Merge branch 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Ingo Molnar:
 "These are the fixes left over from the v5.4 cycle:

   - Various low level 32-bit entry code fixes and improvements by Andy
     Lutomirski, Peter Zijlstra and Thomas Gleixner.

   - Fix 32-bit Xen PV breakage, by Jan Beulich"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/entry/32: Fix FIXUP_ESPFIX_STACK with user CR3
  x86/pti/32: Calculate the various PTI cpu_entry_area sizes correctly, make the CPU_ENTRY_AREA_PAGES assert precise
  selftests/x86/sigreturn/32: Invalidate DS and ES when abusing the kernel
  selftests/x86/mov_ss_trap: Fix the SYSENTER test
  x86/entry/32: Fix NMI vs ESPFIX
  x86/entry/32: Unwind the ESPFIX stack earlier on exception entry
  x86/entry/32: Move FIXUP_FRAME after pushing %fs in SAVE_ALL
  x86/entry/32: Use %ss segment where required
  x86/entry/32: Fix IRET exception
  x86/cpu_entry_area: Add guard page for entry stack on 32bit
  x86/pti/32: Size initial_page_table correctly
  x86/doublefault/32: Fix stack canaries in the double fault handler
  x86/xen/32: Simplify ring check in xen_iret_crit_fixup()
  x86/xen/32: Make xen_iret_crit_fixup() independent of frame layout
  x86/stackframe/32: Repair 32-bit Xen PV

3 files changed, 28 insertions, 10 deletions

diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h
index 8348f7d69fd5..ea866c7bf31d 100644
--- a/arch/x86/include/asm/cpu_entry_area.h
+++ b/arch/x86/include/asm/cpu_entry_area.h
@@ -78,8 +78,12 @@ struct cpu_entry_area {
 
 	/*
 	 * The GDT is just below entry_stack and thus serves (on x86_64) as
-	 * a a read-only guard page.
+	 * a read-only guard page. On 32-bit the GDT must be writeable, so
+	 * it needs an extra guard page.
 	 */
+#ifdef CONFIG_X86_32
+	char guard_entry_stack[PAGE_SIZE];
+#endif
 	struct entry_stack_page entry_stack_page;
 
 	/*
@@ -94,7 +98,6 @@ struct cpu_entry_area {
 	 */
 	struct cea_exception_stacks estacks;
 #endif
-#ifdef CONFIG_CPU_SUP_INTEL
 	/*
 	 * Per CPU debug store for Intel performance monitoring. Wastes a
 	 * full page at the moment.
@@ -105,11 +108,13 @@ struct cpu_entry_area {
 	 * Reserve enough fixmap PTEs.
 	 */
 	struct debug_store_buffers cpu_debug_buffers;
-#endif
 };
 
-#define CPU_ENTRY_AREA_SIZE	(sizeof(struct cpu_entry_area))
-#define CPU_ENTRY_AREA_TOT_SIZE	(CPU_ENTRY_AREA_SIZE * NR_CPUS)
+#define CPU_ENTRY_AREA_SIZE		(sizeof(struct cpu_entry_area))
+#define CPU_ENTRY_AREA_ARRAY_SIZE	(CPU_ENTRY_AREA_SIZE * NR_CPUS)
+
+/* Total size includes the readonly IDT mapping page as well: */
+#define CPU_ENTRY_AREA_TOTAL_SIZE	(CPU_ENTRY_AREA_ARRAY_SIZE + PAGE_SIZE)
 
 DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
 DECLARE_PER_CPU(struct cea_exception_stacks *, cea_exception_stacks);
@@ -117,13 +122,14 @@ DECLARE_PER_CPU(struct cea_exception_stacks *, cea_exception_stacks);
 extern void setup_cpu_entry_areas(void);
 extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags);
 
+/* Single page reserved for the readonly IDT mapping: */
 #define	CPU_ENTRY_AREA_RO_IDT		CPU_ENTRY_AREA_BASE
 #define CPU_ENTRY_AREA_PER_CPU		(CPU_ENTRY_AREA_RO_IDT + PAGE_SIZE)
 
 #define CPU_ENTRY_AREA_RO_IDT_VADDR	((void *)CPU_ENTRY_AREA_RO_IDT)
 
 #define CPU_ENTRY_AREA_MAP_SIZE			\
-	(CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_TOT_SIZE - CPU_ENTRY_AREA_BASE)
+	(CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_ARRAY_SIZE - CPU_ENTRY_AREA_BASE)
 
 extern struct cpu_entry_area *get_cpu_entry_area(int cpu);
 
diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h
index b0bc0fff5f1f..1636eb8e5a5b 100644
--- a/arch/x86/include/asm/pgtable_32_types.h
+++ b/arch/x86/include/asm/pgtable_32_types.h
@@ -44,11 +44,11 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */
  * Define this here and validate with BUILD_BUG_ON() in pgtable_32.c
  * to avoid include recursion hell
  */
-#define CPU_ENTRY_AREA_PAGES	(NR_CPUS * 40)
+#define CPU_ENTRY_AREA_PAGES	(NR_CPUS * 39)
 
-#define CPU_ENTRY_AREA_BASE						\
-	((FIXADDR_TOT_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1))   \
-	 & PMD_MASK)
+/* The +1 is for the readonly IDT page: */
+#define CPU_ENTRY_AREA_BASE	\
+	((FIXADDR_TOT_START - PAGE_SIZE*(CPU_ENTRY_AREA_PAGES+1)) & PMD_MASK)
 
 #define LDT_BASE_ADDR		\
 	((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK)
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index ac3892920419..6669164abadc 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -31,6 +31,18 @@
  */
 #define SEGMENT_RPL_MASK	0x3
 
+/*
+ * When running on Xen PV, the actual privilege level of the kernel is 1,
+ * not 0. Testing the Requested Privilege Level in a segment selector to
+ * determine whether the context is user mode or kernel mode with
+ * SEGMENT_RPL_MASK is wrong because the PV kernel's privilege level
+ * matches the 0x3 mask.
+ *
+ * Testing with USER_SEGMENT_RPL_MASK is valid for both native and Xen PV
+ * kernels because privilege level 2 is never used.
+ */
+#define USER_SEGMENT_RPL_MASK	0x2
+
 /* User mode is privilege level 3: */
 #define USER_RPL		0x3