@@ -24,11 +24,43 @@
#include "qom/cpu.h"
#include "hw/qdev-properties.h"
#include "qapi/error.h"
+#include "qemu/jhash.h"
#include "qemu/error-report.h"
#include "hw/arm/smmu-common.h"
#include "smmu-internal.h"
+/* IOTLB Management */
+
+inline void smmu_iotlb_inv_all(SMMUState *s)
+{
+ trace_smmu_iotlb_inv_all();
+ g_hash_table_remove_all(s->iotlb);
+}
+
+static gboolean smmu_hash_remove_by_asid(gpointer key, gpointer value,
+ gpointer user_data)
+{
+ uint16_t asid = *(uint16_t *)user_data;
+ SMMUIOTLBKey *iotlb_key = (SMMUIOTLBKey *)key;
+
+ return iotlb_key->asid == asid;
+}
+
+inline void smmu_iotlb_inv_iova(SMMUState *s, uint16_t asid, dma_addr_t iova)
+{
+ SMMUIOTLBKey key = {.asid = asid, .iova = iova};
+
+ trace_smmu_iotlb_inv_iova(asid, iova);
+ g_hash_table_remove(s->iotlb, &key);
+}
+
+inline void smmu_iotlb_inv_asid(SMMUState *s, uint16_t asid)
+{
+ trace_smmu_iotlb_inv_asid(asid);
+ g_hash_table_foreach_remove(s->iotlb, smmu_hash_remove_by_asid, &asid);
+}
+
/* VMSAv8-64 Translation */
/**
@@ -328,6 +360,31 @@ IOMMUMemoryRegion *smmu_iommu_mr(SMMUState *s, uint32_t sid)
return NULL;
}
+static guint smmu_iotlb_key_hash(gconstpointer v)
+{
+ SMMUIOTLBKey *key = (SMMUIOTLBKey *)v;
+ uint32_t a, b, c;
+
+ /* Jenkins hash */
+ a = b = c = JHASH_INITVAL + sizeof(*key);
+ a += key->asid;
+ b += extract64(key->iova, 0, 32);
+ c += extract64(key->iova, 32, 32);
+
+ __jhash_mix(a, b, c);
+ __jhash_final(a, b, c);
+
+ return c;
+}
+
+static gboolean smmu_iotlb_key_equal(gconstpointer v1, gconstpointer v2)
+{
+ const SMMUIOTLBKey *k1 = v1;
+ const SMMUIOTLBKey *k2 = v2;
+
+ return (k1->asid == k2->asid) && (k1->iova == k2->iova);
+}
+
static void smmu_base_realize(DeviceState *dev, Error **errp)
{
SMMUState *s = ARM_SMMU(dev);
@@ -340,6 +397,8 @@ static void smmu_base_realize(DeviceState *dev, Error **errp)
return;
}
s->configs = g_hash_table_new_full(NULL, NULL, NULL, g_free);
+ s->iotlb = g_hash_table_new_full(smmu_iotlb_key_hash, smmu_iotlb_key_equal,
+ g_free, g_free);
s->smmu_pcibus_by_busptr = g_hash_table_new(NULL, NULL);
if (s->primary_bus) {
@@ -354,6 +413,7 @@ static void smmu_base_reset(DeviceState *dev)
SMMUState *s = ARM_SMMU(dev);
g_hash_table_remove_all(s->configs);
+ g_hash_table_remove_all(s->iotlb);
}
static Property smmu_dev_properties[] = {
@@ -605,6 +605,10 @@ static IOMMUTLBEntry smmuv3_translate(IOMMUMemoryRegion *mr, hwaddr addr,
SMMUEventInfo event = {.type = SMMU_EVT_NONE, .sid = sid};
SMMUPTWEventInfo ptw_info = {};
SMMUTranslationStatus status;
+ SMMUState *bs = ARM_SMMU(s);
+ uint64_t page_mask, aligned_addr;
+ IOMMUTLBEntry *cached_entry = NULL;
+ SMMUTransTableInfo *tt;
SMMUTransCfg *cfg = NULL;
IOMMUTLBEntry entry = {
.target_as = &address_space_memory,
@@ -613,6 +617,7 @@ static IOMMUTLBEntry smmuv3_translate(IOMMUMemoryRegion *mr, hwaddr addr,
.addr_mask = ~(hwaddr)0,
.perm = IOMMU_NONE,
};
+ SMMUIOTLBKey key, *new_key;
qemu_mutex_lock(&s->mutex);
@@ -637,7 +642,57 @@ static IOMMUTLBEntry smmuv3_translate(IOMMUMemoryRegion *mr, hwaddr addr,
goto epilogue;
}
- if (smmu_ptw(cfg, addr, flag, &entry, &ptw_info)) {
+ tt = select_tt(cfg, addr);
+ if (!tt) {
+ if (event.record_trans_faults) {
+ event.type = SMMU_EVT_F_TRANSLATION;
+ event.u.f_translation.addr = addr;
+ event.u.f_translation.rnw = flag & 0x1;
+ }
+ status = SMMU_TRANS_ERROR;
+ goto epilogue;
+ }
+
+ page_mask = (1ULL << (tt->granule_sz)) - 1;
+ aligned_addr = addr & ~page_mask;
+
+ key.asid = cfg->asid;
+ key.iova = aligned_addr;
+
+ cached_entry = g_hash_table_lookup(bs->iotlb, &key);
+ if (cached_entry) {
+ cfg->iotlb_hits++;
+ trace_smmu_iotlb_cache_hit(cfg->asid, aligned_addr,
+ cfg->iotlb_hits, cfg->iotlb_misses,
+ 100 * cfg->iotlb_hits /
+ (cfg->iotlb_hits + cfg->iotlb_misses));
+ if ((flag & IOMMU_WO) && !(cached_entry->perm & IOMMU_WO)) {
+ status = SMMU_TRANS_ERROR;
+ if (event.record_trans_faults) {
+ event.type = SMMU_EVT_F_PERMISSION;
+ event.u.f_permission.addr = addr;
+ event.u.f_permission.rnw = flag & 0x1;
+ }
+ } else {
+ status = SMMU_TRANS_SUCCESS;
+ }
+ goto epilogue;
+ }
+
+ cfg->iotlb_misses++;
+ trace_smmu_iotlb_cache_miss(cfg->asid, addr & ~page_mask,
+ cfg->iotlb_hits, cfg->iotlb_misses,
+ 100 * cfg->iotlb_hits /
+ (cfg->iotlb_hits + cfg->iotlb_misses));
+
+ if (g_hash_table_size(bs->iotlb) >= SMMU_IOTLB_MAX_SIZE) {
+ smmu_iotlb_inv_all(bs);
+ }
+
+ cached_entry = g_new0(IOMMUTLBEntry, 1);
+
+ if (smmu_ptw(cfg, aligned_addr, flag, cached_entry, &ptw_info)) {
+ g_free(cached_entry);
switch (ptw_info.type) {
case SMMU_PTW_ERR_WALK_EABT:
event.type = SMMU_EVT_F_WALK_EABT;
@@ -679,6 +734,10 @@ static IOMMUTLBEntry smmuv3_translate(IOMMUMemoryRegion *mr, hwaddr addr,
}
status = SMMU_TRANS_ERROR;
} else {
+ new_key = g_new0(SMMUIOTLBKey, 1);
+ new_key->asid = cfg->asid;
+ new_key->iova = aligned_addr;
+ g_hash_table_insert(bs->iotlb, new_key, cached_entry);
status = SMMU_TRANS_SUCCESS;
}
@@ -687,6 +746,9 @@ epilogue:
switch (status) {
case SMMU_TRANS_SUCCESS:
entry.perm = flag;
+ entry.translated_addr = cached_entry->translated_addr +
+ (addr & page_mask);
+ entry.addr_mask = cached_entry->addr_mask;
trace_smmuv3_translate_success(mr->parent_obj.name, sid, addr,
entry.translated_addr, entry.perm);
break;
@@ -832,10 +894,39 @@ static int smmuv3_cmdq_consume(SMMUv3State *s)
smmuv3_flush_config(sdev);
break;
}
- case SMMU_CMD_TLBI_NH_ALL:
case SMMU_CMD_TLBI_NH_ASID:
- case SMMU_CMD_TLBI_NH_VA:
+ {
+ uint16_t asid = CMD_ASID(&cmd);
+
+ trace_smmuv3_cmdq_tlbi_nh_asid(asid);
+ smmu_iotlb_inv_asid(bs, asid);
+ break;
+ }
+ case SMMU_CMD_TLBI_NH_ALL:
+ case SMMU_CMD_TLBI_NSNH_ALL:
+ trace_smmuv3_cmdq_tlbi_nh();
+ smmu_iotlb_inv_all(bs);
+ break;
case SMMU_CMD_TLBI_NH_VAA:
+ {
+ dma_addr_t addr = CMD_ADDR(&cmd);
+ uint16_t vmid = CMD_VMID(&cmd);
+
+ trace_smmuv3_cmdq_tlbi_nh_vaa(vmid, addr);
+ smmu_iotlb_inv_all(bs);
+ break;
+ }
+ case SMMU_CMD_TLBI_NH_VA:
+ {
+ uint16_t asid = CMD_ASID(&cmd);
+ uint16_t vmid = CMD_VMID(&cmd);
+ dma_addr_t addr = CMD_ADDR(&cmd);
+ bool leaf = CMD_LEAF(&cmd);
+
+ trace_smmuv3_cmdq_tlbi_nh_va(vmid, asid, addr, leaf);
+ smmu_iotlb_inv_iova(bs, asid, addr);
+ break;
+ }
case SMMU_CMD_TLBI_EL3_ALL:
case SMMU_CMD_TLBI_EL3_VA:
case SMMU_CMD_TLBI_EL2_ALL:
@@ -844,7 +935,6 @@ static int smmuv3_cmdq_consume(SMMUv3State *s)
case SMMU_CMD_TLBI_EL2_VAA:
case SMMU_CMD_TLBI_S12_VMALL:
case SMMU_CMD_TLBI_S2_IPA:
- case SMMU_CMD_TLBI_NSNH_ALL:
case SMMU_CMD_ATC_INV:
case SMMU_CMD_PRI_RESP:
case SMMU_CMD_RESUME:
@@ -12,6 +12,11 @@ smmu_ptw_invalid_pte(int stage, int level, uint64_t baseaddr, uint64_t pteaddr,
smmu_ptw_page_pte(int stage, int level, uint64_t iova, uint64_t baseaddr, uint64_t pteaddr, uint64_t pte, uint64_t address) "stage=%d level=%d iova=0x%"PRIx64" base@=0x%"PRIx64" pte@=0x%"PRIx64" pte=0x%"PRIx64" page address = 0x%"PRIx64
smmu_ptw_block_pte(int stage, int level, uint64_t baseaddr, uint64_t pteaddr, uint64_t pte, uint64_t iova, uint64_t gpa, int bsize_mb) "stage=%d level=%d base@=0x%"PRIx64" pte@=0x%"PRIx64" pte=0x%"PRIx64" iova=0x%"PRIx64" block address = 0x%"PRIx64" block size = %d MiB"
smmu_get_pte(uint64_t baseaddr, int index, uint64_t pteaddr, uint64_t pte) "baseaddr=0x%"PRIx64" index=0x%x, pteaddr=0x%"PRIx64", pte=0x%"PRIx64
+smmu_iotlb_cache_hit(uint16_t asid, uint64_t addr, uint32_t hit, uint32_t miss, uint32_t p) "IOTLB cache HIT asid=%d addr=0x%"PRIx64" hit=%d miss=%d hit rate=%d"
+smmu_iotlb_cache_miss(uint16_t asid, uint64_t addr, uint32_t hit, uint32_t miss, uint32_t p) "IOTLB cache MISS asid=%d addr=0x%"PRIx64" hit=%d miss=%d hit rate=%d"
+smmu_iotlb_inv_all(void) "IOTLB invalidate all"
+smmu_iotlb_inv_asid(uint16_t asid) "IOTLB invalidate asid=%d"
+smmu_iotlb_inv_iova(uint16_t asid, uint64_t addr) "IOTLB invalidate asid=%d addr=0x%"PRIx64
#hw/arm/smmuv3.c
smmuv3_read_mmio(uint64_t addr, uint64_t val, unsigned size, uint32_t r) "addr: 0x%"PRIx64" val:0x%"PRIx64" size: 0x%x(%d)"
@@ -45,4 +50,8 @@ smmuv3_cmdq_cfgi_ste_range(int start, int end) "start=0x%d - end=0x%d"
smmuv3_cmdq_cfgi_cd(uint32_t sid) "streamid = %d"
smmuv3_config_cache_hit(uint32_t sid, uint32_t hits, uint32_t misses, uint32_t perc) "Config cache HIT for sid %d (hits=%d, misses=%d, hit rate=%d)"
smmuv3_config_cache_miss(uint32_t sid, uint32_t hits, uint32_t misses, uint32_t perc) "Config cache MISS for sid %d (hits=%d, misses=%d, hit rate=%d)"
+smmuv3_cmdq_tlbi_nh_va(int vmid, int asid, uint64_t addr, bool leaf) "vmid =%d asid =%d addr=0x%"PRIx64" leaf=%d"
+smmuv3_cmdq_tlbi_nh_vaa(int vmid, uint64_t addr) "vmid =%d addr=0x%"PRIx64
+smmuv3_cmdq_tlbi_nh(void) ""
+smmuv3_cmdq_tlbi_nh_asid(uint16_t asid) "asid=%d"
smmuv3_config_cache_inv(uint32_t sid) "Config cache INV for sid %d"
@@ -67,6 +67,8 @@ typedef struct SMMUTransCfg {
uint8_t tbi; /* Top Byte Ignore */
uint16_t asid;
SMMUTransTableInfo tt[2];
+ uint32_t iotlb_hits; /* counts IOTLB hits for this asid */
+ uint32_t iotlb_misses; /* counts IOTLB misses for this asid */
} SMMUTransCfg;
typedef struct SMMUDevice {
@@ -89,6 +91,11 @@ typedef struct SMMUPciBus {
SMMUDevice *pbdev[0]; /* Parent array is sparse, so dynamically alloc */
} SMMUPciBus;
+typedef struct SMMUIOTLBKey {
+ uint64_t iova;
+ uint16_t asid;
+} SMMUIOTLBKey;
+
typedef struct SMMUState {
/* <private> */
SysBusDevice dev;
@@ -147,4 +154,10 @@ SMMUTransTableInfo *select_tt(SMMUTransCfg *cfg, dma_addr_t iova);
/* Return the iommu mr associated to @sid, or NULL if none */
IOMMUMemoryRegion *smmu_iommu_mr(SMMUState *s, uint32_t sid);
+#define SMMU_IOTLB_MAX_SIZE 256
+
+void smmu_iotlb_inv_all(SMMUState *s);
+void smmu_iotlb_inv_asid(SMMUState *s, uint16_t asid);
+void smmu_iotlb_inv_iova(SMMUState *s, uint16_t asid, dma_addr_t iova);
+
#endif /* HW_ARM_SMMU_COMMON */
We emulate a TLB cache of size SMMU_IOTLB_MAX_SIZE=256. It is implemented as a hash table whose key is a combination of the 16b asid and 48b IOVA (Jenkins hash). Entries are invalidated on TLB invalidation commands, either globally, or per asid, or per asid/iova. Signed-off-by: Eric Auger <eric.auger@redhat.com> --- v2 -> v3: - use uint32_t instead of float when printing the iotlb hit rate - use const local variables in smmu_iotlb_key_equal v1 -> v2: - add comment about Jenkins Hash - remove init of iotlb_hits, misses v1: - Add new trace point when smmu is bypassed - s/iotlb_miss/iotlb_misses, s/iotlb_hit/iotlb_hits - use SMMUIOTLBKey as a key Credit to Tomasz Nowicki who did the first implementation of this IOTLB implementation, inspired of intel_iommu implementation. --- hw/arm/smmu-common.c | 60 +++++++++++++++++++++++++++ hw/arm/smmuv3.c | 98 ++++++++++++++++++++++++++++++++++++++++++-- hw/arm/trace-events | 9 ++++ include/hw/arm/smmu-common.h | 13 ++++++ 4 files changed, 176 insertions(+), 4 deletions(-)