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

…/kernel/git/tip/linux-2.6-tip * 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (50 commits) x86, mm: Allow ZONE_DMA to be configurable x86, NUMA: Trim numa meminfo with max_pfn in a separate loop x86, NUMA: Rename setup_node_bootmem() to setup_node_data() x86, NUMA: Enable emulation on 32bit too x86, NUMA: Enable CONFIG_AMD_NUMA on 32bit too x86, NUMA: Rename amdtopology_64.c to amdtopology.c x86, NUMA: Make numa_init_array() static x86, NUMA: Make 32bit use common NUMA init path x86, NUMA: Initialize and use remap allocator from setup_node_bootmem() x86-32, NUMA: Add @start and @EnD to init_alloc_remap() x86, NUMA: Remove long 64bit assumption from numa.c x86, NUMA: Enable build of generic NUMA init code on 32bit x86, NUMA: Move NUMA init logic from numa_64.c to numa.c x86-32, NUMA: Update numaq to use new NUMA init protocol x86-32, NUMA: Replace srat_32.c with srat.c x86-32, NUMA: implement temporary NUMA init shims x86, NUMA: Move numa_nodes_parsed to numa.[hc] x86-32, NUMA: Move get_memcfg_numa() into numa_32.c x86, NUMA: make srat.c 32bit safe x86, NUMA: rename srat_64.c to srat.c ...
fracktal · May 20, 2011 · 1358820 · 1358820
2 parents ac2941f + dc382fd
commit 1358820
Show file tree

Hide file tree

Showing 39 changed files with 836 additions and 1,614 deletions.
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
@@ -112,7 +112,14 @@ config MMU
 	def_bool y
 
 config ZONE_DMA
-	def_bool y
+	bool "DMA memory allocation support" if EXPERT
+	default y
+	help
+	  DMA memory allocation support allows devices with less than 32-bit
+	  addressing to allocate within the first 16MB of address space.
+	  Disable if no such devices will be used.
+
+	  If unsure, say Y.
 
 config SBUS
 	bool
@@ -1164,7 +1171,7 @@ comment "NUMA (Summit) requires SMP, 64GB highmem support, ACPI"
 config AMD_NUMA
 	def_bool y
 	prompt "Old style AMD Opteron NUMA detection"
-	depends on X86_64 && NUMA && PCI
+	depends on NUMA && PCI
 	---help---
 	  Enable AMD NUMA node topology detection.  You should say Y here if
 	  you have a multi processor AMD system. This uses an old method to
@@ -1191,7 +1198,7 @@ config NODES_SPAN_OTHER_NODES
 
 config NUMA_EMU
 	bool "NUMA emulation"
-	depends on X86_64 && NUMA
+	depends on NUMA
 	---help---
 	  Enable NUMA emulation. A flat machine will be split
 	  into virtual nodes when booted with "numa=fake=N", where N is the
@@ -1213,6 +1220,10 @@ config HAVE_ARCH_BOOTMEM
 	def_bool y
 	depends on X86_32 && NUMA
 
+config HAVE_ARCH_ALLOC_REMAP
+	def_bool y
+	depends on X86_32 && NUMA
+
 config ARCH_HAVE_MEMORY_PRESENT
 	def_bool y
 	depends on X86_32 && DISCONTIGMEM
@@ -1221,13 +1232,9 @@ config NEED_NODE_MEMMAP_SIZE
 	def_bool y
 	depends on X86_32 && (DISCONTIGMEM || SPARSEMEM)
 
-config HAVE_ARCH_ALLOC_REMAP
-	def_bool y
-	depends on X86_32 && NUMA
-
 config ARCH_FLATMEM_ENABLE
 	def_bool y
-	depends on X86_32 && ARCH_SELECT_MEMORY_MODEL && !NUMA
+	depends on X86_32 && !NUMA
 
 config ARCH_DISCONTIGMEM_ENABLE
 	def_bool y
@@ -1237,20 +1244,16 @@ config ARCH_DISCONTIGMEM_DEFAULT
 	def_bool y
 	depends on NUMA && X86_32
 
-config ARCH_PROC_KCORE_TEXT
-	def_bool y
-	depends on X86_64 && PROC_KCORE
-
-config ARCH_SPARSEMEM_DEFAULT
-	def_bool y
-	depends on X86_64
-
 config ARCH_SPARSEMEM_ENABLE
 	def_bool y
 	depends on X86_64 || NUMA || (EXPERIMENTAL && X86_32) || X86_32_NON_STANDARD
 	select SPARSEMEM_STATIC if X86_32
 	select SPARSEMEM_VMEMMAP_ENABLE if X86_64
 
+config ARCH_SPARSEMEM_DEFAULT
+	def_bool y
+	depends on X86_64
+
 config ARCH_SELECT_MEMORY_MODEL
 	def_bool y
 	depends on ARCH_SPARSEMEM_ENABLE
@@ -1259,6 +1262,10 @@ config ARCH_MEMORY_PROBE
 	def_bool X86_64
 	depends on MEMORY_HOTPLUG
 
+config ARCH_PROC_KCORE_TEXT
+	def_bool y
+	depends on X86_64 && PROC_KCORE
+
 config ILLEGAL_POINTER_VALUE
        hex
        default 0 if X86_32
@@ -1693,10 +1700,6 @@ config ARCH_ENABLE_MEMORY_HOTREMOVE
 	def_bool y
 	depends on MEMORY_HOTPLUG
 
-config HAVE_ARCH_EARLY_PFN_TO_NID
-	def_bool X86_64
-	depends on NUMA
-
 config USE_PERCPU_NUMA_NODE_ID
 	def_bool y
 	depends on NUMA

diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
@@ -183,8 +183,6 @@ static inline void disable_acpi(void) { }
 
 #define ARCH_HAS_POWER_INIT	1
 
-struct bootnode;
-
 #ifdef CONFIG_ACPI_NUMA
 extern int acpi_numa;
 extern int x86_acpi_numa_init(void);

diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
@@ -11,7 +11,6 @@ struct amd_nb_bus_dev_range {
 
 extern const struct pci_device_id amd_nb_misc_ids[];
 extern const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[];
-struct bootnode;
 
 extern bool early_is_amd_nb(u32 value);
 extern int amd_cache_northbridges(void);

diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
@@ -363,7 +363,12 @@ struct apic {
 	 */
 	int (*x86_32_early_logical_apicid)(int cpu);
 
-	/* determine CPU -> NUMA node mapping */
+	/*
+	 * Optional method called from setup_local_APIC() after logical
+	 * apicid is guaranteed to be known to initialize apicid -> node
+	 * mapping if NUMA initialization hasn't done so already.  Don't
+	 * add new users.
+	 */
 	int (*x86_32_numa_cpu_node)(int cpu);
 #endif
 };
@@ -537,8 +542,6 @@ static inline int default_phys_pkg_id(int cpuid_apic, int index_msb)
 	return cpuid_apic >> index_msb;
 }
 
-extern int default_x86_32_numa_cpu_node(int cpu);
-
 #endif
 
 static inline unsigned int

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
@@ -208,8 +208,7 @@ extern const char * const x86_power_flags[32];
 #define test_cpu_cap(c, bit)						\
 	 test_bit(bit, (unsigned long *)((c)->x86_capability))
 
-#define cpu_has(c, bit)							\
-	(__builtin_constant_p(bit) &&					\
+#define REQUIRED_MASK_BIT_SET(bit)					\
 	 ( (((bit)>>5)==0 && (1UL<<((bit)&31) & REQUIRED_MASK0)) ||	\
 	   (((bit)>>5)==1 && (1UL<<((bit)&31) & REQUIRED_MASK1)) ||	\
 	   (((bit)>>5)==2 && (1UL<<((bit)&31) & REQUIRED_MASK2)) ||	\
@@ -219,10 +218,16 @@ extern const char * const x86_power_flags[32];
 	   (((bit)>>5)==6 && (1UL<<((bit)&31) & REQUIRED_MASK6)) ||	\
 	   (((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) ||	\
 	   (((bit)>>5)==8 && (1UL<<((bit)&31) & REQUIRED_MASK8)) ||	\
-	   (((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9)) )	\
-	  ? 1 :								\
+	   (((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9)) )
+
+#define cpu_has(c, bit)							\
+	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\
 	 test_cpu_cap(c, bit))
 
+#define this_cpu_has(bit)						\
+	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : 	\
+	 x86_this_cpu_test_bit(bit, (unsigned long *)&cpu_info.x86_capability))
+
 #define boot_cpu_has(bit)	cpu_has(&boot_cpu_data, bit)
 
 #define set_cpu_cap(c, bit)	set_bit(bit, (unsigned long *)((c)->x86_capability))

diff --git a/arch/x86/include/asm/dma.h b/arch/x86/include/asm/dma.h
@@ -69,22 +69,18 @@
 
 #define MAX_DMA_CHANNELS	8
 
-#ifdef CONFIG_X86_32
-
-/* The maximum address that we can perform a DMA transfer to on this platform */
-#define MAX_DMA_ADDRESS      (PAGE_OFFSET + 0x1000000)
-
-#else
-
 /* 16MB ISA DMA zone */
 #define MAX_DMA_PFN   ((16 * 1024 * 1024) >> PAGE_SHIFT)
 
 /* 4GB broken PCI/AGP hardware bus master zone */
 #define MAX_DMA32_PFN ((4UL * 1024 * 1024 * 1024) >> PAGE_SHIFT)
 
+#ifdef CONFIG_X86_32
+/* The maximum address that we can perform a DMA transfer to on this platform */
+#define MAX_DMA_ADDRESS      (PAGE_OFFSET + 0x1000000)
+#else
 /* Compat define for old dma zone */
 #define MAX_DMA_ADDRESS ((unsigned long)__va(MAX_DMA_PFN << PAGE_SHIFT))
-
 #endif
 
 /* 8237 DMA controllers */

diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h
@@ -13,31 +13,11 @@ extern struct pglist_data *node_data[];
 #define NODE_DATA(nid)	(node_data[nid])
 
 #include <asm/numaq.h>
-/* summit or generic arch */
-#include <asm/srat.h>
-
-extern int get_memcfg_numa_flat(void);
-/*
- * This allows any one NUMA architecture to be compiled
- * for, and still fall back to the flat function if it
- * fails.
- */
-static inline void get_memcfg_numa(void)
-{
-
-	if (get_memcfg_numaq())
-		return;
-	if (get_memcfg_from_srat())
-		return;
-	get_memcfg_numa_flat();
-}
 
 extern void resume_map_numa_kva(pgd_t *pgd);
 
 #else /* !CONFIG_NUMA */
 
-#define get_memcfg_numa get_memcfg_numa_flat
-
 static inline void resume_map_numa_kva(pgd_t *pgd) {}
 
 #endif /* CONFIG_NUMA */

diff --git a/arch/x86/include/asm/mmzone_64.h b/arch/x86/include/asm/mmzone_64.h
@@ -4,36 +4,13 @@
 #ifndef _ASM_X86_MMZONE_64_H
 #define _ASM_X86_MMZONE_64_H
 
-
 #ifdef CONFIG_NUMA
 
 #include <linux/mmdebug.h>
-
 #include <asm/smp.h>
 
-/* Simple perfect hash to map physical addresses to node numbers */
-struct memnode {
-	int shift;
-	unsigned int mapsize;
-	s16 *map;
-	s16 embedded_map[64 - 8];
-} ____cacheline_aligned; /* total size = 128 bytes */
-extern struct memnode memnode;
-#define memnode_shift memnode.shift
-#define memnodemap memnode.map
-#define memnodemapsize memnode.mapsize
-
 extern struct pglist_data *node_data[];
 
-static inline __attribute__((pure)) int phys_to_nid(unsigned long addr)
-{
-	unsigned nid;
-	VIRTUAL_BUG_ON(!memnodemap);
-	nid = memnodemap[addr >> memnode_shift];
-	VIRTUAL_BUG_ON(nid >= MAX_NUMNODES || !node_data[nid]);
-	return nid;
-}
-
 #define NODE_DATA(nid)		(node_data[nid])
 
 #define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)

diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
@@ -1,12 +1,24 @@
 #ifndef _ASM_X86_NUMA_H
 #define _ASM_X86_NUMA_H
 
+#include <linux/nodemask.h>
+
 #include <asm/topology.h>
 #include <asm/apicdef.h>
 
 #ifdef CONFIG_NUMA
 
 #define NR_NODE_MEMBLKS		(MAX_NUMNODES*2)
+#define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT))
+
+/*
+ * Too small node sizes may confuse the VM badly. Usually they
+ * result from BIOS bugs. So dont recognize nodes as standalone
+ * NUMA entities that have less than this amount of RAM listed:
+ */
+#define NODE_MIN_SIZE (4*1024*1024)
+
+extern int numa_off;
 
 /*
  * __apicid_to_node[] stores the raw mapping between physical apicid and
@@ -17,15 +29,27 @@
  * numa_cpu_node().
  */
 extern s16 __apicid_to_node[MAX_LOCAL_APIC];
+extern nodemask_t numa_nodes_parsed __initdata;
+
+extern int __init numa_add_memblk(int nodeid, u64 start, u64 end);
+extern void __init numa_set_distance(int from, int to, int distance);
 
 static inline void set_apicid_to_node(int apicid, s16 node)
 {
 	__apicid_to_node[apicid] = node;
 }
+
+extern int __cpuinit numa_cpu_node(int cpu);
+
 #else	/* CONFIG_NUMA */
 static inline void set_apicid_to_node(int apicid, s16 node)
 {
 }
+
+static inline int numa_cpu_node(int cpu)
+{
+	return NUMA_NO_NODE;
+}
 #endif	/* CONFIG_NUMA */
 
 #ifdef CONFIG_X86_32
@@ -37,14 +61,12 @@ static inline void set_apicid_to_node(int apicid, s16 node)
 #ifdef CONFIG_NUMA
 extern void __cpuinit numa_set_node(int cpu, int node);
 extern void __cpuinit numa_clear_node(int cpu);
-extern void __init numa_init_array(void);
 extern void __init init_cpu_to_node(void);
 extern void __cpuinit numa_add_cpu(int cpu);
 extern void __cpuinit numa_remove_cpu(int cpu);
 #else	/* CONFIG_NUMA */
 static inline void numa_set_node(int cpu, int node)	{ }
 static inline void numa_clear_node(int cpu)		{ }
-static inline void numa_init_array(void)		{ }
 static inline void init_cpu_to_node(void)		{ }
 static inline void numa_add_cpu(int cpu)		{ }
 static inline void numa_remove_cpu(int cpu)		{ }
@@ -54,4 +76,10 @@ static inline void numa_remove_cpu(int cpu)		{ }
 void debug_cpumask_set_cpu(int cpu, int node, bool enable);
 #endif
 
+#ifdef CONFIG_NUMA_EMU
+#define FAKE_NODE_MIN_SIZE	((u64)32 << 20)
+#define FAKE_NODE_MIN_HASH_MASK	(~(FAKE_NODE_MIN_SIZE - 1UL))
+void numa_emu_cmdline(char *);
+#endif /* CONFIG_NUMA_EMU */
+
 #endif	/* _ASM_X86_NUMA_H */
diff --git a/arch/x86/include/asm/numa_32.h b/arch/x86/include/asm/numa_32.h
@@ -1,16 +1,6 @@
 #ifndef _ASM_X86_NUMA_32_H
 #define _ASM_X86_NUMA_32_H
 
-extern int numa_off;
-
-extern int pxm_to_nid(int pxm);
-
-#ifdef CONFIG_NUMA
-extern int __cpuinit numa_cpu_node(int cpu);
-#else	/* CONFIG_NUMA */
-static inline int numa_cpu_node(int cpu)		{ return NUMA_NO_NODE; }
-#endif	/* CONFIG_NUMA */
-
 #ifdef CONFIG_HIGHMEM
 extern void set_highmem_pages_init(void);
 #else