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

Pull x86 mm changes from Ingo Molnar:
 "PCID support, 5-level paging support, Secure Memory Encryption support

  The main changes in this cycle are support for three new, complex
  hardware features of x86 CPUs:

   - Add 5-level paging support, which is a new hardware feature on
     upcoming Intel CPUs allowing up to 128 PB of virtual address space
     and 4 PB of physical RAM space - a 512-fold increase over the old
     limits. (Supercomputers of the future forecasting hurricanes on an
     ever warming planet can certainly make good use of more RAM.)

     Many of the necessary changes went upstream in previous cycles,
     v4.14 is the first kernel that can enable 5-level paging.

     This feature is activated via CONFIG_X86_5LEVEL=y - disabled by
     default.

     (By Kirill A. Shutemov)

   - Add 'encrypted memory' support, which is a new hardware feature on
     upcoming AMD CPUs ('Secure Memory Encryption', SME) allowing system
     RAM to be encrypted and decrypted (mostly) transparently by the
     CPU, with a little help from the kernel to transition to/from
     encrypted RAM. Such RAM should be more secure against various
     attacks like RAM access via the memory bus and should make the
     radio signature of memory bus traffic harder to intercept (and
     decrypt) as well.

     This feature is activated via CONFIG_AMD_MEM_ENCRYPT=y - disabled
     by default.

     (By Tom Lendacky)

   - Enable PCID optimized TLB flushing on newer Intel CPUs: PCID is a
     hardware feature that attaches an address space tag to TLB entries
     and thus allows to skip TLB flushing in many cases, even if we
     switch mm's.

     (By Andy Lutomirski)

  All three of these features were in the works for a long time, and
  it's coincidence of the three independent development paths that they
  are all enabled in v4.14 at once"

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (65 commits)
  x86/mm: Enable RCU based page table freeing (CONFIG_HAVE_RCU_TABLE_FREE=y)
  x86/mm: Use pr_cont() in dump_pagetable()
  x86/mm: Fix SME encryption stack ptr handling
  kvm/x86: Avoid clearing the C-bit in rsvd_bits()
  x86/CPU: Align CR3 defines
  x86/mm, mm/hwpoison: Clear PRESENT bit for kernel 1:1 mappings of poison pages
  acpi, x86/mm: Remove encryption mask from ACPI page protection type
  x86/mm, kexec: Fix memory corruption with SME on successive kexecs
  x86/mm/pkeys: Fix typo in Documentation/x86/protection-keys.txt
  x86/mm/dump_pagetables: Speed up page tables dump for CONFIG_KASAN=y
  x86/mm: Implement PCID based optimization: try to preserve old TLB entries using PCID
  x86: Enable 5-level paging support via CONFIG_X86_5LEVEL=y
  x86/mm: Allow userspace have mappings above 47-bit
  x86/mm: Prepare to expose larger address space to userspace
  x86/mpx: Do not allow MPX if we have mappings above 47-bit
  x86/mm: Rename tasksize_32bit/64bit to task_size_32bit/64bit()
  x86/xen: Redefine XEN_ELFNOTE_INIT_P2M using PUD_SIZE * PTRS_PER_PUD
  x86/mm/dump_pagetables: Fix printout of p4d level
  x86/mm/dump_pagetables: Generalize address normalization
  x86/boot: Fix memremap() related build failure
  ...

2 files changed, 27 insertions, 5 deletions

diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 1ae7c41c33c1..20fef1a38602 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -301,7 +301,7 @@ static struct page *kimage_alloc_pages(gfp_t gfp_mask, unsigned int order)
 {
 	struct page *pages;
 
-	pages = alloc_pages(gfp_mask, order);
+	pages = alloc_pages(gfp_mask & ~__GFP_ZERO, order);
 	if (pages) {
 		unsigned int count, i;
 
@@ -310,6 +310,13 @@ static struct page *kimage_alloc_pages(gfp_t gfp_mask, unsigned int order)
 		count = 1 << order;
 		for (i = 0; i < count; i++)
 			SetPageReserved(pages + i);
+
+		arch_kexec_post_alloc_pages(page_address(pages), count,
+					    gfp_mask);
+
+		if (gfp_mask & __GFP_ZERO)
+			for (i = 0; i < count; i++)
+				clear_highpage(pages + i);
 	}
 
 	return pages;
@@ -321,6 +328,9 @@ static void kimage_free_pages(struct page *page)
 
 	order = page_private(page);
 	count = 1 << order;
+
+	arch_kexec_pre_free_pages(page_address(page), count);
+
 	for (i = 0; i < count; i++)
 		ClearPageReserved(page + i);
 	__free_pages(page, order);
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 124bed776532..9afdc434fb49 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -34,13 +34,24 @@ static void *arch_memremap_wb(resource_size_t offset, unsigned long size)
 }
 #endif
 
-static void *try_ram_remap(resource_size_t offset, size_t size)
+#ifndef arch_memremap_can_ram_remap
+static bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size,
+					unsigned long flags)
+{
+	return true;
+}
+#endif
+
+static void *try_ram_remap(resource_size_t offset, size_t size,
+			   unsigned long flags)
 {
 	unsigned long pfn = PHYS_PFN(offset);
 
 	/* In the simple case just return the existing linear address */
-	if (pfn_valid(pfn) && !PageHighMem(pfn_to_page(pfn)))
+	if (pfn_valid(pfn) && !PageHighMem(pfn_to_page(pfn)) &&
+	    arch_memremap_can_ram_remap(offset, size, flags))
 		return __va(offset);
+
 	return NULL; /* fallback to arch_memremap_wb */
 }
 
@@ -48,7 +59,8 @@ static void *try_ram_remap(resource_size_t offset, size_t size)
  * memremap() - remap an iomem_resource as cacheable memory
  * @offset: iomem resource start address
  * @size: size of remap
- * @flags: any of MEMREMAP_WB, MEMREMAP_WT and MEMREMAP_WC
+ * @flags: any of MEMREMAP_WB, MEMREMAP_WT, MEMREMAP_WC,
+ *		  MEMREMAP_ENC, MEMREMAP_DEC
  *
  * memremap() is "ioremap" for cases where it is known that the resource
  * being mapped does not have i/o side effects and the __iomem
@@ -95,7 +107,7 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags)
 		 * the requested range is potentially in System RAM.
 		 */
 		if (is_ram == REGION_INTERSECTS)
-			addr = try_ram_remap(offset, size);
+			addr = try_ram_remap(offset, size, flags);
 		if (!addr)
 			addr = arch_memremap_wb(offset, size);
 	}