linux-kernel - [PATCH v4 4/6] iommu/arm-smmu-qcom: Add stall support

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20210601224750.513996-6-robdclark@gmail.com>
Date:   Tue,  1 Jun 2021 15:47:23 -0700
From:   Rob Clark <robdclark@...il.com>
To:     dri-devel@...ts.freedesktop.org
Cc:     Jordan Crouse <jordan@...micpenguin.net>,
        Rob Clark <robdclark@...omium.org>,
        Will Deacon <will@...nel.org>,
        Robin Murphy <robin.murphy@....com>,
        Joerg Roedel <joro@...tes.org>,
        Bjorn Andersson <bjorn.andersson@...aro.org>,
        "Isaac J. Manjarres" <isaacm@...eaurora.org>,
        Sai Prakash Ranjan <saiprakash.ranjan@...eaurora.org>,
        linux-arm-kernel@...ts.infradead.org (moderated list:ARM SMMU DRIVERS),
        iommu@...ts.linux-foundation.org (open list:IOMMU DRIVERS),
        linux-kernel@...r.kernel.org (open list)
Subject: [PATCH v4 4/6] iommu/arm-smmu-qcom: Add stall support

From: Rob Clark <robdclark@...omium.org>

Add, via the adreno-smmu-priv interface, a way for the GPU to request
the SMMU to stall translation on faults, and then later resume the
translation, either retrying or terminating the current translation.

This will be used on the GPU side to "freeze" the GPU while we snapshot
useful state for devcoredump.

Signed-off-by: Rob Clark <robdclark@...omium.org>
---
 drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c | 33 ++++++++++++++++++++++
 include/linux/adreno-smmu-priv.h           |  7 +++++
 2 files changed, 40 insertions(+)

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index b2e31ea84128..61fc645c1325 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -13,6 +13,7 @@ struct qcom_smmu {
 	struct arm_smmu_device smmu;
 	bool bypass_quirk;
 	u8 bypass_cbndx;
+	u32 stall_enabled;
 };
 
 static struct qcom_smmu *to_qcom_smmu(struct arm_smmu_device *smmu)
@@ -23,12 +24,17 @@ static struct qcom_smmu *to_qcom_smmu(struct arm_smmu_device *smmu)
 static void qcom_adreno_smmu_write_sctlr(struct arm_smmu_device *smmu, int idx,
 		u32 reg)
 {
+	struct qcom_smmu *qsmmu = to_qcom_smmu(smmu);
+
 	/*
 	 * On the GPU device we want to process subsequent transactions after a
 	 * fault to keep the GPU from hanging
 	 */
 	reg |= ARM_SMMU_SCTLR_HUPCF;
 
+	if (qsmmu->stall_enabled & BIT(idx))
+		reg |= ARM_SMMU_SCTLR_CFCFG;
+
 	arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_SCTLR, reg);
 }
 
@@ -48,6 +54,31 @@ static void qcom_adreno_smmu_get_fault_info(const void *cookie,
 	info->contextidr = arm_smmu_cb_read(smmu, cfg->cbndx, ARM_SMMU_CB_CONTEXTIDR);
 }
 
+static void qcom_adreno_smmu_set_stall(const void *cookie, bool enabled)
+{
+	struct arm_smmu_domain *smmu_domain = (void *)cookie;
+	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
+	struct qcom_smmu *qsmmu = to_qcom_smmu(smmu_domain->smmu);
+
+	if (enabled)
+		qsmmu->stall_enabled |= BIT(cfg->cbndx);
+	else
+		qsmmu->stall_enabled &= ~BIT(cfg->cbndx);
+}
+
+static void qcom_adreno_smmu_resume_translation(const void *cookie, bool terminate)
+{
+	struct arm_smmu_domain *smmu_domain = (void *)cookie;
+	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	u32 reg = 0;
+
+	if (terminate)
+		reg |= ARM_SMMU_RESUME_TERMINATE;
+
+	arm_smmu_cb_write(smmu, cfg->cbndx, ARM_SMMU_CB_RESUME, reg);
+}
+
 #define QCOM_ADRENO_SMMU_GPU_SID 0
 
 static bool qcom_adreno_smmu_is_gpu_device(struct device *dev)
@@ -173,6 +204,8 @@ static int qcom_adreno_smmu_init_context(struct arm_smmu_domain *smmu_domain,
 	priv->get_ttbr1_cfg = qcom_adreno_smmu_get_ttbr1_cfg;
 	priv->set_ttbr0_cfg = qcom_adreno_smmu_set_ttbr0_cfg;
 	priv->get_fault_info = qcom_adreno_smmu_get_fault_info;
+	priv->set_stall = qcom_adreno_smmu_set_stall;
+	priv->resume_translation = qcom_adreno_smmu_resume_translation;
 
 	return 0;
 }
diff --git a/include/linux/adreno-smmu-priv.h b/include/linux/adreno-smmu-priv.h
index 53fe32fb9214..c637e0997f6d 100644
--- a/include/linux/adreno-smmu-priv.h
+++ b/include/linux/adreno-smmu-priv.h
@@ -45,6 +45,11 @@ struct adreno_smmu_fault_info {
  *                 TTBR0 translation is enabled with the specified cfg
  * @get_fault_info: Called by the GPU fault handler to get information about
  *                  the fault
+ * @set_stall:     Configure whether stall on fault (CFCFG) is enabled.  Call
+ *                 before set_ttbr0_cfg().  If stalling on fault is enabled,
+ *                 the GPU driver must call resume_translation()
+ * @resume_translation: Resume translation after a fault
+ *
  *
  * The GPU driver (drm/msm) and adreno-smmu work together for controlling
  * the GPU's SMMU instance.  This is by necessity, as the GPU is directly
@@ -60,6 +65,8 @@ struct adreno_smmu_priv {
     const struct io_pgtable_cfg *(*get_ttbr1_cfg)(const void *cookie);
     int (*set_ttbr0_cfg)(const void *cookie, const struct io_pgtable_cfg *cfg);
     void (*get_fault_info)(const void *cookie, struct adreno_smmu_fault_info *info);
+    void (*set_stall)(const void *cookie, bool enabled);
+    void (*resume_translation)(const void *cookie, bool terminate);
 };
 
 #endif /* __ADRENO_SMMU_PRIV_H */
-- 
2.31.1