)]}'
{
  "log": [
    {
      "commit": "86998aa6534e839ec003ed2ef7067d6fe8696ccc",
      "tree": "ca2e8fff9371ef26f339f2893c6c1d50c5f4e2fe",
      "parents": [
        "47a5c6fa0e204a2b63309c648bb2fde36836c826"
      ],
      "author": {
        "name": "Ingo Molnar",
        "email": "mingo@elte.hu",
        "time": "Tue Sep 19 11:14:34 2006 +0200"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@g5.osdl.org",
        "time": "Tue Sep 19 07:57:20 2006 -0700"
      },
      "message": "[PATCH] genirq core: fix handle_level_irq()\n\nwhile porting the -rt tree to 2.6.18-rc7 i noticed the following\nscreaming-IRQ scenario on an SMP system:\n\n 2274  0Dn.:1 0.001ms: do_IRQ+0xc/0x103  \u003c\u003d (ret_from_intr+0x0/0xf)\n 2274  0Dn.:1 0.010ms: do_IRQ+0xc/0x103  \u003c\u003d (ret_from_intr+0x0/0xf)\n 2274  0Dn.:1 0.020ms: do_IRQ+0xc/0x103  \u003c\u003d (ret_from_intr+0x0/0xf)\n 2274  0Dn.:1 0.029ms: do_IRQ+0xc/0x103  \u003c\u003d (ret_from_intr+0x0/0xf)\n 2274  0Dn.:1 0.039ms: do_IRQ+0xc/0x103  \u003c\u003d (ret_from_intr+0x0/0xf)\n 2274  0Dn.:1 0.048ms: do_IRQ+0xc/0x103  \u003c\u003d (ret_from_intr+0x0/0xf)\n 2274  0Dn.:1 0.058ms: do_IRQ+0xc/0x103  \u003c\u003d (ret_from_intr+0x0/0xf)\n 2274  0Dn.:1 0.068ms: do_IRQ+0xc/0x103  \u003c\u003d (ret_from_intr+0x0/0xf)\n 2274  0Dn.:1 0.077ms: do_IRQ+0xc/0x103  \u003c\u003d (ret_from_intr+0x0/0xf)\n 2274  0Dn.:1 0.087ms: do_IRQ+0xc/0x103  \u003c\u003d (ret_from_intr+0x0/0xf)\n 2274  0Dn.:1 0.097ms: do_IRQ+0xc/0x103  \u003c\u003d (ret_from_intr+0x0/0xf)\n\nas it turns out, the bug is caused by handle_level_irq(), which if it\nraces with another CPU already handling this IRQ, it _unmasks_ the IRQ\nline on the way out. This is not how 2.6.17 works, and we introduced\nthis bug in one of the early genirq cleanups right before it went into\n-mm. (the bug was not in the genirq patchset for a long time, and we\ndidnt notice the bug due to the lack of -rt rebase to the new genirq\ncode. -rt, and hardirq-preemption in particular opens up such races much\nwider than anything else.)\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nAcked-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    },
    {
      "commit": "5a43a066b11ac2fe84cf67307f20b83bea390f83",
      "tree": "d4770958575f4e7592620d9a0d36c431ecceefc9",
      "parents": [
        "3e9a69275f23baec86b54febc5dad0b2fc7fb200"
      ],
      "author": {
        "name": "Benjamin Herrenschmidt",
        "email": "benh@kernel.crashing.org",
        "time": "Mon Jul 03 19:54:59 2006 +1000"
      },
      "committer": {
        "name": "Paul Mackerras",
        "email": "paulus@samba.org",
        "time": "Mon Jul 03 19:54:59 2006 +1000"
      },
      "message": "[PATCH] genirq: Allow fasteoi handler to retrigger disabled interrupts\n\nMake the fasteoi handler mark disabled interrupts as pending if they\nhappen anyway. This allow implementation of a delayed disable scheme\nwith the fasteoi handler.\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nAcked-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nAcked-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n"
    },
    {
      "commit": "f8b5473fcbddbfde827ecf82aa0e81fa2a878220",
      "tree": "0d6d504f95830610cb2c2fb1e6e9e1ebf932762b",
      "parents": [
        "a2166abd06e7a9fd34eb18b7b27da18c6146e6ef"
      ],
      "author": {
        "name": "Thomas Gleixner",
        "email": "tglx@linutronix.de",
        "time": "Sat Jul 01 22:30:08 2006 +0100"
      },
      "committer": {
        "name": "Russell King",
        "email": "rmk+kernel@arm.linux.org.uk",
        "time": "Sat Jul 01 22:30:08 2006 +0100"
      },
      "message": "[ARM] 3690/1: genirq: Introduce and make use of dummy irq chip\n\nPatch from Thomas Gleixner\n\nFrom: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n\nARM has a couple of really dumb interrupt controllers.\nImplement a generic one and fixup the ARM migration. ARM reused\nthe no_irq_chip for this purpose, but this does not work out\nfor platforms which are not converted to the new interrupt\ntype handling model.\n\nSigned-off-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Russell King \u003crmk+kernel@arm.linux.org.uk\u003e\n"
    },
    {
      "commit": "47c2a3aa4475d27073dd3c7e183fcc13f495c8f5",
      "tree": "d151e03da804103753977c2c94e17b71104e3d35",
      "parents": [
        "f702d7013c7470284843a6370aaa53b8b75c5a40"
      ],
      "author": {
        "name": "Ingo Molnar",
        "email": "mingo@elte.hu",
        "time": "Thu Jun 29 02:25:03 2006 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@g5.osdl.org",
        "time": "Thu Jun 29 10:26:26 2006 -0700"
      },
      "message": "[PATCH] genirq: add chip-\u003eeoi(), fastack -\u003e fasteoi\n\nClean up the fastack concept by turning it into fasteoi and introducing the\n-\u003eeoi() method for chips.\n\nThis also allows the cleanup of an i386 EOI quirk - now the quirk is\ncleanly separated from the pure ACK implementation.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: Roland Dreier \u003crolandd@cisco.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    },
    {
      "commit": "98bb244b685eb2a297aa60fa2e5c0631f95828e1",
      "tree": "468ab2cf22dc3b10d1bc48660360b908d24cabef",
      "parents": [
        "f210be198ddd3f54b17d4aa6e69b829f75f226e5"
      ],
      "author": {
        "name": "Benjamin Herrenschmidt",
        "email": "benh@kernel.crashing.org",
        "time": "Thu Jun 29 02:25:01 2006 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@g5.osdl.org",
        "time": "Thu Jun 29 10:26:25 2006 -0700"
      },
      "message": "[PATCH] genirq: fasteoi handler: handle interrupt disabling\n\nNote when a disable interrupt happened with the fasteoi handler as well so\nthat delayed disable can be implemented with fasteoi-type controllers.\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nAcked-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    },
    {
      "commit": "dd87eb3a24c4527741122713e223d74b85d43c85",
      "tree": "0c3796af23da908515d890a7b8fde37893eb3b2a",
      "parents": [
        "dae8620421833bb2e9a01c4ccc42bdc3759b81df"
      ],
      "author": {
        "name": "Thomas Gleixner",
        "email": "tglx@linutronix.de",
        "time": "Thu Jun 29 02:24:53 2006 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@g5.osdl.org",
        "time": "Thu Jun 29 10:26:24 2006 -0700"
      },
      "message": "[PATCH] genirq: add irq-chip support\n\nEnable platforms to use the irq-chip and irq-flow abstractions: allow setting\nof the chip, the type and provide highlevel handlers for common irq-flows.\n\n[rostedt@goodmis.org: misroute-irq: Don\u0027t call desc-\u003echip-\u003eend because of edge interrupts]\nSigned-off-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    }
  ]
}