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
  ...

1 files changed, 49 insertions, 8 deletions

diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index a8d74a7..8c6c83e 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -30,6 +30,7 @@
 #include <linux/highmem.h>
 #include <linux/gfp.h>
 #include <linux/scatterlist.h>
+#include <linux/mem_encrypt.h>
 
 #include <asm/io.h>
 #include <asm/dma.h>
@@ -155,6 +156,15 @@ unsigned long swiotlb_size_or_default(void)
 	return size ? size : (IO_TLB_DEFAULT_SIZE);
 }
 
+void __weak swiotlb_set_mem_attributes(void *vaddr, unsigned long size) { }
+
+/* For swiotlb, clear memory encryption mask from dma addresses */
+static dma_addr_t swiotlb_phys_to_dma(struct device *hwdev,
+				      phys_addr_t address)
+{
+	return __sme_clr(phys_to_dma(hwdev, address));
+}
+
 /* Note that this doesn't work with highmem page */
 static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev,
 				      volatile void *address)
@@ -183,6 +193,31 @@ void swiotlb_print_info(void)
 	       bytes >> 20, vstart, vend - 1);
 }
 
+/*
+ * Early SWIOTLB allocation may be too early to allow an architecture to
+ * perform the desired operations.  This function allows the architecture to
+ * call SWIOTLB when the operations are possible.  It needs to be called
+ * before the SWIOTLB memory is used.
+ */
+void __init swiotlb_update_mem_attributes(void)
+{
+	void *vaddr;
+	unsigned long bytes;
+
+	if (no_iotlb_memory || late_alloc)
+		return;
+
+	vaddr = phys_to_virt(io_tlb_start);
+	bytes = PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT);
+	swiotlb_set_mem_attributes(vaddr, bytes);
+	memset(vaddr, 0, bytes);
+
+	vaddr = phys_to_virt(io_tlb_overflow_buffer);
+	bytes = PAGE_ALIGN(io_tlb_overflow);
+	swiotlb_set_mem_attributes(vaddr, bytes);
+	memset(vaddr, 0, bytes);
+}
+
 int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
 {
 	void *v_overflow_buffer;
@@ -320,6 +355,7 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
 	io_tlb_start = virt_to_phys(tlb);
 	io_tlb_end = io_tlb_start + bytes;
 
+	swiotlb_set_mem_attributes(tlb, bytes);
 	memset(tlb, 0, bytes);
 
 	/*
@@ -330,6 +366,8 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
 	if (!v_overflow_buffer)
 		goto cleanup2;
 
+	swiotlb_set_mem_attributes(v_overflow_buffer, io_tlb_overflow);
+	memset(v_overflow_buffer, 0, io_tlb_overflow);
 	io_tlb_overflow_buffer = virt_to_phys(v_overflow_buffer);
 
 	/*
@@ -469,6 +507,9 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
 	if (no_iotlb_memory)
 		panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
 
+	if (sme_active())
+		pr_warn_once("SME is active and system is using DMA bounce buffers\n");
+
 	mask = dma_get_seg_boundary(hwdev);
 
 	tbl_dma_addr &= mask;
@@ -581,7 +622,7 @@ map_single(struct device *hwdev, phys_addr_t phys, size_t size,
 		return SWIOTLB_MAP_ERROR;
 	}
 
-	start_dma_addr = phys_to_dma(hwdev, io_tlb_start);
+	start_dma_addr = swiotlb_phys_to_dma(hwdev, io_tlb_start);
 	return swiotlb_tbl_map_single(hwdev, start_dma_addr, phys, size,
 				      dir, attrs);
 }
@@ -702,7 +743,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 			goto err_warn;
 
 		ret = phys_to_virt(paddr);
-		dev_addr = phys_to_dma(hwdev, paddr);
+		dev_addr = swiotlb_phys_to_dma(hwdev, paddr);
 
 		/* Confirm address can be DMA'd by device */
 		if (dev_addr + size - 1 > dma_mask) {
@@ -812,10 +853,10 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
 	map = map_single(dev, phys, size, dir, attrs);
 	if (map == SWIOTLB_MAP_ERROR) {
 		swiotlb_full(dev, size, dir, 1);
-		return phys_to_dma(dev, io_tlb_overflow_buffer);
+		return swiotlb_phys_to_dma(dev, io_tlb_overflow_buffer);
 	}
 
-	dev_addr = phys_to_dma(dev, map);
+	dev_addr = swiotlb_phys_to_dma(dev, map);
 
 	/* Ensure that the address returned is DMA'ble */
 	if (dma_capable(dev, dev_addr, size))
@@ -824,7 +865,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
 	attrs |= DMA_ATTR_SKIP_CPU_SYNC;
 	swiotlb_tbl_unmap_single(dev, map, size, dir, attrs);
 
-	return phys_to_dma(dev, io_tlb_overflow_buffer);
+	return swiotlb_phys_to_dma(dev, io_tlb_overflow_buffer);
 }
 EXPORT_SYMBOL_GPL(swiotlb_map_page);
 
@@ -958,7 +999,7 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
 				sg_dma_len(sgl) = 0;
 				return 0;
 			}
-			sg->dma_address = phys_to_dma(hwdev, map);
+			sg->dma_address = swiotlb_phys_to_dma(hwdev, map);
 		} else
 			sg->dma_address = dev_addr;
 		sg_dma_len(sg) = sg->length;
@@ -1026,7 +1067,7 @@ EXPORT_SYMBOL(swiotlb_sync_sg_for_device);
 int
 swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
 {
-	return (dma_addr == phys_to_dma(hwdev, io_tlb_overflow_buffer));
+	return (dma_addr == swiotlb_phys_to_dma(hwdev, io_tlb_overflow_buffer));
 }
 EXPORT_SYMBOL(swiotlb_dma_mapping_error);
 
@@ -1039,6 +1080,6 @@ EXPORT_SYMBOL(swiotlb_dma_mapping_error);
 int
 swiotlb_dma_supported(struct device *hwdev, u64 mask)
 {
-	return phys_to_dma(hwdev, io_tlb_end - 1) <= mask;
+	return swiotlb_phys_to_dma(hwdev, io_tlb_end - 1) <= mask;
 }
 EXPORT_SYMBOL(swiotlb_dma_supported);