[PATCH 05/11] x86: add comments about various syscall instructions, no code changes
From: Denys Vlasenko
Date: Wed Jan 14 2015 - 16:49:39 EST
SYSCALL/SYSRET and SYSENTER/SYSEXIT have weird semantics.
Moreover, they differ in 32- and 64-bit mode.
What is saved? What is not? Is rsp set? Are interrupts disabled?
People tend to not remember these details well enough.
This patch adds comments which explain in detail
what registers are modified by each of these instructions.
The comments are placed immediately before corresponding
entry and exit points.
Signed-off-by: Denys Vlasenko <dvlasenk@xxxxxxxxxx>
CC: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
CC: Oleg Nesterov <oleg@xxxxxxxxxx>
CC: Borislav Petkov <bp@xxxxxxxxx>
CC: "H. Peter Anvin" <hpa@xxxxxxxxx>
CC: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
CC: Frederic Weisbecker <fweisbec@xxxxxxxxx>
CC: X86 ML <x86@xxxxxxxxxx>
CC: Alexei Starovoitov <ast@xxxxxxxxxxxx>
CC: Will Drewry <wad@xxxxxxxxxxxx>
CC: Kees Cook <keescook@xxxxxxxxxxxx>
CC: linux-kernel@xxxxxxxxxxxxxxx
---
arch/x86/ia32/ia32entry.S | 133 ++++++++++++++++++++++++++++-----------------
arch/x86/kernel/entry_64.S | 32 ++++++-----
2 files changed, 102 insertions(+), 63 deletions(-)
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 9f4c877..366f633 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -99,22 +99,25 @@ ENDPROC(native_irq_enable_sysexit)
/*
* 32bit SYSENTER instruction entry.
*
+ * SYSENTER loads ss, rsp, cs, and rip from previously programmed MSRs.
+ * IF and VM in rflags are cleared (IOW: interrupts are off).
+ * SYSENTER does not save anything on the stack,
+ * and does not save old rip (!!!) and rflags.
+ *
* Arguments:
- * %eax System call number.
- * %ebx Arg1
- * %ecx Arg2
- * %edx Arg3
- * %esi Arg4
- * %edi Arg5
- * %ebp user stack
- * 0(%ebp) Arg6
- *
- * Interrupts off.
- *
+ * eax system call number
+ * ebx arg1
+ * ecx arg2
+ * edx arg3
+ * esi arg4
+ * edi arg5
+ * ebp user stack
+ * 0(%ebp) arg6
+ *
* This is purely a fast path. For anything complicated we use the int 0x80
- * path below. Set up a complete hardware stack frame to share code
+ * path below. We set up a complete hardware stack frame to share code
* with the int 0x80 path.
- */
+ */
ENTRY(ia32_sysenter_target)
CFI_STARTPROC32 simple
CFI_SIGNAL_FRAME
@@ -128,6 +131,7 @@ ENTRY(ia32_sysenter_target)
* disabled irqs, here we enable it straight after entry:
*/
ENABLE_INTERRUPTS(CLBR_NONE)
+ /* Construct iret frame (ss,rsp,rflags,cs,rip) */
movl %ebp,%ebp /* zero extension */
pushq_cfi $__USER32_DS
/*CFI_REL_OFFSET ss,0*/
@@ -140,14 +144,19 @@ ENTRY(ia32_sysenter_target)
pushq_cfi $__USER32_CS
/*CFI_REL_OFFSET cs,0*/
movl %eax, %eax
+ /* Store thread_info->sysenter_return in rip stack slot */
pushq_cfi %r10
CFI_REL_OFFSET rip,0
+ /* Store orig_ax */
pushq_cfi %rax
+ /* Construct the rest of "struct pt_regs" */
cld
ALLOC_PT_GPREGS_ON_STACK
SAVE_C_REGS_EXCEPT_R891011
- /* no need to do an access_ok check here because rbp has been
- 32bit zero extended */
+ /*
+ * no need to do an access_ok check here because rbp has been
+ * 32bit zero extended
+ */
ASM_STAC
1: movl (%rbp),%ebp
_ASM_EXTABLE(1b,ia32_badarg)
@@ -184,6 +193,7 @@ sysexit_from_sys_call:
movl RIP(%rsp),%edx /* User %eip */
CFI_REGISTER rip,rdx
RESTORE_RSI_RDI
+ /* pop everything except ss,rsp,rflags slots */
REMOVE_PT_GPREGS_FROM_STACK 3*8
xorq %r8,%r8
xorq %r9,%r9
@@ -194,6 +204,10 @@ sysexit_from_sys_call:
popq_cfi %rcx /* User %esp */
CFI_REGISTER rsp,rcx
TRACE_IRQS_ON
+ /*
+ * 32bit SYSEXIT restores eip from edx, esp from ecx.
+ * cs and ss are loaded from MSRs.
+ */
ENABLE_INTERRUPTS_SYSEXIT32
CFI_RESTORE_STATE
@@ -274,23 +288,33 @@ ENDPROC(ia32_sysenter_target)
/*
* 32bit SYSCALL instruction entry.
*
+ * 32bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
+ * then loads new ss, cs, and rip from previously programmed MSRs.
+ * rflags gets masked by a value from another MSR (so CLD and CLAC
+ * are not needed). SYSCALL does not save anything on the stack
+ * and does not change rsp.
+ *
+ * Note: rflags saving+masking-with-MSR happens only in Long mode
+ * (in legacy 32bit mode, IF, RF and VM bits are cleared and that's it).
+ * Don't get confused: rflags saving+masking depends on Long Mode Active bit
+ * (EFER.LMA=1), NOT on bitness of userspace where SYSCALL executes
+ * or target CS descriptor's L bit (SYSCALL does not read segment descriptors).
+ *
* Arguments:
- * %eax System call number.
- * %ebx Arg1
- * %ecx return EIP
- * %edx Arg3
- * %esi Arg4
- * %edi Arg5
- * %ebp Arg2 [note: not saved in the stack frame, should not be touched]
- * %esp user stack
- * 0(%esp) Arg6
- *
- * Interrupts off.
- *
+ * eax system call number
+ * ecx return address
+ * ebx arg1
+ * ebp arg2 (note: not saved in the stack frame, should not be touched)
+ * edx arg3
+ * esi arg4
+ * edi arg5
+ * esp user stack
+ * 0(%esp) arg6
+ *
* This is purely a fast path. For anything complicated we use the int 0x80
- * path below. Set up a complete hardware stack frame to share code
- * with the int 0x80 path.
- */
+ * path below. We set up a complete hardware stack frame to share code
+ * with the int 0x80 path.
+ */
ENTRY(ia32_cstar_target)
CFI_STARTPROC32 simple
CFI_SIGNAL_FRAME
@@ -306,7 +330,7 @@ ENTRY(ia32_cstar_target)
* disabled irqs and here we enable it straight after entry:
*/
ENABLE_INTERRUPTS(CLBR_NONE)
- ALLOC_PT_GPREGS_ON_STACK 8
+ ALLOC_PT_GPREGS_ON_STACK 8 /* +8: space for orig_ax */
SAVE_C_REGS_EXCEPT_RCX_R891011
movl %eax,%eax /* zero extension */
movq %rax,ORIG_RAX(%rsp)
@@ -320,9 +344,11 @@ ENTRY(ia32_cstar_target)
/*CFI_REL_OFFSET rflags,EFLAGS*/
movq %r8,RSP(%rsp)
CFI_REL_OFFSET rsp,RSP
- /* no need to do an access_ok check here because r8 has been
- 32bit zero extended */
- /* hardware stack frame is complete now */
+ /* iret stack frame is complete now */
+ /*
+ * no need to do an access_ok check here because r8 has been
+ * 32bit zero extended
+ */
ASM_STAC
1: movl (%r8),%r9d
_ASM_EXTABLE(1b,ia32_badarg)
@@ -355,8 +381,15 @@ sysretl_from_sys_call:
TRACE_IRQS_ON
movl RSP(%rsp),%esp
CFI_RESTORE rsp
+ /*
+ * 64bit->32bit SYSRET restores eip from ecx,
+ * eflags from r11 (but RF and VM bits are forced to 0),
+ * cs and ss are loaded from MSRs.
+ * (Note: 32bit->32bit SYSRET is different: since r11
+ * does not exist, it merely sets eflags.IF=1).
+ */
USERGS_SYSRET32
-
+
#ifdef CONFIG_AUDITSYSCALL
cstar_auditsys:
CFI_RESTORE_STATE
@@ -394,26 +427,26 @@ ia32_badarg:
jmp ia32_sysret
CFI_ENDPROC
-/*
- * Emulated IA32 system calls via int 0x80.
+/*
+ * Emulated IA32 system calls via int 0x80.
*
- * Arguments:
- * %eax System call number.
- * %ebx Arg1
- * %ecx Arg2
- * %edx Arg3
- * %esi Arg4
- * %edi Arg5
- * %ebp Arg6 [note: not saved in the stack frame, should not be touched]
+ * Arguments:
+ * eax system call number
+ * ebx arg1
+ * ecx arg2
+ * edx arg3
+ * esi arg4
+ * edi arg5
+ * ebp arg6 (note: not saved in the stack frame, should not be touched)
*
* Notes:
- * Uses the same stack frame as the x86-64 version.
- * All registers except %eax must be saved (but ptrace may violate that)
+ * Uses the same stack frame as the x86-64 version.
+ * All registers except eax must be saved (but ptrace may violate that).
* Arguments are zero extended. For system calls that want sign extension and
* take long arguments a wrapper is needed. Most calls can just be called
* directly.
- * Assumes it is only called from user space and entered with interrupts off.
- */
+ * Assumes it is only called from user space and entered with interrupts off.
+ */
ENTRY(ia32_syscall)
CFI_STARTPROC32 simple
@@ -432,7 +465,7 @@ ENTRY(ia32_syscall)
*/
ENABLE_INTERRUPTS(CLBR_NONE)
movl %eax,%eax
- pushq_cfi %rax
+ pushq_cfi %rax /* store orig_ax */
cld
/* note the registers are not zero extended to the sf.
this could be a problem. */
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index c9259f4..3498274 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -255,25 +255,25 @@ ENTRY(ret_from_fork)
END(ret_from_fork)
/*
- * System call entry. Up to 6 arguments in registers are supported.
+ * 64bit SYSCALL instruction entry. Up to 6 arguments in registers.
*
- * SYSCALL does not save anything on the stack and does not change the
- * stack pointer. However, it does mask the flags register for us, so
- * CLD and CLAC are not needed.
- */
-
-/*
- * Register setup:
+ * 64bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
+ * then loads new ss, cs, and rip from previously programmed MSRs.
+ * rflags gets masked by a value from another MSR (so CLD and CLAC
+ * are not needed). SYSCALL does not save anything on the stack
+ * and does not change rsp.
+ *
+ * Registers on entry:
* rax system call number
+ * rcx return address
+ * r11 saved rflags (note: r11 is callee-clobbered register in C ABI)
* rdi arg0
- * rcx return address for syscall/sysret, C arg3
* rsi arg1
* rdx arg2
- * r10 arg3 (--> moved to rcx for C)
+ * r10 arg3 (needs to be moved to rcx to conform to C ABI)
* r8 arg4
* r9 arg5
- * r11 eflags for syscall/sysret, temporary for C
- * r12-r15,rbp,rbx saved by C code, not touched.
+ * (note: r12-r15,rbp,rbx are callee-preserved in C ABI)
*
* Interrupts are off on entry.
* Only called from user space.
@@ -301,13 +301,14 @@ ENTRY(system_call)
GLOBAL(system_call_after_swapgs)
movq %rsp,PER_CPU_VAR(old_rsp)
+ /* kernel_stack is set so that 5 slots (iret frame) are preallocated */
movq PER_CPU_VAR(kernel_stack),%rsp
/*
* No need to follow this irqs off/on section - it's straight
* and short:
*/
ENABLE_INTERRUPTS(CLBR_NONE)
- ALLOC_PT_GPREGS_ON_STACK 8
+ ALLOC_PT_GPREGS_ON_STACK 8 /* +8: space for orig_ax */
SAVE_C_REGS_EXCEPT_RAX_RCX
movq $-ENOSYS,RAX(%rsp)
movq_cfi rax,(ORIG_RAX)
@@ -350,6 +351,11 @@ sysret_check:
CFI_REGISTER rip,rcx
/*CFI_REGISTER rflags,r11*/
movq PER_CPU_VAR(old_rsp), %rsp
+ /*
+ * 64bit SYSRET restores rip from rcx,
+ * rflags from r11 (but RF and VM bits are forced to 0),
+ * cs and ss are loaded from MSRs.
+ */
USERGS_SYSRET64
CFI_RESTORE_STATE
--
1.8.1.4
--
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/