diff options
Diffstat (limited to 'arch/x86/kernel')
59 files changed, 915 insertions, 1162 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 581386c7e429..84c00592d359 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -100,8 +100,6 @@ obj-$(CONFIG_HPET_TIMER) += hpet.o obj-$(CONFIG_APB_TIMER) += apb_timer.o obj-$(CONFIG_AMD_NB) += amd_nb.o -obj-$(CONFIG_DEBUG_RODATA_TEST) += test_rodata.o -obj-$(CONFIG_DEBUG_NX_TEST) += test_nx.o obj-$(CONFIG_DEBUG_NMI_SELFTEST) += nmi_selftest.o obj-$(CONFIG_KVM_GUEST) += kvm.o kvmclock.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 873552718270..a468f0fdc907 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -35,6 +35,7 @@ #include <linux/bootmem.h> #include <linux/ioport.h> #include <linux/pci.h> +#include <linux/efi-bgrt.h> #include <asm/e820/api.h> #include <asm/irqdomain.h> @@ -724,11 +725,12 @@ int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) return 0; } -int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, int *pcpu) +int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id, + int *pcpu) { int cpu; - cpu = acpi_register_lapic(physid, U32_MAX, ACPI_MADT_ENABLED); + cpu = acpi_register_lapic(physid, acpi_id, ACPI_MADT_ENABLED); if (cpu < 0) { pr_info(PREFIX "Unable to map lapic to logical cpu number\n"); return cpu; @@ -1558,6 +1560,12 @@ int __init early_acpi_boot_init(void) return 0; } +static int __init acpi_parse_bgrt(struct acpi_table_header *table) +{ + efi_bgrt_init(table); + return 0; +} + int __init acpi_boot_init(void) { /* those are executed after early-quirks are executed */ @@ -1582,6 +1590,8 @@ int __init acpi_boot_init(void) acpi_process_madt(); acpi_table_parse(ACPI_SIG_HPET, acpi_parse_hpet); + if (IS_ENABLED(CONFIG_ACPI_BGRT)) + acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt); if (!acpi_noirq) x86_init.pci.init = pci_acpi_init; diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index af15f4444330..8233a630280f 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -12,7 +12,6 @@ #include <linux/sched.h> #include <acpi/processor.h> -#include <asm/acpi.h> #include <asm/mwait.h> #include <asm/special_insns.h> @@ -89,7 +88,8 @@ static long acpi_processor_ffh_cstate_probe_cpu(void *_cx) retval = 0; /* If the HW does not support any sub-states in this C-state */ if (num_cstate_subtype == 0) { - pr_warn(FW_BUG "ACPI MWAIT C-state 0x%x not supported by HW (0x%x)\n", cx->address, edx_part); + pr_warn(FW_BUG "ACPI MWAIT C-state 0x%x not supported by HW (0x%x)\n", + cx->address, edx_part); retval = -1; goto out; } @@ -104,8 +104,8 @@ static long acpi_processor_ffh_cstate_probe_cpu(void *_cx) if (!mwait_supported[cstate_type]) { mwait_supported[cstate_type] = 1; printk(KERN_DEBUG - "Monitor-Mwait will be used to enter C-%d " - "state\n", cx->type); + "Monitor-Mwait will be used to enter C-%d state\n", + cx->type); } snprintf(cx->desc, ACPI_CX_DESC_LEN, "ACPI FFH INTEL MWAIT 0x%x", @@ -166,6 +166,7 @@ EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_enter); static int __init ffh_cstate_init(void) { struct cpuinfo_x86 *c = &boot_cpu_data; + if (c->x86_vendor != X86_VENDOR_INTEL) return -1; diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index 63ff468a7986..82dfe32faaf4 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -695,7 +695,7 @@ static __init int init_amd_gatt(struct agp_kern_info *info) return -1; } -static struct dma_map_ops gart_dma_ops = { +static const struct dma_map_ops gart_dma_ops = { .map_sg = gart_map_sg, .unmap_sg = gart_unmap_sg, .map_page = gart_map_page, diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 4cb43df5079f..4eca103a1e01 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -529,18 +529,19 @@ static void lapic_timer_broadcast(const struct cpumask *mask) * The local apic timer can be used for any function which is CPU local. */ static struct clock_event_device lapic_clockevent = { - .name = "lapic", - .features = CLOCK_EVT_FEAT_PERIODIC | - CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP - | CLOCK_EVT_FEAT_DUMMY, - .shift = 32, - .set_state_shutdown = lapic_timer_shutdown, - .set_state_periodic = lapic_timer_set_periodic, - .set_state_oneshot = lapic_timer_set_oneshot, - .set_next_event = lapic_next_event, - .broadcast = lapic_timer_broadcast, - .rating = 100, - .irq = -1, + .name = "lapic", + .features = CLOCK_EVT_FEAT_PERIODIC | + CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP + | CLOCK_EVT_FEAT_DUMMY, + .shift = 32, + .set_state_shutdown = lapic_timer_shutdown, + .set_state_periodic = lapic_timer_set_periodic, + .set_state_oneshot = lapic_timer_set_oneshot, + .set_state_oneshot_stopped = lapic_timer_shutdown, + .set_next_event = lapic_next_event, + .broadcast = lapic_timer_broadcast, + .rating = 100, + .irq = -1, }; static DEFINE_PER_CPU(struct clock_event_device, lapic_events); @@ -1245,7 +1246,7 @@ static void lapic_setup_esr(void) /** * setup_local_APIC - setup the local APIC * - * Used to setup local APIC while initializing BSP or bringin up APs. + * Used to setup local APIC while initializing BSP or bringing up APs. * Always called with preemption disabled. */ void setup_local_APIC(void) @@ -1864,14 +1865,14 @@ static void __smp_spurious_interrupt(u8 vector) "should never happen.\n", vector, smp_processor_id()); } -__visible void smp_spurious_interrupt(struct pt_regs *regs) +__visible void __irq_entry smp_spurious_interrupt(struct pt_regs *regs) { entering_irq(); __smp_spurious_interrupt(~regs->orig_ax); exiting_irq(); } -__visible void smp_trace_spurious_interrupt(struct pt_regs *regs) +__visible void __irq_entry smp_trace_spurious_interrupt(struct pt_regs *regs) { u8 vector = ~regs->orig_ax; @@ -1922,14 +1923,14 @@ static void __smp_error_interrupt(struct pt_regs *regs) } -__visible void smp_error_interrupt(struct pt_regs *regs) +__visible void __irq_entry smp_error_interrupt(struct pt_regs *regs) { entering_irq(); __smp_error_interrupt(regs); exiting_irq(); } -__visible void smp_trace_error_interrupt(struct pt_regs *regs) +__visible void __irq_entry smp_trace_error_interrupt(struct pt_regs *regs) { entering_irq(); trace_error_apic_entry(ERROR_APIC_VECTOR); @@ -2028,8 +2029,8 @@ void disconnect_bsp_APIC(int virt_wire_setup) /* * The number of allocated logical CPU IDs. Since logical CPU IDs are allocated * contiguously, it equals to current allocated max logical CPU ID plus 1. - * All allocated CPU ID should be in [0, nr_logical_cpuidi), so the maximum of - * nr_logical_cpuids is nr_cpu_ids. + * All allocated CPU IDs should be in the [0, nr_logical_cpuids) range, + * so the maximum of nr_logical_cpuids is nr_cpu_ids. * * NOTE: Reserve 0 for BSP. */ @@ -2094,7 +2095,7 @@ int __generic_processor_info(int apicid, int version, bool enabled) * Since fixing handling of boot_cpu_physical_apicid requires * another discussion and tests on each platform, we leave it * for now and here we use read_apic_id() directly in this - * function, generic_processor_info(). + * function, __generic_processor_info(). */ if (disabled_cpu_apicid != BAD_APICID && disabled_cpu_apicid != read_apic_id() && diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 1e35dd06b090..347bb9f65737 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1107,12 +1107,12 @@ int mp_map_gsi_to_irq(u32 gsi, unsigned int flags, struct irq_alloc_info *info) ioapic = mp_find_ioapic(gsi); if (ioapic < 0) - return -1; + return -ENODEV; pin = mp_find_ioapic_pin(ioapic, gsi); idx = find_irq_entry(ioapic, pin, mp_INT); if ((flags & IOAPIC_MAP_CHECK) && idx < 0) - return -1; + return -ENODEV; return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags, info); } @@ -2117,6 +2117,7 @@ static inline void __init check_timer(void) if (idx != -1 && irq_trigger(idx)) unmask_ioapic_irq(irq_get_chip_data(0)); } + irq_domain_deactivate_irq(irq_data); irq_domain_activate_irq(irq_data); if (timer_irq_works()) { if (disable_timer_pin_1 > 0) @@ -2138,6 +2139,7 @@ static inline void __init check_timer(void) * legacy devices should be connected to IO APIC #0 */ replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2); + irq_domain_deactivate_irq(irq_data); irq_domain_activate_irq(irq_data); legacy_pic->unmask(0); if (timer_irq_works()) { diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 015bbf30e3e3..c61aec7e65f4 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -82,7 +82,7 @@ int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) if (domain == NULL) return -ENOSYS; - return pci_msi_domain_alloc_irqs(domain, dev, nvec, type); + return msi_domain_alloc_irqs(domain, &dev->dev, nvec); } void native_teardown_msi_irq(unsigned int irq) diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 5d30c5e42bb1..f3557a1eb562 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -559,7 +559,7 @@ void send_cleanup_vector(struct irq_cfg *cfg) __send_cleanup_vector(data); } -asmlinkage __visible void smp_irq_move_cleanup_interrupt(void) +asmlinkage __visible void __irq_entry smp_irq_move_cleanup_interrupt(void) { unsigned vector, me; diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index c99d9333ebac..7f179f1c467c 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -42,40 +42,44 @@ DEFINE_PER_CPU(int, x2apic_extra_bits); -#define PR_DEVEL(fmt, args...) pr_devel("%s: " fmt, __func__, args) - -static enum uv_system_type uv_system_type; -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 enum uv_system_type uv_system_type; +static bool uv_hubless_system; +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; + +/* Information 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; + unsigned int gnode_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 */ +/* 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 */ + + /* Cause a machine fault: */ + return ~0ul; } EXPORT_SYMBOL(uv_undefined); @@ -86,18 +90,19 @@ static unsigned long __init uv_early_read_mmr(unsigned long addr) mmr = early_ioremap(UV_LOCAL_MMR_BASE | addr, sizeof(*mmr)); val = *mmr; early_iounmap(mmr, sizeof(*mmr)); + return val; } static inline bool is_GRU_range(u64 start, u64 end) { if (gru_dist_base) { - u64 su = start & gru_dist_umask; /* upper (incl pnode) bits */ - u64 sl = start & gru_dist_lmask; /* base offset bits */ + u64 su = start & gru_dist_umask; /* Upper (incl pnode) bits */ + u64 sl = start & gru_dist_lmask; /* Base offset bits */ u64 eu = end & gru_dist_umask; u64 el = end & gru_dist_lmask; - /* Must reside completely within a single GRU range */ + /* Must reside completely within a single GRU range: */ return (sl == gru_dist_base && el == gru_dist_base && su >= gru_first_node_paddr && su <= gru_last_node_paddr && @@ -134,13 +139,14 @@ static int __init early_get_pnodeid(void) break; case UV4_HUB_PART_NUMBER: uv_min_hub_revision_id += UV4_HUB_REVISION_BASE - 1; + uv_cpuid.gnode_shift = 2; /* min partition is 4 sockets */ break; } uv_hub_info->hub_revision = uv_min_hub_revision_id; 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 */ + 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, @@ -148,11 +154,12 @@ static int __init early_get_pnodeid(void) return pnode; } -/* [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 +/* [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) @@ -166,11 +173,13 @@ static void set_x2apic_bits(void) 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 { @@ -181,8 +190,9 @@ static void set_x2apic_bits(void) } sub_index++; } while (LEAFB_SUBTYPE(ecx) != INVALID_TYPE); - uv_cpuid.apicid_shift = 0; - uv_cpuid.apicid_mask = (~(-1 << sid_shift)); + + uv_cpuid.apicid_shift = 0; + uv_cpuid.apicid_mask = (~(-1 << sid_shift)); uv_cpuid.socketid_shift = sid_shift; } @@ -193,10 +203,8 @@ static void __init early_get_apic_socketid_shift(void) 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); + 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); } /* @@ -209,10 +217,8 @@ static void __init uv_set_apicid_hibit(void) union uv1h_lb_target_physical_apic_id_mask_u apicid_mask; if (is_uv1_hub()) { - apicid_mask.v = - uv_early_read_mmr(UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK); - uv_apicid_hibits = - apicid_mask.s1.bit_enables & UV_APICID_HIBIT_MASK; + apicid_mask.v = uv_early_read_mmr(UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK); + uv_apicid_hibits = apicid_mask.s1.bit_enables & UV_APICID_HIBIT_MASK; } } @@ -221,20 +227,26 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) int pnodeid; int uv_apic; - if (strncmp(oem_id, "SGI", 3) != 0) + if (strncmp(oem_id, "SGI", 3) != 0) { + if (strncmp(oem_id, "NSGI", 4) == 0) { + uv_hubless_system = true; + pr_info("UV: OEM IDs %s/%s, HUBLESS\n", + oem_id, oem_table_id); + } return 0; + } if (numa_off) { pr_err("UV: NUMA is off, disabling UV support\n"); return 0; } - /* Setup early hub type field in uv_hub_info for Node 0 */ + /* Set up 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 + * 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) @@ -250,31 +262,32 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) pnodeid = early_get_pnodeid(); early_get_apic_socketid_shift(); - x86_platform.is_untracked_pat_range = uv_is_untracked_pat_range; + + x86_platform.is_untracked_pat_range = uv_is_untracked_pat_range; x86_platform.nmi_init = uv_nmi_init; - if (!strcmp(oem_table_id, "UVX")) { /* most common */ + if (!strcmp(oem_table_id, "UVX")) { + /* This is the most common hardware variant: */ uv_system_type = UV_X2APIC; uv_apic = 0; - } else if (!strcmp(oem_table_id, "UVH")) { /* only UV1 systems */ + } else if (!strcmp(oem_table_id, "UVH")) { + /* Only UV1 systems: */ uv_system_type = UV_NON_UNIQUE_APIC; - __this_cpu_write(x2apic_extra_bits, - pnodeid << uvh_apicid.s.pnode_shift); + __this_cpu_write(x2apic_extra_bits, pnodeid << uvh_apicid.s.pnode_shift); uv_set_apicid_hibit(); uv_apic = 1; - } else if (!strcmp(oem_table_id, "UVL")) { /* only used for */ - uv_system_type = UV_LEGACY_APIC; /* very small systems */ + } else if (!strcmp(oem_table_id, "UVL")) { + /* Only used for very small systems: */ + uv_system_type = UV_LEGACY_APIC; uv_apic = 0; } else { goto badbios; } - pr_info("UV: OEM IDs %s/%s, System/HUB Types %d/%d, uv_apic %d\n", - oem_id, oem_table_id, uv_system_type, - uv_min_hub_revision_id, uv_apic); + pr_info("UV: OEM IDs %s/%s, System/HUB Types %d/%d, uv_apic %d\n", oem_id, oem_table_id, uv_system_type, uv_min_hub_revision_id, uv_apic); return uv_apic; @@ -295,6 +308,12 @@ int is_uv_system(void) } EXPORT_SYMBOL_GPL(is_uv_system); +int is_uv_hubless(void) +{ + return uv_hubless_system; +} +EXPORT_SYMBOL_GPL(is_uv_hubless); + void **__uv_hub_info_list; EXPORT_SYMBOL_GPL(__uv_hub_info_list); @@ -307,16 +326,18 @@ 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; +/* 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) @@ -325,7 +346,7 @@ extern int uv_hub_info_version(void) } EXPORT_SYMBOL(uv_hub_info_version); -/* Build GAM range lookup table */ +/* Build GAM range lookup table: */ static __init void build_uv_gr_table(void) { struct uv_gam_range_entry *gre = uv_gre_table; @@ -343,25 +364,24 @@ static __init void build_uv_gr_table(void) 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 */ + 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)); + 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)); + 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 */ + if (lsid < sid) { + /* New range: */ grt = &_gr_table[indx]; grt->base = lindx; grt->nasid = gre->nasid; @@ -370,27 +390,32 @@ static __init void build_uv_gr_table(void) lindx = indx++; continue; } - if (lsid == sid && !ram_limit) { /* update range */ - if (grt->limit == last_limit) { /* .. if contiguous */ + /* Update range: */ + if (lsid == sid && !ram_limit) { + /* .. if contiguous: */ + if (grt->limit == last_limit) { grt->limit = last_limit = gre->limit; continue; } } - if (!ram_limit) { /* non-contiguous ram range */ + /* Non-contiguous RAM range: */ + if (!ram_limit) { grt++; grt->base = lindx; 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 */ + /* Non-contiguous/non-RAM: */ + grt++; + /* base is this entry */ + grt->base = grt - _gr_table; grt->nasid = gre->nasid; grt->limit = last_limit = gre->limit; lsid++; } - /* shorten table if possible */ + /* Shorten table if possible */ grt++; i = grt - _gr_table; if (i < _gr_table_len) { @@ -404,16 +429,15 @@ static __init void build_uv_gr_table(void) } } - /* display resultant gam range table */ + /* Display resultant GAM range table: */ for (i = 0, grt = _gr_table; i < _gr_table_len; i++, grt++) { + unsigned long start, end; 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); + start = gb < 0 ? 0 : (unsigned long)_gr_table[gb].limit << UV_GAM_RANGE_SHFT; + 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); } } @@ -424,16 +448,19 @@ static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip) pnode = uv_apicid_to_pnode(phys_apicid); phys_apicid |= uv_apicid_hibits; + val = (1UL << UVH_IPI_INT_SEND_SHFT) | (phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) | ((start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) | APIC_DM_INIT; + uv_write_global_mmr64(pnode, UVH_IPI_INT, val); val = (1UL << UVH_IPI_INT_SEND_SHFT) | (phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) | ((start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) | APIC_DM_STARTUP; + uv_write_global_mmr64(pnode, UVH_IPI_INT, val); return 0; @@ -567,7 +594,7 @@ static struct apic apic_x2apic_uv_x __ro_after_init = { .apic_id_registered = uv_apic_id_registered, .irq_delivery_mode = dest_Fixed, - .irq_dest_mode = 0, /* physical */ + .irq_dest_mode = 0, /* Physical */ .target_cpus = online_target_cpus, .disable_esr = 0, @@ -628,23 +655,22 @@ static __init void get_lowmem_redirect(unsigned long *base, unsigned long *size) switch (i) { case 0: m_redirect = UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR; - m_overlay = UVH_RH_GAM_ALIAS210_OVERLAY_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; + 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; + 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(m_redirect); - *base = (unsigned long)redirect.s.dest_base - << DEST_SHIFT; + *base = (unsigned long)redirect.s.dest_base << DEST_SHIFT; return; } } @@ -653,8 +679,7 @@ static __init void get_lowmem_redirect(unsigned long *base, unsigned long *size) enum map_type {map_wb, map_uc}; -static __init void map_high(char *id, unsigned long base, int pshift, - int bshift, int max_pnode, enum map_type map_type) +static __init void map_high(char *id, unsigned long base, int pshift, int bshift, int max_pnode, enum map_type map_type) { unsigned long bytes, paddr; @@ -679,16 +704,19 @@ static __init void map_gru_distributed(unsigned long c) int nid; gru.v = c; - /* only base bits 42:28 relevant in dist mode */ + + /* Only base bits 42:28 relevant in dist mode */ gru_dist_base = gru.v & 0x000007fff0000000UL; if (!gru_dist_base) { pr_info("UV: Map GRU_DIST base address NULL\n"); return; } + bytes = 1UL << UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT; gru_dist_lmask = ((1UL << uv_hub_info->m_val) - 1) & ~(bytes - 1); gru_dist_umask = ~((1UL << uv_hub_info->m_val) - 1); gru_dist_base &= gru_dist_lmask; /* Clear bits above M */ + for_each_online_node(nid) { paddr = ((u64)uv_node_to_pnode(nid) << uv_hub_info->m_val) | gru_dist_base; @@ -696,11 +724,12 @@ static __init void map_gru_distributed(unsigned long c) gru_first_node_paddr = min(paddr, gru_first_node_paddr); gru_last_node_paddr = max(paddr, gru_last_node_paddr); } + /* Save upper (63:M) bits of address only for is_GRU_range */ gru_first_node_paddr &= gru_dist_umask; gru_last_node_paddr &= gru_dist_umask; - pr_debug("UV: Map GRU_DIST base 0x%016llx 0x%016llx - 0x%016llx\n", - gru_dist_base, gru_first_node_paddr, gru_last_node_paddr); + + pr_debug("UV: Map GRU_DIST base 0x%016llx 0x%016llx - 0x%016llx\n", gru_dist_base, gru_first_node_paddr, gru_last_node_paddr); } static __init void map_gru_high(int max_pnode) @@ -720,6 +749,7 @@ static __init void map_gru_high(int max_pnode) map_gru_distributed(gru.v); return; } + base = (gru.v & mask) >> shift; map_high("GRU", base, shift, shift, max_pnode, map_wb); gru_start_paddr = ((u64)base << shift); @@ -773,8 +803,8 @@ static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode) id = mmiohs[index].id; overlay.v = uv_read_local_mmr(mmiohs[index].overlay); - pr_info("UV: %s overlay 0x%lx base:0x%x m_io:%d\n", - id, overlay.v, overlay.s3.base, overlay.s3.m_io); + + pr_info("UV: %s overlay 0x%lx base:0x%x m_io:%d\n", id, overlay.v, overlay.s3.base, overlay.s3.m_io); if (!overlay.s3.enable) { pr_info("UV: %s disabled\n", id); return; @@ -785,7 +815,8 @@ static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode) m_io = overlay.s3.m_io; mmr = mmiohs[index].redirect; n = UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH; - min_pnode *= 2; /* convert to NASID */ + /* Convert to NASID: */ + min_pnode *= 2; max_pnode *= 2; max_io = lnasid = fi = li = -1; @@ -794,16 +825,18 @@ static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode) redirect.v = uv_read_local_mmr(mmr + i * 8); nasid = redirect.s3.nasid; + /* Invalid NASID: */ if (nasid < min_pnode || max_pnode < nasid) - nasid = -1; /* invalid NASID */ + nasid = -1; if (nasid == lnasid) { li = i; - if (i != n-1) /* last entry check */ + /* Last entry check: */ + if (i != n-1) continue; } - /* check if we have a cached (or last) redirect to print */ + /* Check if we have a cached (or last) redirect to print: */ if (lnasid != -1 || (i == n-1 && nasid != -1)) { unsigned long addr1, addr2; int f, l; @@ -815,12 +848,9 @@ static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode) f = fi; l = li; } - addr1 = (base << shift) + - f * (1ULL << m_io); - addr2 = (base << shift) + - (l + 1) * (1ULL << m_io); - pr_info("UV: %s[%03d..%03d] NASID 0x%04x ADDR 0x%016lx - 0x%016lx\n", - id, fi, li, lnasid, addr1, addr2); + addr1 = (base << shift) + f * (1ULL << m_io); + addr2 = (base << shift) + (l + 1) * (1ULL << m_io); + pr_info("UV: %s[%03d..%03d] NASID 0x%04x ADDR 0x%016lx - 0x%016lx\n", id, fi, li, lnasid, addr1, addr2); if (max_io < l) max_io = l; } @@ -828,8 +858,7 @@ static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode) lnasid = nasid; } - pr_info("UV: %s base:0x%lx shift:%d M_IO:%d MAX_IO:%d\n", - id, base, shift, m_io, max_io); + pr_info("UV: %s base:0x%lx shift:%d M_IO:%d MAX_IO:%d\n", id, base, shift, m_io, max_io); if (max_io >= 0) map_high(id, base, shift, m_io, max_io, map_uc); @@ -842,36 +871,35 @@ static __init void map_mmioh_high(int min_pnode, int max_pnode) int shift, enable, m_io, n_io; if (is_uv3_hub() || is_uv4_hub()) { - /* Map both MMIOH Regions */ + /* Map both MMIOH regions: */ map_mmioh_high_uv3(0, min_pnode, max_pnode); map_mmioh_high_uv3(1, min_pnode, max_pnode); return; } if (is_uv1_hub()) { - mmr = UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR; - shift = UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT; - mmioh.v = uv_read_local_mmr(mmr); - enable = !!mmioh.s1.enable; - base = mmioh.s1.base; - m_io = mmioh.s1.m_io; - n_io = mmioh.s1.n_io; + mmr = UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR; + shift = UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT; + mmioh.v = uv_read_local_mmr(mmr); + enable = !!mmioh.s1.enable; + base = mmioh.s1.base; + m_io = mmioh.s1.m_io; + n_io = mmioh.s1.n_io; } else if (is_uv2_hub()) { - mmr = UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR; - shift = UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT; - mmioh.v = uv_read_local_mmr(mmr); - enable = !!mmioh.s2.enable; - base = mmioh.s2.base; - m_io = mmioh.s2.m_io; - n_io = mmioh.s2.n_io; - } else + mmr = UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR; + shift = UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT; + mmioh.v = uv_read_local_mmr(mmr); + enable = !!mmioh.s2.enable; + base = mmioh.s2.base; + m_io = mmioh.s2.m_io; + n_io = mmioh.s2.n_io; + } else { return; + } if (enable) { max_pnode &= (1 << n_io) - 1; - pr_info( - "UV: base:0x%lx shift:%d N_IO:%d M_IO:%d max_pnode:0x%x\n", - base, shift, m_io, n_io, max_pnode); + pr_info("UV: base:0x%lx shift:%d N_IO:%d M_IO:%d max_pnode:0x%x\n", base, shift, m_io, n_io, max_pnode); map_high("MMIOH", base, shift, m_io, max_pnode, map_uc); } else { pr_info("UV: MMIOH disabled\n"); @@ -889,16 +917,16 @@ static __init void uv_rtc_init(void) long status; u64 ticks_per_sec; - status = uv_bios_freq_base(BIOS_FREQ_BASE_REALTIME_CLOCK, - &ticks_per_sec); + status = uv_bios_freq_base(BIOS_FREQ_BASE_REALTIME_CLOCK, &ticks_per_sec); + if (status != BIOS_STATUS_SUCCESS || ticks_per_sec < 100000) { - printk(KERN_WARNING - "unable to determine platform RTC clock frequency, " - "guessing.\n"); - /* BIOS gives wrong value for clock freq. so guess */ + pr_warn("UV: unable to determine platform RTC clock frequency, guessing.\n"); + + /* BIOS gives wrong value for clock frequency, so guess: */ sn_rtc_cycles_per_second = 1000000000000UL / 30000UL; - } else + } else { sn_rtc_cycles_per_second = ticks_per_sec; + } } /* @@ -909,19 +937,19 @@ static void uv_heartbeat(unsigned long ignored) struct timer_list *timer = &uv_scir_info->timer; unsigned char bits = uv_scir_info->state; - /* flip heartbeat bit */ + /* Flip heartbeat bit: */ bits ^= SCIR_CPU_HEARTBEAT; - /* is this cpu idle? */ + /* Is this CPU idle? */ if (idle_cpu(raw_smp_processor_id())) bits &= ~SCIR_CPU_ACTIVITY; else bits |= SCIR_CPU_ACTIVITY; - /* update system controller interface reg */ + /* Update system controller interface reg: */ uv_set_scir_bits(bits); - /* enable next timer period */ + /* Enable next timer period: */ mod_timer(timer, jiffies + SCIR_CPU_HB_INTERVAL); } @@ -936,7 +964,7 @@ static int uv_heartbeat_enable(unsigned int cpu) add_timer_on(timer, cpu); uv_cpu_scir_info(cpu)->enabled = 1; - /* also ensure that boot cpu is enabled */ + /* Also ensure that boot CPU is enabled: */ cpu = 0; } return 0; @@ -969,9 +997,11 @@ static __init int uv_init_heartbeat(void) { int cpu; - if (is_uv_system()) + if (is_uv_system()) { for_each_online_cpu(cpu) uv_heartbeat_enable(cpu); + } + return 0; } @@ -980,14 +1010,10 @@ late_initcall(uv_init_heartbeat); #endif /* !CONFIG_HOTPLUG_CPU */ /* Direct Legacy VGA I/O traffic to designated IOH */ -int uv_set_vga_state(struct pci_dev *pdev, bool decode, - unsigned int command_bits, u32 flags) +int uv_set_vga_state(struct pci_dev *pdev, bool decode, unsigned int command_bits, u32 flags) { int domain, bus, rc; - PR_DEVEL("devfn %x decode %d cmd %x flags %d\n", - pdev->devfn, decode, command_bits, flags); - if (!(flags & PCI_VGA_STATE_CHANGE_BRIDGE)) return 0; @@ -998,13 +1024,12 @@ int uv_set_vga_state(struct pci_dev *pdev, bool decode, bus = pdev->bus->number; rc = uv_bios_set_legacy_vga_target(decode, domain, bus); - PR_DEVEL("vga decode %d %x:%x, rc: %d\n", decode, domain, bus, rc); return rc; } /* - * Called on each cpu to initialize the per_cpu UV data area. + * Called on each CPU to initialize the per_cpu UV data area. * FIXME: hotplug not supported yet */ void uv_cpu_init(void) @@ -1031,90 +1056,79 @@ static void get_mn(struct mn *mnp) union uvh_rh_gam_config_mmr_u m_n_config; union uv3h_gr0_gam_gr_config_u m_gr_config; - m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR); - mnp->n_val = m_n_config.s.n_skt; + /* Make sure the whole structure is well initialized: */ + memset(mnp, 0, sizeof(*mnp)); + + 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; + 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; + 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; + 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; + mnp->m_val = m_n_config.s1.m_skt; + mnp->n_lshift = mnp->m_val; } mnp->m_shift = mnp->m_val ? 64 - mnp->m_val : 0; } -void __init uv_init_hub_info(struct uv_hub_info_s *hub_info) +void __init uv_init_hub_info(struct uv_hub_info_s *hi) { - struct mn mn = {0}; /* avoid unitialized warnings */ union uvh_node_id_u node_id; + struct mn mn; 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 ? + hi->gpa_mask = mn.m_val ? (1UL << (mn.m_val + mn.n_val)) - 1 : (1UL << uv_cpuid.gpa_shift) - 1; - 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); + hi->m_val = mn.m_val; + hi->n_val = mn.n_val; + hi->m_shift = mn.m_shift; + hi->n_lshift = mn.n_lshift ? mn.n_lshift : 0; + hi->hub_revision = uv_hub_info->hub_revision; + hi->pnode_mask = uv_cpuid.pnode_mask; + hi->min_pnode = _min_pnode; + hi->min_socket = _min_socket; + hi->pnode_to_socket = _pnode_to_socket; + hi->socket_to_node = _socket_to_node; + hi->socket_to_pnode = _socket_to_pnode; + hi->gr_table_len = _gr_table_len; + hi->gr_table = _gr_table; + + node_id.v = uv_read_local_mmr(UVH_NODE_ID); + uv_cpuid.gnode_shift = max_t(unsigned int, uv_cpuid.gnode_shift, mn.n_val); + hi->gnode_extra = (node_id.s.node_id & ~((1 << uv_cpuid.gnode_shift) - 1)) >> 1; + hi->gnode_upper = (unsigned long)hi->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; + hi->global_mmr_base = uv_gp_table->mmr_base; + hi->global_mmr_shift = uv_gp_table->mmr_shift; + hi->global_gru_base = uv_gp_table->gru_base; + hi->global_gru_shift = uv_gp_table->gru_shift; + hi->gpa_shift = uv_gp_table->gpa_shift; + hi->gpa_mask = (1UL << hi->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; + hi->global_mmr_base = uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) & ~UV_MMR_ENABLE; + hi->global_mmr_shift = _UV_GLOBAL_MMR64_PNODE_SHIFT; } - get_lowmem_redirect( - &hub_info->lowmem_remap_base, &hub_info->lowmem_remap_top); - - hub_info->apic_pnode_shift = uv_cpuid.socketid_shift; - - /* 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); - - 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); + get_lowmem_redirect(&hi->lowmem_remap_base, &hi->lowmem_remap_top); - 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); + hi->apic_pnode_shift = uv_cpuid.socketid_shift; - pr_info("UV: gnode_upper:0x%lx gnode_extra:0x%x\n", - hub_info->gnode_upper, hub_info->gnode_extra); + /* Show system specific info: */ + pr_info("UV: N:%d M:%d m_shift:%d n_lshift:%d\n", hi->n_val, hi->m_val, hi->m_shift, hi->n_lshift); + pr_info("UV: gpa_mask/shift:0x%lx/%d pnode_mask:0x%x apic_pns:%d\n", hi->gpa_mask, hi->gpa_shift, hi->pnode_mask, hi->apic_pnode_shift); + pr_info("UV: mmr_base/shift:0x%lx/%ld gru_base/shift:0x%lx/%ld\n", hi->global_mmr_base, hi->global_mmr_shift, hi->global_gru_base, hi->global_gru_shift); + pr_info("UV: gnode_upper:0x%lx gnode_extra:0x%x\n", hi->gnode_upper, hi->gnode_extra); } static void __init decode_gam_params(unsigned long ptr) @@ -1140,12 +1154,9 @@ static void __init decode_gam_rng_tbl(unsigned long ptr) 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\n", - "Range", "", "Size", "Type", "NASID", - "SID", "PN"); + pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", "SID", "PN"); } - pr_info( - "UV: %2d: 0x%014lx-0x%014lx %5luG %3d %04x %02x %02x\n", + pr_info("UV: %2d: 0x%014lx-0x%014lx %5luG %3d %04x %02x %02x\n", index++, (unsigned long)lgre << UV_GAM_RANGE_SHFT, (unsigned long)gre->limit << UV_GAM_RANGE_SHFT, @@ -1163,29 +1174,32 @@ static void __init decode_gam_rng_tbl(unsigned long ptr) 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); + _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) +static int __init decode_uv_systab(void) { struct uv_systab *st; int i; + if (uv_hub_info->hub_revision < UV4_HUB_REVISION_BASE) + return 0; /* No extended UVsystab required */ + 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(); + if ((!st) || (st->revision < UV_SYSTAB_VERSION_UV4_LATEST)) { + int rev = st ? st->revision : 0; + + pr_err("UV: BIOS UVsystab version(%x) mismatch, expecting(%x)\n", rev, UV_SYSTAB_VERSION_UV4_LATEST); + pr_err("UV: Cannot support UV operations, switching to generic PC\n"); + uv_system_type = UV_NONE; + + return -EINVAL; } for (i = 0; st->entry[i].type != UV_SYSTAB_TYPE_UNUSED; i++) { @@ -1206,10 +1220,11 @@ static void __init decode_uv_systab(void) break; } } + return 0; } /* - * Setup physical blade translations from UVH_NODE_PRESENT_TABLE + * Set up physical blade translations from UVH_NODE_PRESENT_TABLE * .. NB: UVH_NODE_PRESENT_TABLE is going away, * .. being replaced by GAM Range Table */ @@ -1245,14 +1260,13 @@ static void __init build_socket_tables(void) if (!gre) { if (is_uv1_hub() || is_uv2_hub() || is_uv3_hub()) { pr_info("UV: No UVsystab socket table, ignoring\n"); - return; /* not required */ + return; } - pr_crit( - "UV: Error: UVsystab address translations not available!\n"); + pr_crit("UV: Error: UVsystab address translations not available!\n"); BUG(); } - /* build socket id -> node id, pnode */ + /* Build socket id -> node id, pnode */ num = maxsock - minsock + 1; bytes = num * sizeof(_socket_to_node[0]); _socket_to_node = kmalloc(bytes, GFP_KERNEL); @@ -1269,27 +1283,27 @@ static void __init build_socket_tables(void) for (i = 0; i < nump; i++) _pnode_to_socket[i] = SOCK_EMPTY; - /* fill in pnode/node/addr conversion list values */ + /* Fill in pnode/node/addr conversion list values: */ pr_info("UV: GAM Building socket/pnode conversion tables\n"); for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) { if (gre->type == UV_GAM_RANGE_TYPE_HOLE) continue; i = gre->sockid - minsock; + /* Duplicate: */ if (_socket_to_pnode[i] != SOCK_EMPTY) - continue; /* duplicate */ + continue; _socket_to_pnode[i] = gre->pnode; i = gre->pnode - minpnode; _pnode_to_socket[i] = gre->sockid; - pr_info( - "UV: sid:%02x type:%d nasid:%04x pn:%02x pn2s:%2x\n", + pr_info("UV: sid:%02x type:%d nasid:%04x pn:%02x pn2s:%2x\n", gre->sockid, gre->type, gre->nasid, _socket_to_pnode[gre->sockid - minsock], _pnode_to_socket[gre->pnode - minpnode]); } - /* Set socket -> node values */ + /* Set socket -> node values: */ lnid = -1; for_each_present_cpu(cpu) { int nid = cpu_to_node(cpu); @@ -1305,7 +1319,7 @@ static void __init build_socket_tables(void) sockid, apicid, nid); } - /* Setup physical blade to pnode translation from GAM Range Table */ + /* Set up 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); @@ -1315,8 +1329,7 @@ static void __init build_socket_tables(void) for (sockid = minsock; sockid <= maxsock; sockid++) { if (lnid == _socket_to_node[sockid - minsock]) { - _node_to_pnode[lnid] = - _socket_to_pnode[sockid - minsock]; + _node_to_pnode[lnid] = _socket_to_pnode[sockid - minsock]; break; } } @@ -1333,8 +1346,7 @@ static void __init build_socket_tables(void) 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]) + if (_socket_to_node[i] == SOCK_EMPTY || i != _socket_to_node[i]) break; if (i >= num) { kfree(_socket_to_node); @@ -1355,7 +1367,7 @@ static void __init build_socket_tables(void) } } -void __init uv_system_init(void) +static void __init uv_system_init_hub(void) { struct uv_hub_info_s hub_info = {0}; int bytes, cpu, nodeid; @@ -1373,8 +1385,13 @@ void __init uv_system_init(void) map_low_mmrs(); - uv_bios_init(); /* get uv_systab for decoding */ - decode_uv_systab(); + /* Get uv_systab for decoding: */ + uv_bios_init(); + + /* If there's an UVsystab problem then abort UV init: */ + if (decode_uv_systab() < 0) + return; + build_socket_tables(); build_uv_gr_table(); uv_init_hub_info(&hub_info); @@ -1382,14 +1399,10 @@ void __init uv_system_init(void) 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_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_get_sn_info(0, &uv_type, &sn_partition_id, &sn_coherency_id, - &sn_region_size, &system_serial_number); + 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(); @@ -1402,33 +1415,31 @@ void __init uv_system_init(void) struct uv_hub_info_s *new_hub; if (__uv_hub_info_list[nodeid]) { - pr_err("UV: Node %d UV HUB already initialized!?\n", - nodeid); + pr_err("UV: Node %d UV HUB already initialized!?\n", nodeid); BUG(); } /* Allocate new per hub info list */ - new_hub = (nodeid == 0) ? - &uv_hub_info_node0 : - kzalloc_node(bytes, GFP_KERNEL, nodeid); + 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 */ + /* Use information from GAM table if available: */ if (_node_to_pnode) new_hub->pnode = _node_to_pnode[nodeid]; - else /* Fill in during cpu loop */ + else /* Or 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 */ + /* Initialize per CPU info: */ for_each_possible_cpu(cpu) { int apicid = per_cpu(x86_cpu_to_apicid, cpu); int numa_node_id; @@ -1439,22 +1450,24 @@ void __init uv_system_init(void) pnode = uv_apicid_to_pnode(apicid); 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++; + 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 */ + + /* Init memoryless node: */ + if (nodeid != numa_node_id && 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_scir_info(cpu)->offset = uv_scir_offset(apicid); } for_each_node(nodeid) { unsigned short pnode = uv_hub_info_list(nodeid)->pnode; - /* Add pnode info for pre-GAM list nodes without cpus */ + /* Add pnode info for pre-GAM list nodes without CPUs: */ if (pnode == 0xffff) { unsigned long paddr; @@ -1480,15 +1493,30 @@ void __init uv_system_init(void) uv_scir_register_cpu_notifier(); proc_mkdir("sgi_uv", NULL); - /* register Legacy VGA I/O redirection handler */ + /* Register Legacy VGA I/O redirection handler: */ pci_register_set_vga_state(uv_set_vga_state); /* * For a kdump kernel the reset must be BOOT_ACPI, not BOOT_EFI, as - * EFI is not enabled in the kdump kernel. + * EFI is not enabled in the kdump kernel: */ if (is_kdump_kernel()) reboot_type = BOOT_ACPI; } +/* + * There is a small amount of UV specific code needed to initialize a + * UV system that does not have a "UV HUB" (referred to as "hubless"). + */ +void __init uv_system_init(void) +{ + if (likely(!is_uv_system() && !is_uv_hubless())) + return; + + if (is_uv_system()) + uv_system_init_hub(); + else + uv_nmi_setup_hubless(); +} + apic_driver(apic_x2apic_uv_x); diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 45d44c173cf9..4a7080c84a5a 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -905,8 +905,8 @@ static int apm_cpu_idle(struct cpuidle_device *dev, { static int use_apm_idle; /* = 0 */ static unsigned int last_jiffies; /* = 0 */ - static unsigned int last_stime; /* = 0 */ - cputime_t stime, utime; + static u64 last_stime; /* = 0 */ + u64 stime, utime; int apm_idle_done = 0; unsigned int jiffies_since_last_check = jiffies - last_jiffies; @@ -919,7 +919,7 @@ recalc: } else if (jiffies_since_last_check > idle_period) { unsigned int idle_percentage; - idle_percentage = cputime_to_jiffies(stime - last_stime); + idle_percentage = nsecs_to_jiffies(stime - last_stime); idle_percentage *= 100; idle_percentage /= jiffies_since_last_check; use_apm_idle = (idle_percentage > idle_threshold); diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index c62e015b126c..de827d6ac8c2 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -81,6 +81,7 @@ void common(void) { BLANK(); OFFSET(BP_scratch, boot_params, scratch); + OFFSET(BP_secure_boot, boot_params, secure_boot); OFFSET(BP_loadflags, boot_params, hdr.loadflags); OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch); OFFSET(BP_version, boot_params, hdr.version); diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 210927ee2e74..99332f550c48 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -13,6 +13,10 @@ static char syscalls_ia32[] = { #include <asm/syscalls_32.h> }; +#if defined(CONFIG_KVM_GUEST) && defined(CONFIG_PARAVIRT_SPINLOCKS) +#include <asm/kvm_para.h> +#endif + int main(void) { #ifdef CONFIG_PARAVIRT @@ -22,6 +26,11 @@ int main(void) BLANK(); #endif +#if defined(CONFIG_KVM_GUEST) && defined(CONFIG_PARAVIRT_SPINLOCKS) + OFFSET(KVM_STEAL_TIME_preempted, kvm_steal_time, preempted); + BLANK(); +#endif + #define ENTRY(entry) OFFSET(pt_regs_ ## entry, pt_regs, entry) ENTRY(bx); ENTRY(cx); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 1d3167269a67..4e95b2e0d95f 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -309,8 +309,22 @@ static void amd_get_topology(struct cpuinfo_x86 *c) /* get information required for multi-node processors */ if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { + u32 eax, ebx, ecx, edx; - node_id = cpuid_ecx(0x8000001e) & 7; + cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); + + node_id = ecx & 0xff; + smp_num_siblings = ((ebx >> 8) & 0xff) + 1; + + if (c->x86 == 0x15) + c->cu_id = ebx & 0xff; + + if (c->x86 >= 0x17) { + c->cpu_core_id = ebx & 0xff; + + if (smp_num_siblings > 1) + c->x86_max_cores /= smp_num_siblings; + } /* * We may have multiple LLCs if L3 caches exist, so check if we @@ -541,8 +555,10 @@ static void early_init_amd(struct cpuinfo_x86 *c) if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); - if (!check_tsc_unstable()) - set_sched_clock_stable(); + if (check_tsc_unstable()) + clear_sched_clock_stable(); + } else { + clear_sched_clock_stable(); } /* Bit 12 of 8000_0007 edx is accumulated power mechanism. */ diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 48d4ff2d9798..0e150d6dc64c 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -1,5 +1,5 @@ -#include <linux/bitops.h> -#include <linux/kernel.h> + +#include <linux/sched.h> #include <asm/cpufeature.h> #include <asm/e820/api.h> @@ -104,6 +104,8 @@ static void early_init_centaur(struct cpuinfo_x86 *c) #ifdef CONFIG_X86_64 set_cpu_cap(c, X86_FEATURE_SYSENTER32); #endif + + clear_sched_clock_stable(); } static void init_centaur(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 9bab7a8a4293..c64ca5929cb5 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -35,6 +35,7 @@ #include <asm/desc.h> #include <asm/fpu/internal.h> #include <asm/mtrr.h> +#include <asm/hwcap2.h> #include <linux/numa.h> #include <asm/asm.h> #include <asm/bugs.h> @@ -51,6 +52,8 @@ #include "cpu.h" +u32 elf_hwcap2 __read_mostly; + /* all of these masks are initialized in setup_cpu_local_masks() */ cpumask_var_t cpu_initialized_mask; cpumask_var_t cpu_callout_mask; @@ -83,6 +86,7 @@ static void default_init(struct cpuinfo_x86 *c) strcpy(c->x86_model_id, "386"); } #endif + clear_sched_clock_stable(); } static const struct cpu_dev default_cpu = { @@ -655,6 +659,16 @@ void cpu_detect(struct cpuinfo_x86 *c) } } +static void apply_forced_caps(struct cpuinfo_x86 *c) +{ + int i; + + for (i = 0; i < NCAPINTS; i++) { + c->x86_capability[i] &= ~cpu_caps_cleared[i]; + c->x86_capability[i] |= cpu_caps_set[i]; + } +} + void get_cpu_cap(struct cpuinfo_x86 *c) { u32 eax, ebx, ecx, edx; @@ -748,6 +762,13 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a); init_scattered_cpuid_features(c); + + /* + * Clear/Set all flags overridden by options, after probe. + * This needs to happen each time we re-probe, which may happen + * several times during CPU initialization. + */ + apply_forced_caps(c); } static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) @@ -801,14 +822,12 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) memset(&c->x86_capability, 0, sizeof c->x86_capability); c->extended_cpuid_level = 0; - if (!have_cpuid_p()) - identify_cpu_without_cpuid(c); - /* cyrix could have cpuid enabled via c_identify()*/ if (have_cpuid_p()) { cpu_detect(c); get_cpu_vendor(c); get_cpu_cap(c); + setup_force_cpu_cap(X86_FEATURE_CPUID); if (this_cpu->c_early_init) this_cpu->c_early_init(c); @@ -818,6 +837,9 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) if (this_cpu->c_bsp_init) this_cpu->c_bsp_init(c); + } else { + identify_cpu_without_cpuid(c); + setup_clear_cpu_cap(X86_FEATURE_CPUID); } setup_force_cpu_cap(X86_FEATURE_ALWAYS); @@ -1015,6 +1037,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) c->x86_model_id[0] = '\0'; /* Unset */ c->x86_max_cores = 1; c->x86_coreid_bits = 0; + c->cu_id = 0xff; #ifdef CONFIG_X86_64 c->x86_clflush_size = 64; c->x86_phys_bits = 36; @@ -1034,10 +1057,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) this_cpu->c_identify(c); /* Clear/Set all flags overridden by options, after probe */ - for (i = 0; i < NCAPINTS; i++) { - c->x86_capability[i] &= ~cpu_caps_cleared[i]; - c->x86_capability[i] |= cpu_caps_set[i]; - } + apply_forced_caps(c); #ifdef CONFIG_X86_64 c->apicid = apic->phys_pkg_id(c->initial_apicid, 0); @@ -1055,6 +1075,8 @@ static void identify_cpu(struct cpuinfo_x86 *c) */ if (this_cpu->c_init) this_cpu->c_init(c); + else + clear_sched_clock_stable(); /* Disable the PN if appropriate */ squash_the_stupid_serial_number(c); @@ -1096,10 +1118,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) * Clear/Set all flags overridden by options, need do it * before following smp all cpus cap AND. */ - for (i = 0; i < NCAPINTS; i++) { - c->x86_capability[i] &= ~cpu_caps_cleared[i]; - c->x86_capability[i] |= cpu_caps_set[i]; - } + apply_forced_caps(c); /* * On SMP, boot_cpu_data holds the common feature set between @@ -1491,7 +1510,7 @@ void cpu_init(void) for (i = 0; i <= IO_BITMAP_LONGS; i++) t->io_bitmap[i] = ~0UL; - atomic_inc(&init_mm.mm_count); + mmgrab(&init_mm); me->active_mm = &init_mm; BUG_ON(me->mm); enter_lazy_tlb(&init_mm, me); @@ -1542,7 +1561,7 @@ void cpu_init(void) /* * Set up and load the per-CPU TSS and LDT */ - atomic_inc(&init_mm.mm_count); + mmgrab(&init_mm); curr->active_mm = &init_mm; BUG_ON(curr->mm); enter_lazy_tlb(&init_mm, curr); diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index bd9dcd6b712d..47416f959a48 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -9,6 +9,7 @@ #include <asm/pci-direct.h> #include <asm/tsc.h> #include <asm/cpufeature.h> +#include <linux/sched.h> #include "cpu.h" @@ -183,6 +184,7 @@ static void early_init_cyrix(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_CYRIX_ARR); break; } + clear_sched_clock_stable(); } static void init_cyrix(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 203f860d2ab3..017ecd3bb553 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -15,6 +15,8 @@ #include <asm/cpu.h> #include <asm/intel-family.h> #include <asm/microcode_intel.h> +#include <asm/hwcap2.h> +#include <asm/elf.h> #ifdef CONFIG_X86_64 #include <linux/topology.h> @@ -62,6 +64,46 @@ void check_mpx_erratum(struct cpuinfo_x86 *c) } } +static bool ring3mwait_disabled __read_mostly; + +static int __init ring3mwait_disable(char *__unused) +{ + ring3mwait_disabled = true; + return 0; +} +__setup("ring3mwait=disable", ring3mwait_disable); + +static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c) +{ + /* + * Ring 3 MONITOR/MWAIT feature cannot be detected without + * cpu model and family comparison. + */ + if (c->x86 != 6) + return; + switch (c->x86_model) { + case INTEL_FAM6_XEON_PHI_KNL: + case INTEL_FAM6_XEON_PHI_KNM: + break; + default: + return; + } + + if (ring3mwait_disabled) { + msr_clear_bit(MSR_MISC_FEATURE_ENABLES, + MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT); + return; + } + + msr_set_bit(MSR_MISC_FEATURE_ENABLES, + MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT); + + set_cpu_cap(c, X86_FEATURE_RING3MWAIT); + + if (c == &boot_cpu_data) + ELF_HWCAP2 |= HWCAP2_RING3MWAIT; +} + static void early_init_intel(struct cpuinfo_x86 *c) { u64 misc_enable; @@ -119,8 +161,10 @@ static void early_init_intel(struct cpuinfo_x86 *c) if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); - if (!check_tsc_unstable()) - set_sched_clock_stable(); + if (check_tsc_unstable()) + clear_sched_clock_stable(); + } else { + clear_sched_clock_stable(); } /* Penwell and Cloverview have the TSC which doesn't sleep on S3 */ @@ -560,6 +604,8 @@ static void init_intel(struct cpuinfo_x86 *c) detect_vmx_virtcap(c); init_intel_energy_perf(c); + + probe_xeon_phi_r3mwait(c); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c index 83f1a98d37db..2eee85379689 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-apei.c +++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c @@ -52,8 +52,11 @@ void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err) if (severity >= GHES_SEV_RECOVERABLE) m.status |= MCI_STATUS_UC; - if (severity >= GHES_SEV_PANIC) + + if (severity >= GHES_SEV_PANIC) { m.status |= MCI_STATUS_PCC; + m.tsc = rdtsc(); + } m.addr = mem_err->physical_addr; mce_log(&m); diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c index 93d824ec3120..1e5a50c11d3c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c +++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c @@ -72,7 +72,7 @@ struct llist_node *mce_gen_pool_prepare_records(void) return new_head.first; } -void mce_gen_pool_process(void) +void mce_gen_pool_process(struct work_struct *__unused) { struct llist_node *head; struct mce_evt_llist *node, *tmp; diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index 517619ea6498..99165b206df3 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -152,7 +152,6 @@ static void raise_mce(struct mce *m) if (context == MCJ_CTX_RANDOM) return; -#ifdef CONFIG_X86_LOCAL_APIC if (m->inject_flags & (MCJ_IRQ_BROADCAST | MCJ_NMI_BROADCAST)) { unsigned long start; int cpu; @@ -192,9 +191,7 @@ static void raise_mce(struct mce *m) raise_local(); put_cpu(); put_online_cpus(); - } else -#endif - { + } else { preempt_disable(); raise_local(); preempt_enable(); diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index cd74a3f00aea..903043e6a62b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -31,7 +31,7 @@ struct mce_evt_llist { struct mce mce; }; -void mce_gen_pool_process(void); +void mce_gen_pool_process(struct work_struct *__unused); bool mce_gen_pool_empty(void); int mce_gen_pool_add(struct mce *mce); int mce_gen_pool_init(void); diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 00ef43233e03..8e9725c607ea 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -128,7 +128,6 @@ void mce_setup(struct mce *m) { memset(m, 0, sizeof(struct mce)); m->cpu = m->extcpu = smp_processor_id(); - m->tsc = rdtsc(); /* We hope get_seconds stays lockless */ m->time = get_seconds(); m->cpuvendor = boot_cpu_data.x86_vendor; @@ -217,9 +216,7 @@ void mce_register_decode_chain(struct notifier_block *nb) { atomic_inc(&num_notifiers); - /* Ensure SRAO notifier has the highest priority in the decode chain. */ - if (nb != &mce_srao_nb && nb->priority == INT_MAX) - nb->priority -= 1; + WARN_ON(nb->priority > MCE_PRIO_LOWEST && nb->priority < MCE_PRIO_EDAC); atomic_notifier_chain_register(&x86_mce_decoder_chain, nb); } @@ -583,7 +580,7 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, } static struct notifier_block mce_srao_nb = { .notifier_call = srao_decode_notifier, - .priority = INT_MAX, + .priority = MCE_PRIO_SRAO, }; static int mce_default_notifier(struct notifier_block *nb, unsigned long val, @@ -609,7 +606,7 @@ static int mce_default_notifier(struct notifier_block *nb, unsigned long val, static struct notifier_block mce_default_nb = { .notifier_call = mce_default_notifier, /* lowest prio, we want it to run last. */ - .priority = 0, + .priority = MCE_PRIO_LOWEST, }; /* @@ -710,14 +707,8 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) mce_gather_info(&m, NULL); - /* - * m.tsc was set in mce_setup(). Clear it if not requested. - * - * FIXME: Propagate @flags to mce_gather_info/mce_setup() to avoid - * that dance. - */ - if (!(flags & MCP_TIMESTAMP)) - m.tsc = 0; + if (flags & MCP_TIMESTAMP) + m.tsc = rdtsc(); for (i = 0; i < mca_cfg.banks; i++) { if (!mce_banks[i].ctl || !test_bit(i, *b)) @@ -1156,6 +1147,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) goto out; mce_gather_info(&m, regs); + m.tsc = rdtsc(); final = this_cpu_ptr(&mces_seen); *final = m; @@ -1322,41 +1314,6 @@ int memory_failure(unsigned long pfn, int vector, int flags) #endif /* - * Action optional processing happens here (picking up - * from the list of faulting pages that do_machine_check() - * placed into the genpool). - */ -static void mce_process_work(struct work_struct *dummy) -{ - mce_gen_pool_process(); -} - -#ifdef CONFIG_X86_MCE_INTEL -/*** - * mce_log_therm_throt_event - Logs the thermal throttling event to mcelog - * @cpu: The CPU on which the event occurred. - * @status: Event status information - * - * This function should be called by the thermal interrupt after the - * event has been processed and the decision was made to log the event - * further. - * - * The status parameter will be saved to the 'status' field of 'struct mce' - * and historically has been the register value of the - * MSR_IA32_THERMAL_STATUS (Intel) msr. - */ -void mce_log_therm_throt_event(__u64 status) -{ - struct mce m; - - mce_setup(&m); - m.bank = MCE_THERMAL_BANK; - m.status = status; - mce_log(&m); -} -#endif /* CONFIG_X86_MCE_INTEL */ - -/* * Periodic polling timer for "silent" machine check errors. If the * poller finds an MCE, poll 2x faster. When the poller finds no more * errors, poll 2x slower (up to check_interval seconds). @@ -1373,20 +1330,15 @@ static unsigned long mce_adjust_timer_default(unsigned long interval) static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default; -static void __restart_timer(struct timer_list *t, unsigned long interval) +static void __start_timer(struct timer_list *t, unsigned long interval) { unsigned long when = jiffies + interval; unsigned long flags; local_irq_save(flags); - if (timer_pending(t)) { - if (time_before(when, t->expires)) - mod_timer(t, when); - } else { - t->expires = round_jiffies(when); - add_timer_on(t, smp_processor_id()); - } + if (!timer_pending(t) || time_before(when, t->expires)) + mod_timer(t, round_jiffies(when)); local_irq_restore(flags); } @@ -1421,7 +1373,7 @@ static void mce_timer_fn(unsigned long data) done: __this_cpu_write(mce_next_interval, iv); - __restart_timer(t, iv); + __start_timer(t, iv); } /* @@ -1432,7 +1384,7 @@ void mce_timer_kick(unsigned long interval) struct timer_list *t = this_cpu_ptr(&mce_timer); unsigned long iv = __this_cpu_read(mce_next_interval); - __restart_timer(t, interval); + __start_timer(t, interval); if (interval < iv) __this_cpu_write(mce_next_interval, interval); @@ -1779,17 +1731,15 @@ static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c) } } -static void mce_start_timer(unsigned int cpu, struct timer_list *t) +static void mce_start_timer(struct timer_list *t) { unsigned long iv = check_interval * HZ; if (mca_cfg.ignore_ce || !iv) return; - per_cpu(mce_next_interval, cpu) = iv; - - t->expires = round_jiffies(jiffies + iv); - add_timer_on(t, cpu); + this_cpu_write(mce_next_interval, iv); + __start_timer(t, iv); } static void __mcheck_cpu_setup_timer(void) @@ -1806,7 +1756,7 @@ static void __mcheck_cpu_init_timer(void) unsigned int cpu = smp_processor_id(); setup_pinned_timer(t, mce_timer_fn, cpu); - mce_start_timer(cpu, t); + mce_start_timer(t); } /* Handle unconfigured int18 (should never happen) */ @@ -2196,7 +2146,7 @@ int __init mcheck_init(void) mce_register_decode_chain(&mce_default_nb); mcheck_vendor_init_severity(); - INIT_WORK(&mce_work, mce_process_work); + INIT_WORK(&mce_work, mce_gen_pool_process); init_irq_work(&mce_irq_work, mce_irq_work_cb); return 0; @@ -2566,7 +2516,7 @@ static int mce_cpu_dead(unsigned int cpu) static int mce_cpu_online(unsigned int cpu) { - struct timer_list *t = &per_cpu(mce_timer, cpu); + struct timer_list *t = this_cpu_ptr(&mce_timer); int ret; mce_device_create(cpu); @@ -2577,13 +2527,13 @@ static int mce_cpu_online(unsigned int cpu) return ret; } mce_reenable_cpu(); - mce_start_timer(cpu, t); + mce_start_timer(t); return 0; } static int mce_cpu_pre_down(unsigned int cpu) { - struct timer_list *t = &per_cpu(mce_timer, cpu); + struct timer_list *t = this_cpu_ptr(&mce_timer); mce_disable_cpu(); del_timer_sync(t); diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index a5fd137417a2..524cc5780a77 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -192,6 +192,7 @@ static void get_smca_bank_info(unsigned int bank) smca_banks[bank].hwid = s_hwid; smca_banks[bank].id = instance_id; + smca_banks[bank].sysfs_id = s_hwid->count++; break; } } @@ -777,7 +778,8 @@ __log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc) mce_setup(&m); m.status = status; - m.bank = bank; + m.bank = bank; + m.tsc = rdtsc(); if (threshold_err) m.misc = misc; @@ -814,14 +816,14 @@ static inline void __smp_deferred_error_interrupt(void) deferred_error_int_vector(); } -asmlinkage __visible void smp_deferred_error_interrupt(void) +asmlinkage __visible void __irq_entry smp_deferred_error_interrupt(void) { entering_irq(); __smp_deferred_error_interrupt(); exiting_ack_irq(); } -asmlinkage __visible void smp_trace_deferred_error_interrupt(void) +asmlinkage __visible void __irq_entry smp_trace_deferred_error_interrupt(void) { entering_irq(); trace_deferred_error_apic_entry(DEFERRED_ERROR_VECTOR); @@ -1064,9 +1066,12 @@ static const char *get_name(unsigned int bank, struct threshold_block *b) return NULL; } + if (smca_banks[bank].hwid->count == 1) + return smca_get_name(bank_type); + snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN, "%s_%x", smca_get_name(bank_type), - smca_banks[bank].id); + smca_banks[bank].sysfs_id); return buf_mcatype; } diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 465aca8be009..d7cc190ae457 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -6,7 +6,7 @@ * * Maintains a counter in /sys that keeps track of the number of thermal * events, such that the user knows how bad the thermal problem might be - * (since the logging to syslog and mcelog is rate limited). + * (since the logging to syslog is rate limited). * * Author: Dmitriy Zavin (dmitriyz@google.com) * @@ -141,13 +141,8 @@ static struct attribute_group thermal_attr_group = { * IRQ has been acknowledged. * * It will take care of rate limiting and printing messages to the syslog. - * - * Returns: 0 : Event should NOT be further logged, i.e. still in - * "timeout" from previous log message. - * 1 : Event should be logged further, and a message has been - * printed to the syslog. */ -static int therm_throt_process(bool new_event, int event, int level) +static void therm_throt_process(bool new_event, int event, int level) { struct _thermal_state *state; unsigned int this_cpu = smp_processor_id(); @@ -162,16 +157,16 @@ static int therm_throt_process(bool new_event, int event, int level) else if (event == POWER_LIMIT_EVENT) state = &pstate->core_power_limit; else - return 0; + return; } else if (level == PACKAGE_LEVEL) { if (event == THERMAL_THROTTLING_EVENT) state = &pstate->package_throttle; else if (event == POWER_LIMIT_EVENT) state = &pstate->package_power_limit; else - return 0; + return; } else - return 0; + return; old_event = state->new_event; state->new_event = new_event; @@ -181,7 +176,7 @@ static int therm_throt_process(bool new_event, int event, int level) if (time_before64(now, state->next_check) && state->count != state->last_count) - return 0; + return; state->next_check = now + CHECK_INTERVAL; state->last_count = state->count; @@ -193,16 +188,14 @@ static int therm_throt_process(bool new_event, int event, int level) this_cpu, level == CORE_LEVEL ? "Core" : "Package", state->count); - return 1; + return; } if (old_event) { if (event == THERMAL_THROTTLING_EVENT) pr_info("CPU%d: %s temperature/speed normal\n", this_cpu, level == CORE_LEVEL ? "Core" : "Package"); - return 1; + return; } - - return 0; } static int thresh_event_valid(int level, int event) @@ -365,10 +358,9 @@ static void intel_thermal_interrupt(void) /* Check for violation of core thermal thresholds*/ notify_thresholds(msr_val); - if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT, - THERMAL_THROTTLING_EVENT, - CORE_LEVEL) != 0) - mce_log_therm_throt_event(msr_val); + therm_throt_process(msr_val & THERM_STATUS_PROCHOT, + THERMAL_THROTTLING_EVENT, + CORE_LEVEL); if (this_cpu_has(X86_FEATURE_PLN) && int_pln_enable) therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT, @@ -404,14 +396,16 @@ static inline void __smp_thermal_interrupt(void) smp_thermal_vector(); } -asmlinkage __visible void smp_thermal_interrupt(struct pt_regs *regs) +asmlinkage __visible void __irq_entry +smp_thermal_interrupt(struct pt_regs *regs) { entering_irq(); __smp_thermal_interrupt(); exiting_ack_irq(); } -asmlinkage __visible void smp_trace_thermal_interrupt(struct pt_regs *regs) +asmlinkage __visible void __irq_entry +smp_trace_thermal_interrupt(struct pt_regs *regs) { entering_irq(); trace_thermal_apic_entry(THERMAL_APIC_VECTOR); diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c b/arch/x86/kernel/cpu/mcheck/threshold.c index 9beb092d68a5..bb0e75eed10a 100644 --- a/arch/x86/kernel/cpu/mcheck/threshold.c +++ b/arch/x86/kernel/cpu/mcheck/threshold.c @@ -23,14 +23,14 @@ static inline void __smp_threshold_interrupt(void) mce_threshold_vector(); } -asmlinkage __visible void smp_threshold_interrupt(void) +asmlinkage __visible void __irq_entry smp_threshold_interrupt(void) { entering_irq(); __smp_threshold_interrupt(); exiting_ack_irq(); } -asmlinkage __visible void smp_trace_threshold_interrupt(void) +asmlinkage __visible void __irq_entry smp_trace_threshold_interrupt(void) { entering_irq(); trace_threshold_apic_entry(THRESHOLD_APIC_VECTOR); diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 6a31e2691f3a..7889ae492af0 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -42,16 +42,19 @@ static struct equiv_cpu_entry *equiv_cpu_table; /* * This points to the current valid container of microcode patches which we will - * save from the initrd/builtin before jettisoning its contents. + * save from the initrd/builtin before jettisoning its contents. @mc is the + * microcode patch we found to match. */ -struct container { - u8 *data; - size_t size; -} cont; +struct cont_desc { + struct microcode_amd *mc; + u32 cpuid_1_eax; + u32 psize; + u8 *data; + size_t size; +}; static u32 ucode_new_rev; static u8 amd_ucode_patch[PATCH_MAX_SIZE]; -static u16 this_equiv_id; /* * Microcode patch container file is prepended to the initrd in cpio @@ -60,57 +63,13 @@ static u16 this_equiv_id; static const char ucode_path[] __maybe_unused = "kernel/x86/microcode/AuthenticAMD.bin"; -static size_t compute_container_size(u8 *data, u32 total_size) +static u16 find_equiv_id(struct equiv_cpu_entry *equiv_table, u32 sig) { - size_t size = 0; - u32 *header = (u32 *)data; - - if (header[0] != UCODE_MAGIC || - header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */ - header[2] == 0) /* size */ - return size; - - size = header[2] + CONTAINER_HDR_SZ; - total_size -= size; - data += size; - - while (total_size) { - u16 patch_size; - - header = (u32 *)data; - - if (header[0] != UCODE_UCODE_TYPE) - break; - - /* - * Sanity-check patch size. - */ - patch_size = header[1]; - if (patch_size > PATCH_MAX_SIZE) - break; - - size += patch_size + SECTION_HDR_SIZE; - data += patch_size + SECTION_HDR_SIZE; - total_size -= patch_size + SECTION_HDR_SIZE; + for (; equiv_table && equiv_table->installed_cpu; equiv_table++) { + if (sig == equiv_table->installed_cpu) + return equiv_table->equiv_cpu; } - return size; -} - -static inline u16 find_equiv_id(struct equiv_cpu_entry *equiv_cpu_table, - unsigned int sig) -{ - int i = 0; - - if (!equiv_cpu_table) - return 0; - - while (equiv_cpu_table[i].installed_cpu != 0) { - if (sig == equiv_cpu_table[i].installed_cpu) - return equiv_cpu_table[i].equiv_cpu; - - i++; - } return 0; } @@ -118,91 +77,109 @@ static inline u16 find_equiv_id(struct equiv_cpu_entry *equiv_cpu_table, * This scans the ucode blob for the proper container as we can have multiple * containers glued together. Returns the equivalence ID from the equivalence * table or 0 if none found. + * Returns the amount of bytes consumed while scanning. @desc contains all the + * data we're going to use in later stages of the application. */ -static u16 -find_proper_container(u8 *ucode, size_t size, struct container *ret_cont) +static ssize_t parse_container(u8 *ucode, ssize_t size, struct cont_desc *desc) { - struct container ret = { NULL, 0 }; - u32 eax, ebx, ecx, edx; struct equiv_cpu_entry *eq; - int offset, left; - u16 eq_id = 0; - u32 *header; - u8 *data; + ssize_t orig_size = size; + u32 *hdr = (u32 *)ucode; + u16 eq_id; + u8 *buf; - data = ucode; - left = size; - header = (u32 *)data; + /* Am I looking at an equivalence table header? */ + if (hdr[0] != UCODE_MAGIC || + hdr[1] != UCODE_EQUIV_CPU_TABLE_TYPE || + hdr[2] == 0) + return CONTAINER_HDR_SZ; + buf = ucode; - /* find equiv cpu table */ - if (header[0] != UCODE_MAGIC || - header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */ - header[2] == 0) /* size */ - return eq_id; + eq = (struct equiv_cpu_entry *)(buf + CONTAINER_HDR_SZ); - eax = 0x00000001; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); + /* Find the equivalence ID of our CPU in this table: */ + eq_id = find_equiv_id(eq, desc->cpuid_1_eax); - while (left > 0) { - eq = (struct equiv_cpu_entry *)(data + CONTAINER_HDR_SZ); + buf += hdr[2] + CONTAINER_HDR_SZ; + size -= hdr[2] + CONTAINER_HDR_SZ; + + /* + * Scan through the rest of the container to find where it ends. We do + * some basic sanity-checking too. + */ + while (size > 0) { + struct microcode_amd *mc; + u32 patch_size; - ret.data = data; + hdr = (u32 *)buf; - /* Advance past the container header */ - offset = header[2] + CONTAINER_HDR_SZ; - data += offset; - left -= offset; + if (hdr[0] != UCODE_UCODE_TYPE) + break; - eq_id = find_equiv_id(eq, eax); - if (eq_id) { - ret.size = compute_container_size(ret.data, left + offset); + /* Sanity-check patch size. */ + patch_size = hdr[1]; + if (patch_size > PATCH_MAX_SIZE) + break; - /* - * truncate how much we need to iterate over in the - * ucode update loop below - */ - left = ret.size - offset; + /* Skip patch section header: */ + buf += SECTION_HDR_SIZE; + size -= SECTION_HDR_SIZE; - *ret_cont = ret; - return eq_id; + mc = (struct microcode_amd *)buf; + if (eq_id == mc->hdr.processor_rev_id) { + desc->psize = patch_size; + desc->mc = mc; } - /* - * support multiple container files appended together. if this - * one does not have a matching equivalent cpu entry, we fast - * forward to the next container file. - */ - while (left > 0) { - header = (u32 *)data; - - if (header[0] == UCODE_MAGIC && - header[1] == UCODE_EQUIV_CPU_TABLE_TYPE) - break; - - offset = header[1] + SECTION_HDR_SIZE; - data += offset; - left -= offset; - } + buf += patch_size; + size -= patch_size; + } - /* mark where the next microcode container file starts */ - offset = data - (u8 *)ucode; - ucode = data; + /* + * If we have found a patch (desc->mc), it means we're looking at the + * container which has a patch for this CPU so return 0 to mean, @ucode + * already points to the proper container. Otherwise, we return the size + * we scanned so that we can advance to the next container in the + * buffer. + */ + if (desc->mc) { + desc->data = ucode; + desc->size = orig_size - size; + + return 0; } - return eq_id; + return orig_size - size; } -static int __apply_microcode_amd(struct microcode_amd *mc_amd) +/* + * Scan the ucode blob for the proper container as we can have multiple + * containers glued together. + */ +static void scan_containers(u8 *ucode, size_t size, struct cont_desc *desc) +{ + ssize_t rem = size; + + while (rem >= 0) { + ssize_t s = parse_container(ucode, rem, desc); + if (!s) + return; + + ucode += s; + rem -= s; + } +} + +static int __apply_microcode_amd(struct microcode_amd *mc) { u32 rev, dummy; - native_wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc_amd->hdr.data_code); + native_wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc->hdr.data_code); /* verify patch application was successful */ native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); - if (rev != mc_amd->hdr.patch_id) + if (rev != mc->hdr.patch_id) return -1; return 0; @@ -217,17 +194,16 @@ static int __apply_microcode_amd(struct microcode_amd *mc_amd) * load_microcode_amd() to save equivalent cpu table and microcode patches in * kernel heap memory. * - * Returns true if container found (sets @ret_cont), false otherwise. + * Returns true if container found (sets @desc), false otherwise. */ -static bool apply_microcode_early_amd(void *ucode, size_t size, bool save_patch, - struct container *ret_cont) +static bool +apply_microcode_early_amd(u32 cpuid_1_eax, void *ucode, size_t size, bool save_patch) { + struct cont_desc desc = { 0 }; u8 (*patch)[PATCH_MAX_SIZE]; - u32 rev, *header, *new_rev; - struct container ret; - int offset, left; - u16 eq_id = 0; - u8 *data; + struct microcode_amd *mc; + u32 rev, dummy, *new_rev; + bool ret = false; #ifdef CONFIG_X86_32 new_rev = (u32 *)__pa_nodebug(&ucode_new_rev); @@ -237,50 +213,27 @@ static bool apply_microcode_early_amd(void *ucode, size_t size, bool save_patch, patch = &amd_ucode_patch; #endif - if (check_current_patch_level(&rev, true)) - return false; - - eq_id = find_proper_container(ucode, size, &ret); - if (!eq_id) - return false; - - this_equiv_id = eq_id; - header = (u32 *)ret.data; - - /* We're pointing to an equiv table, skip over it. */ - data = ret.data + header[2] + CONTAINER_HDR_SZ; - left = ret.size - (header[2] + CONTAINER_HDR_SZ); - - while (left > 0) { - struct microcode_amd *mc; - - header = (u32 *)data; - if (header[0] != UCODE_UCODE_TYPE || /* type */ - header[1] == 0) /* size */ - break; + desc.cpuid_1_eax = cpuid_1_eax; - mc = (struct microcode_amd *)(data + SECTION_HDR_SIZE); + scan_containers(ucode, size, &desc); - if (eq_id == mc->hdr.processor_rev_id && rev < mc->hdr.patch_id) { + mc = desc.mc; + if (!mc) + return ret; - if (!__apply_microcode_amd(mc)) { - rev = mc->hdr.patch_id; - *new_rev = rev; + native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); + if (rev >= mc->hdr.patch_id) + return ret; - if (save_patch) - memcpy(patch, mc, min_t(u32, header[1], PATCH_MAX_SIZE)); - } - } + if (!__apply_microcode_amd(mc)) { + *new_rev = mc->hdr.patch_id; + ret = true; - offset = header[1] + SECTION_HDR_SIZE; - data += offset; - left -= offset; + if (save_patch) + memcpy(patch, mc, min_t(u32, desc.psize, PATCH_MAX_SIZE)); } - if (ret_cont) - *ret_cont = ret; - - return true; + return ret; } static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family) @@ -298,10 +251,9 @@ static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family) #endif } -void __init load_ucode_amd_bsp(unsigned int family) +void __load_ucode_amd(unsigned int cpuid_1_eax, struct cpio_data *ret) { struct ucode_cpu_info *uci; - u32 eax, ebx, ecx, edx; struct cpio_data cp; const char *path; bool use_pa; @@ -316,183 +268,95 @@ void __init load_ucode_amd_bsp(unsigned int family) use_pa = false; } - if (!get_builtin_microcode(&cp, family)) + if (!get_builtin_microcode(&cp, x86_family(cpuid_1_eax))) cp = find_microcode_in_initrd(path, use_pa); - if (!(cp.data && cp.size)) - return; - - /* Get BSP's CPUID.EAX(1), needed in load_microcode_amd() */ - eax = 1; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); - uci->cpu_sig.sig = eax; + /* Needed in load_microcode_amd() */ + uci->cpu_sig.sig = cpuid_1_eax; - apply_microcode_early_amd(cp.data, cp.size, true, NULL); + *ret = cp; } -#ifdef CONFIG_X86_32 -/* - * On 32-bit, since AP's early load occurs before paging is turned on, we - * cannot traverse cpu_equiv_table and microcode_cache in kernel heap memory. - * So during cold boot, AP will apply_ucode_in_initrd() just like the BSP. - * In save_microcode_in_initrd_amd() BSP's patch is copied to amd_ucode_patch, - * which is used upon resume from suspend. - */ -void load_ucode_amd_ap(unsigned int family) +void __init load_ucode_amd_bsp(unsigned int cpuid_1_eax) { - struct microcode_amd *mc; - struct cpio_data cp; - - mc = (struct microcode_amd *)__pa_nodebug(amd_ucode_patch); - if (mc->hdr.patch_id && mc->hdr.processor_rev_id) { - __apply_microcode_amd(mc); - return; - } - - if (!get_builtin_microcode(&cp, family)) - cp = find_microcode_in_initrd((const char *)__pa_nodebug(ucode_path), true); + struct cpio_data cp = { }; + __load_ucode_amd(cpuid_1_eax, &cp); if (!(cp.data && cp.size)) return; - /* - * This would set amd_ucode_patch above so that the following APs can - * use it directly instead of going down this path again. - */ - apply_microcode_early_amd(cp.data, cp.size, true, NULL); + apply_microcode_early_amd(cpuid_1_eax, cp.data, cp.size, true); } -#else -void load_ucode_amd_ap(unsigned int family) + +void load_ucode_amd_ap(unsigned int cpuid_1_eax) { - struct equiv_cpu_entry *eq; struct microcode_amd *mc; - u32 rev, eax; - u16 eq_id; - - /* 64-bit runs with paging enabled, thus early==false. */ - if (check_current_patch_level(&rev, false)) - return; - - /* First AP hasn't cached it yet, go through the blob. */ - if (!cont.data) { - struct cpio_data cp = { NULL, 0, "" }; + struct cpio_data cp; + u32 *new_rev, rev, dummy; - if (cont.size == -1) - return; + if (IS_ENABLED(CONFIG_X86_32)) { + mc = (struct microcode_amd *)__pa_nodebug(amd_ucode_patch); + new_rev = (u32 *)__pa_nodebug(&ucode_new_rev); + } else { + mc = (struct microcode_amd *)amd_ucode_patch; + new_rev = &ucode_new_rev; + } -reget: - if (!get_builtin_microcode(&cp, family)) { -#ifdef CONFIG_BLK_DEV_INITRD - cp = find_cpio_data(ucode_path, (void *)initrd_start, - initrd_end - initrd_start, NULL); -#endif - if (!(cp.data && cp.size)) { - /* - * Mark it so that other APs do not scan again - * for no real reason and slow down boot - * needlessly. - */ - cont.size = -1; - return; - } - } + native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); - if (!apply_microcode_early_amd(cp.data, cp.size, false, &cont)) { - cont.size = -1; + /* Check whether we have saved a new patch already: */ + if (*new_rev && rev < mc->hdr.patch_id) { + if (!__apply_microcode_amd(mc)) { + *new_rev = mc->hdr.patch_id; return; } } - eax = cpuid_eax(0x00000001); - eq = (struct equiv_cpu_entry *)(cont.data + CONTAINER_HDR_SZ); - - eq_id = find_equiv_id(eq, eax); - if (!eq_id) + __load_ucode_amd(cpuid_1_eax, &cp); + if (!(cp.data && cp.size)) return; - if (eq_id == this_equiv_id) { - mc = (struct microcode_amd *)amd_ucode_patch; - - if (mc && rev < mc->hdr.patch_id) { - if (!__apply_microcode_amd(mc)) - ucode_new_rev = mc->hdr.patch_id; - } - - } else { - - /* - * AP has a different equivalence ID than BSP, looks like - * mixed-steppings silicon so go through the ucode blob anew. - */ - goto reget; - } + apply_microcode_early_amd(cpuid_1_eax, cp.data, cp.size, false); } -#endif /* CONFIG_X86_32 */ static enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size); -int __init save_microcode_in_initrd_amd(unsigned int fam) +int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax) { + struct cont_desc desc = { 0 }; enum ucode_state ret; - int retval = 0; - u16 eq_id; - - if (!cont.data) { - if (IS_ENABLED(CONFIG_X86_32) && (cont.size != -1)) { - struct cpio_data cp = { NULL, 0, "" }; - -#ifdef CONFIG_BLK_DEV_INITRD - cp = find_cpio_data(ucode_path, (void *)initrd_start, - initrd_end - initrd_start, NULL); -#endif + struct cpio_data cp; - if (!(cp.data && cp.size)) { - cont.size = -1; - return -EINVAL; - } + cp = find_microcode_in_initrd(ucode_path, false); + if (!(cp.data && cp.size)) + return -EINVAL; - eq_id = find_proper_container(cp.data, cp.size, &cont); - if (!eq_id) { - cont.size = -1; - return -EINVAL; - } + desc.cpuid_1_eax = cpuid_1_eax; - } else - return -EINVAL; - } + scan_containers(cp.data, cp.size, &desc); + if (!desc.mc) + return -EINVAL; - ret = load_microcode_amd(smp_processor_id(), fam, cont.data, cont.size); + ret = load_microcode_amd(smp_processor_id(), x86_family(cpuid_1_eax), + desc.data, desc.size); if (ret != UCODE_OK) - retval = -EINVAL; - - /* - * This will be freed any msec now, stash patches for the current - * family and switch to patch cache for cpu hotplug, etc later. - */ - cont.data = NULL; - cont.size = 0; + return -EINVAL; - return retval; + return 0; } void reload_ucode_amd(void) { struct microcode_amd *mc; - u32 rev; - - /* - * early==false because this is a syscore ->resume path and by - * that time paging is long enabled. - */ - if (check_current_patch_level(&rev, false)) - return; + u32 rev, dummy; mc = (struct microcode_amd *)amd_ucode_patch; if (!mc) return; + rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); + if (rev < mc->hdr.patch_id) { if (!__apply_microcode_amd(mc)) { ucode_new_rev = mc->hdr.patch_id; @@ -630,60 +494,13 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size, return patch_size; } -/* - * Those patch levels cannot be updated to newer ones and thus should be final. - */ -static u32 final_levels[] = { - 0x01000098, - 0x0100009f, - 0x010000af, - 0, /* T-101 terminator */ -}; - -/* - * Check the current patch level on this CPU. - * - * @rev: Use it to return the patch level. It is set to 0 in the case of - * error. - * - * Returns: - * - true: if update should stop - * - false: otherwise - */ -bool check_current_patch_level(u32 *rev, bool early) -{ - u32 lvl, dummy, i; - bool ret = false; - u32 *levels; - - native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy); - - if (IS_ENABLED(CONFIG_X86_32) && early) - levels = (u32 *)__pa_nodebug(&final_levels); - else - levels = final_levels; - - for (i = 0; levels[i]; i++) { - if (lvl == levels[i]) { - lvl = 0; - ret = true; - break; - } - } - - if (rev) - *rev = lvl; - - return ret; -} - static int apply_microcode_amd(int cpu) { struct cpuinfo_x86 *c = &cpu_data(cpu); struct microcode_amd *mc_amd; struct ucode_cpu_info *uci; struct ucode_patch *p; - u32 rev; + u32 rev, dummy; BUG_ON(raw_smp_processor_id() != cpu); @@ -696,8 +513,7 @@ static int apply_microcode_amd(int cpu) mc_amd = p->data; uci->mc = p->data; - if (check_current_patch_level(&rev, false)) - return -1; + rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); /* need to apply patch? */ if (rev >= mc_amd->hdr.patch_id) { diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 2af69d27da62..b4a4cd39b358 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -46,6 +46,8 @@ static struct microcode_ops *microcode_ops; static bool dis_ucode_ldr = true; +bool initrd_gone; + LIST_HEAD(microcode_cache); /* @@ -64,19 +66,50 @@ static DEFINE_MUTEX(microcode_mutex); struct ucode_cpu_info ucode_cpu_info[NR_CPUS]; -/* - * Operations that are run on a target cpu: - */ - struct cpu_info_ctx { struct cpu_signature *cpu_sig; int err; }; +/* + * Those patch levels cannot be updated to newer ones and thus should be final. + */ +static u32 final_levels[] = { + 0x01000098, + 0x0100009f, + 0x010000af, + 0, /* T-101 terminator */ +}; + +/* + * Check the current patch level on this CPU. + * + * Returns: + * - true: if update should stop + * - false: otherwise + */ +static bool amd_check_current_patch_level(void) +{ + u32 lvl, dummy, i; + u32 *levels; + + native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy); + + if (IS_ENABLED(CONFIG_X86_32)) + levels = (u32 *)__pa_nodebug(&final_levels); + else + levels = final_levels; + + for (i = 0; levels[i]; i++) { + if (lvl == levels[i]) + return true; + } + return false; +} + static bool __init check_loader_disabled_bsp(void) { static const char *__dis_opt_str = "dis_ucode_ldr"; - u32 a, b, c, d; #ifdef CONFIG_X86_32 const char *cmdline = (const char *)__pa_nodebug(boot_command_line); @@ -92,18 +125,19 @@ static bool __init check_loader_disabled_bsp(void) if (!have_cpuid_p()) return *res; - a = 1; - c = 0; - native_cpuid(&a, &b, &c, &d); - /* * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not * completely accurate as xen pv guests don't see that CPUID bit set but * that's good enough as they don't land on the BSP path anyway. */ - if (c & BIT(31)) + if (native_cpuid_ecx(1) & BIT(31)) return *res; + if (x86_cpuid_vendor() == X86_VENDOR_AMD) { + if (amd_check_current_patch_level()) + return *res; + } + if (cmdline_find_option_bool(cmdline, option) <= 0) *res = false; @@ -131,23 +165,21 @@ bool get_builtin_firmware(struct cpio_data *cd, const char *name) void __init load_ucode_bsp(void) { - int vendor; - unsigned int family; + unsigned int cpuid_1_eax; if (check_loader_disabled_bsp()) return; - vendor = x86_cpuid_vendor(); - family = x86_cpuid_family(); + cpuid_1_eax = native_cpuid_eax(1); - switch (vendor) { + switch (x86_cpuid_vendor()) { case X86_VENDOR_INTEL: - if (family >= 6) + if (x86_family(cpuid_1_eax) >= 6) load_ucode_intel_bsp(); break; case X86_VENDOR_AMD: - if (family >= 0x10) - load_ucode_amd_bsp(family); + if (x86_family(cpuid_1_eax) >= 0x10) + load_ucode_amd_bsp(cpuid_1_eax); break; default: break; @@ -165,22 +197,21 @@ static bool check_loader_disabled_ap(void) void load_ucode_ap(void) { - int vendor, family; + unsigned int cpuid_1_eax; if (check_loader_disabled_ap()) return; - vendor = x86_cpuid_vendor(); - family = x86_cpuid_family(); + cpuid_1_eax = native_cpuid_eax(1); - switch (vendor) { + switch (x86_cpuid_vendor()) { case X86_VENDOR_INTEL: - if (family >= 6) + if (x86_family(cpuid_1_eax) >= 6) load_ucode_intel_ap(); break; case X86_VENDOR_AMD: - if (family >= 0x10) - load_ucode_amd_ap(family); + if (x86_family(cpuid_1_eax) >= 0x10) + load_ucode_amd_ap(cpuid_1_eax); break; default: break; @@ -190,21 +221,24 @@ void load_ucode_ap(void) static int __init save_microcode_in_initrd(void) { struct cpuinfo_x86 *c = &boot_cpu_data; + int ret = -EINVAL; switch (c->x86_vendor) { case X86_VENDOR_INTEL: if (c->x86 >= 6) - return save_microcode_in_initrd_intel(); + ret = save_microcode_in_initrd_intel(); break; case X86_VENDOR_AMD: if (c->x86 >= 0x10) - return save_microcode_in_initrd_amd(c->x86); + return save_microcode_in_initrd_amd(cpuid_eax(1)); break; default: break; } - return -EINVAL; + initrd_gone = true; + + return ret; } struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa) @@ -247,9 +281,16 @@ struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa) * has the virtual address of the beginning of the initrd. It also * possibly relocates the ramdisk. In either case, initrd_start contains * the updated address so use that instead. + * + * initrd_gone is for the hotplug case where we've thrown out initrd + * already. */ - if (!use_pa && initrd_start) - start = initrd_start; + if (!use_pa) { + if (initrd_gone) + return (struct cpio_data){ NULL, 0, "" }; + if (initrd_start) + start = initrd_start; + } return find_cpio_data(path, (void *)start, size, NULL); #else /* !CONFIG_BLK_DEV_INITRD */ diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 3f329b74e040..8325d8a09ab0 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -41,7 +41,7 @@ static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin"; -/* Current microcode patch used in early patching */ +/* Current microcode patch used in early patching on the APs. */ struct microcode_intel *intel_ucode_patch; static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1, @@ -607,12 +607,6 @@ int __init save_microcode_in_initrd_intel(void) struct ucode_cpu_info uci; struct cpio_data cp; - /* - * AP loading didn't find any microcode patch, no need to save anything. - */ - if (!intel_ucode_patch || IS_ERR(intel_ucode_patch)) - return 0; - if (!load_builtin_intel_microcode(&cp)) cp = find_microcode_in_initrd(ucode_path, false); @@ -628,7 +622,6 @@ int __init save_microcode_in_initrd_intel(void) return 0; } - /* * @res_patch, output: a pointer to the patch we found. */ diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 65e20c97e04b..b5375b9497b3 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -133,26 +133,6 @@ static uint32_t __init ms_hyperv_platform(void) return 0; } -static u64 read_hv_clock(struct clocksource *arg) -{ - u64 current_tick; - /* - * Read the partition counter to get the current tick count. This count - * is set to 0 when the partition is created and is incremented in - * 100 nanosecond units. - */ - rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick); - return current_tick; -} - -static struct clocksource hyperv_cs = { - .name = "hyperv_clocksource", - .rating = 400, /* use this when running on Hyperv*/ - .read = read_hv_clock, - .mask = CLOCKSOURCE_MASK(64), - .flags = CLOCK_SOURCE_IS_CONTINUOUS, -}; - static unsigned char hv_get_nmi_reason(void) { return 0; @@ -180,6 +160,11 @@ static int hv_nmi_unknown(unsigned int val, struct pt_regs *regs) static void __init ms_hyperv_init_platform(void) { + int hv_host_info_eax; + int hv_host_info_ebx; + int hv_host_info_ecx; + int hv_host_info_edx; + /* * Extract the features and hints */ @@ -190,6 +175,21 @@ static void __init ms_hyperv_init_platform(void) pr_info("HyperV: features 0x%x, hints 0x%x\n", ms_hyperv.features, ms_hyperv.hints); + /* + * Extract host information. + */ + if (cpuid_eax(HVCPUID_VENDOR_MAXFUNCTION) >= HVCPUID_VERSION) { + hv_host_info_eax = cpuid_eax(HVCPUID_VERSION); + hv_host_info_ebx = cpuid_ebx(HVCPUID_VERSION); + hv_host_info_ecx = cpuid_ecx(HVCPUID_VERSION); + hv_host_info_edx = cpuid_edx(HVCPUID_VERSION); + + pr_info("Hyper-V Host Build:%d-%d.%d-%d-%d.%d\n", + hv_host_info_eax, hv_host_info_ebx >> 16, + hv_host_info_ebx & 0xFFFF, hv_host_info_ecx, + hv_host_info_edx >> 24, hv_host_info_edx & 0xFFFFFF); + } + #ifdef CONFIG_X86_LOCAL_APIC if (ms_hyperv.features & HV_X64_MSR_APIC_FREQUENCY_AVAILABLE) { /* @@ -208,9 +208,6 @@ static void __init ms_hyperv_init_platform(void) "hv_nmi_unknown"); #endif - if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE) - clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100); - #ifdef CONFIG_X86_IO_APIC no_timer_check = 1; #endif @@ -227,6 +224,13 @@ static void __init ms_hyperv_init_platform(void) */ if (efi_enabled(EFI_BOOT)) x86_platform.get_nmi_reason = hv_get_nmi_reason; + +#if IS_ENABLED(CONFIG_HYPERV) + /* + * Setup the hook to get control post apic initialization. + */ + x86_platform.apic_post_init = hyperv_init; +#endif } const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c index 34178564be2a..c1ea5b999839 100644 --- a/arch/x86/kernel/cpu/transmeta.c +++ b/arch/x86/kernel/cpu/transmeta.c @@ -1,4 +1,5 @@ #include <linux/kernel.h> +#include <linux/sched.h> #include <linux/mm.h> #include <asm/cpufeature.h> #include <asm/msr.h> @@ -14,6 +15,8 @@ static void early_init_transmeta(struct cpuinfo_x86 *c) if (xlvl >= 0x80860001) c->x86_capability[CPUID_8086_0001_EDX] = cpuid_edx(0x80860001); } + + clear_sched_clock_stable(); } static void init_transmeta(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index e4e97a5355ce..e1114f070c2d 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -178,13 +178,8 @@ void fpstate_init(union fpregs_state *state) memset(state, 0, fpu_kernel_xstate_size); - /* - * XRSTORS requires that this bit is set in xcomp_bv, or - * it will #GP. Make sure it is replaced after the memset(). - */ if (static_cpu_has(X86_FEATURE_XSAVES)) - state->xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT; - + fpstate_init_xstate(&state->xsave); if (static_cpu_has(X86_FEATURE_FXSR)) fpstate_init_fxstate(&state->fxsave); else diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 60dece392b3a..19bdd1bf8160 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -48,13 +48,7 @@ void fpu__init_cpu(void) fpu__init_cpu_xstate(); } -/* - * The earliest FPU detection code. - * - * Set the X86_FEATURE_FPU CPU-capability bit based on - * trying to execute an actual sequence of FPU instructions: - */ -static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) +static bool fpu__probe_without_cpuid(void) { unsigned long cr0; u16 fsw, fcw; @@ -65,18 +59,25 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) cr0 &= ~(X86_CR0_TS | X86_CR0_EM); write_cr0(cr0); - if (!test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) { - asm volatile("fninit ; fnstsw %0 ; fnstcw %1" - : "+m" (fsw), "+m" (fcw)); + asm volatile("fninit ; fnstsw %0 ; fnstcw %1" : "+m" (fsw), "+m" (fcw)); + + pr_info("x86/fpu: Probing for FPU: FSW=0x%04hx FCW=0x%04hx\n", fsw, fcw); - if (fsw == 0 && (fcw & 0x103f) == 0x003f) - set_cpu_cap(c, X86_FEATURE_FPU); + return fsw == 0 && (fcw & 0x103f) == 0x003f; +} + +static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) +{ + if (!boot_cpu_has(X86_FEATURE_CPUID) && + !test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) { + if (fpu__probe_without_cpuid()) + setup_force_cpu_cap(X86_FEATURE_FPU); else - clear_cpu_cap(c, X86_FEATURE_FPU); + setup_clear_cpu_cap(X86_FEATURE_FPU); } #ifndef CONFIG_MATH_EMULATION - if (!boot_cpu_has(X86_FEATURE_FPU)) { + if (!test_cpu_cap(&boot_cpu_data, X86_FEATURE_FPU)) { pr_emerg("x86/fpu: Giving up, no FPU found and no math emulation present\n"); for (;;) asm volatile("hlt"); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 1d7770447b3e..c24ac1efb12d 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -78,6 +78,7 @@ void fpu__xstate_clear_all_cpu_caps(void) setup_clear_cpu_cap(X86_FEATURE_PKU); setup_clear_cpu_cap(X86_FEATURE_AVX512_4VNNIW); setup_clear_cpu_cap(X86_FEATURE_AVX512_4FMAPS); + setup_clear_cpu_cap(X86_FEATURE_AVX512_VPOPCNTDQ); } /* @@ -705,8 +706,14 @@ void __init fpu__init_system_xstate(void) WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; + if (!boot_cpu_has(X86_FEATURE_FPU)) { + pr_info("x86/fpu: No FPU detected\n"); + return; + } + if (!boot_cpu_has(X86_FEATURE_XSAVE)) { - pr_info("x86/fpu: Legacy x87 FPU detected.\n"); + pr_info("x86/fpu: x87 FPU will use %s\n", + boot_cpu_has(X86_FEATURE_FXSR) ? "FXSAVE" : "FSAVE"); return; } diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 85e87b46c318..dc6ba5bda9fc 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -352,6 +352,7 @@ static int hpet_resume(struct clock_event_device *evt, int timer) } else { struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); + irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq)); irq_domain_activate_irq(irq_get_irq_data(hdev->irq)); disable_irq(hdev->irq); irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu)); diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 589b3193f102..b01bc8517450 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -16,6 +16,7 @@ #include <linux/syscalls.h> #include <linux/bitmap.h> #include <asm/syscalls.h> +#include <asm/desc.h> /* * this changes the io permissions bitmap in the current task. @@ -45,6 +46,10 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) memset(bitmap, 0xff, IO_BITMAP_BYTES); t->io_bitmap_ptr = bitmap; set_thread_flag(TIF_IO_BITMAP); + + preempt_disable(); + refresh_TR(); + preempt_enable(); } /* diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 7c6e9ffe4424..4d8183b5f113 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -264,7 +264,7 @@ void __smp_x86_platform_ipi(void) x86_platform_ipi_callback(); } -__visible void smp_x86_platform_ipi(struct pt_regs *regs) +__visible void __irq_entry smp_x86_platform_ipi(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); @@ -315,7 +315,7 @@ __visible void smp_kvm_posted_intr_wakeup_ipi(struct pt_regs *regs) } #endif -__visible void smp_trace_x86_platform_ipi(struct pt_regs *regs) +__visible void __irq_entry smp_trace_x86_platform_ipi(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c index 3512ba607361..275487872be2 100644 --- a/arch/x86/kernel/irq_work.c +++ b/arch/x86/kernel/irq_work.c @@ -9,6 +9,7 @@ #include <linux/hardirq.h> #include <asm/apic.h> #include <asm/trace/irq_vectors.h> +#include <linux/interrupt.h> static inline void __smp_irq_work_interrupt(void) { @@ -16,14 +17,14 @@ static inline void __smp_irq_work_interrupt(void) irq_work_run(); } -__visible void smp_irq_work_interrupt(struct pt_regs *regs) +__visible void __irq_entry smp_irq_work_interrupt(struct pt_regs *regs) { ipi_entering_ack_irq(); __smp_irq_work_interrupt(); exiting_irq(); } -__visible void smp_trace_irq_work_interrupt(struct pt_regs *regs) +__visible void __irq_entry smp_trace_irq_work_interrupt(struct pt_regs *regs) { ipi_entering_ack_irq(); trace_irq_work_entry(IRQ_WORK_VECTOR); diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c index cb9c1ed1d391..f73f475d0573 100644 --- a/arch/x86/kernel/itmt.c +++ b/arch/x86/kernel/itmt.c @@ -132,10 +132,8 @@ int sched_set_itmt_support(void) sysctl_sched_itmt_enabled = 1; - if (sysctl_sched_itmt_enabled) { - x86_topology_update = true; - rebuild_sched_domains(); - } + x86_topology_update = true; + rebuild_sched_domains(); mutex_unlock(&itmt_update_mutex); diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index fc25f698d792..c37bd0f39c70 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -32,8 +32,7 @@ static void bug_at(unsigned char *ip, int line) * Something went wrong. Crash the box, as something could be * corrupting the kernel. */ - pr_warning("Unexpected op at %pS [%p] (%02x %02x %02x %02x %02x) %s:%d\n", - ip, ip, ip[0], ip[1], ip[2], ip[3], ip[4], __FILE__, line); + pr_crit("jump_label: Fatal kernel bug, unexpected op at %pS [%p] (%5ph) %d\n", ip, ip, ip, line); BUG(); } diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index eb3509338ae0..520b8dfe1640 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -745,7 +745,7 @@ __visible __used void *trampoline_handler(struct pt_regs *regs) * will be the real return address, and all the rest will * point to kretprobe_trampoline. */ - hlist_for_each_entry_safe(ri, tmp, head, hlist) { + hlist_for_each_entry(ri, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 36bc66416021..14f65a5f938e 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -589,7 +589,8 @@ out: local_irq_restore(flags); } -__visible bool __kvm_vcpu_is_preempted(int cpu) +#ifdef CONFIG_X86_32 +__visible bool __kvm_vcpu_is_preempted(long cpu) { struct kvm_steal_time *src = &per_cpu(steal_time, cpu); @@ -597,6 +598,29 @@ __visible bool __kvm_vcpu_is_preempted(int cpu) } PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted); +#else + +#include <asm/asm-offsets.h> + +extern bool __raw_callee_save___kvm_vcpu_is_preempted(long); + +/* + * Hand-optimize version for x86-64 to avoid 8 64-bit register saving and + * restoring to/from the stack. + */ +asm( +".pushsection .text;" +".global __raw_callee_save___kvm_vcpu_is_preempted;" +".type __raw_callee_save___kvm_vcpu_is_preempted, @function;" +"__raw_callee_save___kvm_vcpu_is_preempted:" +"movq __per_cpu_offset(,%rdi,8), %rax;" +"cmpb $0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);" +"setne %al;" +"ret;" +".popsection"); + +#endif + /* * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present. */ @@ -620,18 +644,4 @@ void __init kvm_spinlock_init(void) } } -static __init int kvm_spinlock_init_jump(void) -{ - if (!kvm_para_available()) - return 0; - if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) - return 0; - - static_key_slow_inc(¶virt_ticketlocks_enabled); - printk(KERN_INFO "KVM setup paravirtual spinlock\n"); - - return 0; -} -early_initcall(kvm_spinlock_init_jump); - #endif /* CONFIG_PARAVIRT_SPINLOCKS */ diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 2a5cafdf8808..bae6ea6cfb94 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -28,6 +28,7 @@ #include <asm/x86_init.h> #include <asm/reboot.h> +#include <asm/kvmclock.h> static int kvmclock __ro_after_init = 1; static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME; @@ -49,6 +50,7 @@ struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void) { return hv_clock; } +EXPORT_SYMBOL_GPL(pvclock_pvti_cpu0_va); /* * The wallclock is the time of day when we booted. Since then, some time may @@ -107,12 +109,12 @@ static inline void kvm_sched_clock_init(bool stable) { if (!stable) { pv_time_ops.sched_clock = kvm_clock_read; + clear_sched_clock_stable(); return; } kvm_sched_clock_offset = kvm_clock_read(); pv_time_ops.sched_clock = kvm_sched_clock_read; - set_sched_clock_stable(); printk(KERN_INFO "kvm-clock: using sched offset of %llu cycles\n", kvm_sched_clock_offset); @@ -174,13 +176,14 @@ bool kvm_check_and_clear_guest_paused(void) return ret; } -static struct clocksource kvm_clock = { +struct clocksource kvm_clock = { .name = "kvm-clock", .read = kvm_clock_get_cycles, .rating = 400, .mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; +EXPORT_SYMBOL_GPL(kvm_clock); int kvm_register_clock(char *txt) { diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c index 6d4bf812af45..8f2d1c9d43a8 100644 --- a/arch/x86/kernel/paravirt-spinlocks.c +++ b/arch/x86/kernel/paravirt-spinlocks.c @@ -20,7 +20,7 @@ bool pv_is_native_spin_unlock(void) __raw_callee_save___native_queued_spin_unlock; } -__visible bool __native_vcpu_is_preempted(int cpu) +__visible bool __native_vcpu_is_preempted(long cpu) { return false; } @@ -42,6 +42,3 @@ struct pv_lock_ops pv_lock_ops = { #endif /* SMP */ }; EXPORT_SYMBOL(pv_lock_ops); - -struct static_key paravirt_ticketlocks_enabled = STATIC_KEY_INIT_FALSE; -EXPORT_SYMBOL(paravirt_ticketlocks_enabled); diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index a1bfba0f7234..4797e87b0fb6 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -425,6 +425,7 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_init = { .pmd_clear = native_pmd_clear, #endif .set_pud = native_set_pud, + .set_pud_at = native_set_pud_at, .pmd_val = PTE_IDENT, .make_pmd = PTE_IDENT, diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 5d400ba1349d..0c150c06fa5a 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -296,7 +296,7 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, /* were we called with bad_dma_address? */ badend = DMA_ERROR_CODE + (EMERGENCY_PAGES * PAGE_SIZE); - if (unlikely((dma_addr >= DMA_ERROR_CODE) && (dma_addr < badend))) { + if (unlikely(dma_addr < badend)) { WARN(1, KERN_ERR "Calgary: driver tried unmapping bad DMA " "address 0x%Lx\n", dma_addr); return; @@ -478,7 +478,7 @@ static void calgary_free_coherent(struct device *dev, size_t size, free_pages((unsigned long)vaddr, get_order(size)); } -static struct dma_map_ops calgary_dma_ops = { +static const struct dma_map_ops calgary_dma_ops = { .alloc = calgary_alloc_coherent, .free = calgary_free_coherent, .map_sg = calgary_map_sg, @@ -1177,7 +1177,7 @@ static int __init calgary_init(void) tbl = find_iommu_table(&dev->dev); if (translation_enabled(tbl)) - dev->dev.archdata.dma_ops = &calgary_dma_ops; + dev->dev.dma_ops = &calgary_dma_ops; } return ret; @@ -1201,7 +1201,7 @@ error: calgary_disable_translation(dev); calgary_free_bus(dev); pci_dev_put(dev); /* Undo calgary_init_one()'s pci_dev_get() */ - dev->dev.archdata.dma_ops = NULL; + dev->dev.dma_ops = NULL; } while (1); return ret; diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index d30c37750765..3a216ec869cd 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -17,7 +17,7 @@ static int forbid_dac __read_mostly; -struct dma_map_ops *dma_ops = &nommu_dma_ops; +const struct dma_map_ops *dma_ops = &nommu_dma_ops; EXPORT_SYMBOL(dma_ops); static int iommu_sac_force __read_mostly; @@ -91,7 +91,8 @@ again: page = NULL; /* CMA can be used only in the context which permits sleeping */ if (gfpflags_allow_blocking(flag)) { - page = dma_alloc_from_contiguous(dev, count, get_order(size)); + page = dma_alloc_from_contiguous(dev, count, get_order(size), + flag); if (page && page_to_phys(page) + size > dma_mask) { dma_release_from_contiguous(dev, page, count); page = NULL; @@ -214,7 +215,7 @@ early_param("iommu", iommu_setup); int dma_supported(struct device *dev, u64 mask) { - struct dma_map_ops *ops = get_dma_ops(dev); + const struct dma_map_ops *ops = get_dma_ops(dev); #ifdef CONFIG_PCI if (mask > 0xffffffff && forbid_dac > 0) { diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c index 00e71ce396a8..a88952ef371c 100644 --- a/arch/x86/kernel/pci-nommu.c +++ b/arch/x86/kernel/pci-nommu.c @@ -88,7 +88,7 @@ static void nommu_sync_sg_for_device(struct device *dev, flush_write_buffers(); } -struct dma_map_ops nommu_dma_ops = { +const struct dma_map_ops nommu_dma_ops = { .alloc = dma_generic_alloc_coherent, .free = dma_generic_free_coherent, .map_sg = nommu_map_sg, diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index 410efb2c7b80..1e23577e17cf 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -45,7 +45,7 @@ void x86_swiotlb_free_coherent(struct device *dev, size_t size, dma_generic_free_coherent(dev, size, vaddr, dma_addr, attrs); } -static struct dma_map_ops swiotlb_dma_ops = { +static const struct dma_map_ops swiotlb_dma_ops = { .mapping_error = swiotlb_dma_mapping_error, .alloc = x86_swiotlb_alloc_coherent, .free = x86_swiotlb_free_coherent, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index b615a1113f58..7780efa635b9 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -32,6 +32,7 @@ #include <asm/mce.h> #include <asm/vm86.h> #include <asm/switch_to.h> +#include <asm/desc.h> /* * per-CPU TSS segments. Threads are completely 'soft' on Linux, @@ -64,6 +65,9 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = { }; EXPORT_PER_CPU_SYMBOL(cpu_tss); +DEFINE_PER_CPU(bool, need_tr_refresh); +EXPORT_PER_CPU_SYMBOL_GPL(need_tr_refresh); + /* * this gets called so that we can store lazy state into memory and copy the * current task into the new thread. @@ -209,6 +213,12 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, */ memcpy(tss->io_bitmap, next->io_bitmap_ptr, max(prev->io_bitmap_max, next->io_bitmap_max)); + + /* + * Make sure that the TSS limit is correct for the CPU + * to notice the IO bitmap. + */ + refresh_TR(); } else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) { /* * Clear any possible leftover bits: diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index a1114ffff0f5..cab13f75908b 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -552,7 +552,9 @@ static void __init reserve_crashkernel(void) /* 0 means: find the address automatically */ if (crash_base <= 0) { /* - * kexec want bzImage is below CRASH_KERNEL_ADDR_MAX + * Set CRASH_ADDR_LOW_MAX upper bound for crash memory, + * as old kexec-tools loads bzImage below that, unless + * "crashkernel=size[KMG],high" is specified. */ crash_base = memblock_find_in_range(CRASH_ALIGN, high ? CRASH_ADDR_HIGH_MAX @@ -1152,6 +1154,20 @@ void __init setup_arch(char **cmdline_p) /* Allocate bigger log buffer */ setup_log_buf(1); + if (efi_enabled(EFI_BOOT)) { + switch (boot_params.secure_boot) { + case efi_secureboot_mode_disabled: + pr_info("Secure boot disabled\n"); + break; + case efi_secureboot_mode_enabled: + pr_info("Secure boot enabled\n"); + break; + default: + pr_info("Secure boot could not be determined\n"); + break; + } + } + reserve_initrd(); acpi_table_upgrade(); diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 68f8cc222f25..d3c66a15bbde 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -259,7 +259,7 @@ static inline void __smp_reschedule_interrupt(void) scheduler_ipi(); } -__visible void smp_reschedule_interrupt(struct pt_regs *regs) +__visible void __irq_entry smp_reschedule_interrupt(struct pt_regs *regs) { ack_APIC_irq(); __smp_reschedule_interrupt(); @@ -268,7 +268,7 @@ __visible void smp_reschedule_interrupt(struct pt_regs *regs) */ } -__visible void smp_trace_reschedule_interrupt(struct pt_regs *regs) +__visible void __irq_entry smp_trace_reschedule_interrupt(struct pt_regs *regs) { /* * Need to call irq_enter() before calling the trace point. @@ -292,14 +292,15 @@ static inline void __smp_call_function_interrupt(void) inc_irq_stat(irq_call_count); } -__visible void smp_call_function_interrupt(struct pt_regs *regs) +__visible void __irq_entry smp_call_function_interrupt(struct pt_regs *regs) { ipi_entering_ack_irq(); __smp_call_function_interrupt(); exiting_irq(); } -__visible void smp_trace_call_function_interrupt(struct pt_regs *regs) +__visible void __irq_entry +smp_trace_call_function_interrupt(struct pt_regs *regs) { ipi_entering_ack_irq(); trace_call_function_entry(CALL_FUNCTION_VECTOR); @@ -314,14 +315,16 @@ static inline void __smp_call_function_single_interrupt(void) inc_irq_stat(irq_call_count); } -__visible void smp_call_function_single_interrupt(struct pt_regs *regs) +__visible void __irq_entry +smp_call_function_single_interrupt(struct pt_regs *regs) { ipi_entering_ack_irq(); __smp_call_function_single_interrupt(); exiting_irq(); } -__visible void smp_trace_call_function_single_interrupt(struct pt_regs *regs) +__visible void __irq_entry +smp_trace_call_function_single_interrupt(struct pt_regs *regs) { ipi_entering_ack_irq(); trace_call_function_single_entry(CALL_FUNCTION_SINGLE_VECTOR); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 46732dc3b73c..a0d38685f7df 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -433,9 +433,15 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) int cpu1 = c->cpu_index, cpu2 = o->cpu_index; if (c->phys_proc_id == o->phys_proc_id && - per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2) && - c->cpu_core_id == o->cpu_core_id) - return topology_sane(c, o, "smt"); + per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) { + if (c->cpu_core_id == o->cpu_core_id) + return topology_sane(c, o, "smt"); + + if ((c->cu_id != 0xff) && + (o->cu_id != 0xff) && + (c->cu_id == o->cu_id)) + return topology_sane(c, o, "smt"); + } } else if (c->phys_proc_id == o->phys_proc_id && c->cpu_core_id == o->cpu_core_id) { @@ -1341,8 +1347,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) pr_info("CPU0: "); print_cpu_info(&cpu_data(0)); - if (is_uv_system()) - uv_system_init(); + uv_system_init(); set_mtrr_aps_delayed_init(); diff --git a/arch/x86/kernel/test_nx.c b/arch/x86/kernel/test_nx.c deleted file mode 100644 index a3b875c9e6af..000000000000 --- a/arch/x86/kernel/test_nx.c +++ /dev/null @@ -1,173 +0,0 @@ -/* - * test_nx.c: functional test for NX functionality - * - * (C) Copyright 2008 Intel Corporation - * Author: Arjan van de Ven <arjan@linux.intel.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; version 2 - * of the License. - */ -#include <linux/module.h> -#include <linux/sort.h> -#include <linux/slab.h> - -#include <linux/uaccess.h> -#include <asm/asm.h> - -extern int rodata_test_data; - -/* - * This file checks 4 things: - * 1) Check if the stack is not executable - * 2) Check if kmalloc memory is not executable - * 3) Check if the .rodata section is not executable - * 4) Check if the .data section of a module is not executable - * - * To do this, the test code tries to execute memory in stack/kmalloc/etc, - * and then checks if the expected trap happens. - * - * Sadly, this implies having a dynamic exception handling table entry. - * ... which can be done (and will make Rusty cry)... but it can only - * be done in a stand-alone module with only 1 entry total. - * (otherwise we'd have to sort and that's just too messy) - */ - - - -/* - * We want to set up an exception handling point on our stack, - * which means a variable value. This function is rather dirty - * and walks the exception table of the module, looking for a magic - * marker and replaces it with a specific function. - */ -static void fudze_exception_table(void *marker, void *new) -{ - struct module *mod = THIS_MODULE; - struct exception_table_entry *extable; - - /* - * Note: This module has only 1 exception table entry, - * so searching and sorting is not needed. If that changes, - * this would be the place to search and re-sort the exception - * table. - */ - if (mod->num_exentries > 1) { - printk(KERN_ERR "test_nx: too many exception table entries!\n"); - printk(KERN_ERR "test_nx: test results are not reliable.\n"); - return; - } - extable = (struct exception_table_entry *)mod->extable; - extable[0].insn = (unsigned long)new; -} - - -/* - * exception tables get their symbols translated so we need - * to use a fake function to put in there, which we can then - * replace at runtime. - */ -void foo_label(void); - -/* - * returns 0 for not-executable, negative for executable - * - * Note: we cannot allow this function to be inlined, because - * that would give us more than 1 exception table entry. - * This in turn would break the assumptions above. - */ -static noinline int test_address(void *address) -{ - unsigned long result; - - /* Set up an exception table entry for our address */ - fudze_exception_table(&foo_label, address); - result = 1; - asm volatile( - "foo_label:\n" - "0: call *%[fake_code]\n" - "1:\n" - ".section .fixup,\"ax\"\n" - "2: mov %[zero], %[rslt]\n" - " ret\n" - ".previous\n" - _ASM_EXTABLE(0b,2b) - : [rslt] "=r" (result) - : [fake_code] "r" (address), [zero] "r" (0UL), "0" (result) - ); - /* change the exception table back for the next round */ - fudze_exception_table(address, &foo_label); - - if (result) - return -ENODEV; - return 0; -} - -static unsigned char test_data = 0xC3; /* 0xC3 is the opcode for "ret" */ - -static int test_NX(void) -{ - int ret = 0; - /* 0xC3 is the opcode for "ret" */ - char stackcode[] = {0xC3, 0x90, 0 }; - char *heap; - - test_data = 0xC3; - - printk(KERN_INFO "Testing NX protection\n"); - - /* Test 1: check if the stack is not executable */ - if (test_address(&stackcode)) { - printk(KERN_ERR "test_nx: stack was executable\n"); - ret = -ENODEV; - } - - - /* Test 2: Check if the heap is executable */ - heap = kmalloc(64, GFP_KERNEL); - if (!heap) - return -ENOMEM; - heap[0] = 0xC3; /* opcode for "ret" */ - - if (test_address(heap)) { - printk(KERN_ERR "test_nx: heap was executable\n"); - ret = -ENODEV; - } - kfree(heap); - - /* - * The following 2 tests currently fail, this needs to get fixed - * Until then, don't run them to avoid too many people getting scared - * by the error message - */ - - /* Test 3: Check if the .rodata section is executable */ - if (rodata_test_data != 0xC3) { - printk(KERN_ERR "test_nx: .rodata marker has invalid value\n"); - ret = -ENODEV; - } else if (test_address(&rodata_test_data)) { - printk(KERN_ERR "test_nx: .rodata section is executable\n"); - ret = -ENODEV; - } - -#if 0 - /* Test 4: Check if the .data section of a module is executable */ - if (test_address(&test_data)) { - printk(KERN_ERR "test_nx: .data section is executable\n"); - ret = -ENODEV; - } - -#endif - return ret; -} - -static void test_exit(void) -{ -} - -module_init(test_NX); -module_exit(test_exit); -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("Testcase for the NX infrastructure"); -MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>"); diff --git a/arch/x86/kernel/test_rodata.c b/arch/x86/kernel/test_rodata.c deleted file mode 100644 index 222e84e2432e..000000000000 --- a/arch/x86/kernel/test_rodata.c +++ /dev/null @@ -1,75 +0,0 @@ -/* - * test_rodata.c: functional test for mark_rodata_ro function - * - * (C) Copyright 2008 Intel Corporation - * Author: Arjan van de Ven <arjan@linux.intel.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; version 2 - * of the License. - */ -#include <asm/cacheflush.h> -#include <asm/sections.h> -#include <asm/asm.h> - -int rodata_test(void) -{ - unsigned long result; - unsigned long start, end; - - /* test 1: read the value */ - /* If this test fails, some previous testrun has clobbered the state */ - if (!rodata_test_data) { - printk(KERN_ERR "rodata_test: test 1 fails (start data)\n"); - return -ENODEV; - } - - /* test 2: write to the variable; this should fault */ - /* - * If this test fails, we managed to overwrite the data - * - * This is written in assembly to be able to catch the - * exception that is supposed to happen in the correct - * case - */ - - result = 1; - asm volatile( - "0: mov %[zero],(%[rodata_test])\n" - " mov %[zero], %[rslt]\n" - "1:\n" - ".section .fixup,\"ax\"\n" - "2: jmp 1b\n" - ".previous\n" - _ASM_EXTABLE(0b,2b) - : [rslt] "=r" (result) - : [rodata_test] "r" (&rodata_test_data), [zero] "r" (0UL) - ); - - - if (!result) { - printk(KERN_ERR "rodata_test: test data was not read only\n"); - return -ENODEV; - } - - /* test 3: check the value hasn't changed */ - /* If this test fails, we managed to overwrite the data */ - if (!rodata_test_data) { - printk(KERN_ERR "rodata_test: Test 3 fails (end data)\n"); - return -ENODEV; - } - /* test 4: check if the rodata section is 4Kb aligned */ - start = (unsigned long)__start_rodata; - end = (unsigned long)__end_rodata; - if (start & (PAGE_SIZE - 1)) { - printk(KERN_ERR "rodata_test: .rodata is not 4k aligned\n"); - return -ENODEV; - } - if (end & (PAGE_SIZE - 1)) { - printk(KERN_ERR "rodata_test: .rodata end is not 4k aligned\n"); - return -ENODEV; - } - - return 0; -} diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index bf0c6d049080..1dc86ee60a03 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -563,11 +563,9 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) * as we may switch to the interrupt stack. */ debug_stack_usage_inc(); - preempt_disable(); cond_local_irq_enable(regs); do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL); cond_local_irq_disable(regs); - preempt_enable_no_resched(); debug_stack_usage_dec(); exit: ist_exit(regs); @@ -742,14 +740,12 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) debug_stack_usage_inc(); /* It's safe to allow irq's after DR6 has been saved */ - preempt_disable(); cond_local_irq_enable(regs); if (v8086_mode(regs)) { handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, X86_TRAP_DB); cond_local_irq_disable(regs); - preempt_enable_no_resched(); debug_stack_usage_dec(); goto exit; } @@ -769,7 +765,6 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp) send_sigtrap(tsk, regs, error_code, si_code); cond_local_irq_disable(regs); - preempt_enable_no_resched(); debug_stack_usage_dec(); exit: diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index e41af597aed8..2724dc82f992 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1107,6 +1107,16 @@ static u64 read_tsc(struct clocksource *cs) return (u64)rdtsc_ordered(); } +static void tsc_cs_mark_unstable(struct clocksource *cs) +{ + if (tsc_unstable) + return; + tsc_unstable = 1; + clear_sched_clock_stable(); + disable_sched_clock_irqtime(); + pr_info("Marking TSC unstable due to clocksource watchdog\n"); +} + /* * .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc() */ @@ -1119,6 +1129,7 @@ static struct clocksource clocksource_tsc = { CLOCK_SOURCE_MUST_VERIFY, .archdata = { .vclock_mode = VCLOCK_TSC }, .resume = tsc_resume, + .mark_unstable = tsc_cs_mark_unstable, }; void mark_tsc_unstable(char *reason) @@ -1356,6 +1367,9 @@ void __init tsc_init(void) (unsigned long)cpu_khz / 1000, (unsigned long)cpu_khz % 1000); + /* Sanitize TSC ADJUST before cyc2ns gets initialized */ + tsc_store_and_check_tsc_adjust(true); + /* * Secondary CPUs do not run through tsc_init(), so set up * all the scale factors for all CPUs, assuming the same @@ -1386,8 +1400,6 @@ void __init tsc_init(void) if (unsynchronized_tsc()) mark_tsc_unstable("TSCs unsynchronized"); - else - tsc_store_and_check_tsc_adjust(true); check_system_tsc_reliable(); diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index d0db011051a5..728f75378475 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -286,13 +286,6 @@ void check_tsc_sync_source(int cpu) if (unsynchronized_tsc()) return; - if (tsc_clocksource_reliable) { - if (cpu == (nr_cpu_ids-1) || system_state != SYSTEM_BOOTING) - pr_info( - "Skipped synchronization checks as TSC is reliable.\n"); - return; - } - /* * Set the maximum number of test runs to * 1 if the CPU does not provide the TSC_ADJUST MSR @@ -380,14 +373,19 @@ void check_tsc_sync_target(void) int cpus = 2; /* Also aborts if there is no TSC. */ - if (unsynchronized_tsc() || tsc_clocksource_reliable) + if (unsynchronized_tsc()) return; /* * Store, verify and sanitize the TSC adjust register. If * successful skip the test. + * + * The test is also skipped when the TSC is marked reliable. This + * is true for SoCs which have no fallback clocksource. On these + * SoCs the TSC is frequency synchronized, but still the TSC ADJUST + * register might have been wreckaged by the BIOS.. */ - if (tsc_store_and_check_tsc_adjust(false)) { + if (tsc_store_and_check_tsc_adjust(false) || tsc_clocksource_reliable) { atomic_inc(&skip_test); return; } diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index ec5d7545e6dc..0442d98367ae 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -160,11 +160,12 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval) static void mark_screen_rdonly(struct mm_struct *mm) { + struct vm_area_struct *vma; + spinlock_t *ptl; pgd_t *pgd; pud_t *pud; pmd_t *pmd; pte_t *pte; - spinlock_t *ptl; int i; down_write(&mm->mmap_sem); @@ -177,7 +178,7 @@ static void mark_screen_rdonly(struct mm_struct *mm) pmd = pmd_offset(pud, 0xA0000); if (pmd_trans_huge(*pmd)) { - struct vm_area_struct *vma = find_vma(mm, 0xA0000); + vma = find_vma(mm, 0xA0000); split_huge_pmd(vma, pmd, 0xA0000); } if (pmd_none_or_clear_bad(pmd)) diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index e79f15f108a8..ad0118fbce90 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -346,6 +346,7 @@ SECTIONS /DISCARD/ : { *(.eh_frame) *(__func_stack_frame_non_standard) + *(__unreachable) } } |