diff options
Diffstat (limited to 'arch/x86/kernel')
52 files changed, 1298 insertions, 565 deletions
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 4558f0d0822d..ce664f33ea8e 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 4c39baa8facc..013c1810ce72 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/aperture_64.c b/arch/x86/kernel/aperture_64.c index 3d2661ca6542..6e76c191a835 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -88,13 +88,13 @@ static u32 __init allocate_aperture(void) */ addr = memblock_find_in_range(GART_MIN_ADDR, GART_MAX_ADDR, aper_size, aper_size); - if (addr == MEMBLOCK_ERROR || addr + aper_size > GART_MAX_ADDR) { + if (!addr || addr + aper_size > GART_MAX_ADDR) { printk(KERN_ERR "Cannot allocate aperture memory hole (%lx,%uK)\n", addr, aper_size>>10); return 0; } - memblock_x86_reserve_range(addr, addr + aper_size, "aperture64"); + memblock_reserve(addr, aper_size); /* * Kmemleak should not scan this block as it may not be mapped via the * kernel direct mapping. diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile index 767fd04f2843..0ae0323b1f9c 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 f98d84caf94c..2eec05b6d1b8 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); @@ -876,8 +887,8 @@ void __irq_entry smp_apic_timer_interrupt(struct pt_regs *regs) * Besides, if we don't timer interrupts ignore the global * interrupt lock, which is the WrongThing (tm) to do. */ - exit_idle(); irq_enter(); + exit_idle(); local_apic_timer_interrupt(); irq_exit(); @@ -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 @@ -1809,8 +1864,8 @@ void smp_spurious_interrupt(struct pt_regs *regs) { u32 v; - exit_idle(); irq_enter(); + exit_idle(); /* * Check if this really is a spurious interrupt and ACK it * if it is a vectored one. Just in case... @@ -1846,8 +1901,8 @@ void smp_error_interrupt(struct pt_regs *regs) "Illegal register address", /* APIC Error Bit 7 */ }; - exit_idle(); irq_enter(); + exit_idle(); /* First tickle the hardware, only then report what went on. -- REW */ v0 = apic_read(APIC_ESR); apic_write(APIC_ESR, 0); diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index f7a41e4cae47..8c3cdded6f2b 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 000000000000..09d3d8c1cd99 --- /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 6d939d7847e2..fb072754bc1d 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2421,8 +2421,8 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void) unsigned vector, me; ack_APIC_irq(); - exit_idle(); irq_enter(); + exit_idle(); me = smp_processor_id(); for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { @@ -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/check.c b/arch/x86/kernel/check.c index 452932d34730..5da1269e8ddc 100644 --- a/arch/x86/kernel/check.c +++ b/arch/x86/kernel/check.c @@ -62,7 +62,8 @@ early_param("memory_corruption_check_size", set_corruption_check_size); void __init setup_bios_corruption_check(void) { - u64 addr = PAGE_SIZE; /* assume first page is reserved anyway */ + phys_addr_t start, end; + u64 i; if (memory_corruption_check == -1) { memory_corruption_check = @@ -82,28 +83,23 @@ void __init s |