x86, swiotlb: Add memory encryption support

Since DMA addresses will effectively look like 48-bit addresses when the
memory encryption mask is set, SWIOTLB is needed if the DMA mask of the
device performing the DMA does not support 48-bits. SWIOTLB will be
initialized to create decrypted bounce buffers for use by these devices.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brijesh Singh <brijesh.singh@amd.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Larry Woodman <lwoodman@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matt Fleming <matt@codeblueprint.co.uk>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Toshimitsu Kani <toshi.kani@hpe.com>
Cc: kasan-dev@googlegroups.com
Cc: kvm@vger.kernel.org
Cc: linux-arch@vger.kernel.org
Cc: linux-doc@vger.kernel.org
Cc: linux-efi@vger.kernel.org
Cc: linux-mm@kvack.org
Link: http://lkml.kernel.org/r/aa2d29b78ae7d508db8881e46a3215231b9327a7.1500319216.git.thomas.lendacky@amd.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 398c79889f5c43d384b72238ce025f140debeb0b..1387dafdba2d2c24061adb014354b82174f620d4 100644 (file)
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -12,6 +12,7 @@
 #include <asm/io.h>
 #include <asm/swiotlb.h>
 #include <linux/dma-contiguous.h>
+#include <linux/mem_encrypt.h>
 
 #ifdef CONFIG_ISA
 # define ISA_DMA_BIT_MASK DMA_BIT_MASK(24)
@@ -57,12 +58,12 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
 
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
-       return paddr;
+       return __sme_set(paddr);
 }
 
 static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 {
-       return daddr;
+       return __sme_clr(daddr);
 }
 #endif /* CONFIG_X86_DMA_REMAP */
 

diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index ab1fe77c2f730f5ddd3db01d6b5f98046c7d2914..70e55f6b9adf379cdf8a70fe95747b1ddacca725 100644 (file)
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -34,6 +34,11 @@ void __init sme_early_init(void);
 void __init sme_encrypt_kernel(void);
 void __init sme_enable(void);
 
+/* Architecture __weak replacement functions */
+void __init mem_encrypt_init(void);
+
+void swiotlb_set_mem_attributes(void *vaddr, unsigned long size);
+
 #else  /* !CONFIG_AMD_MEM_ENCRYPT */
 
 #define sme_me_mask    0UL

diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 5e16d3f2959468f6d05aaa1be5eef2f8b945abb1..0accc2404b9214d1b318577668f103bc41bc8d35 100644 (file)
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -93,9 +93,12 @@ again:
        if (gfpflags_allow_blocking(flag)) {
                page = dma_alloc_from_contiguous(dev, count, get_order(size),
                                                 flag);
-               if (page && page_to_phys(page) + size > dma_mask) {
-                       dma_release_from_contiguous(dev, page, count);
-                       page = NULL;
+               if (page) {
+                       addr = phys_to_dma(dev, page_to_phys(page));
+                       if (addr + size > dma_mask) {
+                               dma_release_from_contiguous(dev, page, count);
+                               page = NULL;
+                       }
                }
        }
        /* fallback */
@@ -104,7 +107,7 @@ again:
        if (!page)
                return NULL;
 
-       addr = page_to_phys(page);
+       addr = phys_to_dma(dev, page_to_phys(page));
        if (addr + size > dma_mask) {
                __free_pages(page, get_order(size));
 

diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
index a6d404087fe3285f65de353613153abde4a698a0..4fc3cb60ea11a546b08ae8c2f3fdbb9007dee670 100644 (file)
--- a/arch/x86/kernel/pci-nommu.c
+++ b/arch/x86/kernel/pci-nommu.c
@@ -32,7 +32,7 @@ static dma_addr_t nommu_map_page(struct device *dev, struct page *page,
                                 enum dma_data_direction dir,
                                 unsigned long attrs)
 {
-       dma_addr_t bus = page_to_phys(page) + offset;
+       dma_addr_t bus = phys_to_dma(dev, page_to_phys(page)) + offset;
        WARN_ON(size == 0);
        if (!check_addr("map_single", dev, bus, size))
                return NOMMU_MAPPING_ERROR;

diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 1e23577e17cf10f87d584e4cdc38f4691db57862..677077510e308ebfabb56d8072a2afed439f23c8 100644 (file)
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -6,12 +6,14 @@
 #include <linux/swiotlb.h>
 #include <linux/bootmem.h>
 #include <linux/dma-mapping.h>
+#include <linux/mem_encrypt.h>
 
 #include <asm/iommu.h>
 #include <asm/swiotlb.h>
 #include <asm/dma.h>
 #include <asm/xen/swiotlb-xen.h>
 #include <asm/iommu_table.h>
+
 int swiotlb __read_mostly;
 
 void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
@@ -79,8 +81,8 @@ IOMMU_INIT_FINISH(pci_swiotlb_detect_override,
                  pci_swiotlb_late_init);
 
 /*
- * if 4GB or more detected (and iommu=off not set) return 1
- * and set swiotlb to 1.
+ * If 4GB or more detected (and iommu=off not set) or if SME is active
+ * then set swiotlb to 1 and return 1.
  */
 int __init pci_swiotlb_detect_4gb(void)
 {
@@ -89,6 +91,15 @@ int __init pci_swiotlb_detect_4gb(void)
        if (!no_iommu && max_possible_pfn > MAX_DMA32_PFN)
                swiotlb = 1;
 #endif
+
+       /*
+        * If SME is active then swiotlb will be set to 1 so that bounce
+        * buffers are allocated and used for devices that do not support
+        * the addressing range required for the encryption mask.
+        */
+       if (sme_active())
+               swiotlb = 1;
+
        return swiotlb;
 }
 IOMMU_INIT(pci_swiotlb_detect_4gb,

diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 0843d023da4ad83648023ab9b8f80ba6ff51900b..a7400ec8538b37162613a53d2973d1c62292b6b5 100644 (file)
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -13,11 +13,14 @@
 #include <linux/linkage.h>
 #include <linux/init.h>
 #include <linux/mm.h>
+#include <linux/dma-mapping.h>
+#include <linux/swiotlb.h>
 
 #include <asm/tlbflush.h>
 #include <asm/fixmap.h>
 #include <asm/setup.h>
 #include <asm/bootparam.h>
+#include <asm/set_memory.h>
 
 /*
  * Since SME related variables are set early in the boot process they must
@@ -177,6 +180,25 @@ void __init sme_early_init(void)
                protection_map[i] = pgprot_encrypted(protection_map[i]);
 }
 
+/* Architecture __weak replacement functions */
+void __init mem_encrypt_init(void)
+{
+       if (!sme_me_mask)
+               return;
+
+       /* Call into SWIOTLB to update the SWIOTLB DMA buffers */
+       swiotlb_update_mem_attributes();
+}
+
+void swiotlb_set_mem_attributes(void *vaddr, unsigned long size)
+{
+       WARN(PAGE_ALIGN(size) != size,
+            "size is not page-aligned (%#lx)\n", size);
+
+       /* Make the SWIOTLB buffer area decrypted */
+       set_memory_decrypted((unsigned long)vaddr, size >> PAGE_SHIFT);
+}
+
 void __init sme_encrypt_kernel(void)
 {
 }

diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 4ee479f2f355b1fa2658b1c2aabbdfc376125651..15e7160751a85a4be938f860257d05595b03105d 100644 (file)
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -35,6 +35,7 @@ int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose);
 extern unsigned long swiotlb_nr_tbl(void);
 unsigned long swiotlb_size_or_default(void);
 extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs);
+extern void __init swiotlb_update_mem_attributes(void);
 
 /*
  * Enumeration for sync targets

diff --git a/init/main.c b/init/main.c
index 052481fbe3633f64b420c5bbd6deea3be261e6a9..9789ab7fe85e14f7434be3b0298a9ebf920242e0 100644 (file)
--- a/init/main.c
+++ b/init/main.c
@@ -488,6 +488,8 @@ void __init __weak thread_stack_cache_init(void)
 }
 #endif
 
+void __init __weak mem_encrypt_init(void) { }
+
 /*
  * Set up kernel memory allocators
  */
@@ -641,6 +643,14 @@ asmlinkage __visible void __init start_kernel(void)
         */
        locking_selftest();
 
+       /*
+        * This needs to be called before any devices perform DMA
+        * operations that might use the SWIOTLB bounce buffers. It will
+        * mark the bounce buffers as decrypted so that their usage will
+        * not cause "plain-text" data to be decrypted when accessed.
+        */
+       mem_encrypt_init();
+
 #ifdef CONFIG_BLK_DEV_INITRD
        if (initrd_start && !initrd_below_start_ok &&
            page_to_pfn(virt_to_page((void *)initrd_start)) < min_low_pfn) {

diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index a8d74a733a38b54a912f5e292f0a15a2cfff4a95..04ac91acf193058442fdf76f13be26c0bdc9d6e4 100644 (file)
--- 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);
 
        /*
@@ -581,7 +619,7 @@ 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 +740,7 @@ 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 +850,10 @@ 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 +862,7 @@ 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 +996,7 @@ 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 +1064,7 @@ 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 +1077,6 @@ 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);