5 files changed, 61 insertions, 101 deletions

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;
 }