All manipulations of PER_CPU(old_rsp) in C code are removed:
it is not used on SYSRET return, so storing anything there is
pointless.
This also allows us to get rid of thread_struct::usersp,
which was needed only to set PER_CPU(old_rsp) for correct
return from fork/clone.
Tweak a few comments as well: we no longer have "partial stack frame",
ever.
Signed-off-by: Denys Vlasenko <dvlas...@redhat.com>
CC: Linus Torvalds <torva...@linux-foundation.org>
CC: Steven Rostedt <rost...@goodmis.org>
CC: Ingo Molnar <mi...@kernel.org>
CC: Borislav Petkov <b...@alien8.de>
CC: "H. Peter Anvin" <h...@zytor.com>
CC: Andy Lutomirski <l...@amacapital.net>
CC: Oleg Nesterov <o...@redhat.com>
CC: Frederic Weisbecker <fweis...@gmail.com>
CC: Alexei Starovoitov <a...@plumgrid.com>
CC: Will Drewry <w...@chromium.org>
CC: Kees Cook <keesc...@chromium.org>
CC: x...@kernel.org
CC: linux-kernel@vger.kernel.org
---
Run-tested, including with PARAVIRT on.
arch/x86/include/asm/processor.h | 6 ------
arch/x86/kernel/entry_64.S | 14 ++++++--------
arch/x86/kernel/process_64.c | 5 -----
3 files changed, 6 insertions(+), 19 deletions(-)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 997e6a1..66a1954 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -496,7 +496,6 @@ struct thread_struct {
#ifdef CONFIG_X86_32
unsigned long sysenter_cs;
#else
- unsigned long usersp; /* Copy from PDA */
unsigned short es;
unsigned short ds;
unsigned short fsindex;
@@ -908,11 +907,6 @@ extern unsigned long thread_saved_pc(struct task_struct
*tsk);
#define task_pt_regs(tsk) ((struct pt_regs *)(tsk)->thread.sp0 - 1)
extern unsigned long KSTK_ESP(struct task_struct *task);
-/*
- * User space RSP while inside the SYSCALL fast path
- */
-DECLARE_PER_CPU(unsigned long, old_rsp);
-
#endif /* CONFIG_X86_64 */
extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 3054a9d..cb86db0 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -15,10 +15,8 @@
* after an interrupt and after each system call.
*
* A note on terminology:
- * - top of stack: Architecture defined interrupt frame from SS to RIP
+ * - iret frame: Architecture defined interrupt frame from SS to RIP
* at the top of the kernel process stack.
- * - partial stack frame: partially saved registers up to R11.
- * - full stack frame: Like partial stack frame, but all register saved.
*
* Some macro usage:
* - CFI macros are used to generate dwarf2 unwind information for better
@@ -219,7 +217,7 @@ ENDPROC(native_usergs_sysret64)
* Interrupts are off on entry.
* Only called from user space.
*
- * When user can change the frames always force IRET. That is because
+ * When user can change pt_regs->foo always force IRET. That is because
* it deals with uncanonical addresses better. SYSRET has trouble
* with them due to bugs in both AMD and Intel CPUs.
*/
@@ -303,7 +301,7 @@ int_ret_from_sys_call_fixup:
FIXUP_TOP_OF_STACK %r11
jmp int_ret_from_sys_call
- /* Do syscall tracing */
+ /* Do syscall entry tracing */
tracesys:
movq %rsp, %rdi
movq $AUDIT_ARCH_X86_64, %rsi
@@ -339,11 +337,11 @@ tracesys_phase2:
movq %r10,%rcx /* fixup for C */
call *sys_call_table(,%rax,8)
movq %rax,RAX(%rsp)
- /* Use IRET because user could have changed frame */
+ /* Use IRET because user could have changed pt_regs->foo */
/*
* Syscall return path ending with IRET.
- * Has correct top of stack, but partial stack frame.
+ * Has correct iret frame.
*/
GLOBAL(int_ret_from_sys_call)
DISABLE_INTERRUPTS(CLBR_NONE)
@@ -374,7 +372,7 @@ int_careful:
TRACE_IRQS_OFF
jmp int_with_check
- /* handle signals and tracing -- both require a full stack frame */
+ /* handle signals and tracing -- both require a full pt_regs */
int_very_careful:
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_NONE)
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index e8c124a..14df2be 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -161,7 +161,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
p->thread.sp0 = (unsigned long)task_stack_page(p) + THREAD_SIZE;
childregs = task_pt_regs(p);
p->thread.sp = (unsigned long) childregs;
- p->thread.usersp = me->thread.usersp;
set_tsk_thread_flag(p, TIF_FORK);
p->thread.io_bitmap_ptr = NULL;
@@ -235,10 +234,8 @@ start_thread_common(struct pt_regs *regs, unsigned long
new_ip,
loadsegment(es, _ds);
loadsegment(ds, _ds);
load_gs_index(0);
- current->thread.usersp = new_sp;
regs->ip = new_ip;
regs->sp = new_sp;
- this_cpu_write(old_rsp, new_sp);
regs->cs = _cs;
regs->ss = _ss;
regs->flags = X86_EFLAGS_IF;
@@ -398,8 +395,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct
*next_p)
/*
* Switch the PDA and FPU contexts.
*/
- prev->usersp = this_cpu_read(old_rsp);
- this_cpu_write(old_rsp, next->usersp);
this_cpu_write(current_task, next_p);
/*
--
1.8.1.4
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
