[PATCH v2] x86: Remove compat vdso support

From: Andy Lutomirski
Date: Mon Mar 10 2014 - 21:03:16 EST

The compat vDSO is a complicated hack that's needed to maintain
compatibility with a small range of never-released glibc versions.

This removes it and replaces it with a much simpler hack: a config
option to disable the 32-bit vDSO by default.

Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
---

This is a bit of an abuse of the no-breaking-userspace policy. It
breaks OpenSUSE 9. The breakage can be fixed up with a config option or
with a boot parameter, though.

This applies to Linus' tree. It does not apply to tip/x86/vdso (and IMO
if it's accepted then the 32-bit vDSO stuff should be rebased on top,
since a couple of the 32-bit vDSO changes will be unnecessary).

I've tested this lightly in 32-bit and 64-bit configurations. It might
be nice to get this into -next to see what shakes loose. The behavior
is as expected on OpenSUSE 9.

The renaming of the config option is very much intentional --
CONFIG_COMPAT_VDSO currently defaults to y and I want everyone to
rethink their default, since I suspect that >99% of people using the
default are doing so incorrectly.

If something like this works, it has a major benefit: we never have to
think about the compat vDSO again :)

Changes from v1: Note that OpenSUSE 9 is affected in the config text.


Documentation/kernel-parameters.txt | 11 +-
arch/x86/Kconfig | 23 ++--
arch/x86/include/asm/elf.h | 4 -
arch/x86/include/asm/fixmap.h | 8 --
arch/x86/include/asm/pgtable_types.h | 7 +-
arch/x86/include/asm/vdso.h | 5 +-
arch/x86/vdso/vdso-layout.lds.S | 2 +-
arch/x86/vdso/vdso32-setup.c | 234 ++++-------------------------------
arch/x86/vdso/vdso32/vdso32.lds.S | 2 -
9 files changed, 47 insertions(+), 249 deletions(-)

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 7116fda..67d8e7b 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -3409,14 +3409,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
of CONFIG_HIGHPTE.

vdso= [X86,SH]
- vdso=2: enable compat VDSO (default with COMPAT_VDSO)
- vdso=1: enable VDSO (default)
+ On X86_32, this is an alias for vdso32=. Otherwise:
+
+ vdso=1: enable VDSO (the default)
vdso=0: disable VDSO mapping

vdso32= [X86]
- vdso32=2: enable compat VDSO (default with COMPAT_VDSO)
- vdso32=1: enable 32-bit VDSO (default)
- vdso32=0: disable 32-bit VDSO mapping
+ vdso32=1: enable 32-bit VDSO (default if
+ ENABLE_VDSO32_BY_DEFAULT)
+ vdso32=0: disable 32-bit VDSO

vector= [IA-64,SMP]
vector=percpu: enable percpu vector domain
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0af5250..14461ef 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1835,18 +1835,27 @@ config DEBUG_HOTPLUG_CPU0

If unsure, say N.

-config COMPAT_VDSO
+config ENABLE_VDSO32_BY_DEFAULT
def_bool y
- prompt "Compat VDSO support"
+ prompt "Enable the 32-bit vDSO by default"
depends on X86_32 || IA32_EMULATION
---help---
- Map the 32-bit VDSO to the predictable old-style address too.
+ Certain buggy versions of glibc (those that support a vDSO but
+ do not include commit 49ad572a70b8aeb91e57483a11dd1b) will
+ crash if they are presented with a 32-bit vDSO that not mapped
+ at the address indicated in its segment table.

- Say N here if you are running a sufficiently recent glibc
- version (2.3.3 or later), to remove the high-mapped
- VDSO mapping and to exclusively use the randomized VDSO.
+ There is no released version of glibc that has this problem.
+ OpenSUSE 9, however, uses a buggy glibc.

- If unsure, say Y.
+ While it is theoretically possible for the kernel to provide a
+ usable vDSO for these versions of glibc, doing so is not
+ currently supported.
+
+ Disiabling this option will change the kernel's default to
+ vdso32=0 to workaround the problem. Doing so may cause a
+ performance loss on all system calls. Unless you have a buggy
+ glibc, say Y.

config CMDLINE_BOOL
bool "Built-in kernel command line"
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 9c999c1..2c71182 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -281,16 +281,12 @@ do { \

#define STACK_RND_MASK (0x7ff)

-#define VDSO_HIGH_BASE (__fix_to_virt(FIX_VDSO))
-
#define ARCH_DLINFO ARCH_DLINFO_IA32(vdso_enabled)

/* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */

#else /* CONFIG_X86_32 */

-#define VDSO_HIGH_BASE 0xffffe000U /* CONFIG_COMPAT_VDSO address */
-
/* 1GB for 64bit, 8MB for 32bit */
#define STACK_RND_MASK (test_thread_flag(TIF_ADDR32) ? 0x7ff : 0x3fffff)

diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 7252cd3..2377f56 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -40,15 +40,8 @@
*/
extern unsigned long __FIXADDR_TOP;
#define FIXADDR_TOP ((unsigned long)__FIXADDR_TOP)
-
-#define FIXADDR_USER_START __fix_to_virt(FIX_VDSO)
-#define FIXADDR_USER_END __fix_to_virt(FIX_VDSO - 1)
#else
#define FIXADDR_TOP (VSYSCALL_END-PAGE_SIZE)
-
-/* Only covers 32bit vsyscalls currently. Need another set for 64bit. */
-#define FIXADDR_USER_START ((unsigned long)VSYSCALL32_VSYSCALL)
-#define FIXADDR_USER_END (FIXADDR_USER_START + PAGE_SIZE)
#endif


@@ -74,7 +67,6 @@ extern unsigned long __FIXADDR_TOP;
enum fixed_addresses {
#ifdef CONFIG_X86_32
FIX_HOLE,
- FIX_VDSO,
#else
VSYSCALL_LAST_PAGE,
VSYSCALL_FIRST_PAGE = VSYSCALL_LAST_PAGE
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 1aa9ccd..943f166 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -214,13 +214,8 @@
#ifdef CONFIG_X86_64
#define __PAGE_KERNEL_IDENT_LARGE_EXEC __PAGE_KERNEL_LARGE_EXEC
#else
-/*
- * For PDE_IDENT_ATTR include USER bit. As the PDE and PTE protection
- * bits are combined, this will alow user to access the high address mapped
- * VDSO in the presence of CONFIG_COMPAT_VDSO
- */
#define PTE_IDENT_ATTR 0x003 /* PRESENT+RW */
-#define PDE_IDENT_ATTR 0x067 /* PRESENT+RW+USER+DIRTY+ACCESSED */
+#define PDE_IDENT_ATTR 0x063 /* PRESENT+RW+USER+DIRTY+ACCESSED */
#define PGD_IDENT_ATTR 0x001 /* PRESENT (no other attributes) */
#endif

diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index fddb53d..5594e84 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -2,8 +2,6 @@
#define _ASM_X86_VDSO_H

#if defined CONFIG_X86_32 || defined CONFIG_COMPAT
-extern const char VDSO32_PRELINK[];
-
/*
* 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.
@@ -11,8 +9,7 @@ extern const char VDSO32_PRELINK[];
#define VDSO32_SYMBOL(base, name) \
({ \
extern const char VDSO32_##name[]; \
- (void __user *)(VDSO32_##name - VDSO32_PRELINK + \
- (unsigned long)(base)); \
+ (void __user *)(VDSO32_##name + (unsigned long)(base)); \
})
#endif

diff --git a/arch/x86/vdso/vdso-layout.lds.S b/arch/x86/vdso/vdso-layout.lds.S
index 634a2cf..8c550c1 100644
--- a/arch/x86/vdso/vdso-layout.lds.S
+++ b/arch/x86/vdso/vdso-layout.lds.S
@@ -6,7 +6,7 @@

SECTIONS
{
- . = VDSO_PRELINK + SIZEOF_HEADERS;
+ . = SIZEOF_HEADERS;

.hash : { *(.hash) } :text
.gnu.hash : { *(.gnu.hash) }
diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c
index d6bfb87..4290ff7 100644
--- a/arch/x86/vdso/vdso32-setup.c
+++ b/arch/x86/vdso/vdso32-setup.c
@@ -26,16 +26,10 @@
#include <asm/vdso.h>
#include <asm/proto.h>

-enum {
- VDSO_DISABLED = 0,
- VDSO_ENABLED = 1,
- VDSO_COMPAT = 2,
-};
-
-#ifdef CONFIG_COMPAT_VDSO
-#define VDSO_DEFAULT VDSO_COMPAT
+#ifdef CONFIG_ENABLE_VDSO32_BY_DEFAULT
+#define VDSO_DEFAULT 1
#else
-#define VDSO_DEFAULT VDSO_ENABLED
+#define VDSO_DEFAULT 0
#endif

#ifdef CONFIG_X86_64
@@ -44,13 +38,6 @@ 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 +47,9 @@ static int __init vdso_setup(char *s)
{
vdso_enabled = simple_strtoul(s, NULL, 0);

+ if (vdso_enabled > 1)
+ printk(KERN_WARNING "vdso32 values other than 0 and 1 are no longer allowed; vdso disabled\n");
+
return 1;
}

@@ -76,123 +66,6 @@ __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];

#ifdef CONFIG_X86_64
@@ -212,12 +85,6 @@ 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))
@@ -241,37 +108,6 @@ 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)
@@ -282,10 +118,6 @@ int __init sysenter_setup(void)

vdso32_pages[0] = virt_to_page(syscall_page);

-#ifdef CONFIG_X86_32
- gate_vma_init();
-#endif
-
if (vdso32_syscall()) {
vsyscall = &vdso32_syscall_start;
vsyscall_len = &vdso32_syscall_end - &vdso32_syscall_start;
@@ -298,7 +130,6 @@ int __init sysenter_setup(void)
}

memcpy(syscall_page, vsyscall, vsyscall_len);
- relocate_vdso(syscall_page);

return 0;
}
@@ -309,48 +140,35 @@ 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;

#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);
-
- map_compat_vdso(compat);
-
- 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;
- }
+ addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0);
+ if (IS_ERR_VALUE(addr)) {
+ ret = addr;
+ goto up_fail;
}

current->mm->context.vdso = (void *)addr;

- 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);
-
- if (ret)
- goto up_fail;
- }
+ /*
+ * 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);
+
+ if (ret)
+ goto up_fail;

current_thread_info()->sysenter_return =
VDSO32_SYMBOL(addr, SYSENTER_RETURN);
@@ -411,20 +229,12 @@ 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)
diff --git a/arch/x86/vdso/vdso32/vdso32.lds.S b/arch/x86/vdso/vdso32/vdso32.lds.S
index 976124b..90e7aa9 100644
--- a/arch/x86/vdso/vdso32/vdso32.lds.S
+++ b/arch/x86/vdso/vdso32/vdso32.lds.S
@@ -8,7 +8,6 @@
* values visible using the asm-x86/vdso.h macros from the kernel proper.
*/

-#define VDSO_PRELINK 0
#include "../vdso-layout.lds.S"

/* The ELF entry point can be used to set the AT_SYSINFO value. */
@@ -31,7 +30,6 @@ VERSION
/*
* Symbols we define here called VDSO* get their values into vdso32-syms.h.
*/
-VDSO32_PRELINK = VDSO_PRELINK;
VDSO32_vsyscall = __kernel_vsyscall;
VDSO32_sigreturn = __kernel_sigreturn;
VDSO32_rt_sigreturn = __kernel_rt_sigreturn;
--
1.8.5.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/