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

Pull x86 fixes from Thomas Gleixner:

 - the high latency PIT detection fix, which slipped through the cracks
   for rc1

 - a regression fix for the early printk mechanism

 - the x86 part to plug irq/vector related hotplug races

 - move the allocation of the espfix pages on cpu hotplug to non atomic
   context.  The current code triggers a might_sleep() warning.

 - a series of KASAN fixes addressing boot crashes and usability

 - a trivial typo fix for Kconfig help text

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/kconfig: Fix typo in the CONFIG_CMDLINE_BOOL help text
  x86/irq: Retrieve irq data after locking irq_desc
  x86/irq: Use proper locking in check_irq_vectors_for_cpu_disable()
  x86/irq: Plug irq vector hotplug race
  x86/earlyprintk: Allow early_printk() to use console style parameters like '115200n8'
  x86/espfix: Init espfix on the boot CPU side
  x86/espfix: Add 'cpu' parameter to init_espfix_ap()
  x86/kasan: Move KASAN_SHADOW_OFFSET to the arch Kconfig
  x86/kasan: Add message about KASAN being initialized
  x86/kasan: Fix boot crash on AMD processors
  x86/kasan: Flush TLBs after switching CR3
  x86/kasan: Fix KASAN shadow region page tables
  x86/init: Clear 'init_level4_pgt' earlier
  x86/tsc: Let high latency PIT fail fast in quick_pit_calibrate()

arch/x86/Kconfig

@@ -254,6 +254,11 @@ config ARCH_SUPPORTS_OPTIMIZED_INLINING
 config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	def_bool y
 
+config KASAN_SHADOW_OFFSET
+	hex
+	depends on KASAN
+	default 0xdffffc0000000000
+
 config HAVE_INTEL_TXT
 	def_bool y
 	depends on INTEL_IOMMU && ACPI
@@ -2015,7 +2020,7 @@ config CMDLINE_BOOL
 
 	  To compile command line arguments into the kernel,
 	  set this option to 'Y', then fill in the
-	  the boot arguments in CONFIG_CMDLINE.
+	  boot arguments in CONFIG_CMDLINE.
 
 	  Systems with fully functional boot loaders (i.e. non-embedded)
 	  should leave this option set to 'N'.

arch/x86/include/asm/espfix.h

@@ -9,7 +9,7 @@ DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack);
 DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
 
 extern void init_espfix_bsp(void);
-extern void init_espfix_ap(void);
+extern void init_espfix_ap(int cpu);
 
 #endif /* CONFIG_X86_64 */
 

arch/x86/include/asm/kasan.h

@@ -14,15 +14,11 @@
 
 #ifndef __ASSEMBLY__
 
-extern pte_t kasan_zero_pte[];
-extern pte_t kasan_zero_pmd[];
-extern pte_t kasan_zero_pud[];
-
 #ifdef CONFIG_KASAN
-void __init kasan_map_early_shadow(pgd_t *pgd);
+void __init kasan_early_init(void);
 void __init kasan_init(void);
 #else
-static inline void kasan_map_early_shadow(pgd_t *pgd) { }
+static inline void kasan_early_init(void) { }
 static inline void kasan_init(void) { }
 #endif
 

arch/x86/kernel/apic/vector.c

@@ -409,12 +409,6 @@ static void __setup_vector_irq(int cpu)
 	int irq, vector;
 	struct apic_chip_data *data;
 
-	/*
-	 * vector_lock will make sure that we don't run into irq vector
-	 * assignments that might be happening on another cpu in parallel,
-	 * while we setup our initial vector to irq mappings.
-	 */
-	raw_spin_lock(&vector_lock);
 	/* Mark the inuse vectors */
 	for_each_active_irq(irq) {
 		data = apic_chip_data(irq_get_irq_data(irq));
@@ -436,16 +430,16 @@ static void __setup_vector_irq(int cpu)
 		if (!cpumask_test_cpu(cpu, data->domain))
 			per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
 	}
-	raw_spin_unlock(&vector_lock);
 }
 
 /*
- * Setup the vector to irq mappings.
+ * Setup the vector to irq mappings. Must be called with vector_lock held.
  */
 void setup_vector_irq(int cpu)
 {
 	int irq;
 
+	lockdep_assert_held(&vector_lock);
 	/*
 	 * On most of the platforms, legacy PIC delivers the interrupts on the
 	 * boot cpu. But there are certain platforms where PIC interrupts are

arch/x86/kernel/early_printk.c

@@ -175,7 +175,9 @@ static __init void early_serial_init(char *s)
 	}
 
 	if (*s) {
-		if (kstrtoul(s, 0, &baud) < 0 || baud == 0)
+		baud = simple_strtoull(s, &e, 0);
+
+		if (baud == 0 || s == e)
 			baud = DEFAULT_BAUD;
 	}
 

arch/x86/kernel/espfix_64.c

@@ -131,25 +131,24 @@ void __init init_espfix_bsp(void)
 	init_espfix_random();
 
 	/* The rest is the same as for any other processor */
-	init_espfix_ap();
+	init_espfix_ap(0);
 }
 
-void init_espfix_ap(void)
+void init_espfix_ap(int cpu)
 {
-	unsigned int cpu, page;
+	unsigned int page;
 	unsigned long addr;
 	pud_t pud, *pud_p;
 	pmd_t pmd, *pmd_p;
 	pte_t pte, *pte_p;
-	int n;
+	int n, node;
 	void *stack_page;
 	pteval_t ptemask;
 
 	/* We only have to do this once... */
-	if (likely(this_cpu_read(espfix_stack)))
+	if (likely(per_cpu(espfix_stack, cpu)))
 		return;		/* Already initialized */
 
-	cpu = smp_processor_id();
 	addr = espfix_base_addr(cpu);
 	page = cpu/ESPFIX_STACKS_PER_PAGE;
 
@@ -165,12 +164,15 @@ void init_espfix_ap(void)
 	if (stack_page)
 		goto unlock_done;
 
+	node = cpu_to_node(cpu);
 	ptemask = __supported_pte_mask;
 
 	pud_p = &espfix_pud_page[pud_index(addr)];
 	pud = *pud_p;
 	if (!pud_present(pud)) {
-		pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP);
+		struct page *page = alloc_pages_node(node, PGALLOC_GFP, 0);
+
+		pmd_p = (pmd_t *)page_address(page);
 		pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask));
 		paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT);
 		for (n = 0; n < ESPFIX_PUD_CLONES; n++)
@@ -180,7 +182,9 @@ void init_espfix_ap(void)
 	pmd_p = pmd_offset(&pud, addr);
 	pmd = *pmd_p;
 	if (!pmd_present(pmd)) {
-		pte_p = (pte_t *)__get_free_page(PGALLOC_GFP);
+		struct page *page = alloc_pages_node(node, PGALLOC_GFP, 0);
+
+		pte_p = (pte_t *)page_address(page);
 		pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask));
 		paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT);
 		for (n = 0; n < ESPFIX_PMD_CLONES; n++)
@@ -188,7 +192,7 @@ void init_espfix_ap(void)
 	}
 
 	pte_p = pte_offset_kernel(&pmd, addr);
-	stack_page = (void *)__get_free_page(GFP_KERNEL);
+	stack_page = page_address(alloc_pages_node(node, GFP_KERNEL, 0));
 	pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask));
 	for (n = 0; n < ESPFIX_PTE_CLONES; n++)
 		set_pte(&pte_p[n*PTE_STRIDE], pte);
@@ -199,7 +203,7 @@ void init_espfix_ap(void)
 unlock_done:
 	mutex_unlock(&espfix_init_mutex);
 done:
-	this_cpu_write(espfix_stack, addr);
-	this_cpu_write(espfix_waddr, (unsigned long)stack_page
-		       + (addr & ~PAGE_MASK));
+	per_cpu(espfix_stack, cpu) = addr;
+	per_cpu(espfix_waddr, cpu) = (unsigned long)stack_page
+				      + (addr & ~PAGE_MASK);
 }

arch/x86/kernel/head64.c

@@ -161,11 +161,12 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
 	/* Kill off the identity-map trampoline */
 	reset_early_page_tables();
 
-	kasan_map_early_shadow(early_level4_pgt);
-
-	/* clear bss before set_intr_gate with early_idt_handler */
 	clear_bss();
 
+	clear_page(init_level4_pgt);
+
+	kasan_early_init();
+
 	for (i = 0; i < NUM_EXCEPTION_VECTORS; i++)
 		set_intr_gate(i, early_idt_handler_array[i]);
 	load_idt((const struct desc_ptr *)&idt_descr);
@@ -177,12 +178,9 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
 	 */
 	load_ucode_bsp();
 
-	clear_page(init_level4_pgt);
 	/* set init_level4_pgt kernel high mapping*/
 	init_level4_pgt[511] = early_level4_pgt[511];
 
-	kasan_map_early_shadow(init_level4_pgt);
-
 	x86_64_start_reservations(real_mode_data);
 }
 

arch/x86/kernel/head_64.S

@@ -516,38 +516,9 @@ ENTRY(phys_base)
 	/* This must match the first entry in level2_kernel_pgt */
 	.quad   0x0000000000000000
 
-#ifdef CONFIG_KASAN
-#define FILL(VAL, COUNT)				\
-	.rept (COUNT) ;					\
-	.quad	(VAL) ;					\
-	.endr
-
-NEXT_PAGE(kasan_zero_pte)
-	FILL(kasan_zero_page - __START_KERNEL_map + _KERNPG_TABLE, 512)
-NEXT_PAGE(kasan_zero_pmd)
-	FILL(kasan_zero_pte - __START_KERNEL_map + _KERNPG_TABLE, 512)
-NEXT_PAGE(kasan_zero_pud)
-	FILL(kasan_zero_pmd - __START_KERNEL_map + _KERNPG_TABLE, 512)
-
-#undef FILL
-#endif
-
-
 #include "../../x86/xen/xen-head.S"
 	
 	__PAGE_ALIGNED_BSS
 NEXT_PAGE(empty_zero_page)
 	.skip PAGE_SIZE
 
-#ifdef CONFIG_KASAN
-/*
- * This page used as early shadow. We don't use empty_zero_page
- * at early stages, stack instrumentation could write some garbage
- * to this page.
- * Latter we reuse it as zero shadow for large ranges of memory
- * that allowed to access, but not instrumented by kasan
- * (vmalloc/vmemmap ...).
- */
-NEXT_PAGE(kasan_zero_page)
-	.skip PAGE_SIZE
-#endif

arch/x86/kernel/irq.c

@@ -347,14 +347,22 @@ int check_irq_vectors_for_cpu_disable(void)
 			if (!desc)
 				continue;
 
+			/*
+			 * Protect against concurrent action removal,
+			 * affinity changes etc.
+			 */
+			raw_spin_lock(&desc->lock);
 			data = irq_desc_get_irq_data(desc);
 			cpumask_copy(&affinity_new, data->affinity);
 			cpumask_clear_cpu(this_cpu, &affinity_new);
 
 			/* Do not count inactive or per-cpu irqs. */
-			if (!irq_has_action(irq) || irqd_is_per_cpu(data))
+			if (!irq_has_action(irq) || irqd_is_per_cpu(data)) {
+				raw_spin_unlock(&desc->lock);
 				continue;
+			}
 
+			raw_spin_unlock(&desc->lock);
 			/*
 			 * A single irq may be mapped to multiple
 			 * cpu's vector_irq[] (for example IOAPIC cluster
@@ -385,6 +393,9 @@ int check_irq_vectors_for_cpu_disable(void)
 		 * vector. If the vector is marked in the used vectors
 		 * bitmap or an irq is assigned to it, we don't count
 		 * it as available.
+		 *
+		 * As this is an inaccurate snapshot anyway, we can do
+		 * this w/o holding vector_lock.
 		 */
 		for (vector = FIRST_EXTERNAL_VECTOR;
 		     vector < first_system_vector; vector++) {
@@ -486,6 +497,11 @@ void fixup_irqs(void)
 	 */
 	mdelay(1);
 
+	/*
+	 * We can walk the vector array of this cpu without holding
+	 * vector_lock because the cpu is already marked !online, so
+	 * nothing else will touch it.
+	 */
 	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
 		unsigned int irr;
 
@@ -497,9 +513,9 @@ void fixup_irqs(void)
 			irq = __this_cpu_read(vector_irq[vector]);
 
 			desc = irq_to_desc(irq);
+			raw_spin_lock(&desc->lock);
 			data = irq_desc_get_irq_data(desc);
 			chip = irq_data_get_irq_chip(data);
-			raw_spin_lock(&desc->lock);
 			if (chip->irq_retrigger) {
 				chip->irq_retrigger(data);
 				__this_cpu_write(vector_irq[vector], VECTOR_RETRIGGERED);

arch/x86/kernel/smpboot.c

@@ -170,11 +170,6 @@ static void smp_callin(void)
 	 */
 	apic_ap_setup();
 
-	/*
-	 * Need to setup vector mappings before we enable interrupts.
-	 */
-	setup_vector_irq(smp_processor_id());
-
 	/*
 	 * Save our processor parameters. Note: this information
 	 * is needed for clock calibration.
@@ -239,18 +234,13 @@ static void notrace start_secondary(void *unused)
 	check_tsc_sync_target();
 
 	/*
-	 * Enable the espfix hack for this CPU
-	 */
-#ifdef CONFIG_X86_ESPFIX64
-	init_espfix_ap();
-#endif
-
-	/*
-	 * We need to hold vector_lock so there the set of online cpus
-	 * does not change while we are assigning vectors to cpus.  Holding
-	 * this lock ensures we don't half assign or remove an irq from a cpu.
+	 * Lock vector_lock and initialize the vectors on this cpu
+	 * before setting the cpu online. We must set it online with
+	 * vector_lock held to prevent a concurrent setup/teardown
+	 * from seeing a half valid vector space.
 	 */
 	lock_vector_lock();
+	setup_vector_irq(smp_processor_id());
 	set_cpu_online(smp_processor_id(), true);
 	unlock_vector_lock();
 	cpu_set_state_online(smp_processor_id());
@@ -854,6 +844,13 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 	initial_code = (unsigned long)start_secondary;
 	stack_start  = idle->thread.sp;
 
+	/*
+	 * Enable the espfix hack for this CPU
+	*/
+#ifdef CONFIG_X86_ESPFIX64
+	init_espfix_ap(cpu);
+#endif
+
 	/* So we see what's up */
 	announce_cpu(cpu, apicid);
 

arch/x86/kernel/tsc.c

@@ -598,10 +598,19 @@ static unsigned long quick_pit_calibrate(void)
 			if (!pit_expect_msb(0xff-i, &delta, &d2))
 				break;
 
+			delta -= tsc;
+
+			/*
+			 * Extrapolate the error and fail fast if the error will
+			 * never be below 500 ppm.
+			 */
+			if (i == 1 &&
+			    d1 + d2 >= (delta * MAX_QUICK_PIT_ITERATIONS) >> 11)
+				return 0;
+
 			/*
 			 * Iterate until the error is less than 500 ppm
 			 */
-			delta -= tsc;
 			if (d1+d2 >= delta >> 11)
 				continue;
 

arch/x86/mm/kasan_init_64.c

+#define pr_fmt(fmt) "kasan: " fmt
 #include <linux/bootmem.h>
 #include <linux/kasan.h>
 #include <linux/kdebug.h>
@@ -11,7 +12,19 @@
 extern pgd_t early_level4_pgt[PTRS_PER_PGD];
 extern struct range pfn_mapped[E820_X_MAX];
 
-extern unsigned char kasan_zero_page[PAGE_SIZE];
+static pud_t kasan_zero_pud[PTRS_PER_PUD] __page_aligned_bss;
+static pmd_t kasan_zero_pmd[PTRS_PER_PMD] __page_aligned_bss;
+static pte_t kasan_zero_pte[PTRS_PER_PTE] __page_aligned_bss;
+
+/*
+ * This page used as early shadow. We don't use empty_zero_page
+ * at early stages, stack instrumentation could write some garbage
+ * to this page.
+ * Latter we reuse it as zero shadow for large ranges of memory
+ * that allowed to access, but not instrumented by kasan
+ * (vmalloc/vmemmap ...).
+ */
+static unsigned char kasan_zero_page[PAGE_SIZE] __page_aligned_bss;
 
 static int __init map_range(struct range *range)
 {
@@ -36,7 +49,7 @@ static void __init clear_pgds(unsigned long start,
 		pgd_clear(pgd_offset_k(start));
 }
 
-void __init kasan_map_early_shadow(pgd_t *pgd)
+static void __init kasan_map_early_shadow(pgd_t *pgd)
 {
 	int i;
 	unsigned long start = KASAN_SHADOW_START;
@@ -73,7 +86,7 @@ static int __init zero_pmd_populate(pud_t *pud, unsigned long addr,
 	while (IS_ALIGNED(addr, PMD_SIZE) && addr + PMD_SIZE <= end) {
 		WARN_ON(!pmd_none(*pmd));
 		set_pmd(pmd, __pmd(__pa_nodebug(kasan_zero_pte)
-					| __PAGE_KERNEL_RO));
+					| _KERNPG_TABLE));
 		addr += PMD_SIZE;
 		pmd = pmd_offset(pud, addr);
 	}
@@ -99,7 +112,7 @@ static int __init zero_pud_populate(pgd_t *pgd, unsigned long addr,
 	while (IS_ALIGNED(addr, PUD_SIZE) && addr + PUD_SIZE <= end) {
 		WARN_ON(!pud_none(*pud));
 		set_pud(pud, __pud(__pa_nodebug(kasan_zero_pmd)
-					| __PAGE_KERNEL_RO));
+					| _KERNPG_TABLE));
 		addr += PUD_SIZE;
 		pud = pud_offset(pgd, addr);
 	}
@@ -124,7 +137,7 @@ static int __init zero_pgd_populate(unsigned long addr, unsigned long end)
 	while (IS_ALIGNED(addr, PGDIR_SIZE) && addr + PGDIR_SIZE <= end) {
 		WARN_ON(!pgd_none(*pgd));
 		set_pgd(pgd, __pgd(__pa_nodebug(kasan_zero_pud)
-					| __PAGE_KERNEL_RO));
+					| _KERNPG_TABLE));
 		addr += PGDIR_SIZE;
 		pgd = pgd_offset_k(addr);
 	}
@@ -166,6 +179,26 @@ static struct notifier_block kasan_die_notifier = {
 };
 #endif
 
+void __init kasan_early_init(void)
+{
+	int i;
+	pteval_t pte_val = __pa_nodebug(kasan_zero_page) | __PAGE_KERNEL;
+	pmdval_t pmd_val = __pa_nodebug(kasan_zero_pte) | _KERNPG_TABLE;
+	pudval_t pud_val = __pa_nodebug(kasan_zero_pmd) | _KERNPG_TABLE;
+
+	for (i = 0; i < PTRS_PER_PTE; i++)
+		kasan_zero_pte[i] = __pte(pte_val);
+
+	for (i = 0; i < PTRS_PER_PMD; i++)
+		kasan_zero_pmd[i] = __pmd(pmd_val);
+
+	for (i = 0; i < PTRS_PER_PUD; i++)
+		kasan_zero_pud[i] = __pud(pud_val);
+
+	kasan_map_early_shadow(early_level4_pgt);
+	kasan_map_early_shadow(init_level4_pgt);
+}
+
 void __init kasan_init(void)
 {
 	int i;
@@ -176,6 +209,7 @@ void __init kasan_init(void)
 
 	memcpy(early_level4_pgt, init_level4_pgt, sizeof(early_level4_pgt));
 	load_cr3(early_level4_pgt);
+	__flush_tlb_all();
 
 	clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END);
 
@@ -202,5 +236,8 @@ void __init kasan_init(void)
 	memset(kasan_zero_page, 0, PAGE_SIZE);
 
 	load_cr3(init_level4_pgt);
+	__flush_tlb_all();
 	init_task.kasan_depth = 0;
+
+	pr_info("Kernel address sanitizer initialized\n");
 }

lib/Kconfig.kasan

@@ -18,10 +18,6 @@ config KASAN
 	  For better error detection enable CONFIG_STACKTRACE,
 	  and add slub_debug=U to boot cmdline.
 
-config KASAN_SHADOW_OFFSET
-	hex
-	default 0xdffffc0000000000 if X86_64
-
 choice
 	prompt "Instrumentation type"
 	depends on KASAN