[PATCH v4 06/11] vpci/header: handle p2m range sets per BAR

[Oleksandr Andrushchenko <andr2000@gmail.com>]

From: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>

Instead of handling a single range set, that contains all the memory
regions of all the BARs and ROM, have them per BAR.

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

Signed-off-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>

---
Since v3:
- re-work vpci_cancel_pending accordingly to the per-BAR handling
- s/num_mem_ranges/map_pending and s/uint8_t/bool
- ASSERT(bar->mem) in modify_bars
- create and destroy the rangesets on add/remove
---
 xen/drivers/vpci/header.c | 178 ++++++++++++++++++++++++++------------
 xen/drivers/vpci/vpci.c   |  26 +++++-
 xen/include/xen/vpci.h    |   3 +-
 3 files changed, 150 insertions(+), 57 deletions(-)

diff --git a/xen/drivers/vpci/header.c b/xen/drivers/vpci/header.c
index 1239051ee8ff..5fc2dfbbc864 100644
--- a/xen/drivers/vpci/header.c
+++ b/xen/drivers/vpci/header.c
@@ -131,34 +131,50 @@ static void modify_decoding(const struct pci_dev *pdev, uint16_t cmd,
 
 bool vpci_process_pending(struct vcpu *v)
 {
-    if ( v->vpci.mem )
+    if ( v->vpci.map_pending )
     {
         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);
+        struct pci_dev *pdev = v->vpci.pdev;
+        struct vpci_header *header = &pdev->vpci->header;
+        unsigned int i;
 
-        if ( rc == -ERESTART )
-            return true;
+        for ( i = 0; i < ARRAY_SIZE(header->bars); i++ )
+        {
+            struct vpci_bar *bar = &header->bars[i];
+            int rc;
 
-        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);
+            if ( rangeset_is_empty(bar->mem) )
+                continue;
 
-        vpci_cancel_pending(v->vpci.pdev);
-        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_remove_device(v->vpci.pdev);
+            rc = rangeset_consume_ranges(bar->mem, map_range, &data);
+
+            if ( rc == -ERESTART )
+                return true;
+
+            spin_lock(&pdev->vpci->lock);
+            /* Disable memory decoding unconditionally on failure. */
+            modify_decoding(pdev,
+                            rc ? v->vpci.cmd & ~PCI_COMMAND_MEMORY : v->vpci.cmd,
+                            !rc && v->vpci.rom_only);
+            spin_unlock(&pdev->vpci->lock);
+
+            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_remove_device(pdev);
+                break;
+            }
+        }
+        v->vpci.map_pending = false;
     }
 
     return false;
@@ -169,22 +185,48 @@ void vpci_cancel_pending(const struct pci_dev *pdev)
     struct vcpu *v = current;
 
     /* Cancel any pending work now. */
-    if ( v->vpci.mem && v->vpci.pdev == pdev)
+    if ( v->vpci.map_pending && v->vpci.pdev == pdev)
     {
-        rangeset_destroy(v->vpci.mem);
-        v->vpci.mem = NULL;
+        struct vpci_header *header = &pdev->vpci->header;
+        unsigned int i;
+        int rc;
+
+        for ( i = 0; i < ARRAY_SIZE(header->bars); i++ )
+        {
+            struct vpci_bar *bar = &header->bars[i];
+
+            if ( rangeset_is_empty(bar->mem) )
+                continue;
+
+            rc = rangeset_remove_range(bar->mem, 0, ~0ULL);
+            if ( !rc )
+                printk(XENLOG_ERR
+                       "%pd %pp failed to remove range set for BAR: %d\n",
+                       v->domain, &pdev->sbdf, rc);
+        }
+        v->vpci.map_pending = 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;
+
+    for ( i = 0; i < ARRAY_SIZE(header->bars); i++ )
+    {
+        struct vpci_bar *bar = &header->bars[i];
+
+        if ( rangeset_is_empty(bar->mem) )
+            continue;
 
-    while ( (rc = rangeset_consume_ranges(mem, map_range, &data)) == -ERESTART )
-        process_pending_softirqs();
-    rangeset_destroy(mem);
+        while ( (rc = rangeset_consume_ranges(bar->mem, map_range,
+                                              &data)) == -ERESTART )
+            process_pending_softirqs();
+    }
     if ( !rc )
         modify_decoding(pdev, cmd, false);
 
@@ -192,7 +234,7 @@ 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;
 
@@ -203,9 +245,9 @@ 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;
+    curr->vpci.map_pending = true;
     /*
      * Raise a scheduler softirq in order to prevent the guest from resuming
      * execution with pending mapping operations, to trigger the invocation
@@ -217,42 +259,40 @@ 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 vpci_msix *msix = pdev->vpci->msix;
-    unsigned int i;
+    unsigned int i, j;
     int rc;
-
-    if ( !mem )
-        return -ENOMEM;
+    bool map_pending;
 
     /*
-     * Create a rangeset that represents the current device BARs memory region
+     * 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 all the BARs 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);
 
+        ASSERT(bar->mem);
+
         if ( !MAPPABLE_BAR(bar) ||
              (rom_only ? bar->type != VPCI_BAR_ROM
                        : (bar->type == VPCI_BAR_ROM && !header->rom_enabled)) )
             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;
+            goto fail;
         }
     }
 
@@ -263,14 +303,21 @@ 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 )
+            {
+                printk(XENLOG_G_WARNING
+                       "Failed to remove MSIX table [%lx, %lx]: %d\n",
+                       start, end, rc);
+                goto fail;
+            }
         }
     }
 
@@ -302,7 +349,8 @@ static int modify_bars(const struct pci_dev *pdev, uint16_t cmd, bool rom_only)
             unsigned long start = PFN_DOWN(bar->addr);
             unsigned long end = PFN_DOWN(bar->addr + bar->size - 1);
 
-            if ( !bar->enabled || !rangeset_overlaps_range(mem, start, end) ||
+            if ( !bar->enabled ||
+                 !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
@@ -311,13 +359,12 @@ static int modify_bars(const struct pci_dev *pdev, uint16_t cmd, bool rom_only)
                  (rom_only && tmp == pdev && bar->type == VPCI_BAR_ROM) )
                 continue;
 
-            rc = rangeset_remove_range(mem, start, end);
+            rc = rangeset_remove_range(bar->mem, start, end);
             if ( rc )
             {
                 printk(XENLOG_G_WARNING "Failed to remove [%lx, %lx]: %d\n",
                        start, end, rc);
-                rangeset_destroy(mem);
-                return rc;
+                goto fail;
             }
         }
     }
@@ -335,12 +382,35 @@ 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);
+    /* Find out how many memory ranges has left after MSI and overlaps. */
+    map_pending = false;
+    for ( i = 0; i < ARRAY_SIZE(header->bars); i++ )
+        if ( !rangeset_is_empty(header->bars[i].mem) )
+        {
+            map_pending = true;
+            break;
+        }
+
+    /*
+     * There are cases when PCI device, root port for example, has neither
+     * memory space nor IO. In this case PCI command register write is
+     * missed resulting in the underlying PCI device not functional, so:
+     *   - if there are no regions write the command register now
+     *   - if there are regions then defer work and write later on
+     */
+    if ( !map_pending )
+        pci_conf_write16(pdev->sbdf, PCI_COMMAND, cmd);
+    else
+        defer_map(dev->domain, dev, cmd, rom_only);
 
     return 0;
+
+fail:
+    vpci_cancel_pending(pdev);
+    return rc;
 }
 
 static void cmd_write(const struct pci_dev *pdev, unsigned int reg,
diff --git a/xen/drivers/vpci/vpci.c b/xen/drivers/vpci/vpci.c
index 5f086398a98c..45733300f00b 100644
--- a/xen/drivers/vpci/vpci.c
+++ b/xen/drivers/vpci/vpci.c
@@ -55,7 +55,12 @@ void vpci_remove_device_handlers(const struct pci_dev *pdev)
 
 void vpci_remove_device(struct pci_dev *pdev)
 {
+    struct vpci_header *header = &pdev->vpci->header;
+    unsigned int i;
+
     vpci_cancel_pending(pdev);
+    for ( i = 0; i < ARRAY_SIZE(header->bars); i++ )
+        rangeset_destroy(header->bars[i].mem);
     vpci_remove_device_handlers(pdev);
     xfree(pdev->vpci->msix);
     xfree(pdev->vpci->msi);
@@ -80,6 +85,8 @@ static int run_vpci_init(struct pci_dev *pdev)
 
 int vpci_add_handlers(struct pci_dev *pdev)
 {
+    struct vpci_header *header;
+    unsigned int i;
     int rc;
 
     if ( !has_vpci(pdev->domain) )
@@ -95,10 +102,25 @@ int vpci_add_handlers(struct pci_dev *pdev)
     INIT_LIST_HEAD(&pdev->vpci->handlers);
     spin_lock_init(&pdev->vpci->lock);
 
+    header = &pdev->vpci->header;
+    for ( i = 0; i < ARRAY_SIZE(header->bars); i++ )
+    {
+        struct vpci_bar *bar = &header->bars[i];
+
+        bar->mem = rangeset_new(NULL, NULL, 0);
+        if ( !bar->mem )
+        {
+            rc = -ENOMEM;
+            goto fail;
+        }
+    }
+
     rc = run_vpci_init(pdev);
-    if ( rc )
-        vpci_remove_device(pdev);
+    if ( !rc )
+        return 0;
 
+ fail:
+    vpci_remove_device(pdev);
     return rc;
 }
 
diff --git a/xen/include/xen/vpci.h b/xen/include/xen/vpci.h
index 3e7428da822c..143f3166a730 100644
--- a/xen/include/xen/vpci.h
+++ b/xen/include/xen/vpci.h
@@ -75,6 +75,7 @@ struct vpci {
             /* Guest view of the BAR. */
             uint64_t guest_addr;
             uint64_t size;
+            struct rangeset *mem;
             enum {
                 VPCI_BAR_EMPTY,
                 VPCI_BAR_IO,
@@ -149,9 +150,9 @@ 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 map_pending : 1;
     bool rom_only : 1;
 };
 
-- 
2.25.1