[PATCH 2/2] Do not access /dev/mem in MSI-X PCI passthrough on Xen

[Marek Marczykowski-Górecki]

The /dev/mem is used for two purposes:
 - reading PCI_MSIX_ENTRY_CTRL_MASKBIT
 - reading Pending Bit Array (PBA)

The first one was originally done because when Xen did not send all
vector ctrl writes to the device model, so QEMU might have outdated old
register value. This has been changed in Xen, so QEMU can now use its
cached value of the register instead.

The Pending Bit Array (PBA) handling is for the case where it lives on
the same page as the MSI-X table itself. Xen has been extended to handle
this case too (as well as other registers that may live on those pages),
so QEMU handling is not necessary anymore.

Removing /dev/mem access is useful to work within stubdomain, and
necessary when dom0 kernel runs in lockdown mode.

Signed-off-by: Marek Marczykowski-Górecki <marmarek@invisiblethingslab.com>
---
 hw/xen/xen_pt.h     |  1 -
 hw/xen/xen_pt_msi.c | 51 ++++-----------------------------------------
 2 files changed, 4 insertions(+), 48 deletions(-)

diff --git a/hw/xen/xen_pt.h b/hw/xen/xen_pt.h
index e7c4316a7d..de4094e7ec 100644
--- a/hw/xen/xen_pt.h
+++ b/hw/xen/xen_pt.h
@@ -206,7 +206,6 @@ typedef struct XenPTMSIX {
     uint32_t table_offset_adjust; /* page align mmap */
     uint64_t mmio_base_addr;
     MemoryRegion mmio;
-    void *phys_iomem_base;
     XenPTMSIXEntry msix_entry[];
 } XenPTMSIX;
 
diff --git a/hw/xen/xen_pt_msi.c b/hw/xen/xen_pt_msi.c
index b71563f98a..a8a75dff66 100644
--- a/hw/xen/xen_pt_msi.c
+++ b/hw/xen/xen_pt_msi.c
@@ -460,15 +460,7 @@ static void pci_msix_write(void *opaque, hwaddr addr,
         entry->updated = true;
     } else if (msix->enabled && entry->updated &&
                !(val & PCI_MSIX_ENTRY_CTRL_MASKBIT)) {
-        const volatile uint32_t *vec_ctrl;
-
-        /*
-         * If Xen intercepts the mask bit access, entry->vec_ctrl may not be
-         * up-to-date. Read from hardware directly.
-         */
-        vec_ctrl = s->msix->phys_iomem_base + entry_nr * PCI_MSIX_ENTRY_SIZE
-            + PCI_MSIX_ENTRY_VECTOR_CTRL;
-        xen_pt_msix_update_one(s, entry_nr, *vec_ctrl);
+        xen_pt_msix_update_one(s, entry_nr, entry->latch(VECTOR_CTRL));
     }
 
     set_entry_value(entry, offset, val);
@@ -493,7 +485,9 @@ static uint64_t pci_msix_read(void *opaque, hwaddr addr,
         return get_entry_value(&msix->msix_entry[entry_nr], offset);
     } else {
         /* Pending Bit Array (PBA) */
-        return *(uint32_t *)(msix->phys_iomem_base + addr);
+        XEN_PT_LOG(&s->dev, "reading PBA, addr %#lx, offset %#lx\n",
+                   addr, addr - msix->total_entries * PCI_MSIX_ENTRY_SIZE);
+        return 0xFFFFFFFF;
     }
 }
 
@@ -529,7 +523,6 @@ int xen_pt_msix_init(XenPCIPassthroughState *s, uint32_t 
base)
     int i, total_entries, bar_index;
     XenHostPCIDevice *hd = &s->real_device;
     PCIDevice *d = &s->dev;
-    int fd = -1;
     XenPTMSIX *msix = NULL;
     int rc = 0;
 
@@ -576,34 +569,6 @@ int xen_pt_msix_init(XenPCIPassthroughState *s, uint32_t 
base)
     msix->table_base = s->real_device.io_regions[bar_index].base_addr;
     XEN_PT_LOG(d, "get MSI-X table BAR base 0x%"PRIx64"\n", msix->table_base);
 
-    fd = open("/dev/mem", O_RDWR);
-    if (fd == -1) {
-        rc = -errno;
-        XEN_PT_ERR(d, "Can't open /dev/mem: %s\n", strerror(errno));
-        goto error_out;
-    }
-    XEN_PT_LOG(d, "table_off = 0x%x, total_entries = %d\n",
-               table_off, total_entries);
-    msix->table_offset_adjust = table_off & 0x0fff;
-    msix->phys_iomem_base =
-        mmap(NULL,
-             total_entries * PCI_MSIX_ENTRY_SIZE + msix->table_offset_adjust,
-             PROT_READ,
-             MAP_SHARED | MAP_LOCKED,
-             fd,
-             msix->table_base + table_off - msix->table_offset_adjust);
-    close(fd);
-    if (msix->phys_iomem_base == MAP_FAILED) {
-        rc = -errno;
-        XEN_PT_ERR(d, "Can't map physical MSI-X table: %s\n", strerror(errno));
-        goto error_out;
-    }
-    msix->phys_iomem_base = (char *)msix->phys_iomem_base
-        + msix->table_offset_adjust;
-
-    XEN_PT_LOG(d, "mapping physical MSI-X table to %p\n",
-               msix->phys_iomem_base);
-
     memory_region_add_subregion_overlap(&s->bar[bar_index], table_off,
                                         &msix->mmio,
                                         2); /* Priority: pci default + 1 */
@@ -624,14 +589,6 @@ void xen_pt_msix_unmap(XenPCIPassthroughState *s)
         return;
     }
 
-    /* unmap the MSI-X memory mapped register area */
-    if (msix->phys_iomem_base) {
-        XEN_PT_LOG(&s->dev, "unmapping physical MSI-X table from %p\n",
-                   msix->phys_iomem_base);
-        munmap(msix->phys_iomem_base, msix->total_entries * PCI_MSIX_ENTRY_SIZE
-               + msix->table_offset_adjust);
-    }
-
     memory_region_del_subregion(&s->bar[msix->bar_index], &msix->mmio);
 }
 
-- 
2.37.3