intel-iommu: nested vIOMMU, cleanups, bug fixes

index fb31de9416..b359efd6f9 100644
@@ -722,6 +722,15 @@ static int vtd_iova_to_slpte(VTDContextEntry *ce, uint64_t iova, bool is_write,
 
 typedef int (*vtd_page_walk_hook)(IOMMUTLBEntry *entry, void *private);
 
+static int vtd_page_walk_one(IOMMUTLBEntry *entry, int level,
+                             vtd_page_walk_hook hook_fn, void *private)
+{
+    assert(hook_fn);
+    trace_vtd_page_walk_one(level, entry->iova, entry->translated_addr,
+                            entry->addr_mask, entry->perm);
+    return hook_fn(entry, private);
+}
+
 /**
  * vtd_page_walk_level - walk over specific level for IOVA range
  *

@@ -781,28 +790,37 @@ static int vtd_page_walk_level(dma_addr_t addr, uint64_t start,
          */
         entry_valid = read_cur | write_cur;
 
+        entry.target_as = &address_space_memory;
+        entry.iova = iova & subpage_mask;
+        entry.perm = IOMMU_ACCESS_FLAG(read_cur, write_cur);
+        entry.addr_mask = ~subpage_mask;
+
         if (vtd_is_last_slpte(slpte, level)) {
-            entry.target_as = &address_space_memory;
-            entry.iova = iova & subpage_mask;
             /* NOTE: this is only meaningful if entry_valid == true */
             entry.translated_addr = vtd_get_slpte_addr(slpte, aw);
-            entry.addr_mask = ~subpage_mask;
-            entry.perm = IOMMU_ACCESS_FLAG(read_cur, write_cur);
             if (!entry_valid && !notify_unmap) {
                 trace_vtd_page_walk_skip_perm(iova, iova_next);
                 goto next;
             }
-            trace_vtd_page_walk_one(level, entry.iova, entry.translated_addr,
-                                    entry.addr_mask, entry.perm);
-            if (hook_fn) {
-                ret = hook_fn(&entry, private);
-                if (ret < 0) {
-                    return ret;
-                }
+            ret = vtd_page_walk_one(&entry, level, hook_fn, private);
+            if (ret < 0) {
+                return ret;
             }
         } else {
             if (!entry_valid) {
-                trace_vtd_page_walk_skip_perm(iova, iova_next);
+                if (notify_unmap) {
+                    /*
+                     * The whole entry is invalid; unmap it all.
+                     * Translated address is meaningless, zero it.
+                     */
+                    entry.translated_addr = 0x0;
+                    ret = vtd_page_walk_one(&entry, level, hook_fn, private);
+                    if (ret < 0) {
+                        return ret;
+                    }
+                } else {
+                    trace_vtd_page_walk_skip_perm(iova, iova_next);
+                }
                 goto next;
             }
             ret = vtd_page_walk_level(vtd_get_slpte_addr(slpte, aw), iova,

index 45ec8919b6..032e33bcb2 100644
@@ -67,7 +67,6 @@ typedef union VTD_IR_TableEntry VTD_IR_TableEntry;
 typedef union VTD_IR_MSIAddress VTD_IR_MSIAddress;
 typedef struct VTDIrq VTDIrq;
 typedef struct VTD_MSIMessage VTD_MSIMessage;
-typedef struct IntelIOMMUNotifierNode IntelIOMMUNotifierNode;
 
 /* Context-Entry */
 struct VTDContextEntry {

@@ -93,6 +92,7 @@ struct VTDAddressSpace {
     MemoryRegion iommu_ir;      /* Interrupt region: 0xfeeXXXXX */
     IntelIOMMUState *iommu_state;
     VTDContextCacheEntry context_cache_entry;
+    QLIST_ENTRY(VTDAddressSpace) next;
 };
 
 struct VTDBus {

@@ -253,11 +253,6 @@ struct VTD_MSIMessage {
 /* When IR is enabled, all MSI/MSI-X data bits should be zero */
 #define VTD_IR_MSI_DATA          (0)
 
-struct IntelIOMMUNotifierNode {
-    VTDAddressSpace *vtd_as;
-    QLIST_ENTRY(IntelIOMMUNotifierNode) next;
-};
-
 /* The iommu (DMAR) device state struct */
 struct IntelIOMMUState {
     X86IOMMUState x86_iommu;

@@ -295,7 +290,7 @@ struct IntelIOMMUState {
     GHashTable *vtd_as_by_busptr;   /* VTDBus objects indexed by PCIBus* reference */
     VTDBus *vtd_as_by_bus_num[VTD_PCI_BUS_MAX]; /* VTDBus objects indexed by bus number */
     /* list of registered notifiers */
-    QLIST_HEAD(, IntelIOMMUNotifierNode) notifiers_list;
+    QLIST_HEAD(, VTDAddressSpace) vtd_as_with_notifiers;
 
     /* interrupt remapping */
     bool intr_enabled;              /* Whether guest enabled IR */

96 lines not on this page · raw message

index 032e33bcb2..016e74bedb 100644
@@ -300,6 +300,12 @@ struct IntelIOMMUState {
     OnOffAuto intr_eim;             /* Toggle for EIM cabability */
     bool buggy_eim;                 /* Force buggy EIM unless eim=off */
     uint8_t aw_bits;                /* Host/IOVA address width (in bits) */
+
+    /*
+     * Protects IOMMU states in general.  Currently it protects the
+     * per-IOMMU IOTLB cache, and context entry cache in VTDAddressSpace.
+     */
+    QemuMutex iommu_lock;
 };
 
 /* Find the VTD Address space associated with the given bus pointer,

171 lines not on this page · raw message

index 016e74bedb..156f35e919 100644
@@ -93,6 +93,8 @@ struct VTDAddressSpace {
     IntelIOMMUState *iommu_state;
     VTDContextCacheEntry context_cache_entry;
     QLIST_ENTRY(VTDAddressSpace) next;
+    /* Superset of notifier flags that this address space has */
+    IOMMUNotifierFlag notifier_flags;
 };
 
 struct VTDBus {

73 lines not on this page · raw message

index 38ccc741f9..e247269659 100644
@@ -748,9 +748,27 @@ static int vtd_iova_to_slpte(VTDContextEntry *ce, uint64_t iova, bool is_write,
 
 typedef int (*vtd_page_walk_hook)(IOMMUTLBEntry *entry, void *private);
 
+/**
+ * Constant information used during page walking
+ *
+ * @hook_fn: hook func to be called when detected page
+ * @private: private data to be passed into hook func
+ * @notify_unmap: whether we should notify invalid entries
+ * @aw: maximum address width
+ */
+typedef struct {
+    vtd_page_walk_hook hook_fn;
+    void *private;
+    bool notify_unmap;
+    uint8_t aw;
+} vtd_page_walk_info;
+
 static int vtd_page_walk_one(IOMMUTLBEntry *entry, int level,
-                             vtd_page_walk_hook hook_fn, void *private)
+                             vtd_page_walk_info *info)
 {
+    vtd_page_walk_hook hook_fn = info->hook_fn;
+    void *private = info->private;
+
     assert(hook_fn);
     trace_vtd_page_walk_one(level, entry->iova, entry->translated_addr,
                             entry->addr_mask, entry->perm);

@@ -763,17 +781,13 @@ static int vtd_page_walk_one(IOMMUTLBEntry *entry, int level,
  * @addr: base GPA addr to start the walk
  * @start: IOVA range start address
  * @end: IOVA range end address (start <= addr < end)
- * @hook_fn: hook func to be called when detected page
- * @private: private data to be passed into hook func
  * @read: whether parent level has read permission
  * @write: whether parent level has write permission
- * @notify_unmap: whether we should notify invalid entries
- * @aw: maximum address width
+ * @info: constant information for the page walk
  */
 static int vtd_page_walk_level(dma_addr_t addr, uint64_t start,
-                               uint64_t end, vtd_page_walk_hook hook_fn,
-                               void *private, uint32_t level, bool read,
-                               bool write, bool notify_unmap, uint8_t aw)
+                               uint64_t end, uint32_t level, bool read,
+                               bool write, vtd_page_walk_info *info)
 {
     bool read_cur, write_cur, entry_valid;
     uint32_t offset;

@@ -823,24 +837,24 @@ static int vtd_page_walk_level(dma_addr_t addr, uint64_t start,
 
         if (vtd_is_last_slpte(slpte, level)) {
             /* NOTE: this is only meaningful if entry_valid == true */
-            entry.translated_addr = vtd_get_slpte_addr(slpte, aw);
-            if (!entry_valid && !notify_unmap) {
+            entry.translated_addr = vtd_get_slpte_addr(slpte, info->aw);
+            if (!entry_valid && !info->notify_unmap) {
                 trace_vtd_page_walk_skip_perm(iova, iova_next);
                 goto next;
             }
-            ret = vtd_page_walk_one(&entry, level, hook_fn, private);
+            ret = vtd_page_walk_one(&entry, level, info);
             if (ret < 0) {
                 return ret;
             }
         } else {
             if (!entry_valid) {
-                if (notify_unmap) {
+                if (info->notify_unmap) {
                     /*
                      * The whole entry is invalid; unmap it all.
                      * Translated address is meaningless, zero it.
                      */
                     entry.translated_addr = 0x0;
-                    ret = vtd_page_walk_one(&entry, level, hook_fn, private);
+                    ret = vtd_page_walk_one(&entry, level, info);
                     if (ret < 0) {
                         return ret;
                     }

@@ -849,10 +863,9 @@ static int vtd_page_walk_level(dma_addr_t addr, uint64_t start,
                 }
                 goto next;
             }
-            ret = vtd_page_walk_level(vtd_get_slpte_addr(slpte, aw), iova,
-                                      MIN(iova_next, end), hook_fn, private,
-                                      level - 1, read_cur, write_cur,
-                                      notify_unmap, aw);
+            ret = vtd_page_walk_level(vtd_get_slpte_addr(slpte, info->aw),
+                                      iova, MIN(iova_next, end), level - 1,
+                                      read_cur, write_cur, info);
             if (ret < 0) {
                 return ret;
             }

@@ -871,28 +884,24 @@ next:
  * @ce: context entry to walk upon
  * @start: IOVA address to start the walk
  * @end: IOVA range end address (start <= addr < end)
- * @hook_fn: the hook that to be called for each detected area
- * @private: private data for the hook function
- * @aw: maximum address width
+ * @info: page walking information struct
  */
 static int vtd_page_walk(VTDContextEntry *ce, uint64_t start, uint64_t end,
-                         vtd_page_walk_hook hook_fn, void *private,
-                         bool notify_unmap, uint8_t aw)
+                         vtd_page_walk_info *info)
 {
     dma_addr_t addr = vtd_ce_get_slpt_base(ce);
     uint32_t level = vtd_ce_get_level(ce);
 
-    if (!vtd_iova_range_check(start, ce, aw)) {
+    if (!vtd_iova_range_check(start, ce, info->aw)) {
         return -VTD_FR_ADDR_BEYOND_MGAW;
     }
 
-    if (!vtd_iova_range_check(end, ce, aw)) {
+    if (!vtd_iova_range_check(end, ce, info->aw)) {
         /* Fix end so that it reaches the maximum */
-        end = vtd_iova_limit(ce, aw);
+        end = vtd_iova_limit(ce, info->aw);
     }
 
-    return vtd_page_walk_level(addr, start, end, hook_fn, private,
-                               level, true, true, notify_unmap, aw);
+    return vtd_page_walk_level(addr, start, end, level, true, true, info);
 }
 
 /* Map a device to its corresponding domain (context-entry) */

@@ -1449,14 +1458,19 @@ static void vtd_iotlb_page_invalidate_notify(IntelIOMMUState *s,
                                        vtd_as->devfn, &ce);
         if (!ret && domain_id == VTD_CONTEXT_ENTRY_DID(ce.hi)) {
             if (vtd_as_has_map_notifier(vtd_as)) {
+                vtd_page_walk_info info = {
+                    .hook_fn = vtd_page_invalidate_notify_hook,
+                    .private = (void *)&vtd_as->iommu,
+                    .notify_unmap = true,
+                    .aw = s->aw_bits,
+                };
+
                 /*
                  * As long as we have MAP notifications registered in
                  * any of our IOMMU notifiers, we need to sync the
                  * shadow page table.
                  */
-                vtd_page_walk(&ce, addr, addr + size,
-                              vtd_page_invalidate_notify_hook,
-                              (void *)&vtd_as->iommu, true, s->aw_bits);
+                vtd_page_walk(&ce, addr, addr + size, &info);
             } else {
                 /*
                  * For UNMAP-only notifiers, we don't need to walk the

@@ -2924,8 +2938,14 @@ static void vtd_iommu_replay(IOMMUMemoryRegion *iommu_mr, IOMMUNotifier *n)
                                   ce.hi, ce.lo);
         if (vtd_as_has_map_notifier(vtd_as)) {
             /* This is required only for MAP typed notifiers */
-            vtd_page_walk(&ce, 0, ~0ULL, vtd_replay_hook, (void *)n, false,
-                          s->aw_bits);
+            vtd_page_walk_info info = {
+                .hook_fn = vtd_replay_hook,
+                .private = (void *)n,
+                .notify_unmap = false,
+                .aw = s->aw_bits,
+            };
+
+            vtd_page_walk(&ce, 0, ~0ULL, &info);
         }
     } else {
         trace_vtd_replay_ce_invalid(bus_n, PCI_SLOT(vtd_as->devfn),

index e247269659..a882894f49 100644
@@ -754,9 +754,11 @@ typedef int (*vtd_page_walk_hook)(IOMMUTLBEntry *entry, void *private);
  * @hook_fn: hook func to be called when detected page
  * @private: private data to be passed into hook func
  * @notify_unmap: whether we should notify invalid entries
+ * @as: VT-d address space of the device
  * @aw: maximum address width
  */
 typedef struct {
+    VTDAddressSpace *as;
     vtd_page_walk_hook hook_fn;
     void *private;
     bool notify_unmap;

@@ -1463,6 +1465,7 @@ static void vtd_iotlb_page_invalidate_notify(IntelIOMMUState *s,
                     .private = (void *)&vtd_as->iommu,
                     .notify_unmap = true,
                     .aw = s->aw_bits,
+                    .as = vtd_as,
                 };
 
                 /*

@@ -2943,6 +2946,7 @@ static void vtd_iommu_replay(IOMMUMemoryRegion *iommu_mr, IOMMUNotifier *n)
                 .private = (void *)n,
                 .notify_unmap = false,
                 .aw = s->aw_bits,
+                .as = vtd_as,
             };
 
             vtd_page_walk(&ce, 0, ~0ULL, &info);

index a882894f49..61bb3d31e7 100644
@@ -756,6 +756,7 @@ typedef int (*vtd_page_walk_hook)(IOMMUTLBEntry *entry, void *private);
  * @notify_unmap: whether we should notify invalid entries
  * @as: VT-d address space of the device
  * @aw: maximum address width
+ * @domain: domain ID of the page walk
  */
 typedef struct {
     VTDAddressSpace *as;

@@ -763,17 +764,18 @@ typedef struct {
     void *private;
     bool notify_unmap;
     uint8_t aw;
+    uint16_t domain_id;
 } vtd_page_walk_info;
 
-static int vtd_page_walk_one(IOMMUTLBEntry *entry, int level,
-                             vtd_page_walk_info *info)
+static int vtd_page_walk_one(IOMMUTLBEntry *entry, vtd_page_walk_info *info)
 {
     vtd_page_walk_hook hook_fn = info->hook_fn;
     void *private = info->private;
 
     assert(hook_fn);
-    trace_vtd_page_walk_one(level, entry->iova, entry->translated_addr,
-                            entry->addr_mask, entry->perm);
+    trace_vtd_page_walk_one(info->domain_id, entry->iova,
+                            entry->translated_addr, entry->addr_mask,
+                            entry->perm);
     return hook_fn(entry, private);
 }
 

@@ -844,7 +846,7 @@ static int vtd_page_walk_level(dma_addr_t addr, uint64_t start,
                 trace_vtd_page_walk_skip_perm(iova, iova_next);
                 goto next;
             }
-            ret = vtd_page_walk_one(&entry, level, info);
+            ret = vtd_page_walk_one(&entry, info);
             if (ret < 0) {
                 return ret;
             }

@@ -856,7 +858,7 @@ static int vtd_page_walk_level(dma_addr_t addr, uint64_t start,
                      * Translated address is meaningless, zero it.
                      */
                     entry.translated_addr = 0x0;
-                    ret = vtd_page_walk_one(&entry, level, info);
+                    ret = vtd_page_walk_one(&entry, info);
                     if (ret < 0) {
                         return ret;
                     }

@@ -1466,6 +1468,7 @@ static void vtd_iotlb_page_invalidate_notify(IntelIOMMUState *s,
                     .notify_unmap = true,
                     .aw = s->aw_bits,
                     .as = vtd_as,
+                    .domain_id = domain_id,
                 };
 
                 /*

@@ -2947,6 +2950,7 @@ static void vtd_iommu_replay(IOMMUMemoryRegion *iommu_mr, IOMMUNotifier *n)
                 .notify_unmap = false,
                 .aw = s->aw_bits,
                 .as = vtd_as,
+                .domain_id = VTD_CONTEXT_ENTRY_DID(ce.hi),
             };
 
             vtd_page_walk(&ce, 0, ~0ULL, &info);

new file mode 100644
index 0000000000..b061932097
@@ -0,0 +1,134 @@
+/*
+ * An very simplified iova tree implementation based on GTree.
+ *
+ * Copyright 2018 Red Hat, Inc.
+ *
+ * Authors:
+ *  Peter Xu <[email protected]>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ */
+#ifndef IOVA_TREE_H
+#define IOVA_TREE_H
+
+/*
+ * Currently the iova tree will only allow to keep ranges
+ * information, and no extra user data is allowed for each element.  A
+ * benefit is that we can merge adjacent ranges internally within the
+ * tree.  It can save a lot of memory when the ranges are splitted but
+ * mostly continuous.
+ *
+ * Note that current implementation does not provide any thread
+ * protections.  Callers of the iova tree should be responsible
+ * for the thread safety issue.
+ */
+
+#include "qemu/osdep.h"
+#include "exec/memory.h"
+#include "exec/hwaddr.h"
+
+#define  IOVA_OK           (0)
+#define  IOVA_ERR_INVALID  (-1) /* Invalid parameters */
+#define  IOVA_ERR_OVERLAP  (-2) /* IOVA range overlapped */
+
+typedef struct IOVATree IOVATree;
+typedef struct DMAMap {
+    hwaddr iova;
+    hwaddr translated_addr;
+    hwaddr size;                /* Inclusive */
+    IOMMUAccessFlags perm;
+} QEMU_PACKED DMAMap;
+typedef gboolean (*iova_tree_iterator)(DMAMap *map);
+
+/**
+ * iova_tree_new:
+ *
+ * Create a new iova tree.
+ *
+ * Returns: the tree pointer when succeeded, or NULL if error.
+ */
+IOVATree *iova_tree_new(void);
+
+/**
+ * iova_tree_insert:
+ *
+ * @tree: the iova tree to insert
+ * @map: the mapping to insert
+ *
+ * Insert an iova range to the tree.  If there is overlapped
+ * ranges, IOVA_ERR_OVERLAP will be returned.
+ *
+ * Return: 0 if succeeded, or <0 if error.
+ */
+int iova_tree_insert(IOVATree *tree, DMAMap *map);
+
+/**
+ * iova_tree_remove:
+ *
+ * @tree: the iova tree to remove range from
+ * @map: the map range to remove
+ *
+ * Remove mappings from the tree that are covered by the map range
+ * provided.  The range does not need to be exactly what has inserted,
+ * all the mappings that are included in the provided range will be
+ * removed from the tree.  Here map->translated_addr is meaningless.
+ *
+ * Return: 0 if succeeded, or <0 if error.
+ */
+int iova_tree_remove(IOVATree *tree, DMAMap *map);
+
+/**
+ * iova_tree_find:
+ *
+ * @tree: the iova tree to search from
+ * @map: the mapping to search
+ *
+ * Search for a mapping in the iova tree that overlaps with the
+ * mapping range specified.  Only the first found mapping will be
+ * returned.
+ *
+ * Return: DMAMap pointer if found, or NULL if not found.  Note that
+ * the returned DMAMap pointer is maintained internally.  User should
+ * only read the content but never modify or free the content.  Also,
+ * user is responsible to make sure the pointer is valid (say, no
+ * concurrent deletion in progress).
+ */
+DMAMap *iova_tree_find(IOVATree *tree, DMAMap *map);
+
+/**
+ * iova_tree_find_address:
+ *
+ * @tree: the iova tree to search from
+ * @iova: the iova address to find
+ *
+ * Similar to iova_tree_find(), but it tries to find mapping with
+ * range iova=iova & size=0.
+ *
+ * Return: same as iova_tree_find().
+ */
+DMAMap *iova_tree_find_address(IOVATree *tree, hwaddr iova);
+
+/**
+ * iova_tree_foreach:
+ *
+ * @tree: the iova tree to iterate on
+ * @iterator: the interator for the mappings, return true to stop
+ *
+ * Iterate over the iova tree.
+ *
+ * Return: 1 if found any overlap, 0 if not, <0 if error.
+ */
+void iova_tree_foreach(IOVATree *tree, iova_tree_iterator iterator);
+
+/**
+ * iova_tree_destroy:
+ *
+ * @tree: the iova tree to destroy
+ *
+ * Destroy an existing iova tree.
+ *
+ * Return: None.
+ */
+void iova_tree_destroy(IOVATree *tree);
+
+#endif

114 lines not on this page · raw message

index 156f35e919..fbfedcb1c0 100644
@@ -27,6 +27,7 @@
 #include "hw/i386/ioapic.h"
 #include "hw/pci/msi.h"
 #include "hw/sysbus.h"
+#include "qemu/iova-tree.h"
 
 #define TYPE_INTEL_IOMMU_DEVICE "intel-iommu"
 #define INTEL_IOMMU_DEVICE(obj) \

@@ -95,6 +96,7 @@ struct VTDAddressSpace {
     QLIST_ENTRY(VTDAddressSpace) next;
     /* Superset of notifier flags that this address space has */
     IOMMUNotifierFlag notifier_flags;
+    IOVATree *iova_tree;          /* Traces mapped IOVA ranges */
 };
 
 struct VTDBus {

294 lines not on this page · raw message