* [PATCH 1/6] x86: entry_64.S: delete unused code
2014-08-04 13:19 [PATCH 0/6 v2] x86: entry_64.S: always allocate complete "struct pt_regs" Denys Vlasenko
@ 2014-08-04 13:19 ` Denys Vlasenko
2014-08-04 13:19 ` [PATCH 2/6] x86: open-code register save/restore in trace_hardirqs thunks Denys Vlasenko
` (4 subsequent siblings)
5 siblings, 0 replies; 12+ messages in thread
From: Denys Vlasenko @ 2014-08-04 13:19 UTC (permalink / raw)
To: linux-kernel
Cc: Denys Vlasenko, Oleg Nesterov, H. Peter Anvin, Andy Lutomirski,
Frederic Weisbecker, X86 ML, Alexei Starovoitov, Will Drewry,
Kees Cook
A define, two macros and an unreferenced bit of assembly are gone.
Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com>
CC: Oleg Nesterov <oleg@redhat.com>
CC: "H. Peter Anvin" <hpa@zytor.com>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Frederic Weisbecker <fweisbec@gmail.com>
CC: X86 ML <x86@kernel.org>
CC: Alexei Starovoitov <ast@plumgrid.com>
CC: Will Drewry <wad@chromium.org>
CC: Kees Cook <keescook@chromium.org>
CC: linux-kernel@vger.kernel.org
---
arch/x86/include/asm/calling.h | 1 -
arch/x86/kernel/entry_64.S | 34 ----------------------------------
2 files changed, 35 deletions(-)
diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h
index cb4c73b..e176cea 100644
--- a/arch/x86/include/asm/calling.h
+++ b/arch/x86/include/asm/calling.h
@@ -83,7 +83,6 @@ For 32-bit we have the following conventions - kernel is built with
#define SS 160
#define ARGOFFSET R11
-#define SWFRAME ORIG_RAX
.macro SAVE_ARGS addskip=0, save_rcx=1, save_r891011=1
subq $9*8+\addskip, %rsp
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index b25ca96..dbfd037 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -155,27 +155,6 @@ ENDPROC(native_usergs_sysret64)
movq \tmp,R11+\offset(%rsp)
.endm
- .macro FAKE_STACK_FRAME child_rip
- /* push in order ss, rsp, eflags, cs, rip */
- xorl %eax, %eax
- pushq_cfi $__KERNEL_DS /* ss */
- /*CFI_REL_OFFSET ss,0*/
- pushq_cfi %rax /* rsp */
- CFI_REL_OFFSET rsp,0
- pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED) /* eflags - interrupts on */
- /*CFI_REL_OFFSET rflags,0*/
- pushq_cfi $__KERNEL_CS /* cs */
- /*CFI_REL_OFFSET cs,0*/
- pushq_cfi \child_rip /* rip */
- CFI_REL_OFFSET rip,0
- pushq_cfi %rax /* orig rax */
- .endm
-
- .macro UNFAKE_STACK_FRAME
- addq $8*6, %rsp
- CFI_ADJUST_CFA_OFFSET -(6*8)
- .endm
-
/*
* initial frame state for interrupts (and exceptions without error code)
*/
@@ -640,19 +619,6 @@ END(\label)
FORK_LIKE vfork
FIXED_FRAME stub_iopl, sys_iopl
-ENTRY(ptregscall_common)
- DEFAULT_FRAME 1 8 /* offset 8: return address */
- RESTORE_TOP_OF_STACK %r11, 8
- movq_cfi_restore R15+8, r15
- movq_cfi_restore R14+8, r14
- movq_cfi_restore R13+8, r13
- movq_cfi_restore R12+8, r12
- movq_cfi_restore RBP+8, rbp
- movq_cfi_restore RBX+8, rbx
- ret $REST_SKIP /* pop extended registers */
- CFI_ENDPROC
-END(ptregscall_common)
-
ENTRY(stub_execve)
CFI_STARTPROC
addq $8, %rsp
--
1.8.1.4
^ permalink raw reply related [flat|nested] 12+ messages in thread* [PATCH 2/6] x86: open-code register save/restore in trace_hardirqs thunks
2014-08-04 13:19 [PATCH 0/6 v2] x86: entry_64.S: always allocate complete "struct pt_regs" Denys Vlasenko
2014-08-04 13:19 ` [PATCH 1/6] x86: entry_64.S: delete unused code Denys Vlasenko
@ 2014-08-04 13:19 ` Denys Vlasenko
2014-08-04 13:19 ` [PATCH 3/6] x86: entry_64.S: fold SAVE_ARGS_IRQ macro into its sole user Denys Vlasenko
` (3 subsequent siblings)
5 siblings, 0 replies; 12+ messages in thread
From: Denys Vlasenko @ 2014-08-04 13:19 UTC (permalink / raw)
To: linux-kernel
Cc: Denys Vlasenko, Oleg Nesterov, H. Peter Anvin, Andy Lutomirski,
Frederic Weisbecker, X86 ML, Alexei Starovoitov, Will Drewry,
Kees Cook
This is a preparatory patch for change in "struct pt_regs"
handling in entry_64.S.
trace_hardirqs thunks were (ab)using a part of pt_regs
handling code, namely SAVE_ARGS/RESTORE_ARGS macros,
to save/restore registers across C function calls.
Since SAVE_ARGS is going to be changed, open-code
register saving/restoring here.
Incidentally, this removes a bit of dead code:
one SAVE_ARGS was just to emit a CFI annotation,
but it also generated unreachable assembly insns.
Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com>
CC: Oleg Nesterov <oleg@redhat.com>
CC: "H. Peter Anvin" <hpa@zytor.com>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Frederic Weisbecker <fweisbec@gmail.com>
CC: X86 ML <x86@kernel.org>
CC: Alexei Starovoitov <ast@plumgrid.com>
CC: Will Drewry <wad@chromium.org>
CC: Kees Cook <keescook@chromium.org>
CC: linux-kernel@vger.kernel.org
---
arch/x86/lib/thunk_64.S | 29 ++++++++++++++++++++++++-----
1 file changed, 24 insertions(+), 5 deletions(-)
diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/lib/thunk_64.S
index 92d9fea..c1c9131 100644
--- a/arch/x86/lib/thunk_64.S
+++ b/arch/x86/lib/thunk_64.S
@@ -16,10 +16,20 @@
\name:
CFI_STARTPROC
- /* this one pushes 9 elems, the next one would be %rIP */
- SAVE_ARGS
+ subq $9*8, %rsp
+ CFI_ADJUST_CFA_OFFSET 9*8
+ movq_cfi rdi, 8*8
+ movq_cfi rsi, 7*8
+ movq_cfi rdx, 6*8
+ movq_cfi rcx, 5*8
+ movq_cfi rax, 4*8
+ movq_cfi r8, 3*8
+ movq_cfi r9, 2*8
+ movq_cfi r10, 1*8
+ movq_cfi r11, 0*8
.if \put_ret_addr_in_rdi
+ /* 9*8(%rsp) is return addr on stack */
movq_cfi_restore 9*8, rdi
.endif
@@ -38,11 +48,20 @@
THUNK lockdep_sys_exit_thunk,lockdep_sys_exit
#endif
- /* SAVE_ARGS below is used only for the .cfi directives it contains. */
CFI_STARTPROC
- SAVE_ARGS
+ CFI_ADJUST_CFA_OFFSET 9*8
restore:
- RESTORE_ARGS
+ movq_cfi_restore 0*8, r11
+ movq_cfi_restore 1*8, r10
+ movq_cfi_restore 2*8, r9
+ movq_cfi_restore 3*8, r8
+ movq_cfi_restore 4*8, rax
+ movq_cfi_restore 5*8, rcx
+ movq_cfi_restore 6*8, rdx
+ movq_cfi_restore 7*8, rsi
+ movq_cfi_restore 8*8, rdi
+ addq 9*8, %rsp
+ CFI_ADJUST_CFA_OFFSET -9*8
ret
CFI_ENDPROC
_ASM_NOKPROBE(restore)
--
1.8.1.4
^ permalink raw reply related [flat|nested] 12+ messages in thread* [PATCH 3/6] x86: entry_64.S: fold SAVE_ARGS_IRQ macro into its sole user
2014-08-04 13:19 [PATCH 0/6 v2] x86: entry_64.S: always allocate complete "struct pt_regs" Denys Vlasenko
2014-08-04 13:19 ` [PATCH 1/6] x86: entry_64.S: delete unused code Denys Vlasenko
2014-08-04 13:19 ` [PATCH 2/6] x86: open-code register save/restore in trace_hardirqs thunks Denys Vlasenko
@ 2014-08-04 13:19 ` Denys Vlasenko
2014-08-04 13:19 ` [PATCH 4/6] x86: entry_64.S: always allocate complete "struct pt_regs" Denys Vlasenko
` (2 subsequent siblings)
5 siblings, 0 replies; 12+ messages in thread
From: Denys Vlasenko @ 2014-08-04 13:19 UTC (permalink / raw)
To: linux-kernel
Cc: Denys Vlasenko, Oleg Nesterov, H. Peter Anvin, Andy Lutomirski,
Frederic Weisbecker, X86 ML, Alexei Starovoitov, Will Drewry,
Kees Cook
No code changes.
This is a preparatory patch for change in "struct pt_regs" handling.
Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com>
CC: Oleg Nesterov <oleg@redhat.com>
CC: "H. Peter Anvin" <hpa@zytor.com>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Frederic Weisbecker <fweisbec@gmail.com>
CC: X86 ML <x86@kernel.org>
CC: Alexei Starovoitov <ast@plumgrid.com>
CC: Will Drewry <wad@chromium.org>
CC: Kees Cook <keescook@chromium.org>
CC: linux-kernel@vger.kernel.org
---
arch/x86/kernel/entry_64.S | 88 ++++++++++++++++++++++------------------------
1 file changed, 42 insertions(+), 46 deletions(-)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index dbfd037..37f7d95 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -218,51 +218,6 @@ ENDPROC(native_usergs_sysret64)
CFI_REL_OFFSET r15, R15+\offset
.endm
-/* save partial stack frame */
- .macro SAVE_ARGS_IRQ
- cld
- /* start from rbp in pt_regs and jump over */
- movq_cfi rdi, (RDI-RBP)
- movq_cfi rsi, (RSI-RBP)
- movq_cfi rdx, (RDX-RBP)
- movq_cfi rcx, (RCX-RBP)
- movq_cfi rax, (RAX-RBP)
- movq_cfi r8, (R8-RBP)
- movq_cfi r9, (R9-RBP)
- movq_cfi r10, (R10-RBP)
- movq_cfi r11, (R11-RBP)
-
- /* Save rbp so that we can unwind from get_irq_regs() */
- movq_cfi rbp, 0
-
- /* Save previous stack value */
- movq %rsp, %rsi
-
- leaq -RBP(%rsp),%rdi /* arg1 for handler */
- testl $3, CS-RBP(%rsi)
- je 1f
- SWAPGS
- /*
- * irq_count is used to check if a CPU is already on an interrupt stack
- * or not. While this is essentially redundant with preempt_count it is
- * a little cheaper to use a separate counter in the PDA (short of
- * moving irq_enter into assembly, which would be too much work)
- */
-1: incl PER_CPU_VAR(irq_count)
- cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
- CFI_DEF_CFA_REGISTER rsi
-
- /* Store previous stack value */
- pushq %rsi
- CFI_ESCAPE 0x0f /* DW_CFA_def_cfa_expression */, 6, \
- 0x77 /* DW_OP_breg7 */, 0, \
- 0x06 /* DW_OP_deref */, \
- 0x08 /* DW_OP_const1u */, SS+8-RBP, \
- 0x22 /* DW_OP_plus */
- /* We entered an interrupt context - irqs are off: */
- TRACE_IRQS_OFF
- .endm
-
ENTRY(save_paranoid)
XCPT_FRAME 1 RDI+8
cld
@@ -731,7 +686,48 @@ END(interrupt)
/* reserve pt_regs for scratch regs and rbp */
subq $ORIG_RAX-RBP, %rsp
CFI_ADJUST_CFA_OFFSET ORIG_RAX-RBP
- SAVE_ARGS_IRQ
+ cld
+ /* start from rbp in pt_regs and jump over */
+ movq_cfi rdi, (RDI-RBP)
+ movq_cfi rsi, (RSI-RBP)
+ movq_cfi rdx, (RDX-RBP)
+ movq_cfi rcx, (RCX-RBP)
+ movq_cfi rax, (RAX-RBP)
+ movq_cfi r8, (R8-RBP)
+ movq_cfi r9, (R9-RBP)
+ movq_cfi r10, (R10-RBP)
+ movq_cfi r11, (R11-RBP)
+
+ /* Save rbp so that we can unwind from get_irq_regs() */
+ movq_cfi rbp, 0
+
+ /* Save previous stack value */
+ movq %rsp, %rsi
+
+ leaq -RBP(%rsp),%rdi /* arg1 for handler */
+ testl $3, CS-RBP(%rsi)
+ je 1f
+ SWAPGS
+ /*
+ * irq_count is used to check if a CPU is already on an interrupt stack
+ * or not. While this is essentially redundant with preempt_count it is
+ * a little cheaper to use a separate counter in the PDA (short of
+ * moving irq_enter into assembly, which would be too much work)
+ */
+1: incl PER_CPU_VAR(irq_count)
+ cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
+ CFI_DEF_CFA_REGISTER rsi
+
+ /* Store previous stack value */
+ pushq %rsi
+ CFI_ESCAPE 0x0f /* DW_CFA_def_cfa_expression */, 6, \
+ 0x77 /* DW_OP_breg7 */, 0, \
+ 0x06 /* DW_OP_deref */, \
+ 0x08 /* DW_OP_const1u */, SS+8-RBP, \
+ 0x22 /* DW_OP_plus */
+ /* We entered an interrupt context - irqs are off: */
+ TRACE_IRQS_OFF
+
call \func
.endm
--
1.8.1.4
^ permalink raw reply related [flat|nested] 12+ messages in thread* [PATCH 4/6] x86: entry_64.S: always allocate complete "struct pt_regs"
2014-08-04 13:19 [PATCH 0/6 v2] x86: entry_64.S: always allocate complete "struct pt_regs" Denys Vlasenko
` (2 preceding siblings ...)
2014-08-04 13:19 ` [PATCH 3/6] x86: entry_64.S: fold SAVE_ARGS_IRQ macro into its sole user Denys Vlasenko
@ 2014-08-04 13:19 ` Denys Vlasenko
2014-08-04 17:05 ` [PATCH?] x86: reimplement ___preempt_schedule*() using THUNK helpers Oleg Nesterov
2014-08-04 13:19 ` [PATCH 5/6] x86: mass removal of ARGOFFSET Denys Vlasenko
2014-08-04 13:19 ` [PATCH 6/6] x86: rename some macros and labels, no code changes Denys Vlasenko
5 siblings, 1 reply; 12+ messages in thread
From: Denys Vlasenko @ 2014-08-04 13:19 UTC (permalink / raw)
To: linux-kernel
Cc: Denys Vlasenko, Oleg Nesterov, H. Peter Anvin, Andy Lutomirski,
Frederic Weisbecker, X86 ML, Alexei Starovoitov, Will Drewry,
Kees Cook
64-bit code was using six stack slots fewer by not saving/restoring
registers which a callee-preserved according to C ABI,
and not allocating space for them.
Only when syscall needed a complete "struct pt_regs",
the complete area was allocated and filled in.
As an additional twist, on interrupt entry a "slightly less truncated pt_regs"
trick is used, to make nested interrupt stacks easier to unwind.
This proved to be a source of significant obfuscation and subtle bugs.
For example, stub_fork had to pop the return address,
extend the struct, save registers, and push return address back. Ugly.
ia32_ptregs_common pops return address and "returns" via jmp insn,
throwing a wrench into CPU return stack cache.
This patch changes code to always allocate a complete "struct pt_regs".
The saving of registers is still done lazily.
"Partial pt_regs" trick on interrupt stack is retained, but with added comments
which explain what we are doing, and why. Existing comments are improved.
Macros which manipulate "struct pt_regs" on stack are reworked:
ALLOC_PTREGS_ON_STACK allocates the structure.
SAVE_C_REGS saves to it those registers which are clobbered by C code.
SAVE_EXTRA_REGS saves to it all other registers.
Corresponding RESTORE_* and REMOVE_PTREGS_FROM_STACK macros reverse it.
ia32_ptregs_common, stub_fork and friends lost their ugly dance with
return pointer.
LOAD_ARGS32 in ia32entry.S now uses symbolic stack offsets
instead of magic numbers.
error_entry and save_paranoid now use SAVE_C_REGS + SAVE_EXTRA_REGS
instead of having it open-coded yet again.
Misleading and slightly wrong comments in "struct pt_regs" are fixed
(four instances).
Patch was run-tested: 64-bit executables, 32-bit executables,
strace works.
Timing tests did not show measurable difference in 32-bit
and 64-bit syscalls.
Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com>
CC: Oleg Nesterov <oleg@redhat.com>
CC: "H. Peter Anvin" <hpa@zytor.com>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Frederic Weisbecker <fweisbec@gmail.com>
CC: X86 ML <x86@kernel.org>
CC: Alexei Starovoitov <ast@plumgrid.com>
CC: Will Drewry <wad@chromium.org>
CC: Kees Cook <keescook@chromium.org>
CC: linux-kernel@vger.kernel.org
---
arch/x86/ia32/ia32entry.S | 47 +++----
arch/x86/include/asm/calling.h | 217 ++++++++++++++++-----------------
arch/x86/include/asm/irqflags.h | 4 +-
arch/x86/include/asm/ptrace.h | 13 +-
arch/x86/include/uapi/asm/ptrace-abi.h | 16 ++-
arch/x86/include/uapi/asm/ptrace.h | 13 +-
arch/x86/kernel/entry_64.S | 191 +++++++++++------------------
arch/x86/kernel/preempt.S | 16 ++-
8 files changed, 249 insertions(+), 268 deletions(-)
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 4299eb0..ef9ee16 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -62,12 +62,12 @@
*/
.macro LOAD_ARGS32 offset, _r9=0
.if \_r9
- movl \offset+16(%rsp),%r9d
+ movl \offset+R9(%rsp),%r9d
.endif
- movl \offset+40(%rsp),%ecx
- movl \offset+48(%rsp),%edx
- movl \offset+56(%rsp),%esi
- movl \offset+64(%rsp),%edi
+ movl \offset+RCX(%rsp),%ecx
+ movl \offset+RDX(%rsp),%edx
+ movl \offset+RSI(%rsp),%esi
+ movl \offset+RDI(%rsp),%edi
movl %eax,%eax /* zero extension */
.endm
@@ -144,7 +144,8 @@ ENTRY(ia32_sysenter_target)
CFI_REL_OFFSET rip,0
pushq_cfi %rax
cld
- SAVE_ARGS 0,1,0
+ ALLOC_PTREGS_ON_STACK
+ SAVE_C_REGS_EXCEPT_R891011
/* no need to do an access_ok check here because rbp has been
32bit zero extended */
ASM_STAC
@@ -172,7 +173,8 @@ sysexit_from_sys_call:
andl $~0x200,EFLAGS-R11(%rsp)
movl RIP-R11(%rsp),%edx /* User %eip */
CFI_REGISTER rip,rdx
- RESTORE_ARGS 0,24,0,0,0,0
+ RESTORE_RSI_RDI
+ REMOVE_PTREGS_FROM_STACK 8*3
xorq %r8,%r8
xorq %r9,%r9
xorq %r10,%r10
@@ -240,13 +242,13 @@ sysenter_tracesys:
testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
jz sysenter_auditsys
#endif
- SAVE_REST
+ SAVE_EXTRA_REGS
CLEAR_RREGS
movq $-ENOSYS,RAX(%rsp)/* ptrace can change this for a bad syscall */
movq %rsp,%rdi /* &pt_regs -> arg1 */
call syscall_trace_enter
LOAD_ARGS32 ARGOFFSET /* reload args from stack in case ptrace changed it */
- RESTORE_REST
+ RESTORE_EXTRA_REGS
cmpq $(IA32_NR_syscalls-1),%rax
ja int_ret_from_sys_call /* sysenter_tracesys has set RAX(%rsp) */
jmp sysenter_do_call
@@ -288,7 +290,8 @@ ENTRY(ia32_cstar_target)
* disabled irqs and here we enable it straight after entry:
*/
ENABLE_INTERRUPTS(CLBR_NONE)
- SAVE_ARGS 8,0,0
+ ALLOC_PTREGS_ON_STACK 8
+ SAVE_C_REGS_EXCEPT_RCX_R891011
movl %eax,%eax /* zero extension */
movq %rax,ORIG_RAX-ARGOFFSET(%rsp)
movq %rcx,RIP-ARGOFFSET(%rsp)
@@ -325,7 +328,7 @@ cstar_dispatch:
jnz sysretl_audit
sysretl_from_sys_call:
andl $~TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
- RESTORE_ARGS 0,-ARG_SKIP,0,0,0
+ RESTORE_RSI_RDI_RDX
movl RIP-ARGOFFSET(%rsp),%ecx
CFI_REGISTER rip,rcx
movl EFLAGS-ARGOFFSET(%rsp),%r11d
@@ -356,13 +359,13 @@ cstar_tracesys:
jz cstar_auditsys
#endif
xchgl %r9d,%ebp
- SAVE_REST
+ SAVE_EXTRA_REGS
CLEAR_RREGS 0, r9
movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
movq %rsp,%rdi /* &pt_regs -> arg1 */
call syscall_trace_enter
LOAD_ARGS32 ARGOFFSET, 1 /* reload args from stack in case ptrace changed it */
- RESTORE_REST
+ RESTORE_EXTRA_REGS
xchgl %ebp,%r9d
cmpq $(IA32_NR_syscalls-1),%rax
ja int_ret_from_sys_call /* cstar_tracesys has set RAX(%rsp) */
@@ -417,7 +420,8 @@ ENTRY(ia32_syscall)
cld
/* note the registers are not zero extended to the sf.
this could be a problem. */
- SAVE_ARGS 0,1,0
+ ALLOC_PTREGS_ON_STACK
+ SAVE_C_REGS_EXCEPT_R891011
orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
jnz ia32_tracesys
@@ -430,16 +434,16 @@ ia32_sysret:
movq %rax,RAX-ARGOFFSET(%rsp)
ia32_ret_from_sys_call:
CLEAR_RREGS -ARGOFFSET
- jmp int_ret_from_sys_call
+ jmp int_ret_from_sys_call
-ia32_tracesys:
- SAVE_REST
+ia32_tracesys:
+ SAVE_EXTRA_REGS
CLEAR_RREGS
movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
movq %rsp,%rdi /* &pt_regs -> arg1 */
call syscall_trace_enter
LOAD_ARGS32 ARGOFFSET /* reload args from stack in case ptrace changed it */
- RESTORE_REST
+ RESTORE_EXTRA_REGS
cmpq $(IA32_NR_syscalls-1),%rax
ja int_ret_from_sys_call /* ia32_tracesys has set RAX(%rsp) */
jmp ia32_do_call
@@ -475,7 +479,6 @@ GLOBAL(stub32_clone)
ALIGN
ia32_ptregs_common:
- popq %r11
CFI_ENDPROC
CFI_STARTPROC32 simple
CFI_SIGNAL_FRAME
@@ -490,9 +493,9 @@ ia32_ptregs_common:
/* CFI_REL_OFFSET rflags,EFLAGS-ARGOFFSET*/
CFI_REL_OFFSET rsp,RSP-ARGOFFSET
/* CFI_REL_OFFSET ss,SS-ARGOFFSET*/
- SAVE_REST
+ SAVE_EXTRA_REGS 8
call *%rax
- RESTORE_REST
- jmp ia32_sysret /* misbalances the return cache */
+ RESTORE_EXTRA_REGS 8
+ ret
CFI_ENDPROC
END(ia32_ptregs_common)
diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h
index e176cea..7642948 100644
--- a/arch/x86/include/asm/calling.h
+++ b/arch/x86/include/asm/calling.h
@@ -52,142 +52,135 @@ For 32-bit we have the following conventions - kernel is built with
/*
* 64-bit system call stack frame layout defines and helpers,
- * for assembly code:
+ * for assembly code.
*/
-#define R15 0
-#define R14 8
-#define R13 16
-#define R12 24
-#define RBP 32
-#define RBX 40
-
-/* arguments: interrupts/non tracing syscalls only save up to here: */
-#define R11 48
-#define R10 56
-#define R9 64
-#define R8 72
-#define RAX 80
-#define RCX 88
-#define RDX 96
-#define RSI 104
-#define RDI 112
-#define ORIG_RAX 120 /* + error_code */
-/* end of arguments */
-
-/* cpu exception frame or undefined in case of fast syscall: */
-#define RIP 128
-#define CS 136
-#define EFLAGS 144
-#define RSP 152
-#define SS 160
-
-#define ARGOFFSET R11
-
- .macro SAVE_ARGS addskip=0, save_rcx=1, save_r891011=1
- subq $9*8+\addskip, %rsp
- CFI_ADJUST_CFA_OFFSET 9*8+\addskip
- movq_cfi rdi, 8*8
- movq_cfi rsi, 7*8
- movq_cfi rdx, 6*8
-
- .if \save_rcx
- movq_cfi rcx, 5*8
- .endif
-
- movq_cfi rax, 4*8
+/* The layout forms the "struct pt_regs" on the stack: */
+/*
+ * C ABI says these regs are callee-preserved. They aren't saved on kernel entry
+ * unless syscall needs a complete, fully filled "struct pt_regs".
+ */
+#define R15 0*8
+#define R14 1*8
+#define R13 2*8
+#define R12 3*8
+#define RBP 4*8
+#define RBX 5*8
+/* These regs are callee-clobbered. Always saved on kernel entry. */
+#define R11 6*8
+#define R10 7*8
+#define R9 8*8
+#define R8 9*8
+#define RAX 10*8
+#define RCX 11*8
+#define RDX 12*8
+#define RSI 13*8
+#define RDI 14*8
+/*
+ * On syscall entry, this is syscall#. On CPU exception, this is error code.
+ * On hw interrupt, it's IRQ number:
+ */
+#define ORIG_RAX 15*8
+/* Return frame for iretq */
+#define RIP 16*8
+#define CS 17*8
+#define EFLAGS 18*8
+#define RSP 19*8
+#define SS 20*8
+
+#define ARGOFFSET 0
+
+ .macro ALLOC_PTREGS_ON_STACK addskip=0
+ subq $15*8+\addskip, %rsp
+ CFI_ADJUST_CFA_OFFSET 15*8+\addskip
+ .endm
- .if \save_r891011
- movq_cfi r8, 3*8
- movq_cfi r9, 2*8
- movq_cfi r10, 1*8
- movq_cfi r11, 0*8
+ .macro SAVE_C_REGS_HELPER offset=0 rcx=1 r8plus=1
+ movq_cfi rdi, 14*8+\offset
+ movq_cfi rsi, 13*8+\offset
+ movq_cfi rdx, 12*8+\offset
+ .if \rcx
+ movq_cfi rcx, 11*8+\offset
+ .endif
+ movq_cfi rax, 10*8+\offset
+ .if \r8plus
+ movq_cfi r8, 9*8+\offset
+ movq_cfi r9, 8*8+\offset
+ movq_cfi r10, 7*8+\offset
+ movq_cfi r11, 6*8+\offset
.endif
+ .endm
+ .macro SAVE_C_REGS offset=0
+ SAVE_C_REGS_HELPER \offset, 1, 1
+ .endm
+ .macro SAVE_C_REGS_EXCEPT_R891011
+ SAVE_C_REGS_HELPER 0, 1, 0
+ .endm
+ .macro SAVE_C_REGS_EXCEPT_RCX_R891011
+ SAVE_C_REGS_HELPER 0, 0, 0
+ .endm
+ .macro SAVE_EXTRA_REGS offset=0
+ movq_cfi rbx, 5*8+\offset
+ movq_cfi rbp, 4*8+\offset
+ movq_cfi r12, 3*8+\offset
+ movq_cfi r13, 2*8+\offset
+ movq_cfi r14, 1*8+\offset
+ movq_cfi r15, 0*8+\offset
+ .endm
+ .macro SAVE_EXTRA_REGS_RBP offset=0
+ movq_cfi rbp, 4*8+\offset
.endm
-#define ARG_SKIP (9*8)
+ .macro RESTORE_EXTRA_REGS offset=0
+ movq_cfi_restore 0*8+\offset, r15
+ movq_cfi_restore 1*8+\offset, r14
+ movq_cfi_restore 2*8+\offset, r13
+ movq_cfi_restore 3*8+\offset, r12
+ movq_cfi_restore 4*8+\offset, rbp
+ movq_cfi_restore 5*8+\offset, rbx
+ .endm
- .macro RESTORE_ARGS rstor_rax=1, addskip=0, rstor_rcx=1, rstor_r11=1, \
- rstor_r8910=1, rstor_rdx=1
+ .macro RESTORE_C_REGS_HELPER rstor_rax=1, rstor_rcx=1, rstor_r11=1, rstor_r8910=1, rstor_rdx=1
.if \rstor_r11
- movq_cfi_restore 0*8, r11
+ movq_cfi_restore 6*8, r11
.endif
-
.if \rstor_r8910
- movq_cfi_restore 1*8, r10
- movq_cfi_restore 2*8, r9
- movq_cfi_restore 3*8, r8
+ movq_cfi_restore 7*8, r10
+ movq_cfi_restore 8*8, r9
+ movq_cfi_restore 9*8, r8
.endif
-
.if \rstor_rax
- movq_cfi_restore 4*8, rax
+ movq_cfi_restore 10*8, rax
.endif
-
.if \rstor_rcx
- movq_cfi_restore 5*8, rcx
+ movq_cfi_restore 11*8, rcx
.endif
-
.if \rstor_rdx
- movq_cfi_restore 6*8, rdx
- .endif
-
- movq_cfi_restore 7*8, rsi
- movq_cfi_restore 8*8, rdi
-
- .if ARG_SKIP+\addskip > 0
- addq $ARG_SKIP+\addskip, %rsp
- CFI_ADJUST_CFA_OFFSET -(ARG_SKIP+\addskip)
+ movq_cfi_restore 12*8, rdx
.endif
+ movq_cfi_restore 13*8, rsi
+ movq_cfi_restore 14*8, rdi
.endm
-
- .macro LOAD_ARGS offset, skiprax=0
- movq \offset(%rsp), %r11
- movq \offset+8(%rsp), %r10
- movq \offset+16(%rsp), %r9
- movq \offset+24(%rsp), %r8
- movq \offset+40(%rsp), %rcx
- movq \offset+48(%rsp), %rdx
- movq \offset+56(%rsp), %rsi
- movq \offset+64(%rsp), %rdi
- .if \skiprax
- .else
- movq \offset+72(%rsp), %rax
- .endif
+ .macro RESTORE_C_REGS
+ RESTORE_C_REGS_HELPER 1,1,1,1,1
.endm
-
-#define REST_SKIP (6*8)
-
- .macro SAVE_REST
- subq $REST_SKIP, %rsp
- CFI_ADJUST_CFA_OFFSET REST_SKIP
- movq_cfi rbx, 5*8
- movq_cfi rbp, 4*8
- movq_cfi r12, 3*8
- movq_cfi r13, 2*8
- movq_cfi r14, 1*8
- movq_cfi r15, 0*8
+ .macro RESTORE_C_REGS_EXCEPT_RAX
+ RESTORE_C_REGS_HELPER 0,1,1,1,1
.endm
-
- .macro RESTORE_REST
- movq_cfi_restore 0*8, r15
- movq_cfi_restore 1*8, r14
- movq_cfi_restore 2*8, r13
- movq_cfi_restore 3*8, r12
- movq_cfi_restore 4*8, rbp
- movq_cfi_restore 5*8, rbx
- addq $REST_SKIP, %rsp
- CFI_ADJUST_CFA_OFFSET -(REST_SKIP)
+ .macro RESTORE_C_REGS_EXCEPT_RCX
+ RESTORE_C_REGS_HELPER 1,0,1,1,1
.endm
-
- .macro SAVE_ALL
- SAVE_ARGS
- SAVE_REST
+ .macro RESTORE_RSI_RDI
+ RESTORE_C_REGS_HELPER 0,0,0,0,0
+ .endm
+ .macro RESTORE_RSI_RDI_RDX
+ RESTORE_C_REGS_HELPER 0,0,0,0,1
.endm
- .macro RESTORE_ALL addskip=0
- RESTORE_REST
- RESTORE_ARGS 1, \addskip
+ .macro REMOVE_PTREGS_FROM_STACK addskip=0
+ addq $15*8+\addskip, %rsp
+ CFI_ADJUST_CFA_OFFSET -(15*8+\addskip)
.endm
.macro icebp
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index bba3cf8..6f98c16 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -171,9 +171,9 @@ static inline int arch_irqs_disabled(void)
#define ARCH_LOCKDEP_SYS_EXIT_IRQ \
TRACE_IRQS_ON; \
sti; \
- SAVE_REST; \
+ SAVE_EXTRA_REGS; \
LOCKDEP_SYS_EXIT; \
- RESTORE_REST; \
+ RESTORE_EXTRA_REGS; \
cli; \
TRACE_IRQS_OFF;
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 6205f0c..c822b35 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -31,13 +31,17 @@ struct pt_regs {
#else /* __i386__ */
struct pt_regs {
+/*
+ * C ABI says these regs are callee-preserved. They aren't saved on kernel entry
+ * unless syscall needs a complete, fully filled "struct pt_regs".
+ */
unsigned long r15;
unsigned long r14;
unsigned long r13;
unsigned long r12;
unsigned long bp;
unsigned long bx;
-/* arguments: non interrupts/non tracing syscalls only save up to here*/
+/* These regs are callee-clobbered. Always saved on kernel entry. */
unsigned long r11;
unsigned long r10;
unsigned long r9;
@@ -47,9 +51,12 @@ struct pt_regs {
unsigned long dx;
unsigned long si;
unsigned long di;
+/*
+ * On syscall entry, this is syscall#. On CPU exception, this is error code.
+ * On hw interrupt, it's IRQ number:
+ */
unsigned long orig_ax;
-/* end of arguments */
-/* cpu exception frame or undefined */
+/* Return frame for iretq */
unsigned long ip;
unsigned long cs;
unsigned long flags;
diff --git a/arch/x86/include/uapi/asm/ptrace-abi.h b/arch/x86/include/uapi/asm/ptrace-abi.h
index 7b0a55a..580aee3 100644
--- a/arch/x86/include/uapi/asm/ptrace-abi.h
+++ b/arch/x86/include/uapi/asm/ptrace-abi.h
@@ -25,13 +25,17 @@
#else /* __i386__ */
#if defined(__ASSEMBLY__) || defined(__FRAME_OFFSETS)
+/*
+ * C ABI says these regs are callee-preserved. They aren't saved on kernel entry
+ * unless syscall needs a complete, fully filled "struct pt_regs".
+ */
#define R15 0
#define R14 8
#define R13 16
#define R12 24
#define RBP 32
#define RBX 40
-/* arguments: interrupts/non tracing syscalls only save up to here*/
+/* These regs are callee-clobbered. Always saved on kernel entry. */
#define R11 48
#define R10 56
#define R9 64
@@ -41,15 +45,17 @@
#define RDX 96
#define RSI 104
#define RDI 112
-#define ORIG_RAX 120 /* = ERROR */
-/* end of arguments */
-/* cpu exception frame or undefined in case of fast syscall. */
+/*
+ * On syscall entry, this is syscall#. On CPU exception, this is error code.
+ * On hw interrupt, it's IRQ number:
+ */
+#define ORIG_RAX 120
+/* Return frame for iretq */
#define RIP 128
#define CS 136
#define EFLAGS 144
#define RSP 152
#define SS 160
-#define ARGOFFSET R11
#endif /* __ASSEMBLY__ */
/* top of stack page */
diff --git a/arch/x86/include/uapi/asm/ptrace.h b/arch/x86/include/uapi/asm/ptrace.h
index ac4b9aa..bc16115 100644
--- a/arch/x86/include/uapi/asm/ptrace.h
+++ b/arch/x86/include/uapi/asm/ptrace.h
@@ -41,13 +41,17 @@ struct pt_regs {
#ifndef __KERNEL__
struct pt_regs {
+/*
+ * C ABI says these regs are callee-preserved. They aren't saved on kernel entry
+ * unless syscall needs a complete, fully filled "struct pt_regs".
+ */
unsigned long r15;
unsigned long r14;
unsigned long r13;
unsigned long r12;
unsigned long rbp;
unsigned long rbx;
-/* arguments: non interrupts/non tracing syscalls only save up to here*/
+/* These regs are callee-clobbered. Always saved on kernel entry. */
unsigned long r11;
unsigned long r10;
unsigned long r9;
@@ -57,9 +61,12 @@ struct pt_regs {
unsigned long rdx;
unsigned long rsi;
unsigned long rdi;
+/*
+ * On syscall entry, this is syscall#. On CPU exception, this is error code.
+ * On hw interrupt, it's IRQ number:
+ */
unsigned long orig_rax;
-/* end of arguments */
-/* cpu exception frame or undefined */
+/* Return frame for iretq */
unsigned long rip;
unsigned long cs;
unsigned long eflags;
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 37f7d95..c489a2d 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -14,9 +14,6 @@
* NOTE: This code handles signal-recognition, which happens every time
* after an interrupt and after each system call.
*
- * Normal syscalls and interrupts don't save a full stack frame, this is
- * only done for syscall tracing, signals or fork/exec et.al.
- *
* A note on terminology:
* - top of stack: Architecture defined interrupt frame from SS to RIP
* at the top of the kernel process stack.
@@ -26,12 +23,6 @@
* Some macro usage:
* - CFI macros are used to generate dwarf2 unwind information for better
* backtraces. They don't change any code.
- * - SAVE_ALL/RESTORE_ALL - Save/restore all registers
- * - SAVE_ARGS/RESTORE_ARGS - Save/restore registers that C functions modify.
- * There are unfortunately lots of special cases where some registers
- * not touched. The macro is a big mess that should be cleaned up.
- * - SAVE_REST/RESTORE_REST - Handle the registers not saved by SAVE_ARGS.
- * Gives a full stack frame.
* - ENTRY/END Define functions in the symbol table.
* - FIXUP_TOP_OF_STACK/RESTORE_TOP_OF_STACK - Fix up the hardware stack
* frame that is otherwise undefined after a SYSCALL
@@ -156,7 +147,7 @@ ENDPROC(native_usergs_sysret64)
.endm
/*
- * initial frame state for interrupts (and exceptions without error code)
+ * empty frame
*/
.macro EMPTY_FRAME start=1 offset=0
.if \start
@@ -190,9 +181,9 @@ ENDPROC(native_usergs_sysret64)
.endm
/*
- * frame that enables calling into C.
+ * frame that enables passing a complete pt_regs to a C function.
*/
- .macro PARTIAL_FRAME start=1 offset=0
+ .macro DEFAULT_FRAME start=1 offset=0
XCPT_FRAME \start, ORIG_RAX+\offset-ARGOFFSET
CFI_REL_OFFSET rdi, RDI+\offset-ARGOFFSET
CFI_REL_OFFSET rsi, RSI+\offset-ARGOFFSET
@@ -203,13 +194,6 @@ ENDPROC(native_usergs_sysret64)
CFI_REL_OFFSET r9, R9+\offset-ARGOFFSET
CFI_REL_OFFSET r10, R10+\offset-ARGOFFSET
CFI_REL_OFFSET r11, R11+\offset-ARGOFFSET
- .endm
-
-/*
- * frame that enables passing a complete pt_regs to a C function.
- */
- .macro DEFAULT_FRAME start=1 offset=0
- PARTIAL_FRAME \start, R11+\offset-R15
CFI_REL_OFFSET rbx, RBX+\offset
CFI_REL_OFFSET rbp, RBP+\offset
CFI_REL_OFFSET r12, R12+\offset
@@ -221,21 +205,8 @@ ENDPROC(native_usergs_sysret64)
ENTRY(save_paranoid)
XCPT_FRAME 1 RDI+8
cld
- movq_cfi rdi, RDI+8
- movq_cfi rsi, RSI+8
- movq_cfi rdx, RDX+8
- movq_cfi rcx, RCX+8
- movq_cfi rax, RAX+8
- movq_cfi r8, R8+8
- movq_cfi r9, R9+8
- movq_cfi r10, R10+8
- movq_cfi r11, R11+8
- movq_cfi rbx, RBX+8
- movq_cfi rbp, RBP+8
- movq_cfi r12, R12+8
- movq_cfi r13, R13+8
- movq_cfi r14, R14+8
- movq_cfi r15, R15+8
+ SAVE_C_REGS 8
+ SAVE_EXTRA_REGS 8
movl $1,%ebx
movl $MSR_GS_BASE,%ecx
rdmsr
@@ -264,7 +235,7 @@ ENTRY(ret_from_fork)
GET_THREAD_INFO(%rcx)
- RESTORE_REST
+ RESTORE_EXTRA_REGS
testl $3, CS-ARGOFFSET(%rsp) # from kernel_thread?
jz 1f
@@ -276,12 +247,10 @@ ENTRY(ret_from_fork)
jmp ret_from_sys_call # go to the SYSRET fastpath
1:
- subq $REST_SKIP, %rsp # leave space for volatiles
- CFI_ADJUST_CFA_OFFSET REST_SKIP
movq %rbp, %rdi
call *%rbx
movl $0, RAX(%rsp)
- RESTORE_REST
+ RESTORE_EXTRA_REGS
jmp int_ret_from_sys_call
CFI_ENDPROC
END(ret_from_fork)
@@ -339,7 +308,8 @@ GLOBAL(system_call_after_swapgs)
* and short:
*/
ENABLE_INTERRUPTS(CLBR_NONE)
- SAVE_ARGS 8,0
+ ALLOC_PTREGS_ON_STACK 8
+ SAVE_C_REGS
movq %rax,ORIG_RAX-ARGOFFSET(%rsp)
movq %rcx,RIP-ARGOFFSET(%rsp)
CFI_REL_OFFSET rip,RIP-ARGOFFSET
@@ -375,9 +345,9 @@ sysret_check:
* sysretq will re-enable interrupts:
*/
TRACE_IRQS_ON
+ RESTORE_C_REGS_EXCEPT_RCX
movq RIP-ARGOFFSET(%rsp),%rcx
CFI_REGISTER rip,rcx
- RESTORE_ARGS 1,-ARG_SKIP,0
/*CFI_REGISTER rflags,r11*/
movq PER_CPU_VAR(old_rsp), %rsp
USERGS_SYSRET64
@@ -429,7 +399,7 @@ auditsys:
movq %rax,%rsi /* 2nd arg: syscall number */
movl $AUDIT_ARCH_X86_64,%edi /* 1st arg: audit arch */
call __audit_syscall_entry
- LOAD_ARGS 0 /* reload call-clobbered registers */
+ RESTORE_C_REGS /* reload call-clobbered registers */
jmp system_call_fastpath
/*
@@ -453,7 +423,7 @@ tracesys:
testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
jz auditsys
#endif
- SAVE_REST
+ SAVE_EXTRA_REGS
movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
FIXUP_TOP_OF_STACK %rdi
movq %rsp,%rdi
@@ -463,8 +433,8 @@ tracesys:
* We don't reload %rax because syscall_trace_enter() returned
* the value it wants us to use in the table lookup.
*/
- LOAD_ARGS ARGOFFSET, 1
- RESTORE_REST
+ RESTORE_C_REGS_EXCEPT_RAX
+ RESTORE_EXTRA_REGS
#if __SYSCALL_MASK == ~0
cmpq $__NR_syscall_max,%rax
#else
@@ -515,7 +485,7 @@ int_very_careful:
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_NONE)
int_check_syscall_exit_work:
- SAVE_REST
+ SAVE_EXTRA_REGS
/* Check for syscall exit trace */
testl $_TIF_WORK_SYSCALL_EXIT,%edx
jz int_signal
@@ -534,7 +504,7 @@ int_signal:
call do_notify_resume
1: movl $_TIF_WORK_MASK,%edi
int_restore_rest:
- RESTORE_REST
+ RESTORE_EXTRA_REGS
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
jmp int_with_check
@@ -544,15 +514,12 @@ END(system_call)
.macro FORK_LIKE func
ENTRY(stub_\func)
CFI_STARTPROC
- popq %r11 /* save return address */
- PARTIAL_FRAME 0
- SAVE_REST
- pushq %r11 /* put it back on stack */
+ DEFAULT_FRAME 0, 8 /* offset 8: return address */
+ SAVE_EXTRA_REGS 8
FIXUP_TOP_OF_STACK %r11, 8
- DEFAULT_FRAME 0 8 /* offset 8: return address */
call sys_\func
RESTORE_TOP_OF_STACK %r11, 8
- ret $REST_SKIP /* pop extended registers */
+ ret
CFI_ENDPROC
END(stub_\func)
.endm
@@ -560,7 +527,7 @@ END(stub_\func)
.macro FIXED_FRAME label,func
ENTRY(\label)
CFI_STARTPROC
- PARTIAL_FRAME 0 8 /* offset 8: return address */
+ DEFAULT_FRAME 0, 8 /* offset 8: return address */
FIXUP_TOP_OF_STACK %r11, 8-ARGOFFSET
call \func
RESTORE_TOP_OF_STACK %r11, 8-ARGOFFSET
@@ -577,12 +544,12 @@ END(\label)
ENTRY(stub_execve)
CFI_STARTPROC
addq $8, %rsp
- PARTIAL_FRAME 0
- SAVE_REST
+ DEFAULT_FRAME 0
+ SAVE_EXTRA_REGS
FIXUP_TOP_OF_STACK %r11
call sys_execve
movq %rax,RAX(%rsp)
- RESTORE_REST
+ RESTORE_EXTRA_REGS
jmp int_ret_from_sys_call
CFI_ENDPROC
END(stub_execve)
@@ -594,12 +561,12 @@ END(stub_execve)
ENTRY(stub_rt_sigreturn)
CFI_STARTPROC
addq $8, %rsp
- PARTIAL_FRAME 0
- SAVE_REST
+ DEFAULT_FRAME 0
+ SAVE_EXTRA_REGS
FIXUP_TOP_OF_STACK %r11
call sys_rt_sigreturn
movq %rax,RAX(%rsp) # fixme, this could be done at the higher layer
- RESTORE_REST
+ RESTORE_EXTRA_REGS
jmp int_ret_from_sys_call
CFI_ENDPROC
END(stub_rt_sigreturn)
@@ -608,12 +575,12 @@ END(stub_rt_sigreturn)
ENTRY(stub_x32_rt_sigreturn)
CFI_STARTPROC
addq $8, %rsp
- PARTIAL_FRAME 0
- SAVE_REST
+ DEFAULT_FRAME 0
+ SAVE_EXTRA_REGS
FIXUP_TOP_OF_STACK %r11
call sys32_x32_rt_sigreturn
movq %rax,RAX(%rsp) # fixme, this could be done at the higher layer
- RESTORE_REST
+ RESTORE_EXTRA_REGS
jmp int_ret_from_sys_call
CFI_ENDPROC
END(stub_x32_rt_sigreturn)
@@ -621,13 +588,13 @@ END(stub_x32_rt_sigreturn)
ENTRY(stub_x32_execve)
CFI_STARTPROC
addq $8, %rsp
- PARTIAL_FRAME 0
- SAVE_REST
+ DEFAULT_FRAME 0
+ SAVE_EXTRA_REGS
FIXUP_TOP_OF_STACK %r11
call compat_sys_execve
RESTORE_TOP_OF_STACK %r11
movq %rax,RAX(%rsp)
- RESTORE_REST
+ RESTORE_EXTRA_REGS
jmp int_ret_from_sys_call
CFI_ENDPROC
END(stub_x32_execve)
@@ -683,42 +650,36 @@ END(interrupt)
/* 0(%rsp): ~(interrupt number) */
.macro interrupt func
- /* reserve pt_regs for scratch regs and rbp */
- subq $ORIG_RAX-RBP, %rsp
- CFI_ADJUST_CFA_OFFSET ORIG_RAX-RBP
cld
- /* start from rbp in pt_regs and jump over */
- movq_cfi rdi, (RDI-RBP)
- movq_cfi rsi, (RSI-RBP)
- movq_cfi rdx, (RDX-RBP)
- movq_cfi rcx, (RCX-RBP)
- movq_cfi rax, (RAX-RBP)
- movq_cfi r8, (R8-RBP)
- movq_cfi r9, (R9-RBP)
- movq_cfi r10, (R10-RBP)
- movq_cfi r11, (R11-RBP)
-
- /* Save rbp so that we can unwind from get_irq_regs() */
- movq_cfi rbp, 0
-
- /* Save previous stack value */
- movq %rsp, %rsi
+ /*
+ * Since nothing in interrupt handling code touches r12...r15 members
+ * of "struct pt_regs", and since interrupts can nest, we can save
+ * four stack slots and simultaneously provide
+ * an unwind-friendly stack layout by saving "truncated" pt_regs
+ * exactly up to rbp slot, without these members.
+ */
+ ALLOC_PTREGS_ON_STACK -RBP
+ SAVE_C_REGS -RBP
+ /* this goes to 0(%rsp) for unwinder, not for saving the value: */
+ SAVE_EXTRA_REGS_RBP -RBP
- leaq -RBP(%rsp),%rdi /* arg1 for handler */
- testl $3, CS-RBP(%rsi)
+ leaq -RBP(%rsp),%rdi /* arg1 for \func (pointer to pt_regs) */
+
+ testl $3, CS-RBP(%rsp)
je 1f
SWAPGS
+1:
/*
+ * Save previous stack pointer, optionally switch to interrupt stack.
* irq_count is used to check if a CPU is already on an interrupt stack
* or not. While this is essentially redundant with preempt_count it is
* a little cheaper to use a separate counter in the PDA (short of
* moving irq_enter into assembly, which would be too much work)
*/
-1: incl PER_CPU_VAR(irq_count)
+ movq %rsp, %rsi
+ incl PER_CPU_VAR(irq_count)
cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
CFI_DEF_CFA_REGISTER rsi
-
- /* Store previous stack value */
pushq %rsi
CFI_ESCAPE 0x0f /* DW_CFA_def_cfa_expression */, 6, \
0x77 /* DW_OP_breg7 */, 0, \
@@ -750,6 +711,7 @@ ret_from_intr:
/* Restore saved previous stack */
popq %rsi
CFI_DEF_CFA rsi,SS+8-RBP /* reg/off reset after def_cfa_expr */
+ /* return code expects complete pt_regs - adjust rsp accordingly: */
leaq ARGOFFSET-RBP(%rsi), %rsp
CFI_DEF_CFA_REGISTER rsp
CFI_ADJUST_CFA_OFFSET RBP-ARGOFFSET
@@ -761,7 +723,7 @@ exit_intr:
/* Interrupt came from user space */
/*
- * Has a correct top of stack, but a partial stack frame
+ * Has a correct top of stack.
* %rcx: thread info. Interrupts off.
*/
retint_with_reschedule:
@@ -789,7 +751,8 @@ retint_restore_args: /* return to kernel space */
*/
TRACE_IRQS_IRETQ
restore_args:
- RESTORE_ARGS 1,8,1
+ RESTORE_C_REGS
+ REMOVE_PTREGS_FROM_STACK 8
irq_return:
/*
@@ -876,12 +839,12 @@ retint_signal:
jz retint_swapgs
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_NONE)
- SAVE_REST
+ SAVE_EXTRA_REGS
movq $-1,ORIG_RAX(%rsp)
xorl %esi,%esi # oldset
movq %rsp,%rdi # &pt_regs
call do_notify_resume
- RESTORE_REST
+ RESTORE_EXTRA_REGS
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
GET_THREAD_INFO(%rcx)
@@ -1044,8 +1007,7 @@ ENTRY(\sym)
pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */
.endif
- subq $ORIG_RAX-R15, %rsp
- CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
+ ALLOC_PTREGS_ON_STACK
.if \paranoid
call save_paranoid
@@ -1256,7 +1218,9 @@ ENTRY(xen_failsafe_callback)
addq $0x30,%rsp
CFI_ADJUST_CFA_OFFSET -0x30
pushq_cfi $-1 /* orig_ax = -1 => not a system call */
- SAVE_ALL
+ ALLOC_PTREGS_ON_STACK
+ SAVE_C_REGS
+ SAVE_EXTRA_REGS
jmp error_exit
CFI_ENDPROC
END(xen_failsafe_callback)
@@ -1313,11 +1277,15 @@ ENTRY(paranoid_exit)
paranoid_swapgs:
TRACE_IRQS_IRETQ 0
SWAPGS_UNSAFE_STACK
- RESTORE_ALL 8
+ RESTORE_EXTRA_REGS
+ RESTORE_C_REGS
+ REMOVE_PTREGS_FROM_STACK 8
jmp irq_return
paranoid_restore:
TRACE_IRQS_IRETQ_DEBUG 0
- RESTORE_ALL 8
+ RESTORE_EXTRA_REGS
+ RESTORE_C_REGS
+ REMOVE_PTREGS_FROM_STACK 8
jmp irq_return
paranoid_userspace:
GET_THREAD_INFO(%rcx)
@@ -1357,21 +1325,8 @@ ENTRY(error_entry)
CFI_ADJUST_CFA_OFFSET 15*8
/* oldrax contains error code */
cld
- movq_cfi rdi, RDI+8
- movq_cfi rsi, RSI+8
- movq_cfi rdx, RDX+8
- movq_cfi rcx, RCX+8
- movq_cfi rax, RAX+8
- movq_cfi r8, R8+8
- movq_cfi r9, R9+8
- movq_cfi r10, R10+8
- movq_cfi r11, R11+8
- movq_cfi rbx, RBX+8
- movq_cfi rbp, RBP+8
- movq_cfi r12, R12+8
- movq_cfi r13, R13+8
- movq_cfi r14, R14+8
- movq_cfi r15, R15+8
+ SAVE_C_REGS 8
+ SAVE_EXTRA_REGS 8
xorl %ebx,%ebx
testl $3,CS+8(%rsp)
je error_kernelspace
@@ -1412,7 +1367,7 @@ END(error_entry)
ENTRY(error_exit)
DEFAULT_FRAME
movl %ebx,%eax
- RESTORE_REST
+ RESTORE_EXTRA_REGS
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
GET_THREAD_INFO(%rcx)
@@ -1631,8 +1586,8 @@ end_repeat_nmi:
* so that we repeat another NMI.
*/
pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */
- subq $ORIG_RAX-R15, %rsp
- CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
+ ALLOC_PTREGS_ON_STACK
+
/*
* Use save_paranoid to handle SWAPGS, but no need to use paranoid_exit
* as we should not be calling schedule in NMI context.
@@ -1671,8 +1626,10 @@ end_repeat_nmi:
nmi_swapgs:
SWAPGS_UNSAFE_STACK
nmi_restore:
+ RESTORE_EXTRA_REGS
+ RESTORE_C_REGS
/* Pop the extra iret frame at once */
- RESTORE_ALL 6*8
+ REMOVE_PTREGS_FROM_STACK 6*8
/* Clear the NMI executing stack variable */
movq $0, 5*8(%rsp)
diff --git a/arch/x86/kernel/preempt.S b/arch/x86/kernel/preempt.S
index ca7f0d5..673da2f 100644
--- a/arch/x86/kernel/preempt.S
+++ b/arch/x86/kernel/preempt.S
@@ -6,9 +6,13 @@
ENTRY(___preempt_schedule)
CFI_STARTPROC
- SAVE_ALL
+ ALLOC_PTREGS_ON_STACK
+ SAVE_C_REGS
+ SAVE_EXTRA_REGS
call preempt_schedule
- RESTORE_ALL
+ RESTORE_EXTRA_REGS
+ RESTORE_C_REGS
+ REMOVE_PTREGS_FROM_STACK
ret
CFI_ENDPROC
@@ -16,9 +20,13 @@ ENTRY(___preempt_schedule)
ENTRY(___preempt_schedule_context)
CFI_STARTPROC
- SAVE_ALL
+ ALLOC_PTREGS_ON_STACK
+ SAVE_C_REGS
+ SAVE_EXTRA_REGS
call preempt_schedule_context
- RESTORE_ALL
+ RESTORE_EXTRA_REGS
+ RESTORE_C_REGS
+ REMOVE_PTREGS_FROM_STACK
ret
CFI_ENDPROC
--
1.8.1.4
^ permalink raw reply related [flat|nested] 12+ messages in thread* [PATCH?] x86: reimplement ___preempt_schedule*() using THUNK helpers
2014-08-04 13:19 ` [PATCH 4/6] x86: entry_64.S: always allocate complete "struct pt_regs" Denys Vlasenko
@ 2014-08-04 17:05 ` Oleg Nesterov
2014-08-04 17:18 ` Peter Zijlstra
0 siblings, 1 reply; 12+ messages in thread
From: Oleg Nesterov @ 2014-08-04 17:05 UTC (permalink / raw)
To: Denys Vlasenko, Peter Zijlstra
Cc: linux-kernel, H. Peter Anvin, Andy Lutomirski,
Frederic Weisbecker, X86 ML, Alexei Starovoitov, Will Drewry,
Kees Cook
On 08/04, Denys Vlasenko wrote:
>
> --- a/arch/x86/kernel/preempt.S
> +++ b/arch/x86/kernel/preempt.S
> @@ -6,9 +6,13 @@
>
> ENTRY(___preempt_schedule)
> CFI_STARTPROC
> - SAVE_ALL
> + ALLOC_PTREGS_ON_STACK
> + SAVE_C_REGS
> + SAVE_EXTRA_REGS
> call preempt_schedule
> - RESTORE_ALL
> + RESTORE_EXTRA_REGS
> + RESTORE_C_REGS
> + REMOVE_PTREGS_FROM_STACK
> ret
> CFI_ENDPROC
>
> @@ -16,9 +20,13 @@ ENTRY(___preempt_schedule)
>
> ENTRY(___preempt_schedule_context)
> CFI_STARTPROC
> - SAVE_ALL
> + ALLOC_PTREGS_ON_STACK
> + SAVE_C_REGS
> + SAVE_EXTRA_REGS
> call preempt_schedule_context
> - RESTORE_ALL
> + RESTORE_EXTRA_REGS
> + RESTORE_C_REGS
> + REMOVE_PTREGS_FROM_STACK
> ret
> CFI_ENDPROC
Hmm. This part looks fine, but with or without this patch this all is
suboptimal, we do not need SAVE_ALL unless I missed something. Can't we
simply kill preempt.S ?
Peter, what do you think?
Oleg.
----------------------------------------------------------------------------
Subject: [PATCH] x86: reimplement ___preempt_schedule*() using THUNK helpers
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 047f9ff..3f5d657 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -39,8 +39,6 @@ obj-y += tsc.o tsc_msr.o io_delay.o rtc.o
obj-y += pci-iommu_table.o
obj-y += resource.o
-obj-$(CONFIG_PREEMPT) += preempt.o
-
obj-y += process.o
obj-y += i387.o xsave.o
obj-y += ptrace.o
diff --git a/arch/x86/kernel/preempt.S b/arch/x86/kernel/preempt.S
deleted file mode 100644
index ca7f0d5..0000000
--- a/arch/x86/kernel/preempt.S
+++ /dev/null
@@ -1,25 +0,0 @@
-
-#include <linux/linkage.h>
-#include <asm/dwarf2.h>
-#include <asm/asm.h>
-#include <asm/calling.h>
-
-ENTRY(___preempt_schedule)
- CFI_STARTPROC
- SAVE_ALL
- call preempt_schedule
- RESTORE_ALL
- ret
- CFI_ENDPROC
-
-#ifdef CONFIG_CONTEXT_TRACKING
-
-ENTRY(___preempt_schedule_context)
- CFI_STARTPROC
- SAVE_ALL
- call preempt_schedule_context
- RESTORE_ALL
- ret
- CFI_ENDPROC
-
-#endif
diff --git a/arch/x86/lib/thunk_32.S b/arch/x86/lib/thunk_32.S
index 28f85c9..dc2b8fd 100644
--- a/arch/x86/lib/thunk_32.S
+++ b/arch/x86/lib/thunk_32.S
@@ -7,7 +7,6 @@
#include <linux/linkage.h>
#include <asm/asm.h>
-#ifdef CONFIG_TRACE_IRQFLAGS
/* put return address in eax (arg1) */
.macro thunk_ra name,func
.globl \name
@@ -25,6 +24,15 @@
_ASM_NOKPROBE(\name)
.endm
+#ifdef CONFIG_TRACE_IRQFLAGS
thunk_ra trace_hardirqs_on_thunk,trace_hardirqs_on_caller
thunk_ra trace_hardirqs_off_thunk,trace_hardirqs_off_caller
#endif
+
+#ifdef CONFIG_PREEMPT
+ THUNK ___preempt_schedule, preempt_schedule
+#ifdef CONFIG_CONTEXT_TRACKING
+ THUNK ___preempt_schedule_context, preempt_schedule_context
+#endif
+#endif
+
diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/lib/thunk_64.S
index 92d9fea..b30b5eb 100644
--- a/arch/x86/lib/thunk_64.S
+++ b/arch/x86/lib/thunk_64.S
@@ -38,6 +38,13 @@
THUNK lockdep_sys_exit_thunk,lockdep_sys_exit
#endif
+#ifdef CONFIG_PREEMPT
+ THUNK ___preempt_schedule, preempt_schedule
+#ifdef CONFIG_CONTEXT_TRACKING
+ THUNK ___preempt_schedule_context, preempt_schedule_context
+#endif
+#endif
+
/* SAVE_ARGS below is used only for the .cfi directives it contains. */
CFI_STARTPROC
SAVE_ARGS
^ permalink raw reply related [flat|nested] 12+ messages in thread
* Re: [PATCH?] x86: reimplement ___preempt_schedule*() using THUNK helpers
2014-08-04 17:05 ` [PATCH?] x86: reimplement ___preempt_schedule*() using THUNK helpers Oleg Nesterov
@ 2014-08-04 17:18 ` Peter Zijlstra
2014-08-04 17:36 ` [PATCH? v2] " Oleg Nesterov
0 siblings, 1 reply; 12+ messages in thread
From: Peter Zijlstra @ 2014-08-04 17:18 UTC (permalink / raw)
To: Oleg Nesterov
Cc: Denys Vlasenko, linux-kernel, H. Peter Anvin, Andy Lutomirski,
Frederic Weisbecker, X86 ML, Alexei Starovoitov, Will Drewry,
Kees Cook
[-- Attachment #1: Type: text/plain, Size: 362 bytes --]
On Mon, Aug 04, 2014 at 07:05:19PM +0200, Oleg Nesterov wrote:
> Hmm. This part looks fine, but with or without this patch this all is
> suboptimal, we do not need SAVE_ALL unless I missed something. Can't we
> simply kill preempt.S ?
>
> Peter, what do you think?
HPA right, not me? I'm never sure on these details, if hpa thinks its
fine, I'm good.
[-- Attachment #2: Type: application/pgp-signature, Size: 836 bytes --]
^ permalink raw reply [flat|nested] 12+ messages in thread
* [PATCH? v2] x86: reimplement ___preempt_schedule*() using THUNK helpers
2014-08-04 17:18 ` Peter Zijlstra
@ 2014-08-04 17:36 ` Oleg Nesterov
2014-08-05 4:41 ` Mike Galbraith
0 siblings, 1 reply; 12+ messages in thread
From: Oleg Nesterov @ 2014-08-04 17:36 UTC (permalink / raw)
To: Peter Zijlstra
Cc: Denys Vlasenko, linux-kernel, H. Peter Anvin, Andy Lutomirski,
Frederic Weisbecker, X86 ML, Alexei Starovoitov, Will Drewry,
Kees Cook
On 08/04, Peter Zijlstra wrote:
>
> On Mon, Aug 04, 2014 at 07:05:19PM +0200, Oleg Nesterov wrote:
> > Hmm. This part looks fine, but with or without this patch this all is
> > suboptimal, we do not need SAVE_ALL unless I missed something. Can't we
> > simply kill preempt.S ?
> >
> > Peter, what do you think?
>
> HPA right, not me?
You too ;)
> I'm never sure on these details, if hpa thinks its
> fine, I'm good.
OK, please see v2 below, I missed the unconditional "Place EIP in the arg1"
in thunk_32.S.
Seems to work at least on x86_64, but I do not know how to test, lets see
what HPA thinks.
_If_ this is correct, I should probably rebase it on top of Denys's
changes... Or, given that this patch is simple, perhaps Denys can take
this patch as 1/X. If correct ;)
Oleg.
----------------------------------------------------------------------------
Subject: [PATCH] x86: reimplement ___preempt_schedule*() using THUNK helpers
---
arch/x86/kernel/Makefile | 2 --
arch/x86/kernel/preempt.S | 25 -------------------------
arch/x86/lib/thunk_32.S | 20 ++++++++++++++++----
arch/x86/lib/thunk_64.S | 7 +++++++
4 files changed, 23 insertions(+), 31 deletions(-)
delete mode 100644 arch/x86/kernel/preempt.S
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 047f9ff..3f5d657 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -39,8 +39,6 @@ obj-y += tsc.o tsc_msr.o io_delay.o rtc.o
obj-y += pci-iommu_table.o
obj-y += resource.o
-obj-$(CONFIG_PREEMPT) += preempt.o
-
obj-y += process.o
obj-y += i387.o xsave.o
obj-y += ptrace.o
diff --git a/arch/x86/kernel/preempt.S b/arch/x86/kernel/preempt.S
deleted file mode 100644
index ca7f0d5..0000000
--- a/arch/x86/kernel/preempt.S
+++ /dev/null
@@ -1,25 +0,0 @@
-
-#include <linux/linkage.h>
-#include <asm/dwarf2.h>
-#include <asm/asm.h>
-#include <asm/calling.h>
-
-ENTRY(___preempt_schedule)
- CFI_STARTPROC
- SAVE_ALL
- call preempt_schedule
- RESTORE_ALL
- ret
- CFI_ENDPROC
-
-#ifdef CONFIG_CONTEXT_TRACKING
-
-ENTRY(___preempt_schedule_context)
- CFI_STARTPROC
- SAVE_ALL
- call preempt_schedule_context
- RESTORE_ALL
- ret
- CFI_ENDPROC
-
-#endif
diff --git a/arch/x86/lib/thunk_32.S b/arch/x86/lib/thunk_32.S
index 28f85c9..7f1641a 100644
--- a/arch/x86/lib/thunk_32.S
+++ b/arch/x86/lib/thunk_32.S
@@ -7,16 +7,19 @@
#include <linux/linkage.h>
#include <asm/asm.h>
-#ifdef CONFIG_TRACE_IRQFLAGS
/* put return address in eax (arg1) */
- .macro thunk_ra name,func
+ .macro thunk_ra name, func, put_ret_addr_in_eax=0
.globl \name
\name:
pushl %eax
pushl %ecx
pushl %edx
+
+ .if \put_ret_addr_in_eax
/* Place EIP in the arg1 */
movl 3*4(%esp), %eax
+ .endif
+
call \func
popl %edx
popl %ecx
@@ -25,6 +28,15 @@
_ASM_NOKPROBE(\name)
.endm
- thunk_ra trace_hardirqs_on_thunk,trace_hardirqs_on_caller
- thunk_ra trace_hardirqs_off_thunk,trace_hardirqs_off_caller
+#ifdef CONFIG_TRACE_IRQFLAGS
+ thunk_ra trace_hardirqs_on_thunk,trace_hardirqs_on_caller,1
+ thunk_ra trace_hardirqs_off_thunk,trace_hardirqs_off_caller,1
+#endif
+
+#ifdef CONFIG_PREEMPT
+ THUNK ___preempt_schedule, preempt_schedule
+#ifdef CONFIG_CONTEXT_TRACKING
+ THUNK ___preempt_schedule_context, preempt_schedule_context
#endif
+#endif
+
diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/lib/thunk_64.S
index 92d9fea..b30b5eb 100644
--- a/arch/x86/lib/thunk_64.S
+++ b/arch/x86/lib/thunk_64.S
@@ -38,6 +38,13 @@
THUNK lockdep_sys_exit_thunk,lockdep_sys_exit
#endif
+#ifdef CONFIG_PREEMPT
+ THUNK ___preempt_schedule, preempt_schedule
+#ifdef CONFIG_CONTEXT_TRACKING
+ THUNK ___preempt_schedule_context, preempt_schedule_context
+#endif
+#endif
+
/* SAVE_ARGS below is used only for the .cfi directives it contains. */
CFI_STARTPROC
SAVE_ARGS
--
1.5.5.1
^ permalink raw reply related [flat|nested] 12+ messages in thread
* Re: [PATCH? v2] x86: reimplement ___preempt_schedule*() using THUNK helpers
2014-08-04 17:36 ` [PATCH? v2] " Oleg Nesterov
@ 2014-08-05 4:41 ` Mike Galbraith
0 siblings, 0 replies; 12+ messages in thread
From: Mike Galbraith @ 2014-08-05 4:41 UTC (permalink / raw)
To: Oleg Nesterov
Cc: Peter Zijlstra, Denys Vlasenko, linux-kernel, H. Peter Anvin,
Andy Lutomirski, Frederic Weisbecker, X86 ML, Alexei Starovoitov,
Will Drewry, Kees Cook
On Mon, 2014-08-04 at 19:36 +0200, Oleg Nesterov wrote:
> Seems to work at least on x86_64, but I do not know how to test, lets see
> what HPA thinks.
Seeing the words "preempt" and "test", blindly feeding it to -rt seemed
like a reasonable thing to do over morning java (la la la;)... it hasn't
spat it out yet.
-Mike
^ permalink raw reply [flat|nested] 12+ messages in thread
* [PATCH 5/6] x86: mass removal of ARGOFFSET
2014-08-04 13:19 [PATCH 0/6 v2] x86: entry_64.S: always allocate complete "struct pt_regs" Denys Vlasenko
` (3 preceding siblings ...)
2014-08-04 13:19 ` [PATCH 4/6] x86: entry_64.S: always allocate complete "struct pt_regs" Denys Vlasenko
@ 2014-08-04 13:19 ` Denys Vlasenko
2014-08-05 11:09 ` Denys Vlasenko
2014-08-04 13:19 ` [PATCH 6/6] x86: rename some macros and labels, no code changes Denys Vlasenko
5 siblings, 1 reply; 12+ messages in thread
From: Denys Vlasenko @ 2014-08-04 13:19 UTC (permalink / raw)
To: linux-kernel
Cc: Denys Vlasenko, Oleg Nesterov, H. Peter Anvin, Andy Lutomirski,
Frederic Weisbecker, X86 ML, Alexei Starovoitov, Will Drewry,
Kees Cook
ARGOFFSET is zero now, removing it changes no code.
A few macros lost "offset" parameter, since it is always zero now too.
Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com>
CC: Oleg Nesterov <oleg@redhat.com>
CC: "H. Peter Anvin" <hpa@zytor.com>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Frederic Weisbecker <fweisbec@gmail.com>
CC: X86 ML <x86@kernel.org>
CC: Alexei Starovoitov <ast@plumgrid.com>
CC: Will Drewry <wad@chromium.org>
CC: Kees Cook <keescook@chromium.org>
CC: linux-kernel@vger.kernel.org
---
arch/x86/ia32/ia32entry.S | 136 ++++++++++++++++++++---------------------
arch/x86/include/asm/calling.h | 2 -
arch/x86/kernel/entry_64.S | 66 ++++++++++----------
3 files changed, 101 insertions(+), 103 deletions(-)
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index ef9ee16..7315179 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -41,13 +41,13 @@
movl %edx,%edx /* zero extension */
.endm
- /* clobbers %eax */
- .macro CLEAR_RREGS offset=0, _r9=rax
+ /* clobbers %rax */
+ .macro CLEAR_RREGS _r9=rax
xorl %eax,%eax
- movq %rax,\offset+R11(%rsp)
- movq %rax,\offset+R10(%rsp)
- movq %\_r9,\offset+R9(%rsp)
- movq %rax,\offset+R8(%rsp)
+ movq %rax,R11(%rsp)
+ movq %rax,R10(%rsp)
+ movq %\_r9,R9(%rsp)
+ movq %rax,R8(%rsp)
.endm
/*
@@ -60,14 +60,14 @@
* If it's -1 to make us punt the syscall, then (u32)-1 is still
* an appropriately invalid value.
*/
- .macro LOAD_ARGS32 offset, _r9=0
+ .macro LOAD_ARGS32 _r9=0
.if \_r9
- movl \offset+R9(%rsp),%r9d
+ movl R9(%rsp),%r9d
.endif
- movl \offset+RCX(%rsp),%ecx
- movl \offset+RDX(%rsp),%edx
- movl \offset+RSI(%rsp),%esi
- movl \offset+RDI(%rsp),%edi
+ movl RCX(%rsp),%ecx
+ movl RDX(%rsp),%edx
+ movl RSI(%rsp),%esi
+ movl RDI(%rsp),%edi
movl %eax,%eax /* zero extension */
.endm
@@ -152,8 +152,8 @@ ENTRY(ia32_sysenter_target)
1: movl (%rbp),%ebp
_ASM_EXTABLE(1b,ia32_badarg)
ASM_CLAC
- orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
- testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+ orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP)
+ testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP)
CFI_REMEMBER_STATE
jnz sysenter_tracesys
cmpq $(IA32_NR_syscalls-1),%rax
@@ -162,13 +162,13 @@ sysenter_do_call:
IA32_ARG_FIXUP
sysenter_dispatch:
call *ia32_sys_call_table(,%rax,8)
- movq %rax,RAX-ARGOFFSET(%rsp)
+ movq %rax,RAX(%rsp)
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
- testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+ testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP)
jnz sysexit_audit
sysexit_from_sys_call:
- andl $~TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+ andl $~TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP)
/* clear IF, that popfq doesn't enable interrupts early */
andl $~0x200,EFLAGS-R11(%rsp)
movl RIP-R11(%rsp),%edx /* User %eip */
@@ -195,18 +195,18 @@ sysexit_from_sys_call:
movl %eax,%esi /* 2nd arg: syscall number */
movl $AUDIT_ARCH_I386,%edi /* 1st arg: audit arch */
call __audit_syscall_entry
- movl RAX-ARGOFFSET(%rsp),%eax /* reload syscall number */
+ movl RAX(%rsp),%eax /* reload syscall number */
cmpq $(IA32_NR_syscalls-1),%rax
ja ia32_badsys
movl %ebx,%edi /* reload 1st syscall arg */
- movl RCX-ARGOFFSET(%rsp),%esi /* reload 2nd syscall arg */
- movl RDX-ARGOFFSET(%rsp),%edx /* reload 3rd syscall arg */
- movl RSI-ARGOFFSET(%rsp),%ecx /* reload 4th syscall arg */
- movl RDI-ARGOFFSET(%rsp),%r8d /* reload 5th syscall arg */
+ movl RCX(%rsp),%esi /* reload 2nd syscall arg */
+ movl RDX(%rsp),%edx /* reload 3rd syscall arg */
+ movl RSI(%rsp),%ecx /* reload 4th syscall arg */
+ movl RDI(%rsp),%r8d /* reload 5th syscall arg */
.endm
.macro auditsys_exit exit
- testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+ testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP)
jnz ia32_ret_from_sys_call
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_NONE)
@@ -217,13 +217,13 @@ sysexit_from_sys_call:
1: setbe %al /* 1 if error, 0 if not */
movzbl %al,%edi /* zero-extend that into %edi */
call __audit_syscall_exit
- movq RAX-ARGOFFSET(%rsp),%rax /* reload syscall return value */
+ movq RAX(%rsp),%rax /* reload syscall return value */
movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
- testl %edi,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+ testl %edi,TI_flags+THREAD_INFO(%rsp,RIP)
jz \exit
- CLEAR_RREGS -ARGOFFSET
+ CLEAR_RREGS
jmp int_with_check
.endm
@@ -239,7 +239,7 @@ sysexit_audit:
sysenter_tracesys:
#ifdef CONFIG_AUDITSYSCALL
- testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+ testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP)
jz sysenter_auditsys
#endif
SAVE_EXTRA_REGS
@@ -247,7 +247,7 @@ sysenter_tracesys:
movq $-ENOSYS,RAX(%rsp)/* ptrace can change this for a bad syscall */
movq %rsp,%rdi /* &pt_regs -> arg1 */
call syscall_trace_enter
- LOAD_ARGS32 ARGOFFSET /* reload args from stack in case ptrace changed it */
+ LOAD_ARGS32 /* reload args from stack in case ptrace changed it */
RESTORE_EXTRA_REGS
cmpq $(IA32_NR_syscalls-1),%rax
ja int_ret_from_sys_call /* sysenter_tracesys has set RAX(%rsp) */
@@ -293,17 +293,17 @@ ENTRY(ia32_cstar_target)
ALLOC_PTREGS_ON_STACK 8
SAVE_C_REGS_EXCEPT_RCX_R891011
movl %eax,%eax /* zero extension */
- movq %rax,ORIG_RAX-ARGOFFSET(%rsp)
- movq %rcx,RIP-ARGOFFSET(%rsp)
- CFI_REL_OFFSET rip,RIP-ARGOFFSET
- movq %rbp,RCX-ARGOFFSET(%rsp) /* this lies slightly to ptrace */
+ movq %rax,ORIG_RAX(%rsp)
+ movq %rcx,RIP(%rsp)
+ CFI_REL_OFFSET rip,RIP
+ movq %rbp,RCX(%rsp) /* this lies slightly to ptrace */
movl %ebp,%ecx
- movq $__USER32_CS,CS-ARGOFFSET(%rsp)
- movq $__USER32_DS,SS-ARGOFFSET(%rsp)
- movq %r11,EFLAGS-ARGOFFSET(%rsp)
- /*CFI_REL_OFFSET rflags,EFLAGS-ARGOFFSET*/
- movq %r8,RSP-ARGOFFSET(%rsp)
- CFI_REL_OFFSET rsp,RSP-ARGOFFSET
+ movq $__USER32_CS,CS(%rsp)
+ movq $__USER32_DS,SS(%rsp)
+ movq %r11,EFLAGS(%rsp)
+ /*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 */
@@ -311,8 +311,8 @@ ENTRY(ia32_cstar_target)
1: movl (%r8),%r9d
_ASM_EXTABLE(1b,ia32_badarg)
ASM_CLAC
- orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
- testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+ orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP)
+ testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP)
CFI_REMEMBER_STATE
jnz cstar_tracesys
cmpq $IA32_NR_syscalls-1,%rax
@@ -321,32 +321,32 @@ cstar_do_call:
IA32_ARG_FIXUP 1
cstar_dispatch:
call *ia32_sys_call_table(,%rax,8)
- movq %rax,RAX-ARGOFFSET(%rsp)
+ movq %rax,RAX(%rsp)
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
- testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+ testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP)
jnz sysretl_audit
sysretl_from_sys_call:
- andl $~TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+ andl $~TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP)
RESTORE_RSI_RDI_RDX
- movl RIP-ARGOFFSET(%rsp),%ecx
+ movl RIP(%rsp),%ecx
CFI_REGISTER rip,rcx
- movl EFLAGS-ARGOFFSET(%rsp),%r11d
+ movl EFLAGS(%rsp),%r11d
/*CFI_REGISTER rflags,r11*/
xorq %r10,%r10
xorq %r9,%r9
xorq %r8,%r8
TRACE_IRQS_ON
- movl RSP-ARGOFFSET(%rsp),%esp
+ movl RSP(%rsp),%esp
CFI_RESTORE rsp
USERGS_SYSRET32
#ifdef CONFIG_AUDITSYSCALL
cstar_auditsys:
CFI_RESTORE_STATE
- movl %r9d,R9-ARGOFFSET(%rsp) /* register to be clobbered by call */
+ movl %r9d,R9(%rsp) /* register to be clobbered by call */
auditsys_entry_common
- movl R9-ARGOFFSET(%rsp),%r9d /* reload 6th syscall arg */
+ movl R9(%rsp),%r9d /* reload 6th syscall arg */
jmp cstar_dispatch
sysretl_audit:
@@ -355,16 +355,16 @@ sysretl_audit:
cstar_tracesys:
#ifdef CONFIG_AUDITSYSCALL
- testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+ testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP)
jz cstar_auditsys
#endif
xchgl %r9d,%ebp
SAVE_EXTRA_REGS
- CLEAR_RREGS 0, r9
+ CLEAR_RREGS r9
movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
movq %rsp,%rdi /* &pt_regs -> arg1 */
call syscall_trace_enter
- LOAD_ARGS32 ARGOFFSET, 1 /* reload args from stack in case ptrace changed it */
+ LOAD_ARGS32 1 /* reload args from stack in case ptrace changed it */
RESTORE_EXTRA_REGS
xchgl %ebp,%r9d
cmpq $(IA32_NR_syscalls-1),%rax
@@ -422,8 +422,8 @@ ENTRY(ia32_syscall)
this could be a problem. */
ALLOC_PTREGS_ON_STACK
SAVE_C_REGS_EXCEPT_R891011
- orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
- testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+ orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP)
+ testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP)
jnz ia32_tracesys
cmpq $(IA32_NR_syscalls-1),%rax
ja ia32_badsys
@@ -431,9 +431,9 @@ ia32_do_call:
IA32_ARG_FIXUP
call *ia32_sys_call_table(,%rax,8) # xxx: rip relative
ia32_sysret:
- movq %rax,RAX-ARGOFFSET(%rsp)
+ movq %rax,RAX(%rsp)
ia32_ret_from_sys_call:
- CLEAR_RREGS -ARGOFFSET
+ CLEAR_RREGS
jmp int_ret_from_sys_call
ia32_tracesys:
@@ -442,7 +442,7 @@ ia32_tracesys:
movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
movq %rsp,%rdi /* &pt_regs -> arg1 */
call syscall_trace_enter
- LOAD_ARGS32 ARGOFFSET /* reload args from stack in case ptrace changed it */
+ LOAD_ARGS32 /* reload args from stack in case ptrace changed it */
RESTORE_EXTRA_REGS
cmpq $(IA32_NR_syscalls-1),%rax
ja int_ret_from_sys_call /* ia32_tracesys has set RAX(%rsp) */
@@ -450,7 +450,7 @@ ia32_tracesys:
END(ia32_syscall)
ia32_badsys:
- movq $0,ORIG_RAX-ARGOFFSET(%rsp)
+ movq $0,ORIG_RAX(%rsp)
movq $-ENOSYS,%rax
jmp ia32_sysret
@@ -482,17 +482,17 @@ ia32_ptregs_common:
CFI_ENDPROC
CFI_STARTPROC32 simple
CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,SS+8-ARGOFFSET
- CFI_REL_OFFSET rax,RAX-ARGOFFSET
- CFI_REL_OFFSET rcx,RCX-ARGOFFSET
- CFI_REL_OFFSET rdx,RDX-ARGOFFSET
- CFI_REL_OFFSET rsi,RSI-ARGOFFSET
- CFI_REL_OFFSET rdi,RDI-ARGOFFSET
- CFI_REL_OFFSET rip,RIP-ARGOFFSET
-/* CFI_REL_OFFSET cs,CS-ARGOFFSET*/
-/* CFI_REL_OFFSET rflags,EFLAGS-ARGOFFSET*/
- CFI_REL_OFFSET rsp,RSP-ARGOFFSET
-/* CFI_REL_OFFSET ss,SS-ARGOFFSET*/
+ CFI_DEF_CFA rsp,SS+8
+ CFI_REL_OFFSET rax,RAX
+ CFI_REL_OFFSET rcx,RCX
+ CFI_REL_OFFSET rdx,RDX
+ CFI_REL_OFFSET rsi,RSI
+ CFI_REL_OFFSET rdi,RDI
+ CFI_REL_OFFSET rip,RIP
+/* CFI_REL_OFFSET cs,CS*/
+/* CFI_REL_OFFSET rflags,EFLAGS*/
+ CFI_REL_OFFSET rsp,RSP
+/* CFI_REL_OFFSET ss,SS*/
SAVE_EXTRA_REGS 8
call *%rax
RESTORE_EXTRA_REGS 8
diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h
index 7642948..e8e2e41 100644
--- a/arch/x86/include/asm/calling.h
+++ b/arch/x86/include/asm/calling.h
@@ -88,8 +88,6 @@ For 32-bit we have the following conventions - kernel is built with
#define RSP 19*8
#define SS 20*8
-#define ARGOFFSET 0
-
.macro ALLOC_PTREGS_ON_STACK addskip=0
subq $15*8+\addskip, %rsp
CFI_ADJUST_CFA_OFFSET 15*8+\addskip
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index c489a2d..8c6a01d 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -73,7 +73,7 @@ ENDPROC(native_usergs_sysret64)
#endif /* CONFIG_PARAVIRT */
-.macro TRACE_IRQS_IRETQ offset=ARGOFFSET
+.macro TRACE_IRQS_IRETQ offset=0
#ifdef CONFIG_TRACE_IRQFLAGS
bt $9,EFLAGS-\offset(%rsp) /* interrupts off? */
jnc 1f
@@ -107,7 +107,7 @@ ENDPROC(native_usergs_sysret64)
call debug_stack_reset
.endm
-.macro TRACE_IRQS_IRETQ_DEBUG offset=ARGOFFSET
+.macro TRACE_IRQS_IRETQ_DEBUG offset=0
bt $9,EFLAGS-\offset(%rsp) /* interrupts off? */
jnc 1f
TRACE_IRQS_ON_DEBUG
@@ -184,16 +184,16 @@ ENDPROC(native_usergs_sysret64)
* frame that enables passing a complete pt_regs to a C function.
*/
.macro DEFAULT_FRAME start=1 offset=0
- XCPT_FRAME \start, ORIG_RAX+\offset-ARGOFFSET
- CFI_REL_OFFSET rdi, RDI+\offset-ARGOFFSET
- CFI_REL_OFFSET rsi, RSI+\offset-ARGOFFSET
- CFI_REL_OFFSET rdx, RDX+\offset-ARGOFFSET
- CFI_REL_OFFSET rcx, RCX+\offset-ARGOFFSET
- CFI_REL_OFFSET rax, RAX+\offset-ARGOFFSET
- CFI_REL_OFFSET r8, R8+\offset-ARGOFFSET
- CFI_REL_OFFSET r9, R9+\offset-ARGOFFSET
- CFI_REL_OFFSET r10, R10+\offset-ARGOFFSET
- CFI_REL_OFFSET r11, R11+\offset-ARGOFFSET
+ XCPT_FRAME \start, ORIG_RAX+\offset
+ CFI_REL_OFFSET rdi, RDI+\offset
+ CFI_REL_OFFSET rsi, RSI+\offset
+ CFI_REL_OFFSET rdx, RDX+\offset
+ CFI_REL_OFFSET rcx, RCX+\offset
+ CFI_REL_OFFSET rax, RAX+\offset
+ CFI_REL_OFFSET r8, R8+\offset
+ CFI_REL_OFFSET r9, R9+\offset
+ CFI_REL_OFFSET r10, R10+\offset
+ CFI_REL_OFFSET r11, R11+\offset
CFI_REL_OFFSET rbx, RBX+\offset
CFI_REL_OFFSET rbp, RBP+\offset
CFI_REL_OFFSET r12, R12+\offset
@@ -237,13 +237,13 @@ ENTRY(ret_from_fork)
RESTORE_EXTRA_REGS
- testl $3, CS-ARGOFFSET(%rsp) # from kernel_thread?
+ testl $3, CS(%rsp) # from kernel_thread?
jz 1f
testl $_TIF_IA32, TI_flags(%rcx) # 32-bit compat task needs IRET
jnz int_ret_from_sys_call
- RESTORE_TOP_OF_STACK %rdi, -ARGOFFSET
+ RESTORE_TOP_OF_STACK %rdi
jmp ret_from_sys_call # go to the SYSRET fastpath
1:
@@ -310,10 +310,10 @@ GLOBAL(system_call_after_swapgs)
ENABLE_INTERRUPTS(CLBR_NONE)
ALLOC_PTREGS_ON_STACK 8
SAVE_C_REGS
- movq %rax,ORIG_RAX-ARGOFFSET(%rsp)
- movq %rcx,RIP-ARGOFFSET(%rsp)
- CFI_REL_OFFSET rip,RIP-ARGOFFSET
- testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+ movq %rax,ORIG_RAX(%rsp)
+ movq %rcx,RIP(%rsp)
+ CFI_REL_OFFSET rip,RIP
+ testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP)
jnz tracesys
system_call_fastpath:
#if __SYSCALL_MASK == ~0
@@ -325,7 +325,7 @@ system_call_fastpath:
ja badsys
movq %r10,%rcx
call *sys_call_table(,%rax,8) # XXX: rip relative
- movq %rax,RAX-ARGOFFSET(%rsp)
+ movq %rax,RAX(%rsp)
/*
* Syscall return path ending with SYSRET (fast path)
* Has incomplete stack frame and undefined top of stack.
@@ -337,7 +337,7 @@ sysret_check:
LOCKDEP_SYS_EXIT
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
- movl TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET),%edx
+ movl TI_flags+THREAD_INFO(%rsp,RIP),%edx
andl %edi,%edx
jnz sysret_careful
CFI_REMEMBER_STATE
@@ -346,7 +346,7 @@ sysret_check:
*/
TRACE_IRQS_ON
RESTORE_C_REGS_EXCEPT_RCX
- movq RIP-ARGOFFSET(%rsp),%rcx
+ movq RIP(%rsp),%rcx
CFI_REGISTER rip,rcx
/*CFI_REGISTER rflags,r11*/
movq PER_CPU_VAR(old_rsp), %rsp
@@ -378,11 +378,11 @@ sysret_signal:
* These all wind up with the iret return path anyway,
* so just join that path right now.
*/
- FIXUP_TOP_OF_STACK %r11, -ARGOFFSET
+ FIXUP_TOP_OF_STACK %r11
jmp int_check_syscall_exit_work
badsys:
- movq $-ENOSYS,RAX-ARGOFFSET(%rsp)
+ movq $-ENOSYS,RAX(%rsp)
jmp ret_from_sys_call
#ifdef CONFIG_AUDITSYSCALL
@@ -408,7 +408,7 @@ auditsys:
* masked off.
*/
sysret_audit:
- movq RAX-ARGOFFSET(%rsp),%rsi /* second arg, syscall return value */
+ movq RAX(%rsp),%rsi /* second arg, syscall return value */
cmpq $-MAX_ERRNO,%rsi /* is it < -MAX_ERRNO? */
setbe %al /* 1 if so, 0 if not */
movzbl %al,%edi /* zero-extend that into %edi */
@@ -420,7 +420,7 @@ sysret_audit:
/* Do syscall tracing */
tracesys:
#ifdef CONFIG_AUDITSYSCALL
- testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+ testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP)
jz auditsys
#endif
SAVE_EXTRA_REGS
@@ -444,7 +444,7 @@ tracesys:
ja int_ret_from_sys_call /* RAX(%rsp) set to -ENOSYS above */
movq %r10,%rcx /* fixup for C */
call *sys_call_table(,%rax,8)
- movq %rax,RAX-ARGOFFSET(%rsp)
+ movq %rax,RAX(%rsp)
/* Use IRET because user could have changed frame */
/*
@@ -528,9 +528,9 @@ END(stub_\func)
ENTRY(\label)
CFI_STARTPROC
DEFAULT_FRAME 0, 8 /* offset 8: return address */
- FIXUP_TOP_OF_STACK %r11, 8-ARGOFFSET
+ FIXUP_TOP_OF_STACK %r11, 8
call \func
- RESTORE_TOP_OF_STACK %r11, 8-ARGOFFSET
+ RESTORE_TOP_OF_STACK %r11, 8
ret
CFI_ENDPROC
END(\label)
@@ -702,7 +702,7 @@ common_interrupt:
ASM_CLAC
addq $-0x80,(%rsp) /* Adjust vector to [-256,-1] range */
interrupt do_IRQ
- /* 0(%rsp): old_rsp-ARGOFFSET */
+ /* 0(%rsp): old_rsp */
ret_from_intr:
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
@@ -712,13 +712,13 @@ ret_from_intr:
popq %rsi
CFI_DEF_CFA rsi,SS+8-RBP /* reg/off reset after def_cfa_expr */
/* return code expects complete pt_regs - adjust rsp accordingly: */
- leaq ARGOFFSET-RBP(%rsi), %rsp
+ leaq -RBP(%rsi), %rsp
CFI_DEF_CFA_REGISTER rsp
- CFI_ADJUST_CFA_OFFSET RBP-ARGOFFSET
+ CFI_ADJUST_CFA_OFFSET RBP
exit_intr:
GET_THREAD_INFO(%rcx)
- testl $3,CS-ARGOFFSET(%rsp)
+ testl $3,CS(%rsp)
je retint_kernel
/* Interrupt came from user space */
@@ -856,7 +856,7 @@ retint_signal:
ENTRY(retint_kernel)
cmpl $0,PER_CPU_VAR(__preempt_count)
jnz retint_restore_args
- bt $9,EFLAGS-ARGOFFSET(%rsp) /* interrupts off? */
+ bt $9,EFLAGS(%rsp) /* interrupts off? */
jnc retint_restore_args
call preempt_schedule_irq
jmp exit_intr
--
1.8.1.4
^ permalink raw reply related [flat|nested] 12+ messages in thread* Re: [PATCH 5/6] x86: mass removal of ARGOFFSET
2014-08-04 13:19 ` [PATCH 5/6] x86: mass removal of ARGOFFSET Denys Vlasenko
@ 2014-08-05 11:09 ` Denys Vlasenko
0 siblings, 0 replies; 12+ messages in thread
From: Denys Vlasenko @ 2014-08-05 11:09 UTC (permalink / raw)
To: Denys Vlasenko
Cc: Linux Kernel Mailing List, Oleg Nesterov, H. Peter Anvin,
Andy Lutomirski, Frederic Weisbecker, X86 ML, Alexei Starovoitov,
Will Drewry, Kees Cook
FYI: the patch is incomplete. arch/x86/ia32/ia32entry.S has a bug, fix is:
sysexit_from_sys_call:
andl $~TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
/* clear IF, that popfq doesn't enable interrupts early */
- andl $~0x200,EFLAGS-R11(%rsp).
- movl RIP-R11(%rsp),%edx /* User %eip */
+ andl $~0x200,EFLAGS-ARGOFFSET(%rsp)
+ movl RIP-ARGOFFSET(%rsp),%edx /* User %eip */
CFI_REGISTER rip,rdx
RESTORE_ARGS 0,24,0,0,0,0
xorq %r8,%r8
It went unnoticed for so long because
these two constants are the same.
Patch #4 changes ARGOFFSET to 0, but of course R11 stays the same,
breaking this code.
^ permalink raw reply [flat|nested] 12+ messages in thread
* [PATCH 6/6] x86: rename some macros and labels, no code changes
2014-08-04 13:19 [PATCH 0/6 v2] x86: entry_64.S: always allocate complete "struct pt_regs" Denys Vlasenko
` (4 preceding siblings ...)
2014-08-04 13:19 ` [PATCH 5/6] x86: mass removal of ARGOFFSET Denys Vlasenko
@ 2014-08-04 13:19 ` Denys Vlasenko
5 siblings, 0 replies; 12+ messages in thread
From: Denys Vlasenko @ 2014-08-04 13:19 UTC (permalink / raw)
To: linux-kernel
Cc: Denys Vlasenko, Oleg Nesterov, H. Peter Anvin, Andy Lutomirski,
Frederic Weisbecker, X86 ML, Alexei Starovoitov, Will Drewry,
Kees Cook
Rename LOAD_ARGS32 to RESTORE_REGS32 to match other RESTORE_* macros.
The "ARGS" part was misleading anyway - we are restoring registers,
not arguments.
Similarly, rename [retint_]restore_args to [retint_]restore_c_regs:
at these labels, we restore registers clobbered by C ABI;
rename int_restore_rest to int_restore_extra_regs.
Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com>
CC: Oleg Nesterov <oleg@redhat.com>
CC: "H. Peter Anvin" <hpa@zytor.com>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Frederic Weisbecker <fweisbec@gmail.com>
CC: X86 ML <x86@kernel.org>
CC: Alexei Starovoitov <ast@plumgrid.com>
CC: Will Drewry <wad@chromium.org>
CC: Kees Cook <keescook@chromium.org>
CC: linux-kernel@vger.kernel.org
---
arch/x86/ia32/ia32entry.S | 10 +++++-----
arch/x86/kernel/entry_64.S | 16 ++++++++--------
2 files changed, 13 insertions(+), 13 deletions(-)
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 7315179..dd1c5fd 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -51,7 +51,7 @@
.endm
/*
- * Reload arg registers from stack in case ptrace changed them.
+ * Reload registers from stack in case ptrace changed them.
* We don't reload %eax because syscall_trace_enter() returned
* the %rax value we should see. Instead, we just truncate that
* value to 32 bits again as we did on entry from user mode.
@@ -60,7 +60,7 @@
* If it's -1 to make us punt the syscall, then (u32)-1 is still
* an appropriately invalid value.
*/
- .macro LOAD_ARGS32 _r9=0
+ .macro RESTORE_REGS32 _r9=0
.if \_r9
movl R9(%rsp),%r9d
.endif
@@ -247,7 +247,7 @@ sysenter_tracesys:
movq $-ENOSYS,RAX(%rsp)/* ptrace can change this for a bad syscall */
movq %rsp,%rdi /* &pt_regs -> arg1 */
call syscall_trace_enter
- LOAD_ARGS32 /* reload args from stack in case ptrace changed it */
+ RESTORE_REGS32 /* reload regs from stack in case ptrace changed it */
RESTORE_EXTRA_REGS
cmpq $(IA32_NR_syscalls-1),%rax
ja int_ret_from_sys_call /* sysenter_tracesys has set RAX(%rsp) */
@@ -364,7 +364,7 @@ cstar_tracesys:
movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
movq %rsp,%rdi /* &pt_regs -> arg1 */
call syscall_trace_enter
- LOAD_ARGS32 1 /* reload args from stack in case ptrace changed it */
+ RESTORE_REGS32 1 /* reload regs from stack in case ptrace changed it */
RESTORE_EXTRA_REGS
xchgl %ebp,%r9d
cmpq $(IA32_NR_syscalls-1),%rax
@@ -442,7 +442,7 @@ ia32_tracesys:
movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
movq %rsp,%rdi /* &pt_regs -> arg1 */
call syscall_trace_enter
- LOAD_ARGS32 /* reload args from stack in case ptrace changed it */
+ RESTORE_REGS32 /* reload args from stack in case ptrace changed it */
RESTORE_EXTRA_REGS
cmpq $(IA32_NR_syscalls-1),%rax
ja int_ret_from_sys_call /* ia32_tracesys has set RAX(%rsp) */
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 8c6a01d..e9bbe02 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -62,7 +62,7 @@
#ifndef CONFIG_PREEMPT
-#define retint_kernel retint_restore_args
+#define retint_kernel retint_restore_c_regs
#endif
#ifdef CONFIG_PARAVIRT
@@ -494,7 +494,7 @@ int_check_syscall_exit_work:
call syscall_trace_leave
popq_cfi %rdi
andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU),%edi
- jmp int_restore_rest
+ jmp int_restore_extra_regs
int_signal:
testl $_TIF_DO_NOTIFY_MASK,%edx
@@ -503,7 +503,7 @@ int_signal:
xorl %esi,%esi # oldset -> arg2
call do_notify_resume
1: movl $_TIF_WORK_MASK,%edi
-int_restore_rest:
+int_restore_extra_regs:
RESTORE_EXTRA_REGS
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
@@ -742,15 +742,15 @@ retint_swapgs: /* return to user-space */
DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_IRETQ
SWAPGS
- jmp restore_args
+ jmp restore_c_regs
-retint_restore_args: /* return to kernel space */
+retint_restore_c_regs: /* return to kernel space */
DISABLE_INTERRUPTS(CLBR_ANY)
/*
* The iretq could re-enable interrupts:
*/
TRACE_IRQS_IRETQ
-restore_args:
+restore_c_regs:
RESTORE_C_REGS
REMOVE_PTREGS_FROM_STACK 8
@@ -855,9 +855,9 @@ retint_signal:
/* rcx: threadinfo. interrupts off. */
ENTRY(retint_kernel)
cmpl $0,PER_CPU_VAR(__preempt_count)
- jnz retint_restore_args
+ jnz retint_restore_c_regs
bt $9,EFLAGS(%rsp) /* interrupts off? */
- jnc retint_restore_args
+ jnc retint_restore_c_regs
call preempt_schedule_irq
jmp exit_intr
#endif
--
1.8.1.4
^ permalink raw reply related [flat|nested] 12+ messages in thread