)]}'
{
  "log": [
    {
      "commit": "e6a92013ba458804161c0c5b6d134d82204dc233",
      "tree": "ecee5fdcef80d1dba0ac6ea87370931ea39ffecd",
      "parents": [
        "eabc069401bcf45bcc3f19e643017bf761780aa8"
      ],
      "author": {
        "name": "Alan Stern",
        "email": "stern@rowland.harvard.edu",
        "time": "Wed Oct 04 02:17:05 2006 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@g5.osdl.org",
        "time": "Wed Oct 04 07:55:30 2006 -0700"
      },
      "message": "[PATCH] SRCU: report out-of-memory errors\n\nCurrently the init_srcu_struct() routine has no way to report out-of-memory\nerrors.  This patch (as761) makes it return -ENOMEM when the per-cpu data\nallocation fails.\n\nThe patch also makes srcu_init_notifier_head() report a BUG if a notifier\nhead can\u0027t be initialized.  Perhaps it should return -ENOMEM instead, but\nin the most likely cases where this might occur I don\u0027t think any recovery\nis possible.  Notifier chains generally are not created dynamically.\n\n[akpm@osdl.org: avoid statement-with-side-effect in macro]\nSigned-off-by: Alan Stern \u003cstern@rowland.harvard.edu\u003e\nAcked-by: Paul E. McKenney \u003cpaulmck@us.ibm.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    },
    {
      "commit": "eabc069401bcf45bcc3f19e643017bf761780aa8",
      "tree": "1175b8bed2d88cc9f437edbc239d7681f13b8a7d",
      "parents": [
        "b2896d2e75c87ea6a842c088db730b03c91db737"
      ],
      "author": {
        "name": "Alan Stern",
        "email": "stern@rowland.harvard.edu",
        "time": "Wed Oct 04 02:17:04 2006 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@g5.osdl.org",
        "time": "Wed Oct 04 07:55:30 2006 -0700"
      },
      "message": "[PATCH] Add SRCU-based notifier chains\n\nThis patch (as751) adds a new type of notifier chain, based on the SRCU\n(Sleepable Read-Copy Update) primitives recently added to the kernel.  An\nSRCU notifier chain is much like a blocking notifier chain, in that it must\nbe called in process context and its callout routines are allowed to sleep.\n The difference is that the chain\u0027s links are protected by the SRCU\nmechanism rather than by an rw-semaphore, so calling the chain has\nextremely low overhead: no memory barriers and no cache-line bouncing.  On\nthe other hand, unregistering from the chain is expensive and the chain\nhead requires special runtime initialization (plus cleanup if it is to be\ndeallocated).\n\nSRCU notifiers are appropriate for notifiers that will be called very\nfrequently and for which unregistration occurs very seldom.  The proposed\n\"task notifier\" scheme qualifies, as may some of the network notifiers.\n\nSigned-off-by: Alan Stern \u003cstern@rowland.harvard.edu\u003e\nAcked-by: Paul E. McKenney \u003cpaulmck@us.ibm.com\u003e\nAcked-by: Chandra Seetharaman \u003csekharan@us.ibm.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    },
    {
      "commit": "621934ee7ed5b073c7fd638b347e632c53572761",
      "tree": "5722f9cda22c099ad60545f963410dcbc762ee65",
      "parents": [
        "95d77884c77beed676036d2f74d10b470a483c63"
      ],
      "author": {
        "name": "Paul E. McKenney",
        "email": "paulmck@us.ibm.com",
        "time": "Wed Oct 04 02:17:02 2006 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@g5.osdl.org",
        "time": "Wed Oct 04 07:55:30 2006 -0700"
      },
      "message": "[PATCH] srcu-3: RCU variant permitting read-side blocking\n\nUpdated patch adding a variant of RCU that permits sleeping in read-side\ncritical sections.  SRCU is as follows:\n\no\tEach use of SRCU creates its own srcu_struct, and each\n\tsrcu_struct has its own set of grace periods.  This is\n\tcritical, as it prevents one subsystem with a blocking\n\treader from holding up SRCU grace periods for other\n\tsubsystems.\n\no\tThe SRCU primitives (srcu_read_lock(), srcu_read_unlock(),\n\tand synchronize_srcu()) all take a pointer to a srcu_struct.\n\no\tThe SRCU primitives must be called from process context.\n\no\tsrcu_read_lock() returns an int that must be passed to\n\tthe matching srcu_read_unlock().  Realtime RCU avoids the\n\tneed for this by storing the state in the task struct,\n\tbut SRCU needs to allow a given code path to pass through\n\tmultiple SRCU domains -- storing state in the task struct\n\twould therefore require either arbitrary space in the\n\ttask struct or arbitrary limits on SRCU nesting.  So I\n\tkicked the state-storage problem up to the caller.\n\n\tOf course, it is not permitted to call synchronize_srcu()\n\twhile in an SRCU read-side critical section.\n\no\tThere is no call_srcu().  It would not be hard to implement\n\tone, but it seems like too easy a way to OOM the system.\n\t(Hey, we have enough trouble with call_rcu(), which does\n\t-not- permit readers to sleep!!!)  So, if you want it,\n\tplease tell me why...\n\n[josht@us.ibm.com: sparse notation]\nSigned-off-by: Paul E. McKenney \u003cpaulmck@us.ibm.com\u003e\nSigned-off-by: Josh Triplett \u003cjosh@freedesktop.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    }
  ]
}