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 couple of fixes addressing the following issues:

   - The last polishing for the TLB code, removing the last BUG_ON() and
     the debug file along with tidying up the lazy TLB code.

   - Prevent triple fault on 1st Gen. 486 caused by stupidly calling the
     early IDT setup after the first function which causes a fault which
     should be caught by the exception table.

   - Limit the mmap of /dev/mem to valid addresses

   - Prevent late microcode loading on Broadwell X

   - Remove a redundant assignment in the cache info code"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mm: Limit mmap() of /dev/mem to valid physical addresses
  x86/mm: Remove debug/x86/tlb_defer_switch_to_init_mm
  x86/mm: Tidy up "x86/mm: Flush more aggressively in lazy TLB mode"
  x86/mm/64: Remove the last VM_BUG_ON() from the TLB code
  x86/microcode/intel: Disable late loading on model 79
  x86/idt: Initialize early IDT before cr4_init_shadow()
  x86/cpu/intel_cacheinfo: Remove redundant assignment to 'this_leaf'

7 files changed, 59 insertions, 67 deletions

diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index c40a95c33bb8..322d25ae23ab 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -110,6 +110,10 @@ build_mmio_write(__writeq, "q", unsigned long, "r", )
 
 #endif
 
+#define ARCH_HAS_VALID_PHYS_ADDR_RANGE
+extern int valid_phys_addr_range(phys_addr_t addr, size_t size);
+extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size);
+
 /**
  *	virt_to_phys	-	map virtual addresses to physical
  *	@address: address to remap
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index d362161d3291..c4aed0de565e 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -82,12 +82,21 @@ static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
 #define __flush_tlb_single(addr) __native_flush_tlb_single(addr)
 #endif
 
-/*
- * If tlb_use_lazy_mode is true, then we try to avoid switching CR3 to point
- * to init_mm when we switch to a kernel thread (e.g. the idle thread).  If
- * it's false, then we immediately switch CR3 when entering a kernel thread.
- */
-DECLARE_STATIC_KEY_TRUE(tlb_use_lazy_mode);
+static inline bool tlb_defer_switch_to_init_mm(void)
+{
+	/*
+	 * If we have PCID, then switching to init_mm is reasonably
+	 * fast.  If we don't have PCID, then switching to init_mm is
+	 * quite slow, so we try to defer it in the hopes that we can
+	 * avoid it entirely.  The latter approach runs the risk of
+	 * receiving otherwise unnecessary IPIs.
+	 *
+	 * This choice is just a heuristic.  The tlb code can handle this
+	 * function returning true or false regardless of whether we have
+	 * PCID.
+	 */
+	return !static_cpu_has(X86_FEATURE_PCID);
+}
 
 /*
  * 6 because 6 should be plenty and struct tlb_state will fit in
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 24f749324c0f..9990a71e311f 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -831,7 +831,6 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index,
 	} else if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
 		unsigned int apicid, nshared, first, last;
 
-		this_leaf = this_cpu_ci->info_list + index;
 		nshared = base->eax.split.num_threads_sharing + 1;
 		apicid = cpu_data(cpu).apicid;
 		first = apicid - (apicid % nshared);
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 8f7a9bbad514..7dbcb7adf797 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -34,6 +34,7 @@
 #include <linux/mm.h>
 
 #include <asm/microcode_intel.h>
+#include <asm/intel-family.h>
 #include <asm/processor.h>
 #include <asm/tlbflush.h>
 #include <asm/setup.h>
@@ -918,6 +919,18 @@ static int get_ucode_fw(void *to, const void *from, size_t n)
 	return 0;
 }
 
+static bool is_blacklisted(unsigned int cpu)
+{
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+	if (c->x86 == 6 && c->x86_model == INTEL_FAM6_BROADWELL_X) {
+		pr_err_once("late loading on model 79 is disabled.\n");
+		return true;
+	}
+
+	return false;
+}
+
 static enum ucode_state request_microcode_fw(int cpu, struct device *device,
 					     bool refresh_fw)
 {
@@ -926,6 +939,9 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device,
 	const struct firmware *firmware;
 	enum ucode_state ret;
 
+	if (is_blacklisted(cpu))
+		return UCODE_NFOUND;
+
 	sprintf(name, "intel-ucode/%02x-%02x-%02x",
 		c->x86, c->x86_model, c->x86_mask);
 
@@ -950,6 +966,9 @@ static int get_ucode_user(void *to, const void *from, size_t n)
 static enum ucode_state
 request_microcode_user(int cpu, const void __user *buf, size_t size)
 {
+	if (is_blacklisted(cpu))
+		return UCODE_NFOUND;
+
 	return generic_load_microcode(cpu, (void *)buf, size, &get_ucode_user);
 }
 
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index cf2ce063f65a..2902ca4d5993 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -30,10 +30,11 @@ static void __init i386_default_early_setup(void)
 
 asmlinkage __visible void __init i386_start_kernel(void)
 {
-	cr4_init_shadow();
-
+	/* Make sure IDT is set up before any exception happens */
 	idt_setup_early_handler();
 
+	cr4_init_shadow();
+
 	sanitize_boot_params(&boot_params);
 
 	x86_early_init_platform_quirks();
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index a99679826846..320c6237e1d1 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -174,3 +174,15 @@ const char *arch_vma_name(struct vm_area_struct *vma)
 		return "[mpx]";
 	return NULL;
 }
+
+int valid_phys_addr_range(phys_addr_t addr, size_t count)
+{
+	return addr + count <= __pa(high_memory);
+}
+
+int valid_mmap_phys_addr_range(unsigned long pfn, size_t count)
+{
+	phys_addr_t addr = (phys_addr_t)pfn << PAGE_SHIFT;
+
+	return valid_phys_addr_range(addr, count);
+}
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 658bf0090565..0f3d0cea4d00 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -30,7 +30,6 @@
 
 atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1);
 
-DEFINE_STATIC_KEY_TRUE(tlb_use_lazy_mode);
 
 static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
 			    u16 *new_asid, bool *need_flush)
@@ -147,8 +146,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 	this_cpu_write(cpu_tlbstate.is_lazy, false);
 
 	if (real_prev == next) {
-		VM_BUG_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
-			  next->context.ctx_id);
+		VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
+			   next->context.ctx_id);
 
 		/*
 		 * We don't currently support having a real mm loaded without
@@ -213,6 +212,9 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 }
 
 /*
+ * Please ignore the name of this function.  It should be called
+ * switch_to_kernel_thread().
+ *
  * enter_lazy_tlb() is a hint from the scheduler that we are entering a
  * kernel thread or other context without an mm.  Acceptable implementations
  * include doing nothing whatsoever, switching to init_mm, or various clever
@@ -227,7 +229,7 @@ void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 	if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm)
 		return;
 
-	if (static_branch_unlikely(&tlb_use_lazy_mode)) {
+	if (tlb_defer_switch_to_init_mm()) {
 		/*
 		 * There's a significant optimization that may be possible
 		 * here.  We have accurate enough TLB flush tracking that we
@@ -626,57 +628,3 @@ static int __init create_tlb_single_page_flush_ceiling(void)
 	return 0;
 }
 late_initcall(create_tlb_single_page_flush_ceiling);
-
-static ssize_t tlblazy_read_file(struct file *file, char __user *user_buf,
-				 size_t count, loff_t *ppos)
-{
-	char buf[2];
-
-	buf[0] = static_branch_likely(&tlb_use_lazy_mode) ? '1' : '0';
-	buf[1] = '\n';
-
-	return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
-}
-
-static ssize_t tlblazy_write_file(struct file *file,
-		 const char __user *user_buf, size_t count, loff_t *ppos)
-{
-	bool val;
-
-	if (kstrtobool_from_user(user_buf, count, &val))
-		return -EINVAL;
-
-	if (val)
-		static_branch_enable(&tlb_use_lazy_mode);
-	else
-		static_branch_disable(&tlb_use_lazy_mode);
-
-	return count;
-}
-
-static const struct file_operations fops_tlblazy = {
-	.read = tlblazy_read_file,
-	.write = tlblazy_write_file,
-	.llseek = default_llseek,
-};
-
-static int __init init_tlb_use_lazy_mode(void)
-{
-	if (boot_cpu_has(X86_FEATURE_PCID)) {
-		/*
-		 * Heuristic: with PCID on, switching to and from
-		 * init_mm is reasonably fast, but remote flush IPIs
-		 * as expensive as ever, so turn off lazy TLB mode.
-		 *
-		 * We can't do this in setup_pcid() because static keys
-		 * haven't been initialized yet, and it would blow up
-		 * badly.
-		 */
-		static_branch_disable(&tlb_use_lazy_mode);
-	}
-
-	debugfs_create_file("tlb_use_lazy_mode", S_IRUSR | S_IWUSR,
-			    arch_debugfs_dir, NULL, &fops_tlblazy);
-	return 0;
-}
-late_initcall(init_tlb_use_lazy_mode);