[PATCH] unwinding for vsyscall code

Now that the kernel provides code user programs are executing directly
(I mean the vsyscall code on x86) it is necessary to add unwind
information for that code as well.  The unwind information is used not
only in C++ code.

This patch adds a AT_SYSINFO_EH_FRAME ELF aux-table value that points to
the unwinding block description for the sysinfo frame, and makes sure
the AT_* value is passed to applications.  It defines the static data
for the unwind blocks (two, one for int80 and the other for sysenter),
and finally adds code to copy the data in place.

arch/i386/kernel/sysenter.c

@@ -12,6 +12,7 @@
 #include <linux/sched.h>
 #include <linux/gfp.h>
 #include <linux/string.h>
+#include <linux/elf.h>
 
 #include <asm/cpufeature.h>
 #include <asm/msr.h>
@@ -52,11 +53,47 @@ void enable_sep_cpu(void *info)
 
 static int __init sysenter_setup(void)
 {
-	static const char int80[] = {
+	static const char __initdata int80[] = {
 		0xcd, 0x80,		/* int $0x80 */
 		0xc3			/* ret */
 	};
-	static const char sysent[] = {
+	/* Unwind information for the int80 code.  Keep track of
+	   where the return address is stored.  */
+	static const char __initdata int80_eh_frame[] = {
+	/* First the Common Information Entry (CIE):  */
+		0x14, 0x00, 0x00, 0x00,	/* Length of the CIE */
+		0x00, 0x00, 0x00, 0x00,	/* CIE Identifier Tag */
+		0x01,			/* CIE Version */
+		'z', 'R', 0x00,		/* CIE Augmentation */
+		0x01,			/* CIE Code Alignment Factor */
+		0x7c,			/* CIE Data Alignment Factor */
+		0x08,			/* CIE RA Column */
+		0x01,			/* Augmentation size */
+		0x1b,			/* FDE Encoding (pcrel sdata4) */
+		0x0c,			/* DW_CFA_def_cfa */
+		0x04,
+		0x04,
+		0x88,			/* DW_CFA_offset, column 0x8 */
+		0x01,
+		0x00,			/* padding */
+		0x00,
+	/* Now the FDE which contains the instructions for the frame.  */
+		0x0a, 0x00, 0x00, 0x00,	/* FDE Length */
+		0x1c, 0x00, 0x00, 0x00,	/* FDE CIE offset */
+	/* The PC-relative offset to the beginning of the code this
+	   FDE covers.  The computation below assumes that the offset
+	   can be represented in one byte.  Change if this is not true
+	   anymore.  The offset from the beginning of the .eh_frame
+	   is represented by EH_FRAME_OFFSET.  The word with the offset
+	   starts at byte 0x20 of the .eh_frame.  */
+		0x100 - (EH_FRAME_OFFSET + 0x20),
+		0xff, 0xff, 0xff,	/* FDE initial location */
+		3,			/* FDE address range */
+		0x00			/* Augmentation size */
+	/* The code does not change the stack pointer.  We need not
+	   record any operations.  */
+	};
+	static const char __initdata sysent[] = {
 		0x51,			/* push %ecx */
 		0x52,			/* push %edx */
 		0x55,			/* push %ebp */
@@ -76,13 +113,71 @@ static int __init sysenter_setup(void)
 		0x59,			/* pop %ecx */
 		0xc3			/* ret */
 	};
-	static const char sigreturn[] = {
+	/* Unwind information for the sysenter code.  Keep track of
+	   where the return address is stored.  */
+	static const char __initdata sysent_eh_frame[] = {
+	/* First the Common Information Entry (CIE):  */
+		0x14, 0x00, 0x00, 0x00,	/* Length of the CIE */
+		0x00, 0x00, 0x00, 0x00,	/* CIE Identifier Tag */
+		0x01,			/* CIE Version */
+		'z', 'R', 0x00,		/* CIE Augmentation */
+		0x01,			/* CIE Code Alignment Factor */
+		0x7c,			/* CIE Data Alignment Factor */
+		0x08,			/* CIE RA Column */
+		0x01,			/* Augmentation size */
+		0x1b,			/* FDE Encoding (pcrel sdata4) */
+		0x0c,			/* DW_CFA_def_cfa */
+		0x04,
+		0x04,
+		0x88,			/* DW_CFA_offset, column 0x8 */
+		0x01,
+		0x00,			/* padding */
+		0x00,
+	/* Now the FDE which contains the instructions for the frame.  */
+		0x22, 0x00, 0x00, 0x00,	/* FDE Length */
+		0x1c, 0x00, 0x00, 0x00,	/* FDE CIE offset */
+	/* The PC-relative offset to the beginning of the code this
+	   FDE covers.  The computation below assumes that the offset
+	   can be represented in one byte.  Change if this is not true
+	   anymore.  The offset from the beginning of the .eh_frame
+	   is represented by EH_FRAME_OFFSET.  The word with the offset
+	   starts at byte 0x20 of the .eh_frame.  */
+		0x100 - (EH_FRAME_OFFSET + 0x20),
+		0xff, 0xff, 0xff,	/* FDE initial location */
+		0x14, 0x00, 0x00, 0x00,	/* FDE address range */
+		0x00,			/* Augmentation size */
+	/* What follows are the instructions for the table generation.
+	   We have to record all changes of the stack pointer and
+	   callee-saved registers.  */
+		0x41,			/* DW_CFA_advance_loc+1, push %ecx */
+		0x0e,			/* DW_CFA_def_cfa_offset */
+		0x08,			/* RA at offset 8 now */
+		0x41,			/* DW_CFA_advance_loc+1, push %edx */
+		0x0e,			/* DW_CFA_def_cfa_offset */
+		0x0c,			/* RA at offset 12 now */
+		0x41,			/* DW_CFA_advance_loc+1, push %ebp */
+		0x0e,			/* DW_CFA_def_cfa_offset */
+		0x10,			/* RA at offset 16 now */
+		0x85, 0x04,		/* DW_CFA_offset %ebp -16 */
+	/* Finally the epilogue.  */
+		0x4e,			/* DW_CFA_advance_loc+14, pop %ebx */
+		0x0e,			/* DW_CFA_def_cfa_offset */
+		0x12,			/* RA at offset 12 now */
+		0xc5,			/* DW_CFA_restore %ebp */
+		0x41,			/* DW_CFA_advance_loc+1, pop %edx */
+		0x0e,			/* DW_CFA_def_cfa_offset */
+		0x08,			/* RA at offset 8 now */
+		0x41,			/* DW_CFA_advance_loc+1, pop %ecx */
+		0x0e,			/* DW_CFA_def_cfa_offset */
+		0x04			/* RA at offset 4 now */
+	};
+	static const char __initdata sigreturn[] = {
 	/* 32: sigreturn point */
 		0x58,				/* popl %eax */
 		0xb8, __NR_sigreturn, 0, 0, 0,	/* movl $__NR_sigreturn, %eax */
 		0xcd, 0x80,			/* int $0x80 */
 	};
-	static const char rt_sigreturn[] = {
+	static const char __initdata rt_sigreturn[] = {
 	/* 64: rt_sigreturn point */
 		0xb8, __NR_rt_sigreturn, 0, 0, 0,	/* movl $__NR_rt_sigreturn, %eax */
 		0xcd, 0x80,			/* int $0x80 */
@@ -93,10 +188,14 @@ static int __init sysenter_setup(void)
 	memcpy((void *) page, int80, sizeof(int80));
 	memcpy((void *)(page + 32), sigreturn, sizeof(sigreturn));
 	memcpy((void *)(page + 64), rt_sigreturn, sizeof(rt_sigreturn));
+	memcpy((void *)(page + EH_FRAME_OFFSET), int80_eh_frame,
+	       sizeof(int80_eh_frame));
 	if (!boot_cpu_has(X86_FEATURE_SEP))
 		return 0;
 
 	memcpy((void *) page, sysent, sizeof(sysent));
+	memcpy((void *)(page + EH_FRAME_OFFSET), sysent_eh_frame,
+	       sizeof(sysent_eh_frame));
 	on_each_cpu(enable_sep_cpu, NULL, 1, 1);
 	return 0;
 }

include/asm-i386/elf.h

@@ -100,7 +100,8 @@ typedef struct user_fxsr_struct elf_fpxregset_t;
  * Architecture-neutral AT_ values in 0-17, leave some room
  * for more of them, start the x86-specific ones at 32.
  */
-#define AT_SYSINFO	32
+#define AT_SYSINFO		32
+#define AT_SYSINFO_EH_FRAME	33
 
 #ifdef __KERNEL__
 #define SET_PERSONALITY(ex, ibcs2) set_personality((ibcs2)?PER_SVR4:PER_LINUX)
@@ -118,9 +119,15 @@ extern void dump_smp_unlazy_fpu(void);
 #define ELF_CORE_SYNC dump_smp_unlazy_fpu
 #endif
 
-#define ARCH_DLINFO					\
-do {							\
-		NEW_AUX_ENT(AT_SYSINFO, 0xffffe000);	\
+/* Offset from the beginning of the page where the .eh_frame information
+   for the code in the vsyscall page starts.  */
+#define EH_FRAME_OFFSET 96
+
+#define ARCH_DLINFO						\
+do {								\
+		NEW_AUX_ENT(AT_SYSINFO, 0xffffe000);		\
+		NEW_AUX_ENT(AT_SYSINFO_EH_FRAME,		\
+			    0xffffe000 + EH_FRAME_OFFSET);	\
 } while (0)
 
 #endif