x86 fixes

index 7178043b0e1d..59405a248fc2 100644
@@ -22,10 +22,6 @@ typedef struct {
 #ifdef CONFIG_SMP
 	unsigned int irq_resched_count;
 	unsigned int irq_call_count;
-	/*
-	 * irq_tlb_count is double-counted in irq_call_count, so it must be
-	 * subtracted from irq_call_count when displaying irq_call_count
-	 */
 	unsigned int irq_tlb_count;
 #endif
 #ifdef CONFIG_X86_THERMAL_VECTOR

index 7e8ec7ae10fa..1cc82ece9ac1 100644
@@ -145,7 +145,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
  *
  * |     ...            | 11| 10|  9|8|7|6|5| 4| 3|2|1|0| <- bit number
  * |     ...            |SW3|SW2|SW1|G|L|D|A|CD|WT|U|W|P| <- bit names
- * | OFFSET (14->63) | TYPE (10-13) |0|X|X|X| X| X|X|X|0| <- swp entry
+ * | OFFSET (14->63) | TYPE (9-13)  |0|X|X|X| X| X|X|X|0| <- swp entry
  *
  * G (8) is aliased and used as a PROT_NONE indicator for
  * !present ptes.  We need to start storing swap entries above

@@ -156,7 +156,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
 #define SWP_TYPE_FIRST_BIT (_PAGE_BIT_PROTNONE + 1)
 #define SWP_TYPE_BITS 5
 /* Place the offset above the type: */
-#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS + 1)
+#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS)
 
 #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)
 

index 9c6b890d5e7a..b2988c0ed829 100644
@@ -58,7 +58,15 @@ extern unsigned char boot_gdt[];
 extern unsigned char secondary_startup_64[];
 #endif
 
+static inline size_t real_mode_size_needed(void)
+{
+	if (real_mode_header)
+		return 0;	/* already allocated. */
+
+	return ALIGN(real_mode_blob_end - real_mode_blob, PAGE_SIZE);
+}
+
+void set_real_mode_mem(phys_addr_t mem, size_t size);
 void reserve_real_mode(void);
-void setup_real_mode(void);
 
 #endif /* _ARCH_X86_REALMODE_H */

index 4e5be94e079a..6fa85944af83 100644
@@ -135,7 +135,14 @@ static inline void cr4_set_bits_and_update_boot(unsigned long mask)
 
 static inline void __native_flush_tlb(void)
 {
+	/*
+	 * If current->mm == NULL then we borrow a mm which may change during a
+	 * task switch and therefore we must not be preempted while we write CR3
+	 * back:
+	 */
+	preempt_disable();
 	native_write_cr3(native_read_cr3());
+	preempt_enable();
 }
 
 static inline void __native_flush_tlb_global_irq_disabled(void)

index c852590254d5..e652a7cc6186 100644
@@ -79,7 +79,7 @@ struct uv_gam_range_entry {
 	u16	nasid;		/* HNasid */
 	u16	sockid;		/* Socket ID, high bits of APIC ID */
 	u16	pnode;		/* Index to MMR and GRU spaces */
-	u32	pxm;		/* ACPI proximity domain number */
+	u32	unused2;
 	u32	limit;		/* PA bits 56:26 (UV_GAM_RANGE_SHFT) */
 };
 

@@ -88,7 +88,8 @@ struct uv_gam_range_entry {
 #define	UV_SYSTAB_VERSION_UV4		0x400	/* UV4 BIOS base version */
 #define	UV_SYSTAB_VERSION_UV4_1		0x401	/* + gpa_shift */
 #define	UV_SYSTAB_VERSION_UV4_2		0x402	/* + TYPE_NVRAM/WINDOW/MBOX */
-#define	UV_SYSTAB_VERSION_UV4_LATEST	UV_SYSTAB_VERSION_UV4_2
+#define	UV_SYSTAB_VERSION_UV4_3		0x403	/* - GAM Range PXM Value */
+#define	UV_SYSTAB_VERSION_UV4_LATEST	UV_SYSTAB_VERSION_UV4_3
 
 #define	UV_SYSTAB_TYPE_UNUSED		0	/* End of table (offset == 0) */
 #define	UV_SYSTAB_TYPE_GAM_PARAMS	1	/* GAM PARAM conversions */

index 6368fa69d2af..54f35d988025 100644
@@ -155,7 +155,7 @@ static void init_x2apic_ldr(void)
 /*
  * At CPU state changes, update the x2apic cluster sibling info.
  */
-int x2apic_prepare_cpu(unsigned int cpu)
+static int x2apic_prepare_cpu(unsigned int cpu)
 {
 	if (!zalloc_cpumask_var(&per_cpu(cpus_in_cluster, cpu), GFP_KERNEL))
 		return -ENOMEM;

@@ -168,7 +168,7 @@ int x2apic_prepare_cpu(unsigned int cpu)
 	return 0;
 }
 
-int x2apic_dead_cpu(unsigned int this_cpu)
+static int x2apic_dead_cpu(unsigned int this_cpu)
 {
 	int cpu;
 

@@ -186,13 +186,18 @@ int x2apic_dead_cpu(unsigned int this_cpu)
 static int x2apic_cluster_probe(void)
 {
 	int cpu = smp_processor_id();
+	int ret;
 
 	if (!x2apic_mode)
 		return 0;
 
+	ret = cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "X2APIC_PREPARE",
+				x2apic_prepare_cpu, x2apic_dead_cpu);
+	if (ret < 0) {
+		pr_err("Failed to register X2APIC_PREPARE\n");
+		return 0;
+	}
 	cpumask_set_cpu(cpu, per_cpu(cpus_in_cluster, cpu));
-	cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "X2APIC_PREPARE",
-			  x2apic_prepare_cpu, x2apic_dead_cpu);
 	return 1;
 }
 

111 lines not on this page · raw message

165 lines not on this page · raw message

index 2dda0bc4576e..f16c55bfc090 100644
@@ -25,8 +25,6 @@ static void __init i386_default_early_setup(void)
 	/* Initialize 32bit specific setup functions */
 	x86_init.resources.reserve_resources = i386_reserve_resources;
 	x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc;
-
-	reserve_bios_regions();
 }
 
 asmlinkage __visible void __init i386_start_kernel(void)

index 99d48e7d2974..54a2372f5dbb 100644
@@ -183,7 +183,6 @@ void __init x86_64_start_reservations(char *real_mode_data)
 		copy_bootdata(__va(real_mode_data));
 
 	x86_early_init_platform_quirks();
-	reserve_bios_regions();
 
 	switch (boot_params.hdr.hardware_subarch) {
 	case X86_SUBARCH_INTEL_MID:

index 61521dc19c10..9f669fdd2010 100644
@@ -102,8 +102,7 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 	seq_puts(p, "  Rescheduling interrupts\n");
 	seq_printf(p, "%*s: ", prec, "CAL");
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", irq_stats(j)->irq_call_count -
-					irq_stats(j)->irq_tlb_count);
+		seq_printf(p, "%10u ", irq_stats(j)->irq_call_count);
 	seq_puts(p, "  Function call interrupts\n");
 	seq_printf(p, "%*s: ", prec, "TLB");
 	for_each_online_cpu(j)

index 991b77986d57..0fa60f5f5a16 100644
@@ -936,8 +936,6 @@ void __init setup_arch(char **cmdline_p)
 
 	x86_init.oem.arch_setup();
 
-	kernel_randomize_memory();
-
 	iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1;
 	setup_memory_map();
 	parse_setup_data();

@@ -1055,6 +1053,12 @@ void __init setup_arch(char **cmdline_p)
 
 	max_possible_pfn = max_pfn;
 
+	/*
+	 * Define random base addresses for memory sections after max_pfn is
+	 * defined and before each memory section base is used.
+	 */
+	kernel_randomize_memory();
+
 #ifdef CONFIG_X86_32
 	/* max_low_pfn get updated here */
 	find_low_pfn_range();

@@ -1097,6 +1101,8 @@ void __init setup_arch(char **cmdline_p)
 		efi_find_mirror();
 	}
 
+	reserve_bios_regions();
+
 	/*
 	 * The EFI specification says that boot service code won't be called
 	 * after ExitBootServices(). This is, in fact, a lie.

@@ -1125,7 +1131,15 @@ void __init setup_arch(char **cmdline_p)
 
 	early_trap_pf_init();
 
-	setup_real_mode();
+	/*
+	 * Update mmu_cr4_features (and, indirectly, trampoline_cr4_features)
+	 * with the current CR4 value.  This may not be necessary, but
+	 * auditing all the early-boot CR4 manipulation would be needed to
+	 * rule it out.
+	 */
+	if (boot_cpu_data.cpuid_level >= 0)
+		/* A CPU has %cr4 if and only if it has CPUID. */
+		mmu_cr4_features = __read_cr4();
 
 	memblock_set_current_limit(get_max_mapped());
 

@@ -1174,13 +1188,6 @@ void __init setup_arch(char **cmdline_p)
 
 	kasan_init();
 
-	if (boot_cpu_data.cpuid_level >= 0) {
-		/* A CPU has %cr4 if and only if it has CPUID */
-		mmu_cr4_features = __read_cr4();
-		if (trampoline_cr4_features)
-			*trampoline_cr4_features = mmu_cr4_features;
-	}
-
 #ifdef CONFIG_X86_32
 	/* sync back kernel address range */
 	clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,

index f7dfeda83e5c..121f59c6ee54 100644
@@ -19,7 +19,7 @@
 #include <asm/cpufeature.h>
 #include <asm/setup.h>
 
-#define debug_putstr(v) early_printk(v)
+#define debug_putstr(v) early_printk("%s", v)
 #define has_cpuflag(f) boot_cpu_has(f)
 #define get_boot_seed() kaslr_offset()
 #endif

index 620928903be3..d28a2d741f9e 100644
@@ -122,8 +122,18 @@ __ref void *alloc_low_pages(unsigned int num)
 	return __va(pfn << PAGE_SHIFT);
 }
 
-/* need 3 4k for initial PMD_SIZE,  3 4k for 0-ISA_END_ADDRESS */
-#define INIT_PGT_BUF_SIZE	(6 * PAGE_SIZE)
+/*
+ * By default need 3 4k for initial PMD_SIZE,  3 4k for 0-ISA_END_ADDRESS.
+ * With KASLR memory randomization, depending on the machine e820 memory
+ * and the PUD alignment. We may need twice more pages when KASLR memory
+ * randomization is enabled.
+ */
+#ifndef CONFIG_RANDOMIZE_MEMORY
+#define INIT_PGD_PAGE_COUNT      6
+#else
+#define INIT_PGD_PAGE_COUNT      12
+#endif
+#define INIT_PGT_BUF_SIZE	(INIT_PGD_PAGE_COUNT * PAGE_SIZE)
 RESERVE_BRK(early_pgt_alloc, INIT_PGT_BUF_SIZE);
 void  __init early_alloc_pgt_buf(void)
 {

index 26dccd6c0df1..ec8654f117d8 100644
@@ -97,7 +97,7 @@ void __init kernel_randomize_memory(void)
 	 * add padding if needed (especially for memory hotplug support).
 	 */
 	BUG_ON(kaslr_regions[0].base != &page_offset_base);
-	memory_tb = ((max_pfn << PAGE_SHIFT) >> TB_SHIFT) +
+	memory_tb = DIV_ROUND_UP(max_pfn << PAGE_SHIFT, 1UL << TB_SHIFT) +
 		CONFIG_RANDOMIZE_MEMORY_PHYSICAL_PADDING;
 
 	/* Adapt phyiscal memory region size based on available memory */

index 4480c06cade7..89d1146f5a6f 100644
@@ -254,6 +254,7 @@ void __init efi_free_boot_services(void)
 	for_each_efi_memory_desc(md) {
 		unsigned long long start = md->phys_addr;
 		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
+		size_t rm_size;
 
 		if (md->type != EFI_BOOT_SERVICES_CODE &&
 		    md->type != EFI_BOOT_SERVICES_DATA)

@@ -263,6 +264,26 @@ void __init efi_free_boot_services(void)
 		if (md->attribute & EFI_MEMORY_RUNTIME)
 			continue;
 
+		/*
+		 * Nasty quirk: if all sub-1MB memory is used for boot
+		 * services, we can get here without having allocated the
+		 * real mode trampoline.  It's too late to hand boot services
+		 * memory back to the memblock allocator, so instead
+		 * try to manually allocate the trampoline if needed.
+		 *
+		 * I've seen this on a Dell XPS 13 9350 with firmware
+		 * 1.4.4 with SGX enabled booting Linux via Fedora 24's
+		 * grub2-efi on a hard disk.  (And no, I don't know why
+		 * this happened, but Linux should still try to boot rather
+		 * panicing early.)
+		 */
+		rm_size = real_mode_size_needed();
+		if (rm_size && (start + rm_size) < (1<<20) && size >= rm_size) {
+			set_real_mode_mem(start, rm_size);
+			start += rm_size;
+			size -= rm_size;
+		}
+
 		free_bootmem_late(start, size);
 	}
 

index 66b2166ea4a1..4e9fd1378aec 100644
@@ -199,12 +199,14 @@ void uv_bios_init(void)
 		return;
 	}
 
+	/* Starting with UV4 the UV systab size is variable */
 	if (uv_systab->revision >= UV_SYSTAB_VERSION_UV4) {
+		int size = uv_systab->size;
+
 		iounmap(uv_systab);
-		uv_systab = ioremap(efi.uv_systab, uv_systab->size);
+		uv_systab = ioremap(efi.uv_systab, size);
 		if (!uv_systab) {
-			pr_err("UV: UVsystab: ioremap(%d) failed!\n",
-				uv_systab->size);
+			pr_err("UV: UVsystab: ioremap(%d) failed!\n", size);
 			return;
 		}
 	}

90 lines not on this page · raw message