[PATCH 01/16] x86/asm/64: Allocate and enable the SYSENTER stack

[Andy Lutomirski <luto@kernel.org>]

This will simplify future changes that want scratch variables early in
the SYSENTER handler -- they'll be able to spill registers to the
stack.  It also lets us get rid of a SWAPGS_UNSAFE_STACK user.

This does not depend on CONFIG_IA32_EMULATION because we'll want the
stack space even without IA32 emulation.

As far as I can tell, the reason that this wasn't done from day 1 is
that we use IST for #DB and #BP, which is IMO rather nasty and causes
a lot more problems than it solves.  But, since #DB uses IST, we don't
actually need a real stack for SYSENTER (because SYSENTER with TF set
will invoke #DB on the IST stack rather than the SYSENTER stack).
I want to remove IST usage from these vectors some day, and this patch
is a prerequisite for that as well.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
---
 arch/x86/entry/entry_64_compat.S | 2 +-
 arch/x86/include/asm/processor.h | 3 ---
 arch/x86/kernel/asm-offsets.c    | 5 +++++
 arch/x86/kernel/asm-offsets_32.c | 5 -----
 arch/x86/kernel/cpu/common.c     | 4 +++-
 arch/x86/kernel/process.c        | 2 --
 arch/x86/kernel/traps.c          | 3 +--
 7 files changed, 10 insertions(+), 14 deletions(-)

diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 568e130d932c..dcc6987f9bae 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -48,7 +48,7 @@
  */
 ENTRY(entry_SYSENTER_compat)
 	/* Interrupts are off on entry. */
-	SWAPGS_UNSAFE_STACK
+	SWAPGS
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 	/*
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 2db7cf720b04..789dad5da20f 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -339,14 +339,11 @@ struct tss_struct {
 	 */
 	unsigned long		io_bitmap[IO_BITMAP_LONGS + 1];
 
-#ifdef CONFIG_X86_32
 	/*
 	 * Space for the temporary SYSENTER stack.
 	 */
 	unsigned long		SYSENTER_stack_canary;
 	unsigned long		SYSENTER_stack[64];
-#endif
-
 } ____cacheline_aligned;
 
 DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss);
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 8ea78275480d..b275863128eb 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -93,4 +93,9 @@ void common(void) {
 
 	BLANK();
 	DEFINE(PTREGS_SIZE, sizeof(struct pt_regs));
+
+	/* Offset from cpu_tss to SYSENTER_stack */
+	OFFSET(CPU_TSS_SYSENTER_stack, tss_struct, SYSENTER_stack);
+	/* Size of SYSENTER_stack */
+	DEFINE(SIZEOF_SYSENTER_stack, sizeof(((struct tss_struct *)0)->SYSENTER_stack));
 }
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index dedf428b20b6..52ce4ea16e53 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -50,11 +50,6 @@ void foo(void)
 	DEFINE(TSS_sysenter_sp0, offsetof(struct tss_struct, x86_tss.sp0) -
 	       offsetofend(struct tss_struct, SYSENTER_stack));
 
-	/* Offset from cpu_tss to SYSENTER_stack */
-	OFFSET(CPU_TSS_SYSENTER_stack, tss_struct, SYSENTER_stack);
-	/* Size of SYSENTER_stack */
-	DEFINE(SIZEOF_SYSENTER_stack, sizeof(((struct tss_struct *)0)->SYSENTER_stack));
-
 #ifdef CONFIG_CC_STACKPROTECTOR
 	BLANK();
 	OFFSET(stack_canary_offset, stack_canary, canary);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 13ae9e5eec2f..1243f732810b 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1384,7 +1384,9 @@ void syscall_init(void)
 	 * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit).
 	 */
 	wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
-	wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
+	wrmsrl_safe(MSR_IA32_SYSENTER_ESP,
+		    (unsigned long)this_cpu_ptr(&cpu_tss) +
+		    offsetofend(struct tss_struct, SYSENTER_stack));
 	wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
 #else
 	wrmsrl(MSR_CSTAR, (unsigned long)ignore_sysret);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 97fb3e5737f5..35d674157fda 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -71,9 +71,7 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = {
 	  */
 	.io_bitmap		= { [0 ... IO_BITMAP_LONGS] = ~0 },
 #endif
-#ifdef CONFIG_X86_32
 	.SYSENTER_stack_canary	= STACK_END_MAGIC,
-#endif
 };
 EXPORT_PER_CPU_SYMBOL(cpu_tss);
 
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 989514c94a55..81841f27beff 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -795,14 +795,13 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
 	debug_stack_usage_dec();
 
 exit:
-#if defined(CONFIG_X86_32)
 	/*
 	 * This is the most likely code path that involves non-trivial use
 	 * of the SYSENTER stack.  Check that we haven't overrun it.
 	 */
 	WARN(this_cpu_read(cpu_tss.SYSENTER_stack_canary) != STACK_END_MAGIC,
 	     "Overran or corrupted SYSENTER stack\n");
-#endif
+
 	ist_exit(regs);
 }
 NOKPROBE_SYMBOL(do_debug);
-- 
2.13.6