Merge branches 'x86-efi-for-linus', 'x86-gart-for-linus', 'x86-irq-fo…

…r-linus' and 'x86-mce-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86-efi-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86, efi: Ensure that the entirity of a region is mapped
  x86, efi: Pass a minimal map to SetVirtualAddressMap()
  x86, efi: Merge contiguous memory regions of the same type and attribute
  x86, efi: Consolidate EFI nx control
  x86, efi: Remove virtual-mode SetVirtualAddressMap call

* 'x86-gart-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86, gart: Don't enforce GART aperture lower-bound by alignment

* 'x86-irq-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86: Don't unmask disabled irqs when migrating them
  x86: Skip migrating IRQF_PER_CPU irqs in fixup_irqs()

* 'x86-mce-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86, mce: Drop the default decoding notifier
  x86, MCE: Do not taint when handling correctable errors

arch/x86/include/asm/efi.h

@@ -90,6 +90,7 @@ extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
 #endif /* CONFIG_X86_32 */
 
 extern int add_efi_memmap;
+extern void efi_set_executable(efi_memory_desc_t *md, bool executable);
 extern void efi_memblock_x86_reserve_range(void);
 extern void efi_call_phys_prelog(void);
 extern void efi_call_phys_epilog(void);

arch/x86/include/asm/mce.h

@@ -142,8 +142,6 @@ static inline void winchip_mcheck_init(struct cpuinfo_x86 *c) {}
 static inline void enable_p5_mce(void) {}
 #endif
 
-extern void (*x86_mce_decode_callback)(struct mce *m);
-
 void mce_setup(struct mce *m);
 void mce_log(struct mce *m);
 DECLARE_PER_CPU(struct sys_device, mce_dev);

arch/x86/kernel/aperture_64.c

@@ -30,6 +30,22 @@
 #include <asm/amd_nb.h>
 #include <asm/x86_init.h>
 
+/*
+ * Using 512M as goal, in case kexec will load kernel_big
+ * that will do the on-position decompress, and could overlap with
+ * with the gart aperture that is used.
+ * Sequence:
+ * kernel_small
+ * ==> kexec (with kdump trigger path or gart still enabled)
+ * ==> kernel_small (gart area become e820_reserved)
+ * ==> kexec (with kdump trigger path or gart still enabled)
+ * ==> kerne_big (uncompressed size will be big than 64M or 128M)
+ * So don't use 512M below as gart iommu, leave the space for kernel
+ * code for safe.
+ */
+#define GART_MIN_ADDR	(512ULL << 20)
+#define GART_MAX_ADDR	(1ULL   << 32)
+
 int gart_iommu_aperture;
 int gart_iommu_aperture_disabled __initdata;
 int gart_iommu_aperture_allowed __initdata;
@@ -70,21 +86,9 @@ static u32 __init allocate_aperture(void)
 	 * memory. Unfortunately we cannot move it up because that would
 	 * make the IOMMU useless.
 	 */
-	/*
-	 * using 512M as goal, in case kexec will load kernel_big
-	 * that will do the on position decompress, and  could overlap with
-	 * that position with gart that is used.
-	 * sequende:
-	 * kernel_small
-	 * ==> kexec (with kdump trigger path or previous doesn't shutdown gart)
-	 * ==> kernel_small(gart area become e820_reserved)
-	 * ==> kexec (with kdump trigger path or previous doesn't shutdown gart)
-	 * ==> kerne_big (uncompressed size will be big than 64M or 128M)
-	 * so don't use 512M below as gart iommu, leave the space for kernel
-	 * code for safe
-	 */
-	addr = memblock_find_in_range(0, 1ULL<<32, aper_size, 512ULL<<20);
-	if (addr == MEMBLOCK_ERROR || addr + aper_size > 0xffffffff) {
+	addr = memblock_find_in_range(GART_MIN_ADDR, GART_MAX_ADDR,
+				      aper_size, aper_size);
+	if (addr == MEMBLOCK_ERROR || addr + aper_size > GART_MAX_ADDR) {
 		printk(KERN_ERR
 			"Cannot allocate aperture memory hole (%lx,%uK)\n",
 				addr, aper_size>>10);

arch/x86/kernel/cpu/mcheck/mce.c

@@ -105,20 +105,6 @@ static int			cpu_missing;
 ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
 EXPORT_SYMBOL_GPL(x86_mce_decoder_chain);
 
-static int default_decode_mce(struct notifier_block *nb, unsigned long val,
-			       void *data)
-{
-	pr_emerg(HW_ERR "No human readable MCE decoding support on this CPU type.\n");
-	pr_emerg(HW_ERR "Run the message through 'mcelog --ascii' to decode.\n");
-
-	return NOTIFY_STOP;
-}
-
-static struct notifier_block mce_dec_nb = {
-	.notifier_call = default_decode_mce,
-	.priority      = -1,
-};
-
 /* MCA banks polled by the period polling timer for corrected events */
 DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
 	[0 ... BITS_TO_LONGS(MAX_NR_BANKS)-1] = ~0UL
@@ -212,6 +198,8 @@ void mce_log(struct mce *mce)
 
 static void print_mce(struct mce *m)
 {
+	int ret = 0;
+
 	pr_emerg(HW_ERR "CPU %d: Machine Check Exception: %Lx Bank %d: %016Lx\n",
 	       m->extcpu, m->mcgstatus, m->bank, m->status);
 
@@ -239,7 +227,11 @@ static void print_mce(struct mce *m)
 	 * Print out human-readable details about the MCE error,
 	 * (if the CPU has an implementation for that)
 	 */
-	atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
+	ret = atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
+	if (ret == NOTIFY_STOP)
+		return;
+
+	pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n");
 }
 
 #define PANIC_TIMEOUT 5 /* 5 seconds */
@@ -590,7 +582,6 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 		if (!(flags & MCP_DONTLOG) && !mce_dont_log_ce) {
 			mce_log(&m);
 			atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, &m);
-			add_taint(TAINT_MACHINE_CHECK);
 		}
 
 		/*
@@ -1722,8 +1713,6 @@ __setup("mce", mcheck_enable);
 
 int __init mcheck_init(void)
 {
-	atomic_notifier_chain_register(&x86_mce_decoder_chain, &mce_dec_nb);
-
 	mcheck_intel_therm_init();
 
 	return 0;

arch/x86/kernel/cpu/mcheck/therm_throt.c

@@ -187,8 +187,6 @@ static int therm_throt_process(bool new_event, int event, int level)
 				this_cpu,
 				level == CORE_LEVEL ? "Core" : "Package",
 				state->count);
-
-		add_taint(TAINT_MACHINE_CHECK);
 		return 1;
 	}
 	if (old_event) {
@@ -393,7 +391,6 @@ static void unexpected_thermal_interrupt(void)
 {
 	printk(KERN_ERR "CPU%d: Unexpected LVT thermal interrupt!\n",
 			smp_processor_id());
-	add_taint(TAINT_MACHINE_CHECK);
 }
 
 static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt;

arch/x86/kernel/irq.c

@@ -249,7 +249,7 @@ void fixup_irqs(void)
 
 		data = irq_desc_get_irq_data(desc);
 		affinity = data->affinity;
-		if (!irq_has_action(irq) ||
+		if (!irq_has_action(irq) || irqd_is_per_cpu(data) ||
 		    cpumask_subset(affinity, cpu_online_mask)) {
 			raw_spin_unlock(&desc->lock);
 			continue;
@@ -276,7 +276,8 @@ void fixup_irqs(void)
 		else if (!(warned++))
 			set_affinity = 0;
 
-		if (!irqd_can_move_in_process_context(data) && chip->irq_unmask)
+		if (!irqd_can_move_in_process_context(data) &&
+		    !irqd_irq_disabled(data) && chip->irq_unmask)
 			chip->irq_unmask(data);
 
 		raw_spin_unlock(&desc->lock);

arch/x86/platform/efi/efi.c

@@ -145,17 +145,6 @@ static void virt_efi_reset_system(int reset_type,
 		       data_size, data);
 }
 
-static efi_status_t virt_efi_set_virtual_address_map(
-	unsigned long memory_map_size,
-	unsigned long descriptor_size,
-	u32 descriptor_version,
-	efi_memory_desc_t *virtual_map)
-{
-	return efi_call_virt4(set_virtual_address_map,
-			      memory_map_size, descriptor_size,
-			      descriptor_version, virtual_map);
-}
-
 static efi_status_t __init phys_efi_set_virtual_address_map(
 	unsigned long memory_map_size,
 	unsigned long descriptor_size,
@@ -468,11 +457,25 @@ void __init efi_init(void)
 #endif
 }
 
+void __init efi_set_executable(efi_memory_desc_t *md, bool executable)
+{
+	u64 addr, npages;
+
+	addr = md->virt_addr;
+	npages = md->num_pages;
+
+	memrange_efi_to_native(&addr, &npages);
+
+	if (executable)
+		set_memory_x(addr, npages);
+	else
+		set_memory_nx(addr, npages);
+}
+
 static void __init runtime_code_page_mkexec(void)
 {
 	efi_memory_desc_t *md;
 	void *p;
-	u64 addr, npages;
 
 	/* Make EFI runtime service code area executable */
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
@@ -481,10 +484,7 @@ static void __init runtime_code_page_mkexec(void)
 		if (md->type != EFI_RUNTIME_SERVICES_CODE)
 			continue;
 
-		addr = md->virt_addr;
-		npages = md->num_pages;
-		memrange_efi_to_native(&addr, &npages);
-		set_memory_x(addr, npages);
+		efi_set_executable(md, true);
 	}
 }
 
@@ -498,13 +498,42 @@ static void __init runtime_code_page_mkexec(void)
  */
 void __init efi_enter_virtual_mode(void)
 {
-	efi_memory_desc_t *md;
+	efi_memory_desc_t *md, *prev_md = NULL;
 	efi_status_t status;
 	unsigned long size;
 	u64 end, systab, addr, npages, end_pfn;
-	void *p, *va;
+	void *p, *va, *new_memmap = NULL;
+	int count = 0;
 
 	efi.systab = NULL;
+
+	/* Merge contiguous regions of the same type and attribute */
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		u64 prev_size;
+		md = p;
+
+		if (!prev_md) {
+			prev_md = md;
+			continue;
+		}
+
+		if (prev_md->type != md->type ||
+		    prev_md->attribute != md->attribute) {
+			prev_md = md;
+			continue;
+		}
+
+		prev_size = prev_md->num_pages << EFI_PAGE_SHIFT;
+
+		if (md->phys_addr == (prev_md->phys_addr + prev_size)) {
+			prev_md->num_pages += md->num_pages;
+			md->type = EFI_RESERVED_TYPE;
+			md->attribute = 0;
+			continue;
+		}
+		prev_md = md;
+	}
+
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		md = p;
 		if (!(md->attribute & EFI_MEMORY_RUNTIME))
@@ -541,15 +570,21 @@ void __init efi_enter_virtual_mode(void)
 			systab += md->virt_addr - md->phys_addr;
 			efi.systab = (efi_system_table_t *) (unsigned long) systab;
 		}
+		new_memmap = krealloc(new_memmap,
+				      (count + 1) * memmap.desc_size,
+				      GFP_KERNEL);
+		memcpy(new_memmap + (count * memmap.desc_size), md,
+		       memmap.desc_size);
+		count++;
 	}
 
 	BUG_ON(!efi.systab);
 
 	status = phys_efi_set_virtual_address_map(
-		memmap.desc_size * memmap.nr_map,
+		memmap.desc_size * count,
 		memmap.desc_size,
 		memmap.desc_version,
-		memmap.phys_map);
+		(efi_memory_desc_t *)__pa(new_memmap));
 
 	if (status != EFI_SUCCESS) {
 		printk(KERN_ALERT "Unable to switch EFI into virtual mode "
@@ -572,11 +607,12 @@ void __init efi_enter_virtual_mode(void)
 	efi.set_variable = virt_efi_set_variable;
 	efi.get_next_high_mono_count = virt_efi_get_next_high_mono_count;
 	efi.reset_system = virt_efi_reset_system;
-	efi.set_virtual_address_map = virt_efi_set_virtual_address_map;
+	efi.set_virtual_address_map = NULL;
 	if (__supported_pte_mask & _PAGE_NX)
 		runtime_code_page_mkexec();
 	early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size);
 	memmap.map = NULL;
+	kfree(new_memmap);
 }
 
 /*

arch/x86/platform/efi/efi_64.c

@@ -41,22 +41,7 @@
 static pgd_t save_pgd __initdata;
 static unsigned long efi_flags __initdata;
 
-static void __init early_mapping_set_exec(unsigned long start,
-					  unsigned long end,
-					  int executable)
-{
-	unsigned long num_pages;
-
-	start &= PMD_MASK;
-	end = (end + PMD_SIZE - 1) & PMD_MASK;
-	num_pages = (end - start) >> PAGE_SHIFT;
-	if (executable)
-		set_memory_x((unsigned long)__va(start), num_pages);
-	else
-		set_memory_nx((unsigned long)__va(start), num_pages);
-}
-
-static void __init early_runtime_code_mapping_set_exec(int executable)
+static void __init early_code_mapping_set_exec(int executable)
 {
 	efi_memory_desc_t *md;
 	void *p;
@@ -67,19 +52,16 @@ static void __init early_runtime_code_mapping_set_exec(int executable)
 	/* Make EFI runtime service code area executable */
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		md = p;
-		if (md->type == EFI_RUNTIME_SERVICES_CODE) {
-			unsigned long end;
-			end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT);
-			early_mapping_set_exec(md->phys_addr, end, executable);
-		}
+		if (md->type == EFI_RUNTIME_SERVICES_CODE)
+			efi_set_executable(md, executable);
 	}
 }
 
 void __init efi_call_phys_prelog(void)
 {
 	unsigned long vaddress;
 
-	early_runtime_code_mapping_set_exec(1);
+	early_code_mapping_set_exec(1);
 	local_irq_save(efi_flags);
 	vaddress = (unsigned long)__va(0x0UL);
 	save_pgd = *pgd_offset_k(0x0UL);
@@ -95,7 +77,7 @@ void __init efi_call_phys_epilog(void)
 	set_pgd(pgd_offset_k(0x0UL), save_pgd);
 	__flush_tlb_all();
 	local_irq_restore(efi_flags);
-	early_runtime_code_mapping_set_exec(0);
+	early_code_mapping_set_exec(0);
 }
 
 void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
@@ -107,8 +89,10 @@ void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
 		return ioremap(phys_addr, size);
 
 	last_map_pfn = init_memory_mapping(phys_addr, phys_addr + size);
-	if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size)
-		return NULL;
+	if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size) {
+		unsigned long top = last_map_pfn << PAGE_SHIFT;
+		efi_ioremap(top, size - (top - phys_addr), type);
+	}
 
 	return (void __iomem *)__va(phys_addr);
 }