diff options
Diffstat (limited to 'arch/x86/kernel')
114 files changed, 5168 insertions, 2151 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 04ceea8f4a89..5eeb808eb024 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -47,6 +47,8 @@ endif # non-deterministic coverage. KCOV_INSTRUMENT := n +CFLAGS_head$(BITS).o += -fno-stack-protector + CFLAGS_irq.o := -I $(srctree)/$(src)/../include/asm/trace obj-y := process_$(BITS).o signal.o @@ -159,5 +161,3 @@ ifeq ($(CONFIG_X86_64),y) obj-$(CONFIG_MMCONF_FAM10H) += mmconf-fam10h_64.o obj-y += vsmp_64.o endif - -obj-$(CONFIG_IMA_SECURE_AND_OR_TRUSTED_BOOT) += ima_arch.o diff --git a/arch/x86/kernel/acpi/apei.c b/arch/x86/kernel/acpi/apei.c index c22fb55abcfd..0916f00a992e 100644 --- a/arch/x86/kernel/acpi/apei.c +++ b/arch/x86/kernel/acpi/apei.c @@ -43,3 +43,8 @@ void arch_apei_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) apei_mce_report_mem_error(sev, mem_err); #endif } + +int arch_apei_report_x86_error(struct cper_ia_proc_ctx *ctx_info, u64 lapic_id) +{ + return apei_smca_report_x86_error(ctx_info, lapic_id); +} diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index c8daa92f38dc..5d3a0b8fd379 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -112,7 +112,7 @@ SYM_FUNC_START(do_suspend_lowlevel) movq pt_regs_r14(%rax), %r14 movq pt_regs_r15(%rax), %r15 -#ifdef CONFIG_KASAN +#if defined(CONFIG_KASAN) && CONFIG_KASAN_STACK /* * The suspend path may have poisoned some areas deeper in the stack, * which we now need to unpoison. diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 4adbe65afe23..8d778e46725d 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -807,6 +807,15 @@ static inline temp_mm_state_t use_temporary_mm(struct mm_struct *mm) temp_mm_state_t temp_state; lockdep_assert_irqs_disabled(); + + /* + * Make sure not to be in TLB lazy mode, as otherwise we'll end up + * with a stale address space WITHOUT being in lazy mode after + * restoring the previous mm. + */ + if (this_cpu_read(cpu_tlbstate.is_lazy)) + leave_mm(smp_processor_id()); + temp_state.mm = this_cpu_read(cpu_tlbstate.loaded_mm); switch_mm_irqs_off(NULL, mm, current); @@ -1365,7 +1374,7 @@ void __ref text_poke_queue(void *addr, const void *opcode, size_t len, const voi * @addr: address to patch * @opcode: opcode of new instruction * @len: length to copy - * @handler: address to jump to when the temporary breakpoint is hit + * @emulate: instruction to be emulated * * Update a single instruction with the vector in the stack, avoiding * dynamically allocated memory. This function should be used when it is diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 18f6b7c4bd79..b4396952c9a6 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -384,7 +384,7 @@ struct resource *amd_get_mmconfig_range(struct resource *res) int amd_get_subcaches(int cpu) { - struct pci_dev *link = node_to_amd_nb(amd_get_nb_id(cpu))->link; + struct pci_dev *link = node_to_amd_nb(topology_die_id(cpu))->link; unsigned int mask; if (!amd_nb_has_feature(AMD_NB_L3_PARTITIONING)) @@ -398,7 +398,7 @@ int amd_get_subcaches(int cpu) int amd_set_subcaches(int cpu, unsigned long mask) { static unsigned int reset, ban; - struct amd_northbridge *nb = node_to_amd_nb(amd_get_nb_id(cpu)); + struct amd_northbridge *nb = node_to_amd_nb(topology_die_id(cpu)); unsigned int reg; int cuid; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index b3eef1d5c903..819db00c9388 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -41,6 +41,7 @@ #include <asm/perf_event.h> #include <asm/x86_init.h> #include <linux/atomic.h> +#include <asm/barrier.h> #include <asm/mpspec.h> #include <asm/i8259.h> #include <asm/proto.h> @@ -94,6 +95,11 @@ static unsigned int disabled_cpu_apicid __ro_after_init = BAD_APICID; static int apic_extnmi __ro_after_init = APIC_EXTNMI_BSP; /* + * Hypervisor supports 15 bits of APIC ID in MSI Extended Destination ID + */ +static bool virt_ext_dest_id __ro_after_init; + +/* * Map cpu index to physical APIC ID */ DEFINE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid, BAD_APICID); @@ -472,6 +478,9 @@ static int lapic_next_deadline(unsigned long delta, { u64 tsc; + /* This MSR is special and need a special fence: */ + weak_wrmsr_fence(); + tsc = rdtsc(); wrmsrl(MSR_IA32_TSC_DEADLINE, tsc + (((u64) delta) * TSC_DIVISOR)); return 0; @@ -1591,7 +1600,7 @@ static void setup_local_APIC(void) apic->init_apic_ldr(); #ifdef CONFIG_X86_32 - if (apic->dest_logical) { + if (apic->dest_mode_logical) { int logical_apicid, ldr_apicid; /* @@ -1738,6 +1747,7 @@ void apic_ap_setup(void) #ifdef CONFIG_X86_X2APIC int x2apic_mode; +EXPORT_SYMBOL_GPL(x2apic_mode); enum { X2APIC_OFF, @@ -1841,20 +1851,34 @@ static __init void try_to_enable_x2apic(int remap_mode) return; if (remap_mode != IRQ_REMAP_X2APIC_MODE) { - /* IR is required if there is APIC ID > 255 even when running - * under KVM + u32 apic_limit = 255; + + /* + * Using X2APIC without IR is not architecturally supported + * on bare metal but may be supported in guests. */ - if (max_physical_apicid > 255 || - !x86_init.hyper.x2apic_available()) { + if (!x86_init.hyper.x2apic_available()) { pr_info("x2apic: IRQ remapping doesn't support X2APIC mode\n"); x2apic_disable(); return; } /* - * without IR all CPUs can be addressed by IOAPIC/MSI - * only in physical mode + * If the hypervisor supports extended destination ID in + * MSI, that increases the maximum APIC ID that can be + * used for non-remapped IRQ domains. */ + if (x86_init.hyper.msi_ext_dest_id()) { + virt_ext_dest_id = 1; + apic_limit = 32767; + } + + /* + * Without IR, all CPUs can be addressed by IOAPIC/MSI only + * in physical mode, and CPUs with an APIC ID that cannnot + * be addressed must not be brought online. + */ + x2apic_set_max_apicid(apic_limit); x2apic_phys = 1; } x2apic_enable(); @@ -2478,6 +2502,46 @@ int hard_smp_processor_id(void) return read_apic_id(); } +void __irq_msi_compose_msg(struct irq_cfg *cfg, struct msi_msg *msg, + bool dmar) +{ + memset(msg, 0, sizeof(*msg)); + + msg->arch_addr_lo.base_address = X86_MSI_BASE_ADDRESS_LOW; + msg->arch_addr_lo.dest_mode_logical = apic->dest_mode_logical; + msg->arch_addr_lo.destid_0_7 = cfg->dest_apicid & 0xFF; + + msg->arch_data.delivery_mode = APIC_DELIVERY_MODE_FIXED; + msg->arch_data.vector = cfg->vector; + + msg->address_hi = X86_MSI_BASE_ADDRESS_HIGH; + /* + * Only the IOMMU itself can use the trick of putting destination + * APIC ID into the high bits of the address. Anything else would + * just be writing to memory if it tried that, and needs IR to + * address APICs which can't be addressed in the normal 32-bit + * address range at 0xFFExxxxx. That is typically just 8 bits, but + * some hypervisors allow the extended destination ID field in bits + * 5-11 to be used, giving support for 15 bits of APIC IDs in total. + */ + if (dmar) + msg->arch_addr_hi.destid_8_31 = cfg->dest_apicid >> 8; + else if (virt_ext_dest_id && cfg->dest_apicid < 0x8000) + msg->arch_addr_lo.virt_destid_8_14 = cfg->dest_apicid >> 8; + else + WARN_ON_ONCE(cfg->dest_apicid > 0xFF); +} + +u32 x86_msi_msg_get_destid(struct msi_msg *msg, bool extid) +{ + u32 dest = msg->arch_addr_lo.destid_0_7; + + if (extid) + dest |= msg->arch_addr_hi.destid_8_31 << 8; + return dest; +} +EXPORT_SYMBOL_GPL(x86_msi_msg_get_destid); + /* * Override the generic EOI implementation with an optimized version. * Only called during early boot when only one CPU is active and with diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index 7862b152a052..8f72b4351c9f 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -53,7 +53,7 @@ static void _flat_send_IPI_mask(unsigned long mask, int vector) unsigned long flags; local_irq_save(flags); - __default_send_IPI_dest_field(mask, vector, apic->dest_logical); + __default_send_IPI_dest_field(mask, vector, APIC_DEST_LOGICAL); local_irq_restore(flags); } @@ -113,15 +113,13 @@ static struct apic apic_flat __ro_after_init = { .apic_id_valid = default_apic_id_valid, .apic_id_registered = flat_apic_id_registered, - .irq_delivery_mode = dest_Fixed, - .irq_dest_mode = 1, /* logical */ + .delivery_mode = APIC_DELIVERY_MODE_FIXED, + .dest_mode_logical = true, .disable_esr = 0, - .dest_logical = APIC_DEST_LOGICAL, - .check_apicid_used = NULL, + .check_apicid_used = NULL, .init_apic_ldr = flat_init_apic_ldr, - .ioapic_phys_id_map = NULL, .setup_apic_routing = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, @@ -206,15 +204,13 @@ static struct apic apic_physflat __ro_after_init = { .apic_id_valid = default_apic_id_valid, .apic_id_registered = flat_apic_id_registered, - .irq_delivery_mode = dest_Fixed, - .irq_dest_mode = 0, /* physical */ + .delivery_mode = APIC_DELIVERY_MODE_FIXED, + .dest_mode_logical = false, .disable_esr = 0, - .dest_logical = 0, - .check_apicid_used = NULL, + .check_apicid_used = NULL, .init_apic_ldr = physflat_init_apic_ldr, - .ioapic_phys_id_map = NULL, .setup_apic_routing = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index 780c702969b7..fe78319e0f7a 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -95,19 +95,15 @@ struct apic apic_noop __ro_after_init = { .apic_id_valid = default_apic_id_valid, .apic_id_registered = noop_apic_id_registered, - .irq_delivery_mode = dest_Fixed, - /* logical delivery broadcast to all CPUs: */ - .irq_dest_mode = 1, + .delivery_mode = APIC_DELIVERY_MODE_FIXED, + .dest_mode_logical = true, .disable_esr = 0, - .dest_logical = APIC_DEST_LOGICAL, - .check_apicid_used = default_check_apicid_used, + .check_apicid_used = default_check_apicid_used, .init_apic_ldr = noop_init_apic_ldr, - .ioapic_phys_id_map = default_ioapic_phys_id_map, .setup_apic_routing = NULL, - .cpu_present_to_apicid = default_cpu_present_to_apicid, .apicid_to_cpu_present = physid_set_mask_of_physid, diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index 35edd57f064a..a54d817eb4b6 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -246,15 +246,13 @@ static const struct apic apic_numachip1 __refconst = { .apic_id_valid = numachip_apic_id_valid, .apic_id_registered = numachip_apic_id_registered, - .irq_delivery_mode = dest_Fixed, - .irq_dest_mode = 0, /* physical */ + .delivery_mode = APIC_DELIVERY_MODE_FIXED, + .dest_mode_logical = false, .disable_esr = 0, - .dest_logical = 0, - .check_apicid_used = NULL, + .check_apicid_used = NULL, .init_apic_ldr = flat_init_apic_ldr, - .ioapic_phys_id_map = NULL, .setup_apic_routing = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, @@ -295,15 +293,13 @@ static const struct apic apic_numachip2 __refconst = { .apic_id_valid = numachip_apic_id_valid, .apic_id_registered = numachip_apic_id_registered, - .irq_delivery_mode = dest_Fixed, - .irq_dest_mode = 0, /* physical */ + .delivery_mode = APIC_DELIVERY_MODE_FIXED, + .dest_mode_logical = false, .disable_esr = 0, - .dest_logical = 0, - .check_apicid_used = NULL, + .check_apicid_used = NULL, .init_apic_ldr = flat_init_apic_ldr, - .ioapic_phys_id_map = NULL, .setup_apic_routing = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 98d015a4405a..77555f66c14d 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -127,16 +127,13 @@ static struct apic apic_bigsmp __ro_after_init = { .apic_id_valid = default_apic_id_valid, .apic_id_registered = bigsmp_apic_id_registered, - .irq_delivery_mode = dest_Fixed, - /* phys delivery to target CPU: */ - .irq_dest_mode = 0, + .delivery_mode = APIC_DELIVERY_MODE_FIXED, + .dest_mode_logical = false, .disable_esr = 1, - .dest_logical = 0, - .check_apicid_used = bigsmp_check_apicid_used, + .check_apicid_used = bigsmp_check_apicid_used, .init_apic_ldr = bigsmp_init_apic_ldr, - .ioapic_phys_id_map = bigsmp_ioapic_phys_id_map, .setup_apic_routing = bigsmp_setup_apic_routing, .cpu_present_to_apicid = bigsmp_cpu_present_to_apicid, diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 7b3c7e0d4a09..e4ab4804b20d 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -48,6 +48,7 @@ #include <linux/jiffies.h> /* time_after() */ #include <linux/slab.h> #include <linux/memblock.h> +#include <linux/msi.h> #include <asm/irqdomain.h> #include <asm/io.h> @@ -63,7 +64,6 @@ #include <asm/setup.h> #include <asm/irq_remapping.h> #include <asm/hw_irq.h> - #include <asm/apic.h> #define for_each_ioapic(idx) \ @@ -89,12 +89,12 @@ struct irq_pin_list { }; struct mp_chip_data { - struct list_head irq_2_pin; - struct IO_APIC_route_entry entry; - int trigger; - int polarity; + struct list_head irq_2_pin; + struct IO_APIC_route_entry entry; + bool is_level; + bool active_low; + bool isa_irq; u32 count; - bool isa_irq; }; struct mp_ioapic_gsi { @@ -286,31 +286,26 @@ static void io_apic_write(unsigned int apic, unsigned int reg, writel(value, &io_apic->data); } -union entry_union { - struct { u32 w1, w2; }; - struct IO_APIC_route_entry entry; -}; - static struct IO_APIC_route_entry __ioapic_read_entry(int apic, int pin) { - union entry_union eu; + struct IO_APIC_route_entry entry; - eu.w1 = io_apic_read(apic, 0x10 + 2 * pin); - eu.w2 = io_apic_read(apic, 0x11 + 2 * pin); + entry.w1 = io_apic_read(apic, 0x10 + 2 * pin); + entry.w2 = io_apic_read(apic, 0x11 + 2 * pin); - return eu.entry; + return entry; } static struct IO_APIC_route_entry ioapic_read_entry(int apic, int pin) { - union entry_union eu; + struct IO_APIC_route_entry entry; unsigned long flags; raw_spin_lock_irqsave(&ioapic_lock, flags); - eu.entry = __ioapic_read_entry(apic, pin); + entry = __ioapic_read_entry(apic, pin); raw_spin_unlock_irqrestore(&ioapic_lock, flags); - return eu.entry; + return entry; } /* @@ -321,11 +316,8 @@ static struct IO_APIC_route_entry ioapic_read_entry(int apic, int pin) */ static void __ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e) { - union entry_union eu = {{0, 0}}; - - eu.entry = e; - io_apic_write(apic, 0x11 + 2*pin, eu.w2); - io_apic_write(apic, 0x10 + 2*pin, eu.w1); + io_apic_write(apic, 0x11 + 2*pin, e.w2); + io_apic_write(apic, 0x10 + 2*pin, e.w1); } static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e) @@ -344,12 +336,12 @@ static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e) */ static void ioapic_mask_entry(int apic, int pin) { + struct IO_APIC_route_entry e = { .masked = true }; unsigned long flags; - union entry_union eu = { .entry.mask = IOAPIC_MASKED }; raw_spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(apic, 0x10 + 2*pin, eu.w1); - io_apic_write(apic, 0x11 + 2*pin, eu.w2); + io_apic_write(apic, 0x10 + 2*pin, e.w1); + io_apic_write(apic, 0x11 + 2*pin, e.w2); raw_spin_unlock_irqrestore(&ioapic_lock, flags); } @@ -422,20 +414,15 @@ static void __init replace_pin_at_irq_node(struct mp_chip_data *data, int node, add_pin_to_irq_node(data, node, newapic, newpin); } -static void io_apic_modify_irq(struct mp_chip_data *data, - int mask_and, int mask_or, +static void io_apic_modify_irq(struct mp_chip_data *data, bool masked, void (*final)(struct irq_pin_list *entry)) { - union entry_union eu; struct irq_pin_list *entry; - eu.entry = data->entry; - eu.w1 &= mask_and; - eu.w1 |= mask_or; - data->entry = eu.entry; + data->entry.masked = masked; for_each_irq_pin(entry, data->irq_2_pin) { - io_apic_write(entry->apic, 0x10 + 2 * entry->pin, eu.w1); + io_apic_write(entry->apic, 0x10 + 2 * entry->pin, data->entry.w1); if (final) final(entry); } @@ -459,13 +446,13 @@ static void mask_ioapic_irq(struct irq_data *irq_data) unsigned long flags; raw_spin_lock_irqsave(&ioapic_lock, flags); - io_apic_modify_irq(data, ~0, IO_APIC_REDIR_MASKED, &io_apic_sync); + io_apic_modify_irq(data, true, &io_apic_sync); raw_spin_unlock_irqrestore(&ioapic_lock, flags); } static void __unmask_ioapic(struct mp_chip_data *data) { - io_apic_modify_irq(data, ~IO_APIC_REDIR_MASKED, 0, NULL); + io_apic_modify_irq(data, false, NULL); } static void unmask_ioapic_irq(struct irq_data *irq_data) @@ -506,8 +493,8 @@ static void __eoi_ioapic_pin(int apic, int pin, int vector) /* * Mask the entry and change the trigger mode to edge. */ - entry1.mask = IOAPIC_MASKED; - entry1.trigger = IOAPIC_EDGE; + entry1.masked = true; + entry1.is_level = false; __ioapic_write_entry(apic, pin, entry1); @@ -535,15 +522,15 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) /* Check delivery_mode to be sure we're not clearing an SMI pin */ entry = ioapic_read_entry(apic, pin); - if (entry.delivery_mode == dest_SMI) + if (entry.delivery_mode == APIC_DELIVERY_MODE_SMI) return; /* * Make sure the entry is masked and re-read the contents to check * if it is a level triggered pin and if the remote-IRR is set. */ - if (entry.mask == IOAPIC_UNMASKED) { - entry.mask = IOAPIC_MASKED; + if (!entry.masked) { + entry.masked = true; ioapic_write_entry(apic, pin, entry); entry = ioapic_read_entry(apic, pin); } @@ -556,8 +543,8 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) * doesn't clear the remote-IRR if the trigger mode is not * set to level. */ - if (entry.trigger == IOAPIC_EDGE) { - entry.trigger = IOAPIC_LEVEL; + if (!entry.is_level) { + entry.is_level = true; ioapic_write_entry(apic, pin, entry); } raw_spin_lock_irqsave(&ioapic_lock, flags); @@ -659,8 +646,8 @@ void mask_ioapic_entries(void) struct IO_APIC_route_entry entry; entry = ioapics[apic].saved_registers[pin]; - if (entry.mask == IOAPIC_UNMASKED) { - entry.mask = IOAPIC_MASKED; + if (!entry.masked) { + entry.masked = true; ioapic_write_entry(apic, pin, entry); } } @@ -745,44 +732,7 @@ static int __init find_isa_irq_apic(int irq, int type) return -1; } -#ifdef CONFIG_EISA -/* - * EISA Edge/Level control register, ELCR - */ -static int EISA_ELCR(unsigned int irq) -{ - if (irq < nr_legacy_irqs()) { - unsigned int port = 0x4d0 + (irq >> 3); - return (inb(port) >> (irq & 7)) & 1; - } - apic_printk(APIC_VERBOSE, KERN_INFO - "Broken MPtable reports ISA irq %d\n", irq); - return 0; -} - -#endif - -/* ISA interrupts are always active high edge triggered, - * when listed as conforming in the MP table. */ - -#define default_ISA_trigger(idx) (IOAPIC_EDGE) -#define default_ISA_polarity(idx) (IOAPIC_POL_HIGH) - -/* EISA interrupts are always polarity zero and can be edge or level - * trigger depending on the ELCR value. If an interrupt is listed as - * EISA conforming in the MP table, that means its trigger type must - * be read in from the ELCR */ - -#define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].srcbusirq)) -#define default_EISA_polarity(idx) default_ISA_polarity(idx) - -/* PCI interrupts are always active low level triggered, - * when listed as conforming in the MP table. */ - -#define default_PCI_trigger(idx) (IOAPIC_LEVEL) -#define default_PCI_polarity(idx) (IOAPIC_POL_LOW) - -static int irq_polarity(int idx) +static bool irq_active_low(int idx) { int bus = mp_irqs[idx].srcbus; @@ -791,90 +741,139 @@ static int irq_polarity(int idx) */ switch (mp_irqs[idx].irqflag & MP_IRQPOL_MASK) { case MP_IRQPOL_DEFAULT: - /* conforms to spec, ie. bus-type dependent polarity */ - if (test_bit(bus, mp_bus_not_pci)) - return default_ISA_polarity(idx); - else - return default_PCI_polarity(idx); + /* + * Conforms to spec, ie. bus-type dependent polarity. PCI + * defaults to low active. [E]ISA defaults to high active. + */ + return !test_bit(bus, mp_bus_not_pci); case MP_IRQPOL_ACTIVE_HIGH: - return IOAPIC_POL_HIGH; + return false; case MP_IRQPOL_RESERVED: pr_warn("IOAPIC: Invalid polarity: 2, defaulting to low\n"); fallthrough; case MP_IRQPOL_ACTIVE_LOW: default: /* Pointless default required due to do gcc stupidity */ - return IOAPIC_POL_LOW; + return true; } } #ifdef CONFIG_EISA -static int eisa_irq_trigger(int idx, int bus, int trigger) +/* + * EISA Edge/Level control register, ELCR + */ +static bool EISA_ELCR(unsigned int irq) +{ + if (irq < nr_legacy_irqs()) { + unsigned int port = 0x4d0 + (irq >> 3); + return (inb(port) >> (irq & 7)) & 1; + } + apic_printk(APIC_VERBOSE, KERN_INFO + "Broken MPtable reports ISA irq %d\n", irq); + return false; +} + +/* + * EISA interrupts are always active high and can be edge or level + * triggered depending on the ELCR value. If an interrupt is listed as + * EISA conforming in the MP table, that means its trigger type must be + * read in from the ELCR. + */ +static bool eisa_irq_is_level(int idx, int bus, bool level) { switch (mp_bus_id_to_type[bus]) { case MP_BUS_PCI: case MP_BUS_ISA: - return trigger; + return level; case MP_BUS_EISA: - return default_EISA_trigger(idx); + return EISA_ELCR(mp_irqs[idx].srcbusirq); } pr_warn("IOAPIC: Invalid srcbus: %d defaulting to level\n", bus); - return IOAPIC_LEVEL; + return true; } #else -static inline int eisa_irq_trigger(int idx, int bus, int trigger) +static inline int eisa_irq_is_level(int idx, int bus, bool level) { - return trigger; + return level; } #endif -static int irq_trigger(int idx) +static bool irq_is_level(int idx) { int bus = mp_irqs[idx].srcbus; - int trigger; + bool level; /* * Determine IRQ trigger mode (edge or level sensitive): */ switch (mp_irqs[idx].irqflag & MP_IRQTRIG_MASK) { case MP_IRQTRIG_DEFAULT: - /* conforms to spec, ie. bus-type dependent trigger mode */ - if (test_bit(bus, mp_bus_not_pci)) - trigger = default_ISA_trigger(idx); - else - trigger = default_PCI_trigger(idx); + /* + * Conforms to spec, ie. bus-type dependent trigger + * mode. PCI defaults to level, ISA to edge. + */ + level = !test_bit(bus, mp_bus_not_pci); /* Take EISA into account */ - return eisa_irq_trigger(idx, bus, trigger); + return eisa_irq_is_level(idx, bus, level); case MP_IRQTRIG_EDGE: - return IOAPIC_EDGE; + return false; case MP_IRQTRIG_RESERVED: pr_warn("IOAPIC: Invalid trigger mode 2 defaulting to level\n"); fallthrough; case MP_IRQTRIG_LEVEL: default: /* Pointless default required due to do gcc stupidity */ - return IOAPIC_LEVEL; + return true; } } +static int __acpi_get_override_irq(u32 gsi, bool *trigger, bool *polarity) +{ + int ioapic, pin, idx; + + if (skip_ioapic_setup) + return -1; + + ioapic = mp_find_ioapic(gsi); + if (ioapic < 0) + return -1; + + pin = mp_find_ioapic_pin(ioapic, gsi); + if (pin < 0) + return -1; + + idx = find_irq_entry(ioapic, pin, mp_INT); + if (idx < 0) + return -1; + + *trigger = irq_is_level(idx); + *polarity = irq_active_low(idx); + return 0; +} + +#ifdef CONFIG_ACPI +int acpi_get_override_irq(u32 gsi, int *is_level, int *active_low) +{ + *is_level = *active_low = 0; + return __acpi_get_override_irq(gsi, (bool *)is_level, + (bool *)active_low); +} +#endif + void ioapic_set_alloc_attr(struct irq_alloc_info *info, int node, int trigger, int polarity) { init_irq_alloc_info(info, NULL); info->type = X86_IRQ_ALLOC_TYPE_IOAPIC; info->ioapic.node = node; - info->ioapic.trigger = trigger; - info->ioapic.polarity = polarity; + info->ioapic.is_level = trigger; + info->ioapic.active_low = polarity; info->ioapic.valid = 1; } -#ifndef CONFIG_ACPI -int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity); -#endif - static void ioapic_copy_alloc_attr(struct irq_alloc_info *dst, struct irq_alloc_info *src, u32 gsi, int ioapic_idx, int pin) { - int trigger, polarity; + bool level, pol_low; copy_irq_alloc_info(dst, src); dst->type = X86_IRQ_ALLOC_TYPE_IOAPIC; @@ -883,20 +882,20 @@ static void ioapic_copy_alloc_attr(struct irq_alloc_info *dst, dst->ioapic.valid = 1; if (src && src->ioapic.valid) { dst->ioapic.node = src->ioapic.node; - dst->ioapic.trigger = src->ioapic.trigger; - dst->ioapic.polarity = src->ioapic.polarity; + dst->ioapic.is_level = src->ioapic.is_level; + dst->ioapic.active_low = src->ioapic.active_low; } else { dst->ioapic.node = NUMA_NO_NODE; - if (acpi_get_override_irq(gsi, &trigger, &polarity) >= 0) { - dst->ioapic.trigger = trigger; - dst->ioapic.polarity = polarity; + if (__acpi_get_override_irq(gsi, &level, &pol_low) >= 0) { + dst->ioapic.is_level = level; + dst->ioapic.active_low = pol_low; } else { /* * PCI interrupts are always active low level * triggered. */ - dst->ioapic.trigger = IOAPIC_LEVEL; - dst->ioapic.polarity = IOAPIC_POL_LOW; + dst->ioapic.is_level = true; + dst->ioapic.active_low = true; } } } @@ -906,12 +905,12 @@ static int ioapic_alloc_attr_node(struct irq_alloc_info *info) return (info && info->ioapic.valid) ? info->ioapic.node : NUMA_NO_NODE; } -static void mp_register_handler(unsigned int irq, unsigned long trigger) +static void mp_register_handler(unsigned int irq, bool level) { irq_flow_handler_t hdl; bool fasteoi; - if (trigger) { + if (level) { irq_set_status_flags(irq, IRQ_LEVEL); fasteoi = true; } else { @@ -933,14 +932,14 @@ static bool mp_check_pin_attr(int irq, struct irq_alloc_info *info) * pin with real trigger and polarity attributes. */ if (irq < nr_legacy_irqs() && data->count == 1) { - if (info->ioapic.trigger != data->trigger) - mp_register_handler(irq, info->ioapic.trigger); - data->entry.trigger = data->trigger = info->ioapic.trigger; - data->entry.polarity = data->polarity = info->ioapic.polarity; + if (info->ioapic.is_level != data->is_level) + mp_register_handler(irq, info->ioapic.is_level); + data->entry.is_level = data->is_level = info->ioapic.is_level; + data->entry.active_low = data->active_low = info->ioapic.active_low; } - return data->trigger == info->ioapic.trigger && - data->polarity == info->ioapic.polarity; + return data->is_level == info->ioapic.is_level && + data->active_low == info->ioapic.active_low; } static int alloc_irq_from_domain(struct irq_domain *domain, int ioapic, u32 gsi, @@ -1219,10 +1218,9 @@ void ioapic_zap_locks(void) static void io_apic_print_entries(unsigned int apic, unsigned int nr_entries) { - int i; - char buf[256]; struct IO_APIC_route_entry entry; - struct IR_IO_APIC_route_entry *ir_entry = (void *)&entry; + char buf[256]; + int i; printk(KERN_DEBUG "IOAPIC %d:\n", apic); for (i = 0; i <= nr_entries; i++) { @@ -1230,20 +1228,21 @@ static void io_apic_print_entries(unsigned int apic, unsigned int nr_entries) snprintf(buf, sizeof(buf), " pin%02x, %s, %s, %s, V(%02X), IRR(%1d), S(%1d)", i, - entry.mask == IOAPIC_MASKED ? "disabled" : "enabled ", - entry.trigger == IOAPIC_LEVEL ? "level" : "edge ", - entry.polarity == IOAPIC_POL_LOW ? "low " : "high", + entry.masked ? "disabled" : "enabled ", + entry.is_level ? "level" : "edge ", + entry.active_low ? "low " : "high", entry.vector, entry.irr, entry.delivery_status); - if (ir_entry->format) + if (entry.ir_format) { printk(KERN_DEBUG "%s, remapped, I(%04X), Z(%X)\n", - buf, (ir_entry->index2 << 15) | ir_entry->index, - ir_entry->zero); - else - printk(KERN_DEBUG "%s, %s, D(%02X), M(%1d)\n", buf, - entry.dest_mode == IOAPIC_DEST_MODE_LOGICAL ? - "logical " : "physical", - entry.dest, entry.delivery_mode); + (entry.ir_index_15 << 15) | entry.ir_index_0_14, + entry.ir_zero); + } else { + printk(KERN_DEBUG "%s, %s, D(%02X%02X), M(%1d)\n", buf, + entry.dest_mode_logical ? "logical " : "physical", + entry.virt_destid_8_14, entry.destid_0_7, + entry.delivery_mode); + } } } @@ -1368,7 +1367,8 @@ void __init enable_IO_APIC(void) /* If the interrupt line is enabled and in ExtInt mode * I have found the pin where the i8259 is connected. */ - if ((entry.mask == 0) && (entry.delivery_mode == dest_ExtINT)) { + if (!entry.masked && + entry.delivery_mode == APIC_DELIVERY_MODE_EXTINT) { ioapic_i8259.apic = apic; ioapic_i8259.pin = pin; goto found_i8259; @@ -1410,14 +1410,16 @@ void native_restore_boot_irq_mode(void) */ if (ioapic_i8259.pin != -1) { struct IO_APIC_route_entry entry; + u32 apic_id = read_apic_id(); memset(&entry, 0, sizeof(entry)); - entry.mask = IOAPIC_UNMASKED; - entry.trigger = IOAPIC_EDGE; - entry.polarity = IOAPIC_POL_HIGH; - entry.dest_mode = IOAPIC_DEST_MODE_PHYSICAL; - entry.delivery_mode = dest_ExtINT; - entry.dest = read_apic_id(); + entry.masked = false; + entry.is_level = false; + entry.active_low = false; + entry.dest_mode_logical = false; + entry.delivery_mode = APIC_DELIVERY_MODE_EXTINT; + entry.destid_0_7 = apic_id & 0xFF; + entry.virt_destid_8_14 = apic_id >> 8; /* * Add it to the IO-APIC irq-routing table: @@ -1618,21 +1620,16 @@ static void __init delay_without_tsc(void) static int __init timer_irq_works(void) { unsigned long t1 = jiffies; - unsigned long flags; if (no_timer_check) return 1; - local_save_flags(flags); local_irq_enable(); - if (boot_cpu_has(X86_FEATURE_TSC)) delay_with_tsc(); else delay_without_tsc(); - local_irq_restore(flags); - /* * Expect a few ticks at least, to be sure some possible * glue logic does not lock up after one or two first @@ -1641,10 +1638,10 @@ static int __init timer_irq_works(void) * least one tick may be lost due to delays. */ - /* jiffies wrap? */ - if (time_after(jiffies, t1 + 4)) - return 1; - return 0; + local_irq_disable(); + + /* Did jiffies advance? */ + return time_after(jiffies, t1 + 4); } /* @@ -1696,13 +1693,13 @@ static bool io_apic_level_ack_pending(struct mp_chip_data *data) raw_spin_lock_irqsave(&ioapic_lock, flags); for_each_irq_pin(entry, data->irq_2_pin) { - unsigned int reg; + struct IO_APIC_route_entry e; int pin; pin = entry->pin; - reg = io_apic_read(entry->apic, 0x10 + pin*2); + e.w1 = io_apic_read(entry->apic, 0x10 + pin*2); /* Is the remote IRR bit set? */ - if (reg & IO_APIC_REDIR_REMOTE_IRR) { + if (e.irr) { raw_spin_unlock_irqrestore(&ioapic_lock, flags); return true; } @@ -1849,21 +1846,62 @@ static void ioapic_ir_ack_level(struct irq_data *irq_data) eoi_ioapic_pin(data->entry.vector, data); } +/* + * The I/OAPIC is just a device for generating MSI messages from legacy + * interrupt pins. Various fields of the RTE translate into bits of the + * resulting MSI which had a historical meaning. + * + * With interrupt remapping, many of those bits have different meanings + * in the underlying MSI, but the way that the I/OAPIC transforms them + * from its RTE to the MSI message is the same. This function allows + * the parent IRQ domain to compose the MSI message, then takes the + * relevant bits to put them in the appropriate places in the RTE in + * order to generate that message when the IRQ happens. + * + * The setup here relies on a preconfigured route entry (is_level, + * active_low, masked) because the parent domain is merely composing the + * generic message routing information which is used for the MSI. + */ +static void ioapic_setup_msg_from_msi(struct irq_data *irq_data, + struct IO_APIC_route_entry *entry) +{ + struct msi_msg msg; + + /* Let the parent domain compose the MSI message */ + irq_chip_compose_msi_msg(irq_data, &msg); + + /* + * - Real vector + * - DMAR/IR: 8bit subhandle (ioapic.pin) + * - AMD/IR: 8bit IRTE index + */ + entry->vector = msg.arch_data.vector; + /* Delivery mode (for DMAR/IR all 0) */ + entry->delivery_mode = msg.arch_data.delivery_mode; + /* Destination mode or DMAR/IR index bit 15 */ + entry->dest_mode_logical = msg.arch_addr_lo.dest_mode_logical; + /* DMAR/IR: 1, 0 for all other modes */ + entry->ir_format = msg.arch_addr_lo.dmar_format; + /* + * - DMAR/IR: index bit 0-14. + * + * - Virt: If the host supports x2apic without a virtualized IR + * unit then bit 0-6 of dmar_index_0_14 are providing bit + * 8-14 of the destination id. + * + * All other modes have bit 0-6 of dmar_index_0_14 cleared and the + * topmost 8 bits are destination id bit 0-7 (entry::destid_0_7). + */ + entry->ir_index_0_14 = msg.arch_addr_lo.dmar_index_0_14; +} + 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; - } + ioapic_setup_msg_from_msi(irqd, &mpd->entry); + for_each_irq_pin(entry, mpd->irq_2_pin) __ioapic_write_entry(entry->apic, entry->pin, mpd->entry); } @@ -1919,7 +1957,7 @@ static int ioapic_irq_get_chip_state(struct irq_data *irqd, * irrelevant because the IO-APIC treats them as fire and * forget. */ - if (rentry.irr && rentry.trigger) { + if (rentry.irr && rentry.is_level) { *state = true; break; } @@ -2027,6 +2065,7 @@ static inline void __init unlock_ExtINT_logic(void) int apic, pin, i; struct IO_APIC_route_entry entry0, entry1; unsigned char save_control, save_freq_select; + u32 apic_id; pin = find_isa_irq_pin(8, mp_INT); if (pin == -1) { @@ -2042,14 +2081,16 @@ static inline void __init unlock_ExtINT_logic(void) entry0 = ioapic_read_entry(apic, pin); clear_IO_APIC_pin(apic, pin); + apic_id = hard_smp_processor_id(); memset(&entry1, 0, sizeof(entry1)); - entry1.dest_mode = IOAPIC_DEST_MODE_PHYSICAL; - entry1.mask = IOAPIC_UNMASKED; - entry1.dest = hard_smp_processor_id(); - entry1.delivery_mode = dest_ExtINT; - entry1.polarity = entry0.polarity; - entry1.trigger = IOAPIC_EDGE; + entry1.dest_mode_logical = true; + entry1.masked = false; + entry1.destid_0_7 = apic_id & 0xFF; + entry1.virt_destid_8_14 = apic_id >> 8; + entry1.delivery_mode = APIC_DELIVERY_MODE_EXTINT; + entry1.active_low = entry0.active_low; + entry1.is_level = false; entry1.vector = 0; ioapic_write_entry(apic, pin, entry1); @@ -2117,13 +2158,12 @@ static inline void __init check_timer(void) struct irq_cfg *cfg = irqd_cfg(irq_data); int node = cpu_to_node(0); int apic1, pin1, apic2, pin2; - unsigned long flags; int no_pin1 = 0; if (!global_clock_event) return; - local_irq_save(flags); + local_irq_disable(); /* * get/set the timer IRQ vector: @@ -2178,9 +2218,9 @@ static inline void __init check_timer(void) * so only need to unmask if it is level-trigger * do we really have level trigger timer? */ - int idx; - idx = find_irq_entry(apic1, pin1, mp_INT); - if (idx != -1 && irq_trigger(idx)) + int idx = find_irq_entry(apic1, pin1, mp_INT); + + if (idx != -1 && irq_is_level(idx)) unmask_ioapic_irq(irq_get_irq_data(0)); } irq_domain_deactivate_irq(irq_data); @@ -2191,7 +2231,6 @@ static inline void __init check_timer(void) goto out; } panic_if_irq_remap("timer doesn't work through Interrupt-remapped IO-APIC"); - local_irq_disable(); clear_IO_APIC_pin(apic1, pin1); if (!no_pin1) apic_printk(APIC_QUIET, KERN_ERR "..MP-BIOS bug: " @@ -2215,7 +2254,6 @@ static inline void __init check_timer(void) /* * Cleanup, just in case ... */ - local_irq_disable(); legacy_pic->mask(0); clear_IO_APIC_pin(apic2, pin2); apic_printk(APIC_QUIET, KERN_INFO "....... failed.\n"); @@ -2232,7 +2270,6 @@ static inline void __init check_timer(void) apic_printk(APIC_QUIET, KERN_INFO "..... works.\n"); goto out; } - local_irq_disable(); legacy_pic->mask(0); apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | cfg->vector); apic_printk(APIC_QUIET, KERN_INFO "..... failed.\n"); @@ -2251,7 +2288,6 @@ static inline void __init check_timer(void) apic_printk(APIC_QUIET, KERN_INFO "..... works.\n"); goto out; } - local_irq_disable(); apic_printk(APIC_QUIET, KERN_INFO "..... failed :(.\n"); if (apic_is_x2apic_enabled()) apic_printk(APIC_QUIET, KERN_INFO @@ -2260,7 +2296,7 @@ static inline void __init check_timer(void) panic("IO-APIC + timer doesn't work! Boot with apic=debug and send a " "report. Then try booting with the 'noapic' option.\n"); out: - local_irq_restore(flags); + local_irq_enable(); } /* @@ -2284,36 +2320,37 @@ out: static int mp_irqdomain_create(int ioapic) { - struct irq_alloc_info info; struct irq_domain *parent; int hwirqs = mp_ioapic_pin_count(ioapic); struct ioapic *ip = &ioapics[ioapic]; struct ioapic_domain_cfg *cfg = &ip->irqdomain_cfg; struct mp_ioapic_gsi *gsi_cfg = mp_ioapic_gsi_routing(ioapic); struct fwnode_handle *fn; - char *name = "IO-APIC"; + struct irq_fwspec fwspec; if (cfg->type == IOAPIC_DOMAIN_INVALID) return 0; - init_irq_alloc_info(&info, NULL); - info.type = X86_IRQ_ALLOC_TYPE_IOAPIC_GET_PARENT; - info.devid = mpc_ioapic_id(ioapic); - parent = irq_remapping_get_irq_domain(&info); - if (!parent) - parent = x86_vector_domain; - else - name = "IO-APIC-IR"; - /* Handle device tree enumerated APICs proper */ if (cfg->dev) { fn = of_node_to_fwnode(cfg->dev); } else { - fn = irq_domain_alloc_named_id_fwnode(name, ioapic); + fn = irq_domain_alloc_named_id_fwnode("IO-APIC", mpc_ioapic_id(ioapic)); if (!fn) return -ENOMEM; } + fwspec.fwnode = fn; + fwspec.param_count = 1; + fwspec.param[0] = mpc_ioapic_id(ioapic); + + parent = irq_find_matching_fwspec(&fwspec, DOMAIN_BUS_ANY); + if (!parent) { + if (!cfg->dev) + irq_domain_free_fwnode(fn); + return -ENODEV; + } + ip->irqdomain = irq_domain_create_linear(fn, hwirqs, cfg->ops, (void *)(long)ioapic); @@ -2587,30 +2624,6 @@ static int io_apic_get_version(int ioapic) return reg_01.bits.version; } -int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity) -{ - int ioapic, pin, idx; - - if (skip_ioapic_setup) - return -1; - - ioapic = mp_find_ioapic(gsi); - if (ioapic < 0) - return -1; - - pin = mp_find_ioapic_pin(ioapic, gsi); - if (pin < 0) - return -1; - - idx = find_irq_entry(ioapic, pin, mp_INT); - if (idx < 0) - return -1; - - *trigger = irq_trigger(idx); - *polarity = irq_polarity(idx); - return 0; -} - /* * This function updates target affinity of IOAPIC interrupts to include * the CPUs which came online during SMP bringup. @@ -2934,44 +2947,49 @@ static void mp_irqdomain_get_attr(u32 gsi, struct mp_chip_data *data, struct irq_alloc_info *info) { if (info && info->ioapic.valid) { - data->trigger = info->ioapic.trigger; - data->polarity = info->ioapic.polarity; - } else if (acpi_get_override_irq(gsi, &data->trigger, - &data->polarity) < 0) { + data->is_level = info->ioapic.is_level; + data->active_low = info->ioapic.active_low; + } else if (__acpi_get_override_irq(gsi, &data->is_level, + &data->active_low) < 0) { /* PCI interrupts are always active low level triggered. */ - data->trigger = IOAPIC_LEVEL; - data->polarity = IOAPIC_POL_LOW; + data->is_level = true; + data->active_low = true; } } -static void mp_setup_entry(struct irq_cfg *cfg, struct mp_chip_data *data, - struct IO_APIC_route_entry *entry) +/* + * Configure the I/O-APIC specific fields in the routing entry. + * + * This is important to setup the I/O-APIC specific bits (is_level, + * active_low, masked) because the underlying parent domain will only + * provide the routing information and is oblivious of the I/O-APIC + * specific bits. + * + * The entry is just preconfigured at this point and not written into the + * RTE. This happens later during activation which will fill in the actual + * routing information. + */ +static void mp_preconfigure_entry(struct mp_chip_data *data) { + struct IO_APIC_route_entry *entry = &data->entry; + memset(entry, 0, sizeof(*entry)); - entry->delivery_mode = apic->irq_delivery_mode; - entry->dest_mode = apic->irq_dest_mode; - entry->dest = cfg->dest_apicid; - entry->vector = cfg->vector; - entry->trigger = data->trigger; - entry->polarity = data->polarity; + entry->is_level = data->is_level; + entry->active_low = data->active_low; /* * Mask level triggered irqs. Edge triggered irqs are masked * by the irq core code in case they fire. */ - if (data->trigger == IOAPIC_LEVEL) - entry->mask = IOAPIC_MASKED; - else - entry->mask = IOAPIC_UNMASKED; + entry->masked = data->is_level; } int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs, void *arg) { - int ret, ioapic, pin; - struct irq_cfg *cfg; - struct irq_data *irq_data; - struct mp_chip_data *data; struct irq_alloc_info *info = arg; + struct mp_chip_data *data; + struct irq_data *irq_data; + int ret, ioapic, pin; unsigned long flags; if (!info || nr_irqs > 1) @@ -2989,7 +3007,6 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, if (!data) return -ENOMEM; - info->ioapic.entry = &data->entry; ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info); if (ret < 0) { kfree(data); @@ -3003,22 +3020,20 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, irq_data->chip_data = data; mp_irqdomain_get_attr(mp_pin_to_gsi(ioapic, pin), data, info); - cfg = irqd_cfg(irq_data); add_pin_to_irq_node(data, ioapic_alloc_attr_node(info), ioapic, pin); + mp_preconfigure_entry(data); + mp_register_handler(virq, data->is_level); + local_irq_save(flags); - if (info->ioapic.entry) - mp_setup_entry(cfg, data, info->ioapic.entry); - mp_register_handler(virq, data->trigger); if (virq < nr_legacy_irqs()) legacy_pic->mask(virq); local_irq_restore(flags); apic_printk(APIC_VERBOSE, KERN_DEBUG - "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> IRQ %d Mode:%i Active:%i Dest:%d)\n", - ioapic, mpc_ioapic_id(ioapic), pin, cfg->vector, - virq, data->trigger, data->polarity, cfg->dest_apicid); - + "IOAPIC[%d]: Preconfigured routing entry (%d-%d -> IRQ %d Level:%i ActiveLow:%i)\n", + ioapic, mpc_ioapic_id(ioapic), pin, virq, + data->is_level, data->active_low); return 0; } diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c index 387154e39e08..d1fb874fbe64 100644 --- a/arch/x86/kernel/apic/ipi.c +++ b/arch/x86/kernel/apic/ipi.c @@ -260,7 +260,7 @@ void default_send_IPI_mask_sequence_logical(const struct cpumask *mask, for_each_cpu(query_cpu, mask) __default_send_IPI_dest_field( early_per_cpu(x86_cpu_to_logical_apicid, query_cpu), - vector, apic->dest_logical); + vector, APIC_DEST_LOGICAL); local_irq_restore(flags); } @@ -279,7 +279,7 @@ void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask, continue; __default_send_IPI_dest_field( early_per_cpu(x86_cpu_to_logical_apicid, query_cpu), - vector, apic->dest_logical); + vector, APIC_DEST_LOGICAL); } local_irq_restore(flags); } @@ -297,7 +297,7 @@ void default_send_IPI_mask_logical(const struct cpumask *cpumask, int vector) local_irq_save(flags); WARN_ON(mask & ~cpumask_bits(cpu_online_mask)[0]); - __default_send_IPI_dest_field(mask, vector, apic->dest_logical); + __default_send_IPI_dest_field(mask, vector, APIC_DEST_LOGICAL); local_irq_restore(flags); } diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 6313f0a05db7..44ebe25e7703 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -15,7 +15,6 @@ #include <linux/hpet.h> #include <linux/msi.h> #include <asm/irqdomain.h> -#include <asm/msidef.h> #include <asm/hpet.h> #include <asm/hw_irq.h> #include <asm/apic.h> @@ -23,38 +22,11 @@ struct irq_domain *x86_pci_msi_default_domain __ro_after_init; -static void __irq_msi_compose_msg(struct irq_cfg *cfg, struct msi_msg *msg) -{ - msg->address_hi = MSI_ADDR_BASE_HI; - - if (x2apic_enabled()) - msg->address_hi |= MSI_ADDR_EXT_DEST_ID(cfg->dest_apicid); - - msg->address_lo = - MSI_ADDR_BASE_LO | - ((apic->irq_dest_mode == 0) ? - MSI_ADDR_DEST_MODE_PHYSICAL : - MSI_ADDR_DEST_MODE_LOGICAL) | - MSI_ADDR_REDIRECTION_CPU | - MSI_ADDR_DEST_ID(cfg->dest_apicid); - - msg->data = - MSI_DATA_TRIGGER_EDGE | - MSI_DATA_LEVEL_ASSERT | - MSI_DATA_DELIVERY_FIXED | - MSI_DATA_VECTOR(cfg->vector); -} - -void x86_vector_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) -{ - __irq_msi_compose_msg(irqd_cfg(data), msg); -} - static void irq_msi_update_msg(struct irq_data *irqd, struct irq_cfg *cfg) { struct msi_msg msg[2] = { [1] = { }, }; - __irq_msi_compose_msg(cfg, msg); + __irq_msi_compose_msg(cfg, msg, false); irq_data_get_irq_chip(irqd)->irq_write_msi_msg(irqd, msg); } @@ -276,6 +248,17 @@ struct irq_domain *arch_create_remap_msi_irq_domain(struct irq_domain *parent, #endif #ifdef CONFIG_DMAR_TABLE +/* + * The Intel IOMMU (ab)uses the high bits of the MSI address to contain the + * high bits of the destination APIC ID. This can't be done in the general + * case for MSIs as it would be targeting real memory above 4GiB not the + * APIC. + */ +static void dmar_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) +{ + __irq_msi_compose_msg(irqd_cfg(data), msg, true); +} + static void dmar_msi_write_msg(struct irq_data *data, struct msi_msg *msg) { dmar_msi_write(data->irq, msg); @@ -288,6 +271,7 @@ static struct irq_chip dmar_msi_controller = { .irq_ack = irq_chip_ack_parent, .irq_set_affinity = msi_domain_set_affinity, .irq_retrigger = irq_chip_retrigger_hierarchy, + .irq_compose_msi_msg = dmar_msi_compose_msg, .irq_write_msi_msg = dmar_msi_write_msg, .flags = IRQCHIP_SKIP_SET_WAKE, }; @@ -356,114 +340,3 @@ void dmar_free_hwirq(int irq) irq_domain_free_irqs(irq, 1); } #endif - -/* - * MSI message composition - */ -#ifdef CONFIG_HPET_TIMER -static inline int hpet_dev_id(struct irq_domain *domain) -{ - struct msi_domain_info *info = msi_get_domain_info(domain); - - return (int)(long)info->data; -} - -static void hpet_msi_write_msg(struct irq_data *data, struct msi_msg *msg) -{ - hpet_msi_write(irq_data_get_irq_handler_data(data), msg); -} - -static struct irq_chip hpet_msi_controller __ro_after_init = { - .name = "HPET-MSI", - .irq_unmask = hpet_msi_unmask, - .irq_mask = hpet_msi_mask, - .irq_ack = irq_chip_ack_parent, - .irq_set_affinity = msi_domain_set_affinity, - .irq_retrigger = irq_chip_retrigger_hierarchy, - .irq_write_msi_msg = hpet_msi_write_msg, - .flags = IRQCHIP_SKIP_SET_WAKE, -}; - -static int hpet_msi_init(struct irq_domain *domain, - struct msi_domain_info *info, unsigned int virq, - irq_hw_number_t hwirq, msi_alloc_info_t *arg) -{ - irq_set_status_flags(virq, IRQ_MOVE_PCNTXT); - irq_domain_set_info(domain, virq, arg->hwirq, info->chip, NULL, - handle_edge_irq, arg->data, "edge"); - - return 0; -} - -static void hpet_msi_free(struct irq_domain *domain, - struct msi_domain_info *info, unsigned int virq) -{ - irq_clear_status_flags(virq, IRQ_MOVE_PCNTXT); -} - -static struct msi_domain_ops hpet_msi_domain_ops = { - .msi_init = hpet_msi_init, - .msi_free = hpet_msi_free, -}; - -static struct msi_domain_info hpet_msi_domain_info = { - .ops = &hpet_msi_domain_ops, - .chip = &hpet_msi_controller, - .flags = MSI_FLAG_USE_DEF_DOM_OPS, -}; - -struct irq_domain *hpet_create_irq_domain(int hpet_id) -{ - struct msi_domain_info *domain_info; - struct irq_domain *parent, *d; - struct irq_alloc_info info; - struct fwnode_handle *fn; - - if (x86_vector_domain == NULL) - return NULL; - - domain_info = kzalloc(sizeof(*domain_info), GFP_KERNEL); - if (!domain_info) - return NULL; - - *domain_info = hpet_msi_domain_info; - domain_info->data = (void *)(long)hpet_id; - - init_irq_alloc_info(&info, NULL); - info.type = X86_IRQ_ALLOC_TYPE_HPET_GET_PARENT; - info.devid = hpet_id; - parent = irq_remapping_get_irq_domain(&info); - if (parent == NULL) - parent = x86_vector_domain; - else - hpet_msi_controller.name = "IR-HPET-MSI"; - - fn = irq_domain_alloc_named_id_fwnode(hpet_msi_controller.name, - hpet_id); - if (!fn) { - kfree(domain_info); - return NULL; - } - - d = msi_create_irq_domain(fn, domain_info, parent); - if (!d) { - irq_domain_free_fwnode(fn); - kfree(domain_info); - } - return d; -} - -int hpet_assign_irq(struct irq_domain *domain, struct hpet_channel *hc, - int dev_num) -{ - struct irq_alloc_info info; - - init_irq_alloc_info(&info, NULL); - info.type = X86_IRQ_ALLOC_TYPE_HPET; - info.data = hc; - info.devid = hpet_dev_id(domain); - info.hwirq = dev_num; - - return irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, &info); -} -#endif diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 67b6f7c049ec..a61f642b1b90 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -69,16 +69,13 @@ static struct apic apic_default __ro_after_init = { .apic_id_valid = default_apic_id_valid, .apic_id_registered = default_apic_id_registered, - .irq_delivery_mode = dest_Fixed, - /* logical delivery broadcast to all CPUs: */ - .irq_dest_mode = 1, + .delivery_mode = APIC_DELIVERY_MODE_FIXED, + .dest_mode_logical = true, .disable_esr = 0, - .dest_logical = APIC_DEST_LOGICAL, - .check_apicid_used = default_check_apicid_used, + .check_apicid_used = default_check_apicid_used, .init_apic_ldr = default_init_apic_ldr, - .ioapic_phys_id_map = default_ioapic_phys_id_map, .setup_apic_routing = setup_apic_flat_routing, .cpu_present_to_apicid = default_cpu_present_to_apicid, diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 1eac53632786..3c9c7492252f 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -273,20 +273,24 @@ static int assign_irq_vector_any_locked(struct irq_data *irqd) 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; -all: + if (node != NUMA_NO_NODE) { + /* 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 full affinity mask */ cpumask_and(vector_searchmask, affmsk, cpu_online_mask); if (!assign_vector_locked(irqd, vector_searchmask)) return 0; + + if (node != NUMA_NO_NODE) { + /* Try the node mask */ + if (!assign_vector_locked(irqd, cpumask_of_node(node))) + return 0; + } + /* Try the full online mask */ return assign_vector_locked(irqd, cpu_online_mask); } @@ -636,7 +640,50 @@ static void x86_vector_debug_show(struct seq_file *m, struct irq_domain *d, } #endif +int x86_fwspec_is_ioapic(struct irq_fwspec *fwspec) +{ + if (fwspec->param_count != 1) + return 0; + + if (is_fwnode_irqchip(fwspec->fwnode)) { + const char *fwname = fwnode_get_name(fwspec->fwnode); + return fwname && !strncmp(fwname, "IO-APIC-", 8) && + simple_strtol(fwname+8, NULL, 10) == fwspec->param[0]; + } + return to_of_node(fwspec->fwnode) && + of_device_is_compatible(to_of_node(fwspec->fwnode), + "intel,ce4100-ioapic"); +} + +int x86_fwspec_is_hpet(struct irq_fwspec *fwspec) +{ + if (fwspec->param_count != 1) + return 0; + + if (is_fwnode_irqchip(fwspec->fwnode)) { + const char *fwname = fwnode_get_name(fwspec->fwnode); + return fwname && !strncmp(fwname, "HPET-MSI-", 9) && + simple_strtol(fwname+9, NULL, 10) == fwspec->param[0]; + } + return 0; +} + +static int x86_vector_select(struct irq_domain *d, struct irq_fwspec *fwspec, + enum irq_domain_bus_token bus_token) +{ + /* + * HPET and I/OAPIC cannot be parented in the vector domain + * if IRQ remapping is enabled. APIC IDs above 15 bits are + * only permitted if IRQ remapping is enabled, so check that. + */ + if (apic->apic_id_valid(32768)) + return 0; + + return x86_fwspec_is_ioapic(fwspec) || x86_fwspec_is_hpet(fwspec); +} + static const struct irq_domain_ops x86_vector_domain_ops = { + .select = x86_vector_select, .alloc = x86_vector_alloc_irqs, .free = x86_vector_free_irqs, .activate = x86_vector_activate, @@ -818,6 +865,12 @@ void apic_ack_edge(struct irq_data *irqd) apic_ack_irq(irqd); } +static void x86_vector_msi_compose_msg(struct irq_data *data, + struct msi_msg *msg) +{ + __irq_msi_compose_msg(irqd_cfg(data), msg, false); +} + static struct irq_chip lapic_controller = { .name = "APIC", .irq_ack = apic_ack_edge, diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index b0889c48a2ac..f4da9bb69a88 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -29,7 +29,8 @@ static void x2apic_send_IPI(int cpu, int vector) { u32 dest = per_cpu(x86_cpu_to_logical_apicid, cpu); - x2apic_wrmsr_fence(); + /* x2apic MSRs are special and need a special fence: */ + weak_wrmsr_fence(); __x2apic_send_IPI_dest(dest, vector, APIC_DEST_LOGICAL); } @@ -41,7 +42,8 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest) unsigned long flags; u32 dest; - x2apic_wrmsr_fence(); + /* x2apic MSRs are special and need a special fence: */ + weak_wrmsr_fence(); local_irq_save(flags); tmpmsk = this_cpu_cpumask_var_ptr(ipi_mask); @@ -61,7 +63,7 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest) if (!dest) continue; - __x2apic_send_IPI_dest(dest, vector, apic->dest_logical); + __x2apic_send_IPI_dest(dest, vector, APIC_DEST_LOGICAL); /* Remove cluster CPUs from tmpmask */ cpumask_andnot(tmpmsk, tmpmsk, &cmsk->mask); } @@ -184,15 +186,13 @@ static struct apic apic_x2apic_cluster __ro_after_init = { .apic_id_valid = x2apic_apic_id_valid, .apic_id_registered = x2apic_apic_id_registered, - .irq_delivery_mode = dest_Fixed, - .irq_dest_mode = 1, /* logical */ + .delivery_mode = APIC_DELIVERY_MODE_FIXED, + .dest_mode_logical = true, .disable_esr = 0, - .dest_logical = APIC_DEST_LOGICAL, - .check_apicid_used = NULL, + .check_apicid_used = NULL, .init_apic_ldr = init_x2apic_ldr, - .ioapic_phys_id_map = NULL, .setup_apic_routing = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index bc9693841353..6bde05a86b4e 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -8,6 +8,12 @@ int x2apic_phys; static struct apic apic_x2apic_phys; +static u32 x2apic_max_apicid __ro_after_init; + +void __init x2apic_set_max_apicid(u32 apicid) +{ + x2apic_max_apicid = apicid; +} static int __init set_x2apic_phys_mode(char *arg) { @@ -37,7 +43,8 @@ static void x2apic_send_IPI(int cpu, int vector) { u32 dest = per_cpu(x86_cpu_to_apicid, cpu); - x2apic_wrmsr_fence(); + /* x2apic MSRs are special and need a special fence: */ + weak_wrmsr_fence(); __x2apic_send_IPI_dest(dest, vector, APIC_DEST_PHYSICAL); } @@ -48,7 +55,8 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest) unsigned long this_cpu; unsigned long flags; - x2apic_wrmsr_fence(); + /* x2apic MSRs are special and need a special fence: */ + weak_wrmsr_fence(); local_irq_save(flags); @@ -98,6 +106,9 @@ static int x2apic_phys_probe(void) /* Common x2apic functions, also used by x2apic_cluster */ int x2apic_apic_id_valid(u32 apicid) { + if (x2apic_max_apicid && apicid > x2apic_max_apicid) + return 0; + return 1; } @@ -116,7 +127,8 @@ void __x2apic_send_IPI_shorthand(int vector, u32 which) { unsigned long cfg = __prepare_ICR(which, vector, 0); - x2apic_wrmsr_fence(); + /* x2apic MSRs are special and need a special fence: */ + weak_wrmsr_fence(); native_x2apic_icr_write(cfg, 0); } @@ -148,15 +160,13 @@ static struct apic apic_x2apic_phys __ro_after_init = { .apic_id_valid = x2apic_apic_id_valid, .apic_id_registered = x2apic_apic_id_registered, - .irq_delivery_mode = dest_Fixed, - .irq_dest_mode = 0, /* physical */ + .delivery_mode = APIC_DELIVERY_MODE_FIXED, + .dest_mode_logical = false, .disable_esr = 0, - .dest_logical = 0, - .check_apicid_used = NULL, + .check_apicid_used = NULL, .init_apic_ldr = init_x2apic_ldr, - .ioapic_phys_id_map = NULL, .setup_apic_routing = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 714233cee0b5..52bc217ca8c3 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -33,7 +33,7 @@ static union uvh_apicid uvh_apicid; static int uv_node_id; /* Unpack AT/OEM/TABLE ID's to be NULL terminated strings */ -static u8 uv_archtype[UV_AT_SIZE]; +static u8 uv_archtype[UV_AT_SIZE + 1]; static u8 oem_id[ACPI_OEM_ID_SIZE + 1]; static u8 oem_table_id[ACPI_OEM_TABLE_ID_SIZE + 1]; @@ -161,7 +161,7 @@ static int __init early_set_hub_type(void) /* UV4/4A only have a revision difference */ case UV4_HUB_PART_NUMBER: uv_min_hub_revision_id = node_id.s.revision - + UV4_HUB_REVISION_BASE; + + UV4_HUB_REVISION_BASE - 1; uv_hub_type_set(UV4); if (uv_min_hub_revision_id == UV4A_HUB_REVISION_BASE) uv_hub_type_set(UV4|UV4A); @@ -290,6 +290,9 @@ static void __init uv_stringify(int len, char *to, char *from) { /* Relies on 'to' being NULL chars so result will be NULL terminated */ strncpy(to, from, len-1); + + /* Trim trailing spaces */ + (void)strim(to); } /* Find UV arch type entry in UVsystab */ @@ -317,7 +320,7 @@ static int __init decode_arch_type(unsigned long ptr) if (n > 0 && n < sizeof(uv_ate->archtype)) { pr_info("UV: UVarchtype received from BIOS\n"); - uv_stringify(UV_AT_SIZE, uv_archtype, uv_ate->archtype); + uv_stringify(sizeof(uv_archtype), uv_archtype, uv_ate->archtype); return 1; } return 0; @@ -366,7 +369,7 @@ static int __init early_get_arch_type(void) return ret; } -static int __init uv_set_system_type(char *_oem_id) +static int __init uv_set_system_type(char *_oem_id, char *_oem_table_id) { /* Save OEM_ID passed from ACPI MADT */ uv_stringify(sizeof(oem_id), oem_id, _oem_id); @@ -375,7 +378,7 @@ static int __init uv_set_system_type(char *_oem_id) if (!early_get_arch_type()) /* If not use OEM ID for UVarchtype */ - uv_stringify(UV_AT_SIZE, uv_archtype, _oem_id); + uv_stringify(sizeof(uv_archtype), uv_archtype, oem_id); /* Check if not hubbed */ if (strncmp(uv_archtype, "SGI", 3) != 0) { @@ -386,13 +389,23 @@ static int __init uv_set_system_type(char *_oem_id) /* (Not hubless), not a UV */ return 0; + /* Is UV hubless system */ + uv_hubless_system = 0x01; + + /* UV5 Hubless */ + if (strncmp(uv_archtype, "NSGI5", 5) == 0) + uv_hubless_system |= 0x20; + /* UV4 Hubless: CH */ - if (strncmp(uv_archtype, "NSGI4", 5) == 0) - uv_hubless_system = 0x11; + else if (strncmp(uv_archtype, "NSGI4", 5) == 0) + uv_hubless_system |= 0x10; /* UV3 Hubless: UV300/MC990X w/o hub */ else - uv_hubless_system = 0x9; + uv_hubless_system |= 0x8; + + /* Copy APIC type */ + uv_stringify(sizeof(oem_table_id), oem_table_id, _oem_table_id); pr_info("UV: OEM IDs %s/%s, SystemType %d, HUBLESS ID %x\n", oem_id, oem_table_id, uv_system_type, uv_hubless_system); @@ -456,7 +469,7 @@ static int __init uv_acpi_madt_oem_check(char *_oem_id, char *_oem_table_id) uv_cpu_info->p_uv_hub_info = &uv_hub_info_node0; /* If not UV, return. */ - if (likely(uv_set_system_type(_oem_id) == 0)) + if (uv_set_system_type(_oem_id, _oem_table_id) == 0) return 0; /* Save and Decode OEM Table ID */ @@ -489,6 +502,18 @@ enum uv_system_type get_uv_system_type(void) return uv_system_type; } +int uv_get_hubless_system(void) +{ + return uv_hubless_system; +} +EXPORT_SYMBOL_GPL(uv_get_hubless_system); + +ssize_t uv_get_archtype(char *buf, int len) +{ + return scnprintf(buf, len, "%s/%s", uv_archtype, oem_table_id); +} +EXPORT_SYMBOL_GPL(uv_get_archtype); + int is_uv_system(void) { return uv_system_type != UV_NONE; @@ -703,9 +728,9 @@ static void uv_send_IPI_one(int cpu, int vector) unsigned long dmode, val; if (vector == NMI_VECTOR) - dmode = dest_NMI; + dmode = APIC_DELIVERY_MODE_NMI; else - dmode = dest_Fixed; + dmode = APIC_DELIVERY_MODE_FIXED; val = (1UL << UVH_IPI_INT_SEND_SHFT) | (apicid << UVH_IPI_INT_APIC_ID_SHFT) | @@ -807,15 +832,13 @@ static struct apic apic_x2apic_uv_x __ro_after_init = { .apic_id_valid = uv_apic_id_valid, .apic_id_registered = uv_apic_id_registered, - .irq_delivery_mode = dest_Fixed, - .irq_dest_mode = 0, /* Physical */ + .delivery_mode = APIC_DELIVERY_MODE_FIXED, + .dest_mode_logical = false, .disable_esr = 0, - .dest_logical = APIC_DEST_LOGICAL, - .check_apicid_used = NULL, + .check_apicid_used = NULL, .init_apic_ldr = uv_init_apic_ldr, - .ioapic_phys_id_map = NULL, .setup_apic_routing = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, @@ -1590,21 +1613,30 @@ static void check_efi_reboot(void) reboot_type = BOOT_ACPI; } -/* Setup user proc fs files */ +/* + * User proc fs file handling now deprecated. + * Recommend using /sys/firmware/sgi_uv/... instead. + */ static int __maybe_unused proc_hubbed_show(struct seq_file *file, void *data) { + pr_notice_once("%s: using deprecated /proc/sgi_uv/hubbed, use /sys/firmware/sgi_uv/hub_type\n", + current->comm); seq_printf(file, "0x%x\n", uv_hubbed_system); return 0; } static int __maybe_unused proc_hubless_show(struct seq_file *file, void *data) { + pr_notice_once("%s: using deprecated /proc/sgi_uv/hubless, use /sys/firmware/sgi_uv/hubless\n", + current->comm); seq_printf(file, "0x%x\n", uv_hubless_system); return 0; } static int __maybe_unused proc_archtype_show(struct seq_file *file, void *data) { + pr_notice_once("%s: using deprecated /proc/sgi_uv/archtype, use /sys/firmware/sgi_uv/archtype\n", + current->comm); seq_printf(file, "%s/%s\n", uv_archtype, oem_table_id); return 0; } diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 3ca07ad552ae..60b9f42ce3c1 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -38,9 +38,6 @@ static void __used common(void) #endif BLANK(); - OFFSET(TASK_addr_limit, task_struct, thread.addr_limit); - - BLANK(); OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx); BLANK(); @@ -69,7 +66,6 @@ static void __used common(void) OFFSET(PV_IRQ_irq_disable, paravirt_patch_template, irq.irq_disable); OFFSET(PV_IRQ_irq_enable, paravirt_patch_template, irq.irq_enable); OFFSET(PV_CPU_iret, paravirt_patch_template, cpu.iret); - OFFSET(PV_MMU_read_cr2, paravirt_patch_template, mmu.read_cr2); #endif #ifdef CONFIG_XEN diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 828be792231e..b14533af7676 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -13,9 +13,6 @@ int main(void) { #ifdef CONFIG_PARAVIRT #ifdef CONFIG_PARAVIRT_XXL - OFFSET(PV_CPU_usergs_sysret64, paravirt_patch_template, - cpu.usergs_sysret64); - OFFSET(PV_CPU_swapgs, paravirt_patch_template, cpu.swapgs); #ifdef CONFIG_DEBUG_ENTRY OFFSET(PV_IRQ_save_fl, paravirt_patch_template, irq.save_fl); #endif diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 93792b457b81..637b499450d1 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -48,6 +48,7 @@ obj-$(CONFIG_X86_MCE) += mce/ obj-$(CONFIG_MTRR) += mtrr/ obj-$(CONFIG_MICROCODE) += microcode/ obj-$(CONFIG_X86_CPU_RESCTRL) += resctrl/ +obj-$(CONFIG_X86_SGX) += sgx/ obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 6062ce586b95..347a956f71ca 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -23,7 +23,6 @@ #ifdef CONFIG_X86_64 # include <asm/mmconfig.h> -# include <asm/set_memory.h> #endif #include "cpu.h" @@ -330,7 +329,6 @@ static void legacy_fixup_core_id(struct cpuinfo_x86 *c) */ static void amd_get_topology(struct cpuinfo_x86 *c) { - u8 node_id; int cpu = smp_processor_id(); /* get information required for multi-node processors */ @@ -340,7 +338,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c) cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); - node_id = ecx & 0xff; + c->cpu_die_id = ecx & 0xff; if (c->x86 == 0x15) c->cu_id = ebx & 0xff; @@ -360,15 +358,15 @@ static void amd_get_topology(struct cpuinfo_x86 *c) if (!err) c->x86_coreid_bits = get_count_order(c->x86_max_cores); - cacheinfo_amd_init_llc_id(c, cpu, node_id); + cacheinfo_amd_init_llc_id(c, cpu); } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) { u64 value; rdmsrl(MSR_FAM10H_NODE_ID, value); - node_id = value & 7; + c->cpu_die_id = value & 7; - per_cpu(cpu_llc_id, cpu) = node_id; + per_cpu(cpu_llc_id, cpu) = c->cpu_die_id; } else return; @@ -393,7 +391,7 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c) /* Convert the initial APIC ID into the socket ID */ c->phys_proc_id = c->initial_apicid >> bits; /* use socket ID also for last level cache */ - per_cpu(cpu_llc_id, cpu) = c->phys_proc_id; + per_cpu(cpu_llc_id, cpu) = c->cpu_die_id = c->phys_proc_id; } static void amd_detect_ppin(struct cpuinfo_x86 *c) @@ -425,12 +423,6 @@ clear_ppin: clear_cpu_cap(c, X86_FEATURE_AMD_PPIN); } -u16 amd_get_nb_id(int cpu) -{ - return per_cpu(cpu_llc_id, cpu); -} -EXPORT_SYMBOL_GPL(amd_get_nb_id); - u32 amd_get_nodes_per_socket(void) { return nodes_per_socket; @@ -516,26 +508,6 @@ static void early_init_amd_mc(struct cpuinfo_x86 *c) static void bsp_init_amd(struct cpuinfo_x86 *c) { - -#ifdef CONFIG_X86_64 - if (c->x86 >= 0xf) { - unsigned long long tseg; - - /* - * Split up direct mapping around the TSEG SMM area. - * Don't do it for gbpages because there seems very little - * benefit in doing so. - */ - if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) { - unsigned long pfn = tseg >> PAGE_SHIFT; - - pr_debug("tseg: %010llx\n", tseg); - if (pfn_range_is_mapped(pfn, pfn + 1)) - set_memory_4k((unsigned long)__va(tseg), 1); - } - } -#endif - if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) { if (c->x86 > 0x10 || @@ -570,12 +542,12 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) u32 ecx; ecx = cpuid_ecx(0x8000001e); - nodes_per_socket = ((ecx >> 8) & 7) + 1; + __max_die_per_package = nodes_per_socket = ((ecx >> 8) & 7) + 1; } else if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) { u64 value; rdmsrl(MSR_FAM10H_NODE_ID, value); - nodes_per_socket = ((value >> 3) & 7) + 1; + __max_die_per_package = nodes_per_socket = ((value >> 3) & 7) + 1; } if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) && diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c index e2f319dc992d..22911deacb6e 100644 --- a/arch/x86/kernel/cpu/aperfmperf.c +++ b/arch/x86/kernel/cpu/aperfmperf.c @@ -14,11 +14,13 @@ #include <linux/cpufreq.h> #include <linux/smp.h> #include <linux/sched/isolation.h> +#include <linux/rcupdate.h> #include "cpu.h" struct aperfmperf_sample { unsigned int khz; + atomic_t scfpending; ktime_t time; u64 aperf; u64 mperf; @@ -62,17 +64,20 @@ static void aperfmperf_snapshot_khz(void *dummy) s->aperf = aperf; s->mperf = mperf; s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta); + atomic_set_release(&s->scfpending, 0); } static bool aperfmperf_snapshot_cpu(int cpu, ktime_t now, bool wait) { s64 time_delta = ktime_ms_delta(now, per_cpu(samples.time, cpu)); + struct aperfmperf_sample *s = per_cpu_ptr(&samples, 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); + if (!atomic_xchg(&s->scfpending, 1) || wait) + 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; @@ -89,6 +94,9 @@ unsigned int aperfmperf_get_khz(int cpu) if (!housekeeping_cpu(cpu, HK_FLAG_MISC)) return 0; + if (rcu_is_idle_cpu(cpu)) + return 0; /* Idle CPUs are completely uninteresting. */ + aperfmperf_snapshot_cpu(cpu, ktime_get(), true); return per_cpu(samples.khz, cpu); } @@ -108,6 +116,8 @@ void arch_freq_prepare_all(void) for_each_online_cpu(cpu) { if (!housekeeping_cpu(cpu, HK_FLAG_MISC)) continue; + if (rcu_is_idle_cpu(cpu)) + continue; /* Idle CPUs are completely uninteresting. */ if (!aperfmperf_snapshot_cpu(cpu, now, false)) wait = true; } @@ -118,6 +128,8 @@ void arch_freq_prepare_all(void) unsigned int arch_freq_get_on_cpu(int cpu) { + struct aperfmperf_sample *s = per_cpu_ptr(&samples, cpu); + if (!cpu_khz) return 0; @@ -131,6 +143,8 @@ unsigned int arch_freq_get_on_cpu(int cpu) return per_cpu(samples.khz, cpu); msleep(APERFMPERF_REFRESH_DELAY_MS); + atomic_set(&s->scfpending, 1); + smp_mb(); /* ->scfpending before smp_call_function_single(). */ 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 d3f0db463f96..d41b70fe4918 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -739,11 +739,13 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) if (boot_cpu_has(X86_FEATURE_IBPB)) { setup_force_cpu_cap(X86_FEATURE_USE_IBPB); + spectre_v2_user_ibpb = mode; switch (cmd) { case SPECTRE_V2_USER_CMD_FORCE: case SPECTRE_V2_USER_CMD_PRCTL_IBPB: case SPECTRE_V2_USER_CMD_SECCOMP_IBPB: static_branch_enable(&switch_mm_always_ibpb); + spectre_v2_user_ibpb = SPECTRE_V2_USER_STRICT; break; case SPECTRE_V2_USER_CMD_PRCTL: case SPECTRE_V2_USER_CMD_AUTO: @@ -757,8 +759,6 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) pr_info("mitigation: Enabling %s Indirect Branch Prediction Barrier\n", static_key_enabled(&switch_mm_always_ibpb) ? "always-on" : "conditional"); - - spectre_v2_user_ibpb = mode; } /* @@ -1254,6 +1254,14 @@ static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl) return 0; } +static bool is_spec_ib_user_controlled(void) +{ + return spectre_v2_user_ibpb == SPECTRE_V2_USER_PRCTL || + spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP || + spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL || + spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP; +} + static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) { switch (ctrl) { @@ -1261,16 +1269,26 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return 0; + /* - * Indirect branch speculation is always disabled in strict - * mode. It can neither be enabled if it was force-disabled - * by a previous prctl call. + * With strict mode for both IBPB and STIBP, the instruction + * code paths avoid checking this task flag and instead, + * unconditionally run the instruction. However, STIBP and IBPB + * are independent and either can be set to conditionally + * enabled regardless of the mode of the other. + * + * If either is set to conditional, allow the task flag to be + * updated, unless it was force-disabled by a previous prctl + * call. Currently, this is possible on an AMD CPU which has the + * feature X86_FEATURE_AMD_STIBP_ALWAYS_ON. In this case, if the + * kernel is booted with 'spectre_v2_user=seccomp', then + * spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP and + * spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED. */ - if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED || + if (!is_spec_ib_user_controlled() || task_spec_ib_force_disable(task)) return -EPERM; + task_clear_spec_ib_disable(task); task_update_spec_tif(task); break; @@ -1283,10 +1301,10 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return -EPERM; - if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED) + + if (!is_spec_ib_user_controlled()) return 0; + task_set_spec_ib_disable(task); if (ctrl == PR_SPEC_FORCE_DISABLE) task_set_spec_ib_force_disable(task); @@ -1351,20 +1369,17 @@ static int ib_prctl_get(struct task_struct *task) if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return PR_SPEC_ENABLE; - else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED) - return PR_SPEC_DISABLE; - else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_PRCTL || - spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP || - spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL || - spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP) { + else if (is_spec_ib_user_controlled()) { if (task_spec_ib_force_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE; if (task_spec_ib_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_DISABLE; return PR_SPEC_PRCTL | PR_SPEC_ENABLE; - } else + } else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED) + return PR_SPEC_DISABLE; + else return PR_SPEC_NOT_AFFECTED; } diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index 57074cf3ad7c..3ca9be482a9e 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -580,7 +580,7 @@ static void amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf, int index) if (index < 3) return; - node = amd_get_nb_id(smp_processor_id()); + node = topology_die_id(smp_processor_id()); this_leaf->nb = node_to_amd_nb(node); if (this_leaf->nb && !this_leaf->nb->l3_cache.indices) amd_calc_l3_indices(this_leaf->nb); @@ -646,7 +646,7 @@ static int find_num_cache_leaves(struct cpuinfo_x86 *c) return i; } -void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id) +void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu) { /* * We may have multiple LLCs if L3 caches exist, so check if we @@ -657,7 +657,7 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id) if (c->x86 < 0x17) { /* LLC is at the node level. */ - per_cpu(cpu_llc_id, cpu) = node_id; + per_cpu(cpu_llc_id, cpu) = c->cpu_die_id; } else if (c->x86 == 0x17 && c->x86_model <= 0x1F) { /* * LLC is at the core complex level. @@ -684,7 +684,7 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id) } } -void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id) +void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu) { /* * We may have multiple LLCs if L3 caches exist, so check if we diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 35ad8480c464..9215b91bc044 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -960,6 +960,9 @@ void get_cpu_cap(struct cpuinfo_x86 *c) if (c->extended_cpuid_level >= 0x8000000a) c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a); + if (c->extended_cpuid_level >= 0x8000001f) + c->x86_capability[CPUID_8000_001F_EAX] = cpuid_eax(0x8000001f); + init_scattered_cpuid_features(c); init_speculation_control(c); diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 9d033693519a..67944128876d 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -38,7 +38,7 @@ struct _tlb_table { #define cpu_dev_register(cpu_devX) \ static const struct cpu_dev *const __cpu_dev_##cpu_devX __used \ - __attribute__((__section__(".x86_cpu_dev.init"))) = \ + __section(".x86_cpu_dev.init") = \ &cpu_devX; extern const struct cpu_dev *const __x86_cpu_dev_start[], diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index d502241995a3..42af31b64c2c 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -69,6 +69,7 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_CQM_MBM_TOTAL, X86_FEATURE_CQM_LLC }, { X86_FEATURE_CQM_MBM_LOCAL, X86_FEATURE_CQM_LLC }, { X86_FEATURE_AVX512_BF16, X86_FEATURE_AVX512VL }, + { X86_FEATURE_AVX512_FP16, X86_FEATURE_AVX512BW }, { X86_FEATURE_ENQCMD, X86_FEATURE_XSAVES }, { X86_FEATURE_PER_THREAD_MBA, X86_FEATURE_MBA }, {} diff --git a/arch/x86/kernel/cpu/feat_ctl.c b/arch/x86/kernel/cpu/feat_ctl.c index 29a3bedabd06..3b1b01f2b248 100644 --- a/arch/x86/kernel/cpu/feat_ctl.c +++ b/arch/x86/kernel/cpu/feat_ctl.c @@ -93,16 +93,41 @@ static void init_vmx_capabilities(struct cpuinfo_x86 *c) } #endif /* CONFIG_X86_VMX_FEATURE_NAMES */ +static void clear_sgx_caps(void) +{ + setup_clear_cpu_cap(X86_FEATURE_SGX); + setup_clear_cpu_cap(X86_FEATURE_SGX_LC); +} + +static int __init nosgx(char *str) +{ + clear_sgx_caps(); + + return 0; +} + +early_param("nosgx", nosgx); + void init_ia32_feat_ctl(struct cpuinfo_x86 *c) { bool tboot = tboot_enabled(); + bool enable_sgx; u64 msr; if (rdmsrl_safe(MSR_IA32_FEAT_CTL, &msr)) { clear_cpu_cap(c, X86_FEATURE_VMX); + clear_sgx_caps(); return; } + /* + * Enable SGX if and only if the kernel supports SGX and Launch Control + * is supported, i.e. disable SGX if the LE hash MSRs can't be written. + */ + enable_sgx = cpu_has(c, X86_FEATURE_SGX) && + cpu_has(c, X86_FEATURE_SGX_LC) && + IS_ENABLED(CONFIG_X86_SGX); + if (msr & FEAT_CTL_LOCKED) goto update_caps; @@ -124,13 +149,16 @@ void init_ia32_feat_ctl(struct cpuinfo_x86 *c) msr |= FEAT_CTL_VMX_ENABLED_INSIDE_SMX; } + if (enable_sgx) + msr |= FEAT_CTL_SGX_ENABLED | FEAT_CTL_SGX_LC_ENABLED; + wrmsrl(MSR_IA32_FEAT_CTL, msr); update_caps: set_cpu_cap(c, X86_FEATURE_MSR_IA32_FEAT_CTL); if (!cpu_has(c, X86_FEATURE_VMX)) - return; + goto update_sgx; if ( (tboot && !(msr & FEAT_CTL_VMX_ENABLED_INSIDE_SMX)) || (!tboot && !(msr & FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX))) { @@ -143,4 +171,12 @@ update_caps: init_vmx_capabilities(c); #endif } + +update_sgx: + if (!(msr & FEAT_CTL_SGX_ENABLED) || + !(msr & FEAT_CTL_SGX_LC_ENABLED) || !enable_sgx) { + if (enable_sgx) + pr_err_once("SGX disabled by BIOS\n"); + clear_sgx_caps(); + } } diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c index ac6c30e5801d..ae59115d18f9 100644 --- a/arch/x86/kernel/cpu/hygon.c +++ b/arch/x86/kernel/cpu/hygon.c @@ -14,9 +14,6 @@ #include <asm/cacheinfo.h> #include <asm/spec-ctrl.h> #include <asm/delay.h> -#ifdef CONFIG_X86_64 -# include <asm/set_memory.h> -#endif #include "cpu.h" @@ -65,7 +62,6 @@ static void hygon_get_topology_early(struct cpuinfo_x86 *c) */ static void hygon_get_topology(struct cpuinfo_x86 *c) { - u8 node_id; int cpu = smp_processor_id(); /* get information required for multi-node processors */ @@ -75,7 +71,7 @@ static void hygon_get_topology(struct cpuinfo_x86 *c) cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); - node_id = ecx & 0xff; + c->cpu_die_id = ecx & 0xff; c->cpu_core_id = ebx & 0xff; @@ -93,14 +89,14 @@ static void hygon_get_topology(struct cpuinfo_x86 *c) /* Socket ID is ApicId[6] for these processors. */ c->phys_proc_id = c->apicid >> APICID_SOCKET_ID_BIT; - cacheinfo_hygon_init_llc_id(c, cpu, node_id); + cacheinfo_hygon_init_llc_id(c, cpu); } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) { u64 value; rdmsrl(MSR_FAM10H_NODE_ID, value); - node_id = value & 7; + c->cpu_die_id = value & 7; - per_cpu(cpu_llc_id, cpu) = node_id; + per_cpu(cpu_llc_id, cpu) = c->cpu_die_id; } else return; @@ -123,7 +119,7 @@ static void hygon_detect_cmp(struct cpuinfo_x86 *c) /* Convert the initial APIC ID into the socket ID */ c->phys_proc_id = c->initial_apicid >> bits; /* use socket ID also for last level cache */ - per_cpu(cpu_llc_id, cpu) = c->phys_proc_id; + per_cpu(cpu_llc_id, cpu) = c->cpu_die_id = c->phys_proc_id; } static void srat_detect_node(struct cpuinfo_x86 *c) @@ -204,23 +200,6 @@ static void early_init_hygon_mc(struct cpuinfo_x86 *c) static void bsp_init_hygon(struct cpuinfo_x86 *c) { -#ifdef CONFIG_X86_64 - unsigned long long tseg; - - /* - * Split up direct mapping around the TSEG SMM area. - * Don't do it for gbpages because there seems very little - * benefit in doing so. - */ - if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) { - unsigned long pfn = tseg >> PAGE_SHIFT; - - pr_debug("tseg: %010llx\n", tseg); - if (pfn_range_is_mapped(pfn, pfn + 1)) - set_memory_4k((unsigned long)__va(tseg), 1); - } -#endif - if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) { u64 val; diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 59a1e3ce3f14..0e422a544835 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -24,6 +24,7 @@ #include <asm/traps.h> #include <asm/resctrl.h> #include <asm/numa.h> +#include <asm/thermal.h> #ifdef CONFIG_X86_64 #include <linux/topology.h> @@ -719,6 +720,8 @@ static void init_intel(struct cpuinfo_x86 *c) tsx_disable(); split_lock_init(); + + intel_init_thermal(c); } #ifdef CONFIG_X86_32 @@ -1159,6 +1162,7 @@ static const struct x86_cpu_id split_lock_cpu_ids[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, 1), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, 1), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, 1), + X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, 1), {} }; diff --git a/arch/x86/kernel/cpu/mce/Makefile b/arch/x86/kernel/cpu/mce/Makefile index 9f020c994154..015856abdbb1 100644 --- a/arch/x86/kernel/cpu/mce/Makefile +++ b/arch/x86/kernel/cpu/mce/Makefile @@ -9,8 +9,6 @@ obj-$(CONFIG_X86_MCE_THRESHOLD) += threshold.o mce-inject-y := inject.o obj-$(CONFIG_X86_MCE_INJECT) += mce-inject.o -obj-$(CONFIG_X86_THERMAL_VECTOR) += therm_throt.o - obj-$(CONFIG_ACPI_APEI) += apei.o obj-$(CONFIG_X86_MCELOG_LEGACY) += dev-mcelog.o diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 0c6b02dd744c..e486f96b3cb3 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -1341,7 +1341,7 @@ static int threshold_create_bank(struct threshold_bank **bp, unsigned int cpu, return -ENODEV; if (is_shared_bank(bank)) { - nb = node_to_amd_nb(amd_get_nb_id(cpu)); + nb = node_to_amd_nb(topology_die_id(cpu)); /* threshold descriptor already initialized on this node? */ if (nb && nb->bank4) { @@ -1445,7 +1445,7 @@ static void threshold_remove_bank(struct threshold_bank *bank) * The last CPU on this node using the shared bank is going * away, remove that bank now. */ - nb = node_to_amd_nb(amd_get_nb_id(smp_processor_id())); + nb = node_to_amd_nb(topology_die_id(smp_processor_id())); nb->bank4 = NULL; } diff --git a/arch/x86/kernel/cpu/mce/apei.c b/arch/x86/kernel/cpu/mce/apei.c index af8d37962586..b58b85380ddb 100644 --- a/arch/x86/kernel/cpu/mce/apei.c +++ b/arch/x86/kernel/cpu/mce/apei.c @@ -51,6 +51,67 @@ void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err) } EXPORT_SYMBOL_GPL(apei_mce_report_mem_error); +int apei_smca_report_x86_error(struct cper_ia_proc_ctx *ctx_info, u64 lapic_id) +{ + const u64 *i_mce = ((const u64 *) (ctx_info + 1)); + unsigned int cpu; + struct mce m; + + if (!boot_cpu_has(X86_FEATURE_SMCA)) + return -EINVAL; + + /* + * The starting address of the register array extracted from BERT must + * match with the first expected register in the register layout of + * SMCA address space. This address corresponds to banks's MCA_STATUS + * register. + * + * Match any MCi_STATUS register by turning off bank numbers. + */ + if ((ctx_info->msr_addr & MSR_AMD64_SMCA_MC0_STATUS) != + MSR_AMD64_SMCA_MC0_STATUS) + return -EINVAL; + + /* + * The register array size must be large enough to include all the + * SMCA registers which need to be extracted. + * + * The number of registers in the register array is determined by + * Register Array Size/8 as defined in UEFI spec v2.8, sec N.2.4.2.2. + * The register layout is fixed and currently the raw data in the + * register array includes 6 SMCA registers which the kernel can + * extract. + */ + if (ctx_info->reg_arr_size < 48) + return -EINVAL; + + mce_setup(&m); + + m.extcpu = -1; + m.socketid = -1; + + for_each_possible_cpu(cpu) { + if (cpu_data(cpu).initial_apicid == lapic_id) { + m.extcpu = cpu; + m.socketid = cpu_data(m.extcpu).phys_proc_id; + break; + } + } + + m.apicid = lapic_id; + m.bank = (ctx_info->msr_addr >> 4) & 0xFF; + m.status = *i_mce; + m.addr = *(i_mce + 1); + m.misc = *(i_mce + 2); + /* Skipping MCA_CONFIG */ + m.ipid = *(i_mce + 4); + m.synd = *(i_mce + 5); + + mce_log(&m); + + return 0; +} + #define CPER_CREATOR_MCE \ GUID_INIT(0x75a574e3, 0x5052, 0x4b29, 0x8a, 0x8e, 0xbe, 0x2c, \ 0x64, 0x90, 0xb8, 0x9d) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 1c08cb9eb9f6..7962355436da 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -162,7 +162,8 @@ EXPORT_SYMBOL_GPL(mce_log); void mce_register_decode_chain(struct notifier_block *nb) { - if (WARN_ON(nb->priority > MCE_PRIO_MCELOG && nb->priority < MCE_PRIO_EDAC)) + if (WARN_ON(nb->priority < MCE_PRIO_LOWEST || + nb->priority > MCE_PRIO_HIGHEST)) return; blocking_notifier_chain_register(&x86_mce_decoder_chain, nb); @@ -877,6 +878,12 @@ static atomic_t mce_executing; static atomic_t mce_callin; /* + * Track which CPUs entered the MCA broadcast synchronization and which not in + * order to print holdouts. + */ +static cpumask_t mce_missing_cpus = CPU_MASK_ALL; + +/* * Check if a timeout waiting for other CPUs happened. */ static int mce_timed_out(u64 *t, const char *msg) @@ -893,8 +900,12 @@ static int mce_timed_out(u64 *t, const char *msg) if (!mca_cfg.monarch_timeout) goto out; if ((s64)*t < SPINUNIT) { - if (mca_cfg.tolerant <= 1) + if (mca_cfg.tolerant <= 1) { + if (cpumask_and(&mce_missing_cpus, cpu_online_mask, &mce_missing_cpus)) + pr_emerg("CPUs not responding to MCE broadcast (may include false positives): %*pbl\n", + cpumask_pr_args(&mce_missing_cpus)); mce_panic(msg, NULL, NULL); + } cpu_missing = 1; return 1; } @@ -1005,6 +1016,7 @@ static int mce_start(int *no_way_out) * is updated before mce_callin. */ order = atomic_inc_return(&mce_callin); + cpumask_clear_cpu(smp_processor_id(), &mce_missing_cpus); /* * Wait for everyone. @@ -1113,6 +1125,7 @@ static int mce_end(int order) reset: atomic_set(&global_nwo, 0); atomic_set(&mce_callin, 0); + cpumask_setall(&mce_missing_cpus); barrier(); /* @@ -1265,19 +1278,19 @@ static void kill_me_maybe(struct callback_head *cb) } } -static void queue_task_work(struct mce *m, int kill_it) +static void queue_task_work(struct mce *m, int kill_current_task) { current->mce_addr = m->addr; current->mce_kflags = m->kflags; current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV); current->mce_whole_page = whole_page(m); - if (kill_it) + if (kill_current_task) current->mce_kill_me.func = kill_me_now; else current->mce_kill_me.func = kill_me_maybe; - task_work_add(current, ¤t->mce_kill_me, true); + task_work_add(current, ¤t->mce_kill_me, TWA_RESUME); } /* @@ -1320,10 +1333,10 @@ noinstr void do_machine_check(struct pt_regs *regs) int no_way_out = 0; /* - * If kill_it gets set, there might be a way to recover from this + * If kill_current_task is not set, there might be a way to recover from this * error. */ - int kill_it = 0; + int kill_current_task = 0; /* * MCEs are always local on AMD. Same is determined by MCG_STATUS_LMCES @@ -1350,8 +1363,7 @@ noinstr void do_machine_check(struct pt_regs *regs) * severity is MCE_AR_SEVERITY we have other options. */ if (!(m.mcgstatus & MCG_STATUS_RIPV)) - kill_it = 1; - + kill_current_task = (cfg->tolerant == 3) ? 0 : 1; /* * Check if this MCE is signaled to only this logical processor, * on Intel, Zhaoxin only. @@ -1368,7 +1380,7 @@ noinstr void do_machine_check(struct pt_regs *regs) * to see it will clear it. */ if (lmce) { - if (no_way_out) + if (no_way_out && cfg->tolerant < 3) mce_panic("Fatal local machine check", &m, msg); } else { order = mce_start(&no_way_out); @@ -1384,8 +1396,13 @@ noinstr void do_machine_check(struct pt_regs *regs) * When there's any problem use only local no_way_out state. */ if (!lmce) { - if (mce_end(order) < 0) - no_way_out = worst >= MCE_PANIC_SEVERITY; + if (mce_end(order) < 0) { + if (!no_way_out) + no_way_out = worst >= MCE_PANIC_SEVERITY; + + if (no_way_out && cfg->tolerant < 3) + mce_panic("Fatal machine check on current CPU", &m, msg); + } } else { /* * If there was a fatal machine check we should have @@ -1401,19 +1418,7 @@ noinstr void do_machine_check(struct pt_regs *regs) } } - /* - * If tolerant is at an insane level we drop requests to kill - * processes and continue even when there is no way out. - */ - if (cfg->tolerant == 3) - kill_it = 0; - else if (no_way_out) - mce_panic("Fatal machine check on current CPU", &m, msg); - - if (worst > 0) - irq_work_queue(&mce_irq_work); - - if (worst != MCE_AR_SEVERITY && !kill_it) + if (worst != MCE_AR_SEVERITY && !kill_current_task) goto out; /* Fault was in user mode and we need to take some action */ @@ -1421,7 +1426,7 @@ noinstr void do_machine_check(struct pt_regs *regs) /* If this triggers there is no way to recover. Die hard. */ BUG_ON(!on_thread_stack() || !user_mode(regs)); - queue_task_work(&m, kill_it); + queue_task_work(&m, kill_current_task); } else { /* @@ -1439,7 +1444,7 @@ noinstr void do_machine_check(struct pt_regs *regs) } if (m.kflags & MCE_IN_KERNEL_COPYIN) - queue_task_work(&m, kill_it); + queue_task_work(&m, kill_current_task); } out: mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); @@ -1581,7 +1586,7 @@ static void __mcheck_cpu_mce_banks_init(void) * __mcheck_cpu_init_clear_banks() does the final bank setup. */ b->ctl = -1ULL; - b->init = 1; + b->init = true; } } @@ -1762,7 +1767,7 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) */ if (c->x86 == 6 && c->x86_model < 0x1A && this_cpu_read(mce_num_banks) > 0) - mce_banks[0].init = 0; + mce_banks[0].init = false; /* * All newer Intel systems support MCE broadcasting. Enable @@ -1811,11 +1816,9 @@ static int __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c) case X86_VENDOR_INTEL: intel_p5_mcheck_init(c); return 1; - break; case X86_VENDOR_CENTAUR: winchip_mcheck_init(c); return 1; - break; default: return 0; } @@ -1983,7 +1986,7 @@ void (*machine_check_vector)(struct pt_regs *) = unexpected_machine_check; static __always_inline void exc_machine_check_kernel(struct pt_regs *regs) { - bool irq_state; + irqentry_state_t irq_state; WARN_ON_ONCE(user_mode(regs)); @@ -1995,25 +1998,26 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *regs) mce_check_crashing_cpu()) return; - irq_state = idtentry_enter_nmi(regs); + irq_state = irqentry_nmi_enter(regs); /* * The call targets are marked noinstr, but objtool can't figure * that out because it's an indirect call. Annotate it. */ instrumentation_begin(); - trace_hardirqs_off_finish(); + machine_check_vector(regs); - if (regs->flags & X86_EFLAGS_IF) - trace_hardirqs_on_prepare(); + instrumentation_end(); - idtentry_exit_nmi(regs, irq_state); + irqentry_nmi_exit(regs, irq_state); } static __always_inline void exc_machine_check_user(struct pt_regs *regs) { irqentry_enter_from_user_mode(regs); instrumentation_begin(); + machine_check_vector(regs); + instrumentation_end(); irqentry_exit_to_user_mode(regs); } @@ -2186,7 +2190,6 @@ __setup("mce", mcheck_enable); int __init mcheck_init(void) { - mcheck_intel_therm_init(); mce_register_decode_chain(&early_nb); mce_register_decode_chain(&mce_uc_nb); mce_register_decode_chain(&mce_default_nb); @@ -2721,6 +2724,7 @@ static void mce_reset(void) atomic_set(&mce_executing, 0); atomic_set(&mce_callin, 0); atomic_set(&global_nwo, 0); + cpumask_setall(&mce_missing_cpus); } static int fake_panic_get(void *data, u64 *val) diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c index 3a44346f2276..7b360731fc2d 100644 --- a/arch/x86/kernel/cpu/mce/inject.c +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -522,8 +522,8 @@ static void do_inject(void) if (boot_cpu_has(X86_FEATURE_AMD_DCM) && b == 4 && boot_cpu_data.x86 < 0x17) { - toggle_nb_mca_mst_cpu(amd_get_nb_id(cpu)); - cpu = get_nbc_for_node(amd_get_nb_id(cpu)); + toggle_nb_mca_mst_cpu(topology_die_id(cpu)); + cpu = get_nbc_for_node(topology_die_id(cpu)); } get_online_cpus(); diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index abe9fe0fb851..e309476743b7 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -509,12 +509,32 @@ static void intel_ppin_init(struct cpuinfo_x86 *c) } } +/* + * Enable additional error logs from the integrated + * memory controller on processors that support this. + */ +static void intel_imc_init(struct cpuinfo_x86 *c) +{ + u64 error_control; + + switch (c->x86_model) { + case INTEL_FAM6_SANDYBRIDGE_X: + case INTEL_FAM6_IVYBRIDGE_X: + case INTEL_FAM6_HASWELL_X: + if (rdmsrl_safe(MSR_ERROR_CONTROL, &error_control)) + return; + error_control |= 2; + wrmsrl_safe(MSR_ERROR_CONTROL, error_control); + break; + } +} + void mce_intel_feature_init(struct cpuinfo_x86 *c) { - intel_init_thermal(c); intel_init_cmci(); intel_init_lmce(); intel_ppin_init(c); + intel_imc_init(c); } void mce_intel_feature_clear(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/mce/therm_throt.c b/arch/x86/kernel/cpu/mce/therm_throt.c deleted file mode 100644 index a7cd2d203ced..000000000000 --- a/arch/x86/kernel/cpu/mce/therm_throt.c +++ /dev/null @@ -1,739 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Thermal throttle event support code (such as syslog messaging and rate - * limiting) that was factored out from x86_64 (mce_intel.c) and i386 (p4.c). - * - * This allows consistent reporting of CPU thermal throttle events. - * - * Maintains a counter in /sys that keeps track of the number of thermal - * events, such that the user knows how bad the thermal problem might be - * (since the logging to syslog is rate limited). - * - * Author: Dmitriy Zavin ([email protected]) - * - * Credits: Adapted from Zwane Mwaikambo's original code in mce_intel.c. - * Inspired by Ross Biro's and Al Borchers' counter code. - */ -#include <linux/interrupt.h> -#include <linux/notifier.h> -#include <linux/jiffies.h> -#include <linux/kernel.h> -#include <linux/percpu.h> -#include <linux/export.h> -#include <linux/types.h> -#include <linux/init.h> -#include <linux/smp.h> -#include <linux/cpu.h> - -#include <asm/processor.h> -#include <asm/traps.h> -#include <asm/apic.h> -#include <asm/mce.h> -#include <asm/msr.h> -#include <asm/trace/irq_vectors.h> - -#include "internal.h" - -/* How long to wait between reporting thermal events */ -#define CHECK_INTERVAL (300 * HZ) - -#define THERMAL_THROTTLING_EVENT 0 -#define POWER_LIMIT_EVENT 1 - -/** - * struct _thermal_state - Represent the current thermal event state - * @next_check: Stores the next timestamp, when it is allowed - * to log the next warning message. - * @last_interrupt_time: Stores the timestamp for the last threshold - * high event. - * @therm_work: Delayed workqueue structure - * @count: Stores the current running count for thermal - * or power threshold interrupts. - * @last_count: Stores the previous running count for thermal - * or power threshold interrupts. - * @max_time_ms: This shows the maximum amount of time CPU was - * in throttled state for a single thermal - * threshold high to low state. - * @total_time_ms: This is a cumulative time during which CPU was - * in the throttled state. - * @rate_control_active: Set when a throttling message is logged. - * This is used for the purpose of rate-control. - * @new_event: Stores the last high/low status of the - * THERM_STATUS_PROCHOT or - * THERM_STATUS_POWER_LIMIT. - * @level: Stores whether this _thermal_state instance is - * for a CORE level or for PACKAGE level. - * @sample_index: Index for storing the next sample in the buffer - * temp_samples[]. - * @sample_count: Total number of samples collected in the buffer - * temp_samples[]. - * @average: The last moving average of temperature samples - * @baseline_temp: Temperature at which thermal threshold high - * interrupt was generated. - * @temp_samples: Storage for temperature samples to calculate - * moving average. - * - * This structure is used to represent data related to thermal state for a CPU. - * There is a separate storage for core and package level for each CPU. - */ -struct _thermal_state { - u64 next_check; - u64 last_interrupt_time; - struct delayed_work therm_work; - unsigned long count; - unsigned long last_count; - unsigned long max_time_ms; - unsigned long total_time_ms; - bool rate_control_active; - bool new_event; - u8 level; - u8 sample_index; - u8 sample_count; - u8 average; - u8 baseline_temp; - u8 temp_samples[3]; -}; - -struct thermal_state { - struct _thermal_state core_throttle; - struct _thermal_state core_power_limit; - struct _thermal_state package_throttle; - struct _thermal_state package_power_limit; - struct _thermal_state core_thresh0; - struct _thermal_state core_thresh1; - struct _thermal_state pkg_thresh0; - struct _thermal_state pkg_thresh1; -}; - -/* Callback to handle core threshold interrupts */ -int (*platform_thermal_notify)(__u64 msr_val); -EXPORT_SYMBOL(platform_thermal_notify); - -/* Callback to handle core package threshold_interrupts */ -int (*platform_thermal_package_notify)(__u64 msr_val); -EXPORT_SYMBOL_GPL(platform_thermal_package_notify); - -/* Callback support of rate control, return true, if - * callback has rate control */ -bool (*platform_thermal_package_rate_control)(void); -EXPORT_SYMBOL_GPL(platform_thermal_package_rate_control); - - -static DEFINE_PER_CPU(struct thermal_state, thermal_state); - -static atomic_t therm_throt_en = ATOMIC_INIT(0); - -static u32 lvtthmr_init __read_mostly; - -#ifdef CONFIG_SYSFS -#define define_therm_throt_device_one_ro(_name) \ - static DEVICE_ATTR(_name, 0444, \ - therm_throt_device_show_##_name, \ - NULL) \ - -#define define_therm_throt_device_show_func(event, name) \ - \ -static ssize_t therm_throt_device_show_##event##_##name( \ - struct device *dev, \ - struct device_attribute *attr, \ - char *buf) \ -{ \ - unsigned int cpu = dev->id; \ - ssize_t ret; \ - \ - preempt_disable(); /* CPU hotplug */ \ - if (cpu_online(cpu)) { \ - ret = sprintf(buf, "%lu\n", \ - per_cpu(thermal_state, cpu).event.name); \ - } else \ - ret = 0; \ - preempt_enable(); \ - \ - return ret; \ -} - -define_therm_throt_device_show_func(core_throttle, count); -define_therm_throt_device_one_ro(core_throttle_count); - -define_therm_throt_device_show_func(core_power_limit, count); -define_therm_throt_device_one_ro(core_power_limit_count); - -define_therm_throt_device_show_func(package_throttle, count); -define_therm_throt_device_one_ro(package_throttle_count); - -define_therm_throt_device_show_func(package_power_limit, count); -define_therm_throt_device_one_ro(package_power_limit_count); - -define_therm_throt_device_show_func(core_throttle, max_time_ms); -define_therm_throt_device_one_ro(core_throttle_max_time_ms); - -define_therm_throt_device_show_func(package_throttle, max_time_ms); -define_therm_throt_device_one_ro(package_throttle_max_time_ms); - -define_therm_throt_device_show_func(core_throttle, total_time_ms); -define_therm_throt_device_one_ro(core_throttle_total_time_ms); - -define_therm_throt_device_show_func(package_throttle, total_time_ms); -define_therm_throt_device_one_ro(package_throttle_total_time_ms); - -static struct attribute *thermal_throttle_attrs[] = { - &dev_attr_core_throttle_count.attr, - &dev_attr_core_throttle_max_time_ms.attr, - &dev_attr_core_throttle_total_time_ms.attr, - NULL -}; - -static const struct attribute_group thermal_attr_group = { - .attrs = thermal_throttle_attrs, - .name = "thermal_throttle" -}; -#endif /* CONFIG_SYSFS */ - -#define CORE_LEVEL 0 -#define PACKAGE_LEVEL 1 - -#define THERM_THROT_POLL_INTERVAL HZ -#define THERM_STATUS_PROCHOT_LOG BIT(1) - -#define THERM_STATUS_CLEAR_CORE_MASK (BIT(1) | BIT(3) | BIT(5) | BIT(7) | BIT(9) | BIT(11) | BIT(13) | BIT(15)) -#define THERM_STATUS_CLEAR_PKG_MASK (BIT(1) | BIT(3) | BIT(5) | BIT(7) | BIT(9) | BIT(11)) - -static void clear_therm_status_log(int level) -{ - int msr; - u64 mask, msr_val; - - if (level == CORE_LEVEL) { - msr = MSR_IA32_THERM_STATUS; - mask = THERM_STATUS_CLEAR_CORE_MASK; - } else { - msr = MSR_IA32_PACKAGE_THERM_STATUS; - mask = THERM_STATUS_CLEAR_PKG_MASK; - } - - rdmsrl(msr, msr_val); - msr_val &= mask; - wrmsrl(msr, msr_val & ~THERM_STATUS_PROCHOT_LOG); -} - -static void get_therm_status(int level, bool *proc_hot, u8 *temp) -{ - int msr; - u64 msr_val; - - if (level == CORE_LEVEL) - msr = MSR_IA32_THERM_STATUS; - else - msr = MSR_IA32_PACKAGE_THERM_STATUS; - - rdmsrl(msr, msr_val); - if (msr_val & THERM_STATUS_PROCHOT_LOG) - *proc_hot = true; - else - *proc_hot = false; - - *temp = (msr_val >> 16) & 0x7F; -} - -static void __maybe_unused throttle_active_work(struct work_struct *work) -{ - struct _thermal_state *state = container_of(to_delayed_work(work), - struct _thermal_state, therm_work); - unsigned int i, avg, this_cpu = smp_processor_id(); - u64 now = get_jiffies_64(); - bool hot; - u8 temp; - - get_therm_status(state->level, &hot, &temp); - /* temperature value is offset from the max so lesser means hotter */ - if (!hot && temp > state->baseline_temp) { - if (state->rate_control_active) - pr_info("CPU%d: %s temperature/speed normal (total events = %lu)\n", - this_cpu, - state->level == CORE_LEVEL ? "Core" : "Package", - state->count); - - state->rate_control_active = false; - return; - } - - if (time_before64(now, state->next_check) && - state->rate_control_active) - goto re_arm; - - state->next_check = now + CHECK_INTERVAL; - - if (state->count != state->last_count) { - /* There was one new thermal interrupt */ - state->last_count = state->count; - state->average = 0; - state->sample_count = 0; - state->sample_index = 0; - } - - state->temp_samples[state->sample_index] = temp; - state->sample_count++; - state->sample_index = (state->sample_index + 1) % ARRAY_SIZE(state->temp_samples); - if (state->sample_count < ARRAY_SIZE(state->temp_samples)) - goto re_arm; - - avg = 0; - for (i = 0; i < ARRAY_SIZE(state->temp_samples); ++i) - avg += state->temp_samples[i]; - - avg /= ARRAY_SIZE(state->temp_samples); - - if (state->average > avg) { - pr_warn("CPU%d: %s temperature is above threshold, cpu clock is throttled (total events = %lu)\n", - this_cpu, - state->level == CORE_LEVEL ? "Core" : "Package", - state->count); - state->rate_control_active = true; - } - - state->average = avg; - -re_arm: - clear_therm_status_log(state->level); - schedule_delayed_work_on(this_cpu, &state->therm_work, THERM_THROT_POLL_INTERVAL); -} - -/*** - * therm_throt_process - Process thermal throttling event from interrupt - * @curr: Whether the condition is current or not (boolean), since the - * thermal interrupt normally gets called both when the thermal - * event begins and once the event has ended. - * - * This function is called by the thermal interrupt after the - * IRQ has been acknowledged. - * - * It will take care of rate limiting and printing messages to the syslog. - */ -static void therm_throt_process(bool new_event, int event, int level) -{ - struct _thermal_state *state; - unsigned int this_cpu = smp_processor_id(); - bool old_event; - u64 now; - struct thermal_state *pstate = &per_cpu(thermal_state, this_cpu); - - now = get_jiffies_64(); - if (level == CORE_LEVEL) { - if (event == THERMAL_THROTTLING_EVENT) - state = &pstate->core_throttle; - else if (event == POWER_LIMIT_EVENT) - state = &pstate->core_power_limit; - else - return; - } else if (level == PACKAGE_LEVEL) { - if (event == THERMAL_THROTTLING_EVENT) - state = &pstate->package_throttle; - else if (event == POWER_LIMIT_EVENT) - state = &pstate->package_power_limit; - else - return; - } else - return; - - old_event = state->new_event; - state->new_event = new_event; - - if (new_event) - state->count++; - - if (event != THERMAL_THROTTLING_EVENT) - return; - - if (new_event && !state->last_interrupt_time) { - bool hot; - u8 temp; - - get_therm_status(state->level, &hot, &temp); - /* - * Ignore short temperature spike as the system is not close - * to PROCHOT. 10C offset is large enough to ignore. It is - * already dropped from the high threshold temperature. - */ - if (temp > 10) - return; - - state->baseline_temp = temp; - state->last_interrupt_time = now; - schedule_delayed_work_on(this_cpu, &state->therm_work, THERM_THROT_POLL_INTERVAL); - } else if (old_event && state->last_interrupt_time) { - unsigned long throttle_time; - - throttle_time = jiffies_delta_to_msecs(now - state->last_interrupt_time); - if (throttle_time > state->max_time_ms) - state->max_time_ms = throttle_time; - state->total_time_ms += throttle_time; - state->last_interrupt_time = 0; - } -} - -static int thresh_event_valid(int level, int event) -{ - struct _thermal_state *state; - unsigned int this_cpu = smp_processor_id(); - struct thermal_state *pstate = &per_cpu(thermal_state, this_cpu); - u64 now = get_jiffies_64(); - - if (level == PACKAGE_LEVEL) - state = (event == 0) ? &pstate->pkg_thresh0 : - &pstate->pkg_thresh1; - else - state = (event == 0) ? &pstate->core_thresh0 : - &pstate->core_thresh1; - - if (time_before64(now, state->next_check)) - return 0; - - state->next_check = now + CHECK_INTERVAL; - - return 1; -} - -static bool int_pln_enable; -static int __init int_pln_enable_setup(char *s) -{ - int_pln_enable = true; - - return 1; -} -__setup("int_pln_enable", int_pln_enable_setup); - -#ifdef CONFIG_SYSFS -/* Add/Remove thermal_throttle interface for CPU device: */ -static int thermal_throttle_add_dev(struct device *dev, unsigned int cpu) -{ - int err; - struct cpuinfo_x86 *c = &cpu_data(cpu); - - err = sysfs_create_group(&dev->kobj, &thermal_attr_group); - if (err) - return err; - - if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) { - err = sysfs_add_file_to_group(&dev->kobj, - &dev_attr_core_power_limit_count.attr, - thermal_attr_group.name); - if (err) - goto del_group; - } - - if (cpu_has(c, X86_FEATURE_PTS)) { - err = sysfs_add_file_to_group(&dev->kobj, - &dev_attr_package_throttle_count.attr, - thermal_attr_group.name); - if (err) - goto del_group; - - err = sysfs_add_file_to_group(&dev->kobj, - &dev_attr_package_throttle_max_time_ms.attr, - thermal_attr_group.name); - if (err) - goto del_group; - - err = sysfs_add_file_to_group(&dev->kobj, - &dev_attr_package_throttle_total_time_ms.attr, - thermal_attr_group.name); - if (err) - goto del_group; - - if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) { - err = sysfs_add_file_to_group(&dev->kobj, - &dev_attr_package_power_limit_count.attr, - thermal_attr_group.name); - if (err) - goto del_group; - } - } - - return 0; - -del_group: - sysfs_remove_group(&dev->kobj, &thermal_attr_group); - - return err; -} - -static void thermal_throttle_remove_dev(struct device *dev) -{ - sysfs_remove_group(&dev->kobj, &thermal_attr_group); -} - -/* Get notified when a cpu comes on/off. Be hotplug friendly. */ -static int thermal_throttle_online(unsigned int cpu) -{ - struct thermal_state *state = &per_cpu(thermal_state, cpu); - struct device *dev = get_cpu_device(cpu); - u32 l; - - state->package_throttle.level = PACKAGE_LEVEL; - state->core_throttle.level = CORE_LEVEL; - - INIT_DELAYED_WORK(&state->package_throttle.therm_work, throttle_active_work); - INIT_DELAYED_WORK(&state->core_throttle.therm_work, throttle_active_work); - - /* Unmask the thermal vector after the above workqueues are initialized. */ - l = apic_read(APIC_LVTTHMR); - apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED); - - return thermal_throttle_add_dev(dev, cpu); -} - -static int thermal_throttle_offline(unsigned int cpu) -{ - struct thermal_state *state = &per_cpu(thermal_state, cpu); - struct device *dev = get_cpu_device(cpu); - u32 l; - - /* Mask the thermal vector before draining evtl. pending work */ - l = apic_read(APIC_LVTTHMR); - apic_write(APIC_LVTTHMR, l | APIC_LVT_MASKED); - - cancel_delayed_work_sync(&state->package_throttle.therm_work); - cancel_delayed_work_sync(&state->core_throttle.therm_work); - - state->package_throttle.rate_control_active = false; - state->core_throttle.rate_control_active = false; - - thermal_throttle_remove_dev(dev); - return 0; -} - -static __init int thermal_throttle_init_device(void) -{ - int ret; - - if (!atomic_read(&therm_throt_en)) - return 0; - - ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/therm:online", - thermal_throttle_online, - thermal_throttle_offline); - return ret < 0 ? ret : 0; -} -device_initcall(thermal_throttle_init_device); - -#endif /* CONFIG_SYSFS */ - -static void notify_package_thresholds(__u64 msr_val) -{ - bool notify_thres_0 = false; - bool notify_thres_1 = false; - - if (!platform_thermal_package_notify) - return; - - /* lower threshold check */ - if (msr_val & THERM_LOG_THRESHOLD0) - notify_thres_0 = true; - /* higher threshold check */ - if (msr_val & THERM_LOG_THRESHOLD1) - notify_thres_1 = true; - - if (!notify_thres_0 && !notify_thres_1) - return; - - if (platform_thermal_package_rate_control && - platform_thermal_package_rate_control()) { - /* Rate control is implemented in callback */ - platform_thermal_package_notify(msr_val); - return; - } - - /* lower threshold reached */ - if (notify_thres_0 && thresh_event_valid(PACKAGE_LEVEL, 0)) - platform_thermal_package_notify(msr_val); - /* higher threshold reached */ - if (notify_thres_1 && thresh_event_valid(PACKAGE_LEVEL, 1)) - platform_thermal_package_notify(msr_val); -} - -static void notify_thresholds(__u64 msr_val) -{ - /* check whether the interrupt handler is defined; - * otherwise simply return - */ - if (!platform_thermal_notify) - return; - - /* lower threshold reached */ - if ((msr_val & THERM_LOG_THRESHOLD0) && - thresh_event_valid(CORE_LEVEL, 0)) - platform_thermal_notify(msr_val); - /* higher threshold reached */ - if ((msr_val & THERM_LOG_THRESHOLD1) && - thresh_event_valid(CORE_LEVEL, 1)) - platform_thermal_notify(msr_val); -} - -/* Thermal transition interrupt handler */ -static void intel_thermal_interrupt(void) -{ - __u64 msr_val; - - if (static_cpu_has(X86_FEATURE_HWP)) - wrmsrl_safe(MSR_HWP_STATUS, 0); - - rdmsrl(MSR_IA32_THERM_STATUS, msr_val); - - /* Check for violation of core thermal thresholds*/ - notify_thresholds(msr_val); - - therm_throt_process(msr_val & THERM_STATUS_PROCHOT, - THERMAL_THROTTLING_EVENT, - CORE_LEVEL); - - if (this_cpu_has(X86_FEATURE_PLN) && int_pln_enable) - therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT, - POWER_LIMIT_EVENT, - CORE_LEVEL); - - if (this_cpu_has(X86_FEATURE_PTS)) { - rdmsrl(MSR_IA32_PACKAGE_THERM_STATUS, msr_val); - /* check violations of package thermal thresholds */ - notify_package_thresholds(msr_val); - therm_throt_process(msr_val & PACKAGE_THERM_STATUS_PROCHOT, - THERMAL_THROTTLING_EVENT, - PACKAGE_LEVEL); - if (this_cpu_has(X86_FEATURE_PLN) && int_pln_enable) - therm_throt_process(msr_val & - PACKAGE_THERM_STATUS_POWER_LIMIT, - POWER_LIMIT_EVENT, - PACKAGE_LEVEL); - } -} - -static void unexpected_thermal_interrupt(void) -{ - pr_err("CPU%d: Unexpected LVT thermal interrupt!\n", - smp_processor_id()); -} - -static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt; - -DEFINE_IDTENTRY_SYSVEC(sysvec_thermal) -{ - trace_thermal_apic_entry(THERMAL_APIC_VECTOR); - inc_irq_stat(irq_thermal_count); - smp_thermal_vector(); - trace_thermal_apic_exit(THERMAL_APIC_VECTOR); - ack_APIC_irq(); -} - -/* Thermal monitoring depends on APIC, ACPI and clock modulation */ -static int intel_thermal_supported(struct cpuinfo_x86 *c) -{ - if (!boot_cpu_has(X86_FEATURE_APIC)) - return 0; - if (!cpu_has(c, X86_FEATURE_ACPI) || !cpu_has(c, X86_FEATURE_ACC)) - return 0; - return 1; -} - -void __init mcheck_intel_therm_init(void) -{ - /* - * This function is only called on boot CPU. Save the init thermal - * LVT value on BSP and use that value to restore APs' thermal LVT - * entry BIOS programmed later - */ - if (intel_thermal_supported(&boot_cpu_data)) - lvtthmr_init = apic_read(APIC_LVTTHMR); -} - -void intel_init_thermal(struct cpuinfo_x86 *c) -{ - unsigned int cpu = smp_processor_id(); - int tm2 = 0; - u32 l, h; - - if (!intel_thermal_supported(c)) - return; - - /* - * First check if its enabled already, in which case there might - * be some SMM goo which handles it, so we can't even put a handler - * since it might be delivered via SMI already: - */ - rdmsr(MSR_IA32_MISC_ENABLE, l, h); - - h = lvtthmr_init; - /* - * The initial value of thermal LVT entries on all APs always reads - * 0x10000 because APs are woken up by BSP issuing INIT-SIPI-SIPI - * sequence to them and LVT registers are reset to 0s except for - * the mask bits which are set to 1s when APs receive INIT IPI. - * If BIOS takes over the thermal interrupt and sets its interrupt - * delivery mode to SMI (not fixed), it restores the value that the - * BIOS has programmed on AP based on BSP's info we saved since BIOS - * is always setting the same value for all threads/cores. - */ - if ((h & APIC_DM_FIXED_MASK) != APIC_DM_FIXED) - apic_write(APIC_LVTTHMR, lvtthmr_init); - - - if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) { - if (system_state == SYSTEM_BOOTING) - pr_debug("CPU%d: Thermal monitoring handled by SMI\n", cpu); - return; - } - - /* early Pentium M models use different method for enabling TM2 */ - if (cpu_has(c, X86_FEATURE_TM2)) { - if (c->x86 == 6 && (c->x86_model == 9 || c->x86_model == 13)) { - rdmsr(MSR_THERM2_CTL, l, h); - if (l & MSR_THERM2_CTL_TM_SELECT) - tm2 = 1; - } else if (l & MSR_IA32_MISC_ENABLE_TM2) - tm2 = 1; - } - - /* We'll mask the thermal vector in the lapic till we're ready: */ - h = THERMAL_APIC_VECTOR | APIC_DM_FIXED | APIC_LVT_MASKED; - apic_write(APIC_LVTTHMR, h); - - rdmsr(MSR_IA32_THERM_INTERRUPT, l, h); - if (cpu_has(c, X86_FEATURE_PLN) && !int_pln_enable) - wrmsr(MSR_IA32_THERM_INTERRUPT, - (l | (THERM_INT_LOW_ENABLE - | THERM_INT_HIGH_ENABLE)) & ~THERM_INT_PLN_ENABLE, h); - else if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) - wrmsr(MSR_IA32_THERM_INTERRUPT, - l | (THERM_INT_LOW_ENABLE - | THERM_INT_HIGH_ENABLE | THERM_INT_PLN_ENABLE), h); - else - wrmsr(MSR_IA32_THERM_INTERRUPT, - l | (THERM_INT_LOW_ENABLE | THERM_INT_HIGH_ENABLE), h); - - if (cpu_has(c, X86_FEATURE_PTS)) { - rdmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h); - if (cpu_has(c, X86_FEATURE_PLN) && !int_pln_enable) - wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, - (l | (PACKAGE_THERM_INT_LOW_ENABLE - | PACKAGE_THERM_INT_HIGH_ENABLE)) - & ~PACKAGE_THERM_INT_PLN_ENABLE, h); - else if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) - wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, - l | (PACKAGE_THERM_INT_LOW_ENABLE - | PACKAGE_THERM_INT_HIGH_ENABLE - | PACKAGE_THERM_INT_PLN_ENABLE), h); - else - wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, - l | (PACKAGE_THERM_INT_LOW_ENABLE - | PACKAGE_THERM_INT_HIGH_ENABLE), h); - } - - smp_thermal_vector = intel_thermal_interrupt; - - rdmsr(MSR_IA32_MISC_ENABLE, l, h); - wrmsr(MSR_IA32_MISC_ENABLE, l | MSR_IA32_MISC_ENABLE_TM1, h); - - pr_info_once("CPU0: Thermal monitoring enabled (%s)\n", - tm2 ? "TM2" : "TM1"); - - /* enable thermal throttle processing */ - atomic_set(&therm_throt_en, 1); -} diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 3f6b137ef4e6..3d4a48336084 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -215,7 +215,6 @@ static unsigned int __verify_patch_size(u8 family, u32 sh_psize, size_t buf_size default: WARN(1, "%s: WTF family: 0x%x\n", __func__, family); return 0; - break; } if (sh_psize > min_t(u32, buf_size, max_size)) diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index ec6f0415bc6d..b935e1b5f115 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -830,7 +830,7 @@ static const struct attribute_group cpu_root_microcode_group = { .attrs = cpu_root_microcode_attrs, }; -int __init microcode_init(void) +static int __init microcode_init(void) { struct cpuinfo_x86 *c = &boot_cpu_data; int error; diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 6a99535d7f37..7e8e07bddd5f 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -100,53 +100,6 @@ static int has_newer_microcode(void *mc, unsigned int csig, int cpf, int new_rev return find_matching_signature(mc, csig, cpf); } -/* - * Given CPU signature and a microcode patch, this function finds if the - * microcode patch has matching family and model with the CPU. - * - * %true - if there's a match - * %false - otherwise - */ -static bool microcode_matches(struct microcode_header_intel *mc_header, - unsigned long sig) -{ - unsigned long total_size = get_totalsize(mc_header); - unsigned long data_size = get_datasize(mc_header); - struct extended_sigtable *ext_header; - unsigned int fam_ucode, model_ucode; - struct extended_signature *ext_sig; - unsigned int fam, model; - int ext_sigcount, i; - - fam = x86_family(sig); - model = x86_model(sig); - - fam_ucode = x86_family(mc_header->sig); - model_ucode = x86_model(mc_header->sig); - - if (fam == fam_ucode && model == model_ucode) - return true; - - /* Look for ext. headers: */ - if (total_size <= data_size + MC_HEADER_SIZE) - return false; - - ext_header = (void *) mc_header + data_size + MC_HEADER_SIZE; - ext_sig = (void *)ext_header + EXT_HEADER_SIZE; - ext_sigcount = ext_header->count; - - for (i = 0; i < ext_sigcount; i++) { - fam_ucode = x86_family(ext_sig->sig); - model_ucode = x86_model(ext_sig->sig); - - if (fam == fam_ucode && model == model_ucode) - return true; - - ext_sig++; - } - return false; -} - static struct ucode_patch *memdup_patch(void *data, unsigned int size) { struct ucode_patch *p; @@ -164,7 +117,7 @@ static struct ucode_patch *memdup_patch(void *data, unsigned int size) return p; } -static void save_microcode_patch(void *data, unsigned int size) +static void save_microcode_patch(struct ucode_cpu_info *uci, void *data, unsigned int size) { struct microcode_header_intel *mc_hdr, *mc_saved_hdr; struct ucode_patch *iter, *tmp, *p = NULL; @@ -210,6 +163,9 @@ static void save_microcode_patch(void *data, unsigned int size) if (!p) return; + if (!find_matching_signature(p->data, uci->cpu_sig.sig, uci->cpu_sig.pf)) + return; + /* * Save for early loading. On 32-bit, that needs to be a physical * address as the APs are running from physical addresses, before @@ -344,13 +300,14 @@ scan_microcode(void *data, size_t size, struct ucode_cpu_info *uci, bool save) size -= mc_size; - if (!microcode_matches(mc_header, uci->cpu_sig.sig)) { + if (!find_matching_signature(data, uci->cpu_sig.sig, + uci->cpu_sig.pf)) { data += mc_size; continue; } if (save) { - save_microcode_patch(data, mc_size); + save_microcode_patch(uci, data, mc_size); goto next; } @@ -483,14 +440,14 @@ static void show_saved_mc(void) * Save this microcode patch. It will be loaded early when a CPU is * hot-added or resumes. */ -static void save_mc_for_early(u8 *mc, unsigned int size) +static void save_mc_for_early(struct ucode_cpu_info *uci, u8 *mc, unsigned int size) { /* Synchronization during CPU hotplug. */ static DEFINE_MUTEX(x86_cpu_microcode_mutex); mutex_lock(&x86_cpu_microcode_mutex); - save_microcode_patch(mc, size); + save_microcode_patch(uci, mc, size); show_saved_mc(); mutex_unlock(&x86_cpu_microcode_mutex); @@ -935,7 +892,7 @@ static enum ucode_state generic_load_microcode(int cpu, struct iov_iter *iter) * permanent memory. So it will be loaded early when a CPU is hot added * or resumes. */ - save_mc_for_early(new_mc, new_mc_size); + save_mc_for_early(uci, new_mc, new_mc_size); pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n", cpu, new_rev, uci->cpu_sig.rev); diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 9834a43cd0fa..e88bc296afca 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -31,6 +31,11 @@ #include <asm/reboot.h> #include <asm/nmi.h> #include <clocksource/hyperv_timer.h> +#include <asm/numa.h> + +/* Is Linux running as the root partition? */ +bool hv_root_partition; +EXPORT_SYMBOL_GPL(hv_root_partition); struct ms_hyperv_info ms_hyperv; EXPORT_SYMBOL_GPL(ms_hyperv); @@ -55,9 +60,14 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_callback) set_irq_regs(old_regs); } -void hv_setup_vmbus_irq(void (*handler)(void)) +int hv_setup_vmbus_irq(int irq, void (*handler)(void)) { + /* + * The 'irq' argument is ignored on x86/x64 because a hard-coded + * interrupt vector is used for Hyper-V interrupts. + */ vmbus_handler = handler; + return 0; } void hv_remove_vmbus_irq(void) @@ -130,14 +140,32 @@ static void hv_machine_shutdown(void) { if (kexec_in_progress && hv_kexec_handler) hv_kexec_handler(); + + /* + * Call hv_cpu_die() on all the CPUs, otherwise later the hypervisor + * corrupts the old VP Assist Pages and can crash the kexec kernel. + */ + if (kexec_in_progress && hyperv_init_cpuhp > 0) + cpuhp_remove_state(hyperv_init_cpuhp); + + /* The function calls stop_other_cpus(). */ native_machine_shutdown(); + + /* Disable the hypercall page when there is only 1 active CPU. */ + if (kexec_in_progress) + hyperv_cleanup(); } static void hv_machine_crash_shutdown(struct pt_regs *regs) { if (hv_crash_handler) hv_crash_handler(regs); + + /* The function calls crash_smp_send_stop(). */ native_machine_crash_shutdown(regs); + + /* Disable the hypercall page when there is only 1 active CPU. */ + hyperv_cleanup(); } #endif /* CONFIG_KEXEC_CORE */ #endif /* CONFIG_HYPERV */ @@ -203,6 +231,32 @@ static void __init hv_smp_prepare_boot_cpu(void) hv_init_spinlocks(); #endif } + +static void __init hv_smp_prepare_cpus(unsigned int max_cpus) +{ +#ifdef CONFIG_X86_64 + int i; + int ret; +#endif + + native_smp_prepare_cpus(max_cpus); + +#ifdef CONFIG_X86_64 + for_each_present_cpu(i) { + if (i == 0) + continue; + ret = hv_call_add_logical_proc(numa_cpu_node(i), i, cpu_physical_id(i)); + BUG_ON(ret); + } + + for_each_present_cpu(i) { + if (i == 0) + continue; + ret = hv_call_create_vp(numa_cpu_node(i), hv_current_partition_id, i, i); + BUG_ON(ret); + } +#endif +} #endif static void __init ms_hyperv_init_platform(void) @@ -220,6 +274,7 @@ static void __init ms_hyperv_init_platform(void) * Extract the features and hints */ ms_hyperv.features = cpuid_eax(HYPERV_CPUID_FEATURES); + ms_hyperv.features_b = cpuid_ebx(HYPERV_CPUID_FEATURES); ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES); ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO); @@ -233,6 +288,22 @@ static void __init ms_hyperv_init_platform(void) ms_hyperv.max_vp_index, ms_hyperv.max_lp_index); /* + * Check CPU management privilege. + * + * To mirror what Windows does we should extract CPU management + * features and use the ReservedIdentityBit to detect if Linux is the + * root partition. But that requires negotiating CPU management + * interface (a process to be finalized). + * + * For now, use the privilege flag as the indicator for running as + * root. + */ + if (cpuid_ebx(HYPERV_CPUID_FEATURES) & HV_CPU_MANAGEMENT) { + hv_root_partition = true; + pr_info("Hyper-V: running as root partition\n"); + } + + /* * Extract host information. */ if (cpuid_eax(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS) >= @@ -254,6 +325,14 @@ static void __init ms_hyperv_init_platform(void) x86_platform.calibrate_cpu = hv_get_tsc_khz; } + if (ms_hyperv.features_b & HV_ISOLATION) { + ms_hyperv.isolation_config_a = cpuid_eax(HYPERV_CPUID_ISOLATION_CONFIG); + ms_hyperv.isolation_config_b = cpuid_ebx(HYPERV_CPUID_ISOLATION_CONFIG); + + pr_info("Hyper-V: Isolation Config: Group A 0x%x, Group B 0x%x\n", + ms_hyperv.isolation_config_a, ms_hyperv.isolation_config_b); + } + if (ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED) { ms_hyperv.nested_features = cpuid_eax(HYPERV_CPUID_NESTED_FEATURES); @@ -343,6 +422,8 @@ static void __init ms_hyperv_init_platform(void) # ifdef CONFIG_SMP smp_ops.smp_prepare_boot_cpu = hv_smp_prepare_boot_cpu; + if (hv_root_partition) + smp_ops.smp_prepare_cpus = hv_smp_prepare_cpus; # endif /* @@ -361,9 +442,38 @@ static void __init ms_hyperv_init_platform(void) #endif } +static bool __init ms_hyperv_x2apic_available(void) +{ + return x2apic_supported(); +} + +/* + * If ms_hyperv_msi_ext_dest_id() returns true, hyperv_prepare_irq_remapping() + * returns -ENODEV and the Hyper-V IOMMU driver is not used; instead, the + * generic support of the 15-bit APIC ID is used: see __irq_msi_compose_msg(). + * + * Note: for a VM on Hyper-V, the I/O-APIC is the only device which + * (logically) generates MSIs directly to the system APIC irq domain. + * There is no HPET, and PCI MSI/MSI-X interrupts are remapped by the + * pci-hyperv host bridge. + */ +static bool __init ms_hyperv_msi_ext_dest_id(void) +{ + u32 eax; + + eax = cpuid_eax(HYPERV_CPUID_VIRT_STACK_INTERFACE); + if (eax != HYPERV_VS_INTERFACE_EAX_SIGNATURE) + return false; + + eax = cpuid_eax(HYPERV_CPUID_VIRT_STACK_PROPERTIES); + return eax & HYPERV_VS_PROPERTIES_EAX_EXTENDED_IOAPIC_RTE; +} + const __initconst struct hypervisor_x86 x86_hyper_ms_hyperv = { .name = "Microsoft Hyper-V", .detect = ms_hyperv_platform, .type = X86_HYPER_MS_HYPERV, + .init.x2apic_available = ms_hyperv_x2apic_available, + .init.msi_ext_dest_id = ms_hyperv_msi_ext_dest_id, .init.init_platform = ms_hyperv_init_platform, }; diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 5bd011737272..9231640782fa 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -537,9 +537,9 @@ static void __init print_out_mtrr_range_state(void) if (!size_base) continue; - size_base = to_size_factor(size_base, &size_factor), + size_base = to_size_factor(size_base, &size_factor); start_base = range_state[i].base_pfn << (PAGE_SHIFT - 10); - start_base = to_size_factor(start_base, &start_factor), + start_base = to_size_factor(start_base, &start_factor); type = range_state[i].type; pr_debug("reg %d, base: %ld%cB, range: %ld%cB, type %s\n", diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 23ad8e953dfb..b90f3f437765 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -3,7 +3,6 @@ * This only handles 32bit MTRR on 32bit hosts. This is strictly wrong * because MTRRs can span up to 40 bits (36bits on most modern x86) */ -#define DEBUG #include <linux/export.h> #include <linux/init.h> @@ -167,9 +166,6 @@ static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end, *repeat = 0; *uniform = 1; - /* Make end inclusive instead of exclusive */ - end--; - prev_match = MTRR_TYPE_INVALID; for (i = 0; i < num_var_ranges; ++i) { unsigned short start_state, end_state, inclusive; @@ -261,6 +257,9 @@ u8 mtrr_type_lookup(u64 start, u64 end, u8 *uniform) int repeat; u64 partial_end; + /* Make end inclusive instead of exclusive */ + end--; + if (!mtrr_state_set) return MTRR_TYPE_INVALID; diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index 6a80f36b5d59..28c8a23aa42e 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -31,8 +31,6 @@ System Programming Guide; Section 9.11. (1997 edition - PPro). */ -#define DEBUG - #include <linux/types.h> /* FIXME: kvm_para.h needs this */ #include <linux/stop_machine.h> @@ -794,8 +792,6 @@ void mtrr_ap_init(void) if (!use_intel() || mtrr_aps_delayed_init) return; - rcu_cpu_starting(smp_processor_id()); - /* * Ideally we should hold mtrr_mutex here to avoid mtrr entries * changed, but this routine will be called in cpu boot time, @@ -813,7 +809,8 @@ void mtrr_ap_init(void) } /** - * Save current fixed-range MTRR state of the first cpu in cpu_online_mask. + * mtrr_save_state - Save current fixed-range MTRR state of the first + * cpu in cpu_online_mask. */ void mtrr_save_state(void) { diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index a5ee607a3b89..3ef5868ac588 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -3,7 +3,7 @@ * local apic based NMI watchdog for various CPUs. * * This file also handles reservation of performance counters for coordination - * with other users (like oprofile). + * with other users. * * Note that these events normally don't tick when the CPU idles. This means * the frequency varies with CPU load. @@ -105,15 +105,6 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr) } -/* checks for a bit availability (hack for oprofile) */ -int avail_to_resrv_perfctr_nmi_bit(unsigned int counter) -{ - BUG_ON(counter > NMI_MAX_COUNTER_BITS); - - return !test_bit(counter, perfctr_nmi_owner); -} -EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi_bit); - int reserve_perfctr_nmi(unsigned int msr) { unsigned int counter; diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index e5f4ee8f4c3b..698bb26aeb6e 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -570,6 +570,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) if (d) { cpumask_set_cpu(cpu, &d->cpu_mask); + if (r->cache.arch_has_per_cpu_cfg) + rdt_domain_reconfigure_cdp(r); return; } @@ -893,6 +895,10 @@ static __init void __check_quirks_intel(void) set_rdt_options("!cmt,!mbmtotal,!mbmlocal,!l3cat"); else set_rdt_options("!l3cat"); + fallthrough; + case INTEL_FAM6_BROADWELL_X: + intel_rdt_mbm_apply_quirk(); + break; } } @@ -923,6 +929,7 @@ static __init void rdt_init_res_defs_intel(void) r->rid == RDT_RESOURCE_L2CODE) { r->cache.arch_has_sparse_bitmaps = false; r->cache.arch_has_empty_bitmaps = false; + r->cache.arch_has_per_cpu_cfg = false; } else if (r->rid == RDT_RESOURCE_MBA) { r->msr_base = MSR_IA32_MBA_THRTL_BASE; r->msr_update = mba_wrmsr_intel; @@ -943,6 +950,7 @@ static __init void rdt_init_res_defs_amd(void) r->rid == RDT_RESOURCE_L2CODE) { r->cache.arch_has_sparse_bitmaps = true; r->cache.arch_has_empty_bitmaps = true; + r->cache.arch_has_per_cpu_cfg = true; } else if (r->rid == RDT_RESOURCE_MBA) { r->msr_base = MSR_IA32_MBA_BW_BASE; r->msr_update = mba_wrmsr_amd; diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 80fa997fae60..c4d320d02fd5 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -264,7 +264,7 @@ void __exit rdtgroup_exit(void); struct rftype { char *name; umode_t mode; - struct kernfs_ops *kf_ops; + const struct kernfs_ops *kf_ops; unsigned long flags; unsigned long fflags; @@ -360,6 +360,8 @@ struct msr_param { * executing entities * @arch_has_sparse_bitmaps: True if a bitmap like f00f is valid. * @arch_has_empty_bitmaps: True if the '0' bitmap is valid. + * @arch_has_per_cpu_cfg: True if QOS_CFG register for this cache + * level has CPU scope. */ struct rdt_cache { unsigned int cbm_len; @@ -369,6 +371,7 @@ struct rdt_cache { unsigned int shareable_bits; bool arch_has_sparse_bitmaps; bool arch_has_empty_bitmaps; + bool arch_has_per_cpu_cfg; }; /** @@ -569,6 +572,7 @@ union cpuid_0x10_x_edx { void rdt_last_cmd_clear(void); void rdt_last_cmd_puts(const char *s); +__printf(1, 2) void rdt_last_cmd_printf(const char *fmt, ...); void rdt_ctrl_update(void *arg); @@ -616,6 +620,7 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms); void mbm_handle_overflow(struct work_struct *work); +void __init intel_rdt_mbm_apply_quirk(void); bool is_mba_sc(struct rdt_resource *r); void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm); u32 delay_bw_map(unsigned long bw, struct rdt_resource *r); diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 54dffe574e67..7ac31210e452 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -64,6 +64,69 @@ unsigned int rdt_mon_features; */ unsigned int resctrl_cqm_threshold; +#define CF(cf) ((unsigned long)(1048576 * (cf) + 0.5)) + +/* + * The correction factor table is documented in Documentation/x86/resctrl.rst. + * If rmid > rmid threshold, MBM total and local values should be multiplied + * by the correction factor. + * + * The original table is modified for better code: + * + * 1. The threshold 0 is changed to rmid count - 1 so don't do correction + * for the case. + * 2. MBM total and local correction table indexed by core counter which is + * equal to (x86_cache_max_rmid + 1) / 8 - 1 and is from 0 up to 27. + * 3. The correction factor is normalized to 2^20 (1048576) so it's faster + * to calculate corrected value by shifting: + * corrected_value = (original_value * correction_factor) >> 20 + */ +static const struct mbm_correction_factor_table { + u32 rmidthreshold; + u64 cf; +} mbm_cf_table[] __initdata = { + {7, CF(1.000000)}, + {15, CF(1.000000)}, + {15, CF(0.969650)}, + {31, CF(1.000000)}, + {31, CF(1.066667)}, + {31, CF(0.969650)}, + {47, CF(1.142857)}, + {63, CF(1.000000)}, + {63, CF(1.185115)}, + {63, CF(1.066553)}, + {79, CF(1.454545)}, + {95, CF(1.000000)}, + {95, CF(1.230769)}, + {95, CF(1.142857)}, + {95, CF(1.066667)}, + {127, CF(1.000000)}, + {127, CF(1.254863)}, + {127, CF(1.185255)}, + {151, CF(1.000000)}, + {127, CF(1.066667)}, + {167, CF(1.000000)}, + {159, CF(1.454334)}, + {183, CF(1.000000)}, + {127, CF(0.969744)}, + {191, CF(1.280246)}, + {191, CF(1.230921)}, + {215, CF(1.000000)}, + {191, CF(1.143118)}, +}; + +static u32 mbm_cf_rmidthreshold __read_mostly = UINT_MAX; +static u64 mbm_cf __read_mostly; + +static inline u64 get_corrected_mbm_count(u32 rmid, unsigned long val) +{ + /* Correct MBM value. */ + if (rmid > mbm_cf_rmidthreshold) + val = (val * mbm_cf) >> 20; + + return val; +} + static inline struct rmid_entry *__rmid_entry(u32 rmid) { struct rmid_entry *entry; @@ -260,7 +323,8 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr) m->chunks += chunks; m->prev_msr = tval; - rr->val += m->chunks; + rr->val += get_corrected_mbm_count(rmid, m->chunks); + return 0; } @@ -279,8 +343,7 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr) return; chunks = mbm_overflow_count(m->prev_bw_msr, tval, rr->r->mbm_width); - m->chunks += chunks; - cur_bw = (chunks * r->mon_scale) >> 20; + cur_bw = (get_corrected_mbm_count(rmid, chunks) * r->mon_scale) >> 20; if (m->delta_comp) m->delta_bw = abs(cur_bw - m->prev_bw); @@ -450,15 +513,14 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid) } if (is_mbm_local_enabled()) { rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID; + __mon_event_count(rmid, &rr); /* * Call the MBA software controller only for the * control groups and when user has enabled * the software controller explicitly. */ - if (!is_mba_sc(NULL)) - __mon_event_count(rmid, &rr); - else + if (is_mba_sc(NULL)) mbm_bw_count(rmid, &rr); } } @@ -644,3 +706,17 @@ int rdt_get_mon_l3_config(struct rdt_resource *r) return 0; } + +void __init intel_rdt_mbm_apply_quirk(void) +{ + int cf_index; + + cf_index = (boot_cpu_data.x86_cache_max_rmid + 1) / 8 - 1; + if (cf_index >= ARRAY_SIZE(mbm_cf_table)) { + pr_info("No MBM correction factor available\n"); + return; + } + + mbm_cf_rmidthreshold = mbm_cf_table[cf_index].rmidthreshold; + mbm_cf = mbm_cf_table[cf_index].cf; +} diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index 0daf2f1cf7a8..e916646adc69 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -1458,7 +1458,7 @@ static int pseudo_lock_dev_release(struct inode *inode, struct file *filp) return 0; } -static int pseudo_lock_dev_mremap(struct vm_area_struct *area) +static int pseudo_lock_dev_mremap(struct vm_area_struct *area, unsigned long flags) { /* Not supported */ return -EINVAL; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index b494187632b2..f9190adc52cb 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -240,13 +240,13 @@ static ssize_t rdtgroup_file_write(struct kernfs_open_file *of, char *buf, return -EINVAL; } -static struct kernfs_ops rdtgroup_kf_single_ops = { +static const struct kernfs_ops rdtgroup_kf_single_ops = { .atomic_write_len = PAGE_SIZE, .write = rdtgroup_file_write, .seq_show = rdtgroup_seqfile_show, }; -static struct kernfs_ops kf_mondata_ops = { +static const struct kernfs_ops kf_mondata_ops = { .atomic_write_len = PAGE_SIZE, .seq_show = rdtgroup_mondata_show, }; @@ -507,89 +507,88 @@ unlock: return ret ?: nbytes; } -struct task_move_callback { - struct callback_head work; - struct rdtgroup *rdtgrp; -}; - -static void move_myself(struct callback_head *head) +/** + * rdtgroup_remove - the helper to remove resource group safely + * @rdtgrp: resource group to remove + * + * On resource group creation via a mkdir, an extra kernfs_node reference is + * taken to ensure that the rdtgroup structure remains accessible for the + * rdtgroup_kn_unlock() calls where it is removed. + * + * Drop the extra reference here, then free the rdtgroup structure. + * + * Return: void + */ +static void rdtgroup_remove(struct rdtgroup *rdtgrp) { - struct task_move_callback *callback; - struct rdtgroup *rdtgrp; - - callback = container_of(head, struct task_move_callback, work); - rdtgrp = callback->rdtgrp; + kernfs_put(rdtgrp->kn); + kfree(rdtgrp); +} +static void _update_task_closid_rmid(void *task) +{ /* - * If resource group was deleted before this task work callback - * was invoked, then assign the task to root group and free the - * resource group. + * If the task is still current on this CPU, update PQR_ASSOC MSR. + * Otherwise, the MSR is updated when the task is scheduled in. */ - if (atomic_dec_and_test(&rdtgrp->waitcount) && - (rdtgrp->flags & RDT_DELETED)) { - current->closid = 0; - current->rmid = 0; - kfree(rdtgrp); - } - - if (unlikely(current->flags & PF_EXITING)) - goto out; - - preempt_disable(); - /* update PQR_ASSOC MSR to make resource group go into effect */ - resctrl_sched_in(); - preempt_enable(); + if (task == current) + resctrl_sched_in(); +} -out: - kfree(callback); +static void update_task_closid_rmid(struct task_struct *t) +{ + if (IS_ENABLED(CONFIG_SMP) && task_curr(t)) + smp_call_function_single(task_cpu(t), _update_task_closid_rmid, t, 1); + else + _update_task_closid_rmid(t); } static int __rdtgroup_move_task(struct task_struct *tsk, struct rdtgroup *rdtgrp) { - struct task_move_callback *callback; - int ret; - - callback = kzalloc(sizeof(*callback), GFP_KERNEL); - if (!callback) - return -ENOMEM; - callback->work.func = move_myself; - callback->rdtgrp = rdtgrp; + /* If the task is already in rdtgrp, no need to move the task. */ + if ((rdtgrp->type == RDTCTRL_GROUP && tsk->closid == rdtgrp->closid && + tsk->rmid == rdtgrp->mon.rmid) || + (rdtgrp->type == RDTMON_GROUP && tsk->rmid == rdtgrp->mon.rmid && + tsk->closid == rdtgrp->mon.parent->closid)) + return 0; /* - * Take a refcount, so rdtgrp cannot be freed before the - * callback has been invoked. + * Set the task's closid/rmid before the PQR_ASSOC MSR can be + * updated by them. + * + * For ctrl_mon groups, move both closid and rmid. + * For monitor groups, can move the tasks only from + * their parent CTRL group. */ - atomic_inc(&rdtgrp->waitcount); - ret = task_work_add(tsk, &callback->work, true); - if (ret) { - /* - * Task is exiting. Drop the refcount and free the callback. - * No need to check the refcount as the group cannot be - * deleted before the write function unlocks rdtgroup_mutex. - */ - atomic_dec(&rdtgrp->waitcount); - kfree(callback); - rdt_last_cmd_puts("Task exited\n"); - } else { - /* - * 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; - } + + if (rdtgrp->type == RDTCTRL_GROUP) { + WRITE_ONCE(tsk->closid, rdtgrp->closid); + WRITE_ONCE(tsk->rmid, rdtgrp->mon.rmid); + } else if (rdtgrp->type == RDTMON_GROUP) { + if (rdtgrp->mon.parent->closid == tsk->closid) { + WRITE_ONCE(tsk->rmid, rdtgrp->mon.rmid); + } else { + rdt_last_cmd_puts("Can't move task to different control group\n"); + return -EINVAL; } } - return ret; + + /* + * Ensure the task's closid and rmid are written before determining if + * the task is current that will decide if it will be interrupted. + */ + barrier(); + + /* + * By now, the task's closid and rmid are set. If the task is current + * on a CPU, the PQR_ASSOC MSR needs to be updated to make the resource + * group go into effect. If the task is not current, the MSR will be + * updated when the task is scheduled in. + */ + update_task_closid_rmid(tsk); + + return 0; } static bool is_closid_match(struct task_struct *t, struct rdtgroup *r) @@ -1769,7 +1768,6 @@ static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name, 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; @@ -1792,7 +1790,6 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL); if (IS_ERR(kn_info)) return PTR_ERR(kn_info); - kernfs_get(kn_info); ret = rdtgroup_add_files(kn_info, RF_TOP_INFO); if (ret) @@ -1813,12 +1810,6 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) goto out_destroy; } - /* - * This extra ref will be put in kernfs_remove() and guarantees - * that @rdtgrp->kn is always accessible. - */ - kernfs_get(kn_info); - ret = rdtgroup_kn_set_ugid(kn_info); if (ret) goto out_destroy; @@ -1847,12 +1838,6 @@ mongroup_create_dir(struct kernfs_node *parent_kn, struct rdtgroup *prgrp, 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; @@ -1905,8 +1890,13 @@ static int set_cache_qos_cfg(int level, bool enable) r_l = &rdt_resources_all[level]; list_for_each_entry(d, &r_l->domains, list) { - /* Pick one CPU from each domain instance to update MSR */ - cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); + if (r_l->cache.arch_has_per_cpu_cfg) + /* Pick all the CPUs in the domain instance */ + for_each_cpu(cpu, &d->cpu_mask) + cpumask_set_cpu(cpu, cpu_mask); + else + /* Pick one CPU from each domain instance to update MSR */ + cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); } cpu = get_cpu(); /* Update QOS_CFG MSR on this cpu if it's in cpu_mask. */ @@ -2079,8 +2069,7 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn) rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) rdtgroup_pseudo_lock_remove(rdtgrp); kernfs_unbreak_active_protection(kn); - kernfs_put(rdtgrp->kn); - kfree(rdtgrp); + rdtgroup_remove(rdtgrp); } else { kernfs_unbreak_active_protection(kn); } @@ -2139,13 +2128,11 @@ static int rdt_get_tree(struct fs_context *fc) &kn_mongrp); if (ret < 0) goto out_info; - kernfs_get(kn_mongrp); ret = mkdir_mondata_all(rdtgroup_default.kn, &rdtgroup_default, &kn_mondata); if (ret < 0) goto out_mongrp; - kernfs_get(kn_mondata); rdtgroup_default.mon.mon_data_kn = kn_mondata; } @@ -2323,22 +2310,18 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to, for_each_process_thread(p, t) { if (!from || is_closid_match(t, from) || is_rmid_match(t, from)) { - t->closid = to->closid; - t->rmid = to->mon.rmid; + WRITE_ONCE(t->closid, to->closid); + WRITE_ONCE(t->rmid, to->mon.rmid); -#ifdef CONFIG_SMP /* - * This is safe on x86 w/o barriers as the ordering - * of writing to task_cpu() and t->on_cpu is - * reverse to the reading here. The detection is - * inaccurate as tasks might move or schedule - * before the smp function call takes place. In - * such a case the function call is pointless, but + * If the task is on a CPU, set the CPU in the mask. + * The detection is inaccurate as tasks might move or + * schedule before the smp function call takes place. + * In such a case the function call is pointless, but * there is no other side effect. */ - if (mask && t->on_cpu) + if (IS_ENABLED(CONFIG_SMP) && mask && task_curr(t)) cpumask_set_cpu(task_cpu(t), mask); -#endif } } read_unlock(&tasklist_lock); @@ -2357,7 +2340,7 @@ static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp) if (atomic_read(&sentry->waitcount) != 0) sentry->flags = RDT_DELETED; else - kfree(sentry); + rdtgroup_remove(sentry); } } @@ -2399,7 +2382,7 @@ static void rmdir_all_sub(void) if (atomic_read(&rdtgrp->waitcount) != 0) rdtgrp->flags = RDT_DELETED; else - kfree(rdtgrp); + rdtgroup_remove(rdtgrp); } /* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */ update_closid_rmid(cpu_online_mask, &rdtgroup_default); @@ -2499,11 +2482,6 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn, 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; @@ -2838,8 +2816,8 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, /* * kernfs_remove() will drop the reference count on "kn" which * will free it. But we still need it to stick around for the - * rdtgroup_kn_unlock(kn} call below. Take one extra reference - * here, which will be dropped inside rdtgroup_kn_unlock(). + * rdtgroup_kn_unlock(kn) call. Take one extra reference here, + * which will be dropped by kernfs_put() in rdtgroup_remove(). */ kernfs_get(kn); @@ -2880,6 +2858,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, out_idfree: free_rmid(rdtgrp->mon.rmid); out_destroy: + kernfs_put(rdtgrp->kn); kernfs_remove(rdtgrp->kn); out_free_rgrp: kfree(rdtgrp); @@ -2892,7 +2871,7 @@ static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp) { kernfs_remove(rgrp->kn); free_rmid(rgrp->mon.rmid); - kfree(rgrp); + rdtgroup_remove(rgrp); } /* @@ -3021,8 +3000,7 @@ static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name, return -EPERM; } -static int rdtgroup_rmdir_mon(struct kernfs_node *kn, struct rdtgroup *rdtgrp, - cpumask_var_t tmpmask) +static int rdtgroup_rmdir_mon(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask) { struct rdtgroup *prdtgrp = rdtgrp->mon.parent; int cpu; @@ -3049,33 +3027,21 @@ static int rdtgroup_rmdir_mon(struct kernfs_node *kn, struct rdtgroup *rdtgrp, 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_ctrl_remove(struct kernfs_node *kn, - struct rdtgroup *rdtgrp) +static int rdtgroup_ctrl_remove(struct rdtgroup *rdtgrp) { rdtgrp->flags = RDT_DELETED; list_del(&rdtgrp->rdtgroup_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) +static int rdtgroup_rmdir_ctrl(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask) { int cpu; @@ -3102,7 +3068,7 @@ static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp, closid_free(rdtgrp->closid); free_rmid(rdtgrp->mon.rmid); - rdtgroup_ctrl_remove(kn, rdtgrp); + rdtgroup_ctrl_remove(rdtgrp); /* * Free all the child monitor group rmids. @@ -3139,13 +3105,13 @@ static int rdtgroup_rmdir(struct kernfs_node *kn) rdtgrp != &rdtgroup_default) { if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { - ret = rdtgroup_ctrl_remove(kn, rdtgrp); + ret = rdtgroup_ctrl_remove(rdtgrp); } else { - ret = rdtgroup_rmdir_ctrl(kn, rdtgrp, tmpmask); + ret = rdtgroup_rmdir_ctrl(rdtgrp, tmpmask); } } else if (rdtgrp->type == RDTMON_GROUP && is_mon_groups(parent_kn, kn->name)) { - ret = rdtgroup_rmdir_mon(kn, rdtgrp, tmpmask); + ret = rdtgroup_rmdir_mon(rdtgrp, tmpmask); } else { ret = -EPERM; } diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 866c9a9bcdee..972ec3bfa9c0 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -40,10 +40,6 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 }, { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 }, { X86_FEATURE_MBA, CPUID_EBX, 6, 0x80000008, 0 }, - { X86_FEATURE_SME, CPUID_EAX, 0, 0x8000001f, 0 }, - { X86_FEATURE_SEV, CPUID_EAX, 1, 0x8000001f, 0 }, - { X86_FEATURE_SEV_ES, CPUID_EAX, 3, 0x8000001f, 0 }, - { X86_FEATURE_SME_COHERENT, CPUID_EAX, 10, 0x8000001f, 0 }, { 0, 0, 0, 0, 0 } }; diff --git a/arch/x86/kernel/cpu/sgx/Makefile b/arch/x86/kernel/cpu/sgx/Makefile new file mode 100644 index 000000000000..91d3dc784a29 --- /dev/null +++ b/arch/x86/kernel/cpu/sgx/Makefile @@ -0,0 +1,5 @@ +obj-y += \ + driver.o \ + encl.o \ + ioctl.o \ + main.o diff --git a/arch/x86/kernel/cpu/sgx/arch.h b/arch/x86/kernel/cpu/sgx/arch.h new file mode 100644 index 000000000000..dd7602c44c72 --- /dev/null +++ b/arch/x86/kernel/cpu/sgx/arch.h @@ -0,0 +1,338 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/** + * Copyright(c) 2016-20 Intel Corporation. + * + * Contains data structures defined by the SGX architecture. Data structures + * defined by the Linux software stack should not be placed here. + */ +#ifndef _ASM_X86_SGX_ARCH_H +#define _ASM_X86_SGX_ARCH_H + +#include <linux/bits.h> +#include <linux/types.h> + +/* The SGX specific CPUID function. */ +#define SGX_CPUID 0x12 +/* EPC enumeration. */ +#define SGX_CPUID_EPC 2 +/* An invalid EPC section, i.e. the end marker. */ +#define SGX_CPUID_EPC_INVALID 0x0 +/* A valid EPC section. */ +#define SGX_CPUID_EPC_SECTION 0x1 +/* The bitmask for the EPC section type. */ +#define SGX_CPUID_EPC_MASK GENMASK(3, 0) + +/** + * enum sgx_return_code - The return code type for ENCLS, ENCLU and ENCLV + * %SGX_NOT_TRACKED: Previous ETRACK's shootdown sequence has not + * been completed yet. + * %SGX_INVALID_EINITTOKEN: EINITTOKEN is invalid and enclave signer's + * public key does not match IA32_SGXLEPUBKEYHASH. + * %SGX_UNMASKED_EVENT: An unmasked event, e.g. INTR, was received + */ +enum sgx_return_code { + SGX_NOT_TRACKED = 11, + SGX_INVALID_EINITTOKEN = 16, + SGX_UNMASKED_EVENT = 128, +}; + +/* The modulus size for 3072-bit RSA keys. */ +#define SGX_MODULUS_SIZE 384 + +/** + * enum sgx_miscselect - additional information to an SSA frame + * %SGX_MISC_EXINFO: Report #PF or #GP to the SSA frame. + * + * Save State Area (SSA) is a stack inside the enclave used to store processor + * state when an exception or interrupt occurs. This enum defines additional + * information stored to an SSA frame. + */ +enum sgx_miscselect { + SGX_MISC_EXINFO = BIT(0), +}; + +#define SGX_MISC_RESERVED_MASK GENMASK_ULL(63, 1) + +#define SGX_SSA_GPRS_SIZE 184 +#define SGX_SSA_MISC_EXINFO_SIZE 16 + +/** + * enum sgx_attributes - the attributes field in &struct sgx_secs + * %SGX_ATTR_INIT: Enclave can be entered (is initialized). + * %SGX_ATTR_DEBUG: Allow ENCLS(EDBGRD) and ENCLS(EDBGWR). + * %SGX_ATTR_MODE64BIT: Tell that this a 64-bit enclave. + * %SGX_ATTR_PROVISIONKEY: Allow to use provisioning keys for remote + * attestation. + * %SGX_ATTR_KSS: Allow to use key separation and sharing (KSS). + * %SGX_ATTR_EINITTOKENKEY: Allow to use token signing key that is used to + * sign cryptographic tokens that can be passed to + * EINIT as an authorization to run an enclave. + */ +enum sgx_attribute { + SGX_ATTR_INIT = BIT(0), + SGX_ATTR_DEBUG = BIT(1), + SGX_ATTR_MODE64BIT = BIT(2), + SGX_ATTR_PROVISIONKEY = BIT(4), + SGX_ATTR_EINITTOKENKEY = BIT(5), + SGX_ATTR_KSS = BIT(7), +}; + +#define SGX_ATTR_RESERVED_MASK (BIT_ULL(3) | BIT_ULL(6) | GENMASK_ULL(63, 8)) + +/** + * struct sgx_secs - SGX Enclave Control Structure (SECS) + * @size: size of the address space + * @base: base address of the address space + * @ssa_frame_size: size of an SSA frame + * @miscselect: additional information stored to an SSA frame + * @attributes: attributes for enclave + * @xfrm: XSave-Feature Request Mask (subset of XCR0) + * @mrenclave: SHA256-hash of the enclave contents + * @mrsigner: SHA256-hash of the public key used to sign the SIGSTRUCT + * @config_id: a user-defined value that is used in key derivation + * @isv_prod_id: a user-defined value that is used in key derivation + * @isv_svn: a user-defined value that is used in key derivation + * @config_svn: a user-defined value that is used in key derivation + * + * SGX Enclave Control Structure (SECS) is a special enclave page that is not + * visible in the address space. In fact, this structure defines the address + * range and other global attributes for the enclave and it is the first EPC + * page created for any enclave. It is moved from a temporary buffer to an EPC + * by the means of ENCLS[ECREATE] function. + */ +struct sgx_secs { + u64 size; + u64 base; + u32 ssa_frame_size; + u32 miscselect; + u8 reserved1[24]; + u64 attributes; + u64 xfrm; + u32 mrenclave[8]; + u8 reserved2[32]; + u32 mrsigner[8]; + u8 reserved3[32]; + u32 config_id[16]; + u16 isv_prod_id; + u16 isv_svn; + u16 config_svn; + u8 reserved4[3834]; +} __packed; + +/** + * enum sgx_tcs_flags - execution flags for TCS + * %SGX_TCS_DBGOPTIN: If enabled allows single-stepping and breakpoints + * inside an enclave. It is cleared by EADD but can + * be set later with EDBGWR. + */ +enum sgx_tcs_flags { + SGX_TCS_DBGOPTIN = 0x01, +}; + +#define SGX_TCS_RESERVED_MASK GENMASK_ULL(63, 1) +#define SGX_TCS_RESERVED_SIZE 4024 + +/** + * struct sgx_tcs - Thread Control Structure (TCS) + * @state: used to mark an entered TCS + * @flags: execution flags (cleared by EADD) + * @ssa_offset: SSA stack offset relative to the enclave base + * @ssa_index: the current SSA frame index (cleard by EADD) + * @nr_ssa_frames: the number of frame in the SSA stack + * @entry_offset: entry point offset relative to the enclave base + * @exit_addr: address outside the enclave to exit on an exception or + * interrupt + * @fs_offset: offset relative to the enclave base to become FS + * segment inside the enclave + * @gs_offset: offset relative to the enclave base to become GS + * segment inside the enclave + * @fs_limit: size to become a new FS-limit (only 32-bit enclaves) + * @gs_limit: size to become a new GS-limit (only 32-bit enclaves) + * + * Thread Control Structure (TCS) is an enclave page visible in its address + * space that defines an entry point inside the enclave. A thread enters inside + * an enclave by supplying address of TCS to ENCLU(EENTER). A TCS can be entered + * by only one thread at a time. + */ +struct sgx_tcs { + u64 state; + u64 flags; + u64 ssa_offset; + u32 ssa_index; + u32 nr_ssa_frames; + u64 entry_offset; + u64 exit_addr; + u64 fs_offset; + u64 gs_offset; + u32 fs_limit; + u32 gs_limit; + u8 reserved[SGX_TCS_RESERVED_SIZE]; +} __packed; + +/** + * struct sgx_pageinfo - an enclave page descriptor + * @addr: address of the enclave page + * @contents: pointer to the page contents + * @metadata: pointer either to a SECINFO or PCMD instance + * @secs: address of the SECS page + */ +struct sgx_pageinfo { + u64 addr; + u64 contents; + u64 metadata; + u64 secs; +} __packed __aligned(32); + + +/** + * enum sgx_page_type - bits in the SECINFO flags defining the page type + * %SGX_PAGE_TYPE_SECS: a SECS page + * %SGX_PAGE_TYPE_TCS: a TCS page + * %SGX_PAGE_TYPE_REG: a regular page + * %SGX_PAGE_TYPE_VA: a VA page + * %SGX_PAGE_TYPE_TRIM: a page in trimmed state + */ +enum sgx_page_type { + SGX_PAGE_TYPE_SECS, + SGX_PAGE_TYPE_TCS, + SGX_PAGE_TYPE_REG, + SGX_PAGE_TYPE_VA, + SGX_PAGE_TYPE_TRIM, +}; + +#define SGX_NR_PAGE_TYPES 5 +#define SGX_PAGE_TYPE_MASK GENMASK(7, 0) + +/** + * enum sgx_secinfo_flags - the flags field in &struct sgx_secinfo + * %SGX_SECINFO_R: allow read + * %SGX_SECINFO_W: allow write + * %SGX_SECINFO_X: allow execution + * %SGX_SECINFO_SECS: a SECS page + * %SGX_SECINFO_TCS: a TCS page + * %SGX_SECINFO_REG: a regular page + * %SGX_SECINFO_VA: a VA page + * %SGX_SECINFO_TRIM: a page in trimmed state + */ +enum sgx_secinfo_flags { + SGX_SECINFO_R = BIT(0), + SGX_SECINFO_W = BIT(1), + SGX_SECINFO_X = BIT(2), + SGX_SECINFO_SECS = (SGX_PAGE_TYPE_SECS << 8), + SGX_SECINFO_TCS = (SGX_PAGE_TYPE_TCS << 8), + SGX_SECINFO_REG = (SGX_PAGE_TYPE_REG << 8), + SGX_SECINFO_VA = (SGX_PAGE_TYPE_VA << 8), + SGX_SECINFO_TRIM = (SGX_PAGE_TYPE_TRIM << 8), +}; + +#define SGX_SECINFO_PERMISSION_MASK GENMASK_ULL(2, 0) +#define SGX_SECINFO_PAGE_TYPE_MASK (SGX_PAGE_TYPE_MASK << 8) +#define SGX_SECINFO_RESERVED_MASK ~(SGX_SECINFO_PERMISSION_MASK | \ + SGX_SECINFO_PAGE_TYPE_MASK) + +/** + * struct sgx_secinfo - describes attributes of an EPC page + * @flags: permissions and type + * + * Used together with ENCLS leaves that add or modify an EPC page to an + * enclave to define page permissions and type. + */ +struct sgx_secinfo { + u64 flags; + u8 reserved[56]; +} __packed __aligned(64); + +#define SGX_PCMD_RESERVED_SIZE 40 + +/** + * struct sgx_pcmd - Paging Crypto Metadata (PCMD) + * @enclave_id: enclave identifier + * @mac: MAC over PCMD, page contents and isvsvn + * + * PCMD is stored for every swapped page to the regular memory. When ELDU loads + * the page back it recalculates the MAC by using a isvsvn number stored in a + * VA page. Together these two structures bring integrity and rollback + * protection. + */ +struct sgx_pcmd { + struct sgx_secinfo secinfo; + u64 enclave_id; + u8 reserved[SGX_PCMD_RESERVED_SIZE]; + u8 mac[16]; +} __packed __aligned(128); + +#define SGX_SIGSTRUCT_RESERVED1_SIZE 84 +#define SGX_SIGSTRUCT_RESERVED2_SIZE 20 +#define SGX_SIGSTRUCT_RESERVED3_SIZE 32 +#define SGX_SIGSTRUCT_RESERVED4_SIZE 12 + +/** + * struct sgx_sigstruct_header - defines author of the enclave + * @header1: constant byte string + * @vendor: must be either 0x0000 or 0x8086 + * @date: YYYYMMDD in BCD + * @header2: costant byte string + * @swdefined: software defined value + */ +struct sgx_sigstruct_header { + u64 header1[2]; + u32 vendor; + u32 date; + u64 header2[2]; + u32 swdefined; + u8 reserved1[84]; +} __packed; + +/** + * struct sgx_sigstruct_body - defines contents of the enclave + * @miscselect: additional information stored to an SSA frame + * @misc_mask: required miscselect in SECS + * @attributes: attributes for enclave + * @xfrm: XSave-Feature Request Mask (subset of XCR0) + * @attributes_mask: required attributes in SECS + * @xfrm_mask: required XFRM in SECS + * @mrenclave: SHA256-hash of the enclave contents + * @isvprodid: a user-defined value that is used in key derivation + * @isvsvn: a user-defined value that is used in key derivation + */ +struct sgx_sigstruct_body { + u32 miscselect; + u32 misc_mask; + u8 reserved2[20]; + u64 attributes; + u64 xfrm; + u64 attributes_mask; + u64 xfrm_mask; + u8 mrenclave[32]; + u8 reserved3[32]; + u16 isvprodid; + u16 isvsvn; +} __packed; + +/** + * struct sgx_sigstruct - an enclave signature + * @header: defines author of the enclave + * @modulus: the modulus of the public key + * @exponent: the exponent of the public key + * @signature: the signature calculated over the fields except modulus, + * @body: defines contents of the enclave + * @q1: a value used in RSA signature verification + * @q2: a value used in RSA signature verification + * + * Header and body are the parts that are actual signed. The remaining fields + * define the signature of the enclave. + */ +struct sgx_sigstruct { + struct sgx_sigstruct_header header; + u8 modulus[SGX_MODULUS_SIZE]; + u32 exponent; + u8 signature[SGX_MODULUS_SIZE]; + struct sgx_sigstruct_body body; + u8 reserved4[12]; + u8 q1[SGX_MODULUS_SIZE]; + u8 q2[SGX_MODULUS_SIZE]; +} __packed; + +#define SGX_LAUNCH_TOKEN_SIZE 304 + +#endif /* _ASM_X86_SGX_ARCH_H */ diff --git a/arch/x86/kernel/cpu/sgx/driver.c b/arch/x86/kernel/cpu/sgx/driver.c new file mode 100644 index 000000000000..8ce6d8371cfb --- /dev/null +++ b/arch/x86/kernel/cpu/sgx/driver.c @@ -0,0 +1,197 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2016-20 Intel Corporation. */ + +#include <linux/acpi.h> +#include <linux/miscdevice.h> +#include <linux/mman.h> +#include <linux/security.h> +#include <linux/suspend.h> +#include <asm/traps.h> +#include "driver.h" +#include "encl.h" + +u64 sgx_attributes_reserved_mask; +u64 sgx_xfrm_reserved_mask = ~0x3; +u32 sgx_misc_reserved_mask; + +static int sgx_open(struct inode *inode, struct file *file) +{ + struct sgx_encl *encl; + int ret; + + encl = kzalloc(sizeof(*encl), GFP_KERNEL); + if (!encl) + return -ENOMEM; + + kref_init(&encl->refcount); + xa_init(&encl->page_array); + mutex_init(&encl->lock); + INIT_LIST_HEAD(&encl->va_pages); + INIT_LIST_HEAD(&encl->mm_list); + spin_lock_init(&encl->mm_lock); + + ret = init_srcu_struct(&encl->srcu); + if (ret) { + kfree(encl); + return ret; + } + + file->private_data = encl; + + return 0; +} + +static int sgx_release(struct inode *inode, struct file *file) +{ + struct sgx_encl *encl = file->private_data; + struct sgx_encl_mm *encl_mm; + + /* + * Drain the remaining mm_list entries. At this point the list contains + * entries for processes, which have closed the enclave file but have + * not exited yet. The processes, which have exited, are gone from the + * list by sgx_mmu_notifier_release(). + */ + for ( ; ; ) { + spin_lock(&encl->mm_lock); + + if (list_empty(&encl->mm_list)) { + encl_mm = NULL; + } else { + encl_mm = list_first_entry(&encl->mm_list, + struct sgx_encl_mm, list); + list_del_rcu(&encl_mm->list); + } + + spin_unlock(&encl->mm_lock); + + /* The enclave is no longer mapped by any mm. */ + if (!encl_mm) + break; + + synchronize_srcu(&encl->srcu); + mmu_notifier_unregister(&encl_mm->mmu_notifier, encl_mm->mm); + kfree(encl_mm); + + /* 'encl_mm' is gone, put encl_mm->encl reference: */ + kref_put(&encl->refcount, sgx_encl_release); + } + + kref_put(&encl->refcount, sgx_encl_release); + return 0; +} + +static int sgx_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct sgx_encl *encl = file->private_data; + int ret; + + ret = sgx_encl_may_map(encl, vma->vm_start, vma->vm_end, vma->vm_flags); + if (ret) + return ret; + + ret = sgx_encl_mm_add(encl, vma->vm_mm); + if (ret) + return ret; + + vma->vm_ops = &sgx_vm_ops; + vma->vm_flags |= VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | VM_IO; + vma->vm_private_data = encl; + + return 0; +} + +static unsigned long sgx_get_unmapped_area(struct file *file, + unsigned long addr, + unsigned long len, + unsigned long pgoff, + unsigned long flags) +{ + if ((flags & MAP_TYPE) == MAP_PRIVATE) + return -EINVAL; + + if (flags & MAP_FIXED) + return addr; + + return current->mm->get_unmapped_area(file, addr, len, pgoff, flags); +} + +#ifdef CONFIG_COMPAT +static long sgx_compat_ioctl(struct file *filep, unsigned int cmd, + unsigned long arg) +{ + return sgx_ioctl(filep, cmd, arg); +} +#endif + +static const struct file_operations sgx_encl_fops = { + .owner = THIS_MODULE, + .open = sgx_open, + .release = sgx_release, + .unlocked_ioctl = sgx_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = sgx_compat_ioctl, +#endif + .mmap = sgx_mmap, + .get_unmapped_area = sgx_get_unmapped_area, +}; + +const struct file_operations sgx_provision_fops = { + .owner = THIS_MODULE, +}; + +static struct miscdevice sgx_dev_enclave = { + .minor = MISC_DYNAMIC_MINOR, + .name = "sgx_enclave", + .nodename = "sgx_enclave", + .fops = &sgx_encl_fops, +}; + +static struct miscdevice sgx_dev_provision = { + .minor = MISC_DYNAMIC_MINOR, + .name = "sgx_provision", + .nodename = "sgx_provision", + .fops = &sgx_provision_fops, +}; + +int __init sgx_drv_init(void) +{ + unsigned int eax, ebx, ecx, edx; + u64 attr_mask; + u64 xfrm_mask; + int ret; + + if (!cpu_feature_enabled(X86_FEATURE_SGX_LC)) + return -ENODEV; + + cpuid_count(SGX_CPUID, 0, &eax, &ebx, &ecx, &edx); + + if (!(eax & 1)) { + pr_err("SGX disabled: SGX1 instruction support not available.\n"); + return -ENODEV; + } + + sgx_misc_reserved_mask = ~ebx | SGX_MISC_RESERVED_MASK; + + cpuid_count(SGX_CPUID, 1, &eax, &ebx, &ecx, &edx); + + attr_mask = (((u64)ebx) << 32) + (u64)eax; + sgx_attributes_reserved_mask = ~attr_mask | SGX_ATTR_RESERVED_MASK; + + if (cpu_feature_enabled(X86_FEATURE_OSXSAVE)) { + xfrm_mask = (((u64)edx) << 32) + (u64)ecx; + sgx_xfrm_reserved_mask = ~xfrm_mask; + } + + ret = misc_register(&sgx_dev_enclave); + if (ret) + return ret; + + ret = misc_register(&sgx_dev_provision); + if (ret) { + misc_deregister(&sgx_dev_enclave); + return ret; + } + + return 0; +} diff --git a/arch/x86/kernel/cpu/sgx/driver.h b/arch/x86/kernel/cpu/sgx/driver.h new file mode 100644 index 000000000000..4eddb4d571ef --- /dev/null +++ b/arch/x86/kernel/cpu/sgx/driver.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ARCH_SGX_DRIVER_H__ +#define __ARCH_SGX_DRIVER_H__ + +#include <crypto/hash.h> +#include <linux/kref.h> +#include <linux/mmu_notifier.h> +#include <linux/radix-tree.h> +#include <linux/rwsem.h> +#include <linux/sched.h> +#include <linux/workqueue.h> +#include <uapi/asm/sgx.h> +#include "sgx.h" + +#define SGX_EINIT_SPIN_COUNT 20 +#define SGX_EINIT_SLEEP_COUNT 50 +#define SGX_EINIT_SLEEP_TIME 20 + +extern u64 sgx_attributes_reserved_mask; +extern u64 sgx_xfrm_reserved_mask; +extern u32 sgx_misc_reserved_mask; + +extern const struct file_operations sgx_provision_fops; + +long sgx_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); + +int sgx_drv_init(void); + +#endif /* __ARCH_X86_SGX_DRIVER_H__ */ diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c new file mode 100644 index 000000000000..7449ef33f081 --- /dev/null +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -0,0 +1,737 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2016-20 Intel Corporation. */ + +#include <linux/lockdep.h> +#include <linux/mm.h> +#include <linux/mman.h> +#include <linux/shmem_fs.h> +#include <linux/suspend.h> +#include <linux/sched/mm.h> +#include "arch.h" +#include "encl.h" +#include "encls.h" +#include "sgx.h" + +/* + * ELDU: Load an EPC page as unblocked. For more info, see "OS Management of EPC + * Pages" in the SDM. + */ +static int __sgx_encl_eldu(struct sgx_encl_page *encl_page, + struct sgx_epc_page *epc_page, + struct sgx_epc_page *secs_page) +{ + unsigned long va_offset = encl_page->desc & SGX_ENCL_PAGE_VA_OFFSET_MASK; + struct sgx_encl *encl = encl_page->encl; + struct sgx_pageinfo pginfo; + struct sgx_backing b; + pgoff_t page_index; + int ret; + + if (secs_page) + page_index = PFN_DOWN(encl_page->desc - encl_page->encl->base); + else + page_index = PFN_DOWN(encl->size); + + ret = sgx_encl_get_backing(encl, page_index, &b); + if (ret) + return ret; + + pginfo.addr = encl_page->desc & PAGE_MASK; + pginfo.contents = (unsigned long)kmap_atomic(b.contents); + pginfo.metadata = (unsigned long)kmap_atomic(b.pcmd) + + b.pcmd_offset; + + if (secs_page) + pginfo.secs = (u64)sgx_get_epc_virt_addr(secs_page); + else + pginfo.secs = 0; + + ret = __eldu(&pginfo, sgx_get_epc_virt_addr(epc_page), + sgx_get_epc_virt_addr(encl_page->va_page->epc_page) + va_offset); + if (ret) { + if (encls_failed(ret)) + ENCLS_WARN(ret, "ELDU"); + + ret = -EFAULT; + } + + kunmap_atomic((void *)(unsigned long)(pginfo.metadata - b.pcmd_offset)); + kunmap_atomic((void *)(unsigned long)pginfo.contents); + + sgx_encl_put_backing(&b, false); + + return ret; +} + +static struct sgx_epc_page *sgx_encl_eldu(struct sgx_encl_page *encl_page, + struct sgx_epc_page *secs_page) +{ + + unsigned long va_offset = encl_page->desc & SGX_ENCL_PAGE_VA_OFFSET_MASK; + struct sgx_encl *encl = encl_page->encl; + struct sgx_epc_page *epc_page; + int ret; + + epc_page = sgx_alloc_epc_page(encl_page, false); + if (IS_ERR(epc_page)) + return epc_page; + + ret = __sgx_encl_eldu(encl_page, epc_page, secs_page); + if (ret) { + sgx_free_epc_page(epc_page); + return ERR_PTR(ret); + } + + sgx_free_va_slot(encl_page->va_page, va_offset); + list_move(&encl_page->va_page->list, &encl->va_pages); + encl_page->desc &= ~SGX_ENCL_PAGE_VA_OFFSET_MASK; + encl_page->epc_page = epc_page; + + return epc_page; +} + +static struct sgx_encl_page *sgx_encl_load_page(struct sgx_encl *encl, + unsigned long addr, + unsigned long vm_flags) +{ + unsigned long vm_prot_bits = vm_flags & (VM_READ | VM_WRITE | VM_EXEC); + struct sgx_epc_page *epc_page; + struct sgx_encl_page *entry; + + entry = xa_load(&encl->page_array, PFN_DOWN(addr)); + if (!entry) + return ERR_PTR(-EFAULT); + + /* + * Verify that the faulted page has equal or higher build time + * permissions than the VMA permissions (i.e. the subset of {VM_READ, + * VM_WRITE, VM_EXECUTE} in vma->vm_flags). + */ + if ((entry->vm_max_prot_bits & vm_prot_bits) != vm_prot_bits) + return ERR_PTR(-EFAULT); + + /* Entry successfully located. */ + if (entry->epc_page) { + if (entry->desc & SGX_ENCL_PAGE_BEING_RECLAIMED) + return ERR_PTR(-EBUSY); + + return entry; + } + + if (!(encl->secs.epc_page)) { + epc_page = sgx_encl_eldu(&encl->secs, NULL); + if (IS_ERR(epc_page)) + return ERR_CAST(epc_page); + } + + epc_page = sgx_encl_eldu(entry, encl->secs.epc_page); + if (IS_ERR(epc_page)) + return ERR_CAST(epc_page); + + encl->secs_child_cnt++; + sgx_mark_page_reclaimable(entry->epc_page); + + return entry; +} + +static vm_fault_t sgx_vma_fault(struct vm_fault *vmf) +{ + unsigned long addr = (unsigned long)vmf->address; + struct vm_area_struct *vma = vmf->vma; + struct sgx_encl_page *entry; + unsigned long phys_addr; + struct sgx_encl *encl; + vm_fault_t ret; + + encl = vma->vm_private_data; + + /* + * It's very unlikely but possible that allocating memory for the + * mm_list entry of a forked process failed in sgx_vma_open(). When + * this happens, vm_private_data is set to NULL. + */ + if (unlikely(!encl)) + return VM_FAULT_SIGBUS; + + mutex_lock(&encl->lock); + + entry = sgx_encl_load_page(encl, addr, vma->vm_flags); + if (IS_ERR(entry)) { + mutex_unlock(&encl->lock); + + if (PTR_ERR(entry) == -EBUSY) + return VM_FAULT_NOPAGE; + + return VM_FAULT_SIGBUS; + } + + phys_addr = sgx_get_epc_phys_addr(entry->epc_page); + + ret = vmf_insert_pfn(vma, addr, PFN_DOWN(phys_addr)); + if (ret != VM_FAULT_NOPAGE) { + mutex_unlock(&encl->lock); + + return VM_FAULT_SIGBUS; + } + + sgx_encl_test_and_clear_young(vma->vm_mm, entry); + mutex_unlock(&encl->lock); + + return VM_FAULT_NOPAGE; +} + +static void sgx_vma_open(struct vm_area_struct *vma) +{ + struct sgx_encl *encl = vma->vm_private_data; + + /* + * It's possible but unlikely that vm_private_data is NULL. This can + * happen in a grandchild of a process, when sgx_encl_mm_add() had + * failed to allocate memory in this callback. + */ + if (unlikely(!encl)) + return; + + if (sgx_encl_mm_add(encl, vma->vm_mm)) + vma->vm_private_data = NULL; +} + + +/** + * sgx_encl_may_map() - Check if a requested VMA mapping is allowed + * @encl: an enclave pointer + * @start: lower bound of the address range, inclusive + * @end: upper bound of the address range, exclusive + * @vm_flags: VMA flags + * + * Iterate through the enclave pages contained within [@start, @end) to verify + * that the permissions requested by a subset of {VM_READ, VM_WRITE, VM_EXEC} + * do not contain any permissions that are not contained in the build time + * permissions of any of the enclave pages within the given address range. + * + * An enclave creator must declare the strongest permissions that will be + * needed for each enclave page. This ensures that mappings have the identical + * or weaker permissions than the earlier declared permissions. + * + * Return: 0 on success, -EACCES otherwise + */ +int sgx_encl_may_map(struct sgx_encl *encl, unsigned long start, + unsigned long end, unsigned long vm_flags) +{ + unsigned long vm_prot_bits = vm_flags & (VM_READ | VM_WRITE | VM_EXEC); + struct sgx_encl_page *page; + unsigned long count = 0; + int ret = 0; + + XA_STATE(xas, &encl->page_array, PFN_DOWN(start)); + + /* + * Disallow READ_IMPLIES_EXEC tasks as their VMA permissions might + * conflict with the enclave page permissions. + */ + if (current->personality & READ_IMPLIES_EXEC) + return -EACCES; + + mutex_lock(&encl->lock); + xas_lock(&xas); + xas_for_each(&xas, page, PFN_DOWN(end - 1)) { + if (~page->vm_max_prot_bits & vm_prot_bits) { + ret = -EACCES; + break; + } + + /* Reschedule on every XA_CHECK_SCHED iteration. */ + if (!(++count % XA_CHECK_SCHED)) { + xas_pause(&xas); + xas_unlock(&xas); + mutex_unlock(&encl->lock); + + cond_resched(); + + mutex_lock(&encl->lock); + xas_lock(&xas); + } + } + xas_unlock(&xas); + mutex_unlock(&encl->lock); + + return ret; +} + +static int sgx_vma_mprotect(struct vm_area_struct *vma, unsigned long start, + unsigned long end, unsigned long newflags) +{ + return sgx_encl_may_map(vma->vm_private_data, start, end, newflags); +} + +static int sgx_encl_debug_read(struct sgx_encl *encl, struct sgx_encl_page *page, + unsigned long addr, void *data) +{ + unsigned long offset = addr & ~PAGE_MASK; + int ret; + + + ret = __edbgrd(sgx_get_epc_virt_addr(page->epc_page) + offset, data); + if (ret) + return -EIO; + + return 0; +} + +static int sgx_encl_debug_write(struct sgx_encl *encl, struct sgx_encl_page *page, + unsigned long addr, void *data) +{ + unsigned long offset = addr & ~PAGE_MASK; + int ret; + + ret = __edbgwr(sgx_get_epc_virt_addr(page->epc_page) + offset, data); + if (ret) + return -EIO; + + return 0; +} + +/* + * Load an enclave page to EPC if required, and take encl->lock. + */ +static struct sgx_encl_page *sgx_encl_reserve_page(struct sgx_encl *encl, + unsigned long addr, + unsigned long vm_flags) +{ + struct sgx_encl_page *entry; + + for ( ; ; ) { + mutex_lock(&encl->lock); + + entry = sgx_encl_load_page(encl, addr, vm_flags); + if (PTR_ERR(entry) != -EBUSY) + break; + + mutex_unlock(&encl->lock); + } + + if (IS_ERR(entry)) + mutex_unlock(&encl->lock); + + return entry; +} + +static int sgx_vma_access(struct vm_area_struct *vma, unsigned long addr, + void *buf, int len, int write) +{ + struct sgx_encl *encl = vma->vm_private_data; + struct sgx_encl_page *entry = NULL; + char data[sizeof(unsigned long)]; + unsigned long align; + int offset; + int cnt; + int ret = 0; + int i; + + /* + * If process was forked, VMA is still there but vm_private_data is set + * to NULL. + */ + if (!encl) + return -EFAULT; + + if (!test_bit(SGX_ENCL_DEBUG, &encl->flags)) + return -EFAULT; + + for (i = 0; i < len; i += cnt) { + entry = sgx_encl_reserve_page(encl, (addr + i) & PAGE_MASK, + vma->vm_flags); + if (IS_ERR(entry)) { + ret = PTR_ERR(entry); + break; + } + + align = ALIGN_DOWN(addr + i, sizeof(unsigned long)); + offset = (addr + i) & (sizeof(unsigned long) - 1); + cnt = sizeof(unsigned long) - offset; + cnt = min(cnt, len - i); + + ret = sgx_encl_debug_read(encl, entry, align, data); + if (ret) + goto out; + + if (write) { + memcpy(data + offset, buf + i, cnt); + ret = sgx_encl_debug_write(encl, entry, align, data); + if (ret) + goto out; + } else { + memcpy(buf + i, data + offset, cnt); + } + +out: + mutex_unlock(&encl->lock); + + if (ret) + break; + } + + return ret < 0 ? ret : i; +} + +const struct vm_operations_struct sgx_vm_ops = { + .fault = sgx_vma_fault, + .mprotect = sgx_vma_mprotect, + .open = sgx_vma_open, + .access = sgx_vma_access, +}; + +/** + * sgx_encl_release - Destroy an enclave instance + * @kref: address of a kref inside &sgx_encl + * + * Used together with kref_put(). Frees all the resources associated with the + * enclave and the instance itself. + */ +void sgx_encl_release(struct kref *ref) +{ + struct sgx_encl *encl = container_of(ref, struct sgx_encl, refcount); + struct sgx_va_page *va_page; + struct sgx_encl_page *entry; + unsigned long index; + + xa_for_each(&encl->page_array, index, entry) { + if (entry->epc_page) { + /* + * The page and its radix tree entry cannot be freed + * if the page is being held by the reclaimer. + */ + if (sgx_unmark_page_reclaimable(entry->epc_page)) + continue; + + sgx_free_epc_page(entry->epc_page); + encl->secs_child_cnt--; + entry->epc_page = NULL; + } + + kfree(entry); + } + + xa_destroy(&encl->page_array); + + if (!encl->secs_child_cnt && encl->secs.epc_page) { + sgx_free_epc_page(encl->secs.epc_page); + encl->secs.epc_page = NULL; + } + + while (!list_empty(&encl->va_pages)) { + va_page = list_first_entry(&encl->va_pages, struct sgx_va_page, + list); + list_del(&va_page->list); + sgx_free_epc_page(va_page->epc_page); + kfree(va_page); + } + + if (encl->backing) + fput(encl->backing); + + cleanup_srcu_struct(&encl->srcu); + + WARN_ON_ONCE(!list_empty(&encl->mm_list)); + + /* Detect EPC page leak's. */ + WARN_ON_ONCE(encl->secs_child_cnt); + WARN_ON_ONCE(encl->secs.epc_page); + + kfree(encl); +} + +/* + * 'mm' is exiting and no longer needs mmu notifications. + */ +static void sgx_mmu_notifier_release(struct mmu_notifier *mn, + struct mm_struct *mm) +{ + struct sgx_encl_mm *encl_mm = container_of(mn, struct sgx_encl_mm, mmu_notifier); + struct sgx_encl_mm *tmp = NULL; + + /* + * The enclave itself can remove encl_mm. Note, objects can't be moved + * off an RCU protected list, but deletion is ok. + */ + spin_lock(&encl_mm->encl->mm_lock); + list_for_each_entry(tmp, &encl_mm->encl->mm_list, list) { + if (tmp == encl_mm) { + list_del_rcu(&encl_mm->list); + break; + } + } + spin_unlock(&encl_mm->encl->mm_lock); + + if (tmp == encl_mm) { + synchronize_srcu(&encl_mm->encl->srcu); + mmu_notifier_put(mn); + } +} + +static void sgx_mmu_notifier_free(struct mmu_notifier *mn) +{ + struct sgx_encl_mm *encl_mm = container_of(mn, struct sgx_encl_mm, mmu_notifier); + + /* 'encl_mm' is going away, put encl_mm->encl reference: */ + kref_put(&encl_mm->encl->refcount, sgx_encl_release); + + kfree(encl_mm); +} + +static const struct mmu_notifier_ops sgx_mmu_notifier_ops = { + .release = sgx_mmu_notifier_release, + .free_notifier = sgx_mmu_notifier_free, +}; + +static struct sgx_encl_mm *sgx_encl_find_mm(struct sgx_encl *encl, + struct mm_struct *mm) +{ + struct sgx_encl_mm *encl_mm = NULL; + struct sgx_encl_mm *tmp; + int idx; + + idx = srcu_read_lock(&encl->srcu); + + list_for_each_entry_rcu(tmp, &encl->mm_list, list) { + if (tmp->mm == mm) { + encl_mm = tmp; + break; + } + } + + srcu_read_unlock(&encl->srcu, idx); + + return encl_mm; +} + +int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm) +{ + struct sgx_encl_mm *encl_mm; + int ret; + + /* + * Even though a single enclave may be mapped into an mm more than once, + * each 'mm' only appears once on encl->mm_list. This is guaranteed by + * holding the mm's mmap lock for write before an mm can be added or + * remove to an encl->mm_list. + */ + mmap_assert_write_locked(mm); + + /* + * It's possible that an entry already exists in the mm_list, because it + * is removed only on VFS release or process exit. + */ + if (sgx_encl_find_mm(encl, mm)) + return 0; + + encl_mm = kzalloc(sizeof(*encl_mm), GFP_KERNEL); + if (!encl_mm) + return -ENOMEM; + + /* Grab a refcount for the encl_mm->encl reference: */ + kref_get(&encl->refcount); + encl_mm->encl = encl; + encl_mm->mm = mm; + encl_mm->mmu_notifier.ops = &sgx_mmu_notifier_ops; + + ret = __mmu_notifier_register(&encl_mm->mmu_notifier, mm); + if (ret) { + kfree(encl_mm); + return ret; + } + + spin_lock(&encl->mm_lock); + list_add_rcu(&encl_mm->list, &encl->mm_list); + /* Pairs with smp_rmb() in sgx_reclaimer_block(). */ + smp_wmb(); + encl->mm_list_version++; + spin_unlock(&encl->mm_lock); + + return 0; +} + +static struct page *sgx_encl_get_backing_page(struct sgx_encl *encl, + pgoff_t index) +{ + struct inode *inode = encl->backing->f_path.dentry->d_inode; + struct address_space *mapping = inode->i_mapping; + gfp_t gfpmask = mapping_gfp_mask(mapping); + + return shmem_read_mapping_page_gfp(mapping, index, gfpmask); +} + +/** + * sgx_encl_get_backing() - Pin the backing storage + * @encl: an enclave pointer + * @page_index: enclave page index + * @backing: data for accessing backing storage for the page + * + * Pin the backing storage pages for storing the encrypted contents and Paging + * Crypto MetaData (PCMD) of an enclave page. + * + * Return: + * 0 on success, + * -errno otherwise. + */ +int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, + struct sgx_backing *backing) +{ + pgoff_t pcmd_index = PFN_DOWN(encl->size) + 1 + (page_index >> 5); + struct page *contents; + struct page *pcmd; + + contents = sgx_encl_get_backing_page(encl, page_index); + if (IS_ERR(contents)) + return PTR_ERR(contents); + + pcmd = sgx_encl_get_backing_page(encl, pcmd_index); + if (IS_ERR(pcmd)) { + put_page(contents); + return PTR_ERR(pcmd); + } + + backing->page_index = page_index; + backing->contents = contents; + backing->pcmd = pcmd; + backing->pcmd_offset = + (page_index & (PAGE_SIZE / sizeof(struct sgx_pcmd) - 1)) * + sizeof(struct sgx_pcmd); + + return 0; +} + +/** + * sgx_encl_put_backing() - Unpin the backing storage + * @backing: data for accessing backing storage for the page + * @do_write: mark pages dirty + */ +void sgx_encl_put_backing(struct sgx_backing *backing, bool do_write) +{ + if (do_write) { + set_page_dirty(backing->pcmd); + set_page_dirty(backing->contents); + } + + put_page(backing->pcmd); + put_page(backing->contents); +} + +static int sgx_encl_test_and_clear_young_cb(pte_t *ptep, unsigned long addr, + void *data) +{ + pte_t pte; + int ret; + + ret = pte_young(*ptep); + if (ret) { + pte = pte_mkold(*ptep); + set_pte_at((struct mm_struct *)data, addr, ptep, pte); + } + + return ret; +} + +/** + * sgx_encl_test_and_clear_young() - Test and reset the accessed bit + * @mm: mm_struct that is checked + * @page: enclave page to be tested for recent access + * + * Checks the Access (A) bit from the PTE corresponding to the enclave page and + * clears it. + * + * Return: 1 if the page has been recently accessed and 0 if not. + */ +int sgx_encl_test_and_clear_young(struct mm_struct *mm, + struct sgx_encl_page *page) +{ + unsigned long addr = page->desc & PAGE_MASK; + struct sgx_encl *encl = page->encl; + struct vm_area_struct *vma; + int ret; + + ret = sgx_encl_find(mm, addr, &vma); + if (ret) + return 0; + + if (encl != vma->vm_private_data) + return 0; + + ret = apply_to_page_range(vma->vm_mm, addr, PAGE_SIZE, + sgx_encl_test_and_clear_young_cb, vma->vm_mm); + if (ret < 0) + return 0; + + return ret; +} + +/** + * sgx_alloc_va_page() - Allocate a Version Array (VA) page + * + * Allocate a free EPC page and convert it to a Version Array (VA) page. + * + * Return: + * a VA page, + * -errno otherwise + */ +struct sgx_epc_page *sgx_alloc_va_page(void) +{ + struct sgx_epc_page *epc_page; + int ret; + + epc_page = sgx_alloc_epc_page(NULL, true); + if (IS_ERR(epc_page)) + return ERR_CAST(epc_page); + + ret = __epa(sgx_get_epc_virt_addr(epc_page)); + if (ret) { + WARN_ONCE(1, "EPA returned %d (0x%x)", ret, ret); + sgx_free_epc_page(epc_page); + return ERR_PTR(-EFAULT); + } + + return epc_page; +} + +/** + * sgx_alloc_va_slot - allocate a VA slot + * @va_page: a &struct sgx_va_page instance + * + * Allocates a slot from a &struct sgx_va_page instance. + * + * Return: offset of the slot inside the VA page + */ +unsigned int sgx_alloc_va_slot(struct sgx_va_page *va_page) +{ + int slot = find_first_zero_bit(va_page->slots, SGX_VA_SLOT_COUNT); + + if (slot < SGX_VA_SLOT_COUNT) + set_bit(slot, va_page->slots); + + return slot << 3; +} + +/** + * sgx_free_va_slot - free a VA slot + * @va_page: a &struct sgx_va_page instance + * @offset: offset of the slot inside the VA page + * + * Frees a slot from a &struct sgx_va_page instance. + */ +void sgx_free_va_slot(struct sgx_va_page *va_page, unsigned int offset) +{ + clear_bit(offset >> 3, va_page->slots); +} + +/** + * sgx_va_page_full - is the VA page full? + * @va_page: a &struct sgx_va_page instance + * + * Return: true if all slots have been taken + */ +bool sgx_va_page_full(struct sgx_va_page *va_page) +{ + int slot = find_first_zero_bit(va_page->slots, SGX_VA_SLOT_COUNT); + + return slot == SGX_VA_SLOT_COUNT; +} diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h new file mode 100644 index 000000000000..d8d30ccbef4c --- /dev/null +++ b/arch/x86/kernel/cpu/sgx/encl.h @@ -0,0 +1,119 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/** + * Copyright(c) 2016-20 Intel Corporation. + * + * Contains the software defined data structures for enclaves. + */ +#ifndef _X86_ENCL_H +#define _X86_ENCL_H + +#include <linux/cpumask.h> +#include <linux/kref.h> +#include <linux/list.h> +#include <linux/mm_types.h> +#include <linux/mmu_notifier.h> +#include <linux/mutex.h> +#include <linux/notifier.h> +#include <linux/srcu.h> +#include <linux/workqueue.h> +#include <linux/xarray.h> +#include "sgx.h" + +/* 'desc' bits holding the offset in the VA (version array) page. */ +#define SGX_ENCL_PAGE_VA_OFFSET_MASK GENMASK_ULL(11, 3) + +/* 'desc' bit marking that the page is being reclaimed. */ +#define SGX_ENCL_PAGE_BEING_RECLAIMED BIT(3) + +struct sgx_encl_page { + unsigned long desc; + unsigned long vm_max_prot_bits; + struct sgx_epc_page *epc_page; + struct sgx_encl *encl; + struct sgx_va_page *va_page; +}; + +enum sgx_encl_flags { + SGX_ENCL_IOCTL = BIT(0), + SGX_ENCL_DEBUG = BIT(1), + SGX_ENCL_CREATED = BIT(2), + SGX_ENCL_INITIALIZED = BIT(3), +}; + +struct sgx_encl_mm { + struct sgx_encl *encl; + struct mm_struct *mm; + struct list_head list; + struct mmu_notifier mmu_notifier; +}; + +struct sgx_encl { + unsigned long base; + unsigned long size; + unsigned long flags; + unsigned int page_cnt; + unsigned int secs_child_cnt; + struct mutex lock; + struct xarray page_array; + struct sgx_encl_page secs; + unsigned long attributes; + unsigned long attributes_mask; + + cpumask_t cpumask; + struct file *backing; + struct kref refcount; + struct list_head va_pages; + unsigned long mm_list_version; + struct list_head mm_list; + spinlock_t mm_lock; + struct srcu_struct srcu; +}; + +#define SGX_VA_SLOT_COUNT 512 + +struct sgx_va_page { + struct sgx_epc_page *epc_page; + DECLARE_BITMAP(slots, SGX_VA_SLOT_COUNT); + struct list_head list; +}; + +struct sgx_backing { + pgoff_t page_index; + struct page *contents; + struct page *pcmd; + unsigned long pcmd_offset; +}; + +extern const struct vm_operations_struct sgx_vm_ops; + +static inline int sgx_encl_find(struct mm_struct *mm, unsigned long addr, + struct vm_area_struct **vma) +{ + struct vm_area_struct *result; + + result = find_vma(mm, addr); + if (!result || result->vm_ops != &sgx_vm_ops || addr < result->vm_start) + return -EINVAL; + + *vma = result; + + return 0; +} + +int sgx_encl_may_map(struct sgx_encl *encl, unsigned long start, + unsigned long end, unsigned long vm_flags); + +void sgx_encl_release(struct kref *ref); +int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm); +int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, + struct sgx_backing *backing); +void sgx_encl_put_backing(struct sgx_backing *backing, bool do_write); +int sgx_encl_test_and_clear_young(struct mm_struct *mm, + struct sgx_encl_page *page); + +struct sgx_epc_page *sgx_alloc_va_page(void); +unsigned int sgx_alloc_va_slot(struct sgx_va_page *va_page); +void sgx_free_va_slot(struct sgx_va_page *va_page, unsigned int offset); +bool sgx_va_page_full(struct sgx_va_page *va_page); + +#endif /* _X86_ENCL_H */ diff --git a/arch/x86/kernel/cpu/sgx/encls.h b/arch/x86/kernel/cpu/sgx/encls.h new file mode 100644 index 000000000000..443188fe7e70 --- /dev/null +++ b/arch/x86/kernel/cpu/sgx/encls.h @@ -0,0 +1,231 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _X86_ENCLS_H +#define _X86_ENCLS_H + +#include <linux/bitops.h> +#include <linux/err.h> +#include <linux/io.h> +#include <linux/rwsem.h> +#include <linux/types.h> +#include <asm/asm.h> +#include <asm/traps.h> +#include "sgx.h" + +enum sgx_encls_function { + ECREATE = 0x00, + EADD = 0x01, + EINIT = 0x02, + EREMOVE = 0x03, + EDGBRD = 0x04, + EDGBWR = 0x05, + EEXTEND = 0x06, + ELDU = 0x08, + EBLOCK = 0x09, + EPA = 0x0A, + EWB = 0x0B, + ETRACK = 0x0C, +}; + +/** + * ENCLS_FAULT_FLAG - flag signifying an ENCLS return code is a trapnr + * + * ENCLS has its own (positive value) error codes and also generates + * ENCLS specific #GP and #PF faults. And the ENCLS values get munged + * with system error codes as everything percolates back up the stack. + * Unfortunately (for us), we need to precisely identify each unique + * error code, e.g. the action taken if EWB fails varies based on the + * type of fault and on the exact SGX error code, i.e. we can't simply + * convert all faults to -EFAULT. + * + * To make all three error types coexist, we set bit 30 to identify an + * ENCLS fault. Bit 31 (technically bits N:31) is used to differentiate + * between positive (faults and SGX error codes) and negative (system + * error codes) values. + */ +#define ENCLS_FAULT_FLAG 0x40000000 + +/* Retrieve the encoded trapnr from the specified return code. */ +#define ENCLS_TRAPNR(r) ((r) & ~ENCLS_FAULT_FLAG) + +/* Issue a WARN() about an ENCLS function. */ +#define ENCLS_WARN(r, name) { \ + do { \ + int _r = (r); \ + WARN_ONCE(_r, "%s returned %d (0x%x)\n", (name), _r, _r); \ + } while (0); \ +} + +/** + * encls_failed() - Check if an ENCLS function failed + * @ret: the return value of an ENCLS function call + * + * Check if an ENCLS function failed. This happens when the function causes a + * fault that is not caused by an EPCM conflict or when the function returns a + * non-zero value. + */ +static inline bool encls_failed(int ret) +{ + if (ret & ENCLS_FAULT_FLAG) + return ENCLS_TRAPNR(ret) != X86_TRAP_PF; + + return !!ret; +} + +/** + * __encls_ret_N - encode an ENCLS function that returns an error code in EAX + * @rax: function number + * @inputs: asm inputs for the function + * + * Emit assembly for an ENCLS function that returns an error code, e.g. EREMOVE. + * And because SGX isn't complex enough as it is, function that return an error + * code also modify flags. + * + * Return: + * 0 on success, + * SGX error code on failure + */ +#define __encls_ret_N(rax, inputs...) \ + ({ \ + int ret; \ + asm volatile( \ + "1: .byte 0x0f, 0x01, 0xcf;\n\t" \ + "2:\n" \ + ".section .fixup,\"ax\"\n" \ + "3: orl $"__stringify(ENCLS_FAULT_FLAG)",%%eax\n" \ + " jmp 2b\n" \ + ".previous\n" \ + _ASM_EXTABLE_FAULT(1b, 3b) \ + : "=a"(ret) \ + : "a"(rax), inputs \ + : "memory", "cc"); \ + ret; \ + }) + +#define __encls_ret_1(rax, rcx) \ + ({ \ + __encls_ret_N(rax, "c"(rcx)); \ + }) + +#define __encls_ret_2(rax, rbx, rcx) \ + ({ \ + __encls_ret_N(rax, "b"(rbx), "c"(rcx)); \ + }) + +#define __encls_ret_3(rax, rbx, rcx, rdx) \ + ({ \ + __encls_ret_N(rax, "b"(rbx), "c"(rcx), "d"(rdx)); \ + }) + +/** + * __encls_N - encode an ENCLS function that doesn't return an error code + * @rax: function number + * @rbx_out: optional output variable + * @inputs: asm inputs for the function + * + * Emit assembly for an ENCLS function that does not return an error code, e.g. + * ECREATE. Leaves without error codes either succeed or fault. @rbx_out is an + * optional parameter for use by EDGBRD, which returns the requested value in + * RBX. + * + * Return: + * 0 on success, + * trapnr with ENCLS_FAULT_FLAG set on fault + */ +#define __encls_N(rax, rbx_out, inputs...) \ + ({ \ + int ret; \ + asm volatile( \ + "1: .byte 0x0f, 0x01, 0xcf;\n\t" \ + " xor %%eax,%%eax;\n" \ + "2:\n" \ + ".section .fixup,\"ax\"\n" \ + "3: orl $"__stringify(ENCLS_FAULT_FLAG)",%%eax\n" \ + " jmp 2b\n" \ + ".previous\n" \ + _ASM_EXTABLE_FAULT(1b, 3b) \ + : "=a"(ret), "=b"(rbx_out) \ + : "a"(rax), inputs \ + : "memory"); \ + ret; \ + }) + +#define __encls_2(rax, rbx, rcx) \ + ({ \ + unsigned long ign_rbx_out; \ + __encls_N(rax, ign_rbx_out, "b"(rbx), "c"(rcx)); \ + }) + +#define __encls_1_1(rax, data, rcx) \ + ({ \ + unsigned long rbx_out; \ + int ret = __encls_N(rax, rbx_out, "c"(rcx)); \ + if (!ret) \ + data = rbx_out; \ + ret; \ + }) + +static inline int __ecreate(struct sgx_pageinfo *pginfo, void *secs) +{ + return __encls_2(ECREATE, pginfo, secs); +} + +static inline int __eextend(void *secs, void *addr) +{ + return __encls_2(EEXTEND, secs, addr); +} + +static inline int __eadd(struct sgx_pageinfo *pginfo, void *addr) +{ + return __encls_2(EADD, pginfo, addr); +} + +static inline int __einit(void *sigstruct, void *token, void *secs) +{ + return __encls_ret_3(EINIT, sigstruct, secs, token); +} + +static inline int __eremove(void *addr) +{ + return __encls_ret_1(EREMOVE, addr); +} + +static inline int __edbgwr(void *addr, unsigned long *data) +{ + return __encls_2(EDGBWR, *data, addr); +} + +static inline int __edbgrd(void *addr, unsigned long *data) +{ + return __encls_1_1(EDGBRD, *data, addr); +} + +static inline int __etrack(void *addr) +{ + return __encls_ret_1(ETRACK, addr); +} + +static inline int __eldu(struct sgx_pageinfo *pginfo, void *addr, + void *va) +{ + return __encls_ret_3(ELDU, pginfo, addr, va); +} + +static inline int __eblock(void *addr) +{ + return __encls_ret_1(EBLOCK, addr); +} + +static inline int __epa(void *addr) +{ + unsigned long rbx = SGX_PAGE_TYPE_VA; + + return __encls_2(EPA, rbx, addr); +} + +static inline int __ewb(struct sgx_pageinfo *pginfo, void *addr, + void *va) +{ + return __encls_ret_3(EWB, pginfo, addr, va); +} + +#endif /* _X86_ENCLS_H */ diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c new file mode 100644 index 000000000000..90a5caf76939 --- /dev/null +++ b/arch/x86/kernel/cpu/sgx/ioctl.c @@ -0,0 +1,716 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2016-20 Intel Corporation. */ + +#include <asm/mman.h> +#include <linux/mman.h> +#include <linux/delay.h> +#include <linux/file.h> +#include <linux/hashtable.h> +#include <linux/highmem.h> +#include <linux/ratelimit.h> +#include <linux/sched/signal.h> +#include <linux/shmem_fs.h> +#include <linux/slab.h> +#include <linux/suspend.h> +#include "driver.h" +#include "encl.h" +#include "encls.h" + +static struct sgx_va_page *sgx_encl_grow(struct sgx_encl *encl) +{ + struct sgx_va_page *va_page = NULL; + void *err; + + BUILD_BUG_ON(SGX_VA_SLOT_COUNT != + (SGX_ENCL_PAGE_VA_OFFSET_MASK >> 3) + 1); + + if (!(encl->page_cnt % SGX_VA_SLOT_COUNT)) { + va_page = kzalloc(sizeof(*va_page), GFP_KERNEL); + if (!va_page) + return ERR_PTR(-ENOMEM); + + va_page->epc_page = sgx_alloc_va_page(); + if (IS_ERR(va_page->epc_page)) { + err = ERR_CAST(va_page->epc_page); + kfree(va_page); + return err; + } + + WARN_ON_ONCE(encl->page_cnt % SGX_VA_SLOT_COUNT); + } + encl->page_cnt++; + return va_page; +} + +static void sgx_encl_shrink(struct sgx_encl *encl, struct sgx_va_page *va_page) +{ + encl->page_cnt--; + + if (va_page) { + sgx_free_epc_page(va_page->epc_page); + list_del(&va_page->list); + kfree(va_page); + } +} + +static int sgx_encl_create(struct sgx_encl *encl, struct sgx_secs *secs) +{ + struct sgx_epc_page *secs_epc; + struct sgx_va_page *va_page; + struct sgx_pageinfo pginfo; + struct sgx_secinfo secinfo; + unsigned long encl_size; + struct file *backing; + long ret; + + va_page = sgx_encl_grow(encl); + if (IS_ERR(va_page)) + return PTR_ERR(va_page); + else if (va_page) + list_add(&va_page->list, &encl->va_pages); + /* else the tail page of the VA page list had free slots. */ + + /* The extra page goes to SECS. */ + encl_size = secs->size + PAGE_SIZE; + + backing = shmem_file_setup("SGX backing", encl_size + (encl_size >> 5), + VM_NORESERVE); + if (IS_ERR(backing)) { + ret = PTR_ERR(backing); + goto err_out_shrink; + } + + encl->backing = backing; + + secs_epc = sgx_alloc_epc_page(&encl->secs, true); + if (IS_ERR(secs_epc)) { + ret = PTR_ERR(secs_epc); + goto err_out_backing; + } + + encl->secs.epc_page = secs_epc; + + pginfo.addr = 0; + pginfo.contents = (unsigned long)secs; + pginfo.metadata = (unsigned long)&secinfo; + pginfo.secs = 0; + memset(&secinfo, 0, sizeof(secinfo)); + + ret = __ecreate((void *)&pginfo, sgx_get_epc_virt_addr(secs_epc)); + if (ret) { + ret = -EIO; + goto err_out; + } + + if (secs->attributes & SGX_ATTR_DEBUG) + set_bit(SGX_ENCL_DEBUG, &encl->flags); + + encl->secs.encl = encl; + encl->base = secs->base; + encl->size = secs->size; + encl->attributes = secs->attributes; + encl->attributes_mask = SGX_ATTR_DEBUG | SGX_ATTR_MODE64BIT | SGX_ATTR_KSS; + + /* Set only after completion, as encl->lock has not been taken. */ + set_bit(SGX_ENCL_CREATED, &encl->flags); + + return 0; + +err_out: + sgx_free_epc_page(encl->secs.epc_page); + encl->secs.epc_page = NULL; + +err_out_backing: + fput(encl->backing); + encl->backing = NULL; + +err_out_shrink: + sgx_encl_shrink(encl, va_page); + + return ret; +} + +/** + * sgx_ioc_enclave_create() - handler for %SGX_IOC_ENCLAVE_CREATE + * @encl: An enclave pointer. + * @arg: The ioctl argument. + * + * Allocate kernel data structures for the enclave and invoke ECREATE. + * + * Return: + * - 0: Success. + * - -EIO: ECREATE failed. + * - -errno: POSIX error. + */ +static long sgx_ioc_enclave_create(struct sgx_encl *encl, void __user *arg) +{ + struct sgx_enclave_create create_arg; + void *secs; + int ret; + + if (test_bit(SGX_ENCL_CREATED, &encl->flags)) + return -EINVAL; + + if (copy_from_user(&create_arg, arg, sizeof(create_arg))) + return -EFAULT; + + secs = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!secs) + return -ENOMEM; + + if (copy_from_user(secs, (void __user *)create_arg.src, PAGE_SIZE)) + ret = -EFAULT; + else + ret = sgx_encl_create(encl, secs); + + kfree(secs); + return ret; +} + +static struct sgx_encl_page *sgx_encl_page_alloc(struct sgx_encl *encl, + unsigned long offset, + u64 secinfo_flags) +{ + struct sgx_encl_page *encl_page; + unsigned long prot; + + encl_page = kzalloc(sizeof(*encl_page), GFP_KERNEL); + if (!encl_page) + return ERR_PTR(-ENOMEM); + + encl_page->desc = encl->base + offset; + encl_page->encl = encl; + + prot = _calc_vm_trans(secinfo_flags, SGX_SECINFO_R, PROT_READ) | + _calc_vm_trans(secinfo_flags, SGX_SECINFO_W, PROT_WRITE) | + _calc_vm_trans(secinfo_flags, SGX_SECINFO_X, PROT_EXEC); + + /* + * TCS pages must always RW set for CPU access while the SECINFO + * permissions are *always* zero - the CPU ignores the user provided + * values and silently overwrites them with zero permissions. + */ + if ((secinfo_flags & SGX_SECINFO_PAGE_TYPE_MASK) == SGX_SECINFO_TCS) + prot |= PROT_READ | PROT_WRITE; + + /* Calculate maximum of the VM flags for the page. */ + encl_page->vm_max_prot_bits = calc_vm_prot_bits(prot, 0); + + return encl_page; +} + +static int sgx_validate_secinfo(struct sgx_secinfo *secinfo) +{ + u64 perm = secinfo->flags & SGX_SECINFO_PERMISSION_MASK; + u64 pt = secinfo->flags & SGX_SECINFO_PAGE_TYPE_MASK; + + if (pt != SGX_SECINFO_REG && pt != SGX_SECINFO_TCS) + return -EINVAL; + + if ((perm & SGX_SECINFO_W) && !(perm & SGX_SECINFO_R)) + return -EINVAL; + + /* + * CPU will silently overwrite the permissions as zero, which means + * that we need to validate it ourselves. + */ + if (pt == SGX_SECINFO_TCS && perm) + return -EINVAL; + + if (secinfo->flags & SGX_SECINFO_RESERVED_MASK) + return -EINVAL; + + if (memchr_inv(secinfo->reserved, 0, sizeof(secinfo->reserved))) + return -EINVAL; + + return 0; +} + +static int __sgx_encl_add_page(struct sgx_encl *encl, + struct sgx_encl_page *encl_page, + struct sgx_epc_page *epc_page, + struct sgx_secinfo *secinfo, unsigned long src) +{ + struct sgx_pageinfo pginfo; + struct vm_area_struct *vma; + struct page *src_page; + int ret; + + /* Deny noexec. */ + vma = find_vma(current->mm, src); + if (!vma) + return -EFAULT; + + if (!(vma->vm_flags & VM_MAYEXEC)) + return -EACCES; + + ret = get_user_pages(src, 1, 0, &src_page, NULL); + if (ret < 1) + return -EFAULT; + + pginfo.secs = (unsigned long)sgx_get_epc_virt_addr(encl->secs.epc_page); + pginfo.addr = encl_page->desc & PAGE_MASK; + pginfo.metadata = (unsigned long)secinfo; + pginfo.contents = (unsigned long)kmap_atomic(src_page); + + ret = __eadd(&pginfo, sgx_get_epc_virt_addr(epc_page)); + + kunmap_atomic((void *)pginfo.contents); + put_page(src_page); + + return ret ? -EIO : 0; +} + +/* + * If the caller requires measurement of the page as a proof for the content, + * use EEXTEND to add a measurement for 256 bytes of the page. Repeat this + * operation until the entire page is measured." + */ +static int __sgx_encl_extend(struct sgx_encl *encl, + struct sgx_epc_page *epc_page) +{ + unsigned long offset; + int ret; + + for (offset = 0; offset < PAGE_SIZE; offset += SGX_EEXTEND_BLOCK_SIZE) { + ret = __eextend(sgx_get_epc_virt_addr(encl->secs.epc_page), + sgx_get_epc_virt_addr(epc_page) + offset); + if (ret) { + if (encls_failed(ret)) + ENCLS_WARN(ret, "EEXTEND"); + + return -EIO; + } + } + + return 0; +} + +static int sgx_encl_add_page(struct sgx_encl *encl, unsigned long src, + unsigned long offset, struct sgx_secinfo *secinfo, + unsigned long flags) +{ + struct sgx_encl_page *encl_page; + struct sgx_epc_page *epc_page; + struct sgx_va_page *va_page; + int ret; + + encl_page = sgx_encl_page_alloc(encl, offset, secinfo->flags); + if (IS_ERR(encl_page)) + return PTR_ERR(encl_page); + + epc_page = sgx_alloc_epc_page(encl_page, true); + if (IS_ERR(epc_page)) { + kfree(encl_page); + return PTR_ERR(epc_page); + } + + va_page = sgx_encl_grow(encl); + if (IS_ERR(va_page)) { + ret = PTR_ERR(va_page); + goto err_out_free; + } + + mmap_read_lock(current->mm); + mutex_lock(&encl->lock); + + /* + * Adding to encl->va_pages must be done under encl->lock. Ditto for + * deleting (via sgx_encl_shrink()) in the error path. + */ + if (va_page) + list_add(&va_page->list, &encl->va_pages); + + /* + * Insert prior to EADD in case of OOM. EADD modifies MRENCLAVE, i.e. + * can't be gracefully unwound, while failure on EADD/EXTEND is limited + * to userspace errors (or kernel/hardware bugs). + */ + ret = xa_insert(&encl->page_array, PFN_DOWN(encl_page->desc), + encl_page, GFP_KERNEL); + if (ret) + goto err_out_unlock; + + ret = __sgx_encl_add_page(encl, encl_page, epc_page, secinfo, + src); + if (ret) + goto err_out; + + /* + * Complete the "add" before doing the "extend" so that the "add" + * isn't in a half-baked state in the extremely unlikely scenario + * the enclave will be destroyed in response to EEXTEND failure. + */ + encl_page->encl = encl; + encl_page->epc_page = epc_page; + encl->secs_child_cnt++; + + if (flags & SGX_PAGE_MEASURE) { + ret = __sgx_encl_extend(encl, epc_page); + if (ret) + goto err_out; + } + + sgx_mark_page_reclaimable(encl_page->epc_page); + mutex_unlock(&encl->lock); + mmap_read_unlock(current->mm); + return ret; + +err_out: + xa_erase(&encl->page_array, PFN_DOWN(encl_page->desc)); + +err_out_unlock: + sgx_encl_shrink(encl, va_page); + mutex_unlock(&encl->lock); + mmap_read_unlock(current->mm); + +err_out_free: + sgx_free_epc_page(epc_page); + kfree(encl_page); + + return ret; +} + +/** + * sgx_ioc_enclave_add_pages() - The handler for %SGX_IOC_ENCLAVE_ADD_PAGES + * @encl: an enclave pointer + * @arg: a user pointer to a struct sgx_enclave_add_pages instance + * + * Add one or more pages to an uninitialized enclave, and optionally extend the + * measurement with the contents of the page. The SECINFO and measurement mask + * are applied to all pages. + * + * A SECINFO for a TCS is required to always contain zero permissions because + * CPU silently zeros them. Allowing anything else would cause a mismatch in + * the measurement. + * + * mmap()'s protection bits are capped by the page permissions. For each page + * address, the maximum protection bits are computed with the following + * heuristics: + * + * 1. A regular page: PROT_R, PROT_W and PROT_X match the SECINFO permissions. + * 2. A TCS page: PROT_R | PROT_W. + * + * mmap() is not allowed to surpass the minimum of the maximum protection bits + * within the given address range. + * + * The function deinitializes kernel data structures for enclave and returns + * -EIO in any of the following conditions: + * + * - Enclave Page Cache (EPC), the physical memory holding enclaves, has + * been invalidated. This will cause EADD and EEXTEND to fail. + * - If the source address is corrupted somehow when executing EADD. + * + * Return: + * - 0: Success. + * - -EACCES: The source page is located in a noexec partition. + * - -ENOMEM: Out of EPC pages. + * - -EINTR: The call was interrupted before data was processed. + * - -EIO: Either EADD or EEXTEND failed because invalid source address + * or power cycle. + * - -errno: POSIX error. + */ +static long sgx_ioc_enclave_add_pages(struct sgx_encl *encl, void __user *arg) +{ + struct sgx_enclave_add_pages add_arg; + struct sgx_secinfo secinfo; + unsigned long c; + int ret; + + if (!test_bit(SGX_ENCL_CREATED, &encl->flags) || + test_bit(SGX_ENCL_INITIALIZED, &encl->flags)) + return -EINVAL; + + if (copy_from_user(&add_arg, arg, sizeof(add_arg))) + return -EFAULT; + + if (!IS_ALIGNED(add_arg.offset, PAGE_SIZE) || + !IS_ALIGNED(add_arg.src, PAGE_SIZE)) + return -EINVAL; + + if (!add_arg.length || add_arg.length & (PAGE_SIZE - 1)) + return -EINVAL; + + if (add_arg.offset + add_arg.length - PAGE_SIZE >= encl->size) + return -EINVAL; + + if (copy_from_user(&secinfo, (void __user *)add_arg.secinfo, + sizeof(secinfo))) + return -EFAULT; + + if (sgx_validate_secinfo(&secinfo)) + return -EINVAL; + + for (c = 0 ; c < add_arg.length; c += PAGE_SIZE) { + if (signal_pending(current)) { + if (!c) + ret = -ERESTARTSYS; + + break; + } + + if (need_resched()) + cond_resched(); + + ret = sgx_encl_add_page(encl, add_arg.src + c, add_arg.offset + c, + &secinfo, add_arg.flags); + if (ret) + break; + } + + add_arg.count = c; + + if (copy_to_user(arg, &add_arg, sizeof(add_arg))) + return -EFAULT; + + return ret; +} + +static int __sgx_get_key_hash(struct crypto_shash *tfm, const void *modulus, + void *hash) +{ + SHASH_DESC_ON_STACK(shash, tfm); + + shash->tfm = tfm; + + return crypto_shash_digest(shash, modulus, SGX_MODULUS_SIZE, hash); +} + +static int sgx_get_key_hash(const void *modulus, void *hash) +{ + struct crypto_shash *tfm; + int ret; + + tfm = crypto_alloc_shash("sha256", 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(tfm)) + return PTR_ERR(tfm); + + ret = __sgx_get_key_hash(tfm, modulus, hash); + + crypto_free_shash(tfm); + return ret; +} + +static int sgx_encl_init(struct sgx_encl *encl, struct sgx_sigstruct *sigstruct, + void *token) +{ + u64 mrsigner[4]; + int i, j, k; + void *addr; + int ret; + + /* + * Deny initializing enclaves with attributes (namely provisioning) + * that have not been explicitly allowed. + */ + if (encl->attributes & ~encl->attributes_mask) + return -EACCES; + + /* + * Attributes should not be enforced *only* against what's available on + * platform (done in sgx_encl_create) but checked and enforced against + * the mask for enforcement in sigstruct. For example an enclave could + * opt to sign with AVX bit in xfrm, but still be loadable on a platform + * without it if the sigstruct->body.attributes_mask does not turn that + * bit on. + */ + if (sigstruct->body.attributes & sigstruct->body.attributes_mask & + sgx_attributes_reserved_mask) + return -EINVAL; + + if (sigstruct->body.miscselect & sigstruct->body.misc_mask & + sgx_misc_reserved_mask) + return -EINVAL; + + if (sigstruct->body.xfrm & sigstruct->body.xfrm_mask & + sgx_xfrm_reserved_mask) + return -EINVAL; + + ret = sgx_get_key_hash(sigstruct->modulus, mrsigner); + if (ret) + return ret; + + mutex_lock(&encl->lock); + + /* + * ENCLS[EINIT] is interruptible because it has such a high latency, + * e.g. 50k+ cycles on success. If an IRQ/NMI/SMI becomes pending, + * EINIT may fail with SGX_UNMASKED_EVENT so that the event can be + * serviced. + */ + for (i = 0; i < SGX_EINIT_SLEEP_COUNT; i++) { + for (j = 0; j < SGX_EINIT_SPIN_COUNT; j++) { + addr = sgx_get_epc_virt_addr(encl->secs.epc_page); + + preempt_disable(); + + for (k = 0; k < 4; k++) + wrmsrl(MSR_IA32_SGXLEPUBKEYHASH0 + k, mrsigner[k]); + + ret = __einit(sigstruct, token, addr); + + preempt_enable(); + + if (ret == SGX_UNMASKED_EVENT) + continue; + else + break; + } + + if (ret != SGX_UNMASKED_EVENT) + break; + + msleep_interruptible(SGX_EINIT_SLEEP_TIME); + + if (signal_pending(current)) { + ret = -ERESTARTSYS; + goto err_out; + } + } + + if (ret & ENCLS_FAULT_FLAG) { + if (encls_failed(ret)) + ENCLS_WARN(ret, "EINIT"); + + ret = -EIO; + } else if (ret) { + pr_debug("EINIT returned %d\n", ret); + ret = -EPERM; + } else { + set_bit(SGX_ENCL_INITIALIZED, &encl->flags); + } + +err_out: + mutex_unlock(&encl->lock); + return ret; +} + +/** + * sgx_ioc_enclave_init() - handler for %SGX_IOC_ENCLAVE_INIT + * @encl: an enclave pointer + * @arg: userspace pointer to a struct sgx_enclave_init instance + * + * Flush any outstanding enqueued EADD operations and perform EINIT. The + * Launch Enclave Public Key Hash MSRs are rewritten as necessary to match + * the enclave's MRSIGNER, which is caculated from the provided sigstruct. + * + * Return: + * - 0: Success. + * - -EPERM: Invalid SIGSTRUCT. + * - -EIO: EINIT failed because of a power cycle. + * - -errno: POSIX error. + */ +static long sgx_ioc_enclave_init(struct sgx_encl *encl, void __user *arg) +{ + struct sgx_sigstruct *sigstruct; + struct sgx_enclave_init init_arg; + struct page *initp_page; + void *token; + int ret; + + if (!test_bit(SGX_ENCL_CREATED, &encl->flags) || + test_bit(SGX_ENCL_INITIALIZED, &encl->flags)) + return -EINVAL; + + if (copy_from_user(&init_arg, arg, sizeof(init_arg))) + return -EFAULT; + + initp_page = alloc_page(GFP_KERNEL); + if (!initp_page) + return -ENOMEM; + + sigstruct = kmap(initp_page); + token = (void *)((unsigned long)sigstruct + PAGE_SIZE / 2); + memset(token, 0, SGX_LAUNCH_TOKEN_SIZE); + + if (copy_from_user(sigstruct, (void __user *)init_arg.sigstruct, + sizeof(*sigstruct))) { + ret = -EFAULT; + goto out; + } + + /* + * A legacy field used with Intel signed enclaves. These used to mean + * regular and architectural enclaves. The CPU only accepts these values + * but they do not have any other meaning. + * + * Thus, reject any other values. + */ + if (sigstruct->header.vendor != 0x0000 && + sigstruct->header.vendor != 0x8086) { + ret = -EINVAL; + goto out; + } + + ret = sgx_encl_init(encl, sigstruct, token); + +out: + kunmap(initp_page); + __free_page(initp_page); + return ret; +} + +/** + * sgx_ioc_enclave_provision() - handler for %SGX_IOC_ENCLAVE_PROVISION + * @encl: an enclave pointer + * @arg: userspace pointer to a struct sgx_enclave_provision instance + * + * Allow ATTRIBUTE.PROVISION_KEY for an enclave by providing a file handle to + * /dev/sgx_provision. + * + * Return: + * - 0: Success. + * - -errno: Otherwise. + */ +static long sgx_ioc_enclave_provision(struct sgx_encl *encl, void __user *arg) +{ + struct sgx_enclave_provision params; + struct file *file; + + if (copy_from_user(¶ms, arg, sizeof(params))) + return -EFAULT; + + file = fget(params.fd); + if (!file) + return -EINVAL; + + if (file->f_op != &sgx_provision_fops) { + fput(file); + return -EINVAL; + } + + encl->attributes_mask |= SGX_ATTR_PROVISIONKEY; + + fput(file); + return 0; +} + +long sgx_ioctl(struct file *filep, unsigned int cmd, unsigned long arg) +{ + struct sgx_encl *encl = filep->private_data; + int ret; + + if (test_and_set_bit(SGX_ENCL_IOCTL, &encl->flags)) + return -EBUSY; + + switch (cmd) { + case SGX_IOC_ENCLAVE_CREATE: + ret = sgx_ioc_enclave_create(encl, (void __user *)arg); + break; + case SGX_IOC_ENCLAVE_ADD_PAGES: + ret = sgx_ioc_enclave_add_pages(encl, (void __user *)arg); + break; + case SGX_IOC_ENCLAVE_INIT: + ret = sgx_ioc_enclave_init(encl, (void __user *)arg); + break; + case SGX_IOC_ENCLAVE_PROVISION: + ret = sgx_ioc_enclave_provision(encl, (void __user *)arg); + break; + default: + ret = -ENOIOCTLCMD; + break; + } + + clear_bit(SGX_ENCL_IOCTL, &encl->flags); + return ret; +} diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c new file mode 100644 index 000000000000..8df81a3ed945 --- /dev/null +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -0,0 +1,737 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2016-20 Intel Corporation. */ + +#include <linux/freezer.h> +#include <linux/highmem.h> +#include <linux/kthread.h> +#include <linux/pagemap.h> +#include <linux/ratelimit.h> +#include <linux/sched/mm.h> +#include <linux/sched/signal.h> +#include <linux/slab.h> +#include "driver.h" +#include "encl.h" +#include "encls.h" + +struct sgx_epc_section sgx_epc_sections[SGX_MAX_EPC_SECTIONS]; +static int sgx_nr_epc_sections; +static struct task_struct *ksgxd_tsk; +static DECLARE_WAIT_QUEUE_HEAD(ksgxd_waitq); + +/* + * These variables are part of the state of the reclaimer, and must be accessed + * with sgx_reclaimer_lock acquired. + */ +static LIST_HEAD(sgx_active_page_list); + +static DEFINE_SPINLOCK(sgx_reclaimer_lock); + +/* + * Reset dirty EPC pages to uninitialized state. Laundry can be left with SECS + * pages whose child pages blocked EREMOVE. + */ +static void sgx_sanitize_section(struct sgx_epc_section *section) +{ + struct sgx_epc_page *page; + LIST_HEAD(dirty); + int ret; + + /* init_laundry_list is thread-local, no need for a lock: */ + while (!list_empty(§ion->init_laundry_list)) { + if (kthread_should_stop()) + return; + + /* needed for access to ->page_list: */ + spin_lock(§ion->lock); + + page = list_first_entry(§ion->init_laundry_list, + struct sgx_epc_page, list); + + ret = __eremove(sgx_get_epc_virt_addr(page)); + if (!ret) + list_move(&page->list, §ion->page_list); + else + list_move_tail(&page->list, &dirty); + + spin_unlock(§ion->lock); + + cond_resched(); + } + + list_splice(&dirty, §ion->init_laundry_list); +} + +static bool sgx_reclaimer_age(struct sgx_epc_page *epc_page) +{ + struct sgx_encl_page *page = epc_page->owner; + struct sgx_encl *encl = page->encl; + struct sgx_encl_mm *encl_mm; + bool ret = true; + int idx; + + idx = srcu_read_lock(&encl->srcu); + + list_for_each_entry_rcu(encl_mm, &encl->mm_list, list) { + if (!mmget_not_zero(encl_mm->mm)) + continue; + + mmap_read_lock(encl_mm->mm); + ret = !sgx_encl_test_and_clear_young(encl_mm->mm, page); + mmap_read_unlock(encl_mm->mm); + + mmput_async(encl_mm->mm); + + if (!ret) + break; + } + + srcu_read_unlock(&encl->srcu, idx); + + if (!ret) + return false; + + return true; +} + +static void sgx_reclaimer_block(struct sgx_epc_page *epc_page) +{ + struct sgx_encl_page *page = epc_page->owner; + unsigned long addr = page->desc & PAGE_MASK; + struct sgx_encl *encl = page->encl; + unsigned long mm_list_version; + struct sgx_encl_mm *encl_mm; + struct vm_area_struct *vma; + int idx, ret; + + do { + mm_list_version = encl->mm_list_version; + + /* Pairs with smp_rmb() in sgx_encl_mm_add(). */ + smp_rmb(); + + idx = srcu_read_lock(&encl->srcu); + + list_for_each_entry_rcu(encl_mm, &encl->mm_list, list) { + if (!mmget_not_zero(encl_mm->mm)) + continue; + + mmap_read_lock(encl_mm->mm); + + ret = sgx_encl_find(encl_mm->mm, addr, &vma); + if (!ret && encl == vma->vm_private_data) + zap_vma_ptes(vma, addr, PAGE_SIZE); + + mmap_read_unlock(encl_mm->mm); + + mmput_async(encl_mm->mm); + } + + srcu_read_unlock(&encl->srcu, idx); + } while (unlikely(encl->mm_list_version != mm_list_version)); + + mutex_lock(&encl->lock); + + ret = __eblock(sgx_get_epc_virt_addr(epc_page)); + if (encls_failed(ret)) + ENCLS_WARN(ret, "EBLOCK"); + + mutex_unlock(&encl->lock); +} + +static int __sgx_encl_ewb(struct sgx_epc_page *epc_page, void *va_slot, + struct sgx_backing *backing) +{ + struct sgx_pageinfo pginfo; + int ret; + + pginfo.addr = 0; + pginfo.secs = 0; + + pginfo.contents = (unsigned long)kmap_atomic(backing->contents); + pginfo.metadata = (unsigned long)kmap_atomic(backing->pcmd) + + backing->pcmd_offset; + + ret = __ewb(&pginfo, sgx_get_epc_virt_addr(epc_page), va_slot); + + kunmap_atomic((void *)(unsigned long)(pginfo.metadata - + backing->pcmd_offset)); + kunmap_atomic((void *)(unsigned long)pginfo.contents); + + return ret; +} + +static void sgx_ipi_cb(void *info) +{ +} + +static const cpumask_t *sgx_encl_ewb_cpumask(struct sgx_encl *encl) +{ + cpumask_t *cpumask = &encl->cpumask; + struct sgx_encl_mm *encl_mm; + int idx; + + /* + * Can race with sgx_encl_mm_add(), but ETRACK has already been + * executed, which means that the CPUs running in the new mm will enter + * into the enclave with a fresh epoch. + */ + cpumask_clear(cpumask); + + idx = srcu_read_lock(&encl->srcu); + + list_for_each_entry_rcu(encl_mm, &encl->mm_list, list) { + if (!mmget_not_zero(encl_mm->mm)) + continue; + + cpumask_or(cpumask, cpumask, mm_cpumask(encl_mm->mm)); + + mmput_async(encl_mm->mm); + } + + srcu_read_unlock(&encl->srcu, idx); + + return cpumask; +} + +/* + * Swap page to the regular memory transformed to the blocked state by using + * EBLOCK, which means that it can no loger be referenced (no new TLB entries). + * + * The first trial just tries to write the page assuming that some other thread + * has reset the count for threads inside the enlave by using ETRACK, and + * previous thread count has been zeroed out. The second trial calls ETRACK + * before EWB. If that fails we kick all the HW threads out, and then do EWB, + * which should be guaranteed the succeed. + */ +static void sgx_encl_ewb(struct sgx_epc_page *epc_page, + struct sgx_backing *backing) +{ + struct sgx_encl_page *encl_page = epc_page->owner; + struct sgx_encl *encl = encl_page->encl; + struct sgx_va_page *va_page; + unsigned int va_offset; + void *va_slot; + int ret; + + encl_page->desc &= ~SGX_ENCL_PAGE_BEING_RECLAIMED; + + va_page = list_first_entry(&encl->va_pages, struct sgx_va_page, + list); + va_offset = sgx_alloc_va_slot(va_page); + va_slot = sgx_get_epc_virt_addr(va_page->epc_page) + va_offset; + if (sgx_va_page_full(va_page)) + list_move_tail(&va_page->list, &encl->va_pages); + + ret = __sgx_encl_ewb(epc_page, va_slot, backing); + if (ret == SGX_NOT_TRACKED) { + ret = __etrack(sgx_get_epc_virt_addr(encl->secs.epc_page)); + if (ret) { + if (encls_failed(ret)) + ENCLS_WARN(ret, "ETRACK"); + } + + ret = __sgx_encl_ewb(epc_page, va_slot, backing); + if (ret == SGX_NOT_TRACKED) { + /* + * Slow path, send IPIs to kick cpus out of the + * enclave. Note, it's imperative that the cpu + * mask is generated *after* ETRACK, else we'll + * miss cpus that entered the enclave between + * generating the mask and incrementing epoch. + */ + on_each_cpu_mask(sgx_encl_ewb_cpumask(encl), + sgx_ipi_cb, NULL, 1); + ret = __sgx_encl_ewb(epc_page, va_slot, backing); + } + } + + if (ret) { + if (encls_failed(ret)) + ENCLS_WARN(ret, "EWB"); + + sgx_free_va_slot(va_page, va_offset); + } else { + encl_page->desc |= va_offset; + encl_page->va_page = va_page; + } +} + +static void sgx_reclaimer_write(struct sgx_epc_page *epc_page, + struct sgx_backing *backing) +{ + struct sgx_encl_page *encl_page = epc_page->owner; + struct sgx_encl *encl = encl_page->encl; + struct sgx_backing secs_backing; + int ret; + + mutex_lock(&encl->lock); + + sgx_encl_ewb(epc_page, backing); + encl_page->epc_page = NULL; + encl->secs_child_cnt--; + + if (!encl->secs_child_cnt && test_bit(SGX_ENCL_INITIALIZED, &encl->flags)) { + ret = sgx_encl_get_backing(encl, PFN_DOWN(encl->size), + &secs_backing); + if (ret) + goto out; + + sgx_encl_ewb(encl->secs.epc_page, &secs_backing); + + sgx_free_epc_page(encl->secs.epc_page); + encl->secs.epc_page = NULL; + + sgx_encl_put_backing(&secs_backing, true); + } + +out: + mutex_unlock(&encl->lock); +} + +/* + * Take a fixed number of pages from the head of the active page pool and + * reclaim them to the enclave's private shmem files. Skip the pages, which have + * been accessed since the last scan. Move those pages to the tail of active + * page pool so that the pages get scanned in LRU like fashion. + * + * Batch process a chunk of pages (at the moment 16) in order to degrade amount + * of IPI's and ETRACK's potentially required. sgx_encl_ewb() does degrade a bit + * among the HW threads with three stage EWB pipeline (EWB, ETRACK + EWB and IPI + * + EWB) but not sufficiently. Reclaiming one page at a time would also be + * problematic as it would increase the lock contention too much, which would + * halt forward progress. + */ +static void sgx_reclaim_pages(void) +{ + struct sgx_epc_page *chunk[SGX_NR_TO_SCAN]; + struct sgx_backing backing[SGX_NR_TO_SCAN]; + struct sgx_epc_section *section; + struct sgx_encl_page *encl_page; + struct sgx_epc_page *epc_page; + pgoff_t page_index; + int cnt = 0; + int ret; + int i; + + spin_lock(&sgx_reclaimer_lock); + for (i = 0; i < SGX_NR_TO_SCAN; i++) { + if (list_empty(&sgx_active_page_list)) + break; + + epc_page = list_first_entry(&sgx_active_page_list, + struct sgx_epc_page, list); + list_del_init(&epc_page->list); + encl_page = epc_page->owner; + + if (kref_get_unless_zero(&encl_page->encl->refcount) != 0) + chunk[cnt++] = epc_page; + else + /* The owner is freeing the page. No need to add the + * page back to the list of reclaimable pages. + */ + epc_page->flags &= ~SGX_EPC_PAGE_RECLAIMER_TRACKED; + } + spin_unlock(&sgx_reclaimer_lock); + + for (i = 0; i < cnt; i++) { + epc_page = chunk[i]; + encl_page = epc_page->owner; + + if (!sgx_reclaimer_age(epc_page)) + goto skip; + + page_index = PFN_DOWN(encl_page->desc - encl_page->encl->base); + ret = sgx_encl_get_backing(encl_page->encl, page_index, &backing[i]); + if (ret) + goto skip; + + mutex_lock(&encl_page->encl->lock); + encl_page->desc |= SGX_ENCL_PAGE_BEING_RECLAIMED; + mutex_unlock(&encl_page->encl->lock); + continue; + +skip: + spin_lock(&sgx_reclaimer_lock); + list_add_tail(&epc_page->list, &sgx_active_page_list); + spin_unlock(&sgx_reclaimer_lock); + + kref_put(&encl_page->encl->refcount, sgx_encl_release); + + chunk[i] = NULL; + } + + for (i = 0; i < cnt; i++) { + epc_page = chunk[i]; + if (epc_page) + sgx_reclaimer_block(epc_page); + } + + for (i = 0; i < cnt; i++) { + epc_page = chunk[i]; + if (!epc_page) + continue; + + encl_page = epc_page->owner; + sgx_reclaimer_write(epc_page, &backing[i]); + sgx_encl_put_backing(&backing[i], true); + + kref_put(&encl_page->encl->refcount, sgx_encl_release); + epc_page->flags &= ~SGX_EPC_PAGE_RECLAIMER_TRACKED; + + section = &sgx_epc_sections[epc_page->section]; + spin_lock(§ion->lock); + list_add_tail(&epc_page->list, §ion->page_list); + section->free_cnt++; + spin_unlock(§ion->lock); + } +} + +static unsigned long sgx_nr_free_pages(void) +{ + unsigned long cnt = 0; + int i; + + for (i = 0; i < sgx_nr_epc_sections; i++) + cnt += sgx_epc_sections[i].free_cnt; + + return cnt; +} + +static bool sgx_should_reclaim(unsigned long watermark) +{ + return sgx_nr_free_pages() < watermark && + !list_empty(&sgx_active_page_list); +} + +static int ksgxd(void *p) +{ + int i; + + set_freezable(); + + /* + * Sanitize pages in order to recover from kexec(). The 2nd pass is + * required for SECS pages, whose child pages blocked EREMOVE. + */ + for (i = 0; i < sgx_nr_epc_sections; i++) + sgx_sanitize_section(&sgx_epc_sections[i]); + + for (i = 0; i < sgx_nr_epc_sections; i++) { + sgx_sanitize_section(&sgx_epc_sections[i]); + + /* Should never happen. */ + if (!list_empty(&sgx_epc_sections[i].init_laundry_list)) + WARN(1, "EPC section %d has unsanitized pages.\n", i); + } + + while (!kthread_should_stop()) { + if (try_to_freeze()) + continue; + + wait_event_freezable(ksgxd_waitq, + kthread_should_stop() || + sgx_should_reclaim(SGX_NR_HIGH_PAGES)); + + if (sgx_should_reclaim(SGX_NR_HIGH_PAGES)) + sgx_reclaim_pages(); + + cond_resched(); + } + + return 0; +} + +static bool __init sgx_page_reclaimer_init(void) +{ + struct task_struct *tsk; + + tsk = kthread_run(ksgxd, NULL, "ksgxd"); + if (IS_ERR(tsk)) + return false; + + ksgxd_tsk = tsk; + + return true; +} + +static struct sgx_epc_page *__sgx_alloc_epc_page_from_section(struct sgx_epc_section *section) +{ + struct sgx_epc_page *page; + + spin_lock(§ion->lock); + + if (list_empty(§ion->page_list)) { + spin_unlock(§ion->lock); + return NULL; + } + + page = list_first_entry(§ion->page_list, struct sgx_epc_page, list); + list_del_init(&page->list); + section->free_cnt--; + + spin_unlock(§ion->lock); + return page; +} + +/** + * __sgx_alloc_epc_page() - Allocate an EPC page + * + * Iterate through EPC sections and borrow a free EPC page to the caller. When a + * page is no longer needed it must be released with sgx_free_epc_page(). + * + * Return: + * an EPC page, + * -errno on error + */ +struct sgx_epc_page *__sgx_alloc_epc_page(void) +{ + struct sgx_epc_section *section; + struct sgx_epc_page *page; + int i; + + for (i = 0; i < sgx_nr_epc_sections; i++) { + section = &sgx_epc_sections[i]; + + page = __sgx_alloc_epc_page_from_section(section); + if (page) + return page; + } + + return ERR_PTR(-ENOMEM); +} + +/** + * sgx_mark_page_reclaimable() - Mark a page as reclaimable + * @page: EPC page + * + * Mark a page as reclaimable and add it to the active page list. Pages + * are automatically removed from the active list when freed. + */ +void sgx_mark_page_reclaimable(struct sgx_epc_page *page) +{ + spin_lock(&sgx_reclaimer_lock); + page->flags |= SGX_EPC_PAGE_RECLAIMER_TRACKED; + list_add_tail(&page->list, &sgx_active_page_list); + spin_unlock(&sgx_reclaimer_lock); +} + +/** + * sgx_unmark_page_reclaimable() - Remove a page from the reclaim list + * @page: EPC page + * + * Clear the reclaimable flag and remove the page from the active page list. + * + * Return: + * 0 on success, + * -EBUSY if the page is in the process of being reclaimed + */ +int sgx_unmark_page_reclaimable(struct sgx_epc_page *page) +{ + spin_lock(&sgx_reclaimer_lock); + if (page->flags & SGX_EPC_PAGE_RECLAIMER_TRACKED) { + /* The page is being reclaimed. */ + if (list_empty(&page->list)) { + spin_unlock(&sgx_reclaimer_lock); + return -EBUSY; + } + + list_del(&page->list); + page->flags &= ~SGX_EPC_PAGE_RECLAIMER_TRACKED; + } + spin_unlock(&sgx_reclaimer_lock); + + return 0; +} + +/** + * sgx_alloc_epc_page() - Allocate an EPC page + * @owner: the owner of the EPC page + * @reclaim: reclaim pages if necessary + * + * Iterate through EPC sections and borrow a free EPC page to the caller. When a + * page is no longer needed it must be released with sgx_free_epc_page(). If + * @reclaim is set to true, directly reclaim pages when we are out of pages. No + * mm's can be locked when @reclaim is set to true. + * + * Finally, wake up ksgxd when the number of pages goes below the watermark + * before returning back to the caller. + * + * Return: + * an EPC page, + * -errno on error + */ +struct sgx_epc_page *sgx_alloc_epc_page(void *owner, bool reclaim) +{ + struct sgx_epc_page *page; + + for ( ; ; ) { + page = __sgx_alloc_epc_page(); + if (!IS_ERR(page)) { + page->owner = owner; + break; + } + + if (list_empty(&sgx_active_page_list)) + return ERR_PTR(-ENOMEM); + + if (!reclaim) { + page = ERR_PTR(-EBUSY); + break; + } + + if (signal_pending(current)) { + page = ERR_PTR(-ERESTARTSYS); + break; + } + + sgx_reclaim_pages(); + cond_resched(); + } + + if (sgx_should_reclaim(SGX_NR_LOW_PAGES)) + wake_up(&ksgxd_waitq); + + return page; +} + +/** + * sgx_free_epc_page() - Free an EPC page + * @page: an EPC page + * + * Call EREMOVE for an EPC page and insert it back to the list of free pages. + */ +void sgx_free_epc_page(struct sgx_epc_page *page) +{ + struct sgx_epc_section *section = &sgx_epc_sections[page->section]; + int ret; + + WARN_ON_ONCE(page->flags & SGX_EPC_PAGE_RECLAIMER_TRACKED); + + ret = __eremove(sgx_get_epc_virt_addr(page)); + if (WARN_ONCE(ret, "EREMOVE returned %d (0x%x)", ret, ret)) + return; + + spin_lock(§ion->lock); + list_add_tail(&page->list, §ion->page_list); + section->free_cnt++; + spin_unlock(§ion->lock); +} + +static bool __init sgx_setup_epc_section(u64 phys_addr, u64 size, + unsigned long index, + struct sgx_epc_section *section) +{ + unsigned long nr_pages = size >> PAGE_SHIFT; + unsigned long i; + + section->virt_addr = memremap(phys_addr, size, MEMREMAP_WB); + if (!section->virt_addr) + return false; + + section->pages = vmalloc(nr_pages * sizeof(struct sgx_epc_page)); + if (!section->pages) { + memunmap(section->virt_addr); + return false; + } + + section->phys_addr = phys_addr; + spin_lock_init(§ion->lock); + INIT_LIST_HEAD(§ion->page_list); + INIT_LIST_HEAD(§ion->init_laundry_list); + + for (i = 0; i < nr_pages; i++) { + section->pages[i].section = index; + section->pages[i].flags = 0; + section->pages[i].owner = NULL; + list_add_tail(§ion->pages[i].list, §ion->init_laundry_list); + } + + section->free_cnt = nr_pages; + return true; +} + +/** + * A section metric is concatenated in a way that @low bits 12-31 define the + * bits 12-31 of the metric and @high bits 0-19 define the bits 32-51 of the + * metric. + */ +static inline u64 __init sgx_calc_section_metric(u64 low, u64 high) +{ + return (low & GENMASK_ULL(31, 12)) + + ((high & GENMASK_ULL(19, 0)) << 32); +} + +static bool __init sgx_page_cache_init(void) +{ + u32 eax, ebx, ecx, edx, type; + u64 pa, size; + int i; + + for (i = 0; i < ARRAY_SIZE(sgx_epc_sections); i++) { + cpuid_count(SGX_CPUID, i + SGX_CPUID_EPC, &eax, &ebx, &ecx, &edx); + + type = eax & SGX_CPUID_EPC_MASK; + if (type == SGX_CPUID_EPC_INVALID) + break; + + if (type != SGX_CPUID_EPC_SECTION) { + pr_err_once("Unknown EPC section type: %u\n", type); + break; + } + + pa = sgx_calc_section_metric(eax, ebx); + size = sgx_calc_section_metric(ecx, edx); + + pr_info("EPC section 0x%llx-0x%llx\n", pa, pa + size - 1); + + if (!sgx_setup_epc_section(pa, size, i, &sgx_epc_sections[i])) { + pr_err("No free memory for an EPC section\n"); + break; + } + + sgx_nr_epc_sections++; + } + + if (!sgx_nr_epc_sections) { + pr_err("There are zero EPC sections.\n"); + return false; + } + + return true; +} + +static int __init sgx_init(void) +{ + int ret; + int i; + + if (!cpu_feature_enabled(X86_FEATURE_SGX)) + return -ENODEV; + + if (!sgx_page_cache_init()) + return -ENOMEM; + + if (!sgx_page_reclaimer_init()) { + ret = -ENOMEM; + goto err_page_cache; + } + + ret = sgx_drv_init(); + if (ret) + goto err_kthread; + + return 0; + +err_kthread: + kthread_stop(ksgxd_tsk); + +err_page_cache: + for (i = 0; i < sgx_nr_epc_sections; i++) { + vfree(sgx_epc_sections[i].pages); + memunmap(sgx_epc_sections[i].virt_addr); + } + + return ret; +} + +device_initcall(sgx_init); diff --git a/arch/x86/kernel/cpu/sgx/sgx.h b/arch/x86/kernel/cpu/sgx/sgx.h new file mode 100644 index 000000000000..5fa42d143feb --- /dev/null +++ b/arch/x86/kernel/cpu/sgx/sgx.h @@ -0,0 +1,86 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _X86_SGX_H +#define _X86_SGX_H + +#include <linux/bitops.h> +#include <linux/err.h> +#include <linux/io.h> +#include <linux/rwsem.h> +#include <linux/types.h> +#include <asm/asm.h> +#include "arch.h" + +#undef pr_fmt +#define pr_fmt(fmt) "sgx: " fmt + +#define SGX_MAX_EPC_SECTIONS 8 +#define SGX_EEXTEND_BLOCK_SIZE 256 +#define SGX_NR_TO_SCAN 16 +#define SGX_NR_LOW_PAGES 32 +#define SGX_NR_HIGH_PAGES 64 + +/* Pages, which are being tracked by the page reclaimer. */ +#define SGX_EPC_PAGE_RECLAIMER_TRACKED BIT(0) + +struct sgx_epc_page { + unsigned int section; + unsigned int flags; + struct sgx_encl_page *owner; + struct list_head list; +}; + +/* + * The firmware can define multiple chunks of EPC to the different areas of the + * physical memory e.g. for memory areas of the each node. This structure is + * used to store EPC pages for one EPC section and virtual memory area where + * the pages have been mapped. + * + * 'lock' must be held before accessing 'page_list' or 'free_cnt'. + */ +struct sgx_epc_section { + unsigned long phys_addr; + void *virt_addr; + struct sgx_epc_page *pages; + + spinlock_t lock; + struct list_head page_list; + unsigned long free_cnt; + + /* + * Pages which need EREMOVE run on them before they can be + * used. Only safe to be accessed in ksgxd and init code. + * Not protected by locks. + */ + struct list_head init_laundry_list; +}; + +extern struct sgx_epc_section sgx_epc_sections[SGX_MAX_EPC_SECTIONS]; + +static inline unsigned long sgx_get_epc_phys_addr(struct sgx_epc_page *page) +{ + struct sgx_epc_section *section = &sgx_epc_sections[page->section]; + unsigned long index; + + index = ((unsigned long)page - (unsigned long)section->pages) / sizeof(*page); + + return section->phys_addr + index * PAGE_SIZE; +} + +static inline void *sgx_get_epc_virt_addr(struct sgx_epc_page *page) +{ + struct sgx_epc_section *section = &sgx_epc_sections[page->section]; + unsigned long index; + + index = ((unsigned long)page - (unsigned long)section->pages) / sizeof(*page); + + return section->virt_addr + index * PAGE_SIZE; +} + +struct sgx_epc_page *__sgx_alloc_epc_page(void); +void sgx_free_epc_page(struct sgx_epc_page *page); + +void sgx_mark_page_reclaimable(struct sgx_epc_page *page); +int sgx_unmark_page_reclaimable(struct sgx_epc_page *page); +struct sgx_epc_page *sgx_alloc_epc_page(void *owner, bool reclaim); + +#endif /* _X86_SGX_H */ diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index d3a0791bc052..8678864ce712 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -25,10 +25,10 @@ #define BITS_SHIFT_NEXT_LEVEL(eax) ((eax) & 0x1f) #define LEVEL_MAX_SIBLINGS(ebx) ((ebx) & 0xffff) -#ifdef CONFIG_SMP unsigned int __max_die_per_package __read_mostly = 1; EXPORT_SYMBOL(__max_die_per_package); +#ifdef CONFIG_SMP /* * Check if given CPUID extended toplogy "leaf" is implemented */ @@ -96,6 +96,7 @@ int detect_extended_topology(struct cpuinfo_x86 *c) unsigned int ht_mask_width, core_plus_mask_width, die_plus_mask_width; unsigned int core_select_mask, core_level_siblings; unsigned int die_select_mask, die_level_siblings; + bool die_level_present = false; int leaf; leaf = detect_extended_topology_leaf(c); @@ -126,6 +127,7 @@ int detect_extended_topology(struct cpuinfo_x86 *c) die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); } if (LEAFB_SUBTYPE(ecx) == DIE_TYPE) { + die_level_present = true; die_level_siblings = LEVEL_MAX_SIBLINGS(ebx); die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); } @@ -139,8 +141,12 @@ int detect_extended_topology(struct cpuinfo_x86 *c) c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, ht_mask_width) & core_select_mask; - c->cpu_die_id = apic->phys_pkg_id(c->initial_apicid, - core_plus_mask_width) & die_select_mask; + + if (die_level_present) { + c->cpu_die_id = apic->phys_pkg_id(c->initial_apicid, + core_plus_mask_width) & die_select_mask; + } + c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, die_plus_mask_width); /* diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 924571fe5864..c6ede3b3d302 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -501,12 +501,12 @@ static bool vmware_sev_es_hcall_finish(struct ghcb *ghcb, struct pt_regs *regs) ghcb_rbp_is_valid(ghcb))) return false; - regs->bx = ghcb->save.rbx; - regs->cx = ghcb->save.rcx; - regs->dx = ghcb->save.rdx; - regs->si = ghcb->save.rsi; - regs->di = ghcb->save.rdi; - regs->bp = ghcb->save.rbp; + regs->bx = ghcb_get_rbx(ghcb); + regs->cx = ghcb_get_rcx(ghcb); + regs->dx = ghcb_get_rdx(ghcb); + regs->si = ghcb_get_rsi(ghcb); + regs->di = ghcb_get_rdi(ghcb); + regs->bp = ghcb_get_rbp(ghcb); return true; } diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index 3492aa36bf09..6f7b8cc1bc9f 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -74,10 +74,9 @@ static ssize_t cpuid_read(struct file *file, char __user *buf, init_completion(&cmd.done); for (; count; count -= 16) { - call_single_data_t csd = { - .func = cpuid_smp_cpuid, - .info = &cmd, - }; + call_single_data_t csd; + + INIT_CSD(&csd, cpuid_smp_cpuid, &cmd); cmd.regs.eax = pos; cmd.regs.ecx = pos >> 32; diff --git a/arch/x86/kernel/crash_dump_32.c b/arch/x86/kernel/crash_dump_32.c index 33ee47670b99..5fcac46aaf6b 100644 --- a/arch/x86/kernel/crash_dump_32.c +++ b/arch/x86/kernel/crash_dump_32.c @@ -13,8 +13,6 @@ #include <linux/uaccess.h> -static void *kdump_buf_page; - static inline bool is_crashed_pfn_valid(unsigned long pfn) { #ifndef CONFIG_X86_PAE @@ -41,15 +39,11 @@ static inline bool is_crashed_pfn_valid(unsigned long pfn) * @userbuf: if set, @buf is in user address space, use copy_to_user(), * otherwise @buf is in kernel address space, use memcpy(). * - * Copy a page from "oldmem". For this page, there is no pte mapped - * in the current kernel. We stitch up a pte, similar to kmap_atomic. - * - * Calling copy_to_user() in atomic context is not desirable. Hence first - * copying the data to a pre-allocated kernel page and then copying to user - * space in non-atomic context. + * Copy a page from "oldmem". For this page, there might be no pte mapped + * in the current kernel. */ -ssize_t copy_oldmem_page(unsigned long pfn, char *buf, - size_t csize, unsigned long offset, int userbuf) +ssize_t copy_oldmem_page(unsigned long pfn, char *buf, size_t csize, + unsigned long offset, int userbuf) { void *vaddr; @@ -59,38 +53,16 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, if (!is_crashed_pfn_valid(pfn)) return -EFAULT; - vaddr = kmap_atomic_pfn(pfn); + vaddr = kmap_local_pfn(pfn); if (!userbuf) { - memcpy(buf, (vaddr + offset), csize); - kunmap_atomic(vaddr); + memcpy(buf, vaddr + offset, csize); } else { - if (!kdump_buf_page) { - printk(KERN_WARNING "Kdump: Kdump buffer page not" - " allocated\n"); - kunmap_atomic(vaddr); - return -EFAULT; - } - copy_page(kdump_buf_page, vaddr); - kunmap_atomic(vaddr); - if (copy_to_user(buf, (kdump_buf_page + offset), csize)) - return -EFAULT; + if (copy_to_user(buf, vaddr + offset, csize)) + csize = -EFAULT; } - return csize; -} + kunmap_local(vaddr); -static int __init kdump_buf_page_init(void) -{ - int ret = 0; - - kdump_buf_page = kmalloc(PAGE_SIZE, GFP_KERNEL); - if (!kdump_buf_page) { - printk(KERN_WARNING "Kdump: Failed to allocate kdump buffer" - " page\n"); - ret = -ENOMEM; - } - - return ret; + return csize; } -arch_initcall(kdump_buf_page_init); diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index ddffd80f5c52..6a4cb71c2498 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -184,31 +184,31 @@ static unsigned int ioapic_id; struct of_ioapic_type { u32 out_type; - u32 trigger; - u32 polarity; + u32 is_level; + u32 active_low; }; static struct of_ioapic_type of_ioapic_type[] = { { - .out_type = IRQ_TYPE_EDGE_RISING, - .trigger = IOAPIC_EDGE, - .polarity = 1, + .out_type = IRQ_TYPE_EDGE_FALLING, + .is_level = 0, + .active_low = 1, }, { - .out_type = IRQ_TYPE_LEVEL_LOW, - .trigger = IOAPIC_LEVEL, - .polarity = 0, + .out_type = IRQ_TYPE_LEVEL_HIGH, + .is_level = 1, + .active_low = 0, }, { - .out_type = IRQ_TYPE_LEVEL_HIGH, - .trigger = IOAPIC_LEVEL, - .polarity = 1, + .out_type = IRQ_TYPE_LEVEL_LOW, + .is_level = 1, + .active_low = 1, }, { - .out_type = IRQ_TYPE_EDGE_FALLING, - .trigger = IOAPIC_EDGE, - .polarity = 0, + .out_type = IRQ_TYPE_EDGE_RISING, + .is_level = 0, + .active_low = 0, }, }; @@ -228,7 +228,7 @@ static int dt_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, return -EINVAL; it = &of_ioapic_type[type_index]; - ioapic_set_alloc_attr(&tmp, NUMA_NO_NODE, it->trigger, it->polarity); + ioapic_set_alloc_attr(&tmp, NUMA_NO_NODE, it->is_level, it->active_low); tmp.devid = mpc_ioapic_id(mp_irqdomain_ioapic_idx(domain)); tmp.ioapic.pin = fwspec->param[0]; diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 25c06b67e7e0..299c20f0a38b 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -78,6 +78,9 @@ static int copy_code(struct pt_regs *regs, u8 *buf, unsigned long src, if (!user_mode(regs)) return copy_from_kernel_nofault(buf, (u8 *)src, nbytes); + /* The user space code from other tasks cannot be accessed. */ + if (regs != task_pt_regs(current)) + return -EPERM; /* * Make sure userspace isn't trying to trick us into dumping kernel * memory by pointing the userspace instruction pointer at it. @@ -85,6 +88,12 @@ static int copy_code(struct pt_regs *regs, u8 *buf, unsigned long src, if (__chk_range_not_ok(src, nbytes, TASK_SIZE_MAX)) return -EINVAL; + /* + * Even if named copy_from_user_nmi() this can be invoked from + * other contexts and will not try to resolve a pagefault, which is + * the correct thing to do here as this code can be called from any + * context. + */ return copy_from_user_nmi(buf, (void __user *)src, nbytes); } @@ -115,13 +124,19 @@ void show_opcodes(struct pt_regs *regs, const char *loglvl) u8 opcodes[OPCODE_BUFSIZE]; unsigned long prologue = regs->ip - PROLOGUE_SIZE; - if (copy_code(regs, opcodes, prologue, sizeof(opcodes))) { - printk("%sCode: Unable to access opcode bytes at RIP 0x%lx.\n", - loglvl, prologue); - } else { + switch (copy_code(regs, opcodes, prologue, sizeof(opcodes))) { + case 0: printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %" __stringify(EPILOGUE_SIZE) "ph\n", loglvl, opcodes, opcodes[PROLOGUE_SIZE], opcodes + PROLOGUE_SIZE + 1); + break; + case -EPERM: + /* No access to the user space stack of other tasks. Ignore. */ + break; + default: + printk("%sCode: Unable to access opcode bytes at RIP 0x%lx.\n", + loglvl, prologue); + break; } } @@ -168,7 +183,7 @@ static void show_regs_if_on_stack(struct stack_info *info, struct pt_regs *regs, } } -void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, +static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, unsigned long *stack, const char *log_lvl) { struct unwind_state state; diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index eb86a2b831b1..571220ac8bea 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -121,7 +121,7 @@ int copy_fpregs_to_fpstate(struct fpu *fpu) } EXPORT_SYMBOL(copy_fpregs_to_fpstate); -void kernel_fpu_begin(void) +void kernel_fpu_begin_mask(unsigned int kfpu_mask) { preempt_disable(); @@ -141,13 +141,14 @@ void kernel_fpu_begin(void) } __cpu_invalidate_fpregs_state(); - if (boot_cpu_has(X86_FEATURE_XMM)) + /* Put sane initial values into the control registers. */ + if (likely(kfpu_mask & KFPU_MXCSR) && boot_cpu_has(X86_FEATURE_XMM)) ldmxcsr(MXCSR_DEFAULT); - if (boot_cpu_has(X86_FEATURE_FPU)) + if (unlikely(kfpu_mask & KFPU_387) && boot_cpu_has(X86_FEATURE_FPU)) asm volatile ("fninit"); } -EXPORT_SYMBOL_GPL(kernel_fpu_begin); +EXPORT_SYMBOL_GPL(kernel_fpu_begin_mask); void kernel_fpu_end(void) { diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 5d8047441a0a..683749b80ae2 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -167,14 +167,14 @@ void fpstate_sanitize_xstate(struct fpu *fpu) fx->fop = 0; fx->rip = 0; fx->rdp = 0; - memset(&fx->st_space[0], 0, 128); + memset(fx->st_space, 0, sizeof(fx->st_space)); } /* * SSE is in init state */ if (!(xfeatures & XFEATURE_MASK_SSE)) - memset(&fx->xmm_space[0], 0, 256); + memset(fx->xmm_space, 0, sizeof(fx->xmm_space)); /* * First two features are FPU and SSE, which above we handled diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index ac3d5f22fe64..0d54099c2a3a 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -140,16 +140,27 @@ SYM_FUNC_START(ftrace_caller) /* save_mcount_regs fills in first two parameters */ save_mcount_regs + /* Stack - skipping return address of ftrace_caller */ + leaq MCOUNT_REG_SIZE+8(%rsp), %rcx + movq %rcx, RSP(%rsp) + SYM_INNER_LABEL(ftrace_caller_op_ptr, SYM_L_GLOBAL) /* Load the ftrace_ops into the 3rd parameter */ movq function_trace_op(%rip), %rdx - /* regs go into 4th parameter (but make it NULL) */ - movq $0, %rcx + /* regs go into 4th parameter */ + leaq (%rsp), %rcx + + /* Only ops with REGS flag set should have CS register set */ + movq $0, CS(%rsp) SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) call ftrace_stub + /* Handlers can change the RIP */ + movq RIP(%rsp), %rax + movq %rax, MCOUNT_REG_SIZE(%rsp) + restore_mcount_regs /* diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 4199f25c0063..5e9beb77cafd 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -37,7 +37,6 @@ #include <asm/kasan.h> #include <asm/fixmap.h> #include <asm/realmode.h> -#include <asm/desc.h> #include <asm/extable.h> #include <asm/trapnr.h> #include <asm/sev-es.h> @@ -84,7 +83,7 @@ static struct desc_ptr startup_gdt_descr = { .address = 0, }; -#define __head __section(.head.text) +#define __head __section(".head.text") static void __head *fixup_pointer(void *ptr, unsigned long physaddr) { diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 7eb2a1c87969..04bddaaba8e2 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -26,15 +26,6 @@ #include <asm/nospec-branch.h> #include <asm/fixmap.h> -#ifdef CONFIG_PARAVIRT_XXL -#include <asm/asm-offsets.h> -#include <asm/paravirt.h> -#define GET_CR2_INTO(reg) GET_CR2_INTO_AX ; _ASM_MOV %_ASM_AX, reg -#else -#define INTERRUPT_RETURN iretq -#define GET_CR2_INTO(reg) _ASM_MOV %cr2, reg -#endif - /* * We are not able to switch in one step to the final KERNEL ADDRESS SPACE * because we need identity-mapped pages. @@ -161,6 +152,21 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) /* Setup early boot stage 4-/5-level pagetables. */ addq phys_base(%rip), %rax + + /* + * For SEV guests: Verify that the C-bit is correct. A malicious + * hypervisor could lie about the C-bit position to perform a ROP + * attack on the guest by writing to the unencrypted stack and wait for + * the next RET instruction. + * %rsi carries pointer to realmode data and is callee-clobbered. Save + * and restore it. + */ + pushq %rsi + movq %rax, %rdi + call sev_verify_cbit + popq %rsi + + /* Switch to new page-table */ movq %rax, %cr3 /* Ensure I am executing from virtual addresses */ @@ -279,6 +285,7 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) SYM_CODE_END(secondary_startup_64) #include "verify_cpu.S" +#include "sev_verify_cbit.S" #ifdef CONFIG_HOTPLUG_CPU /* @@ -524,21 +531,19 @@ SYM_DATA_END(level3_kernel_pgt) SYM_DATA_START_PAGE_ALIGNED(level2_kernel_pgt) /* - * 512 MB kernel mapping. We spend a full page on this pagetable - * anyway. + * Kernel high mapping. * - * The kernel code+data+bss must not be bigger than that. + * The kernel code+data+bss must be located below KERNEL_IMAGE_SIZE in + * virtual address space, which is 1 GiB if RANDOMIZE_BASE is enabled, + * 512 MiB otherwise. * - * (NOTE: at +512MB starts the module area, see MODULES_VADDR. - * If you want to increase this then increase MODULES_VADDR - * too.) + * (NOTE: after that starts the module area, see MODULES_VADDR.) * - * This table is eventually used by the kernel during normal - * runtime. Care must be taken to clear out undesired bits - * later, like _PAGE_RW or _PAGE_GLOBAL in some cases. + * This table is eventually used by the kernel during normal runtime. + * Care must be taken to clear out undesired bits later, like _PAGE_RW + * or _PAGE_GLOBAL in some cases. */ - PMDS(0, __PAGE_KERNEL_LARGE_EXEC, - KERNEL_IMAGE_SIZE/PMD_SIZE) + PMDS(0, __PAGE_KERNEL_LARGE_EXEC, KERNEL_IMAGE_SIZE/PMD_SIZE) SYM_DATA_END(level2_kernel_pgt) SYM_DATA_START_PAGE_ALIGNED(level2_fixmap_pgt) diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 7a50f0b62a70..08651a4e6aa0 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -7,6 +7,7 @@ #include <linux/cpu.h> #include <linux/irq.h> +#include <asm/irq_remapping.h> #include <asm/hpet.h> #include <asm/time.h> @@ -50,7 +51,7 @@ unsigned long hpet_address; u8 hpet_blockid; /* OS timer block num */ bool hpet_msi_disable; -#ifdef CONFIG_PCI_MSI +#ifdef CONFIG_GENERIC_MSI_IRQ static DEFINE_PER_CPU(struct hpet_channel *, cpu_hpet_channel); static struct irq_domain *hpet_domain; #endif @@ -467,9 +468,8 @@ static void __init hpet_legacy_clockevent_register(struct hpet_channel *hc) /* * HPET MSI Support */ -#ifdef CONFIG_PCI_MSI - -void hpet_msi_unmask(struct irq_data *data) +#ifdef CONFIG_GENERIC_MSI_IRQ +static void hpet_msi_unmask(struct irq_data *data) { struct hpet_channel *hc = irq_data_get_irq_handler_data(data); unsigned int cfg; @@ -479,7 +479,7 @@ void hpet_msi_unmask(struct irq_data *data) hpet_writel(cfg, HPET_Tn_CFG(hc->num)); } -void hpet_msi_mask(struct irq_data *data) +static void hpet_msi_mask(struct irq_data *data) { struct hpet_channel *hc = irq_data_get_irq_handler_data(data); unsigned int cfg; @@ -489,12 +489,122 @@ void hpet_msi_mask(struct irq_data *data) hpet_writel(cfg, HPET_Tn_CFG(hc->num)); } -void hpet_msi_write(struct hpet_channel *hc, struct msi_msg *msg) +static void hpet_msi_write(struct hpet_channel *hc, struct msi_msg *msg) { hpet_writel(msg->data, HPET_Tn_ROUTE(hc->num)); hpet_writel(msg->address_lo, HPET_Tn_ROUTE(hc->num) + 4); } +static void hpet_msi_write_msg(struct irq_data *data, struct msi_msg *msg) +{ + hpet_msi_write(irq_data_get_irq_handler_data(data), msg); +} + +static struct irq_chip hpet_msi_controller __ro_after_init = { + .name = "HPET-MSI", + .irq_unmask = hpet_msi_unmask, + .irq_mask = hpet_msi_mask, + .irq_ack = irq_chip_ack_parent, + .irq_set_affinity = msi_domain_set_affinity, + .irq_retrigger = irq_chip_retrigger_hierarchy, + .irq_write_msi_msg = hpet_msi_write_msg, + .flags = IRQCHIP_SKIP_SET_WAKE, +}; + +static int hpet_msi_init(struct irq_domain *domain, + struct msi_domain_info *info, unsigned int virq, + irq_hw_number_t hwirq, msi_alloc_info_t *arg) +{ + irq_set_status_flags(virq, IRQ_MOVE_PCNTXT); + irq_domain_set_info(domain, virq, arg->hwirq, info->chip, NULL, + handle_edge_irq, arg->data, "edge"); + + return 0; +} + +static void hpet_msi_free(struct irq_domain *domain, + struct msi_domain_info *info, unsigned int virq) +{ + irq_clear_status_flags(virq, IRQ_MOVE_PCNTXT); +} + +static struct msi_domain_ops hpet_msi_domain_ops = { + .msi_init = hpet_msi_init, + .msi_free = hpet_msi_free, +}; + +static struct msi_domain_info hpet_msi_domain_info = { + .ops = &hpet_msi_domain_ops, + .chip = &hpet_msi_controller, + .flags = MSI_FLAG_USE_DEF_DOM_OPS, +}; + +static struct irq_domain *hpet_create_irq_domain(int hpet_id) +{ + struct msi_domain_info *domain_info; + struct irq_domain *parent, *d; + struct fwnode_handle *fn; + struct irq_fwspec fwspec; + + if (x86_vector_domain == NULL) + return NULL; + + domain_info = kzalloc(sizeof(*domain_info), GFP_KERNEL); + if (!domain_info) + return NULL; + + *domain_info = hpet_msi_domain_info; + domain_info->data = (void *)(long)hpet_id; + + fn = irq_domain_alloc_named_id_fwnode(hpet_msi_controller.name, + hpet_id); + if (!fn) { + kfree(domain_info); + return NULL; + } + + fwspec.fwnode = fn; + fwspec.param_count = 1; + fwspec.param[0] = hpet_id; + + parent = irq_find_matching_fwspec(&fwspec, DOMAIN_BUS_ANY); + if (!parent) { + irq_domain_free_fwnode(fn); + kfree(domain_info); + return NULL; + } + if (parent != x86_vector_domain) + hpet_msi_controller.name = "IR-HPET-MSI"; + + d = msi_create_irq_domain(fn, domain_info, parent); + if (!d) { + irq_domain_free_fwnode(fn); + kfree(domain_info); + } + return d; +} + +static inline int hpet_dev_id(struct irq_domain *domain) +{ + struct msi_domain_info *info = msi_get_domain_info(domain); + + return (int)(long)info->data; +} + +static int hpet_assign_irq(struct irq_domain *domain, struct hpet_channel *hc, + int dev_num) +{ + struct irq_alloc_info info; + + init_irq_alloc_info(&info, NULL); + info.type = X86_IRQ_ALLOC_TYPE_HPET; + info.data = hc; + info.devid = hpet_dev_id(domain); + info.hwirq = dev_num; + + return irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, &info); +} + static int hpet_clkevt_msi_resume(struct clock_event_device *evt) { struct hpet_channel *hc = clockevent_to_channel(evt); diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 03aa33b58165..668a4a6533d9 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -269,6 +269,20 @@ static inline bool within_cpu_entry(unsigned long addr, unsigned long end) CPU_ENTRY_AREA_TOTAL_SIZE)) return true; + /* + * When FSGSBASE is enabled, paranoid_entry() fetches the per-CPU + * GSBASE value via __per_cpu_offset or pcpu_unit_offsets. + */ +#ifdef CONFIG_SMP + if (within_area(addr, end, (unsigned long)__per_cpu_offset, + sizeof(unsigned long) * nr_cpu_ids)) + return true; +#else + if (within_area(addr, end, (unsigned long)&pcpu_unit_offsets, + sizeof(pcpu_unit_offsets))) + return true; +#endif + for_each_possible_cpu(cpu) { /* The original rw GDT is being used after load_direct_gdt() */ if (within_area(addr, end, (unsigned long)get_cpu_gdt_rw(cpu), @@ -293,6 +307,14 @@ static inline bool within_cpu_entry(unsigned long addr, unsigned long end) (unsigned long)&per_cpu(cpu_tlbstate, cpu), sizeof(struct tlb_state))) return true; + + /* + * When in guest (X86_FEATURE_HYPERVISOR), local_db_save() + * will read per-cpu cpu_dr7 before clear dr7 register. + */ + if (within_area(addr, end, (unsigned long)&per_cpu(cpu_dr7, cpu), + sizeof(cpu_dr7))) + return true; } return false; @@ -491,15 +513,12 @@ static int hw_breakpoint_handler(struct die_args *args) struct perf_event *bp; unsigned long *dr6_p; unsigned long dr6; + bool bpx; /* The DR6 value is pointed by args->err */ dr6_p = (unsigned long *)ERR_PTR(args->err); dr6 = *dr6_p; - /* If it's a single step, TRAP bits are random */ - if (dr6 & DR_STEP) - return NOTIFY_DONE; - /* Do an early return if no trap bits are set in DR6 */ if ((dr6 & DR_TRAP_BITS) == 0) return NOTIFY_DONE; @@ -509,28 +528,29 @@ static int hw_breakpoint_handler(struct die_args *args) if (likely(!(dr6 & (DR_TRAP0 << i)))) continue; + bp = this_cpu_read(bp_per_reg[i]); + if (!bp) + continue; + + bpx = bp->hw.info.type == X86_BREAKPOINT_EXECUTE; + /* - * The counter may be concurrently released but that can only - * occur from a call_rcu() path. We can then safely fetch - * the breakpoint, use its callback, touch its counter - * while we are in an rcu_read_lock() path. + * TF and data breakpoints are traps and can be merged, however + * instruction breakpoints are faults and will be raised + * separately. + * + * However DR6 can indicate both TF and instruction + * breakpoints. In that case take TF as that has precedence and + * delay the instruction breakpoint for the next exception. */ - rcu_read_lock(); + if (bpx && (dr6 & DR_STEP)) + continue; - bp = this_cpu_read(bp_per_reg[i]); /* * Reset the 'i'th TRAP bit in dr6 to denote completion of * exception handling */ (*dr6_p) &= ~(DR_TRAP0 << i); - /* - * bp can be NULL due to lazy debug register switching - * or due to concurrent perf counter removing. - */ - if (!bp) { - rcu_read_unlock(); - break; - } perf_bp_event(bp, args->regs); @@ -538,11 +558,10 @@ static int hw_breakpoint_handler(struct die_args *args) * Set up resume flag to avoid breakpoint recursion when * returning back to origin. */ - if (bp->hw.info.type == X86_BREAKPOINT_EXECUTE) + if (bpx) args->regs->flags |= X86_EFLAGS_RF; - - rcu_read_unlock(); } + /* * Further processing in do_debug() is needed for a) user-space * breakpoints (to generate signals) and b) when the system has diff --git a/arch/x86/kernel/ima_arch.c b/arch/x86/kernel/ima_arch.c deleted file mode 100644 index 7dfb1e808928..000000000000 --- a/arch/x86/kernel/ima_arch.c +++ /dev/null @@ -1,94 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ -/* - * Copyright (C) 2018 IBM Corporation - */ -#include <linux/efi.h> -#include <linux/module.h> -#include <linux/ima.h> - -extern struct boot_params boot_params; - -static enum efi_secureboot_mode get_sb_mode(void) -{ - efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID; - efi_status_t status; - unsigned long size; - u8 secboot, setupmode; - - size = sizeof(secboot); - - if (!efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE)) { - pr_info("ima: secureboot mode unknown, no efi\n"); - return efi_secureboot_mode_unknown; - } - - /* Get variable contents into buffer */ - status = efi.get_variable(L"SecureBoot", &efi_variable_guid, - NULL, &size, &secboot); - if (status == EFI_NOT_FOUND) { - pr_info("ima: secureboot mode disabled\n"); - return efi_secureboot_mode_disabled; - } - - if (status != EFI_SUCCESS) { - pr_info("ima: secureboot mode unknown\n"); - return efi_secureboot_mode_unknown; - } - - size = sizeof(setupmode); - status = efi.get_variable(L"SetupMode", &efi_variable_guid, - NULL, &size, &setupmode); - - if (status != EFI_SUCCESS) /* ignore unknown SetupMode */ - setupmode = 0; - - if (secboot == 0 || setupmode == 1) { - pr_info("ima: secureboot mode disabled\n"); - return efi_secureboot_mode_disabled; - } - - pr_info("ima: secureboot mode enabled\n"); - return efi_secureboot_mode_enabled; -} - -bool arch_ima_get_secureboot(void) -{ - static enum efi_secureboot_mode sb_mode; - static bool initialized; - - if (!initialized && efi_enabled(EFI_BOOT)) { - sb_mode = boot_params.secure_boot; - - if (sb_mode == efi_secureboot_mode_unset) - sb_mode = get_sb_mode(); - initialized = true; - } - - if (sb_mode == efi_secureboot_mode_enabled) - return true; - else - return false; -} - -/* secureboot arch rules */ -static const char * const sb_arch_rules[] = { -#if !IS_ENABLED(CONFIG_KEXEC_SIG) - "appraise func=KEXEC_KERNEL_CHECK appraise_type=imasig", -#endif /* CONFIG_KEXEC_SIG */ - "measure func=KEXEC_KERNEL_CHECK", -#if !IS_ENABLED(CONFIG_MODULE_SIG) - "appraise func=MODULE_CHECK appraise_type=imasig", -#endif - "measure func=MODULE_CHECK", - NULL -}; - -const char * const *arch_get_ima_policy(void) -{ - if (IS_ENABLED(CONFIG_IMA_ARCH_POLICY) && arch_ima_get_secureboot()) { - if (IS_ENABLED(CONFIG_MODULE_SIG)) - set_module_sig_enforced(); - return sb_arch_rules; - } - return NULL; -} diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index c5dd50369e2f..d4ad344e80bf 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -21,6 +21,7 @@ #include <asm/hw_irq.h> #include <asm/desc.h> #include <asm/traps.h> +#include <asm/thermal.h> #define CREATE_TRACE_POINTS #include <asm/trace/irq_vectors.h> @@ -374,3 +375,23 @@ void fixup_irqs(void) } } #endif + +#ifdef CONFIG_X86_THERMAL_VECTOR +static void smp_thermal_vector(void) +{ + if (x86_thermal_enabled()) + intel_thermal_interrupt(); + else + pr_err("CPU%d: Unexpected LVT thermal interrupt!\n", + smp_processor_id()); +} + +DEFINE_IDTENTRY_SYSVEC(sysvec_thermal) +{ + trace_thermal_apic_entry(THERMAL_APIC_VECTOR); + inc_irq_stat(irq_thermal_count); + smp_thermal_vector(); + trace_thermal_apic_exit(THERMAL_APIC_VECTOR); + ack_APIC_irq(); +} +#endif diff --git a/arch/x86/kernel/irqflags.S b/arch/x86/kernel/irqflags.S index 0db0375235b4..8ef35063964b 100644 --- a/arch/x86/kernel/irqflags.S +++ b/arch/x86/kernel/irqflags.S @@ -13,14 +13,3 @@ SYM_FUNC_START(native_save_fl) ret SYM_FUNC_END(native_save_fl) EXPORT_SYMBOL(native_save_fl) - -/* - * void native_restore_fl(unsigned long flags) - * %eax/%rdi: flags - */ -SYM_FUNC_START(native_restore_fl) - push %_ASM_ARG1 - popf - ret -SYM_FUNC_END(native_restore_fl) -EXPORT_SYMBOL(native_restore_fl) diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 57c2ecf43134..ce831f9448e7 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -200,8 +200,7 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params, params->hdr.hardware_subarch = boot_params.hdr.hardware_subarch; /* Copying screen_info will do? */ - memcpy(¶ms->screen_info, &boot_params.screen_info, - sizeof(struct screen_info)); + memcpy(¶ms->screen_info, &screen_info, sizeof(struct screen_info)); /* Fill in memsize later */ params->screen_info.ext_mem_k = 0; diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 547c7abb39f5..df776cdca327 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -133,26 +133,6 @@ void synthesize_relcall(void *dest, void *from, void *to) NOKPROBE_SYMBOL(synthesize_relcall); /* - * Skip the prefixes of the instruction. - */ -static kprobe_opcode_t *skip_prefixes(kprobe_opcode_t *insn) -{ - insn_attr_t attr; - - attr = inat_get_opcode_attribute((insn_byte_t)*insn); - while (inat_is_legacy_prefix(attr)) { - insn++; - attr = inat_get_opcode_attribute((insn_byte_t)*insn); - } -#ifdef CONFIG_X86_64 - if (inat_is_rex_prefix(attr)) - insn++; -#endif - return insn; -} -NOKPROBE_SYMBOL(skip_prefixes); - -/* * Returns non-zero if INSN is boostable. * RIP relative instructions are adjusted at copying time in 64 bits mode */ @@ -312,25 +292,6 @@ static int can_probe(unsigned long paddr) } /* - * Returns non-zero if opcode modifies the interrupt flag. - */ -static int is_IF_modifier(kprobe_opcode_t *insn) -{ - /* Skip prefixes */ - insn = skip_prefixes(insn); - - switch (*insn) { - case 0xfa: /* cli */ - case 0xfb: /* sti */ - case 0xcf: /* iret/iretd */ - case 0x9d: /* popf/popfd */ - return 1; - } - - return 0; -} - -/* * Copy an instruction with recovering modified instruction by kprobes * and adjust the displacement if the instruction uses the %rip-relative * addressing mode. Note that since @real will be the final place of copied @@ -411,9 +372,9 @@ static int prepare_boost(kprobe_opcode_t *buf, struct kprobe *p, synthesize_reljump(buf + len, p->ainsn.insn + len, p->addr + insn->length); len += JMP32_INSN_SIZE; - p->ainsn.boostable = true; + p->ainsn.boostable = 1; } else { - p->ainsn.boostable = false; + p->ainsn.boostable = 0; } return len; @@ -450,6 +411,67 @@ void free_insn_page(void *page) module_memfree(page); } +static void set_resume_flags(struct kprobe *p, struct insn *insn) +{ + insn_byte_t opcode = insn->opcode.bytes[0]; + + switch (opcode) { + case 0xfa: /* cli */ + case 0xfb: /* sti */ + case 0x9d: /* popf/popfd */ + /* Check whether the instruction modifies Interrupt Flag or not */ + p->ainsn.if_modifier = 1; + break; + case 0x9c: /* pushfl */ + p->ainsn.is_pushf = 1; + break; + case 0xcf: /* iret */ + p->ainsn.if_modifier = 1; + fallthrough; + case 0xc2: /* ret/lret */ + case 0xc3: + case 0xca: + case 0xcb: + case 0xea: /* jmp absolute -- ip is correct */ + /* ip is already adjusted, no more changes required */ + p->ainsn.is_abs_ip = 1; + /* Without resume jump, this is boostable */ + p->ainsn.boostable = 1; + break; + case 0xe8: /* call relative - Fix return addr */ + p->ainsn.is_call = 1; + break; +#ifdef CONFIG_X86_32 + case 0x9a: /* call absolute -- same as call absolute, indirect */ + p->ainsn.is_call = 1; + p->ainsn.is_abs_ip = 1; + break; +#endif + case 0xff: + opcode = insn->opcode.bytes[1]; + if ((opcode & 0x30) == 0x10) { + /* + * call absolute, indirect + * Fix return addr; ip is correct. + * But this is not boostable + */ + p->ainsn.is_call = 1; + p->ainsn.is_abs_ip = 1; + break; + } else if (((opcode & 0x31) == 0x20) || + ((opcode & 0x31) == 0x21)) { + /* + * jmp near and far, absolute indirect + * ip is correct. + */ + p->ainsn.is_abs_ip = 1; + /* Without resume jump, this is boostable */ + p->ainsn.boostable = 1; + } + break; + } +} + static int arch_copy_kprobe(struct kprobe *p) { struct insn insn; @@ -467,8 +489,8 @@ static int arch_copy_kprobe(struct kprobe *p) */ len = prepare_boost(buf, p, &insn); - /* Check whether the instruction modifies Interrupt Flag or not */ - p->ainsn.if_modifier = is_IF_modifier(buf); + /* Analyze the opcode and set resume flags */ + set_resume_flags(p, &insn); /* Also, displacement change doesn't affect the first byte */ p->opcode = buf[0]; @@ -491,6 +513,9 @@ int arch_prepare_kprobe(struct kprobe *p) if (!can_probe((unsigned long)p->addr)) return -EILSEQ; + + memset(&p->ainsn, 0, sizeof(p->ainsn)); + /* insn: must be on special executable page on x86. */ p->ainsn.insn = get_insn_slot(); if (!p->ainsn.insn) @@ -806,11 +831,6 @@ NOKPROBE_SYMBOL(trampoline_handler); * 2) If the single-stepped instruction was a call, the return address * that is atop the stack is the address following the copied instruction. * We need to make it the address following the original instruction. - * - * If this is the first time we've single-stepped the instruction at - * this probepoint, and the instruction is boostable, boost it: add a - * jump instruction after the copied instruction, that jumps to the next - * instruction after the probepoint. */ static void resume_execution(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) @@ -818,59 +838,20 @@ static void resume_execution(struct kprobe *p, struct pt_regs *regs, unsigned long *tos = stack_addr(regs); unsigned long copy_ip = (unsigned long)p->ainsn.insn; unsigned long orig_ip = (unsigned long)p->addr; - kprobe_opcode_t *insn = p->ainsn.insn; - - /* Skip prefixes */ - insn = skip_prefixes(insn); regs->flags &= ~X86_EFLAGS_TF; - switch (*insn) { - case 0x9c: /* pushfl */ + + /* Fixup the contents of top of stack */ + if (p->ainsn.is_pushf) { *tos &= ~(X86_EFLAGS_TF | X86_EFLAGS_IF); *tos |= kcb->kprobe_old_flags; - break; - case 0xc2: /* iret/ret/lret */ - case 0xc3: - case 0xca: - case 0xcb: - case 0xcf: - case 0xea: /* jmp absolute -- ip is correct */ - /* ip is already adjusted, no more changes required */ - p->ainsn.boostable = true; - goto no_change; - case 0xe8: /* call relative - Fix return addr */ + } else if (p->ainsn.is_call) { *tos = orig_ip + (*tos - copy_ip); - break; -#ifdef CONFIG_X86_32 - case 0x9a: /* call absolute -- same as call absolute, indirect */ - *tos = orig_ip + (*tos - copy_ip); - goto no_change; -#endif - case 0xff: - if ((insn[1] & 0x30) == 0x10) { - /* - * call absolute, indirect - * Fix return addr; ip is correct. - * But this is not boostable - */ - *tos = orig_ip + (*tos - copy_ip); - goto no_change; - } else if (((insn[1] & 0x31) == 0x20) || - ((insn[1] & 0x31) == 0x21)) { - /* - * jmp near and far, absolute indirect - * ip is correct. And this is boostable - */ - p->ainsn.boostable = true; - goto no_change; - } - default: - break; } - regs->ip += orig_ip - copy_ip; + if (!p->ainsn.is_abs_ip) + regs->ip += orig_ip - copy_ip; -no_change: restore_btf(); } NOKPROBE_SYMBOL(resume_execution); @@ -937,6 +918,11 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr) * So clear it by resetting the current kprobe: */ regs->flags &= ~X86_EFLAGS_TF; + /* + * Since the single step (trap) has been cancelled, + * we need to restore BTF here. + */ + restore_btf(); /* * If the TF flag was set before the kprobe hit, diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c index 681a4b36e9bb..373e5fa3ce1f 100644 --- a/arch/x86/kernel/kprobes/ftrace.c +++ b/arch/x86/kernel/kprobes/ftrace.c @@ -14,15 +14,21 @@ /* 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 ftrace_ops *ops, struct ftrace_regs *fregs) { + struct pt_regs *regs = ftrace_get_regs(fregs); struct kprobe *p; struct kprobe_ctlblk *kcb; + int bit; - /* Preempt is disabled by ftrace */ + bit = ftrace_test_recursion_trylock(ip, parent_ip); + if (bit < 0) + return; + + preempt_disable_notrace(); p = get_kprobe((kprobe_opcode_t *)ip); if (unlikely(!p) || kprobe_disabled(p)) - return; + goto out; kcb = get_kprobe_ctlblk(); if (kprobe_running()) { @@ -52,6 +58,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, */ __this_cpu_write(current_kprobe, NULL); } +out: + preempt_enable_notrace(); + ftrace_test_recursion_unlock(bit); } NOKPROBE_SYMBOL(kprobe_ftrace_handler); diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 041f0b50bc27..08eb23074f92 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -272,6 +272,19 @@ static int insn_is_indirect_jump(struct insn *insn) return ret; } +static bool is_padding_int3(unsigned long addr, unsigned long eaddr) +{ + unsigned char ops; + + for (; addr < eaddr; addr++) { + if (get_kernel_nofault(ops, (void *)addr) < 0 || + ops != INT3_INSN_OPCODE) + return false; + } + + return true; +} + /* Decode whole function to ensure any instructions don't jump into target */ static int can_optimize(unsigned long paddr) { @@ -310,9 +323,14 @@ static int can_optimize(unsigned long paddr) return 0; kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE); insn_get_length(&insn); - /* Another subsystem puts a breakpoint */ + /* + * In the case of detecting unknown breakpoint, this could be + * a padding INT3 between functions. Let's check that all the + * rest of the bytes are also INT3. + */ if (insn.opcode.bytes[0] == INT3_INSN_OPCODE) - return 0; + return is_padding_int3(addr, paddr - offset + size) ? 1 : 0; + /* Recover address */ insn.kaddr = (void *)addr; insn.next_byte = (void *)(addr + insn.length); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 1c0f2560a41c..5e78e01ca3b4 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -740,6 +740,11 @@ static void __init kvm_apic_init(void) #endif } +static bool __init kvm_msi_ext_dest_id(void) +{ + return kvm_para_has_feature(KVM_FEATURE_MSI_EXT_DEST_ID); +} + static void __init kvm_init_platform(void) { kvmclock_init(); @@ -769,6 +774,7 @@ const __initconst struct hypervisor_x86 x86_hyper_kvm = { .type = X86_HYPER_KVM, .init.guest_late_init = kvm_guest_init, .init.x2apic_available = kvm_para_available, + .init.msi_ext_dest_id = kvm_msi_ext_dest_id, .init.init_platform = kvm_init_platform, #if defined(CONFIG_AMD_MEM_ENCRYPT) .runtime.sev_es_hcall_prepare = kvm_sev_es_hcall_prepare, @@ -975,7 +981,7 @@ void arch_haltpoll_disable(unsigned int cpu) if (!kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL)) return; - /* Enable guest halt poll disables host halt poll */ + /* Disable guest halt poll enables host halt poll */ smp_call_function_single(cpu, kvm_enable_host_haltpoll, NULL, 1); } EXPORT_SYMBOL_GPL(arch_haltpoll_disable); diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 34b18f6eeb2c..aa593743acf6 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -44,7 +44,6 @@ static int __init parse_no_kvmclock_vsyscall(char *arg) early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall); /* Aligned to page sizes to match whats mapped via vsyscalls to userspace */ -#define HV_CLOCK_SIZE (sizeof(struct pvclock_vsyscall_time_info) * NR_CPUS) #define HVC_BOOT_ARRAY_SIZE \ (PAGE_SIZE / sizeof(struct pvclock_vsyscall_time_info)) diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index b8aee71840ae..aa15132228da 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -398,9 +398,15 @@ static void free_ldt_pgtables(struct mm_struct *mm) if (!boot_cpu_has(X86_FEATURE_PTI)) return; - tlb_gather_mmu(&tlb, mm, start, end); + /* + * Although free_pgd_range() is intended for freeing user + * page-tables, it also works out for kernel mappings on x86. + * We use tlb_gather_mmu_fullmm() to avoid confusing the + * range-tracking logic in __tlb_adjust_range(). + */ + tlb_gather_mmu_fullmm(&tlb, mm); free_pgd_range(&tlb, start, end, start, end); - tlb_finish_mmu(&tlb, start, end); + tlb_finish_mmu(&tlb); #endif } diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 34b153cbd4ac..5e9a34b5bd74 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -114,6 +114,7 @@ int apply_relocate(Elf32_Shdr *sechdrs, *location += sym->st_value; break; case R_386_PC32: + case R_386_PLT32: /* Add the value, subtract its position */ *location += sym->st_value - (uint32_t)location; break; diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index c0d409810658..ed8ac6bcbafb 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -99,11 +99,9 @@ static int filter_write(u32 reg) if (!__ratelimit(&fw_rs)) return 0; - if (reg == MSR_IA32_ENERGY_PERF_BIAS) - return 0; - - pr_err("Write to unrecognized MSR 0x%x by %s (pid: %d). Please report to [email protected].\n", - reg, current->comm, current->pid); + pr_warn("Write to unrecognized MSR 0x%x by %s (pid: %d).\n", + reg, current->comm, current->pid); + pr_warn("See https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git/about for details.\n"); return 0; } @@ -184,6 +182,13 @@ static long msr_ioctl(struct file *file, unsigned int ioc, unsigned long arg) err = security_locked_down(LOCKDOWN_MSR); if (err) break; + + err = filter_write(regs[1]); + if (err) + return err; + + add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK); + err = wrmsr_safe_regs_on_cpu(cpu, regs); if (err) break; diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 4bc77aaf1303..bf250a339655 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -475,7 +475,7 @@ static DEFINE_PER_CPU(unsigned long, nmi_dr7); DEFINE_IDTENTRY_RAW(exc_nmi) { - bool irq_state; + irqentry_state_t irq_state; /* * Re-enable NMIs right here when running as an SEV-ES guest. This might @@ -502,14 +502,14 @@ nmi_restart: this_cpu_write(nmi_dr7, local_db_save()); - irq_state = idtentry_enter_nmi(regs); + irq_state = irqentry_nmi_enter(regs); inc_irq_stat(__nmi_count); if (!ignore_nmis) default_do_nmi(regs); - idtentry_exit_nmi(regs, irq_state); + irqentry_nmi_exit(regs, irq_state); local_db_restore(this_cpu_read(nmi_dr7)); diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 6c3407ba6ee9..c60222ab8ab9 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -135,8 +135,7 @@ unsigned paravirt_patch_default(u8 type, void *insn_buff, else if (opfunc == _paravirt_ident_64) ret = paravirt_patch_ident_64(insn_buff, len); - else if (type == PARAVIRT_PATCH(cpu.iret) || - type == PARAVIRT_PATCH(cpu.usergs_sysret64)) + else if (type == PARAVIRT_PATCH(cpu.iret)) /* If operation requires a jmp, then jmp */ ret = paravirt_patch_jmp(insn_buff, opfunc, addr, len); #endif @@ -170,7 +169,6 @@ static u64 native_steal_clock(int cpu) /* These are in entry.S */ extern void native_iret(void); -extern void native_usergs_sysret64(void); static struct resource reserve_ioports = { .start = 0, @@ -310,9 +308,7 @@ struct paravirt_patch_template pv_ops = { .cpu.load_sp0 = native_load_sp0, - .cpu.usergs_sysret64 = native_usergs_sysret64, .cpu.iret = native_iret, - .cpu.swapgs = native_swapgs, #ifdef CONFIG_X86_IOPL_IOPERM .cpu.invalidate_io_bitmap = native_tss_invalidate_io_bitmap, @@ -324,7 +320,6 @@ struct paravirt_patch_template pv_ops = { /* Irq ops. */ .irq.save_fl = __PV_IS_CALLEE_SAVE(native_save_fl), - .irq.restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl), .irq.irq_disable = __PV_IS_CALLEE_SAVE(native_irq_disable), .irq.irq_enable = __PV_IS_CALLEE_SAVE(native_irq_enable), .irq.safe_halt = native_safe_halt, diff --git a/arch/x86/kernel/paravirt_patch.c b/arch/x86/kernel/paravirt_patch.c index ace6e334cb39..abd27ec67397 100644 --- a/arch/x86/kernel/paravirt_patch.c +++ b/arch/x86/kernel/paravirt_patch.c @@ -25,10 +25,7 @@ struct patch_xxl { const unsigned char mmu_read_cr2[3]; const unsigned char mmu_read_cr3[3]; const unsigned char mmu_write_cr3[3]; - const unsigned char irq_restore_fl[2]; const unsigned char cpu_wbinvd[2]; - const unsigned char cpu_usergs_sysret64[6]; - const unsigned char cpu_swapgs[3]; const unsigned char mov64[3]; }; @@ -39,11 +36,7 @@ static const struct patch_xxl patch_data_xxl = { .mmu_read_cr2 = { 0x0f, 0x20, 0xd0 }, // mov %cr2, %[re]ax .mmu_read_cr3 = { 0x0f, 0x20, 0xd8 }, // mov %cr3, %[re]ax .mmu_write_cr3 = { 0x0f, 0x22, 0xdf }, // mov %rdi, %cr3 - .irq_restore_fl = { 0x57, 0x9d }, // push %rdi; popfq .cpu_wbinvd = { 0x0f, 0x09 }, // wbinvd - .cpu_usergs_sysret64 = { 0x0f, 0x01, 0xf8, - 0x48, 0x0f, 0x07 }, // swapgs; sysretq - .cpu_swapgs = { 0x0f, 0x01, 0xf8 }, // swapgs .mov64 = { 0x48, 0x89, 0xf8 }, // mov %rdi, %rax }; @@ -76,7 +69,6 @@ unsigned int native_patch(u8 type, void *insn_buff, unsigned long addr, switch (type) { #ifdef CONFIG_PARAVIRT_XXL - PATCH_CASE(irq, restore_fl, xxl, insn_buff, len); PATCH_CASE(irq, save_fl, xxl, insn_buff, len); PATCH_CASE(irq, irq_enable, xxl, insn_buff, len); PATCH_CASE(irq, irq_disable, xxl, insn_buff, len); @@ -85,8 +77,6 @@ unsigned int native_patch(u8 type, void *insn_buff, unsigned long addr, PATCH_CASE(mmu, read_cr3, xxl, insn_buff, len); PATCH_CASE(mmu, write_cr3, xxl, insn_buff, len); - PATCH_CASE(cpu, usergs_sysret64, xxl, insn_buff, len); - PATCH_CASE(cpu, swapgs, xxl, insn_buff, len); PATCH_CASE(cpu, wbinvd, xxl, insn_buff, len); #endif diff --git a/arch/x86/kernel/pci-iommu_table.c b/arch/x86/kernel/pci-iommu_table.c index 2e9006c1e240..42e92ec62973 100644 --- a/arch/x86/kernel/pci-iommu_table.c +++ b/arch/x86/kernel/pci-iommu_table.c @@ -4,9 +4,6 @@ #include <linux/string.h> #include <linux/kallsyms.h> - -#define DEBUG 1 - static struct iommu_table_entry * __init find_dependents_of(struct iommu_table_entry *start, struct iommu_table_entry *finish, diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c index bb7e1132290b..624703af80a1 100644 --- a/arch/x86/kernel/perf_regs.c +++ b/arch/x86/kernel/perf_regs.c @@ -101,8 +101,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = perf_reg_abi(current); @@ -123,18 +122,26 @@ int perf_reg_validate(u64 mask) u64 perf_reg_abi(struct task_struct *task) { - if (test_tsk_thread_flag(task, TIF_IA32)) + if (!user_64bit_mode(task_pt_regs(task))) return PERF_SAMPLE_REGS_ABI_32; else return PERF_SAMPLE_REGS_ABI_64; } +static DEFINE_PER_CPU(struct pt_regs, nmi_user_regs); + void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { + struct pt_regs *regs_user_copy = this_cpu_ptr(&nmi_user_regs); struct pt_regs *user_regs = task_pt_regs(current); + if (!in_nmi()) { + regs_user->regs = user_regs; + regs_user->abi = perf_reg_abi(current); + return; + } + /* * If we're in an NMI that interrupted task_pt_regs setup, then * we can't sample user regs at all. This check isn't really diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index ba4593a913fa..145a7ac0c19a 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -685,7 +685,7 @@ void arch_cpu_idle(void) */ void __cpuidle default_idle(void) { - safe_halt(); + raw_safe_halt(); } #if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE) EXPORT_SYMBOL(default_idle); @@ -736,6 +736,8 @@ void stop_this_cpu(void *dummy) /* * AMD Erratum 400 aware idle routine. We handle it the same way as C3 power * states (local apic timer and TSC stop). + * + * XXX this function is completely buggered vs RCU and tracing. */ static void amd_e400_idle(void) { @@ -757,9 +759,9 @@ static void amd_e400_idle(void) * The switch back from broadcast mode needs to be called with * interrupts disabled. */ - local_irq_disable(); + raw_local_irq_disable(); tick_broadcast_exit(); - local_irq_enable(); + raw_local_irq_enable(); } /* @@ -801,9 +803,9 @@ static __cpuidle void mwait_idle(void) if (!need_resched()) __sti_mwait(0, 0); else - local_irq_enable(); + raw_local_irq_enable(); } else { - local_irq_enable(); + raw_local_irq_enable(); } __current_clr_polling(); } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index df342bedea88..ad582f9ac5a6 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -511,11 +511,10 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) EXPORT_SYMBOL_GPL(start_thread); #ifdef CONFIG_COMPAT -void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp) +void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp, bool x32) { start_thread_common(regs, new_ip, new_sp, - test_thread_flag(TIF_X32) - ? __USER_CS : __USER32_CS, + x32 ? __USER_CS : __USER32_CS, __USER_DS, __USER_DS); } #endif @@ -641,16 +640,12 @@ void set_personality_64bit(void) /* inherit personality from parent */ /* Make sure to be in 64bit mode */ - clear_thread_flag(TIF_IA32); clear_thread_flag(TIF_ADDR32); - clear_thread_flag(TIF_X32); /* Pretend that this comes from a 64bit execve */ task_pt_regs(current)->orig_ax = __NR_execve; current_thread_info()->status &= ~TS_COMPAT; - - /* Ensure the corresponding mm is not marked. */ if (current->mm) - current->mm->context.ia32_compat = 0; + current->mm->context.flags = MM_CONTEXT_HAS_VSYSCALL; /* TBD: overwrites user setup. Should have two bits. But 64bit processes have always behaved this way, @@ -662,10 +657,9 @@ void set_personality_64bit(void) static void __set_personality_x32(void) { #ifdef CONFIG_X86_X32 - clear_thread_flag(TIF_IA32); - set_thread_flag(TIF_X32); if (current->mm) - current->mm->context.ia32_compat = TIF_X32; + current->mm->context.flags = 0; + current->personality &= ~READ_IMPLIES_EXEC; /* * in_32bit_syscall() uses the presence of the x32 syscall bit @@ -683,10 +677,14 @@ static void __set_personality_x32(void) static void __set_personality_ia32(void) { #ifdef CONFIG_IA32_EMULATION - set_thread_flag(TIF_IA32); - clear_thread_flag(TIF_X32); - if (current->mm) - current->mm->context.ia32_compat = TIF_IA32; + if (current->mm) { + /* + * uprobes applied to this MM need to know this and + * cannot use user_64bit_mode() at that time. + */ + current->mm->context.flags = MM_CONTEXT_UPROBE_IA32; + } + current->personality |= force_personality32; /* Prepare the first "return" to user space */ task_pt_regs(current)->orig_ax = __NR_ia32_execve; diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index bedca011459c..87a4143aa7d7 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -704,6 +704,9 @@ void ptrace_disable(struct task_struct *child) #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION static const struct user_regset_view user_x86_32_view; /* Initialized below. */ #endif +#ifdef CONFIG_X86_64 +static const struct user_regset_view user_x86_64_view; /* Initialized below. */ +#endif long arch_ptrace(struct task_struct *child, long request, unsigned long addr, unsigned long data) @@ -711,6 +714,14 @@ long arch_ptrace(struct task_struct *child, long request, int ret; unsigned long __user *datap = (unsigned long __user *)data; +#ifdef CONFIG_X86_64 + /* This is native 64-bit ptrace() */ + const struct user_regset_view *regset_view = &user_x86_64_view; +#else + /* This is native 32-bit ptrace() */ + const struct user_regset_view *regset_view = &user_x86_32_view; +#endif + switch (request) { /* read the word at location addr in the USER area. */ case PTRACE_PEEKUSR: { @@ -749,28 +760,28 @@ long arch_ptrace(struct task_struct *child, long request, case PTRACE_GETREGS: /* Get all gp regs from the child. */ return copy_regset_to_user(child, - task_user_regset_view(current), + regset_view, REGSET_GENERAL, 0, sizeof(struct user_regs_struct), datap); case PTRACE_SETREGS: /* Set all gp regs in the child. */ return copy_regset_from_user(child, - task_user_regset_view(current), + regset_view, REGSET_GENERAL, 0, sizeof(struct user_regs_struct), datap); case PTRACE_GETFPREGS: /* Get the child FPU state. */ return copy_regset_to_user(child, - task_user_regset_view(current), + regset_view, REGSET_FP, 0, sizeof(struct user_i387_struct), datap); case PTRACE_SETFPREGS: /* Set the child FPU state. */ return copy_regset_from_user(child, - task_user_regset_view(current), + regset_view, REGSET_FP, 0, sizeof(struct user_i387_struct), datap); @@ -1152,28 +1163,28 @@ static long x32_arch_ptrace(struct task_struct *child, case PTRACE_GETREGS: /* Get all gp regs from the child. */ return copy_regset_to_user(child, - task_user_regset_view(current), + &user_x86_64_view, REGSET_GENERAL, 0, sizeof(struct user_regs_struct), datap); case PTRACE_SETREGS: /* Set all gp regs in the child. */ return copy_regset_from_user(child, - task_user_regset_view(current), + &user_x86_64_view, REGSET_GENERAL, 0, sizeof(struct user_regs_struct), datap); case PTRACE_GETFPREGS: /* Get the child FPU state. */ return copy_regset_to_user(child, - task_user_regset_view(current), + &user_x86_64_view, REGSET_FP, 0, sizeof(struct user_i387_struct), datap); case PTRACE_SETFPREGS: /* Set the child FPU state. */ return copy_regset_from_user(child, - task_user_regset_view(current), + &user_x86_64_view, REGSET_FP, 0, sizeof(struct user_i387_struct), datap); @@ -1309,6 +1320,25 @@ void __init update_regset_xstate_info(unsigned int size, u64 xstate_mask) xstate_fx_sw_bytes[USER_XSTATE_XCR0_WORD] = xstate_mask; } +/* + * This is used by the core dump code to decide which regset to dump. The + * core dump code writes out the resulting .e_machine and the corresponding + * regsets. This is suboptimal if the task is messing around with its CS.L + * field, but at worst the core dump will end up missing some information. + * + * Unfortunately, it is also used by the broken PTRACE_GETREGSET and + * PTRACE_SETREGSET APIs. These APIs look at the .regsets field but have + * no way to make sure that the e_machine they use matches the caller's + * expectations. The result is that the data format returned by + * PTRACE_GETREGSET depends on the returned CS field (and even the offset + * of the returned CS field depends on its value!) and the data format + * accepted by PTRACE_SETREGSET is determined by the old CS value. The + * upshot is that it is basically impossible to use these APIs correctly. + * + * The best way to fix it in the long run would probably be to add new + * improved ptrace() APIs to read and write registers reliably, possibly by + * allowing userspace to select the ELF e_machine variant that they expect. + */ const struct user_regset_view *task_user_regset_view(struct task_struct *task) { #ifdef CONFIG_IA32_EMULATION diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index db115943e8bd..b29657b76e3f 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -477,6 +477,15 @@ static const struct dmi_system_id reboot_dmi_table[] __initconst = { }, }, + { /* PCIe Wifi card isn't detected after reboot otherwise */ + .callback = set_pci_reboot, + .ident = "Zotac ZBOX CI327 nano", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "NA"), + DMI_MATCH(DMI_PRODUCT_NAME, "ZBOX-CI327NANO-GS-01"), + }, + }, + /* Sony */ { /* Handle problems with rebooting on Sony VGN-Z540N */ .callback = set_bios_reboot, @@ -538,31 +547,21 @@ static void emergency_vmx_disable_all(void) local_irq_disable(); /* - * We need to disable VMX on all CPUs before rebooting, otherwise - * we risk hanging up the machine, because the CPU ignores INIT - * signals when VMX is enabled. - * - * We can't take any locks and we may be on an inconsistent - * state, so we use NMIs as IPIs to tell the other CPUs to disable - * VMX and halt. + * Disable VMX on all CPUs before rebooting, otherwise we risk hanging + * the machine, because the CPU blocks INIT when it's in VMX root. * - * For safety, we will avoid running the nmi_shootdown_cpus() - * stuff unnecessarily, but we don't have a way to check - * if other CPUs have VMX enabled. So we will call it only if the - * CPU we are running on has VMX enabled. + * We can't take any locks and we may be on an inconsistent state, so + * use NMIs as IPIs to tell the other CPUs to exit VMX root and halt. * - * We will miss cases where VMX is not enabled on all CPUs. This - * shouldn't do much harm because KVM always enable VMX on all - * CPUs anyway. But we can miss it on the small window where KVM - * is still enabling VMX. + * Do the NMI shootdown even if VMX if off on _this_ CPU, as that + * doesn't prevent a different CPU from being in VMX root operation. */ - if (cpu_has_vmx() && cpu_vmx_enabled()) { - /* Disable VMX on this CPU. */ - cpu_vmxoff(); + if (cpu_has_vmx()) { + /* Safely force _this_ CPU out of VMX root operation. */ + __cpu_emergency_vmxoff(); - /* Halt and disable VMX on the other CPUs */ + /* Halt and exit VMX root operation on the other CPUs. */ nmi_shootdown_cpus(vmxoff_nmi); - } } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 84f581c91db4..740f3bdb3f61 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -119,11 +119,6 @@ EXPORT_SYMBOL(boot_cpu_data); unsigned int def_to_bigsmp; -/* For MCA, but anyone else can use it if they want */ -unsigned int machine_id; -unsigned int machine_submodel_id; -unsigned int BIOS_revision; - struct apm_info apm_info; EXPORT_SYMBOL(apm_info); @@ -1054,6 +1049,12 @@ void __init setup_arch(char **cmdline_p) memblock_set_current_limit(ISA_END_ADDRESS); e820__memblock_setup(); + /* + * Needs to run after memblock setup because it needs the physical + * memory size. + */ + sev_setup_arch(); + reserve_bios_regions(); efi_fake_memmap(); diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c index 5f83ccaab877..cdc04d091242 100644 --- a/arch/x86/kernel/sev-es-shared.c +++ b/arch/x86/kernel/sev-es-shared.c @@ -178,6 +178,32 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) goto fail; regs->dx = val >> 32; + /* + * This is a VC handler and the #VC is only raised when SEV-ES is + * active, which means SEV must be active too. Do sanity checks on the + * CPUID results to make sure the hypervisor does not trick the kernel + * into the no-sev path. This could map sensitive data unencrypted and + * make it accessible to the hypervisor. + * + * In particular, check for: + * - Hypervisor CPUID bit + * - Availability of CPUID leaf 0x8000001f + * - SEV CPUID bit. + * + * The hypervisor might still report the wrong C-bit position, but this + * can't be checked here. + */ + + if ((fn == 1 && !(regs->cx & BIT(31)))) + /* Hypervisor bit */ + goto fail; + else if (fn == 0x80000000 && (regs->ax < 0x8000001f)) + /* SEV leaf check */ + goto fail; + else if ((fn == 0x8000001f && !(regs->ax & BIT(1)))) + /* SEV bit */ + goto fail; + /* Skip over the CPUID two-byte opcode */ regs->ip += 2; @@ -279,14 +305,14 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo) case 0xe4: case 0xe5: *exitinfo |= IOIO_TYPE_IN; - *exitinfo |= (u64)insn->immediate.value << 16; + *exitinfo |= (u8)insn->immediate.value << 16; break; /* OUT immediate opcodes */ case 0xe6: case 0xe7: *exitinfo |= IOIO_TYPE_OUT; - *exitinfo |= (u64)insn->immediate.value << 16; + *exitinfo |= (u8)insn->immediate.value << 16; break; /* IN register opcodes */ diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 4a96726fbaf8..84c1821819af 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -225,7 +225,7 @@ static inline u64 sev_es_rd_ghcb_msr(void) return __rdmsr(MSR_AMD64_SEV_ES_GHCB); } -static inline void sev_es_wr_ghcb_msr(u64 val) +static __always_inline void sev_es_wr_ghcb_msr(u64 val) { u32 low, high; @@ -286,6 +286,12 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt, u16 d2; u8 d1; + /* If instruction ran in kernel mode and the I/O buffer is in kernel space */ + if (!user_mode(ctxt->regs) && !access_ok(target, size)) { + memcpy(dst, buf, size); + return ES_OK; + } + switch (size) { case 1: memcpy(&d1, buf, 1); @@ -335,6 +341,12 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, u16 d2; u8 d1; + /* If instruction ran in kernel mode and the I/O buffer is in kernel space */ + if (!user_mode(ctxt->regs) && !access_ok(s, size)) { + memcpy(buf, src, size); + return ES_OK; + } + switch (size) { case 1: if (get_user(d1, s)) @@ -374,8 +386,8 @@ fault: return ES_EXCEPTION; } -static bool vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt, - unsigned long vaddr, phys_addr_t *paddr) +static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt, + unsigned long vaddr, phys_addr_t *paddr) { unsigned long va = (unsigned long)vaddr; unsigned int level; @@ -394,15 +406,19 @@ static bool vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt, if (user_mode(ctxt->regs)) ctxt->fi.error_code |= X86_PF_USER; - return false; + return ES_EXCEPTION; } + if (WARN_ON_ONCE(pte_val(*pte) & _PAGE_ENC)) + /* Emulated MMIO to/from encrypted memory not supported */ + return ES_UNSUPPORTED; + pa = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; pa |= va & ~page_level_mask(level); *paddr = pa; - return true; + return ES_OK; } /* Include code shared with pre-decompression boot stage */ @@ -731,6 +747,7 @@ static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt, { u64 exit_code, exit_info_1, exit_info_2; unsigned long ghcb_pa = __pa(ghcb); + enum es_result res; phys_addr_t paddr; void __user *ref; @@ -740,11 +757,12 @@ static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt, exit_code = read ? SVM_VMGEXIT_MMIO_READ : SVM_VMGEXIT_MMIO_WRITE; - if (!vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr)) { - if (!read) + res = vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr); + if (res != ES_OK) { + if (res == ES_EXCEPTION && !read) ctxt->fi.error_code |= X86_PF_WRITE; - return ES_EXCEPTION; + return res; } exit_info_1 = paddr; diff --git a/arch/x86/kernel/sev_verify_cbit.S b/arch/x86/kernel/sev_verify_cbit.S new file mode 100644 index 000000000000..ee04941a6546 --- /dev/null +++ b/arch/x86/kernel/sev_verify_cbit.S @@ -0,0 +1,89 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * sev_verify_cbit.S - Code for verification of the C-bit position reported + * by the Hypervisor when running with SEV enabled. + * + * Copyright (c) 2020 Joerg Roedel ([email protected]) + * + * sev_verify_cbit() is called before switching to a new long-mode page-table + * at boot. + * + * Verify that the C-bit position is correct by writing a random value to + * an encrypted memory location while on the current page-table. Then it + * switches to the new page-table to verify the memory content is still the + * same. After that it switches back to the current page-table and when the + * check succeeded it returns. If the check failed the code invalidates the + * stack pointer and goes into a hlt loop. The stack-pointer is invalidated to + * make sure no interrupt or exception can get the CPU out of the hlt loop. + * + * New page-table pointer is expected in %rdi (first parameter) + * + */ +SYM_FUNC_START(sev_verify_cbit) +#ifdef CONFIG_AMD_MEM_ENCRYPT + /* First check if a C-bit was detected */ + movq sme_me_mask(%rip), %rsi + testq %rsi, %rsi + jz 3f + + /* sme_me_mask != 0 could mean SME or SEV - Check also for SEV */ + movq sev_status(%rip), %rsi + testq %rsi, %rsi + jz 3f + + /* Save CR4 in %rsi */ + movq %cr4, %rsi + + /* Disable Global Pages */ + movq %rsi, %rdx + andq $(~X86_CR4_PGE), %rdx + movq %rdx, %cr4 + + /* + * Verified that running under SEV - now get a random value using + * RDRAND. This instruction is mandatory when running as an SEV guest. + * + * Don't bail out of the loop if RDRAND returns errors. It is better to + * prevent forward progress than to work with a non-random value here. + */ +1: rdrand %rdx + jnc 1b + + /* Store value to memory and keep it in %rdx */ + movq %rdx, sev_check_data(%rip) + + /* Backup current %cr3 value to restore it later */ + movq %cr3, %rcx + + /* Switch to new %cr3 - This might unmap the stack */ + movq %rdi, %cr3 + + /* + * Compare value in %rdx with memory location. If C-bit is incorrect + * this would read the encrypted data and make the check fail. + */ + cmpq %rdx, sev_check_data(%rip) + + /* Restore old %cr3 */ + movq %rcx, %cr3 + + /* Restore previous CR4 */ + movq %rsi, %cr4 + + /* Check CMPQ result */ + je 3f + + /* + * The check failed, prevent any forward progress to prevent ROP + * attacks, invalidate the stack and go into a hlt loop. + */ + xorq %rsp, %rsp + subq $0x1000, %rsp +2: hlt + jmp 2b +3: +#endif + /* Return page-table pointer */ + movq %rdi, %rax + ret +SYM_FUNC_END(sev_verify_cbit) diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index be0d7d4152ec..ea794a083c44 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -804,11 +804,11 @@ static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) * want to handle. Thus you cannot kill init even with a SIGKILL even by * mistake. */ -void arch_do_signal(struct pt_regs *regs) +void arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal) { struct ksignal ksig; - if (get_signal(&ksig)) { + if (has_signal && get_signal(&ksig)) { /* Whee! Actually deliver the signal. */ handle_signal(&ksig, regs); return; diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index a7f3e12cfbdb..a5330ff498f0 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -31,7 +31,7 @@ static inline void signal_compat_build_tests(void) BUILD_BUG_ON(NSIGBUS != 5); BUILD_BUG_ON(NSIGTRAP != 5); BUILD_BUG_ON(NSIGCHLD != 6); - BUILD_BUG_ON(NSIGSYS != 1); + BUILD_BUG_ON(NSIGSYS != 2); /* This is part of the ABI and can never change in size: */ BUILD_BUG_ON(sizeof(compat_siginfo_t) != 128); @@ -165,16 +165,9 @@ void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact) { signal_compat_build_tests(); - /* Don't leak in-kernel non-uapi flags to user-space */ - if (oact) - oact->sa.sa_flags &= ~(SA_IA32_ABI | SA_X32_ABI); - if (!act) return; - /* Don't let flags to be set from userspace */ - act->sa.sa_flags &= ~(SA_IA32_ABI | SA_X32_ABI); - if (in_ia32_syscall()) act->sa.sa_flags |= SA_IA32_ABI; if (in_x32_syscall()) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index de776b2e6046..02813a7f3a7c 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -56,6 +56,7 @@ #include <linux/numa.h> #include <linux/pgtable.h> #include <linux/overflow.h> +#include <linux/syscore_ops.h> #include <asm/acpi.h> #include <asm/desc.h> @@ -82,6 +83,10 @@ #include <asm/hw_irq.h> #include <asm/stackprotector.h> +#ifdef CONFIG_ACPI_CPPC_LIB +#include <acpi/cppc_acpi.h> +#endif + /* representing HT siblings of each logical CPU */ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map); EXPORT_PER_CPU_SYMBOL(cpu_sibling_map); @@ -148,7 +153,7 @@ static inline void smpboot_restore_warm_reset_vector(void) *((volatile u32 *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0; } -static void init_freq_invariance(bool secondary); +static void init_freq_invariance(bool secondary, bool cppc_ready); /* * Report back to the Boot Processor during boot time or to the caller processor @@ -186,7 +191,7 @@ static void smp_callin(void) */ set_cpu_sibling_map(raw_smp_processor_id()); - init_freq_invariance(true); + init_freq_invariance(true, false); /* * Get our bogomips. @@ -229,6 +234,7 @@ static void notrace start_secondary(void *unused) #endif cpu_init_exception_handling(); cpu_init(); + rcu_cpu_starting(raw_smp_processor_id()); x86_cpuinit.early_percpu_clock_init(); preempt_disable(); smp_callin(); @@ -747,13 +753,14 @@ static void __init smp_quirk_init_udelay(void) int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip) { + u32 dm = apic->dest_mode_logical ? APIC_DEST_LOGICAL : APIC_DEST_PHYSICAL; unsigned long send_status, accept_status = 0; int maxlvt; /* Target chip */ /* Boot on the stack */ /* Kick the second */ - apic_icr_write(APIC_DM_NMI | apic->dest_logical, apicid); + apic_icr_write(APIC_DM_NMI | dm, apicid); pr_debug("Waiting for send to finish...\n"); send_status = safe_apic_wait_icr_idle(); @@ -980,10 +987,7 @@ wakeup_cpu_via_init_nmi(int cpu, unsigned long start_ip, int apicid, if (!boot_error) { enable_start_cpu0 = 1; *cpu0_nmi_registered = 1; - if (apic->dest_logical == APIC_DEST_LOGICAL) - id = cpu0_logical_apicid; - else - id = apicid; + id = apic->dest_mode_logical ? cpu0_logical_apicid : apicid; boot_error = wakeup_secondary_cpu_via_nmi(id, start_ip); } @@ -1340,7 +1344,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) set_sched_topology(x86_topology); set_cpu_sibling_map(0); - init_freq_invariance(false); + init_freq_invariance(false, false); smp_sanity_check(); switch (apic_intr_mode) { @@ -1829,6 +1833,7 @@ void arch_set_max_freq_ratio(bool turbo_disabled) arch_max_freq_ratio = turbo_disabled ? SCHED_CAPACITY_SCALE : arch_turbo_freq_ratio; } +EXPORT_SYMBOL_GPL(arch_set_max_freq_ratio); static bool turbo_disabled(void) { @@ -2027,6 +2032,48 @@ out: return true; } +#ifdef CONFIG_ACPI_CPPC_LIB +static bool amd_set_max_freq_ratio(void) +{ + struct cppc_perf_caps perf_caps; + u64 highest_perf, nominal_perf; + u64 perf_ratio; + int rc; + + rc = cppc_get_perf_caps(0, &perf_caps); + if (rc) { + pr_debug("Could not retrieve perf counters (%d)\n", rc); + return false; + } + + highest_perf = perf_caps.highest_perf; + nominal_perf = perf_caps.nominal_perf; + + if (!highest_perf || !nominal_perf) { + pr_debug("Could not retrieve highest or nominal performance\n"); + return false; + } + + perf_ratio = div_u64(highest_perf * SCHED_CAPACITY_SCALE, nominal_perf); + /* midpoint between max_boost and max_P */ + perf_ratio = (perf_ratio + SCHED_CAPACITY_SCALE) >> 1; + if (!perf_ratio) { + pr_debug("Non-zero highest/nominal perf values led to a 0 ratio\n"); + return false; + } + + arch_turbo_freq_ratio = perf_ratio; + arch_set_max_freq_ratio(false); + + return true; +} +#else +static bool amd_set_max_freq_ratio(void) +{ + return false; +} +#endif + static void init_counter_refs(void) { u64 aperf, mperf; @@ -2038,7 +2085,24 @@ static void init_counter_refs(void) this_cpu_write(arch_prev_mperf, mperf); } -static void init_freq_invariance(bool secondary) +#ifdef CONFIG_PM_SLEEP +static struct syscore_ops freq_invariance_syscore_ops = { + .resume = init_counter_refs, +}; + +static void register_freq_invariance_syscore_ops(void) +{ + /* Bail out if registered already. */ + if (freq_invariance_syscore_ops.node.prev) + return; + + register_syscore_ops(&freq_invariance_syscore_ops); +} +#else +static inline void register_freq_invariance_syscore_ops(void) {} +#endif + +static void init_freq_invariance(bool secondary, bool cppc_ready) { bool ret = false; @@ -2054,15 +2118,39 @@ static void init_freq_invariance(bool secondary) if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) ret = intel_set_max_freq_ratio(); + else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { + if (!cppc_ready) { + return; + } + ret = amd_set_max_freq_ratio(); + } if (ret) { init_counter_refs(); static_branch_enable(&arch_scale_freq_key); + register_freq_invariance_syscore_ops(); + pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio); } else { pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n"); } } +#ifdef CONFIG_ACPI_CPPC_LIB +static DEFINE_MUTEX(freq_invariance_lock); + +void init_freq_invariance_cppc(void) +{ + static bool secondary; + + mutex_lock(&freq_invariance_lock); + + init_freq_invariance(secondary, true); + secondary = true; + + mutex_unlock(&freq_invariance_lock); +} +#endif + static void disable_freq_invariance_workfn(struct work_struct *work) { static_branch_disable(&arch_scale_freq_key); @@ -2112,7 +2200,7 @@ error: schedule_work(&disable_freq_invariance_work); } #else -static inline void init_freq_invariance(bool secondary) +static inline void init_freq_invariance(bool secondary, bool cppc_ready) { } #endif /* CONFIG_X86_64 */ diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index ca9a380d9c0b..9442c4136c38 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -11,14 +11,26 @@ enum insn_type { RET = 3, /* tramp / site cond-tail-call */ }; +/* + * data16 data16 xorq %rax, %rax - a single 5 byte instruction that clears %rax + * The REX.W cancels the effect of any data16. + */ +static const u8 xor5rax[] = { 0x66, 0x66, 0x48, 0x31, 0xc0 }; + static void __ref __static_call_transform(void *insn, enum insn_type type, void *func) { + const void *emulate = NULL; int size = CALL_INSN_SIZE; const void *code; switch (type) { case CALL: code = text_gen_insn(CALL_INSN_OPCODE, insn, func); + if (func == &__static_call_return0) { + emulate = code; + code = &xor5rax; + } + break; case NOP: @@ -41,7 +53,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, void if (unlikely(system_state == SYSTEM_BOOTING)) return text_poke_early(insn, code, size); - text_poke_bp(insn, code, size, NULL); + text_poke_bp(insn, code, size, emulate); } static void __static_call_validate(void *insn, bool tail) @@ -54,7 +66,8 @@ static void __static_call_validate(void *insn, bool tail) return; } else { if (opcode == CALL_INSN_OPCODE || - !memcmp(insn, ideal_nops[NOP_ATOMIC5], 5)) + !memcmp(insn, ideal_nops[NOP_ATOMIC5], 5) || + !memcmp(insn, xor5rax, 5)) return; } diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index 60d2c3798ba2..0f3c307b37b3 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -127,12 +127,17 @@ static int enable_single_step(struct task_struct *child) regs->flags |= X86_EFLAGS_TF; /* - * Always set TIF_SINGLESTEP - this guarantees that - * we single-step system calls etc.. This will also + * Always set TIF_SINGLESTEP. This will also * cause us to set TF when returning to user mode. */ set_tsk_thread_flag(child, TIF_SINGLESTEP); + /* + * Ensure that a trap is triggered once stepping out of a system + * call prior to executing any user instruction. + */ + set_task_syscall_work(child, SYSCALL_EXIT_TRAP); + oflags = regs->flags; /* Set TF on the kernel stack.. */ @@ -230,6 +235,7 @@ void user_disable_single_step(struct task_struct *child) /* Always clear TIF_SINGLESTEP... */ clear_tsk_thread_flag(child, TIF_SINGLESTEP); + clear_task_syscall_work(child, SYSCALL_EXIT_TRAP); /* But touch TF only if it was set by us.. */ if (test_and_clear_tsk_thread_flag(child, TIF_FORCED_TF)) diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 504fa5425bce..660b78827638 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -90,14 +90,10 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, unsigned long, prot, unsigned long, flags, unsigned long, fd, unsigned long, off) { - long error; - error = -EINVAL; if (off & ~PAGE_MASK) - goto out; + return -EINVAL; - error = ksys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT); -out: - return error; + return ksys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT); } static void find_start_end(unsigned long addr, unsigned long flags, diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index 992fb1415c0f..4c09ba110204 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -93,6 +93,7 @@ static struct mm_struct tboot_mm = { .pgd = swapper_pg_dir, .mm_users = ATOMIC_INIT(2), .mm_count = ATOMIC_INIT(1), + .write_protect_seq = SEQCNT_ZERO(tboot_mm.write_protect_seq), MMAP_LOCK_INITIALIZER(init_mm) .page_table_lock = __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock), .mmlist = LIST_HEAD_INIT(init_mm.mmlist), @@ -514,16 +515,10 @@ int tboot_force_iommu(void) if (!tboot_enabled()) return 0; - if (intel_iommu_tboot_noforce) - return 1; - - if (no_iommu || swiotlb || dmar_disabled) + if (no_iommu || dmar_disabled) pr_warn("Forcing Intel-IOMMU to enabled\n"); dmar_disabled = 0; -#ifdef CONFIG_SWIOTLB - swiotlb = 0; -#endif no_iommu = 0; return 1; diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index 0a2ec801b63f..f5477eab5692 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -25,6 +25,7 @@ * * Send feedback to <[email protected]> */ +#include <linux/interrupt.h> #include <linux/nodemask.h> #include <linux/export.h> #include <linux/mmzone.h> diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 3c70fb34028b..7f5aec758f0e 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -60,6 +60,7 @@ #include <asm/umip.h> #include <asm/insn.h> #include <asm/insn-eval.h> +#include <asm/vdso.h> #ifdef CONFIG_X86_64 #include <asm/x86_init.h> @@ -117,6 +118,9 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, const char *str, tsk->thread.error_code = error_code; tsk->thread.trap_nr = trapnr; die(str, regs, error_code); + } else { + if (fixup_vdso_exception(regs, trapnr, error_code, 0)) + return 0; } /* @@ -299,11 +303,12 @@ DEFINE_IDTENTRY_ERRORCODE(exc_alignment_check) local_irq_enable(); if (handle_user_split_lock(regs, error_code)) - return; + goto out; do_trap(X86_TRAP_AC, SIGBUS, "alignment check", regs, error_code, BUS_ADRALN, NULL); +out: local_irq_disable(); } @@ -405,7 +410,7 @@ DEFINE_IDTENTRY_DF(exc_double_fault) } #endif - idtentry_enter_nmi(regs); + irqentry_nmi_enter(regs); instrumentation_begin(); notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV); @@ -550,6 +555,9 @@ DEFINE_IDTENTRY_ERRORCODE(exc_general_protection) tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_GP; + if (fixup_vdso_exception(regs, X86_TRAP_GP, error_code, 0)) + return; + show_signal(tsk, SIGSEGV, "", desc, regs, error_code); force_sig(SIGSEGV); goto exit; @@ -651,12 +659,13 @@ DEFINE_IDTENTRY_RAW(exc_int3) instrumentation_end(); irqentry_exit_to_user_mode(regs); } else { - bool irq_state = idtentry_enter_nmi(regs); + irqentry_state_t irq_state = irqentry_nmi_enter(regs); + instrumentation_begin(); if (!do_int3(regs)) die("int3", regs, 0); instrumentation_end(); - idtentry_exit_nmi(regs, irq_state); + irqentry_nmi_exit(regs, irq_state); } } @@ -793,19 +802,6 @@ static __always_inline unsigned long debug_read_clear_dr6(void) set_debugreg(DR6_RESERVED, 6); dr6 ^= DR6_RESERVED; /* Flip to positive polarity */ - /* - * Clear the virtual DR6 value, ptrace routines will set bits here for - * things we want signals for. - */ - current->thread.virtual_dr6 = 0; - - /* - * The SDM says "The processor clears the BTF flag when it - * generates a debug exception." Clear TIF_BLOCKSTEP to keep - * TIF_BLOCKSTEP in sync with the hardware BTF flag. - */ - clear_thread_flag(TIF_BLOCKSTEP); - return dr6; } @@ -864,7 +860,7 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs, * includes the entry stack is excluded for everything. */ unsigned long dr7 = local_db_save(); - bool irq_state = idtentry_enter_nmi(regs); + irqentry_state_t irq_state = irqentry_nmi_enter(regs); instrumentation_begin(); /* @@ -873,6 +869,20 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs, */ WARN_ON_ONCE(user_mode(regs)); + if (test_thread_flag(TIF_BLOCKSTEP)) { + /* + * The SDM says "The processor clears the BTF flag when it + * generates a debug exception." but PTRACE_BLOCKSTEP requested + * it for userspace, but we just took a kernel #DB, so re-set + * BTF. + */ + unsigned long debugctl; + + rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + debugctl |= DEBUGCTLMSR_BTF; + wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + } + /* * Catch SYSENTER with TF set and clear DR_STEP. If this hit a * watchpoint at the same time then that will still be handled. @@ -907,7 +917,7 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs, regs->flags &= ~X86_EFLAGS_TF; out: instrumentation_end(); - idtentry_exit_nmi(regs, irq_state); + irqentry_nmi_exit(regs, irq_state); local_db_restore(dr7); } @@ -925,7 +935,7 @@ static __always_inline void exc_debug_user(struct pt_regs *regs, /* * NB: We can't easily clear DR7 here because - * idtentry_exit_to_usermode() can invoke ptrace, schedule, access + * irqentry_exit_to_usermode() can invoke ptrace, schedule, access * user memory, etc. This means that a recursive #DB is possible. If * this happens, that #DB will hit exc_debug_kernel() and clear DR7. * Since we're not on the IST stack right now, everything will be @@ -936,6 +946,22 @@ static __always_inline void exc_debug_user(struct pt_regs *regs, instrumentation_begin(); /* + * Start the virtual/ptrace DR6 value with just the DR_STEP mask + * of the real DR6. ptrace_triggered() will set the DR_TRAPn bits. + * + * Userspace expects DR_STEP to be visible in ptrace_get_debugreg(6) + * even if it is not the result of PTRACE_SINGLESTEP. + */ + current->thread.virtual_dr6 = (dr6 & DR_STEP); + + /* + * The SDM says "The processor clears the BTF flag when it + * generates a debug exception." Clear TIF_BLOCKSTEP to keep + * TIF_BLOCKSTEP in sync with the hardware BTF flag. + */ + clear_thread_flag(TIF_BLOCKSTEP); + + /* * If dr6 has no reason to give us about the origin of this trap, * then it's very likely the result of an icebp/int01 trap. * User wants a sigtrap for that. @@ -1031,6 +1057,9 @@ static void math_error(struct pt_regs *regs, int trapnr) if (!si_code) goto exit; + if (fixup_vdso_exception(regs, trapnr, 0, 0)) + return; + force_sig_fault(SIGFPE, si_code, (void __user *)uprobe_get_trap_addr(regs)); exit: diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 6a339ce328e0..73f800100066 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -321,19 +321,12 @@ EXPORT_SYMBOL_GPL(unwind_get_return_address); unsigned long *unwind_get_return_address_ptr(struct unwind_state *state) { - struct task_struct *task = state->task; - if (unwind_done(state)) return NULL; if (state->regs) return &state->regs->ip; - if (task != current && state->sp == task->thread.sp) { - struct inactive_task_frame *frame = (void *)task->thread.sp; - return &frame->ret_addr; - } - if (state->sp) return (unsigned long *)state->sp - 1; @@ -663,7 +656,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, } else { struct inactive_task_frame *frame = (void *)task->thread.sp; - state->sp = task->thread.sp; + state->sp = task->thread.sp + sizeof(*frame); state->bp = READ_ONCE_NOCHECK(frame->bp); state->ip = READ_ONCE_NOCHECK(frame->ret_addr); state->signal = (void *)state->ip == ret_from_fork; diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 3fdaa042823d..a2b413394917 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -255,12 +255,13 @@ static volatile u32 good_2byte_insns[256 / 32] = { static bool is_prefix_bad(struct insn *insn) { + insn_byte_t p; int i; - for (i = 0; i < insn->prefixes.nbytes; i++) { + for_each_insn_prefix(insn, i, p) { insn_attr_t attr; - attr = inat_get_opcode_attribute(insn->prefixes.bytes[i]); + attr = inat_get_opcode_attribute(p); switch (attr) { case INAT_MAKE_PREFIX(INAT_PFX_ES): case INAT_MAKE_PREFIX(INAT_PFX_CS): @@ -715,6 +716,7 @@ static const struct uprobe_xol_ops push_xol_ops = { static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn) { u8 opc1 = OPCODE1(insn); + insn_byte_t p; int i; switch (opc1) { @@ -746,8 +748,8 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn) * Intel and AMD behavior differ in 64-bit mode: Intel ignores 66 prefix. * No one uses these insns, reject any branch insns with such prefix. */ - for (i = 0; i < insn->prefixes.nbytes; i++) { - if (insn->prefixes.bytes[i] == 0x66) + for_each_insn_prefix(insn, i, p) { + if (p == 0x66) return -ENOTSUPP; } @@ -1015,6 +1017,8 @@ int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, if (uprobe_post_sstep_notifier(regs)) ret = NOTIFY_STOP; + break; + default: break; } diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 764573de3996..e5a7a10a0164 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -134,7 +134,11 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval) unsafe_put_user(regs->ds, &user->regs.ds, Efault_end); unsafe_put_user(regs->fs, &user->regs.fs, Efault_end); unsafe_put_user(regs->gs, &user->regs.gs, Efault_end); - unsafe_put_user(vm86->screen_bitmap, &user->screen_bitmap, Efault_end); + + /* + * Don't write screen_bitmap in case some user had a value there + * and expected it to remain unchanged. + */ user_access_end(); @@ -160,49 +164,6 @@ Efault: do_exit(SIGSEGV); } -static void mark_screen_rdonly(struct mm_struct *mm) -{ - struct vm_area_struct *vma; - spinlock_t *ptl; - pgd_t *pgd; - p4d_t *p4d; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - int i; - - mmap_write_lock(mm); - pgd = pgd_offset(mm, 0xA0000); - if (pgd_none_or_clear_bad(pgd)) - goto out; - p4d = p4d_offset(pgd, 0xA0000); - if (p4d_none_or_clear_bad(p4d)) - goto out; - pud = pud_offset(p4d, 0xA0000); - if (pud_none_or_clear_bad(pud)) - goto out; - pmd = pmd_offset(pud, 0xA0000); - - if (pmd_trans_huge(*pmd)) { - vma = find_vma(mm, 0xA0000); - split_huge_pmd(vma, pmd, 0xA0000); - } - if (pmd_none_or_clear_bad(pmd)) - goto out; - pte = pte_offset_map_lock(mm, pmd, 0xA0000, &ptl); - for (i = 0; i < 32; i++) { - if (pte_present(*pte)) - set_pte(pte, pte_wrprotect(*pte)); - pte++; - } - pte_unmap_unlock(pte, ptl); -out: - mmap_write_unlock(mm); - flush_tlb_mm_range(mm, 0xA0000, 0xA0000 + 32*PAGE_SIZE, PAGE_SHIFT, false); -} - - - static int do_vm86_irq_handling(int subfunction, int irqnumber); static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus); @@ -282,6 +243,15 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) offsetof(struct vm86_struct, int_revectored))) return -EFAULT; + + /* VM86_SCREEN_BITMAP had numerous bugs and appears to have no users. */ + if (v.flags & VM86_SCREEN_BITMAP) { + char comm[TASK_COMM_LEN]; + + pr_info_once("vm86: '%s' uses VM86_SCREEN_BITMAP, which is no longer supported\n", get_task_comm(comm, current)); + return -EINVAL; + } + memset(&vm86regs, 0, sizeof(vm86regs)); vm86regs.pt.bx = v.regs.ebx; @@ -302,7 +272,6 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) vm86regs.gs = v.regs.gs; vm86->flags = v.flags; - vm86->screen_bitmap = v.screen_bitmap; vm86->cpu_type = v.cpu_type; if (copy_from_user(&vm86->int_revectored, @@ -370,9 +339,6 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) update_task_stack(tsk); preempt_enable(); - if (vm86->flags & VM86_SCREEN_BITMAP) - mark_screen_rdonly(tsk->mm); - memcpy((struct kernel_vm86_regs *)regs, &vm86regs, sizeof(vm86regs)); return regs->ax; } diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index bf9e0adb5b7e..efd9e9ea17f2 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -454,13 +454,13 @@ SECTIONS ASSERT(SIZEOF(.rela.dyn) == 0, "Unexpected run-time relocations (.rela) detected!") } -#ifdef CONFIG_X86_32 /* * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility: */ . = ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE), "kernel image bigger than KERNEL_IMAGE_SIZE"); -#else + +#ifdef CONFIG_X86_64 /* * Per-cpu symbols which need to be offset from __per_cpu_load * for the boot processor. @@ -470,18 +470,12 @@ INIT_PER_CPU(gdt_page); INIT_PER_CPU(fixed_percpu_data); INIT_PER_CPU(irq_stack_backing_store); -/* - * Build-time check on the image size: - */ -. = ASSERT((_end - _text <= KERNEL_IMAGE_SIZE), - "kernel image bigger than KERNEL_IMAGE_SIZE"); - #ifdef CONFIG_SMP . = ASSERT((fixed_percpu_data == 0), "fixed_percpu_data is not at start of per-cpu area"); #endif -#endif /* CONFIG_X86_32 */ +#endif /* CONFIG_X86_64 */ #ifdef CONFIG_KEXEC_CORE #include <asm/kexec.h> diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index a3038d8deb6a..8b395821cb8d 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -110,6 +110,7 @@ struct x86_init_ops x86_init __initdata = { .init_platform = x86_init_noop, .guest_late_init = x86_init_noop, .x2apic_available = bool_x86_init_noop, + .msi_ext_dest_id = bool_x86_init_noop, .init_mem_mapping = x86_init_noop, .init_after_bootmem = x86_init_noop, }, |