From: Jean-Philippe Brucker <jean-philippe.brucker@arm.com> To: will.deacon@arm.com Cc: mark.rutland@arm.com, devicetree@vger.kernel.org, jacob.jun.pan@linux.intel.com, joro@8bytes.org, linux-kernel@vger.kernel.org, eric.auger@redhat.com, iommu@lists.linux-foundation.org, robh+dt@kernel.org, robin.murphy@arm.com, linux-arm-kernel@lists.infradead.org Subject: [PATCH 5/8] iommu/arm-smmu-v3: Add second level of context descriptor table Date: Mon, 10 Jun 2019 19:47:11 +0100 Message-ID: <20190610184714.6786-6-jean-philippe.brucker@arm.com> (raw) In-Reply-To: <20190610184714.6786-1-jean-philippe.brucker@arm.com> The SMMU can support up to 20 bits of SSID. Add a second level of page tables to accommodate this. Devices that support more than 1024 SSIDs now have a table of 1024 L1 entries (8kB), pointing to tables of 1024 context descriptors (64kB), allocated on demand. Signed-off-by: Jean-Philippe Brucker <jean-philippe.brucker@arm.com> --- drivers/iommu/arm-smmu-v3.c | 136 +++++++++++++++++++++++++++++++++--- 1 file changed, 128 insertions(+), 8 deletions(-) diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index d90eb604b65d..326b71793336 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -216,6 +216,8 @@ #define STRTAB_STE_0_S1FMT GENMASK_ULL(5, 4) #define STRTAB_STE_0_S1FMT_LINEAR 0 +#define STRTAB_STE_0_S1FMT_4K_L2 1 +#define STRTAB_STE_0_S1FMT_64K_L2 2 #define STRTAB_STE_0_S1CTXPTR_MASK GENMASK_ULL(51, 6) #define STRTAB_STE_0_S1CDMAX GENMASK_ULL(63, 59) @@ -255,6 +257,18 @@ #define STRTAB_STE_3_S2TTB_MASK GENMASK_ULL(51, 4) +/* + * Linear: when less than 1024 SSIDs are supported + * 2lvl: at most 1024 L1 entrie, + * 1024 lazy entries per table. + */ +#define CTXDESC_SPLIT 10 +#define CTXDESC_NUM_L2_ENTRIES (1 << CTXDESC_SPLIT) + +#define CTXDESC_L1_DESC_DWORD 1 +#define CTXDESC_L1_DESC_VALID 1 +#define CTXDESC_L1_DESC_L2PTR_MASK GENMASK_ULL(51, 12) + /* Context descriptor (stage-1 only) */ #define CTXDESC_CD_DWORDS 8 #define CTXDESC_CD_0_TCR_T0SZ GENMASK_ULL(5, 0) @@ -530,7 +544,10 @@ struct arm_smmu_ctx_desc { struct arm_smmu_s1_cfg { u8 s1fmt; u8 s1cdmax; - struct arm_smmu_cd_table table; + struct arm_smmu_cd_table *tables; + size_t num_tables; + __le64 *l1ptr; + dma_addr_t l1ptr_dma; /* Context descriptor 0, when substreams are disabled or s1dss = 0b10 */ struct arm_smmu_ctx_desc cd; @@ -1118,12 +1135,51 @@ static void arm_smmu_free_cd_leaf_table(struct arm_smmu_device *smmu, { size_t size = num_entries * (CTXDESC_CD_DWORDS << 3); + if (!table->ptr) + return; dmam_free_coherent(smmu->dev, size, table->ptr, table->ptr_dma); } -static __le64 *arm_smmu_get_cd_ptr(struct arm_smmu_s1_cfg *cfg, u32 ssid) +static void arm_smmu_write_cd_l1_desc(__le64 *dst, + struct arm_smmu_cd_table *table) { - return cfg->table.ptr + ssid * CTXDESC_CD_DWORDS; + u64 val = (table->ptr_dma & CTXDESC_L1_DESC_L2PTR_MASK) | + CTXDESC_L1_DESC_VALID; + + *dst = cpu_to_le64(val); +} + +static __le64 *arm_smmu_get_cd_ptr(struct arm_smmu_domain *smmu_domain, + u32 ssid) +{ + unsigned int idx; + struct arm_smmu_cd_table *table; + struct arm_smmu_device *smmu = smmu_domain->smmu; + struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg; + + if (cfg->s1fmt == STRTAB_STE_0_S1FMT_LINEAR) { + table = &cfg->tables[0]; + idx = ssid; + } else { + idx = ssid >> CTXDESC_SPLIT; + if (idx >= cfg->num_tables) + return NULL; + + table = &cfg->tables[idx]; + if (!table->ptr) { + __le64 *l1ptr = cfg->l1ptr + idx * CTXDESC_L1_DESC_DWORD; + + if (arm_smmu_alloc_cd_leaf_table(smmu, table, + CTXDESC_NUM_L2_ENTRIES)) + return NULL; + + arm_smmu_write_cd_l1_desc(l1ptr, table); + /* An invalid L1 entry is allowed to be cached */ + arm_smmu_sync_cd(smmu_domain, ssid, false); + } + idx = ssid & (CTXDESC_NUM_L2_ENTRIES - 1); + } + return table->ptr + idx * CTXDESC_CD_DWORDS; } static u64 arm_smmu_cpu_tcr_to_cd(u64 tcr) @@ -1149,7 +1205,7 @@ static int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, u64 val; bool cd_live; struct arm_smmu_device *smmu = smmu_domain->smmu; - __le64 *cdptr = arm_smmu_get_cd_ptr(&smmu_domain->s1_cfg, ssid); + __le64 *cdptr = arm_smmu_get_cd_ptr(smmu_domain, ssid); /* * This function handles the following cases: @@ -1213,20 +1269,81 @@ static int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, static int arm_smmu_alloc_cd_tables(struct arm_smmu_domain *smmu_domain, struct arm_smmu_master *master) { + int ret; + size_t size = 0; + size_t max_contexts, num_leaf_entries; struct arm_smmu_device *smmu = smmu_domain->smmu; struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg; cfg->s1fmt = STRTAB_STE_0_S1FMT_LINEAR; cfg->s1cdmax = master->ssid_bits; - return arm_smmu_alloc_cd_leaf_table(smmu, &cfg->table, 1 << cfg->s1cdmax); + + max_contexts = 1 << cfg->s1cdmax; + if (!(smmu->features & ARM_SMMU_FEAT_2_LVL_CDTAB) || + max_contexts <= CTXDESC_NUM_L2_ENTRIES) { + cfg->s1fmt = STRTAB_STE_0_S1FMT_LINEAR; + cfg->num_tables = 1; + num_leaf_entries = max_contexts; + } else { + cfg->s1fmt = STRTAB_STE_0_S1FMT_64K_L2; + /* + * SSID[S1CDmax-1:10] indexes 1st-level table, SSID[9:0] indexes + * 2nd-level + */ + cfg->num_tables = max_contexts / CTXDESC_NUM_L2_ENTRIES; + + size = cfg->num_tables * (CTXDESC_L1_DESC_DWORD << 3); + cfg->l1ptr = dmam_alloc_coherent(smmu->dev, size, + &cfg->l1ptr_dma, + GFP_KERNEL | __GFP_ZERO); + if (!cfg->l1ptr) { + dev_warn(smmu->dev, "failed to allocate L1 context table\n"); + return -ENOMEM; + } + + num_leaf_entries = CTXDESC_NUM_L2_ENTRIES; + } + + cfg->tables = devm_kzalloc(smmu->dev, sizeof(struct arm_smmu_cd_table) * + cfg->num_tables, GFP_KERNEL); + if (!cfg->tables) + return -ENOMEM; + + ret = arm_smmu_alloc_cd_leaf_table(smmu, &cfg->tables[0], num_leaf_entries); + if (ret) + goto err_free_l1; + + if (cfg->l1ptr) + arm_smmu_write_cd_l1_desc(cfg->l1ptr, &cfg->tables[0]); + + return 0; + +err_free_l1: + if (cfg->l1ptr) + dmam_free_coherent(smmu->dev, size, cfg->l1ptr, cfg->l1ptr_dma); + devm_kfree(smmu->dev, cfg->tables); + return ret; } static void arm_smmu_free_cd_tables(struct arm_smmu_domain *smmu_domain) { + int i; struct arm_smmu_device *smmu = smmu_domain->smmu; struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg; + size_t num_leaf_entries = 1 << cfg->s1cdmax; + struct arm_smmu_cd_table *table = cfg->tables; + + if (cfg->l1ptr) { + size_t size = cfg->num_tables * (CTXDESC_L1_DESC_DWORD << 3); - arm_smmu_free_cd_leaf_table(smmu, &cfg->table, 1 << cfg->s1cdmax); + dmam_free_coherent(smmu->dev, size, cfg->l1ptr, + cfg->l1ptr_dma); + num_leaf_entries = CTXDESC_NUM_L2_ENTRIES; + } + + for (i = 0; i < cfg->num_tables; i++, table++) + arm_smmu_free_cd_leaf_table(smmu, table, num_leaf_entries); + devm_kfree(smmu->dev, cfg->tables); } /* Stream table manipulation functions */ @@ -1346,6 +1463,9 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid, } if (s1_cfg) { + dma_addr_t ptr_dma = s1_cfg->l1ptr ? s1_cfg->l1ptr_dma : + s1_cfg->tables[0].ptr_dma; + BUG_ON(ste_live); dst[1] = cpu_to_le64( FIELD_PREP(STRTAB_STE_1_S1DSS, STRTAB_STE_1_S1DSS_SSID0) | @@ -1358,7 +1478,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid, !(smmu->features & ARM_SMMU_FEAT_STALL_FORCE)) dst[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD); - val |= (s1_cfg->table.ptr_dma & STRTAB_STE_0_S1CTXPTR_MASK) | + val |= (ptr_dma & STRTAB_STE_0_S1CTXPTR_MASK) | FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S1_TRANS) | FIELD_PREP(STRTAB_STE_0_S1CDMAX, s1_cfg->s1cdmax) | FIELD_PREP(STRTAB_STE_0_S1FMT, s1_cfg->s1fmt); @@ -1815,7 +1935,7 @@ static void arm_smmu_domain_free(struct iommu_domain *domain) if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) { struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg; - if (cfg->table.ptr) { + if (cfg->tables) { arm_smmu_free_cd_tables(smmu_domain); arm_smmu_bitmap_free(smmu->asid_map, cfg->cd.asid); } -- 2.21.0 _______________________________________________ linux-arm-kernel mailing list linux-arm-kernel@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
next prev parent reply index Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top 2019-06-10 18:47 [PATCH 0/8] iommu: Add auxiliary domain and PASID support to Arm SMMUv3 Jean-Philippe Brucker 2019-06-10 18:47 ` [PATCH 1/8] iommu: Add I/O ASID allocator Jean-Philippe Brucker 2019-06-11 9:36 ` Jonathan Cameron 2019-06-11 14:35 ` Jean-Philippe Brucker 2019-06-11 18:13 ` Jacob Pan 2019-06-18 14:22 ` Jean-Philippe Brucker 2019-06-18 17:05 ` Jacob Pan 2019-06-19 14:26 ` Jean-Philippe Brucker 2019-06-11 12:26 ` Jacob Pan 2019-06-11 14:37 ` Jean-Philippe Brucker 2019-06-11 17:10 ` Jacob Pan 2019-06-12 11:30 ` Jean-Philippe Brucker 2019-06-10 18:47 ` [PATCH 2/8] dt-bindings: document PASID property for IOMMU masters Jean-Philippe Brucker 2019-07-08 7:58 ` Auger Eric 2019-06-10 18:47 ` [PATCH 3/8] iommu/arm-smmu-v3: Support platform SSID Jean-Philippe Brucker 2019-06-11 9:42 ` Jonathan Cameron 2019-06-11 14:35 ` Jean-Philippe Brucker 2019-06-18 18:08 ` Will Deacon 2019-06-19 11:53 ` Jean-Philippe Brucker 2019-07-08 7:58 ` Auger Eric 2019-09-19 14:51 ` Jean-Philippe Brucker 2019-06-10 18:47 ` [PATCH 4/8] iommu/arm-smmu-v3: Add support for Substream IDs Jean-Philippe Brucker 2019-06-11 10:19 ` Jonathan Cameron 2019-06-11 14:35 ` Jean-Philippe Brucker 2019-06-26 18:00 ` Will Deacon 2019-07-04 9:33 ` Jean-Philippe Brucker 2019-09-19 14:57 ` Jean-Philippe Brucker 2019-07-08 15:31 ` Auger Eric 2019-09-19 15:01 ` Jean-Philippe Brucker 2019-06-10 18:47 ` Jean-Philippe Brucker [this message] 2019-06-11 10:24 ` [PATCH 5/8] iommu/arm-smmu-v3: Add second level of context descriptor table Jonathan Cameron 2019-07-08 15:13 ` Auger Eric 2019-06-10 18:47 ` [PATCH 6/8] iommu/arm-smmu-v3: Support auxiliary domains Jean-Philippe Brucker 2019-06-26 17:59 ` Will Deacon 2019-07-05 16:29 ` Jean-Philippe Brucker 2019-09-19 15:06 ` Jean-Philippe Brucker 2019-06-10 18:47 ` [PATCH 7/8] iommu/arm-smmu-v3: Improve add_device() error handling Jean-Philippe Brucker 2019-07-08 7:58 ` Auger Eric 2019-06-10 18:47 ` [PATCH 8/8] iommu/arm-smmu-v3: Add support for PCI PASID Jean-Philippe Brucker 2019-06-11 10:45 ` Jonathan Cameron 2019-06-11 14:35 ` Jean-Philippe Brucker 2019-07-08 7:58 ` Auger Eric 2019-09-19 15:10 ` Jean-Philippe Brucker
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20190610184714.6786-6-jean-philippe.brucker@arm.com \ --to=jean-philippe.brucker@arm.com \ --cc=devicetree@vger.kernel.org \ --cc=eric.auger@redhat.com \ --cc=iommu@lists.linux-foundation.org \ --cc=jacob.jun.pan@linux.intel.com \ --cc=joro@8bytes.org \ --cc=linux-arm-kernel@lists.infradead.org \ --cc=linux-kernel@vger.kernel.org \ --cc=mark.rutland@arm.com \ --cc=robh+dt@kernel.org \ --cc=robin.murphy@arm.com \ --cc=will.deacon@arm.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: link
Linux-ARM-Kernel Archive on lore.kernel.org Archives are clonable: git clone --mirror https://lore.kernel.org/linux-arm-kernel/0 linux-arm-kernel/git/0.git git clone --mirror https://lore.kernel.org/linux-arm-kernel/1 linux-arm-kernel/git/1.git # If you have public-inbox 1.1+ installed, you may # initialize and index your mirror using the following commands: public-inbox-init -V2 linux-arm-kernel linux-arm-kernel/ https://lore.kernel.org/linux-arm-kernel \ linux-arm-kernel@lists.infradead.org public-inbox-index linux-arm-kernel Example config snippet for mirrors Newsgroup available over NNTP: nntp://nntp.lore.kernel.org/org.infradead.lists.linux-arm-kernel AGPL code for this site: git clone https://public-inbox.org/public-inbox.git