)]}'
{
  "log": [
    {
      "commit": "2d9e1e2f58b5612aa4eab0ab54c84308a29dbd79",
      "tree": "08e91f7f485a8fa8ec2515f8c706870c0d44044b",
      "parents": [
        "56397f8dadb40055479a8ffff23f21a890098a31"
      ],
      "author": {
        "name": "Jeremy Fitzhardinge",
        "email": "jeremy@goop.org",
        "time": "Mon Jul 07 12:07:53 2008 -0700"
      },
      "committer": {
        "name": "Ingo Molnar",
        "email": "mingo@elte.hu",
        "time": "Wed Jul 16 11:15:53 2008 +0200"
      },
      "message": "xen: implement Xen-specific spinlocks\n\nThe standard ticket spinlocks are very expensive in a virtual\nenvironment, because their performance depends on Xen\u0027s scheduler\ngiving vcpus time in the order that they\u0027re supposed to take the\nspinlock.\n\nThis implements a Xen-specific spinlock, which should be much more\nefficient.\n\nThe fast-path is essentially the old Linux-x86 locks, using a single\nlock byte.  The locker decrements the byte; if the result is 0, then\nthey have the lock.  If the lock is negative, then locker must spin\nuntil the lock is positive again.\n\nWhen there\u0027s contention, the locker spin for 2^16[*] iterations waiting\nto get the lock.  If it fails to get the lock in that time, it adds\nitself to the contention count in the lock and blocks on a per-cpu\nevent channel.\n\nWhen unlocking the spinlock, the locker looks to see if there\u0027s anyone\nblocked waiting for the lock by checking for a non-zero waiter count.\nIf there\u0027s a waiter, it traverses the per-cpu \"lock_spinners\"\nvariable, which contains which lock each CPU is waiting on.  It picks\none CPU waiting on the lock and sends it an event to wake it up.\n\nThis allows efficient fast-path spinlock operation, while allowing\nspinning vcpus to give up their processor time while waiting for a\ncontended lock.\n\n[*] 2^16 iterations is threshold at which 98% locks have been taken\naccording to Thomas Friebel\u0027s Xen Summit talk \"Preventing Guests from\nSpinning Around\".  Therefore, we\u0027d expect the lock and unlock slow\npaths will only be entered 2% of the time.\n\nSigned-off-by: Jeremy Fitzhardinge \u003cjeremy.fitzhardinge@citrix.com\u003e\nCc: Jens Axboe \u003caxboe@kernel.dk\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Christoph Lameter \u003cclameter@linux-foundation.org\u003e\nCc: Petr Tesarik \u003cptesarik@suse.cz\u003e\nCc: Virtualization \u003cvirtualization@lists.linux-foundation.org\u003e\nCc: Xen devel \u003cxen-devel@lists.xensource.com\u003e\nCc: Thomas Friebel \u003cthomas.friebel@amd.com\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n"
    },
    {
      "commit": "0e91398f2a5d4eb6b07df8115917d0d1cf3e9b58",
      "tree": "c6a3b31b7bcbbfb55bb2304d8651abdd28cdad54",
      "parents": [
        "7d88d32a4670af583c896e5ecd3929b78538ca62"
      ],
      "author": {
        "name": "Jeremy Fitzhardinge",
        "email": "jeremy@goop.org",
        "time": "Mon May 26 23:31:27 2008 +0100"
      },
      "committer": {
        "name": "Thomas Gleixner",
        "email": "tglx@linutronix.de",
        "time": "Tue May 27 10:11:38 2008 +0200"
      },
      "message": "xen: implement save/restore\n\nThis patch implements Xen save/restore and migration.\n\nSaving is triggered via xenbus, which is polled in\ndrivers/xen/manage.c.  When a suspend request comes in, the kernel\nprepares itself for saving by:\n\n1 - Freeze all processes.  This is primarily to prevent any\n    partially-completed pagetable updates from confusing the suspend\n    process.  If CONFIG_PREEMPT isn\u0027t defined, then this isn\u0027t necessary.\n\n2 - Suspend xenbus and other devices\n\n3 - Stop_machine, to make sure all the other vcpus are quiescent.  The\n    Xen tools require the domain to run its save off vcpu0.\n\n4 - Within the stop_machine state, it pins any unpinned pgds (under\n    construction or destruction), performs canonicalizes various other\n    pieces of state (mostly converting mfns to pfns), and finally\n\n5 - Suspend the domain\n\nRestore reverses the steps used to save the domain, ending when all\nthe frozen processes are thawed.\n\nSigned-off-by: Jeremy Fitzhardinge \u003cjeremy.fitzhardinge@citrix.com\u003e\nSigned-off-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n"
    },
    {
      "commit": "eb1e305f4ef201e549ffd475b7dcbcd4ec36d7dc",
      "tree": "078c5acb7d6ca6e3f24b45c5d4a660abcdc75202",
      "parents": [
        "d5edbc1f75420935b1ec7e65df10c8f81cea82de"
      ],
      "author": {
        "name": "Jeremy Fitzhardinge",
        "email": "jeremy@goop.org",
        "time": "Mon May 26 23:31:23 2008 +0100"
      },
      "committer": {
        "name": "Thomas Gleixner",
        "email": "tglx@linutronix.de",
        "time": "Tue May 27 10:11:37 2008 +0200"
      },
      "message": "xen: add rebind_evtchn_irq\n\nAdd rebind_evtchn_irq(), which will rebind an device driver\u0027s existing\nirq to a new event channel on restore.  Since the new event channel\nwill be masked and bound to vcpu0, we update the state accordingly and\nunmask the irq once everything is set up.\n\nSigned-off-by: Jeremy Fitzhardinge \u003cjeremy.fitzhardinge@citrix.com\u003e\nSigned-off-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n"
    },
    {
      "commit": "642e0c882cd5369429c833d97e4804c8be473e8a",
      "tree": "c9032832801bd68379b30983ce61fd80f823adb0",
      "parents": [
        "e849c3e9e0b786619c451d89ef0c47ac9a28fbc1"
      ],
      "author": {
        "name": "Isaku Yamahata",
        "email": "yamahata@valinux.co.jp",
        "time": "Wed Apr 02 10:53:57 2008 -0700"
      },
      "committer": {
        "name": "Ingo Molnar",
        "email": "mingo@elte.hu",
        "time": "Thu Apr 24 23:57:32 2008 +0200"
      },
      "message": "xen: add resend_irq_on_evtchn() definition into events.c\n\nDefine resend_irq_on_evtchn() which ia64/xen uses.\nAlthough it isn\u0027t used by current x86/xen code, it\u0027s arch generic\nso that put it into common code.\n\nSigned-off-by: Isaku Yamahata \u003cyamahata@valinux.co.jp\u003e\nSigned-off-by: Jeremy Fitzhardinge \u003cjeremy.fitzhardinge@citrix.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n"
    },
    {
      "commit": "e849c3e9e0b786619c451d89ef0c47ac9a28fbc1",
      "tree": "bc3500d40095c2f868e2efca4918b73a6b0a1090",
      "parents": [
        "e04d0d0767a9c272d3c7300fb7a5221c5e3a71eb"
      ],
      "author": {
        "name": "Isaku Yamahata",
        "email": "yamahata@valinux.co.jp",
        "time": "Wed Apr 02 10:53:56 2008 -0700"
      },
      "committer": {
        "name": "Ingo Molnar",
        "email": "mingo@elte.hu",
        "time": "Thu Apr 24 23:57:32 2008 +0200"
      },
      "message": "Xen: make events.c portable for ia64/xen support\n\nRemove x86 dependency in drivers/xen/events.c for ia64/xen support\nintroducing include/asm/xen/events.h.\nIntroduce xen_irqs_disabled() to hide regs-\u003eflags\nIntroduce xen_do_IRQ() to hide regs-\u003eorig_ax.\nmake enum ipi_vector definition arch specific. ia64/xen needs four vectors.\nAdd one rmb() because on ia64 xchg() isn\u0027t barrier.\n\nSigned-off-by: Isaku Yamahata \u003cyamahata@valinux.co.jp\u003e\nSigned-off-by: Jeremy Fitzhardinge \u003cjeremy.fitzhardinge@citrix.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n"
    },
    {
      "commit": "b536b4b9623084d86f2b1f19cb44a2d6d74f00bf",
      "tree": "86c1981309dbd8b9bf120d4ddba50abd105af89a",
      "parents": [
        "8b84ad942b534f8faeb34b68f0f7277ea375fed0"
      ],
      "author": {
        "name": "Jeremy Fitzhardinge",
        "email": "jeremy@xensource.com",
        "time": "Tue Jul 17 18:37:06 2007 -0700"
      },
      "committer": {
        "name": "Jeremy Fitzhardinge",
        "email": "jeremy@goop.org",
        "time": "Wed Jul 18 08:47:44 2007 -0700"
      },
      "message": "xen: use the hvc console infrastructure for Xen console\n\nImplement a Xen back-end for hvc console.\n\n* * *\nAdd early printk support via hvc console, enable using\n\"earlyprintk\u003dxen\" on the kernel command line.\n\nFrom: Gerd Hoffmann \u003ckraxel@suse.de\u003e\nSigned-off-by: Jeremy Fitzhardinge \u003cjeremy@xensource.com\u003e\nSigned-off-by: Chris Wright \u003cchrisw@sous-sol.org\u003e\nAcked-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nAcked-by: Olof Johansson \u003colof@lixom.net\u003e\n"
    },
    {
      "commit": "f87e4cac4f4e940b328d3deb5b53e642e3881f43",
      "tree": "7409f86561e5f97459378abd2ae21e9a5c82bfea",
      "parents": [
        "ab55028886dd1dd54585f22bf19a00eb23869340"
      ],
      "author": {
        "name": "Jeremy Fitzhardinge",
        "email": "jeremy@xensource.com",
        "time": "Tue Jul 17 18:37:06 2007 -0700"
      },
      "committer": {
        "name": "Jeremy Fitzhardinge",
        "email": "jeremy@goop.org",
        "time": "Wed Jul 18 08:47:44 2007 -0700"
      },
      "message": "xen: SMP guest support\n\nThis is a fairly straightforward Xen implementation of smp_ops.\n\nXen has its own IPI mechanisms, and has no dependency on any\nAPIC-based IPI.  The smp_ops hooks and the flush_tlb_others pv_op\nallow a Xen guest to avoid all APIC code in arch/i386 (the only apic\noperation is a single apic_read for the apic version number).\n\nOne subtle point which needs to be addressed is unpinning pagetables\nwhen another cpu may have a lazy tlb reference to the pagetable. Xen\nwill not allow an in-use pagetable to be unpinned, so we must find any\nother cpus with a reference to the pagetable and get them to shoot\ndown their references.\n\nSigned-off-by: Jeremy Fitzhardinge \u003cjeremy@xensource.com\u003e\nSigned-off-by: Chris Wright \u003cchrisw@sous-sol.org\u003e\nCc: Benjamin LaHaise \u003cbcrl@kvack.org\u003e\nCc: Ingo Molnar \u003cmingo@redhat.com\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\n"
    },
    {
      "commit": "e46cdb66c8fc1c8d61cfae0f219ff47ac4b9d531",
      "tree": "7d9cdfef91e69fcfcba762a5a70cd58900308a5b",
      "parents": [
        "3b827c1b3aadf3adb4c602d19863f2d24e7cbc18"
      ],
      "author": {
        "name": "Jeremy Fitzhardinge",
        "email": "jeremy@xensource.com",
        "time": "Tue Jul 17 18:37:05 2007 -0700"
      },
      "committer": {
        "name": "Jeremy Fitzhardinge",
        "email": "jeremy@goop.org",
        "time": "Wed Jul 18 08:47:42 2007 -0700"
      },
      "message": "xen: event channels\n\nXen implements interrupts in terms of event channels.  Each guest\ndomain gets 1024 event channels which can be used for a variety of\npurposes, such as Xen timer events, inter-domain events,\ninter-processor events (IPI) or for real hardware IRQs.\n\nWithin the kernel, we map the event channels to IRQs, and implement\nthe whole interrupt handling using a Xen irq_chip.\n\nRather than setting NR_IRQ to 1024 under PARAVIRT in order to\naccomodate Xen, we create a dynamic mapping between event channels and\nIRQs.  Ideally, Linux will eventually move towards dynamically\nallocating per-irq structures, and we can use a 1:1 mapping between\nevent channels and irqs.\n\nSigned-off-by: Jeremy Fitzhardinge \u003cjeremy@xensource.com\u003e\nSigned-off-by: Chris Wright \u003cchrisw@sous-sol.org\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Eric W. Biederman \u003cebiederm@xmission.com\u003e\n"
    }
  ]
}