed to continue work for the next kernel cycle; in fact Andy has
  already produced another set of cleanups that came too late for this
  cycle.

  An incidental, but arguably important, change is that this ensures
  that unused space in the VVAR page is properly zeroed.  It wasn't
  before, and would contain whatever garbage was left in memory by BIOS
  or the bootloader.  Since the VVAR page is accessible to user space
  this had the potential of information leaks"

* 'x86-vdso-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
  x86, vdso: Fix the symbol versions on the 32-bit vDSO
  x86, vdso, build: Don't rebuild 32-bit vdsos on every make
  x86, vdso: Actually discard the .discard sections
  x86, vdso: Fix size of get_unmapped_area()
  x86, vdso: Finish removing VDSO32_PRELINK
  x86, vdso: Move more vdso definitions into vdso.h
  x86: Load the 32-bit vdso in place, just like the 64-bit vdsos
  x86, vdso32: handle 32 bit vDSO larger one page
  x86, vdso32: Disable stack protector, adjust optimizations
  x86, vdso: Zero-pad the VVAR page
  x86, vdso: Add 32 bit VDSO time support for 64 bit kernel
  x86, vdso: Add 32 bit VDSO time support for 32 bit kernel
  x86, vdso: Patch alternatives in the 32-bit VDSO
  x86, vdso: Introduce VVAR marco for vdso32
  x86, vdso: Cleanup __vdso_gettimeofday()
  x86, vdso: Replace VVAR(vsyscall_gtod_data) by gtod macro
  x86, vdso: __vdso_clock_gettime() cleanup
  x86, vdso: Revamp vclock_gettime.c
  mm: Add new func _install_special_mapping() to mmap.c
  x86, vdso: Make vsyscall_gtod_data handling x86 generic
  ...

1 files changed, 81 insertions, 220 deletions

diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c
index d6bfb876cfb0..00348980a3a6 100644
--- a/arch/x86/vdso/vdso32-setup.c
+++ b/arch/x86/vdso/vdso32-setup.c
@@ -16,6 +16,7 @@
 #include <linux/mm.h>
 #include <linux/err.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 
 #include <asm/cpufeature.h>
 #include <asm/msr.h>
@@ -25,17 +26,14 @@
 #include <asm/tlbflush.h>
 #include <asm/vdso.h>
 #include <asm/proto.h>
-
-enum {
-	VDSO_DISABLED = 0,
-	VDSO_ENABLED = 1,
-	VDSO_COMPAT = 2,
-};
+#include <asm/fixmap.h>
+#include <asm/hpet.h>
+#include <asm/vvar.h>
 
 #ifdef CONFIG_COMPAT_VDSO
-#define VDSO_DEFAULT	VDSO_COMPAT
+#define VDSO_DEFAULT	0
 #else
-#define VDSO_DEFAULT	VDSO_ENABLED
+#define VDSO_DEFAULT	1
 #endif
 
 #ifdef CONFIG_X86_64
@@ -44,13 +42,6 @@ enum {
 #endif
 
 /*
- * This is the difference between the prelinked addresses in the vDSO images
- * and the VDSO_HIGH_BASE address where CONFIG_COMPAT_VDSO places the vDSO
- * in the user address space.
- */
-#define VDSO_ADDR_ADJUST	(VDSO_HIGH_BASE - (unsigned long)VDSO32_PRELINK)
-
-/*
  * Should the kernel map a VDSO page into processes and pass its
  * address down to glibc upon exec()?
  */
@@ -60,6 +51,9 @@ static int __init vdso_setup(char *s)
 {
 	vdso_enabled = simple_strtoul(s, NULL, 0);
 
+	if (vdso_enabled > 1)
+		pr_warn("vdso32 values other than 0 and 1 are no longer allowed; vdso disabled\n");
+
 	return 1;
 }
 
@@ -76,124 +70,8 @@ __setup_param("vdso=", vdso32_setup, vdso_setup, 0);
 EXPORT_SYMBOL_GPL(vdso_enabled);
 #endif
 
-static __init void reloc_symtab(Elf32_Ehdr *ehdr,
-				unsigned offset, unsigned size)
-{
-	Elf32_Sym *sym = (void *)ehdr + offset;
-	unsigned nsym = size / sizeof(*sym);
-	unsigned i;
-
-	for(i = 0; i < nsym; i++, sym++) {
-		if (sym->st_shndx == SHN_UNDEF ||
-		    sym->st_shndx == SHN_ABS)
-			continue;  /* skip */
-
-		if (sym->st_shndx > SHN_LORESERVE) {
-			printk(KERN_INFO "VDSO: unexpected st_shndx %x\n",
-			       sym->st_shndx);
-			continue;
-		}
-
-		switch(ELF_ST_TYPE(sym->st_info)) {
-		case STT_OBJECT:
-		case STT_FUNC:
-		case STT_SECTION:
-		case STT_FILE:
-			sym->st_value += VDSO_ADDR_ADJUST;
-		}
-	}
-}
-
-static __init void reloc_dyn(Elf32_Ehdr *ehdr, unsigned offset)
-{
-	Elf32_Dyn *dyn = (void *)ehdr + offset;
-
-	for(; dyn->d_tag != DT_NULL; dyn++)
-		switch(dyn->d_tag) {
-		case DT_PLTGOT:
-		case DT_HASH:
-		case DT_STRTAB:
-		case DT_SYMTAB:
-		case DT_RELA:
-		case DT_INIT:
-		case DT_FINI:
-		case DT_REL:
-		case DT_DEBUG:
-		case DT_JMPREL:
-		case DT_VERSYM:
-		case DT_VERDEF:
-		case DT_VERNEED:
-		case DT_ADDRRNGLO ... DT_ADDRRNGHI:
-			/* definitely pointers needing relocation */
-			dyn->d_un.d_ptr += VDSO_ADDR_ADJUST;
-			break;
-
-		case DT_ENCODING ... OLD_DT_LOOS-1:
-		case DT_LOOS ... DT_HIOS-1:
-			/* Tags above DT_ENCODING are pointers if
-			   they're even */
-			if (dyn->d_tag >= DT_ENCODING &&
-			    (dyn->d_tag & 1) == 0)
-				dyn->d_un.d_ptr += VDSO_ADDR_ADJUST;
-			break;
-
-		case DT_VERDEFNUM:
-		case DT_VERNEEDNUM:
-		case DT_FLAGS_1:
-		case DT_RELACOUNT:
-		case DT_RELCOUNT:
-		case DT_VALRNGLO ... DT_VALRNGHI:
-			/* definitely not pointers */
-			break;
-
-		case OLD_DT_LOOS ... DT_LOOS-1:
-		case DT_HIOS ... DT_VALRNGLO-1:
-		default:
-			if (dyn->d_tag > DT_ENCODING)
-				printk(KERN_INFO "VDSO: unexpected DT_tag %x\n",
-				       dyn->d_tag);
-			break;
-		}
-}
-
-static __init void relocate_vdso(Elf32_Ehdr *ehdr)
-{
-	Elf32_Phdr *phdr;
-	Elf32_Shdr *shdr;
-	int i;
-
-	BUG_ON(memcmp(ehdr->e_ident, ELFMAG, SELFMAG) != 0 ||
-	       !elf_check_arch_ia32(ehdr) ||
-	       ehdr->e_type != ET_DYN);
-
-	ehdr->e_entry += VDSO_ADDR_ADJUST;
-
-	/* rebase phdrs */
-	phdr = (void *)ehdr + ehdr->e_phoff;
-	for (i = 0; i < ehdr->e_phnum; i++) {
-		phdr[i].p_vaddr += VDSO_ADDR_ADJUST;
-
-		/* relocate dynamic stuff */
-		if (phdr[i].p_type == PT_DYNAMIC)
-			reloc_dyn(ehdr, phdr[i].p_offset);
-	}
-
-	/* rebase sections */
-	shdr = (void *)ehdr + ehdr->e_shoff;
-	for(i = 0; i < ehdr->e_shnum; i++) {
-		if (!(shdr[i].sh_flags & SHF_ALLOC))
-			continue;
-
-		shdr[i].sh_addr += VDSO_ADDR_ADJUST;
-
-		if (shdr[i].sh_type == SHT_SYMTAB ||
-		    shdr[i].sh_type == SHT_DYNSYM)
-			reloc_symtab(ehdr, shdr[i].sh_offset,
-				     shdr[i].sh_size);
-	}
-}
-
-static struct page *vdso32_pages[1];
+static struct page **vdso32_pages;
+static unsigned vdso32_size;
 
 #ifdef CONFIG_X86_64
 
@@ -212,12 +90,6 @@ void syscall32_cpu_init(void)
 	wrmsrl(MSR_CSTAR, ia32_cstar_target);
 }
 
-#define compat_uses_vma		1
-
-static inline void map_compat_vdso(int map)
-{
-}
-
 #else  /* CONFIG_X86_32 */
 
 #define vdso32_sysenter()	(boot_cpu_has(X86_FEATURE_SEP))
@@ -241,64 +113,36 @@ void enable_sep_cpu(void)
 	put_cpu();	
 }
 
-static struct vm_area_struct gate_vma;
-
-static int __init gate_vma_init(void)
-{
-	gate_vma.vm_mm = NULL;
-	gate_vma.vm_start = FIXADDR_USER_START;
-	gate_vma.vm_end = FIXADDR_USER_END;
-	gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC;
-	gate_vma.vm_page_prot = __P101;
-
-	return 0;
-}
-
-#define compat_uses_vma		0
-
-static void map_compat_vdso(int map)
-{
-	static int vdso_mapped;
-
-	if (map == vdso_mapped)
-		return;
-
-	vdso_mapped = map;
-
-	__set_fixmap(FIX_VDSO, page_to_pfn(vdso32_pages[0]) << PAGE_SHIFT,
-		     map ? PAGE_READONLY_EXEC : PAGE_NONE);
-
-	/* flush stray tlbs */
-	flush_tlb_all();
-}
-
 #endif	/* CONFIG_X86_64 */
 
 int __init sysenter_setup(void)
 {
-	void *syscall_page = (void *)get_zeroed_page(GFP_ATOMIC);
-	const void *vsyscall;
-	size_t vsyscall_len;
-
-	vdso32_pages[0] = virt_to_page(syscall_page);
-
-#ifdef CONFIG_X86_32
-	gate_vma_init();
-#endif
+	char *vdso32_start, *vdso32_end;
+	int npages, i;
 
+#ifdef CONFIG_COMPAT
 	if (vdso32_syscall()) {
-		vsyscall = &vdso32_syscall_start;
-		vsyscall_len = &vdso32_syscall_end - &vdso32_syscall_start;
-	} else if (vdso32_sysenter()){
-		vsyscall = &vdso32_sysenter_start;
-		vsyscall_len = &vdso32_sysenter_end - &vdso32_sysenter_start;
+		vdso32_start = vdso32_syscall_start;
+		vdso32_end = vdso32_syscall_end;
+		vdso32_pages = vdso32_syscall_pages;
+	} else
+#endif
+	if (vdso32_sysenter()) {
+		vdso32_start = vdso32_sysenter_start;
+		vdso32_end = vdso32_sysenter_end;
+		vdso32_pages = vdso32_sysenter_pages;
 	} else {
-		vsyscall = &vdso32_int80_start;
-		vsyscall_len = &vdso32_int80_end - &vdso32_int80_start;
+		vdso32_start = vdso32_int80_start;
+		vdso32_end = vdso32_int80_end;
+		vdso32_pages = vdso32_int80_pages;
 	}
 
-	memcpy(syscall_page, vsyscall, vsyscall_len);
-	relocate_vdso(syscall_page);
+	npages = ((vdso32_end - vdso32_start) + PAGE_SIZE - 1) / PAGE_SIZE;
+	vdso32_size = npages << PAGE_SHIFT;
+	for (i = 0; i < npages; i++)
+		vdso32_pages[i] = virt_to_page(vdso32_start + i*PAGE_SIZE);
+
+	patch_vdso32(vdso32_start, vdso32_size);
 
 	return 0;
 }
@@ -309,48 +153,73 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	struct mm_struct *mm = current->mm;
 	unsigned long addr;
 	int ret = 0;
-	bool compat;
+	struct vm_area_struct *vma;
 
 #ifdef CONFIG_X86_X32_ABI
 	if (test_thread_flag(TIF_X32))
 		return x32_setup_additional_pages(bprm, uses_interp);
 #endif
 
-	if (vdso_enabled == VDSO_DISABLED)
+	if (vdso_enabled != 1)  /* Other values all mean "disabled" */
 		return 0;
 
 	down_write(&mm->mmap_sem);
 
-	/* Test compat mode once here, in case someone
-	   changes it via sysctl */
-	compat = (vdso_enabled == VDSO_COMPAT);
+	addr = get_unmapped_area(NULL, 0, vdso32_size + VDSO_OFFSET(VDSO_PREV_PAGES), 0, 0);
+	if (IS_ERR_VALUE(addr)) {
+		ret = addr;
+		goto up_fail;
+	}
+
+	addr += VDSO_OFFSET(VDSO_PREV_PAGES);
 
-	map_compat_vdso(compat);
+	current->mm->context.vdso = (void *)addr;
 
-	if (compat)
-		addr = VDSO_HIGH_BASE;
-	else {
-		addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0);
-		if (IS_ERR_VALUE(addr)) {
-			ret = addr;
-			goto up_fail;
-		}
+	/*
+	 * MAYWRITE to allow gdb to COW and set breakpoints
+	 */
+	ret = install_special_mapping(mm,
+			addr,
+			vdso32_size,
+			VM_READ|VM_EXEC|
+			VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
+			vdso32_pages);
+
+	if (ret)
+		goto up_fail;
+
+	vma = _install_special_mapping(mm,
+			addr -  VDSO_OFFSET(VDSO_PREV_PAGES),
+			VDSO_OFFSET(VDSO_PREV_PAGES),
+			VM_READ,
+			NULL);
+
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
+		goto up_fail;
 	}
 
-	current->mm->context.vdso = (void *)addr;
+	ret = remap_pfn_range(vma,
+		addr - VDSO_OFFSET(VDSO_VVAR_PAGE),
+		__pa_symbol(&__vvar_page) >> PAGE_SHIFT,
+		PAGE_SIZE,
+		PAGE_READONLY);
+
+	if (ret)
+		goto up_fail;
 
-	if (compat_uses_vma || !compat) {
-		/*
-		 * MAYWRITE to allow gdb to COW and set breakpoints
-		 */
-		ret = install_special_mapping(mm, addr, PAGE_SIZE,
-					      VM_READ|VM_EXEC|
-					      VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
-					      vdso32_pages);
+#ifdef CONFIG_HPET_TIMER
+	if (hpet_address) {
+		ret = io_remap_pfn_range(vma,
+			addr - VDSO_OFFSET(VDSO_HPET_PAGE),
+			hpet_address >> PAGE_SHIFT,
+			PAGE_SIZE,
+			pgprot_noncached(PAGE_READONLY));
 
 		if (ret)
 			goto up_fail;
 	}
+#endif
 
 	current_thread_info()->sysenter_return =
 		VDSO32_SYMBOL(addr, SYSENTER_RETURN);
@@ -411,20 +280,12 @@ const char *arch_vma_name(struct vm_area_struct *vma)
 
 struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
 {
-	/*
-	 * Check to see if the corresponding task was created in compat vdso
-	 * mode.
-	 */
-	if (mm && mm->context.vdso == (void *)VDSO_HIGH_BASE)
-		return &gate_vma;
 	return NULL;
 }
 
 int in_gate_area(struct mm_struct *mm, unsigned long addr)
 {
-	const struct vm_area_struct *vma = get_gate_vma(mm);
-
-	return vma && addr >= vma->vm_start && addr < vma->vm_end;
+	return 0;
 }
 
 int in_gate_area_no_mm(unsigned long addr)