September 2022 - Kernel - mailweb.openeuler.org

[PATCH openEuler-22.09 v2] bpf:programmable: Fix build error of 'stack exceeds 512 bytes'
by Zheng Zengkai 21 Sep '22

21 Sep '22

From: Hui Tang <tanghui20(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5RMFU CVE: NA -------------------------------- 1.Change arg type of 'bpf_get_cpumask_info' to avoid bpf program stack exceeds 512 bytes. 2.Fix back-edge error in sample 'sched_select_core' 3.Fix loop too complex in sample 'sached_select_core' Changes in v2: Move cpu initialization out of the for loop. Fixes: 1bf0417b95a9 ("sched: programmable: Add helper function for cpu topo...") Fixes: 2c1189e32bf9 ("samples:bpf: Add samples for cfs select core") Signed-off-by: Hui Tang <tanghui20(a)huawei.com> --- include/uapi/linux/bpf.h | 2 +- kernel/sched/bpf_topology.c | 9 ++- samples/bpf/sched_select_core_kern.c | 32 ++++++++--- tools/include/uapi/linux/bpf.h | 2 +- tools/lib/bpf/libbpf_sched.h | 86 +++++++++++++++++++++------- 5 files changed, 96 insertions(+), 35 deletions(-) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index db585d960d64..7e474c6fc4a7 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3903,7 +3903,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_get_cpumask_info(struct bpf_cpumask_info *cpus, int len) + * int bpf_get_cpumask_info(struct bpf_map *map, struct bpf_cpumask_info *cpus) * Description * Get system cpus returned in *cpus*. * Return diff --git a/kernel/sched/bpf_topology.c b/kernel/sched/bpf_topology.c index 9c2eda139e2a..843b6092a64f 100644 --- a/kernel/sched/bpf_topology.c +++ b/kernel/sched/bpf_topology.c @@ -70,10 +70,9 @@ const struct bpf_func_proto bpf_init_cpu_topology_proto = { .arg2_type = ARG_ANYTHING, }; -BPF_CALL_2(bpf_get_cpumask_info, struct bpf_cpumask_info *, cpus, - int, len) +BPF_CALL_2(bpf_get_cpumask_info, struct bpf_map *, map, struct bpf_cpumask_info *, cpus) { - if (len != sizeof(*cpus)) + if (!cpus) return -EINVAL; cpumask_copy(&cpus->cpu_possible_cpumask, cpu_possible_mask); @@ -92,6 +91,6 @@ const struct bpf_func_proto bpf_get_cpumask_info_proto = { .func = bpf_get_cpumask_info, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_UNINIT_MEM, - .arg2_type = ARG_CONST_SIZE, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, }; diff --git a/samples/bpf/sched_select_core_kern.c b/samples/bpf/sched_select_core_kern.c index 18617e89b395..30765ae65f85 100644 --- a/samples/bpf/sched_select_core_kern.c +++ b/samples/bpf/sched_select_core_kern.c @@ -62,7 +62,7 @@ struct tag_info { struct tag_info tag_tbl[] = { {TAG_NONE, ""}, - {TAG_ID(1), "0-3"}, + {TAG_ID(1), "0-1"}, {TAG_ID(2), "4-7"}, {TAG_MAX, ""}, }; @@ -94,13 +94,17 @@ static struct cpumask *select_better_cpus(struct task_struct *p, long min_util = INT_MIN; struct task_group *tg; long spare; - int cpu; + int cpu, i; if (!prefer_cpus_valid(prefer_cpus, (void *)getVal(p->cpus_ptr))) return (void *)getVal(p->cpus_ptr); tg = p->sched_task_group; - libbpf_for_each_cpu(cpu, prefer_cpus) { + for (i = 0, cpu = -1; i < BPF_SCHED_LOOP_MAX; i++) { + cpu = libbpf_cpumask_next(cpu, (void *)getVal(prefer_cpus)); + if (cpu >= libbpf_nr_cpus_ids()) + break; + if (idlest_cpu && libbpf_available_idle_cpu(cpu)) { *idlest_cpu = cpu; } else if (idlest_cpu) { @@ -159,9 +163,14 @@ int BPF_PROG(cfs_select_cpu_range, struct sched_migrate_ctx *h_ctx) SEC("sched/cfs_select_rq_exit") int BPF_PROG(cfs_select_cpu_range_exit, struct sched_migrate_ctx *h_ctx) { + struct task_struct *p = getVal(h_ctx->task); + long tag = getVal(p->tag); int *idlest_cpu; int key = 0; + if (tag <= TAG_NONE || tag >= TAG_MAX) + return SELECT_RQ_EXIT_CPU_VALID; + idlest_cpu = bpf_map_lookup_elem(&map_idlest_cpu, &key); if (!idlest_cpu) { libbpf_sched_set_task_cpus_ptr(h_ctx, (void *)getVal(h_ctx->cpus_allowed)); @@ -186,7 +195,7 @@ static int find_idlest_cpu(struct task_struct *p, int parent) int cpu; int i; - for (i = 0, cpu = -1; i < NR_CPUS; i++) { + for (i = 0, cpu = -1; i < BPF_SCHED_LOOP_MAX; i++) { cpu = libbpf_cpumask_next(cpu, (void *)getVal(p->cpus_ptr)); if (cpu >= libbpf_nr_cpus_ids()) break; @@ -203,17 +212,26 @@ static int find_idlest_cpu(struct task_struct *p, int parent) static int select_idle_cpu(struct task_struct *p, int parent, int prev_cpu) { - int cpu; + int cpu, i; if (libbpf_available_idle_cpu(prev_cpu)) return prev_cpu; if (libbpf_available_idle_cpu(parent)) - return prev_cpu; + return parent; + + cpu = libbpf_cpumask_next_wrap(prev_cpu - 1, + (void *)getVal(p->cpus_ptr), + prev_cpu, false); + for (i = 0; i < BPF_SCHED_LOOP_MAX; i++) { + if (cpu >= libbpf_nr_cpumask_bits()) + break; - libbpf_for_each_cpu_wrap(cpu, (void *)getVal(p->cpus_ptr), prev_cpu) { if (libbpf_available_idle_cpu(cpu)) return cpu; + + cpu = libbpf_cpumask_next_wrap(cpu, (void *)getVal(p->cpus_ptr), + prev_cpu, true); } return prev_cpu; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 57b927e99092..22f7880a0bb6 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4613,7 +4613,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_get_cpumask_info(struct bpf_cpumask_info *cpus, int len) + * int bpf_get_cpumask_info(struct bpf_map *map, struct bpf_cpumask_info *cpus) * Description * Get system cpus returned in *cpus*. * Return diff --git a/tools/lib/bpf/libbpf_sched.h b/tools/lib/bpf/libbpf_sched.h index 6cb30e8e81f8..187e854b99b3 100644 --- a/tools/lib/bpf/libbpf_sched.h +++ b/tools/lib/bpf/libbpf_sched.h @@ -21,6 +21,8 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> +/* set bigger value may lead verifier failed */ +#define BPF_SCHED_LOOP_MAX 1024 #define INVALID_PTR ((void *)(0UL)) #define getVal(P) \ ({ \ @@ -69,6 +71,13 @@ static __always_inline int libbpf_nr_cpumask_bits(void); #endif +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __type(key, u32); + __type(value, struct bpf_cpumask_info); + __uint(max_entries, 1); +} map_cpumask_info SEC(".maps"); + static __always_inline long libbpf_cpumask_copy(struct cpumask *dst, struct cpumask *src) { @@ -228,58 +237,93 @@ static __always_inline long libbpf_cpumask_cpulist_parse(char *src1, static __always_inline int libbpf_num_active_cpus(void) { - struct bpf_cpumask_info cpus; + struct bpf_cpumask_info *cpus; + int key = 0; + + cpus = bpf_map_lookup_elem(&map_cpumask_info, &key); + if (!cpus) + return -1; - bpf_get_cpumask_info(&cpus, sizeof(cpus)); - return getVal(cpus.nums_active_cpus); + bpf_get_cpumask_info(&map_cpumask_info, cpus); + return getVal(cpus->nums_active_cpus); } static __always_inline int libbpf_num_possible_cpus(void) { - struct bpf_cpumask_info cpus; + struct bpf_cpumask_info *cpus; + int key = 0; - bpf_get_cpumask_info(&cpus, sizeof(cpus)); - return getVal(cpus.nums_possible_cpus); + cpus = bpf_map_lookup_elem(&map_cpumask_info, &key); + if (!cpus) + return -1; + + bpf_get_cpumask_info(&map_cpumask_info, cpus); + return getVal(cpus->nums_possible_cpus); } static __always_inline void libbpf_possible_cpus_mask(struct cpumask *mask) { - struct bpf_cpumask_info cpus; + struct bpf_cpumask_info *cpus; + int key = 0; + + cpus = bpf_map_lookup_elem(&map_cpumask_info, &key); + if (!cpus) + return; - bpf_get_cpumask_info(&cpus, sizeof(cpus)); - libbpf_cpumask_copy(mask, &cpus.cpu_possible_cpumask); + bpf_get_cpumask_info(&map_cpumask_info, cpus); + libbpf_cpumask_copy(mask, &cpus->cpu_possible_cpumask); } static __always_inline void libbpf_active_cpus_mask(struct cpumask *mask) { - struct bpf_cpumask_info cpus; + struct bpf_cpumask_info *cpus; + int key = 0; - bpf_get_cpumask_info(&cpus, sizeof(cpus)); - libbpf_cpumask_copy(mask, &cpus.cpu_active_cpumask); + cpus = bpf_map_lookup_elem(&map_cpumask_info, &key); + if (!cpus) + return; + + bpf_get_cpumask_info(&map_cpumask_info, cpus); + libbpf_cpumask_copy(mask, &cpus->cpu_active_cpumask); } static __always_inline void libbpf_isolate_cpus_mask(struct cpumask *mask) { - struct bpf_cpumask_info cpus; + struct bpf_cpumask_info *cpus; + int key = 0; + + cpus = bpf_map_lookup_elem(&map_cpumask_info, &key); + if (!cpus) + return; - bpf_get_cpumask_info(&cpus, sizeof(cpus)); - libbpf_cpumask_copy(mask, &cpus.cpu_isolate_cpumask); + bpf_get_cpumask_info(&map_cpumask_info, cpus); + libbpf_cpumask_copy(mask, &cpus->cpu_isolate_cpumask); } static __always_inline int libbpf_nr_cpus_ids(void) { - struct bpf_cpumask_info cpus; + struct bpf_cpumask_info *cpus; + int key = 0; - bpf_get_cpumask_info(&cpus, sizeof(cpus)); - return getVal(cpus.nr_cpu_ids); + cpus = bpf_map_lookup_elem(&map_cpumask_info, &key); + if (!cpus) + return -1; + + bpf_get_cpumask_info(&map_cpumask_info, cpus); + return getVal(cpus->nr_cpu_ids); } static __always_inline int libbpf_nr_cpumask_bits(void) { - struct bpf_cpumask_info cpus; + struct bpf_cpumask_info *cpus; + int key = 0; + + cpus = bpf_map_lookup_elem(&map_cpumask_info, &key); + if (!cpus) + return -1; - bpf_get_cpumask_info(&cpus, sizeof(cpus)); - return getVal(cpus.bpf_nr_cpumask_bits); + bpf_get_cpumask_info(&map_cpumask_info, cpus); + return getVal(cpus->bpf_nr_cpumask_bits); } static __always_inline unsigned long libbpf_cfs_load_avg_of(int cpu) -- 2.20.1

1 0

[PATCH openEuler-5.10-LTS 01/18] x86/speculation: Add RSB VM Exit protections
by Zheng Zengkai 20 Sep '22

20 Sep '22

From: Daniel Sneddon <daniel.sneddon(a)linux.intel.com> stable inclusion from stable-v5.10.136 commit 509c2c9fe75ea7493eebbb6bb2f711f37530ae19 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I5N1SO CVE: CVE-2022-26373 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 2b1299322016731d56807aa49254a5ea3080b6b3 upstream. tl;dr: The Enhanced IBRS mitigation for Spectre v2 does not work as documented for RET instructions after VM exits. Mitigate it with a new one-entry RSB stuffing mechanism and a new LFENCE. == Background == Indirect Branch Restricted Speculation (IBRS) was designed to help mitigate Branch Target Injection and Speculative Store Bypass, i.e. Spectre, attacks. IBRS prevents software run in less privileged modes from affecting branch prediction in more privileged modes. IBRS requires the MSR to be written on every privilege level change. To overcome some of the performance issues of IBRS, Enhanced IBRS was introduced. eIBRS is an "always on" IBRS, in other words, just turn it on once instead of writing the MSR on every privilege level change. When eIBRS is enabled, more privileged modes should be protected from less privileged modes, including protecting VMMs from guests. == Problem == Here's a simplification of how guests are run on Linux' KVM: void run_kvm_guest(void) { // Prepare to run guest VMRESUME(); // Clean up after guest runs } The execution flow for that would look something like this to the processor: 1. Host-side: call run_kvm_guest() 2. Host-side: VMRESUME 3. Guest runs, does "CALL guest_function" 4. VM exit, host runs again 5. Host might make some "cleanup" function calls 6. Host-side: RET from run_kvm_guest() Now, when back on the host, there are a couple of possible scenarios of post-guest activity the host needs to do before executing host code: * on pre-eIBRS hardware (legacy IBRS, or nothing at all), the RSB is not touched and Linux has to do a 32-entry stuffing. * on eIBRS hardware, VM exit with IBRS enabled, or restoring the host IBRS=1 shortly after VM exit, has a documented side effect of flushing the RSB except in this PBRSB situation where the software needs to stuff the last RSB entry "by hand". IOW, with eIBRS supported, host RET instructions should no longer be influenced by guest behavior after the host retires a single CALL instruction. However, if the RET instructions are "unbalanced" with CALLs after a VM exit as is the RET in #6, it might speculatively use the address for the instruction after the CALL in #3 as an RSB prediction. This is a problem since the (untrusted) guest controls this address. Balanced CALL/RET instruction pairs such as in step #5 are not affected. == Solution == The PBRSB issue affects a wide variety of Intel processors which support eIBRS. But not all of them need mitigation. Today, X86_FEATURE_RSB_VMEXIT triggers an RSB filling sequence that mitigates PBRSB. Systems setting RSB_VMEXIT need no further mitigation - i.e., eIBRS systems which enable legacy IBRS explicitly. However, such systems (X86_FEATURE_IBRS_ENHANCED) do not set RSB_VMEXIT and most of them need a new mitigation. Therefore, introduce a new feature flag X86_FEATURE_RSB_VMEXIT_LITE which triggers a lighter-weight PBRSB mitigation versus RSB_VMEXIT. The lighter-weight mitigation performs a CALL instruction which is immediately followed by a speculative execution barrier (INT3). This steers speculative execution to the barrier -- just like a retpoline -- which ensures that speculation can never reach an unbalanced RET. Then, ensure this CALL is retired before continuing execution with an LFENCE. In other words, the window of exposure is opened at VM exit where RET behavior is troublesome. While the window is open, force RSB predictions sampling for RET targets to a dead end at the INT3. Close the window with the LFENCE. There is a subset of eIBRS systems which are not vulnerable to PBRSB. Add these systems to the cpu_vuln_whitelist[] as NO_EIBRS_PBRSB. Future systems that aren't vulnerable will set ARCH_CAP_PBRSB_NO. [ bp: Massage, incorporate review comments from Andy Cooper. ] Signed-off-by: Daniel Sneddon <daniel.sneddon(a)linux.intel.com> Co-developed-by: Pawan Gupta <pawan.kumar.gupta(a)linux.intel.com> Signed-off-by: Pawan Gupta <pawan.kumar.gupta(a)linux.intel.com> Signed-off-by: Borislav Petkov <bp(a)suse.de> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> conflict: arch/x86/include/asm/cpufeatures.h Signed-off-by: Chen Jiahao <chenjiahao16(a)huawei.com> Reviewed-by: Zhang Jianhua <chris.zjh(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- Documentation/admin-guide/hw-vuln/spectre.rst | 8 ++ arch/x86/include/asm/cpufeatures.h | 2 + arch/x86/include/asm/msr-index.h | 4 + arch/x86/include/asm/nospec-branch.h | 17 +++- arch/x86/kernel/cpu/bugs.c | 86 ++++++++++++++----- arch/x86/kernel/cpu/common.c | 12 ++- arch/x86/kvm/vmx/vmenter.S | 8 +- tools/arch/x86/include/asm/cpufeatures.h | 1 + tools/arch/x86/include/asm/msr-index.h | 4 + 9 files changed, 113 insertions(+), 29 deletions(-) diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst index 6bd97cd50d62..7e061ed449aa 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/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index bf531e883e82..b5852d41d9b9 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -297,6 +297,7 @@ #define X86_FEATURE_RETPOLINE_LFENCE (11*32+13) /* "" Use LFENCE for Spectre variant 2 */ #define X86_FEATURE_RETHUNK (11*32+14) /* "" Use REturn THUNK */ #define X86_FEATURE_UNRET (11*32+15) /* "" AMD BTB untrain return */ +#define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* "" 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 */ @@ -428,5 +429,6 @@ #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_RETBLEED X86_BUG(26) /* CPU is affected by RETBleed */ +#define X86_BUG_EIBRS_PBRSB X86_BUG(27) /* 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 ffc09df04d41..d9c352e76850 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -148,6 +148,10 @@ * are restricted to targets in * kernel. */ +#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 32e25cac72b2..3c615488b740 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -118,13 +118,28 @@ #endif .endm +.macro ISSUE_UNBALANCED_RET_GUARD + ANNOTATE_INTRA_FUNCTION_CALL + call .Lunbalanced_ret_guard_\@ + int3 +.Lunbalanced_ret_guard_\@: + add $(BITS_PER_LONG/8), %_ASM_SP + lfence +.endm + /* * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP * monstrosity above, manually. */ -.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req +.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req ftr2 +.ifb \ftr2 ALTERNATIVE "jmp .Lskip_rsb_\@", "", \ftr +.else + ALTERNATIVE_2 "jmp .Lskip_rsb_\@", "", \ftr, "jmp .Lunbalanced_\@", \ftr2 +.endif __FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP) +.Lunbalanced_\@: + ISSUE_UNBALANCED_RET_GUARD .Lskip_rsb_\@: .endm diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index bc6382f5ec27..d4cb9ff639aa 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1290,6 +1290,53 @@ static void __init spec_ctrl_disable_kernel_rrsba(void) } } +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: + 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; + + case SPECTRE_V2_EIBRS_RETPOLINE: + case SPECTRE_V2_RETPOLINE: + case SPECTRE_V2_LFENCE: + case SPECTRE_V2_IBRS: + setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT); + pr_info("Spectre v2 / SpectreRSB : Filling RSB 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(); @@ -1438,28 +1485,7 @@ 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"); - /* - * Similar to context switches, there are two types of RSB attacks - * after vmexit: - * - * 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, on the other hand, has RSB-poisoning protections, so it - * doesn't need RSB clearing after vmexit. - */ - if (boot_cpu_has(X86_FEATURE_RETPOLINE) || - boot_cpu_has(X86_FEATURE_KERNEL_IBRS)) - setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT); + spectre_v2_determine_rsb_fill_type_at_vmexit(mode); /* * Retpoline protects the kernel, but doesn't protect firmware. IBRS @@ -2202,6 +2228,19 @@ 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_RSB_VMEXIT)) + 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) @@ -2214,12 +2253,13 @@ 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 901352bd3b42..9fc91482e85e 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1024,6 +1024,7 @@ 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_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist) @@ -1064,7 +1065,7 @@ 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 @@ -1074,7 +1075,9 @@ 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), @@ -1252,6 +1255,11 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_RETBLEED); } + 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 857fa0fc49fa..982138bebb70 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -197,11 +197,13 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL) * entries and (in some cases) RSB underflow. * * eIBRS has its own protection against poisoned RSB, so it doesn't - * need the RSB filling sequence. But it does need to be enabled - * before the first unbalanced RET. + * need the RSB filling sequence. But it does need to be enabled, and a + * single call to retire, before the first unbalanced RET. */ - FILL_RETURN_BUFFER %_ASM_CX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT + FILL_RETURN_BUFFER %_ASM_CX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT,\ + X86_FEATURE_RSB_VMEXIT_LITE + pop %_ASM_ARG2 /* @flags */ pop %_ASM_ARG1 /* @vmx */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 54ba20492ad1..ec53f52a06a5 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -296,6 +296,7 @@ #define X86_FEATURE_RETPOLINE_LFENCE (11*32+13) /* "" Use LFENCE for Spectre variant 2 */ #define X86_FEATURE_RETHUNK (11*32+14) /* "" Use REturn THUNK */ #define X86_FEATURE_UNRET (11*32+15) /* "" AMD BTB untrain return */ +#define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* "" 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/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 53373ca3b487..b8954262d767 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -148,6 +148,10 @@ * are restricted to targets in * kernel. */ +#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) /* -- 2.20.1

1 17

[PATCH openEuler-1.0-LTS 0/2] fix the i40e crash problem
by tangbin 20 Sep '22

20 Sep '22

The two patches solve the crash of i40e Ivan Vecera (1): i40e: Fix kernel crash during module removal Yunjian Wang (1): i40e: Fix use-after-free in i40e_client_subtask() drivers/net/ethernet/intel/i40e/i40e_client.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) -- 2.18.4

1 2

[PATCH openEuler-5.10 000/139] Add patches for CVE-2022-29900,
by Zheng Zengkai 20 Sep '22

20 Sep '22

Patches for CVE-2022-29900, CVE-2022-23816 and CVE-2022-29901 Reference: https://lore.kernel.org/all/CAODzB9qH9WhxQ0eB+mNvmsn64bHXUVppuSTMDGJekYOPCw… https://www.amd.com/system/files/documents/technical-guidance-for-mitigatin… https://www.intel.com/content/www/us/en/developer/articles/technical/softwa… Alexandre Chartre (2): x86/bugs: Report AMD retbleed vulnerability x86/bugs: Add AMD retbleed= boot parameter Andrew Cooper (1): x86/cpu/amd: Enumerate BTC_NO Arnaldo Carvalho de Melo (5): tools arch: Update arch/x86/lib/mem{cpy,set}_64.S copies used in 'perf bench mem memcpy' tools arch x86: Sync the msr-index.h copy with the kernel sources tools headers cpufeatures: Sync with the kernel sources tools arch: Update arch/x86/lib/mem{cpy,set}_64.S copies used in 'perf bench mem memcpy' - again tools headers: Remove broken definition of __LITTLE_ENDIAN Ben Hutchings (3): x86: Add insn_decode_kernel() Makefile: Set retpoline cflags based on CONFIG_CC_IS_{CLANG,GCC} x86/xen: Fix initialisation in hypercall_page after rethunk Borislav Petkov (7): x86/insn: Rename insn_decode() to insn_decode_from_regs() x86/insn: Add a __ignore_sync_check__ marker x86/insn: Add an insn_decode() API x86/alternative: Use insn_decode() x86/alternative: Optimize single-byte NOPs at an arbitrary position kvm/emulate: Fix SETcc emulation function offsets with SLS tools/insn: Restore the relative include paths for cross building Greg Kroah-Hartman (1): x86, kvm: use proper ASM macros for kvm_vcpu_is_preempted Joe Lawrence (1): objtool: Make .altinstructions section entry size consistent Josh Poimboeuf (24): objtool: Refactor ORC section generation objtool: Add 'alt_group' struct objtool: Support stack layout changes in alternatives objtool: Support retpoline jump detection for vmlinux.o objtool: Assume only ELF functions do sibling calls objtool: Combine UNWIND_HINT_RET_OFFSET and UNWIND_HINT_FUNC x86/xen: Support objtool validation in xen-asm.S x86/xen: Support objtool vmlinux.o validation in xen-head.S objtool: Support asm jump tables objtool: Don't make .altinstructions writable objtool: Remove reloc symbol type checks in get_alt_entry() x86/bugs: Do IBPB fallback check only once x86/speculation: Fix RSB filling with CONFIG_RETPOLINE=n x86/speculation: Fix firmware entry SPEC_CTRL handling x86/speculation: Fix SPEC_CTRL write on SMT state change x86/speculation: Use cached host SPEC_CTRL value for guest entry/exit x86/speculation: Remove x86_spec_ctrl_mask objtool: Re-add UNWIND_HINT_{SAVE_RESTORE} KVM: VMX: Flatten __vmx_vcpu_run() KVM: VMX: Convert launched argument to flags KVM: VMX: Prevent guest RSB poisoning attacks with eIBRS KVM: VMX: Fix IBRS handling after vmexit x86/speculation: Fill RSB on vmexit for IBRS x86/ftrace: Add UNWIND_HINT_FUNC annotation for ftrace_stub Juergen Gross (4): x86/alternative: Merge include files x86/alternative: Support not-feature x86/alternative: Support ALTERNATIVE_TERNARY x86/alternative: Use ALTERNATIVE_TERNARY() in _static_cpu_has() Kim Phillips (3): x86/sev: Avoid using __x86_return_thunk x86/bugs: Enable STIBP for JMP2RET x86/bugs: Remove apostrophe typo Konrad Rzeszutek Wilk (1): x86/kexec: Disable RET on kexec Lin Yujun (2): x86: Fix objtool build warning Re-add padlen to the structure alt_instr Linus Torvalds (2): objtool: print out the symbol type when complaining about it kvm: fix objtool relocation warning Nathan Chancellor (1): x86/speculation: Use DECLARE_PER_CPU for x86_spec_ctrl_current Pawan Gupta (3): x86/speculation: Add spectre_v2=ibrs option to support Kernel IBRS x86/bugs: Add Cannon lake to RETBleed affected CPU list x86/speculation: Disable RRSBA behavior Peter Zijlstra (70): x86/alternatives: Optimize optimize_nops() x86/retpoline: Simplify retpolines objtool: Correctly handle retpoline thunk calls objtool: Handle per arch retpoline naming objtool: Rework the elf_rebuild_reloc_section() logic objtool: Add elf_create_reloc() helper objtool: Create reloc sections implicitly objtool: Extract elf_strtab_concat() objtool: Extract elf_symbol_add() objtool: Add elf_create_undef_symbol() objtool: Keep track of retpoline call sites objtool: Cache instruction relocs objtool: Skip magical retpoline .altinstr_replacement objtool/x86: Rewrite retpoline thunk calls objtool: Fix .symtab_shndx handling for elf_create_undef_symbol() objtool: Only rewrite unconditional retpoline thunk calls objtool/x86: Ignore __x86_indirect_alt_* symbols objtool: Teach get_alt_entry() about more relocation types objtool: Introduce CFI hash objtool: Handle __sanitize_cov*() tail calls objtool: Classify symbols objtool: Explicitly avoid self modifying code in .altinstr_replacement objtool,x86: Replace alternatives with .retpoline_sites x86/retpoline: Remove unused replacement symbols x86/asm: Fix register order x86/asm: Fixup odd GEN-for-each-reg.h usage x86/retpoline: Move the retpoline thunk declarations to nospec-branch.h x86/retpoline: Create a retpoline thunk array x86/alternative: Implement .retpoline_sites support bpf,x86: Simplify computing label offsets bpf,x86: Respect X86_FEATURE_RETPOLINE* x86/lib/atomic64_386_32: Rename things x86: Prepare asm files for straight-line-speculation x86: Prepare inline-asm for straight-line-speculation x86/alternative: Relax text_poke_bp() constraint objtool: Add straight-line-speculation validation x86: Add straight-line-speculation mitigation objtool: Default ignore INT3 for unreachable crypto: x86/poly1305 - Fixup SLS objtool: Fix SLS validation for kcov tail-call replacement x86/entry: Remove skip_r11rcx x86/kvm/vmx: Make noinstr clean x86/cpufeatures: Move RETPOLINE flags to word 11 x86/retpoline: Cleanup some #ifdefery x86/retpoline: Swizzle retpoline thunk x86/retpoline: Use -mfunction-return x86: Undo return-thunk damage x86,objtool: Create .return_sites x86,static_call: Use alternative RET encoding x86/ftrace: Use alternative RET encoding x86/bpf: Use alternative RET encoding x86/kvm: Fix SETcc emulation for return thunks x86/vsyscall_emu/64: Don't use RET in vsyscall emulation x86: Use return-thunk in asm code objtool: Treat .text.__x86.* as noinstr x86: Add magic AMD return-thunk x86/bugs: Keep a per-CPU IA32_SPEC_CTRL value x86/entry: Add kernel IBRS implementation x86/bugs: Optimize SPEC_CTRL MSR writes x86/bugs: Split spectre_v2_select_mitigation() and spectre_v2_user_select_mitigation() x86/bugs: Report Intel retbleed vulnerability intel_idle: Disable IBRS during long idle objtool: Update Retpoline validation x86/xen: Rename SYS* entry points x86/bugs: Add retbleed=ibpb objtool: Add entry UNRET validation x86/cpu/amd: Add Spectral Chicken x86/common: Stamp out the stepping madness x86/retbleed: Add fine grained Kconfig knobs um: Add missing apply_returns() Thadeu Lima de Souza Cascardo (5): x86/realmode: build with -D__DISABLE_EXPORTS objtool: skip non-text sections when adding return-thunk sites x86/bugs: Do not enable IBPB-on-entry when IBPB is not supported efi/x86: use naked RET on mixed mode call wrapper x86/kvm: fix FASTOP_SIZE when return thunks are enabled Thomas Gleixner (1): x86/static_call: Serialize __static_call_fixup() properly Uros Bizjak (2): KVM/VMX: Use TEST %REG,%REG instead of CMP $0,%REG in vmenter.S KVM/nVMX: Use __vmx_vcpu_run in nested_vmx_check_vmentry_hw Vasily Gorbik (1): objtool: Fix elf_create_undef_symbol() endianness .../admin-guide/kernel-parameters.txt | 25 + Makefile | 20 +- arch/um/kernel/um_arch.c | 8 + arch/x86/Kconfig | 91 +- arch/x86/Makefile | 8 +- arch/x86/boot/compressed/efi_thunk_64.S | 2 +- arch/x86/boot/compressed/head_64.S | 4 +- arch/x86/boot/compressed/mem_encrypt.S | 4 +- arch/x86/crypto/aegis128-aesni-asm.S | 48 +- arch/x86/crypto/aes_ctrby8_avx-x86_64.S | 2 +- arch/x86/crypto/aesni-intel_asm.S | 52 +- arch/x86/crypto/aesni-intel_avx-x86_64.S | 40 +- arch/x86/crypto/blake2s-core.S | 4 +- arch/x86/crypto/blowfish-x86_64-asm_64.S | 12 +- arch/x86/crypto/camellia-aesni-avx-asm_64.S | 18 +- arch/x86/crypto/camellia-aesni-avx2-asm_64.S | 18 +- arch/x86/crypto/camellia-x86_64-asm_64.S | 12 +- arch/x86/crypto/cast5-avx-x86_64-asm_64.S | 12 +- arch/x86/crypto/cast6-avx-x86_64-asm_64.S | 16 +- arch/x86/crypto/chacha-avx2-x86_64.S | 6 +- arch/x86/crypto/chacha-avx512vl-x86_64.S | 6 +- arch/x86/crypto/chacha-ssse3-x86_64.S | 8 +- arch/x86/crypto/crc32-pclmul_asm.S | 2 +- arch/x86/crypto/crc32c-pcl-intel-asm_64.S | 2 +- arch/x86/crypto/crct10dif-pcl-asm_64.S | 2 +- arch/x86/crypto/des3_ede-asm_64.S | 4 +- arch/x86/crypto/ghash-clmulni-intel_asm.S | 6 +- arch/x86/crypto/nh-avx2-x86_64.S | 2 +- arch/x86/crypto/nh-sse2-x86_64.S | 2 +- arch/x86/crypto/poly1305-x86_64-cryptogams.pl | 38 +- arch/x86/crypto/serpent-avx-x86_64-asm_64.S | 16 +- arch/x86/crypto/serpent-avx2-asm_64.S | 16 +- arch/x86/crypto/serpent-sse2-i586-asm_32.S | 6 +- arch/x86/crypto/serpent-sse2-x86_64-asm_64.S | 6 +- arch/x86/crypto/sha1_avx2_x86_64_asm.S | 2 +- arch/x86/crypto/sha1_ni_asm.S | 2 +- arch/x86/crypto/sha1_ssse3_asm.S | 2 +- arch/x86/crypto/sha256-avx-asm.S | 2 +- arch/x86/crypto/sha256-avx2-asm.S | 2 +- arch/x86/crypto/sha256-ssse3-asm.S | 2 +- arch/x86/crypto/sha256_ni_asm.S | 2 +- arch/x86/crypto/sha512-avx-asm.S | 2 +- arch/x86/crypto/sha512-avx2-asm.S | 2 +- arch/x86/crypto/sha512-ssse3-asm.S | 2 +- arch/x86/crypto/twofish-avx-x86_64-asm_64.S | 16 +- arch/x86/crypto/twofish-i586-asm_32.S | 4 +- arch/x86/crypto/twofish-x86_64-asm_64-3way.S | 6 +- arch/x86/crypto/twofish-x86_64-asm_64.S | 4 +- arch/x86/entry/Makefile | 2 +- arch/x86/entry/calling.h | 72 +- arch/x86/entry/entry.S | 22 + arch/x86/entry/entry_32.S | 6 +- arch/x86/entry/entry_64.S | 62 +- arch/x86/entry/entry_64_compat.S | 21 +- arch/x86/entry/thunk_32.S | 2 +- arch/x86/entry/thunk_64.S | 2 +- arch/x86/entry/vdso/Makefile | 1 + arch/x86/entry/vdso/vdso32/system_call.S | 4 +- arch/x86/entry/vsyscall/vsyscall_emu_64.S | 3 + arch/x86/include/asm/GEN-for-each-reg.h | 14 +- arch/x86/include/asm/alternative-asm.h | 114 -- arch/x86/include/asm/alternative.h | 133 +- arch/x86/include/asm/asm-prototypes.h | 17 - arch/x86/include/asm/cpufeature.h | 41 +- arch/x86/include/asm/cpufeatures.h | 12 +- arch/x86/include/asm/disabled-features.h | 21 +- arch/x86/include/asm/inat.h | 2 +- arch/x86/include/asm/insn-eval.h | 4 +- arch/x86/include/asm/insn.h | 28 +- arch/x86/include/asm/linkage.h | 22 + arch/x86/include/asm/msr-index.h | 13 + arch/x86/include/asm/nospec-branch.h | 148 ++- arch/x86/include/asm/paravirt.h | 2 +- arch/x86/include/asm/qspinlock_paravirt.h | 4 +- arch/x86/include/asm/smap.h | 5 +- arch/x86/include/asm/static_call.h | 19 +- arch/x86/include/asm/unwind_hints.h | 23 +- arch/x86/kernel/acpi/wakeup_32.S | 6 +- arch/x86/kernel/alternative.c | 356 +++++- arch/x86/kernel/cpu/amd.c | 46 +- arch/x86/kernel/cpu/bugs.c | 475 ++++++- arch/x86/kernel/cpu/common.c | 61 +- arch/x86/kernel/cpu/cpu.h | 2 + arch/x86/kernel/cpu/hygon.c | 6 + arch/x86/kernel/cpu/scattered.c | 1 + arch/x86/kernel/ftrace.c | 7 +- arch/x86/kernel/ftrace_32.S | 6 +- arch/x86/kernel/ftrace_64.S | 13 +- arch/x86/kernel/head_32.S | 2 +- arch/x86/kernel/head_64.S | 5 + arch/x86/kernel/irqflags.S | 4 +- arch/x86/kernel/kprobes/core.c | 2 +- arch/x86/kernel/kvm.c | 2 +- arch/x86/kernel/module.c | 15 +- arch/x86/kernel/paravirt.c | 2 +- arch/x86/kernel/process.c | 2 +- arch/x86/kernel/relocate_kernel_32.S | 15 +- arch/x86/kernel/relocate_kernel_64.S | 13 +- arch/x86/kernel/sev-es.c | 2 +- arch/x86/kernel/sev_verify_cbit.S | 2 +- arch/x86/kernel/static_call.c | 52 +- arch/x86/kernel/umip.c | 2 +- arch/x86/kernel/verify_cpu.S | 4 +- arch/x86/kernel/vmlinux.lds.S | 23 +- arch/x86/kvm/emulate.c | 39 +- arch/x86/kvm/svm/vmenter.S | 11 +- arch/x86/kvm/vmx/nested.c | 32 +- arch/x86/kvm/vmx/run_flags.h | 8 + arch/x86/kvm/vmx/vmenter.S | 170 +-- arch/x86/kvm/vmx/vmx.c | 78 +- arch/x86/kvm/vmx/vmx.h | 5 + arch/x86/kvm/x86.c | 4 +- arch/x86/lib/atomic64_386_32.S | 88 +- arch/x86/lib/atomic64_cx8_32.S | 18 +- arch/x86/lib/checksum_32.S | 8 +- arch/x86/lib/clear_page_64.S | 6 +- arch/x86/lib/cmpxchg16b_emu.S | 4 +- arch/x86/lib/cmpxchg8b_emu.S | 4 +- arch/x86/lib/copy_mc_64.S | 6 +- arch/x86/lib/copy_page_64.S | 10 +- arch/x86/lib/copy_user_64.S | 12 +- arch/x86/lib/csum-copy_64.S | 2 +- arch/x86/lib/error-inject.c | 3 +- arch/x86/lib/getuser.S | 22 +- arch/x86/lib/hweight.S | 6 +- arch/x86/lib/inat.c | 2 +- arch/x86/lib/insn-eval.c | 6 +- arch/x86/lib/insn.c | 222 +++- arch/x86/lib/iomap_copy_64.S | 2 +- arch/x86/lib/memcpy_64.S | 14 +- arch/x86/lib/memmove_64.S | 11 +- arch/x86/lib/memset_64.S | 8 +- arch/x86/lib/msr-reg.S | 4 +- arch/x86/lib/putuser.S | 6 +- arch/x86/lib/retpoline.S | 118 +- arch/x86/math-emu/div_Xsig.S | 2 +- arch/x86/math-emu/div_small.S | 2 +- arch/x86/math-emu/mul_Xsig.S | 6 +- arch/x86/math-emu/polynom_Xsig.S | 2 +- arch/x86/math-emu/reg_norm.S | 6 +- arch/x86/math-emu/reg_round.S | 2 +- arch/x86/math-emu/reg_u_add.S | 2 +- arch/x86/math-emu/reg_u_div.S | 2 +- arch/x86/math-emu/reg_u_mul.S | 2 +- arch/x86/math-emu/reg_u_sub.S | 2 +- arch/x86/math-emu/round_Xsig.S | 4 +- arch/x86/math-emu/shr_Xsig.S | 8 +- arch/x86/math-emu/wm_shrx.S | 16 +- arch/x86/mm/mem_encrypt_boot.S | 6 + arch/x86/net/bpf_jit_comp.c | 185 ++- arch/x86/net/bpf_jit_comp32.c | 22 +- arch/x86/platform/efi/efi_stub_32.S | 2 +- arch/x86/platform/efi/efi_stub_64.S | 2 +- arch/x86/platform/efi/efi_thunk_64.S | 5 +- arch/x86/platform/olpc/xo1-wakeup.S | 6 +- arch/x86/power/hibernate_asm_32.S | 4 +- arch/x86/power/hibernate_asm_64.S | 4 +- arch/x86/um/checksum_32.S | 4 +- arch/x86/um/setjmp_32.S | 2 +- arch/x86/um/setjmp_64.S | 2 +- arch/x86/xen/Makefile | 1 - arch/x86/xen/setup.c | 6 +- arch/x86/xen/xen-asm.S | 43 +- arch/x86/xen/xen-head.S | 6 +- arch/x86/xen/xen-ops.h | 6 +- drivers/base/cpu.c | 8 + drivers/idle/intel_idle.c | 43 +- include/linux/cpu.h | 2 + include/linux/kvm_host.h | 2 +- include/linux/objtool.h | 14 +- samples/ftrace/ftrace-direct-modify.c | 4 +- samples/ftrace/ftrace-direct-too.c | 2 +- samples/ftrace/ftrace-direct.c | 2 +- scripts/Makefile.build | 6 + scripts/link-vmlinux.sh | 6 + security/Kconfig | 11 - tools/arch/x86/include/asm/cpufeatures.h | 12 +- .../arch/x86/include/asm/disabled-features.h | 21 +- tools/arch/x86/include/asm/inat.h | 2 +- tools/arch/x86/include/asm/insn.h | 28 +- tools/arch/x86/include/asm/msr-index.h | 13 + tools/arch/x86/lib/inat.c | 2 +- tools/arch/x86/lib/insn.c | 222 +++- tools/arch/x86/lib/memcpy_64.S | 14 +- tools/arch/x86/lib/memset_64.S | 8 +- .../asm/{alternative-asm.h => alternative.h} | 0 tools/include/linux/kconfig.h | 67 + tools/include/linux/objtool.h | 14 +- .../Documentation/stack-validation.txt | 16 +- tools/objtool/Makefile | 4 - tools/objtool/arch.h | 13 +- tools/objtool/arch/x86/decode.c | 58 +- tools/objtool/builtin-check.c | 6 +- tools/objtool/builtin-orc.c | 6 +- tools/objtool/builtin.h | 3 +- tools/objtool/cfi.h | 2 + tools/objtool/check.c | 1131 +++++++++++++---- tools/objtool/check.h | 35 +- tools/objtool/elf.c | 230 ++-- tools/objtool/elf.h | 20 +- tools/objtool/objtool.c | 2 + tools/objtool/objtool.h | 5 +- tools/objtool/orc_gen.c | 324 ++--- tools/objtool/special.c | 22 +- tools/objtool/sync-check.sh | 17 +- tools/objtool/weak.c | 7 +- tools/perf/check-headers.sh | 15 +- 207 files changed, 4322 insertions(+), 1901 deletions(-) create mode 100644 arch/x86/entry/entry.S delete mode 100644 arch/x86/include/asm/alternative-asm.h create mode 100644 arch/x86/kvm/vmx/run_flags.h rename tools/include/asm/{alternative-asm.h => alternative.h} (100%) create mode 100644 tools/include/linux/kconfig.h -- 2.20.1

1 139

[PATCH openEuler-5.10] KVM: x86: do not report a vCPU as preempted outside instruction boundaries
by Zheng Zengkai 20 Sep '22

20 Sep '22

From: Paolo Bonzini <pbonzini(a)redhat.com> mainline inclusion from mainline-v5.19-rc2 commit 6cd88243c7e03845a450795e134b488fc2afb736 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I5PJ7H CVE: CVE-2022-39189 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ---------------------------------------- If a vCPU is outside guest mode and is scheduled out, it might be in the process of making a memory access. A problem occurs if another vCPU uses the PV TLB flush feature during the period when the vCPU is scheduled out, and a virtual address has already been translated but has not yet been accessed, because this is equivalent to using a stale TLB entry. To avoid this, only report a vCPU as preempted if sure that the guest is at an instruction boundary. A rescheduling request will be delivered to the host physical CPU as an external interrupt, so for simplicity consider any vmexit *not* instruction boundary except for external interrupts. It would in principle be okay to report the vCPU as preempted also if it is sleeping in kvm_vcpu_block(): a TLB flush IPI will incur the vmentry/vmexit overhead unnecessarily, and optimistic spinning is also unlikely to succeed. However, leave it for later because right now kvm_vcpu_check_block() is doing memory accesses. Even though the TLB flush issue only applies to virtual memory address, it's very much preferrable to be conservative. Reported-by: Jann Horn <jannh(a)google.com> Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> conflict: arch/x86/kvm/x86.c Signed-off-by: Guo Mengqi <guomengqi3(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Reviewed-by: Weilong Chen <chenweilong(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- arch/x86/include/asm/kvm_host.h | 3 +++ arch/x86/kvm/svm/svm.c | 2 ++ arch/x86/kvm/vmx/vmx.c | 1 + arch/x86/kvm/x86.c | 24 ++++++++++++++++++++++++ 4 files changed, 30 insertions(+) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 3d9da4629325..5103638cc911 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -553,6 +553,7 @@ struct kvm_vcpu_arch { u64 ia32_misc_enable_msr; u64 smbase; u64 smi_count; + bool at_instruction_boundary; bool tpr_access_reporting; bool xsaves_enabled; u64 ia32_xss; @@ -1077,6 +1078,8 @@ struct kvm_vcpu_stat { u64 utime; u64 stime; u64 gtime; + u64 preemption_reported; + u64 preemption_other; u64 preemption_timer_exits; }; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 2124fe54abfb..5231f40e8312 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3992,6 +3992,8 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu, static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu) { + if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_INTR) + vcpu->arch.at_instruction_boundary = true; } static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 6bb07e495eca..fad74e5faade 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6605,6 +6605,7 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) return; handle_interrupt_nmi_irqoff(vcpu, gate_offset(desc)); + vcpu->arch.at_instruction_boundary = true; } static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 284bf9b0c12c..c275efd0bb70 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -233,6 +233,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { VCPU_STAT("l1d_flush", l1d_flush), VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns), VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns), + VCPU_STAT("preemption_reported", preemption_reported), + VCPU_STAT("preemption_other", preemption_other), VM_STAT("mmu_shadow_zapped", mmu_shadow_zapped), VM_STAT("mmu_pte_write", mmu_pte_write), VM_STAT("mmu_pde_zapped", mmu_pde_zapped), @@ -287,6 +289,8 @@ struct dfx_kvm_stats_debugfs_item dfx_debugfs_entries[] = { DFX_STAT("stime", stime), DFX_STAT("gtime", gtime), DFX_STAT("preemption_timer_exits", preemption_timer_exits), + DFX_STAT("preemption_reported", preemption_reported), + DFX_STAT("preemption_other", preemption_other), { NULL } }; @@ -4082,6 +4086,19 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) struct kvm_host_map map; struct kvm_steal_time *st; + /* + * The vCPU can be marked preempted if and only if the VM-Exit was on + * an instruction boundary and will not trigger guest emulation of any + * kind (see vcpu_run). Vendor specific code controls (conservatively) + * when this is true, for example allowing the vCPU to be marked + * preempted if and only if the VM-Exit was due to a host interrupt. + */ + if (!vcpu->arch.at_instruction_boundary) { + vcpu->stat.preemption_other++; + return; + } + + vcpu->stat.preemption_reported++; if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; @@ -9329,6 +9346,13 @@ static int vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.l1tf_flush_l1d = true; for (;;) { + /* + * If another guest vCPU requests a PV TLB flush in the middle + * of instruction emulation, the rest of the emulation could + * use a stale page translation. Assume that any code after + * this point can start executing an instruction. + */ + vcpu->arch.at_instruction_boundary = false; if (kvm_vcpu_running(vcpu)) { r = vcpu_enter_guest(vcpu); } else { -- 2.20.1

1 0

[PATCH openEuler-5.10 01/14] block: fix the problem of io_ticks becoming smaller
by Zheng Zengkai 20 Sep '22

20 Sep '22

From: Chunguang Xu <brookxu(a)tencent.com> mainline inclusion from mainline-v5.14-rc1 commit d80c228d44640f0b47b57a2ca4afa26ef87e16b0 category: bugfix bugzilla: 187475, https://gitee.com/openeuler/kernel/issues/I5ME0J CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- On the IO submission path, blk_account_io_start() may interrupt the system interruption. When the interruption returns, the value of part->stamp may have been updated by other cores, so the time value collected before the interruption may be less than part-> stamp. So when this happens, we should do nothing to make io_ticks more accurate? For kernels less than 5.0, this may cause io_ticks to become smaller, which in turn may cause abnormal ioutil values. Signed-off-by: Chunguang Xu <brookxu(a)tencent.com> Reviewed-by: Christoph Hellwig <hch(a)lst.de> Link: https://lore.kernel.org/r/1625521646-1069-1-git-send-email-brookxu.cn@gmail… Signed-off-by: Jens Axboe <axboe(a)kernel.dk> conflict: block/blk-core.c Signed-off-by: Li Nan <linan122(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- block/blk-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/blk-core.c b/block/blk-core.c index 109fb2750453..0b496dabc5ac 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1258,7 +1258,7 @@ void update_io_ticks(struct hd_struct *part, unsigned long now, bool end) unsigned long stamp; again: stamp = READ_ONCE(part->stamp); - if (unlikely(stamp != now)) { + if (unlikely(time_after(now, stamp))) { if (likely(cmpxchg(&part->stamp, stamp, now) == stamp)) __part_stat_add(part, io_ticks, end ? now - stamp : 1); } -- 2.20.1

1 13

[PATCH RFC v2 openEuler-1.0-LTS 0/6] md: improve performance
by Yu Kuai 20 Sep '22

20 Sep '22

From: Yu Kuai <yukuai3(a)huawei.com> Changes in v2: - fix the problem that if 'nr_pending' is decreased to 0 in wait_barrier_nolock() in patch 1, 'conf->barrier' is not waked, and raise_barrier() can hang while waiting 'nr_pending' to be 0. - only modify hot path in patch 2. - use node 1 as default in patch 6. In some architecture, for example KUNPENG 920, memory access latency is very bad across nodes compare to local node. For consequence, io performance is rather bad while users issue io from multiple nodes if lock contention exist in the driver. This patchset tries to avoid memory access across nodes in driver. Test environment: aarch64 Huawei KUNPENG 920 Raid10 initialize: mdadm --create /dev/md0 --level 10 --bitmap none --raid-devices 4 /dev/nvme0n1 /dev/nvme1n1 /dev/nvme2n1 /dev/nvme3n1 Test cmd: (task set -c 0-15) fio -name=0 -ioengine=libaio -direct=1 -group_reporting=1 -randseed=2022 -rwmixread=70 -refill_buffers -filename=/dev/md0 -numjobs=16 -runtime=60s -bs=4k -iodepth=256 -rw=randread Test result: before this patchset: 3.2 GiB/s bind node before this patchset: 6.9 Gib/s after this patchset: 7.9 Gib/s bind node after this patchset: 8.0 Gib/s Wang ShaoBo (1): arm64/topology: Getting preferred sibling's cpumask supported by platform Yu Kuai (5): md/raid10: convert resync_lock to use seqlock md/raid10: prevent unnecessary calls to wake_up() in fast path block: add new fields in request_queue block: support to dispatch bio asynchronously md: enable dispatching bio asynchronously by default arch/arm64/Kconfig | 8 ++ arch/arm64/include/asm/smp_plat.h | 14 ++ arch/arm64/kernel/smp.c | 9 ++ arch/arm64/kernel/topology.c | 51 +++++++ block/blk-core.c | 212 +++++++++++++++++++++++++++++- block/blk-sysfs.c | 40 ++++++ drivers/md/md.c | 5 + drivers/md/raid10.c | 98 +++++++++----- drivers/md/raid10.h | 2 +- include/linux/arch_topology.h | 7 + include/linux/blkdev.h | 6 + 11 files changed, 420 insertions(+), 32 deletions(-) -- 2.31.1

2 11

[PATCH 1/2] jfs: fix GPF in diFree
by Laibin Qiu 20 Sep '22

20 Sep '22

From: Pavel Skripkin <paskripkin(a)gmail.com> mainline inclusion from mainline-6.0-rc4 commit 9d574f985fe33efd6911f4d752de6f485a1ea732 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I5RX0N?from=project-issue CVE: CVE-2022-3202 -------------------------------- Avoid passing inode with JFS_SBI(inode->i_sb)->ipimap == NULL to diFree()[1]. GFP will appear: struct inode *ipimap = JFS_SBI(ip->i_sb)->ipimap; struct inomap *imap = JFS_IP(ipimap)->i_imap; JFS_IP() will return invalid pointer when ipimap == NULL Call Trace: diFree+0x13d/0x2dc0 fs/jfs/jfs_imap.c:853 [1] jfs_evict_inode+0x2c9/0x370 fs/jfs/inode.c:154 evict+0x2ed/0x750 fs/inode.c:578 iput_final fs/inode.c:1654 [inline] iput.part.0+0x3fe/0x820 fs/inode.c:1680 iput+0x58/0x70 fs/inode.c:1670 Reported-and-tested-by: syzbot+0a89a7b56db04c21a656(a)syzkaller.appspotmail.com Signed-off-by: Pavel Skripkin <paskripkin(a)gmail.com> Signed-off-by: Dave Kleikamp <dave.kleikamp(a)oracle.com> Signed-off-by: ZhaoLong Wang <wangzhaolong1(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Laibin Qiu <qiulaibin(a)huawei.com> --- fs/jfs/inode.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index 054cc761b426..87b41edc800d 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -161,7 +161,8 @@ void jfs_evict_inode(struct inode *inode) if (test_cflag(COMMIT_Freewmap, inode)) jfs_free_zero_link(inode); - diFree(inode); + if (JFS_SBI(inode->i_sb)->ipimap) + diFree(inode); /* * Free the inode from the quota allocation. -- 2.25.1

1 1

[PATCH openEuler-22.09] arm64/__mc_ex_table: fix __mc_ex_table do_sort() issue
by Zheng Zengkai 20 Sep '22

20 Sep '22

From: Tong Tiangen <tongtiangen(a)huawei.com> hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I5GB28 CVE: NA ------------------------------- If ARCH_HAS_MC_EXTABLE is not set then the _mc_ex_table is empty. There is a logic error in do_sort(). _mc_ex_table is different from _ex_table. _ex_table is always not empty, while _mc_ex_table may be empty. If _mc_ex_table is empty, there is a issue with setting the initial value of mc_extable_index to 0. Fixes: 7c3d926bb083 ("[Huawei] arm64: extable: add new extable type "__mc_ex_table"") Signed-off-by: Tong Tiangen <tongtiangen(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- scripts/sorttable.h | 20 +++++++++----------- 1 file changed, 9 insertions(+), 11 deletions(-) diff --git a/scripts/sorttable.h b/scripts/sorttable.h index 874cbd7046b0..d67242f8c75f 100644 --- a/scripts/sorttable.h +++ b/scripts/sorttable.h @@ -227,7 +227,6 @@ static int do_sort(Elf_Ehdr *ehdr, Elf_Rel *mc_relocs = NULL; int mc_relocs_size = 0; char *mc_extab_image = NULL; - int mc_extab_index = 0; shstrndx = r2(&ehdr->e_shstrndx); if (shstrndx == SHN_XINDEX) @@ -245,11 +244,6 @@ static int do_sort(Elf_Ehdr *ehdr, extab_index = i; } - if (!strcmp(secstrings + idx, "__mc_ex_table")) { - mc_extab_sec = s; - mc_extab_index = i; - } - if (!strcmp(secstrings + idx, ".symtab")) symtab_sec = s; if (!strcmp(secstrings + idx, ".strtab")) @@ -262,11 +256,15 @@ static int do_sort(Elf_Ehdr *ehdr, relocs_size = _r(&s->sh_size); } - if ((r(&s->sh_type) == SHT_REL || - r(&s->sh_type) == SHT_RELA) && - r(&s->sh_info) == mc_extab_index) { - mc_relocs = (void *)ehdr + _r(&s->sh_offset); - mc_relocs_size = _r(&s->sh_size); + if (!strcmp(secstrings + idx, "__mc_ex_table")) { + mc_extab_sec = s; + + if ((r(&s->sh_type) == SHT_REL || + r(&s->sh_type) == SHT_RELA) && + r(&s->sh_info) == i) { + mc_relocs = (void *)ehdr + _r(&s->sh_offset); + mc_relocs_size = _r(&s->sh_size); + } } if (r(&s->sh_type) == SHT_SYMTAB_SHNDX) -- 2.20.1

1 0

[PATCH openEuler-1.0-LTS] xfs: preserve default grace interval during quotacheck
by tangbin 19 Sep '22

19 Sep '22

From: "Darrick J. Wong" <darrick.wong(a)oracle.com> stable inclusion from stable-v5.10.143 commit f1101295c145e9710b1b37e9b0a13ef9af9af0c9 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5RTF5 CVE: NA -------------------------------- commit 5885539f0af371024d07afd14974bfdc3fff84c5 upstream. When quotacheck runs, it zeroes all the timer fields in every dquot. Unfortunately, it also does this to the root dquot, which erases any preconfigured grace intervals and warning limits that the administrator may have set. Worse yet, the incore copies of those variables remain set. This cache coherence problem manifests itself as the grace interval mysteriously being reset back to the defaults at the /next/ mount. Fix it by not resetting the root disk dquot's timer and warning fields. Signed-off-by: Darrick J. Wong <darrick.wong(a)oracle.com> Reviewed-by: Dave Chinner <dchinner(a)redhat.com> Reviewed-by: Christoph Hellwig <hch(a)lst.de> Signed-off-by: tangbin <tangbin(a)cmss.chinamobile.com> --- fs/xfs/xfs_qm.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 65b77ea9d5a9..0fb2b37b56f2 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -870,12 +870,20 @@ xfs_qm_reset_dqcounts( ddq->d_bcount = 0; ddq->d_icount = 0; ddq->d_rtbcount = 0; - ddq->d_btimer = 0; - ddq->d_itimer = 0; - ddq->d_rtbtimer = 0; - ddq->d_bwarns = 0; - ddq->d_iwarns = 0; - ddq->d_rtbwarns = 0; + + /* + * dquot id 0 stores the default grace period and the maximum + * warning limit that were set by the administrator, so we + * should not reset them. + */ + if (ddq->d_id != 0) { + ddq->d_btimer = 0; + ddq->d_itimer = 0; + ddq->d_rtbtimer = 0; + ddq->d_bwarns = 0; + ddq->d_iwarns = 0; + ddq->d_rtbwarns = 0; + } if (xfs_sb_version_hascrc(&mp->m_sb)) { xfs_update_cksum((char *)&dqb[j], -- 2.18.4

1 0

[PATCH openEuler-22.09 1/2] bpf:programmable: Fix build error of 'stack exceeds 512 bytes'
by Zheng Zengkai 19 Sep '22

19 Sep '22

From: Hui Tang <tanghui20(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5RMFU CVE: NA -------------------------------- 1.Change arg type of 'bpf_get_cpumask_info' to avoid bpf program stack exceeds 512 bytes. 2.Fix back-edge error in sample 'sched_select_core' 3.Fix loop too complex in sample 'sached_select_core' Fixes: 1bf0417b95a9 ("sched: programmable: Add helper function for cpu topo...") Fixes: 2c1189e32bf9 ("samples:bpf: Add samples for cfs select core") Signed-off-by: Hui Tang <tanghui20(a)huawei.com> --- include/uapi/linux/bpf.h | 2 +- kernel/sched/bpf_topology.c | 9 ++- samples/bpf/sched_select_core_kern.c | 33 ++++++++--- tools/include/uapi/linux/bpf.h | 2 +- tools/lib/bpf/libbpf_sched.h | 86 +++++++++++++++++++++------- 5 files changed, 97 insertions(+), 35 deletions(-) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index db585d960d64..7e474c6fc4a7 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3903,7 +3903,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_get_cpumask_info(struct bpf_cpumask_info *cpus, int len) + * int bpf_get_cpumask_info(struct bpf_map *map, struct bpf_cpumask_info *cpus) * Description * Get system cpus returned in *cpus*. * Return diff --git a/kernel/sched/bpf_topology.c b/kernel/sched/bpf_topology.c index 9c2eda139e2a..843b6092a64f 100644 --- a/kernel/sched/bpf_topology.c +++ b/kernel/sched/bpf_topology.c @@ -70,10 +70,9 @@ const struct bpf_func_proto bpf_init_cpu_topology_proto = { .arg2_type = ARG_ANYTHING, }; -BPF_CALL_2(bpf_get_cpumask_info, struct bpf_cpumask_info *, cpus, - int, len) +BPF_CALL_2(bpf_get_cpumask_info, struct bpf_map *, map, struct bpf_cpumask_info *, cpus) { - if (len != sizeof(*cpus)) + if (!cpus) return -EINVAL; cpumask_copy(&cpus->cpu_possible_cpumask, cpu_possible_mask); @@ -92,6 +91,6 @@ const struct bpf_func_proto bpf_get_cpumask_info_proto = { .func = bpf_get_cpumask_info, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_UNINIT_MEM, - .arg2_type = ARG_CONST_SIZE, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, }; diff --git a/samples/bpf/sched_select_core_kern.c b/samples/bpf/sched_select_core_kern.c index 18617e89b395..62ffb29f2725 100644 --- a/samples/bpf/sched_select_core_kern.c +++ b/samples/bpf/sched_select_core_kern.c @@ -62,7 +62,7 @@ struct tag_info { struct tag_info tag_tbl[] = { {TAG_NONE, ""}, - {TAG_ID(1), "0-3"}, + {TAG_ID(1), "0-1"}, {TAG_ID(2), "4-7"}, {TAG_MAX, ""}, }; @@ -94,13 +94,17 @@ static struct cpumask *select_better_cpus(struct task_struct *p, long min_util = INT_MIN; struct task_group *tg; long spare; - int cpu; + int cpu, i; if (!prefer_cpus_valid(prefer_cpus, (void *)getVal(p->cpus_ptr))) return (void *)getVal(p->cpus_ptr); tg = p->sched_task_group; - libbpf_for_each_cpu(cpu, prefer_cpus) { + for (i = 0, cpu = -1; i < BPF_SCHED_LOOP_MAX; i++) { + cpu = libbpf_cpumask_next(cpu, (void *)getVal(prefer_cpus)); + if (cpu >= libbpf_nr_cpus_ids()) + break; + if (idlest_cpu && libbpf_available_idle_cpu(cpu)) { *idlest_cpu = cpu; } else if (idlest_cpu) { @@ -159,9 +163,14 @@ int BPF_PROG(cfs_select_cpu_range, struct sched_migrate_ctx *h_ctx) SEC("sched/cfs_select_rq_exit") int BPF_PROG(cfs_select_cpu_range_exit, struct sched_migrate_ctx *h_ctx) { + struct task_struct *p = getVal(h_ctx->task); + long tag = getVal(p->tag); int *idlest_cpu; int key = 0; + if (tag <= TAG_NONE || tag >= TAG_MAX) + return SELECT_RQ_EXIT_CPU_VALID; + idlest_cpu = bpf_map_lookup_elem(&map_idlest_cpu, &key); if (!idlest_cpu) { libbpf_sched_set_task_cpus_ptr(h_ctx, (void *)getVal(h_ctx->cpus_allowed)); @@ -186,7 +195,7 @@ static int find_idlest_cpu(struct task_struct *p, int parent) int cpu; int i; - for (i = 0, cpu = -1; i < NR_CPUS; i++) { + for (i = 0, cpu = -1; i < BPF_SCHED_LOOP_MAX; i++) { cpu = libbpf_cpumask_next(cpu, (void *)getVal(p->cpus_ptr)); if (cpu >= libbpf_nr_cpus_ids()) break; @@ -203,17 +212,27 @@ static int find_idlest_cpu(struct task_struct *p, int parent) static int select_idle_cpu(struct task_struct *p, int parent, int prev_cpu) { - int cpu; + int cpu, i; if (libbpf_available_idle_cpu(prev_cpu)) return prev_cpu; if (libbpf_available_idle_cpu(parent)) - return prev_cpu; + return parent; + + for (i = 0, cpu = libbpf_cpumask_next_wrap(prev_cpu - 1, + (void *)getVal(p->cpus_ptr), + prev_cpu, false); + i < BPF_SCHED_LOOP_MAX; i++) { + + if (cpu >= libbpf_nr_cpumask_bits()) + break; - libbpf_for_each_cpu_wrap(cpu, (void *)getVal(p->cpus_ptr), prev_cpu) { if (libbpf_available_idle_cpu(cpu)) return cpu; + + cpu = libbpf_cpumask_next_wrap(cpu, (void *)getVal(p->cpus_ptr), + prev_cpu, true); } return prev_cpu; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 57b927e99092..22f7880a0bb6 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4613,7 +4613,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_get_cpumask_info(struct bpf_cpumask_info *cpus, int len) + * int bpf_get_cpumask_info(struct bpf_map *map, struct bpf_cpumask_info *cpus) * Description * Get system cpus returned in *cpus*. * Return diff --git a/tools/lib/bpf/libbpf_sched.h b/tools/lib/bpf/libbpf_sched.h index 6cb30e8e81f8..187e854b99b3 100644 --- a/tools/lib/bpf/libbpf_sched.h +++ b/tools/lib/bpf/libbpf_sched.h @@ -21,6 +21,8 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> +/* set bigger value may lead verifier failed */ +#define BPF_SCHED_LOOP_MAX 1024 #define INVALID_PTR ((void *)(0UL)) #define getVal(P) \ ({ \ @@ -69,6 +71,13 @@ static __always_inline int libbpf_nr_cpumask_bits(void); #endif +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __type(key, u32); + __type(value, struct bpf_cpumask_info); + __uint(max_entries, 1); +} map_cpumask_info SEC(".maps"); + static __always_inline long libbpf_cpumask_copy(struct cpumask *dst, struct cpumask *src) { @@ -228,58 +237,93 @@ static __always_inline long libbpf_cpumask_cpulist_parse(char *src1, static __always_inline int libbpf_num_active_cpus(void) { - struct bpf_cpumask_info cpus; + struct bpf_cpumask_info *cpus; + int key = 0; + + cpus = bpf_map_lookup_elem(&map_cpumask_info, &key); + if (!cpus) + return -1; - bpf_get_cpumask_info(&cpus, sizeof(cpus)); - return getVal(cpus.nums_active_cpus); + bpf_get_cpumask_info(&map_cpumask_info, cpus); + return getVal(cpus->nums_active_cpus); } static __always_inline int libbpf_num_possible_cpus(void) { - struct bpf_cpumask_info cpus; + struct bpf_cpumask_info *cpus; + int key = 0; - bpf_get_cpumask_info(&cpus, sizeof(cpus)); - return getVal(cpus.nums_possible_cpus); + cpus = bpf_map_lookup_elem(&map_cpumask_info, &key); + if (!cpus) + return -1; + + bpf_get_cpumask_info(&map_cpumask_info, cpus); + return getVal(cpus->nums_possible_cpus); } static __always_inline void libbpf_possible_cpus_mask(struct cpumask *mask) { - struct bpf_cpumask_info cpus; + struct bpf_cpumask_info *cpus; + int key = 0; + + cpus = bpf_map_lookup_elem(&map_cpumask_info, &key); + if (!cpus) + return; - bpf_get_cpumask_info(&cpus, sizeof(cpus)); - libbpf_cpumask_copy(mask, &cpus.cpu_possible_cpumask); + bpf_get_cpumask_info(&map_cpumask_info, cpus); + libbpf_cpumask_copy(mask, &cpus->cpu_possible_cpumask); } static __always_inline void libbpf_active_cpus_mask(struct cpumask *mask) { - struct bpf_cpumask_info cpus; + struct bpf_cpumask_info *cpus; + int key = 0; - bpf_get_cpumask_info(&cpus, sizeof(cpus)); - libbpf_cpumask_copy(mask, &cpus.cpu_active_cpumask); + cpus = bpf_map_lookup_elem(&map_cpumask_info, &key); + if (!cpus) + return; + + bpf_get_cpumask_info(&map_cpumask_info, cpus); + libbpf_cpumask_copy(mask, &cpus->cpu_active_cpumask); } static __always_inline void libbpf_isolate_cpus_mask(struct cpumask *mask) { - struct bpf_cpumask_info cpus; + struct bpf_cpumask_info *cpus; + int key = 0; + + cpus = bpf_map_lookup_elem(&map_cpumask_info, &key); + if (!cpus) + return; - bpf_get_cpumask_info(&cpus, sizeof(cpus)); - libbpf_cpumask_copy(mask, &cpus.cpu_isolate_cpumask); + bpf_get_cpumask_info(&map_cpumask_info, cpus); + libbpf_cpumask_copy(mask, &cpus->cpu_isolate_cpumask); } static __always_inline int libbpf_nr_cpus_ids(void) { - struct bpf_cpumask_info cpus; + struct bpf_cpumask_info *cpus; + int key = 0; - bpf_get_cpumask_info(&cpus, sizeof(cpus)); - return getVal(cpus.nr_cpu_ids); + cpus = bpf_map_lookup_elem(&map_cpumask_info, &key); + if (!cpus) + return -1; + + bpf_get_cpumask_info(&map_cpumask_info, cpus); + return getVal(cpus->nr_cpu_ids); } static __always_inline int libbpf_nr_cpumask_bits(void) { - struct bpf_cpumask_info cpus; + struct bpf_cpumask_info *cpus; + int key = 0; + + cpus = bpf_map_lookup_elem(&map_cpumask_info, &key); + if (!cpus) + return -1; - bpf_get_cpumask_info(&cpus, sizeof(cpus)); - return getVal(cpus.bpf_nr_cpumask_bits); + bpf_get_cpumask_info(&map_cpumask_info, cpus); + return getVal(cpus->bpf_nr_cpumask_bits); } static __always_inline unsigned long libbpf_cfs_load_avg_of(int cpu) -- 2.20.1

1 1

[PATCH openEuler-5.10-LTS v2 000/139] Patches for CVE-2022-29900,
by Zheng Zengkai 16 Sep '22

16 Sep '22

Add patches for CVE-2022-29900, CVE-2022-23816 and CVE-2022-29901. Reference: https://lore.kernel.org/all/CAODzB9qH9WhxQ0eB+mNvmsn64bHXUVppuSTMDGJekYOPCw… https://www.amd.com/system/files/documents/technical-guidance-for-mitigatin… https://www.intel.com/content/www/us/en/developer/articles/technical/softwa… Alexandre Chartre (2): x86/bugs: Report AMD retbleed vulnerability x86/bugs: Add AMD retbleed= boot parameter Andrew Cooper (1): x86/cpu/amd: Enumerate BTC_NO Arnaldo Carvalho de Melo (5): tools arch: Update arch/x86/lib/mem{cpy,set}_64.S copies used in 'perf bench mem memcpy' tools arch x86: Sync the msr-index.h copy with the kernel sources tools headers cpufeatures: Sync with the kernel sources tools arch: Update arch/x86/lib/mem{cpy,set}_64.S copies used in 'perf bench mem memcpy' - again tools headers: Remove broken definition of __LITTLE_ENDIAN Ben Hutchings (3): x86: Add insn_decode_kernel() Makefile: Set retpoline cflags based on CONFIG_CC_IS_{CLANG,GCC} x86/xen: Fix initialisation in hypercall_page after rethunk Borislav Petkov (7): x86/insn: Rename insn_decode() to insn_decode_from_regs() x86/insn: Add a __ignore_sync_check__ marker x86/insn: Add an insn_decode() API x86/alternative: Use insn_decode() x86/alternative: Optimize single-byte NOPs at an arbitrary position kvm/emulate: Fix SETcc emulation function offsets with SLS tools/insn: Restore the relative include paths for cross building Greg Kroah-Hartman (1): x86, kvm: use proper ASM macros for kvm_vcpu_is_preempted Joe Lawrence (1): objtool: Make .altinstructions section entry size consistent Josh Poimboeuf (24): objtool: Refactor ORC section generation objtool: Add 'alt_group' struct objtool: Support stack layout changes in alternatives objtool: Support retpoline jump detection for vmlinux.o objtool: Assume only ELF functions do sibling calls objtool: Combine UNWIND_HINT_RET_OFFSET and UNWIND_HINT_FUNC x86/xen: Support objtool validation in xen-asm.S x86/xen: Support objtool vmlinux.o validation in xen-head.S objtool: Support asm jump tables objtool: Don't make .altinstructions writable objtool: Remove reloc symbol type checks in get_alt_entry() x86/bugs: Do IBPB fallback check only once x86/speculation: Fix RSB filling with CONFIG_RETPOLINE=n x86/speculation: Fix firmware entry SPEC_CTRL handling x86/speculation: Fix SPEC_CTRL write on SMT state change x86/speculation: Use cached host SPEC_CTRL value for guest entry/exit x86/speculation: Remove x86_spec_ctrl_mask objtool: Re-add UNWIND_HINT_{SAVE_RESTORE} KVM: VMX: Flatten __vmx_vcpu_run() KVM: VMX: Convert launched argument to flags KVM: VMX: Prevent guest RSB poisoning attacks with eIBRS KVM: VMX: Fix IBRS handling after vmexit x86/speculation: Fill RSB on vmexit for IBRS x86/ftrace: Add UNWIND_HINT_FUNC annotation for ftrace_stub Juergen Gross (4): x86/alternative: Merge include files x86/alternative: Support not-feature x86/alternative: Support ALTERNATIVE_TERNARY x86/alternative: Use ALTERNATIVE_TERNARY() in _static_cpu_has() Kim Phillips (3): x86/sev: Avoid using __x86_return_thunk x86/bugs: Enable STIBP for JMP2RET x86/bugs: Remove apostrophe typo Konrad Rzeszutek Wilk (1): x86/kexec: Disable RET on kexec Lin Yujun (2): x86: Fix objtool build warning Re-add padlen to the structure alt_instr Linus Torvalds (2): objtool: print out the symbol type when complaining about it kvm: fix objtool relocation warning Nathan Chancellor (1): x86/speculation: Use DECLARE_PER_CPU for x86_spec_ctrl_current Pawan Gupta (3): x86/speculation: Add spectre_v2=ibrs option to support Kernel IBRS x86/bugs: Add Cannon lake to RETBleed affected CPU list x86/speculation: Disable RRSBA behavior Peter Zijlstra (70): x86/alternatives: Optimize optimize_nops() x86/retpoline: Simplify retpolines objtool: Correctly handle retpoline thunk calls objtool: Handle per arch retpoline naming objtool: Rework the elf_rebuild_reloc_section() logic objtool: Add elf_create_reloc() helper objtool: Create reloc sections implicitly objtool: Extract elf_strtab_concat() objtool: Extract elf_symbol_add() objtool: Add elf_create_undef_symbol() objtool: Keep track of retpoline call sites objtool: Cache instruction relocs objtool: Skip magical retpoline .altinstr_replacement objtool/x86: Rewrite retpoline thunk calls objtool: Fix .symtab_shndx handling for elf_create_undef_symbol() objtool: Only rewrite unconditional retpoline thunk calls objtool/x86: Ignore __x86_indirect_alt_* symbols objtool: Teach get_alt_entry() about more relocation types objtool: Introduce CFI hash objtool: Handle __sanitize_cov*() tail calls objtool: Classify symbols objtool: Explicitly avoid self modifying code in .altinstr_replacement objtool,x86: Replace alternatives with .retpoline_sites x86/retpoline: Remove unused replacement symbols x86/asm: Fix register order x86/asm: Fixup odd GEN-for-each-reg.h usage x86/retpoline: Move the retpoline thunk declarations to nospec-branch.h x86/retpoline: Create a retpoline thunk array x86/alternative: Implement .retpoline_sites support bpf,x86: Simplify computing label offsets bpf,x86: Respect X86_FEATURE_RETPOLINE* x86/lib/atomic64_386_32: Rename things x86: Prepare asm files for straight-line-speculation x86: Prepare inline-asm for straight-line-speculation x86/alternative: Relax text_poke_bp() constraint objtool: Add straight-line-speculation validation x86: Add straight-line-speculation mitigation objtool: Default ignore INT3 for unreachable crypto: x86/poly1305 - Fixup SLS objtool: Fix SLS validation for kcov tail-call replacement x86/entry: Remove skip_r11rcx x86/kvm/vmx: Make noinstr clean x86/cpufeatures: Move RETPOLINE flags to word 11 x86/retpoline: Cleanup some #ifdefery x86/retpoline: Swizzle retpoline thunk x86/retpoline: Use -mfunction-return x86: Undo return-thunk damage x86,objtool: Create .return_sites x86,static_call: Use alternative RET encoding x86/ftrace: Use alternative RET encoding x86/bpf: Use alternative RET encoding x86/kvm: Fix SETcc emulation for return thunks x86/vsyscall_emu/64: Don't use RET in vsyscall emulation x86: Use return-thunk in asm code objtool: Treat .text.__x86.* as noinstr x86: Add magic AMD return-thunk x86/bugs: Keep a per-CPU IA32_SPEC_CTRL value x86/entry: Add kernel IBRS implementation x86/bugs: Optimize SPEC_CTRL MSR writes x86/bugs: Split spectre_v2_select_mitigation() and spectre_v2_user_select_mitigation() x86/bugs: Report Intel retbleed vulnerability intel_idle: Disable IBRS during long idle objtool: Update Retpoline validation x86/xen: Rename SYS* entry points x86/bugs: Add retbleed=ibpb objtool: Add entry UNRET validation x86/cpu/amd: Add Spectral Chicken x86/common: Stamp out the stepping madness x86/retbleed: Add fine grained Kconfig knobs um: Add missing apply_returns() Thadeu Lima de Souza Cascardo (5): x86/realmode: build with -D__DISABLE_EXPORTS objtool: skip non-text sections when adding return-thunk sites x86/bugs: Do not enable IBPB-on-entry when IBPB is not supported efi/x86: use naked RET on mixed mode call wrapper x86/kvm: fix FASTOP_SIZE when return thunks are enabled Thomas Gleixner (1): x86/static_call: Serialize __static_call_fixup() properly Uros Bizjak (2): KVM/VMX: Use TEST %REG,%REG instead of CMP $0,%REG in vmenter.S KVM/nVMX: Use __vmx_vcpu_run in nested_vmx_check_vmentry_hw Vasily Gorbik (1): objtool: Fix elf_create_undef_symbol() endianness .../admin-guide/kernel-parameters.txt | 25 + Makefile | 20 +- arch/um/kernel/um_arch.c | 8 + arch/x86/Kconfig | 91 +- arch/x86/Makefile | 8 +- arch/x86/boot/compressed/efi_thunk_64.S | 2 +- arch/x86/boot/compressed/head_64.S | 4 +- arch/x86/boot/compressed/mem_encrypt.S | 4 +- arch/x86/crypto/aegis128-aesni-asm.S | 48 +- arch/x86/crypto/aes_ctrby8_avx-x86_64.S | 2 +- arch/x86/crypto/aesni-intel_asm.S | 52 +- arch/x86/crypto/aesni-intel_avx-x86_64.S | 40 +- arch/x86/crypto/blake2s-core.S | 4 +- arch/x86/crypto/blowfish-x86_64-asm_64.S | 12 +- arch/x86/crypto/camellia-aesni-avx-asm_64.S | 18 +- arch/x86/crypto/camellia-aesni-avx2-asm_64.S | 18 +- arch/x86/crypto/camellia-x86_64-asm_64.S | 12 +- arch/x86/crypto/cast5-avx-x86_64-asm_64.S | 12 +- arch/x86/crypto/cast6-avx-x86_64-asm_64.S | 16 +- arch/x86/crypto/chacha-avx2-x86_64.S | 6 +- arch/x86/crypto/chacha-avx512vl-x86_64.S | 6 +- arch/x86/crypto/chacha-ssse3-x86_64.S | 8 +- arch/x86/crypto/crc32-pclmul_asm.S | 2 +- arch/x86/crypto/crc32c-pcl-intel-asm_64.S | 2 +- arch/x86/crypto/crct10dif-pcl-asm_64.S | 2 +- arch/x86/crypto/des3_ede-asm_64.S | 4 +- arch/x86/crypto/ghash-clmulni-intel_asm.S | 6 +- arch/x86/crypto/nh-avx2-x86_64.S | 2 +- arch/x86/crypto/nh-sse2-x86_64.S | 2 +- arch/x86/crypto/poly1305-x86_64-cryptogams.pl | 38 +- arch/x86/crypto/serpent-avx-x86_64-asm_64.S | 16 +- arch/x86/crypto/serpent-avx2-asm_64.S | 16 +- arch/x86/crypto/serpent-sse2-i586-asm_32.S | 6 +- arch/x86/crypto/serpent-sse2-x86_64-asm_64.S | 6 +- arch/x86/crypto/sha1_avx2_x86_64_asm.S | 2 +- arch/x86/crypto/sha1_ni_asm.S | 2 +- arch/x86/crypto/sha1_ssse3_asm.S | 2 +- arch/x86/crypto/sha256-avx-asm.S | 2 +- arch/x86/crypto/sha256-avx2-asm.S | 2 +- arch/x86/crypto/sha256-ssse3-asm.S | 2 +- arch/x86/crypto/sha256_ni_asm.S | 2 +- arch/x86/crypto/sha512-avx-asm.S | 2 +- arch/x86/crypto/sha512-avx2-asm.S | 2 +- arch/x86/crypto/sha512-ssse3-asm.S | 2 +- arch/x86/crypto/twofish-avx-x86_64-asm_64.S | 16 +- arch/x86/crypto/twofish-i586-asm_32.S | 4 +- arch/x86/crypto/twofish-x86_64-asm_64-3way.S | 6 +- arch/x86/crypto/twofish-x86_64-asm_64.S | 4 +- arch/x86/entry/Makefile | 2 +- arch/x86/entry/calling.h | 72 +- arch/x86/entry/entry.S | 22 + arch/x86/entry/entry_32.S | 6 +- arch/x86/entry/entry_64.S | 62 +- arch/x86/entry/entry_64_compat.S | 21 +- arch/x86/entry/thunk_32.S | 2 +- arch/x86/entry/thunk_64.S | 2 +- arch/x86/entry/vdso/Makefile | 1 + arch/x86/entry/vdso/vdso32/system_call.S | 4 +- arch/x86/entry/vsyscall/vsyscall_emu_64.S | 3 + arch/x86/include/asm/GEN-for-each-reg.h | 14 +- arch/x86/include/asm/alternative-asm.h | 114 -- arch/x86/include/asm/alternative.h | 133 +- arch/x86/include/asm/asm-prototypes.h | 17 - arch/x86/include/asm/cpufeature.h | 41 +- arch/x86/include/asm/cpufeatures.h | 12 +- arch/x86/include/asm/disabled-features.h | 21 +- arch/x86/include/asm/inat.h | 2 +- arch/x86/include/asm/insn-eval.h | 4 +- arch/x86/include/asm/insn.h | 28 +- arch/x86/include/asm/linkage.h | 22 + arch/x86/include/asm/msr-index.h | 13 + arch/x86/include/asm/nospec-branch.h | 148 ++- arch/x86/include/asm/paravirt.h | 2 +- arch/x86/include/asm/qspinlock_paravirt.h | 4 +- arch/x86/include/asm/smap.h | 5 +- arch/x86/include/asm/static_call.h | 19 +- arch/x86/include/asm/unwind_hints.h | 23 +- arch/x86/kernel/acpi/wakeup_32.S | 6 +- arch/x86/kernel/alternative.c | 356 +++++- arch/x86/kernel/cpu/amd.c | 46 +- arch/x86/kernel/cpu/bugs.c | 475 ++++++- arch/x86/kernel/cpu/common.c | 61 +- arch/x86/kernel/cpu/cpu.h | 2 + arch/x86/kernel/cpu/hygon.c | 6 + arch/x86/kernel/cpu/scattered.c | 1 + arch/x86/kernel/ftrace.c | 7 +- arch/x86/kernel/ftrace_32.S | 6 +- arch/x86/kernel/ftrace_64.S | 13 +- arch/x86/kernel/head_32.S | 2 +- arch/x86/kernel/head_64.S | 5 + arch/x86/kernel/irqflags.S | 4 +- arch/x86/kernel/kprobes/core.c | 2 +- arch/x86/kernel/kvm.c | 2 +- arch/x86/kernel/module.c | 15 +- arch/x86/kernel/paravirt.c | 2 +- arch/x86/kernel/process.c | 2 +- arch/x86/kernel/relocate_kernel_32.S | 15 +- arch/x86/kernel/relocate_kernel_64.S | 13 +- arch/x86/kernel/sev-es.c | 2 +- arch/x86/kernel/sev_verify_cbit.S | 2 +- arch/x86/kernel/static_call.c | 52 +- arch/x86/kernel/umip.c | 2 +- arch/x86/kernel/verify_cpu.S | 4 +- arch/x86/kernel/vmlinux.lds.S | 23 +- arch/x86/kvm/emulate.c | 39 +- arch/x86/kvm/svm/vmenter.S | 11 +- arch/x86/kvm/vmx/nested.c | 32 +- arch/x86/kvm/vmx/run_flags.h | 8 + arch/x86/kvm/vmx/vmenter.S | 170 +-- arch/x86/kvm/vmx/vmx.c | 78 +- arch/x86/kvm/vmx/vmx.h | 5 + arch/x86/kvm/x86.c | 4 +- arch/x86/lib/atomic64_386_32.S | 88 +- arch/x86/lib/atomic64_cx8_32.S | 18 +- arch/x86/lib/checksum_32.S | 8 +- arch/x86/lib/clear_page_64.S | 6 +- arch/x86/lib/cmpxchg16b_emu.S | 4 +- arch/x86/lib/cmpxchg8b_emu.S | 4 +- arch/x86/lib/copy_mc_64.S | 6 +- arch/x86/lib/copy_page_64.S | 10 +- arch/x86/lib/copy_user_64.S | 14 +- arch/x86/lib/csum-copy_64.S | 2 +- arch/x86/lib/error-inject.c | 3 +- arch/x86/lib/getuser.S | 22 +- arch/x86/lib/hweight.S | 6 +- arch/x86/lib/inat.c | 2 +- arch/x86/lib/insn-eval.c | 6 +- arch/x86/lib/insn.c | 222 +++- arch/x86/lib/iomap_copy_64.S | 2 +- arch/x86/lib/memcpy_64.S | 14 +- arch/x86/lib/memmove_64.S | 11 +- arch/x86/lib/memset_64.S | 8 +- arch/x86/lib/msr-reg.S | 4 +- arch/x86/lib/putuser.S | 6 +- arch/x86/lib/retpoline.S | 118 +- arch/x86/math-emu/div_Xsig.S | 2 +- arch/x86/math-emu/div_small.S | 2 +- arch/x86/math-emu/mul_Xsig.S | 6 +- arch/x86/math-emu/polynom_Xsig.S | 2 +- arch/x86/math-emu/reg_norm.S | 6 +- arch/x86/math-emu/reg_round.S | 2 +- arch/x86/math-emu/reg_u_add.S | 2 +- arch/x86/math-emu/reg_u_div.S | 2 +- arch/x86/math-emu/reg_u_mul.S | 2 +- arch/x86/math-emu/reg_u_sub.S | 2 +- arch/x86/math-emu/round_Xsig.S | 4 +- arch/x86/math-emu/shr_Xsig.S | 8 +- arch/x86/math-emu/wm_shrx.S | 16 +- arch/x86/mm/mem_encrypt_boot.S | 6 + arch/x86/net/bpf_jit_comp.c | 185 ++- arch/x86/net/bpf_jit_comp32.c | 22 +- arch/x86/platform/efi/efi_stub_32.S | 2 +- arch/x86/platform/efi/efi_stub_64.S | 2 +- arch/x86/platform/efi/efi_thunk_64.S | 5 +- arch/x86/platform/olpc/xo1-wakeup.S | 6 +- arch/x86/power/hibernate_asm_32.S | 4 +- arch/x86/power/hibernate_asm_64.S | 4 +- arch/x86/um/checksum_32.S | 4 +- arch/x86/um/setjmp_32.S | 2 +- arch/x86/um/setjmp_64.S | 2 +- arch/x86/xen/Makefile | 1 - arch/x86/xen/setup.c | 6 +- arch/x86/xen/xen-asm.S | 43 +- arch/x86/xen/xen-head.S | 6 +- arch/x86/xen/xen-ops.h | 6 +- drivers/base/cpu.c | 8 + drivers/idle/intel_idle.c | 43 +- include/linux/cpu.h | 2 + include/linux/kvm_host.h | 2 +- include/linux/objtool.h | 14 +- samples/ftrace/ftrace-direct-modify.c | 4 +- samples/ftrace/ftrace-direct-too.c | 2 +- samples/ftrace/ftrace-direct.c | 2 +- scripts/Makefile.build | 6 + scripts/link-vmlinux.sh | 6 + security/Kconfig | 11 - tools/arch/x86/include/asm/cpufeatures.h | 12 +- .../arch/x86/include/asm/disabled-features.h | 21 +- tools/arch/x86/include/asm/inat.h | 2 +- tools/arch/x86/include/asm/insn.h | 28 +- tools/arch/x86/include/asm/msr-index.h | 13 + tools/arch/x86/lib/inat.c | 2 +- tools/arch/x86/lib/insn.c | 222 +++- tools/arch/x86/lib/memcpy_64.S | 14 +- tools/arch/x86/lib/memset_64.S | 8 +- .../asm/{alternative-asm.h => alternative.h} | 0 tools/include/linux/kconfig.h | 67 + tools/include/linux/objtool.h | 14 +- .../Documentation/stack-validation.txt | 16 +- tools/objtool/Makefile | 4 - tools/objtool/arch.h | 13 +- tools/objtool/arch/x86/decode.c | 58 +- tools/objtool/builtin-check.c | 6 +- tools/objtool/builtin-orc.c | 6 +- tools/objtool/builtin.h | 3 +- tools/objtool/cfi.h | 2 + tools/objtool/check.c | 1131 +++++++++++++---- tools/objtool/check.h | 35 +- tools/objtool/elf.c | 230 ++-- tools/objtool/elf.h | 20 +- tools/objtool/objtool.c | 2 + tools/objtool/objtool.h | 5 +- tools/objtool/orc_gen.c | 324 ++--- tools/objtool/special.c | 22 +- tools/objtool/sync-check.sh | 17 +- tools/objtool/weak.c | 7 +- tools/perf/check-headers.sh | 15 +- 207 files changed, 4323 insertions(+), 1902 deletions(-) create mode 100644 arch/x86/entry/entry.S delete mode 100644 arch/x86/include/asm/alternative-asm.h create mode 100644 arch/x86/kvm/vmx/run_flags.h rename tools/include/asm/{alternative-asm.h => alternative.h} (100%) create mode 100644 tools/include/linux/kconfig.h -- 2.20.1

1 139

[PATCH RFC v2 openEuler-1.0-LTS 0/6] md: improve performance
by Yu Kuai 16 Sep '22

16 Sep '22

From: Yu Kuai <yukuai3(a)huawei.com> Changes in v2: - fix the problem that if 'nr_pending' is decreased to 0 in wait_barrier_nolock() in patch 1, 'conf->barrier' is not waked, and raise_barrier() can hang while waiting 'nr_pending' to be 0. - only modify hot path in patch 2. - use node 1 as default in patch 6. In some architecture, for example KUNPENG 920, memory access latency is very bad across nodes compare to local node. For consequence, io performance is rather bad while users issue io from multiple nodes if lock contention exist in the driver. This patchset tries to avoid memory access across nodes in driver. Test environment: aarch64 Huawei KUNPENG 920 Raid10 initialize: mdadm --create /dev/md0 --level 10 --bitmap none --raid-devices 4 /dev/nvme0n1 /dev/nvme1n1 /dev/nvme2n1 /dev/nvme3n1 Test cmd: (task set -c 0-15) fio -name=0 -ioengine=libaio -direct=1 -group_reporting=1 -randseed=2022 -rwmixread=70 -refill_buffers -filename=/dev/md0 -numjobs=16 -runtime=60s -bs=4k -iodepth=256 -rw=randread Test result: before this patchset: 3.2 GiB/s bind node before this patchset: 6.9 Gib/s after this patchset: 7.9 Gib/s bind node after this patchset: 8.0 Gib/s Wang ShaoBo (1): arm64/topology: Getting preferred sibling's cpumask supported by platform Yu Kuai (5): md/raid10: convert resync_lock to use seqlock md/raid10: prevent unnecessary calls to wake_up() in fast path block: add new fields in request_queue block: support to dispatch bio asynchronously md: enable dispatching bio asynchronously by default arch/arm64/Kconfig | 8 ++ arch/arm64/include/asm/smp_plat.h | 14 ++ arch/arm64/kernel/smp.c | 9 ++ arch/arm64/kernel/topology.c | 51 +++++++ block/blk-core.c | 212 +++++++++++++++++++++++++++++- block/blk-sysfs.c | 40 ++++++ drivers/md/md.c | 5 + drivers/md/raid10.c | 98 +++++++++----- drivers/md/raid10.h | 2 +- include/linux/arch_topology.h | 7 + include/linux/blkdev.h | 6 + 11 files changed, 420 insertions(+), 32 deletions(-) -- 2.31.1

1 6

subscribe
by hiixfj 16 Sep '22

16 Sep '22

1 0

help
by hiixfj 16 Sep '22

16 Sep '22

1 0

[PATCH openEuler-1.0-LTS] mm: Force TLB flush for PFNMAP mappings before unlink_file_vma()
by Yongqiang Liu 14 Sep '22

14 Sep '22

From: Jann Horn <jannh(a)google.com> stable inclusion from stable-v4.19.257 commit c3b1e88f14e7f442e2ddcbec94527eec84ac0ca3 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I5PE9S CVE: CVE-2022-39188 -------------------------------- commit b67fbebd4cf980aecbcc750e1462128bffe8ae15 upstream. Some drivers rely on having all VMAs through which a PFN might be accessible listed in the rmap for correctness. However, on X86, it was possible for a VMA with stale TLB entries to not be listed in the rmap. This was fixed in mainline with commit b67fbebd4cf9 ("mmu_gather: Force tlb-flush VM_PFNMAP vmas"), but that commit relies on preceding refactoring in commit 18ba064e42df3 ("mmu_gather: Let there be one tlb_{start,end}_vma() implementation") and commit 1e9fdf21a4339 ("mmu_gather: Remove per arch tlb_{start,end}_vma()"). This patch provides equivalent protection without needing that refactoring, by forcing a TLB flush between removing PTEs in unmap_vmas() and the call to unlink_file_vma() in free_pgtables(). [This is a stable-specific rewrite of the upstream commit!] Signed-off-by: Jann Horn <jannh(a)google.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Reviewed-by: zuoze <zuoze1(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- mm/mmap.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/mm/mmap.c b/mm/mmap.c index a2699bc10f7b..3bf113a24599 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2899,6 +2899,18 @@ static void unmap_region(struct mm_struct *mm, tlb_gather_mmu(&tlb, mm, start, end); update_hiwater_rss(mm); unmap_vmas(&tlb, vma, start, end); + + /* + * Ensure we have no stale TLB entries by the time this mapping is + * removed from the rmap. + * Note that we don't have to worry about nested flushes here because + * we're holding the mm semaphore for removing the mapping - so any + * concurrent flush in this region has to be coming through the rmap, + * and we synchronize against that using the rmap lock. + */ + if ((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) != 0) + tlb_flush_mmu(&tlb); + free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS, next ? next->vm_start : USER_PGTABLES_CEILING); tlb_finish_mmu(&tlb, start, end); -- 2.25.1

1 0

[PATCH openEuler-5.10] Script: Add shell script for adding openeuler patch header
by Zheng Zengkai 14 Sep '22

14 Sep '22

script for adding mainline patch header. Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- add-openeuler-patch-header-mainline.sh | 56 ++++++++++++++++++++++++++ 1 file changed, 56 insertions(+) create mode 100755 add-openeuler-patch-header-mainline.sh diff --git a/add-openeuler-patch-header-mainline.sh b/add-openeuler-patch-header-mainline.sh new file mode 100755 index 000000000000..e9352911d242 --- /dev/null +++ b/add-openeuler-patch-header-mainline.sh @@ -0,0 +1,56 @@ +#!/bin/sh + +# +# Usage: +# +# prerequisite: +# +# The patches to add header should be patches from linux mainline. +# +# command (run in the directory where patch files stored): +# add-openeuler-patch-header-mainline.sh commit1..commit2 gitee_issue_url +# +# commit1: mainline start commit id +# commit2: mainline end commit id +# gitee_issue_url: for example: https://gitee.com/openeuler/kernel/issues/I4MKP4 +# +# Example: +# add-openeuler-patch-header-mainline.sh 2c85ebc57b3e..80e78fcce86d https://gitee.com/openeuler/kernel/issues/I5OHOB +# + +for p in `ls *.patch` +do + if [ $p == "0000-cover-letter.patch" ]; then + continue + fi + + title=$(sed '/^Subject: \[PATCH .*\]/{N;s/\n / /g}' $p | grep -E "^Subject: \[PATCH .*\]" | cut -d ']' -f 2) + commit=$(git log --pretty=oneline $1 | grep -F "$title" | cut -d ' ' -f 1) + if [ -n "$multi" ]; then + echo "$p" has multi-commits + commit="multi" + continue + fi + if [ -z "$commit" ]; then + echo "$p" commit is null + commit="null" + continue + fi + + # find insert line + i=5 + while true + do + ln=""$i"p" + sub=`cat $p | sed -n "$ln"` + i=$(($i+1)) + if [ -z "$sub" ]; then + break + fi + done + i=$(($i-1)) + + version=`git name-rev $commit | awk -F '[v~^]' '{print $2}'` + + sed ""$i"a mainline inclusion\nfrom mainline-v$version\ncommit $commit\ncategory: feature\nbugzilla: $2\nCVE: NA\n\n--------------------------------\n" -i $p +done -- 2.20.1

1 0

[PATCH openEuler-5.10-LTS 1/6] KVM: x86: do not report a vCPU as preempted outside instruction boundaries
by Zheng Zengkai 14 Sep '22

14 Sep '22

From: Paolo Bonzini <pbonzini(a)redhat.com> mainline inclusion from mainline-v5.19-rc2 commit 6cd88243c7e03845a450795e134b488fc2afb736 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I5PJ7H CVE: CVE-2022-39189 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ---------------------------------------- If a vCPU is outside guest mode and is scheduled out, it might be in the process of making a memory access. A problem occurs if another vCPU uses the PV TLB flush feature during the period when the vCPU is scheduled out, and a virtual address has already been translated but has not yet been accessed, because this is equivalent to using a stale TLB entry. To avoid this, only report a vCPU as preempted if sure that the guest is at an instruction boundary. A rescheduling request will be delivered to the host physical CPU as an external interrupt, so for simplicity consider any vmexit *not* instruction boundary except for external interrupts. It would in principle be okay to report the vCPU as preempted also if it is sleeping in kvm_vcpu_block(): a TLB flush IPI will incur the vmentry/vmexit overhead unnecessarily, and optimistic spinning is also unlikely to succeed. However, leave it for later because right now kvm_vcpu_check_block() is doing memory accesses. Even though the TLB flush issue only applies to virtual memory address, it's very much preferrable to be conservative. Reported-by: Jann Horn <jannh(a)google.com> Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> conflict: arch/x86/kvm/x86.c Signed-off-by: Guo Mengqi <guomengqi3(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Reviewed-by: yezengruan <yezengruan(a)huawei.com> Reviewed-by: Weilong Chen <chenweilong(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- arch/x86/include/asm/kvm_host.h | 3 +++ arch/x86/kvm/svm/svm.c | 2 ++ arch/x86/kvm/vmx/vmx.c | 1 + arch/x86/kvm/x86.c | 24 ++++++++++++++++++++++++ 4 files changed, 30 insertions(+) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index d90792da5b9e..01544554a4c2 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -551,6 +551,7 @@ struct kvm_vcpu_arch { u64 ia32_misc_enable_msr; u64 smbase; u64 smi_count; + bool at_instruction_boundary; bool tpr_access_reporting; bool xsaves_enabled; u64 ia32_xss; @@ -1072,6 +1073,8 @@ struct kvm_vcpu_stat { u64 utime; u64 stime; u64 gtime; + u64 preemption_reported; + u64 preemption_other; u64 preemption_timer_exits; }; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 2124fe54abfb..5231f40e8312 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3992,6 +3992,8 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu, static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu) { + if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_INTR) + vcpu->arch.at_instruction_boundary = true; } static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 79889d27aa5b..96693ac066c2 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6532,6 +6532,7 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) return; handle_interrupt_nmi_irqoff(vcpu, gate_offset(desc)); + vcpu->arch.at_instruction_boundary = true; } static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 24c198e70f8e..dac43d92eb81 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -232,6 +232,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { VCPU_STAT("l1d_flush", l1d_flush), VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns), VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns), + VCPU_STAT("preemption_reported", preemption_reported), + VCPU_STAT("preemption_other", preemption_other), VM_STAT("mmu_shadow_zapped", mmu_shadow_zapped), VM_STAT("mmu_pte_write", mmu_pte_write), VM_STAT("mmu_pde_zapped", mmu_pde_zapped), @@ -286,6 +288,8 @@ struct dfx_kvm_stats_debugfs_item dfx_debugfs_entries[] = { DFX_STAT("stime", stime), DFX_STAT("gtime", gtime), DFX_STAT("preemption_timer_exits", preemption_timer_exits), + DFX_STAT("preemption_reported", preemption_reported), + DFX_STAT("preemption_other", preemption_other), { NULL } }; @@ -4078,6 +4082,19 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) struct kvm_host_map map; struct kvm_steal_time *st; + /* + * The vCPU can be marked preempted if and only if the VM-Exit was on + * an instruction boundary and will not trigger guest emulation of any + * kind (see vcpu_run). Vendor specific code controls (conservatively) + * when this is true, for example allowing the vCPU to be marked + * preempted if and only if the VM-Exit was due to a host interrupt. + */ + if (!vcpu->arch.at_instruction_boundary) { + vcpu->stat.preemption_other++; + return; + } + + vcpu->stat.preemption_reported++; if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; @@ -9306,6 +9323,13 @@ static int vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.l1tf_flush_l1d = true; for (;;) { + /* + * If another guest vCPU requests a PV TLB flush in the middle + * of instruction emulation, the rest of the emulation could + * use a stale page translation. Assume that any code after + * this point can start executing an instruction. + */ + vcpu->arch.at_instruction_boundary = false; if (kvm_vcpu_running(vcpu)) { r = vcpu_enter_guest(vcpu); } else { -- 2.20.1

1 5

openEuler Kernel SIG例会
by openEuler conference 14 Sep '22

14 Sep '22

您好！ Kernel SIG 邀请您参加 2022-09-16 14:00 召开的Zoom会议(自动录制) 会议主题：openEuler Kernel SIG例会会议内容： 1.调度系列技术分享第三期 -- Linux调度器框架 2.openEuler开源之夏特性 -- 轻量级死锁检测实现 3.openEuler-22.09龙芯支持特性简介会议链接：https://us06web.zoom.us/j/87690719217?pwd=cDN6V3Bhc05DU3lqTmhHYzA2L0RBQT09 会议纪要：https://etherpad.openeuler.org/p/Kernel-meetings 温馨提醒：建议接入会议后修改参会人的姓名，也可以使用您在gitee.com的ID 更多资讯尽在：https://openeuler.org/zh/ Hello! openEuler Kernel SIG invites you to attend the Zoom conference(auto recording) will be held at 2022-09-16 14:00, The subject of the conference is openEuler Kernel SIG例会, Summary: 1.调度系列技术分享第三期 -- Linux调度器框架 2.openEuler开源之夏特性 -- 轻量级死锁检测实现 3.openEuler-22.09龙芯支持特性简介 You can join the meeting at https://us06web.zoom.us/j/87690719217?pwd=cDN6V3Bhc05DU3lqTmhHYzA2L0RBQT09. Add topics at https://etherpad.openeuler.org/p/Kernel-meetings. Note: You are advised to change the participant name after joining the conference or use your ID at gitee.com. More information: https://openeuler.org/en/

1 0

[PATCH openEuler-1.0-LTS] video: fbdev: pxa3xx-gcu: Fix integer overflow in pxa3xx_gcu_write
by Yongqiang Liu 14 Sep '22

14 Sep '22

From: Hyunwoo Kim <imv4bel(a)gmail.com> mainline inclusion from mainline-v5.19-rc4 commit a09d2d00af53b43c6f11e6ab3cb58443c2cac8a7 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I5PRMO CVE: CVE-2022-39842 --------------------- In pxa3xx_gcu_write, a count parameter of type size_t is passed to words of type int. Then, copy_from_user() may cause a heap overflow because it is used as the third argument of copy_from_user(). Signed-off-by: Hyunwoo Kim <imv4bel(a)gmail.com> Signed-off-by: Helge Deller <deller(a)gmx.de> Signed-off-by: Zhao Wenhui <zhaowenhui8(a)huawei.com> Reviewed-by: Chen Hui <judy.chenhui(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/video/fbdev/pxa3xx-gcu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/video/fbdev/pxa3xx-gcu.c b/drivers/video/fbdev/pxa3xx-gcu.c index 69cfb337c857..6fe5573e2008 100644 --- a/drivers/video/fbdev/pxa3xx-gcu.c +++ b/drivers/video/fbdev/pxa3xx-gcu.c @@ -394,7 +394,7 @@ pxa3xx_gcu_write(struct file *file, const char *buff, struct pxa3xx_gcu_batch *buffer; struct pxa3xx_gcu_priv *priv = to_pxa3xx_gcu_priv(file); - int words = count / 4; + size_t words = count / 4; /* Does not need to be atomic. There's a lock in user space, * but anyhow, this is just for statistics. */ -- 2.25.1

1 0

[PATCH openEuler-5.10-LTS 000/137] Patches for CVE-2022-29900, CVE-2022-23816
by Zheng Zengkai 14 Sep '22

14 Sep '22

Add patches for CVE-2022-29900, CVE-2022-23816 and CVE-2022-29901. Reference: https://lore.kernel.org/all/CAODzB9qH9WhxQ0eB+mNvmsn64bHXUVppuSTMDGJekYOPCw… https://www.amd.com/system/files/documents/technical-guidance-for-mitigatin… https://www.intel.com/content/www/us/en/developer/articles/technical/softwa… Alexandre Chartre (2): x86/bugs: Report AMD retbleed vulnerability x86/bugs: Add AMD retbleed= boot parameter Andrew Cooper (1): x86/cpu/amd: Enumerate BTC_NO Arnaldo Carvalho de Melo (5): tools arch: Update arch/x86/lib/mem{cpy,set}_64.S copies used in 'perf bench mem memcpy' tools arch x86: Sync the msr-index.h copy with the kernel sources tools headers cpufeatures: Sync with the kernel sources tools arch: Update arch/x86/lib/mem{cpy,set}_64.S copies used in 'perf bench mem memcpy' - again tools headers: Remove broken definition of __LITTLE_ENDIAN Ben Hutchings (3): x86: Add insn_decode_kernel() Makefile: Set retpoline cflags based on CONFIG_CC_IS_{CLANG,GCC} x86/xen: Fix initialisation in hypercall_page after rethunk Borislav Petkov (7): x86/insn: Rename insn_decode() to insn_decode_from_regs() x86/insn: Add a __ignore_sync_check__ marker x86/insn: Add an insn_decode() API x86/alternative: Use insn_decode() x86/alternative: Optimize single-byte NOPs at an arbitrary position kvm/emulate: Fix SETcc emulation function offsets with SLS tools/insn: Restore the relative include paths for cross building Greg Kroah-Hartman (1): x86, kvm: use proper ASM macros for kvm_vcpu_is_preempted Joe Lawrence (1): objtool: Make .altinstructions section entry size consistent Josh Poimboeuf (24): objtool: Refactor ORC section generation objtool: Add 'alt_group' struct objtool: Support stack layout changes in alternatives objtool: Support retpoline jump detection for vmlinux.o objtool: Assume only ELF functions do sibling calls objtool: Combine UNWIND_HINT_RET_OFFSET and UNWIND_HINT_FUNC x86/xen: Support objtool validation in xen-asm.S x86/xen: Support objtool vmlinux.o validation in xen-head.S objtool: Support asm jump tables objtool: Don't make .altinstructions writable objtool: Remove reloc symbol type checks in get_alt_entry() x86/bugs: Do IBPB fallback check only once x86/speculation: Fix RSB filling with CONFIG_RETPOLINE=n x86/speculation: Fix firmware entry SPEC_CTRL handling x86/speculation: Fix SPEC_CTRL write on SMT state change x86/speculation: Use cached host SPEC_CTRL value for guest entry/exit x86/speculation: Remove x86_spec_ctrl_mask objtool: Re-add UNWIND_HINT_{SAVE_RESTORE} KVM: VMX: Flatten __vmx_vcpu_run() KVM: VMX: Convert launched argument to flags KVM: VMX: Prevent guest RSB poisoning attacks with eIBRS KVM: VMX: Fix IBRS handling after vmexit x86/speculation: Fill RSB on vmexit for IBRS x86/ftrace: Add UNWIND_HINT_FUNC annotation for ftrace_stub Juergen Gross (4): x86/alternative: Merge include files x86/alternative: Support not-feature x86/alternative: Support ALTERNATIVE_TERNARY x86/alternative: Use ALTERNATIVE_TERNARY() in _static_cpu_has() Kim Phillips (3): x86/sev: Avoid using __x86_return_thunk x86/bugs: Enable STIBP for JMP2RET x86/bugs: Remove apostrophe typo Konrad Rzeszutek Wilk (1): x86/kexec: Disable RET on kexec Lin Yujun (2): x86: Fix objtool build warning Re-add padlen to the structure alt_instr Linus Torvalds (2): objtool: print out the symbol type when complaining about it kvm: fix objtool relocation warning Nathan Chancellor (1): x86/speculation: Use DECLARE_PER_CPU for x86_spec_ctrl_current Pawan Gupta (3): x86/speculation: Add spectre_v2=ibrs option to support Kernel IBRS x86/bugs: Add Cannon lake to RETBleed affected CPU list x86/speculation: Disable RRSBA behavior Peter Zijlstra (69): x86/alternatives: Optimize optimize_nops() x86/retpoline: Simplify retpolines objtool: Correctly handle retpoline thunk calls objtool: Handle per arch retpoline naming objtool: Rework the elf_rebuild_reloc_section() logic objtool: Add elf_create_reloc() helper objtool: Create reloc sections implicitly objtool: Extract elf_strtab_concat() objtool: Extract elf_symbol_add() objtool: Add elf_create_undef_symbol() objtool: Keep track of retpoline call sites objtool: Cache instruction relocs objtool: Skip magical retpoline .altinstr_replacement objtool/x86: Rewrite retpoline thunk calls objtool: Fix .symtab_shndx handling for elf_create_undef_symbol() objtool: Only rewrite unconditional retpoline thunk calls objtool: Teach get_alt_entry() about more relocation types objtool: Introduce CFI hash objtool: Handle __sanitize_cov*() tail calls objtool: Classify symbols objtool: Explicitly avoid self modifying code in .altinstr_replacement objtool,x86: Replace alternatives with .retpoline_sites objtool/x86: Ignore __x86_indirect_alt_* symbols x86/asm: Fix register order x86/asm: Fixup odd GEN-for-each-reg.h usage x86/retpoline: Move the retpoline thunk declarations to nospec-branch.h x86/retpoline: Create a retpoline thunk array x86/alternative: Implement .retpoline_sites support bpf,x86: Simplify computing label offsets bpf,x86: Respect X86_FEATURE_RETPOLINE* x86/lib/atomic64_386_32: Rename things x86: Prepare asm files for straight-line-speculation x86: Prepare inline-asm for straight-line-speculation x86/alternative: Relax text_poke_bp() constraint objtool: Add straight-line-speculation validation x86: Add straight-line-speculation mitigation objtool: Default ignore INT3 for unreachable crypto: x86/poly1305 - Fixup SLS objtool: Fix SLS validation for kcov tail-call replacement x86/entry: Remove skip_r11rcx x86/kvm/vmx: Make noinstr clean x86/cpufeatures: Move RETPOLINE flags to word 11 x86/retpoline: Cleanup some #ifdefery x86/retpoline: Swizzle retpoline thunk x86/retpoline: Use -mfunction-return x86: Undo return-thunk damage x86,objtool: Create .return_sites x86,static_call: Use alternative RET encoding x86/ftrace: Use alternative RET encoding x86/bpf: Use alternative RET encoding x86/kvm: Fix SETcc emulation for return thunks x86/vsyscall_emu/64: Don't use RET in vsyscall emulation x86: Use return-thunk in asm code objtool: Treat .text.__x86.* as noinstr x86: Add magic AMD return-thunk x86/bugs: Keep a per-CPU IA32_SPEC_CTRL value x86/entry: Add kernel IBRS implementation x86/bugs: Optimize SPEC_CTRL MSR writes x86/bugs: Split spectre_v2_select_mitigation() and spectre_v2_user_select_mitigation() x86/bugs: Report Intel retbleed vulnerability intel_idle: Disable IBRS during long idle objtool: Update Retpoline validation x86/xen: Rename SYS* entry points x86/bugs: Add retbleed=ibpb objtool: Add entry UNRET validation x86/cpu/amd: Add Spectral Chicken x86/common: Stamp out the stepping madness x86/retbleed: Add fine grained Kconfig knobs um: Add missing apply_returns() Thadeu Lima de Souza Cascardo (4): x86/realmode: build with -D__DISABLE_EXPORTS x86/bugs: Do not enable IBPB-on-entry when IBPB is not supported efi/x86: use naked RET on mixed mode call wrapper x86/kvm: fix FASTOP_SIZE when return thunks are enabled Thomas Gleixner (1): x86/static_call: Serialize __static_call_fixup() properly Uros Bizjak (2): KVM/VMX: Use TEST %REG,%REG instead of CMP $0,%REG in vmenter.S KVM/nVMX: Use __vmx_vcpu_run in nested_vmx_check_vmentry_hw Vasily Gorbik (1): objtool: Fix elf_create_undef_symbol() endianness .../admin-guide/kernel-parameters.txt | 25 + Makefile | 20 +- arch/um/kernel/um_arch.c | 8 + arch/x86/Kconfig | 91 +- arch/x86/Makefile | 8 +- arch/x86/boot/compressed/efi_thunk_64.S | 2 +- arch/x86/boot/compressed/head_64.S | 4 +- arch/x86/boot/compressed/mem_encrypt.S | 4 +- arch/x86/crypto/aegis128-aesni-asm.S | 48 +- arch/x86/crypto/aes_ctrby8_avx-x86_64.S | 2 +- arch/x86/crypto/aesni-intel_asm.S | 52 +- arch/x86/crypto/aesni-intel_avx-x86_64.S | 40 +- arch/x86/crypto/blake2s-core.S | 4 +- arch/x86/crypto/blowfish-x86_64-asm_64.S | 12 +- arch/x86/crypto/camellia-aesni-avx-asm_64.S | 18 +- arch/x86/crypto/camellia-aesni-avx2-asm_64.S | 18 +- arch/x86/crypto/camellia-x86_64-asm_64.S | 12 +- arch/x86/crypto/cast5-avx-x86_64-asm_64.S | 12 +- arch/x86/crypto/cast6-avx-x86_64-asm_64.S | 16 +- arch/x86/crypto/chacha-avx2-x86_64.S | 6 +- arch/x86/crypto/chacha-avx512vl-x86_64.S | 6 +- arch/x86/crypto/chacha-ssse3-x86_64.S | 8 +- arch/x86/crypto/crc32-pclmul_asm.S | 2 +- arch/x86/crypto/crc32c-pcl-intel-asm_64.S | 2 +- arch/x86/crypto/crct10dif-pcl-asm_64.S | 2 +- arch/x86/crypto/des3_ede-asm_64.S | 4 +- arch/x86/crypto/ghash-clmulni-intel_asm.S | 6 +- arch/x86/crypto/nh-avx2-x86_64.S | 2 +- arch/x86/crypto/nh-sse2-x86_64.S | 2 +- arch/x86/crypto/poly1305-x86_64-cryptogams.pl | 38 +- arch/x86/crypto/serpent-avx-x86_64-asm_64.S | 16 +- arch/x86/crypto/serpent-avx2-asm_64.S | 16 +- arch/x86/crypto/serpent-sse2-i586-asm_32.S | 6 +- arch/x86/crypto/serpent-sse2-x86_64-asm_64.S | 6 +- arch/x86/crypto/sha1_avx2_x86_64_asm.S | 2 +- arch/x86/crypto/sha1_ni_asm.S | 2 +- arch/x86/crypto/sha1_ssse3_asm.S | 2 +- arch/x86/crypto/sha256-avx-asm.S | 2 +- arch/x86/crypto/sha256-avx2-asm.S | 2 +- arch/x86/crypto/sha256-ssse3-asm.S | 2 +- arch/x86/crypto/sha256_ni_asm.S | 2 +- arch/x86/crypto/sha512-avx-asm.S | 2 +- arch/x86/crypto/sha512-avx2-asm.S | 2 +- arch/x86/crypto/sha512-ssse3-asm.S | 2 +- arch/x86/crypto/twofish-avx-x86_64-asm_64.S | 16 +- arch/x86/crypto/twofish-i586-asm_32.S | 4 +- arch/x86/crypto/twofish-x86_64-asm_64-3way.S | 6 +- arch/x86/crypto/twofish-x86_64-asm_64.S | 4 +- arch/x86/entry/Makefile | 2 +- arch/x86/entry/calling.h | 72 +- arch/x86/entry/entry.S | 22 + arch/x86/entry/entry_32.S | 6 +- arch/x86/entry/entry_64.S | 62 +- arch/x86/entry/entry_64_compat.S | 21 +- arch/x86/entry/thunk_32.S | 2 +- arch/x86/entry/thunk_64.S | 2 +- arch/x86/entry/vdso/Makefile | 1 + arch/x86/entry/vdso/vdso32/system_call.S | 4 +- arch/x86/entry/vsyscall/vsyscall_emu_64.S | 3 + arch/x86/include/asm/GEN-for-each-reg.h | 14 +- arch/x86/include/asm/alternative-asm.h | 114 -- arch/x86/include/asm/alternative.h | 133 +- arch/x86/include/asm/asm-prototypes.h | 17 - arch/x86/include/asm/cpufeature.h | 41 +- arch/x86/include/asm/cpufeatures.h | 12 +- arch/x86/include/asm/disabled-features.h | 21 +- arch/x86/include/asm/inat.h | 2 +- arch/x86/include/asm/insn-eval.h | 4 +- arch/x86/include/asm/insn.h | 28 +- arch/x86/include/asm/linkage.h | 22 + arch/x86/include/asm/msr-index.h | 13 + arch/x86/include/asm/nospec-branch.h | 148 ++- arch/x86/include/asm/paravirt.h | 2 +- arch/x86/include/asm/qspinlock_paravirt.h | 4 +- arch/x86/include/asm/smap.h | 5 +- arch/x86/include/asm/static_call.h | 19 +- arch/x86/include/asm/unwind_hints.h | 23 +- arch/x86/kernel/acpi/wakeup_32.S | 6 +- arch/x86/kernel/alternative.c | 356 +++++- arch/x86/kernel/cpu/amd.c | 46 +- arch/x86/kernel/cpu/bugs.c | 475 ++++++- arch/x86/kernel/cpu/common.c | 61 +- arch/x86/kernel/cpu/cpu.h | 2 + arch/x86/kernel/cpu/hygon.c | 6 + arch/x86/kernel/cpu/scattered.c | 1 + arch/x86/kernel/ftrace.c | 7 +- arch/x86/kernel/ftrace_32.S | 6 +- arch/x86/kernel/ftrace_64.S | 13 +- arch/x86/kernel/head_32.S | 2 +- arch/x86/kernel/head_64.S | 5 + arch/x86/kernel/irqflags.S | 4 +- arch/x86/kernel/kprobes/core.c | 2 +- arch/x86/kernel/kvm.c | 2 +- arch/x86/kernel/module.c | 15 +- arch/x86/kernel/paravirt.c | 2 +- arch/x86/kernel/process.c | 2 +- arch/x86/kernel/relocate_kernel_32.S | 15 +- arch/x86/kernel/relocate_kernel_64.S | 13 +- arch/x86/kernel/sev-es.c | 2 +- arch/x86/kernel/sev_verify_cbit.S | 2 +- arch/x86/kernel/static_call.c | 52 +- arch/x86/kernel/umip.c | 2 +- arch/x86/kernel/verify_cpu.S | 4 +- arch/x86/kernel/vmlinux.lds.S | 23 +- arch/x86/kvm/emulate.c | 39 +- arch/x86/kvm/svm/vmenter.S | 11 +- arch/x86/kvm/vmx/nested.c | 32 +- arch/x86/kvm/vmx/run_flags.h | 8 + arch/x86/kvm/vmx/vmenter.S | 170 +-- arch/x86/kvm/vmx/vmx.c | 78 +- arch/x86/kvm/vmx/vmx.h | 5 + arch/x86/kvm/x86.c | 4 +- arch/x86/lib/atomic64_386_32.S | 88 +- arch/x86/lib/atomic64_cx8_32.S | 18 +- arch/x86/lib/checksum_32.S | 8 +- arch/x86/lib/clear_page_64.S | 6 +- arch/x86/lib/cmpxchg16b_emu.S | 4 +- arch/x86/lib/cmpxchg8b_emu.S | 4 +- arch/x86/lib/copy_mc_64.S | 6 +- arch/x86/lib/copy_page_64.S | 10 +- arch/x86/lib/copy_user_64.S | 14 +- arch/x86/lib/csum-copy_64.S | 2 +- arch/x86/lib/error-inject.c | 3 +- arch/x86/lib/getuser.S | 22 +- arch/x86/lib/hweight.S | 6 +- arch/x86/lib/inat.c | 2 +- arch/x86/lib/insn-eval.c | 6 +- arch/x86/lib/insn.c | 222 +++- arch/x86/lib/iomap_copy_64.S | 2 +- arch/x86/lib/memcpy_64.S | 14 +- arch/x86/lib/memmove_64.S | 11 +- arch/x86/lib/memset_64.S | 8 +- arch/x86/lib/msr-reg.S | 4 +- arch/x86/lib/putuser.S | 6 +- arch/x86/lib/retpoline.S | 118 +- arch/x86/math-emu/div_Xsig.S | 2 +- arch/x86/math-emu/div_small.S | 2 +- arch/x86/math-emu/mul_Xsig.S | 6 +- arch/x86/math-emu/polynom_Xsig.S | 2 +- arch/x86/math-emu/reg_norm.S | 6 +- arch/x86/math-emu/reg_round.S | 2 +- arch/x86/math-emu/reg_u_add.S | 2 +- arch/x86/math-emu/reg_u_div.S | 2 +- arch/x86/math-emu/reg_u_mul.S | 2 +- arch/x86/math-emu/reg_u_sub.S | 2 +- arch/x86/math-emu/round_Xsig.S | 4 +- arch/x86/math-emu/shr_Xsig.S | 8 +- arch/x86/math-emu/wm_shrx.S | 16 +- arch/x86/mm/mem_encrypt_boot.S | 6 + arch/x86/net/bpf_jit_comp.c | 185 ++- arch/x86/net/bpf_jit_comp32.c | 22 +- arch/x86/platform/efi/efi_stub_32.S | 2 +- arch/x86/platform/efi/efi_stub_64.S | 2 +- arch/x86/platform/efi/efi_thunk_64.S | 5 +- arch/x86/platform/olpc/xo1-wakeup.S | 6 +- arch/x86/power/hibernate_asm_32.S | 4 +- arch/x86/power/hibernate_asm_64.S | 4 +- arch/x86/um/checksum_32.S | 4 +- arch/x86/um/setjmp_32.S | 2 +- arch/x86/um/setjmp_64.S | 2 +- arch/x86/xen/Makefile | 1 - arch/x86/xen/setup.c | 6 +- arch/x86/xen/xen-asm.S | 43 +- arch/x86/xen/xen-head.S | 6 +- arch/x86/xen/xen-ops.h | 6 +- drivers/base/cpu.c | 8 + drivers/idle/intel_idle.c | 43 +- include/linux/cpu.h | 2 + include/linux/kvm_host.h | 2 +- include/linux/objtool.h | 14 +- samples/ftrace/ftrace-direct-modify.c | 4 +- samples/ftrace/ftrace-direct-too.c | 2 +- samples/ftrace/ftrace-direct.c | 2 +- scripts/Makefile.build | 6 + scripts/link-vmlinux.sh | 6 + security/Kconfig | 11 - tools/arch/x86/include/asm/cpufeatures.h | 12 +- .../arch/x86/include/asm/disabled-features.h | 21 +- tools/arch/x86/include/asm/inat.h | 2 +- tools/arch/x86/include/asm/insn.h | 28 +- tools/arch/x86/include/asm/msr-index.h | 13 + tools/arch/x86/lib/inat.c | 2 +- tools/arch/x86/lib/insn.c | 222 +++- tools/arch/x86/lib/memcpy_64.S | 14 +- tools/arch/x86/lib/memset_64.S | 8 +- .../asm/{alternative-asm.h => alternative.h} | 0 tools/include/linux/kconfig.h | 67 + tools/include/linux/objtool.h | 14 +- .../Documentation/stack-validation.txt | 16 +- tools/objtool/Makefile | 4 - tools/objtool/arch.h | 13 +- tools/objtool/arch/x86/decode.c | 58 +- tools/objtool/builtin-check.c | 6 +- tools/objtool/builtin-orc.c | 6 +- tools/objtool/builtin.h | 3 +- tools/objtool/cfi.h | 2 + tools/objtool/check.c | 1131 +++++++++++++---- tools/objtool/check.h | 35 +- tools/objtool/elf.c | 230 ++-- tools/objtool/elf.h | 20 +- tools/objtool/objtool.c | 2 + tools/objtool/objtool.h | 5 +- tools/objtool/orc_gen.c | 324 ++--- tools/objtool/special.c | 22 +- tools/objtool/sync-check.sh | 17 +- tools/objtool/weak.c | 7 +- tools/perf/check-headers.sh | 15 +- 207 files changed, 4323 insertions(+), 1902 deletions(-) create mode 100644 arch/x86/entry/entry.S delete mode 100644 arch/x86/include/asm/alternative-asm.h create mode 100644 arch/x86/kvm/vmx/run_flags.h rename tools/include/asm/{alternative-asm.h => alternative.h} (100%) create mode 100644 tools/include/linux/kconfig.h -- 2.20.1

1 137

[PATCH openEuler-1.0-LTS] KVM: x86: do not report a vCPU as preempted outside instruction boundaries
by Yongqiang Liu 14 Sep '22

14 Sep '22

From: Paolo Bonzini <pbonzini(a)redhat.com> mainline inclusion from mainline-v5.19-rc2 commit 6cd88243c7e03845a450795e134b488fc2afb736 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I5PJ7H CVE: CVE-2022-39189 ---------------------------------------- If a vCPU is outside guest mode and is scheduled out, it might be in the process of making a memory access. A problem occurs if another vCPU uses the PV TLB flush feature during the period when the vCPU is scheduled out, and a virtual address has already been translated but has not yet been accessed, because this is equivalent to using a stale TLB entry. To avoid this, only report a vCPU as preempted if sure that the guest is at an instruction boundary. A rescheduling request will be delivered to the host physical CPU as an external interrupt, so for simplicity consider any vmexit *not* instruction boundary except for external interrupts. It would in principle be okay to report the vCPU as preempted also if it is sleeping in kvm_vcpu_block(): a TLB flush IPI will incur the vmentry/vmexit overhead unnecessarily, and optimistic spinning is also unlikely to succeed. However, leave it for later because right now kvm_vcpu_check_block() is doing memory accesses. Even though the TLB flush issue only applies to virtual memory address, it's very much preferrable to be conservative. Reported-by: Jann Horn <jannh(a)google.com> Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> conflict: arch/x86/include/asm/kvm_host.h arch/x86/kvm/svm.c arch/x86/kvm/vmx.c arch/x86/kvm/x86.c Signed-off-by: Guo Mengqi <guomengqi3(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Reviewed-by: Weilong Chen <chenweilong(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- arch/x86/include/asm/kvm_host.h | 3 +++ arch/x86/kvm/svm.c | 3 +++ arch/x86/kvm/vmx.c | 1 + arch/x86/kvm/x86.c | 25 +++++++++++++++++++++++++ 4 files changed, 32 insertions(+) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 6549c20c958c..7afb2cb2d42c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -520,6 +520,7 @@ struct kvm_vcpu_arch { u64 ia32_misc_enable_msr; u64 smbase; u64 smi_count; + bool at_instruction_boundary; bool tpr_access_reporting; u64 ia32_xss; u64 microcode_version; @@ -935,6 +936,8 @@ struct kvm_vcpu_stat { u64 utime; u64 stime; u64 gtime; + u64 preemption_reported; + u64 preemption_other; }; struct x86_instruction_info; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 46567343680f..f611ecdfc145 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -6205,6 +6205,9 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu, static void svm_handle_external_intr(struct kvm_vcpu *vcpu) { + if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_INTR) + vcpu->arch.at_instruction_boundary = true; + local_irq_enable(); /* * We must have an instruction with interrupts enabled, so diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 7ab18b5a8e96..4164016cf105 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -10597,6 +10597,7 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) [cs]"i"(__KERNEL_CS) ); } + vcpu->arch.at_instruction_boundary = true; } STACK_FRAME_NON_STANDARD(vmx_handle_external_intr); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 5da2811219ec..c61cab768d2a 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -186,6 +186,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "halt_successful_poll", VCPU_STAT(halt_successful_poll) }, { "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) }, { "halt_poll_invalid", VCPU_STAT(halt_poll_invalid) }, + { "preemption_reported", VCPU_STAT(preemption_reported) }, + { "preemption_other", VCPU_STAT(preemption_other) }, { "halt_wakeup", VCPU_STAT(halt_wakeup) }, { "hypercalls", VCPU_STAT(hypercalls) }, { "request_irq", VCPU_STAT(request_irq_exits) }, @@ -231,6 +233,8 @@ struct dfx_kvm_stats_debugfs_item dfx_debugfs_entries[] = { DFX_STAT("halt_exits", halt_exits), DFX_STAT("halt_successful_poll", halt_successful_poll), DFX_STAT("halt_attempted_poll", halt_attempted_poll), + DFX_STAT("preemption_reported", preemption_reported), + DFX_STAT("preemption_other", preemption_other), DFX_STAT("halt_wakeup", halt_wakeup), DFX_STAT("request_irq", request_irq_exits), DFX_STAT("irq_exits", irq_exits), @@ -3314,6 +3318,20 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) { + /* + * The vCPU can be marked preempted if and only if the VM-Exit was on + * an instruction boundary and will not trigger guest emulation of any + * kind (see vcpu_run). Vendor specific code controls (conservatively) + * when this is true, for example allowing the vCPU to be marked + * preempted if and only if the VM-Exit was due to a host interrupt. + */ + if (!vcpu->arch.at_instruction_boundary) { + vcpu->stat.preemption_other++; + return; + } + + vcpu->stat.preemption_reported++; + if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; @@ -7920,6 +7938,13 @@ static int vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.l1tf_flush_l1d = true; for (;;) { + /* + * If another guest vCPU requests a PV TLB flush in the middle + * of instruction emulation, the rest of the emulation could + * use a stale page translation. Assume that any code after + * this point can start executing an instruction. + */ + vcpu->arch.at_instruction_boundary = false; if (kvm_vcpu_running(vcpu)) { r = vcpu_enter_guest(vcpu); } else { -- 2.25.1

1 0

[PATCH] KVM: arm64: Write arch.mdcr_el2 changes since last vcpu_load on VHE
by Laibin Qiu 14 Sep '22

14 Sep '22

From: Andrew Murray <andrew.murray(a)arm.com> mainline inclusion from mainline-v5.6 commit 4942dc6638b07b5326b6d2faa142635c559e7cd5 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5QR6C CVE: NA ------------- On VHE systems arch.mdcr_el2 is written to mdcr_el2 at vcpu_load time to set options for self-hosted debug and the performance monitors extension. Unfortunately the value of arch.mdcr_el2 is not calculated until kvm_arm_setup_debug() in the run loop after the vcpu has been loaded. This means that the initial brief iterations of the run loop use a zero value of mdcr_el2 - until the vcpu is preempted. This also results in a delay between changes to vcpu->guest_debug taking effect. Fix this by writing to mdcr_el2 in kvm_arm_setup_debug() on VHE systems when a change to arch.mdcr_el2 has been detected. Fixes: d5a21bcc2995 ("KVM: arm64: Move common VHE/non-VHE trap config in separate functions") Cc: <stable(a)vger.kernel.org> # 4.17.x- Suggested-by: James Morse <james.morse(a)arm.com> Acked-by: Will Deacon <will(a)kernel.org> Reviewed-by: Marc Zyngier <maz(a)kernel.org> Signed-off-by: Andrew Murray <andrew.murray(a)arm.com> Signed-off-by: Catalin Marinas <catalin.marinas(a)arm.com> Signed-off-by: Zengruan Ye <yezengruan(a)huawei.com> Reviewed-by: Keqian Zhu <zhukeqian1(a)huawei.com> Signed-off-by: Laibin Qiu <qiulaibin(a)huawei.com> --- arch/arm64/kvm/debug.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c index 00d422336a45..4e722d73a3c3 100644 --- a/arch/arm64/kvm/debug.c +++ b/arch/arm64/kvm/debug.c @@ -112,7 +112,7 @@ void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) { bool trap_debug = !(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY); - unsigned long mdscr; + unsigned long mdscr, orig_mdcr_el2 = vcpu->arch.mdcr_el2; trace_kvm_arm_setup_debug(vcpu, vcpu->guest_debug); @@ -208,6 +208,10 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) if (vcpu_read_sys_reg(vcpu, MDSCR_EL1) & (DBG_MDSCR_KDE | DBG_MDSCR_MDE)) vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY; + /* Write mdcr_el2 changes since vcpu_load on VHE systems */ + if (has_vhe() && orig_mdcr_el2 != vcpu->arch.mdcr_el2) + write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2); + trace_kvm_arm_set_dreg32("MDCR_EL2", vcpu->arch.mdcr_el2); trace_kvm_arm_set_dreg32("MDSCR_EL1", vcpu_read_sys_reg(vcpu, MDSCR_EL1)); } -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] perf bench futex-wake: Restore thread count default to online CPU count
by tangbin 13 Sep '22

13 Sep '22

From: Tommi Rantala <tommi.t.rantala(a)nokia.com> stable inclusion from stable-v4.19.111 commit 5e8dff99645e574122aef5dec91b8803339a6362 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5QSAP CVE: NA -------------------------------- commit f649bd9dd5d5004543bbc3c50b829577b49f5d75 upstream. Since commit 3b2323c2c1c4 ("perf bench futex: Use cpumaps") the default number of threads the benchmark uses got changed from number of online CPUs to zero: $ perf bench futex wake # Running 'futex/wake' benchmark: Run summary [PID 15930]: blocking on 0 threads (at [private] futex 0x558b8ee4bfac), waking up 1 at a time. [Run 1]: Wokeup 0 of 0 threads in 0.0000 ms [...] [Run 10]: Wokeup 0 of 0 threads in 0.0000 ms Wokeup 0 of 0 threads in 0.0004 ms (+-40.82%) Restore the old behavior by grabbing the number of online CPUs via cpu->nr: $ perf bench futex wake # Running 'futex/wake' benchmark: Run summary [PID 18356]: blocking on 8 threads (at [private] futex 0xb3e62c), waking up 1 at a time. [Run 1]: Wokeup 8 of 8 threads in 0.0260 ms [...] [Run 10]: Wokeup 8 of 8 threads in 0.0270 ms Wokeup 8 of 8 threads in 0.0419 ms (+-24.35%) Fixes: 3b2323c2c1c4 ("perf bench futex: Use cpumaps") Signed-off-by: Tommi Rantala <tommi.t.rantala(a)nokia.com> Tested-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> Cc: Alexander Shishkin <alexander.shishkin(a)linux.intel.com> Cc: Darren Hart <dvhart(a)infradead.org> Cc: Davidlohr Bueso <dave(a)stgolabs.net> Cc: Jiri Olsa <jolsa(a)redhat.com> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Namhyung Kim <namhyung(a)kernel.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Link: http://lore.kernel.org/lkml/20200305083714.9381-3-tommi.t.rantala@nokia.com Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: tangbin <tangbin(a)cmss.chinamobile.com> --- tools/perf/bench/futex-wake.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c index e8181ad7d088..e62006342b18 100644 --- a/tools/perf/bench/futex-wake.c +++ b/tools/perf/bench/futex-wake.c @@ -42,7 +42,7 @@ static bool done = false, silent = false, fshared = false; static pthread_mutex_t thread_lock; static pthread_cond_t thread_parent, thread_worker; static struct stats waketime_stats, wakeup_stats; -static unsigned int ncpus, threads_starting, nthreads = 0; +static unsigned int threads_starting, nthreads = 0; static int futex_flag = 0; static const struct option options[] = { @@ -140,7 +140,7 @@ int bench_futex_wake(int argc, const char **argv) sigaction(SIGINT, &act, NULL); if (!nthreads) - nthreads = ncpus; + nthreads = cpu->nr; worker = calloc(nthreads, sizeof(*worker)); if (!worker) -- 2.18.4

1 0

[PATCH openEuler-1.0-LTS] netfilter: nf_conntrack_irc: Tighten matching on DCC message
by Yongqiang Liu 13 Sep '22

13 Sep '22

From: David Leadbeater <dgl(a)dgl.cx> mainline inclusion from mainline-v6.0-rc6 commit e8d5dfd1d8747b56077d02664a8838c71ced948e category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I5OWZ7 CVE: CVE-2022-2663 --------------------------- CTCP messages should only be at the start of an IRC message, not anywhere within it. While the helper only decodes packes in the ORIGINAL direction, its possible to make a client send a CTCP message back by empedding one into a PING request. As-is, thats enough to make the helper believe that it saw a CTCP message. Fixes: 869f37d8e48f ("[NETFILTER]: nf_conntrack/nf_nat: add IRC helper port") Signed-off-by: David Leadbeater <dgl(a)dgl.cx> Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Liu Jian <liujian56(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- net/netfilter/nf_conntrack_irc.c | 34 ++++++++++++++++++++++++++------ 1 file changed, 28 insertions(+), 6 deletions(-) diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c index 4099f4d79bae..819fc0df233f 100644 --- a/net/netfilter/nf_conntrack_irc.c +++ b/net/netfilter/nf_conntrack_irc.c @@ -150,15 +150,37 @@ static int help(struct sk_buff *skb, unsigned int protoff, data = ib_ptr; data_limit = ib_ptr + skb->len - dataoff; - /* strlen("\1DCC SENT t AAAAAAAA P\1\n")=24 - * 5+MINMATCHLEN+strlen("t AAAAAAAA P\1\n")=14 */ - while (data < data_limit - (19 + MINMATCHLEN)) { - if (memcmp(data, "\1DCC ", 5)) { + /* Skip any whitespace */ + while (data < data_limit - 10) { + if (*data == ' ' || *data == '\r' || *data == '\n') + data++; + else + break; + } + + /* strlen("PRIVMSG x ")=10 */ + if (data < data_limit - 10) { + if (strncasecmp("PRIVMSG ", data, 8)) + goto out; + data += 8; + } + + /* strlen(" :\1DCC SENT t AAAAAAAA P\1\n")=26 + * 7+MINMATCHLEN+strlen("t AAAAAAAA P\1\n")=26 + */ + while (data < data_limit - (21 + MINMATCHLEN)) { + /* Find first " :", the start of message */ + if (memcmp(data, " :", 2)) { data++; continue; } + data += 2; + + /* then check that place only for the DCC command */ + if (memcmp(data, "\1DCC ", 5)) + goto out; data += 5; - /* we have at least (19+MINMATCHLEN)-5 bytes valid data left */ + /* we have at least (21+MINMATCHLEN)-(2+5) bytes valid data left */ iph = ip_hdr(skb); pr_debug("DCC found in master %pI4:%u %pI4:%u\n", @@ -174,7 +196,7 @@ static int help(struct sk_buff *skb, unsigned int protoff, pr_debug("DCC %s detected\n", dccprotos[i]); /* we have at least - * (19+MINMATCHLEN)-5-dccprotos[i].matchlen bytes valid + * (21+MINMATCHLEN)-7-dccprotos[i].matchlen bytes valid * data left (== 14/13 bytes) */ if (parse_dcc(data, data_limit, &dcc_ip, &dcc_port, &addr_beg_p, &addr_end_p)) { -- 2.25.1

1 0