linux/arch/x86/vdso/vdso32/sysenter.S
H. Peter Anvin 7ca0758cdb x86-32, vdso: On system call restart after SYSENTER, use int $0x80
When we enter a 32-bit system call via SYSENTER or SYSCALL, we shuffle
the arguments to match the int $0x80 calling convention.  This was
probably a design mistake, but it's what it is now.  This causes
errors if the system call as to be restarted.

For SYSENTER, we have to invoke the instruction from the vdso as the
return address is hardcoded.  Accordingly, we can simply replace the
jump in the vdso with an int $0x80 instruction and use the slower
entry point for a post-restart.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Link: http://lkml.kernel.org/r/CA%2B55aFztZ=r5wa0x26KJQxvZOaQq8s2v3u50wCyJcA-Sc4g8gQ@mail.gmail.com
Cc: <stable@kernel.org>
2011-08-23 16:20:10 -07:00

117 lines
3.7 KiB
ArmAsm

/*
* Code for the vDSO. This version uses the sysenter instruction.
*
* First get the common code for the sigreturn entry points.
* This must come first.
*/
#include "sigreturn.S"
/*
* The caller puts arg2 in %ecx, which gets pushed. The kernel will use
* %ecx itself for arg2. The pushing is because the sysexit instruction
* (found in entry.S) requires that we clobber %ecx with the desired %esp.
* User code might expect that %ecx is unclobbered though, as it would be
* for returning via the iret instruction, so we must push and pop.
*
* The caller puts arg3 in %edx, which the sysexit instruction requires
* for %eip. Thus, exactly as for arg2, we must push and pop.
*
* Arg6 is different. The caller puts arg6 in %ebp. Since the sysenter
* instruction clobbers %esp, the user's %esp won't even survive entry
* into the kernel. We store %esp in %ebp. Code in entry.S must fetch
* arg6 from the stack.
*
* You can not use this vsyscall for the clone() syscall because the
* three words on the parent stack do not get copied to the child.
*/
.text
.globl __kernel_vsyscall
.type __kernel_vsyscall,@function
ALIGN
__kernel_vsyscall:
.LSTART_vsyscall:
push %ecx
.Lpush_ecx:
push %edx
.Lpush_edx:
push %ebp
.Lenter_kernel:
movl %esp,%ebp
sysenter
/* 7: align return point with nop's to make disassembly easier */
.space 7,0x90
/* 14: System call restart point is here! (SYSENTER_RETURN-2) */
int $0x80
/* 16: System call normal return point is here! */
VDSO32_SYSENTER_RETURN: /* Symbol used by sysenter.c via vdso32-syms.h */
pop %ebp
.Lpop_ebp:
pop %edx
.Lpop_edx:
pop %ecx
.Lpop_ecx:
ret
.LEND_vsyscall:
.size __kernel_vsyscall,.-.LSTART_vsyscall
.previous
.section .eh_frame,"a",@progbits
.LSTARTFRAMEDLSI:
.long .LENDCIEDLSI-.LSTARTCIEDLSI
.LSTARTCIEDLSI:
.long 0 /* CIE ID */
.byte 1 /* Version number */
.string "zR" /* NUL-terminated augmentation string */
.uleb128 1 /* Code alignment factor */
.sleb128 -4 /* Data alignment factor */
.byte 8 /* Return address register column */
.uleb128 1 /* Augmentation value length */
.byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */
.byte 0x0c /* DW_CFA_def_cfa */
.uleb128 4
.uleb128 4
.byte 0x88 /* DW_CFA_offset, column 0x8 */
.uleb128 1
.align 4
.LENDCIEDLSI:
.long .LENDFDEDLSI-.LSTARTFDEDLSI /* Length FDE */
.LSTARTFDEDLSI:
.long .LSTARTFDEDLSI-.LSTARTFRAMEDLSI /* CIE pointer */
.long .LSTART_vsyscall-. /* PC-relative start address */
.long .LEND_vsyscall-.LSTART_vsyscall
.uleb128 0
/* What follows are the instructions for the table generation.
We have to record all changes of the stack pointer. */
.byte 0x40 + (.Lpush_ecx-.LSTART_vsyscall) /* DW_CFA_advance_loc */
.byte 0x0e /* DW_CFA_def_cfa_offset */
.byte 0x08 /* RA at offset 8 now */
.byte 0x40 + (.Lpush_edx-.Lpush_ecx) /* DW_CFA_advance_loc */
.byte 0x0e /* DW_CFA_def_cfa_offset */
.byte 0x0c /* RA at offset 12 now */
.byte 0x40 + (.Lenter_kernel-.Lpush_edx) /* DW_CFA_advance_loc */
.byte 0x0e /* DW_CFA_def_cfa_offset */
.byte 0x10 /* RA at offset 16 now */
.byte 0x85, 0x04 /* DW_CFA_offset %ebp -16 */
/* Finally the epilogue. */
.byte 0x40 + (.Lpop_ebp-.Lenter_kernel) /* DW_CFA_advance_loc */
.byte 0x0e /* DW_CFA_def_cfa_offset */
.byte 0x0c /* RA at offset 12 now */
.byte 0xc5 /* DW_CFA_restore %ebp */
.byte 0x40 + (.Lpop_edx-.Lpop_ebp) /* DW_CFA_advance_loc */
.byte 0x0e /* DW_CFA_def_cfa_offset */
.byte 0x08 /* RA at offset 8 now */
.byte 0x40 + (.Lpop_ecx-.Lpop_edx) /* DW_CFA_advance_loc */
.byte 0x0e /* DW_CFA_def_cfa_offset */
.byte 0x04 /* RA at offset 4 now */
.align 4
.LENDFDEDLSI:
.previous
/*
* Emit a symbol with the size of this .eh_frame data,
* to verify it matches the other versions.
*/
VDSO32_vsyscall_eh_frame_size = (.LENDFDEDLSI-.LSTARTFRAMEDLSI)