From: Riccardo Mancini <rickyman7@gmail.com> mainline inclusion from mainline-5.13-rc4 commit 67069a1f0fe5f9eeca86d954fff2087f5542a008 category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... --------------------------- ASan reported a memory leak caused by info_linear not being deallocated. The info_linear was allocated during in perf_event__synthesize_one_bpf_prog(). This patch adds the corresponding free() when bpf_prog_info_node is freed in perf_env__purge_bpf(). $ sudo ./perf record -- sleep 5 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.025 MB perf.data (8 samples) ] ================================================================= ==297735==ERROR: LeakSanitizer: detected memory leaks Direct leak of 7688 byte(s) in 19 object(s) allocated from: #0 0x4f420f in malloc (/home/user/linux/tools/perf/perf+0x4f420f) #1 0xc06a74 in bpf_program__get_prog_info_linear /home/user/linux/tools/lib/bpf/libbpf.c:11113:16 #2 0xb426fe in perf_event__synthesize_one_bpf_prog /home/user/linux/tools/perf/util/bpf-event.c:191:16 #3 0xb42008 in perf_event__synthesize_bpf_events /home/user/linux/tools/perf/util/bpf-event.c:410:9 #4 0x594596 in record__synthesize /home/user/linux/tools/perf/builtin-record.c:1490:8 #5 0x58c9ac in __cmd_record /home/user/linux/tools/perf/builtin-record.c:1798:8 #6 0x58990b in cmd_record /home/user/linux/tools/perf/builtin-record.c:2901:8 #7 0x7b2a20 in run_builtin /home/user/linux/tools/perf/perf.c:313:11 #8 0x7b12ff in handle_internal_command /home/user/linux/tools/perf/perf.c:365:8 #9 0x7b2583 in run_argv /home/user/linux/tools/perf/perf.c:409:2 #10 0x7b0d79 in main /home/user/linux/tools/perf/perf.c:539:3 #11 0x7fa357ef6b74 in __libc_start_main /usr/src/debug/glibc-2.33-8.fc34.x86_64/csu/../csu/libc-start.c:332:16 Signed-off-by: Riccardo Mancini <rickyman7@gmail.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Jiri Olsa <jolsa@redhat.com> Cc: John Fastabend <john.fastabend@gmail.com> Cc: KP Singh <kpsingh@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Yonghong Song <yhs@fb.com> Link: http://lore.kernel.org/lkml/20210602224024.300485-1-rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Yang Jihong <yangjihong1@huawei.com> Reviewed-by: Kuohai Xu <xukuohai@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- tools/perf/util/env.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 03bc843b1cf8..f0dceb527ca3 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -142,6 +142,7 @@ static void perf_env__purge_bpf(struct perf_env *env) node = rb_entry(next, struct bpf_prog_info_node, rb_node); next = rb_next(&node->rb_node); rb_erase(&node->rb_node, root); + free(node->info_linear); free(node); } -- 2.22.0

From: Arnaldo Carvalho de Melo <acme@redhat.com> mainline inclusion from mainline-5.13-rc3 commit 3b2f17ad1770e51b8b4e68b5069c4f1ee477eff8 category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... --------------------------- To avoid a NULL pointer dereference when the kernel supports the new feature but the tooling still hasn't an entry for it. This happened with the recently added PERF_COUNT_SW_CGROUP_SWITCHES software event. Reported-by: Thomas Richter <tmricht@linux.ibm.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Sumanth Korikkar <sumanthk@linux.ibm.com> Link: https://lore.kernel.org/linux-perf-users/YKVESEKRjKtILhog@kernel.org/ Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Yang Jihong <yangjihong1@huawei.com> Reviewed-by: Kuohai Xu <xukuohai@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- tools/perf/util/parse-events.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 3b273580fb84..61bbbbeb9d3d 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -2810,9 +2810,14 @@ void print_symbol_events(const char *event_glob, unsigned type, } for (i = 0; i < max; i++, syms++) { + /* + * New attr.config still not supported here, the latest + * example was PERF_COUNT_SW_CGROUP_SWITCHES + */ + if (syms->symbol == NULL) + continue; - if (event_glob != NULL && syms->symbol != NULL && - !(strglobmatch(syms->symbol, event_glob) || + if (event_glob != NULL && !(strglobmatch(syms->symbol, event_glob) || (syms->alias && strglobmatch(syms->alias, event_glob)))) continue; -- 2.22.0

From: Jianlin Lv <Jianlin.Lv@arm.com> mainline inclusion from mainline-5.12-rc1 commit 067012974c8ae31a8886046df082aeba93592972 category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... --------------------------- gcc version: 11.0.0 20210208 (experimental) (GCC) Following build error on arm64: ....... In function ‘printf’, inlined from ‘regs_dump__printf’ at util/session.c:1141:3, inlined from ‘regs__printf’ at util/session.c:1169:2: /usr/include/aarch64-linux-gnu/bits/stdio2.h:107:10: \ error: ‘%-5s’ directive argument is null [-Werror=format-overflow=] 107 | return __printf_chk (__USE_FORTIFY_LEVEL - 1, __fmt, \ __va_arg_pack ()); ...... In function ‘fprintf’, inlined from ‘perf_sample__fprintf_regs.isra’ at \ builtin-script.c:622:14: /usr/include/aarch64-linux-gnu/bits/stdio2.h:100:10: \ error: ‘%5s’ directive argument is null [-Werror=format-overflow=] 100 | return __fprintf_chk (__stream, __USE_FORTIFY_LEVEL - 1, __fmt, 101 | __va_arg_pack ()); cc1: all warnings being treated as errors ....... This patch fixes Wformat-overflow warnings. Add helper function to convert NULL to "unknown". Signed-off-by: Jianlin Lv <Jianlin.Lv@arm.com> Reviewed-by: John Garry <john.garry@huawei.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Anju T Sudhakar <anju@linux.vnet.ibm.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Guo Ren <guoren@kernel.org> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Poirier <mathieu.poirier@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Cc: Will Deacon <will@kernel.org> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: iecedge@gmail.com Cc: linux-csky@vger.kernel.org Cc: linux-riscv@lists.infradead.org Link: http://lore.kernel.org/lkml/20210218031245.2078492-1-Jianlin.Lv@arm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Yang Jihong <yangjihong1@huawei.com> Reviewed-by: Kuohai Xu <xukuohai@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- tools/perf/arch/arm/include/perf_regs.h | 2 +- tools/perf/arch/arm64/include/perf_regs.h | 2 +- tools/perf/arch/csky/include/perf_regs.h | 2 +- tools/perf/arch/powerpc/include/perf_regs.h | 2 +- tools/perf/arch/riscv/include/perf_regs.h | 2 +- tools/perf/arch/s390/include/perf_regs.h | 2 +- tools/perf/arch/x86/include/perf_regs.h | 2 +- tools/perf/util/perf_regs.h | 7 +++++++ 8 files changed, 14 insertions(+), 7 deletions(-) diff --git a/tools/perf/arch/arm/include/perf_regs.h b/tools/perf/arch/arm/include/perf_regs.h index ed20e0253e25..4085419283d0 100644 --- a/tools/perf/arch/arm/include/perf_regs.h +++ b/tools/perf/arch/arm/include/perf_regs.h @@ -15,7 +15,7 @@ void perf_regs_load(u64 *regs); #define PERF_REG_IP PERF_REG_ARM_PC #define PERF_REG_SP PERF_REG_ARM_SP -static inline const char *perf_reg_name(int id) +static inline const char *__perf_reg_name(int id) { switch (id) { case PERF_REG_ARM_R0: diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h index baaa5e64a3fb..fa3e07459f76 100644 --- a/tools/perf/arch/arm64/include/perf_regs.h +++ b/tools/perf/arch/arm64/include/perf_regs.h @@ -15,7 +15,7 @@ void perf_regs_load(u64 *regs); #define PERF_REG_IP PERF_REG_ARM64_PC #define PERF_REG_SP PERF_REG_ARM64_SP -static inline const char *perf_reg_name(int id) +static inline const char *__perf_reg_name(int id) { switch (id) { case PERF_REG_ARM64_X0: diff --git a/tools/perf/arch/csky/include/perf_regs.h b/tools/perf/arch/csky/include/perf_regs.h index 8f336ea1161a..25ac3bdcb9d1 100644 --- a/tools/perf/arch/csky/include/perf_regs.h +++ b/tools/perf/arch/csky/include/perf_regs.h @@ -15,7 +15,7 @@ #define PERF_REG_IP PERF_REG_CSKY_PC #define PERF_REG_SP PERF_REG_CSKY_SP -static inline const char *perf_reg_name(int id) +static inline const char *__perf_reg_name(int id) { switch (id) { case PERF_REG_CSKY_A0: diff --git a/tools/perf/arch/powerpc/include/perf_regs.h b/tools/perf/arch/powerpc/include/perf_regs.h index 63f3ac91049f..004bed228693 100644 --- a/tools/perf/arch/powerpc/include/perf_regs.h +++ b/tools/perf/arch/powerpc/include/perf_regs.h @@ -73,7 +73,7 @@ static const char *reg_names[] = { [PERF_REG_POWERPC_SIER3] = "sier3", }; -static inline const char *perf_reg_name(int id) +static inline const char *__perf_reg_name(int id) { return reg_names[id]; } diff --git a/tools/perf/arch/riscv/include/perf_regs.h b/tools/perf/arch/riscv/include/perf_regs.h index 7a8bcde7a2b1..6b02a767c918 100644 --- a/tools/perf/arch/riscv/include/perf_regs.h +++ b/tools/perf/arch/riscv/include/perf_regs.h @@ -19,7 +19,7 @@ #define PERF_REG_IP PERF_REG_RISCV_PC #define PERF_REG_SP PERF_REG_RISCV_SP -static inline const char *perf_reg_name(int id) +static inline const char *__perf_reg_name(int id) { switch (id) { case PERF_REG_RISCV_PC: diff --git a/tools/perf/arch/s390/include/perf_regs.h b/tools/perf/arch/s390/include/perf_regs.h index bcfbaed78cc2..ce3031526623 100644 --- a/tools/perf/arch/s390/include/perf_regs.h +++ b/tools/perf/arch/s390/include/perf_regs.h @@ -14,7 +14,7 @@ void perf_regs_load(u64 *regs); #define PERF_REG_IP PERF_REG_S390_PC #define PERF_REG_SP PERF_REG_S390_R15 -static inline const char *perf_reg_name(int id) +static inline const char *__perf_reg_name(int id) { switch (id) { case PERF_REG_S390_R0: diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h index b7321337d100..cddc4cdc0d9b 100644 --- a/tools/perf/arch/x86/include/perf_regs.h +++ b/tools/perf/arch/x86/include/perf_regs.h @@ -23,7 +23,7 @@ void perf_regs_load(u64 *regs); #define PERF_REG_IP PERF_REG_X86_IP #define PERF_REG_SP PERF_REG_X86_SP -static inline const char *perf_reg_name(int id) +static inline const char *__perf_reg_name(int id) { switch (id) { case PERF_REG_X86_AX: diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h index a45499126184..eeac181ebccf 100644 --- a/tools/perf/util/perf_regs.h +++ b/tools/perf/util/perf_regs.h @@ -33,6 +33,13 @@ extern const struct sample_reg sample_reg_masks[]; int perf_reg_value(u64 *valp, struct regs_dump *regs, int id); +static inline const char *perf_reg_name(int id) +{ + const char *reg_name = __perf_reg_name(id); + + return reg_name ?: "unknown"; +} + #else #define PERF_REGS_MASK 0 #define PERF_REGS_MAX 0 -- 2.22.0

From: Athira Rajeev <atrajeev@linux.vnet.ibm.com> mainline inclusion from mainline-5.11-rc1 commit f66de7ac4849eb42a7b18e26b8ee49e08130fd27 category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... --------------------------- The power_pmu_event_init() callback access per-cpu variable (cpu_hw_events) to check for event constraints and Branch Stack (BHRB). Current usage is to disable preemption when accessing the per-cpu variable, but this does not prevent timer callback from interrupting event_init. Fix this by using 'local_irq_save/restore' to make sure the code path is invoked with disabled interrupts. This change is tested in mambo simulator to ensure that, if a timer interrupt comes in during the per-cpu access in event_init, it will be soft masked and replayed later. For testing purpose, introduced a udelay() in power_pmu_event_init() to make sure a timer interrupt arrives while in per-cpu variable access code between local_irq_save/resore. As expected the timer interrupt was replayed later during local_irq_restore called from power_pmu_event_init. This was confirmed by adding breakpoint in mambo and checking the backtrace when timer_interrupt was hit. Reported-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/1606814880-1720-1-git-send-email-atrajeev@linux.vn... Signed-off-by: Yang Jihong <yangjihong1@huawei.com> Reviewed-by: Kuohai Xu <xukuohai@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/powerpc/perf/core-book3s.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index ded4a3efd3f0..91452313489f 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1884,7 +1884,7 @@ static bool is_event_blacklisted(u64 ev) static int power_pmu_event_init(struct perf_event *event) { u64 ev; - unsigned long flags; + unsigned long flags, irq_flags; struct perf_event *ctrs[MAX_HWEVENTS]; u64 events[MAX_HWEVENTS]; unsigned int cflags[MAX_HWEVENTS]; @@ -1992,7 +1992,9 @@ static int power_pmu_event_init(struct perf_event *event) if (check_excludes(ctrs, cflags, n, 1)) return -EINVAL; - cpuhw = &get_cpu_var(cpu_hw_events); + local_irq_save(irq_flags); + cpuhw = this_cpu_ptr(&cpu_hw_events); + err = power_check_constraints(cpuhw, events, cflags, n + 1); if (has_branch_stack(event)) { @@ -2003,13 +2005,13 @@ static int power_pmu_event_init(struct perf_event *event) event->attr.branch_sample_type); if (bhrb_filter == -1) { - put_cpu_var(cpu_hw_events); + local_irq_restore(irq_flags); return -EOPNOTSUPP; } cpuhw->bhrb_filter = bhrb_filter; } - put_cpu_var(cpu_hw_events); + local_irq_restore(irq_flags); if (err) return -EINVAL; -- 2.22.0

From: Jia Cheng Hu <jia.jiachenghu@gmail.com> mainline inclusion from mainline-v5.12-rc1 commit d4fc3640ff361a09e359867e0bca898abd2b7ecb category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ----------------------------------------------- Since commit c5089591c3ba ("block, bfq: detect wakers and unconditionally inject their I/O"), when the in-service bfq_queue, say Q, is temporarily empty, BFQ checks whether there are I/O requests to inject (also) from the waker bfq_queue for Q. To this goal, the value pointed by bfqq->waker_bfqq->next_rq must be controlled. However, the current implementation mistakenly looks at bfqq->next_rq, which instead points to the next request of the currently served queue. This mistake evidently causes losses of throughput in scenarios with waker bfq_queues. This commit corrects this mistake. Fixes: c5089591c3ba ("block, bfq: detect wakers and unconditionally inject their I/O") Signed-off-by: Jia Cheng Hu <jia.jiachenghu@gmail.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Paolo Valente <paolo.valente@linaro.org> Signed-off-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Yu Kuai <yukuai3@huawei.com> Reviewed-by: Yufen Yu <yuyufen@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- block/bfq-iosched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index c91dca641eb4..b2b1a0bb19e7 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -4499,7 +4499,7 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd) bfqq = bfqq->bic->bfqq[0]; else if (bfq_bfqq_has_waker(bfqq) && bfq_bfqq_busy(bfqq->waker_bfqq) && - bfqq->next_rq && + bfqq->waker_bfqq->next_rq && bfq_serv_to_charge(bfqq->waker_bfqq->next_rq, bfqq->waker_bfqq) <= bfq_bfqq_budget_left(bfqq->waker_bfqq) -- 2.22.0

From: Yonghong Song <yhs@fb.com> mainline inclusion from mainline-v5.13-rc1 commit b910eaaaa4b89976ef02e5d6448f3f73dc671d91 category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ------------------------------------------------- Jiri Olsa reported a bug ([1]) in kernel where cgroup local storage pointer may be NULL in bpf_get_local_storage() helper. There are two issues uncovered by this bug: (1). kprobe or tracepoint prog incorrectly sets cgroup local storage before prog run, (2). due to change from preempt_disable to migrate_disable, preemption is possible and percpu storage might be overwritten by other tasks. This issue (1) is fixed in [2]. This patch tried to address issue (2). The following shows how things can go wrong: task 1: bpf_cgroup_storage_set() for percpu local storage preemption happens task 2: bpf_cgroup_storage_set() for percpu local storage preemption happens task 1: run bpf program task 1 will effectively use the percpu local storage setting by task 2 which will be either NULL or incorrect ones. Instead of just one common local storage per cpu, this patch fixed the issue by permitting 8 local storages per cpu and each local storage is identified by a task_struct pointer. This way, we allow at most 8 nested preemption between bpf_cgroup_storage_set() and bpf_cgroup_storage_unset(). The percpu local storage slot is released (calling bpf_cgroup_storage_unset()) by the same task after bpf program finished running. bpf_test_run() is also fixed to use the new bpf_cgroup_storage_set() interface. The patch is tested on top of [2] with reproducer in [1]. Without this patch, kernel will emit error in 2-3 minutes. With this patch, after one hour, still no error. [1] https://lore.kernel.org/bpf/CAKH8qBuXCfUz=w8L+Fj74OaUpbosO29niYwTki7e3Ag044_... [2] https://lore.kernel.org/bpf/20210309185028.3763817-1-yhs@fb.com Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Roman Gushchin <guro@fb.com> Link: https://lore.kernel.org/bpf/20210323055146.3334476-1-yhs@fb.com Conflicts: include/linux/bpf.h net/bpf/test_run.c Signed-off-by: Pu Lehui <pulehui@huawei.com> Reviewed-by: Kuohai Xu <xukuohai@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- include/linux/bpf-cgroup.h | 57 ++++++++++++++++++++++++++++++++------ include/linux/bpf.h | 43 ++++++++++++++++++++++++++-- kernel/bpf/helpers.c | 15 +++++++--- kernel/bpf/local_storage.c | 5 ++-- net/bpf/test_run.c | 6 +++- 5 files changed, 108 insertions(+), 18 deletions(-) diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index ed71bd1a0825..53f14e8827cc 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -20,14 +20,25 @@ struct bpf_sock_ops_kern; struct bpf_cgroup_storage; struct ctl_table; struct ctl_table_header; +struct task_struct; #ifdef CONFIG_CGROUP_BPF extern struct static_key_false cgroup_bpf_enabled_key; #define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key) -DECLARE_PER_CPU(struct bpf_cgroup_storage*, - bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); +#define BPF_CGROUP_STORAGE_NEST_MAX 8 + +struct bpf_cgroup_storage_info { + struct task_struct *task; + struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]; +}; + +/* For each cpu, permit maximum BPF_CGROUP_STORAGE_NEST_MAX number of tasks + * to use bpf cgroup storage simultaneously. + */ +DECLARE_PER_CPU(struct bpf_cgroup_storage_info, + bpf_cgroup_storage_info[BPF_CGROUP_STORAGE_NEST_MAX]); #define for_each_cgroup_storage_type(stype) \ for (stype = 0; stype < MAX_BPF_CGROUP_STORAGE_TYPE; stype++) @@ -156,13 +167,42 @@ static inline enum bpf_cgroup_storage_type cgroup_storage_type( return BPF_CGROUP_STORAGE_SHARED; } -static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage - *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) +static inline int bpf_cgroup_storage_set(struct bpf_cgroup_storage + *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) { enum bpf_cgroup_storage_type stype; + int i, err = 0; + + preempt_disable(); + for (i = 0; i < BPF_CGROUP_STORAGE_NEST_MAX; i++) { + if (unlikely(this_cpu_read(bpf_cgroup_storage_info[i].task) != NULL)) + continue; + + this_cpu_write(bpf_cgroup_storage_info[i].task, current); + for_each_cgroup_storage_type(stype) + this_cpu_write(bpf_cgroup_storage_info[i].storage[stype], + storage[stype]); + goto out; + } + err = -EBUSY; + WARN_ON_ONCE(1); + +out: + preempt_enable(); + return err; +} + +static inline void bpf_cgroup_storage_unset(void) +{ + int i; + + for (i = 0; i < BPF_CGROUP_STORAGE_NEST_MAX; i++) { + if (unlikely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) + continue; - for_each_cgroup_storage_type(stype) - this_cpu_write(bpf_cgroup_storage[stype], storage[stype]); + this_cpu_write(bpf_cgroup_storage_info[i].task, NULL); + return; + } } struct bpf_cgroup_storage * @@ -410,8 +450,9 @@ static inline int cgroup_bpf_prog_query(const union bpf_attr *attr, return -EINVAL; } -static inline void bpf_cgroup_storage_set( - struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) {} +static inline int bpf_cgroup_storage_set( + struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) { return 0; } +static inline void bpf_cgroup_storage_unset(void) {} static inline int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map) { return 0; } static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c3ccb242d199..39024b7677ea 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1076,6 +1076,38 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *include_prog, struct bpf_prog_array **new_array); +/* For BPF_PROG_RUN_ARRAY_FLAGS and __BPF_PROG_RUN_ARRAY, + * if bpf_cgroup_storage_set() failed, the rest of programs + * will not execute. This should be a really rare scenario + * as it requires BPF_CGROUP_STORAGE_NEST_MAX number of + * preemptions all between bpf_cgroup_storage_set() and + * bpf_cgroup_storage_unset() on the same cpu. + */ +#define BPF_PROG_RUN_ARRAY_FLAGS(array, ctx, func, ret_flags) \ + ({ \ + struct bpf_prog_array_item *_item; \ + struct bpf_prog *_prog; \ + struct bpf_prog_array *_array; \ + u32 _ret = 1; \ + u32 func_ret; \ + migrate_disable(); \ + rcu_read_lock(); \ + _array = rcu_dereference(array); \ + _item = &_array->items[0]; \ + while ((_prog = READ_ONCE(_item->prog))) { \ + if (unlikely(bpf_cgroup_storage_set(_item->cgroup_storage))) \ + break; \ + func_ret = func(_prog, ctx); \ + _ret &= (func_ret & 1); \ + *(ret_flags) |= (func_ret >> 1); \ + bpf_cgroup_storage_unset(); \ + _item++; \ + } \ + rcu_read_unlock(); \ + migrate_enable(); \ + _ret; \ + }) + #define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null, set_cg_storage) \ ({ \ struct bpf_prog_array_item *_item; \ @@ -1089,9 +1121,14 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array, goto _out; \ _item = &_array->items[0]; \ while ((_prog = READ_ONCE(_item->prog))) { \ - if (set_cg_storage) \ - bpf_cgroup_storage_set(_item->cgroup_storage); \ - _ret &= func(_prog, ctx); \ + if (!set_cg_storage) { \ + _ret &= func(_prog, ctx); \ + } else { \ + if (unlikely(bpf_cgroup_storage_set(_item->cgroup_storage))) \ + break; \ + _ret &= func(_prog, ctx); \ + bpf_cgroup_storage_unset(); \ + } \ _item++; \ } \ _out: \ diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index f7e99bb8c3b6..3bd7fbd8c543 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -372,8 +372,8 @@ const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto = { }; #ifdef CONFIG_CGROUP_BPF -DECLARE_PER_CPU(struct bpf_cgroup_storage*, - bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); +DECLARE_PER_CPU(struct bpf_cgroup_storage_info, + bpf_cgroup_storage_info[BPF_CGROUP_STORAGE_NEST_MAX]); BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags) { @@ -382,10 +382,17 @@ BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags) * verifier checks that its value is correct. */ enum bpf_cgroup_storage_type stype = cgroup_storage_type(map); - struct bpf_cgroup_storage *storage; + struct bpf_cgroup_storage *storage = NULL; void *ptr; + int i; - storage = this_cpu_read(bpf_cgroup_storage[stype]); + for (i = 0; i < BPF_CGROUP_STORAGE_NEST_MAX; i++) { + if (unlikely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) + continue; + + storage = this_cpu_read(bpf_cgroup_storage_info[i].storage[stype]); + break; + } if (stype == BPF_CGROUP_STORAGE_SHARED) ptr = &READ_ONCE(storage->buf)->data[0]; diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 571bb351ed3b..b139247d2dd3 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -9,10 +9,11 @@ #include <linux/slab.h> #include <uapi/linux/btf.h> -DEFINE_PER_CPU(struct bpf_cgroup_storage*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); - #ifdef CONFIG_CGROUP_BPF +DEFINE_PER_CPU(struct bpf_cgroup_storage_info, + bpf_cgroup_storage_info[BPF_CGROUP_STORAGE_NEST_MAX]); + #include "../cgroup/cgroup-internal.h" #define LOCAL_STORAGE_CREATE_FLAG_MASK \ diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index e7cbd1b4a5e5..72d424a5a142 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -42,13 +42,17 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, migrate_disable(); time_start = ktime_get_ns(); for (i = 0; i < repeat; i++) { - bpf_cgroup_storage_set(storage); + ret = bpf_cgroup_storage_set(storage); + if (ret) + break; if (xdp) *retval = bpf_prog_run_xdp(prog, ctx); else *retval = BPF_PROG_RUN(prog, ctx); + bpf_cgroup_storage_unset(); + if (signal_pending(current)) { ret = -EINTR; break; -- 2.22.0

From: Tian Tao <tiantao6@hisilicon.com> mainline inclusion from mainline-5.12-rc1 commit fc6697a89f56d9773b2fbff718d4cf2a6d63379d category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ------------------------------------------------- Patch series "Fix the compatibility of zsmalloc and zswap". Patch #1 adds a flag to zpool, then zswap used to determine if zpool drivers such as zbud/z3fold/zsmalloc will enter an atomic context after mapping. The difference between zbud/z3fold and zsmalloc is that zsmalloc requires an atomic context that since its map function holds a preempt-disabled, but zbud/z3fold don't require an atomic context. So patch #2 sets flag sleep_mapped to true indicating that zbud/z3fold can sleep after mapping. zsmalloc didn't support sleep after mapping, so don't set that flag to true. This patch (of 2): Add a flag to zpool, named is "can_sleep_mapped", and have it set true for zbud/z3fold, not set this flag for zsmalloc, so its default value is false. Then zswap could go the current path if the flag is true; and if it's false, copy data from src to a temporary buffer, then unmap the handle, take the mutex, process the buffer instead of src to avoid sleeping function called from atomic context. [natechancellor@gmail.com: add return value in zswap_frontswap_load] Link: https://lkml.kernel.org/r/20210121214804.926843-1-natechancellor@gmail.com [tiantao6@hisilicon.com: fix potential memory leak] Link: https://lkml.kernel.org/r/1611538365-51811-1-git-send-email-tiantao6@hisilic... [colin.king@canonical.com: fix potential uninitialized pointer read on tmp] Link: https://lkml.kernel.org/r/20210128141728.639030-1-colin.king@canonical.com [tiantao6@hisilicon.com: fix variable 'entry' is uninitialized when used] Link: https://lkml.kernel.org/r/1611223030-58346-1-git-send-email-tiantao6@hisilic...: https://lkml.kernel.org/r/1611035683-12732-1-git-send-email-tiantao6@hisilic... Link: https://lkml.kernel.org/r/1611035683-12732-2-git-send-email-tiantao6@hisilic... Signed-off-by: Tian Tao <tiantao6@hisilicon.com> Signed-off-by: Nathan Chancellor <natechancellor@gmail.com> Signed-off-by: Colin Ian King <colin.king@canonical.com> Reviewed-by: Vitaly Wool <vitaly.wool@konsulko.com> Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reported-by: Mike Galbraith <efault@gmx.de> Cc: Barry Song <song.bao.hua@hisilicon.com> Cc: Dan Streetman <ddstreet@ieee.org> Cc: Seth Jennings <sjenning@redhat.com> Cc: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Chen Huang <chenhuang5@huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- include/linux/zpool.h | 3 +++ mm/zpool.c | 13 +++++++++++ mm/zswap.c | 50 +++++++++++++++++++++++++++++++++++++------ 3 files changed, 60 insertions(+), 6 deletions(-) diff --git a/include/linux/zpool.h b/include/linux/zpool.h index 51bf43076165..e8997010612a 100644 --- a/include/linux/zpool.h +++ b/include/linux/zpool.h @@ -73,6 +73,7 @@ u64 zpool_get_total_size(struct zpool *pool); * @malloc: allocate mem from a pool. * @free: free mem from a pool. * @shrink: shrink the pool. + * @sleep_mapped: whether zpool driver can sleep during map. * @map: map a handle. * @unmap: unmap a handle. * @total_size: get total size of a pool. @@ -100,6 +101,7 @@ struct zpool_driver { int (*shrink)(void *pool, unsigned int pages, unsigned int *reclaimed); + bool sleep_mapped; void *(*map)(void *pool, unsigned long handle, enum zpool_mapmode mm); void (*unmap)(void *pool, unsigned long handle); @@ -112,5 +114,6 @@ void zpool_register_driver(struct zpool_driver *driver); int zpool_unregister_driver(struct zpool_driver *driver); bool zpool_evictable(struct zpool *pool); +bool zpool_can_sleep_mapped(struct zpool *pool); #endif diff --git a/mm/zpool.c b/mm/zpool.c index 3744a2d1a624..5ed71207ced7 100644 --- a/mm/zpool.c +++ b/mm/zpool.c @@ -23,6 +23,7 @@ struct zpool { void *pool; const struct zpool_ops *ops; bool evictable; + bool can_sleep_mapped; struct list_head list; }; @@ -183,6 +184,7 @@ struct zpool *zpool_create_pool(const char *type, const char *name, gfp_t gfp, zpool->pool = driver->create(name, gfp, ops, zpool); zpool->ops = ops; zpool->evictable = driver->shrink && ops && ops->evict; + zpool->can_sleep_mapped = driver->sleep_mapped; if (!zpool->pool) { pr_err("couldn't create %s pool\n", type); @@ -393,6 +395,17 @@ bool zpool_evictable(struct zpool *zpool) return zpool->evictable; } +/** + * zpool_can_sleep_mapped - Test if zpool can sleep when do mapped. + * @zpool: The zpool to test + * + * Returns: true if zpool can sleep; false otherwise. + */ +bool zpool_can_sleep_mapped(struct zpool *zpool) +{ + return zpool->can_sleep_mapped; +} + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>"); MODULE_DESCRIPTION("Common API for compressed memory storage"); diff --git a/mm/zswap.c b/mm/zswap.c index fbb782924ccc..4c6ce385c4e7 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -877,13 +877,19 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) struct zswap_entry *entry; struct page *page; struct crypto_comp *tfm; - u8 *src, *dst; + u8 *src, *dst, *tmp = NULL; unsigned int dlen; int ret; struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE, }; + if (!zpool_can_sleep_mapped(pool)) { + tmp = kmalloc(PAGE_SIZE, GFP_ATOMIC); + if (!tmp) + return -ENOMEM; + } + /* extract swpentry from data */ zhdr = zpool_map_handle(pool, handle, ZPOOL_MM_RO); swpentry = zhdr->swpentry; /* here */ @@ -897,11 +903,19 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) /* entry was invalidated */ spin_unlock(&tree->lock); zpool_unmap_handle(pool, handle); + kfree(tmp); return 0; } spin_unlock(&tree->lock); BUG_ON(offset != entry->offset); + src = (u8 *)zhdr + sizeof(struct zswap_header); + if (!zpool_can_sleep_mapped(pool)) { + memcpy(tmp, src, entry->length); + src = tmp; + zpool_unmap_handle(pool, handle); + } + /* try to allocate swap cache page */ switch (zswap_get_swap_cache_page(swpentry, &page)) { case ZSWAP_SWAPCACHE_FAIL: /* no memory or invalidate happened */ @@ -917,7 +931,6 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) case ZSWAP_SWAPCACHE_NEW: /* page is locked */ /* decompress */ dlen = PAGE_SIZE; - src = (u8 *)zhdr + sizeof(struct zswap_header); dst = kmap_atomic(page); tfm = *get_cpu_ptr(entry->pool->tfm); ret = crypto_comp_decompress(tfm, src, entry->length, @@ -969,7 +982,11 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) spin_unlock(&tree->lock); end: - zpool_unmap_handle(pool, handle); + if (zpool_can_sleep_mapped(pool)) + zpool_unmap_handle(pool, handle); + else + kfree(tmp); + return ret; } @@ -1149,7 +1166,7 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset, struct zswap_tree *tree = zswap_trees[type]; struct zswap_entry *entry; struct crypto_comp *tfm; - u8 *src, *dst; + u8 *src, *dst, *tmp; unsigned int dlen; int ret; @@ -1167,20 +1184,41 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset, dst = kmap_atomic(page); zswap_fill_page(dst, entry->value); kunmap_atomic(dst); + ret = 0; goto freeentry; } + if (!zpool_can_sleep_mapped(entry->pool->zpool)) { + tmp = kmalloc(entry->length, GFP_ATOMIC); + if (!tmp) { + ret = -ENOMEM; + goto freeentry; + } + } + /* decompress */ dlen = PAGE_SIZE; src = zpool_map_handle(entry->pool->zpool, entry->handle, ZPOOL_MM_RO); if (zpool_evictable(entry->pool->zpool)) src += sizeof(struct zswap_header); + + if (!zpool_can_sleep_mapped(entry->pool->zpool)) { + memcpy(tmp, src, entry->length); + src = tmp; + zpool_unmap_handle(entry->pool->zpool, entry->handle); + } + dst = kmap_atomic(page); tfm = *get_cpu_ptr(entry->pool->tfm); ret = crypto_comp_decompress(tfm, src, entry->length, dst, &dlen); put_cpu_ptr(entry->pool->tfm); kunmap_atomic(dst); - zpool_unmap_handle(entry->pool->zpool, entry->handle); + + if (zpool_can_sleep_mapped(entry->pool->zpool)) + zpool_unmap_handle(entry->pool->zpool, entry->handle); + else + kfree(tmp); + BUG_ON(ret); freeentry: @@ -1188,7 +1226,7 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset, zswap_entry_put(tree, entry); spin_unlock(&tree->lock); - return 0; + return ret; } /* frees an entry in zswap */ -- 2.22.0

From: Eyal Birger <eyal.birger@gmail.com> mainline inclusion from mainline-5.12-rc7 commit c7c1abfd6d42be8f09d390ab912cd84983000fa2 category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ------------------------------------------------- Frag needed should only be sent if the header enables DF. This fix allows packets larger than MTU to pass the vti interface and be fragmented after encapsulation, aligning behavior with non-vti xfrm. Fixes: d6af1a31cc72 ("vti: Add pmtu handling to vti_xmit.") Signed-off-by: Eyal Birger <eyal.birger@gmail.com> Reviewed-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com> Conflicts: net/ipv4/ip_vti.c Signed-off-by: Ziyang Xuan <xuanziyang2@huawei.com> Reviewed-by: Yue Haibing <yuehaibing@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- net/ipv4/ip_vti.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 84a818b09bee..c040acbf122b 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -218,7 +218,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, } if (dst->flags & DST_XFRM_QUEUE) - goto queued; + goto xmit; if (!vti_state_check(dst->xfrm, parms->iph.daddr, parms->iph.saddr)) { dev->stats.tx_carrier_errors++; @@ -238,6 +238,8 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, if (skb->len > mtu) { skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { + if (!(ip_hdr(skb)->frag_off & htons(IP_DF))) + goto xmit; icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); } else { @@ -251,7 +253,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, goto tx_error; } -queued: +xmit: skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev))); skb_dst_set(skb, dst); skb->dev = skb_dst(skb)->dev; -- 2.22.0

From: Ondrej Mosnacek <omosnace@redhat.com> mainline inclusion from mainline-5.13-rc4 commit 5881fa8dc2de9697a89451f6518e8b3a796c09c6 category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ------------------------------------------------- When (ia->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) is zero, then the SELinux implementation of the locked_down hook might report a denial even though the operation would actually be allowed. To fix this, make sure that security_locked_down() is called only when the return value will be taken into account (i.e. when changing one of the problematic attributes). Note: this was introduced by commit 5496197f9b08 ("debugfs: Restrict debugfs when the kernel is locked down"), but it didn't matter at that time, as the SELinux support came in later. Fixes: 59438b46471a ("security,lockdown,selinux: implement SELinux lockdown") Cc: stable <stable@vger.kernel.org> Signed-off-by: Ondrej Mosnacek <omosnace@redhat.com> Link: https://lore.kernel.org/r/20210507125304.144394-1-omosnace@redhat.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Conflicts: fs/debugfs/inode.c Signed-off-by: Baokun Li <libaokun1@huawei.com> Reviewed-by: Zhang Yi <yi.zhang@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- fs/debugfs/inode.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 720d65f224f0..dc3ea2833a9e 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -44,10 +44,13 @@ static unsigned int debugfs_allow __ro_after_init = DEFAULT_DEBUGFS_ALLOW_BITS; */ static int debugfs_setattr(struct dentry *dentry, struct iattr *ia) { - int ret = security_locked_down(LOCKDOWN_DEBUGFS); + int ret; - if (ret && (ia->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))) - return ret; + if (ia->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) { + ret = security_locked_down(LOCKDOWN_DEBUGFS); + if (ret) + return ret; + } return simple_setattr(dentry, ia); } -- 2.22.0

From: Kefeng Wang <wangkefeng.wang@huawei.com> ohos inclusion category: bugfix issue: #I3ZXZF CVE: NA Reference: https://lore.kernel.org/linux-arm-kernel/20210610123556.171328-1-wangkefeng.... ------------------------------------------------- Clean up the multiple goto statements and drops local variable vm_fault_t fault, which will make the __do_page_fault() much more readability. No functional change. Reviewed-by: Jason Yan <yanaijie@huawei.com> Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/mm/fault.c | 34 +++++++++++++--------------------- 1 file changed, 13 insertions(+), 21 deletions(-) diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index efa402025031..662ac3ca3c8a 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -205,35 +205,27 @@ __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr, unsigned int flags, struct task_struct *tsk, struct pt_regs *regs) { - struct vm_area_struct *vma; - vm_fault_t fault; - - vma = find_vma(mm, addr); - fault = VM_FAULT_BADMAP; + struct vm_area_struct *vma = find_vma(mm, addr); if (unlikely(!vma)) - goto out; - if (unlikely(vma->vm_start > addr)) - goto check_stack; + return VM_FAULT_BADMAP; + + if (unlikely(vma->vm_start > addr)) { + if (!(vma->vm_flags & VM_GROWSDOWN)) + return VM_FAULT_BADMAP; + if (addr < FIRST_USER_ADDRESS) + return VM_FAULT_BADMAP; + if (expand_stack(vma, addr)) + return VM_FAULT_BADMAP; + } /* * Ok, we have a good vm_area for this * memory access, so we can handle it. */ -good_area: - if (access_error(fsr, vma)) { - fault = VM_FAULT_BADACCESS; - goto out; - } + if (access_error(fsr, vma)) + return VM_FAULT_BADACCESS; return handle_mm_fault(vma, addr & PAGE_MASK, flags, regs); - -check_stack: - /* Don't allow expansion below FIRST_USER_ADDRESS */ - if (vma->vm_flags & VM_GROWSDOWN && - addr >= FIRST_USER_ADDRESS && !expand_stack(vma, addr)) - goto good_area; -out: - return fault; } static int __kprobes -- 2.22.0

From: Kefeng Wang <wangkefeng.wang@huawei.com> ohos inclusion category: bugfix issue: #I3ZXZF CVE: NA Reference: https://lore.kernel.org/linux-arm-kernel/20210610123556.171328-1-wangkefeng.... ------------------------------------------------- Now the write fault check in do_page_fault() and access_error() twice, we can cleanup access_error(), and make the fault check and vma flags set into do_page_fault() directly, then pass the vma flags to __do_page_fault. No functional change. Reviewed-by: Jason Yan <yanaijie@huawei.com> Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/mm/fault.c | 38 ++++++++++++++------------------------ 1 file changed, 14 insertions(+), 24 deletions(-) diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 249db395bdf0..9a6d74f6ea1d 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -183,26 +183,9 @@ void do_bad_area(unsigned long addr, unsigned int fsr, struct pt_regs *regs) #define VM_FAULT_BADMAP 0x010000 #define VM_FAULT_BADACCESS 0x020000 -/* - * Check that the permissions on the VMA allow for the fault which occurred. - * If we encountered a write fault, we must have write permission, otherwise - * we allow any permission. - */ -static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma) -{ - unsigned int mask = VM_ACCESS_FLAGS; - - if ((fsr & FSR_WRITE) && !(fsr & FSR_CM)) - mask = VM_WRITE; - if (fsr & FSR_LNX_PF) - mask = VM_EXEC; - - return vma->vm_flags & mask ? false : true; -} - static vm_fault_t __kprobes -__do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr, - unsigned int flags, struct pt_regs *regs) +__do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int flags, + unsigned long vma_flags, struct pt_regs *regs) { struct vm_area_struct *vma = find_vma(mm, addr); if (unlikely(!vma)) @@ -218,10 +201,10 @@ __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr, } /* - * Ok, we have a good vm_area for this - * memory access, so we can handle it. + * ok, we have a good vm_area for this memory access, check the + * permissions on the VMA allow for the fault which occurred. */ - if (access_error(fsr, vma)) + if (!(vma->vm_flags & vma_flags)) return VM_FAULT_BADACCESS; return handle_mm_fault(vma, addr & PAGE_MASK, flags, regs); @@ -234,6 +217,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) int sig, code; vm_fault_t fault; unsigned int flags = FAULT_FLAG_DEFAULT; + unsigned long vm_flags = VM_ACCESS_FLAGS; if (kprobe_page_fault(regs, fsr)) return 0; @@ -252,8 +236,14 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) if (user_mode(regs)) flags |= FAULT_FLAG_USER; - if ((fsr & FSR_WRITE) && !(fsr & FSR_CM)) + + if ((fsr & FSR_WRITE) && !(fsr & FSR_CM)) { flags |= FAULT_FLAG_WRITE; + vm_flags = VM_WRITE; + } + + if (fsr & FSR_LNX_PF) + vm_flags = VM_EXEC; perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr); @@ -281,7 +271,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) #endif } - fault = __do_page_fault(mm, addr, fsr, flags, regs); + fault = __do_page_fault(mm, addr, flags, vm_flags, regs); /* If we need to retry but a fatal signal is pending, handle the * signal first. We do not need to release the mmap_lock because -- 2.22.0

From: Kefeng Wang <wangkefeng.wang@huawei.com> ohos inclusion category: bugfix issue: #I3ZXZF CVE: NA Reference: https://lore.kernel.org/linux-arm-kernel/20210610123556.171328-1-wangkefeng.... ------------------------------------------------- Provide die_kernel_fault() helper to do the kernel fault reporting, which with msg argument, it could report different message in different scenes, and the later patch "ARM: mm: Fix PXN process with LPAE feature" will use it. Reviewed-by: Jason Yan <yanaijie@huawei.com> Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/mm/fault.c | 30 +++++++++++++++++++++--------- 1 file changed, 21 insertions(+), 9 deletions(-) diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 76aced067b12..82bcfe57de20 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -99,6 +99,21 @@ void show_pte(const char *lvl, struct mm_struct *mm, unsigned long addr) { } #endif /* CONFIG_MMU */ +static void die_kernel_fault(const char *msg, struct mm_struct *mm, + unsigned long addr, unsigned int fsr, + struct pt_regs *regs) +{ + bust_spinlocks(1); + pr_alert("8<--- cut here ---\n"); + pr_alert("Unable to handle kernel %s at virtual address %08lx\n", + msg, addr); + + show_pte(KERN_ALERT, mm, addr); + die("Oops", regs, fsr); + bust_spinlocks(0); + do_exit(SIGKILL); +} + /* * Oops. The kernel tried to access some page that wasn't present. */ @@ -106,6 +121,7 @@ static void __do_kernel_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr, struct pt_regs *regs) { + const char *msg; /* * Are we prepared to handle this kernel fault? */ @@ -115,16 +131,12 @@ __do_kernel_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr, /* * No handler, we'll have to terminate things with extreme prejudice. */ - bust_spinlocks(1); - pr_alert("8<--- cut here ---\n"); - pr_alert("Unable to handle kernel %s at virtual address %08lx\n", - (addr < PAGE_SIZE) ? "NULL pointer dereference" : - "paging request", addr); + if (addr < PAGE_SIZE) + msg = "NULL pointer dereference"; + else + msg = "paging request"; - show_pte(KERN_ALERT, mm, addr); - die("Oops", regs, fsr); - bust_spinlocks(0); - do_exit(SIGKILL); + die_kernel_fault(msg, mm, addr, fsr, regs); } /* -- 2.22.0

From: "Eric W. Biederman" <ebiederm@xmission.com> mainline inclusion from mainline-5.11-rc1 commit 878f12dbb8f514799d126544d59be4d2675caac3 category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ------------------------------------------------- Al Viro pointed out that using the phrase "close_on_exec(fd, rcu_dereference_raw(current->files->fdt))" instead of wrapping it in rcu_read_lock(), rcu_read_unlock() is a very questionable optimization[1]. Once wrapped with rcu_read_lock()/rcu_read_unlock() that phrase becomes equivalent the helper function get_close_on_exec so simplify the code and make it more robust by simply using get_close_on_exec. [1] https://lkml.kernel.org/r/20201207222214.GA4115853@ZenIV.linux.org.uk Suggested-by: Al Viro <viro@ftp.linux.org.uk> Link: https://lkml.kernel.org/r/87k0tqr6zi.fsf_-_@x220.int.ebiederm.org Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Baokun Li <libaokun1@huawei.com> Reviewed-by: Zhang Yi <yi.zhang@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- fs/exec.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/exec.c b/fs/exec.c index c7a4ef8df305..7c9d6a8c2b45 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1812,8 +1812,7 @@ static int bprm_execve(struct linux_binprm *bprm, * inaccessible after exec. Relies on having exclusive access to * current->files (due to unshare_files above). */ - if (bprm->fdpath && - close_on_exec(fd, rcu_dereference_raw(current->files->fdt))) + if (bprm->fdpath && get_close_on_exec(fd)) bprm->interp_flags |= BINPRM_FLAGS_PATH_INACCESSIBLE; /* Set the unchanging part of bprm->cred */ -- 2.22.0

From: Mike Christie <michael.christie@oracle.com> mainline inclusion from mainline-v5.12-rc1 commit 5923d64b7ab63dcc6f0df946098f50902f9540d1 category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ----------------------------------------------- The purpose of the taskqueuelock was to handle the issue where a bad target decides to send a R2T and before its data has been sent decides to send a cmd response to complete the cmd. The following patches fix up the frwd/back locks so they are taken from the queue/xmit (frwd) and completion (back) paths again. To get there this patch removes the taskqueuelock which for iSCSI xmit wq based drivers was taken in the queue, xmit and completion paths. Instead of the lock, we just make sure we have a ref to the task when we queue a R2T, and then we always remove the task from the requeue list in the xmit path or the forced cleanup paths. Link: https://lore.kernel.org/r/20210207044608.27585-3-michael.christie@oracle.com Reviewed-by: Lee Duncan <lduncan@suse.com> Signed-off-by: Mike Christie <michael.christie@oracle.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Ye Bin <yebin10@huawei.com> Reviewed-by: Jason Yan <yanaijie@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- drivers/scsi/libiscsi.c | 178 +++++++++++++++++++++++------------- drivers/scsi/libiscsi_tcp.c | 86 +++++++++++------ include/scsi/libiscsi.h | 4 +- 3 files changed, 172 insertions(+), 96 deletions(-) diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index 30d27b670674..9940cc5f4729 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -518,16 +518,6 @@ static void iscsi_complete_task(struct iscsi_task *task, int state) WARN_ON_ONCE(task->state == ISCSI_TASK_FREE); task->state = state; - spin_lock_bh(&conn->taskqueuelock); - if (!list_empty(&task->running)) { - pr_debug_once("%s while task on list", __func__); - list_del_init(&task->running); - } - spin_unlock_bh(&conn->taskqueuelock); - - if (conn->task == task) - conn->task = NULL; - if (READ_ONCE(conn->ping_task) == task) WRITE_ONCE(conn->ping_task, NULL); @@ -559,9 +549,40 @@ void iscsi_complete_scsi_task(struct iscsi_task *task, } EXPORT_SYMBOL_GPL(iscsi_complete_scsi_task); +/* + * Must be called with back and frwd lock + */ +static bool cleanup_queued_task(struct iscsi_task *task) +{ + struct iscsi_conn *conn = task->conn; + bool early_complete = false; + + /* Bad target might have completed task while it was still running */ + if (task->state == ISCSI_TASK_COMPLETED) + early_complete = true; + + if (!list_empty(&task->running)) { + list_del_init(&task->running); + /* + * If it's on a list but still running, this could be from + * a bad target sending a rsp early, cleanup from a TMF, or + * session recovery. + */ + if (task->state == ISCSI_TASK_RUNNING || + task->state == ISCSI_TASK_COMPLETED) + __iscsi_put_task(task); + } + + if (conn->task == task) { + conn->task = NULL; + __iscsi_put_task(task); + } + + return early_complete; +} /* - * session back_lock must be held and if not called for a task that is + * session frwd_lock must be held and if not called for a task that is * still pending or from the xmit thread, then xmit thread must * be suspended. */ @@ -580,6 +601,13 @@ static void fail_scsi_task(struct iscsi_task *task, int err) if (!sc) return; + /* regular RX path uses back_lock */ + spin_lock_bh(&conn->session->back_lock); + if (cleanup_queued_task(task)) { + spin_unlock_bh(&conn->session->back_lock); + return; + } + if (task->state == ISCSI_TASK_PENDING) { /* * cmd never made it to the xmit thread, so we should not count @@ -595,9 +623,6 @@ static void fail_scsi_task(struct iscsi_task *task, int err) sc->result = err << 16; scsi_set_resid(sc, scsi_bufflen(sc)); - - /* regular RX path uses back_lock */ - spin_lock_bh(&conn->session->back_lock); iscsi_complete_task(task, state); spin_unlock_bh(&conn->session->back_lock); } @@ -743,9 +768,7 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr, if (session->tt->xmit_task(task)) goto free_task; } else { - spin_lock_bh(&conn->taskqueuelock); list_add_tail(&task->running, &conn->mgmtqueue); - spin_unlock_bh(&conn->taskqueuelock); iscsi_conn_queue_work(conn); } @@ -1404,31 +1427,61 @@ static int iscsi_check_cmdsn_window_closed(struct iscsi_conn *conn) return 0; } -static int iscsi_xmit_task(struct iscsi_conn *conn) +static int iscsi_xmit_task(struct iscsi_conn *conn, struct iscsi_task *task, + bool was_requeue) { - struct iscsi_task *task = conn->task; int rc; - if (test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx)) - return -ENODATA; - spin_lock_bh(&conn->session->back_lock); - if (conn->task == NULL) { + + if (!conn->task) { + /* Take a ref so we can access it after xmit_task() */ + __iscsi_get_task(task); + } else { + /* Already have a ref from when we failed to send it last call */ + conn->task = NULL; + } + + /* + * If this was a requeue for a R2T we have an extra ref on the task in + * case a bad target sends a cmd rsp before we have handled the task. + */ + if (was_requeue) + __iscsi_put_task(task); + + /* + * Do this after dropping the extra ref because if this was a requeue + * it's removed from that list and cleanup_queued_task would miss it. + */ + if (test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx)) { + /* + * Save the task and ref in case we weren't cleaning up this + * task and get woken up again. + */ + conn->task = task; spin_unlock_bh(&conn->session->back_lock); return -ENODATA; } - __iscsi_get_task(task); spin_unlock_bh(&conn->session->back_lock); + spin_unlock_bh(&conn->session->frwd_lock); rc = conn->session->tt->xmit_task(task); spin_lock_bh(&conn->session->frwd_lock); if (!rc) { /* done with this task */ task->last_xfer = jiffies; - conn->task = NULL; } /* regular RX path uses back_lock */ spin_lock(&conn->session->back_lock); + if (rc && task->state == ISCSI_TASK_RUNNING) { + /* + * get an extra ref that is released next time we access it + * as conn->task above. + */ + __iscsi_get_task(task); + conn->task = task; + } + __iscsi_put_task(task); spin_unlock(&conn->session->back_lock); return rc; @@ -1438,9 +1491,7 @@ static int iscsi_xmit_task(struct iscsi_conn *conn) * iscsi_requeue_task - requeue task to run from session workqueue * @task: task to requeue * - * LLDs that need to run a task from the session workqueue should call - * this. The session frwd_lock must be held. This should only be called - * by software drivers. + * Callers must have taken a ref to the task that is going to be requeued. */ void iscsi_requeue_task(struct iscsi_task *task) { @@ -1450,11 +1501,18 @@ void iscsi_requeue_task(struct iscsi_task *task) * this may be on the requeue list already if the xmit_task callout * is handling the r2ts while we are adding new ones */ - spin_lock_bh(&conn->taskqueuelock); - if (list_empty(&task->running)) + spin_lock_bh(&conn->session->frwd_lock); + if (list_empty(&task->running)) { list_add_tail(&task->running, &conn->requeue); - spin_unlock_bh(&conn->taskqueuelock); + } else { + /* + * Don't need the extra ref since it's already requeued and + * has a ref. + */ + iscsi_put_task(task); + } iscsi_conn_queue_work(conn); + spin_unlock_bh(&conn->session->frwd_lock); } EXPORT_SYMBOL_GPL(iscsi_requeue_task); @@ -1480,7 +1538,7 @@ static int iscsi_data_xmit(struct iscsi_conn *conn) } if (conn->task) { - rc = iscsi_xmit_task(conn); + rc = iscsi_xmit_task(conn, conn->task, false); if (rc) goto done; } @@ -1490,49 +1548,41 @@ static int iscsi_data_xmit(struct iscsi_conn *conn) * only have one nop-out as a ping from us and targets should not * overflow us with nop-ins */ - spin_lock_bh(&conn->taskqueuelock); check_mgmt: while (!list_empty(&conn->mgmtqueue)) { - conn->task = list_entry(conn->mgmtqueue.next, - struct iscsi_task, running); - list_del_init(&conn->task->running); - spin_unlock_bh(&conn->taskqueuelock); - if (iscsi_prep_mgmt_task(conn, conn->task)) { + task = list_entry(conn->mgmtqueue.next, struct iscsi_task, + running); + list_del_init(&task->running); + if (iscsi_prep_mgmt_task(conn, task)) { /* regular RX path uses back_lock */ spin_lock_bh(&conn->session->back_lock); - __iscsi_put_task(conn->task); + __iscsi_put_task(task); spin_unlock_bh(&conn->session->back_lock); - conn->task = NULL; - spin_lock_bh(&conn->taskqueuelock); continue; } - rc = iscsi_xmit_task(conn); + rc = iscsi_xmit_task(conn, task, false); if (rc) goto done; - spin_lock_bh(&conn->taskqueuelock); } /* process pending command queue */ while (!list_empty(&conn->cmdqueue)) { - conn->task = list_entry(conn->cmdqueue.next, struct iscsi_task, - running); - list_del_init(&conn->task->running); - spin_unlock_bh(&conn->taskqueuelock); + task = list_entry(conn->cmdqueue.next, struct iscsi_task, + running); + list_del_init(&task->running); if (conn->session->state == ISCSI_STATE_LOGGING_OUT) { - fail_scsi_task(conn->task, DID_IMM_RETRY); - spin_lock_bh(&conn->taskqueuelock); + fail_scsi_task(task, DID_IMM_RETRY); continue; } - rc = iscsi_prep_scsi_cmd_pdu(conn->task); + rc = iscsi_prep_scsi_cmd_pdu(task); if (rc) { if (rc == -ENOMEM || rc == -EACCES) - fail_scsi_task(conn->task, DID_IMM_RETRY); + fail_scsi_task(task, DID_IMM_RETRY); else - fail_scsi_task(conn->task, DID_ABORT); - spin_lock_bh(&conn->taskqueuelock); + fail_scsi_task(task, DID_ABORT); continue; } - rc = iscsi_xmit_task(conn); + rc = iscsi_xmit_task(conn, task, false); if (rc) goto done; /* @@ -1540,7 +1590,6 @@ static int iscsi_data_xmit(struct iscsi_conn *conn) * we need to check the mgmt queue for nops that need to * be sent to aviod starvation */ - spin_lock_bh(&conn->taskqueuelock); if (!list_empty(&conn->mgmtqueue)) goto check_mgmt; } @@ -1554,21 +1603,17 @@ static int iscsi_data_xmit(struct iscsi_conn *conn) task = list_entry(conn->requeue.next, struct iscsi_task, running); + if (iscsi_check_tmf_restrictions(task, ISCSI_OP_SCSI_DATA_OUT)) break; - conn->task = task; - list_del_init(&conn->task->running); - conn->task->state = ISCSI_TASK_RUNNING; - spin_unlock_bh(&conn->taskqueuelock); - rc = iscsi_xmit_task(conn); + list_del_init(&task->running); + rc = iscsi_xmit_task(conn, task, true); if (rc) goto done; - spin_lock_bh(&conn->taskqueuelock); if (!list_empty(&conn->mgmtqueue)) goto check_mgmt; } - spin_unlock_bh(&conn->taskqueuelock); spin_unlock_bh(&conn->session->frwd_lock); return -ENODATA; @@ -1734,9 +1779,7 @@ int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc) goto prepd_reject; } } else { - spin_lock_bh(&conn->taskqueuelock); list_add_tail(&task->running, &conn->cmdqueue); - spin_unlock_bh(&conn->taskqueuelock); iscsi_conn_queue_work(conn); } @@ -2907,7 +2950,6 @@ iscsi_conn_setup(struct iscsi_cls_session *cls_session, int dd_size, INIT_LIST_HEAD(&conn->mgmtqueue); INIT_LIST_HEAD(&conn->cmdqueue); INIT_LIST_HEAD(&conn->requeue); - spin_lock_init(&conn->taskqueuelock); INIT_WORK(&conn->xmitwork, iscsi_xmitworker); /* allocate login_task used for the login/text sequences */ @@ -3072,10 +3114,16 @@ fail_mgmt_tasks(struct iscsi_session *session, struct iscsi_conn *conn) ISCSI_DBG_SESSION(conn->session, "failing mgmt itt 0x%x state %d\n", task->itt, task->state); + + spin_lock_bh(&session->back_lock); + if (cleanup_queued_task(task)) { + spin_unlock_bh(&session->back_lock); + continue; + } + state = ISCSI_TASK_ABRT_SESS_RECOV; if (task->state == ISCSI_TASK_PENDING) state = ISCSI_TASK_COMPLETED; - spin_lock_bh(&session->back_lock); iscsi_complete_task(task, state); spin_unlock_bh(&session->back_lock); } diff --git a/drivers/scsi/libiscsi_tcp.c b/drivers/scsi/libiscsi_tcp.c index 83f14b2c8804..2e9ffe3d1a55 100644 --- a/drivers/scsi/libiscsi_tcp.c +++ b/drivers/scsi/libiscsi_tcp.c @@ -524,48 +524,79 @@ static int iscsi_tcp_data_in(struct iscsi_conn *conn, struct iscsi_task *task) /** * iscsi_tcp_r2t_rsp - iSCSI R2T Response processing * @conn: iscsi connection - * @task: scsi command task + * @hdr: PDU header */ -static int iscsi_tcp_r2t_rsp(struct iscsi_conn *conn, struct iscsi_task *task) +static int iscsi_tcp_r2t_rsp(struct iscsi_conn *conn, struct iscsi_hdr *hdr) { struct iscsi_session *session = conn->session; - struct iscsi_tcp_task *tcp_task = task->dd_data; - struct iscsi_tcp_conn *tcp_conn = conn->dd_data; - struct iscsi_r2t_rsp *rhdr = (struct iscsi_r2t_rsp *)tcp_conn->in.hdr; + struct iscsi_tcp_task *tcp_task; + struct iscsi_tcp_conn *tcp_conn; + struct iscsi_r2t_rsp *rhdr; struct iscsi_r2t_info *r2t; - int r2tsn = be32_to_cpu(rhdr->r2tsn); + struct iscsi_task *task; u32 data_length; u32 data_offset; + int r2tsn; int rc; + spin_lock(&session->back_lock); + task = iscsi_itt_to_ctask(conn, hdr->itt); + if (!task) { + spin_unlock(&session->back_lock); + return ISCSI_ERR_BAD_ITT; + } else if (task->sc->sc_data_direction != DMA_TO_DEVICE) { + spin_unlock(&session->back_lock); + return ISCSI_ERR_PROTO; + } + /* + * A bad target might complete the cmd before we have handled R2Ts + * so get a ref to the task that will be dropped in the xmit path. + */ + if (task->state != ISCSI_TASK_RUNNING) { + spin_unlock(&session->back_lock); + /* Let the path that got the early rsp complete it */ + return 0; + } + task->last_xfer = jiffies; + __iscsi_get_task(task); + + tcp_conn = conn->dd_data; + rhdr = (struct iscsi_r2t_rsp *)tcp_conn->in.hdr; + /* fill-in new R2T associated with the task */ + iscsi_update_cmdsn(session, (struct iscsi_nopin *)rhdr); + spin_unlock(&session->back_lock); + if (tcp_conn->in.datalen) { iscsi_conn_printk(KERN_ERR, conn, "invalid R2t with datalen %d\n", tcp_conn->in.datalen); - return ISCSI_ERR_DATALEN; + rc = ISCSI_ERR_DATALEN; + goto put_task; } + tcp_task = task->dd_data; + r2tsn = be32_to_cpu(rhdr->r2tsn); if (tcp_task->exp_datasn != r2tsn){ ISCSI_DBG_TCP(conn, "task->exp_datasn(%d) != rhdr->r2tsn(%d)\n", tcp_task->exp_datasn, r2tsn); - return ISCSI_ERR_R2TSN; + rc = ISCSI_ERR_R2TSN; + goto put_task; } - /* fill-in new R2T associated with the task */ - iscsi_update_cmdsn(session, (struct iscsi_nopin*)rhdr); - - if (!task->sc || session->state != ISCSI_STATE_LOGGED_IN) { + if (session->state != ISCSI_STATE_LOGGED_IN) { iscsi_conn_printk(KERN_INFO, conn, "dropping R2T itt %d in recovery.\n", task->itt); - return 0; + rc = 0; + goto put_task; } data_length = be32_to_cpu(rhdr->data_length); if (data_length == 0) { iscsi_conn_printk(KERN_ERR, conn, "invalid R2T with zero data len\n"); - return ISCSI_ERR_DATALEN; + rc = ISCSI_ERR_DATALEN; + goto put_task; } if (data_length > session->max_burst) @@ -579,7 +610,8 @@ static int iscsi_tcp_r2t_rsp(struct iscsi_conn *conn, struct iscsi_task *task) "invalid R2T with data len %u at offset %u " "and total length %d\n", data_length, data_offset, task->sc->sdb.length); - return ISCSI_ERR_DATALEN; + rc = ISCSI_ERR_DATALEN; + goto put_task; } spin_lock(&tcp_task->pool2queue); @@ -589,7 +621,8 @@ static int iscsi_tcp_r2t_rsp(struct iscsi_conn *conn, struct iscsi_task *task) "Target has sent more R2Ts than it " "negotiated for or driver has leaked.\n"); spin_unlock(&tcp_task->pool2queue); - return ISCSI_ERR_PROTO; + rc = ISCSI_ERR_PROTO; + goto put_task; } r2t->exp_statsn = rhdr->statsn; @@ -607,6 +640,10 @@ static int iscsi_tcp_r2t_rsp(struct iscsi_conn *conn, struct iscsi_task *task) iscsi_requeue_task(task); return 0; + +put_task: + iscsi_put_task(task); + return rc; } /* @@ -730,20 +767,11 @@ iscsi_tcp_hdr_dissect(struct iscsi_conn *conn, struct iscsi_hdr *hdr) rc = iscsi_complete_pdu(conn, hdr, NULL, 0); break; case ISCSI_OP_R2T: - spin_lock(&conn->session->back_lock); - task = iscsi_itt_to_ctask(conn, hdr->itt); - spin_unlock(&conn->session->back_lock); - if (!task) - rc = ISCSI_ERR_BAD_ITT; - else if (ahslen) + if (ahslen) { rc = ISCSI_ERR_AHSLEN; - else if (task->sc->sc_data_direction == DMA_TO_DEVICE) { - task->last_xfer = jiffies; - spin_lock(&conn->session->frwd_lock); - rc = iscsi_tcp_r2t_rsp(conn, task); - spin_unlock(&conn->session->frwd_lock); - } else - rc = ISCSI_ERR_PROTO; + break; + } + rc = iscsi_tcp_r2t_rsp(conn, hdr); break; case ISCSI_OP_LOGIN_RSP: case ISCSI_OP_TEXT_RSP: diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h index 2b5f97224f69..0ff3ba6db679 100644 --- a/include/scsi/libiscsi.h +++ b/include/scsi/libiscsi.h @@ -187,7 +187,7 @@ struct iscsi_conn { struct iscsi_task *task; /* xmit task in progress */ /* xmit */ - spinlock_t taskqueuelock; /* protects the next three lists */ + /* items must be added/deleted under frwd lock */ struct list_head mgmtqueue; /* mgmt (control) xmit queue */ struct list_head cmdqueue; /* data-path cmd queue */ struct list_head requeue; /* tasks needing another run */ @@ -331,7 +331,7 @@ struct iscsi_session { * cmdsn, queued_cmdsn * * session resources: * * - cmdpool kfifo_out , * - * - mgmtpool, */ + * - mgmtpool, queues */ spinlock_t back_lock; /* protects cmdsn_exp * * cmdsn_max, * * cmdpool kfifo_in */ -- 2.22.0

From: Mike Christie <michael.christie@oracle.com> mainline inclusion from mainline-v5.12-rc1 commit c435f0a9ecb7435e70f447b7231ca52de589b252 category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ----------------------------------------------- We allocate the iSCSI host workq in iscsi_host_alloc() so iscsi_host_free() should do the destruction. Drivers can then do their error/goto handling and call iscsi_host_free() to clean up what has been allocated in iscsi_host_alloc(). Link: https://lore.kernel.org/r/20210207044608.27585-5-michael.christie@oracle.com Reviewed-by: Lee Duncan <lduncan@suse.com> Signed-off-by: Mike Christie <michael.christie@oracle.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Ye Bin <yebin10@huawei.com> Reviewed-by: Jason Yan <yanaijie@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- drivers/scsi/libiscsi.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index 5d3e91d06901..2c9602a75c8c 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -2729,8 +2729,6 @@ void iscsi_host_remove(struct Scsi_Host *shost) flush_signals(current); scsi_remove_host(shost); - if (ihost->workq) - destroy_workqueue(ihost->workq); } EXPORT_SYMBOL_GPL(iscsi_host_remove); @@ -2738,6 +2736,9 @@ void iscsi_host_free(struct Scsi_Host *shost) { struct iscsi_host *ihost = shost_priv(shost); + if (ihost->workq) + destroy_workqueue(ihost->workq); + kfree(ihost->netdev); kfree(ihost->hwaddress); kfree(ihost->initiatorname); -- 2.22.0

From: Mike Christie <michael.christie@oracle.com> mainline inclusion from mainline-v5.12-rc1 commit 25c400db2083732a5fbdd72f0d3a0337119b2fa5 category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ----------------------------------------------- We are setting the shost's can_queue after we add the host which is too late, because the SCSI midlayer will have allocated the tag set based on the can_queue value at that time. This patch has us use the iscsi_host_get_max_scsi_cmds() helper to figure out the number of SCSI cmds. It also fixes up the template can_queue so it reflects the max SCSI cmds we can support like how other drivers work. Link: https://lore.kernel.org/r/20210207044608.27585-7-michael.christie@oracle.com Reviewed-by: Lee Duncan <lduncan@suse.com> Signed-off-by: Mike Christie <michael.christie@oracle.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Ye Bin <yebin10@huawei.com> Reviewed-by: Jason Yan <yanaijie@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- drivers/scsi/iscsi_tcp.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index df47557a02a3..d39f812d9b92 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -847,6 +847,7 @@ iscsi_sw_tcp_session_create(struct iscsi_endpoint *ep, uint16_t cmds_max, struct iscsi_session *session; struct iscsi_sw_tcp_host *tcp_sw_host; struct Scsi_Host *shost; + int rc; if (ep) { printk(KERN_ERR "iscsi_tcp: invalid ep %p.\n", ep); @@ -864,6 +865,11 @@ iscsi_sw_tcp_session_create(struct iscsi_endpoint *ep, uint16_t cmds_max, shost->max_channel = 0; shost->max_cmd_len = SCSI_MAX_VARLEN_CDB_SIZE; + rc = iscsi_host_get_max_scsi_cmds(shost, cmds_max); + if (rc < 0) + goto free_host; + shost->can_queue = rc; + if (iscsi_host_add(shost, NULL)) goto free_host; @@ -878,7 +884,6 @@ iscsi_sw_tcp_session_create(struct iscsi_endpoint *ep, uint16_t cmds_max, tcp_sw_host = iscsi_host_priv(shost); tcp_sw_host->session = session; - shost->can_queue = session->scsi_cmds_max; if (iscsi_tcp_r2tpool_alloc(session)) goto remove_session; return cls_session; @@ -981,7 +986,7 @@ static struct scsi_host_template iscsi_sw_tcp_sht = { .name = "iSCSI Initiator over TCP/IP", .queuecommand = iscsi_queuecommand, .change_queue_depth = scsi_change_queue_depth, - .can_queue = ISCSI_DEF_XMIT_CMDS_MAX - 1, + .can_queue = ISCSI_TOTAL_CMDS_MAX, .sg_tablesize = 4096, .max_sectors = 0xFFFF, .cmd_per_lun = ISCSI_DEF_CMD_PER_LUN, -- 2.22.0

From: Yufen Yu <yuyufen@huawei.com> ohos inclusion category: bugfix issue: #I3ZXZF CVE: NA ------------------------------------------------- After calling add_disk, we have register new kobj map for sd device, then we can remove old unused kobj map which probed by sd_remove. Signed-off-by: Yufen Yu <yuyufen@huawei.com> Reviewed-by: Jason Yan <yanaijie@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- block/genhd.c | 8 ++++++++ drivers/base/map.c | 28 ++++++++++++++++++++++++++++ drivers/scsi/sd.c | 1 + include/linux/genhd.h | 2 ++ include/linux/kobj_map.h | 2 ++ 5 files changed, 41 insertions(+) diff --git a/block/genhd.c b/block/genhd.c index 796baf761202..b11b70a6bab5 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -663,6 +663,14 @@ void blk_unregister_region(dev_t devt, unsigned long range) EXPORT_SYMBOL(blk_unregister_region); +void blk_delete_region(dev_t devt, unsigned long range, + struct kobject *(*probe)(dev_t, int *, void *)) +{ + kobj_delete(bdev_map, devt, range, probe); +} + +EXPORT_SYMBOL(blk_delete_region); + static struct kobject *exact_match(dev_t devt, int *partno, void *data) { struct gendisk *p = data; diff --git a/drivers/base/map.c b/drivers/base/map.c index 5650ab2b247a..551296d48502 100644 --- a/drivers/base/map.c +++ b/drivers/base/map.c @@ -92,6 +92,34 @@ void kobj_unmap(struct kobj_map *domain, dev_t dev, unsigned long range) kfree(found); } +void kobj_delete(struct kobj_map *domain, dev_t dev, unsigned long range, + kobj_probe_t *probe) +{ + unsigned n = MAJOR(dev + range - 1) - MAJOR(dev) + 1; + unsigned index = MAJOR(dev); + unsigned i; + struct probe *found = NULL; + + if (n > 255) + n = 255; + + mutex_lock(domain->lock); + for (i = 0; i < n; i++, index++) { + struct probe **s; + for (s = &domain->probes[index % 255]; *s; s = &(*s)->next) { + struct probe *p = *s; + if (p->dev == dev && p->range == range && p->get == probe) { + *s = p->next; + if (!found) + found = p; + break; + } + } + } + mutex_unlock(domain->lock); + kfree(found); +} + struct kobject *kobj_lookup(struct kobj_map *domain, dev_t dev, int *index) { struct kobject *kobj; diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index f0c0935d7909..25f47947f669 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3488,6 +3488,7 @@ static int sd_probe(struct device *dev) sdp->host->hostt->rpm_autosuspend_delay); } device_add_disk(dev, gd, NULL); + blk_delete_region(disk_devt(sdkp->disk), SD_MINORS, sd_default_probe); if (sdkp->capacity) sd_dif_config_host(sdkp); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 03da3f603d30..f70458755828 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -349,6 +349,8 @@ extern void blk_register_region(dev_t devt, unsigned long range, int (*lock)(dev_t, void *), void *data); extern void blk_unregister_region(dev_t devt, unsigned long range); +extern void blk_delete_region(dev_t devt, unsigned long range, + struct kobject *(*probe)(dev_t, int *, void *)); #define alloc_disk_node(minors, node_id) \ ({ \ diff --git a/include/linux/kobj_map.h b/include/linux/kobj_map.h index c9919f8b2293..73361fe1c43a 100644 --- a/include/linux/kobj_map.h +++ b/include/linux/kobj_map.h @@ -14,6 +14,8 @@ struct kobj_map; int kobj_map(struct kobj_map *, dev_t, unsigned long, struct module *, kobj_probe_t *, int (*)(dev_t, void *), void *); void kobj_unmap(struct kobj_map *, dev_t, unsigned long); +void kobj_delete(struct kobj_map *, dev_t, unsigned long, + kobj_probe_t *); struct kobject *kobj_lookup(struct kobj_map *, dev_t, int *); struct kobj_map *kobj_map_init(kobj_probe_t *, struct mutex *); -- 2.22.0

From: Ming Lei <ming.lei@redhat.com> mainline inclusion from mainline-5.11-rc1 commit fb01a2932e81a1fb2273f87ff92dc8172b8880ee category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... --------------------------- flush_end_io() may be called recursively from some driver, such as nvme-loop, so lockdep may complain 'possible recursive locking'. Commit b3c6a5997541("block: Fix a lockdep complaint triggered by request queue flushing") tried to address this issue by assigning dynamically allocated per-flush-queue lock class. This solution adds synchronize_rcu() for each hctx's release handler, and causes horrible SCSI MQ probe delay(more than half an hour on megaraid sas). Add new API of blk_mq_hctx_set_fq_lock_class() for these drivers, so we just need to use driver specific lock class for avoiding the lockdep warning of 'possible recursive locking'. Tested-by: Kashyap Desai <kashyap.desai@broadcom.com> Reported-by: Qian Cai <cai@redhat.com> Cc: Sumit Saxena <sumit.saxena@broadcom.com> Cc: John Garry <john.garry@huawei.com> Cc: Kashyap Desai <kashyap.desai@broadcom.com> Cc: Bart Van Assche <bvanassche@acm.org> Cc: Hannes Reinecke <hare@suse.de> Signed-off-by: Ming Lei <ming.lei@redhat.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Signed-off-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: yangerkun <yangerkun@huawei.com> Reviewed-by: Jason Yan <yanaijie@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- block/blk-flush.c | 25 +++++++++++++++++++++++++ include/linux/blk-mq.h | 3 +++ 2 files changed, 28 insertions(+) diff --git a/block/blk-flush.c b/block/blk-flush.c index 7ee7e5e8905d..7ede7849b059 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -494,3 +494,28 @@ void blk_free_flush_queue(struct blk_flush_queue *fq) kfree(fq->flush_rq); kfree(fq); } + +/* + * Allow driver to set its own lock class to fq->mq_flush_lock for + * avoiding lockdep complaint. + * + * flush_end_io() may be called recursively from some driver, such as + * nvme-loop, so lockdep may complain 'possible recursive locking' because + * all 'struct blk_flush_queue' instance share same mq_flush_lock lock class + * key. We need to assign different lock class for these driver's + * fq->mq_flush_lock for avoiding the lockdep warning. + * + * Use dynamically allocated lock class key for each 'blk_flush_queue' + * instance is over-kill, and more worse it introduces horrible boot delay + * issue because synchronize_rcu() is implied in lockdep_unregister_key which + * is called for each hctx release. SCSI probing may synchronously create and + * destroy lots of MQ request_queues for non-existent devices, and some robot + * test kernel always enable lockdep option. It is observed that more than half + * an hour is taken during SCSI MQ probe with per-fq lock class. + */ +void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx, + struct lock_class_key *key) +{ + lockdep_set_class(&hctx->fq->mq_flush_lock, key); +} +EXPORT_SYMBOL_GPL(blk_mq_hctx_set_fq_lock_class); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index f8ea27423d1d..92bbc9a72355 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -5,6 +5,7 @@ #include <linux/blkdev.h> #include <linux/sbitmap.h> #include <linux/srcu.h> +#include <linux/lockdep.h> struct blk_mq_tags; struct blk_flush_queue; @@ -594,5 +595,7 @@ static inline void blk_mq_cleanup_rq(struct request *rq) } blk_qc_t blk_mq_submit_bio(struct bio *bio); +void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx, + struct lock_class_key *key); #endif -- 2.22.0

From: Ming Lei <ming.lei@redhat.com> mainline inclusion from mainline-5.11-rc1 commit 7aa390ec2d9db0cd6677d95d0b8f307f9c086770 category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... --------------------------- This reverts commit b3c6a59975415bde29cfd76ff1ab008edbf614a9. Now we can avoid nvme-loop lockdep warning of 'lockdep possible recursive locking' by nvme-loop's lock class, no need to apply dynamically allocated lock class key, so revert commit b3c6a5997541("block: Fix a lockdep complaint triggered by request queue flushing"). This way fixes horrible SCSI probe delay issue on megaraid_sas, and it is reported the whole probe may take more than half an hour. Tested-by: Kashyap Desai <kashyap.desai@broadcom.com> Reported-by: Qian Cai <cai@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Sumit Saxena <sumit.saxena@broadcom.com> Cc: John Garry <john.garry@huawei.com> Cc: Kashyap Desai <kashyap.desai@broadcom.com> Cc: Bart Van Assche <bvanassche@acm.org> Cc: Hannes Reinecke <hare@suse.de> Signed-off-by: Ming Lei <ming.lei@redhat.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Signed-off-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: yangerkun <yangerkun@huawei.com> Reviewed-by: Jason Yan <yanaijie@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- block/blk-flush.c | 5 ----- block/blk.h | 1 - 2 files changed, 6 deletions(-) diff --git a/block/blk-flush.c b/block/blk-flush.c index 7ede7849b059..bf74f4c222fd 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -69,7 +69,6 @@ #include <linux/blkdev.h> #include <linux/gfp.h> #include <linux/blk-mq.h> -#include <linux/lockdep.h> #include "blk.h" #include "blk-mq.h" @@ -473,9 +472,6 @@ struct blk_flush_queue *blk_alloc_flush_queue(int node, int cmd_size, INIT_LIST_HEAD(&fq->flush_queue[1]); INIT_LIST_HEAD(&fq->flush_data_in_flight); - lockdep_register_key(&fq->key); - lockdep_set_class(&fq->mq_flush_lock, &fq->key); - return fq; fail_rq: @@ -490,7 +486,6 @@ void blk_free_flush_queue(struct blk_flush_queue *fq) if (!fq) return; - lockdep_unregister_key(&fq->key); kfree(fq->flush_rq); kfree(fq); } diff --git a/block/blk.h b/block/blk.h index dfab98465db9..806fd6537295 100644 --- a/block/blk.h +++ b/block/blk.h @@ -25,7 +25,6 @@ struct blk_flush_queue { struct list_head flush_data_in_flight; struct request *flush_rq; - struct lock_class_key key; spinlock_t mq_flush_lock; }; -- 2.22.0

From: Sargun Dhillon <sargun@sargun.me> mainline inclusion from mainline-5.11-rc1 commit d18a9d3fa0f27a47706fb67f1ee0f4d971587c4e category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... --------------------------- There was refactoring done to use the fs_context for mounting done in: 62a55d088cd87: NFS: Additional refactoring for fs_context conversion This made it so that the net_ns is fetched from the fs_context (the netns that fsopen is called in). This change also makes it so that the credential fetched during fsopen is used as well as the net_ns. NFS has already had a number of changes to prepare it for user namespaces: 1a58e8a0e5c1: NFS: Store the credential of the mount process in the nfs_server 264d948ce7d0: NFS: Convert NFSv3 to use the container user namespace c207db2f5da5: NFS: Convert NFSv2 to use the container user namespace Previously, different credentials could be used for creation of the fs_context versus creation of the nfs_server, as FSCONFIG_CMD_CREATE did the actual credential check, and that's where current_creds() were fetched. This meant that the user namespace which fsopen was called in could be a non-init user namespace. This still requires that the user that calls FSCONFIG_CMD_CREATE has CAP_SYS_ADMIN in the init user ns. This roughly allows a privileged user to mount on behalf of an unprivileged usernamespace, by forking off and calling fsopen in the unprivileged user namespace. It can then pass back that fsfd to the privileged process which can configure the NFS mount, and then it can call FSCONFIG_CMD_CREATE before switching back into the mount namespace of the container, and finish up the mounting process and call fsmount and move_mount. Signed-off-by: Sargun Dhillon <sargun@sargun.me> Tested-by: Alban Crequy <alban.crequy@gmail.com> Fixes: 62a55d088cd8 ("NFS: Additional refactoring for fs_context conversion") Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Signed-off-by: Zhang Yi <yi.zhang@huawei.com> Reviewed-by: Zhang Xiaoxu <zhangxiaoxu5@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- fs/nfs/client.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 723d425796cc..e365ef543f4e 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -571,7 +571,7 @@ static int nfs_start_lockd(struct nfs_server *server) 1 : 0, .net = clp->cl_net, .nlmclnt_ops = clp->cl_nfs_mod->rpc_ops->nlmclnt_ops, - .cred = current_cred(), + .cred = server->cred, }; if (nlm_init.nfs_version > 3) @@ -985,7 +985,7 @@ struct nfs_server *nfs_create_server(struct fs_context *fc) if (!server) return ERR_PTR(-ENOMEM); - server->cred = get_cred(current_cred()); + server->cred = get_cred(fc->cred); error = -ENOMEM; fattr = nfs_alloc_fattr(); -- 2.22.0

From: Yang Li <yang.lee@linux.alibaba.com> mainline inclusion from mainline-v5.13-rc1 commit 1406f0f3440265deec6932fd611549b07ac76e89 category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ------------------------------------------------------------- In one of the error paths of the for_each_child_of_node() loop, add missing call to of_node_put(). Fix the following coccicheck warning: ./drivers/crypto/nx/nx-common-powernv.c:927:1-23: WARNING: Function "for_each_child_of_node" should have of_node_put() before return around line 936. Reported-by: Abaci Robot <abaci@linux.alibaba.com> Signed-off-by: Yang Li <yang.lee@linux.alibaba.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: Cui GaoSheng <cuigaosheng1@huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- drivers/crypto/nx/nx-common-powernv.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/crypto/nx/nx-common-powernv.c b/drivers/crypto/nx/nx-common-powernv.c index 13c65deda8e9..446f611726df 100644 --- a/drivers/crypto/nx/nx-common-powernv.c +++ b/drivers/crypto/nx/nx-common-powernv.c @@ -932,8 +932,10 @@ static int __init nx_powernv_probe_vas(struct device_node *pn) ret = find_nx_device_tree(dn, chip_id, vasid, NX_CT_GZIP, "ibm,p9-nx-gzip", &ct_gzip); - if (ret) + if (ret) { + of_node_put(dn); return ret; + } } if (!ct_842 || !ct_gzip) { -- 2.22.0

From: "zhangyi (F)" <yi.zhang@huawei.com> mainline inclusion from mainline-v5.14 commit 3af3d772f7216cf23081bb4176e86f1219d32ebc category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ----------------------------------------------- We have already delete block_dump feature in mark_inode_dirty() because it can be replaced by tracepoints, now we also remove the part in submit_bio() for the same reason. The part of block dump feature in submit_bio() dump the write process, write region and sectors on the target disk into kernel message. it can be replaced by block_bio_queue tracepoint in submit_bio_checks(), so we do not need block_dump anymore, remove the whole block_dump feature. Signed-off-by: zhangyi (F) <yi.zhang@huawei.com> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Christoph Hellwig <hch@lst.de> Link: https://lore.kernel.org/r/20210313030146.2882027-3-yi.zhang@huawei.com Signed-off-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Ye Bin <yebin10@huawei.com> Reviewed-by: Zhang Yi <yi.zhang@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- block/blk-core.c | 9 --------- include/linux/writeback.h | 1 - kernel/sysctl.c | 8 -------- mm/page-writeback.c | 5 ----- 4 files changed, 23 deletions(-) diff --git a/block/blk-core.c b/block/blk-core.c index 2d53e2ff48ff..02da3baf0bf7 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1098,15 +1098,6 @@ blk_qc_t submit_bio(struct bio *bio) task_io_account_read(bio->bi_iter.bi_size); count_vm_events(PGPGIN, count); } - - if (unlikely(block_dump)) { - char b[BDEVNAME_SIZE]; - printk(KERN_DEBUG "%s(%d): %s block %Lu on %s (%u sectors)\n", - current->comm, task_pid_nr(current), - op_is_write(bio_op(bio)) ? "WRITE" : "READ", - (unsigned long long)bio->bi_iter.bi_sector, - bio_devname(bio, b), count); - } } /* diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 8e5c5bb16e2d..9ef50176f3a1 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -360,7 +360,6 @@ extern unsigned int dirty_writeback_interval; extern unsigned int dirty_expire_interval; extern unsigned int dirtytime_expire_interval; extern int vm_highmem_is_dirtyable; -extern int block_dump; extern int laptop_mode; int dirty_background_ratio_handler(struct ctl_table *table, int write, diff --git a/kernel/sysctl.c b/kernel/sysctl.c index b9306d2bb426..1d8b4358aa11 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2946,14 +2946,6 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { - .procname = "block_dump", - .data = &block_dump, - .maxlen = sizeof(block_dump), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - }, { .procname = "vfs_cache_pressure", .data = &sysctl_vfs_cache_pressure, diff --git a/mm/page-writeback.c b/mm/page-writeback.c index eb34d204d4ee..b72da123f242 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -108,11 +108,6 @@ EXPORT_SYMBOL_GPL(dirty_writeback_interval); */ unsigned int dirty_expire_interval = 30 * 100; /* centiseconds */ -/* - * Flag that makes the machine dump writes/reads and block dirtyings. - */ -int block_dump; - /* * Flag that puts the machine in "laptop mode". Doubles as a timeout in jiffies: * a full sync is triggered after this time elapses without any disk activity. -- 2.22.0

From: Dan Williams <dan.j.williams@intel.com> mainline inclusion from mainline-5.11-rc5 commit dad4e5b390866ca902653df0daa864ae4b8d4147 category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... --------------------------- The conversion to move pfn_to_online_page() internal to soft_offline_page() missed that the get_user_pages() reference taken by the madvise() path needs to be dropped when pfn_to_online_page() fails. Note the direct sysfs-path to soft_offline_page() does not perform a get_user_pages() lookup. When soft_offline_page() is handed a pfn_valid() && !pfn_to_online_page() pfn the kernel hangs at dax-device shutdown due to a leaked reference. Link: https://lkml.kernel.org/r/161058501210.1840162.8108917599181157327.stgit@dwi... Fixes: feec24a6139d ("mm, soft-offline: convert parameter to pfn") Signed-off-by: Dan Williams <dan.j.williams@intel.com> Reviewed-by: David Hildenbrand <david@redhat.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Reviewed-by: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Qian Cai <cai@lca.pw> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Nanyong Sun <sunnanyong@huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- mm/memory-failure.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 01445ddff58d..d00d1b2e97da 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1886,6 +1886,12 @@ static int soft_offline_free_page(struct page *page) return rc; } +static void put_ref_page(struct page *page) +{ + if (page) + put_page(page); +} + /** * soft_offline_page - Soft offline a page. * @pfn: pfn to soft-offline @@ -1911,20 +1917,26 @@ static int soft_offline_free_page(struct page *page) int soft_offline_page(unsigned long pfn, int flags) { int ret; - struct page *page; bool try_again = true; + struct page *page, *ref_page = NULL; + + WARN_ON_ONCE(!pfn_valid(pfn) && (flags & MF_COUNT_INCREASED)); if (!pfn_valid(pfn)) return -ENXIO; + if (flags & MF_COUNT_INCREASED) + ref_page = pfn_to_page(pfn); + /* Only online pages can be soft-offlined (esp., not ZONE_DEVICE). */ page = pfn_to_online_page(pfn); - if (!page) + if (!page) { + put_ref_page(ref_page); return -EIO; + } if (PageHWPoison(page)) { pr_info("soft offline: %#lx page already poisoned\n", pfn); - if (flags & MF_COUNT_INCREASED) - put_page(page); + put_ref_page(ref_page); return 0; } -- 2.22.0

From: Ard Biesheuvel <ardb@kernel.org> mainline inclusion from mainline-v5.12-rc1 commit 5a69e1b73d54 category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ----------------------------------------------- Instead of calling into kernel_neon_end() and kernel_neon_begin() (and potentially into schedule()) from the assembler code when running in task mode and a reschedule is pending, perform only the preempt count check in assembler, but simply return early in this case, and let the C code deal with the consequences. This reverts commit 7df8d164753e6e6f229b72767595072bc6a71f48. Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: Wei Li <liwei391@huawei.com> Reviewed-by: Jason Yan <yanaijie@huawei.com> Reviewed-by: Hanjun Guo <guohanjun@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm64/crypto/sha1-ce-core.S | 47 ++++++++++++-------------------- arch/arm64/crypto/sha1-ce-glue.c | 22 ++++++++------- 2 files changed, 29 insertions(+), 40 deletions(-) diff --git a/arch/arm64/crypto/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S index 92d0d2753e81..8c02bbc2684e 100644 --- a/arch/arm64/crypto/sha1-ce-core.S +++ b/arch/arm64/crypto/sha1-ce-core.S @@ -62,40 +62,34 @@ .endm /* - * void sha1_ce_transform(struct sha1_ce_state *sst, u8 const *src, - * int blocks) + * int sha1_ce_transform(struct sha1_ce_state *sst, u8 const *src, + * int blocks) */ SYM_FUNC_START(sha1_ce_transform) - frame_push 3 - - mov x19, x0 - mov x20, x1 - mov x21, x2 - /* load round constants */ -0: loadrc k0.4s, 0x5a827999, w6 + loadrc k0.4s, 0x5a827999, w6 loadrc k1.4s, 0x6ed9eba1, w6 loadrc k2.4s, 0x8f1bbcdc, w6 loadrc k3.4s, 0xca62c1d6, w6 /* load state */ - ld1 {dgav.4s}, [x19] - ldr dgb, [x19, #16] + ld1 {dgav.4s}, [x0] + ldr dgb, [x0, #16] /* load sha1_ce_state::finalize */ ldr_l w4, sha1_ce_offsetof_finalize, x4 - ldr w4, [x19, x4] + ldr w4, [x0, x4] /* load input */ -1: ld1 {v8.4s-v11.4s}, [x20], #64 - sub w21, w21, #1 +0: ld1 {v8.4s-v11.4s}, [x1], #64 + sub w2, w2, #1 CPU_LE( rev32 v8.16b, v8.16b ) CPU_LE( rev32 v9.16b, v9.16b ) CPU_LE( rev32 v10.16b, v10.16b ) CPU_LE( rev32 v11.16b, v11.16b ) -2: add t0.4s, v8.4s, k0.4s +1: add t0.4s, v8.4s, k0.4s mov dg0v.16b, dgav.16b add_update c, ev, k0, 8, 9, 10, 11, dgb @@ -126,25 +120,18 @@ CPU_LE( rev32 v11.16b, v11.16b ) add dgbv.2s, dgbv.2s, dg1v.2s add dgav.4s, dgav.4s, dg0v.4s - cbz w21, 3f - - if_will_cond_yield_neon - st1 {dgav.4s}, [x19] - str dgb, [x19, #16] - do_cond_yield_neon + cbz w2, 2f + cond_yield 3f, x5 b 0b - endif_yield_neon - - b 1b /* * Final block: add padding and total bit count. * Skip if the input size was not a round multiple of the block size, * the padding is handled by the C code in that case. */ -3: cbz x4, 4f +2: cbz x4, 3f ldr_l w4, sha1_ce_offsetof_count, x4 - ldr x4, [x19, x4] + ldr x4, [x0, x4] movi v9.2d, #0 mov x8, #0x80000000 movi v10.2d, #0 @@ -153,11 +140,11 @@ CPU_LE( rev32 v11.16b, v11.16b ) mov x4, #0 mov v11.d[0], xzr mov v11.d[1], x7 - b 2b + b 1b /* store new state */ -4: st1 {dgav.4s}, [x19] - str dgb, [x19, #16] - frame_pop +3: st1 {dgav.4s}, [x0] + str dgb, [x0, #16] + mov w0, w2 ret SYM_FUNC_END(sha1_ce_transform) diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c index 8baf8d1846b6..c1757659516f 100644 --- a/arch/arm64/crypto/sha1-ce-glue.c +++ b/arch/arm64/crypto/sha1-ce-glue.c @@ -29,14 +29,22 @@ struct sha1_ce_state { extern const u32 sha1_ce_offsetof_count; extern const u32 sha1_ce_offsetof_finalize; -asmlinkage void sha1_ce_transform(struct sha1_ce_state *sst, u8 const *src, - int blocks); +asmlinkage int sha1_ce_transform(struct sha1_ce_state *sst, u8 const *src, + int blocks); static void __sha1_ce_transform(struct sha1_state *sst, u8 const *src, int blocks) { - sha1_ce_transform(container_of(sst, struct sha1_ce_state, sst), src, - blocks); + while (blocks) { + int rem; + + kernel_neon_begin(); + rem = sha1_ce_transform(container_of(sst, struct sha1_ce_state, + sst), src, blocks); + kernel_neon_end(); + src += (blocks - rem) * SHA1_BLOCK_SIZE; + blocks = rem; + } } const u32 sha1_ce_offsetof_count = offsetof(struct sha1_ce_state, sst.count); @@ -51,9 +59,7 @@ static int sha1_ce_update(struct shash_desc *desc, const u8 *data, return crypto_sha1_update(desc, data, len); sctx->finalize = 0; - kernel_neon_begin(); sha1_base_do_update(desc, data, len, __sha1_ce_transform); - kernel_neon_end(); return 0; } @@ -73,11 +79,9 @@ static int sha1_ce_finup(struct shash_desc *desc, const u8 *data, */ sctx->finalize = finalize; - kernel_neon_begin(); sha1_base_do_update(desc, data, len, __sha1_ce_transform); if (!finalize) sha1_base_do_finalize(desc, __sha1_ce_transform); - kernel_neon_end(); return sha1_base_finish(desc, out); } @@ -89,9 +93,7 @@ static int sha1_ce_final(struct shash_desc *desc, u8 *out) return crypto_sha1_finup(desc, NULL, 0, out); sctx->finalize = 0; - kernel_neon_begin(); sha1_base_do_finalize(desc, __sha1_ce_transform); - kernel_neon_end(); return sha1_base_finish(desc, out); } -- 2.22.0

From: Ard Biesheuvel <ardb@kernel.org> mainline inclusion from mainline-v5.12-rc1 commit 9ecc9f31d0a4 category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ----------------------------------------------- Instead of calling into kernel_neon_end() and kernel_neon_begin() (and potentially into schedule()) from the assembler code when running in task mode and a reschedule is pending, perform only the preempt count check in assembler, but simply return early in this case, and let the C code deal with the consequences. This reverts commit 7edc86cb1c18b4c274672232117586ea2bef1d9a. Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: Wei Li <liwei391@huawei.com> Reviewed-by: Jason Yan <yanaijie@huawei.com> Reviewed-by: Hanjun Guo <guohanjun@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm64/crypto/sha3-ce-core.S | 81 ++++++++++++-------------------- arch/arm64/crypto/sha3-ce-glue.c | 14 ++++-- 2 files changed, 39 insertions(+), 56 deletions(-) diff --git a/arch/arm64/crypto/sha3-ce-core.S b/arch/arm64/crypto/sha3-ce-core.S index 1cfb768df350..6f5208414fe3 100644 --- a/arch/arm64/crypto/sha3-ce-core.S +++ b/arch/arm64/crypto/sha3-ce-core.S @@ -37,20 +37,13 @@ .endm /* - * sha3_ce_transform(u64 *st, const u8 *data, int blocks, int dg_size) + * int sha3_ce_transform(u64 *st, const u8 *data, int blocks, int dg_size) */ .text SYM_FUNC_START(sha3_ce_transform) - frame_push 4 - - mov x19, x0 - mov x20, x1 - mov x21, x2 - mov x22, x3 - -0: /* load state */ - add x8, x19, #32 - ld1 { v0.1d- v3.1d}, [x19] + /* load state */ + add x8, x0, #32 + ld1 { v0.1d- v3.1d}, [x0] ld1 { v4.1d- v7.1d}, [x8], #32 ld1 { v8.1d-v11.1d}, [x8], #32 ld1 {v12.1d-v15.1d}, [x8], #32 @@ -58,13 +51,13 @@ SYM_FUNC_START(sha3_ce_transform) ld1 {v20.1d-v23.1d}, [x8], #32 ld1 {v24.1d}, [x8] -1: sub w21, w21, #1 +0: sub w2, w2, #1 mov w8, #24 adr_l x9, .Lsha3_rcon /* load input */ - ld1 {v25.8b-v28.8b}, [x20], #32 - ld1 {v29.8b-v31.8b}, [x20], #24 + ld1 {v25.8b-v28.8b}, [x1], #32 + ld1 {v29.8b-v31.8b}, [x1], #24 eor v0.8b, v0.8b, v25.8b eor v1.8b, v1.8b, v26.8b eor v2.8b, v2.8b, v27.8b @@ -73,10 +66,10 @@ SYM_FUNC_START(sha3_ce_transform) eor v5.8b, v5.8b, v30.8b eor v6.8b, v6.8b, v31.8b - tbnz x22, #6, 3f // SHA3-512 + tbnz x3, #6, 2f // SHA3-512 - ld1 {v25.8b-v28.8b}, [x20], #32 - ld1 {v29.8b-v30.8b}, [x20], #16 + ld1 {v25.8b-v28.8b}, [x1], #32 + ld1 {v29.8b-v30.8b}, [x1], #16 eor v7.8b, v7.8b, v25.8b eor v8.8b, v8.8b, v26.8b eor v9.8b, v9.8b, v27.8b @@ -84,34 +77,34 @@ SYM_FUNC_START(sha3_ce_transform) eor v11.8b, v11.8b, v29.8b eor v12.8b, v12.8b, v30.8b - tbnz x22, #4, 2f // SHA3-384 or SHA3-224 + tbnz x3, #4, 1f // SHA3-384 or SHA3-224 // SHA3-256 - ld1 {v25.8b-v28.8b}, [x20], #32 + ld1 {v25.8b-v28.8b}, [x1], #32 eor v13.8b, v13.8b, v25.8b eor v14.8b, v14.8b, v26.8b eor v15.8b, v15.8b, v27.8b eor v16.8b, v16.8b, v28.8b - b 4f + b 3f -2: tbz x22, #2, 4f // bit 2 cleared? SHA-384 +1: tbz x3, #2, 3f // bit 2 cleared? SHA-384 // SHA3-224 - ld1 {v25.8b-v28.8b}, [x20], #32 - ld1 {v29.8b}, [x20], #8 + ld1 {v25.8b-v28.8b}, [x1], #32 + ld1 {v29.8b}, [x1], #8 eor v13.8b, v13.8b, v25.8b eor v14.8b, v14.8b, v26.8b eor v15.8b, v15.8b, v27.8b eor v16.8b, v16.8b, v28.8b eor v17.8b, v17.8b, v29.8b - b 4f + b 3f // SHA3-512 -3: ld1 {v25.8b-v26.8b}, [x20], #16 +2: ld1 {v25.8b-v26.8b}, [x1], #16 eor v7.8b, v7.8b, v25.8b eor v8.8b, v8.8b, v26.8b -4: sub w8, w8, #1 +3: sub w8, w8, #1 eor3 v29.16b, v4.16b, v9.16b, v14.16b eor3 v26.16b, v1.16b, v6.16b, v11.16b @@ -190,33 +183,19 @@ SYM_FUNC_START(sha3_ce_transform) eor v0.16b, v0.16b, v31.16b - cbnz w8, 4b - cbz w21, 5f - - if_will_cond_yield_neon - add x8, x19, #32 - st1 { v0.1d- v3.1d}, [x19] - st1 { v4.1d- v7.1d}, [x8], #32 - st1 { v8.1d-v11.1d}, [x8], #32 - st1 {v12.1d-v15.1d}, [x8], #32 - st1 {v16.1d-v19.1d}, [x8], #32 - st1 {v20.1d-v23.1d}, [x8], #32 - st1 {v24.1d}, [x8] - do_cond_yield_neon - b 0b - endif_yield_neon - - b 1b + cbnz w8, 3b + cond_yield 3f, x8 + cbnz w2, 0b /* save state */ -5: st1 { v0.1d- v3.1d}, [x19], #32 - st1 { v4.1d- v7.1d}, [x19], #32 - st1 { v8.1d-v11.1d}, [x19], #32 - st1 {v12.1d-v15.1d}, [x19], #32 - st1 {v16.1d-v19.1d}, [x19], #32 - st1 {v20.1d-v23.1d}, [x19], #32 - st1 {v24.1d}, [x19] - frame_pop +3: st1 { v0.1d- v3.1d}, [x0], #32 + st1 { v4.1d- v7.1d}, [x0], #32 + st1 { v8.1d-v11.1d}, [x0], #32 + st1 {v12.1d-v15.1d}, [x0], #32 + st1 {v16.1d-v19.1d}, [x0], #32 + st1 {v20.1d-v23.1d}, [x0], #32 + st1 {v24.1d}, [x0] + mov w0, w2 ret SYM_FUNC_END(sha3_ce_transform) diff --git a/arch/arm64/crypto/sha3-ce-glue.c b/arch/arm64/crypto/sha3-ce-glue.c index ddf7aca9ff45..d6cfb792b66c 100644 --- a/arch/arm64/crypto/sha3-ce-glue.c +++ b/arch/arm64/crypto/sha3-ce-glue.c @@ -28,8 +28,8 @@ MODULE_ALIAS_CRYPTO("sha3-256"); MODULE_ALIAS_CRYPTO("sha3-384"); MODULE_ALIAS_CRYPTO("sha3-512"); -asmlinkage void sha3_ce_transform(u64 *st, const u8 *data, int blocks, - int md_len); +asmlinkage int sha3_ce_transform(u64 *st, const u8 *data, int blocks, + int md_len); static int sha3_update(struct shash_desc *desc, const u8 *data, unsigned int len) @@ -59,11 +59,15 @@ static int sha3_update(struct shash_desc *desc, const u8 *data, blocks = len / sctx->rsiz; len %= sctx->rsiz; - if (blocks) { + while (blocks) { + int rem; + kernel_neon_begin(); - sha3_ce_transform(sctx->st, data, blocks, digest_size); + rem = sha3_ce_transform(sctx->st, data, blocks, + digest_size); kernel_neon_end(); - data += blocks * sctx->rsiz; + data += (blocks - rem) * sctx->rsiz; + blocks = rem; } } -- 2.22.0

From: Ard Biesheuvel <ardb@kernel.org> mainline inclusion from mainline-v5.12-rc1 commit f5943ef456f8 category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ----------------------------------------------- There is no need for elaborate yield handling in the bit-sliced NEON implementation of AES, given that skciphers are naturally bounded by the size of the chunks returned by the skcipher_walk API. So remove the yield calls from the asm code. Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: Wei Li <liwei391@huawei.com> Reviewed-by: Jason Yan <yanaijie@huawei.com> Reviewed-by: Hanjun Guo <guohanjun@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm64/crypto/aes-neonbs-core.S | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/arch/arm64/crypto/aes-neonbs-core.S b/arch/arm64/crypto/aes-neonbs-core.S index 63a52ad9a75c..a3405b8c344b 100644 --- a/arch/arm64/crypto/aes-neonbs-core.S +++ b/arch/arm64/crypto/aes-neonbs-core.S @@ -613,7 +613,6 @@ SYM_FUNC_END(aesbs_decrypt8) st1 {\o7\().16b}, [x19], #16 cbz x23, 1f - cond_yield_neon b 99b 1: frame_pop @@ -715,7 +714,6 @@ SYM_FUNC_START(aesbs_cbc_decrypt) 1: st1 {v24.16b}, [x24] // store IV cbz x23, 2f - cond_yield_neon b 99b 2: frame_pop @@ -801,7 +799,7 @@ SYM_FUNC_END(__xts_crypt8) mov x23, x4 mov x24, x5 -0: movi v30.2s, #0x1 + movi v30.2s, #0x1 movi v25.2s, #0x87 uzp1 v30.4s, v30.4s, v25.4s ld1 {v25.16b}, [x24] @@ -846,7 +844,6 @@ SYM_FUNC_END(__xts_crypt8) cbz x23, 1f st1 {v25.16b}, [x24] - cond_yield_neon 0b b 99b 1: st1 {v25.16b}, [x24] @@ -889,7 +886,7 @@ SYM_FUNC_START(aesbs_ctr_encrypt) cset x26, ne add x23, x23, x26 // do one extra block if final -98: ldp x7, x8, [x24] + ldp x7, x8, [x24] ld1 {v0.16b}, [x24] CPU_LE( rev x7, x7 ) CPU_LE( rev x8, x8 ) @@ -967,7 +964,6 @@ CPU_LE( rev x8, x8 ) st1 {v0.16b}, [x24] cbz x23, .Lctr_done - cond_yield_neon 98b b 99b .Lctr_done: -- 2.22.0

From: Ard Biesheuvel <ardb@kernel.org> mainline inclusion from mainline-v5.12-rc1 commit fc754c024a34 category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ----------------------------------------------- Instead of yielding from the bowels of the asm routine if a reschedule is needed, divide up the input into 4 KB chunks in the C glue. This simplifies the code substantially, and avoids scheduling out the task with the asm routine on the call stack, which is undesirable from a CFI/instrumentation point of view. Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: Wei Li <liwei391@huawei.com> Reviewed-by: Jason Yan <yanaijie@huawei.com> Reviewed-by: Hanjun Guo <guohanjun@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm64/crypto/crct10dif-ce-core.S | 43 +++++++-------------------- arch/arm64/crypto/crct10dif-ce-glue.c | 30 +++++++++++++++---- 2 files changed, 35 insertions(+), 38 deletions(-) diff --git a/arch/arm64/crypto/crct10dif-ce-core.S b/arch/arm64/crypto/crct10dif-ce-core.S index 111d9c9abddd..dce6dcebfca1 100644 --- a/arch/arm64/crypto/crct10dif-ce-core.S +++ b/arch/arm64/crypto/crct10dif-ce-core.S @@ -68,10 +68,10 @@ .text .arch armv8-a+crypto - init_crc .req w19 - buf .req x20 - len .req x21 - fold_consts_ptr .req x22 + init_crc .req w0 + buf .req x1 + len .req x2 + fold_consts_ptr .req x3 fold_consts .req v10 @@ -257,12 +257,6 @@ CPU_LE( ext v12.16b, v12.16b, v12.16b, #8 ) .endm .macro crc_t10dif_pmull, p - frame_push 4, 128 - - mov init_crc, w0 - mov buf, x1 - mov len, x2 - __pmull_init_\p // For sizes less than 256 bytes, we can't fold 128 bytes at a time. @@ -317,26 +311,7 @@ CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 ) fold_32_bytes \p, v6, v7 subs len, len, #128 - b.lt .Lfold_128_bytes_loop_done_\@ - - if_will_cond_yield_neon - stp q0, q1, [sp, #.Lframe_local_offset] - stp q2, q3, [sp, #.Lframe_local_offset + 32] - stp q4, q5, [sp, #.Lframe_local_offset + 64] - stp q6, q7, [sp, #.Lframe_local_offset + 96] - do_cond_yield_neon - ldp q0, q1, [sp, #.Lframe_local_offset] - ldp q2, q3, [sp, #.Lframe_local_offset + 32] - ldp q4, q5, [sp, #.Lframe_local_offset + 64] - ldp q6, q7, [sp, #.Lframe_local_offset + 96] - ld1 {fold_consts.2d}, [fold_consts_ptr] - __pmull_init_\p - __pmull_pre_\p fold_consts - endif_yield_neon - - b .Lfold_128_bytes_loop_\@ - -.Lfold_128_bytes_loop_done_\@: + b.ge .Lfold_128_bytes_loop_\@ // Now fold the 112 bytes in v0-v6 into the 16 bytes in v7. @@ -453,7 +428,9 @@ CPU_LE( ext v0.16b, v0.16b, v0.16b, #8 ) // Final CRC value (x^16 * M(x)) mod G(x) is in low 16 bits of v0. umov w0, v0.h[0] - frame_pop + .ifc \p, p8 + ldp x29, x30, [sp], #16 + .endif ret .Lless_than_256_bytes_\@: @@ -489,7 +466,9 @@ CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 ) // Assumes len >= 16. // SYM_FUNC_START(crc_t10dif_pmull_p8) - crc_t10dif_pmull p8 + stp x29, x30, [sp, #-16]! + mov x29, sp + crc_t10dif_pmull p8 SYM_FUNC_END(crc_t10dif_pmull_p8) .align 5 diff --git a/arch/arm64/crypto/crct10dif-ce-glue.c b/arch/arm64/crypto/crct10dif-ce-glue.c index ccc3f6067742..09eb1456aed4 100644 --- a/arch/arm64/crypto/crct10dif-ce-glue.c +++ b/arch/arm64/crypto/crct10dif-ce-glue.c @@ -37,9 +37,18 @@ static int crct10dif_update_pmull_p8(struct shash_desc *desc, const u8 *data, u16 *crc = shash_desc_ctx(desc); if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && crypto_simd_usable()) { - kernel_neon_begin(); - *crc = crc_t10dif_pmull_p8(*crc, data, length); - kernel_neon_end(); + do { + unsigned int chunk = length; + + if (chunk > SZ_4K + CRC_T10DIF_PMULL_CHUNK_SIZE) + chunk = SZ_4K; + + kernel_neon_begin(); + *crc = crc_t10dif_pmull_p8(*crc, data, chunk); + kernel_neon_end(); + data += chunk; + length -= chunk; + } while (length); } else { *crc = crc_t10dif_generic(*crc, data, length); } @@ -53,9 +62,18 @@ static int crct10dif_update_pmull_p64(struct shash_desc *desc, const u8 *data, u16 *crc = shash_desc_ctx(desc); if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && crypto_simd_usable()) { - kernel_neon_begin(); - *crc = crc_t10dif_pmull_p64(*crc, data, length); - kernel_neon_end(); + do { + unsigned int chunk = length; + + if (chunk > SZ_4K + CRC_T10DIF_PMULL_CHUNK_SIZE) + chunk = SZ_4K; + + kernel_neon_begin(); + *crc = crc_t10dif_pmull_p64(*crc, data, chunk); + kernel_neon_end(); + data += chunk; + length -= chunk; + } while (length); } else { *crc = crc_t10dif_generic(*crc, data, length); } -- 2.22.0

From: Ard Biesheuvel <ardb@kernel.org> mainline inclusion from mainline-v5.13-rc1 commit 4c4dcd3541f8 category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ----------------------------------------------- The AArch64 asm syntax has this slightly tedious property that the names used in mnemonics to refer to registers depend on whether the opcode in question targets the entire 64-bits (xN), or only the least significant 8, 16 or 32 bits (wN). When writing parameterized code such as macros, this can be annoying, as macro arguments don't lend themselves to indexed lookups, and so generating a reference to wN in a macro that receives xN as an argument is problematic. For instance, an upcoming patch that modifies the implementation of the cond_yield macro to be able to refer to 32-bit registers would need to modify invocations such as cond_yield 3f, x8 to cond_yield 3f, 8 so that the second argument can be token pasted after x or w to emit the correct register reference. Unfortunately, this interferes with the self documenting nature of the first example, where the second argument is obviously a register, whereas in the second example, one would need to go and look at the code to find out what '8' means. So let's fix this by defining wxN aliases for all xN registers, which resolve to the 32-bit alias of each respective 64-bit register. This allows the macro implementation to paste the xN reference after a w to obtain the correct register name. Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Acked-by: Will Deacon <will@kernel.org> Link: https://lore.kernel.org/r/20210302090118.30666-3-ardb@kernel.org Signed-off-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Wei Li <liwei391@huawei.com> Reviewed-by: Jason Yan <yanaijie@huawei.com> Reviewed-by: Hanjun Guo <guohanjun@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm64/include/asm/assembler.h | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 2746aaa61438..21d679bf1e55 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -23,6 +23,14 @@ #include <asm/ptrace.h> #include <asm/thread_info.h> + /* + * Provide a wxN alias for each wN register so what we can paste a xN + * reference after a 'w' to obtain the 32-bit version. + */ + .irp n,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30 + wx\n .req w\n + .endr + .macro save_and_disable_daif, flags mrs \flags, daif msr daifset, #0xf -- 2.22.0

From: Jason Yan <yanaijie@huawei.com> mainline inclusion from mainline-v5.14 commit 1ee2753422349723d27009f2f973d03289d430ab category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ----------------------------------------------- When a SCSI device is offline a MODE SENSE command will return a result with only DID_NO_CONNECT set. In sd_read_write_protect_flag() only the status byte of the result is checked. Despite a returned status of DID_NO_CONNECT the command is considered successful and we read sdkp->write_prot from a buffer containing garbage. Modify scsi_status_is_good() to treat DID_NO_CONNECT as a failure case. Link: https://lore.kernel.org/r/20210330114727.234467-1-yanaijie@huawei.com Signed-off-by: Jason Yan <yanaijie@huawei.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Ye Bin <yebin10@huawei.com> Reviewed-by: Jason Yan <yanaijie@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- include/scsi/scsi.h | 54 +++++++++++++++++++++++---------------------- 1 file changed, 28 insertions(+), 26 deletions(-) diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h index 5339baadc082..7ac50dbee475 100644 --- a/include/scsi/scsi.h +++ b/include/scsi/scsi.h @@ -30,32 +30,6 @@ enum scsi_timeouts { */ #define SCAN_WILD_CARD ~0 -/** scsi_status_is_good - check the status return. - * - * @status: the status passed up from the driver (including host and - * driver components) - * - * This returns true for known good conditions that may be treated as - * command completed normally - */ -static inline int scsi_status_is_good(int status) -{ - /* - * FIXME: bit0 is listed as reserved in SCSI-2, but is - * significant in SCSI-3. For now, we follow the SCSI-2 - * behaviour and ignore reserved bits. - */ - status &= 0xfe; - return ((status == SAM_STAT_GOOD) || - (status == SAM_STAT_CONDITION_MET) || - /* Next two "intermediate" statuses are obsolete in SAM-4 */ - (status == SAM_STAT_INTERMEDIATE) || - (status == SAM_STAT_INTERMEDIATE_CONDITION_MET) || - /* FIXME: this is obsolete in SAM-3 */ - (status == SAM_STAT_COMMAND_TERMINATED)); -} - - /* * standard mode-select header prepended to all mode-select commands */ @@ -274,4 +248,32 @@ static inline int scsi_is_wlun(u64 lun) /* Used to obtain the PCI location of a device */ #define SCSI_IOCTL_GET_PCI 0x5387 +/** scsi_status_is_good - check the status return. + * + * @status: the status passed up from the driver (including host and + * driver components) + * + * This returns true for known good conditions that may be treated as + * command completed normally + */ +static inline int scsi_status_is_good(int status) +{ + if (host_byte(status) == DID_NO_CONNECT) + return 0; + + /* + * FIXME: bit0 is listed as reserved in SCSI-2, but is + * significant in SCSI-3. For now, we follow the SCSI-2 + * behaviour and ignore reserved bits. + */ + status &= 0xfe; + return ((status == SAM_STAT_GOOD) || + (status == SAM_STAT_CONDITION_MET) || + /* Next two "intermediate" statuses are obsolete in SAM-4 */ + (status == SAM_STAT_INTERMEDIATE) || + (status == SAM_STAT_INTERMEDIATE_CONDITION_MET) || + /* FIXME: this is obsolete in SAM-3 */ + (status == SAM_STAT_COMMAND_TERMINATED)); +} + #endif /* _SCSI_SCSI_H */ -- 2.22.0

From: Theodore Ts'o <tytso@mit.edu> mainline inclusion from mainline-5.14 commit 61bb4a1c417e5b95d9edb4f887f131de32e419cb category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ------------------------------------------------- After commit 618f003199c6 ("ext4: fix memory leak in ext4_fill_super"), after the file system is remounted read-only, there is a race where the kmmpd thread can exit, causing sbi->s_mmp_tsk to point at freed memory, which the call to ext4_stop_mmpd() can trip over. Fix this by only allowing kmmpd() to exit when it is stopped via ext4_stop_mmpd(). Link: https://lore.kernel.org/r/20210707002433.3719773-1-tytso@mit.edu Reported-by: Ye Bin <yebin10@huawei.com> Bug-Report-Link: <20210629143603.2166962-1-yebin10@huawei.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Baokun Li <libaokun1@huawei.com> Reviewed-by: Zhang Yi <yi.zhang@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- fs/ext4/mmp.c | 31 +++++++++++++++---------------- fs/ext4/super.c | 6 +++++- 2 files changed, 20 insertions(+), 17 deletions(-) diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 6cb598b549ca..bc364c119af6 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -156,7 +156,12 @@ static int kmmpd(void *data) memcpy(mmp->mmp_nodename, init_utsname()->nodename, sizeof(mmp->mmp_nodename)); - while (!kthread_should_stop()) { + while (!kthread_should_stop() && !sb_rdonly(sb)) { + if (!ext4_has_feature_mmp(sb)) { + ext4_warning(sb, "kmmpd being stopped since MMP feature" + " has been disabled."); + goto wait_to_exit; + } if (++seq > EXT4_MMP_SEQ_MAX) seq = 1; @@ -177,16 +182,6 @@ static int kmmpd(void *data) failed_writes++; } - if (!(le32_to_cpu(es->s_feature_incompat) & - EXT4_FEATURE_INCOMPAT_MMP)) { - ext4_warning(sb, "kmmpd being stopped since MMP feature" - " has been disabled."); - goto exit_thread; - } - - if (sb_rdonly(sb)) - break; - diff = jiffies - last_update_time; if (diff < mmp_update_interval * HZ) schedule_timeout_interruptible(mmp_update_interval * @@ -207,7 +202,7 @@ static int kmmpd(void *data) ext4_error_err(sb, -retval, "error reading MMP data: %d", retval); - goto exit_thread; + goto wait_to_exit; } mmp_check = (struct mmp_struct *)(bh_check->b_data); @@ -221,7 +216,7 @@ static int kmmpd(void *data) ext4_error_err(sb, EBUSY, "abort"); put_bh(bh_check); retval = -EBUSY; - goto exit_thread; + goto wait_to_exit; } put_bh(bh_check); } @@ -244,7 +239,13 @@ static int kmmpd(void *data) retval = write_mmp_block(sb, bh); -exit_thread: +wait_to_exit: + while (!kthread_should_stop()) { + set_current_state(TASK_INTERRUPTIBLE); + if (!kthread_should_stop()) + schedule(); + } + set_current_state(TASK_RUNNING); return retval; } @@ -391,5 +392,3 @@ int ext4_multi_mount_protect(struct super_block *sb, brelse(bh); return 1; } - - diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 691c48bc965e..e90b848f0fab 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5960,7 +5960,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) */ ext4_mark_recovery_complete(sb, es); } - ext4_stop_mmpd(sbi); } else { /* Make sure we can mount this feature set readwrite */ if (ext4_has_feature_readonly(sb) || @@ -6074,6 +6073,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks) ext4_release_system_zone(sb); + if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb)) + ext4_stop_mmpd(sbi); + /* * Some options can be enabled by ext4 and/or by VFS mount flag * either way we need to make sure it matches in both *flags and @@ -6106,6 +6108,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) for (i = 0; i < EXT4_MAXQUOTAS; i++) kfree(to_free[i]); #endif + if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb)) + ext4_stop_mmpd(sbi); kfree(orig_data); return err; } -- 2.22.0

From: Ido Schimmel <idosch@nvidia.com> mainline inclusion from mainline-v5.13-rc1 commit 812fa71f0d967dea7616810f27e98135d410b27e category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ----------------------------------------------- Netfilter tries to reroute mangled packets as a different route might need to be used following the mangling. When this happens, netfilter does not populate the IP protocol, the source port and the destination port in the flow key. Therefore, FIB rules that match on these fields are ignored and packets can be misrouted. Solve this by dissecting the outer flow and populating the flow key before rerouting the packet. Note that flow dissection only happens when FIB rules that match on these fields are installed, so in the common case there should not be a penalty. Reported-by: Michal Soltys <msoltyspl@yandex.pl> Signed-off-by: Ido Schimmel <idosch@nvidia.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> Signed-off-by: Huang Guobin <huangguobin4@huawei.com> Reviewed-by: Yue Haibing <yuehaibing@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- net/ipv4/netfilter.c | 2 ++ net/ipv6/netfilter.c | 2 ++ 2 files changed, 4 insertions(+) diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 7c841037c533..aff707988e23 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -25,6 +25,7 @@ int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, un __be32 saddr = iph->saddr; __u8 flags; struct net_device *dev = skb_dst(skb)->dev; + struct flow_keys flkeys; unsigned int hh_len; sk = sk_to_full_sk(sk); @@ -48,6 +49,7 @@ int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, un fl4.flowi4_oif = l3mdev_master_ifindex(dev); fl4.flowi4_mark = skb->mark; fl4.flowi4_flags = flags; + fib4_rules_early_flow_dissect(net, skb, &fl4, &flkeys); rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) return PTR_ERR(rt); diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index ab9a279dd6d4..6ab710b5a1a8 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -24,6 +24,7 @@ int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff { const struct ipv6hdr *iph = ipv6_hdr(skb); struct sock *sk = sk_to_full_sk(sk_partial); + struct flow_keys flkeys; unsigned int hh_len; struct dst_entry *dst; int strict = (ipv6_addr_type(&iph->daddr) & @@ -38,6 +39,7 @@ int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff }; int err; + fib6_rules_early_flow_dissect(net, skb, &fl6, &flkeys); dst = ip6_route_output(net, sk, &fl6); err = dst->error; if (err) { -- 2.22.0

From: Vlad Buslov <vladbu@nvidia.com> mainline inclusion from mainline-v5.12-rc1 commit 6f1995523a0fac7dd4fc7d2f175604dd9f699338 category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ----------------------------------------------- The function fib6_walk_continue() cannot return a positive value when called from register_fib_notifier(), but ignoring causes static analyzer to generate warnings in users of register_fib_notifier() that try to convert returned error code to pointer with ERR_PTR(). Handle such case by explicitly checking for positive error values and converting them to -EINVAL in fib6_tables_dump(). Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Suggested-by: Ido Schimmel <idosch@nvidia.com> Signed-off-by: Vlad Buslov <vladbu@nvidia.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Huang Guobin <huangguobin4@huawei.com> Reviewed-by: Yue Haibing <yuehaibing@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- net/ipv6/ip6_fib.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 1fb79dbde0cb..679699e953f1 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -499,7 +499,7 @@ int fib6_tables_dump(struct net *net, struct notifier_block *nb, hlist_for_each_entry_rcu(tb, head, tb6_hlist) { err = fib6_table_dump(net, tb, w); - if (err < 0) + if (err) goto out; } } @@ -507,7 +507,8 @@ int fib6_tables_dump(struct net *net, struct notifier_block *nb, out: kfree(w); - return err; + /* The tree traversal function should never return a positive value. */ + return err > 0 ? -EINVAL : err; } static int fib6_dump_node(struct fib6_walker *w) -- 2.22.0

From: Cui GaoSheng <cuigaosheng1@huawei.com> ohos inclusion category: bugfix issue: #I3ZXZF CVE: NA ----------------------------------------------------------------- The value returned by get_region_number may exceed the usable memory positions indexed by bitmap, it will cause probabilistic boot failure in images which enabled kaslr. Fixes: 156b9ca54d0d ("[Backport] ARM: decompressor: add KASLR support") Signed-off-by: Cui GaoSheng <cuigaosheng1@huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- arch/arm/boot/compressed/kaslr.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/arch/arm/boot/compressed/kaslr.c b/arch/arm/boot/compressed/kaslr.c index cd54b49eec2f..278ae1dad6b2 100644 --- a/arch/arm/boot/compressed/kaslr.c +++ b/arch/arm/boot/compressed/kaslr.c @@ -178,13 +178,18 @@ static u32 count_suitable_regions(const void *fdt, struct regions *regions, return ret; } -static u32 get_region_number(u32 num, u32 *bitmap) +/* The caller ensures that num is within the range of regions.*/ +static u32 get_region_number(u32 num, u32 *bitmap, u32 size) { - u32 i; + u32 i, cnt = size * BITS_PER_BYTE * sizeof(u32); + + for (i = 0; i < cnt; i++) { + if (bitmap[i >> 5] & BIT(i & 0x1f)) + continue; + if (num-- == 0) + break; + } - for (i = 0; num > 0; i++) - if (!(bitmap[i >> 5] & BIT(i & 0x1f))) - num--; return i; } @@ -446,7 +451,7 @@ u32 kaslr_early_init(u32 *kaslr_offset, u32 image_base, u32 image_size, num = ((u16)seed * count) >> 16; puthex32(num); - *kaslr_offset = get_region_number(num, bitmap) * SZ_2M; + *kaslr_offset = get_region_number(num, bitmap, sizeof(bitmap) / sizeof(u32)) * SZ_2M; puthex32(*kaslr_offset); return *kaslr_offset; -- 2.22.0

From: Andrew Morton <akpm@linux-foundation.org> mainline inclusion from mainline-v5.11-rc1 commit 34fe653716b0d340bc26dd4823d2dbe00c57f849 category: bugfix issue: #I3ZXZF Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ----------------------------------------------- With a machine with 3 TB (more than 2 TB memory). If you use vmalloc to allocate > 2 TB memory, the array_size below will be overflowed. The array_size is an unsigned int and can only be used to allocate less than 2 TB memory. If you pass 2*1028*1028*1024*1024 = 2 * 2^40 in the argument of vmalloc. The array_size will become 2*2^31 = 2^32. The 2^32 cannot be store with a 32 bit integer. The fix is to change the type of array_size to unsigned long. [akpm@linux-foundation.org: rework for current mainline] Link: https://bugzilla.kernel.org/show_bug.cgi?id=210023 Reported-by: <hsinhuiwu@gmail.com> Cc: Matthew Wilcox <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Tong Tiangen <tongtiangen@huawei.com> Reviewed-by: Chen Wandun <chenwandun@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- mm/vmalloc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index c1243e0dac83..f988014288e6 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2463,9 +2463,11 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, { const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO; unsigned int nr_pages = get_vm_area_size(area) >> PAGE_SHIFT; - unsigned int array_size = nr_pages * sizeof(struct page *), i; + unsigned long array_size; + unsigned int i; struct page **pages; + array_size = (unsigned long)nr_pages * sizeof(struct page *); gfp_mask |= __GFP_NOWARN; if (!(gfp_mask & (GFP_DMA | GFP_DMA32))) gfp_mask |= __GFP_HIGHMEM; -- 2.22.0

From: Muchun Song <songmuchun@bytedance.com> mainline inclusion from mainline-v5.11-rc1 commit 7ad69832f37e3cea8557db6df7c793905f1135e8 category: bugfix issue: #I3ZXZF Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ----------------------------------------------- When we free a page whose order is very close to MAX_ORDER and greater than pageblock_order, it wastes some CPU cycles to increase max_order to MAX_ORDER one by one and check the pageblock migratetype of that page repeatedly especially when MAX_ORDER is much larger than pageblock_order. We also should not be checking migratetype of buddy when "order == MAX_ORDER - 1" as the buddy pfn may be invalid, so adjust the condition. With the new check, we don't need the max_order check anymore, so we replace it. Also adjust max_order initialization so that it's lower by one than previously, which makes the code hopefully more clear. Link: https://lkml.kernel.org/r/20201204155109.55451-1-songmuchun@bytedance.com Fixes: d9dddbf55667 ("mm/page_alloc: prevent merging between isolated and other pageblocks") Signed-off-by: Muchun Song <songmuchun@bytedance.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Reviewed-by: Oscar Salvador <osalvador@suse.de> Reviewed-by: David Hildenbrand <david@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Tong Tiangen <tongtiangen@huawei.com> Reviewed-by: Chen Wandun <chenwandun@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- mm/page_alloc.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ff8fbc65a78d..6d189b69a9e1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -996,7 +996,7 @@ static inline void __free_one_page(struct page *page, struct page *buddy; bool to_tail; - max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1); + max_order = min_t(unsigned int, MAX_ORDER - 1, pageblock_order); VM_BUG_ON(!zone_is_initialized(zone)); VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP, page); @@ -1009,7 +1009,7 @@ static inline void __free_one_page(struct page *page, VM_BUG_ON_PAGE(bad_range(zone, page), page); continue_merging: - while (order < max_order - 1) { + while (order < max_order) { if (compaction_capture(capc, page, order, migratetype)) { __mod_zone_freepage_state(zone, -(1 << order), migratetype); @@ -1035,7 +1035,7 @@ static inline void __free_one_page(struct page *page, pfn = combined_pfn; order++; } - if (max_order < MAX_ORDER) { + if (order < MAX_ORDER - 1) { /* If we are here, it means order is >= pageblock_order. * We want to prevent merge between freepages on isolate * pageblock and normal pageblock. Without this, pageblock @@ -1056,7 +1056,7 @@ static inline void __free_one_page(struct page *page, is_migrate_isolate(buddy_mt))) goto done_merging; } - max_order++; + max_order = order + 1; goto continue_merging; } -- 2.22.0

From: Muchun Song <songmuchun@bytedance.com> mainline inclusion from mainline-v5.11-rc1 commit 2484be0f88dc6c9670362d51f6a04f2da0626b50 category: bugfix issue: #I3ZXZF Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ----------------------------------------------- A max order page has no buddy page and never merges to another order. So isolating and then freeing it is pointless. Link: https://lkml.kernel.org/r/20201202122114.75316-1-songmuchun@bytedance.com Fixes: 3c605096d315 ("mm/page_alloc: restrict max order of merging on isolated pageblock") Signed-off-by: Muchun Song <songmuchun@bytedance.com> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Reviewed-by: David Hildenbrand <david@redhat.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Matthew Wilcox <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Tong Tiangen <tongtiangen@huawei.com> Reviewed-by: Chen Wandun <chenwandun@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- mm/page_isolation.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/page_isolation.c b/mm/page_isolation.c index abbf42214485..756d1542f2c8 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -89,7 +89,7 @@ static void unset_migratetype_isolate(struct page *page, unsigned migratetype) */ if (PageBuddy(page)) { order = buddy_order(page); - if (order >= pageblock_order) { + if (order >= pageblock_order && order < MAX_ORDER - 1) { pfn = page_to_pfn(page); buddy_pfn = __find_buddy_pfn(pfn, order); buddy = page + (buddy_pfn - pfn); -- 2.22.0

From: Zhihao Cheng <chengzhihao1@huawei.com> mainline inclusion from mainline-v5.14 commit 819f9ab430a4478ce519e5cc8ae4de438d8ad4ba category: bugfix issue: #I3ZXZF Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... --------------------------- Since ubifs_xattr_get and ubifs_xattr_set cannot being executed parallelly after importing @host_ui->xattr_sem, now we can remove ui_mutex imported by commit ab92a20bce3b4c2 ("ubifs: make ubifs_[get|set]xattr atomic"). @xattr_size, @xattr_names and @xattr_cnt can't be out of protection by @host_ui->mutex yet, they are sill accesed in other places, such as pack_inode() called by ubifs_write_inode() triggered by page-writeback. Signed-off-by: Zhihao Cheng <chengzhihao1@huawei.com> Signed-off-by: Richard Weinberger <richard@nod.at> Reviewed-by: Zhang Yi <yi.zhang@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- fs/ubifs/xattr.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index 17745f5462f0..258b97939ba2 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -208,13 +208,11 @@ static int change_xattr(struct ubifs_info *c, struct inode *host, err = -ENOMEM; goto out_free; } - mutex_lock(&ui->ui_mutex); kfree(ui->data); ui->data = buf; inode->i_size = ui->ui_size = size; old_size = ui->data_len; ui->data_len = size; - mutex_unlock(&ui->ui_mutex); mutex_lock(&host_ui->ui_mutex); host->i_ctime = current_time(host); @@ -362,7 +360,6 @@ ssize_t ubifs_xattr_get(struct inode *host, const char *name, void *buf, ubifs_assert(c, inode->i_size == ui->data_len); ubifs_assert(c, ubifs_inode(host)->xattr_size > ui->data_len); - mutex_lock(&ui->ui_mutex); if (buf) { /* If @buf is %NULL we are supposed to return the length */ if (ui->data_len > size) { @@ -375,7 +372,6 @@ ssize_t ubifs_xattr_get(struct inode *host, const char *name, void *buf, err = ui->data_len; out_iput: - mutex_unlock(&ui->ui_mutex); iput(inode); out_cleanup: up_read(&ubifs_inode(host)->xattr_sem); -- 2.22.0

From: Mingrui Ren <jiladahe1997@gmail.com> mainline inclusion from mainline-v5.11-rc1 commit aef1b6a27970607721a618a0b990716ca8dbbf9 category: bugfix issue: #I3ZXZF Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... ------------------------------------------------- As described in Documentation, poll_init() is called by kgdb to initialize hardware which supports both poll_put_char() and poll_get_char(). It's necessary to enable TXEN bit, otherwise, it will cause hardware fault and kernel panic when calling imx_poll_put_char(). Generally, if use /dev/ttymxc0 as kgdb console as well as system console, ttymxc0 is initialized early by system console which does enable TXEN bit.But when use /dev/ttymxc1 as kgbd console, ttymxc1 is only initialized by imx_poll_init() cannot enable the TXEN bit, which will cause kernel panic. Signed-off-by: Mingrui Ren <jiladahe1997@gmail.com> Link: https://lore.kernel.org/r/20201202072543.151-1-972931182@qq.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Lu Jialin <lujialin4@huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- drivers/tty/serial/imx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index cacf7266a262..a66301b3b33d 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -1881,7 +1881,7 @@ static int imx_uart_poll_init(struct uart_port *port) ucr1 |= UCR1_UARTEN; ucr1 &= ~(UCR1_TRDYEN | UCR1_RTSDEN | UCR1_RRDYEN); - ucr2 |= UCR2_RXEN; + ucr2 |= UCR2_RXEN | UCR2_TXEN; ucr2 &= ~UCR2_ATEN; imx_uart_writel(sport, ucr1, UCR1); -- 2.22.0

From: Yang Shi <shy828301@gmail.com> mainline inclusion from mainline-5.13-rc1 commit 41ca668a71e7b03743369a2c6d8b8edc1e943dc8 category: bugfix issue: #I3ZXZF Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... --------------------------- Currently registered shrinker is indicated by non-NULL shrinker->nr_deferred. This approach is fine with nr_deferred at the shrinker level, but the following patches will move MEMCG_AWARE shrinkers' nr_deferred to memcg level, so their shrinker->nr_deferred would always be NULL. This would prevent the shrinkers from unregistering correctly. Remove SHRINKER_REGISTERING since we could check if shrinker is registered successfully by the new flag. Link: https://lkml.kernel.org/r/20210311190845.9708-9-shy828301@gmail.com Signed-off-by: Yang Shi <shy828301@gmail.com> Acked-by: Kirill Tkhai <ktkhai@virtuozzo.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Roman Gushchin <guro@fb.com> Reviewed-by: Shakeel Butt <shakeelb@google.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Conflict: mm/vmscan.c Signed-off-by: Zhang Yi <yi.zhang@huawei.com> Reviewed-by: Yang Erkun <yangerkun@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- include/linux/shrinker.h | 7 ++++--- mm/vmscan.c | 39 +++++++++++++++------------------------ 2 files changed, 19 insertions(+), 27 deletions(-) diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 0f80123650e2..1eac79ce57d4 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -79,13 +79,14 @@ struct shrinker { #define DEFAULT_SEEKS 2 /* A good number if you don't know better. */ /* Flags */ -#define SHRINKER_NUMA_AWARE (1 << 0) -#define SHRINKER_MEMCG_AWARE (1 << 1) +#define SHRINKER_REGISTERED (1 << 0) +#define SHRINKER_NUMA_AWARE (1 << 1) +#define SHRINKER_MEMCG_AWARE (1 << 2) /* * It just makes sense when the shrinker is also MEMCG_AWARE for now, * non-MEMCG_AWARE shrinker should not have this flag set. */ -#define SHRINKER_NONSLAB (1 << 2) +#define SHRINKER_NONSLAB (1 << 3) extern int prealloc_shrinker(struct shrinker *shrinker); extern void register_shrinker_prepared(struct shrinker *shrinker); diff --git a/mm/vmscan.c b/mm/vmscan.c index 67d38334052e..3c6aa8b9caa9 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -187,18 +187,6 @@ static LIST_HEAD(shrinker_list); static DECLARE_RWSEM(shrinker_rwsem); #ifdef CONFIG_MEMCG -/* - * We allow subsystems to populate their shrinker-related - * LRU lists before register_shrinker_prepared() is called - * for the shrinker, since we don't want to impose - * restrictions on their internal registration order. - * In this case shrink_slab_memcg() may find corresponding - * bit is set in the shrinkers map. - * - * This value is used by the function to detect registering - * shrinkers and to skip do_shrink_slab() calls for them. - */ -#define SHRINKER_REGISTERING ((struct shrinker *)~0UL) static DEFINE_IDR(shrinker_idr); static int shrinker_nr_max; @@ -209,7 +197,7 @@ static int prealloc_memcg_shrinker(struct shrinker *shrinker) down_write(&shrinker_rwsem); /* This may call shrinker, so it must use down_read_trylock() */ - id = idr_alloc(&shrinker_idr, SHRINKER_REGISTERING, 0, 0, GFP_KERNEL); + id = idr_alloc(&shrinker_idr, shrinker, 0, 0, GFP_KERNEL); if (id < 0) goto unlock; @@ -234,9 +222,9 @@ static void unregister_memcg_shrinker(struct shrinker *shrinker) BUG_ON(id < 0); - down_write(&shrinker_rwsem); + lockdep_assert_held(&shrinker_rwsem); + idr_remove(&shrinker_idr, id); - up_write(&shrinker_rwsem); } static bool cgroup_reclaim(struct scan_control *sc) @@ -363,8 +351,11 @@ void free_prealloced_shrinker(struct shrinker *shrinker) if (!shrinker->nr_deferred) return; - if (shrinker->flags & SHRINKER_MEMCG_AWARE) + if (shrinker->flags & SHRINKER_MEMCG_AWARE) { + down_write(&shrinker_rwsem); unregister_memcg_shrinker(shrinker); + up_write(&shrinker_rwsem); + } kfree(shrinker->nr_deferred); shrinker->nr_deferred = NULL; @@ -374,10 +365,7 @@ void register_shrinker_prepared(struct shrinker *shrinker) { down_write(&shrinker_rwsem); list_add_tail(&shrinker->list, &shrinker_list); -#ifdef CONFIG_MEMCG - if (shrinker->flags & SHRINKER_MEMCG_AWARE) - idr_replace(&shrinker_idr, shrinker, shrinker->id); -#endif + shrinker->flags |= SHRINKER_REGISTERED; up_write(&shrinker_rwsem); } @@ -397,13 +385,16 @@ EXPORT_SYMBOL(register_shrinker); */ void unregister_shrinker(struct shrinker *shrinker) { - if (!shrinker->nr_deferred) + if (!(shrinker->flags & SHRINKER_REGISTERED)) return; - if (shrinker->flags & SHRINKER_MEMCG_AWARE) - unregister_memcg_shrinker(shrinker); + down_write(&shrinker_rwsem); list_del(&shrinker->list); + shrinker->flags &= ~SHRINKER_REGISTERED; + if (shrinker->flags & SHRINKER_MEMCG_AWARE) + unregister_memcg_shrinker(shrinker); up_write(&shrinker_rwsem); + kfree(shrinker->nr_deferred); shrinker->nr_deferred = NULL; } @@ -569,7 +560,7 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, struct shrinker *shrinker; shrinker = idr_find(&shrinker_idr, i); - if (unlikely(!shrinker || shrinker == SHRINKER_REGISTERING)) { + if (unlikely(!shrinker || !(shrinker->flags & SHRINKER_REGISTERED))) { if (!shrinker) clear_bit(i, map->map); continue; -- 2.22.0

From: Zhang Yi <yi.zhang@huawei.com> mainline inclusion from mainline-v5.14-rc1 commit fcf37549ae19e904bc6a5eadf5c25eca36100c5e category: bugfix issue: #I3ZXZF Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... --------------------------- Although we merged c044f3d8360 ("jbd2: abort journal if free a async write error metadata buffer"), there is a race between jbd2_journal_try_to_free_buffers() and jbd2_journal_destroy(), so the jbd2_log_do_checkpoint() may still fail to detect the buffer write io error flag which may lead to filesystem inconsistency. jbd2_journal_try_to_free_buffers() ext4_put_super() jbd2_journal_destroy() __jbd2_journal_remove_checkpoint() detect buffer write error jbd2_log_do_checkpoint() jbd2_cleanup_journal_tail() <--- lead to inconsistency jbd2_journal_abort() Fix this issue by introducing a new atomic flag which only have one JBD2_CHECKPOINT_IO_ERROR bit now, and set it in __jbd2_journal_remove_checkpoint() when freeing a checkpoint buffer which has write_io_error flag. Then jbd2_journal_destroy() will detect this mark and abort the journal to prevent updating log tail. Signed-off-by: Zhang Yi <yi.zhang@huawei.com> Reviewed-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20210610112440.3438139-3-yi.zhang@huawei.com Signed-off-by: Theodore Ts'o <tytso@mit.edu> Reviewed-by: Yang Erkun <yangerkun@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- fs/jbd2/checkpoint.c | 12 ++++++++++++ fs/jbd2/journal.c | 14 ++++++++++++++ include/linux/jbd2.h | 11 +++++++++++ 3 files changed, 37 insertions(+) diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 96a5713b466a..172a5ad64071 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -564,6 +564,7 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) struct transaction_chp_stats_s *stats; transaction_t *transaction; journal_t *journal; + struct buffer_head *bh = jh2bh(jh); JBUFFER_TRACE(jh, "entry"); @@ -575,6 +576,17 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) journal = transaction->t_journal; JBUFFER_TRACE(jh, "removing from transaction"); + + /* + * If we have failed to write the buffer out to disk, the filesystem + * may become inconsistent. We cannot abort the journal here since + * we hold j_list_lock and we have to be careful about races with + * jbd2_journal_destroy(). So mark the writeback IO error in the + * journal here and we abort the journal later from a better context. + */ + if (buffer_write_io_error(bh)) + set_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags); + __buffer_unlink(jh); jh->b_cp_transaction = NULL; jbd2_journal_put_journal_head(jh); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 188f79d76988..1a11b06b9de9 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1618,6 +1618,10 @@ int jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid, if (is_journal_aborted(journal)) return -EIO; + if (test_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags)) { + jbd2_journal_abort(journal, -EIO); + return -EIO; + } BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); jbd_debug(1, "JBD2: updating superblock (start %lu, seq %u)\n", @@ -1997,6 +2001,16 @@ int jbd2_journal_destroy(journal_t *journal) J_ASSERT(journal->j_checkpoint_transactions == NULL); spin_unlock(&journal->j_list_lock); + /* + * OK, all checkpoint transactions have been checked, now check the + * write out io error flag and abort the journal if some buffer failed + * to write back to the original location, otherwise the filesystem + * may become inconsistent. + */ + if (!is_journal_aborted(journal) && + test_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags)) + jbd2_journal_abort(journal, -EIO); + if (journal->j_sb_buffer) { if (!is_journal_aborted(journal)) { mutex_lock_io(&journal->j_checkpoint_mutex); diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 578ff196b3ce..b737024b4b9c 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -771,6 +771,11 @@ struct journal_s */ unsigned long j_flags; + /** + * @j_atomic_flags: Atomic journaling state flags. + */ + unsigned long j_atomic_flags; + /** * @j_errno: * @@ -1361,6 +1366,12 @@ JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit, FAST_COMMIT) #define JBD2_FAST_COMMIT_ONGOING 0x100 /* Fast commit is ongoing */ #define JBD2_FULL_COMMIT_ONGOING 0x200 /* Full commit is ongoing */ +/* + * Journal atomic flag definitions + */ +#define JBD2_CHECKPOINT_IO_ERROR 0x001 /* Detect io error while writing + * buffer back to disk */ + /* * Function declarations for the journaling transaction and buffer * management -- 2.22.0

From: Zhang Yi <yi.zhang@huawei.com> mainline inclusion from mainline-v5.14-rc1 commit 214eb5a4d8a2032fb9f0711d1b202eb88ee02920 category: bugfix issue: #I3ZXZF Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... --------------------------- Now that __jbd2_journal_remove_checkpoint() can detect buffer io error and mark journal checkpoint error, then we abort the journal later before updating log tail to ensure the filesystem works consistently. So we could remove other redundant buffer io error checkes. Signed-off-by: Zhang Yi <yi.zhang@huawei.com> Reviewed-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20210610112440.3438139-5-yi.zhang@huawei.com Signed-off-by: Theodore Ts'o <tytso@mit.edu> Reviewed-by: Yang Erkun <yangerkun@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- fs/jbd2/checkpoint.c | 13 ++----------- 1 file changed, 2 insertions(+), 11 deletions(-) diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 172a5ad64071..e804e567e90e 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -91,8 +91,7 @@ static int __try_to_free_cp_buf(struct journal_head *jh) int ret = 0; struct buffer_head *bh = jh2bh(jh); - if (jh->b_transaction == NULL && !buffer_locked(bh) && - !buffer_dirty(bh) && !buffer_write_io_error(bh)) { + if (!jh->b_transaction && !buffer_locked(bh) && !buffer_dirty(bh)) { JBUFFER_TRACE(jh, "remove from checkpoint list"); ret = __jbd2_journal_remove_checkpoint(jh) + 1; } @@ -228,7 +227,6 @@ int jbd2_log_do_checkpoint(journal_t *journal) * OK, we need to start writing disk blocks. Take one transaction * and write it. */ - result = 0; spin_lock(&journal->j_list_lock); if (!journal->j_checkpoint_transactions) goto out; @@ -295,8 +293,6 @@ int jbd2_log_do_checkpoint(journal_t *journal) goto restart; } if (!buffer_dirty(bh)) { - if (unlikely(buffer_write_io_error(bh)) && !result) - result = -EIO; BUFFER_TRACE(bh, "remove from checkpoint"); if (__jbd2_journal_remove_checkpoint(jh)) /* The transaction was released; we're done */ @@ -356,8 +352,6 @@ int jbd2_log_do_checkpoint(journal_t *journal) spin_lock(&journal->j_list_lock); goto restart2; } - if (unlikely(buffer_write_io_error(bh)) && !result) - result = -EIO; /* * Now in whatever state the buffer currently is, we @@ -369,10 +363,7 @@ int jbd2_log_do_checkpoint(journal_t *journal) } out: spin_unlock(&journal->j_list_lock); - if (result < 0) - jbd2_journal_abort(journal, result); - else - result = jbd2_cleanup_journal_tail(journal); + result = jbd2_cleanup_journal_tail(journal); return (result < 0) ? result : 0; } -- 2.22.0

From: Zhang Yi <yi.zhang@huawei.com> mainline inclusion from mainline-5.14-rc1 commit dbf2bab7935b65689f3b39178cf87374f0334ead category: bugfix issue: #I3ZXZF Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... --------------------------- Now that __try_to_free_cp_buf() remove checkpointed buffer or transaction when the buffer is not 'busy', which is only called by journal_clean_one_cp_list(). This patch simplify this function by remove __try_to_free_cp_buf() and invoke __cp_buffer_busy() directly. Signed-off-by: Zhang Yi <yi.zhang@huawei.com> Reviewed-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20210610112440.3438139-7-yi.zhang@huawei.com Signed-off-by: Theodore Ts'o <tytso@mit.edu> Reviewed-by: Yang Erkun <yangerkun@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- fs/jbd2/checkpoint.c | 30 ++++-------------------------- 1 file changed, 4 insertions(+), 26 deletions(-) diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 28109638276e..e9111793c0bf 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -91,25 +91,6 @@ static inline bool __cp_buffer_busy(struct journal_head *jh) return (jh->b_transaction || buffer_locked(bh) || buffer_dirty(bh)); } -/* - * Try to release a checkpointed buffer from its transaction. - * Returns 1 if we released it and 2 if we also released the - * whole transaction. - * - * Requires j_list_lock - */ -static int __try_to_free_cp_buf(struct journal_head *jh) -{ - int ret = 0; - struct buffer_head *bh = jh2bh(jh); - - if (!jh->b_transaction && !buffer_locked(bh) && !buffer_dirty(bh)) { - JBUFFER_TRACE(jh, "remove from checkpoint list"); - ret = __jbd2_journal_remove_checkpoint(jh) + 1; - } - return ret; -} - /* * __jbd2_log_wait_for_space: wait until there is space in the journal. * @@ -440,7 +421,6 @@ static int journal_clean_one_cp_list(struct journal_head *jh, bool destroy) { struct journal_head *last_jh; struct journal_head *next_jh = jh; - int ret; if (!jh) return 0; @@ -449,13 +429,11 @@ static int journal_clean_one_cp_list(struct journal_head *jh, bool destroy) do { jh = next_jh; next_jh = jh->b_cpnext; - if (!destroy) - ret = __try_to_free_cp_buf(jh); - else - ret = __jbd2_journal_remove_checkpoint(jh) + 1; - if (!ret) + + if (!destroy && __cp_buffer_busy(jh)) return 0; - if (ret == 2) + + if (__jbd2_journal_remove_checkpoint(jh)) return 1; /* * This function only frees up some memory -- 2.22.0

From: Zhang Yi <yi.zhang@huawei.com> mainline inclusion from mainline-5.14-rc1 commit acc6100d3ffa24bdd2add8ea85fb66811bcce5d4 category: bugfix issue: #I3ZXZF Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... --------------------------- After remove the unique user of sop->bdev_try_to_free_page() callback, we could remove the callback and the corresponding blkdev_releasepage() at all. Signed-off-by: Zhang Yi <yi.zhang@huawei.com> Reviewed-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20210610112440.3438139-9-yi.zhang@huawei.com Signed-off-by: Theodore Ts'o <tytso@mit.edu> Reviewed-by: Yang Erkun <yangerkun@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- fs/block_dev.c | 15 --------------- include/linux/fs.h | 1 - 2 files changed, 16 deletions(-) diff --git a/fs/block_dev.c b/fs/block_dev.c index 6a1295815bd2..b24051a9ed9f 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1964,20 +1964,6 @@ ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to) } EXPORT_SYMBOL_GPL(blkdev_read_iter); -/* - * Try to release a page associated with block device when the system - * is under memory pressure. - */ -static int blkdev_releasepage(struct page *page, gfp_t wait) -{ - struct super_block *super = BDEV_I(page->mapping->host)->bdev.bd_super; - - if (super && super->s_op->bdev_try_to_free_page) - return super->s_op->bdev_try_to_free_page(super, page, wait); - - return try_to_free_buffers(page); -} - static int blkdev_writepages(struct address_space *mapping, struct writeback_control *wbc) { @@ -1991,7 +1977,6 @@ static const struct address_space_operations def_blk_aops = { .write_begin = blkdev_write_begin, .write_end = blkdev_write_end, .writepages = blkdev_writepages, - .releasepage = blkdev_releasepage, .direct_IO = blkdev_direct_IO, .migratepage = buffer_migrate_page_norefs, .is_dirty_writeback = buffer_check_dirty_writeback, diff --git a/include/linux/fs.h b/include/linux/fs.h index 5724f099cf70..638f1c7e4052 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1960,7 +1960,6 @@ struct super_operations { ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); struct dquot **(*get_dquots)(struct inode *); #endif - int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t); long (*nr_cached_objects)(struct super_block *, struct shrink_control *); long (*free_cached_objects)(struct super_block *, -- 2.22.0

From: Theodore Ts'o <tytso@mit.edu> mainline inclusion from mainline-5.14-rc1 commit 0705e8d1e2207ceeb83dc6e1751b6b82718b353a category: bugfix issue: #I3ZXZF Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... --------------------------- The function jbd2_journal_unregister_shrinker() was getting called twice when the file system was getting unmounted. On Power and ARM platforms this was causing kernel crash when unmounting the file system, when a percpu_counter was destroyed twice. Fix this by removing jbd2_journal_[un]register_shrinker() functions, and inlining the shrinker setup and teardown into journal_init_common() and jbd2_journal_destroy(). This means that ext4 and ocfs2 now no longer need to know about registering and unregistering jbd2's shrinker. Also, while we're at it, rename the percpu counter from j_jh_shrink_count to j_checkpoint_jh_count, since this makes it clearer what this counter is intended to track. Link: https://lore.kernel.org/r/20210705145025.3363130-1-tytso@mit.edu Fixes: 4ba3fcdde7e3 ("jbd2,ext4: add a shrinker to release checkpointed buffers") Reported-by: Jon Hunter <jonathanh@nvidia.com> Reported-by: Sachin Sant <sachinp@linux.vnet.ibm.com> Tested-by: Sachin Sant <sachinp@linux.vnet.ibm.com> Tested-by: Jon Hunter <jonathanh@nvidia.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Zhang Yi <yi.zhang@huawei.com> Reviewed-by: Yang Erkun <yangerkun@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- fs/ext4/super.c | 8 --- fs/jbd2/checkpoint.c | 4 +- fs/jbd2/journal.c | 149 +++++++++++++++++-------------------------- include/linux/jbd2.h | 6 +- 4 files changed, 64 insertions(+), 103 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index f0d6188ed278..ef8adada4649 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1181,7 +1181,6 @@ static void ext4_put_super(struct super_block *sb) ext4_unregister_sysfs(sb); if (sbi->s_journal) { - jbd2_journal_unregister_shrinker(sbi->s_journal); aborted = is_journal_aborted(sbi->s_journal); err = jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; @@ -5138,7 +5137,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_ea_block_cache = NULL; if (sbi->s_journal) { - jbd2_journal_unregister_shrinker(sbi->s_journal); jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; } @@ -5464,12 +5462,6 @@ static int ext4_load_journal(struct super_block *sb, ext4_commit_super(sb); } - err = jbd2_journal_register_shrinker(journal); - if (err) { - EXT4_SB(sb)->s_journal = NULL; - goto err_out; - } - return 0; err_out: diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index e9111793c0bf..646fb512bd1e 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -701,7 +701,7 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) __buffer_unlink(jh); jh->b_cp_transaction = NULL; - percpu_counter_dec(&journal->j_jh_shrink_count); + percpu_counter_dec(&journal->j_checkpoint_jh_count); jbd2_journal_put_journal_head(jh); /* Is this transaction empty? */ @@ -764,7 +764,7 @@ void __jbd2_journal_insert_checkpoint(struct journal_head *jh, jh->b_cpnext->b_cpprev = jh; } transaction->t_checkpoint_list = jh; - percpu_counter_inc(&transaction->t_journal->j_jh_shrink_count); + percpu_counter_inc(&transaction->t_journal->j_checkpoint_jh_count); } /* diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index d6759cd93268..d6873bb36e54 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1291,6 +1291,48 @@ static int jbd2_min_tag_size(void) return sizeof(journal_block_tag_t) - 4; } +/** + * jbd2_journal_shrink_scan() + * + * Scan the checkpointed buffer on the checkpoint list and release the + * journal_head. + */ +static unsigned long jbd2_journal_shrink_scan(struct shrinker *shrink, + struct shrink_control *sc) +{ + journal_t *journal = container_of(shrink, journal_t, j_shrinker); + unsigned long nr_to_scan = sc->nr_to_scan; + unsigned long nr_shrunk; + unsigned long count; + + count = percpu_counter_read_positive(&journal->j_checkpoint_jh_count); + trace_jbd2_shrink_scan_enter(journal, sc->nr_to_scan, count); + + nr_shrunk = jbd2_journal_shrink_checkpoint_list(journal, &nr_to_scan); + + count = percpu_counter_read_positive(&journal->j_checkpoint_jh_count); + trace_jbd2_shrink_scan_exit(journal, nr_to_scan, nr_shrunk, count); + + return nr_shrunk; +} + +/** + * jbd2_journal_shrink_count() + * + * Count the number of checkpoint buffers on the checkpoint list. + */ +static unsigned long jbd2_journal_shrink_count(struct shrinker *shrink, + struct shrink_control *sc) +{ + journal_t *journal = container_of(shrink, journal_t, j_shrinker); + unsigned long count; + + count = percpu_counter_read_positive(&journal->j_checkpoint_jh_count); + trace_jbd2_shrink_count(journal, sc->nr_to_scan, count); + + return count; +} + /* * Management for journal control blocks: functions to create and * destroy journal_t structures, and to initialise and read existing @@ -1369,9 +1411,23 @@ static journal_t *journal_init_common(struct block_device *bdev, journal->j_sb_buffer = bh; journal->j_superblock = (journal_superblock_t *)bh->b_data; + journal->j_shrink_transaction = NULL; + journal->j_shrinker.scan_objects = jbd2_journal_shrink_scan; + journal->j_shrinker.count_objects = jbd2_journal_shrink_count; + journal->j_shrinker.seeks = DEFAULT_SEEKS; + journal->j_shrinker.batch = journal->j_max_transaction_buffers; + + if (percpu_counter_init(&journal->j_checkpoint_jh_count, 0, GFP_KERNEL)) + goto err_cleanup; + + if (register_shrinker(&journal->j_shrinker)) { + percpu_counter_destroy(&journal->j_checkpoint_jh_count); + goto err_cleanup; + } return journal; err_cleanup: + brelse(journal->j_sb_buffer); kfree(journal->j_wbuf); jbd2_journal_destroy_revoke(journal); kfree(journal); @@ -1956,93 +2012,6 @@ int jbd2_journal_load(journal_t *journal) return -EIO; } -/** - * jbd2_journal_shrink_scan() - * - * Scan the checkpointed buffer on the checkpoint list and release the - * journal_head. - */ -static unsigned long jbd2_journal_shrink_scan(struct shrinker *shrink, - struct shrink_control *sc) -{ - journal_t *journal = container_of(shrink, journal_t, j_shrinker); - unsigned long nr_to_scan = sc->nr_to_scan; - unsigned long nr_shrunk; - unsigned long count; - - count = percpu_counter_read_positive(&journal->j_jh_shrink_count); - trace_jbd2_shrink_scan_enter(journal, sc->nr_to_scan, count); - - nr_shrunk = jbd2_journal_shrink_checkpoint_list(journal, &nr_to_scan); - - count = percpu_counter_read_positive(&journal->j_jh_shrink_count); - trace_jbd2_shrink_scan_exit(journal, nr_to_scan, nr_shrunk, count); - - return nr_shrunk; -} - -/** - * jbd2_journal_shrink_count() - * - * Count the number of checkpoint buffers on the checkpoint list. - */ -static unsigned long jbd2_journal_shrink_count(struct shrinker *shrink, - struct shrink_control *sc) -{ - journal_t *journal = container_of(shrink, journal_t, j_shrinker); - unsigned long count; - - count = percpu_counter_read_positive(&journal->j_jh_shrink_count); - trace_jbd2_shrink_count(journal, sc->nr_to_scan, count); - - return count; -} - -/** - * jbd2_journal_register_shrinker() - * @journal: Journal to act on. - * - * Init a percpu counter to record the checkpointed buffers on the checkpoint - * list and register a shrinker to release their journal_head. - */ -int jbd2_journal_register_shrinker(journal_t *journal) -{ - int err; - - journal->j_shrink_transaction = NULL; - - err = percpu_counter_init(&journal->j_jh_shrink_count, 0, GFP_KERNEL); - if (err) - return err; - - journal->j_shrinker.scan_objects = jbd2_journal_shrink_scan; - journal->j_shrinker.count_objects = jbd2_journal_shrink_count; - journal->j_shrinker.seeks = DEFAULT_SEEKS; - journal->j_shrinker.batch = journal->j_max_transaction_buffers; - - err = register_shrinker(&journal->j_shrinker); - if (err) { - percpu_counter_destroy(&journal->j_jh_shrink_count); - return err; - } - - return 0; -} -EXPORT_SYMBOL(jbd2_journal_register_shrinker); - -/** - * jbd2_journal_unregister_shrinker() - * @journal: Journal to act on. - * - * Unregister the checkpointed buffer shrinker and destroy the percpu counter. - */ -void jbd2_journal_unregister_shrinker(journal_t *journal) -{ - percpu_counter_destroy(&journal->j_jh_shrink_count); - unregister_shrinker(&journal->j_shrinker); -} -EXPORT_SYMBOL(jbd2_journal_unregister_shrinker); - /** * jbd2_journal_destroy() - Release a journal_t structure. * @journal: Journal to act on. @@ -2115,8 +2084,10 @@ int jbd2_journal_destroy(journal_t *journal) brelse(journal->j_sb_buffer); } - jbd2_journal_unregister_shrinker(journal); - + if (journal->j_shrinker.flags & SHRINKER_REGISTERED) { + percpu_counter_destroy(&journal->j_checkpoint_jh_count); + unregister_shrinker(&journal->j_shrinker); + } if (journal->j_proc_entry) jbd2_stats_proc_exit(journal); iput(journal->j_inode); diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index b435908644d1..9afcfef64a2b 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -908,11 +908,11 @@ struct journal_s struct shrinker j_shrinker; /** - * @j_jh_shrink_count: + * @j_checkpoint_jh_count: * * Number of journal buffers on the checkpoint list. [j_list_lock] */ - struct percpu_counter j_jh_shrink_count; + struct percpu_counter j_checkpoint_jh_count; /** * @j_shrink_transaction: @@ -1542,8 +1542,6 @@ extern int jbd2_journal_set_features (journal_t *, unsigned long, unsigned long, unsigned long); extern void jbd2_journal_clear_features (journal_t *, unsigned long, unsigned long, unsigned long); -extern int jbd2_journal_register_shrinker(journal_t *journal); -extern void jbd2_journal_unregister_shrinker(journal_t *journal); extern int jbd2_journal_load (journal_t *journal); extern int jbd2_journal_destroy (journal_t *); extern int jbd2_journal_recover (journal_t *journal); -- 2.22.0

From: Liu Jian <liujian56@huawei.com> mainline inclusion from mainline-net-next commit 23d2b94043ca8835bd1e67749020e839f396a1c2 category: bugfix issue: #I3ZXZF CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git/commit/?... -------------------------------- I got below panic when doing fuzz test: Kernel panic - not syncing: panic_on_warn set ... CPU: 0 PID: 4056 Comm: syz-executor.3 Tainted: G B 5.14.0-rc1-00195-gcff5c4254439-dirty #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack_lvl+0x7a/0x9b panic+0x2cd/0x5af end_report.cold+0x5a/0x5a kasan_report+0xec/0x110 ip_check_mc_rcu+0x556/0x5d0 __mkroute_output+0x895/0x1740 ip_route_output_key_hash_rcu+0x2d0/0x1050 ip_route_output_key_hash+0x182/0x2e0 ip_route_output_flow+0x28/0x130 udp_sendmsg+0x165d/0x2280 udpv6_sendmsg+0x121e/0x24f0 inet6_sendmsg+0xf7/0x140 sock_sendmsg+0xe9/0x180 ____sys_sendmsg+0x2b8/0x7a0 ___sys_sendmsg+0xf0/0x160 __sys_sendmmsg+0x17e/0x3c0 __x64_sys_sendmmsg+0x9e/0x100 do_syscall_64+0x3b/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x462eb9 Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f3df5af1c58 EFLAGS: 00000246 ORIG_RAX: 0000000000000133 RAX: ffffffffffffffda RBX: 000000000073bf00 RCX: 0000000000462eb9 RDX: 0000000000000312 RSI: 0000000020001700 RDI: 0000000000000007 RBP: 0000000000000004 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f3df5af26bc R13: 00000000004c372d R14: 0000000000700b10 R15: 00000000ffffffff It is one use-after-free in ip_check_mc_rcu. In ip_mc_del_src, the ip_sf_list of pmc has been freed under pmc->lock protection. But access to ip_sf_list in ip_check_mc_rcu is not protected by the lock. Signed-off-by: Liu Jian <liujian56@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Liu Jian <liujian56@huawei.com> Reviewed-by: Yue Haibing <yuehaibing@huawei.com> Signed-off-by: Chen Jun <chenjun102@huawei.com> Signed-off-by: Yu Changchun <yuchangchun1@huawei.com> --- net/ipv4/igmp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 6b3c558a4f23..03589a04f9aa 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2713,6 +2713,7 @@ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u rv = 1; } else if (im) { if (src_addr) { + spin_lock_bh(&im->lock); for (psf = im->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == src_addr) break; @@ -2723,6 +2724,7 @@ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u im->sfcount[MCAST_EXCLUDE]; else rv = im->sfcount[MCAST_EXCLUDE] != 0; + spin_unlock_bh(&im->lock); } else rv = 1; /* unspecified source; tentatively allow */ } -- 2.22.0