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

Pull x86 platform updates from Ingo Molnar:
 "The main change is the addition of SGI/UV4 support"

* 'x86-platform-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (22 commits)
  x86/platform/UV: Fix incorrect nodes and pnodes for cpuless and memoryless nodes
  x86/platform/UV: Remove Obsolete GRU MMR address translation
  x86/platform/UV: Update physical address conversions for UV4
  x86/platform/UV: Build GAM reference tables
  x86/platform/UV: Support UV4 socket address changes
  x86/platform/UV: Add obtaining GAM Range Table from UV BIOS
  x86/platform/UV: Add UV4 addressing discovery function
  x86/platform/UV: Fold blade info into per node hub info structs
  x86/platform/UV: Allocate common per node hub info structs on local node
  x86/platform/UV: Move blade local processor ID to the per cpu info struct
  x86/platform/UV: Move scir info to the per cpu info struct
  x86/platform/UV: Create per cpu info structs to replace per hub info structs
  x86/platform/UV: Update MMIOH setup function to work for both UV3 and UV4
  x86/platform/UV: Clean up redunduncies after merge of UV4 MMR definitions
  x86/platform/UV: Add UV4 Specific MMR definitions
  x86/platform/UV: Prep for UV4 MMR updates
  x86/platform/UV: Add UV MMR Illegal Access Function
  x86/platform/UV: Add UV4 Specific Defines
  x86/platform/UV: Add UV Architecture Defines
  x86/platform/UV: Add Initial UV4 definitions
  ...

Documentation/kernel-parameters.txt

@@ -131,6 +131,7 @@ parameter is applicable:
 			More X86-64 boot options can be found in
 			Documentation/x86/x86_64/boot-options.txt .
 	X86	Either 32-bit or 64-bit x86 (same as X86-32+X86-64)
+	X86_UV	SGI UV support is enabled.
 	XEN	Xen support is enabled
 
 In addition, the following text indicates that the option:
@@ -542,6 +543,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Format: <int> (must be >=0)
 			Default: 64
 
+	bau=		[X86_UV] Enable the BAU on SGI UV.  The default
+			behavior is to disable the BAU (i.e. bau=0).
+			Format: { "0" | "1" }
+			0 - Disable the BAU.
+			1 - Enable the BAU.
+			unset - Disable the BAU.
+
 	baycom_epp=	[HW,AX25]
 			Format: <io>,<mode>
 

arch/x86/include/asm/bios_ebda.h

@@ -17,27 +17,6 @@ static inline unsigned int get_bios_ebda(void)
 	return address;	/* 0 means none */
 }
 
-/*
- * Return the sanitized length of the EBDA in bytes, if it exists.
- */
-static inline unsigned int get_bios_ebda_length(void)
-{
-	unsigned int address;
-	unsigned int length;
-
-	address = get_bios_ebda();
-	if (!address)
-		return 0;
-
-	/* EBDA length is byte 0 of the EBDA (stored in KiB) */
-	length = *(unsigned char *)phys_to_virt(address);
-	length <<= 10;
-
-	/* Trim the length if it extends beyond 640KiB */
-	length = min_t(unsigned int, (640 * 1024) - address, length);
-	return length;
-}
-
 void reserve_ebda_region(void);
 
 #ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION

arch/x86/include/asm/uv/bios.h

@@ -51,15 +51,66 @@ enum {
 	BIOS_STATUS_UNAVAIL		= -EBUSY
 };
 
+/* Address map parameters */
+struct uv_gam_parameters {
+	u64	mmr_base;
+	u64	gru_base;
+	u8	mmr_shift;	/* Convert PNode to MMR space offset */
+	u8	gru_shift;	/* Convert PNode to GRU space offset */
+	u8	gpa_shift;	/* Size of offset field in GRU phys addr */
+	u8	unused1;
+};
+
+/* UV_TABLE_GAM_RANGE_ENTRY values */
+#define UV_GAM_RANGE_TYPE_UNUSED	0 /* End of table */
+#define UV_GAM_RANGE_TYPE_RAM		1 /* Normal RAM */
+#define UV_GAM_RANGE_TYPE_NVRAM		2 /* Non-volatile memory */
+#define UV_GAM_RANGE_TYPE_NV_WINDOW	3 /* NVMDIMM block window */
+#define UV_GAM_RANGE_TYPE_NV_MAILBOX	4 /* NVMDIMM mailbox */
+#define UV_GAM_RANGE_TYPE_HOLE		5 /* Unused address range */
+#define UV_GAM_RANGE_TYPE_MAX		6
+
+/* The structure stores PA bits 56:26, for 64MB granularity */
+#define UV_GAM_RANGE_SHFT		26		/* 64MB */
+
+struct uv_gam_range_entry {
+	char	type;		/* Entry type: GAM_RANGE_TYPE_UNUSED, etc. */
+	char	unused1;
+	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	limit;		/* PA bits 56:26 (UV_GAM_RANGE_SHFT) */
+};
+
+#define	UV_SYSTAB_SIG			"UVST"
+#define	UV_SYSTAB_VERSION_1		1	/* UV1/2/3 BIOS version */
+#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_TYPE_UNUSED		0	/* End of table (offset == 0) */
+#define	UV_SYSTAB_TYPE_GAM_PARAMS	1	/* GAM PARAM conversions */
+#define	UV_SYSTAB_TYPE_GAM_RNG_TBL	2	/* GAM entry table */
+#define	UV_SYSTAB_TYPE_MAX		3
+
 /*
  * The UV system table describes specific firmware
  * capabilities available to the Linux kernel at runtime.
  */
 struct uv_systab {
-	char signature[4];	/* must be "UVST" */
+	char signature[4];	/* must be UV_SYSTAB_SIG */
 	u32 revision;		/* distinguish different firmware revs */
 	u64 function;		/* BIOS runtime callback function ptr */
+	u32 size;		/* systab size (starting with _VERSION_UV4) */
+	struct {
+		u32 type:8;	/* type of entry */
+		u32 offset:24;	/* byte offset from struct start to entry */
+	} entry[1];		/* additional entries follow */
 };
+extern struct uv_systab *uv_systab;
+/* (... end of definitions from UV BIOS ...) */
 
 enum {
 	BIOS_FREQ_BASE_PLATFORM = 0,
@@ -99,7 +150,11 @@ extern s64 uv_bios_change_memprotect(u64, u64, enum uv_memprotect);
 extern s64 uv_bios_reserved_page_pa(u64, u64 *, u64 *, u64 *);
 extern int uv_bios_set_legacy_vga_target(bool decode, int domain, int bus);
 
+#ifdef CONFIG_EFI
 extern void uv_bios_init(void);
+#else
+void uv_bios_init(void) { }
+#endif
 
 extern unsigned long sn_rtc_cycles_per_second;
 extern int uv_type;
@@ -107,7 +162,7 @@ extern long sn_partition_id;
 extern long sn_coherency_id;
 extern long sn_region_size;
 extern long system_serial_number;
-#define partition_coherence_id()	(sn_coherency_id)
+#define uv_partition_coherence_id()	(sn_coherency_id)
 
 extern struct kobject *sgi_uv_kobj;	/* /sys/firmware/sgi_uv */
 

arch/x86/include/asm/uv/uv_bau.h

@@ -598,7 +598,7 @@ struct bau_control {
 	int			timeout_tries;
 	int			ipi_attempts;
 	int			conseccompletes;
-	short			nobau;
+	bool			nobau;
 	short			baudisabled;
 	short			cpu;
 	short			osnode;

arch/x86/include/asm/uv/uv_hub.h

@@ -16,9 +16,11 @@
 #include <linux/percpu.h>
 #include <linux/timer.h>
 #include <linux/io.h>
+#include <linux/topology.h>
 #include <asm/types.h>
 #include <asm/percpu.h>
 #include <asm/uv/uv_mmrs.h>
+#include <asm/uv/bios.h>
 #include <asm/irq_vectors.h>
 #include <asm/io_apic.h>
 
@@ -103,7 +105,6 @@
  *	      processor APICID register.
  */
 
-
 /*
  * Maximum number of bricks in all partitions and in all coherency domains.
  * This is the total number of bricks accessible in the numalink fabric. It
@@ -127,6 +128,7 @@
  */
 #define UV_MAX_NASID_VALUE	(UV_MAX_NUMALINK_BLADES * 2)
 
+/* System Controller Interface Reg info */
 struct uv_scir_s {
 	struct timer_list timer;
 	unsigned long	offset;
@@ -137,71 +139,173 @@ struct uv_scir_s {
 	unsigned char	enabled;
 };
 
+/* GAM (globally addressed memory) range table */
+struct uv_gam_range_s {
+	u32	limit;		/* PA bits 56:26 (GAM_RANGE_SHFT) */
+	u16	nasid;		/* node's global physical address */
+	s8	base;		/* entry index of node's base addr */
+	u8	reserved;
+};
+
 /*
  * The following defines attributes of the HUB chip. These attributes are
- * frequently referenced and are kept in the per-cpu data areas of each cpu.
- * They are kept together in a struct to minimize cache misses.
+ * frequently referenced and are kept in a common per hub struct.
+ * After setup, the struct is read only, so it should be readily
+ * available in the L3 cache on the cpu socket for the node.
  */
 struct uv_hub_info_s {
 	unsigned long		global_mmr_base;
+	unsigned long		global_mmr_shift;
 	unsigned long		gpa_mask;
-	unsigned int		gnode_extra;
+	unsigned short		*socket_to_node;
+	unsigned short		*socket_to_pnode;
+	unsigned short		*pnode_to_socket;
+	struct uv_gam_range_s	*gr_table;
+	unsigned short		min_socket;
+	unsigned short		min_pnode;
+	unsigned char		m_val;
+	unsigned char		n_val;
+	unsigned char		gr_table_len;
 	unsigned char		hub_revision;
 	unsigned char		apic_pnode_shift;
+	unsigned char		gpa_shift;
 	unsigned char		m_shift;
 	unsigned char		n_lshift;
+	unsigned int		gnode_extra;
 	unsigned long		gnode_upper;
 	unsigned long		lowmem_remap_top;
 	unsigned long		lowmem_remap_base;
+	unsigned long		global_gru_base;
+	unsigned long		global_gru_shift;
 	unsigned short		pnode;
 	unsigned short		pnode_mask;
 	unsigned short		coherency_domain_number;
 	unsigned short		numa_blade_id;
-	unsigned char		blade_processor_id;
-	unsigned char		m_val;
-	unsigned char		n_val;
+	unsigned short		nr_possible_cpus;
+	unsigned short		nr_online_cpus;
+	short			memory_nid;
+};
+
+/* CPU specific info with a pointer to the hub common info struct */
+struct uv_cpu_info_s {
+	void			*p_uv_hub_info;
+	unsigned char		blade_cpu_id;
 	struct uv_scir_s	scir;
 };
+DECLARE_PER_CPU(struct uv_cpu_info_s, __uv_cpu_info);
+
+#define uv_cpu_info		this_cpu_ptr(&__uv_cpu_info)
+#define uv_cpu_info_per(cpu)	(&per_cpu(__uv_cpu_info, cpu))
 
-DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
-#define uv_hub_info		this_cpu_ptr(&__uv_hub_info)
-#define uv_cpu_hub_info(cpu)	(&per_cpu(__uv_hub_info, cpu))
+#define	uv_scir_info		(&uv_cpu_info->scir)
+#define	uv_cpu_scir_info(cpu)	(&uv_cpu_info_per(cpu)->scir)
+
+/* Node specific hub common info struct */
+extern void **__uv_hub_info_list;
+static inline struct uv_hub_info_s *uv_hub_info_list(int node)
+{
+	return (struct uv_hub_info_s *)__uv_hub_info_list[node];
+}
+
+static inline struct uv_hub_info_s *_uv_hub_info(void)
+{
+	return (struct uv_hub_info_s *)uv_cpu_info->p_uv_hub_info;
+}
+#define	uv_hub_info	_uv_hub_info()
+
+static inline struct uv_hub_info_s *uv_cpu_hub_info(int cpu)
+{
+	return (struct uv_hub_info_s *)uv_cpu_info_per(cpu)->p_uv_hub_info;
+}
+
+#define	UV_HUB_INFO_VERSION	0x7150
+extern int uv_hub_info_version(void);
+static inline int uv_hub_info_check(int version)
+{
+	if (uv_hub_info_version() == version)
+		return 0;
+
+	pr_crit("UV: uv_hub_info version(%x) mismatch, expecting(%x)\n",
+		uv_hub_info_version(), version);
+
+	BUG();	/* Catastrophic - cannot continue on unknown UV system */
+}
+#define	_uv_hub_info_check()	uv_hub_info_check(UV_HUB_INFO_VERSION)
 
 /*
- * Hub revisions less than UV2_HUB_REVISION_BASE are UV1 hubs. All UV2
- * hubs have revision numbers greater than or equal to UV2_HUB_REVISION_BASE.
+ * HUB revision ranges for each UV HUB architecture.
  * This is a software convention - NOT the hardware revision numbers in
  * the hub chip.
  */
 #define UV1_HUB_REVISION_BASE		1
 #define UV2_HUB_REVISION_BASE		3
 #define UV3_HUB_REVISION_BASE		5
+#define UV4_HUB_REVISION_BASE		7
 
+#ifdef	UV1_HUB_IS_SUPPORTED
 static inline int is_uv1_hub(void)
 {
 	return uv_hub_info->hub_revision < UV2_HUB_REVISION_BASE;
 }
+#else
+static inline int is_uv1_hub(void)
+{
+	return 0;
+}
+#endif
 
+#ifdef	UV2_HUB_IS_SUPPORTED
 static inline int is_uv2_hub(void)
 {
 	return ((uv_hub_info->hub_revision >= UV2_HUB_REVISION_BASE) &&
 		(uv_hub_info->hub_revision < UV3_HUB_REVISION_BASE));
 }
+#else
+static inline int is_uv2_hub(void)
+{
+	return 0;
+}
+#endif
 
+#ifdef	UV3_HUB_IS_SUPPORTED
 static inline int is_uv3_hub(void)
 {
-	return uv_hub_info->hub_revision >= UV3_HUB_REVISION_BASE;
+	return ((uv_hub_info->hub_revision >= UV3_HUB_REVISION_BASE) &&
+		(uv_hub_info->hub_revision < UV4_HUB_REVISION_BASE));
+}
+#else
+static inline int is_uv3_hub(void)
+{
+	return 0;
 }
+#endif
 
-static inline int is_uv_hub(void)
+#ifdef	UV4_HUB_IS_SUPPORTED
+static inline int is_uv4_hub(void)
 {
-	return uv_hub_info->hub_revision;
+	return uv_hub_info->hub_revision >= UV4_HUB_REVISION_BASE;
+}
+#else
+static inline int is_uv4_hub(void)
+{
+	return 0;
 }
+#endif
 
-/* code common to uv2 and uv3 only */
 static inline int is_uvx_hub(void)
 {
-	return uv_hub_info->hub_revision >= UV2_HUB_REVISION_BASE;
+	if (uv_hub_info->hub_revision >= UV2_HUB_REVISION_BASE)
+		return uv_hub_info->hub_revision;
+
+	return 0;
+}
+
+static inline int is_uv_hub(void)
+{
+#ifdef	UV1_HUB_IS_SUPPORTED
+	return uv_hub_info->hub_revision;
+#endif
+	return is_uvx_hub();
 }
 
 union uvh_apicid {
@@ -243,24 +347,42 @@ union uvh_apicid {
 #define UV3_LOCAL_MMR_SIZE		(32UL * 1024 * 1024)
 #define UV3_GLOBAL_MMR32_SIZE		(32UL * 1024 * 1024)
 
-#define UV_LOCAL_MMR_BASE		(is_uv1_hub() ? UV1_LOCAL_MMR_BASE : \
-					(is_uv2_hub() ? UV2_LOCAL_MMR_BASE : \
-							UV3_LOCAL_MMR_BASE))
-#define UV_GLOBAL_MMR32_BASE		(is_uv1_hub() ? UV1_GLOBAL_MMR32_BASE :\
-					(is_uv2_hub() ? UV2_GLOBAL_MMR32_BASE :\
-							UV3_GLOBAL_MMR32_BASE))
-#define UV_LOCAL_MMR_SIZE		(is_uv1_hub() ? UV1_LOCAL_MMR_SIZE : \
-					(is_uv2_hub() ? UV2_LOCAL_MMR_SIZE : \
-							UV3_LOCAL_MMR_SIZE))
-#define UV_GLOBAL_MMR32_SIZE		(is_uv1_hub() ? UV1_GLOBAL_MMR32_SIZE :\
-					(is_uv2_hub() ? UV2_GLOBAL_MMR32_SIZE :\
-							UV3_GLOBAL_MMR32_SIZE))
+#define UV4_LOCAL_MMR_BASE		0xfa000000UL
+#define UV4_GLOBAL_MMR32_BASE		0xfc000000UL
+#define UV4_LOCAL_MMR_SIZE		(32UL * 1024 * 1024)
+#define UV4_GLOBAL_MMR32_SIZE		(16UL * 1024 * 1024)
+
+#define UV_LOCAL_MMR_BASE		(				\
+					is_uv1_hub() ? UV1_LOCAL_MMR_BASE : \
+					is_uv2_hub() ? UV2_LOCAL_MMR_BASE : \
+					is_uv3_hub() ? UV3_LOCAL_MMR_BASE : \
+					/*is_uv4_hub*/ UV4_LOCAL_MMR_BASE)
+
+#define UV_GLOBAL_MMR32_BASE		(				\
+					is_uv1_hub() ? UV1_GLOBAL_MMR32_BASE : \
+					is_uv2_hub() ? UV2_GLOBAL_MMR32_BASE : \
+					is_uv3_hub() ? UV3_GLOBAL_MMR32_BASE : \
+					/*is_uv4_hub*/ UV4_GLOBAL_MMR32_BASE)
+
+#define UV_LOCAL_MMR_SIZE		(				\
+					is_uv1_hub() ? UV1_LOCAL_MMR_SIZE : \
+					is_uv2_hub() ? UV2_LOCAL_MMR_SIZE : \
+					is_uv3_hub() ? UV3_LOCAL_MMR_SIZE : \
+					/*is_uv4_hub*/ UV4_LOCAL_MMR_SIZE)
+
+#define UV_GLOBAL_MMR32_SIZE		(				\
+					is_uv1_hub() ? UV1_GLOBAL_MMR32_SIZE : \
+					is_uv2_hub() ? UV2_GLOBAL_MMR32_SIZE : \
+					is_uv3_hub() ? UV3_GLOBAL_MMR32_SIZE : \
+					/*is_uv4_hub*/ UV4_GLOBAL_MMR32_SIZE)
+
 #define UV_GLOBAL_MMR64_BASE		(uv_hub_info->global_mmr_base)
 
 #define UV_GLOBAL_GRU_MMR_BASE		0x4000000
 
 #define UV_GLOBAL_MMR32_PNODE_SHIFT	15
-#define UV_GLOBAL_MMR64_PNODE_SHIFT	26
+#define _UV_GLOBAL_MMR64_PNODE_SHIFT	26
+#define UV_GLOBAL_MMR64_PNODE_SHIFT	(uv_hub_info->global_mmr_shift)
 
 #define UV_GLOBAL_MMR32_PNODE_BITS(p)	((p) << (UV_GLOBAL_MMR32_PNODE_SHIFT))
 
@@ -307,18 +429,74 @@ union uvh_apicid {
  *	      between socket virtual and socket physical addresses.
  */
 
+/* global bits offset - number of local address bits in gpa for this UV arch */
+static inline unsigned int uv_gpa_shift(void)
+{
+	return uv_hub_info->gpa_shift;
+}
+#define	_uv_gpa_shift
+
+/* Find node that has the address range that contains global address  */
+static inline struct uv_gam_range_s *uv_gam_range(unsigned long pa)
+{
+	struct uv_gam_range_s *gr = uv_hub_info->gr_table;
+	unsigned long pal = (pa & uv_hub_info->gpa_mask) >> UV_GAM_RANGE_SHFT;
+	int i, num = uv_hub_info->gr_table_len;
+
+	if (gr) {
+		for (i = 0; i < num; i++, gr++) {
+			if (pal < gr->limit)
+				return gr;
+		}
+	}
+	pr_crit("UV: GAM Range for 0x%lx not found at %p!\n", pa, gr);
+	BUG();
+}
+
+/* Return base address of node that contains global address  */
+static inline unsigned long uv_gam_range_base(unsigned long pa)
+{
+	struct uv_gam_range_s *gr = uv_gam_range(pa);
+	int base = gr->base;
+
+	if (base < 0)
+		return 0UL;
+
+	return uv_hub_info->gr_table[base].limit;
+}
+
+/* socket phys RAM --> UV global NASID (UV4+) */
+static inline unsigned long uv_soc_phys_ram_to_nasid(unsigned long paddr)
+{
+	return uv_gam_range(paddr)->nasid;
+}
+#define	_uv_soc_phys_ram_to_nasid
+
+/* socket virtual --> UV global NASID (UV4+) */
+static inline unsigned long uv_gpa_nasid(void *v)
+{
+	return uv_soc_phys_ram_to_nasid(__pa(v));
+}
+
 /* socket phys RAM --> UV global physical address */
 static inline unsigned long uv_soc_phys_ram_to_gpa(unsigned long paddr)
 {
+	unsigned int m_val = uv_hub_info->m_val;
+
 	if (paddr < uv_hub_info->lowmem_remap_top)
 		paddr |= uv_hub_info->lowmem_remap_base;
 	paddr |= uv_hub_info->gnode_upper;
-	paddr = ((paddr << uv_hub_info->m_shift) >> uv_hub_info->m_shift) |
-		((paddr >> uv_hub_info->m_val) << uv_hub_info->n_lshift);
+	if (m_val)
+		paddr = ((paddr << uv_hub_info->m_shift)
+						>> uv_hub_info->m_shift) |
+			((paddr >> uv_hub_info->m_val)
+						<< uv_hub_info->n_lshift);
+	else
+		paddr |= uv_soc_phys_ram_to_nasid(paddr)
+						<< uv_hub_info->gpa_shift;
 	return paddr;
 }
 
-
 /* socket virtual --> UV global physical address */
 static inline unsigned long uv_gpa(void *v)
 {
@@ -338,54 +516,89 @@ static inline unsigned long uv_gpa_to_soc_phys_ram(unsigned long gpa)
 	unsigned long paddr;
 	unsigned long remap_base = uv_hub_info->lowmem_remap_base;
 	unsigned long remap_top =  uv_hub_info->lowmem_remap_top;
+	unsigned int m_val = uv_hub_info->m_val;
 
+	if (m_val)
 		gpa = ((gpa << uv_hub_info->m_shift) >> uv_hub_info->m_shift) |
 			((gpa >> uv_hub_info->n_lshift) << uv_hub_info->m_val);
+
 	paddr = gpa & uv_hub_info->gpa_mask;
 	if (paddr >= remap_base && paddr < remap_base + remap_top)
 		paddr -= remap_base;
 	return paddr;
 }
 
-
-/* gpa -> pnode */
+/* gpa -> gnode */
 static inline unsigned long uv_gpa_to_gnode(unsigned long gpa)
 {
-	return gpa >> uv_hub_info->n_lshift;
+	unsigned int n_lshift = uv_hub_info->n_lshift;
+
+	if (n_lshift)
+		return gpa >> n_lshift;
+
+	return uv_gam_range(gpa)->nasid >> 1;
 }
 
 /* gpa -> pnode */
 static inline int uv_gpa_to_pnode(unsigned long gpa)
 {
-	unsigned long n_mask = (1UL << uv_hub_info->n_val) - 1;
-
-	return uv_gpa_to_gnode(gpa) & n_mask;
+	return uv_gpa_to_gnode(gpa) & uv_hub_info->pnode_mask;
 }
 
-/* gpa -> node offset*/
+/* gpa -> node offset */
 static inline unsigned long uv_gpa_to_offset(unsigned long gpa)
 {
-	return (gpa << uv_hub_info->m_shift) >> uv_hub_info->m_shift;
+	unsigned int m_shift = uv_hub_info->m_shift;
+
+	if (m_shift)
+		return (gpa << m_shift) >> m_shift;
+
+	return (gpa & uv_hub_info->gpa_mask) - uv_gam_range_base(gpa);
+}
+
+/* Convert socket to node */
+static inline int _uv_socket_to_node(int socket, unsigned short *s2nid)
+{
+	return s2nid ? s2nid[socket - uv_hub_info->min_socket] : socket;
+}
+
+static inline int uv_socket_to_node(int socket)
+{
+	return _uv_socket_to_node(socket, uv_hub_info->socket_to_node);
 }
 
 /* pnode, offset --> socket virtual */
 static inline void *uv_pnode_offset_to_vaddr(int pnode, unsigned long offset)
 {
-	return __va(((unsigned long)pnode << uv_hub_info->m_val) | offset);
-}
+	unsigned int m_val = uv_hub_info->m_val;
+	unsigned long base;
+	unsigned short sockid, node, *p2s;
 
+	if (m_val)
+		return __va(((unsigned long)pnode << m_val) | offset);
 
-/*
- * Extract a PNODE from an APICID (full apicid, not processor subset)
- */
+	p2s = uv_hub_info->pnode_to_socket;
+	sockid = p2s ? p2s[pnode - uv_hub_info->min_pnode] : pnode;
+	node = uv_socket_to_node(sockid);
+
+	/* limit address of previous socket is our base, except node 0 is 0 */
+	if (!node)
+		return __va((unsigned long)offset);
+
+	base = (unsigned long)(uv_hub_info->gr_table[node - 1].limit);
+	return __va(base << UV_GAM_RANGE_SHFT | offset);
+}
+
+/* Extract/Convert a PNODE from an APICID (full apicid, not processor subset) */
 static inline int uv_apicid_to_pnode(int apicid)
 {
-	return (apicid >> uv_hub_info->apic_pnode_shift);
+	int pnode = apicid >> uv_hub_info->apic_pnode_shift;
+	unsigned short *s2pn = uv_hub_info->socket_to_pnode;
+
+	return s2pn ? s2pn[pnode - uv_hub_info->min_socket] : pnode;
 }
 
-/*
- * Convert an apicid to the socket number on the blade
- */
+/* Convert an apicid to the socket number on the blade */
 static inline int uv_apicid_to_socket(int apicid)
 {
 	if (is_uv1_hub())
@@ -434,16 +647,6 @@ static inline unsigned long uv_read_global_mmr64(int pnode, unsigned long offset
 	return readq(uv_global_mmr64_address(pnode, offset));
 }
 
-/*
- * Global MMR space addresses when referenced by the GRU. (GRU does
- * NOT use socket addressing).
- */
-static inline unsigned long uv_global_gru_mmr_address(int pnode, unsigned long offset)
-{
-	return UV_GLOBAL_GRU_MMR_BASE | offset |
-		((unsigned long)pnode << uv_hub_info->m_val);
-}
-
 static inline void uv_write_global_mmr8(int pnode, unsigned long offset, unsigned char val)
 {
 	writeb(val, uv_global_mmr64_address(pnode, offset));
@@ -483,27 +686,23 @@ static inline void uv_write_local_mmr8(unsigned long offset, unsigned char val)
 	writeb(val, uv_local_mmr_address(offset));
 }
 
-/*
- * Structures and definitions for converting between cpu, node, pnode, and blade
- * numbers.
- */
-struct uv_blade_info {
-	unsigned short	nr_possible_cpus;
-	unsigned short	nr_online_cpus;
-	unsigned short	pnode;
-	short		memory_nid;
-	spinlock_t	nmi_lock;	/* obsolete, see uv_hub_nmi */
-	unsigned long	nmi_count;	/* obsolete, see uv_hub_nmi */
-};
-extern struct uv_blade_info *uv_blade_info;
-extern short *uv_node_to_blade;
-extern short *uv_cpu_to_blade;
-extern short uv_possible_blades;
-
 /* Blade-local cpu number of current cpu. Numbered 0 .. <# cpus on the blade> */
 static inline int uv_blade_processor_id(void)
 {
-	return uv_hub_info->blade_processor_id;
+	return uv_cpu_info->blade_cpu_id;
+}
+
+/* Blade-local cpu number of cpu N. Numbered 0 .. <# cpus on the blade> */
+static inline int uv_cpu_blade_processor_id(int cpu)
+{
+	return uv_cpu_info_per(cpu)->blade_cpu_id;
+}
+#define _uv_cpu_blade_processor_id 1	/* indicate function available */
+
+/* Blade number to Node number (UV1..UV4 is 1:1) */
+static inline int uv_blade_to_node(int blade)
+{
+	return blade;
 }
 
 /* Blade number of current cpu. Numnbered 0 .. <#blades -1> */
@@ -512,55 +711,60 @@ static inline int uv_numa_blade_id(void)
 	return uv_hub_info->numa_blade_id;
 }
 
-/* Convert a cpu number to the the UV blade number */
-static inline int uv_cpu_to_blade_id(int cpu)
+/*
+ * Convert linux node number to the UV blade number.
+ * .. Currently for UV1 thru UV4 the node and the blade are identical.
+ * .. If this changes then you MUST check references to this function!
+ */
+static inline int uv_node_to_blade_id(int nid)
 {
-	return uv_cpu_to_blade[cpu];
+	return nid;
 }
 
-/* Convert linux node number to the UV blade number */
-static inline int uv_node_to_blade_id(int nid)
+/* Convert a cpu number to the the UV blade number */
+static inline int uv_cpu_to_blade_id(int cpu)
 {
-	return uv_node_to_blade[nid];
+	return uv_node_to_blade_id(cpu_to_node(cpu));
 }
 
 /* Convert a blade id to the PNODE of the blade */
 static inline int uv_blade_to_pnode(int bid)
 {
-	return uv_blade_info[bid].pnode;
+	return uv_hub_info_list(uv_blade_to_node(bid))->pnode;
 }
 
 /* Nid of memory node on blade. -1 if no blade-local memory */
 static inline int uv_blade_to_memory_nid(int bid)
 {
-	return uv_blade_info[bid].memory_nid;
+	return uv_hub_info_list(uv_blade_to_node(bid))->memory_nid;
 }
 
 /* Determine the number of possible cpus on a blade */
 static inline int uv_blade_nr_possible_cpus(int bid)
 {
-	return uv_blade_info[bid].nr_possible_cpus;
+	return uv_hub_info_list(uv_blade_to_node(bid))->nr_possible_cpus;
 }
 
 /* Determine the number of online cpus on a blade */
 static inline int uv_blade_nr_online_cpus(int bid)
 {
-	return uv_blade_info[bid].nr_online_cpus;
+	return uv_hub_info_list(uv_blade_to_node(bid))->nr_online_cpus;
 }
 
 /* Convert a cpu id to the PNODE of the blade containing the cpu */
 static inline int uv_cpu_to_pnode(int cpu)
 {
-	return uv_blade_info[uv_cpu_to_blade_id(cpu)].pnode;
+	return uv_cpu_hub_info(cpu)->pnode;
 }
 
 /* Convert a linux node number to the PNODE of the blade */
 static inline int uv_node_to_pnode(int nid)
 {
-	return uv_blade_info[uv_node_to_blade_id(nid)].pnode;
+	return uv_hub_info_list(nid)->pnode;
 }
 
 /* Maximum possible number of blades */
+extern short uv_possible_blades;
 static inline int uv_num_possible_blades(void)
 {
 	return uv_possible_blades;
@@ -578,9 +782,7 @@ extern void uv_nmi_setup(void);
 /* Newer SMM NMI handler, not present in all systems */
 #define UVH_NMI_MMRX		UVH_EVENT_OCCURRED0
 #define UVH_NMI_MMRX_CLEAR	UVH_EVENT_OCCURRED0_ALIAS
-#define UVH_NMI_MMRX_SHIFT	(is_uv1_hub() ? \
-					UV1H_EVENT_OCCURRED0_EXTIO_INT0_SHFT :\
-					UVXH_EVENT_OCCURRED0_EXTIO_INT0_SHFT)
+#define UVH_NMI_MMRX_SHIFT	UVH_EVENT_OCCURRED0_EXTIO_INT0_SHFT
 #define	UVH_NMI_MMRX_TYPE	"EXTIO_INT0"
 
 /* Non-zero indicates newer SMM NMI handler present */
@@ -622,9 +824,9 @@ DECLARE_PER_CPU(struct uv_cpu_nmi_s, uv_cpu_nmi);
 /* Update SCIR state */
 static inline void uv_set_scir_bits(unsigned char value)
 {
-	if (uv_hub_info->scir.state != value) {
-		uv_hub_info->scir.state = value;
-		uv_write_local_mmr8(uv_hub_info->scir.offset, value);
+	if (uv_scir_info->state != value) {
+		uv_scir_info->state = value;
+		uv_write_local_mmr8(uv_scir_info->offset, value);
 	}
 }
 
@@ -635,10 +837,10 @@ static inline unsigned long uv_scir_offset(int apicid)
 
 static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value)
 {
-	if (uv_cpu_hub_info(cpu)->scir.state != value) {
+	if (uv_cpu_scir_info(cpu)->state != value) {
 		uv_write_global_mmr8(uv_cpu_to_pnode(cpu),
-				uv_cpu_hub_info(cpu)->scir.offset, value);
-		uv_cpu_hub_info(cpu)->scir.state = value;
+				uv_cpu_scir_info(cpu)->offset, value);
+		uv_cpu_scir_info(cpu)->state = value;
 	}
 }
 
@@ -666,10 +868,7 @@ static inline void uv_hub_send_ipi(int pnode, int apicid, int vector)
 
 /*
  * Get the minimum revision number of the hub chips within the partition.
- *     1 - UV1 rev 1.0 initial silicon
- *     2 - UV1 rev 2.0 production silicon
- *     3 - UV2 rev 1.0 initial silicon
- *     5 - UV3 rev 1.0 initial silicon
+ * (See UVx_HUB_REVISION_BASE above for specific values.)
  */
 static inline int uv_get_min_hub_revision_id(void)
 {

arch/x86/kernel/apic/x2apic_uv_x.c

@@ -48,12 +48,35 @@ static u64 gru_start_paddr, gru_end_paddr;
 static u64 gru_dist_base, gru_first_node_paddr = -1LL, gru_last_node_paddr;
 static u64 gru_dist_lmask, gru_dist_umask;
 static union uvh_apicid uvh_apicid;
+
+/* info derived from CPUID */
+static struct {
+	unsigned int apicid_shift;
+	unsigned int apicid_mask;
+	unsigned int socketid_shift;	/* aka pnode_shift for UV1/2/3 */
+	unsigned int pnode_mask;
+	unsigned int gpa_shift;
+} uv_cpuid;
+
 int uv_min_hub_revision_id;
 EXPORT_SYMBOL_GPL(uv_min_hub_revision_id);
 unsigned int uv_apicid_hibits;
 EXPORT_SYMBOL_GPL(uv_apicid_hibits);
 
 static struct apic apic_x2apic_uv_x;
+static struct uv_hub_info_s uv_hub_info_node0;
+
+/* Set this to use hardware error handler instead of kernel panic */
+static int disable_uv_undefined_panic = 1;
+unsigned long uv_undefined(char *str)
+{
+	if (likely(!disable_uv_undefined_panic))
+		panic("UV: error: undefined MMR: %s\n", str);
+	else
+		pr_crit("UV: error: undefined MMR: %s\n", str);
+	return ~0ul;	/* cause a machine fault  */
+}
+EXPORT_SYMBOL(uv_undefined);
 
 static unsigned long __init uv_early_read_mmr(unsigned long addr)
 {
@@ -108,21 +131,71 @@ static int __init early_get_pnodeid(void)
 	case UV3_HUB_PART_NUMBER_X:
 		uv_min_hub_revision_id += UV3_HUB_REVISION_BASE;
 		break;
+	case UV4_HUB_PART_NUMBER:
+		uv_min_hub_revision_id += UV4_HUB_REVISION_BASE - 1;
+		break;
 	}
 
 	uv_hub_info->hub_revision = uv_min_hub_revision_id;
-	pnode = (node_id.s.node_id >> 1) & ((1 << m_n_config.s.n_skt) - 1);
+	uv_cpuid.pnode_mask = (1 << m_n_config.s.n_skt) - 1;
+	pnode = (node_id.s.node_id >> 1) & uv_cpuid.pnode_mask;
+	uv_cpuid.gpa_shift = 46;	/* default unless changed */
+
+	pr_info("UV: rev:%d part#:%x nodeid:%04x n_skt:%d pnmsk:%x pn:%x\n",
+		node_id.s.revision, node_id.s.part_number, node_id.s.node_id,
+		m_n_config.s.n_skt, uv_cpuid.pnode_mask, pnode);
 	return pnode;
 }
 
-static void __init early_get_apic_pnode_shift(void)
+/* [copied from arch/x86/kernel/cpu/topology.c:detect_extended_topology()] */
+#define SMT_LEVEL	0	/* leaf 0xb SMT level */
+#define INVALID_TYPE	0	/* leaf 0xb sub-leaf types */
+#define SMT_TYPE	1
+#define CORE_TYPE	2
+#define LEAFB_SUBTYPE(ecx)		(((ecx) >> 8) & 0xff)
+#define BITS_SHIFT_NEXT_LEVEL(eax)	((eax) & 0x1f)
+
+static void set_x2apic_bits(void)
 {
+	unsigned int eax, ebx, ecx, edx, sub_index;
+	unsigned int sid_shift;
+
+	cpuid(0, &eax, &ebx, &ecx, &edx);
+	if (eax < 0xb) {
+		pr_info("UV: CPU does not have CPUID.11\n");
+		return;
+	}
+	cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
+	if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE)) {
+		pr_info("UV: CPUID.11 not implemented\n");
+		return;
+	}
+	sid_shift = BITS_SHIFT_NEXT_LEVEL(eax);
+	sub_index = 1;
+	do {
+		cpuid_count(0xb, sub_index, &eax, &ebx, &ecx, &edx);
+		if (LEAFB_SUBTYPE(ecx) == CORE_TYPE) {
+			sid_shift = BITS_SHIFT_NEXT_LEVEL(eax);
+			break;
+		}
+		sub_index++;
+	} while (LEAFB_SUBTYPE(ecx) != INVALID_TYPE);
+	uv_cpuid.apicid_shift = 0;
+	uv_cpuid.apicid_mask = (~(-1 << sid_shift));
+	uv_cpuid.socketid_shift = sid_shift;
+}
+
+static void __init early_get_apic_socketid_shift(void)
+{
+	if (is_uv2_hub() || is_uv3_hub())
 		uvh_apicid.v = uv_early_read_mmr(UVH_APICID);
-	if (!uvh_apicid.v)
-		/*
-		 * Old bios, use default value
-		 */
-		uvh_apicid.s.pnode_shift = UV_APIC_PNODE_SHIFT;
+
+	set_x2apic_bits();
+
+	pr_info("UV: apicid_shift:%d apicid_mask:0x%x\n",
+		uv_cpuid.apicid_shift, uv_cpuid.apicid_mask);
+	pr_info("UV: socketid_shift:%d pnode_mask:0x%x\n",
+		uv_cpuid.socketid_shift, uv_cpuid.pnode_mask);
 }
 
 /*
@@ -150,13 +223,18 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 	if (strncmp(oem_id, "SGI", 3) != 0)
 		return 0;
 
+	/* Setup early hub type field in uv_hub_info for Node 0 */
+	uv_cpu_info->p_uv_hub_info = &uv_hub_info_node0;
+
 	/*
 	 * Determine UV arch type.
 	 *   SGI: UV100/1000
 	 *   SGI2: UV2000/3000
 	 *   SGI3: UV300 (truncated to 4 chars because of different varieties)
+	 *   SGI4: UV400 (truncated to 4 chars because of different varieties)
 	 */
 	uv_hub_info->hub_revision =
+		!strncmp(oem_id, "SGI4", 4) ? UV4_HUB_REVISION_BASE :
 		!strncmp(oem_id, "SGI3", 4) ? UV3_HUB_REVISION_BASE :
 		!strcmp(oem_id, "SGI2") ? UV2_HUB_REVISION_BASE :
 		!strcmp(oem_id, "SGI") ? UV1_HUB_REVISION_BASE : 0;
@@ -165,7 +243,7 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 		goto badbios;
 
 	pnodeid = early_get_pnodeid();
-	early_get_apic_pnode_shift();
+	early_get_apic_socketid_shift();
 	x86_platform.is_untracked_pat_range =  uv_is_untracked_pat_range;
 	x86_platform.nmi_init = uv_nmi_init;
 
@@ -211,17 +289,11 @@ int is_uv_system(void)
 }
 EXPORT_SYMBOL_GPL(is_uv_system);
 
-DEFINE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
-EXPORT_PER_CPU_SYMBOL_GPL(__uv_hub_info);
+void **__uv_hub_info_list;
+EXPORT_SYMBOL_GPL(__uv_hub_info_list);
 
-struct uv_blade_info *uv_blade_info;
-EXPORT_SYMBOL_GPL(uv_blade_info);
-
-short *uv_node_to_blade;
-EXPORT_SYMBOL_GPL(uv_node_to_blade);
-
-short *uv_cpu_to_blade;
-EXPORT_SYMBOL_GPL(uv_cpu_to_blade);
+DEFINE_PER_CPU(struct uv_cpu_info_s, __uv_cpu_info);
+EXPORT_PER_CPU_SYMBOL_GPL(__uv_cpu_info);
 
 short uv_possible_blades;
 EXPORT_SYMBOL_GPL(uv_possible_blades);
@@ -229,6 +301,115 @@ EXPORT_SYMBOL_GPL(uv_possible_blades);
 unsigned long sn_rtc_cycles_per_second;
 EXPORT_SYMBOL(sn_rtc_cycles_per_second);
 
+/* the following values are used for the per node hub info struct */
+static __initdata unsigned short *_node_to_pnode;
+static __initdata unsigned short _min_socket, _max_socket;
+static __initdata unsigned short _min_pnode, _max_pnode, _gr_table_len;
+static __initdata struct uv_gam_range_entry *uv_gre_table;
+static __initdata struct uv_gam_parameters *uv_gp_table;
+static __initdata unsigned short *_socket_to_node;
+static __initdata unsigned short *_socket_to_pnode;
+static __initdata unsigned short *_pnode_to_socket;
+static __initdata struct uv_gam_range_s *_gr_table;
+#define	SOCK_EMPTY	((unsigned short)~0)
+
+extern int uv_hub_info_version(void)
+{
+	return UV_HUB_INFO_VERSION;
+}
+EXPORT_SYMBOL(uv_hub_info_version);
+
+/* Build GAM range lookup table */
+static __init void build_uv_gr_table(void)
+{
+	struct uv_gam_range_entry *gre = uv_gre_table;
+	struct uv_gam_range_s *grt;
+	unsigned long last_limit = 0, ram_limit = 0;
+	int bytes, i, sid, lsid = -1;
+
+	if (!gre)
+		return;
+
+	bytes = _gr_table_len * sizeof(struct uv_gam_range_s);
+	grt = kzalloc(bytes, GFP_KERNEL);
+	BUG_ON(!grt);
+	_gr_table = grt;
+
+	for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) {
+		if (gre->type == UV_GAM_RANGE_TYPE_HOLE) {
+			if (!ram_limit) {   /* mark hole between ram/non-ram */
+				ram_limit = last_limit;
+				last_limit = gre->limit;
+				lsid++;
+				continue;
+			}
+			last_limit = gre->limit;
+			pr_info("UV: extra hole in GAM RE table @%d\n",
+				(int)(gre - uv_gre_table));
+			continue;
+		}
+		if (_max_socket < gre->sockid) {
+			pr_err("UV: GAM table sockid(%d) too large(>%d) @%d\n",
+				gre->sockid, _max_socket,
+				(int)(gre - uv_gre_table));
+			continue;
+		}
+		sid = gre->sockid - _min_socket;
+		if (lsid < sid) {		/* new range */
+			grt = &_gr_table[sid];
+			grt->base = lsid;
+			grt->nasid = gre->nasid;
+			grt->limit = last_limit = gre->limit;
+			lsid = sid;
+			continue;
+		}
+		if (lsid == sid && !ram_limit) {	/* update range */
+			if (grt->limit == last_limit) {	/* .. if contiguous */
+				grt->limit = last_limit = gre->limit;
+				continue;
+			}
+		}
+		if (!ram_limit) {		/* non-contiguous ram range */
+			grt++;
+			grt->base = sid - 1;
+			grt->nasid = gre->nasid;
+			grt->limit = last_limit = gre->limit;
+			continue;
+		}
+		grt++;				/* non-contiguous/non-ram */
+		grt->base = grt - _gr_table;	/* base is this entry */
+		grt->nasid = gre->nasid;
+		grt->limit = last_limit = gre->limit;
+		lsid++;
+	}
+
+	/* shorten table if possible */
+	grt++;
+	i = grt - _gr_table;
+	if (i < _gr_table_len) {
+		void *ret;
+
+		bytes = i * sizeof(struct uv_gam_range_s);
+		ret = krealloc(_gr_table, bytes, GFP_KERNEL);
+		if (ret) {
+			_gr_table = ret;
+			_gr_table_len = i;
+		}
+	}
+
+	/* display resultant gam range table */
+	for (i = 0, grt = _gr_table; i < _gr_table_len; i++, grt++) {
+		int gb = grt->base;
+		unsigned long start = gb < 0 ?  0 :
+			(unsigned long)_gr_table[gb].limit << UV_GAM_RANGE_SHFT;
+		unsigned long end =
+			(unsigned long)grt->limit << UV_GAM_RANGE_SHFT;
+
+		pr_info("UV: GAM Range %2d %04x 0x%013lx-0x%013lx (%d)\n",
+			i, grt->nasid, start, end, gb);
+	}
+}
+
 static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip)
 {
 	unsigned long val;
@@ -355,7 +536,6 @@ static unsigned long set_apic_id(unsigned int id)
 
 static unsigned int uv_read_apic_id(void)
 {
-
 	return x2apic_get_apic_id(apic_read(APIC_ID));
 }
 
@@ -430,58 +610,38 @@ static void set_x2apic_extra_bits(int pnode)
 	__this_cpu_write(x2apic_extra_bits, pnode << uvh_apicid.s.pnode_shift);
 }
 
-/*
- * Called on boot cpu.
- */
-static __init int boot_pnode_to_blade(int pnode)
-{
-	int blade;
-
-	for (blade = 0; blade < uv_num_possible_blades(); blade++)
-		if (pnode == uv_blade_info[blade].pnode)
-			return blade;
-	BUG();
-}
-
-struct redir_addr {
-	unsigned long redirect;
-	unsigned long alias;
-};
-
+#define	UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_LENGTH	3
 #define DEST_SHIFT UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT
 
-static __initdata struct redir_addr redir_addrs[] = {
-	{UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR, UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR},
-	{UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR, UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR},
-	{UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR, UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR},
-};
-
-static unsigned char get_n_lshift(int m_val)
-{
-	union uv3h_gr0_gam_gr_config_u m_gr_config;
-
-	if (is_uv1_hub())
-		return m_val;
-
-	if (is_uv2_hub())
-		return m_val == 40 ? 40 : 39;
-
-	m_gr_config.v = uv_read_local_mmr(UV3H_GR0_GAM_GR_CONFIG);
-	return m_gr_config.s3.m_skt;
-}
-
 static __init void get_lowmem_redirect(unsigned long *base, unsigned long *size)
 {
 	union uvh_rh_gam_alias210_overlay_config_2_mmr_u alias;
 	union uvh_rh_gam_alias210_redirect_config_2_mmr_u redirect;
+	unsigned long m_redirect;
+	unsigned long m_overlay;
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(redir_addrs); i++) {
-		alias.v = uv_read_local_mmr(redir_addrs[i].alias);
+	for (i = 0; i < UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_LENGTH; i++) {
+		switch (i) {
+		case 0:
+			m_redirect = UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR;
+			m_overlay = UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR;
+			break;
+		case 1:
+			m_redirect = UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR;
+			m_overlay = UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR;
+			break;
+		case 2:
+			m_redirect = UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR;
+			m_overlay = UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR;
+			break;
+		}
+		alias.v = uv_read_local_mmr(m_overlay);
 		if (alias.s.enable && alias.s.base == 0) {
 			*size = (1UL << alias.s.m_alias);
-			redirect.v = uv_read_local_mmr(redir_addrs[i].redirect);
-			*base = (unsigned long)redirect.s.dest_base << DEST_SHIFT;
+			redirect.v = uv_read_local_mmr(m_redirect);
+			*base = (unsigned long)redirect.s.dest_base
+							<< DEST_SHIFT;
 			return;
 		}
 	}
@@ -544,6 +704,8 @@ static __init void map_gru_high(int max_pnode)
 {
 	union uvh_rh_gam_gru_overlay_config_mmr_u gru;
 	int shift = UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT;
+	unsigned long mask = UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK;
+	unsigned long base;
 
 	gru.v = uv_read_local_mmr(UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR);
 	if (!gru.s.enable) {
@@ -555,8 +717,9 @@ static __init void map_gru_high(int max_pnode)
 		map_gru_distributed(gru.v);
 		return;
 	}
-	map_high("GRU", gru.s.base, shift, shift, max_pnode, map_wb);
-	gru_start_paddr = ((u64)gru.s.base << shift);
+	base = (gru.v & mask) >> shift;
+	map_high("GRU", base, shift, shift, max_pnode, map_wb);
+	gru_start_paddr = ((u64)base << shift);
 	gru_end_paddr = gru_start_paddr + (1UL << shift) * (max_pnode + 1);
 }
 
@@ -595,6 +758,7 @@ static __initdata struct mmioh_config mmiohs[] = {
 	},
 };
 
+/* UV3 & UV4 have identical MMIOH overlay configs */
 static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode)
 {
 	union uv3h_rh_gam_mmioh_overlay_config0_mmr_u overlay;
@@ -674,7 +838,7 @@ static __init void map_mmioh_high(int min_pnode, int max_pnode)
 	unsigned long mmr, base;
 	int shift, enable, m_io, n_io;
 
-	if (is_uv3_hub()) {
+	if (is_uv3_hub() || is_uv4_hub()) {
 		/* Map both MMIOH Regions */
 		map_mmioh_high_uv3(0, min_pnode, max_pnode);
 		map_mmioh_high_uv3(1, min_pnode, max_pnode);
@@ -739,8 +903,8 @@ static __init void uv_rtc_init(void)
  */
 static void uv_heartbeat(unsigned long ignored)
 {
-	struct timer_list *timer = &uv_hub_info->scir.timer;
-	unsigned char bits = uv_hub_info->scir.state;
+	struct timer_list *timer = &uv_scir_info->timer;
+	unsigned char bits = uv_scir_info->state;
 
 	/* flip heartbeat bit */
 	bits ^= SCIR_CPU_HEARTBEAT;
@@ -760,14 +924,14 @@ static void uv_heartbeat(unsigned long ignored)
 
 static void uv_heartbeat_enable(int cpu)
 {
-	while (!uv_cpu_hub_info(cpu)->scir.enabled) {
-		struct timer_list *timer = &uv_cpu_hub_info(cpu)->scir.timer;
+	while (!uv_cpu_scir_info(cpu)->enabled) {
+		struct timer_list *timer = &uv_cpu_scir_info(cpu)->timer;
 
 		uv_set_cpu_scir_bits(cpu, SCIR_CPU_HEARTBEAT|SCIR_CPU_ACTIVITY);
 		setup_timer(timer, uv_heartbeat, cpu);
 		timer->expires = jiffies + SCIR_CPU_HB_INTERVAL;
 		add_timer_on(timer, cpu);
-		uv_cpu_hub_info(cpu)->scir.enabled = 1;
+		uv_cpu_scir_info(cpu)->enabled = 1;
 
 		/* also ensure that boot cpu is enabled */
 		cpu = 0;
@@ -777,9 +941,9 @@ static void uv_heartbeat_enable(int cpu)
 #ifdef CONFIG_HOTPLUG_CPU
 static void uv_heartbeat_disable(int cpu)
 {
-	if (uv_cpu_hub_info(cpu)->scir.enabled) {
-		uv_cpu_hub_info(cpu)->scir.enabled = 0;
-		del_timer(&uv_cpu_hub_info(cpu)->scir.timer);
+	if (uv_cpu_scir_info(cpu)->enabled) {
+		uv_cpu_scir_info(cpu)->enabled = 0;
+		del_timer(&uv_cpu_scir_info(cpu)->timer);
 	}
 	uv_set_cpu_scir_bits(cpu, 0xff);
 }
@@ -862,155 +1026,475 @@ int uv_set_vga_state(struct pci_dev *pdev, bool decode,
 void uv_cpu_init(void)
 {
 	/* CPU 0 initialization will be done via uv_system_init. */
-	if (!uv_blade_info)
+	if (smp_processor_id() == 0)
 		return;
 
-	uv_blade_info[uv_numa_blade_id()].nr_online_cpus++;
+	uv_hub_info->nr_online_cpus++;
 
 	if (get_uv_system_type() == UV_NON_UNIQUE_APIC)
 		set_x2apic_extra_bits(uv_hub_info->pnode);
 }
 
-void __init uv_system_init(void)
+struct mn {
+	unsigned char	m_val;
+	unsigned char	n_val;
+	unsigned char	m_shift;
+	unsigned char	n_lshift;
+};
+
+static void get_mn(struct mn *mnp)
 {
 	union uvh_rh_gam_config_mmr_u m_n_config;
-	union uvh_node_id_u node_id;
-	unsigned long gnode_upper, lowmem_redir_base, lowmem_redir_size;
-	int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val;
-	int gnode_extra, min_pnode = 999999, max_pnode = -1;
-	unsigned long mmr_base, present, paddr;
-	unsigned short pnode_mask;
-	unsigned char n_lshift;
-	char *hub = (is_uv1_hub() ? "UV100/1000" :
-		    (is_uv2_hub() ? "UV2000/3000" :
-		    (is_uv3_hub() ? "UV300" : NULL)));
+	union uv3h_gr0_gam_gr_config_u m_gr_config;
 
-	if (!hub) {
-		pr_err("UV: Unknown/unsupported UV hub\n");
-		return;
+	m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR);
+	mnp->n_val = m_n_config.s.n_skt;
+	if (is_uv4_hub()) {
+		mnp->m_val = 0;
+		mnp->n_lshift = 0;
+	} else if (is_uv3_hub()) {
+		mnp->m_val = m_n_config.s3.m_skt;
+		m_gr_config.v = uv_read_local_mmr(UV3H_GR0_GAM_GR_CONFIG);
+		mnp->n_lshift = m_gr_config.s3.m_skt;
+	} else if (is_uv2_hub()) {
+		mnp->m_val = m_n_config.s2.m_skt;
+		mnp->n_lshift = mnp->m_val == 40 ? 40 : 39;
+	} else if (is_uv1_hub()) {
+		mnp->m_val = m_n_config.s1.m_skt;
+		mnp->n_lshift = mnp->m_val;
 	}
-	pr_info("UV: Found %s hub\n", hub);
+	mnp->m_shift = mnp->m_val ? 64 - mnp->m_val : 0;
+}
 
-	map_low_mmrs();
+void __init uv_init_hub_info(struct uv_hub_info_s *hub_info)
+{
+	struct mn mn = {0};	/* avoid unitialized warnings */
+	union uvh_node_id_u node_id;
+
+	get_mn(&mn);
+	hub_info->m_val = mn.m_val;
+	hub_info->n_val = mn.n_val;
+	hub_info->m_shift = mn.m_shift;
+	hub_info->n_lshift = mn.n_lshift ? mn.n_lshift : 0;
+
+	hub_info->hub_revision = uv_hub_info->hub_revision;
+	hub_info->pnode_mask = uv_cpuid.pnode_mask;
+	hub_info->min_pnode = _min_pnode;
+	hub_info->min_socket = _min_socket;
+	hub_info->pnode_to_socket = _pnode_to_socket;
+	hub_info->socket_to_node = _socket_to_node;
+	hub_info->socket_to_pnode = _socket_to_pnode;
+	hub_info->gr_table_len = _gr_table_len;
+	hub_info->gr_table = _gr_table;
+	hub_info->gpa_mask = mn.m_val ?
+		(1UL << (mn.m_val + mn.n_val)) - 1 :
+		(1UL << uv_cpuid.gpa_shift) - 1;
 
-	m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR );
-	m_val = m_n_config.s.m_skt;
-	n_val = m_n_config.s.n_skt;
-	pnode_mask = (1 << n_val) - 1;
-	n_lshift = get_n_lshift(m_val);
-	mmr_base =
+	node_id.v = uv_read_local_mmr(UVH_NODE_ID);
+	hub_info->gnode_extra =
+		(node_id.s.node_id & ~((1 << mn.n_val) - 1)) >> 1;
+
+	hub_info->gnode_upper =
+		((unsigned long)hub_info->gnode_extra << mn.m_val);
+
+	if (uv_gp_table) {
+		hub_info->global_mmr_base = uv_gp_table->mmr_base;
+		hub_info->global_mmr_shift = uv_gp_table->mmr_shift;
+		hub_info->global_gru_base = uv_gp_table->gru_base;
+		hub_info->global_gru_shift = uv_gp_table->gru_shift;
+		hub_info->gpa_shift = uv_gp_table->gpa_shift;
+		hub_info->gpa_mask = (1UL << hub_info->gpa_shift) - 1;
+	} else {
+		hub_info->global_mmr_base =
 			uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) &
 					~UV_MMR_ENABLE;
+		hub_info->global_mmr_shift = _UV_GLOBAL_MMR64_PNODE_SHIFT;
+	}
 
-	node_id.v = uv_read_local_mmr(UVH_NODE_ID);
-	gnode_extra = (node_id.s.node_id & ~((1 << n_val) - 1)) >> 1;
-	gnode_upper = ((unsigned long)gnode_extra  << m_val);
-	pr_info("UV: N:%d M:%d pnode_mask:0x%x gnode_upper/extra:0x%lx/0x%x n_lshift 0x%x\n",
-			n_val, m_val, pnode_mask, gnode_upper, gnode_extra,
-			n_lshift);
+	get_lowmem_redirect(
+		&hub_info->lowmem_remap_base, &hub_info->lowmem_remap_top);
 
-	pr_info("UV: global MMR base 0x%lx\n", mmr_base);
+	hub_info->apic_pnode_shift = uv_cpuid.socketid_shift;
 
-	for(i = 0; i < UVH_NODE_PRESENT_TABLE_DEPTH; i++)
-		uv_possible_blades +=
-		  hweight64(uv_read_local_mmr( UVH_NODE_PRESENT_TABLE + i * 8));
+	/* show system specific info */
+	pr_info("UV: N:%d M:%d m_shift:%d n_lshift:%d\n",
+		hub_info->n_val, hub_info->m_val,
+		hub_info->m_shift, hub_info->n_lshift);
 
-	/* uv_num_possible_blades() is really the hub count */
-	pr_info("UV: Found %d blades, %d hubs\n",
-			is_uv1_hub() ? uv_num_possible_blades() :
-			(uv_num_possible_blades() + 1) / 2,
-			uv_num_possible_blades());
+	pr_info("UV: gpa_mask/shift:0x%lx/%d pnode_mask:0x%x apic_pns:%d\n",
+		hub_info->gpa_mask, hub_info->gpa_shift,
+		hub_info->pnode_mask, hub_info->apic_pnode_shift);
 
-	bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades();
-	uv_blade_info = kzalloc(bytes, GFP_KERNEL);
-	BUG_ON(!uv_blade_info);
+	pr_info("UV: mmr_base/shift:0x%lx/%ld gru_base/shift:0x%lx/%ld\n",
+		hub_info->global_mmr_base, hub_info->global_mmr_shift,
+		hub_info->global_gru_base, hub_info->global_gru_shift);
 
-	for (blade = 0; blade < uv_num_possible_blades(); blade++)
-		uv_blade_info[blade].memory_nid = -1;
+	pr_info("UV: gnode_upper:0x%lx gnode_extra:0x%x\n",
+		hub_info->gnode_upper, hub_info->gnode_extra);
+}
 
-	get_lowmem_redirect(&lowmem_redir_base, &lowmem_redir_size);
+static void __init decode_gam_params(unsigned long ptr)
+{
+	uv_gp_table = (struct uv_gam_parameters *)ptr;
 
-	bytes = sizeof(uv_node_to_blade[0]) * num_possible_nodes();
-	uv_node_to_blade = kmalloc(bytes, GFP_KERNEL);
-	BUG_ON(!uv_node_to_blade);
-	memset(uv_node_to_blade, 255, bytes);
+	pr_info("UV: GAM Params...\n");
+	pr_info("UV: mmr_base/shift:0x%llx/%d gru_base/shift:0x%llx/%d gpa_shift:%d\n",
+		uv_gp_table->mmr_base, uv_gp_table->mmr_shift,
+		uv_gp_table->gru_base, uv_gp_table->gru_shift,
+		uv_gp_table->gpa_shift);
+}
+
+static void __init decode_gam_rng_tbl(unsigned long ptr)
+{
+	struct uv_gam_range_entry *gre = (struct uv_gam_range_entry *)ptr;
+	unsigned long lgre = 0;
+	int index = 0;
+	int sock_min = 999999, pnode_min = 99999;
+	int sock_max = -1, pnode_max = -1;
+
+	uv_gre_table = gre;
+	for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) {
+		if (!index) {
+			pr_info("UV: GAM Range Table...\n");
+			pr_info("UV:  # %20s %14s %5s %4s %5s %3s %2s %3s\n",
+				"Range", "", "Size", "Type", "NASID",
+				"SID", "PN", "PXM");
+		}
+		pr_info(
+		"UV: %2d: 0x%014lx-0x%014lx %5luG %3d   %04x  %02x %02x %3d\n",
+			index++,
+			(unsigned long)lgre << UV_GAM_RANGE_SHFT,
+			(unsigned long)gre->limit << UV_GAM_RANGE_SHFT,
+			((unsigned long)(gre->limit - lgre)) >>
+				(30 - UV_GAM_RANGE_SHFT), /* 64M -> 1G */
+			gre->type, gre->nasid, gre->sockid,
+			gre->pnode, gre->pxm);
+
+		lgre = gre->limit;
+		if (sock_min > gre->sockid)
+			sock_min = gre->sockid;
+		if (sock_max < gre->sockid)
+			sock_max = gre->sockid;
+		if (pnode_min > gre->pnode)
+			pnode_min = gre->pnode;
+		if (pnode_max < gre->pnode)
+			pnode_max = gre->pnode;
+	}
+	_min_socket = sock_min;
+	_max_socket = sock_max;
+	_min_pnode = pnode_min;
+	_max_pnode = pnode_max;
+	_gr_table_len = index;
+	pr_info(
+	"UV: GRT: %d entries, sockets(min:%x,max:%x) pnodes(min:%x,max:%x)\n",
+		index, _min_socket, _max_socket, _min_pnode, _max_pnode);
+}
+
+static void __init decode_uv_systab(void)
+{
+	struct uv_systab *st;
+	int i;
 
-	bytes = sizeof(uv_cpu_to_blade[0]) * num_possible_cpus();
-	uv_cpu_to_blade = kmalloc(bytes, GFP_KERNEL);
-	BUG_ON(!uv_cpu_to_blade);
-	memset(uv_cpu_to_blade, 255, bytes);
+	st = uv_systab;
+	if ((!st || st->revision < UV_SYSTAB_VERSION_UV4) && !is_uv4_hub())
+		return;
+	if (st->revision != UV_SYSTAB_VERSION_UV4_LATEST) {
+		pr_crit(
+		"UV: BIOS UVsystab version(%x) mismatch, expecting(%x)\n",
+			st->revision, UV_SYSTAB_VERSION_UV4_LATEST);
+		BUG();
+	}
 
-	blade = 0;
+	for (i = 0; st->entry[i].type != UV_SYSTAB_TYPE_UNUSED; i++) {
+		unsigned long ptr = st->entry[i].offset;
+
+		if (!ptr)
+			continue;
+
+		ptr = ptr + (unsigned long)st;
+
+		switch (st->entry[i].type) {
+		case UV_SYSTAB_TYPE_GAM_PARAMS:
+			decode_gam_params(ptr);
+			break;
+
+		case UV_SYSTAB_TYPE_GAM_RNG_TBL:
+			decode_gam_rng_tbl(ptr);
+			break;
+		}
+	}
+}
+
+/*
+ * Setup physical blade translations from UVH_NODE_PRESENT_TABLE
+ * .. NB: UVH_NODE_PRESENT_TABLE is going away,
+ * .. being replaced by GAM Range Table
+ */
+static __init void boot_init_possible_blades(struct uv_hub_info_s *hub_info)
+{
+	int i, uv_pb = 0;
+
+	pr_info("UV: NODE_PRESENT_DEPTH = %d\n", UVH_NODE_PRESENT_TABLE_DEPTH);
 	for (i = 0; i < UVH_NODE_PRESENT_TABLE_DEPTH; i++) {
-		present = uv_read_local_mmr(UVH_NODE_PRESENT_TABLE + i * 8);
-		for (j = 0; j < 64; j++) {
-			if (!test_bit(j, &present))
+		unsigned long np;
+
+		np = uv_read_local_mmr(UVH_NODE_PRESENT_TABLE + i * 8);
+		if (np)
+			pr_info("UV: NODE_PRESENT(%d) = 0x%016lx\n", i, np);
+
+		uv_pb += hweight64(np);
+	}
+	if (uv_possible_blades != uv_pb)
+		uv_possible_blades = uv_pb;
+}
+
+static void __init build_socket_tables(void)
+{
+	struct uv_gam_range_entry *gre = uv_gre_table;
+	int num, nump;
+	int cpu, i, lnid;
+	int minsock = _min_socket;
+	int maxsock = _max_socket;
+	int minpnode = _min_pnode;
+	int maxpnode = _max_pnode;
+	size_t bytes;
+
+	if (!gre) {
+		if (is_uv1_hub() || is_uv2_hub() || is_uv3_hub()) {
+			pr_info("UV: No UVsystab socket table, ignoring\n");
+			return;		/* not required */
+		}
+		pr_crit(
+		"UV: Error: UVsystab address translations not available!\n");
+		BUG();
+	}
+
+	/* build socket id -> node id, pnode */
+	num = maxsock - minsock + 1;
+	bytes = num * sizeof(_socket_to_node[0]);
+	_socket_to_node = kmalloc(bytes, GFP_KERNEL);
+	_socket_to_pnode = kmalloc(bytes, GFP_KERNEL);
+
+	nump = maxpnode - minpnode + 1;
+	bytes = nump * sizeof(_pnode_to_socket[0]);
+	_pnode_to_socket = kmalloc(bytes, GFP_KERNEL);
+	BUG_ON(!_socket_to_node || !_socket_to_pnode || !_pnode_to_socket);
+
+	for (i = 0; i < num; i++)
+		_socket_to_node[i] = _socket_to_pnode[i] = SOCK_EMPTY;
+
+	for (i = 0; i < nump; i++)
+		_pnode_to_socket[i] = SOCK_EMPTY;
+
+	/* fill in pnode/node/addr conversion list values */
+	pr_info("UV: GAM Building socket/pnode/pxm conversion tables\n");
+	for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) {
+		if (gre->type == UV_GAM_RANGE_TYPE_HOLE)
 			continue;
-			pnode = (i * 64 + j) & pnode_mask;
-			uv_blade_info[blade].pnode = pnode;
-			uv_blade_info[blade].nr_possible_cpus = 0;
-			uv_blade_info[blade].nr_online_cpus = 0;
-			spin_lock_init(&uv_blade_info[blade].nmi_lock);
-			min_pnode = min(pnode, min_pnode);
-			max_pnode = max(pnode, max_pnode);
-			blade++;
+		i = gre->sockid - minsock;
+		if (_socket_to_pnode[i] != SOCK_EMPTY)
+			continue;	/* duplicate */
+		_socket_to_pnode[i] = gre->pnode;
+		_socket_to_node[i] = gre->pxm;
+
+		i = gre->pnode - minpnode;
+		_pnode_to_socket[i] = gre->sockid;
+
+		pr_info(
+		"UV: sid:%02x type:%d nasid:%04x pn:%02x pxm:%2d pn2s:%2x\n",
+			gre->sockid, gre->type, gre->nasid,
+			_socket_to_pnode[gre->sockid - minsock],
+			_socket_to_node[gre->sockid - minsock],
+			_pnode_to_socket[gre->pnode - minpnode]);
 	}
+
+	/* check socket -> node values */
+	lnid = -1;
+	for_each_present_cpu(cpu) {
+		int nid = cpu_to_node(cpu);
+		int apicid, sockid;
+
+		if (lnid == nid)
+			continue;
+		lnid = nid;
+		apicid = per_cpu(x86_cpu_to_apicid, cpu);
+		sockid = apicid >> uv_cpuid.socketid_shift;
+		i = sockid - minsock;
+
+		if (nid != _socket_to_node[i]) {
+			pr_warn(
+			"UV: %02x: type:%d socket:%02x PXM:%02x != node:%2d\n",
+				i, sockid, gre->type, _socket_to_node[i], nid);
+			_socket_to_node[i] = nid;
 		}
+	}
+
+	/* Setup physical blade to pnode translation from GAM Range Table */
+	bytes = num_possible_nodes() * sizeof(_node_to_pnode[0]);
+	_node_to_pnode = kmalloc(bytes, GFP_KERNEL);
+	BUG_ON(!_node_to_pnode);
+
+	for (lnid = 0; lnid < num_possible_nodes(); lnid++) {
+		unsigned short sockid;
+
+		for (sockid = minsock; sockid <= maxsock; sockid++) {
+			if (lnid == _socket_to_node[sockid - minsock]) {
+				_node_to_pnode[lnid] =
+					_socket_to_pnode[sockid - minsock];
+				break;
+			}
+		}
+		if (sockid > maxsock) {
+			pr_err("UV: socket for node %d not found!\n", lnid);
+			BUG();
+		}
+	}
+
+	/*
+	 * If socket id == pnode or socket id == node for all nodes,
+	 *   system runs faster by removing corresponding conversion table.
+	 */
+	pr_info("UV: Checking socket->node/pnode for identity maps\n");
+	if (minsock == 0) {
+		for (i = 0; i < num; i++)
+			if (_socket_to_node[i] == SOCK_EMPTY ||
+				i != _socket_to_node[i])
+				break;
+		if (i >= num) {
+			kfree(_socket_to_node);
+			_socket_to_node = NULL;
+			pr_info("UV: 1:1 socket_to_node table removed\n");
+		}
+	}
+	if (minsock == minpnode) {
+		for (i = 0; i < num; i++)
+			if (_socket_to_pnode[i] != SOCK_EMPTY &&
+				_socket_to_pnode[i] != i + minpnode)
+				break;
+		if (i >= num) {
+			kfree(_socket_to_pnode);
+			_socket_to_pnode = NULL;
+			pr_info("UV: 1:1 socket_to_pnode table removed\n");
+		}
+	}
+}
+
+void __init uv_system_init(void)
+{
+	struct uv_hub_info_s hub_info = {0};
+	int bytes, cpu, nodeid;
+	unsigned short min_pnode = 9999, max_pnode = 0;
+	char *hub = is_uv4_hub() ? "UV400" :
+		    is_uv3_hub() ? "UV300" :
+		    is_uv2_hub() ? "UV2000/3000" :
+		    is_uv1_hub() ? "UV100/1000" : NULL;
+
+	if (!hub) {
+		pr_err("UV: Unknown/unsupported UV hub\n");
+		return;
+	}
+	pr_info("UV: Found %s hub\n", hub);
+
+	map_low_mmrs();
+
+	uv_bios_init();			/* get uv_systab for decoding */
+	decode_uv_systab();
+	build_socket_tables();
+	build_uv_gr_table();
+	uv_init_hub_info(&hub_info);
+	uv_possible_blades = num_possible_nodes();
+	if (!_node_to_pnode)
+		boot_init_possible_blades(&hub_info);
+
+	/* uv_num_possible_blades() is really the hub count */
+	pr_info("UV: Found %d hubs, %d nodes, %d cpus\n",
+			uv_num_possible_blades(),
+			num_possible_nodes(),
+			num_possible_cpus());
 
-	uv_bios_init();
 	uv_bios_get_sn_info(0, &uv_type, &sn_partition_id, &sn_coherency_id,
 			    &sn_region_size, &system_serial_number);
+	hub_info.coherency_domain_number = sn_coherency_id;
 	uv_rtc_init();
 
-	for_each_present_cpu(cpu) {
-		int apicid = per_cpu(x86_cpu_to_apicid, cpu);
+	bytes = sizeof(void *) * uv_num_possible_blades();
+	__uv_hub_info_list = kzalloc(bytes, GFP_KERNEL);
+	BUG_ON(!__uv_hub_info_list);
 
-		nid = cpu_to_node(cpu);
-		/*
-		 * apic_pnode_shift must be set before calling uv_apicid_to_pnode();
-		 */
-		uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask;
-		uv_cpu_hub_info(cpu)->apic_pnode_shift = uvh_apicid.s.pnode_shift;
-		uv_cpu_hub_info(cpu)->hub_revision = uv_hub_info->hub_revision;
+	bytes = sizeof(struct uv_hub_info_s);
+	for_each_node(nodeid) {
+		struct uv_hub_info_s *new_hub;
+
+		if (__uv_hub_info_list[nodeid]) {
+			pr_err("UV: Node %d UV HUB already initialized!?\n",
+				nodeid);
+			BUG();
+		}
 
-		uv_cpu_hub_info(cpu)->m_shift = 64 - m_val;
-		uv_cpu_hub_info(cpu)->n_lshift = n_lshift;
+		/* Allocate new per hub info list */
+		new_hub = (nodeid == 0) ?
+			&uv_hub_info_node0 :
+			kzalloc_node(bytes, GFP_KERNEL, nodeid);
+		BUG_ON(!new_hub);
+		__uv_hub_info_list[nodeid] = new_hub;
+		new_hub = uv_hub_info_list(nodeid);
+		BUG_ON(!new_hub);
+		*new_hub = hub_info;
+
+		/* Use information from GAM table if available */
+		if (_node_to_pnode)
+			new_hub->pnode = _node_to_pnode[nodeid];
+		else	/* Fill in during cpu loop */
+			new_hub->pnode = 0xffff;
+		new_hub->numa_blade_id = uv_node_to_blade_id(nodeid);
+		new_hub->memory_nid = -1;
+		new_hub->nr_possible_cpus = 0;
+		new_hub->nr_online_cpus = 0;
+	}
 
+	/* Initialize per cpu info */
+	for_each_possible_cpu(cpu) {
+		int apicid = per_cpu(x86_cpu_to_apicid, cpu);
+		int numa_node_id;
+		unsigned short pnode;
+
+		nodeid = cpu_to_node(cpu);
+		numa_node_id = numa_cpu_node(cpu);
 		pnode = uv_apicid_to_pnode(apicid);
-		blade = boot_pnode_to_blade(pnode);
-		lcpu = uv_blade_info[blade].nr_possible_cpus;
-		uv_blade_info[blade].nr_possible_cpus++;
-
-		/* Any node on the blade, else will contain -1. */
-		uv_blade_info[blade].memory_nid = nid;
-
-		uv_cpu_hub_info(cpu)->lowmem_remap_base = lowmem_redir_base;
-		uv_cpu_hub_info(cpu)->lowmem_remap_top = lowmem_redir_size;
-		uv_cpu_hub_info(cpu)->m_val = m_val;
-		uv_cpu_hub_info(cpu)->n_val = n_val;
-		uv_cpu_hub_info(cpu)->numa_blade_id = blade;
-		uv_cpu_hub_info(cpu)->blade_processor_id = lcpu;
+
+		uv_cpu_info_per(cpu)->p_uv_hub_info = uv_hub_info_list(nodeid);
+		uv_cpu_info_per(cpu)->blade_cpu_id =
+			uv_cpu_hub_info(cpu)->nr_possible_cpus++;
+		if (uv_cpu_hub_info(cpu)->memory_nid == -1)
+			uv_cpu_hub_info(cpu)->memory_nid = cpu_to_node(cpu);
+		if (nodeid != numa_node_id &&	/* init memoryless node */
+		    uv_hub_info_list(numa_node_id)->pnode == 0xffff)
+			uv_hub_info_list(numa_node_id)->pnode = pnode;
+		else if (uv_cpu_hub_info(cpu)->pnode == 0xffff)
 			uv_cpu_hub_info(cpu)->pnode = pnode;
-		uv_cpu_hub_info(cpu)->gpa_mask = (1UL << (m_val + n_val)) - 1;
-		uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper;
-		uv_cpu_hub_info(cpu)->gnode_extra = gnode_extra;
-		uv_cpu_hub_info(cpu)->global_mmr_base = mmr_base;
-		uv_cpu_hub_info(cpu)->coherency_domain_number = sn_coherency_id;
-		uv_cpu_hub_info(cpu)->scir.offset = uv_scir_offset(apicid);
-		uv_node_to_blade[nid] = blade;
-		uv_cpu_to_blade[cpu] = blade;
+		uv_cpu_scir_info(cpu)->offset = uv_scir_offset(apicid);
 	}
 
-	/* Add blade/pnode info for nodes without cpus */
-	for_each_online_node(nid) {
-		if (uv_node_to_blade[nid] >= 0)
-			continue;
-		paddr = node_start_pfn(nid) << PAGE_SHIFT;
+	for_each_node(nodeid) {
+		unsigned short pnode = uv_hub_info_list(nodeid)->pnode;
+
+		/* Add pnode info for pre-GAM list nodes without cpus */
+		if (pnode == 0xffff) {
+			unsigned long paddr;
+
+			paddr = node_start_pfn(nodeid) << PAGE_SHIFT;
 			pnode = uv_gpa_to_pnode(uv_soc_phys_ram_to_gpa(paddr));
-		blade = boot_pnode_to_blade(pnode);
-		uv_node_to_blade[nid] = blade;
+			uv_hub_info_list(nodeid)->pnode = pnode;
+		}
+		min_pnode = min(pnode, min_pnode);
+		max_pnode = max(pnode, max_pnode);
+		pr_info("UV: UVHUB node:%2d pn:%02x nrcpus:%d\n",
+			nodeid,
+			uv_hub_info_list(nodeid)->pnode,
+			uv_hub_info_list(nodeid)->nr_possible_cpus);
 	}
 
+	pr_info("UV: min_pnode:%02x max_pnode:%02x\n", min_pnode, max_pnode);
 	map_gru_high(max_pnode);
 	map_mmr_high(max_pnode);
 	map_mmioh_high(min_pnode, max_pnode);

arch/x86/platform/uv/bios_uv.c

@@ -21,19 +21,20 @@
 
 #include <linux/efi.h>
 #include <linux/export.h>
+#include <linux/slab.h>
 #include <asm/efi.h>
 #include <linux/io.h>
 #include <asm/uv/bios.h>
 #include <asm/uv/uv_hub.h>
 
-static struct uv_systab uv_systab;
+struct uv_systab *uv_systab;
 
 s64 uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, u64 a4, u64 a5)
 {
-	struct uv_systab *tab = &uv_systab;
+	struct uv_systab *tab = uv_systab;
 	s64 ret;
 
-	if (!tab->function)
+	if (!tab || !tab->function)
 		/*
 		 * BIOS does not support UV systab
 		 */
@@ -183,34 +184,31 @@ int uv_bios_set_legacy_vga_target(bool decode, int domain, int bus)
 }
 EXPORT_SYMBOL_GPL(uv_bios_set_legacy_vga_target);
 
-
 #ifdef CONFIG_EFI
 void uv_bios_init(void)
 {
-	struct uv_systab *tab;
-
-	if ((efi.uv_systab == EFI_INVALID_TABLE_ADDR) ||
-	    (efi.uv_systab == (unsigned long)NULL)) {
-		printk(KERN_CRIT "No EFI UV System Table.\n");
-		uv_systab.function = (unsigned long)NULL;
+	uv_systab = NULL;
+	if ((efi.uv_systab == EFI_INVALID_TABLE_ADDR) || !efi.uv_systab) {
+		pr_crit("UV: UVsystab: missing\n");
 		return;
 	}
 
-	tab = (struct uv_systab *)ioremap(efi.uv_systab,
-					sizeof(struct uv_systab));
-	if (strncmp(tab->signature, "UVST", 4) != 0)
-		printk(KERN_ERR "bad signature in UV system table!");
-
-	/*
-	 * Copy table to permanent spot for later use.
-	 */
-	memcpy(&uv_systab, tab, sizeof(struct uv_systab));
-	iounmap(tab);
+	uv_systab = ioremap(efi.uv_systab, sizeof(struct uv_systab));
+	if (!uv_systab || strncmp(uv_systab->signature, UV_SYSTAB_SIG, 4)) {
+		pr_err("UV: UVsystab: bad signature!\n");
+		iounmap(uv_systab);
+		return;
+	}
 
-	printk(KERN_INFO "EFI UV System Table Revision %d\n",
-					uv_systab.revision);
+	if (uv_systab->revision >= UV_SYSTAB_VERSION_UV4) {
+		iounmap(uv_systab);
+		uv_systab = ioremap(efi.uv_systab, uv_systab->size);
+		if (!uv_systab) {
+			pr_err("UV: UVsystab: ioremap(%d) failed!\n",
+				uv_systab->size);
+			return;
+		}
+	}
+	pr_info("UV: UVsystab: Revision:%x\n", uv_systab->revision);
 }
-#else	/* !CONFIG_EFI */
-
-void uv_bios_init(void) { }
 #endif

arch/x86/platform/uv/tlb_uv.c

@@ -37,7 +37,7 @@ static int timeout_base_ns[] = {
 };
 
 static int timeout_us;
-static int nobau;
+static bool nobau = true;
 static int nobau_perm;
 static cycles_t congested_cycles;
 
@@ -106,13 +106,28 @@ static char *stat_description[] = {
 	"enable:   number times use of the BAU was re-enabled"
 };
 
-static int __init
-setup_nobau(char *arg)
+static int __init setup_bau(char *arg)
 {
-	nobau = 1;
+	int result;
+
+	if (!arg)
+		return -EINVAL;
+
+	result = strtobool(arg, &nobau);
+	if (result)
+		return result;
+
+	/* we need to flip the logic here, so that bau=y sets nobau to false */
+	nobau = !nobau;
+
+	if (!nobau)
+		pr_info("UV BAU Enabled\n");
+	else
+		pr_info("UV BAU Disabled\n");
+
 	return 0;
 }
-early_param("nobau", setup_nobau);
+early_param("bau", setup_bau);
 
 /* base pnode in this partition */
 static int uv_base_pnode __read_mostly;
@@ -131,10 +146,10 @@ set_bau_on(void)
 		pr_info("BAU not initialized; cannot be turned on\n");
 		return;
 	}
-	nobau = 0;
+	nobau = false;
 	for_each_present_cpu(cpu) {
 		bcp = &per_cpu(bau_control, cpu);
-		bcp->nobau = 0;
+		bcp->nobau = false;
 	}
 	pr_info("BAU turned on\n");
 	return;
@@ -146,10 +161,10 @@ set_bau_off(void)
 	int cpu;
 	struct bau_control *bcp;
 
-	nobau = 1;
+	nobau = true;
 	for_each_present_cpu(cpu) {
 		bcp = &per_cpu(bau_control, cpu);
-		bcp->nobau = 1;
+		bcp->nobau = true;
 	}
 	pr_info("BAU turned off\n");
 	return;
@@ -1886,7 +1901,7 @@ static void __init init_per_cpu_tunables(void)
 		bcp = &per_cpu(bau_control, cpu);
 		bcp->baudisabled		= 0;
 		if (nobau)
-			bcp->nobau		= 1;
+			bcp->nobau		= true;
 		bcp->statp			= &per_cpu(ptcstats, cpu);
 		/* time interval to catch a hardware stay-busy bug */
 		bcp->timeout_interval		= usec_2_cycles(2*timeout_us);
@@ -2025,7 +2040,8 @@ static int scan_sock(struct socket_desc *sdp, struct uvhub_desc *bdp,
 			return 1;
 		}
 		bcp->uvhub_master = *hmasterp;
-		bcp->uvhub_cpu = uv_cpu_hub_info(cpu)->blade_processor_id;
+		bcp->uvhub_cpu = uv_cpu_blade_processor_id(cpu);
+
 		if (bcp->uvhub_cpu >= MAX_CPUS_PER_UVHUB) {
 			printk(KERN_EMERG "%d cpus per uvhub invalid\n",
 				bcp->uvhub_cpu);

arch/x86/platform/uv/uv_sysfs.c

@@ -34,7 +34,7 @@ static ssize_t partition_id_show(struct kobject *kobj,
 static ssize_t coherence_id_show(struct kobject *kobj,
 			struct kobj_attribute *attr, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%ld\n", partition_coherence_id());
+	return snprintf(buf, PAGE_SIZE, "%ld\n", uv_partition_coherence_id());
 }
 
 static struct kobj_attribute partition_id_attr =

arch/x86/platform/uv/uv_time.c

@@ -165,7 +165,7 @@ static __init int uv_rtc_allocate_timers(void)
 	for_each_present_cpu(cpu) {
 		int nid = cpu_to_node(cpu);
 		int bid = uv_cpu_to_blade_id(cpu);
-		int bcpu = uv_cpu_hub_info(cpu)->blade_processor_id;
+		int bcpu = uv_cpu_blade_processor_id(cpu);
 		struct uv_rtc_timer_head *head = blade_info[bid];
 
 		if (!head) {
@@ -226,7 +226,7 @@ static int uv_rtc_set_timer(int cpu, u64 expires)
 	int pnode = uv_cpu_to_pnode(cpu);
 	int bid = uv_cpu_to_blade_id(cpu);
 	struct uv_rtc_timer_head *head = blade_info[bid];
-	int bcpu = uv_cpu_hub_info(cpu)->blade_processor_id;
+	int bcpu = uv_cpu_blade_processor_id(cpu);
 	u64 *t = &head->cpu[bcpu].expires;
 	unsigned long flags;
 	int next_cpu;
@@ -262,7 +262,7 @@ static int uv_rtc_unset_timer(int cpu, int force)
 	int pnode = uv_cpu_to_pnode(cpu);
 	int bid = uv_cpu_to_blade_id(cpu);
 	struct uv_rtc_timer_head *head = blade_info[bid];
-	int bcpu = uv_cpu_hub_info(cpu)->blade_processor_id;
+	int bcpu = uv_cpu_blade_processor_id(cpu);
 	u64 *t = &head->cpu[bcpu].expires;
 	unsigned long flags;
 	int rc = 0;

drivers/misc/sgi-gru/grukservices.c

@@ -718,8 +718,8 @@ static int send_message_queue_full(void *cb, struct gru_message_queue_desc *mqd,
 static int send_message_put_nacked(void *cb, struct gru_message_queue_desc *mqd,
 			void *mesg, int lines)
 {
-	unsigned long m, *val = mesg, gpa, save;
-	int ret;
+	unsigned long m;
+	int ret, loops = 200;	/* experimentally determined */
 
 	m = mqd->mq_gpa + (gru_get_amo_value_head(cb) << 6);
 	if (lines == 2) {
@@ -735,22 +735,28 @@ static int send_message_put_nacked(void *cb, struct gru_message_queue_desc *mqd,
 		return MQE_OK;
 
 	/*
-	 * Send a cross-partition interrupt to the SSI that contains the target
-	 * message queue. Normally, the interrupt is automatically delivered by
-	 * hardware but some error conditions require explicit delivery.
-	 * Use the GRU to deliver the interrupt. Otherwise partition failures
+	 * Send a noop message in order to deliver a cross-partition interrupt
+	 * to the SSI that contains the target message queue. Normally, the
+	 * interrupt is automatically delivered by hardware following mesq
+	 * operations, but some error conditions require explicit delivery.
+	 * The noop message will trigger delivery. Otherwise partition failures
 	 * could cause unrecovered errors.
 	 */
-	gpa = uv_global_gru_mmr_address(mqd->interrupt_pnode, UVH_IPI_INT);
-	save = *val;
-	*val = uv_hub_ipi_value(mqd->interrupt_apicid, mqd->interrupt_vector,
-				dest_Fixed);
-	gru_vstore_phys(cb, gpa, gru_get_tri(mesg), IAA_REGISTER, IMA);
-	ret = gru_wait(cb);
-	*val = save;
-	if (ret != CBS_IDLE)
-		return MQE_UNEXPECTED_CB_ERR;
-	return MQE_OK;
+	do {
+		ret = send_noop_message(cb, mqd, mesg);
+	} while ((ret == MQIE_AGAIN || ret == MQE_CONGESTION) && (loops-- > 0));
+
+	if (ret == MQIE_AGAIN || ret == MQE_CONGESTION) {
+		/*
+		 * Don't indicate to the app to resend the message, as it's
+		 * already been successfully sent.  We simply send an OK
+		 * (rather than fail the send with MQE_UNEXPECTED_CB_ERR),
+		 * assuming that the other side is receiving enough
+		 * interrupts to get this message processed anyway.
+		 */
+		ret = MQE_OK;
+	}
+	return ret;
 }
 
 /*