diff options
Diffstat (limited to 'arch/x86/kernel')
28 files changed, 706 insertions, 529 deletions
diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile index fc17b3f136fe..842a5f449404 100644 --- a/arch/x86/kernel/acpi/Makefile +++ b/arch/x86/kernel/acpi/Makefile @@ -4,6 +4,7 @@ obj-$(CONFIG_ACPI) += boot.o obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup_$(BITS).o obj-$(CONFIG_ACPI_APEI) += apei.o obj-$(CONFIG_ACPI_CPPC_LIB) += cppc.o +obj-$(CONFIG_ACPI_MADT_WAKEUP) += madt_wakeup.o madt_playdead.o ifneq ($(CONFIG_ACPI_PROCESSOR),) obj-y += cstate.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 4bf82dbd2a6b..9f4618dcd704 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -67,13 +67,6 @@ static bool has_lapic_cpus __initdata; static bool acpi_support_online_capable; #endif -#ifdef CONFIG_X86_64 -/* Physical address of the Multiprocessor Wakeup Structure mailbox */ -static u64 acpi_mp_wake_mailbox_paddr; -/* Virtual address of the Multiprocessor Wakeup Structure mailbox */ -static struct acpi_madt_multiproc_wakeup_mailbox *acpi_mp_wake_mailbox; -#endif - #ifdef CONFIG_X86_IO_APIC /* * Locks related to IOAPIC hotplug @@ -341,60 +334,6 @@ acpi_parse_lapic_nmi(union acpi_subtable_headers * header, const unsigned long e return 0; } - -#ifdef CONFIG_X86_64 -static int acpi_wakeup_cpu(u32 apicid, unsigned long start_ip) -{ - /* - * Remap mailbox memory only for the first call to acpi_wakeup_cpu(). - * - * Wakeup of secondary CPUs is fully serialized in the core code. - * No need to protect acpi_mp_wake_mailbox from concurrent accesses. - */ - if (!acpi_mp_wake_mailbox) { - acpi_mp_wake_mailbox = memremap(acpi_mp_wake_mailbox_paddr, - sizeof(*acpi_mp_wake_mailbox), - MEMREMAP_WB); - } - - /* - * Mailbox memory is shared between the firmware and OS. Firmware will - * listen on mailbox command address, and once it receives the wakeup - * command, the CPU associated with the given apicid will be booted. - * - * The value of 'apic_id' and 'wakeup_vector' must be visible to the - * firmware before the wakeup command is visible. smp_store_release() - * ensures ordering and visibility. - */ - acpi_mp_wake_mailbox->apic_id = apicid; - acpi_mp_wake_mailbox->wakeup_vector = start_ip; - smp_store_release(&acpi_mp_wake_mailbox->command, - ACPI_MP_WAKE_COMMAND_WAKEUP); - - /* - * Wait for the CPU to wake up. - * - * The CPU being woken up is essentially in a spin loop waiting to be - * woken up. It should not take long for it wake up and acknowledge by - * zeroing out ->command. - * - * ACPI specification doesn't provide any guidance on how long kernel - * has to wait for a wake up acknowledgement. It also doesn't provide - * a way to cancel a wake up request if it takes too long. - * - * In TDX environment, the VMM has control over how long it takes to - * wake up secondary. It can postpone scheduling secondary vCPU - * indefinitely. Giving up on wake up request and reporting error opens - * possible attack vector for VMM: it can wake up a secondary CPU when - * kernel doesn't expect it. Wait until positive result of the wake up - * request. - */ - while (READ_ONCE(acpi_mp_wake_mailbox->command)) - cpu_relax(); - - return 0; -} -#endif /* CONFIG_X86_64 */ #endif /* CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_IO_APIC @@ -1124,29 +1063,6 @@ static int __init acpi_parse_madt_lapic_entries(void) } return 0; } - -#ifdef CONFIG_X86_64 -static int __init acpi_parse_mp_wake(union acpi_subtable_headers *header, - const unsigned long end) -{ - struct acpi_madt_multiproc_wakeup *mp_wake; - - if (!IS_ENABLED(CONFIG_SMP)) - return -ENODEV; - - mp_wake = (struct acpi_madt_multiproc_wakeup *)header; - if (BAD_MADT_ENTRY(mp_wake, end)) - return -EINVAL; - - acpi_table_print_madt_entry(&header->common); - - acpi_mp_wake_mailbox_paddr = mp_wake->base_address; - - apic_update_callback(wakeup_secondary_cpu_64, acpi_wakeup_cpu); - - return 0; -} -#endif /* CONFIG_X86_64 */ #endif /* CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_IO_APIC @@ -1343,7 +1259,7 @@ static void __init acpi_process_madt(void) smp_found_config = 1; } -#ifdef CONFIG_X86_64 +#ifdef CONFIG_ACPI_MADT_WAKEUP /* * Parse MADT MP Wake entry. */ diff --git a/arch/x86/kernel/acpi/madt_playdead.S b/arch/x86/kernel/acpi/madt_playdead.S new file mode 100644 index 000000000000..4e498d28cdc8 --- /dev/null +++ b/arch/x86/kernel/acpi/madt_playdead.S @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/linkage.h> +#include <asm/nospec-branch.h> +#include <asm/page_types.h> +#include <asm/processor-flags.h> + + .text + .align PAGE_SIZE + +/* + * asm_acpi_mp_play_dead() - Hand over control of the CPU to the BIOS + * + * rdi: Address of the ACPI MADT MPWK ResetVector + * rsi: PGD of the identity mapping + */ +SYM_FUNC_START(asm_acpi_mp_play_dead) + /* Turn off global entries. Following CR3 write will flush them. */ + movq %cr4, %rdx + andq $~(X86_CR4_PGE), %rdx + movq %rdx, %cr4 + + /* Switch to identity mapping */ + movq %rsi, %cr3 + + /* Jump to reset vector */ + ANNOTATE_RETPOLINE_SAFE + jmp *%rdi +SYM_FUNC_END(asm_acpi_mp_play_dead) diff --git a/arch/x86/kernel/acpi/madt_wakeup.c b/arch/x86/kernel/acpi/madt_wakeup.c new file mode 100644 index 000000000000..6cfe762be28b --- /dev/null +++ b/arch/x86/kernel/acpi/madt_wakeup.c @@ -0,0 +1,292 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#include <linux/acpi.h> +#include <linux/cpu.h> +#include <linux/delay.h> +#include <linux/io.h> +#include <linux/kexec.h> +#include <linux/memblock.h> +#include <linux/pgtable.h> +#include <linux/sched/hotplug.h> +#include <asm/apic.h> +#include <asm/barrier.h> +#include <asm/init.h> +#include <asm/intel_pt.h> +#include <asm/nmi.h> +#include <asm/processor.h> +#include <asm/reboot.h> + +/* Physical address of the Multiprocessor Wakeup Structure mailbox */ +static u64 acpi_mp_wake_mailbox_paddr __ro_after_init; + +/* Virtual address of the Multiprocessor Wakeup Structure mailbox */ +static struct acpi_madt_multiproc_wakeup_mailbox *acpi_mp_wake_mailbox __ro_after_init; + +static u64 acpi_mp_pgd __ro_after_init; +static u64 acpi_mp_reset_vector_paddr __ro_after_init; + +static void acpi_mp_stop_this_cpu(void) +{ + asm_acpi_mp_play_dead(acpi_mp_reset_vector_paddr, acpi_mp_pgd); +} + +static void acpi_mp_play_dead(void) +{ + play_dead_common(); + asm_acpi_mp_play_dead(acpi_mp_reset_vector_paddr, acpi_mp_pgd); +} + +static void acpi_mp_cpu_die(unsigned int cpu) +{ + u32 apicid = per_cpu(x86_cpu_to_apicid, cpu); + unsigned long timeout; + + /* + * Use TEST mailbox command to prove that BIOS got control over + * the CPU before declaring it dead. + * + * BIOS has to clear 'command' field of the mailbox. + */ + acpi_mp_wake_mailbox->apic_id = apicid; + smp_store_release(&acpi_mp_wake_mailbox->command, + ACPI_MP_WAKE_COMMAND_TEST); + + /* Don't wait longer than a second. */ + timeout = USEC_PER_SEC; + while (READ_ONCE(acpi_mp_wake_mailbox->command) && --timeout) + udelay(1); + + if (!timeout) + pr_err("Failed to hand over CPU %d to BIOS\n", cpu); +} + +/* The argument is required to match type of x86_mapping_info::alloc_pgt_page */ +static void __init *alloc_pgt_page(void *dummy) +{ + return memblock_alloc(PAGE_SIZE, PAGE_SIZE); +} + +static void __init free_pgt_page(void *pgt, void *dummy) +{ + return memblock_free(pgt, PAGE_SIZE); +} + +/* + * Make sure asm_acpi_mp_play_dead() is present in the identity mapping at + * the same place as in the kernel page tables. asm_acpi_mp_play_dead() switches + * to the identity mapping and the function has be present at the same spot in + * the virtual address space before and after switching page tables. + */ +static int __init init_transition_pgtable(pgd_t *pgd) +{ + pgprot_t prot = PAGE_KERNEL_EXEC_NOENC; + unsigned long vaddr, paddr; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + vaddr = (unsigned long)asm_acpi_mp_play_dead; + pgd += pgd_index(vaddr); + if (!pgd_present(*pgd)) { + p4d = (p4d_t *)alloc_pgt_page(NULL); + if (!p4d) + return -ENOMEM; + set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE)); + } + p4d = p4d_offset(pgd, vaddr); + if (!p4d_present(*p4d)) { + pud = (pud_t *)alloc_pgt_page(NULL); + if (!pud) + return -ENOMEM; + set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE)); + } + pud = pud_offset(p4d, vaddr); + if (!pud_present(*pud)) { + pmd = (pmd_t *)alloc_pgt_page(NULL); + if (!pmd) + return -ENOMEM; + set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE)); + } + pmd = pmd_offset(pud, vaddr); + if (!pmd_present(*pmd)) { + pte = (pte_t *)alloc_pgt_page(NULL); + if (!pte) + return -ENOMEM; + set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE)); + } + pte = pte_offset_kernel(pmd, vaddr); + + paddr = __pa(vaddr); + set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, prot)); + + return 0; +} + +static int __init acpi_mp_setup_reset(u64 reset_vector) +{ + struct x86_mapping_info info = { + .alloc_pgt_page = alloc_pgt_page, + .free_pgt_page = free_pgt_page, + .page_flag = __PAGE_KERNEL_LARGE_EXEC, + .kernpg_flag = _KERNPG_TABLE_NOENC, + }; + pgd_t *pgd; + + pgd = alloc_pgt_page(NULL); + if (!pgd) + return -ENOMEM; + + for (int i = 0; i < nr_pfn_mapped; i++) { + unsigned long mstart, mend; + + mstart = pfn_mapped[i].start << PAGE_SHIFT; + mend = pfn_mapped[i].end << PAGE_SHIFT; + if (kernel_ident_mapping_init(&info, pgd, mstart, mend)) { + kernel_ident_mapping_free(&info, pgd); + return -ENOMEM; + } + } + + if (kernel_ident_mapping_init(&info, pgd, + PAGE_ALIGN_DOWN(reset_vector), + PAGE_ALIGN(reset_vector + 1))) { + kernel_ident_mapping_free(&info, pgd); + return -ENOMEM; + } + + if (init_transition_pgtable(pgd)) { + kernel_ident_mapping_free(&info, pgd); + return -ENOMEM; + } + + smp_ops.play_dead = acpi_mp_play_dead; + smp_ops.stop_this_cpu = acpi_mp_stop_this_cpu; + smp_ops.cpu_die = acpi_mp_cpu_die; + + acpi_mp_reset_vector_paddr = reset_vector; + acpi_mp_pgd = __pa(pgd); + + return 0; +} + +static int acpi_wakeup_cpu(u32 apicid, unsigned long start_ip) +{ + if (!acpi_mp_wake_mailbox_paddr) { + pr_warn_once("No MADT mailbox: cannot bringup secondary CPUs. Booting with kexec?\n"); + return -EOPNOTSUPP; + } + + /* + * Remap mailbox memory only for the first call to acpi_wakeup_cpu(). + * + * Wakeup of secondary CPUs is fully serialized in the core code. + * No need to protect acpi_mp_wake_mailbox from concurrent accesses. + */ + if (!acpi_mp_wake_mailbox) { + acpi_mp_wake_mailbox = memremap(acpi_mp_wake_mailbox_paddr, + sizeof(*acpi_mp_wake_mailbox), + MEMREMAP_WB); + } + + /* + * Mailbox memory is shared between the firmware and OS. Firmware will + * listen on mailbox command address, and once it receives the wakeup + * command, the CPU associated with the given apicid will be booted. + * + * The value of 'apic_id' and 'wakeup_vector' must be visible to the + * firmware before the wakeup command is visible. smp_store_release() + * ensures ordering and visibility. + */ + acpi_mp_wake_mailbox->apic_id = apicid; + acpi_mp_wake_mailbox->wakeup_vector = start_ip; + smp_store_release(&acpi_mp_wake_mailbox->command, + ACPI_MP_WAKE_COMMAND_WAKEUP); + + /* + * Wait for the CPU to wake up. + * + * The CPU being woken up is essentially in a spin loop waiting to be + * woken up. It should not take long for it wake up and acknowledge by + * zeroing out ->command. + * + * ACPI specification doesn't provide any guidance on how long kernel + * has to wait for a wake up acknowledgment. It also doesn't provide + * a way to cancel a wake up request if it takes too long. + * + * In TDX environment, the VMM has control over how long it takes to + * wake up secondary. It can postpone scheduling secondary vCPU + * indefinitely. Giving up on wake up request and reporting error opens + * possible attack vector for VMM: it can wake up a secondary CPU when + * kernel doesn't expect it. Wait until positive result of the wake up + * request. + */ + while (READ_ONCE(acpi_mp_wake_mailbox->command)) + cpu_relax(); + + return 0; +} + +static void acpi_mp_disable_offlining(struct acpi_madt_multiproc_wakeup *mp_wake) +{ + cpu_hotplug_disable_offlining(); + + /* + * ACPI MADT doesn't allow to offline a CPU after it was onlined. This + * limits kexec: the second kernel won't be able to use more than one CPU. + * + * To prevent a kexec kernel from onlining secondary CPUs invalidate the + * mailbox address in the ACPI MADT wakeup structure which prevents a + * kexec kernel to use it. + * + * This is safe as the booting kernel has the mailbox address cached + * already and acpi_wakeup_cpu() uses the cached value to bring up the + * secondary CPUs. + * + * Note: This is a Linux specific convention and not covered by the + * ACPI specification. + */ + mp_wake->mailbox_address = 0; +} + +int __init acpi_parse_mp_wake(union acpi_subtable_headers *header, + const unsigned long end) +{ + struct acpi_madt_multiproc_wakeup *mp_wake; + + mp_wake = (struct acpi_madt_multiproc_wakeup *)header; + + /* + * Cannot use the standard BAD_MADT_ENTRY() to sanity check the @mp_wake + * entry. 'sizeof (struct acpi_madt_multiproc_wakeup)' can be larger + * than the actual size of the MP wakeup entry in ACPI table because the + * 'reset_vector' is only available in the V1 MP wakeup structure. + */ + if (!mp_wake) + return -EINVAL; + if (end - (unsigned long)mp_wake < ACPI_MADT_MP_WAKEUP_SIZE_V0) + return -EINVAL; + if (mp_wake->header.length < ACPI_MADT_MP_WAKEUP_SIZE_V0) + return -EINVAL; + + acpi_table_print_madt_entry(&header->common); + + acpi_mp_wake_mailbox_paddr = mp_wake->mailbox_address; + + if (mp_wake->version >= ACPI_MADT_MP_WAKEUP_VERSION_V1 && + mp_wake->header.length >= ACPI_MADT_MP_WAKEUP_SIZE_V1) { + if (acpi_mp_setup_reset(mp_wake->reset_vector)) { + pr_warn("Failed to setup MADT reset vector\n"); + acpi_mp_disable_offlining(mp_wake); + } + } else { + /* + * CPU offlining requires version 1 of the ACPI MADT wakeup + * structure. + */ + acpi_mp_disable_offlining(mp_wake); + } + + apic_update_callback(wakeup_secondary_cpu_64, acpi_wakeup_cpu); + + return 0; +} diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 89de61243272..333b16181357 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -432,6 +432,11 @@ static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a) return 5; } +static inline u8 * instr_va(struct alt_instr *i) +{ + return (u8 *)&i->instr_offset + i->instr_offset; +} + /* * Replace instructions with better alternatives for this CPU type. This runs * before SMP is initialized to avoid SMP problems with self modifying code. @@ -447,7 +452,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, { u8 insn_buff[MAX_PATCH_LEN]; u8 *instr, *replacement; - struct alt_instr *a; + struct alt_instr *a, *b; DPRINTK(ALT, "alt table %px, -> %px", start, end); @@ -473,7 +478,18 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, for (a = start; a < end; a++) { int insn_buff_sz = 0; - instr = (u8 *)&a->instr_offset + a->instr_offset; + /* + * In case of nested ALTERNATIVE()s the outer alternative might + * add more padding. To ensure consistent patching find the max + * padding for all alt_instr entries for this site (nested + * alternatives result in consecutive entries). + */ + for (b = a+1; b < end && instr_va(b) == instr_va(a); b++) { + u8 len = max(a->instrlen, b->instrlen); + a->instrlen = b->instrlen = len; + } + + instr = instr_va(a); replacement = (u8 *)&a->repl_offset + a->repl_offset; BUG_ON(a->instrlen > sizeof(insn_buff)); BUG_ON(a->cpuid >= (NCAPINTS + NBUGINTS) * 32); @@ -1641,7 +1657,7 @@ static noinline void __init alt_reloc_selftest(void) */ asm_inline volatile ( ALTERNATIVE("", "lea %[mem], %%" _ASM_ARG1 "; call __alt_reloc_selftest;", X86_FEATURE_ALWAYS) - : /* output */ + : ASM_CALL_CONSTRAINT : [mem] "m" (__alt_reloc_selftest_addr) : _ASM_ARG1 ); diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 027a8c7a2c9e..059e5c16af05 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -180,6 +180,43 @@ static struct pci_dev *next_northbridge(struct pci_dev *dev, return dev; } +/* + * SMN accesses may fail in ways that are difficult to detect here in the called + * functions amd_smn_read() and amd_smn_write(). Therefore, callers must do + * their own checking based on what behavior they expect. + * + * For SMN reads, the returned value may be zero if the register is Read-as-Zero. + * Or it may be a "PCI Error Response", e.g. all 0xFFs. The "PCI Error Response" + * can be checked here, and a proper error code can be returned. + * + * But the Read-as-Zero response cannot be verified here. A value of 0 may be + * correct in some cases, so callers must check that this correct is for the + * register/fields they need. + * + * For SMN writes, success can be determined through a "write and read back" + * However, this is not robust when done here. + * + * Possible issues: + * + * 1) Bits that are "Write-1-to-Clear". In this case, the read value should + * *not* match the write value. + * + * 2) Bits that are "Read-as-Zero"/"Writes-Ignored". This information cannot be + * known here. + * + * 3) Bits that are "Reserved / Set to 1". Ditto above. + * + * Callers of amd_smn_write() should do the "write and read back" check + * themselves, if needed. + * + * For #1, they can see if their target bits got cleared. + * + * For #2 and #3, they can check if their target bits got set as intended. + * + * This matches what is done for RDMSR/WRMSR. As long as there's no #GP, then + * the operation is considered a success, and the caller does their own + * checking. + */ static int __amd_smn_rw(u16 node, u32 address, u32 *value, bool write) { struct pci_dev *root; @@ -202,9 +239,6 @@ static int __amd_smn_rw(u16 node, u32 address, u32 *value, bool write) err = (write ? pci_write_config_dword(root, 0x64, *value) : pci_read_config_dword(root, 0x64, value)); - if (err) - pr_warn("Error %s SMN address 0x%x.\n", - (write ? "writing to" : "reading from"), address); out_unlock: mutex_unlock(&smn_mutex); @@ -213,7 +247,7 @@ out: return err; } -int amd_smn_read(u16 node, u32 address, u32 *value) +int __must_check amd_smn_read(u16 node, u32 address, u32 *value) { int err = __amd_smn_rw(node, address, value, false); @@ -226,7 +260,7 @@ int amd_smn_read(u16 node, u32 address, u32 *value) } EXPORT_SYMBOL_GPL(amd_smn_read); -int amd_smn_write(u16 node, u32 address, u32 value) +int __must_check amd_smn_write(u16 node, u32 address, u32 value) { return __amd_smn_rw(node, address, &value, true); } diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index a02bba0ed6b9..5857a0f5d514 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -34,7 +34,7 @@ obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_IA32_FEAT_CTL) += feat_ctl.o ifdef CONFIG_CPU_SUP_INTEL -obj-y += intel.o intel_pconfig.o tsx.o +obj-y += intel.o tsx.o obj-$(CONFIG_PM) += intel_epb.o endif obj-$(CONFIG_CPU_SUP_AMD) += amd.o diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 44df3f11e731..be5889bded49 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1220,14 +1220,3 @@ void amd_check_microcode(void) on_each_cpu(zenbleed_check_cpu, NULL, 1); } - -/* - * Issue a DIV 0/1 insn to clear any division data from previous DIV - * operations. - */ -void noinstr amd_clear_divider(void) -{ - asm volatile(ALTERNATIVE("", "div %2\n\t", X86_BUG_DIV0) - :: "a" (0), "d" (0), "r" (1)); -} -EXPORT_SYMBOL_GPL(amd_clear_divider); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index b6f927f6c567..45675da354f3 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1625,6 +1625,7 @@ static bool __init spec_ctrl_bhi_dis(void) enum bhi_mitigations { BHI_MITIGATION_OFF, BHI_MITIGATION_ON, + BHI_MITIGATION_VMEXIT_ONLY, }; static enum bhi_mitigations bhi_mitigation __ro_after_init = @@ -1639,6 +1640,8 @@ static int __init spectre_bhi_parse_cmdline(char *str) bhi_mitigation = BHI_MITIGATION_OFF; else if (!strcmp(str, "on")) bhi_mitigation = BHI_MITIGATION_ON; + else if (!strcmp(str, "vmexit")) + bhi_mitigation = BHI_MITIGATION_VMEXIT_ONLY; else pr_err("Ignoring unknown spectre_bhi option (%s)", str); @@ -1659,19 +1662,22 @@ static void __init bhi_select_mitigation(void) return; } + /* Mitigate in hardware if supported */ if (spec_ctrl_bhi_dis()) return; if (!IS_ENABLED(CONFIG_X86_64)) return; - /* Mitigate KVM by default */ - setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT); - pr_info("Spectre BHI mitigation: SW BHB clearing on vm exit\n"); + if (bhi_mitigation == BHI_MITIGATION_VMEXIT_ONLY) { + pr_info("Spectre BHI mitigation: SW BHB clearing on VM exit only\n"); + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT); + return; + } - /* Mitigate syscalls when the mitigation is forced =on */ + pr_info("Spectre BHI mitigation: SW BHB clearing on syscall and VM exit\n"); setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP); - pr_info("Spectre BHI mitigation: SW BHB clearing on syscall\n"); + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT); } static void __init spectre_v2_select_mitigation(void) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index fdf3489d92a4..08b95a35b5cb 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -72,19 +72,19 @@ static bool cpu_model_supports_sld __ro_after_init; */ static void check_memory_type_self_snoop_errata(struct cpuinfo_x86 *c) { - switch (c->x86_model) { - case INTEL_FAM6_CORE_YONAH: - case INTEL_FAM6_CORE2_MEROM: - case INTEL_FAM6_CORE2_MEROM_L: - case INTEL_FAM6_CORE2_PENRYN: - case INTEL_FAM6_CORE2_DUNNINGTON: - case INTEL_FAM6_NEHALEM: - case INTEL_FAM6_NEHALEM_G: - case INTEL_FAM6_NEHALEM_EP: - case INTEL_FAM6_NEHALEM_EX: - case INTEL_FAM6_WESTMERE: - case INTEL_FAM6_WESTMERE_EP: - case INTEL_FAM6_SANDYBRIDGE: + switch (c->x86_vfm) { + case INTEL_CORE_YONAH: + case INTEL_CORE2_MEROM: + case INTEL_CORE2_MEROM_L: + case INTEL_CORE2_PENRYN: + case INTEL_CORE2_DUNNINGTON: + case INTEL_NEHALEM: + case INTEL_NEHALEM_G: + case INTEL_NEHALEM_EP: + case INTEL_NEHALEM_EX: + case INTEL_WESTMERE: + case INTEL_WESTMERE_EP: + case INTEL_SANDYBRIDGE: setup_clear_cpu_cap(X86_FEATURE_SELFSNOOP); } } @@ -106,9 +106,9 @@ static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c) */ if (c->x86 != 6) return; - switch (c->x86_model) { - case INTEL_FAM6_XEON_PHI_KNL: - case INTEL_FAM6_XEON_PHI_KNM: + switch (c->x86_vfm) { + case INTEL_XEON_PHI_KNL: + case INTEL_XEON_PHI_KNM: break; default: return; @@ -134,32 +134,32 @@ static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c) * - Release note from 20180108 microcode release */ struct sku_microcode { - u8 model; + u32 vfm; u8 stepping; u32 microcode; }; static const struct sku_microcode spectre_bad_microcodes[] = { - { INTEL_FAM6_KABYLAKE, 0x0B, 0x80 }, - { INTEL_FAM6_KABYLAKE, 0x0A, 0x80 }, - { INTEL_FAM6_KABYLAKE, 0x09, 0x80 }, - { INTEL_FAM6_KABYLAKE_L, 0x0A, 0x80 }, - { INTEL_FAM6_KABYLAKE_L, 0x09, 0x80 }, - { INTEL_FAM6_SKYLAKE_X, 0x03, 0x0100013e }, - { INTEL_FAM6_SKYLAKE_X, 0x04, 0x0200003c }, - { INTEL_FAM6_BROADWELL, 0x04, 0x28 }, - { INTEL_FAM6_BROADWELL_G, 0x01, 0x1b }, - { INTEL_FAM6_BROADWELL_D, 0x02, 0x14 }, - { INTEL_FAM6_BROADWELL_D, 0x03, 0x07000011 }, - { INTEL_FAM6_BROADWELL_X, 0x01, 0x0b000025 }, - { INTEL_FAM6_HASWELL_L, 0x01, 0x21 }, - { INTEL_FAM6_HASWELL_G, 0x01, 0x18 }, - { INTEL_FAM6_HASWELL, 0x03, 0x23 }, - { INTEL_FAM6_HASWELL_X, 0x02, 0x3b }, - { INTEL_FAM6_HASWELL_X, 0x04, 0x10 }, - { INTEL_FAM6_IVYBRIDGE_X, 0x04, 0x42a }, + { INTEL_KABYLAKE, 0x0B, 0x80 }, + { INTEL_KABYLAKE, 0x0A, 0x80 }, + { INTEL_KABYLAKE, 0x09, 0x80 }, + { INTEL_KABYLAKE_L, 0x0A, 0x80 }, + { INTEL_KABYLAKE_L, 0x09, 0x80 }, + { INTEL_SKYLAKE_X, 0x03, 0x0100013e }, + { INTEL_SKYLAKE_X, 0x04, 0x0200003c }, + { INTEL_BROADWELL, 0x04, 0x28 }, + { INTEL_BROADWELL_G, 0x01, 0x1b }, + { INTEL_BROADWELL_D, 0x02, 0x14 }, + { INTEL_BROADWELL_D, 0x03, 0x07000011 }, + { INTEL_BROADWELL_X, 0x01, 0x0b000025 }, + { INTEL_HASWELL_L, 0x01, 0x21 }, + { INTEL_HASWELL_G, 0x01, 0x18 }, + { INTEL_HASWELL, 0x03, 0x23 }, + { INTEL_HASWELL_X, 0x02, 0x3b }, + { INTEL_HASWELL_X, 0x04, 0x10 }, + { INTEL_IVYBRIDGE_X, 0x04, 0x42a }, /* Observed in the wild */ - { INTEL_FAM6_SANDYBRIDGE_X, 0x06, 0x61b }, - { INTEL_FAM6_SANDYBRIDGE_X, 0x07, 0x712 }, + { INTEL_SANDYBRIDGE_X, 0x06, 0x61b }, + { INTEL_SANDYBRIDGE_X, 0x07, 0x712 }, }; static bool bad_spectre_microcode(struct cpuinfo_x86 *c) @@ -173,11 +173,8 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_HYPERVISOR)) return false; - if (c->x86 != 6) - return false; - for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) { - if (c->x86_model == spectre_bad_microcodes[i].model && + if (c->x86_vfm == spectre_bad_microcodes[i].vfm && c->x86_stepping == spectre_bad_microcodes[i].stepping) return (c->microcode <= spectre_bad_microcodes[i].microcode); } @@ -190,83 +187,35 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) #define TME_ACTIVATE_LOCKED(x) (x & 0x1) #define TME_ACTIVATE_ENABLED(x) (x & 0x2) -#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */ -#define TME_ACTIVATE_POLICY_AES_XTS_128 0 - #define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */ -#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */ -#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1 - -/* Values for mktme_status (SW only construct) */ -#define MKTME_ENABLED 0 -#define MKTME_DISABLED 1 -#define MKTME_UNINITIALIZED 2 -static int mktme_status = MKTME_UNINITIALIZED; - static void detect_tme_early(struct cpuinfo_x86 *c) { - u64 tme_activate, tme_policy, tme_crypto_algs; - int keyid_bits = 0, nr_keyids = 0; - static u64 tme_activate_cpu0 = 0; + u64 tme_activate; + int keyid_bits; rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate); - if (mktme_status != MKTME_UNINITIALIZED) { - if (tme_activate != tme_activate_cpu0) { - /* Broken BIOS? */ - pr_err_once("x86/tme: configuration is inconsistent between CPUs\n"); - pr_err_once("x86/tme: MKTME is not usable\n"); - mktme_status = MKTME_DISABLED; - - /* Proceed. We may need to exclude bits from x86_phys_bits. */ - } - } else { - tme_activate_cpu0 = tme_activate; - } - if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) { pr_info_once("x86/tme: not enabled by BIOS\n"); - mktme_status = MKTME_DISABLED; clear_cpu_cap(c, X86_FEATURE_TME); return; } - - if (mktme_status != MKTME_UNINITIALIZED) - goto detect_keyid_bits; - - pr_info("x86/tme: enabled by BIOS\n"); - - tme_policy = TME_ACTIVATE_POLICY(tme_activate); - if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128) - pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy); - - tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate); - if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) { - pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n", - tme_crypto_algs); - mktme_status = MKTME_DISABLED; - } -detect_keyid_bits: + pr_info_once("x86/tme: enabled by BIOS\n"); keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate); - nr_keyids = (1UL << keyid_bits) - 1; - if (nr_keyids) { - pr_info_once("x86/mktme: enabled by BIOS\n"); - pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids); - } else { - pr_info_once("x86/mktme: disabled by BIOS\n"); - } - - if (mktme_status == MKTME_UNINITIALIZED) { - /* MKTME is usable */ - mktme_status = MKTME_ENABLED; - } + if (!keyid_bits) + return; /* - * KeyID bits effectively lower the number of physical address - * bits. Update cpuinfo_x86::x86_phys_bits accordingly. + * KeyID bits are set by BIOS and can be present regardless + * of whether the kernel is using them. They effectively lower + * the number of physical address bits. + * + * Update cpuinfo_x86::x86_phys_bits accordingly. */ c->x86_phys_bits -= keyid_bits; + pr_info_once("x86/mktme: BIOS enabled: x86_phys_bits reduced by %d\n", + keyid_bits); } void intel_unlock_cpuid_leafs(struct cpuinfo_x86 *c) @@ -320,7 +269,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) * need the microcode to have already been loaded... so if it is * not, recommend a BIOS update and disable large pages. */ - if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_stepping <= 2 && + if (c->x86_vfm == INTEL_ATOM_BONNELL && c->x86_stepping <= 2 && c->microcode < 0x20e) { pr_warn("Atom PSE erratum detected, BIOS microcode update recommended\n"); clear_cpu_cap(c, X86_FEATURE_PSE); @@ -352,17 +301,13 @@ static void early_init_intel(struct cpuinfo_x86 *c) } /* Penwell and Cloverview have the TSC which doesn't sleep on S3 */ - if (c->x86 == 6) { - switch (c->x86_model) { - case INTEL_FAM6_ATOM_SALTWELL_MID: - case INTEL_FAM6_ATOM_SALTWELL_TABLET: - case INTEL_FAM6_ATOM_SILVERMONT_MID: - case INTEL_FAM6_ATOM_AIRMONT_NP: - set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC_S3); - break; - default: - break; - } + switch (c->x86_vfm) { + case INTEL_ATOM_SALTWELL_MID: + case INTEL_ATOM_SALTWELL_TABLET: + case INTEL_ATOM_SILVERMONT_MID: + case INTEL_ATOM_AIRMONT_NP: + set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC_S3); + break; } /* @@ -401,7 +346,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) * should be false so that __flush_tlb_all() causes CR3 instead of CR4.PGE * to be modified. */ - if (c->x86 == 5 && c->x86_model == 9) { + if (c->x86_vfm == INTEL_QUARK_X1000) { pr_info("Disabling PGE capability bit\n"); setup_clear_cpu_cap(X86_FEATURE_PGE); } @@ -633,12 +578,13 @@ static void init_intel(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_PEBS); } - if (c->x86 == 6 && boot_cpu_has(X86_FEATURE_CLFLUSH) && - (c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47)) + if (boot_cpu_has(X86_FEATURE_CLFLUSH) && + (c->x86_vfm == INTEL_CORE2_DUNNINGTON || + c->x86_vfm == INTEL_NEHALEM_EX || + c->x86_vfm == INTEL_WESTMERE_EX)) set_cpu_bug(c, X86_BUG_CLFLUSH_MONITOR); - if (c->x86 == 6 && boot_cpu_has(X86_FEATURE_MWAIT) && - ((c->x86_model == INTEL_FAM6_ATOM_GOLDMONT))) + if (boot_cpu_has(X86_FEATURE_MWAIT) && c->x86_vfm == INTEL_ATOM_GOLDMONT) set_cpu_bug(c, X86_BUG_MONITOR); #ifdef CONFIG_X86_64 @@ -1254,9 +1200,9 @@ void handle_bus_lock(struct pt_regs *regs) * feature even though they do not enumerate IA32_CORE_CAPABILITIES. */ static const struct x86_cpu_id split_lock_cpu_ids[] __initconst = { - X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, 0), - X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, 0), - X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, 0), + X86_MATCH_VFM(INTEL_ICELAKE_X, 0), + X86_MATCH_VFM(INTEL_ICELAKE_L, 0), + X86_MATCH_VFM(INTEL_ICELAKE_D, 0), {} }; diff --git a/arch/x86/kernel/cpu/intel_pconfig.c b/arch/x86/kernel/cpu/intel_pconfig.c deleted file mode 100644 index 5be2b1790282..000000000000 --- a/arch/x86/kernel/cpu/intel_pconfig.c +++ /dev/null @@ -1,84 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Intel PCONFIG instruction support. - * - * Copyright (C) 2017 Intel Corporation - * - * Author: - * Kirill A. Shutemov <kirill.shutemov@linux.intel.com> - */ -#include <linux/bug.h> -#include <linux/limits.h> - -#include <asm/cpufeature.h> -#include <asm/intel_pconfig.h> - -#define PCONFIG_CPUID 0x1b - -#define PCONFIG_CPUID_SUBLEAF_MASK ((1 << 12) - 1) - -/* Subleaf type (EAX) for PCONFIG CPUID leaf (0x1B) */ -enum { - PCONFIG_CPUID_SUBLEAF_INVALID = 0, - PCONFIG_CPUID_SUBLEAF_TARGETID = 1, -}; - -/* Bitmask of supported targets */ -static u64 targets_supported __read_mostly; - -int pconfig_target_supported(enum pconfig_target target) -{ - /* - * We would need to re-think the implementation once we get > 64 - * PCONFIG targets. Spec allows up to 2^32 targets. - */ - BUILD_BUG_ON(PCONFIG_TARGET_NR >= 64); - - if (WARN_ON_ONCE(target >= 64)) - return 0; - return targets_supported & (1ULL << target); -} - -static int __init intel_pconfig_init(void) -{ - int subleaf; - - if (!boot_cpu_has(X86_FEATURE_PCONFIG)) - return 0; - - /* - * Scan subleafs of PCONFIG CPUID leaf. - * - * Subleafs of the same type need not to be consecutive. - * - * Stop on the first invalid subleaf type. All subleafs after the first - * invalid are invalid too. - */ - for (subleaf = 0; subleaf < INT_MAX; subleaf++) { - struct cpuid_regs regs; - - cpuid_count(PCONFIG_CPUID, subleaf, - ®s.eax, ®s.ebx, ®s.ecx, ®s.edx); - - switch (regs.eax & PCONFIG_CPUID_SUBLEAF_MASK) { - case PCONFIG_CPUID_SUBLEAF_INVALID: - /* Stop on the first invalid subleaf */ - goto out; - case PCONFIG_CPUID_SUBLEAF_TARGETID: - /* Mark supported PCONFIG targets */ - if (regs.ebx < 64) - targets_supported |= (1ULL << regs.ebx); - if (regs.ecx < 64) - targets_supported |= (1ULL << regs.ecx); - if (regs.edx < 64) - targets_supported |= (1ULL << regs.edx); - break; - default: - /* Unknown CPUID.PCONFIG subleaf: ignore */ - break; - } - } -out: - return 0; -} -arch_initcall(intel_pconfig_init); diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index ad0623b659ed..b85ec7a4ec9e 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -677,10 +677,9 @@ DEFINE_PER_CPU(unsigned, mce_poll_count); * is already totally * confused. In this case it's likely it will * not fully execute the machine check handler either. */ -bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) +void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) { struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array); - bool error_seen = false; struct mce m; int i; @@ -754,8 +753,6 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) continue; log_it: - error_seen = true; - if (flags & MCP_DONTLOG) goto clear_it; @@ -787,8 +784,6 @@ clear_it: */ sync_core(); - - return error_seen; } EXPORT_SYMBOL_GPL(machine_check_poll); diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c index 94953d749475..49ed3428785d 100644 --- a/arch/x86/kernel/cpu/mce/inject.c +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -487,12 +487,16 @@ static void prepare_msrs(void *info) wrmsrl(MSR_AMD64_SMCA_MCx_ADDR(b), m.addr); } - wrmsrl(MSR_AMD64_SMCA_MCx_MISC(b), m.misc); wrmsrl(MSR_AMD64_SMCA_MCx_SYND(b), m.synd); + + if (m.misc) + wrmsrl(MSR_AMD64_SMCA_MCx_MISC(b), m.misc); } else { wrmsrl(MSR_IA32_MCx_STATUS(b), m.status); wrmsrl(MSR_IA32_MCx_ADDR(b), m.addr); - wrmsrl(MSR_IA32_MCx_MISC(b), m.misc); + + if (m.misc) + wrmsrl(MSR_IA32_MCx_MISC(b), m.misc); } } @@ -795,4 +799,5 @@ static void __exit inject_exit(void) module_init(inject_init); module_exit(inject_exit); +MODULE_DESCRIPTION("Machine check injection support"); MODULE_LICENSE("GPL"); diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh index 1db560ed2ca3..68f537347466 100644 --- a/arch/x86/kernel/cpu/mkcapflags.sh +++ b/arch/x86/kernel/cpu/mkcapflags.sh @@ -30,8 +30,7 @@ dump_array() # If the /* comment */ starts with a quote string, grab that. VALUE="$(echo "$i" | sed -n 's@.*/\* *\("[^"]*"\).*\*/@\1@p')" - [ -z "$VALUE" ] && VALUE="\"$NAME\"" - [ "$VALUE" = '""' ] && continue + [ ! "$VALUE" ] && continue # Name is uppercase, VALUE is all lowercase VALUE="$(echo "$VALUE" | tr A-Z a-z)" diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 9f53b128bdb4..851b561850e0 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -562,7 +562,8 @@ void free_rmid(u32 closid, u32 rmid) * allows architectures that ignore the closid parameter to avoid an * unnecessary check. */ - if (idx == resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID, + if (!resctrl_arch_mon_capable() || + idx == resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID, RESCTRL_RESERVED_RMID)) return; diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 11f83d07925e..00189cdeb775 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -41,80 +41,97 @@ #define CPUID_VMWARE_INFO_LEAF 0x40000000 #define CPUID_VMWARE_FEATURES_LEAF 0x40000010 -#define CPUID_VMWARE_FEATURES_ECX_VMMCALL BIT(0) -#define CPUID_VMWARE_FEATURES_ECX_VMCALL BIT(1) -#define VMWARE_HYPERVISOR_MAGIC 0x564D5868 - -#define VMWARE_CMD_GETVERSION 10 -#define VMWARE_CMD_GETHZ 45 -#define VMWARE_CMD_GETVCPU_INFO 68 -#define VMWARE_CMD_LEGACY_X2APIC 3 -#define VMWARE_CMD_VCPU_RESERVED 31 -#define VMWARE_CMD_STEALCLOCK 91 +#define GETVCPU_INFO_LEGACY_X2APIC BIT(3) +#define GETVCPU_INFO_VCPU_RESERVED BIT(31) #define STEALCLOCK_NOT_AVAILABLE (-1) #define STEALCLOCK_DISABLED 0 #define STEALCLOCK_ENABLED 1 -#define VMWARE_PORT(cmd, eax, ebx, ecx, edx) \ - __asm__("inl (%%dx), %%eax" : \ - "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) : \ - "a"(VMWARE_HYPERVISOR_MAGIC), \ - "c"(VMWARE_CMD_##cmd), \ - "d"(VMWARE_HYPERVISOR_PORT), "b"(UINT_MAX) : \ - "memory") - -#define VMWARE_VMCALL(cmd, eax, ebx, ecx, edx) \ - __asm__("vmcall" : \ - "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) : \ - "a"(VMWARE_HYPERVISOR_MAGIC), \ - "c"(VMWARE_CMD_##cmd), \ - "d"(0), "b"(UINT_MAX) : \ - "memory") - -#define VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx) \ - __asm__("vmmcall" : \ - "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) : \ - "a"(VMWARE_HYPERVISOR_MAGIC), \ - "c"(VMWARE_CMD_##cmd), \ - "d"(0), "b"(UINT_MAX) : \ - "memory") - -#define VMWARE_CMD(cmd, eax, ebx, ecx, edx) do { \ - switch (vmware_hypercall_mode) { \ - case CPUID_VMWARE_FEATURES_ECX_VMCALL: \ - VMWARE_VMCALL(cmd, eax, ebx, ecx, edx); \ - break; \ - case CPUID_VMWARE_FEATURES_ECX_VMMCALL: \ - VMWARE_VMMCALL(cmd, eax, ebx, ecx, edx); \ - break; \ - default: \ - VMWARE_PORT(cmd, eax, ebx, ecx, edx); \ - break; \ - } \ - } while (0) - struct vmware_steal_time { union { - uint64_t clock; /* stolen time counter in units of vtsc */ + u64 clock; /* stolen time counter in units of vtsc */ struct { /* only for little-endian */ - uint32_t clock_low; - uint32_t clock_high; + u32 clock_low; + u32 clock_high; }; }; - uint64_t reserved[7]; + u64 reserved[7]; }; static unsigned long vmware_tsc_khz __ro_after_init; static u8 vmware_hypercall_mode __ro_after_init; +unsigned long vmware_hypercall_slow(unsigned long cmd, + unsigned long in1, unsigned long in3, + unsigned long in4, unsigned long in5, + u32 *out1, u32 *out2, u32 *out3, + u32 *out4, u32 *out5) +{ + unsigned long out0, rbx, rcx, rdx, rsi, rdi; + + switch (vmware_hypercall_mode) { + case CPUID_VMWARE_FEATURES_ECX_VMCALL: + asm_inline volatile ("vmcall" + : "=a" (out0), "=b" (rbx), "=c" (rcx), + "=d" (rdx), "=S" (rsi), "=D" (rdi) + : "a" (VMWARE_HYPERVISOR_MAGIC), + "b" (in1), + "c" (cmd), + "d" (in3), + "S" (in4), + "D" (in5) + : "cc", "memory"); + break; + case CPUID_VMWARE_FEATURES_ECX_VMMCALL: + asm_inline volatile ("vmmcall" + : "=a" (out0), "=b" (rbx), "=c" (rcx), + "=d" (rdx), "=S" (rsi), "=D" (rdi) + : "a" (VMWARE_HYPERVISOR_MAGIC), + "b" (in1), + "c" (cmd), + "d" (in3), + "S" (in4), + "D" (in5) + : "cc", "memory"); + break; + default: + asm_inline volatile ("movw %[port], %%dx; inl (%%dx), %%eax" + : "=a" (out0), "=b" (rbx), "=c" (rcx), + "=d" (rdx), "=S" (rsi), "=D" (rdi) + : [port] "i" (VMWARE_HYPERVISOR_PORT), + "a" (VMWARE_HYPERVISOR_MAGIC), + "b" (in1), + "c" (cmd), + "d" (in3), + "S" (in4), + "D" (in5) + : "cc", "memory"); + break; + } + + if (out1) + *out1 = rbx; + if (out2) + *out2 = rcx; + if (out3) + *out3 = rdx; + if (out4) + *out4 = rsi; + if (out5) + *out5 = rdi; + + return out0; +} + static inline int __vmware_platform(void) { - uint32_t eax, ebx, ecx, edx; - VMWARE_CMD(GETVERSION, eax, ebx, ecx, edx); - return eax != (uint32_t)-1 && ebx == VMWARE_HYPERVISOR_MAGIC; + u32 eax, ebx, ecx; + + eax = vmware_hypercall3(VMWARE_CMD_GETVERSION, 0, &ebx, &ecx); + return eax != UINT_MAX && ebx == VMWARE_HYPERVISOR_MAGIC; } static unsigned long vmware_get_tsc_khz(void) @@ -166,21 +183,12 @@ static void __init vmware_cyc2ns_setup(void) pr_info("using clock offset of %llu ns\n", d->cyc2ns_offset); } -static int vmware_cmd_stealclock(uint32_t arg1, uint32_t arg2) +static int vmware_cmd_stealclock(u32 addr_hi, u32 addr_lo) { - uint32_t result, info; - - asm volatile (VMWARE_HYPERCALL : - "=a"(result), - "=c"(info) : - "a"(VMWARE_HYPERVISOR_MAGIC), - "b"(0), - "c"(VMWARE_CMD_STEALCLOCK), - "d"(0), - "S"(arg1), - "D"(arg2) : - "memory"); - return result; + u32 info; + + return vmware_hypercall5(VMWARE_CMD_STEALCLOCK, 0, 0, addr_hi, addr_lo, + &info); } static bool stealclock_enable(phys_addr_t pa) @@ -215,15 +223,15 @@ static bool vmware_is_stealclock_available(void) * Return: * The steal clock reading in ns. */ -static uint64_t vmware_steal_clock(int cpu) +static u64 vmware_steal_clock(int cpu) { struct vmware_steal_time *steal = &per_cpu(vmw_steal_time, cpu); - uint64_t clock; + u64 clock; if (IS_ENABLED(CONFIG_64BIT)) clock = READ_ONCE(steal->clock); else { - uint32_t initial_high, low, high; + u32 initial_high, low, high; do { initial_high = READ_ONCE(steal->clock_high); @@ -235,7 +243,7 @@ static uint64_t vmware_steal_clock(int cpu) high = READ_ONCE(steal->clock_high); } while (initial_high != high); - clock = ((uint64_t)high << 32) | low; + clock = ((u64)high << 32) | low; } return mul_u64_u32_shr(clock, vmware_cyc2ns.cyc2ns_mul, @@ -389,13 +397,13 @@ static void __init vmware_set_capabilities(void) static void __init vmware_platform_setup(void) { - uint32_t eax, ebx, ecx, edx; - uint64_t lpj, tsc_khz; + u32 eax, ebx, ecx; + u64 lpj, tsc_khz; - VMWARE_CMD(GETHZ, eax, ebx, ecx, edx); + eax = vmware_hypercall3(VMWARE_CMD_GETHZ, UINT_MAX, &ebx, &ecx); if (ebx != UINT_MAX) { - lpj = tsc_khz = eax | (((uint64_t)ebx) << 32); + lpj = tsc_khz = eax | (((u64)ebx) << 32); do_div(tsc_khz, 1000); WARN_ON(tsc_khz >> 32); pr_info("TSC freq read from hypervisor : %lu.%03lu MHz\n", @@ -446,7 +454,7 @@ static u8 __init vmware_select_hypercall(void) * If !boot_cpu_has(X86_FEATURE_HYPERVISOR), vmware_hypercall_mode * intentionally defaults to 0. */ -static uint32_t __init vmware_platform(void) +static u32 __init vmware_platform(void) { if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { unsigned int eax; @@ -474,12 +482,65 @@ static uint32_t __init vmware_platform(void) /* Checks if hypervisor supports x2apic without VT-D interrupt remapping. */ static bool __init vmware_legacy_x2apic_available(void) { - uint32_t eax, ebx, ecx, edx; - VMWARE_CMD(GETVCPU_INFO, eax, ebx, ecx, edx); - return !(eax & BIT(VMWARE_CMD_VCPU_RESERVED)) && - (eax & BIT(VMWARE_CMD_LEGACY_X2APIC)); + u32 eax; + + eax = vmware_hypercall1(VMWARE_CMD_GETVCPU_INFO, 0); + return !(eax & GETVCPU_INFO_VCPU_RESERVED) && + (eax & GETVCPU_INFO_LEGACY_X2APIC); } +#ifdef CONFIG_INTEL_TDX_GUEST +/* + * TDCALL[TDG.VP.VMCALL] uses %rax (arg0) and %rcx (arg2). Therefore, + * we remap those registers to %r12 and %r13, respectively. + */ +unsigned long vmware_tdx_hypercall(unsigned long cmd, + unsigned long in1, unsigned long in3, + unsigned long in4, unsigned long in5, + u32 *out1, u32 *out2, u32 *out3, + u32 *out4, u32 *out5) +{ + struct tdx_module_args args = {}; + + if (!hypervisor_is_type(X86_HYPER_VMWARE)) { + pr_warn_once("Incorrect usage\n"); + return ULONG_MAX; + } + + if (cmd & ~VMWARE_CMD_MASK) { + pr_warn_once("Out of range command %lx\n", cmd); + return ULONG_MAX; + } + + args.rbx = in1; + args.rdx = in3; + args.rsi = in4; + args.rdi = in5; + args.r10 = VMWARE_TDX_VENDOR_LEAF; + args.r11 = VMWARE_TDX_HCALL_FUNC; + args.r12 = VMWARE_HYPERVISOR_MAGIC; + args.r13 = cmd; + /* CPL */ + args.r15 = 0; + + __tdx_hypercall(&args); + + if (out1) + *out1 = args.rbx; + if (out2) + *out2 = args.r13; + if (out3) + *out3 = args.rdx; + if (out4) + *out4 = args.rsi; + if (out5) + *out5 = args.rdi; + + return args.r12; +} +EXPORT_SYMBOL_GPL(vmware_tdx_hypercall); +#endif + #ifdef CONFIG_AMD_MEM_ENCRYPT static void vmware_sev_es_hcall_prepare(struct ghcb *ghcb, struct pt_regs *regs) diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index f06501445cd9..340af8155658 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -128,6 +128,18 @@ void native_machine_crash_shutdown(struct pt_regs *regs) #ifdef CONFIG_HPET_TIMER hpet_disable(); #endif + + /* + * Non-crash kexec calls enc_kexec_begin() while scheduling is still + * active. This allows the callback to wait until all in-flight + * shared<->private conversions are complete. In a crash scenario, + * enc_kexec_begin() gets called after all but one CPU have been shut + * down and interrupts have been disabled. This allows the callback to + * detect a race with the conversion and report it. + */ + x86_platform.guest.enc_kexec_begin(); + x86_platform.guest.enc_kexec_finish(); + crash_save_cpu(regs, safe_smp_processor_id()); } diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 8e3c53b4d070..64280879c68c 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -83,7 +83,7 @@ static int x86_of_pci_irq_enable(struct pci_dev *dev) ret = pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin); if (ret) - return ret; + return pcibios_err_to_errno(ret); if (!pin) return 0; diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 68b09f718f10..4893d30ce438 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -828,7 +828,7 @@ u64 __init e820__memblock_alloc_reserved(u64 size, u64 align) /* * Find the highest page frame number we have available */ -static unsigned long __init e820_end_pfn(unsigned long limit_pfn, enum e820_type type) +static unsigned long __init e820__end_ram_pfn(unsigned long limit_pfn) { int i; unsigned long last_pfn = 0; @@ -839,7 +839,8 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn, enum e820_type unsigned long start_pfn; unsigned long end_pfn; - if (entry->type != type) + if (entry->type != E820_TYPE_RAM && + entry->type != E820_TYPE_ACPI) continue; start_pfn = entry->addr >> PAGE_SHIFT; @@ -865,12 +866,12 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn, enum e820_type unsigned long __init e820__end_of_ram_pfn(void) { - return e820_end_pfn(MAX_ARCH_PFN, E820_TYPE_RAM); + return e820__end_ram_pfn(MAX_ARCH_PFN); } unsigned long __init e820__end_of_low_ram_pfn(void) { - return e820_end_pfn(1UL << (32 - PAGE_SHIFT), E820_TYPE_RAM); + return e820__end_ram_pfn(1UL << (32 - PAGE_SHIFT)); } static void __init early_panic(char *msg) diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h index 05df04f39628..2ee0b9c53dcc 100644 --- a/arch/x86/kernel/fpu/xstate.h +++ b/arch/x86/kernel/fpu/xstate.h @@ -106,21 +106,17 @@ static inline u64 xfeatures_mask_independent(void) * Otherwise, if XSAVEOPT is enabled, XSAVEOPT replaces XSAVE because XSAVEOPT * supports modified optimization which is not supported by XSAVE. * - * We use XSAVE as a fallback. - * - * The 661 label is defined in the ALTERNATIVE* macros as the address of the - * original instruction which gets replaced. We need to use it here as the - * address of the instruction where we might get an exception at. + * Use XSAVE as a fallback. */ #define XSTATE_XSAVE(st, lmask, hmask, err) \ - asm volatile(ALTERNATIVE_3(XSAVE, \ + asm volatile("1: " ALTERNATIVE_3(XSAVE, \ XSAVEOPT, X86_FEATURE_XSAVEOPT, \ XSAVEC, X86_FEATURE_XSAVEC, \ XSAVES, X86_FEATURE_XSAVES) \ "\n" \ "xor %[err], %[err]\n" \ "3:\n" \ - _ASM_EXTABLE_TYPE_REG(661b, 3b, EX_TYPE_EFAULT_REG, %[err]) \ + _ASM_EXTABLE_TYPE_REG(1b, 3b, EX_TYPE_EFAULT_REG, %[err]) \ : [err] "=r" (err) \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") @@ -130,11 +126,11 @@ static inline u64 xfeatures_mask_independent(void) * XSAVE area format. */ #define XSTATE_XRESTORE(st, lmask, hmask) \ - asm volatile(ALTERNATIVE(XRSTOR, \ + asm volatile("1: " ALTERNATIVE(XRSTOR, \ XRSTORS, X86_FEATURE_XSAVES) \ "\n" \ "3:\n" \ - _ASM_EXTABLE_TYPE(661b, 3b, EX_TYPE_FPU_RESTORE) \ + _ASM_EXTABLE_TYPE(1b, 3b, EX_TYPE_FPU_RESTORE) \ : \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index b8441147eb5e..f63f8fd00a91 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -835,6 +835,13 @@ void __noreturn stop_this_cpu(void *dummy) */ cpumask_clear_cpu(cpu, &cpus_stop_mask); +#ifdef CONFIG_SMP + if (smp_ops.stop_this_cpu) { + smp_ops.stop_this_cpu(); + unreachable(); + } +#endif + for (;;) { /* * Use native_halt() so that memory contents don't change diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index f3130f762784..0e0a4cf6b5eb 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -12,6 +12,7 @@ #include <linux/delay.h> #include <linux/objtool.h> #include <linux/pgtable.h> +#include <linux/kexec.h> #include <acpi/reboot.h> #include <asm/io.h> #include <asm/apic.h> @@ -716,6 +717,14 @@ static void native_machine_emergency_restart(void) void native_machine_shutdown(void) { + /* + * Call enc_kexec_begin() while all CPUs are still active and + * interrupts are enabled. This will allow all in-flight memory + * conversions to finish cleanly. + */ + if (kexec_in_progress) + x86_platform.guest.enc_kexec_begin(); + /* Stop the cpus and apics */ #ifdef CONFIG_X86_IO_APIC /* @@ -752,6 +761,9 @@ void native_machine_shutdown(void) #ifdef CONFIG_X86_64 x86_platform.iommu_shutdown(); #endif + + if (kexec_in_progress) + x86_platform.guest.enc_kexec_finish(); } static void __machine_emergency_restart(int emergency) @@ -868,6 +880,12 @@ static int crash_nmi_callback(unsigned int val, struct pt_regs *regs) cpu_emergency_disable_virtualization(); atomic_dec(&waiting_for_crash_ipi); + + if (smp_ops.stop_this_cpu) { + smp_ops.stop_this_cpu(); + unreachable(); + } + /* Assume hlt works */ halt(); for (;;) diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index 56cab1bb25f5..042c9a0334e9 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -5,6 +5,8 @@ */ #include <linux/linkage.h> +#include <linux/stringify.h> +#include <asm/alternative.h> #include <asm/page_types.h> #include <asm/kexec.h> #include <asm/processor-flags.h> @@ -145,16 +147,15 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) * Set cr4 to a known state: * - physical address extension enabled * - 5-level paging, if it was enabled before + * - Machine check exception on TDX guest, if it was enabled before. + * Clearing MCE might not be allowed in TDX guests, depending on setup. + * + * Use R13 that contains the original CR4 value, read in relocate_kernel(). + * PAE is always set in the original CR4. */ - movl $X86_CR4_PAE, %eax - testq $X86_CR4_LA57, %r13 - jz 1f - orl $X86_CR4_LA57, %eax -1: - movq %rax, %cr4 - - jmp 1f -1: + andl $(X86_CR4_PAE | X86_CR4_LA57), %r13d + ALTERNATIVE "", __stringify(orl $X86_CR4_MCE, %r13d), X86_FEATURE_TDX_GUEST + movq %r13, %cr4 /* Flush the TLB (needed?) */ movq %r9, %cr3 @@ -165,9 +166,9 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) * used by kexec. Flush the caches before copying the kernel. */ testq %r12, %r12 - jz 1f + jz .Lsme_off wbinvd -1: +.Lsme_off: movq %rcx, %r11 call swap_pages @@ -187,7 +188,7 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) */ testq %r11, %r11 - jnz 1f + jnz .Lrelocate xorl %eax, %eax xorl %ebx, %ebx xorl %ecx, %ecx @@ -208,7 +209,7 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) ret int3 -1: +.Lrelocate: popq %rdx leaq PAGE_SIZE(%r10), %rsp ANNOTATE_RETPOLINE_SAFE diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 05c5aa951da7..728927e4ba51 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -165,6 +165,7 @@ unsigned long saved_video_mode; static char __initdata command_line[COMMAND_LINE_SIZE]; #ifdef CONFIG_CMDLINE_BOOL static char __initdata builtin_cmdline[COMMAND_LINE_SIZE] = CONFIG_CMDLINE; +bool builtin_cmdline_added __ro_after_init; #endif #if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE) @@ -765,6 +766,7 @@ void __init setup_arch(char **cmdline_p) strscpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); } #endif + builtin_cmdline_added = true; #endif strscpy(command_line, boot_command_line, COMMAND_LINE_SIZE); diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index e42faa792c07..52e1f3f0b361 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -27,25 +27,7 @@ unsigned long profile_pc(struct pt_regs *regs) { - unsigned long pc = instruction_pointer(regs); - - if (!user_mode(regs) && in_lock_functions(pc)) { -#ifdef CONFIG_FRAME_POINTER - return *(unsigned long *)(regs->bp + sizeof(long)); -#else - unsigned long *sp = (unsigned long *)regs->sp; - /* - * Return address is either directly at stack pointer - * or above a saved flags. Eflags has bits 22-31 zero, - * kernel addresses don't. - */ - if (sp[0] >> 22) - return sp[0]; - if (sp[1] >> 22) - return sp[1]; -#endif - } - return pc; + return instruction_pointer(regs); } EXPORT_SYMBOL(profile_pc); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 06b170759e5b..d4462fb26299 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -50,9 +50,9 @@ int tsc_clocksource_reliable; static int __read_mostly tsc_force_recalibrate; -static u32 art_to_tsc_numerator; -static u32 art_to_tsc_denominator; -static u64 art_to_tsc_offset; +static struct clocksource_base art_base_clk = { + .id = CSID_X86_ART, +}; static bool have_art; struct cyc2ns { @@ -1074,7 +1074,7 @@ core_initcall(cpufreq_register_tsc_scaling); */ static void __init detect_art(void) { - unsigned int unused[2]; + unsigned int unused; if (boot_cpu_data.cpuid_level < ART_CPUID_LEAF) return; @@ -1089,13 +1089,14 @@ static void __init detect_art(void) tsc_async_resets) return; - cpuid(ART_CPUID_LEAF, &art_to_tsc_denominator, - &art_to_tsc_numerator, unused, unused+1); + cpuid(ART_CPUID_LEAF, &art_base_clk.denominator, + &art_base_clk.numerator, &art_base_clk.freq_khz, &unused); - if (art_to_tsc_denominator < ART_MIN_DENOMINATOR) + art_base_clk.freq_khz /= KHZ; + if (art_base_clk.denominator < ART_MIN_DENOMINATOR) return; - rdmsrl(MSR_IA32_TSC_ADJUST, art_to_tsc_offset); + rdmsrl(MSR_IA32_TSC_ADJUST, art_base_clk.offset); /* Make this sticky over multiple CPU init calls */ setup_force_cpu_cap(X86_FEATURE_ART); @@ -1296,67 +1297,6 @@ int unsynchronized_tsc(void) return 0; } -/* - * Convert ART to TSC given numerator/denominator found in detect_art() - */ -struct system_counterval_t convert_art_to_tsc(u64 art) -{ - u64 tmp, res, rem; - - rem = do_div(art, art_to_tsc_denominator); - - res = art * art_to_tsc_numerator; - tmp = rem * art_to_tsc_numerator; - - do_div(tmp, art_to_tsc_denominator); - res += tmp + art_to_tsc_offset; - - return (struct system_counterval_t) { - .cs_id = have_art ? CSID_X86_TSC : CSID_GENERIC, - .cycles = res, - }; -} -EXPORT_SYMBOL(convert_art_to_tsc); - -/** - * convert_art_ns_to_tsc() - Convert ART in nanoseconds to TSC. - * @art_ns: ART (Always Running Timer) in unit of nanoseconds - * - * PTM requires all timestamps to be in units of nanoseconds. When user - * software requests a cross-timestamp, this function converts system timestamp - * to TSC. - * - * This is valid when CPU feature flag X86_FEATURE_TSC_KNOWN_FREQ is set - * indicating the tsc_khz is derived from CPUID[15H]. Drivers should check - * that this flag is set before conversion to TSC is attempted. - * - * Return: - * struct system_counterval_t - system counter value with the ID of the - * corresponding clocksource: - * cycles: System counter value - * cs_id: The clocksource ID for validating comparability - */ - -struct system_counterval_t convert_art_ns_to_tsc(u64 art_ns) -{ - u64 tmp, res, rem; - - rem = do_div(art_ns, USEC_PER_SEC); - - res = art_ns * tsc_khz; - tmp = rem * tsc_khz; - - do_div(tmp, USEC_PER_SEC); - res += tmp; - - return (struct system_counterval_t) { - .cs_id = have_art ? CSID_X86_TSC : CSID_GENERIC, - .cycles = res, - }; -} -EXPORT_SYMBOL(convert_art_ns_to_tsc); - - static void tsc_refine_calibration_work(struct work_struct *work); static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work); /** @@ -1458,8 +1398,10 @@ out: if (tsc_unstable) goto unreg; - if (boot_cpu_has(X86_FEATURE_ART)) + if (boot_cpu_has(X86_FEATURE_ART)) { have_art = true; + clocksource_tsc.base = &art_base_clk; + } clocksource_register_khz(&clocksource_tsc, tsc_khz); unreg: clocksource_unregister(&clocksource_tsc_early); @@ -1484,8 +1426,10 @@ static int __init init_tsc_clocksource(void) * the refined calibration and directly register it as a clocksource. */ if (boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) { - if (boot_cpu_has(X86_FEATURE_ART)) + if (boot_cpu_has(X86_FEATURE_ART)) { have_art = true; + clocksource_tsc.base = &art_base_clk; + } clocksource_register_khz(&clocksource_tsc, tsc_khz); clocksource_unregister(&clocksource_tsc_early); @@ -1509,10 +1453,12 @@ static bool __init determine_cpu_tsc_frequencies(bool early) if (early) { cpu_khz = x86_platform.calibrate_cpu(); - if (tsc_early_khz) + if (tsc_early_khz) { tsc_khz = tsc_early_khz; - else + } else { tsc_khz = x86_platform.calibrate_tsc(); + clocksource_tsc.freq_khz = tsc_khz; + } } else { /* We should not be here with non-native cpu calibration */ WARN_ON(x86_platform.calibrate_cpu != native_calibrate_cpu); diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 3509afc6a672..6e73403e874f 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -357,6 +357,9 @@ SECTIONS PERCPU_SECTION(INTERNODE_CACHE_BYTES) #endif + RUNTIME_CONST(shift, d_hash_shift) + RUNTIME_CONST(ptr, dentry_hashtable) + . = ALIGN(PAGE_SIZE); /* freed after init ends here */ diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index d5dc5a92635a..82b128d3f309 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -134,10 +134,12 @@ struct x86_cpuinit_ops x86_cpuinit = { static void default_nmi_init(void) { }; -static bool enc_status_change_prepare_noop(unsigned long vaddr, int npages, bool enc) { return true; } -static bool enc_status_change_finish_noop(unsigned long vaddr, int npages, bool enc) { return true; } +static int enc_status_change_prepare_noop(unsigned long vaddr, int npages, bool enc) { return 0; } +static int enc_status_change_finish_noop(unsigned long vaddr, int npages, bool enc) { return 0; } static bool enc_tlb_flush_required_noop(bool enc) { return false; } static bool enc_cache_flush_required_noop(void) { return false; } +static void enc_kexec_begin_noop(void) {} +static void enc_kexec_finish_noop(void) {} static bool is_private_mmio_noop(u64 addr) {return false; } struct x86_platform_ops x86_platform __ro_after_init = { @@ -161,6 +163,8 @@ struct x86_platform_ops x86_platform __ro_after_init = { .enc_status_change_finish = enc_status_change_finish_noop, .enc_tlb_flush_required = enc_tlb_flush_required_noop, .enc_cache_flush_required = enc_cache_flush_required_noop, + .enc_kexec_begin = enc_kexec_begin_noop, + .enc_kexec_finish = enc_kexec_finish_noop, }, }; |