diff options
Diffstat (limited to 'arch')
243 files changed, 3417 insertions, 2562 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index aff2746c8af2..63c5d6a2022b 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -34,6 +34,9 @@ config ARCH_HAS_SUBPAGE_FAULTS config HOTPLUG_SMT bool +config SMT_NUM_THREADS_DYNAMIC + bool + # Selected by HOTPLUG_CORE_SYNC_DEAD or HOTPLUG_CORE_SYNC_FULL config HOTPLUG_CORE_SYNC bool diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index d98701ee36c6..5db88b627439 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -97,7 +97,7 @@ struct osf_dirent { unsigned int d_ino; unsigned short d_reclen; unsigned short d_namlen; - char d_name[1]; + char d_name[]; }; struct osf_dirent_callback { diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index 1f13995d00d7..ad37569d0507 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -491,3 +491,4 @@ 559 common futex_waitv sys_futex_waitv 560 common set_mempolicy_home_node sys_ni_syscall 561 common cachestat sys_cachestat +562 common fchmodat2 sys_fchmodat2 diff --git a/arch/arm/include/asm/syscall.h b/arch/arm/include/asm/syscall.h index dfeed440254a..fe4326d938c1 100644 --- a/arch/arm/include/asm/syscall.h +++ b/arch/arm/include/asm/syscall.h @@ -25,6 +25,9 @@ static inline int syscall_get_nr(struct task_struct *task, if (IS_ENABLED(CONFIG_AEABI) && !IS_ENABLED(CONFIG_OABI_COMPAT)) return task_thread_info(task)->abi_syscall; + if (task_thread_info(task)->abi_syscall == -1) + return -1; + return task_thread_info(task)->abi_syscall & __NR_SYSCALL_MASK; } diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index bcc4c9ec3aa4..5c31e9de7a60 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -90,6 +90,7 @@ slow_work_pending: cmp r0, #0 beq no_work_pending movlt scno, #(__NR_restart_syscall - __NR_SYSCALL_BASE) + str scno, [tsk, #TI_ABI_SYSCALL] @ make sure tracers see update ldmia sp, {r0 - r6} @ have to reload r0 - r6 b local_restart @ ... and off we go ENDPROC(ret_fast_syscall) diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 054e9199f30d..dc0fb7a81371 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -626,7 +626,7 @@ int hw_breakpoint_arch_parse(struct perf_event *bp, hw->address &= ~alignment_mask; hw->ctrl.len <<= offset; - if (is_default_overflow_handler(bp)) { + if (uses_default_overflow_handler(bp)) { /* * Mismatch breakpoints are required for single-stepping * breakpoints. @@ -798,7 +798,7 @@ static void watchpoint_handler(unsigned long addr, unsigned int fsr, * Otherwise, insert a temporary mismatch breakpoint so that * we can single-step over the watchpoint trigger. */ - if (!is_default_overflow_handler(wp)) + if (!uses_default_overflow_handler(wp)) continue; step: enable_single_step(wp, instruction_pointer(regs)); @@ -811,7 +811,7 @@ step: info->trigger = addr; pr_debug("watchpoint fired: address = 0x%x\n", info->trigger); perf_bp_event(wp, regs); - if (is_default_overflow_handler(wp)) + if (uses_default_overflow_handler(wp)) enable_single_step(wp, instruction_pointer(regs)); } @@ -886,7 +886,7 @@ static void breakpoint_handler(unsigned long unknown, struct pt_regs *regs) info->trigger = addr; pr_debug("breakpoint fired: address = 0x%x\n", addr); perf_bp_event(bp, regs); - if (is_default_overflow_handler(bp)) + if (uses_default_overflow_handler(bp)) enable_single_step(bp, addr); goto unlock; } diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c index 2d8e2516906b..fef32d73f912 100644 --- a/arch/arm/kernel/ptrace.c +++ b/arch/arm/kernel/ptrace.c @@ -783,8 +783,9 @@ long arch_ptrace(struct task_struct *child, long request, break; case PTRACE_SET_SYSCALL: - task_thread_info(child)->abi_syscall = data & - __NR_SYSCALL_MASK; + if (data != -1) + data &= __NR_SYSCALL_MASK; + task_thread_info(child)->abi_syscall = data; ret = 0; break; diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index 8ebed8a13874..c572d6c3dee0 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -465,3 +465,4 @@ 449 common futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node 451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index a2511b30d0f6..29db061db9bb 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1793,9 +1793,6 @@ config ARM64_PAN The feature is detected at runtime, and will remain as a 'nop' instruction if the cpu does not implement the feature. -config AS_HAS_LDAPR - def_bool $(as-instr,.arch_extension rcpc) - config AS_HAS_LSE_ATOMICS def_bool $(as-instr,.arch_extension lse) @@ -1933,6 +1930,9 @@ config AS_HAS_ARMV8_3 config AS_HAS_CFI_NEGATE_RA_STATE def_bool $(as-instr,.cfi_startproc\n.cfi_negate_ra_state\n.cfi_endproc\n) +config AS_HAS_LDAPR + def_bool $(as-instr,.arch_extension rcpc) + endmenu # "ARMv8.3 architectural features" menu "ARMv8.4 architectural features" diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h index bd68e1b7f29f..4d537d56eb84 100644 --- a/arch/arm64/include/asm/acpi.h +++ b/arch/arm64/include/asm/acpi.h @@ -42,6 +42,9 @@ #define ACPI_MADT_GICC_SPE (offsetof(struct acpi_madt_generic_interrupt, \ spe_interrupt) + sizeof(u16)) +#define ACPI_MADT_GICC_TRBE (offsetof(struct acpi_madt_generic_interrupt, \ + trbe_interrupt) + sizeof(u16)) + /* Basic configuration for ACPI */ #ifdef CONFIG_ACPI pgprot_t __acpi_get_mem_attribute(phys_addr_t addr); diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 4cf2cb053bc8..f482b994c608 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -30,28 +30,16 @@ int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md); int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md, bool has_bti); -#define arch_efi_call_virt_setup() \ -({ \ - efi_virtmap_load(); \ - __efi_fpsimd_begin(); \ - raw_spin_lock(&efi_rt_lock); \ -}) - #undef arch_efi_call_virt #define arch_efi_call_virt(p, f, args...) \ __efi_rt_asm_wrapper((p)->f, #f, args) -#define arch_efi_call_virt_teardown() \ -({ \ - raw_spin_unlock(&efi_rt_lock); \ - __efi_fpsimd_end(); \ - efi_virtmap_unload(); \ -}) - -extern raw_spinlock_t efi_rt_lock; extern u64 *efi_rt_stack_top; efi_status_t __efi_rt_asm_wrapper(void *, const char *, ...); +void arch_efi_call_virt_setup(void); +void arch_efi_call_virt_teardown(void); + /* * efi_rt_stack_top[-1] contains the value the stack pointer had before * switching to the EFI runtime stack. diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index 692b1ec663b2..521267478d18 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -138,6 +138,7 @@ #define KERNEL_HWCAP_SME_B16B16 __khwcap2_feature(SME_B16B16) #define KERNEL_HWCAP_SME_F16F16 __khwcap2_feature(SME_F16F16) #define KERNEL_HWCAP_MOPS __khwcap2_feature(MOPS) +#define KERNEL_HWCAP_HBC __khwcap2_feature(HBC) /* * This yields a mask that user programs can use to figure out what diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h index 577773870b66..85d26143faa5 100644 --- a/arch/arm64/include/asm/kernel-pgtable.h +++ b/arch/arm64/include/asm/kernel-pgtable.h @@ -118,31 +118,4 @@ #define SWAPPER_RX_MMUFLAGS (SWAPPER_RW_MMUFLAGS | PTE_RDONLY) #endif -/* - * To make optimal use of block mappings when laying out the linear - * mapping, round down the base of physical memory to a size that can - * be mapped efficiently, i.e., either PUD_SIZE (4k granule) or PMD_SIZE - * (64k granule), or a multiple that can be mapped using contiguous bits - * in the page tables: 32 * PMD_SIZE (16k granule) - */ -#if defined(CONFIG_ARM64_4K_PAGES) -#define ARM64_MEMSTART_SHIFT PUD_SHIFT -#elif defined(CONFIG_ARM64_16K_PAGES) -#define ARM64_MEMSTART_SHIFT CONT_PMD_SHIFT -#else -#define ARM64_MEMSTART_SHIFT PMD_SHIFT -#endif - -/* - * sparsemem vmemmap imposes an additional requirement on the alignment of - * memstart_addr, due to the fact that the base of the vmemmap region - * has a direct correspondence, and needs to appear sufficiently aligned - * in the virtual address space. - */ -#if ARM64_MEMSTART_SHIFT < SECTION_SIZE_BITS -#define ARM64_MEMSTART_ALIGN (1UL << SECTION_SIZE_BITS) -#else -#define ARM64_MEMSTART_ALIGN (1UL << ARM64_MEMSTART_SHIFT) -#endif - #endif /* __ASM_KERNEL_PGTABLE_H */ diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index 4384eaa0aeb7..94b68850cb9f 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -64,7 +64,6 @@ extern void arm64_memblock_init(void); extern void paging_init(void); extern void bootmem_init(void); extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt); -extern void init_mem_pgprot(void); extern void create_mapping_noalloc(phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot); extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 0bd18de9fd97..72c2e8431360 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -103,6 +103,7 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys) #define pte_young(pte) (!!(pte_val(pte) & PTE_AF)) #define pte_special(pte) (!!(pte_val(pte) & PTE_SPECIAL)) #define pte_write(pte) (!!(pte_val(pte) & PTE_WRITE)) +#define pte_rdonly(pte) (!!(pte_val(pte) & PTE_RDONLY)) #define pte_user(pte) (!!(pte_val(pte) & PTE_USER)) #define pte_user_exec(pte) (!(pte_val(pte) & PTE_UXN)) #define pte_cont(pte) (!!(pte_val(pte) & PTE_CONT)) @@ -120,7 +121,7 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys) (__boundary - 1 < (end) - 1) ? __boundary : (end); \ }) -#define pte_hw_dirty(pte) (pte_write(pte) && !(pte_val(pte) & PTE_RDONLY)) +#define pte_hw_dirty(pte) (pte_write(pte) && !pte_rdonly(pte)) #define pte_sw_dirty(pte) (!!(pte_val(pte) & PTE_DIRTY)) #define pte_dirty(pte) (pte_sw_dirty(pte) || pte_hw_dirty(pte)) @@ -212,7 +213,7 @@ static inline pte_t pte_wrprotect(pte_t pte) * clear), set the PTE_DIRTY bit. */ if (pte_hw_dirty(pte)) - pte = pte_mkdirty(pte); + pte = set_pte_bit(pte, __pgprot(PTE_DIRTY)); pte = clear_pte_bit(pte, __pgprot(PTE_WRITE)); pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); @@ -823,7 +824,8 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) PTE_ATTRINDX_MASK; /* preserve the hardware dirty information */ if (pte_hw_dirty(pte)) - pte = pte_mkdirty(pte); + pte = set_pte_bit(pte, __pgprot(PTE_DIRTY)); + pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask); return pte; } diff --git a/arch/arm64/include/asm/sdei.h b/arch/arm64/include/asm/sdei.h index 4292d9bafb9d..484cb6972e99 100644 --- a/arch/arm64/include/asm/sdei.h +++ b/arch/arm64/include/asm/sdei.h @@ -17,6 +17,9 @@ #include <asm/virt.h> +DECLARE_PER_CPU(struct sdei_registered_event *, sdei_active_normal_event); +DECLARE_PER_CPU(struct sdei_registered_event *, sdei_active_critical_event); + extern unsigned long sdei_exit_mode; /* Software Delegated Exception entry point from firmware*/ @@ -29,6 +32,9 @@ asmlinkage void __sdei_asm_entry_trampoline(unsigned long event_num, unsigned long pc, unsigned long pstate); +/* Abort a running handler. Context is discarded. */ +void __sdei_handler_abort(void); + /* * The above entry point does the minimum to call C code. This function does * anything else, before calling the driver. diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index b481935e9314..16464bf9a8aa 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -803,15 +803,21 @@ /* * For registers without architectural names, or simply unsupported by * GAS. + * + * __check_r forces warnings to be generated by the compiler when + * evaluating r which wouldn't normally happen due to being passed to + * the assembler via __stringify(r). */ #define read_sysreg_s(r) ({ \ u64 __val; \ + u32 __maybe_unused __check_r = (u32)(r); \ asm volatile(__mrs_s("%0", r) : "=r" (__val)); \ __val; \ }) #define write_sysreg_s(v, r) do { \ u64 __val = (u64)(v); \ + u32 __maybe_unused __check_r = (u32)(r); \ asm volatile(__msr_s(r, "%x0") : : "rZ" (__val)); \ } while (0) diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 64a514f90131..bd77253b62e0 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -39,7 +39,7 @@ #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5) #define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800) -#define __NR_compat_syscalls 452 +#define __NR_compat_syscalls 453 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index d952a28463e0..78b68311ec81 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -909,6 +909,8 @@ __SYSCALL(__NR_futex_waitv, sys_futex_waitv) __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node) #define __NR_cachestat 451 __SYSCALL(__NR_cachestat, sys_cachestat) +#define __NR_fchmodat2 452 +__SYSCALL(__NR_fchmodat2, sys_fchmodat2) /* * Please add new compat syscalls above this comment and update diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index a2cac4305b1e..53026f45a509 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -103,5 +103,6 @@ #define HWCAP2_SME_B16B16 (1UL << 41) #define HWCAP2_SME_F16F16 (1UL << 42) #define HWCAP2_MOPS (1UL << 43) +#define HWCAP2_HBC (1UL << 44) #endif /* _UAPI__ASM_HWCAP_H */ diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index f9d456fe132d..a5f533f63b60 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -222,7 +222,7 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = { static const struct arm64_ftr_bits ftr_id_aa64isar2[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_CSSC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_RPRFM_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64ISAR2_EL1_BC_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64ISAR2_EL1_BC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_MOPS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), FTR_STRICT, FTR_EXACT, ID_AA64ISAR2_EL1_APA3_SHIFT, 4, 0), @@ -2708,12 +2708,8 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .desc = "Enhanced Virtualization Traps", .capability = ARM64_HAS_EVT, .type = ARM64_CPUCAP_SYSTEM_FEATURE, - .sys_reg = SYS_ID_AA64MMFR2_EL1, - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64MMFR2_EL1_EVT_SHIFT, - .field_width = 4, - .min_field_value = ID_AA64MMFR2_EL1_EVT_IMP, .matches = has_cpuid_feature, + ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, EVT, IMP) }, {}, }; @@ -2844,6 +2840,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ISAR2_EL1, RPRES, IMP, CAP_HWCAP, KERNEL_HWCAP_RPRES), HWCAP_CAP(ID_AA64ISAR2_EL1, WFxT, IMP, CAP_HWCAP, KERNEL_HWCAP_WFXT), HWCAP_CAP(ID_AA64ISAR2_EL1, MOPS, IMP, CAP_HWCAP, KERNEL_HWCAP_MOPS), + HWCAP_CAP(ID_AA64ISAR2_EL1, BC, IMP, CAP_HWCAP, KERNEL_HWCAP_HBC), #ifdef CONFIG_ARM64_SME HWCAP_CAP(ID_AA64PFR1_EL1, SME, IMP, CAP_HWCAP, KERNEL_HWCAP_SME), HWCAP_CAP(ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64), diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c index d1f68599c29f..f372295207fb 100644 --- a/arch/arm64/kernel/cpuidle.c +++ b/arch/arm64/kernel/cpuidle.c @@ -9,8 +9,6 @@ #include <linux/acpi.h> #include <linux/cpuidle.h> #include <linux/cpu_pm.h> -#include <linux/of.h> -#include <linux/of_device.h> #include <linux/psci.h> #ifdef CONFIG_ACPI_PROCESSOR_IDLE diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 58622dc85917..98fda8500535 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -126,6 +126,7 @@ static const char *const hwcap_str[] = { [KERNEL_HWCAP_SME_B16B16] = "smeb16b16", [KERNEL_HWCAP_SME_F16F16] = "smef16f16", [KERNEL_HWCAP_MOPS] = "mops", + [KERNEL_HWCAP_HBC] = "hbc", }; #ifdef CONFIG_COMPAT diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index baab8dd3ead3..49efbdbd6f7a 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -158,7 +158,21 @@ asmlinkage efi_status_t efi_handle_corrupted_x18(efi_status_t s, const char *f) return s; } -DEFINE_RAW_SPINLOCK(efi_rt_lock); +static DEFINE_RAW_SPINLOCK(efi_rt_lock); + +void arch_efi_call_virt_setup(void) +{ + efi_virtmap_load(); + __efi_fpsimd_begin(); + raw_spin_lock(&efi_rt_lock); +} + +void arch_efi_call_virt_teardown(void) +{ + raw_spin_unlock(&efi_rt_lock); + __efi_fpsimd_end(); + efi_virtmap_unload(); +} asmlinkage u64 *efi_rt_stack_top __ro_after_init; diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 6b2e0c367702..0fc94207e69a 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -355,6 +355,35 @@ static bool cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) } #endif /* CONFIG_ARM64_ERRATUM_1463225 */ +/* + * As per the ABI exit SME streaming mode and clear the SVE state not + * shared with FPSIMD on syscall entry. + */ +static inline void fp_user_discard(void) +{ + /* + * If SME is active then exit streaming mode. If ZA is active + * then flush the SVE registers but leave userspace access to + * both SVE and SME enabled, otherwise disable SME for the + * task and fall through to disabling SVE too. This means + * that after a syscall we never have any streaming mode + * register state to track, if this changes the KVM code will + * need updating. + */ + if (system_supports_sme()) + sme_smstop_sm(); + + if (!system_supports_sve()) + return; + + if (test_thread_flag(TIF_SVE)) { + unsigned int sve_vq_minus_one; + + sve_vq_minus_one = sve_vq_from_vl(task_get_sve_vl(current)) - 1; + sve_flush_live(true, sve_vq_minus_one); + } +} + UNHANDLED(el1t, 64, sync) UNHANDLED(el1t, 64, irq) UNHANDLED(el1t, 64, fiq) @@ -644,6 +673,8 @@ static void noinstr el0_svc(struct pt_regs *regs) { enter_from_user_mode(regs); cortex_a76_erratum_1463225_svc_handler(); + fp_user_discard(); + local_daif_restore(DAIF_PROCCTX); do_el0_svc(regs); exit_to_user_mode(regs); } @@ -783,6 +814,7 @@ static void noinstr el0_svc_compat(struct pt_regs *regs) { enter_from_user_mode(regs); cortex_a76_erratum_1463225_svc_handler(); + local_daif_restore(DAIF_PROCCTX); do_el0_svc_compat(regs); exit_to_user_mode(regs); } diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index a40e5e50fa55..6ad61de03d0a 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -986,9 +986,13 @@ SYM_CODE_START(__sdei_asm_handler) mov x19, x1 -#if defined(CONFIG_VMAP_STACK) || defined(CONFIG_SHADOW_CALL_STACK) + /* Store the registered-event for crash_smp_send_stop() */ ldrb w4, [x19, #SDEI_EVENT_PRIORITY] -#endif + cbnz w4, 1f + adr_this_cpu dst=x5, sym=sdei_active_normal_event, tmp=x6 + b 2f +1: adr_this_cpu dst=x5, sym=sdei_active_critical_event, tmp=x6 +2: str x19, [x5] #ifdef CONFIG_VMAP_STACK /* @@ -1055,6 +1059,14 @@ SYM_CODE_START(__sdei_asm_handler) ldr_l x2, sdei_exit_mode + /* Clear the registered-event seen by crash_smp_send_stop() */ + ldrb w3, [x4, #SDEI_EVENT_PRIORITY] + cbnz w3, 1f + adr_this_cpu dst=x5, sym=sdei_active_normal_event, tmp=x6 + b 2f +1: adr_this_cpu dst=x5, sym=sdei_active_critical_event, tmp=x6 +2: str xzr, [x5] + alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0 sdei_handler_exit exit_mode=x2 alternative_else_nop_endif @@ -1065,4 +1077,15 @@ alternative_else_nop_endif #endif SYM_CODE_END(__sdei_asm_handler) NOKPROBE(__sdei_asm_handler) + +SYM_CODE_START(__sdei_handler_abort) + mov_q x0, SDEI_1_0_FN_SDEI_EVENT_COMPLETE_AND_RESUME + adr x1, 1f + ldr_l x2, sdei_exit_mode + sdei_handler_exit exit_mode=x2 + // exit the handler and jump to the next instruction. + // Exit will stomp x0-x17, PSTATE, ELR_ELx, and SPSR_ELx. +1: ret +SYM_CODE_END(__sdei_handler_abort) +NOKPROBE(__sdei_handler_abort) #endif /* CONFIG_ARM_SDE_INTERFACE */ diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 087c05aa960e..91e44ac7150f 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1179,9 +1179,6 @@ void sve_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p) */ u64 read_zcr_features(void) { - u64 zcr; - unsigned int vq_max; - /* * Set the maximum possible VL, and write zeroes to all other * bits to see if they stick. @@ -1189,12 +1186,8 @@ u64 read_zcr_features(void) sve_kernel_enable(NULL); write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL1); - zcr = read_sysreg_s(SYS_ZCR_EL1); - zcr &= ~(u64)ZCR_ELx_LEN_MASK; /* find sticky 1s outside LEN field */ - vq_max = sve_vq_from_vl(sve_get_vl()); - zcr |= vq_max - 1; /* set LEN field to maximum effective value */ - - return zcr; + /* Return LEN value that would be written to get the maximum VL */ + return sve_vq_from_vl(sve_get_vl()) - 1; } void __init sve_setup(void) @@ -1349,9 +1342,6 @@ void fa64_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p) */ u64 read_smcr_features(void) { - u64 smcr; - unsigned int vq_max; - sme_kernel_enable(NULL); /* @@ -1360,12 +1350,8 @@ u64 read_smcr_features(void) write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_LEN_MASK, SYS_SMCR_EL1); - smcr = read_sysreg_s(SYS_SMCR_EL1); - smcr &= ~(u64)SMCR_ELx_LEN_MASK; /* Only the LEN field */ - vq_max = sve_vq_from_vl(sme_get_vl()); - smcr |= vq_max - 1; /* set LEN field to maximum effective value */ - - return smcr; + /* Return LEN value that would be written to get the maximum VL */ + return sve_vq_from_vl(sme_get_vl()) - 1; } void __init sme_setup(void) diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 757a0de07f91..7b236994f0e1 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -113,7 +113,7 @@ SYM_CODE_START(primary_entry) */ #if VA_BITS > 48 mrs_s x0, SYS_ID_AA64MMFR2_EL1 - tst x0, #0xf << ID_AA64MMFR2_EL1_VARange_SHIFT + tst x0, ID_AA64MMFR2_EL1_VARange_MASK mov x0, #VA_BITS mov x25, #VA_BITS_MIN csel x25, x25, x0, eq @@ -756,7 +756,7 @@ SYM_FUNC_START(__cpu_secondary_check52bitva) b.ne 2f mrs_s x0, SYS_ID_AA64MMFR2_EL1 - and x0, x0, #(0xf << ID_AA64MMFR2_EL1_VARange_SHIFT) + and x0, x0, ID_AA64MMFR2_EL1_VARange_MASK cbnz x0, 2f update_early_cpu_boot_status \ diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index db2a1861bb97..35225632d70a 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -654,7 +654,7 @@ static int breakpoint_handler(unsigned long unused, unsigned long esr, perf_bp_event(bp, regs); /* Do we need to handle the stepping? */ - if (is_default_overflow_handler(bp)) + if (uses_default_overflow_handler(bp)) step = 1; unlock: rcu_read_unlock(); @@ -733,7 +733,7 @@ static u64 get_distance_from_watchpoint(unsigned long addr, u64 val, static int watchpoint_report(struct perf_event *wp, unsigned long addr, struct pt_regs *regs) { - int step = is_default_overflow_handler(wp); + int step = uses_default_overflow_handler(wp); struct arch_hw_breakpoint *info = counter_arch_bp(wp); info->trigger = addr; diff --git a/arch/arm64/kernel/idreg-override.c b/arch/arm64/kernel/idreg-override.c index 2fe2491b692c..aee12c75b738 100644 --- a/arch/arm64/kernel/idreg-override.c +++ b/arch/arm64/kernel/idreg-override.c @@ -262,9 +262,9 @@ static __init void __parse_cmdline(const char *cmdline, bool parse_aliases) if (!len) return; - len = min(len, ARRAY_SIZE(buf) - 1); - strncpy(buf, cmdline, len); - buf[len] = 0; + len = strscpy(buf, cmdline, ARRAY_SIZE(buf)); + if (len == -E2BIG) + len = ARRAY_SIZE(buf) - 1; if (strcmp(buf, "--") == 0) return; diff --git a/arch/arm64/kernel/pci.c b/arch/arm64/kernel/pci.c index 2276689b5411..f872c57e9909 100644 --- a/arch/arm64/kernel/pci.c +++ b/arch/arm64/kernel/pci.c @@ -11,8 +11,6 @@ #include <linux/io.h> #include <linux/kernel.h> #include <linux/mm.h> -#include <linux/of_pci.h> -#include <linux/of_platform.h> #include <linux/pci.h> #include <linux/pci-acpi.h> #include <linux/pci-ecam.h> diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 187aa2b175b4..20d7ef82de90 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -891,7 +891,8 @@ static int sve_set_common(struct task_struct *target, break; default: WARN_ON_ONCE(1); - return -EINVAL; + ret = -EINVAL; + goto out; } /* diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c index 830be01af32d..255d12f881c2 100644 --- a/arch/arm64/kernel/sdei.c +++ b/arch/arm64/kernel/sdei.c @@ -47,6 +47,9 @@ DEFINE_PER_CPU(unsigned long *, sdei_shadow_call_stack_normal_ptr); DEFINE_PER_CPU(unsigned long *, sdei_shadow_call_stack_critical_ptr); #endif +DEFINE_PER_CPU(struct sdei_registered_event *, sdei_active_normal_event); +DEFINE_PER_CPU(struct sdei_registered_event *, sdei_active_critical_event); + static void _free_sdei_stack(unsigned long * __percpu *ptr, int cpu) { unsigned long *p; diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index edd63894d61e..960b98b43506 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -1044,10 +1044,8 @@ void crash_smp_send_stop(void) * If this cpu is the only one alive at this point in time, online or * not, there are no stop messages to be sent around, so just back out. */ - if (num_other_online_cpus() == 0) { - sdei_mask_local_cpu(); - return; - } + if (num_other_online_cpus() == 0) + goto skip_ipi; cpumask_copy(&mask, cpu_online_mask); cpumask_clear_cpu(smp_processor_id(), &mask); @@ -1066,7 +1064,9 @@ void crash_smp_send_stop(void) pr_warn("SMP: failed to stop secondary CPUs %*pbl\n", cpumask_pr_args(&mask)); +skip_ipi: sdei_mask_local_cpu(); + sdei_handler_abort(); } bool smp_crash_stop_failed(void) diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index b1ae2f2eaf77..9a70d9746b66 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -8,7 +8,6 @@ #include <linux/randomize_kstack.h> #include <linux/syscalls.h> -#include <asm/daifflags.h> #include <asm/debug-monitors.h> #include <asm/exception.h> #include <asm/fpsimd.h> @@ -101,8 +100,6 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, * (Similarly for HVC and SMC elsewhere.) */ - local_daif_restore(DAIF_PROCCTX); - if (flags & _TIF_MTE_ASYNC_FAULT) { /* * Process the asynchronous tag check fault before the actual @@ -153,38 +150,8 @@ trace_exit: syscall_trace_exit(regs); } -/* - * As per the ABI exit SME streaming mode and clear the SVE state not - * shared with FPSIMD on syscall entry. - */ -static inline void fp_user_discard(void) -{ - /* - * If SME is active then exit streaming mode. If ZA is active - * then flush the SVE registers but leave userspace access to - * both SVE and SME enabled, otherwise disable SME for the - * task and fall through to disabling SVE too. This means - * that after a syscall we never have any streaming mode - * register state to track, if this changes the KVM code will - * need updating. - */ - if (system_supports_sme()) - sme_smstop_sm(); - - if (!system_supports_sve()) - return; - - if (test_thread_flag(TIF_SVE)) { - unsigned int sve_vq_minus_one; - - sve_vq_minus_one = sve_vq_from_vl(task_get_sve_vl(current)) - 1; - sve_flush_live(true, sve_vq_minus_one); - } -} - void do_el0_svc(struct pt_regs *regs) { - fp_user_discard(); el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table); } diff --git a/arch/arm64/kernel/vdso/vdso.lds.S b/arch/arm64/kernel/vdso/vdso.lds.S index 6028f1fe2d1c..45354f2ddf70 100644 --- a/arch/arm64/kernel/vdso/vdso.lds.S +++ b/arch/arm64/kernel/vdso/vdso.lds.S @@ -50,9 +50,7 @@ SECTIONS . = ALIGN(4); .altinstructions : { - __alt_instructions = .; *(.altinstructions) - __alt_instructions_end = .; } .dynamic : { *(.dynamic) } :text :dynamic diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile index 9ddc025e4b86..2250253a6429 100644 --- a/arch/arm64/kvm/hyp/nvhe/Makefile +++ b/arch/arm64/kvm/hyp/nvhe/Makefile @@ -25,7 +25,7 @@ hyp-obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o host.o cache.o setup.o mm.o mem_protect.o sys_regs.o pkvm.o stacktrace.o ffa.o hyp-obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \ ../fpsimd.o ../hyp-entry.o ../exception.o ../pgtable.o -hyp-obj-$(CONFIG_DEBUG_LIST) += list_debug.o +hyp-obj-$(CONFIG_LIST_HARDENED) += list_debug.o hyp-obj-y += $(lib-objs) ## diff --git a/arch/arm64/kvm/hyp/nvhe/list_debug.c b/arch/arm64/kvm/hyp/nvhe/list_debug.c index d68abd7ea124..46a2d4f2b3c6 100644 --- a/arch/arm64/kvm/hyp/nvhe/list_debug.c +++ b/arch/arm64/kvm/hyp/nvhe/list_debug.c @@ -26,8 +26,9 @@ static inline __must_check bool nvhe_check_data_corruption(bool v) /* The predicates checked here are taken from lib/list_debug.c. */ -bool __list_add_valid(struct list_head *new, struct list_head *prev, - struct list_head *next) +__list_valid_slowpath +bool __list_add_valid_or_report(struct list_head *new, struct list_head *prev, + struct list_head *next) { if (NVHE_CHECK_DATA_CORRUPTION(next->prev != prev) || NVHE_CHECK_DATA_CORRUPTION(prev->next != next) || @@ -37,7 +38,8 @@ bool __list_add_valid(struct list_head *new, struct list_head *prev, return true; } -bool __list_del_entry_valid(struct list_head *entry) +__list_valid_slowpath +bool __list_del_entry_valid_or_report(struct list_head *entry) { struct list_head *prev, *next; diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index d31c3a9290c5..4fcb88a445ef 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -73,6 +73,33 @@ phys_addr_t __ro_after_init arm64_dma_phys_limit; #define DEFAULT_CRASH_KERNEL_LOW_SIZE (128UL << 20) +/* + * To make optimal use of block mappings when laying out the linear + * mapping, round down the base of physical memory to a size that can + * be mapped efficiently, i.e., either PUD_SIZE (4k granule) or PMD_SIZE + * (64k granule), or a multiple that can be mapped using contiguous bits + * in the page tables: 32 * PMD_SIZE (16k granule) + */ +#if defined(CONFIG_ARM64_4K_PAGES) +#define ARM64_MEMSTART_SHIFT PUD_SHIFT +#elif defined(CONFIG_ARM64_16K_PAGES) +#define ARM64_MEMSTART_SHIFT CONT_PMD_SHIFT +#else +#define ARM64_MEMSTART_SHIFT PMD_SHIFT +#endif + +/* + * sparsemem vmemmap imposes an additional requirement on the alignment of + * memstart_addr, due to the fact that the base of the vmemmap region + * has a direct correspondence, and needs to appear sufficiently aligned + * in the virtual address space. + */ +#if ARM64_MEMSTART_SHIFT < SECTION_SIZE_BITS +#define ARM64_MEMSTART_ALIGN (1UL << SECTION_SIZE_BITS) +#else +#define ARM64_MEMSTART_ALIGN (1UL << ARM64_MEMSTART_SHIFT) +#endif + static int __init reserve_crashkernel_low(unsigned long long low_size) { unsigned long long low_base; diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 2baeec419f62..14fdf645edc8 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -447,7 +447,7 @@ SYM_FUNC_START(__cpu_setup) * via capabilities. */ mrs x9, ID_AA64MMFR1_EL1 - and x9, x9, #0xf + and x9, x9, ID_AA64MMFR1_EL1_HAFDBS_MASK cbz x9, 1f orr tcr, tcr, #TCR_HA // hardware Access flag update 1: diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index f8c74ffeeefb..83d8609aec03 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -372,3 +372,4 @@ 449 common futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node 451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index e71d5bf2cee0..465759f6b0ed 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -662,5 +662,3 @@ source "kernel/power/Kconfig" source "drivers/acpi/Kconfig" endmenu - -source "drivers/firmware/Kconfig" diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile index b1e5db51b61c..ef87bab46754 100644 --- a/arch/loongarch/Makefile +++ b/arch/loongarch/Makefile @@ -83,8 +83,8 @@ KBUILD_CFLAGS_KERNEL += -fPIE LDFLAGS_vmlinux += -static -pie --no-dynamic-linker -z notext endif -cflags-y += -ffreestanding cflags-y += $(call cc-option, -mno-check-zero-division) +cflags-y += -fno-builtin-memcpy -fno-builtin-memmove -fno-builtin-memset load-y = 0x9000000000200000 bootvars-y = VMLINUX_LOAD_ADDRESS=$(load-y) diff --git a/arch/loongarch/include/asm/Kbuild b/arch/loongarch/include/asm/Kbuild index 6b222f227342..93783fa24f6e 100644 --- a/arch/loongarch/include/asm/Kbuild +++ b/arch/loongarch/include/asm/Kbuild @@ -1,6 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 generic-y += dma-contiguous.h -generic-y += export.h generic-y += mcs_spinlock.h generic-y += parport.h generic-y += early_ioremap.h diff --git a/arch/loongarch/include/asm/fpu.h b/arch/loongarch/include/asm/fpu.h index b541f6248837..c2d8962fda00 100644 --- a/arch/loongarch/include/asm/fpu.h +++ b/arch/loongarch/include/asm/fpu.h @@ -173,16 +173,30 @@ static inline void restore_fp(struct task_struct *tsk) _restore_fp(&tsk->thread.fpu); } -static inline union fpureg *get_fpu_regs(struct task_struct *tsk) +static inline void save_fpu_regs(struct task_struct *tsk) { + unsigned int euen; + if (tsk == current) { preempt_disable(); - if (is_fpu_owner()) + + euen = csr_read32(LOONGARCH_CSR_EUEN); + +#ifdef CONFIG_CPU_HAS_LASX + if (euen & CSR_EUEN_LASXEN) + _save_lasx(¤t->thread.fpu); + else +#endif +#ifdef CONFIG_CPU_HAS_LSX + if (euen & CSR_EUEN_LSXEN) + _save_lsx(¤t->thread.fpu); + else +#endif + if (euen & CSR_EUEN_FPEN) _save_fp(¤t->thread.fpu); + preempt_enable(); } - - return tsk->thread.fpu.fpr; } static inline int is_simd_owner(void) diff --git a/arch/loongarch/include/asm/local.h b/arch/loongarch/include/asm/local.h index 83e995b30e47..c49675852bdc 100644 --- a/arch/loongarch/include/asm/local.h +++ b/arch/loongarch/include/asm/local.h @@ -63,8 +63,8 @@ static inline long local_cmpxchg(local_t *l, long old, long new) static inline bool local_try_cmpxchg(local_t *l, long *old, long new) { - typeof(l->a.counter) *__old = (typeof(l->a.counter) *) old; - return try_cmpxchg_local(&l->a.counter, __old, new); + return try_cmpxchg_local(&l->a.counter, + (typeof(l->a.counter) *) old, new); } #define local_xchg(l, n) (atomic_long_xchg((&(l)->a), (n))) diff --git a/arch/loongarch/include/asm/ptrace.h b/arch/loongarch/include/asm/ptrace.h index 35f0958163ac..f3ddaed9ef7f 100644 --- a/arch/loongarch/include/asm/ptrace.h +++ b/arch/loongarch/include/asm/ptrace.h @@ -162,7 +162,7 @@ static inline void regs_set_return_value(struct pt_regs *regs, unsigned long val #define instruction_pointer(regs) ((regs)->csr_era) #define profile_pc(regs) instruction_pointer(regs) -extern void die(const char *, struct pt_regs *) __noreturn; +extern void die(const char *str, struct pt_regs *regs); static inline void die_if_kernel(const char *str, struct pt_regs *regs) { diff --git a/arch/loongarch/include/asm/smp.h b/arch/loongarch/include/asm/smp.h index 416b653bccb4..66ecb480c894 100644 --- a/arch/loongarch/include/asm/smp.h +++ b/arch/loongarch/include/asm/smp.h @@ -98,8 +98,6 @@ static inline void __cpu_die(unsigned int cpu) { loongson_cpu_die(cpu); } - -extern void __noreturn play_dead(void); #endif #endif /* __ASM_SMP_H */ diff --git a/arch/loongarch/kernel/fpu.S b/arch/loongarch/kernel/fpu.S index f3df5f0a4509..501094a09f5d 100644 --- a/arch/loongarch/kernel/fpu.S +++ b/arch/loongarch/kernel/fpu.S @@ -6,12 +6,12 @@ * * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ +#include <linux/export.h> #include <asm/asm.h> #include <asm/asmmacro.h> #include <asm/asm-extable.h> #include <asm/asm-offsets.h> #include <asm/errno.h> -#include <asm/export.h> #include <asm/fpregdef.h> #include <asm/loongarch.h> #include <asm/regdef.h> diff --git a/arch/loongarch/kernel/hw_breakpoint.c b/arch/loongarch/kernel/hw_breakpoint.c index 021b59c248fa..fc55c4de2a11 100644 --- a/arch/loongarch/kernel/hw_breakpoint.c +++ b/arch/loongarch/kernel/hw_breakpoint.c @@ -207,8 +207,7 @@ static int hw_breakpoint_control(struct perf_event *bp, write_wb_reg(CSR_CFG_CTRL, i, 0, CTRL_PLV_ENABLE); } else { ctrl = encode_ctrl_reg(info->ctrl); - write_wb_reg(CSR_CFG_CTRL, i, 1, ctrl | CTRL_PLV_ENABLE | - 1 << MWPnCFG3_LoadEn | 1 << MWPnCFG3_StoreEn); + write_wb_reg(CSR_CFG_CTRL, i, 1, ctrl | CTRL_PLV_ENABLE); } enable = csr_read64(LOONGARCH_CSR_CRMD); csr_write64(CSR_CRMD_WE | enable, LOONGARCH_CSR_CRMD); diff --git a/arch/loongarch/kernel/mcount.S b/arch/loongarch/kernel/mcount.S index cb8e5803de4b..3015896016a0 100644 --- a/arch/loongarch/kernel/mcount.S +++ b/arch/loongarch/kernel/mcount.S @@ -5,7 +5,7 @@ * Copyright (C) 2022 Loongson Technology Corporation Limited */ -#include <asm/export.h> +#include <linux/export.h> #include <asm/ftrace.h> #include <asm/regdef.h> #include <asm/stackframe.h> diff --git a/arch/loongarch/kernel/mcount_dyn.S b/arch/loongarch/kernel/mcount_dyn.S index e16ab0b98e5a..482aa553aa2d 100644 --- a/arch/loongarch/kernel/mcount_dyn.S +++ b/arch/loongarch/kernel/mcount_dyn.S @@ -3,7 +3,6 @@ * Copyright (C) 2022 Loongson Technology Corporation Limited */ -#include <asm/export.h> #include <asm/ftrace.h> #include <asm/regdef.h> #include <asm/stackframe.h> diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c index 2e04eb07abb6..4ee1e9d6a65f 100644 --- a/arch/loongarch/kernel/process.c +++ b/arch/loongarch/kernel/process.c @@ -61,13 +61,6 @@ EXPORT_SYMBOL(__stack_chk_guard); unsigned long boot_option_idle_override = IDLE_NO_OVERRIDE; EXPORT_SYMBOL(boot_option_idle_override); -#ifdef CONFIG_HOTPLUG_CPU -void __noreturn arch_cpu_idle_dead(void) -{ - play_dead(); -} -#endif - asmlinkage void ret_from_fork(void); asmlinkage void ret_from_kernel_thread(void); diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c index a0767c3a0f0a..f72adbf530c6 100644 --- a/arch/loongarch/kernel/ptrace.c +++ b/arch/loongarch/kernel/ptrace.c @@ -147,6 +147,8 @@ static int fpr_get(struct task_struct *target, { int r; + save_fpu_regs(target); + if (sizeof(target->thread.fpu.fpr[0]) == sizeof(elf_fpreg_t)) r = gfpr_get(target, &to); else @@ -278,6 +280,8 @@ static int simd_get(struct task_struct *target, { const unsigned int wr_size = NUM_FPU_REGS * regset->size; + save_fpu_regs(target); + if (!tsk_used_math(target)) { /* The task hasn't used FP or LSX, fill with 0xff */ copy_pad_fprs(target, regset, &to, 0); diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index 8ea1bbcf13a7..6667b0a90f81 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -317,7 +317,7 @@ void loongson_cpu_die(unsigned int cpu) mb(); } -void play_dead(void) +void __noreturn arch_cpu_idle_dead(void) { register uint64_t addr; register void (*init_fn)(void); diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index 8fb5e7a77145..89699db45cec 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -383,16 +383,15 @@ void show_registers(struct pt_regs *regs) static DEFINE_RAW_SPINLOCK(die_lock); -void __noreturn die(const char *str, struct pt_regs *regs) +void die(const char *str, struct pt_regs *regs) { + int ret; static int die_counter; - int sig = SIGSEGV; oops_enter(); - if (notify_die(DIE_OOPS, str, regs, 0, current->thread.trap_nr, - SIGSEGV) == NOTIFY_STOP) - sig = 0; + ret = notify_die(DIE_OOPS, str, regs, 0, + current->thread.trap_nr, SIGSEGV); console_verbose(); raw_spin_lock_irq(&die_lock); @@ -405,6 +404,9 @@ void __noreturn die(const char *str, struct pt_regs *regs) oops_exit(); + if (ret == NOTIFY_STOP) + return; + if (regs && kexec_should_crash(current)) crash_kexec(regs); @@ -414,7 +416,7 @@ void __noreturn die(const char *str, struct pt_regs *regs) if (panic_on_oops) panic("Fatal exception"); - make_task_dead(sig); + make_task_dead(SIGSEGV); } static inline void setup_vint_size(unsigned int size) diff --git a/arch/loongarch/lib/clear_user.S b/arch/loongarch/lib/clear_user.S index 9dcf71719387..0790eadce166 100644 --- a/arch/loongarch/lib/clear_user.S +++ b/arch/loongarch/lib/clear_user.S @@ -3,12 +3,12 @@ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ +#include <linux/export.h> #include <asm/alternative-asm.h> #include <asm/asm.h> #include <asm/asmmacro.h> #include <asm/asm-extable.h> #include <asm/cpu.h> -#include <asm/export.h> #include <asm/regdef.h> .irp to, 0, 1, 2, 3, 4, 5, 6, 7 diff --git a/arch/loongarch/lib/copy_user.S b/arch/loongarch/lib/copy_user.S index fecd08cad702..bfe3d2793d00 100644 --- a/arch/loongarch/lib/copy_user.S +++ b/arch/loongarch/lib/copy_user.S @@ -3,12 +3,12 @@ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ +#include <linux/export.h> #include <asm/alternative-asm.h> #include <asm/asm.h> #include <asm/asmmacro.h> #include <asm/asm-extable.h> #include <asm/cpu.h> -#include <asm/export.h> #include <asm/regdef.h> .irp to, 0, 1, 2, 3, 4, 5, 6, 7 diff --git a/arch/loongarch/lib/memcpy.S b/arch/loongarch/lib/memcpy.S index 39ce6621c704..cc30b3b6252f 100644 --- a/arch/loongarch/lib/memcpy.S +++ b/arch/loongarch/lib/memcpy.S @@ -3,11 +3,11 @@ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ +#include <linux/export.h> #include <asm/alternative-asm.h> #include <asm/asm.h> #include <asm/asmmacro.h> #include <asm/cpu.h> -#include <asm/export.h> #include <asm/regdef.h> SYM_FUNC_START(memcpy) diff --git a/arch/loongarch/lib/memmove.S b/arch/loongarch/lib/memmove.S index 45b725ba7867..7dc76d1484b6 100644 --- a/arch/loongarch/lib/memmove.S +++ b/arch/loongarch/lib/memmove.S @@ -3,11 +3,11 @@ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ +#include <linux/export.h> #include <asm/alternative-asm.h> #include <asm/asm.h> #include <asm/asmmacro.h> #include <asm/cpu.h> -#include <asm/export.h> #include <asm/regdef.h> SYM_FUNC_START(memmove) diff --git a/arch/loongarch/lib/memset.S b/arch/loongarch/lib/memset.S index b39c6194e3ae..3f20f7996e8e 100644 --- a/arch/loongarch/lib/memset.S +++ b/arch/loongarch/lib/memset.S @@ -3,11 +3,11 @@ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ +#include <linux/export.h> #include <asm/alternative-asm.h> #include <asm/asm.h> #include <asm/asmmacro.h> #include <asm/cpu.h> -#include <asm/export.h> #include <asm/regdef.h> .macro fill_to_64 r0 diff --git a/arch/loongarch/lib/unaligned.S b/arch/loongarch/lib/unaligned.S index 9177fd638f07..185f82d85810 100644 --- a/arch/loongarch/lib/unaligned.S +++ b/arch/loongarch/lib/unaligned.S @@ -9,7 +9,6 @@ #include <asm/asmmacro.h> #include <asm/asm-extable.h> #include <asm/errno.h> -#include <asm/export.h> #include <asm/regdef.h> .L_fixup_handle_unaligned: diff --git a/arch/loongarch/mm/page.S b/arch/loongarch/mm/page.S index 4c874a7af0ad..7ad76551d313 100644 --- a/arch/loongarch/mm/page.S +++ b/arch/loongarch/mm/page.S @@ -2,9 +2,9 @@ /* * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ +#include <linux/export.h> #include <linux/linkage.h> #include <asm/asm.h> -#include <asm/export.h> #include <asm/page.h> #include <asm/regdef.h> diff --git a/arch/loongarch/mm/tlbex.S b/arch/loongarch/mm/tlbex.S index 4ad78703de6f..ca17dd3a1915 100644 --- a/arch/loongarch/mm/tlbex.S +++ b/arch/loongarch/mm/tlbex.S @@ -3,7 +3,6 @@ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ #include <asm/asm.h> -#include <asm/export.h> #include <asm/loongarch.h> #include <asm/page.h> #include <asm/pgtable.h> diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig index 4383ed851063..6deb8faa564b 100644 --- a/arch/m68k/configs/amiga_defconfig +++ b/arch/m68k/configs/amiga_defconfig @@ -591,7 +591,6 @@ CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m -CONFIG_CRYPTO_SHA3=m CONFIG_CRYPTO_SM3_GENERIC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m @@ -635,6 +634,7 @@ CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m CONFIG_TEST_XARRAY=m +CONFIG_TEST_MAPLE_TREE=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_IDA=m CONFIG_TEST_BITOPS=m diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig index ec0f9c9f9562..802c161827f4 100644 --- a/arch/m68k/configs/apollo_defconfig +++ b/arch/m68k/configs/apollo_defconfig @@ -548,7 +548,6 @@ CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m -CONFIG_CRYPTO_SHA3=m CONFIG_CRYPTO_SM3_GENERIC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m @@ -591,6 +590,7 @@ CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m CONFIG_TEST_XARRAY=m +CONFIG_TEST_MAPLE_TREE=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_IDA=m CONFIG_TEST_BITOPS=m diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig index 8656ae1f239e..2cb3d755873b 100644 --- a/arch/m68k/configs/atari_defconfig +++ b/arch/m68k/configs/atari_defconfig @@ -568,7 +568,6 @@ CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m -CONFIG_CRYPTO_SHA3=m CONFIG_CRYPTO_SM3_GENERIC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m @@ -612,6 +611,7 @@ CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m CONFIG_TEST_XARRAY=m +CONFIG_TEST_MAPLE_TREE=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_IDA=m CONFIG_TEST_BITOPS=m diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig index 496fb6a415ea..b13552caa6b3 100644 --- a/arch/m68k/configs/bvme6000_defconfig +++ b/arch/m68k/configs/bvme6000_defconfig @@ -540,7 +540,6 @@ CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m -CONFIG_CRYPTO_SHA3=m CONFIG_CRYPTO_SM3_GENERIC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m @@ -583,6 +582,7 @@ CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m CONFIG_TEST_XARRAY=m +CONFIG_TEST_MAPLE_TREE=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_IDA=m CONFIG_TEST_BITOPS=m diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig index 4add7ab9973b..f88356c45440 100644 --- a/arch/m68k/configs/hp300_defconfig +++ b/arch/m68k/configs/hp300_defconfig @@ -550,7 +550,6 @@ CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m -CONFIG_CRYPTO_SHA3=m CONFIG_CRYPTO_SM3_GENERIC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m @@ -593,6 +592,7 @@ CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m CONFIG_TEST_XARRAY=m +CONFIG_TEST_MAPLE_TREE=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_IDA=m CONFIG_TEST_BITOPS=m diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig index 5845f1f71fd1..7c2ebb616fba 100644 --- a/arch/m68k/configs/mac_defconfig +++ b/arch/m68k/configs/mac_defconfig @@ -570,7 +570,6 @@ CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m -CONFIG_CRYPTO_SHA3=m CONFIG_CRYPTO_SM3_GENERIC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m @@ -614,6 +613,7 @@ CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m CONFIG_TEST_XARRAY=m +CONFIG_TEST_MAPLE_TREE=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_IDA=m CONFIG_TEST_BITOPS=m diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig index bbb251bab81a..d3b272910b38 100644 --- a/arch/m68k/configs/multi_defconfig +++ b/arch/m68k/configs/multi_defconfig @@ -656,7 +656,6 @@ CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m -CONFIG_CRYPTO_SHA3=m CONFIG_CRYPTO_SM3_GENERIC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m @@ -700,6 +699,7 @@ CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m CONFIG_TEST_XARRAY=m +CONFIG_TEST_MAPLE_TREE=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_IDA=m CONFIG_TEST_BITOPS=m diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig index 4f9cfc70c66d..4529bc4b843c 100644 --- a/arch/m68k/configs/mvme147_defconfig +++ b/arch/m68k/configs/mvme147_defconfig @@ -539,7 +539,6 @@ CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m -CONFIG_CRYPTO_SHA3=m CONFIG_CRYPTO_SM3_GENERIC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m @@ -582,6 +581,7 @@ CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m CONFIG_TEST_XARRAY=m +CONFIG_TEST_MAPLE_TREE=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_IDA=m CONFIG_TEST_BITOPS=m diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig index 67c42b4822f0..30824032e4d5 100644 --- a/arch/m68k/configs/mvme16x_defconfig +++ b/arch/m68k/configs/mvme16x_defconfig @@ -540,7 +540,6 @@ CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m -CONFIG_CRYPTO_SHA3=m CONFIG_CRYPTO_SM3_GENERIC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m @@ -583,6 +582,7 @@ CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m CONFIG_TEST_XARRAY=m +CONFIG_TEST_MAPLE_TREE=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_IDA=m CONFIG_TEST_BITOPS=m diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig index 85f19515200b..3911211410ed 100644 --- a/arch/m68k/configs/q40_defconfig +++ b/arch/m68k/configs/q40_defconfig @@ -557,7 +557,6 @@ CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m -CONFIG_CRYPTO_SHA3=m CONFIG_CRYPTO_SM3_GENERIC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m @@ -601,6 +600,7 @@ CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m CONFIG_TEST_XARRAY=m +CONFIG_TEST_MAPLE_TREE=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_IDA=m CONFIG_TEST_BITOPS=m diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig index b1b15acb5d5f..991730c50957 100644 --- a/arch/m68k/configs/sun3_defconfig +++ b/arch/m68k/configs/sun3_defconfig @@ -538,7 +538,6 @@ CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m -CONFIG_CRYPTO_SHA3=m CONFIG_CRYPTO_SM3_GENERIC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m @@ -580,6 +579,7 @@ CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m CONFIG_TEST_XARRAY=m +CONFIG_TEST_MAPLE_TREE=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_IDA=m CONFIG_TEST_BITOPS=m diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig index 91d66c0f5ab6..e80d7509ab1d 100644 --- a/arch/m68k/configs/sun3x_defconfig +++ b/arch/m68k/configs/sun3x_defconfig @@ -538,7 +538,6 @@ CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m -CONFIG_CRYPTO_SHA3=m CONFIG_CRYPTO_SM3_GENERIC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_WP512=m @@ -581,6 +580,7 @@ CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m CONFIG_TEST_XARRAY=m +CONFIG_TEST_MAPLE_TREE=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_IDA=m CONFIG_TEST_BITOPS=m diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild index 1b720299deb1..0dbf9c5c6fae 100644 --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -1,6 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 generated-y += syscall_table.h -generic-y += export.h generic-y += extable.h generic-y += kvm_para.h generic-y += mcs_spinlock.h diff --git a/arch/m68k/include/asm/div64.h b/arch/m68k/include/asm/div64.h index 365f39f5e256..df1f6b450cc5 100644 --- a/arch/m68k/include/asm/div64.h +++ b/arch/m68k/include/asm/div64.h @@ -31,6 +31,9 @@ __rem; \ }) +/* defining this stops the unused helper function from being built */ +#define __div64_32 __div64_32 + #endif /* CONFIG_CPU_HAS_NO_MULDIV64 */ #endif /* _M68K_DIV64_H */ diff --git a/arch/m68k/include/asm/string.h b/arch/m68k/include/asm/string.h index f0f5021d6327..760cc13acdf4 100644 --- a/arch/m68k/include/asm/string.h +++ b/arch/m68k/include/asm/string.h @@ -41,6 +41,7 @@ static inline char *strncpy(char *dest, const char *src, size_t n) #define __HAVE_ARCH_MEMMOVE extern void *memmove(void *, const void *, __kernel_size_t); +extern int memcmp(const void *, const void *, __kernel_size_t); #define memcmp(d, s, n) __builtin_memcmp(d, s, n) #define __HAVE_ARCH_MEMSET diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 4f504783371f..259ceb125367 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -451,3 +451,4 @@ 449 common futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node 451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 diff --git a/arch/m68k/lib/divsi3.S b/arch/m68k/lib/divsi3.S index 3a2143f51631..62787b4333e7 100644 --- a/arch/m68k/lib/divsi3.S +++ b/arch/m68k/lib/divsi3.S @@ -33,7 +33,7 @@ General Public License for more details. */ D. V. Henkel-Wallace (gumby@cygnus.com) Fete Bastille, 1992 */ -#include <asm/export.h> +#include <linux/export.h> /* These are predefined by new versions of GNU cpp. */ diff --git a/arch/m68k/lib/modsi3.S b/arch/m68k/lib/modsi3.S index 1c967649a4e0..1bcb742d0b76 100644 --- a/arch/m68k/lib/modsi3.S +++ b/arch/m68k/lib/modsi3.S @@ -33,7 +33,7 @@ General Public License for more details. */ D. V. Henkel-Wallace (gumby@cygnus.com) Fete Bastille, 1992 */ -#include <asm/export.h> +#include <linux/export.h> /* These are predefined by new versions of GNU cpp. */ diff --git a/arch/m68k/lib/mulsi3.S b/arch/m68k/lib/mulsi3.S index 855675e69a8a..c2853248249e 100644 --- a/arch/m68k/lib/mulsi3.S +++ b/arch/m68k/lib/mulsi3.S @@ -32,7 +32,7 @@ General Public License for more details. */ Some of this code comes from MINIX, via the folks at ericsson. D. V. Henkel-Wallace (gumby@cygnus.com) Fete Bastille, 1992 */ -#include <asm/export.h> +#include <linux/export.h> /* These are predefined by new versions of GNU cpp. */ #ifndef __USER_LABEL_PREFIX__ diff --git a/arch/m68k/lib/udivsi3.S b/arch/m68k/lib/udivsi3.S index 78440ae513bf..39ad70596293 100644 --- a/arch/m68k/lib/udivsi3.S +++ b/arch/m68k/lib/udivsi3.S @@ -32,7 +32,7 @@ General Public License for more details. */ Some of this code comes from MINIX, via the folks at ericsson. D. V. Henkel-Wallace (gumby@cygnus.com) Fete Bastille, 1992 */ -#include <asm/export.h> +#include <linux/export.h> /* These are predefined by new versions of GNU cpp. */ #ifndef __USER_LABEL_PREFIX__ diff --git a/arch/m68k/lib/umodsi3.S b/arch/m68k/lib/umodsi3.S index b6fd11f58948..6640eaa9eb03 100644 --- a/arch/m68k/lib/umodsi3.S +++ b/arch/m68k/lib/umodsi3.S @@ -32,7 +32,7 @@ General Public License for more details. */ Some of this code comes from MINIX, via the folks at ericsson. D. V. Henkel-Wallace (gumby@cygnus.com) Fete Bastille, 1992 */ -#include <asm/export.h> +#include <linux/export.h> /* These are predefined by new versions of GNU cpp. */ #ifndef __USER_LABEL_PREFIX__ diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index 858d22bf275c..a3798c2637fd 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -457,3 +457,4 @@ 449 common futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node 451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 diff --git a/arch/mips/include/asm/local.h b/arch/mips/include/asm/local.h index 5daf6fe8e3e9..e6ae3df0349d 100644 --- a/arch/mips/include/asm/local.h +++ b/arch/mips/include/asm/local.h @@ -101,8 +101,8 @@ static __inline__ long local_cmpxchg(local_t *l, long old, long new) static __inline__ bool local_try_cmpxchg(local_t *l, long *old, long new) { - typeof(l->a.counter) *__old = (typeof(l->a.counter) *) old; - return try_cmpxchg_local(&l->a.counter, __old, new); + return try_cmpxchg_local(&l->a.counter, + (typeof(l->a.counter) *) old, new); } #define local_xchg(l, n) (atomic_long_xchg((&(l)->a), (n))) diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 1976317d4e8b..152034b8e0a0 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -390,3 +390,4 @@ 449 n32 futex_waitv sys_futex_waitv 450 n32 set_mempolicy_home_node sys_set_mempolicy_home_node 451 n32 cachestat sys_cachestat +452 n32 fchmodat2 sys_fchmodat2 diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index cfda2511badf..cb5e757f6621 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -366,3 +366,4 @@ 449 n64 futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node 451 n64 cachestat sys_cachestat +452 n64 fchmodat2 sys_fchmodat2 diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 7692234c3768..1a646813afdc 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -439,3 +439,4 @@ 449 o32 futex_waitv sys_futex_waitv 450 o32 set_mempolicy_home_node sys_set_mempolicy_home_node 451 o32 cachestat sys_cachestat +452 o32 fchmodat2 sys_fchmodat2 diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index a0a9145b6dd4..e97c175b56f9 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -450,3 +450,4 @@ 449 common futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node 451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 8c0b08b7a80e..20e50586e8a2 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -538,3 +538,4 @@ 449 common futex_waitv sys_futex_waitv 450 nospu set_mempolicy_home_node sys_set_mempolicy_home_node 451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 diff --git a/arch/powerpc/mm/book3s64/subpage_prot.c b/arch/powerpc/mm/book3s64/subpage_prot.c index 0dc85556dec5..ec98e526167e 100644 --- a/arch/powerpc/mm/book3s64/subpage_prot.c +++ b/arch/powerpc/mm/book3s64/subpage_prot.c @@ -145,6 +145,7 @@ static int subpage_walk_pmd_entry(pmd_t *pmd, unsigned long addr, static const struct mm_walk_ops subpage_walk_ops = { .pmd_entry = subpage_walk_pmd_entry, + .walk_lock = PGWALK_WRLOCK_VERIFY, }; static void subpage_mark_vma_nohuge(struct mm_struct *mm, unsigned long addr, diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index ea807aa0c31a..38c5be34c895 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -86,7 +86,7 @@ spufs_new_inode(struct super_block *sb, umode_t mode) inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); - inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); + inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); out: return inode; } diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 10e7a7ad175a..bea7b73e895d 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -580,15 +580,15 @@ config TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI and Zifencei are supported in binutils from version 2.36 onwards. To make life easier, and avoid forcing toolchains that default to a newer ISA spec to version 2.2, relax the check to binutils >= 2.36. - For clang < 17 or GCC < 11.1.0, for which this is not possible, this is - dealt with in CONFIG_TOOLCHAIN_NEEDS_OLD_ISA_SPEC. + For clang < 17 or GCC < 11.3.0, for which this is not possible or need + special treatment, this is dealt with in TOOLCHAIN_NEEDS_OLD_ISA_SPEC. config TOOLCHAIN_NEEDS_OLD_ISA_SPEC def_bool y depends on TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI # https://github.com/llvm/llvm-project/commit/22e199e6afb1263c943c0c0d4498694e15bf8a16 - # https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=b03be74bad08c382da47e048007a78fa3fb4ef49 - depends on (CC_IS_CLANG && CLANG_VERSION < 170000) || (CC_IS_GCC && GCC_VERSION < 110100) + # https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=d29f5d6ab513c52fd872f532c492e35ae9fd6671 + depends on (CC_IS_CLANG && CLANG_VERSION < 170000) || (CC_IS_GCC && GCC_VERSION < 110300) help Certain versions of clang and GCC do not support zicsr and zifencei via -march. This option causes an older ISA spec compatible with these older diff --git a/arch/riscv/include/asm/efi.h b/arch/riscv/include/asm/efi.h index 29e9a0d84b16..8a6a128ec57f 100644 --- a/arch/riscv/include/asm/efi.h +++ b/arch/riscv/include/asm/efi.h @@ -21,12 +21,6 @@ extern void efi_init(void); int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md); int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md, bool); -#define arch_efi_call_virt_setup() ({ \ - sync_kernel_mappings(efi_mm.pgd); \ - efi_virtmap_load(); \ - }) -#define arch_efi_call_virt_teardown() efi_virtmap_unload() - #define ARCH_EFI_IRQ_FLAGS_MASK (SR_IE | SR_SPIE) /* Load initrd anywhere in system RAM */ @@ -46,8 +40,8 @@ static inline unsigned long efi_get_kimg_min_align(void) #define EFI_KIMG_PREFERRED_ADDRESS efi_get_kimg_min_align() -void efi_virtmap_load(void); -void efi_virtmap_unload(void); +void arch_efi_call_virt_setup(void); +void arch_efi_call_virt_teardown(void); unsigned long stext_offset(void); diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h index 3d78930cab51..c5ee07b3df07 100644 --- a/arch/riscv/include/asm/vector.h +++ b/arch/riscv/include/asm/vector.h @@ -70,8 +70,9 @@ static __always_inline void __vstate_csr_save(struct __riscv_v_ext_state *dest) "csrr %1, " __stringify(CSR_VTYPE) "\n\t" "csrr %2, " __stringify(CSR_VL) "\n\t" "csrr %3, " __stringify(CSR_VCSR) "\n\t" + "csrr %4, " __stringify(CSR_VLENB) "\n\t" : "=r" (dest->vstart), "=r" (dest->vtype), "=r" (dest->vl), - "=r" (dest->vcsr) : :); + "=r" (dest->vcsr), "=r" (dest->vlenb) : :); } static __always_inline void __vstate_csr_restore(struct __riscv_v_ext_state *src) diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h index e17c550986a6..283800130614 100644 --- a/arch/riscv/include/uapi/asm/ptrace.h +++ b/arch/riscv/include/uapi/asm/ptrace.h @@ -97,6 +97,7 @@ struct __riscv_v_ext_state { unsigned long vl; unsigned long vtype; unsigned long vcsr; + unsigned long vlenb; void *datap; /* * In signal handler, datap will be set a correct user stack offset diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index 1d572cf3140f..487303e3ef22 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -25,9 +25,6 @@ enum riscv_regset { #ifdef CONFIG_FPU REGSET_F, #endif -#ifdef CONFIG_RISCV_ISA_V - REGSET_V, -#endif }; static int riscv_gpr_get(struct task_struct *target, @@ -84,61 +81,6 @@ static int riscv_fpr_set(struct task_struct *target, } #endif -#ifdef CONFIG_RISCV_ISA_V -static int riscv_vr_get(struct task_struct *target, - const struct user_regset *regset, - struct membuf to) -{ - struct __riscv_v_ext_state *vstate = &target->thread.vstate; - - if (!riscv_v_vstate_query(task_pt_regs(target))) - return -EINVAL; - - /* - * Ensure the vector registers have been saved to the memory before - * copying them to membuf. - */ - if (target == current) - riscv_v_vstate_save(current, task_pt_regs(current)); - - /* Copy vector header from vstate. */ - membuf_write(&to, vstate, offsetof(struct __riscv_v_ext_state, datap)); - membuf_zero(&to, sizeof(vstate->datap)); - - /* Copy all the vector registers from vstate. */ - return membuf_write(&to, vstate->datap, riscv_v_vsize); -} - -static int riscv_vr_set(struct task_struct *target, - const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) -{ - int ret, size; - struct __riscv_v_ext_state *vstate = &target->thread.vstate; - - if (!riscv_v_vstate_query(task_pt_regs(target))) - return -EINVAL; - - /* Copy rest of the vstate except datap */ - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vstate, 0, - offsetof(struct __riscv_v_ext_state, datap)); - if (unlikely(ret)) - return ret; - - /* Skip copy datap. */ - size = sizeof(vstate->datap); - count -= size; - ubuf += size; - - /* Copy all the vector registers. */ - pos = 0; - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vstate->datap, - 0, riscv_v_vsize); - return ret; -} -#endif - static const struct user_regset riscv_user_regset[] = { [REGSET_X] = { .core_note_type = NT_PRSTATUS, @@ -158,17 +100,6 @@ static const struct user_regset riscv_user_regset[] = { .set = riscv_fpr_set, }, #endif -#ifdef CONFIG_RISCV_ISA_V - [REGSET_V] = { - .core_note_type = NT_RISCV_VECTOR, - .align = 16, - .n = ((32 * RISCV_MAX_VLENB) + - sizeof(struct __riscv_v_ext_state)) / sizeof(__u32), - .size = sizeof(__u32), - .regset_get = riscv_vr_get, - .set = riscv_vr_set, - }, -#endif }; static const struct user_regset_view riscv_user_native_view = { diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c index ea3d61de065b..161d0b34c2cb 100644 --- a/arch/riscv/mm/pageattr.c +++ b/arch/riscv/mm/pageattr.c @@ -102,6 +102,7 @@ static const struct mm_walk_ops pageattr_ops = { .pmd_entry = pageattr_pmd_entry, .pte_entry = pageattr_pte_entry, .pte_hole = pageattr_pte_hole, + .walk_lock = PGWALK_RDLOCK, }; static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask, diff --git a/arch/s390/Kbuild b/arch/s390/Kbuild index 76e362277179..8e4d74f51115 100644 --- a/arch/s390/Kbuild +++ b/arch/s390/Kbuild @@ -3,7 +3,7 @@ obj-y += kernel/ obj-y += mm/ obj-$(CONFIG_KVM) += kvm/ obj-y += crypto/ -obj-$(CONFIG_S390_HYPFS_FS) += hypfs/ +obj-$(CONFIG_S390_HYPFS) += hypfs/ obj-$(CONFIG_APPLDATA_BASE) += appldata/ obj-y += net/ obj-$(CONFIG_PCI) += pci/ diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 5b39918b7042..18bf754e1fad 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -174,6 +174,7 @@ config S390 select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_FUNCTION_ERROR_INJECTION + select HAVE_FUNCTION_GRAPH_RETVAL select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_GCC_PLUGINS @@ -512,6 +513,17 @@ config KEXEC_SIG verification for the corresponding kernel image type being loaded in order for this to work. +config CERT_STORE + bool "Get user certificates via DIAG320" + depends on KEYS + select CRYPTO_LIB_SHA256 + help + Enable this option if you want to access user-provided secure boot + certificates via DIAG 0x320. + + These certificates will be made available via the keyring named + 'cert_store'. + config KERNEL_NOBP def_bool n prompt "Enable modified branch prediction for the kernel by default" @@ -743,9 +755,9 @@ config CRASH_DUMP Crash dump kernels are loaded in the main kernel with kexec-tools into a specially reserved region and then later executed after a crash by kdump/kexec. - Refer to <file:Documentation/s390/zfcpdump.rst> for more details on this. + Refer to <file:Documentation/arch/s390/zfcpdump.rst> for more details on this. This option also enables s390 zfcpdump. - See also <file:Documentation/s390/zfcpdump.rst> + See also <file:Documentation/arch/s390/zfcpdump.rst> endmenu @@ -867,13 +879,24 @@ config APPLDATA_NET_SUM This can also be compiled as a module, which will be called appldata_net_sum.o. -config S390_HYPFS_FS +config S390_HYPFS def_bool y + prompt "s390 hypervisor information" + help + This provides several binary files at (debugfs)/s390_hypfs/ to + provide accounting information in an s390 hypervisor environment. + +config S390_HYPFS_FS + def_bool n prompt "s390 hypervisor file system support" select SYS_HYPERVISOR + depends on S390_HYPFS help This is a virtual file system intended to provide accounting - information in an s390 hypervisor environment. + information in an s390 hypervisor environment. This file system + is deprecated and should not be used. + + Say N if you are unsure. source "arch/s390/kvm/Kconfig" diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 5ed242897b0d..a53a36ee0731 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -119,7 +119,6 @@ export KBUILD_CFLAGS_DECOMPRESSOR OBJCOPYFLAGS := -O binary libs-y += arch/s390/lib/ -drivers-y += drivers/s390/ boot := arch/s390/boot syscalls := arch/s390/kernel/syscalls diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index 64bd7ac3e35d..b9681cb22753 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -27,6 +27,7 @@ struct page *__bootdata_preserved(vmemmap); unsigned long __bootdata_preserved(vmemmap_size); unsigned long __bootdata_preserved(MODULES_VADDR); unsigned long __bootdata_preserved(MODULES_END); +unsigned long __bootdata_preserved(max_mappable); unsigned long __bootdata(ident_map_size); u64 __bootdata_preserved(stfle_fac_list[16]); @@ -176,6 +177,7 @@ static unsigned long setup_kernel_memory_layout(void) unsigned long asce_limit; unsigned long rte_size; unsigned long pages; + unsigned long vsize; unsigned long vmax; pages = ident_map_size / PAGE_SIZE; @@ -183,19 +185,19 @@ static unsigned long setup_kernel_memory_layout(void) vmemmap_size = SECTION_ALIGN_UP(pages) * sizeof(struct page); /* choose kernel address space layout: 4 or 3 levels. */ - vmemmap_start = round_up(ident_map_size, _REGION3_SIZE); - if (IS_ENABLED(CONFIG_KASAN) || - vmalloc_size > _REGION2_SIZE || - vmemmap_start + vmemmap_size + vmalloc_size + MODULES_LEN > - _REGION2_SIZE) { + vsize = round_up(ident_map_size, _REGION3_SIZE) + vmemmap_size + + MODULES_LEN + MEMCPY_REAL_SIZE + ABS_LOWCORE_MAP_SIZE; + vsize = size_add(vsize, vmalloc_size); + if (IS_ENABLED(CONFIG_KASAN) || (vsize > _REGION2_SIZE)) { asce_limit = _REGION1_SIZE; rte_size = _REGION2_SIZE; } else { asce_limit = _REGION2_SIZE; rte_size = _REGION3_SIZE; } + /* - * forcing modules and vmalloc area under the ultravisor + * Forcing modules and vmalloc area under the ultravisor * secure storage limit, so that any vmalloc allocation * we do could be used to back secure guest storage. */ @@ -204,7 +206,7 @@ static unsigned long setup_kernel_memory_layout(void) /* force vmalloc and modules below kasan shadow */ vmax = min(vmax, KASAN_SHADOW_START); #endif - __memcpy_real_area = round_down(vmax - PAGE_SIZE, PAGE_SIZE); + __memcpy_real_area = round_down(vmax - MEMCPY_REAL_SIZE, PAGE_SIZE); __abs_lowcore = round_down(__memcpy_real_area - ABS_LOWCORE_MAP_SIZE, sizeof(struct lowcore)); MODULES_END = round_down(__abs_lowcore, _SEGMENT_SIZE); @@ -220,8 +222,9 @@ static unsigned long setup_kernel_memory_layout(void) pages = SECTION_ALIGN_UP(pages); /* keep vmemmap_start aligned to a top level region table entry */ vmemmap_start = round_down(VMALLOC_START - pages * sizeof(struct page), rte_size); - /* vmemmap_start is the future VMEM_MAX_PHYS, make sure it is within MAX_PHYSMEM */ vmemmap_start = min(vmemmap_start, 1UL << MAX_PHYSMEM_BITS); + /* maximum mappable address as seen by arch_get_mappable_range() */ + max_mappable = vmemmap_start; /* make sure identity map doesn't overlay with vmemmap */ ident_map_size = min(ident_map_size, vmemmap_start); vmemmap_size = SECTION_ALIGN_UP(ident_map_size / PAGE_SIZE) * sizeof(struct page); @@ -286,8 +289,9 @@ void startup_kernel(void) setup_lpp(); safe_addr = mem_safe_offset(); + /* - * reserve decompressor memory together with decompression heap, buffer and + * Reserve decompressor memory together with decompression heap, buffer and * memory which might be occupied by uncompressed kernel at default 1Mb * position (if KASLR is off or failed). */ diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 3a6a9a88bd38..af2fbe48e16c 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -835,6 +835,7 @@ CONFIG_RCU_CPU_STALL_TIMEOUT=300 # CONFIG_RCU_TRACE is not set CONFIG_LATENCYTOP=y CONFIG_BOOTTIME_TRACING=y +CONFIG_FUNCTION_GRAPH_RETVAL=y CONFIG_FPROBE=y CONFIG_FUNCTION_PROFILER=y CONFIG_STACK_TRACER=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index b13a5a0d99d2..3f263b767a4c 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -787,6 +787,7 @@ CONFIG_RCU_REF_SCALE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=60 CONFIG_LATENCYTOP=y CONFIG_BOOTTIME_TRACING=y +CONFIG_FUNCTION_GRAPH_RETVAL=y CONFIG_FPROBE=y CONFIG_FUNCTION_PROFILER=y CONFIG_STACK_TRACER=y diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c index 38349150c96e..8b541e44151d 100644 --- a/arch/s390/crypto/paes_s390.c +++ b/arch/s390/crypto/paes_s390.c @@ -35,7 +35,7 @@ * and padding is also possible, the limits need to be generous. */ #define PAES_MIN_KEYSIZE 16 -#define PAES_MAX_KEYSIZE 320 +#define PAES_MAX_KEYSIZE MAXEP11AESKEYBLOBSIZE static u8 *ctrblk; static DEFINE_MUTEX(ctrblk_lock); diff --git a/arch/s390/hypfs/Makefile b/arch/s390/hypfs/Makefile index 06f601509ce9..c34854d298f8 100644 --- a/arch/s390/hypfs/Makefile +++ b/arch/s390/hypfs/Makefile @@ -3,7 +3,12 @@ # Makefile for the linux hypfs filesystem routines. # -obj-$(CONFIG_S390_HYPFS_FS) += s390_hypfs.o +obj-$(CONFIG_S390_HYPFS) += hypfs_dbfs.o +obj-$(CONFIG_S390_HYPFS) += hypfs_diag.o +obj-$(CONFIG_S390_HYPFS) += hypfs_diag0c.o +obj-$(CONFIG_S390_HYPFS) += hypfs_sprp.o +obj-$(CONFIG_S390_HYPFS) += hypfs_vm.o -s390_hypfs-objs := inode.o hypfs_diag.o hypfs_vm.o hypfs_dbfs.o hypfs_sprp.o -s390_hypfs-objs += hypfs_diag0c.o +obj-$(CONFIG_S390_HYPFS_FS) += hypfs_diag_fs.o +obj-$(CONFIG_S390_HYPFS_FS) += hypfs_vm_fs.o +obj-$(CONFIG_S390_HYPFS_FS) += inode.o diff --git a/arch/s390/hypfs/hypfs.h b/arch/s390/hypfs/hypfs.h index 05f3f9aee5fc..65f4036fd541 100644 --- a/arch/s390/hypfs/hypfs.h +++ b/arch/s390/hypfs/hypfs.h @@ -46,6 +46,15 @@ void hypfs_diag0c_exit(void); void hypfs_sprp_init(void); void hypfs_sprp_exit(void); +int __hypfs_fs_init(void); + +static inline int hypfs_fs_init(void) +{ + if (IS_ENABLED(CONFIG_S390_HYPFS_FS)) + return __hypfs_fs_init(); + return 0; +} + /* debugfs interface */ struct hypfs_dbfs_file; @@ -69,7 +78,6 @@ struct hypfs_dbfs_file { struct dentry *dentry; }; -extern void hypfs_dbfs_init(void); extern void hypfs_dbfs_exit(void); extern void hypfs_dbfs_create_file(struct hypfs_dbfs_file *df); extern void hypfs_dbfs_remove_file(struct hypfs_dbfs_file *df); diff --git a/arch/s390/hypfs/hypfs_dbfs.c b/arch/s390/hypfs/hypfs_dbfs.c index f4c7dbfaf8ee..4024599eb448 100644 --- a/arch/s390/hypfs/hypfs_dbfs.c +++ b/arch/s390/hypfs/hypfs_dbfs.c @@ -90,12 +90,33 @@ void hypfs_dbfs_remove_file(struct hypfs_dbfs_file *df) debugfs_remove(df->dentry); } -void hypfs_dbfs_init(void) +static int __init hypfs_dbfs_init(void) { - dbfs_dir = debugfs_create_dir("s390_hypfs", NULL); -} + int rc = -ENODATA; -void hypfs_dbfs_exit(void) -{ + dbfs_dir = debugfs_create_dir("s390_hypfs", NULL); + if (hypfs_diag_init()) + goto fail_dbfs_exit; + if (hypfs_vm_init()) + goto fail_hypfs_diag_exit; + hypfs_sprp_init(); + if (hypfs_diag0c_init()) + goto fail_hypfs_sprp_exit; + rc = hypfs_fs_init(); + if (rc) + goto fail_hypfs_diag0c_exit; + return 0; + +fail_hypfs_diag0c_exit: + hypfs_diag0c_exit(); +fail_hypfs_sprp_exit: + hypfs_sprp_exit(); + hypfs_vm_exit(); +fail_hypfs_diag_exit: + hypfs_diag_exit(); + pr_err("Initialization of hypfs failed with rc=%i\n", rc); +fail_dbfs_exit: debugfs_remove(dbfs_dir); + return rc; } +device_initcall(hypfs_dbfs_init) diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c index c3be533c4cd3..279b7bba4d43 100644 --- a/arch/s390/hypfs/hypfs_diag.c +++ b/arch/s390/hypfs/hypfs_diag.c @@ -18,188 +18,27 @@ #include <linux/mm.h> #include <asm/diag.h> #include <asm/ebcdic.h> +#include "hypfs_diag.h" #include "hypfs.h" -#define TMP_SIZE 64 /* size of temporary buffers */ - #define DBFS_D204_HDR_VERSION 0 -static char *diag224_cpu_names; /* diag 224 name table */ static enum diag204_sc diag204_store_sc; /* used subcode for store */ static enum diag204_format diag204_info_type; /* used diag 204 data format */ static void *diag204_buf; /* 4K aligned buffer for diag204 data */ -static void *diag204_buf_vmalloc; /* vmalloc pointer for diag204 data */ static int diag204_buf_pages; /* number of pages for diag204 data */ static struct dentry *dbfs_d204_file; -/* - * DIAG 204 member access functions. - * - * Since we have two different diag 204 data formats for old and new s390 - * machines, we do not access the structs directly, but use getter functions for - * each struct member instead. This should make the code more readable. - */ - -/* Time information block */ - -static inline int info_blk_hdr__size(enum diag204_format type) -{ - if (type == DIAG204_INFO_SIMPLE) - return sizeof(struct diag204_info_blk_hdr); - else /* DIAG204_INFO_EXT */ - return sizeof(struct diag204_x_info_blk_hdr); -} - -static inline __u8 info_blk_hdr__npar(enum diag204_format type, void *hdr) -{ - if (type == DIAG204_INFO_SIMPLE) - return ((struct diag204_info_blk_hdr *)hdr)->npar; - else /* DIAG204_INFO_EXT */ - return ((struct diag204_x_info_blk_hdr *)hdr)->npar; -} - -static inline __u8 info_blk_hdr__flags(enum diag204_format type, void *hdr) -{ - if (type == DIAG204_INFO_SIMPLE) - return ((struct diag204_info_blk_hdr *)hdr)->flags; - else /* DIAG204_INFO_EXT */ - return ((struct diag204_x_info_blk_hdr *)hdr)->flags; -} - -/* Partition header */ - -static inline int part_hdr__size(enum diag204_format type) -{ - if (type == DIAG204_INFO_SIMPLE) - return sizeof(struct diag204_part_hdr); - else /* DIAG204_INFO_EXT */ - return sizeof(struct diag204_x_part_hdr); -} - -static inline __u8 part_hdr__rcpus(enum diag204_format type, void *hdr) -{ - if (type == DIAG204_INFO_SIMPLE) - return ((struct diag204_part_hdr *)hdr)->cpus; - else /* DIAG204_INFO_EXT */ - return ((struct diag204_x_part_hdr *)hdr)->rcpus; -} - -static inline void part_hdr__part_name(enum diag204_format type, void *hdr, - char *name) -{ - if (type == DIAG204_INFO_SIMPLE) - memcpy(name, ((struct diag204_part_hdr *)hdr)->part_name, - DIAG204_LPAR_NAME_LEN); - else /* DIAG204_INFO_EXT */ - memcpy(name, ((struct diag204_x_part_hdr *)hdr)->part_name, - DIAG204_LPAR_NAME_LEN); - EBCASC(name, DIAG204_LPAR_NAME_LEN); - name[DIAG204_LPAR_NAME_LEN] = 0; - strim(name); -} - -/* CPU info block */ - -static inline int cpu_info__size(enum diag204_format type) -{ - if (type == DIAG204_INFO_SIMPLE) - return sizeof(struct diag204_cpu_info); - else /* DIAG204_INFO_EXT */ - return sizeof(struct diag204_x_cpu_info); -} - -static inline __u8 cpu_info__ctidx(enum diag204_format type, void *hdr) -{ - if (type == DIAG204_INFO_SIMPLE) - return ((struct diag204_cpu_info *)hdr)->ctidx; - else /* DIAG204_INFO_EXT */ - return ((struct diag204_x_cpu_info *)hdr)->ctidx; -} - -static inline __u16 cpu_info__cpu_addr(enum diag204_format type, void *hdr) +enum diag204_format diag204_get_info_type(void) { - if (type == DIAG204_INFO_SIMPLE) - return ((struct diag204_cpu_info *)hdr)->cpu_addr; - else /* DIAG204_INFO_EXT */ - return ((struct diag204_x_cpu_info *)hdr)->cpu_addr; + return diag204_info_type; } -static inline __u64 cpu_info__acc_time(enum diag204_format type, void *hdr) +static void diag204_set_info_type(enum diag204_format type) { - if (type == DIAG204_INFO_SIMPLE) - return ((struct diag204_cpu_info *)hdr)->acc_time; - else /* DIAG204_INFO_EXT */ - return ((struct diag204_x_cpu_info *)hdr)->acc_time; -} - -static inline __u64 cpu_info__lp_time(enum diag204_format type, void *hdr) -{ - if (type == DIAG204_INFO_SIMPLE) - return ((struct diag204_cpu_info *)hdr)->lp_time; - else /* DIAG204_INFO_EXT */ - return ((struct diag204_x_cpu_info *)hdr)->lp_time; -} - -static inline __u64 cpu_info__online_time(enum diag204_format type, void *hdr) -{ - if (type == DIAG204_INFO_SIMPLE) - return 0; /* online_time not available in simple info */ - else /* DIAG204_INFO_EXT */ - return ((struct diag204_x_cpu_info *)hdr)->online_time; -} - -/* Physical header */ - -static inline int phys_hdr__size(enum diag204_format type) -{ - if (type == DIAG204_INFO_SIMPLE) - return sizeof(struct diag204_phys_hdr); - else /* DIAG204_INFO_EXT */ - return sizeof(struct diag204_x_phys_hdr); -} - -static inline __u8 phys_hdr__cpus(enum diag204_format type, void *hdr) -{ - if (type == DIAG204_INFO_SIMPLE) - return ((struct diag204_phys_hdr *)hdr)->cpus; - else /* DIAG204_INFO_EXT */ - return ((struct diag204_x_phys_hdr *)hdr)->cpus; -} - -/* Physical CPU info block */ - -static inline int phys_cpu__size(enum diag204_format type) -{ - if (type == DIAG204_INFO_SIMPLE) - return sizeof(struct diag204_phys_cpu); - else /* DIAG204_INFO_EXT */ - return sizeof(struct diag204_x_phys_cpu); -} - -static inline __u16 phys_cpu__cpu_addr(enum diag204_format type, void *hdr) -{ - if (type == DIAG204_INFO_SIMPLE) - return ((struct diag204_phys_cpu *)hdr)->cpu_addr; - else /* DIAG204_INFO_EXT */ - return ((struct diag204_x_phys_cpu *)hdr)->cpu_addr; -} - -static inline __u64 phys_cpu__mgm_time(enum diag204_format type, void *hdr) -{ - if (type == DIAG204_INFO_SIMPLE) - return ((struct diag204_phys_cpu *)hdr)->mgm_time; - else /* DIAG204_INFO_EXT */ - return ((struct diag204_x_phys_cpu *)hdr)->mgm_time; -} - -static inline __u64 phys_cpu__ctidx(enum diag204_format type, void *hdr) -{ - if (type == DIAG204_INFO_SIMPLE) - return ((struct diag204_phys_cpu *)hdr)->ctidx; - else /* DIAG204_INFO_EXT */ - return ((struct diag204_x_phys_cpu *)hdr)->ctidx; + diag204_info_type = type; } /* Diagnose 204 functions */ @@ -212,43 +51,11 @@ static inline __u64 phys_cpu__ctidx(enum diag204_format type, void *hdr) static void diag204_free_buffer(void) { - if (!diag204_buf) - return; - if (diag204_buf_vmalloc) { - vfree(diag204_buf_vmalloc); - diag204_buf_vmalloc = NULL; - } else { - free_pages((unsigned long) diag204_buf, 0); - } + vfree(diag204_buf); diag204_buf = NULL; } -static void *page_align_ptr(void *ptr) -{ - return (void *) PAGE_ALIGN((unsigned long) ptr); -} - -static void *diag204_alloc_vbuf(int pages) -{ - /* The buffer has to be page aligned! */ - diag204_buf_vmalloc = vmalloc(array_size(PAGE_SIZE, (pages + 1))); - if (!diag204_buf_vmalloc) - return ERR_PTR(-ENOMEM); - diag204_buf = page_align_ptr(diag204_buf_vmalloc); - diag204_buf_pages = pages; - return diag204_buf; -} - -static void *diag204_alloc_rbuf(void) -{ - diag204_buf = (void*)__get_free_pages(GFP_KERNEL,0); - if (!diag204_buf) - return ERR_PTR(-ENOMEM); - diag204_buf_pages = 1; - return diag204_buf; -} - -static void *diag204_get_buffer(enum diag204_format fmt, int *pages) +void *diag204_get_buffer(enum diag204_format fmt, int *pages) { if (diag204_buf) { *pages = diag204_buf_pages; @@ -256,15 +63,19 @@ static void *diag204_get_buffer(enum diag204_format fmt, int *pages) } if (fmt == DIAG204_INFO_SIMPLE) { *pages = 1; - return diag204_alloc_rbuf(); } else {/* DIAG204_INFO_EXT */ *pages = diag204((unsigned long)DIAG204_SUBC_RSI | (unsigned long)DIAG204_INFO_EXT, 0, NULL); if (*pages <= 0) - return ERR_PTR(-ENOSYS); - else - return diag204_alloc_vbuf(*pages); + return ERR_PTR(-EOPNOTSUPP); } + diag204_buf = __vmalloc_node(array_size(*pages, PAGE_SIZE), + PAGE_SIZE, GFP_KERNEL, NUMA_NO_NODE, + __builtin_return_address(0)); + if (!diag204_buf) + return ERR_PTR(-ENOMEM); + diag204_buf_pages = *pages; + return diag204_buf; } /* @@ -291,13 +102,13 @@ static int diag204_probe(void) if (diag204((unsigned long)DIAG204_SUBC_STIB7 | (unsigned long)DIAG204_INFO_EXT, pages, buf) >= 0) { diag204_store_sc = DIAG204_SUBC_STIB7; - diag204_info_type = DIAG204_INFO_EXT; + diag204_set_info_type(DIAG204_INFO_EXT); goto out; } if (diag204((unsigned long)DIAG204_SUBC_STIB6 | (unsigned long)DIAG204_INFO_EXT, pages, buf) >= 0) { diag204_store_sc = DIAG204_SUBC_STIB6; - diag204_info_type = DIAG204_INFO_EXT; + diag204_set_info_type(DIAG204_INFO_EXT); goto out; } diag204_free_buffer(); @@ -313,10 +124,10 @@ static int diag204_probe(void) if (diag204((unsigned long)DIAG204_SUBC_STIB4 | (unsigned long)DIAG204_INFO_SIMPLE, pages, buf) >= 0) { diag204_store_sc = DIAG204_SUBC_STIB4; - diag204_info_type = DIAG204_INFO_SIMPLE; + diag204_set_info_type(DIAG204_INFO_SIMPLE); goto out; } else { - rc = -ENOSYS; + rc = -EOPNOTSUPP; goto fail_store; } out: @@ -327,58 +138,13 @@ fail_alloc: return rc; } -static int diag204_do_store(void *buf, int pages) +int diag204_store(void *buf, int pages) { int rc; - rc = diag204((unsigned long) diag204_store_sc | - (unsigned long) diag204_info_type, pages, buf); - return rc < 0 ? -ENOSYS : 0; -} - -static void *diag204_store(void) -{ - void *buf; - int pages, rc; - - buf = diag204_get_buffer(diag204_info_type, &pages); - if (IS_ERR(buf)) - goto out; - rc = diag204_do_store(buf, pages); - if (rc) - return ERR_PTR(rc); -out: - return buf; -} - -/* Diagnose 224 functions */ - -static int diag224_get_name_table(void) -{ - /* memory must be below 2GB */ - diag224_cpu_names = (char *) __get_free_page(GFP_KERNEL | GFP_DMA); - if (!diag224_cpu_names) - return -ENOMEM; - if (diag224(diag224_cpu_names)) { - free_page((unsigned long) diag224_cpu_names); - return -EOPNOTSUPP; - } - EBCASC(diag224_cpu_names + 16, (*diag224_cpu_names + 1) * 16); - return 0; -} - -static void diag224_delete_name_table(void) -{ - free_page((unsigned long) diag224_cpu_names); -} - -static int diag224_idx2name(int index, char *name) -{ - memcpy(name, diag224_cpu_names + ((index + 1) * DIAG204_CPU_NAME_LEN), - DIAG204_CPU_NAME_LEN); - name[DIAG204_CPU_NAME_LEN] = 0; - strim(name); - return 0; + rc = diag204((unsigned long)diag204_store_sc | + (unsigned long)diag204_get_info_type(), pages, buf); + return rc < 0 ? -EOPNOTSUPP : 0; } struct dbfs_d204_hdr { @@ -403,8 +169,8 @@ static int dbfs_d204_create(void **data, void **data_free_ptr, size_t *size) base = vzalloc(buf_size); if (!base) return -ENOMEM; - d204 = page_align_ptr(base + sizeof(d204->hdr)) - sizeof(d204->hdr); - rc = diag204_do_store(d204->buf, diag204_buf_pages); + d204 = PTR_ALIGN(base + sizeof(d204->hdr), PAGE_SIZE) - sizeof(d204->hdr); + rc = diag204_store(d204->buf, diag204_buf_pages); if (rc) { vfree(base); return rc; @@ -433,176 +199,21 @@ __init int hypfs_diag_init(void) return -ENODATA; } - if (diag204_info_type == DIAG204_INFO_EXT) + if (diag204_get_info_type() == DIAG204_INFO_EXT) hypfs_dbfs_create_file(&dbfs_file_d204); - if (MACHINE_IS_LPAR) { - rc = diag224_get_name_table(); - if (rc) { - pr_err("The hardware system does not provide all " - "functions required by hypfs\n"); - debugfs_remove(dbfs_d204_file); - return rc; - } + rc = hypfs_diag_fs_init(); + if (rc) { + pr_err("The hardware system does not provide all functions required by hypfs\n"); + debugfs_remove(dbfs_d204_file); } - return 0; + return rc; } void hypfs_diag_exit(void) { debugfs_remove(dbfs_d204_file); - diag224_delete_name_table(); + hypfs_diag_fs_exit(); diag204_free_buffer(); hypfs_dbfs_remove_file(&dbfs_file_d204); } - -/* - * Functions to create the directory structure - * ******************************************* - */ - -static int hypfs_create_cpu_files(struct dentry *cpus_dir, void *cpu_info) -{ - struct dentry *cpu_dir; - char buffer[TMP_SIZE]; - void *rc; - - snprintf(buffer, TMP_SIZE, "%d", cpu_info__cpu_addr(diag204_info_type, - cpu_info)); - cpu_dir = hypfs_mkdir(cpus_dir, buffer); - rc = hypfs_create_u64(cpu_dir, "mgmtime", - cpu_info__acc_time(diag204_info_type, cpu_info) - - cpu_info__lp_time(diag204_info_type, cpu_info)); - if (IS_ERR(rc)) - return PTR_ERR(rc); - rc = hypfs_create_u64(cpu_dir, "cputime", - cpu_info__lp_time(diag204_info_type, cpu_info)); - if (IS_ERR(rc)) - return PTR_ERR(rc); - if (diag204_info_type == DIAG204_INFO_EXT) { - rc = hypfs_create_u64(cpu_dir, "onlinetime", - cpu_info__online_time(diag204_info_type, - cpu_info)); - if (IS_ERR(rc)) - return PTR_ERR(rc); - } - diag224_idx2name(cpu_info__ctidx(diag204_info_type, cpu_info), buffer); - rc = hypfs_create_str(cpu_dir, "type", buffer); - return PTR_ERR_OR_ZERO(rc); -} - -static void *hypfs_create_lpar_files(struct dentry *systems_dir, void *part_hdr) -{ - struct dentry *cpus_dir; - struct dentry *lpar_dir; - char lpar_name[DIAG204_LPAR_NAME_LEN + 1]; - void *cpu_info; - int i; - - part_hdr__part_name(diag204_info_type, part_hdr, lpar_name); - lpar_name[DIAG204_LPAR_NAME_LEN] = 0; - lpar_dir = hypfs_mkdir(systems_dir, lpar_name); - if (IS_ERR(lpar_dir)) - return lpar_dir; - cpus_dir = hypfs_mkdir(lpar_dir, "cpus"); - if (IS_ERR(cpus_dir)) - return cpus_dir; - cpu_info = part_hdr + part_hdr__size(diag204_info_type); - for (i = 0; i < part_hdr__rcpus(diag204_info_type, part_hdr); i++) { - int rc; - rc = hypfs_create_cpu_files(cpus_dir, cpu_info); - if (rc) - return ERR_PTR(rc); - cpu_info += cpu_info__size(diag204_info_type); - } - return cpu_info; -} - -static int hypfs_create_phys_cpu_files(struct dentry *cpus_dir, void *cpu_info) -{ - struct dentry *cpu_dir; - char buffer[TMP_SIZE]; - void *rc; - - snprintf(buffer, TMP_SIZE, "%i", phys_cpu__cpu_addr(diag204_info_type, - cpu_info)); - cpu_dir = hypfs_mkdir(cpus_dir, buffer); - if (IS_ERR(cpu_dir)) - return PTR_ERR(cpu_dir); - rc = hypfs_create_u64(cpu_dir, "mgmtime", - phys_cpu__mgm_time(diag204_info_type, cpu_info)); - if (IS_ERR(rc)) - return PTR_ERR(rc); - diag224_idx2name(phys_cpu__ctidx(diag204_info_type, cpu_info), buffer); - rc = hypfs_create_str(cpu_dir, "type", buffer); - return PTR_ERR_OR_ZERO(rc); -} - -static void *hypfs_create_phys_files(struct dentry *parent_dir, void *phys_hdr) -{ - int i; - void *cpu_info; - struct dentry *cpus_dir; - - cpus_dir = hypfs_mkdir(parent_dir, "cpus"); - if (IS_ERR(cpus_dir)) - return cpus_dir; - cpu_info = phys_hdr + phys_hdr__size(diag204_info_type); - for (i = 0; i < phys_hdr__cpus(diag204_info_type, phys_hdr); i++) { - int rc; - rc = hypfs_create_phys_cpu_files(cpus_dir, cpu_info); - if (rc) - return ERR_PTR(rc); - cpu_info += phys_cpu__size(diag204_info_type); - } - return cpu_info; -} - -int hypfs_diag_create_files(struct dentry *root) -{ - struct dentry *systems_dir, *hyp_dir; - void *time_hdr, *part_hdr; - int i, rc; - void *buffer, *ptr; - - buffer = diag204_store(); - if (IS_ERR(buffer)) - return PTR_ERR(buffer); - - systems_dir = hypfs_mkdir(root, "systems"); - if (IS_ERR(systems_dir)) { - rc = PTR_ERR(systems_dir); - goto err_out; - } - time_hdr = (struct x_info_blk_hdr *)buffer; - part_hdr = time_hdr + info_blk_hdr__size(diag204_info_type); - for (i = 0; i < info_blk_hdr__npar(diag204_info_type, time_hdr); i++) { - part_hdr = hypfs_create_lpar_files(systems_dir, part_hdr); - if (IS_ERR(part_hdr)) { - rc = PTR_ERR(part_hdr); - goto err_out; - } - } - if (info_blk_hdr__flags(diag204_info_type, time_hdr) & - DIAG204_LPAR_PHYS_FLG) { - ptr = hypfs_create_phys_files(root, part_hdr); - if (IS_ERR(ptr)) { - rc = PTR_ERR(ptr); - goto err_out; - } - } - hyp_dir = hypfs_mkdir(root, "hyp"); - if (IS_ERR(hyp_dir)) { - rc = PTR_ERR(hyp_dir); - goto err_out; - } - ptr = hypfs_create_str(hyp_dir, "type", "LPAR Hypervisor"); - if (IS_ERR(ptr)) { - rc = PTR_ERR(ptr); - goto err_out; - } - rc = 0; - -err_out: - return rc; -} diff --git a/arch/s390/hypfs/hypfs_diag.h b/arch/s390/hypfs/hypfs_diag.h new file mode 100644 index 000000000000..7090eff27fef --- /dev/null +++ b/arch/s390/hypfs/hypfs_diag.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Hypervisor filesystem for Linux on s390. Diag 204 and 224 + * implementation. + * + * Copyright IBM Corp. 2006, 2008 + * Author(s): Michael Holzheu <holzheu@de.ibm.com> + */ + +#ifndef _S390_HYPFS_DIAG_H_ +#define _S390_HYPFS_DIAG_H_ + +#include <asm/diag.h> + +enum diag204_format diag204_get_info_type(void); +void *diag204_get_buffer(enum diag204_format fmt, int *pages); +int diag204_store(void *buf, int pages); + +int __hypfs_diag_fs_init(void); +void __hypfs_diag_fs_exit(void); + +static inline int hypfs_diag_fs_init(void) +{ + if (IS_ENABLED(CONFIG_S390_HYPFS_FS)) + return __hypfs_diag_fs_init(); + return 0; +} + +static inline void hypfs_diag_fs_exit(void) +{ + if (IS_ENABLED(CONFIG_S390_HYPFS_FS)) + __hypfs_diag_fs_exit(); +} + +#endif /* _S390_HYPFS_DIAG_H_ */ diff --git a/arch/s390/hypfs/hypfs_diag_fs.c b/arch/s390/hypfs/hypfs_diag_fs.c new file mode 100644 index 000000000000..00a6d370a280 --- /dev/null +++ b/arch/s390/hypfs/hypfs_diag_fs.c @@ -0,0 +1,393 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Hypervisor filesystem for Linux on s390. Diag 204 and 224 + * implementation. + * + * Copyright IBM Corp. 2006, 2008 + * Author(s): Michael Holzheu <holzheu@de.ibm.com> + */ + +#define KMSG_COMPONENT "hypfs" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include <linux/types.h> +#include <linux/errno.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/vmalloc.h> +#include <linux/mm.h> +#include <asm/diag.h> +#include <asm/ebcdic.h> +#include "hypfs_diag.h" +#include "hypfs.h" + +#define TMP_SIZE 64 /* size of temporary buffers */ + +static char *diag224_cpu_names; /* diag 224 name table */ +static int diag224_idx2name(int index, char *name); + +/* + * DIAG 204 member access functions. + * + * Since we have two different diag 204 data formats for old and new s390 + * machines, we do not access the structs directly, but use getter functions for + * each struct member instead. This should make the code more readable. + */ + +/* Time information block */ + +static inline int info_blk_hdr__size(enum diag204_format type) +{ + if (type == DIAG204_INFO_SIMPLE) + return sizeof(struct diag204_info_blk_hdr); + else /* DIAG204_INFO_EXT */ + return sizeof(struct diag204_x_info_blk_hdr); +} + +static inline __u8 info_blk_hdr__npar(enum diag204_format type, void *hdr) +{ + if (type == DIAG204_INFO_SIMPLE) + return ((struct diag204_info_blk_hdr *)hdr)->npar; + else /* DIAG204_INFO_EXT */ + return ((struct diag204_x_info_blk_hdr *)hdr)->npar; +} + +static inline __u8 info_blk_hdr__flags(enum diag204_format type, void *hdr) +{ + if (type == DIAG204_INFO_SIMPLE) + return ((struct diag204_info_blk_hdr *)hdr)->flags; + else /* DIAG204_INFO_EXT */ + return ((struct diag204_x_info_blk_hdr *)hdr)->flags; +} + +/* Partition header */ + +static inline int part_hdr__size(enum diag204_format type) +{ + if (type == DIAG204_INFO_SIMPLE) + return sizeof(struct diag204_part_hdr); + else /* DIAG204_INFO_EXT */ + return sizeof(struct diag204_x_part_hdr); +} + +static inline __u8 part_hdr__rcpus(enum diag204_format type, void *hdr) +{ + if (type == DIAG204_INFO_SIMPLE) + return ((struct diag204_part_hdr *)hdr)->cpus; + else /* DIAG204_INFO_EXT */ + return ((struct diag204_x_part_hdr *)hdr)->rcpus; +} + +static inline void part_hdr__part_name(enum diag204_format type, void *hdr, + char *name) +{ + if (type == DIAG204_INFO_SIMPLE) + memcpy(name, ((struct diag204_part_hdr *)hdr)->part_name, + DIAG204_LPAR_NAME_LEN); + else /* DIAG204_INFO_EXT */ + memcpy(name, ((struct diag204_x_part_hdr *)hdr)->part_name, + DIAG204_LPAR_NAME_LEN); + EBCASC(name, DIAG204_LPAR_NAME_LEN); + name[DIAG204_LPAR_NAME_LEN] = 0; + strim(name); +} + +/* CPU info block */ + +static inline int cpu_info__size(enum diag204_format type) +{ + if (type == DIAG204_INFO_SIMPLE) + return sizeof(struct diag204_cpu_info); + else /* DIAG204_INFO_EXT */ + return sizeof(struct diag204_x_cpu_info); +} + +static inline __u8 cpu_info__ctidx(enum diag204_format type, void *hdr) +{ + if (type == DIAG204_INFO_SIMPLE) + return ((struct diag204_cpu_info *)hdr)->ctidx; + else /* DIAG204_INFO_EXT */ + return ((struct diag204_x_cpu_info *)hdr)->ctidx; +} + +static inline __u16 cpu_info__cpu_addr(enum diag204_format type, void *hdr) +{ + if (type == DIAG204_INFO_SIMPLE) + return ((struct diag204_cpu_info *)hdr)->cpu_addr; + else /* DIAG204_INFO_EXT */ + return ((struct diag204_x_cpu_info *)hdr)->cpu_addr; +} + +static inline __u64 cpu_info__acc_time(enum diag204_format type, void *hdr) +{ + if (type == DIAG204_INFO_SIMPLE) + return ((struct diag204_cpu_info *)hdr)->acc_time; + else /* DIAG204_INFO_EXT */ + return ((struct diag204_x_cpu_info *)hdr)->acc_time; +} + +static inline __u64 cpu_info__lp_time(enum diag204_format type, void *hdr) +{ + if (type == DIAG204_INFO_SIMPLE) + return ((struct diag204_cpu_info *)hdr)->lp_time; + else /* DIAG204_INFO_EXT */ + return ((struct diag204_x_cpu_info *)hdr)->lp_time; +} + +static inline __u64 cpu_info__online_time(enum diag204_format type, void *hdr) +{ + if (type == DIAG204_INFO_SIMPLE) + return 0; /* online_time not available in simple info */ + else /* DIAG204_INFO_EXT */ + return ((struct diag204_x_cpu_info *)hdr)->online_time; +} + +/* Physical header */ + +static inline int phys_hdr__size(enum diag204_format type) +{ + if (type == DIAG204_INFO_SIMPLE) + return sizeof(struct diag204_phys_hdr); + else /* DIAG204_INFO_EXT */ + return sizeof(struct diag204_x_phys_hdr); +} + +static inline __u8 phys_hdr__cpus(enum diag204_format type, void *hdr) +{ + if (type == DIAG204_INFO_SIMPLE) + return ((struct diag204_phys_hdr *)hdr)->cpus; + else /* DIAG204_INFO_EXT */ + return ((struct diag204_x_phys_hdr *)hdr)->cpus; +} + +/* Physical CPU info block */ + +static inline int phys_cpu__size(enum diag204_format type) +{ + if (type == DIAG204_INFO_SIMPLE) + return sizeof(struct diag204_phys_cpu); + else /* DIAG204_INFO_EXT */ + return sizeof(struct diag204_x_phys_cpu); +} + +static inline __u16 phys_cpu__cpu_addr(enum diag204_format type, void *hdr) +{ + if (type == DIAG204_INFO_SIMPLE) + return ((struct diag204_phys_cpu *)hdr)->cpu_addr; + else /* DIAG204_INFO_EXT */ + return ((struct diag204_x_phys_cpu *)hdr)->cpu_addr; +} + +static inline __u64 phys_cpu__mgm_time(enum diag204_format type, void *hdr) +{ + if (type == DIAG204_INFO_SIMPLE) + return ((struct diag204_phys_cpu *)hdr)->mgm_time; + else /* DIAG204_INFO_EXT */ + return ((struct diag204_x_phys_cpu *)hdr)->mgm_time; +} + +static inline __u64 phys_cpu__ctidx(enum diag204_format type, void *hdr) +{ + if (type == DIAG204_INFO_SIMPLE) + return ((struct diag204_phys_cpu *)hdr)->ctidx; + else /* DIAG204_INFO_EXT */ + return ((struct diag204_x_phys_cpu *)hdr)->ctidx; +} + +/* + * Functions to create the directory structure + * ******************************************* + */ + +static int hypfs_create_cpu_files(struct dentry *cpus_dir, void *cpu_info) +{ + struct dentry *cpu_dir; + char buffer[TMP_SIZE]; + void *rc; + + snprintf(buffer, TMP_SIZE, "%d", cpu_info__cpu_addr(diag204_get_info_type(), + cpu_info)); + cpu_dir = hypfs_mkdir(cpus_dir, buffer); + rc = hypfs_create_u64(cpu_dir, "mgmtime", + cpu_info__acc_time(diag204_get_info_type(), cpu_info) - + cpu_info__lp_time(diag204_get_info_type(), cpu_info)); + if (IS_ERR(rc)) + return PTR_ERR(rc); + rc = hypfs_create_u64(cpu_dir, "cputime", + cpu_info__lp_time(diag204_get_info_type(), cpu_info)); + if (IS_ERR(rc)) + return PTR_ERR(rc); + if (diag204_get_info_type() == DIAG204_INFO_EXT) { + rc = hypfs_create_u64(cpu_dir, "onlinetime", + cpu_info__online_time(diag204_get_info_type(), + cpu_info)); + if (IS_ERR(rc)) + return PTR_ERR(rc); + } + diag224_idx2name(cpu_info__ctidx(diag204_get_info_type(), cpu_info), buffer); + rc = hypfs_create_str(cpu_dir, "type", buffer); + return PTR_ERR_OR_ZERO(rc); +} + +static void *hypfs_create_lpar_files(struct dentry *systems_dir, void *part_hdr) +{ + struct dentry *cpus_dir; + struct dentry *lpar_dir; + char lpar_name[DIAG204_LPAR_NAME_LEN + 1]; + void *cpu_info; + int i; + + part_hdr__part_name(diag204_get_info_type(), part_hdr, lpar_name); + lpar_name[DIAG204_LPAR_NAME_LEN] = 0; + lpar_dir = hypfs_mkdir(systems_dir, lpar_name); + if (IS_ERR(lpar_dir)) + return lpar_dir; + cpus_dir = hypfs_mkdir(lpar_dir, "cpus"); + if (IS_ERR(cpus_dir)) + return cpus_dir; + cpu_info = part_hdr + part_hdr__size(diag204_get_info_type()); + for (i = 0; i < part_hdr__rcpus(diag204_get_info_type(), part_hdr); i++) { + int rc; + + rc = hypfs_create_cpu_files(cpus_dir, cpu_info); + if (rc) + return ERR_PTR(rc); + cpu_info += cpu_info__size(diag204_get_info_type()); + } + return cpu_info; +} + +static int hypfs_create_phys_cpu_files(struct dentry *cpus_dir, void *cpu_info) +{ + struct dentry *cpu_dir; + char buffer[TMP_SIZE]; + void *rc; + + snprintf(buffer, TMP_SIZE, "%i", phys_cpu__cpu_addr(diag204_get_info_type(), + cpu_info)); + cpu_dir = hypfs_mkdir(cpus_dir, buffer); + if (IS_ERR(cpu_dir)) + return PTR_ERR(cpu_dir); + rc = hypfs_create_u64(cpu_dir, "mgmtime", + phys_cpu__mgm_time(diag204_get_info_type(), cpu_info)); + if (IS_ERR(rc)) + return PTR_ERR(rc); + diag224_idx2name(phys_cpu__ctidx(diag204_get_info_type(), cpu_info), buffer); + rc = hypfs_create_str(cpu_dir, "type", buffer); + return PTR_ERR_OR_ZERO(rc); +} + +static void *hypfs_create_phys_files(struct dentry *parent_dir, void *phys_hdr) +{ + int i; + void *cpu_info; + struct dentry *cpus_dir; + + cpus_dir = hypfs_mkdir(parent_dir, "cpus"); + if (IS_ERR(cpus_dir)) + return cpus_dir; + cpu_info = phys_hdr + phys_hdr__size(diag204_get_info_type()); + for (i = 0; i < phys_hdr__cpus(diag204_get_info_type(), phys_hdr); i++) { + int rc; + + rc = hypfs_create_phys_cpu_files(cpus_dir, cpu_info); + if (rc) + return ERR_PTR(rc); + cpu_info += phys_cpu__size(diag204_get_info_type()); + } + return cpu_info; +} + +int hypfs_diag_create_files(struct dentry *root) +{ + struct dentry *systems_dir, *hyp_dir; + void *time_hdr, *part_hdr; + void *buffer, *ptr; + int i, rc, pages; + + buffer = diag204_get_buffer(diag204_get_info_type(), &pages); + if (IS_ERR(buffer)) + return PTR_ERR(buffer); + rc = diag204_store(buffer, pages); + if (rc) + return rc; + + systems_dir = hypfs_mkdir(root, "systems"); + if (IS_ERR(systems_dir)) { + rc = PTR_ERR(systems_dir); + goto err_out; + } + time_hdr = (struct x_info_blk_hdr *)buffer; + part_hdr = time_hdr + info_blk_hdr__size(diag204_get_info_type()); + for (i = 0; i < info_blk_hdr__npar(diag204_get_info_type(), time_hdr); i++) { + part_hdr = hypfs_create_lpar_files(systems_dir, part_hdr); + if (IS_ERR(part_hdr)) { + rc = PTR_ERR(part_hdr); + goto err_out; + } + } + if (info_blk_hdr__flags(diag204_get_info_type(), time_hdr) & + DIAG204_LPAR_PHYS_FLG) { + ptr = hypfs_create_phys_files(root, part_hdr); + if (IS_ERR(ptr)) { + rc = PTR_ERR(ptr); + goto err_out; + } + } + hyp_dir = hypfs_mkdir(root, "hyp"); + if (IS_ERR(hyp_dir)) { + rc = PTR_ERR(hyp_dir); + goto err_out; + } + ptr = hypfs_create_str(hyp_dir, "type", "LPAR Hypervisor"); + if (IS_ERR(ptr)) { + rc = PTR_ERR(ptr); + goto err_out; + } + rc = 0; + +err_out: + return rc; +} + +/* Diagnose 224 functions */ + +static int diag224_idx2name(int index, char *name) +{ + memcpy(name, diag224_cpu_names + ((index + 1) * DIAG204_CPU_NAME_LEN), + DIAG204_CPU_NAME_LEN); + name[DIAG204_CPU_NAME_LEN] = 0; + strim(name); + return 0; +} + +static int diag224_get_name_table(void) +{ + /* memory must be below 2GB */ + diag224_cpu_names = (char *)__get_free_page(GFP_KERNEL | GFP_DMA); + if (!diag224_cpu_names) + return -ENOMEM; + if (diag224(diag224_cpu_names)) { + free_page((unsigned long)diag224_cpu_names); + return -EOPNOTSUPP; + } + EBCASC(diag224_cpu_names + 16, (*diag224_cpu_names + 1) * 16); + return 0; +} + +static void diag224_delete_name_table(void) +{ + free_page((unsigned long)diag224_cpu_names); +} + +int __init __hypfs_diag_fs_init(void) +{ + if (MACHINE_IS_LPAR) + return diag224_get_name_table(); + return 0; +} + +void __hypfs_diag_fs_exit(void) +{ + diag224_delete_name_table(); +} diff --git a/arch/s390/hypfs/hypfs_vm.c b/arch/s390/hypfs/hypfs_vm.c index a3d881ca0a98..3db40ad853e0 100644 --- a/arch/s390/hypfs/hypfs_vm.c +++ b/arch/s390/hypfs/hypfs_vm.c @@ -14,47 +14,15 @@ #include <asm/diag.h> #include <asm/ebcdic.h> #include <asm/timex.h> +#include "hypfs_vm.h" #include "hypfs.h" -#define NAME_LEN 8 #define DBFS_D2FC_HDR_VERSION 0 static char local_guest[] = " "; static char all_guests[] = "* "; static char *all_groups = all_guests; -static char *guest_query; - -struct diag2fc_data { - __u32 version; - __u32 flags; - __u64 used_cpu; - __u64 el_time; - __u64 mem_min_kb; - __u64 mem_max_kb; - __u64 mem_share_kb; - __u64 mem_used_kb; - __u32 pcpus; - __u32 lcpus; - __u32 vcpus; - __u32 ocpus; - __u32 cpu_max; - __u32 cpu_shares; - __u32 cpu_use_samp; - __u32 cpu_delay_samp; - __u32 page_wait_samp; - __u32 idle_samp; - __u32 other_samp; - __u32 total_samp; - char guest_name[NAME_LEN]; -}; - -struct diag2fc_parm_list { - char userid[NAME_LEN]; - char aci_grp[NAME_LEN]; - __u64 addr; - __u32 size; - __u32 fmt; -}; +char *diag2fc_guest_query; static int diag2fc(int size, char* query, void *addr) { @@ -62,10 +30,10 @@ static int diag2fc(int size, char* query, void *addr) unsigned long rc; struct diag2fc_parm_list parm_list; - memcpy(parm_list.userid, query, NAME_LEN); - ASCEBC(parm_list.userid, NAME_LEN); - memcpy(parm_list.aci_grp, all_groups, NAME_LEN); - ASCEBC(parm_list.aci_grp, NAME_LEN); + memcpy(parm_list.userid, query, DIAG2FC_NAME_LEN); + ASCEBC(parm_list.userid, DIAG2FC_NAME_LEN); + memcpy(parm_list.aci_grp, all_groups, DIAG2FC_NAME_LEN); + ASCEBC(parm_list.aci_grp, DIAG2FC_NAME_LEN); parm_list.addr = (unsigned long)addr; parm_list.size = size; parm_list.fmt = 0x02; @@ -87,7 +55,7 @@ static int diag2fc(int size, char* query, void *addr) /* * Allocate buffer for "query" and store diag 2fc at "offset" */ -static void *diag2fc_store(char *query, unsigned int *count, int offset) +void *diag2fc_store(char *query, unsigned int *count, int offset) { void *data; int size; @@ -108,132 +76,11 @@ static void *diag2fc_store(char *query, unsigned int *count, int offset) return data; } -static void diag2fc_free(const void *data) +void diag2fc_free(const void *data) { vfree(data); } -#define ATTRIBUTE(dir, name, member) \ -do { \ - void *rc; \ - rc = hypfs_create_u64(dir, name, member); \ - if (IS_ERR(rc)) \ - return PTR_ERR(rc); \ -} while(0) - -static int hypfs_vm_create_guest(struct dentry *systems_dir, - struct diag2fc_data *data) -{ - char guest_name[NAME_LEN + 1] = {}; - struct dentry *guest_dir, *cpus_dir, *samples_dir, *mem_dir; - int dedicated_flag, capped_value; - - capped_value = (data->flags & 0x00000006) >> 1; - dedicated_flag = (data->flags & 0x00000008) >> 3; - - /* guest dir */ - memcpy(guest_name, data->guest_name, NAME_LEN); - EBCASC(guest_name, NAME_LEN); - strim(guest_name); - guest_dir = hypfs_mkdir(systems_dir, guest_name); - if (IS_ERR(guest_dir)) - return PTR_ERR(guest_dir); - ATTRIBUTE(guest_dir, "onlinetime_us", data->el_time); - - /* logical cpu information */ - cpus_dir = hypfs_mkdir(guest_dir, "cpus"); - if (IS_ERR(cpus_dir)) - return PTR_ERR(cpus_dir); - ATTRIBUTE(cpus_dir, "cputime_us", data->used_cpu); - ATTRIBUTE(cpus_dir, "capped", capped_value); - ATTRIBUTE(cpus_dir, "dedicated", dedicated_flag); - ATTRIBUTE(cpus_dir, "count", data->vcpus); - /* - * Note: The "weight_min" attribute got the wrong name. - * The value represents the number of non-stopped (operating) - * CPUS. - */ - ATTRIBUTE(cpus_dir, "weight_min", data->ocpus); - ATTRIBUTE(cpus_dir, "weight_max", data->cpu_max); - ATTRIBUTE(cpus_dir, "weight_cur", data->cpu_shares); - - /* memory information */ - mem_dir = hypfs_mkdir(guest_dir, "mem"); - if (IS_ERR(mem_dir)) - return PTR_ERR(mem_dir); - ATTRIBUTE(mem_dir, "min_KiB", data->mem_min_kb); - ATTRIBUTE(mem_dir, "max_KiB", data->mem_max_kb); - ATTRIBUTE(mem_dir, "used_KiB", data->mem_used_kb); - ATTRIBUTE(mem_dir, "share_KiB", data->mem_share_kb); - - /* samples */ - samples_dir = hypfs_mkdir(guest_dir, "samples"); - if (IS_ERR(samples_dir)) - return PTR_ERR(samples_dir); - ATTRIBUTE(samples_dir, "cpu_using", data->cpu_use_samp); - ATTRIBUTE(samples_dir, "cpu_delay", data->cpu_delay_samp); - ATTRIBUTE(samples_dir, "mem_delay", data->page_wait_samp); - ATTRIBUTE(samples_dir, "idle", data->idle_samp); - ATTRIBUTE(samples_dir, "other", data->other_samp); - ATTRIBUTE(samples_dir, "total", data->total_samp); - return 0; -} - -int hypfs_vm_create_files(struct dentry *root) -{ - struct dentry *dir, *file; - struct diag2fc_data *data; - unsigned int count = 0; - int rc, i; - - data = diag2fc_store(guest_query, &count, 0); - if (IS_ERR(data)) - return PTR_ERR(data); - - /* Hypervisor Info */ - dir = hypfs_mkdir(root, "hyp"); - if (IS_ERR(dir)) { - rc = PTR_ERR(dir); - goto failed; - } - file = hypfs_create_str(dir, "type", "z/VM Hypervisor"); - if (IS_ERR(file)) { - rc = PTR_ERR(file); - goto failed; - } - - /* physical cpus */ - dir = hypfs_mkdir(root, "cpus"); - if (IS_ERR(dir)) { - rc = PTR_ERR(dir); - goto failed; - } - file = hypfs_create_u64(dir, "count", data->lcpus); - if (IS_ERR(file)) { - rc = PTR_ERR(file); - goto failed; - } - - /* guests */ - dir = hypfs_mkdir(root, "systems"); - if (IS_ERR(dir)) { - rc = PTR_ERR(dir); - goto failed; - } - - for (i = 0; i < count; i++) { - rc = hypfs_vm_create_guest(dir, &(data[i])); - if (rc) - goto failed; - } - diag2fc_free(data); - return 0; - -failed: - diag2fc_free(data); - return rc; -} - struct dbfs_d2fc_hdr { u64 len; /* Length of d2fc buffer without header */ u16 version; /* Version of header */ @@ -252,7 +99,7 @@ static int dbfs_diag2fc_create(void **data, void **data_free_ptr, size_t *size) struct dbfs_d2fc *d2fc; unsigned int count; - d2fc = diag2fc_store(guest_query, &count, sizeof(d2fc->hdr)); + d2fc = diag2fc_store(diag2fc_guest_query, &count, sizeof(d2fc->hdr)); if (IS_ERR(d2fc)) return PTR_ERR(d2fc); store_tod_clock_ext(&d2fc->hdr.tod_ext); @@ -277,9 +124,9 @@ int hypfs_vm_init(void) if (!MACHINE_IS_VM) return 0; if (diag2fc(0, all_guests, NULL) > 0) - guest_query = all_guests; + diag2fc_guest_query = all_guests; else if (diag2fc(0, local_guest, NULL) > 0) - guest_query = local_guest; + diag2fc_guest_query = local_guest; else return -EACCES; hypfs_dbfs_create_file(&dbfs_file_2fc); diff --git a/arch/s390/hypfs/hypfs_vm.h b/arch/s390/hypfs/hypfs_vm.h new file mode 100644 index 000000000000..fe2e5851addd --- /dev/null +++ b/arch/s390/hypfs/hypfs_vm.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Hypervisor filesystem for Linux on s390. z/VM implementation. + * + * Copyright IBM Corp. 2006 + * Author(s): Michael Holzheu <holzheu@de.ibm.com> + */ + +#ifndef _S390_HYPFS_VM_H_ +#define _S390_HYPFS_VM_H_ + +#define DIAG2FC_NAME_LEN 8 + +struct diag2fc_data { + __u32 version; + __u32 flags; + __u64 used_cpu; + __u64 el_time; + __u64 mem_min_kb; + __u64 mem_max_kb; + __u64 mem_share_kb; + __u64 mem_used_kb; + __u32 pcpus; + __u32 lcpus; + __u32 vcpus; + __u32 ocpus; + __u32 cpu_max; + __u32 cpu_shares; + __u32 cpu_use_samp; + __u32 cpu_delay_samp; + __u32 page_wait_samp; + __u32 idle_samp; + __u32 other_samp; + __u32 total_samp; + char guest_name[DIAG2FC_NAME_LEN]; +}; + +struct diag2fc_parm_list { + char userid[DIAG2FC_NAME_LEN]; + char aci_grp[DIAG2FC_NAME_LEN]; + __u64 addr; + __u32 size; + __u32 fmt; +}; + +void *diag2fc_store(char *query, unsigned int *count, int offset); +void diag2fc_free(const void *data); +extern char *diag2fc_guest_query; + +#endif /* _S390_HYPFS_VM_H_ */ diff --git a/arch/s390/hypfs/hypfs_vm_fs.c b/arch/s390/hypfs/hypfs_vm_fs.c new file mode 100644 index 000000000000..6011289afa8c --- /dev/null +++ b/arch/s390/hypfs/hypfs_vm_fs.c @@ -0,0 +1,139 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Hypervisor filesystem for Linux on s390. z/VM implementation. + * + * Copyright IBM Corp. 2006 + * Author(s): Michael Holzheu <holzheu@de.ibm.com> + */ + +#include <linux/types.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/vmalloc.h> +#include <asm/extable.h> +#include <asm/diag.h> +#include <asm/ebcdic.h> +#include <asm/timex.h> +#include "hypfs_vm.h" +#include "hypfs.h" + +#define ATTRIBUTE(dir, name, member) \ +do { \ + void *rc; \ + rc = hypfs_create_u64(dir, name, member); \ + if (IS_ERR(rc)) \ + return PTR_ERR(rc); \ +} while (0) + +static int hypfs_vm_create_guest(struct dentry *systems_dir, + struct diag2fc_data *data) +{ + char guest_name[DIAG2FC_NAME_LEN + 1] = {}; + struct dentry *guest_dir, *cpus_dir, *samples_dir, *mem_dir; + int dedicated_flag, capped_value; + + capped_value = (data->flags & 0x00000006) >> 1; + dedicated_flag = (data->flags & 0x00000008) >> 3; + + /* guest dir */ + memcpy(guest_name, data->guest_name, DIAG2FC_NAME_LEN); + EBCASC(guest_name, DIAG2FC_NAME_LEN); + strim(guest_name); + guest_dir = hypfs_mkdir(systems_dir, guest_name); + if (IS_ERR(guest_dir)) + return PTR_ERR(guest_dir); + ATTRIBUTE(guest_dir, "onlinetime_us", data->el_time); + + /* logical cpu information */ + cpus_dir = hypfs_mkdir(guest_dir, "cpus"); + if (IS_ERR(cpus_dir)) + return PTR_ERR(cpus_dir); + ATTRIBUTE(cpus_dir, "cputime_us", data->used_cpu); + ATTRIBUTE(cpus_dir, "capped", capped_value); + ATTRIBUTE(cpus_dir, "dedicated", dedicated_flag); + ATTRIBUTE(cpus_dir, "count", data->vcpus); + /* + * Note: The "weight_min" attribute got the wrong name. + * The value represents the number of non-stopped (operating) + * CPUS. + */ + ATTRIBUTE(cpus_dir, "weight_min", data->ocpus); + ATTRIBUTE(cpus_dir, "weight_max", data->cpu_max); + ATTRIBUTE(cpus_dir, "weight_cur", data->cpu_shares); + + /* memory information */ + mem_dir = hypfs_mkdir(guest_dir, "mem"); + if (IS_ERR(mem_dir)) + return PTR_ERR(mem_dir); + ATTRIBUTE(mem_dir, "min_KiB", data->mem_min_kb); + ATTRIBUTE(mem_dir, "max_KiB", data->mem_max_kb); + ATTRIBUTE(mem_dir, "used_KiB", data->mem_used_kb); + ATTRIBUTE(mem_dir, "share_KiB", data->mem_share_kb); + + /* samples */ + samples_dir = hypfs_mkdir(guest_dir, "samples"); + if (IS_ERR(samples_dir)) + return PTR_ERR(samples_dir); + ATTRIBUTE(samples_dir, "cpu_using", data->cpu_use_samp); + ATTRIBUTE(samples_dir, "cpu_delay", data->cpu_delay_samp); + ATTRIBUTE(samples_dir, "mem_delay", data->page_wait_samp); + ATTRIBUTE(samples_dir, "idle", data->idle_samp); + ATTRIBUTE(samples_dir, "other", data->other_samp); + ATTRIBUTE(samples_dir, "total", data->total_samp); + return 0; +} + +int hypfs_vm_create_files(struct dentry *root) +{ + struct dentry *dir, *file; + struct diag2fc_data *data; + unsigned int count = 0; + int rc, i; + + data = diag2fc_store(diag2fc_guest_query, &count, 0); + if (IS_ERR(data)) + return PTR_ERR(data); + + /* Hypervisor Info */ + dir = hypfs_mkdir(root, "hyp"); + if (IS_ERR(dir)) { + rc = PTR_ERR(dir); + goto failed; + } + file = hypfs_create_str(dir, "type", "z/VM Hypervisor"); + if (IS_ERR(file)) { + rc = PTR_ERR(file); + goto failed; + } + + /* physical cpus */ + dir = hypfs_mkdir(root, "cpus"); + if (IS_ERR(dir)) { + rc = PTR_ERR(dir); + goto failed; + } + file = hypfs_create_u64(dir, "count", data->lcpus); + if (IS_ERR(file)) { + rc = PTR_ERR(file); + goto failed; + } + + /* guests */ + dir = hypfs_mkdir(root, "systems"); + if (IS_ERR(dir)) { + rc = PTR_ERR(dir); + goto failed; + } + + for (i = 0; i < count; i++) { + rc = hypfs_vm_create_guest(dir, &data[i]); + if (rc) + goto failed; + } + diag2fc_free(data); + return 0; + +failed: + diag2fc_free(data); + return rc; +} diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index ee919bfc8186..ada83149932f 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -53,7 +53,7 @@ static void hypfs_update_update(struct super_block *sb) struct inode *inode = d_inode(sb_info->update_file); sb_info->last_update = ktime_get_seconds(); - inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); + inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); } /* directory tree removal functions */ @@ -101,7 +101,7 @@ static struct inode *hypfs_make_inode(struct super_block *sb, umode_t mode) ret->i_mode = mode; ret->i_uid = hypfs_info->uid; ret->i_gid = hypfs_info->gid; - ret->i_atime = ret->i_mtime = ret->i_ctime = current_time(ret); + ret->i_atime = ret->i_mtime = inode_set_ctime_current(ret); if (S_ISDIR(mode)) set_nlink(ret, 2); } @@ -460,45 +460,18 @@ static const struct super_operations hypfs_s_ops = { .show_options = hypfs_show_options, }; -static int __init hypfs_init(void) +int __init __hypfs_fs_init(void) { int rc; - hypfs_dbfs_init(); - - if (hypfs_diag_init()) { - rc = -ENODATA; - goto fail_dbfs_exit; - } - if (hypfs_vm_init()) { - rc = -ENODATA; - goto fail_hypfs_diag_exit; - } - hypfs_sprp_init(); - if (hypfs_diag0c_init()) { - rc = -ENODATA; - goto fail_hypfs_sprp_exit; - } rc = sysfs_create_mount_point(hypervisor_kobj, "s390"); if (rc) - goto fail_hypfs_diag0c_exit; + return rc; rc = register_filesystem(&hypfs_type); if (rc) - goto fail_filesystem; + goto fail; return 0; - -fail_filesystem: +fail: sysfs_remove_mount_point(hypervisor_kobj, "s390"); -fail_hypfs_diag0c_exit: - hypfs_diag0c_exit(); -fail_hypfs_sprp_exit: - hypfs_sprp_exit(); - hypfs_vm_exit(); -fail_hypfs_diag_exit: - hypfs_diag_exit(); - pr_err("Initialization of hypfs failed with rc=%i\n", rc); -fail_dbfs_exit: - hypfs_dbfs_exit(); return rc; } -device_initcall(hypfs_init) diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild index 1a18d7b82f86..4b904110d27c 100644 --- a/arch/s390/include/asm/Kbuild +++ b/arch/s390/include/asm/Kbuild @@ -5,6 +5,5 @@ generated-y += syscall_table.h generated-y += unistd_nr.h generic-y += asm-offsets.h -generic-y += export.h generic-y += kvm_types.h generic-y += mcs_spinlock.h diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h index ac665b9670c5..ccd4e148b5ed 100644 --- a/arch/s390/include/asm/debug.h +++ b/arch/s390/include/asm/debug.h @@ -222,7 +222,7 @@ static inline debug_entry_t *debug_text_event(debug_info_t *id, int level, /* * IMPORTANT: Use "%s" in sprintf format strings with care! Only pointers are - * stored in the s390dbf. See Documentation/s390/s390dbf.rst for more details! + * stored in the s390dbf. See Documentation/arch/s390/s390dbf.rst for more details! */ extern debug_entry_t * __debug_sprintf_event(debug_info_t *id, int level, char *string, ...) @@ -350,7 +350,7 @@ static inline debug_entry_t *debug_text_exception(debug_info_t *id, int level, /* * IMPORTANT: Use "%s" in sprintf format strings with care! Only pointers are - * stored in the s390dbf. See Documentation/s390/s390dbf.rst for more details! + * stored in the s390dbf. See Documentation/arch/s390/s390dbf.rst for more details! */ extern debug_entry_t * __debug_sprintf_exception(debug_info_t *id, int level, char *string, ...) diff --git a/arch/s390/include/asm/diag.h b/arch/s390/include/asm/diag.h index 902e0330dd91..bed804137537 100644 --- a/arch/s390/include/asm/diag.h +++ b/arch/s390/include/asm/diag.h @@ -36,6 +36,7 @@ enum diag_stat_enum { DIAG_STAT_X304, DIAG_STAT_X308, DIAG_STAT_X318, + DIAG_STAT_X320, DIAG_STAT_X500, NR_DIAG_STAT }; @@ -108,6 +109,8 @@ enum diag204_sc { DIAG204_SUBC_STIB7 = 7 }; +#define DIAG204_SUBCODE_MASK 0xffff + /* The two available diag 204 data formats */ enum diag204_format { DIAG204_INFO_SIMPLE = 0, diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h index e5c5cb1207e2..5a82b08f03cd 100644 --- a/arch/s390/include/asm/ftrace.h +++ b/arch/s390/include/asm/ftrace.h @@ -54,6 +54,23 @@ static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs * return NULL; } +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +struct fgraph_ret_regs { + unsigned long gpr2; + unsigned long fp; +}; + +static __always_inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs) +{ + return ret_regs->gpr2; +} + +static __always_inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs) +{ + return ret_regs->fp; +} +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + static __always_inline unsigned long ftrace_regs_get_instruction_pointer(const struct ftrace_regs *fregs) { diff --git a/arch/s390/include/asm/kfence.h b/arch/s390/include/asm/kfence.h index d55ba878378b..e47fd8cbe701 100644 --- a/arch/s390/include/asm/kfence.h +++ b/arch/s390/include/asm/kfence.h @@ -35,7 +35,7 @@ static __always_inline void kfence_split_mapping(void) static inline bool kfence_protect_page(unsigned long addr, bool protect) { - __kernel_map_pages(virt_to_page(addr), 1, !protect); + __kernel_map_pages(virt_to_page((void *)addr), 1, !protect); return true; } diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 2bbc3d54959d..91bfecb91321 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -1028,6 +1028,9 @@ static inline int sie64a(struct kvm_s390_sie_block *sie_block, u64 *rsa) extern char sie_exit; +bool kvm_s390_pv_is_protected(struct kvm *kvm); +bool kvm_s390_pv_cpu_is_protected(struct kvm_vcpu *vcpu); + extern int kvm_s390_gisc_register(struct kvm *kvm, u32 gisc); extern int kvm_s390_gisc_unregister(struct kvm *kvm, u32 gisc); diff --git a/arch/s390/include/asm/maccess.h b/arch/s390/include/asm/maccess.h index cfec3141fdba..50225940d971 100644 --- a/arch/s390/include/asm/maccess.h +++ b/arch/s390/include/asm/maccess.h @@ -4,6 +4,9 @@ #include <linux/types.h> +#define MEMCPY_REAL_SIZE PAGE_SIZE +#define MEMCPY_REAL_MASK PAGE_MASK + struct iov_iter; extern unsigned long __memcpy_real_area; diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index a9c138fcd2ad..cfec0743314e 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -191,8 +191,16 @@ int arch_make_page_accessible(struct page *page); #define phys_to_page(phys) pfn_to_page(phys_to_pfn(phys)) #define page_to_phys(page) pfn_to_phys(page_to_pfn(page)) -#define pfn_to_virt(pfn) __va(pfn_to_phys(pfn)) -#define virt_to_pfn(kaddr) (phys_to_pfn(__pa(kaddr))) +static inline void *pfn_to_virt(unsigned long pfn) +{ + return __va(pfn_to_phys(pfn)); +} + +static inline unsigned long virt_to_pfn(const void *kaddr) +{ + return phys_to_pfn(__pa(kaddr)); +} + #define pfn_to_kaddr(pfn) pfn_to_virt(pfn) #define virt_to_page(kaddr) pfn_to_page(virt_to_pfn(kaddr)) diff --git a/arch/s390/include/asm/pfault.h b/arch/s390/include/asm/pfault.h new file mode 100644 index 000000000000..a1bee4a1e470 --- /dev/null +++ b/arch/s390/include/asm/pfault.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright IBM Corp. 1999, 2023 + */ +#ifndef _ASM_S390_PFAULT_H +#define _ASM_S390_PFAULT_H + +#include <linux/errno.h> + +int __pfault_init(void); +void __pfault_fini(void); + +static inline int pfault_init(void) +{ + if (IS_ENABLED(CONFIG_PFAULT)) + return __pfault_init(); + return -EOPNOTSUPP; +} + +static inline void pfault_fini(void) +{ + if (IS_ENABLED(CONFIG_PFAULT)) + __pfault_fini(); +} + +#endif /* _ASM_S390_PFAULT_H */ diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index c55f3c3365af..30909fe27c24 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -89,8 +89,6 @@ extern unsigned long __bootdata_preserved(VMALLOC_END); extern struct page *__bootdata_preserved(vmemmap); extern unsigned long __bootdata_preserved(vmemmap_size); -#define VMEM_MAX_PHYS ((unsigned long) vmemmap) - extern unsigned long __bootdata_preserved(MODULES_VADDR); extern unsigned long __bootdata_preserved(MODULES_END); #define MODULES_VADDR MODULES_VADDR diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h index dac7da88f61f..5742d23bba13 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -86,6 +86,7 @@ struct sclp_info { unsigned char has_kss : 1; unsigned char has_gisaf : 1; unsigned char has_diag318 : 1; + unsigned char has_diag320 : 1; unsigned char has_sipl : 1; unsigned char has_sipl_eckd : 1; unsigned char has_dirq : 1; diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index f191255c60db..b30fe91166e3 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -74,6 +74,7 @@ extern unsigned int zlib_dfltcc_support; extern int noexec_disabled; extern unsigned long ident_map_size; +extern unsigned long max_mappable; /* The Write Back bit position in the physaddr is given by the SLPC PCI */ extern unsigned long mio_wb_bit_mask; @@ -117,14 +118,6 @@ extern unsigned int console_irq; #define SET_CONSOLE_VT220 do { console_mode = 4; } while (0) #define SET_CONSOLE_HVC do { console_mode = 5; } while (0) -#ifdef CONFIG_PFAULT -extern int pfault_init(void); -extern void pfault_fini(void); -#else /* CONFIG_PFAULT */ -#define pfault_init() ({-1;}) -#define pfault_fini() do { } while (0) -#endif /* CONFIG_PFAULT */ - #ifdef CONFIG_VMCP void vmcp_cma_reserve(void); #else diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h index d6bb2f4f78d1..d2cd42bb2c26 100644 --- a/arch/s390/include/asm/uv.h +++ b/arch/s390/include/asm/uv.h @@ -463,6 +463,7 @@ static inline int is_prot_virt_host(void) return prot_virt_host; } +int uv_pin_shared(unsigned long paddr); int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb); int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr); int uv_destroy_owned_page(unsigned long paddr); @@ -475,6 +476,11 @@ void setup_uv(void); #define is_prot_virt_host() 0 static inline void setup_uv(void) {} +static inline int uv_pin_shared(unsigned long paddr) +{ + return 0; +} + static inline int uv_destroy_owned_page(unsigned long paddr) { return 0; diff --git a/arch/s390/include/uapi/asm/pkey.h b/arch/s390/include/uapi/asm/pkey.h index 5faf0a1d2c16..5ad76471e73f 100644 --- a/arch/s390/include/uapi/asm/pkey.h +++ b/arch/s390/include/uapi/asm/pkey.h @@ -26,7 +26,7 @@ #define MAXCLRKEYSIZE 32 /* a clear key value may be up to 32 bytes */ #define MAXAESCIPHERKEYSIZE 136 /* our aes cipher keys have always 136 bytes */ #define MINEP11AESKEYBLOBSIZE 256 /* min EP11 AES key blob size */ -#define MAXEP11AESKEYBLOBSIZE 320 /* max EP11 AES key blob size */ +#define MAXEP11AESKEYBLOBSIZE 336 /* max EP11 AES key blob size */ /* Minimum size of a key blob */ #define MINKEYBLOBSIZE SECKEYBLOBSIZE diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 6b2a051e1f8a..0df2b88cc0da 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -37,9 +37,9 @@ CFLAGS_unwind_bc.o += -fno-optimize-sibling-calls obj-y := head64.o traps.o time.o process.o earlypgm.o early.o setup.o idle.o vtime.o obj-y += processor.o syscall.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o obj-y += debug.o irq.o ipl.o dis.o diag.o vdso.o cpufeature.o -obj-y += sysinfo.o lgr.o os_info.o machine_kexec.o +obj-y += sysinfo.o lgr.o os_info.o obj-y += runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o -obj-y += entry.o reipl.o relocate_kernel.o kdebugfs.o alternative.o +obj-y += entry.o reipl.o kdebugfs.o alternative.o obj-y += nospec-branch.o ipl_vmparm.o machine_kexec_reloc.o unwind_bc.o obj-y += smp.o text_amode31.o stacktrace.o abs_lowcore.o @@ -63,12 +63,13 @@ obj-$(CONFIG_RETHOOK) += rethook.o obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o obj-$(CONFIG_FUNCTION_TRACER) += mcount.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o +obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o obj-$(CONFIG_UPROBES) += uprobes.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o obj-$(CONFIG_KEXEC_FILE) += machine_kexec_file.o kexec_image.o obj-$(CONFIG_KEXEC_FILE) += kexec_elf.o - +obj-$(CONFIG_CERT_STORE) += cert_store.o obj-$(CONFIG_IMA_SECURE_AND_OR_TRUSTED_BOOT) += ima_arch.o obj-$(CONFIG_PERF_EVENTS) += perf_event.o diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 81cf72088041..fa5f6885c74a 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -12,6 +12,7 @@ #include <linux/sched.h> #include <linux/purgatory.h> #include <linux/pgtable.h> +#include <linux/ftrace.h> #include <asm/idle.h> #include <asm/gmap.h> #include <asm/stacktrace.h> @@ -177,5 +178,13 @@ int main(void) DEFINE(OLDMEM_SIZE, PARMAREA + offsetof(struct parmarea, oldmem_size)); DEFINE(COMMAND_LINE, PARMAREA + offsetof(struct parmarea, command_line)); DEFINE(MAX_COMMAND_LINE_SIZE, PARMAREA + offsetof(struct parmarea, max_command_line_size)); +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + /* function graph return value tracing */ + OFFSET(__FGRAPH_RET_GPR2, fgraph_ret_regs, gpr2); + OFFSET(__FGRAPH_RET_FP, fgraph_ret_regs, fp); + DEFINE(__FGRAPH_RET_SIZE, sizeof(struct fgraph_ret_regs)); +#endif + OFFSET(__FTRACE_REGS_PT_REGS, ftrace_regs, regs); + DEFINE(__FTRACE_REGS_SIZE, sizeof(struct ftrace_regs)); return 0; } diff --git a/arch/s390/kernel/cert_store.c b/arch/s390/kernel/cert_store.c new file mode 100644 index 000000000000..3986a044eb36 --- /dev/null +++ b/arch/s390/kernel/cert_store.c @@ -0,0 +1,811 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DIAG 0x320 support and certificate store handling + * + * Copyright IBM Corp. 2023 + * Author(s): Anastasia Eskova <anastasia.eskova@ibm.com> + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/delay.h> +#include <linux/device.h> +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/key-type.h> +#include <linux/key.h> +#include <linux/keyctl.h> +#include <linux/kobject.h> +#include <linux/module.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/sysfs.h> +#include <crypto/sha2.h> +#include <keys/user-type.h> +#include <asm/debug.h> +#include <asm/diag.h> +#include <asm/ebcdic.h> +#include <asm/sclp.h> + +#define DIAG_MAX_RETRIES 10 + +#define VCE_FLAGS_VALID_MASK 0x80 + +#define ISM_LEN_DWORDS 4 +#define VCSSB_LEN_BYTES 128 +#define VCSSB_LEN_NO_CERTS 4 +#define VCB_LEN_NO_CERTS 64 +#define VC_NAME_LEN_BYTES 64 + +#define CERT_STORE_KEY_TYPE_NAME "cert_store_key" +#define CERT_STORE_KEYRING_NAME "cert_store" + +static debug_info_t *cert_store_dbf; +static debug_info_t *cert_store_hexdump; + +#define pr_dbf_msg(fmt, ...) \ + debug_sprintf_event(cert_store_dbf, 3, fmt "\n", ## __VA_ARGS__) + +enum diag320_subcode { + DIAG320_SUBCODES = 0, + DIAG320_STORAGE = 1, + DIAG320_CERT_BLOCK = 2, +}; + +enum diag320_rc { + DIAG320_RC_OK = 0x0001, + DIAG320_RC_CS_NOMATCH = 0x0306, +}; + +/* Verification Certificates Store Support Block (VCSSB). */ +struct vcssb { + u32 vcssb_length; + u8 pad_0x04[3]; + u8 version; + u8 pad_0x08[8]; + u32 cs_token; + u8 pad_0x14[12]; + u16 total_vc_index_count; + u16 max_vc_index_count; + u8 pad_0x24[28]; + u32 max_vce_length; + u32 max_vcxe_length; + u8 pad_0x48[8]; + u32 max_single_vcb_length; + u32 total_vcb_length; + u32 max_single_vcxb_length; + u32 total_vcxb_length; + u8 pad_0x60[32]; +} __packed __aligned(8); + +/* Verification Certificate Entry (VCE) Header. */ +struct vce_header { + u32 vce_length; + u8 flags; + u8 key_type; + u16 vc_index; + u8 vc_name[VC_NAME_LEN_BYTES]; /* EBCDIC */ + u8 vc_format; + u8 pad_0x49; + u16 key_id_length; + u8 pad_0x4c; + u8 vc_hash_type; + u16 vc_hash_length; + u8 pad_0x50[4]; + u32 vc_length; + u8 pad_0x58[8]; + u16 vc_hash_offset; + u16 vc_offset; + u8 pad_0x64[28]; +} __packed __aligned(4); + +/* Verification Certificate Block (VCB) Header. */ +struct vcb_header { + u32 vcb_input_length; + u8 pad_0x04[4]; + u16 first_vc_index; + u16 last_vc_index; + u32 pad_0x0c; + u32 cs_token; + u8 pad_0x14[12]; + u32 vcb_output_length; + u8 pad_0x24[3]; + u8 version; + u16 stored_vc_count; + u16 remaining_vc_count; + u8 pad_0x2c[20]; +} __packed __aligned(4); + +/* Verification Certificate Block (VCB). */ +struct vcb { + struct vcb_header vcb_hdr; + u8 vcb_buf[]; +} __packed __aligned(4); + +/* Verification Certificate Entry (VCE). */ +struct vce { + struct vce_header vce_hdr; + u8 cert_data_buf[]; +} __packed __aligned(4); + +static void cert_store_key_describe(const struct key *key, struct seq_file *m) +{ + char ascii[VC_NAME_LEN_BYTES + 1]; + + /* + * First 64 bytes of the key description is key name in EBCDIC CP 500. + * Convert it to ASCII for displaying in /proc/keys. + */ + strscpy(ascii, key->description, sizeof(ascii)); + EBCASC_500(ascii, VC_NAME_LEN_BYTES); + seq_puts(m, ascii); + + seq_puts(m, &key->description[VC_NAME_LEN_BYTES]); + if (key_is_positive(key)) + seq_printf(m, ": %u", key->datalen); +} + +/* + * Certificate store key type takes over properties of + * user key but cannot be updated. + */ +static struct key_type key_type_cert_store_key = { + .name = CERT_STORE_KEY_TYPE_NAME, + .preparse = user_preparse, + .free_preparse = user_free_preparse, + .instantiate = generic_key_instantiate, + .revoke = user_revoke, + .destroy = user_destroy, + .describe = cert_store_key_describe, + .read = user_read, +}; + +/* Logging functions. */ +static void pr_dbf_vcb(const struct vcb *b) +{ + pr_dbf_msg("VCB Header:"); + pr_dbf_msg("vcb_input_length: %d", b->vcb_hdr.vcb_input_length); + pr_dbf_msg("first_vc_index: %d", b->vcb_hdr.first_vc_index); + pr_dbf_msg("last_vc_index: %d", b->vcb_hdr.last_vc_index); + pr_dbf_msg("cs_token: %d", b->vcb_hdr.cs_token); + pr_dbf_msg("vcb_output_length: %d", b->vcb_hdr.vcb_output_length); + pr_dbf_msg("version: %d", b->vcb_hdr.version); + pr_dbf_msg("stored_vc_count: %d", b->vcb_hdr.stored_vc_count); + pr_dbf_msg("remaining_vc_count: %d", b->vcb_hdr.remaining_vc_count); +} + +static void pr_dbf_vce(const struct vce *e) +{ + unsigned char vc_name[VC_NAME_LEN_BYTES + 1]; + char log_string[VC_NAME_LEN_BYTES + 40]; + + pr_dbf_msg("VCE Header:"); + pr_dbf_msg("vce_hdr.vce_length: %d", e->vce_hdr.vce_length); + pr_dbf_msg("vce_hdr.flags: %d", e->vce_hdr.flags); + pr_dbf_msg("vce_hdr.key_type: %d", e->vce_hdr.key_type); + pr_dbf_msg("vce_hdr.vc_index: %d", e->vce_hdr.vc_index); + pr_dbf_msg("vce_hdr.vc_format: %d", e->vce_hdr.vc_format); + pr_dbf_msg("vce_hdr.key_id_length: %d", e->vce_hdr.key_id_length); + pr_dbf_msg("vce_hdr.vc_hash_type: %d", e->vce_hdr.vc_hash_type); + pr_dbf_msg("vce_hdr.vc_hash_length: %d", e->vce_hdr.vc_hash_length); + pr_dbf_msg("vce_hdr.vc_hash_offset: %d", e->vce_hdr.vc_hash_offset); + pr_dbf_msg("vce_hdr.vc_length: %d", e->vce_hdr.vc_length); + pr_dbf_msg("vce_hdr.vc_offset: %d", e->vce_hdr.vc_offset); + + /* Certificate name in ASCII. */ + memcpy(vc_name, e->vce_hdr.vc_name, VC_NAME_LEN_BYTES); + EBCASC_500(vc_name, VC_NAME_LEN_BYTES); + vc_name[VC_NAME_LEN_BYTES] = '\0'; + + snprintf(log_string, sizeof(log_string), + "index: %d vce_hdr.vc_name (ASCII): %s", + e->vce_hdr.vc_index, vc_name); + debug_text_event(cert_store_hexdump, 3, log_string); + + /* Certificate data. */ + debug_text_event(cert_store_hexdump, 3, "VCE: Certificate data start"); + debug_event(cert_store_hexdump, 3, (u8 *)e->cert_data_buf, 128); + debug_text_event(cert_store_hexdump, 3, "VCE: Certificate data end"); + debug_event(cert_store_hexdump, 3, + (u8 *)e->cert_data_buf + e->vce_hdr.vce_length - 128, 128); +} + +static void pr_dbf_vcssb(const struct vcssb *s) +{ + debug_text_event(cert_store_hexdump, 3, "DIAG320 Subcode1"); + debug_event(cert_store_hexdump, 3, (u8 *)s, VCSSB_LEN_BYTES); + + pr_dbf_msg("VCSSB:"); + pr_dbf_msg("vcssb_length: %u", s->vcssb_length); + pr_dbf_msg("version: %u", s->version); + pr_dbf_msg("cs_token: %u", s->cs_token); + pr_dbf_msg("total_vc_index_count: %u", s->total_vc_index_count); + pr_dbf_msg("max_vc_index_count: %u", s->max_vc_index_count); + pr_dbf_msg("max_vce_length: %u", s->max_vce_length); + pr_dbf_msg("max_vcxe_length: %u", s->max_vce_length); + pr_dbf_msg("max_single_vcb_length: %u", s->max_single_vcb_length); + pr_dbf_msg("total_vcb_length: %u", s->total_vcb_length); + pr_dbf_msg("max_single_vcxb_length: %u", s->max_single_vcxb_length); + pr_dbf_msg("total_vcxb_length: %u", s->total_vcxb_length); +} + +static int __diag320(unsigned long subcode, void *addr) +{ + union register_pair rp = { .even = (unsigned long)addr, }; + + asm volatile( + " diag %[rp],%[subcode],0x320\n" + "0: nopr %%r7\n" + EX_TABLE(0b, 0b) + : [rp] "+d" (rp.pair) + : [subcode] "d" (subcode) + : "cc", "memory"); + + return rp.odd; +} + +static int diag320(unsigned long subcode, void *addr) +{ + diag_stat_inc(DIAG_STAT_X320); + + return __diag320(subcode, addr); +} + +/* + * Calculate SHA256 hash of the VCE certificate and compare it to hash stored in + * VCE. Return -EINVAL if hashes don't match. + */ +static int check_certificate_hash(const struct vce *vce) +{ + u8 hash[SHA256_DIGEST_SIZE]; + u16 vc_hash_length; + u8 *vce_hash; + + vce_hash = (u8 *)vce + vce->vce_hdr.vc_hash_offset; + vc_hash_length = vce->vce_hdr.vc_hash_length; + sha256((u8 *)vce + vce->vce_hdr.vc_offset, vce->vce_hdr.vc_length, hash); + if (memcmp(vce_hash, hash, vc_hash_length) == 0) + return 0; + + pr_dbf_msg("SHA256 hash of received certificate does not match"); + debug_text_event(cert_store_hexdump, 3, "VCE hash:"); + debug_event(cert_store_hexdump, 3, vce_hash, SHA256_DIGEST_SIZE); + debug_text_event(cert_store_hexdump, 3, "Calculated hash:"); + debug_event(cert_store_hexdump, 3, hash, SHA256_DIGEST_SIZE); + + return -EINVAL; +} + +static int check_certificate_valid(const struct vce *vce) +{ + if (!(vce->vce_hdr.flags & VCE_FLAGS_VALID_MASK)) { + pr_dbf_msg("Certificate entry is invalid"); + return -EINVAL; + } + if (vce->vce_hdr.vc_format != 1) { + pr_dbf_msg("Certificate format is not supported"); + return -EINVAL; + } + if (vce->vce_hdr.vc_hash_type != 1) { + pr_dbf_msg("Hash type is not supported"); + return -EINVAL; + } + + return check_certificate_hash(vce); +} + +static struct key *get_user_session_keyring(void) +{ + key_ref_t us_keyring_ref; + + us_keyring_ref = lookup_user_key(KEY_SPEC_USER_SESSION_KEYRING, + KEY_LOOKUP_CREATE, KEY_NEED_LINK); + if (IS_ERR(us_keyring_ref)) { + pr_dbf_msg("Couldn't get user session keyring: %ld", + PTR_ERR(us_keyring_ref)); + return ERR_PTR(-ENOKEY); + } + key_ref_put(us_keyring_ref); + return key_ref_to_ptr(us_keyring_ref); +} + +/* Invalidate all keys from cert_store keyring. */ +static int invalidate_keyring_keys(struct key *keyring) +{ + unsigned long num_keys, key_index; + size_t keyring_payload_len; + key_serial_t *key_array; + struct key *current_key; + int rc; + + keyring_payload_len = key_type_keyring.read(keyring, NULL, 0); + num_keys = keyring_payload_len / sizeof(key_serial_t); + key_array = kcalloc(num_keys, sizeof(key_serial_t), GFP_KERNEL); + if (!key_array) + return -ENOMEM; + + rc = key_type_keyring.read(keyring, (char *)key_array, keyring_payload_len); + if (rc != keyring_payload_len) { + pr_dbf_msg("Couldn't read keyring payload"); + goto out; + } + + for (key_index = 0; key_index < num_keys; key_index++) { + current_key = key_lookup(key_array[key_index]); + pr_dbf_msg("Invalidating key %08x", current_key->serial); + + key_invalidate(current_key); + key_put(current_key); + rc = key_unlink(keyring, current_key); + if (rc) { + pr_dbf_msg("Couldn't unlink key %08x: %d", current_key->serial, rc); + break; + } + } +out: + kfree(key_array); + return rc; +} + +static struct key *find_cs_keyring(void) +{ + key_ref_t cs_keyring_ref; + struct key *cs_keyring; + + cs_keyring_ref = keyring_search(make_key_ref(get_user_session_keyring(), true), + &key_type_keyring, CERT_STORE_KEYRING_NAME, + false); + if (!IS_ERR(cs_keyring_ref)) { + cs_keyring = key_ref_to_ptr(cs_keyring_ref); + key_ref_put(cs_keyring_ref); + goto found; + } + /* Search default locations: thread, process, session keyrings */ + cs_keyring = request_key(&key_type_keyring, CERT_STORE_KEYRING_NAME, NULL); + if (IS_ERR(cs_keyring)) + return NULL; + key_put(cs_keyring); +found: + return cs_keyring; +} + +static void cleanup_cs_keys(void) +{ + struct key *cs_keyring; + + cs_keyring = find_cs_keyring(); + if (!cs_keyring) + return; + + pr_dbf_msg("Found cert_store keyring. Purging..."); + /* + * Remove cert_store_key_type in case invalidation + * of old cert_store keys failed (= severe error). + */ + if (invalidate_keyring_keys(cs_keyring)) + unregister_key_type(&key_type_cert_store_key); + + keyring_clear(cs_keyring); + key_invalidate(cs_keyring); + key_put(cs_keyring); + key_unlink(get_user_session_keyring(), cs_keyring); +} + +static struct key *create_cs_keyring(void) +{ + static struct key *cs_keyring; + + /* Cleanup previous cs_keyring and all associated keys if any. */ + cleanup_cs_keys(); + cs_keyring = keyring_alloc(CERT_STORE_KEYRING_NAME, GLOBAL_ROOT_UID, + GLOBAL_ROOT_GID, current_cred(), + (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW | KEY_USR_READ, + KEY_ALLOC_NOT_IN_QUOTA | KEY_ALLOC_SET_KEEP, + NULL, get_user_session_keyring()); + if (IS_ERR(cs_keyring)) { + pr_dbf_msg("Can't allocate cert_store keyring"); + return NULL; + } + + pr_dbf_msg("Successfully allocated cert_store keyring: %08x", cs_keyring->serial); + + /* + * In case a previous clean-up ran into an + * error and unregistered key type. + */ + register_key_type(&key_type_cert_store_key); + + return cs_keyring; +} + +/* + * Allocate memory and create key description in format + * [key name in EBCDIC]:[VCE index]:[CS token]. + * Return a pointer to key description or NULL if memory + * allocation failed. Memory should be freed by caller. + */ +static char *get_key_description(struct vcssb *vcssb, const struct vce *vce) +{ + size_t len, name_len; + u32 cs_token; + char *desc; + + cs_token = vcssb->cs_token; + /* Description string contains "%64s:%04u:%08u\0". */ + name_len = sizeof(vce->vce_hdr.vc_name); + len = name_len + 1 + 4 + 1 + 8 + 1; + desc = kmalloc(len, GFP_KERNEL); + if (!desc) + return NULL; + + memcpy(desc, vce->vce_hdr.vc_name, name_len); + sprintf(desc + name_len, ":%04u:%08u", vce->vce_hdr.vc_index, cs_token); + + return desc; +} + +/* + * Create a key of type "cert_store_key" using the data from VCE for key + * payload and key description. Link the key to "cert_store" keyring. + */ +static int create_key_from_vce(struct vcssb *vcssb, struct vce *vce, + struct key *keyring) +{ + key_ref_t newkey; + char *desc; + int rc; + + desc = get_key_description(vcssb, vce); + if (!desc) + return -ENOMEM; + + newkey = key_create_or_update( + make_key_ref(keyring, true), CERT_STORE_KEY_TYPE_NAME, + desc, (u8 *)vce + vce->vce_hdr.vc_offset, + vce->vce_hdr.vc_length, + (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW | KEY_USR_READ, + KEY_ALLOC_NOT_IN_QUOTA); + + rc = PTR_ERR_OR_ZERO(newkey); + if (rc) { + pr_dbf_msg("Couldn't create a key from Certificate Entry (%d)", rc); + rc = -ENOKEY; + goto out; + } + + key_ref_put(newkey); +out: + kfree(desc); + return rc; +} + +/* Get Verification Certificate Storage Size block with DIAG320 subcode2. */ +static int get_vcssb(struct vcssb *vcssb) +{ + int diag320_rc; + + memset(vcssb, 0, sizeof(*vcssb)); + vcssb->vcssb_length = VCSSB_LEN_BYTES; + diag320_rc = diag320(DIAG320_STORAGE, vcssb); + pr_dbf_vcssb(vcssb); + + if (diag320_rc != DIAG320_RC_OK) { + pr_dbf_msg("Diag 320 Subcode 1 returned bad RC: %04x", diag320_rc); + return -EIO; + } + if (vcssb->vcssb_length == VCSSB_LEN_NO_CERTS) { + pr_dbf_msg("No certificates available for current configuration"); + return -ENOKEY; + } + + return 0; +} + +static u32 get_4k_mult_vcb_size(struct vcssb *vcssb) +{ + return round_up(vcssb->max_single_vcb_length, PAGE_SIZE); +} + +/* Fill input fields of single-entry VCB that will be read by LPAR. */ +static void fill_vcb_input(struct vcssb *vcssb, struct vcb *vcb, u16 index) +{ + memset(vcb, 0, sizeof(*vcb)); + vcb->vcb_hdr.vcb_input_length = get_4k_mult_vcb_size(vcssb); + vcb->vcb_hdr.cs_token = vcssb->cs_token; + + /* Request single entry. */ + vcb->vcb_hdr.first_vc_index = index; + vcb->vcb_hdr.last_vc_index = index; +} + +static void extract_vce_from_sevcb(struct vcb *vcb, struct vce *vce) +{ + struct vce *extracted_vce; + + extracted_vce = (struct vce *)vcb->vcb_buf; + memcpy(vce, vcb->vcb_buf, extracted_vce->vce_hdr.vce_length); + pr_dbf_vce(vce); +} + +static int get_sevcb(struct vcssb *vcssb, u16 index, struct vcb *vcb) +{ + int rc, diag320_rc; + + fill_vcb_input(vcssb, vcb, index); + + diag320_rc = diag320(DIAG320_CERT_BLOCK, vcb); + pr_dbf_msg("Diag 320 Subcode2 RC %2x", diag320_rc); + pr_dbf_vcb(vcb); + + switch (diag320_rc) { + case DIAG320_RC_OK: + rc = 0; + if (vcb->vcb_hdr.vcb_output_length == VCB_LEN_NO_CERTS) { + pr_dbf_msg("No certificate entry for index %u", index); + rc = -ENOKEY; + } else if (vcb->vcb_hdr.remaining_vc_count != 0) { + /* Retry on insufficient space. */ + pr_dbf_msg("Couldn't get all requested certificates"); + rc = -EAGAIN; + } + break; + case DIAG320_RC_CS_NOMATCH: + pr_dbf_msg("Certificate Store token mismatch"); + rc = -EAGAIN; + break; + default: + pr_dbf_msg("Diag 320 Subcode2 returned bad rc (0x%4x)", diag320_rc); + rc = -EINVAL; + break; + } + + return rc; +} + +/* + * Allocate memory for single-entry VCB, get VCB via DIAG320 subcode 2 call, + * extract VCE and create a key from its' certificate. + */ +static int create_key_from_sevcb(struct vcssb *vcssb, u16 index, + struct key *keyring) +{ + struct vcb *vcb; + struct vce *vce; + int rc; + + rc = -ENOMEM; + vcb = vmalloc(get_4k_mult_vcb_size(vcssb)); + vce = vmalloc(vcssb->max_single_vcb_length - sizeof(vcb->vcb_hdr)); + if (!vcb || !vce) + goto out; + + rc = get_sevcb(vcssb, index, vcb); + if (rc) + goto out; + + extract_vce_from_sevcb(vcb, vce); + rc = check_certificate_valid(vce); + if (rc) + goto out; + + rc = create_key_from_vce(vcssb, vce, keyring); + if (rc) + goto out; + + pr_dbf_msg("Successfully created key from Certificate Entry %d", index); +out: + vfree(vce); + vfree(vcb); + return rc; +} + +/* + * Request a single-entry VCB for each VCE available for the partition. + * Create a key from it and link it to cert_store keyring. If no keys + * could be created (i.e. VCEs were invalid) return -ENOKEY. + */ +static int add_certificates_to_keyring(struct vcssb *vcssb, struct key *keyring) +{ + int rc, index, count, added; + + count = 0; + added = 0; + /* Certificate Store entries indices start with 1 and have no gaps. */ + for (index = 1; index < vcssb->total_vc_index_count + 1; index++) { + pr_dbf_msg("Creating key from VCE %u", index); + rc = create_key_from_sevcb(vcssb, index, keyring); + count++; + + if (rc == -EAGAIN) + return rc; + + if (rc) + pr_dbf_msg("Creating key from VCE %u failed (%d)", index, rc); + else + added++; + } + + if (added == 0) { + pr_dbf_msg("Processed %d entries. No keys created", count); + return -ENOKEY; + } + + pr_info("Added %d of %d keys to cert_store keyring", added, count); + + /* + * Do not allow to link more keys to certificate store keyring after all + * the VCEs were processed. + */ + rc = keyring_restrict(make_key_ref(keyring, true), NULL, NULL); + if (rc) + pr_dbf_msg("Failed to set restriction to cert_store keyring (%d)", rc); + + return 0; +} + +/* + * Check which DIAG320 subcodes are installed. + * Return -ENOENT if subcodes 1 or 2 are not available. + */ +static int query_diag320_subcodes(void) +{ + unsigned long ism[ISM_LEN_DWORDS]; + int rc; + + rc = diag320(0, ism); + if (rc != DIAG320_RC_OK) { + pr_dbf_msg("DIAG320 subcode query returned %04x", rc); + return -ENOENT; + } + + debug_text_event(cert_store_hexdump, 3, "DIAG320 Subcode 0"); + debug_event(cert_store_hexdump, 3, ism, sizeof(ism)); + + if (!test_bit_inv(1, ism) || !test_bit_inv(2, ism)) { + pr_dbf_msg("Not all required DIAG320 subcodes are installed"); + return -ENOENT; + } + + return 0; +} + +/* + * Check if Certificate Store is supported by the firmware and DIAG320 subcodes + * 1 and 2 are installed. Create cert_store keyring and link all certificates + * available for the current partition to it as "cert_store_key" type + * keys. On refresh or error invalidate cert_store keyring and destroy + * all keys of "cert_store_key" type. + */ +static int fill_cs_keyring(void) +{ + struct key *cs_keyring; + struct vcssb *vcssb; + int rc; + + rc = -ENOMEM; + vcssb = kmalloc(VCSSB_LEN_BYTES, GFP_KERNEL); + if (!vcssb) + goto cleanup_keys; + + rc = -ENOENT; + if (!sclp.has_diag320) { + pr_dbf_msg("Certificate Store is not supported"); + goto cleanup_keys; + } + + rc = query_diag320_subcodes(); + if (rc) + goto cleanup_keys; + + rc = get_vcssb(vcssb); + if (rc) + goto cleanup_keys; + + rc = -ENOMEM; + cs_keyring = create_cs_keyring(); + if (!cs_keyring) + goto cleanup_keys; + + rc = add_certificates_to_keyring(vcssb, cs_keyring); + if (rc) + goto cleanup_cs_keyring; + + goto out; + +cleanup_cs_keyring: + key_put(cs_keyring); +cleanup_keys: + cleanup_cs_keys(); +out: + kfree(vcssb); + return rc; +} + +static DEFINE_MUTEX(cs_refresh_lock); +static int cs_status_val = -1; + +static ssize_t cs_status_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + if (cs_status_val == -1) + return sysfs_emit(buf, "uninitialized\n"); + else if (cs_status_val == 0) + return sysfs_emit(buf, "ok\n"); + + return sysfs_emit(buf, "failed (%d)\n", cs_status_val); +} + +static struct kobj_attribute cs_status_attr = __ATTR_RO(cs_status); + +static ssize_t refresh_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int rc, retries; + + pr_dbf_msg("Refresh certificate store information requested"); + rc = mutex_lock_interruptible(&cs_refresh_lock); + if (rc) + return rc; + + for (retries = 0; retries < DIAG_MAX_RETRIES; retries++) { + /* Request certificates from certificate store. */ + rc = fill_cs_keyring(); + if (rc) + pr_dbf_msg("Failed to refresh certificate store information (%d)", rc); + if (rc != -EAGAIN) + break; + } + cs_status_val = rc; + mutex_unlock(&cs_refresh_lock); + + return rc ?: count; +} + +static struct kobj_attribute refresh_attr = __ATTR_WO(refresh); + +static const struct attribute *cert_store_attrs[] __initconst = { + &cs_status_attr.attr, + &refresh_attr.attr, + NULL, +}; + +static struct kobject *cert_store_kobj; + +static int __init cert_store_init(void) +{ + int rc = -ENOMEM; + + cert_store_dbf = debug_register("cert_store_msg", 10, 1, 64); + if (!cert_store_dbf) + goto cleanup_dbf; + + cert_store_hexdump = debug_register("cert_store_hexdump", 3, 1, 128); + if (!cert_store_hexdump) + goto cleanup_dbf; + + debug_register_view(cert_store_hexdump, &debug_hex_ascii_view); + debug_register_view(cert_store_dbf, &debug_sprintf_view); + + /* Create directory /sys/firmware/cert_store. */ + cert_store_kobj = kobject_create_and_add("cert_store", firmware_kobj); + if (!cert_store_kobj) + goto cleanup_dbf; + + rc = sysfs_create_files(cert_store_kobj, cert_store_attrs); + if (rc) + goto cleanup_kobj; + + register_key_type(&key_type_cert_store_key); + + return rc; + +cleanup_kobj: + kobject_put(cert_store_kobj); +cleanup_dbf: + debug_unregister(cert_store_dbf); + debug_unregister(cert_store_hexdump); + + return rc; +} +device_initcall(cert_store_init); diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag.c index 82079f2d8583..f9f06cd8fcee 100644 --- a/arch/s390/kernel/diag.c +++ b/arch/s390/kernel/diag.c @@ -11,6 +11,7 @@ #include <linux/cpu.h> #include <linux/seq_file.h> #include <linux/debugfs.h> +#include <linux/vmalloc.h> #include <asm/asm-extable.h> #include <asm/diag.h> #include <asm/trace/diag.h> @@ -50,6 +51,7 @@ static const struct diag_desc diag_map[NR_DIAG_STAT] = { [DIAG_STAT_X304] = { .code = 0x304, .name = "Partition-Resource Service" }, [DIAG_STAT_X308] = { .code = 0x308, .name = "List-Directed IPL" }, [DIAG_STAT_X318] = { .code = 0x318, .name = "CP Name and Version Codes" }, + [DIAG_STAT_X320] = { .code = 0x320, .name = "Certificate Store" }, [DIAG_STAT_X500] = { .code = 0x500, .name = "Virtio Service" }, }; @@ -167,8 +169,29 @@ static inline int __diag204(unsigned long *subcode, unsigned long size, void *ad return rp.odd; } +/** + * diag204() - Issue diagnose 204 call. + * @subcode: Subcode of diagnose 204 to be executed. + * @size: Size of area in pages which @area points to, if given. + * @addr: Vmalloc'ed memory area where the result is written to. + * + * Execute diagnose 204 with the given subcode and write the result to the + * memory area specified with @addr. For subcodes which do not write a + * result to memory both @size and @addr must be zero. If @addr is + * specified it must be page aligned and must have been allocated with + * vmalloc(). Conversion to real / physical addresses will be handled by + * this function if required. + */ int diag204(unsigned long subcode, unsigned long size, void *addr) { + if (addr) { + if (WARN_ON_ONCE(!is_vmalloc_addr(addr))) + return -1; + if (WARN_ON_ONCE(!IS_ALIGNED((unsigned long)addr, PAGE_SIZE))) + return -1; + } + if ((subcode & DIAG204_SUBCODE_MASK) == DIAG204_SUBC_STIB4) + addr = (void *)pfn_to_phys(vmalloc_to_pfn(addr)); diag_stat_inc(DIAG_STAT_X204); size = __diag204(&subcode, size, addr); if (subcode) @@ -200,7 +223,7 @@ int diag210(struct diag210 *addr) EXPORT_SYMBOL(diag210); /* - * Diagnose 210: Get information about a virtual device + * Diagnose 8C: Access 3270 Display Device Information */ int diag8c(struct diag8c *addr, struct ccw_dev_id *devno) { diff --git a/arch/s390/kernel/ebcdic.c b/arch/s390/kernel/ebcdic.c index 7f8246c9be08..0e51fa537262 100644 --- a/arch/s390/kernel/ebcdic.c +++ b/arch/s390/kernel/ebcdic.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * ECBDIC -> ASCII, ASCII -> ECBDIC, + * EBCDIC -> ASCII, ASCII -> EBCDIC, * upper to lower case (EBCDIC) conversion tables. * * S390 version diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index a660f4b6d654..49a11f6dd7ae 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -8,6 +8,7 @@ * Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com), */ +#include <linux/export.h> #include <linux/init.h> #include <linux/linkage.h> #include <asm/asm-extable.h> @@ -26,7 +27,6 @@ #include <asm/vx-insn.h> #include <asm/setup.h> #include <asm/nmi.h> -#include <asm/export.h> #include <asm/nospec-insn.h> _LPP_OFFSET = __LC_LPP diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 85a00d97a314..05e51666db03 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -266,7 +266,7 @@ static ssize_t sys_##_prefix##_##_name##_store(struct kobject *kobj, \ struct kobj_attribute *attr, \ const char *buf, size_t len) \ { \ - strncpy(_value, buf, sizeof(_value) - 1); \ + strscpy(_value, buf, sizeof(_value)); \ strim(_value); \ return len; \ } \ @@ -557,15 +557,12 @@ static struct kobj_attribute sys_ipl_ccw_loadparm_attr = __ATTR(loadparm, 0444, ipl_ccw_loadparm_show, NULL); static struct attribute *ipl_fcp_attrs[] = { - &sys_ipl_type_attr.attr, &sys_ipl_device_attr.attr, &sys_ipl_fcp_wwpn_attr.attr, &sys_ipl_fcp_lun_attr.attr, &sys_ipl_fcp_bootprog_attr.attr, &sys_ipl_fcp_br_lba_attr.attr, &sys_ipl_ccw_loadparm_attr.attr, - &sys_ipl_secure_attr.attr, - &sys_ipl_has_secure_attr.attr, NULL, }; @@ -575,14 +572,11 @@ static struct attribute_group ipl_fcp_attr_group = { }; static struct attribute *ipl_nvme_attrs[] = { - &sys_ipl_type_attr.attr, &sys_ipl_nvme_fid_attr.attr, &sys_ipl_nvme_nsid_attr.attr, &sys_ipl_nvme_bootprog_attr.attr, &sys_ipl_nvme_br_lba_attr.attr, &sys_ipl_ccw_loadparm_attr.attr, - &sys_ipl_secure_attr.attr, - &sys_ipl_has_secure_attr.attr, NULL, }; @@ -592,13 +586,10 @@ static struct attribute_group ipl_nvme_attr_group = { }; static struct attribute *ipl_eckd_attrs[] = { - &sys_ipl_type_attr.attr, &sys_ipl_eckd_bootprog_attr.attr, &sys_ipl_eckd_br_chr_attr.attr, &sys_ipl_ccw_loadparm_attr.attr, &sys_ipl_device_attr.attr, - &sys_ipl_secure_attr.attr, - &sys_ipl_has_secure_attr.attr, NULL, }; @@ -610,21 +601,15 @@ static struct attribute_group ipl_eckd_attr_group = { /* CCW ipl device attributes */ static struct attribute *ipl_ccw_attrs_vm[] = { - &sys_ipl_type_attr.attr, &sys_ipl_device_attr.attr, &sys_ipl_ccw_loadparm_attr.attr, &sys_ipl_vm_parm_attr.attr, - &sys_ipl_secure_attr.attr, - &sys_ipl_has_secure_attr.attr, NULL, }; static struct attribute *ipl_ccw_attrs_lpar[] = { - &sys_ipl_type_attr.attr, &sys_ipl_device_attr.attr, &sys_ipl_ccw_loadparm_attr.attr, - &sys_ipl_secure_attr.attr, - &sys_ipl_has_secure_attr.attr, NULL, }; @@ -636,15 +621,15 @@ static struct attribute_group ipl_ccw_attr_group_lpar = { .attrs = ipl_ccw_attrs_lpar }; -/* UNKNOWN ipl device attributes */ - -static struct attribute *ipl_unknown_attrs[] = { +static struct attribute *ipl_common_attrs[] = { &sys_ipl_type_attr.attr, + &sys_ipl_secure_attr.attr, + &sys_ipl_has_secure_attr.attr, NULL, }; -static struct attribute_group ipl_unknown_attr_group = { - .attrs = ipl_unknown_attrs, +static struct attribute_group ipl_common_attr_group = { + .attrs = ipl_common_attrs, }; static struct kset *ipl_kset; @@ -668,6 +653,9 @@ static int __init ipl_init(void) rc = -ENOMEM; goto out; } + rc = sysfs_create_group(&ipl_kset->kobj, &ipl_common_attr_group); + if (rc) + goto out; switch (ipl_info.type) { case IPL_TYPE_CCW: if (MACHINE_IS_VM) @@ -689,8 +677,6 @@ static int __init ipl_init(void) rc = sysfs_create_group(&ipl_kset->kobj, &ipl_nvme_attr_group); break; default: - rc = sysfs_create_group(&ipl_kset->kobj, - &ipl_unknown_attr_group); break; } out: diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index 6d9276c096a6..12a2bd4fc88c 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -13,6 +13,7 @@ #include <linux/reboot.h> #include <linux/ftrace.h> #include <linux/debug_locks.h> +#include <asm/pfault.h> #include <asm/cio.h> #include <asm/setup.h> #include <asm/smp.h> diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c index 2df94d32140c..8d207b82d9fe 100644 --- a/arch/s390/kernel/machine_kexec_file.c +++ b/arch/s390/kernel/machine_kexec_file.c @@ -188,7 +188,7 @@ static int kexec_file_add_ipl_report(struct kimage *image, data->memsz = ALIGN(data->memsz, PAGE_SIZE); buf.mem = data->memsz; - ptr = (void *)ipl_cert_list_addr; + ptr = __va(ipl_cert_list_addr); end = ptr + ipl_cert_list_size; ncerts = 0; while (ptr < end) { @@ -200,7 +200,7 @@ static int kexec_file_add_ipl_report(struct kimage *image, addr = data->memsz + data->report->size; addr += ncerts * sizeof(struct ipl_rb_certificate_entry); - ptr = (void *)ipl_cert_list_addr; + ptr = __va(ipl_cert_list_addr); while (ptr < end) { len = *(unsigned int *)ptr; ptr += sizeof(len); diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index dbece2803c50..ae4d4fd9afcd 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -9,15 +9,20 @@ #include <asm/ftrace.h> #include <asm/nospec-insn.h> #include <asm/ptrace.h> -#include <asm/export.h> +#define STACK_FRAME_SIZE_PTREGS (STACK_FRAME_OVERHEAD + __PT_SIZE) +#define STACK_PTREGS (STACK_FRAME_OVERHEAD) +#define STACK_PTREGS_GPRS (STACK_PTREGS + __PT_GPRS) +#define STACK_PTREGS_PSW (STACK_PTREGS + __PT_PSW) + +#define STACK_FRAME_SIZE_FREGS (STACK_FRAME_OVERHEAD + __FTRACE_REGS_SIZE) +#define STACK_FREGS (STACK_FRAME_OVERHEAD) +#define STACK_FREGS_PTREGS (STACK_FRAME_OVERHEAD + __FTRACE_REGS_PT_REGS) +#define STACK_FREGS_PTREGS_GPRS (STACK_FREGS_PTREGS + __PT_GPRS) +#define STACK_FREGS_PTREGS_PSW (STACK_FREGS_PTREGS + __PT_PSW) +#define STACK_FREGS_PTREGS_ORIG_GPR2 (STACK_FREGS_PTREGS + __PT_ORIG_GPR2) +#define STACK_FREGS_PTREGS_FLAGS (STACK_FREGS_PTREGS + __PT_FLAGS) -#define STACK_FRAME_SIZE (STACK_FRAME_OVERHEAD + __PT_SIZE) -#define STACK_PTREGS (STACK_FRAME_OVERHEAD) -#define STACK_PTREGS_GPRS (STACK_PTREGS + __PT_GPRS) -#define STACK_PTREGS_PSW (STACK_PTREGS + __PT_PSW) -#define STACK_PTREGS_ORIG_GPR2 (STACK_PTREGS + __PT_ORIG_GPR2) -#define STACK_PTREGS_FLAGS (STACK_PTREGS + __PT_FLAGS) /* packed stack: allocate just enough for r14, r15 and backchain */ #define TRACED_FUNC_FRAME_SIZE 24 @@ -53,23 +58,23 @@ SYM_CODE_END(ftrace_stub_direct_tramp) stg %r1,__SF_BACKCHAIN(%r15) stg %r0,(__SF_GPRS+8*8)(%r15) stg %r15,(__SF_GPRS+9*8)(%r15) - # allocate pt_regs and stack frame for ftrace_trace_function - aghi %r15,-STACK_FRAME_SIZE - stg %r1,(STACK_PTREGS_GPRS+15*8)(%r15) - xc STACK_PTREGS_ORIG_GPR2(8,%r15),STACK_PTREGS_ORIG_GPR2(%r15) + # allocate ftrace_regs and stack frame for ftrace_trace_function + aghi %r15,-STACK_FRAME_SIZE_FREGS + stg %r1,(STACK_FREGS_PTREGS_GPRS+15*8)(%r15) + xc STACK_FREGS_PTREGS_ORIG_GPR2(8,%r15),STACK_FREGS_PTREGS_ORIG_GPR2(%r15) .if \allregs == 1 - stg %r14,(STACK_PTREGS_PSW)(%r15) - mvghi STACK_PTREGS_FLAGS(%r15),_PIF_FTRACE_FULL_REGS + stg %r14,(STACK_FREGS_PTREGS_PSW)(%r15) + mvghi STACK_FREGS_PTREGS_FLAGS(%r15),_PIF_FTRACE_FULL_REGS .else - xc STACK_PTREGS_FLAGS(8,%r15),STACK_PTREGS_FLAGS(%r15) + xc STACK_FREGS_PTREGS_FLAGS(8,%r15),STACK_FREGS_PTREGS_FLAGS(%r15) .endif lg %r14,(__SF_GPRS+8*8)(%r1) # restore original return address aghi %r1,-TRACED_FUNC_FRAME_SIZE stg %r1,__SF_BACKCHAIN(%r15) - stg %r0,(STACK_PTREGS_PSW+8)(%r15) - stmg %r2,%r14,(STACK_PTREGS_GPRS+2*8)(%r15) + stg %r0,(STACK_FREGS_PTREGS_PSW+8)(%r15) + stmg %r2,%r14,(STACK_FREGS_PTREGS_GPRS+2*8)(%r15) .endm SYM_CODE_START(ftrace_regs_caller) @@ -96,30 +101,30 @@ SYM_CODE_START(ftrace_common) lg %r1,0(%r1) #endif lgr %r3,%r14 - la %r5,STACK_PTREGS(%r15) + la %r5,STACK_FREGS(%r15) BASR_EX %r14,%r1 #ifdef CONFIG_FUNCTION_GRAPH_TRACER # The j instruction gets runtime patched to a nop instruction. # See ftrace_enable_ftrace_graph_caller. SYM_INNER_LABEL(ftrace_graph_caller, SYM_L_GLOBAL) j .Lftrace_graph_caller_end - lmg %r2,%r3,(STACK_PTREGS_GPRS+14*8)(%r15) - lg %r4,(STACK_PTREGS_PSW+8)(%r15) + lmg %r2,%r3,(STACK_FREGS_PTREGS_GPRS+14*8)(%r15) + lg %r4,(STACK_FREGS_PTREGS_PSW+8)(%r15) brasl %r14,prepare_ftrace_return - stg %r2,(STACK_PTREGS_GPRS+14*8)(%r15) + stg %r2,(STACK_FREGS_PTREGS_GPRS+14*8)(%r15) .Lftrace_graph_caller_end: #endif - lg %r0,(STACK_PTREGS_PSW+8)(%r15) + lg %r0,(STACK_FREGS_PTREGS_PSW+8)(%r15) #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES - ltg %r1,STACK_PTREGS_ORIG_GPR2(%r15) + ltg %r1,STACK_FREGS_PTREGS_ORIG_GPR2(%r15) locgrz %r1,%r0 #else - lg %r1,STACK_PTREGS_ORIG_GPR2(%r15) + lg %r1,STACK_FREGS_PTREGS_ORIG_GPR2(%r15) ltgr %r1,%r1 jnz 0f lgr %r1,%r0 #endif -0: lmg %r2,%r15,(STACK_PTREGS_GPRS+2*8)(%r15) +0: lmg %r2,%r15,(STACK_FREGS_PTREGS_GPRS+2*8)(%r15) BR_EX %r1 SYM_CODE_END(ftrace_common) @@ -128,10 +133,14 @@ SYM_CODE_END(ftrace_common) SYM_FUNC_START(return_to_handler) stmg %r2,%r5,32(%r15) lgr %r1,%r15 - aghi %r15,-STACK_FRAME_OVERHEAD + aghi %r15,-(STACK_FRAME_OVERHEAD+__FGRAPH_RET_SIZE) stg %r1,__SF_BACKCHAIN(%r15) + la %r3,STACK_FRAME_OVERHEAD(%r15) + stg %r1,__FGRAPH_RET_FP(%r3) + stg %r2,__FGRAPH_RET_GPR2(%r3) + lgr %r2,%r3 brasl %r14,ftrace_return_to_handler - aghi %r15,STACK_FRAME_OVERHEAD + aghi %r15,STACK_FRAME_OVERHEAD+__FGRAPH_RET_SIZE lgr %r14,%r2 lmg %r2,%r5,32(%r15) BR_EX %r14 @@ -160,11 +169,11 @@ SYM_CODE_END(ftrace_shared_hotpatch_trampoline_exrl) SYM_CODE_START(arch_rethook_trampoline) stg %r14,(__SF_GPRS+8*8)(%r15) - lay %r15,-STACK_FRAME_SIZE(%r15) + lay %r15,-STACK_FRAME_SIZE_PTREGS(%r15) stmg %r0,%r14,STACK_PTREGS_GPRS(%r15) # store original stack pointer in backchain and pt_regs - lay %r7,STACK_FRAME_SIZE(%r15) + lay %r7,STACK_FRAME_SIZE_PTREGS(%r15) stg %r7,__SF_BACKCHAIN(%r15) stg %r7,STACK_PTREGS_GPRS+(15*8)(%r15) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 00d76448319d..c744104e4a9c 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -146,6 +146,7 @@ static u32 __amode31_ref *__ctl_linkage_stack = __ctl_linkage_stack_amode31; static u32 __amode31_ref *__ctl_duct = __ctl_duct_amode31; int __bootdata(noexec_disabled); +unsigned long __bootdata_preserved(max_mappable); unsigned long __bootdata(ident_map_size); struct physmem_info __bootdata(physmem_info); @@ -874,7 +875,7 @@ static void __init log_component_list(void) pr_info("Linux is running with Secure-IPL enabled\n"); else pr_info("Linux is running with Secure-IPL disabled\n"); - ptr = (void *) early_ipl_comp_list_addr; + ptr = __va(early_ipl_comp_list_addr); end = (void *) ptr + early_ipl_comp_list_size; pr_info("The IPL report contains the following components:\n"); while (ptr < end) { diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index f9a2b755f510..a4edb7ea66ea 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -37,6 +37,7 @@ #include <linux/crash_dump.h> #include <linux/kprobes.h> #include <asm/asm-offsets.h> +#include <asm/pfault.h> #include <asm/diag.h> #include <asm/switch_to.h> #include <asm/facility.h> @@ -252,8 +253,9 @@ static void pcpu_free_lowcore(struct pcpu *pcpu) static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu) { - struct lowcore *lc = lowcore_ptr[cpu]; + struct lowcore *lc, *abs_lc; + lc = lowcore_ptr[cpu]; cpumask_set_cpu(cpu, &init_mm.context.cpu_attach_mask); cpumask_set_cpu(cpu, mm_cpumask(&init_mm)); lc->cpu_nr = cpu; @@ -266,7 +268,9 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu) lc->machine_flags = S390_lowcore.machine_flags; lc->user_timer = lc->system_timer = lc->steal_timer = lc->avg_steal_timer = 0; - __ctl_store(lc->cregs_save_area, 0, 15); + abs_lc = get_abs_lowcore(); + memcpy(lc->cregs_save_area, abs_lc->cregs_save_area, sizeof(lc->cregs_save_area)); + put_abs_lowcore(abs_lc); lc->cregs_save_area[1] = lc->kernel_asce; lc->cregs_save_area[7] = lc->user_asce; save_access_regs((unsigned int *) lc->access_regs_save_area); @@ -606,8 +610,8 @@ void smp_ctl_set_clear_bit(int cr, int bit, bool set) ctlreg = (ctlreg & parms.andval) | parms.orval; abs_lc->cregs_save_area[cr] = ctlreg; put_abs_lowcore(abs_lc); - spin_unlock(&ctl_lock); on_each_cpu(smp_ctl_bit_callback, &parms, 1); + spin_unlock(&ctl_lock); } EXPORT_SYMBOL(smp_ctl_set_clear_bit); @@ -927,12 +931,18 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle) rc = pcpu_alloc_lowcore(pcpu, cpu); if (rc) return rc; + /* + * Make sure global control register contents do not change + * until new CPU has initialized control registers. + */ + spin_lock(&ctl_lock); pcpu_prepare_secondary(pcpu, cpu); pcpu_attach_task(pcpu, tidle); pcpu_start_fn(pcpu, smp_start_secondary, NULL); /* Wait until cpu puts itself in the online & active maps */ while (!cpu_online(cpu)) cpu_relax(); + spin_unlock(&ctl_lock); return 0; } diff --git a/arch/s390/kernel/sthyi.c b/arch/s390/kernel/sthyi.c index 2ea7f208f0e7..30bb20461db4 100644 --- a/arch/s390/kernel/sthyi.c +++ b/arch/s390/kernel/sthyi.c @@ -317,7 +317,9 @@ static void fill_diag(struct sthyi_sctns *sctns) if (pages <= 0) return; - diag204_buf = vmalloc(array_size(pages, PAGE_SIZE)); + diag204_buf = __vmalloc_node(array_size(pages, PAGE_SIZE), + PAGE_SIZE, GFP_KERNEL, NUMA_NO_NODE, + __builtin_return_address(0)); if (!diag204_buf) return; diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index a6935af2235c..0122cc156952 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -454,3 +454,4 @@ 449 common futex_waitv sys_futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_mempolicy_home_node 451 common cachestat sys_cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 sys_fchmodat2 diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index 66f0eb1c872b..b771f1b4cdd1 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -88,7 +88,7 @@ fail: * Requests the Ultravisor to pin the page in the shared state. This will * cause an intercept when the guest attempts to unshare the pinned page. */ -static int uv_pin_shared(unsigned long paddr) +int uv_pin_shared(unsigned long paddr) { struct uv_cb_cfs uvcb = { .header.cmd = UVC_CMD_PIN_PAGE_SHARED, @@ -100,6 +100,7 @@ static int uv_pin_shared(unsigned long paddr) return -EINVAL; return 0; } +EXPORT_SYMBOL_GPL(uv_pin_shared); /* * Requests the Ultravisor to destroy a guest page and make it diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 0261d42c7d01..a7ea80cfa445 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -270,18 +270,6 @@ static inline u64 kvm_s390_pv_cpu_get_handle(struct kvm_vcpu *vcpu) return vcpu->arch.pv.handle; } -static inline bool kvm_s390_pv_is_protected(struct kvm *kvm) -{ - lockdep_assert_held(&kvm->lock); - return !!kvm_s390_pv_get_handle(kvm); -} - -static inline bool kvm_s390_pv_cpu_is_protected(struct kvm_vcpu *vcpu) -{ - lockdep_assert_held(&vcpu->mutex); - return !!kvm_s390_pv_cpu_get_handle(vcpu); -} - /* implemented in interrupt.c */ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu); void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu); diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index bf1fdc7bf89e..8d3f39a8a11e 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -18,6 +18,20 @@ #include <linux/mmu_notifier.h> #include "kvm-s390.h" +bool kvm_s390_pv_is_protected(struct kvm *kvm) +{ + lockdep_assert_held(&kvm->lock); + return !!kvm_s390_pv_get_handle(kvm); +} +EXPORT_SYMBOL_GPL(kvm_s390_pv_is_protected); + +bool kvm_s390_pv_cpu_is_protected(struct kvm_vcpu *vcpu) +{ + lockdep_assert_held(&vcpu->mutex); + return !!kvm_s390_pv_cpu_get_handle(vcpu); +} +EXPORT_SYMBOL_GPL(kvm_s390_pv_cpu_is_protected); + /** * struct pv_vm_to_be_destroyed - Represents a protected VM that needs to * be destroyed diff --git a/arch/s390/lib/mem.S b/arch/s390/lib/mem.S index 5a9a55de2e10..08f60a42b9a6 100644 --- a/arch/s390/lib/mem.S +++ b/arch/s390/lib/mem.S @@ -5,8 +5,8 @@ * Copyright IBM Corp. 2012 */ +#include <linux/export.h> #include <linux/linkage.h> -#include <asm/export.h> #include <asm/nospec-insn.h> GEN_BR_THUNK %r14 diff --git a/arch/s390/lib/tishift.S b/arch/s390/lib/tishift.S index de33cf02cfd2..96214f51f49b 100644 --- a/arch/s390/lib/tishift.S +++ b/arch/s390/lib/tishift.S @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/export.h> #include <linux/linkage.h> #include <asm/nospec-insn.h> -#include <asm/export.h> .section .noinstr.text, "ax" diff --git a/arch/s390/mm/Makefile b/arch/s390/mm/Makefile index d90db06a8af5..352ff520fd94 100644 --- a/arch/s390/mm/Makefile +++ b/arch/s390/mm/Makefile @@ -10,3 +10,4 @@ obj-$(CONFIG_CMM) += cmm.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o obj-$(CONFIG_PTDUMP_CORE) += dump_pagetables.o obj-$(CONFIG_PGSTE) += gmap.o +obj-$(CONFIG_PFAULT) += pfault.o diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index 5300c6867d5e..f47515313226 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -90,7 +90,7 @@ static long cmm_alloc_pages(long nr, long *counter, } else free_page((unsigned long) npa); } - diag10_range(virt_to_pfn(addr), 1); + diag10_range(virt_to_pfn((void *)addr), 1); pa->pages[pa->index++] = addr; (*counter)++; spin_unlock(&cmm_lock); diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c index ba5f80268878..afa5db750d92 100644 --- a/arch/s390/mm/dump_pagetables.c +++ b/arch/s390/mm/dump_pagetables.c @@ -297,7 +297,7 @@ static int pt_dump_init(void) address_markers[ABS_LOWCORE_NR].start_address = __abs_lowcore; address_markers[ABS_LOWCORE_END_NR].start_address = __abs_lowcore + ABS_LOWCORE_MAP_SIZE; address_markers[MEMCPY_REAL_NR].start_address = __memcpy_real_area; - address_markers[MEMCPY_REAL_END_NR].start_address = __memcpy_real_area + PAGE_SIZE; + address_markers[MEMCPY_REAL_END_NR].start_address = __memcpy_real_area + MEMCPY_REAL_SIZE; address_markers[VMEMMAP_NR].start_address = (unsigned long) vmemmap; address_markers[VMEMMAP_END_NR].start_address = (unsigned long)vmemmap + vmemmap_size; address_markers[VMALLOC_NR].start_address = VMALLOC_START; diff --git a/arch/s390/mm/extmem.c b/arch/s390/mm/extmem.c index 1bc42ce26599..e41869f5cc95 100644 --- a/arch/s390/mm/extmem.c +++ b/arch/s390/mm/extmem.c @@ -640,10 +640,13 @@ void segment_warning(int rc, char *seg_name) pr_err("There is not enough memory to load or query " "DCSS %s\n", seg_name); break; - case -ERANGE: - pr_err("DCSS %s exceeds the kernel mapping range (%lu) " - "and cannot be loaded\n", seg_name, VMEM_MAX_PHYS); + case -ERANGE: { + struct range mhp_range = arch_get_mappable_range(); + + pr_err("DCSS %s exceeds the kernel mapping range (%llu) " + "and cannot be loaded\n", seg_name, mhp_range.end + 1); break; + } default: break; } diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 2f123429a291..b5e1bea9194c 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -43,8 +43,6 @@ #include "../kernel/entry.h" #define __FAIL_ADDR_MASK -4096L -#define __SUBCODE_MASK 0x0600 -#define __PF_RES_FIELD 0x8000000000000000ULL /* * Allocate private vm_fault_reason from top. Please make sure it won't @@ -583,232 +581,6 @@ void do_dat_exception(struct pt_regs *regs) } NOKPROBE_SYMBOL(do_dat_exception); -#ifdef CONFIG_PFAULT -/* - * 'pfault' pseudo page faults routines. - */ -static int pfault_disable; - -static int __init nopfault(char *str) -{ - pfault_disable = 1; - return 1; -} - -__setup("nopfault", nopfault); - -struct pfault_refbk { - u16 refdiagc; - u16 reffcode; - u16 refdwlen; - u16 refversn; - u64 refgaddr; - u64 refselmk; - u64 refcmpmk; - u64 reserved; -} __attribute__ ((packed, aligned(8))); - -static struct pfault_refbk pfault_init_refbk = { - .refdiagc = 0x258, - .reffcode = 0, - .refdwlen = 5, - .refversn = 2, - .refgaddr = __LC_LPP, - .refselmk = 1ULL << 48, - .refcmpmk = 1ULL << 48, - .reserved = __PF_RES_FIELD -}; - -int pfault_init(void) -{ - int rc; - - if (pfault_disable) - return -1; - diag_stat_inc(DIAG_STAT_X258); - asm volatile( - " diag %1,%0,0x258\n" - "0: j 2f\n" - "1: la %0,8\n" - "2:\n" - EX_TABLE(0b,1b) - : "=d" (rc) - : "a" (&pfault_init_refbk), "m" (pfault_init_refbk) : "cc"); - return rc; -} - -static struct pfault_refbk pfault_fini_refbk = { - .refdiagc = 0x258, - .reffcode = 1, - .refdwlen = 5, - .refversn = 2, -}; - -void pfault_fini(void) -{ - - if (pfault_disable) - return; - diag_stat_inc(DIAG_STAT_X258); - asm volatile( - " diag %0,0,0x258\n" - "0: nopr %%r7\n" - EX_TABLE(0b,0b) - : : "a" (&pfault_fini_refbk), "m" (pfault_fini_refbk) : "cc"); -} - -static DEFINE_SPINLOCK(pfault_lock); -static LIST_HEAD(pfault_list); - -#define PF_COMPLETE 0x0080 - -/* - * The mechanism of our pfault code: if Linux is running as guest, runs a user - * space process and the user space process accesses a page that the host has - * paged out we get a pfault interrupt. - * - * This allows us, within the guest, to schedule a different process. Without - * this mechanism the host would have to suspend the whole virtual cpu until - * the page has been paged in. - * - * So when we get such an interrupt then we set the state of the current task - * to uninterruptible and also set the need_resched flag. Both happens within - * interrupt context(!). If we later on want to return to user space we - * recognize the need_resched flag and then call schedule(). It's not very - * obvious how this works... - * - * Of course we have a lot of additional fun with the completion interrupt (-> - * host signals that a page of a process has been paged in and the process can - * continue to run). This interrupt can arrive on any cpu and, since we have - * virtual cpus, actually appear before the interrupt that signals that a page - * is missing. - */ -static void pfault_interrupt(struct ext_code ext_code, - unsigned int param32, unsigned long param64) -{ - struct task_struct *tsk; - __u16 subcode; - pid_t pid; - - /* - * Get the external interruption subcode & pfault initial/completion - * signal bit. VM stores this in the 'cpu address' field associated - * with the external interrupt. - */ - subcode = ext_code.subcode; - if ((subcode & 0xff00) != __SUBCODE_MASK) - return; - inc_irq_stat(IRQEXT_PFL); - /* Get the token (= pid of the affected task). */ - pid = param64 & LPP_PID_MASK; - rcu_read_lock(); - tsk = find_task_by_pid_ns(pid, &init_pid_ns); - if (tsk) - get_task_struct(tsk); - rcu_read_unlock(); - if (!tsk) - return; - spin_lock(&pfault_lock); - if (subcode & PF_COMPLETE) { - /* signal bit is set -> a page has been swapped in by VM */ - if (tsk->thread.pfault_wait == 1) { - /* Initial interrupt was faster than the completion - * interrupt. pfault_wait is valid. Set pfault_wait - * back to zero and wake up the process. This can - * safely be done because the task is still sleeping - * and can't produce new pfaults. */ - tsk->thread.pfault_wait = 0; - list_del(&tsk->thread.list); - wake_up_process(tsk); - put_task_struct(tsk); - } else { - /* Completion interrupt was faster than initial - * interrupt. Set pfault_wait to -1 so the initial - * interrupt doesn't put the task to sleep. - * If the task is not running, ignore the completion - * interrupt since it must be a leftover of a PFAULT - * CANCEL operation which didn't remove all pending - * completion interrupts. */ - if (task_is_running(tsk)) - tsk->thread.pfault_wait = -1; - } - } else { - /* signal bit not set -> a real page is missing. */ - if (WARN_ON_ONCE(tsk != current)) - goto out; - if (tsk->thread.pfault_wait == 1) { - /* Already on the list with a reference: put to sleep */ - goto block; - } else if (tsk->thread.pfault_wait == -1) { - /* Completion interrupt was faster than the initial - * interrupt (pfault_wait == -1). Set pfault_wait - * back to zero and exit. */ - tsk->thread.pfault_wait = 0; - } else { - /* Initial interrupt arrived before completion - * interrupt. Let the task sleep. - * An extra task reference is needed since a different - * cpu may set the task state to TASK_RUNNING again - * before the scheduler is reached. */ - get_task_struct(tsk); - tsk->thread.pfault_wait = 1; - list_add(&tsk->thread.list, &pfault_list); -block: - /* Since this must be a userspace fault, there - * is no kernel task state to trample. Rely on the - * return to userspace schedule() to block. */ - __set_current_state(TASK_UNINTERRUPTIBLE); - set_tsk_need_resched(tsk); - set_preempt_need_resched(); - } - } -out: - spin_unlock(&pfault_lock); - put_task_struct(tsk); -} - -static int pfault_cpu_dead(unsigned int cpu) -{ - struct thread_struct *thread, *next; - struct task_struct *tsk; - - spin_lock_irq(&pfault_lock); - list_for_each_entry_safe(thread, next, &pfault_list, list) { - thread->pfault_wait = 0; - list_del(&thread->list); - tsk = container_of(thread, struct task_struct, thread); - wake_up_process(tsk); - put_task_struct(tsk); - } - spin_unlock_irq(&pfault_lock); - return 0; -} - -static int __init pfault_irq_init(void) -{ - int rc; - - rc = register_external_irq(EXT_IRQ_CP_SERVICE, pfault_interrupt); - if (rc) - goto out_extint; - rc = pfault_init() == 0 ? 0 : -EOPNOTSUPP; - if (rc) - goto out_pfault; - irq_subclass_register(IRQ_SUBCLASS_SERVICE_SIGNAL); - cpuhp_setup_state_nocalls(CPUHP_S390_PFAULT_DEAD, "s390/pfault:dead", - NULL, pfault_cpu_dead); - return 0; - -out_pfault: - unregister_external_irq(EXT_IRQ_CP_SERVICE, pfault_interrupt); -out_extint: - pfault_disable = 1; - return rc; -} -early_initcall(pfault_irq_init); - -#endif /* CONFIG_PFAULT */ - #if IS_ENABLED(CONFIG_PGSTE) void do_secure_storage_access(struct pt_regs *regs) diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 9c8af31be970..906a7bfc2a78 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -2514,6 +2514,7 @@ static int thp_split_walk_pmd_entry(pmd_t *pmd, unsigned long addr, static const struct mm_walk_ops thp_split_walk_ops = { .pmd_entry = thp_split_walk_pmd_entry, + .walk_lock = PGWALK_WRLOCK_VERIFY, }; static inline void thp_split_mm(struct mm_struct *mm) @@ -2565,6 +2566,7 @@ static int __zap_zero_pages(pmd_t *pmd, unsigned long start, static const struct mm_walk_ops zap_zero_walk_ops = { .pmd_entry = __zap_zero_pages, + .walk_lock = PGWALK_WRLOCK, }; /* @@ -2655,6 +2657,7 @@ static const struct mm_walk_ops enable_skey_walk_ops = { .hugetlb_entry = __s390_enable_skey_hugetlb, .pte_entry = __s390_enable_skey_pte, .pmd_entry = __s390_enable_skey_pmd, + .walk_lock = PGWALK_WRLOCK, }; int s390_enable_skey(void) @@ -2692,6 +2695,7 @@ static int __s390_reset_cmma(pte_t *pte, unsigned long addr, static const struct mm_walk_ops reset_cmma_walk_ops = { .pte_entry = __s390_reset_cmma, + .walk_lock = PGWALK_WRLOCK, }; void s390_reset_cmma(struct mm_struct *mm) @@ -2728,6 +2732,7 @@ static int s390_gather_pages(pte_t *ptep, unsigned long addr, static const struct mm_walk_ops gather_pages_ops = { .pte_entry = s390_gather_pages, + .walk_lock = PGWALK_RDLOCK, }; /* diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c index cbe1df1e9c18..c805b3e2592b 100644 --- a/arch/s390/mm/maccess.c +++ b/arch/s390/mm/maccess.c @@ -86,11 +86,12 @@ size_t memcpy_real_iter(struct iov_iter *iter, unsigned long src, size_t count) void *chunk; pte_t pte; + BUILD_BUG_ON(MEMCPY_REAL_SIZE != PAGE_SIZE); while (count) { - phys = src & PAGE_MASK; - offset = src & ~PAGE_MASK; + phys = src & MEMCPY_REAL_MASK; + offset = src & ~MEMCPY_REAL_MASK; chunk = (void *)(__memcpy_real_area + offset); - len = min(count, PAGE_SIZE - offset); + len = min(count, MEMCPY_REAL_SIZE - offset); pte = mk_pte_phys(phys, PAGE_KERNEL_RO); mutex_lock(&memcpy_real_mutex); diff --git a/arch/s390/mm/pfault.c b/arch/s390/mm/pfault.c new file mode 100644 index 000000000000..1aac13bb8f53 --- /dev/null +++ b/arch/s390/mm/pfault.c @@ -0,0 +1,248 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright IBM Corp. 1999, 2023 + */ + +#include <linux/cpuhotplug.h> +#include <linux/sched/task.h> +#include <linux/errno.h> +#include <linux/init.h> +#include <linux/irq.h> +#include <asm/asm-extable.h> +#include <asm/pfault.h> +#include <asm/diag.h> + +#define __SUBCODE_MASK 0x0600 +#define __PF_RES_FIELD 0x8000000000000000UL + +/* + * 'pfault' pseudo page faults routines. + */ +static int pfault_disable; + +static int __init nopfault(char *str) +{ + pfault_disable = 1; + return 1; +} +early_param("nopfault", nopfault); + +struct pfault_refbk { + u16 refdiagc; + u16 reffcode; + u16 refdwlen; + u16 refversn; + u64 refgaddr; + u64 refselmk; + u64 refcmpmk; + u64 reserved; +}; + +static struct pfault_refbk pfault_init_refbk = { + .refdiagc = 0x258, + .reffcode = 0, + .refdwlen = 5, + .refversn = 2, + .refgaddr = __LC_LPP, + .refselmk = 1UL << 48, + .refcmpmk = 1UL << 48, + .reserved = __PF_RES_FIELD +}; + +int __pfault_init(void) +{ + int rc = -EOPNOTSUPP; + + if (pfault_disable) + return rc; + diag_stat_inc(DIAG_STAT_X258); + asm volatile( + " diag %[refbk],%[rc],0x258\n" + "0: nopr %%r7\n" + EX_TABLE(0b, 0b) + : [rc] "+d" (rc) + : [refbk] "a" (&pfault_init_refbk), "m" (pfault_init_refbk) + : "cc"); + return rc; +} + +static struct pfault_refbk pfault_fini_refbk = { + .refdiagc = 0x258, + .reffcode = 1, + .refdwlen = 5, + .refversn = 2, +}; + +void __pfault_fini(void) +{ + if (pfault_disable) + return; + diag_stat_inc(DIAG_STAT_X258); + asm volatile( + " diag %[refbk],0,0x258\n" + "0: nopr %%r7\n" + EX_TABLE(0b, 0b) + : + : [refbk] "a" (&pfault_fini_refbk), "m" (pfault_fini_refbk) + : "cc"); +} + +static DEFINE_SPINLOCK(pfault_lock); +static LIST_HEAD(pfault_list); + +#define PF_COMPLETE 0x0080 + +/* + * The mechanism of our pfault code: if Linux is running as guest, runs a user + * space process and the user space process accesses a page that the host has + * paged out we get a pfault interrupt. + * + * This allows us, within the guest, to schedule a different process. Without + * this mechanism the host would have to suspend the whole virtual cpu until + * the page has been paged in. + * + * So when we get such an interrupt then we set the state of the current task + * to uninterruptible and also set the need_resched flag. Both happens within + * interrupt context(!). If we later on want to return to user space we + * recognize the need_resched flag and then call schedule(). It's not very + * obvious how this works... + * + * Of course we have a lot of additional fun with the completion interrupt (-> + * host signals that a page of a process has been paged in and the process can + * continue to run). This interrupt can arrive on any cpu and, since we have + * virtual cpus, actually appear before the interrupt that signals that a page + * is missing. + */ +static void pfault_interrupt(struct ext_code ext_code, + unsigned int param32, unsigned long param64) +{ + struct task_struct *tsk; + __u16 subcode; + pid_t pid; + + /* + * Get the external interruption subcode & pfault initial/completion + * signal bit. VM stores this in the 'cpu address' field associated + * with the external interrupt. + */ + subcode = ext_code.subcode; + if ((subcode & 0xff00) != __SUBCODE_MASK) + return; + inc_irq_stat(IRQEXT_PFL); + /* Get the token (= pid of the affected task). */ + pid = param64 & LPP_PID_MASK; + rcu_read_lock(); + tsk = find_task_by_pid_ns(pid, &init_pid_ns); + if (tsk) + get_task_struct(tsk); + rcu_read_unlock(); + if (!tsk) + return; + spin_lock(&pfault_lock); + if (subcode & PF_COMPLETE) { + /* signal bit is set -> a page has been swapped in by VM */ + if (tsk->thread.pfault_wait == 1) { + /* + * Initial interrupt was faster than the completion + * interrupt. pfault_wait is valid. Set pfault_wait + * back to zero and wake up the process. This can + * safely be done because the task is still sleeping + * and can't produce new pfaults. + */ + tsk->thread.pfault_wait = 0; + list_del(&tsk->thread.list); + wake_up_process(tsk); + put_task_struct(tsk); + } else { + /* + * Completion interrupt was faster than initial + * interrupt. Set pfault_wait to -1 so the initial + * interrupt doesn't put the task to sleep. + * If the task is not running, ignore the completion + * interrupt since it must be a leftover of a PFAULT + * CANCEL operation which didn't remove all pending + * completion interrupts. + */ + if (task_is_running(tsk)) + tsk->thread.pfault_wait = -1; + } + } else { + /* signal bit not set -> a real page is missing. */ + if (WARN_ON_ONCE(tsk != current)) + goto out; + if (tsk->thread.pfault_wait == 1) { + /* Already on the list with a reference: put to sleep */ + goto block; + } else if (tsk->thread.pfault_wait == -1) { + /* + * Completion interrupt was faster than the initial + * interrupt (pfault_wait == -1). Set pfault_wait + * back to zero and exit. + */ + tsk->thread.pfault_wait = 0; + } else { + /* + * Initial interrupt arrived before completion + * interrupt. Let the task sleep. + * An extra task reference is needed since a different + * cpu may set the task state to TASK_RUNNING again + * before the scheduler is reached. + */ + get_task_struct(tsk); + tsk->thread.pfault_wait = 1; + list_add(&tsk->thread.list, &pfault_list); +block: + /* + * Since this must be a userspace fault, there + * is no kernel task state to trample. Rely on the + * return to userspace schedule() to block. + */ + __set_current_state(TASK_UNINTERRUPTIBLE); + set_tsk_need_resched(tsk); + set_preempt_need_resched(); + } + } +out: + spin_unlock(&pfault_lock); + put_task_struct(tsk); +} + +static int pfault_cpu_dead(unsigned int cpu) +{ + struct thread_struct *thread, *next; + struct task_struct *tsk; + + spin_lock_irq(&pfault_lock); + list_for_each_entry_safe(thread, next, &pfault_list, list) { + thread->pfault_wait = 0; + list_del(&thread->list); + tsk = container_of(thread, struct task_struct, thread); + wake_up_process(tsk); + put_task_struct(tsk); + } + spin_unlock_irq(&pfault_lock); + return 0; +} + +static int __init pfault_irq_init(void) +{ + int rc; + + rc = register_external_irq(EXT_IRQ_CP_SERVICE, pfault_interrupt); + if (rc) + goto out_extint; + rc = pfault_init() == 0 ? 0 : -EOPNOTSUPP; + if (rc) + goto out_pfault; + irq_subclass_register(IRQ_SUBCLASS_SERVICE_SIGNAL); + cpuhp_setup_state_nocalls(CPUHP_S390_PFAULT_DEAD, "s390/pfault:dead", + NULL, pfault_cpu_dead); + return 0; + +out_pfault: + unregister_external_irq(EXT_IRQ_CP_SERVICE, pfault_interrupt); +out_extint: + pfault_disable = 1; + return rc; +} +early_initcall(pfault_irq_init); diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 24a66670f5c3..e44243b9c0a4 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -36,7 +36,7 @@ static void vmem_free_pages(unsigned long addr, int order) { /* We don't expect boot memory to be removed ever. */ if (!slab_is_available() || - WARN_ON_ONCE(PageReserved(virt_to_page(addr)))) + WARN_ON_ONCE(PageReserved(virt_to_page((void *)addr)))) return; free_pages(addr, order); } @@ -531,7 +531,7 @@ struct range arch_get_mappable_range(void) struct range mhp_range; mhp_range.start = 0; - mhp_range.end = VMEM_MAX_PHYS - 1; + mhp_range.end = max_mappable - 1; return mhp_range; } diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index ee367798e388..ee90a91ed888 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -666,9 +666,4 @@ static struct miscdevice clp_misc_device = { .fops = &clp_misc_fops, }; -static int __init clp_misc_init(void) -{ - return misc_register(&clp_misc_device); -} - -device_initcall(clp_misc_init); +builtin_misc_device(clp_misc_device); diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index 97377e8c5025..e90d585c4d3e 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -454,3 +454,4 @@ 449 common futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node 451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index faa835f3c54a..4ed06c71c43f 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -497,3 +497,4 @@ 449 common futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node 451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 5026e7b9adfe..ff4bda95b9c7 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -554,7 +554,7 @@ struct mconsole_output { static DEFINE_SPINLOCK(client_lock); static LIST_HEAD(clients); -static char console_buf[MCONSOLE_MAX_DATA]; +static char console_buf[MCONSOLE_MAX_DATA] __nonstring; static void console_write(struct console *console, const char *string, unsigned int len) @@ -567,7 +567,7 @@ static void console_write(struct console *console, const char *string, while (len > 0) { n = min((size_t) len, ARRAY_SIZE(console_buf)); - strncpy(console_buf, string, n); + memcpy(console_buf, string, n); string += n; len -= n; diff --git a/arch/um/drivers/vector_user.c b/arch/um/drivers/vector_user.c index c650e428432b..c719e1ec4645 100644 --- a/arch/um/drivers/vector_user.c +++ b/arch/um/drivers/vector_user.c @@ -141,7 +141,7 @@ static int create_tap_fd(char *iface) } memset(&ifr, 0, sizeof(ifr)); ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR; - strncpy((char *)&ifr.ifr_name, iface, sizeof(ifr.ifr_name) - 1); + strscpy(ifr.ifr_name, iface, sizeof(ifr.ifr_name)); err = ioctl(fd, TUNSETIFF, (void *) &ifr); if (err != 0) { @@ -171,7 +171,7 @@ static int create_raw_fd(char *iface, int flags, int proto) goto raw_fd_cleanup; } memset(&ifr, 0, sizeof(ifr)); - strncpy((char *)&ifr.ifr_name, iface, sizeof(ifr.ifr_name) - 1); + strscpy(ifr.ifr_name, iface, sizeof(ifr.ifr_name)); if (ioctl(fd, SIOCGIFINDEX, (void *) &ifr) < 0) { err = -errno; goto raw_fd_cleanup; diff --git a/arch/um/include/shared/user.h b/arch/um/include/shared/user.h index 0347a190429c..981e11d8e025 100644 --- a/arch/um/include/shared/user.h +++ b/arch/um/include/shared/user.h @@ -50,7 +50,6 @@ static inline int printk(const char *fmt, ...) #endif extern int in_aton(char *str); -extern size_t strlcpy(char *, const char *, size_t); extern size_t strlcat(char *, const char *, size_t); extern size_t strscpy(char *, const char *, size_t); diff --git a/arch/um/os-Linux/umid.c b/arch/um/os-Linux/umid.c index 7a1abb829930..288c422bfa96 100644 --- a/arch/um/os-Linux/umid.c +++ b/arch/um/os-Linux/umid.c @@ -40,7 +40,7 @@ static int __init make_uml_dir(void) __func__); goto err; } - strlcpy(dir, home, sizeof(dir)); + strscpy(dir, home, sizeof(dir)); uml_dir++; } strlcat(dir, uml_dir, sizeof(dir)); @@ -243,7 +243,7 @@ int __init set_umid(char *name) if (strlen(name) > UMID_LEN - 1) return -E2BIG; - strlcpy(umid, name, sizeof(umid)); + strscpy(umid, name, sizeof(umid)); return 0; } @@ -262,7 +262,7 @@ static int __init make_umid(void) make_uml_dir(); if (*umid == '\0') { - strlcpy(tmp, uml_dir, sizeof(tmp)); + strscpy(tmp, uml_dir, sizeof(tmp)); strlcat(tmp, "XXXXXX", sizeof(tmp)); fd = mkstemp(tmp); if (fd < 0) { diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index e36261b4ea14..8d9e4b362572 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1308,44 +1308,8 @@ config X86_REBOOTFIXUPS Say N otherwise. config MICROCODE - bool "CPU microcode loading support" - default y + def_bool y depends on CPU_SUP_AMD || CPU_SUP_INTEL - help - If you say Y here, you will be able to update the microcode on - Intel and AMD processors. The Intel support is for the IA32 family, - e.g. Pentium Pro, Pentium II, Pentium III, Pentium 4, Xeon etc. The - AMD support is for families 0x10 and later. You will obviously need - the actual microcode binary data itself which is not shipped with - the Linux kernel. - - The preferred method to load microcode from a detached initrd is described - in Documentation/arch/x86/microcode.rst. For that you need to enable - CONFIG_BLK_DEV_INITRD in order for the loader to be able to scan the - initrd for microcode blobs. - - In addition, you can build the microcode into the kernel. For that you - need to add the vendor-supplied microcode to the CONFIG_EXTRA_FIRMWARE - config option. - -config MICROCODE_INTEL - bool "Intel microcode loading support" - depends on CPU_SUP_INTEL && MICROCODE - default MICROCODE - help - This options enables microcode patch loading support for Intel - processors. - - For the current Intel microcode data package go to - <https://downloadcenter.intel.com> and search for - 'Linux Processor Microcode Data File'. - -config MICROCODE_AMD - bool "AMD microcode loading support" - depends on CPU_SUP_AMD && MICROCODE - help - If you select this option, microcode patch loading support for AMD - processors will be enabled. config MICROCODE_LATE_LOADING bool "Late microcode loading (DANGEROUS)" diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 40d2ff503079..71fc531b95b4 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -74,6 +74,11 @@ LDFLAGS_vmlinux += -z noexecstack ifeq ($(CONFIG_LD_IS_BFD),y) LDFLAGS_vmlinux += $(call ld-option,--no-warn-rwx-segments) endif +ifeq ($(CONFIG_EFI_STUB),y) +# ensure that the static EFI stub library will be pulled in, even if it is +# never referenced explicitly from the startup code +LDFLAGS_vmlinux += -u efi_pe_entry +endif LDFLAGS_vmlinux += -T hostprogs := mkpiggy diff --git a/arch/x86/boot/compressed/efi_mixed.S b/arch/x86/boot/compressed/efi_mixed.S index 4ca70bf93dc0..f4e22ef774ab 100644 --- a/arch/x86/boot/compressed/efi_mixed.S +++ b/arch/x86/boot/compressed/efi_mixed.S @@ -26,8 +26,8 @@ * When booting in 64-bit mode on 32-bit EFI firmware, startup_64_mixed_mode() * is the first thing that runs after switching to long mode. Depending on * whether the EFI handover protocol or the compat entry point was used to - * enter the kernel, it will either branch to the 64-bit EFI handover - * entrypoint at offset 0x390 in the image, or to the 64-bit EFI PE/COFF + * enter the kernel, it will either branch to the common 64-bit EFI stub + * entrypoint efi_stub_entry() directly, or via the 64-bit EFI PE/COFF * entrypoint efi_pe_entry(). In the former case, the bootloader must provide a * struct bootparams pointer as the third argument, so the presence of such a * pointer is used to disambiguate. @@ -37,21 +37,23 @@ * | efi32_pe_entry |---->| | | +-----------+--+ * +------------------+ | | +------+----------------+ | * | startup_32 |---->| startup_64_mixed_mode | | - * +------------------+ | | +------+----------------+ V - * | efi32_stub_entry |---->| | | +------------------+ - * +------------------+ +------------+ +---->| efi64_stub_entry | - * +-------------+----+ - * +------------+ +----------+ | - * | startup_64 |<----| efi_main |<--------------+ - * +------------+ +----------+ + * +------------------+ | | +------+----------------+ | + * | efi32_stub_entry |---->| | | | + * +------------------+ +------------+ | | + * V | + * +------------+ +----------------+ | + * | startup_64 |<----| efi_stub_entry |<--------+ + * +------------+ +----------------+ */ SYM_FUNC_START(startup_64_mixed_mode) lea efi32_boot_args(%rip), %rdx mov 0(%rdx), %edi mov 4(%rdx), %esi +#ifdef CONFIG_EFI_HANDOVER_PROTOCOL mov 8(%rdx), %edx // saved bootparams pointer test %edx, %edx - jnz efi64_stub_entry + jnz efi_stub_entry +#endif /* * efi_pe_entry uses MS calling convention, which requires 32 bytes of * shadow space on the stack even if all arguments are passed in @@ -138,6 +140,28 @@ SYM_FUNC_START(__efi64_thunk) SYM_FUNC_END(__efi64_thunk) .code32 +#ifdef CONFIG_EFI_HANDOVER_PROTOCOL +SYM_FUNC_START(efi32_stub_entry) + call 1f +1: popl %ecx + + /* Clear BSS */ + xorl %eax, %eax + leal (_bss - 1b)(%ecx), %edi + leal (_ebss - 1b)(%ecx), %ecx + subl %edi, %ecx + shrl $2, %ecx + cld + rep stosl + + add $0x4, %esp /* Discard return address */ + popl %ecx + popl %edx + popl %esi + jmp efi32_entry +SYM_FUNC_END(efi32_stub_entry) +#endif + /* * EFI service pointer must be in %edi. * @@ -218,7 +242,7 @@ SYM_FUNC_END(efi_enter32) * stub may still exit and return to the firmware using the Exit() EFI boot * service.] */ -SYM_FUNC_START(efi32_entry) +SYM_FUNC_START_LOCAL(efi32_entry) call 1f 1: pop %ebx @@ -245,10 +269,6 @@ SYM_FUNC_START(efi32_entry) jmp startup_32 SYM_FUNC_END(efi32_entry) -#define ST32_boottime 60 // offsetof(efi_system_table_32_t, boottime) -#define BS32_handle_protocol 88 // offsetof(efi_boot_services_32_t, handle_protocol) -#define LI32_image_base 32 // offsetof(efi_loaded_image_32_t, image_base) - /* * efi_status_t efi32_pe_entry(efi_handle_t image_handle, * efi_system_table_32_t *sys_table) @@ -256,8 +276,6 @@ SYM_FUNC_END(efi32_entry) SYM_FUNC_START(efi32_pe_entry) pushl %ebp movl %esp, %ebp - pushl %eax // dummy push to allocate loaded_image - pushl %ebx // save callee-save registers pushl %edi @@ -266,48 +284,8 @@ SYM_FUNC_START(efi32_pe_entry) movl $0x80000003, %eax // EFI_UNSUPPORTED jnz 2f - call 1f -1: pop %ebx - - /* Get the loaded image protocol pointer from the image handle */ - leal -4(%ebp), %eax - pushl %eax // &loaded_image - leal (loaded_image_proto - 1b)(%ebx), %eax - pushl %eax // pass the GUID address - pushl 8(%ebp) // pass the image handle - - /* - * Note the alignment of the stack frame. - * sys_table - * handle <-- 16-byte aligned on entry by ABI - * return address - * frame pointer - * loaded_image <-- local variable - * saved %ebx <-- 16-byte aligned here - * saved %edi - * &loaded_image - * &loaded_image_proto - * handle <-- 16-byte aligned for call to handle_protocol - */ - - movl 12(%ebp), %eax // sys_table - movl ST32_boottime(%eax), %eax // sys_table->boottime - call *BS32_handle_protocol(%eax) // sys_table->boottime->handle_protocol - addl $12, %esp // restore argument space - testl %eax, %eax - jnz 2f - movl 8(%ebp), %ecx // image_handle movl 12(%ebp), %edx // sys_table - movl -4(%ebp), %esi // loaded_image - movl LI32_image_base(%esi), %esi // loaded_image->image_base - leal (startup_32 - 1b)(%ebx), %ebp // runtime address of startup_32 - /* - * We need to set the image_offset variable here since startup_32() will - * use it before we get to the 64-bit efi_pe_entry() in C code. - */ - subl %esi, %ebp // calculate image_offset - movl %ebp, (image_offset - 1b)(%ebx) // save image_offset xorl %esi, %esi jmp efi32_entry // pass %ecx, %edx, %esi // no other registers remain live @@ -318,14 +296,13 @@ SYM_FUNC_START(efi32_pe_entry) RET SYM_FUNC_END(efi32_pe_entry) - .section ".rodata" - /* EFI loaded image protocol GUID */ - .balign 4 -SYM_DATA_START_LOCAL(loaded_image_proto) - .long 0x5b1b31a1 - .word 0x9562, 0x11d2 - .byte 0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b -SYM_DATA_END(loaded_image_proto) +#ifdef CONFIG_EFI_HANDOVER_PROTOCOL + .org efi32_stub_entry + 0x200 + .code64 +SYM_FUNC_START_NOALIGN(efi64_stub_entry) + jmp efi_handover_entry +SYM_FUNC_END(efi64_stub_entry) +#endif .data .balign 8 diff --git a/arch/x86/boot/compressed/error.c b/arch/x86/boot/compressed/error.c index 5313c5cb2b80..19a8251de506 100644 --- a/arch/x86/boot/compressed/error.c +++ b/arch/x86/boot/compressed/error.c @@ -7,7 +7,7 @@ #include "misc.h" #include "error.h" -void warn(char *m) +void warn(const char *m) { error_putstr("\n\n"); error_putstr(m); diff --git a/arch/x86/boot/compressed/error.h b/arch/x86/boot/compressed/error.h index 86fe33b93715..31f9e080d61a 100644 --- a/arch/x86/boot/compressed/error.h +++ b/arch/x86/boot/compressed/error.h @@ -4,7 +4,7 @@ #include <linux/compiler.h> -void warn(char *m); +void warn(const char *m); void error(char *m) __noreturn; void panic(const char *fmt, ...) __noreturn __cold; diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 987ae727cf9f..1cfe9802a42f 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -84,19 +84,6 @@ SYM_FUNC_START(startup_32) #ifdef CONFIG_RELOCATABLE leal startup_32@GOTOFF(%edx), %ebx - -#ifdef CONFIG_EFI_STUB -/* - * If we were loaded via the EFI LoadImage service, startup_32() will be at an - * offset to the start of the space allocated for the image. efi_pe_entry() will - * set up image_offset to tell us where the image actually starts, so that we - * can use the full available buffer. - * image_offset = startup_32 - image_base - * Otherwise image_offset will be zero and has no effect on the calculations. - */ - subl image_offset@GOTOFF(%edx), %ebx -#endif - movl BP_kernel_alignment(%esi), %eax decl %eax addl %eax, %ebx @@ -150,17 +137,6 @@ SYM_FUNC_START(startup_32) jmp *%eax SYM_FUNC_END(startup_32) -#ifdef CONFIG_EFI_STUB -SYM_FUNC_START(efi32_stub_entry) - add $0x4, %esp - movl 8(%esp), %esi /* save boot_params pointer */ - call efi_main - /* efi_main returns the possibly relocated address of startup_32 */ - jmp *%eax -SYM_FUNC_END(efi32_stub_entry) -SYM_FUNC_ALIAS(efi_stub_entry, efi32_stub_entry) -#endif - .text SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) @@ -179,13 +155,7 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) */ /* push arguments for extract_kernel: */ - pushl output_len@GOTOFF(%ebx) /* decompressed length, end of relocs */ pushl %ebp /* output address */ - pushl input_len@GOTOFF(%ebx) /* input_len */ - leal input_data@GOTOFF(%ebx), %eax - pushl %eax /* input_data */ - leal boot_heap@GOTOFF(%ebx), %eax - pushl %eax /* heap area */ pushl %esi /* real mode pointer */ call extract_kernel /* returns kernel entry point in %eax */ addl $24, %esp @@ -213,8 +183,6 @@ SYM_DATA_END_LABEL(gdt, SYM_L_LOCAL, gdt_end) */ .bss .balign 4 -boot_heap: - .fill BOOT_HEAP_SIZE, 1, 0 boot_stack: .fill BOOT_STACK_SIZE, 1, 0 boot_stack_end: diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 03c4328a88cb..bf4a10a5794f 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -146,19 +146,6 @@ SYM_FUNC_START(startup_32) #ifdef CONFIG_RELOCATABLE movl %ebp, %ebx - -#ifdef CONFIG_EFI_STUB -/* - * If we were loaded via the EFI LoadImage service, startup_32 will be at an - * offset to the start of the space allocated for the image. efi_pe_entry will - * set up image_offset to tell us where the image actually starts, so that we - * can use the full available buffer. - * image_offset = startup_32 - image_base - * Otherwise image_offset will be zero and has no effect on the calculations. - */ - subl rva(image_offset)(%ebp), %ebx -#endif - movl BP_kernel_alignment(%esi), %eax decl %eax addl %eax, %ebx @@ -294,17 +281,6 @@ SYM_FUNC_START(startup_32) lret SYM_FUNC_END(startup_32) -#if IS_ENABLED(CONFIG_EFI_MIXED) && IS_ENABLED(CONFIG_EFI_HANDOVER_PROTOCOL) - .org 0x190 -SYM_FUNC_START(efi32_stub_entry) - add $0x4, %esp /* Discard return address */ - popl %ecx - popl %edx - popl %esi - jmp efi32_entry -SYM_FUNC_END(efi32_stub_entry) -#endif - .code64 .org 0x200 SYM_CODE_START(startup_64) @@ -346,20 +322,6 @@ SYM_CODE_START(startup_64) /* Start with the delta to where the kernel will run at. */ #ifdef CONFIG_RELOCATABLE leaq startup_32(%rip) /* - $startup_32 */, %rbp - -#ifdef CONFIG_EFI_STUB -/* - * If we were loaded via the EFI LoadImage service, startup_32 will be at an - * offset to the start of the space allocated for the image. efi_pe_entry will - * set up image_offset to tell us where the image actually starts, so that we - * can use the full available buffer. - * image_offset = startup_32 - image_base - * Otherwise image_offset will be zero and has no effect on the calculations. - */ - movl image_offset(%rip), %eax - subq %rax, %rbp -#endif - movl BP_kernel_alignment(%rsi), %eax decl %eax addq %rax, %rbp @@ -398,10 +360,6 @@ SYM_CODE_START(startup_64) * For the trampoline, we need the top page table to reside in lower * memory as we don't have a way to load 64-bit values into CR3 in * 32-bit mode. - * - * We go though the trampoline even if we don't have to: if we're - * already in a desired paging mode. This way the trampoline code gets - * tested on every boot. */ /* Make sure we have GDT with 32-bit code segment */ @@ -416,10 +374,14 @@ SYM_CODE_START(startup_64) lretq .Lon_kernel_cs: + /* + * RSI holds a pointer to a boot_params structure provided by the + * loader, and this needs to be preserved across C function calls. So + * move it into a callee saved register. + */ + movq %rsi, %r15 - pushq %rsi call load_stage1_idt - popq %rsi #ifdef CONFIG_AMD_MEM_ENCRYPT /* @@ -430,63 +392,24 @@ SYM_CODE_START(startup_64) * CPUID instructions being issued, so go ahead and do that now via * sev_enable(), which will also handle the rest of the SEV-related * detection/setup to ensure that has been done in advance of any dependent - * code. + * code. Pass the boot_params pointer as the first argument. */ - pushq %rsi - movq %rsi, %rdi /* real mode address */ + movq %r15, %rdi call sev_enable - popq %rsi #endif /* - * paging_prepare() sets up the trampoline and checks if we need to - * enable 5-level paging. + * configure_5level_paging() updates the number of paging levels using + * a trampoline in 32-bit addressable memory if the current number does + * not match the desired number. * - * paging_prepare() returns a two-quadword structure which lands - * into RDX:RAX: - * - Address of the trampoline is returned in RAX. - * - Non zero RDX means trampoline needs to enable 5-level - * paging. - * - * RSI holds real mode data and needs to be preserved across - * this function call. - */ - pushq %rsi - movq %rsi, %rdi /* real mode address */ - call paging_prepare - popq %rsi - - /* Save the trampoline address in RCX */ - movq %rax, %rcx - - /* - * Load the address of trampoline_return() into RDI. - * It will be used by the trampoline to return to the main code. + * Pass the boot_params pointer as the first argument. The second + * argument is the relocated address of the page table to use instead + * of the page table in trampoline memory (if required). */ - leaq trampoline_return(%rip), %rdi - - /* Switch to compatibility mode (CS.L = 0 CS.D = 1) via far return */ - pushq $__KERNEL32_CS - leaq TRAMPOLINE_32BIT_CODE_OFFSET(%rax), %rax - pushq %rax - lretq -trampoline_return: - /* Restore the stack, the 32-bit trampoline uses its own stack */ - leaq rva(boot_stack_end)(%rbx), %rsp - - /* - * cleanup_trampoline() would restore trampoline memory. - * - * RDI is address of the page table to use instead of page table - * in trampoline memory (if required). - * - * RSI holds real mode data and needs to be preserved across - * this function call. - */ - pushq %rsi - leaq rva(top_pgtable)(%rbx), %rdi - call cleanup_trampoline - popq %rsi + movq %r15, %rdi + leaq rva(top_pgtable)(%rbx), %rsi + call configure_5level_paging /* Zero EFLAGS */ pushq $0 @@ -496,7 +419,6 @@ trampoline_return: * Copy the compressed kernel to the end of our buffer * where decompression in place becomes safe. */ - pushq %rsi leaq (_bss-8)(%rip), %rsi leaq rva(_bss-8)(%rbx), %rdi movl $(_bss - startup_32), %ecx @@ -504,7 +426,6 @@ trampoline_return: std rep movsq cld - popq %rsi /* * The GDT may get overwritten either during the copy we just did or @@ -523,21 +444,6 @@ trampoline_return: jmp *%rax SYM_CODE_END(startup_64) -#ifdef CONFIG_EFI_STUB -#ifdef CONFIG_EFI_HANDOVER_PROTOCOL - .org 0x390 -#endif -SYM_FUNC_START(efi64_stub_entry) - and $~0xf, %rsp /* realign the stack */ - movq %rdx, %rbx /* save boot_params pointer */ - call efi_main - movq %rbx,%rsi - leaq rva(startup_64)(%rax), %rax - jmp *%rax -SYM_FUNC_END(efi64_stub_entry) -SYM_FUNC_ALIAS(efi_stub_entry, efi64_stub_entry) -#endif - .text SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) @@ -551,128 +457,122 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) shrq $3, %rcx rep stosq - pushq %rsi call load_stage2_idt /* Pass boot_params to initialize_identity_maps() */ - movq (%rsp), %rdi + movq %r15, %rdi call initialize_identity_maps - popq %rsi /* * Do the extraction, and jump to the new kernel.. */ - pushq %rsi /* Save the real mode argument */ - movq %rsi, %rdi /* real mode address */ - leaq boot_heap(%rip), %rsi /* malloc area for uncompression */ - leaq input_data(%rip), %rdx /* input_data */ - movl input_len(%rip), %ecx /* input_len */ - movq %rbp, %r8 /* output target address */ - movl output_len(%rip), %r9d /* decompressed length, end of relocs */ + /* pass struct boot_params pointer and output target address */ + movq %r15, %rdi + movq %rbp, %rsi call extract_kernel /* returns kernel entry point in %rax */ - popq %rsi /* * Jump to the decompressed kernel. */ + movq %r15, %rsi jmp *%rax SYM_FUNC_END(.Lrelocated) - .code32 /* - * This is the 32-bit trampoline that will be copied over to low memory. + * This is the 32-bit trampoline that will be copied over to low memory. It + * will be called using the ordinary 64-bit calling convention from code + * running in 64-bit mode. * - * RDI contains the return address (might be above 4G). - * ECX contains the base address of the trampoline memory. - * Non zero RDX means trampoline needs to enable 5-level paging. + * Return address is at the top of the stack (might be above 4G). + * The first argument (EDI) contains the address of the temporary PGD level + * page table in 32-bit addressable memory which will be programmed into + * register CR3. */ + .section ".rodata", "a", @progbits SYM_CODE_START(trampoline_32bit_src) - /* Set up data and stack segments */ - movl $__KERNEL_DS, %eax - movl %eax, %ds - movl %eax, %ss + /* + * Preserve callee save 64-bit registers on the stack: this is + * necessary because the architecture does not guarantee that GPRs will + * retain their full 64-bit values across a 32-bit mode switch. + */ + pushq %r15 + pushq %r14 + pushq %r13 + pushq %r12 + pushq %rbp + pushq %rbx + + /* Preserve top half of RSP in a legacy mode GPR to avoid truncation */ + movq %rsp, %rbx + shrq $32, %rbx + + /* Switch to compatibility mode (CS.L = 0 CS.D = 1) via far return */ + pushq $__KERNEL32_CS + leaq 0f(%rip), %rax + pushq %rax + lretq - /* Set up new stack */ - leal TRAMPOLINE_32BIT_STACK_END(%ecx), %esp + /* + * The 32-bit code below will do a far jump back to long mode and end + * up here after reconfiguring the number of paging levels. First, the + * stack pointer needs to be restored to its full 64-bit value before + * the callee save register contents can be popped from the stack. + */ +.Lret: + shlq $32, %rbx + orq %rbx, %rsp + + /* Restore the preserved 64-bit registers */ + popq %rbx + popq %rbp + popq %r12 + popq %r13 + popq %r14 + popq %r15 + retq + .code32 +0: /* Disable paging */ movl %cr0, %eax btrl $X86_CR0_PG_BIT, %eax movl %eax, %cr0 - /* Check what paging mode we want to be in after the trampoline */ - testl %edx, %edx - jz 1f - - /* We want 5-level paging: don't touch CR3 if it already points to 5-level page tables */ - movl %cr4, %eax - testl $X86_CR4_LA57, %eax - jnz 3f - jmp 2f -1: - /* We want 4-level paging: don't touch CR3 if it already points to 4-level page tables */ - movl %cr4, %eax - testl $X86_CR4_LA57, %eax - jz 3f -2: /* Point CR3 to the trampoline's new top level page table */ - leal TRAMPOLINE_32BIT_PGTABLE_OFFSET(%ecx), %eax - movl %eax, %cr3 -3: + movl %edi, %cr3 + /* Set EFER.LME=1 as a precaution in case hypervsior pulls the rug */ - pushl %ecx - pushl %edx movl $MSR_EFER, %ecx rdmsr btsl $_EFER_LME, %eax /* Avoid writing EFER if no change was made (for TDX guest) */ jc 1f wrmsr -1: popl %edx - popl %ecx - -#ifdef CONFIG_X86_MCE - /* - * Preserve CR4.MCE if the kernel will enable #MC support. - * Clearing MCE may fault in some environments (that also force #MC - * support). Any machine check that occurs before #MC support is fully - * configured will crash the system regardless of the CR4.MCE value set - * here. - */ - movl %cr4, %eax - andl $X86_CR4_MCE, %eax -#else - movl $0, %eax -#endif - - /* Enable PAE and LA57 (if required) paging modes */ - orl $X86_CR4_PAE, %eax - testl %edx, %edx - jz 1f - orl $X86_CR4_LA57, %eax 1: + /* Toggle CR4.LA57 */ + movl %cr4, %eax + btcl $X86_CR4_LA57_BIT, %eax movl %eax, %cr4 - /* Calculate address of paging_enabled() once we are executing in the trampoline */ - leal .Lpaging_enabled - trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_OFFSET(%ecx), %eax - - /* Prepare the stack for far return to Long Mode */ - pushl $__KERNEL_CS - pushl %eax - /* Enable paging again. */ movl %cr0, %eax btsl $X86_CR0_PG_BIT, %eax movl %eax, %cr0 - lret + /* + * Return to the 64-bit calling code using LJMP rather than LRET, to + * avoid the need for a 32-bit addressable stack. The destination + * address will be adjusted after the template code is copied into a + * 32-bit addressable buffer. + */ +.Ljmp: ljmpl $__KERNEL_CS, $(.Lret - trampoline_32bit_src) SYM_CODE_END(trampoline_32bit_src) - .code64 -SYM_FUNC_START_LOCAL_NOALIGN(.Lpaging_enabled) - /* Return from the trampoline */ - jmp *%rdi -SYM_FUNC_END(.Lpaging_enabled) +/* + * This symbol is placed right after trampoline_32bit_src() so its address can + * be used to infer the size of the trampoline code. + */ +SYM_DATA(trampoline_ljmp_imm_offset, .word .Ljmp + 1 - trampoline_32bit_src) /* * The trampoline code has a size limit. @@ -681,7 +581,7 @@ SYM_FUNC_END(.Lpaging_enabled) */ .org trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_SIZE - .code32 + .text SYM_FUNC_START_LOCAL_NOALIGN(.Lno_longmode) /* This isn't an x86-64 CPU, so hang intentionally, we cannot continue */ 1: @@ -726,8 +626,6 @@ SYM_DATA_END_LABEL(boot_idt, SYM_L_GLOBAL, boot_idt_end) */ .bss .balign 4 -SYM_DATA_LOCAL(boot_heap, .fill BOOT_HEAP_SIZE, 1, 0) - SYM_DATA_START_LOCAL(boot_stack) .fill BOOT_STACK_SIZE, 1, 0 .balign 16 diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 94b7abcf624b..f711f2a85862 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -330,6 +330,33 @@ static size_t parse_elf(void *output) return ehdr.e_entry - LOAD_PHYSICAL_ADDR; } +const unsigned long kernel_total_size = VO__end - VO__text; + +static u8 boot_heap[BOOT_HEAP_SIZE] __aligned(4); + +extern unsigned char input_data[]; +extern unsigned int input_len, output_len; + +unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr, + void (*error)(char *x)) +{ + unsigned long entry; + + if (!free_mem_ptr) { + free_mem_ptr = (unsigned long)boot_heap; + free_mem_end_ptr = (unsigned long)boot_heap + sizeof(boot_heap); + } + + if (__decompress(input_data, input_len, NULL, NULL, outbuf, output_len, + NULL, error) < 0) + return ULONG_MAX; + + entry = parse_elf(outbuf); + handle_relocations(outbuf, output_len, virt_addr); + + return entry; +} + /* * The compressed kernel image (ZO), has been moved so that its position * is against the end of the buffer used to hold the uncompressed kernel @@ -347,14 +374,10 @@ static size_t parse_elf(void *output) * |-------uncompressed kernel image---------| * */ -asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, - unsigned char *input_data, - unsigned long input_len, - unsigned char *output, - unsigned long output_len) +asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output) { - const unsigned long kernel_total_size = VO__end - VO__text; unsigned long virt_addr = LOAD_PHYSICAL_ADDR; + memptr heap = (memptr)boot_heap; unsigned long needed_size; size_t entry_offset; @@ -412,7 +435,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, * entries. This ensures the full mapped area is usable RAM * and doesn't include any reserved areas. */ - needed_size = max(output_len, kernel_total_size); + needed_size = max_t(unsigned long, output_len, kernel_total_size); #ifdef CONFIG_X86_64 needed_size = ALIGN(needed_size, MIN_KERNEL_ALIGN); #endif @@ -443,7 +466,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, #ifdef CONFIG_X86_64 if (heap > 0x3fffffffffffUL) error("Destination address too large"); - if (virt_addr + max(output_len, kernel_total_size) > KERNEL_IMAGE_SIZE) + if (virt_addr + needed_size > KERNEL_IMAGE_SIZE) error("Destination virtual address is beyond the kernel mapping area"); #else if (heap > ((-__PAGE_OFFSET-(128<<20)-1) & 0x7fffffff)) @@ -461,10 +484,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, accept_memory(__pa(output), __pa(output) + needed_size); } - __decompress(input_data, input_len, NULL, NULL, output, output_len, - NULL, error); - entry_offset = parse_elf(output); - handle_relocations(output, output_len, virt_addr); + entry_offset = decompress_kernel(output, virt_addr, error); debug_putstr("done.\nBooting the kernel (entry_offset: 0x"); debug_puthex(entry_offset); diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 964fe903a1cd..cc70d3fb9049 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -179,9 +179,7 @@ static inline int count_immovable_mem_regions(void) { return 0; } #endif /* ident_map_64.c */ -#ifdef CONFIG_X86_5LEVEL extern unsigned int __pgtable_l5_enabled, pgdir_shift, ptrs_per_p4d; -#endif extern void kernel_add_identity_map(unsigned long start, unsigned long end); /* Used by PAGE_KERN* macros: */ diff --git a/arch/x86/boot/compressed/pgtable.h b/arch/x86/boot/compressed/pgtable.h index cc9b2529a086..6d595abe06b3 100644 --- a/arch/x86/boot/compressed/pgtable.h +++ b/arch/x86/boot/compressed/pgtable.h @@ -3,18 +3,16 @@ #define TRAMPOLINE_32BIT_SIZE (2 * PAGE_SIZE) -#define TRAMPOLINE_32BIT_PGTABLE_OFFSET 0 - #define TRAMPOLINE_32BIT_CODE_OFFSET PAGE_SIZE -#define TRAMPOLINE_32BIT_CODE_SIZE 0x80 - -#define TRAMPOLINE_32BIT_STACK_END TRAMPOLINE_32BIT_SIZE +#define TRAMPOLINE_32BIT_CODE_SIZE 0xA0 #ifndef __ASSEMBLER__ extern unsigned long *trampoline_32bit; -extern void trampoline_32bit_src(void *return_ptr); +extern void trampoline_32bit_src(void *trampoline, bool enable_5lvl); + +extern const u16 trampoline_ljmp_imm_offset; #endif /* __ASSEMBLER__ */ #endif /* BOOT_COMPRESSED_PAGETABLE_H */ diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c index 2ac12ff4111b..7939eb6e6ce9 100644 --- a/arch/x86/boot/compressed/pgtable_64.c +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -16,11 +16,6 @@ unsigned int __section(".data") pgdir_shift = 39; unsigned int __section(".data") ptrs_per_p4d = 1; #endif -struct paging_config { - unsigned long trampoline_start; - unsigned long l5_required; -}; - /* Buffer to preserve trampoline memory */ static char trampoline_save[TRAMPOLINE_32BIT_SIZE]; @@ -29,7 +24,7 @@ static char trampoline_save[TRAMPOLINE_32BIT_SIZE]; * purposes. * * Avoid putting the pointer into .bss as it will be cleared between - * paging_prepare() and extract_kernel(). + * configure_5level_paging() and extract_kernel(). */ unsigned long *trampoline_32bit __section(".data"); @@ -106,12 +101,13 @@ static unsigned long find_trampoline_placement(void) return bios_start - TRAMPOLINE_32BIT_SIZE; } -struct paging_config paging_prepare(void *rmode) +asmlinkage void configure_5level_paging(struct boot_params *bp, void *pgtable) { - struct paging_config paging_config = {}; + void (*toggle_la57)(void *cr3); + bool l5_required = false; /* Initialize boot_params. Required for cmdline_find_option_bool(). */ - boot_params = rmode; + boot_params = bp; /* * Check if LA57 is desired and supported. @@ -129,12 +125,22 @@ struct paging_config paging_prepare(void *rmode) !cmdline_find_option_bool("no5lvl") && native_cpuid_eax(0) >= 7 && (native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)))) { - paging_config.l5_required = 1; + l5_required = true; + + /* Initialize variables for 5-level paging */ + __pgtable_l5_enabled = 1; + pgdir_shift = 48; + ptrs_per_p4d = 512; } - paging_config.trampoline_start = find_trampoline_placement(); + /* + * The trampoline will not be used if the paging mode is already set to + * the desired one. + */ + if (l5_required == !!(native_read_cr4() & X86_CR4_LA57)) + return; - trampoline_32bit = (unsigned long *)paging_config.trampoline_start; + trampoline_32bit = (unsigned long *)find_trampoline_placement(); /* Preserve trampoline memory */ memcpy(trampoline_save, trampoline_32bit, TRAMPOLINE_32BIT_SIZE); @@ -143,32 +149,32 @@ struct paging_config paging_prepare(void *rmode) memset(trampoline_32bit, 0, TRAMPOLINE_32BIT_SIZE); /* Copy trampoline code in place */ - memcpy(trampoline_32bit + TRAMPOLINE_32BIT_CODE_OFFSET / sizeof(unsigned long), + toggle_la57 = memcpy(trampoline_32bit + + TRAMPOLINE_32BIT_CODE_OFFSET / sizeof(unsigned long), &trampoline_32bit_src, TRAMPOLINE_32BIT_CODE_SIZE); /* + * Avoid the need for a stack in the 32-bit trampoline code, by using + * LJMP rather than LRET to return back to long mode. LJMP takes an + * immediate absolute address, which needs to be adjusted based on the + * placement of the trampoline. + */ + *(u32 *)((u8 *)toggle_la57 + trampoline_ljmp_imm_offset) += + (unsigned long)toggle_la57; + + /* * The code below prepares page table in trampoline memory. * * The new page table will be used by trampoline code for switching * from 4- to 5-level paging or vice versa. - * - * If switching is not required, the page table is unused: trampoline - * code wouldn't touch CR3. - */ - - /* - * We are not going to use the page table in trampoline memory if we - * are already in the desired paging mode. */ - if (paging_config.l5_required == !!(native_read_cr4() & X86_CR4_LA57)) - goto out; - if (paging_config.l5_required) { + if (l5_required) { /* * For 4- to 5-level paging transition, set up current CR3 as * the first and the only entry in a new top-level page table. */ - trampoline_32bit[TRAMPOLINE_32BIT_PGTABLE_OFFSET] = __native_read_cr3() | _PAGE_TABLE_NOENC; + *trampoline_32bit = __native_read_cr3() | _PAGE_TABLE_NOENC; } else { unsigned long src; @@ -181,38 +187,17 @@ struct paging_config paging_prepare(void *rmode) * may be above 4G. */ src = *(unsigned long *)__native_read_cr3() & PAGE_MASK; - memcpy(trampoline_32bit + TRAMPOLINE_32BIT_PGTABLE_OFFSET / sizeof(unsigned long), - (void *)src, PAGE_SIZE); + memcpy(trampoline_32bit, (void *)src, PAGE_SIZE); } -out: - return paging_config; -} - -void cleanup_trampoline(void *pgtable) -{ - void *trampoline_pgtable; - - trampoline_pgtable = trampoline_32bit + TRAMPOLINE_32BIT_PGTABLE_OFFSET / sizeof(unsigned long); + toggle_la57(trampoline_32bit); /* - * Move the top level page table out of trampoline memory, - * if it's there. + * Move the top level page table out of trampoline memory. */ - if ((void *)__native_read_cr3() == trampoline_pgtable) { - memcpy(pgtable, trampoline_pgtable, PAGE_SIZE); - native_write_cr3((unsigned long)pgtable); - } + memcpy(pgtable, trampoline_32bit, PAGE_SIZE); + native_write_cr3((unsigned long)pgtable); /* Restore trampoline memory */ memcpy(trampoline_32bit, trampoline_save, TRAMPOLINE_32BIT_SIZE); - - /* Initialize variables for 5-level paging */ -#ifdef CONFIG_X86_5LEVEL - if (__read_cr4() & X86_CR4_LA57) { - __pgtable_l5_enabled = 1; - pgdir_shift = 48; - ptrs_per_p4d = 512; - } -#endif } diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index c3e343bd4760..dc8c876fbd8f 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -365,22 +365,27 @@ static void enforce_vmpl0(void) * by the guest kernel. As and when a new feature is implemented in the * guest kernel, a corresponding bit should be added to the mask. */ -#define SNP_FEATURES_PRESENT (0) +#define SNP_FEATURES_PRESENT MSR_AMD64_SNP_DEBUG_SWAP + +u64 snp_get_unsupported_features(u64 status) +{ + if (!(status & MSR_AMD64_SEV_SNP_ENABLED)) + return 0; + + return status & SNP_FEATURES_IMPL_REQ & ~SNP_FEATURES_PRESENT; +} void snp_check_features(void) { u64 unsupported; - if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) - return; - /* * Terminate the boot if hypervisor has enabled any feature lacking * guest side implementation. Pass on the unsupported features mask through * EXIT_INFO_2 of the GHCB protocol so that those features can be reported * as part of the guest boot failure. */ - unsupported = sev_status & SNP_FEATURES_IMPL_REQ & ~SNP_FEATURES_PRESENT; + unsupported = snp_get_unsupported_features(sev_status); if (unsupported) { if (ghcb_version < 2 || (!boot_ghcb && !early_setup_ghcb())) sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); @@ -390,35 +395,22 @@ void snp_check_features(void) } } -void sev_enable(struct boot_params *bp) +/* + * sev_check_cpu_support - Check for SEV support in the CPU capabilities + * + * Returns < 0 if SEV is not supported, otherwise the position of the + * encryption bit in the page table descriptors. + */ +static int sev_check_cpu_support(void) { unsigned int eax, ebx, ecx, edx; - struct msr m; - bool snp; - - /* - * bp->cc_blob_address should only be set by boot/compressed kernel. - * Initialize it to 0 to ensure that uninitialized values from - * buggy bootloaders aren't propagated. - */ - if (bp) - bp->cc_blob_address = 0; - - /* - * Do an initial SEV capability check before snp_init() which - * loads the CPUID page and the same checks afterwards are done - * without the hypervisor and are trustworthy. - * - * If the HV fakes SEV support, the guest will crash'n'burn - * which is good enough. - */ /* Check for the SME/SEV support leaf */ eax = 0x80000000; ecx = 0; native_cpuid(&eax, &ebx, &ecx, &edx); if (eax < 0x8000001f) - return; + return -ENODEV; /* * Check for the SME/SEV feature: @@ -433,6 +425,35 @@ void sev_enable(struct boot_params *bp) native_cpuid(&eax, &ebx, &ecx, &edx); /* Check whether SEV is supported */ if (!(eax & BIT(1))) + return -ENODEV; + + return ebx & 0x3f; +} + +void sev_enable(struct boot_params *bp) +{ + struct msr m; + int bitpos; + bool snp; + + /* + * bp->cc_blob_address should only be set by boot/compressed kernel. + * Initialize it to 0 to ensure that uninitialized values from + * buggy bootloaders aren't propagated. + */ + if (bp) + bp->cc_blob_address = 0; + + /* + * Do an initial SEV capability check before snp_init() which + * loads the CPUID page and the same checks afterwards are done + * without the hypervisor and are trustworthy. + * + * If the HV fakes SEV support, the guest will crash'n'burn + * which is good enough. + */ + + if (sev_check_cpu_support() < 0) return; /* @@ -443,26 +464,8 @@ void sev_enable(struct boot_params *bp) /* Now repeat the checks with the SNP CPUID table. */ - /* Recheck the SME/SEV support leaf */ - eax = 0x80000000; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); - if (eax < 0x8000001f) - return; - - /* - * Recheck for the SME/SEV feature: - * CPUID Fn8000_001F[EAX] - * - Bit 0 - Secure Memory Encryption support - * - Bit 1 - Secure Encrypted Virtualization support - * CPUID Fn8000_001F[EBX] - * - Bits 5:0 - Pagetable bit position used to indicate encryption - */ - eax = 0x8000001f; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); - /* Check whether SEV is supported */ - if (!(eax & BIT(1))) { + bitpos = sev_check_cpu_support(); + if (bitpos < 0) { if (snp) error("SEV-SNP support indicated by CC blob, but not CPUID."); return; @@ -494,7 +497,24 @@ void sev_enable(struct boot_params *bp) if (snp && !(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) error("SEV-SNP supported indicated by CC blob, but not SEV status MSR."); - sme_me_mask = BIT_ULL(ebx & 0x3f); + sme_me_mask = BIT_ULL(bitpos); +} + +/* + * sev_get_status - Retrieve the SEV status mask + * + * Returns 0 if the CPU is not SEV capable, otherwise the value of the + * AMD64_SEV MSR. + */ +u64 sev_get_status(void) +{ + struct msr m; + + if (sev_check_cpu_support() < 0) + return 0; + + boot_rdmsr(MSR_AMD64_SEV, &m); + return m.q; } /* Search for Confidential Computing blob in the EFI config table. */ diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 75a343f10e58..1b411bbf3cb0 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -33,7 +33,6 @@ CONFIG_HYPERVISOR_GUEST=y CONFIG_PARAVIRT=y CONFIG_NR_CPUS=8 CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS=y -CONFIG_MICROCODE_AMD=y CONFIG_X86_MSR=y CONFIG_X86_CPUID=y CONFIG_X86_CHECK_BIOS_CORRUPTION=y diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 0902518e9b93..409e9182bd29 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -31,7 +31,6 @@ CONFIG_SMP=y CONFIG_HYPERVISOR_GUEST=y CONFIG_PARAVIRT=y CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS=y -CONFIG_MICROCODE_AMD=y CONFIG_X86_MSR=y CONFIG_X86_CPUID=y CONFIG_NUMA=y diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index bc0a3c941b35..2d0b1bd866ea 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -456,3 +456,4 @@ 449 i386 futex_waitv sys_futex_waitv 450 i386 set_mempolicy_home_node sys_set_mempolicy_home_node 451 i386 cachestat sys_cachestat +452 i386 fchmodat2 sys_fchmodat2 diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 227538b0ce80..814768249eae 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -373,6 +373,7 @@ 449 common futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node 451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 # # Due to a historical design error, certain syscalls are numbered differently diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 371014802191..6911c5399d02 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -156,8 +156,8 @@ perf_event_try_update(struct perf_event *event, u64 new_raw_count, int width) * count to the generic event atomically: */ prev_raw_count = local64_read(&hwc->prev_count); - if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, - new_raw_count) != prev_raw_count) + if (!local64_try_cmpxchg(&hwc->prev_count, + &prev_raw_count, new_raw_count)) return 0; /* @@ -247,11 +247,33 @@ int forward_event_to_ibs(struct perf_event *event) return -ENOENT; } +/* + * Grouping of IBS events is not possible since IBS can have only + * one event active at any point in time. + */ +static int validate_group(struct perf_event *event) +{ + struct perf_event *sibling; + + if (event->group_leader == event) + return 0; + + if (event->group_leader->pmu == event->pmu) + return -EINVAL; + + for_each_sibling_event(sibling, event->group_leader) { + if (sibling->pmu == event->pmu) + return -EINVAL; + } + return 0; +} + static int perf_ibs_init(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; struct perf_ibs *perf_ibs; u64 max_cnt, config; + int ret; perf_ibs = get_ibs_pmu(event->attr.type); if (!perf_ibs) @@ -265,6 +287,10 @@ static int perf_ibs_init(struct perf_event *event) if (config & ~perf_ibs->config_mask) return -EINVAL; + ret = validate_group(event); + if (ret) + return ret; + if (hwc->sample_period) { if (config & perf_ibs->cnt_mask) /* raw max_cnt may not be set */ @@ -702,38 +728,63 @@ static u8 perf_ibs_data_src(union ibs_op_data2 *op_data2) return op_data2->data_src_lo; } -static void perf_ibs_get_mem_lvl(union ibs_op_data2 *op_data2, - union ibs_op_data3 *op_data3, - struct perf_sample_data *data) +#define L(x) (PERF_MEM_S(LVL, x) | PERF_MEM_S(LVL, HIT)) +#define LN(x) PERF_MEM_S(LVLNUM, x) +#define REM PERF_MEM_S(REMOTE, REMOTE) +#define HOPS(x) PERF_MEM_S(HOPS, x) + +static u64 g_data_src[8] = { + [IBS_DATA_SRC_LOC_CACHE] = L(L3) | L(REM_CCE1) | LN(ANY_CACHE) | HOPS(0), + [IBS_DATA_SRC_DRAM] = L(LOC_RAM) | LN(RAM), + [IBS_DATA_SRC_REM_CACHE] = L(REM_CCE2) | LN(ANY_CACHE) | REM | HOPS(1), + [IBS_DATA_SRC_IO] = L(IO) | LN(IO), +}; + +#define RMT_NODE_BITS (1 << IBS_DATA_SRC_DRAM) +#define RMT_NODE_APPLICABLE(x) (RMT_NODE_BITS & (1 << x)) + +static u64 g_zen4_data_src[32] = { + [IBS_DATA_SRC_EXT_LOC_CACHE] = L(L3) | LN(L3), + [IBS_DATA_SRC_EXT_NEAR_CCX_CACHE] = L(REM_CCE1) | LN(ANY_CACHE) | REM | HOPS(0), + [IBS_DATA_SRC_EXT_DRAM] = L(LOC_RAM) | LN(RAM), + [IBS_DATA_SRC_EXT_FAR_CCX_CACHE] = L(REM_CCE2) | LN(ANY_CACHE) | REM | HOPS(1), + [IBS_DATA_SRC_EXT_PMEM] = LN(PMEM), + [IBS_DATA_SRC_EXT_IO] = L(IO) | LN(IO), + [IBS_DATA_SRC_EXT_EXT_MEM] = LN(CXL), +}; + +#define ZEN4_RMT_NODE_BITS ((1 << IBS_DATA_SRC_EXT_DRAM) | \ + (1 << IBS_DATA_SRC_EXT_PMEM) | \ + (1 << IBS_DATA_SRC_EXT_EXT_MEM)) +#define ZEN4_RMT_NODE_APPLICABLE(x) (ZEN4_RMT_NODE_BITS & (1 << x)) + +static __u64 perf_ibs_get_mem_lvl(union ibs_op_data2 *op_data2, + union ibs_op_data3 *op_data3, + struct perf_sample_data *data) { union perf_mem_data_src *data_src = &data->data_src; u8 ibs_data_src = perf_ibs_data_src(op_data2); data_src->mem_lvl = 0; + data_src->mem_lvl_num = 0; /* * DcMiss, L2Miss, DataSrc, DcMissLat etc. are all invalid for Uncached * memory accesses. So, check DcUcMemAcc bit early. */ - if (op_data3->dc_uc_mem_acc && ibs_data_src != IBS_DATA_SRC_EXT_IO) { - data_src->mem_lvl = PERF_MEM_LVL_UNC | PERF_MEM_LVL_HIT; - return; - } + if (op_data3->dc_uc_mem_acc && ibs_data_src != IBS_DATA_SRC_EXT_IO) + return L(UNC) | LN(UNC); /* L1 Hit */ - if (op_data3->dc_miss == 0) { - data_src->mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT; - return; - } + if (op_data3->dc_miss == 0) + return L(L1) | LN(L1); /* L2 Hit */ if (op_data3->l2_miss == 0) { /* Erratum #1293 */ if (boot_cpu_data.x86 != 0x19 || boot_cpu_data.x86_model > 0xF || - !(op_data3->sw_pf || op_data3->dc_miss_no_mab_alloc)) { - data_src->mem_lvl = PERF_MEM_LVL_L2 | PERF_MEM_LVL_HIT; - return; - } + !(op_data3->sw_pf || op_data3->dc_miss_no_mab_alloc)) + return L(L2) | LN(L2); } /* @@ -743,82 +794,36 @@ static void perf_ibs_get_mem_lvl(union ibs_op_data2 *op_data2, if (data_src->mem_op != PERF_MEM_OP_LOAD) goto check_mab; - /* L3 Hit */ if (ibs_caps & IBS_CAPS_ZEN4) { - if (ibs_data_src == IBS_DATA_SRC_EXT_LOC_CACHE) { - data_src->mem_lvl = PERF_MEM_LVL_L3 | PERF_MEM_LVL_HIT; - return; - } - } else { - if (ibs_data_src == IBS_DATA_SRC_LOC_CACHE) { - data_src->mem_lvl = PERF_MEM_LVL_L3 | PERF_MEM_LVL_REM_CCE1 | - PERF_MEM_LVL_HIT; - return; - } - } + u64 val = g_zen4_data_src[ibs_data_src]; - /* A peer cache in a near CCX */ - if (ibs_caps & IBS_CAPS_ZEN4 && - ibs_data_src == IBS_DATA_SRC_EXT_NEAR_CCX_CACHE) { - data_src->mem_lvl = PERF_MEM_LVL_REM_CCE1 | PERF_MEM_LVL_HIT; - return; - } + if (!val) + goto check_mab; - /* A peer cache in a far CCX */ - if (ibs_caps & IBS_CAPS_ZEN4) { - if (ibs_data_src == IBS_DATA_SRC_EXT_FAR_CCX_CACHE) { - data_src->mem_lvl = PERF_MEM_LVL_REM_CCE2 | PERF_MEM_LVL_HIT; - return; + /* HOPS_1 because IBS doesn't provide remote socket detail */ + if (op_data2->rmt_node && ZEN4_RMT_NODE_APPLICABLE(ibs_data_src)) { + if (ibs_data_src == IBS_DATA_SRC_EXT_DRAM) + val = L(REM_RAM1) | LN(RAM) | REM | HOPS(1); + else + val |= REM | HOPS(1); } - } else { - if (ibs_data_src == IBS_DATA_SRC_REM_CACHE) { - data_src->mem_lvl = PERF_MEM_LVL_REM_CCE2 | PERF_MEM_LVL_HIT; - return; - } - } - /* DRAM */ - if (ibs_data_src == IBS_DATA_SRC_EXT_DRAM) { - if (op_data2->rmt_node == 0) - data_src->mem_lvl = PERF_MEM_LVL_LOC_RAM | PERF_MEM_LVL_HIT; - else - data_src->mem_lvl = PERF_MEM_LVL_REM_RAM1 | PERF_MEM_LVL_HIT; - return; - } + return val; + } else { + u64 val = g_data_src[ibs_data_src]; - /* PMEM */ - if (ibs_caps & IBS_CAPS_ZEN4 && ibs_data_src == IBS_DATA_SRC_EXT_PMEM) { - data_src->mem_lvl_num = PERF_MEM_LVLNUM_PMEM; - if (op_data2->rmt_node) { - data_src->mem_remote = PERF_MEM_REMOTE_REMOTE; - /* IBS doesn't provide Remote socket detail */ - data_src->mem_hops = PERF_MEM_HOPS_1; - } - return; - } + if (!val) + goto check_mab; - /* Extension Memory */ - if (ibs_caps & IBS_CAPS_ZEN4 && - ibs_data_src == IBS_DATA_SRC_EXT_EXT_MEM) { - data_src->mem_lvl_num = PERF_MEM_LVLNUM_CXL; - if (op_data2->rmt_node) { - data_src->mem_remote = PERF_MEM_REMOTE_REMOTE; - /* IBS doesn't provide Remote socket detail */ - data_src->mem_hops = PERF_MEM_HOPS_1; + /* HOPS_1 because IBS doesn't provide remote socket detail */ + if (op_data2->rmt_node && RMT_NODE_APPLICABLE(ibs_data_src)) { + if (ibs_data_src == IBS_DATA_SRC_DRAM) + val = L(REM_RAM1) | LN(RAM) | REM | HOPS(1); + else + val |= REM | HOPS(1); } - return; - } - /* IO */ - if (ibs_data_src == IBS_DATA_SRC_EXT_IO) { - data_src->mem_lvl = PERF_MEM_LVL_IO; - data_src->mem_lvl_num = PERF_MEM_LVLNUM_IO; - if (op_data2->rmt_node) { - data_src->mem_remote = PERF_MEM_REMOTE_REMOTE; - /* IBS doesn't provide Remote socket detail */ - data_src->mem_hops = PERF_MEM_HOPS_1; - } - return; + return val; } check_mab: @@ -829,12 +834,11 @@ check_mab: * DataSrc simultaneously. Prioritize DataSrc over MAB, i.e. set * MAB only when IBS fails to provide DataSrc. */ - if (op_data3->dc_miss_no_mab_alloc) { - data_src->mem_lvl = PERF_MEM_LVL_LFB | PERF_MEM_LVL_HIT; - return; - } + if (op_data3->dc_miss_no_mab_alloc) + return L(LFB) | LN(LFB); - data_src->mem_lvl = PERF_MEM_LVL_NA; + /* Don't set HIT with NA */ + return PERF_MEM_S(LVL, NA) | LN(NA); } static bool perf_ibs_cache_hit_st_valid(void) @@ -924,7 +928,9 @@ static void perf_ibs_get_data_src(struct perf_ibs_data *ibs_data, union ibs_op_data2 *op_data2, union ibs_op_data3 *op_data3) { - perf_ibs_get_mem_lvl(op_data2, op_data3, data); + union perf_mem_data_src *data_src = &data->data_src; + + data_src->val |= perf_ibs_get_mem_lvl(op_data2, op_data3, data); perf_ibs_get_mem_snoop(op_data2, data); perf_ibs_get_tlb_lvl(op_data3, data); perf_ibs_get_mem_lock(op_data3, data); diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 9d248703cbdd..185f902e5f28 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -129,13 +129,11 @@ u64 x86_perf_event_update(struct perf_event *event) * exchange a new raw count - then add that new-prev delta * count to the generic event atomically: */ -again: prev_raw_count = local64_read(&hwc->prev_count); - rdpmcl(hwc->event_base_rdpmc, new_raw_count); - - if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, - new_raw_count) != prev_raw_count) - goto again; + do { + rdpmcl(hwc->event_base_rdpmc, new_raw_count); + } while (!local64_try_cmpxchg(&hwc->prev_count, + &prev_raw_count, new_raw_count)); /* * Now we have the new raw value and have updated the prev @@ -2168,7 +2166,6 @@ static int __init init_hw_perf_events(void) hybrid_pmu->pmu = pmu; hybrid_pmu->pmu.type = -1; hybrid_pmu->pmu.attr_update = x86_pmu.attr_update; - hybrid_pmu->pmu.capabilities |= PERF_PMU_CAP_HETEROGENEOUS_CPUS; hybrid_pmu->pmu.capabilities |= PERF_PMU_CAP_EXTENDED_HW_TYPE; err = perf_pmu_register(&hybrid_pmu->pmu, hybrid_pmu->name, diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 2a284ba951b7..fa355d3658a6 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2129,6 +2129,17 @@ static struct extra_reg intel_grt_extra_regs[] __read_mostly = { EVENT_EXTRA_END }; +EVENT_ATTR_STR(topdown-retiring, td_retiring_cmt, "event=0x72,umask=0x0"); +EVENT_ATTR_STR(topdown-bad-spec, td_bad_spec_cmt, "event=0x73,umask=0x0"); + +static struct attribute *cmt_events_attrs[] = { + EVENT_PTR(td_fe_bound_tnt), + EVENT_PTR(td_retiring_cmt), + EVENT_PTR(td_bad_spec_cmt), + EVENT_PTR(td_be_bound_tnt), + NULL +}; + static struct extra_reg intel_cmt_extra_regs[] __read_mostly = { /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x800ff3ffffffffffull, RSP_0), @@ -4847,6 +4858,8 @@ PMU_FORMAT_ATTR(ldlat, "config1:0-15"); PMU_FORMAT_ATTR(frontend, "config1:0-23"); +PMU_FORMAT_ATTR(snoop_rsp, "config1:0-63"); + static struct attribute *intel_arch3_formats_attr[] = { &format_attr_event.attr, &format_attr_umask.attr, @@ -4877,6 +4890,13 @@ static struct attribute *slm_format_attr[] = { NULL }; +static struct attribute *cmt_format_attr[] = { + &format_attr_offcore_rsp.attr, + &format_attr_ldlat.attr, + &format_attr_snoop_rsp.attr, + NULL +}; + static struct attribute *skl_format_attr[] = { &format_attr_frontend.attr, NULL, @@ -5656,7 +5676,6 @@ static struct attribute *adl_hybrid_extra_attr[] = { NULL }; -PMU_FORMAT_ATTR_SHOW(snoop_rsp, "config1:0-63"); FORMAT_ATTR_HYBRID(snoop_rsp, hybrid_small); static struct attribute *mtl_hybrid_extra_attr_rtm[] = { @@ -6174,7 +6193,7 @@ __init int intel_pmu_init(void) name = "Tremont"; break; - case INTEL_FAM6_ALDERLAKE_N: + case INTEL_FAM6_ATOM_GRACEMONT: x86_pmu.mid_ack = true; memcpy(hw_cache_event_ids, glp_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -6204,6 +6223,37 @@ __init int intel_pmu_init(void) name = "gracemont"; break; + case INTEL_FAM6_ATOM_CRESTMONT: + case INTEL_FAM6_ATOM_CRESTMONT_X: + x86_pmu.mid_ack = true; + memcpy(hw_cache_event_ids, glp_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, tnt_hw_cache_extra_regs, + sizeof(hw_cache_extra_regs)); + hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1; + + x86_pmu.event_constraints = intel_slm_event_constraints; + x86_pmu.pebs_constraints = intel_grt_pebs_event_constraints; + x86_pmu.extra_regs = intel_cmt_extra_regs; + + x86_pmu.pebs_aliases = NULL; + x86_pmu.pebs_prec_dist = true; + x86_pmu.lbr_pt_coexist = true; + x86_pmu.pebs_block = true; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_INSTR_LATENCY; + + intel_pmu_pebs_data_source_cmt(); + x86_pmu.pebs_latency_data = mtl_latency_data_small; + x86_pmu.get_event_constraints = cmt_get_event_constraints; + x86_pmu.limit_period = spr_limit_period; + td_attr = cmt_events_attrs; + mem_attr = grt_mem_attrs; + extra_attr = cmt_format_attr; + pr_cont("Crestmont events, "); + name = "crestmont"; + break; + case INTEL_FAM6_WESTMERE: case INTEL_FAM6_WESTMERE_EP: case INTEL_FAM6_WESTMERE_EX: diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 835862c548cc..96fffb2d521d 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -365,13 +365,11 @@ static void cstate_pmu_event_update(struct perf_event *event) struct hw_perf_event *hwc = &event->hw; u64 prev_raw_count, new_raw_count; -again: prev_raw_count = local64_read(&hwc->prev_count); - new_raw_count = cstate_pmu_read_counter(event); - - if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, - new_raw_count) != prev_raw_count) - goto again; + do { + new_raw_count = cstate_pmu_read_counter(event); + } while (!local64_try_cmpxchg(&hwc->prev_count, + &prev_raw_count, new_raw_count)); local64_add(new_raw_count - prev_raw_count, &event->count); } @@ -671,6 +669,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &glm_cstates), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT, &glm_cstates), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L, &glm_cstates), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT, &adl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE, &icl_cstates), @@ -686,7 +685,6 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &adl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &adl_cstates), - X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, &adl_cstates), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_cstates), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &adl_cstates), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &adl_cstates), diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index df88576d6b2a..eb8dd8b8a1e8 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -144,7 +144,7 @@ void __init intel_pmu_pebs_data_source_adl(void) __intel_pmu_pebs_data_source_grt(data_source); } -static void __init intel_pmu_pebs_data_source_cmt(u64 *data_source) +static void __init __intel_pmu_pebs_data_source_cmt(u64 *data_source) { data_source[0x07] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD); data_source[0x08] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM); @@ -164,7 +164,12 @@ void __init intel_pmu_pebs_data_source_mtl(void) data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX].pebs_data_source; memcpy(data_source, pebs_data_source, sizeof(pebs_data_source)); - intel_pmu_pebs_data_source_cmt(data_source); + __intel_pmu_pebs_data_source_cmt(data_source); +} + +void __init intel_pmu_pebs_data_source_cmt(void) +{ + __intel_pmu_pebs_data_source_cmt(pebs_data_source); } static u64 precise_store_data(u64 status) diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index bc226603ef3e..69043e02e8a7 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1858,7 +1858,6 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, &rkl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &adl_uncore_init), - X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &adl_uncore_init), @@ -1867,6 +1866,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &spr_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &spr_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &snr_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT, &adl_uncore_init), {}, }; MODULE_DEVICE_TABLE(x86cpu, intel_uncore_match); diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index d49e90dc04a4..4d349986f76a 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -1502,7 +1502,7 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool pci_dev_put(ubox_dev); - return err ? pcibios_err_to_errno(err) : 0; + return pcibios_err_to_errno(err); } int snbep_uncore_pci_init(void) diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index 0feaaa571303..9e237b30f017 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -106,7 +106,7 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_ROCKETLAKE: case INTEL_FAM6_ALDERLAKE: case INTEL_FAM6_ALDERLAKE_L: - case INTEL_FAM6_ALDERLAKE_N: + case INTEL_FAM6_ATOM_GRACEMONT: case INTEL_FAM6_RAPTORLAKE: case INTEL_FAM6_RAPTORLAKE_P: case INTEL_FAM6_RAPTORLAKE_S: @@ -244,12 +244,10 @@ static void msr_event_update(struct perf_event *event) s64 delta; /* Careful, an NMI might modify the previous event value: */ -again: prev = local64_read(&event->hw.prev_count); - now = msr_read_counter(event); - - if (local64_cmpxchg(&event->hw.prev_count, prev, now) != prev) - goto again; + do { + now = msr_read_counter(event); + } while (!local64_try_cmpxchg(&event->hw.prev_count, &prev, now)); delta = now - prev; if (unlikely(event->hw.event_base == MSR_SMI_COUNT)) { diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index d6de4487348c..c8ba2be7585d 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -1606,6 +1606,8 @@ void intel_pmu_pebs_data_source_grt(void); void intel_pmu_pebs_data_source_mtl(void); +void intel_pmu_pebs_data_source_cmt(void); + int intel_pmu_setup_lbr_filter(struct perf_event *event); void intel_pt_interrupt(void); diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index 52e6e7ed4f78..1579429846cc 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -804,7 +804,7 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &model_skl), - X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &model_spr), X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &model_spr), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &model_skl), diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h index 9191280d9ea3..4ae14339cb8c 100644 --- a/arch/x86/include/asm/boot.h +++ b/arch/x86/include/asm/boot.h @@ -62,4 +62,12 @@ # define BOOT_STACK_SIZE 0x1000 #endif +#ifndef __ASSEMBLY__ +extern unsigned int output_len; +extern const unsigned long kernel_total_size; + +unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr, + void (*error)(char *x)); +#endif + #endif /* _ASM_X86_BOOT_H */ diff --git a/arch/x86/include/asm/div64.h b/arch/x86/include/asm/div64.h index b8f1dc0761e4..9931e4c7d73f 100644 --- a/arch/x86/include/asm/div64.h +++ b/arch/x86/include/asm/div64.h @@ -71,6 +71,12 @@ static inline u64 mul_u32_u32(u32 a, u32 b) } #define mul_u32_u32 mul_u32_u32 +/* + * __div64_32() is never called on x86, so prevent the + * generic definition from getting built. + */ +#define __div64_32 + #else # include <asm-generic/div64.h> diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 8b4be7cecdb8..b0994ae3bc23 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -90,6 +90,8 @@ static inline void efi_fpu_end(void) } #ifdef CONFIG_X86_32 +#define EFI_X86_KERNEL_ALLOC_LIMIT (SZ_512M - 1) + #define arch_efi_call_virt_setup() \ ({ \ efi_fpu_begin(); \ @@ -103,8 +105,7 @@ static inline void efi_fpu_end(void) }) #else /* !CONFIG_X86_32 */ - -#define EFI_LOADER_SIGNATURE "EL64" +#define EFI_X86_KERNEL_ALLOC_LIMIT EFI_ALLOC_LIMIT extern asmlinkage u64 __efi_call(void *fp, ...); @@ -218,6 +219,8 @@ efi_status_t efi_set_virtual_address_map(unsigned long memory_map_size, #ifdef CONFIG_EFI_MIXED +#define EFI_ALLOC_LIMIT (efi_is_64bit() ? ULONG_MAX : U32_MAX) + #define ARCH_HAS_EFISTUB_WRAPPERS static inline bool efi_is_64bit(void) diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index b3af2d45bbbb..5fcd85fd64fd 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -98,8 +98,6 @@ #define INTEL_FAM6_ICELAKE_L 0x7E /* Sunny Cove */ #define INTEL_FAM6_ICELAKE_NNPI 0x9D /* Sunny Cove */ -#define INTEL_FAM6_LAKEFIELD 0x8A /* Sunny Cove / Tremont */ - #define INTEL_FAM6_ROCKETLAKE 0xA7 /* Cypress Cove */ #define INTEL_FAM6_TIGERLAKE_L 0x8C /* Willow Cove */ @@ -112,21 +110,24 @@ #define INTEL_FAM6_GRANITERAPIDS_X 0xAD #define INTEL_FAM6_GRANITERAPIDS_D 0xAE +/* "Hybrid" Processors (P-Core/E-Core) */ + +#define INTEL_FAM6_LAKEFIELD 0x8A /* Sunny Cove / Tremont */ + #define INTEL_FAM6_ALDERLAKE 0x97 /* Golden Cove / Gracemont */ #define INTEL_FAM6_ALDERLAKE_L 0x9A /* Golden Cove / Gracemont */ -#define INTEL_FAM6_ALDERLAKE_N 0xBE -#define INTEL_FAM6_RAPTORLAKE 0xB7 +#define INTEL_FAM6_RAPTORLAKE 0xB7 /* Raptor Cove / Enhanced Gracemont */ #define INTEL_FAM6_RAPTORLAKE_P 0xBA #define INTEL_FAM6_RAPTORLAKE_S 0xBF #define INTEL_FAM6_METEORLAKE 0xAC #define INTEL_FAM6_METEORLAKE_L 0xAA -#define INTEL_FAM6_LUNARLAKE_M 0xBD - #define INTEL_FAM6_ARROWLAKE 0xC6 +#define INTEL_FAM6_LUNARLAKE_M 0xBD + /* "Small Core" Processors (Atom/E-Core) */ #define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */ @@ -154,9 +155,10 @@ #define INTEL_FAM6_ATOM_TREMONT 0x96 /* Elkhart Lake */ #define INTEL_FAM6_ATOM_TREMONT_L 0x9C /* Jasper Lake */ -#define INTEL_FAM6_SIERRAFOREST_X 0xAF +#define INTEL_FAM6_ATOM_GRACEMONT 0xBE /* Alderlake N */ -#define INTEL_FAM6_GRANDRIDGE 0xB6 +#define INTEL_FAM6_ATOM_CRESTMONT_X 0xAF /* Sierra Forest */ +#define INTEL_FAM6_ATOM_CRESTMONT 0xB6 /* Grand Ridge */ /* Xeon Phi */ diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h index 56d4ef604b91..635132a12778 100644 --- a/arch/x86/include/asm/local.h +++ b/arch/x86/include/asm/local.h @@ -127,8 +127,8 @@ static inline long local_cmpxchg(local_t *l, long old, long new) static inline bool local_try_cmpxchg(local_t *l, long *old, long new) { - typeof(l->a.counter) *__old = (typeof(l->a.counter) *) old; - return try_cmpxchg_local(&l->a.counter, __old, new); + return try_cmpxchg_local(&l->a.counter, + (typeof(l->a.counter) *) old, new); } /* Always has a lock prefix */ diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 7f97a8a97e24..473b16d73b47 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -50,8 +50,8 @@ void __init sme_enable(struct boot_params *bp); int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size); int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size); -void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, - bool enc); +void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, + unsigned long size, bool enc); void __init mem_encrypt_free_decrypted_mem(void); @@ -85,7 +85,7 @@ early_set_memory_decrypted(unsigned long vaddr, unsigned long size) { return 0; static inline int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; } static inline void __init -early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, bool enc) {} +early_set_mem_enc_dec_hypercall(unsigned long vaddr, unsigned long size, bool enc) {} static inline void mem_encrypt_free_decrypted_mem(void) { } diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 66dbba181bd9..bbbe9d744977 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -2,138 +2,77 @@ #ifndef _ASM_X86_MICROCODE_H #define _ASM_X86_MICROCODE_H -#include <asm/cpu.h> -#include <linux/earlycpio.h> -#include <linux/initrd.h> -#include <asm/microcode_amd.h> - -struct ucode_patch { - struct list_head plist; - void *data; /* Intel uses only this one */ - unsigned int size; - u32 patch_id; - u16 equiv_cpu; -}; - -extern struct list_head microcode_cache; - struct cpu_signature { unsigned int sig; unsigned int pf; unsigned int rev; }; -struct device; - -enum ucode_state { - UCODE_OK = 0, - UCODE_NEW, - UCODE_UPDATED, - UCODE_NFOUND, - UCODE_ERROR, -}; - -struct microcode_ops { - enum ucode_state (*request_microcode_fw) (int cpu, struct device *); - - void (*microcode_fini_cpu) (int cpu); - - /* - * The generic 'microcode_core' part guarantees that - * the callbacks below run on a target cpu when they - * are being called. - * See also the "Synchronization" section in microcode_core.c. - */ - enum ucode_state (*apply_microcode) (int cpu); - int (*collect_cpu_info) (int cpu, struct cpu_signature *csig); -}; - struct ucode_cpu_info { struct cpu_signature cpu_sig; void *mc; }; -extern struct ucode_cpu_info ucode_cpu_info[]; -struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa); - -#ifdef CONFIG_MICROCODE_INTEL -extern struct microcode_ops * __init init_intel_microcode(void); -#else -static inline struct microcode_ops * __init init_intel_microcode(void) -{ - return NULL; -} -#endif /* CONFIG_MICROCODE_INTEL */ -#ifdef CONFIG_MICROCODE_AMD -extern struct microcode_ops * __init init_amd_microcode(void); -extern void __exit exit_amd_microcode(void); +#ifdef CONFIG_MICROCODE +void load_ucode_bsp(void); +void load_ucode_ap(void); +void microcode_bsp_resume(void); #else -static inline struct microcode_ops * __init init_amd_microcode(void) -{ - return NULL; -} -static inline void __exit exit_amd_microcode(void) {} +static inline void load_ucode_bsp(void) { } +static inline void load_ucode_ap(void) { } +static inline void microcode_bsp_resume(void) { } #endif -#define MAX_UCODE_COUNT 128 +#ifdef CONFIG_CPU_SUP_INTEL +/* Intel specific microcode defines. Public for IFS */ +struct microcode_header_intel { + unsigned int hdrver; + unsigned int rev; + unsigned int date; + unsigned int sig; + unsigned int cksum; + unsigned int ldrver; + unsigned int pf; + unsigned int datasize; + unsigned int totalsize; + unsigned int metasize; + unsigned int reserved[2]; +}; -#define QCHAR(a, b, c, d) ((a) + ((b) << 8) + ((c) << 16) + ((d) << 24)) -#define CPUID_INTEL1 QCHAR('G', 'e', 'n', 'u') -#define CPUID_INTEL2 QCHAR('i', 'n', 'e', 'I') -#define CPUID_INTEL3 QCHAR('n', 't', 'e', 'l') -#define CPUID_AMD1 QCHAR('A', 'u', 't', 'h') -#define CPUID_AMD2 QCHAR('e', 'n', 't', 'i') -#define CPUID_AMD3 QCHAR('c', 'A', 'M', 'D') +struct microcode_intel { + struct microcode_header_intel hdr; + unsigned int bits[]; +}; -#define CPUID_IS(a, b, c, ebx, ecx, edx) \ - (!((ebx ^ (a))|(edx ^ (b))|(ecx ^ (c)))) +#define DEFAULT_UCODE_DATASIZE (2000) +#define MC_HEADER_SIZE (sizeof(struct microcode_header_intel)) +#define MC_HEADER_TYPE_MICROCODE 1 +#define MC_HEADER_TYPE_IFS 2 -/* - * In early loading microcode phase on BSP, boot_cpu_data is not set up yet. - * x86_cpuid_vendor() gets vendor id for BSP. - * - * In 32 bit AP case, accessing boot_cpu_data needs linear address. To simplify - * coding, we still use x86_cpuid_vendor() to get vendor id for AP. - * - * x86_cpuid_vendor() gets vendor information directly from CPUID. - */ -static inline int x86_cpuid_vendor(void) +static inline int intel_microcode_get_datasize(struct microcode_header_intel *hdr) { - u32 eax = 0x00000000; - u32 ebx, ecx = 0, edx; - - native_cpuid(&eax, &ebx, &ecx, &edx); - - if (CPUID_IS(CPUID_INTEL1, CPUID_INTEL2, CPUID_INTEL3, ebx, ecx, edx)) - return X86_VENDOR_INTEL; - - if (CPUID_IS(CPUID_AMD1, CPUID_AMD2, CPUID_AMD3, ebx, ecx, edx)) - return X86_VENDOR_AMD; - - return X86_VENDOR_UNKNOWN; + return hdr->datasize ? : DEFAULT_UCODE_DATASIZE; } -static inline unsigned int x86_cpuid_family(void) +static inline u32 intel_get_microcode_revision(void) { - u32 eax = 0x00000001; - u32 ebx, ecx = 0, edx; + u32 rev, dummy; + + native_wrmsrl(MSR_IA32_UCODE_REV, 0); - native_cpuid(&eax, &ebx, &ecx, &edx); + /* As documented in the SDM: Do a CPUID 1 here */ + native_cpuid_eax(1); - return x86_family(eax); + /* get the current revision from MSR 0x8B */ + native_rdmsr(MSR_IA32_UCODE_REV, dummy, rev); + + return rev; } -#ifdef CONFIG_MICROCODE -extern void __init load_ucode_bsp(void); -extern void load_ucode_ap(void); -void reload_early_microcode(unsigned int cpu); -extern bool initrd_gone; -void microcode_bsp_resume(void); -#else -static inline void __init load_ucode_bsp(void) { } -static inline void load_ucode_ap(void) { } -static inline void reload_early_microcode(unsigned int cpu) { } -static inline void microcode_bsp_resume(void) { } -#endif +void show_ucode_info_early(void); + +#else /* CONFIG_CPU_SUP_INTEL */ +static inline void show_ucode_info_early(void) { } +#endif /* !CONFIG_CPU_SUP_INTEL */ #endif /* _ASM_X86_MICROCODE_H */ diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h deleted file mode 100644 index 9675c621c1ca..000000000000 --- a/arch/x86/include/asm/microcode_amd.h +++ /dev/null @@ -1,60 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_X86_MICROCODE_AMD_H -#define _ASM_X86_MICROCODE_AMD_H - -#include <asm/microcode.h> - -#define UCODE_MAGIC 0x00414d44 -#define UCODE_EQUIV_CPU_TABLE_TYPE 0x00000000 -#define UCODE_UCODE_TYPE 0x00000001 - -#define SECTION_HDR_SIZE 8 -#define CONTAINER_HDR_SZ 12 - -struct equiv_cpu_entry { - u32 installed_cpu; - u32 fixed_errata_mask; - u32 fixed_errata_compare; - u16 equiv_cpu; - u16 res; -} __attribute__((packed)); - -struct microcode_header_amd { - u32 data_code; - u32 patch_id; - u16 mc_patch_data_id; - u8 mc_patch_data_len; - u8 init_flag; - u32 mc_patch_data_checksum; - u32 nb_dev_id; - u32 sb_dev_id; - u16 processor_rev_id; - u8 nb_rev_id; - u8 sb_rev_id; - u8 bios_api_rev; - u8 reserved1[3]; - u32 match_reg[8]; -} __attribute__((packed)); - -struct microcode_amd { - struct microcode_header_amd hdr; - unsigned int mpb[]; -}; - -#define PATCH_MAX_SIZE (3 * PAGE_SIZE) - -#ifdef CONFIG_MICROCODE_AMD -extern void __init load_ucode_amd_bsp(unsigned int family); -extern void load_ucode_amd_ap(unsigned int family); -extern int __init save_microcode_in_initrd_amd(unsigned int family); -void reload_ucode_amd(unsigned int cpu); -extern void amd_check_microcode(void); -#else -static inline void __init load_ucode_amd_bsp(unsigned int family) {} -static inline void load_ucode_amd_ap(unsigned int family) {} -static inline int __init -save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; } -static inline void reload_ucode_amd(unsigned int cpu) {} -static inline void amd_check_microcode(void) {} -#endif -#endif /* _ASM_X86_MICROCODE_AMD_H */ diff --git a/arch/x86/include/asm/microcode_intel.h b/arch/x86/include/asm/microcode_intel.h deleted file mode 100644 index f1fa979e05bf..000000000000 --- a/arch/x86/include/asm/microcode_intel.h +++ /dev/null @@ -1,88 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_X86_MICROCODE_INTEL_H -#define _ASM_X86_MICROCODE_INTEL_H - -#include <asm/microcode.h> - -struct microcode_header_intel { - unsigned int hdrver; - unsigned int rev; - unsigned int date; - unsigned int sig; - unsigned int cksum; - unsigned int ldrver; - unsigned int pf; - unsigned int datasize; - unsigned int totalsize; - unsigned int metasize; - unsigned int reserved[2]; -}; - -struct microcode_intel { - struct microcode_header_intel hdr; - unsigned int bits[]; -}; - -/* microcode format is extended from prescott processors */ -struct extended_signature { - unsigned int sig; - unsigned int pf; - unsigned int cksum; -}; - -struct extended_sigtable { - unsigned int count; - unsigned int cksum; - unsigned int reserved[3]; - struct extended_signature sigs[]; -}; - -#define DEFAULT_UCODE_DATASIZE (2000) -#define MC_HEADER_SIZE (sizeof(struct microcode_header_intel)) -#define DEFAULT_UCODE_TOTALSIZE (DEFAULT_UCODE_DATASIZE + MC_HEADER_SIZE) -#define EXT_HEADER_SIZE (sizeof(struct extended_sigtable)) -#define EXT_SIGNATURE_SIZE (sizeof(struct extended_signature)) -#define MC_HEADER_TYPE_MICROCODE 1 -#define MC_HEADER_TYPE_IFS 2 - -#define get_totalsize(mc) \ - (((struct microcode_intel *)mc)->hdr.datasize ? \ - ((struct microcode_intel *)mc)->hdr.totalsize : \ - DEFAULT_UCODE_TOTALSIZE) - -#define get_datasize(mc) \ - (((struct microcode_intel *)mc)->hdr.datasize ? \ - ((struct microcode_intel *)mc)->hdr.datasize : DEFAULT_UCODE_DATASIZE) - -#define exttable_size(et) ((et)->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE) - -static inline u32 intel_get_microcode_revision(void) -{ - u32 rev, dummy; - - native_wrmsrl(MSR_IA32_UCODE_REV, 0); - - /* As documented in the SDM: Do a CPUID 1 here */ - native_cpuid_eax(1); - - /* get the current revision from MSR 0x8B */ - native_rdmsr(MSR_IA32_UCODE_REV, dummy, rev); - - return rev; -} - -#ifdef CONFIG_MICROCODE_INTEL -extern void __init load_ucode_intel_bsp(void); -extern void load_ucode_intel_ap(void); -extern void show_ucode_info_early(void); -extern int __init save_microcode_in_initrd_intel(void); -void reload_ucode_intel(void); -#else -static inline __init void load_ucode_intel_bsp(void) {} -static inline void load_ucode_intel_ap(void) {} -static inline void show_ucode_info_early(void) {} -static inline int __init save_microcode_in_initrd_intel(void) { return -EINVAL; } -static inline void reload_ucode_intel(void) {} -#endif - -#endif /* _ASM_X86_MICROCODE_INTEL_H */ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index b49778664d2b..6c8ff12140ae 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -739,6 +739,7 @@ static __always_inline unsigned long arch_local_irq_save(void) ".popsection") extern void default_banner(void); +void native_pv_lock_init(void) __init; #else /* __ASSEMBLY__ */ @@ -778,6 +779,12 @@ extern void default_banner(void); #endif /* __ASSEMBLY__ */ #else /* CONFIG_PARAVIRT */ # define default_banner x86_init_noop + +#ifndef __ASSEMBLY__ +static inline void native_pv_lock_init(void) +{ +} +#endif #endif /* !CONFIG_PARAVIRT */ #ifndef __ASSEMBLY__ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index fd750247ca89..861e53e201e9 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -678,11 +678,13 @@ extern u32 amd_get_nodes_per_socket(void); extern u32 amd_get_highest_perf(void); extern bool cpu_has_ibpb_brtype_microcode(void); extern void amd_clear_divider(void); +extern void amd_check_microcode(void); #else static inline u32 amd_get_nodes_per_socket(void) { return 0; } static inline u32 amd_get_highest_perf(void) { return 0; } static inline bool cpu_has_ibpb_brtype_microcode(void) { return false; } static inline void amd_clear_divider(void) { } +static inline void amd_check_microcode(void) { } #endif extern unsigned long arch_align_stack(unsigned long sp); diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h index d87451df480b..cde8357bb226 100644 --- a/arch/x86/include/asm/qspinlock.h +++ b/arch/x86/include/asm/qspinlock.h @@ -74,8 +74,6 @@ static inline bool vcpu_is_preempted(long cpu) */ DECLARE_STATIC_KEY_TRUE(virt_spin_lock_key); -void native_pv_lock_init(void) __init; - /* * Shortcut for the queued_spin_lock_slowpath() function that allows * virt to hijack it. @@ -103,10 +101,7 @@ static inline bool virt_spin_lock(struct qspinlock *lock) return true; } -#else -static inline void native_pv_lock_init(void) -{ -} + #endif /* CONFIG_PARAVIRT */ #include <asm-generic/qspinlock.h> diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h index 42b17cf10b10..85b6e3609cb9 100644 --- a/arch/x86/include/asm/qspinlock_paravirt.h +++ b/arch/x86/include/asm/qspinlock_paravirt.h @@ -4,6 +4,8 @@ #include <asm/ibt.h> +void __lockfunc __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked); + /* * For x86-64, PV_CALLEE_SAVE_REGS_THUNK() saves and restores 8 64-bit * registers. For i386, however, only 1 32-bit register needs to be saved diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 66c806784c52..5b4a1ce3d368 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -164,6 +164,7 @@ static __always_inline void sev_es_nmi_complete(void) __sev_es_nmi_complete(); } extern int __init sev_es_efi_map_ghcbs(pgd_t *pgd); +extern void sev_enable(struct boot_params *bp); static inline int rmpadjust(unsigned long vaddr, bool rmp_psize, unsigned long attrs) { @@ -210,12 +211,15 @@ bool snp_init(struct boot_params *bp); void __init __noreturn snp_abort(void); int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio); void snp_accept_memory(phys_addr_t start, phys_addr_t end); +u64 snp_get_unsupported_features(u64 status); +u64 sev_get_status(void); #else static inline void sev_es_ist_enter(struct pt_regs *regs) { } static inline void sev_es_ist_exit(void) { } static inline int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) { return 0; } static inline void sev_es_nmi_complete(void) { } static inline int sev_es_efi_map_ghcbs(pgd_t *pgd) { return 0; } +static inline void sev_enable(struct boot_params *bp) { } static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate) { return 0; } static inline int rmpadjust(unsigned long vaddr, bool rmp_psize, unsigned long attrs) { return 0; } static inline void setup_ghcb(void) { } @@ -235,6 +239,8 @@ static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *in } static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { } +static inline u64 snp_get_unsupported_features(u64 status) { return 0; } +static inline u64 sev_get_status(void) { return 0; } #endif #endif diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index caf41c4869a0..3235ba1e5b06 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -136,10 +136,11 @@ static inline int topology_max_smt_threads(void) return __max_smt_threads; } +#include <linux/cpu_smt.h> + int topology_update_package_map(unsigned int apicid, unsigned int cpu); int topology_update_die_map(unsigned int dieid, unsigned int cpu); int topology_phys_to_logical_pkg(unsigned int pkg); -bool topology_smt_supported(void); extern struct cpumask __cpu_primary_thread_mask; #define cpu_primary_thread_mask ((const struct cpumask *)&__cpu_primary_thread_mask) @@ -162,7 +163,6 @@ static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; } static inline int topology_max_die_per_package(void) { return 1; } static inline int topology_max_smt_threads(void) { return 1; } static inline bool topology_is_primary_thread(unsigned int cpu) { return true; } -static inline bool topology_smt_supported(void) { return false; } #endif /* !CONFIG_SMP */ static inline void arch_fix_phys_package_id(int num, u32 slot) diff --git a/arch/x86/include/asm/uv/bios.h b/arch/x86/include/asm/uv/bios.h index 1b6455f881f9..6989b824fd32 100644 --- a/arch/x86/include/asm/uv/bios.h +++ b/arch/x86/include/asm/uv/bios.h @@ -10,6 +10,7 @@ * Copyright (c) Russ Anderson <rja@sgi.com> */ +#include <linux/efi.h> #include <linux/rtc.h> /* @@ -115,7 +116,8 @@ struct uv_arch_type_entry { struct uv_systab { char signature[4]; /* must be UV_SYSTAB_SIG */ u32 revision; /* distinguish different firmware revs */ - u64 function; /* BIOS runtime callback function ptr */ + u64 (__efiapi *function)(enum uv_bios_cmd, ...); + /* BIOS runtime callback function ptr */ u32 size; /* systab size (starting with _VERSION_UV4) */ struct { u32 type:8; /* type of entry */ diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index fa9ec20783fa..85e63d58c074 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -295,7 +295,10 @@ static inline unsigned long bfn_to_local_pfn(unsigned long mfn) /* VIRT <-> MACHINE conversion */ #define virt_to_machine(v) (phys_to_machine(XPADDR(__pa(v)))) -#define virt_to_pfn(v) (PFN_DOWN(__pa(v))) +static inline unsigned long virt_to_pfn(const void *v) +{ + return PFN_DOWN(__pa(v)); +} #define virt_to_mfn(v) (pfn_to_mfn(virt_to_pfn(v))) #define mfn_to_virt(m) (__va(mfn_to_pfn(m) << PAGE_SHIFT)) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 099d58d02a26..a5ead6a6d233 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -1527,6 +1527,7 @@ static noinline void __init int3_selftest(void) static __initdata int __alt_reloc_selftest_addr; +extern void __init __alt_reloc_selftest(void *arg); __visible noinline void __init __alt_reloc_selftest(void *arg) { WARN_ON(arg != &__alt_reloc_selftest_addr); diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 035a3db5330b..356de955e78d 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -24,6 +24,8 @@ #define PCI_DEVICE_ID_AMD_19H_M40H_ROOT 0x14b5 #define PCI_DEVICE_ID_AMD_19H_M60H_ROOT 0x14d8 #define PCI_DEVICE_ID_AMD_19H_M70H_ROOT 0x14e8 +#define PCI_DEVICE_ID_AMD_1AH_M00H_ROOT 0x153a +#define PCI_DEVICE_ID_AMD_1AH_M20H_ROOT 0x1507 #define PCI_DEVICE_ID_AMD_MI200_ROOT 0x14bb #define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464 @@ -39,6 +41,7 @@ #define PCI_DEVICE_ID_AMD_19H_M60H_DF_F4 0x14e4 #define PCI_DEVICE_ID_AMD_19H_M70H_DF_F4 0x14f4 #define PCI_DEVICE_ID_AMD_19H_M78H_DF_F4 0x12fc +#define PCI_DEVICE_ID_AMD_1AH_M00H_DF_F4 0x12c4 #define PCI_DEVICE_ID_AMD_MI200_DF_F4 0x14d4 /* Protect the PCI config register pairs used for SMN. */ @@ -56,6 +59,8 @@ static const struct pci_device_id amd_root_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M60H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M70H_ROOT) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_ROOT) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_ROOT) }, {} }; @@ -85,6 +90,8 @@ static const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M60H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M70H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F3) }, {} }; @@ -106,6 +113,7 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F4) }, {} }; diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c index 2a6509e8c840..9bfd6e397384 100644 --- a/arch/x86/kernel/apic/ipi.c +++ b/arch/x86/kernel/apic/ipi.c @@ -301,6 +301,7 @@ void default_send_IPI_mask_logical(const struct cpumask *cpumask, int vector) local_irq_restore(flags); } +#ifdef CONFIG_SMP /* must come after the send_IPI functions above for inlining */ static int convert_apicid_to_cpu(int apic_id) { @@ -329,3 +330,4 @@ int safe_smp_processor_id(void) return cpuid >= 0 ? cpuid : 0; } #endif +#endif diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index d9384d5b4b8e..b524dee1cbbb 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -294,8 +294,7 @@ static void __init early_get_apic_socketid_shift(void) static void __init uv_stringify(int len, char *to, char *from) { - /* Relies on 'to' being NULL chars so result will be NULL terminated */ - strncpy(to, from, len-1); + strscpy(to, from, len); /* Trim trailing spaces */ (void)strim(to); @@ -1013,7 +1012,7 @@ static void __init calc_mmioh_map(enum mmioh_arch index, /* One (UV2) mapping */ if (index == UV2_MMIOH) { - strncpy(id, "MMIOH", sizeof(id)); + strscpy(id, "MMIOH", sizeof(id)); max_io = max_pnode; mapped = 0; goto map_exit; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index e3a65e9fc750..41b573f34a10 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -59,7 +59,6 @@ #include <asm/cacheinfo.h> #include <asm/memtype.h> #include <asm/microcode.h> -#include <asm/microcode_intel.h> #include <asm/intel-family.h> #include <asm/cpu_device_id.h> #include <asm/uv/uv.h> @@ -2300,8 +2299,7 @@ void store_cpu_caps(struct cpuinfo_x86 *curr_info) * @prev_info: CPU capabilities stored before an update. * * The microcode loader calls this upon late microcode load to recheck features, - * only when microcode has been updated. Caller holds microcode_mutex and CPU - * hotplug lock. + * only when microcode has been updated. Caller holds and CPU hotplug lock. * * Return: None */ @@ -2343,7 +2341,7 @@ void __init arch_cpu_finalize_init(void) * identify_boot_cpu() initialized SMT support information, let the * core code know. */ - cpu_smt_check_topology(); + cpu_smt_set_num_threads(smp_num_siblings, smp_num_siblings); if (!IS_ENABLED(CONFIG_SMP)) { pr_info("CPU: "); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 1c4639588ff9..be4045628fd3 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -20,7 +20,7 @@ #include <asm/bugs.h> #include <asm/cpu.h> #include <asm/intel-family.h> -#include <asm/microcode_intel.h> +#include <asm/microcode.h> #include <asm/hwcap2.h> #include <asm/elf.h> #include <asm/cpu_device_id.h> @@ -184,180 +184,6 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) return false; } -int intel_cpu_collect_info(struct ucode_cpu_info *uci) -{ - unsigned int val[2]; - unsigned int family, model; - struct cpu_signature csig = { 0 }; - unsigned int eax, ebx, ecx, edx; - - memset(uci, 0, sizeof(*uci)); - - eax = 0x00000001; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); - csig.sig = eax; - - family = x86_family(eax); - model = x86_model(eax); - - if (model >= 5 || family > 6) { - /* get processor flags from MSR 0x17 */ - native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]); - csig.pf = 1 << ((val[1] >> 18) & 7); - } - - csig.rev = intel_get_microcode_revision(); - - uci->cpu_sig = csig; - - return 0; -} -EXPORT_SYMBOL_GPL(intel_cpu_collect_info); - -/* - * Returns 1 if update has been found, 0 otherwise. - */ -int intel_find_matching_signature(void *mc, unsigned int csig, int cpf) -{ - struct microcode_header_intel *mc_hdr = mc; - struct extended_sigtable *ext_hdr; - struct extended_signature *ext_sig; - int i; - - if (intel_cpu_signatures_match(csig, cpf, mc_hdr->sig, mc_hdr->pf)) - return 1; - - /* Look for ext. headers: */ - if (get_totalsize(mc_hdr) <= get_datasize(mc_hdr) + MC_HEADER_SIZE) - return 0; - - ext_hdr = mc + get_datasize(mc_hdr) + MC_HEADER_SIZE; - ext_sig = (void *)ext_hdr + EXT_HEADER_SIZE; - - for (i = 0; i < ext_hdr->count; i++) { - if (intel_cpu_signatures_match(csig, cpf, ext_sig->sig, ext_sig->pf)) - return 1; - ext_sig++; - } - return 0; -} -EXPORT_SYMBOL_GPL(intel_find_matching_signature); - -/** - * intel_microcode_sanity_check() - Sanity check microcode file. - * @mc: Pointer to the microcode file contents. - * @print_err: Display failure reason if true, silent if false. - * @hdr_type: Type of file, i.e. normal microcode file or In Field Scan file. - * Validate if the microcode header type matches with the type - * specified here. - * - * Validate certain header fields and verify if computed checksum matches - * with the one specified in the header. - * - * Return: 0 if the file passes all the checks, -EINVAL if any of the checks - * fail. - */ -int intel_microcode_sanity_check(void *mc, bool print_err, int hdr_type) -{ - unsigned long total_size, data_size, ext_table_size; - struct microcode_header_intel *mc_header = mc; - struct extended_sigtable *ext_header = NULL; - u32 sum, orig_sum, ext_sigcount = 0, i; - struct extended_signature *ext_sig; - - total_size = get_totalsize(mc_header); - data_size = get_datasize(mc_header); - - if (data_size + MC_HEADER_SIZE > total_size) { - if (print_err) - pr_err("Error: bad microcode data file size.\n"); - return -EINVAL; - } - - if (mc_header->ldrver != 1 || mc_header->hdrver != hdr_type) { - if (print_err) - pr_err("Error: invalid/unknown microcode update format. Header type %d\n", - mc_header->hdrver); - return -EINVAL; - } - - ext_table_size = total_size - (MC_HEADER_SIZE + data_size); - if (ext_table_size) { - u32 ext_table_sum = 0; - u32 *ext_tablep; - - if (ext_table_size < EXT_HEADER_SIZE || - ((ext_table_size - EXT_HEADER_SIZE) % EXT_SIGNATURE_SIZE)) { - if (print_err) - pr_err("Error: truncated extended signature table.\n"); - return -EINVAL; - } - - ext_header = mc + MC_HEADER_SIZE + data_size; - if (ext_table_size != exttable_size(ext_header)) { - if (print_err) - pr_err("Error: extended signature table size mismatch.\n"); - return -EFAULT; - } - - ext_sigcount = ext_header->count; - - /* - * Check extended table checksum: the sum of all dwords that - * comprise a valid table must be 0. - */ - ext_tablep = (u32 *)ext_header; - - i = ext_table_size / sizeof(u32); - while (i--) - ext_table_sum += ext_tablep[i]; - - if (ext_table_sum) { - if (print_err) - pr_warn("Bad extended signature table checksum, aborting.\n"); - return -EINVAL; - } - } - - /* - * Calculate the checksum of update data and header. The checksum of - * valid update data and header including the extended signature table - * must be 0. - */ - orig_sum = 0; - i = (MC_HEADER_SIZE + data_size) / sizeof(u32); - while (i--) - orig_sum += ((u32 *)mc)[i]; - - if (orig_sum) { - if (print_err) - pr_err("Bad microcode data checksum, aborting.\n"); - return -EINVAL; - } - - if (!ext_table_size) - return 0; - - /* - * Check extended signature checksum: 0 => valid. - */ - for (i = 0; i < ext_sigcount; i++) { - ext_sig = (void *)ext_header + EXT_HEADER_SIZE + - EXT_SIGNATURE_SIZE * i; - - sum = (mc_header->sig + mc_header->pf + mc_header->cksum) - - (ext_sig->sig + ext_sig->pf + ext_sig->cksum); - if (sum) { - if (print_err) - pr_err("Bad extended signature checksum, aborting.\n"); - return -EINVAL; - } - } - return 0; -} -EXPORT_SYMBOL_GPL(intel_microcode_sanity_check); - static void early_init_intel(struct cpuinfo_x86 *c) { u64 misc_enable; diff --git a/arch/x86/kernel/cpu/intel_epb.c b/arch/x86/kernel/cpu/intel_epb.c index 3b8476158236..e4c3ba91321c 100644 --- a/arch/x86/kernel/cpu/intel_epb.c +++ b/arch/x86/kernel/cpu/intel_epb.c @@ -206,7 +206,7 @@ static int intel_epb_offline(unsigned int cpu) static const struct x86_cpu_id intel_epb_normal[] = { X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, ENERGY_PERF_BIAS_NORMAL_POWERSAVE), - X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, + X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT, ENERGY_PERF_BIAS_NORMAL_POWERSAVE), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, ENERGY_PERF_BIAS_NORMAL_POWERSAVE), diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 89e2aab5d34d..6f35f724cc14 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -843,6 +843,26 @@ static noinstr bool quirk_skylake_repmov(void) } /* + * Some Zen-based Instruction Fetch Units set EIPV=RIPV=0 on poison consumption + * errors. This means mce_gather_info() will not save the "ip" and "cs" registers. + * + * However, the context is still valid, so save the "cs" register for later use. + * + * The "ip" register is truly unknown, so don't save it or fixup EIPV/RIPV. + * + * The Instruction Fetch Unit is at MCA bank 1 for all affected systems. + */ +static __always_inline void quirk_zen_ifu(int bank, struct mce *m, struct pt_regs *regs) +{ + if (bank != 1) + return; + if (!(m->status & MCI_STATUS_POISON)) + return; + + m->cs = regs->cs; +} + +/* * Do a quick check if any of the events requires a panic. * This decides if we keep the events around or clear them. */ @@ -861,6 +881,9 @@ static __always_inline int mce_no_way_out(struct mce *m, char **msg, unsigned lo if (mce_flags.snb_ifu_quirk) quirk_sandybridge_ifu(i, m, regs); + if (mce_flags.zen_ifu_quirk) + quirk_zen_ifu(i, m, regs); + m->bank = i; if (mce_severity(m, regs, &tmp, true) >= MCE_PANIC_SEVERITY) { mce_read_aux(m, i); @@ -1608,6 +1631,13 @@ static void __start_timer(struct timer_list *t, unsigned long interval) local_irq_restore(flags); } +static void mc_poll_banks_default(void) +{ + machine_check_poll(0, this_cpu_ptr(&mce_poll_banks)); +} + +void (*mc_poll_banks)(void) = mc_poll_banks_default; + static void mce_timer_fn(struct timer_list *t) { struct timer_list *cpu_t = this_cpu_ptr(&mce_timer); @@ -1618,7 +1648,7 @@ static void mce_timer_fn(struct timer_list *t) iv = __this_cpu_read(mce_next_interval); if (mce_available(this_cpu_ptr(&cpu_info))) { - machine_check_poll(0, this_cpu_ptr(&mce_poll_banks)); + mc_poll_banks(); if (mce_intel_cmci_poll()) { iv = mce_adjust_timer(iv); @@ -1842,6 +1872,9 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) if (c->x86 == 0x15 && c->x86_model <= 0xf) mce_flags.overflow_recov = 1; + if (c->x86 >= 0x17 && c->x86 <= 0x1A) + mce_flags.zen_ifu_quirk = 1; + } if (c->x86_vendor == X86_VENDOR_INTEL) { diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index 95275a5e57e0..f5323551c1a9 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -56,6 +56,13 @@ static DEFINE_PER_CPU(int, cmci_backoff_cnt); */ static DEFINE_RAW_SPINLOCK(cmci_discover_lock); +/* + * On systems that do support CMCI but it's disabled, polling for MCEs can + * cause the same event to be reported multiple times because IA32_MCi_STATUS + * is shared by the same package. + */ +static DEFINE_SPINLOCK(cmci_poll_lock); + #define CMCI_THRESHOLD 1 #define CMCI_POLL_INTERVAL (30 * HZ) #define CMCI_STORM_INTERVAL (HZ) @@ -426,12 +433,22 @@ void cmci_disable_bank(int bank) raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); } +/* Bank polling function when CMCI is disabled. */ +static void cmci_mc_poll_banks(void) +{ + spin_lock(&cmci_poll_lock); + machine_check_poll(0, this_cpu_ptr(&mce_poll_banks)); + spin_unlock(&cmci_poll_lock); +} + void intel_init_cmci(void) { int banks; - if (!cmci_supported(&banks)) + if (!cmci_supported(&banks)) { + mc_poll_banks = cmci_mc_poll_banks; return; + } mce_threshold_vector = intel_threshold_interrupt; cmci_discover(banks); diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index d2412ce2d312..bcf1b3c66c9c 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -157,6 +157,9 @@ struct mce_vendor_flags { */ smca : 1, + /* Zen IFU quirk */ + zen_ifu_quirk : 1, + /* AMD-style error thresholding banks present. */ amd_threshold : 1, @@ -172,7 +175,7 @@ struct mce_vendor_flags { /* Skylake, Cascade Lake, Cooper Lake REP;MOVS* quirk */ skx_repmov_quirk : 1, - __reserved_0 : 56; + __reserved_0 : 55; }; extern struct mce_vendor_flags mce_flags; @@ -274,4 +277,5 @@ static __always_inline u32 mca_msr_reg(int bank, enum mca_msr reg) return 0; } +extern void (*mc_poll_banks)(void); #endif /* __X86_MCE_INTERNAL_H__ */ diff --git a/arch/x86/kernel/cpu/microcode/Makefile b/arch/x86/kernel/cpu/microcode/Makefile index 34098d48c48f..193d98b33a0a 100644 --- a/arch/x86/kernel/cpu/microcode/Makefile +++ b/arch/x86/kernel/cpu/microcode/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only microcode-y := core.o obj-$(CONFIG_MICROCODE) += microcode.o -microcode-$(CONFIG_MICROCODE_INTEL) += intel.o -microcode-$(CONFIG_MICROCODE_AMD) += amd.o +microcode-$(CONFIG_CPU_SUP_INTEL) += intel.o +microcode-$(CONFIG_CPU_SUP_AMD) += amd.o diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 87208e46f7ed..bbd1dc38ea03 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -29,13 +29,53 @@ #include <linux/kernel.h> #include <linux/pci.h> -#include <asm/microcode_amd.h> #include <asm/microcode.h> #include <asm/processor.h> #include <asm/setup.h> #include <asm/cpu.h> #include <asm/msr.h> +#include "internal.h" + +#define UCODE_MAGIC 0x00414d44 +#define UCODE_EQUIV_CPU_TABLE_TYPE 0x00000000 +#define UCODE_UCODE_TYPE 0x00000001 + +#define SECTION_HDR_SIZE 8 +#define CONTAINER_HDR_SZ 12 + +struct equiv_cpu_entry { + u32 installed_cpu; + u32 fixed_errata_mask; + u32 fixed_errata_compare; + u16 equiv_cpu; + u16 res; +} __packed; + +struct microcode_header_amd { + u32 data_code; + u32 patch_id; + u16 mc_patch_data_id; + u8 mc_patch_data_len; + u8 init_flag; + u32 mc_patch_data_checksum; + u32 nb_dev_id; + u32 sb_dev_id; + u16 processor_rev_id; + u8 nb_rev_id; + u8 sb_rev_id; + u8 bios_api_rev; + u8 reserved1[3]; + u32 match_reg[8]; +} __packed; + +struct microcode_amd { + struct microcode_header_amd hdr; + unsigned int mpb[]; +}; + +#define PATCH_MAX_SIZE (3 * PAGE_SIZE) + static struct equiv_cpu_table { unsigned int num_entries; struct equiv_cpu_entry *entry; @@ -56,9 +96,6 @@ struct cont_desc { static u32 ucode_new_rev; -/* One blob per node. */ -static u8 amd_ucode_patch[MAX_NUMNODES][PATCH_MAX_SIZE]; - /* * Microcode patch container file is prepended to the initrd in cpio * format. See Documentation/arch/x86/microcode.rst @@ -415,20 +452,17 @@ static int __apply_microcode_amd(struct microcode_amd *mc) * * Returns true if container found (sets @desc), false otherwise. */ -static bool early_apply_microcode(u32 cpuid_1_eax, void *ucode, size_t size, bool save_patch) +static bool early_apply_microcode(u32 cpuid_1_eax, void *ucode, size_t size) { struct cont_desc desc = { 0 }; - u8 (*patch)[PATCH_MAX_SIZE]; struct microcode_amd *mc; u32 rev, dummy, *new_rev; bool ret = false; #ifdef CONFIG_X86_32 new_rev = (u32 *)__pa_nodebug(&ucode_new_rev); - patch = (u8 (*)[PATCH_MAX_SIZE])__pa_nodebug(&amd_ucode_patch); #else new_rev = &ucode_new_rev; - patch = &amd_ucode_patch[0]; #endif desc.cpuid_1_eax = cpuid_1_eax; @@ -452,9 +486,6 @@ static bool early_apply_microcode(u32 cpuid_1_eax, void *ucode, size_t size, boo if (!__apply_microcode_amd(mc)) { *new_rev = mc->hdr.patch_id; ret = true; - - if (save_patch) - memcpy(patch, mc, min_t(u32, desc.psize, PATCH_MAX_SIZE)); } return ret; @@ -507,7 +538,7 @@ static void find_blobs_in_containers(unsigned int cpuid_1_eax, struct cpio_data *ret = cp; } -void __init load_ucode_amd_bsp(unsigned int cpuid_1_eax) +static void apply_ucode_from_containers(unsigned int cpuid_1_eax) { struct cpio_data cp = { }; @@ -515,42 +546,12 @@ void __init load_ucode_amd_bsp(unsigned int cpuid_1_eax) if (!(cp.data && cp.size)) return; - early_apply_microcode(cpuid_1_eax, cp.data, cp.size, true); + early_apply_microcode(cpuid_1_eax, cp.data, cp.size); } -void load_ucode_amd_ap(unsigned int cpuid_1_eax) +void load_ucode_amd_early(unsigned int cpuid_1_eax) { - struct microcode_amd *mc; - struct cpio_data cp; - u32 *new_rev, rev, dummy; - - if (IS_ENABLED(CONFIG_X86_32)) { - mc = (struct microcode_amd *)__pa_nodebug(amd_ucode_patch); - new_rev = (u32 *)__pa_nodebug(&ucode_new_rev); - } else { - mc = (struct microcode_amd *)amd_ucode_patch; - new_rev = &ucode_new_rev; - } - - native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); - - /* - * Check whether a new patch has been saved already. Also, allow application of - * the same revision in order to pick up SMT-thread-specific configuration even - * if the sibling SMT thread already has an up-to-date revision. - */ - if (*new_rev && rev <= mc->hdr.patch_id) { - if (!__apply_microcode_amd(mc)) { - *new_rev = mc->hdr.patch_id; - return; - } - } - - find_blobs_in_containers(cpuid_1_eax, &cp); - if (!(cp.data && cp.size)) - return; - - early_apply_microcode(cpuid_1_eax, cp.data, cp.size, false); + return apply_ucode_from_containers(cpuid_1_eax); } static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size); @@ -578,23 +579,6 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax) return 0; } -void reload_ucode_amd(unsigned int cpu) -{ - u32 rev, dummy __always_unused; - struct microcode_amd *mc; - - mc = (struct microcode_amd *)amd_ucode_patch[cpu_to_node(cpu)]; - - rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); - - if (rev < mc->hdr.patch_id) { - if (!__apply_microcode_amd(mc)) { - ucode_new_rev = mc->hdr.patch_id; - pr_info("reload patch_level=0x%08x\n", ucode_new_rev); - } - } -} - /* * a small, trivial cache of per-family ucode patches */ @@ -655,6 +639,28 @@ static struct ucode_patch *find_patch(unsigned int cpu) return cache_find_patch(equiv_id); } +void reload_ucode_amd(unsigned int cpu) +{ + u32 rev, dummy __always_unused; + struct microcode_amd *mc; + struct ucode_patch *p; + + p = find_patch(cpu); + if (!p) + return; + + mc = p->data; + + rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); + + if (rev < mc->hdr.patch_id) { + if (!__apply_microcode_amd(mc)) { + ucode_new_rev = mc->hdr.patch_id; + pr_info("reload patch_level=0x%08x\n", ucode_new_rev); + } + } +} + static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig) { struct cpuinfo_x86 *c = &cpu_data(cpu); @@ -875,9 +881,6 @@ static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t siz continue; ret = UCODE_NEW; - - memset(&amd_ucode_patch[nid], 0, PATCH_MAX_SIZE); - memcpy(&amd_ucode_patch[nid], p->data, min_t(u32, p->size, PATCH_MAX_SIZE)); } return ret; diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 3afcf3de0dd4..6cc7a2c181da 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -31,15 +31,14 @@ #include <linux/fs.h> #include <linux/mm.h> -#include <asm/microcode_intel.h> #include <asm/cpu_device_id.h> -#include <asm/microcode_amd.h> #include <asm/perf_event.h> -#include <asm/microcode.h> #include <asm/processor.h> #include <asm/cmdline.h> #include <asm/setup.h> +#include "internal.h" + #define DRIVER_VERSION "2.2" static struct microcode_ops *microcode_ops; @@ -54,15 +53,12 @@ LIST_HEAD(microcode_cache); * * All non cpu-hotplug-callback call sites use: * - * - microcode_mutex to synchronize with each other; * - cpus_read_lock/unlock() to synchronize with * the cpu-hotplug-callback call sites. * * We guarantee that only a single cpu is being * updated at any particular moment of time. */ -static DEFINE_MUTEX(microcode_mutex); - struct ucode_cpu_info ucode_cpu_info[NR_CPUS]; struct cpu_info_ctx { @@ -172,7 +168,7 @@ void __init load_ucode_bsp(void) if (intel) load_ucode_intel_bsp(); else - load_ucode_amd_bsp(cpuid_1_eax); + load_ucode_amd_early(cpuid_1_eax); } static bool check_loader_disabled_ap(void) @@ -200,7 +196,7 @@ void load_ucode_ap(void) break; case X86_VENDOR_AMD: if (x86_family(cpuid_1_eax) >= 0x10) - load_ucode_amd_ap(cpuid_1_eax); + load_ucode_amd_early(cpuid_1_eax); break; default: break; @@ -298,7 +294,7 @@ struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa) #endif } -void reload_early_microcode(unsigned int cpu) +static void reload_early_microcode(unsigned int cpu) { int vendor, family; @@ -488,10 +484,7 @@ static ssize_t reload_store(struct device *dev, if (tmp_ret != UCODE_NEW) goto put; - mutex_lock(µcode_mutex); ret = microcode_reload_late(); - mutex_unlock(µcode_mutex); - put: cpus_read_unlock(); diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 467cf37ea90a..94dd6af9c963 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -10,15 +10,7 @@ * Copyright (C) 2012 Fenghua Yu <fenghua.yu@intel.com> * H Peter Anvin" <hpa@zytor.com> */ - -/* - * This needs to be before all headers so that pr_debug in printk.h doesn't turn - * printk calls into no_printk(). - * - *#define DEBUG - */ #define pr_fmt(fmt) "microcode: " fmt - #include <linux/earlycpio.h> #include <linux/firmware.h> #include <linux/uaccess.h> @@ -30,13 +22,14 @@ #include <linux/uio.h> #include <linux/mm.h> -#include <asm/microcode_intel.h> #include <asm/intel-family.h> #include <asm/processor.h> #include <asm/tlbflush.h> #include <asm/setup.h> #include <asm/msr.h> +#include "internal.h" + static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin"; /* Current microcode patch used in early patching on the APs. */ @@ -45,6 +38,208 @@ static struct microcode_intel *intel_ucode_patch; /* last level cache size per core */ static int llc_size_per_core; +/* microcode format is extended from prescott processors */ +struct extended_signature { + unsigned int sig; + unsigned int pf; + unsigned int cksum; +}; + +struct extended_sigtable { + unsigned int count; + unsigned int cksum; + unsigned int reserved[3]; + struct extended_signature sigs[]; +}; + +#define DEFAULT_UCODE_TOTALSIZE (DEFAULT_UCODE_DATASIZE + MC_HEADER_SIZE) +#define EXT_HEADER_SIZE (sizeof(struct extended_sigtable)) +#define EXT_SIGNATURE_SIZE (sizeof(struct extended_signature)) + +static inline unsigned int get_totalsize(struct microcode_header_intel *hdr) +{ + return hdr->datasize ? hdr->totalsize : DEFAULT_UCODE_TOTALSIZE; +} + +static inline unsigned int exttable_size(struct extended_sigtable *et) +{ + return et->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE; +} + +int intel_cpu_collect_info(struct ucode_cpu_info *uci) +{ + unsigned int val[2]; + unsigned int family, model; + struct cpu_signature csig = { 0 }; + unsigned int eax, ebx, ecx, edx; + + memset(uci, 0, sizeof(*uci)); + + eax = 0x00000001; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + csig.sig = eax; + + family = x86_family(eax); + model = x86_model(eax); + + if (model >= 5 || family > 6) { + /* get processor flags from MSR 0x17 */ + native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]); + csig.pf = 1 << ((val[1] >> 18) & 7); + } + + csig.rev = intel_get_microcode_revision(); + + uci->cpu_sig = csig; + + return 0; +} +EXPORT_SYMBOL_GPL(intel_cpu_collect_info); + +/* + * Returns 1 if update has been found, 0 otherwise. + */ +int intel_find_matching_signature(void *mc, unsigned int csig, int cpf) +{ + struct microcode_header_intel *mc_hdr = mc; + struct extended_sigtable *ext_hdr; + struct extended_signature *ext_sig; + int i; + + if (intel_cpu_signatures_match(csig, cpf, mc_hdr->sig, mc_hdr->pf)) + return 1; + + /* Look for ext. headers: */ + if (get_totalsize(mc_hdr) <= intel_microcode_get_datasize(mc_hdr) + MC_HEADER_SIZE) + return 0; + + ext_hdr = mc + intel_microcode_get_datasize(mc_hdr) + MC_HEADER_SIZE; + ext_sig = (void *)ext_hdr + EXT_HEADER_SIZE; + + for (i = 0; i < ext_hdr->count; i++) { + if (intel_cpu_signatures_match(csig, cpf, ext_sig->sig, ext_sig->pf)) + return 1; + ext_sig++; + } + return 0; +} +EXPORT_SYMBOL_GPL(intel_find_matching_signature); + +/** + * intel_microcode_sanity_check() - Sanity check microcode file. + * @mc: Pointer to the microcode file contents. + * @print_err: Display failure reason if true, silent if false. + * @hdr_type: Type of file, i.e. normal microcode file or In Field Scan file. + * Validate if the microcode header type matches with the type + * specified here. + * + * Validate certain header fields and verify if computed checksum matches + * with the one specified in the header. + * + * Return: 0 if the file passes all the checks, -EINVAL if any of the checks + * fail. + */ +int intel_microcode_sanity_check(void *mc, bool print_err, int hdr_type) +{ + unsigned long total_size, data_size, ext_table_size; + struct microcode_header_intel *mc_header = mc; + struct extended_sigtable *ext_header = NULL; + u32 sum, orig_sum, ext_sigcount = 0, i; + struct extended_signature *ext_sig; + + total_size = get_totalsize(mc_header); + data_size = intel_microcode_get_datasize(mc_header); + + if (data_size + MC_HEADER_SIZE > total_size) { + if (print_err) + pr_err("Error: bad microcode data file size.\n"); + return -EINVAL; + } + + if (mc_header->ldrver != 1 || mc_header->hdrver != hdr_type) { + if (print_err) + pr_err("Error: invalid/unknown microcode update format. Header type %d\n", + mc_header->hdrver); + return -EINVAL; + } + + ext_table_size = total_size - (MC_HEADER_SIZE + data_size); + if (ext_table_size) { + u32 ext_table_sum = 0; + u32 *ext_tablep; + + if (ext_table_size < EXT_HEADER_SIZE || + ((ext_table_size - EXT_HEADER_SIZE) % EXT_SIGNATURE_SIZE)) { + if (print_err) + pr_err("Error: truncated extended signature table.\n"); + return -EINVAL; + } + + ext_header = mc + MC_HEADER_SIZE + data_size; + if (ext_table_size != exttable_size(ext_header)) { + if (print_err) + pr_err("Error: extended signature table size mismatch.\n"); + return -EFAULT; + } + + ext_sigcount = ext_header->count; + + /* + * Check extended table checksum: the sum of all dwords that + * comprise a valid table must be 0. + */ + ext_tablep = (u32 *)ext_header; + + i = ext_table_size / sizeof(u32); + while (i--) + ext_table_sum += ext_tablep[i]; + + if (ext_table_sum) { + if (print_err) + pr_warn("Bad extended signature table checksum, aborting.\n"); + return -EINVAL; + } + } + + /* + * Calculate the checksum of update data and header. The checksum of + * valid update data and header including the extended signature table + * must be 0. + */ + orig_sum = 0; + i = (MC_HEADER_SIZE + data_size) / sizeof(u32); + while (i--) + orig_sum += ((u32 *)mc)[i]; + + if (orig_sum) { + if (print_err) + pr_err("Bad microcode data checksum, aborting.\n"); + return -EINVAL; + } + + if (!ext_table_size) + return 0; + + /* + * Check extended signature checksum: 0 => valid. + */ + for (i = 0; i < ext_sigcount; i++) { + ext_sig = (void *)ext_header + EXT_HEADER_SIZE + + EXT_SIGNATURE_SIZE * i; + + sum = (mc_header->sig + mc_header->pf + mc_header->cksum) - + (ext_sig->sig + ext_sig->pf + ext_sig->cksum); + if (sum) { + if (print_err) + pr_err("Bad extended signature checksum, aborting.\n"); + return -EINVAL; + } + } + return 0; +} +EXPORT_SYMBOL_GPL(intel_microcode_sanity_check); + /* * Returns 1 if update has been found, 0 otherwise. */ @@ -202,86 +397,6 @@ next: return patch; } -static void show_saved_mc(void) -{ -#ifdef DEBUG - int i = 0, j; - unsigned int sig, pf, rev, total_size, data_size, date; - struct ucode_cpu_info uci; - struct ucode_patch *p; - - if (list_empty(µcode_cache)) { - pr_debug("no microcode data saved.\n"); - return; - } - - intel_cpu_collect_info(&uci); - - sig = uci.cpu_sig.sig; - pf = uci.cpu_sig.pf; - rev = uci.cpu_sig.rev; - pr_debug("CPU: sig=0x%x, pf=0x%x, rev=0x%x\n", sig, pf, rev); - - list_for_each_entry(p, µcode_cache, plist) { - struct microcode_header_intel *mc_saved_header; - struct extended_sigtable *ext_header; - struct extended_signature *ext_sig; - int ext_sigcount; - - mc_saved_header = (struct microcode_header_intel *)p->data; - - sig = mc_saved_header->sig; - pf = mc_saved_header->pf; - rev = mc_saved_header->rev; - date = mc_saved_header->date; - - total_size = get_totalsize(mc_saved_header); - data_size = get_datasize(mc_saved_header); - - pr_debug("mc_saved[%d]: sig=0x%x, pf=0x%x, rev=0x%x, total size=0x%x, date = %04x-%02x-%02x\n", - i++, sig, pf, rev, total_size, - date & 0xffff, - date >> 24, - (date >> 16) & 0xff); - - /* Look for ext. headers: */ - if (total_size <= data_size + MC_HEADER_SIZE) - continue; - - ext_header = (void *)mc_saved_header + data_size + MC_HEADER_SIZE; - ext_sigcount = ext_header->count; - ext_sig = (void *)ext_header + EXT_HEADER_SIZE; - - for (j = 0; j < ext_sigcount; j++) { - sig = ext_sig->sig; - pf = ext_sig->pf; - - pr_debug("\tExtended[%d]: sig=0x%x, pf=0x%x\n", - j, sig, pf); - - ext_sig++; - } - } -#endif -} - -/* - * Save this microcode patch. It will be loaded early when a CPU is - * hot-added or resumes. - */ -static void save_mc_for_early(struct ucode_cpu_info *uci, u8 *mc, unsigned int size) -{ - /* Synchronization during CPU hotplug. */ - static DEFINE_MUTEX(x86_cpu_microcode_mutex); - - mutex_lock(&x86_cpu_microcode_mutex); - - save_microcode_patch(uci, mc, size); - show_saved_mc(); - - mutex_unlock(&x86_cpu_microcode_mutex); -} - static bool load_builtin_intel_microcode(struct cpio_data *cp) { unsigned int eax = 1, ebx, ecx = 0, edx; @@ -428,9 +543,6 @@ int __init save_microcode_in_initrd_intel(void) intel_cpu_collect_info(&uci); scan_microcode(cp.data, cp.size, &uci, true); - - show_saved_mc(); - return 0; } @@ -701,12 +813,8 @@ static enum ucode_state generic_load_microcode(int cpu, struct iov_iter *iter) vfree(uci->mc); uci->mc = (struct microcode_intel *)new_mc; - /* - * If early loading microcode is supported, save this mc into - * permanent memory. So it will be loaded early when a CPU is hot added - * or resumes. - */ - save_mc_for_early(uci, new_mc, new_mc_size); + /* Save for CPU hotplug */ + save_microcode_patch(uci, new_mc, new_mc_size); pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n", cpu, new_rev, uci->cpu_sig.rev); diff --git a/arch/x86/kernel/cpu/microcode/internal.h b/arch/x86/kernel/cpu/microcode/internal.h new file mode 100644 index 000000000000..bf883aa71233 --- /dev/null +++ b/arch/x86/kernel/cpu/microcode/internal.h @@ -0,0 +1,131 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _X86_MICROCODE_INTERNAL_H +#define _X86_MICROCODE_INTERNAL_H + +#include <linux/earlycpio.h> +#include <linux/initrd.h> + +#include <asm/cpu.h> +#include <asm/microcode.h> + +struct ucode_patch { + struct list_head plist; + void *data; /* Intel uses only this one */ + unsigned int size; + u32 patch_id; + u16 equiv_cpu; +}; + +extern struct list_head microcode_cache; + +struct device; + +enum ucode_state { + UCODE_OK = 0, + UCODE_NEW, + UCODE_UPDATED, + UCODE_NFOUND, + UCODE_ERROR, +}; + +struct microcode_ops { + enum ucode_state (*request_microcode_fw)(int cpu, struct device *dev); + + void (*microcode_fini_cpu)(int cpu); + + /* + * The generic 'microcode_core' part guarantees that + * the callbacks below run on a target cpu when they + * are being called. + * See also the "Synchronization" section in microcode_core.c. + */ + enum ucode_state (*apply_microcode)(int cpu); + int (*collect_cpu_info)(int cpu, struct cpu_signature *csig); +}; + +extern struct ucode_cpu_info ucode_cpu_info[]; +struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa); + +#define MAX_UCODE_COUNT 128 + +#define QCHAR(a, b, c, d) ((a) + ((b) << 8) + ((c) << 16) + ((d) << 24)) +#define CPUID_INTEL1 QCHAR('G', 'e', 'n', 'u') +#define CPUID_INTEL2 QCHAR('i', 'n', 'e', 'I') +#define CPUID_INTEL3 QCHAR('n', 't', 'e', 'l') +#define CPUID_AMD1 QCHAR('A', 'u', 't', 'h') +#define CPUID_AMD2 QCHAR('e', 'n', 't', 'i') +#define CPUID_AMD3 QCHAR('c', 'A', 'M', 'D') + +#define CPUID_IS(a, b, c, ebx, ecx, edx) \ + (!(((ebx) ^ (a)) | ((edx) ^ (b)) | ((ecx) ^ (c)))) + +/* + * In early loading microcode phase on BSP, boot_cpu_data is not set up yet. + * x86_cpuid_vendor() gets vendor id for BSP. + * + * In 32 bit AP case, accessing boot_cpu_data needs linear address. To simplify + * coding, we still use x86_cpuid_vendor() to get vendor id for AP. + * + * x86_cpuid_vendor() gets vendor information directly from CPUID. + */ +static inline int x86_cpuid_vendor(void) +{ + u32 eax = 0x00000000; + u32 ebx, ecx = 0, edx; + + native_cpuid(&eax, &ebx, &ecx, &edx); + + if (CPUID_IS(CPUID_INTEL1, CPUID_INTEL2, CPUID_INTEL3, ebx, ecx, edx)) + return X86_VENDOR_INTEL; + + if (CPUID_IS(CPUID_AMD1, CPUID_AMD2, CPUID_AMD3, ebx, ecx, edx)) + return X86_VENDOR_AMD; + + return X86_VENDOR_UNKNOWN; +} + +static inline unsigned int x86_cpuid_family(void) +{ + u32 eax = 0x00000001; + u32 ebx, ecx = 0, edx; + + native_cpuid(&eax, &ebx, &ecx, &edx); + + return x86_family(eax); +} + +extern bool initrd_gone; + +#ifdef CONFIG_CPU_SUP_AMD +void load_ucode_amd_bsp(unsigned int family); +void load_ucode_amd_ap(unsigned int family); +void load_ucode_amd_early(unsigned int cpuid_1_eax); +int save_microcode_in_initrd_amd(unsigned int family); +void reload_ucode_amd(unsigned int cpu); +struct microcode_ops *init_amd_microcode(void); +void exit_amd_microcode(void); +#else /* CONFIG_CPU_SUP_AMD */ +static inline void load_ucode_amd_bsp(unsigned int family) { } +static inline void load_ucode_amd_ap(unsigned int family) { } +static inline void load_ucode_amd_early(unsigned int family) { } +static inline int save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; } +static inline void reload_ucode_amd(unsigned int cpu) { } +static inline struct microcode_ops *init_amd_microcode(void) { return NULL; } +static inline void exit_amd_microcode(void) { } +#endif /* !CONFIG_CPU_SUP_AMD */ + +#ifdef CONFIG_CPU_SUP_INTEL +void load_ucode_intel_bsp(void); +void load_ucode_intel_ap(void); +int save_microcode_in_initrd_intel(void); +void reload_ucode_intel(void); +struct microcode_ops *init_intel_microcode(void); +#else /* CONFIG_CPU_SUP_INTEL */ +static inline void load_ucode_intel_bsp(void) { } +static inline void load_ucode_intel_ap(void) { } +static inline int save_microcode_in_initrd_intel(void) { return -EINVAL; } +static inline void reload_ucode_intel(void) { } +static inline struct microcode_ops *init_intel_microcode(void) { return NULL; } +#endif /* !CONFIG_CPU_SUP_INTEL */ + +#endif /* _X86_MICROCODE_INTERNAL_H */ diff --git a/arch/x86/kernel/fpu/context.h b/arch/x86/kernel/fpu/context.h index af5cbdd9bd29..f6d856bd50bc 100644 --- a/arch/x86/kernel/fpu/context.h +++ b/arch/x86/kernel/fpu/context.h @@ -19,8 +19,7 @@ * FPU state for a task MUST let the rest of the kernel know that the * FPU registers are no longer valid for this task. * - * Either one of these invalidation functions is enough. Invalidate - * a resource you control: CPU if using the CPU for something else + * Invalidate a resource you control: CPU if using the CPU for something else * (with preemption disabled), FPU for the current task, or a task that * is prevented from running by the current task. */ diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 1015af1ae562..98e507cc7d34 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -679,7 +679,7 @@ static void fpu_reset_fpregs(void) struct fpu *fpu = ¤t->thread.fpu; fpregs_lock(); - fpu__drop(fpu); + __fpu_invalidate_fpregs_state(fpu); /* * This does not change the actual hardware registers. It just * resets the memory image and sets TIF_NEED_FPU_LOAD so a diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 0bab497c9436..1afbc4866b10 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -882,6 +882,13 @@ void __init fpu__init_system_xstate(unsigned int legacy_size) goto out_disable; } + /* + * CPU capabilities initialization runs before FPU init. So + * X86_FEATURE_OSXSAVE is not set. Now that XSAVE is completely + * functional, set the feature bit so depending code works. + */ + setup_force_cpu_cap(X86_FEATURE_OSXSAVE); + print_xstate_offset_size(); pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n", fpu_kernel_cfg.max_features, diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index c5b9289837dc..ea6995920b7a 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -51,7 +51,9 @@ SYM_CODE_START_NOALIGN(startup_64) * for us. These identity mapped page tables map all of the * kernel pages and possibly all of memory. * - * %rsi holds a physical pointer to real_mode_data. + * %RSI holds the physical address of the boot_params structure + * provided by the bootloader. Preserve it in %R15 so C function calls + * will not clobber it. * * We come here either directly from a 64bit bootloader, or from * arch/x86/boot/compressed/head_64.S. @@ -62,6 +64,7 @@ SYM_CODE_START_NOALIGN(startup_64) * compiled to run at we first fixup the physical addresses in our page * tables and then reload them. */ + mov %rsi, %r15 /* Set up the stack for verify_cpu() */ leaq (__end_init_task - PTREGS_SIZE)(%rip), %rsp @@ -75,9 +78,7 @@ SYM_CODE_START_NOALIGN(startup_64) shrq $32, %rdx wrmsr - pushq %rsi call startup_64_setup_env - popq %rsi /* Now switch to __KERNEL_CS so IRET works reliably */ pushq $__KERNEL_CS @@ -93,12 +94,10 @@ SYM_CODE_START_NOALIGN(startup_64) * Activate SEV/SME memory encryption if supported/enabled. This needs to * be done now, since this also includes setup of the SEV-SNP CPUID table, * which needs to be done before any CPUID instructions are executed in - * subsequent code. + * subsequent code. Pass the boot_params pointer as the first argument. */ - movq %rsi, %rdi - pushq %rsi + movq %r15, %rdi call sme_enable - popq %rsi #endif /* Sanitize CPU configuration */ @@ -111,9 +110,8 @@ SYM_CODE_START_NOALIGN(startup_64) * programmed into CR3. */ leaq _text(%rip), %rdi - pushq %rsi + movq %r15, %rsi call __startup_64 - popq %rsi /* Form the CR3 value being sure to include the CR3 modifier */ addq $(early_top_pgt - __START_KERNEL_map), %rax @@ -127,8 +125,6 @@ SYM_CODE_START(secondary_startup_64) * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 0, * and someone has loaded a mapped page table. * - * %rsi holds a physical pointer to real_mode_data. - * * We come here either from startup_64 (using physical addresses) * or from trampoline.S (using virtual addresses). * @@ -153,6 +149,9 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) UNWIND_HINT_END_OF_STACK ANNOTATE_NOENDBR + /* Clear %R15 which holds the boot_params pointer on the boot CPU */ + xorq %r15, %r15 + /* * Retrieve the modifier (SME encryption mask if SME is active) to be * added to the initial pgdir entry that will be programmed into CR3. @@ -199,13 +198,9 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) * hypervisor could lie about the C-bit position to perform a ROP * attack on the guest by writing to the unencrypted stack and wait for * the next RET instruction. - * %rsi carries pointer to realmode data and is callee-clobbered. Save - * and restore it. */ - pushq %rsi movq %rax, %rdi call sev_verify_cbit - popq %rsi /* * Switch to new page-table @@ -365,9 +360,7 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) wrmsr /* Setup and Load IDT */ - pushq %rsi call early_setup_idt - popq %rsi /* Check if nx is implemented */ movl $0x80000001, %eax @@ -403,9 +396,8 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) pushq $0 popfq - /* rsi is pointer to real mode structure with interesting info. - pass it to C */ - movq %rsi, %rdi + /* Pass the boot_params pointer as first argument */ + movq %r15, %rdi .Ljump_to_C_code: /* diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index c8eb1ac5125a..1648aa0204d9 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -421,7 +421,7 @@ static void __init hpet_legacy_clockevent_register(struct hpet_channel *hc) * the IO_APIC has been initialized. */ hc->cpu = boot_cpu_data.cpu_index; - strncpy(hc->name, "hpet", sizeof(hc->name)); + strscpy(hc->name, "hpet", sizeof(hc->name)); hpet_init_clockevent(hc, 50); hc->evt.tick_resume = hpet_clkevt_legacy_resume; diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 1cceac5984da..526d4da3dcd4 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -966,10 +966,8 @@ static void __init kvm_init_platform(void) * Ensure that _bss_decrypted section is marked as decrypted in the * shared pages list. */ - nr_pages = DIV_ROUND_UP(__end_bss_decrypted - __start_bss_decrypted, - PAGE_SIZE); early_set_mem_enc_dec_hypercall((unsigned long)__start_bss_decrypted, - nr_pages, 0); + __end_bss_decrypted - __start_bss_decrypted, 0); /* * If not booted using EFI, enable Live migration support. diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index ac10b46c5832..975f98d5eee5 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -75,10 +75,16 @@ DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key); void __init native_pv_lock_init(void) { - if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) + if (IS_ENABLED(CONFIG_PARAVIRT_SPINLOCKS) && + !boot_cpu_has(X86_FEATURE_HYPERVISOR)) static_branch_disable(&virt_spin_lock_key); } +static void native_tlb_remove_table(struct mmu_gather *tlb, void *table) +{ + tlb_remove_page(tlb, table); +} + unsigned int paravirt_patch(u8 type, void *insn_buff, unsigned long addr, unsigned int len) { @@ -295,8 +301,7 @@ struct paravirt_patch_template pv_ops = { .mmu.flush_tlb_kernel = native_flush_tlb_global, .mmu.flush_tlb_one_user = native_flush_tlb_one_user, .mmu.flush_tlb_multi = native_flush_tlb_multi, - .mmu.tlb_remove_table = - (void (*)(struct mmu_gather *, void *))tlb_remove_page, + .mmu.tlb_remove_table = native_tlb_remove_table, .mmu.exit_mmap = paravirt_nop, .mmu.notify_page_enc_status_changed = paravirt_nop, diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index 1ee7bed453de..d380c9399480 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -1575,6 +1575,9 @@ static enum es_result vc_handle_dr7_write(struct ghcb *ghcb, long val, *reg = vc_insn_get_rm(ctxt); enum es_result ret; + if (sev_status & MSR_AMD64_SNP_DEBUG_SWAP) + return ES_VMM_ERROR; + if (!reg) return ES_DECODE_FAILED; @@ -1612,6 +1615,9 @@ static enum es_result vc_handle_dr7_read(struct ghcb *ghcb, struct sev_es_runtime_data *data = this_cpu_read(runtime_data); long *reg = vc_insn_get_rm(ctxt); + if (sev_status & MSR_AMD64_SNP_DEBUG_SWAP) + return ES_VMM_ERROR; + if (!reg) return ES_DECODE_FAILED; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index e1aa2cd7734b..d40ed3a7dc23 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -327,14 +327,6 @@ static void notrace start_secondary(void *unused) } /** - * topology_smt_supported - Check whether SMT is supported by the CPUs - */ -bool topology_smt_supported(void) -{ - return smp_num_siblings > 1; -} - -/** * topology_phys_to_logical_pkg - Map a physical package id to a logical * @phys_pkg: The physical package id to map * @@ -632,14 +624,9 @@ static void __init build_sched_topology(void) }; #endif #ifdef CONFIG_SCHED_CLUSTER - /* - * For now, skip the cluster domain on Hybrid. - */ - if (!cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) { - x86_topology[i++] = (struct sched_domain_topology_level){ - cpu_clustergroup_mask, x86_cluster_flags, SD_INIT_NAME(CLS) - }; - } + x86_topology[i++] = (struct sched_domain_topology_level){ + cpu_clustergroup_mask, x86_cluster_flags, SD_INIT_NAME(CLS) + }; #endif #ifdef CONFIG_SCHED_MC x86_topology[i++] = (struct sched_domain_topology_level){ diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 3425c6a943e4..15f97c0abc9d 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1258,7 +1258,7 @@ static void __init check_system_tsc_reliable(void) if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC) && boot_cpu_has(X86_FEATURE_NONSTOP_TSC) && boot_cpu_has(X86_FEATURE_TSC_ADJUST) && - nr_online_nodes <= 2) + nr_online_nodes <= 4) tsc_disable_clocksource_watchdog(); } diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 8192452d1d2d..ffa25e962343 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -20,7 +20,6 @@ #include <asm/tlb.h> #include <asm/proto.h> #include <asm/dma.h> /* for MAX_DMA_PFN */ -#include <asm/microcode.h> #include <asm/kaslr.h> #include <asm/hypervisor.h> #include <asm/cpufeature.h> @@ -273,7 +272,7 @@ static void __init probe_page_size_mask(void) static const struct x86_cpu_id invlpg_miss_ids[] = { INTEL_MATCH(INTEL_FAM6_ALDERLAKE ), INTEL_MATCH(INTEL_FAM6_ALDERLAKE_L ), - INTEL_MATCH(INTEL_FAM6_ALDERLAKE_N ), + INTEL_MATCH(INTEL_FAM6_ATOM_GRACEMONT ), INTEL_MATCH(INTEL_FAM6_RAPTORLAKE ), INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_P), INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_S), diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c index 54bbd5163e8d..6faea41e99b6 100644 --- a/arch/x86/mm/mem_encrypt_amd.c +++ b/arch/x86/mm/mem_encrypt_amd.c @@ -288,11 +288,10 @@ static bool amd_enc_cache_flush_required(void) return !cpu_feature_enabled(X86_FEATURE_SME_COHERENT); } -static void enc_dec_hypercall(unsigned long vaddr, int npages, bool enc) +static void enc_dec_hypercall(unsigned long vaddr, unsigned long size, bool enc) { #ifdef CONFIG_PARAVIRT - unsigned long sz = npages << PAGE_SHIFT; - unsigned long vaddr_end = vaddr + sz; + unsigned long vaddr_end = vaddr + size; while (vaddr < vaddr_end) { int psize, pmask, level; @@ -342,7 +341,7 @@ static bool amd_enc_status_change_finish(unsigned long vaddr, int npages, bool e snp_set_memory_private(vaddr, npages); if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) - enc_dec_hypercall(vaddr, npages, enc); + enc_dec_hypercall(vaddr, npages << PAGE_SHIFT, enc); return true; } @@ -466,7 +465,7 @@ static int __init early_set_memory_enc_dec(unsigned long vaddr, ret = 0; - early_set_mem_enc_dec_hypercall(start, PAGE_ALIGN(size) >> PAGE_SHIFT, enc); + early_set_mem_enc_dec_hypercall(start, size, enc); out: __flush_tlb_all(); return ret; @@ -482,9 +481,9 @@ int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size) return early_set_memory_enc_dec(vaddr, size, true); } -void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, bool enc) +void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, unsigned long size, bool enc) { - enc_dec_hypercall(vaddr, npages, enc); + enc_dec_hypercall(vaddr, size, enc); } void __init sme_early_init(void) diff --git a/arch/x86/platform/efi/memmap.c b/arch/x86/platform/efi/memmap.c index c69f8471e6d0..4ef20b49eb5e 100644 --- a/arch/x86/platform/efi/memmap.c +++ b/arch/x86/platform/efi/memmap.c @@ -82,7 +82,7 @@ int __init efi_memmap_alloc(unsigned int num_entries, /** * efi_memmap_install - Install a new EFI memory map in efi.memmap - * @ctx: map allocation parameters (address, size, flags) + * @data: efi memmap installation parameters * * Unlike efi_memmap_init_*(), this function does not allow the caller * to switch from early to late mappings. It simply uses the existing diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c index a60af0230e27..a6ab43f69b7d 100644 --- a/arch/x86/platform/uv/uv_nmi.c +++ b/arch/x86/platform/uv/uv_nmi.c @@ -202,21 +202,17 @@ static int param_set_action(const char *val, const struct kernel_param *kp) { int i; int n = ARRAY_SIZE(valid_acts); - char arg[ACTION_LEN], *p; + char arg[ACTION_LEN]; /* (remove possible '\n') */ - strncpy(arg, val, ACTION_LEN - 1); - arg[ACTION_LEN - 1] = '\0'; - p = strchr(arg, '\n'); - if (p) - *p = '\0'; + strscpy(arg, val, strnchrnul(val, sizeof(arg)-1, '\n') - val + 1); for (i = 0; i < n; i++) if (!strcmp(arg, valid_acts[i].action)) break; if (i < n) { - strcpy(uv_nmi_action, arg); + strscpy(uv_nmi_action, arg, sizeof(uv_nmi_action)); pr_info("UV: New NMI action:%s\n", uv_nmi_action); return 0; } @@ -959,7 +955,7 @@ static int uv_handle_nmi(unsigned int reason, struct pt_regs *regs) /* Unexpected return, revert action to "dump" */ if (master) - strncpy(uv_nmi_action, "dump", strlen(uv_nmi_action)); + strscpy(uv_nmi_action, "dump", sizeof(uv_nmi_action)); } /* Pause as all CPU's enter the NMI handler */ diff --git a/arch/x86/purgatory/purgatory.c b/arch/x86/purgatory/purgatory.c index 7558139920f8..aea47e793963 100644 --- a/arch/x86/purgatory/purgatory.c +++ b/arch/x86/purgatory/purgatory.c @@ -14,6 +14,7 @@ #include <crypto/sha2.h> #include <asm/purgatory.h> +#include "../boot/compressed/error.h" #include "../boot/string.h" u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE] __section(".kexec-purgatory"); diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index a3864e2167a8..27fc170838e9 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -523,7 +523,7 @@ static void __init xen_load_gdt_boot(const struct desc_ptr *dtr) BUG_ON(size > PAGE_SIZE); BUG_ON(va & ~PAGE_MASK); - pfn = virt_to_pfn(va); + pfn = virt_to_pfn((void *)va); mfn = pfn_to_mfn(pfn); pte = pfn_pte(pfn, PAGE_KERNEL_RO); diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index e0a975165de7..eb3bac0b22a1 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -2202,13 +2202,13 @@ static void xen_zap_pfn_range(unsigned long vaddr, unsigned int order, mcs = __xen_mc_entry(0); if (in_frames) - in_frames[i] = virt_to_mfn(vaddr); + in_frames[i] = virt_to_mfn((void *)vaddr); MULTI_update_va_mapping(mcs.mc, vaddr, VOID_PTE, 0); - __set_phys_to_machine(virt_to_pfn(vaddr), INVALID_P2M_ENTRY); + __set_phys_to_machine(virt_to_pfn((void *)vaddr), INVALID_P2M_ENTRY); if (out_frames) - out_frames[i] = virt_to_pfn(vaddr); + out_frames[i] = virt_to_pfn((void *)vaddr); } xen_mc_issue(0); } @@ -2250,7 +2250,7 @@ static void xen_remap_exchanged_ptes(unsigned long vaddr, int order, MULTI_update_va_mapping(mcs.mc, vaddr, mfn_pte(mfn, PAGE_KERNEL), flags); - set_phys_to_machine(virt_to_pfn(vaddr), mfn); + set_phys_to_machine(virt_to_pfn((void *)vaddr), mfn); } xen_mc_issue(0); @@ -2310,12 +2310,6 @@ int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, int success; unsigned long vstart = (unsigned long)phys_to_virt(pstart); - /* - * Currently an auto-translated guest will not perform I/O, nor will - * it require PAE page directories below 4GB. Therefore any calls to - * this function are redundant and can be ignored. - */ - if (unlikely(order > MAX_CONTIG_ORDER)) return -ENOMEM; @@ -2327,7 +2321,7 @@ int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, xen_zap_pfn_range(vstart, order, in_frames, NULL); /* 2. Get a new contiguous memory extent. */ - out_frame = virt_to_pfn(vstart); + out_frame = virt_to_pfn((void *)vstart); success = xen_exchange_memory(1UL << order, 0, in_frames, 1, order, &out_frame, address_bits); @@ -2360,7 +2354,7 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order) spin_lock_irqsave(&xen_reservation_lock, flags); /* 1. Find start MFN of contiguous extent. */ - in_frame = virt_to_mfn(vstart); + in_frame = virt_to_mfn((void *)vstart); /* 2. Zap current PTEs. */ xen_zap_pfn_range(vstart, order, NULL, out_frames); diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 8b5cf7bb1f47..50c998b844fb 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -340,7 +340,7 @@ static void __init xen_do_set_identity_and_remap_chunk( WARN_ON(size == 0); - mfn_save = virt_to_mfn(buf); + mfn_save = virt_to_mfn((void *)buf); for (ident_pfn_iter = start_pfn, remap_pfn_iter = remap_pfn; ident_pfn_iter < ident_end_pfn; @@ -503,7 +503,7 @@ void __init xen_remap_memory(void) unsigned long pfn_s = ~0UL; unsigned long len = 0; - mfn_save = virt_to_mfn(buf); + mfn_save = virt_to_mfn((void *)buf); while (xen_remap_mfn != INVALID_P2M_ENTRY) { /* Map the remap information */ diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index 2b69c3c035b6..fc1a4f3c81d9 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -422,3 +422,4 @@ 449 common futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node 451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 |