diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst index 6bd97cd50d625..7e061ed449aaa 100644 --- a/Documentation/admin-guide/hw-vuln/spectre.rst +++ b/Documentation/admin-guide/hw-vuln/spectre.rst @@ -422,6 +422,14 @@ The possible values in this file are: 'RSB filling' Protection of RSB on context switch enabled ============= =========================================== + - EIBRS Post-barrier Return Stack Buffer (PBRSB) protection status: + + =========================== ======================================================= + 'PBRSB-eIBRS: SW sequence' CPU is affected and protection of RSB on VMEXIT enabled + 'PBRSB-eIBRS: Vulnerable' CPU is vulnerable + 'PBRSB-eIBRS: Not affected' CPU is not affected by PBRSB + =========================== ======================================================= + Full mitigation might require a microcode update from the CPU vendor. When the necessary microcode is not available, the kernel will report vulnerability. diff --git a/Makefile b/Makefile index 7093e3b03b9f7..74abb7e389f33 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 4 -SUBLEVEL = 209 +SUBLEVEL = 210 EXTRAVERSION = NAME = Kleptomaniac Octopus diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 8c28a2365a92b..a3e32bc938562 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -286,6 +286,7 @@ #define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* LLC Local MBM monitoring */ #define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* "" LFENCE in user entry SWAPGS path */ #define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */ +#define X86_FEATURE_RSB_VMEXIT_LITE (11*32+ 6) /* "" Fill RSB on VM exit when EIBRS is enabled */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ @@ -406,5 +407,6 @@ #define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ #define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */ #define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */ +#define X86_BUG_EIBRS_PBRSB X86_BUG(26) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index c56042916a7c3..cef4eba03ff36 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -129,6 +129,10 @@ * bit available to control VERW * behavior. */ +#define ARCH_CAP_PBRSB_NO BIT(24) /* + * Not susceptible to Post-Barrier + * Return Stack Buffer Predictions. + */ #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index ece2b2c6d020d..1e5df3ccdd5cb 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -61,7 +61,16 @@ 774: \ dec reg; \ jnz 771b; \ - add $(BITS_PER_LONG/8) * nr, sp; + add $(BITS_PER_LONG/8) * nr, sp; \ + /* barrier for jnz misprediction */ \ + lfence; + +#define __ISSUE_UNBALANCED_RET_GUARD(sp) \ + call 881f; \ + int3; \ +881: \ + add $(BITS_PER_LONG/8), sp; \ + lfence; #ifdef __ASSEMBLY__ @@ -130,6 +139,14 @@ #else call *\reg #endif +.endm + +.macro ISSUE_UNBALANCED_RET_GUARD ftr:req + ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE "jmp .Lskip_pbrsb_\@", \ + __stringify(__ISSUE_UNBALANCED_RET_GUARD(%_ASM_SP)) \ + \ftr +.Lskip_pbrsb_\@: .endm /* diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 09d02b1f6f71f..57efa90f3fbd0 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1043,6 +1043,49 @@ static enum spectre_v2_mitigation __init spectre_v2_select_retpoline(void) return SPECTRE_V2_RETPOLINE; } +static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_mitigation mode) +{ + /* + * Similar to context switches, there are two types of RSB attacks + * after VM exit: + * + * 1) RSB underflow + * + * 2) Poisoned RSB entry + * + * When retpoline is enabled, both are mitigated by filling/clearing + * the RSB. + * + * When IBRS is enabled, while #1 would be mitigated by the IBRS branch + * prediction isolation protections, RSB still needs to be cleared + * because of #2. Note that SMEP provides no protection here, unlike + * user-space-poisoned RSB entries. + * + * eIBRS should protect against RSB poisoning, but if the EIBRS_PBRSB + * bug is present then a LITE version of RSB protection is required, + * just a single call needs to retire before a RET is executed. + */ + switch (mode) { + case SPECTRE_V2_NONE: + /* These modes already fill RSB at vmexit */ + case SPECTRE_V2_LFENCE: + case SPECTRE_V2_RETPOLINE: + case SPECTRE_V2_EIBRS_RETPOLINE: + return; + + case SPECTRE_V2_EIBRS_LFENCE: + case SPECTRE_V2_EIBRS: + if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) { + setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT_LITE); + pr_info("Spectre v2 / PBRSB-eIBRS: Retire a single CALL on VMEXIT\n"); + } + return; + } + + pr_warn_once("Unknown Spectre v2 mode, disabling RSB mitigation at VM exit"); + dump_stack(); +} + static void __init spectre_v2_select_mitigation(void) { enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); @@ -1135,6 +1178,8 @@ static void __init spectre_v2_select_mitigation(void) setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n"); + spectre_v2_determine_rsb_fill_type_at_vmexit(mode); + /* * Retpoline means the kernel is safe because it has no indirect * branches. Enhanced IBRS protects firmware too, so, enable restricted @@ -1879,6 +1924,19 @@ static char *ibpb_state(void) return ""; } +static char *pbrsb_eibrs_state(void) +{ + if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) { + if (boot_cpu_has(X86_FEATURE_RSB_VMEXIT_LITE) || + boot_cpu_has(X86_FEATURE_RETPOLINE)) + return ", PBRSB-eIBRS: SW sequence"; + else + return ", PBRSB-eIBRS: Vulnerable"; + } else { + return ", PBRSB-eIBRS: Not affected"; + } +} + static ssize_t spectre_v2_show_state(char *buf) { if (spectre_v2_enabled == SPECTRE_V2_LFENCE) @@ -1891,12 +1949,13 @@ static ssize_t spectre_v2_show_state(char *buf) spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE) return sprintf(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n"); - return sprintf(buf, "%s%s%s%s%s%s\n", + return sprintf(buf, "%s%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], ibpb_state(), boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", stibp_state(), boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "", + pbrsb_eibrs_state(), spectre_v2_module_string()); } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 305f30e45f3d3..b926b7244d42d 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1025,6 +1025,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #define NO_SWAPGS BIT(6) #define NO_ITLB_MULTIHIT BIT(7) #define NO_SPECTRE_V2 BIT(8) +#define NO_EIBRS_PBRSB BIT(9) #define VULNWL(_vendor, _family, _model, _whitelist) \ { X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist } @@ -1065,7 +1066,7 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), VULNWL_INTEL(ATOM_GOLDMONT_D, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB), /* * Technically, swapgs isn't serializing on AMD (despite it previously @@ -1075,7 +1076,9 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { * good enough for our purposes. */ - VULNWL_INTEL(ATOM_TREMONT_D, NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_TREMONT, NO_EIBRS_PBRSB), + VULNWL_INTEL(ATOM_TREMONT_L, NO_EIBRS_PBRSB), + VULNWL_INTEL(ATOM_TREMONT_D, NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB), /* AMD Family 0xf - 0x12 */ VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), @@ -1236,6 +1239,11 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) !arch_cap_mmio_immune(ia32_cap)) setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA); + if (cpu_has(c, X86_FEATURE_IBRS_ENHANCED) && + !cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) && + !(ia32_cap & ARCH_CAP_PBRSB_NO)) + setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index ca4252f81bf81..946d9205c3b6d 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -92,6 +92,7 @@ ENTRY(vmx_vmexit) pop %_ASM_AX .Lvmexit_skip_rsb: #endif + ISSUE_UNBALANCED_RET_GUARD X86_FEATURE_RSB_VMEXIT_LITE ret ENDPROC(vmx_vmexit) diff --git a/drivers/acpi/apei/bert.c b/drivers/acpi/apei/bert.c index 76b7539a37a93..a06f35528c9a7 100644 --- a/drivers/acpi/apei/bert.c +++ b/drivers/acpi/apei/bert.c @@ -29,16 +29,26 @@ #undef pr_fmt #define pr_fmt(fmt) "BERT: " fmt + +#define ACPI_BERT_PRINT_MAX_RECORDS 5 #define ACPI_BERT_PRINT_MAX_LEN 1024 static int bert_disable; +/* + * Print "all" the error records in the BERT table, but avoid huge spam to + * the console if the BIOS included oversize records, or too many records. + * Skipping some records here does not lose anything because the full + * data is available to user tools in: + * /sys/firmware/acpi/tables/data/BERT + */ static void __init bert_print_all(struct acpi_bert_region *region, unsigned int region_len) { struct acpi_hest_generic_status *estatus = (struct acpi_hest_generic_status *)region; int remain = region_len; + int printed = 0, skipped = 0; u32 estatus_len; while (remain >= sizeof(struct acpi_bert_region)) { @@ -46,24 +56,26 @@ static void __init bert_print_all(struct acpi_bert_region *region, if (remain < estatus_len) { pr_err(FW_BUG "Truncated status block (length: %u).\n", estatus_len); - return; + break; } /* No more error records. */ if (!estatus->block_status) - return; + break; if (cper_estatus_check(estatus)) { pr_err(FW_BUG "Invalid error record.\n"); - return; + break; } - pr_info_once("Error records from previous boot:\n"); - if (region_len < ACPI_BERT_PRINT_MAX_LEN) + if (estatus_len < ACPI_BERT_PRINT_MAX_LEN && + printed < ACPI_BERT_PRINT_MAX_RECORDS) { + pr_info_once("Error records from previous boot:\n"); cper_estatus_print(KERN_INFO HW_ERR, estatus); - else - pr_info_once("Max print length exceeded, table data is available at:\n" - "/sys/firmware/acpi/tables/data/BERT"); + printed++; + } else { + skipped++; + } /* * Because the boot error source is "one-time polled" type, @@ -75,6 +87,9 @@ static void __init bert_print_all(struct acpi_bert_region *region, estatus = (void *)estatus + estatus_len; remain -= estatus_len; } + + if (skipped) + pr_info(HW_ERR "Skipped %d error records\n", skipped); } static int __init setup_bert_disable(char *str) diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index de4142723ff48..3b972ca536896 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -387,7 +387,6 @@ static const struct dmi_system_id video_detect_dmi_table[] = { .callback = video_detect_force_native, .ident = "Clevo NL5xRU", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"), DMI_MATCH(DMI_BOARD_NAME, "NL5xRU"), }, }, @@ -395,59 +394,75 @@ static const struct dmi_system_id video_detect_dmi_table[] = { .callback = video_detect_force_native, .ident = "Clevo NL5xRU", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "SchenkerTechnologiesGmbH"), - DMI_MATCH(DMI_BOARD_NAME, "NL5xRU"), + DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"), + DMI_MATCH(DMI_BOARD_NAME, "AURA1501"), }, }, { .callback = video_detect_force_native, .ident = "Clevo NL5xRU", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Notebook"), - DMI_MATCH(DMI_BOARD_NAME, "NL5xRU"), + DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"), + DMI_MATCH(DMI_BOARD_NAME, "EDUBOOK1502"), }, }, { .callback = video_detect_force_native, - .ident = "Clevo NL5xRU", + .ident = "Clevo NL5xNU", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"), - DMI_MATCH(DMI_BOARD_NAME, "AURA1501"), + DMI_MATCH(DMI_BOARD_NAME, "NL5xNU"), }, }, + /* + * The TongFang PF5PU1G, PF4NU1F, PF5NU1G, and PF5LUXG/TUXEDO BA15 Gen10, + * Pulse 14/15 Gen1, and Pulse 15 Gen2 have the same problem as the Clevo + * NL5xRU and NL5xNU/TUXEDO Aura 15 Gen1 and Gen2. See the description + * above. + */ { .callback = video_detect_force_native, - .ident = "Clevo NL5xRU", + .ident = "TongFang PF5PU1G", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"), - DMI_MATCH(DMI_BOARD_NAME, "EDUBOOK1502"), + DMI_MATCH(DMI_BOARD_NAME, "PF5PU1G"), }, }, { .callback = video_detect_force_native, - .ident = "Clevo NL5xNU", + .ident = "TongFang PF4NU1F", + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "PF4NU1F"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "TongFang PF4NU1F", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"), - DMI_MATCH(DMI_BOARD_NAME, "NL5xNU"), + DMI_MATCH(DMI_BOARD_NAME, "PULSE1401"), }, }, { .callback = video_detect_force_native, - .ident = "Clevo NL5xNU", + .ident = "TongFang PF5NU1G", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "SchenkerTechnologiesGmbH"), - DMI_MATCH(DMI_BOARD_NAME, "NL5xNU"), + DMI_MATCH(DMI_BOARD_NAME, "PF5NU1G"), }, }, { .callback = video_detect_force_native, - .ident = "Clevo NL5xNU", + .ident = "TongFang PF5NU1G", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Notebook"), - DMI_MATCH(DMI_BOARD_NAME, "NL5xNU"), + DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"), + DMI_MATCH(DMI_BOARD_NAME, "PULSE1501"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "TongFang PF5LUXG", + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "PF5LUXG"), }, }, - /* * Desktops which falsely report a backlight and which our heuristics * for this do not catch. diff --git a/drivers/macintosh/adb.c b/drivers/macintosh/adb.c index e49d1f287a175..c37d5fce86f79 100644 --- a/drivers/macintosh/adb.c +++ b/drivers/macintosh/adb.c @@ -647,7 +647,7 @@ do_adb_query(struct adb_request *req) switch(req->data[1]) { case ADB_QUERY_GETDEVINFO: - if (req->nbytes < 3) + if (req->nbytes < 3 || req->data[2] >= 16) break; mutex_lock(&adb_handler_mutex); req->reply[0] = adb_handler[req->data[2]].original_address; diff --git a/drivers/media/v4l2-core/v4l2-mem2mem.c b/drivers/media/v4l2-core/v4l2-mem2mem.c index 639dc8d45e603..d56837c04a81a 100644 --- a/drivers/media/v4l2-core/v4l2-mem2mem.c +++ b/drivers/media/v4l2-core/v4l2-mem2mem.c @@ -460,19 +460,14 @@ int v4l2_m2m_reqbufs(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, } EXPORT_SYMBOL_GPL(v4l2_m2m_reqbufs); -int v4l2_m2m_querybuf(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, - struct v4l2_buffer *buf) +static void v4l2_m2m_adjust_mem_offset(struct vb2_queue *vq, + struct v4l2_buffer *buf) { - struct vb2_queue *vq; - int ret = 0; - unsigned int i; - - vq = v4l2_m2m_get_vq(m2m_ctx, buf->type); - ret = vb2_querybuf(vq, buf); - /* Adjust MMAP memory offsets for the CAPTURE queue */ if (buf->memory == V4L2_MEMORY_MMAP && !V4L2_TYPE_IS_OUTPUT(vq->type)) { if (V4L2_TYPE_IS_MULTIPLANAR(vq->type)) { + unsigned int i; + for (i = 0; i < buf->length; ++i) buf->m.planes[i].m.mem_offset += DST_QUEUE_OFF_BASE; @@ -480,8 +475,23 @@ int v4l2_m2m_querybuf(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, buf->m.offset += DST_QUEUE_OFF_BASE; } } +} - return ret; +int v4l2_m2m_querybuf(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, + struct v4l2_buffer *buf) +{ + struct vb2_queue *vq; + int ret; + + vq = v4l2_m2m_get_vq(m2m_ctx, buf->type); + ret = vb2_querybuf(vq, buf); + if (ret) + return ret; + + /* Adjust MMAP memory offsets for the CAPTURE queue */ + v4l2_m2m_adjust_mem_offset(vq, buf); + + return 0; } EXPORT_SYMBOL_GPL(v4l2_m2m_querybuf); @@ -500,10 +510,16 @@ int v4l2_m2m_qbuf(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, return -EPERM; } ret = vb2_qbuf(vq, vdev->v4l2_dev->mdev, buf); - if (!ret && !(buf->flags & V4L2_BUF_FLAG_IN_REQUEST)) + if (ret) + return ret; + + /* Adjust MMAP memory offsets for the CAPTURE queue */ + v4l2_m2m_adjust_mem_offset(vq, buf); + + if (!(buf->flags & V4L2_BUF_FLAG_IN_REQUEST)) v4l2_m2m_try_schedule(m2m_ctx); - return ret; + return 0; } EXPORT_SYMBOL_GPL(v4l2_m2m_qbuf); @@ -511,9 +527,17 @@ int v4l2_m2m_dqbuf(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, struct v4l2_buffer *buf) { struct vb2_queue *vq; + int ret; vq = v4l2_m2m_get_vq(m2m_ctx, buf->type); - return vb2_dqbuf(vq, buf, file->f_flags & O_NONBLOCK); + ret = vb2_dqbuf(vq, buf, file->f_flags & O_NONBLOCK); + if (ret) + return ret; + + /* Adjust MMAP memory offsets for the CAPTURE queue */ + v4l2_m2m_adjust_mem_offset(vq, buf); + + return 0; } EXPORT_SYMBOL_GPL(v4l2_m2m_dqbuf); @@ -522,9 +546,17 @@ int v4l2_m2m_prepare_buf(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, { struct video_device *vdev = video_devdata(file); struct vb2_queue *vq; + int ret; vq = v4l2_m2m_get_vq(m2m_ctx, buf->type); - return vb2_prepare_buf(vq, vdev->v4l2_dev->mdev, buf); + ret = vb2_prepare_buf(vq, vdev->v4l2_dev->mdev, buf); + if (ret) + return ret; + + /* Adjust MMAP memory offsets for the CAPTURE queue */ + v4l2_m2m_adjust_mem_offset(vq, buf); + + return 0; } EXPORT_SYMBOL_GPL(v4l2_m2m_prepare_buf); diff --git a/drivers/thermal/of-thermal.c b/drivers/thermal/of-thermal.c index 68d0c181ec7bb..1f38da5da6e45 100644 --- a/drivers/thermal/of-thermal.c +++ b/drivers/thermal/of-thermal.c @@ -91,7 +91,7 @@ static int of_thermal_get_temp(struct thermal_zone_device *tz, { struct __thermal_zone *data = tz->devdata; - if (!data->ops->get_temp) + if (!data->ops || !data->ops->get_temp) return -EINVAL; return data->ops->get_temp(data->sensor_data, temp); @@ -188,6 +188,9 @@ static int of_thermal_set_emul_temp(struct thermal_zone_device *tz, { struct __thermal_zone *data = tz->devdata; + if (!data->ops || !data->ops->set_emul_temp) + return -EINVAL; + return data->ops->set_emul_temp(data->sensor_data, temp); } @@ -196,7 +199,7 @@ static int of_thermal_get_trend(struct thermal_zone_device *tz, int trip, { struct __thermal_zone *data = tz->devdata; - if (!data->ops->get_trend) + if (!data->ops || !data->ops->get_trend) return -EINVAL; return data->ops->get_trend(data->sensor_data, trip, trend); @@ -336,7 +339,7 @@ static int of_thermal_set_trip_temp(struct thermal_zone_device *tz, int trip, if (trip >= data->ntrips || trip < 0) return -EDOM; - if (data->ops->set_trip_temp) { + if (data->ops && data->ops->set_trip_temp) { int ret; ret = data->ops->set_trip_temp(data->sensor_data, trip, temp); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 34262d83dce11..f705d3752fe0d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5083,6 +5083,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, coerce_reg_to_size(dst_reg, 4); } + __update_reg_bounds(dst_reg); __reg_deduce_bounds(dst_reg); __reg_bound_offset(dst_reg); return 0; diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 4133c721af6ed..59f924e92c284 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -284,6 +284,7 @@ #define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* LLC Local MBM monitoring */ #define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* "" LFENCE in user entry SWAPGS path */ #define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */ +#define X86_FEATURE_RSB_VMEXIT_LITE (11*32+ 6) /* "" Fill RSB on VM-Exit when EIBRS is enabled */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 0bfad86ec960a..cb0631098f918 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3068,7 +3068,8 @@ struct bpf_sock { __u32 src_ip4; __u32 src_ip6[4]; __u32 src_port; /* host byte order */ - __u32 dst_port; /* network byte order */ + __be16 dst_port; /* network byte order */ + __u16 :16; /* zero padding */ __u32 dst_ip4; __u32 dst_ip6[4]; __u32 state; diff --git a/tools/testing/selftests/bpf/test_align.c b/tools/testing/selftests/bpf/test_align.c index 0262f7b374f9c..4b9a26caa2c2e 100644 --- a/tools/testing/selftests/bpf/test_align.c +++ b/tools/testing/selftests/bpf/test_align.c @@ -359,15 +359,15 @@ static struct bpf_align_test tests[] = { * is still (4n), fixed offset is not changed. * Also, we create a new reg->id. */ - {29, "R5_w=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc))"}, + {29, "R5_w=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc)"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (18) * which is 20. Then the variable offset is (4n), so * the total offset is 4-byte aligned and meets the * load's requirements. */ - {33, "R4=pkt(id=4,off=22,r=22,umax_value=2040,var_off=(0x0; 0x7fc))"}, - {33, "R5=pkt(id=4,off=18,r=22,umax_value=2040,var_off=(0x0; 0x7fc))"}, + {33, "R4=pkt(id=4,off=22,r=22,umax_value=2040,var_off=(0x0; 0x7fc)"}, + {33, "R5=pkt(id=4,off=18,r=22,umax_value=2040,var_off=(0x0; 0x7fc)"}, }, }, { @@ -410,15 +410,15 @@ static struct bpf_align_test tests[] = { /* Adding 14 makes R6 be (4n+2) */ {9, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, /* Packet pointer has (4n+2) offset */ - {11, "R5_w=pkt(id=1,off=0,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, - {13, "R4=pkt(id=1,off=4,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, + {11, "R5_w=pkt(id=1,off=0,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"}, + {13, "R4=pkt(id=1,off=4,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (0) * which is 2. Then the variable offset is (4n+2), so * the total offset is 4-byte aligned and meets the * load's requirements. */ - {15, "R5=pkt(id=1,off=0,r=4,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, + {15, "R5=pkt(id=1,off=0,r=4,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"}, /* Newly read value in R6 was shifted left by 2, so has * known alignment of 4. */ @@ -426,15 +426,15 @@ static struct bpf_align_test tests[] = { /* Added (4n) to packet pointer's (4n+2) var_off, giving * another (4n+2). */ - {19, "R5_w=pkt(id=2,off=0,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"}, - {21, "R4=pkt(id=2,off=4,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"}, + {19, "R5_w=pkt(id=2,off=0,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"}, + {21, "R4=pkt(id=2,off=4,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (0) * which is 2. Then the variable offset is (4n+2), so * the total offset is 4-byte aligned and meets the * load's requirements. */ - {23, "R5=pkt(id=2,off=0,r=4,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"}, + {23, "R5=pkt(id=2,off=0,r=4,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"}, }, }, { @@ -469,16 +469,16 @@ static struct bpf_align_test tests[] = { .matches = { {4, "R5_w=pkt_end(id=0,off=0,imm=0)"}, /* (ptr - ptr) << 2 == unknown, (4n) */ - {6, "R5_w=inv(id=0,smax_value=9223372036854775804,umax_value=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc))"}, + {6, "R5_w=inv(id=0,smax_value=9223372036854775804,umax_value=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc)"}, /* (4n) + 14 == (4n+2). We blow our bounds, because * the add could overflow. */ - {7, "R5_w=inv(id=0,var_off=(0x2; 0xfffffffffffffffc))"}, + {7, "R5_w=inv(id=0,smin_value=-9223372036854775806,smax_value=9223372036854775806,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"}, /* Checked s>=0 */ - {9, "R5=inv(id=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"}, + {9, "R5=inv(id=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, /* packet pointer + nonnegative (4n+2) */ - {11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"}, - {13, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"}, + {11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, + {13, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, /* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine. * We checked the bounds, but it might have been able * to overflow if the packet pointer started in the @@ -486,7 +486,7 @@ static struct bpf_align_test tests[] = { * So we did not get a 'range' on R6, and the access * attempt will fail. */ - {15, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"}, + {15, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, } }, { @@ -528,7 +528,7 @@ static struct bpf_align_test tests[] = { /* New unknown value in R7 is (4n) */ {11, "R7_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Subtracting it from R6 blows our unsigned bounds */ - {12, "R6=inv(id=0,smin_value=-1006,smax_value=1034,var_off=(0x2; 0xfffffffffffffffc))"}, + {12, "R6=inv(id=0,smin_value=-1006,smax_value=1034,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"}, /* Checked s>= 0 */ {14, "R6=inv(id=0,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc))"}, /* At the time the word size load is performed from R5, @@ -537,7 +537,8 @@ static struct bpf_align_test tests[] = { * the total offset is 4-byte aligned and meets the * load's requirements. */ - {20, "R5=pkt(id=1,off=0,r=4,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc))"}, + {20, "R5=pkt(id=1,off=0,r=4,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc)"}, + }, }, { @@ -579,18 +580,18 @@ static struct bpf_align_test tests[] = { /* Adding 14 makes R6 be (4n+2) */ {11, "R6_w=inv(id=0,umin_value=14,umax_value=74,var_off=(0x2; 0x7c))"}, /* Subtracting from packet pointer overflows ubounds */ - {13, "R5_w=pkt(id=1,off=0,r=8,umin_value=18446744073709551542,umax_value=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c))"}, + {13, "R5_w=pkt(id=1,off=0,r=8,umin_value=18446744073709551542,umax_value=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c)"}, /* New unknown value in R7 is (4n), >= 76 */ {15, "R7_w=inv(id=0,umin_value=76,umax_value=1096,var_off=(0x0; 0x7fc))"}, /* Adding it to packet pointer gives nice bounds again */ - {16, "R5_w=pkt(id=2,off=0,r=0,umin_value=2,umax_value=1082,var_off=(0x2; 0x7fc))"}, + {16, "R5_w=pkt(id=2,off=0,r=0,umin_value=2,umax_value=1082,var_off=(0x2; 0xfffffffc)"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (0) * which is 2. Then the variable offset is (4n+2), so * the total offset is 4-byte aligned and meets the * load's requirements. */ - {20, "R5=pkt(id=2,off=0,r=4,umin_value=2,umax_value=1082,var_off=(0x2; 0x7fc))"}, + {20, "R5=pkt(id=2,off=0,r=4,umin_value=2,umax_value=1082,var_off=(0x2; 0xfffffffc)"}, }, }, }; diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c index 92c02e4a1b626..313b345eddcc3 100644 --- a/tools/testing/selftests/bpf/verifier/bounds.c +++ b/tools/testing/selftests/bpf/verifier/bounds.c @@ -411,16 +411,14 @@ BPF_ALU32_IMM(BPF_RSH, BPF_REG_1, 31), /* r1 = 0xffff'fffe (NOT 0!) */ BPF_ALU32_IMM(BPF_SUB, BPF_REG_1, 2), - /* computes OOB pointer */ + /* error on computing OOB pointer */ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), - /* OOB access */ - BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), /* exit */ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, .fixup_map_hash_8b = { 3 }, - .errstr = "R0 invalid mem access", + .errstr = "math between map_value pointer and 4294967294 is not allowed", .result = REJECT, }, { diff --git a/tools/testing/selftests/bpf/verifier/sock.c b/tools/testing/selftests/bpf/verifier/sock.c index 9ed192e14f5fe..b2ce50bb935b8 100644 --- a/tools/testing/selftests/bpf/verifier/sock.c +++ b/tools/testing/selftests/bpf/verifier/sock.c @@ -121,7 +121,25 @@ .result = ACCEPT, }, { - "sk_fullsock(skb->sk): sk->dst_port [narrow load]", + "sk_fullsock(skb->sk): sk->dst_port [word load] (backward compatibility)", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = ACCEPT, +}, +{ + "sk_fullsock(skb->sk): sk->dst_port [half load]", .insns = { BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), @@ -139,7 +157,64 @@ .result = ACCEPT, }, { - "sk_fullsock(skb->sk): sk->dst_port [load 2nd byte]", + "sk_fullsock(skb->sk): sk->dst_port [half load] (invalid)", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = REJECT, + .errstr = "invalid sock access", +}, +{ + "sk_fullsock(skb->sk): sk->dst_port [byte load]", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_B, BPF_REG_2, BPF_REG_0, offsetof(struct bpf_sock, dst_port)), + BPF_LDX_MEM(BPF_B, BPF_REG_2, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 1), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = ACCEPT, +}, +{ + "sk_fullsock(skb->sk): sk->dst_port [byte load] (invalid)", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = REJECT, + .errstr = "invalid sock access", +}, +{ + "sk_fullsock(skb->sk): past sk->dst_port [half load] (invalid)", .insns = { BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), @@ -149,7 +224,7 @@ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), - BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 1), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_0, offsetofend(struct bpf_sock, dst_port)), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c index 6cd91970fbad3..3b2a426070c44 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c +++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c @@ -73,20 +73,19 @@ void ucall_uninit(struct kvm_vm *vm) void ucall(uint64_t cmd, int nargs, ...) { - struct ucall uc = { - .cmd = cmd, - }; + struct ucall uc = {}; va_list va; int i; + WRITE_ONCE(uc.cmd, cmd); nargs = nargs <= UCALL_MAX_ARGS ? nargs : UCALL_MAX_ARGS; va_start(va, nargs); for (i = 0; i < nargs; ++i) - uc.args[i] = va_arg(va, uint64_t); + WRITE_ONCE(uc.args[i], va_arg(va, uint64_t)); va_end(va); - *ucall_exit_mmio_addr = (vm_vaddr_t)&uc; + WRITE_ONCE(*ucall_exit_mmio_addr, (vm_vaddr_t)&uc); } uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 287444e52ccf8..4b445dddb7985 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3329,8 +3329,11 @@ static int kvm_ioctl_create_device(struct kvm *kvm, kvm_put_kvm(kvm); mutex_lock(&kvm->lock); list_del(&dev->vm_node); + if (ops->release) + ops->release(dev); mutex_unlock(&kvm->lock); - ops->destroy(dev); + if (ops->destroy) + ops->destroy(dev); return ret; }