Merge branch 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Thomas Gleixner:
 "A set of x86 fixes:

   - Cure the LDT remapping to user space on 5 level paging which ended
     up in the KASLR space

   - Remove LDT mapping before freeing the LDT pages

   - Make NFIT MCE handling more robust

   - Unbreak the VSMP build by removing the dependency on paravirt ops

   - Support broken PIT emulation on Microsoft hyperV

   - Don't trace vmware_sched_clock() to avoid tracer recursion

   - Remove -pipe from KBUILD CFLAGS which breaks clang and is also
     slower on GCC

   - Trivial coding style and typo fixes"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/cpu/vmware: Do not trace vmware_sched_clock()
  x86/vsmp: Remove dependency on pv_irq_ops
  x86/ldt: Remove unused variable in map_ldt_struct()
  x86/ldt: Unmap PTEs for the slot before freeing LDT pages
  x86/mm: Move LDT remap out of KASLR region on 5-level paging
  acpi/nfit, x86/mce: Validate a MCE's address before using it
  acpi/nfit, x86/mce: Handle only uncorrectable machine checks
  x86/build: Remove -pipe from KBUILD_CFLAGS
  x86/hyper-v: Fix indentation in hv_do_fast_hypercall16()
  Documentation/x86: Fix typo in zero-page.txt
  x86/hyper-v: Enable PIT shutdown quirk
  clockevents/drivers/i8253: Add support for PIT shutdown quirk

12 files changed, 76 insertions, 117 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ba7e3464ee92..9d734f3c8234 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -525,7 +525,6 @@ config X86_VSMP
 	bool "ScaleMP vSMP"
 	select HYPERVISOR_GUEST
 	select PARAVIRT
-	select PARAVIRT_XXL
 	depends on X86_64 && PCI
 	depends on X86_EXTENDED_PLATFORM
 	depends on SMP
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 5b562e464009..88398fdf8129 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -213,8 +213,6 @@ ifdef CONFIG_X86_64
 KBUILD_LDFLAGS += $(call ld-option, -z max-page-size=0x200000)
 endif
 
-# Speed up the build
-KBUILD_CFLAGS += -pipe
 # Workaround for a gcc prelease that unfortunately was shipped in a suse release
 KBUILD_CFLAGS += -Wno-sign-compare
 #
@@ -239,7 +237,7 @@ archheaders:
 archmacros:
 	$(Q)$(MAKE) $(build)=arch/x86/kernel arch/x86/kernel/macros.s
 
-ASM_MACRO_FLAGS = -Wa,arch/x86/kernel/macros.s -Wa,-
+ASM_MACRO_FLAGS = -Wa,arch/x86/kernel/macros.s
 export ASM_MACRO_FLAGS
 KBUILD_CFLAGS += $(ASM_MACRO_FLAGS)
 
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 4da9b1c58d28..c1a812bd5a27 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -221,6 +221,8 @@ static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c) { return mce_am
 
 int mce_available(struct cpuinfo_x86 *c);
 bool mce_is_memory_error(struct mce *m);
+bool mce_is_correctable(struct mce *m);
+int mce_usable_address(struct mce *m);
 
 DECLARE_PER_CPU(unsigned, mce_exception_count);
 DECLARE_PER_CPU(unsigned, mce_poll_count);
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 0d6271cce198..1d0a7778e163 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -232,7 +232,7 @@ static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2)
 				      : "cc");
 	}
 #endif
-		return hv_status;
+	return hv_status;
 }
 
 /*
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index cd0cf1c568b4..8f657286d599 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -33,12 +33,14 @@
 
 /*
  * Set __PAGE_OFFSET to the most negative possible address +
- * PGDIR_SIZE*16 (pgd slot 272).  The gap is to allow a space for a
- * hypervisor to fit.  Choosing 16 slots here is arbitrary, but it's
- * what Xen requires.
+ * PGDIR_SIZE*17 (pgd slot 273).
+ *
+ * The gap is to allow a space for LDT remap for PTI (1 pgd slot) and space for
+ * a hypervisor (16 slots). Choosing 16 slots for a hypervisor is arbitrary,
+ * but it's what Xen requires.
  */
-#define __PAGE_OFFSET_BASE_L5	_AC(0xff10000000000000, UL)
-#define __PAGE_OFFSET_BASE_L4	_AC(0xffff880000000000, UL)
+#define __PAGE_OFFSET_BASE_L5	_AC(0xff11000000000000, UL)
+#define __PAGE_OFFSET_BASE_L4	_AC(0xffff888000000000, UL)
 
 #ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT
 #define __PAGE_OFFSET           page_offset_base
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 04edd2d58211..84bd9bdc1987 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -111,9 +111,7 @@ extern unsigned int ptrs_per_p4d;
  */
 #define MAXMEM			(1UL << MAX_PHYSMEM_BITS)
 
-#define LDT_PGD_ENTRY_L4	-3UL
-#define LDT_PGD_ENTRY_L5	-112UL
-#define LDT_PGD_ENTRY		(pgtable_l5_enabled() ? LDT_PGD_ENTRY_L5 : LDT_PGD_ENTRY_L4)
+#define LDT_PGD_ENTRY		-240UL
 #define LDT_BASE_ADDR		(LDT_PGD_ENTRY << PGDIR_SHIFT)
 #define LDT_END_ADDR		(LDT_BASE_ADDR + PGDIR_SIZE)
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 8c66d2fc8f81..36d2696c9563 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -485,7 +485,7 @@ static void mce_report_event(struct pt_regs *regs)
  * be somewhat complicated (e.g. segment offset would require an instruction
  * parser). So only support physical addresses up to page granuality for now.
  */
-static int mce_usable_address(struct mce *m)
+int mce_usable_address(struct mce *m)
 {
 	if (!(m->status & MCI_STATUS_ADDRV))
 		return 0;
@@ -505,6 +505,7 @@ static int mce_usable_address(struct mce *m)
 
 	return 1;
 }
+EXPORT_SYMBOL_GPL(mce_usable_address);
 
 bool mce_is_memory_error(struct mce *m)
 {
@@ -534,7 +535,7 @@ bool mce_is_memory_error(struct mce *m)
 }
 EXPORT_SYMBOL_GPL(mce_is_memory_error);
 
-static bool mce_is_correctable(struct mce *m)
+bool mce_is_correctable(struct mce *m)
 {
 	if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED)
 		return false;
@@ -547,6 +548,7 @@ static bool mce_is_correctable(struct mce *m)
 
 	return true;
 }
+EXPORT_SYMBOL_GPL(mce_is_correctable);
 
 static bool cec_add_mce(struct mce *m)
 {
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 1c72f3819eb1..e81a2db42df7 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -20,6 +20,7 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/kexec.h>
+#include <linux/i8253.h>
 #include <asm/processor.h>
 #include <asm/hypervisor.h>
 #include <asm/hyperv-tlfs.h>
@@ -295,6 +296,16 @@ static void __init ms_hyperv_init_platform(void)
 	if (efi_enabled(EFI_BOOT))
 		x86_platform.get_nmi_reason = hv_get_nmi_reason;
 
+	/*
+	 * Hyper-V VMs have a PIT emulation quirk such that zeroing the
+	 * counter register during PIT shutdown restarts the PIT. So it
+	 * continues to interrupt @18.2 HZ. Setting i8253_clear_counter
+	 * to false tells pit_shutdown() not to zero the counter so that
+	 * the PIT really is shutdown. Generation 2 VMs don't have a PIT,
+	 * and setting this value has no effect.
+	 */
+	i8253_clear_counter_on_shutdown = false;
+
 #if IS_ENABLED(CONFIG_HYPERV)
 	/*
 	 * Setup the hook to get control post apic initialization.
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index d9ab49bed8af..0eda91f8eeac 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -77,7 +77,7 @@ static __init int setup_vmw_sched_clock(char *s)
 }
 early_param("no-vmw-sched-clock", setup_vmw_sched_clock);
 
-static unsigned long long vmware_sched_clock(void)
+static unsigned long long notrace vmware_sched_clock(void)
 {
 	unsigned long long ns;
 
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index ab18e0884dc6..6135ae8ce036 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -199,14 +199,6 @@ static void sanity_check_ldt_mapping(struct mm_struct *mm)
 /*
  * If PTI is enabled, this maps the LDT into the kernelmode and
  * usermode tables for the given mm.
- *
- * There is no corresponding unmap function.  Even if the LDT is freed, we
- * leave the PTEs around until the slot is reused or the mm is destroyed.
- * This is harmless: the LDT is always in ordinary memory, and no one will
- * access the freed slot.
- *
- * If we wanted to unmap freed LDTs, we'd also need to do a flush to make
- * it useful, and the flush would slow down modify_ldt().
  */
 static int
 map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
@@ -214,8 +206,7 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 	unsigned long va;
 	bool is_vmalloc;
 	spinlock_t *ptl;
-	pgd_t *pgd;
-	int i;
+	int i, nr_pages;
 
 	if (!static_cpu_has(X86_FEATURE_PTI))
 		return 0;
@@ -229,16 +220,11 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 	/* Check if the current mappings are sane */
 	sanity_check_ldt_mapping(mm);
 
-	/*
-	 * Did we already have the top level entry allocated?  We can't
-	 * use pgd_none() for this because it doens't do anything on
-	 * 4-level page table kernels.
-	 */
-	pgd = pgd_offset(mm, LDT_BASE_ADDR);
-
 	is_vmalloc = is_vmalloc_addr(ldt->entries);
 
-	for (i = 0; i * PAGE_SIZE < ldt->nr_entries * LDT_ENTRY_SIZE; i++) {
+	nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE);
+
+	for (i = 0; i < nr_pages; i++) {
 		unsigned long offset = i << PAGE_SHIFT;
 		const void *src = (char *)ldt->entries + offset;
 		unsigned long pfn;
@@ -272,13 +258,39 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 	/* Propagate LDT mapping to the user page-table */
 	map_ldt_struct_to_user(mm);
 
-	va = (unsigned long)ldt_slot_va(slot);
-	flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, PAGE_SHIFT, false);
-
 	ldt->slot = slot;
 	return 0;
 }
 
+static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt)
+{
+	unsigned long va;
+	int i, nr_pages;
+
+	if (!ldt)
+		return;
+
+	/* LDT map/unmap is only required for PTI */
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
+
+	nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE);
+
+	for (i = 0; i < nr_pages; i++) {
+		unsigned long offset = i << PAGE_SHIFT;
+		spinlock_t *ptl;
+		pte_t *ptep;
+
+		va = (unsigned long)ldt_slot_va(ldt->slot) + offset;
+		ptep = get_locked_pte(mm, va, &ptl);
+		pte_clear(mm, va, ptep);
+		pte_unmap_unlock(ptep, ptl);
+	}
+
+	va = (unsigned long)ldt_slot_va(ldt->slot);
+	flush_tlb_mm_range(mm, va, va + nr_pages * PAGE_SIZE, PAGE_SHIFT, false);
+}
+
 #else /* !CONFIG_PAGE_TABLE_ISOLATION */
 
 static int
@@ -286,6 +298,10 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 {
 	return 0;
 }
+
+static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt)
+{
+}
 #endif /* CONFIG_PAGE_TABLE_ISOLATION */
 
 static void free_ldt_pgtables(struct mm_struct *mm)
@@ -524,6 +540,7 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 	}
 
 	install_ldt(mm, new_ldt);
+	unmap_ldt_struct(mm, old_ldt);
 	free_ldt_struct(old_ldt);
 	error = 0;
 
diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c
index 1eae5af491c2..891a75dbc131 100644
--- a/arch/x86/kernel/vsmp_64.c
+++ b/arch/x86/kernel/vsmp_64.c
@@ -26,65 +26,8 @@
 
 #define TOPOLOGY_REGISTER_OFFSET 0x10
 
-#if defined CONFIG_PCI && defined CONFIG_PARAVIRT_XXL
-/*
- * Interrupt control on vSMPowered systems:
- * ~AC is a shadow of IF.  If IF is 'on' AC should be 'off'
- * and vice versa.
- */
-
-asmlinkage __visible unsigned long vsmp_save_fl(void)
-{
-	unsigned long flags = native_save_fl();
-
-	if (!(flags & X86_EFLAGS_IF) || (flags & X86_EFLAGS_AC))
-		flags &= ~X86_EFLAGS_IF;
-	return flags;
-}
-PV_CALLEE_SAVE_REGS_THUNK(vsmp_save_fl);
-
-__visible void vsmp_restore_fl(unsigned long flags)
-{
-	if (flags & X86_EFLAGS_IF)
-		flags &= ~X86_EFLAGS_AC;
-	else
-		flags |= X86_EFLAGS_AC;
-	native_restore_fl(flags);
-}
-PV_CALLEE_SAVE_REGS_THUNK(vsmp_restore_fl);
-
-asmlinkage __visible void vsmp_irq_disable(void)
-{
-	unsigned long flags = native_save_fl();
-
-	native_restore_fl((flags & ~X86_EFLAGS_IF) | X86_EFLAGS_AC);
-}
-PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_disable);
-
-asmlinkage __visible void vsmp_irq_enable(void)
-{
-	unsigned long flags = native_save_fl();
-
-	native_restore_fl((flags | X86_EFLAGS_IF) & (~X86_EFLAGS_AC));
-}
-PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_enable);
-
-static unsigned __init vsmp_patch(u8 type, void *ibuf,
-				  unsigned long addr, unsigned len)
-{
-	switch (type) {
-	case PARAVIRT_PATCH(irq.irq_enable):
-	case PARAVIRT_PATCH(irq.irq_disable):
-	case PARAVIRT_PATCH(irq.save_fl):
-	case PARAVIRT_PATCH(irq.restore_fl):
-		return paravirt_patch_default(type, ibuf, addr, len);
-	default:
-		return native_patch(type, ibuf, addr, len);
-	}
-
-}
-
-static void __init set_vsmp_pv_ops(void)
+#ifdef CONFIG_PCI
+static void __init set_vsmp_ctl(void)
 {
 	void __iomem *address;
 	unsigned int cap, ctl, cfg;
@@ -109,28 +52,12 @@ static void __init set_vsmp_pv_ops(void)
 	}
 #endif
 
-	if (cap & ctl & (1 << 4)) {
-		/* Setup irq ops and turn on vSMP  IRQ fastpath handling */
-		pv_ops.irq.irq_disable = PV_CALLEE_SAVE(vsmp_irq_disable);
-		pv_ops.irq.irq_enable = PV_CALLEE_SAVE(vsmp_irq_enable);
-		pv_ops.irq.save_fl = PV_CALLEE_SAVE(vsmp_save_fl);
-		pv_ops.irq.restore_fl = PV_CALLEE_SAVE(vsmp_restore_fl);
-		pv_ops.init.patch = vsmp_patch;
-		ctl &= ~(1 << 4);
-	}
 	writel(ctl, address + 4);
 	ctl = readl(address + 4);
 	pr_info("vSMP CTL: control set to:0x%08x\n", ctl);
 
 	early_iounmap(address, 8);
 }
-#else
-static void __init set_vsmp_pv_ops(void)
-{
-}
-#endif
-
-#ifdef CONFIG_PCI
 static int is_vsmp = -1;
 
 static void __init detect_vsmp_box(void)
@@ -164,11 +91,14 @@ static int is_vsmp_box(void)
 {
 	return 0;
 }
+static void __init set_vsmp_ctl(void)
+{
+}
 #endif
 
 static void __init vsmp_cap_cpus(void)
 {
-#if !defined(CONFIG_X86_VSMP) && defined(CONFIG_SMP)
+#if !defined(CONFIG_X86_VSMP) && defined(CONFIG_SMP) && defined(CONFIG_PCI)
 	void __iomem *address;
 	unsigned int cfg, topology, node_shift, maxcpus;
 
@@ -221,6 +151,6 @@ void __init vsmp_init(void)
 
 	vsmp_cap_cpus();
 
-	set_vsmp_pv_ops();
+	set_vsmp_ctl();
 	return;
 }
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 0d7b3ae4960b..a5d7ed125337 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1905,7 +1905,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	init_top_pgt[0] = __pgd(0);
 
 	/* Pre-constructed entries are in pfn, so convert to mfn */
-	/* L4[272] -> level3_ident_pgt  */
+	/* L4[273] -> level3_ident_pgt  */
 	/* L4[511] -> level3_kernel_pgt */
 	convert_pfn_mfn(init_top_pgt);
 
@@ -1925,8 +1925,8 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	addr[0] = (unsigned long)pgd;
 	addr[1] = (unsigned long)l3;
 	addr[2] = (unsigned long)l2;
-	/* Graft it onto L4[272][0]. Note that we creating an aliasing problem:
-	 * Both L4[272][0] and L4[511][510] have entries that point to the same
+	/* Graft it onto L4[273][0]. Note that we creating an aliasing problem:
+	 * Both L4[273][0] and L4[511][510] have entries that point to the same
 	 * L2 (PMD) tables. Meaning that if you modify it in __va space
 	 * it will be also modified in the __ka space! (But if you just
 	 * modify the PMD table to point to other PTE's or none, then you