16 files changed, 154 insertions, 28 deletions

diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index c3c1ad2fce5c..8cbfc51ce339 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -722,7 +722,7 @@ static void __init acpi_set_irq_model_ioapic(void)
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
 #include <acpi/processor.h>
 
-int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
+static int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
 {
 #ifdef CONFIG_ACPI_NUMA
 	int nid;
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index bd17db15a2c1..0b6124315441 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -19,6 +19,14 @@
 
 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();
 #ifndef CONFIG_SMP
 	pr_info("CPU: ");
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 4eece91ada37..918e44772b04 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -93,7 +93,7 @@ static const struct cpu_dev default_cpu = {
 
 static const struct cpu_dev *this_cpu = &default_cpu;
 
-DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
+DEFINE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(struct gdt_page, gdt_page) = { .gdt = {
 #ifdef CONFIG_X86_64
 	/*
 	 * We need valid kernel segments for data and code in long mode too
@@ -163,6 +163,24 @@ 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 */
@@ -306,6 +324,39 @@ 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) || kaiser_enabled) {
+			cr4_set_bits(X86_CR4_PCIDE);
+			/*
+			 * INVPCID has two "groups" of types:
+			 * 1/2: Invalidate an individual address
+			 * 3/4: Invalidate all contexts
+			 *
+			 * 1/2 take a PCID, but 3/4 do not.  So, 3/4
+			 * ignore the PCID argument in the descriptor.
+			 * But, we have to be careful not to call 1/2
+			 * with an actual non-zero PCID in them before
+			 * we do the above cr4_set_bits().
+			 */
+			if (cpu_has(c, X86_FEATURE_INVPCID))
+				set_cpu_cap(c, X86_FEATURE_INVPCID_SINGLE);
+		} 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);
+		}
+	}
+	kaiser_setup_pcid();
+}
+
 /*
  * Protection Keys are not available in 32-bit mode.
  */
@@ -1064,6 +1115,9 @@ 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."
@@ -1325,7 +1379,7 @@ static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = {
 	  [DEBUG_STACK - 1]			= DEBUG_STKSZ
 };
 
-static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
+DEFINE_PER_CPU_PAGE_ALIGNED_USER_MAPPED(char, exception_stacks
 	[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]);
 
 /* May not be marked __init: used by software suspend */
@@ -1483,6 +1537,14 @@ void cpu_init(void)
 	 * try to read it.
 	 */
 	cr4_init_shadow();
+	if (!kaiser_enabled) {
+		/*
+		 * secondary_startup_64() deferred setting PGE in cr4:
+		 * probe_page_size_mask() sets it on the boot cpu,
+		 * but it needs to be set on each secondary cpu.
+		 */
+		cr4_set_bits(X86_CR4_PGE);
+	}
 
 	/*
 	 * Load microcode on this cpu if a valid microcode is available.
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 017bda12caae..b74bb29db6b9 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -592,6 +592,7 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size,
 #define F14H_MPB_MAX_SIZE 1824
 #define F15H_MPB_MAX_SIZE 4096
 #define F16H_MPB_MAX_SIZE 3458
+#define F17H_MPB_MAX_SIZE 3200
 
 	switch (family) {
 	case 0x14:
@@ -603,6 +604,9 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size,
 	case 0x16:
 		max_size = F16H_MPB_MAX_SIZE;
 		break;
+	case 0x17:
+		max_size = F17H_MPB_MAX_SIZE;
+		break;
 	default:
 		max_size = F1XH_MPB_MAX_SIZE;
 		break;
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
index 04f89caef9c4..e33b38541be3 100644
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -41,6 +41,7 @@
 #include <asm/pgalloc.h>
 #include <asm/setup.h>
 #include <asm/espfix.h>
+#include <asm/kaiser.h>
 
 /*
  * Note: we only need 6*8 = 48 bytes for the espfix stack, but round
@@ -126,6 +127,15 @@ void __init init_espfix_bsp(void)
 	/* Install the espfix pud into the kernel page directory */
 	pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)];
 	pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page);
+	/*
+	 * Just copy the top-level PGD that is mapping the espfix
+	 * area to ensure it is mapped into the shadow user page
+	 * tables.
+	 */
+	if (kaiser_enabled) {
+		set_pgd(native_get_shadow_pgd(pgd_p),
+			__pgd(_KERNPG_TABLE | __pa((pud_t *)espfix_pud_page)));
+	}
 
 	/* Randomize the locations */
 	init_espfix_random();
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index b4421cc191b0..67cd7c1b99da 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -190,8 +190,8 @@ ENTRY(secondary_startup_64)
 	movq	$(init_level4_pgt - __START_KERNEL_map), %rax
 1:
 
-	/* Enable PAE mode and PGE */
-	movl	$(X86_CR4_PAE | X86_CR4_PGE), %ecx
+	/* Enable PAE and PSE, but defer PGE until kaiser_enabled is decided */
+	movl	$(X86_CR4_PAE | X86_CR4_PSE), %ecx
 	movq	%rcx, %cr4
 
 	/* Setup early boot stage 4 level pagetables. */
@@ -405,6 +405,27 @@ GLOBAL(early_recursion_flag)
 	.balign	PAGE_SIZE; \
 GLOBAL(name)
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * Each PGD needs to be 8k long and 8k aligned.  We do not
+ * ever go out to userspace with these, so we do not
+ * strictly *need* the second page, but this allows us to
+ * have a single set_pgd() implementation that does not
+ * need to worry about whether it has 4k or 8k to work
+ * with.
+ *
+ * This ensures PGDs are 8k long:
+ */
+#define KAISER_USER_PGD_FILL	512
+/* This ensures they are 8k-aligned: */
+#define NEXT_PGD_PAGE(name) \
+	.balign 2 * PAGE_SIZE; \
+GLOBAL(name)
+#else
+#define NEXT_PGD_PAGE(name) NEXT_PAGE(name)
+#define KAISER_USER_PGD_FILL	0
+#endif
+
 /* Automate the creation of 1 to 1 mapping pmd entries */
 #define PMDS(START, PERM, COUNT)			\
 	i = 0 ;						\
@@ -414,9 +435,10 @@ GLOBAL(name)
 	.endr
 
 	__INITDATA
-NEXT_PAGE(early_level4_pgt)
+NEXT_PGD_PAGE(early_level4_pgt)
 	.fill	511,8,0
 	.quad	level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE
+	.fill	KAISER_USER_PGD_FILL,8,0
 
 NEXT_PAGE(early_dynamic_pgts)
 	.fill	512*EARLY_DYNAMIC_PAGE_TABLES,8,0
@@ -424,16 +446,18 @@ NEXT_PAGE(early_dynamic_pgts)
 	.data
 
 #ifndef CONFIG_XEN
-NEXT_PAGE(init_level4_pgt)
+NEXT_PGD_PAGE(init_level4_pgt)
 	.fill	512,8,0
+	.fill	KAISER_USER_PGD_FILL,8,0
 #else
-NEXT_PAGE(init_level4_pgt)
+NEXT_PGD_PAGE(init_level4_pgt)
 	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
 	.org    init_level4_pgt + L4_PAGE_OFFSET*8, 0
 	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
 	.org    init_level4_pgt + L4_START_KERNEL*8, 0
 	/* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
 	.quad   level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE
+	.fill	KAISER_USER_PGD_FILL,8,0
 
 NEXT_PAGE(level3_ident_pgt)
 	.quad	level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
@@ -444,6 +468,7 @@ NEXT_PAGE(level2_ident_pgt)
 	 */
 	PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD)
 #endif
+	.fill	KAISER_USER_PGD_FILL,8,0
 
 NEXT_PAGE(level3_kernel_pgt)
 	.fill	L3_START_KERNEL,8,0
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 932348fbb6ea..9512529e8eab 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -354,7 +354,7 @@ static int hpet_resume(struct clock_event_device *evt, int timer)
 
 		irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq));
 		irq_domain_activate_irq(irq_get_irq_data(hdev->irq));
-		disable_irq(hdev->irq);
+		disable_hardirq(hdev->irq);
 		irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
 		enable_irq(hdev->irq);
 	}
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 1423ab1b0312..f480b38a03c3 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -51,7 +51,7 @@ static struct irqaction irq2 = {
 	.flags = IRQF_NO_THREAD,
 };
 
-DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
+DEFINE_PER_CPU_USER_MAPPED(vector_irq_t, vector_irq) = {
 	[0 ... NR_VECTORS - 1] = VECTOR_UNUSED,
 };
 
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 5f70014ca602..8bc68cfc0d33 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -16,6 +16,7 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
+#include <linux/kaiser.h>
 
 #include <asm/ldt.h>
 #include <asm/desc.h>
@@ -34,11 +35,21 @@ static void flush_ldt(void *current_mm)
 	set_ldt(pc->ldt->entries, pc->ldt->size);
 }
 
+static void __free_ldt_struct(struct ldt_struct *ldt)
+{
+	if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE)
+		vfree(ldt->entries);
+	else
+		free_page((unsigned long)ldt->entries);
+	kfree(ldt);
+}
+
 /* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */
 static struct ldt_struct *alloc_ldt_struct(int size)
 {
 	struct ldt_struct *new_ldt;
 	int alloc_size;
+	int ret;
 
 	if (size > LDT_ENTRIES)
 		return NULL;
@@ -66,7 +77,13 @@ static struct ldt_struct *alloc_ldt_struct(int size)
 		return NULL;
 	}
 
+	ret = kaiser_add_mapping((unsigned long)new_ldt->entries, alloc_size,
+				 __PAGE_KERNEL);
 	new_ldt->size = size;
+	if (ret) {
+		__free_ldt_struct(new_ldt);
+		return NULL;
+	}
 	return new_ldt;
 }
 
@@ -92,12 +109,10 @@ static void free_ldt_struct(struct ldt_struct *ldt)
 	if (likely(!ldt))
 		return;
 
+	kaiser_remove_mapping((unsigned long)ldt->entries,
+			      ldt->size * LDT_ENTRY_SIZE);
 	paravirt_free_ldt(ldt->entries, ldt->size);
-	if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE)
-		vfree(ldt->entries);
-	else
-		free_page((unsigned long)ldt->entries);
-	kfree(ldt);
+	__free_ldt_struct(ldt);
 }
 
 /*
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index bb3840cedb4f..ee43b36075c7 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -9,7 +9,6 @@ DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax");
 DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax");
 DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax");
 DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3");
-DEF_NATIVE(pv_mmu_ops, flush_tlb_single, "invlpg (%rdi)");
 DEF_NATIVE(pv_cpu_ops, clts, "clts");
 DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd");
 
@@ -59,7 +58,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_mmu_ops, read_cr3);
 		PATCH_SITE(pv_mmu_ops, write_cr3);
 		PATCH_SITE(pv_cpu_ops, clts);
-		PATCH_SITE(pv_mmu_ops, flush_tlb_single);
 		PATCH_SITE(pv_cpu_ops, wbinvd);
 #if defined(CONFIG_PARAVIRT_SPINLOCKS)
 		case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 8e10e72bf6ee..a55b32007785 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -41,7 +41,7 @@
  * section. Since TSS's are completely CPU-local, we want them
  * on exact cacheline boundaries, to eliminate cacheline ping-pong.
  */
-__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = {
+__visible DEFINE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(struct tss_struct, cpu_tss) = {
 	.x86_tss = {
 		.sp0 = TOP_OF_INIT_STACK,
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 067f9813fd2c..ce020a69bba9 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -106,6 +106,10 @@ void __noreturn machine_real_restart(unsigned int type)
 	load_cr3(initial_page_table);
 #else
 	write_cr3(real_mode_header->trampoline_pgd);
+
+	/* Exiting long mode will fail if CR4.PCIDE is set. */
+	if (static_cpu_has(X86_FEATURE_PCID))
+		cr4_clear_bits(X86_CR4_PCIDE);
 #endif
 
 	/* Jump to the identity-mapped low memory code */
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index feaab07fa124..6b55012d02a3 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -114,6 +114,7 @@
 #include <asm/microcode.h>
 #include <asm/mmu_context.h>
 #include <asm/kaslr.h>
+#include <asm/kaiser.h>
 
 /*
  * max_low_pfn_mapped: highest direct mapped pfn under 4GB
@@ -1019,6 +1020,12 @@ void __init setup_arch(char **cmdline_p)
 	 */
 	init_hypervisor_platform();
 
+	/*
+	 * This needs to happen right after XENPV is set on xen and
+	 * kaiser_enabled is checked below in cleanup_highmap().
+	 */
+	kaiser_check_boottime_disable();
+
 	x86_init.resources.probe_roms();
 
 	/* after parse_early_param, so could debug it */
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 9fe7b9e1ae30..e803d72ef525 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -115,14 +115,10 @@ static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
 	spin_lock_irqsave(&rtc_lock, flags);
 	CMOS_WRITE(0xa, 0xf);
 	spin_unlock_irqrestore(&rtc_lock, flags);
-	local_flush_tlb();
-	pr_debug("1.\n");
 	*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) =
 							start_eip >> 4;
-	pr_debug("2.\n");
 	*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) =
 							start_eip & 0xf;
-	pr_debug("3.\n");
 }
 
 static inline void smpboot_restore_warm_reset_vector(void)
@@ -130,11 +126,6 @@ static inline void smpboot_restore_warm_reset_vector(void)
 	unsigned long flags;
 
 	/*
-	 * Install writable page 0 entry to set BIOS data area.
-	 */
-	local_flush_tlb();
-
-	/*
 	 * Paranoid:  Set warm reset code and vector here back
 	 * to default values.
 	 */
diff --git a/arch/x86/kernel/tracepoint.c b/arch/x86/kernel/tracepoint.c
index 1c113db9ed57..2bb5ee464df3 100644
--- a/arch/x86/kernel/tracepoint.c
+++ b/arch/x86/kernel/tracepoint.c
@@ -9,10 +9,12 @@
 #include <linux/atomic.h>
 
 atomic_t trace_idt_ctr = ATOMIC_INIT(0);
+__aligned(PAGE_SIZE)
 struct desc_ptr trace_idt_descr = { NR_VECTORS * 16 - 1,
 				(unsigned long) trace_idt_table };
 
 /* No need to be aligned, but done to keep all IDTs defined the same way. */
+__aligned(PAGE_SIZE)
 gate_desc trace_idt_table[NR_VECTORS] __page_aligned_bss;
 
 static int trace_irq_vector_refcount;
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 01f30e56f99e..4b3012888ada 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -191,7 +191,7 @@ static void mark_screen_rdonly(struct mm_struct *mm)
 	pte_unmap_unlock(pte, ptl);
 out:
 	up_write(&mm->mmap_sem);
-	flush_tlb();
+	flush_tlb_mm_range(mm, 0xA0000, 0xA0000 + 32*PAGE_SIZE, 0UL);
 }