diff options
Diffstat (limited to 'arch/x86/kernel')
79 files changed, 4306 insertions, 848 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 68608bd892c0..5eeb808eb024 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -161,5 +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 2400ad62f330..8d778e46725d 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -1374,7 +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..6bd20c0de8bc 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -94,6 +94,11 @@ 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); @@ -1591,7 +1596,7 @@ 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; /* @@ -1841,20 +1846,34 @@ 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 +2497,46 @@ 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 758bbf25ef74..3c9c7492252f 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -640,7 +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, @@ -822,6 +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..df6adc5674c9 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -61,7 +61,7 @@ __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 +184,13 @@ 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..0e4e81971567 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) { @@ -98,6 +104,9 @@ 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; } @@ -148,15 +157,13 @@ 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 235f5cde06fc..52bc217ca8c3 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -502,6 +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; @@ -716,9 +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) | @@ -820,15 +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, @@ -1603,21 +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 70b7154f4bdd..60b9f42ce3c1 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -66,7 +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/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..f8ca66f3d861 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 || 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/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/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/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 32b7099e3511..13d3f1cbda17 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); @@ -1265,14 +1266,14 @@ 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; @@ -1320,10 +1321,10 @@ 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 +1351,7 @@ 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 +1368,7 @@ 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); @@ -1387,6 +1387,9 @@ noinstr void do_machine_check(struct pt_regs *regs) 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 { /* @@ -1403,19 +1406,7 @@ 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 */ @@ -1423,7 +1414,7 @@ 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 { /* @@ -1441,7 +1432,7 @@ 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); @@ -1583,7 +1574,7 @@ 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; } } @@ -1764,7 +1755,7 @@ 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 @@ -1813,11 +1804,9 @@ 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; } @@ -1985,7 +1974,7 @@ 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)); @@ -1997,7 +1986,7 @@ 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. @@ -2008,7 +1997,7 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *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) 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..c2476fe0682e 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -509,12 +509,33 @@ 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/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/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 05ef1f4550cb..f628e3dc150f 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -366,9 +366,38 @@ 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/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index 6a80f36b5d59..61eb26edc6d2 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -794,8 +794,6 @@ 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 +811,8 @@ 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/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index e8b5f1cf1ae8..698bb26aeb6e 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -895,6 +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; } } diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index f65d3c0dbc41..ee71c47844cb 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; @@ -619,6 +619,7 @@ 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 a98519a3a2e6..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; } @@ -279,7 +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); - 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); @@ -642,3 +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 f3418428682b..29ffb95b25ff 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, }; @@ -3023,8 +3023,7 @@ 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; @@ -3056,8 +3055,7 @@ static int rdtgroup_rmdir_mon(struct kernfs_node *kn, struct rdtgroup *rdtgrp, 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); @@ -3066,8 +3064,7 @@ static int rdtgroup_ctrl_remove(struct kernfs_node *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; @@ -3094,7 +3091,7 @@ 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. @@ -3131,13 +3128,13 @@ 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..236924930bf0 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -44,6 +44,7 @@ static const struct cpuid_bit cpuid_bits[] = { { 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 }, + { X86_FEATURE_VM_PAGE_FLUSH, CPUID_EAX, 2, 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..f2eac41bb4ff --- /dev/null +++ b/arch/x86/kernel/cpu/sgx/driver.c @@ -0,0 +1,194 @@ +// 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); + } + + 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..ee50a5010277 --- /dev/null +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -0,0 +1,740 @@ +// 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; + unsigned long pfn; + 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); + + /* Check if another thread got here first to insert the PTE. */ + if (!follow_pfn(vma, addr, &pfn)) { + mutex_unlock(&encl->lock); + + return VM_FAULT_NOPAGE; + } + + 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); + + 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; + + 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..c519fc5f6948 --- /dev/null +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -0,0 +1,733 @@ +// 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 void __init sgx_init(void) +{ + int ret; + int i; + + if (!cpu_feature_enabled(X86_FEATURE_SGX)) + return; + + if (!sgx_page_cache_init()) + return; + + if (!sgx_page_reclaimer_init()) + goto err_page_cache; + + ret = sgx_drv_init(); + if (ret) + goto err_kthread; + + return; + +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); + } +} + +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..1068002c8532 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -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 97aa900386cb..299c20f0a38b 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -183,7 +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/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 05e117137b45..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> diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 3c417734790f..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. @@ -540,21 +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/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/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 547c7abb39f5..a65e9e97857f 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -864,6 +864,7 @@ static void resume_execution(struct kprobe *p, struct pt_regs *regs, p->ainsn.boostable = true; goto no_change; } + break; default: break; } @@ -937,6 +938,11 @@ 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/kvm.c b/arch/x86/kernel/kvm.c index 7f57ede3cb8e..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, 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/msr.c b/arch/x86/kernel/msr.c index c0d409810658..8a67d1fa8dc5 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; } 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/perf_regs.c b/arch/x86/kernel/perf_regs.c index f9e5352b3bef..624703af80a1 100644 --- a/arch/x86/kernel/perf_regs.c +++ b/arch/x86/kernel/perf_regs.c @@ -122,7 +122,7 @@ 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; 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/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/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..8ca66af96a54 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -82,6 +82,10 @@ #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 +152,7 @@ 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 +190,7 @@ 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 +233,7 @@ 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 +752,14 @@ 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 +986,7 @@ 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 +1343,7 @@ 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) { @@ -2027,6 +2030,48 @@ 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 +2083,7 @@ static void init_counter_refs(void) this_cpu_write(arch_prev_mperf, mperf); } -static void init_freq_invariance(bool secondary) +static void init_freq_invariance(bool secondary, bool cppc_ready) { bool ret = false; @@ -2054,15 +2099,38 @@ 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); + 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 +2180,7 @@ 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/tboot.c b/arch/x86/kernel/tboot.c index ae64f98ec2ab..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), 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 e19df6cde35d..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); } } @@ -851,7 +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(); /* @@ -908,7 +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); } @@ -926,7 +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 @@ -1048,6 +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/uprobes.c b/arch/x86/kernel/uprobes.c index 138bdb1fd136..a2b413394917 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -1017,6 +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/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, }, |