[PATCH 2/5] x86: get rid of KERNEL_STACK_OFFSET

From: Denys Vlasenko
Date: Thu Mar 19 2015 - 13:18:44 EST


PER_CPU_VAR(kernel_stack) was set up in a way where it points
five stack slots below the top of stack.

Presumably, it was done to avoid one "sub $5*8,%rsp"
in syscall/sysenter code paths, where iret frame needs to be
created by hand.

Ironically, none of them benefits from this optimization,
since all of them need to allocate additional data on stack
(struct pt_regs), so they still have to perform subtraction.

This patch eliminates KERNEL_STACK_OFFSET.

PER_CPU_VAR(kernel_stack) now points directly to top of stack.
pt_regs allocations are adjusted to allocate iret frame as well.
Hopefully we can merge it later with 32-bit specific
PER_CPU_VAR(cpu_current_top_of_stack) variable...

Net result in generated code is that constants in several insns
are changed.

This change is necessary for changing struct pt_regs creation
in SYSCALL64 code path from MOV to PUSH instructions.

Signed-off-by: Denys Vlasenko <dvlasenk@xxxxxxxxxx>
CC: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
CC: Steven Rostedt <rostedt@xxxxxxxxxxx>
CC: Ingo Molnar <mingo@xxxxxxxxxx>
CC: Borislav Petkov <bp@xxxxxxxxx>
CC: "H. Peter Anvin" <hpa@xxxxxxxxx>
CC: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
CC: Oleg Nesterov <oleg@xxxxxxxxxx>
CC: Frederic Weisbecker <fweisbec@xxxxxxxxx>
CC: Alexei Starovoitov <ast@xxxxxxxxxxxx>
CC: Will Drewry <wad@xxxxxxxxxxxx>
CC: Kees Cook <keescook@xxxxxxxxxxxx>
CC: x86@xxxxxxxxxx
CC: linux-kernel@xxxxxxxxxxxxxxx
---
arch/x86/ia32/ia32entry.S | 4 ++--
arch/x86/include/asm/thread_info.h | 5 ++---
arch/x86/kernel/cpu/common.c | 2 +-
arch/x86/kernel/entry_64.S | 5 ++---
arch/x86/kernel/process_32.c | 2 +-
arch/x86/kernel/process_64.c | 3 +--
arch/x86/kernel/smpboot.c | 3 +--
arch/x86/xen/smp.c | 3 +--
8 files changed, 11 insertions(+), 16 deletions(-)

diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 50190e1..acbff3f 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -311,7 +311,7 @@ ENDPROC(ia32_sysenter_target)
ENTRY(ia32_cstar_target)
CFI_STARTPROC32 simple
CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,KERNEL_STACK_OFFSET
+ CFI_DEF_CFA rsp,0
CFI_REGISTER rip,rcx
/*CFI_REGISTER rflags,r11*/
SWAPGS_UNSAFE_STACK
@@ -323,7 +323,7 @@ ENTRY(ia32_cstar_target)
* disabled irqs and here we enable it straight after entry:
*/
ENABLE_INTERRUPTS(CLBR_NONE)
- ALLOC_PT_GPREGS_ON_STACK 8 /* +8: space for orig_ax */
+ ALLOC_PT_GPREGS_ON_STACK 6*8 /* 6*8: space for orig_ax and iret frame */
SAVE_C_REGS_EXCEPT_RCX_R891011
movl %eax,%eax /* zero extension */
movq %rax,ORIG_RAX(%rsp)
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 0519945..89b814e 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -172,7 +172,6 @@ struct thread_info {
#define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW)

#define STACK_WARN (THREAD_SIZE/8)
-#define KERNEL_STACK_OFFSET (5*(BITS_PER_LONG/8))

/*
* macros/functions for gaining access to the thread information structure
@@ -201,10 +200,10 @@ static inline unsigned long current_stack_pointer(void)

#else /* !__ASSEMBLY__ */

-/* how to get the thread information struct from ASM */
+/* Load thread_info address into "reg" */
#define GET_THREAD_INFO(reg) \
_ASM_MOV PER_CPU_VAR(kernel_stack),reg ; \
- _ASM_SUB $(THREAD_SIZE-KERNEL_STACK_OFFSET),reg ;
+ _ASM_SUB $(THREAD_SIZE),reg ;

/*
* ASM operand which evaluates to thread_info address
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c5b5ccb..9461c83 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1136,7 +1136,7 @@ static __init int setup_disablecpuid(char *arg)
__setup("clearcpuid=", setup_disablecpuid);

DEFINE_PER_CPU(unsigned long, kernel_stack) =
- (unsigned long)&init_thread_union - KERNEL_STACK_OFFSET + THREAD_SIZE;
+ (unsigned long)&init_thread_union + THREAD_SIZE;
EXPORT_PER_CPU_SYMBOL(kernel_stack);

#ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index d785a7d..ecb68d8 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -225,7 +225,7 @@ ENDPROC(native_usergs_sysret64)
ENTRY(system_call)
CFI_STARTPROC simple
CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,KERNEL_STACK_OFFSET
+ CFI_DEF_CFA rsp,0
CFI_REGISTER rip,rcx
/*CFI_REGISTER rflags,r11*/
SWAPGS_UNSAFE_STACK
@@ -242,9 +242,8 @@ GLOBAL(system_call_after_swapgs)
* so we can enable interrupts only after we're done with using rsp_scratch:
*/
movq %rsp,PER_CPU_VAR(rsp_scratch)
- /* kernel_stack is set so that 5 slots (iret frame) are preallocated */
movq PER_CPU_VAR(kernel_stack),%rsp
- ALLOC_PT_GPREGS_ON_STACK 8 /* +8: space for orig_ax */
+ ALLOC_PT_GPREGS_ON_STACK 6*8 /* 6*8: space for orig_ax and iret frame */
movq %rcx,RIP(%rsp)
movq PER_CPU_VAR(rsp_scratch),%rcx
movq %r11,EFLAGS(%rsp)
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 1b9963f..5a4c2f8 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -312,7 +312,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
load_sp0(tss, next);
this_cpu_write(kernel_stack,
(unsigned long)task_stack_page(next_p) +
- THREAD_SIZE - KERNEL_STACK_OFFSET);
+ THREAD_SIZE);
this_cpu_write(cpu_current_top_of_stack,
(unsigned long)task_stack_page(next_p) +
THREAD_SIZE);
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 97f5658..db49063 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -409,8 +409,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
load_sp0(tss, next);

this_cpu_write(kernel_stack,
- (unsigned long)task_stack_page(next_p) +
- THREAD_SIZE - KERNEL_STACK_OFFSET);
+ (unsigned long)task_stack_page(next_p) + THREAD_SIZE);

/*
* Now maybe reload the debug registers and handle I/O bitmaps
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 759388c..7b20ffd 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -813,8 +813,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
initial_gs = per_cpu_offset(cpu);
#endif
per_cpu(kernel_stack, cpu) =
- (unsigned long)task_stack_page(idle) -
- KERNEL_STACK_OFFSET + THREAD_SIZE;
+ (unsigned long)task_stack_page(idle) + THREAD_SIZE;
early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
initial_code = (unsigned long)start_secondary;
stack_start = idle->thread.sp;
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 08e8489..765b768 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -452,8 +452,7 @@ static int xen_cpu_up(unsigned int cpu, struct task_struct *idle)
clear_tsk_thread_flag(idle, TIF_FORK);
#endif
per_cpu(kernel_stack, cpu) =
- (unsigned long)task_stack_page(idle) -
- KERNEL_STACK_OFFSET + THREAD_SIZE;
+ (unsigned long)task_stack_page(idle) + THREAD_SIZE;

xen_setup_runstate_info(cpu);
xen_setup_timer(cpu);
--
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/