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
  ...

21 files changed, 459 insertions, 124 deletions

diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 7491e73d9253..97bb2caf3428 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -115,7 +115,7 @@ static u32 isa_irq_to_gsi[NR_IRQS_LEGACY] __read_mostly = {
 #define	ACPI_INVALID_GSI		INT_MIN
 
 /*
- * This is just a simple wrapper around early_ioremap(),
+ * This is just a simple wrapper around early_memremap(),
  * with sanity checks for phys == 0 and size == 0.
  */
 char *__init __acpi_map_table(unsigned long phys, unsigned long size)
@@ -124,7 +124,7 @@ char *__init __acpi_map_table(unsigned long phys, unsigned long size)
 	if (!phys || !size)
 		return NULL;
 
-	return early_ioremap(phys, size);
+	return early_memremap(phys, size);
 }
 
 void __init __acpi_unmap_table(char *map, unsigned long size)
@@ -132,7 +132,7 @@ void __init __acpi_unmap_table(char *map, unsigned long size)
 	if (!map || !size)
 		return;
 
-	early_iounmap(map, size);
+	early_memunmap(map, size);
 }
 
 #ifdef CONFIG_X86_LOCAL_APIC
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index e44338dd62dd..9862e2cd6d93 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -558,8 +558,12 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 
 static void early_init_amd(struct cpuinfo_x86 *c)
 {
+	u32 dummy;
+
 	early_init_amd_mc(c);
 
+	rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy);
+
 	/*
 	 * c->x86_power is 8000_0007 edx. Bit 8 is TSC runs at constant rate
 	 * with P/T states and does not stop in deep C-states
@@ -622,6 +626,27 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 	 */
 	if (cpu_has_amd_erratum(c, amd_erratum_400))
 		set_cpu_bug(c, X86_BUG_AMD_E400);
+
+	/*
+	 * BIOS support is required for SME. If BIOS has enabled SME then
+	 * adjust x86_phys_bits by the SME physical address space reduction
+	 * value. If BIOS has not enabled SME then don't advertise the
+	 * feature (set in scattered.c). Also, since the SME support requires
+	 * long mode, don't advertise the feature under CONFIG_X86_32.
+	 */
+	if (cpu_has(c, X86_FEATURE_SME)) {
+		u64 msr;
+
+		/* Check if SME is enabled */
+		rdmsrl(MSR_K8_SYSCFG, msr);
+		if (msr & MSR_K8_SYSCFG_MEM_ENCRYPT) {
+			c->x86_phys_bits -= (cpuid_ebx(0x8000001f) >> 6) & 0x3f;
+			if (IS_ENABLED(CONFIG_X86_32))
+				clear_cpu_cap(c, X86_FEATURE_SME);
+		} else {
+			clear_cpu_cap(c, X86_FEATURE_SME);
+		}
+	}
 }
 
 static void init_amd_k8(struct cpuinfo_x86 *c)
@@ -740,8 +765,6 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
 
 static void init_amd(struct cpuinfo_x86 *c)
 {
-	u32 dummy;
-
 	early_init_amd(c);
 
 	/*
@@ -803,8 +826,6 @@ static void init_amd(struct cpuinfo_x86 *c)
 	if (c->x86 > 0x11)
 		set_cpu_cap(c, X86_FEATURE_ARAT);
 
-	rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy);
-
 	/* 3DNow or LM implies PREFETCHW */
 	if (!cpu_has(c, X86_FEATURE_3DNOWPREFETCH))
 		if (cpu_has(c, X86_FEATURE_3DNOW) || cpu_has(c, X86_FEATURE_LM))
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 0af86d9242da..db684880d74a 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -21,6 +21,14 @@
 
 void __init check_bugs(void)
 {
+#ifdef CONFIG_X86_32
+	/*
+	 * Regardless of whether PCID is enumerated, the SDM says
+	 * that it can't be enabled in 32-bit mode.
+	 */
+	setup_clear_cpu_cap(X86_FEATURE_PCID);
+#endif
+
 	identify_boot_cpu();
 
 	if (!IS_ENABLED(CONFIG_SMP)) {
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c8b39870f33e..b95cd94ca97b 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -168,6 +168,24 @@ static int __init x86_mpx_setup(char *s)
 }
 __setup("nompx", x86_mpx_setup);
 
+#ifdef CONFIG_X86_64
+static int __init x86_pcid_setup(char *s)
+{
+	/* require an exact match without trailing characters */
+	if (strlen(s))
+		return 0;
+
+	/* do not emit a message if the feature is not present */
+	if (!boot_cpu_has(X86_FEATURE_PCID))
+		return 1;
+
+	setup_clear_cpu_cap(X86_FEATURE_PCID);
+	pr_info("nopcid: PCID feature disabled\n");
+	return 1;
+}
+__setup("nopcid", x86_pcid_setup);
+#endif
+
 static int __init x86_noinvpcid_setup(char *s)
 {
 	/* noinvpcid doesn't accept parameters */
@@ -311,6 +329,25 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c)
 	}
 }
 
+static void setup_pcid(struct cpuinfo_x86 *c)
+{
+	if (cpu_has(c, X86_FEATURE_PCID)) {
+		if (cpu_has(c, X86_FEATURE_PGE)) {
+			cr4_set_bits(X86_CR4_PCIDE);
+		} else {
+			/*
+			 * flush_tlb_all(), as currently implemented, won't
+			 * work if PCID is on but PGE is not.  Since that
+			 * combination doesn't exist on real hardware, there's
+			 * no reason to try to fully support it, but it's
+			 * polite to avoid corrupting data if we're on
+			 * an improperly configured VM.
+			 */
+			clear_cpu_cap(c, X86_FEATURE_PCID);
+		}
+	}
+}
+
 /*
  * Protection Keys are not available in 32-bit mode.
  */
@@ -1125,6 +1162,9 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 	setup_smep(c);
 	setup_smap(c);
 
+	/* Set up PCID */
+	setup_pcid(c);
+
 	/*
 	 * The vendor-specific functions might have changed features.
 	 * Now we do "generic changes."
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 6dde0497efc7..3b413065c613 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -51,6 +51,7 @@
 #include <asm/mce.h>
 #include <asm/msr.h>
 #include <asm/reboot.h>
+#include <asm/set_memory.h>
 
 #include "mce-internal.h"
 
@@ -1051,6 +1052,48 @@ static int do_memory_failure(struct mce *m)
 	return ret;
 }
 
+#if defined(arch_unmap_kpfn) && defined(CONFIG_MEMORY_FAILURE)
+
+void arch_unmap_kpfn(unsigned long pfn)
+{
+	unsigned long decoy_addr;
+
+	/*
+	 * Unmap this page from the kernel 1:1 mappings to make sure
+	 * we don't log more errors because of speculative access to
+	 * the page.
+	 * We would like to just call:
+	 *	set_memory_np((unsigned long)pfn_to_kaddr(pfn), 1);
+	 * but doing that would radically increase the odds of a
+	 * speculative access to the posion page because we'd have
+	 * the virtual address of the kernel 1:1 mapping sitting
+	 * around in registers.
+	 * Instead we get tricky.  We create a non-canonical address
+	 * that looks just like the one we want, but has bit 63 flipped.
+	 * This relies on set_memory_np() not checking whether we passed
+	 * a legal address.
+	 */
+
+/*
+ * Build time check to see if we have a spare virtual bit. Don't want
+ * to leave this until run time because most developers don't have a
+ * system that can exercise this code path. This will only become a
+ * problem if/when we move beyond 5-level page tables.
+ *
+ * Hard code "9" here because cpp doesn't grok ilog2(PTRS_PER_PGD)
+ */
+#if PGDIR_SHIFT + 9 < 63
+	decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63));
+#else
+#error "no unused virtual bit available"
+#endif
+
+	if (set_memory_np(decoy_addr, 1))
+		pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn);
+
+}
+#endif
+
 /*
  * The actual machine check handler. This only handles real
  * exceptions when something got corrupted coming in through int 18.
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 23c23508c012..05459ad3db46 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -31,6 +31,7 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_HW_PSTATE,	CPUID_EDX,  7, 0x80000007, 0 },
 	{ X86_FEATURE_CPB,		CPUID_EDX,  9, 0x80000007, 0 },
 	{ X86_FEATURE_PROC_FEEDBACK,    CPUID_EDX, 11, 0x80000007, 0 },
+	{ X86_FEATURE_SME,		CPUID_EAX,  0, 0x8000001f, 0 },
 	{ 0, 0, 0, 0, 0 }
 };
 
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 532da61d605c..71c11ad5643e 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -96,7 +96,8 @@ EXPORT_SYMBOL_GPL(e820__mapped_any);
  * Note: this function only works correctly once the E820 table is sorted and
  * not-overlapping (at least for the range specified), which is the case normally.
  */
-bool __init e820__mapped_all(u64 start, u64 end, enum e820_type type)
+static struct e820_entry *__e820__mapped_all(u64 start, u64 end,
+					     enum e820_type type)
 {
 	int i;
 
@@ -122,9 +123,28 @@ bool __init e820__mapped_all(u64 start, u64 end, enum e820_type type)
 		 * coverage of the desired range exists:
 		 */
 		if (start >= end)
-			return 1;
+			return entry;
 	}
-	return 0;
+
+	return NULL;
+}
+
+/*
+ * This function checks if the entire range <start,end> is mapped with type.
+ */
+bool __init e820__mapped_all(u64 start, u64 end, enum e820_type type)
+{
+	return __e820__mapped_all(start, end, type);
+}
+
+/*
+ * This function returns the type associated with the range <start,end>.
+ */
+int e820__get_entry_type(u64 start, u64 end)
+{
+	struct e820_entry *entry = __e820__mapped_all(start, end, 0);
+
+	return entry ? entry->type : -EINVAL;
 }
 
 /*
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
index 6b91e2eb8d3f..9c4e7ba6870c 100644
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -195,7 +195,7 @@ void init_espfix_ap(int cpu)
 
 	pte_p = pte_offset_kernel(&pmd, addr);
 	stack_page = page_address(alloc_pages_node(node, GFP_KERNEL, 0));
-	pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask));
+	pte = __pte(__pa(stack_page) | ((__PAGE_KERNEL_RO | _PAGE_ENC) & ptemask));
 	for (n = 0; n < ESPFIX_PTE_CLONES; n++)
 		set_pte(&pte_p[n*PTE_STRIDE], pte);
 
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 9ba79543d9ee..6a193b93fd95 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -14,6 +14,7 @@
 #include <linux/start_kernel.h>
 #include <linux/io.h>
 #include <linux/memblock.h>
+#include <linux/mem_encrypt.h>
 
 #include <asm/processor.h>
 #include <asm/proto.h>
@@ -33,7 +34,6 @@
 /*
  * Manage page tables very early on.
  */
-extern pgd_t early_top_pgt[PTRS_PER_PGD];
 extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD];
 static unsigned int __initdata next_early_pgt;
 pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX);
@@ -45,9 +45,11 @@ static void __head *fixup_pointer(void *ptr, unsigned long physaddr)
 	return ptr - (void *)_text + (void *)physaddr;
 }
 
-void __head __startup_64(unsigned long physaddr)
+unsigned long __head __startup_64(unsigned long physaddr,
+				  struct boot_params *bp)
 {
 	unsigned long load_delta, *p;
+	unsigned long pgtable_flags;
 	pgdval_t *pgd;
 	p4dval_t *p4d;
 	pudval_t *pud;
@@ -69,6 +71,12 @@ void __head __startup_64(unsigned long physaddr)
 	if (load_delta & ~PMD_PAGE_MASK)
 		for (;;);
 
+	/* Activate Secure Memory Encryption (SME) if supported and enabled */
+	sme_enable(bp);
+
+	/* Include the SME encryption mask in the fixup value */
+	load_delta += sme_get_me_mask();
+
 	/* Fixup the physical addresses in the page table */
 
 	pgd = fixup_pointer(&early_top_pgt, physaddr);
@@ -92,31 +100,35 @@ void __head __startup_64(unsigned long physaddr)
 	 * creates a bunch of nonsense entries but that is fine --
 	 * it avoids problems around wraparound.
 	 */
+
 	next_pgt_ptr = fixup_pointer(&next_early_pgt, physaddr);
 	pud = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr);
 	pmd = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr);
 
+	pgtable_flags = _KERNPG_TABLE_NOENC + sme_get_me_mask();
+
 	if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
 		p4d = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr);
 
 		i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD;
-		pgd[i + 0] = (pgdval_t)p4d + _KERNPG_TABLE;
-		pgd[i + 1] = (pgdval_t)p4d + _KERNPG_TABLE;
+		pgd[i + 0] = (pgdval_t)p4d + pgtable_flags;
+		pgd[i + 1] = (pgdval_t)p4d + pgtable_flags;
 
 		i = (physaddr >> P4D_SHIFT) % PTRS_PER_P4D;
-		p4d[i + 0] = (pgdval_t)pud + _KERNPG_TABLE;
-		p4d[i + 1] = (pgdval_t)pud + _KERNPG_TABLE;
+		p4d[i + 0] = (pgdval_t)pud + pgtable_flags;
+		p4d[i + 1] = (pgdval_t)pud + pgtable_flags;
 	} else {
 		i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD;
-		pgd[i + 0] = (pgdval_t)pud + _KERNPG_TABLE;
-		pgd[i + 1] = (pgdval_t)pud + _KERNPG_TABLE;
+		pgd[i + 0] = (pgdval_t)pud + pgtable_flags;
+		pgd[i + 1] = (pgdval_t)pud + pgtable_flags;
 	}
 
 	i = (physaddr >> PUD_SHIFT) % PTRS_PER_PUD;
-	pud[i + 0] = (pudval_t)pmd + _KERNPG_TABLE;
-	pud[i + 1] = (pudval_t)pmd + _KERNPG_TABLE;
+	pud[i + 0] = (pudval_t)pmd + pgtable_flags;
+	pud[i + 1] = (pudval_t)pmd + pgtable_flags;
 
 	pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL;
+	pmd_entry += sme_get_me_mask();
 	pmd_entry +=  physaddr;
 
 	for (i = 0; i < DIV_ROUND_UP(_end - _text, PMD_SIZE); i++) {
@@ -137,9 +149,30 @@ void __head __startup_64(unsigned long physaddr)
 			pmd[i] += load_delta;
 	}
 
-	/* Fixup phys_base */
+	/*
+	 * Fixup phys_base - remove the memory encryption mask to obtain
+	 * the true physical address.
+	 */
 	p = fixup_pointer(&phys_base, physaddr);
-	*p += load_delta;
+	*p += load_delta - sme_get_me_mask();
+
+	/* Encrypt the kernel (if SME is active) */
+	sme_encrypt_kernel();
+
+	/*
+	 * Return the SME encryption mask (if SME is active) to be used as a
+	 * modifier for the initial pgdir entry programmed into CR3.
+	 */
+	return sme_get_me_mask();
+}
+
+unsigned long __startup_secondary_64(void)
+{
+	/*
+	 * Return the SME encryption mask (if SME is active) to be used as a
+	 * modifier for the initial pgdir entry programmed into CR3.
+	 */
+	return sme_get_me_mask();
 }
 
 /* Wipe all early page tables except for the kernel symbol map */
@@ -147,17 +180,17 @@ static void __init reset_early_page_tables(void)
 {
 	memset(early_top_pgt, 0, sizeof(pgd_t)*(PTRS_PER_PGD-1));
 	next_early_pgt = 0;
-	write_cr3(__pa_nodebug(early_top_pgt));
+	write_cr3(__sme_pa_nodebug(early_top_pgt));
 }
 
 /* Create a new PMD entry */
-int __init early_make_pgtable(unsigned long address)
+int __init __early_make_pgtable(unsigned long address, pmdval_t pmd)
 {
 	unsigned long physaddr = address - __PAGE_OFFSET;
 	pgdval_t pgd, *pgd_p;
 	p4dval_t p4d, *p4d_p;
 	pudval_t pud, *pud_p;
-	pmdval_t pmd, *pmd_p;
+	pmdval_t *pmd_p;
 
 	/* Invalid address or early pgt is done ?  */
 	if (physaddr >= MAXMEM || read_cr3_pa() != __pa_nodebug(early_top_pgt))
@@ -216,12 +249,21 @@ again:
 		memset(pmd_p, 0, sizeof(*pmd_p) * PTRS_PER_PMD);
 		*pud_p = (pudval_t)pmd_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE;
 	}
-	pmd = (physaddr & PMD_MASK) + early_pmd_flags;
 	pmd_p[pmd_index(address)] = pmd;
 
 	return 0;
 }
 
+int __init early_make_pgtable(unsigned long address)
+{
+	unsigned long physaddr = address - __PAGE_OFFSET;
+	pmdval_t pmd;
+
+	pmd = (physaddr & PMD_MASK) + early_pmd_flags;
+
+	return __early_make_pgtable(address, pmd);
+}
+
 /* Don't add a printk in there. printk relies on the PDA which is not initialized 
    yet. */
 static void __init clear_bss(void)
@@ -244,6 +286,12 @@ static void __init copy_bootdata(char *real_mode_data)
 	char * command_line;
 	unsigned long cmd_line_ptr;
 
+	/*
+	 * If SME is active, this will create decrypted mappings of the
+	 * boot data in advance of the copy operations.
+	 */
+	sme_map_bootdata(real_mode_data);
+
 	memcpy(&boot_params, real_mode_data, sizeof boot_params);
 	sanitize_boot_params(&boot_params);
 	cmd_line_ptr = get_cmd_line_ptr();
@@ -251,6 +299,14 @@ static void __init copy_bootdata(char *real_mode_data)
 		command_line = __va(cmd_line_ptr);
 		memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE);
 	}
+
+	/*
+	 * The old boot data is no longer needed and won't be reserved,
+	 * freeing up that memory for use by the system. If SME is active,
+	 * we need to remove the mappings that were created so that the
+	 * memory doesn't remain mapped as decrypted.
+	 */
+	sme_unmap_bootdata(real_mode_data);
 }
 
 asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
@@ -280,6 +336,13 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
 
 	clear_page(init_top_pgt);
 
+	/*
+	 * SME support may update early_pmd_flags to include the memory
+	 * encryption mask, so it needs to be called before anything
+	 * that may generate a page fault.
+	 */
+	sme_early_init();
+
 	kasan_early_init();
 
 	for (i = 0; i < NUM_EXCEPTION_VECTORS; i++)
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 6225550883df..513cbb012ecc 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -73,12 +73,19 @@ startup_64:
 	/* Sanitize CPU configuration */
 	call verify_cpu
 
+	/*
+	 * Perform pagetable fixups. Additionally, if SME is active, encrypt
+	 * the kernel and retrieve the modifier (SME encryption mask if SME
+	 * is active) to be added to the initial pgdir entry that will be
+	 * programmed into CR3.
+	 */
 	leaq	_text(%rip), %rdi
 	pushq	%rsi
 	call	__startup_64
 	popq	%rsi
 
-	movq	$(early_top_pgt - __START_KERNEL_map), %rax
+	/* Form the CR3 value being sure to include the CR3 modifier */
+	addq	$(early_top_pgt - __START_KERNEL_map), %rax
 	jmp 1f
 ENTRY(secondary_startup_64)
 	/*
@@ -98,7 +105,16 @@ ENTRY(secondary_startup_64)
 	/* Sanitize CPU configuration */
 	call verify_cpu
 
-	movq	$(init_top_pgt - __START_KERNEL_map), %rax
+	/*
+	 * Retrieve the modifier (SME encryption mask if SME is active) to be
+	 * added to the initial pgdir entry that will be programmed into CR3.
+	 */
+	pushq	%rsi
+	call	__startup_secondary_64
+	popq	%rsi
+
+	/* Form the CR3 value being sure to include the CR3 modifier */
+	addq	$(init_top_pgt - __START_KERNEL_map), %rax
 1:
 
 	/* Enable PAE mode, PGE and LA57 */
@@ -335,9 +351,9 @@ GLOBAL(name)
 NEXT_PAGE(early_top_pgt)
 	.fill	511,8,0
 #ifdef CONFIG_X86_5LEVEL
-	.quad	level4_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE
+	.quad	level4_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
 #else
-	.quad	level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE
+	.quad	level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
 #endif
 
 NEXT_PAGE(early_dynamic_pgts)
@@ -350,15 +366,15 @@ NEXT_PAGE(init_top_pgt)
 	.fill	512,8,0
 #else
 NEXT_PAGE(init_top_pgt)
-	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
+	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
 	.org    init_top_pgt + PGD_PAGE_OFFSET*8, 0
-	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
+	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
 	.org    init_top_pgt + PGD_START_KERNEL*8, 0
 	/* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
-	.quad   level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE
+	.quad   level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
 
 NEXT_PAGE(level3_ident_pgt)
-	.quad	level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
+	.quad	level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
 	.fill	511, 8, 0
 NEXT_PAGE(level2_ident_pgt)
 	/* Since I easily can, map the first 1G.
@@ -370,14 +386,14 @@ NEXT_PAGE(level2_ident_pgt)
 #ifdef CONFIG_X86_5LEVEL
 NEXT_PAGE(level4_kernel_pgt)
 	.fill	511,8,0
-	.quad	level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE
+	.quad	level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
 #endif
 
 NEXT_PAGE(level3_kernel_pgt)
 	.fill	L3_START_KERNEL,8,0
 	/* (2^48-(2*1024*1024*1024)-((2^39)*511))/(2^30) = 510 */
-	.quad	level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE
-	.quad	level2_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE
+	.quad	level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
+	.quad	level2_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
 
 NEXT_PAGE(level2_kernel_pgt)
 	/*
@@ -395,7 +411,7 @@ NEXT_PAGE(level2_kernel_pgt)
 
 NEXT_PAGE(level2_fixmap_pgt)
 	.fill	506,8,0
-	.quad	level1_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE
+	.quad	level1_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
 	/* 8MB reserved for vsyscalls + a 2MB hole = 4 + 1 entries */
 	.fill	5,8,0
 
diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c
index 38b64587b31b..fd6f8fbbe6f2 100644
--- a/arch/x86/kernel/kdebugfs.c
+++ b/arch/x86/kernel/kdebugfs.c
@@ -33,7 +33,6 @@ static ssize_t setup_data_read(struct file *file, char __user *user_buf,
 	struct setup_data_node *node = file->private_data;
 	unsigned long remain;
 	loff_t pos = *ppos;
-	struct page *pg;
 	void *p;
 	u64 pa;
 
@@ -47,18 +46,13 @@ static ssize_t setup_data_read(struct file *file, char __user *user_buf,
 		count = node->len - pos;
 
 	pa = node->paddr + sizeof(struct setup_data) + pos;
-	pg = pfn_to_page((pa + count - 1) >> PAGE_SHIFT);
-	if (PageHighMem(pg)) {
-		p = ioremap_cache(pa, count);
-		if (!p)
-			return -ENXIO;
-	} else
-		p = __va(pa);
+	p = memremap(pa, count, MEMREMAP_WB);
+	if (!p)
+		return -ENOMEM;
 
 	remain = copy_to_user(user_buf, p, count);
 
-	if (PageHighMem(pg))
-		iounmap(p);
+	memunmap(p);
 
 	if (remain)
 		return -EFAULT;
@@ -109,7 +103,6 @@ static int __init create_setup_data_nodes(struct dentry *parent)
 	struct setup_data *data;
 	int error;
 	struct dentry *d;
-	struct page *pg;
 	u64 pa_data;
 	int no = 0;
 
@@ -126,16 +119,12 @@ static int __init create_setup_data_nodes(struct dentry *parent)
 			goto err_dir;
 		}
 
-		pg = pfn_to_page((pa_data+sizeof(*data)-1) >> PAGE_SHIFT);
-		if (PageHighMem(pg)) {
-			data = ioremap_cache(pa_data, sizeof(*data));
-			if (!data) {
-				kfree(node);
-				error = -ENXIO;
-				goto err_dir;
-			}
-		} else
-			data = __va(pa_data);
+		data = memremap(pa_data, sizeof(*data), MEMREMAP_WB);
+		if (!data) {
+			kfree(node);
+			error = -ENOMEM;
+			goto err_dir;
+		}
 
 		node->paddr = pa_data;
 		node->type = data->type;
@@ -143,8 +132,7 @@ static int __init create_setup_data_nodes(struct dentry *parent)
 		error = create_setup_data_node(d, no, node);
 		pa_data = data->next;
 
-		if (PageHighMem(pg))
-			iounmap(data);
+		memunmap(data);
 		if (error)
 			goto err_dir;
 		no++;
diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c
index 06e1ff5562c0..4b0592ca9e47 100644
--- a/arch/x86/kernel/ksysfs.c
+++ b/arch/x86/kernel/ksysfs.c
@@ -16,8 +16,8 @@
 #include <linux/stat.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
+#include <linux/io.h>
 
-#include <asm/io.h>
 #include <asm/setup.h>
 
 static ssize_t version_show(struct kobject *kobj,
@@ -79,12 +79,12 @@ static int get_setup_data_paddr(int nr, u64 *paddr)
 			*paddr = pa_data;
 			return 0;
 		}
-		data = ioremap_cache(pa_data, sizeof(*data));
+		data = memremap(pa_data, sizeof(*data), MEMREMAP_WB);
 		if (!data)
 			return -ENOMEM;
 
 		pa_data = data->next;
-		iounmap(data);
+		memunmap(data);
 		i++;
 	}
 	return -EINVAL;
@@ -97,17 +97,17 @@ static int __init get_setup_data_size(int nr, size_t *size)
 	u64 pa_data = boot_params.hdr.setup_data;
 
 	while (pa_data) {
-		data = ioremap_cache(pa_data, sizeof(*data));
+		data = memremap(pa_data, sizeof(*data), MEMREMAP_WB);
 		if (!data)
 			return -ENOMEM;
 		if (nr == i) {
 			*size = data->len;
-			iounmap(data);
+			memunmap(data);
 			return 0;
 		}
 
 		pa_data = data->next;
-		iounmap(data);
+		memunmap(data);
 		i++;
 	}
 	return -EINVAL;
@@ -127,12 +127,12 @@ static ssize_t type_show(struct kobject *kobj,
 	ret = get_setup_data_paddr(nr, &paddr);
 	if (ret)
 		return ret;
-	data = ioremap_cache(paddr, sizeof(*data));
+	data = memremap(paddr, sizeof(*data), MEMREMAP_WB);
 	if (!data)
 		return -ENOMEM;
 
 	ret = sprintf(buf, "0x%x\n", data->type);
-	iounmap(data);
+	memunmap(data);
 	return ret;
 }
 
@@ -154,7 +154,7 @@ static ssize_t setup_data_data_read(struct file *fp,
 	ret = get_setup_data_paddr(nr, &paddr);
 	if (ret)
 		return ret;
-	data = ioremap_cache(paddr, sizeof(*data));
+	data = memremap(paddr, sizeof(*data), MEMREMAP_WB);
 	if (!data)
 		return -ENOMEM;
 
@@ -170,15 +170,15 @@ static ssize_t setup_data_data_read(struct file *fp,
 		goto out;
 
 	ret = count;
-	p = ioremap_cache(paddr + sizeof(*data), data->len);
+	p = memremap(paddr + sizeof(*data), data->len, MEMREMAP_WB);
 	if (!p) {
 		ret = -ENOMEM;
 		goto out;
 	}
 	memcpy(buf, p + off, count);
-	iounmap(p);
+	memunmap(p);
 out:
-	iounmap(data);
+	memunmap(data);
 	return ret;
 }
 
@@ -250,13 +250,13 @@ static int __init get_setup_data_total_num(u64 pa_data, int *nr)
 	*nr = 0;
 	while (pa_data) {
 		*nr += 1;
-		data = ioremap_cache(pa_data, sizeof(*data));
+		data = memremap(pa_data, sizeof(*data), MEMREMAP_WB);
 		if (!data) {
 			ret = -ENOMEM;
 			goto out;
 		}
 		pa_data = data->next;
-		iounmap(data);
+		memunmap(data);
 	}
 
 out:
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index cb0a30473c23..1f790cf9d38f 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -87,7 +87,7 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
 		set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE));
 	}
 	pte = pte_offset_kernel(pmd, vaddr);
-	set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC));
+	set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC_NOENC));
 	return 0;
 err:
 	free_transition_pgtable(image);
@@ -115,6 +115,7 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
 		.alloc_pgt_page	= alloc_pgt_page,
 		.context	= image,
 		.page_flag	= __PAGE_KERNEL_LARGE_EXEC,
+		.kernpg_flag	= _KERNPG_TABLE_NOENC,
 	};
 	unsigned long mstart, mend;
 	pgd_t *level4p;
@@ -334,7 +335,8 @@ void machine_kexec(struct kimage *image)
 	image->start = relocate_kernel((unsigned long)image->head,
 				       (unsigned long)page_list,
 				       image->start,
-				       image->preserve_context);
+				       image->preserve_context,
+				       sme_active());
 
 #ifdef CONFIG_KEXEC_JUMP
 	if (image->preserve_context)
@@ -602,3 +604,22 @@ void arch_kexec_unprotect_crashkres(void)
 {
 	kexec_mark_crashkres(false);
 }
+
+int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, gfp_t gfp)
+{
+	/*
+	 * If SME is active we need to be sure that kexec pages are
+	 * not encrypted because when we boot to the new kernel the
+	 * pages won't be accessed encrypted (initially).
+	 */
+	return set_memory_decrypted((unsigned long)vaddr, pages);
+}
+
+void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages)
+{
+	/*
+	 * If SME is active we need to reset the pages back to being
+	 * an encrypted mapping before freeing them.
+	 */
+	set_memory_encrypted((unsigned long)vaddr, pages);
+}
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 0d904d759ff1..5cbb3177ed17 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -429,16 +429,16 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type)
 	}
 }
 
-static struct mpf_intel *mpf_found;
+static unsigned long mpf_base;
 
 static unsigned long __init get_mpc_size(unsigned long physptr)
 {
 	struct mpc_table *mpc;
 	unsigned long size;
 
-	mpc = early_ioremap(physptr, PAGE_SIZE);
+	mpc = early_memremap(physptr, PAGE_SIZE);
 	size = mpc->length;
-	early_iounmap(mpc, PAGE_SIZE);
+	early_memunmap(mpc, PAGE_SIZE);
 	apic_printk(APIC_VERBOSE, "  mpc: %lx-%lx\n", physptr, physptr + size);
 
 	return size;
@@ -450,7 +450,8 @@ static int __init check_physptr(struct mpf_intel *mpf, unsigned int early)
 	unsigned long size;
 
 	size = get_mpc_size(mpf->physptr);
-	mpc = early_ioremap(mpf->physptr, size);
+	mpc = early_memremap(mpf->physptr, size);
+
 	/*
 	 * Read the physical hardware table.  Anything here will
 	 * override the defaults.
@@ -461,10 +462,10 @@ static int __init check_physptr(struct mpf_intel *mpf, unsigned int early)
 #endif
 		pr_err("BIOS bug, MP table errors detected!...\n");
 		pr_cont("... disabling SMP support. (tell your hw vendor)\n");
-		early_iounmap(mpc, size);
+		early_memunmap(mpc, size);
 		return -1;
 	}
-	early_iounmap(mpc, size);
+	early_memunmap(mpc, size);
 
 	if (early)
 		return -1;
@@ -497,12 +498,12 @@ static int __init check_physptr(struct mpf_intel *mpf, unsigned int early)
  */
 void __init default_get_smp_config(unsigned int early)
 {
-	struct mpf_intel *mpf = mpf_found;
+	struct mpf_intel *mpf;
 
 	if (!smp_found_config)
 		return;
 
-	if (!mpf)
+	if (!mpf_base)
 		return;
 
 	if (acpi_lapic && early)
@@ -515,6 +516,12 @@ void __init default_get_smp_config(unsigned int early)
 	if (acpi_lapic && acpi_ioapic)
 		return;
 
+	mpf = early_memremap(mpf_base, sizeof(*mpf));
+	if (!mpf) {
+		pr_err("MPTABLE: error mapping MP table\n");
+		return;
+	}
+
 	pr_info("Intel MultiProcessor Specification v1.%d\n",
 		mpf->specification);
 #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32)
@@ -529,7 +536,7 @@ void __init default_get_smp_config(unsigned int early)
 	/*
 	 * Now see if we need to read further.
 	 */
-	if (mpf->feature1 != 0) {
+	if (mpf->feature1) {
 		if (early) {
 			/*
 			 * local APIC has default address
@@ -542,8 +549,10 @@ void __init default_get_smp_config(unsigned int early)
 		construct_default_ISA_mptable(mpf->feature1);
 
 	} else if (mpf->physptr) {
-		if (check_physptr(mpf, early))
+		if (check_physptr(mpf, early)) {
+			early_memunmap(mpf, sizeof(*mpf));
 			return;
+		}
 	} else
 		BUG();
 
@@ -552,6 +561,8 @@ void __init default_get_smp_config(unsigned int early)
 	/*
 	 * Only use the first configuration found.
 	 */
+
+	early_memunmap(mpf, sizeof(*mpf));
 }
 
 static void __init smp_reserve_memory(struct mpf_intel *mpf)
@@ -561,15 +572,16 @@ static void __init smp_reserve_memory(struct mpf_intel *mpf)
 
 static int __init smp_scan_config(unsigned long base, unsigned long length)
 {
-	unsigned int *bp = phys_to_virt(base);
+	unsigned int *bp;
 	struct mpf_intel *mpf;
-	unsigned long mem;
+	int ret = 0;
 
 	apic_printk(APIC_VERBOSE, "Scan for SMP in [mem %#010lx-%#010lx]\n",
 		    base, base + length - 1);
 	BUILD_BUG_ON(sizeof(*mpf) != 16);
 
 	while (length > 0) {
+		bp = early_memremap(base, length);
 		mpf = (struct mpf_intel *)bp;
 		if ((*bp == SMP_MAGIC_IDENT) &&
 		    (mpf->length == 1) &&
@@ -579,24 +591,26 @@ static int __init smp_scan_config(unsigned long base, unsigned long length)
 #ifdef CONFIG_X86_LOCAL_APIC
 			smp_found_config = 1;
 #endif
-			mpf_found = mpf;
+			mpf_base = base;
 
-			pr_info("found SMP MP-table at [mem %#010llx-%#010llx] mapped at [%p]\n",
-				(unsigned long long) virt_to_phys(mpf),
-				(unsigned long long) virt_to_phys(mpf) +
-				sizeof(*mpf) - 1, mpf);
+			pr_info("found SMP MP-table at [mem %#010lx-%#010lx] mapped at [%p]\n",
+				base, base + sizeof(*mpf) - 1, mpf);
 
-			mem = virt_to_phys(mpf);
-			memblock_reserve(mem, sizeof(*mpf));
+			memblock_reserve(base, sizeof(*mpf));
 			if (mpf->physptr)
 				smp_reserve_memory(mpf);
 
-			return 1;
+			ret = 1;
 		}
-		bp += 4;
+		early_memunmap(bp, length);
+
+		if (ret)
+			break;
+
+		base += 16;
 		length -= 16;
 	}
-	return 0;
+	return ret;
 }
 
 void __init default_find_smp_config(void)
@@ -838,29 +852,40 @@ static int __init update_mp_table(void)
 	char oem[10];
 	struct mpf_intel *mpf;
 	struct mpc_table *mpc, *mpc_new;
+	unsigned long size;
 
 	if (!enable_update_mptable)
 		return 0;
 
-	mpf = mpf_found;
-	if (!mpf)
+	if (!mpf_base)
 		return 0;
 
+	mpf = early_memremap(mpf_base, sizeof(*mpf));
+	if (!mpf) {
+		pr_err("MPTABLE: mpf early_memremap() failed\n");
+		return 0;
+	}
+
 	/*
 	 * Now see if we need to go further.
 	 */
-	if (mpf->feature1 != 0)
-		return 0;
+	if (mpf->feature1)
+		goto do_unmap_mpf;
 
 	if (!mpf->physptr)
-		return 0;
+		goto do_unmap_mpf;
 
-	mpc = phys_to_virt(mpf->physptr);
+	size = get_mpc_size(mpf->physptr);
+	mpc = early_memremap(mpf->physptr, size);
+	if (!mpc) {
+		pr_err("MPTABLE: mpc early_memremap() failed\n");
+		goto do_unmap_mpf;
+	}
 
 	if (!smp_check_mpc(mpc, oem, str))
-		return 0;
+		goto do_unmap_mpc;
 
-	pr_info("mpf: %llx\n", (u64)virt_to_phys(mpf));
+	pr_info("mpf: %llx\n", (u64)mpf_base);
 	pr_info("physptr: %x\n", mpf->physptr);
 
 	if (mpc_new_phys && mpc->length > mpc_new_length) {
@@ -878,21 +903,32 @@ static int __init update_mp_table(void)
 		new = mpf_checksum((unsigned char *)mpc, mpc->length);
 		if (old == new) {
 			pr_info("mpc is readonly, please try alloc_mptable instead\n");
-			return 0;
+			goto do_unmap_mpc;
 		}
 		pr_info("use in-position replacing\n");
 	} else {
+		mpc_new = early_memremap(mpc_new_phys, mpc_new_length);
+		if (!mpc_new) {
+			pr_err("MPTABLE: new mpc early_memremap() failed\n");
+			goto do_unmap_mpc;
+		}
 		mpf->physptr = mpc_new_phys;
-		mpc_new = phys_to_virt(mpc_new_phys);
 		memcpy(mpc_new, mpc, mpc->length);
+		early_memunmap(mpc, size);
 		mpc = mpc_new;
+		size = mpc_new_length;
 		/* check if we can modify that */
 		if (mpc_new_phys - mpf->physptr) {
 			struct mpf_intel *mpf_new;
 			/* steal 16 bytes from [0, 1k) */
+			mpf_new = early_memremap(0x400 - 16, sizeof(*mpf_new));
+			if (!mpf_new) {
+				pr_err("MPTABLE: new mpf early_memremap() failed\n");
+				goto do_unmap_mpc;
+			}
 			pr_info("mpf new: %x\n", 0x400 - 16);
-			mpf_new = phys_to_virt(0x400 - 16);
 			memcpy(mpf_new, mpf, 16);
+			early_memunmap(mpf, sizeof(*mpf));
 			mpf = mpf_new;
 			mpf->physptr = mpc_new_phys;
 		}
@@ -909,6 +945,12 @@ static int __init update_mp_table(void)
 	 */
 	replace_intsrc_all(mpc, mpc_new_phys, mpc_new_length);
 
+do_unmap_mpc:
+	early_memunmap(mpc, size);
+
+do_unmap_mpf:
+	early_memunmap(mpf, sizeof(*mpf));
+
 	return 0;
 }
 
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 5e16d3f29594..0accc2404b92 100644
--- 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 a6d404087fe3..4fc3cb60ea11 100644
--- 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 1e23577e17cf..677077510e30 100644
--- 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/kernel/process.c b/arch/x86/kernel/process.c
index 3ca198080ea9..bd6b85fac666 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -355,6 +355,7 @@ bool xen_set_default_idle(void)
 	return ret;
 }
 #endif
+
 void stop_this_cpu(void *dummy)
 {
 	local_irq_disable();
@@ -365,8 +366,20 @@ void stop_this_cpu(void *dummy)
 	disable_local_APIC();
 	mcheck_cpu_clear(this_cpu_ptr(&cpu_info));
 
-	for (;;)
-		halt();
+	for (;;) {
+		/*
+		 * Use wbinvd followed by hlt to stop the processor. This
+		 * provides support for kexec on a processor that supports
+		 * SME. With kexec, going from SME inactive to SME active
+		 * requires clearing cache entries so that addresses without
+		 * the encryption bit set don't corrupt the same physical
+		 * address that has the encryption bit set when caches are
+		 * flushed. To achieve this a wbinvd is performed followed by
+		 * a hlt. Even if the processor is not in the kexec/SME
+		 * scenario this only adds a wbinvd to a halting processor.
+		 */
+		asm volatile("wbinvd; hlt" : : : "memory");
+	}
 }
 
 /*
diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S
index 98111b38ebfd..307d3bac5f04 100644
--- a/arch/x86/kernel/relocate_kernel_64.S
+++ b/arch/x86/kernel/relocate_kernel_64.S
@@ -47,6 +47,7 @@ relocate_kernel:
 	 * %rsi page_list
 	 * %rdx start address
 	 * %rcx preserve_context
+	 * %r8  sme_active
 	 */
 
 	/* Save the CPU context, used for jumping back */
@@ -71,6 +72,9 @@ relocate_kernel:
 	pushq $0
 	popfq
 
+	/* Save SME active flag */
+	movq	%r8, %r12
+
 	/*
 	 * get physical address of control page now
 	 * this is impossible after page table switch
@@ -132,6 +136,16 @@ identity_mapped:
 	/* Flush the TLB (needed?) */
 	movq	%r9, %cr3
 
+	/*
+	 * If SME is active, there could be old encrypted cache line
+	 * entries that will conflict with the now unencrypted memory
+	 * used by kexec. Flush the caches before copying the kernel.
+	 */
+	testq	%r12, %r12
+	jz 1f
+	wbinvd
+1:
+
 	movq	%rcx, %r11
 	call	swap_pages
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index ecab32282f0f..022ebddb3734 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -69,6 +69,7 @@
 #include <linux/crash_dump.h>
 #include <linux/tboot.h>
 #include <linux/jiffies.h>
+#include <linux/mem_encrypt.h>
 
 #include <linux/usb/xhci-dbgp.h>
 #include <video/edid.h>
@@ -375,6 +376,14 @@ static void __init reserve_initrd(void)
 	    !ramdisk_image || !ramdisk_size)
 		return;		/* No initrd provided by bootloader */
 
+	/*
+	 * If SME is active, this memory will be marked encrypted by the
+	 * kernel when it is accessed (including relocation). However, the
+	 * ramdisk image was loaded decrypted by the bootloader, so make
+	 * sure that it is encrypted before accessing it.
+	 */
+	sme_early_encrypt(ramdisk_image, ramdisk_end - ramdisk_image);
+
 	initrd_start = 0;
 
 	mapped_size = memblock_mem_size(max_pfn_mapped);
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index 213ddf3e937d..73e4d28112f8 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -21,6 +21,7 @@
 #include <asm/compat.h>
 #include <asm/ia32.h>
 #include <asm/syscalls.h>
+#include <asm/mpx.h>
 
 /*
  * Align a virtual address to avoid aliasing in the I$ on AMD F15h.
@@ -100,8 +101,8 @@ out:
 	return error;
 }
 
-static void find_start_end(unsigned long flags, unsigned long *begin,
-			   unsigned long *end)
+static void find_start_end(unsigned long addr, unsigned long flags,
+		unsigned long *begin, unsigned long *end)
 {
 	if (!in_compat_syscall() && (flags & MAP_32BIT)) {
 		/* This is usually used needed to map code in small
@@ -120,7 +121,10 @@ static void find_start_end(unsigned long flags, unsigned long *begin,
 	}
 
 	*begin	= get_mmap_base(1);
-	*end	= in_compat_syscall() ? tasksize_32bit() : tasksize_64bit();
+	if (in_compat_syscall())
+		*end = task_size_32bit();
+	else
+		*end = task_size_64bit(addr > DEFAULT_MAP_WINDOW);
 }
 
 unsigned long
@@ -132,10 +136,14 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	struct vm_unmapped_area_info info;
 	unsigned long begin, end;
 
+	addr = mpx_unmapped_area_check(addr, len, flags);
+	if (IS_ERR_VALUE(addr))
+		return addr;
+
 	if (flags & MAP_FIXED)
 		return addr;
 
-	find_start_end(flags, &begin, &end);
+	find_start_end(addr, flags, &begin, &end);
 
 	if (len > end)
 		return -ENOMEM;
@@ -171,6 +179,10 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	unsigned long addr = addr0;
 	struct vm_unmapped_area_info info;
 
+	addr = mpx_unmapped_area_check(addr, len, flags);
+	if (IS_ERR_VALUE(addr))
+		return addr;
+
 	/* requested length too big for entire address space */
 	if (len > TASK_SIZE)
 		return -ENOMEM;
@@ -195,6 +207,16 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	info.length = len;
 	info.low_limit = PAGE_SIZE;
 	info.high_limit = get_mmap_base(0);
+
+	/*
+	 * If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area
+	 * in the full address space.
+	 *
+	 * !in_compat_syscall() check to avoid high addresses for x32.
+	 */
+	if (addr > DEFAULT_MAP_WINDOW && !in_compat_syscall())
+		info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW;
+
 	info.align_mask = 0;
 	info.align_offset = pgoff << PAGE_SHIFT;
 	if (filp) {