From: Mostafa Saleh <smostafa@google.com>
To: qemu-arm@nongnu.org, eric.auger@redhat.com,
peter.maydell@linaro.org, qemu-devel@nongnu.org
Cc: jean-philippe@linaro.org, alex.bennee@linaro.org, maz@kernel.org,
nicolinc@nvidia.com, julien@xen.org,
Mostafa Saleh <smostafa@google.com>
Subject: [RFC PATCH 03/12] hw/arm/smmu: Add stage to TLB
Date: Mon, 25 Mar 2024 10:13:59 +0000 [thread overview]
Message-ID: <20240325101442.1306300-4-smostafa@google.com> (raw)
In-Reply-To: <20240325101442.1306300-1-smostafa@google.com>
TLBs for nesting will be extended to be combined, a new index is added
"stage", with 2 valid values:
- SMMU_STAGE_1: Meaning this translates VA to PADDR, this entry can
be cached from fully nested configuration or from stage-1 only.
We don't support separate cached entries (VA to IPA)
- SMMU_STAGE_2: Meaning this translates IPA to PADDR, cached from
stage-2 only configuration.
For TLB invalidation:
- by VA: Invalidate TLBs tagged with SMMU_STAGE_1
- by IPA: Invalidate TLBs tagged with SMMU_STAGE_2
- All: Will invalidate both, this is communicated to the TLB as
SMMU_NESTED which is (SMMU_STAGE_1 | SMMU_STAGE_2) which uses
it as a mask.
This briefly described in the user manual (ARM IHI 0070 F.b) in
"16.2.1 Caching combined structures".
Signed-off-by: Mostafa Saleh <smostafa@google.com>
---
hw/arm/smmu-common.c | 27 +++++++++++++++++----------
hw/arm/smmu-internal.h | 2 ++
hw/arm/smmuv3.c | 5 +++--
hw/arm/trace-events | 3 ++-
include/hw/arm/smmu-common.h | 8 ++++++--
5 files changed, 30 insertions(+), 15 deletions(-)
diff --git a/hw/arm/smmu-common.c b/hw/arm/smmu-common.c
index 20630eb670..677dcf9a13 100644
--- a/hw/arm/smmu-common.c
+++ b/hw/arm/smmu-common.c
@@ -38,7 +38,7 @@ static guint smmu_iotlb_key_hash(gconstpointer v)
/* Jenkins hash */
a = b = c = JHASH_INITVAL + sizeof(*key);
- a += key->asid + key->vmid + key->level + key->tg;
+ a += key->asid + key->vmid + key->level + key->tg + key->stage;
b += extract64(key->iova, 0, 32);
c += extract64(key->iova, 32, 32);
@@ -54,14 +54,14 @@ static gboolean smmu_iotlb_key_equal(gconstpointer v1, gconstpointer v2)
return (k1->asid == k2->asid) && (k1->iova == k2->iova) &&
(k1->level == k2->level) && (k1->tg == k2->tg) &&
- (k1->vmid == k2->vmid);
+ (k1->vmid == k2->vmid) && (k1->stage == k2->stage);
}
SMMUIOTLBKey smmu_get_iotlb_key(uint16_t asid, uint16_t vmid, uint64_t iova,
- uint8_t tg, uint8_t level)
+ uint8_t tg, uint8_t level, SMMUStage stage)
{
SMMUIOTLBKey key = {.asid = asid, .vmid = vmid, .iova = iova,
- .tg = tg, .level = level};
+ .tg = tg, .level = level, .stage = stage};
return key;
}
@@ -81,7 +81,8 @@ SMMUTLBEntry *smmu_iotlb_lookup(SMMUState *bs, SMMUTransCfg *cfg,
SMMUIOTLBKey key;
key = smmu_get_iotlb_key(cfg->asid, cfg->s2cfg.vmid,
- iova & ~mask, tg, level);
+ iova & ~mask, tg, level,
+ SMMU_STAGE_TO_TLB_TAG(cfg->stage));
entry = g_hash_table_lookup(bs->iotlb, &key);
if (entry) {
break;
@@ -109,15 +110,16 @@ void smmu_iotlb_insert(SMMUState *bs, SMMUTransCfg *cfg, SMMUTLBEntry *new)
{
SMMUIOTLBKey *key = g_new0(SMMUIOTLBKey, 1);
uint8_t tg = (new->granule - 10) / 2;
+ SMMUStage stage_tag = SMMU_STAGE_TO_TLB_TAG(cfg->stage);
if (g_hash_table_size(bs->iotlb) >= SMMU_IOTLB_MAX_SIZE) {
smmu_iotlb_inv_all(bs);
}
*key = smmu_get_iotlb_key(cfg->asid, cfg->s2cfg.vmid, new->entry.iova,
- tg, new->level);
+ tg, new->level, stage_tag);
trace_smmu_iotlb_insert(cfg->asid, cfg->s2cfg.vmid, new->entry.iova,
- tg, new->level);
+ tg, new->level, stage_tag);
g_hash_table_insert(bs->iotlb, key, new);
}
@@ -159,18 +161,22 @@ static gboolean smmu_hash_remove_by_asid_vmid_iova(gpointer key, gpointer value,
if (info->vmid >= 0 && info->vmid != SMMU_IOTLB_VMID(iotlb_key)) {
return false;
}
+ if (!(info->stage & SMMU_IOTLB_STAGE(iotlb_key))) {
+ return false;
+ }
return ((info->iova & ~entry->addr_mask) == entry->iova) ||
((entry->iova & ~info->mask) == info->iova);
}
void smmu_iotlb_inv_iova(SMMUState *s, int asid, int vmid, dma_addr_t iova,
- uint8_t tg, uint64_t num_pages, uint8_t ttl)
+ uint8_t tg, uint64_t num_pages, uint8_t ttl,
+ SMMUStage stage)
{
/* if tg is not set we use 4KB range invalidation */
uint8_t granule = tg ? tg * 2 + 10 : 12;
if (ttl && (num_pages == 1) && (asid >= 0)) {
- SMMUIOTLBKey key = smmu_get_iotlb_key(asid, vmid, iova, tg, ttl);
+ SMMUIOTLBKey key = smmu_get_iotlb_key(asid, vmid, iova, tg, ttl, stage);
if (g_hash_table_remove(s->iotlb, &key)) {
return;
@@ -184,6 +190,7 @@ void smmu_iotlb_inv_iova(SMMUState *s, int asid, int vmid, dma_addr_t iova,
SMMUIOTLBPageInvInfo info = {
.asid = asid, .iova = iova,
.vmid = vmid,
+ .stage = stage,
.mask = (num_pages * 1 << granule) - 1};
g_hash_table_foreach_remove(s->iotlb,
@@ -597,7 +604,7 @@ SMMUTLBEntry *smmu_translate(SMMUState *bs, SMMUTransCfg *cfg, dma_addr_t addr,
if (cached_entry) {
if ((flag & IOMMU_WO) && !(cached_entry->entry.perm & IOMMU_WO)) {
info->type = SMMU_PTW_ERR_PERMISSION;
- info->stage = cfg->stage;
+ info->stage = SMMU_STAGE_TO_TLB_TAG(cfg->stage);
return NULL;
}
return cached_entry;
diff --git a/hw/arm/smmu-internal.h b/hw/arm/smmu-internal.h
index 843bebb185..6caa0ddf21 100644
--- a/hw/arm/smmu-internal.h
+++ b/hw/arm/smmu-internal.h
@@ -133,12 +133,14 @@ static inline int pgd_concat_idx(int start_level, int granule_sz,
#define SMMU_IOTLB_ASID(key) ((key).asid)
#define SMMU_IOTLB_VMID(key) ((key).vmid)
+#define SMMU_IOTLB_STAGE(key) ((key).stage)
typedef struct SMMUIOTLBPageInvInfo {
int asid;
int vmid;
uint64_t iova;
uint64_t mask;
+ SMMUStage stage;
} SMMUIOTLBPageInvInfo;
typedef struct SMMUSIDRange {
diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c
index f081ff0cc4..b27bf297e1 100644
--- a/hw/arm/smmuv3.c
+++ b/hw/arm/smmuv3.c
@@ -1087,7 +1087,7 @@ static void smmuv3_range_inval(SMMUState *s, Cmd *cmd)
if (!tg) {
trace_smmuv3_range_inval(vmid, asid, addr, tg, 1, ttl, leaf);
smmuv3_inv_notifiers_iova(s, asid, vmid, addr, tg, 1);
- smmu_iotlb_inv_iova(s, asid, vmid, addr, tg, 1, ttl);
+ smmu_iotlb_inv_iova(s, asid, vmid, addr, tg, 1, ttl, SMMU_NESTED);
return;
}
@@ -1105,7 +1105,8 @@ static void smmuv3_range_inval(SMMUState *s, Cmd *cmd)
num_pages = (mask + 1) >> granule;
trace_smmuv3_range_inval(vmid, asid, addr, tg, num_pages, ttl, leaf);
smmuv3_inv_notifiers_iova(s, asid, vmid, addr, tg, num_pages);
- smmu_iotlb_inv_iova(s, asid, vmid, addr, tg, num_pages, ttl);
+ smmu_iotlb_inv_iova(s, asid, vmid, addr, tg,
+ num_pages, ttl, SMMU_NESTED);
addr += mask + 1;
}
}
diff --git a/hw/arm/trace-events b/hw/arm/trace-events
index cc12924a84..3000c3bf14 100644
--- a/hw/arm/trace-events
+++ b/hw/arm/trace-events
@@ -14,10 +14,11 @@ smmu_iotlb_inv_all(void) "IOTLB invalidate all"
smmu_iotlb_inv_asid(uint16_t asid) "IOTLB invalidate asid=%d"
smmu_iotlb_inv_vmid(uint16_t vmid) "IOTLB invalidate vmid=%d"
smmu_iotlb_inv_iova(uint16_t asid, uint64_t addr) "IOTLB invalidate asid=%d addr=0x%"PRIx64
+smmu_iotlb_inv_stage(int stage) "Stage invalidate stage=%d"
smmu_inv_notifiers_mr(const char *name) "iommu mr=%s"
smmu_iotlb_lookup_hit(uint16_t asid, uint16_t vmid, uint64_t addr, uint32_t hit, uint32_t miss, uint32_t p) "IOTLB cache HIT asid=%d vmid=%d addr=0x%"PRIx64" hit=%d miss=%d hit rate=%d"
smmu_iotlb_lookup_miss(uint16_t asid, uint16_t vmid, uint64_t addr, uint32_t hit, uint32_t miss, uint32_t p) "IOTLB cache MISS asid=%d vmid=%d addr=0x%"PRIx64" hit=%d miss=%d hit rate=%d"
-smmu_iotlb_insert(uint16_t asid, uint16_t vmid, uint64_t addr, uint8_t tg, uint8_t level) "IOTLB ++ asid=%d vmid=%d addr=0x%"PRIx64" tg=%d level=%d"
+smmu_iotlb_insert(uint16_t asid, uint16_t vmid, uint64_t addr, uint8_t tg, uint8_t level, int stage) "IOTLB ++ asid=%d vmid=%d addr=0x%"PRIx64" tg=%d level=%d stage=%d"
# 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)"
diff --git a/include/hw/arm/smmu-common.h b/include/hw/arm/smmu-common.h
index 876e78975c..695d6d10ad 100644
--- a/include/hw/arm/smmu-common.h
+++ b/include/hw/arm/smmu-common.h
@@ -37,6 +37,8 @@
#define VMSA_IDXMSK(isz, strd, lvl) ((1ULL << \
VMSA_BIT_LVL(isz, strd, lvl)) - 1)
+#define SMMU_STAGE_TO_TLB_TAG(stage) (((stage) == SMMU_NESTED) ? \
+ SMMU_STAGE_1 : (stage))
/*
* Page table walk error types
*/
@@ -136,6 +138,7 @@ typedef struct SMMUIOTLBKey {
uint16_t vmid;
uint8_t tg;
uint8_t level;
+ SMMUStage stage;
} SMMUIOTLBKey;
struct SMMUState {
@@ -203,12 +206,13 @@ SMMUTLBEntry *smmu_iotlb_lookup(SMMUState *bs, SMMUTransCfg *cfg,
SMMUTransTableInfo *tt, hwaddr iova);
void smmu_iotlb_insert(SMMUState *bs, SMMUTransCfg *cfg, SMMUTLBEntry *entry);
SMMUIOTLBKey smmu_get_iotlb_key(uint16_t asid, uint16_t vmid, uint64_t iova,
- uint8_t tg, uint8_t level);
+ uint8_t tg, uint8_t level, SMMUStage stage);
void smmu_iotlb_inv_all(SMMUState *s);
void smmu_iotlb_inv_asid(SMMUState *s, uint16_t asid);
void smmu_iotlb_inv_vmid(SMMUState *s, uint16_t vmid);
void smmu_iotlb_inv_iova(SMMUState *s, int asid, int vmid, dma_addr_t iova,
- uint8_t tg, uint64_t num_pages, uint8_t ttl);
+ uint8_t tg, uint64_t num_pages, uint8_t ttl,
+ SMMUStage stage);
/* Unmap the range of all the notifiers registered to any IOMMU mr */
void smmu_inv_notifiers_all(SMMUState *s);
--
2.44.0.396.g6e790dbe36-goog
next prev parent reply other threads:[~2024-03-25 10:16 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-03-25 10:13 [RFC PATCH 00/12] SMMUv3 nested translation support Mostafa Saleh
2024-03-25 10:13 ` [RFC PATCH 01/12] hw/arm/smmu: Use enum for SMMU stage Mostafa Saleh
2024-04-02 16:32 ` Eric Auger
2024-03-25 10:13 ` [RFC PATCH 02/12] hw/arm/smmu: Split smmuv3_translate() Mostafa Saleh
2024-04-02 16:32 ` Eric Auger
2024-03-25 10:13 ` Mostafa Saleh [this message]
2024-04-02 17:15 ` [RFC PATCH 03/12] hw/arm/smmu: Add stage to TLB Eric Auger
2024-04-02 18:47 ` Mostafa Saleh
2024-04-03 7:22 ` Eric Auger
2024-04-03 9:55 ` Mostafa Saleh
2024-03-25 10:14 ` [RFC PATCH 04/12] hw/arm/smmu: Support nesting in commands Mostafa Saleh
2024-03-25 10:14 ` [RFC PATCH 05/12] hw/arm/smmuv3: Support nested SMMUs in smmuv3_notify_iova() Mostafa Saleh
2024-03-25 10:14 ` [RFC PATCH 06/12] hw/arm/smmuv3: Translate CD and TT using stage-2 table Mostafa Saleh
2024-03-25 10:14 ` [RFC PATCH 07/12] hw/arm/smmu-common: Support nested translation Mostafa Saleh
2024-03-25 14:20 ` Julien Grall
2024-03-25 20:47 ` Mostafa Saleh
2024-03-25 10:14 ` [RFC PATCH 08/12] hw/arm/smmuv3: Support and advertise nesting Mostafa Saleh
2024-03-25 10:14 ` [RFC PATCH 09/12] hw/arm/smmuv3: Advertise S2FWB Mostafa Saleh
2024-03-25 10:14 ` [RFC PATCH 10/12] hw/arm/smmu: Refactor SMMU OAS Mostafa Saleh
2024-03-25 10:14 ` [RFC PATCH 11/12] hw/arm/smmuv3: Add property for OAS Mostafa Saleh
2024-03-25 10:14 ` [RFC PATCH 12/12] hw/arm/virt: Set SMMU OAS based on CPU PARANGE Mostafa Saleh
2024-03-25 17:50 ` [RFC PATCH 00/12] SMMUv3 nested translation support Marcin Juszkiewicz
2024-04-02 22:28 ` Nicolin Chen
2024-04-03 10:39 ` Mostafa Saleh
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240325101442.1306300-4-smostafa@google.com \
--to=smostafa@google.com \
--cc=alex.bennee@linaro.org \
--cc=eric.auger@redhat.com \
--cc=jean-philippe@linaro.org \
--cc=julien@xen.org \
--cc=maz@kernel.org \
--cc=nicolinc@nvidia.com \
--cc=peter.maydell@linaro.org \
--cc=qemu-arm@nongnu.org \
--cc=qemu-devel@nongnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).