[PATCH 2/3] x86/entry/64: Use the TSS sp2 slot for rsp_scratch

[Andy Lutomirski]

In the non-trampoline SYSCALL64 path, we use a percpu variable to
temporarily store the user RSP value.  Instead of a separate
variable, use the otherwise unused sp2 slot in the TSS.  This will
improve cache locality, as the sp1 slot is already used in the same
code to find the kernel stack.  It will also simplify a future
change to make the non-trampoline path work in PTI mode.

Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxx>
---
 arch/x86/include/asm/processor.h   | 6 ++++++
 arch/x86/include/asm/thread_info.h | 1 +
 arch/x86/kernel/asm-offsets.c      | 3 ++-
 arch/x86/kernel/process_64.c       | 2 --
 4 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c24297268ebc..8433d76bc37b 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -313,7 +313,13 @@ struct x86_hw_tss {
 	 */
 	u64			sp1;
 
+	/*
+	 * Since Linux does not use ring 2, the 'sp2' slot is unused by
+	 * hardware.  entry_SYSCALL_64 uses it as scratch space to stash
+	 * the user RSP value.
+	 */
 	u64			sp2;
+
 	u64			reserved2;
 	u64			ist[7];
 	u32			reserved3;
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 2ff2a30a264f..9a2f84233e39 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -209,6 +209,7 @@ static inline int arch_within_stack_frames(const void * const stack,
 
 #ifdef CONFIG_X86_64
 # define cpu_current_top_of_stack (cpu_tss_rw + TSS_sp1)
+# define rsp_scratch (cpu_tss_rw + TSS_sp2)
 #endif
 
 #endif
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 01de31db300d..fc2e90d3429a 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -105,7 +105,8 @@ void common(void) {
 	DEFINE(SIZEOF_entry_stack, sizeof(struct entry_stack));
 	DEFINE(MASK_entry_stack, (~(sizeof(struct entry_stack) - 1)));
 
-	/* Offset for sp0 and sp1 into the tss_struct */
+	/* Offset for fields in tss_struct */
 	OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
 	OFFSET(TSS_sp1, tss_struct, x86_tss.sp1);
+	OFFSET(TSS_sp2, tss_struct, x86_tss.sp2);
 }
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index a451bc374b9b..0fa7aa19f09e 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -59,8 +59,6 @@
 #include <asm/unistd_32_ia32.h>
 #endif
 
-__visible DEFINE_PER_CPU(unsigned long, rsp_scratch);
-
 /* Prints also some state that isn't saved in the pt_regs */
 void __show_regs(struct pt_regs *regs, int all)
 {
-- 
2.17.1