diff options
Diffstat (limited to 'kernel')
47 files changed, 465 insertions, 300 deletions
diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c index 6edff97ad594..6639640523c0 100644 --- a/kernel/bpf/bpf_inode_storage.c +++ b/kernel/bpf/bpf_inode_storage.c @@ -125,8 +125,12 @@ static int bpf_fd_inode_storage_update_elem(struct bpf_map *map, void *key, fd = *(int *)key; f = fget_raw(fd); - if (!f || !inode_storage_ptr(f->f_inode)) + if (!f) + return -EBADF; + if (!inode_storage_ptr(f->f_inode)) { + fput(f); return -EBADF; + } sdata = bpf_local_storage_update(f->f_inode, (struct bpf_local_storage_map *)map, @@ -176,14 +180,14 @@ BPF_CALL_4(bpf_inode_storage_get, struct bpf_map *, map, struct inode *, inode, * bpf_local_storage_update expects the owner to have a * valid storage pointer. */ - if (!inode_storage_ptr(inode)) + if (!inode || !inode_storage_ptr(inode)) return (unsigned long)NULL; sdata = inode_storage_lookup(inode, map, true); if (sdata) return (unsigned long)sdata->data; - /* This helper must only called from where the inode is gurranteed + /* This helper must only called from where the inode is guaranteed * to have a refcount and cannot be freed. */ if (flags & BPF_LOCAL_STORAGE_GET_F_CREATE) { @@ -200,7 +204,10 @@ BPF_CALL_4(bpf_inode_storage_get, struct bpf_map *, map, struct inode *, inode, BPF_CALL_2(bpf_inode_storage_delete, struct bpf_map *, map, struct inode *, inode) { - /* This helper must only called from where the inode is gurranteed + if (!inode) + return -EINVAL; + + /* This helper must only called from where the inode is guaranteed * to have a refcount and cannot be freed. */ return inode_storage_delete(inode, map); diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 70e5e0b6d69d..1622a44d1617 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -149,7 +149,11 @@ BTF_ID(func, bpf_lsm_file_ioctl) BTF_ID(func, bpf_lsm_file_lock) BTF_ID(func, bpf_lsm_file_open) BTF_ID(func, bpf_lsm_file_receive) + +#ifdef CONFIG_SECURITY_NETWORK BTF_ID(func, bpf_lsm_inet_conn_established) +#endif /* CONFIG_SECURITY_NETWORK */ + BTF_ID(func, bpf_lsm_inode_create) BTF_ID(func, bpf_lsm_inode_free_security) BTF_ID(func, bpf_lsm_inode_getattr) @@ -166,7 +170,11 @@ BTF_ID(func, bpf_lsm_inode_symlink) BTF_ID(func, bpf_lsm_inode_unlink) BTF_ID(func, bpf_lsm_kernel_module_request) BTF_ID(func, bpf_lsm_kernfs_init_security) + +#ifdef CONFIG_KEYS BTF_ID(func, bpf_lsm_key_free) +#endif /* CONFIG_KEYS */ + BTF_ID(func, bpf_lsm_mmap_file) BTF_ID(func, bpf_lsm_netlink_send) BTF_ID(func, bpf_lsm_path_notify) @@ -181,6 +189,8 @@ BTF_ID(func, bpf_lsm_sb_show_options) BTF_ID(func, bpf_lsm_sb_statfs) BTF_ID(func, bpf_lsm_sb_umount) BTF_ID(func, bpf_lsm_settime) + +#ifdef CONFIG_SECURITY_NETWORK BTF_ID(func, bpf_lsm_socket_accept) BTF_ID(func, bpf_lsm_socket_bind) BTF_ID(func, bpf_lsm_socket_connect) @@ -195,6 +205,8 @@ BTF_ID(func, bpf_lsm_socket_recvmsg) BTF_ID(func, bpf_lsm_socket_sendmsg) BTF_ID(func, bpf_lsm_socket_shutdown) BTF_ID(func, bpf_lsm_socket_socketpair) +#endif /* CONFIG_SECURITY_NETWORK */ + BTF_ID(func, bpf_lsm_syslog) BTF_ID(func, bpf_lsm_task_alloc) BTF_ID(func, bpf_lsm_task_getsecid) diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c index 4ef1959a78f2..e0da0258b732 100644 --- a/kernel/bpf/bpf_task_storage.c +++ b/kernel/bpf/bpf_task_storage.c @@ -218,7 +218,7 @@ BPF_CALL_4(bpf_task_storage_get, struct bpf_map *, map, struct task_struct *, * bpf_local_storage_update expects the owner to have a * valid storage pointer. */ - if (!task_storage_ptr(task)) + if (!task || !task_storage_ptr(task)) return (unsigned long)NULL; sdata = task_storage_lookup(task, map, true); @@ -243,6 +243,9 @@ BPF_CALL_4(bpf_task_storage_get, struct bpf_map *, map, struct task_struct *, BPF_CALL_2(bpf_task_storage_delete, struct bpf_map *, map, struct task_struct *, task) { + if (!task) + return -EINVAL; + /* This helper must only be called from places where the lifetime of the task * is guaranteed. Either by being refcounted or by being protected * by an RCU read-side critical section. diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 8d6bdb4f4d61..84a36ee4a4c2 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -4172,7 +4172,7 @@ static int btf_parse_hdr(struct btf_verifier_env *env) return -ENOTSUPP; } - if (btf_data_size == hdr->hdr_len) { + if (!btf->base_btf && btf_data_size == hdr->hdr_len) { btf_verifier_log(env, "No data"); return -EINVAL; } diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 6ec088a96302..6aa9e10c6335 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1391,12 +1391,13 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, if (ctx.optlen != 0) { *optlen = ctx.optlen; *kernel_optval = ctx.optval; + /* export and don't free sockopt buf */ + return 0; } } out: - if (ret) - sockopt_free_buf(&ctx); + sockopt_free_buf(&ctx); return ret; } @@ -1441,6 +1442,11 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, goto out; } + if (ctx.optlen < 0) { + ret = -EFAULT; + goto out; + } + if (copy_from_user(ctx.optval, optval, min(ctx.optlen, max_optlen)) != 0) { ret = -EFAULT; @@ -1458,7 +1464,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, goto out; } - if (ctx.optlen > max_optlen) { + if (ctx.optlen > max_optlen || ctx.optlen < 0) { ret = -EFAULT; goto out; } diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 7e848200cd26..c1ac7f964bc9 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -152,6 +152,7 @@ static void htab_init_buckets(struct bpf_htab *htab) lockdep_set_class(&htab->buckets[i].lock, &htab->lockdep_key); } + cond_resched(); } } diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index bd8a3183d030..41ca280b1dc1 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -108,7 +108,7 @@ BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value) } const struct bpf_func_proto bpf_map_peek_elem_proto = { - .func = bpf_map_pop_elem, + .func = bpf_map_peek_elem, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, diff --git a/kernel/bpf/preload/Makefile b/kernel/bpf/preload/Makefile index 23ee310b6eb4..1951332dd15f 100644 --- a/kernel/bpf/preload/Makefile +++ b/kernel/bpf/preload/Makefile @@ -4,8 +4,11 @@ LIBBPF_SRCS = $(srctree)/tools/lib/bpf/ LIBBPF_A = $(obj)/libbpf.a LIBBPF_OUT = $(abspath $(obj)) +# Although not in use by libbpf's Makefile, set $(O) so that the "dummy" test +# in tools/scripts/Makefile.include always succeeds when building the kernel +# with $(O) pointing to a relative path, as in "make O=build bindeb-pkg". $(LIBBPF_A): - $(Q)$(MAKE) -C $(LIBBPF_SRCS) OUTPUT=$(LIBBPF_OUT)/ $(LIBBPF_OUT)/libbpf.a + $(Q)$(MAKE) -C $(LIBBPF_SRCS) O=$(LIBBPF_OUT)/ OUTPUT=$(LIBBPF_OUT)/ $(LIBBPF_OUT)/libbpf.a userccflags += -I $(srctree)/tools/include/ -I $(srctree)/tools/include/uapi \ -I $(srctree)/tools/lib/ -Wno-unused-result diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index aea96b638473..bfafbf115bf3 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -115,6 +115,8 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) /* hash table size must be power of 2 */ n_buckets = roundup_pow_of_two(attr->max_entries); + if (!n_buckets) + return ERR_PTR(-E2BIG); cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap); cost += n_buckets * (value_size + sizeof(struct stack_map_bucket)); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 4caf06fe4152..e5999d86c76e 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -17,7 +17,6 @@ #include <linux/fs.h> #include <linux/license.h> #include <linux/filter.h> -#include <linux/version.h> #include <linux/kernel.h> #include <linux/idr.h> #include <linux/cred.h> @@ -2713,7 +2712,6 @@ out_unlock: out_put_prog: if (tgt_prog_fd && tgt_prog) bpf_prog_put(tgt_prog); - bpf_prog_put(prog); return err; } @@ -2826,7 +2824,10 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) tp_name = prog->aux->attach_func_name; break; } - return bpf_tracing_prog_attach(prog, 0, 0); + err = bpf_tracing_prog_attach(prog, 0, 0); + if (err >= 0) + return err; + goto out_put_prog; case BPF_PROG_TYPE_RAW_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: if (strncpy_from_user(buf, diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index e73c07593024..175b7b42bfc4 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -37,7 +37,7 @@ retry: if (!task) { ++*tid; goto retry; - } else if (skip_if_dup_files && task->tgid != task->pid && + } else if (skip_if_dup_files && !thread_group_leader(task) && task->files == task->group_leader->files) { put_task_struct(task); task = NULL; @@ -151,13 +151,14 @@ again: curr_task = info->task; curr_fd = info->fd; } else { - curr_task = task_seq_get_next(ns, &curr_tid, true); - if (!curr_task) { - info->task = NULL; - return NULL; - } - - /* set info->task and info->tid */ + curr_task = task_seq_get_next(ns, &curr_tid, true); + if (!curr_task) { + info->task = NULL; + info->tid = curr_tid; + return NULL; + } + + /* set info->task and info->tid */ info->task = curr_task; if (curr_tid == info->tid) { curr_fd = info->fd; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 17270b8404f1..37581919e050 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2217,6 +2217,8 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case PTR_TO_RDWR_BUF: case PTR_TO_RDWR_BUF_OR_NULL: case PTR_TO_PERCPU_BTF_ID: + case PTR_TO_MEM: + case PTR_TO_MEM_OR_NULL: return true; default: return false; @@ -5311,7 +5313,7 @@ static bool signed_add_overflows(s64 a, s64 b) return res < a; } -static bool signed_add32_overflows(s64 a, s64 b) +static bool signed_add32_overflows(s32 a, s32 b) { /* Do the add in u32, where overflow is well-defined */ s32 res = (s32)((u32)a + (u32)b); @@ -5321,7 +5323,7 @@ static bool signed_add32_overflows(s64 a, s64 b) return res < a; } -static bool signed_sub_overflows(s32 a, s32 b) +static bool signed_sub_overflows(s64 a, s64 b) { /* Do the sub in u64, where overflow is well-defined */ s64 res = (s64)((u64)a - (u64)b); @@ -5333,7 +5335,7 @@ static bool signed_sub_overflows(s32 a, s32 b) static bool signed_sub32_overflows(s32 a, s32 b) { - /* Do the sub in u64, where overflow is well-defined */ + /* Do the sub in u32, where overflow is well-defined */ s32 res = (s32)((u32)a - (u32)b); if (b < 0) @@ -6875,7 +6877,7 @@ static int is_branch32_taken(struct bpf_reg_state *reg, u32 val, u8 opcode) case BPF_JSGT: if (reg->s32_min_value > sval) return 1; - else if (reg->s32_max_value < sval) + else if (reg->s32_max_value <= sval) return 0; break; case BPF_JLT: @@ -6948,7 +6950,7 @@ static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode) case BPF_JSGT: if (reg->smin_value > sval) return 1; - else if (reg->smax_value < sval) + else if (reg->smax_value <= sval) return 0; break; case BPF_JLT: @@ -8588,7 +8590,11 @@ static bool range_within(struct bpf_reg_state *old, return old->umin_value <= cur->umin_value && old->umax_value >= cur->umax_value && old->smin_value <= cur->smin_value && - old->smax_value >= cur->smax_value; + old->smax_value >= cur->smax_value && + old->u32_min_value <= cur->u32_min_value && + old->u32_max_value >= cur->u32_max_value && + old->s32_min_value <= cur->s32_min_value && + old->s32_max_value >= cur->s32_max_value; } /* Maximum number of register states that can exist at once */ @@ -10997,30 +11003,28 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) insn->code == (BPF_ALU | BPF_MOD | BPF_X) || insn->code == (BPF_ALU | BPF_DIV | BPF_X)) { bool is64 = BPF_CLASS(insn->code) == BPF_ALU64; - struct bpf_insn mask_and_div[] = { - BPF_MOV32_REG(insn->src_reg, insn->src_reg), + bool isdiv = BPF_OP(insn->code) == BPF_DIV; + struct bpf_insn *patchlet; + struct bpf_insn chk_and_div[] = { /* Rx div 0 -> 0 */ - BPF_JMP_IMM(BPF_JNE, insn->src_reg, 0, 2), + BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | + BPF_JNE | BPF_K, insn->src_reg, + 0, 2, 0), BPF_ALU32_REG(BPF_XOR, insn->dst_reg, insn->dst_reg), BPF_JMP_IMM(BPF_JA, 0, 0, 1), *insn, }; - struct bpf_insn mask_and_mod[] = { - BPF_MOV32_REG(insn->src_reg, insn->src_reg), + struct bpf_insn chk_and_mod[] = { /* Rx mod 0 -> Rx */ - BPF_JMP_IMM(BPF_JEQ, insn->src_reg, 0, 1), + BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | + BPF_JEQ | BPF_K, insn->src_reg, + 0, 1, 0), *insn, }; - struct bpf_insn *patchlet; - if (insn->code == (BPF_ALU64 | BPF_DIV | BPF_X) || - insn->code == (BPF_ALU | BPF_DIV | BPF_X)) { - patchlet = mask_and_div + (is64 ? 1 : 0); - cnt = ARRAY_SIZE(mask_and_div) - (is64 ? 1 : 0); - } else { - patchlet = mask_and_mod + (is64 ? 1 : 0); - cnt = ARRAY_SIZE(mask_and_mod) - (is64 ? 1 : 0); - } + patchlet = isdiv ? chk_and_div : chk_and_mod; + cnt = isdiv ? ARRAY_SIZE(chk_and_div) : + ARRAY_SIZE(chk_and_mod); new_prog = bpf_patch_insn_data(env, i + delta, patchlet, cnt); if (!new_prog) diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 32596fdbcd5b..a5751784ad74 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -917,6 +917,9 @@ int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param) for_each_subsys(ss, i) { if (strcmp(param->key, ss->legacy_name)) continue; + if (!cgroup_ssid_enabled(i) || cgroup1_ssid_disabled(i)) + return invalfc(fc, "Disabled controller '%s'", + param->key); ctx->subsys_mask |= (1 << i); return 0; } diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 613845769103..1ea995f801ec 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3564,6 +3564,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, { struct psi_trigger *new; struct cgroup *cgrp; + struct psi_group *psi; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) @@ -3572,7 +3573,8 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, cgroup_get(cgrp); cgroup_kn_unlock(of->kn); - new = psi_trigger_create(&cgrp->psi, buf, nbytes, res); + psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi; + new = psi_trigger_create(psi, buf, nbytes, res); if (IS_ERR(new)) { cgroup_put(cgrp); return PTR_ERR(new); diff --git a/kernel/configs/android-recommended.config b/kernel/configs/android-recommended.config index 53d688bdd894..eb0029c9a6a6 100644 --- a/kernel/configs/android-recommended.config +++ b/kernel/configs/android-recommended.config @@ -81,7 +81,6 @@ CONFIG_INPUT_JOYSTICK=y CONFIG_INPUT_MISC=y CONFIG_INPUT_TABLET=y CONFIG_INPUT_UINPUT=y -CONFIG_ION=y CONFIG_JOYSTICK_XPAD=y CONFIG_JOYSTICK_XPAD_FF=y CONFIG_JOYSTICK_XPAD_LEDS=y diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c index b1496e744c68..da95df381483 100644 --- a/kernel/dma/map_benchmark.c +++ b/kernel/dma/map_benchmark.c @@ -36,7 +36,7 @@ struct map_benchmark { __s32 node; /* which numa node this benchmark will run on */ __u32 dma_bits; /* DMA addressing capability */ __u32 dma_dir; /* DMA data direction */ - __u64 expansion[10]; /* For future use */ + __u8 expansion[84]; /* For future use */ }; struct map_benchmark_data { @@ -147,8 +147,10 @@ static int do_map_benchmark(struct map_benchmark_data *map) atomic64_set(&map->sum_sq_unmap, 0); atomic64_set(&map->loops, 0); - for (i = 0; i < threads; i++) + for (i = 0; i < threads; i++) { + get_task_struct(tsk[i]); wake_up_process(tsk[i]); + } msleep_interruptible(map->bparam.seconds * 1000); @@ -183,6 +185,8 @@ static int do_map_benchmark(struct map_benchmark_data *map) } out: + for (i = 0; i < threads; i++) + put_task_struct(tsk[i]); put_device(map->dev); kfree(tsk); return ret; diff --git a/kernel/entry/common.c b/kernel/entry/common.c index 378341642f94..f9d491b17b78 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -209,26 +209,18 @@ static void exit_to_user_mode_prepare(struct pt_regs *regs) lockdep_sys_exit(); } -#ifndef _TIF_SINGLESTEP -static inline bool report_single_step(unsigned long work) -{ - return false; -} -#else /* * If SYSCALL_EMU is set, then the only reason to report is when - * TIF_SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP). This syscall + * SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP). This syscall * instruction has been already reported in syscall_enter_from_user_mode(). */ static inline bool report_single_step(unsigned long work) { - if (!(work & SYSCALL_WORK_SYSCALL_EMU)) + if (work & SYSCALL_WORK_SYSCALL_EMU) return false; - return !!(current_thread_info()->flags & _TIF_SINGLESTEP); + return work & SYSCALL_WORK_SYSCALL_EXIT_TRAP; } -#endif - static void syscall_exit_work(struct pt_regs *regs, unsigned long work) { diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c index b0338a5625d9..c240302f56e2 100644 --- a/kernel/entry/syscall_user_dispatch.c +++ b/kernel/entry/syscall_user_dispatch.c @@ -50,10 +50,10 @@ bool syscall_user_dispatch(struct pt_regs *regs) if (unlikely(__get_user(state, sd->selector))) do_exit(SIGSEGV); - if (likely(state == PR_SYS_DISPATCH_OFF)) + if (likely(state == SYSCALL_DISPATCH_FILTER_ALLOW)) return false; - if (state != PR_SYS_DISPATCH_ON) + if (state != SYSCALL_DISPATCH_FILTER_BLOCK) do_exit(SIGSYS); } diff --git a/kernel/fork.c b/kernel/fork.c index 37720a6d04ea..d66cd1014211 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -819,9 +819,8 @@ void __init fork_init(void) init_task.signal->rlim[RLIMIT_SIGPENDING] = init_task.signal->rlim[RLIMIT_NPROC]; - for (i = 0; i < UCOUNT_COUNTS; i++) { + for (i = 0; i < UCOUNT_COUNTS; i++) init_user_ns.ucount_max[i] = max_threads/2; - } #ifdef CONFIG_VMAP_STACK cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache", @@ -1654,9 +1653,8 @@ static inline void init_task_pid_links(struct task_struct *task) { enum pid_type type; - for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) { + for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) INIT_HLIST_NODE(&task->pid_links[type]); - } } static inline void diff --git a/kernel/futex.c b/kernel/futex.c index c47d1015d759..45a13eb8894e 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -763,6 +763,29 @@ static struct futex_pi_state *alloc_pi_state(void) return pi_state; } +static void pi_state_update_owner(struct futex_pi_state *pi_state, + struct task_struct *new_owner) +{ + struct task_struct *old_owner = pi_state->owner; + + lockdep_assert_held(&pi_state->pi_mutex.wait_lock); + + if (old_owner) { + raw_spin_lock(&old_owner->pi_lock); + WARN_ON(list_empty(&pi_state->list)); + list_del_init(&pi_state->list); + raw_spin_unlock(&old_owner->pi_lock); + } + + if (new_owner) { + raw_spin_lock(&new_owner->pi_lock); + WARN_ON(!list_empty(&pi_state->list)); + list_add(&pi_state->list, &new_owner->pi_state_list); + pi_state->owner = new_owner; + raw_spin_unlock(&new_owner->pi_lock); + } +} + static void get_pi_state(struct futex_pi_state *pi_state) { WARN_ON_ONCE(!refcount_inc_not_zero(&pi_state->refcount)); @@ -785,17 +808,11 @@ static void put_pi_state(struct futex_pi_state *pi_state) * and has cleaned up the pi_state already */ if (pi_state->owner) { - struct task_struct *owner; unsigned long flags; raw_spin_lock_irqsave(&pi_state->pi_mutex.wait_lock, flags); - owner = pi_state->owner; - if (owner) { - raw_spin_lock(&owner->pi_lock); - list_del_init(&pi_state->list); - raw_spin_unlock(&owner->pi_lock); - } - rt_mutex_proxy_unlock(&pi_state->pi_mutex, owner); + pi_state_update_owner(pi_state, NULL); + rt_mutex_proxy_unlock(&pi_state->pi_mutex); raw_spin_unlock_irqrestore(&pi_state->pi_mutex.wait_lock, flags); } @@ -941,7 +958,8 @@ static inline void exit_pi_state_list(struct task_struct *curr) { } * FUTEX_OWNER_DIED bit. See [4] * * [10] There is no transient state which leaves owner and user space - * TID out of sync. + * TID out of sync. Except one error case where the kernel is denied + * write access to the user address, see fixup_pi_state_owner(). * * * Serialization and lifetime rules: @@ -1521,26 +1539,15 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_ ret = -EINVAL; } - if (ret) - goto out_unlock; - - /* - * This is a point of no return; once we modify the uval there is no - * going back and subsequent operations must not fail. - */ - - raw_spin_lock(&pi_state->owner->pi_lock); - WARN_ON(list_empty(&pi_state->list)); - list_del_init(&pi_state->list); - raw_spin_unlock(&pi_state->owner->pi_lock); - - raw_spin_lock(&new_owner->pi_lock); - WARN_ON(!list_empty(&pi_state->list)); - list_add(&pi_state->list, &new_owner->pi_state_list); - pi_state->owner = new_owner; - raw_spin_unlock(&new_owner->pi_lock); - - postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q); + if (!ret) { + /* + * This is a point of no return; once we modified the uval + * there is no going back and subsequent operations must + * not fail. + */ + pi_state_update_owner(pi_state, new_owner); + postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q); + } out_unlock: raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); @@ -2323,18 +2330,13 @@ static void unqueue_me_pi(struct futex_q *q) spin_unlock(q->lock_ptr); } -static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, - |