Received-SPF: pass (google.com: domain of linux-kernel+bounces-736-linux.lists.archive=gmail.com@vger.kernel.org designates 139.178.88.99 as permitted sender) client-ip=139.178.88.99;
From: Bibek Kumar Patro <quic_bibekkum@quicinc.com>
To: <will@kernel.org>, <robin.murphy@arm.com>, <joro@8bytes.org>,
        <dmitry.baryshkov@linaro.org>, <konrad.dybcio@linaro.org>,
        <jsnitsel@redhat.com>, <quic_bjorande@quicinc.com>, <mani@kernel.org>,
        <quic_eberman@quicinc.com>, <robdclark@chromium.org>,
        <u.kleine-koenig@pengutronix.de>, <robh@kernel.org>,
        <vladimir.oltean@nxp.com>, <quic_pkondeti@quicinc.com>,
        <quic_molvera@quicinc.com>
CC: <linux-arm-msm@vger.kernel.org>, <linux-arm-kernel@lists.infradead.org>,
        <iommu@lists.linux.dev>, <linux-kernel@vger.kernel.org>,
        <qipl.kernel.upstream@quicinc.com>,
        Bibek Kumar Patro
	<quic_bibekkum@quicinc.com>
Subject: [PATCH v4 2/5] iommu/arm-smmu: introduction of ACTLR for custom prefetcher settings
Date: Fri, 15 Dec 2023 15:48:24 +0530
Message-ID: <20231215101827.30549-3-quic_bibekkum@quicinc.com>
In-Reply-To: <20231215101827.30549-1-quic_bibekkum@quicinc.com>
References: <20231215101827.30549-1-quic_bibekkum@quicinc.com>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain

Currently in Qualcomm  SoCs the default prefetch is set to 1 which allows
the TLB to fetch just the next page table. MMU-500 features ACTLR
register which is implementation defined and is used for Qualcomm SoCs
to have a custom prefetch setting enabling TLB to prefetch the next set
of page tables accordingly allowing for faster translations.

ACTLR value is unique for each SMR (Stream matching register) and stored
in a pre-populated table. This value is set to the register during
context bank initialisation.

Signed-off-by: Bibek Kumar Patro <quic_bibekkum@quicinc.com>
---
 drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c | 45 ++++++++++++++++++++++
 drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h |  4 ++
 drivers/iommu/arm/arm-smmu/arm-smmu.c      |  5 ++-
 drivers/iommu/arm/arm-smmu/arm-smmu.h      |  5 +++
 4 files changed, 57 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index 8a7c16a86694..cb49291f5233 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -14,6 +14,12 @@

 #define QCOM_DUMMY_VAL	-1

+struct actlr_config {
+	u16 sid;
+	u16 mask;
+	u32 actlr;
+};
+
 static struct qcom_smmu *to_qcom_smmu(struct arm_smmu_device *smmu)
 {
 	return container_of(smmu, struct qcom_smmu, smmu);
@@ -205,9 +211,38 @@ static bool qcom_adreno_can_do_ttbr1(struct arm_smmu_device *smmu)
 	return true;
 }

+static void qcom_smmu_set_actlr(struct device *dev, struct arm_smmu_device *smmu, int cbndx,
+		const struct actlr_config *actlrcfg)
+{
+	struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev);
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct arm_smmu_smr *smr;
+	u16 mask;
+	int idx;
+	u16 id;
+	int i;
+
+	for (; actlrcfg->sid || actlrcfg->mask || actlrcfg->actlr; actlrcfg++) {
+		id = actlrcfg->sid;
+		mask = actlrcfg->mask;
+
+		for_each_cfg_sme(cfg, fwspec, i, idx) {
+			smr = &smmu->smrs[idx];
+			if (smr_is_subset(smr, id, mask)) {
+				arm_smmu_cb_write(smmu, cbndx, ARM_SMMU_CB_ACTLR,
+						actlrcfg->actlr);
+				break;
+			}
+		}
+	}
+}
+
 static int qcom_adreno_smmu_init_context(struct arm_smmu_domain *smmu_domain,
 		struct io_pgtable_cfg *pgtbl_cfg, struct device *dev)
 {
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct qcom_smmu *qsmmu = to_qcom_smmu(smmu);
+	int cbndx = smmu_domain->cfg.cbndx;
 	struct adreno_smmu_priv *priv;

 	smmu_domain->cfg.flush_walk_prefer_tlbiasid = true;
@@ -238,6 +273,9 @@ static int qcom_adreno_smmu_init_context(struct arm_smmu_domain *smmu_domain,
 	priv->set_stall = qcom_adreno_smmu_set_stall;
 	priv->resume_translation = qcom_adreno_smmu_resume_translation;

+	if (qsmmu->data->actlrcfg_gfx)
+		qcom_smmu_set_actlr(dev, smmu, cbndx, qsmmu->data->actlrcfg_gfx);
+
 	return 0;
 }

@@ -264,6 +302,13 @@ static const struct of_device_id qcom_smmu_client_of_match[] __maybe_unused = {
 static int qcom_smmu_init_context(struct arm_smmu_domain *smmu_domain,
 		struct io_pgtable_cfg *pgtbl_cfg, struct device *dev)
 {
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct qcom_smmu *qsmmu = to_qcom_smmu(smmu);
+	int cbndx = smmu_domain->cfg.cbndx;
+
+	if (qsmmu->data->actlrcfg)
+		qcom_smmu_set_actlr(dev, smmu, cbndx, qsmmu->data->actlrcfg);
+
 	smmu_domain->cfg.flush_walk_prefer_tlbiasid = true;

 	return 0;
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h
index f3b91963e234..448a66b5332f 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h
@@ -24,7 +24,11 @@ struct qcom_smmu_config {
 	const u32 *reg_offset;
 };

+struct actlr_config;
+
 struct qcom_smmu_match_data {
+	const struct actlr_config *actlrcfg;
+	const struct actlr_config *actlrcfg_gfx;
 	const struct qcom_smmu_config *cfg;
 	const struct arm_smmu_impl *impl;
 	const struct arm_smmu_impl *adreno_impl;
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index d6d1a2a55cc0..0c7f700b27dd 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -990,9 +990,10 @@ static int arm_smmu_find_sme(struct arm_smmu_device *smmu, u16 id, u16 mask)
 		 * expect simply identical entries for this case, but there's
 		 * no harm in accommodating the generalisation.
 		 */
-		if ((mask & smrs[i].mask) == mask &&
-		    !((id ^ smrs[i].id) & ~smrs[i].mask))
+
+		if (smr_is_subset(&smrs[i], id, mask))
 			return i;
+
 		/*
 		 * If the new entry has any other overlap with an existing one,
 		 * though, then there always exists at least one stream ID
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.h b/drivers/iommu/arm/arm-smmu/arm-smmu.h
index 703fd5817ec1..2e4f65412c6b 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.h
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.h
@@ -501,6 +501,11 @@ static inline void arm_smmu_writeq(struct arm_smmu_device *smmu, int page,
 		writeq_relaxed(val, arm_smmu_page(smmu, page) + offset);
 }

+static inline bool smr_is_subset(struct arm_smmu_smr *smrs, u16 id, u16 mask)
+{
+	return (mask & smrs->mask) == mask && !((id ^ smrs->id) & ~smrs->mask);
+}
+
 #define ARM_SMMU_GR0		0
 #define ARM_SMMU_GR1		1
 #define ARM_SMMU_CB(s, n)	((s)->numpage + (n))
--
2.17.1