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

Pull x86 mm updates from Ingo Molnar:
 "The main changes in this cycle were:

   - Enable full ASLR randomization for 32-bit programs (Hector
     Marco-Gisbert)

   - Add initial minimal INVPCI support, to flush global mappings (Andy
     Lutomirski)

   - Add KASAN enhancements (Andrey Ryabinin)

   - Fix mmiotrace for huge pages (Karol Herbst)

   - ... misc cleanups and small enhancements"

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mm/32: Enable full randomization on i386 and X86_32
  x86/mm/kmmio: Fix mmiotrace for hugepages
  x86/mm: Avoid premature success when changing page attributes
  x86/mm/ptdump: Remove paravirt_enabled()
  x86/mm: Fix INVPCID asm constraint
  x86/dmi: Switch dmi_remap() from ioremap() [uncached] to ioremap_cache()
  x86/mm: If INVPCID is available, use it to flush global mappings
  x86/mm: Add a 'noinvpcid' boot option to turn off INVPCID
  x86/mm: Add INVPCID helpers
  x86/kasan: Write protect kasan zero shadow
  x86/kasan: Clear kasan_zero_page after TLB flush
  x86/mm/numa: Check for failures in numa_clear_kernel_node_hotplug()
  x86/mm/numa: Clean up numa_clear_kernel_node_hotplug()
  x86/mm: Make kmap_prot into a #define
  x86/mm/32: Set NX in __supported_pte_mask before enabling paging
  x86/mm: Streamline and restore probe_memory_block_size()

3 files changed, 59 insertions, 2 deletions

diff --git a/arch/x86/include/asm/dmi.h b/arch/x86/include/asm/dmi.h
index 535192f6bfad..3c69fed215c5 100644
--- a/arch/x86/include/asm/dmi.h
+++ b/arch/x86/include/asm/dmi.h
@@ -15,7 +15,7 @@ static __always_inline __init void *dmi_alloc(unsigned len)
 /* Use early IO mappings for DMI because it's initialized early */
 #define dmi_early_remap		early_ioremap
 #define dmi_early_unmap		early_iounmap
-#define dmi_remap		ioremap
+#define dmi_remap		ioremap_cache
 #define dmi_unmap		iounmap
 
 #endif /* _ASM_X86_DMI_H */
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 6d7d0e52ed5a..8554f960e21b 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -138,7 +138,7 @@ extern void reserve_top_address(unsigned long reserve);
 extern int fixmaps_set;
 
 extern pte_t *kmap_pte;
-extern pgprot_t kmap_prot;
+#define kmap_prot PAGE_KERNEL
 extern pte_t *pkmap_page_table;
 
 void __native_set_fixmap(enum fixed_addresses idx, pte_t pte);
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 0bb31cb8c73b..c24b4224d439 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -8,6 +8,54 @@
 #include <asm/cpufeature.h>
 #include <asm/special_insns.h>
 
+static inline void __invpcid(unsigned long pcid, unsigned long addr,
+			     unsigned long type)
+{
+	struct { u64 d[2]; } desc = { { pcid, addr } };
+
+	/*
+	 * The memory clobber is because the whole point is to invalidate
+	 * stale TLB entries and, especially if we're flushing global
+	 * mappings, we don't want the compiler to reorder any subsequent
+	 * memory accesses before the TLB flush.
+	 *
+	 * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and
+	 * invpcid (%rcx), %rax in long mode.
+	 */
+	asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01"
+		      : : "m" (desc), "a" (type), "c" (&desc) : "memory");
+}
+
+#define INVPCID_TYPE_INDIV_ADDR		0
+#define INVPCID_TYPE_SINGLE_CTXT	1
+#define INVPCID_TYPE_ALL_INCL_GLOBAL	2
+#define INVPCID_TYPE_ALL_NON_GLOBAL	3
+
+/* Flush all mappings for a given pcid and addr, not including globals. */
+static inline void invpcid_flush_one(unsigned long pcid,
+				     unsigned long addr)
+{
+	__invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR);
+}
+
+/* Flush all mappings for a given PCID, not including globals. */
+static inline void invpcid_flush_single_context(unsigned long pcid)
+{
+	__invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT);
+}
+
+/* Flush all mappings, including globals, for all PCIDs. */
+static inline void invpcid_flush_all(void)
+{
+	__invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL);
+}
+
+/* Flush all mappings for all PCIDs except globals. */
+static inline void invpcid_flush_all_nonglobals(void)
+{
+	__invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL);
+}
+
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else
@@ -105,6 +153,15 @@ static inline void __native_flush_tlb_global(void)
 {
 	unsigned long flags;
 
+	if (static_cpu_has(X86_FEATURE_INVPCID)) {
+		/*
+		 * Using INVPCID is considerably faster than a pair of writes
+		 * to CR4 sandwiched inside an IRQ flag save/restore.
+		 */
+		invpcid_flush_all();
+		return;
+	}
+
 	/*
 	 * Read-modify-write to CR4 - protect it from preemption and
 	 * from interrupts. (Use the raw variant because this code can