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

Pull x86 apic updates from Ingo Molnar:
 "The main changes are:

   - Persistent CPU/node numbering across CPU hotplug/unplug events.
     This is a pretty involved series of changes that first fetches all
     the information during bootup and then uses it for the various
     hotplug/unplug methods. (Gu Zheng, Dou Liyang)

   - IO-APIC hot-add/remove fixes and enhancements. (Rui Wang)

   - ... various fixes, cleanups and enhancements"

* 'x86-apic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (22 commits)
  x86/apic: Fix silent & fatal merge conflict in __generic_processor_info()
  acpi: Fix broken error check in map_processor()
  acpi: Validate processor id when mapping the processor
  acpi: Provide mechanism to validate processors in the ACPI tables
  x86/acpi: Set persistent cpuid <-> nodeid mapping when booting
  x86/acpi: Enable MADT APIs to return disabled apicids
  x86/acpi: Introduce persistent storage for cpuid <-> apicid mapping
  x86/acpi: Enable acpi to register all possible cpus at boot time
  x86/numa: Online memory-less nodes at boot time
  x86/apic: Get rid of apic_version[] array
  x86/apic: Order irq_enter/exit() calls correctly vs. ack_APIC_irq()
  x86/ioapic: Ignore root bridges without a companion ACPI device
  x86/apic: Update comment about disabling processor focus
  x86/smpboot: Check APIC ID before setting up default routing
  x86/ioapic: Fix IOAPIC failing to request resource
  x86/ioapic: Fix lost IOAPIC resource after hot-removal and hotadd
  x86/ioapic: Fix setup_res() failing to get resource
  x86/ioapic: Support hot-removal of IOAPICs present during boot
  x86/ioapic: Change prototype of acpi_ioapic_add()
  x86/apic, ACPI: Fix incorrect assignment when handling apic/x2apic entries
  ...

12 files changed, 120 insertions, 90 deletions

diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index 92b7bc956795..9273e034b730 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -796,7 +796,7 @@ int acpi_isa_irq_to_gsi(unsigned isa_irq, u32 *gsi)
  *  ACPI based hotplug CPU support
  */
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
-static int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
+int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
 {
 #ifdef CONFIG_ACPI_NUMA
 	/*
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 124357773ffa..f5aaf6c83222 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -650,8 +650,8 @@ static inline void entering_ack_irq(void)
 
 static inline void ipi_entering_ack_irq(void)
 {
-	ack_APIC_irq();
 	irq_enter();
+	ack_APIC_irq();
 }
 
 static inline void exiting_irq(void)
@@ -661,9 +661,8 @@ static inline void exiting_irq(void)
 
 static inline void exiting_ack_irq(void)
 {
-	irq_exit();
-	/* Ack only at the end to avoid potential reentry */
 	ack_APIC_irq();
+	irq_exit();
 }
 
 extern void ioapic_zap_locks(void);
diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index b07233b64578..32007041ef8c 100644
--- a/arch/x86/include/asm/mpspec.h
+++ b/arch/x86/include/asm/mpspec.h
@@ -6,7 +6,6 @@
 #include <asm/x86_init.h>
 #include <asm/apicdef.h>
 
-extern int apic_version[];
 extern int pic_mode;
 
 #ifdef CONFIG_X86_32
@@ -40,6 +39,7 @@ extern int mp_bus_id_to_type[MAX_MP_BUSSES];
 extern DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
 
 extern unsigned int boot_cpu_physical_apicid;
+extern u8 boot_cpu_apic_version;
 extern unsigned long mp_lapic_addr;
 
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -86,6 +86,7 @@ static inline void early_reserve_e820_mpc_new(void) { }
 #endif
 
 int generic_processor_info(int apicid, int version);
+int __generic_processor_info(int apicid, int version, bool enabled);
 
 #define PHYSID_ARRAY_SIZE	BITS_TO_LONGS(MAX_LOCAL_APIC)
 
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index ccd27fe9ca81..32a7d70913ac 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -176,15 +176,10 @@ static int acpi_register_lapic(int id, u32 acpiid, u8 enabled)
 		return -EINVAL;
 	}
 
-	if (!enabled) {
-		++disabled_cpus;
-		return -EINVAL;
-	}
-
 	if (boot_cpu_physical_apicid != -1U)
-		ver = apic_version[boot_cpu_physical_apicid];
+		ver = boot_cpu_apic_version;
 
-	cpu = generic_processor_info(id, ver);
+	cpu = __generic_processor_info(id, ver, enabled);
 	if (cpu >= 0)
 		early_per_cpu(x86_cpu_to_acpiid, cpu) = acpiid;
 
@@ -282,6 +277,8 @@ acpi_parse_lapic_addr_ovr(struct acpi_subtable_header * header,
 	if (BAD_MADT_ENTRY(lapic_addr_ovr, end))
 		return -EINVAL;
 
+	acpi_table_print_madt_entry(header);
+
 	acpi_lapic_addr = lapic_addr_ovr->address;
 
 	return 0;
@@ -705,7 +702,7 @@ static void __init acpi_set_irq_model_ioapic(void)
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
 #include <acpi/processor.h>
 
-static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
+int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
 {
 #ifdef CONFIG_ACPI_NUMA
 	int nid;
@@ -716,6 +713,7 @@ static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
 		numa_set_node(cpu, nid);
 	}
 #endif
+	return 0;
 }
 
 int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, int *pcpu)
@@ -998,21 +996,6 @@ static int __init acpi_parse_madt_lapic_entries(void)
 	if (!boot_cpu_has(X86_FEATURE_APIC))
 		return -ENODEV;
 
-	/*
-	 * Note that the LAPIC address is obtained from the MADT (32-bit value)
-	 * and (optionally) overridden by a LAPIC_ADDR_OVR entry (64-bit value).
-	 */
-
-	count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_OVERRIDE,
-				      acpi_parse_lapic_addr_ovr, 0);
-	if (count < 0) {
-		printk(KERN_ERR PREFIX
-		       "Error parsing LAPIC address override entry\n");
-		return count;
-	}
-
-	register_lapic_address(acpi_lapic_addr);
-
 	count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_SAPIC,
 				      acpi_parse_sapic, MAX_LOCAL_APIC);
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index f3e9b2df4b16..f266b8a92a9e 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -64,6 +64,8 @@ unsigned disabled_cpus;
 unsigned int boot_cpu_physical_apicid = -1U;
 EXPORT_SYMBOL_GPL(boot_cpu_physical_apicid);
 
+u8 boot_cpu_apic_version;
+
 /*
  * The highest APIC ID seen during enumeration.
  */
@@ -1374,7 +1376,6 @@ void setup_local_APIC(void)
 	 * Actually disabling the focus CPU check just makes the hang less
 	 * frequent as it makes the interrupt distributon model be more
 	 * like LRU than MRU (the short-term load is more even across CPUs).
-	 * See also the comment in end_level_ioapic_irq().  --macro
 	 */
 
 	/*
@@ -1816,8 +1817,7 @@ void __init init_apic_mappings(void)
 		 * since smp_sanity_check is prepared for such a case
 		 * and disable smp mode
 		 */
-		apic_version[new_apicid] =
-			 GET_APIC_VERSION(apic_read(APIC_LVR));
+		boot_cpu_apic_version = GET_APIC_VERSION(apic_read(APIC_LVR));
 	}
 }
 
@@ -1828,17 +1828,14 @@ void __init register_lapic_address(unsigned long address)
 	if (!x2apic_mode) {
 		set_fixmap_nocache(FIX_APIC_BASE, address);
 		apic_printk(APIC_VERBOSE, "mapped APIC to %16lx (%16lx)\n",
-			    APIC_BASE, mp_lapic_addr);
+			    APIC_BASE, address);
 	}
 	if (boot_cpu_physical_apicid == -1U) {
 		boot_cpu_physical_apicid  = read_apic_id();
-		apic_version[boot_cpu_physical_apicid] =
-			 GET_APIC_VERSION(apic_read(APIC_LVR));
+		boot_cpu_apic_version = GET_APIC_VERSION(apic_read(APIC_LVR));
 	}
 }
 
-int apic_version[MAX_LOCAL_APIC];
-
 /*
  * Local APIC interrupts
  */
@@ -2027,7 +2024,53 @@ void disconnect_bsp_APIC(int virt_wire_setup)
 	apic_write(APIC_LVT1, value);
 }
 
-int generic_processor_info(int apicid, int version)
+/*
+ * The number of allocated logical CPU IDs. Since logical CPU IDs are allocated
+ * contiguously, it equals to current allocated max logical CPU ID plus 1.
+ * All allocated CPU ID should be in [0, nr_logical_cpuidi), so the maximum of
+ * nr_logical_cpuids is nr_cpu_ids.
+ *
+ * NOTE: Reserve 0 for BSP.
+ */
+static int nr_logical_cpuids = 1;
+
+/*
+ * Used to store mapping between logical CPU IDs and APIC IDs.
+ */
+static int cpuid_to_apicid[] = {
+	[0 ... NR_CPUS - 1] = -1,
+};
+
+/*
+ * Should use this API to allocate logical CPU IDs to keep nr_logical_cpuids
+ * and cpuid_to_apicid[] synchronized.
+ */
+static int allocate_logical_cpuid(int apicid)
+{
+	int i;
+
+	/*
+	 * cpuid <-> apicid mapping is persistent, so when a cpu is up,
+	 * check if the kernel has allocated a cpuid for it.
+	 */
+	for (i = 0; i < nr_logical_cpuids; i++) {
+		if (cpuid_to_apicid[i] == apicid)
+			return i;
+	}
+
+	/* Allocate a new cpuid. */
+	if (nr_logical_cpuids >= nr_cpu_ids) {
+		WARN_ONCE(1, "Only %d processors supported."
+			     "Processor %d/0x%x and the rest are ignored.\n",
+			     nr_cpu_ids - 1, nr_logical_cpuids, apicid);
+		return -1;
+	}
+
+	cpuid_to_apicid[nr_logical_cpuids] = apicid;
+	return nr_logical_cpuids++;
+}
+
+int __generic_processor_info(int apicid, int version, bool enabled)
 {
 	int cpu, max = nr_cpu_ids;
 	bool boot_cpu_detected = physid_isset(boot_cpu_physical_apicid,
@@ -2102,8 +2145,16 @@ int generic_processor_info(int apicid, int version)
 		 * for BSP.
 		 */
 		cpu = 0;
-	} else
-		cpu = cpumask_next_zero(-1, cpu_present_mask);
+
+		/* Logical cpuid 0 is reserved for BSP. */
+		cpuid_to_apicid[0] = apicid;
+	} else {
+		cpu = allocate_logical_cpuid(apicid);
+		if (cpu < 0) {
+			disabled_cpus++;
+			return -EINVAL;
+		}
+	}
 
 	/*
 	 * This can happen on physical hotplug. The sanity check at boot time
@@ -2120,8 +2171,6 @@ int generic_processor_info(int apicid, int version)
 		return -ENOSPC;
 	}
 
-	num_processors++;
-
 	/*
 	 * Validate version
 	 */
@@ -2130,14 +2179,12 @@ int generic_processor_info(int apicid, int version)
 			   cpu, apicid);
 		version = 0x10;
 	}
-	apic_version[apicid] = version;
 
-	if (version != apic_version[boot_cpu_physical_apicid]) {
+	if (version != boot_cpu_apic_version) {
 		pr_warning("BIOS bug: APIC version mismatch, boot CPU: %x, CPU %d: version %x\n",
-			apic_version[boot_cpu_physical_apicid], cpu, version);
+			boot_cpu_apic_version, cpu, version);
 	}
 
-	physid_set(apicid, phys_cpu_present_map);
 	if (apicid > max_physical_apicid)
 		max_physical_apicid = apicid;
 
@@ -2150,11 +2197,23 @@ int generic_processor_info(int apicid, int version)
 		apic->x86_32_early_logical_apicid(cpu);
 #endif
 	set_cpu_possible(cpu, true);
-	set_cpu_present(cpu, true);
+
+	if (enabled) {
+		num_processors++;
+		physid_set(apicid, phys_cpu_present_map);
+		set_cpu_present(cpu, true);
+	} else {
+		disabled_cpus++;
+	}
 
 	return cpu;
 }
 
+int generic_processor_info(int apicid, int version)
+{
+	return __generic_processor_info(apicid, version, true);
+}
+
 int hard_smp_processor_id(void)
 {
 	return read_apic_id();
@@ -2277,7 +2336,7 @@ int __init APIC_init_uniprocessor(void)
 	 * Complain if the BIOS pretends there is one.
 	 */
 	if (!boot_cpu_has(X86_FEATURE_APIC) &&
-	    APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) {
+	    APIC_INTEGRATED(boot_cpu_apic_version)) {
 		pr_err("BIOS bug, local APIC 0x%x not detected!...\n",
 			boot_cpu_physical_apicid);
 		return -1;
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 7491f417a8e4..48e6d84f173e 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1593,7 +1593,7 @@ void __init setup_ioapic_ids_from_mpc(void)
 	 * no meaning without the serial APIC bus.
 	 */
 	if (!(boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
-		|| APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
+		|| APIC_XAPIC(boot_cpu_apic_version))
 		return;
 	setup_ioapic_ids_from_mpc_nocheck();
 }
@@ -2423,7 +2423,7 @@ static int io_apic_get_unique_id(int ioapic, int apic_id)
 static u8 io_apic_unique_id(int idx, u8 id)
 {
 	if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) &&
-	    !APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
+	    !APIC_XAPIC(boot_cpu_apic_version))
 		return io_apic_get_unique_id(idx, id);
 	else
 		return id;
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 7c43e716c158..563096267ca2 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -152,7 +152,7 @@ early_param("apic", parse_apic);
 
 void __init default_setup_apic_routing(void)
 {
-	int version = apic_version[boot_cpu_physical_apicid];
+	int version = boot_cpu_apic_version;
 
 	if (num_possible_cpus() > 8) {
 		switch (boot_cpu_data.x86_vendor) {
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 068c4a929de6..0f8d20497383 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -499,6 +499,9 @@ void __init default_get_smp_config(unsigned int early)
 {
 	struct mpf_intel *mpf = mpf_found;
 
+	if (!smp_found_config)
+		return;
+
 	if (!mpf)
 		return;
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 7e54491f126a..2c4bc85dfe90 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1219,8 +1219,7 @@ void __init setup_arch(char **cmdline_p)
 	/*
 	 * get boot-time SMP configuration:
 	 */
-	if (smp_found_config)
-		get_smp_config();
+	get_smp_config();
 
 	prefill_possible_map();
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 7137ec4eea9a..54e2f1a968a4 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -691,7 +691,7 @@ wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip)
 	 * Give the other CPU some time to accept the IPI.
 	 */
 	udelay(200);
-	if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) {
+	if (APIC_INTEGRATED(boot_cpu_apic_version)) {
 		maxlvt = lapic_get_maxlvt();
 		if (maxlvt > 3)			/* Due to the Pentium erratum 3AP.  */
 			apic_write(APIC_ESR, 0);
@@ -718,7 +718,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
 	/*
 	 * Be paranoid about clearing APIC errors.
 	 */
-	if (APIC_INTEGRATED(apic_version[phys_apicid])) {
+	if (APIC_INTEGRATED(boot_cpu_apic_version)) {
 		if (maxlvt > 3)		/* Due to the Pentium erratum 3AP.  */
 			apic_write(APIC_ESR, 0);
 		apic_read(APIC_ESR);
@@ -757,7 +757,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
 	 * Determine this based on the APIC version.
 	 * If we don't have an integrated APIC, don't send the STARTUP IPIs.
 	 */
-	if (APIC_INTEGRATED(apic_version[phys_apicid]))
+	if (APIC_INTEGRATED(boot_cpu_apic_version))
 		num_starts = 2;
 	else
 		num_starts = 0;
@@ -995,7 +995,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 		/*
 		 * Be paranoid about clearing APIC errors.
 		*/
-		if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) {
+		if (APIC_INTEGRATED(boot_cpu_apic_version)) {
 			apic_write(APIC_ESR, 0);
 			apic_read(APIC_ESR);
 		}
@@ -1250,7 +1250,7 @@ static int __init smp_sanity_check(unsigned max_cpus)
 	/*
 	 * If we couldn't find a local APIC, then get out of here now!
 	 */
-	if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid]) &&
+	if (APIC_INTEGRATED(boot_cpu_apic_version) &&
 	    !boot_cpu_has(X86_FEATURE_APIC)) {
 		if (!disable_apic) {
 			pr_err("BIOS bug, local APIC #%d not detected!...\n",
@@ -1334,14 +1334,13 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 		break;
 	}
 
-	default_setup_apic_routing();
-
 	if (read_apic_id() != boot_cpu_physical_apicid) {
 		panic("Boot APIC ID in local APIC unexpected (%d vs %d)",
 		     read_apic_id(), boot_cpu_physical_apicid);
 		/* Or can we switch back to PIC here? */
 	}
 
+	default_setup_apic_routing();
 	cpu0_logical_apicid = apic_bsp_setup(false);
 
 	pr_info("CPU%d: ", 0);
diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c
index ba47524f56e8..d1c7de095808 100644
--- a/arch/x86/mm/amdtopology.c
+++ b/arch/x86/mm/amdtopology.c
@@ -52,21 +52,6 @@ static __init int find_northbridge(void)
 	return -ENOENT;
 }
 
-static __init void early_get_boot_cpu_id(void)
-{
-	/*
-	 * need to get the APIC ID of the BSP so can use that to
-	 * create apicid_to_node in amd_scan_nodes()
-	 */
-#ifdef CONFIG_X86_MPPARSE
-	/*
-	 * get boot-time SMP configuration:
-	 */
-	if (smp_found_config)
-		early_get_smp_config();
-#endif
-}
-
 int __init amd_numa_init(void)
 {
 	u64 start = PFN_PHYS(0);
@@ -180,8 +165,11 @@ int __init amd_numa_init(void)
 	cores = 1 << bits;
 	apicid_base = 0;
 
-	/* get the APIC ID of the BSP early for systems with apicid lifting */
-	early_get_boot_cpu_id();
+	/*
+	 * get boot-time SMP configuration:
+	 */
+	early_get_smp_config();
+
 	if (boot_cpu_physical_apicid > 0) {
 		pr_info("BSP APIC ID: %02x\n", boot_cpu_physical_apicid);
 		apicid_base = boot_cpu_physical_apicid;
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index fb682108f4dc..3f35b48d1d9d 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -722,22 +722,19 @@ void __init x86_numa_init(void)
 	numa_init(dummy_numa_init);
 }
 
-static __init int find_near_online_node(int node)
+static void __init init_memory_less_node(int nid)
 {
-	int n, val;
-	int min_val = INT_MAX;
-	int best_node = -1;
+	unsigned long zones_size[MAX_NR_ZONES] = {0};
+	unsigned long zholes_size[MAX_NR_ZONES] = {0};
 
-	for_each_online_node(n) {
-		val = node_distance(node, n);
+	/* Allocate and initialize node data. Memory-less node is now online.*/
+	alloc_node_data(nid);
+	free_area_init_node(nid, zones_size, 0, zholes_size);
 
-		if (val < min_val) {
-			min_val = val;
-			best_node = n;
-		}
-	}
-
-	return best_node;
+	/*
+	 * All zonelists will be built later in start_kernel() after per cpu
+	 * areas are initialized.
+	 */
 }
 
 /*
@@ -766,8 +763,10 @@ void __init init_cpu_to_node(void)
 
 		if (node == NUMA_NO_NODE)
 			continue;
+
 		if (!node_online(node))
-			node = find_near_online_node(node);
+			init_memory_less_node(node);
+
 		numa_set_node(cpu, node);
 	}
 }