[PATCH 07/16] x86/asm: Move SYSENTER_stack to the beginning of struct tss_struct

[Andy Lutomirski <luto@kernel.org>]

I want SYSENTER_stack to have reliable overflow detection, which
means that it needs to be at the bottom of a page, not the top.
Move it to the beginning of struct tss_struct and page-align it.

Also add an assertion to make sure that the fixed hardware TSS
doesn't cross a page boundary.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
---
 arch/x86/include/asm/processor.h | 24 +++++++++++++++---------
 arch/x86/kernel/cpu/common.c     | 22 ++++++++++++++++++++++
 2 files changed, 37 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index d32a3c88a968..f816ed2601d4 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -327,7 +327,19 @@ struct x86_hw_tss {
 
 struct tss_struct {
 	/*
-	 * The hardware state:
+	 * Space for the temporary SYSENTER stack.  Used for the entry
+	 * trampoline as well.  Size it such that tss_struct ends up
+	 * as a multiple of PAGE_SIZE.  This calculation assumes that
+	 * io_bitmap is a multiple of PAGE_SIZE (8192 bytes) plus one
+	 * long.
+	 */
+	unsigned long		SYSENTER_stack_canary;
+	unsigned long		SYSENTER_stack[64];
+
+	/*
+	 * The fixed hardware portion.  This must not cross a page boundary
+	 * at risk of violating the SDM's advice and potentially triggering
+	 * errata.
 	 */
 	struct x86_hw_tss	x86_tss;
 
@@ -338,15 +350,9 @@ struct tss_struct {
 	 * be within the limit.
 	 */
 	unsigned long		io_bitmap[IO_BITMAP_LONGS + 1];
+} __attribute__((__aligned__(PAGE_SIZE)));
 
-	/*
-	 * Space for the temporary SYSENTER stack.
-	 */
-	unsigned long		SYSENTER_stack_canary;
-	unsigned long		SYSENTER_stack[64];
-} ____cacheline_aligned;
-
-DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss);
+DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss);
 
 /*
  * sizeof(unsigned long) coming from an extra "long" at the end
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 099fca92f6be..1868fe693fe1 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -509,6 +509,28 @@ static inline void setup_cpu_entry_area(int cpu)
 #endif
 
 	__set_fixmap(get_cpu_entry_area_index(cpu, gdt), get_cpu_gdt_paddr(cpu), gdt_prot);
+
+	/*
+	 *
+	 * The Intel SDM says (Volume 3, 7.2.1):
+	 *
+	 *  Avoid placing a page boundary in the part of the TSS that the
+	 *  processor reads during a task switch (the first 104 bytes). The
+	 *  processor may not correctly perform address translations if a
+	 *  boundary occurs in this area. During a task switch, the processor
+	 *  reads and writes into the first 104 bytes of each TSS (using
+	 *  contiguous physical addresses beginning with the physical address
+	 *  of the first byte of the TSS). So, after TSS access begins, if
+	 *  part of the 104 bytes is not physically contiguous, the processor
+	 *  will access incorrect information without generating a page-fault
+	 *  exception.
+	 *
+	 * There are also a lot of errata involving the TSS spanning a page
+	 * boundary.  Assert that we're not doing that.
+	 */
+	BUILD_BUG_ON((offsetof(struct tss_struct, x86_tss) ^
+		      offsetofend(struct tss_struct, x86_tss)) & PAGE_MASK);
+
 }
 
 /* Load the original GDT from the per-cpu structure */
-- 
2.13.6