vpci/header: handle p2m range sets per BAR

Instead of handling a single range set, that contains all the memory
regions of all the BARs and ROM, have them per BAR.
As the range sets are now created when a PCI device is added and destroyed
when it is removed so make them named and accounted.

Note that rangesets were chosen here despite there being only up to
3 separate ranges in each set (typically just 1). But rangeset per BAR
was chosen for the ease of implementation and existing code re-usability.

Also note that error handling of vpci_process_pending() is slightly
modified, and that vPCI handlers are no longer removed if the creation
of the mappings in vpci_process_pending() fails, as that's unlikely to
lead to a functional device in any case.

This is in preparation of making non-identity mappings in p2m for the MMIOs.

Signed-off-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Signed-off-by: Volodymyr Babchuk <volodymyr_babchuk@epam.com>
Reviewed-by: Roger Pau Monné <roger.pau@citrix.com>
Signed-off-by: Stewart Hildebrand <stewart.hildebrand@amd.com>

xen/drivers/vpci/header.c

@@ -162,63 +162,107 @@ static void modify_decoding(const struct pci_dev *pdev, uint16_t cmd,
 
 bool vpci_process_pending(struct vcpu *v)
 {
-    if ( v->vpci.mem )
+    struct pci_dev *pdev = v->vpci.pdev;
+    struct map_data data = {
+        .d = v->domain,
+        .map = v->vpci.cmd & PCI_COMMAND_MEMORY,
+    };
+    struct vpci_header *header = NULL;
+    unsigned int i;
+
+    if ( !pdev )
+        return false;
+
+    read_lock(&v->domain->pci_lock);
+
+    if ( !pdev->vpci || (v->domain != pdev->domain) )
     {
-        struct map_data data = {
-            .d = v->domain,
-            .map = v->vpci.cmd & PCI_COMMAND_MEMORY,
-        };
-        int rc = rangeset_consume_ranges(v->vpci.mem, map_range, &data);
+        v->vpci.pdev = NULL;
+        read_unlock(&v->domain->pci_lock);
+        return false;
+    }
+
+    header = &pdev->vpci->header;
+    for ( i = 0; i < ARRAY_SIZE(header->bars); i++ )
+    {
+        struct vpci_bar *bar = &header->bars[i];
+        int rc;
+
+        if ( rangeset_is_empty(bar->mem) )
+            continue;
+
+        rc = rangeset_consume_ranges(bar->mem, map_range, &data);
 
         if ( rc == -ERESTART )
+        {
+            read_unlock(&v->domain->pci_lock);
             return true;
+        }
 
-        write_lock(&v->domain->pci_lock);
-        spin_lock(&v->vpci.pdev->vpci->lock);
-        /* Disable memory decoding unconditionally on failure. */
-        modify_decoding(v->vpci.pdev,
-                        rc ? v->vpci.cmd & ~PCI_COMMAND_MEMORY : v->vpci.cmd,
-                        !rc && v->vpci.rom_only);
-        spin_unlock(&v->vpci.pdev->vpci->lock);
-
-        rangeset_destroy(v->vpci.mem);
-        v->vpci.mem = NULL;
         if ( rc )
-            /*
-             * FIXME: in case of failure remove the device from the domain.
-             * Note that there might still be leftover mappings. While this is
-             * safe for Dom0, for DomUs the domain will likely need to be
-             * killed in order to avoid leaking stale p2m mappings on
-             * failure.
-             */
-            vpci_deassign_device(v->vpci.pdev);
-        write_unlock(&v->domain->pci_lock);
+        {
+            spin_lock(&pdev->vpci->lock);
+            /* Disable memory decoding unconditionally on failure. */
+            modify_decoding(pdev, v->vpci.cmd & ~PCI_COMMAND_MEMORY,
+                            false);
+            spin_unlock(&pdev->vpci->lock);
+
+            /* Clean all the rangesets */
+            for ( i = 0; i < ARRAY_SIZE(header->bars); i++ )
+                if ( !rangeset_is_empty(header->bars[i].mem) )
+                     rangeset_purge(header->bars[i].mem);
+
+            v->vpci.pdev = NULL;
+
+            read_unlock(&v->domain->pci_lock);
+
+            if ( !is_hardware_domain(v->domain) )
+                domain_crash(v->domain);
+
+            return false;
+        }
     }
+    v->vpci.pdev = NULL;
+
+    spin_lock(&pdev->vpci->lock);
+    modify_decoding(pdev, v->vpci.cmd, v->vpci.rom_only);
+    spin_unlock(&pdev->vpci->lock);
+
+    read_unlock(&v->domain->pci_lock);
 
     return false;
 }
 
 static int __init apply_map(struct domain *d, const struct pci_dev *pdev,
-                            struct rangeset *mem, uint16_t cmd)
+                            uint16_t cmd)
 {
     struct map_data data = { .d = d, .map = true };
-    int rc;
+    struct vpci_header *header = &pdev->vpci->header;
+    int rc = 0;
+    unsigned int i;
 
     ASSERT(rw_is_write_locked(&d->pci_lock));
 
-    while ( (rc = rangeset_consume_ranges(mem, map_range, &data)) == -ERESTART )
+    for ( i = 0; i < ARRAY_SIZE(header->bars); i++ )
     {
-        /*
-         * It's safe to drop and reacquire the lock in this context
-         * without risking pdev disappearing because devices cannot be
-         * removed until the initial domain has been started.
-         */
-        write_unlock(&d->pci_lock);
-        process_pending_softirqs();
-        write_lock(&d->pci_lock);
-    }
+        struct vpci_bar *bar = &header->bars[i];
 
-    rangeset_destroy(mem);
+        if ( rangeset_is_empty(bar->mem) )
+            continue;
+
+        while ( (rc = rangeset_consume_ranges(bar->mem, map_range,
+                                              &data)) == -ERESTART )
+        {
+            /*
+             * It's safe to drop and reacquire the lock in this context
+             * without risking pdev disappearing because devices cannot be
+             * removed until the initial domain has been started.
+             */
+            write_unlock(&d->pci_lock);
+            process_pending_softirqs();
+            write_lock(&d->pci_lock);
+        }
+    }
     if ( !rc )
         modify_decoding(pdev, cmd, false);
 
@@ -226,7 +270,7 @@ static int __init apply_map(struct domain *d, const struct pci_dev *pdev,
 }
 
 static void defer_map(struct domain *d, struct pci_dev *pdev,
-                      struct rangeset *mem, uint16_t cmd, bool rom_only)
+                      uint16_t cmd, bool rom_only)
 {
     struct vcpu *curr = current;
 
@@ -237,7 +281,6 @@ static void defer_map(struct domain *d, struct pci_dev *pdev,
      * started for the same device if the domain is not well-behaved.
      */
     curr->vpci.pdev = pdev;
-    curr->vpci.mem = mem;
     curr->vpci.cmd = cmd;
     curr->vpci.rom_only = rom_only;
     /*
@@ -251,33 +294,33 @@ static void defer_map(struct domain *d, struct pci_dev *pdev,
 static int modify_bars(const struct pci_dev *pdev, uint16_t cmd, bool rom_only)
 {
     struct vpci_header *header = &pdev->vpci->header;
-    struct rangeset *mem = rangeset_new(NULL, NULL, 0);
     struct pci_dev *tmp, *dev = NULL;
     const struct domain *d;
     const struct vpci_msix *msix = pdev->vpci->msix;
-    unsigned int i;
+    unsigned int i, j;
     int rc;
 
     ASSERT(rw_is_write_locked(&pdev->domain->pci_lock));
 
-    if ( !mem )
-        return -ENOMEM;
-
     /*
-     * Create a rangeset that represents the current device BARs memory region
-     * and compare it against all the currently active BAR memory regions. If
-     * an overlap is found, subtract it from the region to be mapped/unmapped.
+     * Create a rangeset per BAR that represents the current device memory
+     * region and compare it against all the currently active BAR memory
+     * regions. If an overlap is found, subtract it from the region to be
+     * mapped/unmapped.
      *
-     * First fill the rangeset with all the BARs of this device or with the ROM
+     * First fill the rangesets with the BAR of this device or with the ROM
      * BAR only, depending on whether the guest is toggling the memory decode
      * bit of the command register, or the enable bit of the ROM BAR register.
      */
     for ( i = 0; i < ARRAY_SIZE(header->bars); i++ )
     {
-        const struct vpci_bar *bar = &header->bars[i];
+        struct vpci_bar *bar = &header->bars[i];
         unsigned long start = PFN_DOWN(bar->addr);
         unsigned long end = PFN_DOWN(bar->addr + bar->size - 1);
 
+        if ( !bar->mem )
+            continue;
+
         if ( !MAPPABLE_BAR(bar) ||
              (rom_only ? bar->type != VPCI_BAR_ROM
                        : (bar->type == VPCI_BAR_ROM && !header->rom_enabled)) ||
@@ -293,14 +336,31 @@ static int modify_bars(const struct pci_dev *pdev, uint16_t cmd, bool rom_only)
             continue;
         }
 
-        rc = rangeset_add_range(mem, start, end);
+        rc = rangeset_add_range(bar->mem, start, end);
         if ( rc )
         {
             printk(XENLOG_G_WARNING "Failed to add [%lx, %lx]: %d\n",
                    start, end, rc);
-            rangeset_destroy(mem);
             return rc;
         }
+
+        /* Check for overlap with the already setup BAR ranges. */
+        for ( j = 0; j < i; j++ )
+        {
+            struct vpci_bar *prev_bar = &header->bars[j];
+
+            if ( rangeset_is_empty(prev_bar->mem) )
+                continue;
+
+            rc = rangeset_remove_range(prev_bar->mem, start, end);
+            if ( rc )
+            {
+                gprintk(XENLOG_WARNING,
+                       "%pp: failed to remove overlapping range [%lx, %lx]: %d\n",
+                        &pdev->sbdf, start, end, rc);
+                return rc;
+            }
+        }
     }
 
     /* Remove any MSIX regions if present. */
@@ -310,14 +370,21 @@ static int modify_bars(const struct pci_dev *pdev, uint16_t cmd, bool rom_only)
         unsigned long end = PFN_DOWN(vmsix_table_addr(pdev->vpci, i) +
                                      vmsix_table_size(pdev->vpci, i) - 1);
 
-        rc = rangeset_remove_range(mem, start, end);
-        if ( rc )
+        for ( j = 0; j < ARRAY_SIZE(header->bars); j++ )
         {
-            printk(XENLOG_G_WARNING
-                   "Failed to remove MSIX table [%lx, %lx]: %d\n",
-                   start, end, rc);
-            rangeset_destroy(mem);
-            return rc;
+            const struct vpci_bar *bar = &header->bars[j];
+
+            if ( rangeset_is_empty(bar->mem) )
+                continue;
+
+            rc = rangeset_remove_range(bar->mem, start, end);
+            if ( rc )
+            {
+                gprintk(XENLOG_WARNING,
+                       "%pp: failed to remove MSIX table [%lx, %lx]: %d\n",
+                        &pdev->sbdf, start, end, rc);
+                return rc;
+            }
         }
     }
 
@@ -357,27 +424,37 @@ static int modify_bars(const struct pci_dev *pdev, uint16_t cmd, bool rom_only)
 
             for ( i = 0; i < ARRAY_SIZE(tmp->vpci->header.bars); i++ )
             {
-                const struct vpci_bar *bar = &tmp->vpci->header.bars[i];
-                unsigned long start = PFN_DOWN(bar->addr);
-                unsigned long end = PFN_DOWN(bar->addr + bar->size - 1);
+                const struct vpci_bar *remote_bar = &tmp->vpci->header.bars[i];
+                unsigned long start = PFN_DOWN(remote_bar->addr);
+                unsigned long end = PFN_DOWN(remote_bar->addr +
+                                             remote_bar->size - 1);
 
-                if ( !bar->enabled ||
-                     !rangeset_overlaps_range(mem, start, end) ||
-                     /*
-                      * If only the ROM enable bit is toggled check against
-                      * other BARs in the same device for overlaps, but not
-                      * against the same ROM BAR.
-                      */
-                     (rom_only && tmp == pdev && bar->type == VPCI_BAR_ROM) )
+                if ( !remote_bar->enabled )
                     continue;
 
-                rc = rangeset_remove_range(mem, start, end);
-                if ( rc )
+                for ( j = 0; j < ARRAY_SIZE(header->bars); j++)
                 {
-                    printk(XENLOG_G_WARNING "Failed to remove [%lx, %lx]: %d\n",
-                           start, end, rc);
-                    rangeset_destroy(mem);
-                    return rc;
+                    const struct vpci_bar *bar = &header->bars[j];
+
+                    if ( !rangeset_overlaps_range(bar->mem, start, end) ||
+                         /*
+                          * If only the ROM enable bit is toggled check against
+                          * other BARs in the same device for overlaps, but not
+                          * against the same ROM BAR.
+                          */
+                         (rom_only &&
+                          tmp == pdev &&
+                          bar->type == VPCI_BAR_ROM) )
+                        continue;
+
+                    rc = rangeset_remove_range(bar->mem, start, end);
+                    if ( rc )
+                    {
+                        gprintk(XENLOG_WARNING,
+                                "%pp: failed to remove [%lx, %lx]: %d\n",
+                                &pdev->sbdf, start, end, rc);
+                        return rc;
+                    }
                 }
             }
         }
@@ -401,10 +478,10 @@ static int modify_bars(const struct pci_dev *pdev, uint16_t cmd, bool rom_only)
          * will always be to establish mappings and process all the BARs.
          */
         ASSERT((cmd & PCI_COMMAND_MEMORY) && !rom_only);
-        return apply_map(pdev->domain, pdev, mem, cmd);
+        return apply_map(pdev->domain, pdev, cmd);
     }
 
-    defer_map(dev->domain, dev, mem, cmd, rom_only);
+    defer_map(dev->domain, dev, cmd, rom_only);
 
     return 0;
 }
@@ -593,6 +670,18 @@ static void cf_check rom_write(
         rom->addr = val & PCI_ROM_ADDRESS_MASK;
 }
 
+static int bar_add_rangeset(const struct pci_dev *pdev, struct vpci_bar *bar,
+                            unsigned int i)
+{
+    char str[32];
+
+    snprintf(str, sizeof(str), "%pp:BAR%u", &pdev->sbdf, i);
+
+    bar->mem = rangeset_new(pdev->domain, str, RANGESETF_no_print);
+
+    return !bar->mem ? -ENOMEM : 0;
+}
+
 static int cf_check init_header(struct pci_dev *pdev)
 {
     uint16_t cmd;
@@ -748,6 +837,10 @@ static int cf_check init_header(struct pci_dev *pdev)
         else
             bars[i].type = VPCI_BAR_MEM32;
 
+        rc = bar_add_rangeset(pdev, &bars[i], i);
+        if ( rc )
+            goto fail;
+
         rc = pci_size_mem_bar(pdev->sbdf, reg, &addr, &size,
                               (i == num_bars - 1) ? PCI_BAR_LAST : 0);
         if ( rc < 0 )
@@ -798,6 +891,12 @@ static int cf_check init_header(struct pci_dev *pdev)
                                4, rom);
         if ( rc )
             rom->type = VPCI_BAR_EMPTY;
+        else
+        {
+            rc = bar_add_rangeset(pdev, rom, num_bars);
+            if ( rc )
+                goto fail;
+        }
     }
     else if ( !is_hwdom )
     {

xen/drivers/vpci/vpci.c

@@ -42,6 +42,8 @@ extern vpci_register_init_t *const __end_vpci_array[];
 
 void vpci_deassign_device(struct pci_dev *pdev)
 {
+    unsigned int i;
+
     ASSERT(rw_is_write_locked(&pdev->domain->pci_lock));
 
     if ( !has_vpci(pdev->domain) || !pdev->vpci )
@@ -67,6 +69,10 @@ void vpci_deassign_device(struct pci_dev *pdev)
             if ( pdev->vpci->msix->table[i] )
                 iounmap(pdev->vpci->msix->table[i]);
     }
+
+    for ( i = 0; i < ARRAY_SIZE(pdev->vpci->header.bars); i++ )
+        rangeset_destroy(pdev->vpci->header.bars[i].mem);
+
     xfree(pdev->vpci->msix);
     xfree(pdev->vpci->msi);
     xfree(pdev->vpci);

xen/include/xen/vpci.h

@@ -92,6 +92,7 @@ struct vpci {
             /* Guest address. */
             uint64_t guest_addr;
             uint64_t size;
+            struct rangeset *mem;
             enum {
                 VPCI_BAR_EMPTY,
                 VPCI_BAR_IO,
@@ -176,7 +177,6 @@ struct vpci {
 
 struct vpci_vcpu {
     /* Per-vcpu structure to store state while {un}mapping of PCI BARs. */
-    struct rangeset *mem;
     struct pci_dev *pdev;
     uint16_t cmd;
     bool rom_only : 1;