x86/asm/entry/64: Fix comments

 - Misleading and slightly incorrect comments in "struct pt_regs" are
   fixed (four instances).

 - Fix incorrect comment atop EMPTY_FRAME macro.

 - Explain in more detail what we do with stack layout during hw interrupt.

 - Correct comments about "partial stack frame" which are no longer
   true.

Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com>
Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Cc: Alexei Starovoitov <ast@plumgrid.com>
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: Will Drewry <wad@chromium.org>
Link: http://lkml.kernel.org/r/1423778052-21038-3-git-send-email-dvlasenk@redhat.com
Link: http://lkml.kernel.org/r/e1f4429c491fe6ceeddb879dea2786e0f8920f9c.1424989793.git.luto@amacapital.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 86fc2bb82287a687bd8ca0e976e8d32761678480..4077d963a1a0a561171652c75c69f55f2ce98c01 100644 (file)
--- 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 ad115bf779f36cde8e94af720187b52f7509d6e5..580aee3072e0684082b0f74e1358925efaf4f540 100644 (file)
--- 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
@@ -41,9 +45,12 @@
 #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

diff --git a/arch/x86/include/uapi/asm/ptrace.h b/arch/x86/include/uapi/asm/ptrace.h
index ac4b9aa4d9996b413eaf71ada8bb6b458e7a83a0..bc16115af39b9e66c048b5e0237180f505535b77 100644 (file)
--- 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 e8372e08f8c2512a0b21a51d2b9c6e4ffda63f41..695f4d434a847d02b15f38b0503639e8ea963b7d 100644 (file)
--- 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.
@@ -151,7 +148,7 @@ 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
@@ -379,7 +376,7 @@ tracesys_phase2:
        call syscall_trace_enter_phase2
 
        /*
-        * Reload arg registers from stack in case ptrace changed them.
+        * Reload registers from stack in case ptrace changed them.
         * We don't reload %rax because syscall_trace_entry_phase2() returned
         * the value it wants us to use in the table lookup.
         */
@@ -629,6 +626,13 @@ END(interrupt)
 /* 0(%rsp): ~(interrupt number) */
        .macro interrupt func
        cld
+       /*
+        * 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_PT_GPREGS_ON_STACK -RBP
        SAVE_C_REGS -RBP
        /* this goes to 0(%rsp) for unwinder, not for saving the value: */
@@ -641,6 +645,7 @@ END(interrupt)
        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
@@ -681,6 +686,7 @@ 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
@@ -692,7 +698,7 @@ 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: