x86/pci: Treat EfiMemoryMappedIO as reservation of ECAM space

Normally we reject ECAM space unless it is reported as reserved in the E820
table or via a PNP0C02 _CRS method (PCI Firmware, r3.3, sec 4.1.2).

07eab0901ede ("efi/x86: Remove EfiMemoryMappedIO from E820 map"), removes
E820 entries that correspond to EfiMemoryMappedIO regions because some
other firmware uses EfiMemoryMappedIO for PCI host bridge windows, and the
E820 entries prevent Linux from allocating BAR space for hot-added devices.

Some firmware doesn't report ECAM space via PNP0C02 _CRS methods, but does
mention it as an EfiMemoryMappedIO region via EFI GetMemoryMap(), which is
normally converted to an E820 entry by a bootloader or EFI stub.  After
07eab0901ede, that E820 entry is removed, so we reject this ECAM space,
which makes PCI extended config space (offsets 0x100-0xfff) inaccessible.

The lack of extended config space breaks anything that relies on it,
including perf, VSEC telemetry, EDAC, QAT, SR-IOV, etc.

Allow use of ECAM for extended config space when the region is covered by
an EfiMemoryMappedIO region, even if it's not included in E820 or PNP0C02
_CRS.

Link: https://lore.kernel.org/r/[email protected]
Link: https://bugzilla.kernel.org/show_bug.cgi?id=216891
Fixes: 07eab0901ede ("efi/x86: Remove EfiMemoryMappedIO from E820 map")
Link: https://lore.kernel.org/r/[email protected]
Reported-by: Kan Liang <[email protected]>
Reported-by: Tony Luck <[email protected]>
Reported-by: Giovanni Cabiddu <[email protected]>
Reported-by: Yunying Sun <[email protected]>
Reported-by: Baowen Zheng <[email protected]>
Reported-by: Zhenzhong Duan <[email protected]>
Reported-by: Yang Lixiao <[email protected]>
Tested-by: Tony Luck <[email protected]>
Tested-by: Giovanni Cabiddu <[email protected]>
Tested-by: Kan Liang <[email protected]>
Tested-by: Yunying Sun <[email protected]>
Signed-off-by: Bjorn Helgaas <[email protected]>
Reviewed-by: Dan Williams <[email protected]>
Reviewed-by: Rafael J. Wysocki <[email protected]>

diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 51c951699b2ed41c23d1945bd25f57f7fdb8749d..4b3efaa82ab7c14a747cea8dbe50ad6645cf1981 100644 (file)
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/acpi.h>
+#include <linux/efi.h>
 #include <linux/pci.h>
 #include <linux/init.h>
 #include <linux/bitmap.h>
@@ -442,6 +443,32 @@ static bool is_acpi_reserved(u64 start, u64 end, enum e820_type not_used)
        return mcfg_res.flags;
 }
 
+static bool is_efi_mmio(u64 start, u64 end, enum e820_type not_used)
+{
+#ifdef CONFIG_EFI
+       efi_memory_desc_t *md;
+       u64 size, mmio_start, mmio_end;
+
+       for_each_efi_memory_desc(md) {
+               if (md->type == EFI_MEMORY_MAPPED_IO) {
+                       size = md->num_pages << EFI_PAGE_SHIFT;
+                       mmio_start = md->phys_addr;
+                       mmio_end = mmio_start + size;
+
+                       /*
+                        * N.B. Caller supplies (start, start + size),
+                        * so to match, mmio_end is the first address
+                        * *past* the EFI_MEMORY_MAPPED_IO area.
+                        */
+                       if (mmio_start <= start && end <= mmio_end)
+                               return true;
+               }
+       }
+#endif
+
+       return false;
+}
+
 typedef bool (*check_reserved_t)(u64 start, u64 end, enum e820_type type);
 
 static bool __ref is_mmconf_reserved(check_reserved_t is_reserved,
@@ -513,6 +540,10 @@ pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int e
                               "MMCONFIG at %pR not reserved in "
                               "ACPI motherboard resources\n",
                               &cfg->res);
+
+               if (is_mmconf_reserved(is_efi_mmio, cfg, dev,
+                                      "EfiMemoryMappedIO"))
+                       return true;
        }
 
        /*