[PATCH 1/3] intel_iommu: Handle PASID cache invalidation

[Zhenzhong Duan <zhenzhong.duan@intel.com>]

Adds an new entry VTDPASIDCacheEntry in VTDAddressSpace to cache the pasid
entry and track PASID usage and future PASID tagged DMA address translation
support in vIOMMU.

When guest triggers pasid cache invalidation, QEMU will capture it and
update or invalidate pasid cache.

vIOMMU emulator could figure out the reason by fetching latest guest pasid
entry in memory and compare it with cached PASID entry if it's valid.

Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
---
 hw/i386/intel_iommu_internal.h |  19 ++++-
 include/hw/i386/intel_iommu.h  |   6 ++
 hw/i386/intel_iommu.c          | 150 ++++++++++++++++++++++++++++++---
 hw/i386/trace-events           |   3 +
 4 files changed, 165 insertions(+), 13 deletions(-)

diff --git a/hw/i386/intel_iommu_internal.h b/hw/i386/intel_iommu_internal.h
index 0f6a1237e4..80193ff28b 100644
--- a/hw/i386/intel_iommu_internal.h
+++ b/hw/i386/intel_iommu_internal.h
@@ -316,6 +316,8 @@ typedef enum VTDFaultReason {
                                   * request while disabled */
     VTD_FR_IR_SID_ERR = 0x26,   /* Invalid Source-ID */
 
+    VTD_FR_RTADDR_INV_TTM = 0x31,  /* Invalid TTM in RTADDR */
+
     VTD_FR_SM_PRE_ABS = 0x47,   /* SCT.8 : PRE bit in a present SM CE is 0 */
 
     /* PASID directory entry access failure */
@@ -517,6 +519,15 @@ typedef union VTDPRDesc VTDPRDesc;
 #define VTD_INV_DESC_PIOTLB_RSVD_VAL0     0xfff000000000f1c0ULL
 #define VTD_INV_DESC_PIOTLB_RSVD_VAL1     0xf80ULL
 
+/* PASID-cache Invalidate Descriptor (pc_inv_dsc) fields */
+#define VTD_INV_DESC_PASIDC_G(x)        extract64((x)->val[0], 4, 2)
+#define VTD_INV_DESC_PASIDC_G_DSI       0
+#define VTD_INV_DESC_PASIDC_G_PASID_SI  1
+#define VTD_INV_DESC_PASIDC_G_GLOBAL    3
+#define VTD_INV_DESC_PASIDC_DID(x)      extract64((x)->val[0], 16, 16)
+#define VTD_INV_DESC_PASIDC_PASID(x)    extract64((x)->val[0], 32, 20)
+#define VTD_INV_DESC_PASIDC_RSVD_VAL0   0xfff000000000f1c0ULL
+
 /* Page Request Descriptor */
 /* For the low 64-bit of 128-bit */
 #define VTD_PRD_TYPE            (1ULL)
@@ -603,6 +614,12 @@ typedef struct VTDRootEntry VTDRootEntry;
 #define VTD_SM_CONTEXT_ENTRY_RSVD_VAL1      0xffffffffffe00000ULL
 #define VTD_SM_CONTEXT_ENTRY_PRE            0x10ULL
 
+typedef struct VTDPASIDCacheInfo {
+    uint8_t type;
+    uint16_t did;
+    uint32_t pasid;
+} VTDPASIDCacheInfo;
+
 /* PASID Table Related Definitions */
 #define VTD_PASID_DIR_BASE_ADDR_MASK  (~0xfffULL)
 #define VTD_PASID_TABLE_BASE_ADDR_MASK (~0xfffULL)
@@ -624,7 +641,7 @@ typedef struct VTDRootEntry VTDRootEntry;
 #define VTD_SM_PASID_ENTRY_PT          (4ULL << 6)
 
 #define VTD_SM_PASID_ENTRY_AW          7ULL /* Adjusted guest-address-width */
-#define VTD_SM_PASID_ENTRY_DID(val)    ((val) & VTD_DOMAIN_ID_MASK)
+#define VTD_SM_PASID_ENTRY_DID(x)      extract64((x)->val[1], 0, 16)
 
 #define VTD_SM_PASID_ENTRY_FLPM          3ULL
 #define VTD_SM_PASID_ENTRY_FLPTPTR       (~0xfffULL)
diff --git a/include/hw/i386/intel_iommu.h b/include/hw/i386/intel_iommu.h
index 47730ac3c7..6e68734b3c 100644
--- a/include/hw/i386/intel_iommu.h
+++ b/include/hw/i386/intel_iommu.h
@@ -95,6 +95,11 @@ struct VTDPASIDEntry {
     uint64_t val[8];
 };
 
+typedef struct VTDPASIDCacheEntry {
+    struct VTDPASIDEntry pasid_entry;
+    bool valid;
+} VTDPASIDCacheEntry;
+
 struct VTDAddressSpace {
     PCIBus *bus;
     uint8_t devfn;
@@ -107,6 +112,7 @@ struct VTDAddressSpace {
     MemoryRegion iommu_ir_fault; /* Interrupt region for catching fault */
     IntelIOMMUState *iommu_state;
     VTDContextCacheEntry context_cache_entry;
+    VTDPASIDCacheEntry pasid_cache_entry;
     QLIST_ENTRY(VTDAddressSpace) next;
     /* Superset of notifier flags that this address space has */
     IOMMUNotifierFlag notifier_flags;
diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
index 6a168d5107..66f45f89cb 100644
--- a/hw/i386/intel_iommu.c
+++ b/hw/i386/intel_iommu.c
@@ -1607,7 +1607,7 @@ static uint16_t vtd_get_domain_id(IntelIOMMUState *s,
 
     if (s->root_scalable) {
         vtd_ce_get_rid2pasid_entry(s, ce, &pe, pasid);
-        return VTD_SM_PASID_ENTRY_DID(pe.val[1]);
+        return VTD_SM_PASID_ENTRY_DID(&pe);
     }
 
     return VTD_CONTEXT_ENTRY_DID(ce->hi);
@@ -3051,6 +3051,135 @@ static bool vtd_process_piotlb_desc(IntelIOMMUState *s,
     return true;
 }
 
+static inline int vtd_dev_get_pe_from_pasid(VTDAddressSpace *vtd_as,
+                                            VTDPASIDEntry *pe)
+{
+    IntelIOMMUState *s = vtd_as->iommu_state;
+    VTDContextEntry ce;
+    int ret;
+
+    if (!s->root_scalable) {
+        return -VTD_FR_RTADDR_INV_TTM;
+    }
+
+    ret = vtd_dev_to_context_entry(s, pci_bus_num(vtd_as->bus), vtd_as->devfn,
+                                   &ce);
+    if (ret) {
+        return ret;
+    }
+
+    return vtd_ce_get_rid2pasid_entry(s, &ce, pe, vtd_as->pasid);
+}
+
+/*
+ * Update or invalidate pasid cache based on the value in memory.
+ */
+static void vtd_pasid_cache_sync_locked(gpointer key, gpointer value,
+                                        gpointer user_data)
+{
+    VTDPASIDCacheInfo *pc_info = user_data;
+    VTDAddressSpace *vtd_as = value;
+    VTDPASIDCacheEntry *pc_entry = &vtd_as->pasid_cache_entry;
+    VTDPASIDEntry pe;
+    uint16_t did;
+
+    if (vtd_dev_get_pe_from_pasid(vtd_as, &pe)) {
+        /*
+         * No valid pasid entry in guest memory. e.g. pasid entry was modified
+         * to be either all-zero or non-present. Either case means existing
+         * pasid cache should be invalidated.
+         */
+        pc_entry->valid = false;
+        return;
+    }
+
+    /*
+     * VTD_INV_DESC_PASIDC_G_DSI and VTD_INV_DESC_PASIDC_G_PASID_SI require
+     * DID check. If DID doesn't match the value in cache or memory, then
+     * it's not a pasid entry we want to invalidate.
+     */
+    switch (pc_info->type) {
+    case VTD_INV_DESC_PASIDC_G_PASID_SI:
+        if (pc_info->pasid != vtd_as->pasid) {
+            return;
+        }
+        /* Fall through */
+    case VTD_INV_DESC_PASIDC_G_DSI:
+        if (pc_entry->valid) {
+            did = VTD_SM_PASID_ENTRY_DID(&pc_entry->pasid_entry);
+            if (pc_info->did == did) {
+                break;
+            }
+        }
+        did = VTD_SM_PASID_ENTRY_DID(&pe);
+        if (pc_info->did == did) {
+            break;
+        }
+        return;
+    }
+
+    pc_entry->pasid_entry = pe;
+    pc_entry->valid = true;
+}
+
+static void vtd_pasid_cache_sync(IntelIOMMUState *s, VTDPASIDCacheInfo *pc_info)
+{
+    if (!s->root_scalable || !s->dmar_enabled) {
+        return;
+    }
+
+    vtd_iommu_lock(s);
+    g_hash_table_foreach(s->vtd_address_spaces, vtd_pasid_cache_sync_locked,
+                         pc_info);
+    vtd_iommu_unlock(s);
+}
+
+static bool vtd_process_pasid_desc(IntelIOMMUState *s,
+                                   VTDInvDesc *inv_desc)
+{
+    uint16_t did;
+    uint32_t pasid;
+    VTDPASIDCacheInfo pc_info = {};
+    uint64_t mask[4] = {VTD_INV_DESC_PASIDC_RSVD_VAL0, VTD_INV_DESC_ALL_ONE,
+                        VTD_INV_DESC_ALL_ONE, VTD_INV_DESC_ALL_ONE};
+
+    if (!vtd_inv_desc_reserved_check(s, inv_desc, mask, true,
+                                     __func__, "pasid cache inv")) {
+        return false;
+    }
+
+    did = VTD_INV_DESC_PASIDC_DID(inv_desc);
+    pasid = VTD_INV_DESC_PASIDC_PASID(inv_desc);
+    pc_info.type = VTD_INV_DESC_PASIDC_G(inv_desc);
+
+    switch (pc_info.type) {
+    case VTD_INV_DESC_PASIDC_G_DSI:
+        trace_vtd_inv_desc_pasid_cache_dsi(did);
+        pc_info.did = did;
+        break;
+
+    case VTD_INV_DESC_PASIDC_G_PASID_SI:
+        /* PASID selective implies a DID selective */
+        trace_vtd_inv_desc_pasid_cache_psi(did, pasid);
+        pc_info.did = did;
+        pc_info.pasid = pasid ?: PCI_NO_PASID;
+        break;
+
+    case VTD_INV_DESC_PASIDC_G_GLOBAL:
+        trace_vtd_inv_desc_pasid_cache_gsi();
+        break;
+
+    default:
+        error_report_once("invalid granularity field in PASID-cache invalidate "
+                          "descriptor, hi: 0x%"PRIx64" lo: 0x%" PRIx64,
+                           inv_desc->val[1], inv_desc->val[0]);
+        return false;
+    }
+
+    vtd_pasid_cache_sync(s, &pc_info);
+    return true;
+}
+
 static bool vtd_process_inv_iec_desc(IntelIOMMUState *s,
                                      VTDInvDesc *inv_desc)
 {
@@ -3266,6 +3395,13 @@ static bool vtd_process_inv_desc(IntelIOMMUState *s)
         }
         break;
 
+    case VTD_INV_DESC_PC:
+        trace_vtd_inv_desc("pasid-cache", inv_desc.val[1], inv_desc.val[0]);
+        if (!vtd_process_pasid_desc(s, &inv_desc)) {
+            return false;
+        }
+        break;
+
     case VTD_INV_DESC_PIOTLB:
         trace_vtd_inv_desc("p-iotlb", inv_desc.val[1], inv_desc.val[0]);
         if (!vtd_process_piotlb_desc(s, &inv_desc)) {
@@ -3308,16 +3444,6 @@ static bool vtd_process_inv_desc(IntelIOMMUState *s)
         }
         break;
 
-    /*
-     * TODO: the entity of below two cases will be implemented in future series.
-     * To make guest (which integrates scalable mode support patch set in
-     * iommu driver) work, just return true is enough so far.
-     */
-    case VTD_INV_DESC_PC:
-        if (s->scalable_mode) {
-            break;
-        }
-    /* fallthrough */
     default:
         error_report_once("%s: invalid inv desc: hi=%"PRIx64", lo=%"PRIx64
                           " (unknown type)", __func__, inv_desc.hi,
@@ -5005,7 +5131,7 @@ static int vtd_pri_perform_implicit_invalidation(VTDAddressSpace *vtd_as,
         return -EINVAL;
     }
     pgtt = VTD_PE_GET_TYPE(&pe);
-    domain_id = VTD_SM_PASID_ENTRY_DID(pe.val[1]);
+    domain_id = VTD_SM_PASID_ENTRY_DID(&pe);
     ret = 0;
     switch (pgtt) {
     case VTD_SM_PASID_ENTRY_FLT:
diff --git a/hw/i386/trace-events b/hw/i386/trace-events
index ac9e1a10aa..298addb24d 100644
--- a/hw/i386/trace-events
+++ b/hw/i386/trace-events
@@ -24,6 +24,9 @@ vtd_inv_qi_head(uint16_t head) "read head %d"
 vtd_inv_qi_tail(uint16_t head) "write tail %d"
 vtd_inv_qi_fetch(void) ""
 vtd_context_cache_reset(void) ""
+vtd_inv_desc_pasid_cache_gsi(void) ""
+vtd_inv_desc_pasid_cache_dsi(uint16_t domain) "Domain selective PC invalidation domain 0x%"PRIx16
+vtd_inv_desc_pasid_cache_psi(uint16_t domain, uint32_t pasid) "PASID selective PC invalidation domain 0x%"PRIx16" pasid 0x%"PRIx32
 vtd_re_not_present(uint8_t bus) "Root entry bus %"PRIu8" not present"
 vtd_ce_not_present(uint8_t bus, uint8_t devfn) "Context entry bus %"PRIu8" devfn %"PRIu8" not present"
 vtd_iotlb_page_hit(uint16_t sid, uint64_t addr, uint64_t slpte, uint16_t domain) "IOTLB page hit sid 0x%"PRIx16" iova 0x%"PRIx64" slpte 0x%"PRIx64" domain 0x%"PRIx16
-- 
2.47.1