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
  ...

4 files changed, 55 insertions, 21 deletions

diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 354cbd6392cd..4ad7e5e31943 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -575,7 +575,7 @@ static void dump_dte_entry(u16 devid)
 
 static void dump_command(unsigned long phys_addr)
 {
-	struct iommu_cmd *cmd = phys_to_virt(phys_addr);
+	struct iommu_cmd *cmd = iommu_phys_to_virt(phys_addr);
 	int i;
 
 	for (i = 0; i < 4; ++i)
@@ -919,11 +919,13 @@ static void copy_cmd_to_buffer(struct amd_iommu *iommu,
 
 static void build_completion_wait(struct iommu_cmd *cmd, u64 address)
 {
+	u64 paddr = iommu_virt_to_phys((void *)address);
+
 	WARN_ON(address & 0x7ULL);
 
 	memset(cmd, 0, sizeof(*cmd));
-	cmd->data[0] = lower_32_bits(__pa(address)) | CMD_COMPL_WAIT_STORE_MASK;
-	cmd->data[1] = upper_32_bits(__pa(address));
+	cmd->data[0] = lower_32_bits(paddr) | CMD_COMPL_WAIT_STORE_MASK;
+	cmd->data[1] = upper_32_bits(paddr);
 	cmd->data[2] = 1;
 	CMD_SET_TYPE(cmd, CMD_COMPL_WAIT);
 }
@@ -1383,7 +1385,7 @@ static bool increase_address_space(struct protection_domain *domain,
 		return false;
 
 	*pte             = PM_LEVEL_PDE(domain->mode,
-					virt_to_phys(domain->pt_root));
+					iommu_virt_to_phys(domain->pt_root));
 	domain->pt_root  = pte;
 	domain->mode    += 1;
 	domain->updated  = true;
@@ -1420,7 +1422,7 @@ static u64 *alloc_pte(struct protection_domain *domain,
 			if (!page)
 				return NULL;
 
-			__npte = PM_LEVEL_PDE(level, virt_to_phys(page));
+			__npte = PM_LEVEL_PDE(level, iommu_virt_to_phys(page));
 
 			/* pte could have been changed somewhere. */
 			if (cmpxchg64(pte, __pte, __npte) != __pte) {
@@ -1536,10 +1538,10 @@ static int iommu_map_page(struct protection_domain *dom,
 			return -EBUSY;
 
 	if (count > 1) {
-		__pte = PAGE_SIZE_PTE(phys_addr, page_size);
+		__pte = PAGE_SIZE_PTE(__sme_set(phys_addr), page_size);
 		__pte |= PM_LEVEL_ENC(7) | IOMMU_PTE_P | IOMMU_PTE_FC;
 	} else
-		__pte = phys_addr | IOMMU_PTE_P | IOMMU_PTE_FC;
+		__pte = __sme_set(phys_addr) | IOMMU_PTE_P | IOMMU_PTE_FC;
 
 	if (prot & IOMMU_PROT_IR)
 		__pte |= IOMMU_PTE_IR;
@@ -1755,7 +1757,7 @@ static void free_gcr3_tbl_level1(u64 *tbl)
 		if (!(tbl[i] & GCR3_VALID))
 			continue;
 
-		ptr = __va(tbl[i] & PAGE_MASK);
+		ptr = iommu_phys_to_virt(tbl[i] & PAGE_MASK);
 
 		free_page((unsigned long)ptr);
 	}
@@ -1770,7 +1772,7 @@ static void free_gcr3_tbl_level2(u64 *tbl)
 		if (!(tbl[i] & GCR3_VALID))
 			continue;
 
-		ptr = __va(tbl[i] & PAGE_MASK);
+		ptr = iommu_phys_to_virt(tbl[i] & PAGE_MASK);
 
 		free_gcr3_tbl_level1(ptr);
 	}
@@ -2049,7 +2051,7 @@ static void set_dte_entry(u16 devid, struct protection_domain *domain, bool ats)
 	u64 flags = 0;
 
 	if (domain->mode != PAGE_MODE_NONE)
-		pte_root = virt_to_phys(domain->pt_root);
+		pte_root = iommu_virt_to_phys(domain->pt_root);
 
 	pte_root |= (domain->mode & DEV_ENTRY_MODE_MASK)
 		    << DEV_ENTRY_MODE_SHIFT;
@@ -2061,7 +2063,7 @@ static void set_dte_entry(u16 devid, struct protection_domain *domain, bool ats)
 		flags |= DTE_FLAG_IOTLB;
 
 	if (domain->flags & PD_IOMMUV2_MASK) {
-		u64 gcr3 = __pa(domain->gcr3_tbl);
+		u64 gcr3 = iommu_virt_to_phys(domain->gcr3_tbl);
 		u64 glx  = domain->glx;
 		u64 tmp;
 
@@ -3606,10 +3608,10 @@ static u64 *__get_gcr3_pte(u64 *root, int level, int pasid, bool alloc)
 			if (root == NULL)
 				return NULL;
 
-			*pte = __pa(root) | GCR3_VALID;
+			*pte = iommu_virt_to_phys(root) | GCR3_VALID;
 		}
 
-		root = __va(*pte & PAGE_MASK);
+		root = iommu_phys_to_virt(*pte & PAGE_MASK);
 
 		level -= 1;
 	}
@@ -3788,7 +3790,7 @@ static void set_dte_irq_entry(u16 devid, struct irq_remap_table *table)
 
 	dte	= amd_iommu_dev_table[devid].data[2];
 	dte	&= ~DTE_IRQ_PHYS_ADDR_MASK;
-	dte	|= virt_to_phys(table->table);
+	dte	|= iommu_virt_to_phys(table->table);
 	dte	|= DTE_IRQ_REMAP_INTCTL;
 	dte	|= DTE_IRQ_TABLE_LEN;
 	dte	|= DTE_IRQ_REMAP_ENABLE;
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 372303700566..2292a6cece76 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -30,6 +30,7 @@
 #include <linux/iommu.h>
 #include <linux/kmemleak.h>
 #include <linux/crash_dump.h>
+#include <linux/mem_encrypt.h>
 #include <asm/pci-direct.h>
 #include <asm/iommu.h>
 #include <asm/gart.h>
@@ -348,7 +349,7 @@ static void iommu_set_device_table(struct amd_iommu *iommu)
 
 	BUG_ON(iommu->mmio_base == NULL);
 
-	entry = virt_to_phys(amd_iommu_dev_table);
+	entry = iommu_virt_to_phys(amd_iommu_dev_table);
 	entry |= (dev_table_size >> 12) - 1;
 	memcpy_toio(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET,
 			&entry, sizeof(entry));
@@ -606,7 +607,7 @@ static void iommu_enable_command_buffer(struct amd_iommu *iommu)
 
 	BUG_ON(iommu->cmd_buf == NULL);
 
-	entry = (u64)virt_to_phys(iommu->cmd_buf);
+	entry = iommu_virt_to_phys(iommu->cmd_buf);
 	entry |= MMIO_CMD_SIZE_512;
 
 	memcpy_toio(iommu->mmio_base + MMIO_CMD_BUF_OFFSET,
@@ -635,7 +636,7 @@ static void iommu_enable_event_buffer(struct amd_iommu *iommu)
 
 	BUG_ON(iommu->evt_buf == NULL);
 
-	entry = (u64)virt_to_phys(iommu->evt_buf) | EVT_LEN_MASK;
+	entry = iommu_virt_to_phys(iommu->evt_buf) | EVT_LEN_MASK;
 
 	memcpy_toio(iommu->mmio_base + MMIO_EVT_BUF_OFFSET,
 		    &entry, sizeof(entry));
@@ -668,7 +669,7 @@ static void iommu_enable_ppr_log(struct amd_iommu *iommu)
 	if (iommu->ppr_log == NULL)
 		return;
 
-	entry = (u64)virt_to_phys(iommu->ppr_log) | PPR_LOG_SIZE_512;
+	entry = iommu_virt_to_phys(iommu->ppr_log) | PPR_LOG_SIZE_512;
 
 	memcpy_toio(iommu->mmio_base + MMIO_PPR_LOG_OFFSET,
 		    &entry, sizeof(entry));
@@ -748,10 +749,10 @@ static int iommu_init_ga_log(struct amd_iommu *iommu)
 	if (!iommu->ga_log_tail)
 		goto err_out;
 
-	entry = (u64)virt_to_phys(iommu->ga_log) | GA_LOG_SIZE_512;
+	entry = iommu_virt_to_phys(iommu->ga_log) | GA_LOG_SIZE_512;
 	memcpy_toio(iommu->mmio_base + MMIO_GA_LOG_BASE_OFFSET,
 		    &entry, sizeof(entry));
-	entry = ((u64)virt_to_phys(iommu->ga_log) & 0xFFFFFFFFFFFFFULL) & ~7ULL;
+	entry = (iommu_virt_to_phys(iommu->ga_log) & 0xFFFFFFFFFFFFFULL) & ~7ULL;
 	memcpy_toio(iommu->mmio_base + MMIO_GA_LOG_TAIL_OFFSET,
 		    &entry, sizeof(entry));
 	writel(0x00, iommu->mmio_base + MMIO_GA_HEAD_OFFSET);
@@ -2564,6 +2565,24 @@ static int __init amd_iommu_init(void)
 	return ret;
 }
 
+static bool amd_iommu_sme_check(void)
+{
+	if (!sme_active() || (boot_cpu_data.x86 != 0x17))
+		return true;
+
+	/* For Fam17h, a specific level of support is required */
+	if (boot_cpu_data.microcode >= 0x08001205)
+		return true;
+
+	if ((boot_cpu_data.microcode >= 0x08001126) &&
+	    (boot_cpu_data.microcode <= 0x080011ff))
+		return true;
+
+	pr_notice("AMD-Vi: IOMMU not currently supported when SME is active\n");
+
+	return false;
+}
+
 /****************************************************************************
  *
  * Early detect code. This code runs at IOMMU detection time in the DMA
@@ -2578,6 +2597,9 @@ int __init amd_iommu_detect(void)
 	if (no_iommu || (iommu_detected && !gart_iommu_aperture))
 		return -ENODEV;
 
+	if (!amd_iommu_sme_check())
+		return -ENODEV;
+
 	ret = iommu_go_to_state(IOMMU_IVRS_DETECTED);
 	if (ret)
 		return ret;
diff --git a/drivers/iommu/amd_iommu_proto.h b/drivers/iommu/amd_iommu_proto.h
index 466260f8a1df..3f12fb2338ea 100644
--- a/drivers/iommu/amd_iommu_proto.h
+++ b/drivers/iommu/amd_iommu_proto.h
@@ -87,4 +87,14 @@ static inline bool iommu_feature(struct amd_iommu *iommu, u64 f)
 	return !!(iommu->features & f);
 }
 
+static inline u64 iommu_virt_to_phys(void *vaddr)
+{
+	return (u64)__sme_set(virt_to_phys(vaddr));
+}
+
+static inline void *iommu_phys_to_virt(unsigned long paddr)
+{
+	return phys_to_virt(__sme_clr(paddr));
+}
+
 #endif /* _ASM_X86_AMD_IOMMU_PROTO_H  */
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index d6b873b57054..8e3a85759242 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -344,7 +344,7 @@
 
 #define IOMMU_PAGE_MASK (((1ULL << 52) - 1) & ~0xfffULL)
 #define IOMMU_PTE_PRESENT(pte) ((pte) & IOMMU_PTE_P)
-#define IOMMU_PTE_PAGE(pte) (phys_to_virt((pte) & IOMMU_PAGE_MASK))
+#define IOMMU_PTE_PAGE(pte) (iommu_phys_to_virt((pte) & IOMMU_PAGE_MASK))
 #define IOMMU_PTE_MODE(pte) (((pte) >> 9) & 0x07)
 
 #define IOMMU_PROT_MASK 0x03