AMD/IOMMU: add "ivmd=" command line option

Just like VT-d's "rmrr=" it can be used to cover for firmware omissions.
Since systems surfacing IVMDs seem to be rare, it is also meant to allow
testing of the involved code.

Only the IVMD flavors actually understood by the IVMD parsing logic can
be generated, and for this initial implementation there's also no way to
control the flags field - unity r/w mappings are assumed.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Paul Durrant <paul@xen.org>

diff --git a/docs/misc/xen-command-line.pandoc b/docs/misc/xen-command-line.pandoc
index b175645fdebb84f6258bd4809f87bfec5b8a1ad2..177e656f12b731649ef4de0dcc1246f97d2d30e0 100644 (file)
--- a/docs/misc/xen-command-line.pandoc
+++ b/docs/misc/xen-command-line.pandoc
@@ -836,12 +836,12 @@ Controls for the dom0 IOMMU setup.
 
     Typically, some devices in a system use bits of RAM for communication, and
     these areas should be listed as reserved in the E820 table and identified
-    via RMRR or IVMD entries in the APCI tables, so Xen can ensure that they
+    via RMRR or IVMD entries in the ACPI tables, so Xen can ensure that they
     are identity-mapped in the IOMMU.  However, some firmware makes mistakes,
     and this option is a coarse-grain workaround for those errors.
 
     Where possible, finer grain corrections should be made with the `rmrr=`,
-    `ivrs_hpet=` or `ivrs_ioapic=` command line options.
+    `ivmd=`, `ivrs_hpet[]=`, or `ivrs_ioapic[]=` command line options.
 
     This option is disabled by default, and deprecated and intended for
     removal in future versions of Xen.  If specifying `map-inclusive` is the
@@ -1523,6 +1523,31 @@ _dom0-iommu=map-inclusive_ - using both options in combination is undefined.**
 > `= <integer>`
 
 ### irq_vector_map (x86)
+
+### ivmd (x86)
+> `= <start>[-<end>][=<bdf1>[-<bdf1'>][,<bdf2>[-<bdf2'>][,...]]][;<start>...]`
+
+Define IVMD-like ranges that are missing from ACPI tables along with the
+device(s) they belong to, and use them for 1:1 mapping.  End addresses can be
+omitted when exactly one page is meant.  The ranges are inclusive when start
+and end are specified.  Note that only PCI segment 0 is supported at this time,
+but it is fine to specify it explicitly.
+
+'start' and 'end' values are page numbers (not full physical addresses),
+in hexadecimal format (can optionally be preceded by "0x").
+
+Omitting the optional (range of) BDF spcifiers signals that the range is to
+be applied to all devices.
+
+Usage example: If device 0:0:1d.0 requires one page (0xd5d45) to be
+reserved, and devices 0:0:1a.0...0:0:1a.3 collectively require three pages
+(0xd5d46 thru 0xd5d48) to be reserved, one usage would be:
+
+ivmd=d5d45=0:1d.0;0xd5d46-0xd5d48=0:1a.0-0:1a.3
+
+Note: grub2 requires to escape or quote special characters, like ';' when
+multiple ranges are specified - refer to the grub2 documentation.
+
 ### ivrs_hpet[`<hpet>`] (AMD)
 > `=[<seg>:]<bus>:<device>.<func>`
 

diff --git a/xen/drivers/passthrough/amd/iommu_acpi.c b/xen/drivers/passthrough/amd/iommu_acpi.c
index 0860b23c8882cc76c9eb2ec5f84193df2b0e1220..53f4b61d0d030082b06a2b13f174e86a31576fc2 100644 (file)
--- a/xen/drivers/passthrough/amd/iommu_acpi.c
+++ b/xen/drivers/passthrough/amd/iommu_acpi.c
@@ -1049,6 +1049,9 @@ static void __init dump_acpi_table_header(struct acpi_table_header *table)
 
 }
 
+static struct acpi_ivrs_memory __initdata user_ivmds[8];
+static unsigned int __initdata nr_ivmd;
+
 #define to_ivhd_block(hdr) \
     container_of(hdr, const struct acpi_ivrs_hardware, header)
 #define to_ivmd_block(hdr) \
@@ -1072,7 +1075,7 @@ static int __init parse_ivrs_table(struct acpi_table_header *table)
 {
     const struct acpi_ivrs_header *ivrs_block;
     unsigned long length;
-    unsigned int apic;
+    unsigned int apic, i;
     bool_t sb_ioapic = !iommu_intremap;
     int error = 0;
 
@@ -1107,6 +1110,12 @@ static int __init parse_ivrs_table(struct acpi_table_header *table)
         length += ivrs_block->length;
     }
 
+    /* Add command line specified IVMD-equivalents. */
+    if ( nr_ivmd )
+        AMD_IOMMU_DEBUG("IVMD: %u command line provided entries\n", nr_ivmd);
+    for ( i = 0; !error && i < nr_ivmd; ++i )
+        error = parse_ivmd_block(user_ivmds + i);
+
     /* Each IO-APIC must have been mentioned in the table. */
     for ( apic = 0; !error && iommu_intremap && apic < nr_ioapics; ++apic )
     {
@@ -1348,3 +1357,80 @@ int __init amd_iommu_get_supported_ivhd_type(void)
 {
     return acpi_table_parse(ACPI_SIG_IVRS, get_supported_ivhd_type);
 }
+
+/*
+ * Parse "ivmd" command line option to later add the parsed devices / regions
+ * into unity mapping lists, just like IVMDs parsed from ACPI.
+ * Format:
+ * ivmd=<start>[-<end>][=<bdf1>[-<bdf1>'][,<bdf2>[-<bdf2>'][,...]]][;<start>...]
+ */
+static int __init parse_ivmd_param(const char *s)
+{
+    do {
+        unsigned long start, end;
+        const char *cur;
+
+        if ( nr_ivmd >= ARRAY_SIZE(user_ivmds) )
+            return -E2BIG;
+
+        start = simple_strtoul(cur = s, &s, 16);
+        if ( cur == s )
+            return -EINVAL;
+
+        if ( *s == '-' )
+        {
+            end = simple_strtoul(cur = s + 1, &s, 16);
+            if ( cur == s || end < start )
+                return -EINVAL;
+        }
+        else
+            end = start;
+
+        if ( *s != '=' )
+        {
+            user_ivmds[nr_ivmd].start_address = start << PAGE_SHIFT;
+            user_ivmds[nr_ivmd].memory_length = (end - start + 1) << PAGE_SHIFT;
+            user_ivmds[nr_ivmd].header.flags = ACPI_IVMD_UNITY |
+                                               ACPI_IVMD_READ | ACPI_IVMD_WRITE;
+            user_ivmds[nr_ivmd].header.length = sizeof(*user_ivmds);
+            user_ivmds[nr_ivmd].header.type = ACPI_IVRS_TYPE_MEMORY_ALL;
+            ++nr_ivmd;
+            continue;
+        }
+
+        do {
+            unsigned int seg, bus, dev, func;
+
+            if ( nr_ivmd >= ARRAY_SIZE(user_ivmds) )
+                return -E2BIG;
+
+            s = parse_pci(s + 1, &seg, &bus, &dev, &func);
+            if ( !s || seg )
+                return -EINVAL;
+
+            user_ivmds[nr_ivmd].start_address = start << PAGE_SHIFT;
+            user_ivmds[nr_ivmd].memory_length = (end - start + 1) << PAGE_SHIFT;
+            user_ivmds[nr_ivmd].header.flags = ACPI_IVMD_UNITY |
+                                               ACPI_IVMD_READ | ACPI_IVMD_WRITE;
+            user_ivmds[nr_ivmd].header.length = sizeof(*user_ivmds);
+            user_ivmds[nr_ivmd].header.device_id = PCI_BDF(bus, dev, func);
+            user_ivmds[nr_ivmd].header.type = ACPI_IVRS_TYPE_MEMORY_ONE;
+
+            if ( *s == '-' )
+            {
+                s = parse_pci(s + 1, &seg, &bus, &dev, &func);
+                if ( !s || seg )
+                    return -EINVAL;
+
+                user_ivmds[nr_ivmd].aux_data = PCI_BDF(bus, dev, func);
+                if ( user_ivmds[nr_ivmd].aux_data <
+                     user_ivmds[nr_ivmd].header.device_id )
+                    return -EINVAL;
+                user_ivmds[nr_ivmd].header.type = ACPI_IVRS_TYPE_MEMORY_RANGE;
+            }
+        } while ( ++nr_ivmd, *s == ',' );
+    } while ( *s++ == ';' );
+
+    return s[-1] ? -EINVAL : 0;
+}
+custom_param("ivmd", parse_ivmd_param);