x86/asm/entry: Get rid of KERNEL_STACK_OFFSET

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@redhat.com>
Acked-by: Borislav Petkov <bp@suse.de>
Acked-by: Andy Lutomirski <luto@kernel.org>
Cc: Alexei Starovoitov <ast@plumgrid.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Will Drewry <wad@chromium.org>
Link: http://lkml.kernel.org/r/1426785469-15125-2-git-send-email-dvlasenk@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

5 files changed, 6 insertions, 9 deletions

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 66d62aef7214..002216ab9145 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1116,7 +1116,7 @@ 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 8076df982a18..eae69bba3a2c 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 c5e987022ca0..8ed2106b06da 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -308,7 +308,7 @@ __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 da8b74598d90..4baaa972f52a 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -410,8 +410,7 @@ __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 759388c538cf..7b20ffd2fffc 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;