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

…inux/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

Documentation/x86/x86_64/mm.txt

@@ -34,23 +34,24 @@ __________________|____________|__________________|_________|___________________
 ____________________________________________________________|___________________________________________________________
                   |            |                  |         |
  ffff800000000000 | -128    TB | ffff87ffffffffff |    8 TB | ... guard hole, also reserved for hypervisor
- ffff880000000000 | -120    TB | ffffc7ffffffffff |   64 TB | direct mapping of all physical memory (page_offset_base)
- ffffc80000000000 |  -56    TB | ffffc8ffffffffff |    1 TB | ... unused hole
+ ffff880000000000 | -120    TB | ffff887fffffffff |  0.5 TB | LDT remap for PTI
+ ffff888000000000 | -119.5  TB | ffffc87fffffffff |   64 TB | direct mapping of all physical memory (page_offset_base)
+ ffffc88000000000 |  -55.5  TB | ffffc8ffffffffff |  0.5 TB | ... unused hole
  ffffc90000000000 |  -55    TB | ffffe8ffffffffff |   32 TB | vmalloc/ioremap space (vmalloc_base)
  ffffe90000000000 |  -23    TB | ffffe9ffffffffff |    1 TB | ... unused hole
  ffffea0000000000 |  -22    TB | ffffeaffffffffff |    1 TB | virtual memory map (vmemmap_base)
  ffffeb0000000000 |  -21    TB | ffffebffffffffff |    1 TB | ... unused hole
  ffffec0000000000 |  -20    TB | fffffbffffffffff |   16 TB | KASAN shadow memory
- fffffc0000000000 |   -4    TB | fffffdffffffffff |    2 TB | ... unused hole
-                  |            |                  |         | vaddr_end for KASLR
- fffffe0000000000 |   -2    TB | fffffe7fffffffff |  0.5 TB | cpu_entry_area mapping
- fffffe8000000000 |   -1.5  TB | fffffeffffffffff |  0.5 TB | LDT remap for PTI
- ffffff0000000000 |   -1    TB | ffffff7fffffffff |  0.5 TB | %esp fixup stacks
 __________________|____________|__________________|_________|____________________________________________________________
                                                             |
-                                                            | Identical layout to the 47-bit one from here on:
+                                                            | Identical layout to the 56-bit one from here on:
 ____________________________________________________________|____________________________________________________________
                   |            |                  |         |
+ fffffc0000000000 |   -4    TB | fffffdffffffffff |    2 TB | ... unused hole
+                  |            |                  |         | vaddr_end for KASLR
+ fffffe0000000000 |   -2    TB | fffffe7fffffffff |  0.5 TB | cpu_entry_area mapping
+ fffffe8000000000 |   -1.5  TB | fffffeffffffffff |  0.5 TB | ... unused hole
+ ffffff0000000000 |   -1    TB | ffffff7fffffffff |  0.5 TB | %esp fixup stacks
  ffffff8000000000 | -512    GB | ffffffeeffffffff |  444 GB | ... unused hole
  ffffffef00000000 |  -68    GB | fffffffeffffffff |   64 GB | EFI region mapping space
  ffffffff00000000 |   -4    GB | ffffffff7fffffff |    2 GB | ... unused hole
@@ -83,31 +84,32 @@ Notes:
 __________________|____________|__________________|_________|___________________________________________________________
                   |            |                  |         |
  0000800000000000 |  +64    PB | ffff7fffffffffff | ~16K PB | ... huge, still almost 64 bits wide hole of non-canonical
-                  |            |                  |         |     virtual memory addresses up to the -128 TB
+                  |            |                  |         |     virtual memory addresses up to the -64 PB
                   |            |                  |         |     starting offset of kernel mappings.
 __________________|____________|__________________|_________|___________________________________________________________
                                                             |
                                                             | Kernel-space virtual memory, shared between all processes:
 ____________________________________________________________|___________________________________________________________
                   |            |                  |         |
  ff00000000000000 |  -64    PB | ff0fffffffffffff |    4 PB | ... guard hole, also reserved for hypervisor
- ff10000000000000 |  -60    PB | ff8fffffffffffff |   32 PB | direct mapping of all physical memory (page_offset_base)
- ff90000000000000 |  -28    PB | ff9fffffffffffff |    4 PB | LDT remap for PTI
+ ff10000000000000 |  -60    PB | ff10ffffffffffff | 0.25 PB | LDT remap for PTI
+ ff11000000000000 |  -59.75 PB | ff90ffffffffffff |   32 PB | direct mapping of all physical memory (page_offset_base)
+ ff91000000000000 |  -27.75 PB | ff9fffffffffffff | 3.75 PB | ... unused hole
  ffa0000000000000 |  -24    PB | ffd1ffffffffffff | 12.5 PB | vmalloc/ioremap space (vmalloc_base)
  ffd2000000000000 |  -11.5  PB | ffd3ffffffffffff |  0.5 PB | ... unused hole
  ffd4000000000000 |  -11    PB | ffd5ffffffffffff |  0.5 PB | virtual memory map (vmemmap_base)
  ffd6000000000000 |  -10.5  PB | ffdeffffffffffff | 2.25 PB | ... unused hole
  ffdf000000000000 |   -8.25 PB | fffffdffffffffff |   ~8 PB | KASAN shadow memory
- fffffc0000000000 |   -4    TB | fffffdffffffffff |    2 TB | ... unused hole
-                  |            |                  |         | vaddr_end for KASLR
- fffffe0000000000 |   -2    TB | fffffe7fffffffff |  0.5 TB | cpu_entry_area mapping
- fffffe8000000000 |   -1.5  TB | fffffeffffffffff |  0.5 TB | ... unused hole
- ffffff0000000000 |   -1    TB | ffffff7fffffffff |  0.5 TB | %esp fixup stacks
 __________________|____________|__________________|_________|____________________________________________________________
                                                             |
                                                             | Identical layout to the 47-bit one from here on:
 ____________________________________________________________|____________________________________________________________
                   |            |                  |         |
+ fffffc0000000000 |   -4    TB | fffffdffffffffff |    2 TB | ... unused hole
+                  |            |                  |         | vaddr_end for KASLR
+ fffffe0000000000 |   -2    TB | fffffe7fffffffff |  0.5 TB | cpu_entry_area mapping
+ fffffe8000000000 |   -1.5  TB | fffffeffffffffff |  0.5 TB | ... unused hole
+ ffffff0000000000 |   -1    TB | ffffff7fffffffff |  0.5 TB | %esp fixup stacks
  ffffff8000000000 | -512    GB | ffffffeeffffffff |  444 GB | ... unused hole
  ffffffef00000000 |  -68    GB | fffffffeffffffff |   64 GB | EFI region mapping space
  ffffffff00000000 |   -4    GB | ffffffff7fffffff |    2 GB | ... unused hole

Documentation/x86/zero-page.txt

@@ -25,7 +25,7 @@ Offset	Proto	Name		Meaning
 0C8/004	ALL	ext_cmd_line_ptr  cmd_line_ptr high 32bits
 140/080	ALL	edid_info	Video mode setup (struct edid_info)
 1C0/020	ALL	efi_info	EFI 32 information (struct efi_info)
-1E0/004	ALL	alk_mem_k	Alternative mem check, in KB
+1E0/004	ALL	alt_mem_k	Alternative mem check, in KB
 1E4/004	ALL	scratch		Scratch field for the kernel setup code
 1E8/001	ALL	e820_entries	Number of entries in e820_table (below)
 1E9/001	ALL	eddbuf_entries	Number of entries in eddbuf (below)

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

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)
 

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);

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;
 }
 
 /*

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

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)
 

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)
 {

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.

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;
 

arch/x86/kernel/ldt.c

@@ -199,23 +199,14 @@ 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)
 {
 	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;
@@ -272,20 +258,50 @@ 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
 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;