* [PATCH v2 0/2] bugfix and optimization about CMD_SYNC
@ 2018-08-09 11:48 Zhen Lei
2018-08-09 11:48 ` [PATCH v2 1/2] iommu/arm-smmu-v3: fix unexpected CMD_SYNC timeout Zhen Lei
2018-08-09 11:48 ` [PATCH v2 2/2] iommu/arm-smmu-v3: avoid redundant CMD_SYNCs if possible Zhen Lei
0 siblings, 2 replies; 4+ messages in thread
From: Zhen Lei @ 2018-08-09 11:48 UTC (permalink / raw)
To: Robin Murphy, Will Deacon, Joerg Roedel, linux-arm-kernel, iommu,
linux-kernel
Cc: Zhen Lei, LinuxArm, Hanjun Guo, Libin
v1->v2:
1. move the call to arm_smmu_cmdq_build_cmd into the critical section,
and keep itself unchange.
2. Although patch2 can make sure no two CMD_SYNCs will be adjacent,
but patch1 is still needed, see below:
cpu0 cpu1 cpu2
msidata=0
msidata=1
insert cmd1
insert a TLBI command
insert cmd0
smmu execute cmd1
smmu execute TLBI
smmu execute cmd0
poll timeout, because msidata=1 is overridden by
cmd0, that means VAL=0, sync_idx=1.
Zhen Lei (2):
iommu/arm-smmu-v3: fix unexpected CMD_SYNC timeout
iommu/arm-smmu-v3: avoid redundant CMD_SYNCs if possible
drivers/iommu/arm-smmu-v3.c | 26 ++++++++++++++++++++------
1 file changed, 20 insertions(+), 6 deletions(-)
--
1.8.3
^ permalink raw reply [flat|nested] 4+ messages in thread
* [PATCH v2 1/2] iommu/arm-smmu-v3: fix unexpected CMD_SYNC timeout
2018-08-09 11:48 [PATCH v2 0/2] bugfix and optimization about CMD_SYNC Zhen Lei
@ 2018-08-09 11:48 ` Zhen Lei
2018-08-09 11:48 ` [PATCH v2 2/2] iommu/arm-smmu-v3: avoid redundant CMD_SYNCs if possible Zhen Lei
1 sibling, 0 replies; 4+ messages in thread
From: Zhen Lei @ 2018-08-09 11:48 UTC (permalink / raw)
To: Robin Murphy, Will Deacon, Joerg Roedel, linux-arm-kernel, iommu,
linux-kernel
Cc: Zhen Lei, LinuxArm, Hanjun Guo, Libin
The condition "(int)(VAL - sync_idx) >= 0" to break loop in function
__arm_smmu_sync_poll_msi requires that sync_idx must be increased
monotonously according to the sequence of the CMDs in the cmdq.
But ".msidata = atomic_inc_return_relaxed(&smmu->sync_nr)" is not protected
by spinlock, so the following scenarios may appear:
cpu0 cpu1
msidata=0
msidata=1
insert cmd1
insert cmd0
smmu execute cmd1
smmu execute cmd0
poll timeout, because msidata=1 is overridden by
cmd0, that means VAL=0, sync_idx=1.
This is not a functional problem, just make the caller wait for a long
time until TIMEOUT. It's rare to happen, because any other CMD_SYNCs
during the waiting period will break it.
Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
---
drivers/iommu/arm-smmu-v3.c | 8 +++-----
1 file changed, 3 insertions(+), 5 deletions(-)
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 1d64710..d17a9a7 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -566,7 +566,7 @@ struct arm_smmu_device {
int gerr_irq;
int combined_irq;
- atomic_t sync_nr;
+ u32 sync_nr;
unsigned long ias; /* IPA */
unsigned long oas; /* PA */
@@ -947,14 +947,13 @@ static int __arm_smmu_cmdq_issue_sync_msi(struct arm_smmu_device *smmu)
struct arm_smmu_cmdq_ent ent = {
.opcode = CMDQ_OP_CMD_SYNC,
.sync = {
- .msidata = atomic_inc_return_relaxed(&smmu->sync_nr),
.msiaddr = virt_to_phys(&smmu->sync_count),
},
};
- arm_smmu_cmdq_build_cmd(cmd, &ent);
-
spin_lock_irqsave(&smmu->cmdq.lock, flags);
+ ent.sync.msidata = ++smmu->sync_nr;
+ arm_smmu_cmdq_build_cmd(cmd, &ent);
arm_smmu_cmdq_insert_cmd(smmu, cmd);
spin_unlock_irqrestore(&smmu->cmdq.lock, flags);
@@ -2179,7 +2178,6 @@ static int arm_smmu_init_structures(struct arm_smmu_device *smmu)
{
int ret;
- atomic_set(&smmu->sync_nr, 0);
ret = arm_smmu_init_queues(smmu);
if (ret)
return ret;
--
1.8.3
^ permalink raw reply related [flat|nested] 4+ messages in thread
* [PATCH v2 2/2] iommu/arm-smmu-v3: avoid redundant CMD_SYNCs if possible
2018-08-09 11:48 [PATCH v2 0/2] bugfix and optimization about CMD_SYNC Zhen Lei
2018-08-09 11:48 ` [PATCH v2 1/2] iommu/arm-smmu-v3: fix unexpected CMD_SYNC timeout Zhen Lei
@ 2018-08-09 11:48 ` Zhen Lei
2018-08-09 12:02 ` Robin Murphy
1 sibling, 1 reply; 4+ messages in thread
From: Zhen Lei @ 2018-08-09 11:48 UTC (permalink / raw)
To: Robin Murphy, Will Deacon, Joerg Roedel, linux-arm-kernel, iommu,
linux-kernel
Cc: Zhen Lei, LinuxArm, Hanjun Guo, Libin
More than two CMD_SYNCs maybe adjacent in the command queue, and the first
one has done what others want to do. Drop the redundant CMD_SYNCs can
improve IO performance especially under the pressure scene.
I did the statistics in my test environment, the number of CMD_SYNCs can
be reduced about 1/3. See below:
CMD_SYNCs reduced: 19542181
CMD_SYNCs total: 58098548 (include reduced)
CMDs total: 116197099 (TLBI:SYNC about 1:1)
Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
---
drivers/iommu/arm-smmu-v3.c | 22 +++++++++++++++++++---
1 file changed, 19 insertions(+), 3 deletions(-)
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index d17a9a7..b96d2d2 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -567,6 +567,7 @@ struct arm_smmu_device {
int gerr_irq;
int combined_irq;
u32 sync_nr;
+ u8 prev_cmd_opcode;
unsigned long ias; /* IPA */
unsigned long oas; /* PA */
@@ -775,6 +776,11 @@ static int queue_remove_raw(struct arm_smmu_queue *q, u64 *ent)
return 0;
}
+static inline u8 arm_smmu_cmd_opcode_get(u64 *cmd)
+{
+ return cmd[0] & CMDQ_0_OP;
+}
+
/* High-level queue accessors */
static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
{
@@ -900,6 +906,8 @@ static void arm_smmu_cmdq_insert_cmd(struct arm_smmu_device *smmu, u64 *cmd)
struct arm_smmu_queue *q = &smmu->cmdq.q;
bool wfe = !!(smmu->features & ARM_SMMU_FEAT_SEV);
+ smmu->prev_cmd_opcode = arm_smmu_cmd_opcode_get(cmd);
+
while (queue_insert_raw(q, cmd) == -ENOSPC) {
if (queue_poll_cons(q, false, wfe))
dev_err_ratelimited(smmu->dev, "CMDQ timeout\n");
@@ -952,9 +960,17 @@ static int __arm_smmu_cmdq_issue_sync_msi(struct arm_smmu_device *smmu)
};
spin_lock_irqsave(&smmu->cmdq.lock, flags);
- ent.sync.msidata = ++smmu->sync_nr;
- arm_smmu_cmdq_build_cmd(cmd, &ent);
- arm_smmu_cmdq_insert_cmd(smmu, cmd);
+ if (smmu->prev_cmd_opcode == CMDQ_OP_CMD_SYNC) {
+ /*
+ * Previous command is CMD_SYNC also, there is no need to add
+ * one more. Just poll it.
+ */
+ ent.sync.msidata = smmu->sync_nr;
+ } else {
+ ent.sync.msidata = ++smmu->sync_nr;
+ arm_smmu_cmdq_build_cmd(cmd, &ent);
+ arm_smmu_cmdq_insert_cmd(smmu, cmd);
+ }
spin_unlock_irqrestore(&smmu->cmdq.lock, flags);
return __arm_smmu_sync_poll_msi(smmu, ent.sync.msidata);
--
1.8.3
^ permalink raw reply related [flat|nested] 4+ messages in thread
* Re: [PATCH v2 2/2] iommu/arm-smmu-v3: avoid redundant CMD_SYNCs if possible
2018-08-09 11:48 ` [PATCH v2 2/2] iommu/arm-smmu-v3: avoid redundant CMD_SYNCs if possible Zhen Lei
@ 2018-08-09 12:02 ` Robin Murphy
0 siblings, 0 replies; 4+ messages in thread
From: Robin Murphy @ 2018-08-09 12:02 UTC (permalink / raw)
To: Zhen Lei, Will Deacon, Joerg Roedel, linux-arm-kernel, iommu,
linux-kernel
Cc: LinuxArm, Hanjun Guo, Libin
On 09/08/18 12:48, Zhen Lei wrote:
> More than two CMD_SYNCs maybe adjacent in the command queue, and the first
> one has done what others want to do. Drop the redundant CMD_SYNCs can
> improve IO performance especially under the pressure scene.
>
> I did the statistics in my test environment, the number of CMD_SYNCs can
> be reduced about 1/3. See below:
> CMD_SYNCs reduced: 19542181
> CMD_SYNCs total: 58098548 (include reduced)
> CMDs total: 116197099 (TLBI:SYNC about 1:1)
>
> Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
> ---
> drivers/iommu/arm-smmu-v3.c | 22 +++++++++++++++++++---
> 1 file changed, 19 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
> index d17a9a7..b96d2d2 100644
> --- a/drivers/iommu/arm-smmu-v3.c
> +++ b/drivers/iommu/arm-smmu-v3.c
> @@ -567,6 +567,7 @@ struct arm_smmu_device {
> int gerr_irq;
> int combined_irq;
> u32 sync_nr;
> + u8 prev_cmd_opcode;
>
> unsigned long ias; /* IPA */
> unsigned long oas; /* PA */
> @@ -775,6 +776,11 @@ static int queue_remove_raw(struct arm_smmu_queue *q, u64 *ent)
> return 0;
> }
>
> +static inline u8 arm_smmu_cmd_opcode_get(u64 *cmd)
> +{
> + return cmd[0] & CMDQ_0_OP;
> +}
> +
> /* High-level queue accessors */
> static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
> {
> @@ -900,6 +906,8 @@ static void arm_smmu_cmdq_insert_cmd(struct arm_smmu_device *smmu, u64 *cmd)
> struct arm_smmu_queue *q = &smmu->cmdq.q;
> bool wfe = !!(smmu->features & ARM_SMMU_FEAT_SEV);
>
> + smmu->prev_cmd_opcode = arm_smmu_cmd_opcode_get(cmd);
> +
> while (queue_insert_raw(q, cmd) == -ENOSPC) {
> if (queue_poll_cons(q, false, wfe))
> dev_err_ratelimited(smmu->dev, "CMDQ timeout\n");
> @@ -952,9 +960,17 @@ static int __arm_smmu_cmdq_issue_sync_msi(struct arm_smmu_device *smmu)
> };
>
> spin_lock_irqsave(&smmu->cmdq.lock, flags);
> - ent.sync.msidata = ++smmu->sync_nr;
> - arm_smmu_cmdq_build_cmd(cmd, &ent);
> - arm_smmu_cmdq_insert_cmd(smmu, cmd);
> + if (smmu->prev_cmd_opcode == CMDQ_OP_CMD_SYNC) {
> + /*
> + * Previous command is CMD_SYNC also, there is no need to add
> + * one more. Just poll it.
> + */
> + ent.sync.msidata = smmu->sync_nr;
Aha! at the time I had pondered how to make multiple callers wait on a
previous sync instead of issuing another back-to-back, but it seemed
complicated precisely *because* of the counter being updated outside the
lock. If only I'd realised... :)
Now I just need to figure out if we can do the same for the polling case.
Robin.
> + } else {
> + ent.sync.msidata = ++smmu->sync_nr;
> + arm_smmu_cmdq_build_cmd(cmd, &ent);
> + arm_smmu_cmdq_insert_cmd(smmu, cmd);
> + }
> spin_unlock_irqrestore(&smmu->cmdq.lock, flags);
>
> return __arm_smmu_sync_poll_msi(smmu, ent.sync.msidata);
> --
> 1.8.3
>
>
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2018-08-09 12:02 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2018-08-09 11:48 [PATCH v2 0/2] bugfix and optimization about CMD_SYNC Zhen Lei
2018-08-09 11:48 ` [PATCH v2 1/2] iommu/arm-smmu-v3: fix unexpected CMD_SYNC timeout Zhen Lei
2018-08-09 11:48 ` [PATCH v2 2/2] iommu/arm-smmu-v3: avoid redundant CMD_SYNCs if possible Zhen Lei
2018-08-09 12:02 ` Robin Murphy
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).