)]}'
{
  "commit": "d510d6cc653bc4b3094ea73afe12600d0ab445b3",
  "tree": "60ea170465dcddcd5cdd7c29a29df3f28407c202",
  "parents": [
    "2350bd1f62c8706c22b8e58c3bfff10806c0a31b"
  ],
  "author": {
    "name": "Sheng Yang",
    "email": "sheng@linux.intel.com",
    "time": "Wed Feb 25 17:22:28 2009 +0800"
  },
  "committer": {
    "name": "Avi Kivity",
    "email": "avi@redhat.com",
    "time": "Wed Jun 10 11:48:23 2009 +0300"
  },
  "message": "KVM: Enable MSI-X for KVM assigned device\n\nThis patch finally enable MSI-X.\n\nWhat we need for MSI-X:\n1. Intercept one page in MMIO region of device. So that we can get guest desired\nMSI-X table and set up the real one. Now this have been done by guest, and\ntransfer to kernel using ioctl KVM_SET_MSIX_NR and KVM_SET_MSIX_ENTRY.\n\n2. Information for incoming interrupt. Now one device can have more than one\ninterrupt, and they are all handled by one workqueue structure. So we need to\nidentify them. The previous patch enable gsi_msg_pending_bitmap get this done.\n\n3. Mapping from host IRQ to guest gsi as well as guest gsi to real MSI/MSI-X\nmessage address/data. We used same entry number for the host and guest here, so\nthat it\u0027s easy to find the correlated guest gsi.\n\nWhat we lack for now:\n1. The PCI spec said nothing can existed with MSI-X table in the same page of\nMMIO region, except pending bits. The patch ignore pending bits as the first\nstep (so they are always 0 - no pending).\n\n2. The PCI spec allowed to change MSI-X table dynamically. That means, the OS\ncan enable MSI-X, then mask one MSI-X entry, modify it, and unmask it. The patch\ndidn\u0027t support this, and Linux also don\u0027t work in this way.\n\n3. The patch didn\u0027t implement MSI-X mask all and mask single entry. I would\nimplement the former in driver/pci/msi.c later. And for single entry, userspace\nshould have reposibility to handle it.\n\nSigned-off-by: Sheng Yang \u003csheng@linux.intel.com\u003e\nSigned-off-by: Avi Kivity \u003cavi@redhat.com\u003e\n",
  "tree_diff": [
    {
      "type": "modify",
      "old_id": "dc3f6cf117045ee50b2e92aa87a9b772ce8150bd",
      "old_mode": 33188,
      "old_path": "arch/x86/include/asm/kvm.h",
      "new_id": "125be8b19568e2828614d85b741d5ee2e2a53535",
      "new_mode": 33188,
      "new_path": "arch/x86/include/asm/kvm.h"
    },
    {
      "type": "modify",
      "old_id": "78cdee8c63556a8ba315758d12e031631d7a6fef",
      "old_mode": 33188,
      "old_path": "include/linux/kvm.h",
      "new_id": "640835ed2708d3914b97dc700271da0f38297f49",
      "new_mode": 33188,
      "new_path": "include/linux/kvm.h"
    },
    {
      "type": "modify",
      "old_id": "8bd44d6985c7a1e444ee40768658f5a6c3b73956",
      "old_mode": 33188,
      "old_path": "virt/kvm/kvm_main.c",
      "new_id": "3bed82754a5dec7941365ecf158efed2d3f7a95f",
      "new_mode": 33188,
      "new_path": "virt/kvm/kvm_main.c"
    }
  ]
}