diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 2d34748be6d8..40723d64309f 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3813,6 +3813,10 @@ nox2apic [X86-64,APIC] Do not enable x2APIC mode. + NOTE: this parameter will be ignored on systems with the + LEGACY_XAPIC_DISABLED bit set in the + IA32_XAPIC_DISABLE_STATUS MSR. + nps_mtm_hs_ctr= [KNL,ARC] This parameter sets the maximum duration, in cycles, each HW thread of the CTOP can run diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index cabd6e13f549..5b53ecca1e15 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -451,6 +451,11 @@ config X86_X2APIC This allows 32-bit apic IDs (so it can support very large systems), and accesses the local apic via MSRs not via mmio. + Some Intel systems circa 2022 and later are locked into x2APIC mode + and can not fall back to the legacy APIC modes if SGX or TDX are + enabled in the BIOS. They will be unable to boot without enabling + this option. + If you don't know what to do here, say N. config X86_MPPARSE @@ -1922,7 +1927,7 @@ endchoice config X86_SGX bool "Software Guard eXtensions (SGX)" - depends on X86_64 && CPU_SUP_INTEL + depends on X86_64 && CPU_SUP_INTEL && X86_X2APIC depends on CRYPTO=y depends on CRYPTO_SHA256=y select SRCU @@ -2572,7 +2577,7 @@ menuconfig APM 1) make sure that you have enough swap space and that it is enabled. - 2) pass the "no-hlt" option to the kernel + 2) pass the "idle=poll" option to the kernel 3) switch on floating point emulation in the kernel and pass the "no387" option to the kernel 4) pass the "floppy=nodma" option to the kernel diff --git a/arch/x86/include/asm/acrn.h b/arch/x86/include/asm/acrn.h index e003a01b7c67..1dd14381bcb6 100644 --- a/arch/x86/include/asm/acrn.h +++ b/arch/x86/include/asm/acrn.h @@ -10,6 +10,15 @@ /* Bit 0 indicates whether guest VM is privileged */ #define ACRN_FEATURE_PRIVILEGED_VM BIT(0) +/* + * Timing Information. + * This leaf returns the current TSC frequency in kHz. + * + * EAX: (Virtual) TSC frequency in kHz. + * EBX, ECX, EDX: RESERVED (reserved fields are set to zero). + */ +#define ACRN_CPUID_TIMING_INFO 0x40000010 + void acrn_setup_intr_handler(void (*handler)(void)); void acrn_remove_intr_handler(void); @@ -21,6 +30,11 @@ static inline u32 acrn_cpuid_base(void) return 0; } +static inline unsigned long acrn_get_tsc_khz(void) +{ + return cpuid_eax(ACRN_CPUID_TIMING_INFO); +} + /* * Hypercalls for ACRN * diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 0fe9de58af31..2edf68475fec 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -247,17 +247,30 @@ arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr) variable_test_bit(nr, addr); } +static __always_inline unsigned long variable__ffs(unsigned long word) +{ + asm("rep; bsf %1,%0" + : "=r" (word) + : "rm" (word)); + return word; +} + /** * __ffs - find first set bit in word * @word: The word to search * * Undefined if no bit exists, so code should check against 0 first. */ -static __always_inline unsigned long __ffs(unsigned long word) +#define __ffs(word) \ + (__builtin_constant_p(word) ? \ + (unsigned long)__builtin_ctzl(word) : \ + variable__ffs(word)) + +static __always_inline unsigned long variable_ffz(unsigned long word) { asm("rep; bsf %1,%0" : "=r" (word) - : "rm" (word)); + : "r" (~word)); return word; } @@ -267,13 +280,10 @@ static __always_inline unsigned long __ffs(unsigned long word) * * Undefined if no zero exists, so code should check against ~0UL first. */ -static __always_inline unsigned long ffz(unsigned long word) -{ - asm("rep; bsf %1,%0" - : "=r" (word) - : "r" (~word)); - return word; -} +#define ffz(word) \ + (__builtin_constant_p(word) ? \ + (unsigned long)__builtin_ctzl(~word) : \ + variable_ffz(word)) /* * __fls: find last set bit in word @@ -292,18 +302,7 @@ static __always_inline unsigned long __fls(unsigned long word) #undef ADDR #ifdef __KERNEL__ -/** - * ffs - find first set bit in word - * @x: the word to search - * - * This is defined the same way as the libc and compiler builtin ffs - * routines, therefore differs in spirit from the other bitops. - * - * ffs(value) returns 0 if value is 0 or the position of the first - * set bit if value is nonzero. The first (least significant) bit - * is at position 1. - */ -static __always_inline int ffs(int x) +static __always_inline int variable_ffs(int x) { int r; @@ -333,6 +332,19 @@ static __always_inline int ffs(int x) return r + 1; } +/** + * ffs - find first set bit in word + * @x: the word to search + * + * This is defined the same way as the libc and compiler builtin ffs + * routines, therefore differs in spirit from the other bitops. + * + * ffs(value) returns 0 if value is 0 or the position of the first + * set bit if value is nonzero. The first (least significant) bit + * is at position 1. + */ +#define ffs(x) (__builtin_constant_p(x) ? __builtin_ffs(x) : variable_ffs(x)) + /** * fls - find last set bit in word * @x: the word to search diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index 8cbf623f0ecf..b472ef76826a 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -94,4 +94,6 @@ static inline bool intel_cpu_signatures_match(unsigned int s1, unsigned int p1, return p1 & p2; } +extern u64 x86_read_arch_cap_msr(void); + #endif /* _ASM_X86_CPU_H */ diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h index 97198001e567..6115bb3d5795 100644 --- a/arch/x86/include/asm/mc146818rtc.h +++ b/arch/x86/include/asm/mc146818rtc.h @@ -95,7 +95,7 @@ static inline unsigned char current_lock_cmos_reg(void) unsigned char rtc_cmos_read(unsigned char addr); void rtc_cmos_write(unsigned char val, unsigned char addr); -extern int mach_set_rtc_mmss(const struct timespec64 *now); +extern int mach_set_cmos_time(const struct timespec64 *now); extern void mach_get_cmos_time(struct timespec64 *now); #define RTC_IRQ 8 diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index cc73061e7255..6e986088817d 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -42,6 +42,7 @@ #define MCI_STATUS_CEC_SHIFT 38 /* Corrected Error Count */ #define MCI_STATUS_CEC_MASK GENMASK_ULL(52,38) #define MCI_STATUS_CEC(c) (((c) & MCI_STATUS_CEC_MASK) >> MCI_STATUS_CEC_SHIFT) +#define MCI_STATUS_MSCOD(m) (((m) >> 16) & 0xffff) /* AMD-specific bits */ #define MCI_STATUS_TCC BIT_ULL(55) /* Task context corrupt */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 6674bdb096f3..1e086b37a307 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -155,6 +155,11 @@ * Return Stack Buffer Predictions. */ +#define ARCH_CAP_XAPIC_DISABLE BIT(21) /* + * IA32_XAPIC_DISABLE_STATUS MSR + * supported + */ + #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* * Writeback and invalidate the @@ -1054,4 +1059,12 @@ #define MSR_IA32_HW_FEEDBACK_PTR 0x17d0 #define MSR_IA32_HW_FEEDBACK_CONFIG 0x17d1 +/* x2APIC locked status */ +#define MSR_IA32_XAPIC_DISABLE_STATUS 0xBD +#define LEGACY_XAPIC_DISABLED BIT(0) /* + * x2APIC mode is locked and + * disabling x2APIC will cause + * a #GP + */ + #endif /* _ASM_X86_MSR_INDEX_H */ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 964442b99245..2a0b8dd4ec33 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -743,6 +743,7 @@ extern void default_banner(void); word 771b; \ .byte ptype; \ .byte 772b-771b; \ + _ASM_ALIGN; \ .popsection diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index b1ab5d94881b..f3d601574730 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -294,6 +294,7 @@ extern struct paravirt_patch_template pv_ops; " .byte " type "\n" \ " .byte 772b-771b\n" \ " .short " clobber "\n" \ + _ASM_ALIGN "\n" \ ".popsection\n" /* Generate patchable code, with the default asm parameters. */ diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 913e593a3b45..c46207946e05 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -502,9 +502,6 @@ strncpy_from_user(char *dst, const char __user *src, long count); extern __must_check long strnlen_user(const char __user *str, long n); -unsigned long __must_check clear_user(void __user *mem, unsigned long len); -unsigned long __must_check __clear_user(void __user *mem, unsigned long len); - #ifdef CONFIG_ARCH_HAS_COPY_MC unsigned long __must_check copy_mc_to_kernel(void *to, const void *from, unsigned len); @@ -526,6 +523,8 @@ extern struct movsl_mask { #define ARCH_HAS_NOCACHE_UACCESS 1 #ifdef CONFIG_X86_32 +unsigned long __must_check clear_user(void __user *mem, unsigned long len); +unsigned long __must_check __clear_user(void __user *mem, unsigned long len); # include #else # include diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 45697e04d771..d13d71af5cf6 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -79,4 +79,49 @@ __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size) kasan_check_write(dst, size); return __copy_user_flushcache(dst, src, size); } + +/* + * Zero Userspace. + */ + +__must_check unsigned long +clear_user_original(void __user *addr, unsigned long len); +__must_check unsigned long +clear_user_rep_good(void __user *addr, unsigned long len); +__must_check unsigned long +clear_user_erms(void __user *addr, unsigned long len); + +static __always_inline __must_check unsigned long __clear_user(void __user *addr, unsigned long size) +{ + might_fault(); + stac(); + + /* + * No memory constraint because it doesn't change any memory gcc + * knows about. + */ + asm volatile( + "1:\n\t" + ALTERNATIVE_3("rep stosb", + "call clear_user_erms", ALT_NOT(X86_FEATURE_FSRM), + "call clear_user_rep_good", ALT_NOT(X86_FEATURE_ERMS), + "call clear_user_original", ALT_NOT(X86_FEATURE_REP_GOOD)) + "2:\n" + _ASM_EXTABLE_UA(1b, 2b) + : "+c" (size), "+D" (addr), ASM_CALL_CONSTRAINT + : "a" (0) + /* rep_good clobbers %rdx */ + : "rdx"); + + clac(); + + return size; +} + +static __always_inline unsigned long clear_user(void __user *to, unsigned long n) +{ + if (access_ok(to, n)) + return __clear_user(to, n); + return n; +} #endif /* _ASM_X86_UACCESS_64_H */ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 4f3204364caa..5cadcea035e0 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -453,6 +453,15 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes) return ret; i += ret; + /* + * The compiler is supposed to EMIT an INT3 after every unconditional + * JMP instruction due to AMD BTC. However, if the compiler is too old + * or SLS isn't enabled, we still need an INT3 after indirect JMPs + * even on Intel. + */ + if (op == JMP32_INSN_OPCODE && i < insn->length) + bytes[i++] = INT3_INSN_OPCODE; + for (; i < insn->length;) bytes[i++] = BYTES_NOP1; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 6d303d1d276c..c6876d3ea4b1 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -61,6 +61,7 @@ #include #include #include +#include unsigned int num_processors; @@ -1751,11 +1752,26 @@ EXPORT_SYMBOL_GPL(x2apic_mode); enum { X2APIC_OFF, - X2APIC_ON, X2APIC_DISABLED, + /* All states below here have X2APIC enabled */ + X2APIC_ON, + X2APIC_ON_LOCKED }; static int x2apic_state; +static bool x2apic_hw_locked(void) +{ + u64 ia32_cap; + u64 msr; + + ia32_cap = x86_read_arch_cap_msr(); + if (ia32_cap & ARCH_CAP_XAPIC_DISABLE) { + rdmsrl(MSR_IA32_XAPIC_DISABLE_STATUS, msr); + return (msr & LEGACY_XAPIC_DISABLED); + } + return false; +} + static void __x2apic_disable(void) { u64 msr; @@ -1793,6 +1809,10 @@ static int __init setup_nox2apic(char *str) apicid); return 0; } + if (x2apic_hw_locked()) { + pr_warn("APIC locked in x2apic mode, can't disable\n"); + return 0; + } pr_warn("x2apic already enabled.\n"); __x2apic_disable(); } @@ -1807,10 +1827,18 @@ early_param("nox2apic", setup_nox2apic); void x2apic_setup(void) { /* - * If x2apic is not in ON state, disable it if already enabled + * Try to make the AP's APIC state match that of the BSP, but if the + * BSP is unlocked and the AP is locked then there is a state mismatch. + * Warn about the mismatch in case a GP fault occurs due to a locked AP + * trying to be turned off. + */ + if (x2apic_state != X2APIC_ON_LOCKED && x2apic_hw_locked()) + pr_warn("x2apic lock mismatch between BSP and AP.\n"); + /* + * If x2apic is not in ON or LOCKED state, disable it if already enabled * from BIOS. */ - if (x2apic_state != X2APIC_ON) { + if (x2apic_state < X2APIC_ON) { __x2apic_disable(); return; } @@ -1831,6 +1859,11 @@ static __init void x2apic_disable(void) if (x2apic_id >= 255) panic("Cannot disable x2apic, id: %08x\n", x2apic_id); + if (x2apic_hw_locked()) { + pr_warn("Cannot disable locked x2apic, id: %08x\n", x2apic_id); + return; + } + __x2apic_disable(); register_lapic_address(mp_lapic_addr); } @@ -1889,7 +1922,10 @@ void __init check_x2apic(void) if (x2apic_enabled()) { pr_info("x2apic: enabled by BIOS, switching to x2apic ops\n"); x2apic_mode = 1; - x2apic_state = X2APIC_ON; + if (x2apic_hw_locked()) + x2apic_state = X2APIC_ON_LOCKED; + else + x2apic_state = X2APIC_ON; } else if (!boot_cpu_has(X86_FEATURE_X2APIC)) { x2apic_state = X2APIC_DISABLED; } diff --git a/arch/x86/kernel/cpu/acrn.c b/arch/x86/kernel/cpu/acrn.c index 23f5f27b5a02..485441b7f030 100644 --- a/arch/x86/kernel/cpu/acrn.c +++ b/arch/x86/kernel/cpu/acrn.c @@ -28,6 +28,9 @@ static void __init acrn_init_platform(void) { /* Setup the IDT for ACRN hypervisor callback */ alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_acrn_hv_callback); + + x86_platform.calibrate_tsc = acrn_get_tsc_khz; + x86_platform.calibrate_cpu = acrn_get_tsc_khz; } static bool acrn_x2apic_available(void) diff --git a/arch/x86/kernel/cpu/mce/apei.c b/arch/x86/kernel/cpu/mce/apei.c index 717192915f28..8ed341714686 100644 --- a/arch/x86/kernel/cpu/mce/apei.c +++ b/arch/x86/kernel/cpu/mce/apei.c @@ -29,15 +29,26 @@ void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err) { struct mce m; + int lsb; if (!(mem_err->validation_bits & CPER_MEM_VALID_PA)) return; + /* + * Even if the ->validation_bits are set for address mask, + * to be extra safe, check and reject an error radius '0', + * and fall back to the default page size. + */ + if (mem_err->validation_bits & CPER_MEM_VALID_PA_MASK) + lsb = find_first_bit((void *)&mem_err->physical_addr_mask, PAGE_SHIFT); + else + lsb = PAGE_SHIFT; + mce_setup(&m); m.bank = -1; /* Fake a memory read error with unknown channel */ m.status = MCI_STATUS_VAL | MCI_STATUS_EN | MCI_STATUS_ADDRV | MCI_STATUS_MISCV | 0x9f; - m.misc = (MCI_MISC_ADDR_PHYS << 6) | PAGE_SHIFT; + m.misc = (MCI_MISC_ADDR_PHYS << 6) | lsb; if (severity >= GHES_SEV_RECOVERABLE) m.status |= MCI_STATUS_UC; diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index 8bdeae2fc309..9f13d724172e 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -12,6 +12,9 @@ #include "encls.h" #include "sgx.h" +static int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index, + struct sgx_backing *backing); + #define PCMDS_PER_PAGE (PAGE_SIZE / sizeof(struct sgx_pcmd)) /* * 32 PCMD entries share a PCMD page. PCMD_FIRST_MASK is used to @@ -917,7 +920,7 @@ static struct page *sgx_encl_get_backing_page(struct sgx_encl *encl, } /** - * sgx_encl_get_backing() - Pin the backing storage + * __sgx_encl_get_backing() - Pin the backing storage * @encl: an enclave pointer * @page_index: enclave page index * @backing: data for accessing backing storage for the page @@ -929,7 +932,7 @@ static struct page *sgx_encl_get_backing_page(struct sgx_encl *encl, * 0 on success, * -errno otherwise. */ -static int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, +static int __sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, struct sgx_backing *backing) { pgoff_t page_pcmd_off = sgx_encl_get_backing_page_pcmd_offset(encl, page_index); @@ -1004,7 +1007,7 @@ static struct mem_cgroup *sgx_encl_get_mem_cgroup(struct sgx_encl *encl) } /** - * sgx_encl_alloc_backing() - allocate a new backing storage page + * sgx_encl_alloc_backing() - create a new backing storage page * @encl: an enclave pointer * @page_index: enclave page index * @backing: data for accessing backing storage for the page @@ -1012,7 +1015,9 @@ static struct mem_cgroup *sgx_encl_get_mem_cgroup(struct sgx_encl *encl) * When called from ksgxd, sets the active memcg from one of the * mms in the enclave's mm_list prior to any backing page allocation, * in order to ensure that shmem page allocations are charged to the - * enclave. + * enclave. Create a backing page for loading data back into an EPC page with + * ELDU. This function takes a reference on a new backing page which + * must be dropped with a corresponding call to sgx_encl_put_backing(). * * Return: * 0 on success, @@ -1025,7 +1030,7 @@ int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index, struct mem_cgroup *memcg = set_active_memcg(encl_memcg); int ret; - ret = sgx_encl_get_backing(encl, page_index, backing); + ret = __sgx_encl_get_backing(encl, page_index, backing); set_active_memcg(memcg); mem_cgroup_put(encl_memcg); @@ -1043,15 +1048,17 @@ int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index, * It is the caller's responsibility to ensure that it is appropriate to use * sgx_encl_lookup_backing() rather than sgx_encl_alloc_backing(). If lookup is * not used correctly, this will cause an allocation which is not accounted for. + * This function takes a reference on an existing backing page which must be + * dropped with a corresponding call to sgx_encl_put_backing(). * * Return: * 0 on success, * -errno otherwise. */ -int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index, +static int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index, struct sgx_backing *backing) { - return sgx_encl_get_backing(encl, page_index, backing); + return __sgx_encl_get_backing(encl, page_index, backing); } /** diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h index a65a952116fd..f94ff14c9486 100644 --- a/arch/x86/kernel/cpu/sgx/encl.h +++ b/arch/x86/kernel/cpu/sgx/encl.h @@ -107,8 +107,6 @@ bool current_is_ksgxd(void); void sgx_encl_release(struct kref *ref); int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm); const cpumask_t *sgx_encl_cpumask(struct sgx_encl *encl); -int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index, - struct sgx_backing *backing); int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index, struct sgx_backing *backing); void sgx_encl_put_backing(struct sgx_backing *backing); diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index afae4dd77495..b3dba35f466e 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -128,7 +128,7 @@ void show_opcodes(struct pt_regs *regs, const char *loglvl) /* No access to the user space stack of other tasks. Ignore. */ break; default: - printk("%sCode: Unable to access opcode bytes at RIP 0x%lx.\n", + printk("%sCode: Unable to access opcode bytes at 0x%lx.\n", loglvl, prologue); break; } diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index 68b38925a74f..44f937015e1e 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -264,11 +264,11 @@ static __init void early_pci_serial_init(char *s) bar0 = read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_0); /* - * Verify it is a UART type device + * Verify it is a 16550-UART type device */ if (((classcode >> 16 != PCI_CLASS_COMMUNICATION_MODEM) && (classcode >> 16 != PCI_CLASS_COMMUNICATION_SERIAL)) || - (((classcode >> 8) & 0xff) != 0x02)) /* 16550 I/F at BAR0 */ { + (((classcode >> 8) & 0xff) != PCI_SERIAL_16550_COMPATIBLE)) { if (!force) return; } @@ -276,22 +276,22 @@ static __init void early_pci_serial_init(char *s) /* * Determine if it is IO or memory mapped */ - if (bar0 & 0x01) { + if ((bar0 & PCI_BASE_ADDRESS_SPACE) == PCI_BASE_ADDRESS_SPACE_IO) { /* it is IO mapped */ serial_in = io_serial_in; serial_out = io_serial_out; - early_serial_base = bar0&0xfffffffc; + early_serial_base = bar0 & PCI_BASE_ADDRESS_IO_MASK; write_pci_config(bus, slot, func, PCI_COMMAND, - cmdreg|PCI_COMMAND_IO); + cmdreg|PCI_COMMAND_IO); } else { /* It is memory mapped - assume 32-bit alignment */ serial_in = mem32_serial_in; serial_out = mem32_serial_out; /* WARNING! assuming the address is always in the first 4G */ early_serial_base = - (unsigned long)early_ioremap(bar0 & 0xfffffff0, 0x10); + (unsigned long)early_ioremap(bar0 & PCI_BASE_ADDRESS_MEM_MASK, 0x10); write_pci_config(bus, slot, func, PCI_COMMAND, - cmdreg|PCI_COMMAND_MEMORY); + cmdreg|PCI_COMMAND_MEMORY); } /* diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 586f718b8e95..349046434513 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -4,11 +4,8 @@ */ #include #include -#include -#include #include #include -#include #include #include @@ -20,26 +17,23 @@ /* * This is a special lock that is owned by the CPU and holds the index * register we are working with. It is required for NMI access to the - * CMOS/RTC registers. See include/asm-i386/mc146818rtc.h for details. + * CMOS/RTC registers. See arch/x86/include/asm/mc146818rtc.h for details. */ volatile unsigned long cmos_lock; EXPORT_SYMBOL(cmos_lock); #endif /* CONFIG_X86_32 */ -/* For two digit years assume time is always after that */ -#define CMOS_YEARS_OFFS 2000 - DEFINE_SPINLOCK(rtc_lock); EXPORT_SYMBOL(rtc_lock); /* - * In order to set the CMOS clock precisely, set_rtc_mmss has to be + * In order to set the CMOS clock precisely, mach_set_cmos_time has to be * called 500 ms after the second nowtime has started, because when * nowtime is written into the registers of the CMOS clock, it will * jump to the next second precisely 500 ms later. Check the Motorola * MC146818A or Dallas DS12887 data sheet for details. */ -int mach_set_rtc_mmss(const struct timespec64 *now) +int mach_set_cmos_time(const struct timespec64 *now) { unsigned long long nowtime = now->tv_sec; struct rtc_time tm; @@ -62,8 +56,7 @@ int mach_set_rtc_mmss(const struct timespec64 *now) void mach_get_cmos_time(struct timespec64 *now) { - unsigned int status, year, mon, day, hour, min, sec, century = 0; - unsigned long flags; + struct rtc_time tm; /* * If pm_trace abused the RTC as storage, set the timespec to 0, @@ -74,51 +67,13 @@ void mach_get_cmos_time(struct timespec64 *now) return; } - spin_lock_irqsave(&rtc_lock, flags); - - /* - * If UIP is clear, then we have >= 244 microseconds before - * RTC registers will be updated. Spec sheet says that this - * is the reliable way to read RTC - registers. If UIP is set - * then the register access might be invalid. - */ - while ((CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP)) - cpu_relax(); - - sec = CMOS_READ(RTC_SECONDS); - min = CMOS_READ(RTC_MINUTES); - hour = CMOS_READ(RTC_HOURS); - day = CMOS_READ(RTC_DAY_OF_MONTH); - mon = CMOS_READ(RTC_MONTH); - year = CMOS_READ(RTC_YEAR); - -#ifdef CONFIG_ACPI - if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID && - acpi_gbl_FADT.century) - century = CMOS_READ(acpi_gbl_FADT.century); -#endif - - status = CMOS_READ(RTC_CONTROL); - WARN_ON_ONCE(RTC_ALWAYS_BCD && (status & RTC_DM_BINARY)); - - spin_unlock_irqrestore(&rtc_lock, flags); - - if (RTC_ALWAYS_BCD || !(status & RTC_DM_BINARY)) { - sec = bcd2bin(sec); - min = bcd2bin(min); - hour = bcd2bin(hour); - day = bcd2bin(day); - mon = bcd2bin(mon); - year = bcd2bin(year); + if (mc146818_get_time(&tm)) { + pr_err("Unable to read current time from RTC\n"); + now->tv_sec = now->tv_nsec = 0; + return; } - if (century) { - century = bcd2bin(century); - year += century * 100; - } else - year += CMOS_YEARS_OFFS; - - now->tv_sec = mktime64(year, mon, day, hour, min, sec); + now->tv_sec = rtc_tm_to_time64(&tm); now->tv_nsec = 0; } diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index e84ee5cdbd8c..57353519bc11 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -138,7 +138,7 @@ struct x86_platform_ops x86_platform __ro_after_init = { .calibrate_cpu = native_calibrate_cpu_early, .calibrate_tsc = native_calibrate_tsc, .get_wallclock = mach_get_cmos_time, - .set_wallclock = mach_set_rtc_mmss, + .set_wallclock = mach_set_cmos_time, .iommu_shutdown = iommu_shutdown_noop, .is_untracked_pat_range = is_ISA_range, .nmi_init = default_nmi_init, diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S index fe59b8ac4fcc..ecbfb4dd3b01 100644 --- a/arch/x86/lib/clear_page_64.S +++ b/arch/x86/lib/clear_page_64.S @@ -1,5 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ #include +#include #include /* @@ -50,3 +51,140 @@ SYM_FUNC_START(clear_page_erms) RET SYM_FUNC_END(clear_page_erms) EXPORT_SYMBOL_GPL(clear_page_erms) + +/* + * Default clear user-space. + * Input: + * rdi destination + * rcx count + * + * Output: + * rcx: uncleared bytes or 0 if successful. + */ +SYM_FUNC_START(clear_user_original) + /* + * Copy only the lower 32 bits of size as that is enough to handle the rest bytes, + * i.e., no need for a 'q' suffix and thus a REX prefix. + */ + mov %ecx,%eax + shr $3,%rcx + jz .Lrest_bytes + + # do the qwords first + .p2align 4 +.Lqwords: + movq $0,(%rdi) + lea 8(%rdi),%rdi + dec %rcx + jnz .Lqwords + +.Lrest_bytes: + and $7, %eax + jz .Lexit + + # now do the rest bytes +.Lbytes: + movb $0,(%rdi) + inc %rdi + dec %eax + jnz .Lbytes + +.Lexit: + /* + * %rax still needs to be cleared in the exception case because this function is called + * from inline asm and the compiler expects %rax to be zero when exiting the inline asm, + * in case it might reuse it somewhere. + */ + xor %eax,%eax + RET + +.Lqwords_exception: + # convert remaining qwords back into bytes to return to caller + shl $3, %rcx + and $7, %eax + add %rax,%rcx + jmp .Lexit + +.Lbytes_exception: + mov %eax,%ecx + jmp .Lexit + + _ASM_EXTABLE_UA(.Lqwords, .Lqwords_exception) + _ASM_EXTABLE_UA(.Lbytes, .Lbytes_exception) +SYM_FUNC_END(clear_user_original) +EXPORT_SYMBOL(clear_user_original) + +/* + * Alternative clear user-space when CPU feature X86_FEATURE_REP_GOOD is + * present. + * Input: + * rdi destination + * rcx count + * + * Output: + * rcx: uncleared bytes or 0 if successful. + */ +SYM_FUNC_START(clear_user_rep_good) + # call the original thing for less than a cacheline + cmp $64, %rcx + jb clear_user_original + +.Lprep: + # copy lower 32-bits for rest bytes + mov %ecx, %edx + shr $3, %rcx + jz .Lrep_good_rest_bytes + +.Lrep_good_qwords: + rep stosq + +.Lrep_good_rest_bytes: + and $7, %edx + jz .Lrep_good_exit + +.Lrep_good_bytes: + mov %edx, %ecx + rep stosb + +.Lrep_good_exit: + # see .Lexit comment above + xor %eax, %eax + RET + +.Lrep_good_qwords_exception: + # convert remaining qwords back into bytes to return to caller + shl $3, %rcx + and $7, %edx + add %rdx, %rcx + jmp .Lrep_good_exit + + _ASM_EXTABLE_UA(.Lrep_good_qwords, .Lrep_good_qwords_exception) + _ASM_EXTABLE_UA(.Lrep_good_bytes, .Lrep_good_exit) +SYM_FUNC_END(clear_user_rep_good) +EXPORT_SYMBOL(clear_user_rep_good) + +/* + * Alternative clear user-space when CPU feature X86_FEATURE_ERMS is present. + * Input: + * rdi destination + * rcx count + * + * Output: + * rcx: uncleared bytes or 0 if successful. + * + */ +SYM_FUNC_START(clear_user_erms) + # call the original thing for less than a cacheline + cmp $64, %rcx + jb clear_user_original + +.Lerms_bytes: + rep stosb + +.Lerms_exit: + xorl %eax,%eax + RET + + _ASM_EXTABLE_UA(.Lerms_bytes, .Lerms_exit) +SYM_FUNC_END(clear_user_erms) +EXPORT_SYMBOL(clear_user_erms) diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index 0ae6cf804197..6c1f8ac5e721 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -14,46 +14,6 @@ * Zero Userspace */ -unsigned long __clear_user(void __user *addr, unsigned long size) -{ - long __d0; - might_fault(); - /* no memory constraint because it doesn't change any memory gcc knows - about */ - stac(); - asm volatile( - " testq %[size8],%[size8]\n" - " jz 4f\n" - " .align 16\n" - "0: movq $0,(%[dst])\n" - " addq $8,%[dst]\n" - " decl %%ecx ; jnz 0b\n" - "4: movq %[size1],%%rcx\n" - " testl %%ecx,%%ecx\n" - " jz 2f\n" - "1: movb $0,(%[dst])\n" - " incq %[dst]\n" - " decl %%ecx ; jnz 1b\n" - "2:\n" - - _ASM_EXTABLE_TYPE_REG(0b, 2b, EX_TYPE_UCOPY_LEN8, %[size1]) - _ASM_EXTABLE_UA(1b, 2b) - - : [size8] "=&c"(size), [dst] "=&D" (__d0) - : [size1] "r"(size & 7), "[size8]" (size / 8), "[dst]"(addr)); - clac(); - return size; -} -EXPORT_SYMBOL(__clear_user); - -unsigned long clear_user(void __user *to, unsigned long n) -{ - if (access_ok(to, n)) - return __clear_user(to, n); - return n; -} -EXPORT_SYMBOL(clear_user); - #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE /** * clean_cache_range - write back a cache range with CLWB diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index fa71a5d12e87..a498ae1fbe66 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -769,6 +769,8 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code, unsigned long address, struct task_struct *tsk) { const char *loglvl = task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG; + /* This is a racy snapshot, but it's better than nothing. */ + int cpu = raw_smp_processor_id(); if (!unhandled_signal(tsk, SIGSEGV)) return; @@ -782,6 +784,14 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code, print_vma_addr(KERN_CONT " in ", regs->ip); + /* + * Dump the likely CPU where the fatal segfault happened. + * This can help identify faulty hardware. + */ + printk(KERN_CONT " likely on CPU %d (core %d, socket %d)", cpu, + topology_core_id(cpu), topology_physical_package_id(cpu)); + + printk(KERN_CONT "\n"); show_opcodes(regs, loglvl); diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index c1f6c1c51d99..4922517ddb0d 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -419,7 +419,9 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) OPTIMIZER_HIDE_VAR(reg); emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip); } else { - EMIT2(0xFF, 0xE0 + reg); + EMIT2(0xFF, 0xE0 + reg); /* jmp *%\reg */ + if (IS_ENABLED(CONFIG_RETPOLINE) || IS_ENABLED(CONFIG_SLS)) + EMIT1(0xCC); /* int3 */ } *pprog = prog; diff --git a/block/bdev.c b/block/bdev.c index ce05175e71ce..d699ecdb3260 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -26,6 +26,7 @@ #include #include #include +#include #include "../fs/internal.h" #include "blk.h" @@ -1069,3 +1070,25 @@ void sync_bdevs(bool wait) spin_unlock(&blockdev_superblock->s_inode_list_lock); iput(old_inode); } + +/* + * Handle STATX_DIOALIGN for block devices. + * + * Note that the inode passed to this is the inode of a block device node file, + * not the block device's internal inode. Therefore it is *not* valid to use + * I_BDEV() here; the block device has to be looked up by i_rdev instead. + */ +void bdev_statx_dioalign(struct inode *inode, struct kstat *stat) +{ + struct block_device *bdev; + + bdev = blkdev_get_no_open(inode->i_rdev); + if (!bdev) + return; + + stat->dio_mem_align = bdev_dma_alignment(bdev) + 1; + stat->dio_offset_align = bdev_logical_block_size(bdev); + stat->result_mask |= STATX_DIOALIGN; + + blkdev_put_no_open(bdev); +} diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index eb58644bb019..6faeb2ab3960 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -103,7 +103,6 @@ static void edac_mc_dump_dimm(struct dimm_info *dimm) edac_dbg(4, " dimm->label = '%s'\n", dimm->label); edac_dbg(4, " dimm->nr_pages = 0x%x\n", dimm->nr_pages); edac_dbg(4, " dimm->grain = %d\n", dimm->grain); - edac_dbg(4, " dimm->nr_pages = 0x%x\n", dimm->nr_pages); } static void edac_mc_dump_csrow(struct csrow_info *csrow) diff --git a/drivers/edac/edac_module.h b/drivers/edac/edac_module.h index 96f6de0c8ff6..50ed9f2425bb 100644 --- a/drivers/edac/edac_module.h +++ b/drivers/edac/edac_module.h @@ -28,13 +28,9 @@ void edac_mc_sysfs_exit(void); extern int edac_create_sysfs_mci_device(struct mem_ctl_info *mci, const struct attribute_group **groups); extern void edac_remove_sysfs_mci_device(struct mem_ctl_info *mci); -extern int edac_get_log_ue(void); -extern int edac_get_log_ce(void); -extern int edac_get_panic_on_ue(void); extern int edac_mc_get_log_ue(void); extern int edac_mc_get_log_ce(void); extern int edac_mc_get_panic_on_ue(void); -extern int edac_get_poll_msec(void); extern unsigned int edac_mc_get_poll_msec(void); unsigned edac_dimm_info_location(struct dimm_info *dimm, char *buf, diff --git a/drivers/edac/i10nm_base.c b/drivers/edac/i10nm_base.c index 6cf50ee0b77c..a22ea053f8e1 100644 --- a/drivers/edac/i10nm_base.c +++ b/drivers/edac/i10nm_base.c @@ -74,31 +74,47 @@ static struct list_head *i10nm_edac_list; static struct res_config *res_cfg; static int retry_rd_err_log; +static int decoding_via_mca; +static bool mem_cfg_2lm; static u32 offsets_scrub_icx[] = {0x22c60, 0x22c54, 0x22c5c, 0x22c58, 0x22c28, 0x20ed8}; static u32 offsets_scrub_spr[] = {0x22c60, 0x22c54, 0x22f08, 0x22c58, 0x22c28, 0x20ed8}; +static u32 offsets_scrub_spr_hbm0[] = {0x2860, 0x2854, 0x2b08, 0x2858, 0x2828, 0x0ed8}; +static u32 offsets_scrub_spr_hbm1[] = {0x2c60, 0x2c54, 0x2f08, 0x2c58, 0x2c28, 0x0fa8}; static u32 offsets_demand_icx[] = {0x22e54, 0x22e60, 0x22e64, 0x22e58, 0x22e5c, 0x20ee0}; static u32 offsets_demand_spr[] = {0x22e54, 0x22e60, 0x22f10, 0x22e58, 0x22e5c, 0x20ee0}; +static u32 offsets_demand2_spr[] = {0x22c70, 0x22d80, 0x22f18, 0x22d58, 0x22c64, 0x20f10}; +static u32 offsets_demand_spr_hbm0[] = {0x2a54, 0x2a60, 0x2b10, 0x2a58, 0x2a5c, 0x0ee0}; +static u32 offsets_demand_spr_hbm1[] = {0x2e54, 0x2e60, 0x2f10, 0x2e58, 0x2e5c, 0x0fb0}; -static void __enable_retry_rd_err_log(struct skx_imc *imc, int chan, bool enable) +static void __enable_retry_rd_err_log(struct skx_imc *imc, int chan, bool enable, + u32 *offsets_scrub, u32 *offsets_demand, + u32 *offsets_demand2) { - u32 s, d; + u32 s, d, d2; - if (!imc->mbase) - return; - - s = I10NM_GET_REG32(imc, chan, res_cfg->offsets_scrub[0]); - d = I10NM_GET_REG32(imc, chan, res_cfg->offsets_demand[0]); + s = I10NM_GET_REG32(imc, chan, offsets_scrub[0]); + d = I10NM_GET_REG32(imc, chan, offsets_demand[0]); + if (offsets_demand2) + d2 = I10NM_GET_REG32(imc, chan, offsets_demand2[0]); if (enable) { /* Save default configurations */ imc->chan[chan].retry_rd_err_log_s = s; imc->chan[chan].retry_rd_err_log_d = d; + if (offsets_demand2) + imc->chan[chan].retry_rd_err_log_d2 = d2; s &= ~RETRY_RD_ERR_LOG_NOOVER_UC; s |= RETRY_RD_ERR_LOG_EN; d &= ~RETRY_RD_ERR_LOG_NOOVER_UC; d |= RETRY_RD_ERR_LOG_EN; + + if (offsets_demand2) { + d2 &= ~RETRY_RD_ERR_LOG_UC; + d2 |= RETRY_RD_ERR_LOG_NOOVER; + d2 |= RETRY_RD_ERR_LOG_EN; + } } else { /* Restore default configurations */ if (imc->chan[chan].retry_rd_err_log_s & RETRY_RD_ERR_LOG_UC) @@ -113,23 +129,55 @@ static void __enable_retry_rd_err_log(struct skx_imc *imc, int chan, bool enable d |= RETRY_RD_ERR_LOG_NOOVER; if (!(imc->chan[chan].retry_rd_err_log_d & RETRY_RD_ERR_LOG_EN)) d &= ~RETRY_RD_ERR_LOG_EN; + + if (offsets_demand2) { + if (imc->chan[chan].retry_rd_err_log_d2 & RETRY_RD_ERR_LOG_UC) + d2 |= RETRY_RD_ERR_LOG_UC; + if (!(imc->chan[chan].retry_rd_err_log_d2 & RETRY_RD_ERR_LOG_NOOVER)) + d2 &= ~RETRY_RD_ERR_LOG_NOOVER; + if (!(imc->chan[chan].retry_rd_err_log_d2 & RETRY_RD_ERR_LOG_EN)) + d2 &= ~RETRY_RD_ERR_LOG_EN; + } } - I10NM_SET_REG32(imc, chan, res_cfg->offsets_scrub[0], s); - I10NM_SET_REG32(imc, chan, res_cfg->offsets_demand[0], d); + I10NM_SET_REG32(imc, chan, offsets_scrub[0], s); + I10NM_SET_REG32(imc, chan, offsets_demand[0], d); + if (offsets_demand2) + I10NM_SET_REG32(imc, chan, offsets_demand2[0], d2); } static void enable_retry_rd_err_log(bool enable) { + struct skx_imc *imc; struct skx_dev *d; int i, j; edac_dbg(2, "\n"); list_for_each_entry(d, i10nm_edac_list, list) - for (i = 0; i < I10NM_NUM_IMC; i++) - for (j = 0; j < I10NM_NUM_CHANNELS; j++) - __enable_retry_rd_err_log(&d->imc[i], j, enable); + for (i = 0; i < I10NM_NUM_IMC; i++) { + imc = &d->imc[i]; + if (!imc->mbase) + continue; + + for (j = 0; j < I10NM_NUM_CHANNELS; j++) { + if (imc->hbm_mc) { + __enable_retry_rd_err_log(imc, j, enable, + res_cfg->offsets_scrub_hbm0, + res_cfg->offsets_demand_hbm0, + NULL); + __enable_retry_rd_err_log(imc, j, enable, + res_cfg->offsets_scrub_hbm1, + res_cfg->offsets_demand_hbm1, + NULL); + } else { + __enable_retry_rd_err_log(imc, j, enable, + res_cfg->offsets_scrub, + res_cfg->offsets_demand, + res_cfg->offsets_demand2); + } + } + } } static void show_retry_rd_err_log(struct decoded_addr *res, char *msg, @@ -138,14 +186,33 @@ static void show_retry_rd_err_log(struct decoded_addr *res, char *msg, struct skx_imc *imc = &res->dev->imc[res->imc]; u32 log0, log1, log2, log3, log4; u32 corr0, corr1, corr2, corr3; + u32 lxg0, lxg1, lxg3, lxg4; + u32 *xffsets = NULL; u64 log2a, log5; + u64 lxg2a, lxg5; u32 *offsets; - int n; + int n, pch; if (!imc->mbase) return; - offsets = scrub_err ? res_cfg->offsets_scrub : res_cfg->offsets_demand; + if (imc->hbm_mc) { + pch = res->cs & 1; + + if (pch) + offsets = scrub_err ? res_cfg->offsets_scrub_hbm1 : + res_cfg->offsets_demand_hbm1; + else + offsets = scrub_err ? res_cfg->offsets_scrub_hbm0 : + res_cfg->offsets_demand_hbm0; + } else { + if (scrub_err) { + offsets = res_cfg->offsets_scrub; + } else { + offsets = res_cfg->offsets_demand; + xffsets = res_cfg->offsets_demand2; + } + } log0 = I10NM_GET_REG32(imc, res->channel, offsets[0]); log1 = I10NM_GET_REG32(imc, res->channel, offsets[1]); @@ -153,20 +220,52 @@ static void show_retry_rd_err_log(struct decoded_addr *res, char *msg, log4 = I10NM_GET_REG32(imc, res->channel, offsets[4]); log5 = I10NM_GET_REG64(imc, res->channel, offsets[5]); + if (xffsets) { + lxg0 = I10NM_GET_REG32(imc, res->channel, xffsets[0]); + lxg1 = I10NM_GET_REG32(imc, res->channel, xffsets[1]); + lxg3 = I10NM_GET_REG32(imc, res->channel, xffsets[3]); + lxg4 = I10NM_GET_REG32(imc, res->channel, xffsets[4]); + lxg5 = I10NM_GET_REG64(imc, res->channel, xffsets[5]); + } + if (res_cfg->type == SPR) { log2a = I10NM_GET_REG64(imc, res->channel, offsets[2]); - n = snprintf(msg, len, " retry_rd_err_log[%.8x %.8x %.16llx %.8x %.8x %.16llx]", + n = snprintf(msg, len, " retry_rd_err_log[%.8x %.8x %.16llx %.8x %.8x %.16llx", log0, log1, log2a, log3, log4, log5); + + if (len - n > 0) { + if (xffsets) { + lxg2a = I10NM_GET_REG64(imc, res->channel, xffsets[2]); + n += snprintf(msg + n, len - n, " %.8x %.8x %.16llx %.8x %.8x %.16llx]", + lxg0, lxg1, lxg2a, lxg3, lxg4, lxg5); + } else { + n += snprintf(msg + n, len - n, "]"); + } + } } else { log2 = I10NM_GET_REG32(imc, res->channel, offsets[2]); n = snprintf(msg, len, " retry_rd_err_log[%.8x %.8x %.8x %.8x %.8x %.16llx]", log0, log1, log2, log3, log4, log5); } - corr0 = I10NM_GET_REG32(imc, res->channel, 0x22c18); - corr1 = I10NM_GET_REG32(imc, res->channel, 0x22c1c); - corr2 = I10NM_GET_REG32(imc, res->channel, 0x22c20); - corr3 = I10NM_GET_REG32(imc, res->channel, 0x22c24); + if (imc->hbm_mc) { + if (pch) { + corr0 = I10NM_GET_REG32(imc, res->channel, 0x2c18); + corr1 = I10NM_GET_REG32(imc, res->channel, 0x2c1c); + corr2 = I10NM_GET_REG32(imc, res->channel, 0x2c20); + corr3 = I10NM_GET_REG32(imc, res->channel, 0x2c24); + } else { + corr0 = I10NM_GET_REG32(imc, res->channel, 0x2818); + corr1 = I10NM_GET_REG32(imc, res->channel, 0x281c); + corr2 = I10NM_GET_REG32(imc, res->channel, 0x2820); + corr3 = I10NM_GET_REG32(imc, res->channel, 0x2824); + } + } else { + corr0 = I10NM_GET_REG32(imc, res->channel, 0x22c18); + corr1 = I10NM_GET_REG32(imc, res->channel, 0x22c1c); + corr2 = I10NM_GET_REG32(imc, res->channel, 0x22c20); + corr3 = I10NM_GET_REG32(imc, res->channel, 0x22c24); + } if (len - n > 0) snprintf(msg + n, len - n, @@ -177,9 +276,16 @@ static void show_retry_rd_err_log(struct decoded_addr *res, char *msg, corr3 & 0xffff, corr3 >> 16); /* Clear status bits */ - if (retry_rd_err_log == 2 && (log0 & RETRY_RD_ERR_LOG_OVER_UC_V)) { - log0 &= ~RETRY_RD_ERR_LOG_OVER_UC_V; - I10NM_SET_REG32(imc, res->channel, offsets[0], log0); + if (retry_rd_err_log == 2) { + if (log0 & RETRY_RD_ERR_LOG_OVER_UC_V) { + log0 &= ~RETRY_RD_ERR_LOG_OVER_UC_V; + I10NM_SET_REG32(imc, res->channel, offsets[0], log0); + } + + if (xffsets && (lxg0 & RETRY_RD_ERR_LOG_OVER_UC_V)) { + lxg0 &= ~RETRY_RD_ERR_LOG_OVER_UC_V; + I10NM_SET_REG32(imc, res->channel, xffsets[0], lxg0); + } } } @@ -231,6 +337,103 @@ static bool i10nm_check_2lm(struct res_config *cfg) return false; } +/* + * Check whether the error comes from DDRT by ICX/Tremont model specific error code. + * Refer to SDM vol3B 16.11.3 Intel IMC MC error codes for IA32_MCi_STATUS. + */ +static bool i10nm_mscod_is_ddrt(u32 mscod) +{ + switch (mscod) { + case 0x0106: case 0x0107: + case 0x0800: case 0x0804: + case 0x0806 ... 0x0808: + case 0x080a ... 0x080e: + case 0x0810: case 0x0811: + case 0x0816: case 0x081e: + case 0x081f: + return true; + } + + return false; +} + +static bool i10nm_mc_decode_available(struct mce *mce) +{ + u8 bank; + + if (!decoding_via_mca || mem_cfg_2lm) + return false; + + if ((mce->status & (MCI_STATUS_MISCV | MCI_STATUS_ADDRV)) + != (MCI_STATUS_MISCV | MCI_STATUS_ADDRV)) + return false; + + bank = mce->bank; + + switch (res_cfg->type) { + case I10NM: + if (bank < 13 || bank > 26) + return false; + + /* DDRT errors can't be decoded from MCA bank registers */ + if (MCI_MISC_ECC_MODE(mce->misc) == MCI_MISC_ECC_DDRT) + return false; + + if (i10nm_mscod_is_ddrt(MCI_STATUS_MSCOD(mce->status))) + return false; + + /* Check whether one of {13,14,17,18,21,22,25,26} */ + return ((bank - 13) & BIT(1)) == 0; + default: + return false; + } +} + +static bool i10nm_mc_decode(struct decoded_addr *res) +{ + struct mce *m = res->mce; + struct skx_dev *d; + u8 bank; + + if (!i10nm_mc_decode_available(m)) + return false; + + list_for_each_entry(d, i10nm_edac_list, list) { + if (d->imc[0].src_id == m->socketid) { + res->socket = m->socketid; + res->dev = d; + break; + } + } + + switch (res_cfg->type) { + case I10NM: + bank = m->bank - 13; + res->imc = bank / 4; + res->channel = bank % 2; + break; + default: + return false; + } + + if (!res->dev) { + skx_printk(KERN_ERR, "No device for src_id %d imc %d\n", + m->socketid, res->imc); + return false; + } + + res->column = GET_BITFIELD(m->misc, 9, 18) << 2; + res->row = GET_BITFIELD(m->misc, 19, 39); + res->bank_group = GET_BITFIELD(m->misc, 40, 41); + res->bank_address = GET_BITFIELD(m->misc, 42, 43); + res->bank_group |= GET_BITFIELD(m->misc, 44, 44) << 2; + res->rank = GET_BITFIELD(m->misc, 56, 58); + res->dimm = res->rank >> 2; + res->rank = res->rank % 4; + + return true; +} + static int i10nm_get_ddr_munits(void) { struct pci_dev *mdev; @@ -420,7 +623,12 @@ static struct res_config spr_cfg = { .sad_all_devfn = PCI_DEVFN(10, 0), .sad_all_offset = 0x300, .offsets_scrub = offsets_scrub_spr, + .offsets_scrub_hbm0 = offsets_scrub_spr_hbm0, + .offsets_scrub_hbm1 = offsets_scrub_spr_hbm1, .offsets_demand = offsets_demand_spr, + .offsets_demand2 = offsets_demand2_spr, + .offsets_demand_hbm0 = offsets_demand_spr_hbm0, + .offsets_demand_hbm1 = offsets_demand_spr_hbm1, }; static const struct x86_cpu_id i10nm_cpuids[] = { @@ -574,7 +782,8 @@ static int __init i10nm_init(void) return -ENODEV; } - skx_set_mem_cfg(i10nm_check_2lm(cfg)); + mem_cfg_2lm = i10nm_check_2lm(cfg); + skx_set_mem_cfg(mem_cfg_2lm); rc = i10nm_get_ddr_munits(); @@ -626,9 +835,11 @@ static int __init i10nm_init(void) setup_i10nm_debug(); if (retry_rd_err_log && res_cfg->offsets_scrub && res_cfg->offsets_demand) { - skx_set_decode(NULL, show_retry_rd_err_log); + skx_set_decode(i10nm_mc_decode, show_retry_rd_err_log); if (retry_rd_err_log == 2) enable_retry_rd_err_log(true); + } else { + skx_set_decode(i10nm_mc_decode, NULL); } i10nm_printk(KERN_INFO, "%s\n", I10NM_REVISION); @@ -658,6 +869,34 @@ static void __exit i10nm_exit(void) module_init(i10nm_init); module_exit(i10nm_exit); +static int set_decoding_via_mca(const char *buf, const struct kernel_param *kp) +{ + unsigned long val; + int ret; + + ret = kstrtoul(buf, 0, &val); + + if (ret || val > 1) + return -EINVAL; + + if (val && mem_cfg_2lm) { + i10nm_printk(KERN_NOTICE, "Decoding errors via MCA banks for 2LM isn't supported yet\n"); + return -EIO; + } + + ret = param_set_int(buf, kp); + + return ret; +} + +static const struct kernel_param_ops decoding_via_mca_param_ops = { + .set = set_decoding_via_mca, + .get = param_get_int, +}; + +module_param_cb(decoding_via_mca, &decoding_via_mca_param_ops, &decoding_via_mca, 0644); +MODULE_PARM_DESC(decoding_via_mca, "decoding_via_mca: 0=off(default), 1=enable"); + module_param(retry_rd_err_log, int, 0444); MODULE_PARM_DESC(retry_rd_err_log, "retry_rd_err_log: 0=off(default), 1=bios(Linux doesn't reset any control bits, but just reports values.), 2=linux(Linux tries to take control and resets mode bits, clear valid/UC bits after reading.)"); diff --git a/drivers/edac/i7300_edac.c b/drivers/edac/i7300_edac.c index 4f28b8c8d378..61adaa872ba7 100644 --- a/drivers/edac/i7300_edac.c +++ b/drivers/edac/i7300_edac.c @@ -1193,7 +1193,7 @@ static int __init i7300_init(void) } /** - * i7300_init() - Unregisters the driver + * i7300_exit() - Unregisters the driver */ static void __exit i7300_exit(void) { diff --git a/drivers/edac/ie31200_edac.c b/drivers/edac/ie31200_edac.c index 9a9ff5ad611a..9ef13570f2e5 100644 --- a/drivers/edac/ie31200_edac.c +++ b/drivers/edac/ie31200_edac.c @@ -20,11 +20,15 @@ * 0c08: Xeon E3-1200 v3 Processor DRAM Controller * 1918: Xeon E3-1200 v5 Skylake Host Bridge/DRAM Registers * 5918: Xeon E3-1200 Xeon E3-1200 v6/7th Gen Core Processor Host Bridge/DRAM Registers + * 190f: 6th Gen Core Dual-Core Processor Host Bridge/DRAM Registers + * 191f: 6th Gen Core Quad-Core Processor Host Bridge/DRAM Registers * 3e..: 8th/9th Gen Core Processor Host Bridge/DRAM Registers * * Based on Intel specification: * https://www.intel.com/content/dam/www/public/us/en/documents/datasheets/xeon-e3-1200v3-vol-2-datasheet.pdf * http://www.intel.com/content/www/us/en/processors/xeon/xeon-e3-1200-family-vol-2-datasheet.html + * https://www.intel.com/content/dam/www/public/us/en/documents/datasheets/desktop-6th-gen-core-family-datasheet-vol-2.pdf + * https://www.intel.com/content/dam/www/public/us/en/documents/datasheets/xeon-e3-1200v6-vol-2-datasheet.pdf * https://www.intel.com/content/www/us/en/processors/core/7th-gen-core-family-mobile-h-processor-lines-datasheet-vol-2.html * https://www.intel.com/content/www/us/en/products/docs/processors/core/8th-gen-core-family-datasheet-vol-2.html * @@ -53,15 +57,17 @@ #define ie31200_printk(level, fmt, arg...) \ edac_printk(level, "ie31200", fmt, ##arg) -#define PCI_DEVICE_ID_INTEL_IE31200_HB_1 0x0108 -#define PCI_DEVICE_ID_INTEL_IE31200_HB_2 0x010c -#define PCI_DEVICE_ID_INTEL_IE31200_HB_3 0x0150 -#define PCI_DEVICE_ID_INTEL_IE31200_HB_4 0x0158 -#define PCI_DEVICE_ID_INTEL_IE31200_HB_5 0x015c -#define PCI_DEVICE_ID_INTEL_IE31200_HB_6 0x0c04 -#define PCI_DEVICE_ID_INTEL_IE31200_HB_7 0x0c08 -#define PCI_DEVICE_ID_INTEL_IE31200_HB_8 0x1918 -#define PCI_DEVICE_ID_INTEL_IE31200_HB_9 0x5918 +#define PCI_DEVICE_ID_INTEL_IE31200_HB_1 0x0108 +#define PCI_DEVICE_ID_INTEL_IE31200_HB_2 0x010c +#define PCI_DEVICE_ID_INTEL_IE31200_HB_3 0x0150 +#define PCI_DEVICE_ID_INTEL_IE31200_HB_4 0x0158 +#define PCI_DEVICE_ID_INTEL_IE31200_HB_5 0x015c +#define PCI_DEVICE_ID_INTEL_IE31200_HB_6 0x0c04 +#define PCI_DEVICE_ID_INTEL_IE31200_HB_7 0x0c08 +#define PCI_DEVICE_ID_INTEL_IE31200_HB_8 0x190F +#define PCI_DEVICE_ID_INTEL_IE31200_HB_9 0x1918 +#define PCI_DEVICE_ID_INTEL_IE31200_HB_10 0x191F +#define PCI_DEVICE_ID_INTEL_IE31200_HB_11 0x5918 /* Coffee Lake-S */ #define PCI_DEVICE_ID_INTEL_IE31200_HB_CFL_MASK 0x3e00 @@ -80,6 +86,8 @@ #define DEVICE_ID_SKYLAKE_OR_LATER(did) \ (((did) == PCI_DEVICE_ID_INTEL_IE31200_HB_8) || \ ((did) == PCI_DEVICE_ID_INTEL_IE31200_HB_9) || \ + ((did) == PCI_DEVICE_ID_INTEL_IE31200_HB_10) || \ + ((did) == PCI_DEVICE_ID_INTEL_IE31200_HB_11) || \ (((did) & PCI_DEVICE_ID_INTEL_IE31200_HB_CFL_MASK) == \ PCI_DEVICE_ID_INTEL_IE31200_HB_CFL_MASK)) @@ -577,6 +585,8 @@ static const struct pci_device_id ie31200_pci_tbl[] = { { PCI_VEND_DEV(INTEL, IE31200_HB_7), PCI_ANY_ID, PCI_ANY_ID, 0, 0, IE31200 }, { PCI_VEND_DEV(INTEL, IE31200_HB_8), PCI_ANY_ID, PCI_ANY_ID, 0, 0, IE31200 }, { PCI_VEND_DEV(INTEL, IE31200_HB_9), PCI_ANY_ID, PCI_ANY_ID, 0, 0, IE31200 }, + { PCI_VEND_DEV(INTEL, IE31200_HB_10), PCI_ANY_ID, PCI_ANY_ID, 0, 0, IE31200 }, + { PCI_VEND_DEV(INTEL, IE31200_HB_11), PCI_ANY_ID, PCI_ANY_ID, 0, 0, IE31200 }, { PCI_VEND_DEV(INTEL, IE31200_HB_CFL_1), PCI_ANY_ID, PCI_ANY_ID, 0, 0, IE31200 }, { PCI_VEND_DEV(INTEL, IE31200_HB_CFL_2), PCI_ANY_ID, PCI_ANY_ID, 0, 0, IE31200 }, { PCI_VEND_DEV(INTEL, IE31200_HB_CFL_3), PCI_ANY_ID, PCI_ANY_ID, 0, 0, IE31200 }, diff --git a/drivers/edac/ppc4xx_edac.c b/drivers/edac/ppc4xx_edac.c index 0bc670778c99..046969b4e82e 100644 --- a/drivers/edac/ppc4xx_edac.c +++ b/drivers/edac/ppc4xx_edac.c @@ -178,11 +178,6 @@ struct ppc4xx_ecc_status { u32 wmirq; }; -/* Function Prototypes */ - -static int ppc4xx_edac_probe(struct platform_device *device); -static int ppc4xx_edac_remove(struct platform_device *device); - /* Global Variables */ /* @@ -197,15 +192,6 @@ static const struct of_device_id ppc4xx_edac_match[] = { }; MODULE_DEVICE_TABLE(of, ppc4xx_edac_match); -static struct platform_driver ppc4xx_edac_driver = { - .probe = ppc4xx_edac_probe, - .remove = ppc4xx_edac_remove, - .driver = { - .name = PPC4XX_EDAC_MODULE_NAME, - .of_match_table = ppc4xx_edac_match, - }, -}; - /* * TODO: The row and channel parameters likely need to be dynamically * set based on the aforementioned variant controller realizations. @@ -1391,6 +1377,15 @@ ppc4xx_edac_opstate_init(void) EDAC_OPSTATE_UNKNOWN_STR))); } +static struct platform_driver ppc4xx_edac_driver = { + .probe = ppc4xx_edac_probe, + .remove = ppc4xx_edac_remove, + .driver = { + .name = PPC4XX_EDAC_MODULE_NAME, + .of_match_table = ppc4xx_edac_match, + }, +}; + /** * ppc4xx_edac_init - driver/module insertion entry point * diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index 9678ab97c7ac..8e39370fdb5c 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -335,6 +335,12 @@ struct sbridge_info { struct sbridge_channel { u32 ranks; u32 dimms; + struct dimm { + u32 rowbits; + u32 colbits; + u32 bank_xor_enable; + u32 amap_fine; + } dimm[MAX_DIMMS]; }; struct pci_id_descr { @@ -1603,7 +1609,7 @@ static int __populate_dimms(struct mem_ctl_info *mci, banks = 8; for (i = 0; i < channels; i++) { - u32 mtr; + u32 mtr, amap = 0; int max_dimms_per_channel; @@ -1615,6 +1621,7 @@ static int __populate_dimms(struct mem_ctl_info *mci, max_dimms_per_channel = ARRAY_SIZE(mtr_regs); if (!pvt->pci_tad[i]) continue; + pci_read_config_dword(pvt->pci_tad[i], 0x8c, &amap); } for (j = 0; j < max_dimms_per_channel; j++) { @@ -1627,6 +1634,7 @@ static int __populate_dimms(struct mem_ctl_info *mci, mtr_regs[j], &mtr); } edac_dbg(4, "Channel #%d MTR%d = %x\n", i, j, mtr); + if (IS_DIMM_PRESENT(mtr)) { if (!IS_ECC_ENABLED(pvt->info.mcmtr)) { sbridge_printk(KERN_ERR, "CPU SrcID #%d, Ha #%d, Channel #%d has DIMMs, but ECC is disabled\n", @@ -1661,6 +1669,11 @@ static int __populate_dimms(struct mem_ctl_info *mci, dimm->dtype = pvt->info.get_width(pvt, mtr); dimm->mtype = mtype; dimm->edac_mode = mode; + pvt->channel[i].dimm[j].rowbits = order_base_2(rows); + pvt->channel[i].dimm[j].colbits = order_base_2(cols); + pvt->channel[i].dimm[j].bank_xor_enable = + GET_BITFIELD(pvt->info.mcmtr, 9, 9); + pvt->channel[i].dimm[j].amap_fine = GET_BITFIELD(amap, 0, 0); snprintf(dimm->label, sizeof(dimm->label), "CPU_SrcID#%u_Ha#%u_Chan#%u_DIMM#%u", pvt->sbridge_dev->source_id, pvt->sbridge_dev->dom, i, j); @@ -1922,6 +1935,99 @@ static struct mem_ctl_info *get_mci_for_node_id(u8 node_id, u8 ha) return NULL; } +static u8 sb_close_row[] = { + 15, 16, 17, 18, 20, 21, 22, 28, 10, 11, 12, 13, 29, 30, 31, 32, 33 +}; + +static u8 sb_close_column[] = { + 3, 4, 5, 14, 19, 23, 24, 25, 26, 27 +}; + +static u8 sb_open_row[] = { + 14, 15, 16, 20, 28, 21, 22, 23, 24, 25, 26, 27, 29, 30, 31, 32, 33 +}; + +static u8 sb_open_column[] = { + 3, 4, 5, 6, 7, 8, 9, 10, 11, 12 +}; + +static u8 sb_open_fine_column[] = { + 3, 4, 5, 7, 8, 9, 10, 11, 12, 13 +}; + +static int sb_bits(u64 addr, int nbits, u8 *bits) +{ + int i, res = 0; + + for (i = 0; i < nbits; i++) + res |= ((addr >> bits[i]) & 1) << i; + return res; +} + +static int sb_bank_bits(u64 addr, int b0, int b1, int do_xor, int x0, int x1) +{ + int ret = GET_BITFIELD(addr, b0, b0) | (GET_BITFIELD(addr, b1, b1) << 1); + + if (do_xor) + ret ^= GET_BITFIELD(addr, x0, x0) | (GET_BITFIELD(addr, x1, x1) << 1); + + return ret; +} + +static bool sb_decode_ddr4(struct mem_ctl_info *mci, int ch, u8 rank, + u64 rank_addr, char *msg) +{ + int dimmno = 0; + int row, col, bank_address, bank_group; + struct sbridge_pvt *pvt; + u32 bg0 = 0, rowbits = 0, colbits = 0; + u32 amap_fine = 0, bank_xor_enable = 0; + + dimmno = (rank < 12) ? rank / 4 : 2; + pvt = mci->pvt_info; + amap_fine = pvt->channel[ch].dimm[dimmno].amap_fine; + bg0 = amap_fine ? 6 : 13; + rowbits = pvt->channel[ch].dimm[dimmno].rowbits; + colbits = pvt->channel[ch].dimm[dimmno].colbits; + bank_xor_enable = pvt->channel[ch].dimm[dimmno].bank_xor_enable; + + if (pvt->is_lockstep) { + pr_warn_once("LockStep row/column decode is not supported yet!\n"); + msg[0] = '\0'; + return false; + } + + if (pvt->is_close_pg) { + row = sb_bits(rank_addr, rowbits, sb_close_row); + col = sb_bits(rank_addr, colbits, sb_close_column); + col |= 0x400; /* C10 is autoprecharge, always set */ + bank_address = sb_bank_bits(rank_addr, 8, 9, bank_xor_enable, 22, 28); + bank_group = sb_bank_bits(rank_addr, 6, 7, bank_xor_enable, 20, 21); + } else { + row = sb_bits(rank_addr, rowbits, sb_open_row); + if (amap_fine) + col = sb_bits(rank_addr, colbits, sb_open_fine_column); + else + col = sb_bits(rank_addr, colbits, sb_open_column); + bank_address = sb_bank_bits(rank_addr, 18, 19, bank_xor_enable, 22, 23); + bank_group = sb_bank_bits(rank_addr, bg0, 17, bank_xor_enable, 20, 21); + } + + row &= (1u << rowbits) - 1; + + sprintf(msg, "row:0x%x col:0x%x bank_addr:%d bank_group:%d", + row, col, bank_address, bank_group); + return true; +} + +static bool sb_decode_ddr3(struct mem_ctl_info *mci, int ch, u8 rank, + u64 rank_addr, char *msg) +{ + pr_warn_once("DDR3 row/column decode not support yet!\n"); + msg[0] = '\0'; + return false; +} + static int get_memory_error_data(struct mem_ctl_info *mci, u64 addr, u8 *socket, u8 *ha, @@ -1937,12 +2043,13 @@ static int get_memory_error_data(struct mem_ctl_info *mci, int interleave_mode, shiftup = 0; unsigned int sad_interleave[MAX_INTERLEAVE]; u32 reg, dram_rule; - u8 ch_way, sck_way, pkg, sad_ha = 0; + u8 ch_way, sck_way, pkg, sad_ha = 0, rankid = 0; u32 tad_offset; u32 rir_way; u32 mb, gb; u64 ch_addr, offset, limit = 0, prv = 0; - + u64 rank_addr; + enum mem_type mtype; /* * Step 0) Check if the address is at special memory ranges @@ -2226,6 +2333,28 @@ static int get_memory_error_data(struct mem_ctl_info *mci, pci_read_config_dword(pvt->pci_tad[base_ch], rir_offset[n_rir][idx], ®); *rank = RIR_RNK_TGT(pvt->info.type, reg); + if (pvt->info.type == BROADWELL) { + if (pvt->is_close_pg) + shiftup = 6; + else + shiftup = 13; + + rank_addr = ch_addr >> shiftup; + rank_addr /= (1 << rir_way); + rank_addr <<= shiftup; + rank_addr |= ch_addr & GENMASK_ULL(shiftup - 1, 0); + rank_addr -= RIR_OFFSET(pvt->info.type, reg); + + mtype = pvt->info.get_memory_type(pvt); + rankid = *rank; + if (mtype == MEM_DDR4 || mtype == MEM_RDDR4) + sb_decode_ddr4(mci, base_ch, rankid, rank_addr, msg); + else + sb_decode_ddr3(mci, base_ch, rankid, rank_addr, msg); + } else { + msg[0] = '\0'; + } + edac_dbg(0, "RIR#%d: channel address 0x%08Lx < 0x%08Lx, RIR interleave %d, index %d\n", n_rir, ch_addr, @@ -2950,7 +3079,7 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci, struct mem_ctl_info *new_mci; struct sbridge_pvt *pvt = mci->pvt_info; enum hw_event_mc_err_type tp_event; - char *optype, msg[256]; + char *optype, msg[256], msg_full[512]; bool ripv = GET_BITFIELD(m->mcgstatus, 0, 0); bool overflow = GET_BITFIELD(m->status, 62, 62); bool uncorrected_error = GET_BITFIELD(m->status, 61, 61); @@ -3089,18 +3218,17 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci, */ if (!pvt->is_lockstep && !pvt->is_cur_addr_mirrored && !pvt->is_close_pg) channel = first_channel; - - snprintf(msg, sizeof(msg), - "%s%s area:%s err_code:%04x:%04x socket:%d ha:%d channel_mask:%ld rank:%d", + snprintf(msg_full, sizeof(msg_full), + "%s%s area:%s err_code:%04x:%04x socket:%d ha:%d channel_mask:%ld rank:%d %s", overflow ? " OVERFLOW" : "", (uncorrected_error && recoverable) ? " recoverable" : "", area_type, mscod, errcode, socket, ha, channel_mask, - rank); + rank, msg); - edac_dbg(0, "%s\n", msg); + edac_dbg(0, "%s\n", msg_full); /* FIXME: need support for channel mask */ @@ -3111,7 +3239,7 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci, edac_mc_handle_error(tp_event, mci, core_err_cnt, m->addr >> PAGE_SHIFT, m->addr & ~PAGE_MASK, 0, channel, dimm, -1, - optype, msg); + optype, msg_full); return; err_parsing: edac_mc_handle_error(tp_event, mci, core_err_cnt, 0, 0, 0, diff --git a/drivers/edac/skx_base.c b/drivers/edac/skx_base.c index 1abc020d49ab..7e2762f62eec 100644 --- a/drivers/edac/skx_base.c +++ b/drivers/edac/skx_base.c @@ -714,8 +714,13 @@ static int __init skx_init(void) skx_set_decode(skx_decode, skx_show_retry_rd_err_log); - if (nvdimm_count && skx_adxl_get() == -ENODEV) - skx_printk(KERN_NOTICE, "Only decoding DDR4 address!\n"); + if (nvdimm_count && skx_adxl_get() != -ENODEV) { + skx_set_decode(NULL, skx_show_retry_rd_err_log); + } else { + if (nvdimm_count) + skx_printk(KERN_NOTICE, "Only decoding DDR4 address!\n"); + skx_set_decode(skx_decode, skx_show_retry_rd_err_log); + } /* Ensure that the OPSTATE is set correctly for POLL or NMI */ opstate_init(); diff --git a/drivers/edac/skx_common.c b/drivers/edac/skx_common.c index 19c17c5198c5..f0f8e98f6efb 100644 --- a/drivers/edac/skx_common.c +++ b/drivers/edac/skx_common.c @@ -27,9 +27,11 @@ static const char * const component_names[] = { [INDEX_MEMCTRL] = "MemoryControllerId", [INDEX_CHANNEL] = "ChannelId", [INDEX_DIMM] = "DimmSlotId", + [INDEX_CS] = "ChipSelect", [INDEX_NM_MEMCTRL] = "NmMemoryControllerId", [INDEX_NM_CHANNEL] = "NmChannelId", [INDEX_NM_DIMM] = "NmDimmSlotId", + [INDEX_NM_CS] = "NmChipSelect", }; static int component_indices[ARRAY_SIZE(component_names)]; @@ -40,7 +42,7 @@ static char *adxl_msg; static unsigned long adxl_nm_bitmap; static char skx_msg[MSG_SIZE]; -static skx_decode_f skx_decode; +static skx_decode_f driver_decode; static skx_show_retry_log_f skx_show_retry_rd_err_log; static u64 skx_tolm, skx_tohm; static LIST_HEAD(dev_edac_list); @@ -139,10 +141,13 @@ static bool skx_adxl_decode(struct decoded_addr *res, bool error_in_1st_level_me (int)adxl_values[component_indices[INDEX_NM_CHANNEL]] : -1; res->dimm = (adxl_nm_bitmap & BIT_NM_DIMM) ? (int)adxl_values[component_indices[INDEX_NM_DIMM]] : -1; + res->cs = (adxl_nm_bitmap & BIT_NM_CS) ? + (int)adxl_values[component_indices[INDEX_NM_CS]] : -1; } else { res->imc = (int)adxl_values[component_indices[INDEX_MEMCTRL]]; res->channel = (int)adxl_values[component_indices[INDEX_CHANNEL]]; res->dimm = (int)adxl_values[component_indices[INDEX_DIMM]]; + res->cs = (int)adxl_values[component_indices[INDEX_CS]]; } if (res->imc > NUM_IMC - 1 || res->imc < 0) { @@ -173,6 +178,8 @@ static bool skx_adxl_decode(struct decoded_addr *res, bool error_in_1st_level_me break; } + res->decoded_by_adxl = true; + return true; } @@ -183,7 +190,7 @@ void skx_set_mem_cfg(bool mem_cfg_2lm) void skx_set_decode(skx_decode_f decode, skx_show_retry_log_f show_retry_log) { - skx_decode = decode; + driver_decode = decode; skx_show_retry_rd_err_log = show_retry_log; } @@ -591,19 +598,19 @@ static void skx_mce_output_error(struct mem_ctl_info *mci, break; } } - if (adxl_component_count) { + if (res->decoded_by_adxl) { len = snprintf(skx_msg, MSG_SIZE, "%s%s err_code:0x%04x:0x%04x %s", overflow ? " OVERFLOW" : "", (uncorrected_error && recoverable) ? " recoverable" : "", mscod, errcode, adxl_msg); } else { len = snprintf(skx_msg, MSG_SIZE, - "%s%s err_code:0x%04x:0x%04x socket:%d imc:%d rank:%d bg:%d ba:%d row:0x%x col:0x%x", + "%s%s err_code:0x%04x:0x%04x ProcessorSocketId:0x%x MemoryControllerId:0x%x PhysicalRankId:0x%x Row:0x%x Column:0x%x Bank:0x%x BankGroup:0x%x", overflow ? " OVERFLOW" : "", (uncorrected_error && recoverable) ? " recoverable" : "", mscod, errcode, res->socket, res->imc, res->rank, - res->bank_group, res->bank_address, res->row, res->column); + res->row, res->column, res->bank_address, res->bank_group); } if (skx_show_retry_rd_err_log) @@ -649,13 +656,14 @@ int skx_mce_check_error(struct notifier_block *nb, unsigned long val, return NOTIFY_DONE; memset(&res, 0, sizeof(res)); + res.mce = mce; res.addr = mce->addr; - if (adxl_component_count) { - if (!skx_adxl_decode(&res, skx_error_in_1st_level_mem(mce))) + /* Try driver decoder first */ + if (!(driver_decode && driver_decode(&res))) { + /* Then try firmware decoder (ACPI DSM methods) */ + if (!(adxl_component_count && skx_adxl_decode(&res, skx_error_in_1st_level_mem(mce)))) return NOTIFY_DONE; - } else if (!skx_decode || !skx_decode(&res)) { - return NOTIFY_DONE; } mci = res.dev->imc[res.imc].mci; diff --git a/drivers/edac/skx_common.h b/drivers/edac/skx_common.h index 03ac067a80b9..0cbadd3d2cd3 100644 --- a/drivers/edac/skx_common.h +++ b/drivers/edac/skx_common.h @@ -10,6 +10,7 @@ #define _SKX_COMM_EDAC_H #include +#include #define MSG_SIZE 1024 @@ -52,6 +53,9 @@ #define IS_DIMM_PRESENT(r) GET_BITFIELD(r, 15, 15) #define IS_NVDIMM_PRESENT(r, i) GET_BITFIELD(r, i, i) +#define MCI_MISC_ECC_MODE(m) (((m) >> 59) & 15) +#define MCI_MISC_ECC_DDRT 8 /* read from DDRT */ + /* * Each cpu socket contains some pci devices that provide global * information, and also some that are local to each of the two @@ -82,6 +86,7 @@ struct skx_dev { struct pci_dev *edev; u32 retry_rd_err_log_s; u32 retry_rd_err_log_d; + u32 retry_rd_err_log_d2; struct skx_dimm { u8 close_pg; u8 bank_xor_enable; @@ -108,18 +113,22 @@ enum { INDEX_MEMCTRL, INDEX_CHANNEL, INDEX_DIMM, + INDEX_CS, INDEX_NM_FIRST, INDEX_NM_MEMCTRL = INDEX_NM_FIRST, INDEX_NM_CHANNEL, INDEX_NM_DIMM, + INDEX_NM_CS, INDEX_MAX }; #define BIT_NM_MEMCTRL BIT_ULL(INDEX_NM_MEMCTRL) #define BIT_NM_CHANNEL BIT_ULL(INDEX_NM_CHANNEL) #define BIT_NM_DIMM BIT_ULL(INDEX_NM_DIMM) +#define BIT_NM_CS BIT_ULL(INDEX_NM_CS) struct decoded_addr { + struct mce *mce; struct skx_dev *dev; u64 addr; int socket; @@ -129,6 +138,7 @@ struct decoded_addr { int sktways; int chanways; int dimm; + int cs; int rank; int channel_rank; u64 rank_address; @@ -136,6 +146,7 @@ struct decoded_addr { int column; int bank_address; int bank_group; + bool decoded_by_adxl; }; struct res_config { @@ -154,7 +165,12 @@ struct res_config { int sad_all_offset; /* Offsets of retry_rd_err_log registers */ u32 *offsets_scrub; + u32 *offsets_scrub_hbm0; + u32 *offsets_scrub_hbm1; u32 *offsets_demand; + u32 *offsets_demand2; + u32 *offsets_demand_hbm0; + u32 *offsets_demand_hbm1; }; typedef int (*get_dimm_config_f)(struct mem_ctl_info *mci, diff --git a/drivers/edac/wq.c b/drivers/edac/wq.c index d021d287eaec..ad3f516627c5 100644 --- a/drivers/edac/wq.c +++ b/drivers/edac/wq.c @@ -37,7 +37,6 @@ int edac_workqueue_setup(void) void edac_workqueue_teardown(void) { - flush_workqueue(wq); destroy_workqueue(wq); wq = NULL; } diff --git a/drivers/ras/cec.c b/drivers/ras/cec.c index 42f2fc0bc8a9..321af498ee11 100644 --- a/drivers/ras/cec.c +++ b/drivers/ras/cec.c @@ -556,6 +556,14 @@ static int __init cec_init(void) if (ce_arr.disabled) return -ENODEV; + /* + * Intel systems may avoid uncorrectable errors + * if pages with corrected errors are aggressively + * taken offline. + */ + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) + action_threshold = 2; + ce_arr.array = (void *)get_zeroed_page(GFP_KERNEL); if (!ce_arr.array) { pr_err("Error allocating CE array page!\n"); diff --git a/fs/crypto/inline_crypt.c b/fs/crypto/inline_crypt.c index 3b4e838c2d15..5a6abb8c1470 100644 --- a/fs/crypto/inline_crypt.c +++ b/fs/crypto/inline_crypt.c @@ -460,46 +460,45 @@ bool fscrypt_mergeable_bio_bh(struct bio *bio, EXPORT_SYMBOL_GPL(fscrypt_mergeable_bio_bh); /** - * fscrypt_dio_supported() - check whether a DIO (direct I/O) request is - * supported as far as encryption is concerned - * @iocb: the file and position the I/O is targeting - * @iter: the I/O data segment(s) + * fscrypt_dio_supported() - check whether DIO (direct I/O) is supported on an + * inode, as far as encryption is concerned + * @inode: the inode in question * * Return: %true if there are no encryption constraints that prevent DIO from * being supported; %false if DIO is unsupported. (Note that in the * %true case, the filesystem might have other, non-encryption-related - * constraints that prevent DIO from actually being supported.) + * constraints that prevent DIO from actually being supported. Also, on + * encrypted files the filesystem is still responsible for only allowing + * DIO when requests are filesystem-block-aligned.) */ -bool fscrypt_dio_supported(struct kiocb *iocb, struct iov_iter *iter) +bool fscrypt_dio_supported(struct inode *inode) { - const struct inode *inode = file_inode(iocb->ki_filp); - const unsigned int blocksize = i_blocksize(inode); + int err; /* If the file is unencrypted, no veto from us. */ if (!fscrypt_needs_contents_encryption(inode)) return true; - /* We only support DIO with inline crypto, not fs-layer crypto. */ - if (!fscrypt_inode_uses_inline_crypto(inode)) - return false; - /* - * Since the granularity of encryption is filesystem blocks, the file - * position and total I/O length must be aligned to the filesystem block - * size -- not just to the block device's logical block size as is - * traditionally the case for DIO on many filesystems. + * We only support DIO with inline crypto, not fs-layer crypto. * - * We require that the user-provided memory buffers be filesystem block - * aligned too. It is simpler to have a single alignment value required - * for all properties of the I/O, as is normally the case for DIO. - * Also, allowing less aligned buffers would imply that data units could - * cross bvecs, which would greatly complicate the I/O stack, which - * assumes that bios can be split at any bvec boundary. + * To determine whether the inode is using inline crypto, we have to set + * up the key if it wasn't already done. This is because in the current + * design of fscrypt, the decision of whether to use inline crypto or + * not isn't made until the inode's encryption key is being set up. In + * the DIO read/write case, the key will always be set up already, since + * the file will be open. But in the case of statx(), the key might not + * be set up yet, as the file might not have been opened yet. */ - if (!IS_ALIGNED(iocb->ki_pos | iov_iter_alignment(iter), blocksize)) + err = fscrypt_require_key(inode); + if (err) { + /* + * Key unavailable or couldn't be set up. This edge case isn't + * worth worrying about; just report that DIO is unsupported. + */ return false; - - return true; + } + return fscrypt_inode_uses_inline_crypto(inode); } EXPORT_SYMBOL_GPL(fscrypt_dio_supported); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 3bf9a6926798..e5f2f5ca5120 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2977,6 +2977,7 @@ extern struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, extern int ext4_write_inode(struct inode *, struct writeback_control *); extern int ext4_setattr(struct user_namespace *, struct dentry *, struct iattr *); +extern u32 ext4_dio_alignment(struct inode *inode); extern int ext4_getattr(struct user_namespace *, const struct path *, struct kstat *, u32, unsigned int); extern void ext4_evict_inode(struct inode *); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 109d07629f81..8bb1c35fd6dd 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -36,19 +36,34 @@ #include "acl.h" #include "truncate.h" -static bool ext4_dio_supported(struct kiocb *iocb, struct iov_iter *iter) +/* + * Returns %true if the given DIO request should be attempted with DIO, or + * %false if it should fall back to buffered I/O. + * + * DIO isn't well specified; when it's unsupported (either due to the request + * being misaligned, or due to the file not supporting DIO at all), filesystems + * either fall back to buffered I/O or return EINVAL. For files that don't use + * any special features like encryption or verity, ext4 has traditionally + * returned EINVAL for misaligned DIO. iomap_dio_rw() uses this convention too. + * In this case, we should attempt the DIO, *not* fall back to buffered I/O. + * + * In contrast, in cases where DIO is unsupported due to ext4 features, ext4 + * traditionally falls back to buffered I/O. + * + * This function implements the traditional ext4 behavior in all these cases. + */ +static bool ext4_should_use_dio(struct kiocb *iocb, struct iov_iter *iter) { struct inode *inode = file_inode(iocb->ki_filp); + u32 dio_align = ext4_dio_alignment(inode); - if (!fscrypt_dio_supported(iocb, iter)) + if (dio_align == 0) return false; - if (fsverity_active(inode)) - return false; - if (ext4_should_journal_data(inode)) - return false; - if (ext4_has_inline_data(inode)) - return false; - return true; + + if (dio_align == 1) + return true; + + return IS_ALIGNED(iocb->ki_pos | iov_iter_alignment(iter), dio_align); } static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to) @@ -63,7 +78,7 @@ static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to) inode_lock_shared(inode); } - if (!ext4_dio_supported(iocb, to)) { + if (!ext4_should_use_dio(iocb, to)) { inode_unlock_shared(inode); /* * Fallback to buffered I/O if the operation being performed on @@ -511,7 +526,7 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) } /* Fallback to buffered I/O if the inode does not support direct I/O. */ - if (!ext4_dio_supported(iocb, from)) { + if (!ext4_should_use_dio(iocb, from)) { if (ilock_shared) inode_unlock_shared(inode); else diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 601214453c3a..364774230d87 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5550,6 +5550,22 @@ err_out: return error; } +u32 ext4_dio_alignment(struct inode *inode) +{ + if (fsverity_active(inode)) + return 0; + if (ext4_should_journal_data(inode)) + return 0; + if (ext4_has_inline_data(inode)) + return 0; + if (IS_ENCRYPTED(inode)) { + if (!fscrypt_dio_supported(inode)) + return 0; + return i_blocksize(inode); + } + return 1; /* use the iomap defaults */ +} + int ext4_getattr(struct user_namespace *mnt_userns, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { @@ -5565,6 +5581,27 @@ int ext4_getattr(struct user_namespace *mnt_userns, const struct path *path, stat->btime.tv_nsec = ei->i_crtime.tv_nsec; } + /* + * Return the DIO alignment restrictions if requested. We only return + * this information when requested, since on encrypted files it might + * take a fair bit of work to get if the file wasn't opened recently. + */ + if ((request_mask & STATX_DIOALIGN) && S_ISREG(inode->i_mode)) { + u32 dio_align = ext4_dio_alignment(inode); + + stat->result_mask |= STATX_DIOALIGN; + if (dio_align == 1) { + struct block_device *bdev = inode->i_sb->s_bdev; + + /* iomap defaults */ + stat->dio_mem_align = bdev_dma_alignment(bdev) + 1; + stat->dio_offset_align = bdev_logical_block_size(bdev); + } else { + stat->dio_mem_align = dio_align; + stat->dio_offset_align = dio_align; + } + } + flags = ei->i_flags & EXT4_FL_USER_VISIBLE; if (flags & EXT4_APPEND_FL) stat->attributes |= STATX_ATTR_APPEND; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 3c7cdb70fe2e..aea816a133a8 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -4471,17 +4471,6 @@ static inline void f2fs_i_compr_blocks_update(struct inode *inode, f2fs_mark_inode_dirty_sync(inode, true); } -static inline int block_unaligned_IO(struct inode *inode, - struct kiocb *iocb, struct iov_iter *iter) -{ - unsigned int i_blkbits = READ_ONCE(inode->i_blkbits); - unsigned int blocksize_mask = (1 << i_blkbits) - 1; - loff_t offset = iocb->ki_pos; - unsigned long align = offset | iov_iter_alignment(iter); - - return align & blocksize_mask; -} - static inline bool f2fs_allow_multi_device_dio(struct f2fs_sb_info *sbi, int flag) { @@ -4492,35 +4481,6 @@ static inline bool f2fs_allow_multi_device_dio(struct f2fs_sb_info *sbi, return sbi->aligned_blksize; } -static inline bool f2fs_force_buffered_io(struct inode *inode, - struct kiocb *iocb, struct iov_iter *iter) -{ - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - int rw = iov_iter_rw(iter); - - if (!fscrypt_dio_supported(iocb, iter)) - return true; - if (fsverity_active(inode)) - return true; - if (f2fs_compressed_file(inode)) - return true; - - /* disallow direct IO if any of devices has unaligned blksize */ - if (f2fs_is_multi_device(sbi) && !sbi->aligned_blksize) - return true; - - if (f2fs_lfs_mode(sbi) && (rw == WRITE)) { - if (block_unaligned_IO(inode, iocb, iter)) - return true; - if (F2FS_IO_ALIGNED(sbi)) - return true; - } - if (is_sbi_flag_set(F2FS_I_SB(inode), SBI_CP_DISABLED)) - return true; - - return false; -} - static inline bool f2fs_need_verity(const struct inode *inode, pgoff_t idx) { return fsverity_active(inode) && diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index ce4905a073b3..791770507328 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -808,6 +808,29 @@ int f2fs_truncate(struct inode *inode) return 0; } +static bool f2fs_force_buffered_io(struct inode *inode, int rw) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + + if (!fscrypt_dio_supported(inode)) + return true; + if (fsverity_active(inode)) + return true; + if (f2fs_compressed_file(inode)) + return true; + + /* disallow direct IO if any of devices has unaligned blksize */ + if (f2fs_is_multi_device(sbi) && !sbi->aligned_blksize) + return true; + + if (f2fs_lfs_mode(sbi) && rw == WRITE && F2FS_IO_ALIGNED(sbi)) + return true; + if (is_sbi_flag_set(sbi, SBI_CP_DISABLED)) + return true; + + return false; +} + int f2fs_getattr(struct user_namespace *mnt_userns, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { @@ -824,6 +847,24 @@ int f2fs_getattr(struct user_namespace *mnt_userns, const struct path *path, stat->btime.tv_nsec = fi->i_crtime.tv_nsec; } + /* + * Return the DIO alignment restrictions if requested. We only return + * this information when requested, since on encrypted files it might + * take a fair bit of work to get if the file wasn't opened recently. + * + * f2fs sometimes supports DIO reads but not DIO writes. STATX_DIOALIGN + * cannot represent that, so in that case we report no DIO support. + */ + if ((request_mask & STATX_DIOALIGN) && S_ISREG(inode->i_mode)) { + unsigned int bsize = i_blocksize(inode); + + stat->result_mask |= STATX_DIOALIGN; + if (!f2fs_force_buffered_io(inode, WRITE)) { + stat->dio_mem_align = bsize; + stat->dio_offset_align = bsize; + } + } + flags = fi->i_flags; if (flags & F2FS_COMPR_FL) stat->attributes |= STATX_ATTR_COMPRESSED; @@ -4182,7 +4223,7 @@ static bool f2fs_should_use_dio(struct inode *inode, struct kiocb *iocb, if (!(iocb->ki_flags & IOCB_DIRECT)) return false; - if (f2fs_force_buffered_io(inode, iocb, iter)) + if (f2fs_force_buffered_io(inode, iov_iter_rw(iter))) return false; /* diff --git a/fs/stat.c b/fs/stat.c index 9ced8860e0f3..ef50573c72a2 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -5,6 +5,7 @@ * Copyright (C) 1991, 1992 Linus Torvalds */ +#include #include #include #include @@ -230,11 +231,22 @@ retry: goto out; error = vfs_getattr(&path, stat, request_mask, flags); + stat->mnt_id = real_mount(path.mnt)->mnt_id; stat->result_mask |= STATX_MNT_ID; + if (path.mnt->mnt_root == path.dentry) stat->attributes |= STATX_ATTR_MOUNT_ROOT; stat->attributes_mask |= STATX_ATTR_MOUNT_ROOT; + + /* Handle STATX_DIOALIGN for block devices. */ + if (request_mask & STATX_DIOALIGN) { + struct inode *inode = d_backing_inode(path.dentry); + + if (S_ISBLK(inode->i_mode)) + bdev_statx_dioalign(inode, stat); + } + path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; @@ -611,6 +623,8 @@ cp_statx(const struct kstat *stat, struct statx __user *buffer) tmp.stx_dev_major = MAJOR(stat->dev); tmp.stx_dev_minor = MINOR(stat->dev); tmp.stx_mnt_id = stat->mnt_id; + tmp.stx_dio_mem_align = stat->dio_mem_align; + tmp.stx_dio_offset_align = stat->dio_offset_align; return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0; } diff --git a/fs/verity/read_metadata.c b/fs/verity/read_metadata.c index 6ee849dc7bc1..2aefc5565152 100644 --- a/fs/verity/read_metadata.c +++ b/fs/verity/read_metadata.c @@ -53,14 +53,14 @@ static int fsverity_read_merkle_tree(struct inode *inode, break; } - virt = kmap(page); + virt = kmap_local_page(page); if (copy_to_user(buf, virt + offs_in_page, bytes_to_copy)) { - kunmap(page); + kunmap_local(virt); put_page(page); err = -EFAULT; break; } - kunmap(page); + kunmap_local(virt); put_page(page); retval += bytes_to_copy; diff --git a/fs/verity/verify.c b/fs/verity/verify.c index 14e2fb49cff5..bde8c9b7d25f 100644 --- a/fs/verity/verify.c +++ b/fs/verity/verify.c @@ -39,16 +39,6 @@ static void hash_at_level(const struct merkle_tree_params *params, (params->log_blocksize - params->log_arity); } -/* Extract a hash from a hash page */ -static void extract_hash(struct page *hpage, unsigned int hoffset, - unsigned int hsize, u8 *out) -{ - void *virt = kmap_atomic(hpage); - - memcpy(out, virt + hoffset, hsize); - kunmap_atomic(virt); -} - static inline int cmp_hashes(const struct fsverity_info *vi, const u8 *want_hash, const u8 *real_hash, pgoff_t index, int level) @@ -129,7 +119,7 @@ static bool verify_page(struct inode *inode, const struct fsverity_info *vi, } if (PageChecked(hpage)) { - extract_hash(hpage, hoffset, hsize, _want_hash); + memcpy_from_page(_want_hash, hpage, hoffset, hsize); want_hash = _want_hash; put_page(hpage); pr_debug_ratelimited("Hash page already checked, want %s:%*phN\n", @@ -158,7 +148,7 @@ descend: if (err) goto out; SetPageChecked(hpage); - extract_hash(hpage, hoffset, hsize, _want_hash); + memcpy_from_page(_want_hash, hpage, hoffset, hsize); want_hash = _want_hash; put_page(hpage); pr_debug("Verified hash page at level %d, now want %s:%*phN\n", diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 45518b8c613c..f51c60d7e205 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -604,6 +604,16 @@ xfs_vn_getattr( stat->blksize = BLKDEV_IOSIZE; stat->rdev = inode->i_rdev; break; + case S_IFREG: + if (request_mask & STATX_DIOALIGN) { + struct xfs_buftarg *target = xfs_inode_buftarg(ip); + struct block_device *bdev = target->bt_bdev; + + stat->result_mask |= STATX_DIOALIGN; + stat->dio_mem_align = bdev_dma_alignment(bdev) + 1; + stat->dio_offset_align = bdev_logical_block_size(bdev); + } + fallthrough; default: stat->blksize = xfs_stat_blksize(ip); stat->rdev = 0; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 84b13fdd34a7..8038c5fbde40 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1498,6 +1498,7 @@ int sync_blockdev(struct block_device *bdev); int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend); int sync_blockdev_nowait(struct block_device *bdev); void sync_bdevs(bool wait); +void bdev_statx_dioalign(struct inode *inode, struct kstat *stat); void printk_all_partitions(void); #else static inline void invalidate_bdev(struct block_device *bdev) @@ -1514,6 +1515,9 @@ static inline int sync_blockdev_nowait(struct block_device *bdev) static inline void sync_bdevs(bool wait) { } +static inline void bdev_statx_dioalign(struct inode *inode, struct kstat *stat) +{ +} static inline void printk_all_partitions(void) { } diff --git a/include/linux/edac.h b/include/linux/edac.h index e730b3468719..fa4bda2a70f6 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -231,21 +231,21 @@ enum mem_type { #define MEM_FLAG_DDR BIT(MEM_DDR) #define MEM_FLAG_RDDR BIT(MEM_RDDR) #define MEM_FLAG_RMBS BIT(MEM_RMBS) -#define MEM_FLAG_DDR2 BIT(MEM_DDR2) -#define MEM_FLAG_FB_DDR2 BIT(MEM_FB_DDR2) -#define MEM_FLAG_RDDR2 BIT(MEM_RDDR2) -#define MEM_FLAG_XDR BIT(MEM_XDR) -#define MEM_FLAG_DDR3 BIT(MEM_DDR3) -#define MEM_FLAG_RDDR3 BIT(MEM_RDDR3) -#define MEM_FLAG_LPDDR3 BIT(MEM_LPDDR3) -#define MEM_FLAG_DDR4 BIT(MEM_DDR4) -#define MEM_FLAG_RDDR4 BIT(MEM_RDDR4) -#define MEM_FLAG_LRDDR4 BIT(MEM_LRDDR4) -#define MEM_FLAG_LPDDR4 BIT(MEM_LPDDR4) -#define MEM_FLAG_DDR5 BIT(MEM_DDR5) -#define MEM_FLAG_RDDR5 BIT(MEM_RDDR5) -#define MEM_FLAG_LRDDR5 BIT(MEM_LRDDR5) -#define MEM_FLAG_NVDIMM BIT(MEM_NVDIMM) +#define MEM_FLAG_DDR2 BIT(MEM_DDR2) +#define MEM_FLAG_FB_DDR2 BIT(MEM_FB_DDR2) +#define MEM_FLAG_RDDR2 BIT(MEM_RDDR2) +#define MEM_FLAG_XDR BIT(MEM_XDR) +#define MEM_FLAG_DDR3 BIT(MEM_DDR3) +#define MEM_FLAG_RDDR3 BIT(MEM_RDDR3) +#define MEM_FLAG_LPDDR3 BIT(MEM_LPDDR3) +#define MEM_FLAG_DDR4 BIT(MEM_DDR4) +#define MEM_FLAG_RDDR4 BIT(MEM_RDDR4) +#define MEM_FLAG_LRDDR4 BIT(MEM_LRDDR4) +#define MEM_FLAG_LPDDR4 BIT(MEM_LPDDR4) +#define MEM_FLAG_DDR5 BIT(MEM_DDR5) +#define MEM_FLAG_RDDR5 BIT(MEM_RDDR5) +#define MEM_FLAG_LRDDR5 BIT(MEM_LRDDR5) +#define MEM_FLAG_NVDIMM BIT(MEM_NVDIMM) #define MEM_FLAG_WIO2 BIT(MEM_WIO2) #define MEM_FLAG_HBM2 BIT(MEM_HBM2) diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 37b2d7bceacf..bdcf21d1f839 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -764,7 +764,7 @@ bool fscrypt_mergeable_bio(struct bio *bio, const struct inode *inode, bool fscrypt_mergeable_bio_bh(struct bio *bio, const struct buffer_head *next_bh); -bool fscrypt_dio_supported(struct kiocb *iocb, struct iov_iter *iter); +bool fscrypt_dio_supported(struct inode *inode); u64 fscrypt_limit_io_blocks(const struct inode *inode, u64 lblk, u64 nr_blocks); @@ -797,11 +797,8 @@ static inline bool fscrypt_mergeable_bio_bh(struct bio *bio, return true; } -static inline bool fscrypt_dio_supported(struct kiocb *iocb, - struct iov_iter *iter) +static inline bool fscrypt_dio_supported(struct inode *inode) { - const struct inode *inode = file_inode(iocb->ki_filp); - return !fscrypt_needs_contents_encryption(inode); } diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 15b49e655ce3..b362d90eb9b0 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -75,6 +75,9 @@ #define PCI_CLASS_COMMUNICATION_MODEM 0x0703 #define PCI_CLASS_COMMUNICATION_OTHER 0x0780 +/* Interface for SERIAL/MODEM */ +#define PCI_SERIAL_16550_COMPATIBLE 0x02 + #define PCI_BASE_CLASS_SYSTEM 0x08 #define PCI_CLASS_SYSTEM_PIC 0x0800 #define PCI_CLASS_SYSTEM_PIC_IOAPIC 0x080010 diff --git a/include/linux/stat.h b/include/linux/stat.h index 7df06931f25d..ff277ced50e9 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -50,6 +50,8 @@ struct kstat { struct timespec64 btime; /* File creation time */ u64 blocks; u64 mnt_id; + u32 dio_mem_align; + u32 dio_offset_align; }; #endif diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index 1500a0f58041..7cab2c65d3d7 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -124,7 +124,8 @@ struct statx { __u32 stx_dev_minor; /* 0x90 */ __u64 stx_mnt_id; - __u64 __spare2; + __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */ + __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */ /* 0xa0 */ __u64 __spare3[12]; /* Spare space for future expansion */ /* 0x100 */ @@ -152,6 +153,7 @@ struct statx { #define STATX_BASIC_STATS 0x000007ffU /* The stuff in the normal stat struct */ #define STATX_BTIME 0x00000800U /* Want/got stx_btime */ #define STATX_MNT_ID 0x00001000U /* Got stx_mnt_id */ +#define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 48e18737a2d1..4a9ba6ab80d5 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -1073,6 +1073,9 @@ static const char *uaccess_safe_builtin[] = { "copy_mc_fragile_handle_tail", "copy_mc_enhanced_fast_string", "ftrace_likely_update", /* CONFIG_TRACE_BRANCH_PROFILING */ + "clear_user_erms", + "clear_user_rep_good", + "clear_user_original", NULL };