x86: make generic arch support NUMAQ

... so it could fall back to normal numa and we'd reduce the impact of the
NUMAQ subarch.

NUMAQ depends on GENERICARCH
also decouple genericarch numa from acpi.
also make it fall back to bigsmp if apicid > 8.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/x86/Kconfig

@@ -268,36 +268,6 @@ config X86_VOYAGER
 	  If you do not specifically know you have a Voyager based machine,
 	  say N here, otherwise the kernel you build will not be bootable.
 
-config X86_NUMAQ
-	bool "NUMAQ (IBM/Sequent)"
-	depends on SMP && X86_32
-	select NUMA
-	help
-	  This option is used for getting Linux to run on a (IBM/Sequent) NUMA
-	  multiquad box. This changes the way that processors are bootstrapped,
-	  and uses Clustered Logical APIC addressing mode instead of Flat Logical.
-	  You will need a new lynxer.elf file to flash your firmware with - send
-	  email to <Martin.Bligh@us.ibm.com>.
-
-config X86_SUMMIT
-	bool "Summit/EXA (IBM x440)"
-	depends on X86_32 && SMP
-	help
-	  This option is needed for IBM systems that use the Summit/EXA chipset.
-	  In particular, it is needed for the x440.
-
-	  If you don't have one of these computers, you should say N here.
-	  If you want to build a NUMA kernel, you must select ACPI.
-
-config X86_BIGSMP
-	bool "Support for other sub-arch SMP systems with more than 8 CPUs"
-	depends on X86_32 && SMP
-	help
-	  This option is needed for the systems that have more than 8 CPUs
-	  and if the system is not of any sub-arch type above.
-
-	  If you don't have such a system, you should say N here.
-
 config X86_VISWS
 	bool "SGI 320/540 (Visual Workstation)"
 	depends on X86_32
@@ -311,21 +281,49 @@ config X86_VISWS
 	  and vice versa. See <file:Documentation/sgi-visws.txt> for details.
 
 config X86_GENERICARCH
-       bool "Generic architecture (Summit, bigsmp, ES7000, default)"
+       bool "Generic architecture"
 	depends on X86_32
        help
-          This option compiles in the Summit, bigsmp, ES7000, default subarchitectures.
-	  It is intended for a generic binary kernel.
-	  If you want a NUMA kernel, select ACPI.   We need SRAT for NUMA.
+          This option compiles in the NUMAQ, Summit, bigsmp, ES7000, default
+	  subarchitectures.  It is intended for a generic binary kernel.
+	  if you select them all, kernel will probe it one by one. and will
+	  fallback to default.
+
+if X86_GENERICARCH
+
+config X86_NUMAQ
+	bool "NUMAQ (IBM/Sequent)"
+	depends on SMP && X86_32
+	select NUMA
+	help
+	  This option is used for getting Linux to run on a NUMAQ (IBM/Sequent)
+	  NUMA multiquad box. This changes the way that processors are
+	  bootstrapped, and uses Clustered Logical APIC addressing mode instead
+	  of Flat Logical.  You will need a new lynxer.elf file to flash your
+	  firmware with - send email to <Martin.Bligh@us.ibm.com>.
+
+config X86_SUMMIT
+	bool "Summit/EXA (IBM x440)"
+	depends on X86_32 && SMP
+	help
+	  This option is needed for IBM systems that use the Summit/EXA chipset.
+	  In particular, it is needed for the x440.
 
 config X86_ES7000
 	bool "Support for Unisys ES7000 IA32 series"
 	depends on X86_32 && SMP
 	help
 	  Support for Unisys ES7000 systems.  Say 'Y' here if this kernel is
 	  supposed to run on an IA32-based Unisys ES7000 system.
-	  Only choose this option if you have such a system, otherwise you
-	  should say N here.
+
+config X86_BIGSMP
+	bool "Support for big SMP systems with more than 8 CPUs"
+	depends on X86_32 && SMP
+	help
+	  This option is needed for the systems that have more than 8 CPUs
+	  and if the system is not of any sub-arch type above.
+
+endif
 
 config X86_RDC321X
 	bool "RDC R-321x SoC"
@@ -913,9 +911,9 @@ config X86_PAE
 config NUMA
 	bool "Numa Memory Allocation and Scheduler Support (EXPERIMENTAL)"
 	depends on SMP
-	depends on X86_64 || (X86_32 && HIGHMEM64G && (X86_NUMAQ || (X86_SUMMIT || X86_GENERICARCH) && ACPI) && EXPERIMENTAL)
+	depends on X86_64 || (X86_32 && HIGHMEM64G && (X86_NUMAQ || X86_GENERICARCH || X86_SUMMIT && ACPI) && EXPERIMENTAL)
 	default n if X86_PC
-	default y if (X86_NUMAQ || X86_SUMMIT)
+	default y if (X86_NUMAQ || X86_SUMMIT || X86_GENERICARCH)
 	help
 	  Enable NUMA (Non Uniform Memory Access) support.
 	  The kernel will try to allocate memory used by a CPU on the

arch/x86/Makefile

@@ -117,29 +117,11 @@ mcore-$(CONFIG_X86_VOYAGER)	:= arch/x86/mach-voyager/
 mflags-$(CONFIG_X86_VISWS)	:= -Iinclude/asm-x86/mach-visws
 mcore-$(CONFIG_X86_VISWS)	:= arch/x86/mach-visws/
 
-# NUMAQ subarch support
-mflags-$(CONFIG_X86_NUMAQ)	:= -Iinclude/asm-x86/mach-numaq
-mcore-$(CONFIG_X86_NUMAQ)	:= arch/x86/mach-default/
-
-# BIGSMP subarch support
-mflags-$(CONFIG_X86_BIGSMP)	:= -Iinclude/asm-x86/mach-bigsmp
-mcore-$(CONFIG_X86_BIGSMP)	:= arch/x86/mach-default/
-
-#Summit subarch support
-mflags-$(CONFIG_X86_SUMMIT)	:= -Iinclude/asm-x86/mach-summit
-mcore-$(CONFIG_X86_SUMMIT)	:= arch/x86/mach-default/
-
 # generic subarchitecture
 mflags-$(CONFIG_X86_GENERICARCH):= -Iinclude/asm-x86/mach-generic
 fcore-$(CONFIG_X86_GENERICARCH)	+= arch/x86/mach-generic/
 mcore-$(CONFIG_X86_GENERICARCH)	:= arch/x86/mach-default/
 
-
-# ES7000 subarch support
-mflags-$(CONFIG_X86_ES7000)	:= -Iinclude/asm-x86/mach-es7000
-fcore-$(CONFIG_X86_ES7000)	:= arch/x86/mach-es7000/
-mcore-$(CONFIG_X86_ES7000)	:= arch/x86/mach-default/
-
 # RDC R-321x subarch support
 mflags-$(CONFIG_X86_RDC321X)	:= -Iinclude/asm-x86/mach-rdc321x
 mcore-$(CONFIG_X86_RDC321X)	:= arch/x86/mach-default/

arch/x86/boot/compressed/misc.c

@@ -221,10 +221,6 @@ static char *vidmem;
 static int vidport;
 static int lines, cols;
 
-#ifdef CONFIG_X86_NUMAQ
-void *xquad_portio;
-#endif
-
 #include "../../../../lib/inflate.c"
 
 static void *malloc(int size)

arch/x86/kernel/acpi/boot.c

@@ -848,7 +848,7 @@ static int __init acpi_parse_madt_lapic_entries(void)
 #ifdef	CONFIG_X86_IO_APIC
 #define MP_ISA_BUS		0
 
-#if defined(CONFIG_X86_ES7000) || defined(CONFIG_X86_GENERICARCH)
+#ifdef CONFIG_X86_ES7000
 extern int es7000_plat;
 #endif
 
@@ -997,7 +997,7 @@ void __init mp_config_acpi_legacy_irqs(void)
 	set_bit(MP_ISA_BUS, mp_bus_not_pci);
 	Dprintk("Bus #%d is ISA\n", MP_ISA_BUS);
 
-#if defined(CONFIG_X86_ES7000) || defined(CONFIG_X86_GENERICARCH)
+#ifdef CONFIG_X86_ES7000
 	/*
 	 * Older generations of ES7000 have no legacy identity mappings
 	 */

arch/x86/kernel/io_apic_32.c

@@ -1722,7 +1722,6 @@ void disable_IO_APIC(void)
  * by Matt Domsch <Matt_Domsch@dell.com>  Tue Dec 21 12:25:05 CST 1999
  */
 
-#ifndef CONFIG_X86_NUMAQ
 static void __init setup_ioapic_ids_from_mpc(void)
 {
 	union IO_APIC_reg_00 reg_00;
@@ -1732,6 +1731,11 @@ static void __init setup_ioapic_ids_from_mpc(void)
 	unsigned char old_id;
 	unsigned long flags;
 
+#ifdef CONFIG_X86_NUMAQ
+	if (found_numaq)
+		return;
+#endif
+
 	/*
 	 * Don't check I/O APIC IDs for xAPIC systems.  They have
 	 * no meaning without the serial APIC bus.
@@ -1828,9 +1832,6 @@ static void __init setup_ioapic_ids_from_mpc(void)
 			apic_printk(APIC_VERBOSE, " ok.\n");
 	}
 }
-#else
-static void __init setup_ioapic_ids_from_mpc(void) { }
-#endif
 
 int no_timer_check __initdata;
 

arch/x86/kernel/mpparse.c

@@ -49,15 +49,73 @@ static int __init mpf_checksum(unsigned char *mp, int len)
 }
 
 #ifdef CONFIG_X86_NUMAQ
+int found_numaq;
 /*
  * Have to match translation table entries to main table entries by counter
  * hence the mpc_record variable .... can't see a less disgusting way of
  * doing this ....
  */
+struct mpc_config_translation {
+	unsigned char mpc_type;
+	unsigned char trans_len;
+	unsigned char trans_type;
+	unsigned char trans_quad;
+	unsigned char trans_global;
+	unsigned char trans_local;
+	unsigned short trans_reserved;
+};
+
 
 static int mpc_record;
 static struct mpc_config_translation *translation_table[MAX_MPC_ENTRY]
     __cpuinitdata;
+
+static inline int generate_logical_apicid(int quad, int phys_apicid)
+{
+	return (quad << 4) + (phys_apicid ? phys_apicid << 1 : 1);
+}
+
+
+static inline int mpc_apic_id(struct mpc_config_processor *m,
+			struct mpc_config_translation *translation_record)
+{
+	int quad = translation_record->trans_quad;
+	int logical_apicid = generate_logical_apicid(quad, m->mpc_apicid);
+
+	printk(KERN_DEBUG "Processor #%d %u:%u APIC version %d (quad %d, apic %d)\n",
+	       m->mpc_apicid,
+	       (m->mpc_cpufeature & CPU_FAMILY_MASK) >> 8,
+	       (m->mpc_cpufeature & CPU_MODEL_MASK) >> 4,
+	       m->mpc_apicver, quad, logical_apicid);
+	return logical_apicid;
+}
+
+int mp_bus_id_to_node[MAX_MP_BUSSES];
+
+int mp_bus_id_to_local[MAX_MP_BUSSES];
+
+static void mpc_oem_bus_info(struct mpc_config_bus *m, char *name,
+	struct mpc_config_translation *translation)
+{
+	int quad = translation->trans_quad;
+	int local = translation->trans_local;
+
+	mp_bus_id_to_node[m->mpc_busid] = quad;
+	mp_bus_id_to_local[m->mpc_busid] = local;
+	printk(KERN_INFO "Bus #%d is %s (node %d)\n",
+	       m->mpc_busid, name, quad);
+}
+
+int quad_local_to_mp_bus_id [NR_CPUS/4][4];
+static void mpc_oem_pci_bus(struct mpc_config_bus *m,
+	struct mpc_config_translation *translation)
+{
+	int quad = translation->trans_quad;
+	int local = translation->trans_local;
+
+	quad_local_to_mp_bus_id[quad][local] = m->mpc_busid;
+}
+
 #endif
 
 static void __cpuinit MP_processor_info(struct mpc_config_processor *m)
@@ -321,11 +379,11 @@ static void __init smp_read_mpc_oem(struct mp_config_oemtable *oemtable,
 	}
 }
 
-static inline void mps_oem_check(struct mp_config_table *mpc, char *oem,
+void numaq_mps_oem_check(struct mp_config_table *mpc, char *oem,
 				 char *productid)
 {
 	if (strncmp(oem, "IBM NUMA", 8))
-		printk("Warning!  May not be a NUMA-Q system!\n");
+		printk("Warning!  Not a NUMA-Q system!\n");
 	else
 		found_numaq = 1;
 
@@ -388,7 +446,16 @@ static int __init smp_read_mpc(struct mp_config_table *mpc, unsigned early)
 		return 0;
 
 #ifdef CONFIG_X86_32
-	mps_oem_check(mpc, oem, str);
+	/*
+	 * need to make sure summit and es7000's mps_oem_check is safe to be
+	 * called early via genericarch 's mps_oem_check
+	 */
+	if (early) {
+#ifdef CONFIG_X86_NUMAQ
+		numaq_mps_oem_check(mpc, oem, str);
+#endif
+	} else
+		mps_oem_check(mpc, oem, str);
 #endif
 
 	/* save the local APIC address, it might be non-default */

arch/x86/kernel/numaq_32.c

@@ -36,8 +36,6 @@
 
 #define	MB_TO_PAGES(addr) ((addr) << (20 - PAGE_SHIFT))
 
-int found_numaq;
-
 /*
  * Function: smp_dump_qct()
  *

arch/x86/kernel/summit_32.c

@@ -36,7 +36,9 @@ static struct rio_table_hdr *rio_table_hdr __initdata;
 static struct scal_detail   *scal_devs[MAX_NUMNODES] __initdata;
 static struct rio_detail    *rio_devs[MAX_NUMNODES*4] __initdata;
 
+#ifndef CONFIG_X86_NUMAQ
 static int mp_bus_id_to_node[MAX_MP_BUSSES] __initdata;
+#endif
 
 static int __init setup_pci_node_map_for_wpeg(int wpeg_num, int last_bus)
 {

arch/x86/mach-es7000/Makefile

@@ -3,4 +3,3 @@
 #
 
 obj-$(CONFIG_X86_ES7000)	:= es7000plat.o
-obj-$(CONFIG_X86_GENERICARCH)	:= es7000plat.o

arch/x86/mach-es7000/es7000plat.c

@@ -177,53 +177,6 @@ find_unisys_acpi_oem_table(unsigned long *oem_addr)
 }
 #endif
 
-/*
- * This file also gets compiled if CONFIG_X86_GENERICARCH is set. Generic
- * arch already has got following function definitions (asm-generic/es7000.c)
- * hence no need to define these for that case.
- */
-#ifndef CONFIG_X86_GENERICARCH
-void es7000_sw_apic(void);
-void __init enable_apic_mode(void)
-{
-	es7000_sw_apic();
-	return;
-}
-
-__init int mps_oem_check(struct mp_config_table *mpc, char *oem,
-		char *productid)
-{
-	if (mpc->mpc_oemptr) {
-		struct mp_config_oemtable *oem_table =
-			(struct mp_config_oemtable *)mpc->mpc_oemptr;
-		if (!strncmp(oem, "UNISYS", 6))
-			return parse_unisys_oem((char *)oem_table);
-	}
-	return 0;
-}
-#ifdef CONFIG_ACPI
-/* Hook from generic ACPI tables.c */
-int __init acpi_madt_oem_check(char *oem_id, char *oem_table_id)
-{
-	unsigned long oem_addr;
-	if (!find_unisys_acpi_oem_table(&oem_addr)) {
-		if (es7000_check_dsdt())
-			return parse_unisys_oem((char *)oem_addr);
-		else {
-			setup_unisys();
-			return 1;
-		}
-	}
-	return 0;
-}
-#else
-int __init acpi_madt_oem_check(char *oem_id, char *oem_table_id)
-{
-	return 0;
-}
-#endif
-#endif /* COFIG_X86_GENERICARCH */
-
 static void
 es7000_spin(int n)
 {

arch/x86/mach-generic/Makefile

@@ -2,7 +2,11 @@
 # Makefile for the generic architecture
 #
 
-EXTRA_CFLAGS	:= -Iarch/x86/kernel
+EXTRA_CFLAGS			:= -Iarch/x86/kernel
 
-obj-y		:= probe.o summit.o bigsmp.o es7000.o default.o 
-obj-y		+= ../../x86/mach-es7000/
+obj-y				:= probe.o default.o
+obj-$(CONFIG_X86_NUMAQ)		+= numaq.o
+obj-$(CONFIG_X86_SUMMIT)	+= summit.o
+obj-$(CONFIG_X86_BIGSMP)	+= bigsmp.o
+obj-$(CONFIG_X86_ES7000)	+= es7000.o
+obj-$(CONFIG_X86_ES7000)	+= ../../x86/mach-es7000/