@@ -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 */
@@ -775,6 +775,17 @@ static int queue_remove_raw(struct arm_smmu_queue *q, u64 *ent)
return 0;
}
+static inline
+void arm_smmu_cmdq_build_sync_msi_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
+{
+ cmd[0] = FIELD_PREP(CMDQ_0_OP, ent->opcode);
+ cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_CS, CMDQ_SYNC_0_CS_IRQ);
+ cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_MSH, ARM_SMMU_SH_ISH);
+ cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_MSIATTR, ARM_SMMU_MEMATTR_OIWB);
+ cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_MSIDATA, ent->sync.msidata);
+ cmd[1] = ent->sync.msiaddr & CMDQ_SYNC_1_MSIADDR_MASK;
+}
+
/* High-level queue accessors */
static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
{
@@ -830,14 +841,9 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
cmd[1] |= FIELD_PREP(CMDQ_PRI_1_RESP, ent->pri.resp);
break;
case CMDQ_OP_CMD_SYNC:
- if (ent->sync.msiaddr)
- cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_CS, CMDQ_SYNC_0_CS_IRQ);
- else
- cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_CS, CMDQ_SYNC_0_CS_SEV);
+ cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_CS, CMDQ_SYNC_0_CS_SEV);
cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_MSH, ARM_SMMU_SH_ISH);
cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_MSIATTR, ARM_SMMU_MEMATTR_OIWB);
- cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_MSIDATA, ent->sync.msidata);
- cmd[1] |= ent->sync.msiaddr & CMDQ_SYNC_1_MSIADDR_MASK;
break;
default:
return -ENOENT;
@@ -947,14 +953,13 @@ 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_sync_msi_cmd(cmd, &ent);
arm_smmu_cmdq_insert_cmd(smmu, cmd);
spin_unlock_irqrestore(&smmu->cmdq.lock, flags);
@@ -2179,7 +2184,6 @@ 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;
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. Split the building of CMD_SYNC for SIG_IRQ mode into a single function, to ensure better performance and good coding style. Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com> --- drivers/iommu/arm-smmu-v3.c | 26 +++++++++++++++----------- 1 file changed, 15 insertions(+), 11 deletions(-) -- 1.8.3