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

…ux/kernel/git/tip/tip

* 'x86-apic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86: Skip cpus with apic-ids >= 255 in !x2apic_mode
  x86, x2apic: Allow "nox2apic" to disable x2apic mode setup by BIOS
  x86, x2apic: Fallback to xapic when BIOS doesn't setup interrupt-remapping
  x86, acpi: Skip acpi x2apic entries if the x2apic feature is not present
  x86, apic: Add probe() for apic_flat
  x86: Simplify code by removing a !SMP #ifdefs from 'struct cpuinfo_x86'
  x86: Convert per-cpu counter icr_read_retry_count into a member of irq_stat
  x86: Add per-cpu stat counter for APIC ICR read tries
  pci, x86/io-apic: Allow PCI_IOAPIC to be user configurable on x86
  x86: Fix the !CONFIG_NUMA build of the new CPU ID fixup code support
  x86: Add NumaChip support
  x86: Add x86_init platform override to fix up NUMA core numbering
  x86: Make flat_init_apic_ldr() available

arch/x86/Kconfig

@@ -342,6 +342,7 @@ config X86_EXTENDED_PLATFORM
 
 	  If you enable this option then you'll be able to select support
 	  for the following (non-PC) 64 bit x86 platforms:
+		Numascale NumaChip
 		ScaleMP vSMP
 		SGI Ultraviolet
 
@@ -350,6 +351,18 @@ config X86_EXTENDED_PLATFORM
 endif
 # This is an alphabetically sorted list of 64 bit extended platforms
 # Please maintain the alphabetic order if and when there are additions
+config X86_NUMACHIP
+	bool "Numascale NumaChip"
+	depends on X86_64
+	depends on X86_EXTENDED_PLATFORM
+	depends on NUMA
+	depends on SMP
+	depends on X86_X2APIC
+	depends on !EDAC_AMD64
+	---help---
+	  Adds support for Numascale NumaChip large-SMP systems. Needed to
+	  enable more than ~168 cores.
+	  If you don't have one of these, you should say N here.
 
 config X86_VSMP
 	bool "ScaleMP vSMP"

arch/x86/include/asm/apic.h

@@ -176,6 +176,7 @@ static inline u64 native_x2apic_icr_read(void)
 }
 
 extern int x2apic_phys;
+extern int x2apic_preenabled;
 extern void check_x2apic(void);
 extern void enable_x2apic(void);
 extern void x2apic_icr_write(u32 low, u32 id);
@@ -198,6 +199,9 @@ static inline void x2apic_force_phys(void)
 	x2apic_phys = 1;
 }
 #else
+static inline void disable_x2apic(void)
+{
+}
 static inline void check_x2apic(void)
 {
 }
@@ -212,6 +216,7 @@ static inline void x2apic_force_phys(void)
 {
 }
 
+#define	nox2apic	0
 #define	x2apic_preenabled 0
 #define	x2apic_supported()	0
 #endif
@@ -410,6 +415,7 @@ extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip);
 #endif
 
 #ifdef CONFIG_X86_LOCAL_APIC
+
 static inline u32 apic_read(u32 reg)
 {
 	return apic->read(reg);

arch/x86/include/asm/apic_flat_64.h

@@ -0,0 +1,7 @@
+#ifndef _ASM_X86_APIC_FLAT_64_H
+#define _ASM_X86_APIC_FLAT_64_H
+
+extern void flat_init_apic_ldr(void);
+
+#endif
+

arch/x86/include/asm/apicdef.h

@@ -144,6 +144,7 @@
 
 #define APIC_BASE (fix_to_virt(FIX_APIC_BASE))
 #define APIC_BASE_MSR	0x800
+#define XAPIC_ENABLE	(1UL << 11)
 #define X2APIC_ENABLE	(1UL << 10)
 
 #ifdef CONFIG_X86_32

arch/x86/include/asm/hardirq.h

@@ -11,6 +11,7 @@ typedef struct {
 #ifdef CONFIG_X86_LOCAL_APIC
 	unsigned int apic_timer_irqs;	/* arch dependent */
 	unsigned int irq_spurious_count;
+	unsigned int icr_read_retry_count;
 #endif
 	unsigned int x86_platform_ipis;	/* arch dependent */
 	unsigned int apic_perf_irqs;

arch/x86/include/asm/numachip/numachip_csr.h

@@ -0,0 +1,167 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Numascale NumaConnect-Specific Header file
+ *
+ * Copyright (C) 2011 Numascale AS. All rights reserved.
+ *
+ * Send feedback to <support@numascale.com>
+ *
+ */
+
+#ifndef _ASM_X86_NUMACHIP_NUMACHIP_CSR_H
+#define _ASM_X86_NUMACHIP_NUMACHIP_CSR_H
+
+#include <linux/numa.h>
+#include <linux/percpu.h>
+#include <linux/io.h>
+#include <linux/swab.h>
+#include <asm/types.h>
+#include <asm/processor.h>
+
+#define CSR_NODE_SHIFT		16
+#define CSR_NODE_BITS(p)	(((unsigned long)(p)) << CSR_NODE_SHIFT)
+#define CSR_NODE_MASK		0x0fff		/* 4K nodes */
+
+/* 32K CSR space, b15 indicates geo/non-geo */
+#define CSR_OFFSET_MASK	0x7fffUL
+
+/* Global CSR space covers all 4K possible nodes with 64K CSR space per node */
+#define NUMACHIP_GCSR_BASE	0x3fff00000000ULL
+#define NUMACHIP_GCSR_LIM	0x3fff0fffffffULL
+#define NUMACHIP_GCSR_SIZE	(NUMACHIP_GCSR_LIM - NUMACHIP_GCSR_BASE + 1)
+
+/*
+ * Local CSR space starts in global CSR space with "nodeid" = 0xfff0, however
+ * when using the direct mapping on x86_64, both start and size needs to be
+ * aligned with PMD_SIZE which is 2M
+ */
+#define NUMACHIP_LCSR_BASE	0x3ffffe000000ULL
+#define NUMACHIP_LCSR_LIM	0x3fffffffffffULL
+#define NUMACHIP_LCSR_SIZE	(NUMACHIP_LCSR_LIM - NUMACHIP_LCSR_BASE + 1)
+
+static inline void *gcsr_address(int node, unsigned long offset)
+{
+	return __va(NUMACHIP_GCSR_BASE | (1UL << 15) |
+		CSR_NODE_BITS(node & CSR_NODE_MASK) | (offset & CSR_OFFSET_MASK));
+}
+
+static inline void *lcsr_address(unsigned long offset)
+{
+	return __va(NUMACHIP_LCSR_BASE | (1UL << 15) |
+		CSR_NODE_BITS(0xfff0) | (offset & CSR_OFFSET_MASK));
+}
+
+static inline unsigned int read_gcsr(int node, unsigned long offset)
+{
+	return swab32(readl(gcsr_address(node, offset)));
+}
+
+static inline void write_gcsr(int node, unsigned long offset, unsigned int val)
+{
+	writel(swab32(val), gcsr_address(node, offset));
+}
+
+static inline unsigned int read_lcsr(unsigned long offset)
+{
+	return swab32(readl(lcsr_address(offset)));
+}
+
+static inline void write_lcsr(unsigned long offset, unsigned int val)
+{
+	writel(swab32(val), lcsr_address(offset));
+}
+
+/* ========================================================================= */
+/*                   CSR_G0_STATE_CLEAR                                      */
+/* ========================================================================= */
+
+#define CSR_G0_STATE_CLEAR (0x000 + (0 << 12))
+union numachip_csr_g0_state_clear {
+	unsigned int v;
+	struct numachip_csr_g0_state_clear_s {
+		unsigned int _state:2;
+		unsigned int _rsvd_2_6:5;
+		unsigned int _lost:1;
+		unsigned int _rsvd_8_31:24;
+	} s;
+};
+
+/* ========================================================================= */
+/*                   CSR_G0_NODE_IDS                                         */
+/* ========================================================================= */
+
+#define CSR_G0_NODE_IDS (0x008 + (0 << 12))
+union numachip_csr_g0_node_ids {
+	unsigned int v;
+	struct numachip_csr_g0_node_ids_s {
+		unsigned int _initialid:16;
+		unsigned int _nodeid:12;
+		unsigned int _rsvd_28_31:4;
+	} s;
+};
+
+/* ========================================================================= */
+/*                   CSR_G3_EXT_IRQ_GEN                                      */
+/* ========================================================================= */
+
+#define CSR_G3_EXT_IRQ_GEN (0x030 + (3 << 12))
+union numachip_csr_g3_ext_irq_gen {
+	unsigned int v;
+	struct numachip_csr_g3_ext_irq_gen_s {
+		unsigned int _vector:8;
+		unsigned int _msgtype:3;
+		unsigned int _index:5;
+		unsigned int _destination_apic_id:16;
+	} s;
+};
+
+/* ========================================================================= */
+/*                   CSR_G3_EXT_IRQ_STATUS                                   */
+/* ========================================================================= */
+
+#define CSR_G3_EXT_IRQ_STATUS (0x034 + (3 << 12))
+union numachip_csr_g3_ext_irq_status {
+	unsigned int v;
+	struct numachip_csr_g3_ext_irq_status_s {
+		unsigned int _result:32;
+	} s;
+};
+
+/* ========================================================================= */
+/*                   CSR_G3_EXT_IRQ_DEST                                     */
+/* ========================================================================= */
+
+#define CSR_G3_EXT_IRQ_DEST (0x038 + (3 << 12))
+union numachip_csr_g3_ext_irq_dest {
+	unsigned int v;
+	struct numachip_csr_g3_ext_irq_dest_s {
+		unsigned int _irq:8;
+		unsigned int _rsvd_8_31:24;
+	} s;
+};
+
+/* ========================================================================= */
+/*                   CSR_G3_NC_ATT_MAP_SELECT                                */
+/* ========================================================================= */
+
+#define CSR_G3_NC_ATT_MAP_SELECT (0x7fc + (3 << 12))
+union numachip_csr_g3_nc_att_map_select {
+	unsigned int v;
+	struct numachip_csr_g3_nc_att_map_select_s {
+		unsigned int _upper_address_bits:4;
+		unsigned int _select_ram:4;
+		unsigned int _rsvd_8_31:24;
+	} s;
+};
+
+/* ========================================================================= */
+/*                   CSR_G3_NC_ATT_MAP_SELECT_0-255                          */
+/* ========================================================================= */
+
+#define CSR_G3_NC_ATT_MAP_SELECT_0 (0x800 + (3 << 12))
+
+#endif /* _ASM_X86_NUMACHIP_NUMACHIP_CSR_H */
+

arch/x86/include/asm/processor.h

@@ -99,7 +99,6 @@ struct cpuinfo_x86 {
 	u16			apicid;
 	u16			initial_apicid;
 	u16			x86_clflush_size;
-#ifdef CONFIG_SMP
 	/* number of cores as seen by the OS: */
 	u16			booted_cores;
 	/* Physical processor id: */
@@ -110,7 +109,6 @@ struct cpuinfo_x86 {
 	u8			compute_unit_id;
 	/* Index into per_cpu list: */
 	u16			cpu_index;
-#endif
 	u32			microcode;
 } __attribute__((__aligned__(SMP_CACHE_BYTES)));
 

arch/x86/include/asm/x86_init.h

@@ -7,6 +7,7 @@
 struct mpc_bus;
 struct mpc_cpu;
 struct mpc_table;
+struct cpuinfo_x86;
 
 /**
  * struct x86_init_mpparse - platform specific mpparse ops
@@ -147,6 +148,7 @@ struct x86_init_ops {
  */
 struct x86_cpuinit_ops {
 	void (*setup_percpu_clockev)(void);
+	void (*fixup_cpu_id)(struct cpuinfo_x86 *c, int node);
 };
 
 /**
@@ -186,5 +188,6 @@ extern struct x86_msi_ops x86_msi;
 
 extern void x86_init_noop(void);
 extern void x86_init_uint_noop(unsigned int unused);
+extern void x86_default_fixup_cpu_id(struct cpuinfo_x86 *c, int node);
 
 #endif

arch/x86/kernel/acpi/boot.c

@@ -219,6 +219,8 @@ static int __init
 acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end)
 {
 	struct acpi_madt_local_x2apic *processor = NULL;
+	int apic_id;
+	u8 enabled;
 
 	processor = (struct acpi_madt_local_x2apic *)header;
 
@@ -227,6 +229,8 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end)
 
 	acpi_table_print_madt_entry(header);
 
+	apic_id = processor->local_apic_id;
+	enabled = processor->lapic_flags & ACPI_MADT_ENABLED;
 #ifdef CONFIG_X86_X2APIC
 	/*
 	 * We need to register disabled CPU as well to permit
@@ -235,8 +239,10 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end)
 	 * to not preallocating memory for all NR_CPUS
 	 * when we use CPU hotplug.
 	 */
-	acpi_register_lapic(processor->local_apic_id,	/* APIC ID */
-			    processor->lapic_flags & ACPI_MADT_ENABLED);
+	if (!cpu_has_x2apic && (apic_id >= 0xff) && enabled)
+		printk(KERN_WARNING PREFIX "x2apic entry ignored\n");
+	else
+		acpi_register_lapic(apic_id, enabled);
 #else
 	printk(KERN_WARNING PREFIX "x2apic entry ignored\n");
 #endif

arch/x86/kernel/amd_nb.c

@@ -123,16 +123,14 @@ int amd_get_subcaches(int cpu)
 {
 	struct pci_dev *link = node_to_amd_nb(amd_get_nb_id(cpu))->link;
 	unsigned int mask;
-	int cuid = 0;
+	int cuid;
 
 	if (!amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
 		return 0;
 
 	pci_read_config_dword(link, 0x1d4, &mask);
 
-#ifdef CONFIG_SMP
 	cuid = cpu_data(cpu).compute_unit_id;
-#endif
 	return (mask >> (4 * cuid)) & 0xf;
 }
 
@@ -141,7 +139,7 @@ int amd_set_subcaches(int cpu, int mask)
 	static unsigned int reset, ban;
 	struct amd_northbridge *nb = node_to_amd_nb(amd_get_nb_id(cpu));
 	unsigned int reg;
-	int cuid = 0;
+	int cuid;
 
 	if (!amd_nb_has_feature(AMD_NB_L3_PARTITIONING) || mask > 0xf)
 		return -EINVAL;
@@ -159,9 +157,7 @@ int amd_set_subcaches(int cpu, int mask)
 		pci_write_config_dword(nb->misc, 0x1b8, reg & ~0x180000);
 	}
 
-#ifdef CONFIG_SMP
 	cuid = cpu_data(cpu).compute_unit_id;
-#endif
 	mask <<= 4 * cuid;
 	mask |= (0xf ^ (1 << cuid)) << 26;
 

arch/x86/kernel/apic/Makefile

@@ -10,6 +10,7 @@ obj-$(CONFIG_SMP)		+= ipi.o
 
 ifeq ($(CONFIG_X86_64),y)
 # APIC probe will depend on the listing order here
+obj-$(CONFIG_X86_NUMACHIP)	+= apic_numachip.o
 obj-$(CONFIG_X86_UV)		+= x2apic_uv_x.o
 obj-$(CONFIG_X86_X2APIC)	+= x2apic_phys.o
 obj-$(CONFIG_X86_X2APIC)	+= x2apic_cluster.o