gnttab: Improve scaleability

421 lines not on this page · raw message

index bb90627..fee34ee 100644
@@ -288,10 +288,10 @@ static inline void
 put_maptrack_handle(
     struct grant_table *t, int handle)
 {
-    spin_lock(&t->lock);
+    spin_lock(&t->maptrack_lock);
     maptrack_entry(t, handle).ref = t->maptrack_head;
     t->maptrack_head = handle;
-    spin_unlock(&t->lock);
+    spin_unlock(&t->maptrack_lock);
 }
 
 static inline int

@@ -303,7 +303,7 @@ get_maptrack_handle(
     struct grant_mapping *new_mt;
     unsigned int          new_mt_limit, nr_frames;
 
-    spin_lock(&lgt->lock);
+    spin_lock(&lgt->maptrack_lock);
 
     while ( unlikely((handle = __get_maptrack_handle(lgt)) == -1) )
     {

@@ -332,7 +332,7 @@ get_maptrack_handle(
                  nr_frames + 1);
     }
 
-    spin_unlock(&lgt->lock);
+    spin_unlock(&lgt->maptrack_lock);
 
     return handle;
 }

@@ -3005,6 +3005,7 @@ grant_table_create(
 
     /* Simple stuff. */
     spin_lock_init(&t->lock);
+    spin_lock_init(&t->maptrack_lock);
     t->nr_grant_frames = INITIAL_NR_GRANT_FRAMES;
 
     /* Active grant table. */

index 32f5786..0b35a5e 100644
@@ -82,6 +82,8 @@ struct grant_table {
     struct grant_mapping **maptrack;
     unsigned int          maptrack_head;
     unsigned int          maptrack_limit;
+    /* Lock protecting the maptrack page list, head, and limit */
+    spinlock_t            maptrack_lock;
     /* Lock protecting updates to active and shared grant tables. */
     spinlock_t            lock;
     /* The defined versions are 1 and 2.  Set to 0 if we don't know

index a91ea77..b305041 100644
@@ -1048,7 +1048,7 @@ int xenmem_add_to_physmap_one(
     switch ( space )
     {
     case XENMAPSPACE_grant_table:
-        spin_lock(&d->grant_table->lock);
+        write_lock(&d->grant_table->lock);
 
         if ( d->grant_table->gt_version == 0 )
             d->grant_table->gt_version = 1;

@@ -1078,7 +1078,7 @@ int xenmem_add_to_physmap_one(
 
         t = p2m_ram_rw;
 
-        spin_unlock(&d->grant_table->lock);
+        write_unlock(&d->grant_table->lock);
         break;
     case XENMAPSPACE_shared_info:
         if ( idx != 0 )

index 5fe08df..8ca38b0 100644
@@ -4593,7 +4593,7 @@ int xenmem_add_to_physmap_one(
                 mfn = virt_to_mfn(d->shared_info);
             break;
         case XENMAPSPACE_grant_table:
-            spin_lock(&d->grant_table->lock);
+            write_lock(&d->grant_table->lock);
 
             if ( d->grant_table->gt_version == 0 )
                 d->grant_table->gt_version = 1;

@@ -4615,7 +4615,7 @@ int xenmem_add_to_physmap_one(
                     mfn = virt_to_mfn(d->grant_table->shared_raw[idx]);
             }
 
-            spin_unlock(&d->grant_table->lock);
+            write_unlock(&d->grant_table->lock);
             break;
         case XENMAPSPACE_gmfn_range:
         case XENMAPSPACE_gmfn:

481 lines not on this page · raw message

index 0b35a5e..f22ebd0 100644
@@ -64,6 +64,11 @@ struct grant_mapping {
 
 /* Per-domain grant information. */
 struct grant_table {
+    /*
+     * Lock protecting updates to grant table state (version, active
+     * entry list, etc.)
+     */
+    rwlock_t              lock;
     /* Table size. Number of frames shared with guest */
     unsigned int          nr_grant_frames;
     /* Shared grant table (see include/public/grant_table.h). */

@@ -84,8 +89,6 @@ struct grant_table {
     unsigned int          maptrack_limit;
     /* Lock protecting the maptrack page list, head, and limit */
     spinlock_t            maptrack_lock;
-    /* Lock protecting updates to active and shared grant tables. */
-    spinlock_t            lock;
     /* The defined versions are 1 and 2.  Set to 0 if we don't know
        what version to use yet. */
     unsigned              gt_version;

@@ -103,7 +106,7 @@ gnttab_release_mappings(
     struct domain *d);
 
 /* Increase the size of a domain's grant table.
- * Caller must hold d's grant table lock.
+ * Caller must hold d's grant table write lock.
  */
 int
 gnttab_grow_table(struct domain *d, unsigned int req_nr_frames);

index 7d9f64d..cdfd0c4 100644
@@ -118,9 +118,9 @@ struct gnttab_unmap_common {
     ((t)->maptrack[(e)/MAPTRACK_PER_PAGE][(e)%MAPTRACK_PER_PAGE])
 
 static inline unsigned int
-nr_maptrack_frames(struct grant_table *t)
+nr_vcpu_maptrack_frames(struct vcpu *v)
 {
-    return t->maptrack_limit / MAPTRACK_PER_PAGE;
+    return v->maptrack_limit / MAPTRACK_PER_PAGE;
 }
 
 #define MAPTRACK_TAIL (~0u)

@@ -275,66 +275,101 @@ double_gt_unlock(struct grant_table *lgt, struct grant_table *rgt)
 
 static inline int
 __get_maptrack_handle(
-    struct grant_table *t)
+    struct grant_table *t,
+    struct vcpu *v)
 {
-    unsigned int h;
-    if ( unlikely((h = t->maptrack_head) == MAPTRACK_TAIL) )
+    unsigned int head, next;
+
+    /* No maptrack pages allocated for this VCPU yet? */
+    head = v->maptrack_head;
+    if ( unlikely(head == MAPTRACK_TAIL) )
+        return -1;
+
+    /*
+     * Always keep one entry in the free list to make it easier to add
+     * free entries to the tail.
+     */
+    next = read_atomic(&maptrack_entry(t, head).ref);
+    if ( unlikely(next == MAPTRACK_TAIL) )
         return -1;
-    t->maptrack_head = maptrack_entry(t, h).ref;
-    return h;
+
+    v->maptrack_head = next;
+
+    return head;
 }
 
 static inline void
 put_maptrack_handle(
     struct grant_table *t, int handle)
 {
-    spin_lock(&t->maptrack_lock);
-    maptrack_entry(t, handle).ref = t->maptrack_head;
-    t->maptrack_head = handle;
-    spin_unlock(&t->maptrack_lock);
+    struct domain *d = current->domain;
+    struct vcpu *v;
+    unsigned int prev_tail, cur_tail;
+
+    /* 1. Set entry to be a tail. */
+    maptrack_entry(t, handle).ref = MAPTRACK_TAIL;
+
+    /* 2. Add entry to the tail of the list on the original VCPU. */
+    v = d->vcpu[maptrack_entry(t,handle).vcpu];
+
+    cur_tail = read_atomic(&v->maptrack_tail);
+    do {
+        prev_tail = cur_tail;
+        cur_tail = cmpxchg(&v->maptrack_tail, prev_tail, handle);
+    } while ( cur_tail != prev_tail );
+
+    /* 3. Update the old tail entry to point to the new entry. */
+    write_atomic(&maptrack_entry(t, prev_tail).ref, handle);
 }
 
 static inline int
 get_maptrack_handle(
     struct grant_table *lgt)
 {
+    struct vcpu          *v = current;
     int                   i;
     grant_handle_t        handle;
     struct grant_mapping *new_mt;
-    unsigned int          new_mt_limit, nr_frames;
+    unsigned int          nr_frames;
 
-    spin_lock(&lgt->maptrack_lock);
+    handle = __get_maptrack_handle(lgt, v);
+    if ( likely(handle != -1) )
+        return handle;
 
-    while ( unlikely((handle = __get_maptrack_handle(lgt)) == -1) )
-    {
-        nr_frames = nr_maptrack_frames(lgt);
-        if ( nr_frames >= max_maptrack_frames )
-            break;
+    nr_frames = nr_vcpu_maptrack_frames(v);
+    if ( nr_frames >= max_maptrack_frames )
+        return -1;
 
-        new_mt = alloc_xenheap_page();
-        if ( !new_mt )
-            break;
+    new_mt = alloc_xenheap_page();
+    if ( !new_mt )
+        return -1;
+    clear_page(new_mt);
 
-        clear_page(new_mt);
+    spin_lock(&lgt->maptrack_lock);
 
-        new_mt_limit = lgt->maptrack_limit + MAPTRACK_PER_PAGE;
+    for ( i = 1; i < MAPTRACK_PER_PAGE; i++ )
+    {
+        new_mt[i - 1].ref = (lgt->maptrack_pages * MAPTRACK_PER_PAGE) + i;
+        new_mt[i - 1].vcpu = v->vcpu_id;
+    }
+    /* Set last entry vcpu and ref */
+    new_mt[i - 1].ref = v->maptrack_head;
+    new_mt[i - 1].vcpu = v->vcpu_id;
 
-        for ( i = 1; i < MAPTRACK_PER_PAGE; i++ )
-            new_mt[i - 1].ref = lgt->maptrack_limit + i;
-        new_mt[i - 1].ref = lgt->maptrack_head;
-        lgt->maptrack_head = lgt->maptrack_limit;
+    v->maptrack_head = lgt->maptrack_pages * MAPTRACK_PER_PAGE;
 
-        lgt->maptrack[nr_frames] = new_mt;
-        smp_wmb();
-        lgt->maptrack_limit      = new_mt_limit;
+    /* Set tail directly if this is the first page for this VCPU. */
+    if ( v->maptrack_tail == MAPTRACK_TAIL )
+        v->maptrack_tail = (lgt->maptrack_pages * MAPTRACK_PER_PAGE)
+            + MAPTRACK_PER_PAGE - 1;
 
-        gdprintk(XENLOG_INFO, "Increased maptrack size to %u frames\n",
-                 nr_frames + 1);
-    }
+    lgt->maptrack[lgt->maptrack_pages++] = new_mt;
 
     spin_unlock(&lgt->maptrack_lock);
 
-    return handle;
+    v->maptrack_limit += MAPTRACK_PER_PAGE;
+
+    return __get_maptrack_handle(lgt, v);
 }
 
 /* Number of grant table entries. Caller must hold d's grant table lock. */

@@ -573,7 +608,8 @@ static void mapcount(
      */
     ASSERT(rw_is_write_locked(&rd->grant_table->lock));
 
-    for ( handle = 0; handle < lgt->maptrack_limit; handle++ )
+    for ( handle = 0; handle < lgt->maptrack_pages * MAPTRACK_PER_PAGE; 
+          handle++ )
     {
         map = &maptrack_entry(lgt, handle);
         if ( !(map->flags & (GNTMAP_device_map|GNTMAP_host_map)) ||

@@ -931,7 +967,7 @@ __gnttab_unmap_common(
 
     op->frame = (unsigned long)(op->dev_bus_addr >> PAGE_SHIFT);
 
-    if ( unlikely(op->handle >= lgt->maptrack_limit) )
+    if ( unlikely(op->handle >= lgt->maptrack_pages * MAPTRACK_PER_PAGE) )
     {
         gdprintk(XENLOG_INFO, "Bad handle (%d).\n", op->handle);
         op->status = GNTST_bad_handle;

@@ -1406,6 +1442,7 @@ gnttab_setup_table(
     struct gnttab_setup_table op;
     struct domain *d;
     struct grant_table *gt;
+    struct vcpu *v;
     int            i;
     xen_pfn_t  gmfn;
 

@@ -1447,6 +1484,17 @@ gnttab_setup_table(
     gt = d->grant_table;
     write_lock(&gt->lock);
 
+    /* Tracking of mapped foreign frames table */
+    if ( (gt->maptrack = xzalloc_array(struct grant_mapping *,
+                                       max_maptrack_frames * d->max_vcpus)) == NULL )
+        goto out3;
+    for_each_vcpu( d, v )
+    {
+        v->maptrack_head = MAPTRACK_TAIL;
+        v->maptrack_tail = MAPTRACK_TAIL;
+    }
+    gt->maptrack_pages = 0;
+
     if ( gt->gt_version == 0 )
         gt->gt_version = 1;
 

@@ -3030,18 +3078,6 @@ grant_table_create(
             spin_lock_init(&t->active[i][j].lock);
     }
 
-    /* Tracking of mapped foreign frames table */
-    if ( (t->maptrack = xzalloc_array(struct grant_mapping *,
-                                      max_maptrack_frames)) == NULL )
-        goto no_mem_2;
-    if ( (t->maptrack[0] = alloc_xenheap_page()) == NULL )
-        goto no_mem_3;
-    clear_page(t->maptrack[0]);
-    t->maptrack_limit = MAPTRACK_PER_PAGE;
-    for ( i = 1; i < MAPTRACK_PER_PAGE; i++ )
-        t->maptrack[0][i - 1].ref = i;
-    t->maptrack[0][i - 1].ref = MAPTRACK_TAIL;
-
     /* Shared grant table. */
     if ( (t->shared_raw = xzalloc_array(void *, max_grant_frames)) == NULL )
         goto no_mem_3;

@@ -3072,8 +3108,6 @@ grant_table_create(
         free_xenheap_page(t->shared_raw[i]);
     xfree(t->shared_raw);
  no_mem_3:
-    free_xenheap_page(t->maptrack[0]);
-    xfree(t->maptrack);
  no_mem_2:
     for ( i = 0;
           i < num_act_frames_from_sha_frames(INITIAL_NR_GRANT_FRAMES); i++ )

@@ -3101,7 +3135,8 @@ gnttab_release_mappings(
 
     BUG_ON(!d->is_dying);
 
-    for ( handle = 0; handle < gt->maptrack_limit; handle++ )
+    for ( handle = 0; handle < gt->maptrack_pages * MAPTRACK_PER_PAGE;
+          handle++ )
     {
         map = &maptrack_entry(gt, handle);
         if ( !(map->flags & (GNTMAP_device_map|GNTMAP_host_map)) )

@@ -3206,7 +3241,7 @@ grant_table_destroy(
         free_xenheap_page(t->shared_raw[i]);
     xfree(t->shared_raw);
 
-    for ( i = 0; i < nr_maptrack_frames(t); i++ )
+    for ( i = 0; i < t->maptrack_pages; i++ )
         free_xenheap_page(t->maptrack[i]);
     xfree(t->maptrack);
 

index f22ebd0..c6e4ebf 100644
@@ -60,6 +60,8 @@ struct grant_mapping {
     u32      ref;           /* grant ref */
     u16      flags;         /* 0-4: GNTMAP_* ; 5-15: unused */
     domid_t  domid;         /* granting domain */
+    u32      vcpu;          /* vcpu which created the grant mapping */
+    u32      pad;           /* round size to a power of 2 */
 };
 
 /* Per-domain grant information. */

@@ -83,10 +85,10 @@ struct grant_table {
     grant_status_t       **status;
     /* Active grant table. */
     struct active_grant_entry **active;
-    /* Mapping tracking table. */
+    /* Mapping tracking table per vcpu. */
     struct grant_mapping **maptrack;
-    unsigned int          maptrack_head;
-    unsigned int          maptrack_limit;
+    /* Total pages used for mapping tracking table */
+    unsigned int          maptrack_pages;
     /* Lock protecting the maptrack page list, head, and limit */
     spinlock_t            maptrack_lock;
     /* The defined versions are 1 and 2.  Set to 0 if we don't know

index 80c6f62..7f8422e 100644
@@ -219,6 +219,11 @@ struct vcpu
     /* VCPU paused by system controller. */
     int              controller_pause_count;
 
+    /* Maptrack */
+    unsigned int     maptrack_head;
+    unsigned int     maptrack_tail;
+    unsigned int     maptrack_limit;
+
     /* IRQ-safe virq_lock protects against delivering VIRQ to stale evtchn. */
     evtchn_port_t    virq_to_evtchn[NR_VIRQS];
     spinlock_t       virq_lock;