[XEN PATCH v4] hvmloader: Enable MMIO and I/O decode, after all resource allocation

[Harsha Shamsundara Havanur <havanur@xxxxxxxxxx>]

It was observed that PCI MMIO and/or IO BARs were programmed with
memory and I/O decodes (bits 0 and 1 of PCI COMMAND register) enabled,
during PCI setup phase. This resulted in incorrect memory mapping as
soon as the lower half of the 64 bit bar is programmed.
This displaced any RAM mappings under 4G. After the
upper half is programmed PCI memory mapping is restored to its
intended high mem location, but the RAM displaced is not restored.
The OS then continues to boot and function until it tries to access
the displaced RAM at which point it suffers a page fault and crashes.

This patch address the issue by deferring enablement of memory and
I/O decode in command register until all the resources, like interrupts
I/O and/or MMIO BARs for all the PCI device functions are programmed,
in the descending order of memory requested.

Signed-off-by: Harsha Shamsundara Havanur <havanur@xxxxxxxxxx>

---
Changes in v4:
  Addressed review comments from Jan Beulich <jbeulich@xxxxxxxx>
  - Disable decodes before writing ~0 to BARs
  - Enable BUS MASTER at the end along with decode bits

Changes in v3:
  - Retained enabling of BUS master for all device functions as
    was in original commit

Changes in v2:
  - BUS MASTER state was captured and restored to the same state
    while enabling decode bits.
---
---
 tools/firmware/hvmloader/pci.c | 45 ++++++++++++++++++++++++++++++------------
 1 file changed, 32 insertions(+), 13 deletions(-)

diff --git a/tools/firmware/hvmloader/pci.c b/tools/firmware/hvmloader/pci.c
index 0b708bf578..69c30f0548 100644
--- a/tools/firmware/hvmloader/pci.c
+++ b/tools/firmware/hvmloader/pci.c
@@ -84,6 +84,7 @@ void pci_setup(void)
     uint32_t vga_devfn = 256;
     uint16_t class, vendor_id, device_id;
     unsigned int bar, pin, link, isa_irq;
+    uint8_t pci_devfn_decode_type[256] = {};
 
     /* Resources assignable to PCI devices via BARs. */
     struct resource {
@@ -120,6 +121,11 @@ void pci_setup(void)
      */
     bool allow_memory_relocate = 1;
 
+    BUILD_BUG_ON((typeof(*pci_devfn_decode_type))PCI_COMMAND_MEMORY
+            != PCI_COMMAND_MEMORY);
+    BUILD_BUG_ON((typeof(*pci_devfn_decode_type))PCI_COMMAND_IO
+            != PCI_COMMAND_IO);
+
     s = xenstore_read(HVM_XS_ALLOW_MEMORY_RELOCATE, NULL);
     if ( s )
         allow_memory_relocate = strtoll(s, NULL, 0);
@@ -208,6 +214,20 @@ void pci_setup(void)
             break;
         }
 
+        /*
+         * Disable memory and I/O decode,
+         * It is recommended that BAR programming be done whilst
+         * decode bits are cleared to avoid incorrect mappings being created,
+         * when 64-bit memory BAR is programmed first by writing the lower half
+         * and then the upper half, which first maps to an address under 4G
+         * replacing any RAM mapped in that address, which is not restored
+         * back after the upper half is written and PCI memory is correctly
+         * mapped to its intended high mem address.
+         */
+        cmd = pci_readw(devfn, PCI_COMMAND);
+        cmd &= ~(PCI_COMMAND_MEMORY | PCI_COMMAND_IO);
+        pci_writew(devfn, PCI_COMMAND, cmd);
+
         /* Map the I/O memory and port resources. */
         for ( bar = 0; bar < 7; bar++ )
         {
@@ -289,10 +309,6 @@ void pci_setup(void)
                    devfn>>3, devfn&7, 'A'+pin-1, isa_irq);
         }
 
-        /* Enable bus mastering. */
-        cmd = pci_readw(devfn, PCI_COMMAND);
-        cmd |= PCI_COMMAND_MASTER;
-        pci_writew(devfn, PCI_COMMAND, cmd);
     }
 
     if ( mmio_hole_size )
@@ -497,16 +513,12 @@ void pci_setup(void)
                PRIllx_arg(bar_sz),
                bar_data_upper, bar_data);
                        
-
-        /* Now enable the memory or I/O mapping. */
-        cmd = pci_readw(devfn, PCI_COMMAND);
         if ( (bar_reg == PCI_ROM_ADDRESS) ||
              ((bar_data & PCI_BASE_ADDRESS_SPACE) ==
               PCI_BASE_ADDRESS_SPACE_MEMORY) )
-            cmd |= PCI_COMMAND_MEMORY;
+            pci_devfn_decode_type[devfn] |= PCI_COMMAND_MEMORY;
         else
-            cmd |= PCI_COMMAND_IO;
-        pci_writew(devfn, PCI_COMMAND, cmd);
+            pci_devfn_decode_type[devfn] |= PCI_COMMAND_IO;
     }
 
     if ( pci_hi_mem_start )
@@ -526,10 +538,17 @@ void pci_setup(void)
          * has IO enabled, even if there is no I/O BAR on that
          * particular device.
          */
-        cmd = pci_readw(vga_devfn, PCI_COMMAND);
-        cmd |= PCI_COMMAND_IO;
-        pci_writew(vga_devfn, PCI_COMMAND, cmd);
+        pci_devfn_decode_type[vga_devfn] |= PCI_COMMAND_IO;
     }
+
+    /* Enable bus master, memory and I/O decode. */
+    for ( devfn = 0; devfn < 256; devfn++ )
+        if ( pci_devfn_decode_type[devfn] )
+        {
+            cmd = pci_readw(devfn, PCI_COMMAND);
+            cmd |= (PCI_COMMAND_MASTER | pci_devfn_decode_type[devfn]);
+            pci_writew(devfn, PCI_COMMAND, cmd);
+        }
 }
 
 /*
-- 
2.16.6