[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [PATCH v6 16/16] pci: remove hard-coded bar size in msix_in
From: |
Jason Wang |
Subject: |
[Qemu-devel] [PATCH v6 16/16] pci: remove hard-coded bar size in msix_init_exclusive_bar() |
Date: |
Fri, 17 Apr 2015 12:48:40 +0800 |
This patch lets msix_init_exclusive_bar() can calculate the bar and
pba size based on the number of MSI-X vectors other than using a
hard-coded limit 4096. This is needed to allow device to have more
than 128 MSI_X vectors. To keep migration compatibility, keep using
4096 as bar size and 2048 for pba offset.
Notes: We don't care about the case that using vectors > 128 for
legacy machine type. Since we limit the queue max to 64, so vectors >=
65 is meaningless.
Virtio device will be the first user for this.
Cc: Keith Busch <address@hidden>
Cc: Kevin Wolf <address@hidden>
Cc: Stefan Hajnoczi <address@hidden>
Cc: Michael S. Tsirkin <address@hidden>
Signed-off-by: Jason Wang <address@hidden>
---
hw/pci/msix.c | 30 +++++++++++++++++++-----------
1 file changed, 19 insertions(+), 11 deletions(-)
diff --git a/hw/pci/msix.c b/hw/pci/msix.c
index 24de260..f8748cf 100644
--- a/hw/pci/msix.c
+++ b/hw/pci/msix.c
@@ -295,29 +295,37 @@ int msix_init_exclusive_bar(PCIDevice *dev, unsigned
short nentries,
{
int ret;
char *name;
+ uint32_t bar_size = 4096;
+ uint32_t bar_pba_offset = bar_size / 2;
+ uint32_t bar_pba_size = (nentries / 8 + 1) * 8;
/*
* Migration compatibility dictates that this remains a 4k
* BAR with the vector table in the lower half and PBA in
- * the upper half. Do not use these elsewhere!
+ * the upper half for nentries which is lower or equal to 128.
+ * No need to care about using more than 65 entries for legacy
+ * machine types who has at most 64 queues.
*/
-#define MSIX_EXCLUSIVE_BAR_SIZE 4096
-#define MSIX_EXCLUSIVE_BAR_TABLE_OFFSET 0
-#define MSIX_EXCLUSIVE_BAR_PBA_OFFSET (MSIX_EXCLUSIVE_BAR_SIZE / 2)
-#define MSIX_EXCLUSIVE_CAP_OFFSET 0
+ if (nentries * PCI_MSIX_ENTRY_SIZE > bar_pba_offset) {
+ bar_pba_offset = nentries * PCI_MSIX_ENTRY_SIZE;
+ }
- if (nentries * PCI_MSIX_ENTRY_SIZE > MSIX_EXCLUSIVE_BAR_PBA_OFFSET) {
- return -EINVAL;
+ if (bar_pba_offset + bar_pba_size > 4096) {
+ bar_size = bar_pba_offset + bar_pba_size;
+ }
+
+ if (bar_size & (bar_size - 1)) {
+ bar_size = 1 << qemu_fls(bar_size);
}
name = g_strdup_printf("%s-msix", dev->name);
- memory_region_init(&dev->msix_exclusive_bar, OBJECT(dev), name,
MSIX_EXCLUSIVE_BAR_SIZE);
+ memory_region_init(&dev->msix_exclusive_bar, OBJECT(dev), name, bar_size);
g_free(name);
ret = msix_init(dev, nentries, &dev->msix_exclusive_bar, bar_nr,
- MSIX_EXCLUSIVE_BAR_TABLE_OFFSET, &dev->msix_exclusive_bar,
- bar_nr, MSIX_EXCLUSIVE_BAR_PBA_OFFSET,
- MSIX_EXCLUSIVE_CAP_OFFSET);
+ 0, &dev->msix_exclusive_bar,
+ bar_nr, bar_pba_offset,
+ 0);
if (ret) {
return ret;
}
--
2.1.0
- [Qemu-devel] [PATCH v6 06/16] monitor: check return value of qemu_find_net_clients_except(), (continued)
- [Qemu-devel] [PATCH v6 06/16] monitor: check return value of qemu_find_net_clients_except(), Jason Wang, 2015/04/17
- [Qemu-devel] [PATCH v6 05/16] monitor: replace the magic number 255 with MAX_QUEUE_NUM, Jason Wang, 2015/04/17
- [Qemu-devel] [PATCH v6 07/16] virtio-ccw: using VIRTIO_NO_VECTOR instead of 0 for invalid virtqueue, Jason Wang, 2015/04/17
- [Qemu-devel] [PATCH v6 09/16] virtio-ccw: introduce ccw specific queue limit, Jason Wang, 2015/04/17
- [Qemu-devel] [PATCH v6 11/16] virtio-mmio: switch to bus specific queue limit, Jason Wang, 2015/04/17
- [Qemu-devel] [PATCH v6 12/16] virtio-pci: switch to use bus specific queue limit, Jason Wang, 2015/04/17
- [Qemu-devel] [PATCH v6 14/16] virtio-pci: speedup MSI-X masking and unmasking, Jason Wang, 2015/04/17
- [Qemu-devel] [PATCH v6 15/16] virtio-pci: increase the maximum number of virtqueues to 513, Jason Wang, 2015/04/17
- [Qemu-devel] [PATCH v6 16/16] pci: remove hard-coded bar size in msix_init_exclusive_bar(),
Jason Wang <=
- [Qemu-devel] [PATCH v6 13/16] virtio: introduce vector to virtqueues mapping, Jason Wang, 2015/04/17
- [Qemu-devel] [PATCH v6 10/16] virtio-s390: switch to bus specific queue limit, Jason Wang, 2015/04/17
- [Qemu-devel] [PATCH v6 08/16] virtio: introduce bus specific queue limit, Jason Wang, 2015/04/17