2 files changed, 154 insertions, 37 deletions

diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 0d3a4fa34560..3ae4128013e6 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -51,7 +51,17 @@
 int efi_enabled;
 EXPORT_SYMBOL(efi_enabled);
 
-struct efi efi;
+struct efi __read_mostly efi = {
+	.mps        = EFI_INVALID_TABLE_ADDR,
+	.acpi       = EFI_INVALID_TABLE_ADDR,
+	.acpi20     = EFI_INVALID_TABLE_ADDR,
+	.smbios     = EFI_INVALID_TABLE_ADDR,
+	.sal_systab = EFI_INVALID_TABLE_ADDR,
+	.boot_info  = EFI_INVALID_TABLE_ADDR,
+	.hcdp       = EFI_INVALID_TABLE_ADDR,
+	.uga        = EFI_INVALID_TABLE_ADDR,
+	.uv_systab  = EFI_INVALID_TABLE_ADDR,
+};
 EXPORT_SYMBOL(efi);
 
 struct efi_memory_map memmap;
@@ -79,26 +89,50 @@ early_param("add_efi_memmap", setup_add_efi_memmap);
 
 static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
 {
-	return efi_call_virt2(get_time, tm, tc);
+	unsigned long flags;
+	efi_status_t status;
+
+	spin_lock_irqsave(&rtc_lock, flags);
+	status = efi_call_virt2(get_time, tm, tc);
+	spin_unlock_irqrestore(&rtc_lock, flags);
+	return status;
 }
 
 static efi_status_t virt_efi_set_time(efi_time_t *tm)
 {
-	return efi_call_virt1(set_time, tm);
+	unsigned long flags;
+	efi_status_t status;
+
+	spin_lock_irqsave(&rtc_lock, flags);
+	status = efi_call_virt1(set_time, tm);
+	spin_unlock_irqrestore(&rtc_lock, flags);
+	return status;
 }
 
 static efi_status_t virt_efi_get_wakeup_time(efi_bool_t *enabled,
 					     efi_bool_t *pending,
 					     efi_time_t *tm)
 {
-	return efi_call_virt3(get_wakeup_time,
-			      enabled, pending, tm);
+	unsigned long flags;
+	efi_status_t status;
+
+	spin_lock_irqsave(&rtc_lock, flags);
+	status = efi_call_virt3(get_wakeup_time,
+				enabled, pending, tm);
+	spin_unlock_irqrestore(&rtc_lock, flags);
+	return status;
 }
 
 static efi_status_t virt_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
 {
-	return efi_call_virt2(set_wakeup_time,
-			      enabled, tm);
+	unsigned long flags;
+	efi_status_t status;
+
+	spin_lock_irqsave(&rtc_lock, flags);
+	status = efi_call_virt2(set_wakeup_time,
+				enabled, tm);
+	spin_unlock_irqrestore(&rtc_lock, flags);
+	return status;
 }
 
 static efi_status_t virt_efi_get_variable(efi_char16_t *name,
@@ -122,7 +156,7 @@ static efi_status_t virt_efi_get_next_variable(unsigned long *name_size,
 
 static efi_status_t virt_efi_set_variable(efi_char16_t *name,
 					  efi_guid_t *vendor,
-					  unsigned long attr,
+					  u32 attr,
 					  unsigned long data_size,
 					  void *data)
 {
@@ -131,6 +165,18 @@ static efi_status_t virt_efi_set_variable(efi_char16_t *name,
 			      data_size, data);
 }
 
+static efi_status_t virt_efi_query_variable_info(u32 attr,
+						 u64 *storage_space,
+						 u64 *remaining_space,
+						 u64 *max_variable_size)
+{
+	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+		return EFI_UNSUPPORTED;
+
+	return efi_call_virt4(query_variable_info, attr, storage_space,
+			      remaining_space, max_variable_size);
+}
+
 static efi_status_t virt_efi_get_next_high_mono_count(u32 *count)
 {
 	return efi_call_virt1(get_next_high_mono_count, count);
@@ -145,6 +191,28 @@ static void virt_efi_reset_system(int reset_type,
 		       data_size, data);
 }
 
+static efi_status_t virt_efi_update_capsule(efi_capsule_header_t **capsules,
+					    unsigned long count,
+					    unsigned long sg_list)
+{
+	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+		return EFI_UNSUPPORTED;
+
+	return efi_call_virt3(update_capsule, capsules, count, sg_list);
+}
+
+static efi_status_t virt_efi_query_capsule_caps(efi_capsule_header_t **capsules,
+						unsigned long count,
+						u64 *max_size,
+						int *reset_type)
+{
+	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+		return EFI_UNSUPPORTED;
+
+	return efi_call_virt4(query_capsule_caps, capsules, count, max_size,
+			      reset_type);
+}
+
 static efi_status_t __init phys_efi_set_virtual_address_map(
 	unsigned long memory_map_size,
 	unsigned long descriptor_size,
@@ -164,11 +232,14 @@ static efi_status_t __init phys_efi_set_virtual_address_map(
 static efi_status_t __init phys_efi_get_time(efi_time_t *tm,
 					     efi_time_cap_t *tc)
 {
+	unsigned long flags;
 	efi_status_t status;
 
+	spin_lock_irqsave(&rtc_lock, flags);
 	efi_call_phys_prelog();
 	status = efi_call_phys2(efi_phys.get_time, tm, tc);
 	efi_call_phys_epilog();
+	spin_unlock_irqrestore(&rtc_lock, flags);
 	return status;
 }
 
@@ -310,14 +381,31 @@ void __init efi_reserve_boot_services(void)
 
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		efi_memory_desc_t *md = p;
-		unsigned long long start = md->phys_addr;
-		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
+		u64 start = md->phys_addr;
+		u64 size = md->num_pages << EFI_PAGE_SHIFT;
 
 		if (md->type != EFI_BOOT_SERVICES_CODE &&
 		    md->type != EFI_BOOT_SERVICES_DATA)
 			continue;
-
-		memblock_x86_reserve_range(start, start + size, "EFI Boot");
+		/* Only reserve where possible:
+		 * - Not within any already allocated areas
+		 * - Not over any memory area (really needed, if above?)
+		 * - Not within any part of the kernel
+		 * - Not the bios reserved area
+		*/
+		if ((start+size >= virt_to_phys(_text)
+				&& start <= virt_to_phys(_end)) ||
+			!e820_all_mapped(start, start+size, E820_RAM) ||
+			memblock_x86_check_reserved_size(&start, &size,
+							1<<EFI_PAGE_SHIFT)) {
+			/* Could not reserve, skip it */
+			md->num_pages = 0;
+			memblock_dbg(PFX "Could not reserve boot range "
+					"[0x%010llx-0x%010llx]\n",
+						start, start+size-1);
+		} else
+			memblock_x86_reserve_range(start, start+size,
+							"EFI Boot");
 	}
 }
 
@@ -334,6 +422,10 @@ static void __init efi_free_boot_services(void)
 		    md->type != EFI_BOOT_SERVICES_DATA)
 			continue;
 
+		/* Could not reserve boot area */
+		if (!size)
+			continue;
+
 		free_bootmem_late(start, size);
 	}
 }
@@ -483,9 +575,6 @@ void __init efi_init(void)
 	x86_platform.set_wallclock = efi_set_rtc_mmss;
 #endif
 
-	/* Setup for EFI runtime service */
-	reboot_type = BOOT_EFI;
-
 #if EFI_DEBUG
 	print_efi_memmap();
 #endif
@@ -651,6 +740,9 @@ void __init efi_enter_virtual_mode(void)
 	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 = NULL;
+	efi.query_variable_info = virt_efi_query_variable_info;
+	efi.update_capsule = virt_efi_update_capsule;
+	efi.query_capsule_caps = virt_efi_query_capsule_caps;
 	if (__supported_pte_mask & _PAGE_NX)
 		runtime_code_page_mkexec();
 	early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size);
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 68e467f69fec..db8b915f54bc 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -296,14 +296,18 @@ static void bau_process_message(struct msg_desc *mdp,
 }
 
 /*
- * Determine the first cpu on a uvhub.
+ * Determine the first cpu on a pnode.
  */
-static int uvhub_to_first_cpu(int uvhub)
+static int pnode_to_first_cpu(int pnode, struct bau_control *smaster)
 {
 	int cpu;
-	for_each_present_cpu(cpu)
-		if (uvhub == uv_cpu_to_blade_id(cpu))
+	struct hub_and_pnode *hpp;
+
+	for_each_present_cpu(cpu) {
+		hpp = &smaster->thp[cpu];
+		if (pnode == hpp->pnode)
 			return cpu;
+	}
 	return -1;
 }
 
@@ -366,28 +370,32 @@ static void do_reset(void *ptr)
  * Use IPI to get all target uvhubs to release resources held by
  * a given sending cpu number.
  */
-static void reset_with_ipi(struct bau_targ_hubmask *distribution, int sender)
+static void reset_with_ipi(struct pnmask *distribution, struct bau_control *bcp)
 {
-	int uvhub;
+	int pnode;
+	int apnode;
 	int maskbits;
-	cpumask_t mask;
+	int sender = bcp->cpu;
+	cpumask_t *mask = bcp->uvhub_master->cpumask;
+	struct bau_control *smaster = bcp->socket_master;
 	struct reset_args reset_args;
 
 	reset_args.sender = sender;
-	cpus_clear(mask);
+	cpus_clear(*mask);
 	/* find a single cpu for each uvhub in this distribution mask */
-	maskbits = sizeof(struct bau_targ_hubmask) * BITSPERBYTE;
-	for (uvhub = 0; uvhub < maskbits; uvhub++) {
+	maskbits = sizeof(struct pnmask) * BITSPERBYTE;
+	/* each bit is a pnode relative to the partition base pnode */
+	for (pnode = 0; pnode < maskbits; pnode++) {
 		int cpu;
-		if (!bau_uvhub_isset(uvhub, distribution))
+		if (!bau_uvhub_isset(pnode, distribution))
 			continue;
-		/* find a cpu for this uvhub */
-		cpu = uvhub_to_first_cpu(uvhub);
-		cpu_set(cpu, mask);
+		apnode = pnode + bcp->partition_base_pnode;
+		cpu = pnode_to_first_cpu(apnode, smaster);
+		cpu_set(cpu, *mask);
 	}
 
 	/* IPI all cpus; preemption is already disabled */
-	smp_call_function_many(&mask, do_reset, (void *)&reset_args, 1);
+	smp_call_function_many(mask, do_reset, (void *)&reset_args, 1);
 	return;
 }
 
@@ -604,7 +612,7 @@ static void destination_plugged(struct bau_desc *bau_desc,
 		quiesce_local_uvhub(hmaster);
 
 		spin_lock(&hmaster->queue_lock);
-		reset_with_ipi(&bau_desc->distribution, bcp->cpu);
+		reset_with_ipi(&bau_desc->distribution, bcp);
 		spin_unlock(&hmaster->queue_lock);
 
 		end_uvhub_quiesce(hmaster);
@@ -626,7 +634,7 @@ static void destination_timeout(struct bau_desc *bau_desc,
 		quiesce_local_uvhub(hmaster);
 
 		spin_lock(&hmaster->queue_lock);
-		reset_with_ipi(&bau_desc->distribution, bcp->cpu);
+		reset_with_ipi(&bau_desc->distribution, bcp);
 		spin_unlock(&hmaster->queue_lock);
 
 		end_uvhub_quiesce(hmaster);
@@ -1334,9 +1342,10 @@ static ssize_t tunables_write(struct file *file, const char __user *user,
 
 	instr[count] = '\0';
 
-	bcp = &per_cpu(bau_control, smp_processor_id());
-
+	cpu = get_cpu();
+	bcp = &per_cpu(bau_control, cpu);
 	ret = parse_tunables_write(bcp, instr, count);
+	put_cpu();
 	if (ret)
 		return ret;
 
@@ -1687,6 +1696,16 @@ static void make_per_cpu_thp(struct bau_control *smaster)
 }
 
 /*
+ * Each uvhub is to get a local cpumask.
+ */
+static void make_per_hub_cpumask(struct bau_control *hmaster)
+{
+	int sz = sizeof(cpumask_t);
+
+	hmaster->cpumask = kzalloc_node(sz, GFP_KERNEL, hmaster->osnode);
+}
+
+/*
  * Initialize all the per_cpu information for the cpu's on a given socket,
  * given what has been gathered into the socket_desc struct.
  * And reports the chosen hub and socket masters back to the caller.
@@ -1751,11 +1770,12 @@ static int __init summarize_uvhub_sockets(int nuvhubs,
 				sdp = &bdp->socket[socket];
 				if (scan_sock(sdp, bdp, &smaster, &hmaster))
 					return 1;
+				make_per_cpu_thp(smaster);
 			}
 			socket++;
 			socket_mask = (socket_mask >> 1);
-			make_per_cpu_thp(smaster);
 		}
+		make_per_hub_cpumask(hmaster);
 	}
 	return 0;
 }
@@ -1777,15 +1797,20 @@ static int __init init_per_cpu(int nuvhubs, int base_part_pnode)
 	uvhub_mask = kzalloc((nuvhubs+7)/8, GFP_KERNEL);
 
 	if (get_cpu_topology(base_part_pnode, uvhub_descs, uvhub_mask))
-		return 1;
+		goto fail;
 
 	if (summarize_uvhub_sockets(nuvhubs, uvhub_descs, uvhub_mask))
-		return 1;
+		goto fail;
 
 	kfree(uvhub_descs);
 	kfree(uvhub_mask);
 	init_per_cpu_tunables();
 	return 0;
+
+fail:
+	kfree(uvhub_descs);
+	kfree(uvhub_mask);
+	return 1;
 }
 
 /*