)]}'
{
  "log": [
    {
      "commit": "38bc2b8c56a2e212bbd19de7cf9976dcc7bf9953",
      "tree": "26071dbb540926c329ece0ab4d4425807021b5c8",
      "parents": [
        "5dac051bc6030963181b69faddd9e0ad04f85fa8"
      ],
      "author": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:11 2009 -0600"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:11 2009 +0930"
      },
      "message": "lguest: implement deferred interrupts in example Launcher\n\nRather than sending an interrupt on every buffer, we only send an interrupt\nwhen we\u0027re about to wait for the Guest to send us a new one.  The console\ninput and network input still send interrupts manually, but the block device,\nnetwork and console output queues can simply rely on this logic to send\ninterrupts to the Guest at the right time.\n\nThe patch is cluttered by moving trigger_irq() higher in the code.\n\nIn practice, two factors make this optimization less interesting:\n(1) we often only get one input at a time, even for networking,\n(2) triggering an interrupt rapidly tends to get coalesced anyway.\n\nBefore:\t\t\t\tSecs\tRxIRQS\tTxIRQs\n 1G TCP Guest-\u003eHost:\t\t3.72\t32784\t32771\n 1M normal pings:\t\t99\t1000004\t995541\n 100,000 1k pings (-l 120):\t5\t49510\t49058\n\nAfter:\n 1G TCP Guest-\u003eHost:\t\t3.69\t32809\t32769\n 1M normal pings:\t\t99\t1000004\t996196\n 100,000 1k pings (-l 120):\t5\t52435\t52361\n\n(Note the interrupt count on 100k pings goes *up*: see next patch).\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n"
    },
    {
      "commit": "5dac051bc6030963181b69faddd9e0ad04f85fa8",
      "tree": "4a0456e1d971bbe9f68f4ac13d31716c12fbb618",
      "parents": [
        "659a0e6633567246edcb7bd400c7e2bece9237d9"
      ],
      "author": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:10 2009 -0600"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:11 2009 +0930"
      },
      "message": "lguest: remove obsolete LHREQ_BREAK call\n\nWe no longer need an efficient mechanism to force the Guest back into\nhost userspace, as each device is serviced without bothering the main\nGuest process (aka. the Launcher).\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n"
    },
    {
      "commit": "659a0e6633567246edcb7bd400c7e2bece9237d9",
      "tree": "2ece97564e432b837389e166d9b61773d34b1063",
      "parents": [
        "df60aeef4f4fe0645d9a195a7689005520422de5"
      ],
      "author": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:10 2009 -0600"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:10 2009 +0930"
      },
      "message": "lguest: have example Launcher service all devices in separate threads\n\nCurrently lguest has three threads: the main Launcher thread, a Waker\nthread, and a thread for the block device (because synchronous block\nwas simply too painful to bear).\n\nThe Waker selects() on all the input file descriptors (eg. stdin, net\ndevices, pipe to the block thread) and when one becomes readable it calls\ninto the kernel to kick the Launcher thread out into userspace, which\nrepeats the poll, services the device(s), and then tells the kernel to\nrelease the Waker before re-entering the kernel to run the Guest.\n\nAlso, to make a slightly-decent network transmit routine, the Launcher\nwould suppress further network interrupts while it set a timer: that\nsignal handler would write to a pipe, which would rouse the Waker\nwhich would prod the Launcher out of the kernel to check the network\ndevice again.\n\nNow we can convert all our virtqueues to separate threads: each one has\na separate eventfd for when the Guest pokes the device, and can trigger\ninterrupts in the Guest directly.\n\nThe linecount shows how much this simplifies, but to really bring it\nhome, here\u0027s an strace analysis of single Guest-\u003eHost ping before:\n\n* Guest sends packet, notifies xmit vq, return control to Launcher\n* Launcher clears notification flag on xmit ring\n* Launcher writes packet to TUN device\n\twritev(4, [{\"\\0\\0\\0\\0\\0\\0\\0\\0\\0\\0\", 10}, {\"\\366\\r\\224`\\2058\\272m\\224vf\\274\\10\\0E\\0\\0T\\0\\0@\\0@\\1\\265\"..., 98}], 2) \u003d 108\n* Launcher sets up interrupt for Guest (xmit ring is empty)\n\twrite(10, \"\\2\\0\\0\\0\\3\\0\\0\\0\", 8) \u003d 0\n* Launcher sets up timer for interrupt mitigation\n\tsetitimer(ITIMER_REAL, {it_interval\u003d{0, 0}, it_value\u003d{0, 505}}, NULL) \u003d 0\n* Launcher re-runs guest\n\tpread64(10, 0xbfa5f4d4, 4, 0) ...\n* Waker notices reply packet in tun device (it was in select)\n\tselect(12, [0 3 4 6 11], NULL, NULL, NULL) \u003d 1 (in [4])\n* Waker kicks Launcher out of guest:\n\tpwrite64(10, \"\\3\\0\\0\\0\\1\\0\\0\\0\", 8, 0) \u003d 0\n* Launcher returns from running guest:\n\t... \u003d -1 EAGAIN (Resource temporarily unavailable)\n* Launcher looks at input fds:\n\tselect(7, [0 3 4 6], NULL, NULL, {0, 0}) \u003d 1 (in [4], left {0, 0})\n* Launcher reads pong from tun device:\n\treadv(4, [{\"\\0\\0\\0\\0\\0\\0\\0\\0\\0\\0\", 10}, {\"\\272m\\224vf\\274\\366\\r\\224`\\2058\\10\\0E\\0\\0T\\364\\26\\0\\0@\"..., 1518}], 2) \u003d 108\n* Launcher injects guest notification:\n\twrite(10, \"\\2\\0\\0\\0\\2\\0\\0\\0\", 8) \u003d 0\n* Launcher rechecks fds:\n\tselect(7, [0 3 4 6], NULL, NULL, {0, 0}) \u003d 0 (Timeout)\n* Launcher clears Waker:\n\tpwrite64(10, \"\\3\\0\\0\\0\\0\\0\\0\\0\", 8, 0) \u003d 0\n* Launcher reruns Guest:\n\tpread64(10, 0xbfa5f4d4, 4, 0) \u003d ? ERESTARTSYS (To be restarted)\n* Signal comes in, uses pipe to wake up Launcher:\n\t--- SIGALRM (Alarm clock) @ 0 (0) ---\n\twrite(8, \"\\0\", 1)       \u003d 1\n\tsigreturn()             \u003d ? (mask now [])\n* Waker sees write on pipe:\n\tselect(12, [0 3 4 6 11], NULL, NULL, NULL) \u003d 1 (in [6])\n* Waker kicks Launcher out of Guest:\n\tpwrite64(10, \"\\3\\0\\0\\0\\1\\0\\0\\0\", 8, 0) \u003d 0\n* Launcher exits from kernel:\n\tpread64(10, 0xbfa5f4d4, 4, 0) \u003d -1 EAGAIN (Resource temporarily unavailable)\n* Launcher looks to see what fd woke it:\n\tselect(7, [0 3 4 6], NULL, NULL, {0, 0}) \u003d 1 (in [6], left {0, 0})\n* Launcher reads timeout fd, sets notification flag on xmit ring\n\tread(6, \"\\0\", 32)       \u003d 1\n* Launcher rechecks fds:\n\tselect(7, [0 3 4 6], NULL, NULL, {0, 0}) \u003d 0 (Timeout)\n* Launcher clears Waker:\n\tpwrite64(10, \"\\3\\0\\0\\0\\0\\0\\0\\0\", 8, 0) \u003d 0\n* Launcher resumes Guest:\n\tpread64(10, \"\\0p\\0\\4\", 4, 0) ....\n\nstrace analysis of single Guest-\u003eHost ping after:\n\n* Guest sends packet, notifies xmit vq, creates event on eventfd.\n* Network xmit thread wakes from read on eventfd:\n\tread(7, \"\\1\\0\\0\\0\\0\\0\\0\\0\", 8)          \u003d 8\n* Network xmit thread writes packet to TUN device\n\twritev(4, [{\"\\0\\0\\0\\0\\0\\0\\0\\0\\0\\0\", 10}, {\"J\\217\\232FI\\37j\\27\\375\\276\\0\\304\\10\\0E\\0\\0T\\0\\0@\\0@\\1\\265\"..., 98}], 2) \u003d 108\n* Network recv thread wakes up from read on tunfd:\n\treadv(4, [{\"\\0\\0\\0\\0\\0\\0\\0\\0\\0\\0\", 10}, {\"j\\27\\375\\276\\0\\304J\\217\\232FI\\37\\10\\0E\\0\\0TiO\\0\\0@\\1\\214\"..., 1518}], 2) \u003d 108\n* Network recv thread sets up interrupt for the Guest\n\twrite(6, \"\\2\\0\\0\\0\\2\\0\\0\\0\", 8) \u003d 0\n* Network recv thread goes back to reading tunfd\n\t13:39:42.460285 readv(4,  \u003cunfinished ...\u003e\n* Network xmit thread sets up interrupt for Guest (xmit ring is empty)\n\twrite(6, \"\\2\\0\\0\\0\\3\\0\\0\\0\", 8) \u003d 0\n* Network xmit thread goes back to reading from eventfd\n\tread(7, \u003cunfinished ...\u003e\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n"
    },
    {
      "commit": "df60aeef4f4fe0645d9a195a7689005520422de5",
      "tree": "3cfa3c4a986436c8accd5f0a57d5a6f70f1b7965",
      "parents": [
        "5718607bb670c721f45f0dbb1cc7d6c64969aab1"
      ],
      "author": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:09 2009 -0600"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:10 2009 +0930"
      },
      "message": "lguest: use eventfds for device notification\n\nCurrently, when a Guest wants to perform I/O it calls LHCALL_NOTIFY with\nan address: the main Launcher process returns with this address, and figures\nout what device to run.\n\nA far nicer model is to let processes bind an eventfd to an address: if we\nfind one, we simply signal the eventfd.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nCc: Davide Libenzi \u003cdavidel@xmailserver.org\u003e\n"
    },
    {
      "commit": "5718607bb670c721f45f0dbb1cc7d6c64969aab1",
      "tree": "9b595af2cd4649bea4c130b9dc223a5f886c34d2",
      "parents": [
        "9f155a9b3d5a5444bcc5e049ec2547bb5107150e"
      ],
      "author": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:09 2009 -0600"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:09 2009 +0930"
      },
      "message": "eventfd: export eventfd_signal and eventfd_fget for lguest\n\nlguest wants to attach eventfds to guest notifications, and lguest is\nusually a module.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nTo: Davide Libenzi \u003cdavidel@xmailserver.org\u003e\n"
    },
    {
      "commit": "9f155a9b3d5a5444bcc5e049ec2547bb5107150e",
      "tree": "ef8fe2d5a319abb3bb1c89374f9d2fef1b0881c3",
      "parents": [
        "92b4d8df8436cdd74d22a2a5b6b23b9abc737a3e"
      ],
      "author": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:08 2009 -0600"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:09 2009 +0930"
      },
      "message": "lguest: allow any process to send interrupts\n\nWe currently only allow the Launcher process to send interrupts, but it\nas we already send interrupts from the hrtimer, it\u0027s a simple matter of\nextracting that code into a common set_interrupt routine.\n\nAs we switch to a thread per virtqueue, this avoids a bottleneck through the\nmain Launcher process.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n"
    },
    {
      "commit": "92b4d8df8436cdd74d22a2a5b6b23b9abc737a3e",
      "tree": "bba0dce08d1fde432f370b7ef2845e0ae195a34d",
      "parents": [
        "acdd0b6292b282c4511897ac2691a47befbf1c6a"
      ],
      "author": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:08 2009 -0600"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:08 2009 +0930"
      },
      "message": "lguest: PAE fixes\n\n1) j wasn\u0027t initialized in setup_pagetables, so they weren\u0027t set up for me\n   causing immediate guest crashes.\n\n2) gpte_addr should not re-read the pmd from the Guest.  Especially\n   not BUG_ON() based on the value.  If we ever supported SMP guests,\n   they could trigger that.  And the Launcher could also trigger it\n   (tho currently root-only).\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n"
    },
    {
      "commit": "acdd0b6292b282c4511897ac2691a47befbf1c6a",
      "tree": "1bfcfc32b11d35e99fec5bbf52b19d6ee038f25e",
      "parents": [
        "cefcad1773197523e11e18b669f245e6a8d32058"
      ],
      "author": {
        "name": "Matias Zabaljauregui",
        "email": "zabaljauregui@gmail.com",
        "time": "Fri Jun 12 22:27:07 2009 -0600"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:08 2009 +0930"
      },
      "message": "lguest: PAE support\n\nThis version requires that host and guest have the same PAE status.\nNX cap is not offered to the guest, yet.\n\nSigned-off-by: Matias Zabaljauregui \u003czabaljauregui@gmail.com\u003e\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n"
    },
    {
      "commit": "cefcad1773197523e11e18b669f245e6a8d32058",
      "tree": "2d94e3df551b3ee58c1ac89ed4872e2153496c05",
      "parents": [
        "ebe0ba84f55950a89cb7af94c7ffc35ee3992f9e"
      ],
      "author": {
        "name": "Matias Zabaljauregui",
        "email": "zabaljauregui@gmail.com",
        "time": "Fri Jun 12 22:27:07 2009 -0600"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:07 2009 +0930"
      },
      "message": "lguest: Add support for kvm_hypercall4()\n\nAdd support for kvm_hypercall4(); PAE wants it.\n\nSigned-off-by: Matias Zabaljauregui \u003czabaljauregui at gmail.com\u003e\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n"
    },
    {
      "commit": "ebe0ba84f55950a89cb7af94c7ffc35ee3992f9e",
      "tree": "df1c3373274846b4998ea75c56f347a264b2c8ad",
      "parents": [
        "90603d15fa95605d1d08235b73e220d766f04bb0"
      ],
      "author": {
        "name": "Matias Zabaljauregui",
        "email": "zabaljauregui@gmail.com",
        "time": "Sat May 30 15:48:08 2009 -0300"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:07 2009 +0930"
      },
      "message": "lguest: replace hypercall name LHCALL_SET_PMD with LHCALL_SET_PGD\n\nreplace LHCALL_SET_PMD with LHCALL_SET_PGD hypercall name\n(That\u0027s really what it is, and the confusion gets worse with PAE support)\n\nSigned-off-by: Matias Zabaljauregui \u003czabaljauregui@gmail.com\u003e\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nReported-by: Jeremy Fitzhardinge \u003cjeremy@goop.org\u003e\n"
    },
    {
      "commit": "90603d15fa95605d1d08235b73e220d766f04bb0",
      "tree": "669b5a41ebdb368e578898409d8a48021074746a",
      "parents": [
        "ed1dc77810159a733240ba6751c1b31023bf8dd7"
      ],
      "author": {
        "name": "Matias Zabaljauregui",
        "email": "zabaljauregui@gmail.com",
        "time": "Fri Jun 12 22:27:06 2009 -0600"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:06 2009 +0930"
      },
      "message": "lguest: use native_set_* macros, which properly handle 64-bit entries when PAE is activated\n\nSome cleanups and replace direct assignment with native_set_* macros which properly handle 64-bit entries when PAE is activated\n\nSigned-off-by: Matias Zabaljauregui \u003czabaljauregui@gmail.com\u003e\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n"
    },
    {
      "commit": "ed1dc77810159a733240ba6751c1b31023bf8dd7",
      "tree": "d77ed52cd56e2cf3f5eac9d5db22ad1196e694d8",
      "parents": [
        "7b5c806c35f6ff76b2e36a8b5b1513c8a83fcff7"
      ],
      "author": {
        "name": "Matias Zabaljauregui",
        "email": "zabaljauregui@gmail.com",
        "time": "Sat May 30 15:35:49 2009 -0300"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:06 2009 +0930"
      },
      "message": "lguest: map switcher with executable page table entries\n\nMap switcher with executable page table entries.\n(This bug didn\u0027t matter before PAE and hence NX support -- RR)\n\nSigned-off-by: Matias Zabaljauregui \u003czabaljauregui@gmail.com\u003e\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n"
    },
    {
      "commit": "7b5c806c35f6ff76b2e36a8b5b1513c8a83fcff7",
      "tree": "382e194aadcae193229c121c60c0d4838255c327",
      "parents": [
        "e606490c440900e50ccf73a54f6fc6150ff40815"
      ],
      "author": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:05 2009 -0600"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:05 2009 +0930"
      },
      "message": "lguest: fix writev returning short on console output\n\nI\u0027ve never seen it here, but I can\u0027t find anywhere that says writev\nwill write everything.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n"
    },
    {
      "commit": "e606490c440900e50ccf73a54f6fc6150ff40815",
      "tree": "43a660399ee81b3926789bd1644513e83c605d50",
      "parents": [
        "f086122bb6e885f926f935b1418fca3b293375f0"
      ],
      "author": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:04 2009 -0600"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:05 2009 +0930"
      },
      "message": "lguest: clean up length-used value in example launcher\n\nThe \"len\" field in the used ring for virtio indicates the number of\nbytes *written* to the buffer.  This means the guest doesn\u0027t have to\nzero the buffers in advance as it always knows the used length.\n\nErroneously, the console and network example code puts the length\n*read* into that field.  The guest ignores it, but it\u0027s wrong.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n"
    },
    {
      "commit": "f086122bb6e885f926f935b1418fca3b293375f0",
      "tree": "21f14d50489380e609ecffb61cdc4f5b2f624694",
      "parents": [
        "81b79b01d057f8c5a378c38d2f738775b972934a"
      ],
      "author": {
        "name": "Matias Zabaljauregui",
        "email": "zabaljauregui@gmail.com",
        "time": "Fri Jun 12 22:27:04 2009 -0600"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:04 2009 +0930"
      },
      "message": "lguest: Segment selectors are 16-bit long. Fix lg_cpu.ss1 definition.\n\nIf GDT_ENTRIES were every \u003e 256, this could become a problem.\n\nSigned-off-by: Matias Zabaljauregui \u003czabaljauregui at gmail.com\u003e\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n"
    },
    {
      "commit": "81b79b01d057f8c5a378c38d2f738775b972934a",
      "tree": "0e2c295109568916e187a65e6d93a3319bbb51a9",
      "parents": [
        "2644f17d6c932929fd68cfec95691490947e0fd1"
      ],
      "author": {
        "name": "Roel Kluin",
        "email": "roel.kluin@gmail.com",
        "time": "Wed May 20 01:45:45 2009 +0200"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:04 2009 +0930"
      },
      "message": "lguest: beyond ARRAY_SIZE of cpu-\u003earch.gdt\n\nDo not go beyond ARRAY_SIZE of cpu-\u003earch.gdt\n\nSigned-off-by: Roel Kluin \u003croel.kluin@gmail.com\u003e\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n"
    },
    {
      "commit": "2644f17d6c932929fd68cfec95691490947e0fd1",
      "tree": "82e3c567fec2c48aa4d5a053da2563e4a2fdcf5a",
      "parents": [
        "61f4bc83fea248a3092beb7ba43daa5629615513"
      ],
      "author": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:03 2009 -0600"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:03 2009 +0930"
      },
      "message": "lguest: clean up example launcher compile flags.\n\n18 months ago 5bbf89fc260830f3f58b331d946a16b39ad1ca2d changed to loading\nbzImages directly, and no longer manually ungzipping them, so we no longer\nneed libz.\n\nAlso, -m32 is useful for those on 64-bit platforms (and harmless on\n32-bit).\n\nReported-by: Ron Minnich \u003crminnich@gmail.com\u003e\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n"
    },
    {
      "commit": "61f4bc83fea248a3092beb7ba43daa5629615513",
      "tree": "5ce12fc0676f93a49f743dab1c60f8e1ca991ec3",
      "parents": [
        "a32a8813d0173163ba44d8f9556e0d89fdc4fb46"
      ],
      "author": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:03 2009 -0600"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:03 2009 +0930"
      },
      "message": "lguest: optimize by coding restore_flags and irq_enable in assembler.\n\nThe downside of the last patch which made restore_flags and irq_enable\ncheck interrupts is that they are now too big to be patched directly\ninto the callsites, so the C versions are always used.\n\nBut the C versions go via PV_CALLEE_SAVE_REGS_THUNK which saves all\nthe registers.  In fact, we don\u0027t need any registers in the fast path,\nso we can do better than this if we actually code them in assembler.\n\nThe results are in the noise, but since it\u0027s about the same amount of\ncode, it\u0027s worth applying.\n\n1GB Guest-\u003eHost: input(suppressed),output(suppressed)\nBefore:\n\tSeconds: 0:16.53\n\tPackets: 377268,753673\n\tInterrupts: 22461,24297\n\tNotifications: 1(5245),21303(732370)\n\tNet IRQs triggered: 377023(245),42578(711095)\n\nAfter:\n\tSeconds: 0:16.48\n\tPackets: 377289,753673\n\tInterrupts: 22281,24465\n\tNotifications: 1(5245),21296(732377)\n\tNet IRQs triggered: 377060(229),42564(711109)\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n"
    },
    {
      "commit": "a32a8813d0173163ba44d8f9556e0d89fdc4fb46",
      "tree": "fddb6742338047d0219e8c2536cd39b04e643b16",
      "parents": [
        "abd41f037e1a64543000ed73b42f616d04d92700"
      ],
      "author": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:02 2009 -0600"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:03 2009 +0930"
      },
      "message": "lguest: improve interrupt handling, speed up stream networking\n\nlguest never checked for pending interrupts when enabling interrupts, and\nthings still worked.  However, it makes a significant difference to TCP\nperformance, so it\u0027s time we fixed it by introducing a pending_irq flag\nand checking it on irq_restore and irq_enable.\n\nThese two routines are now too big to patch into the 8/10 bytes\npatch space, so we drop that code.\n\nNote: The high latency on interrupt delivery had a very curious\neffect: once everything else was optimized, networking without GSO was\nfaster than networking with GSO, since more interrupts were sent and\nhence a greater chance of one getting through to the Guest!\n\nNote2: (Almost) Closing the same loophole for iret doesn\u0027t have any\nmeasurable effect, so I\u0027m leaving that patch for the moment.\n\nBefore:\n\t1GB tcpblast Guest-\u003eHost:\t\t30.7 seconds\n\t1GB tcpblast Guest-\u003eHost (no GSO):\t76.0 seconds\n\nAfter:\n\t1GB tcpblast Guest-\u003eHost:\t\t6.8 seconds\n\t1GB tcpblast Guest-\u003eHost (no GSO):\t27.8 seconds\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n"
    },
    {
      "commit": "abd41f037e1a64543000ed73b42f616d04d92700",
      "tree": "d9013e66f4d8fc66fc92ce0587f8d126e156b253",
      "parents": [
        "ebf9a5a99c1a464afe0b4dfa64416fc8b273bc5c"
      ],
      "author": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:02 2009 -0600"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:02 2009 +0930"
      },
      "message": "lguest: fix race in halt code\n\nWhen the Guest does the LHCALL_HALT hypercall, we go to sleep, expecting\nthat a timer or the Waker will wake_up_process() us.\n\nBut we do it in a stupid way, leaving a classic missing wakeup race.\n\nSo split maybe_do_interrupt() into interrupt_pending() and\ntry_deliver_interrupt(), and check maybe_do_interrupt() and the\n\"break_out\" flag before calling schedule.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n"
    },
    {
      "commit": "ebf9a5a99c1a464afe0b4dfa64416fc8b273bc5c",
      "tree": "b5f0631172db5d97e0a5c6b8a6bc0f83c4a4eed5",
      "parents": [
        "a6c372de6e4b9a8188b66badcee3e3792eccdd26"
      ],
      "author": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:01 2009 -0600"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:02 2009 +0930"
      },
      "message": "lguest: remove invalid interrupt forcing logic.\n\n20887611523e749d99cc7d64ff6c97d27529fbae (lguest: notify on empty) introduced\nlguest support for the VIRTIO_F_NOTIFY_ON_EMPTY flag, but in fact it turned on\ninterrupts all the time.\n\nBecause we always process one buffer at a time, the inflight count is always 0\nwhen call trigger_irq and so we always ignore VRING_AVAIL_F_NO_INTERRUPT from\nthe Guest.\n\nIt should be looking to see if there are more buffers in the Guest\u0027s queue:\nif it\u0027s empty, then we force an interrupt.\n\nThis makes little difference, since we usually have an empty queue; but\nthat\u0027s the subject of another patch.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n"
    },
    {
      "commit": "a6c372de6e4b9a8188b66badcee3e3792eccdd26",
      "tree": "b6b67f4cc447cc0ee8ae617bb503ef7d7f6e4958",
      "parents": [
        "b43e352139f51216a8c56b0bd5fc3d4e05c65619"
      ],
      "author": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:01 2009 -0600"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:01 2009 +0930"
      },
      "message": "lguest: fix lguest wake on guest clock tick, or fd activity\n\nThe Launcher could be inside the Guest on another CPU; wake_up_process\nwill do nothing because it is \"running\".  kick_process will knock it\nback into our kernel in this case, otherwise we\u0027ll miss it until the\nnext guest exit.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n"
    },
    {
      "commit": "b43e352139f51216a8c56b0bd5fc3d4e05c65619",
      "tree": "f7766a7d5dc21e424bc914c99e03a4816a35d78a",
      "parents": [
        "f7027c6387d0c3acf569845165ec7947e2083c82"
      ],
      "author": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:00 2009 -0600"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:01 2009 +0930"
      },
      "message": "sched: export kick_process\n\nlguest needs kick_process: wake_up_process() does nothing if a process\nis running, which isn\u0027t sufficient (we need it in the kernel).\n\nAnd lguest support is usually modular.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\n"
    },
    {
      "commit": "f7027c6387d0c3acf569845165ec7947e2083c82",
      "tree": "306f36650d615491d468e040d7055b07053d2fb6",
      "parents": [
        "1028375e93a7aa4dbe466947d1c65f368b1f61c1"
      ],
      "author": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:00 2009 -0600"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:00 2009 +0930"
      },
      "message": "lguest: get more serious about wmb() in example Launcher code\n\nSince the Launcher process runs the Guest, it doesn\u0027t have to be very\nserious about its barriers: the Guest isn\u0027t running while we are (Guest\nis UP).\n\nBefore we change to use threads to service devices, we need to fix this.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n"
    },
    {
      "commit": "1028375e93a7aa4dbe466947d1c65f368b1f61c1",
      "tree": "33199b0bb9c79fded3159b880d8ad9e0e6bcb28c",
      "parents": [
        "56739c802ca845435f60e909104637880e14c769"
      ],
      "author": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:26:59 2009 -0600"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:27:00 2009 +0930"
      },
      "message": "lguest: clean up lguest_init_IRQ\n\nCopy from arch/x86/kernel/irqinit_32.c: we don\u0027t use the vectors beyond\nLGUEST_IRQS (if any), but we might as well set them all.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n"
    },
    {
      "commit": "56739c802ca845435f60e909104637880e14c769",
      "tree": "3831f2b7e2c973b11e2f9823002340420fbc327b",
      "parents": [
        "713b15b3781240653d2b38414da3f4567dcbcf91"
      ],
      "author": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:26:59 2009 -0600"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:26:59 2009 +0930"
      },
      "message": "lguest: cleanup passing of /dev/lguest fd around example launcher.\n\nWe hand the /dev/lguest fd everywhere; it\u0027s far neater to just make it\na global (it already is, in fact, hidden in the waker_fds struct).\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n"
    },
    {
      "commit": "713b15b3781240653d2b38414da3f4567dcbcf91",
      "tree": "9b6a01f00bf4aee60548d8b8cf38458863888564",
      "parents": [
        "8ebf975608aaebd7feb33d77f07ba21a6380e086"
      ],
      "author": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:26:58 2009 -0600"
      },
      "committer": {
        "name": "Rusty Russell",
        "email": "rusty@rustcorp.com.au",
        "time": "Fri Jun 12 22:26:59 2009 +0930"
      },
      "message": "lguest: be paranoid about guest playing with device descriptors.\n\nWe can\u0027t trust the values in the device descriptor table once the\nguest has booted, so keep local copies.  They could set them to\nstrange values then cause us to segv (they\u0027re 8 bit values, so they\ncan\u0027t make our pointers go too wild).\n\nThis becomes more important with the following patches which read them.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n"
    },
    {
      "commit": "8ebf975608aaebd7feb33d77f07ba21a6380e086",
      "tree": "6de4ee1dd3ede890169644ea586ed7c8c9d8f7b2",
      "parents": [
        "4b4f1d017815f96737ca4a62f90e5a1f0b9f02d6"
      ],
      "author": {
        "name": "Randy Dunlap",
        "email": "randy.dunlap@oracle.com",
        "time": "Thu Jun 11 20:00:41 2009 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Thu Jun 11 20:14:23 2009 -0700"
      },
      "message": "block: fix kernel-doc in recent block/ changes\n\nFix kernel-doc warnings in recently changed block/ source code.\n\nSigned-off-by: Randy Dunlap \u003crandy.dunlap@oracle.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "4b4f1d017815f96737ca4a62f90e5a1f0b9f02d6",
      "tree": "c95ae92ec01cabf6c2a40d31a31da6a4d9256816",
      "parents": [
        "875287caa067492779670f5fb3b98ec8dcfe2cb0",
        "aa7dfb8954ccf49e026ba13d12991a4eb7defb96"
      ],
      "author": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Thu Jun 11 20:05:37 2009 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Thu Jun 11 20:05:37 2009 -0700"
      },
      "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6\n\n* \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6: (87 commits)\n  nilfs2: get rid of bd_mount_sem use from nilfs\n  nilfs2: correct exclusion control in nilfs_remount function\n  nilfs2: simplify remaining sget() use\n  nilfs2: get rid of sget use for checking if current mount is present\n  nilfs2: get rid of sget use for acquiring nilfs object\n  nilfs2: remove meaningless EBUSY case from nilfs_get_sb function\n  remove the call to -\u003ewrite_super in __sync_filesystem\n  nilfs2: call nilfs2_write_super from nilfs2_sync_fs\n  jffs2: call jffs2_write_super from jffs2_sync_fs\n  ufs: add -\u003esync_fs\n  sysv: add -\u003esync_fs\n  hfsplus: add -\u003esync_fs\n  hfs: add -\u003esync_fs\n  fat: add -\u003esync_fs\n  ext2: add -\u003esync_fs\n  exofs: add -\u003esync_fs\n  bfs: add -\u003esync_fs\n  affs: add -\u003esync_fs\n  sanitize -\u003efsync() for affs\n  repair bfs_write_inode(), switch bfs to simple_fsync()\n  ...\n"
    },
    {
      "commit": "875287caa067492779670f5fb3b98ec8dcfe2cb0",
      "tree": "258037cc7678cfaeb738b970b4791ea10e193c96",
      "parents": [
        "aee74f3bb3f4fb5dbeae8c1947c6d8ebdc19ee01",
        "193e98401a89707ea374e9c32c1b9a5a9dd87a48"
      ],
      "author": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Thu Jun 11 20:05:08 2009 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Thu Jun 11 20:05:08 2009 -0700"
      },
      "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/gerg/m68knommu\n\n* \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/gerg/m68knommu:\n  m68knommu: remove unecessary include of thread_info.h in entry.S\n  m68knommu: enumerate INIT_THREAD fields properly\n  headers_check fix: m68k, swab.h\n  arch/m68knommu: Convert #ifdef DEBUG printk(KERN_DEBUG to pr_debug(\n  m68knommu: remove obsolete reset code\n  m68knommu: move CPU reset code for the 5272 ColdFire into its platform code\n  m68knommu: move CPU reset code for the 528x ColdFire into its platform code\n  m68knommu: move CPU reset code for the 527x ColdFire into its platform code\n  m68knommu: move CPU reset code for the 523x ColdFire into its platform code\n  m68knommu: move CPU reset code for the 520x ColdFire into its platform code\n  m68knommu: add CPU reset code for the 532x ColdFire\n  m68knommu: add CPU reset code for the 5249 ColdFire\n  m68knommu: add CPU reset code for the 5206e ColdFire\n  m68knommu: add CPU reset code for the 5206 ColdFire\n  m68knommu: add CPU reset code for the 5407 ColdFire\n  m68knommu: add CPU reset code for the 5307 ColdFire\n  m68knommu: merge system reset for code ColdFire 523x family\n  m68knommu: fix system reset for ColdFire 527x family\n"
    },
    {
      "commit": "aee74f3bb3f4fb5dbeae8c1947c6d8ebdc19ee01",
      "tree": "fd86fd5a4f8adf8d185c1bfb8972253570958cdf",
      "parents": [
        "12274e96b42884f043dfaa87eb1e5e10281bfac3"
      ],
      "author": {
        "name": "Yinghai Lu",
        "email": "yinghai@kernel.org",
        "time": "Thu Jun 11 15:09:00 2009 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Thu Jun 11 20:04:37 2009 -0700"
      },
      "message": "kvm: remove the duplicated cpumask_clear\n\nzalloc_cpumask_var already cleared it.\n\nSigned-off-by: Yinghai Lu \u003cyinghai@kernel.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "12274e96b42884f043dfaa87eb1e5e10281bfac3",
      "tree": "7171d6a49dbac49826670128e114c52e7539782d",
      "parents": [
        "e14112d1bd5e193166b54be19119cf6440470560"
      ],
      "author": {
        "name": "Yinghai Lu",
        "email": "yinghai@kernel.org",
        "time": "Thu Jun 11 15:07:48 2009 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Thu Jun 11 20:04:36 2009 -0700"
      },
      "message": "x86: use zalloc_cpumask_var in arch_early_irq_init\n\nSo we make sure MAXSMP gets a cleared cpumask\n\nSigned-off-by: Yinghai Lu \u003cyinghai@kernel.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "e14112d1bd5e193166b54be19119cf6440470560",
      "tree": "7e38942535b91872b5f9869a1e6597add34c60cc",
      "parents": [
        "a525890cb6a2949b644d212ae290b658967d3919"
      ],
      "author": {
        "name": "Stephen Rothwell",
        "email": "sfr@canb.auug.org.au",
        "time": "Fri Jun 12 10:14:22 2009 +1000"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Thu Jun 11 20:03:13 2009 -0700"
      },
      "message": "perfcounters: remove powerpc definitions of perf_counter_do_pending\n\nCommit 925d519ab82b6dd7aca9420d809ee83819c08db2 (\"perf_counter:\nunify and fix delayed counter wakeup\") added global definitions.\n\nSigned-off-by: Stephen Rothwell \u003csfr@canb.auug.org.au\u003e\nAcked-by: Paul Mackerras \u003cpaulus@samba.org\u003e\nAcked-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "aa7dfb8954ccf49e026ba13d12991a4eb7defb96",
      "tree": "ff2d6cf81629322906bd0cea1423e9efe516ffee",
      "parents": [
        "e59399d0102c1813cec48db5cebe1750313f88a0"
      ],
      "author": {
        "name": "Ryusuke Konishi",
        "email": "konishi.ryusuke@lab.ntt.co.jp",
        "time": "Mon Jun 08 01:39:33 2009 +0900"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:18 2009 -0400"
      },
      "message": "nilfs2: get rid of bd_mount_sem use from nilfs\n\nThis will remove every bd_mount_sem use in nilfs.\n\nThe intended exclusion control was replaced by the previous patch\n(\"nilfs2: correct exclusion control in nilfs_remount function\") for\nnilfs_remount(), and this patch will replace remains with a new mutex\nthat this inserts in nilfs object.\n\nSigned-off-by: Ryusuke Konishi \u003ckonishi.ryusuke@lab.ntt.co.jp\u003e\nCc: Christoph Hellwig \u003chch@infradead.org\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "e59399d0102c1813cec48db5cebe1750313f88a0",
      "tree": "cd4fde6b5c442ede5d00b9640d3a545f847aeb8c",
      "parents": [
        "6dd4740662405a68bb229ac2b9e0aeaaf2188bf2"
      ],
      "author": {
        "name": "Ryusuke Konishi",
        "email": "konishi.ryusuke@lab.ntt.co.jp",
        "time": "Mon Jun 08 01:39:32 2009 +0900"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:18 2009 -0400"
      },
      "message": "nilfs2: correct exclusion control in nilfs_remount function\n\nnilfs_remount() changes mount state of a superblock instance.  Even\nthough nilfs accesses other superblock instances during mount or\nremount, the mount state was not properly protected in\nnilfs_remount().\n\nMoreover, nilfs_remount() has a lock order reversal problem;\nnilfs_get_sb() holds:\n\n  1. bdev-\u003ebd_mount_sem\n  2. sb-\u003es_umount  (sget acquires)\n\nand nilfs_remount() holds:\n\n  1. sb-\u003es_umount  (locked by the caller in vfs)\n  2. bdev-\u003ebd_mount_sem\n\nTo avoid these problems, this patch divides a semaphore protecting\nsuper block instances from nilfs-\u003ens_sem, and applies it to the mount\nstate protection in nilfs_remount().\n\nWith this change, bd_mount_sem use is removed from nilfs_remount() and\nthe lock order reversal will be resolved.  And the new rw-semaphore,\nnilfs-\u003ens_super_sem will properly protect the mount state except the\nmodification from nilfs_error function.\n\nSigned-off-by: Ryusuke Konishi \u003ckonishi.ryusuke@lab.ntt.co.jp\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "6dd4740662405a68bb229ac2b9e0aeaaf2188bf2",
      "tree": "36e6ae2a095613be1c36e8828ee9471e60c09de6",
      "parents": [
        "3f82ff55168e92859119bf348e9e0bd6714d2fea"
      ],
      "author": {
        "name": "Ryusuke Konishi",
        "email": "konishi.ryusuke@lab.ntt.co.jp",
        "time": "Mon Jun 08 01:39:31 2009 +0900"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:18 2009 -0400"
      },
      "message": "nilfs2: simplify remaining sget() use\n\nThis simplifies the test function passed on the remaining sget()\ncallsite in nilfs.\n\nInstead of checking mount type (i.e. ro-mount/rw-mount/snapshot mount)\nin the test function passed to sget(), this patch first looks up the\nnilfs_sb_info struct which the given mount type matches, and then\nacquires the super block instance holding the nilfs_sb_info.\n\nSigned-off-by: Ryusuke Konishi \u003ckonishi.ryusuke@lab.ntt.co.jp\u003e\nCc: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "3f82ff55168e92859119bf348e9e0bd6714d2fea",
      "tree": "f35bf723b02d6fe8c101252aa4a2c0e0172fd4aa",
      "parents": [
        "33c8e57c86d1bd1548c12a4f7c4bceb94b862cca"
      ],
      "author": {
        "name": "Ryusuke Konishi",
        "email": "konishi.ryusuke@lab.ntt.co.jp",
        "time": "Mon Jun 08 01:39:30 2009 +0900"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:17 2009 -0400"
      },
      "message": "nilfs2: get rid of sget use for checking if current mount is present\n\nThis stops using sget() for checking if an r/w-mount or an r/o-mount\nexists on the device.  This elimination uses a back pointer to the\ncurrent mount added to nilfs object.\n\nSigned-off-by: Ryusuke Konishi \u003ckonishi.ryusuke@lab.ntt.co.jp\u003e\nCc: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "33c8e57c86d1bd1548c12a4f7c4bceb94b862cca",
      "tree": "8e2052a81dc1036e64d78da1082ab6af01ae4bbd",
      "parents": [
        "81fc20bd0e75ba6357bce2403767d7c2585d8f28"
      ],
      "author": {
        "name": "Ryusuke Konishi",
        "email": "konishi.ryusuke@lab.ntt.co.jp",
        "time": "Mon Jun 08 01:39:29 2009 +0900"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:17 2009 -0400"
      },
      "message": "nilfs2: get rid of sget use for acquiring nilfs object\n\nThis will change the way to obtain nilfs object in nilfs_get_sb()\nfunction.\n\nPreviously, a preliminary sget() call was performed, and the nilfs\nobject was acquired from a super block instance found by the sget()\ncall.\n\nThis patch, instead, instroduces a new dedicated function\nfind_or_create_nilfs(); as the name implies, the function finds an\nexistent nilfs object from a global list or creates a new one if no\nobject is found on the device.\n\nSigned-off-by: Ryusuke Konishi \u003ckonishi.ryusuke@lab.ntt.co.jp\u003e\nCc: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "81fc20bd0e75ba6357bce2403767d7c2585d8f28",
      "tree": "e3680d7c8184da3cbb4b7efe83fe99626d08cd68",
      "parents": [
        "0c95ee190e1dea60c55c834d14695341085c9b7b"
      ],
      "author": {
        "name": "Ryusuke Konishi",
        "email": "konishi.ryusuke@lab.ntt.co.jp",
        "time": "Mon Jun 08 01:39:28 2009 +0900"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:17 2009 -0400"
      },
      "message": "nilfs2: remove meaningless EBUSY case from nilfs_get_sb function\n\nThe following EBUSY case in nilfs_get_sb() is meaningless.  Indeed,\nthis error code is never returned to the caller.\n\n    if (!s-\u003es_root) {\n          ...\n    } else if (!(s-\u003es_flags \u0026 MS_RDONLY)) {\n        err \u003d -EBUSY;\n    }\n\nThis simply removes the else case.\n\nSigned-off-by: Ryusuke Konishi \u003ckonishi.ryusuke@lab.ntt.co.jp\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "0c95ee190e1dea60c55c834d14695341085c9b7b",
      "tree": "2d0899f7aa04acc0679a760e6710c8605745ac92",
      "parents": [
        "d731e06323cb705003e4172ec209e469be4c18e1"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Mon Jun 08 10:08:54 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:17 2009 -0400"
      },
      "message": "remove the call to -\u003ewrite_super in __sync_filesystem\n\nNow that all filesystems provide -\u003esync_fs methods we can change\n__sync_filesystem to only call -\u003esync_fs.\n\nThis gives us a clear separation between periodic writeouts which\nare driven by -\u003ewrite_super and data integrity syncs that go\nthrough -\u003esync_fs. (modulo file_fsync which is also going away)\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "d731e06323cb705003e4172ec209e469be4c18e1",
      "tree": "636b1b2f7aaea08fa7be27b3d908fe6dbe6ec70b",
      "parents": [
        "d579ed00aa96a7f7486978540a0d7cecaff742ae"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Mon Jun 08 10:08:36 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:17 2009 -0400"
      },
      "message": "nilfs2: call nilfs2_write_super from nilfs2_sync_fs\n\nThe call to -\u003ewrite_super from __sync_filesystem will go away, so make\nsure nilfs2 performs the same actions from inside -\u003esync_fs.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "d579ed00aa96a7f7486978540a0d7cecaff742ae",
      "tree": "a1c988e4f97ea9e3750779ff9cfa0f12d95386e4",
      "parents": [
        "8c8006564a58d0ea912bf7f2d0a758d97e4b464f"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Mon Jun 08 10:08:21 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:16 2009 -0400"
      },
      "message": "jffs2: call jffs2_write_super from jffs2_sync_fs\n\nThe call to -\u003ewrite_super from __sync_filesystem will go away, so make\nsure jffs2 performs the same actions from inside -\u003esync_fs.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "8c8006564a58d0ea912bf7f2d0a758d97e4b464f",
      "tree": "696dd67b5b2c3e303fe17bf992ced9ccb4b34806",
      "parents": [
        "ad43ffdeea0a7bd3e6036c4aeec2e6699aef8ac7"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Mon Jun 08 10:08:05 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:16 2009 -0400"
      },
      "message": "ufs: add -\u003esync_fs\n\nAdd a -\u003esync_fs method for data integrity syncs, and reimplement\n-\u003ewrite_super ontop of it.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "ad43ffdeea0a7bd3e6036c4aeec2e6699aef8ac7",
      "tree": "dcab8568dca72f130287dbe356c0fe0d7afe4ab7",
      "parents": [
        "7fbc6df0e7a561a313f49faa77829d5de45a97f8"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Mon Jun 08 10:07:45 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:16 2009 -0400"
      },
      "message": "sysv: add -\u003esync_fs\n\nAdd a -\u003esync_fs method for data integrity syncs, and reimplement\n-\u003ewrite_super ontop of it.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "7fbc6df0e7a561a313f49faa77829d5de45a97f8",
      "tree": "c19d60ff362527ce66489d2fdbecc34a89b0a0ef",
      "parents": [
        "58bc5bbb873eb5d86126a3fd3ff02aaa69ec15d0"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Mon Jun 08 10:05:12 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:16 2009 -0400"
      },
      "message": "hfsplus: add -\u003esync_fs\n\nAdd a -\u003esync_fs method for data integrity syncs, and reimplement\n-\u003ewrite_super ontop of it.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "58bc5bbb873eb5d86126a3fd3ff02aaa69ec15d0",
      "tree": "ecc9df2d1205d031cdca77f0d2fb4cd588621f3e",
      "parents": [
        "f83d6d46e7adf241a064a4a425e5cd8a8fd8925f"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Mon Jun 08 10:04:54 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:15 2009 -0400"
      },
      "message": "hfs: add -\u003esync_fs\n\nAdd a -\u003esync_fs method for data integrity syncs.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "f83d6d46e7adf241a064a4a425e5cd8a8fd8925f",
      "tree": "3ebefc6dc784ec0156fd3a074b694630b5a88d88",
      "parents": [
        "40f31dd47e7c3d15af1f9845eda0fa0c4c33f32f"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Mon Jun 08 10:04:35 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:15 2009 -0400"
      },
      "message": "fat: add -\u003esync_fs\n\nAdd a -\u003esync_fs method for data integrity syncs.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "40f31dd47e7c3d15af1f9845eda0fa0c4c33f32f",
      "tree": "f711eb7629ced0f4ffd3cfb47eb69a9717143559",
      "parents": [
        "80e09fb942d38beb19dcffbeb14d496beeb0a989"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Mon Jun 08 10:04:17 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:15 2009 -0400"
      },
      "message": "ext2: add -\u003esync_fs\n\nAdd a -\u003esync_fs method for data integrity syncs, and reimplement\n-\u003ewrite_super ontop of it.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "80e09fb942d38beb19dcffbeb14d496beeb0a989",
      "tree": "cdaa5cf4baf745ee4c83b8e03cb75581e7ea1ffa",
      "parents": [
        "561e47ce7244168788d4ecef9a2271df204b3c89"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Mon Jun 08 10:03:58 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:15 2009 -0400"
      },
      "message": "exofs: add -\u003esync_fs\n\nAdd a -\u003esync_fs method for data integrity syncs, and reimplement\n-\u003ewrite_super ontop of it.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "561e47ce7244168788d4ecef9a2271df204b3c89",
      "tree": "b587db305924ff4fea0ca1ad18b341dfda65281e",
      "parents": [
        "e28964365faf3b9961695eb62b48cbc9f2a2a245"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Mon Jun 08 10:03:38 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:14 2009 -0400"
      },
      "message": "bfs: add -\u003esync_fs\n\nAdd a -\u003esync_fs method for data integrity syncs, and reimplement\n-\u003ewrite_super ontop of it.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "e28964365faf3b9961695eb62b48cbc9f2a2a245",
      "tree": "413a1bfac3009e2f9a370b8f709c37b1ea8878d0",
      "parents": [
        "c475879556a8602bbe2faa9a06f6e5fcc8c05bb2"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Mon Jun 08 10:03:15 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:14 2009 -0400"
      },
      "message": "affs: add -\u003esync_fs\n\nAdd a -\u003esync_fs method for data integrity syncs.  Factor out common code\nbetween affs_put_super, affs_write_super and the new affs_sync_fs into\na helper.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "c475879556a8602bbe2faa9a06f6e5fcc8c05bb2",
      "tree": "9d7e4882a08171d1ff1b84e3f02d3e604756815b",
      "parents": [
        "4427f0c36e22e2cd6696b2fe7643e9756a14b3d3"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Mon Jun 08 01:22:00 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:14 2009 -0400"
      },
      "message": "sanitize -\u003efsync() for affs\n\nunfortunately, for affs (especially for affs directories) we have\nno real way to keep track of metadata ownership.  So we have to\ndo more or less what file_fsync() does, but we do *not* need to\ncall write_super() there.\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "4427f0c36e22e2cd6696b2fe7643e9756a14b3d3",
      "tree": "1d3035350178d974a1099b7795dc4a5f64b29fe8",
      "parents": [
        "224c886643e52e6b4c1143489cd0b289b6c03976"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Mon Jun 08 01:15:58 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:14 2009 -0400"
      },
      "message": "repair bfs_write_inode(), switch bfs to simple_fsync()\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "224c886643e52e6b4c1143489cd0b289b6c03976",
      "tree": "62b7ca28fa19649acc39eb25f9b9c439a07ba87b",
      "parents": [
        "ffdc9064f8b4fa9db37a7d5180f41cce2ea2b7ad"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Mon Jun 08 00:46:40 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:14 2009 -0400"
      },
      "message": "Fix adfs GET_FRAG_ID() on big-endian\n\nMissing conversion to host-endian before doing shifts\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "ffdc9064f8b4fa9db37a7d5180f41cce2ea2b7ad",
      "tree": "a7cc3f3940211682289983865e453b4d7083554b",
      "parents": [
        "bea6b64c277f0824cdaea6190209b26a164419d6"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Mon Jun 08 00:44:42 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:13 2009 -0400"
      },
      "message": "repair adfs -\u003ewrite_inode(), switch to simple_fsync()\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "bea6b64c277f0824cdaea6190209b26a164419d6",
      "tree": "0eebdf31c3faf13d5ed7cc81f9e5e253dd4afe54",
      "parents": [
        "90de066443a8632bb42fed0a8216313d7da07aba"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sun Jun 07 15:44:50 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:13 2009 -0400"
      },
      "message": "switch omfs to simple_fsync()\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "90de066443a8632bb42fed0a8216313d7da07aba",
      "tree": "7ee2fb0e0a87fd83cf7cce88e1044293fc438fc0",
      "parents": [
        "a932801543fe74050ebee07fde082234c46b624f"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sun Jun 07 15:40:27 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:13 2009 -0400"
      },
      "message": "switch udf to simple_fsync()\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "a932801543fe74050ebee07fde082234c46b624f",
      "tree": "2cda35832500fd0003a467b685fd9fb82968db73",
      "parents": [
        "05459ca81ac3064cb040d983342bc453cccec458"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sun Jun 07 15:35:18 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:13 2009 -0400"
      },
      "message": "switch ufs to simple_fsync()\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "05459ca81ac3064cb040d983342bc453cccec458",
      "tree": "3f563253b1d980a24659fcf0967be3b57ec020c5",
      "parents": [
        "0d7916d7e985da52cdd2989c900485e17b035972"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sun Jun 07 15:29:45 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:12 2009 -0400"
      },
      "message": "repair sysv_write_inode(), switch sysv to simple_fsync()\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "0d7916d7e985da52cdd2989c900485e17b035972",
      "tree": "dfb4992f5150ece7ebb09754501e9e5981bb12ca",
      "parents": [
        "e1740a462ecb2eae213be15857b577cc6f6bb8b4"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sun Jun 07 15:21:06 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:12 2009 -0400"
      },
      "message": "switch minix to simple_fsync()\n\n* get minix_write_inode() to honour the second argument\n* now we can use simple_fsync() for minixfs\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "e1740a462ecb2eae213be15857b577cc6f6bb8b4",
      "tree": "8ac67062735e9bbf6ec9ef450ba3a7e5a74405f1",
      "parents": [
        "b522412aeabadbb302fd4338eaabf09d10e2d29c"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sun Jun 07 15:14:02 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:12 2009 -0400"
      },
      "message": "switch ext2 to simple_fsync()\n\nkill ext2_sync_file() (along with ext2/fsync.c), get rid of\next2_update_inode() - it\u0027s an alias of ext2_write_inode().\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "b522412aeabadbb302fd4338eaabf09d10e2d29c",
      "tree": "6b6b73686bc77e10a3a8275e84bc545ddf7755b6",
      "parents": [
        "964f5369667b342994fe3f384e9ba41d404ee796"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sun Jun 07 13:44:36 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:12 2009 -0400"
      },
      "message": "Sanitize -\u003efsync() for FAT\n\n* mark directory data blocks as assoc. metadata\n* add new inode to deal with FAT, mark FAT blocks as assoc. metadata of that\n* now -\u003efsync() is trivial both for files and directories\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "964f5369667b342994fe3f384e9ba41d404ee796",
      "tree": "ad8a5f942af0696d69fb58abf05773c19d05e58b",
      "parents": [
        "79d25767583e4e086f8309bfd1f502660a64fe7f"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sun Jun 07 09:47:13 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:12 2009 -0400"
      },
      "message": "fs/qnx4: sanitize includes\n\nfs-internal parts of qnx4_fs.h taken to fs/qnx4/qnx4.h, includes adjusted,\nqnx4_fs.h doesn\u0027t need unifdef anymore.\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "79d25767583e4e086f8309bfd1f502660a64fe7f",
      "tree": "f13414f324d859f82c604bb4027a4aab19bed909",
      "parents": [
        "d5aacad548db1ff547adf35d0a77eb2a8ed4fe14"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sun Jun 07 09:30:08 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:11 2009 -0400"
      },
      "message": "Sanitize qnx4 fsync handling\n\n* have directory operations use mark_buffer_dirty_inode(),\n  so that sync_mapping_buffers() would get those.\n* make qnx4_write_inode() honour its last argument.\n* get rid of insane copies of very ancient \"walk the indirect blocks\"\n  in qnx4/fsync - they never matched the actual fs layout and, fortunately,\n  never\u0027d been called.  Again, all this junk is not needed; -\u003efsync()\n  should just do sync_mapping_buffers + sync_inode (and if we implement\n  block allocation for qnx4, we\u0027ll need to use mark_buffer_dirty_inode()\n  for extent blocks)\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "d5aacad548db1ff547adf35d0a77eb2a8ed4fe14",
      "tree": "fbdf12dbacde76a1bb57738f1f67b87a673ddff2",
      "parents": [
        "337eb00a2c3a421999c39c94ce7e33545ee8baa7"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sun Jun 07 14:56:44 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:11 2009 -0400"
      },
      "message": "New helper - simple_fsync()\n\nwrites associated buffers, then does sync_inode() to write\nthe inode itself (and to make it clean).  Depends on\n-\u003ewrite_inode() honouring the second argument.\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "337eb00a2c3a421999c39c94ce7e33545ee8baa7",
      "tree": "d9b780d095b638b1d8fa23841ff70347cf5daa08",
      "parents": [
        "4195f73d1329e49727bcceb028e58cb38376c2b0"
      ],
      "author": {
        "name": "Alessio Igor Bogani",
        "email": "abogani@texware.it",
        "time": "Tue May 12 15:10:54 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:11 2009 -0400"
      },
      "message": "Push BKL down into -\u003eremount_fs()\n\n[xfs, btrfs, capifs, shmem don\u0027t need BKL, exempt]\n\nSigned-off-by: Alessio Igor Bogani \u003cabogani@texware.it\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "4195f73d1329e49727bcceb028e58cb38376c2b0",
      "tree": "b4c729c164d6907e4186f6dc51e319a604dee416",
      "parents": [
        "545b9fd3d737afc0bb5203b1e79194a471605acd"
      ],
      "author": {
        "name": "Nick Piggin",
        "email": "npiggin@suse.de",
        "time": "Thu May 28 09:01:15 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:10 2009 -0400"
      },
      "message": "fs: block_dump missing dentry locking\n\nI think the block_dump output in __mark_inode_dirty is missing dentry locking.\nSurely the i_dentry list can change any time, so we may not even *get* a\ndentry there. If we do get one by chance, then it would appear to be able to\ngo away or get renamed at any time...\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "545b9fd3d737afc0bb5203b1e79194a471605acd",
      "tree": "9b9a39b55c3145a225c5256ff2be3b07a1ee43bb",
      "parents": [
        "8688b8635266cf98f00c6b0350ea2dbe7c42c321"
      ],
      "author": {
        "name": "Nick Piggin",
        "email": "npiggin@suse.de",
        "time": "Tue Jun 02 12:07:47 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:10 2009 -0400"
      },
      "message": "fs: remove incorrect I_NEW warnings\n\nSome filesystems can call in to sync an inode that is still in the\nI_NEW state (eg. ext family, when mounted with -osync). This is OK\nbecause the filesystem has sole access to the new inode, so it can\nmodify i_state without races (because no other thread should be\nmodifying it, by definition of I_NEW). Ie. a false positive, so\nremove the warnings.\n\nThe races are described here 7ef0d7377cb287e08f3ae94cebc919448e1f5dff,\nwhich is also where the warnings were introduced.\n\nReported-by: Stephen Hemminger \u003cshemminger@vyatta.com\u003e\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "8688b8635266cf98f00c6b0350ea2dbe7c42c321",
      "tree": "d49153695f4637f5671fe5c10810b93959e65ccf",
      "parents": [
        "f95022161d23ee661a48af8f280472209f513a67"
      ],
      "author": {
        "name": "Mike Frysinger",
        "email": "vapier@gentoo.org",
        "time": "Tue May 26 05:45:04 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:10 2009 -0400"
      },
      "message": "linux/magic.h: move cramfs magic out of cramfs_fs.h\n\nSigned-off-by: Mike Frysinger \u003cvapier@gentoo.org\u003e\nCC: Alexander Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "f95022161d23ee661a48af8f280472209f513a67",
      "tree": "9e7c8455e4126b1dd5586ae973ad16c17653f5b3",
      "parents": [
        "13205fb9260c2377438599ef0773c6a3eaeb0b07"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Fri Jun 05 12:26:23 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:10 2009 -0400"
      },
      "message": "xfs: remove -\u003ewrite_super and stop maintaining -\u003es_dirt\n\nthe write_super method is used for\n\n (1) writing back the superblock periodically from pdflush\n (2) called just before -\u003esync_fs for data integerity syncs\n\nWe don\u0027t need (1) because we have our own peridoc writeout through xfssyncd,\nand we don\u0027t need (2) because xfs_fs_sync_fs performs a proper synchronous\nsuperblock writeout after all other data and metadata has been written out.\n\nAlso remove -\u003es_dirt tracking as it\u0027s only used to decide when too call\n-\u003ewrite_super.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nReviewed-by: Eric Sandeen \u003csandeen@sandeen.net\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "13205fb9260c2377438599ef0773c6a3eaeb0b07",
      "tree": "bcf5dee805d504ccc173c17cf28488a42cef2cb3",
      "parents": [
        "28ad0c118b0ed98b042d362acfe0017591921138"
      ],
      "author": {
        "name": "Jens Axboe",
        "email": "jens.axboe@oracle.com",
        "time": "Mon May 25 09:30:45 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:10 2009 -0400"
      },
      "message": "ntfs: remove old debug check for dirty data in ntfs_put_super()\n\nThis should not trigger anymore, so kill it.\n\nAcked-by: Anton Altaparmakov \u003caia21@cam.ac.uk\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "28ad0c118b0ed98b042d362acfe0017591921138",
      "tree": "71a8954cbd50216c11c5c3557efcb7535c433e0a",
      "parents": [
        "9fd5746fd3d7838bf6ff991d50f1257057d1156f"
      ],
      "author": {
        "name": "Theodore Ts\u0027o",
        "email": "tytso@mit.edu",
        "time": "Thu May 21 16:01:02 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:09 2009 -0400"
      },
      "message": "fs: Rearrange inode structure elements to avoid waste due to padding\n\nSigned-off-by: \"Theodore Ts\u0027o\" \u003ctytso@mit.edu\u003e\nCc: linux-fsdevel@vger.kernel.org\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "9fd5746fd3d7838bf6ff991d50f1257057d1156f",
      "tree": "e0afe14ea9415b0e54c40703bb44acfec100a4b3",
      "parents": [
        "ebc1ac164560a241d9bf1b7519062910c3f90a01"
      ],
      "author": {
        "name": "Theodore Ts\u0027o",
        "email": "tytso@mit.edu",
        "time": "Thu May 21 16:01:00 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:09 2009 -0400"
      },
      "message": "fs: Remove i_cindex from struct inode\n\nThe only user of the i_cindex element in the inode structure is used\nis by the firewire drivers.  As part of an attempt to slim down the\ninode structure to save memory --- since a typical Linux system will\nhave hundreds of thousands if not millions of inodes cached, a\nreduction in the size inode has high leverage.\n\nThe firewire driver does not need i_cindex in any fast path, so it\u0027s\nsimple enough to calculate when it is needed, instead of wasting space\nin the inode structure.\n\nSigned-off-by: \"Theodore Ts\u0027o\" \u003ctytso@mit.edu\u003e\nCc: krh@redhat.com\nCc: stefanr@s5r6.in-berlin.de\nCc: linux-fsdevel@vger.kernel.org\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "ebc1ac164560a241d9bf1b7519062910c3f90a01",
      "tree": "db17fd3043b15f8269cce2c2d00213814022fc30",
      "parents": [
        "01ba687577647beef6c5f2ea59bfb56fac9fcde2"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Mon May 11 23:35:03 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:09 2009 -0400"
      },
      "message": "-\u003ewrite_super lock_super pushdown\n\nPush down lock_super into -\u003ewrite_super instances and remove it from the\ncaller.\n\nFollowing filesystem don\u0027t need -\u003es_lock in -\u003ewrite_super and are skipped:\n\n * bfs, nilfs2 - no other uses of s_lock and have internal locks in\n\t-\u003ewrite_super\n * ext2 - uses BKL in ext2_write_super and has internal calls without s_lock\n * reiserfs - no other uses of s_lock as has reiserfs_write_lock (BKL) in\n \t-\u003ewrite_super\n * xfs - no other uses of s_lock and uses internal lock (buffer lock on\n\tsuperblock buffer) to serialize -\u003ewrite_super.  Also xfs_fs_write_super\n\tis superflous and will go away in the next merge window\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "01ba687577647beef6c5f2ea59bfb56fac9fcde2",
      "tree": "fadd888ca8568f3e373bda5b80857396cd79828a",
      "parents": [
        "4aa98cf768b6f2ea4b204620d949a665959214f6"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Mon May 11 23:34:27 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:09 2009 -0400"
      },
      "message": "jffs2: move jffs2_write_super to super.c\n\njffs2_write_super is only called from super.c and doesn\u0027t use any\nfunctionality from fs.c.  So move it over to super.c and make it\nstatic there.\n\n[should go in through the vfs tree as it is a requirement for the\n next patch]\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "4aa98cf768b6f2ea4b204620d949a665959214f6",
      "tree": "dd6f5be97396b9e1f24a9697524da19463e7a8da",
      "parents": [
        "7f78d4cd4c5d01864943c22b79df1b6bde923129"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Fri May 08 13:36:58 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:08 2009 -0400"
      },
      "message": "Push BKL down into do_remount_sb()\n\n[folded fix from Jiri Slaby]\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "7f78d4cd4c5d01864943c22b79df1b6bde923129",
      "tree": "c232d14121976caa8a38e49d6a8a555e99e27c04",
      "parents": [
        "6fac98dd218653c6aff8a0f56305c424930cea2a"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Fri May 08 13:34:06 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:08 2009 -0400"
      },
      "message": "Push BKL down beyond VFS-only parts of do_mount()\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "6fac98dd218653c6aff8a0f56305c424930cea2a",
      "tree": "0c5bdca0092e5ec3b201bae958071a7e8385409d",
      "parents": [
        "bbd6851a3213a525128473e978b692ab6ac11aba"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Fri May 08 13:31:17 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:08 2009 -0400"
      },
      "message": "Push BKL into do_mount()\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "bbd6851a3213a525128473e978b692ab6ac11aba",
      "tree": "8ebddebadd8992871ab98456187cb00849a82058",
      "parents": [
        "6cfd0148425e528b859b26e436b01f23f6926224"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Wed May 06 10:43:07 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:08 2009 -0400"
      },
      "message": "Push lock_super() into the -\u003eremount_fs() of filesystems that care about it\n\nNote that since we can\u0027t run into contention between remount_fs and write_super\n(due to exclusion on s_umount), we have to care only about filesystems that\ntouch lock_super() on their own.  Out of those ext3, ext4, hpfs, sysv and ufs\ndo need it; fat doesn\u0027t since its -\u003eremount_fs() only accesses assign-once\ndata (basically, it\u0027s \"we have no atime on directories and only have atime on\nfiles for vfat; force nodiratime and possibly noatime into *flags\").\n\n[folded a build fix from hch]\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "6cfd0148425e528b859b26e436b01f23f6926224",
      "tree": "60e3257053554ff198fe5825e6f12a00c3b4422a",
      "parents": [
        "a9e220f8322e2b0e0b8903fe00265461cffad3f0"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Tue May 05 15:40:36 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:07 2009 -0400"
      },
      "message": "push BKL down into -\u003eput_super\n\nMove BKL into -\u003eput_super from the only caller.  A couple of\nfilesystems had trivial enough -\u003eput_super (only kfree and NULLing of\ns_fs_info + stuff in there) to not get any locking: coda, cramfs, efs,\nhugetlbfs, omfs, qnx4, shmem, all others got the full treatment.  Most\nof them probably don\u0027t need it, but I\u0027d rather sort that out individually.\nPreferably after all the other BKL pushdowns in that area.\n\n[AV: original used to move lock_super() down as well; these changes are\nremoved since we don\u0027t do lock_super() at all in generic_shutdown_super()\nnow]\n[AV: fuse, btrfs and xfs are known to need no damn BKL, exempt]\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "a9e220f8322e2b0e0b8903fe00265461cffad3f0",
      "tree": "b3be7d58b8eb9fd810636223f0458191ec1b9d75",
      "parents": [
        "62c6943b4b1e818aea60c11c5a68a50785b83119"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Tue May 05 22:10:44 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:07 2009 -0400"
      },
      "message": "No need to do lock_super() for exclusion in generic_shutdown_super()\n\nWe can\u0027t run into contention on it.  All other callers of lock_super()\neither hold s_umount (and we have it exclusive) or hold an active\nreference to superblock in question, which prevents the call of\ngeneric_shutdown_super() while the reference is held.  So we can\nreplace lock_super(s) with get_fs_excl() in generic_shutdown_super()\n(and corresponding change for unlock_super(), of course).\n\nSince ext4 expects s_lock held for its put_super, take lock_super()\ninto it.  The rest of filesystems do not care at all.\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "62c6943b4b1e818aea60c11c5a68a50785b83119",
      "tree": "ecdbb1c63d5c37b42f7074e4c53beaaa850ada2b",
      "parents": [
        "443b94baaa16771e98b29ca7c24f1e305738ffca"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu May 07 03:12:29 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:07 2009 -0400"
      },
      "message": "Trim a bit of crap from fs.h\n\ndo_remount_sb() is fs/internal.h fodder, fsync_no_super() is long gone.\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "443b94baaa16771e98b29ca7c24f1e305738ffca",
      "tree": "cf498a25d012330928e0315222c46ea90c200530",
      "parents": [
        "5af7926ff33b68b3ba46531471c6e0564b285efc"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Tue May 05 23:48:50 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:07 2009 -0400"
      },
      "message": "Make sure that all callers of remount hold s_umount exclusive\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "5af7926ff33b68b3ba46531471c6e0564b285efc",
      "tree": "a25266f9db482ce9dd8e663148ffb0f1a524bd83",
      "parents": [
        "e5004753388dcf5e1b8a52ac0ab807d232340fbb"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Tue May 05 15:41:25 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:06 2009 -0400"
      },
      "message": "enforce -\u003esync_fs is only called for rw superblock\n\nMake sure a superblock really is writeable by checking MS_RDONLY\nunder s_umount.  sync_filesystems needed some re-arragement for\nthat, but all but one sync_filesystem caller had the correct locking\nalready so that we could add that check there.  cachefiles grew\ns_umount locking.\n\nI\u0027ve also added a WARN_ON to sync_filesystem to assert this for\nfuture callers.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "e5004753388dcf5e1b8a52ac0ab807d232340fbb",
      "tree": "4a74a93f1468acb111ba9a3e9ed4a55f338f51fe",
      "parents": [
        "f3da392e9ff14b9f388e74319e6d195848991c07"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Tue May 05 16:08:56 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:06 2009 -0400"
      },
      "message": "cleanup sync_supers\n\nMerge the write_super helper into sync_super and move the check for\n-\u003ewrite_super earlier so that we can avoid grabbing a reference to\na superblock that doesn\u0027t have it.\n\nWhile we\u0027re at it also add a little comment documenting sync_supers.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "f3da392e9ff14b9f388e74319e6d195848991c07",
      "tree": "d9e7660e5c0b4524aeaafcc5b89a9d68a7ca3817",
      "parents": [
        "8c85e125124a473d6f3e9bb187b0b84207f81d91"
      ],
      "author": {
        "name": "Alexey Dobriyan",
        "email": "adobriyan@gmail.com",
        "time": "Mon May 04 03:32:03 2009 +0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:06 2009 -0400"
      },
      "message": "dcache: extrace and use d_unlinked()\n\nd_unlinked() will be used in middle-term to ban checkpointing when opened\nbut unlinked file is detected, and in long term, to detect such situation\nand special case on it.\n\nSigned-off-by: Alexey Dobriyan \u003cadobriyan@gmail.com\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "8c85e125124a473d6f3e9bb187b0b84207f81d91",
      "tree": "d883424a156c00c55193e46567efdffddb6ef6b9",
      "parents": [
        "517bfae28353e996160518add4d00033d3886e61"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Tue Apr 28 18:00:26 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:06 2009 -0400"
      },
      "message": "remove -\u003ewrite_super call in generic_shutdown_super\n\nWe just did a full fs writeout using sync_filesystem before, and if\nthat\u0027s not enough for the filesystem it can perform it\u0027s own writeout\nin -\u003eput_super, which many filesystems already do.\n\nMove a call to foofs_write_super into every foofs_put_super for now to\nguarantee identical behaviour until it\u0027s cleaned up by the individual\nfilesystem maintainers.\n\nExceptions:\n\n - affs already has identical copy \u0026 pasted code at the beginning of\n   affs_put_super so no need to do it twice.\n - xfs does the right thing without it and I have changes pending for\n   the xfs tree touching this are so I don\u0027t really need conflicts\n   here..\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "517bfae28353e996160518add4d00033d3886e61",
      "tree": "037d4c4de72da1c65a8be7c33a28f5ebcf0b31a3",
      "parents": [
        "94cb993f2ee99f3a9318e7b4dbb383497c4bedea"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@infradead.org",
        "time": "Mon Apr 27 09:46:45 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:05 2009 -0400"
      },
      "message": "qnx4: remove -\u003ewrite_super\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "94cb993f2ee99f3a9318e7b4dbb383497c4bedea",
      "tree": "71c2436a8588d253938d50e30b561dcefbb83cd7",
      "parents": [
        "b7d245de25d1f0bb75a0d04194b647762b30d3db"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@infradead.org",
        "time": "Mon Apr 27 09:46:44 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:05 2009 -0400"
      },
      "message": "ocfs2: remove -\u003ewrite_super and stop maintaining -\u003es_dirt\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nAcked-by: Joel Becker \u003cjoel.becker@oracle.com\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "b7d245de25d1f0bb75a0d04194b647762b30d3db",
      "tree": "7c7f00651751db70432feef2a6a8327f67bc4109",
      "parents": [
        "ca41f7b918294c2a17780e057568413dcbfc6d49"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@infradead.org",
        "time": "Mon Apr 27 09:46:43 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:05 2009 -0400"
      },
      "message": "gfs2: remove -\u003ewrite_super and stop maintaining -\u003es_dirt\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nAcked-by: Steven Whitehouse \u003cswhiteho@redhat.com\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "ca41f7b918294c2a17780e057568413dcbfc6d49",
      "tree": "0f10dbd7e56d5e594802898d744820e551f17cda",
      "parents": [
        "59d697b70285c348c01cfc2695c3469ba71d7539"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@infradead.org",
        "time": "Mon Apr 27 09:46:42 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:05 2009 -0400"
      },
      "message": "ext3: remove -\u003ewrite_super and stop maintaining -\u003es_dirt\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "59d697b70285c348c01cfc2695c3469ba71d7539",
      "tree": "e383e5a2c0fc6196bed269aac032d3e363e9c4f7",
      "parents": [
        "c3f8a40c1cd5591b882497d1d00d43d0e5bb4698"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@infradead.org",
        "time": "Mon Apr 27 09:46:41 2009 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:05 2009 -0400"
      },
      "message": "btrfs: remove -\u003ewrite_super and stop maintaining -\u003es_dirt\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "c3f8a40c1cd5591b882497d1d00d43d0e5bb4698",
      "tree": "8280d4c7748be5d3b2b96c6bd11a643280d0b232",
      "parents": [
        "850b201b087f5525a0a7278551c2bcd0423c3b26"
      ],
      "author": {
        "name": "Jan Kara",
        "email": "jack@suse.cz",
        "time": "Mon Apr 27 16:43:55 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:04 2009 -0400"
      },
      "message": "quota: Introduce writeout_quota_sb() (version 4)\n\nIntroduce this function which just writes all the quota structures but\navoids all the syncing and cache pruning work to expose quota structures\nto userspace. Use this function from __sync_filesystem when wait \u003d\u003d 0.\n\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "850b201b087f5525a0a7278551c2bcd0423c3b26",
      "tree": "a076f135430380d2ffaeb041ee53d09352cb2752",
      "parents": [
        "60b0680fa236ac4e17ce31a50048c9d75f9ec831"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Mon Apr 27 16:43:54 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:04 2009 -0400"
      },
      "message": "quota: cleanup dquota sync functions (version 4)\n\nCurrently the VFS calls vfs_dq_sync to sync out disk quotas for a given\nsuperblock.  This is a small wrapper around sync_dquots which for the\ncase of a non-NULL superblock is a small wrapper around quota_sync_sb.\n\nJust make quota_sync_sb global (rename it to sync_quota_sb) and call it\ndirectly.  Also call it directly for those cases in quota.c that have a\nsuperblock and leave sync_dquots purely an iterator over sync_quota_sb and\nremove it\u0027s superblock argument.\n\nTo make this nicer move the check for the lack of a quota_sync method\nfrom the callers into sync_quota_sb.\n\n[folded build fix from Alexander Beregalov \u003ca.beregalov@gmail.com\u003e]\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "60b0680fa236ac4e17ce31a50048c9d75f9ec831",
      "tree": "c8ca34340a173326694247eab779e713c57202c2",
      "parents": [
        "c15c54f5f056ee4819da9fde59a5f2cd45445f23"
      ],
      "author": {
        "name": "Jan Kara",
        "email": "jack@suse.cz",
        "time": "Mon Apr 27 16:43:53 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:04 2009 -0400"
      },
      "message": "vfs: Rename fsync_super() to sync_filesystem() (version 4)\n\nRename the function so that it better describe what it really does. Also\nremove the unnecessary include of buffer_head.h.\n\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "c15c54f5f056ee4819da9fde59a5f2cd45445f23",
      "tree": "0b8d142f0b8d44b71bf7ff9db7a373f90d0556a3",
      "parents": [
        "5cee5815d1564bbbd505fea86f4550f1efdb5cd0"
      ],
      "author": {
        "name": "Jan Kara",
        "email": "jack@suse.cz",
        "time": "Mon Apr 27 16:43:52 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:04 2009 -0400"
      },
      "message": "vfs: Move syncing code from super.c to sync.c (version 4)\n\nMove sync_filesystems(), __fsync_super(), fsync_super() from\nsuper.c to sync.c where it fits better.\n\n[build fixes folded]\n\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "5cee5815d1564bbbd505fea86f4550f1efdb5cd0",
      "tree": "ba99c38932dc534bf56f0d7dcfeeca153f50b007",
      "parents": [
        "429479f031322a0cc5c921ffb2321a51718dc875"
      ],
      "author": {
        "name": "Jan Kara",
        "email": "jack@suse.cz",
        "time": "Mon Apr 27 16:43:51 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:03 2009 -0400"
      },
      "message": "vfs: Make sys_sync() use fsync_super() (version 4)\n\nIt is unnecessarily fragile to have two places (fsync_super() and do_sync())\ndoing data integrity sync of the filesystem. Alter __fsync_super() to\naccommodate needs of both callers and use it. So after this patch\n__fsync_super() is the only place where we gather all the calls needed to\nproperly send all data on a filesystem to disk.\n\nNice bonus is that we get a complete livelock avoidance and write_supers()\nis now only used for periodic writeback of superblocks.\n\nsync_blockdevs() introduced a couple of patches ago is gone now.\n\n[build fixes folded]\n\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "429479f031322a0cc5c921ffb2321a51718dc875",
      "tree": "6741f7f1bfa1d889bbc4f44ab0489de97a3e47c0",
      "parents": [
        "bfe881255c74800147523b59c85328a1a826ba21"
      ],
      "author": {
        "name": "Jan Kara",
        "email": "jack@suse.cz",
        "time": "Mon Apr 27 16:43:50 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:03 2009 -0400"
      },
      "message": "vfs: Make __fsync_super() a static function (version 4)\n\n__fsync_super() does the same thing as fsync_super(). So change the only\ncaller to use fsync_super() and make __fsync_super() static. This removes\nunnecessarily duplicated call to sync_blockdev() and prepares ground\nfor the changes to __fsync_super() in the following patches.\n\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "bfe881255c74800147523b59c85328a1a826ba21",
      "tree": "4ed9b761a440ee0b69a35a5c8bddc42c64195e47",
      "parents": [
        "5a3e5cb8e08bd876e2542c1451c9a93dab1b0e39"
      ],
      "author": {
        "name": "Jan Kara",
        "email": "jack@suse.cz",
        "time": "Mon Apr 27 16:43:49 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:03 2009 -0400"
      },
      "message": "vfs: Call -\u003esync_fs() even if s_dirt is 0 (version 4)\n\nsync_filesystems() has a condition that if wait \u003d\u003d 0 and s_dirt \u003d\u003d 0, then\n-\u003esync_fs() isn\u0027t called. This does not really make much sence since s_dirt is\ngenerally used by a filesystem to mean that -\u003ewrite_super() needs to be called.\nBut -\u003esync_fs() does different things. I even suspect that some filesystems\n(btrfs?) sets s_dirt just to fool this logic.\n\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "5a3e5cb8e08bd876e2542c1451c9a93dab1b0e39",
      "tree": "3b792d21246f1001adeca8b67df24ca71593dd3f",
      "parents": [
        "876a9f76abbcb775f8d21cbc99fa161f9e5937f1"
      ],
      "author": {
        "name": "Jan Kara",
        "email": "jack@suse.cz",
        "time": "Mon Apr 27 16:43:48 2009 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Jun 11 21:36:03 2009 -0400"
      },
      "message": "vfs: Fix sys_sync() and fsync_super() reliability (version 4)\n\nSo far, do_sync() called:\n  sync_inodes(0);\n  sync_supers();\n  sync_filesystems(0);\n  sync_filesystems(1);\n  sync_inodes(1);\n\nThis ordering makes it kind of hard for filesystems as sync_inodes(0) need not\nsubmit all the IO (for example it skips inodes with I_SYNC set) so e.g. forcing\ntransaction to disk in -\u003esync_fs() is not really enough. Therefore sys_sync has\nnot been completely reliable on some filesystems (ext3, ext4, reiserfs, ocfs2\nand others are hit by this) when racing e.g. with background writeback. A\nsimilar problem hits also other filesystems (e.g. ext2) because of\nwrite_supers() being called before the sync_inodes(1).\n\nChange the ordering of calls in do_sync() - this requires a new function\nsync_blockdevs() to preserve the property that block devices are always synced\nafter write_super() / sync_fs() call.\n\nThe same issue is fixed in __fsync_super() function used on umount /\nremount read-only.\n\n[AV: build fixes]\n\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    }
  ],
  "next": "876a9f76abbcb775f8d21cbc99fa161f9e5937f1"
}