提交 afb27ac8 编写于 作者: Z Zhen Lei 提交者: Caspar Zhang

iommu/arm-smmu-v3: Fix unexpected CMD_SYNC timeout

commit 0f02477d16980938a84aba8688a4e3a303306116 upstream

The condition break condition of:

	(int)(VAL - sync_idx) >= 0

in the __arm_smmu_sync_poll_msi() polling loop requires that sync_idx
must be increased monotonically according to the sequence of the CMDs in
the cmdq.

However, since the msidata is populated using atomic_inc_return_relaxed()
before taking the command-queue spinlock, then the following scenario
can occur:

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, since the caller will eventually either
timeout or exit due to another CMD_SYNC, however it's clearly not what
the code is supposed to be doing. Fix it, by incrementing the sequence
count with the command-queue lock held, allowing us to drop the atomic
operations altogether.
Signed-off-by: NZhen Lei <thunder.leizhen@huawei.com>
[will: dropped the specialised cmd building routine for now]
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NZou Cao <zoucao@linux.alibaba.com>
Reviewed-by: NBaoyou Xie <xie.baoyou@linux.alibaba.com>
上级 4fed8b77
...@@ -567,7 +567,7 @@ struct arm_smmu_device { ...@@ -567,7 +567,7 @@ struct arm_smmu_device {
int gerr_irq; int gerr_irq;
int combined_irq; int combined_irq;
atomic_t sync_nr; u32 sync_nr;
unsigned long ias; /* IPA */ unsigned long ias; /* IPA */
unsigned long oas; /* PA */ unsigned long oas; /* PA */
...@@ -964,14 +964,13 @@ static int __arm_smmu_cmdq_issue_sync_msi(struct arm_smmu_device *smmu) ...@@ -964,14 +964,13 @@ static int __arm_smmu_cmdq_issue_sync_msi(struct arm_smmu_device *smmu)
struct arm_smmu_cmdq_ent ent = { struct arm_smmu_cmdq_ent ent = {
.opcode = CMDQ_OP_CMD_SYNC, .opcode = CMDQ_OP_CMD_SYNC,
.sync = { .sync = {
.msidata = atomic_inc_return_relaxed(&smmu->sync_nr),
.msiaddr = virt_to_phys(&smmu->sync_count), .msiaddr = virt_to_phys(&smmu->sync_count),
}, },
}; };
arm_smmu_cmdq_build_cmd(cmd, &ent);
spin_lock_irqsave(&smmu->cmdq.lock, flags); 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); arm_smmu_cmdq_insert_cmd(smmu, cmd);
spin_unlock_irqrestore(&smmu->cmdq.lock, flags); spin_unlock_irqrestore(&smmu->cmdq.lock, flags);
...@@ -2196,7 +2195,6 @@ static int arm_smmu_init_structures(struct arm_smmu_device *smmu) ...@@ -2196,7 +2195,6 @@ static int arm_smmu_init_structures(struct arm_smmu_device *smmu)
{ {
int ret; int ret;
atomic_set(&smmu->sync_nr, 0);
ret = arm_smmu_init_queues(smmu); ret = arm_smmu_init_queues(smmu);
if (ret) if (ret)
return ret; return ret;
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册