Jeremy Fitzhardinge
2007-Apr-18 13:02 UTC
[patch 4/4] Make COMPAT_VDSO runtime selectable.
Now that relocation of the VDSO for COMPAT_VDSO users is done at
runtime rather than compile time, it is possible to enable/disable
compat mode at runtime.
This patch allows you to enable COMPAT_VDSO mode with "vdso=2" on the
kernel command line, or via sysctl. (Switching on a running system
shouldn't be done lightly; any process which was relying on the compat
VDSO will be upset if it goes away.)
The COMPAT_VDSO config option still exists, but if enabled it just
makes vdso_enabled default to VDSO_COMPAT.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: Zachary Amsden <zach@vmware.com>
Cc: "Jan Beulich" <JBeulich@novell.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Andi Kleen <ak@suse.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Roland McGrath <roland@redhat.com>
---
Documentation/kernel-parameters.txt | 1
arch/i386/kernel/sysenter.c | 141 +++++++++++++++++++++++------------
include/asm-i386/page.h | 2
3 files changed, 94 insertions(+), 50 deletions(-)
==================================================================---
a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1807,6 +1807,7 @@ and is between 256 and 4096 characters.
[USBHID] The interval which mice are to be polled at.
vdso= [IA-32,SH]
+ vdso=2: enable compat VDSO (default with COMPAT_VDSO)
vdso=1: enable VDSO (default)
vdso=0: disable VDSO mapping
==================================================================---
a/arch/i386/kernel/sysenter.c
+++ b/arch/i386/kernel/sysenter.c
@@ -23,12 +23,25 @@
#include <asm/pgtable.h>
#include <asm/unistd.h>
#include <asm/elf.h>
+#include <asm/tlbflush.h>
+
+enum {
+ VDSO_DISABLED = 0,
+ VDSO_ENABLED = 1,
+ VDSO_COMPAT = 2,
+};
+
+#ifdef CONFIG_COMPAT_VDSO
+#define VDSO_DEFAULT VDSO_COMPAT
+#else
+#define VDSO_DEFAULT VDSO_ENABLED
+#endif
/*
* Should the kernel map a VDSO page into processes and pass its
* address down to glibc upon exec()?
*/
-unsigned int __read_mostly vdso_enabled = 1;
+unsigned int __read_mostly vdso_enabled = VDSO_DEFAULT;
EXPORT_SYMBOL_GPL(vdso_enabled);
@@ -43,7 +56,6 @@ __setup("vdso=", vdso_setup);
extern asmlinkage void sysenter_entry(void);
-#ifdef CONFIG_COMPAT_VDSO
static __init void reloc_symtab(Elf32_Ehdr *ehdr,
unsigned offset, unsigned size)
{
@@ -160,11 +172,6 @@ static __init void relocate_vdso(Elf32_E
shdr[i].sh_size);
}
}
-#else
-static inline void relocate_vdso(Elf32_Ehdr *ehdr)
-{
-}
-#endif /* COMPAT_VDSO */
void enable_sep_cpu(void)
{
@@ -182,6 +189,25 @@ void enable_sep_cpu(void)
wrmsr(MSR_IA32_SYSENTER_ESP, tss->esp1, 0);
wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long) sysenter_entry, 0);
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;
+ /*
+ * Make sure the vDSO gets into every core dump.
+ * Dumping its contents makes post-mortem fully interpretable later
+ * without matching up the same kernel and hardware config to see
+ * what PC values meant.
+ */
+ gate_vma.vm_flags |= VM_ALWAYSDUMP;
+ return 0;
}
/*
@@ -192,6 +218,22 @@ extern const char vsyscall_sysenter_star
extern const char vsyscall_sysenter_start, vsyscall_sysenter_end;
static struct page *syscall_pages[1];
+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(syscall_pages[0]) << PAGE_SHIFT,
+ map ? PAGE_READONLY_EXEC : PAGE_NONE);
+
+ /* flush stray tlbs */
+ flush_tlb_all();
+}
+
int __init sysenter_setup(void)
{
void *syscall_page = (void *)get_zeroed_page(GFP_ATOMIC);
@@ -200,10 +242,9 @@ int __init sysenter_setup(void)
syscall_pages[0] = virt_to_page(syscall_page);
-#ifdef CONFIG_COMPAT_VDSO
- __set_fixmap(FIX_VDSO, __pa(syscall_page), PAGE_READONLY_EXEC);
+ gate_vma_init();
+
printk("Compat vDSO mapped to %08lx.\n", __fix_to_virt(FIX_VDSO));
-#endif
if (!boot_cpu_has(X86_FEATURE_SEP)) {
vsyscall = &vsyscall_int80_start;
@@ -222,42 +263,57 @@ int __init sysenter_setup(void)
/* Defined in vsyscall-sysenter.S */
extern void SYSENTER_RETURN;
-#ifdef __HAVE_ARCH_GATE_AREA
/* Setup a VMA at program startup for the vsyscall page */
int arch_setup_additional_pages(struct linux_binprm *bprm, int exstack)
{
struct mm_struct *mm = current->mm;
unsigned long addr;
int ret;
+ bool compat;
down_write(&mm->mmap_sem);
- 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
- *
- * Make sure the vDSO gets into every core dump.
- * Dumping its contents makes post-mortem fully interpretable later
- * without matching up the same kernel and hardware config to see
- * what PC values meant.
- */
- ret = install_special_mapping(mm, addr, PAGE_SIZE,
- VM_READ|VM_EXEC|
- VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
- VM_ALWAYSDUMP,
- syscall_pages);
- if (ret)
- goto up_fail;
+
+ /* 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;
+ }
+
+ /*
+ * MAYWRITE to allow gdb to COW and set breakpoints
+ *
+ * Make sure the vDSO gets into every core dump.
+ * Dumping its contents makes post-mortem fully
+ * interpretable later without matching up the same
+ * kernel and hardware config to see what PC values
+ * meant.
+ */
+ ret = install_special_mapping(mm, addr, PAGE_SIZE,
+ VM_READ|VM_EXEC|
+ VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
+ VM_ALWAYSDUMP,
+ syscall_pages);
+
+ if (ret)
+ goto up_fail;
+ }
current->mm->context.vdso = (void *)addr;
current_thread_info()->sysenter_return - (void
*)VDSO_SYM(&SYSENTER_RETURN);
-up_fail:
+ (void *)VDSO_SYM(&SYSENTER_RETURN);
+
+ up_fail:
up_write(&mm->mmap_sem);
+
return ret;
}
@@ -270,6 +326,9 @@ const char *arch_vma_name(struct vm_area
struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
{
+ /* Check to see if this task was created in compat vdso mode */
+ if (tsk->mm->context.vdso == (void *)VDSO_HIGH_BASE)
+ return &gate_vma;
return NULL;
}
@@ -282,17 +341,3 @@ int in_gate_area_no_task(unsigned long a
{
return 0;
}
-#else /* !__HAVE_ARCH_GATE_AREA */
-int arch_setup_additional_pages(struct linux_binprm *bprm, int exstack)
-{
- /*
- * If not creating userspace VMA, simply set vdso to point to
- * fixmap page.
- */
- current->mm->context.vdso = (void *)VDSO_HIGH_BASE;
- current_thread_info()->sysenter_return - (void
*)VDSO_SYM(&SYSENTER_RETURN);
-
- return 0;
-}
-#endif /* __HAVE_ARCH_GATE_AREA */
==================================================================---
a/include/asm-i386/page.h
+++ b/include/asm-i386/page.h
@@ -143,9 +143,7 @@ extern int page_is_ram(unsigned long pag
#include <asm-generic/memory_model.h>
#include <asm-generic/page.h>
-#ifndef CONFIG_COMPAT_VDSO
#define __HAVE_ARCH_GATE_AREA 1
-#endif
#endif /* __KERNEL__ */
#endif /* _I386_PAGE_H */
--
Most of asm-i386/bugs.h is code which should be in a C file, so put it there.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
---
arch/i386/kernel/cpu/Makefile | 2
arch/i386/kernel/cpu/bugs.c | 191 +++++++++++++++++++++++++++++++++++++++
include/asm-i386/alternative.h | 1
include/asm-i386/bugs.h | 194 ----------------------------------------
4 files changed, 197 insertions(+), 191 deletions(-)
==================================================================---
a/arch/i386/kernel/cpu/Makefile
+++ b/arch/i386/kernel/cpu/Makefile
@@ -2,7 +2,7 @@
# Makefile for x86-compatible CPU details and quirks
#
-obj-y := common.o proc.o
+obj-y := common.o proc.o bugs.o
obj-y += amd.o
obj-y += cyrix.o
==================================================================--- /dev/null
+++ b/arch/i386/kernel/cpu/bugs.c
@@ -0,0 +1,191 @@
+/*
+ * arch/i386/cpu/bugs.c
+ *
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Cyrix stuff, June 1998 by:
+ * - Rafael R. Reilova (moved everything from head.S),
+ * <rreilova@ececs.uc.edu>
+ * - Channing Corn (tests & fixes),
+ * - Andrew D. Balsa (code cleanup).
+ */
+#include <linux/init.h>
+#include <linux/utsname.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+#include <asm/msr.h>
+#include <asm/paravirt.h>
+#include <asm/alternative.h>
+
+static int __init no_halt(char *s)
+{
+ boot_cpu_data.hlt_works_ok = 0;
+ return 1;
+}
+
+__setup("no-hlt", no_halt);
+
+static int __init mca_pentium(char *s)
+{
+ mca_pentium_flag = 1;
+ return 1;
+}
+
+__setup("mca-pentium", mca_pentium);
+
+static int __init no_387(char *s)
+{
+ boot_cpu_data.hard_math = 0;
+ write_cr0(0xE | read_cr0());
+ return 1;
+}
+
+__setup("no387", no_387);
+
+static double __initdata x = 4195835.0;
+static double __initdata y = 3145727.0;
+
+/*
+ * This used to check for exceptions..
+ * However, it turns out that to support that,
+ * the XMM trap handlers basically had to
+ * be buggy. So let's have a correct XMM trap
+ * handler, and forget about printing out
+ * some status at boot.
+ *
+ * We should really only care about bugs here
+ * anyway. Not features.
+ */
+static void __init check_fpu(void)
+{
+ if (!boot_cpu_data.hard_math) {
+#ifndef CONFIG_MATH_EMULATION
+ printk(KERN_EMERG "No coprocessor found and no math emulation
present.\n");
+ printk(KERN_EMERG "Giving up.\n");
+ for (;;) ;
+#endif
+ return;
+ }
+
+/* trap_init() enabled FXSR and company _before_ testing for FP problems here.
*/
+ /* Test for the divl bug.. */
+ __asm__("fninit\n\t"
+ "fldl %1\n\t"
+ "fdivl %2\n\t"
+ "fmull %2\n\t"
+ "fldl %1\n\t"
+ "fsubp %%st,%%st(1)\n\t"
+ "fistpl %0\n\t"
+ "fwait\n\t"
+ "fninit"
+ : "=m" (*&boot_cpu_data.fdiv_bug)
+ : "m" (*&x), "m" (*&y));
+ if (boot_cpu_data.fdiv_bug)
+ printk("Hmm, FPU with FDIV bug.\n");
+}
+
+static void __init check_hlt(void)
+{
+ if (paravirt_enabled())
+ return;
+
+ printk(KERN_INFO "Checking 'hlt' instruction... ");
+ if (!boot_cpu_data.hlt_works_ok) {
+ printk("disabled\n");
+ return;
+ }
+ halt();
+ halt();
+ halt();
+ halt();
+ printk("OK.\n");
+}
+
+/*
+ * Most 386 processors have a bug where a POPAD can lock the
+ * machine even from user space.
+ */
+
+static void __init check_popad(void)
+{
+#ifndef CONFIG_X86_POPAD_OK
+ int res, inp = (int) &res;
+
+ printk(KERN_INFO "Checking for popad bug... ");
+ __asm__ __volatile__(
+ "movl $12345678,%%eax; movl $0,%%edi; pusha; popa; movl
(%%edx,%%edi),%%ecx "
+ : "=&a" (res)
+ : "d" (inp)
+ : "ecx", "edi" );
+ /* If this fails, it means that any user program may lock the CPU hard. Too
bad. */
+ if (res != 12345678) printk( "Buggy.\n" );
+ else printk( "OK.\n" );
+#endif
+}
+
+/*
+ * Check whether we are able to run this kernel safely on SMP.
+ *
+ * - In order to run on a i386, we need to be compiled for i386
+ * (for due to lack of "invlpg" and working WP on a i386)
+ * - In order to run on anything without a TSC, we need to be
+ * compiled for a i486.
+ * - In order to support the local APIC on a buggy Pentium machine,
+ * we need to be compiled with CONFIG_X86_GOOD_APIC disabled,
+ * which happens implicitly if compiled for a Pentium or lower
+ * (unless an advanced selection of CPU features is used) as an
+ * otherwise config implies a properly working local APIC without
+ * the need to do extra reads from the APIC.
+*/
+
+static void __init check_config(void)
+{
+/*
+ * We'd better not be a i386 if we're configured to use some
+ * i486+ only features! (WP works in supervisor mode and the
+ * new "invlpg" and "bswap" instructions)
+ */
+#if defined(CONFIG_X86_WP_WORKS_OK) || defined(CONFIG_X86_INVLPG) ||
defined(CONFIG_X86_BSWAP)
+ if (boot_cpu_data.x86 == 3)
+ panic("Kernel requires i486+ for 'invlpg' and other
features");
+#endif
+
+/*
+ * If we configured ourselves for a TSC, we'd better have one!
+ */
+#ifdef CONFIG_X86_TSC
+ if (!cpu_has_tsc && !tsc_disable)
+ panic("Kernel compiled for Pentium+, requires TSC feature!");
+#endif
+
+/*
+ * If we were told we had a good local APIC, check for buggy Pentia,
+ * i.e. all B steppings and the C2 stepping of P54C when using their
+ * integrated APIC (see 11AP erratum in "Pentium Processor
+ * Specification Update").
+ */
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_GOOD_APIC)
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL
+ && cpu_has_apic
+ && boot_cpu_data.x86 == 5
+ && boot_cpu_data.x86_model == 2
+ && (boot_cpu_data.x86_mask < 6 || boot_cpu_data.x86_mask ==
11))
+ panic("Kernel compiled for PMMX+, assumes a local APIC without the
read-before-write bug!");
+#endif
+}
+
+
+void __init check_bugs(void)
+{
+ identify_boot_cpu();
+#ifndef CONFIG_SMP
+ printk("CPU: ");
+ print_cpu_info(&boot_cpu_data);
+#endif
+ check_config();
+ check_fpu();
+ check_hlt();
+ check_popad();
+ init_utsname()->machine[1] = '0' + (boot_cpu_data.x86 > 6 ? 6 :
boot_cpu_data.x86);
+ alternative_instructions();
+}
==================================================================---
a/include/asm-i386/alternative.h
+++ b/include/asm-i386/alternative.h
@@ -14,6 +14,7 @@ struct alt_instr {
u8 pad;
};
+extern void alternative_instructions(void);
extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
struct module;
==================================================================---
a/include/asm-i386/bugs.h
+++ b/include/asm-i386/bugs.h
@@ -1,198 +1,12 @@
-/*
- * include/asm-i386/bugs.h
- *
- * Copyright (C) 1994 Linus Torvalds
- *
- * Cyrix stuff, June 1998 by:
- * - Rafael R. Reilova (moved everything from head.S),
- * <rreilova@ececs.uc.edu>
- * - Channing Corn (tests & fixes),
- * - Andrew D. Balsa (code cleanup).
- */
-
/*
* This is included by init/main.c to check for architecture-dependent bugs.
*
* Needs:
* void check_bugs(void);
*/
+#ifndef _ASM_I386_BUG_H
+#define _ASM_I386_BUG_H
-#include <linux/init.h>
-#include <asm/processor.h>
-#include <asm/i387.h>
-#include <asm/msr.h>
-#include <asm/paravirt.h>
+extern void __init check_bugs(void);
-static int __init no_halt(char *s)
-{
- boot_cpu_data.hlt_works_ok = 0;
- return 1;
-}
-
-__setup("no-hlt", no_halt);
-
-static int __init mca_pentium(char *s)
-{
- mca_pentium_flag = 1;
- return 1;
-}
-
-__setup("mca-pentium", mca_pentium);
-
-static int __init no_387(char *s)
-{
- boot_cpu_data.hard_math = 0;
- write_cr0(0xE | read_cr0());
- return 1;
-}
-
-__setup("no387", no_387);
-
-static double __initdata x = 4195835.0;
-static double __initdata y = 3145727.0;
-
-/*
- * This used to check for exceptions..
- * However, it turns out that to support that,
- * the XMM trap handlers basically had to
- * be buggy. So let's have a correct XMM trap
- * handler, and forget about printing out
- * some status at boot.
- *
- * We should really only care about bugs here
- * anyway. Not features.
- */
-static void __init check_fpu(void)
-{
- if (!boot_cpu_data.hard_math) {
-#ifndef CONFIG_MATH_EMULATION
- printk(KERN_EMERG "No coprocessor found and no math emulation
present.\n");
- printk(KERN_EMERG "Giving up.\n");
- for (;;) ;
-#endif
- return;
- }
-
-/* trap_init() enabled FXSR and company _before_ testing for FP problems here.
*/
- /* Test for the divl bug.. */
- __asm__("fninit\n\t"
- "fldl %1\n\t"
- "fdivl %2\n\t"
- "fmull %2\n\t"
- "fldl %1\n\t"
- "fsubp %%st,%%st(1)\n\t"
- "fistpl %0\n\t"
- "fwait\n\t"
- "fninit"
- : "=m" (*&boot_cpu_data.fdiv_bug)
- : "m" (*&x), "m" (*&y));
- if (boot_cpu_data.fdiv_bug)
- printk("Hmm, FPU with FDIV bug.\n");
-}
-
-static void __init check_hlt(void)
-{
- if (paravirt_enabled())
- return;
-
- printk(KERN_INFO "Checking 'hlt' instruction... ");
- if (!boot_cpu_data.hlt_works_ok) {
- printk("disabled\n");
- return;
- }
- halt();
- halt();
- halt();
- halt();
- printk("OK.\n");
-}
-
-/*
- * Most 386 processors have a bug where a POPAD can lock the
- * machine even from user space.
- */
-
-static void __init check_popad(void)
-{
-#ifndef CONFIG_X86_POPAD_OK
- int res, inp = (int) &res;
-
- printk(KERN_INFO "Checking for popad bug... ");
- __asm__ __volatile__(
- "movl $12345678,%%eax; movl $0,%%edi; pusha; popa; movl
(%%edx,%%edi),%%ecx "
- : "=&a" (res)
- : "d" (inp)
- : "ecx", "edi" );
- /* If this fails, it means that any user program may lock the CPU hard. Too
bad. */
- if (res != 12345678) printk( "Buggy.\n" );
- else printk( "OK.\n" );
-#endif
-}
-
-/*
- * Check whether we are able to run this kernel safely on SMP.
- *
- * - In order to run on a i386, we need to be compiled for i386
- * (for due to lack of "invlpg" and working WP on a i386)
- * - In order to run on anything without a TSC, we need to be
- * compiled for a i486.
- * - In order to support the local APIC on a buggy Pentium machine,
- * we need to be compiled with CONFIG_X86_GOOD_APIC disabled,
- * which happens implicitly if compiled for a Pentium or lower
- * (unless an advanced selection of CPU features is used) as an
- * otherwise config implies a properly working local APIC without
- * the need to do extra reads from the APIC.
-*/
-
-static void __init check_config(void)
-{
-/*
- * We'd better not be a i386 if we're configured to use some
- * i486+ only features! (WP works in supervisor mode and the
- * new "invlpg" and "bswap" instructions)
- */
-#if defined(CONFIG_X86_WP_WORKS_OK) || defined(CONFIG_X86_INVLPG) ||
defined(CONFIG_X86_BSWAP)
- if (boot_cpu_data.x86 == 3)
- panic("Kernel requires i486+ for 'invlpg' and other
features");
-#endif
-
-/*
- * If we configured ourselves for a TSC, we'd better have one!
- */
-#ifdef CONFIG_X86_TSC
- if (!cpu_has_tsc && !tsc_disable)
- panic("Kernel compiled for Pentium+, requires TSC feature!");
-#endif
-
-/*
- * If we were told we had a good local APIC, check for buggy Pentia,
- * i.e. all B steppings and the C2 stepping of P54C when using their
- * integrated APIC (see 11AP erratum in "Pentium Processor
- * Specification Update").
- */
-#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_GOOD_APIC)
- if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL
- && cpu_has_apic
- && boot_cpu_data.x86 == 5
- && boot_cpu_data.x86_model == 2
- && (boot_cpu_data.x86_mask < 6 || boot_cpu_data.x86_mask ==
11))
- panic("Kernel compiled for PMMX+, assumes a local APIC without the
read-before-write bug!");
-#endif
-}
-
-extern void alternative_instructions(void);
-
-static void __init check_bugs(void)
-{
- identify_cpu(&boot_cpu_data);
-#ifndef CONFIG_SMP
- printk("CPU: ");
- print_cpu_info(&boot_cpu_data);
-#endif
- check_config();
- check_fpu();
- check_hlt();
- check_popad();
- init_utsname()->machine[1] = '0' + (boot_cpu_data.x86 > 6 ? 6 :
boot_cpu_data.x86);
- alternative_instructions();
-}
+#endif /* _ASM_I386_BUG_H */
--
Jeremy Fitzhardinge
2007-Apr-18 13:02 UTC
[patch 3/4] Relocate VDSO ELF headers to match mapped location with COMPAT_VDSO
Some versions of libc can't deal with a VDSO which doesn't have its
ELF headers matching its mapped address. COMPAT_VDSO maps the VDSO at
a specific system-wide fixed address. Previously this was all done at
build time, on the grounds that the fixed VDSO address is always at
the top of the address space. However, a hypervisor may reserve some
of that address space, pushing the fixmap address down.
This patch does the adjustment dynamically at runtime, depending on
the runtime location of the VDSO fixmap.
[ Patch has been through several hands: Jan Beulich wrote the orignal
version; Zach reworked it, and Jeremy converted it to relocate phdrs
as well as sections. ]
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: Zachary Amsden <zach@vmware.com>
Cc: "Jan Beulich" <JBeulich@novell.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Andi Kleen <ak@suse.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Roland McGrath <roland@redhat.com>
---
arch/i386/kernel/entry.S | 4 -
arch/i386/kernel/sysenter.c | 170 +++++++++++++++++++++++++++++++++++++++----
arch/i386/mm/pgtable.c | 6 -
include/asm-i386/elf.h | 28 ++-----
include/asm-i386/fixmap.h | 8 --
include/linux/elf.h | 17 ++++
6 files changed, 184 insertions(+), 49 deletions(-)
==================================================================---
a/arch/i386/kernel/entry.S
+++ b/arch/i386/kernel/entry.S
@@ -305,16 +305,12 @@ sysenter_past_esp:
pushl $(__USER_CS)
CFI_ADJUST_CFA_OFFSET 4
/*CFI_REL_OFFSET cs, 0*/
-#ifndef CONFIG_COMPAT_VDSO
/*
* Push current_thread_info()->sysenter_return to the stack.
* A tiny bit of offset fixup is necessary - 4*4 means the 4 words
* pushed above; +8 corresponds to copy_thread's esp0 setting.
*/
pushl (TI_sysenter_return-THREAD_SIZE+8+4*4)(%esp)
-#else
- pushl $SYSENTER_RETURN
-#endif
CFI_ADJUST_CFA_OFFSET 4
CFI_REL_OFFSET eip, 0
==================================================================---
a/arch/i386/kernel/sysenter.c
+++ b/arch/i386/kernel/sysenter.c
@@ -22,6 +22,7 @@
#include <asm/msr.h>
#include <asm/pgtable.h>
#include <asm/unistd.h>
+#include <asm/elf.h>
/*
* Should the kernel map a VDSO page into processes and pass its
@@ -41,6 +42,129 @@ __setup("vdso=", vdso_setup);
__setup("vdso=", vdso_setup);
extern asmlinkage void sysenter_entry(void);
+
+#ifdef CONFIG_COMPAT_VDSO
+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_HIGH_BASE;
+ }
+ }
+}
+
+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_HIGH_BASE;
+ 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_HIGH_BASE;
+ 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, 4) != 0 ||
+ !elf_check_arch(ehdr) ||
+ ehdr->e_type != ET_DYN);
+
+ ehdr->e_entry += VDSO_HIGH_BASE;
+
+ /* rebase phdrs */
+ phdr = (void *)ehdr + ehdr->e_phoff;
+ for (i = 0; i < ehdr->e_phnum; i++) {
+ phdr[i].p_vaddr += VDSO_HIGH_BASE;
+
+ /* 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_HIGH_BASE;
+
+ if (shdr[i].sh_type == SHT_SYMTAB ||
+ shdr[i].sh_type == SHT_DYNSYM)
+ reloc_symtab(ehdr, shdr[i].sh_offset,
+ shdr[i].sh_size);
+ }
+}
+#else
+static inline void relocate_vdso(Elf32_Ehdr *ehdr)
+{
+}
+#endif /* COMPAT_VDSO */
void enable_sep_cpu(void)
{
@@ -71,6 +195,9 @@ int __init sysenter_setup(void)
int __init sysenter_setup(void)
{
void *syscall_page = (void *)get_zeroed_page(GFP_ATOMIC);
+ const void *vsyscall;
+ size_t vsyscall_len;
+
syscall_pages[0] = virt_to_page(syscall_page);
#ifdef CONFIG_COMPAT_VDSO
@@ -79,23 +206,23 @@ int __init sysenter_setup(void)
#endif
if (!boot_cpu_has(X86_FEATURE_SEP)) {
- memcpy(syscall_page,
- &vsyscall_int80_start,
- &vsyscall_int80_end - &vsyscall_int80_start);
- return 0;
- }
-
- memcpy(syscall_page,
- &vsyscall_sysenter_start,
- &vsyscall_sysenter_end - &vsyscall_sysenter_start);
-
- return 0;
-}
-
-#ifndef CONFIG_COMPAT_VDSO
+ vsyscall = &vsyscall_int80_start;
+ vsyscall_len = &vsyscall_int80_end - &vsyscall_int80_start;
+ } else {
+ vsyscall = &vsyscall_sysenter_start;
+ vsyscall_len = &vsyscall_sysenter_end - &vsyscall_sysenter_start;
+ }
+
+ memcpy(syscall_page, vsyscall, vsyscall_len);
+ relocate_vdso(syscall_page);
+
+ return 0;
+}
+
/* Defined in vsyscall-sysenter.S */
extern void SYSENTER_RETURN;
+#ifdef __HAVE_ARCH_GATE_AREA
/* Setup a VMA at program startup for the vsyscall page */
int arch_setup_additional_pages(struct linux_binprm *bprm, int exstack)
{
@@ -155,4 +282,17 @@ int in_gate_area_no_task(unsigned long a
{
return 0;
}
-#endif
+#else /* !__HAVE_ARCH_GATE_AREA */
+int arch_setup_additional_pages(struct linux_binprm *bprm, int exstack)
+{
+ /*
+ * If not creating userspace VMA, simply set vdso to point to
+ * fixmap page.
+ */
+ current->mm->context.vdso = (void *)VDSO_HIGH_BASE;
+ current_thread_info()->sysenter_return + (void
*)VDSO_SYM(&SYSENTER_RETURN);
+
+ return 0;
+}
+#endif /* __HAVE_ARCH_GATE_AREA */
==================================================================---
a/arch/i386/mm/pgtable.c
+++ b/arch/i386/mm/pgtable.c
@@ -144,10 +144,8 @@ void set_pmd_pfn(unsigned long vaddr, un
}
static int fixmaps;
-#ifndef CONFIG_COMPAT_VDSO
unsigned long __FIXADDR_TOP = 0xfffff000;
EXPORT_SYMBOL(__FIXADDR_TOP);
-#endif
void __set_fixmap (enum fixed_addresses idx, unsigned long phys, pgprot_t
flags)
{
@@ -173,12 +171,8 @@ void reserve_top_address(unsigned long r
BUG_ON(fixmaps > 0);
printk(KERN_INFO "Reserving virtual address space above 0x%08x\n",
(int)-reserve);
-#ifdef CONFIG_COMPAT_VDSO
- BUG_ON(reserve != 0);
-#else
__FIXADDR_TOP = -reserve - PAGE_SIZE;
__VMALLOC_RESERVE += reserve;
-#endif
}
pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
==================================================================---
a/include/asm-i386/elf.h
+++ b/include/asm-i386/elf.h
@@ -133,39 +133,31 @@ extern int dump_task_extended_fpu (struc
#define ELF_CORE_COPY_XFPREGS(tsk, elf_xfpregs) dump_task_extended_fpu(tsk,
elf_xfpregs)
#define VDSO_HIGH_BASE (__fix_to_virt(FIX_VDSO))
-#define VDSO_BASE ((unsigned long)current->mm->context.vdso)
-
-#ifdef CONFIG_COMPAT_VDSO
-# define VDSO_COMPAT_BASE VDSO_HIGH_BASE
-# define VDSO_PRELINK VDSO_HIGH_BASE
-#else
-# define VDSO_COMPAT_BASE VDSO_BASE
-# define VDSO_PRELINK 0
-#endif
+#define VDSO_CURRENT_BASE ((unsigned long)current->mm->context.vdso)
+#define VDSO_PRELINK 0
#define VDSO_SYM(x) \
- (VDSO_COMPAT_BASE + (unsigned long)(x) - VDSO_PRELINK)
+ (VDSO_CURRENT_BASE + (unsigned long)(x) - VDSO_PRELINK)
#define VDSO_HIGH_EHDR ((const struct elfhdr *) VDSO_HIGH_BASE)
-#define VDSO_EHDR ((const struct elfhdr *) VDSO_COMPAT_BASE)
+#define VDSO_EHDR ((const struct elfhdr *) VDSO_CURRENT_BASE)
extern void __kernel_vsyscall;
#define VDSO_ENTRY VDSO_SYM(&__kernel_vsyscall)
-#ifndef CONFIG_COMPAT_VDSO
+struct linux_binprm;
+
#define ARCH_HAS_SETUP_ADDITIONAL_PAGES
-struct linux_binprm;
extern int arch_setup_additional_pages(struct linux_binprm *bprm,
int executable_stack);
-#endif
extern unsigned int vdso_enabled;
-#define ARCH_DLINFO \
-do if (vdso_enabled) { \
- NEW_AUX_ENT(AT_SYSINFO, VDSO_ENTRY); \
- NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_COMPAT_BASE); \
+#define ARCH_DLINFO \
+do if (vdso_enabled) { \
+ NEW_AUX_ENT(AT_SYSINFO, VDSO_ENTRY); \
+ NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_CURRENT_BASE); \
} while (0)
#endif
==================================================================---
a/include/asm-i386/fixmap.h
+++ b/include/asm-i386/fixmap.h
@@ -19,13 +19,9 @@
* Leave one empty page between vmalloc'ed areas and
* the start of the fixmap.
*/
-#ifndef CONFIG_COMPAT_VDSO
extern unsigned long __FIXADDR_TOP;
-#else
-#define __FIXADDR_TOP 0xfffff000
-#define FIXADDR_USER_START __fix_to_virt(FIX_VDSO)
-#define FIXADDR_USER_END __fix_to_virt(FIX_VDSO - 1)
-#endif
+#define FIXADDR_USER_START __fix_to_virt(FIX_VDSO)
+#define FIXADDR_USER_END __fix_to_virt(FIX_VDSO - 1)
#ifndef __ASSEMBLY__
#include <linux/kernel.h>
==================================================================---
a/include/linux/elf.h
+++ b/include/linux/elf.h
@@ -83,6 +83,23 @@ typedef __s64 Elf64_Sxword;
#define DT_DEBUG 21
#define DT_TEXTREL 22
#define DT_JMPREL 23
+#define DT_ENCODING 32
+#define OLD_DT_LOOS 0x60000000
+#define DT_LOOS 0x6000000d
+#define DT_HIOS 0x6ffff000
+#define DT_VALRNGLO 0x6ffffd00
+#define DT_VALRNGHI 0x6ffffdff
+#define DT_ADDRRNGLO 0x6ffffe00
+#define DT_ADDRRNGHI 0x6ffffeff
+#define DT_VERSYM 0x6ffffff0
+#define DT_RELACOUNT 0x6ffffff9
+#define DT_RELCOUNT 0x6ffffffa
+#define DT_FLAGS_1 0x6ffffffb
+#define DT_VERDEF 0x6ffffffc
+#define DT_VERDEFNUM 0x6ffffffd
+#define DT_VERNEED 0x6ffffffe
+#define DT_VERNEEDNUM 0x6fffffff
+#define OLD_DT_HIOS 0x6fffffff
#define DT_LOPROC 0x70000000
#define DT_HIPROC 0x7fffffff
--
Jeremy Fitzhardinge
2007-Apr-18 13:02 UTC
[patch 0/4] Clean up asm/bugs.h, identify_cpu() and update COMPAT_VDSO
Hi Andi, Four patches: - clean up asm/bugs.h, by moving all the C code into its own C file - split identify_cpu() into boot and secondary variants, so that boot-time setup functions can be marked __init - repost of the COMPAT_VDSO patches with a bit more robustness from unknown DT_tags, and functions marked __init, since all this is boot-time only setup. Thanks, J --
identify_cpu() is used to identify both the boot CPU and secondary
CPUs, but it performs some actions which only apply to the boot CPU.
Those functions are therefore really __init functions, but because
they're called by identify_cpu(), they must be marked __cpuinit.
This patch splits identify_cpu() into identify_boot_cpu() and
identify_secondary_cpu(), and calls the appropriate init functions
from each. Also, identify_boot_cpu() and all the functions it
dominates are marked __init.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
---
arch/i386/kernel/cpu/common.c | 25 ++++++++++++++++---------
arch/i386/kernel/cpu/mtrr/main.c | 4 ++--
arch/i386/kernel/smpboot.c | 2 +-
arch/i386/kernel/sysenter.c | 2 +-
include/asm-i386/processor.h | 3 ++-
5 files changed, 22 insertions(+), 14 deletions(-)
==================================================================---
a/arch/i386/kernel/cpu/common.c
+++ b/arch/i386/kernel/cpu/common.c
@@ -390,7 +390,7 @@ __setup("serialnumber", x86_serial_nr_se
/*
* This does the hard work of actually picking apart the CPU stuff...
*/
-void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
+static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
{
int i;
@@ -501,15 +501,22 @@ void __cpuinit identify_cpu(struct cpuin
/* Init Machine Check Exception if available. */
mcheck_init(c);
-
- if (c == &boot_cpu_data)
- sysenter_setup();
+}
+
+void __init identify_boot_cpu(void)
+{
+ identify_cpu(&boot_cpu_data);
+ sysenter_setup();
enable_sep_cpu();
-
- if (c == &boot_cpu_data)
- mtrr_bp_init();
- else
- mtrr_ap_init();
+ mtrr_bp_init();
+}
+
+void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c)
+{
+ BUG_ON(c == &boot_cpu_data);
+ identify_cpu(c);
+ enable_sep_cpu();
+ mtrr_ap_init();
}
#ifdef CONFIG_X86_HT
==================================================================---
a/arch/i386/kernel/cpu/mtrr/main.c
+++ b/arch/i386/kernel/cpu/mtrr/main.c
@@ -571,7 +571,7 @@ extern void cyrix_init_mtrr(void);
extern void cyrix_init_mtrr(void);
extern void centaur_init_mtrr(void);
-static void __cpuinit init_ifs(void)
+static void __init init_ifs(void)
{
#ifndef CONFIG_X86_64
amd_init_mtrr();
@@ -639,7 +639,7 @@ static struct sysdev_driver mtrr_sysdev_
* initialized (i.e. before smp_init()).
*
*/
-void __cpuinit mtrr_bp_init(void)
+void __init mtrr_bp_init(void)
{
init_ifs();
==================================================================---
a/arch/i386/kernel/smpboot.c
+++ b/arch/i386/kernel/smpboot.c
@@ -157,7 +157,7 @@ static void __cpuinit smp_store_cpu_info
*c = boot_cpu_data;
if (id!=0)
- identify_cpu(c);
+ identify_secondary_cpu(c);
/*
* Mask B, Pentium, but not Pentium MMX
*/
==================================================================---
a/arch/i386/kernel/sysenter.c
+++ b/arch/i386/kernel/sysenter.c
@@ -68,7 +68,7 @@ extern const char vsyscall_sysenter_star
extern const char vsyscall_sysenter_start, vsyscall_sysenter_end;
static struct page *syscall_pages[1];
-int __cpuinit sysenter_setup(void)
+int __init sysenter_setup(void)
{
void *syscall_page = (void *)get_zeroed_page(GFP_ATOMIC);
syscall_pages[0] = virt_to_page(syscall_page);
==================================================================---
a/include/asm-i386/processor.h
+++ b/include/asm-i386/processor.h
@@ -116,7 +116,8 @@ extern char ignore_fpu_irq;
void __init cpu_detect(struct cpuinfo_x86 *c);
-extern void identify_cpu(struct cpuinfo_x86 *);
+extern void identify_boot_cpu(void);
+extern void identify_secondary_cpu(struct cpuinfo_x86 *);
extern void print_cpu_info(struct cpuinfo_x86 *);
extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
extern unsigned short num_cache_leaves;
--
Possibly Parallel Threads
- [patch 0/4] Clean up asm/bugs.h, identify_cpu() and update COMPAT_VDSO
- [patch 0/2] Updates to compat VDSOs
- [patch 0/2] Updates to compat VDSOs
- [RFC, PATCH] Fixup COMPAT_VDSO to work with CONFIG_PARAVIRT
- [RFC, PATCH] Fixup COMPAT_VDSO to work with CONFIG_PARAVIRT