x86/stackframe/32: Provide consistent pt_regs

Currently pt_regs on x86_32 has an oddity in that kernel regs
(!user_mode(regs)) are short two entries (esp/ss). This means that any
code trying to use them (typically: regs->sp) needs to jump through
some unfortunate hoops.

Change the entry code to fix this up and create a full pt_regs frame.

This then simplifies various trampolines in ftrace and kprobes, the
stack unwinder, ptrace, kdump and kgdb.

Much thanks to Josh for help with the cleanups!

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

3 files changed, 26 insertions, 27 deletions

diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h
index 2e25f5f3fa1f..7d3a2e2daf01 100644
--- a/arch/x86/kernel/kprobes/common.h
+++ b/arch/x86/kernel/kprobes/common.h
@@ -72,8 +72,8 @@
 	"	popl %edi\n"			\
 	"	popl %ebp\n"			\
 	"	popl %eax\n"			\
-	/* Skip ds, es, fs, gs, orig_ax, and ip. Note: don't pop cs here*/\
-	"	addl $24, %esp\n"
+	/* Skip ds, es, fs, gs, orig_ax, ip, and cs. */\
+	"	addl $7*4, %esp\n"
 #endif
 
 /* Ensure if the instruction can be boostable */
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 6afd8061dbae..bd17dbb15d6a 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -56,7 +56,7 @@
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
-#define stack_addr(regs) ((unsigned long *)kernel_stack_pointer(regs))
+#define stack_addr(regs) ((unsigned long *)regs->sp)
 
 #define W(row, b0, b1, b2, b3, b4, b5, b6, b7, b8, b9, ba, bb, bc, bd, be, bf)\
 	(((b0##UL << 0x0)|(b1##UL << 0x1)|(b2##UL << 0x2)|(b3##UL << 0x3) |   \
@@ -718,29 +718,27 @@ asm(
 	".global kretprobe_trampoline\n"
 	".type kretprobe_trampoline, @function\n"
 	"kretprobe_trampoline:\n"
-#ifdef CONFIG_X86_64
 	/* We don't bother saving the ss register */
+#ifdef CONFIG_X86_64
 	"	pushq %rsp\n"
 	"	pushfq\n"
 	SAVE_REGS_STRING
 	"	movq %rsp, %rdi\n"
 	"	call trampoline_handler\n"
 	/* Replace saved sp with true return address. */
-	"	movq %rax, 152(%rsp)\n"
+	"	movq %rax, 19*8(%rsp)\n"
 	RESTORE_REGS_STRING
 	"	popfq\n"
 #else
-	"	pushf\n"
+	"	pushl %esp\n"
+	"	pushfl\n"
 	SAVE_REGS_STRING
 	"	movl %esp, %eax\n"
 	"	call trampoline_handler\n"
-	/* Move flags to cs */
-	"	movl 56(%esp), %edx\n"
-	"	movl %edx, 52(%esp)\n"
-	/* Replace saved flags with true return address. */
-	"	movl %eax, 56(%esp)\n"
+	/* Replace saved sp with true return address. */
+	"	movl %eax, 15*4(%esp)\n"
 	RESTORE_REGS_STRING
-	"	popf\n"
+	"	popfl\n"
 #endif
 	"	ret\n"
 	".size kretprobe_trampoline, .-kretprobe_trampoline\n"
@@ -781,16 +779,13 @@ __used __visible void *trampoline_handler(struct pt_regs *regs)
 	INIT_HLIST_HEAD(&empty_rp);
 	kretprobe_hash_lock(current, &head, &flags);
 	/* fixup registers */
-#ifdef CONFIG_X86_64
 	regs->cs = __KERNEL_CS;
-	/* On x86-64, we use pt_regs->sp for return address holder. */
-	frame_pointer = &regs->sp;
-#else
-	regs->cs = __KERNEL_CS | get_kernel_rpl();
+#ifdef CONFIG_X86_32
+	regs->cs |= get_kernel_rpl();
 	regs->gs = 0;
-	/* On x86-32, we use pt_regs->flags for return address holder. */
-	frame_pointer = &regs->flags;
 #endif
+	/* We use pt_regs->sp for return address holder. */
+	frame_pointer = &regs->sp;
 	regs->ip = trampoline_address;
 	regs->orig_ax = ~0UL;
 
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 7c361a24c6df..282b4eb67e30 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -102,14 +102,15 @@ asm (
 			"optprobe_template_call:\n"
 			ASM_NOP5
 			/* Move flags to rsp */
-			"	movq 144(%rsp), %rdx\n"
-			"	movq %rdx, 152(%rsp)\n"
+			"	movq 18*8(%rsp), %rdx\n"
+			"	movq %rdx, 19*8(%rsp)\n"
 			RESTORE_REGS_STRING
 			/* Skip flags entry */
 			"	addq $8, %rsp\n"
 			"	popfq\n"
 #else /* CONFIG_X86_32 */
-			"	pushf\n"
+			"	pushl %esp\n"
+			"	pushfl\n"
 			SAVE_REGS_STRING
 			"	movl %esp, %edx\n"
 			".global optprobe_template_val\n"
@@ -118,9 +119,13 @@ asm (
 			".global optprobe_template_call\n"
 			"optprobe_template_call:\n"
 			ASM_NOP5
+			/* Move flags into esp */
+			"	movl 14*4(%esp), %edx\n"
+			"	movl %edx, 15*4(%esp)\n"
 			RESTORE_REGS_STRING
-			"	addl $4, %esp\n"	/* skip cs */
-			"	popf\n"
+			/* Skip flags entry */
+			"	addl $4, %esp\n"
+			"	popfl\n"
 #endif
 			".global optprobe_template_end\n"
 			"optprobe_template_end:\n"
@@ -152,10 +157,9 @@ optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs)
 	} else {
 		struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 		/* Save skipped registers */
-#ifdef CONFIG_X86_64
 		regs->cs = __KERNEL_CS;
-#else
-		regs->cs = __KERNEL_CS | get_kernel_rpl();
+#ifdef CONFIG_X86_32
+		regs->cs |= get_kernel_rpl();
 		regs->gs = 0;
 #endif
 		regs->ip = (unsigned long)op->kp.addr + INT3_SIZE;