Re: Why disable vdso by default with CONFIG_PARAVIRT?

[Rusty Russell <rusty@rustcorp.com.au>]

On Tue, 2006-12-12 at 22:15 +0100, Andi Kleen wrote:
> The failure is an assertation failure in ld.so.

OK, this patch tested on an assert() in init.

===
Older glibcs assert() that the vdso will be in a particular spot
(which it can no longer be with CONFIG_PARAVIRT).  As this glibc was
shipped in SuSE 9.0 and Fedora Core 1, it's not a trivial breakage.

Try to detect the failing init at runtime, turn off vdso and re-exec.
Untested on the actual failing systems, but should work.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>

diff -r ed1ffbd17965 arch/i386/Kconfig
--- a/arch/i386/Kconfig	Wed Dec 13 14:11:14 2006 +1100
+++ b/arch/i386/Kconfig	Wed Dec 13 14:30:30 2006 +1100
@@ -816,15 +816,14 @@ config HOTPLUG_CPU
 	  /sys/devices/system/cpu.
 
 config COMPAT_VDSO
-	bool "Compat VDSO support"
-	default y
-	depends on !PARAVIRT
-	help
-	  Map the VDSO to the predictable old-style address too.
-	---help---
-	  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.
+	bool "Disable VDSO for old glibc"
+	default y
+	---help---
+	  Old glibc does not like the modern VDSO placement (glibc
+	  2.3.3 or later is fine, Fedora Core 1 and SuSE 9.0 have
+	  problems).  Very old glibc versions don't use the VDSO at
+	  all.  This option tries to detect the glibc assertion which
+	  occurs and then disables the VDSO.
 
 	  If unsure, say Y.
 
diff -r ed1ffbd17965 arch/i386/kernel/signal.c
--- a/arch/i386/kernel/signal.c	Wed Dec 13 14:11:14 2006 +1100
+++ b/arch/i386/kernel/signal.c	Wed Dec 13 15:26:37 2006 +1100
@@ -608,6 +608,20 @@ static void fastcall do_signal(struct pt
 
 		return;
 	}
+#ifdef CONFIG_COMPAT_VDSO
+	else if (signr == -1) {
+		void reexec_init(void);
+		if (vdso_enabled) {
+			printk(KERN_WARNING "COMPAT_VDSO: Old glibc?"
+			       " Re-execing init with vdso disabled\n");
+			vdso_enabled = 0;
+			/* kill() made us think we're dying: we're not. */
+			current->signal->group_stop_count = 0;
+			reexec_init();
+			printk(KERN_WARNING "Re-exec of init failed\n");
+		}
+	}
+#endif
 
 	/* Did we come from a system call? */
 	if (regs->orig_eax >= 0) {
diff -r ed1ffbd17965 arch/i386/kernel/sysenter.c
--- a/arch/i386/kernel/sysenter.c	Wed Dec 13 14:11:14 2006 +1100
+++ b/arch/i386/kernel/sysenter.c	Wed Dec 13 14:13:35 2006 +1100
@@ -27,11 +27,7 @@
  * Should the kernel map a VDSO page into processes and pass its
  * address down to glibc upon exec()?
  */
-#ifdef CONFIG_PARAVIRT
-unsigned int __read_mostly vdso_enabled = 0;
-#else
 unsigned int __read_mostly vdso_enabled = 1;
-#endif
 
 EXPORT_SYMBOL_GPL(vdso_enabled);
 
@@ -76,15 +72,10 @@ int __init sysenter_setup(void)
 {
 	syscall_page = (void *)get_zeroed_page(GFP_ATOMIC);
 
-#ifdef CONFIG_COMPAT_VDSO
-	__set_fixmap(FIX_VDSO, __pa(syscall_page), PAGE_READONLY);
-	printk("Compat vDSO mapped to %08lx.\n", __fix_to_virt(FIX_VDSO));
-#else
 	/*
 	 * In the non-compat case the ELF coredumping code needs the fixmap:
 	 */
 	__set_fixmap(FIX_VDSO, __pa(syscall_page), PAGE_KERNEL_RO);
-#endif
 
 	if (!boot_cpu_has(X86_FEATURE_SEP)) {
 		memcpy(syscall_page,
diff -r ed1ffbd17965 arch/i386/mm/pgtable.c
--- a/arch/i386/mm/pgtable.c	Wed Dec 13 14:11:14 2006 +1100
+++ b/arch/i386/mm/pgtable.c	Wed Dec 13 14:30:33 2006 +1100
@@ -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)
 {
@@ -171,12 +169,8 @@ void reserve_top_address(unsigned long r
 void reserve_top_address(unsigned long reserve)
 {
 	BUG_ON(fixmaps > 0);
-#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)
diff -r ed1ffbd17965 include/asm-i386/elf.h
--- a/include/asm-i386/elf.h	Wed Dec 13 14:11:14 2006 +1100
+++ b/include/asm-i386/elf.h	Wed Dec 13 14:11:14 2006 +1100
@@ -135,13 +135,8 @@ extern int dump_task_extended_fpu (struc
 #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_COMPAT_SYM(x) \
 		(VDSO_COMPAT_BASE + (unsigned long)(x) - VDSO_PRELINK)
diff -r ed1ffbd17965 include/asm-i386/fixmap.h
--- a/include/asm-i386/fixmap.h	Wed Dec 13 14:11:14 2006 +1100
+++ b/include/asm-i386/fixmap.h	Wed Dec 13 14:11:14 2006 +1100
@@ -19,11 +19,7 @@
  * 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
-#endif
 
 #ifndef __ASSEMBLY__
 #include <linux/kernel.h>
diff -r ed1ffbd17965 init/main.c
--- a/init/main.c	Wed Dec 13 14:11:14 2006 +1100
+++ b/init/main.c	Wed Dec 13 15:31:57 2006 +1100
@@ -710,6 +710,16 @@ static void run_init_process(char *init_
 	kernel_execve(init_filename, argv_init, envp_init);
 }
 
+#ifdef CONFIG_COMPAT_VDSO
+void reexec_init(void)
+{
+	mm_segment_t oldfs = get_fs();
+	set_fs(KERNEL_DS);
+	kernel_execve(argv_init[0], argv_init, envp_init);
+	set_fs(oldfs);
+}
+#endif
+
 static int init(void * unused)
 {
 	lock_kernel();
diff -r ed1ffbd17965 kernel/signal.c
--- a/kernel/signal.c	Wed Dec 13 14:11:14 2006 +1100
+++ b/kernel/signal.c	Wed Dec 13 14:55:07 2006 +1100
@@ -1878,8 +1878,17 @@ relock:
 			continue;
 
 		/* Init gets no signals it doesn't want.  */
-		if (current == child_reaper)
+		if (current == child_reaper) {
+#ifdef CONFIG_COMPAT_VDSO
+			/* Gross hack: Old glibc asserts, not
+			   liking moved vdso (SuSE 9, FC1) */
+			if (signr == SIGABRT) {
+				signr = -1;
+				break;
+			}
+#endif				
 			continue;
+		}
 
 		if (sig_kernel_stop(signr)) {
 			/*