[Qemu-devel] [PATCH 33/39] msix: convert to memory API

[Avi Kivity <avi@redhat.com>]

The msix table is defined as a subregion, to allow for a BAR that
mixes device specific regions with the msix table.

Signed-off-by: Avi Kivity <avi@redhat.com>
---
 hw/ivshmem.c    |   11 +++++----
 hw/msix.c       |   64 +++++++++++++++++++------------------------------------
 hw/msix.h       |    6 +---
 hw/pci.h        |    2 +-
 hw/virtio-pci.c |   16 ++++++++-----
 hw/virtio-pci.h |    1 +
 6 files changed, 42 insertions(+), 58 deletions(-)

diff --git a/hw/ivshmem.c b/hw/ivshmem.c
index f80e7b6..bacba60 100644
--- a/hw/ivshmem.c
+++ b/hw/ivshmem.c
@@ -65,6 +65,7 @@ typedef struct IVShmemState {
      */
     MemoryRegion bar;
     MemoryRegion ivshmem;
+    MemoryRegion msix_bar;
     uint64_t ivshmem_size; /* size of shared memory region */
     int shm_fd; /* shared memory file descriptor */
 
@@ -540,11 +541,11 @@ static void ivshmem_setup_msi(IVShmemState * s) {
 
     /* allocate the MSI-X vectors */
 
-    if (!msix_init(&s->dev, s->vectors, 1, 0)) {
-        pci_register_bar(&s->dev, 1,
-                         msix_bar_size(&s->dev),
-                         PCI_BASE_ADDRESS_SPACE_MEMORY,
-                         msix_mmio_map);
+    memory_region_init(&s->msix_bar, "ivshmem-msix", 4096);
+    if (!msix_init(&s->dev, s->vectors, &s->msix_bar, 1, 0)) {
+        pci_register_bar_region(&s->dev, 1,
+                                PCI_BASE_ADDRESS_SPACE_MEMORY,
+                                &s->msix_bar);
         IVSHMEM_DPRINTF("msix initialized (%d vectors)\n", s->vectors);
     } else {
         IVSHMEM_DPRINTF("msix initialization failed\n");
diff --git a/hw/msix.c b/hw/msix.c
index e67e700..8536c3f 100644
--- a/hw/msix.c
+++ b/hw/msix.c
@@ -82,7 +82,8 @@ static int msix_add_config(struct PCIDevice *pdev, unsigned short nentries,
     return 0;
 }
 
-static uint32_t msix_mmio_readl(void *opaque, target_phys_addr_t addr)
+static uint64_t msix_mmio_read(void *opaque, target_phys_addr_t addr,
+                               unsigned size)
 {
     PCIDevice *dev = opaque;
     unsigned int offset = addr & (MSIX_PAGE_SIZE - 1) & ~0x3;
@@ -91,12 +92,6 @@ static uint32_t msix_mmio_readl(void *opaque, target_phys_addr_t addr)
     return pci_get_long(page + offset);
 }
 
-static uint32_t msix_mmio_read_unallowed(void *opaque, target_phys_addr_t addr)
-{
-    fprintf(stderr, "MSI-X: only dword read is allowed!\n");
-    return 0;
-}
-
 static uint8_t msix_pending_mask(int vector)
 {
     return 1 << (vector % 8);
@@ -169,8 +164,8 @@ void msix_write_config(PCIDevice *dev, uint32_t addr,
     }
 }
 
-static void msix_mmio_writel(void *opaque, target_phys_addr_t addr,
-                             uint32_t val)
+static void msix_mmio_write(void *opaque, target_phys_addr_t addr,
+                            uint64_t val, unsigned size)
 {
     PCIDevice *dev = opaque;
     unsigned int offset = addr & (MSIX_PAGE_SIZE - 1) & ~0x3;
@@ -179,37 +174,25 @@ static void msix_mmio_writel(void *opaque, target_phys_addr_t addr,
     msix_handle_mask_update(dev, vector);
 }
 
-static void msix_mmio_write_unallowed(void *opaque, target_phys_addr_t addr,
-                                      uint32_t val)
-{
-    fprintf(stderr, "MSI-X: only dword write is allowed!\n");
-}
-
-static CPUWriteMemoryFunc * const msix_mmio_write[] = {
-    msix_mmio_write_unallowed, msix_mmio_write_unallowed, msix_mmio_writel
-};
-
-static CPUReadMemoryFunc * const msix_mmio_read[] = {
-    msix_mmio_read_unallowed, msix_mmio_read_unallowed, msix_mmio_readl
+static const MemoryRegionOps msix_mmio_ops = {
+    .read = msix_mmio_read,
+    .write = msix_mmio_write,
+    .endianness = DEVICE_NATIVE_ENDIAN,
+    .valid = {
+        .min_access_size = 4,
+        .max_access_size = 4,
+    },
 };
 
-/* Should be called from device's map method. */
-void msix_mmio_map(PCIDevice *d, int region_num,
-                   pcibus_t addr, pcibus_t size, int type)
+static void msix_mmio_setup(PCIDevice *d, MemoryRegion *bar)
 {
     uint8_t *config = d->config + d->msix_cap;
     uint32_t table = pci_get_long(config + PCI_MSIX_TABLE);
     uint32_t offset = table & ~(MSIX_PAGE_SIZE - 1);
     /* TODO: for assigned devices, we'll want to make it possible to map
      * pending bits separately in case they are in a separate bar. */
-    int table_bir = table & PCI_MSIX_FLAGS_BIRMASK;
 
-    if (table_bir != region_num)
-        return;
-    if (size <= offset)
-        return;
-    cpu_register_physical_memory(addr + offset, size - offset,
-                                 d->msix_mmio_index);
+    memory_region_add_subregion(bar, offset, &d->msix_mmio);
 }
 
 static void msix_mask_all(struct PCIDevice *dev, unsigned nentries)
@@ -225,6 +208,7 @@ static void msix_mask_all(struct PCIDevice *dev, unsigned nentries)
 /* Initialize the MSI-X structures. Note: if MSI-X is supported, BAR size is
  * modified, it should be retrieved with msix_bar_size. */
 int msix_init(struct PCIDevice *dev, unsigned short nentries,
+              MemoryRegion *bar,
               unsigned bar_nr, unsigned bar_size)
 {
     int ret;
@@ -241,13 +225,8 @@ int msix_init(struct PCIDevice *dev, unsigned short nentries,
     dev->msix_table_page = qemu_mallocz(MSIX_PAGE_SIZE);
     msix_mask_all(dev, nentries);
 
-    dev->msix_mmio_index = cpu_register_io_memory(msix_mmio_read,
-                                                  msix_mmio_write, dev,
-                                                  DEVICE_NATIVE_ENDIAN);
-    if (dev->msix_mmio_index == -1) {
-        ret = -EBUSY;
-        goto err_index;
-    }
+    memory_region_init_io(&dev->msix_mmio, &msix_mmio_ops, dev,
+                          "msix", MSIX_PAGE_SIZE);
 
     dev->msix_entries_nr = nentries;
     ret = msix_add_config(dev, nentries, bar_nr, bar_size);
@@ -255,12 +234,12 @@ int msix_init(struct PCIDevice *dev, unsigned short nentries,
         goto err_config;
 
     dev->cap_present |= QEMU_PCI_CAP_MSIX;
+    msix_mmio_setup(dev, bar);
     return 0;
 
 err_config:
     dev->msix_entries_nr = 0;
-    cpu_unregister_io_memory(dev->msix_mmio_index);
-err_index:
+    memory_region_destroy(&dev->msix_mmio);
     qemu_free(dev->msix_table_page);
     dev->msix_table_page = NULL;
     qemu_free(dev->msix_entry_used);
@@ -279,7 +258,7 @@ static void msix_free_irq_entries(PCIDevice *dev)
 }
 
 /* Clean up resources for the device. */
-int msix_uninit(PCIDevice *dev)
+int msix_uninit(PCIDevice *dev, MemoryRegion *bar)
 {
     if (!(dev->cap_present & QEMU_PCI_CAP_MSIX))
         return 0;
@@ -287,7 +266,8 @@ int msix_uninit(PCIDevice *dev)
     dev->msix_cap = 0;
     msix_free_irq_entries(dev);
     dev->msix_entries_nr = 0;
-    cpu_unregister_io_memory(dev->msix_mmio_index);
+    memory_region_del_subregion(bar, &dev->msix_mmio);
+    memory_region_destroy(&dev->msix_mmio);
     qemu_free(dev->msix_table_page);
     dev->msix_table_page = NULL;
     qemu_free(dev->msix_entry_used);
diff --git a/hw/msix.h b/hw/msix.h
index a9f7993..7e04336 100644
--- a/hw/msix.h
+++ b/hw/msix.h
@@ -5,15 +5,13 @@
 #include "pci.h"
 
 int msix_init(PCIDevice *pdev, unsigned short nentries,
+              MemoryRegion *bar,
               unsigned bar_nr, unsigned bar_size);
 
 void msix_write_config(PCIDevice *pci_dev, uint32_t address,
                        uint32_t val, int len);
 
-void msix_mmio_map(PCIDevice *pci_dev, int region_num,
-                   pcibus_t addr, pcibus_t size, int type);
-
-int msix_uninit(PCIDevice *d);
+int msix_uninit(PCIDevice *d, MemoryRegion *bar);
 
 void msix_save(PCIDevice *dev, QEMUFile *f);
 void msix_load(PCIDevice *dev, QEMUFile *f);
diff --git a/hw/pci.h b/hw/pci.h
index 928e96c..a95e2ad 100644
--- a/hw/pci.h
+++ b/hw/pci.h
@@ -176,7 +176,7 @@ struct PCIDevice {
     /* Space to store MSIX table */
     uint8_t *msix_table_page;
     /* MMIO index used to map MSIX table and pending bit entries. */
-    int msix_mmio_index;
+    MemoryRegion msix_mmio;
     /* Reference-count for entries actually in use by driver. */
     unsigned *msix_entry_used;
     /* Region including the MSI-X table */
diff --git a/hw/virtio-pci.c b/hw/virtio-pci.c
index c114e1a..2df59f0 100644
--- a/hw/virtio-pci.c
+++ b/hw/virtio-pci.c
@@ -645,11 +645,12 @@ void virtio_init_pci(VirtIOPCIProxy *proxy, VirtIODevice *vdev)
     pci_set_word(config + 0x2e, vdev->device_id);
     config[0x3d] = 1;
 
-    if (vdev->nvectors && !msix_init(&proxy->pci_dev, vdev->nvectors, 1, 0)) {
-        pci_register_bar(&proxy->pci_dev, 1,
-                         msix_bar_size(&proxy->pci_dev),
-                         PCI_BASE_ADDRESS_SPACE_MEMORY,
-                         msix_mmio_map);
+    memory_region_init(&proxy->msix_bar, "virtio-msix", 4096);
+    if (vdev->nvectors && !msix_init(&proxy->pci_dev, vdev->nvectors,
+                                     &proxy->msix_bar, 1, 0)) {
+        pci_register_bar_region(&proxy->pci_dev, 1,
+                                PCI_BASE_ADDRESS_SPACE_MEMORY,
+                                &proxy->msix_bar);
     } else
         vdev->nvectors = 0;
 
@@ -698,9 +699,12 @@ static int virtio_blk_init_pci(PCIDevice *pci_dev)
 static int virtio_exit_pci(PCIDevice *pci_dev)
 {
     VirtIOPCIProxy *proxy = DO_UPCAST(VirtIOPCIProxy, pci_dev, pci_dev);
+    int r;
 
     memory_region_destroy(&proxy->bar);
-    return msix_uninit(pci_dev);
+    r = msix_uninit(pci_dev, &proxy->msix_bar);
+    memory_region_destroy(&proxy->msix_bar);
+    return r;
 }
 
 static int virtio_blk_exit_pci(PCIDevice *pci_dev)
diff --git a/hw/virtio-pci.h b/hw/virtio-pci.h
index 5af1c8c..14c10f7 100644
--- a/hw/virtio-pci.h
+++ b/hw/virtio-pci.h
@@ -22,6 +22,7 @@ typedef struct {
     PCIDevice pci_dev;
     VirtIODevice *vdev;
     MemoryRegion bar;
+    MemoryRegion msix_bar;
     uint32_t flags;
     uint32_t class_code;
     uint32_t nvectors;
-- 
1.7.5.3