diff options
Diffstat (limited to 'arch/x86/kernel')
186 files changed, 7427 insertions, 3346 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index a01892bdd61a..81bb565f4497 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Makefile for the linux kernel. # @@ -24,9 +25,9 @@ endif KASAN_SANITIZE_head$(BITS).o := n KASAN_SANITIZE_dumpstack.o := n KASAN_SANITIZE_dumpstack_$(BITS).o := n -KASAN_SANITIZE_stacktrace.o := n +KASAN_SANITIZE_stacktrace.o := n +KASAN_SANITIZE_paravirt.o := n -OBJECT_FILES_NON_STANDARD_head_$(BITS).o := y OBJECT_FILES_NON_STANDARD_relocate_kernel_$(BITS).o := y OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o := y OBJECT_FILES_NON_STANDARD_test_nx.o := y @@ -42,7 +43,7 @@ CFLAGS_irq.o := -I$(src)/../include/asm/trace obj-y := process_$(BITS).o signal.o obj-$(CONFIG_COMPAT) += signal_compat.o -obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o +obj-y += traps.o idt.o irq.o irq_$(BITS).o dumpstack_$(BITS).o obj-y += time.o ioport.o dumpstack.o nmi.o obj-$(CONFIG_MODIFY_LDT_SYSCALL) += ldt.o obj-y += setup.o x86_init.o i8259.o irqinit.o jump_label.o @@ -111,6 +112,7 @@ obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o obj-$(CONFIG_X86_PMEM_LEGACY_DEVICE) += pmem.o +obj-$(CONFIG_EISA) += eisa.o obj-$(CONFIG_PCSPKR_PLATFORM) += pcspeaker.o obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o @@ -125,12 +127,11 @@ obj-$(CONFIG_EFI) += sysfb_efi.o obj-$(CONFIG_PERF_EVENTS) += perf_regs.o obj-$(CONFIG_TRACING) += tracepoint.o obj-$(CONFIG_SCHED_MC_PRIO) += itmt.o +obj-$(CONFIG_X86_INTEL_UMIP) += umip.o -ifdef CONFIG_FRAME_POINTER -obj-y += unwind_frame.o -else -obj-y += unwind_guess.o -endif +obj-$(CONFIG_UNWINDER_ORC) += unwind_orc.o +obj-$(CONFIG_UNWINDER_FRAME_POINTER) += unwind_frame.o +obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o ### # 64 bit specific files diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile index 85a9e17e0dbc..f1bb57b0e41e 100644 --- a/arch/x86/kernel/acpi/Makefile +++ b/arch/x86/kernel/acpi/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 OBJECT_FILES_NON_STANDARD_wakeup_$(BITS).o := y obj-$(CONFIG_ACPI) += boot.o diff --git a/arch/x86/kernel/acpi/apei.c b/arch/x86/kernel/acpi/apei.c index ea3046e0b0cf..bb8d300fecbd 100644 --- a/arch/x86/kernel/acpi/apei.c +++ b/arch/x86/kernel/acpi/apei.c @@ -52,8 +52,3 @@ void arch_apei_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) apei_mce_report_mem_error(sev, mem_err); #endif } - -void arch_apei_flush_tlb_one(unsigned long addr) -{ - __flush_tlb_one(addr); -} diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 7491e73d9253..f4c463df8b08 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -115,24 +115,24 @@ static u32 isa_irq_to_gsi[NR_IRQS_LEGACY] __read_mostly = { #define ACPI_INVALID_GSI INT_MIN /* - * This is just a simple wrapper around early_ioremap(), + * This is just a simple wrapper around early_memremap(), * with sanity checks for phys == 0 and size == 0. */ -char *__init __acpi_map_table(unsigned long phys, unsigned long size) +void __init __iomem *__acpi_map_table(unsigned long phys, unsigned long size) { if (!phys || !size) return NULL; - return early_ioremap(phys, size); + return early_memremap(phys, size); } -void __init __acpi_unmap_table(char *map, unsigned long size) +void __init __acpi_unmap_table(void __iomem *map, unsigned long size) { if (!map || !size) return; - early_iounmap(map, size); + early_memunmap(map, size); } #ifdef CONFIG_X86_LOCAL_APIC @@ -199,8 +199,10 @@ static int __init acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end) { struct acpi_madt_local_x2apic *processor = NULL; +#ifdef CONFIG_X86_X2APIC int apic_id; u8 enabled; +#endif processor = (struct acpi_madt_local_x2apic *)header; @@ -209,9 +211,10 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end) acpi_table_print_madt_entry(header); +#ifdef CONFIG_X86_X2APIC apic_id = processor->local_apic_id; enabled = processor->lapic_flags & ACPI_MADT_ENABLED; -#ifdef CONFIG_X86_X2APIC + /* * We need to register disabled CPU as well to permit * counting disabled CPUs. This allows us to size @@ -339,13 +342,12 @@ acpi_parse_lapic_nmi(struct acpi_subtable_header * header, const unsigned long e #ifdef CONFIG_X86_IO_APIC #define MP_ISA_BUS 0 +static int __init mp_register_ioapic_irq(u8 bus_irq, u8 polarity, + u8 trigger, u32 gsi); + static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi) { - int ioapic; - int pin; - struct mpc_intsrc mp_irq; - /* * Check bus_irq boundary. */ @@ -355,14 +357,6 @@ static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, } /* - * Convert 'gsi' to 'ioapic.pin'. - */ - ioapic = mp_find_ioapic(gsi); - if (ioapic < 0) - return; - pin = mp_find_ioapic_pin(ioapic, gsi); - - /* * TBD: This check is for faulty timer entries, where the override * erroneously sets the trigger to level, resulting in a HUGE * increase of timer interrupts! @@ -370,16 +364,8 @@ static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, if ((bus_irq == 0) && (trigger == 3)) trigger = 1; - mp_irq.type = MP_INTSRC; - mp_irq.irqtype = mp_INT; - mp_irq.irqflag = (trigger << 2) | polarity; - mp_irq.srcbus = MP_ISA_BUS; - mp_irq.srcbusirq = bus_irq; /* IRQ */ - mp_irq.dstapic = mpc_ioapic_id(ioapic); /* APIC ID */ - mp_irq.dstirq = pin; /* INTIN# */ - - mp_save_irq(&mp_irq); - + if (mp_register_ioapic_irq(bus_irq, polarity, trigger, gsi) < 0) + return; /* * Reset default identity mapping if gsi is also an legacy IRQ, * otherwise there will be more than one entry with the same GSI @@ -426,6 +412,34 @@ static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger, return 0; } +static int __init mp_register_ioapic_irq(u8 bus_irq, u8 polarity, + u8 trigger, u32 gsi) +{ + struct mpc_intsrc mp_irq; + int ioapic, pin; + + /* Convert 'gsi' to 'ioapic.pin'(INTIN#) */ + ioapic = mp_find_ioapic(gsi); + if (ioapic < 0) { + pr_warn("Failed to find ioapic for gsi : %u\n", gsi); + return ioapic; + } + + pin = mp_find_ioapic_pin(ioapic, gsi); + + mp_irq.type = MP_INTSRC; + mp_irq.irqtype = mp_INT; + mp_irq.irqflag = (trigger << 2) | polarity; + mp_irq.srcbus = MP_ISA_BUS; + mp_irq.srcbusirq = bus_irq; + mp_irq.dstapic = mpc_ioapic_id(ioapic); + mp_irq.dstirq = pin; + + mp_save_irq(&mp_irq); + + return 0; +} + static int __init acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end) { @@ -470,7 +484,11 @@ static void __init acpi_sci_ioapic_setup(u8 bus_irq, u16 polarity, u16 trigger, if (acpi_sci_flags & ACPI_MADT_POLARITY_MASK) polarity = acpi_sci_flags & ACPI_MADT_POLARITY_MASK; - mp_override_legacy_irq(bus_irq, polarity, trigger, gsi); + if (bus_irq < NR_IRQS_LEGACY) + mp_override_legacy_irq(bus_irq, polarity, trigger, gsi); + else + mp_register_ioapic_irq(bus_irq, polarity, trigger, gsi); + acpi_penalize_sci_irq(bus_irq, trigger, polarity); /* @@ -958,6 +976,11 @@ static int __init acpi_parse_fadt(struct acpi_table_header *table) x86_platform.legacy.rtc = 0; } + if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_VGA) { + pr_debug("ACPI: probing for VGA not safe\n"); + x86_platform.legacy.no_vga = 1; + } + #ifdef CONFIG_X86_PM_TIMER /* detect the location of the ACPI PM Timer */ if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) { @@ -1083,7 +1106,7 @@ static void __init mp_config_acpi_legacy_irqs(void) mp_bus_id_to_type[MP_ISA_BUS] = MP_BUS_ISA; #endif set_bit(MP_ISA_BUS, mp_bus_not_pci); - pr_debug("Bus #%d is ISA\n", MP_ISA_BUS); + pr_debug("Bus #%d is ISA (nIRQs: %d)\n", MP_ISA_BUS, nr_legacy_irqs()); /* * Use the default configuration for the IRQs 0-15. Unless @@ -1370,7 +1393,7 @@ static void __init acpi_reduced_hw_init(void) * If your system is blacklisted here, but you find that acpi=force * works for you, please contact linux-acpi@vger.kernel.org */ -static struct dmi_system_id __initdata acpi_dmi_table[] = { +static const struct dmi_system_id acpi_dmi_table[] __initconst = { /* * Boxes that need ACPI disabled */ @@ -1445,7 +1468,7 @@ static struct dmi_system_id __initdata acpi_dmi_table[] = { }; /* second table for DMI checks that should run after early-quirks */ -static struct dmi_system_id __initdata acpi_dmi_table_late[] = { +static const struct dmi_system_id acpi_dmi_table_late[] __initconst = { /* * HP laptops which use a DSDT reporting as HP/SB400/10000, * which includes some code which overrides all temperature diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index ed014814ea35..7188aea91549 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * sleep.c - x86-specific ACPI sleep support. * diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h index 65c7b606b606..fbb60ca4255c 100644 --- a/arch/x86/kernel/acpi/sleep.h +++ b/arch/x86/kernel/acpi/sleep.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Variables and functions used by the code in sleep.c */ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 32e14d137416..dbaf14d69ebd 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -442,7 +442,6 @@ static void alternatives_smp_lock(const s32 *start, const s32 *end, { const s32 *poff; - mutex_lock(&text_mutex); for (poff = start; poff < end; poff++) { u8 *ptr = (u8 *)poff + *poff; @@ -452,7 +451,6 @@ static void alternatives_smp_lock(const s32 *start, const s32 *end, if (*ptr == 0x3e) text_poke(ptr, ((unsigned char []){0xf0}), 1); } - mutex_unlock(&text_mutex); } static void alternatives_smp_unlock(const s32 *start, const s32 *end, @@ -460,7 +458,6 @@ static void alternatives_smp_unlock(const s32 *start, const s32 *end, { const s32 *poff; - mutex_lock(&text_mutex); for (poff = start; poff < end; poff++) { u8 *ptr = (u8 *)poff + *poff; @@ -470,7 +467,6 @@ static void alternatives_smp_unlock(const s32 *start, const s32 *end, if (*ptr == 0xf0) text_poke(ptr, ((unsigned char []){0x3E}), 1); } - mutex_unlock(&text_mutex); } struct smp_alt_module { @@ -489,8 +485,7 @@ struct smp_alt_module { struct list_head next; }; static LIST_HEAD(smp_alt_modules); -static DEFINE_MUTEX(smp_alt); -static bool uniproc_patched = false; /* protected by smp_alt */ +static bool uniproc_patched = false; /* protected by text_mutex */ void __init_or_module alternatives_smp_module_add(struct module *mod, char *name, @@ -499,7 +494,7 @@ void __init_or_module alternatives_smp_module_add(struct module *mod, { struct smp_alt_module *smp; - mutex_lock(&smp_alt); + mutex_lock(&text_mutex); if (!uniproc_patched) goto unlock; @@ -526,14 +521,14 @@ void __init_or_module alternatives_smp_module_add(struct module *mod, smp_unlock: alternatives_smp_unlock(locks, locks_end, text, text_end); unlock: - mutex_unlock(&smp_alt); + mutex_unlock(&text_mutex); } void __init_or_module alternatives_smp_module_del(struct module *mod) { struct smp_alt_module *item; - mutex_lock(&smp_alt); + mutex_lock(&text_mutex); list_for_each_entry(item, &smp_alt_modules, next) { if (mod != item->mod) continue; @@ -541,7 +536,7 @@ void __init_or_module alternatives_smp_module_del(struct module *mod) kfree(item); break; } - mutex_unlock(&smp_alt); + mutex_unlock(&text_mutex); } void alternatives_enable_smp(void) @@ -551,7 +546,7 @@ void alternatives_enable_smp(void) /* Why bother if there are no other CPUs? */ BUG_ON(num_possible_cpus() == 1); - mutex_lock(&smp_alt); + mutex_lock(&text_mutex); if (uniproc_patched) { pr_info("switching to SMP code\n"); @@ -563,10 +558,13 @@ void alternatives_enable_smp(void) mod->text, mod->text_end); uniproc_patched = false; } - mutex_unlock(&smp_alt); + mutex_unlock(&text_mutex); } -/* Return 1 if the address range is reserved for smp-alternatives */ +/* + * Return 1 if the address range is reserved for SMP-alternatives. + * Must hold text_mutex. + */ int alternatives_text_reserved(void *start, void *end) { struct smp_alt_module *mod; @@ -574,6 +572,8 @@ int alternatives_text_reserved(void *start, void *end) u8 *text_start = start; u8 *text_end = end; + lockdep_assert_held(&text_mutex); + list_for_each_entry(mod, &smp_alt_modules, next) { if (mod->text > text_end || mod->text_end < text_start) continue; @@ -742,7 +742,16 @@ static void *bp_int3_handler, *bp_int3_addr; int poke_int3_handler(struct pt_regs *regs) { - /* bp_patching_in_progress */ + /* + * Having observed our INT3 instruction, we now must observe + * bp_patching_in_progress. + * + * in_progress = TRUE INT3 + * WMB RMB + * write INT3 if (in_progress) + * + * Idem for bp_int3_handler. + */ smp_rmb(); if (likely(!bp_patching_in_progress)) @@ -788,9 +797,8 @@ void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler) bp_int3_addr = (u8 *)addr + sizeof(int3); bp_patching_in_progress = true; /* - * Corresponding read barrier in int3 notifier for - * making sure the in_progress flags is correctly ordered wrt. - * patching + * Corresponding read barrier in int3 notifier for making sure the + * in_progress and handler are correctly ordered wrt. patching. */ smp_wmb(); @@ -815,9 +823,11 @@ void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler) text_poke(addr, opcode, sizeof(int3)); on_each_cpu(do_sync_core, NULL, 1); - + /* + * sync_core() implies an smp_mb() and orders this store against + * the writing of the new instruction. + */ bp_patching_in_progress = false; - smp_wmb(); return addr; } diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 458da8509b75..6db28f17ff28 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -27,6 +27,8 @@ static const struct pci_device_id amd_root_ids[] = { {} }; +#define PCI_DEVICE_ID_AMD_CNB17H_F4 0x1704 + const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) }, @@ -37,6 +39,7 @@ const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) }, {} }; EXPORT_SYMBOL_GPL(amd_nb_misc_ids); @@ -48,6 +51,7 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, {} }; @@ -402,11 +406,48 @@ void amd_flush_garts(void) } EXPORT_SYMBOL_GPL(amd_flush_garts); +static void __fix_erratum_688(void *info) +{ +#define MSR_AMD64_IC_CFG 0xC0011021 + + msr_set_bit(MSR_AMD64_IC_CFG, 3); + msr_set_bit(MSR_AMD64_IC_CFG, 14); +} + +/* Apply erratum 688 fix so machines without a BIOS fix work. */ +static __init void fix_erratum_688(void) +{ + struct pci_dev *F4; + u32 val; + + if (boot_cpu_data.x86 != 0x14) + return; + + if (!amd_northbridges.num) + return; + + F4 = node_to_amd_nb(0)->link; + if (!F4) + return; + + if (pci_read_config_dword(F4, 0x164, &val)) + return; + + if (val & BIT(2)) + return; + + on_each_cpu(__fix_erratum_688, NULL, 0); + + pr_info("x86/cpu/AMD: CPU erratum 688 worked around\n"); +} + static __init int init_amd_nbs(void) { amd_cache_northbridges(); amd_cache_gart(); + fix_erratum_688(); + return 0; } diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index ef2859f9fcce..f5d92bc3b884 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Firmware replacement code. * diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile index 8e63ebdcbd0b..a6fcaf16cdbf 100644 --- a/arch/x86/kernel/apic/Makefile +++ b/arch/x86/kernel/apic/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Makefile for local APIC drivers and for the IO-APIC code # @@ -6,12 +7,11 @@ # In particualr, smp_apic_timer_interrupt() is called in random places. KCOV_INSTRUMENT := n -obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_noop.o ipi.o vector.o +obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_common.o apic_noop.o ipi.o vector.o obj-y += hw_nmi.o obj-$(CONFIG_X86_IO_APIC) += io_apic.o obj-$(CONFIG_PCI_MSI) += msi.o -obj-$(CONFIG_HT_IRQ) += htirq.o obj-$(CONFIG_SMP) += ipi.o ifeq ($(CONFIG_X86_64),y) diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 98b3dd8cf2bf..6e272f3ea984 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -177,8 +177,6 @@ static int disable_apic_timer __initdata; int local_apic_timer_c2_ok; EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok); -int first_system_vector = FIRST_SYSTEM_VECTOR; - /* * Debug level, exported for io_apic.c */ @@ -213,11 +211,7 @@ static inline int lapic_get_version(void) */ static inline int lapic_is_integrated(void) { -#ifdef CONFIG_X86_64 - return 1; -#else return APIC_INTEGRATED(lapic_get_version()); -#endif } /* @@ -300,14 +294,11 @@ int get_physical_broadcast(void) */ int lapic_get_maxlvt(void) { - unsigned int v; - - v = apic_read(APIC_LVR); /* * - we always have APIC integrated on 64bit mode * - 82489DXs do not report # of LVT entries */ - return APIC_INTEGRATED(GET_APIC_VERSION(v)) ? GET_APIC_MAXLVT(v) : 2; + return lapic_is_integrated() ? GET_APIC_MAXLVT(apic_read(APIC_LVR)) : 2; } /* @@ -575,11 +566,21 @@ static u32 bdx_deadline_rev(void) return ~0U; } +static u32 skx_deadline_rev(void) +{ + switch (boot_cpu_data.x86_mask) { + case 0x03: return 0x01000136; + case 0x04: return 0x02000014; + } + + return ~0U; +} + static const struct x86_cpu_id deadline_match[] = { DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_HASWELL_X, hsx_deadline_rev), DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_X, 0x0b000020), DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_BROADWELL_XEON_D, bdx_deadline_rev), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE_X, 0x02000014), + DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_SKYLAKE_X, skx_deadline_rev), DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_CORE, 0x22), DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_ULT, 0x20), @@ -599,9 +600,14 @@ static const struct x86_cpu_id deadline_match[] = { static void apic_check_deadline_errata(void) { - const struct x86_cpu_id *m = x86_match_cpu(deadline_match); + const struct x86_cpu_id *m; u32 rev; + if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER) || + boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return; + + m = x86_match_cpu(deadline_match); if (!m) return; @@ -990,8 +996,7 @@ void setup_secondary_APIC_clock(void) */ static void local_apic_timer_interrupt(void) { - int cpu = smp_processor_id(); - struct clock_event_device *evt = &per_cpu(lapic_events, cpu); + struct clock_event_device *evt = this_cpu_ptr(&lapic_events); /* * Normally we should not be here till LAPIC has been initialized but @@ -1005,7 +1010,8 @@ static void local_apic_timer_interrupt(void) * spurious. */ if (!evt->event_handler) { - pr_warning("Spurious LAPIC timer interrupt on cpu %d\n", cpu); + pr_warning("Spurious LAPIC timer interrupt on cpu %d\n", + smp_processor_id()); /* Switch it off */ lapic_timer_shutdown(evt); return; @@ -1040,25 +1046,6 @@ __visible void __irq_entry smp_apic_timer_interrupt(struct pt_regs *regs) * interrupt lock, which is the WrongThing (tm) to do. */ entering_ack_irq(); - local_apic_timer_interrupt(); - exiting_irq(); - - set_irq_regs(old_regs); -} - -__visible void __irq_entry smp_trace_apic_timer_interrupt(struct pt_regs *regs) -{ - struct pt_regs *old_regs = set_irq_regs(regs); - - /* - * NOTE! We'd better ACK the irq immediately, - * because timer handling can be slow. - * - * update_process_times() expects us to have done irq_enter(). - * Besides, if we don't timer interrupts ignore the global - * interrupt lock, which is the WrongThing (tm) to do. - */ - entering_ack_irq(); trace_local_timer_entry(LOCAL_TIMER_VECTOR); local_apic_timer_interrupt(); trace_local_timer_exit(LOCAL_TIMER_VECTOR); @@ -1235,53 +1222,100 @@ void __init sync_Arb_IDs(void) APIC_INT_LEVELTRIG | APIC_DM_INIT); } -/* - * An initial setup of the virtual wire mode. - */ -void __init init_bsp_APIC(void) +enum apic_intr_mode_id apic_intr_mode; + +static int __init apic_intr_mode_select(void) { - unsigned int value; + /* Check kernel option */ + if (disable_apic) { + pr_info("APIC disabled via kernel command line\n"); + return APIC_PIC; + } - /* - * Don't do the setup now if we have a SMP BIOS as the - * through-I/O-APIC virtual wire mode might be active. - */ - if (smp_found_config || !boot_cpu_has(X86_FEATURE_APIC)) - return; + /* Check BIOS */ +#ifdef CONFIG_X86_64 + /* On 64-bit, the APIC must be integrated, Check local APIC only */ + if (!boot_cpu_has(X86_FEATURE_APIC)) { + disable_apic = 1; + pr_info("APIC disabled by BIOS\n"); + return APIC_PIC; + } +#else + /* On 32-bit, the APIC may be integrated APIC or 82489DX */ - /* - * Do not trust the local APIC being empty at bootup. - */ - clear_local_APIC(); + /* Neither 82489DX nor integrated APIC ? */ + if (!boot_cpu_has(X86_FEATURE_APIC) && !smp_found_config) { + disable_apic = 1; + return APIC_PIC; + } - /* - * Enable APIC. - */ - value = apic_read(APIC_SPIV); - value &= ~APIC_VECTOR_MASK; - value |= APIC_SPIV_APIC_ENABLED; + /* If the BIOS pretends there is an integrated APIC ? */ + if (!boot_cpu_has(X86_FEATURE_APIC) && + APIC_INTEGRATED(boot_cpu_apic_version)) { + disable_apic = 1; + pr_err(FW_BUG "Local APIC %d not detected, force emulation\n", + boot_cpu_physical_apicid); + return APIC_PIC; + } +#endif -#ifdef CONFIG_X86_32 - /* This bit is reserved on P4/Xeon and should be cleared */ - if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && - (boot_cpu_data.x86 == 15)) - value &= ~APIC_SPIV_FOCUS_DISABLED; - else + /* Check MP table or ACPI MADT configuration */ + if (!smp_found_config) { + disable_ioapic_support(); + if (!acpi_lapic) { + pr_info("APIC: ACPI MADT or MP tables are not detected\n"); + return APIC_VIRTUAL_WIRE_NO_CONFIG; + } + return APIC_VIRTUAL_WIRE; + } + +#ifdef CONFIG_SMP + /* If SMP should be disabled, then really disable it! */ + if (!setup_max_cpus) { + pr_info("APIC: SMP mode deactivated\n"); + return APIC_SYMMETRIC_IO_NO_ROUTING; + } + + if (read_apic_id() != boot_cpu_physical_apicid) { + panic("Boot APIC ID in local APIC unexpected (%d vs %d)", + read_apic_id(), boot_cpu_physical_apicid); + /* Or can we switch back to PIC here? */ + } #endif - value |= APIC_SPIV_FOCUS_DISABLED; - value |= SPURIOUS_APIC_VECTOR; - apic_write(APIC_SPIV, value); - /* - * Set up the virtual wire mode. - */ - apic_write(APIC_LVT0, APIC_DM_EXTINT); - value = APIC_DM_NMI; - if (!lapic_is_integrated()) /* 82489DX */ - value |= APIC_LVT_LEVEL_TRIGGER; - if (apic_extnmi == APIC_EXTNMI_NONE) - value |= APIC_LVT_MASKED; - apic_write(APIC_LVT1, value); + return APIC_SYMMETRIC_IO; +} + +/* Init the interrupt delivery mode for the BSP */ +void __init apic_intr_mode_init(void) +{ + bool upmode = IS_ENABLED(CONFIG_UP_LATE_INIT); + + apic_intr_mode = apic_intr_mode_select(); + + switch (apic_intr_mode) { + case APIC_PIC: + pr_info("APIC: Keep in PIC mode(8259)\n"); + return; + case APIC_VIRTUAL_WIRE: + pr_info("APIC: Switch to virtual wire mode setup\n"); + default_setup_apic_routing(); + break; + case APIC_VIRTUAL_WIRE_NO_CONFIG: + pr_info("APIC: Switch to virtual wire mode setup with no configuration\n"); + upmode = true; + default_setup_apic_routing(); + break; + case APIC_SYMMETRIC_IO: + pr_info("APIC: Switch to symmetric I/O mode setup\n"); + default_setup_apic_routing(); + break; + case APIC_SYMMETRIC_IO_NO_ROUTING: + pr_info("APIC: Switch to symmetric I/O mode setup in no SMP routine\n"); + break; + } + + apic_bsp_setup(upmode); } static void lapic_setup_esr(void) @@ -1479,7 +1513,7 @@ void setup_local_APIC(void) /* * Set up LVT0, LVT1: * - * set up through-local-APIC on the BP's LINT0. This is not + * set up through-local-APIC on the boot CPU's LINT0. This is not * strictly necessary in pure symmetric-IO mode, but sometimes * we delegate interrupts to the 8259A. */ @@ -1505,7 +1539,9 @@ void setup_local_APIC(void) value = APIC_DM_NMI; else value = APIC_DM_NMI | APIC_LVT_MASKED; - if (!lapic_is_integrated()) /* 82489DX */ + + /* Is 82489DX ? */ + if (!lapic_is_integrated()) value |= APIC_LVT_LEVEL_TRIGGER; apic_write(APIC_LVT1, value); @@ -1651,7 +1687,7 @@ static __init void try_to_enable_x2apic(int remap_mode) * under KVM */ if (max_physical_apicid > 255 || - !hypervisor_x2apic_available()) { + !x86_init.hyper.x2apic_available()) { pr_info("x2apic: IRQ remapping doesn't support X2APIC mode\n"); x2apic_disable(); return; @@ -1891,8 +1927,8 @@ void __init init_apic_mappings(void) * yeah -- we lie about apic_version * in case if apic was disabled via boot option * but it's not a problem for SMP compiled kernel - * since smp_sanity_check is prepared for such a case - * and disable smp mode + * since apic_intr_mode_select is prepared for such + * a case and disable smp mode */ boot_cpu_apic_version = GET_APIC_VERSION(apic_read(APIC_LVR)); } @@ -1920,10 +1956,14 @@ void __init register_lapic_address(unsigned long address) /* * This interrupt should _never_ happen with our APIC/SMP architecture */ -static void __smp_spurious_interrupt(u8 vector) +__visible void __irq_entry smp_spurious_interrupt(struct pt_regs *regs) { + u8 vector = ~regs->orig_ax; u32 v; + entering_irq(); + trace_spurious_apic_entry(vector); + /* * Check if this really is a spurious interrupt and ACK it * if it is a vectored one. Just in case... @@ -1938,22 +1978,7 @@ static void __smp_spurious_interrupt(u8 vector) /* see sw-dev-man vol 3, chapter 7.4.13.5 */ pr_info("spurious APIC interrupt through vector %02x on CPU#%d, " "should never happen.\n", vector, smp_processor_id()); -} - -__visible void __irq_entry smp_spurious_interrupt(struct pt_regs *regs) -{ - entering_irq(); - __smp_spurious_interrupt(~regs->orig_ax); - exiting_irq(); -} -__visible void __irq_entry smp_trace_spurious_interrupt(struct pt_regs *regs) -{ - u8 vector = ~regs->orig_ax; - - entering_irq(); - trace_spurious_apic_entry(vector); - __smp_spurious_interrupt(vector); trace_spurious_apic_exit(vector); exiting_irq(); } @@ -1961,10 +1986,8 @@ __visible void __irq_entry smp_trace_spurious_interrupt(struct pt_regs *regs) /* * This interrupt should never happen with our APIC/SMP architecture */ -static void __smp_error_interrupt(struct pt_regs *regs) +__visible void __irq_entry smp_error_interrupt(struct pt_regs *regs) { - u32 v; - u32 i = 0; static const char * const error_interrupt_reason[] = { "Send CS error", /* APIC Error Bit 0 */ "Receive CS error", /* APIC Error Bit 1 */ @@ -1975,6 +1998,10 @@ static void __smp_error_interrupt(struct pt_regs *regs) "Received illegal vector", /* APIC Error Bit 6 */ "Illegal register address", /* APIC Error Bit 7 */ }; + u32 v, i = 0; + + entering_irq(); + trace_error_apic_entry(ERROR_APIC_VECTOR); /* First tickle the hardware, only then report what went on. -- REW */ if (lapic_get_maxlvt() > 3) /* Due to the Pentium erratum 3AP. */ @@ -1996,20 +2023,6 @@ static void __smp_error_interrupt(struct pt_regs *regs) apic_printk(APIC_DEBUG, KERN_CONT "\n"); -} - -__visible void __irq_entry smp_error_interrupt(struct pt_regs *regs) -{ - entering_irq(); - __smp_error_interrupt(regs); - exiting_irq(); -} - -__visible void __irq_entry smp_trace_error_interrupt(struct pt_regs *regs) -{ - entering_irq(); - trace_error_apic_entry(ERROR_APIC_VECTOR); - __smp_error_interrupt(regs); trace_error_apic_exit(ERROR_APIC_VECTOR); exiting_irq(); } @@ -2137,7 +2150,7 @@ static int allocate_logical_cpuid(int apicid) /* Allocate a new cpuid. */ if (nr_logical_cpuids >= nr_cpu_ids) { - WARN_ONCE(1, "APIC: NR_CPUS/possible_cpus limit of %i reached. " + WARN_ONCE(1, "APIC: NR_CPUS/possible_cpus limit of %u reached. " "Processor %d/0x%x and the rest are ignored.\n", nr_cpu_ids, nr_logical_cpuids, apicid); return -EINVAL; @@ -2170,7 +2183,7 @@ int generic_processor_info(int apicid, int version) * 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() && @@ -2271,44 +2284,6 @@ int hard_smp_processor_id(void) return read_apic_id(); } -void default_init_apic_ldr(void) -{ - unsigned long val; - - apic_write(APIC_DFR, APIC_DFR_VALUE); - val = apic_read(APIC_LDR) & ~APIC_LDR_MASK; - val |= SET_APIC_LOGICAL_ID(1UL << smp_processor_id()); - apic_write(APIC_LDR, val); -} - -int default_cpu_mask_to_apicid(const struct cpumask *mask, - struct irq_data *irqdata, - unsigned int *apicid) -{ - unsigned int cpu = cpumask_first(mask); - - if (cpu >= nr_cpu_ids) - return -EINVAL; - *apicid = per_cpu(x86_cpu_to_apicid, cpu); - irq_data_update_effective_affinity(irqdata, cpumask_of(cpu)); - return 0; -} - -int flat_cpu_mask_to_apicid(const struct cpumask *mask, - struct irq_data *irqdata, - unsigned int *apicid) - -{ - struct cpumask *effmsk = irq_data_get_effective_affinity_mask(irqdata); - unsigned long cpu_mask = cpumask_bits(mask)[0] & APIC_ALL_CPUS; - - if (!cpu_mask) - return -EINVAL; - *apicid = (unsigned int)cpu_mask; - cpumask_bits(effmsk)[0] = cpu_mask; - return 0; -} - /* * Override the generic EOI implementation with an optimized version. * Only called during early boot when only one CPU is active and with @@ -2351,72 +2326,27 @@ static void __init apic_bsp_up_setup(void) * Returns: * apic_id of BSP APIC */ -int __init apic_bsp_setup(bool upmode) +void __init apic_bsp_setup(bool upmode) { - int id; - connect_bsp_APIC(); if (upmode) apic_bsp_up_setup(); setup_local_APIC(); - if (x2apic_mode) - id = apic_read(APIC_LDR); - else - id = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); - enable_IO_APIC(); end_local_APIC_setup(); irq_remap_enable_fault_handling(); setup_IO_APIC(); - /* Setup local timer */ - x86_init.timers.setup_percpu_clockev(); - return id; -} - -/* - * This initializes the IO-APIC and APIC hardware if this is - * a UP kernel. - */ -int __init APIC_init_uniprocessor(void) -{ - if (disable_apic) { - pr_info("Apic disabled\n"); - return -1; - } -#ifdef CONFIG_X86_64 - if (!boot_cpu_has(X86_FEATURE_APIC)) { - disable_apic = 1; - pr_info("Apic disabled by BIOS\n"); - return -1; - } -#else - if (!smp_found_config && !boot_cpu_has(X86_FEATURE_APIC)) - return -1; - - /* - * Complain if the BIOS pretends there is one. - */ - if (!boot_cpu_has(X86_FEATURE_APIC) && - APIC_INTEGRATED(boot_cpu_apic_version)) { - pr_err("BIOS bug, local APIC 0x%x not detected!...\n", - boot_cpu_physical_apicid); - return -1; - } -#endif - - if (!smp_found_config) - disable_ioapic_support(); - - default_setup_apic_routing(); - apic_bsp_setup(true); - return 0; } #ifdef CONFIG_UP_LATE_INIT void __init up_late_init(void) { - APIC_init_uniprocessor(); + if (apic_intr_mode == APIC_PIC) + return; + + /* Setup local timer */ + x86_init.timers.setup_percpu_clockev(); } #endif diff --git a/arch/x86/kernel/apic/apic_common.c b/arch/x86/kernel/apic/apic_common.c new file mode 100644 index 000000000000..a360801779ae --- /dev/null +++ b/arch/x86/kernel/apic/apic_common.c @@ -0,0 +1,46 @@ +/* + * Common functions shared between the various APIC flavours + * + * SPDX-License-Identifier: GPL-2.0 + */ +#include <linux/irq.h> +#include <asm/apic.h> + +u32 apic_default_calc_apicid(unsigned int cpu) +{ + return per_cpu(x86_cpu_to_apicid, cpu); +} + +u32 apic_flat_calc_apicid(unsigned int cpu) +{ + return 1U << cpu; +} + +bool default_check_apicid_used(physid_mask_t *map, int apicid) +{ + return physid_isset(apicid, *map); +} + +void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap) +{ + *retmap = *phys_map; +} + +int default_cpu_present_to_apicid(int mps_cpu) +{ + if (mps_cpu < nr_cpu_ids && cpu_present(mps_cpu)) + return (int)per_cpu(x86_bios_cpu_apicid, mps_cpu); + else + return BAD_APICID; +} +EXPORT_SYMBOL_GPL(default_cpu_present_to_apicid); + +int default_check_phys_apicid_present(int phys_apicid) +{ + return physid_isset(phys_apicid, phys_cpu_present_map); +} + +int default_apic_id_valid(int apicid) +{ + return (apicid < 255); +} diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index dedd5a41ba48..aa85690e9b64 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -119,7 +119,7 @@ static unsigned int flat_get_apic_id(unsigned long x) return (x >> 24) & 0xFF; } -static unsigned long set_apic_id(unsigned int id) +static u32 set_apic_id(unsigned int id) { return (id & 0xFF) << 24; } @@ -154,12 +154,10 @@ static struct apic apic_flat __ro_after_init = { .irq_delivery_mode = dest_LowestPrio, .irq_dest_mode = 1, /* logical */ - .target_cpus = online_target_cpus, .disable_esr = 0, .dest_logical = APIC_DEST_LOGICAL, .check_apicid_used = NULL, - .vector_allocation_domain = flat_vector_allocation_domain, .init_apic_ldr = flat_init_apic_ldr, .ioapic_phys_id_map = NULL, @@ -172,7 +170,7 @@ static struct apic apic_flat __ro_after_init = { .get_apic_id = flat_get_apic_id, .set_apic_id = set_apic_id, - .cpu_mask_to_apicid = flat_cpu_mask_to_apicid, + .calc_dest_apicid = apic_flat_calc_apicid, .send_IPI = default_send_IPI_single, .send_IPI_mask = flat_send_IPI_mask, @@ -249,12 +247,10 @@ static struct apic apic_physflat __ro_after_init = { .irq_delivery_mode = dest_Fixed, .irq_dest_mode = 0, /* physical */ - .target_cpus = online_target_cpus, .disable_esr = 0, .dest_logical = 0, .check_apicid_used = NULL, - .vector_allocation_domain = default_vector_allocation_domain, /* not needed, but shouldn't hurt: */ .init_apic_ldr = flat_init_apic_ldr, @@ -268,7 +264,7 @@ static struct apic apic_physflat __ro_after_init = { .get_apic_id = flat_get_apic_id, .set_apic_id = set_apic_id, - .cpu_mask_to_apicid = default_cpu_mask_to_apicid, + .calc_dest_apicid = apic_default_calc_apicid, .send_IPI = default_send_IPI_single_phys, .send_IPI_mask = default_send_IPI_mask_sequence_phys, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index 6599f437b4ab..7b659c4480c9 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * NOOP APIC driver. * @@ -83,20 +84,6 @@ static int noop_apic_id_registered(void) return physid_isset(0, phys_cpu_present_map); } -static const struct cpumask *noop_target_cpus(void) -{ - /* only BSP here */ - return cpumask_of(0); -} - -static void noop_vector_allocation_domain(int cpu, struct cpumask *retmask, - const struct cpumask *mask) -{ - if (cpu != 0) - pr_warning("APIC: Vector allocated for non-BSP cpu\n"); - cpumask_copy(retmask, cpumask_of(cpu)); -} - static u32 noop_apic_read(u32 reg) { WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_APIC) && !disable_apic); @@ -108,6 +95,13 @@ static void noop_apic_write(u32 reg, u32 v) WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_APIC) && !disable_apic); } +#ifdef CONFIG_X86_32 +static int noop_x86_32_early_logical_apicid(int cpu) +{ + return BAD_APICID; +} +#endif + struct apic apic_noop __ro_after_init = { .name = "noop", .probe = noop_probe, @@ -120,12 +114,10 @@ struct apic apic_noop __ro_after_init = { /* logical delivery broadcast to all CPUs: */ .irq_dest_mode = 1, - .target_cpus = noop_target_cpus, .disable_esr = 0, .dest_logical = APIC_DEST_LOGICAL, .check_apicid_used = default_check_apicid_used, - .vector_allocation_domain = noop_vector_allocation_domain, .init_apic_ldr = noop_init_apic_ldr, .ioapic_phys_id_map = default_ioapic_phys_id_map, @@ -141,7 +133,7 @@ struct apic apic_noop __ro_after_init = { .get_apic_id = noop_get_apic_id, .set_apic_id = NULL, - .cpu_mask_to_apicid = flat_cpu_mask_to_apicid, + .calc_dest_apicid = apic_flat_calc_apicid, .send_IPI = noop_send_IPI, .send_IPI_mask = noop_send_IPI_mask, diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index 2fda912219a6..134e04506ab4 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -38,7 +38,7 @@ static unsigned int numachip1_get_apic_id(unsigned long x) return id; } -static unsigned long numachip1_set_apic_id(unsigned int id) +static u32 numachip1_set_apic_id(unsigned int id) { return (id & 0xff) << 24; } @@ -51,7 +51,7 @@ static unsigned int numachip2_get_apic_id(unsigned long x) return ((mcfg >> (28 - 8)) & 0xfff00) | (x >> 24); } -static unsigned long numachip2_set_apic_id(unsigned int id) +static u32 numachip2_set_apic_id(unsigned int id) { return id << 24; } @@ -249,12 +249,10 @@ static const struct apic apic_numachip1 __refconst = { .irq_delivery_mode = dest_Fixed, .irq_dest_mode = 0, /* physical */ - .target_cpus = online_target_cpus, .disable_esr = 0, .dest_logical = 0, .check_apicid_used = NULL, - .vector_allocation_domain = default_vector_allocation_domain, .init_apic_ldr = flat_init_apic_ldr, .ioapic_phys_id_map = NULL, @@ -267,7 +265,7 @@ static const struct apic apic_numachip1 __refconst = { .get_apic_id = numachip1_get_apic_id, .set_apic_id = numachip1_set_apic_id, - .cpu_mask_to_apicid = default_cpu_mask_to_apicid, + .calc_dest_apicid = apic_default_calc_apicid, .send_IPI = numachip_send_IPI_one, .send_IPI_mask = numachip_send_IPI_mask, @@ -300,12 +298,10 @@ static const struct apic apic_numachip2 __refconst = { .irq_delivery_mode = dest_Fixed, .irq_dest_mode = 0, /* physical */ - .target_cpus = online_target_cpus, .disable_esr = 0, .dest_logical = 0, .check_apicid_used = NULL, - .vector_allocation_domain = default_vector_allocation_domain, .init_apic_ldr = flat_init_apic_ldr, .ioapic_phys_id_map = NULL, @@ -318,7 +314,7 @@ static const struct apic apic_numachip2 __refconst = { .get_apic_id = numachip2_get_apic_id, .set_apic_id = numachip2_set_apic_id, - .cpu_mask_to_apicid = default_cpu_mask_to_apicid, + .calc_dest_apicid = apic_default_calc_apicid, .send_IPI = numachip_send_IPI_one, .send_IPI_mask = numachip_send_IPI_mask, diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 456e45e8bf84..afee386ff711 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * APIC driver for "bigsmp" xAPIC machines with more than 8 virtual CPUs. * @@ -26,9 +27,9 @@ static int bigsmp_apic_id_registered(void) return 1; } -static unsigned long bigsmp_check_apicid_used(physid_mask_t *map, int apicid) +static bool bigsmp_check_apicid_used(physid_mask_t *map, int apicid) { - return 0; + return false; } static int bigsmp_early_logical_apicid(int cpu) @@ -154,12 +155,10 @@ static struct apic apic_bigsmp __ro_after_init = { /* phys delivery to target CPU: */ .irq_dest_mode = 0, - .target_cpus = default_target_cpus, .disable_esr = 1, .dest_logical = 0, .check_apicid_used = bigsmp_check_apicid_used, - .vector_allocation_domain = default_vector_allocation_domain, .init_apic_ldr = bigsmp_init_apic_ldr, .ioapic_phys_id_map = bigsmp_ioapic_phys_id_map, @@ -172,7 +171,7 @@ static struct apic apic_bigsmp __ro_after_init = { .get_apic_id = bigsmp_get_apic_id, .set_apic_id = NULL, - .cpu_mask_to_apicid = default_cpu_mask_to_apicid, + .calc_dest_apicid = apic_default_calc_apicid, .send_IPI = default_send_IPI_single_phys, .send_IPI_mask = default_send_IPI_mask_sequence_phys, diff --git a/arch/x86/kernel/apic/htirq.c b/arch/x86/kernel/apic/htirq.c deleted file mode 100644 index 56ccf9346b08..000000000000 --- a/arch/x86/kernel/apic/htirq.c +++ /dev/null @@ -1,197 +0,0 @@ -/* - * Support Hypertransport IRQ - * - * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo - * Moved from arch/x86/kernel/apic/io_apic.c. - * Jiang Liu <jiang.liu@linux.intel.com> - * Add support of hierarchical irqdomain - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#include <linux/mm.h> -#include <linux/interrupt.h> -#include <linux/init.h> -#include <linux/device.h> -#include <linux/pci.h> -#include <linux/htirq.h> -#include <asm/irqdomain.h> -#include <asm/hw_irq.h> -#include <asm/apic.h> -#include <asm/hypertransport.h> - -static struct irq_domain *htirq_domain; - -/* - * Hypertransport interrupt support - */ -static int -ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) -{ - struct irq_data *parent = data->parent_data; - int ret; - - ret = parent->chip->irq_set_affinity(parent, mask, force); - if (ret >= 0) { - struct ht_irq_msg msg; - struct irq_cfg *cfg = irqd_cfg(data); - - fetch_ht_irq_msg(data->irq, &msg); - msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK | - HT_IRQ_LOW_DEST_ID_MASK); - msg.address_lo |= HT_IRQ_LOW_VECTOR(cfg->vector) | - HT_IRQ_LOW_DEST_ID(cfg->dest_apicid); - msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK); - msg.address_hi |= HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid); - write_ht_irq_msg(data->irq, &msg); - } - - return ret; -} - -static struct irq_chip ht_irq_chip = { - .name = "PCI-HT", - .irq_mask = mask_ht_irq, - .irq_unmask = unmask_ht_irq, - .irq_ack = irq_chip_ack_parent, - .irq_set_affinity = ht_set_affinity, - .irq_retrigger = irq_chip_retrigger_hierarchy, - .flags = IRQCHIP_SKIP_SET_WAKE, -}; - -static int htirq_domain_alloc(struct irq_domain *domain, unsigned int virq, - unsigned int nr_irqs, void *arg) -{ - struct ht_irq_cfg *ht_cfg; - struct irq_alloc_info *info = arg; - struct pci_dev *dev; - irq_hw_number_t hwirq; - int ret; - - if (nr_irqs > 1 || !info) - return -EINVAL; - - dev = info->ht_dev; - hwirq = (info->ht_idx & 0xFF) | - PCI_DEVID(dev->bus->number, dev->devfn) << 8 | - (pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 24; - if (irq_find_mapping(domain, hwirq) > 0) - return -EEXIST; - - ht_cfg = kmalloc(sizeof(*ht_cfg), GFP_KERNEL); - if (!ht_cfg) - return -ENOMEM; - - ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info); - if (ret < 0) { - kfree(ht_cfg); - return ret; - } - - /* Initialize msg to a value that will never match the first write. */ - ht_cfg->msg.address_lo = 0xffffffff; - ht_cfg->msg.address_hi = 0xffffffff; - ht_cfg->dev = info->ht_dev; - ht_cfg->update = info->ht_update; - ht_cfg->pos = info->ht_pos; - ht_cfg->idx = 0x10 + (info->ht_idx * 2); - irq_domain_set_info(domain, virq, hwirq, &ht_irq_chip, ht_cfg, - handle_edge_irq, ht_cfg, "edge"); - - return 0; -} - -static void htirq_domain_free(struct irq_domain *domain, unsigned int virq, - unsigned int nr_irqs) -{ - struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq); - - BUG_ON(nr_irqs != 1); - kfree(irq_data->chip_data); - irq_domain_free_irqs_top(domain, virq, nr_irqs); -} - -static void htirq_domain_activate(struct irq_domain *domain, - struct irq_data *irq_data) -{ - struct ht_irq_msg msg; - struct irq_cfg *cfg = irqd_cfg(irq_data); - - msg.address_hi = HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid); - msg.address_lo = - HT_IRQ_LOW_BASE | - HT_IRQ_LOW_DEST_ID(cfg->dest_apicid) | - HT_IRQ_LOW_VECTOR(cfg->vector) | - ((apic->irq_dest_mode == 0) ? - HT_IRQ_LOW_DM_PHYSICAL : - HT_IRQ_LOW_DM_LOGICAL) | - HT_IRQ_LOW_RQEOI_EDGE | - ((apic->irq_delivery_mode != dest_LowestPrio) ? - HT_IRQ_LOW_MT_FIXED : - HT_IRQ_LOW_MT_ARBITRATED) | - HT_IRQ_LOW_IRQ_MASKED; - write_ht_irq_msg(irq_data->irq, &msg); -} - -static void htirq_domain_deactivate(struct irq_domain *domain, - struct irq_data *irq_data) -{ - struct ht_irq_msg msg; - - memset(&msg, 0, sizeof(msg)); - write_ht_irq_msg(irq_data->irq, &msg); -} - -static const struct irq_domain_ops htirq_domain_ops = { - .alloc = htirq_domain_alloc, - .free = htirq_domain_free, - .activate = htirq_domain_activate, - .deactivate = htirq_domain_deactivate, -}; - -void __init arch_init_htirq_domain(struct irq_domain *parent) -{ - struct fwnode_handle *fn; - - if (disable_apic) - return; - - fn = irq_domain_alloc_named_fwnode("PCI-HT"); - if (!fn) - goto warn; - - htirq_domain = irq_domain_create_tree(fn, &htirq_domain_ops, NULL); - irq_domain_free_fwnode(fn); - if (!htirq_domain) - goto warn; - - htirq_domain->parent = parent; - return; - -warn: - pr_warn("Failed to initialize irqdomain for HTIRQ.\n"); -} - -int arch_setup_ht_irq(int idx, int pos, struct pci_dev *dev, - ht_irq_update_t *update) -{ - struct irq_alloc_info info; - - if (!htirq_domain) - return -ENOSYS; - - init_irq_alloc_info(&info, NULL); - info.ht_idx = idx; - info.ht_pos = pos; - info.ht_dev = dev; - info.ht_update = update; - - return irq_domain_alloc_irqs(htirq_domain, 1, dev_to_node(&dev->dev), - &info); -} - -void arch_teardown_ht_irq(unsigned int irq) -{ - irq_domain_free_irqs(irq, 1); -} diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index d6f387780849..d1fc62a67320 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * HW NMI watchdog support * diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 237e9c2341c7..201579dc5242 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Intel IO-APIC support for multi-Pentium hosts. * @@ -1013,6 +1014,7 @@ static int alloc_isa_irq_from_domain(struct irq_domain *domain, info->ioapic_pin)) return -ENOMEM; } else { + info->flags |= X86_IRQ_ALLOC_LEGACY; irq = __irq_domain_alloc_irqs(domain, irq, 1, node, info, true, NULL); if (irq >= 0) { @@ -1243,7 +1245,7 @@ static void io_apic_print_entries(unsigned int apic, unsigned int nr_entries) entry.vector, entry.irr, entry.delivery_status); if (ir_entry->format) printk(KERN_DEBUG "%s, remapped, I(%04X), Z(%X)\n", - buf, (ir_entry->index << 15) | ir_entry->index, + buf, (ir_entry->index2 << 15) | ir_entry->index, ir_entry->zero); else printk(KERN_DEBUG "%s, %s, D(%02X), M(%1d)\n", @@ -1585,6 +1587,43 @@ static int __init notimercheck(char *s) } __setup("no_timer_check", notimercheck); +static void __init delay_with_tsc(void) +{ + unsigned long long start, now; + unsigned long end = jiffies + 4; + + start = rdtsc(); + + /* + * We don't know the TSC frequency yet, but waiting for + * 40000000000/HZ TSC cycles is safe: + * 4 GHz == 10 jiffies + * 1 GHz == 40 jiffies + */ + do { + rep_nop(); + now = rdtsc(); + } while ((now - start) < 40000000000UL / HZ && + time_before_eq(jiffies, end)); +} + +static void __init delay_without_tsc(void) +{ + unsigned long end = jiffies + 4; + int band = 1; + + /* + * We don't know any frequency yet, but waiting for + * 40940000000/HZ cycles is safe: + * 4 GHz == 10 jiffies + * 1 GHz == 40 jiffies + * 1 << 1 + 1 << 2 +...+ 1 << 11 = 4094 + */ + do { + __delay(((1U << band++) * 10000000UL) / HZ); + } while (band < 12 && time_before_eq(jiffies, end)); +} + /* * There is a nasty bug in some older SMP boards, their mptable lies * about the timer IRQ. We do the following to work around the situation: @@ -1603,8 +1642,12 @@ static int __init timer_irq_works(void) local_save_flags(flags); local_irq_enable(); - /* Let ten ticks pass... */ - mdelay((10 * 1000) / HZ); + + if (boot_cpu_has(X86_FEATURE_TSC)) + delay_with_tsc(); + else + delay_without_tsc(); + local_irq_restore(flags); /* @@ -1820,26 +1863,36 @@ static void ioapic_ir_ack_level(struct irq_data *irq_data) eoi_ioapic_pin(data->entry.vector, data); } +static void ioapic_configure_entry(struct irq_data *irqd) +{ + struct mp_chip_data *mpd = irqd->chip_data; + struct irq_cfg *cfg = irqd_cfg(irqd); + struct irq_pin_list *entry; + + /* + * Only update when the parent is the vector domain, don't touch it + * if the parent is the remapping domain. Check the installed + * ioapic chip to verify that. + */ + if (irqd->chip == &ioapic_chip) { + mpd->entry.dest = cfg->dest_apicid; + mpd->entry.vector = cfg->vector; + } + for_each_irq_pin(entry, mpd->irq_2_pin) + __ioapic_write_entry(entry->apic, entry->pin, mpd->entry); +} + static int ioapic_set_affinity(struct irq_data *irq_data, const struct cpumask *mask, bool force) { struct irq_data *parent = irq_data->parent_data; - struct mp_chip_data *data = irq_data->chip_data; - struct irq_pin_list *entry; - struct irq_cfg *cfg; unsigned long flags; int ret; ret = parent->chip->irq_set_affinity(parent, mask, force); raw_spin_lock_irqsave(&ioapic_lock, flags); - if (ret >= 0 && ret != IRQ_SET_MASK_OK_DONE) { - cfg = irqd_cfg(irq_data); - data->entry.dest = cfg->dest_apicid; - data->entry.vector = cfg->vector; - for_each_irq_pin(entry, data->irq_2_pin) - __ioapic_write_entry(entry->apic, entry->pin, - data->entry); - } + if (ret >= 0 && ret != IRQ_SET_MASK_OK_DONE) + ioapic_configure_entry(irq_data); raw_spin_unlock_irqrestore(&ioapic_lock, flags); return ret; @@ -2096,7 +2149,7 @@ static inline void __init check_timer(void) unmask_ioapic_irq(irq_get_irq_data(0)); } irq_domain_deactivate_irq(irq_data); - irq_domain_activate_irq(irq_data); + irq_domain_activate_irq(irq_data, false); if (timer_irq_works()) { if (disable_timer_pin_1 > 0) clear_IO_APIC_pin(0, pin1); @@ -2118,7 +2171,7 @@ static inline void __init check_timer(void) */ replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2); irq_domain_deactivate_irq(irq_data); - irq_domain_activate_irq(irq_data); + irq_domain_activate_irq(irq_data, false); legacy_pic->unmask(0); if (timer_irq_works()) { apic_printk(APIC_QUIET, KERN_INFO "....... works.\n"); @@ -2512,52 +2565,9 @@ int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity) } /* - * This function currently is only a helper for the i386 smp boot process where - * we need to reprogram the ioredtbls to cater for the cpus which have come online - * so mask in all cases should simply be apic->target_cpus() + * This function updates target affinity of IOAPIC interrupts to include + * the CPUs which came online during SMP bringup. */ -#ifdef CONFIG_SMP -void __init setup_ioapic_dest(void) -{ - int pin, ioapic, irq, irq_entry; - const struct cpumask *mask; - struct irq_desc *desc; - struct irq_data *idata; - struct irq_chip *chip; - - if (skip_ioapic_setup == 1) - return; - - for_each_ioapic_pin(ioapic, pin) { - irq_entry = find_irq_entry(ioapic, pin, mp_INT); - if (irq_entry == -1) - continue; - - irq = pin_2_irq(irq_entry, ioapic, pin, 0); - if (irq < 0 || !mp_init_irq_at_boot(ioapic, irq)) - continue; - - desc = irq_to_desc(irq); - raw_spin_lock_irq(&desc->lock); - idata = irq_desc_get_irq_data(desc); - - /* - * Honour affinities which have been set in early boot - */ - if (!irqd_can_balance(idata) || irqd_affinity_was_set(idata)) - mask = irq_data_get_affinity_mask(idata); - else - mask = apic->target_cpus(); - - chip = irq_data_get_irq_chip(idata); - /* Might be lapic_chip for irq 0 */ - if (chip->irq_set_affinity) - chip->irq_set_affinity(idata, mask, false); - raw_spin_unlock_irq(&desc->lock); - } -} -#endif - #define IOAPIC_RESOURCE_NAME_SIZE 11 static struct resource *ioapic_resources; @@ -2977,17 +2987,15 @@ void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq, irq_domain_free_irqs_top(domain, virq, nr_irqs); } -void mp_irqdomain_activate(struct irq_domain *domain, - struct irq_data *irq_data) +int mp_irqdomain_activate(struct irq_domain *domain, + struct irq_data *irq_data, bool early) { unsigned long flags; - struct irq_pin_list *entry; - struct mp_chip_data *data = irq_data->chip_data; raw_spin_lock_irqsave(&ioapic_lock, flags); - for_each_irq_pin(entry, data->irq_2_pin) - __ioapic_write_entry(entry->apic, entry->pin, data->entry); + ioapic_configure_entry(irq_data); raw_spin_unlock_irqrestore(&ioapic_lock, flags); + return 0; } void mp_irqdomain_deactivate(struct irq_domain *domain, diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c index 3a205d4a12d0..82f9244fe61f 100644 --- a/arch/x86/kernel/apic/ipi.c +++ b/arch/x86/kernel/apic/ipi.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/cpumask.h> #include <linux/interrupt.h> diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 63287659adb6..fa22017de806 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -66,6 +66,31 @@ static void setup_apic_flat_routing(void) #endif } +static int default_apic_id_registered(void) +{ + return physid_isset(read_apic_id(), phys_cpu_present_map); +} + +/* + * Set up the logical destination ID. Intel recommends to set DFR, LDR and + * TPR before enabling an APIC. See e.g. "AP-388 82489DX User's Manual" + * (Intel document number 292116). + */ +static void default_init_apic_ldr(void) +{ + unsigned long val; + + apic_write(APIC_DFR, APIC_DFR_VALUE); + val = apic_read(APIC_LDR) & ~APIC_LDR_MASK; + val |= SET_APIC_LOGICAL_ID(1UL << smp_processor_id()); + apic_write(APIC_LDR, val); +} + +static int default_phys_pkg_id(int cpuid_apic, int index_msb) +{ + return cpuid_apic >> index_msb; +} + /* should be called last. */ static int probe_default(void) { @@ -84,12 +109,10 @@ static struct apic apic_default __ro_after_init = { /* logical delivery broadcast to all CPUs: */ .irq_dest_mode = 1, - .target_cpus = default_target_cpus, .disable_esr = 0, .dest_logical = APIC_DEST_LOGICAL, .check_apicid_used = default_check_apicid_used, - .vector_allocation_domain = flat_vector_allocation_domain, .init_apic_ldr = default_init_apic_ldr, .ioapic_phys_id_map = default_ioapic_phys_id_map, @@ -102,7 +125,7 @@ static struct apic apic_default __ro_after_init = { .get_apic_id = default_get_apic_id, .set_apic_id = NULL, - .cpu_mask_to_apicid = flat_cpu_mask_to_apicid, + .calc_dest_apicid = apic_flat_calc_apicid, .send_IPI = default_send_IPI_single, .send_IPI_mask = default_send_IPI_mask_logical, diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index b3af457ed667..6a823a25eaff 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -1,5 +1,5 @@ /* - * Local APIC related interfaces to support IOAPIC, MSI, HT_IRQ etc. + * Local APIC related interfaces to support IOAPIC, MSI, etc. * * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo * Moved from arch/x86/kernel/apic/io_apic.c. @@ -11,6 +11,7 @@ * published by the Free Software Foundation. */ #include <linux/interrupt.h> +#include <linux/seq_file.h> #include <linux/init.h> #include <linux/compiler.h> #include <linux/slab.h> @@ -21,20 +22,30 @@ #include <asm/desc.h> #include <asm/irq_remapping.h> +#include <asm/trace/irq_vectors.h> + struct apic_chip_data { - struct irq_cfg cfg; - cpumask_var_t domain; - cpumask_var_t old_domain; - u8 move_in_progress : 1; + struct irq_cfg hw_irq_cfg; + unsigned int vector; + unsigned int prev_vector; + unsigned int cpu; + unsigned int prev_cpu; + unsigned int irq; + struct hlist_node clist; + unsigned int move_in_progress : 1, + is_managed : 1, + can_reserve : 1, + has_reserved : 1; }; struct irq_domain *x86_vector_domain; EXPORT_SYMBOL_GPL(x86_vector_domain); static DEFINE_RAW_SPINLOCK(vector_lock); -static cpumask_var_t vector_cpumask, vector_searchmask, searched_cpumask; +static cpumask_var_t vector_searchmask; static struct irq_chip lapic_controller; -#ifdef CONFIG_X86_IO_APIC -static struct apic_chip_data *legacy_irq_data[NR_IRQS_LEGACY]; +static struct irq_matrix *vector_matrix; +#ifdef CONFIG_SMP +static DEFINE_PER_CPU(struct hlist_head, cleanup_list); #endif void lock_vector_lock(void) @@ -50,22 +61,37 @@ void unlock_vector_lock(void) raw_spin_unlock(&vector_lock); } -static struct apic_chip_data *apic_chip_data(struct irq_data *irq_data) +void init_irq_alloc_info(struct irq_alloc_info *info, + const struct cpumask *mask) +{ + memset(info, 0, sizeof(*info)); + info->mask = mask; +} + +void copy_irq_alloc_info(struct irq_alloc_info *dst, struct irq_alloc_info *src) { - if (!irq_data) + if (src) + *dst = *src; + else + memset(dst, 0, sizeof(*dst)); +} + +static struct apic_chip_data *apic_chip_data(struct irq_data *irqd) +{ + if (!irqd) return NULL; - while (irq_data->parent_data) - irq_data = irq_data->parent_data; + while (irqd->parent_data) + irqd = irqd->parent_data; - return irq_data->chip_data; + return irqd->chip_data; } -struct irq_cfg *irqd_cfg(struct irq_data *irq_data) +struct irq_cfg *irqd_cfg(struct irq_data *irqd) { - struct apic_chip_data *data = apic_chip_data(irq_data); + struct apic_chip_data *apicd = apic_chip_data(irqd); - return data ? &data->cfg : NULL; + return apicd ? &apicd->hw_irq_cfg : NULL; } EXPORT_SYMBOL_GPL(irqd_cfg); @@ -76,270 +102,395 @@ struct irq_cfg *irq_cfg(unsigned int irq) static struct apic_chip_data *alloc_apic_chip_data(int node) { - struct apic_chip_data *data; + struct apic_chip_data *apicd; - data = kzalloc_node(sizeof(*data), GFP_KERNEL, node); - if (!data) - return NULL; - if (!zalloc_cpumask_var_node(&data->domain, GFP_KERNEL, node)) - goto out_data; - if (!zalloc_cpumask_var_node(&data->old_domain, GFP_KERNEL, node)) - goto out_domain; - return data; -out_domain: - free_cpumask_var(data->domain); -out_data: - kfree(data); - return NULL; -} - -static void free_apic_chip_data(struct apic_chip_data *data) -{ - if (data) { - free_cpumask_var(data->domain); - free_cpumask_var(data->old_domain); - kfree(data); + apicd = kzalloc_node(sizeof(*apicd), GFP_KERNEL, node); + if (apicd) + INIT_HLIST_NODE(&apicd->clist); + return apicd; +} + +static void free_apic_chip_data(struct apic_chip_data *apicd) +{ + kfree(apicd); +} + +static void apic_update_irq_cfg(struct irq_data *irqd, unsigned int vector, + unsigned int cpu) +{ + struct apic_chip_data *apicd = apic_chip_data(irqd); + + lockdep_assert_held(&vector_lock); + + apicd->hw_irq_cfg.vector = vector; + apicd->hw_irq_cfg.dest_apicid = apic->calc_dest_apicid(cpu); + irq_data_update_effective_affinity(irqd, cpumask_of(cpu)); + trace_vector_config(irqd->irq, vector, cpu, + apicd->hw_irq_cfg.dest_apicid); +} + +static void apic_update_vector(struct irq_data *irqd, unsigned int newvec, + unsigned int newcpu) +{ + struct apic_chip_data *apicd = apic_chip_data(irqd); + struct irq_desc *desc = irq_data_to_desc(irqd); + + lockdep_assert_held(&vector_lock); + + trace_vector_update(irqd->irq, newvec, newcpu, apicd->vector, + apicd->cpu); + + /* Setup the vector move, if required */ + if (apicd->vector && cpu_online(apicd->cpu)) { + apicd->move_in_progress = true; + apicd->prev_vector = apicd->vector; + apicd->prev_cpu = apicd->cpu; + } else { + apicd->prev_vector = 0; } + + apicd->vector = newvec; + apicd->cpu = newcpu; + BUG_ON(!IS_ERR_OR_NULL(per_cpu(vector_irq, newcpu)[newvec])); + per_cpu(vector_irq, newcpu)[newvec] = desc; } -static int __assign_irq_vector(int irq, struct apic_chip_data *d, - const struct cpumask *mask, - struct irq_data *irqdata) +static void vector_assign_managed_shutdown(struct irq_data *irqd) { - /* - * NOTE! The local APIC isn't very good at handling - * multiple interrupts at the same interrupt level. - * As the interrupt level is determined by taking the - * vector number and shifting that right by 4, we - * want to spread these out a bit so that they don't - * all fall in the same interrupt level. - * - * Also, we've got to be careful not to trash gate - * 0x80, because int 0x80 is hm, kind of importantish. ;) - */ - static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START; - static int current_offset = VECTOR_OFFSET_START % 16; - int cpu, vector; + unsigned int cpu = cpumask_first(cpu_online_mask); - /* - * If there is still a move in progress or the previous move has not - * been cleaned up completely, tell the caller to come back later. - */ - if (d->move_in_progress || - cpumask_intersects(d->old_domain, cpu_online_mask)) - return -EBUSY; + apic_update_irq_cfg(irqd, MANAGED_IRQ_SHUTDOWN_VECTOR, cpu); +} - /* Only try and allocate irqs on cpus that are present */ - cpumask_clear(d->old_domain); - cpumask_clear(searched_cpumask); - cpu = cpumask_first_and(mask, cpu_online_mask); - while (cpu < nr_cpu_ids) { - int new_cpu, offset; +static int reserve_managed_vector(struct irq_data *irqd) +{ + const struct cpumask *affmsk = irq_data_get_affinity_mask(irqd); + struct apic_chip_data *apicd = apic_chip_data(irqd); + unsigned long flags; + int ret; - /* Get the possible target cpus for @mask/@cpu from the apic */ - apic->vector_allocation_domain(cpu, vector_cpumask, mask); + raw_spin_lock_irqsave(&vector_lock, flags); + apicd->is_managed = true; + ret = irq_matrix_reserve_managed(vector_matrix, affmsk); + raw_spin_unlock_irqrestore(&vector_lock, flags); + trace_vector_reserve_managed(irqd->irq, ret); + return ret; +} - /* - * Clear the offline cpus from @vector_cpumask for searching - * and verify whether the result overlaps with @mask. If true, - * then the call to apic->cpu_mask_to_apicid() will - * succeed as well. If not, no point in trying to find a - * vector in this mask. - */ - cpumask_and(vector_searchmask, vector_cpumask, cpu_online_mask); - if (!cpumask_intersects(vector_searchmask, mask)) - goto next_cpu; - - if (cpumask_subset(vector_cpumask, d->domain)) { - if (cpumask_equal(vector_cpumask, d->domain)) - goto success; - /* - * Mark the cpus which are not longer in the mask for - * cleanup. - */ - cpumask_andnot(d->old_domain, d->domain, vector_cpumask); - vector = d->cfg.vector; - goto update; - } +static void reserve_irq_vector_locked(struct irq_data *irqd) +{ + struct apic_chip_data *apicd = apic_chip_data(irqd); - vector = current_vector; - offset = current_offset; -next: - vector += 16; - if (vector >= first_system_vector) { - offset = (offset + 1) % 16; - vector = FIRST_EXTERNAL_VECTOR + offset; - } + irq_matrix_reserve(vector_matrix); + apicd->can_reserve = true; + apicd->has_reserved = true; + trace_vector_reserve(irqd->irq, 0); + vector_assign_managed_shutdown(irqd); +} - /* If the search wrapped around, try the next cpu */ - if (unlikely(current_vector == vector)) - goto next_cpu; +static int reserve_irq_vector(struct irq_data *irqd) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&vector_lock, flags); + reserve_irq_vector_locked(irqd); + raw_spin_unlock_irqrestore(&vector_lock, flags); + return 0; +} - if (test_bit(vector, used_vectors)) - goto next; +static int allocate_vector(struct irq_data *irqd, const struct cpumask *dest) +{ + struct apic_chip_data *apicd = apic_chip_data(irqd); + bool resvd = apicd->has_reserved; + unsigned int cpu = apicd->cpu; + int vector = apicd->vector; - for_each_cpu(new_cpu, vector_searchmask) { - if (!IS_ERR_OR_NULL(per_cpu(vector_irq, new_cpu)[vector])) - goto next; - } - /* Found one! */ - current_vector = vector; - current_offset = offset; - /* Schedule the old vector for cleanup on all cpus */ - if (d->cfg.vector) - cpumask_copy(d->old_domain, d->domain); - for_each_cpu(new_cpu, vector_searchmask) - per_cpu(vector_irq, new_cpu)[vector] = irq_to_desc(irq); - goto update; - -next_cpu: - /* - * We exclude the current @vector_cpumask from the requested - * @mask and try again with the next online cpu in the - * result. We cannot modify @mask, so we use @vector_cpumask - * as a temporary buffer here as it will be reassigned when - * calling apic->vector_allocation_domain() above. - */ - cpumask_or(searched_cpumask, searched_cpumask, vector_cpumask); - cpumask_andnot(vector_cpumask, mask, searched_cpumask); - cpu = cpumask_first_and(vector_cpumask, cpu_online_mask); - continue; - } - return -ENOSPC; + lockdep_assert_held(&vector_lock); -update: /* - * Exclude offline cpus from the cleanup mask and set the - * move_in_progress flag when the result is not empty. + * If the current target CPU is online and in the new requested + * affinity mask, there is no point in moving the interrupt from + * one CPU to another. */ - cpumask_and(d->old_domain, d->old_domain, cpu_online_mask); - d->move_in_progress = !cpumask_empty(d->old_domain); - d->cfg.old_vector = d->move_in_progress ? d->cfg.vector : 0; - d->cfg.vector = vector; - cpumask_copy(d->domain, vector_cpumask); -success: - /* - * Cache destination APIC IDs into cfg->dest_apicid. This cannot fail - * as we already established, that mask & d->domain & cpu_online_mask - * is not empty. - * - * vector_searchmask is a subset of d->domain and has the offline - * cpus masked out. - */ - cpumask_and(vector_searchmask, vector_searchmask, mask); - BUG_ON(apic->cpu_mask_to_apicid(vector_searchmask, irqdata, - &d->cfg.dest_apicid)); + if (vector && cpu_online(cpu) && cpumask_test_cpu(cpu, dest)) + return 0; + + vector = irq_matrix_alloc(vector_matrix, dest, resvd, &cpu); + if (vector > 0) + apic_update_vector(irqd, vector, cpu); + trace_vector_alloc(irqd->irq, vector, resvd, vector); + return vector; +} + +static int assign_vector_locked(struct irq_data *irqd, + const struct cpumask *dest) +{ + struct apic_chip_data *apicd = apic_chip_data(irqd); + int vector = allocate_vector(irqd, dest); + + if (vector < 0) + return vector; + + apic_update_irq_cfg(irqd, apicd->vector, apicd->cpu); return 0; } -static int assign_irq_vector(int irq, struct apic_chip_data *data, - const struct cpumask *mask, - struct irq_data *irqdata) +static int assign_irq_vector(struct irq_data *irqd, const struct cpumask *dest) { - int err; unsigned long flags; + int ret; raw_spin_lock_irqsave(&vector_lock, flags); - err = __assign_irq_vector(irq, data, mask, irqdata); + cpumask_and(vector_searchmask, dest, cpu_online_mask); + ret = assign_vector_locked(irqd, vector_searchmask); raw_spin_unlock_irqrestore(&vector_lock, flags); - return err; + return ret; } -static int assign_irq_vector_policy(int irq, int node, - struct apic_chip_data *data, - struct irq_alloc_info *info, - struct irq_data *irqdata) +static int assign_irq_vector_any_locked(struct irq_data *irqd) { - if (info && info->mask) - return assign_irq_vector(irq, data, info->mask, irqdata); - if (node != NUMA_NO_NODE && - assign_irq_vector(irq, data, cpumask_of_node(node), irqdata) == 0) + /* Get the affinity mask - either irq_default_affinity or (user) set */ + const struct cpumask *affmsk = irq_data_get_affinity_mask(irqd); + int node = irq_data_get_node(irqd); + + if (node == NUMA_NO_NODE) + goto all; + /* Try the intersection of @affmsk and node mask */ + cpumask_and(vector_searchmask, cpumask_of_node(node), affmsk); + if (!assign_vector_locked(irqd, vector_searchmask)) + return 0; + /* Try the node mask */ + if (!assign_vector_locked(irqd, cpumask_of_node(node))) return 0; - return assign_irq_vector(irq, data, apic->target_cpus(), irqdata); +all: + /* Try the full affinity mask */ + cpumask_and(vector_searchmask, affmsk, cpu_online_mask); + if (!assign_vector_locked(irqd, vector_searchmask)) + return 0; + /* Try the full online mask */ + return assign_vector_locked(irqd, cpu_online_mask); +} + +static int +assign_irq_vector_policy(struct irq_data *irqd, struct irq_alloc_info *info) +{ + if (irqd_affinity_is_managed(irqd)) + return reserve_managed_vector(irqd); + if (info->mask) + return assign_irq_vector(irqd, info->mask); + /* + * Make only a global reservation with no guarantee. A real vector + * is associated at activation time. + */ + return reserve_irq_vector(irqd); } -static void clear_irq_vector(int irq, struct apic_chip_data *data) +static int +assign_managed_vector(struct irq_data *irqd, const struct cpumask *dest) { - struct irq_desc *desc; - int cpu, vector; + const struct cpumask *affmsk = irq_data_get_affinity_mask(irqd); + struct apic_chip_data *apicd = apic_chip_data(irqd); + int vector, cpu; - if (!data->cfg.vector) + cpumask_and(vector_searchmask, vector_searchmask, affmsk); + cpu = cpumask_first(vector_searchmask); + if (cpu >= nr_cpu_ids) + return -EINVAL; + /* set_affinity might call here for nothing */ + if (apicd->vector && cpumask_test_cpu(apicd->cpu, vector_searchmask)) + return 0; + vector = irq_matrix_alloc_managed(vector_matrix, cpu); + trace_vector_alloc_managed(irqd->irq, vector, vector); + if (vector < 0) + return vector; + apic_update_vector(irqd, vector, cpu); + apic_update_irq_cfg(irqd, vector, cpu); + return 0; +} + +static void clear_irq_vector(struct irq_data *irqd) +{ + struct apic_chip_data *apicd = apic_chip_data(irqd); + bool managed = irqd_affinity_is_managed(irqd); + unsigned int vector = apicd->vector; + + lockdep_assert_held(&vector_lock); + + if (!vector) return; - vector = data->cfg.vector; - for_each_cpu_and(cpu, data->domain, cpu_online_mask) - per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED; + trace_vector_clear(irqd->irq, vector, apicd->cpu, apicd->prev_vector, + apicd->prev_cpu); - data->cfg.vector = 0; - cpumask_clear(data->domain); + per_cpu(vector_irq, apicd->cpu)[vector] = VECTOR_UNUSED; + irq_matrix_free(vector_matrix, apicd->cpu, vector, managed); + apicd->vector = 0; - /* - * If move is in progress or the old_domain mask is not empty, - * i.e. the cleanup IPI has not been processed yet, we need to remove - * the old references to desc from all cpus vector tables. - */ - if (!data->move_in_progress && cpumask_empty(data->old_domain)) + /* Clean up move in progress */ + vector = apicd->prev_vector; + if (!vector) return; - desc = irq_to_desc(irq); - for_each_cpu_and(cpu, data->old_domain, cpu_online_mask) { - for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; - vector++) { - if (per_cpu(vector_irq, cpu)[vector] != desc) - continue; - per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED; - break; - } + per_cpu(vector_irq, apicd->prev_cpu)[vector] = VECTOR_UNUSED; + irq_matrix_free(vector_matrix, apicd->prev_cpu, vector, managed); + apicd->prev_vector = 0; + apicd->move_in_progress = 0; + hlist_del_init(&apicd->clist); +} + +static void x86_vector_deactivate(struct irq_domain *dom, struct irq_data *irqd) +{ + struct apic_chip_data *apicd = apic_chip_data(irqd); + unsigned long flags; + + trace_vector_deactivate(irqd->irq, apicd->is_managed, + apicd->can_reserve, false); + + /* Regular fixed assigned interrupt */ + if (!apicd->is_managed && !apicd->can_reserve) + return; + /* If the interrupt has a global reservation, nothing to do */ + if (apicd->has_reserved) + return; + + raw_spin_lock_irqsave(&vector_lock, flags); + clear_irq_vector(irqd); + if (apicd->can_reserve) + reserve_irq_vector_locked(irqd); + else + vector_assign_managed_shutdown(irqd); + raw_spin_unlock_irqrestore(&vector_lock, flags); +} + +static int activate_reserved(struct irq_data *irqd) +{ + struct apic_chip_data *apicd = apic_chip_data(irqd); + int ret; + + ret = assign_irq_vector_any_locked(irqd); + if (!ret) + apicd->has_reserved = false; + return ret; +} + +static int activate_managed(struct irq_data *irqd) +{ + const struct cpumask *dest = irq_data_get_affinity_mask(irqd); + int ret; + + cpumask_and(vector_searchmask, dest, cpu_online_mask); + if (WARN_ON_ONCE(cpumask_empty(vector_searchmask))) { + /* Something in the core code broke! Survive gracefully */ + pr_err("Managed startup for irq %u, but no CPU\n", irqd->irq); + return EINVAL; + } + + ret = assign_managed_vector(irqd, vector_searchmask); + /* + * This should not happen. The vector reservation got buggered. Handle + * it gracefully. + */ + if (WARN_ON_ONCE(ret < 0)) { + pr_err("Managed startup irq %u, no vector available\n", + irqd->irq); } - data->move_in_progress = 0; + return ret; } -void init_irq_alloc_info(struct irq_alloc_info *info, - const struct cpumask *mask) +static int x86_vector_activate(struct irq_domain *dom, struct irq_data *irqd, + bool early) { - memset(info, 0, sizeof(*info)); - info->mask = mask; + struct apic_chip_data *apicd = apic_chip_data(irqd); + unsigned long flags; + int ret = 0; + + trace_vector_activate(irqd->irq, apicd->is_managed, + apicd->can_reserve, early); + + /* Nothing to do for fixed assigned vectors */ + if (!apicd->can_reserve && !apicd->is_managed) + return 0; + + raw_spin_lock_irqsave(&vector_lock, flags); + if (early || irqd_is_managed_and_shutdown(irqd)) + vector_assign_managed_shutdown(irqd); + else if (apicd->is_managed) + ret = activate_managed(irqd); + else if (apicd->has_reserved) + ret = activate_reserved(irqd); + raw_spin_unlock_irqrestore(&vector_lock, flags); + return ret; } -void copy_irq_alloc_info(struct irq_alloc_info *dst, struct irq_alloc_info *src) +static void vector_free_reserved_and_managed(struct irq_data *irqd) { - if (src) - *dst = *src; - else - memset(dst, 0, sizeof(*dst)); + const struct cpumask *dest = irq_data_get_affinity_mask(irqd); + struct apic_chip_data *apicd = apic_chip_data(irqd); + + trace_vector_teardown(irqd->irq, apicd->is_managed, + apicd->has_reserved); + + if (apicd->has_reserved) + irq_matrix_remove_reserved(vector_matrix); + if (apicd->is_managed) + irq_matrix_remove_managed(vector_matrix, dest); } static void x86_vector_free_irqs(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs) { - struct apic_chip_data *apic_data; - struct irq_data *irq_data; + struct apic_chip_data *apicd; + struct irq_data *irqd; unsigned long flags; int i; for (i = 0; i < nr_irqs; i++) { - irq_data = irq_domain_get_irq_data(x86_vector_domain, virq + i); - if (irq_data && irq_data->chip_data) { + irqd = irq_domain_get_irq_data(x86_vector_domain, virq + i); + if (irqd && irqd->chip_data) { raw_spin_lock_irqsave(&vector_lock, flags); - clear_irq_vector(virq + i, irq_data->chip_data); - apic_data = irq_data->chip_data; - irq_domain_reset_irq_data(irq_data); + clear_irq_vector(irqd); + vector_free_reserved_and_managed(irqd); + apicd = irqd->chip_data; + irq_domain_reset_irq_data(irqd); raw_spin_unlock_irqrestore(&vector_lock, flags); - free_apic_chip_data(apic_data); -#ifdef CONFIG_X86_IO_APIC - if (virq + i < nr_legacy_irqs()) - legacy_irq_data[virq + i] = NULL; -#endif + free_apic_chip_data(apicd); } } } +static bool vector_configure_legacy(unsigned int virq, struct irq_data *irqd, + struct apic_chip_data *apicd) +{ + unsigned long flags; + bool realloc = false; + + apicd->vector = ISA_IRQ_VECTOR(virq); + apicd->cpu = 0; + + raw_spin_lock_irqsave(&vector_lock, flags); + /* + * If the interrupt is activated, then it must stay at this vector + * position. That's usually the timer interrupt (0). + */ + if (irqd_is_activated(irqd)) { + trace_vector_setup(virq, true, 0); + apic_update_irq_cfg(irqd, apicd->vector, apicd->cpu); + } else { + /* Release the vector */ + apicd->can_reserve = true; + clear_irq_vector(irqd); + realloc = true; + } + raw_spin_unlock_irqrestore(&vector_lock, flags); + return realloc; +} + static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs, void *arg) { struct irq_alloc_info *info = arg; - struct apic_chip_data *data; - struct irq_data *irq_data; + struct apic_chip_data *apicd; + struct irq_data *irqd; int i, err, node; if (disable_apic) @@ -350,34 +501,37 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, return -ENOSYS; for (i = 0; i < nr_irqs; i++) { - irq_data = irq_domain_get_irq_data(domain, virq + i); - BUG_ON(!irq_data); - node = irq_data_get_node(irq_data); -#ifdef CONFIG_X86_IO_APIC - if (virq + i < nr_legacy_irqs() && legacy_irq_data[virq + i]) - data = legacy_irq_data[virq + i]; - else -#endif - data = alloc_apic_chip_data(node); - if (!data) { + irqd = irq_domain_get_irq_data(domain, virq + i); + BUG_ON(!irqd); + node = irq_data_get_node(irqd); + WARN_ON_ONCE(irqd->chip_data); + apicd = alloc_apic_chip_data(node); + if (!apicd) { err = -ENOMEM; goto error; } - irq_data->chip = &lapic_controller; - irq_data->chip_data = data; - irq_data->hwirq = virq + i; - err = assign_irq_vector_policy(virq + i, node, data, info, - irq_data); - if (err) - goto error; + apicd->irq = virq + i; + irqd->chip = &lapic_controller; + irqd->chip_data = apicd; + irqd->hwirq = virq + i; + irqd_set_single_target(irqd); /* - * If the apic destination mode is physical, then the - * effective affinity is restricted to a single target - * CPU. Mark the interrupt accordingly. + * Legacy vectors are already assigned when the IOAPIC + * takes them over. They stay on the same vector. This is + * required for check_timer() to work correctly as it might + * switch back to legacy mode. Only update the hardware + * config. */ - if (!apic->irq_dest_mode) - irqd_set_single_target(irq_data); + if (info->flags & X86_IRQ_ALLOC_LEGACY) { + if (!vector_configure_legacy(virq + i, irqd, apicd)) + continue; + } + + err = assign_irq_vector_policy(irqd, info); + trace_vector_setup(virq + i, false, err); + if (err) + goto error; } return 0; @@ -387,9 +541,56 @@ error: return err; } +#ifdef CONFIG_GENERIC_IRQ_DEBUGFS +void x86_vector_debug_show(struct seq_file *m, struct irq_domain *d, + struct irq_data *irqd, int ind) +{ + unsigned int cpu, vector, prev_cpu, prev_vector; + struct apic_chip_data *apicd; + unsigned long flags; + int irq; + + if (!irqd) { + irq_matrix_debug_show(m, vector_matrix, ind); + return; + } + + irq = irqd->irq; + if (irq < nr_legacy_irqs() && !test_bit(irq, &io_apic_irqs)) { + seq_printf(m, "%*sVector: %5d\n", ind, "", ISA_IRQ_VECTOR(irq)); + seq_printf(m, "%*sTarget: Legacy PIC all CPUs\n", ind, ""); + return; + } + + apicd = irqd->chip_data; + if (!apicd) { + seq_printf(m, "%*sVector: Not assigned\n", ind, ""); + return; + } + + raw_spin_lock_irqsave(&vector_lock, flags); + cpu = apicd->cpu; + vector = apicd->vector; + prev_cpu = apicd->prev_cpu; + prev_vector = apicd->prev_vector; + raw_spin_unlock_irqrestore(&vector_lock, flags); + seq_printf(m, "%*sVector: %5u\n", ind, "", vector); + seq_printf(m, "%*sTarget: %5u\n", ind, "", cpu); + if (prev_vector) { + seq_printf(m, "%*sPrevious vector: %5u\n", ind, "", prev_vector); + seq_printf(m, "%*sPrevious target: %5u\n", ind, "", prev_cpu); + } +} +#endif + static const struct irq_domain_ops x86_vector_domain_ops = { - .alloc = x86_vector_alloc_irqs, - .free = x86_vector_free_irqs, + .alloc = x86_vector_alloc_irqs, + .free = x86_vector_free_irqs, + .activate = x86_vector_activate, + .deactivate = x86_vector_deactivate, +#ifdef CONFIG_GENERIC_IRQ_DEBUGFS + .debug_show = x86_vector_debug_show, +#endif }; int __init arch_probe_nr_irqs(void) @@ -400,7 +601,7 @@ int __init arch_probe_nr_irqs(void) nr_irqs = NR_VECTORS * nr_cpu_ids; nr = (gsi_top + nr_legacy_irqs()) + 8 * nr_cpu_ids; -#if defined(CONFIG_PCI_MSI) || defined(CONFIG_HT_IRQ) +#if defined(CONFIG_PCI_MSI) /* * for MSI and HT dyn irq */ @@ -419,35 +620,40 @@ int __init arch_probe_nr_irqs(void) return legacy_pic->probe(); } -#ifdef CONFIG_X86_IO_APIC -static void __init init_legacy_irqs(void) +void lapic_assign_legacy_vector(unsigned int irq, bool replace) { - int i, node = cpu_to_node(0); - struct apic_chip_data *data; - /* - * For legacy IRQ's, start with assigning irq0 to irq15 to - * ISA_IRQ_VECTOR(i) for all cpu's. + * Use assign system here so it wont get accounted as allocated + * and moveable in the cpu hotplug check and it prevents managed + * irq reservation from touching it. */ - for (i = 0; i < nr_legacy_irqs(); i++) { - data = legacy_irq_data[i] = alloc_apic_chip_data(node); - BUG_ON(!data); + irq_matrix_assign_system(vector_matrix, ISA_IRQ_VECTOR(irq), replace); +} + +void __init lapic_assign_system_vectors(void) +{ + unsigned int i, vector = 0; - data->cfg.vector = ISA_IRQ_VECTOR(i); - cpumask_setall(data->domain); - irq_set_chip_data(i, data); + for_each_set_bit_from(vector, system_vectors, NR_VECTORS) + irq_matrix_assign_system(vector_matrix, vector, false); + + if (nr_legacy_irqs() > 1) + lapic_assign_legacy_vector(PIC_CASCADE_IR, false); + + /* System vectors are reserved, online it */ + irq_matrix_online(vector_matrix); + + /* Mark the preallocated legacy interrupts */ + for (i = 0; i < nr_legacy_irqs(); i++) { + if (i != PIC_CASCADE_IR) + irq_matrix_assign(vector_matrix, ISA_IRQ_VECTOR(i)); } } -#else -static inline void init_legacy_irqs(void) { } -#endif int __init arch_early_irq_init(void) { struct fwnode_handle *fn; - init_legacy_irqs(); - fn = irq_domain_alloc_named_fwnode("VECTOR"); BUG_ON(!fn); x86_vector_domain = irq_domain_create_tree(fn, &x86_vector_domain_ops, @@ -457,102 +663,116 @@ int __init arch_early_irq_init(void) irq_set_default_host(x86_vector_domain); arch_init_msi_domain(x86_vector_domain); - arch_init_htirq_domain(x86_vector_domain); - BUG_ON(!alloc_cpumask_var(&vector_cpumask, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&vector_searchmask, GFP_KERNEL)); - BUG_ON(!alloc_cpumask_var(&searched_cpumask, GFP_KERNEL)); + + /* + * Allocate the vector matrix allocator data structure and limit the + * search area. + */ + vector_matrix = irq_alloc_matrix(NR_VECTORS, FIRST_EXTERNAL_VECTOR, + FIRST_SYSTEM_VECTOR); + BUG_ON(!vector_matrix); return arch_early_ioapic_init(); } -/* Initialize vector_irq on a new cpu */ -static void __setup_vector_irq(int cpu) +#ifdef CONFIG_SMP + +static struct irq_desc *__setup_vector_irq(int vector) { - struct apic_chip_data *data; - struct irq_desc *desc; - int irq, vector; + int isairq = vector - ISA_IRQ_VECTOR(0); + + /* Check whether the irq is in the legacy space */ + if (isairq < 0 || isairq >= nr_legacy_irqs()) + return VECTOR_UNUSED; + /* Check whether the irq is handled by the IOAPIC */ + if (test_bit(isairq, &io_apic_irqs)) + return VECTOR_UNUSED; + return irq_to_desc(isairq); +} - /* Mark the inuse vectors */ - for_each_irq_desc(irq, desc) { - struct irq_data *idata = irq_desc_get_irq_data(desc); +/* Online the local APIC infrastructure and initialize the vectors */ +void lapic_online(void) +{ + unsigned int vector; - data = apic_chip_data(idata); - if (!data || !cpumask_test_cpu(cpu, data->domain)) - continue; - vector = data->cfg.vector; - per_cpu(vector_irq, cpu)[vector] = desc; - } - /* Mark the free vectors */ - for (vector = 0; vector < NR_VECTORS; ++vector) { - desc = per_cpu(vector_irq, cpu)[vector]; - if (IS_ERR_OR_NULL(desc)) - continue; + lockdep_assert_held(&vector_lock); - data = apic_chip_data(irq_desc_get_irq_data(desc)); - if (!cpumask_test_cpu(cpu, data->domain)) - per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED; - } + /* Online the vector matrix array for this CPU */ + irq_matrix_online(vector_matrix); + + /* + * The interrupt affinity logic never targets interrupts to offline + * CPUs. The exception are the legacy PIC interrupts. In general + * they are only targeted to CPU0, but depending on the platform + * they can be distributed to any online CPU in hardware. The + * kernel has no influence on that. So all active legacy vectors + * must be installed on all CPUs. All non legacy interrupts can be + * cleared. + */ + for (vector = 0; vector < NR_VECTORS; vector++) + this_cpu_write(vector_irq[vector], __setup_vector_irq(vector)); } -/* - * Setup the vector to irq mappings. Must be called with vector_lock held. - */ -void setup_vector_irq(int cpu) +void lapic_offline(void) { - int irq; + lock_vector_lock(); + irq_matrix_offline(vector_matrix); + unlock_vector_lock(); +} + +static int apic_set_affinity(struct irq_data *irqd, + const struct cpumask *dest, bool force) +{ + struct apic_chip_data *apicd = apic_chip_data(irqd); + int err; - lockdep_assert_held(&vector_lock); /* - * On most of the platforms, legacy PIC delivers the interrupts on the - * boot cpu. But there are certain platforms where PIC interrupts are - * delivered to multiple cpu's. If the legacy IRQ is handled by the - * legacy PIC, for the new cpu that is coming online, setup the static - * legacy vector to irq mapping: + * Core code can call here for inactive interrupts. For inactive + * interrupts which use managed or reservation mode there is no + * point in going through the vector assignment right now as the + * activation will assign a vector which fits the destination + * cpumask. Let the core code store the destination mask and be + * done with it. */ - for (irq = 0; irq < nr_legacy_irqs(); irq++) - per_cpu(vector_irq, cpu)[ISA_IRQ_VECTOR(irq)] = irq_to_desc(irq); + if (!irqd_is_activated(irqd) && + (apicd->is_managed || apicd->can_reserve)) + return IRQ_SET_MASK_OK; - __setup_vector_irq(cpu); + raw_spin_lock(&vector_lock); + cpumask_and(vector_searchmask, dest, cpu_online_mask); + if (irqd_affinity_is_managed(irqd)) + err = assign_managed_vector(irqd, vector_searchmask); + else + err = assign_vector_locked(irqd, vector_searchmask); + raw_spin_unlock(&vector_lock); + return err ? err : IRQ_SET_MASK_OK; } -static int apic_retrigger_irq(struct irq_data *irq_data) +#else +# define apic_set_affinity NULL +#endif + +static int apic_retrigger_irq(struct irq_data *irqd) { - struct apic_chip_data *data = apic_chip_data(irq_data); + struct apic_chip_data *apicd = apic_chip_data(irqd); unsigned long flags; - int cpu; raw_spin_lock_irqsave(&vector_lock, flags); - cpu = cpumask_first_and(data->domain, cpu_online_mask); - apic->send_IPI_mask(cpumask_of(cpu), data->cfg.vector); + apic->send_IPI(apicd->cpu, apicd->vector); raw_spin_unlock_irqrestore(&vector_lock, flags); return 1; } -void apic_ack_edge(struct irq_data *data) +void apic_ack_edge(struct irq_data *irqd) { - irq_complete_move(irqd_cfg(data)); - irq_move_irq(data); + irq_complete_move(irqd_cfg(irqd)); + irq_move_irq(irqd); ack_APIC_irq(); } -static int apic_set_affinity(struct irq_data *irq_data, - const struct cpumask *dest, bool force) -{ - struct apic_chip_data *data = irq_data->chip_data; - int err, irq = irq_data->irq; - - if (!IS_ENABLED(CONFIG_SMP)) - return -EPERM; - - if (!cpumask_intersects(dest, cpu_online_mask)) - return -EINVAL; - - err = assign_irq_vector(irq, data, dest, irq_data); - return err ? err : IRQ_SET_MASK_OK; -} - static struct irq_chip lapic_controller = { .name = "APIC", .irq_ack = apic_ack_edge, @@ -561,115 +781,98 @@ static struct irq_chip lapic_controller = { }; #ifdef CONFIG_SMP -static void __send_cleanup_vector(struct apic_chip_data *data) -{ - raw_spin_lock(&vector_lock); - cpumask_and(data->old_domain, data->old_domain, cpu_online_mask); - data->move_in_progress = 0; - if (!cpumask_empty(data->old_domain)) - apic->send_IPI_mask(data->old_domain, IRQ_MOVE_CLEANUP_VECTOR); - raw_spin_unlock(&vector_lock); -} -void send_cleanup_vector(struct irq_cfg *cfg) +static void free_moved_vector(struct apic_chip_data *apicd) { - struct apic_chip_data *data; + unsigned int vector = apicd->prev_vector; + unsigned int cpu = apicd->prev_cpu; + bool managed = apicd->is_managed; - data = container_of(cfg, struct apic_chip_data, cfg); - if (data->move_in_progress) - __send_cleanup_vector(data); + /* + * This should never happen. Managed interrupts are not + * migrated except on CPU down, which does not involve the + * cleanup vector. But try to keep the accounting correct + * nevertheless. + */ + WARN_ON_ONCE(managed); + + trace_vector_free_moved(apicd->irq, cpu, vector, managed); + irq_matrix_free(vector_matrix, cpu, vector, managed); + per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED; + hlist_del_init(&apicd->clist); + apicd->prev_vector = 0; + apicd->move_in_progress = 0; } asmlinkage __visible void __irq_entry smp_irq_move_cleanup_interrupt(void) { - unsigned vector, me; + struct hlist_head *clhead = this_cpu_ptr(&cleanup_list); + struct apic_chip_data *apicd; + struct hlist_node *tmp; entering_ack_irq(); - /* Prevent vectors vanishing under us */ raw_spin_lock(&vector_lock); - me = smp_processor_id(); - for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { - struct apic_chip_data *data; - struct irq_desc *desc; - unsigned int irr; - - retry: - desc = __this_cpu_read(vector_irq[vector]); - if (IS_ERR_OR_NULL(desc)) - continue; - - if (!raw_spin_trylock(&desc->lock)) { - raw_spin_unlock(&vector_lock); - cpu_relax(); - raw_spin_lock(&vector_lock); - goto retry; - } - - data = apic_chip_data(irq_desc_get_irq_data(desc)); - if (!data) - goto unlock; + hlist_for_each_entry_safe(apicd, tmp, clhead, clist) { + unsigned int irr, vector = apicd->prev_vector; /* - * Nothing to cleanup if irq migration is in progress - * or this cpu is not set in the cleanup mask. - */ - if (data->move_in_progress || - !cpumask_test_cpu(me, data->old_domain)) - goto unlock; - - /* - * We have two cases to handle here: - * 1) vector is unchanged but the target mask got reduced - * 2) vector and the target mask has changed - * - * #1 is obvious, but in #2 we have two vectors with the same - * irq descriptor: the old and the new vector. So we need to - * make sure that we only cleanup the old vector. The new - * vector has the current @vector number in the config and - * this cpu is part of the target mask. We better leave that - * one alone. - */ - if (vector == data->cfg.vector && - cpumask_test_cpu(me, data->domain)) - goto unlock; - - irr = apic_read(APIC_IRR + (vector / 32 * 0x10)); - /* - * Check if the vector that needs to be cleanedup is - * registered at the cpu's IRR. If so, then this is not - * the best time to clean it up. Lets clean it up in the + * Paranoia: Check if the vector that needs to be cleaned + * up is registered at the APICs IRR. If so, then this is + * not the best time to clean it up. Clean it up in the * next attempt by sending another IRQ_MOVE_CLEANUP_VECTOR - * to myself. + * to this CPU. IRQ_MOVE_CLEANUP_VECTOR is the lowest + * priority external vector, so on return from this + * interrupt the device interrupt will happen first. */ - if (irr & (1 << (vector % 32))) { + irr = apic_read(APIC_IRR + (vector / 32 * 0x10)); + if (irr & (1U << (vector % 32))) { apic->send_IPI_self(IRQ_MOVE_CLEANUP_VECTOR); - goto unlock; + continue; } - __this_cpu_write(vector_irq[vector], VECTOR_UNUSED); - cpumask_clear_cpu(me, data->old_domain); -unlock: - raw_spin_unlock(&desc->lock); + free_moved_vector(apicd); } raw_spin_unlock(&vector_lock); - exiting_irq(); } +static void __send_cleanup_vector(struct apic_chip_data *apicd) +{ + unsigned int cpu; + + raw_spin_lock(&vector_lock); + apicd->move_in_progress = 0; + cpu = apicd->prev_cpu; + if (cpu_online(cpu)) { + hlist_add_head(&apicd->clist, per_cpu_ptr(&cleanup_list, cpu)); + apic->send_IPI(cpu, IRQ_MOVE_CLEANUP_VECTOR); + } else { + apicd->prev_vector = 0; + } + raw_spin_unlock(&vector_lock); +} + +void send_cleanup_vector(struct irq_cfg *cfg) +{ + struct apic_chip_data *apicd; + + apicd = container_of(cfg, struct apic_chip_data, hw_irq_cfg); + if (apicd->move_in_progress) + __send_cleanup_vector(apicd); +} + static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector) { - unsigned me; - struct apic_chip_data *data; + struct apic_chip_data *apicd; - data = container_of(cfg, struct apic_chip_data, cfg); - if (likely(!data->move_in_progress)) + apicd = container_of(cfg, struct apic_chip_data, hw_irq_cfg); + if (likely(!apicd->move_in_progress)) return; - me = smp_processor_id(); - if (vector == data->cfg.vector && cpumask_test_cpu(me, data->domain)) - __send_cleanup_vector(data); + if (vector == apicd->vector && apicd->cpu == smp_processor_id()) + __send_cleanup_vector(apicd); } void irq_complete_move(struct irq_cfg *cfg) @@ -682,10 +885,9 @@ void irq_complete_move(struct irq_cfg *cfg) */ void irq_force_complete_move(struct irq_desc *desc) { - struct irq_data *irqdata; - struct apic_chip_data *data; - struct irq_cfg *cfg; - unsigned int cpu; + struct apic_chip_data *apicd; + struct irq_data *irqd; + unsigned int vector; /* * The function is called for all descriptors regardless of which @@ -696,43 +898,31 @@ void irq_force_complete_move(struct irq_desc *desc) * Check first that the chip_data is what we expect * (apic_chip_data) before touching it any further. */ - irqdata = irq_domain_get_irq_data(x86_vector_domain, - irq_desc_get_irq(desc)); - if (!irqdata) + irqd = irq_domain_get_irq_data(x86_vector_domain, + irq_desc_get_irq(desc)); + if (!irqd) return; - data = apic_chip_data(irqdata); - cfg = data ? &data->cfg : NULL; + raw_spin_lock(&vector_lock); + apicd = apic_chip_data(irqd); + if (!apicd) + goto unlock; - if (!cfg) - return; + /* + * If prev_vector is empty, no action required. + */ + vector = apicd->prev_vector; + if (!vector) + goto unlock; /* - * This is tricky. If the cleanup of @data->old_domain has not been + * This is tricky. If the cleanup of the old vector has not been * done yet, then the following setaffinity call will fail with * -EBUSY. This can leave the interrupt in a stale state. * * All CPUs are stuck in stop machine with interrupts disabled so * calling __irq_complete_move() would be completely pointless. - */ - raw_spin_lock(&vector_lock); - /* - * Clean out all offline cpus (including the outgoing one) from the - * old_domain mask. - */ - cpumask_and(data->old_domain, data->old_domain, cpu_online_mask); - - /* - * If move_in_progress is cleared and the old_domain mask is empty, - * then there is nothing to cleanup. fixup_irqs() will take care of - * the stale vectors on the outgoing cpu. - */ - if (!data->move_in_progress && cpumask_empty(data->old_domain)) { - raw_spin_unlock(&vector_lock); - return; - } - - /* + * * 1) The interrupt is in move_in_progress state. That means that we * have not seen an interrupt since the io_apic was reprogrammed to * the new vector. @@ -740,7 +930,7 @@ void irq_force_complete_move(struct irq_desc *desc) * 2) The interrupt has fired on the new vector, but the cleanup IPIs * have not been processed yet. */ - if (data->move_in_progress) { + if (apicd->move_in_progress) { /* * In theory there is a race: * @@ -774,21 +964,43 @@ void irq_force_complete_move(struct irq_desc *desc) * area arises. */ pr_warn("IRQ fixup: irq %d move in progress, old vector %d\n", - irqdata->irq, cfg->old_vector); + irqd->irq, vector); } - /* - * If old_domain is not empty, then other cpus still have the irq - * descriptor set in their vector array. Clean it up. - */ - for_each_cpu(cpu, data->old_domain) - per_cpu(vector_irq, cpu)[cfg->old_vector] = VECTOR_UNUSED; + free_moved_vector(apicd); +unlock: + raw_spin_unlock(&vector_lock); +} + +#ifdef CONFIG_HOTPLUG_CPU +/* + * Note, this is not accurate accounting, but at least good enough to + * prevent that the actual interrupt move will run out of vectors. + */ +int lapic_can_unplug_cpu(void) +{ + unsigned int rsvd, avl, tomove, cpu = smp_processor_id(); + int ret = 0; - /* Cleanup the left overs of the (half finished) move */ - cpumask_clear(data->old_domain); - data->move_in_progress = 0; + raw_spin_lock(&vector_lock); + tomove = irq_matrix_allocated(vector_matrix); + avl = irq_matrix_available(vector_matrix, true); + if (avl < tomove) { + pr_warn("CPU %u has %u vectors, %u available. Cannot disable CPU\n", + cpu, tomove, avl); + ret = -ENOSPC; + goto out; + } + rsvd = irq_matrix_reserved(vector_matrix); + if (avl < rsvd) { + pr_warn("Reserved vectors %u > available %u. IRQ request may fail\n", + rsvd, avl); + } +out: raw_spin_unlock(&vector_lock); + return ret; } -#endif +#endif /* HOTPLUG_CPU */ +#endif /* SMP */ static void __init print_APIC_field(int base) { diff --git a/arch/x86/kernel/apic/x2apic.h b/arch/x86/kernel/apic/x2apic.h new file mode 100644 index 000000000000..b107de381cb5 --- /dev/null +++ b/arch/x86/kernel/apic/x2apic.h @@ -0,0 +1,9 @@ +/* Common bits for X2APIC cluster/physical modes. */ + +int x2apic_apic_id_valid(int apicid); +int x2apic_apic_id_registered(void); +void __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest); +unsigned int x2apic_get_apic_id(unsigned long id); +u32 x2apic_set_apic_id(unsigned int id); +int x2apic_phys_pkg_id(int initial_apicid, int index_msb); +void x2apic_send_IPI_self(int vector); diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 481237cb1544..622f13ca8a94 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/threads.h> #include <linux/cpumask.h> #include <linux/string.h> @@ -8,22 +9,24 @@ #include <linux/cpu.h> #include <asm/smp.h> -#include <asm/x2apic.h> +#include "x2apic.h" + +struct cluster_mask { + unsigned int clusterid; + int node; + struct cpumask mask; +}; static DEFINE_PER_CPU(u32, x86_cpu_to_logical_apicid); -static DEFINE_PER_CPU(cpumask_var_t, cpus_in_cluster); static DEFINE_PER_CPU(cpumask_var_t, ipi_mask); +static DEFINE_PER_CPU(struct cluster_mask *, cluster_masks); +static struct cluster_mask *cluster_hotplug_mask; static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { return x2apic_enabled(); } -static inline u32 x2apic_cluster(int cpu) -{ - return per_cpu(x86_cpu_to_logical_apicid, cpu) >> 16; -} - static void x2apic_send_IPI(int cpu, int vector) { u32 dest = per_cpu(x86_cpu_to_logical_apicid, cpu); @@ -35,49 +38,34 @@ static void x2apic_send_IPI(int cpu, int vector) static void __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest) { - struct cpumask *cpus_in_cluster_ptr; - struct cpumask *ipi_mask_ptr; - unsigned int cpu, this_cpu; + unsigned int cpu, clustercpu; + struct cpumask *tmpmsk; unsigned long flags; u32 dest; x2apic_wrmsr_fence(); - local_irq_save(flags); - this_cpu = smp_processor_id(); + tmpmsk = this_cpu_cpumask_var_ptr(ipi_mask); + cpumask_copy(tmpmsk, mask); + /* If IPI should not be sent to self, clear current CPU */ + if (apic_dest != APIC_DEST_ALLINC) + cpumask_clear_cpu(smp_processor_id(), tmpmsk); - /* - * We are to modify mask, so we need an own copy - * and be sure it's manipulated with irq off. - */ - ipi_mask_ptr = this_cpu_cpumask_var_ptr(ipi_mask); - cpumask_copy(ipi_mask_ptr, mask); - - /* - * The idea is to send one IPI per cluster. - */ - for_each_cpu(cpu, ipi_mask_ptr) { - unsigned long i; + /* Collapse cpus in a cluster so a single IPI per cluster is sent */ + for_each_cpu(cpu, tmpmsk) { + struct cluster_mask *cmsk = per_cpu(cluster_masks, cpu); - cpus_in_cluster_ptr = per_cpu(cpus_in_cluster, cpu); dest = 0; - - /* Collect cpus in cluster. */ - for_each_cpu_and(i, ipi_mask_ptr, cpus_in_cluster_ptr) { - if (apic_dest == APIC_DEST_ALLINC || i != this_cpu) - dest |= per_cpu(x86_cpu_to_logical_apicid, i); - } + for_each_cpu_and(clustercpu, tmpmsk, &cmsk->mask) + dest |= per_cpu(x86_cpu_to_logical_apicid, clustercpu); if (!dest) continue; __x2apic_send_IPI_dest(dest, vector, apic->dest_logical); - /* - * Cluster sibling cpus should be discared now so - * we would not send IPI them second time. - */ - cpumask_andnot(ipi_mask_ptr, ipi_mask_ptr, cpus_in_cluster_ptr); + /* Remove cluster CPUs from tmpmask */ + cpumask_andnot(tmpmsk, tmpmsk, &cmsk->mask); } local_irq_restore(flags); @@ -104,125 +92,90 @@ static void x2apic_send_IPI_all(int vector) __x2apic_send_IPI_mask(cpu_online_mask, vector, APIC_DEST_ALLINC); } -static int -x2apic_cpu_mask_to_apicid(const struct cpumask *mask, struct irq_data *irqdata, - unsigned int *apicid) +static u32 x2apic_calc_apicid(unsigned int cpu) { - struct cpumask *effmsk = irq_data_get_effective_affinity_mask(irqdata); - unsigned int cpu; - u32 dest = 0; - u16 cluster; - - cpu = cpumask_first(mask); - if (cpu >= nr_cpu_ids) - return -EINVAL; - - dest = per_cpu(x86_cpu_to_logical_apicid, cpu); - cluster = x2apic_cluster(cpu); - - cpumask_clear(effmsk); - for_each_cpu(cpu, mask) { - if (cluster != x2apic_cluster(cpu)) - continue; - dest |= per_cpu(x86_cpu_to_logical_apicid, cpu); - cpumask_set_cpu(cpu, effmsk); - } - - *apicid = dest; - return 0; + return per_cpu(x86_cpu_to_logical_apicid, cpu); } static void init_x2apic_ldr(void) { - unsigned int this_cpu = smp_processor_id(); + struct cluster_mask *cmsk = this_cpu_read(cluster_masks); + u32 cluster, apicid = apic_read(APIC_LDR); unsigned int cpu; - per_cpu(x86_cpu_to_logical_apicid, this_cpu) = apic_read(APIC_LDR); + this_cpu_write(x86_cpu_to_logical_apicid, apicid); + + if (cmsk) + goto update; - cpumask_set_cpu(this_cpu, per_cpu(cpus_in_cluster, this_cpu)); + cluster = apicid >> 16; for_each_online_cpu(cpu) { - if (x2apic_cluster(this_cpu) != x2apic_cluster(cpu)) - continue; - cpumask_set_cpu(this_cpu, per_cpu(cpus_in_cluster, cpu)); - cpumask_set_cpu(cpu, per_cpu(cpus_in_cluster, this_cpu)); + cmsk = per_cpu(cluster_masks, cpu); + /* Matching cluster found. Link and update it. */ + if (cmsk && cmsk->clusterid == cluster) + goto update; } + cmsk = cluster_hotplug_mask; + cluster_hotplug_mask = NULL; +update: + this_cpu_write(cluster_masks, cmsk); + cpumask_set_cpu(smp_processor_id(), &cmsk->mask); } -/* - * At CPU state changes, update the x2apic cluster sibling info. - */ -static int x2apic_prepare_cpu(unsigned int cpu) +static int alloc_clustermask(unsigned int cpu, int node) { - if (!zalloc_cpumask_var(&per_cpu(cpus_in_cluster, cpu), GFP_KERNEL)) - return -ENOMEM; + if (per_cpu(cluster_masks, cpu)) + return 0; + /* + * If a hotplug spare mask exists, check whether it's on the right + * node. If not, free it and allocate a new one. + */ + if (cluster_hotplug_mask) { + if (cluster_hotplug_mask->node == node) + return 0; + kfree(cluster_hotplug_mask); + } - if (!zalloc_cpumask_var(&per_cpu(ipi_mask, cpu), GFP_KERNEL)) { - free_cpumask_var(per_cpu(cpus_in_cluster, cpu)); + cluster_hotplug_mask = kzalloc_node(sizeof(*cluster_hotplug_mask), + GFP_KERNEL, node); + if (!cluster_hotplug_mask) return -ENOMEM; - } + cluster_hotplug_mask->node = node; + return 0; +} +static int x2apic_prepare_cpu(unsigned int cpu) +{ + if (alloc_clustermask(cpu, cpu_to_node(cpu)) < 0) + return -ENOMEM; + if (!zalloc_cpumask_var(&per_cpu(ipi_mask, cpu), GFP_KERNEL)) + return -ENOMEM; return 0; } -static int x2apic_dead_cpu(unsigned int this_cpu) +static int x2apic_dead_cpu(unsigned int dead_cpu) { - int cpu; + struct cluster_mask *cmsk = per_cpu(cluster_masks, dead_cpu); - for_each_online_cpu(cpu) { - if (x2apic_cluster(this_cpu) != x2apic_cluster(cpu)) - continue; - cpumask_clear_cpu(this_cpu, per_cpu(cpus_in_cluster, cpu)); - cpumask_clear_cpu(cpu, per_cpu(cpus_in_cluster, this_cpu)); - } - free_cpumask_var(per_cpu(cpus_in_cluster, this_cpu)); - free_cpumask_var(per_cpu(ipi_mask, this_cpu)); + cpumask_clear_cpu(dead_cpu, &cmsk->mask); + free_cpumask_var(per_cpu(ipi_mask, dead_cpu)); return 0; } static int x2apic_cluster_probe(void) { - int cpu = smp_processor_id(); - int ret; - if (!x2apic_mode) return 0; - ret = cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "x86/x2apic:prepare", - x2apic_prepare_cpu, x2apic_dead_cpu); - if (ret < 0) { + if (cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "x86/x2apic:prepare", + x2apic_prepare_cpu, x2apic_dead_cpu) < 0) { pr_err("Failed to register X2APIC_PREPARE\n"); return 0; } - cpumask_set_cpu(cpu, per_cpu(cpus_in_cluster, cpu)); + init_x2apic_ldr(); return 1; } -static const struct cpumask *x2apic_cluster_target_cpus(void) -{ - return cpu_all_mask; -} - -/* - * Each x2apic cluster is an allocation domain. - */ -static void cluster_vector_allocation_domain(int cpu, struct cpumask *retmask, - const struct cpumask *mask) -{ - /* - * To minimize vector pressure, default case of boot, device bringup - * etc will use a single cpu for the interrupt destination. - * - * On explicit migration requests coming from irqbalance etc, - * interrupts will be routed to the x2apic cluster (cluster-id - * derived from the first cpu in the mask) members specified - * in the mask. - */ - if (mask == x2apic_cluster_target_cpus()) - cpumask_copy(retmask, cpumask_of(cpu)); - else - cpumask_and(retmask, mask, per_cpu(cpus_in_cluster, cpu)); -} - static struct apic apic_x2apic_cluster __ro_after_init = { .name = "cluster x2apic", @@ -234,12 +187,10 @@ static struct apic apic_x2apic_cluster __ro_after_init = { .irq_delivery_mode = dest_LowestPrio, .irq_dest_mode = 1, /* logical */ - .target_cpus = x2apic_cluster_target_cpus, .disable_esr = 0, .dest_logical = APIC_DEST_LOGICAL, .check_apicid_used = NULL, - .vector_allocation_domain = cluster_vector_allocation_domain, .init_apic_ldr = init_x2apic_ldr, .ioapic_phys_id_map = NULL, @@ -252,7 +203,7 @@ static struct apic apic_x2apic_cluster __ro_after_init = { .get_apic_id = x2apic_get_apic_id, .set_apic_id = x2apic_set_apic_id, - .cpu_mask_to_apicid = x2apic_cpu_mask_to_apicid, + .calc_dest_apicid = x2apic_calc_apicid, .send_IPI = x2apic_send_IPI, .send_IPI_mask = x2apic_send_IPI_mask, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 3baf0c3dc875..f8d9d69994e6 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/threads.h> #include <linux/cpumask.h> #include <linux/string.h> @@ -6,7 +7,8 @@ #include <linux/dmar.h> #include <asm/smp.h> -#include <asm/x2apic.h> +#include <asm/ipi.h> +#include "x2apic.h" int x2apic_phys; @@ -98,6 +100,43 @@ static int x2apic_phys_probe(void) return apic == &apic_x2apic_phys; } +/* Common x2apic functions, also used by x2apic_cluster */ +int x2apic_apic_id_valid(int apicid) +{ + return 1; +} + +int x2apic_apic_id_registered(void) +{ + return 1; +} + +void __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest) +{ + unsigned long cfg = __prepare_ICR(0, vector, dest); + native_x2apic_icr_write(cfg, apicid); +} + +unsigned int x2apic_get_apic_id(unsigned long id) +{ + return id; +} + +u32 x2apic_set_apic_id(unsigned int id) +{ + return id; +} + +int x2apic_phys_pkg_id(int initial_apicid, int index_msb) +{ + return initial_apicid >> index_msb; +} + +void x2apic_send_IPI_self(int vector) +{ + apic_write(APIC_SELF_IPI, vector); +} + static struct apic apic_x2apic_phys __ro_after_init = { .name = "physical x2apic", @@ -109,12 +148,10 @@ static struct apic apic_x2apic_phys __ro_after_init = { .irq_delivery_mode = dest_Fixed, .irq_dest_mode = 0, /* physical */ - .target_cpus = online_target_cpus, .disable_esr = 0, .dest_logical = 0, .check_apicid_used = NULL, - .vector_allocation_domain = default_vector_allocation_domain, .init_apic_ldr = init_x2apic_ldr, .ioapic_phys_id_map = NULL, @@ -127,7 +164,7 @@ static struct apic apic_x2apic_phys __ro_after_init = { .get_apic_id = x2apic_get_apic_id, .set_apic_id = x2apic_set_apic_id, - .cpu_mask_to_apicid = default_cpu_mask_to_apicid, + .calc_dest_apicid = apic_default_calc_apicid, .send_IPI = x2apic_send_IPI, .send_IPI_mask = x2apic_send_IPI_mask, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 0d57bb9079c9..e1b8e8bf6b3c 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -154,6 +154,48 @@ static int __init early_get_pnodeid(void) return pnode; } +static void __init uv_tsc_check_sync(void) +{ + u64 mmr; + int sync_state; + int mmr_shift; + char *state; + bool valid; + + /* Accommodate different UV arch BIOSes */ + mmr = uv_early_read_mmr(UVH_TSC_SYNC_MMR); + mmr_shift = + is_uv1_hub() ? 0 : + is_uv2_hub() ? UVH_TSC_SYNC_SHIFT_UV2K : UVH_TSC_SYNC_SHIFT; + if (mmr_shift) + sync_state = (mmr >> mmr_shift) & UVH_TSC_SYNC_MASK; + else + sync_state = 0; + + switch (sync_state) { + case UVH_TSC_SYNC_VALID: + state = "in sync"; + valid = true; + break; + + case UVH_TSC_SYNC_INVALID: + state = "unstable"; + valid = false; + break; + default: + state = "unknown: assuming valid"; + valid = true; + break; + } + pr_info("UV: TSC sync state from BIOS:0%d(%s)\n", sync_state, state); + + /* Mark flag that says TSC != 0 is valid for socket 0 */ + if (valid) + mark_tsc_async_resets("UV BIOS"); + else + mark_tsc_unstable("UV BIOS"); +} + /* [Copied from arch/x86/kernel/cpu/topology.c:detect_extended_topology()] */ #define SMT_LEVEL 0 /* Leaf 0xb SMT level */ @@ -288,6 +330,7 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) } 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); + uv_tsc_check_sync(); return uv_apic; @@ -525,16 +568,9 @@ static void uv_init_apic_ldr(void) { } -static int -uv_cpu_mask_to_apicid(const struct cpumask *mask, struct irq_data *irqdata, - unsigned int *apicid) +static u32 apic_uv_calc_apicid(unsigned int cpu) { - int ret = default_cpu_mask_to_apicid(mask, irqdata, apicid); - - if (!ret) - *apicid |= uv_apicid_hibits; - - return ret; + return apic_default_calc_apicid(cpu) | uv_apicid_hibits; } static unsigned int x2apic_get_apic_id(unsigned long x) @@ -547,7 +583,7 @@ static unsigned int x2apic_get_apic_id(unsigned long x) return id; } -static unsigned long set_apic_id(unsigned int id) +static u32 set_apic_id(unsigned int id) { /* CHECKME: Do we need to mask out the xapic extra bits? */ return id; @@ -584,12 +620,10 @@ static struct apic apic_x2apic_uv_x __ro_after_init = { .irq_delivery_mode = dest_Fixed, .irq_dest_mode = 0, /* Physical */ - .target_cpus = online_target_cpus, .disable_esr = 0, .dest_logical = APIC_DEST_LOGICAL, .check_apicid_used = NULL, - .vector_allocation_domain = default_vector_allocation_domain, .init_apic_ldr = uv_init_apic_ldr, .ioapic_phys_id_map = NULL, @@ -602,7 +636,7 @@ static struct apic apic_x2apic_uv_x __ro_after_init = { .get_apic_id = x2apic_get_apic_id, .set_apic_id = set_apic_id, - .cpu_mask_to_apicid = uv_cpu_mask_to_apicid, + .calc_dest_apicid = apic_uv_calc_apicid, .send_IPI = uv_send_IPI_one, .send_IPI_mask = uv_send_IPI_mask, @@ -920,9 +954,8 @@ static __init void uv_rtc_init(void) /* * percpu heartbeat timer */ -static void uv_heartbeat(unsigned long ignored) +static void uv_heartbeat(struct timer_list *timer) { - struct timer_list *timer = &uv_scir_info->timer; unsigned char bits = uv_scir_info->state; /* Flip heartbeat bit: */ @@ -947,7 +980,7 @@ static int uv_heartbeat_enable(unsigned int cpu) struct timer_list *timer = &uv_cpu_scir_info(cpu)->timer; uv_set_cpu_scir_bits(cpu, SCIR_CPU_HEARTBEAT|SCIR_CPU_ACTIVITY); - setup_pinned_timer(timer, uv_heartbeat, cpu); + timer_setup(timer, uv_heartbeat, TIMER_PINNED); timer->expires = jiffies + SCIR_CPU_HB_INTERVAL; add_timer_on(timer, cpu); uv_cpu_scir_info(cpu)->enabled = 1; diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 446b0d3d4932..e4b0d92b3ae0 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -2043,7 +2043,7 @@ static int __init swab_apm_power_in_minutes(const struct dmi_system_id *d) return 0; } -static struct dmi_system_id __initdata apm_dmi_table[] = { +static const struct dmi_system_id apm_dmi_table[] __initconst = { { print_if_true, KERN_WARNING "IBM T23 - BIOS 1.03b+ and controller firmware 1.02+ may be needed for Linux APM.", diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index de827d6ac8c2..8ea78275480d 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Generate definitions needed by assembly language modules. * This code generates raw asm output which is post-processed to extract diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index 880aa093268d..dedf428b20b6 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -1,12 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 #ifndef __LINUX_KBUILD_H # error "Please do not build this file directly, build asm-offsets.c instead" #endif #include <asm/ucontext.h> -#include <linux/lguest.h> -#include "../../../drivers/lguest/lg.h" - #define __SYSCALL_I386(nr, sym, qual) [nr] = 1, static char syscalls[] = { #include <asm/syscalls_32.h> @@ -62,23 +60,6 @@ void foo(void) OFFSET(stack_canary_offset, stack_canary, canary); #endif -#if defined(CONFIG_LGUEST) || defined(CONFIG_LGUEST_GUEST) || defined(CONFIG_LGUEST_MODULE) - BLANK(); - OFFSET(LGUEST_DATA_irq_enabled, lguest_data, irq_enabled); - OFFSET(LGUEST_DATA_irq_pending, lguest_data, irq_pending); - - BLANK(); - OFFSET(LGUEST_PAGES_host_gdt_desc, lguest_pages, state.host_gdt_desc); - OFFSET(LGUEST_PAGES_host_idt_desc, lguest_pages, state.host_idt_desc); - OFFSET(LGUEST_PAGES_host_cr3, lguest_pages, state.host_cr3); - OFFSET(LGUEST_PAGES_host_sp, lguest_pages, state.host_sp); - OFFSET(LGUEST_PAGES_guest_gdt_desc, lguest_pages,state.guest_gdt_desc); - OFFSET(LGUEST_PAGES_guest_idt_desc, lguest_pages,state.guest_idt_desc); - OFFSET(LGUEST_PAGES_guest_gdt, lguest_pages, state.guest_gdt); - OFFSET(LGUEST_PAGES_regs_trapnum, lguest_pages, regs.trapnum); - OFFSET(LGUEST_PAGES_regs_errcode, lguest_pages, regs.errcode); - OFFSET(LGUEST_PAGES_regs, lguest_pages, regs); -#endif BLANK(); DEFINE(__NR_syscall_max, sizeof(syscalls) - 1); DEFINE(NR_syscalls, sizeof(syscalls)); diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 99332f550c48..630212fa9b9d 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #ifndef __LINUX_KBUILD_H # error "Please do not build this file directly, build asm-offsets.c instead" #endif @@ -20,7 +21,6 @@ static char syscalls_ia32[] = { int main(void) { #ifdef CONFIG_PARAVIRT - OFFSET(PV_IRQ_adjust_exception_frame, pv_irq_ops, adjust_exception_frame); OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64); OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs); BLANK(); diff --git a/arch/x86/kernel/audit_64.c b/arch/x86/kernel/audit_64.c index f3672508b249..e1efe44ebefc 100644 --- a/arch/x86/kernel/audit_64.c +++ b/arch/x86/kernel/audit_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/init.h> #include <linux/types.h> #include <linux/audit.h> diff --git a/arch/x86/kernel/bootflag.c b/arch/x86/kernel/bootflag.c index 52c8e3c7789d..3fed7ae58b60 100644 --- a/arch/x86/kernel/bootflag.c +++ b/arch/x86/kernel/bootflag.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Implement 'Simple Boot Flag Specification 2.0' */ diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c index 145863d4d343..33399426793e 100644 --- a/arch/x86/kernel/check.c +++ b/arch/x86/kernel/check.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/init.h> #include <linux/sched.h> #include <linux/kthread.h> diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index cdf82492b770..570e8bb1f386 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Makefile for x86-compatible CPU details, features and quirks # @@ -21,7 +22,8 @@ obj-y += common.o obj-y += rdrand.o obj-y += match.o obj-y += bugs.o -obj-$(CONFIG_CPU_FREQ) += aperfmperf.o +obj-y += aperfmperf.o +obj-y += cpuid-deps.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o @@ -33,7 +35,7 @@ obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o obj-$(CONFIG_CPU_SUP_TRANSMETA_32) += transmeta.o obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o -obj-$(CONFIG_INTEL_RDT_A) += intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_schemata.o +obj-$(CONFIG_INTEL_RDT) += intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_monitor.o intel_rdt_ctrlmondata.o obj-$(CONFIG_X86_MCE) += mcheck/ obj-$(CONFIG_MTRR) += mtrr/ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 3b9e220621f8..d58184b7cd44 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -297,13 +297,29 @@ static int nearby_node(int apicid) } #endif +#ifdef CONFIG_SMP +/* + * Fix up cpu_core_id for pre-F17h systems to be in the + * [0 .. cores_per_node - 1] range. Not really needed but + * kept so as not to break existing setups. + */ +static void legacy_fixup_core_id(struct cpuinfo_x86 *c) +{ + u32 cus_per_node; + + if (c->x86 >= 0x17) + return; + + cus_per_node = c->x86_max_cores / nodes_per_socket; + c->cpu_core_id %= cus_per_node; +} + /* * Fixup core topology information for * (1) AMD multi-node processors * Assumption: Number of cores in each internal node is the same. * (2) AMD processors supporting compute units */ -#ifdef CONFIG_SMP static void amd_get_topology(struct cpuinfo_x86 *c) { u8 node_id; @@ -354,15 +370,9 @@ static void amd_get_topology(struct cpuinfo_x86 *c) } else return; - /* fixup multi-node processor information */ if (nodes_per_socket > 1) { - u32 cus_per_node; - set_cpu_cap(c, X86_FEATURE_AMD_DCM); - cus_per_node = c->x86_max_cores / nodes_per_socket; - - /* core id has to be in the [0 .. cores_per_node - 1] range */ - c->cpu_core_id %= cus_per_node; + legacy_fixup_core_id(c); } } #endif @@ -548,8 +558,12 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) static void early_init_amd(struct cpuinfo_x86 *c) { + u32 dummy; + early_init_amd_mc(c); + rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy); + /* * c->x86_power is 8000_0007 edx. Bit 8 is TSC runs at constant rate * with P/T states and does not stop in deep C-states @@ -612,6 +626,27 @@ static void early_init_amd(struct cpuinfo_x86 *c) */ if (cpu_has_amd_erratum(c, amd_erratum_400)) set_cpu_bug(c, X86_BUG_AMD_E400); + + /* + * BIOS support is required for SME. If BIOS has enabled SME then + * adjust x86_phys_bits by the SME physical address space reduction + * value. If BIOS has not enabled SME then don't advertise the + * feature (set in scattered.c). Also, since the SME support requires + * long mode, don't advertise the feature under CONFIG_X86_32. + */ + if (cpu_has(c, X86_FEATURE_SME)) { + u64 msr; + + /* Check if SME is enabled */ + rdmsrl(MSR_K8_SYSCFG, msr); + if (msr & MSR_K8_SYSCFG_MEM_ENCRYPT) { + c->x86_phys_bits -= (cpuid_ebx(0x8000001f) >> 6) & 0x3f; + if (IS_ENABLED(CONFIG_X86_32)) + clear_cpu_cap(c, X86_FEATURE_SME); + } else { + clear_cpu_cap(c, X86_FEATURE_SME); + } + } } static void init_amd_k8(struct cpuinfo_x86 *c) @@ -728,10 +763,18 @@ static void init_amd_bd(struct cpuinfo_x86 *c) } } -static void init_amd(struct cpuinfo_x86 *c) +static void init_amd_zn(struct cpuinfo_x86 *c) { - u32 dummy; + /* + * Fix erratum 1076: CPB feature bit not being set in CPUID. It affects + * all up to and including B1. + */ + if (c->x86_model <= 1 && c->x86_mask <= 1) + set_cpu_cap(c, X86_FEATURE_CPB); +} +static void init_amd(struct cpuinfo_x86 *c) +{ early_init_amd(c); /* @@ -758,6 +801,7 @@ static void init_amd(struct cpuinfo_x86 *c) case 0x10: init_amd_gh(c); break; case 0x12: init_amd_ln(c); break; case 0x15: init_amd_bd(c); break; + case 0x17: init_amd_zn(c); break; } /* Enable workaround for FXSAVE leak */ @@ -793,8 +837,6 @@ static void init_amd(struct cpuinfo_x86 *c) if (c->x86 > 0x11) set_cpu_cap(c, X86_FEATURE_ARAT); - rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy); - /* 3DNow or LM implies PREFETCHW */ if (!cpu_has(c, X86_FEATURE_3DNOWPREFETCH)) if (cpu_has(c, X86_FEATURE_3DNOW) || cpu_has(c, X86_FEATURE_LM)) diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c index d869c8671e36..7eba34df54c3 100644 --- a/arch/x86/kernel/cpu/aperfmperf.c +++ b/arch/x86/kernel/cpu/aperfmperf.c @@ -8,20 +8,27 @@ * This file is licensed under GPLv2. */ -#include <linux/jiffies.h> +#include <linux/delay.h> +#include <linux/ktime.h> #include <linux/math64.h> #include <linux/percpu.h> #include <linux/smp.h> +#include "cpu.h" + struct aperfmperf_sample { unsigned int khz; - unsigned long jiffies; + ktime_t time; u64 aperf; u64 mperf; }; static DEFINE_PER_CPU(struct aperfmperf_sample, samples); +#define APERFMPERF_CACHE_THRESHOLD_MS 10 +#define APERFMPERF_REFRESH_DELAY_MS 10 +#define APERFMPERF_STALE_THRESHOLD_MS 1000 + /* * aperfmperf_snapshot_khz() * On the current CPU, snapshot APERF, MPERF, and jiffies @@ -33,13 +40,12 @@ static void aperfmperf_snapshot_khz(void *dummy) u64 aperf, aperf_delta; u64 mperf, mperf_delta; struct aperfmperf_sample *s = this_cpu_ptr(&samples); + unsigned long flags; - /* Don't bother re-computing within 10 ms */ - if (time_before(jiffies, s->jiffies + HZ/100)) - return; - + local_irq_save(flags); rdmsrl(MSR_IA32_APERF, aperf); rdmsrl(MSR_IA32_MPERF, mperf); + local_irq_restore(flags); aperf_delta = aperf - s->aperf; mperf_delta = mperf - s->mperf; @@ -51,18 +57,56 @@ static void aperfmperf_snapshot_khz(void *dummy) if (mperf_delta == 0) return; - /* - * if (cpu_khz * aperf_delta) fits into ULLONG_MAX, then - * khz = (cpu_khz * aperf_delta) / mperf_delta - */ - if (div64_u64(ULLONG_MAX, cpu_khz) > aperf_delta) - s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta); - else /* khz = aperf_delta / (mperf_delta / cpu_khz) */ - s->khz = div64_u64(aperf_delta, - div64_u64(mperf_delta, cpu_khz)); - s->jiffies = jiffies; + s->time = ktime_get(); s->aperf = aperf; s->mperf = mperf; + s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta); +} + +static bool aperfmperf_snapshot_cpu(int cpu, ktime_t now, bool wait) +{ + s64 time_delta = ktime_ms_delta(now, per_cpu(samples.time, cpu)); + + /* Don't bother re-computing within the cache threshold time. */ + if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS) + return true; + + smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, wait); + + /* Return false if the previous iteration was too long ago. */ + return time_delta <= APERFMPERF_STALE_THRESHOLD_MS; +} + +unsigned int aperfmperf_get_khz(int cpu) +{ + if (!cpu_khz) + return 0; + + if (!static_cpu_has(X86_FEATURE_APERFMPERF)) + return 0; + + aperfmperf_snapshot_cpu(cpu, ktime_get(), true); + return per_cpu(samples.khz, cpu); +} + +void arch_freq_prepare_all(void) +{ + ktime_t now = ktime_get(); + bool wait = false; + int cpu; + + if (!cpu_khz) + return; + + if (!static_cpu_has(X86_FEATURE_APERFMPERF)) + return; + + for_each_online_cpu(cpu) + if (!aperfmperf_snapshot_cpu(cpu, now, false)) + wait = true; + + if (wait) + msleep(APERFMPERF_REFRESH_DELAY_MS); } unsigned int arch_freq_get_on_cpu(int cpu) @@ -73,6 +117,10 @@ unsigned int arch_freq_get_on_cpu(int cpu) if (!static_cpu_has(X86_FEATURE_APERFMPERF)) return 0; + if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true)) + return per_cpu(samples.khz, cpu); + + msleep(APERFMPERF_REFRESH_DELAY_MS); smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1); return per_cpu(samples.khz, cpu); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 0af86d9242da..ba0b2424c9b0 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1994 Linus Torvalds * diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 44207b71fee1..68bc6d9b3132 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/sched.h> #include <linux/sched/clock.h> diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index c8b39870f33e..fa998ca8aa5a 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -168,6 +168,24 @@ static int __init x86_mpx_setup(char *s) } __setup("nompx", x86_mpx_setup); +#ifdef CONFIG_X86_64 +static int __init x86_nopcid_setup(char *s) +{ + /* nopcid doesn't accept parameters */ + if (s) + return -EINVAL; + + /* do not emit a message if the feature is not present */ + if (!boot_cpu_has(X86_FEATURE_PCID)) + return 0; + + setup_clear_cpu_cap(X86_FEATURE_PCID); + pr_info("nopcid: PCID feature disabled\n"); + return 0; +} +early_param("nopcid", x86_nopcid_setup); +#endif + static int __init x86_noinvpcid_setup(char *s) { /* noinvpcid doesn't accept parameters */ @@ -311,6 +329,30 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c) } } +static __always_inline void setup_umip(struct cpuinfo_x86 *c) +{ + /* Check the boot processor, plus build option for UMIP. */ + if (!cpu_feature_enabled(X86_FEATURE_UMIP)) + goto out; + + /* Check the current processor's cpuid bits. */ + if (!cpu_has(c, X86_FEATURE_UMIP)) + goto out; + + cr4_set_bits(X86_CR4_UMIP); + + pr_info("x86/cpu: Activated the Intel User Mode Instruction Prevention (UMIP) CPU feature\n"); + + return; + +out: + /* + * Make sure UMIP is disabled in case it was enabled in a + * previous boot (e.g., via kexec). + */ + cr4_clear_bits(X86_CR4_UMIP); +} + /* * Protection Keys are not available in 32-bit mode. */ @@ -845,8 +887,8 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) * cache alignment. * The others are not touched to avoid unwanted side effects. * - * WARNING: this function is only called on the BP. Don't add code here - * that is supposed to run on all CPUs. + * WARNING: this function is only called on the boot CPU. Don't add code + * here that is supposed to run on all CPUs. */ static void __init early_identify_cpu(struct cpuinfo_x86 *c) { @@ -886,6 +928,14 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) setup_force_cpu_cap(X86_FEATURE_ALWAYS); fpu__init_system(c); + +#ifdef CONFIG_X86_32 + /* + * Regardless of whether PCID is enumerated, the SDM says + * that it can't be enabled in 32-bit mode. + */ + setup_clear_cpu_cap(X86_FEATURE_PCID); +#endif } void __init early_cpu_init(void) @@ -1121,9 +1171,10 @@ static void identify_cpu(struct cpuinfo_x86 *c) /* Disable the PN if appropriate */ squash_the_stupid_serial_number(c); - /* Set up SMEP/SMAP */ + /* Set up SMEP/SMAP/UMIP */ setup_smep(c); setup_smap(c); + setup_umip(c); /* * The vendor-specific functions might have changed features. @@ -1275,29 +1326,18 @@ void print_cpu_info(struct cpuinfo_x86 *c) pr_cont(")\n"); } -static __init int setup_disablecpuid(char *arg) +/* + * clearcpuid= was already parsed in fpu__init_parse_early_param. + * But we need to keep a dummy __setup around otherwise it would + * show up as an environment variable for init. + */ +static __init int setup_clearcpuid(char *arg) { - int bit; - - if (get_option(&arg, &bit) && bit >= 0 && bit < NCAPINTS * 32) - setup_clear_cpu_cap(bit); - else - return 0; - return 1; } -__setup("clearcpuid=", setup_disablecpuid); +__setup("clearcpuid=", setup_clearcpuid); #ifdef CONFIG_X86_64 -struct desc_ptr idt_descr __ro_after_init = { - .size = NR_VECTORS * 16 - 1, - .address = (unsigned long) idt_table, -}; -const struct desc_ptr debug_idt_descr = { - .size = NR_VECTORS * 16 - 1, - .address = (unsigned long) debug_idt_table, -}; - DEFINE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __aligned(PAGE_SIZE) __visible; @@ -1552,11 +1592,16 @@ void cpu_init(void) mmgrab(&init_mm); me->active_mm = &init_mm; BUG_ON(me->mm); + initialize_tlbstate_and_flush(); enter_lazy_tlb(&init_mm, me); - load_sp0(t, ¤t->thread); + /* + * Initialize the TSS. Don't bother initializing sp0, as the initial + * task never enters user mode. + */ set_tss_desc(cpu, t); load_TR_desc(); + load_mm_ldt(&init_mm); clear_all_debug_regs(); @@ -1578,7 +1623,6 @@ void cpu_init(void) int cpu = smp_processor_id(); struct task_struct *curr = current; struct tss_struct *t = &per_cpu(cpu_tss, cpu); - struct thread_struct *thread = &curr->thread; wait_for_master_cpu(cpu); @@ -1606,11 +1650,16 @@ void cpu_init(void) mmgrab(&init_mm); curr->active_mm = &init_mm; BUG_ON(curr->mm); + initialize_tlbstate_and_flush(); enter_lazy_tlb(&init_mm, curr); - load_sp0(t, thread); + /* + * Initialize the TSS. Don't bother initializing sp0, as the initial + * task never enters user mode. + */ set_tss_desc(cpu, t); load_TR_desc(); + load_mm_ldt(&init_mm); t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap); diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 2584265d4745..e806b11a99af 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef ARCH_X86_CPU_H #define ARCH_X86_CPU_H @@ -46,4 +47,7 @@ extern const struct cpu_dev *const __x86_cpu_dev_start[], extern void get_cpu_cap(struct cpuinfo_x86 *c); extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c); + +unsigned int aperfmperf_get_khz(int cpu); + #endif /* ARCH_X86_CPU_H */ diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c new file mode 100644 index 000000000000..904b0a3c4e53 --- /dev/null +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -0,0 +1,121 @@ +/* Declare dependencies between CPUIDs */ +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <asm/cpufeature.h> + +struct cpuid_dep { + unsigned int feature; + unsigned int depends; +}; + +/* + * Table of CPUID features that depend on others. + * + * This only includes dependencies that can be usefully disabled, not + * features part of the base set (like FPU). + * + * Note this all is not __init / __initdata because it can be + * called from cpu hotplug. It shouldn't do anything in this case, + * but it's difficult to tell that to the init reference checker. + */ +const static struct cpuid_dep cpuid_deps[] = { + { X86_FEATURE_XSAVEOPT, X86_FEATURE_XSAVE }, + { X86_FEATURE_XSAVEC, X86_FEATURE_XSAVE }, + { X86_FEATURE_XSAVES, X86_FEATURE_XSAVE }, + { X86_FEATURE_AVX, X86_FEATURE_XSAVE }, + { X86_FEATURE_PKU, X86_FEATURE_XSAVE }, + { X86_FEATURE_MPX, X86_FEATURE_XSAVE }, + { X86_FEATURE_XGETBV1, X86_FEATURE_XSAVE }, + { X86_FEATURE_FXSR_OPT, X86_FEATURE_FXSR }, + { X86_FEATURE_XMM, X86_FEATURE_FXSR }, + { X86_FEATURE_XMM2, X86_FEATURE_XMM }, + { X86_FEATURE_XMM3, X86_FEATURE_XMM2 }, + { X86_FEATURE_XMM4_1, X86_FEATURE_XMM2 }, + { X86_FEATURE_XMM4_2, X86_FEATURE_XMM2 }, + { X86_FEATURE_XMM3, X86_FEATURE_XMM2 }, + { X86_FEATURE_PCLMULQDQ, X86_FEATURE_XMM2 }, + { X86_FEATURE_SSSE3, X86_FEATURE_XMM2, }, + { X86_FEATURE_F16C, X86_FEATURE_XMM2, }, + { X86_FEATURE_AES, X86_FEATURE_XMM2 }, + { X86_FEATURE_SHA_NI, X86_FEATURE_XMM2 }, + { X86_FEATURE_FMA, X86_FEATURE_AVX }, + { X86_FEATURE_AVX2, X86_FEATURE_AVX, }, + { X86_FEATURE_AVX512F, X86_FEATURE_AVX, }, + { X86_FEATURE_AVX512IFMA, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512PF, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512ER, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512CD, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512DQ, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512BW, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512VL, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512VBMI, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512_VBMI2, X86_FEATURE_AVX512VL }, + { X86_FEATURE_GFNI, X86_FEATURE_AVX512VL }, + { X86_FEATURE_VAES, X86_FEATURE_AVX512VL }, + { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX512VL }, + { X86_FEATURE_AVX512_VNNI, X86_FEATURE_AVX512VL }, + { X86_FEATURE_AVX512_BITALG, X86_FEATURE_AVX512VL }, + { X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512_4FMAPS, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512_VPOPCNTDQ, X86_FEATURE_AVX512F }, + {} +}; + +static inline void clear_feature(struct cpuinfo_x86 *c, unsigned int feature) +{ + /* + * Note: This could use the non atomic __*_bit() variants, but the + * rest of the cpufeature code uses atomics as well, so keep it for + * consistency. Cleanup all of it separately. + */ + if (!c) { + clear_cpu_cap(&boot_cpu_data, feature); + set_bit(feature, (unsigned long *)cpu_caps_cleared); + } else { + clear_bit(feature, (unsigned long *)c->x86_capability); + } +} + +/* Take the capabilities and the BUG bits into account */ +#define MAX_FEATURE_BITS ((NCAPINTS + NBUGINTS) * sizeof(u32) * 8) + +static void do_clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int feature) +{ + DECLARE_BITMAP(disable, MAX_FEATURE_BITS); + const struct cpuid_dep *d; + bool changed; + + if (WARN_ON(feature >= MAX_FEATURE_BITS)) + return; + + clear_feature(c, feature); + + /* Collect all features to disable, handling dependencies */ + memset(disable, 0, sizeof(disable)); + __set_bit(feature, disable); + + /* Loop until we get a stable state. */ + do { + changed = false; + for (d = cpuid_deps; d->feature; d++) { + if (!test_bit(d->depends, disable)) + continue; + if (__test_and_set_bit(d->feature, disable)) + continue; + + changed = true; + clear_feature(c, d->feature); + } + } while (changed); +} + +void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int feature) +{ + do_clear_cpu_cap(c, feature); +} + +void setup_clear_cpu_cap(unsigned int feature) +{ + do_clear_cpu_cap(NULL, feature); +} diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index 6f077445647a..6b4bb335641f 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/bitops.h> #include <linux/delay.h> #include <linux/pci.h> diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c index 4fa90006ac68..bea8d3e24f50 100644 --- a/arch/x86/kernel/cpu/hypervisor.c +++ b/arch/x86/kernel/cpu/hypervisor.c @@ -26,6 +26,12 @@ #include <asm/processor.h> #include <asm/hypervisor.h> +extern const struct hypervisor_x86 x86_hyper_vmware; +extern const struct hypervisor_x86 x86_hyper_ms_hyperv; +extern const struct hypervisor_x86 x86_hyper_xen_pv; +extern const struct hypervisor_x86 x86_hyper_xen_hvm; +extern const struct hypervisor_x86 x86_hyper_kvm; + static const __initconst struct hypervisor_x86 * const hypervisors[] = { #ifdef CONFIG_XEN_PV @@ -41,54 +47,52 @@ static const __initconst struct hypervisor_x86 * const hypervisors[] = #endif }; -const struct hypervisor_x86 *x86_hyper; -EXPORT_SYMBOL(x86_hyper); +enum x86_hypervisor_type x86_hyper_type; +EXPORT_SYMBOL(x86_hyper_type); -static inline void __init +static inline const struct hypervisor_x86 * __init detect_hypervisor_vendor(void) { - const struct hypervisor_x86 *h, * const *p; + const struct hypervisor_x86 *h = NULL, * const *p; uint32_t pri, max_pri = 0; for (p = hypervisors; p < hypervisors + ARRAY_SIZE(hypervisors); p++) { - h = *p; - pri = h->detect(); - if (pri != 0 && pri > max_pri) { + pri = (*p)->detect(); + if (pri > max_pri) { max_pri = pri; - x86_hyper = h; + h = *p; } } - if (max_pri) - pr_info("Hypervisor detected: %s\n", x86_hyper->name); + if (h) + pr_info("Hypervisor detected: %s\n", h->name); + + return h; } -void __init init_hypervisor_platform(void) +static void __init copy_array(const void *src, void *target, unsigned int size) { + unsigned int i, n = size / sizeof(void *); + const void * const *from = (const void * const *)src; + const void **to = (const void **)target; - detect_hypervisor_vendor(); - - if (!x86_hyper) - return; - - if (x86_hyper->init_platform) - x86_hyper->init_platform(); + for (i = 0; i < n; i++) + if (from[i]) + to[i] = from[i]; } -bool __init hypervisor_x2apic_available(void) +void __init init_hypervisor_platform(void) { - return x86_hyper && - x86_hyper->x2apic_available && - x86_hyper->x2apic_available(); -} + const struct hypervisor_x86 *h; -void hypervisor_pin_vcpu(int cpu) -{ - if (!x86_hyper) + h = detect_hypervisor_vendor(); + + if (!h) return; - if (x86_hyper->pin_vcpu) - x86_hyper->pin_vcpu(cpu); - else - WARN_ONCE(1, "vcpu pinning requested but not supported!\n"); + copy_array(&h->init, &x86_init.hyper, sizeof(h->init)); + copy_array(&h->runtime, &x86_platform.hyper, sizeof(h->runtime)); + + x86_hyper_type = h->type; + x86_init.hyper.init_platform(); } diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index dfa90a3a5145..b1af22073e28 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/string.h> @@ -186,21 +187,6 @@ static void early_init_intel(struct cpuinfo_x86 *c) if (c->x86 == 6 && c->x86_model < 15) clear_cpu_cap(c, X86_FEATURE_PAT); -#ifdef CONFIG_KMEMCHECK - /* - * P4s have a "fast strings" feature which causes single- - * stepping REP instructions to only generate a #DB on - * cache-line boundaries. - * - * Ingo Molnar reported a Pentium D (model 6) and a Xeon - * (model 2) with the same problem. - */ - if (c->x86 == 15) - if (msr_clear_bit(MSR_IA32_MISC_ENABLE, - MSR_IA32_MISC_ENABLE_FAST_STRING_BIT) > 0) - pr_info("kmemcheck: Disabling fast string operations\n"); -#endif - /* * If fast string is not enabled in IA32_MISC_ENABLE for any reason, * clear the fast string and enhanced fast string CPU capabilities. diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index c55fb2cb2acc..54d04d574148 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Routines to identify caches on Intel CPU. * @@ -811,10 +812,26 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index, struct cacheinfo *this_leaf; int i, sibling; - if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { + /* + * For L3, always use the pre-calculated cpu_llc_shared_mask + * to derive shared_cpu_map. + */ + if (index == 3) { + for_each_cpu(i, cpu_llc_shared_mask(cpu)) { + this_cpu_ci = get_cpu_cacheinfo(i); + if (!this_cpu_ci->info_list) + continue; + this_leaf = this_cpu_ci->info_list + index; + for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) { + if (!cpu_online(sibling)) + continue; + cpumask_set_cpu(sibling, + &this_leaf->shared_cpu_map); + } + } + } else if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { unsigned int apicid, nshared, first, last; - this_leaf = this_cpu_ci->info_list + index; nshared = base->eax.split.num_threads_sharing + 1; apicid = cpu_data(cpu).apicid; first = apicid - (apicid % nshared); @@ -839,19 +856,6 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index, &this_leaf->shared_cpu_map); } } - } else if (index == 3) { - for_each_cpu(i, cpu_llc_shared_mask(cpu)) { - this_cpu_ci = get_cpu_cacheinfo(i); - if (!this_cpu_ci->info_list) - continue; - this_leaf = this_cpu_ci->info_list + index; - for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) { - if (!cpu_online(sibling)) - continue; - cpumask_set_cpu(sibling, - &this_leaf->shared_cpu_map); - } - } } else return 0; diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index 5b366462f579..88dcf8479013 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -30,7 +30,8 @@ #include <linux/cpuhotplug.h> #include <asm/intel-family.h> -#include <asm/intel_rdt.h> +#include <asm/intel_rdt_sched.h> +#include "intel_rdt.h" #define MAX_MBA_BW 100u #define MBA_IS_LINEAR 0x4 @@ -38,7 +39,13 @@ /* Mutex to protect rdtgroup access. */ DEFINE_MUTEX(rdtgroup_mutex); -DEFINE_PER_CPU_READ_MOSTLY(int, cpu_closid); +/* + * The cached intel_pqr_state is strictly per CPU and can never be + * updated from a remote CPU. Functions which modify the state + * are called with interrupts disabled and no preemption, which + * is sufficient for the protection. + */ +DEFINE_PER_CPU(struct intel_pqr_state, pqr_state); /* * Used to store the max resource name width and max resource data width @@ -46,6 +53,12 @@ DEFINE_PER_CPU_READ_MOSTLY(int, cpu_closid); */ int max_name_width, max_data_width; +/* + * Global boolean for rdt_alloc which is true if any + * resource allocation is enabled. + */ +bool rdt_alloc_capable; + static void mba_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r); static void @@ -54,7 +67,9 @@ cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r); #define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].domains) struct rdt_resource rdt_resources_all[] = { + [RDT_RESOURCE_L3] = { + .rid = RDT_RESOURCE_L3, .name = "L3", .domains = domain_init(RDT_RESOURCE_L3), .msr_base = IA32_L3_CBM_BASE, @@ -67,8 +82,11 @@ struct rdt_resource rdt_resources_all[] = { }, .parse_ctrlval = parse_cbm, .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, }, + [RDT_RESOURCE_L3DATA] = { + .rid = RDT_RESOURCE_L3DATA, .name = "L3DATA", .domains = domain_init(RDT_RESOURCE_L3DATA), .msr_base = IA32_L3_CBM_BASE, @@ -81,8 +99,11 @@ struct rdt_resource rdt_resources_all[] = { }, .parse_ctrlval = parse_cbm, .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, }, + [RDT_RESOURCE_L3CODE] = { + .rid = RDT_RESOURCE_L3CODE, .name = "L3CODE", .domains = domain_init(RDT_RESOURCE_L3CODE), .msr_base = IA32_L3_CBM_BASE, @@ -95,8 +116,11 @@ struct rdt_resource rdt_resources_all[] = { }, .parse_ctrlval = parse_cbm, .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, }, + [RDT_RESOURCE_L2] = { + .rid = RDT_RESOURCE_L2, .name = "L2", .domains = domain_init(RDT_RESOURCE_L2), .msr_base = IA32_L2_CBM_BASE, @@ -109,8 +133,11 @@ struct rdt_resource rdt_resources_all[] = { }, .parse_ctrlval = parse_cbm, .format_str = "%d=%0*x", + .fflags = RFTYPE_RES_CACHE, }, + [RDT_RESOURCE_MBA] = { + .rid = RDT_RESOURCE_MBA, .name = "MB", .domains = domain_init(RDT_RESOURCE_MBA), .msr_base = IA32_MBA_THRTL_BASE, @@ -118,6 +145,7 @@ struct rdt_resource rdt_resources_all[] = { .cache_level = 3, .parse_ctrlval = parse_bw, .format_str = "%d=%*d", + .fflags = RFTYPE_RES_MB, }, }; @@ -144,33 +172,28 @@ static unsigned int cbm_idx(struct rdt_resource *r, unsigned int closid) * is always 20 on hsw server parts. The minimum cache bitmask length * allowed for HSW server is always 2 bits. Hardcode all of them. */ -static inline bool cache_alloc_hsw_probe(void) +static inline void cache_alloc_hsw_probe(void) { - if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && - boot_cpu_data.x86 == 6 && - boot_cpu_data.x86_model == INTEL_FAM6_HASWELL_X) { - struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3]; - u32 l, h, max_cbm = BIT_MASK(20) - 1; - - if (wrmsr_safe(IA32_L3_CBM_BASE, max_cbm, 0)) - return false; - rdmsr(IA32_L3_CBM_BASE, l, h); + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3]; + u32 l, h, max_cbm = BIT_MASK(20) - 1; - /* If all the bits were set in MSR, return success */ - if (l != max_cbm) - return false; + if (wrmsr_safe(IA32_L3_CBM_BASE, max_cbm, 0)) + return; + rdmsr(IA32_L3_CBM_BASE, l, h); - r->num_closid = 4; - r->default_ctrl = max_cbm; - r->cache.cbm_len = 20; - r->cache.min_cbm_bits = 2; - r->capable = true; - r->enabled = true; + /* If all the bits were set in MSR, return success */ + if (l != max_cbm) + return; - return true; - } + r->num_closid = 4; + r->default_ctrl = max_cbm; + r->cache.cbm_len = 20; + r->cache.shareable_bits = 0xc0000; + r->cache.min_cbm_bits = 2; + r->alloc_capable = true; + r->alloc_enabled = true; - return false; + rdt_alloc_capable = true; } /* @@ -213,15 +236,14 @@ static bool rdt_get_mem_config(struct rdt_resource *r) return false; } r->data_width = 3; - rdt_get_mba_infofile(r); - r->capable = true; - r->enabled = true; + r->alloc_capable = true; + r->alloc_enabled = true; return true; } -static void rdt_get_cache_config(int idx, struct rdt_resource *r) +static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r) { union cpuid_0x10_1_eax eax; union cpuid_0x10_x_edx edx; @@ -231,10 +253,10 @@ static void rdt_get_cache_config(int idx, struct rdt_resource *r) r->num_closid = edx.split.cos_max + 1; r->cache.cbm_len = eax.split.cbm_len + 1; r->default_ctrl = BIT_MASK(eax.split.cbm_len + 1) - 1; + r->cache.shareable_bits = ebx & r->default_ctrl; r->data_width = (r->cache.cbm_len + 3) / 4; - rdt_get_cache_infofile(r); - r->capable = true; - r->enabled = true; + r->alloc_capable = true; + r->alloc_enabled = true; } static void rdt_get_cdp_l3_config(int type) @@ -245,13 +267,14 @@ static void rdt_get_cdp_l3_config(int type) r->num_closid = r_l3->num_closid / 2; r->cache.cbm_len = r_l3->cache.cbm_len; r->default_ctrl = r_l3->default_ctrl; + r->cache.shareable_bits = r_l3->cache.shareable_bits; r->data_width = (r->cache.cbm_len + 3) / 4; - r->capable = true; + r->alloc_capable = true; /* * By default, CDP is disabled. CDP can be enabled by mount parameter * "cdp" during resctrl file system mount time. */ - r->enabled = false; + r->alloc_enabled = false; } static int get_cache_id(int cpu, int level) @@ -300,6 +323,19 @@ cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r) wrmsrl(r->msr_base + cbm_idx(r, i), d->ctrl_val[i]); } +struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r) +{ + struct rdt_domain *d; + + list_for_each_entry(d, &r->domains, list) { + /* Find the domain that contains this CPU */ + if (cpumask_test_cpu(cpu, &d->cpu_mask)) + return d; + } + + return NULL; +} + void rdt_ctrl_update(void *arg) { struct msr_param *m = arg; @@ -307,12 +343,10 @@ void rdt_ctrl_update(void *arg) int cpu = smp_processor_id(); struct rdt_domain *d; - list_for_each_entry(d, &r->domains, list) { - /* Find the domain that contains this CPU */ - if (cpumask_test_cpu(cpu, &d->cpu_mask)) { - r->msr_update(d, m, r); - return; - } + d = get_domain_from_cpu(cpu, r); + if (d) { + r->msr_update(d, m, r); + return; } pr_warn_once("cpu %d not found in any domain for resource %s\n", cpu, r->name); @@ -326,8 +360,8 @@ void rdt_ctrl_update(void *arg) * caller, return the first domain whose id is bigger than the input id. * The domain list is sorted by id in ascending order. */ -static struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id, - struct list_head **pos) +struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id, + struct list_head **pos) { struct rdt_domain *d; struct list_head *l; @@ -377,6 +411,44 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d) return 0; } +static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) +{ + size_t tsize; + + if (is_llc_occupancy_enabled()) { + d->rmid_busy_llc = kcalloc(BITS_TO_LONGS(r->num_rmid), + sizeof(unsigned long), + GFP_KERNEL); + if (!d->rmid_busy_llc) + return -ENOMEM; + INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo); + } + if (is_mbm_total_enabled()) { + tsize = sizeof(*d->mbm_total); + d->mbm_total = kcalloc(r->num_rmid, tsize, GFP_KERNEL); + if (!d->mbm_total) { + kfree(d->rmid_busy_llc); + return -ENOMEM; + } + } + if (is_mbm_local_enabled()) { + tsize = sizeof(*d->mbm_local); + d->mbm_local = kcalloc(r->num_rmid, tsize, GFP_KERNEL); + if (!d->mbm_local) { + kfree(d->rmid_busy_llc); + kfree(d->mbm_total); + return -ENOMEM; + } + } + + if (is_mbm_enabled()) { + INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow); + mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL); + } + + return 0; +} + /* * domain_add_cpu - Add a cpu to a resource's domain list. * @@ -412,14 +484,26 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) return; d->id = id; + cpumask_set_cpu(cpu, &d->cpu_mask); - if (domain_setup_ctrlval(r, d)) { + if (r->alloc_capable && domain_setup_ctrlval(r, d)) { + kfree(d); + return; + } + + if (r->mon_capable && domain_setup_mon_state(r, d)) { kfree(d); return; } - cpumask_set_cpu(cpu, &d->cpu_mask); list_add_tail(&d->list, add_pos); + + /* + * If resctrl is mounted, add + * per domain monitor data directories. + */ + if (static_branch_unlikely(&rdt_mon_enable_key)) + mkdir_mondata_subdir_allrdtgrp(r, d); } static void domain_remove_cpu(int cpu, struct rdt_resource *r) @@ -435,19 +519,58 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) cpumask_clear_cpu(cpu, &d->cpu_mask); if (cpumask_empty(&d->cpu_mask)) { + /* + * If resctrl is mounted, remove all the + * per domain monitor data directories. + */ + if (static_branch_unlikely(&rdt_mon_enable_key)) + rmdir_mondata_subdir_allrdtgrp(r, d->id); kfree(d->ctrl_val); + kfree(d->rmid_busy_llc); + kfree(d->mbm_total); + kfree(d->mbm_local); list_del(&d->list); + if (is_mbm_enabled()) + cancel_delayed_work(&d->mbm_over); + if (is_llc_occupancy_enabled() && has_busy_rmid(r, d)) { + /* + * When a package is going down, forcefully + * decrement rmid->ebusy. There is no way to know + * that the L3 was flushed and hence may lead to + * incorrect counts in rare scenarios, but leaving + * the RMID as busy creates RMID leaks if the + * package never comes back. + */ + __check_limbo(d, true); + cancel_delayed_work(&d->cqm_limbo); + } + kfree(d); + return; + } + + if (r == &rdt_resources_all[RDT_RESOURCE_L3]) { + if (is_mbm_enabled() && cpu == d->mbm_work_cpu) { + cancel_delayed_work(&d->mbm_over); + mbm_setup_overflow_handler(d, 0); + } + if (is_llc_occupancy_enabled() && cpu == d->cqm_work_cpu && + has_busy_rmid(r, d)) { + cancel_delayed_work(&d->cqm_limbo); + cqm_setup_limbo_handler(d, 0); + } } } -static void clear_closid(int cpu) +static void clear_closid_rmid(int cpu) { struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); - per_cpu(cpu_closid, cpu) = 0; - state->closid = 0; - wrmsr(MSR_IA32_PQR_ASSOC, state->rmid, 0); + state->default_closid = 0; + state->default_rmid = 0; + state->cur_closid = 0; + state->cur_rmid = 0; + wrmsr(IA32_PQR_ASSOC, 0, 0); } static int intel_rdt_online_cpu(unsigned int cpu) @@ -459,12 +582,23 @@ static int intel_rdt_online_cpu(unsigned int cpu) domain_add_cpu(cpu, r); /* The cpu is set in default rdtgroup after online. */ cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask); - clear_closid(cpu); + clear_closid_rmid(cpu); mutex_unlock(&rdtgroup_mutex); return 0; } +static void clear_childcpus(struct rdtgroup *r, unsigned int cpu) +{ + struct rdtgroup *cr; + + list_for_each_entry(cr, &r->mon.crdtgrp_list, mon.crdtgrp_list) { + if (cpumask_test_and_clear_cpu(cpu, &cr->cpu_mask)) { + break; + } + } +} + static int intel_rdt_offline_cpu(unsigned int cpu) { struct rdtgroup *rdtgrp; @@ -474,10 +608,12 @@ static int intel_rdt_offline_cpu(unsigned int cpu) for_each_capable_rdt_resource(r) domain_remove_cpu(cpu, r); list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) { - if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) + if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) { + clear_childcpus(rdtgrp, cpu); break; + } } - clear_closid(cpu); + clear_closid_rmid(cpu); mutex_unlock(&rdtgroup_mutex); return 0; @@ -492,7 +628,7 @@ static __init void rdt_init_padding(void) struct rdt_resource *r; int cl; - for_each_capable_rdt_resource(r) { + for_each_alloc_capable_rdt_resource(r) { cl = strlen(r->name); if (cl > max_name_width) max_name_width = cl; @@ -502,38 +638,153 @@ static __init void rdt_init_padding(void) } } -static __init bool get_rdt_resources(void) +enum { + RDT_FLAG_CMT, + RDT_FLAG_MBM_TOTAL, + RDT_FLAG_MBM_LOCAL, + RDT_FLAG_L3_CAT, + RDT_FLAG_L3_CDP, + RDT_FLAG_L2_CAT, + RDT_FLAG_MBA, +}; + +#define RDT_OPT(idx, n, f) \ +[idx] = { \ + .name = n, \ + .flag = f \ +} + +struct rdt_options { + char *name; + int flag; + bool force_off, force_on; +}; + +static struct rdt_options rdt_options[] __initdata = { + RDT_OPT(RDT_FLAG_CMT, "cmt", X86_FEATURE_CQM_OCCUP_LLC), + RDT_OPT(RDT_FLAG_MBM_TOTAL, "mbmtotal", X86_FEATURE_CQM_MBM_TOTAL), + RDT_OPT(RDT_FLAG_MBM_LOCAL, "mbmlocal", X86_FEATURE_CQM_MBM_LOCAL), + RDT_OPT(RDT_FLAG_L3_CAT, "l3cat", X86_FEATURE_CAT_L3), + RDT_OPT(RDT_FLAG_L3_CDP, "l3cdp", X86_FEATURE_CDP_L3), + RDT_OPT(RDT_FLAG_L2_CAT, "l2cat", X86_FEATURE_CAT_L2), + RDT_OPT(RDT_FLAG_MBA, "mba", X86_FEATURE_MBA), +}; +#define NUM_RDT_OPTIONS ARRAY_SIZE(rdt_options) + +static int __init set_rdt_options(char *str) +{ + struct rdt_options *o; + bool force_off; + char *tok; + + if (*str == '=') + str++; + while ((tok = strsep(&str, ",")) != NULL) { + force_off = *tok == '!'; + if (force_off) + tok++; + for (o = rdt_options; o < &rdt_options[NUM_RDT_OPTIONS]; o++) { + if (strcmp(tok, o->name) == 0) { + if (force_off) + o->force_off = true; + else + o->force_on = true; + break; + } + } + } + return 1; +} +__setup("rdt", set_rdt_options); + +static bool __init rdt_cpu_has(int flag) +{ + bool ret = boot_cpu_has(flag); + struct rdt_options *o; + + if (!ret) + return ret; + + for (o = rdt_options; o < &rdt_options[NUM_RDT_OPTIONS]; o++) { + if (flag == o->flag) { + if (o->force_off) + ret = false; + if (o->force_on) + ret = true; + break; + } + } + return ret; +} + +static __init bool get_rdt_alloc_resources(void) { bool ret = false; - if (cache_alloc_hsw_probe()) + if (rdt_alloc_capable) return true; if (!boot_cpu_has(X86_FEATURE_RDT_A)) return false; - if (boot_cpu_has(X86_FEATURE_CAT_L3)) { - rdt_get_cache_config(1, &rdt_resources_all[RDT_RESOURCE_L3]); - if (boot_cpu_has(X86_FEATURE_CDP_L3)) { + if (rdt_cpu_has(X86_FEATURE_CAT_L3)) { + rdt_get_cache_alloc_cfg(1, &rdt_resources_all[RDT_RESOURCE_L3]); + if (rdt_cpu_has(X86_FEATURE_CDP_L3)) { rdt_get_cdp_l3_config(RDT_RESOURCE_L3DATA); rdt_get_cdp_l3_config(RDT_RESOURCE_L3CODE); } ret = true; } - if (boot_cpu_has(X86_FEATURE_CAT_L2)) { + if (rdt_cpu_has(X86_FEATURE_CAT_L2)) { /* CPUID 0x10.2 fields are same format at 0x10.1 */ - rdt_get_cache_config(2, &rdt_resources_all[RDT_RESOURCE_L2]); + rdt_get_cache_alloc_cfg(2, &rdt_resources_all[RDT_RESOURCE_L2]); ret = true; } - if (boot_cpu_has(X86_FEATURE_MBA)) { + if (rdt_cpu_has(X86_FEATURE_MBA)) { if (rdt_get_mem_config(&rdt_resources_all[RDT_RESOURCE_MBA])) ret = true; } - return ret; } +static __init bool get_rdt_mon_resources(void) +{ + if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC)) + rdt_mon_features |= (1 << QOS_L3_OCCUP_EVENT_ID); + if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) + rdt_mon_features |= (1 << QOS_L3_MBM_TOTAL_EVENT_ID); + if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) + rdt_mon_features |= (1 << QOS_L3_MBM_LOCAL_EVENT_ID); + + if (!rdt_mon_features) + return false; + + return !rdt_get_mon_l3_config(&rdt_resources_all[RDT_RESOURCE_L3]); +} + +static __init void rdt_quirks(void) +{ + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_HASWELL_X: + if (!rdt_options[RDT_FLAG_L3_CAT].force_off) + cache_alloc_hsw_probe(); + break; + case INTEL_FAM6_SKYLAKE_X: + if (boot_cpu_data.x86_mask <= 4) + set_rdt_options("!cmt,!mbmtotal,!mbmlocal,!l3cat"); + } +} + +static __init bool get_rdt_resources(void) +{ + rdt_quirks(); + rdt_alloc_capable = get_rdt_alloc_resources(); + rdt_mon_capable = get_rdt_mon_resources(); + + return (rdt_mon_capable || rdt_alloc_capable); +} + static int __init intel_rdt_late_init(void) { struct rdt_resource *r; @@ -556,9 +807,12 @@ static int __init intel_rdt_late_init(void) return ret; } - for_each_capable_rdt_resource(r) + for_each_alloc_capable_rdt_resource(r) pr_info("Intel RDT %s allocation detected\n", r->name); + for_each_mon_capable_rdt_resource(r) + pr_info("Intel RDT %s monitoring detected\n", r->name); + return 0; } diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h new file mode 100644 index 000000000000..3397244984f5 --- /dev/null +++ b/arch/x86/kernel/cpu/intel_rdt.h @@ -0,0 +1,448 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_INTEL_RDT_H +#define _ASM_X86_INTEL_RDT_H + +#include <linux/sched.h> +#include <linux/kernfs.h> +#include <linux/jump_label.h> + +#define IA32_L3_QOS_CFG 0xc81 +#define IA32_L3_CBM_BASE 0xc90 +#define IA32_L2_CBM_BASE 0xd10 +#define IA32_MBA_THRTL_BASE 0xd50 + +#define L3_QOS_CDP_ENABLE 0x01ULL + +/* + * Event IDs are used to program IA32_QM_EVTSEL before reading event + * counter from IA32_QM_CTR + */ +#define QOS_L3_OCCUP_EVENT_ID 0x01 +#define QOS_L3_MBM_TOTAL_EVENT_ID 0x02 +#define QOS_L3_MBM_LOCAL_EVENT_ID 0x03 + +#define CQM_LIMBOCHECK_INTERVAL 1000 + +#define MBM_CNTR_WIDTH 24 +#define MBM_OVERFLOW_INTERVAL 1000 + +#define RMID_VAL_ERROR BIT_ULL(63) +#define RMID_VAL_UNAVAIL BIT_ULL(62) + +DECLARE_STATIC_KEY_FALSE(rdt_enable_key); + +/** + * struct mon_evt - Entry in the event list of a resource + * @evtid: event id + * @name: name of the event + */ +struct mon_evt { + u32 evtid; + char *name; + struct list_head list; +}; + +/** + * struct mon_data_bits - Monitoring details for each event file + * @rid: Resource id associated with the event file. + * @evtid: Event id associated with the event file + * @domid: The domain to which the event file belongs + */ +union mon_data_bits { + void *priv; + struct { + unsigned int rid : 10; + unsigned int evtid : 8; + unsigned int domid : 14; + } u; +}; + +struct rmid_read { + struct rdtgroup *rgrp; + struct rdt_domain *d; + int evtid; + bool first; + u64 val; +}; + +extern unsigned int intel_cqm_threshold; +extern bool rdt_alloc_capable; +extern bool rdt_mon_capable; +extern unsigned int rdt_mon_features; + +enum rdt_group_type { + RDTCTRL_GROUP = 0, + RDTMON_GROUP, + RDT_NUM_GROUP, +}; + +/** + * struct mongroup - store mon group's data in resctrl fs. + * @mon_data_kn kernlfs node for the mon_data directory + * @parent: parent rdtgrp + * @crdtgrp_list: child rdtgroup node list + * @rmid: rmid for this rdtgroup + */ +struct mongroup { + struct kernfs_node *mon_data_kn; + struct rdtgroup *parent; + struct list_head crdtgrp_list; + u32 rmid; +}; + +/** + * struct rdtgroup - store rdtgroup's data in resctrl file system. + * @kn: kernfs node + * @rdtgroup_list: linked list for all rdtgroups + * @closid: closid for this rdtgroup + * @cpu_mask: CPUs assigned to this rdtgroup + * @flags: status bits + * @waitcount: how many cpus expect to find this + * group when they acquire rdtgroup_mutex + * @type: indicates type of this rdtgroup - either + * monitor only or ctrl_mon group + * @mon: mongroup related data + */ +struct rdtgroup { + struct kernfs_node *kn; + struct list_head rdtgroup_list; + u32 closid; + struct cpumask cpu_mask; + int flags; + atomic_t waitcount; + enum rdt_group_type type; + struct mongroup mon; +}; + +/* rdtgroup.flags */ +#define RDT_DELETED 1 + +/* rftype.flags */ +#define RFTYPE_FLAGS_CPUS_LIST 1 + +/* + * Define the file type flags for base and info directories. + */ +#define RFTYPE_INFO BIT(0) +#define RFTYPE_BASE BIT(1) +#define RF_CTRLSHIFT 4 +#define RF_MONSHIFT 5 +#define RF_TOPSHIFT 6 +#define RFTYPE_CTRL BIT(RF_CTRLSHIFT) +#define RFTYPE_MON BIT(RF_MONSHIFT) +#define RFTYPE_TOP BIT(RF_TOPSHIFT) +#define RFTYPE_RES_CACHE BIT(8) +#define RFTYPE_RES_MB BIT(9) +#define RF_CTRL_INFO (RFTYPE_INFO | RFTYPE_CTRL) +#define RF_MON_INFO (RFTYPE_INFO | RFTYPE_MON) +#define RF_TOP_INFO (RFTYPE_INFO | RFTYPE_TOP) +#define RF_CTRL_BASE (RFTYPE_BASE | RFTYPE_CTRL) + +/* List of all resource groups */ +extern struct list_head rdt_all_groups; + +extern int max_name_width, max_data_width; + +int __init rdtgroup_init(void); + +/** + * struct rftype - describe each file in the resctrl file system + * @name: File name + * @mode: Access mode + * @kf_ops: File operations + * @flags: File specific RFTYPE_FLAGS_* flags + * @fflags: File specific RF_* or RFTYPE_* flags + * @seq_show: Show content of the file + * @write: Write to the file + */ +struct rftype { + char *name; + umode_t mode; + struct kernfs_ops *kf_ops; + unsigned long flags; + unsigned long fflags; + + int (*seq_show)(struct kernfs_open_file *of, + struct seq_file *sf, void *v); + /* + * write() is the generic write callback which maps directly to + * kernfs write operation and overrides all other operations. + * Maximum write size is determined by ->max_write_len. + */ + ssize_t (*write)(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off); +}; + +/** + * struct mbm_state - status for each MBM counter in each domain + * @chunks: Total data moved (multiply by rdt_group.mon_scale to get bytes) + * @prev_msr Value of IA32_QM_CTR for this RMID last time we read it + */ +struct mbm_state { + u64 chunks; + u64 prev_msr; +}; + +/** + * struct rdt_domain - group of cpus sharing an RDT resource + * @list: all instances of this resource + * @id: unique id for this instance + * @cpu_mask: which cpus share this resource + * @rmid_busy_llc: + * bitmap of which limbo RMIDs are above threshold + * @mbm_total: saved state for MBM total bandwidth + * @mbm_local: saved state for MBM local bandwidth + * @mbm_over: worker to periodically read MBM h/w counters + * @cqm_limbo: worker to periodically read CQM h/w counters + * @mbm_work_cpu: + * worker cpu for MBM h/w counters + * @cqm_work_cpu: + * worker cpu for CQM h/w counters + * @ctrl_val: array of cache or mem ctrl values (indexed by CLOSID) + * @new_ctrl: new ctrl value to be loaded + * @have_new_ctrl: did user provide new_ctrl for this domain + */ +struct rdt_domain { + struct list_head list; + int id; + struct cpumask cpu_mask; + unsigned long *rmid_busy_llc; + struct mbm_state *mbm_total; + struct mbm_state *mbm_local; + struct delayed_work mbm_over; + struct delayed_work cqm_limbo; + int mbm_work_cpu; + int cqm_work_cpu; + u32 *ctrl_val; + u32 new_ctrl; + bool have_new_ctrl; +}; + +/** + * struct msr_param - set a range of MSRs from a domain + * @res: The resource to use + * @low: Beginning index from base MSR + * @high: End index + */ +struct msr_param { + struct rdt_resource *res; + int low; + int high; +}; + +/** + * struct rdt_cache - Cache allocation related data + * @cbm_len: Length of the cache bit mask + * @min_cbm_bits: Minimum number of consecutive bits to be set + * @cbm_idx_mult: Multiplier of CBM index + * @cbm_idx_offset: Offset of CBM index. CBM index is computed by: + * closid * cbm_idx_multi + cbm_idx_offset + * in a cache bit mask + * @shareable_bits: Bitmask of shareable resource with other + * executing entities + */ +struct rdt_cache { + unsigned int cbm_len; + unsigned int min_cbm_bits; + unsigned int cbm_idx_mult; + unsigned int cbm_idx_offset; + unsigned int shareable_bits; +}; + +/** + * struct rdt_membw - Memory bandwidth allocation related data + * @max_delay: Max throttle delay. Delay is the hardware + * representation for memory bandwidth. + * @min_bw: Minimum memory bandwidth percentage user can request + * @bw_gran: Granularity at which the memory bandwidth is allocated + * @delay_linear: True if memory B/W delay is in linear scale + * @mb_map: Mapping of memory B/W percentage to memory B/W delay + */ +struct rdt_membw { + u32 max_delay; + u32 min_bw; + u32 bw_gran; + u32 delay_linear; + u32 *mb_map; +}; + +static inline bool is_llc_occupancy_enabled(void) +{ + return (rdt_mon_features & (1 << QOS_L3_OCCUP_EVENT_ID)); +} + +static inline bool is_mbm_total_enabled(void) +{ + return (rdt_mon_features & (1 << QOS_L3_MBM_TOTAL_EVENT_ID)); +} + +static inline bool is_mbm_local_enabled(void) +{ + return (rdt_mon_features & (1 << QOS_L3_MBM_LOCAL_EVENT_ID)); +} + +static inline bool is_mbm_enabled(void) +{ + return (is_mbm_total_enabled() || is_mbm_local_enabled()); +} + +static inline bool is_mbm_event(int e) +{ + return (e >= QOS_L3_MBM_TOTAL_EVENT_ID && + e <= QOS_L3_MBM_LOCAL_EVENT_ID); +} + +/** + * struct rdt_resource - attributes of an RDT resource + * @rid: The index of the resource + * @alloc_enabled: Is allocation enabled on this machine + * @mon_enabled: Is monitoring enabled for this feature + * @alloc_capable: Is allocation available on this machine + * @mon_capable: Is monitor feature available on this machine + * @name: Name to use in "schemata" file + * @num_closid: Number of CLOSIDs available + * @cache_level: Which cache level defines scope of this resource + * @default_ctrl: Specifies default cache cbm or memory B/W percent. + * @msr_base: Base MSR address for CBMs + * @msr_update: Function pointer to update QOS MSRs + * @data_width: Character width of data when displaying + * @domains: All domains for this resource + * @cache: Cache allocation related data + * @format_str: Per resource format string to show domain value + * @parse_ctrlval: Per resource function pointer to parse control values + * @evt_list: List of monitoring events + * @num_rmid: Number of RMIDs available + * @mon_scale: cqm counter * mon_scale = occupancy in bytes + * @fflags: flags to choose base and info files + */ +struct rdt_resource { + int rid; + bool alloc_enabled; + bool mon_enabled; + bool alloc_capable; + bool mon_capable; + char *name; + int num_closid; + int cache_level; + u32 default_ctrl; + unsigned int msr_base; + void (*msr_update) (struct rdt_domain *d, struct msr_param *m, + struct rdt_resource *r); + int data_width; + struct list_head domains; + struct rdt_cache cache; + struct rdt_membw membw; + const char *format_str; + int (*parse_ctrlval) (char *buf, struct rdt_resource *r, + struct rdt_domain *d); + struct list_head evt_list; + int num_rmid; + unsigned int mon_scale; + unsigned long fflags; +}; + +int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d); +int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d); + +extern struct mutex rdtgroup_mutex; + +extern struct rdt_resource rdt_resources_all[]; +extern struct rdtgroup rdtgroup_default; +DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key); + +int __init rdtgroup_init(void); + +enum { + RDT_RESOURCE_L3, + RDT_RESOURCE_L3DATA, + RDT_RESOURCE_L3CODE, + RDT_RESOURCE_L2, + RDT_RESOURCE_MBA, + + /* Must be the last */ + RDT_NUM_RESOURCES, +}; + +#define for_each_capable_rdt_resource(r) \ + for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ + r++) \ + if (r->alloc_capable || r->mon_capable) + +#define for_each_alloc_capable_rdt_resource(r) \ + for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ + r++) \ + if (r->alloc_capable) + +#define for_each_mon_capable_rdt_resource(r) \ + for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ + r++) \ + if (r->mon_capable) + +#define for_each_alloc_enabled_rdt_resource(r) \ + for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ + r++) \ + if (r->alloc_enabled) + +#define for_each_mon_enabled_rdt_resource(r) \ + for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ + r++) \ + if (r->mon_enabled) + +/* CPUID.(EAX=10H, ECX=ResID=1).EAX */ +union cpuid_0x10_1_eax { + struct { + unsigned int cbm_len:5; + } split; + unsigned int full; +}; + +/* CPUID.(EAX=10H, ECX=ResID=3).EAX */ +union cpuid_0x10_3_eax { + struct { + unsigned int max_delay:12; + } split; + unsigned int full; +}; + +/* CPUID.(EAX=10H, ECX=ResID).EDX */ +union cpuid_0x10_x_edx { + struct { + unsigned int cos_max:16; + } split; + unsigned int full; +}; + +void rdt_last_cmd_clear(void); +void rdt_last_cmd_puts(const char *s); +void rdt_last_cmd_printf(const char *fmt, ...); + +void rdt_ctrl_update(void *arg); +struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn); +void rdtgroup_kn_unlock(struct kernfs_node *kn); +struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id, + struct list_head **pos); +ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off); +int rdtgroup_schemata_show(struct kernfs_open_file *of, + struct seq_file *s, void *v); +struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r); +int alloc_rmid(void); +void free_rmid(u32 rmid); +int rdt_get_mon_l3_config(struct rdt_resource *r); +void mon_event_count(void *info); +int rdtgroup_mondata_show(struct seq_file *m, void *arg); +void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, + unsigned int dom_id); +void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, + struct rdt_domain *d); +void mon_event_read(struct rmid_read *rr, struct rdt_domain *d, + struct rdtgroup *rdtgrp, int evtid, int first); +void mbm_setup_overflow_handler(struct rdt_domain *dom, + unsigned long delay_ms); +void mbm_handle_overflow(struct work_struct *work); +void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms); +void cqm_handle_limbo(struct work_struct *work); +bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d); +void __check_limbo(struct rdt_domain *d, bool force_free); + +#endif /* _ASM_X86_INTEL_RDT_H */ diff --git a/arch/x86/kernel/cpu/intel_rdt_schemata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c index 406d7a6532f9..23e1d5c249c6 100644 --- a/arch/x86/kernel/cpu/intel_rdt_schemata.c +++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c @@ -26,7 +26,7 @@ #include <linux/kernfs.h> #include <linux/seq_file.h> #include <linux/slab.h> -#include <asm/intel_rdt.h> +#include "intel_rdt.h" /* * Check whether MBA bandwidth percentage value is correct. The value is @@ -42,15 +42,22 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) /* * Only linear delay values is supported for current Intel SKUs. */ - if (!r->membw.delay_linear) + if (!r->membw.delay_linear) { + rdt_last_cmd_puts("No support for non-linear MB domains\n"); return false; + } ret = kstrtoul(buf, 10, &bw); - if (ret) + if (ret) { + rdt_last_cmd_printf("Non-decimal digit in MB value %s\n", buf); return false; + } - if (bw < r->membw.min_bw || bw > r->default_ctrl) + if (bw < r->membw.min_bw || bw > r->default_ctrl) { + rdt_last_cmd_printf("MB value %ld out of range [%d,%d]\n", bw, + r->membw.min_bw, r->default_ctrl); return false; + } *data = roundup(bw, (unsigned long)r->membw.bw_gran); return true; @@ -60,8 +67,10 @@ int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d) { unsigned long data; - if (d->have_new_ctrl) + if (d->have_new_ctrl) { + rdt_last_cmd_printf("duplicate domain %d\n", d->id); return -EINVAL; + } if (!bw_validate(buf, &data, r)) return -EINVAL; @@ -84,20 +93,29 @@ static bool cbm_validate(char *buf, unsigned long *data, struct rdt_resource *r) int ret; ret = kstrtoul(buf, 16, &val); - if (ret) + if (ret) { + rdt_last_cmd_printf("non-hex character in mask %s\n", buf); return false; + } - if (val == 0 || val > r->default_ctrl) + if (val == 0 || val > r->default_ctrl) { + rdt_last_cmd_puts("mask out of range\n"); return false; + } first_bit = find_first_bit(&val, cbm_len); zero_bit = find_next_zero_bit(&val, cbm_len, first_bit); - if (find_next_bit(&val, cbm_len, zero_bit) < cbm_len) + if (find_next_bit(&val, cbm_len, zero_bit) < cbm_len) { + rdt_last_cmd_printf("mask %lx has non-consecutive 1-bits\n", val); return false; + } - if ((zero_bit - first_bit) < r->cache.min_cbm_bits) + if ((zero_bit - first_bit) < r->cache.min_cbm_bits) { + rdt_last_cmd_printf("Need at least %d bits in mask\n", + r->cache.min_cbm_bits); return false; + } *data = val; return true; @@ -111,8 +129,10 @@ int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d) { unsigned long data; - if (d->have_new_ctrl) + if (d->have_new_ctrl) { + rdt_last_cmd_printf("duplicate domain %d\n", d->id); return -EINVAL; + } if(!cbm_validate(buf, &data, r)) return -EINVAL; @@ -139,8 +159,10 @@ next: return 0; dom = strsep(&line, ";"); id = strsep(&dom, "="); - if (!dom || kstrtoul(id, 10, &dom_id)) + if (!dom || kstrtoul(id, 10, &dom_id)) { + rdt_last_cmd_puts("Missing '=' or non-numeric domain\n"); return -EINVAL; + } dom = strim(dom); list_for_each_entry(d, &r->domains, list) { if (d->id == dom_id) { @@ -192,10 +214,11 @@ static int rdtgroup_parse_resource(char *resname, char *tok, int closid) { struct rdt_resource *r; - for_each_enabled_rdt_resource(r) { + for_each_alloc_enabled_rdt_resource(r) { if (!strcmp(resname, r->name) && closid < r->num_closid) return parse_line(tok, r); } + rdt_last_cmd_printf("unknown/unsupported resource name '%s'\n", resname); return -EINVAL; } @@ -218,10 +241,11 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, rdtgroup_kn_unlock(of->kn); return -ENOENT; } + rdt_last_cmd_clear(); closid = rdtgrp->closid; - for_each_enabled_rdt_resource(r) { + for_each_alloc_enabled_rdt_resource(r) { list_for_each_entry(dom, &r->domains, list) dom->have_new_ctrl = false; } @@ -229,6 +253,12 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, while ((tok = strsep(&buf, "\n")) != NULL) { resname = strim(strsep(&tok, ":")); if (!tok) { + rdt_last_cmd_puts("Missing ':'\n"); + ret = -EINVAL; + goto out; + } + if (tok[0] == '\0') { + rdt_last_cmd_printf("Missing '%s' value\n", resname); ret = -EINVAL; goto out; } @@ -237,7 +267,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, goto out; } - for_each_enabled_rdt_resource(r) { + for_each_alloc_enabled_rdt_resource(r) { ret = update_domains(r, closid); if (ret) goto out; @@ -269,12 +299,13 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of, { struct rdtgroup *rdtgrp; struct rdt_resource *r; - int closid, ret = 0; + int ret = 0; + u32 closid; rdtgrp = rdtgroup_kn_lock_live(of->kn); if (rdtgrp) { closid = rdtgrp->closid; - for_each_enabled_rdt_resource(r) { + for_each_alloc_enabled_rdt_resource(r) { if (closid < r->num_closid) show_doms(s, r, closid); } @@ -284,3 +315,57 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of, rdtgroup_kn_unlock(of->kn); return ret; } + +void mon_event_read(struct rmid_read *rr, struct rdt_domain *d, + struct rdtgroup *rdtgrp, int evtid, int first) +{ + /* + * setup the parameters to send to the IPI to read the data. + */ + rr->rgrp = rdtgrp; + rr->evtid = evtid; + rr->d = d; + rr->val = 0; + rr->first = first; + + smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1); +} + +int rdtgroup_mondata_show(struct seq_file *m, void *arg) +{ + struct kernfs_open_file *of = m->private; + u32 resid, evtid, domid; + struct rdtgroup *rdtgrp; + struct rdt_resource *r; + union mon_data_bits md; + struct rdt_domain *d; + struct rmid_read rr; + int ret = 0; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + + md.priv = of->kn->priv; + resid = md.u.rid; + domid = md.u.domid; + evtid = md.u.evtid; + + r = &rdt_resources_all[resid]; + d = rdt_find_domain(r, domid, NULL); + if (!d) { + ret = -ENOENT; + goto out; + } + + mon_event_read(&rr, d, rdtgrp, evtid, false); + + if (rr.val & RMID_VAL_ERROR) + seq_puts(m, "Error\n"); + else if (rr.val & RMID_VAL_UNAVAIL) + seq_puts(m, "Unavailable\n"); + else + seq_printf(m, "%llu\n", rr.val * r->mon_scale); + +out: + rdtgroup_kn_unlock(of->kn); + return ret; +} diff --git a/arch/x86/kernel/cpu/intel_rdt_monitor.c b/arch/x86/kernel/cpu/intel_rdt_monitor.c new file mode 100644 index 000000000000..681450eee428 --- /dev/null +++ b/arch/x86/kernel/cpu/intel_rdt_monitor.c @@ -0,0 +1,499 @@ +/* + * Resource Director Technology(RDT) + * - Monitoring code + * + * Copyright (C) 2017 Intel Corporation + * + * Author: + * Vikas Shivappa <vikas.shivappa@intel.com> + * + * This replaces the cqm.c based on perf but we reuse a lot of + * code and datastructures originally from Peter Zijlstra and Matt Fleming. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * More information about RDT be found in the Intel (R) x86 Architecture + * Software Developer Manual June 2016, volume 3, section 17.17. + */ + +#include <linux/module.h> +#include <linux/slab.h> +#include <asm/cpu_device_id.h> +#include "intel_rdt.h" + +#define MSR_IA32_QM_CTR 0x0c8e +#define MSR_IA32_QM_EVTSEL 0x0c8d + +struct rmid_entry { + u32 rmid; + int busy; + struct list_head list; +}; + +/** + * @rmid_free_lru A least recently used list of free RMIDs + * These RMIDs are guaranteed to have an occupancy less than the + * threshold occupancy + */ +static LIST_HEAD(rmid_free_lru); + +/** + * @rmid_limbo_count count of currently unused but (potentially) + * dirty RMIDs. + * This counts RMIDs that no one is currently using but that + * may have a occupancy value > intel_cqm_threshold. User can change + * the threshold occupancy value. + */ +static unsigned int rmid_limbo_count; + +/** + * @rmid_entry - The entry in the limbo and free lists. + */ +static struct rmid_entry *rmid_ptrs; + +/* + * Global boolean for rdt_monitor which is true if any + * resource monitoring is enabled. + */ +bool rdt_mon_capable; + +/* + * Global to indicate which monitoring events are enabled. + */ +unsigned int rdt_mon_features; + +/* + * This is the threshold cache occupancy at which we will consider an + * RMID available for re-allocation. + */ +unsigned int intel_cqm_threshold; + +static inline struct rmid_entry *__rmid_entry(u32 rmid) +{ + struct rmid_entry *entry; + + entry = &rmid_ptrs[rmid]; + WARN_ON(entry->rmid != rmid); + + return entry; +} + +static u64 __rmid_read(u32 rmid, u32 eventid) +{ + u64 val; + + /* + * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured + * with a valid event code for supported resource type and the bits + * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID, + * IA32_QM_CTR.data (bits 61:0) reports the monitored data. + * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62) + * are error bits. + */ + wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid); + rdmsrl(MSR_IA32_QM_CTR, val); + + return val; +} + +static bool rmid_dirty(struct rmid_entry *entry) +{ + u64 val = __rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID); + + return val >= intel_cqm_threshold; +} + +/* + * Check the RMIDs that are marked as busy for this domain. If the + * reported LLC occupancy is below the threshold clear the busy bit and + * decrement the count. If the busy count gets to zero on an RMID, we + * free the RMID + */ +void __check_limbo(struct rdt_domain *d, bool force_free) +{ + struct rmid_entry *entry; + struct rdt_resource *r; + u32 crmid = 1, nrmid; + + r = &rdt_resources_all[RDT_RESOURCE_L3]; + + /* + * Skip RMID 0 and start from RMID 1 and check all the RMIDs that + * are marked as busy for occupancy < threshold. If the occupancy + * is less than the threshold decrement the busy counter of the + * RMID and move it to the free list when the counter reaches 0. + */ + for (;;) { + nrmid = find_next_bit(d->rmid_busy_llc, r->num_rmid, crmid); + if (nrmid >= r->num_rmid) + break; + + entry = __rmid_entry(nrmid); + if (force_free || !rmid_dirty(entry)) { + clear_bit(entry->rmid, d->rmid_busy_llc); + if (!--entry->busy) { + rmid_limbo_count--; + list_add_tail(&entry->list, &rmid_free_lru); + } + } + crmid = nrmid + 1; + } +} + +bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d) +{ + return find_first_bit(d->rmid_busy_llc, r->num_rmid) != r->num_rmid; +} + +/* + * As of now the RMIDs allocation is global. + * However we keep track of which packages the RMIDs + * are used to optimize the limbo list management. + */ +int alloc_rmid(void) +{ + struct rmid_entry *entry; + + lockdep_assert_held(&rdtgroup_mutex); + + if (list_empty(&rmid_free_lru)) + return rmid_limbo_count ? -EBUSY : -ENOSPC; + + entry = list_first_entry(&rmid_free_lru, + struct rmid_entry, list); + list_del(&entry->list); + + return entry->rmid; +} + +static void add_rmid_to_limbo(struct rmid_entry *entry) +{ + struct rdt_resource *r; + struct rdt_domain *d; + int cpu; + u64 val; + + r = &rdt_resources_all[RDT_RESOURCE_L3]; + + entry->busy = 0; + cpu = get_cpu(); + list_for_each_entry(d, &r->domains, list) { + if (cpumask_test_cpu(cpu, &d->cpu_mask)) { + val = __rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID); + if (val <= intel_cqm_threshold) + continue; + } + + /* + * For the first limbo RMID in the domain, + * setup up the limbo worker. + */ + if (!has_busy_rmid(r, d)) + cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL); + set_bit(entry->rmid, d->rmid_busy_llc); + entry->busy++; + } + put_cpu(); + + if (entry->busy) + rmid_limbo_count++; + else + list_add_tail(&entry->list, &rmid_free_lru); +} + +void free_rmid(u32 rmid) +{ + struct rmid_entry *entry; + + if (!rmid) + return; + + lockdep_assert_held(&rdtgroup_mutex); + + entry = __rmid_entry(rmid); + + if (is_llc_occupancy_enabled()) + add_rmid_to_limbo(entry); + else + list_add_tail(&entry->list, &rmid_free_lru); +} + +static int __mon_event_count(u32 rmid, struct rmid_read *rr) +{ + u64 chunks, shift, tval; + struct mbm_state *m; + + tval = __rmid_read(rmid, rr->evtid); + if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) { + rr->val = tval; + return -EINVAL; + } + switch (rr->evtid) { + case QOS_L3_OCCUP_EVENT_ID: + rr->val += tval; + return 0; + case QOS_L3_MBM_TOTAL_EVENT_ID: + m = &rr->d->mbm_total[rmid]; + break; + case QOS_L3_MBM_LOCAL_EVENT_ID: + m = &rr->d->mbm_local[rmid]; + break; + default: + /* + * Code would never reach here because + * an invalid event id would fail the __rmid_read. + */ + return -EINVAL; + } + + if (rr->first) { + m->prev_msr = tval; + m->chunks = 0; + return 0; + } + + shift = 64 - MBM_CNTR_WIDTH; + chunks = (tval << shift) - (m->prev_msr << shift); + chunks >>= shift; + m->chunks += chunks; + m->prev_msr = tval; + + rr->val += m->chunks; + return 0; +} + +/* + * This is called via IPI to read the CQM/MBM counters + * on a domain. + */ +void mon_event_count(void *info) +{ + struct rdtgroup *rdtgrp, *entry; + struct rmid_read *rr = info; + struct list_head *head; + + rdtgrp = rr->rgrp; + + if (__mon_event_count(rdtgrp->mon.rmid, rr)) + return; + + /* + * For Ctrl groups read data from child monitor groups. + */ + head = &rdtgrp->mon.crdtgrp_list; + + if (rdtgrp->type == RDTCTRL_GROUP) { + list_for_each_entry(entry, head, mon.crdtgrp_list) { + if (__mon_event_count(entry->mon.rmid, rr)) + return; + } + } +} + +static void mbm_update(struct rdt_domain *d, int rmid) +{ + struct rmid_read rr; + + rr.first = false; + rr.d = d; + + /* + * This is protected from concurrent reads from user + * as both the user and we hold the global mutex. + */ + if (is_mbm_total_enabled()) { + rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID; + __mon_event_count(rmid, &rr); + } + if (is_mbm_local_enabled()) { + rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID; + __mon_event_count(rmid, &rr); + } +} + +/* + * Handler to scan the limbo list and move the RMIDs + * to free list whose occupancy < threshold_occupancy. + */ +void cqm_handle_limbo(struct work_struct *work) +{ + unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL); + int cpu = smp_processor_id(); + struct rdt_resource *r; + struct rdt_domain *d; + + mutex_lock(&rdtgroup_mutex); + + r = &rdt_resources_all[RDT_RESOURCE_L3]; + d = get_domain_from_cpu(cpu, r); + + if (!d) { + pr_warn_once("Failure to get domain for limbo worker\n"); + goto out_unlock; + } + + __check_limbo(d, false); + + if (has_busy_rmid(r, d)) + schedule_delayed_work_on(cpu, &d->cqm_limbo, delay); + +out_unlock: + mutex_unlock(&rdtgroup_mutex); +} + +void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms) +{ + unsigned long delay = msecs_to_jiffies(delay_ms); + struct rdt_resource *r; + int cpu; + + r = &rdt_resources_all[RDT_RESOURCE_L3]; + + cpu = cpumask_any(&dom->cpu_mask); + dom->cqm_work_cpu = cpu; + + schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay); +} + +void mbm_handle_overflow(struct work_struct *work) +{ + unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL); + struct rdtgroup *prgrp, *crgrp; + int cpu = smp_processor_id(); + struct list_head *head; + struct rdt_domain *d; + + mutex_lock(&rdtgroup_mutex); + + if (!static_branch_likely(&rdt_enable_key)) + goto out_unlock; + + d = get_domain_from_cpu(cpu, &rdt_resources_all[RDT_RESOURCE_L3]); + if (!d) + goto out_unlock; + + list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { + mbm_update(d, prgrp->mon.rmid); + + head = &prgrp->mon.crdtgrp_list; + list_for_each_entry(crgrp, head, mon.crdtgrp_list) + mbm_update(d, crgrp->mon.rmid); + } + + schedule_delayed_work_on(cpu, &d->mbm_over, delay); + +out_unlock: + mutex_unlock(&rdtgroup_mutex); +} + +void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms) +{ + unsigned long delay = msecs_to_jiffies(delay_ms); + int cpu; + + if (!static_branch_likely(&rdt_enable_key)) + return; + cpu = cpumask_any(&dom->cpu_mask); + dom->mbm_work_cpu = cpu; + schedule_delayed_work_on(cpu, &dom->mbm_over, delay); +} + +static int dom_data_init(struct rdt_resource *r) +{ + struct rmid_entry *entry = NULL; + int i, nr_rmids; + + nr_rmids = r->num_rmid; + rmid_ptrs = kcalloc(nr_rmids, sizeof(struct rmid_entry), GFP_KERNEL); + if (!rmid_ptrs) + return -ENOMEM; + + for (i = 0; i < nr_rmids; i++) { + entry = &rmid_ptrs[i]; + INIT_LIST_HEAD(&entry->list); + + entry->rmid = i; + list_add_tail(&entry->list, &rmid_free_lru); + } + + /* + * RMID 0 is special and is always allocated. It's used for all + * tasks that are not monitored. + */ + entry = __rmid_entry(0); + list_del(&entry->list); + + return 0; +} + +static struct mon_evt llc_occupancy_event = { + .name = "llc_occupancy", + .evtid = QOS_L3_OCCUP_EVENT_ID, +}; + +static struct mon_evt mbm_total_event = { + .name = "mbm_total_bytes", + .evtid = QOS_L3_MBM_TOTAL_EVENT_ID, +}; + +static struct mon_evt mbm_local_event = { + .name = "mbm_local_bytes", + .evtid = QOS_L3_MBM_LOCAL_EVENT_ID, +}; + +/* + * Initialize the event list for the resource. + * + * Note that MBM events are also part of RDT_RESOURCE_L3 resource + * because as per the SDM the total and local memory bandwidth + * are enumerated as part of L3 monitoring. + */ +static void l3_mon_evt_init(struct rdt_resource *r) +{ + INIT_LIST_HEAD(&r->evt_list); + + if (is_llc_occupancy_enabled()) + list_add_tail(&llc_occupancy_event.list, &r->evt_list); + if (is_mbm_total_enabled()) + list_add_tail(&mbm_total_event.list, &r->evt_list); + if (is_mbm_local_enabled()) + list_add_tail(&mbm_local_event.list, &r->evt_list); +} + +int rdt_get_mon_l3_config(struct rdt_resource *r) +{ + int ret; + + r->mon_scale = boot_cpu_data.x86_cache_occ_scale; + r->num_rmid = boot_cpu_data.x86_cache_max_rmid + 1; + + /* + * A reasonable upper limit on the max threshold is the number + * of lines tagged per RMID if all RMIDs have the same number of + * lines tagged in the LLC. + * + * For a 35MB LLC and 56 RMIDs, this is ~1.8% of the LLC. + */ + intel_cqm_threshold = boot_cpu_data.x86_cache_size * 1024 / r->num_rmid; + + /* h/w works in units of "boot_cpu_data.x86_cache_occ_scale" */ + intel_cqm_threshold /= r->mon_scale; + + ret = dom_data_init(r); + if (ret) + return ret; + + l3_mon_evt_init(r); + + r->mon_capable = true; + r->mon_enabled = true; + + return 0; +} diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index 9257bd9dc664..64c5ff97ee0d 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -24,6 +24,7 @@ #include <linux/fs.h> #include <linux/sysfs.h> #include <linux/kernfs.h> +#include <linux/seq_buf.h> #include <linux/seq_file.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> @@ -32,17 +33,50 @@ #include <uapi/linux/magic.h> -#include <asm/intel_rdt.h> -#include <asm/intel_rdt_common.h> +#include <asm/intel_rdt_sched.h> +#include "intel_rdt.h" DEFINE_STATIC_KEY_FALSE(rdt_enable_key); -struct kernfs_root *rdt_root; +DEFINE_STATIC_KEY_FALSE(rdt_mon_enable_key); +DEFINE_STATIC_KEY_FALSE(rdt_alloc_enable_key); +static struct kernfs_root *rdt_root; struct rdtgroup rdtgroup_default; LIST_HEAD(rdt_all_groups); /* Kernel fs node for "info" directory under root */ static struct kernfs_node *kn_info; +/* Kernel fs node for "mon_groups" directory under root */ +static struct kernfs_node *kn_mongrp; + +/* Kernel fs node for "mon_data" directory under root */ +static struct kernfs_node *kn_mondata; + +static struct seq_buf last_cmd_status; +static char last_cmd_status_buf[512]; + +void rdt_last_cmd_clear(void) +{ + lockdep_assert_held(&rdtgroup_mutex); + seq_buf_clear(&last_cmd_status); +} + +void rdt_last_cmd_puts(const char *s) +{ + lockdep_assert_held(&rdtgroup_mutex); + seq_buf_puts(&last_cmd_status, s); +} + +void rdt_last_cmd_printf(const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + lockdep_assert_held(&rdtgroup_mutex); + seq_buf_vprintf(&last_cmd_status, fmt, ap); + va_end(ap); +} + /* * Trivial allocator for CLOSIDs. Since h/w only supports a small number, * we can keep a bitmap of free CLOSIDs in a single integer. @@ -66,7 +100,7 @@ static void closid_init(void) int rdt_min_closid = 32; /* Compute rdt_min_closid across all resources */ - for_each_enabled_rdt_resource(r) + for_each_alloc_enabled_rdt_resource(r) rdt_min_closid = min(rdt_min_closid, r->num_closid); closid_free_map = BIT_MASK(rdt_min_closid) - 1; @@ -75,9 +109,9 @@ static void closid_init(void) closid_free_map &= ~1; } -int closid_alloc(void) +static int closid_alloc(void) { - int closid = ffs(closid_free_map); + u32 closid = ffs(closid_free_map); if (closid == 0) return -ENOSPC; @@ -125,28 +159,6 @@ static int rdtgroup_add_file(struct kernfs_node *parent_kn, struct rftype *rft) return 0; } -static int rdtgroup_add_files(struct kernfs_node *kn, struct rftype *rfts, - int len) -{ - struct rftype *rft; - int ret; - - lockdep_assert_held(&rdtgroup_mutex); - - for (rft = rfts; rft < rfts + len; rft++) { - ret = rdtgroup_add_file(kn, rft); - if (ret) - goto error; - } - - return 0; -error: - pr_warn("Failed to add %s, err=%d\n", rft->name, ret); - while (--rft >= rfts) - kernfs_remove_by_name(kn, rft->name); - return ret; -} - static int rdtgroup_seqfile_show(struct seq_file *m, void *arg) { struct kernfs_open_file *of = m->private; @@ -174,6 +186,11 @@ static struct kernfs_ops rdtgroup_kf_single_ops = { .seq_show = rdtgroup_seqfile_show, }; +static struct kernfs_ops kf_mondata_ops = { + .atomic_write_len = PAGE_SIZE, + .seq_show = rdtgroup_mondata_show, +}; + static bool is_cpu_list(struct kernfs_open_file *of) { struct rftype *rft = of->kn->priv; @@ -203,13 +220,18 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of, /* * This is safe against intel_rdt_sched_in() called from __switch_to() * because __switch_to() is executed with interrupts disabled. A local call - * from rdt_update_closid() is proteced against __switch_to() because + * from update_closid_rmid() is proteced against __switch_to() because * preemption is disabled. */ -static void rdt_update_cpu_closid(void *closid) +static void update_cpu_closid_rmid(void *info) { - if (closid) - this_cpu_write(cpu_closid, *(int *)closid); + struct rdtgroup *r = info; + + if (r) { + this_cpu_write(pqr_state.default_closid, r->closid); + this_cpu_write(pqr_state.default_rmid, r->mon.rmid); + } + /* * We cannot unconditionally write the MSR because the current * executing task might have its own closid selected. Just reuse @@ -221,28 +243,132 @@ static void rdt_update_cpu_closid(void *closid) /* * Update the PGR_ASSOC MSR on all cpus in @cpu_mask, * - * Per task closids must have been set up before calling this function. - * - * The per cpu closids are updated with the smp function call, when @closid - * is not NULL. If @closid is NULL then all affected percpu closids must - * have been set up before calling this function. + * Per task closids/rmids must have been set up before calling this function. */ static void -rdt_update_closid(const struct cpumask *cpu_mask, int *closid) +update_closid_rmid(const struct cpumask *cpu_mask, struct rdtgroup *r) { int cpu = get_cpu(); if (cpumask_test_cpu(cpu, cpu_mask)) - rdt_update_cpu_closid(closid); - smp_call_function_many(cpu_mask, rdt_update_cpu_closid, closid, 1); + update_cpu_closid_rmid(r); + smp_call_function_many(cpu_mask, update_cpu_closid_rmid, r, 1); put_cpu(); } +static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask, + cpumask_var_t tmpmask) +{ + struct rdtgroup *prgrp = rdtgrp->mon.parent, *crgrp; + struct list_head *head; + + /* Check whether cpus belong to parent ctrl group */ + cpumask_andnot(tmpmask, newmask, &prgrp->cpu_mask); + if (cpumask_weight(tmpmask)) { + rdt_last_cmd_puts("can only add CPUs to mongroup that belong to parent\n"); + return -EINVAL; + } + + /* Check whether cpus are dropped from this group */ + cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask); + if (cpumask_weight(tmpmask)) { + /* Give any dropped cpus to parent rdtgroup */ + cpumask_or(&prgrp->cpu_mask, &prgrp->cpu_mask, tmpmask); + update_closid_rmid(tmpmask, prgrp); + } + + /* + * If we added cpus, remove them from previous group that owned them + * and update per-cpu rmid + */ + cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask); + if (cpumask_weight(tmpmask)) { + head = &prgrp->mon.crdtgrp_list; + list_for_each_entry(crgrp, head, mon.crdtgrp_list) { + if (crgrp == rdtgrp) + continue; + cpumask_andnot(&crgrp->cpu_mask, &crgrp->cpu_mask, + tmpmask); + } + update_closid_rmid(tmpmask, rdtgrp); + } + + /* Done pushing/pulling - update this group with new mask */ + cpumask_copy(&rdtgrp->cpu_mask, newmask); + + return 0; +} + +static void cpumask_rdtgrp_clear(struct rdtgroup *r, struct cpumask *m) +{ + struct rdtgroup *crgrp; + + cpumask_andnot(&r->cpu_mask, &r->cpu_mask, m); + /* update the child mon group masks as well*/ + list_for_each_entry(crgrp, &r->mon.crdtgrp_list, mon.crdtgrp_list) + cpumask_and(&crgrp->cpu_mask, &r->cpu_mask, &crgrp->cpu_mask); +} + +static int cpus_ctrl_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask, + cpumask_var_t tmpmask, cpumask_var_t tmpmask1) +{ + struct rdtgroup *r, *crgrp; + struct list_head *head; + + /* Check whether cpus are dropped from this group */ + cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask); + if (cpumask_weight(tmpmask)) { + /* Can't drop from default group */ + if (rdtgrp == &rdtgroup_default) { + rdt_last_cmd_puts("Can't drop CPUs from default group\n"); + return -EINVAL; + } + + /* Give any dropped cpus to rdtgroup_default */ + cpumask_or(&rdtgroup_default.cpu_mask, + &rdtgroup_default.cpu_mask, tmpmask); + update_closid_rmid(tmpmask, &rdtgroup_default); + } + + /* + * If we added cpus, remove them from previous group and + * the prev group's child groups that owned them + * and update per-cpu closid/rmid. + */ + cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask); + if (cpumask_weight(tmpmask)) { + list_for_each_entry(r, &rdt_all_groups, rdtgroup_list) { + if (r == rdtgrp) + continue; + cpumask_and(tmpmask1, &r->cpu_mask, tmpmask); + if (cpumask_weight(tmpmask1)) + cpumask_rdtgrp_clear(r, tmpmask1); + } + update_closid_rmid(tmpmask, rdtgrp); + } + + /* Done pushing/pulling - update this group with new mask */ + cpumask_copy(&rdtgrp->cpu_mask, newmask); + + /* + * Clear child mon group masks since there is a new parent mask + * now and update the rmid for the cpus the child lost. + */ + head = &rdtgrp->mon.crdtgrp_list; + list_for_each_entry(crgrp, head, mon.crdtgrp_list) { + cpumask_and(tmpmask, &rdtgrp->cpu_mask, &crgrp->cpu_mask); + update_closid_rmid(tmpmask, rdtgrp); + cpumask_clear(&crgrp->cpu_mask); + } + + return 0; +} + static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - cpumask_var_t tmpmask, newmask; - struct rdtgroup *rdtgrp, *r; + cpumask_var_t tmpmask, newmask, tmpmask1; + struct rdtgroup *rdtgrp; int ret; if (!buf) @@ -254,10 +380,17 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, free_cpumask_var(tmpmask); return -ENOMEM; } + if (!zalloc_cpumask_var(&tmpmask1, GFP_KERNEL)) { + free_cpumask_var(tmpmask); + free_cpumask_var(newmask); + return -ENOMEM; + } rdtgrp = rdtgroup_kn_lock_live(of->kn); + rdt_last_cmd_clear(); if (!rdtgrp) { ret = -ENOENT; + rdt_last_cmd_puts("directory was removed\n"); goto unlock; } @@ -266,51 +399,31 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, else ret = cpumask_parse(buf, newmask); - if (ret) + if (ret) { + rdt_last_cmd_puts("bad cpu list/mask\n"); goto unlock; + } /* check that user didn't specify any offline cpus */ cpumask_andnot(tmpmask, newmask, cpu_online_mask); if (cpumask_weight(tmpmask)) { ret = -EINVAL; + rdt_last_cmd_puts("can only assign online cpus\n"); goto unlock; } - /* Check whether cpus are dropped from this group */ - cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask); - if (cpumask_weight(tmpmask)) { - /* Can't drop from default group */ - if (rdtgrp == &rdtgroup_default) { - ret = -EINVAL; - goto unlock; - } - /* Give any dropped cpus to rdtgroup_default */ - cpumask_or(&rdtgroup_default.cpu_mask, - &rdtgroup_default.cpu_mask, tmpmask); - rdt_update_closid(tmpmask, &rdtgroup_default.closid); - } - - /* - * If we added cpus, remove them from previous group that owned them - * and update per-cpu closid - */ - cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask); - if (cpumask_weight(tmpmask)) { - list_for_each_entry(r, &rdt_all_groups, rdtgroup_list) { - if (r == rdtgrp) - continue; - cpumask_andnot(&r->cpu_mask, &r->cpu_mask, tmpmask); - } - rdt_update_closid(tmpmask, &rdtgrp->closid); - } - - /* Done pushing/pulling - update this group with new mask */ - cpumask_copy(&rdtgrp->cpu_mask, newmask); + if (rdtgrp->type == RDTCTRL_GROUP) + ret = cpus_ctrl_write(rdtgrp, newmask, tmpmask, tmpmask1); + else if (rdtgrp->type == RDTMON_GROUP) + ret = cpus_mon_write(rdtgrp, newmask, tmpmask); + else + ret = -EINVAL; unlock: rdtgroup_kn_unlock(of->kn); free_cpumask_var(tmpmask); free_cpumask_var(newmask); + free_cpumask_var(tmpmask1); return ret ?: nbytes; } @@ -336,6 +449,7 @@ static void move_myself(struct callback_head *head) if (atomic_dec_and_test(&rdtgrp->waitcount) && (rdtgrp->flags & RDT_DELETED)) { current->closid = 0; + current->rmid = 0; kfree(rdtgrp); } @@ -373,8 +487,24 @@ static int __rdtgroup_move_task(struct task_struct *tsk, */ atomic_dec(&rdtgrp->waitcount); kfree(callback); + rdt_last_cmd_puts("task exited\n"); } else { - tsk->closid = rdtgrp->closid; + /* + * For ctrl_mon groups move both closid and rmid. + * For monitor groups, can move the tasks only from + * their parent CTRL group. + */ + if (rdtgrp->type == RDTCTRL_GROUP) { + tsk->closid = rdtgrp->closid; + tsk->rmid = rdtgrp->mon.rmid; + } else if (rdtgrp->type == RDTMON_GROUP) { + if (rdtgrp->mon.parent->closid == tsk->closid) { + tsk->rmid = rdtgrp->mon.rmid; + } else { + rdt_last_cmd_puts("Can't move task to different control group\n"); + ret = -EINVAL; + } + } } return ret; } @@ -392,8 +522,10 @@ static int rdtgroup_task_write_permission(struct task_struct *task, */ if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) && !uid_eq(cred->euid, tcred->uid) && - !uid_eq(cred->euid, tcred->suid)) + !uid_eq(cred->euid, tcred->suid)) { + rdt_last_cmd_printf("No permission to move task %d\n", task->pid); ret = -EPERM; + } put_cred(tcred); return ret; @@ -410,6 +542,7 @@ static int rdtgroup_move_task(pid_t pid, struct rdtgroup *rdtgrp, tsk = find_task_by_vpid(pid); if (!tsk) { rcu_read_unlock(); + rdt_last_cmd_printf("No task %d\n", pid); return -ESRCH; } } else { @@ -437,6 +570,7 @@ static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of, if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) return -EINVAL; rdtgrp = rdtgroup_kn_lock_live(of->kn); + rdt_last_cmd_clear(); if (rdtgrp) ret = rdtgroup_move_task(pid, rdtgrp, of); @@ -454,7 +588,8 @@ static void show_rdt_tasks(struct rdtgroup *r, struct seq_file *s) rcu_read_lock(); for_each_process_thread(p, t) { - if (t->closid == r->closid) + if ((r->type == RDTCTRL_GROUP && t->closid == r->closid) || + (r->type == RDTMON_GROUP && t->rmid == r->mon.rmid)) seq_printf(s, "%d\n", t->pid); } rcu_read_unlock(); @@ -476,38 +611,20 @@ static int rdtgroup_tasks_show(struct kernfs_open_file *of, return ret; } -/* Files in each rdtgroup */ -static struct rftype rdtgroup_base_files[] = { - { - .name = "cpus", - .mode = 0644, - .kf_ops = &rdtgroup_kf_single_ops, - .write = rdtgroup_cpus_write, - .seq_show = rdtgroup_cpus_show, - }, - { - .name = "cpus_list", - .mode = 0644, - .kf_ops = &rdtgroup_kf_single_ops, - .write = rdtgroup_cpus_write, - .seq_show = rdtgroup_cpus_show, - .flags = RFTYPE_FLAGS_CPUS_LIST, - }, - { - .name = "tasks", - .mode = 0644, - .kf_ops = &rdtgroup_kf_single_ops, - .write = rdtgroup_tasks_write, - .seq_show = rdtgroup_tasks_show, - }, - { - .name = "schemata", - .mode = 0644, - .kf_ops = &rdtgroup_kf_single_ops, - .write = rdtgroup_schemata_write, - .seq_show = rdtgroup_schemata_show, - }, -}; +static int rdt_last_cmd_status_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + int len; + + mutex_lock(&rdtgroup_mutex); + len = seq_buf_used(&last_cmd_status); + if (len) + seq_printf(seq, "%.*s", len, last_cmd_status_buf); + else + seq_puts(seq, "ok\n"); + mutex_unlock(&rdtgroup_mutex); + return 0; +} static int rdt_num_closids_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) @@ -536,6 +653,15 @@ static int rdt_min_cbm_bits_show(struct kernfs_open_file *of, return 0; } +static int rdt_shareable_bits_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + + seq_printf(seq, "%x\n", r->cache.shareable_bits); + return 0; +} + static int rdt_min_bw_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { @@ -545,6 +671,28 @@ static int rdt_min_bw_show(struct kernfs_open_file *of, return 0; } +static int rdt_num_rmids_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + + seq_printf(seq, "%d\n", r->num_rmid); + + return 0; +} + +static int rdt_mon_features_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + struct mon_evt *mevt; + + list_for_each_entry(mevt, &r->evt_list, list) + seq_printf(seq, "%s\n", mevt->name); + + return 0; +} + static int rdt_bw_gran_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { @@ -563,74 +711,207 @@ static int rdt_delay_linear_show(struct kernfs_open_file *of, return 0; } +static int max_threshold_occ_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct rdt_resource *r = of->kn->parent->priv; + + seq_printf(seq, "%u\n", intel_cqm_threshold * r->mon_scale); + + return 0; +} + +static ssize_t max_threshold_occ_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct rdt_resource *r = of->kn->parent->priv; + unsigned int bytes; + int ret; + + ret = kstrtouint(buf, 0, &bytes); + if (ret) + return ret; + + if (bytes > (boot_cpu_data.x86_cache_size * 1024)) + return -EINVAL; + + intel_cqm_threshold = bytes / r->mon_scale; + + return nbytes; +} + /* rdtgroup information files for one cache resource. */ -static struct rftype res_cache_info_files[] = { +static struct rftype res_common_files[] = { + { + .name = "last_cmd_status", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_last_cmd_status_show, + .fflags = RF_TOP_INFO, + }, { .name = "num_closids", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_num_closids_show, + .fflags = RF_CTRL_INFO, + }, + { + .name = "mon_features", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_mon_features_show, + .fflags = RF_MON_INFO, + }, + { + .name = "num_rmids", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_num_rmids_show, + .fflags = RF_MON_INFO, }, { .name = "cbm_mask", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_default_ctrl_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, }, { .name = "min_cbm_bits", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_min_cbm_bits_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, }, -}; - -/* rdtgroup information files for memory bandwidth. */ -static struct rftype res_mba_info_files[] = { { - .name = "num_closids", + .name = "shareable_bits", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, - .seq_show = rdt_num_closids_show, + .seq_show = rdt_shareable_bits_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, }, { .name = "min_bandwidth", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_min_bw_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_MB, }, { .name = "bandwidth_gran", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_bw_gran_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_MB, }, { .name = "delay_linear", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_delay_linear_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_MB, + }, + { + .name = "max_threshold_occupancy", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = max_threshold_occ_write, + .seq_show = max_threshold_occ_show, + .fflags = RF_MON_INFO | RFTYPE_RES_CACHE, + }, + { + .name = "cpus", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_cpus_write, + .seq_show = rdtgroup_cpus_show, + .fflags = RFTYPE_BASE, + }, + { + .name = "cpus_list", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_cpus_write, + .seq_show = rdtgroup_cpus_show, + .flags = RFTYPE_FLAGS_CPUS_LIST, + .fflags = RFTYPE_BASE, + }, + { + .name = "tasks", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_tasks_write, + .seq_show = rdtgroup_tasks_show, + .fflags = RFTYPE_BASE, + }, + { + .name = "schemata", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_schemata_write, + .seq_show = rdtgroup_schemata_show, + .fflags = RF_CTRL_BASE, }, }; -void rdt_get_mba_infofile(struct rdt_resource *r) +static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags) { - r->info_files = res_mba_info_files; - r->nr_info_files = ARRAY_SIZE(res_mba_info_files); + struct rftype *rfts, *rft; + int ret, len; + + rfts = res_common_files; + len = ARRAY_SIZE(res_common_files); + + lockdep_assert_held(&rdtgroup_mutex); + + for (rft = rfts; rft < rfts + len; rft++) { + if ((fflags & rft->fflags) == rft->fflags) { + ret = rdtgroup_add_file(kn, rft); + if (ret) + goto error; + } + } + + return 0; +error: + pr_warn("Failed to add %s, err=%d\n", rft->name, ret); + while (--rft >= rfts) { + if ((fflags & rft->fflags) == rft->fflags) + kernfs_remove_by_name(kn, rft->name); + } + return ret; } -void rdt_get_cache_infofile(struct rdt_resource *r) +static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name, + unsigned long fflags) { - r->info_files = res_cache_info_files; - r->nr_info_files = ARRAY_SIZE(res_cache_info_files); + struct kernfs_node *kn_subdir; + int ret; + + kn_subdir = kernfs_create_dir(kn_info, name, + kn_info->mode, r); + if (IS_ERR(kn_subdir)) + return PTR_ERR(kn_subdir); + + kernfs_get(kn_subdir); + ret = rdtgroup_kn_set_ugid(kn_subdir); + if (ret) + return ret; + + ret = rdtgroup_add_files(kn_subdir, fflags); + if (!ret) + kernfs_activate(kn_subdir); + + return ret; } static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) { - struct kernfs_node *kn_subdir; - struct rftype *res_info_files; struct rdt_resource *r; - int ret, len; + unsigned long fflags; + char name[32]; + int ret; /* create the directory */ kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL); @@ -638,25 +919,23 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) return PTR_ERR(kn_info); kernfs_get(kn_info); - for_each_enabled_rdt_resource(r) { - kn_subdir = kernfs_create_dir(kn_info, r->name, - kn_info->mode, r); - if (IS_ERR(kn_subdir)) { - ret = PTR_ERR(kn_subdir); - goto out_destroy; - } - kernfs_get(kn_subdir); - ret = rdtgroup_kn_set_ugid(kn_subdir); + ret = rdtgroup_add_files(kn_info, RF_TOP_INFO); + if (ret) + goto out_destroy; + + for_each_alloc_enabled_rdt_resource(r) { + fflags = r->fflags | RF_CTRL_INFO; + ret = rdtgroup_mkdir_info_resdir(r, r->name, fflags); if (ret) goto out_destroy; + } - res_info_files = r->info_files; - len = r->nr_info_files; - - ret = rdtgroup_add_files(kn_subdir, res_info_files, len); + for_each_mon_enabled_rdt_resource(r) { + fflags = r->fflags | RF_MON_INFO; + sprintf(name, "%s_MON", r->name); + ret = rdtgroup_mkdir_info_resdir(r, name, fflags); if (ret) goto out_destroy; - kernfs_activate(kn_subdir); } /* @@ -678,6 +957,39 @@ out_destroy: return ret; } +static int +mongroup_create_dir(struct kernfs_node *parent_kn, struct rdtgroup *prgrp, + char *name, struct kernfs_node **dest_kn) +{ + struct kernfs_node *kn; + int ret; + + /* create the directory */ + kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp); + if (IS_ERR(kn)) + return PTR_ERR(kn); + + if (dest_kn) + *dest_kn = kn; + + /* + * This extra ref will be put in kernfs_remove() and guarantees + * that @rdtgrp->kn is always accessible. + */ + kernfs_get(kn); + + ret = rdtgroup_kn_set_ugid(kn); + if (ret) + goto out_destroy; + + kernfs_activate(kn); + + return 0; + +out_destroy: + kernfs_remove(kn); + return ret; +} static void l3_qos_cfg_update(void *arg) { bool *enable = arg; @@ -718,14 +1030,15 @@ static int cdp_enable(void) struct rdt_resource *r_l3 = &rdt_resources_all[RDT_RESOURCE_L3]; int ret; - if (!r_l3->capable || !r_l3data->capable || !r_l3code->capable) + if (!r_l3->alloc_capable || !r_l3data->alloc_capable || + !r_l3code->alloc_capable) return -EINVAL; ret = set_l3_qos_cfg(r_l3, true); if (!ret) { - r_l3->enabled = false; - r_l3data->enabled = true; - r_l3code->enabled = true; + r_l3->alloc_enabled = false; + r_l3data->alloc_enabled = true; + r_l3code->alloc_enabled = true; } return ret; } @@ -734,11 +1047,11 @@ static void cdp_disable(void) { struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3]; - r->enabled = r->capable; + r->alloc_enabled = r->alloc_capable; - if (rdt_resources_all[RDT_RESOURCE_L3DATA].enabled) { - rdt_resources_all[RDT_RESOURCE_L3DATA].enabled = false; - rdt_resources_all[RDT_RESOURCE_L3CODE].enabled = false; + if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled) { + rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled = false; + rdt_resources_all[RDT_RESOURCE_L3CODE].alloc_enabled = false; set_l3_qos_cfg(r, false); } } @@ -823,13 +1136,20 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn) } } +static int mkdir_mondata_all(struct kernfs_node *parent_kn, + struct rdtgroup *prgrp, + struct kernfs_node **mon_data_kn); + static struct dentry *rdt_mount(struct file_system_type *fs_type, int flags, const char *unused_dev_name, void *data) { + struct rdt_domain *dom; + struct rdt_resource *r; struct dentry *dentry; int ret; + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); /* * resctrl file system can only be mounted once. @@ -853,20 +1173,61 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type, goto out_cdp; } + if (rdt_mon_capable) { + ret = mongroup_create_dir(rdtgroup_default.kn, + NULL, "mon_groups", + &kn_mongrp); + if (ret) { + dentry = ERR_PTR(ret); + goto out_info; + } + kernfs_get(kn_mongrp); + + ret = mkdir_mondata_all(rdtgroup_default.kn, + &rdtgroup_default, &kn_mondata); + if (ret) { + dentry = ERR_PTR(ret); + goto out_mongrp; + } + kernfs_get(kn_mondata); + rdtgroup_default.mon.mon_data_kn = kn_mondata; + } + dentry = kernfs_mount(fs_type, flags, rdt_root, RDTGROUP_SUPER_MAGIC, NULL); if (IS_ERR(dentry)) - goto out_destroy; + goto out_mondata; + + if (rdt_alloc_capable) + static_branch_enable_cpuslocked(&rdt_alloc_enable_key); + if (rdt_mon_capable) + static_branch_enable_cpuslocked(&rdt_mon_enable_key); + + if (rdt_alloc_capable || rdt_mon_capable) + static_branch_enable_cpuslocked(&rdt_enable_key); + + if (is_mbm_enabled()) { + r = &rdt_resources_all[RDT_RESOURCE_L3]; + list_for_each_entry(dom, &r->domains, list) + mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL); + } - static_branch_enable(&rdt_enable_key); goto out; -out_destroy: +out_mondata: + if (rdt_mon_capable) + kernfs_remove(kn_mondata); +out_mongrp: + if (rdt_mon_capable) + kernfs_remove(kn_mongrp); +out_info: kernfs_remove(kn_info); out_cdp: cdp_disable(); out: + rdt_last_cmd_clear(); mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); return dentry; } @@ -909,6 +1270,18 @@ static int reset_all_ctrls(struct rdt_resource *r) return 0; } +static bool is_closid_match(struct task_struct *t, struct rdtgroup *r) +{ + return (rdt_alloc_capable && + (r->type == RDTCTRL_GROUP) && (t->closid == r->closid)); +} + +static bool is_rmid_match(struct task_struct *t, struct rdtgroup *r) +{ + return (rdt_mon_capable && + (r->type == RDTMON_GROUP) && (t->rmid == r->mon.rmid)); +} + /* * Move tasks from one to the other group. If @from is NULL, then all tasks * in the systems are moved unconditionally (used for teardown). @@ -924,8 +1297,11 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to, read_lock(&tasklist_lock); for_each_process_thread(p, t) { - if (!from || t->closid == from->closid) { + if (!from || is_closid_match(t, from) || + is_rmid_match(t, from)) { t->closid = to->closid; + t->rmid = to->mon.rmid; + #ifdef CONFIG_SMP /* * This is safe on x86 w/o barriers as the ordering @@ -944,6 +1320,19 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to, read_unlock(&tasklist_lock); } +static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp) +{ + struct rdtgroup *sentry, *stmp; + struct list_head *head; + + head = &rdtgrp->mon.crdtgrp_list; + list_for_each_entry_safe(sentry, stmp, head, mon.crdtgrp_list) { + free_rmid(sentry->mon.rmid); + list_del(&sentry->mon.crdtgrp_list); + kfree(sentry); + } +} + /* * Forcibly remove all of subdirectories under root. */ @@ -955,6 +1344,9 @@ static void rmdir_all_sub(void) rdt_move_group_tasks(NULL, &rdtgroup_default, NULL); list_for_each_entry_safe(rdtgrp, tmp, &rdt_all_groups, rdtgroup_list) { + /* Free any child rmids */ + free_all_child_rdtgrp(rdtgrp); + /* Remove each rdtgroup other than root */ if (rdtgrp == &rdtgroup_default) continue; @@ -967,32 +1359,38 @@ static void rmdir_all_sub(void) cpumask_or(&rdtgroup_default.cpu_mask, &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask); + free_rmid(rdtgrp->mon.rmid); + kernfs_remove(rdtgrp->kn); list_del(&rdtgrp->rdtgroup_list); kfree(rdtgrp); } /* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */ - get_online_cpus(); - rdt_update_closid(cpu_online_mask, &rdtgroup_default.closid); - put_online_cpus(); + update_closid_rmid(cpu_online_mask, &rdtgroup_default); kernfs_remove(kn_info); + kernfs_remove(kn_mongrp); + kernfs_remove(kn_mondata); } static void rdt_kill_sb(struct super_block *sb) { struct rdt_resource *r; + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); /*Put everything back to default values. */ - for_each_enabled_rdt_resource(r) + for_each_alloc_enabled_rdt_resource(r) reset_all_ctrls(r); cdp_disable(); rmdir_all_sub(); - static_branch_disable(&rdt_enable_key); + static_branch_disable_cpuslocked(&rdt_alloc_enable_key); + static_branch_disable_cpuslocked(&rdt_mon_enable_key); + static_branch_disable_cpuslocked(&rdt_enable_key); kernfs_kill_sb(sb); mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); } static struct file_system_type rdt_fs_type = { @@ -1001,46 +1399,227 @@ static struct file_system_type rdt_fs_type = { .kill_sb = rdt_kill_sb, }; -static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name, - umode_t mode) +static int mon_addfile(struct kernfs_node *parent_kn, const char *name, + void *priv) { - struct rdtgroup *parent, *rdtgrp; struct kernfs_node *kn; - int ret, closid; + int ret = 0; - /* Only allow mkdir in the root directory */ - if (parent_kn != rdtgroup_default.kn) - return -EPERM; + kn = __kernfs_create_file(parent_kn, name, 0444, 0, + &kf_mondata_ops, priv, NULL, NULL); + if (IS_ERR(kn)) + return PTR_ERR(kn); - /* Do not accept '\n' to avoid unparsable situation. */ - if (strchr(name, '\n')) - return -EINVAL; + ret = rdtgroup_kn_set_ugid(kn); + if (ret) { + kernfs_remove(kn); + return ret; + } - parent = rdtgroup_kn_lock_live(parent_kn); - if (!parent) { - ret = -ENODEV; - goto out_unlock; + return ret; +} + +/* + * Remove all subdirectories of mon_data of ctrl_mon groups + * and monitor groups with given domain id. + */ +void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, unsigned int dom_id) +{ + struct rdtgroup *prgrp, *crgrp; + char name[32]; + + if (!r->mon_enabled) + return; + + list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { + sprintf(name, "mon_%s_%02d", r->name, dom_id); + kernfs_remove_by_name(prgrp->mon.mon_data_kn, name); + + list_for_each_entry(crgrp, &prgrp->mon.crdtgrp_list, mon.crdtgrp_list) + kernfs_remove_by_name(crgrp->mon.mon_data_kn, name); } +} - ret = closid_alloc(); - if (ret < 0) +static int mkdir_mondata_subdir(struct kernfs_node *parent_kn, + struct rdt_domain *d, + struct rdt_resource *r, struct rdtgroup *prgrp) +{ + union mon_data_bits priv; + struct kernfs_node *kn; + struct mon_evt *mevt; + struct rmid_read rr; + char name[32]; + int ret; + + sprintf(name, "mon_%s_%02d", r->name, d->id); + /* create the directory */ + kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp); + if (IS_ERR(kn)) + return PTR_ERR(kn); + + /* + * This extra ref will be put in kernfs_remove() and guarantees + * that kn is always accessible. + */ + kernfs_get(kn); + ret = rdtgroup_kn_set_ugid(kn); + if (ret) + goto out_destroy; + + if (WARN_ON(list_empty(&r->evt_list))) { + ret = -EPERM; + goto out_destroy; + } + + priv.u.rid = r->rid; + priv.u.domid = d->id; + list_for_each_entry(mevt, &r->evt_list, list) { + priv.u.evtid = mevt->evtid; + ret = mon_addfile(kn, mevt->name, priv.priv); + if (ret) + goto out_destroy; + + if (is_mbm_event(mevt->evtid)) + mon_event_read(&rr, d, prgrp, mevt->evtid, true); + } + kernfs_activate(kn); + return 0; + +out_destroy: + kernfs_remove(kn); + return ret; +} + +/* + * Add all subdirectories of mon_data for "ctrl_mon" groups + * and "monitor" groups with given domain id. + */ +void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, + struct rdt_domain *d) +{ + struct kernfs_node *parent_kn; + struct rdtgroup *prgrp, *crgrp; + struct list_head *head; + + if (!r->mon_enabled) + return; + + list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { + parent_kn = prgrp->mon.mon_data_kn; + mkdir_mondata_subdir(parent_kn, d, r, prgrp); + + head = &prgrp->mon.crdtgrp_list; + list_for_each_entry(crgrp, head, mon.crdtgrp_list) { + parent_kn = crgrp->mon.mon_data_kn; + mkdir_mondata_subdir(parent_kn, d, r, crgrp); + } + } +} + +static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn, + struct rdt_resource *r, + struct rdtgroup *prgrp) +{ + struct rdt_domain *dom; + int ret; + + list_for_each_entry(dom, &r->domains, list) { + ret = mkdir_mondata_subdir(parent_kn, dom, r, prgrp); + if (ret) + return ret; + } + + return 0; +} + +/* + * This creates a directory mon_data which contains the monitored data. + * + * mon_data has one directory for each domain whic are named + * in the format mon_<domain_name>_<domain_id>. For ex: A mon_data + * with L3 domain looks as below: + * ./mon_data: + * mon_L3_00 + * mon_L3_01 + * mon_L3_02 + * ... + * + * Each domain directory has one file per event: + * ./mon_L3_00/: + * llc_occupancy + * + */ +static int mkdir_mondata_all(struct kernfs_node *parent_kn, + struct rdtgroup *prgrp, + struct kernfs_node **dest_kn) +{ + struct rdt_resource *r; + struct kernfs_node *kn; + int ret; + + /* + * Create the mon_data directory first. + */ + ret = mongroup_create_dir(parent_kn, NULL, "mon_data", &kn); + if (ret) + return ret; + + if (dest_kn) + *dest_kn = kn; + + /* + * Create the subdirectories for each domain. Note that all events + * in a domain like L3 are grouped into a resource whose domain is L3 + */ + for_each_mon_enabled_rdt_resource(r) { + ret = mkdir_mondata_subdir_alldom(kn, r, prgrp); + if (ret) + goto out_destroy; + } + + return 0; + +out_destroy: + kernfs_remove(kn); + return ret; +} + +static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, + struct kernfs_node *prgrp_kn, + const char *name, umode_t mode, + enum rdt_group_type rtype, struct rdtgroup **r) +{ + struct rdtgroup *prdtgrp, *rdtgrp; + struct kernfs_node *kn; + uint files = 0; + int ret; + + prdtgrp = rdtgroup_kn_lock_live(prgrp_kn); + rdt_last_cmd_clear(); + if (!prdtgrp) { + ret = -ENODEV; + rdt_last_cmd_puts("directory was removed\n"); goto out_unlock; - closid = ret; + } /* allocate the rdtgroup. */ rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL); if (!rdtgrp) { ret = -ENOSPC; - goto out_closid_free; + rdt_last_cmd_puts("kernel out of memory\n"); + goto out_unlock; } - rdtgrp->closid = closid; - list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups); + *r = rdtgrp; + rdtgrp->mon.parent = prdtgrp; + rdtgrp->type = rtype; + INIT_LIST_HEAD(&rdtgrp->mon.crdtgrp_list); /* kernfs creates the directory for rdtgrp */ - kn = kernfs_create_dir(parent->kn, name, mode, rdtgrp); + kn = kernfs_create_dir(parent_kn, name, mode, rdtgrp); if (IS_ERR(kn)) { ret = PTR_ERR(kn); - goto out_cancel_ref; + rdt_last_cmd_puts("kernfs create error\n"); + goto out_free_rgrp; } rdtgrp->kn = kn; @@ -1053,46 +1632,225 @@ static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name, kernfs_get(kn); ret = rdtgroup_kn_set_ugid(kn); - if (ret) + if (ret) { + rdt_last_cmd_puts("kernfs perm error\n"); goto out_destroy; + } - ret = rdtgroup_add_files(kn, rdtgroup_base_files, - ARRAY_SIZE(rdtgroup_base_files)); - if (ret) + files = RFTYPE_BASE | BIT(RF_CTRLSHIFT + rtype); + ret = rdtgroup_add_files(kn, files); + if (ret) { + rdt_last_cmd_puts("kernfs fill error\n"); goto out_destroy; + } + if (rdt_mon_capable) { + ret = alloc_rmid(); + if (ret < 0) { + rdt_last_cmd_puts("out of RMIDs\n"); + goto out_destroy; + } + rdtgrp->mon.rmid = ret; + + ret = mkdir_mondata_all(kn, rdtgrp, &rdtgrp->mon.mon_data_kn); + if (ret) { + rdt_last_cmd_puts("kernfs subdir error\n"); + goto out_idfree; + } + } kernfs_activate(kn); - ret = 0; - goto out_unlock; + /* + * The caller unlocks the prgrp_kn upon success. + */ + return 0; +out_idfree: + free_rmid(rdtgrp->mon.rmid); out_destroy: kernfs_remove(rdtgrp->kn); -out_cancel_ref: - list_del(&rdtgrp->rdtgroup_list); +out_free_rgrp: kfree(rdtgrp); -out_closid_free: - closid_free(closid); out_unlock: - rdtgroup_kn_unlock(parent_kn); + rdtgroup_kn_unlock(prgrp_kn); return ret; } -static int rdtgroup_rmdir(struct kernfs_node *kn) +static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp) +{ + kernfs_remove(rgrp->kn); + free_rmid(rgrp->mon.rmid); + kfree(rgrp); +} + +/* + * Create a monitor group under "mon_groups" directory of a control + * and monitor group(ctrl_mon). This is a resource group + * to monitor a subset of tasks and cpus in its parent ctrl_mon group. + */ +static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn, + struct kernfs_node *prgrp_kn, + const char *name, + umode_t mode) +{ + struct rdtgroup *rdtgrp, *prgrp; + int ret; + + ret = mkdir_rdt_prepare(parent_kn, prgrp_kn, name, mode, RDTMON_GROUP, + &rdtgrp); + if (ret) + return ret; + + prgrp = rdtgrp->mon.parent; + rdtgrp->closid = prgrp->closid; + + /* + * Add the rdtgrp to the list of rdtgrps the parent + * ctrl_mon group has to track. + */ + list_add_tail(&rdtgrp->mon.crdtgrp_list, &prgrp->mon.crdtgrp_list); + + rdtgroup_kn_unlock(prgrp_kn); + return ret; +} + +/* + * These are rdtgroups created under the root directory. Can be used + * to allocate and monitor resources. + */ +static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, + struct kernfs_node *prgrp_kn, + const char *name, umode_t mode) { - int ret, cpu, closid = rdtgroup_default.closid; struct rdtgroup *rdtgrp; - cpumask_var_t tmpmask; + struct kernfs_node *kn; + u32 closid; + int ret; - if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) - return -ENOMEM; + ret = mkdir_rdt_prepare(parent_kn, prgrp_kn, name, mode, RDTCTRL_GROUP, + &rdtgrp); + if (ret) + return ret; - rdtgrp = rdtgroup_kn_lock_live(kn); - if (!rdtgrp) { - ret = -EPERM; - goto out; + kn = rdtgrp->kn; + ret = closid_alloc(); + if (ret < 0) { + rdt_last_cmd_puts("out of CLOSIDs\n"); + goto out_common_fail; + } + closid = ret; + + rdtgrp->closid = closid; + list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups); + + if (rdt_mon_capable) { + /* + * Create an empty mon_groups directory to hold the subset + * of tasks and cpus to monitor. + */ + ret = mongroup_create_dir(kn, NULL, "mon_groups", NULL); + if (ret) { + rdt_last_cmd_puts("kernfs subdir error\n"); + goto out_id_free; + } } + goto out_unlock; + +out_id_free: + closid_free(closid); + list_del(&rdtgrp->rdtgroup_list); +out_common_fail: + mkdir_rdt_prepare_clean(rdtgrp); +out_unlock: + rdtgroup_kn_unlock(prgrp_kn); + return ret; +} + +/* + * We allow creating mon groups only with in a directory called "mon_groups" + * which is present in every ctrl_mon group. Check if this is a valid + * "mon_groups" directory. + * + * 1. The directory should be named "mon_groups". + * 2. The mon group itself should "not" be named "mon_groups". + * This makes sure "mon_groups" directory always has a ctrl_mon group + * as parent. + */ +static bool is_mon_groups(struct kernfs_node *kn, const char *name) +{ + return (!strcmp(kn->name, "mon_groups") && + strcmp(name, "mon_groups")); +} + +static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name, + umode_t mode) +{ + /* Do not accept '\n' to avoid unparsable situation. */ + if (strchr(name, '\n')) + return -EINVAL; + + /* + * If the parent directory is the root directory and RDT + * allocation is supported, add a control and monitoring + * subdirectory + */ + if (rdt_alloc_capable && parent_kn == rdtgroup_default.kn) + return rdtgroup_mkdir_ctrl_mon(parent_kn, parent_kn, name, mode); + + /* + * If RDT monitoring is supported and the parent directory is a valid + * "mon_groups" directory, add a monitoring subdirectory. + */ + if (rdt_mon_capable && is_mon_groups(parent_kn, name)) + return rdtgroup_mkdir_mon(parent_kn, parent_kn->parent, name, mode); + + return -EPERM; +} + +static int rdtgroup_rmdir_mon(struct kernfs_node *kn, struct rdtgroup *rdtgrp, + cpumask_var_t tmpmask) +{ + struct rdtgroup *prdtgrp = rdtgrp->mon.parent; + int cpu; + + /* Give any tasks back to the parent group */ + rdt_move_group_tasks(rdtgrp, prdtgrp, tmpmask); + + /* Update per cpu rmid of the moved CPUs first */ + for_each_cpu(cpu, &rdtgrp->cpu_mask) + per_cpu(pqr_state.default_rmid, cpu) = prdtgrp->mon.rmid; + /* + * Update the MSR on moved CPUs and CPUs which have moved + * task running on them. + */ + cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask); + update_closid_rmid(tmpmask, NULL); + + rdtgrp->flags = RDT_DELETED; + free_rmid(rdtgrp->mon.rmid); + + /* + * Remove the rdtgrp from the parent ctrl_mon group's list + */ + WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list)); + list_del(&rdtgrp->mon.crdtgrp_list); + + /* + * one extra hold on this, will drop when we kfree(rdtgrp) + * in rdtgroup_kn_unlock() + */ + kernfs_get(kn); + kernfs_remove(rdtgrp->kn); + + return 0; +} + +static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp, + cpumask_var_t tmpmask) +{ + int cpu; + /* Give any tasks back to the default group */ rdt_move_group_tasks(rdtgrp, &rdtgroup_default, tmpmask); @@ -1100,18 +1858,28 @@ static int rdtgroup_rmdir(struct kernfs_node *kn) cpumask_or(&rdtgroup_default.cpu_mask, &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask); - /* Update per cpu closid of the moved CPUs first */ - for_each_cpu(cpu, &rdtgrp->cpu_mask) - per_cpu(cpu_closid, cpu) = closid; + /* Update per cpu closid and rmid of the moved CPUs first */ + for_each_cpu(cpu, &rdtgrp->cpu_mask) { + per_cpu(pqr_state.default_closid, cpu) = rdtgroup_default.closid; + per_cpu(pqr_state.default_rmid, cpu) = rdtgroup_default.mon.rmid; + } + /* * Update the MSR on moved CPUs and CPUs which have moved * task running on them. */ cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask); - rdt_update_closid(tmpmask, NULL); + update_closid_rmid(tmpmask, NULL); rdtgrp->flags = RDT_DELETED; closid_free(rdtgrp->closid); + free_rmid(rdtgrp->mon.rmid); + + /* + * Free all the child monitor group rmids. + */ + free_all_child_rdtgrp(rdtgrp); + list_del(&rdtgrp->rdtgroup_list); /* @@ -1120,7 +1888,41 @@ static int rdtgroup_rmdir(struct kernfs_node *kn) */ kernfs_get(kn); kernfs_remove(rdtgrp->kn); - ret = 0; + + return 0; +} + +static int rdtgroup_rmdir(struct kernfs_node *kn) +{ + struct kernfs_node *parent_kn = kn->parent; + struct rdtgroup *rdtgrp; + cpumask_var_t tmpmask; + int ret = 0; + + if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) + return -ENOMEM; + + rdtgrp = rdtgroup_kn_lock_live(kn); + if (!rdtgrp) { + ret = -EPERM; + goto out; + } + + /* + * If the rdtgroup is a ctrl_mon group and parent directory + * is the root directory, remove the ctrl_mon group. + * + * If the rdtgroup is a mon group and parent directory + * is a valid "mon_groups" directory, remove the mon group. + */ + if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn) + ret = rdtgroup_rmdir_ctrl(kn, rdtgrp, tmpmask); + else if (rdtgrp->type == RDTMON_GROUP && + is_mon_groups(parent_kn, kn->name)) + ret = rdtgroup_rmdir_mon(kn, rdtgrp, tmpmask); + else + ret = -EPERM; + out: rdtgroup_kn_unlock(kn); free_cpumask_var(tmpmask); @@ -1129,7 +1931,7 @@ out: static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf) { - if (rdt_resources_all[RDT_RESOURCE_L3DATA].enabled) + if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled) seq_puts(seq, ",cdp"); return 0; } @@ -1153,10 +1955,13 @@ static int __init rdtgroup_setup_root(void) mutex_lock(&rdtgroup_mutex); rdtgroup_default.closid = 0; + rdtgroup_default.mon.rmid = 0; + rdtgroup_default.type = RDTCTRL_GROUP; + INIT_LIST_HEAD(&rdtgroup_default.mon.crdtgrp_list); + list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups); - ret = rdtgroup_add_files(rdt_root->kn, rdtgroup_base_files, - ARRAY_SIZE(rdtgroup_base_files)); + ret = rdtgroup_add_files(rdt_root->kn, RF_CTRL_BASE); if (ret) { kernfs_destroy_root(rdt_root); goto out; @@ -1183,6 +1988,9 @@ int __init rdtgroup_init(void) { int ret = 0; + seq_buf_init(&last_cmd_status, last_cmd_status_buf, + sizeof(last_cmd_status_buf)); + ret = rdtgroup_setup_root(); if (ret) return ret; diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c index e42117d5f4d7..3fed38812eea 100644 --- a/arch/x86/kernel/cpu/match.c +++ b/arch/x86/kernel/cpu/match.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <asm/cpu_device_id.h> #include <asm/cpufeature.h> #include <linux/cpu.h> diff --git a/arch/x86/kernel/cpu/mcheck/Makefile b/arch/x86/kernel/cpu/mcheck/Makefile index 43051f0777d4..bcc7c54c7041 100644 --- a/arch/x86/kernel/cpu/mcheck/Makefile +++ b/arch/x86/kernel/cpu/mcheck/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 obj-y = mce.o mce-severity.o mce-genpool.o obj-$(CONFIG_X86_ANCIENT_MCE) += winchip.o p5.o diff --git a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c index 10cec43aac38..7f85b76f43bc 100644 --- a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c +++ b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c @@ -24,14 +24,6 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex); static char mce_helper[128]; static char *mce_helper_argv[2] = { mce_helper, NULL }; -#define mce_log_get_idx_check(p) \ -({ \ - RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ - !lockdep_is_held(&mce_chrdev_read_mutex), \ - "suspicious mce_log_get_idx_check() usage"); \ - smp_load_acquire(&(p)); \ -}) - /* * Lockless MCE logging infrastructure. * This avoids deadlocks on printk locks without having to break locks. Also @@ -53,43 +45,32 @@ static int dev_mce_log(struct notifier_block *nb, unsigned long val, void *data) { struct mce *mce = (struct mce *)data; - unsigned int next, entry; - - wmb(); - for (;;) { - entry = mce_log_get_idx_check(mcelog.next); - for (;;) { - - /* - * When the buffer fills up discard new entries. - * Assume that the earlier errors are the more - * interesting ones: - */ - if (entry >= MCE_LOG_LEN) { - set_bit(MCE_OVERFLOW, - (unsigned long *)&mcelog.flags); - return NOTIFY_OK; - } - /* Old left over entry. Skip: */ - if (mcelog.entry[entry].finished) { - entry++; - continue; - } - break; - } - smp_rmb(); - next = entry + 1; - if (cmpxchg(&mcelog.next, entry, next) == entry) - break; + unsigned int entry; + + mutex_lock(&mce_chrdev_read_mutex); + + entry = mcelog.next; + + /* + * When the buffer fills up discard new entries. Assume that the + * earlier errors are the more interesting ones: + */ + if (entry >= MCE_LOG_LEN) { + set_bit(MCE_OVERFLOW, (unsigned long *)&mcelog.flags); + goto unlock; } + + mcelog.next = entry + 1; + memcpy(mcelog.entry + entry, mce, sizeof(struct mce)); - wmb(); mcelog.entry[entry].finished = 1; - wmb(); /* wake processes polling /dev/mcelog */ wake_up_interruptible(&mce_chrdev_wait); +unlock: + mutex_unlock(&mce_chrdev_read_mutex); + return NOTIFY_OK; } @@ -177,13 +158,6 @@ static int mce_chrdev_release(struct inode *inode, struct file *file) return 0; } -static void collect_tscs(void *data) -{ - unsigned long *cpu_tsc = (unsigned long *)data; - - cpu_tsc[smp_processor_id()] = rdtsc(); -} - static int mce_apei_read_done; /* Collect MCE record of previous boot in persistent storage via APEI ERST. */ @@ -231,14 +205,9 @@ static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf, size_t usize, loff_t *off) { char __user *buf = ubuf; - unsigned long *cpu_tsc; - unsigned prev, next; + unsigned next; int i, err; - cpu_tsc = kmalloc(nr_cpu_ids * sizeof(long), GFP_KERNEL); - if (!cpu_tsc) - return -ENOMEM; - mutex_lock(&mce_chrdev_read_mutex); if (!mce_apei_read_done) { @@ -247,65 +216,29 @@ static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf, goto out; } - next = mce_log_get_idx_check(mcelog.next); - /* Only supports full reads right now */ err = -EINVAL; if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce)) goto out; + next = mcelog.next; err = 0; - prev = 0; - do { - for (i = prev; i < next; i++) { - unsigned long start = jiffies; - struct mce *m = &mcelog.entry[i]; - - while (!m->finished) { - if (time_after_eq(jiffies, start + 2)) { - memset(m, 0, sizeof(*m)); - goto timeout; - } - cpu_relax(); - } - smp_rmb(); - err |= copy_to_user(buf, m, sizeof(*m)); - buf += sizeof(*m); -timeout: - ; - } - - memset(mcelog.entry + prev, 0, - (next - prev) * sizeof(struct mce)); - prev = next; - next = cmpxchg(&mcelog.next, prev, 0); - } while (next != prev); - - synchronize_sched(); - /* - * Collect entries that were still getting written before the - * synchronize. - */ - on_each_cpu(collect_tscs, cpu_tsc, 1); - - for (i = next; i < MCE_LOG_LEN; i++) { + for (i = 0; i < next; i++) { struct mce *m = &mcelog.entry[i]; - if (m->finished && m->tsc < cpu_tsc[m->cpu]) { - err |= copy_to_user(buf, m, sizeof(*m)); - smp_rmb(); - buf += sizeof(*m); - memset(m, 0, sizeof(*m)); - } + err |= copy_to_user(buf, m, sizeof(*m)); + buf += sizeof(*m); } + memset(mcelog.entry, 0, next * sizeof(struct mce)); + mcelog.next = 0; + if (err) err = -EFAULT; out: mutex_unlock(&mce_chrdev_read_mutex); - kfree(cpu_tsc); return err ? err : buf - ubuf; } diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index 098530a93bb7..aa0d5df9dc60 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -1,3 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __X86_MCE_INTERNAL_H__ +#define __X86_MCE_INTERNAL_H__ + #include <linux/device.h> #include <asm/mce.h> @@ -108,3 +112,7 @@ static inline void mce_work_trigger(void) { } static inline void mce_register_injector_chain(struct notifier_block *nb) { } static inline void mce_unregister_injector_chain(struct notifier_block *nb) { } #endif + +extern struct mca_config mca_cfg; + +#endif /* __X86_MCE_INTERNAL_H__ */ diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 87cc9ab7a13c..4ca632a06e0b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -204,7 +204,7 @@ static int error_context(struct mce *m) return IN_KERNEL; } -static int mce_severity_amd_smca(struct mce *m, int err_ctx) +static int mce_severity_amd_smca(struct mce *m, enum context err_ctx) { u32 addr = MSR_AMD64_SMCA_MCx_CONFIG(m->bank); u32 low, high; @@ -245,6 +245,9 @@ static int mce_severity_amd(struct mce *m, int tolerant, char **msg, bool is_exc if (m->status & MCI_STATUS_UC) { + if (ctx == IN_KERNEL) + return MCE_PANIC_SEVERITY; + /* * On older systems where overflow_recov flag is not present, we * should simply panic if an error overflow occurs. If @@ -255,10 +258,6 @@ static int mce_severity_amd(struct mce *m, int tolerant, char **msg, bool is_exc if (mce_flags.smca) return mce_severity_amd_smca(m, ctx); - /* software can try to contain */ - if (!(m->mcgstatus & MCG_STATUS_RIPV) && (ctx == IN_KERNEL)) - return MCE_PANIC_SEVERITY; - /* kill current process */ return MCE_AR_SEVERITY; } else { diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 6dde0497efc7..b1d616d08eee 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -51,6 +51,7 @@ #include <asm/mce.h> #include <asm/msr.h> #include <asm/reboot.h> +#include <asm/set_memory.h> #include "mce-internal.h" @@ -1051,6 +1052,48 @@ static int do_memory_failure(struct mce *m) return ret; } +#if defined(arch_unmap_kpfn) && defined(CONFIG_MEMORY_FAILURE) + +void arch_unmap_kpfn(unsigned long pfn) +{ + unsigned long decoy_addr; + + /* + * Unmap this page from the kernel 1:1 mappings to make sure + * we don't log more errors because of speculative access to + * the page. + * We would like to just call: + * set_memory_np((unsigned long)pfn_to_kaddr(pfn), 1); + * but doing that would radically increase the odds of a + * speculative access to the posion page because we'd have + * the virtual address of the kernel 1:1 mapping sitting + * around in registers. + * Instead we get tricky. We create a non-canonical address + * that looks just like the one we want, but has bit 63 flipped. + * This relies on set_memory_np() not checking whether we passed + * a legal address. + */ + +/* + * Build time check to see if we have a spare virtual bit. Don't want + * to leave this until run time because most developers don't have a + * system that can exercise this code path. This will only become a + * problem if/when we move beyond 5-level page tables. + * + * Hard code "9" here because cpp doesn't grok ilog2(PTRS_PER_PGD) + */ +#if PGDIR_SHIFT + 9 < 63 + decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63)); +#else +#error "no unused virtual bit available" +#endif + + if (set_memory_np(decoy_addr, 1)) + pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn); + +} +#endif + /* * The actual machine check handler. This only handles real * exceptions when something got corrupted coming in through int 18. @@ -1324,13 +1367,12 @@ static void __start_timer(struct timer_list *t, unsigned long interval) local_irq_restore(flags); } -static void mce_timer_fn(unsigned long data) +static void mce_timer_fn(struct timer_list *t) { - struct timer_list *t = this_cpu_ptr(&mce_timer); - int cpu = smp_processor_id(); + struct timer_list *cpu_t = this_cpu_ptr(&mce_timer); unsigned long iv; - WARN_ON(cpu != data); + WARN_ON(cpu_t != t); iv = __this_cpu_read(mce_next_interval); @@ -1720,17 +1762,15 @@ static void mce_start_timer(struct timer_list *t) static void __mcheck_cpu_setup_timer(void) { struct timer_list *t = this_cpu_ptr(&mce_timer); - unsigned int cpu = smp_processor_id(); - setup_pinned_timer(t, mce_timer_fn, cpu); + timer_setup(t, mce_timer_fn, TIMER_PINNED); } static void __mcheck_cpu_init_timer(void) { struct timer_list *t = this_cpu_ptr(&mce_timer); - unsigned int cpu = smp_processor_id(); - setup_pinned_timer(t, mce_timer_fn, cpu); + timer_setup(t, mce_timer_fn, TIMER_PINNED); mce_start_timer(t); } diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 9e314bcf67cc..486f640b02ef 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -28,6 +28,8 @@ #include <asm/msr.h> #include <asm/trace/irq_vectors.h> +#include "mce-internal.h" + #define NR_BLOCKS 5 #define THRESHOLD_MAX 0xFFF #define INT_TYPE_APIC 0x00020000 @@ -201,8 +203,8 @@ static void smca_configure(unsigned int bank, unsigned int cpu) wrmsr(smca_config, low, high); } - /* Collect bank_info using CPU 0 for now. */ - if (cpu) + /* Return early if this bank was already initialized. */ + if (smca_banks[bank].hwid) return; if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) { @@ -216,11 +218,6 @@ static void smca_configure(unsigned int bank, unsigned int cpu) for (i = 0; i < ARRAY_SIZE(smca_hwid_mcatypes); i++) { s_hwid = &smca_hwid_mcatypes[i]; if (hwid_mcatype == s_hwid->hwid_mcatype) { - - WARN(smca_banks[bank].hwid, - "Bank %s already initialized!\n", - smca_get_name(s_hwid->bank_type)); - smca_banks[bank].hwid = s_hwid; smca_banks[bank].id = low; smca_banks[bank].sysfs_id = s_hwid->count++; @@ -776,24 +773,12 @@ static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc) mce_log(&m); } -static inline void __smp_deferred_error_interrupt(void) -{ - inc_irq_stat(irq_deferred_error_count); - deferred_error_int_vector(); -} - asmlinkage __visible void __irq_entry smp_deferred_error_interrupt(void) { entering_irq(); - __smp_deferred_error_interrupt(); - exiting_ack_irq(); -} - -asmlinkage __visible void __irq_entry smp_trace_deferred_error_interrupt(void) -{ - entering_irq(); trace_deferred_error_apic_entry(DEFERRED_ERROR_VECTOR); - __smp_deferred_error_interrupt(); + inc_irq_stat(irq_deferred_error_count); + deferred_error_int_vector(); trace_deferred_error_apic_exit(DEFERRED_ERROR_VECTOR); exiting_ack_irq(); } diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index e84db79ef272..d05be307d081 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Intel specific MCE features. * Copyright 2004 Zwane Mwaikambo <zwane@linuxpower.ca> diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mcheck/p5.c index 2a0717bf8033..5cddf831720f 100644 --- a/arch/x86/kernel/cpu/mcheck/p5.c +++ b/arch/x86/kernel/cpu/mcheck/p5.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * P5 specific Machine Check Exception Reporting * (C) Copyright 2002 Alan Cox <alan@lxorguk.ukuu.org.uk> diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index d7cc190ae457..2da67b70ba98 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -122,7 +122,7 @@ static struct attribute *thermal_throttle_attrs[] = { NULL }; -static struct attribute_group thermal_attr_group = { +static const struct attribute_group thermal_attr_group = { .attrs = thermal_throttle_attrs, .name = "thermal_throttle" }; @@ -390,26 +390,12 @@ static void unexpected_thermal_interrupt(void) static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt; -static inline void __smp_thermal_interrupt(void) -{ - inc_irq_stat(irq_thermal_count); - smp_thermal_vector(); -} - -asmlinkage __visible void __irq_entry -smp_thermal_interrupt(struct pt_regs *regs) -{ - entering_irq(); - __smp_thermal_interrupt(); - exiting_ack_irq(); -} - -asmlinkage __visible void __irq_entry -smp_trace_thermal_interrupt(struct pt_regs *regs) +asmlinkage __visible void __irq_entry smp_thermal_interrupt(struct pt_regs *r) { entering_irq(); trace_thermal_apic_entry(THERMAL_APIC_VECTOR); - __smp_thermal_interrupt(); + inc_irq_stat(irq_thermal_count); + smp_thermal_vector(); trace_thermal_apic_exit(THERMAL_APIC_VECTOR); exiting_ack_irq(); } diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c b/arch/x86/kernel/cpu/mcheck/threshold.c index bb0e75eed10a..2b584b319eff 100644 --- a/arch/x86/kernel/cpu/mcheck/threshold.c +++ b/arch/x86/kernel/cpu/mcheck/threshold.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Common corrected MCE threshold handler code: */ @@ -17,24 +18,12 @@ static void default_threshold_interrupt(void) void (*mce_threshold_vector)(void) = default_threshold_interrupt; -static inline void __smp_threshold_interrupt(void) -{ - inc_irq_stat(irq_threshold_count); - mce_threshold_vector(); -} - asmlinkage __visible void __irq_entry smp_threshold_interrupt(void) { entering_irq(); - __smp_threshold_interrupt(); - exiting_ack_irq(); -} - -asmlinkage __visible void __irq_entry smp_trace_threshold_interrupt(void) -{ - entering_irq(); trace_threshold_apic_entry(THRESHOLD_APIC_VECTOR); - __smp_threshold_interrupt(); + inc_irq_stat(irq_threshold_count); + mce_threshold_vector(); trace_threshold_apic_exit(THRESHOLD_APIC_VECTOR); exiting_ack_irq(); } diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mcheck/winchip.c index c6a722e1d011..3b45b270a865 100644 --- a/arch/x86/kernel/cpu/mcheck/winchip.c +++ b/arch/x86/kernel/cpu/mcheck/winchip.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * IDT Winchip specific Machine Check Exception Reporting * (C) Copyright 2002 Alan Cox <alan@lxorguk.ukuu.org.uk> diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 21b185793c80..c6daec4bdba5 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -400,9 +400,12 @@ static void update_cache(struct ucode_patch *new_patch) list_for_each_entry(p, µcode_cache, plist) { if (p->equiv_cpu == new_patch->equiv_cpu) { - if (p->patch_id >= new_patch->patch_id) + if (p->patch_id >= new_patch->patch_id) { /* we already have the latest patch */ + kfree(new_patch->data); + kfree(new_patch); return; + } list_replace(&p->plist, &new_patch->plist); kfree(p->data); diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 9cb98ee103db..c4fa4a85d4cb 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -122,9 +122,6 @@ static bool __init check_loader_disabled_bsp(void) bool *res = &dis_ucode_ldr; #endif - if (!have_cpuid_p()) - return *res; - /* * 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 @@ -166,24 +163,36 @@ bool get_builtin_firmware(struct cpio_data *cd, const char *name) void __init load_ucode_bsp(void) { unsigned int cpuid_1_eax; + bool intel = true; - if (check_loader_disabled_bsp()) + if (!have_cpuid_p()) return; cpuid_1_eax = native_cpuid_eax(1); switch (x86_cpuid_vendor()) { case X86_VENDOR_INTEL: - if (x86_family(cpuid_1_eax) >= 6) - load_ucode_intel_bsp(); + if (x86_family(cpuid_1_eax) < 6) + return; break; + case X86_VENDOR_AMD: - if (x86_family(cpuid_1_eax) >= 0x10) - load_ucode_amd_bsp(cpuid_1_eax); + if (x86_family(cpuid_1_eax) < 0x10) + return; + intel = false; break; + default: - break; + return; } + + if (check_loader_disabled_bsp()) + return; + + if (intel) + load_ucode_intel_bsp(); + else + load_ucode_amd_bsp(cpuid_1_eax); } static bool check_loader_disabled_ap(void) @@ -561,7 +570,7 @@ static struct attribute *mc_default_attrs[] = { NULL }; -static struct attribute_group mc_attr_group = { +static const struct attribute_group mc_attr_group = { .attrs = mc_default_attrs, .name = "microcode", }; @@ -707,7 +716,7 @@ static struct attribute *cpu_root_microcode_attrs[] = { NULL }; -static struct attribute_group cpu_root_microcode_group = { +static const struct attribute_group cpu_root_microcode_group = { .name = "microcode", .attrs = cpu_root_microcode_attrs, }; diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 59edbe9d4ccb..7dbcb7adf797 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -34,6 +34,7 @@ #include <linux/mm.h> #include <asm/microcode_intel.h> +#include <asm/intel-family.h> #include <asm/processor.h> #include <asm/tlbflush.h> #include <asm/setup.h> @@ -146,18 +147,18 @@ static bool microcode_matches(struct microcode_header_intel *mc_header, return false; } -static struct ucode_patch *__alloc_microcode_buf(void *data, unsigned int size) +static struct ucode_patch *memdup_patch(void *data, unsigned int size) { struct ucode_patch *p; p = kzalloc(sizeof(struct ucode_patch), GFP_KERNEL); if (!p) - return ERR_PTR(-ENOMEM); + return NULL; p->data = kmemdup(data, size, GFP_KERNEL); if (!p->data) { kfree(p); - return ERR_PTR(-ENOMEM); + return NULL; } return p; @@ -183,8 +184,8 @@ static void save_microcode_patch(void *data, unsigned int size) if (mc_hdr->rev <= mc_saved_hdr->rev) continue; - p = __alloc_microcode_buf(data, size); - if (IS_ERR(p)) + p = memdup_patch(data, size); + if (!p) pr_err("Error allocating buffer %p\n", data); else list_replace(&iter->plist, &p->plist); @@ -196,24 +197,25 @@ static void save_microcode_patch(void *data, unsigned int size) * newly found. */ if (!prev_found) { - p = __alloc_microcode_buf(data, size); - if (IS_ERR(p)) + p = memdup_patch(data, size); + if (!p) pr_err("Error allocating buffer for %p\n", data); else list_add_tail(&p->plist, µcode_cache); } + if (!p) + return; + /* * Save for early loading. On 32-bit, that needs to be a physical * address as the APs are running from physical addresses, before * paging has been enabled. */ - if (p) { - if (IS_ENABLED(CONFIG_X86_32)) - intel_ucode_patch = (struct microcode_intel *)__pa_nodebug(p->data); - else - intel_ucode_patch = p->data; - } + if (IS_ENABLED(CONFIG_X86_32)) + intel_ucode_patch = (struct microcode_intel *)__pa_nodebug(p->data); + else + intel_ucode_patch = p->data; } static int microcode_sanity_check(void *mc, int print_err) @@ -917,6 +919,18 @@ static int get_ucode_fw(void *to, const void *from, size_t n) return 0; } +static bool is_blacklisted(unsigned int cpu) +{ + struct cpuinfo_x86 *c = &cpu_data(cpu); + + if (c->x86 == 6 && c->x86_model == INTEL_FAM6_BROADWELL_X) { + pr_err_once("late loading on model 79 is disabled.\n"); + return true; + } + + return false; +} + static enum ucode_state request_microcode_fw(int cpu, struct device *device, bool refresh_fw) { @@ -925,6 +939,9 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device, const struct firmware *firmware; enum ucode_state ret; + if (is_blacklisted(cpu)) + return UCODE_NFOUND; + sprintf(name, "intel-ucode/%02x-%02x-%02x", c->x86, c->x86_model, c->x86_mask); @@ -949,6 +966,9 @@ static int get_ucode_user(void *to, const void *from, size_t n) static enum ucode_state request_microcode_user(int cpu, const void __user *buf, size_t size) { + if (is_blacklisted(cpu)) + return UCODE_NFOUND; + return generic_load_microcode(cpu, (void *)buf, size, &get_ucode_user); } diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh index 6988c74409a8..d0dfb892c72f 100644 --- a/arch/x86/kernel/cpu/mkcapflags.sh +++ b/arch/x86/kernel/cpu/mkcapflags.sh @@ -1,4 +1,5 @@ #!/bin/sh +# SPDX-License-Identifier: GPL-2.0 # # Generate the x86_cap/bug_flags[] arrays from include/asm/cpufeatures.h # diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 70e717fccdd6..85eb5fc180c8 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -59,13 +59,6 @@ void hyperv_vector_handler(struct pt_regs *regs) void hv_setup_vmbus_irq(void (*handler)(void)) { vmbus_handler = handler; - /* - * Setup the IDT for hypervisor callback. Prevent reallocation - * at module reload. - */ - if (!test_bit(HYPERVISOR_CALLBACK_VECTOR, used_vectors)) - alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, - hyperv_callback_vector); } void hv_remove_vmbus_irq(void) @@ -184,9 +177,15 @@ static void __init ms_hyperv_init_platform(void) ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES); ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO); - pr_info("HyperV: features 0x%x, hints 0x%x\n", + pr_info("Hyper-V: features 0x%x, hints 0x%x\n", ms_hyperv.features, ms_hyperv.hints); + ms_hyperv.max_vp_index = cpuid_eax(HVCPUID_IMPLEMENTATION_LIMITS); + ms_hyperv.max_lp_index = cpuid_ebx(HVCPUID_IMPLEMENTATION_LIMITS); + + pr_debug("Hyper-V: max %u virtual processors, %u logical processors\n", + ms_hyperv.max_vp_index, ms_hyperv.max_lp_index); + /* * Extract host information. */ @@ -219,7 +218,7 @@ static void __init ms_hyperv_init_platform(void) rdmsrl(HV_X64_MSR_APIC_FREQUENCY, hv_lapic_frequency); hv_lapic_frequency = div_u64(hv_lapic_frequency, HZ); lapic_timer_frequency = hv_lapic_frequency; - pr_info("HyperV: LAPIC Timer Frequency: %#x\n", + pr_info("Hyper-V: LAPIC Timer Frequency: %#x\n", lapic_timer_frequency); } @@ -249,12 +248,15 @@ static void __init ms_hyperv_init_platform(void) * Setup the hook to get control post apic initialization. */ x86_platform.apic_post_init = hyperv_init; + hyperv_setup_mmu_ops(); + /* Setup the IDT for hypervisor callback */ + alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector); #endif } -const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { - .name = "Microsoft HyperV", +const __initconst struct hypervisor_x86 x86_hyper_ms_hyperv = { + .name = "Microsoft Hyper-V", .detect = ms_hyperv_platform, - .init_platform = ms_hyperv_init_platform, + .type = X86_HYPER_MS_HYPERV, + .init.init_platform = ms_hyperv_init_platform, }; -EXPORT_SYMBOL(x86_hyper_ms_hyperv); diff --git a/arch/x86/kernel/cpu/mtrr/amd.c b/arch/x86/kernel/cpu/mtrr/amd.c index 92ba9cd31c9a..a65a0272096d 100644 --- a/arch/x86/kernel/cpu/mtrr/amd.c +++ b/arch/x86/kernel/cpu/mtrr/amd.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/init.h> #include <linux/mm.h> #include <asm/mtrr.h> diff --git a/arch/x86/kernel/cpu/mtrr/centaur.c b/arch/x86/kernel/cpu/mtrr/centaur.c index 3d689937fc1b..f27177816569 100644 --- a/arch/x86/kernel/cpu/mtrr/centaur.c +++ b/arch/x86/kernel/cpu/mtrr/centaur.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/init.h> #include <linux/mm.h> diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c index b1086f79e57e..4296c702a3f7 100644 --- a/arch/x86/kernel/cpu/mtrr/cyrix.c +++ b/arch/x86/kernel/cpu/mtrr/cyrix.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/init.h> #include <linux/io.h> #include <linux/mm.h> diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c index 6d9b45549109..558444b23923 100644 --- a/arch/x86/kernel/cpu/mtrr/if.c +++ b/arch/x86/kernel/cpu/mtrr/if.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/capability.h> #include <linux/seq_file.h> #include <linux/uaccess.h> diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index c5bb63be4ba1..40d5a8a75212 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -237,6 +237,18 @@ set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type typ stop_machine(mtrr_rendezvous_handler, &data, cpu_online_mask); } +static void set_mtrr_cpuslocked(unsigned int reg, unsigned long base, + unsigned long size, mtrr_type type) +{ + struct set_mtrr_data data = { .smp_reg = reg, + .smp_base = base, + .smp_size = size, + .smp_type = type + }; + + stop_machine_cpuslocked(mtrr_rendezvous_handler, &data, cpu_online_mask); +} + static void set_mtrr_from_inactive_cpu(unsigned int reg, unsigned long base, unsigned long size, mtrr_type type) { @@ -370,7 +382,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, /* Search for an empty MTRR */ i = mtrr_if->get_free_region(base, size, replace); if (i >= 0) { - set_mtrr(i, base, size, type); + set_mtrr_cpuslocked(i, base, size, type); if (likely(replace < 0)) { mtrr_usage_table[i] = 1; } else { @@ -378,7 +390,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, if (increment) mtrr_usage_table[i]++; if (unlikely(replace != i)) { - set_mtrr(replace, 0, 0, 0); + set_mtrr_cpuslocked(replace, 0, 0, 0); mtrr_usage_table[replace] = 0; } } @@ -506,7 +518,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) goto out; } if (--mtrr_usage_table[reg] < 1) - set_mtrr(reg, 0, 0, 0); + set_mtrr_cpuslocked(reg, 0, 0, 0); error = reg; out: mutex_unlock(&mtrr_mutex); diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h index ad8bd763efa5..2ac99e561181 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.h +++ b/arch/x86/kernel/cpu/mtrr/mtrr.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * local MTRR defines. */ diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index 181eabecae25..d389083330c5 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * local apic based NMI watchdog for various CPUs. * diff --git a/arch/x86/kernel/cpu/powerflags.c b/arch/x86/kernel/cpu/powerflags.c index 1dd8294fd730..fd6ec2aa0303 100644 --- a/arch/x86/kernel/cpu/powerflags.c +++ b/arch/x86/kernel/cpu/powerflags.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Strings for the various x86 power flags * diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 218f79825b3c..e7ecedafa1c8 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -1,7 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/smp.h> #include <linux/timex.h> #include <linux/string.h> #include <linux/seq_file.h> +#include <linux/cpufreq.h> + +#include "cpu.h" /* * Get CPU information for use by the procfs. @@ -75,9 +79,16 @@ static int show_cpuinfo(struct seq_file *m, void *v) if (c->microcode) seq_printf(m, "microcode\t: 0x%x\n", c->microcode); - if (cpu_has(c, X86_FEATURE_TSC)) + if (cpu_has(c, X86_FEATURE_TSC)) { + unsigned int freq = aperfmperf_get_khz(cpu); + + if (!freq) + freq = cpufreq_quick_get(cpu); + if (!freq) + freq = cpu_khz; seq_printf(m, "cpu MHz\t\t: %u.%03u\n", - cpu_khz / 1000, (cpu_khz % 1000)); + freq / 1000, (freq % 1000)); + } /* Cache size */ if (c->x86_cache_size >= 0) diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 23c23508c012..05459ad3db46 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -31,6 +31,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_HW_PSTATE, CPUID_EDX, 7, 0x80000007, 0 }, { X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 }, { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 }, + { X86_FEATURE_SME, CPUID_EAX, 0, 0x8000001f, 0 }, { 0, 0, 0, 0, 0 } }; diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index cd531355e838..b099024d339c 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Check for extended topology enumeration cpuid leaf 0xb and if it * exists, use it for populating initial_apicid and cpu topology diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c index d77d07ab310b..42c939827621 100644 --- a/arch/x86/kernel/cpu/transmeta.c +++ b/arch/x86/kernel/cpu/transmeta.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/sched.h> #include <linux/sched/clock.h> diff --git a/arch/x86/kernel/cpu/umc.c b/arch/x86/kernel/cpu/umc.c index ef9c2a0078bd..65a58a390fc3 100644 --- a/arch/x86/kernel/cpu/umc.c +++ b/arch/x86/kernel/cpu/umc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <asm/processor.h> #include "cpu.h" diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 40ed26852ebd..8e005329648b 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -205,10 +205,10 @@ static bool __init vmware_legacy_x2apic_available(void) (eax & (1 << VMWARE_PORT_CMD_LEGACY_X2APIC)) != 0; } -const __refconst struct hypervisor_x86 x86_hyper_vmware = { +const __initconst struct hypervisor_x86 x86_hyper_vmware = { .name = "VMware", .detect = vmware_platform, - .init_platform = vmware_platform_setup, - .x2apic_available = vmware_legacy_x2apic_available, + .type = X86_HYPER_VMWARE, + .init.init_platform = vmware_platform_setup, + .init.x2apic_available = vmware_legacy_x2apic_available, }; -EXPORT_SYMBOL(x86_hyper_vmware); diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 44404e2307bb..10e74d4778a1 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -209,7 +209,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs) } #ifdef CONFIG_KEXEC_FILE -static int get_nr_ram_ranges_callback(u64 start, u64 end, void *arg) +static int get_nr_ram_ranges_callback(struct resource *res, void *arg) { unsigned int *nr_ranges = arg; @@ -342,7 +342,7 @@ static int elf_header_exclude_ranges(struct crash_elf_data *ced, return ret; } -static int prepare_elf64_ram_headers_callback(u64 start, u64 end, void *arg) +static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg) { struct crash_elf_data *ced = arg; Elf64_Ehdr *ehdr; @@ -355,7 +355,7 @@ static int prepare_elf64_ram_headers_callback(u64 start, u64 end, void *arg) ehdr = ced->ehdr; /* Exclude unwanted mem ranges */ - ret = elf_header_exclude_ranges(ced, start, end); + ret = elf_header_exclude_ranges(ced, res->start, res->end); if (ret) return ret; @@ -518,14 +518,14 @@ static int add_e820_entry(struct boot_params *params, struct e820_entry *entry) return 0; } -static int memmap_entry_callback(u64 start, u64 end, void *arg) +static int memmap_entry_callback(struct resource *res, void *arg) { struct crash_memmap_data *cmd = arg; struct boot_params *params = cmd->params; struct e820_entry ei; - ei.addr = start; - ei.size = end - start + 1; + ei.addr = res->start; + ei.size = resource_size(res); ei.type = cmd->type; add_e820_entry(params, &ei); @@ -619,12 +619,12 @@ out: return ret; } -static int determine_backup_region(u64 start, u64 end, void *arg) +static int determine_backup_region(struct resource *res, void *arg) { struct kimage *image = arg; - image->arch.backup_src_start = start; - image->arch.backup_src_sz = end - start + 1; + image->arch.backup_src_start = res->start; + image->arch.backup_src_sz = resource_size(res); /* Expecting only one range for backup region */ return 1; diff --git a/arch/x86/kernel/crash_dump_32.c b/arch/x86/kernel/crash_dump_32.c index 538fedea9b3f..33ee47670b99 100644 --- a/arch/x86/kernel/crash_dump_32.c +++ b/arch/x86/kernel/crash_dump_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Memory preserving reboot related code. * diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c index afa64adb75ee..4f2e0778feac 100644 --- a/arch/x86/kernel/crash_dump_64.c +++ b/arch/x86/kernel/crash_dump_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Memory preserving reboot related code. * diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index cbf1f6ba39a8..76e07698e6d1 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Architecture specific OF callbacks. */ diff --git a/arch/x86/kernel/doublefault.c b/arch/x86/kernel/doublefault.c index f9c324e08d85..0e662c55ae90 100644 --- a/arch/x86/kernel/doublefault.c +++ b/arch/x86/kernel/doublefault.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/mm.h> #include <linux/sched.h> #include <linux/sched/debug.h> diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index dbce3cca94cb..f13b4c00a5de 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -94,6 +94,9 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, if (stack_name) printk("%s <%s>\n", log_lvl, stack_name); + if (regs && on_stack(&stack_info, regs, sizeof(*regs))) + __show_regs(regs, 0); + /* * Scan the stack, printing any text addresses we find. At the * same time, follow proper stack frames with the unwinder. @@ -118,10 +121,8 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, * Don't print regs->ip again if it was already printed * by __show_regs() below. */ - if (regs && stack == ®s->ip) { - unwind_next_frame(&state); - continue; - } + if (regs && stack == ®s->ip) + goto next; if (stack == ret_addr_p) reliable = 1; @@ -144,6 +145,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, if (!reliable) continue; +next: /* * Get the next frame from the unwinder. No need to * check for an error: if anything goes wrong, the rest @@ -153,7 +155,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, /* if the frame has entry regs, print them */ regs = unwind_get_entry_regs(&state); - if (regs) + if (regs && on_stack(&stack_info, regs, sizeof(*regs))) __show_regs(regs, 0); } @@ -265,7 +267,7 @@ int __die(const char *str, struct pt_regs *regs, long err) #ifdef CONFIG_X86_32 if (user_mode(regs)) { sp = regs->sp; - ss = regs->ss & 0xffff; + ss = regs->ss; } else { sp = kernel_stack_pointer(regs); savesegment(ss, ss); diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index e5f0b40e66d2..daefae83a3aa 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs @@ -37,7 +38,7 @@ static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info) * This is a software stack, so 'end' can be a valid stack pointer. * It just means the stack is empty. */ - if (stack < begin || stack > end) + if (stack <= begin || stack > end) return false; info->type = STACK_TYPE_IRQ; @@ -62,7 +63,7 @@ static bool in_softirq_stack(unsigned long *stack, struct stack_info *info) * This is a software stack, so 'end' can be a valid stack pointer. * It just means the stack is empty. */ - if (stack < begin || stack > end) + if (stack <= begin || stack > end) return false; info->type = STACK_TYPE_SOFTIRQ; diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 3e1471d57487..88ce2ffdb110 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs @@ -55,7 +56,7 @@ static bool in_exception_stack(unsigned long *stack, struct stack_info *info) begin = end - (exception_stack_sizes[k] / sizeof(long)); regs = (struct pt_regs *)end - 1; - if (stack < begin || stack >= end) + if (stack <= begin || stack >= end) continue; info->type = STACK_TYPE_EXCEPTION + k; @@ -78,7 +79,7 @@ static bool in_irq_stack(unsigned long *stack, struct stack_info *info) * This is a software stack, so 'end' can be a valid stack pointer. * It just means the stack is empty. */ - if (stack < begin || stack > end) + if (stack <= begin || stack > end) return false; info->type = STACK_TYPE_IRQ; diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 532da61d605c..71c11ad5643e 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -96,7 +96,8 @@ EXPORT_SYMBOL_GPL(e820__mapped_any); * Note: this function only works correctly once the E820 table is sorted and * not-overlapping (at least for the range specified), which is the case normally. */ -bool __init e820__mapped_all(u64 start, u64 end, enum e820_type type) +static struct e820_entry *__e820__mapped_all(u64 start, u64 end, + enum e820_type type) { int i; @@ -122,9 +123,28 @@ bool __init e820__mapped_all(u64 start, u64 end, enum e820_type type) * coverage of the desired range exists: */ if (start >= end) - return 1; + return entry; } - return 0; + + return NULL; +} + +/* + * This function checks if the entire range <start,end> is mapped with type. + */ +bool __init e820__mapped_all(u64 start, u64 end, enum e820_type type) +{ + return __e820__mapped_all(start, end, type); +} + +/* + * This function returns the type associated with the range <start,end>. + */ +int e820__get_entry_type(u64 start, u64 end) +{ + struct e820_entry *entry = __e820__mapped_all(start, end, 0); + + return entry ? entry->type : -EINVAL; } /* diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index d907c3d8633f..1e82f787c160 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* Various workarounds for chipset bugs. This code runs very early and can't use the regular PCI subsystem The entries are keyed to PCI bridges which usually identify chipsets @@ -12,10 +13,10 @@ #include <linux/pci.h> #include <linux/acpi.h> #include <linux/delay.h> -#include <linux/dmi.h> #include <linux/pci_ids.h> #include <linux/bcma/bcma.h> #include <linux/bcma/bcma_regs.h> +#include <linux/platform_data/x86/apple.h> #include <drm/i915_drm.h> #include <asm/pci-direct.h> #include <asm/dma.h> @@ -527,6 +528,7 @@ static const struct pci_device_id intel_early_ids[] __initconst = { INTEL_BXT_IDS(&gen9_early_ops), INTEL_KBL_IDS(&gen9_early_ops), INTEL_GLK_IDS(&gen9_early_ops), + INTEL_CNL_IDS(&gen9_early_ops), }; static void __init @@ -593,7 +595,7 @@ static void __init apple_airport_reset(int bus, int slot, int func) u64 addr; int i; - if (!dmi_match(DMI_SYS_VENDOR, "Apple Inc.")) + if (!x86_apple_machine) return; /* Card may have been put into PCI_D3hot by grub quirk */ diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index 0f0840304452..5e801c8c8ce7 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/console.h> #include <linux/kernel.h> #include <linux/init.h> diff --git a/arch/x86/kernel/ebda.c b/arch/x86/kernel/ebda.c index 4312f8ae71b7..38e7d597b660 100644 --- a/arch/x86/kernel/ebda.c +++ b/arch/x86/kernel/ebda.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/init.h> #include <linux/memblock.h> diff --git a/arch/x86/kernel/eisa.c b/arch/x86/kernel/eisa.c new file mode 100644 index 000000000000..f260e452e4f8 --- /dev/null +++ b/arch/x86/kernel/eisa.c @@ -0,0 +1,19 @@ +/* + * EISA specific code + * + * This file is licensed under the GPL V2 + */ +#include <linux/ioport.h> +#include <linux/eisa.h> +#include <linux/io.h> + +static __init int eisa_bus_probe(void) +{ + void __iomem *p = ioremap(0x0FFFD9, 4); + + if (readl(p) == 'E' + ('I'<<8) + ('S'<<16) + ('A'<<24)) + EISA_bus = 1; + iounmap(p); + return 0; +} +subsys_initcall(eisa_bus_probe); diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 6b91e2eb8d3f..e5ec3cafa72e 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -57,7 +57,7 @@ # error "Need more virtual address space for the ESPFIX hack" #endif -#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO) +#define PGALLOC_GFP (GFP_KERNEL | __GFP_ZERO) /* This contains the *bottom* address of the espfix stack */ DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack); @@ -155,14 +155,14 @@ void init_espfix_ap(int cpu) page = cpu/ESPFIX_STACKS_PER_PAGE; /* Did another CPU already set this up? */ - stack_page = ACCESS_ONCE(espfix_pages[page]); + stack_page = READ_ONCE(espfix_pages[page]); if (likely(stack_page)) goto done; mutex_lock(&espfix_init_mutex); /* Did we race on the lock? */ - stack_page = ACCESS_ONCE(espfix_pages[page]); + stack_page = READ_ONCE(espfix_pages[page]); if (stack_page) goto unlock_done; @@ -195,12 +195,12 @@ void init_espfix_ap(int cpu) pte_p = pte_offset_kernel(&pmd, addr); stack_page = page_address(alloc_pages_node(node, GFP_KERNEL, 0)); - pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask)); + pte = __pte(__pa(stack_page) | ((__PAGE_KERNEL_RO | _PAGE_ENC) & ptemask)); for (n = 0; n < ESPFIX_PTE_CLONES; n++) set_pte(&pte_p[n*PTE_STRIDE], pte); /* Job is done for this CPU and any CPU which shares this page */ - ACCESS_ONCE(espfix_pages[page]) = stack_page; + WRITE_ONCE(espfix_pages[page], stack_page); unlock_done: mutex_unlock(&espfix_init_mutex); diff --git a/arch/x86/kernel/fpu/bugs.c b/arch/x86/kernel/fpu/bugs.c index d913047f832c..2954fab15e51 100644 --- a/arch/x86/kernel/fpu/bugs.c +++ b/arch/x86/kernel/fpu/bugs.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * x86 FPU bug checks: */ diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index e1114f070c2d..f92a6593de1e 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -100,7 +100,7 @@ void __kernel_fpu_begin(void) kernel_fpu_disable(); - if (fpu->fpregs_active) { + if (fpu->initialized) { /* * Ignore return value -- we don't care if reg state * is clobbered. @@ -116,7 +116,7 @@ void __kernel_fpu_end(void) { struct fpu *fpu = ¤t->thread.fpu; - if (fpu->fpregs_active) + if (fpu->initialized) copy_kernel_to_fpregs(&fpu->state); kernel_fpu_enable(); @@ -148,7 +148,7 @@ void fpu__save(struct fpu *fpu) preempt_disable(); trace_x86_fpu_before_save(fpu); - if (fpu->fpregs_active) { + if (fpu->initialized) { if (!copy_fpregs_to_fpstate(fpu)) { copy_kernel_to_fpregs(&fpu->state); } @@ -189,10 +189,9 @@ EXPORT_SYMBOL_GPL(fpstate_init); int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) { - dst_fpu->fpregs_active = 0; dst_fpu->last_cpu = -1; - if (!src_fpu->fpstate_active || !static_cpu_has(X86_FEATURE_FPU)) + if (!src_fpu->initialized || !static_cpu_has(X86_FEATURE_FPU)) return 0; WARN_ON_FPU(src_fpu != ¤t->thread.fpu); @@ -206,26 +205,14 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) /* * Save current FPU registers directly into the child * FPU context, without any memory-to-memory copying. - * In lazy mode, if the FPU context isn't loaded into - * fpregs, CR0.TS will be set and do_device_not_available - * will load the FPU context. * - * We have to do all this with preemption disabled, - * mostly because of the FNSAVE case, because in that - * case we must not allow preemption in the window - * between the FNSAVE and us marking the context lazy. - * - * It shouldn't be an issue as even FNSAVE is plenty - * fast in terms of critical section length. + * ( The function 'fails' in the FNSAVE case, which destroys + * register contents so we have to copy them back. ) */ - preempt_disable(); if (!copy_fpregs_to_fpstate(dst_fpu)) { - memcpy(&src_fpu->state, &dst_fpu->state, - fpu_kernel_xstate_size); - + memcpy(&src_fpu->state, &dst_fpu->state, fpu_kernel_xstate_size); copy_kernel_to_fpregs(&src_fpu->state); } - preempt_enable(); trace_x86_fpu_copy_src(src_fpu); trace_x86_fpu_copy_dst(dst_fpu); @@ -237,45 +224,48 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) * Activate the current task's in-memory FPU context, * if it has not been used before: */ -void fpu__activate_curr(struct fpu *fpu) +void fpu__initialize(struct fpu *fpu) { WARN_ON_FPU(fpu != ¤t->thread.fpu); - if (!fpu->fpstate_active) { + if (!fpu->initialized) { fpstate_init(&fpu->state); trace_x86_fpu_init_state(fpu); trace_x86_fpu_activate_state(fpu); /* Safe to do for the current task: */ - fpu->fpstate_active = 1; + fpu->initialized = 1; } } -EXPORT_SYMBOL_GPL(fpu__activate_curr); +EXPORT_SYMBOL_GPL(fpu__initialize); /* * This function must be called before we read a task's fpstate. * - * If the task has not used the FPU before then initialize its - * fpstate. + * There's two cases where this gets called: + * + * - for the current task (when coredumping), in which case we have + * to save the latest FPU registers into the fpstate, + * + * - or it's called for stopped tasks (ptrace), in which case the + * registers were already saved by the context-switch code when + * the task scheduled out - we only have to initialize the registers + * if they've never been initialized. * * If the task has used the FPU before then save it. */ -void fpu__activate_fpstate_read(struct fpu *fpu) +void fpu__prepare_read(struct fpu *fpu) { - /* - * If fpregs are active (in the current CPU), then - * copy them to the fpstate: - */ - if (fpu->fpregs_active) { + if (fpu == ¤t->thread.fpu) { fpu__save(fpu); } else { - if (!fpu->fpstate_active) { + if (!fpu->initialized) { fpstate_init(&fpu->state); trace_x86_fpu_init_state(fpu); trace_x86_fpu_activate_state(fpu); /* Safe to do for current and for stopped child tasks: */ - fpu->fpstate_active = 1; + fpu->initialized = 1; } } } @@ -283,17 +273,17 @@ void fpu__activate_fpstate_read(struct fpu *fpu) /* * This function must be called before we write a task's fpstate. * - * If the task has used the FPU before then unlazy it. + * If the task has used the FPU before then invalidate any cached FPU registers. * If the task has not used the FPU before then initialize its fpstate. * * After this function call, after registers in the fpstate are * modified and the child task has woken up, the child task will * restore the modified FPU state from the modified context. If we - * didn't clear its lazy status here then the lazy in-registers + * didn't clear its cached status here then the cached in-registers * state pending on its former CPU could be restored, corrupting * the modifications. */ -void fpu__activate_fpstate_write(struct fpu *fpu) +void fpu__prepare_write(struct fpu *fpu) { /* * Only stopped child tasks can be used to modify the FPU @@ -301,8 +291,8 @@ void fpu__activate_fpstate_write(struct fpu *fpu) */ WARN_ON_FPU(fpu == ¤t->thread.fpu); - if (fpu->fpstate_active) { - /* Invalidate any lazy state: */ + if (fpu->initialized) { + /* Invalidate any cached state: */ __fpu_invalidate_fpregs_state(fpu); } else { fpstate_init(&fpu->state); @@ -310,74 +300,11 @@ void fpu__activate_fpstate_write(struct fpu *fpu) trace_x86_fpu_activate_state(fpu); /* Safe to do for stopped child tasks: */ - fpu->fpstate_active = 1; + fpu->initialized = 1; } } /* - * This function must be called before we write the current - * task's fpstate. - * - * This call gets the current FPU register state and moves - * it in to the 'fpstate'. Preemption is disabled so that - * no writes to the 'fpstate' can occur from context - * swiches. - * - * Must be followed by a fpu__current_fpstate_write_end(). - */ -void fpu__current_fpstate_write_begin(void) -{ - struct fpu *fpu = ¤t->thread.fpu; - - /* - * Ensure that the context-switching code does not write - * over the fpstate while we are doing our update. - */ - preempt_disable(); - - /* - * Move the fpregs in to the fpu's 'fpstate'. - */ - fpu__activate_fpstate_read(fpu); - - /* - * The caller is about to write to 'fpu'. Ensure that no - * CPU thinks that its fpregs match the fpstate. This - * ensures we will not be lazy and skip a XRSTOR in the - * future. - */ - __fpu_invalidate_fpregs_state(fpu); -} - -/* - * This function must be paired with fpu__current_fpstate_write_begin() - * - * This will ensure that the modified fpstate gets placed back in - * the fpregs if necessary. - * - * Note: This function may be called whether or not an _actual_ - * write to the fpstate occurred. - */ -void fpu__current_fpstate_write_end(void) -{ - struct fpu *fpu = ¤t->thread.fpu; - - /* - * 'fpu' now has an updated copy of the state, but the - * registers may still be out of date. Update them with - * an XRSTOR if they are active. - */ - if (fpregs_active()) - copy_kernel_to_fpregs(&fpu->state); - - /* - * Our update is done and the fpregs/fpstate are in sync - * if necessary. Context switches can happen again. - */ - preempt_enable(); -} - -/* * 'fpu__restore()' is called to copy FPU registers from * the FPU fpstate to the live hw registers and to activate * access to the hardware registers, so that FPU instructions @@ -389,7 +316,7 @@ void fpu__current_fpstate_write_end(void) */ void fpu__restore(struct fpu *fpu) { - fpu__activate_curr(fpu); + fpu__initialize(fpu); /* Avoid __kernel_fpu_begin() right after fpregs_activate() */ kernel_fpu_disable(); @@ -414,15 +341,17 @@ void fpu__drop(struct fpu *fpu) { preempt_disable(); - if (fpu->fpregs_active) { - /* Ignore delayed exceptions from user space */ - asm volatile("1: fwait\n" - "2:\n" - _ASM_EXTABLE(1b, 2b)); - fpregs_deactivate(fpu); + if (fpu == ¤t->thread.fpu) { + if (fpu->initialized) { + /* Ignore delayed exceptions from user space */ + asm volatile("1: fwait\n" + "2:\n" + _ASM_EXTABLE(1b, 2b)); + fpregs_deactivate(fpu); + } } - fpu->fpstate_active = 0; + fpu->initialized = 0; trace_x86_fpu_dropped(fpu); @@ -462,9 +391,11 @@ void fpu__clear(struct fpu *fpu) * Make sure fpstate is cleared and initialized. */ if (static_cpu_has(X86_FEATURE_FPU)) { - fpu__activate_curr(fpu); + preempt_disable(); + fpu__initialize(fpu); user_fpu_begin(); copy_init_fpstate_to_fpregs(); + preempt_enable(); } } diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index d5d44c452624..6abd83572b01 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -240,7 +240,7 @@ static void __init fpu__init_system_ctx_switch(void) WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; - WARN_ON_FPU(current->thread.fpu.fpstate_active); + WARN_ON_FPU(current->thread.fpu.initialized); } /* @@ -249,6 +249,10 @@ static void __init fpu__init_system_ctx_switch(void) */ static void __init fpu__init_parse_early_param(void) { + char arg[32]; + char *argptr = arg; + int bit; + if (cmdline_find_option_bool(boot_command_line, "no387")) setup_clear_cpu_cap(X86_FEATURE_FPU); @@ -266,6 +270,13 @@ static void __init fpu__init_parse_early_param(void) if (cmdline_find_option_bool(boot_command_line, "noxsaves")) setup_clear_cpu_cap(X86_FEATURE_XSAVES); + + if (cmdline_find_option(boot_command_line, "clearcpuid", arg, + sizeof(arg)) && + get_option(&argptr, &bit) && + bit >= 0 && + bit < NCAPINTS * 32) + setup_clear_cpu_cap(bit); } /* diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index b188b16841e3..bc02f5144b95 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * FPU register's regset abstraction, for ptrace, core dumps, etc. */ @@ -16,14 +17,14 @@ int regset_fpregs_active(struct task_struct *target, const struct user_regset *r { struct fpu *target_fpu = &target->thread.fpu; - return target_fpu->fpstate_active ? regset->n : 0; + return target_fpu->initialized ? regset->n : 0; } int regset_xregset_fpregs_active(struct task_struct *target, const struct user_regset *regset) { struct fpu *target_fpu = &target->thread.fpu; - if (boot_cpu_has(X86_FEATURE_FXSR) && target_fpu->fpstate_active) + if (boot_cpu_has(X86_FEATURE_FXSR) && target_fpu->initialized) return regset->n; else return 0; @@ -38,7 +39,7 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset, if (!boot_cpu_has(X86_FEATURE_FXSR)) return -ENODEV; - fpu__activate_fpstate_read(fpu); + fpu__prepare_read(fpu); fpstate_sanitize_xstate(fpu); return user_regset_copyout(&pos, &count, &kbuf, &ubuf, @@ -55,7 +56,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, if (!boot_cpu_has(X86_FEATURE_FXSR)) return -ENODEV; - fpu__activate_fpstate_write(fpu); + fpu__prepare_write(fpu); fpstate_sanitize_xstate(fpu); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, @@ -89,10 +90,13 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, xsave = &fpu->state.xsave; - fpu__activate_fpstate_read(fpu); + fpu__prepare_read(fpu); if (using_compacted_format()) { - ret = copyout_from_xsaves(pos, count, kbuf, ubuf, xsave); + if (kbuf) + ret = copy_xstate_to_kernel(kbuf, xsave, pos, count); + else + ret = copy_xstate_to_user(ubuf, xsave, pos, count); } else { fpstate_sanitize_xstate(fpu); /* @@ -129,28 +133,29 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, xsave = &fpu->state.xsave; - fpu__activate_fpstate_write(fpu); + fpu__prepare_write(fpu); - if (boot_cpu_has(X86_FEATURE_XSAVES)) - ret = copyin_to_xsaves(kbuf, ubuf, xsave); - else + if (using_compacted_format()) { + if (kbuf) + ret = copy_kernel_to_xstate(xsave, kbuf); + else + ret = copy_user_to_xstate(xsave, ubuf); + } else { ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); - - /* - * In case of failure, mark all states as init: - */ - if (ret) - fpstate_init(&fpu->state); + if (!ret) + ret = validate_xstate_header(&xsave->header); + } /* * mxcsr reserved bits must be masked to zero for security reasons. */ xsave->i387.mxcsr &= mxcsr_feature_mask; - xsave->header.xfeatures &= xfeatures_mask; + /* - * These bits must be zero. + * In case of failure, mark all states as init: */ - memset(&xsave->header.reserved, 0, 48); + if (ret) + fpstate_init(&fpu->state); return ret; } @@ -299,7 +304,7 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset, struct fpu *fpu = &target->thread.fpu; struct user_i387_ia32_struct env; - fpu__activate_fpstate_read(fpu); + fpu__prepare_read(fpu); if (!boot_cpu_has(X86_FEATURE_FPU)) return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); @@ -329,7 +334,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, struct user_i387_ia32_struct env; int ret; - fpu__activate_fpstate_write(fpu); + fpu__prepare_write(fpu); fpstate_sanitize_xstate(fpu); if (!boot_cpu_has(X86_FEATURE_FPU)) @@ -369,7 +374,7 @@ int dump_fpu(struct pt_regs *regs, struct user_i387_struct *ufpu) struct fpu *fpu = &tsk->thread.fpu; int fpvalid; - fpvalid = fpu->fpstate_active; + fpvalid = fpu->initialized; if (fpvalid) fpvalid = !fpregs_get(tsk, NULL, 0, sizeof(struct user_i387_ia32_struct), diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 83c23c230b4c..23f1691670b6 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * FPU signal frame handling routines. */ @@ -155,7 +156,8 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf) */ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) { - struct xregs_state *xsave = ¤t->thread.fpu.state.xsave; + struct fpu *fpu = ¤t->thread.fpu; + struct xregs_state *xsave = &fpu->state.xsave; struct task_struct *tsk = current; int ia32_fxstate = (buf != buf_fx); @@ -170,13 +172,13 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) sizeof(struct user_i387_ia32_struct), NULL, (struct _fpstate_32 __user *) buf) ? -1 : 1; - if (fpregs_active() || using_compacted_format()) { + if (fpu->initialized || using_compacted_format()) { /* Save the live register state to the user directly. */ if (copy_fpregs_to_sigframe(buf_fx)) return -1; /* Update the thread's fxstate to save the fsave header. */ if (ia32_fxstate) - copy_fxregs_to_kernel(&tsk->thread.fpu); + copy_fxregs_to_kernel(fpu); } else { /* * It is a *bug* if kernel uses compacted-format for xsave @@ -189,7 +191,7 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) return -1; } - fpstate_sanitize_xstate(&tsk->thread.fpu); + fpstate_sanitize_xstate(fpu); if (__copy_to_user(buf_fx, xsave, fpu_user_xstate_size)) return -1; } @@ -213,8 +215,11 @@ sanitize_restored_xstate(struct task_struct *tsk, struct xstate_header *header = &xsave->header; if (use_xsave()) { - /* These bits must be zero. */ - memset(header->reserved, 0, 48); + /* + * Note: we don't need to zero the reserved bits in the + * xstate_header here because we either didn't copy them at all, + * or we checked earlier that they aren't set. + */ /* * Init the state that is not present in the memory @@ -223,7 +228,7 @@ sanitize_restored_xstate(struct task_struct *tsk, if (fx_only) header->xfeatures = XFEATURE_MASK_FPSSE; else - header->xfeatures &= (xfeatures_mask & xfeatures); + header->xfeatures &= xfeatures; } if (use_fxsr()) { @@ -279,7 +284,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) if (!access_ok(VERIFY_READ, buf, size)) return -EACCES; - fpu__activate_curr(fpu); + fpu__initialize(fpu); if (!static_cpu_has(X86_FEATURE_FPU)) return fpregs_soft_set(current, NULL, @@ -307,28 +312,29 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) /* * For 32-bit frames with fxstate, copy the user state to the * thread's fpu state, reconstruct fxstate from the fsave - * header. Sanitize the copied state etc. + * header. Validate and sanitize the copied state. */ struct fpu *fpu = &tsk->thread.fpu; struct user_i387_ia32_struct env; int err = 0; /* - * Drop the current fpu which clears fpu->fpstate_active. This ensures + * Drop the current fpu which clears fpu->initialized. This ensures * that any context-switch during the copy of the new state, * avoids the intermediate state from getting restored/saved. * Thus avoiding the new restored state from getting corrupted. * We will be ready to restore/save the state only after - * fpu->fpstate_active is again set. + * fpu->initialized is again set. */ fpu__drop(fpu); if (using_compacted_format()) { - err = copyin_to_xsaves(NULL, buf_fx, - &fpu->state.xsave); + err = copy_user_to_xstate(&fpu->state.xsave, buf_fx); } else { - err = __copy_from_user(&fpu->state.xsave, - buf_fx, state_size); + err = __copy_from_user(&fpu->state.xsave, buf_fx, state_size); + + if (!err && state_size > offsetof(struct xregs_state, header)) + err = validate_xstate_header(&fpu->state.xsave.header); } if (err || __copy_from_user(&env, buf, sizeof(env))) { @@ -339,7 +345,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) sanitize_restored_xstate(tsk, &env, xfeatures, fx_only); } - fpu->fpstate_active = 1; + fpu->initialized = 1; preempt_disable(); fpu__restore(fpu); preempt_enable(); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index c24ac1efb12d..87a57b7642d3 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -15,6 +15,7 @@ #include <asm/fpu/xstate.h> #include <asm/tlbflush.h> +#include <asm/cpufeature.h> /* * Although we spell it out in here, the Processor Trace @@ -36,6 +37,19 @@ static const char *xfeature_names[] = "unknown xstate feature" , }; +static short xsave_cpuid_features[] __initdata = { + X86_FEATURE_FPU, + X86_FEATURE_XMM, + X86_FEATURE_AVX, + X86_FEATURE_MPX, + X86_FEATURE_MPX, + X86_FEATURE_AVX512F, + X86_FEATURE_AVX512F, + X86_FEATURE_AVX512F, + X86_FEATURE_INTEL_PT, + X86_FEATURE_PKU, +}; + /* * Mask of xstate features supported by the CPU and the kernel: */ @@ -59,26 +73,6 @@ unsigned int fpu_user_xstate_size; void fpu__xstate_clear_all_cpu_caps(void) { setup_clear_cpu_cap(X86_FEATURE_XSAVE); - setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); - setup_clear_cpu_cap(X86_FEATURE_XSAVEC); - setup_clear_cpu_cap(X86_FEATURE_XSAVES); - setup_clear_cpu_cap(X86_FEATURE_AVX); - setup_clear_cpu_cap(X86_FEATURE_AVX2); - setup_clear_cpu_cap(X86_FEATURE_AVX512F); - setup_clear_cpu_cap(X86_FEATURE_AVX512IFMA); - setup_clear_cpu_cap(X86_FEATURE_AVX512PF); - setup_clear_cpu_cap(X86_FEATURE_AVX512ER); - setup_clear_cpu_cap(X86_FEATURE_AVX512CD); - setup_clear_cpu_cap(X86_FEATURE_AVX512DQ); - setup_clear_cpu_cap(X86_FEATURE_AVX512BW); - setup_clear_cpu_cap(X86_FEATURE_AVX512VL); - setup_clear_cpu_cap(X86_FEATURE_MPX); - setup_clear_cpu_cap(X86_FEATURE_XGETBV1); - setup_clear_cpu_cap(X86_FEATURE_AVX512VBMI); - 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); } /* @@ -483,6 +477,30 @@ int using_compacted_format(void) return boot_cpu_has(X86_FEATURE_XSAVES); } +/* Validate an xstate header supplied by userspace (ptrace or sigreturn) */ +int validate_xstate_header(const struct xstate_header *hdr) +{ + /* No unknown or supervisor features may be set */ + if (hdr->xfeatures & (~xfeatures_mask | XFEATURE_MASK_SUPERVISOR)) + return -EINVAL; + + /* Userspace must use the uncompacted format */ + if (hdr->xcomp_bv) + return -EINVAL; + + /* + * If 'reserved' is shrunken to add a new field, make sure to validate + * that new field here! + */ + BUILD_BUG_ON(sizeof(hdr->reserved) != 48); + + /* No reserved bits may be set */ + if (memchr_inv(hdr->reserved, 0, sizeof(hdr->reserved))) + return -EINVAL; + + return 0; +} + static void __xstate_dump_leaves(void) { int i; @@ -702,6 +720,7 @@ void __init fpu__init_system_xstate(void) unsigned int eax, ebx, ecx, edx; static int on_boot_cpu __initdata = 1; int err; + int i; WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; @@ -735,6 +754,14 @@ void __init fpu__init_system_xstate(void) goto out_disable; } + /* + * Clear XSAVE features that are disabled in the normal CPUID. + */ + for (i = 0; i < ARRAY_SIZE(xsave_cpuid_features); i++) { + if (!boot_cpu_has(xsave_cpuid_features[i])) + xfeatures_mask &= ~BIT(i); + } + xfeatures_mask &= fpu__get_supported_xfeatures_mask(); /* Enable xstate instructions to be able to continue with initialization: */ @@ -867,7 +894,7 @@ const void *get_xsave_field_ptr(int xsave_state) { struct fpu *fpu = ¤t->thread.fpu; - if (!fpu->fpstate_active) + if (!fpu->initialized) return NULL; /* * fpu__save() takes the CPU's xstate registers @@ -921,38 +948,129 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, #endif /* ! CONFIG_ARCH_HAS_PKEYS */ /* + * Weird legacy quirk: SSE and YMM states store information in the + * MXCSR and MXCSR_FLAGS fields of the FP area. That means if the FP + * area is marked as unused in the xfeatures header, we need to copy + * MXCSR and MXCSR_FLAGS if either SSE or YMM are in use. + */ +static inline bool xfeatures_mxcsr_quirk(u64 xfeatures) +{ + if (!(xfeatures & (XFEATURE_MASK_SSE|XFEATURE_MASK_YMM))) + return false; + + if (xfeatures & XFEATURE_MASK_FP) + return false; + + return true; +} + +/* * This is similar to user_regset_copyout(), but will not add offset to * the source data pointer or increment pos, count, kbuf, and ubuf. */ -static inline int xstate_copyout(unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf, - const void *data, const int start_pos, - const int end_pos) +static inline void +__copy_xstate_to_kernel(void *kbuf, const void *data, + unsigned int offset, unsigned int size, unsigned int size_total) { - if ((count == 0) || (pos < start_pos)) - return 0; + if (offset < size_total) { + unsigned int copy = min(size, size_total - offset); - if (end_pos < 0 || pos < end_pos) { - unsigned int copy = (end_pos < 0 ? count : min(count, end_pos - pos)); + memcpy(kbuf + offset, data, copy); + } +} - if (kbuf) { - memcpy(kbuf + pos, data, copy); - } else { - if (__copy_to_user(ubuf + pos, data, copy)) - return -EFAULT; +/* + * Convert from kernel XSAVES compacted format to standard format and copy + * to a kernel-space ptrace buffer. + * + * It supports partial copy but pos always starts from zero. This is called + * from xstateregs_get() and there we check the CPU has XSAVES. + */ +int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total) +{ + unsigned int offset, size; + struct xstate_header header; + int i; + + /* + * Currently copy_regset_to_user() starts from pos 0: + */ + if (unlikely(offset_start != 0)) + return -EFAULT; + + /* + * The destination is a ptrace buffer; we put in only user xstates: + */ + memset(&header, 0, sizeof(header)); + header.xfeatures = xsave->header.xfeatures; + header.xfeatures &= ~XFEATURE_MASK_SUPERVISOR; + + /* + * Copy xregs_state->header: + */ + offset = offsetof(struct xregs_state, header); + size = sizeof(header); + + __copy_xstate_to_kernel(kbuf, &header, offset, size, size_total); + + for (i = 0; i < XFEATURE_MAX; i++) { + /* + * Copy only in-use xstates: + */ + if ((header.xfeatures >> i) & 1) { + void *src = __raw_xsave_addr(xsave, 1 << i); + + offset = xstate_offsets[i]; + size = xstate_sizes[i]; + + /* The next component has to fit fully into the output buffer: */ + if (offset + size > size_total) + break; + + __copy_xstate_to_kernel(kbuf, src, offset, size, size_total); } + + } + + if (xfeatures_mxcsr_quirk(header.xfeatures)) { + offset = offsetof(struct fxregs_state, mxcsr); + size = MXCSR_AND_FLAGS_SIZE; + __copy_xstate_to_kernel(kbuf, &xsave->i387.mxcsr, offset, size, size_total); + } + + /* + * Fill xsave->i387.sw_reserved value for ptrace frame: + */ + offset = offsetof(struct fxregs_state, sw_reserved); + size = sizeof(xstate_fx_sw_bytes); + + __copy_xstate_to_kernel(kbuf, xstate_fx_sw_bytes, offset, size, size_total); + + return 0; +} + +static inline int +__copy_xstate_to_user(void __user *ubuf, const void *data, unsigned int offset, unsigned int size, unsigned int size_total) +{ + if (!size) + return 0; + + if (offset < size_total) { + unsigned int copy = min(size, size_total - offset); + + if (__copy_to_user(ubuf + offset, data, copy)) + return -EFAULT; } return 0; } /* * Convert from kernel XSAVES compacted format to standard format and copy - * to a ptrace buffer. It supports partial copy but pos always starts from + * to a user-space buffer. It supports partial copy but pos always starts from * zero. This is called from xstateregs_get() and there we check the CPU * has XSAVES. */ -int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, - void __user *ubuf, struct xregs_state *xsave) +int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total) { unsigned int offset, size; int ret, i; @@ -961,7 +1079,7 @@ int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, /* * Currently copy_regset_to_user() starts from pos 0: */ - if (unlikely(pos != 0)) + if (unlikely(offset_start != 0)) return -EFAULT; /* @@ -977,8 +1095,7 @@ int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, offset = offsetof(struct xregs_state, header); size = sizeof(header); - ret = xstate_copyout(offset, size, kbuf, ubuf, &header, 0, count); - + ret = __copy_xstate_to_user(ubuf, &header, offset, size, size_total); if (ret) return ret; @@ -992,25 +1109,30 @@ int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, offset = xstate_offsets[i]; size = xstate_sizes[i]; - ret = xstate_copyout(offset, size, kbuf, ubuf, src, 0, count); + /* The next component has to fit fully into the output buffer: */ + if (offset + size > size_total) + break; + ret = __copy_xstate_to_user(ubuf, src, offset, size, size_total); if (ret) return ret; - - if (offset + size >= count) - break; } } + if (xfeatures_mxcsr_quirk(header.xfeatures)) { + offset = offsetof(struct fxregs_state, mxcsr); + size = MXCSR_AND_FLAGS_SIZE; + __copy_xstate_to_user(ubuf, &xsave->i387.mxcsr, offset, size, size_total); + } + /* * Fill xsave->i387.sw_reserved value for ptrace frame: */ offset = offsetof(struct fxregs_state, sw_reserved); size = sizeof(xstate_fx_sw_bytes); - ret = xstate_copyout(offset, size, kbuf, ubuf, xstate_fx_sw_bytes, 0, count); - + ret = __copy_xstate_to_user(ubuf, xstate_fx_sw_bytes, offset, size, size_total); if (ret) return ret; @@ -1018,55 +1140,98 @@ int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, } /* - * Convert from a ptrace standard-format buffer to kernel XSAVES format - * and copy to the target thread. This is called from xstateregs_set() and - * there we check the CPU has XSAVES and a whole standard-sized buffer - * exists. + * Convert from a ptrace standard-format kernel buffer to kernel XSAVES format + * and copy to the target thread. This is called from xstateregs_set(). */ -int copyin_to_xsaves(const void *kbuf, const void __user *ubuf, - struct xregs_state *xsave) +int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) { unsigned int offset, size; int i; - u64 xfeatures; - u64 allowed_features; + struct xstate_header hdr; offset = offsetof(struct xregs_state, header); - size = sizeof(xfeatures); + size = sizeof(hdr); - if (kbuf) { - memcpy(&xfeatures, kbuf + offset, size); - } else { - if (__copy_from_user(&xfeatures, ubuf + offset, size)) - return -EFAULT; + memcpy(&hdr, kbuf + offset, size); + + if (validate_xstate_header(&hdr)) + return -EINVAL; + + for (i = 0; i < XFEATURE_MAX; i++) { + u64 mask = ((u64)1 << i); + + if (hdr.xfeatures & mask) { + void *dst = __raw_xsave_addr(xsave, 1 << i); + + offset = xstate_offsets[i]; + size = xstate_sizes[i]; + + memcpy(dst, kbuf + offset, size); + } + } + + if (xfeatures_mxcsr_quirk(hdr.xfeatures)) { + offset = offsetof(struct fxregs_state, mxcsr); + size = MXCSR_AND_FLAGS_SIZE; + memcpy(&xsave->i387.mxcsr, kbuf + offset, size); } /* - * Reject if the user sets any disabled or supervisor features: + * The state that came in from userspace was user-state only. + * Mask all the user states out of 'xfeatures': + */ + xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR; + + /* + * Add back in the features that came in from userspace: */ - allowed_features = xfeatures_mask & ~XFEATURE_MASK_SUPERVISOR; + xsave->header.xfeatures |= hdr.xfeatures; + + return 0; +} - if (xfeatures & ~allowed_features) +/* + * Convert from a ptrace or sigreturn standard-format user-space buffer to + * kernel XSAVES format and copy to the target thread. This is called from + * xstateregs_set(), as well as potentially from the sigreturn() and + * rt_sigreturn() system calls. + */ +int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf) +{ + unsigned int offset, size; + int i; + struct xstate_header hdr; + + offset = offsetof(struct xregs_state, header); + size = sizeof(hdr); + + if (__copy_from_user(&hdr, ubuf + offset, size)) + return -EFAULT; + + if (validate_xstate_header(&hdr)) return -EINVAL; for (i = 0; i < XFEATURE_MAX; i++) { u64 mask = ((u64)1 << i); - if (xfeatures & mask) { + if (hdr.xfeatures & mask) { void *dst = __raw_xsave_addr(xsave, 1 << i); offset = xstate_offsets[i]; size = xstate_sizes[i]; - if (kbuf) { - memcpy(dst, kbuf + offset, size); - } else { - if (__copy_from_user(dst, ubuf + offset, size)) - return -EFAULT; - } + if (__copy_from_user(dst, ubuf + offset, size)) + return -EFAULT; } } + if (xfeatures_mxcsr_quirk(hdr.xfeatures)) { + offset = offsetof(struct fxregs_state, mxcsr); + size = MXCSR_AND_FLAGS_SIZE; + if (__copy_from_user(&xsave->i387.mxcsr, ubuf + offset, size)) + return -EFAULT; + } + /* * The state that came in from userspace was user-state only. * Mask all the user states out of 'xfeatures': @@ -1076,7 +1241,7 @@ int copyin_to_xsaves(const void *kbuf, const void __user *ubuf, /* * Add back in the features that came in from userspace: */ - xsave->header.xfeatures |= xfeatures; + xsave->header.xfeatures |= hdr.xfeatures; return 0; } diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 9bef1bbeba63..01ebcb6f263e 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Dynamic function tracing support. * diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S index 722a145b4139..b6c6468e10bc 100644 --- a/arch/x86/kernel/ftrace_32.S +++ b/arch/x86/kernel/ftrace_32.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2017 Steven Rostedt, VMware Inc. */ diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 1dfac634bbf7..c832291d948a 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2014 Steven Rostedt, Red Hat Inc */ diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 538ec012b371..ec6fefbfd3c0 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * linux/arch/i386/kernel/head32.c -- prepare to run common code * @@ -10,6 +11,7 @@ #include <linux/mm.h> #include <linux/memblock.h> +#include <asm/desc.h> #include <asm/setup.h> #include <asm/sections.h> #include <asm/e820/api.h> @@ -29,7 +31,11 @@ static void __init i386_default_early_setup(void) asmlinkage __visible void __init i386_start_kernel(void) { + /* Make sure IDT is set up before any exception happens */ + idt_setup_early_handler(); + cr4_init_shadow(); + sanitize_boot_params(&boot_params); x86_early_init_platform_quirks(); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 46c3c73e7f43..6a5d757b9cfd 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * prepare to run common code * @@ -14,6 +15,7 @@ #include <linux/start_kernel.h> #include <linux/io.h> #include <linux/memblock.h> +#include <linux/mem_encrypt.h> #include <asm/processor.h> #include <asm/proto.h> @@ -33,7 +35,6 @@ /* * Manage page tables very early on. */ -extern pgd_t early_top_pgt[PTRS_PER_PGD]; extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD]; static unsigned int __initdata next_early_pgt; pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX); @@ -45,14 +46,17 @@ static void __head *fixup_pointer(void *ptr, unsigned long physaddr) return ptr - (void *)_text + (void *)physaddr; } -void __head __startup_64(unsigned long physaddr) +unsigned long __head __startup_64(unsigned long physaddr, + struct boot_params *bp) { unsigned long load_delta, *p; + unsigned long pgtable_flags; pgdval_t *pgd; p4dval_t *p4d; pudval_t *pud; pmdval_t *pmd, pmd_entry; int i; + unsigned int *next_pgt_ptr; /* Is the address too large? */ if (physaddr >> MAX_PHYSMEM_BITS) @@ -68,6 +72,12 @@ void __head __startup_64(unsigned long physaddr) if (load_delta & ~PMD_PAGE_MASK) for (;;); + /* Activate Secure Memory Encryption (SME) if supported and enabled */ + sme_enable(bp); + + /* Include the SME encryption mask in the fixup value */ + load_delta += sme_get_me_mask(); + /* Fixup the physical addresses in the page table */ pgd = fixup_pointer(&early_top_pgt, physaddr); @@ -92,30 +102,34 @@ void __head __startup_64(unsigned long physaddr) * it avoids problems around wraparound. */ - pud = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); - pmd = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); + next_pgt_ptr = fixup_pointer(&next_early_pgt, physaddr); + pud = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr); + pmd = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr); + + pgtable_flags = _KERNPG_TABLE_NOENC + sme_get_me_mask(); if (IS_ENABLED(CONFIG_X86_5LEVEL)) { p4d = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD; - pgd[i + 0] = (pgdval_t)p4d + _KERNPG_TABLE; - pgd[i + 1] = (pgdval_t)p4d + _KERNPG_TABLE; + pgd[i + 0] = (pgdval_t)p4d + pgtable_flags; + pgd[i + 1] = (pgdval_t)p4d + pgtable_flags; i = (physaddr >> P4D_SHIFT) % PTRS_PER_P4D; - p4d[i + 0] = (pgdval_t)pud + _KERNPG_TABLE; - p4d[i + 1] = (pgdval_t)pud + _KERNPG_TABLE; + p4d[i + 0] = (pgdval_t)pud + pgtable_flags; + p4d[i + 1] = (pgdval_t)pud + pgtable_flags; } else { i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD; - pgd[i + 0] = (pgdval_t)pud + _KERNPG_TABLE; - pgd[i + 1] = (pgdval_t)pud + _KERNPG_TABLE; + pgd[i + 0] = (pgdval_t)pud + pgtable_flags; + pgd[i + 1] = (pgdval_t)pud + pgtable_flags; } i = (physaddr >> PUD_SHIFT) % PTRS_PER_PUD; - pud[i + 0] = (pudval_t)pmd + _KERNPG_TABLE; - pud[i + 1] = (pudval_t)pmd + _KERNPG_TABLE; + pud[i + 0] = (pudval_t)pmd + pgtable_flags; + pud[i + 1] = (pudval_t)pmd + pgtable_flags; pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL; + pmd_entry += sme_get_me_mask(); pmd_entry += physaddr; for (i = 0; i < DIV_ROUND_UP(_end - _text, PMD_SIZE); i++) { @@ -136,9 +150,30 @@ void __head __startup_64(unsigned long physaddr) pmd[i] += load_delta; } - /* Fixup phys_base */ + /* + * Fixup phys_base - remove the memory encryption mask to obtain + * the true physical address. + */ p = fixup_pointer(&phys_base, physaddr); - *p += load_delta; + *p += load_delta - sme_get_me_mask(); + + /* Encrypt the kernel (if SME is active) */ + sme_encrypt_kernel(); + + /* + * Return the SME encryption mask (if SME is active) to be used as a + * modifier for the initial pgdir entry programmed into CR3. + */ + return sme_get_me_mask(); +} + +unsigned long __startup_secondary_64(void) +{ + /* + * Return the SME encryption mask (if SME is active) to be used as a + * modifier for the initial pgdir entry programmed into CR3. + */ + return sme_get_me_mask(); } /* Wipe all early page tables except for the kernel symbol map */ @@ -146,17 +181,17 @@ static void __init reset_early_page_tables(void) { memset(early_top_pgt, 0, sizeof(pgd_t)*(PTRS_PER_PGD-1)); next_early_pgt = 0; - write_cr3(__pa_nodebug(early_top_pgt)); + write_cr3(__sme_pa_nodebug(early_top_pgt)); } /* Create a new PMD entry */ -int __init early_make_pgtable(unsigned long address) +int __init __early_make_pgtable(unsigned long address, pmdval_t pmd) { unsigned long physaddr = address - __PAGE_OFFSET; pgdval_t pgd, *pgd_p; p4dval_t p4d, *p4d_p; pudval_t pud, *pud_p; - pmdval_t pmd, *pmd_p; + pmdval_t *pmd_p; /* Invalid address or early pgt is done ? */ if (physaddr >= MAXMEM || read_cr3_pa() != __pa_nodebug(early_top_pgt)) @@ -215,12 +250,21 @@ again: memset(pmd_p, 0, sizeof(*pmd_p) * PTRS_PER_PMD); *pud_p = (pudval_t)pmd_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE; } - pmd = (physaddr & PMD_MASK) + early_pmd_flags; pmd_p[pmd_index(address)] = pmd; return 0; } +int __init early_make_pgtable(unsigned long address) +{ + unsigned long physaddr = address - __PAGE_OFFSET; + pmdval_t pmd; + + pmd = (physaddr & PMD_MASK) + early_pmd_flags; + + return __early_make_pgtable(address, pmd); +} + /* Don't add a printk in there. printk relies on the PDA which is not initialized yet. */ static void __init clear_bss(void) @@ -243,6 +287,12 @@ static void __init copy_bootdata(char *real_mode_data) char * command_line; unsigned long cmd_line_ptr; + /* + * If SME is active, this will create decrypted mappings of the + * boot data in advance of the copy operations. + */ + sme_map_bootdata(real_mode_data); + memcpy(&boot_params, real_mode_data, sizeof boot_params); sanitize_boot_params(&boot_params); cmd_line_ptr = get_cmd_line_ptr(); @@ -250,12 +300,18 @@ static void __init copy_bootdata(char *real_mode_data) command_line = __va(cmd_line_ptr); memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE); } + + /* + * The old boot data is no longer needed and won't be reserved, + * freeing up that memory for use by the system. If SME is active, + * we need to remove the mappings that were created so that the + * memory doesn't remain mapped as decrypted. + */ + sme_unmap_bootdata(real_mode_data); } asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) { - int i; - /* * Build-time sanity checks on the kernel image and module * area mappings. (these are purely build-time and produce no code) @@ -279,11 +335,16 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) clear_page(init_top_pgt); + /* + * SME support may update early_pmd_flags to include the memory + * encryption mask, so it needs to be called before anything + * that may generate a page fault. + */ + sme_early_init(); + kasan_early_init(); - for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) - set_intr_gate(i, early_idt_handler_array[i]); - load_idt((const struct desc_ptr *)&idt_descr); + idt_setup_early_handler(); copy_bootdata(__va(real_mode_data)); diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 1f85ee8f9439..c29020907886 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * * Copyright (C) 1991, 1992 Linus Torvalds @@ -155,7 +156,6 @@ ENTRY(startup_32) jmp *%eax .Lbad_subarch: -WEAK(lguest_entry) WEAK(xen_entry) /* Unknown implementation; there's really nothing we can do at this point. */ @@ -165,7 +165,6 @@ WEAK(xen_entry) subarch_entries: .long .Ldefault_entry /* normal x86/PC */ - .long lguest_entry /* lguest hypervisor */ .long xen_entry /* Xen hypervisor */ .long .Ldefault_entry /* Moorestown MID */ num_subarch_entries = (. - subarch_entries) / 4 @@ -213,9 +212,6 @@ ENTRY(startup_32_smp) #endif .Ldefault_entry: -#define CR0_STATE (X86_CR0_PE | X86_CR0_MP | X86_CR0_ET | \ - X86_CR0_NE | X86_CR0_WP | X86_CR0_AM | \ - X86_CR0_PG) movl $(CR0_STATE & ~X86_CR0_PG),%eax movl %eax,%cr0 @@ -347,7 +343,6 @@ ENTRY(startup_32_smp) movl %eax,%cr0 lgdt early_gdt_descr - lidt idt_descr ljmp $(__KERNEL_CS),$1f 1: movl $(__KERNEL_DS),%eax # reload all the segment registers movl %eax,%ss # after changing gdt. @@ -380,37 +375,6 @@ ENDPROC(startup_32_smp) */ __INIT setup_once: - /* - * Set up a idt with 256 interrupt gates that push zero if there - * is no error code and then jump to early_idt_handler_common. - * It doesn't actually load the idt - that needs to be done on - * each CPU. Interrupts are enabled elsewhere, when we can be - * relatively sure everything is ok. - */ - - movl $idt_table,%edi - movl $early_idt_handler_array,%eax - movl $NUM_EXCEPTION_VECTORS,%ecx -1: - movl %eax,(%edi) - movl %eax,4(%edi) - /* interrupt gate, dpl=0, present */ - movl $(0x8E000000 + __KERNEL_CS),2(%edi) - addl $EARLY_IDT_HANDLER_SIZE,%eax - addl $8,%edi - loop 1b - - movl $256 - NUM_EXCEPTION_VECTORS,%ecx - movl $ignore_int,%edx - movl $(__KERNEL_CS << 16),%eax - movw %dx,%ax /* selector = 0x0010 = cs */ - movw $0x8E00,%dx /* interrupt gate - dpl=0, present */ -2: - movl %eax,(%edi) - movl %edx,4(%edi) - addl $8,%edi - loop 2b - #ifdef CONFIG_CC_STACKPROTECTOR /* * Configure the stack canary. The linker can't handle this by @@ -435,7 +399,7 @@ ENTRY(early_idt_handler_array) # 24(%rsp) error code i = 0 .rept NUM_EXCEPTION_VECTORS - .ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1 + .if ((EXCEPTION_ERRCODE_MASK >> i) & 1) == 0 pushl $0 # Dummy error code, to make stack frame uniform .endif pushl $i # 20(%esp) Vector number @@ -457,12 +421,9 @@ early_idt_handler_common: /* The vector number is in pt_regs->gs */ cld - pushl %fs /* pt_regs->fs */ - movw $0, 2(%esp) /* clear high bits (some CPUs leave garbage) */ - pushl %es /* pt_regs->es */ - movw $0, 2(%esp) /* clear high bits (some CPUs leave garbage) */ - pushl %ds /* pt_regs->ds */ - movw $0, 2(%esp) /* clear high bits (some CPUs leave garbage) */ + pushl %fs /* pt_regs->fs (__fsh varies by model) */ + pushl %es /* pt_regs->es (__esh varies by model) */ + pushl %ds /* pt_regs->ds (__dsh varies by model) */ pushl %eax /* pt_regs->ax */ pushl %ebp /* pt_regs->bp */ pushl %edi /* pt_regs->di */ @@ -479,9 +440,8 @@ early_idt_handler_common: /* Load the vector number into EDX */ movl PT_GS(%esp), %edx - /* Load GS into pt_regs->gs and clear high bits */ + /* Load GS into pt_regs->gs (and maybe clobber __gsh) */ movw %gs, PT_GS(%esp) - movw $0, PT_GS+2(%esp) movl %esp, %eax /* args are pt_regs (EAX), trapnr (EDX) */ call early_fixup_exception @@ -493,18 +453,17 @@ early_idt_handler_common: popl %edi /* pt_regs->di */ popl %ebp /* pt_regs->bp */ popl %eax /* pt_regs->ax */ - popl %ds /* pt_regs->ds */ - popl %es /* pt_regs->es */ - popl %fs /* pt_regs->fs */ - popl %gs /* pt_regs->gs */ + popl %ds /* pt_regs->ds (always ignores __dsh) */ + popl %es /* pt_regs->es (always ignores __esh) */ + popl %fs /* pt_regs->fs (always ignores __fsh) */ + popl %gs /* pt_regs->gs (always ignores __gsh) */ decl %ss:early_recursion_flag addl $4, %esp /* pop pt_regs->orig_ax */ iret ENDPROC(early_idt_handler_common) /* This is the default interrupt "handler" :-) */ - ALIGN -ignore_int: +ENTRY(early_ignore_irq) cld #ifdef CONFIG_PRINTK pushl %eax @@ -539,7 +498,8 @@ ignore_int: hlt_loop: hlt jmp hlt_loop -ENDPROC(ignore_int) +ENDPROC(early_ignore_irq) + __INITDATA .align 4 GLOBAL(early_recursion_flag) @@ -628,7 +588,6 @@ int_msg: .data .globl boot_gdt_descr -.globl idt_descr ALIGN # early boot GDT descriptor (must use 1:1 address mapping) @@ -637,11 +596,6 @@ boot_gdt_descr: .word __BOOT_DS+7 .long boot_gdt - __PAGE_OFFSET - .word 0 # 32-bit align idt_desc.address -idt_descr: - .word IDT_ENTRIES*8-1 # idt contains 256 entries - .long idt_table - # boot GDT descriptor (later on used by CPU#0): .word 0 # 32 bit align gdt_desc.address ENTRY(early_gdt_descr) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 6225550883df..7dca675fe78d 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * linux/arch/x86/kernel/head_64.S -- start in 32bit and switch to 64bit * @@ -37,11 +38,12 @@ * */ -#define p4d_index(x) (((x) >> P4D_SHIFT) & (PTRS_PER_P4D-1)) #define pud_index(x) (((x) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) +#if defined(CONFIG_XEN_PV) || defined(CONFIG_XEN_PVH) PGD_PAGE_OFFSET = pgd_index(__PAGE_OFFSET_BASE) PGD_START_KERNEL = pgd_index(__START_KERNEL_map) +#endif L3_START_KERNEL = pud_index(__START_KERNEL_map) .text @@ -49,6 +51,7 @@ L3_START_KERNEL = pud_index(__START_KERNEL_map) .code64 .globl startup_64 startup_64: + UNWIND_HINT_EMPTY /* * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 0, * and someone has loaded an identity mapped page table @@ -73,14 +76,22 @@ startup_64: /* Sanitize CPU configuration */ call verify_cpu + /* + * Perform pagetable fixups. Additionally, if SME is active, encrypt + * the kernel and retrieve the modifier (SME encryption mask if SME + * is active) to be added to the initial pgdir entry that will be + * programmed into CR3. + */ leaq _text(%rip), %rdi pushq %rsi call __startup_64 popq %rsi - movq $(early_top_pgt - __START_KERNEL_map), %rax + /* Form the CR3 value being sure to include the CR3 modifier */ + addq $(early_top_pgt - __START_KERNEL_map), %rax jmp 1f ENTRY(secondary_startup_64) + UNWIND_HINT_EMPTY /* * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 0, * and someone has loaded a mapped page table. @@ -98,7 +109,16 @@ ENTRY(secondary_startup_64) /* Sanitize CPU configuration */ call verify_cpu - movq $(init_top_pgt - __START_KERNEL_map), %rax + /* + * Retrieve the modifier (SME encryption mask if SME is active) to be + * added to the initial pgdir entry that will be programmed into CR3. + */ + pushq %rsi + call __startup_secondary_64 + popq %rsi + + /* Form the CR3 value being sure to include the CR3 modifier */ + addq $(init_top_pgt - __START_KERNEL_map), %rax 1: /* Enable PAE mode, PGE and LA57 */ @@ -116,6 +136,7 @@ ENTRY(secondary_startup_64) movq $1f, %rax jmp *%rax 1: + UNWIND_HINT_EMPTY /* Check if nx is implemented */ movl $0x80000001, %eax @@ -133,9 +154,6 @@ ENTRY(secondary_startup_64) 1: wrmsr /* Make changes effective */ /* Setup cr0 */ -#define CR0_STATE (X86_CR0_PE | X86_CR0_MP | X86_CR0_ET | \ - X86_CR0_NE | X86_CR0_WP | X86_CR0_AM | \ - X86_CR0_PG) movl $CR0_STATE, %eax /* Make changes effective */ movq %rax, %cr0 @@ -218,7 +236,7 @@ ENTRY(secondary_startup_64) pushq %rax # target address in negative space lretq .Lafter_lret: -ENDPROC(secondary_startup_64) +END(secondary_startup_64) #include "verify_cpu.S" @@ -230,6 +248,7 @@ ENDPROC(secondary_startup_64) */ ENTRY(start_cpu0) movq initial_stack(%rip), %rsp + UNWIND_HINT_EMPTY jmp .Ljump_to_C_code ENDPROC(start_cpu0) #endif @@ -249,26 +268,24 @@ ENDPROC(start_cpu0) .quad init_thread_union + THREAD_SIZE - SIZEOF_PTREGS __FINITDATA -bad_address: - jmp bad_address - __INIT ENTRY(early_idt_handler_array) - # 104(%rsp) %rflags - # 96(%rsp) %cs - # 88(%rsp) %rip - # 80(%rsp) error code i = 0 .rept NUM_EXCEPTION_VECTORS - .ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1 - pushq $0 # Dummy error code, to make stack frame uniform + .if ((EXCEPTION_ERRCODE_MASK >> i) & 1) == 0 + UNWIND_HINT_IRET_REGS + pushq $0 # Dummy error code, to make stack frame uniform + .else + UNWIND_HINT_IRET_REGS offset=8 .endif pushq $i # 72(%rsp) Vector number jmp early_idt_handler_common + UNWIND_HINT_IRET_REGS i = i + 1 .fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc .endr -ENDPROC(early_idt_handler_array) + UNWIND_HINT_IRET_REGS offset=16 +END(early_idt_handler_array) early_idt_handler_common: /* @@ -296,6 +313,7 @@ early_idt_handler_common: pushq %r13 /* pt_regs->r13 */ pushq %r14 /* pt_regs->r14 */ pushq %r15 /* pt_regs->r15 */ + UNWIND_HINT_REGS cmpq $14,%rsi /* Page fault? */ jnz 10f @@ -310,8 +328,8 @@ early_idt_handler_common: 20: decl early_recursion_flag(%rip) - jmp restore_regs_and_iret -ENDPROC(early_idt_handler_common) + jmp restore_regs_and_return_to_kernel +END(early_idt_handler_common) __INITDATA @@ -335,9 +353,9 @@ GLOBAL(name) NEXT_PAGE(early_top_pgt) .fill 511,8,0 #ifdef CONFIG_X86_5LEVEL - .quad level4_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE + .quad level4_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC #else - .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE + .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC #endif NEXT_PAGE(early_dynamic_pgts) @@ -345,39 +363,39 @@ NEXT_PAGE(early_dynamic_pgts) .data -#ifndef CONFIG_XEN -NEXT_PAGE(init_top_pgt) - .fill 512,8,0 -#else +#if defined(CONFIG_XEN_PV) || defined(CONFIG_XEN_PVH) NEXT_PAGE(init_top_pgt) - .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE + .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC .org init_top_pgt + PGD_PAGE_OFFSET*8, 0 - .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE + .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC .org init_top_pgt + PGD_START_KERNEL*8, 0 /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */ - .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE + .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC NEXT_PAGE(level3_ident_pgt) - .quad level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE + .quad level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC .fill 511, 8, 0 NEXT_PAGE(level2_ident_pgt) /* Since I easily can, map the first 1G. * Don't set NX because code runs from these pages. */ PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD) +#else +NEXT_PAGE(init_top_pgt) + .fill 512,8,0 #endif #ifdef CONFIG_X86_5LEVEL NEXT_PAGE(level4_kernel_pgt) .fill 511,8,0 - .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE + .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC #endif NEXT_PAGE(level3_kernel_pgt) .fill L3_START_KERNEL,8,0 /* (2^48-(2*1024*1024*1024)-((2^39)*511))/(2^30) = 510 */ - .quad level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE - .quad level2_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE + .quad level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC + .quad level2_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC NEXT_PAGE(level2_kernel_pgt) /* @@ -395,7 +413,7 @@ NEXT_PAGE(level2_kernel_pgt) NEXT_PAGE(level2_fixmap_pgt) .fill 506,8,0 - .quad level1_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE + .quad level1_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC /* 8MB reserved for vsyscalls + a 2MB hole = 4 + 1 entries */ .fill 5,8,0 @@ -418,7 +436,7 @@ ENTRY(phys_base) EXPORT_SYMBOL(phys_base) #include "../../x86/xen/xen-head.S" - + __PAGE_ALIGNED_BSS NEXT_PAGE(empty_zero_page) .skip PAGE_SIZE diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 16f82a3aaec7..8ce4212e2b8d 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -345,21 +345,10 @@ static int hpet_shutdown(struct clock_event_device *evt, int timer) return 0; } -static int hpet_resume(struct clock_event_device *evt, int timer) -{ - if (!timer) { - hpet_enable_legacy_int(); - } 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_hardirq(hdev->irq); - irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu)); - enable_irq(hdev->irq); - } +static int hpet_resume(struct clock_event_device *evt) +{ + hpet_enable_legacy_int(); hpet_print_config(); - return 0; } @@ -417,7 +406,7 @@ static int hpet_legacy_set_periodic(struct clock_event_device *evt) static int hpet_legacy_resume(struct clock_event_device *evt) { - return hpet_resume(evt, 0); + return hpet_resume(evt); } static int hpet_legacy_next_event(unsigned long delta, @@ -510,8 +499,14 @@ static int hpet_msi_set_periodic(struct clock_event_device *evt) static int hpet_msi_resume(struct clock_event_device *evt) { struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); + struct irq_data *data = irq_get_irq_data(hdev->irq); + struct msi_msg msg; - return hpet_resume(evt, hdev->num); + /* Restore the MSI msg and unmask the interrupt */ + irq_chip_compose_msi_msg(data, &msg); + hpet_msi_write(hdev, &msg); + hpet_msi_unmask(data); + return 0; } static int hpet_msi_next_event(unsigned long delta, diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c index 6ebe00cb4a3b..0d307a657abb 100644 --- a/arch/x86/kernel/i8253.c +++ b/arch/x86/kernel/i8253.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * 8253/PIT functions * diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 4e3b8a587c88..86c4439f9d74 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/linkage.h> #include <linux/errno.h> #include <linux/signal.h> @@ -113,6 +114,7 @@ static void make_8259A_irq(unsigned int irq) io_apic_irqs &= ~(1<<irq); irq_set_chip_and_handler(irq, &i8259A_chip, handle_level_irq); enable_irq(irq); + lapic_assign_legacy_vector(irq, true); } /* diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c new file mode 100644 index 000000000000..d985cef3984f --- /dev/null +++ b/arch/x86/kernel/idt.c @@ -0,0 +1,369 @@ +/* + * Interrupt descriptor table related code + * + * This file is licensed under the GPL V2 + */ +#include <linux/interrupt.h> + +#include <asm/traps.h> +#include <asm/proto.h> +#include <asm/desc.h> + +struct idt_data { + unsigned int vector; + unsigned int segment; + struct idt_bits bits; + const void *addr; +}; + +#define DPL0 0x0 +#define DPL3 0x3 + +#define DEFAULT_STACK 0 + +#define G(_vector, _addr, _ist, _type, _dpl, _segment) \ + { \ + .vector = _vector, \ + .bits.ist = _ist, \ + .bits.type = _type, \ + .bits.dpl = _dpl, \ + .bits.p = 1, \ + .addr = _addr, \ + .segment = _segment, \ + } + +/* Interrupt gate */ +#define INTG(_vector, _addr) \ + G(_vector, _addr, DEFAULT_STACK, GATE_INTERRUPT, DPL0, __KERNEL_CS) + +/* System interrupt gate */ +#define SYSG(_vector, _addr) \ + G(_vector, _addr, DEFAULT_STACK, GATE_INTERRUPT, DPL3, __KERNEL_CS) + +/* Interrupt gate with interrupt stack */ +#define ISTG(_vector, _addr, _ist) \ + G(_vector, _addr, _ist, GATE_INTERRUPT, DPL0, __KERNEL_CS) + +/* System interrupt gate with interrupt stack */ +#define SISTG(_vector, _addr, _ist) \ + G(_vector, _addr, _ist, GATE_INTERRUPT, DPL3, __KERNEL_CS) + +/* Task gate */ +#define TSKG(_vector, _gdt) \ + G(_vector, NULL, DEFAULT_STACK, GATE_TASK, DPL0, _gdt << 3) + +/* + * Early traps running on the DEFAULT_STACK because the other interrupt + * stacks work only after cpu_init(). + */ +static const __initdata struct idt_data early_idts[] = { + INTG(X86_TRAP_DB, debug), + SYSG(X86_TRAP_BP, int3), +#ifdef CONFIG_X86_32 + INTG(X86_TRAP_PF, page_fault), +#endif +}; + +/* + * The default IDT entries which are set up in trap_init() before + * cpu_init() is invoked. Interrupt stacks cannot be used at that point and + * the traps which use them are reinitialized with IST after cpu_init() has + * set up TSS. + */ +static const __initdata struct idt_data def_idts[] = { + INTG(X86_TRAP_DE, divide_error), + INTG(X86_TRAP_NMI, nmi), + INTG(X86_TRAP_BR, bounds), + INTG(X86_TRAP_UD, invalid_op), + INTG(X86_TRAP_NM, device_not_available), + INTG(X86_TRAP_OLD_MF, coprocessor_segment_overrun), + INTG(X86_TRAP_TS, invalid_TSS), + INTG(X86_TRAP_NP, segment_not_present), + INTG(X86_TRAP_SS, stack_segment), + INTG(X86_TRAP_GP, general_protection), + INTG(X86_TRAP_SPURIOUS, spurious_interrupt_bug), + INTG(X86_TRAP_MF, coprocessor_error), + INTG(X86_TRAP_AC, alignment_check), + INTG(X86_TRAP_XF, simd_coprocessor_error), + +#ifdef CONFIG_X86_32 + TSKG(X86_TRAP_DF, GDT_ENTRY_DOUBLEFAULT_TSS), +#else + INTG(X86_TRAP_DF, double_fault), +#endif + INTG(X86_TRAP_DB, debug), + +#ifdef CONFIG_X86_MCE + INTG(X86_TRAP_MC, &machine_check), +#endif + + SYSG(X86_TRAP_OF, overflow), +#if defined(CONFIG_IA32_EMULATION) + SYSG(IA32_SYSCALL_VECTOR, entry_INT80_compat), +#elif defined(CONFIG_X86_32) + SYSG(IA32_SYSCALL_VECTOR, entry_INT80_32), +#endif +}; + +/* + * The APIC and SMP idt entries + */ +static const __initdata struct idt_data apic_idts[] = { +#ifdef CONFIG_SMP + INTG(RESCHEDULE_VECTOR, reschedule_interrupt), + INTG(CALL_FUNCTION_VECTOR, call_function_interrupt), + INTG(CALL_FUNCTION_SINGLE_VECTOR, call_function_single_interrupt), + INTG(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt), + INTG(REBOOT_VECTOR, reboot_interrupt), +#endif + +#ifdef CONFIG_X86_THERMAL_VECTOR + INTG(THERMAL_APIC_VECTOR, thermal_interrupt), +#endif + +#ifdef CONFIG_X86_MCE_THRESHOLD + INTG(THRESHOLD_APIC_VECTOR, threshold_interrupt), +#endif + +#ifdef CONFIG_X86_MCE_AMD + INTG(DEFERRED_ERROR_VECTOR, deferred_error_interrupt), +#endif + +#ifdef CONFIG_X86_LOCAL_APIC + INTG(LOCAL_TIMER_VECTOR, apic_timer_interrupt), + INTG(X86_PLATFORM_IPI_VECTOR, x86_platform_ipi), +# ifdef CONFIG_HAVE_KVM + INTG(POSTED_INTR_VECTOR, kvm_posted_intr_ipi), + INTG(POSTED_INTR_WAKEUP_VECTOR, kvm_posted_intr_wakeup_ipi), + INTG(POSTED_INTR_NESTED_VECTOR, kvm_posted_intr_nested_ipi), +# endif +# ifdef CONFIG_IRQ_WORK + INTG(IRQ_WORK_VECTOR, irq_work_interrupt), +# endif + INTG(SPURIOUS_APIC_VECTOR, spurious_interrupt), + INTG(ERROR_APIC_VECTOR, error_interrupt), +#endif +}; + +#ifdef CONFIG_X86_64 +/* + * Early traps running on the DEFAULT_STACK because the other interrupt + * stacks work only after cpu_init(). + */ +static const __initdata struct idt_data early_pf_idts[] = { + INTG(X86_TRAP_PF, page_fault), +}; + +/* + * Override for the debug_idt. Same as the default, but with interrupt + * stack set to DEFAULT_STACK (0). Required for NMI trap handling. + */ +static const __initdata struct idt_data dbg_idts[] = { + INTG(X86_TRAP_DB, debug), + INTG(X86_TRAP_BP, int3), +}; +#endif + +/* Must be page-aligned because the real IDT is used in a fixmap. */ +gate_desc idt_table[IDT_ENTRIES] __page_aligned_bss; + +struct desc_ptr idt_descr __ro_after_init = { + .size = (IDT_ENTRIES * 2 * sizeof(unsigned long)) - 1, + .address = (unsigned long) idt_table, +}; + +#ifdef CONFIG_X86_64 +/* No need to be aligned, but done to keep all IDTs defined the same way. */ +gate_desc debug_idt_table[IDT_ENTRIES] __page_aligned_bss; + +/* + * The exceptions which use Interrupt stacks. They are setup after + * cpu_init() when the TSS has been initialized. + */ +static const __initdata struct idt_data ist_idts[] = { + ISTG(X86_TRAP_DB, debug, DEBUG_STACK), + ISTG(X86_TRAP_NMI, nmi, NMI_STACK), + SISTG(X86_TRAP_BP, int3, DEBUG_STACK), + ISTG(X86_TRAP_DF, double_fault, DOUBLEFAULT_STACK), +#ifdef CONFIG_X86_MCE + ISTG(X86_TRAP_MC, &machine_check, MCE_STACK), +#endif +}; + +/* + * Override for the debug_idt. Same as the default, but with interrupt + * stack set to DEFAULT_STACK (0). Required for NMI trap handling. + */ +const struct desc_ptr debug_idt_descr = { + .size = IDT_ENTRIES * 16 - 1, + .address = (unsigned long) debug_idt_table, +}; +#endif + +static inline void idt_init_desc(gate_desc *gate, const struct idt_data *d) +{ + unsigned long addr = (unsigned long) d->addr; + + gate->offset_low = (u16) addr; + gate->segment = (u16) d->segment; + gate->bits = d->bits; + gate->offset_middle = (u16) (addr >> 16); +#ifdef CONFIG_X86_64 + gate->offset_high = (u32) (addr >> 32); + gate->reserved = 0; +#endif +} + +static void +idt_setup_from_table(gate_desc *idt, const struct idt_data *t, int size, bool sys) +{ + gate_desc desc; + + for (; size > 0; t++, size--) { + idt_init_desc(&desc, t); + write_idt_entry(idt, t->vector, &desc); + if (sys) + set_bit(t->vector, system_vectors); + } +} + +static void set_intr_gate(unsigned int n, const void *addr) +{ + struct idt_data data; + + BUG_ON(n > 0xFF); + + memset(&data, 0, sizeof(data)); + data.vector = n; + data.addr = addr; + data.segment = __KERNEL_CS; + data.bits.type = GATE_INTERRUPT; + data.bits.p = 1; + + idt_setup_from_table(idt_table, &data, 1, false); +} + +/** + * idt_setup_early_traps - Initialize the idt table with early traps + * + * On X8664 these traps do not use interrupt stacks as they can't work + * before cpu_init() is invoked and sets up TSS. The IST variants are + * installed after that. + */ +void __init idt_setup_early_traps(void) +{ + idt_setup_from_table(idt_table, early_idts, ARRAY_SIZE(early_idts), + true); + load_idt(&idt_descr); +} + +/** + * idt_setup_traps - Initialize the idt table with default traps + */ +void __init idt_setup_traps(void) +{ + idt_setup_from_table(idt_table, def_idts, ARRAY_SIZE(def_idts), true); +} + +#ifdef CONFIG_X86_64 +/** + * idt_setup_early_pf - Initialize the idt table with early pagefault handler + * + * On X8664 this does not use interrupt stacks as they can't work before + * cpu_init() is invoked and sets up TSS. The IST variant is installed + * after that. + * + * FIXME: Why is 32bit and 64bit installing the PF handler at different + * places in the early setup code? + */ +void __init idt_setup_early_pf(void) +{ + idt_setup_from_table(idt_table, early_pf_idts, + ARRAY_SIZE(early_pf_idts), true); +} + +/** + * idt_setup_ist_traps - Initialize the idt table with traps using IST + */ +void __init idt_setup_ist_traps(void) +{ + idt_setup_from_table(idt_table, ist_idts, ARRAY_SIZE(ist_idts), true); +} + +/** + * idt_setup_debugidt_traps - Initialize the debug idt table with debug traps + */ +void __init idt_setup_debugidt_traps(void) +{ + memcpy(&debug_idt_table, &idt_table, IDT_ENTRIES * 16); + + idt_setup_from_table(debug_idt_table, dbg_idts, ARRAY_SIZE(dbg_idts), false); +} +#endif + +/** + * idt_setup_apic_and_irq_gates - Setup APIC/SMP and normal interrupt gates + */ +void __init idt_setup_apic_and_irq_gates(void) +{ + int i = FIRST_EXTERNAL_VECTOR; + void *entry; + + idt_setup_from_table(idt_table, apic_idts, ARRAY_SIZE(apic_idts), true); + + for_each_clear_bit_from(i, system_vectors, FIRST_SYSTEM_VECTOR) { + entry = irq_entries_start + 8 * (i - FIRST_EXTERNAL_VECTOR); + set_intr_gate(i, entry); + } + + for_each_clear_bit_from(i, system_vectors, NR_VECTORS) { +#ifdef CONFIG_X86_LOCAL_APIC + set_bit(i, system_vectors); + set_intr_gate(i, spurious_interrupt); +#else + entry = irq_entries_start + 8 * (i - FIRST_EXTERNAL_VECTOR); + set_intr_gate(i, entry); +#endif + } +} + +/** + * idt_setup_early_handler - Initializes the idt table with early handlers + */ +void __init idt_setup_early_handler(void) +{ + int i; + + for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) + set_intr_gate(i, early_idt_handler_array[i]); +#ifdef CONFIG_X86_32 + for ( ; i < NR_VECTORS; i++) + set_intr_gate(i, early_ignore_irq); +#endif + load_idt(&idt_descr); +} + +/** + * idt_invalidate - Invalidate interrupt descriptor table + * @addr: The virtual address of the 'invalid' IDT + */ +void idt_invalidate(void *addr) +{ + struct desc_ptr idt = { .address = (unsigned long) addr, .size = 0 }; + + load_idt(&idt); +} + +void __init update_intr_gate(unsigned int n, const void *addr) +{ + if (WARN_ON_ONCE(!test_bit(n, system_vectors))) + return; + set_intr_gate(n, addr); +} + +void alloc_intr_gate(unsigned int n, const void *addr) +{ + BUG_ON(n < FIRST_SYSTEM_VECTOR); + if (!test_and_set_bit(n, system_vectors)) + set_intr_gate(n, addr); +} diff --git a/arch/x86/kernel/io_delay.c b/arch/x86/kernel/io_delay.c index 50c89e8a95f2..805b7a341aca 100644 --- a/arch/x86/kernel/io_delay.c +++ b/arch/x86/kernel/io_delay.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * I/O delay strategies for inb_p/outb_p * @@ -58,7 +59,7 @@ static int __init dmi_io_delay_0xed_port(const struct dmi_system_id *id) * Quirk table for systems that misbehave (lock up, etc.) if port * 0x80 is used: */ -static struct dmi_system_id __initdata io_delay_0xed_port_dmi_table[] = { +static const struct dmi_system_id io_delay_0xed_port_dmi_table[] __initconst = { { .callback = dmi_io_delay_0xed_port, .ident = "Compaq Presario V6000", diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 9c3cf0944bce..3feb648781c4 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * This contains the io-permission bitmap code - written by obz, with changes * by Linus. 32/64 bits code unification by Miguel Botón. diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 4aa03c5a14c9..49cfd9fe7589 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -29,9 +29,6 @@ EXPORT_PER_CPU_SYMBOL(irq_regs); atomic_t irq_err_count; -/* Function pointer for generic interrupt vector handling */ -void (*x86_platform_ipi_callback)(void) = NULL; - /* * 'what should we do if we get a hw irq event on an illegal vector'. * each architecture has to answer this themselves. @@ -87,13 +84,13 @@ int arch_show_interrupts(struct seq_file *p, int prec) for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->icr_read_retry_count); seq_puts(p, " APIC ICR read retries\n"); -#endif if (x86_platform_ipi_callback) { seq_printf(p, "%*s: ", prec, "PLT"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->x86_platform_ipis); seq_puts(p, " Platform interrupts\n"); } +#endif #ifdef CONFIG_SMP seq_printf(p, "%*s: ", prec, "RES"); for_each_online_cpu(j) @@ -137,7 +134,7 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_puts(p, " Machine check polls\n"); #endif #if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN) - if (test_bit(HYPERVISOR_CALLBACK_VECTOR, used_vectors)) { + if (test_bit(HYPERVISOR_CALLBACK_VECTOR, system_vectors)) { seq_printf(p, "%*s: ", prec, "HYP"); for_each_online_cpu(j) seq_printf(p, "%10u ", @@ -155,6 +152,12 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_printf(p, "%10u ", irq_stats(j)->kvm_posted_intr_ipis); seq_puts(p, " Posted-interrupt notification event\n"); + seq_printf(p, "%*s: ", prec, "NPI"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", + irq_stats(j)->kvm_posted_intr_nested_ipis); + seq_puts(p, " Nested posted-interrupt event\n"); + seq_printf(p, "%*s: ", prec, "PIW"); for_each_online_cpu(j) seq_printf(p, "%10u ", @@ -177,9 +180,9 @@ u64 arch_irq_stat_cpu(unsigned int cpu) sum += irq_stats(cpu)->apic_perf_irqs; sum += irq_stats(cpu)->apic_irq_work_irqs; sum += irq_stats(cpu)->icr_read_retry_count; -#endif if (x86_platform_ipi_callback) sum += irq_stats(cpu)->x86_platform_ipis; +#endif #ifdef CONFIG_SMP sum += irq_stats(cpu)->irq_resched_count; sum += irq_stats(cpu)->irq_call_count; @@ -253,26 +256,26 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs) return 1; } +#ifdef CONFIG_X86_LOCAL_APIC +/* Function pointer for generic interrupt vector handling */ +void (*x86_platform_ipi_callback)(void) = NULL; /* * Handler for X86_PLATFORM_IPI_VECTOR. */ -void __smp_x86_platform_ipi(void) -{ - inc_irq_stat(x86_platform_ipis); - - if (x86_platform_ipi_callback) - x86_platform_ipi_callback(); -} - __visible void __irq_entry smp_x86_platform_ipi(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); entering_ack_irq(); - __smp_x86_platform_ipi(); + trace_x86_platform_ipi_entry(X86_PLATFORM_IPI_VECTOR); + inc_irq_stat(x86_platform_ipis); + if (x86_platform_ipi_callback) + x86_platform_ipi_callback(); + trace_x86_platform_ipi_exit(X86_PLATFORM_IPI_VECTOR); exiting_irq(); set_irq_regs(old_regs); } +#endif #ifdef CONFIG_HAVE_KVM static void dummy_handler(void) {} @@ -313,122 +316,23 @@ __visible void smp_kvm_posted_intr_wakeup_ipi(struct pt_regs *regs) exiting_irq(); set_irq_regs(old_regs); } -#endif -__visible void __irq_entry smp_trace_x86_platform_ipi(struct pt_regs *regs) +/* + * Handler for POSTED_INTERRUPT_NESTED_VECTOR. + */ +__visible void smp_kvm_posted_intr_nested_ipi(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); entering_ack_irq(); - trace_x86_platform_ipi_entry(X86_PLATFORM_IPI_VECTOR); - __smp_x86_platform_ipi(); - trace_x86_platform_ipi_exit(X86_PLATFORM_IPI_VECTOR); + inc_irq_stat(kvm_posted_intr_nested_ipis); exiting_irq(); set_irq_regs(old_regs); } +#endif -EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq); #ifdef CONFIG_HOTPLUG_CPU - -/* These two declarations are only used in check_irq_vectors_for_cpu_disable() - * below, which is protected by stop_machine(). Putting them on the stack - * results in a stack frame overflow. Dynamically allocating could result in a - * failure so declare these two cpumasks as global. - */ -static struct cpumask affinity_new, online_new; - -/* - * This cpu is going to be removed and its vectors migrated to the remaining - * online cpus. Check to see if there are enough vectors in the remaining cpus. - * This function is protected by stop_machine(). - */ -int check_irq_vectors_for_cpu_disable(void) -{ - unsigned int this_cpu, vector, this_count, count; - struct irq_desc *desc; - struct irq_data *data; - int cpu; - - this_cpu = smp_processor_id(); - cpumask_copy(&online_new, cpu_online_mask); - cpumask_clear_cpu(this_cpu, &online_new); - - this_count = 0; - for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { - desc = __this_cpu_read(vector_irq[vector]); - if (IS_ERR_OR_NULL(desc)) - continue; - /* - * Protect against concurrent action removal, affinity - * changes etc. - */ - raw_spin_lock(&desc->lock); - data = irq_desc_get_irq_data(desc); - cpumask_copy(&affinity_new, - irq_data_get_affinity_mask(data)); - cpumask_clear_cpu(this_cpu, &affinity_new); - - /* Do not count inactive or per-cpu irqs. */ - if (!irq_desc_has_action(desc) || irqd_is_per_cpu(data)) { - raw_spin_unlock(&desc->lock); - continue; - } - - raw_spin_unlock(&desc->lock); - /* - * A single irq may be mapped to multiple cpu's - * vector_irq[] (for example IOAPIC cluster mode). In - * this case we have two possibilities: - * - * 1) the resulting affinity mask is empty; that is - * this the down'd cpu is the last cpu in the irq's - * affinity mask, or - * - * 2) the resulting affinity mask is no longer a - * subset of the online cpus but the affinity mask is - * not zero; that is the down'd cpu is the last online - * cpu in a user set affinity mask. - */ - if (cpumask_empty(&affinity_new) || - !cpumask_subset(&affinity_new, &online_new)) - this_count++; - } - /* No need to check any further. */ - if (!this_count) - return 0; - - count = 0; - for_each_online_cpu(cpu) { - if (cpu == this_cpu) - continue; - /* - * We scan from FIRST_EXTERNAL_VECTOR to first system - * vector. If the vector is marked in the used vectors - * bitmap or an irq is assigned to it, we don't count - * it as available. - * - * As this is an inaccurate snapshot anyway, we can do - * this w/o holding vector_lock. - */ - for (vector = FIRST_EXTERNAL_VECTOR; - vector < first_system_vector; vector++) { - if (!test_bit(vector, used_vectors) && - IS_ERR_OR_NULL(per_cpu(vector_irq, cpu)[vector])) { - if (++count == this_count) - return 0; - } - } - } - - if (count < this_count) { - pr_warn("CPU %d disable failed: CPU has %u vectors assigned and there are only %u available.\n", - this_cpu, this_count, count); - return -ERANGE; - } - return 0; -} - /* A cpu has been removed from cpu_online_mask. Reset irq affinities. */ void fixup_irqs(void) { diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 1f38d9a4d9de..a83b3346a0e1 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar * @@ -64,7 +65,7 @@ static void call_on_stack(void *func, void *stack) static inline void *current_stack(void) { - return (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1)); + return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1)); } static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc) @@ -88,7 +89,7 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc) /* Save the next esp at the bottom of the stack */ prev_esp = (u32 *)irqstk; - *prev_esp = current_stack_pointer(); + *prev_esp = current_stack_pointer; if (unlikely(overflow)) call_on_stack(print_stack_overflow, isp); @@ -139,7 +140,7 @@ void do_softirq_own_stack(void) /* Push the previous esp onto the stack */ prev_esp = (u32 *)irqstk; - *prev_esp = current_stack_pointer(); + *prev_esp = current_stack_pointer; call_on_stack(__do_softirq, isp); } diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 3be74fbdeff2..020efbf5786b 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar * diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c index 275487872be2..80bee7695a20 100644 --- a/arch/x86/kernel/irq_work.c +++ b/arch/x86/kernel/irq_work.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * x86 specific code for irq_work * @@ -11,35 +12,23 @@ #include <asm/trace/irq_vectors.h> #include <linux/interrupt.h> -static inline void __smp_irq_work_interrupt(void) -{ - inc_irq_stat(apic_irq_work_irqs); - irq_work_run(); -} - +#ifdef CONFIG_X86_LOCAL_APIC __visible void __irq_entry smp_irq_work_interrupt(struct pt_regs *regs) { ipi_entering_ack_irq(); - __smp_irq_work_interrupt(); - exiting_irq(); -} - -__visible void __irq_entry smp_trace_irq_work_interrupt(struct pt_regs *regs) -{ - ipi_entering_ack_irq(); trace_irq_work_entry(IRQ_WORK_VECTOR); - __smp_irq_work_interrupt(); + inc_irq_stat(apic_irq_work_irqs); + irq_work_run(); trace_irq_work_exit(IRQ_WORK_VECTOR); exiting_irq(); } void arch_irq_work_raise(void) { -#ifdef CONFIG_X86_LOCAL_APIC if (!arch_irq_work_has_interrupt()) return; apic->send_IPI_self(IRQ_WORK_VECTOR); apic_wait_icr_idle(); -#endif } +#endif diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 7468c6987547..8da3e909e967 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/linkage.h> #include <linux/errno.h> #include <linux/signal.h> @@ -55,26 +56,11 @@ DEFINE_PER_CPU(vector_irq_t, vector_irq) = { [0 ... NR_VECTORS - 1] = VECTOR_UNUSED, }; -int vector_used_by_percpu_irq(unsigned int vector) -{ - int cpu; - - for_each_online_cpu(cpu) { - if (!IS_ERR_OR_NULL(per_cpu(vector_irq, cpu)[vector])) - return 1; - } - - return 0; -} - void __init init_ISA_irqs(void) { struct irq_chip *chip = legacy_pic->chip; int i; -#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC) - init_bsp_APIC(); -#endif legacy_pic->init(0); for (i = 0; i < nr_legacy_irqs(); i++) @@ -99,98 +85,13 @@ void __init init_IRQ(void) x86_init.irqs.intr_init(); } -static void __init smp_intr_init(void) -{ -#ifdef CONFIG_SMP - /* - * The reschedule interrupt is a CPU-to-CPU reschedule-helper - * IPI, driven by wakeup. - */ - alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt); - - /* IPI for generic function call */ - alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt); - - /* IPI for generic single function call */ - alloc_intr_gate(CALL_FUNCTION_SINGLE_VECTOR, - call_function_single_interrupt); - - /* Low priority IPI to cleanup after moving an irq */ - set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt); - set_bit(IRQ_MOVE_CLEANUP_VECTOR, used_vectors); - - /* IPI used for rebooting/stopping */ - alloc_intr_gate(REBOOT_VECTOR, reboot_interrupt); -#endif /* CONFIG_SMP */ -} - -static void __init apic_intr_init(void) -{ - smp_intr_init(); - -#ifdef CONFIG_X86_THERMAL_VECTOR - alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt); -#endif -#ifdef CONFIG_X86_MCE_THRESHOLD - alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt); -#endif - -#ifdef CONFIG_X86_MCE_AMD - alloc_intr_gate(DEFERRED_ERROR_VECTOR, deferred_error_interrupt); -#endif - -#ifdef CONFIG_X86_LOCAL_APIC - /* self generated IPI for local APIC timer */ - alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt); - - /* IPI for X86 platform specific use */ - alloc_intr_gate(X86_PLATFORM_IPI_VECTOR, x86_platform_ipi); -#ifdef CONFIG_HAVE_KVM - /* IPI for KVM to deliver posted interrupt */ - alloc_intr_gate(POSTED_INTR_VECTOR, kvm_posted_intr_ipi); - /* IPI for KVM to deliver interrupt to wake up tasks */ - alloc_intr_gate(POSTED_INTR_WAKEUP_VECTOR, kvm_posted_intr_wakeup_ipi); -#endif - - /* IPI vectors for APIC spurious and error interrupts */ - alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt); - alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt); - - /* IRQ work interrupts: */ -# ifdef CONFIG_IRQ_WORK - alloc_intr_gate(IRQ_WORK_VECTOR, irq_work_interrupt); -# endif - -#endif -} - void __init native_init_IRQ(void) { - int i; - /* Execute any quirks before the call gates are initialised: */ x86_init.irqs.pre_vector_init(); - apic_intr_init(); - - /* - * Cover the whole vector space, no vector can escape - * us. (some of these will be overridden and become - * 'special' SMP interrupts) - */ - i = FIRST_EXTERNAL_VECTOR; -#ifndef CONFIG_X86_LOCAL_APIC -#define first_system_vector NR_VECTORS -#endif - for_each_clear_bit_from(i, used_vectors, first_system_vector) { - /* IA32_SYSCALL_VECTOR could be used in trap_init already. */ - set_intr_gate(i, irq_entries_start + - 8 * (i - FIRST_EXTERNAL_VECTOR)); - } -#ifdef CONFIG_X86_LOCAL_APIC - for_each_clear_bit_from(i, used_vectors, NR_VECTORS) - set_intr_gate(i, spurious_interrupt); -#endif + idt_setup_apic_and_irq_gates(); + lapic_assign_system_vectors(); if (!acpi_ioapic && !of_ioapic && nr_legacy_irqs()) setup_irq(2, &irq2); diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index ab4f491da2a9..e56c95be2808 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * jump label x86 support * diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c index 38b64587b31b..fd6f8fbbe6f2 100644 --- a/arch/x86/kernel/kdebugfs.c +++ b/arch/x86/kernel/kdebugfs.c @@ -33,7 +33,6 @@ static ssize_t setup_data_read(struct file *file, char __user *user_buf, struct setup_data_node *node = file->private_data; unsigned long remain; loff_t pos = *ppos; - struct page *pg; void *p; u64 pa; @@ -47,18 +46,13 @@ static ssize_t setup_data_read(struct file *file, char __user *user_buf, count = node->len - pos; pa = node->paddr + sizeof(struct setup_data) + pos; - pg = pfn_to_page((pa + count - 1) >> PAGE_SHIFT); - if (PageHighMem(pg)) { - p = ioremap_cache(pa, count); - if (!p) - return -ENXIO; - } else - p = __va(pa); + p = memremap(pa, count, MEMREMAP_WB); + if (!p) + return -ENOMEM; remain = copy_to_user(user_buf, p, count); - if (PageHighMem(pg)) - iounmap(p); + memunmap(p); if (remain) return -EFAULT; @@ -109,7 +103,6 @@ static int __init create_setup_data_nodes(struct dentry *parent) struct setup_data *data; int error; struct dentry *d; - struct page *pg; u64 pa_data; int no = 0; @@ -126,16 +119,12 @@ static int __init create_setup_data_nodes(struct dentry *parent) goto err_dir; } - pg = pfn_to_page((pa_data+sizeof(*data)-1) >> PAGE_SHIFT); - if (PageHighMem(pg)) { - data = ioremap_cache(pa_data, sizeof(*data)); - if (!data) { - kfree(node); - error = -ENXIO; - goto err_dir; - } - } else - data = __va(pa_data); + data = memremap(pa_data, sizeof(*data), MEMREMAP_WB); + if (!data) { + kfree(node); + error = -ENOMEM; + goto err_dir; + } node->paddr = pa_data; node->type = data->type; @@ -143,8 +132,7 @@ static int __init create_setup_data_nodes(struct dentry *parent) error = create_setup_data_node(d, no, node); pa_data = data->next; - if (PageHighMem(pg)) - iounmap(data); + memunmap(data); if (error) goto err_dir; no++; diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h index db2182d63ed0..ae38dccf0c8f 100644 --- a/arch/x86/kernel/kprobes/common.h +++ b/arch/x86/kernel/kprobes/common.h @@ -1,8 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __X86_KERNEL_KPROBES_COMMON_H #define __X86_KERNEL_KPROBES_COMMON_H /* Kprobes and Optprobes common header */ +#include <asm/asm.h> + +#ifdef CONFIG_FRAME_POINTER +# define SAVE_RBP_STRING " push %" _ASM_BP "\n" \ + " mov %" _ASM_SP ", %" _ASM_BP "\n" +#else +# define SAVE_RBP_STRING " push %" _ASM_BP "\n" +#endif + #ifdef CONFIG_X86_64 #define SAVE_REGS_STRING \ /* Skip cs, ip, orig_ax. */ \ @@ -17,7 +27,7 @@ " pushq %r10\n" \ " pushq %r11\n" \ " pushq %rbx\n" \ - " pushq %rbp\n" \ + SAVE_RBP_STRING \ " pushq %r12\n" \ " pushq %r13\n" \ " pushq %r14\n" \ @@ -48,7 +58,7 @@ " pushl %es\n" \ " pushl %ds\n" \ " pushl %eax\n" \ - " pushl %ebp\n" \ + SAVE_RBP_STRING \ " pushl %edi\n" \ " pushl %esi\n" \ " pushl %edx\n" \ @@ -75,11 +85,11 @@ extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf, * Copy an instruction and adjust the displacement if the instruction * uses the %rip-relative addressing mode. */ -extern int __copy_instruction(u8 *dest, u8 *src, struct insn *insn); +extern int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn); /* Generate a relative-jump/call instruction */ -extern void synthesize_reljump(void *from, void *to); -extern void synthesize_relcall(void *from, void *to); +extern void synthesize_reljump(void *dest, void *from, void *to); +extern void synthesize_relcall(void *dest, void *from, void *to); #ifdef CONFIG_OPTPROBES extern int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter); diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 6b877807598b..bd36f3c33cd0 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -119,29 +119,29 @@ struct kretprobe_blackpoint kretprobe_blacklist[] = { const int kretprobe_blacklist_size = ARRAY_SIZE(kretprobe_blacklist); static nokprobe_inline void -__synthesize_relative_insn(void *from, void *to, u8 op) +__synthesize_relative_insn(void *dest, void *from, void *to, u8 op) { struct __arch_relative_insn { u8 op; s32 raddr; } __packed *insn; - insn = (struct __arch_relative_insn *)from; + insn = (struct __arch_relative_insn *)dest; insn->raddr = (s32)((long)(to) - ((long)(from) + 5)); insn->op = op; } /* Insert a jump instruction at address 'from', which jumps to address 'to'.*/ -void synthesize_reljump(void *from, void *to) +void synthesize_reljump(void *dest, void *from, void *to) { - __synthesize_relative_insn(from, to, RELATIVEJUMP_OPCODE); + __synthesize_relative_insn(dest, from, to, RELATIVEJUMP_OPCODE); } NOKPROBE_SYMBOL(synthesize_reljump); /* Insert a call instruction at address 'from', which calls address 'to'.*/ -void synthesize_relcall(void *from, void *to) +void synthesize_relcall(void *dest, void *from, void *to) { - __synthesize_relative_insn(from, to, RELATIVECALL_OPCODE); + __synthesize_relative_insn(dest, from, to, RELATIVECALL_OPCODE); } NOKPROBE_SYMBOL(synthesize_relcall); @@ -346,10 +346,11 @@ static int is_IF_modifier(kprobe_opcode_t *insn) /* * Copy an instruction with recovering modified instruction by kprobes * and adjust the displacement if the instruction uses the %rip-relative - * addressing mode. + * addressing mode. Note that since @real will be the final place of copied + * instruction, displacement must be adjust by @real, not @dest. * This returns the length of copied instruction, or 0 if it has an error. */ -int __copy_instruction(u8 *dest, u8 *src, struct insn *insn) +int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn) { kprobe_opcode_t buf[MAX_INSN_SIZE]; unsigned long recovered_insn = @@ -387,11 +388,11 @@ int __copy_instruction(u8 *dest, u8 *src, struct insn *insn) * have given. */ newdisp = (u8 *) src + (s64) insn->displacement.value - - (u8 *) dest; + - (u8 *) real; if ((s64) (s32) newdisp != newdisp) { pr_err("Kprobes error: new displacement does not fit into s32 (%llx)\n", newdisp); pr_err("\tSrc: %p, Dest: %p, old disp: %x\n", - src, dest, insn->displacement.value); + src, real, insn->displacement.value); return 0; } disp = (u8 *) dest + insn_offset_displacement(insn); @@ -402,20 +403,38 @@ int __copy_instruction(u8 *dest, u8 *src, struct insn *insn) } /* Prepare reljump right after instruction to boost */ -static void prepare_boost(struct kprobe *p, struct insn *insn) +static int prepare_boost(kprobe_opcode_t *buf, struct kprobe *p, + struct insn *insn) { + int len = insn->length; + if (can_boost(insn, p->addr) && - MAX_INSN_SIZE - insn->length >= RELATIVEJUMP_SIZE) { + MAX_INSN_SIZE - len >= RELATIVEJUMP_SIZE) { /* * These instructions can be executed directly if it * jumps back to correct address. */ - synthesize_reljump(p->ainsn.insn + insn->length, + synthesize_reljump(buf + len, p->ainsn.insn + len, p->addr + insn->length); + len += RELATIVEJUMP_SIZE; p->ainsn.boostable = true; } else { p->ainsn.boostable = false; } + + return len; +} + +/* Make page to RO mode when allocate it */ +void *alloc_insn_page(void) +{ + void *page; + + page = module_alloc(PAGE_SIZE); + if (page) + set_memory_ro((unsigned long)page & PAGE_MASK, 1); + + return page; } /* Recover page to RW mode before releasing it */ @@ -429,12 +448,11 @@ void free_insn_page(void *page) static int arch_copy_kprobe(struct kprobe *p) { struct insn insn; + kprobe_opcode_t buf[MAX_INSN_SIZE]; int len; - set_memory_rw((unsigned long)p->ainsn.insn & PAGE_MASK, 1); - /* Copy an instruction with recovering if other optprobe modifies it.*/ - len = __copy_instruction(p->ainsn.insn, p->addr, &insn); + len = __copy_instruction(buf, p->addr, p->ainsn.insn, &insn); if (!len) return -EINVAL; @@ -442,21 +460,24 @@ static int arch_copy_kprobe(struct kprobe *p) * __copy_instruction can modify the displacement of the instruction, * but it doesn't affect boostable check. */ - prepare_boost(p, &insn); - - set_memory_ro((unsigned long)p->ainsn.insn & PAGE_MASK, 1); + len = prepare_boost(buf, p, &insn); /* Check whether the instruction modifies Interrupt Flag or not */ - p->ainsn.if_modifier = is_IF_modifier(p->ainsn.insn); + p->ainsn.if_modifier = is_IF_modifier(buf); /* Also, displacement change doesn't affect the first byte */ - p->opcode = p->ainsn.insn[0]; + p->opcode = buf[0]; + + /* OK, write back the instruction(s) into ROX insn buffer */ + text_poke(p->ainsn.insn, buf, len); return 0; } int arch_prepare_kprobe(struct kprobe *p) { + int ret; + if (alternatives_text_reserved(p->addr, p->addr)) return -EINVAL; @@ -467,7 +488,13 @@ int arch_prepare_kprobe(struct kprobe *p) if (!p->ainsn.insn) return -ENOMEM; - return arch_copy_kprobe(p); + ret = arch_copy_kprobe(p); + if (ret) { + free_insn_slot(p->ainsn.insn, 0); + p->ainsn.insn = NULL; + } + + return ret; } void arch_arm_kprobe(struct kprobe *p) @@ -1072,8 +1099,6 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) * raw stack chunk with redzones: */ __memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr, MIN_STACK_SIZE(addr)); - regs->flags &= ~X86_EFLAGS_IF; - trace_hardirqs_off(); regs->ip = (unsigned long)(jp->entry); /* diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c index 041f7b6dfa0f..8dc0161cec8f 100644 --- a/arch/x86/kernel/kprobes/ftrace.c +++ b/arch/x86/kernel/kprobes/ftrace.c @@ -26,7 +26,7 @@ #include "common.h" static nokprobe_inline -int __skip_singlestep(struct kprobe *p, struct pt_regs *regs, +void __skip_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb, unsigned long orig_ip) { /* @@ -41,33 +41,31 @@ int __skip_singlestep(struct kprobe *p, struct pt_regs *regs, __this_cpu_write(current_kprobe, NULL); if (orig_ip) regs->ip = orig_ip; - return 1; } int skip_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) { - if (kprobe_ftrace(p)) - return __skip_singlestep(p, regs, kcb, 0); - else - return 0; + if (kprobe_ftrace(p)) { + __skip_singlestep(p, regs, kcb, 0); + preempt_enable_no_resched(); + return 1; + } + return 0; } NOKPROBE_SYMBOL(skip_singlestep); -/* Ftrace callback handler for kprobes */ +/* Ftrace callback handler for kprobes -- called under preepmt disabed */ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct pt_regs *regs) { struct kprobe *p; struct kprobe_ctlblk *kcb; - unsigned long flags; - - /* Disable irq for emulating a breakpoint and avoiding preempt */ - local_irq_save(flags); + /* Preempt is disabled by ftrace */ p = get_kprobe((kprobe_opcode_t *)ip); if (unlikely(!p) || kprobe_disabled(p)) - goto end; + return; kcb = get_kprobe_ctlblk(); if (kprobe_running()) { @@ -77,17 +75,19 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, /* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */ regs->ip = ip + sizeof(kprobe_opcode_t); + /* To emulate trap based kprobes, preempt_disable here */ + preempt_disable(); __this_cpu_write(current_kprobe, p); kcb->kprobe_status = KPROBE_HIT_ACTIVE; - if (!p->pre_handler || !p->pre_handler(p, regs)) + if (!p->pre_handler || !p->pre_handler(p, regs)) { __skip_singlestep(p, regs, kcb, orig_ip); + preempt_enable_no_resched(); + } /* * If pre_handler returns !0, it sets regs->ip and - * resets current kprobe. + * resets current kprobe, and keep preempt count +1. */ } -end: - local_irq_restore(flags); } NOKPROBE_SYMBOL(kprobe_ftrace_handler); diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 69ea0bc1cfa3..e941136e24d8 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -39,6 +39,7 @@ #include <asm/insn.h> #include <asm/debugreg.h> #include <asm/set_memory.h> +#include <asm/sections.h> #include "common.h" @@ -141,11 +142,11 @@ void optprobe_template_func(void); STACK_FRAME_NON_STANDARD(optprobe_template_func); #define TMPL_MOVE_IDX \ - ((long)&optprobe_template_val - (long)&optprobe_template_entry) + ((long)optprobe_template_val - (long)optprobe_template_entry) #define TMPL_CALL_IDX \ - ((long)&optprobe_template_call - (long)&optprobe_template_entry) + ((long)optprobe_template_call - (long)optprobe_template_entry) #define TMPL_END_IDX \ - ((long)&optprobe_template_end - (long)&optprobe_template_entry) + ((long)optprobe_template_end - (long)optprobe_template_entry) #define INT3_SIZE sizeof(kprobe_opcode_t) @@ -153,17 +154,15 @@ STACK_FRAME_NON_STANDARD(optprobe_template_func); static void optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) { - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - unsigned long flags; - /* This is possible if op is under delayed unoptimizing */ if (kprobe_disabled(&op->kp)) return; - local_irq_save(flags); + preempt_disable(); if (kprobe_running()) { kprobes_inc_nmissed_count(&op->kp); } else { + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); /* Save skipped registers */ #ifdef CONFIG_X86_64 regs->cs = __KERNEL_CS; @@ -179,17 +178,17 @@ optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) opt_pre_handler(&op->kp, regs); __this_cpu_write(current_kprobe, NULL); } - local_irq_restore(flags); + preempt_enable_no_resched(); } NOKPROBE_SYMBOL(optimized_callback); -static int copy_optimized_instructions(u8 *dest, u8 *src) +static int copy_optimized_instructions(u8 *dest, u8 *src, u8 *real) { struct insn insn; int len = 0, ret; while (len < RELATIVEJUMP_SIZE) { - ret = __copy_instruction(dest + len, src + len, &insn); + ret = __copy_instruction(dest + len, src + len, real, &insn); if (!ret || !can_boost(&insn, src + len)) return -EINVAL; len += ret; @@ -251,10 +250,12 @@ static int can_optimize(unsigned long paddr) /* * Do not optimize in the entry code due to the unstable - * stack handling. + * stack handling and registers setup. */ - if ((paddr >= (unsigned long)__entry_text_start) && - (paddr < (unsigned long)__entry_text_end)) + if (((paddr >= (unsigned long)__entry_text_start) && + (paddr < (unsigned long)__entry_text_end)) || + ((paddr >= (unsigned long)__irqentry_text_start) && + (paddr < (unsigned long)__irqentry_text_end))) return 0; /* Check there is enough space for a relative jump. */ @@ -340,57 +341,66 @@ void arch_remove_optimized_kprobe(struct optimized_kprobe *op) int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *__unused) { - u8 *buf; - int ret; + u8 *buf = NULL, *slot; + int ret, len; long rel; if (!can_optimize((unsigned long)op->kp.addr)) return -EILSEQ; - op->optinsn.insn = get_optinsn_slot(); - if (!op->optinsn.insn) + buf = kzalloc(MAX_OPTINSN_SIZE, GFP_KERNEL); + if (!buf) return -ENOMEM; + op->optinsn.insn = slot = get_optinsn_slot(); + if (!slot) { + ret = -ENOMEM; + goto out; + } + /* * Verify if the address gap is in 2GB range, because this uses * a relative jump. */ - rel = (long)op->optinsn.insn - (long)op->kp.addr + RELATIVEJUMP_SIZE; + rel = (long)slot - (long)op->kp.addr + RELATIVEJUMP_SIZE; if (abs(rel) > 0x7fffffff) { - __arch_remove_optimized_kprobe(op, 0); - return -ERANGE; + ret = -ERANGE; + goto err; } - buf = (u8 *)op->optinsn.insn; - set_memory_rw((unsigned long)buf & PAGE_MASK, 1); + /* Copy arch-dep-instance from template */ + memcpy(buf, optprobe_template_entry, TMPL_END_IDX); /* Copy instructions into the out-of-line buffer */ - ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr); - if (ret < 0) { - __arch_remove_optimized_kprobe(op, 0); - return ret; - } + ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr, + slot + TMPL_END_IDX); + if (ret < 0) + goto err; op->optinsn.size = ret; - - /* Copy arch-dep-instance from template */ - memcpy(buf, &optprobe_template_entry, TMPL_END_IDX); + len = TMPL_END_IDX + op->optinsn.size; /* Set probe information */ synthesize_set_arg1(buf + TMPL_MOVE_IDX, (unsigned long)op); /* Set probe function call */ - synthesize_relcall(buf + TMPL_CALL_IDX, optimized_callback); + synthesize_relcall(buf + TMPL_CALL_IDX, + slot + TMPL_CALL_IDX, optimized_callback); /* Set returning jmp instruction at the tail of out-of-line buffer */ - synthesize_reljump(buf + TMPL_END_IDX + op->optinsn.size, + synthesize_reljump(buf + len, slot + len, (u8 *)op->kp.addr + op->optinsn.size); - - set_memory_ro((unsigned long)buf & PAGE_MASK, 1); - - flush_icache_range((unsigned long) buf, - (unsigned long) buf + TMPL_END_IDX + - op->optinsn.size + RELATIVEJUMP_SIZE); - return 0; + len += RELATIVEJUMP_SIZE; + + /* We have to use text_poke for instuction buffer because it is RO */ + text_poke(slot, buf, len); + ret = 0; +out: + kfree(buf); + return ret; + +err: + __arch_remove_optimized_kprobe(op, 0); + goto out; } /* diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c index 4afc67f5facc..8c1cc08f514f 100644 --- a/arch/x86/kernel/ksysfs.c +++ b/arch/x86/kernel/ksysfs.c @@ -16,8 +16,8 @@ #include <linux/stat.h> #include <linux/slab.h> #include <linux/mm.h> +#include <linux/io.h> -#include <asm/io.h> #include <asm/setup.h> static ssize_t version_show(struct kobject *kobj, @@ -55,7 +55,7 @@ static struct bin_attribute *boot_params_data_attrs[] = { NULL, }; -static struct attribute_group boot_params_attr_group = { +static const struct attribute_group boot_params_attr_group = { .attrs = boot_params_version_attrs, .bin_attrs = boot_params_data_attrs, }; @@ -79,12 +79,12 @@ static int get_setup_data_paddr(int nr, u64 *paddr) *paddr = pa_data; return 0; } - data = ioremap_cache(pa_data, sizeof(*data)); + data = memremap(pa_data, sizeof(*data), MEMREMAP_WB); if (!data) return -ENOMEM; pa_data = data->next; - iounmap(data); + memunmap(data); i++; } return -EINVAL; @@ -97,17 +97,17 @@ static int __init get_setup_data_size(int nr, size_t *size) u64 pa_data = boot_params.hdr.setup_data; while (pa_data) { - data = ioremap_cache(pa_data, sizeof(*data)); + data = memremap(pa_data, sizeof(*data), MEMREMAP_WB); if (!data) return -ENOMEM; if (nr == i) { *size = data->len; - iounmap(data); + memunmap(data); return 0; } pa_data = data->next; - iounmap(data); + memunmap(data); i++; } return -EINVAL; @@ -127,12 +127,12 @@ static ssize_t type_show(struct kobject *kobj, ret = get_setup_data_paddr(nr, &paddr); if (ret) return ret; - data = ioremap_cache(paddr, sizeof(*data)); + data = memremap(paddr, sizeof(*data), MEMREMAP_WB); if (!data) return -ENOMEM; ret = sprintf(buf, "0x%x\n", data->type); - iounmap(data); + memunmap(data); return ret; } @@ -154,7 +154,7 @@ static ssize_t setup_data_data_read(struct file *fp, ret = get_setup_data_paddr(nr, &paddr); if (ret) return ret; - data = ioremap_cache(paddr, sizeof(*data)); + data = memremap(paddr, sizeof(*data), MEMREMAP_WB); if (!data) return -ENOMEM; @@ -170,15 +170,15 @@ static ssize_t setup_data_data_read(struct file *fp, goto out; ret = count; - p = ioremap_cache(paddr + sizeof(*data), data->len); + p = memremap(paddr + sizeof(*data), data->len, MEMREMAP_WB); if (!p) { ret = -ENOMEM; goto out; } memcpy(buf, p + off, count); - iounmap(p); + memunmap(p); out: - iounmap(data); + memunmap(data); return ret; } @@ -202,7 +202,7 @@ static struct bin_attribute *setup_data_data_attrs[] = { NULL, }; -static struct attribute_group setup_data_attr_group = { +static const struct attribute_group setup_data_attr_group = { .attrs = setup_data_type_attrs, .bin_attrs = setup_data_data_attrs, }; @@ -250,13 +250,13 @@ static int __init get_setup_data_total_num(u64 pa_data, int *nr) *nr = 0; while (pa_data) { *nr += 1; - data = ioremap_cache(pa_data, sizeof(*data)); + data = memremap(pa_data, sizeof(*data), MEMREMAP_WB); if (!data) { ret = -ENOMEM; goto out; } pa_data = data->next; - iounmap(data); + memunmap(data); } out: @@ -299,7 +299,7 @@ static int __init create_setup_data_nodes(struct kobject *parent) return 0; out_clean_nodes: - for (j = i - 1; j > 0; j--) + for (j = i - 1; j >= 0; j--) cleanup_setup_data_node(*(kobjp + j)); kfree(kobjp); out_setup_data_kobj: diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 71c17a5be983..b40ffbf156c1 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -75,8 +75,8 @@ static int parse_no_kvmclock_vsyscall(char *arg) early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall); -static DEFINE_PER_CPU(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64); -static DEFINE_PER_CPU(struct kvm_steal_time, steal_time) __aligned(64); +static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64); +static DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64); static int has_steal_clock = 0; /* @@ -117,7 +117,11 @@ static struct kvm_task_sleep_node *_find_apf_task(struct kvm_task_sleep_head *b, return NULL; } -void kvm_async_pf_task_wait(u32 token) +/* + * @interrupt_kernel: Is this called from a routine which interrupts the kernel + * (other than user space)? + */ +void kvm_async_pf_task_wait(u32 token, int interrupt_kernel) { u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS); struct kvm_task_sleep_head *b = &async_pf_sleepers[key]; @@ -140,7 +144,10 @@ void kvm_async_pf_task_wait(u32 token) n.token = token; n.cpu = smp_processor_id(); - n.halted = is_idle_task(current) || preempt_count() > 1; + n.halted = is_idle_task(current) || + (IS_ENABLED(CONFIG_PREEMPT_COUNT) + ? preempt_count() > 1 || rcu_preempt_depth() + : interrupt_kernel); init_swait_queue_head(&n.wq); hlist_add_head(&n.link, &b->list); raw_spin_unlock(&b->lock); @@ -151,6 +158,8 @@ void kvm_async_pf_task_wait(u32 token) if (hlist_unhashed(&n.link)) break; + rcu_irq_exit(); + if (!n.halted) { local_irq_enable(); schedule(); @@ -159,11 +168,11 @@ void kvm_async_pf_task_wait(u32 token) /* * We cannot reschedule. So halt. */ - rcu_irq_exit(); native_safe_halt(); local_irq_disable(); - rcu_irq_enter(); } + + rcu_irq_enter(); } if (!n.halted) finish_swait(&n.wq, &wait); @@ -178,7 +187,7 @@ static void apf_task_wake_one(struct kvm_task_sleep_node *n) hlist_del_init(&n->link); if (n->halted) smp_send_reschedule(n->cpu); - else if (swait_active(&n->wq)) + else if (swq_has_sleeper(&n->wq)) swake_up(&n->wq); } @@ -261,12 +270,12 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code) switch (kvm_read_and_reset_pf_reason()) { default: - trace_do_page_fault(regs, error_code); + do_page_fault(regs, error_code); break; case KVM_PV_REASON_PAGE_NOT_PRESENT: /* page is swapped out by the host. */ prev_state = exception_enter(); - kvm_async_pf_task_wait((u32)read_cr2()); + kvm_async_pf_task_wait((u32)read_cr2(), !user_mode(regs)); exception_exit(prev_state); break; case KVM_PV_REASON_PAGE_READY: @@ -303,7 +312,7 @@ static void kvm_register_steal_time(void) cpu, (unsigned long long) slow_virt_to_phys(st)); } -static DEFINE_PER_CPU(unsigned long, kvm_apic_eoi) = KVM_PV_EOI_DISABLED; +static DEFINE_PER_CPU_DECRYPTED(unsigned long, kvm_apic_eoi) = KVM_PV_EOI_DISABLED; static notrace void kvm_guest_apic_eoi_write(u32 reg, u32 val) { @@ -417,9 +426,42 @@ void kvm_disable_steal_time(void) wrmsr(MSR_KVM_STEAL_TIME, 0, 0); } +static inline void __set_percpu_decrypted(void *ptr, unsigned long size) +{ + early_set_memory_decrypted((unsigned long) ptr, size); +} + +/* + * Iterate through all possible CPUs and map the memory region pointed + * by apf_reason, steal_time and kvm_apic_eoi as decrypted at once. + * + * Note: we iterate through all possible CPUs to ensure that CPUs + * hotplugged will have their per-cpu variable already mapped as + * decrypted. + */ +static void __init sev_map_percpu_data(void) +{ + int cpu; + + if (!sev_active()) + return; + + for_each_possible_cpu(cpu) { + __set_percpu_decrypted(&per_cpu(apf_reason, cpu), sizeof(apf_reason)); + __set_percpu_decrypted(&per_cpu(steal_time, cpu), sizeof(steal_time)); + __set_percpu_decrypted(&per_cpu(kvm_apic_eoi, cpu), sizeof(kvm_apic_eoi)); + } +} + #ifdef CONFIG_SMP static void __init kvm_smp_prepare_boot_cpu(void) { + /* + * Map the per-cpu variables as decrypted before kvm_guest_cpu_init() + * shares the guest physical address with the hypervisor. + */ + sev_map_percpu_data(); + kvm_guest_cpu_init(); native_smp_prepare_boot_cpu(); kvm_spinlock_init(); @@ -453,10 +495,10 @@ static int kvm_cpu_down_prepare(unsigned int cpu) static void __init kvm_apf_trap_init(void) { - set_intr_gate(14, async_page_fault); + update_intr_gate(X86_TRAP_PF, async_page_fault); } -void __init kvm_guest_init(void) +static void __init kvm_guest_init(void) { int i; @@ -487,6 +529,7 @@ void __init kvm_guest_init(void) kvm_cpu_online, kvm_cpu_down_prepare) < 0) pr_err("kvm_guest: Failed to install cpu hotplug callbacks\n"); #else + sev_map_percpu_data(); kvm_guest_cpu_init(); #endif @@ -535,12 +578,13 @@ static uint32_t __init kvm_detect(void) return kvm_cpuid_base(); } -const struct hypervisor_x86 x86_hyper_kvm __refconst = { +const __initconst struct hypervisor_x86 x86_hyper_kvm = { .name = "KVM", .detect = kvm_detect, - .x2apic_available = kvm_para_available, + .type = X86_HYPER_KVM, + .init.guest_late_init = kvm_guest_init, + .init.x2apic_available = kvm_para_available, }; -EXPORT_SYMBOL_GPL(x86_hyper_kvm); static __init int activate_jump_labels(void) { diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index d88967659098..8b26c9e01cc4 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -27,6 +27,7 @@ #include <linux/sched.h> #include <linux/sched/clock.h> +#include <asm/mem_encrypt.h> #include <asm/x86_init.h> #include <asm/reboot.h> #include <asm/kvmclock.h> @@ -45,13 +46,7 @@ early_param("no-kvmclock", parse_no_kvmclock); /* The hypervisor will put information about time periodically here */ static struct pvclock_vsyscall_time_info *hv_clock; -static struct pvclock_wall_clock wall_clock; - -struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void) -{ - return hv_clock; -} -EXPORT_SYMBOL_GPL(pvclock_pvti_cpu0_va); +static struct pvclock_wall_clock *wall_clock; /* * The wallclock is the time of day when we booted. Since then, some time may @@ -64,22 +59,22 @@ static void kvm_get_wallclock(struct timespec *now) int low, high; int cpu; - low = (int)__pa_symbol(&wall_clock); - high = ((u64)__pa_symbol(&wall_clock) >> 32); + low = (int)slow_virt_to_phys(wall_clock); + high = ((u64)slow_virt_to_phys(wall_clock) >> 32); native_write_msr(msr_kvm_wall_clock, low, high); cpu = get_cpu(); vcpu_time = &hv_clock[cpu].pvti; - pvclock_read_wallclock(&wall_clock, vcpu_time, now); + pvclock_read_wallclock(wall_clock, vcpu_time, now); put_cpu(); } static int kvm_set_wallclock(const struct timespec *now) { - return -1; + return -ENODEV; } static u64 kvm_clock_read(void) @@ -249,11 +244,39 @@ static void kvm_shutdown(void) native_machine_shutdown(); } +static phys_addr_t __init kvm_memblock_alloc(phys_addr_t size, + phys_addr_t align) +{ + phys_addr_t mem; + + mem = memblock_alloc(size, align); + if (!mem) + return 0; + + if (sev_active()) { + if (early_set_memory_decrypted((unsigned long)__va(mem), size)) + goto e_free; + } + + return mem; +e_free: + memblock_free(mem, size); + return 0; +} + +static void __init kvm_memblock_free(phys_addr_t addr, phys_addr_t size) +{ + if (sev_active()) + early_set_memory_encrypted((unsigned long)__va(addr), size); + + memblock_free(addr, size); +} + void __init kvmclock_init(void) { struct pvclock_vcpu_time_info *vcpu_time; - unsigned long mem; - int size, cpu; + unsigned long mem, mem_wall_clock; + int size, cpu, wall_clock_size; u8 flags; size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS); @@ -267,21 +290,35 @@ void __init kvmclock_init(void) } else if (!(kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE))) return; - printk(KERN_INFO "kvm-clock: Using msrs %x and %x", - msr_kvm_system_time, msr_kvm_wall_clock); + wall_clock_size = PAGE_ALIGN(sizeof(struct pvclock_wall_clock)); + mem_wall_clock = kvm_memblock_alloc(wall_clock_size, PAGE_SIZE); + if (!mem_wall_clock) + return; - mem = memblock_alloc(size, PAGE_SIZE); - if (!mem) + wall_clock = __va(mem_wall_clock); + memset(wall_clock, 0, wall_clock_size); + + mem = kvm_memblock_alloc(size, PAGE_SIZE); + if (!mem) { + kvm_memblock_free(mem_wall_clock, wall_clock_size); + wall_clock = NULL; return; + } + hv_clock = __va(mem); memset(hv_clock, 0, size); if (kvm_register_clock("primary cpu clock")) { hv_clock = NULL; - memblock_free(mem, size); + kvm_memblock_free(mem, size); + kvm_memblock_free(mem_wall_clock, wall_clock_size); + wall_clock = NULL; return; } + printk(KERN_INFO "kvm-clock: Using msrs %x and %x", + msr_kvm_system_time, msr_kvm_wall_clock); + if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT); @@ -334,6 +371,7 @@ int __init kvm_setup_vsyscall_timeinfo(void) return 1; } + pvclock_set_pvti_cpu0_va(hv_clock); put_cpu(); kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK; diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index a870910c8565..1c1eae961340 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1992 Krishna Balasubramanian and Linus Torvalds * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com> @@ -12,6 +13,7 @@ #include <linux/string.h> #include <linux/mm.h> #include <linux/smp.h> +#include <linux/syscalls.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> @@ -21,6 +23,25 @@ #include <asm/mmu_context.h> #include <asm/syscalls.h> +static void refresh_ldt_segments(void) +{ +#ifdef CONFIG_X86_64 + unsigned short sel; + + /* + * Make sure that the cached DS and ES descriptors match the updated + * LDT. + */ + savesegment(ds, sel); + if ((sel & SEGMENT_TI_MASK) == SEGMENT_LDT) + loadsegment(ds, sel); + + savesegment(es, sel); + if ((sel & SEGMENT_TI_MASK) == SEGMENT_LDT) + loadsegment(es, sel); +#endif +} + /* context.lock is held for us, so we don't need any locking. */ static void flush_ldt(void *__mm) { @@ -32,6 +53,8 @@ static void flush_ldt(void *__mm) pc = &mm->context; set_ldt(pc->ldt->entries, pc->ldt->nr_entries); + + refresh_ldt_segments(); } /* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */ @@ -80,7 +103,7 @@ static void finalize_ldt_struct(struct ldt_struct *ldt) static void install_ldt(struct mm_struct *current_mm, struct ldt_struct *ldt) { - /* Synchronizes with lockless_dereference in load_mm_ldt. */ + /* Synchronizes with READ_ONCE in load_mm_ldt. */ smp_store_release(¤t_mm->context.ldt, ldt); /* Activate the LDT for all CPUs using current_mm. */ @@ -273,8 +296,8 @@ out: return error; } -asmlinkage int sys_modify_ldt(int func, void __user *ptr, - unsigned long bytecount) +SYSCALL_DEFINE3(modify_ldt, int , func , void __user * , ptr , + unsigned long , bytecount) { int ret = -ENOSYS; @@ -292,5 +315,14 @@ asmlinkage int sys_modify_ldt(int func, void __user *ptr, ret = write_ldt(ptr, bytecount, 0); break; } - return ret; + /* + * The SYSCALL_DEFINE() macros give us an 'unsigned long' + * return type, but tht ABI for sys_modify_ldt() expects + * 'int'. This cast gives us an int-sized value in %rax + * for the return code. The 'unsigned' is necessary so + * the compiler does not try to sign-extend the negative + * return codes into the high half of the register when + * taking the value from int->long. + */ + return (unsigned int)ret; } diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 8c53c5d7a1bc..00bc751c861c 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -26,18 +26,6 @@ #include <asm/set_memory.h> #include <asm/debugreg.h> -static void set_idt(void *newidt, __u16 limit) -{ - struct desc_ptr curidt; - - /* ia32 supports unaliged loads & stores */ - curidt.size = limit; - curidt.address = (unsigned long)newidt; - - load_idt(&curidt); -} - - static void set_gdt(void *newgdt, __u16 limit) { struct desc_ptr curgdt; @@ -245,7 +233,7 @@ void machine_kexec(struct kimage *image) * If you want to load them you must set up your own idt & gdt. */ set_gdt(phys_to_virt(0), 0); - set_idt(phys_to_virt(0), 0); + idt_invalidate(phys_to_virt(0)); /* now call it */ image->start = relocate_kernel_ptr((unsigned long)image->head, diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index cb0a30473c23..1f790cf9d38f 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -87,7 +87,7 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd) set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE)); } pte = pte_offset_kernel(pmd, vaddr); - set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC)); + set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC_NOENC)); return 0; err: free_transition_pgtable(image); @@ -115,6 +115,7 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable) .alloc_pgt_page = alloc_pgt_page, .context = image, .page_flag = __PAGE_KERNEL_LARGE_EXEC, + .kernpg_flag = _KERNPG_TABLE_NOENC, }; unsigned long mstart, mend; pgd_t *level4p; @@ -334,7 +335,8 @@ void machine_kexec(struct kimage *image) image->start = relocate_kernel((unsigned long)image->head, (unsigned long)page_list, image->start, - image->preserve_context); + image->preserve_context, + sme_active()); #ifdef CONFIG_KEXEC_JUMP if (image->preserve_context) @@ -602,3 +604,22 @@ void arch_kexec_unprotect_crashkres(void) { kexec_mark_crashkres(false); } + +int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, gfp_t gfp) +{ + /* + * If SME is active we need to be sure that kexec pages are + * not encrypted because when we boot to the new kernel the + * pages won't be accessed encrypted (initially). + */ + return set_memory_decrypted((unsigned long)vaddr, pages); +} + +void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages) +{ + /* + * If SME is active we need to reset the pages back to being + * an encrypted mapping before freeing them. + */ + set_memory_encrypted((unsigned long)vaddr, pages); +} diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c index f4c886d9165c..b5cb49e57df8 100644 --- a/arch/x86/kernel/mmconf-fam10h_64.c +++ b/arch/x86/kernel/mmconf-fam10h_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * AMD Family 10h mmconfig enablement */ diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index f67bd3205df7..da0c160e5589 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -35,6 +35,7 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/setup.h> +#include <asm/unwind.h> #if 0 #define DEBUGP(fmt, ...) \ @@ -171,19 +172,27 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, case R_X86_64_NONE: break; case R_X86_64_64: + if (*(u64 *)loc != 0) + goto invalid_relocation; *(u64 *)loc = val; break; case R_X86_64_32: + if (*(u32 *)loc != 0) + goto invalid_relocation; *(u32 *)loc = val; if (val != *(u32 *)loc) goto overflow; break; case R_X86_64_32S: + if (*(s32 *)loc != 0) + goto invalid_relocation; *(s32 *)loc = val; if ((s64)val != *(s32 *)loc) goto overflow; break; case R_X86_64_PC32: + if (*(u32 *)loc != 0) + goto invalid_relocation; val -= (u64)loc; *(u32 *)loc = val; #if 0 @@ -199,6 +208,11 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, } return 0; +invalid_relocation: + pr_err("x86/modules: Skipping invalid relocation target, existing value is nonzero for type %d, loc %p, val %Lx\n", + (int)ELF64_R_TYPE(rel[i].r_info), loc, val); + return -ENOEXEC; + overflow: pr_err("overflow in relocation type %d val %Lx\n", (int)ELF64_R_TYPE(rel[i].r_info), val); @@ -213,7 +227,7 @@ int module_finalize(const Elf_Ehdr *hdr, struct module *me) { const Elf_Shdr *s, *text = NULL, *alt = NULL, *locks = NULL, - *para = NULL; + *para = NULL, *orc = NULL, *orc_ip = NULL; char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) { @@ -225,6 +239,10 @@ int module_finalize(const Elf_Ehdr *hdr, locks = s; if (!strcmp(".parainstructions", secstrings + s->sh_name)) para = s; + if (!strcmp(".orc_unwind", secstrings + s->sh_name)) + orc = s; + if (!strcmp(".orc_unwind_ip", secstrings + s->sh_name)) + orc_ip = s; } if (alt) { @@ -248,6 +266,10 @@ int module_finalize(const Elf_Ehdr *hdr, /* make jump label nops */ jump_label_apply_nops(me); + if (orc && orc_ip) + unwind_module_init(me, (void *)orc_ip->sh_addr, orc_ip->sh_size, + (void *)orc->sh_addr, orc->sh_size); + return 0; } diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 0d904d759ff1..3a4b12809ab5 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Intel Multiprocessor Specification 1.1 and 1.4 * compliant MP-table parsing routines. @@ -429,16 +430,17 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type) } } -static struct mpf_intel *mpf_found; +static unsigned long mpf_base; +static bool mpf_found; static unsigned long __init get_mpc_size(unsigned long physptr) { struct mpc_table *mpc; unsigned long size; - mpc = early_ioremap(physptr, PAGE_SIZE); + mpc = early_memremap(physptr, PAGE_SIZE); size = mpc->length; - early_iounmap(mpc, PAGE_SIZE); + early_memunmap(mpc, PAGE_SIZE); apic_printk(APIC_VERBOSE, " mpc: %lx-%lx\n", physptr, physptr + size); return size; @@ -450,7 +452,8 @@ static int __init check_physptr(struct mpf_intel *mpf, unsigned int early) unsigned long size; size = get_mpc_size(mpf->physptr); - mpc = early_ioremap(mpf->physptr, size); + mpc = early_memremap(mpf->physptr, size); + /* * Read the physical hardware table. Anything here will * override the defaults. @@ -461,10 +464,10 @@ static int __init check_physptr(struct mpf_intel *mpf, unsigned int early) #endif pr_err("BIOS bug, MP table errors detected!...\n"); pr_cont("... disabling SMP support. (tell your hw vendor)\n"); - early_iounmap(mpc, size); + early_memunmap(mpc, size); return -1; } - early_iounmap(mpc, size); + early_memunmap(mpc, size); if (early) return -1; @@ -497,12 +500,12 @@ static int __init check_physptr(struct mpf_intel *mpf, unsigned int early) */ void __init default_get_smp_config(unsigned int early) { - struct mpf_intel *mpf = mpf_found; + struct mpf_intel *mpf; if (!smp_found_config) return; - if (!mpf) + if (!mpf_found) return; if (acpi_lapic && early) @@ -515,6 +518,12 @@ void __init default_get_smp_config(unsigned int early) if (acpi_lapic && acpi_ioapic) return; + mpf = early_memremap(mpf_base, sizeof(*mpf)); + if (!mpf) { + pr_err("MPTABLE: error mapping MP table\n"); + return; + } + pr_info("Intel MultiProcessor Specification v1.%d\n", mpf->specification); #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32) @@ -529,7 +538,7 @@ void __init default_get_smp_config(unsigned int early) /* * Now see if we need to read further. */ - if (mpf->feature1 != 0) { + if (mpf->feature1) { if (early) { /* * local APIC has default address @@ -542,8 +551,10 @@ void __init default_get_smp_config(unsigned int early) construct_default_ISA_mptable(mpf->feature1); } else if (mpf->physptr) { - if (check_physptr(mpf, early)) + if (check_physptr(mpf, early)) { + early_memunmap(mpf, sizeof(*mpf)); return; + } } else BUG(); @@ -552,6 +563,8 @@ void __init default_get_smp_config(unsigned int early) /* * Only use the first configuration found. */ + + early_memunmap(mpf, sizeof(*mpf)); } static void __init smp_reserve_memory(struct mpf_intel *mpf) @@ -561,15 +574,16 @@ static void __init smp_reserve_memory(struct mpf_intel *mpf) static int __init smp_scan_config(unsigned long base, unsigned long length) { - unsigned int *bp = phys_to_virt(base); + unsigned int *bp; struct mpf_intel *mpf; - unsigned long mem; + int ret = 0; apic_printk(APIC_VERBOSE, "Scan for SMP in [mem %#010lx-%#010lx]\n", base, base + length - 1); BUILD_BUG_ON(sizeof(*mpf) != 16); while (length > 0) { + bp = early_memremap(base, length); mpf = (struct mpf_intel *)bp; if ((*bp == SMP_MAGIC_IDENT) && (mpf->length == 1) && @@ -579,24 +593,27 @@ static int __init smp_scan_config(unsigned long base, unsigned long length) #ifdef CONFIG_X86_LOCAL_APIC smp_found_config = 1; #endif - mpf_found = mpf; + mpf_base = base; + mpf_found = true; - pr_info("found SMP MP-table at [mem %#010llx-%#010llx] mapped at [%p]\n", - (unsigned long long) virt_to_phys(mpf), - (unsigned long long) virt_to_phys(mpf) + - sizeof(*mpf) - 1, mpf); + pr_info("found SMP MP-table at [mem %#010lx-%#010lx] mapped at [%p]\n", + base, base + sizeof(*mpf) - 1, mpf); - mem = virt_to_phys(mpf); - memblock_reserve(mem, sizeof(*mpf)); + memblock_reserve(base, sizeof(*mpf)); if (mpf->physptr) smp_reserve_memory(mpf); - return 1; + ret = 1; } - bp += 4; + early_memunmap(bp, length); + + if (ret) + break; + + base += 16; length -= 16; } - return 0; + return ret; } void __init default_find_smp_config(void) @@ -838,29 +855,40 @@ static int __init update_mp_table(void) char oem[10]; struct mpf_intel *mpf; struct mpc_table *mpc, *mpc_new; + unsigned long size; if (!enable_update_mptable) return 0; - mpf = mpf_found; - if (!mpf) + if (!mpf_found) return 0; + mpf = early_memremap(mpf_base, sizeof(*mpf)); + if (!mpf) { + pr_err("MPTABLE: mpf early_memremap() failed\n"); + return 0; + } + /* * Now see if we need to go further. */ - if (mpf->feature1 != 0) - return 0; + if (mpf->feature1) + goto do_unmap_mpf; if (!mpf->physptr) - return 0; + goto do_unmap_mpf; - mpc = phys_to_virt(mpf->physptr); + size = get_mpc_size(mpf->physptr); + mpc = early_memremap(mpf->physptr, size); + if (!mpc) { + pr_err("MPTABLE: mpc early_memremap() failed\n"); + goto do_unmap_mpf; + } if (!smp_check_mpc(mpc, oem, str)) - return 0; + goto do_unmap_mpc; - pr_info("mpf: %llx\n", (u64)virt_to_phys(mpf)); + pr_info("mpf: %llx\n", (u64)mpf_base); pr_info("physptr: %x\n", mpf->physptr); if (mpc_new_phys && mpc->length > mpc_new_length) { @@ -878,21 +906,32 @@ static int __init update_mp_table(void) new = mpf_checksum((unsigned char *)mpc, mpc->length); if (old == new) { pr_info("mpc is readonly, please try alloc_mptable instead\n"); - return 0; + goto do_unmap_mpc; } pr_info("use in-position replacing\n"); } else { + mpc_new = early_memremap(mpc_new_phys, mpc_new_length); + if (!mpc_new) { + pr_err("MPTABLE: new mpc early_memremap() failed\n"); + goto do_unmap_mpc; + } mpf->physptr = mpc_new_phys; - mpc_new = phys_to_virt(mpc_new_phys); memcpy(mpc_new, mpc, mpc->length); + early_memunmap(mpc, size); mpc = mpc_new; + size = mpc_new_length; /* check if we can modify that */ if (mpc_new_phys - mpf->physptr) { struct mpf_intel *mpf_new; /* steal 16 bytes from [0, 1k) */ + mpf_new = early_memremap(0x400 - 16, sizeof(*mpf_new)); + if (!mpf_new) { + pr_err("MPTABLE: new mpf early_memremap() failed\n"); + goto do_unmap_mpc; + } pr_info("mpf new: %x\n", 0x400 - 16); - mpf_new = phys_to_virt(0x400 - 16); memcpy(mpf_new, mpf, 16); + early_memunmap(mpf, sizeof(*mpf)); mpf = mpf_new; mpf->physptr = mpc_new_phys; } @@ -909,6 +948,12 @@ static int __init update_mp_table(void) */ replace_intsrc_all(mpc, mpc_new_phys, mpc_new_length); +do_unmap_mpc: + early_memunmap(mpc, size); + +do_unmap_mpf: + early_memunmap(mpf, sizeof(*mpf)); + return 0; } diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 446c8aa09b9b..18bc9b51ac9b 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -39,26 +39,26 @@ #include <trace/events/nmi.h> struct nmi_desc { - spinlock_t lock; + raw_spinlock_t lock; struct list_head head; }; static struct nmi_desc nmi_desc[NMI_MAX] = { { - .lock = __SPIN_LOCK_UNLOCKED(&nmi_desc[0].lock), + .lock = __RAW_SPIN_LOCK_UNLOCKED(&nmi_desc[0].lock), .head = LIST_HEAD_INIT(nmi_desc[0].head), }, { - .lock = __SPIN_LOCK_UNLOCKED(&nmi_desc[1].lock), + .lock = __RAW_SPIN_LOCK_UNLOCKED(&nmi_desc[1].lock), .head = LIST_HEAD_INIT(nmi_desc[1].head), }, { - .lock = __SPIN_LOCK_UNLOCKED(&nmi_desc[2].lock), + .lock = __RAW_SPIN_LOCK_UNLOCKED(&nmi_desc[2].lock), .head = LIST_HEAD_INIT(nmi_desc[2].head), }, { - .lock = __SPIN_LOCK_UNLOCKED(&nmi_desc[3].lock), + .lock = __RAW_SPIN_LOCK_UNLOCKED(&nmi_desc[3].lock), .head = LIST_HEAD_INIT(nmi_desc[3].head), }, @@ -105,7 +105,7 @@ static void nmi_max_handler(struct irq_work *w) { struct nmiaction *a = container_of(w, struct nmiaction, irq_work); int remainder_ns, decimal_msecs; - u64 whole_msecs = ACCESS_ONCE(a->max_duration); + u64 whole_msecs = READ_ONCE(a->max_duration); remainder_ns = do_div(whole_msecs, (1000 * 1000)); decimal_msecs = remainder_ns / 1000; @@ -163,7 +163,7 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action) init_irq_work(&action->irq_work, nmi_max_handler); - spin_lock_irqsave(&desc->lock, flags); + raw_spin_lock_irqsave(&desc->lock, flags); /* * Indicate if there are multiple registrations on the @@ -181,7 +181,7 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action) else list_add_tail_rcu(&action->list, &desc->head); - spin_unlock_irqrestore(&desc->lock, flags); + raw_spin_unlock_irqrestore(&desc->lock, flags); return 0; } EXPORT_SYMBOL(__register_nmi_handler); @@ -192,7 +192,7 @@ void unregister_nmi_handler(unsigned int type, const char *name) struct nmiaction *n; unsigned long flags; - spin_lock_irqsave(&desc->lock, flags); + raw_spin_lock_irqsave(&desc->lock, flags); list_for_each_entry_rcu(n, &desc->head, list) { /* @@ -207,7 +207,7 @@ void unregister_nmi_handler(unsigned int type, const char *name) } } - spin_unlock_irqrestore(&desc->lock, flags); + raw_spin_unlock_irqrestore(&desc->lock, flags); synchronize_rcu(); } EXPORT_SYMBOL_GPL(unregister_nmi_handler); diff --git a/arch/x86/kernel/nmi_selftest.c b/arch/x86/kernel/nmi_selftest.c index d27f8d84c4ff..a1a96df3dff1 100644 --- a/arch/x86/kernel/nmi_selftest.c +++ b/arch/x86/kernel/nmi_selftest.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * arch/x86/kernel/nmi-selftest.c * diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c index 8f2d1c9d43a8..71f2d1125ec0 100644 --- a/arch/x86/kernel/paravirt-spinlocks.c +++ b/arch/x86/kernel/paravirt-spinlocks.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Split spinlock implementation out into its own file, so it can be * compiled in a FTRACE-compatible way. diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index bc0a849589bb..041096bdef86 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -115,8 +115,18 @@ unsigned paravirt_patch_jmp(void *insnbuf, const void *target, return 5; } -/* Neat trick to map patch type back to the call within the - * corresponding structure. */ +DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key); + +void __init native_pv_lock_init(void) +{ + if (!static_cpu_has(X86_FEATURE_HYPERVISOR)) + static_branch_disable(&virt_spin_lock_key); +} + +/* + * Neat trick to map patch type back to the call within the + * corresponding structure. + */ static void *get_call_destination(u8 type) { struct paravirt_patch_template tmpl = { @@ -319,9 +329,6 @@ __visible struct pv_irq_ops pv_irq_ops = { .irq_enable = __PV_IS_CALLEE_SAVE(native_irq_enable), .safe_halt = native_safe_halt, .halt = native_halt, -#ifdef CONFIG_X86_64 - .adjust_exception_frame = paravirt_nop, -#endif }; __visible struct pv_cpu_ops pv_cpu_ops = { @@ -330,7 +337,6 @@ __visible struct pv_cpu_ops pv_cpu_ops = { .set_debugreg = native_set_debugreg, .read_cr0 = native_read_cr0, .write_cr0 = native_write_cr0, - .read_cr4 = native_read_cr4, .write_cr4 = native_write_cr4, #ifdef CONFIG_X86_64 .read_cr8 = native_read_cr8, @@ -346,7 +352,6 @@ __visible struct pv_cpu_ops pv_cpu_ops = { .set_ldt = native_set_ldt, .load_gdt = native_load_gdt, .load_idt = native_load_idt, - .store_idt = native_store_idt, .store_tr = native_store_tr, .load_tls = native_load_tls, #ifdef CONFIG_X86_64 @@ -414,8 +419,6 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_init = { .set_pte = native_set_pte, .set_pte_at = native_set_pte_at, .set_pmd = native_set_pmd, - .set_pmd_at = native_set_pmd_at, - .pte_update = paravirt_nop, .ptep_modify_prot_start = __ptep_modify_prot_start, .ptep_modify_prot_commit = __ptep_modify_prot_commit, @@ -427,7 +430,6 @@ 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/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c index 553acbbb4d32..758e69d72ebf 100644 --- a/arch/x86/kernel/paravirt_patch_32.c +++ b/arch/x86/kernel/paravirt_patch_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <asm/paravirt.h> DEF_NATIVE(pv_irq_ops, irq_disable, "cli"); diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index 11aaf1eaa0e4..ac0be8283325 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <asm/paravirt.h> #include <asm/asm-offsets.h> #include <linux/stringify.h> diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 5286a4a92cf7..35c461f21815 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -898,10 +898,9 @@ static void calioc2_dump_error_regs(struct iommu_table *tbl) PHB_ROOT_COMPLEX_STATUS); } -static void calgary_watchdog(unsigned long data) +static void calgary_watchdog(struct timer_list *t) { - struct pci_dev *dev = (struct pci_dev *)data; - struct iommu_table *tbl = pci_iommu(dev->bus); + struct iommu_table *tbl = from_timer(tbl, t, watchdog_timer); void __iomem *bbar = tbl->bbar; u32 val32; void __iomem *target; @@ -1016,8 +1015,7 @@ static void __init calgary_enable_translation(struct pci_dev *dev) writel(cpu_to_be32(val32), target); readl(target); /* flush */ - setup_timer(&tbl->watchdog_timer, &calgary_watchdog, - (unsigned long)dev); + timer_setup(&tbl->watchdog_timer, calgary_watchdog, 0); mod_timer(&tbl->watchdog_timer, jiffies); } diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 5e16d3f29594..599d7462eccc 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/dma-mapping.h> #include <linux/dma-debug.h> #include <linux/dmar.h> @@ -93,9 +94,12 @@ again: if (gfpflags_allow_blocking(flag)) { 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; + if (page) { + addr = phys_to_dma(dev, page_to_phys(page)); + if (addr + size > dma_mask) { + dma_release_from_contiguous(dev, page, count); + page = NULL; + } } } /* fallback */ @@ -104,7 +108,7 @@ again: if (!page) return NULL; - addr = page_to_phys(page); + addr = phys_to_dma(dev, page_to_phys(page)); if (addr + size > dma_mask) { __free_pages(page, get_order(size)); diff --git a/arch/x86/kernel/pci-iommu_table.c b/arch/x86/kernel/pci-iommu_table.c index f712dfdf1357..4dfd90a75e63 100644 --- a/arch/x86/kernel/pci-iommu_table.c +++ b/arch/x86/kernel/pci-iommu_table.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/dma-mapping.h> #include <asm/iommu_table.h> #include <linux/string.h> diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c index a6d404087fe3..b0caae27e1b7 100644 --- a/arch/x86/kernel/pci-nommu.c +++ b/arch/x86/kernel/pci-nommu.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* Fallback functions when the main IOMMU code is not compiled in. This code is roughly equivalent to i386. */ #include <linux/dma-mapping.h> @@ -32,7 +33,7 @@ static dma_addr_t nommu_map_page(struct device *dev, struct page *page, enum dma_data_direction dir, unsigned long attrs) { - dma_addr_t bus = page_to_phys(page) + offset; + dma_addr_t bus = phys_to_dma(dev, page_to_phys(page)) + offset; WARN_ON(size == 0); if (!check_addr("map_single", dev, bus, size)) return NOMMU_MAPPING_ERROR; diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index 1e23577e17cf..53bd05ea90d8 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* Glue code to lib/swiotlb.c */ #include <linux/pci.h> @@ -6,12 +7,14 @@ #include <linux/swiotlb.h> #include <linux/bootmem.h> #include <linux/dma-mapping.h> +#include <linux/mem_encrypt.h> #include <asm/iommu.h> #include <asm/swiotlb.h> #include <asm/dma.h> #include <asm/xen/swiotlb-xen.h> #include <asm/iommu_table.h> + int swiotlb __read_mostly; void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, @@ -79,8 +82,8 @@ IOMMU_INIT_FINISH(pci_swiotlb_detect_override, pci_swiotlb_late_init); /* - * if 4GB or more detected (and iommu=off not set) return 1 - * and set swiotlb to 1. + * If 4GB or more detected (and iommu=off not set) or if SME is active + * then set swiotlb to 1 and return 1. */ int __init pci_swiotlb_detect_4gb(void) { @@ -89,6 +92,15 @@ int __init pci_swiotlb_detect_4gb(void) if (!no_iommu && max_possible_pfn > MAX_DMA32_PFN) swiotlb = 1; #endif + + /* + * If SME is active then swiotlb will be set to 1 so that bounce + * buffers are allocated and used for devices that do not support + * the addressing range required for the encryption mask. + */ + if (sme_active()) + swiotlb = 1; + return swiotlb; } IOMMU_INIT(pci_swiotlb_detect_4gb, diff --git a/arch/x86/kernel/pcspeaker.c b/arch/x86/kernel/pcspeaker.c index a311ffcaad16..da5190a1ea16 100644 --- a/arch/x86/kernel/pcspeaker.c +++ b/arch/x86/kernel/pcspeaker.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/platform_device.h> #include <linux/err.h> #include <linux/init.h> diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c index 587d887f7f17..e47b2dbbdef3 100644 --- a/arch/x86/kernel/perf_regs.c +++ b/arch/x86/kernel/perf_regs.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/errno.h> #include <linux/kernel.h> #include <linux/sched.h> diff --git a/arch/x86/kernel/platform-quirks.c b/arch/x86/kernel/platform-quirks.c index 91271122f0df..39a59299bfa0 100644 --- a/arch/x86/kernel/platform-quirks.c +++ b/arch/x86/kernel/platform-quirks.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/init.h> @@ -16,7 +17,6 @@ void __init x86_early_init_platform_quirks(void) x86_platform.legacy.reserve_bios_regions = 1; break; case X86_SUBARCH_XEN: - case X86_SUBARCH_LGUEST: x86_platform.legacy.devices.pnpbios = 0; x86_platform.legacy.rtc = 0; break; diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c index 0c5315d322c8..6b07faaa1579 100644 --- a/arch/x86/kernel/pmem.c +++ b/arch/x86/kernel/pmem.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2015, Christoph Hellwig. * Copyright (c) 2015, Intel Corporation. @@ -6,7 +7,7 @@ #include <linux/init.h> #include <linux/ioport.h> -static int found(u64 start, u64 end, void *data) +static int found(struct resource *res, void *data) { return 1; } diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c index 963e3fb56437..ee0286390a4c 100644 --- a/arch/x86/kernel/probe_roms.c +++ b/arch/x86/kernel/probe_roms.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/sched.h> #include <linux/mm.h> #include <linux/uaccess.h> diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 3ca198080ea9..97fb3e5737f5 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/errno.h> @@ -48,7 +49,13 @@ */ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = { .x86_tss = { - .sp0 = TOP_OF_INIT_STACK, + /* + * .sp0 is only used when entering ring 0 from a lower + * privilege level. Since the init task never runs anything + * but ring 0 code, there is no need for a valid value here. + * Poison it. + */ + .sp0 = (1UL << (BITS_PER_LONG-1)) + 1, #ifdef CONFIG_X86_32 .ss0 = __KERNEL_DS, .ss1 = __KERNEL_CS, @@ -355,6 +362,7 @@ bool xen_set_default_idle(void) return ret; } #endif + void stop_this_cpu(void *dummy) { local_irq_disable(); @@ -365,8 +373,20 @@ void stop_this_cpu(void *dummy) disable_local_APIC(); mcheck_cpu_clear(this_cpu_ptr(&cpu_info)); - for (;;) - halt(); + for (;;) { + /* + * Use wbinvd followed by hlt to stop the processor. This + * provides support for kexec on a processor that supports + * SME. With kexec, going from SME inactive to SME active + * requires clearing cache entries so that addresses without + * the encryption bit set don't corrupt the same physical + * address that has the encryption bit set when caches are + * flushed. To achieve this a wbinvd is performed followed by + * a hlt. Even if the processor is not in the kexec/SME + * scenario this only adds a wbinvd to a halting processor. + */ + asm volatile("wbinvd; hlt" : : : "memory"); + } } /* diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index c6d6dc5f8bb2..45bf0c5f93e1 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -56,7 +56,7 @@ #include <asm/debugreg.h> #include <asm/switch_to.h> #include <asm/vm86.h> -#include <asm/intel_rdt.h> +#include <asm/intel_rdt_sched.h> #include <asm/proto.h> void __show_regs(struct pt_regs *regs, int all) @@ -68,7 +68,7 @@ void __show_regs(struct pt_regs *regs, int all) if (user_mode(regs)) { sp = regs->sp; - ss = regs->ss & 0xffff; + ss = regs->ss; gs = get_user_gs(regs); } else { sp = kernel_stack_pointer(regs); @@ -284,9 +284,11 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) /* * Reload esp0 and cpu_current_top_of_stack. This changes - * current_thread_info(). + * current_thread_info(). Refresh the SYSENTER configuration in + * case prev or next is vm86. */ - load_sp0(tss, next); + update_sp0(next_p); + refresh_sysenter_cs(next); this_cpu_write(cpu_current_top_of_stack, (unsigned long)task_stack_page(next_p) + THREAD_SIZE); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index c3169be4c596..eeeb34f85c25 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -52,7 +52,7 @@ #include <asm/switch_to.h> #include <asm/xen/hypervisor.h> #include <asm/vdso.h> -#include <asm/intel_rdt.h> +#include <asm/intel_rdt_sched.h> #include <asm/unistd.h> #ifdef CONFIG_IA32_EMULATION /* Not included via unistd.h */ @@ -69,8 +69,7 @@ void __show_regs(struct pt_regs *regs, int all) unsigned int fsindex, gsindex; unsigned int ds, cs, es; - printk(KERN_DEFAULT "RIP: %04lx:%pS\n", regs->cs & 0xffff, - (void *)regs->ip); + printk(KERN_DEFAULT "RIP: %04lx:%pS\n", regs->cs, (void *)regs->ip); printk(KERN_DEFAULT "RSP: %04lx:%016lx EFLAGS: %08lx", regs->ss, regs->sp, regs->flags); if (regs->orig_ax != -1) @@ -149,6 +148,123 @@ void release_thread(struct task_struct *dead_task) } } +enum which_selector { + FS, + GS +}; + +/* + * Saves the FS or GS base for an outgoing thread if FSGSBASE extensions are + * not available. The goal is to be reasonably fast on non-FSGSBASE systems. + * It's forcibly inlined because it'll generate better code and this function + * is hot. + */ +static __always_inline void save_base_legacy(struct task_struct *prev_p, + unsigned short selector, + enum which_selector which) +{ + if (likely(selector == 0)) { + /* + * On Intel (without X86_BUG_NULL_SEG), the segment base could + * be the pre-existing saved base or it could be zero. On AMD + * (with X86_BUG_NULL_SEG), the segment base could be almost + * anything. + * + * This branch is very hot (it's hit twice on almost every + * context switch between 64-bit programs), and avoiding + * the RDMSR helps a lot, so we just assume that whatever + * value is already saved is correct. This matches historical + * Linux behavior, so it won't break existing applications. + * + * To avoid leaking state, on non-X86_BUG_NULL_SEG CPUs, if we + * report that the base is zero, it needs to actually be zero: + * see the corresponding logic in load_seg_legacy. + */ + } else { + /* + * If the selector is 1, 2, or 3, then the base is zero on + * !X86_BUG_NULL_SEG CPUs and could be anything on + * X86_BUG_NULL_SEG CPUs. In the latter case, Linux + * has never attempted to preserve the base across context + * switches. + * + * If selector > 3, then it refers to a real segment, and + * saving the base isn't necessary. + */ + if (which == FS) + prev_p->thread.fsbase = 0; + else + prev_p->thread.gsbase = 0; + } +} + +static __always_inline void save_fsgs(struct task_struct *task) +{ + savesegment(fs, task->thread.fsindex); + savesegment(gs, task->thread.gsindex); + save_base_legacy(task, task->thread.fsindex, FS); + save_base_legacy(task, task->thread.gsindex, GS); +} + +static __always_inline void loadseg(enum which_selector which, + unsigned short sel) +{ + if (which == FS) + loadsegment(fs, sel); + else + load_gs_index(sel); +} + +static __always_inline void load_seg_legacy(unsigned short prev_index, + unsigned long prev_base, + unsigned short next_index, + unsigned long next_base, + enum which_selector which) +{ + if (likely(next_index <= 3)) { + /* + * The next task is using 64-bit TLS, is not using this + * segment at all, or is having fun with arcane CPU features. + */ + if (next_base == 0) { + /* + * Nasty case: on AMD CPUs, we need to forcibly zero + * the base. + */ + if (static_cpu_has_bug(X86_BUG_NULL_SEG)) { + loadseg(which, __USER_DS); + loadseg(which, next_index); + } else { + /* + * We could try to exhaustively detect cases + * under which we can skip the segment load, + * but there's really only one case that matters + * for performance: if both the previous and + * next states are fully zeroed, we can skip + * the load. + * + * (This assumes that prev_base == 0 has no + * false positives. This is the case on + * Intel-style CPUs.) + */ + if (likely(prev_index | next_index | prev_base)) + loadseg(which, next_index); + } + } else { + if (prev_index != next_index) + loadseg(which, next_index); + wrmsrl(which == FS ? MSR_FS_BASE : MSR_KERNEL_GS_BASE, + next_base); + } + } else { + /* + * The next task is using a real segment. Loading the selector + * is sufficient. + */ + loadseg(which, next_index); + } +} + int copy_thread_tls(unsigned long clone_flags, unsigned long sp, unsigned long arg, struct task_struct *p, unsigned long tls) { @@ -158,7 +274,6 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, struct inactive_task_frame *frame; struct task_struct *me = current; - p->thread.sp0 = (unsigned long)task_stack_page(p) + THREAD_SIZE; childregs = task_pt_regs(p); fork_frame = container_of(childregs, struct fork_frame, regs); frame = &fork_frame->frame; @@ -229,10 +344,19 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp, unsigned int _cs, unsigned int _ss, unsigned int _ds) { + WARN_ON_ONCE(regs != current_pt_regs()); + + if (static_cpu_has(X86_BUG_NULL_SEG)) { + /* Loading zero below won't clear the base. */ + loadsegment(fs, __USER_DS); + load_gs_index(__USER_DS); + } + loadsegment(fs, 0); loadsegment(es, _ds); loadsegment(ds, _ds); load_gs_index(0); + regs->ip = new_ip; regs->sp = new_sp; regs->cs = _cs; @@ -277,7 +401,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(cpu_tss, cpu); - unsigned prev_fsindex, prev_gsindex; + + WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) && + this_cpu_read(irq_count) != -1); switch_fpu_prepare(prev_fpu, cpu); @@ -286,8 +412,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * * (e.g. xen_load_tls()) */ - savesegment(fs, prev_fsindex); - savesegment(gs, prev_gsindex); + save_fsgs(prev_p); /* * Load TLS before restoring any segments so that segment loads @@ -326,108 +451,10 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) if (unlikely(next->ds | prev->ds)) loadsegment(ds, next->ds); - /* - * Switch FS and GS. - * - * These are even more complicated than DS and ES: they have - * 64-bit bases are that controlled by arch_prctl. The bases - * don't necessarily match the selectors, as user code can do - * any number of things to cause them to be inconsistent. - * - * We don't promise to preserve the bases if the selectors are - * nonzero. We also don't promise to preserve the base if the - * selector is zero and the base doesn't match whatever was - * most recently passed to ARCH_SET_FS/GS. (If/when the - * FSGSBASE instructions are enabled, we'll need to offer - * stronger guarantees.) - * - * As an invariant, - * (fsbase != 0 && fsindex != 0) || (gsbase != 0 && gsindex != 0) is - * impossible. - */ - if (next->fsindex) { - /* Loading a nonzero value into FS sets the index and base. */ - loadsegment(fs, next->fsindex); - } else { - if (next->fsbase) { - /* Next index is zero but next base is nonzero. */ - if (prev_fsindex) - loadsegment(fs, 0); - wrmsrl(MSR_FS_BASE, next->fsbase); - } else { - /* Next base and index are both zero. */ - if (static_cpu_has_bug(X86_BUG_NULL_SEG)) { - /* - * We don't know the previous base and can't - * find out without RDMSR. Forcibly clear it. - */ - loadsegment(fs, __USER_DS); - loadsegment(fs, 0); - } else { - /* - * If the previous index is zero and ARCH_SET_FS - * didn't change the base, then the base is - * also zero and we don't need to do anything. - */ - if (prev->fsbase || prev_fsindex) - loadsegment(fs, 0); - } - } - } - /* - * Save the old state and preserve the invariant. - * NB: if prev_fsindex == 0, then we can't reliably learn the base - * without RDMSR because Intel user code can zero it without telling - * us and AMD user code can program any 32-bit value without telling - * us. - */ - if (prev_fsindex) - prev->fsbase = 0; - prev->fsindex = prev_fsindex; - - if (next->gsindex) { - /* Loading a nonzero value into GS sets the index and base. */ - load_gs_index(next->gsindex); - } else { - if (next->gsbase) { - /* Next index is zero but next base is nonzero. */ - if (prev_gsindex) - load_gs_index(0); - wrmsrl(MSR_KERNEL_GS_BASE, next->gsbase); - } else { - /* Next base and index are both zero. */ - if (static_cpu_has_bug(X86_BUG_NULL_SEG)) { - /* - * We don't know the previous base and can't - * find out without RDMSR. Forcibly clear it. - * - * This contains a pointless SWAPGS pair. - * Fixing it would involve an explicit check - * for Xen or a new pvop. - */ - load_gs_index(__USER_DS); - load_gs_index(0); - } else { - /* - * If the previous index is zero and ARCH_SET_GS - * didn't change the base, then the base is - * also zero and we don't need to do anything. - */ - if (prev->gsbase || prev_gsindex) - load_gs_index(0); - } - } - } - /* - * Save the old state and preserve the invariant. - * NB: if prev_gsindex == 0, then we can't reliably learn the base - * without RDMSR because Intel user code can zero it without telling - * us and AMD user code can program any 32-bit value without telling - * us. - */ - if (prev_gsindex) - prev->gsbase = 0; - prev->gsindex = prev_gsindex; + load_seg_legacy(prev->fsindex, prev->fsbase, + next->fsindex, next->fsbase, FS); + load_seg_legacy(prev->gsindex, prev->gsbase, + next->gsindex, next->gsbase, GS); switch_fpu_finish(next_fpu, cpu); @@ -436,8 +463,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) */ this_cpu_write(current_task, next_p); - /* Reload esp0 and ss1. This changes current_thread_info(). */ - load_sp0(tss, next); + /* Reload sp0. */ + update_sp0(next_p); /* * Now maybe reload the debug registers and handle I/O bitmaps diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 5c3f6d6a5078..761f6af6efa5 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -25,8 +25,10 @@ #include <asm/fixmap.h> #include <asm/pvclock.h> +#include <asm/vgtod.h> static u8 valid_flags __read_mostly = 0; +static struct pvclock_vsyscall_time_info *pvti_cpu0_va __read_mostly; void pvclock_set_flags(u8 flags) { @@ -144,3 +146,15 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); } + +void pvclock_set_pvti_cpu0_va(struct pvclock_vsyscall_time_info *pvti) +{ + WARN_ON(vclock_was_used(VCLOCK_PVCLOCK)); + pvti_cpu0_va = pvti; +} + +struct pvclock_vsyscall_time_info *pvclock_get_pvti_cpu0_va(void) +{ + return pvti_cpu0_va; +} +EXPORT_SYMBOL_GPL(pvclock_get_pvti_cpu0_va); diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 0bee04d41bed..697a4ce04308 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -1,6 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 /* * This file contains work-arounds for x86 and x86_64 platform bugs. */ +#include <linux/dmi.h> #include <linux/pci.h> #include <linux/irq.h> @@ -656,3 +658,12 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, quirk_intel_brickland_xeon_ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2083, quirk_intel_purley_xeon_ras_cap); #endif #endif + +bool x86_apple_machine; +EXPORT_SYMBOL(x86_apple_machine); + +void __init early_platform_quirks(void) +{ + x86_apple_machine = dmi_match(DMI_SYS_VENDOR, "Apple Inc.") || + dmi_match(DMI_SYS_VENDOR, "Apple Computer, Inc."); +} diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 67393fc88353..2126b9d27c34 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/export.h> @@ -38,8 +39,6 @@ void (*pm_power_off)(void); EXPORT_SYMBOL(pm_power_off); -static const struct desc_ptr no_idt = {}; - /* * This is set if we need to go through the 'emergency' path. * When machine_emergency_restart() is called, we may be on @@ -107,6 +106,10 @@ void __noreturn machine_real_restart(unsigned int type) load_cr3(initial_page_table); #else write_cr3(real_mode_header->trampoline_pgd); + + /* Exiting long mode will fail if CR4.PCIDE is set. */ + if (static_cpu_has(X86_FEATURE_PCID)) + cr4_clear_bits(X86_CR4_PCIDE); #endif /* Jump to the identity-mapped low memory code */ @@ -152,7 +155,7 @@ static int __init set_kbd_reboot(const struct dmi_system_id *d) /* * This is a single dmi_table handling all reboot quirks. */ -static struct dmi_system_id __initdata reboot_dmi_table[] = { +static const struct dmi_system_id reboot_dmi_table[] __initconst = { /* Acer */ { /* Handle reboot issue on Acer Aspire one */ @@ -471,12 +474,12 @@ static int __init reboot_init(void) /* * The DMI quirks table takes precedence. If no quirks entry - * matches and the ACPI Hardware Reduced bit is set, force EFI - * reboot. + * matches and the ACPI Hardware Reduced bit is set and EFI + * runtime services are enabled, force EFI reboot. */ rv = dmi_check_system(reboot_dmi_table); - if (!rv && efi_reboot_required()) + if (!rv && efi_reboot_required() && !efi_runtime_disabled()) reboot_type = BOOT_EFI; return 0; @@ -638,7 +641,7 @@ static void native_machine_emergency_restart(void) break; case BOOT_TRIPLE: - load_idt(&no_idt); + idt_invalidate(NULL); __asm__ __volatile__("int3"); /* We're probably dead after this, but... */ diff --git a/arch/x86/kernel/reboot_fixups_32.c b/arch/x86/kernel/reboot_fixups_32.c index c8e41e90f59c..b7c0f142d026 100644 --- a/arch/x86/kernel/reboot_fixups_32.c +++ b/arch/x86/kernel/reboot_fixups_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * This is a good place to put board specific reboot fixups. * diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index 98111b38ebfd..307d3bac5f04 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -47,6 +47,7 @@ relocate_kernel: * %rsi page_list * %rdx start address * %rcx preserve_context + * %r8 sme_active */ /* Save the CPU context, used for jumping back */ @@ -71,6 +72,9 @@ relocate_kernel: pushq $0 popfq + /* Save SME active flag */ + movq %r8, %r12 + /* * get physical address of control page now * this is impossible after page table switch @@ -132,6 +136,16 @@ identity_mapped: /* Flush the TLB (needed?) */ movq %r9, %cr3 + /* + * If SME is active, there could be old encrypted cache line + * entries that will conflict with the now unencrypted memory + * used by kexec. Flush the caches before copying the kernel. + */ + testq %r12, %r12 + jz 1f + wbinvd +1: + movq %rcx, %r11 call swap_pages diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c index 5ab3895516ac..9b9fb7882c20 100644 --- a/arch/x86/kernel/resource.c +++ b/arch/x86/kernel/resource.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/ioport.h> #include <asm/e820/api.h> diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 5b21cb7d84d6..69ac9cb9cac6 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * RTC related functions */ diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 3486d0498800..8af2e8d0c0a1 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -69,6 +69,7 @@ #include <linux/crash_dump.h> #include <linux/tboot.h> #include <linux/jiffies.h> +#include <linux/mem_encrypt.h> #include <linux/usb/xhci-dbgp.h> #include <video/edid.h> @@ -115,6 +116,7 @@ #include <asm/microcode.h> #include <asm/mmu_context.h> #include <asm/kaslr.h> +#include <asm/unwind.h> /* * max_low_pfn_mapped: highest direct mapped pfn under 4GB @@ -134,18 +136,6 @@ RESERVE_BRK(dmi_alloc, 65536); static __initdata unsigned long _brk_start = (unsigned long)__brk_base; unsigned long _brk_end = (unsigned long)__brk_base; -#ifdef CONFIG_X86_64 -int default_cpu_present_to_apicid(int mps_cpu) -{ - return __default_cpu_present_to_apicid(mps_cpu); -} - -int default_check_phys_apicid_present(int phys_apicid) -{ - return __default_check_phys_apicid_present(phys_apicid); -} -#endif - struct boot_params boot_params; /* @@ -374,6 +364,16 @@ static void __init reserve_initrd(void) !ramdisk_image || !ramdisk_size) return; /* No initrd provided by bootloader */ + /* + * If SME is active, this memory will be marked encrypted by the + * kernel when it is accessed (including relocation). However, the + * ramdisk image was loaded decrypted by the bootloader, so make + * sure that it is encrypted before accessing it. For SEV the + * ramdisk will already be encrypted, so only do this for SME. + */ + if (sme_active()) + sme_early_encrypt(ramdisk_image, ramdisk_end - ramdisk_image); + initrd_start = 0; mapped_size = memblock_mem_size(max_pfn_mapped); @@ -812,26 +812,6 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p) return 0; } -static void __init simple_udelay_calibration(void) -{ - unsigned int tsc_khz, cpu_khz; - unsigned long lpj; - - if (!boot_cpu_has(X86_FEATURE_TSC)) - return; - - cpu_khz = x86_platform.calibrate_cpu(); - tsc_khz = x86_platform.calibrate_tsc(); - - tsc_khz = tsc_khz ? : cpu_khz; - if (!tsc_khz) - return; - - lpj = tsc_khz * 1000; - do_div(lpj, HZ); - loops_per_jiffy = lpj; -} - /* * Determine if we were loaded by an EFI loader. If so, then we have also been * passed the efi memmap, systab, etc., so we should use these data structures @@ -890,7 +870,7 @@ void __init setup_arch(char **cmdline_p) */ olpc_ofw_detect(); - early_trap_init(); + idt_setup_early_traps(); early_cpu_init(); early_ioremap_init(); @@ -1035,12 +1015,10 @@ void __init setup_arch(char **cmdline_p) /* * VMware detection requires dmi to be available, so this - * needs to be done after dmi_scan_machine, for the BP. + * needs to be done after dmi_scan_machine(), for the boot CPU. */ init_hypervisor_platform(); - simple_udelay_calibration(); - x86_init.resources.probe_roms(); /* after parse_early_param, so could debug it */ @@ -1125,9 +1103,6 @@ void __init setup_arch(char **cmdline_p) memblock_set_current_limit(ISA_END_ADDRESS); e820__memblock_setup(); - if (!early_xdbc_setup_hardware()) - early_xdbc_register_console(); - reserve_bios_regions(); if (efi_enabled(EFI_MEMMAP)) { @@ -1161,15 +1136,18 @@ void __init setup_arch(char **cmdline_p) init_mem_mapping(); - early_trap_pf_init(); + idt_setup_early_pf(); /* * Update mmu_cr4_features (and, indirectly, trampoline_cr4_features) * with the current CR4 value. This may not be necessary, but * auditing all the early-boot CR4 manipulation would be needed to * rule it out. + * + * Mask off features that don't work outside long mode (just + * PCIDE for now). */ - mmu_cr4_features = __read_cr4(); + mmu_cr4_features = __read_cr4() & ~X86_CR4_PCIDE; memblock_set_current_limit(get_max_mapped()); @@ -1206,6 +1184,8 @@ void __init setup_arch(char **cmdline_p) io_delay_init(); + early_platform_quirks(); + /* * Parse the ACPI tables for possible boot-time SMP configuration. */ @@ -1228,6 +1208,10 @@ void __init setup_arch(char **cmdline_p) kvmclock_init(); #endif + tsc_early_delay_calibrate(); + if (!early_xdbc_setup_hardware()) + early_xdbc_register_console(); + x86_init.paging.pagetable_init(); kasan_init(); @@ -1279,7 +1263,7 @@ void __init setup_arch(char **cmdline_p) io_apic_init_mappings(); - kvm_guest_init(); + x86_init.hyper.guest_late_init(); e820__reserve_resources(); e820__register_nosave_regions(max_low_pfn); @@ -1310,6 +1294,8 @@ void __init setup_arch(char **cmdline_p) if (efi_enabled(EFI_BOOT)) efi_apply_memmap_quirks(); #endif + + unwind_init(); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 10edd1e69a68..497aa766fab3 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> @@ -155,13 +156,10 @@ static void __init pcpup_populate_pte(unsigned long addr) static inline void setup_percpu_segment(int cpu) { #ifdef CONFIG_X86_32 - struct desc_struct gdt; + struct desc_struct d = GDT_ENTRY_INIT(0x8092, per_cpu_offset(cpu), + 0xFFFFF); - pack_descriptor(&gdt, per_cpu_offset(cpu), 0xFFFFF, - 0x2 | DESCTYPE_S, 0x8); - gdt.s = 1; - write_gdt_entry(get_cpu_gdt_rw(cpu), - GDT_ENTRY_PERCPU, &gdt, DESCTYPE_S); + write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_PERCPU, &d, DESCTYPE_S); #endif } @@ -171,7 +169,7 @@ void __init setup_per_cpu_areas(void) unsigned long delta; int rc; - pr_info("NR_CPUS:%d nr_cpumask_bits:%d nr_cpu_ids:%d nr_node_ids:%d\n", + pr_info("NR_CPUS:%d nr_cpumask_bits:%d nr_cpu_ids:%u nr_node_ids:%d\n", NR_CPUS, nr_cpumask_bits, nr_cpu_ids, nr_node_ids); /* diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index cc30a74e4adb..b9e00e8f1c9b 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs @@ -256,14 +257,14 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, sp = current->sas_ss_sp + current->sas_ss_size; } else if (IS_ENABLED(CONFIG_X86_32) && !onsigstack && - (regs->ss & 0xffff) != __USER_DS && + regs->ss != __USER_DS && !(ka->sa.sa_flags & SA_RESTORER) && ka->sa.sa_restorer) { /* This is the legacy signal stack switching. */ sp = (unsigned long) ka->sa.sa_restorer; } - if (fpu->fpstate_active) { + if (fpu->initialized) { sp = fpu__alloc_mathframe(sp, IS_ENABLED(CONFIG_X86_32), &buf_fx, &math_size); *fpstate = (void __user *)sp; @@ -279,7 +280,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, return (void __user *)-1L; /* save i387 and extended state */ - if (fpu->fpstate_active && + if (fpu->initialized && copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size) < 0) return (void __user *)-1L; @@ -755,7 +756,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) /* * Ensure the signal handler starts with the new fpu state. */ - if (fpu->fpstate_active) + if (fpu->initialized) fpu__clear(fpu); } signal_setup_done(failed, ksig, stepping); diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index 71beb28600d4..8c6da1a643da 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/compat.h> #include <linux/uaccess.h> #include <linux/ptrace.h> @@ -129,7 +130,7 @@ int __copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from, 3 ints plus the relevant union member. */ put_user_ex(from->si_signo, &to->si_signo); put_user_ex(from->si_errno, &to->si_errno); - put_user_ex((short)from->si_code, &to->si_code); + put_user_ex(from->si_code, &to->si_code); if (from->si_code < 0) { put_user_ex(from->si_pid, &to->si_pid); @@ -142,8 +143,8 @@ int __copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from, */ put_user_ex(from->_sifields._pad[0], &to->_sifields._pad[0]); - switch (from->si_code >> 16) { - case __SI_FAULT >> 16: + switch (siginfo_layout(from->si_signo, from->si_code)) { + case SIL_FAULT: if (from->si_signo == SIGBUS && (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO)) @@ -160,11 +161,11 @@ int __copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from, put_user_ex(from->si_pkey, &to->si_pkey); } break; - case __SI_SYS >> 16: + case SIL_SYS: put_user_ex(from->si_syscall, &to->si_syscall); put_user_ex(from->si_arch, &to->si_arch); break; - case __SI_CHLD >> 16: + case SIL_CHLD: if (!x32_ABI) { put_user_ex(from->si_utime, &to->si_utime); put_user_ex(from->si_stime, &to->si_stime); @@ -174,21 +175,18 @@ int __copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from, } put_user_ex(from->si_status, &to->si_status); /* FALL THROUGH */ - default: - case __SI_KILL >> 16: + case SIL_KILL: put_user_ex(from->si_uid, &to->si_uid); break; - case __SI_POLL >> 16: + case SIL_POLL: put_user_ex(from->si_fd, &to->si_fd); break; - case __SI_TIMER >> 16: + case SIL_TIMER: put_user_ex(from->si_overrun, &to->si_overrun); put_user_ex(ptr_to_compat(from->si_ptr), &to->si_ptr); break; - /* This is not generated by the kernel as of now. */ - case __SI_RT >> 16: - case __SI_MESGQ >> 16: + case SIL_RT: put_user_ex(from->si_uid, &to->si_uid); put_user_ex(from->si_int, &to->si_int); break; diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index d798c0da451c..5c574dff4c1a 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -254,84 +254,45 @@ finish: } /* - * Reschedule call back. + * Reschedule call back. KVM uses this interrupt to force a cpu out of + * guest mode */ -static inline void __smp_reschedule_interrupt(void) -{ - inc_irq_stat(irq_resched_count); - scheduler_ipi(); -} - __visible void __irq_entry smp_reschedule_interrupt(struct pt_regs *regs) { ack_APIC_irq(); - __smp_reschedule_interrupt(); - /* - * KVM uses this interrupt to force a cpu out of guest mode - */ -} - -__visible void __irq_entry smp_trace_reschedule_interrupt(struct pt_regs *regs) -{ - /* - * Need to call irq_enter() before calling the trace point. - * __smp_reschedule_interrupt() calls irq_enter/exit() too (in - * scheduler_ipi(). This is OK, since those functions are allowed - * to nest. - */ - ipi_entering_ack_irq(); - trace_reschedule_entry(RESCHEDULE_VECTOR); - __smp_reschedule_interrupt(); - trace_reschedule_exit(RESCHEDULE_VECTOR); - exiting_irq(); - /* - * KVM uses this interrupt to force a cpu out of guest mode - */ -} + inc_irq_stat(irq_resched_count); -static inline void __smp_call_function_interrupt(void) -{ - generic_smp_call_function_interrupt(); - inc_irq_stat(irq_call_count); + if (trace_resched_ipi_enabled()) { + /* + * scheduler_ipi() might call irq_enter() as well, but + * nested calls are fine. + */ + irq_enter(); + trace_reschedule_entry(RESCHEDULE_VECTOR); + scheduler_ipi(); + trace_reschedule_exit(RESCHEDULE_VECTOR); + irq_exit(); + return; + } + scheduler_ipi(); } __visible void __irq_entry smp_call_function_interrupt(struct pt_regs *regs) { ipi_entering_ack_irq(); - __smp_call_function_interrupt(); - exiting_irq(); -} - -__visible void __irq_entry -smp_trace_call_function_interrupt(struct pt_regs *regs) -{ - ipi_entering_ack_irq(); trace_call_function_entry(CALL_FUNCTION_VECTOR); - __smp_call_function_interrupt(); - trace_call_function_exit(CALL_FUNCTION_VECTOR); - exiting_irq(); -} - -static inline void __smp_call_function_single_interrupt(void) -{ - generic_smp_call_function_single_interrupt(); inc_irq_stat(irq_call_count); -} - -__visible void __irq_entry -smp_call_function_single_interrupt(struct pt_regs *regs) -{ - ipi_entering_ack_irq(); - __smp_call_function_single_interrupt(); + generic_smp_call_function_interrupt(); + trace_call_function_exit(CALL_FUNCTION_VECTOR); exiting_irq(); } -__visible void __irq_entry -smp_trace_call_function_single_interrupt(struct pt_regs *regs) +__visible void __irq_entry smp_call_function_single_interrupt(struct pt_regs *r) { ipi_entering_ack_irq(); trace_call_function_single_entry(CALL_FUNCTION_SINGLE_VECTOR); - __smp_call_function_single_interrupt(); + inc_irq_stat(irq_call_count); + generic_smp_call_function_single_interrupt(); trace_call_function_single_exit(CALL_FUNCTION_SINGLE_VECTOR); exiting_irq(); } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index b474c8de7fba..3d01df7d7cf6 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -77,6 +77,7 @@ #include <asm/i8259.h> #include <asm/realmode.h> #include <asm/misc.h> +#include <asm/qspinlock.h> /* Number of siblings per CPU package */ int smp_num_siblings = 1; @@ -100,9 +101,6 @@ DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); EXPORT_PER_CPU_SYMBOL(cpu_info); /* Logical package management. We might want to allocate that dynamically */ -static int *physical_to_logical_pkg __read_mostly; -static unsigned long *physical_package_map __read_mostly;; -static unsigned int max_physical_pkg_id __read_mostly; unsigned int __max_logical_packages __read_mostly; EXPORT_SYMBOL(__max_logical_packages); static unsigned int logical_packages __read_mostly; @@ -194,6 +192,12 @@ static void smp_callin(void) smp_store_cpu_info(cpuid); /* + * The topology information must be up to date before + * calibrate_delay() and notify_cpu_starting(). + */ + set_cpu_sibling_map(raw_smp_processor_id()); + + /* * Get our bogomips. * Update loops_per_jiffy in cpu_data. Previous call to * smp_store_cpu_info() stored a value that is close but not as @@ -203,11 +207,6 @@ static void smp_callin(void) cpu_data(cpuid).loops_per_jiffy = loops_per_jiffy; pr_debug("Stack at about %p\n", &cpuid); - /* - * This must be done before setting cpu_online_mask - * or calling notify_cpu_starting. - */ - set_cpu_sibling_map(raw_smp_processor_id()); wmb(); notify_cpu_starting(cpuid); @@ -226,16 +225,12 @@ static int enable_start_cpu0; static void notrace start_secondary(void *unused) { /* - * Don't put *anything* before cpu_init(), SMP booting is too - * fragile that we want to limit the things done here to the - * most necessary things. + * Don't put *anything* except direct CPU state initialization + * before cpu_init(), SMP booting is too fragile that we want to + * limit the things done here to the most necessary things. */ - cpu_init(); - x86_cpuinit.early_percpu_clock_init(); - preempt_disable(); - smp_callin(); - - enable_start_cpu0 = 0; + if (boot_cpu_has(X86_FEATURE_PCID)) + __write_cr4(__read_cr4() | X86_CR4_PCIDE); #ifdef CONFIG_X86_32 /* switch away from the initial page table */ @@ -243,22 +238,29 @@ static void notrace start_secondary(void *unused) __flush_tlb_all(); #endif + cpu_init(); + x86_cpuinit.early_percpu_clock_init(); + preempt_disable(); + smp_callin(); + + enable_start_cpu0 = 0; + /* otherwise gcc will move up smp_processor_id before the cpu_init */ barrier(); /* - * Check TSC synchronization with the BP: + * Check TSC synchronization with the boot CPU: */ check_tsc_sync_target(); /* - * Lock vector_lock and initialize the vectors on this cpu - * before setting the cpu online. We must set it online with - * vector_lock held to prevent a concurrent setup/teardown - * from seeing a half valid vector space. + * Lock vector_lock, set CPU online and bring the vector + * allocator online. Online must be set with vector_lock held + * to prevent a concurrent irq setup/teardown from seeing a + * half valid vector space. */ lock_vector_lock(); - setup_vector_irq(smp_processor_id()); set_cpu_online(smp_processor_id(), true); + lapic_online(); unlock_vector_lock(); cpu_set_state_online(smp_processor_id()); x86_platform.nmi_init(); @@ -276,108 +278,48 @@ static void notrace start_secondary(void *unused) } /** + * topology_phys_to_logical_pkg - Map a physical package id to a logical + * + * Returns logical package id or -1 if not found + */ +int topology_phys_to_logical_pkg(unsigned int phys_pkg) +{ + int cpu; + + for_each_possible_cpu(cpu) { + struct cpuinfo_x86 *c = &cpu_data(cpu); + + if (c->initialized && c->phys_proc_id == phys_pkg) + return c->logical_proc_id; + } + return -1; +} +EXPORT_SYMBOL(topology_phys_to_logical_pkg); + +/** * topology_update_package_map - Update the physical to logical package map * @pkg: The physical package id as retrieved via CPUID * @cpu: The cpu for which this is updated */ int topology_update_package_map(unsigned int pkg, unsigned int cpu) { - unsigned int new; - - /* Called from early boot ? */ - if (!physical_package_map) - return 0; - - if (pkg >= max_physical_pkg_id) - return -EINVAL; + int new; - /* Set the logical package id */ - if (test_and_set_bit(pkg, physical_package_map)) + /* Already available somewhere? */ + new = topology_phys_to_logical_pkg(pkg); + if (new >= 0) goto found; - if (logical_packages >= __max_logical_packages) { - pr_warn("Package %u of CPU %u exceeds BIOS package data %u.\n", - logical_packages, cpu, __max_logical_packages); - return -ENOSPC; - } - new = logical_packages++; if (new != pkg) { pr_info("CPU %u Converting physical %u to logical package %u\n", cpu, pkg, new); } - physical_to_logical_pkg[pkg] = new; - found: - cpu_data(cpu).logical_proc_id = physical_to_logical_pkg[pkg]; + cpu_data(cpu).logical_proc_id = new; return 0; } -/** - * topology_phys_to_logical_pkg - Map a physical package id to a logical - * - * Returns logical package id or -1 if not found - */ -int topology_phys_to_logical_pkg(unsigned int phys_pkg) -{ - if (phys_pkg >= max_physical_pkg_id) - return -1; - return physical_to_logical_pkg[phys_pkg]; -} -EXPORT_SYMBOL(topology_phys_to_logical_pkg); - -static void __init smp_init_package_map(struct cpuinfo_x86 *c, unsigned int cpu) -{ - unsigned int ncpus; - size_t size; - - /* - * Today neither Intel nor AMD support heterogenous systems. That - * might change in the future.... - * - * While ideally we'd want '* smp_num_siblings' in the below @ncpus - * computation, this won't actually work since some Intel BIOSes - * report inconsistent HT data when they disable HT. - * - * In particular, they reduce the APIC-IDs to only include the cores, - * but leave the CPUID topology to say there are (2) siblings. - * This means we don't know how many threads there will be until - * after the APIC enumeration. - * - * By not including this we'll sometimes over-estimate the number of - * logical packages by the amount of !present siblings, but this is - * still better than MAX_LOCAL_APIC. - * - * We use total_cpus not nr_cpu_ids because nr_cpu_ids can be limited - * on the command line leading to a similar issue as the HT disable - * problem because the hyperthreads are usually enumerated after the - * primary cores. - */ - ncpus = boot_cpu_data.x86_max_cores; - if (!ncpus) { - pr_warn("x86_max_cores == zero !?!?"); - ncpus = 1; - } - - __max_logical_packages = DIV_ROUND_UP(total_cpus, ncpus); - logical_packages = 0; - - /* - * Possibly larger than what we need as the number of apic ids per - * package can be smaller than the actual used apic ids. - */ - max_physical_pkg_id = DIV_ROUND_UP(MAX_LOCAL_APIC, ncpus); - size = max_physical_pkg_id * sizeof(unsigned int); - physical_to_logical_pkg = kmalloc(size, GFP_KERNEL); - memset(physical_to_logical_pkg, 0xff, size); - size = BITS_TO_LONGS(max_physical_pkg_id) * sizeof(unsigned long); - physical_package_map = kzalloc(size, GFP_KERNEL); - - pr_info("Max logical packages: %u\n", __max_logical_packages); - - topology_update_package_map(c->phys_proc_id, cpu); -} - void __init smp_store_boot_cpu_info(void) { int id = 0; /* CPU 0 */ @@ -385,7 +327,8 @@ void __init smp_store_boot_cpu_info(void) *c = boot_cpu_data; c->cpu_index = id; - smp_init_package_map(c, id); + topology_update_package_map(c->phys_proc_id, id); + c->initialized = true; } /* @@ -396,13 +339,16 @@ void smp_store_cpu_info(int id) { struct cpuinfo_x86 *c = &cpu_data(id); - *c = boot_cpu_data; + /* Copy boot_cpu_data only on the first bringup */ + if (!c->initialized) + *c = boot_cpu_data; c->cpu_index = id; /* * During boot time, CPU0 has this setup already. Save the info when * bringing up AP or offlined CPU0. */ identify_secondary_cpu(c); + c->initialized = true; } static bool @@ -958,8 +904,7 @@ void common_cpu_up(unsigned int cpu, struct task_struct *idle) #ifdef CONFIG_X86_32 /* Stack for startup_32 can be just as for start_secondary onwards */ irq_ctx_init(cpu); - per_cpu(cpu_current_top_of_stack, cpu) = - (unsigned long)task_stack_page(idle) + THREAD_SIZE; + per_cpu(cpu_current_top_of_stack, cpu) = task_top_of_stack(idle); #else initial_gs = per_cpu_offset(cpu); #endif @@ -971,7 +916,8 @@ void common_cpu_up(unsigned int cpu, struct task_struct *idle) * Returns zero if CPU booted OK, else error code from * ->wakeup_secondary_cpu. */ -static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) +static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle, + int *cpu0_nmi_registered) { volatile u32 *trampoline_status = (volatile u32 *) __va(real_mode_header->trampoline_status); @@ -979,7 +925,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) unsigned long start_ip = real_mode_header->trampoline_start; unsigned long boot_error = 0; - int cpu0_nmi_registered = 0; unsigned long timeout; idle->thread.sp = (unsigned long)task_pt_regs(idle); @@ -1035,7 +980,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) boot_error = apic->wakeup_secondary_cpu(apicid, start_ip); else boot_error = wakeup_cpu_via_init_nmi(cpu, start_ip, apicid, - &cpu0_nmi_registered); + cpu0_nmi_registered); if (!boot_error) { /* @@ -1080,12 +1025,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) */ smpboot_restore_warm_reset_vector(); } - /* - * Clean up the nmi handler. Do this after the callin and callout sync - * to avoid impact of possible long unregister time. - */ - if (cpu0_nmi_registered) - unregister_nmi_handler(NMI_LOCAL, "wake_cpu0"); return boot_error; } @@ -1093,10 +1032,11 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) int native_cpu_up(unsigned int cpu, struct task_struct *tidle) { int apicid = apic->cpu_present_to_apicid(cpu); + int cpu0_nmi_registered = 0; unsigned long flags; - int err; + int err, ret = 0; - WARN_ON(irqs_disabled()); + lockdep_assert_irqs_enabled(); pr_debug("++++++++++++++++++++=_---CPU UP %u\n", cpu); @@ -1131,10 +1071,11 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) common_cpu_up(cpu, tidle); - err = do_boot_cpu(apicid, cpu, tidle); + err = do_boot_cpu(apicid, cpu, tidle, &cpu0_nmi_registered); if (err) { pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu); - return -EIO; + ret = -EIO; + goto unreg_nmi; } /* @@ -1150,7 +1091,15 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) touch_nmi_watchdog(); } - return 0; +unreg_nmi: + /* + * Clean up the nmi handler. Do this after the callin and callout sync + * to avoid impact of possible long unregister time. + */ + if (cpu0_nmi_registered) + unregister_nmi_handler(NMI_LOCAL, "wake_cpu0"); + + return ret; } /** @@ -1183,17 +1132,10 @@ static __init void disable_smp(void) cpumask_set_cpu(0, topology_core_cpumask(0)); } -enum { - SMP_OK, - SMP_NO_CONFIG, - SMP_NO_APIC, - SMP_FORCE_UP, -}; - /* * Various sanity checks. */ -static int __init smp_sanity_check(unsigned max_cpus) +static void __init smp_sanity_check(void) { preempt_disable(); @@ -1231,16 +1173,6 @@ static int __init smp_sanity_check(unsigned max_cpus) } /* - * If we couldn't find an SMP configuration at boot time, - * get out of here now! - */ - if (!smp_found_config && !acpi_lapic) { - preempt_enable(); - pr_notice("SMP motherboard not detected\n"); - return SMP_NO_CONFIG; - } - - /* * Should not be necessary because the MP table should list the boot * CPU too, but we do it for the sake of robustness anyway. */ @@ -1250,29 +1182,6 @@ static int __init smp_sanity_check(unsigned max_cpus) physid_set(hard_smp_processor_id(), phys_cpu_present_map); } preempt_enable(); - - /* - * If we couldn't find a local APIC, then get out of here now! - */ - if (APIC_INTEGRATED(boot_cpu_apic_version) && - !boot_cpu_has(X86_FEATURE_APIC)) { - if (!disable_apic) { - pr_err("BIOS bug, local APIC #%d not detected!...\n", - boot_cpu_physical_apicid); - pr_err("... forcing use of dummy APIC emulation (tell your hw vendor)\n"); - } - return SMP_NO_APIC; - } - - /* - * If SMP should be disabled, then really disable it! - */ - if (!max_cpus) { - pr_info("SMP mode deactivated\n"); - return SMP_FORCE_UP; - } - - return SMP_OK; } static void __init smp_cpu_index_default(void) @@ -1287,9 +1196,18 @@ static void __init smp_cpu_index_default(void) } } +static void __init smp_get_logical_apicid(void) +{ + if (x2apic_mode) + cpu0_logical_apicid = apic_read(APIC_LDR); + else + cpu0_logical_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); +} + /* - * Prepare for SMP bootup. The MP table or ACPI has been read - * earlier. Just do some sanity checking here and enable APIC mode. + * Prepare for SMP bootup. + * @max_cpus: configured maximum number of CPUs, It is a legacy parameter + * for common interface support. */ void __init native_smp_prepare_cpus(unsigned int max_cpus) { @@ -1321,35 +1239,33 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) set_cpu_sibling_map(0); - switch (smp_sanity_check(max_cpus)) { - case SMP_NO_CONFIG: - disable_smp(); - if (APIC_init_uniprocessor()) - pr_notice("Local APIC not detected. Using dummy APIC emulation.\n"); - return; - case SMP_NO_APIC: + smp_sanity_check(); + + switch (apic_intr_mode) { + case APIC_PIC: + case APIC_VIRTUAL_WIRE_NO_CONFIG: disable_smp(); return; - case SMP_FORCE_UP: + case APIC_SYMMETRIC_IO_NO_ROUTING: disable_smp(); - apic_bsp_setup(false); + /* Setup local timer */ + x86_init.timers.setup_percpu_clockev(); return; - case SMP_OK: + case APIC_VIRTUAL_WIRE: + case APIC_SYMMETRIC_IO: break; } - if (read_apic_id() != boot_cpu_physical_apicid) { - panic("Boot APIC ID in local APIC unexpected (%d vs %d)", - read_apic_id(), boot_cpu_physical_apicid); - /* Or can we switch back to PIC here? */ - } + /* Setup local timer */ + x86_init.timers.setup_percpu_clockev(); - default_setup_apic_routing(); - cpu0_logical_apicid = apic_bsp_setup(false); + smp_get_logical_apicid(); pr_info("CPU0: "); print_cpu_info(&cpu_data(0)); + native_pv_lock_init(); + uv_system_init(); set_mtrr_aps_delayed_init(); @@ -1381,14 +1297,22 @@ void __init native_smp_prepare_boot_cpu(void) void __init native_smp_cpus_done(unsigned int max_cpus) { + int ncpus; + pr_debug("Boot done\n"); + /* + * Today neither Intel nor AMD support heterogenous systems so + * extrapolate the boot cpu's data to all packages. + */ + ncpus = cpu_data(0).booted_cores * smp_num_siblings; + __max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus); + pr_info("Max logical packages: %u\n", __max_logical_packages); if (x86_has_numa_in_package) set_sched_topology(x86_numa_in_package_topology); nmi_selftest(); impress_friends(); - setup_ioapic_dest(); mtrr_aps_init(); } @@ -1457,7 +1381,7 @@ __init void prefill_possible_map(void) /* nr_cpu_ids could be reduced via nr_cpus= */ if (possible > nr_cpu_ids) { - pr_warn("%d Processors exceeds NR_CPUS limit of %d\n", + pr_warn("%d Processors exceeds NR_CPUS limit of %u\n", possible, nr_cpu_ids); possible = nr_cpu_ids; } @@ -1547,13 +1471,14 @@ void cpu_disable_common(void) remove_cpu_from_maps(cpu); unlock_vector_lock(); fixup_irqs(); + lapic_offline(); } int native_cpu_disable(void) { int ret; - ret = check_irq_vectors_for_cpu_disable(); + ret = lapic_can_unplug_cpu(); if (ret) return ret; diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 8dabd7bf1673..77835bc021c7 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -30,7 +30,7 @@ static int save_stack_address(struct stack_trace *trace, unsigned long addr, return 0; } -static void __save_stack_trace(struct stack_trace *trace, +static void noinline __save_stack_trace(struct stack_trace *trace, struct task_struct *task, struct pt_regs *regs, bool nosched) { @@ -56,6 +56,7 @@ static void __save_stack_trace(struct stack_trace *trace, */ void save_stack_trace(struct stack_trace *trace) { + trace->skip++; __save_stack_trace(trace, current, NULL, false); } EXPORT_SYMBOL_GPL(save_stack_trace); @@ -70,6 +71,8 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) if (!try_get_task_stack(tsk)) return; + if (tsk == current) + trace->skip++; __save_stack_trace(trace, tsk, NULL, true); put_task_stack(tsk); @@ -88,8 +91,9 @@ EXPORT_SYMBOL_GPL(save_stack_trace_tsk); } \ }) -static int __save_stack_trace_reliable(struct stack_trace *trace, - struct task_struct *task) +static int __always_inline +__save_stack_trace_reliable(struct stack_trace *trace, + struct task_struct *task) { struct unwind_state state; struct pt_regs *regs; diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index 5f25cfbd952e..60d2c3798ba2 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * x86 single-step support code, common to 32-bit and 64-bit. */ @@ -13,7 +14,7 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re unsigned long addr, seg; addr = regs->ip; - seg = regs->cs & 0xffff; + seg = regs->cs; if (v8086_mode(regs)) { addr = (addr & 0xffff) + (seg << 4); return addr; diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 213ddf3e937d..676774b9bb8d 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/errno.h> #include <linux/sched.h> #include <linux/sched/mm.h> @@ -21,6 +22,7 @@ #include <asm/compat.h> #include <asm/ia32.h> #include <asm/syscalls.h> +#include <asm/mpx.h> /* * Align a virtual address to avoid aliasing in the I$ on AMD F15h. @@ -100,8 +102,8 @@ out: return error; } -static void find_start_end(unsigned long flags, unsigned long *begin, - unsigned long *end) +static void find_start_end(unsigned long addr, unsigned long flags, + unsigned long *begin, unsigned long *end) { if (!in_compat_syscall() && (flags & MAP_32BIT)) { /* This is usually used needed to map code in small @@ -120,7 +122,10 @@ static void find_start_end(unsigned long flags, unsigned long *begin, } *begin = get_mmap_base(1); - *end = in_compat_syscall() ? tasksize_32bit() : tasksize_64bit(); + if (in_compat_syscall()) + *end = task_size_32bit(); + else + *end = task_size_64bit(addr > DEFAULT_MAP_WINDOW); } unsigned long @@ -132,10 +137,14 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, struct vm_unmapped_area_info info; unsigned long begin, end; + addr = mpx_unmapped_area_check(addr, len, flags); + if (IS_ERR_VALUE(addr)) + return addr; + if (flags & MAP_FIXED) return addr; - find_start_end(flags, &begin, &end); + find_start_end(addr, flags, &begin, &end); if (len > end) return -ENOMEM; @@ -171,10 +180,15 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, unsigned long addr = addr0; struct vm_unmapped_area_info info; + addr = mpx_unmapped_area_check(addr, len, flags); + if (IS_ERR_VALUE(addr)) + return addr; + /* requested length too big for entire address space */ if (len > TASK_SIZE) return -ENOMEM; + /* No address checking. See comment at mmap_address_hint_valid() */ if (flags & MAP_FIXED) return addr; @@ -184,17 +198,30 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, /* requesting a specific address */ if (addr) { - addr = PAGE_ALIGN(addr); + addr &= PAGE_MASK; + if (!mmap_address_hint_valid(addr, len)) + goto get_unmapped_area; + vma = find_vma(mm, addr); - if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vm_start_gap(vma))) + if (!vma || addr + len <= vm_start_gap(vma)) return addr; } +get_unmapped_area: info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; info.low_limit = PAGE_SIZE; info.high_limit = get_mmap_base(0); + + /* + * If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area + * in the full address space. + * + * !in_compat_syscall() check to avoid high addresses for x32. + */ + if (addr > DEFAULT_MAP_WINDOW && !in_compat_syscall()) + info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW; + info.align_mask = 0; info.align_offset = pgoff << PAGE_SHIFT; if (filp) { diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index e0754cdbad37..749d189f8cd4 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 1991,1992,1995 Linus Torvalds * Copyright (c) 1994 Alan Modra @@ -84,6 +85,11 @@ void __init hpet_time_init(void) static __init void x86_late_time_init(void) { x86_init.timers.timer_init(); + /* + * After PIT/HPET timers init, select and setup + * the final interrupt mode for delivering IRQs. + */ + x86_init.irqs.intr_mode_init(); tsc_init(); } diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index dcd699baea1b..9a9c9b076955 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/errno.h> #include <linux/sched.h> @@ -93,7 +94,7 @@ static void set_tls_desc(struct task_struct *p, int idx, while (n-- > 0) { if (LDT_empty(info) || LDT_zero(info)) { - desc->a = desc->b = 0; + memset(desc, 0, sizeof(*desc)); } else { fill_ldt(desc, info); diff --git a/arch/x86/kernel/trace_clock.c b/arch/x86/kernel/trace_clock.c index 80bb24d9b880..b8e7abe00b06 100644 --- a/arch/x86/kernel/trace_clock.c +++ b/arch/x86/kernel/trace_clock.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * X86 trace clocks */ diff --git a/arch/x86/kernel/tracepoint.c b/arch/x86/kernel/tracepoint.c index 15515132bf0d..5bd30c442794 100644 --- a/arch/x86/kernel/tracepoint.c +++ b/arch/x86/kernel/tracepoint.c @@ -1,60 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Code for supporting irq vector tracepoints. * * Copyright (C) 2013 Seiji Aguchi <seiji.aguchi@hds.com> * */ -#include <asm/hw_irq.h> -#include <asm/desc.h> +#include <linux/jump_label.h> #include <linux/atomic.h> -atomic_t trace_idt_ctr = ATOMIC_INIT(0); -struct desc_ptr trace_idt_descr = { NR_VECTORS * 16 - 1, - (unsigned long) trace_idt_table }; - -/* No need to be aligned, but done to keep all IDTs defined the same way. */ -gate_desc trace_idt_table[NR_VECTORS] __page_aligned_bss; +#include <asm/hw_irq.h> +#include <asm/desc.h> -static int trace_irq_vector_refcount; -static DEFINE_MUTEX(irq_vector_mutex); +DEFINE_STATIC_KEY_FALSE(trace_pagefault_key); -static void set_trace_idt_ctr(int val) +int trace_pagefault_reg(void) { - atomic_set(&trace_idt_ctr, val); - /* Ensure the trace_idt_ctr is set before sending IPI */ - wmb(); + static_branch_inc(&trace_pagefault_key); + return 0; } -static void switch_idt(void *arg) +void trace_pagefault_unreg(void) { - unsigned long flags; - - local_irq_save(flags); - load_current_idt(); - local_irq_restore(flags); + static_branch_dec(&trace_pagefault_key); } -int trace_irq_vector_regfunc(void) +#ifdef CONFIG_SMP + +DEFINE_STATIC_KEY_FALSE(trace_resched_ipi_key); + +int trace_resched_ipi_reg(void) { - mutex_lock(&irq_vector_mutex); - if (!trace_irq_vector_refcount) { - set_trace_idt_ctr(1); - smp_call_function(switch_idt, NULL, 0); - switch_idt(NULL); - } - trace_irq_vector_refcount++; - mutex_unlock(&irq_vector_mutex); + static_branch_inc(&trace_resched_ipi_key); return 0; } -void trace_irq_vector_unregfunc(void) +void trace_resched_ipi_unreg(void) { - mutex_lock(&irq_vector_mutex); - trace_irq_vector_refcount--; - if (!trace_irq_vector_refcount) { - set_trace_idt_ctr(0); - smp_call_function(switch_idt, NULL, 0); - switch_idt(NULL); - } - mutex_unlock(&irq_vector_mutex); + static_branch_dec(&trace_resched_ipi_key); } + +#endif diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index bf54309b85da..989514c94a55 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -38,16 +38,10 @@ #include <linux/smp.h> #include <linux/io.h> -#ifdef CONFIG_EISA -#include <linux/ioport.h> -#include <linux/eisa.h> -#endif - #if defined(CONFIG_EDAC) #include <linux/edac.h> #endif -#include <asm/kmemcheck.h> #include <asm/stacktrace.h> #include <asm/processor.h> #include <asm/debugreg.h> @@ -65,25 +59,19 @@ #include <asm/trace/mpx.h> #include <asm/mpx.h> #include <asm/vm86.h> +#include <asm/umip.h> #ifdef CONFIG_X86_64 #include <asm/x86_init.h> #include <asm/pgalloc.h> #include <asm/proto.h> - -/* No need to be aligned, but done to keep all IDTs defined the same way. */ -gate_desc debug_idt_table[NR_VECTORS] __page_aligned_bss; #else #include <asm/processor-flags.h> #include <asm/setup.h> #include <asm/proto.h> #endif -/* Must be page-aligned because the real IDT is used in a fixmap. */ -gate_desc idt_table[NR_VECTORS] __page_aligned_bss; - -DECLARE_BITMAP(used_vectors, NR_VECTORS); -EXPORT_SYMBOL_GPL(used_vectors); +DECLARE_BITMAP(system_vectors, NR_VECTORS); static inline void cond_local_irq_enable(struct pt_regs *regs) { @@ -153,8 +141,7 @@ void ist_begin_non_atomic(struct pt_regs *regs) * will catch asm bugs and any attempt to use ist_preempt_enable * from double_fault. */ - BUG_ON((unsigned long)(current_top_of_stack() - - current_stack_pointer()) >= THREAD_SIZE); + BUG_ON(!on_thread_stack()); preempt_enable_no_resched(); } @@ -221,9 +208,6 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str, if (fixup_exception(regs, trapnr)) return 0; - if (fixup_bug(regs, trapnr)) - return 0; - tsk->thread.error_code = error_code; tsk->thread.trap_nr = trapnr; die(str, regs, error_code); @@ -304,6 +288,13 @@ static void do_error_trap(struct pt_regs *regs, long error_code, char *str, RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); + /* + * WARN*()s end up here; fix them up before we call the + * notifier chain. + */ + if (!user_mode(regs) && fixup_bug(regs, trapnr)) + return; + if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) != NOTIFY_STOP) { cond_local_irq_enable(regs); @@ -526,6 +517,11 @@ do_general_protection(struct pt_regs *regs, long error_code) RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); cond_local_irq_enable(regs); + if (static_cpu_has(X86_FEATURE_UMIP)) { + if (user_mode(regs) && fixup_umip_exception(regs)) + return; + } + if (v8086_mode(regs)) { local_irq_enable(); handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code); @@ -752,10 +748,6 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) if (!dr6 && user_mode(regs)) user_icebp = 1; - /* Catch kmemcheck conditions! */ - if ((dr6 & DR_STEP) && kmemcheck_trap(regs)) - goto exit; - /* Store the virtualized DR6 value */ tsk->thread.debugreg6 = dr6; @@ -935,87 +927,9 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) } #endif -/* Set of traps needed for early debugging. */ -void __init early_trap_init(void) -{ - /* - * Don't use IST to set DEBUG_STACK as it doesn't work until TSS - * is ready in cpu_init() <-- trap_init(). Before trap_init(), - * CPU runs at ring 0 so it is impossible to hit an invalid - * stack. Using the original stack works well enough at this - * early stage. DEBUG_STACK will be equipped after cpu_init() in - * trap_init(). - * - * We don't need to set trace_idt_table like set_intr_gate(), - * since we don't have trace_debug and it will be reset to - * 'debug' in trap_init() by set_intr_gate_ist(). - */ - set_intr_gate_notrace(X86_TRAP_DB, debug); - /* int3 can be called from all */ - set_system_intr_gate(X86_TRAP_BP, &int3); -#ifdef CONFIG_X86_32 - set_intr_gate(X86_TRAP_PF, page_fault); -#endif - load_idt(&idt_descr); -} - -void __init early_trap_pf_init(void) -{ -#ifdef CONFIG_X86_64 - set_intr_gate(X86_TRAP_PF, page_fault); -#endif -} - void __init trap_init(void) { - int i; - -#ifdef CONFIG_EISA - void __iomem *p = early_ioremap(0x0FFFD9, 4); - - if (readl(p) == 'E' + ('I'<<8) + ('S'<<16) + ('A'<<24)) - EISA_bus = 1; - early_iounmap(p, 4); -#endif - - set_intr_gate(X86_TRAP_DE, divide_error); - set_intr_gate_ist(X86_TRAP_NMI, &nmi, NMI_STACK); - /* int4 can be called from all */ - set_system_intr_gate(X86_TRAP_OF, &overflow); - set_intr_gate(X86_TRAP_BR, bounds); - set_intr_gate(X86_TRAP_UD, invalid_op); - set_intr_gate(X86_TRAP_NM, device_not_available); -#ifdef CONFIG_X86_32 - set_task_gate(X86_TRAP_DF, GDT_ENTRY_DOUBLEFAULT_TSS); -#else - set_intr_gate_ist(X86_TRAP_DF, &double_fault, DOUBLEFAULT_STACK); -#endif - set_intr_gate(X86_TRAP_OLD_MF, coprocessor_segment_overrun); - set_intr_gate(X86_TRAP_TS, invalid_TSS); - set_intr_gate(X86_TRAP_NP, segment_not_present); - set_intr_gate(X86_TRAP_SS, stack_segment); - set_intr_gate(X86_TRAP_GP, general_protection); - set_intr_gate(X86_TRAP_SPURIOUS, spurious_interrupt_bug); - set_intr_gate(X86_TRAP_MF, coprocessor_error); - set_intr_gate(X86_TRAP_AC, alignment_check); -#ifdef CONFIG_X86_MCE - set_intr_gate_ist(X86_TRAP_MC, &machine_check, MCE_STACK); -#endif - set_intr_gate(X86_TRAP_XF, simd_coprocessor_error); - - /* Reserve all the builtin and the syscall vector: */ - for (i = 0; i < FIRST_EXTERNAL_VECTOR; i++) - set_bit(i, used_vectors); - -#ifdef CONFIG_IA32_EMULATION - set_system_intr_gate(IA32_SYSCALL_VECTOR, entry_INT80_compat); - set_bit(IA32_SYSCALL_VECTOR, used_vectors); -#endif - -#ifdef CONFIG_X86_32 - set_system_intr_gate(IA32_SYSCALL_VECTOR, entry_INT80_32); - set_bit(IA32_SYSCALL_VECTOR, used_vectors); -#endif + idt_setup_traps(); /* * Set the IDT descriptor to a fixed read-only location, so that the @@ -1030,20 +944,9 @@ void __init trap_init(void) */ cpu_init(); - /* - * X86_TRAP_DB and X86_TRAP_BP have been set - * in early_trap_init(). However, ITS works only after - * cpu_init() loads TSS. See comments in early_trap_init(). - */ - set_intr_gate_ist(X86_TRAP_DB, &debug, DEBUG_STACK); - /* int3 can be called from all */ - set_system_intr_gate_ist(X86_TRAP_BP, &int3, DEBUG_STACK); + idt_setup_ist_traps(); x86_init.irqs.trap_init(); -#ifdef CONFIG_X86_64 - memcpy(&debug_idt_table, &idt_table, IDT_ENTRIES * 16); - set_nmi_gate(X86_TRAP_DB, &debug); - set_nmi_gate(X86_TRAP_BP, &int3); -#endif + idt_setup_debugidt_traps(); } diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 796d96bb0821..8ea117f8142e 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -112,7 +112,7 @@ static void cyc2ns_data_init(struct cyc2ns_data *data) data->cyc2ns_offset = 0; } -static void cyc2ns_init(int cpu) +static void __init cyc2ns_init(int cpu) { struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu); @@ -812,13 +812,13 @@ unsigned long native_calibrate_cpu(void) return tsc_pit_min; } -int recalibrate_cpu_khz(void) +void recalibrate_cpu_khz(void) { #ifndef CONFIG_SMP unsigned long cpu_khz_old = cpu_khz; if (!boot_cpu_has(X86_FEATURE_TSC)) - return -ENODEV; + return; cpu_khz = x86_platform.calibrate_cpu(); tsc_khz = x86_platform.calibrate_tsc(); @@ -828,10 +828,6 @@ int recalibrate_cpu_khz(void) cpu_khz = tsc_khz; cpu_data(0).loops_per_jiffy = cpufreq_scale(cpu_data(0).loops_per_jiffy, cpu_khz_old, cpu_khz); - - return 0; -#else - return -ENODEV; #endif } @@ -959,17 +955,21 @@ core_initcall(cpufreq_register_tsc_scaling); /* * If ART is present detect the numerator:denominator to convert to TSC */ -static void detect_art(void) +static void __init detect_art(void) { unsigned int unused[2]; if (boot_cpu_data.cpuid_level < ART_CPUID_LEAF) return; - /* Don't enable ART in a VM, non-stop TSC and TSC_ADJUST required */ + /* + * Don't enable ART in a VM, non-stop TSC and TSC_ADJUST required, + * and the TSC counter resets must not occur asynchronously. + */ if (boot_cpu_has(X86_FEATURE_HYPERVISOR) || !boot_cpu_has(X86_FEATURE_NONSTOP_TSC) || - !boot_cpu_has(X86_FEATURE_TSC_ADJUST)) + !boot_cpu_has(X86_FEATURE_TSC_ADJUST) || + tsc_async_resets) return; cpuid(ART_CPUID_LEAF, &art_to_tsc_denominator, @@ -1263,6 +1263,25 @@ static int __init init_tsc_clocksource(void) */ device_initcall(init_tsc_clocksource); +void __init tsc_early_delay_calibrate(void) +{ + unsigned long lpj; + + if (!boot_cpu_has(X86_FEATURE_TSC)) + return; + + cpu_khz = x86_platform.calibrate_cpu(); + tsc_khz = x86_platform.calibrate_tsc(); + + tsc_khz = tsc_khz ? : cpu_khz; + if (!tsc_khz) + return; + + lpj = tsc_khz * 1000; + do_div(lpj, HZ); + loops_per_jiffy = lpj; +} + void __init tsc_init(void) { u64 lpj, cyc; @@ -1346,12 +1365,10 @@ void __init tsc_init(void) unsigned long calibrate_delay_is_known(void) { int sibling, cpu = smp_processor_id(); - struct cpumask *mask = topology_core_cpumask(cpu); - - if (!tsc_disabled && !cpu_has(&cpu_data(cpu), X86_FEATURE_CONSTANT_TSC)) - return 0; + int constant_tsc = cpu_has(&cpu_data(cpu), X86_FEATURE_CONSTANT_TSC); + const struct cpumask *mask = topology_core_cpumask(cpu); - if (!mask) + if (tsc_disabled || !constant_tsc || !mask) return 0; sibling = cpumask_any_but(mask, cpu); diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 7842371bc9e4..ec534f978867 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * check TSC synchronization. * @@ -30,6 +31,20 @@ struct tsc_adjust { static DEFINE_PER_CPU(struct tsc_adjust, tsc_adjust); +/* + * TSC's on different sockets may be reset asynchronously. + * This may cause the TSC ADJUST value on socket 0 to be NOT 0. + */ +bool __read_mostly tsc_async_resets; + +void mark_tsc_async_resets(char *reason) +{ + if (tsc_async_resets) + return; + tsc_async_resets = true; + pr_info("tsc: Marking TSC async resets true due to %s\n", reason); +} + void tsc_verify_tsc_adjust(bool resume) { struct tsc_adjust *adj = this_cpu_ptr(&tsc_adjust); @@ -38,6 +53,10 @@ void tsc_verify_tsc_adjust(bool resume) if (!boot_cpu_has(X86_FEATURE_TSC_ADJUST)) return; + /* Skip unnecessary error messages if TSC already unstable */ + if (check_tsc_unstable()) + return; + /* Rate limit the MSR check */ if (!resume && time_before(jiffies, adj->nextcheck)) return; @@ -71,12 +90,22 @@ static void tsc_sanitize_first_cpu(struct tsc_adjust *cur, s64 bootval, * non zero. We don't do that on non boot cpus because physical * hotplug should have set the ADJUST register to a value > 0 so * the TSC is in sync with the already running cpus. + * + * Also don't force the ADJUST value to zero if that is a valid value + * for socket 0 as determined by the system arch. This is required + * when multiple sockets are reset asynchronously with each other + * and socket 0 may not have an TSC ADJUST value of 0. */ if (bootcpu && bootval != 0) { - pr_warn(FW_BUG "TSC ADJUST: CPU%u: %lld force to 0\n", cpu, - bootval); - wrmsrl(MSR_IA32_TSC_ADJUST, 0); - bootval = 0; + if (likely(!tsc_async_resets)) { + pr_warn(FW_BUG "TSC ADJUST: CPU%u: %lld force to 0\n", + cpu, bootval); + wrmsrl(MSR_IA32_TSC_ADJUST, 0); + bootval = 0; + } else { + pr_info("TSC ADJUST: CPU%u: %lld NOT forced to 0\n", + cpu, bootval); + } } cur->adjusted = bootval; } @@ -90,6 +119,10 @@ bool __init tsc_store_and_check_tsc_adjust(bool bootcpu) if (!boot_cpu_has(X86_FEATURE_TSC_ADJUST)) return false; + /* Skip unnecessary error messages if TSC already unstable */ + if (check_tsc_unstable()) + return false; + rdmsrl(MSR_IA32_TSC_ADJUST, bootval); cur->bootval = bootval; cur->nextcheck = jiffies + HZ; @@ -118,6 +151,13 @@ bool tsc_store_and_check_tsc_adjust(bool bootcpu) cur->warned = false; /* + * If a non-zero TSC value for socket 0 may be valid then the default + * adjusted value cannot assumed to be zero either. + */ + if (tsc_async_resets) + cur->adjusted = bootval; + + /* * Check whether this CPU is the first in a package to come up. In * this case do not check the boot value against another package * because the new package might have been physically hotplugged, @@ -138,10 +178,9 @@ bool tsc_store_and_check_tsc_adjust(bool bootcpu) * Compare the boot value and complain if it differs in the * package. */ - if (bootval != ref->bootval) { - pr_warn(FW_BUG "TSC ADJUST differs: Reference CPU%u: %lld CPU%u: %lld\n", - refcpu, ref->bootval, cpu, bootval); - } + if (bootval != ref->bootval) + printk_once(FW_BUG "TSC ADJUST differs within socket(s), fixing all errors\n"); + /* * The TSC_ADJUST values in a package must be the same. If the boot * value on this newly upcoming CPU differs from the adjustment @@ -149,8 +188,6 @@ bool tsc_store_and_check_tsc_adjust(bool bootcpu) * adjusted value. */ if (bootval != ref->adjusted) { - pr_warn("TSC ADJUST synchronize: Reference CPU%u: %lld CPU%u: %lld\n", - refcpu, ref->adjusted, cpu, bootval); cur->adjusted = ref->adjusted; wrmsrl(MSR_IA32_TSC_ADJUST, ref->adjusted); } diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c new file mode 100644 index 000000000000..f44ce0fb3583 --- /dev/null +++ b/arch/x86/kernel/umip.c @@ -0,0 +1,428 @@ +/* + * umip.c Emulation for instruction protected by the Intel User-Mode + * Instruction Prevention feature + * + * Copyright (c) 2017, Intel Corporation. + * Ricardo Neri <ricardo.neri-calderon@linux.intel.com> + */ + +#include <linux/uaccess.h> +#include <asm/umip.h> +#include <asm/traps.h> +#include <asm/insn.h> +#include <asm/insn-eval.h> +#include <linux/ratelimit.h> + +#undef pr_fmt +#define pr_fmt(fmt) "umip: " fmt + +/** DOC: Emulation for User-Mode Instruction Prevention (UMIP) + * + * The feature User-Mode Instruction Prevention present in recent Intel + * processor prevents a group of instructions (sgdt, sidt, sldt, smsw, and str) + * from being executed with CPL > 0. Otherwise, a general protection fault is + * issued. + * + * Rather than relaying to the user space the general protection fault caused by + * the UMIP-protected instructions (in the form of a SIGSEGV signal), it can be + * trapped and emulate the result of such instructions to provide dummy values. + * This allows to both conserve the current kernel behavior and not reveal the + * system resources that UMIP intends to protect (i.e., the locations of the + * global descriptor and interrupt descriptor tables, the segment selectors of + * the local descriptor table, the value of the task state register and the + * contents of the CR0 register). + * + * This emulation is needed because certain applications (e.g., WineHQ and + * DOSEMU2) rely on this subset of instructions to function. + * + * The instructions protected by UMIP can be split in two groups. Those which + * return a kernel memory address (sgdt and sidt) and those which return a + * value (sldt, str and smsw). + * + * For the instructions that return a kernel memory address, applications + * such as WineHQ rely on the result being located in the kernel memory space, + * not the actual location of the table. The result is emulated as a hard-coded + * value that, lies close to the top of the kernel memory. The limit for the GDT + * and the IDT are set to zero. + * + * Given that sldt and str are not commonly used in programs that run on WineHQ + * or DOSEMU2, they are not emulated. + * + * The instruction smsw is emulated to return the value that the register CR0 + * has at boot time as set in the head_32. + * + * Also, emulation is provided only for 32-bit processes; 64-bit processes + * that attempt to use the instructions that UMIP protects will receive the + * SIGSEGV signal issued as a consequence of the general protection fault. + * + * Care is taken to appropriately emulate the results when segmentation is + * used. That is, rather than relying on USER_DS and USER_CS, the function + * insn_get_addr_ref() inspects the segment descriptor pointed by the + * registers in pt_regs. This ensures that we correctly obtain the segment + * base address and the address and operand sizes even if the user space + * application uses a local descriptor table. + */ + +#define UMIP_DUMMY_GDT_BASE 0xfffe0000 +#define UMIP_DUMMY_IDT_BASE 0xffff0000 + +/* + * The SGDT and SIDT instructions store the contents of the global descriptor + * table and interrupt table registers, respectively. The destination is a + * memory operand of X+2 bytes. X bytes are used to store the base address of + * the table and 2 bytes are used to store the limit. In 32-bit processes, the + * only processes for which emulation is provided, X has a value of 4. + */ +#define UMIP_GDT_IDT_BASE_SIZE 4 +#define UMIP_GDT_IDT_LIMIT_SIZE 2 + +#define UMIP_INST_SGDT 0 /* 0F 01 /0 */ +#define UMIP_INST_SIDT 1 /* 0F 01 /1 */ +#define UMIP_INST_SMSW 2 /* 0F 01 /4 */ +#define UMIP_INST_SLDT 3 /* 0F 00 /0 */ +#define UMIP_INST_STR 4 /* 0F 00 /1 */ + +const char * const umip_insns[5] = { + [UMIP_INST_SGDT] = "SGDT", + [UMIP_INST_SIDT] = "SIDT", + [UMIP_INST_SMSW] = "SMSW", + [UMIP_INST_SLDT] = "SLDT", + [UMIP_INST_STR] = "STR", +}; + +#define umip_pr_err(regs, fmt, ...) \ + umip_printk(regs, KERN_ERR, fmt, ##__VA_ARGS__) +#define umip_pr_warning(regs, fmt, ...) \ + umip_printk(regs, KERN_WARNING, fmt, ##__VA_ARGS__) + +/** + * umip_printk() - Print a rate-limited message + * @regs: Register set with the context in which the warning is printed + * @log_level: Kernel log level to print the message + * @fmt: The text string to print + * + * Print the text contained in @fmt. The print rate is limited to bursts of 5 + * messages every two minutes. The purpose of this customized version of + * printk() is to print messages when user space processes use any of the + * UMIP-protected instructions. Thus, the printed text is prepended with the + * task name and process ID number of the current task as well as the + * instruction and stack pointers in @regs as seen when entering kernel mode. + * + * Returns: + * + * None. + */ +static __printf(3, 4) +void umip_printk(const struct pt_regs *regs, const char *log_level, + const char *fmt, ...) +{ + /* Bursts of 5 messages every two minutes */ + static DEFINE_RATELIMIT_STATE(ratelimit, 2 * 60 * HZ, 5); + struct task_struct *tsk = current; + struct va_format vaf; + va_list args; + + if (!__ratelimit(&ratelimit)) + return; + + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + printk("%s" pr_fmt("%s[%d] ip:%lx sp:%lx: %pV"), log_level, tsk->comm, + task_pid_nr(tsk), regs->ip, regs->sp, &vaf); + va_end(args); +} + +/** + * identify_insn() - Identify a UMIP-protected instruction + * @insn: Instruction structure with opcode and ModRM byte. + * + * From the opcode and ModRM.reg in @insn identify, if any, a UMIP-protected + * instruction that can be emulated. + * + * Returns: + * + * On success, a constant identifying a specific UMIP-protected instruction that + * can be emulated. + * + * -EINVAL on error or when not an UMIP-protected instruction that can be + * emulated. + */ +static int identify_insn(struct insn *insn) +{ + /* By getting modrm we also get the opcode. */ + insn_get_modrm(insn); + + if (!insn->modrm.nbytes) + return -EINVAL; + + /* All the instructions of interest start with 0x0f. */ + if (insn->opcode.bytes[0] != 0xf) + return -EINVAL; + + if (insn->opcode.bytes[1] == 0x1) { + switch (X86_MODRM_REG(insn->modrm.value)) { + case 0: + return UMIP_INST_SGDT; + case 1: + return UMIP_INST_SIDT; + case 4: + return UMIP_INST_SMSW; + default: + return -EINVAL; + } + } else if (insn->opcode.bytes[1] == 0x0) { + if (X86_MODRM_REG(insn->modrm.value) == 0) + return UMIP_INST_SLDT; + else if (X86_MODRM_REG(insn->modrm.value) == 1) + return UMIP_INST_STR; + else + return -EINVAL; + } else { + return -EINVAL; + } +} + +/** + * emulate_umip_insn() - Emulate UMIP instructions and return dummy values + * @insn: Instruction structure with operands + * @umip_inst: A constant indicating the instruction to emulate + * @data: Buffer into which the dummy result is stored + * @data_size: Size of the emulated result + * + * Emulate an instruction protected by UMIP and provide a dummy result. The + * result of the emulation is saved in @data. The size of the results depends + * on both the instruction and type of operand (register vs memory address). + * The size of the result is updated in @data_size. Caller is responsible + * of providing a @data buffer of at least UMIP_GDT_IDT_BASE_SIZE + + * UMIP_GDT_IDT_LIMIT_SIZE bytes. + * + * Returns: + * + * 0 on success, -EINVAL on error while emulating. + */ +static int emulate_umip_insn(struct insn *insn, int umip_inst, + unsigned char *data, int *data_size) +{ + unsigned long dummy_base_addr, dummy_value; + unsigned short dummy_limit = 0; + + if (!data || !data_size || !insn) + return -EINVAL; + /* + * These two instructions return the base address and limit of the + * global and interrupt descriptor table, respectively. According to the + * Intel Software Development manual, the base address can be 24-bit, + * 32-bit or 64-bit. Limit is always 16-bit. If the operand size is + * 16-bit, the returned value of the base address is supposed to be a + * zero-extended 24-byte number. However, it seems that a 32-byte number + * is always returned irrespective of the operand size. + */ + if (umip_inst == UMIP_INST_SGDT || umip_inst == UMIP_INST_SIDT) { + /* SGDT and SIDT do not use registers operands. */ + if (X86_MODRM_MOD(insn->modrm.value) == 3) + return -EINVAL; + + if (umip_inst == UMIP_INST_SGDT) + dummy_base_addr = UMIP_DUMMY_GDT_BASE; + else + dummy_base_addr = UMIP_DUMMY_IDT_BASE; + + *data_size = UMIP_GDT_IDT_LIMIT_SIZE + UMIP_GDT_IDT_BASE_SIZE; + + memcpy(data + 2, &dummy_base_addr, UMIP_GDT_IDT_BASE_SIZE); + memcpy(data, &dummy_limit, UMIP_GDT_IDT_LIMIT_SIZE); + + } else if (umip_inst == UMIP_INST_SMSW) { + dummy_value = CR0_STATE; + + /* + * Even though the CR0 register has 4 bytes, the number + * of bytes to be copied in the result buffer is determined + * by whether the operand is a register or a memory location. + * If operand is a register, return as many bytes as the operand + * size. If operand is memory, return only the two least + * siginificant bytes of CR0. + */ + if (X86_MODRM_MOD(insn->modrm.value) == 3) + *data_size = insn->opnd_bytes; + else + *data_size = 2; + + memcpy(data, &dummy_value, *data_size); + /* STR and SLDT are not emulated */ + } else { + return -EINVAL; + } + + return 0; +} + +/** + * force_sig_info_umip_fault() - Force a SIGSEGV with SEGV_MAPERR + * @addr: Address that caused the signal + * @regs: Register set containing the instruction pointer + * + * Force a SIGSEGV signal with SEGV_MAPERR as the error code. This function is + * intended to be used to provide a segmentation fault when the result of the + * UMIP emulation could not be copied to the user space memory. + * + * Returns: none + */ +static void force_sig_info_umip_fault(void __user *addr, struct pt_regs *regs) +{ + siginfo_t info; + struct task_struct *tsk = current; + + tsk->thread.cr2 = (unsigned long)addr; + tsk->thread.error_code = X86_PF_USER | X86_PF_WRITE; + tsk->thread.trap_nr = X86_TRAP_PF; + + info.si_signo = SIGSEGV; + info.si_errno = 0; + info.si_code = SEGV_MAPERR; + info.si_addr = addr; + force_sig_info(SIGSEGV, &info, tsk); + + if (!(show_unhandled_signals && unhandled_signal(tsk, SIGSEGV))) + return; + + umip_pr_err(regs, "segfault in emulation. error%x\n", + X86_PF_USER | X86_PF_WRITE); +} + +/** + * fixup_umip_exception() - Fixup a general protection fault caused by UMIP + * @regs: Registers as saved when entering the #GP handler + * + * The instructions sgdt, sidt, str, smsw, sldt cause a general protection + * fault if executed with CPL > 0 (i.e., from user space). If the offending + * user-space process is not in long mode, this function fixes the exception + * up and provides dummy results for sgdt, sidt and smsw; str and sldt are not + * fixed up. Also long mode user-space processes are not fixed up. + * + * If operands are memory addresses, results are copied to user-space memory as + * indicated by the instruction pointed by eIP using the registers indicated in + * the instruction operands. If operands are registers, results are copied into + * the context that was saved when entering kernel mode. + * + * Returns: + * + * True if emulation was successful; false if not. + */ +bool fixup_umip_exception(struct pt_regs *regs) +{ + int not_copied, nr_copied, reg_offset, dummy_data_size, umip_inst; + unsigned long seg_base = 0, *reg_addr; + /* 10 bytes is the maximum size of the result of UMIP instructions */ + unsigned char dummy_data[10] = { 0 }; + unsigned char buf[MAX_INSN_SIZE]; + void __user *uaddr; + struct insn insn; + int seg_defs; + + if (!regs) + return false; + + /* + * If not in user-space long mode, a custom code segment could be in + * use. This is true in protected mode (if the process defined a local + * descriptor table), or virtual-8086 mode. In most of the cases + * seg_base will be zero as in USER_CS. + */ + if (!user_64bit_mode(regs)) + seg_base = insn_get_seg_base(regs, INAT_SEG_REG_CS); + + if (seg_base == -1L) + return false; + + not_copied = copy_from_user(buf, (void __user *)(seg_base + regs->ip), + sizeof(buf)); + nr_copied = sizeof(buf) - not_copied; + + /* + * The copy_from_user above could have failed if user code is protected + * by a memory protection key. Give up on emulation in such a case. + * Should we issue a page fault? + */ + if (!nr_copied) + return false; + + insn_init(&insn, buf, nr_copied, user_64bit_mode(regs)); + + /* + * Override the default operand and address sizes with what is specified + * in the code segment descriptor. The instruction decoder only sets + * the address size it to either 4 or 8 address bytes and does nothing + * for the operand bytes. This OK for most of the cases, but we could + * have special cases where, for instance, a 16-bit code segment + * descriptor is used. + * If there is an address override prefix, the instruction decoder + * correctly updates these values, even for 16-bit defaults. + */ + seg_defs = insn_get_code_seg_params(regs); + if (seg_defs == -EINVAL) + return false; + + insn.addr_bytes = INSN_CODE_SEG_ADDR_SZ(seg_defs); + insn.opnd_bytes = INSN_CODE_SEG_OPND_SZ(seg_defs); + + insn_get_length(&insn); + if (nr_copied < insn.length) + return false; + + umip_inst = identify_insn(&insn); + if (umip_inst < 0) + return false; + + umip_pr_warning(regs, "%s instruction cannot be used by applications.\n", + umip_insns[umip_inst]); + + /* Do not emulate SLDT, STR or user long mode processes. */ + if (umip_inst == UMIP_INST_STR || umip_inst == UMIP_INST_SLDT || user_64bit_mode(regs)) + return false; + + umip_pr_warning(regs, "For now, expensive software emulation returns the result.\n"); + + if (emulate_umip_insn(&insn, umip_inst, dummy_data, &dummy_data_size)) + return false; + + /* + * If operand is a register, write result to the copy of the register + * value that was pushed to the stack when entering into kernel mode. + * Upon exit, the value we write will be restored to the actual hardware + * register. + */ + if (X86_MODRM_MOD(insn.modrm.value) == 3) { + reg_offset = insn_get_modrm_rm_off(&insn, regs); + + /* + * Negative values are usually errors. In memory addressing, + * the exception is -EDOM. Since we expect a register operand, + * all negative values are errors. + */ + if (reg_offset < 0) + return false; + + reg_addr = (unsigned long *)((unsigned long)regs + reg_offset); + memcpy(reg_addr, dummy_data, dummy_data_size); + } else { + uaddr = insn_get_addr_ref(&insn, regs); + if ((unsigned long)uaddr == -1L) + return false; + + nr_copied = copy_to_user(uaddr, dummy_data, dummy_data_size); + if (nr_copied > 0) { + /* + * If copy fails, send a signal and tell caller that + * fault was fixed up. + */ + force_sig_info_umip_fault(uaddr, regs); + return true; + } + } + + /* increase IP to let the program keep going */ + regs->ip += insn.length; + return true; +} diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index b9389d72b2f7..3dc26f95d46e 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -10,20 +10,22 @@ #define FRAME_HEADER_SIZE (sizeof(long) * 2) -/* - * This disables KASAN checking when reading a value from another task's stack, - * since the other task could be running on another CPU and could have poisoned - * the stack in the meantime. - */ -#define READ_ONCE_TASK_STACK(task, x) \ -({ \ - unsigned long val; \ - if (task == current) \ - val = READ_ONCE(x); \ - else \ - val = READ_ONCE_NOCHECK(x); \ - val; \ -}) +unsigned long unwind_get_return_address(struct unwind_state *state) +{ + if (unwind_done(state)) + return 0; + + return __kernel_text_address(state->ip) ? state->ip : 0; +} +EXPORT_SYMBOL_GPL(unwind_get_return_address); + +unsigned long *unwind_get_return_address_ptr(struct unwind_state *state) +{ + if (unwind_done(state)) + return NULL; + + return state->regs ? &state->regs->ip : state->bp + 1; +} static void unwind_dump(struct unwind_state *state) { @@ -42,7 +44,8 @@ static void unwind_dump(struct unwind_state *state) state->stack_info.type, state->stack_info.next_sp, state->stack_mask, state->graph_idx); - for (sp = state->orig_sp; sp; sp = PTR_ALIGN(stack_info.next_sp, sizeof(long))) { + for (sp = PTR_ALIGN(state->orig_sp, sizeof(long)); sp; + sp = PTR_ALIGN(stack_info.next_sp, sizeof(long))) { if (get_stack_info(sp, state->task, &stack_info, &visit_mask)) break; @@ -66,15 +69,6 @@ static void unwind_dump(struct unwind_state *state) } } -unsigned long unwind_get_return_address(struct unwind_state *state) -{ - if (unwind_done(state)) - return 0; - - return __kernel_text_address(state->ip) ? state->ip : 0; -} -EXPORT_SYMBOL_GPL(unwind_get_return_address); - static size_t regs_size(struct pt_regs *regs) { /* x86_32 regs from kernel mode are two words shorter: */ @@ -91,10 +85,8 @@ static bool in_entry_code(unsigned long ip) if (addr >= __entry_text_start && addr < __entry_text_end) return true; -#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN) if (addr >= __irqentry_text_start && addr < __irqentry_text_end) return true; -#endif return false; } @@ -183,6 +175,7 @@ static bool is_last_task_frame(struct unwind_state *state) * This determines if the frame pointer actually contains an encoded pointer to * pt_regs on the stack. See ENCODE_FRAME_POINTER. */ +#ifdef CONFIG_X86_64 static struct pt_regs *decode_frame_pointer(unsigned long *bp) { unsigned long regs = (unsigned long)bp; @@ -192,6 +185,23 @@ static struct pt_regs *decode_frame_pointer(unsigned long *bp) return (struct pt_regs *)(regs & ~0x1); } +#else +static struct pt_regs *decode_frame_pointer(unsigned long *bp) +{ + unsigned long regs = (unsigned long)bp; + + if (regs & 0x80000000) + return NULL; + + return (struct pt_regs *)(regs | 0x80000000); +} +#endif + +#ifdef CONFIG_X86_32 +#define KERNEL_REGS_SIZE (sizeof(struct pt_regs) - 2*sizeof(long)) +#else +#define KERNEL_REGS_SIZE (sizeof(struct pt_regs)) +#endif static bool update_stack_state(struct unwind_state *state, unsigned long *next_bp) @@ -211,7 +221,7 @@ static bool update_stack_state(struct unwind_state *state, regs = decode_frame_pointer(next_bp); if (regs) { frame = (unsigned long *)regs; - len = regs_size(regs); + len = KERNEL_REGS_SIZE; state->got_irq = true; } else { frame = next_bp; @@ -235,6 +245,14 @@ static bool update_stack_state(struct unwind_state *state, frame < prev_frame_end) return false; + /* + * On 32-bit with user mode regs, make sure the last two regs are safe + * to access: + */ + if (IS_ENABLED(CONFIG_X86_32) && regs && user_mode(regs) && + !on_stack(info, frame, len + 2*sizeof(long))) + return false; + /* Move state to the next frame: */ if (regs) { state->regs = regs; @@ -337,6 +355,13 @@ bad_address: state->regs->sp < (unsigned long)task_pt_regs(state->task)) goto the_end; + /* + * There are some known frame pointer issues on 32-bit. Disable + * unwinder warnings on 32-bit until it gets objtool support. + */ + if (IS_ENABLED(CONFIG_X86_32)) + goto the_end; + if (state->regs) { printk_deferred_once(KERN_WARNING "WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n", diff --git a/arch/x86/kernel/unwind_guess.c b/arch/x86/kernel/unwind_guess.c index 039f36738e49..4f0e17b90463 100644 --- a/arch/x86/kernel/unwind_guess.c +++ b/arch/x86/kernel/unwind_guess.c @@ -19,6 +19,11 @@ unsigned long unwind_get_return_address(struct unwind_state *state) } EXPORT_SYMBOL_GPL(unwind_get_return_address); +unsigned long *unwind_get_return_address_ptr(struct unwind_state *state) +{ + return NULL; +} + bool unwind_next_frame(struct unwind_state *state) { struct stack_info *info = &state->stack_info; diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c new file mode 100644 index 000000000000..a3f973b2c97a --- /dev/null +++ b/arch/x86/kernel/unwind_orc.c @@ -0,0 +1,583 @@ +#include <linux/module.h> +#include <linux/sort.h> +#include <asm/ptrace.h> +#include <asm/stacktrace.h> +#include <asm/unwind.h> +#include <asm/orc_types.h> +#include <asm/orc_lookup.h> +#include <asm/sections.h> + +#define orc_warn(fmt, ...) \ + printk_deferred_once(KERN_WARNING pr_fmt("WARNING: " fmt), ##__VA_ARGS__) + +extern int __start_orc_unwind_ip[]; +extern int __stop_orc_unwind_ip[]; +extern struct orc_entry __start_orc_unwind[]; +extern struct orc_entry __stop_orc_unwind[]; + +static DEFINE_MUTEX(sort_mutex); +int *cur_orc_ip_table = __start_orc_unwind_ip; +struct orc_entry *cur_orc_table = __start_orc_unwind; + +unsigned int lookup_num_blocks; +bool orc_init; + +static inline unsigned long orc_ip(const int *ip) +{ + return (unsigned long)ip + *ip; +} + +static struct orc_entry *__orc_find(int *ip_table, struct orc_entry *u_table, + unsigned int num_entries, unsigned long ip) +{ + int *first = ip_table; + int *last = ip_table + num_entries - 1; + int *mid = first, *found = first; + + if (!num_entries) + return NULL; + + /* + * Do a binary range search to find the rightmost duplicate of a given + * starting address. Some entries are section terminators which are + * "weak" entries for ensuring there are no gaps. They should be + * ignored when they conflict with a real entry. + */ + while (first <= last) { + mid = first + ((last - first) / 2); + + if (orc_ip(mid) <= ip) { + found = mid; + first = mid + 1; + } else + last = mid - 1; + } + + return u_table + (found - ip_table); +} + +#ifdef CONFIG_MODULES +static struct orc_entry *orc_module_find(unsigned long ip) +{ + struct module *mod; + + mod = __module_address(ip); + if (!mod || !mod->arch.orc_unwind || !mod->arch.orc_unwind_ip) + return NULL; + return __orc_find(mod->arch.orc_unwind_ip, mod->arch.orc_unwind, + mod->arch.num_orcs, ip); +} +#else +static struct orc_entry *orc_module_find(unsigned long ip) +{ + return NULL; +} +#endif + +static struct orc_entry *orc_find(unsigned long ip) +{ + if (!orc_init) + return NULL; + + /* For non-init vmlinux addresses, use the fast lookup table: */ + if (ip >= LOOKUP_START_IP && ip < LOOKUP_STOP_IP) { + unsigned int idx, start, stop; + + idx = (ip - LOOKUP_START_IP) / LOOKUP_BLOCK_SIZE; + + if (unlikely((idx >= lookup_num_blocks-1))) { + orc_warn("WARNING: bad lookup idx: idx=%u num=%u ip=%pB\n", + idx, lookup_num_blocks, (void *)ip); + return NULL; + } + + start = orc_lookup[idx]; + stop = orc_lookup[idx + 1] + 1; + + if (unlikely((__start_orc_unwind + start >= __stop_orc_unwind) || + (__start_orc_unwind + stop > __stop_orc_unwind))) { + orc_warn("WARNING: bad lookup value: idx=%u num=%u start=%u stop=%u ip=%pB\n", + idx, lookup_num_blocks, start, stop, (void *)ip); + return NULL; + } + + return __orc_find(__start_orc_unwind_ip + start, + __start_orc_unwind + start, stop - start, ip); + } + + /* vmlinux .init slow lookup: */ + if (ip >= (unsigned long)_sinittext && ip < (unsigned long)_einittext) + return __orc_find(__start_orc_unwind_ip, __start_orc_unwind, + __stop_orc_unwind_ip - __start_orc_unwind_ip, ip); + + /* Module lookup: */ + return orc_module_find(ip); +} + +static void orc_sort_swap(void *_a, void *_b, int size) +{ + struct orc_entry *orc_a, *orc_b; + struct orc_entry orc_tmp; + int *a = _a, *b = _b, tmp; + int delta = _b - _a; + + /* Swap the .orc_unwind_ip entries: */ + tmp = *a; + *a = *b + delta; + *b = tmp - delta; + + /* Swap the corresponding .orc_unwind entries: */ + orc_a = cur_orc_table + (a - cur_orc_ip_table); + orc_b = cur_orc_table + (b - cur_orc_ip_table); + orc_tmp = *orc_a; + *orc_a = *orc_b; + *orc_b = orc_tmp; +} + +static int orc_sort_cmp(const void *_a, const void *_b) +{ + struct orc_entry *orc_a; + const int *a = _a, *b = _b; + unsigned long a_val = orc_ip(a); + unsigned long b_val = orc_ip(b); + + if (a_val > b_val) + return 1; + if (a_val < b_val) + return -1; + + /* + * The "weak" section terminator entries need to always be on the left + * to ensure the lookup code skips them in favor of real entries. + * These terminator entries exist to handle any gaps created by + * whitelisted .o files which didn't get objtool generation. + */ + orc_a = cur_orc_table + (a - cur_orc_ip_table); + return orc_a->sp_reg == ORC_REG_UNDEFINED ? -1 : 1; +} + +#ifdef CONFIG_MODULES +void unwind_module_init(struct module *mod, void *_orc_ip, size_t orc_ip_size, + void *_orc, size_t orc_size) +{ + int *orc_ip = _orc_ip; + struct orc_entry *orc = _orc; + unsigned int num_entries = orc_ip_size / sizeof(int); + + WARN_ON_ONCE(orc_ip_size % sizeof(int) != 0 || + orc_size % sizeof(*orc) != 0 || + num_entries != orc_size / sizeof(*orc)); + + /* + * The 'cur_orc_*' globals allow the orc_sort_swap() callback to + * associate an .orc_unwind_ip table entry with its corresponding + * .orc_unwind entry so they can both be swapped. + */ + mutex_lock(&sort_mutex); + cur_orc_ip_table = orc_ip; + cur_orc_table = orc; + sort(orc_ip, num_entries, sizeof(int), orc_sort_cmp, orc_sort_swap); + mutex_unlock(&sort_mutex); + + mod->arch.orc_unwind_ip = orc_ip; + mod->arch.orc_unwind = orc; + mod->arch.num_orcs = num_entries; +} +#endif + +void __init unwind_init(void) +{ + size_t orc_ip_size = (void *)__stop_orc_unwind_ip - (void *)__start_orc_unwind_ip; + size_t orc_size = (void *)__stop_orc_unwind - (void *)__start_orc_unwind; + size_t num_entries = orc_ip_size / sizeof(int); + struct orc_entry *orc; + int i; + + if (!num_entries || orc_ip_size % sizeof(int) != 0 || + orc_size % sizeof(struct orc_entry) != 0 || + num_entries != orc_size / sizeof(struct orc_entry)) { + orc_warn("WARNING: Bad or missing .orc_unwind table. Disabling unwinder.\n"); + return; + } + + /* Sort the .orc_unwind and .orc_unwind_ip tables: */ + sort(__start_orc_unwind_ip, num_entries, sizeof(int), orc_sort_cmp, + orc_sort_swap); + + /* Initialize the fast lookup table: */ + lookup_num_blocks = orc_lookup_end - orc_lookup; + for (i = 0; i < lookup_num_blocks-1; i++) { + orc = __orc_find(__start_orc_unwind_ip, __start_orc_unwind, + num_entries, + LOOKUP_START_IP + (LOOKUP_BLOCK_SIZE * i)); + if (!orc) { + orc_warn("WARNING: Corrupt .orc_unwind table. Disabling unwinder.\n"); + return; + } + + orc_lookup[i] = orc - __start_orc_unwind; + } + + /* Initialize the ending block: */ + orc = __orc_find(__start_orc_unwind_ip, __start_orc_unwind, num_entries, + LOOKUP_STOP_IP); + if (!orc) { + orc_warn("WARNING: Corrupt .orc_unwind table. Disabling unwinder.\n"); + return; + } + orc_lookup[lookup_num_blocks-1] = orc - __start_orc_unwind; + + orc_init = true; +} + +unsigned long unwind_get_return_address(struct unwind_state *state) +{ + if (unwind_done(state)) + return 0; + + return __kernel_text_address(state->ip) ? state->ip : 0; +} +EXPORT_SYMBOL_GPL(unwind_get_return_address); + +unsigned long *unwind_get_return_address_ptr(struct unwind_state *state) +{ + if (unwind_done(state)) + return NULL; + + if (state->regs) + return &state->regs->ip; + + if (state->sp) + return (unsigned long *)state->sp - 1; + + return NULL; +} + +static bool stack_access_ok(struct unwind_state *state, unsigned long addr, + size_t len) +{ + struct stack_info *info = &state->stack_info; + + /* + * If the address isn't on the current stack, switch to the next one. + * + * We may have to traverse multiple stacks to deal with the possibility + * that info->next_sp could point to an empty stack and the address + * could be on a subsequent stack. + */ + while (!on_stack(info, (void *)addr, len)) + if (get_stack_info(info->next_sp, state->task, info, + &state->stack_mask)) + return false; + + return true; +} + +static bool deref_stack_reg(struct unwind_state *state, unsigned long addr, + unsigned long *val) +{ + if (!stack_access_ok(state, addr, sizeof(long))) + return false; + + *val = READ_ONCE_NOCHECK(*(unsigned long *)addr); + return true; +} + +#define REGS_SIZE (sizeof(struct pt_regs)) +#define SP_OFFSET (offsetof(struct pt_regs, sp)) +#define IRET_REGS_SIZE (REGS_SIZE - offsetof(struct pt_regs, ip)) +#define IRET_SP_OFFSET (SP_OFFSET - offsetof(struct pt_regs, ip)) + +static bool deref_stack_regs(struct unwind_state *state, unsigned long addr, + unsigned long *ip, unsigned long *sp, bool full) +{ + size_t regs_size = full ? REGS_SIZE : IRET_REGS_SIZE; + size_t sp_offset = full ? SP_OFFSET : IRET_SP_OFFSET; + struct pt_regs *regs = (struct pt_regs *)(addr + regs_size - REGS_SIZE); + + if (IS_ENABLED(CONFIG_X86_64)) { + if (!stack_access_ok(state, addr, regs_size)) + return false; + + *ip = regs->ip; + *sp = regs->sp; + + return true; + } + + if (!stack_access_ok(state, addr, sp_offset)) + return false; + + *ip = regs->ip; + + if (user_mode(regs)) { + if (!stack_access_ok(state, addr + sp_offset, + REGS_SIZE - SP_OFFSET)) + return false; + + *sp = regs->sp; + } else + *sp = (unsigned long)®s->sp; + + return true; +} + +bool unwind_next_frame(struct unwind_state *state) +{ + unsigned long ip_p, sp, orig_ip, prev_sp = state->sp; + enum stack_type prev_type = state->stack_info.type; + struct orc_entry *orc; + struct pt_regs *ptregs; + bool indirect = false; + + if (unwind_done(state)) + return false; + + /* Don't let modules unload while we're reading their ORC data. */ + preempt_disable(); + + /* Have we reached the end? */ + if (state->regs && user_mode(state->regs)) + goto done; + + /* + * Find the orc_entry associated with the text address. + * + * Decrement call return addresses by one so they work for sibling + * calls and calls to noreturn functions. + */ + orc = orc_find(state->signal ? state->ip : state->ip - 1); + if (!orc || orc->sp_reg == ORC_REG_UNDEFINED) + goto done; + orig_ip = state->ip; + + /* Find the previous frame's stack: */ + switch (orc->sp_reg) { + case ORC_REG_SP: + sp = state->sp + orc->sp_offset; + break; + + case ORC_REG_BP: + sp = state->bp + orc->sp_offset; + break; + + case ORC_REG_SP_INDIRECT: + sp = state->sp + orc->sp_offset; + indirect = true; + break; + + case ORC_REG_BP_INDIRECT: + sp = state->bp + orc->sp_offset; + indirect = true; + break; + + case ORC_REG_R10: + if (!state->regs || !state->full_regs) { + orc_warn("missing regs for base reg R10 at ip %pB\n", + (void *)state->ip); + goto done; + } + sp = state->regs->r10; + break; + + case ORC_REG_R13: + if (!state->regs || !state->full_regs) { + orc_warn("missing regs for base reg R13 at ip %pB\n", + (void *)state->ip); + goto done; + } + sp = state->regs->r13; + break; + + case ORC_REG_DI: + if (!state->regs || !state->full_regs) { + orc_warn("missing regs for base reg DI at ip %pB\n", + (void *)state->ip); + goto done; + } + sp = state->regs->di; + break; + + case ORC_REG_DX: + if (!state->regs || !state->full_regs) { + orc_warn("missing regs for base reg DX at ip %pB\n", + (void *)state->ip); + goto done; + } + sp = state->regs->dx; + break; + + default: + orc_warn("unknown SP base reg %d for ip %pB\n", + orc->sp_reg, (void *)state->ip); + goto done; + } + + if (indirect) { + if (!deref_stack_reg(state, sp, &sp)) + goto done; + } + + /* Find IP, SP and possibly regs: */ + switch (orc->type) { + case ORC_TYPE_CALL: + ip_p = sp - sizeof(long); + + if (!deref_stack_reg(state, ip_p, &state->ip)) + goto done; + + state->ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, + state->ip, (void *)ip_p); + + state->sp = sp; + state->regs = NULL; + state->signal = false; + break; + + case ORC_TYPE_REGS: + if (!deref_stack_regs(state, sp, &state->ip, &state->sp, true)) { + orc_warn("can't dereference registers at %p for ip %pB\n", + (void *)sp, (void *)orig_ip); + goto done; + } + + state->regs = (struct pt_regs *)sp; + state->full_regs = true; + state->signal = true; + break; + + case ORC_TYPE_REGS_IRET: + if (!deref_stack_regs(state, sp, &state->ip, &state->sp, false)) { + orc_warn("can't dereference iret registers at %p for ip %pB\n", + (void *)sp, (void *)orig_ip); + goto done; + } + + ptregs = container_of((void *)sp, struct pt_regs, ip); + if ((unsigned long)ptregs >= prev_sp && + on_stack(&state->stack_info, ptregs, REGS_SIZE)) { + state->regs = ptregs; + state->full_regs = false; + } else + state->regs = NULL; + + state->signal = true; + break; + + default: + orc_warn("unknown .orc_unwind entry type %d for ip %pB\n", + orc->type, (void *)orig_ip); + break; + } + + /* Find BP: */ + switch (orc->bp_reg) { + case ORC_REG_UNDEFINED: + if (state->regs && state->full_regs) + state->bp = state->regs->bp; + break; + + case ORC_REG_PREV_SP: + if (!deref_stack_reg(state, sp + orc->bp_offset, &state->bp)) + goto done; + break; + + case ORC_REG_BP: + if (!deref_stack_reg(state, state->bp + orc->bp_offset, &state->bp)) + goto done; + break; + + default: + orc_warn("unknown BP base reg %d for ip %pB\n", + orc->bp_reg, (void *)orig_ip); + goto done; + } + + /* Prevent a recursive loop due to bad ORC data: */ + if (state->stack_info.type == prev_type && + on_stack(&state->stack_info, (void *)state->sp, sizeof(long)) && + state->sp <= prev_sp) { + orc_warn("stack going in the wrong direction? ip=%pB\n", + (void *)orig_ip); + goto done; + } + + preempt_enable(); + return true; + +done: + preempt_enable(); + state->stack_info.type = STACK_TYPE_UNKNOWN; + return false; +} +EXPORT_SYMBOL_GPL(unwind_next_frame); + +void __unwind_start(struct unwind_state *state, struct task_struct *task, + struct pt_regs *regs, unsigned long *first_frame) +{ + memset(state, 0, sizeof(*state)); + state->task = task; + + /* + * Refuse to unwind the stack of a task while it's executing on another + * CPU. This check is racy, but that's ok: the unwinder has other + * checks to prevent it from going off the rails. + */ + if (task_on_another_cpu(task)) + goto done; + + if (regs) { + if (user_mode(regs)) + goto done; + + state->ip = regs->ip; + state->sp = kernel_stack_pointer(regs); + state->bp = regs->bp; + state->regs = regs; + state->full_regs = true; + state->signal = true; + + } else if (task == current) { + asm volatile("lea (%%rip), %0\n\t" + "mov %%rsp, %1\n\t" + "mov %%rbp, %2\n\t" + : "=r" (state->ip), "=r" (state->sp), + "=r" (state->bp)); + + } else { + struct inactive_task_frame *frame = (void *)task->thread.sp; + + state->sp = task->thread.sp; + state->bp = READ_ONCE_NOCHECK(frame->bp); + state->ip = READ_ONCE_NOCHECK(frame->ret_addr); + } + + if (get_stack_info((unsigned long *)state->sp, state->task, + &state->stack_info, &state->stack_mask)) + return; + + /* + * The caller can provide the address of the first frame directly + * (first_frame) or indirectly (regs->sp) to indicate which stack frame + * to start unwinding at. Skip ahead until we reach it. + */ + + /* When starting from regs, skip the regs frame: */ + if (regs) { + unwind_next_frame(state); + return; + } + + /* Otherwise, skip ahead to the user-specified starting frame: */ + while (!unwind_done(state) && + (!on_stack(&state->stack_info, first_frame, sizeof(long)) || + state->sp <= (unsigned long)first_frame)) + unwind_next_frame(state); + + return; + +done: + state->stack_info.type = STACK_TYPE_UNKNOWN; + return; +} +EXPORT_SYMBOL_GPL(__unwind_start); diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 495c776de4b4..a3755d293a48 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -271,12 +271,15 @@ static bool is_prefix_bad(struct insn *insn) int i; for (i = 0; i < insn->prefixes.nbytes; i++) { - switch (insn->prefixes.bytes[i]) { - case 0x26: /* INAT_PFX_ES */ - case 0x2E: /* INAT_PFX_CS */ - case 0x36: /* INAT_PFX_DS */ - case 0x3E: /* INAT_PFX_SS */ - case 0xF0: /* INAT_PFX_LOCK */ + insn_attr_t attr; + + attr = inat_get_opcode_attribute(insn->prefixes.bytes[i]); + switch (attr) { + case INAT_MAKE_PREFIX(INAT_PFX_ES): + case INAT_MAKE_PREFIX(INAT_PFX_CS): + case INAT_MAKE_PREFIX(INAT_PFX_DS): + case INAT_MAKE_PREFIX(INAT_PFX_SS): + case INAT_MAKE_PREFIX(INAT_PFX_LOCK): return true; } } diff --git a/arch/x86/kernel/verify_cpu.S b/arch/x86/kernel/verify_cpu.S index 014ea59aa153..3d3c2f71f617 100644 --- a/arch/x86/kernel/verify_cpu.S +++ b/arch/x86/kernel/verify_cpu.S @@ -33,7 +33,7 @@ #include <asm/cpufeatures.h> #include <asm/msr-index.h> -verify_cpu: +ENTRY(verify_cpu) pushf # Save caller passed flags push $0 # Kill any dangerous flags popf @@ -139,3 +139,4 @@ verify_cpu: popf # Restore caller passed flags xorl %eax, %eax ret +ENDPROC(verify_cpu) diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 7924a5356c8a..5edb27f1a2c4 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1994 Linus Torvalds * @@ -54,6 +55,7 @@ #include <asm/irq.h> #include <asm/traps.h> #include <asm/vm86.h> +#include <asm/switch_to.h> /* * Known problems: @@ -93,7 +95,6 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval) { - struct tss_struct *tss; struct task_struct *tsk = current; struct vm86plus_struct __user *user; struct vm86 *vm86 = current->thread.vm86; @@ -145,12 +146,13 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval) do_exit(SIGSEGV); } - tss = &per_cpu(cpu_tss, get_cpu()); + preempt_disable(); tsk->thread.sp0 = vm86->saved_sp0; tsk->thread.sysenter_cs = __KERNEL_CS; - load_sp0(tss, &tsk->thread); + update_sp0(tsk); + refresh_sysenter_cs(&tsk->thread); vm86->saved_sp0 = 0; - put_cpu(); + preempt_enable(); memcpy(®s->pt, &vm86->regs32, sizeof(struct pt_regs)); @@ -236,7 +238,6 @@ SYSCALL_DEFINE2(vm86, unsigned long, cmd, unsigned long, arg) static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) { - struct tss_struct *tss; struct task_struct *tsk = current; struct vm86 *vm86 = tsk->thread.vm86; struct kernel_vm86_regs vm86regs; @@ -364,15 +365,17 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) vm86->saved_sp0 = tsk->thread.sp0; lazy_save_gs(vm86->regs32.gs); - tss = &per_cpu(cpu_tss, get_cpu()); /* make room for real-mode segments */ + preempt_disable(); tsk->thread.sp0 += 16; - if (static_cpu_has(X86_FEATURE_SEP)) + if (static_cpu_has(X86_FEATURE_SEP)) { tsk->thread.sysenter_cs = 0; + refresh_sysenter_cs(&tsk->thread); + } - load_sp0(tss, &tsk->thread); - put_cpu(); + update_sp0(tsk); + preempt_enable(); if (vm86->flags & VM86_SCREEN_BITMAP) mark_screen_rdonly(tsk->mm); diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index c8a3b61be0aa..a4009fb9be87 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * ld script for the x86 kernel * @@ -24,6 +25,7 @@ #include <asm/asm-offsets.h> #include <asm/thread_info.h> #include <asm/page_types.h> +#include <asm/orc_lookup.h> #include <asm/cache.h> #include <asm/boot.h> @@ -148,6 +150,8 @@ SECTIONS BUG_TABLE + ORC_UNWIND_TABLE + . = ALIGN(PAGE_SIZE); __vvar_page = .; diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c index b034b1b14b9c..44685fb2a192 100644 --- a/arch/x86/kernel/vsmp_64.c +++ b/arch/x86/kernel/vsmp_64.c @@ -26,9 +26,6 @@ #define TOPOLOGY_REGISTER_OFFSET 0x10 -/* Flag below is initialized once during vSMP PCI initialization. */ -static int irq_routing_comply = 1; - #if defined CONFIG_PCI && defined CONFIG_PARAVIRT /* * Interrupt control on vSMPowered systems: @@ -105,9 +102,6 @@ static void __init set_vsmp_pv_ops(void) if (cap & ctl & BIT(8)) { ctl &= ~BIT(8); - /* Interrupt routing set to ignore */ - irq_routing_comply = 0; - #ifdef CONFIG_PROC_FS /* Don't let users change irq affinity via procfs */ no_irq_affinity = 1; @@ -211,23 +205,10 @@ static int apicid_phys_pkg_id(int initial_apic_id, int index_msb) return hard_smp_processor_id() >> index_msb; } -/* - * In vSMP, all cpus should be capable of handling interrupts, regardless of - * the APIC used. - */ -static void fill_vector_allocation_domain(int cpu, struct cpumask *retmask, - const struct cpumask *mask) -{ - cpumask_setall(retmask); -} - static void vsmp_apic_post_init(void) { /* need to update phys_pkg_id */ apic->phys_pkg_id = apicid_phys_pkg_id; - - if (!irq_routing_comply) - apic->vector_allocation_domain = fill_vector_allocation_domain; } void __init vsmp_init(void) diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index a088b2c47f73..1151ccd72ce9 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -28,6 +28,8 @@ void x86_init_noop(void) { } void __init x86_init_uint_noop(unsigned int unused) { } int __init iommu_init_noop(void) { return 0; } void iommu_shutdown_noop(void) { } +bool __init bool_x86_init_noop(void) { return false; } +void x86_op_int_noop(int cpu) { } /* * The platform setup functions are preset with the default functions @@ -55,6 +57,7 @@ struct x86_init_ops x86_init __initdata = { .pre_vector_init = init_ISA_irqs, .intr_init = native_init_IRQ, .trap_init = x86_init_noop, + .intr_mode_init = apic_intr_mode_init }, .oem = { @@ -81,6 +84,13 @@ struct x86_init_ops x86_init __initdata = { .init_irq = x86_default_pci_init_irq, .fixup_irqs = x86_default_pci_fixup_irqs, }, + + .hyper = { + .init_platform = x86_init_noop, + .guest_late_init = x86_init_noop, + .x2apic_available = bool_x86_init_noop, + .init_mem_mapping = x86_init_noop, + }, }; struct x86_cpuinit_ops x86_cpuinit = { @@ -101,6 +111,7 @@ struct x86_platform_ops x86_platform __ro_after_init = { .get_nmi_reason = default_get_nmi_reason, .save_sched_clock_state = tsc_save_sched_clock_state, .restore_sched_clock_state = tsc_restore_sched_clock_state, + .hyper.pin_vcpu = x86_op_int_noop, }; EXPORT_SYMBOL_GPL(x86_platform); |