diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-01-06 13:58:21 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-01-06 13:58:21 -0800 |
commit | 67b0243131150391125d8d0beb5359d7aec78b55 (patch) | |
tree | ce1299f3a6e5bb75e89ccf003095be4942cd5e29 /arch/x86 | |
parent | 376613e81ddc68f545fd5c87ffc3ad222b7abe5f (diff) | |
parent | c284b42abadbb22083bfde24d308899c08d44ffa (diff) | |
download | linux-3.10-67b0243131150391125d8d0beb5359d7aec78b55.tar.gz linux-3.10-67b0243131150391125d8d0beb5359d7aec78b55.tar.bz2 linux-3.10-67b0243131150391125d8d0beb5359d7aec78b55.zip |
Merge branch 'x86-apic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
* 'x86-apic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86: Skip cpus with apic-ids >= 255 in !x2apic_mode
x86, x2apic: Allow "nox2apic" to disable x2apic mode setup by BIOS
x86, x2apic: Fallback to xapic when BIOS doesn't setup interrupt-remapping
x86, acpi: Skip acpi x2apic entries if the x2apic feature is not present
x86, apic: Add probe() for apic_flat
x86: Simplify code by removing a !SMP #ifdefs from 'struct cpuinfo_x86'
x86: Convert per-cpu counter icr_read_retry_count into a member of irq_stat
x86: Add per-cpu stat counter for APIC ICR read tries
pci, x86/io-apic: Allow PCI_IOAPIC to be user configurable on x86
x86: Fix the !CONFIG_NUMA build of the new CPU ID fixup code support
x86: Add NumaChip support
x86: Add x86_init platform override to fix up NUMA core numbering
x86: Make flat_init_apic_ldr() available
Diffstat (limited to 'arch/x86')
25 files changed, 627 insertions, 60 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 67d6af3581b..5731eb70e0a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -342,6 +342,7 @@ config X86_EXTENDED_PLATFORM If you enable this option then you'll be able to select support for the following (non-PC) 64 bit x86 platforms: + Numascale NumaChip ScaleMP vSMP SGI Ultraviolet @@ -350,6 +351,18 @@ config X86_EXTENDED_PLATFORM endif # This is an alphabetically sorted list of 64 bit extended platforms # Please maintain the alphabetic order if and when there are additions +config X86_NUMACHIP + bool "Numascale NumaChip" + depends on X86_64 + depends on X86_EXTENDED_PLATFORM + depends on NUMA + depends on SMP + depends on X86_X2APIC + depends on !EDAC_AMD64 + ---help--- + Adds support for Numascale NumaChip large-SMP systems. Needed to + enable more than ~168 cores. + If you don't have one of these, you should say N here. config X86_VSMP bool "ScaleMP vSMP" diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 1a6c09af048..3ab9bdd87e7 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -176,6 +176,7 @@ static inline u64 native_x2apic_icr_read(void) } extern int x2apic_phys; +extern int x2apic_preenabled; extern void check_x2apic(void); extern void enable_x2apic(void); extern void x2apic_icr_write(u32 low, u32 id); @@ -198,6 +199,9 @@ static inline void x2apic_force_phys(void) x2apic_phys = 1; } #else +static inline void disable_x2apic(void) +{ +} static inline void check_x2apic(void) { } @@ -212,6 +216,7 @@ static inline void x2apic_force_phys(void) { } +#define nox2apic 0 #define x2apic_preenabled 0 #define x2apic_supported() 0 #endif @@ -410,6 +415,7 @@ extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip); #endif #ifdef CONFIG_X86_LOCAL_APIC + static inline u32 apic_read(u32 reg) { return apic->read(reg); diff --git a/arch/x86/include/asm/apic_flat_64.h b/arch/x86/include/asm/apic_flat_64.h new file mode 100644 index 00000000000..a2d31279644 --- /dev/null +++ b/arch/x86/include/asm/apic_flat_64.h @@ -0,0 +1,7 @@ +#ifndef _ASM_X86_APIC_FLAT_64_H +#define _ASM_X86_APIC_FLAT_64_H + +extern void flat_init_apic_ldr(void); + +#endif + diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h index 3925d800786..134bba00df0 100644 --- a/arch/x86/include/asm/apicdef.h +++ b/arch/x86/include/asm/apicdef.h @@ -144,6 +144,7 @@ #define APIC_BASE (fix_to_virt(FIX_APIC_BASE)) #define APIC_BASE_MSR 0x800 +#define XAPIC_ENABLE (1UL << 11) #define X2APIC_ENABLE (1UL << 10) #ifdef CONFIG_X86_32 diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 55e4de613f0..da0b3ca815b 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -11,6 +11,7 @@ typedef struct { #ifdef CONFIG_X86_LOCAL_APIC unsigned int apic_timer_irqs; /* arch dependent */ unsigned int irq_spurious_count; + unsigned int icr_read_retry_count; #endif unsigned int x86_platform_ipis; /* arch dependent */ unsigned int apic_perf_irqs; diff --git a/arch/x86/include/asm/numachip/numachip_csr.h b/arch/x86/include/asm/numachip/numachip_csr.h new file mode 100644 index 00000000000..660f843df92 --- /dev/null +++ b/arch/x86/include/asm/numachip/numachip_csr.h @@ -0,0 +1,167 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Numascale NumaConnect-Specific Header file + * + * Copyright (C) 2011 Numascale AS. All rights reserved. + * + * Send feedback to <support@numascale.com> + * + */ + +#ifndef _ASM_X86_NUMACHIP_NUMACHIP_CSR_H +#define _ASM_X86_NUMACHIP_NUMACHIP_CSR_H + +#include <linux/numa.h> +#include <linux/percpu.h> +#include <linux/io.h> +#include <linux/swab.h> +#include <asm/types.h> +#include <asm/processor.h> + +#define CSR_NODE_SHIFT 16 +#define CSR_NODE_BITS(p) (((unsigned long)(p)) << CSR_NODE_SHIFT) +#define CSR_NODE_MASK 0x0fff /* 4K nodes */ + +/* 32K CSR space, b15 indicates geo/non-geo */ +#define CSR_OFFSET_MASK 0x7fffUL + +/* Global CSR space covers all 4K possible nodes with 64K CSR space per node */ +#define NUMACHIP_GCSR_BASE 0x3fff00000000ULL +#define NUMACHIP_GCSR_LIM 0x3fff0fffffffULL +#define NUMACHIP_GCSR_SIZE (NUMACHIP_GCSR_LIM - NUMACHIP_GCSR_BASE + 1) + +/* + * Local CSR space starts in global CSR space with "nodeid" = 0xfff0, however + * when using the direct mapping on x86_64, both start and size needs to be + * aligned with PMD_SIZE which is 2M + */ +#define NUMACHIP_LCSR_BASE 0x3ffffe000000ULL +#define NUMACHIP_LCSR_LIM 0x3fffffffffffULL +#define NUMACHIP_LCSR_SIZE (NUMACHIP_LCSR_LIM - NUMACHIP_LCSR_BASE + 1) + +static inline void *gcsr_address(int node, unsigned long offset) +{ + return __va(NUMACHIP_GCSR_BASE | (1UL << 15) | + CSR_NODE_BITS(node & CSR_NODE_MASK) | (offset & CSR_OFFSET_MASK)); +} + +static inline void *lcsr_address(unsigned long offset) +{ + return __va(NUMACHIP_LCSR_BASE | (1UL << 15) | + CSR_NODE_BITS(0xfff0) | (offset & CSR_OFFSET_MASK)); +} + +static inline unsigned int read_gcsr(int node, unsigned long offset) +{ + return swab32(readl(gcsr_address(node, offset))); +} + +static inline void write_gcsr(int node, unsigned long offset, unsigned int val) +{ + writel(swab32(val), gcsr_address(node, offset)); +} + +static inline unsigned int read_lcsr(unsigned long offset) +{ + return swab32(readl(lcsr_address(offset))); +} + +static inline void write_lcsr(unsigned long offset, unsigned int val) +{ + writel(swab32(val), lcsr_address(offset)); +} + +/* ========================================================================= */ +/* CSR_G0_STATE_CLEAR */ +/* ========================================================================= */ + +#define CSR_G0_STATE_CLEAR (0x000 + (0 << 12)) +union numachip_csr_g0_state_clear { + unsigned int v; + struct numachip_csr_g0_state_clear_s { + unsigned int _state:2; + unsigned int _rsvd_2_6:5; + unsigned int _lost:1; + unsigned int _rsvd_8_31:24; + } s; +}; + +/* ========================================================================= */ +/* CSR_G0_NODE_IDS */ +/* ========================================================================= */ + +#define CSR_G0_NODE_IDS (0x008 + (0 << 12)) +union numachip_csr_g0_node_ids { + unsigned int v; + struct numachip_csr_g0_node_ids_s { + unsigned int _initialid:16; + unsigned int _nodeid:12; + unsigned int _rsvd_28_31:4; + } s; +}; + +/* ========================================================================= */ +/* CSR_G3_EXT_IRQ_GEN */ +/* ========================================================================= */ + +#define CSR_G3_EXT_IRQ_GEN (0x030 + (3 << 12)) +union numachip_csr_g3_ext_irq_gen { + unsigned int v; + struct numachip_csr_g3_ext_irq_gen_s { + unsigned int _vector:8; + unsigned int _msgtype:3; + unsigned int _index:5; + unsigned int _destination_apic_id:16; + } s; +}; + +/* ========================================================================= */ +/* CSR_G3_EXT_IRQ_STATUS */ +/* ========================================================================= */ + +#define CSR_G3_EXT_IRQ_STATUS (0x034 + (3 << 12)) +union numachip_csr_g3_ext_irq_status { + unsigned int v; + struct numachip_csr_g3_ext_irq_status_s { + unsigned int _result:32; + } s; +}; + +/* ========================================================================= */ +/* CSR_G3_EXT_IRQ_DEST */ +/* ========================================================================= */ + +#define CSR_G3_EXT_IRQ_DEST (0x038 + (3 << 12)) +union numachip_csr_g3_ext_irq_dest { + unsigned int v; + struct numachip_csr_g3_ext_irq_dest_s { + unsigned int _irq:8; + unsigned int _rsvd_8_31:24; + } s; +}; + +/* ========================================================================= */ +/* CSR_G3_NC_ATT_MAP_SELECT */ +/* ========================================================================= */ + +#define CSR_G3_NC_ATT_MAP_SELECT (0x7fc + (3 << 12)) +union numachip_csr_g3_nc_att_map_select { + unsigned int v; + struct numachip_csr_g3_nc_att_map_select_s { + unsigned int _upper_address_bits:4; + unsigned int _select_ram:4; + unsigned int _rsvd_8_31:24; + } s; +}; + +/* ========================================================================= */ +/* CSR_G3_NC_ATT_MAP_SELECT_0-255 */ +/* ========================================================================= */ + +#define CSR_G3_NC_ATT_MAP_SELECT_0 (0x800 + (3 << 12)) + +#endif /* _ASM_X86_NUMACHIP_NUMACHIP_CSR_H */ + diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index b650435ffb5..aa9088c2693 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -99,7 +99,6 @@ struct cpuinfo_x86 { u16 apicid; u16 initial_apicid; u16 x86_clflush_size; -#ifdef CONFIG_SMP /* number of cores as seen by the OS: */ u16 booted_cores; /* Physical processor id: */ @@ -110,7 +109,6 @@ struct cpuinfo_x86 { u8 compute_unit_id; /* Index into per_cpu list: */ u16 cpu_index; -#endif u32 microcode; } __attribute__((__aligned__(SMP_CACHE_BYTES))); diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 1971e652d24..1ac860a0984 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -7,6 +7,7 @@ struct mpc_bus; struct mpc_cpu; struct mpc_table; +struct cpuinfo_x86; /** * struct x86_init_mpparse - platform specific mpparse ops @@ -147,6 +148,7 @@ struct x86_init_ops { */ struct x86_cpuinit_ops { void (*setup_percpu_clockev)(void); + void (*fixup_cpu_id)(struct cpuinfo_x86 *c, int node); }; /** @@ -186,5 +188,6 @@ extern struct x86_msi_ops x86_msi; extern void x86_init_noop(void); extern void x86_init_uint_noop(unsigned int unused); +extern void x86_default_fixup_cpu_id(struct cpuinfo_x86 *c, int node); #endif diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 4558f0d0822..ce664f33ea8 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -219,6 +219,8 @@ static int __init acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end) { struct acpi_madt_local_x2apic *processor = NULL; + int apic_id; + u8 enabled; processor = (struct acpi_madt_local_x2apic *)header; @@ -227,6 +229,8 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end) acpi_table_print_madt_entry(header); + apic_id = processor->local_apic_id; + enabled = processor->lapic_flags & ACPI_MADT_ENABLED; #ifdef CONFIG_X86_X2APIC /* * We need to register disabled CPU as well to permit @@ -235,8 +239,10 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end) * to not preallocating memory for all NR_CPUS * when we use CPU hotplug. */ - acpi_register_lapic(processor->local_apic_id, /* APIC ID */ - processor->lapic_flags & ACPI_MADT_ENABLED); + if (!cpu_has_x2apic && (apic_id >= 0xff) && enabled) + printk(KERN_WARNING PREFIX "x2apic entry ignored\n"); + else + acpi_register_lapic(apic_id, enabled); #else printk(KERN_WARNING PREFIX "x2apic entry ignored\n"); #endif diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 4c39baa8fac..013c1810ce7 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -123,16 +123,14 @@ int amd_get_subcaches(int cpu) { struct pci_dev *link = node_to_amd_nb(amd_get_nb_id(cpu))->link; unsigned int mask; - int cuid = 0; + int cuid; if (!amd_nb_has_feature(AMD_NB_L3_PARTITIONING)) return 0; pci_read_config_dword(link, 0x1d4, &mask); -#ifdef CONFIG_SMP cuid = cpu_data(cpu).compute_unit_id; -#endif return (mask >> (4 * cuid)) & 0xf; } @@ -141,7 +139,7 @@ int amd_set_subcaches(int cpu, int mask) static unsigned int reset, ban; struct amd_northbridge *nb = node_to_amd_nb(amd_get_nb_id(cpu)); unsigned int reg; - int cuid = 0; + int cuid; if (!amd_nb_has_feature(AMD_NB_L3_PARTITIONING) || mask > 0xf) return -EINVAL; @@ -159,9 +157,7 @@ int amd_set_subcaches(int cpu, int mask) pci_write_config_dword(nb->misc, 0x1b8, reg & ~0x180000); } -#ifdef CONFIG_SMP cuid = cpu_data(cpu).compute_unit_id; -#endif mask <<= 4 * cuid; mask |= (0xf ^ (1 << cuid)) << 26; diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile index 767fd04f284..0ae0323b1f9 100644 --- a/arch/x86/kernel/apic/Makefile +++ b/arch/x86/kernel/apic/Makefile @@ -10,6 +10,7 @@ obj-$(CONFIG_SMP) += ipi.o ifeq ($(CONFIG_X86_64),y) # APIC probe will depend on the listing order here +obj-$(CONFIG_X86_NUMACHIP) += apic_numachip.o obj-$(CONFIG_X86_UV) += x2apic_uv_x.o obj-$(CONFIG_X86_X2APIC) += x2apic_phys.o obj-$(CONFIG_X86_X2APIC) += x2apic_cluster.o diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 2cd2d93643d..2eec05b6d1b 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -146,16 +146,26 @@ __setup("apicpmtimer", setup_apicpmtimer); int x2apic_mode; #ifdef CONFIG_X86_X2APIC /* x2apic enabled before OS handover */ -static int x2apic_preenabled; +int x2apic_preenabled; +static int x2apic_disabled; +static int nox2apic; static __init int setup_nox2apic(char *str) { if (x2apic_enabled()) { - pr_warning("Bios already enabled x2apic, " - "can't enforce nox2apic"); - return 0; - } + int apicid = native_apic_msr_read(APIC_ID); + + if (apicid >= 255) { + pr_warning("Apicid: %08x, cannot enforce nox2apic\n", + apicid); + return 0; + } + + pr_warning("x2apic already enabled. will disable it\n"); + } else + setup_clear_cpu_cap(X86_FEATURE_X2APIC); + + nox2apic = 1; - setup_clear_cpu_cap(X86_FEATURE_X2APIC); return 0; } early_param("nox2apic", setup_nox2apic); @@ -250,6 +260,7 @@ u32 native_safe_apic_wait_icr_idle(void) send_status = apic_read(APIC_ICR) & APIC_ICR_BUSY; if (!send_status) break; + inc_irq_stat(icr_read_retry_count); udelay(100); } while (timeout++ < 1000); @@ -1431,6 +1442,45 @@ void __init bsp_end_local_APIC_setup(void) } #ifdef CONFIG_X86_X2APIC +/* + * Need to disable xapic and x2apic at the same time and then enable xapic mode + */ +static inline void __disable_x2apic(u64 msr) +{ + wrmsrl(MSR_IA32_APICBASE, + msr & ~(X2APIC_ENABLE | XAPIC_ENABLE)); + wrmsrl(MSR_IA32_APICBASE, msr & ~X2APIC_ENABLE); +} + +static __init void disable_x2apic(void) +{ + u64 msr; + + if (!cpu_has_x2apic) + return; + + rdmsrl(MSR_IA32_APICBASE, msr); + if (msr & X2APIC_ENABLE) { + u32 x2apic_id = read_apic_id(); + + if (x2apic_id >= 255) + panic("Cannot disable x2apic, id: %08x\n", x2apic_id); + + pr_info("Disabling x2apic\n"); + __disable_x2apic(msr); + + if (nox2apic) { + clear_cpu_cap(&cpu_data(0), X86_FEATURE_X2APIC); + setup_clear_cpu_cap(X86_FEATURE_X2APIC); + } + + x2apic_disabled = 1; + x2apic_mode = 0; + + register_lapic_address(mp_lapic_addr); + } +} + void check_x2apic(void) { if (x2apic_enabled()) { @@ -1441,15 +1491,20 @@ void check_x2apic(void) void enable_x2apic(void) { - int msr, msr2; + u64 msr; + + rdmsrl(MSR_IA32_APICBASE, msr); + if (x2apic_disabled) { + __disable_x2apic(msr); + return; + } if (!x2apic_mode) return; - rdmsr(MSR_IA32_APICBASE, msr, msr2); if (!(msr & X2APIC_ENABLE)) { printk_once(KERN_INFO "Enabling x2apic\n"); - wrmsr(MSR_IA32_APICBASE, msr | X2APIC_ENABLE, msr2); + wrmsrl(MSR_IA32_APICBASE, msr | X2APIC_ENABLE); } } #endif /* CONFIG_X86_X2APIC */ @@ -1486,25 +1541,34 @@ void __init enable_IR_x2apic(void) ret = save_ioapic_entries(); if (ret) { pr_info("Saving IO-APIC state failed: %d\n", ret); - goto out; + return; } local_irq_save(flags); legacy_pic->mask_all(); mask_ioapic_entries(); + if (x2apic_preenabled && nox2apic) + disable_x2apic(); + if (dmar_table_init_ret) ret = -1; else ret = enable_IR(); + if (!x2apic_supported()) + goto skip_x2apic; + if (ret < 0) { /* IR is required if there is APIC ID > 255 even when running * under KVM */ if (max_physical_apicid > 255 || - !hypervisor_x2apic_available()) - goto nox2apic; + !hypervisor_x2apic_available()) { + if (x2apic_preenabled) + disable_x2apic(); + goto skip_x2apic; + } /* * without IR all CPUs can be addressed by IOAPIC/MSI * only in physical mode @@ -1512,8 +1576,10 @@ void __init enable_IR_x2apic(void) x2apic_force_phys(); } - if (ret == IRQ_REMAP_XAPIC_MODE) - goto nox2apic; + if (ret == IRQ_REMAP_XAPIC_MODE) { + pr_info("x2apic not enabled, IRQ remapping is in xapic mode\n"); + goto skip_x2apic; + } x2apic_enabled = 1; @@ -1523,22 +1589,11 @@ void __init enable_IR_x2apic(void) pr_info("Enabled x2apic\n"); } -nox2apic: +skip_x2apic: if (ret < 0) /* IR enabling failed */ restore_ioapic_entries(); legacy_pic->restore_mask(); local_irq_restore(flags); - -out: - if (x2apic_enabled || !x2apic_supported()) - return; - - if (x2apic_preenabled) - panic("x2apic: enabled by BIOS but kernel init failed."); - else if (ret == IRQ_REMAP_XAPIC_MODE) - pr_info("x2apic not enabled, IRQ remapping is in xapic mode\n"); - else if (ret < 0) - pr_info("x2apic not enabled, IRQ remapping init failed\n"); } #ifdef CONFIG_X86_64 diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index f7a41e4cae4..8c3cdded6f2 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -62,7 +62,7 @@ static void flat_vector_allocation_domain(int cpu, struct cpumask *retmask) * an APIC. See e.g. "AP-388 82489DX User's Manual" (Intel * document number 292116). So here it goes... */ -static void flat_init_apic_ldr(void) +void flat_init_apic_ldr(void) { unsigned long val; unsigned long num, id; @@ -171,9 +171,14 @@ static int flat_phys_pkg_id(int initial_apic_id, int index_msb) return initial_apic_id >> index_msb; } +static int flat_probe(void) +{ + return 1; +} + static struct apic apic_flat = { .name = "flat", - .probe = NULL, + .probe = flat_probe, .acpi_madt_oem_check = flat_acpi_madt_oem_check, .apic_id_registered = flat_apic_id_registered, diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c new file mode 100644 index 00000000000..09d3d8c1cd9 --- /dev/null +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -0,0 +1,294 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Numascale NumaConnect-Specific APIC Code + * + * Copyright (C) 2011 Numascale AS. All rights reserved. + * + * Send feedback to <support@numascale.com> + * + */ + +#include <linux/errno.h> +#include <linux/threads.h> +#include <linux/cpumask.h> +#include <linux/string.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/ctype.h> +#include <linux/init.h> +#include <linux/hardirq.h> +#include <linux/delay.h> + +#include <asm/numachip/numachip_csr.h> +#include <asm/smp.h> +#include <asm/apic.h> +#include <asm/ipi.h> +#include <asm/apic_flat_64.h> + +static int numachip_system __read_mostly; + +static struct apic apic_numachip __read_mostly; + +static unsigned int get_apic_id(unsigned long x) +{ + unsigned long value; + unsigned int id; + + rdmsrl(MSR_FAM10H_NODE_ID, value); + id = ((x >> 24) & 0xffU) | ((value << 2) & 0x3f00U); + + return id; +} + +static unsigned long set_apic_id(unsigned int id) +{ + unsigned long x; + + x = ((id & 0xffU) << 24); + return x; +} + +static unsigned int read_xapic_id(void) +{ + return get_apic_id(apic_read(APIC_ID)); +} + +static int numachip_apic_id_registered(void) +{ + return physid_isset(read_xapic_id(), phys_cpu_present_map); +} + +static int numachip_phys_pkg_id(int initial_apic_id, int index_msb) +{ + return initial_apic_id >> index_msb; +} + +static const struct cpumask *numachip_target_cpus(void) +{ + return cpu_online_mask; +} + +static void numachip_vector_allocation_domain(int cpu, struct cpumask *retmask) +{ + cpumask_clear(retmask); + cpumask_set_cpu(cpu, retmask); +} + +static int __cpuinit numachip_wakeup_secondary(int phys_apicid, unsigned long start_rip) +{ + union numachip_csr_g3_ext_irq_gen int_gen; + + int_gen.s._destination_apic_id = phys_apicid; + int_gen.s._vector = 0; + int_gen.s._msgtype = APIC_DM_INIT >> 8; + int_gen.s._index = 0; + + write_lcsr(CSR_G3_EXT_IRQ_GEN, int_gen.v); + + int_gen.s._msgtype = APIC_DM_STARTUP >> 8; + int_gen.s._vector = start_rip >> 12; + + write_lcsr(CSR_G3_EXT_IRQ_GEN, int_gen.v); + + atomic_set(&init_deasserted, 1); + return 0; +} + +static void numachip_send_IPI_one(int cpu, int vector) +{ + union numachip_csr_g3_ext_irq_gen int_gen; + int apicid = per_cpu(x86_cpu_to_apicid, cpu); + + int_gen.s._destination_apic_id = apicid; + int_gen.s._vector = vector; + int_gen.s._msgtype = (vector == NMI_VECTOR ? APIC_DM_NMI : APIC_DM_FIXED) >> 8; + int_gen.s._index = 0; + + write_lcsr(CSR_G3_EXT_IRQ_GEN, int_gen.v); +} + +static void numachip_send_IPI_mask(const struct cpumask *mask, int vector) +{ + unsigned int cpu; + + for_each_cpu(cpu, mask) + numachip_send_IPI_one(cpu, vector); +} + +static void numachip_send_IPI_mask_allbutself(const struct cpumask *mask, + int vector) +{ + unsigned int this_cpu = smp_processor_id(); + unsigned int cpu; + + for_each_cpu(cpu, mask) { + if (cpu != this_cpu) + numachip_send_IPI_one(cpu, vector); + } +} + +static void numachip_send_IPI_allbutself(int vector) +{ + unsigned int this_cpu = smp_processor_id(); + unsigned int cpu; + + for_each_online_cpu(cpu) { + if (cpu != this_cpu) + numachip_send_IPI_one(cpu, vector); + } +} + +static void numachip_send_IPI_all(int vector) +{ + numachip_send_IPI_mask(cpu_online_mask, vector); +} + +static void numachip_send_IPI_self(int vector) +{ + __default_send_IPI_shortcut(APIC_DEST_SELF, vector, APIC_DEST_PHYSICAL); +} + +static unsigned int numachip_cpu_mask_to_apicid(const struct cpumask *cpumask) +{ + int cpu; + + /* + * We're using fixed IRQ delivery, can only return one phys APIC ID. + * May as well be the first. + */ + cpu = cpumask_first(cpumask); + if (likely((unsigned)cpu < nr_cpu_ids)) + return per_cpu(x86_cpu_to_apicid, cpu); + + return BAD_APICID; +} + +static unsigned int +numachip_cpu_mask_to_apicid_and(const struct cpumask *cpumask, + const struct cpumask *andmask) +{ + int cpu; + + /* + * We're using fixed IRQ delivery, can only return one phys APIC ID. + * May as well be the first. + */ + for_each_cpu_and(cpu, cpumask, andmask) { + if (cpumask_test_cpu(cpu, cpu_online_mask)) + break; + } + return per_cpu(x86_cpu_to_apicid, cpu); +} + +static int __init numachip_probe(void) +{ + return apic == &apic_numachip; +} + +static void __init map_csrs(void) +{ + printk(KERN_INFO "NumaChip: Mapping local CSR space (%016llx - %016llx)\n", + NUMACHIP_LCSR_BASE, NUMACHIP_LCSR_BASE + NUMACHIP_LCSR_SIZE - 1); + init_extra_mapping_uc(NUMACHIP_LCSR_BASE, NUMACHIP_LCSR_SIZE); + + printk(KERN_INFO "NumaChip: Mapping global CSR space (%016llx - %016llx)\n", + NUMACHIP_GCSR_BASE, NUMACHIP_GCSR_BASE + NUMACHIP_GCSR_SIZE - 1); + init_extra_mapping_uc(NUMACHIP_GCSR_BASE, NUMACHIP_GCSR_SIZE); +} + +static void fixup_cpu_id(struct cpuinfo_x86 *c, int node) +{ + c->phys_proc_id = node; + per_cpu(cpu_llc_id, smp_processor_id()) = node; +} + +static int __init numachip_system_init(void) +{ + unsigned int val; + + if (!numachip_system) + return 0; + + x86_cpuinit.fixup_cpu_id = fixup_cpu_id; + + map_csrs(); + + val = read_lcsr(CSR_G0_NODE_IDS); + printk(KERN_INFO "NumaChip: Local NodeID = %08x\n", val); + + return 0; +} +early_initcall(numachip_system_init); + +static int numachip_acpi_madt_oem_check(char *oem_id, char *oem_table_id) +{ + if (!strncmp(oem_id, "NUMASC", 6)) { + numachip_system = 1; + return 1; + } + + return 0; +} + +static struct apic apic_numachip __refconst = { + + .name = "NumaConnect system", + .probe = numachip_probe, + .acpi_madt_oem_check = numachip_acpi_madt_oem_check, + .apic_id_registered = numachip_apic_id_registered, + + .irq_delivery_mode = dest_Fixed, + .irq_dest_mode = 0, /* physical */ + + .target_cpus = numachip_target_cpus, + .disable_esr = 0, + .dest_logical = 0, + .check_apicid_used = NULL, + .check_apicid_present = NULL, + + .vector_allocation_domain = numachip_vector_allocation_domain, + .init_apic_ldr = flat_init_apic_ldr, + + .ioapic_phys_id_map = NULL, + .setup_apic_routing = NULL, + .multi_timer_check = NULL, + .cpu_present_to_apicid = default_cpu_present_to_apicid, + .apicid_to_cpu_present = NULL, + .setup_portio_remap = NULL, + .check_phys_apicid_present = default_check_phys_apicid_present, + .enable_apic_mode = NULL, + .phys_pkg_id = numachip_phys_pkg_id, + .mps_oem_check = NULL, + + .get_apic_id = get_apic_id, + .set_apic_id = set_apic_id, + .apic_id_mask = 0xffU << 24, + + .cpu_mask_to_apicid = numachip_cpu_mask_to_apicid, + .cpu_mask_to_apicid_and = numachip_cpu_mask_to_apicid_and, + + .send_IPI_mask = numachip_send_IPI_mask, + .send_IPI_mask_allbutself = numachip_send_IPI_mask_allbutself, + .send_IPI_allbutself = numachip_send_IPI_allbutself, + .send_IPI_all = numachip_send_IPI_all, + .send_IPI_self = numachip_send_IPI_self, + + .wakeup_secondary_cpu = numachip_wakeup_secondary, + .trampoline_phys_low = DEFAULT_TRAMPOLINE_PHYS_LOW, + .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, + .wait_for_init_deassert = NULL, + .smp_callin_clear_local_apic = NULL, + .inquire_remote_apic = NULL, /* REMRD not supported */ + + .read = native_apic_mem_read, + .write = native_apic_mem_write, + .icr_read = native_apic_icr_read, + .icr_write = native_apic_icr_write, + .wait_icr_idle = native_apic_wait_icr_idle, + .safe_wait_icr_idle = native_safe_apic_wait_icr_idle, +}; +apic_driver(apic_numachip); + diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 89805558551..fb072754bc1 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2948,6 +2948,10 @@ static inline void __init check_timer(void) } local_irq_disable(); apic_printk(APIC_QUIET, KERN_INFO "..... failed :(.\n"); + if (x2apic_preenabled) + apic_printk(APIC_QUIET, KERN_INFO + "Perhaps problem with the pre-enabled x2apic mode\n" + "Try booting with x2apic and interrupt-remapping disabled in the bios.\n"); panic("IO-APIC + timer doesn't work! Boot with apic=debug and send a " "report. Then try booting with the 'noapic' option.\n"); out: diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 0bab2b18bb2..f4773f4aae3 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -148,7 +148,6 @@ static void __cpuinit init_amd_k6(struct cpuinfo_x86 *c) static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c) { -#ifdef CONFIG_SMP /* calling is from identify_secondary_cpu() ? */ if (!c->cpu_index) return; @@ -192,7 +191,6 @@ static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c) valid_k7: ; -#endif } static void __cpuinit init_amd_k7(struct cpuinfo_x86 *c) @@ -353,6 +351,13 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c) if (node == NUMA_NO_NODE) node = per_cpu(cpu_llc_id, cpu); + /* + * If core numbers are inconsistent, it's likely a multi-fabric platform, + * so invoke platform-specific handler + */ + if (c->phys_proc_id != node) + x86_cpuinit.fixup_cpu_id(c, node); + if (!node_online(node)) { /* * Two possibilities here: diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index aa003b13a83..850f2963a42 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -676,9 +676,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) if (this_cpu->c_early_init) this_cpu->c_early_init(c); -#ifdef CONFIG_SMP c->cpu_index = 0; -#endif filter_cpuid_features(c, false); setup_smep(c); @@ -764,10 +762,7 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 *c) c->apicid = c->initial_apicid; # endif #endif - -#ifdef CONFIG_X86_HT c->phys_proc_id = c->initial_apicid; -#endif } setup_smep(c); @@ -1141,6 +1136,15 @@ static void dbg_restore_debug_regs(void) #endif /* ! CONFIG_KGDB */ /* + * Prints an error where the NUMA and configured core-number mismatch and the + * platform didn't override this to fix it up + */ +void __cpuinit x86_default_fixup_cpu_id(struct cpuinfo_x86 *c, int node) +{ + pr_err("NUMA core number %d differs from configured core number %d\n", node, c->phys_proc_id); +} + +/* * cpu_init() initializes state that is per-CPU. Some data is already * initialized (naturally) in the bootstrap process, such as the GDT * and IDT. We reload them nevertheless, this function acts as a diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 523131213f0..3e6ff6cbf42 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -181,7 +181,6 @@ static void __cpuinit trap_init_f00f_bug(void) static void __cpuinit intel_smp_check(struct cpuinfo_x86 *c) { -#ifdef CONFIG_SMP /* calling is from identify_secondary_cpu() ? */ if (!c->cpu_index) return; @@ -198,7 +197,6 @@ static void __cpuinit intel_smp_check(struct cpuinfo_x86 *c) WARN_ONCE(1, "WARNING: SMP operation may be unreliable" "with B stepping processors.\n"); } -#endif } static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 2af127d4c3d..e9c9d0aab36 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -119,9 +119,7 @@ void mce_setup(struct mce *m) m->time = get_seconds(); m->cpuvendor = boot_cpu_data.x86_vendor; m->cpuid = cpuid_eax(1); -#ifdef CONFIG_SMP m->socketid = cpu_data(m->extcpu).phys_proc_id; -#endif m->apicid = cpu_data(m->extcpu).initial_apicid; rdmsrl(MSR_IA32_MCG_CAP, m->mcgcap); } diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index f5474218cff..1d76872b6a4 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -64,11 +64,9 @@ struct threshold_bank { }; static DEFINE_PER_CPU(struct threshold_bank * [NR_BANKS], threshold_banks); -#ifdef CONFIG_SMP static unsigned char shared_bank[NR_BANKS] = { 0, 0, 0, 0, 1 }; -#endif static DEFINE_PER_CPU(unsigned char, bank_map); /* see which banks are on */ @@ -202,10 +200,9 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) if (!block) per_cpu(bank_map, cpu) |= (1 << bank); -#ifdef CONFIG_SMP if (shared_bank[bank] && c->cpu_core_id) break; -#endif + offset = setup_APIC_mce(offset, (high & MASK_LVTOFF_HI) >> 20); @@ -531,7 +528,6 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) sprintf(name, "threshold_bank%i", bank); -#ifdef CONFIG_SMP if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) { /* symlink */ i = cpumask_first(cpu_llc_shared_mask(cpu)); @@ -558,7 +554,6 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) goto out; } -#endif b = kzalloc(sizeof(struct threshold_bank), GFP_KERNEL); if (!b) { diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 14b23140e81..8022c668148 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -64,12 +64,10 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c) static int show_cpuinfo(struct seq_file *m, void *v) { struct cpuinfo_x86 *c = v; - unsigned int cpu = 0; + unsigned int cpu; int i; -#ifdef CONFIG_SMP cpu = c->cpu_index; -#endif seq_printf(m, "processor\t: %u\n" "vendor_id\t: %s\n" "cpu family\t: %d\n" diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 5d31e5bdbf8..7943e0c21bd 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -74,6 +74,10 @@ int arch_show_interrupts(struct seq_file *p, int prec) for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->apic_irq_work_irqs); seq_printf(p, " IRQ work interrupts\n"); + seq_printf(p, "%*s: ", prec, "RTR"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", irq_stats(j)->icr_read_retry_count); + seq_printf(p, " APIC ICR read retries\n"); #endif if (x86_platform_ipi_callback) { seq_printf(p, "%*s: ", prec, "PLT"); @@ -136,6 +140,7 @@ u64 arch_irq_stat_cpu(unsigned int cpu) sum += irq_stats(cpu)->irq_spurious_count; sum += irq_stats(cpu)->apic_perf_irqs; sum += irq_stats(cpu)->apic_irq_work_irqs; + sum += irq_stats(cpu)->icr_read_retry_count; #endif if (x86_platform_ipi_callback) sum += irq_stats(cpu)->x86_platform_ipis; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 9f548cb4a95..e38e21754ee 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -840,7 +840,8 @@ int __cpuinit native_cpu_up(unsigned int cpu) pr_debug("++++++++++++++++++++=_---CPU UP %u\n", cpu); if (apicid == BAD_APICID || apicid == boot_cpu_physical_apicid || - !physid_isset(apicid, phys_cpu_present_map)) { + !physid_isset(apicid, phys_cpu_present_map) || + (!x2apic_mode && apicid >= 255)) { printk(KERN_ERR "%s: bad cpu %d\n", __func__, cpu); return -EINVAL; } diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index c1d6cd54939..91f83e21b98 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -92,6 +92,7 @@ struct x86_init_ops x86_init __initdata = { struct x86_cpuinit_ops x86_cpuinit __cpuinitdata = { .setup_percpu_clockev = setup_secondary_APIC_clock, + .fixup_cpu_id = x86_default_fixup_cpu_id, }; static void default_nmi_init(void) { }; diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index 81dbfdeb080..fd61b3fb734 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -69,6 +69,12 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa) if ((pa->flags & ACPI_SRAT_CPU_ENABLED) == 0) return; pxm = pa->proximity_domain; + apic_id = pa->apic_id; + if (!cpu_has_x2apic && (apic_id >= 0xff)) { + printk(KERN_INFO "SRAT: PXM %u -> X2APIC 0x%04x ignored\n", + pxm, apic_id); + return; + } node = setup_node(pxm); if (node < 0) { printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm); @@ -76,7 +82,6 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa) return; } - apic_id = pa->apic_id; if (apic_id >= MAX_LOCAL_APIC) { printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%04x -> Node %u skipped apicid that is too big\n", pxm, apic_id, node); return; |