发明名称 Resolving RCU-scheduler deadlocks
摘要 A technique for resolving deadlocks between an RCU subsystem and an operating system scheduler. An RCU reader manipulates a counter when entering and exiting an RCU read-side critical section. At the entry, the counter is incremented. At the exit, the counter is manipulated differently depending on the counter value. A first counter manipulation path is taken when the counter indicates a task-context RCU reader is exiting an outermost RCU read-side critical section. This path includes condition-based processing that may result in invocation of the operating system scheduler. The first path further includes a deadlock protection operation that manipulates the counter to prevent an intervening RCU reader from taking the same path. The second manipulation path is taken when the counter value indicates a task-context RCU reader is exiting a non-outermost RCU read-side critical section, or an RCU reader is nested within the first path. This path bypasses the condition-based processing.
申请公布号 US9003420(B2) 申请公布日期 2015.04.07
申请号 US201213475003 申请日期 2012.05.18
申请人 International Business Machines Corporation 发明人 McKenney Paul E.
分类号 G06F9/46;G06F9/00;G06F9/48;G06F9/52 主分类号 G06F9/46
代理机构 代理人 Duft Walter W.
主权项 1. A system, comprising: one or more processors; a memory coupled to said processors, said memory including a computer useable storage medium tangibly embodying at least one program of instructions executable by said processors to implement a read-copy update (RCU) subsystem and to perform operations for resolving deadlocks between said RCU subsystem and an operating system scheduler, comprising: providing an RCU registration component that allows an RCU reader to manipulate an rcu_read_lock_nesting counter when said RCU reader enters an RCU read-side critical section; providing an RCU unregistration component that allows an RCU reader to manipulate said rcu_read_lock_nesting counter when said RCU reader leaves an RCU read-side critical section; said unregistration component providing first and second rcu_read_lock_nesting manipulation paths that are dependent on a current value of said rcu_read_lock_nesting counter; said first rcu_read_lock_nesting manipulation path being taken when said current value of said rcu_read_lock_nesting counter is indicative of a task-context RCU reader exiting an outermost RCU read-side critical section; said first rcu_read_lock_nesting manipulation path including condition-based read-side helper processing that may result in invocation of said operating system scheduler; said first rcu_read_lock_nesting manipulation path further including a deadlock protection operation that manipulates said rcu_read_lock_nesting counter to prevent any intervening RCU reader from taking said first rcu_read_lock_nesting manipulation path while a task-context RCU reader is within that path; said second rcu_read_lock_nesting manipulation path being taken when said current value of said rcu_read_lock_nesting counter is indicative of a task-context RCU reader exiting a non-outermost RCU read-side critical section or an RCU reader being nested within said first rcu_read_lock_nesting manipulation path; said second rcu_read_lock_nesting manipulation path bypassing said condition-based read-side helper processing said RCU unregistration component allowing an RCU reader to manipulate said rcu_read_lock_nesting counter by either decrementing it or setting it to a value, depending on which manipulation path is taken by said RCU reader; and said first manipulation path comprising setting said rcu_read_lock_nesting counter to a deadlock protection value and said second manipulation path comprises decrementing said rcu_read_lock_nesting counter.
地址 Armonk NY US