[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Xen-changelog] [xen master] VT-d: add command line option for extra rmrrs



commit 431685e8deb660976d8e986c41a647944e410c6c
Author:     Elena Ufimtseva <elena.ufimtseva@xxxxxxxxxx>
AuthorDate: Wed Jan 25 10:38:05 2017 +0100
Commit:     Jan Beulich <jbeulich@xxxxxxxx>
CommitDate: Wed Jan 25 10:38:05 2017 +0100

    VT-d: add command line option for extra rmrrs
    
    On some platforms firmware fails to specify RMRR regions in ACPI tables and
    thus those regions will not be mapped in dom0 or guests and may cause IO
    Page Faults and prevent dom0 from booting if "iommu=dom0-strict" option is
    specified on the Xen command line.
    
    New Xen command line option rmrr allows to specify such devices and
    memory regions. These regions are added to the list of RMRR defined in ACPI
    if the device is present in system. As a result, additional RMRRs will be
    mapped 1:1 in dom0 with correct permissions.
    
    The above mentioned problems were discovered during the PVH work with
    ThinkCentre M and Dell 5600T. No official documentation was found so far
    in regards to what devices and why cause this. Experiments show that
    ThinkCentre M USB devices with enabled debug port generate DMA read
    transactions to the regions of memory marked reserved in host e820 map.
    
    For Dell 5600T the device and faulting addresses are not found yet.
    For detailed history of the discussion please check following threads:
        http://lists.Xen.org/archives/html/xen-devel/2015-02/msg01724.html
        http://lists.Xen.org/archives/html/xen-devel/2015-01/msg02513.html
    
    Format for rmrr Xen command line option:
        
rmrr=start<-end>=[s1]bdf1[,[s1]bdf2[,...]];start<-end>=[s2]bdf1[,[s2]bdf2[,...]]
        For example, for Lenovo ThinkCentre M, use:
            rmrr=0xd5d45=0:0:1d.0;0xd5d46=0:0:1a.0
        If grub2 used and multiple ranges are specified, ';' should be
        quoted/escaped, refer to grub2 manual for more information.
    
    Signed-off-by: Elena Ufimtseva <elena.ufimtseva@xxxxxxxxxx>
    Signed-off-by: Venu Busireddy <venu.busireddy@xxxxxxxxxx>
    Acked-by: Kevin Tian <kevin.tian@xxxxxxxxx>
    Reviewed-by: Jan Beulich <jbeulich@xxxxxxxx>
---
 docs/misc/xen-command-line.markdown |  13 +++
 xen/drivers/passthrough/vtd/dmar.c  | 203 +++++++++++++++++++++++++++++++++++-
 2 files changed, 215 insertions(+), 1 deletion(-)

diff --git a/docs/misc/xen-command-line.markdown 
b/docs/misc/xen-command-line.markdown
index 0138978..a11fdf9 100644
--- a/docs/misc/xen-command-line.markdown
+++ b/docs/misc/xen-command-line.markdown
@@ -1377,6 +1377,19 @@ Specify the host reboot method.
 'efi' instructs Xen to reboot using the EFI reboot call (in EFI mode by
  default it will use that method first).
 
+### rmrr
+> '= 
start<-end>=[s1]bdf1[,[s1]bdf2[,...]];start<-end>=[s2]bdf1[,[s2]bdf2[,...]]
+
+Define RMRR units that are missing from ACPI table along with device they
+belong to and use them for 1:1 mapping. End addresses can be omitted and one
+page will be mapped. The ranges are inclusive when start and end are specified.
+If segment of the first device is not specified, segment zero will be used.
+If other segments are not specified, first device segment will be used.
+If a segment is specified for other than the first device and it does not match
+the one specified for the first one, an error will be reported.
+Note: grub2 requires to escape or use quotations if special characters are 
used,
+namely ';', refer to the grub2 documentation if multiple ranges are specified.
+
 ### ro-hpet
 > `= <boolean>`
 
diff --git a/xen/drivers/passthrough/vtd/dmar.c 
b/xen/drivers/passthrough/vtd/dmar.c
index 3c7c9b2..831fe1a 100644
--- a/xen/drivers/passthrough/vtd/dmar.c
+++ b/xen/drivers/passthrough/vtd/dmar.c
@@ -859,6 +859,134 @@ out:
     return ret;
 }
 
+#define MAX_USER_RMRR_PAGES 16
+#define MAX_USER_RMRR 10
+
+/* RMRR units derived from command line rmrr option. */
+#define MAX_USER_RMRR_DEV 20
+struct user_rmrr {
+    struct list_head list;
+    unsigned long base_pfn, end_pfn;
+    unsigned int dev_count;
+    u32 sbdf[MAX_USER_RMRR_DEV];
+};
+
+static __initdata unsigned int nr_rmrr;
+static struct __initdata user_rmrr user_rmrrs[MAX_USER_RMRR];
+
+/* Macro for RMRR inclusive range formatting. */
+#define ERMRRU_FMT "[%lx-%lx]"
+#define ERMRRU_ARG(eru) eru.base_pfn, eru.end_pfn
+
+static int __init add_user_rmrr(void)
+{
+    struct acpi_rmrr_unit *rmrr, *rmrru;
+    unsigned int idx, seg, i;
+    unsigned long base, end;
+    bool overlap;
+
+    for ( i = 0; i < nr_rmrr; i++ )
+    {
+        base = user_rmrrs[i].base_pfn;
+        end = user_rmrrs[i].end_pfn;
+
+        if ( base > end )
+        {
+            printk(XENLOG_ERR VTDPREFIX
+                   "Invalid RMRR Range "ERMRRU_FMT"\n",
+                   ERMRRU_ARG(user_rmrrs[i]));
+            continue;
+        }
+
+        if ( (end - base) >= MAX_USER_RMRR_PAGES )
+        {
+            printk(XENLOG_ERR VTDPREFIX
+                   "RMRR range "ERMRRU_FMT" exceeds "\
+                   __stringify(MAX_USER_RMRR_PAGES)" pages\n",
+                   ERMRRU_ARG(user_rmrrs[i]));
+            continue;
+        }
+
+        overlap = false;
+        list_for_each_entry(rmrru, &acpi_rmrr_units, list)
+        {
+            if ( pfn_to_paddr(base) <= rmrru->end_address &&
+                 rmrru->base_address <= pfn_to_paddr(end) )
+            {
+                printk(XENLOG_ERR VTDPREFIX
+                       "Overlapping RMRRs: "ERMRRU_FMT" and [%lx-%lx]\n",
+                       ERMRRU_ARG(user_rmrrs[i]),
+                       paddr_to_pfn(rmrru->base_address),
+                       paddr_to_pfn(rmrru->end_address));
+                overlap = true;
+                break;
+            }
+        }
+        /* Don't add overlapping RMRR. */
+        if ( overlap )
+            continue;
+
+        do
+        {
+            if ( !mfn_valid(base) )
+            {
+                printk(XENLOG_ERR VTDPREFIX
+                       "Invalid pfn in RMRR range "ERMRRU_FMT"\n",
+                       ERMRRU_ARG(user_rmrrs[i]));
+                break;
+            }
+        } while ( base++ < end );
+
+        /* Invalid pfn in range as the loop ended before end_pfn was reached. 
*/
+        if ( base <= end )
+            continue;
+
+        rmrr = xzalloc(struct acpi_rmrr_unit);
+        if ( !rmrr )
+            return -ENOMEM;
+
+        rmrr->scope.devices = xmalloc_array(u16, user_rmrrs[i].dev_count);
+        if ( !rmrr->scope.devices )
+        {
+            xfree(rmrr);
+            return -ENOMEM;
+        }
+
+        seg = 0;
+        for ( idx = 0; idx < user_rmrrs[i].dev_count; idx++ )
+        {
+            rmrr->scope.devices[idx] = user_rmrrs[i].sbdf[idx];
+            seg |= PCI_SEG(user_rmrrs[i].sbdf[idx]);
+        }
+        if ( seg != PCI_SEG(user_rmrrs[i].sbdf[0]) )
+        {
+            printk(XENLOG_ERR VTDPREFIX
+                   "Segments are not equal for RMRR range "ERMRRU_FMT"\n",
+                   ERMRRU_ARG(user_rmrrs[i]));
+            scope_devices_free(&rmrr->scope);
+            xfree(rmrr);
+            continue;
+        }
+
+        rmrr->segment = seg;
+        rmrr->base_address = pfn_to_paddr(user_rmrrs[i].base_pfn);
+        /* Align the end_address to the end of the page */
+        rmrr->end_address = pfn_to_paddr(user_rmrrs[i].end_pfn) | ~PAGE_MASK;
+        rmrr->scope.devices_cnt = user_rmrrs[i].dev_count;
+
+        if ( register_one_rmrr(rmrr) )
+        {
+            printk(XENLOG_ERR VTDPREFIX
+                   "Could not register RMMR range "ERMRRU_FMT"\n",
+                   ERMRRU_ARG(user_rmrrs[i]));
+            scope_devices_free(&rmrr->scope);
+            xfree(rmrr);
+        }
+    }
+
+    return 0;
+}
+
 #include <asm/tboot.h>
 /* ACPI tables may not be DMA protected by tboot, so use DMAR copy */
 /* SINIT saved in SinitMleData in TXT heap (which is DMA protected) */
@@ -868,6 +996,7 @@ int __init acpi_dmar_init(void)
 {
     acpi_physical_address dmar_addr;
     acpi_native_uint dmar_len;
+    int ret;
 
     if ( ACPI_SUCCESS(acpi_get_table_phys(ACPI_SIG_DMAR, 0,
                                           &dmar_addr, &dmar_len)) )
@@ -878,7 +1007,12 @@ int __init acpi_dmar_init(void)
         dmar_table = __va(dmar_addr);
     }
 
-    return parse_dmar_table(acpi_parse_dmar);
+    ret = parse_dmar_table(acpi_parse_dmar);
+
+    if ( !ret )
+        return add_user_rmrr();
+
+    return ret;
 }
 
 void acpi_dmar_reinstate(void)
@@ -937,3 +1071,70 @@ int intel_iommu_get_reserved_device_memory(iommu_grdm_t 
*func, void *ctxt)
 
     return 0;
 }
+
+/*
+ * Parse rmrr Xen command line options and add parsed devices and regions into
+ * acpi_rmrr_unit list to mapped as RMRRs parsed from ACPI.
+ * Format:
+ * 
rmrr=start<-end>=[s1]bdf1[,[s1]bdf2[,...]];start<-end>=[s2]bdf1[,[s2]bdf2[,...]]
+ * If the segment of the first device is not specified,
+ * segment zero will be used.
+ * If other segments are not specified, first device segment will be used.
+ * If a segment is specified for other than the first device, and it does not
+ * match the one specified for the first one, an error will be reported.
+ */
+static void __init parse_rmrr_param(const char *str)
+{
+    const char *s = str, *cur, *stmp;
+    unsigned int seg, bus, dev, func, dev_count;
+    unsigned long start, end;
+
+    do {
+        start = simple_strtoul(cur = s, &s, 0);
+        if ( cur == s )
+            break;
+
+        if ( *s == '-' )
+        {
+            end = simple_strtoul(cur = s + 1, &s, 0);
+            if ( cur == s )
+                break;
+        }
+        else
+            end = start;
+
+        user_rmrrs[nr_rmrr].base_pfn = start;
+        user_rmrrs[nr_rmrr].end_pfn = end;
+
+        if ( *s != '=' )
+            continue;
+
+        do {
+            bool def_seg = false;
+
+            stmp = parse_pci_seg(s + 1, &seg, &bus, &dev, &func, &def_seg);
+            if ( !stmp )
+                break;
+
+            /*
+             * Not specified.
+             * Segment will be replaced with one from first device.
+             */
+            if ( user_rmrrs[nr_rmrr].dev_count && def_seg )
+                seg = PCI_SEG(user_rmrrs[nr_rmrr].sbdf[0]);
+
+            /* Keep sbdf's even if they differ and later report an error. */
+            dev_count = user_rmrrs[nr_rmrr].dev_count;
+            user_rmrrs[nr_rmrr].sbdf[dev_count] = PCI_SBDF(seg, bus, dev, 
func);
+
+            user_rmrrs[nr_rmrr].dev_count++;
+            s = stmp;
+        } while ( *s == ',' &&
+                  user_rmrrs[nr_rmrr].dev_count < MAX_USER_RMRR_DEV );
+
+        if ( user_rmrrs[nr_rmrr].dev_count )
+            nr_rmrr++;
+
+    } while ( *s++ == ';' && nr_rmrr < MAX_USER_RMRR );
+}
+custom_param("rmrr", parse_rmrr_param);
--
generated by git-patchbot for /home/xen/git/xen.git#master

_______________________________________________
Xen-changelog mailing list
Xen-changelog@xxxxxxxxxxxxx
https://lists.xenproject.org/xen-changelog

 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.