diff -drupN a/drivers/android/binder.c b/drivers/android/binder.c --- a/drivers/android/binder.c 2018-08-06 17:23:04.000000000 +0300 +++ b/drivers/android/binder.c 2022-06-12 05:28:14.000000000 +0300 @@ -15,6 +15,40 @@ * */ +/* + * Locking overview + * + * There are 3 main spinlocks which must be acquired in the + * order shown: + * + * 1) proc->outer_lock : protects binder_ref + * binder_proc_lock() and binder_proc_unlock() are + * used to acq/rel. + * 2) node->lock : protects most fields of binder_node. + * binder_node_lock() and binder_node_unlock() are + * used to acq/rel + * 3) proc->inner_lock : protects the thread and node lists + * (proc->threads, proc->waiting_threads, proc->nodes) + * and all todo lists associated with the binder_proc + * (proc->todo, thread->todo, proc->delivered_death and + * node->async_todo), as well as thread->transaction_stack + * binder_inner_proc_lock() and binder_inner_proc_unlock() + * are used to acq/rel + * + * Any lock under procA must never be nested under any lock at the same + * level or below on procB. + * + * Functions that require a lock held on entry indicate which lock + * in the suffix of the function name: + * + * foo_olocked() : requires node->outer_lock + * foo_nlocked() : requires node->lock + * foo_ilocked() : requires proc->inner_lock + * foo_oilocked(): requires proc->outer_lock and proc->inner_lock + * foo_nilocked(): requires node->lock and proc->inner_lock + * ... + */ + #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include @@ -24,7 +58,6 @@ #include #include #include -#include #include #include #include @@ -34,31 +67,31 @@ #include #include #include -#include -#include #include #include +#include #ifdef CONFIG_ANDROID_BINDER_IPC_32BIT #define BINDER_IPC_32BIT 1 #endif #include +#include "binder_alloc.h" #include "binder_trace.h" -static DEFINE_MUTEX(binder_main_lock); +static HLIST_HEAD(binder_deferred_list); static DEFINE_MUTEX(binder_deferred_lock); -static DEFINE_MUTEX(binder_mmap_lock); +static HLIST_HEAD(binder_devices); static HLIST_HEAD(binder_procs); -static HLIST_HEAD(binder_deferred_list); +static DEFINE_MUTEX(binder_procs_lock); + static HLIST_HEAD(binder_dead_nodes); +static DEFINE_SPINLOCK(binder_dead_nodes_lock); static struct dentry *binder_debugfs_dir_entry_root; static struct dentry *binder_debugfs_dir_entry_proc; -static struct binder_node *binder_context_mgr_node; -static kuid_t binder_context_mgr_uid = INVALID_UID; -static int binder_last_id; +static atomic_t binder_last_id; #define BINDER_DEBUG_ENTRY(name) \ static int binder_##name##_open(struct inode *inode, struct file *file) \ @@ -104,22 +137,21 @@ enum { BINDER_DEBUG_TRANSACTION_COMPLETE = 1U << 10, BINDER_DEBUG_FREE_BUFFER = 1U << 11, BINDER_DEBUG_INTERNAL_REFS = 1U << 12, - BINDER_DEBUG_BUFFER_ALLOC = 1U << 13, - BINDER_DEBUG_PRIORITY_CAP = 1U << 14, - BINDER_DEBUG_BUFFER_ALLOC_ASYNC = 1U << 15, + BINDER_DEBUG_PRIORITY_CAP = 1U << 13, + BINDER_DEBUG_SPINLOCKS = 1U << 14, }; static uint32_t binder_debug_mask = BINDER_DEBUG_USER_ERROR | BINDER_DEBUG_FAILED_TRANSACTION | BINDER_DEBUG_DEAD_TRANSACTION; module_param_named(debug_mask, binder_debug_mask, uint, S_IWUSR | S_IRUGO); -static bool binder_debug_no_lock; -module_param_named(proc_no_lock, binder_debug_no_lock, bool, S_IWUSR | S_IRUGO); +static char *binder_devices_param = CONFIG_ANDROID_BINDER_DEVICES; +module_param_named(devices, binder_devices_param, charp, S_IRUGO); static DECLARE_WAIT_QUEUE_HEAD(binder_user_error_wait); static int binder_stop_on_user_error; static int binder_set_stop_on_user_error(const char *val, - struct kernel_param *kp) + const struct kernel_param *kp) { int ret; @@ -145,6 +177,17 @@ module_param_call(stop_on_user_error, bi binder_stop_on_user_error = 2; \ } while (0) +#define to_flat_binder_object(hdr) \ + container_of(hdr, struct flat_binder_object, hdr) + +#define to_binder_fd_object(hdr) container_of(hdr, struct binder_fd_object, hdr) + +#define to_binder_buffer_object(hdr) \ + container_of(hdr, struct binder_buffer_object, hdr) + +#define to_binder_fd_array_object(hdr) \ + container_of(hdr, struct binder_fd_array_object, hdr) + enum binder_stat_types { BINDER_STAT_PROC, BINDER_STAT_THREAD, @@ -157,26 +200,27 @@ enum binder_stat_types { }; struct binder_stats { - int br[_IOC_NR(BR_FAILED_REPLY) + 1]; - int bc[_IOC_NR(BC_DEAD_BINDER_DONE) + 1]; - int obj_created[BINDER_STAT_COUNT]; - int obj_deleted[BINDER_STAT_COUNT]; + atomic_t br[_IOC_NR(BR_FAILED_REPLY) + 1]; + atomic_t bc[_IOC_NR(BC_REPLY_SG) + 1]; + atomic_t obj_created[BINDER_STAT_COUNT]; + atomic_t obj_deleted[BINDER_STAT_COUNT]; }; static struct binder_stats binder_stats; static inline void binder_stats_deleted(enum binder_stat_types type) { - binder_stats.obj_deleted[type]++; + atomic_inc(&binder_stats.obj_deleted[type]); } static inline void binder_stats_created(enum binder_stat_types type) { - binder_stats.obj_created[type]++; + atomic_inc(&binder_stats.obj_created[type]); } struct binder_transaction_log_entry { int debug_id; + int debug_id_done; int call_type; int from_proc; int from_thread; @@ -186,10 +230,14 @@ struct binder_transaction_log_entry { int to_node; int data_size; int offsets_size; + int return_error_line; + uint32_t return_error; + uint32_t return_error_param; + const char *context_name; }; struct binder_transaction_log { - int next; - int full; + atomic_t cur; + bool full; struct binder_transaction_log_entry entry[32]; }; static struct binder_transaction_log binder_transaction_log; @@ -199,22 +247,50 @@ static struct binder_transaction_log_ent struct binder_transaction_log *log) { struct binder_transaction_log_entry *e; + unsigned int cur = atomic_inc_return(&log->cur); - e = &log->entry[log->next]; - memset(e, 0, sizeof(*e)); - log->next++; - if (log->next == ARRAY_SIZE(log->entry)) { - log->next = 0; + if (cur >= ARRAY_SIZE(log->entry)) log->full = 1; - } + e = &log->entry[cur % ARRAY_SIZE(log->entry)]; + WRITE_ONCE(e->debug_id_done, 0); + /* + * write-barrier to synchronize access to e->debug_id_done. + * We make sure the initialized 0 value is seen before + * memset() other fields are zeroed by memset. + */ + smp_wmb(); + memset(e, 0, sizeof(*e)); return e; } +struct binder_context { + struct binder_node *binder_context_mgr_node; + struct mutex context_mgr_node_lock; + + kuid_t binder_context_mgr_uid; + const char *name; +}; + +struct binder_device { + struct hlist_node hlist; + struct miscdevice miscdev; + struct binder_context context; +}; + +/** + * struct binder_work - work enqueued on a worklist + * @entry: node enqueued on list + * @type: type of work to be performed + * + * There are separate work lists for proc, thread, and node (async). + */ struct binder_work { struct list_head entry; + enum { BINDER_WORK_TRANSACTION = 1, BINDER_WORK_TRANSACTION_COMPLETE, + BINDER_WORK_RETURN_ERROR, BINDER_WORK_NODE, BINDER_WORK_DEAD_BINDER, BINDER_WORK_DEAD_BINDER_AND_CLEAR, @@ -222,8 +298,76 @@ struct binder_work { } type; }; +struct binder_error { + struct binder_work work; + uint32_t cmd; +}; + +/** + * struct binder_node - binder node bookkeeping + * @debug_id: unique ID for debugging + * (invariant after initialized) + * @lock: lock for node fields + * @work: worklist element for node work + * (protected by @proc->inner_lock) + * @rb_node: element for proc->nodes tree + * (protected by @proc->inner_lock) + * @dead_node: element for binder_dead_nodes list + * (protected by binder_dead_nodes_lock) + * @proc: binder_proc that owns this node + * (invariant after initialized) + * @refs: list of references on this node + * (protected by @lock) + * @internal_strong_refs: used to take strong references when + * initiating a transaction + * (protected by @proc->inner_lock if @proc + * and by @lock) + * @local_weak_refs: weak user refs from local process + * (protected by @proc->inner_lock if @proc + * and by @lock) + * @local_strong_refs: strong user refs from local process + * (protected by @proc->inner_lock if @proc + * and by @lock) + * @tmp_refs: temporary kernel refs + * (protected by @proc->inner_lock while @proc + * is valid, and by binder_dead_nodes_lock + * if @proc is NULL. During inc/dec and node release + * it is also protected by @lock to provide safety + * as the node dies and @proc becomes NULL) + * @ptr: userspace pointer for node + * (invariant, no lock needed) + * @cookie: userspace cookie for node + * (invariant, no lock needed) + * @has_strong_ref: userspace notified of strong ref + * (protected by @proc->inner_lock if @proc + * and by @lock) + * @pending_strong_ref: userspace has acked notification of strong ref + * (protected by @proc->inner_lock if @proc + * and by @lock) + * @has_weak_ref: userspace notified of weak ref + * (protected by @proc->inner_lock if @proc + * and by @lock) + * @pending_weak_ref: userspace has acked notification of weak ref + * (protected by @proc->inner_lock if @proc + * and by @lock) + * @has_async_transaction: async transaction to node in progress + * (protected by @lock) + * @sched_policy: minimum scheduling policy for node + * (invariant after initialized) + * @accept_fds: file descriptor operations supported for node + * (invariant after initialized) + * @min_priority: minimum scheduling priority + * (invariant after initialized) + * @inherit_rt: inherit RT scheduling policy from caller + * (invariant after initialized) + * @async_todo: list of async work items + * (protected by @proc->inner_lock) + * + * Bookkeeping structure for binder nodes. + */ struct binder_node { int debug_id; + spinlock_t lock; struct binder_work work; union { struct rb_node rb_node; @@ -234,87 +378,186 @@ struct binder_node { int internal_strong_refs; int local_weak_refs; int local_strong_refs; + int tmp_refs; binder_uintptr_t ptr; binder_uintptr_t cookie; - unsigned has_strong_ref:1; - unsigned pending_strong_ref:1; - unsigned has_weak_ref:1; - unsigned pending_weak_ref:1; - unsigned has_async_transaction:1; - unsigned accept_fds:1; - unsigned min_priority:8; + struct { + /* + * bitfield elements protected by + * proc inner_lock + */ + u8 has_strong_ref:1; + u8 pending_strong_ref:1; + u8 has_weak_ref:1; + u8 pending_weak_ref:1; + }; + struct { + /* + * invariant after initialization + */ + u8 sched_policy:2; + u8 inherit_rt:1; + u8 accept_fds:1; + u8 min_priority; + }; + bool has_async_transaction; struct list_head async_todo; }; struct binder_ref_death { + /** + * @work: worklist element for death notifications + * (protected by inner_lock of the proc that + * this ref belongs to) + */ struct binder_work work; binder_uintptr_t cookie; }; +/** + * struct binder_ref_data - binder_ref counts and id + * @debug_id: unique ID for the ref + * @desc: unique userspace handle for ref + * @strong: strong ref count (debugging only if not locked) + * @weak: weak ref count (debugging only if not locked) + * + * Structure to hold ref count and ref id information. Since + * the actual ref can only be accessed with a lock, this structure + * is used to return information about the ref to callers of + * ref inc/dec functions. + */ +struct binder_ref_data { + int debug_id; + uint32_t desc; + int strong; + int weak; +}; + +/** + * struct binder_ref - struct to track references on nodes + * @data: binder_ref_data containing id, handle, and current refcounts + * @rb_node_desc: node for lookup by @data.desc in proc's rb_tree + * @rb_node_node: node for lookup by @node in proc's rb_tree + * @node_entry: list entry for node->refs list in target node + * (protected by @node->lock) + * @proc: binder_proc containing ref + * @node: binder_node of target node. When cleaning up a + * ref for deletion in binder_cleanup_ref, a non-NULL + * @node indicates the node must be freed + * @death: pointer to death notification (ref_death) if requested + * (protected by @node->lock) + * + * Structure to track references from procA to target node (on procB). This + * structure is unsafe to access without holding @proc->outer_lock. + */ struct binder_ref { /* Lookups needed: */ /* node + proc => ref (transaction) */ /* desc + proc => ref (transaction, inc/dec ref) */ /* node => refs + procs (proc exit) */ - int debug_id; + struct binder_ref_data data; struct rb_node rb_node_desc; struct rb_node rb_node_node; struct hlist_node node_entry; struct binder_proc *proc; struct binder_node *node; - uint32_t desc; - int strong; - int weak; struct binder_ref_death *death; }; -struct binder_buffer { - struct list_head entry; /* free and allocated entries by address */ - struct rb_node rb_node; /* free entry by size or allocated entry */ - /* by address */ - unsigned free:1; - unsigned allow_user_free:1; - unsigned async_transaction:1; - unsigned debug_id:29; - - struct binder_transaction *transaction; - - struct binder_node *target_node; - size_t data_size; - size_t offsets_size; - uint8_t data[0]; -}; - enum binder_deferred_state { BINDER_DEFERRED_PUT_FILES = 0x01, BINDER_DEFERRED_FLUSH = 0x02, BINDER_DEFERRED_RELEASE = 0x04, }; +/** + * struct binder_priority - scheduler policy and priority + * @sched_policy scheduler policy + * @prio [100..139] for SCHED_NORMAL, [0..99] for FIFO/RT + * + * The binder driver supports inheriting the following scheduler policies: + * SCHED_NORMAL + * SCHED_BATCH + * SCHED_FIFO + * SCHED_RR + */ +struct binder_priority { + unsigned int sched_policy; + int prio; +}; + +/** + * struct binder_proc - binder process bookkeeping + * @proc_node: element for binder_procs list + * @threads: rbtree of binder_threads in this proc + * (protected by @inner_lock) + * @nodes: rbtree of binder nodes associated with + * this proc ordered by node->ptr + * (protected by @inner_lock) + * @refs_by_desc: rbtree of refs ordered by ref->desc + * (protected by @outer_lock) + * @refs_by_node: rbtree of refs ordered by ref->node + * (protected by @outer_lock) + * @waiting_threads: threads currently waiting for proc work + * (protected by @inner_lock) + * @pid PID of group_leader of process + * (invariant after initialized) + * @tsk task_struct for group_leader of process + * (invariant after initialized) + * @files files_struct for process + * (invariant after initialized) + * @deferred_work_node: element for binder_deferred_list + * (protected by binder_deferred_lock) + * @deferred_work: bitmap of deferred work to perform + * (protected by binder_deferred_lock) + * @is_dead: process is dead and awaiting free + * when outstanding transactions are cleaned up + * (protected by @inner_lock) + * @todo: list of work for this process + * (protected by @inner_lock) + * @wait: wait queue head to wait for proc work + * (invariant after initialized) + * @stats: per-process binder statistics + * (atomics, no lock needed) + * @delivered_death: list of delivered death notification + * (protected by @inner_lock) + * @max_threads: cap on number of binder threads + * (protected by @inner_lock) + * @requested_threads: number of binder threads requested but not + * yet started. In current implementation, can + * only be 0 or 1. + * (protected by @inner_lock) + * @requested_threads_started: number binder threads started + * (protected by @inner_lock) + * @tmp_ref: temporary reference to indicate proc is in use + * (protected by @inner_lock) + * @default_priority: default scheduler priority + * (invariant after initialized) + * @debugfs_entry: debugfs node + * @alloc: binder allocator bookkeeping + * @context: binder_context for this proc + * (invariant after initialized) + * @inner_lock: can nest under outer_lock and/or node lock + * @outer_lock: no nesting under innor or node lock + * Lock order: 1) outer, 2) node, 3) inner + * + * Bookkeeping structure for binder processes + */ struct binder_proc { struct hlist_node proc_node; struct rb_root threads; struct rb_root nodes; struct rb_root refs_by_desc; struct rb_root refs_by_node; + struct list_head waiting_threads; int pid; - struct vm_area_struct *vma; - struct mm_struct *vma_vm_mm; struct task_struct *tsk; struct files_struct *files; + struct mutex files_lock; struct hlist_node deferred_work_node; int deferred_work; - void *buffer; - ptrdiff_t user_buffer_offset; - - struct list_head buffers; - struct rb_root free_buffers; - struct rb_root allocated_buffers; - size_t free_async_space; + bool is_dead; - struct page **pages; - size_t buffer_size; - uint32_t buffer_free; struct list_head todo; wait_queue_head_t wait; struct binder_stats stats; @@ -322,9 +565,13 @@ struct binder_proc { int max_threads; int requested_threads; int requested_threads_started; - int ready_threads; - long default_priority; + int tmp_ref; + struct binder_priority default_priority; struct dentry *debugfs_entry; + struct binder_alloc alloc; + struct binder_context *context; + spinlock_t inner_lock; + spinlock_t outer_lock; }; enum { @@ -333,22 +580,60 @@ enum { BINDER_LOOPER_STATE_EXITED = 0x04, BINDER_LOOPER_STATE_INVALID = 0x08, BINDER_LOOPER_STATE_WAITING = 0x10, - BINDER_LOOPER_STATE_NEED_RETURN = 0x20 + BINDER_LOOPER_STATE_POLL = 0x20, }; +/** + * struct binder_thread - binder thread bookkeeping + * @proc: binder process for this thread + * (invariant after initialization) + * @rb_node: element for proc->threads rbtree + * (protected by @proc->inner_lock) + * @waiting_thread_node: element for @proc->waiting_threads list + * (protected by @proc->inner_lock) + * @pid: PID for this thread + * (invariant after initialization) + * @looper: bitmap of looping state + * (only accessed by this thread) + * @looper_needs_return: looping thread needs to exit driver + * (no lock needed) + * @transaction_stack: stack of in-progress transactions for this thread + * (protected by @proc->inner_lock) + * @todo: list of work to do for this thread + * (protected by @proc->inner_lock) + * @return_error: transaction errors reported by this thread + * (only accessed by this thread) + * @reply_error: transaction errors reported by target thread + * (protected by @proc->inner_lock) + * @wait: wait queue for thread work + * @stats: per-thread statistics + * (atomics, no lock needed) + * @tmp_ref: temporary reference to indicate thread is in use + * (atomic since @proc->inner_lock cannot + * always be acquired) + * @is_dead: thread is dead and awaiting free + * when outstanding transactions are cleaned up + * (protected by @proc->inner_lock) + * @task: struct task_struct for this thread + * + * Bookkeeping structure for binder threads. + */ struct binder_thread { struct binder_proc *proc; struct rb_node rb_node; + struct list_head waiting_thread_node; int pid; - int looper; + int looper; /* only modified by this thread */ + bool looper_need_return; /* can be written by other thread */ struct binder_transaction *transaction_stack; struct list_head todo; - uint32_t return_error; /* Write failed, return error code in read buf */ - uint32_t return_error2; /* Write failed, return error code in read */ - /* buffer. Used when sending a reply to a dead process that */ - /* we are also waiting on */ + struct binder_error return_error; + struct binder_error reply_error; wait_queue_head_t wait; struct binder_stats stats; + atomic_t tmp_ref; + bool is_dead; + struct task_struct *task; }; struct binder_transaction { @@ -365,30 +650,280 @@ struct binder_transaction { struct binder_buffer *buffer; unsigned int code; unsigned int flags; - long priority; - long saved_priority; + struct binder_priority priority; + struct binder_priority saved_priority; + bool set_priority_called; kuid_t sender_euid; + /** + * @lock: protects @from, @to_proc, and @to_thread + * + * @from, @to_proc, and @to_thread can be set to NULL + * during thread teardown + */ + spinlock_t lock; }; +/** + * binder_proc_lock() - Acquire outer lock for given binder_proc + * @proc: struct binder_proc to acquire + * + * Acquires proc->outer_lock. Used to protect binder_ref + * structures associated with the given proc. + */ +#define binder_proc_lock(proc) _binder_proc_lock(proc, __LINE__) +static void +_binder_proc_lock(struct binder_proc *proc, int line) +{ + binder_debug(BINDER_DEBUG_SPINLOCKS, + "%s: line=%d\n", __func__, line); + spin_lock(&proc->outer_lock); +} + +/** + * binder_proc_unlock() - Release spinlock for given binder_proc + * @proc: struct binder_proc to acquire + * + * Release lock acquired via binder_proc_lock() + */ +#define binder_proc_unlock(_proc) _binder_proc_unlock(_proc, __LINE__) +static void +_binder_proc_unlock(struct binder_proc *proc, int line) +{ + binder_debug(BINDER_DEBUG_SPINLOCKS, + "%s: line=%d\n", __func__, line); + spin_unlock(&proc->outer_lock); +} + +/** + * binder_inner_proc_lock() - Acquire inner lock for given binder_proc + * @proc: struct binder_proc to acquire + * + * Acquires proc->inner_lock. Used to protect todo lists + */ +#define binder_inner_proc_lock(proc) _binder_inner_proc_lock(proc, __LINE__) +static void +_binder_inner_proc_lock(struct binder_proc *proc, int line) +{ + binder_debug(BINDER_DEBUG_SPINLOCKS, + "%s: line=%d\n", __func__, line); + spin_lock(&proc->inner_lock); +} + +/** + * binder_inner_proc_unlock() - Release inner lock for given binder_proc + * @proc: struct binder_proc to acquire + * + * Release lock acquired via binder_inner_proc_lock() + */ +#define binder_inner_proc_unlock(proc) _binder_inner_proc_unlock(proc, __LINE__) +static void +_binder_inner_proc_unlock(struct binder_proc *proc, int line) +{ + binder_debug(BINDER_DEBUG_SPINLOCKS, + "%s: line=%d\n", __func__, line); + spin_unlock(&proc->inner_lock); +} + +/** + * binder_node_lock() - Acquire spinlock for given binder_node + * @node: struct binder_node to acquire + * + * Acquires node->lock. Used to protect binder_node fields + */ +#define binder_node_lock(node) _binder_node_lock(node, __LINE__) +static void +_binder_node_lock(struct binder_node *node, int line) +{ + binder_debug(BINDER_DEBUG_SPINLOCKS, + "%s: line=%d\n", __func__, line); + spin_lock(&node->lock); +} + +/** + * binder_node_unlock() - Release spinlock for given binder_proc + * @node: struct binder_node to acquire + * + * Release lock acquired via binder_node_lock() + */ +#define binder_node_unlock(node) _binder_node_unlock(node, __LINE__) +static void +_binder_node_unlock(struct binder_node *node, int line) +{ + binder_debug(BINDER_DEBUG_SPINLOCKS, + "%s: line=%d\n", __func__, line); + spin_unlock(&node->lock); +} + +/** + * binder_node_inner_lock() - Acquire node and inner locks + * @node: struct binder_node to acquire + * + * Acquires node->lock. If node->proc also acquires + * proc->inner_lock. Used to protect binder_node fields + */ +#define binder_node_inner_lock(node) _binder_node_inner_lock(node, __LINE__) +static void +_binder_node_inner_lock(struct binder_node *node, int line) +{ + binder_debug(BINDER_DEBUG_SPINLOCKS, + "%s: line=%d\n", __func__, line); + spin_lock(&node->lock); + if (node->proc) + binder_inner_proc_lock(node->proc); +} + +/** + * binder_node_unlock() - Release node and inner locks + * @node: struct binder_node to acquire + * + * Release lock acquired via binder_node_lock() + */ +#define binder_node_inner_unlock(node) _binder_node_inner_unlock(node, __LINE__) +static void +_binder_node_inner_unlock(struct binder_node *node, int line) +{ + struct binder_proc *proc = node->proc; + + binder_debug(BINDER_DEBUG_SPINLOCKS, + "%s: line=%d\n", __func__, line); + if (proc) + binder_inner_proc_unlock(proc); + spin_unlock(&node->lock); +} + +static bool binder_worklist_empty_ilocked(struct list_head *list) +{ + return list_empty(list); +} + +/** + * binder_worklist_empty() - Check if no items on the work list + * @proc: binder_proc associated with list + * @list: list to check + * + * Return: true if there are no items on list, else false + */ +static bool binder_worklist_empty(struct binder_proc *proc, + struct list_head *list) +{ + bool ret; + + binder_inner_proc_lock(proc); + ret = binder_worklist_empty_ilocked(list); + binder_inner_proc_unlock(proc); + return ret; +} + +static void +binder_enqueue_work_ilocked(struct binder_work *work, + struct list_head *target_list) +{ + BUG_ON(target_list == NULL); + BUG_ON(work->entry.next && !list_empty(&work->entry)); + list_add_tail(&work->entry, target_list); +} + +/** + * binder_enqueue_work() - Add an item to the work list + * @proc: binder_proc associated with list + * @work: struct binder_work to add to list + * @target_list: list to add work to + * + * Adds the work to the specified list. Asserts that work + * is not already on a list. + */ +static void +binder_enqueue_work(struct binder_proc *proc, + struct binder_work *work, + struct list_head *target_list) +{ + binder_inner_proc_lock(proc); + binder_enqueue_work_ilocked(work, target_list); + binder_inner_proc_unlock(proc); +} + +static void +binder_dequeue_work_ilocked(struct binder_work *work) +{ + list_del_init(&work->entry); +} + +/** + * binder_dequeue_work() - Removes an item from the work list + * @proc: binder_proc associated with list + * @work: struct binder_work to remove from list + * + * Removes the specified work item from whatever list it is on. + * Can safely be called if work is not on any list. + */ +static void +binder_dequeue_work(struct binder_proc *proc, struct binder_work *work) +{ + binder_inner_proc_lock(proc); + binder_dequeue_work_ilocked(work); + binder_inner_proc_unlock(proc); +} + +static struct binder_work *binder_dequeue_work_head_ilocked( + struct list_head *list) +{ + struct binder_work *w; + + w = list_first_entry_or_null(list, struct binder_work, entry); + if (w) + list_del_init(&w->entry); + return w; +} + +/** + * binder_dequeue_work_head() - Dequeues the item at head of list + * @proc: binder_proc associated with list + * @list: list to dequeue head + * + * Removes the head of the list if there are items on the list + * + * Return: pointer dequeued binder_work, NULL if list was empty + */ +static struct binder_work *binder_dequeue_work_head( + struct binder_proc *proc, + struct list_head *list) +{ + struct binder_work *w; + + binder_inner_proc_lock(proc); + w = binder_dequeue_work_head_ilocked(list); + binder_inner_proc_unlock(proc); + return w; +} + static void binder_defer_work(struct binder_proc *proc, enum binder_deferred_state defer); +static void binder_free_thread(struct binder_thread *thread); +static void binder_free_proc(struct binder_proc *proc); +static void binder_inc_node_tmpref_ilocked(struct binder_node *node); static int task_get_unused_fd_flags(struct binder_proc *proc, int flags) { - struct files_struct *files = proc->files; unsigned long rlim_cur; unsigned long irqs; + int ret; - if (files == NULL) - return -ESRCH; - - if (!lock_task_sighand(proc->tsk, &irqs)) - return -EMFILE; - + mutex_lock(&proc->files_lock); + if (proc->files == NULL) { + ret = -ESRCH; + goto err; + } + if (!lock_task_sighand(proc->tsk, &irqs)) { + ret = -EMFILE; + goto err; + } rlim_cur = task_rlimit(proc->tsk, RLIMIT_NOFILE); unlock_task_sighand(proc->tsk, &irqs); - return __alloc_fd(files, 0, rlim_cur, flags); + ret = __alloc_fd(proc->files, 0, rlim_cur, flags); +err: + mutex_unlock(&proc->files_lock); + return ret; } /* @@ -397,8 +932,10 @@ static int task_get_unused_fd_flags(stru static void task_fd_install( struct binder_proc *proc, unsigned int fd, struct file *file) { + mutex_lock(&proc->files_lock); if (proc->files) __fd_install(proc->files, fd, file); + mutex_unlock(&proc->files_lock); } /* @@ -408,9 +945,11 @@ static long task_close_fd(struct binder_ { int retval; - if (proc->files == NULL) - return -ESRCH; - + mutex_lock(&proc->files_lock); + if (proc->files == NULL) { + retval = -ESRCH; + goto err; + } retval = __close_fd(proc->files, fd); /* can't restart close syscall because file table entry was cleared */ if (unlikely(retval == -ERESTARTSYS || @@ -418,457 +957,286 @@ static long task_close_fd(struct binder_ retval == -ERESTARTNOHAND || retval == -ERESTART_RESTARTBLOCK)) retval = -EINTR; - +err: + mutex_unlock(&proc->files_lock); return retval; } -static inline void binder_lock(const char *tag) +static bool binder_has_work_ilocked(struct binder_thread *thread, + bool do_proc_work) { - trace_binder_lock(tag); - mutex_lock(&binder_main_lock); - trace_binder_locked(tag); + return !binder_worklist_empty_ilocked(&thread->todo) || + thread->looper_need_return || + (do_proc_work && + !binder_worklist_empty_ilocked(&thread->proc->todo)); } -static inline void binder_unlock(const char *tag) +static bool binder_has_work(struct binder_thread *thread, bool do_proc_work) { - trace_binder_unlock(tag); - mutex_unlock(&binder_main_lock); -} + bool has_work; -static void binder_set_nice(long nice) -{ - long min_nice; + binder_inner_proc_lock(thread->proc); + has_work = binder_has_work_ilocked(thread, do_proc_work); + binder_inner_proc_unlock(thread->proc); - if (can_nice(current, nice)) { - set_user_nice(current, nice); - return; - } - min_nice = rlimit_to_nice(current->signal->rlim[RLIMIT_NICE].rlim_cur); - binder_debug(BINDER_DEBUG_PRIORITY_CAP, - "%d: nice value %ld not allowed use %ld instead\n", - current->pid, nice, min_nice); - set_user_nice(current, min_nice); - if (min_nice <= MAX_NICE) - return; - binder_user_error("%d RLIMIT_NICE not set\n", current->pid); + return has_work; } -static size_t binder_buffer_size(struct binder_proc *proc, - struct binder_buffer *buffer) +static bool binder_available_for_proc_work_ilocked(struct binder_thread *thread) { - if (list_is_last(&buffer->entry, &proc->buffers)) - return proc->buffer + proc->buffer_size - (void *)buffer->data; - return (size_t)list_entry(buffer->entry.next, - struct binder_buffer, entry) - (size_t)buffer->data; + return !thread->transaction_stack && + binder_worklist_empty_ilocked(&thread->todo) && + (thread->looper & (BINDER_LOOPER_STATE_ENTERED | + BINDER_LOOPER_STATE_REGISTERED)); } -static void binder_insert_free_buffer(struct binder_proc *proc, - struct binder_buffer *new_buffer) +static void binder_wakeup_poll_threads_ilocked(struct binder_proc *proc, + bool sync) { - struct rb_node **p = &proc->free_buffers.rb_node; - struct rb_node *parent = NULL; - struct binder_buffer *buffer; - size_t buffer_size; - size_t new_buffer_size; - - BUG_ON(!new_buffer->free); - - new_buffer_size = binder_buffer_size(proc, new_buffer); - - binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%d: add free buffer, size %zd, at %p\n", - proc->pid, new_buffer_size, new_buffer); - - while (*p) { - parent = *p; - buffer = rb_entry(parent, struct binder_buffer, rb_node); - BUG_ON(!buffer->free); - - buffer_size = binder_buffer_size(proc, buffer); + struct rb_node *n; + struct binder_thread *thread; - if (new_buffer_size < buffer_size) - p = &parent->rb_left; - else - p = &parent->rb_right; + for (n = rb_first(&proc->threads); n != NULL; n = rb_next(n)) { + thread = rb_entry(n, struct binder_thread, rb_node); + if (thread->looper & BINDER_LOOPER_STATE_POLL && + binder_available_for_proc_work_ilocked(thread)) { + if (sync) + wake_up_interruptible_sync(&thread->wait); + else + wake_up_interruptible(&thread->wait); + } } - rb_link_node(&new_buffer->rb_node, parent, p); - rb_insert_color(&new_buffer->rb_node, &proc->free_buffers); } -static void binder_insert_allocated_buffer(struct binder_proc *proc, - struct binder_buffer *new_buffer) +/** + * binder_select_thread_ilocked() - selects a thread for doing proc work. + * @proc: process to select a thread from + * + * Note that calling this function moves the thread off the waiting_threads + * list, so it can only be woken up by the caller of this function, or a + * signal. Therefore, callers *should* always wake up the thread this function + * returns. + * + * Return: If there's a thread currently waiting for process work, + * returns that thread. Otherwise returns NULL. + */ +static struct binder_thread * +binder_select_thread_ilocked(struct binder_proc *proc) { - struct rb_node **p = &proc->allocated_buffers.rb_node; - struct rb_node *parent = NULL; - struct binder_buffer *buffer; + struct binder_thread *thread; - BUG_ON(new_buffer->free); + assert_spin_locked(&proc->inner_lock); + thread = list_first_entry_or_null(&proc->waiting_threads, + struct binder_thread, + waiting_thread_node); - while (*p) { - parent = *p; - buffer = rb_entry(parent, struct binder_buffer, rb_node); - BUG_ON(buffer->free); + if (thread) + list_del_init(&thread->waiting_thread_node); - if (new_buffer < buffer) - p = &parent->rb_left; - else if (new_buffer > buffer) - p = &parent->rb_right; - else - BUG(); - } - rb_link_node(&new_buffer->rb_node, parent, p); - rb_insert_color(&new_buffer->rb_node, &proc->allocated_buffers); + return thread; } -static struct binder_buffer *binder_buffer_lookup(struct binder_proc *proc, - uintptr_t user_ptr) +/** + * binder_wakeup_thread_ilocked() - wakes up a thread for doing proc work. + * @proc: process to wake up a thread in + * @thread: specific thread to wake-up (may be NULL) + * @sync: whether to do a synchronous wake-up + * + * This function wakes up a thread in the @proc process. + * The caller may provide a specific thread to wake-up in + * the @thread parameter. If @thread is NULL, this function + * will wake up threads that have called poll(). + * + * Note that for this function to work as expected, callers + * should first call binder_select_thread() to find a thread + * to handle the work (if they don't have a thread already), + * and pass the result into the @thread parameter. + */ +static void binder_wakeup_thread_ilocked(struct binder_proc *proc, + struct binder_thread *thread, + bool sync) { - struct rb_node *n = proc->allocated_buffers.rb_node; - struct binder_buffer *buffer; - struct binder_buffer *kern_ptr; - - kern_ptr = (struct binder_buffer *)(user_ptr - proc->user_buffer_offset - - offsetof(struct binder_buffer, data)); - - while (n) { - buffer = rb_entry(n, struct binder_buffer, rb_node); - BUG_ON(buffer->free); + assert_spin_locked(&proc->inner_lock); - if (kern_ptr < buffer) - n = n->rb_left; - else if (kern_ptr > buffer) - n = n->rb_right; + if (thread) { + if (sync) + wake_up_interruptible_sync(&thread->wait); else - return buffer; + wake_up_interruptible(&thread->wait); + return; } - return NULL; + + /* Didn't find a thread waiting for proc work; this can happen + * in two scenarios: + * 1. All threads are busy handling transactions + * In that case, one of those threads should call back into + * the kernel driver soon and pick up this work. + * 2. Threads are using the (e)poll interface, in which case + * they may be blocked on the waitqueue without having been + * added to waiting_threads. For this case, we just iterate + * over all threads not handling transaction work, and + * wake them all up. We wake all because we don't know whether + * a thread that called into (e)poll is handling non-binder + * work currently. + */ + binder_wakeup_poll_threads_ilocked(proc, sync); } -static int binder_update_page_range(struct binder_proc *proc, int allocate, - void *start, void *end, - struct vm_area_struct *vma) +static void binder_wakeup_proc_ilocked(struct binder_proc *proc) { - void *page_addr; - unsigned long user_page_addr; - struct page **page; - struct mm_struct *mm; - - binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%d: %s pages %p-%p\n", proc->pid, - allocate ? "allocate" : "free", start, end); - - if (end <= start) - return 0; - - trace_binder_update_page_range(proc, allocate, start, end); - - if (vma) - mm = NULL; - else - mm = get_task_mm(proc->tsk); - - if (mm) { - down_write(&mm->mmap_sem); - vma = proc->vma; - if (vma && mm != proc->vma_vm_mm) { - pr_err("%d: vma mm and task mm mismatch\n", - proc->pid); - vma = NULL; - } - } - - if (allocate == 0) - goto free_range; + struct binder_thread *thread = binder_select_thread_ilocked(proc); - if (vma == NULL) { - pr_err("%d: binder_alloc_buf failed to map pages in userspace, no vma\n", - proc->pid); - goto err_no_vma; - } + binder_wakeup_thread_ilocked(proc, thread, /* sync = */false); +} - for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) { - int ret; +static bool is_rt_policy(int policy) +{ + return policy == SCHED_FIFO || policy == SCHED_RR; +} - page = &proc->pages[(page_addr - proc->buffer) / PAGE_SIZE]; +static bool is_fair_policy(int policy) +{ + return policy == SCHED_NORMAL || policy == SCHED_BATCH; +} - BUG_ON(*page); - *page = alloc_page(GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO); - if (*page == NULL) { - pr_err("%d: binder_alloc_buf failed for page at %p\n", - proc->pid, page_addr); - goto err_alloc_page_failed; - } - ret = map_kernel_range_noflush((unsigned long)page_addr, - PAGE_SIZE, PAGE_KERNEL, page); - flush_cache_vmap((unsigned long)page_addr, - (unsigned long)page_addr + PAGE_SIZE); - if (ret != 1) { - pr_err("%d: binder_alloc_buf failed to map page at %p in kernel\n", - proc->pid, page_addr); - goto err_map_kernel_failed; - } - user_page_addr = - (uintptr_t)page_addr + proc->user_buffer_offset; - ret = vm_insert_page(vma, user_page_addr, page[0]); - if (ret) { - pr_err("%d: binder_alloc_buf failed to map page at %lx in userspace\n", - proc->pid, user_page_addr); - goto err_vm_insert_page_failed; - } - /* vm_insert_page does not seem to increment the refcount */ - } - if (mm) { - up_write(&mm->mmap_sem); - mmput(mm); - } - return 0; +static bool binder_supported_policy(int policy) +{ + return is_fair_policy(policy) || is_rt_policy(policy); +} -free_range: - for (page_addr = end - PAGE_SIZE; page_addr >= start; - page_addr -= PAGE_SIZE) { - page = &proc->pages[(page_addr - proc->buffer) / PAGE_SIZE]; - if (vma) - zap_page_range(vma, (uintptr_t)page_addr + - proc->user_buffer_offset, PAGE_SIZE, NULL); -err_vm_insert_page_failed: - unmap_kernel_range((unsigned long)page_addr, PAGE_SIZE); -err_map_kernel_failed: - __free_page(*page); - *page = NULL; -err_alloc_page_failed: - ; - } -err_no_vma: - if (mm) { - up_write(&mm->mmap_sem); - mmput(mm); - } - return -ENOMEM; +static int to_userspace_prio(int policy, int kernel_priority) +{ + if (is_fair_policy(policy)) + return PRIO_TO_NICE(kernel_priority); + else + return MAX_USER_RT_PRIO - 1 - kernel_priority; } -static struct binder_buffer *binder_alloc_buf(struct binder_proc *proc, - size_t data_size, - size_t offsets_size, int is_async) +static int to_kernel_prio(int policy, int user_priority) { - struct rb_node *n = proc->free_buffers.rb_node; - struct binder_buffer *buffer; - size_t buffer_size; - struct rb_node *best_fit = NULL; - void *has_page_addr; - void *end_page_addr; - size_t size; + if (is_fair_policy(policy)) + return NICE_TO_PRIO(user_priority); + else + return MAX_USER_RT_PRIO - 1 - user_priority; +} - if (proc->vma == NULL) { - pr_err("%d: binder_alloc_buf, no vma\n", - proc->pid); - return NULL; - } +static void binder_do_set_priority(struct task_struct *task, + struct binder_priority desired, + bool verify) +{ + int priority; /* user-space prio value */ + bool has_cap_nice; + unsigned int policy = desired.sched_policy; - size = ALIGN(data_size, sizeof(void *)) + - ALIGN(offsets_size, sizeof(void *)); + if (task->policy == policy && task->normal_prio == desired.prio) + return; - if (size < data_size || size < offsets_size) { - binder_user_error("%d: got transaction with invalid size %zd-%zd\n", - proc->pid, data_size, offsets_size); - return NULL; - } + has_cap_nice = has_capability_noaudit(task, CAP_SYS_NICE); - if (is_async && - proc->free_async_space < size + sizeof(struct binder_buffer)) { - binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%d: binder_alloc_buf size %zd failed, no async space left\n", - proc->pid, size); - return NULL; - } + priority = to_userspace_prio(policy, desired.prio); - while (n) { - buffer = rb_entry(n, struct binder_buffer, rb_node); - BUG_ON(!buffer->free); - buffer_size = binder_buffer_size(proc, buffer); + if (verify && is_rt_policy(policy) && !has_cap_nice) { + long max_rtprio = task_rlimit(task, RLIMIT_RTPRIO); - if (size < buffer_size) { - best_fit = n; - n = n->rb_left; - } else if (size > buffer_size) - n = n->rb_right; - else { - best_fit = n; - break; + if (max_rtprio == 0) { + policy = SCHED_NORMAL; + priority = MIN_NICE; + } else if (priority > max_rtprio) { + priority = max_rtprio; } } - if (best_fit == NULL) { - pr_err("%d: binder_alloc_buf size %zd failed, no address space\n", - proc->pid, size); - return NULL; - } - if (n == NULL) { - buffer = rb_entry(best_fit, struct binder_buffer, rb_node); - buffer_size = binder_buffer_size(proc, buffer); - } - binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%d: binder_alloc_buf size %zd got buffer %p size %zd\n", - proc->pid, size, buffer, buffer_size); + if (verify && is_fair_policy(policy) && !has_cap_nice) { + long min_nice = rlimit_to_nice(task_rlimit(task, RLIMIT_NICE)); - has_page_addr = - (void *)(((uintptr_t)buffer->data + buffer_size) & PAGE_MASK); - if (n == NULL) { - if (size + sizeof(struct binder_buffer) + 4 >= buffer_size) - buffer_size = size; /* no room for other buffers */ - else - buffer_size = size + sizeof(struct binder_buffer); + if (min_nice > MAX_NICE) { + binder_user_error("%d RLIMIT_NICE not set\n", + task->pid); + return; + } else if (priority < min_nice) { + priority = min_nice; + } } - end_page_addr = - (void *)PAGE_ALIGN((uintptr_t)buffer->data + buffer_size); - if (end_page_addr > has_page_addr) - end_page_addr = has_page_addr; - if (binder_update_page_range(proc, 1, - (void *)PAGE_ALIGN((uintptr_t)buffer->data), end_page_addr, NULL)) - return NULL; - rb_erase(best_fit, &proc->free_buffers); - buffer->free = 0; - binder_insert_allocated_buffer(proc, buffer); - if (buffer_size != size) { - struct binder_buffer *new_buffer = (void *)buffer->data + size; + if (policy != desired.sched_policy || + to_kernel_prio(policy, priority) != desired.prio) + binder_debug(BINDER_DEBUG_PRIORITY_CAP, + "%d: priority %d not allowed, using %d instead\n", + task->pid, desired.prio, + to_kernel_prio(policy, priority)); - list_add(&new_buffer->entry, &buffer->entry); - new_buffer->free = 1; - binder_insert_free_buffer(proc, new_buffer); - } - binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%d: binder_alloc_buf size %zd got %p\n", - proc->pid, size, buffer); - buffer->data_size = data_size; - buffer->offsets_size = offsets_size; - buffer->async_transaction = is_async; - if (is_async) { - proc->free_async_space -= size + sizeof(struct binder_buffer); - binder_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC, - "%d: binder_alloc_buf size %zd async free %zd\n", - proc->pid, size, proc->free_async_space); - } + /* Set the actual priority */ + if (task->policy != policy || is_rt_policy(policy)) { + struct sched_param params; - return buffer; -} + params.sched_priority = is_rt_policy(policy) ? priority : 0; -static void *buffer_start_page(struct binder_buffer *buffer) -{ - return (void *)((uintptr_t)buffer & PAGE_MASK); + sched_setscheduler_nocheck(task, + policy | SCHED_RESET_ON_FORK, + ¶ms); + } + if (is_fair_policy(policy)) + set_user_nice(task, priority); } -static void *buffer_end_page(struct binder_buffer *buffer) +static void binder_set_priority(struct task_struct *task, + struct binder_priority desired) { - return (void *)(((uintptr_t)(buffer + 1) - 1) & PAGE_MASK); + binder_do_set_priority(task, desired, /* verify = */ true); } -static void binder_delete_free_buffer(struct binder_proc *proc, - struct binder_buffer *buffer) +static void binder_restore_priority(struct task_struct *task, + struct binder_priority desired) { - struct binder_buffer *prev, *next = NULL; - int free_page_end = 1; - int free_page_start = 1; - - BUG_ON(proc->buffers.next == &buffer->entry); - prev = list_entry(buffer->entry.prev, struct binder_buffer, entry); - BUG_ON(!prev->free); - if (buffer_end_page(prev) == buffer_start_page(buffer)) { - free_page_start = 0; - if (buffer_end_page(prev) == buffer_end_page(buffer)) - free_page_end = 0; - binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%d: merge free, buffer %p share page with %p\n", - proc->pid, buffer, prev); - } - - if (!list_is_last(&buffer->entry, &proc->buffers)) { - next = list_entry(buffer->entry.next, - struct binder_buffer, entry); - if (buffer_start_page(next) == buffer_end_page(buffer)) { - free_page_end = 0; - if (buffer_start_page(next) == - buffer_start_page(buffer)) - free_page_start = 0; - binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%d: merge free, buffer %p share page with %p\n", - proc->pid, buffer, prev); - } - } - list_del(&buffer->entry); - if (free_page_start || free_page_end) { - binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%d: merge free, buffer %p do not share page%s%s with %p or %p\n", - proc->pid, buffer, free_page_start ? "" : " end", - free_page_end ? "" : " start", prev, next); - binder_update_page_range(proc, 0, free_page_start ? - buffer_start_page(buffer) : buffer_end_page(buffer), - (free_page_end ? buffer_end_page(buffer) : - buffer_start_page(buffer)) + PAGE_SIZE, NULL); - } + binder_do_set_priority(task, desired, /* verify = */ false); } -static void binder_free_buf(struct binder_proc *proc, - struct binder_buffer *buffer) +static void binder_transaction_priority(struct task_struct *task, + struct binder_transaction *t, + struct binder_priority node_prio, + bool inherit_rt) { - size_t size, buffer_size; - - buffer_size = binder_buffer_size(proc, buffer); - - size = ALIGN(buffer->data_size, sizeof(void *)) + - ALIGN(buffer->offsets_size, sizeof(void *)); - - binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%d: binder_free_buf %p size %zd buffer_size %zd\n", - proc->pid, buffer, size, buffer_size); + struct binder_priority desired_prio; - BUG_ON(buffer->free); - BUG_ON(size > buffer_size); - BUG_ON(buffer->transaction != NULL); - BUG_ON((void *)buffer < proc->buffer); - BUG_ON((void *)buffer > proc->buffer + proc->buffer_size); + if (t->set_priority_called) + return; - if (buffer->async_transaction) { - proc->free_async_space += size + sizeof(struct binder_buffer); + t->set_priority_called = true; + t->saved_priority.sched_policy = task->policy; + t->saved_priority.prio = task->normal_prio; - binder_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC, - "%d: binder_free_buf size %zd async free %zd\n", - proc->pid, size, proc->free_async_space); + if (!inherit_rt && is_rt_policy(desired_prio.sched_policy)) { + desired_prio.prio = NICE_TO_PRIO(0); + desired_prio.sched_policy = SCHED_NORMAL; + } else { + desired_prio.prio = t->priority.prio; + desired_prio.sched_policy = t->priority.sched_policy; } - binder_update_page_range(proc, 0, - (void *)PAGE_ALIGN((uintptr_t)buffer->data), - (void *)(((uintptr_t)buffer->data + buffer_size) & PAGE_MASK), - NULL); - rb_erase(&buffer->rb_node, &proc->allocated_buffers); - buffer->free = 1; - if (!list_is_last(&buffer->entry, &proc->buffers)) { - struct binder_buffer *next = list_entry(buffer->entry.next, - struct binder_buffer, entry); - - if (next->free) { - rb_erase(&next->rb_node, &proc->free_buffers); - binder_delete_free_buffer(proc, next); - } + if (node_prio.prio < t->priority.prio || + (node_prio.prio == t->priority.prio && + node_prio.sched_policy == SCHED_FIFO)) { + /* + * In case the minimum priority on the node is + * higher (lower value), use that priority. If + * the priority is the same, but the node uses + * SCHED_FIFO, prefer SCHED_FIFO, since it can + * run unbounded, unlike SCHED_RR. + */ + desired_prio = node_prio; } - if (proc->buffers.next != &buffer->entry) { - struct binder_buffer *prev = list_entry(buffer->entry.prev, - struct binder_buffer, entry); - if (prev->free) { - binder_delete_free_buffer(proc, buffer); - rb_erase(&prev->rb_node, &proc->free_buffers); - buffer = prev; - } - } - binder_insert_free_buffer(proc, buffer); + binder_set_priority(task, desired_prio); } -static struct binder_node *binder_get_node(struct binder_proc *proc, - binder_uintptr_t ptr) +static struct binder_node *binder_get_node_ilocked(struct binder_proc *proc, + binder_uintptr_t ptr) { struct rb_node *n = proc->nodes.rb_node; struct binder_node *node; + assert_spin_locked(&proc->inner_lock); + while (n) { node = rb_entry(n, struct binder_node, rb_node); @@ -876,21 +1244,47 @@ static struct binder_node *binder_get_no n = n->rb_left; else if (ptr > node->ptr) n = n->rb_right; - else + else { + /* + * take an implicit weak reference + * to ensure node stays alive until + * call to binder_put_node() + */ + binder_inc_node_tmpref_ilocked(node); return node; + } } return NULL; } -static struct binder_node *binder_new_node(struct binder_proc *proc, - binder_uintptr_t ptr, - binder_uintptr_t cookie) +static struct binder_node *binder_get_node(struct binder_proc *proc, + binder_uintptr_t ptr) +{ + struct binder_node *node; + + binder_inner_proc_lock(proc); + node = binder_get_node_ilocked(proc, ptr); + binder_inner_proc_unlock(proc); + return node; +} + +static struct binder_node *binder_init_node_ilocked( + struct binder_proc *proc, + struct binder_node *new_node, + struct flat_binder_object *fp) { struct rb_node **p = &proc->nodes.rb_node; struct rb_node *parent = NULL; struct binder_node *node; + binder_uintptr_t ptr = fp ? fp->binder : 0; + binder_uintptr_t cookie = fp ? fp->cookie : 0; + __u32 flags = fp ? fp->flags : 0; + s8 priority; + + assert_spin_locked(&proc->inner_lock); while (*p) { + parent = *p; node = rb_entry(parent, struct binder_node, rb_node); @@ -898,39 +1292,86 @@ static struct binder_node *binder_new_no p = &(*p)->rb_left; else if (ptr > node->ptr) p = &(*p)->rb_right; - else - return NULL; + else { + /* + * A matching node is already in + * the rb tree. Abandon the init + * and return it. + */ + binder_inc_node_tmpref_ilocked(node); + return node; + } } - - node = kzalloc(sizeof(*node), GFP_KERNEL); - if (node == NULL) - return NULL; + node = new_node; binder_stats_created(BINDER_STAT_NODE); + node->tmp_refs++; rb_link_node(&node->rb_node, parent, p); rb_insert_color(&node->rb_node, &proc->nodes); - node->debug_id = ++binder_last_id; + node->debug_id = atomic_inc_return(&binder_last_id); node->proc = proc; node->ptr = ptr; node->cookie = cookie; node->work.type = BINDER_WORK_NODE; + priority = flags & FLAT_BINDER_FLAG_PRIORITY_MASK; + node->sched_policy = (flags & FLAT_BINDER_FLAG_PRIORITY_MASK) >> + FLAT_BINDER_FLAG_SCHED_POLICY_SHIFT; + node->min_priority = to_kernel_prio(node->sched_policy, priority); + node->accept_fds = !!(flags & FLAT_BINDER_FLAG_ACCEPTS_FDS); + node->inherit_rt = !!(flags & FLAT_BINDER_FLAG_INHERIT_RT); + spin_lock_init(&node->lock); INIT_LIST_HEAD(&node->work.entry); INIT_LIST_HEAD(&node->async_todo); binder_debug(BINDER_DEBUG_INTERNAL_REFS, "%d:%d node %d u%016llx c%016llx created\n", proc->pid, current->pid, node->debug_id, (u64)node->ptr, (u64)node->cookie); + return node; } -static int binder_inc_node(struct binder_node *node, int strong, int internal, - struct list_head *target_list) +static struct binder_node *binder_new_node(struct binder_proc *proc, + struct flat_binder_object *fp) { + struct binder_node *node; + struct binder_node *new_node = kzalloc(sizeof(*node), GFP_KERNEL); + + if (!new_node) + return NULL; + binder_inner_proc_lock(proc); + node = binder_init_node_ilocked(proc, new_node, fp); + binder_inner_proc_unlock(proc); + if (node != new_node) + /* + * The node was already added by another thread + */ + kfree(new_node); + + return node; +} + +static void binder_free_node(struct binder_node *node) +{ + kfree(node); + binder_stats_deleted(BINDER_STAT_NODE); +} + +static int binder_inc_node_nilocked(struct binder_node *node, int strong, + int internal, + struct list_head *target_list) +{ + struct binder_proc *proc = node->proc; + + assert_spin_locked(&node->lock); + if (proc) + assert_spin_locked(&proc->inner_lock); if (strong) { if (internal) { if (target_list == NULL && node->internal_strong_refs == 0 && - !(node == binder_context_mgr_node && - node->has_strong_ref)) { + !(node->proc && + node == node->proc->context-> + binder_context_mgr_node && + node->has_strong_ref)) { pr_err("invalid inc strong node for %d\n", node->debug_id); return -EINVAL; @@ -939,8 +1380,8 @@ static int binder_inc_node(struct binder } else node->local_strong_refs++; if (!node->has_strong_ref && target_list) { - list_del_init(&node->work.entry); - list_add_tail(&node->work.entry, target_list); + binder_dequeue_work_ilocked(&node->work); + binder_enqueue_work_ilocked(&node->work, target_list); } } else { if (!internal) @@ -951,58 +1392,169 @@ static int binder_inc_node(struct binder node->debug_id); return -EINVAL; } - list_add_tail(&node->work.entry, target_list); + binder_enqueue_work_ilocked(&node->work, target_list); } } return 0; } -static int binder_dec_node(struct binder_node *node, int strong, int internal) +static int binder_inc_node(struct binder_node *node, int strong, int internal, + struct list_head *target_list) +{ + int ret; + + binder_node_inner_lock(node); + ret = binder_inc_node_nilocked(node, strong, internal, target_list); + binder_node_inner_unlock(node); + + return ret; +} + +static bool binder_dec_node_nilocked(struct binder_node *node, + int strong, int internal) { + struct binder_proc *proc = node->proc; + + assert_spin_locked(&node->lock); + if (proc) + assert_spin_locked(&proc->inner_lock); if (strong) { if (internal) node->internal_strong_refs--; else node->local_strong_refs--; if (node->local_strong_refs || node->internal_strong_refs) - return 0; + return false; } else { if (!internal) node->local_weak_refs--; - if (node->local_weak_refs || !hlist_empty(&node->refs)) - return 0; + if (node->local_weak_refs || node->tmp_refs || + !hlist_empty(&node->refs)) + return false; } - if (node->proc && (node->has_strong_ref || node->has_weak_ref)) { + + if (proc && (node->has_strong_ref || node->has_weak_ref)) { if (list_empty(&node->work.entry)) { - list_add_tail(&node->work.entry, &node->proc->todo); - wake_up_interruptible(&node->proc->wait); + binder_enqueue_work_ilocked(&node->work, &proc->todo); + binder_wakeup_proc_ilocked(proc); } } else { if (hlist_empty(&node->refs) && !node->local_strong_refs && - !node->local_weak_refs) { - list_del_init(&node->work.entry); - if (node->proc) { - rb_erase(&node->rb_node, &node->proc->nodes); + !node->local_weak_refs && !node->tmp_refs) { + if (proc) { + binder_dequeue_work_ilocked(&node->work); + rb_erase(&node->rb_node, &proc->nodes); binder_debug(BINDER_DEBUG_INTERNAL_REFS, "refless node %d deleted\n", node->debug_id); } else { + BUG_ON(!list_empty(&node->work.entry)); + spin_lock(&binder_dead_nodes_lock); + /* + * tmp_refs could have changed so + * check it again + */ + if (node->tmp_refs) { + spin_unlock(&binder_dead_nodes_lock); + return false; + } hlist_del(&node->dead_node); + spin_unlock(&binder_dead_nodes_lock); binder_debug(BINDER_DEBUG_INTERNAL_REFS, "dead node %d deleted\n", node->debug_id); } - kfree(node); - binder_stats_deleted(BINDER_STAT_NODE); + return true; } } + return false; +} - return 0; +static void binder_dec_node(struct binder_node *node, int strong, int internal) +{ + bool free_node; + + binder_node_inner_lock(node); + free_node = binder_dec_node_nilocked(node, strong, internal); + binder_node_inner_unlock(node); + if (free_node) + binder_free_node(node); } +static void binder_inc_node_tmpref_ilocked(struct binder_node *node) +{ + /* + * No call to binder_inc_node() is needed since we + * don't need to inform userspace of any changes to + * tmp_refs + */ + node->tmp_refs++; +} -static struct binder_ref *binder_get_ref(struct binder_proc *proc, - u32 desc, bool need_strong_ref) +/** + * binder_inc_node_tmpref() - take a temporary reference on node + * @node: node to reference + * + * Take reference on node to prevent the node from being freed + * while referenced only by a local variable. The inner lock is + * needed to serialize with the node work on the queue (which + * isn't needed after the node is dead). If the node is dead + * (node->proc is NULL), use binder_dead_nodes_lock to protect + * node->tmp_refs against dead-node-only cases where the node + * lock cannot be acquired (eg traversing the dead node list to + * print nodes) + */ +static void binder_inc_node_tmpref(struct binder_node *node) +{ + binder_node_lock(node); + if (node->proc) + binder_inner_proc_lock(node->proc); + else + spin_lock(&binder_dead_nodes_lock); + binder_inc_node_tmpref_ilocked(node); + if (node->proc) + binder_inner_proc_unlock(node->proc); + else + spin_unlock(&binder_dead_nodes_lock); + binder_node_unlock(node); +} + +/** + * binder_dec_node_tmpref() - remove a temporary reference on node + * @node: node to reference + * + * Release temporary reference on node taken via binder_inc_node_tmpref() + */ +static void binder_dec_node_tmpref(struct binder_node *node) +{ + bool free_node; + + binder_node_inner_lock(node); + if (!node->proc) + spin_lock(&binder_dead_nodes_lock); + node->tmp_refs--; + BUG_ON(node->tmp_refs < 0); + if (!node->proc) + spin_unlock(&binder_dead_nodes_lock); + /* + * Call binder_dec_node() to check if all refcounts are 0 + * and cleanup is needed. Calling with strong=0 and internal=1 + * causes no actual reference to be released in binder_dec_node(). + * If that changes, a change is needed here too. + */ + free_node = binder_dec_node_nilocked(node, 0, 1); + binder_node_inner_unlock(node); + if (free_node) + binder_free_node(node); +} + +static void binder_put_node(struct binder_node *node) +{ + binder_dec_node_tmpref(node); +} + +static struct binder_ref *binder_get_ref_olocked(struct binder_proc *proc, + u32 desc, bool need_strong_ref) { struct rb_node *n = proc->refs_by_desc.rb_node; struct binder_ref *ref; @@ -1010,11 +1562,11 @@ static struct binder_ref *binder_get_ref while (n) { ref = rb_entry(n, struct binder_ref, rb_node_desc); - if (desc < ref->desc) { + if (desc < ref->data.desc) { n = n->rb_left; - } else if (desc > ref->desc) { + } else if (desc > ref->data.desc) { n = n->rb_right; - } else if (need_strong_ref && !ref->strong) { + } else if (need_strong_ref && !ref->data.strong) { binder_user_error("tried to use weak ref as strong ref\n"); return NULL; } else { @@ -1024,13 +1576,34 @@ static struct binder_ref *binder_get_ref return NULL; } -static struct binder_ref *binder_get_ref_for_node(struct binder_proc *proc, - struct binder_node *node) +/** + * binder_get_ref_for_node_olocked() - get the ref associated with given node + * @proc: binder_proc that owns the ref + * @node: binder_node of target + * @new_ref: newly allocated binder_ref to be initialized or %NULL + * + * Look up the ref for the given node and return it if it exists + * + * If it doesn't exist and the caller provides a newly allocated + * ref, initialize the fields of the newly allocated ref and insert + * into the given proc rb_trees and node refs list. + * + * Return: the ref for node. It is possible that another thread + * allocated/initialized the ref first in which case the + * returned ref would be different than the passed-in + * new_ref. new_ref must be kfree'd by the caller in + * this case. + */ +static struct binder_ref *binder_get_ref_for_node_olocked( + struct binder_proc *proc, + struct binder_node *node, + struct binder_ref *new_ref) { - struct rb_node *n; + struct binder_context *context = proc->context; struct rb_node **p = &proc->refs_by_node.rb_node; struct rb_node *parent = NULL; - struct binder_ref *ref, *new_ref; + struct binder_ref *ref; + struct rb_node *n; while (*p) { parent = *p; @@ -1043,22 +1616,22 @@ static struct binder_ref *binder_get_ref else return ref; } - new_ref = kzalloc(sizeof(*ref), GFP_KERNEL); - if (new_ref == NULL) + if (!new_ref) return NULL; + binder_stats_created(BINDER_STAT_REF); - new_ref->debug_id = ++binder_last_id; + new_ref->data.debug_id = atomic_inc_return(&binder_last_id); new_ref->proc = proc; new_ref->node = node; rb_link_node(&new_ref->rb_node_node, parent, p); rb_insert_color(&new_ref->rb_node_node, &proc->refs_by_node); - new_ref->desc = (node == binder_context_mgr_node) ? 0 : 1; + new_ref->data.desc = (node == context->binder_context_mgr_node) ? 0 : 1; for (n = rb_first(&proc->refs_by_desc); n != NULL; n = rb_next(n)) { ref = rb_entry(n, struct binder_ref, rb_node_desc); - if (ref->desc > new_ref->desc) + if (ref->data.desc > new_ref->data.desc) break; - new_ref->desc = ref->desc + 1; + new_ref->data.desc = ref->data.desc + 1; } p = &proc->refs_by_desc.rb_node; @@ -1066,121 +1639,423 @@ static struct binder_ref *binder_get_ref parent = *p; ref = rb_entry(parent, struct binder_ref, rb_node_desc); - if (new_ref->desc < ref->desc) + if (new_ref->data.desc < ref->data.desc) p = &(*p)->rb_left; - else if (new_ref->desc > ref->desc) + else if (new_ref->data.desc > ref->data.desc) p = &(*p)->rb_right; else BUG(); } rb_link_node(&new_ref->rb_node_desc, parent, p); rb_insert_color(&new_ref->rb_node_desc, &proc->refs_by_desc); - if (node) { - hlist_add_head(&new_ref->node_entry, &node->refs); - binder_debug(BINDER_DEBUG_INTERNAL_REFS, - "%d new ref %d desc %d for node %d\n", - proc->pid, new_ref->debug_id, new_ref->desc, - node->debug_id); - } else { - binder_debug(BINDER_DEBUG_INTERNAL_REFS, - "%d new ref %d desc %d for dead node\n", - proc->pid, new_ref->debug_id, new_ref->desc); - } + binder_node_lock(node); + hlist_add_head(&new_ref->node_entry, &node->refs); + + binder_debug(BINDER_DEBUG_INTERNAL_REFS, + "%d new ref %d desc %d for node %d\n", + proc->pid, new_ref->data.debug_id, new_ref->data.desc, + node->debug_id); + binder_node_unlock(node); return new_ref; } -static void binder_delete_ref(struct binder_ref *ref) +static void binder_cleanup_ref_olocked(struct binder_ref *ref) { + bool delete_node = false; + binder_debug(BINDER_DEBUG_INTERNAL_REFS, "%d delete ref %d desc %d for node %d\n", - ref->proc->pid, ref->debug_id, ref->desc, + ref->proc->pid, ref->data.debug_id, ref->data.desc, ref->node->debug_id); rb_erase(&ref->rb_node_desc, &ref->proc->refs_by_desc); rb_erase(&ref->rb_node_node, &ref->proc->refs_by_node); - if (ref->strong) - binder_dec_node(ref->node, 1, 1); + + binder_node_inner_lock(ref->node); + if (ref->data.strong) + binder_dec_node_nilocked(ref->node, 1, 1); + hlist_del(&ref->node_entry); - binder_dec_node(ref->node, 0, 1); + delete_node = binder_dec_node_nilocked(ref->node, 0, 1); + binder_node_inner_unlock(ref->node); + /* + * Clear ref->node unless we want the caller to free the node + */ + if (!delete_node) { + /* + * The caller uses ref->node to determine + * whether the node needs to be freed. Clear + * it since the node is still alive. + */ + ref->node = NULL; + } + if (ref->death) { binder_debug(BINDER_DEBUG_DEAD_BINDER, "%d delete ref %d desc %d has death notification\n", - ref->proc->pid, ref->debug_id, ref->desc); - list_del(&ref->death->work.entry); - kfree(ref->death); + ref->proc->pid, ref->data.debug_id, + ref->data.desc); + binder_dequeue_work(ref->proc, &ref->death->work); binder_stats_deleted(BINDER_STAT_DEATH); } - kfree(ref); binder_stats_deleted(BINDER_STAT_REF); } -static int binder_inc_ref(struct binder_ref *ref, int strong, - struct list_head *target_list) +/** + * binder_inc_ref_olocked() - increment the ref for given handle + * @ref: ref to be incremented + * @strong: if true, strong increment, else weak + * @target_list: list to queue node work on + * + * Increment the ref. @ref->proc->outer_lock must be held on entry + * + * Return: 0, if successful, else errno + */ +static int binder_inc_ref_olocked(struct binder_ref *ref, int strong, + struct list_head *target_list) { int ret; if (strong) { - if (ref->strong == 0) { + if (ref->data.strong == 0) { ret = binder_inc_node(ref->node, 1, 1, target_list); if (ret) return ret; } - ref->strong++; + ref->data.strong++; } else { - if (ref->weak == 0) { + if (ref->data.weak == 0) { ret = binder_inc_node(ref->node, 0, 1, target_list); if (ret) return ret; } - ref->weak++; + ref->data.weak++; } return 0; } - -static int binder_dec_ref(struct binder_ref *ref, int strong) +/** + * binder_dec_ref() - dec the ref for given handle + * @ref: ref to be decremented + * @strong: if true, strong decrement, else weak + * + * Decrement the ref. + * + * Return: true if ref is cleaned up and ready to be freed + */ +static bool binder_dec_ref_olocked(struct binder_ref *ref, int strong) { if (strong) { - if (ref->strong == 0) { + if (ref->data.strong == 0) { binder_user_error("%d invalid dec strong, ref %d desc %d s %d w %d\n", - ref->proc->pid, ref->debug_id, - ref->desc, ref->strong, ref->weak); - return -EINVAL; - } - ref->strong--; - if (ref->strong == 0) { - int ret; - - ret = binder_dec_node(ref->node, strong, 1); - if (ret) - return ret; + ref->proc->pid, ref->data.debug_id, + ref->data.desc, ref->data.strong, + ref->data.weak); + return false; } + ref->data.strong--; + if (ref->data.strong == 0) + binder_dec_node(ref->node, strong, 1); } else { - if (ref->weak == 0) { + if (ref->data.weak == 0) { binder_user_error("%d invalid dec weak, ref %d desc %d s %d w %d\n", - ref->proc->pid, ref->debug_id, - ref->desc, ref->strong, ref->weak); - return -EINVAL; + ref->proc->pid, ref->data.debug_id, + ref->data.desc, ref->data.strong, + ref->data.weak); + return false; } - ref->weak--; + ref->data.weak--; } - if (ref->strong == 0 && ref->weak == 0) - binder_delete_ref(ref); - return 0; + if (ref->data.strong == 0 && ref->data.weak == 0) { + binder_cleanup_ref_olocked(ref); + return true; + } + return false; } -static void binder_pop_transaction(struct binder_thread *target_thread, - struct binder_transaction *t) +/** + * binder_get_node_from_ref() - get the node from the given proc/desc + * @proc: proc containing the ref + * @desc: the handle associated with the ref + * @need_strong_ref: if true, only return node if ref is strong + * @rdata: the id/refcount data for the ref + * + * Given a proc and ref handle, return the associated binder_node + * + * Return: a binder_node or NULL if not found or not strong when strong required + */ +static struct binder_node *binder_get_node_from_ref( + struct binder_proc *proc, + u32 desc, bool need_strong_ref, + struct binder_ref_data *rdata) { - if (target_thread) { - BUG_ON(target_thread->transaction_stack != t); - BUG_ON(target_thread->transaction_stack->from != target_thread); - target_thread->transaction_stack = - target_thread->transaction_stack->from_parent; - t->from = NULL; + struct binder_node *node; + struct binder_ref *ref; + + binder_proc_lock(proc); + ref = binder_get_ref_olocked(proc, desc, need_strong_ref); + if (!ref) + goto err_no_ref; + node = ref->node; + /* + * Take an implicit reference on the node to ensure + * it stays alive until the call to binder_put_node() + */ + binder_inc_node_tmpref(node); + if (rdata) + *rdata = ref->data; + binder_proc_unlock(proc); + + return node; + +err_no_ref: + binder_proc_unlock(proc); + return NULL; +} + +/** + * binder_free_ref() - free the binder_ref + * @ref: ref to free + * + * Free the binder_ref. Free the binder_node indicated by ref->node + * (if non-NULL) and the binder_ref_death indicated by ref->death. + */ +static void binder_free_ref(struct binder_ref *ref) +{ + if (ref->node) + binder_free_node(ref->node); + kfree(ref->death); + kfree(ref); +} + +/** + * binder_update_ref_for_handle() - inc/dec the ref for given handle + * @proc: proc containing the ref + * @desc: the handle associated with the ref + * @increment: true=inc reference, false=dec reference + * @strong: true=strong reference, false=weak reference + * @rdata: the id/refcount data for the ref + * + * Given a proc and ref handle, increment or decrement the ref + * according to "increment" arg. + * + * Return: 0 if successful, else errno + */ +static int binder_update_ref_for_handle(struct binder_proc *proc, + uint32_t desc, bool increment, bool strong, + struct binder_ref_data *rdata) +{ + int ret = 0; + struct binder_ref *ref; + bool delete_ref = false; + + binder_proc_lock(proc); + ref = binder_get_ref_olocked(proc, desc, strong); + if (!ref) { + ret = -EINVAL; + goto err_no_ref; } - t->need_reply = 0; + if (increment) + ret = binder_inc_ref_olocked(ref, strong, NULL); + else + delete_ref = binder_dec_ref_olocked(ref, strong); + + if (rdata) + *rdata = ref->data; + binder_proc_unlock(proc); + + if (delete_ref) + binder_free_ref(ref); + return ret; + +err_no_ref: + binder_proc_unlock(proc); + return ret; +} + +/** + * binder_dec_ref_for_handle() - dec the ref for given handle + * @proc: proc containing the ref + * @desc: the handle associated with the ref + * @strong: true=strong reference, false=weak reference + * @rdata: the id/refcount data for the ref + * + * Just calls binder_update_ref_for_handle() to decrement the ref. + * + * Return: 0 if successful, else errno + */ +static int binder_dec_ref_for_handle(struct binder_proc *proc, + uint32_t desc, bool strong, struct binder_ref_data *rdata) +{ + return binder_update_ref_for_handle(proc, desc, false, strong, rdata); +} + + +/** + * binder_inc_ref_for_node() - increment the ref for given proc/node + * @proc: proc containing the ref + * @node: target node + * @strong: true=strong reference, false=weak reference + * @target_list: worklist to use if node is incremented + * @rdata: the id/refcount data for the ref + * + * Given a proc and node, increment the ref. Create the ref if it + * doesn't already exist + * + * Return: 0 if successful, else errno + */ +static int binder_inc_ref_for_node(struct binder_proc *proc, + struct binder_node *node, + bool strong, + struct list_head *target_list, + struct binder_ref_data *rdata) +{ + struct binder_ref *ref; + struct binder_ref *new_ref = NULL; + int ret = 0; + + binder_proc_lock(proc); + ref = binder_get_ref_for_node_olocked(proc, node, NULL); + if (!ref) { + binder_proc_unlock(proc); + new_ref = kzalloc(sizeof(*ref), GFP_KERNEL); + if (!new_ref) + return -ENOMEM; + binder_proc_lock(proc); + ref = binder_get_ref_for_node_olocked(proc, node, new_ref); + } + ret = binder_inc_ref_olocked(ref, strong, target_list); + *rdata = ref->data; + binder_proc_unlock(proc); + if (new_ref && ref != new_ref) + /* + * Another thread created the ref first so + * free the one we allocated + */ + kfree(new_ref); + return ret; +} + +static void binder_pop_transaction_ilocked(struct binder_thread *target_thread, + struct binder_transaction *t) +{ + BUG_ON(!target_thread); + assert_spin_locked(&target_thread->proc->inner_lock); + BUG_ON(target_thread->transaction_stack != t); + BUG_ON(target_thread->transaction_stack->from != target_thread); + target_thread->transaction_stack = + target_thread->transaction_stack->from_parent; + t->from = NULL; +} + +/** + * binder_thread_dec_tmpref() - decrement thread->tmp_ref + * @thread: thread to decrement + * + * A thread needs to be kept alive while being used to create or + * handle a transaction. binder_get_txn_from() is used to safely + * extract t->from from a binder_transaction and keep the thread + * indicated by t->from from being freed. When done with that + * binder_thread, this function is called to decrement the + * tmp_ref and free if appropriate (thread has been released + * and no transaction being processed by the driver) + */ +static void binder_thread_dec_tmpref(struct binder_thread *thread) +{ + /* + * atomic is used to protect the counter value while + * it cannot reach zero or thread->is_dead is false + */ + binder_inner_proc_lock(thread->proc); + atomic_dec(&thread->tmp_ref); + if (thread->is_dead && !atomic_read(&thread->tmp_ref)) { + binder_inner_proc_unlock(thread->proc); + binder_free_thread(thread); + return; + } + binder_inner_proc_unlock(thread->proc); +} + +/** + * binder_proc_dec_tmpref() - decrement proc->tmp_ref + * @proc: proc to decrement + * + * A binder_proc needs to be kept alive while being used to create or + * handle a transaction. proc->tmp_ref is incremented when + * creating a new transaction or the binder_proc is currently in-use + * by threads that are being released. When done with the binder_proc, + * this function is called to decrement the counter and free the + * proc if appropriate (proc has been released, all threads have + * been released and not currenly in-use to process a transaction). + */ +static void binder_proc_dec_tmpref(struct binder_proc *proc) +{ + binder_inner_proc_lock(proc); + proc->tmp_ref--; + if (proc->is_dead && RB_EMPTY_ROOT(&proc->threads) && + !proc->tmp_ref) { + binder_inner_proc_unlock(proc); + binder_free_proc(proc); + return; + } + binder_inner_proc_unlock(proc); +} + +/** + * binder_get_txn_from() - safely extract the "from" thread in transaction + * @t: binder transaction for t->from + * + * Atomically return the "from" thread and increment the tmp_ref + * count for the thread to ensure it stays alive until + * binder_thread_dec_tmpref() is called. + * + * Return: the value of t->from + */ +static struct binder_thread *binder_get_txn_from( + struct binder_transaction *t) +{ + struct binder_thread *from; + + spin_lock(&t->lock); + from = t->from; + if (from) + atomic_inc(&from->tmp_ref); + spin_unlock(&t->lock); + return from; +} + +/** + * binder_get_txn_from_and_acq_inner() - get t->from and acquire inner lock + * @t: binder transaction for t->from + * + * Same as binder_get_txn_from() except it also acquires the proc->inner_lock + * to guarantee that the thread cannot be released while operating on it. + * The caller must call binder_inner_proc_unlock() to release the inner lock + * as well as call binder_dec_thread_txn() to release the reference. + * + * Return: the value of t->from + */ +static struct binder_thread *binder_get_txn_from_and_acq_inner( + struct binder_transaction *t) +{ + struct binder_thread *from; + + from = binder_get_txn_from(t); + if (!from) + return NULL; + binder_inner_proc_lock(from->proc); + if (t->from) { + BUG_ON(from != t->from); + return from; + } + binder_inner_proc_unlock(from->proc); + binder_thread_dec_tmpref(from); + return NULL; +} + +static void binder_free_transaction(struct binder_transaction *t) +{ if (t->buffer) t->buffer->transaction = NULL; kfree(t); @@ -1195,30 +2070,28 @@ static void binder_send_failed_reply(str BUG_ON(t->flags & TF_ONE_WAY); while (1) { - target_thread = t->from; + target_thread = binder_get_txn_from_and_acq_inner(t); if (target_thread) { - if (target_thread->return_error != BR_OK && - target_thread->return_error2 == BR_OK) { - target_thread->return_error2 = - target_thread->return_error; - target_thread->return_error = BR_OK; - } - if (target_thread->return_error == BR_OK) { - binder_debug(BINDER_DEBUG_FAILED_TRANSACTION, - "send failed reply for transaction %d to %d:%d\n", - t->debug_id, - target_thread->proc->pid, - target_thread->pid); + binder_debug(BINDER_DEBUG_FAILED_TRANSACTION, + "send failed reply for transaction %d to %d:%d\n", + t->debug_id, + target_thread->proc->pid, + target_thread->pid); - binder_pop_transaction(target_thread, t); - target_thread->return_error = error_code; + binder_pop_transaction_ilocked(target_thread, t); + if (target_thread->reply_error.cmd == BR_OK) { + target_thread->reply_error.cmd = error_code; + binder_enqueue_work_ilocked( + &target_thread->reply_error.work, + &target_thread->todo); wake_up_interruptible(&target_thread->wait); } else { - pr_err("reply failed, target thread, %d:%d, has error code %d already\n", - target_thread->proc->pid, - target_thread->pid, - target_thread->return_error); + WARN(1, "Unexpected reply error: %u\n", + target_thread->reply_error.cmd); } + binder_inner_proc_unlock(target_thread->proc); + binder_thread_dec_tmpref(target_thread); + binder_free_transaction(t); return; } next = t->from_parent; @@ -1227,7 +2100,7 @@ static void binder_send_failed_reply(str "send failed reply for transaction %d, target dead\n", t->debug_id); - binder_pop_transaction(target_thread, t); + binder_free_transaction(t); if (next == NULL) { binder_debug(BINDER_DEBUG_DEAD_BINDER, "reply failed, no target thread at root\n"); @@ -1240,11 +2113,158 @@ static void binder_send_failed_reply(str } } +/** + * binder_validate_object() - checks for a valid metadata object in a buffer. + * @buffer: binder_buffer that we're parsing. + * @offset: offset in the buffer at which to validate an object. + * + * Return: If there's a valid metadata object at @offset in @buffer, the + * size of that object. Otherwise, it returns zero. + */ +static size_t binder_validate_object(struct binder_buffer *buffer, u64 offset) +{ + /* Check if we can read a header first */ + struct binder_object_header *hdr; + size_t object_size = 0; + + if (offset > buffer->data_size - sizeof(*hdr) || + buffer->data_size < sizeof(*hdr) || + !IS_ALIGNED(offset, sizeof(u32))) + return 0; + + /* Ok, now see if we can read a complete object. */ + hdr = (struct binder_object_header *)(buffer->data + offset); + switch (hdr->type) { + case BINDER_TYPE_BINDER: + case BINDER_TYPE_WEAK_BINDER: + case BINDER_TYPE_HANDLE: + case BINDER_TYPE_WEAK_HANDLE: + object_size = sizeof(struct flat_binder_object); + break; + case BINDER_TYPE_FD: + object_size = sizeof(struct binder_fd_object); + break; + case BINDER_TYPE_PTR: + object_size = sizeof(struct binder_buffer_object); + break; + case BINDER_TYPE_FDA: + object_size = sizeof(struct binder_fd_array_object); + break; + default: + return 0; + } + if (offset <= buffer->data_size - object_size && + buffer->data_size >= object_size) + return object_size; + else + return 0; +} + +/** + * binder_validate_ptr() - validates binder_buffer_object in a binder_buffer. + * @b: binder_buffer containing the object + * @index: index in offset array at which the binder_buffer_object is + * located + * @start: points to the start of the offset array + * @num_valid: the number of valid offsets in the offset array + * + * Return: If @index is within the valid range of the offset array + * described by @start and @num_valid, and if there's a valid + * binder_buffer_object at the offset found in index @index + * of the offset array, that object is returned. Otherwise, + * %NULL is returned. + * Note that the offset found in index @index itself is not + * verified; this function assumes that @num_valid elements + * from @start were previously verified to have valid offsets. + */ +static struct binder_buffer_object *binder_validate_ptr(struct binder_buffer *b, + binder_size_t index, + binder_size_t *start, + binder_size_t num_valid) +{ + struct binder_buffer_object *buffer_obj; + binder_size_t *offp; + + if (index >= num_valid) + return NULL; + + offp = start + index; + buffer_obj = (struct binder_buffer_object *)(b->data + *offp); + if (buffer_obj->hdr.type != BINDER_TYPE_PTR) + return NULL; + + return buffer_obj; +} + +/** + * binder_validate_fixup() - validates pointer/fd fixups happen in order. + * @b: transaction buffer + * @objects_start start of objects buffer + * @buffer: binder_buffer_object in which to fix up + * @offset: start offset in @buffer to fix up + * @last_obj: last binder_buffer_object that we fixed up in + * @last_min_offset: minimum fixup offset in @last_obj + * + * Return: %true if a fixup in buffer @buffer at offset @offset is + * allowed. + * + * For safety reasons, we only allow fixups inside a buffer to happen + * at increasing offsets; additionally, we only allow fixup on the last + * buffer object that was verified, or one of its parents. + * + * Example of what is allowed: + * + * A + * B (parent = A, offset = 0) + * C (parent = A, offset = 16) + * D (parent = C, offset = 0) + * E (parent = A, offset = 32) // min_offset is 16 (C.parent_offset) + * + * Examples of what is not allowed: + * + * Decreasing offsets within the same parent: + * A + * C (parent = A, offset = 16) + * B (parent = A, offset = 0) // decreasing offset within A + * + * Referring to a parent that wasn't the last object or any of its parents: + * A + * B (parent = A, offset = 0) + * C (parent = A, offset = 0) + * C (parent = A, offset = 16) + * D (parent = B, offset = 0) // B is not A or any of A's parents + */ +static bool binder_validate_fixup(struct binder_buffer *b, + binder_size_t *objects_start, + struct binder_buffer_object *buffer, + binder_size_t fixup_offset, + struct binder_buffer_object *last_obj, + binder_size_t last_min_offset) +{ + if (!last_obj) { + /* Nothing to fix up in */ + return false; + } + + while (last_obj != buffer) { + /* + * Safe to retrieve the parent of last_obj, since it + * was already previously verified by the driver. + */ + if ((last_obj->flags & BINDER_BUFFER_FLAG_HAS_PARENT) == 0) + return false; + last_min_offset = last_obj->parent_offset + sizeof(uintptr_t); + last_obj = (struct binder_buffer_object *) + (b->data + *(objects_start + last_obj->parent)); + } + return (fixup_offset >= last_min_offset); +} + static void binder_transaction_buffer_release(struct binder_proc *proc, struct binder_buffer *buffer, binder_size_t *failed_at) { - binder_size_t *offp, *off_end; + binder_size_t *offp, *off_start, *off_end; int debug_id = buffer->debug_id; binder_debug(BINDER_DEBUG_TRANSACTION, @@ -1255,28 +2275,30 @@ static void binder_transaction_buffer_re if (buffer->target_node) binder_dec_node(buffer->target_node, 1, 0); - offp = (binder_size_t *)(buffer->data + - ALIGN(buffer->data_size, sizeof(void *))); + off_start = (binder_size_t *)(buffer->data + + ALIGN(buffer->data_size, sizeof(void *))); if (failed_at) off_end = failed_at; else - off_end = (void *)offp + buffer->offsets_size; - for (; offp < off_end; offp++) { - struct flat_binder_object *fp; + off_end = (void *)off_start + buffer->offsets_size; + for (offp = off_start; offp < off_end; offp++) { + struct binder_object_header *hdr; + size_t object_size = binder_validate_object(buffer, *offp); - if (*offp > buffer->data_size - sizeof(*fp) || - buffer->data_size < sizeof(*fp) || - !IS_ALIGNED(*offp, sizeof(u32))) { - pr_err("transaction release %d bad offset %lld, size %zd\n", + if (object_size == 0) { + pr_err("transaction release %d bad object at offset %lld, size %zd\n", debug_id, (u64)*offp, buffer->data_size); continue; } - fp = (struct flat_binder_object *)(buffer->data + *offp); - switch (fp->type) { + hdr = (struct binder_object_header *)(buffer->data + *offp); + switch (hdr->type) { case BINDER_TYPE_BINDER: case BINDER_TYPE_WEAK_BINDER: { - struct binder_node *node = binder_get_node(proc, fp->binder); + struct flat_binder_object *fp; + struct binder_node *node; + fp = to_flat_binder_object(hdr); + node = binder_get_node(proc, fp->binder); if (node == NULL) { pr_err("transaction release %d bad node %016llx\n", debug_id, (u64)fp->binder); @@ -1285,90 +2307,564 @@ static void binder_transaction_buffer_re binder_debug(BINDER_DEBUG_TRANSACTION, " node %d u%016llx\n", node->debug_id, (u64)node->ptr); - binder_dec_node(node, fp->type == BINDER_TYPE_BINDER, 0); + binder_dec_node(node, hdr->type == BINDER_TYPE_BINDER, + 0); + binder_put_node(node); } break; case BINDER_TYPE_HANDLE: case BINDER_TYPE_WEAK_HANDLE: { - struct binder_ref *ref; + struct flat_binder_object *fp; + struct binder_ref_data rdata; + int ret; - ref = binder_get_ref(proc, fp->handle, - fp->type == BINDER_TYPE_HANDLE); + fp = to_flat_binder_object(hdr); + ret = binder_dec_ref_for_handle(proc, fp->handle, + hdr->type == BINDER_TYPE_HANDLE, &rdata); - if (ref == NULL) { - pr_err("transaction release %d bad handle %d\n", - debug_id, fp->handle); + if (ret) { + pr_err("transaction release %d bad handle %d, ret = %d\n", + debug_id, fp->handle, ret); break; } binder_debug(BINDER_DEBUG_TRANSACTION, - " ref %d desc %d (node %d)\n", - ref->debug_id, ref->desc, ref->node->debug_id); - binder_dec_ref(ref, fp->type == BINDER_TYPE_HANDLE); + " ref %d desc %d\n", + rdata.debug_id, rdata.desc); } break; - case BINDER_TYPE_FD: + case BINDER_TYPE_FD: { + struct binder_fd_object *fp = to_binder_fd_object(hdr); + binder_debug(BINDER_DEBUG_TRANSACTION, - " fd %d\n", fp->handle); + " fd %d\n", fp->fd); if (failed_at) - task_close_fd(proc, fp->handle); + task_close_fd(proc, fp->fd); + } break; + case BINDER_TYPE_PTR: + /* + * Nothing to do here, this will get cleaned up when the + * transaction buffer gets freed + */ break; + case BINDER_TYPE_FDA: { + struct binder_fd_array_object *fda; + struct binder_buffer_object *parent; + uintptr_t parent_buffer; + u32 *fd_array; + size_t fd_index; + binder_size_t fd_buf_size; + + fda = to_binder_fd_array_object(hdr); + parent = binder_validate_ptr(buffer, fda->parent, + off_start, + offp - off_start); + if (!parent) { + pr_err("transaction release %d bad parent offset", + debug_id); + continue; + } + /* + * Since the parent was already fixed up, convert it + * back to kernel address space to access it + */ + parent_buffer = parent->buffer - + binder_alloc_get_user_buffer_offset( + &proc->alloc); + fd_buf_size = sizeof(u32) * fda->num_fds; + if (fda->num_fds >= SIZE_MAX / sizeof(u32)) { + pr_err("transaction release %d invalid number of fds (%lld)\n", + debug_id, (u64)fda->num_fds); + continue; + } + if (fd_buf_size > parent->length || + fda->parent_offset > parent->length - fd_buf_size) { + /* No space for all file descriptors here. */ + pr_err("transaction release %d not enough space for %lld fds in buffer\n", + debug_id, (u64)fda->num_fds); + continue; + } + fd_array = (u32 *)(parent_buffer + fda->parent_offset); + for (fd_index = 0; fd_index < fda->num_fds; fd_index++) + task_close_fd(proc, fd_array[fd_index]); + } break; default: pr_err("transaction release %d bad object type %x\n", - debug_id, fp->type); + debug_id, hdr->type); break; } } } +static int binder_translate_binder(struct flat_binder_object *fp, + struct binder_transaction *t, + struct binder_thread *thread) +{ + struct binder_node *node; + struct binder_proc *proc = thread->proc; + struct binder_proc *target_proc = t->to_proc; + struct binder_ref_data rdata; + int ret = 0; + + node = binder_get_node(proc, fp->binder); + if (!node) { + node = binder_new_node(proc, fp); + if (!node) + return -ENOMEM; + } + if (fp->cookie != node->cookie) { + binder_user_error("%d:%d sending u%016llx node %d, cookie mismatch %016llx != %016llx\n", + proc->pid, thread->pid, (u64)fp->binder, + node->debug_id, (u64)fp->cookie, + (u64)node->cookie); + ret = -EINVAL; + goto done; + } + if (security_binder_transfer_binder(proc->tsk, target_proc->tsk)) { + ret = -EPERM; + goto done; + } + + ret = binder_inc_ref_for_node(target_proc, node, + fp->hdr.type == BINDER_TYPE_BINDER, + &thread->todo, &rdata); + if (ret) + goto done; + + if (fp->hdr.type == BINDER_TYPE_BINDER) + fp->hdr.type = BINDER_TYPE_HANDLE; + else + fp->hdr.type = BINDER_TYPE_WEAK_HANDLE; + fp->binder = 0; + fp->handle = rdata.desc; + fp->cookie = 0; + + trace_binder_transaction_node_to_ref(t, node, &rdata); + binder_debug(BINDER_DEBUG_TRANSACTION, + " node %d u%016llx -> ref %d desc %d\n", + node->debug_id, (u64)node->ptr, + rdata.debug_id, rdata.desc); +done: + binder_put_node(node); + return ret; +} + +static int binder_translate_handle(struct flat_binder_object *fp, + struct binder_transaction *t, + struct binder_thread *thread) +{ + struct binder_proc *proc = thread->proc; + struct binder_proc *target_proc = t->to_proc; + struct binder_node *node; + struct binder_ref_data src_rdata; + int ret = 0; + + node = binder_get_node_from_ref(proc, fp->handle, + fp->hdr.type == BINDER_TYPE_HANDLE, &src_rdata); + if (!node) { + binder_user_error("%d:%d got transaction with invalid handle, %d\n", + proc->pid, thread->pid, fp->handle); + return -EINVAL; + } + if (security_binder_transfer_binder(proc->tsk, target_proc->tsk)) { + ret = -EPERM; + goto done; + } + + binder_node_lock(node); + if (node->proc == target_proc) { + if (fp->hdr.type == BINDER_TYPE_HANDLE) + fp->hdr.type = BINDER_TYPE_BINDER; + else + fp->hdr.type = BINDER_TYPE_WEAK_BINDER; + fp->binder = node->ptr; + fp->cookie = node->cookie; + if (node->proc) + binder_inner_proc_lock(node->proc); + binder_inc_node_nilocked(node, + fp->hdr.type == BINDER_TYPE_BINDER, + 0, NULL); + if (node->proc) + binder_inner_proc_unlock(node->proc); + trace_binder_transaction_ref_to_node(t, node, &src_rdata); + binder_debug(BINDER_DEBUG_TRANSACTION, + " ref %d desc %d -> node %d u%016llx\n", + src_rdata.debug_id, src_rdata.desc, node->debug_id, + (u64)node->ptr); + binder_node_unlock(node); + } else { + struct binder_ref_data dest_rdata; + + binder_node_unlock(node); + ret = binder_inc_ref_for_node(target_proc, node, + fp->hdr.type == BINDER_TYPE_HANDLE, + NULL, &dest_rdata); + if (ret) + goto done; + + fp->binder = 0; + fp->handle = dest_rdata.desc; + fp->cookie = 0; + trace_binder_transaction_ref_to_ref(t, node, &src_rdata, + &dest_rdata); + binder_debug(BINDER_DEBUG_TRANSACTION, + " ref %d desc %d -> ref %d desc %d (node %d)\n", + src_rdata.debug_id, src_rdata.desc, + dest_rdata.debug_id, dest_rdata.desc, + node->debug_id); + } +done: + binder_put_node(node); + return ret; +} + +static int binder_translate_fd(int fd, + struct binder_transaction *t, + struct binder_thread *thread, + struct binder_transaction *in_reply_to) +{ + struct binder_proc *proc = thread->proc; + struct binder_proc *target_proc = t->to_proc; + int target_fd; + struct file *file; + int ret; + bool target_allows_fd; + + if (in_reply_to) + target_allows_fd = !!(in_reply_to->flags & TF_ACCEPT_FDS); + else + target_allows_fd = t->buffer->target_node->accept_fds; + if (!target_allows_fd) { + binder_user_error("%d:%d got %s with fd, %d, but target does not allow fds\n", + proc->pid, thread->pid, + in_reply_to ? "reply" : "transaction", + fd); + ret = -EPERM; + goto err_fd_not_accepted; + } + + file = fget(fd); + if (!file) { + binder_user_error("%d:%d got transaction with invalid fd, %d\n", + proc->pid, thread->pid, fd); + ret = -EBADF; + goto err_fget; + } + ret = security_binder_transfer_file(proc->tsk, target_proc->tsk, file); + if (ret < 0) { + ret = -EPERM; + goto err_security; + } + + target_fd = task_get_unused_fd_flags(target_proc, O_CLOEXEC); + if (target_fd < 0) { + ret = -ENOMEM; + goto err_get_unused_fd; + } + task_fd_install(target_proc, target_fd, file); + trace_binder_transaction_fd(t, fd, target_fd); + binder_debug(BINDER_DEBUG_TRANSACTION, " fd %d -> %d\n", + fd, target_fd); + + return target_fd; + +err_get_unused_fd: +err_security: + fput(file); +err_fget: +err_fd_not_accepted: + return ret; +} + +static int binder_translate_fd_array(struct binder_fd_array_object *fda, + struct binder_buffer_object *parent, + struct binder_transaction *t, + struct binder_thread *thread, + struct binder_transaction *in_reply_to) +{ + binder_size_t fdi, fd_buf_size, num_installed_fds; + int target_fd; + uintptr_t parent_buffer; + u32 *fd_array; + struct binder_proc *proc = thread->proc; + struct binder_proc *target_proc = t->to_proc; + + fd_buf_size = sizeof(u32) * fda->num_fds; + if (fda->num_fds >= SIZE_MAX / sizeof(u32)) { + binder_user_error("%d:%d got transaction with invalid number of fds (%lld)\n", + proc->pid, thread->pid, (u64)fda->num_fds); + return -EINVAL; + } + if (fd_buf_size > parent->length || + fda->parent_offset > parent->length - fd_buf_size) { + /* No space for all file descriptors here. */ + binder_user_error("%d:%d not enough space to store %lld fds in buffer\n", + proc->pid, thread->pid, (u64)fda->num_fds); + return -EINVAL; + } + /* + * Since the parent was already fixed up, convert it + * back to the kernel address space to access it + */ + parent_buffer = parent->buffer - + binder_alloc_get_user_buffer_offset(&target_proc->alloc); + fd_array = (u32 *)(parent_buffer + fda->parent_offset); + if (!IS_ALIGNED((unsigned long)fd_array, sizeof(u32))) { + binder_user_error("%d:%d parent offset not aligned correctly.\n", + proc->pid, thread->pid); + return -EINVAL; + } + for (fdi = 0; fdi < fda->num_fds; fdi++) { + target_fd = binder_translate_fd(fd_array[fdi], t, thread, + in_reply_to); + if (target_fd < 0) + goto err_translate_fd_failed; + fd_array[fdi] = target_fd; + } + return 0; + +err_translate_fd_failed: + /* + * Failed to allocate fd or security error, free fds + * installed so far. + */ + num_installed_fds = fdi; + for (fdi = 0; fdi < num_installed_fds; fdi++) + task_close_fd(target_proc, fd_array[fdi]); + return target_fd; +} + +static int binder_fixup_parent(struct binder_transaction *t, + struct binder_thread *thread, + struct binder_buffer_object *bp, + binder_size_t *off_start, + binder_size_t num_valid, + struct binder_buffer_object *last_fixup_obj, + binder_size_t last_fixup_min_off) +{ + struct binder_buffer_object *parent; + u8 *parent_buffer; + struct binder_buffer *b = t->buffer; + struct binder_proc *proc = thread->proc; + struct binder_proc *target_proc = t->to_proc; + + if (!(bp->flags & BINDER_BUFFER_FLAG_HAS_PARENT)) + return 0; + + parent = binder_validate_ptr(b, bp->parent, off_start, num_valid); + if (!parent) { + binder_user_error("%d:%d got transaction with invalid parent offset or type\n", + proc->pid, thread->pid); + return -EINVAL; + } + + if (!binder_validate_fixup(b, off_start, + parent, bp->parent_offset, + last_fixup_obj, + last_fixup_min_off)) { + binder_user_error("%d:%d got transaction with out-of-order buffer fixup\n", + proc->pid, thread->pid); + return -EINVAL; + } + + if (parent->length < sizeof(binder_uintptr_t) || + bp->parent_offset > parent->length - sizeof(binder_uintptr_t)) { + /* No space for a pointer here! */ + binder_user_error("%d:%d got transaction with invalid parent offset\n", + proc->pid, thread->pid); + return -EINVAL; + } + parent_buffer = (u8 *)(parent->buffer - + binder_alloc_get_user_buffer_offset( + &target_proc->alloc)); + *(binder_uintptr_t *)(parent_buffer + bp->parent_offset) = bp->buffer; + + return 0; +} + +/** + * binder_proc_transaction() - sends a transaction to a process and wakes it up + * @t: transaction to send + * @proc: process to send the transaction to + * @thread: thread in @proc to send the transaction to (may be NULL) + * + * This function queues a transaction to the specified process. It will try + * to find a thread in the target process to handle the transaction and + * wake it up. If no thread is found, the work is queued to the proc + * waitqueue. + * + * If the @thread parameter is not NULL, the transaction is always queued + * to the waitlist of that specific thread. + * + * Return: true if the transactions was successfully queued + * false if the target process or thread is dead + */ +static bool binder_proc_transaction(struct binder_transaction *t, + struct binder_proc *proc, + struct binder_thread *thread) +{ + struct list_head *target_list = NULL; + struct binder_node *node = t->buffer->target_node; + struct binder_priority node_prio; + bool oneway = !!(t->flags & TF_ONE_WAY); + bool wakeup = true; + + BUG_ON(!node); + binder_node_lock(node); + node_prio.prio = node->min_priority; + node_prio.sched_policy = node->sched_policy; + + if (oneway) { + BUG_ON(thread); + if (node->has_async_transaction) { + target_list = &node->async_todo; + wakeup = false; + } else { + node->has_async_transaction = 1; + } + } + + binder_inner_proc_lock(proc); + + if (proc->is_dead || (thread && thread->is_dead)) { + binder_inner_proc_unlock(proc); + binder_node_unlock(node); + return false; + } + + if (!thread && !target_list) + thread = binder_select_thread_ilocked(proc); + + if (thread) { + target_list = &thread->todo; + binder_transaction_priority(thread->task, t, node_prio, + node->inherit_rt); + } else if (!target_list) { + target_list = &proc->todo; + } else { + BUG_ON(target_list != &node->async_todo); + } + + binder_enqueue_work_ilocked(&t->work, target_list); + + if (wakeup) + binder_wakeup_thread_ilocked(proc, thread, !oneway /* sync */); + + binder_inner_proc_unlock(proc); + binder_node_unlock(node); + + return true; +} + +/** + * binder_get_node_refs_for_txn() - Get required refs on node for txn + * @node: struct binder_node for which to get refs + * @proc: returns @node->proc if valid + * @error: if no @proc then returns BR_DEAD_REPLY + * + * User-space normally keeps the node alive when creating a transaction + * since it has a reference to the target. The local strong ref keeps it + * alive if the sending process dies before the target process processes + * the transaction. If the source process is malicious or has a reference + * counting bug, relying on the local strong ref can fail. + * + * Since user-space can cause the local strong ref to go away, we also take + * a tmpref on the node to ensure it survives while we are constructing + * the transaction. We also need a tmpref on the proc while we are + * constructing the transaction, so we take that here as well. + * + * Return: The target_node with refs taken or NULL if no @node->proc is NULL. + * Also sets @proc if valid. If the @node->proc is NULL indicating that the + * target proc has died, @error is set to BR_DEAD_REPLY + */ +static struct binder_node *binder_get_node_refs_for_txn( + struct binder_node *node, + struct binder_proc **procp, + uint32_t *error) +{ + struct binder_node *target_node = NULL; + + binder_node_inner_lock(node); + if (node->proc) { + target_node = node; + binder_inc_node_nilocked(node, 1, 0, NULL); + binder_inc_node_tmpref_ilocked(node); + node->proc->tmp_ref++; + *procp = node->proc; + } else + *error = BR_DEAD_REPLY; + binder_node_inner_unlock(node); + + return target_node; +} + static void binder_transaction(struct binder_proc *proc, struct binder_thread *thread, - struct binder_transaction_data *tr, int reply) + struct binder_transaction_data *tr, int reply, + binder_size_t extra_buffers_size) { + int ret; struct binder_transaction *t; struct binder_work *tcomplete; - binder_size_t *offp, *off_end; + binder_size_t *offp, *off_end, *off_start; binder_size_t off_min; - struct binder_proc *target_proc; + u8 *sg_bufp, *sg_buf_end; + struct binder_proc *target_proc = NULL; struct binder_thread *target_thread = NULL; struct binder_node *target_node = NULL; - struct list_head *target_list; - wait_queue_head_t *target_wait; struct binder_transaction *in_reply_to = NULL; struct binder_transaction_log_entry *e; - uint32_t return_error; + uint32_t return_error = 0; + uint32_t return_error_param = 0; + uint32_t return_error_line = 0; + struct binder_buffer_object *last_fixup_obj = NULL; + binder_size_t last_fixup_min_off = 0; + struct binder_context *context = proc->context; + int t_debug_id = atomic_inc_return(&binder_last_id); e = binder_transaction_log_add(&binder_transaction_log); + e->debug_id = t_debug_id; e->call_type = reply ? 2 : !!(tr->flags & TF_ONE_WAY); e->from_proc = proc->pid; e->from_thread = thread->pid; e->target_handle = tr->target.handle; e->data_size = tr->data_size; e->offsets_size = tr->offsets_size; + e->context_name = proc->context->name; if (reply) { + binder_inner_proc_lock(proc); in_reply_to = thread->transaction_stack; if (in_reply_to == NULL) { + binder_inner_proc_unlock(proc); binder_user_error("%d:%d got reply transaction with no transaction stack\n", proc->pid, thread->pid); return_error = BR_FAILED_REPLY; + return_error_param = -EPROTO; + return_error_line = __LINE__; goto err_empty_call_stack; } - binder_set_nice(in_reply_to->saved_priority); if (in_reply_to->to_thread != thread) { + spin_lock(&in_reply_to->lock); binder_user_error("%d:%d got reply transaction with bad transaction stack, transaction %d has target %d:%d\n", proc->pid, thread->pid, in_reply_to->debug_id, in_reply_to->to_proc ? in_reply_to->to_proc->pid : 0, in_reply_to->to_thread ? in_reply_to->to_thread->pid : 0); + spin_unlock(&in_reply_to->lock); + binder_inner_proc_unlock(proc); return_error = BR_FAILED_REPLY; + return_error_param = -EPROTO; + return_error_line = __LINE__; in_reply_to = NULL; goto err_bad_call_stack; } thread->transaction_stack = in_reply_to->to_parent; - target_thread = in_reply_to->from; + binder_inner_proc_unlock(proc); + target_thread = binder_get_txn_from_and_acq_inner(in_reply_to); if (target_thread == NULL) { return_error = BR_DEAD_REPLY; + return_error_line = __LINE__; goto err_dead_binder; } if (target_thread->transaction_stack != in_reply_to) { @@ -1377,106 +2873,148 @@ static void binder_transaction(struct bi target_thread->transaction_stack ? target_thread->transaction_stack->debug_id : 0, in_reply_to->debug_id); + binder_inner_proc_unlock(target_thread->proc); return_error = BR_FAILED_REPLY; + return_error_param = -EPROTO; + return_error_line = __LINE__; in_reply_to = NULL; target_thread = NULL; goto err_dead_binder; } target_proc = target_thread->proc; + target_proc->tmp_ref++; + binder_inner_proc_unlock(target_thread->proc); } else { if (tr->target.handle) { struct binder_ref *ref; - ref = binder_get_ref(proc, tr->target.handle, true); - if (ref == NULL) { + /* + * There must already be a strong ref + * on this node. If so, do a strong + * increment on the node to ensure it + * stays alive until the transaction is + * done. + */ + binder_proc_lock(proc); + ref = binder_get_ref_olocked(proc, tr->target.handle, + true); + if (ref) { + target_node = binder_get_node_refs_for_txn( + ref->node, &target_proc, + &return_error); + } else { binder_user_error("%d:%d got transaction to invalid handle\n", - proc->pid, thread->pid); + proc->pid, thread->pid); return_error = BR_FAILED_REPLY; - goto err_invalid_target_handle; } - target_node = ref->node; + binder_proc_unlock(proc); } else { - target_node = binder_context_mgr_node; - if (target_node == NULL) { + mutex_lock(&context->context_mgr_node_lock); + target_node = context->binder_context_mgr_node; + if (target_node) + target_node = binder_get_node_refs_for_txn( + target_node, &target_proc, + &return_error); + else return_error = BR_DEAD_REPLY; - goto err_no_context_mgr_node; - } + mutex_unlock(&context->context_mgr_node_lock); } - e->to_node = target_node->debug_id; - target_proc = target_node->proc; - if (target_proc == NULL) { - return_error = BR_DEAD_REPLY; + if (!target_node) { + /* + * return_error is set above + */ + return_error_param = -EINVAL; + return_error_line = __LINE__; goto err_dead_binder; } + e->to_node = target_node->debug_id; if (security_binder_transaction(proc->tsk, target_proc->tsk) < 0) { return_error = BR_FAILED_REPLY; + return_error_param = -EPERM; + return_error_line = __LINE__; goto err_invalid_target_handle; } + binder_inner_proc_lock(proc); if (!(tr->flags & TF_ONE_WAY) && thread->transaction_stack) { struct binder_transaction *tmp; tmp = thread->transaction_stack; if (tmp->to_thread != thread) { + spin_lock(&tmp->lock); binder_user_error("%d:%d got new transaction with bad transaction stack, transaction %d has target %d:%d\n", proc->pid, thread->pid, tmp->debug_id, tmp->to_proc ? tmp->to_proc->pid : 0, tmp->to_thread ? tmp->to_thread->pid : 0); + spin_unlock(&tmp->lock); + binder_inner_proc_unlock(proc); return_error = BR_FAILED_REPLY; + return_error_param = -EPROTO; + return_error_line = __LINE__; goto err_bad_call_stack; } while (tmp) { - if (tmp->from && tmp->from->proc == target_proc) - target_thread = tmp->from; + struct binder_thread *from; + + spin_lock(&tmp->lock); + from = tmp->from; + if (from && from->proc == target_proc) { + atomic_inc(&from->tmp_ref); + target_thread = from; + spin_unlock(&tmp->lock); + break; + } + spin_unlock(&tmp->lock); tmp = tmp->from_parent; } } + binder_inner_proc_unlock(proc); } - if (target_thread) { + if (target_thread) e->to_thread = target_thread->pid; - target_list = &target_thread->todo; - target_wait = &target_thread->wait; - } else { - target_list = &target_proc->todo; - target_wait = &target_proc->wait; - } e->to_proc = target_proc->pid; /* TODO: reuse incoming transaction for reply */ t = kzalloc(sizeof(*t), GFP_KERNEL); if (t == NULL) { return_error = BR_FAILED_REPLY; + return_error_param = -ENOMEM; + return_error_line = __LINE__; goto err_alloc_t_failed; } binder_stats_created(BINDER_STAT_TRANSACTION); + spin_lock_init(&t->lock); tcomplete = kzalloc(sizeof(*tcomplete), GFP_KERNEL); if (tcomplete == NULL) { return_error = BR_FAILED_REPLY; + return_error_param = -ENOMEM; + return_error_line = __LINE__; goto err_alloc_tcomplete_failed; } binder_stats_created(BINDER_STAT_TRANSACTION_COMPLETE); - t->debug_id = ++binder_last_id; - e->debug_id = t->debug_id; + t->debug_id = t_debug_id; if (reply) binder_debug(BINDER_DEBUG_TRANSACTION, - "%d:%d BC_REPLY %d -> %d:%d, data %016llx-%016llx size %lld-%lld\n", + "%d:%d BC_REPLY %d -> %d:%d, data %016llx-%016llx size %lld-%lld-%lld\n", proc->pid, thread->pid, t->debug_id, target_proc->pid, target_thread->pid, (u64)tr->data.ptr.buffer, (u64)tr->data.ptr.offsets, - (u64)tr->data_size, (u64)tr->offsets_size); + (u64)tr->data_size, (u64)tr->offsets_size, + (u64)extra_buffers_size); else binder_debug(BINDER_DEBUG_TRANSACTION, - "%d:%d BC_TRANSACTION %d -> %d - node %d, data %016llx-%016llx size %lld-%lld\n", + "%d:%d BC_TRANSACTION %d -> %d - node %d, data %016llx-%016llx size %lld-%lld-%lld\n", proc->pid, thread->pid, t->debug_id, target_proc->pid, target_node->debug_id, (u64)tr->data.ptr.buffer, (u64)tr->data.ptr.offsets, - (u64)tr->data_size, (u64)tr->offsets_size); + (u64)tr->data_size, (u64)tr->offsets_size, + (u64)extra_buffers_size); if (!reply && !(tr->flags & TF_ONE_WAY)) t->from = thread; @@ -1487,32 +3025,47 @@ static void binder_transaction(struct bi t->to_thread = target_thread; t->code = tr->code; t->flags = tr->flags; - t->priority = task_nice(current); + if (!(t->flags & TF_ONE_WAY) && + binder_supported_policy(current->policy)) { + /* Inherit supported policies for synchronous transactions */ + t->priority.sched_policy = current->policy; + t->priority.prio = current->normal_prio; + } else { + /* Otherwise, fall back to the default priority */ + t->priority = target_proc->default_priority; + } trace_binder_transaction(reply, t, target_node); - t->buffer = binder_alloc_buf(target_proc, tr->data_size, - tr->offsets_size, !reply && (t->flags & TF_ONE_WAY)); - if (t->buffer == NULL) { - return_error = BR_FAILED_REPLY; + t->buffer = binder_alloc_new_buf(&target_proc->alloc, tr->data_size, + tr->offsets_size, extra_buffers_size, + !reply && (t->flags & TF_ONE_WAY)); + if (IS_ERR(t->buffer)) { + /* + * -ESRCH indicates VMA cleared. The target is dying. + */ + return_error_param = PTR_ERR(t->buffer); + return_error = return_error_param == -ESRCH ? + BR_DEAD_REPLY : BR_FAILED_REPLY; + return_error_line = __LINE__; + t->buffer = NULL; goto err_binder_alloc_buf_failed; } - t->buffer->allow_user_free = 0; t->buffer->debug_id = t->debug_id; t->buffer->transaction = t; t->buffer->target_node = target_node; trace_binder_transaction_alloc_buf(t->buffer); - if (target_node) - binder_inc_node(target_node, 1, 0, NULL); - - offp = (binder_size_t *)(t->buffer->data + - ALIGN(tr->data_size, sizeof(void *))); + off_start = (binder_size_t *)(t->buffer->data + + ALIGN(tr->data_size, sizeof(void *))); + offp = off_start; if (copy_from_user(t->buffer->data, (const void __user *)(uintptr_t) tr->data.ptr.buffer, tr->data_size)) { binder_user_error("%d:%d got transaction with invalid data ptr\n", proc->pid, thread->pid); return_error = BR_FAILED_REPLY; + return_error_param = -EFAULT; + return_error_line = __LINE__; goto err_copy_data_failed; } if (copy_from_user(offp, (const void __user *)(uintptr_t) @@ -1520,231 +3073,244 @@ static void binder_transaction(struct bi binder_user_error("%d:%d got transaction with invalid offsets ptr\n", proc->pid, thread->pid); return_error = BR_FAILED_REPLY; + return_error_param = -EFAULT; + return_error_line = __LINE__; goto err_copy_data_failed; } if (!IS_ALIGNED(tr->offsets_size, sizeof(binder_size_t))) { binder_user_error("%d:%d got transaction with invalid offsets size, %lld\n", proc->pid, thread->pid, (u64)tr->offsets_size); return_error = BR_FAILED_REPLY; + return_error_param = -EINVAL; + return_error_line = __LINE__; goto err_bad_offset; } - off_end = (void *)offp + tr->offsets_size; + if (!IS_ALIGNED(extra_buffers_size, sizeof(u64))) { + binder_user_error("%d:%d got transaction with unaligned buffers size, %lld\n", + proc->pid, thread->pid, + (u64)extra_buffers_size); + return_error = BR_FAILED_REPLY; + return_error_param = -EINVAL; + return_error_line = __LINE__; + goto err_bad_offset; + } + off_end = (void *)off_start + tr->offsets_size; + sg_bufp = (u8 *)(PTR_ALIGN(off_end, sizeof(void *))); + sg_buf_end = sg_bufp + extra_buffers_size; off_min = 0; for (; offp < off_end; offp++) { - struct flat_binder_object *fp; + struct binder_object_header *hdr; + size_t object_size = binder_validate_object(t->buffer, *offp); - if (*offp > t->buffer->data_size - sizeof(*fp) || - *offp < off_min || - t->buffer->data_size < sizeof(*fp) || - !IS_ALIGNED(*offp, sizeof(u32))) { - binder_user_error("%d:%d got transaction with invalid offset, %lld (min %lld, max %lld)\n", + if (object_size == 0 || *offp < off_min) { + binder_user_error("%d:%d got transaction with invalid offset (%lld, min %lld max %lld) or object.\n", proc->pid, thread->pid, (u64)*offp, (u64)off_min, - (u64)(t->buffer->data_size - - sizeof(*fp))); + (u64)t->buffer->data_size); return_error = BR_FAILED_REPLY; + return_error_param = -EINVAL; + return_error_line = __LINE__; goto err_bad_offset; } - fp = (struct flat_binder_object *)(t->buffer->data + *offp); - off_min = *offp + sizeof(struct flat_binder_object); - switch (fp->type) { + + hdr = (struct binder_object_header *)(t->buffer->data + *offp); + off_min = *offp + object_size; + switch (hdr->type) { case BINDER_TYPE_BINDER: case BINDER_TYPE_WEAK_BINDER: { - struct binder_ref *ref; - struct binder_node *node = binder_get_node(proc, fp->binder); + struct flat_binder_object *fp; - if (node == NULL) { - node = binder_new_node(proc, fp->binder, fp->cookie); - if (node == NULL) { - return_error = BR_FAILED_REPLY; - goto err_binder_new_node_failed; - } - node->min_priority = fp->flags & FLAT_BINDER_FLAG_PRIORITY_MASK; - node->accept_fds = !!(fp->flags & FLAT_BINDER_FLAG_ACCEPTS_FDS); - } - if (fp->cookie != node->cookie) { - binder_user_error("%d:%d sending u%016llx node %d, cookie mismatch %016llx != %016llx\n", - proc->pid, thread->pid, - (u64)fp->binder, node->debug_id, - (u64)fp->cookie, (u64)node->cookie); - return_error = BR_FAILED_REPLY; - goto err_binder_get_ref_for_node_failed; - } - if (security_binder_transfer_binder(proc->tsk, - target_proc->tsk)) { - return_error = BR_FAILED_REPLY; - goto err_binder_get_ref_for_node_failed; - } - ref = binder_get_ref_for_node(target_proc, node); - if (ref == NULL) { + fp = to_flat_binder_object(hdr); + ret = binder_translate_binder(fp, t, thread); + if (ret < 0) { return_error = BR_FAILED_REPLY; - goto err_binder_get_ref_for_node_failed; + return_error_param = ret; + return_error_line = __LINE__; + goto err_translate_failed; } - if (fp->type == BINDER_TYPE_BINDER) - fp->type = BINDER_TYPE_HANDLE; - else - fp->type = BINDER_TYPE_WEAK_HANDLE; - fp->binder = 0; - fp->handle = ref->desc; - fp->cookie = 0; - binder_inc_ref(ref, fp->type == BINDER_TYPE_HANDLE, - &thread->todo); - - trace_binder_transaction_node_to_ref(t, node, ref); - binder_debug(BINDER_DEBUG_TRANSACTION, - " node %d u%016llx -> ref %d desc %d\n", - node->debug_id, (u64)node->ptr, - ref->debug_id, ref->desc); } break; case BINDER_TYPE_HANDLE: case BINDER_TYPE_WEAK_HANDLE: { - struct binder_ref *ref; - - ref = binder_get_ref(proc, fp->handle, - fp->type == BINDER_TYPE_HANDLE); + struct flat_binder_object *fp; - if (ref == NULL) { - binder_user_error("%d:%d got transaction with invalid handle, %d\n", - proc->pid, - thread->pid, fp->handle); - return_error = BR_FAILED_REPLY; - goto err_binder_get_ref_failed; - } - if (security_binder_transfer_binder(proc->tsk, - target_proc->tsk)) { + fp = to_flat_binder_object(hdr); + ret = binder_translate_handle(fp, t, thread); + if (ret < 0) { return_error = BR_FAILED_REPLY; - goto err_binder_get_ref_failed; - } - if (ref->node->proc == target_proc) { - if (fp->type == BINDER_TYPE_HANDLE) - fp->type = BINDER_TYPE_BINDER; - else - fp->type = BINDER_TYPE_WEAK_BINDER; - fp->binder = ref->node->ptr; - fp->cookie = ref->node->cookie; - binder_inc_node(ref->node, fp->type == BINDER_TYPE_BINDER, 0, NULL); - trace_binder_transaction_ref_to_node(t, ref); - binder_debug(BINDER_DEBUG_TRANSACTION, - " ref %d desc %d -> node %d u%016llx\n", - ref->debug_id, ref->desc, ref->node->debug_id, - (u64)ref->node->ptr); - } else { - struct binder_ref *new_ref; - - new_ref = binder_get_ref_for_node(target_proc, ref->node); - if (new_ref == NULL) { - return_error = BR_FAILED_REPLY; - goto err_binder_get_ref_for_node_failed; - } - fp->binder = 0; - fp->handle = new_ref->desc; - fp->cookie = 0; - binder_inc_ref(new_ref, fp->type == BINDER_TYPE_HANDLE, NULL); - trace_binder_transaction_ref_to_ref(t, ref, - new_ref); - binder_debug(BINDER_DEBUG_TRANSACTION, - " ref %d desc %d -> ref %d desc %d (node %d)\n", - ref->debug_id, ref->desc, new_ref->debug_id, - new_ref->desc, ref->node->debug_id); + return_error_param = ret; + return_error_line = __LINE__; + goto err_translate_failed; } } break; case BINDER_TYPE_FD: { - int target_fd; - struct file *file; + struct binder_fd_object *fp = to_binder_fd_object(hdr); + int target_fd = binder_translate_fd(fp->fd, t, thread, + in_reply_to); - if (reply) { - if (!(in_reply_to->flags & TF_ACCEPT_FDS)) { - binder_user_error("%d:%d got reply with fd, %d, but target does not allow fds\n", - proc->pid, thread->pid, fp->handle); - return_error = BR_FAILED_REPLY; - goto err_fd_not_allowed; - } - } else if (!target_node->accept_fds) { - binder_user_error("%d:%d got transaction with fd, %d, but target does not allow fds\n", - proc->pid, thread->pid, fp->handle); + if (target_fd < 0) { return_error = BR_FAILED_REPLY; - goto err_fd_not_allowed; + return_error_param = target_fd; + return_error_line = __LINE__; + goto err_translate_failed; } - - file = fget(fp->handle); - if (file == NULL) { - binder_user_error("%d:%d got transaction with invalid fd, %d\n", - proc->pid, thread->pid, fp->handle); + fp->pad_binder = 0; + fp->fd = target_fd; + } break; + case BINDER_TYPE_FDA: { + struct binder_fd_array_object *fda = + to_binder_fd_array_object(hdr); + struct binder_buffer_object *parent = + binder_validate_ptr(t->buffer, fda->parent, + off_start, + offp - off_start); + if (!parent) { + binder_user_error("%d:%d got transaction with invalid parent offset or type\n", + proc->pid, thread->pid); return_error = BR_FAILED_REPLY; - goto err_fget_failed; + return_error_param = -EINVAL; + return_error_line = __LINE__; + goto err_bad_parent; } - if (security_binder_transfer_file(proc->tsk, - target_proc->tsk, - file) < 0) { - fput(file); + if (!binder_validate_fixup(t->buffer, off_start, + parent, fda->parent_offset, + last_fixup_obj, + last_fixup_min_off)) { + binder_user_error("%d:%d got transaction with out-of-order buffer fixup\n", + proc->pid, thread->pid); return_error = BR_FAILED_REPLY; - goto err_get_unused_fd_failed; + return_error_param = -EINVAL; + return_error_line = __LINE__; + goto err_bad_parent; } - target_fd = task_get_unused_fd_flags(target_proc, O_CLOEXEC); - if (target_fd < 0) { - fput(file); + ret = binder_translate_fd_array(fda, parent, t, thread, + in_reply_to); + if (ret < 0) { return_error = BR_FAILED_REPLY; - goto err_get_unused_fd_failed; + return_error_param = ret; + return_error_line = __LINE__; + goto err_translate_failed; } - task_fd_install(target_proc, target_fd, file); - trace_binder_transaction_fd(t, fp->handle, target_fd); - binder_debug(BINDER_DEBUG_TRANSACTION, - " fd %d -> %d\n", fp->handle, target_fd); - /* TODO: fput? */ - fp->binder = 0; - fp->handle = target_fd; + last_fixup_obj = parent; + last_fixup_min_off = + fda->parent_offset + sizeof(u32) * fda->num_fds; } break; + case BINDER_TYPE_PTR: { + struct binder_buffer_object *bp = + to_binder_buffer_object(hdr); + size_t buf_left = sg_buf_end - sg_bufp; + + if (bp->length > buf_left) { + binder_user_error("%d:%d got transaction with too large buffer\n", + proc->pid, thread->pid); + return_error = BR_FAILED_REPLY; + return_error_param = -EINVAL; + return_error_line = __LINE__; + goto err_bad_offset; + } + if (copy_from_user(sg_bufp, + (const void __user *)(uintptr_t) + bp->buffer, bp->length)) { + binder_user_error("%d:%d got transaction with invalid offsets ptr\n", + proc->pid, thread->pid); + return_error_param = -EFAULT; + return_error = BR_FAILED_REPLY; + return_error_line = __LINE__; + goto err_copy_data_failed; + } + /* Fixup buffer pointer to target proc address space */ + bp->buffer = (uintptr_t)sg_bufp + + binder_alloc_get_user_buffer_offset( + &target_proc->alloc); + sg_bufp += ALIGN(bp->length, sizeof(u64)); + ret = binder_fixup_parent(t, thread, bp, off_start, + offp - off_start, + last_fixup_obj, + last_fixup_min_off); + if (ret < 0) { + return_error = BR_FAILED_REPLY; + return_error_param = ret; + return_error_line = __LINE__; + goto err_translate_failed; + } + last_fixup_obj = bp; + last_fixup_min_off = 0; + } break; default: binder_user_error("%d:%d got transaction with invalid object type, %x\n", - proc->pid, thread->pid, fp->type); + proc->pid, thread->pid, hdr->type); return_error = BR_FAILED_REPLY; + return_error_param = -EINVAL; + return_error_line = __LINE__; goto err_bad_object_type; } } + tcomplete->type = BINDER_WORK_TRANSACTION_COMPLETE; + binder_enqueue_work(proc, tcomplete, &thread->todo); + t->work.type = BINDER_WORK_TRANSACTION; + if (reply) { + binder_inner_proc_lock(target_proc); + if (target_thread->is_dead) { + binder_inner_proc_unlock(target_proc); + goto err_dead_proc_or_thread; + } BUG_ON(t->buffer->async_transaction != 0); - binder_pop_transaction(target_thread, in_reply_to); + binder_pop_transaction_ilocked(target_thread, in_reply_to); + binder_enqueue_work_ilocked(&t->work, &target_thread->todo); + binder_inner_proc_unlock(target_proc); + wake_up_interruptible_sync(&target_thread->wait); + binder_restore_priority(current, in_reply_to->saved_priority); + binder_free_transaction(in_reply_to); } else if (!(t->flags & TF_ONE_WAY)) { BUG_ON(t->buffer->async_transaction != 0); + binder_inner_proc_lock(proc); t->need_reply = 1; t->from_parent = thread->transaction_stack; thread->transaction_stack = t; + binder_inner_proc_unlock(proc); + if (!binder_proc_transaction(t, target_proc, target_thread)) { + binder_inner_proc_lock(proc); + binder_pop_transaction_ilocked(thread, t); + binder_inner_proc_unlock(proc); + goto err_dead_proc_or_thread; + } } else { BUG_ON(target_node == NULL); BUG_ON(t->buffer->async_transaction != 1); - if (target_node->has_async_transaction) { - target_list = &target_node->async_todo; - target_wait = NULL; - } else - target_node->has_async_transaction = 1; - } - t->work.type = BINDER_WORK_TRANSACTION; - list_add_tail(&t->work.entry, target_list); - tcomplete->type = BINDER_WORK_TRANSACTION_COMPLETE; - list_add_tail(&tcomplete->entry, &thread->todo); - if (target_wait) { - if (reply || !(t->flags & TF_ONE_WAY)) - wake_up_interruptible_sync(target_wait); - else - wake_up_interruptible(target_wait); + if (!binder_proc_transaction(t, target_proc, NULL)) + goto err_dead_proc_or_thread; } + if (target_thread) + binder_thread_dec_tmpref(target_thread); + binder_proc_dec_tmpref(target_proc); + if (target_node) + binder_dec_node_tmpref(target_node); + /* + * write barrier to synchronize with initialization + * of log entry + */ + smp_wmb(); + WRITE_ONCE(e->debug_id_done, t_debug_id); return; -err_get_unused_fd_failed: -err_fget_failed: -err_fd_not_allowed: -err_binder_get_ref_for_node_failed: -err_binder_get_ref_failed: -err_binder_new_node_failed: +err_dead_proc_or_thread: + return_error = BR_DEAD_REPLY; + return_error_line = __LINE__; + binder_dequeue_work(proc, tcomplete); +err_translate_failed: err_bad_object_type: err_bad_offset: +err_bad_parent: err_copy_data_failed: trace_binder_transaction_failed_buffer_release(t->buffer); binder_transaction_buffer_release(target_proc, t->buffer, offp); + if (target_node) + binder_dec_node_tmpref(target_node); + target_node = NULL; t->buffer->transaction = NULL; - binder_free_buf(target_proc, t->buffer); + binder_alloc_free_buf(&target_proc->alloc, t->buffer); err_binder_alloc_buf_failed: kfree(tcomplete); binder_stats_deleted(BINDER_STAT_TRANSACTION_COMPLETE); @@ -1756,25 +3322,52 @@ err_bad_call_stack: err_empty_call_stack: err_dead_binder: err_invalid_target_handle: -err_no_context_mgr_node: + if (target_thread) + binder_thread_dec_tmpref(target_thread); + if (target_proc) + binder_proc_dec_tmpref(target_proc); + if (target_node) { + binder_dec_node(target_node, 1, 0); + binder_dec_node_tmpref(target_node); + } + binder_debug(BINDER_DEBUG_FAILED_TRANSACTION, - "%d:%d transaction failed %d, size %lld-%lld\n", - proc->pid, thread->pid, return_error, - (u64)tr->data_size, (u64)tr->offsets_size); + "%d:%d transaction failed %d/%d, size %lld-%lld line %d\n", + proc->pid, thread->pid, return_error, return_error_param, + (u64)tr->data_size, (u64)tr->offsets_size, + return_error_line); { struct binder_transaction_log_entry *fe; + e->return_error = return_error; + e->return_error_param = return_error_param; + e->return_error_line = return_error_line; fe = binder_transaction_log_add(&binder_transaction_log_failed); *fe = *e; + /* + * write barrier to synchronize with initialization + * of log entry + */ + smp_wmb(); + WRITE_ONCE(e->debug_id_done, t_debug_id); + WRITE_ONCE(fe->debug_id_done, t_debug_id); } - BUG_ON(thread->return_error != BR_OK); + BUG_ON(thread->return_error.cmd != BR_OK); if (in_reply_to) { - thread->return_error = BR_TRANSACTION_COMPLETE; + binder_restore_priority(current, in_reply_to->saved_priority); + thread->return_error.cmd = BR_TRANSACTION_COMPLETE; + binder_enqueue_work(thread->proc, + &thread->return_error.work, + &thread->todo); binder_send_failed_reply(in_reply_to, return_error); - } else - thread->return_error = return_error; + } else { + thread->return_error.cmd = return_error; + binder_enqueue_work(thread->proc, + &thread->return_error.work, + &thread->todo); + } } static int binder_thread_write(struct binder_proc *proc, @@ -1783,19 +3376,22 @@ static int binder_thread_write(struct bi binder_size_t *consumed) { uint32_t cmd; + struct binder_context *context = proc->context; void __user *buffer = (void __user *)(uintptr_t)binder_buffer; void __user *ptr = buffer + *consumed; void __user *end = buffer + size; - while (ptr < end && thread->return_error == BR_OK) { + while (ptr < end && thread->return_error.cmd == BR_OK) { + int ret; + if (get_user(cmd, (uint32_t __user *)ptr)) return -EFAULT; ptr += sizeof(uint32_t); trace_binder_command(cmd); if (_IOC_NR(cmd) < ARRAY_SIZE(binder_stats.bc)) { - binder_stats.bc[_IOC_NR(cmd)]++; - proc->stats.bc[_IOC_NR(cmd)]++; - thread->stats.bc[_IOC_NR(cmd)]++; + atomic_inc(&binder_stats.bc[_IOC_NR(cmd)]); + atomic_inc(&proc->stats.bc[_IOC_NR(cmd)]); + atomic_inc(&thread->stats.bc[_IOC_NR(cmd)]); } switch (cmd) { case BC_INCREFS: @@ -1803,53 +3399,61 @@ static int binder_thread_write(struct bi case BC_RELEASE: case BC_DECREFS: { uint32_t target; - struct binder_ref *ref; const char *debug_string; + bool strong = cmd == BC_ACQUIRE || cmd == BC_RELEASE; + bool increment = cmd == BC_INCREFS || cmd == BC_ACQUIRE; + struct binder_ref_data rdata; if (get_user(target, (uint32_t __user *)ptr)) return -EFAULT; + ptr += sizeof(uint32_t); - if (target == 0 && binder_context_mgr_node && - (cmd == BC_INCREFS || cmd == BC_ACQUIRE)) { - ref = binder_get_ref_for_node(proc, - binder_context_mgr_node); - if (ref->desc != target) { - binder_user_error("%d:%d tried to acquire reference to desc 0, got %d instead\n", - proc->pid, thread->pid, - ref->desc); - } - } else - ref = binder_get_ref(proc, target, - cmd == BC_ACQUIRE || - cmd == BC_RELEASE); - if (ref == NULL) { - binder_user_error("%d:%d refcount change on invalid ref %d\n", - proc->pid, thread->pid, target); - break; + ret = -1; + if (increment && !target) { + struct binder_node *ctx_mgr_node; + mutex_lock(&context->context_mgr_node_lock); + ctx_mgr_node = context->binder_context_mgr_node; + if (ctx_mgr_node) + ret = binder_inc_ref_for_node( + proc, ctx_mgr_node, + strong, NULL, &rdata); + mutex_unlock(&context->context_mgr_node_lock); + } + if (ret) + ret = binder_update_ref_for_handle( + proc, target, increment, strong, + &rdata); + if (!ret && rdata.desc != target) { + binder_user_error("%d:%d tried to acquire reference to desc %d, got %d instead\n", + proc->pid, thread->pid, + target, rdata.desc); } switch (cmd) { case BC_INCREFS: debug_string = "IncRefs"; - binder_inc_ref(ref, 0, NULL); break; case BC_ACQUIRE: debug_string = "Acquire"; - binder_inc_ref(ref, 1, NULL); break; case BC_RELEASE: debug_string = "Release"; - binder_dec_ref(ref, 1); break; case BC_DECREFS: default: debug_string = "DecRefs"; - binder_dec_ref(ref, 0); + break; + } + if (ret) { + binder_user_error("%d:%d %s %d refcount change on invalid ref %d ret %d\n", + proc->pid, thread->pid, debug_string, + strong, target, ret); break; } binder_debug(BINDER_DEBUG_USER_REFS, - "%d:%d %s ref %d desc %d s %d w %d for node %d\n", - proc->pid, thread->pid, debug_string, ref->debug_id, - ref->desc, ref->strong, ref->weak, ref->node->debug_id); + "%d:%d %s ref %d desc %d s %d w %d\n", + proc->pid, thread->pid, debug_string, + rdata.debug_id, rdata.desc, rdata.strong, + rdata.weak); break; } case BC_INCREFS_DONE: @@ -1857,6 +3461,7 @@ static int binder_thread_write(struct bi binder_uintptr_t node_ptr; binder_uintptr_t cookie; struct binder_node *node; + bool free_node; if (get_user(node_ptr, (binder_uintptr_t __user *)ptr)) return -EFAULT; @@ -1881,13 +3486,17 @@ static int binder_thread_write(struct bi "BC_INCREFS_DONE" : "BC_ACQUIRE_DONE", (u64)node_ptr, node->debug_id, (u64)cookie, (u64)node->cookie); + binder_put_node(node); break; } + binder_node_inner_lock(node); if (cmd == BC_ACQUIRE_DONE) { if (node->pending_strong_ref == 0) { binder_user_error("%d:%d BC_ACQUIRE_DONE node %d has no pending acquire request\n", proc->pid, thread->pid, node->debug_id); + binder_node_inner_unlock(node); + binder_put_node(node); break; } node->pending_strong_ref = 0; @@ -1896,16 +3505,23 @@ static int binder_thread_write(struct bi binder_user_error("%d:%d BC_INCREFS_DONE node %d has no pending increfs request\n", proc->pid, thread->pid, node->debug_id); + binder_node_inner_unlock(node); + binder_put_node(node); break; } node->pending_weak_ref = 0; } - binder_dec_node(node, cmd == BC_ACQUIRE_DONE, 0); + free_node = binder_dec_node_nilocked(node, + cmd == BC_ACQUIRE_DONE, 0); + WARN_ON(free_node); binder_debug(BINDER_DEBUG_USER_REFS, - "%d:%d %s node %d ls %d lw %d\n", + "%d:%d %s node %d ls %d lw %d tr %d\n", proc->pid, thread->pid, cmd == BC_INCREFS_DONE ? "BC_INCREFS_DONE" : "BC_ACQUIRE_DONE", - node->debug_id, node->local_strong_refs, node->local_weak_refs); + node->debug_id, node->local_strong_refs, + node->local_weak_refs, node->tmp_refs); + binder_node_inner_unlock(node); + binder_put_node(node); break; } case BC_ATTEMPT_ACQUIRE: @@ -1923,15 +3539,20 @@ static int binder_thread_write(struct bi return -EFAULT; ptr += sizeof(binder_uintptr_t); - buffer = binder_buffer_lookup(proc, data_ptr); - if (buffer == NULL) { - binder_user_error("%d:%d BC_FREE_BUFFER u%016llx no match\n", - proc->pid, thread->pid, (u64)data_ptr); - break; - } - if (!buffer->allow_user_free) { - binder_user_error("%d:%d BC_FREE_BUFFER u%016llx matched unreturned buffer\n", - proc->pid, thread->pid, (u64)data_ptr); + buffer = binder_alloc_prepare_to_free(&proc->alloc, + data_ptr); + if (IS_ERR_OR_NULL(buffer)) { + if (PTR_ERR(buffer) == -EPERM) { + binder_user_error( + "%d:%d BC_FREE_BUFFER u%016llx matched unreturned or currently freeing buffer\n", + proc->pid, thread->pid, + (u64)data_ptr); + } else { + binder_user_error( + "%d:%d BC_FREE_BUFFER u%016llx no match\n", + proc->pid, thread->pid, + (u64)data_ptr); + } break; } binder_debug(BINDER_DEBUG_FREE_BUFFER, @@ -1945,18 +3566,41 @@ static int binder_thread_write(struct bi buffer->transaction = NULL; } if (buffer->async_transaction && buffer->target_node) { - BUG_ON(!buffer->target_node->has_async_transaction); - if (list_empty(&buffer->target_node->async_todo)) - buffer->target_node->has_async_transaction = 0; - else - list_move_tail(buffer->target_node->async_todo.next, &thread->todo); + struct binder_node *buf_node; + struct binder_work *w; + + buf_node = buffer->target_node; + binder_node_inner_lock(buf_node); + BUG_ON(!buf_node->has_async_transaction); + BUG_ON(buf_node->proc != proc); + w = binder_dequeue_work_head_ilocked( + &buf_node->async_todo); + if (!w) { + buf_node->has_async_transaction = 0; + } else { + binder_enqueue_work_ilocked( + w, &proc->todo); + binder_wakeup_proc_ilocked(proc); + } + binder_node_inner_unlock(buf_node); } trace_binder_transaction_buffer_release(buffer); binder_transaction_buffer_release(proc, buffer, NULL); - binder_free_buf(proc, buffer); + binder_alloc_free_buf(&proc->alloc, buffer); break; } + case BC_TRANSACTION_SG: + case BC_REPLY_SG: { + struct binder_transaction_data_sg tr; + + if (copy_from_user(&tr, ptr, sizeof(tr))) + return -EFAULT; + ptr += sizeof(tr); + binder_transaction(proc, thread, &tr.transaction_data, + cmd == BC_REPLY_SG, tr.buffers_size); + break; + } case BC_TRANSACTION: case BC_REPLY: { struct binder_transaction_data tr; @@ -1964,7 +3608,8 @@ static int binder_thread_write(struct bi if (copy_from_user(&tr, ptr, sizeof(tr))) return -EFAULT; ptr += sizeof(tr); - binder_transaction(proc, thread, &tr, cmd == BC_REPLY); + binder_transaction(proc, thread, &tr, + cmd == BC_REPLY, 0); break; } @@ -1972,6 +3617,7 @@ static int binder_thread_write(struct bi binder_debug(BINDER_DEBUG_THREADS, "%d:%d BC_REGISTER_LOOPER\n", proc->pid, thread->pid); + binder_inner_proc_lock(proc); if (thread->looper & BINDER_LOOPER_STATE_ENTERED) { thread->looper |= BINDER_LOOPER_STATE_INVALID; binder_user_error("%d:%d ERROR: BC_REGISTER_LOOPER called after BC_ENTER_LOOPER\n", @@ -1985,6 +3631,7 @@ static int binder_thread_write(struct bi proc->requested_threads_started++; } thread->looper |= BINDER_LOOPER_STATE_REGISTERED; + binder_inner_proc_unlock(proc); break; case BC_ENTER_LOOPER: binder_debug(BINDER_DEBUG_THREADS, @@ -2009,7 +3656,7 @@ static int binder_thread_write(struct bi uint32_t target; binder_uintptr_t cookie; struct binder_ref *ref; - struct binder_ref_death *death; + struct binder_ref_death *death = NULL; if (get_user(target, (uint32_t __user *)ptr)) return -EFAULT; @@ -2017,7 +3664,29 @@ static int binder_thread_write(struct bi if (get_user(cookie, (binder_uintptr_t __user *)ptr)) return -EFAULT; ptr += sizeof(binder_uintptr_t); - ref = binder_get_ref(proc, target, false); + if (cmd == BC_REQUEST_DEATH_NOTIFICATION) { + /* + * Allocate memory for death notification + * before taking lock + */ + death = kzalloc(sizeof(*death), GFP_KERNEL); + if (death == NULL) { + WARN_ON(thread->return_error.cmd != + BR_OK); + thread->return_error.cmd = BR_ERROR; + binder_enqueue_work( + thread->proc, + &thread->return_error.work, + &thread->todo); + binder_debug( + BINDER_DEBUG_FAILED_TRANSACTION, + "%d:%d BC_REQUEST_DEATH_NOTIFICATION failed\n", + proc->pid, thread->pid); + break; + } + } + binder_proc_lock(proc); + ref = binder_get_ref_olocked(proc, target, false); if (ref == NULL) { binder_user_error("%d:%d %s invalid ref %d\n", proc->pid, thread->pid, @@ -2025,6 +3694,8 @@ static int binder_thread_write(struct bi "BC_REQUEST_DEATH_NOTIFICATION" : "BC_CLEAR_DEATH_NOTIFICATION", target); + binder_proc_unlock(proc); + kfree(death); break; } @@ -2034,21 +3705,18 @@ static int binder_thread_write(struct bi cmd == BC_REQUEST_DEATH_NOTIFICATION ? "BC_REQUEST_DEATH_NOTIFICATION" : "BC_CLEAR_DEATH_NOTIFICATION", - (u64)cookie, ref->debug_id, ref->desc, - ref->strong, ref->weak, ref->node->debug_id); + (u64)cookie, ref->data.debug_id, + ref->data.desc, ref->data.strong, + ref->data.weak, ref->node->debug_id); + binder_node_lock(ref->node); if (cmd == BC_REQUEST_DEATH_NOTIFICATION) { if (ref->death) { binder_user_error("%d:%d BC_REQUEST_DEATH_NOTIFICATION death notification already set\n", proc->pid, thread->pid); - break; - } - death = kzalloc(sizeof(*death), GFP_KERNEL); - if (death == NULL) { - thread->return_error = BR_ERROR; - binder_debug(BINDER_DEBUG_FAILED_TRANSACTION, - "%d:%d BC_REQUEST_DEATH_NOTIFICATION failed\n", - proc->pid, thread->pid); + binder_node_unlock(ref->node); + binder_proc_unlock(proc); + kfree(death); break; } binder_stats_created(BINDER_STAT_DEATH); @@ -2057,17 +3725,19 @@ static int binder_thread_write(struct bi ref->death = death; if (ref->node->proc == NULL) { ref->death->work.type = BINDER_WORK_DEAD_BINDER; - if (thread->looper & (BINDER_LOOPER_STATE_REGISTERED | BINDER_LOOPER_STATE_ENTERED)) { - list_add_tail(&ref->death->work.entry, &thread->todo); - } else { - list_add_tail(&ref->death->work.entry, &proc->todo); - wake_up_interruptible(&proc->wait); - } + + binder_inner_proc_lock(proc); + binder_enqueue_work_ilocked( + &ref->death->work, &proc->todo); + binder_wakeup_proc_ilocked(proc); + binder_inner_proc_unlock(proc); } } else { if (ref->death == NULL) { binder_user_error("%d:%d BC_CLEAR_DEATH_NOTIFICATION death notification not active\n", proc->pid, thread->pid); + binder_node_unlock(ref->node); + binder_proc_unlock(proc); break; } death = ref->death; @@ -2076,22 +3746,35 @@ static int binder_thread_write(struct bi proc->pid, thread->pid, (u64)death->cookie, (u64)cookie); + binder_node_unlock(ref->node); + binder_proc_unlock(proc); break; } ref->death = NULL; + binder_inner_proc_lock(proc); if (list_empty(&death->work.entry)) { death->work.type = BINDER_WORK_CLEAR_DEATH_NOTIFICATION; - if (thread->looper & (BINDER_LOOPER_STATE_REGISTERED | BINDER_LOOPER_STATE_ENTERED)) { - list_add_tail(&death->work.entry, &thread->todo); - } else { - list_add_tail(&death->work.entry, &proc->todo); - wake_up_interruptible(&proc->wait); + if (thread->looper & + (BINDER_LOOPER_STATE_REGISTERED | + BINDER_LOOPER_STATE_ENTERED)) + binder_enqueue_work_ilocked( + &death->work, + &thread->todo); + else { + binder_enqueue_work_ilocked( + &death->work, + &proc->todo); + binder_wakeup_proc_ilocked( + proc); } } else { BUG_ON(death->work.type != BINDER_WORK_DEAD_BINDER); death->work.type = BINDER_WORK_DEAD_BINDER_AND_CLEAR; } + binder_inner_proc_unlock(proc); } + binder_node_unlock(ref->node); + binder_proc_unlock(proc); } break; case BC_DEAD_BINDER_DONE: { struct binder_work *w; @@ -2102,8 +3785,13 @@ static int binder_thread_write(struct bi return -EFAULT; ptr += sizeof(cookie); - list_for_each_entry(w, &proc->delivered_death, entry) { - struct binder_ref_death *tmp_death = container_of(w, struct binder_ref_death, work); + binder_inner_proc_lock(proc); + list_for_each_entry(w, &proc->delivered_death, + entry) { + struct binder_ref_death *tmp_death = + container_of(w, + struct binder_ref_death, + work); if (tmp_death->cookie == cookie) { death = tmp_death; @@ -2117,19 +3805,25 @@ static int binder_thread_write(struct bi if (death == NULL) { binder_user_error("%d:%d BC_DEAD_BINDER_DONE %016llx not found\n", proc->pid, thread->pid, (u64)cookie); + binder_inner_proc_unlock(proc); break; } - - list_del_init(&death->work.entry); + binder_dequeue_work_ilocked(&death->work); if (death->work.type == BINDER_WORK_DEAD_BINDER_AND_CLEAR) { death->work.type = BINDER_WORK_CLEAR_DEATH_NOTIFICATION; - if (thread->looper & (BINDER_LOOPER_STATE_REGISTERED | BINDER_LOOPER_STATE_ENTERED)) { - list_add_tail(&death->work.entry, &thread->todo); - } else { - list_add_tail(&death->work.entry, &proc->todo); - wake_up_interruptible(&proc->wait); + if (thread->looper & + (BINDER_LOOPER_STATE_REGISTERED | + BINDER_LOOPER_STATE_ENTERED)) + binder_enqueue_work_ilocked( + &death->work, &thread->todo); + else { + binder_enqueue_work_ilocked( + &death->work, + &proc->todo); + binder_wakeup_proc_ilocked(proc); } } + binder_inner_proc_unlock(proc); } break; default: @@ -2147,23 +3841,73 @@ static void binder_stat_br(struct binder { trace_binder_return(cmd); if (_IOC_NR(cmd) < ARRAY_SIZE(binder_stats.br)) { - binder_stats.br[_IOC_NR(cmd)]++; - proc->stats.br[_IOC_NR(cmd)]++; - thread->stats.br[_IOC_NR(cmd)]++; + atomic_inc(&binder_stats.br[_IOC_NR(cmd)]); + atomic_inc(&proc->stats.br[_IOC_NR(cmd)]); + atomic_inc(&thread->stats.br[_IOC_NR(cmd)]); } } -static int binder_has_proc_work(struct binder_proc *proc, - struct binder_thread *thread) +static int binder_put_node_cmd(struct binder_proc *proc, + struct binder_thread *thread, + void __user **ptrp, + binder_uintptr_t node_ptr, + binder_uintptr_t node_cookie, + int node_debug_id, + uint32_t cmd, const char *cmd_name) { - return !list_empty(&proc->todo) || - (thread->looper & BINDER_LOOPER_STATE_NEED_RETURN); + void __user *ptr = *ptrp; + + if (put_user(cmd, (uint32_t __user *)ptr)) + return -EFAULT; + ptr += sizeof(uint32_t); + + if (put_user(node_ptr, (binder_uintptr_t __user *)ptr)) + return -EFAULT; + ptr += sizeof(binder_uintptr_t); + + if (put_user(node_cookie, (binder_uintptr_t __user *)ptr)) + return -EFAULT; + ptr += sizeof(binder_uintptr_t); + + binder_stat_br(proc, thread, cmd); + binder_debug(BINDER_DEBUG_USER_REFS, "%d:%d %s %d u%016llx c%016llx\n", + proc->pid, thread->pid, cmd_name, node_debug_id, + (u64)node_ptr, (u64)node_cookie); + + *ptrp = ptr; + return 0; } -static int binder_has_thread_work(struct binder_thread *thread) +static int binder_wait_for_work(struct binder_thread *thread, + bool do_proc_work) { - return !list_empty(&thread->todo) || thread->return_error != BR_OK || - (thread->looper & BINDER_LOOPER_STATE_NEED_RETURN); + DEFINE_WAIT(wait); + struct binder_proc *proc = thread->proc; + int ret = 0; + + freezer_do_not_count(); + binder_inner_proc_lock(proc); + for (;;) { + prepare_to_wait(&thread->wait, &wait, TASK_INTERRUPTIBLE); + if (binder_has_work_ilocked(thread, do_proc_work)) + break; + if (do_proc_work) + list_add(&thread->waiting_thread_node, + &proc->waiting_threads); + binder_inner_proc_unlock(proc); + schedule(); + binder_inner_proc_lock(proc); + list_del_init(&thread->waiting_thread_node); + if (signal_pending(current)) { + ret = -ERESTARTSYS; + break; + } + } + finish_wait(&thread->wait, &wait); + binder_inner_proc_unlock(proc); + freezer_count(); + + return ret; } static int binder_thread_read(struct binder_proc *proc, @@ -2185,37 +3929,15 @@ static int binder_thread_read(struct bin } retry: - wait_for_proc_work = thread->transaction_stack == NULL && - list_empty(&thread->todo); - - if (thread->return_error != BR_OK && ptr < end) { - if (thread->return_error2 != BR_OK) { - if (put_user(thread->return_error2, (uint32_t __user *)ptr)) - return -EFAULT; - ptr += sizeof(uint32_t); - binder_stat_br(proc, thread, thread->return_error2); - if (ptr == end) - goto done; - thread->return_error2 = BR_OK; - } - if (put_user(thread->return_error, (uint32_t __user *)ptr)) - return -EFAULT; - ptr += sizeof(uint32_t); - binder_stat_br(proc, thread, thread->return_error); - thread->return_error = BR_OK; - goto done; - } - + binder_inner_proc_lock(proc); + wait_for_proc_work = binder_available_for_proc_work_ilocked(thread); + binder_inner_proc_unlock(proc); thread->looper |= BINDER_LOOPER_STATE_WAITING; - if (wait_for_proc_work) - proc->ready_threads++; - - binder_unlock(__func__); trace_binder_wait_for_work(wait_for_proc_work, !!thread->transaction_stack, - !list_empty(&thread->todo)); + !binder_worklist_empty(proc, &thread->todo)); if (wait_for_proc_work) { if (!(thread->looper & (BINDER_LOOPER_STATE_REGISTERED | BINDER_LOOPER_STATE_ENTERED))) { @@ -2224,24 +3946,16 @@ retry: wait_event_interruptible(binder_user_error_wait, binder_stop_on_user_error < 2); } - binder_set_nice(proc->default_priority); - if (non_block) { - if (!binder_has_proc_work(proc, thread)) - ret = -EAGAIN; - } else - ret = wait_event_freezable_exclusive(proc->wait, binder_has_proc_work(proc, thread)); - } else { - if (non_block) { - if (!binder_has_thread_work(thread)) - ret = -EAGAIN; - } else - ret = wait_event_freezable(thread->wait, binder_has_thread_work(thread)); + binder_restore_priority(current, proc->default_priority); } - binder_lock(__func__); + if (non_block) { + if (!binder_has_work(thread, wait_for_proc_work)) + ret = -EAGAIN; + } else { + ret = binder_wait_for_work(thread, wait_for_proc_work); + } - if (wait_for_proc_work) - proc->ready_threads--; thread->looper &= ~BINDER_LOOPER_STATE_WAITING; if (ret) @@ -2250,31 +3964,52 @@ retry: while (1) { uint32_t cmd; struct binder_transaction_data tr; - struct binder_work *w; + struct binder_work *w = NULL; + struct list_head *list = NULL; struct binder_transaction *t = NULL; + struct binder_thread *t_from; + + binder_inner_proc_lock(proc); + if (!binder_worklist_empty_ilocked(&thread->todo)) + list = &thread->todo; + else if (!binder_worklist_empty_ilocked(&proc->todo) && + wait_for_proc_work) + list = &proc->todo; + else { + binder_inner_proc_unlock(proc); - if (!list_empty(&thread->todo)) { - w = list_first_entry(&thread->todo, struct binder_work, - entry); - } else if (!list_empty(&proc->todo) && wait_for_proc_work) { - w = list_first_entry(&proc->todo, struct binder_work, - entry); - } else { /* no data added */ - if (ptr - buffer == 4 && - !(thread->looper & BINDER_LOOPER_STATE_NEED_RETURN)) + if (ptr - buffer == 4 && !thread->looper_need_return) goto retry; break; } - if (end - ptr < sizeof(tr) + 4) + if (end - ptr < sizeof(tr) + 4) { + binder_inner_proc_unlock(proc); break; + } + w = binder_dequeue_work_head_ilocked(list); switch (w->type) { case BINDER_WORK_TRANSACTION: { + binder_inner_proc_unlock(proc); t = container_of(w, struct binder_transaction, work); } break; + case BINDER_WORK_RETURN_ERROR: { + struct binder_error *e = container_of( + w, struct binder_error, work); + + WARN_ON(e->cmd == BR_OK); + binder_inner_proc_unlock(proc); + if (put_user(e->cmd, (uint32_t __user *)ptr)) + return -EFAULT; + e->cmd = BR_OK; + ptr += sizeof(uint32_t); + + binder_stat_br(proc, thread, cmd); + } break; case BINDER_WORK_TRANSACTION_COMPLETE: { + binder_inner_proc_unlock(proc); cmd = BR_TRANSACTION_COMPLETE; if (put_user(cmd, (uint32_t __user *)ptr)) return -EFAULT; @@ -2284,113 +4019,134 @@ retry: binder_debug(BINDER_DEBUG_TRANSACTION_COMPLETE, "%d:%d BR_TRANSACTION_COMPLETE\n", proc->pid, thread->pid); - - list_del(&w->entry); kfree(w); binder_stats_deleted(BINDER_STAT_TRANSACTION_COMPLETE); } break; case BINDER_WORK_NODE: { struct binder_node *node = container_of(w, struct binder_node, work); - uint32_t cmd = BR_NOOP; - const char *cmd_name; - int strong = node->internal_strong_refs || node->local_strong_refs; - int weak = !hlist_empty(&node->refs) || node->local_weak_refs || strong; + int strong, weak; + binder_uintptr_t node_ptr = node->ptr; + binder_uintptr_t node_cookie = node->cookie; + int node_debug_id = node->debug_id; + int has_weak_ref; + int has_strong_ref; + void __user *orig_ptr = ptr; - if (weak && !node->has_weak_ref) { - cmd = BR_INCREFS; - cmd_name = "BR_INCREFS"; + BUG_ON(proc != node->proc); + strong = node->internal_strong_refs || + node->local_strong_refs; + weak = !hlist_empty(&node->refs) || + node->local_weak_refs || + node->tmp_refs || strong; + has_strong_ref = node->has_strong_ref; + has_weak_ref = node->has_weak_ref; + + if (weak && !has_weak_ref) { node->has_weak_ref = 1; node->pending_weak_ref = 1; node->local_weak_refs++; - } else if (strong && !node->has_strong_ref) { - cmd = BR_ACQUIRE; - cmd_name = "BR_ACQUIRE"; + } + if (strong && !has_strong_ref) { node->has_strong_ref = 1; node->pending_strong_ref = 1; node->local_strong_refs++; - } else if (!strong && node->has_strong_ref) { - cmd = BR_RELEASE; - cmd_name = "BR_RELEASE"; + } + if (!strong && has_strong_ref) node->has_strong_ref = 0; - } else if (!weak && node->has_weak_ref) { - cmd = BR_DECREFS; - cmd_name = "BR_DECREFS"; + if (!weak && has_weak_ref) node->has_weak_ref = 0; - } - if (cmd != BR_NOOP) { - if (put_user(cmd, (uint32_t __user *)ptr)) - return -EFAULT; - ptr += sizeof(uint32_t); - if (put_user(node->ptr, - (binder_uintptr_t __user *)ptr)) - return -EFAULT; - ptr += sizeof(binder_uintptr_t); - if (put_user(node->cookie, - (binder_uintptr_t __user *)ptr)) - return -EFAULT; - ptr += sizeof(binder_uintptr_t); + if (!weak && !strong) { + binder_debug(BINDER_DEBUG_INTERNAL_REFS, + "%d:%d node %d u%016llx c%016llx deleted\n", + proc->pid, thread->pid, + node_debug_id, + (u64)node_ptr, + (u64)node_cookie); + rb_erase(&node->rb_node, &proc->nodes); + binder_inner_proc_unlock(proc); + binder_node_lock(node); + /* + * Acquire the node lock before freeing the + * node to serialize with other threads that + * may have been holding the node lock while + * decrementing this node (avoids race where + * this thread frees while the other thread + * is unlocking the node after the final + * decrement) + */ + binder_node_unlock(node); + binder_free_node(node); + } else + binder_inner_proc_unlock(proc); - binder_stat_br(proc, thread, cmd); - binder_debug(BINDER_DEBUG_USER_REFS, - "%d:%d %s %d u%016llx c%016llx\n", - proc->pid, thread->pid, cmd_name, - node->debug_id, - (u64)node->ptr, (u64)node->cookie); - } else { - list_del_init(&w->entry); - if (!weak && !strong) { - binder_debug(BINDER_DEBUG_INTERNAL_REFS, - "%d:%d node %d u%016llx c%016llx deleted\n", - proc->pid, thread->pid, - node->debug_id, - (u64)node->ptr, - (u64)node->cookie); - rb_erase(&node->rb_node, &proc->nodes); - kfree(node); - binder_stats_deleted(BINDER_STAT_NODE); - } else { - binder_debug(BINDER_DEBUG_INTERNAL_REFS, - "%d:%d node %d u%016llx c%016llx state unchanged\n", - proc->pid, thread->pid, - node->debug_id, - (u64)node->ptr, - (u64)node->cookie); - } - } + if (weak && !has_weak_ref) + ret = binder_put_node_cmd( + proc, thread, &ptr, node_ptr, + node_cookie, node_debug_id, + BR_INCREFS, "BR_INCREFS"); + if (!ret && strong && !has_strong_ref) + ret = binder_put_node_cmd( + proc, thread, &ptr, node_ptr, + node_cookie, node_debug_id, + BR_ACQUIRE, "BR_ACQUIRE"); + if (!ret && !strong && has_strong_ref) + ret = binder_put_node_cmd( + proc, thread, &ptr, node_ptr, + node_cookie, node_debug_id, + BR_RELEASE, "BR_RELEASE"); + if (!ret && !weak && has_weak_ref) + ret = binder_put_node_cmd( + proc, thread, &ptr, node_ptr, + node_cookie, node_debug_id, + BR_DECREFS, "BR_DECREFS"); + if (orig_ptr == ptr) + binder_debug(BINDER_DEBUG_INTERNAL_REFS, + "%d:%d node %d u%016llx c%016llx state unchanged\n", + proc->pid, thread->pid, + node_debug_id, + (u64)node_ptr, + (u64)node_cookie); + if (ret) + return ret; } break; case BINDER_WORK_DEAD_BINDER: case BINDER_WORK_DEAD_BINDER_AND_CLEAR: case BINDER_WORK_CLEAR_DEATH_NOTIFICATION: { struct binder_ref_death *death; uint32_t cmd; + binder_uintptr_t cookie; death = container_of(w, struct binder_ref_death, work); if (w->type == BINDER_WORK_CLEAR_DEATH_NOTIFICATION) cmd = BR_CLEAR_DEATH_NOTIFICATION_DONE; else cmd = BR_DEAD_BINDER; - if (put_user(cmd, (uint32_t __user *)ptr)) - return -EFAULT; - ptr += sizeof(uint32_t); - if (put_user(death->cookie, - (binder_uintptr_t __user *)ptr)) - return -EFAULT; - ptr += sizeof(binder_uintptr_t); - binder_stat_br(proc, thread, cmd); + cookie = death->cookie; + binder_debug(BINDER_DEBUG_DEATH_NOTIFICATION, "%d:%d %s %016llx\n", proc->pid, thread->pid, cmd == BR_DEAD_BINDER ? "BR_DEAD_BINDER" : "BR_CLEAR_DEATH_NOTIFICATION_DONE", - (u64)death->cookie); - + (u64)cookie); if (w->type == BINDER_WORK_CLEAR_DEATH_NOTIFICATION) { - list_del(&w->entry); + binder_inner_proc_unlock(proc); kfree(death); binder_stats_deleted(BINDER_STAT_DEATH); - } else - list_move(&w->entry, &proc->delivered_death); + } else { + binder_enqueue_work_ilocked( + w, &proc->delivered_death); + binder_inner_proc_unlock(proc); + } + if (put_user(cmd, (uint32_t __user *)ptr)) + return -EFAULT; + ptr += sizeof(uint32_t); + if (put_user(cookie, + (binder_uintptr_t __user *)ptr)) + return -EFAULT; + ptr += sizeof(binder_uintptr_t); + binder_stat_br(proc, thread, cmd); if (cmd == BR_DEAD_BINDER) goto done; /* DEAD_BINDER notifications can cause transactions */ } break; @@ -2402,16 +4158,14 @@ retry: BUG_ON(t->buffer == NULL); if (t->buffer->target_node) { struct binder_node *target_node = t->buffer->target_node; + struct binder_priority node_prio; tr.target.ptr = target_node->ptr; tr.cookie = target_node->cookie; - t->saved_priority = task_nice(current); - if (t->priority < target_node->min_priority && - !(t->flags & TF_ONE_WAY)) - binder_set_nice(t->priority); - else if (!(t->flags & TF_ONE_WAY) || - t->saved_priority > target_node->min_priority) - binder_set_nice(target_node->min_priority); + node_prio.sched_policy = target_node->sched_policy; + node_prio.prio = target_node->min_priority; + binder_transaction_priority(current, t, node_prio, + target_node->inherit_rt); cmd = BR_TRANSACTION; } else { tr.target.ptr = 0; @@ -2422,8 +4176,9 @@ retry: tr.flags = t->flags; tr.sender_euid = from_kuid(current_user_ns(), t->sender_euid); - if (t->from) { - struct task_struct *sender = t->from->proc->tsk; + t_from = binder_get_txn_from(t); + if (t_from) { + struct task_struct *sender = t_from->proc->tsk; tr.sender_pid = task_tgid_nr_ns(sender, task_active_pid_ns(current)); @@ -2433,18 +4188,24 @@ retry: tr.data_size = t->buffer->data_size; tr.offsets_size = t->buffer->offsets_size; - tr.data.ptr.buffer = (binder_uintptr_t)( - (uintptr_t)t->buffer->data + - proc->user_buffer_offset); + tr.data.ptr.buffer = (binder_uintptr_t) + ((uintptr_t)t->buffer->data + + binder_alloc_get_user_buffer_offset(&proc->alloc)); tr.data.ptr.offsets = tr.data.ptr.buffer + ALIGN(t->buffer->data_size, sizeof(void *)); - if (put_user(cmd, (uint32_t __user *)ptr)) + if (put_user(cmd, (uint32_t __user *)ptr)) { + if (t_from) + binder_thread_dec_tmpref(t_from); return -EFAULT; + } ptr += sizeof(uint32_t); - if (copy_to_user(ptr, &tr, sizeof(tr))) + if (copy_to_user(ptr, &tr, sizeof(tr))) { + if (t_from) + binder_thread_dec_tmpref(t_from); return -EFAULT; + } ptr += sizeof(tr); trace_binder_transaction_received(t); @@ -2454,21 +4215,22 @@ retry: proc->pid, thread->pid, (cmd == BR_TRANSACTION) ? "BR_TRANSACTION" : "BR_REPLY", - t->debug_id, t->from ? t->from->proc->pid : 0, - t->from ? t->from->pid : 0, cmd, + t->debug_id, t_from ? t_from->proc->pid : 0, + t_from ? t_from->pid : 0, cmd, t->buffer->data_size, t->buffer->offsets_size, (u64)tr.data.ptr.buffer, (u64)tr.data.ptr.offsets); - list_del(&t->work.entry); + if (t_from) + binder_thread_dec_tmpref(t_from); t->buffer->allow_user_free = 1; if (cmd == BR_TRANSACTION && !(t->flags & TF_ONE_WAY)) { + binder_inner_proc_lock(thread->proc); t->to_parent = thread->transaction_stack; t->to_thread = thread; thread->transaction_stack = t; + binder_inner_proc_unlock(thread->proc); } else { - t->buffer->transaction = NULL; - kfree(t); - binder_stats_deleted(BINDER_STAT_TRANSACTION); + binder_free_transaction(t); } break; } @@ -2476,29 +4238,36 @@ retry: done: *consumed = ptr - buffer; - if (proc->requested_threads + proc->ready_threads == 0 && + binder_inner_proc_lock(proc); + if (proc->requested_threads == 0 && + list_empty(&thread->proc->waiting_threads) && proc->requested_threads_started < proc->max_threads && (thread->looper & (BINDER_LOOPER_STATE_REGISTERED | BINDER_LOOPER_STATE_ENTERED)) /* the user-space code fails to */ /*spawn a new thread if we leave this out */) { proc->requested_threads++; + binder_inner_proc_unlock(proc); binder_debug(BINDER_DEBUG_THREADS, "%d:%d BR_SPAWN_LOOPER\n", proc->pid, thread->pid); if (put_user(BR_SPAWN_LOOPER, (uint32_t __user *)buffer)) return -EFAULT; binder_stat_br(proc, thread, BR_SPAWN_LOOPER); - } + } else + binder_inner_proc_unlock(proc); return 0; } -static void binder_release_work(struct list_head *list) +static void binder_release_work(struct binder_proc *proc, + struct list_head *list) { struct binder_work *w; - while (!list_empty(list)) { - w = list_first_entry(list, struct binder_work, entry); - list_del_init(&w->entry); + while (1) { + w = binder_dequeue_work_head(proc, list); + if (!w) + return; + switch (w->type) { case BINDER_WORK_TRANSACTION: { struct binder_transaction *t; @@ -2511,11 +4280,17 @@ static void binder_release_work(struct l binder_debug(BINDER_DEBUG_DEAD_TRANSACTION, "undelivered transaction %d\n", t->debug_id); - t->buffer->transaction = NULL; - kfree(t); - binder_stats_deleted(BINDER_STAT_TRANSACTION); + binder_free_transaction(t); } } break; + case BINDER_WORK_RETURN_ERROR: { + struct binder_error *e = container_of( + w, struct binder_error, work); + + binder_debug(BINDER_DEBUG_DEAD_TRANSACTION, + "undelivered TRANSACTION_ERROR: %u\n", + e->cmd); + } break; case BINDER_WORK_TRANSACTION_COMPLETE: { binder_debug(BINDER_DEBUG_DEAD_TRANSACTION, "undelivered TRANSACTION_COMPLETE\n"); @@ -2542,7 +4317,8 @@ static void binder_release_work(struct l } -static struct binder_thread *binder_get_thread(struct binder_proc *proc) +static struct binder_thread *binder_get_thread_ilocked( + struct binder_proc *proc, struct binder_thread *new_thread) { struct binder_thread *thread = NULL; struct rb_node *parent = NULL; @@ -2557,38 +4333,102 @@ static struct binder_thread *binder_get_ else if (current->pid > thread->pid) p = &(*p)->rb_right; else - break; + return thread; } - if (*p == NULL) { - thread = kzalloc(sizeof(*thread), GFP_KERNEL); - if (thread == NULL) + if (!new_thread) + return NULL; + thread = new_thread; + binder_stats_created(BINDER_STAT_THREAD); + thread->proc = proc; + thread->pid = current->pid; + get_task_struct(current); + thread->task = current; + atomic_set(&thread->tmp_ref, 0); + init_waitqueue_head(&thread->wait); + INIT_LIST_HEAD(&thread->todo); + rb_link_node(&thread->rb_node, parent, p); + rb_insert_color(&thread->rb_node, &proc->threads); + thread->looper_need_return = true; + thread->return_error.work.type = BINDER_WORK_RETURN_ERROR; + thread->return_error.cmd = BR_OK; + thread->reply_error.work.type = BINDER_WORK_RETURN_ERROR; + thread->reply_error.cmd = BR_OK; + INIT_LIST_HEAD(&new_thread->waiting_thread_node); + return thread; +} + +static struct binder_thread *binder_get_thread(struct binder_proc *proc) +{ + struct binder_thread *thread; + struct binder_thread *new_thread; + + binder_inner_proc_lock(proc); + thread = binder_get_thread_ilocked(proc, NULL); + binder_inner_proc_unlock(proc); + if (!thread) { + new_thread = kzalloc(sizeof(*thread), GFP_KERNEL); + if (new_thread == NULL) return NULL; - binder_stats_created(BINDER_STAT_THREAD); - thread->proc = proc; - thread->pid = current->pid; - init_waitqueue_head(&thread->wait); - INIT_LIST_HEAD(&thread->todo); - rb_link_node(&thread->rb_node, parent, p); - rb_insert_color(&thread->rb_node, &proc->threads); - thread->looper |= BINDER_LOOPER_STATE_NEED_RETURN; - thread->return_error = BR_OK; - thread->return_error2 = BR_OK; + binder_inner_proc_lock(proc); + thread = binder_get_thread_ilocked(proc, new_thread); + binder_inner_proc_unlock(proc); + if (thread != new_thread) + kfree(new_thread); } return thread; } -static int binder_free_thread(struct binder_proc *proc, - struct binder_thread *thread) +static void binder_free_proc(struct binder_proc *proc) +{ + BUG_ON(!list_empty(&proc->todo)); + BUG_ON(!list_empty(&proc->delivered_death)); + binder_alloc_deferred_release(&proc->alloc); + put_task_struct(proc->tsk); + binder_stats_deleted(BINDER_STAT_PROC); + kfree(proc); +} + +static void binder_free_thread(struct binder_thread *thread) +{ + BUG_ON(!list_empty(&thread->todo)); + binder_stats_deleted(BINDER_STAT_THREAD); + binder_proc_dec_tmpref(thread->proc); + put_task_struct(thread->task); + kfree(thread); +} + +static int binder_thread_release(struct binder_proc *proc, + struct binder_thread *thread) { struct binder_transaction *t; struct binder_transaction *send_reply = NULL; int active_transactions = 0; + struct binder_transaction *last_t = NULL; + binder_inner_proc_lock(thread->proc); + /* + * take a ref on the proc so it survives + * after we remove this thread from proc->threads. + * The corresponding dec is when we actually + * free the thread in binder_free_thread() + */ + proc->tmp_ref++; + /* + * take a ref on this thread to ensure it + * survives while we are releasing it + */ + atomic_inc(&thread->tmp_ref); rb_erase(&thread->rb_node, &proc->threads); t = thread->transaction_stack; - if (t && t->to_thread == thread) - send_reply = t; + if (t) { + spin_lock(&t->lock); + if (t->to_thread == thread) + send_reply = t; + } + thread->is_dead = true; + while (t) { + last_t = t; active_transactions++; binder_debug(BINDER_DEBUG_DEAD_TRANSACTION, "release %d:%d transaction %d %s, still active\n", @@ -2609,12 +4449,16 @@ static int binder_free_thread(struct bin t = t->from_parent; } else BUG(); + spin_unlock(&last_t->lock); + if (t) + spin_lock(&t->lock); } + binder_inner_proc_unlock(thread->proc); + if (send_reply) binder_send_failed_reply(send_reply, BR_DEAD_REPLY); - binder_release_work(&thread->todo); - kfree(thread); - binder_stats_deleted(BINDER_STAT_THREAD); + binder_release_work(proc, &thread->todo); + binder_thread_dec_tmpref(thread); return active_transactions; } @@ -2623,34 +4467,23 @@ static unsigned int binder_poll(struct f { struct binder_proc *proc = filp->private_data; struct binder_thread *thread = NULL; - int wait_for_proc_work; - - binder_lock(__func__); + bool wait_for_proc_work; thread = binder_get_thread(proc); - if (!thread) { - binder_unlock(__func__); + if (!thread) return POLLERR; - } - wait_for_proc_work = thread->transaction_stack == NULL && - list_empty(&thread->todo) && thread->return_error == BR_OK; + binder_inner_proc_lock(thread->proc); + thread->looper |= BINDER_LOOPER_STATE_POLL; + wait_for_proc_work = binder_available_for_proc_work_ilocked(thread); - binder_unlock(__func__); + binder_inner_proc_unlock(thread->proc); + + poll_wait(filp, &thread->wait, wait); + + if (binder_has_work(thread, wait_for_proc_work)) + return POLLIN; - if (wait_for_proc_work) { - if (binder_has_proc_work(proc, thread)) - return POLLIN; - poll_wait(filp, &proc->wait, wait); - if (binder_has_proc_work(proc, thread)) - return POLLIN; - } else { - if (binder_has_thread_work(thread)) - return POLLIN; - poll_wait(filp, &thread->wait, wait); - if (binder_has_thread_work(thread)) - return POLLIN; - } return 0; } @@ -2697,8 +4530,10 @@ static int binder_ioctl_write_read(struc &bwr.read_consumed, filp->f_flags & O_NONBLOCK); trace_binder_read_done(ret); - if (!list_empty(&proc->todo)) - wake_up_interruptible(&proc->wait); + binder_inner_proc_lock(proc); + if (!binder_worklist_empty_ilocked(&proc->todo)) + binder_wakeup_proc_ilocked(proc); + binder_inner_proc_unlock(proc); if (ret < 0) { if (copy_to_user(ubuf, &bwr, sizeof(bwr))) ret = -EFAULT; @@ -2722,9 +4557,12 @@ static int binder_ioctl_set_ctx_mgr(stru { int ret = 0; struct binder_proc *proc = filp->private_data; + struct binder_context *context = proc->context; + struct binder_node *new_node; kuid_t curr_euid = current_euid(); - if (binder_context_mgr_node != NULL) { + mutex_lock(&context->context_mgr_node_lock); + if (context->binder_context_mgr_node) { pr_err("BINDER_SET_CONTEXT_MGR already set\n"); ret = -EBUSY; goto out; @@ -2732,31 +4570,60 @@ static int binder_ioctl_set_ctx_mgr(stru ret = security_binder_set_context_mgr(proc->tsk); if (ret < 0) goto out; - if (uid_valid(binder_context_mgr_uid)) { - if (!uid_eq(binder_context_mgr_uid, curr_euid)) { + if (uid_valid(context->binder_context_mgr_uid)) { + if (!uid_eq(context->binder_context_mgr_uid, curr_euid)) { pr_err("BINDER_SET_CONTEXT_MGR bad uid %d != %d\n", from_kuid(&init_user_ns, curr_euid), from_kuid(&init_user_ns, - binder_context_mgr_uid)); + context->binder_context_mgr_uid)); ret = -EPERM; goto out; } } else { - binder_context_mgr_uid = curr_euid; + context->binder_context_mgr_uid = curr_euid; } - binder_context_mgr_node = binder_new_node(proc, 0, 0); - if (binder_context_mgr_node == NULL) { + new_node = binder_new_node(proc, NULL); + if (!new_node) { ret = -ENOMEM; goto out; } - binder_context_mgr_node->local_weak_refs++; - binder_context_mgr_node->local_strong_refs++; - binder_context_mgr_node->has_strong_ref = 1; - binder_context_mgr_node->has_weak_ref = 1; + binder_node_lock(new_node); + new_node->local_weak_refs++; + new_node->local_strong_refs++; + new_node->has_strong_ref = 1; + new_node->has_weak_ref = 1; + context->binder_context_mgr_node = new_node; + binder_node_unlock(new_node); + binder_put_node(new_node); out: + mutex_unlock(&context->context_mgr_node_lock); return ret; } +static int binder_ioctl_get_node_debug_info(struct binder_proc *proc, + struct binder_node_debug_info *info) { + struct rb_node *n; + binder_uintptr_t ptr = info->ptr; + + memset(info, 0, sizeof(*info)); + + binder_inner_proc_lock(proc); + for (n = rb_first(&proc->nodes); n != NULL; n = rb_next(n)) { + struct binder_node *node = rb_entry(n, struct binder_node, + rb_node); + if (node->ptr > ptr) { + info->ptr = node->ptr; + info->cookie = node->cookie; + info->has_strong_ref = node->has_strong_ref; + info->has_weak_ref = node->has_weak_ref; + break; + } + } + binder_inner_proc_unlock(proc); + + return 0; +} + static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { int ret; @@ -2768,13 +4635,14 @@ static long binder_ioctl(struct file *fi /*pr_info("binder_ioctl: %d:%d %x %lx\n", proc->pid, current->pid, cmd, arg);*/ + binder_selftest_alloc(&proc->alloc); + trace_binder_ioctl(cmd, arg); ret = wait_event_interruptible(binder_user_error_wait, binder_stop_on_user_error < 2); if (ret) goto err_unlocked; - binder_lock(__func__); thread = binder_get_thread(proc); if (thread == NULL) { ret = -ENOMEM; @@ -2787,12 +4655,19 @@ static long binder_ioctl(struct file *fi if (ret) goto err; break; - case BINDER_SET_MAX_THREADS: - if (copy_from_user(&proc->max_threads, ubuf, sizeof(proc->max_threads))) { + case BINDER_SET_MAX_THREADS: { + int max_threads; + + if (copy_from_user(&max_threads, ubuf, + sizeof(max_threads))) { ret = -EINVAL; goto err; } + binder_inner_proc_lock(proc); + proc->max_threads = max_threads; + binder_inner_proc_unlock(proc); break; + } case BINDER_SET_CONTEXT_MGR: ret = binder_ioctl_set_ctx_mgr(filp); if (ret) @@ -2801,7 +4676,7 @@ static long binder_ioctl(struct file *fi case BINDER_THREAD_EXIT: binder_debug(BINDER_DEBUG_THREADS, "%d:%d exit\n", proc->pid, thread->pid); - binder_free_thread(proc, thread); + binder_thread_release(proc, thread); thread = NULL; break; case BINDER_VERSION: { @@ -2818,6 +4693,24 @@ static long binder_ioctl(struct file *fi } break; } + case BINDER_GET_NODE_DEBUG_INFO: { + struct binder_node_debug_info info; + + if (copy_from_user(&info, ubuf, sizeof(info))) { + ret = -EFAULT; + goto err; + } + + ret = binder_ioctl_get_node_debug_info(proc, &info); + if (ret < 0) + goto err; + + if (copy_to_user(ubuf, &info, sizeof(info))) { + ret = -EFAULT; + goto err; + } + break; + } default: ret = -EINVAL; goto err; @@ -2825,8 +4718,7 @@ static long binder_ioctl(struct file *fi ret = 0; err: if (thread) - thread->looper &= ~BINDER_LOOPER_STATE_NEED_RETURN; - binder_unlock(__func__); + thread->looper_need_return = false; wait_event_interruptible(binder_user_error_wait, binder_stop_on_user_error < 2); if (ret && ret != -ERESTARTSYS) pr_info("%d:%d ioctl %x %lx returned %d\n", proc->pid, current->pid, cmd, arg, ret); @@ -2855,8 +4747,7 @@ static void binder_vma_close(struct vm_a proc->pid, vma->vm_start, vma->vm_end, (vma->vm_end - vma->vm_start) / SZ_1K, vma->vm_flags, (unsigned long)pgprot_val(vma->vm_page_prot)); - proc->vma = NULL; - proc->vma_vm_mm = NULL; + binder_alloc_vma_close(&proc->alloc); binder_defer_work(proc, BINDER_DEFERRED_PUT_FILES); } @@ -2874,10 +4765,8 @@ static const struct vm_operations_struct static int binder_mmap(struct file *filp, struct vm_area_struct *vma) { int ret; - struct vm_struct *area; struct binder_proc *proc = filp->private_data; const char *failure_string; - struct binder_buffer *buffer; if (proc->tsk != current->group_leader) return -EINVAL; @@ -2886,8 +4775,8 @@ static int binder_mmap(struct file *filp vma->vm_end = vma->vm_start + SZ_4M; binder_debug(BINDER_DEBUG_OPEN_CLOSE, - "binder_mmap: %d %lx-%lx (%ld K) vma %lx pagep %lx\n", - proc->pid, vma->vm_start, vma->vm_end, + "%s: %d %lx-%lx (%ld K) vma %lx pagep %lx\n", + __func__, proc->pid, vma->vm_start, vma->vm_end, (vma->vm_end - vma->vm_start) / SZ_1K, vma->vm_flags, (unsigned long)pgprot_val(vma->vm_page_prot)); @@ -2897,73 +4786,17 @@ static int binder_mmap(struct file *filp goto err_bad_arg; } vma->vm_flags = (vma->vm_flags | VM_DONTCOPY) & ~VM_MAYWRITE; - - mutex_lock(&binder_mmap_lock); - if (proc->buffer) { - ret = -EBUSY; - failure_string = "already mapped"; - goto err_already_mapped; - } - - area = get_vm_area(vma->vm_end - vma->vm_start, VM_IOREMAP); - if (area == NULL) { - ret = -ENOMEM; - failure_string = "get_vm_area"; - goto err_get_vm_area_failed; - } - proc->buffer = area->addr; - proc->user_buffer_offset = vma->vm_start - (uintptr_t)proc->buffer; - mutex_unlock(&binder_mmap_lock); - -#ifdef CONFIG_CPU_CACHE_VIPT - if (cache_is_vipt_aliasing()) { - while (CACHE_COLOUR((vma->vm_start ^ (uint32_t)proc->buffer))) { - pr_info("binder_mmap: %d %lx-%lx maps %p bad alignment\n", proc->pid, vma->vm_start, vma->vm_end, proc->buffer); - vma->vm_start += PAGE_SIZE; - } - } -#endif - proc->pages = kzalloc(sizeof(proc->pages[0]) * ((vma->vm_end - vma->vm_start) / PAGE_SIZE), GFP_KERNEL); - if (proc->pages == NULL) { - ret = -ENOMEM; - failure_string = "alloc page array"; - goto err_alloc_pages_failed; - } - proc->buffer_size = vma->vm_end - vma->vm_start; - vma->vm_ops = &binder_vm_ops; vma->vm_private_data = proc; - if (binder_update_page_range(proc, 1, proc->buffer, proc->buffer + PAGE_SIZE, vma)) { - ret = -ENOMEM; - failure_string = "alloc small buf"; - goto err_alloc_small_buf_failed; - } - buffer = proc->buffer; - INIT_LIST_HEAD(&proc->buffers); - list_add(&buffer->entry, &proc->buffers); - buffer->free = 1; - binder_insert_free_buffer(proc, buffer); - proc->free_async_space = proc->buffer_size / 2; - barrier(); + ret = binder_alloc_mmap_handler(&proc->alloc, vma); + if (ret) + return ret; + mutex_lock(&proc->files_lock); proc->files = get_files_struct(current); - proc->vma = vma; - proc->vma_vm_mm = vma->vm_mm; - - /*pr_info("binder_mmap: %d %lx-%lx maps %p\n", - proc->pid, vma->vm_start, vma->vm_end, proc->buffer);*/ + mutex_unlock(&proc->files_lock); return 0; -err_alloc_small_buf_failed: - kfree(proc->pages); - proc->pages = NULL; -err_alloc_pages_failed: - mutex_lock(&binder_mmap_lock); - vfree(proc->buffer); - proc->buffer = NULL; -err_get_vm_area_failed: -err_already_mapped: - mutex_unlock(&binder_mmap_lock); err_bad_arg: pr_err("binder_mmap: %d %lx-%lx %s failed %d\n", proc->pid, vma->vm_start, vma->vm_end, failure_string, ret); @@ -2973,6 +4806,7 @@ err_bad_arg: static int binder_open(struct inode *nodp, struct file *filp) { struct binder_proc *proc; + struct binder_device *binder_dev; binder_debug(BINDER_DEBUG_OPEN_CLOSE, "binder_open: %d:%d\n", current->group_leader->pid, current->pid); @@ -2980,28 +4814,50 @@ static int binder_open(struct inode *nod proc = kzalloc(sizeof(*proc), GFP_KERNEL); if (proc == NULL) return -ENOMEM; + spin_lock_init(&proc->inner_lock); + spin_lock_init(&proc->outer_lock); get_task_struct(current->group_leader); proc->tsk = current->group_leader; + mutex_init(&proc->files_lock); INIT_LIST_HEAD(&proc->todo); - init_waitqueue_head(&proc->wait); - proc->default_priority = task_nice(current); + if (binder_supported_policy(current->policy)) { + proc->default_priority.sched_policy = current->policy; + proc->default_priority.prio = current->normal_prio; + } else { + proc->default_priority.sched_policy = SCHED_NORMAL; + proc->default_priority.prio = NICE_TO_PRIO(0); + } - binder_lock(__func__); + binder_dev = container_of(filp->private_data, struct binder_device, + miscdev); + proc->context = &binder_dev->context; + binder_alloc_init(&proc->alloc); binder_stats_created(BINDER_STAT_PROC); - hlist_add_head(&proc->proc_node, &binder_procs); proc->pid = current->group_leader->pid; INIT_LIST_HEAD(&proc->delivered_death); + INIT_LIST_HEAD(&proc->waiting_threads); filp->private_data = proc; - binder_unlock(__func__); + mutex_lock(&binder_procs_lock); + hlist_add_head(&proc->proc_node, &binder_procs); + mutex_unlock(&binder_procs_lock); if (binder_debugfs_dir_entry_proc) { char strbuf[11]; - snprintf(strbuf, sizeof(strbuf), "%u", proc->pid); + snprintf(strbuf, sizeof(strbuf), "%d", proc->pid); + /* + * proc debug entries are shared between contexts, so + * this will fail if the process tries to open the driver + * again with a different context. The priting code will + * anyway print all contexts that a given PID has, so this + * is not a problem. + */ proc->debugfs_entry = debugfs_create_file(strbuf, S_IRUGO, - binder_debugfs_dir_entry_proc, proc, &binder_proc_fops); + binder_debugfs_dir_entry_proc, + (void *)(unsigned long)proc->pid, + &binder_proc_fops); } return 0; @@ -3021,16 +4877,17 @@ static void binder_deferred_flush(struct struct rb_node *n; int wake_count = 0; + binder_inner_proc_lock(proc); for (n = rb_first(&proc->threads); n != NULL; n = rb_next(n)) { struct binder_thread *thread = rb_entry(n, struct binder_thread, rb_node); - thread->looper |= BINDER_LOOPER_STATE_NEED_RETURN; + thread->looper_need_return = true; if (thread->looper & BINDER_LOOPER_STATE_WAITING) { wake_up_interruptible(&thread->wait); wake_count++; } } - wake_up_interruptible_all(&proc->wait); + binder_inner_proc_unlock(proc); binder_debug(BINDER_DEBUG_OPEN_CLOSE, "binder_flush: %d woke %d threads\n", proc->pid, @@ -3051,13 +4908,21 @@ static int binder_node_release(struct bi { struct binder_ref *ref; int death = 0; + struct binder_proc *proc = node->proc; - list_del_init(&node->work.entry); - binder_release_work(&node->async_todo); + binder_release_work(proc, &node->async_todo); - if (hlist_empty(&node->refs)) { - kfree(node); - binder_stats_deleted(BINDER_STAT_NODE); + binder_node_lock(node); + binder_inner_proc_lock(proc); + binder_dequeue_work_ilocked(&node->work); + /* + * The caller must have taken a temporary ref on the node, + */ + BUG_ON(!node->tmp_refs); + if (hlist_empty(&node->refs) && node->tmp_refs == 1) { + binder_inner_proc_unlock(proc); + binder_node_unlock(node); + binder_free_node(node); return refs; } @@ -3065,59 +4930,84 @@ static int binder_node_release(struct bi node->proc = NULL; node->local_strong_refs = 0; node->local_weak_refs = 0; + binder_inner_proc_unlock(proc); + + spin_lock(&binder_dead_nodes_lock); hlist_add_head(&node->dead_node, &binder_dead_nodes); + spin_unlock(&binder_dead_nodes_lock); hlist_for_each_entry(ref, &node->refs, node_entry) { refs++; - - if (!ref->death) + /* + * Need the node lock to synchronize + * with new notification requests and the + * inner lock to synchronize with queued + * death notifications. + */ + binder_inner_proc_lock(ref->proc); + if (!ref->death) { + binder_inner_proc_unlock(ref->proc); continue; + } death++; - if (list_empty(&ref->death->work.entry)) { - ref->death->work.type = BINDER_WORK_DEAD_BINDER; - list_add_tail(&ref->death->work.entry, - &ref->proc->todo); - wake_up_interruptible(&ref->proc->wait); - } else - BUG(); + BUG_ON(!list_empty(&ref->death->work.entry)); + ref->death->work.type = BINDER_WORK_DEAD_BINDER; + binder_enqueue_work_ilocked(&ref->death->work, + &ref->proc->todo); + binder_wakeup_proc_ilocked(ref->proc); + binder_inner_proc_unlock(ref->proc); } binder_debug(BINDER_DEBUG_DEAD_BINDER, "node %d now dead, refs %d, death %d\n", node->debug_id, refs, death); + binder_node_unlock(node); + binder_put_node(node); return refs; } static void binder_deferred_release(struct binder_proc *proc) { - struct binder_transaction *t; + struct binder_context *context = proc->context; struct rb_node *n; - int threads, nodes, incoming_refs, outgoing_refs, buffers, - active_transactions, page_count; + int threads, nodes, incoming_refs, outgoing_refs, active_transactions; - BUG_ON(proc->vma); BUG_ON(proc->files); + mutex_lock(&binder_procs_lock); hlist_del(&proc->proc_node); + mutex_unlock(&binder_procs_lock); - if (binder_context_mgr_node && binder_context_mgr_node->proc == proc) { + mutex_lock(&context->context_mgr_node_lock); + if (context->binder_context_mgr_node && + context->binder_context_mgr_node->proc == proc) { binder_debug(BINDER_DEBUG_DEAD_BINDER, "%s: %d context_mgr_node gone\n", __func__, proc->pid); - binder_context_mgr_node = NULL; + context->binder_context_mgr_node = NULL; } + mutex_unlock(&context->context_mgr_node_lock); + binder_inner_proc_lock(proc); + /* + * Make sure proc stays alive after we + * remove all the threads + */ + proc->tmp_ref++; + proc->is_dead = true; threads = 0; active_transactions = 0; while ((n = rb_first(&proc->threads))) { struct binder_thread *thread; thread = rb_entry(n, struct binder_thread, rb_node); + binder_inner_proc_unlock(proc); threads++; - active_transactions += binder_free_thread(proc, thread); + active_transactions += binder_thread_release(proc, thread); + binder_inner_proc_lock(proc); } nodes = 0; @@ -3127,73 +5017,42 @@ static void binder_deferred_release(stru node = rb_entry(n, struct binder_node, rb_node); nodes++; + /* + * take a temporary ref on the node before + * calling binder_node_release() which will either + * kfree() the node or call binder_put_node() + */ + binder_inc_node_tmpref_ilocked(node); rb_erase(&node->rb_node, &proc->nodes); + binder_inner_proc_unlock(proc); incoming_refs = binder_node_release(node, incoming_refs); + binder_inner_proc_lock(proc); } + binder_inner_proc_unlock(proc); outgoing_refs = 0; + binder_proc_lock(proc); while ((n = rb_first(&proc->refs_by_desc))) { struct binder_ref *ref; ref = rb_entry(n, struct binder_ref, rb_node_desc); outgoing_refs++; - binder_delete_ref(ref); - } - - binder_release_work(&proc->todo); - binder_release_work(&proc->delivered_death); - - buffers = 0; - while ((n = rb_first(&proc->allocated_buffers))) { - struct binder_buffer *buffer; - - buffer = rb_entry(n, struct binder_buffer, rb_node); - - t = buffer->transaction; - if (t) { - t->buffer = NULL; - buffer->transaction = NULL; - pr_err("release proc %d, transaction %d, not freed\n", - proc->pid, t->debug_id); - /*BUG();*/ - } - - binder_free_buf(proc, buffer); - buffers++; - } - - binder_stats_deleted(BINDER_STAT_PROC); - - page_count = 0; - if (proc->pages) { - int i; - - for (i = 0; i < proc->buffer_size / PAGE_SIZE; i++) { - void *page_addr; - - if (!proc->pages[i]) - continue; - - page_addr = proc->buffer + i * PAGE_SIZE; - binder_debug(BINDER_DEBUG_BUFFER_ALLOC, - "%s: %d: page %d at %p not freed\n", - __func__, proc->pid, i, page_addr); - unmap_kernel_range((unsigned long)page_addr, PAGE_SIZE); - __free_page(proc->pages[i]); - page_count++; - } - kfree(proc->pages); - vfree(proc->buffer); + binder_cleanup_ref_olocked(ref); + binder_proc_unlock(proc); + binder_free_ref(ref); + binder_proc_lock(proc); } + binder_proc_unlock(proc); - put_task_struct(proc->tsk); + binder_release_work(proc, &proc->todo); + binder_release_work(proc, &proc->delivered_death); binder_debug(BINDER_DEBUG_OPEN_CLOSE, - "%s: %d threads %d, nodes %d (ref %d), refs %d, active transactions %d, buffers %d, pages %d\n", + "%s: %d threads %d, nodes %d (ref %d), refs %d, active transactions %d\n", __func__, proc->pid, threads, nodes, incoming_refs, - outgoing_refs, active_transactions, buffers, page_count); + outgoing_refs, active_transactions); - kfree(proc); + binder_proc_dec_tmpref(proc); } static void binder_deferred_func(struct work_struct *work) @@ -3204,7 +5063,6 @@ static void binder_deferred_func(struct int defer; do { - binder_lock(__func__); mutex_lock(&binder_deferred_lock); if (!hlist_empty(&binder_deferred_list)) { proc = hlist_entry(binder_deferred_list.first, @@ -3220,9 +5078,11 @@ static void binder_deferred_func(struct files = NULL; if (defer & BINDER_DEFERRED_PUT_FILES) { + mutex_lock(&proc->files_lock); files = proc->files; if (files) proc->files = NULL; + mutex_unlock(&proc->files_lock); } if (defer & BINDER_DEFERRED_FLUSH) @@ -3231,7 +5091,6 @@ static void binder_deferred_func(struct if (defer & BINDER_DEFERRED_RELEASE) binder_deferred_release(proc); /* frees proc */ - binder_unlock(__func__); if (files) put_files_struct(files); } while (proc); @@ -3251,41 +5110,52 @@ binder_defer_work(struct binder_proc *pr mutex_unlock(&binder_deferred_lock); } -static void print_binder_transaction(struct seq_file *m, const char *prefix, - struct binder_transaction *t) +static void print_binder_transaction_ilocked(struct seq_file *m, + struct binder_proc *proc, + const char *prefix, + struct binder_transaction *t) { + struct binder_proc *to_proc; + struct binder_buffer *buffer = t->buffer; + + spin_lock(&t->lock); + to_proc = t->to_proc; seq_printf(m, - "%s %d: %p from %d:%d to %d:%d code %x flags %x pri %ld r%d", + "%s %d: %p from %d:%d to %d:%d code %x flags %x pri %d:%d r%d", prefix, t->debug_id, t, t->from ? t->from->proc->pid : 0, t->from ? t->from->pid : 0, - t->to_proc ? t->to_proc->pid : 0, + to_proc ? to_proc->pid : 0, t->to_thread ? t->to_thread->pid : 0, - t->code, t->flags, t->priority, t->need_reply); - if (t->buffer == NULL) { + t->code, t->flags, t->priority.sched_policy, + t->priority.prio, t->need_reply); + spin_unlock(&t->lock); + + if (proc != to_proc) { + /* + * Can only safely deref buffer if we are holding the + * correct proc inner lock for this node + */ + seq_puts(m, "\n"); + return; + } + + if (buffer == NULL) { seq_puts(m, " buffer free\n"); return; } - if (t->buffer->target_node) - seq_printf(m, " node %d", - t->buffer->target_node->debug_id); + if (buffer->target_node) + seq_printf(m, " node %d", buffer->target_node->debug_id); seq_printf(m, " size %zd:%zd data %p\n", - t->buffer->data_size, t->buffer->offsets_size, - t->buffer->data); -} - -static void print_binder_buffer(struct seq_file *m, const char *prefix, - struct binder_buffer *buffer) -{ - seq_printf(m, "%s %d: %p size %zd:%zd %s\n", - prefix, buffer->debug_id, buffer->data, buffer->data_size, buffer->offsets_size, - buffer->transaction ? "active" : "delivered"); + buffer->data); } -static void print_binder_work(struct seq_file *m, const char *prefix, - const char *transaction_prefix, - struct binder_work *w) +static void print_binder_work_ilocked(struct seq_file *m, + struct binder_proc *proc, + const char *prefix, + const char *transaction_prefix, + struct binder_work *w) { struct binder_node *node; struct binder_transaction *t; @@ -3293,8 +5163,16 @@ static void print_binder_work(struct seq switch (w->type) { case BINDER_WORK_TRANSACTION: t = container_of(w, struct binder_transaction, work); - print_binder_transaction(m, transaction_prefix, t); + print_binder_transaction_ilocked( + m, proc, transaction_prefix, t); break; + case BINDER_WORK_RETURN_ERROR: { + struct binder_error *e = container_of( + w, struct binder_error, work); + + seq_printf(m, "%stransaction error: %u\n", + prefix, e->cmd); + } break; case BINDER_WORK_TRANSACTION_COMPLETE: seq_printf(m, "%stransaction complete\n", prefix); break; @@ -3319,40 +5197,46 @@ static void print_binder_work(struct seq } } -static void print_binder_thread(struct seq_file *m, - struct binder_thread *thread, - int print_always) +static void print_binder_thread_ilocked(struct seq_file *m, + struct binder_thread *thread, + int print_always) { struct binder_transaction *t; struct binder_work *w; size_t start_pos = m->count; size_t header_pos; - seq_printf(m, " thread %d: l %02x\n", thread->pid, thread->looper); + seq_printf(m, " thread %d: l %02x need_return %d tr %d\n", + thread->pid, thread->looper, + thread->looper_need_return, + atomic_read(&thread->tmp_ref)); header_pos = m->count; t = thread->transaction_stack; while (t) { if (t->from == thread) { - print_binder_transaction(m, - " outgoing transaction", t); + print_binder_transaction_ilocked(m, thread->proc, + " outgoing transaction", t); t = t->from_parent; } else if (t->to_thread == thread) { - print_binder_transaction(m, + print_binder_transaction_ilocked(m, thread->proc, " incoming transaction", t); t = t->to_parent; } else { - print_binder_transaction(m, " bad transaction", t); + print_binder_transaction_ilocked(m, thread->proc, + " bad transaction", t); t = NULL; } } list_for_each_entry(w, &thread->todo, entry) { - print_binder_work(m, " ", " pending transaction", w); + print_binder_work_ilocked(m, thread->proc, " ", + " pending transaction", w); } if (!print_always && m->count == header_pos) m->count = start_pos; } -static void print_binder_node(struct seq_file *m, struct binder_node *node) +static void print_binder_node_nilocked(struct seq_file *m, + struct binder_node *node) { struct binder_ref *ref; struct binder_work *w; @@ -3362,27 +5246,35 @@ static void print_binder_node(struct seq hlist_for_each_entry(ref, &node->refs, node_entry) count++; - seq_printf(m, " node %d: u%016llx c%016llx hs %d hw %d ls %d lw %d is %d iw %d", + seq_printf(m, " node %d: u%016llx c%016llx pri %d:%d hs %d hw %d ls %d lw %d is %d iw %d tr %d", node->debug_id, (u64)node->ptr, (u64)node->cookie, + node->sched_policy, node->min_priority, node->has_strong_ref, node->has_weak_ref, node->local_strong_refs, node->local_weak_refs, - node->internal_strong_refs, count); + node->internal_strong_refs, count, node->tmp_refs); if (count) { seq_puts(m, " proc"); hlist_for_each_entry(ref, &node->refs, node_entry) seq_printf(m, " %d", ref->proc->pid); } seq_puts(m, "\n"); - list_for_each_entry(w, &node->async_todo, entry) - print_binder_work(m, " ", - " pending async transaction", w); + if (node->proc) { + list_for_each_entry(w, &node->async_todo, entry) + print_binder_work_ilocked(m, node->proc, " ", + " pending async transaction", w); + } } -static void print_binder_ref(struct seq_file *m, struct binder_ref *ref) +static void print_binder_ref_olocked(struct seq_file *m, + struct binder_ref *ref) { - seq_printf(m, " ref %d: desc %d %snode %d s %d w %d d %p\n", - ref->debug_id, ref->desc, ref->node->proc ? "" : "dead ", - ref->node->debug_id, ref->strong, ref->weak, ref->death); + binder_node_lock(ref->node); + seq_printf(m, " ref %d: desc %d %snode %d s %d w %d d %pK\n", + ref->data.debug_id, ref->data.desc, + ref->node->proc ? "" : "dead ", + ref->node->debug_id, ref->data.strong, + ref->data.weak, ref->death); + binder_node_unlock(ref->node); } static void print_binder_proc(struct seq_file *m, @@ -3392,35 +5284,60 @@ static void print_binder_proc(struct seq struct rb_node *n; size_t start_pos = m->count; size_t header_pos; + struct binder_node *last_node = NULL; seq_printf(m, "proc %d\n", proc->pid); + seq_printf(m, "context %s\n", proc->context->name); header_pos = m->count; + binder_inner_proc_lock(proc); for (n = rb_first(&proc->threads); n != NULL; n = rb_next(n)) - print_binder_thread(m, rb_entry(n, struct binder_thread, + print_binder_thread_ilocked(m, rb_entry(n, struct binder_thread, rb_node), print_all); + for (n = rb_first(&proc->nodes); n != NULL; n = rb_next(n)) { struct binder_node *node = rb_entry(n, struct binder_node, rb_node); - if (print_all || node->has_async_transaction) - print_binder_node(m, node); + /* + * take a temporary reference on the node so it + * survives and isn't removed from the tree + * while we print it. + */ + binder_inc_node_tmpref_ilocked(node); + /* Need to drop inner lock to take node lock */ + binder_inner_proc_unlock(proc); + if (last_node) + binder_put_node(last_node); + binder_node_inner_lock(node); + print_binder_node_nilocked(m, node); + binder_node_inner_unlock(node); + last_node = node; + binder_inner_proc_lock(proc); } + binder_inner_proc_unlock(proc); + if (last_node) + binder_put_node(last_node); + if (print_all) { + binder_proc_lock(proc); for (n = rb_first(&proc->refs_by_desc); n != NULL; n = rb_next(n)) - print_binder_ref(m, rb_entry(n, struct binder_ref, - rb_node_desc)); + print_binder_ref_olocked(m, rb_entry(n, + struct binder_ref, + rb_node_desc)); + binder_proc_unlock(proc); } - for (n = rb_first(&proc->allocated_buffers); n != NULL; n = rb_next(n)) - print_binder_buffer(m, " buffer", - rb_entry(n, struct binder_buffer, rb_node)); + binder_alloc_print_allocated(m, &proc->alloc); + binder_inner_proc_lock(proc); list_for_each_entry(w, &proc->todo, entry) - print_binder_work(m, " ", " pending transaction", w); + print_binder_work_ilocked(m, proc, " ", + " pending transaction", w); list_for_each_entry(w, &proc->delivered_death, entry) { seq_puts(m, " has delivered dead binder\n"); break; } + binder_inner_proc_unlock(proc); if (!print_all && m->count == header_pos) m->count = start_pos; } @@ -3463,7 +5380,9 @@ static const char * const binder_command "BC_EXIT_LOOPER", "BC_REQUEST_DEATH_NOTIFICATION", "BC_CLEAR_DEATH_NOTIFICATION", - "BC_DEAD_BINDER_DONE" + "BC_DEAD_BINDER_DONE", + "BC_TRANSACTION_SG", + "BC_REPLY_SG", }; static const char * const binder_objstat_strings[] = { @@ -3484,17 +5403,21 @@ static void print_binder_stats(struct se BUILD_BUG_ON(ARRAY_SIZE(stats->bc) != ARRAY_SIZE(binder_command_strings)); for (i = 0; i < ARRAY_SIZE(stats->bc); i++) { - if (stats->bc[i]) + int temp = atomic_read(&stats->bc[i]); + + if (temp) seq_printf(m, "%s%s: %d\n", prefix, - binder_command_strings[i], stats->bc[i]); + binder_command_strings[i], temp); } BUILD_BUG_ON(ARRAY_SIZE(stats->br) != ARRAY_SIZE(binder_return_strings)); for (i = 0; i < ARRAY_SIZE(stats->br); i++) { - if (stats->br[i]) + int temp = atomic_read(&stats->br[i]); + + if (temp) seq_printf(m, "%s%s: %d\n", prefix, - binder_return_strings[i], stats->br[i]); + binder_return_strings[i], temp); } BUILD_BUG_ON(ARRAY_SIZE(stats->obj_created) != @@ -3502,11 +5425,15 @@ static void print_binder_stats(struct se BUILD_BUG_ON(ARRAY_SIZE(stats->obj_created) != ARRAY_SIZE(stats->obj_deleted)); for (i = 0; i < ARRAY_SIZE(stats->obj_created); i++) { - if (stats->obj_created[i] || stats->obj_deleted[i]) - seq_printf(m, "%s%s: active %d total %d\n", prefix, + int created = atomic_read(&stats->obj_created[i]); + int deleted = atomic_read(&stats->obj_deleted[i]); + + if (created || deleted) + seq_printf(m, "%s%s: active %d total %d\n", + prefix, binder_objstat_strings[i], - stats->obj_created[i] - stats->obj_deleted[i], - stats->obj_created[i]); + created - deleted, + created); } } @@ -3514,50 +5441,59 @@ static void print_binder_proc_stats(stru struct binder_proc *proc) { struct binder_work *w; + struct binder_thread *thread; struct rb_node *n; - int count, strong, weak; + int count, strong, weak, ready_threads; + size_t free_async_space = + binder_alloc_get_free_async_space(&proc->alloc); seq_printf(m, "proc %d\n", proc->pid); + seq_printf(m, "context %s\n", proc->context->name); count = 0; + ready_threads = 0; + binder_inner_proc_lock(proc); for (n = rb_first(&proc->threads); n != NULL; n = rb_next(n)) count++; + + list_for_each_entry(thread, &proc->waiting_threads, waiting_thread_node) + ready_threads++; + seq_printf(m, " threads: %d\n", count); seq_printf(m, " requested threads: %d+%d/%d\n" " ready threads %d\n" " free async space %zd\n", proc->requested_threads, proc->requested_threads_started, proc->max_threads, - proc->ready_threads, proc->free_async_space); + ready_threads, + free_async_space); count = 0; for (n = rb_first(&proc->nodes); n != NULL; n = rb_next(n)) count++; + binder_inner_proc_unlock(proc); seq_printf(m, " nodes: %d\n", count); count = 0; strong = 0; weak = 0; + binder_proc_lock(proc); for (n = rb_first(&proc->refs_by_desc); n != NULL; n = rb_next(n)) { struct binder_ref *ref = rb_entry(n, struct binder_ref, rb_node_desc); count++; - strong += ref->strong; - weak += ref->weak; + strong += ref->data.strong; + weak += ref->data.weak; } + binder_proc_unlock(proc); seq_printf(m, " refs: %d s %d w %d\n", count, strong, weak); - count = 0; - for (n = rb_first(&proc->allocated_buffers); n != NULL; n = rb_next(n)) - count++; + count = binder_alloc_get_allocated_count(&proc->alloc); seq_printf(m, " buffers: %d\n", count); count = 0; + binder_inner_proc_lock(proc); list_for_each_entry(w, &proc->todo, entry) { - switch (w->type) { - case BINDER_WORK_TRANSACTION: + if (w->type == BINDER_WORK_TRANSACTION) count++; - break; - default: - break; - } } + binder_inner_proc_unlock(proc); seq_printf(m, " pending transactions: %d\n", count); print_binder_stats(m, " ", &proc->stats); @@ -3568,107 +5504,131 @@ static int binder_state_show(struct seq_ { struct binder_proc *proc; struct binder_node *node; - int do_lock = !binder_debug_no_lock; - - if (do_lock) - binder_lock(__func__); + struct binder_node *last_node = NULL; seq_puts(m, "binder state:\n"); + spin_lock(&binder_dead_nodes_lock); if (!hlist_empty(&binder_dead_nodes)) seq_puts(m, "dead nodes:\n"); - hlist_for_each_entry(node, &binder_dead_nodes, dead_node) - print_binder_node(m, node); + hlist_for_each_entry(node, &binder_dead_nodes, dead_node) { + /* + * take a temporary reference on the node so it + * survives and isn't removed from the list + * while we print it. + */ + node->tmp_refs++; + spin_unlock(&binder_dead_nodes_lock); + if (last_node) + binder_put_node(last_node); + binder_node_lock(node); + print_binder_node_nilocked(m, node); + binder_node_unlock(node); + last_node = node; + spin_lock(&binder_dead_nodes_lock); + } + spin_unlock(&binder_dead_nodes_lock); + if (last_node) + binder_put_node(last_node); + mutex_lock(&binder_procs_lock); hlist_for_each_entry(proc, &binder_procs, proc_node) print_binder_proc(m, proc, 1); - if (do_lock) - binder_unlock(__func__); + mutex_unlock(&binder_procs_lock); + return 0; } static int binder_stats_show(struct seq_file *m, void *unused) { struct binder_proc *proc; - int do_lock = !binder_debug_no_lock; - - if (do_lock) - binder_lock(__func__); seq_puts(m, "binder stats:\n"); print_binder_stats(m, "", &binder_stats); + mutex_lock(&binder_procs_lock); hlist_for_each_entry(proc, &binder_procs, proc_node) print_binder_proc_stats(m, proc); - if (do_lock) - binder_unlock(__func__); + mutex_unlock(&binder_procs_lock); + return 0; } static int binder_transactions_show(struct seq_file *m, void *unused) { struct binder_proc *proc; - int do_lock = !binder_debug_no_lock; - - if (do_lock) - binder_lock(__func__); seq_puts(m, "binder transactions:\n"); + mutex_lock(&binder_procs_lock); hlist_for_each_entry(proc, &binder_procs, proc_node) print_binder_proc(m, proc, 0); - if (do_lock) - binder_unlock(__func__); + mutex_unlock(&binder_procs_lock); + return 0; } static int binder_proc_show(struct seq_file *m, void *unused) { struct binder_proc *itr; - struct binder_proc *proc = m->private; - int do_lock = !binder_debug_no_lock; - bool valid_proc = false; - - if (do_lock) - binder_lock(__func__); + int pid = (unsigned long)m->private; + mutex_lock(&binder_procs_lock); hlist_for_each_entry(itr, &binder_procs, proc_node) { - if (itr == proc) { - valid_proc = true; - break; + if (itr->pid == pid) { + seq_puts(m, "binder proc state:\n"); + print_binder_proc(m, itr, 1); } } - if (valid_proc) { - seq_puts(m, "binder proc state:\n"); - print_binder_proc(m, proc, 1); - } - if (do_lock) - binder_unlock(__func__); + mutex_unlock(&binder_procs_lock); + return 0; } static void print_binder_transaction_log_entry(struct seq_file *m, struct binder_transaction_log_entry *e) { + int debug_id = READ_ONCE(e->debug_id_done); + /* + * read barrier to guarantee debug_id_done read before + * we print the log values + */ + smp_rmb(); seq_printf(m, - "%d: %s from %d:%d to %d:%d node %d handle %d size %d:%d\n", + "%d: %s from %d:%d to %d:%d context %s node %d handle %d size %d:%d ret %d/%d l=%d", e->debug_id, (e->call_type == 2) ? "reply" : ((e->call_type == 1) ? "async" : "call "), e->from_proc, - e->from_thread, e->to_proc, e->to_thread, e->to_node, - e->target_handle, e->data_size, e->offsets_size); + e->from_thread, e->to_proc, e->to_thread, e->context_name, + e->to_node, e->target_handle, e->data_size, e->offsets_size, + e->return_error, e->return_error_param, + e->return_error_line); + /* + * read-barrier to guarantee read of debug_id_done after + * done printing the fields of the entry + */ + smp_rmb(); + seq_printf(m, debug_id && debug_id == READ_ONCE(e->debug_id_done) ? + "\n" : " (incomplete)\n"); } static int binder_transaction_log_show(struct seq_file *m, void *unused) { struct binder_transaction_log *log = m->private; + unsigned int log_cur = atomic_read(&log->cur); + unsigned int count; + unsigned int cur; int i; - if (log->full) { - for (i = log->next; i < ARRAY_SIZE(log->entry); i++) - print_binder_transaction_log_entry(m, &log->entry[i]); + count = log_cur + 1; + cur = count < ARRAY_SIZE(log->entry) && !log->full ? + 0 : count % ARRAY_SIZE(log->entry); + if (count > ARRAY_SIZE(log->entry) || log->full) + count = ARRAY_SIZE(log->entry); + for (i = 0; i < count; i++) { + unsigned int index = cur++ % ARRAY_SIZE(log->entry); + + print_binder_transaction_log_entry(m, &log->entry[index]); } - for (i = 0; i < log->next; i++) - print_binder_transaction_log_entry(m, &log->entry[i]); return 0; } @@ -3683,26 +5643,54 @@ static const struct file_operations bind .release = binder_release, }; -static struct miscdevice binder_miscdev = { - .minor = MISC_DYNAMIC_MINOR, - .name = "binder", - .fops = &binder_fops -}; - BINDER_DEBUG_ENTRY(state); BINDER_DEBUG_ENTRY(stats); BINDER_DEBUG_ENTRY(transactions); BINDER_DEBUG_ENTRY(transaction_log); +static int __init init_binder_device(const char *name) +{ + int ret; + struct binder_device *binder_device; + + binder_device = kzalloc(sizeof(*binder_device), GFP_KERNEL); + if (!binder_device) + return -ENOMEM; + + binder_device->miscdev.fops = &binder_fops; + binder_device->miscdev.minor = MISC_DYNAMIC_MINOR; + binder_device->miscdev.name = name; + + binder_device->context.binder_context_mgr_uid = INVALID_UID; + binder_device->context.name = name; + mutex_init(&binder_device->context.context_mgr_node_lock); + + ret = misc_register(&binder_device->miscdev); + if (ret < 0) { + kfree(binder_device); + return ret; + } + + hlist_add_head(&binder_device->hlist, &binder_devices); + + return ret; +} + static int __init binder_init(void) { int ret; + char *device_name, *device_names; + struct binder_device *device; + struct hlist_node *tmp; + + atomic_set(&binder_transaction_log.cur, ~0U); + atomic_set(&binder_transaction_log_failed.cur, ~0U); binder_debugfs_dir_entry_root = debugfs_create_dir("binder", NULL); if (binder_debugfs_dir_entry_root) binder_debugfs_dir_entry_proc = debugfs_create_dir("proc", binder_debugfs_dir_entry_root); - ret = misc_register(&binder_miscdev); + if (binder_debugfs_dir_entry_root) { debugfs_create_file("state", S_IRUGO, @@ -3730,6 +5718,35 @@ static int __init binder_init(void) &binder_transaction_log_failed, &binder_transaction_log_fops); } + + /* + * Copy the module_parameter string, because we don't want to + * tokenize it in-place. + */ + device_names = kzalloc(strlen(binder_devices_param) + 1, GFP_KERNEL); + if (!device_names) { + ret = -ENOMEM; + goto err_alloc_device_names_failed; + } + strcpy(device_names, binder_devices_param); + + while ((device_name = strsep(&device_names, ","))) { + ret = init_binder_device(device_name); + if (ret) + goto err_init_binder_device_failed; + } + + return ret; + +err_init_binder_device_failed: + hlist_for_each_entry_safe(device, tmp, &binder_devices, hlist) { + misc_deregister(&device->miscdev); + hlist_del(&device->hlist); + kfree(device); + } +err_alloc_device_names_failed: + debugfs_remove_recursive(binder_debugfs_dir_entry_root); + return ret; }