From 7aaf0b0e8e9add1688b13588351bb7e8acfeeab4 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 28 Jul 2020 19:08:59 +0200 Subject: iommu/qcom: Drop of_match_ptr to fix -Wunused-const-variable The of_device_id is included unconditionally by of.h header and used in the driver as well. Remove of_match_ptr to fix W=1 compile test warning with !CONFIG_OF: drivers/iommu/qcom_iommu.c:910:34: warning: 'qcom_iommu_of_match' defined but not used [-Wunused-const-variable=] 910 | static const struct of_device_id qcom_iommu_of_match[] = { Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20200728170859.28143-3-krzk@kernel.org Signed-off-by: Joerg Roedel --- drivers/iommu/arm/arm-smmu/qcom_iommu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/iommu/arm') diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c index af6bec3ace00..9535a6af7553 100644 --- a/drivers/iommu/arm/arm-smmu/qcom_iommu.c +++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c @@ -752,7 +752,7 @@ static const struct of_device_id ctx_of_match[] = { static struct platform_driver qcom_iommu_ctx_driver = { .driver = { .name = "qcom-iommu-ctx", - .of_match_table = of_match_ptr(ctx_of_match), + .of_match_table = ctx_of_match, }, .probe = qcom_iommu_ctx_probe, .remove = qcom_iommu_ctx_remove, @@ -915,7 +915,7 @@ static const struct of_device_id qcom_iommu_of_match[] = { static struct platform_driver qcom_iommu_driver = { .driver = { .name = "qcom-iommu", - .of_match_table = of_match_ptr(qcom_iommu_of_match), + .of_match_table = qcom_iommu_of_match, .pm = &qcom_iommu_pm_ops, }, .probe = qcom_iommu_device_probe, -- cgit v1.2.3 From dc898eb84b25c39ea46f28c48a169bdbd0e2c7e0 Mon Sep 17 00:00:00 2001 From: Zenghui Yu Date: Wed, 26 Aug 2020 22:17:58 +0800 Subject: iommu/arm-smmu-v3: Fix l1 stream table size in the error message The actual size of level-1 stream table is l1size. This looks like an oversight on commit d2e88e7c081ef ("iommu/arm-smmu: Fix LOG2SIZE setting for 2-level stream tables") which forgot to update the @size in error message as well. As memory allocation failure is already bad enough, nothing worse would happen. But let's be careful. Signed-off-by: Zenghui Yu Link: https://lore.kernel.org/r/20200826141758.341-1-yuzenghui@huawei.com Signed-off-by: Will Deacon --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/iommu/arm') diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index c192544e874b..bb458d0c7b73 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -3280,7 +3280,7 @@ static int arm_smmu_init_strtab_2lvl(struct arm_smmu_device *smmu) if (!strtab) { dev_err(smmu->dev, "failed to allocate l1 stream table (%u bytes)\n", - size); + l1size); return -ENOMEM; } cfg->strtab = strtab; -- cgit v1.2.3 From fea9ae18cf77a79cb32046d7785d000a00a226cd Mon Sep 17 00:00:00 2001 From: Barry Song Date: Thu, 27 Aug 2020 21:29:55 +1200 Subject: iommu/arm-smmu-v3: replace symbolic permissions by octal permissions for module parameter This fixed the below checkpatch issue: WARNING: Symbolic permissions 'S_IRUGO' are not preferred. Consider using octal permissions '0444'. 417: FILE: drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c:417: module_param_named(disable_bypass, disable_bypass, bool, S_IRUGO); Signed-off-by: Barry Song Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/20200827092957.22500-2-song.bao.hua@hisilicon.com Signed-off-by: Will Deacon --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/iommu/arm') diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index bb458d0c7b73..637de7e6f26e 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -414,7 +414,7 @@ #define MSI_IOVA_LENGTH 0x100000 static bool disable_bypass = 1; -module_param_named(disable_bypass, disable_bypass, bool, S_IRUGO); +module_param_named(disable_bypass, disable_bypass, bool, 0444); MODULE_PARM_DESC(disable_bypass, "Disable bypass streams such that incoming transactions from devices that are not attached to an iommu domain will report an abort back to the device and will not be allowed to pass through the SMMU."); -- cgit v1.2.3 From 9305d02adcc14adc0f4e7d5ad0c370174923e6dc Mon Sep 17 00:00:00 2001 From: Barry Song Date: Thu, 27 Aug 2020 21:29:56 +1200 Subject: iommu/arm-smmu-v3: replace module_param_named by module_param for disable_bypass Just use module_param() - going out of the way to specify a "different" name that's identical to the variable name is silly. Signed-off-by: Barry Song Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/20200827092957.22500-3-song.bao.hua@hisilicon.com Signed-off-by: Will Deacon --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/iommu/arm') diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index 637de7e6f26e..c9805ab296c4 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -414,7 +414,7 @@ #define MSI_IOVA_LENGTH 0x100000 static bool disable_bypass = 1; -module_param_named(disable_bypass, disable_bypass, bool, 0444); +module_param(disable_bypass, bool, 0444); MODULE_PARM_DESC(disable_bypass, "Disable bypass streams such that incoming transactions from devices that are not attached to an iommu domain will report an abort back to the device and will not be allowed to pass through the SMMU."); -- cgit v1.2.3 From bd07a20a38b6598dc09f5543eb03710e807cb429 Mon Sep 17 00:00:00 2001 From: Barry Song Date: Thu, 27 Aug 2020 21:29:57 +1200 Subject: iommu/arm-smmu-v3: permit users to disable msi polling Polling by MSI isn't necessarily faster than polling by SEV. Tests on hi1620 show hns3 100G NIC network throughput can improve from 25G to 27G if we disable MSI polling while running 16 netperf threads sending UDP packets in size 32KB. TX throughput can improve from 7G to 7.7G for single thread. The reason for the throughput improvement is that the latency to poll the completion of CMD_SYNC becomes smaller. After sending a CMD_SYNC in an empty cmd queue, typically we need to wait for 280ns using MSI polling. But we only need around 190ns after disabling MSI polling. This patch provides a command line option so that users can decide to use MSI polling or not based on their tests. Signed-off-by: Barry Song Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/20200827092957.22500-4-song.bao.hua@hisilicon.com Signed-off-by: Will Deacon --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) (limited to 'drivers/iommu/arm') diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index c9805ab296c4..ebb3885e9035 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -418,6 +418,11 @@ module_param(disable_bypass, bool, 0444); MODULE_PARM_DESC(disable_bypass, "Disable bypass streams such that incoming transactions from devices that are not attached to an iommu domain will report an abort back to the device and will not be allowed to pass through the SMMU."); +static bool disable_msipolling; +module_param(disable_msipolling, bool, 0444); +MODULE_PARM_DESC(disable_msipolling, + "Disable MSI-based polling for CMD_SYNC completion."); + enum pri_resp { PRI_RESP_DENY = 0, PRI_RESP_FAIL = 1, @@ -652,6 +657,7 @@ struct arm_smmu_device { #define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0) #define ARM_SMMU_OPT_PAGE0_REGS_ONLY (1 << 1) +#define ARM_SMMU_OPT_MSIPOLL (1 << 2) u32 options; struct arm_smmu_cmdq cmdq; @@ -992,8 +998,7 @@ static void arm_smmu_cmdq_build_sync_cmd(u64 *cmd, struct arm_smmu_device *smmu, * Beware that Hi16xx adds an extra 32 bits of goodness to its MSI * payload, so the write will zero the entire command on that platform. */ - if (smmu->features & ARM_SMMU_FEAT_MSI && - smmu->features & ARM_SMMU_FEAT_COHERENCY) { + if (smmu->options & ARM_SMMU_OPT_MSIPOLL) { ent.sync.msiaddr = q->base_dma + Q_IDX(&q->llq, prod) * q->ent_dwords * 8; } @@ -1331,8 +1336,7 @@ static int __arm_smmu_cmdq_poll_until_consumed(struct arm_smmu_device *smmu, static int arm_smmu_cmdq_poll_until_sync(struct arm_smmu_device *smmu, struct arm_smmu_ll_queue *llq) { - if (smmu->features & ARM_SMMU_FEAT_MSI && - smmu->features & ARM_SMMU_FEAT_COHERENCY) + if (smmu->options & ARM_SMMU_OPT_MSIPOLL) return __arm_smmu_cmdq_poll_until_msi(smmu, llq); return __arm_smmu_cmdq_poll_until_consumed(smmu, llq); @@ -3740,8 +3744,11 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) if (reg & IDR0_SEV) smmu->features |= ARM_SMMU_FEAT_SEV; - if (reg & IDR0_MSI) + if (reg & IDR0_MSI) { smmu->features |= ARM_SMMU_FEAT_MSI; + if (coherent && !disable_msipolling) + smmu->options |= ARM_SMMU_OPT_MSIPOLL; + } if (reg & IDR0_HYP) smmu->features |= ARM_SMMU_FEAT_HYP; -- cgit v1.2.3 From 376cdf66f62444a1b4ebb393bab9fc44966f9b49 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Fri, 18 Sep 2020 16:18:57 +0200 Subject: iommu/arm-smmu-v3: Fix endianness annotations When building with C=1, sparse reports some issues regarding endianness annotations: arm-smmu-v3.c:221:26: warning: cast to restricted __le64 arm-smmu-v3.c:221:24: warning: incorrect type in assignment (different base types) arm-smmu-v3.c:221:24: expected restricted __le64 [usertype] arm-smmu-v3.c:221:24: got unsigned long long [usertype] arm-smmu-v3.c:229:20: warning: incorrect type in argument 1 (different base types) arm-smmu-v3.c:229:20: expected restricted __le64 [usertype] *[assigned] dst arm-smmu-v3.c:229:20: got unsigned long long [usertype] *ent arm-smmu-v3.c:229:25: warning: incorrect type in argument 2 (different base types) arm-smmu-v3.c:229:25: expected unsigned long long [usertype] *[assigned] src arm-smmu-v3.c:229:25: got restricted __le64 [usertype] * arm-smmu-v3.c:396:20: warning: incorrect type in argument 1 (different base types) arm-smmu-v3.c:396:20: expected restricted __le64 [usertype] *[assigned] dst arm-smmu-v3.c:396:20: got unsigned long long * arm-smmu-v3.c:396:25: warning: incorrect type in argument 2 (different base types) arm-smmu-v3.c:396:25: expected unsigned long long [usertype] *[assigned] src arm-smmu-v3.c:396:25: got restricted __le64 [usertype] * arm-smmu-v3.c:1349:32: warning: invalid assignment: |= arm-smmu-v3.c:1349:32: left side has type restricted __le64 arm-smmu-v3.c:1349:32: right side has type unsigned long arm-smmu-v3.c:1396:53: warning: incorrect type in argument 3 (different base types) arm-smmu-v3.c:1396:53: expected restricted __le64 [usertype] *dst arm-smmu-v3.c:1396:53: got unsigned long long [usertype] *strtab arm-smmu-v3.c:1424:39: warning: incorrect type in argument 1 (different base types) arm-smmu-v3.c:1424:39: expected unsigned long long [usertype] *[assigned] strtab arm-smmu-v3.c:1424:39: got restricted __le64 [usertype] *l2ptr While harmless, they are incorrect and could hide actual errors during development. Fix them. Signed-off-by: Jean-Philippe Brucker Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/20200918141856.629722-1-jean-philippe@linaro.org Signed-off-by: Will Deacon --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/iommu/arm') diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index ebb3885e9035..3063aeb38063 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -873,7 +873,7 @@ static void queue_write(__le64 *dst, u64 *src, size_t n_dwords) *dst++ = cpu_to_le64(*src++); } -static void queue_read(__le64 *dst, u64 *src, size_t n_dwords) +static void queue_read(u64 *dst, __le64 *src, size_t n_dwords) { int i; @@ -1943,7 +1943,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid, arm_smmu_cmdq_issue_cmd(smmu, &prefetch_cmd); } -static void arm_smmu_init_bypass_stes(u64 *strtab, unsigned int nent) +static void arm_smmu_init_bypass_stes(__le64 *strtab, unsigned int nent) { unsigned int i; -- cgit v1.2.3 From dd147a89f37d5ad32fe601eb11967326312da71a Mon Sep 17 00:00:00 2001 From: Jordan Crouse Date: Sat, 5 Sep 2020 13:04:18 -0700 Subject: iommu/arm-smmu: Pass io-pgtable config to implementation specific function Construct the io-pgtable config before calling the implementation specific init_context function and pass it so the implementation specific function can get a chance to change it before the io-pgtable is created. Signed-off-by: Jordan Crouse Signed-off-by: Rob Clark Reviewed-by: Bjorn Andersson Signed-off-by: Will Deacon --- drivers/iommu/arm/arm-smmu/arm-smmu-impl.c | 3 ++- drivers/iommu/arm/arm-smmu/arm-smmu.c | 11 ++++++----- drivers/iommu/arm/arm-smmu/arm-smmu.h | 3 ++- 3 files changed, 10 insertions(+), 7 deletions(-) (limited to 'drivers/iommu/arm') diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c index f4ff124a1967..a9861dcd0884 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c @@ -68,7 +68,8 @@ static int cavium_cfg_probe(struct arm_smmu_device *smmu) return 0; } -static int cavium_init_context(struct arm_smmu_domain *smmu_domain) +static int cavium_init_context(struct arm_smmu_domain *smmu_domain, + struct io_pgtable_cfg *pgtbl_cfg) { struct cavium_smmu *cs = container_of(smmu_domain->smmu, struct cavium_smmu, smmu); diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c index 09c42af9f31e..37d8d49299b4 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c @@ -795,11 +795,6 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain, cfg->asid = cfg->cbndx; smmu_domain->smmu = smmu; - if (smmu->impl && smmu->impl->init_context) { - ret = smmu->impl->init_context(smmu_domain); - if (ret) - goto out_unlock; - } pgtbl_cfg = (struct io_pgtable_cfg) { .pgsize_bitmap = smmu->pgsize_bitmap, @@ -810,6 +805,12 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain, .iommu_dev = smmu->dev, }; + if (smmu->impl && smmu->impl->init_context) { + ret = smmu->impl->init_context(smmu_domain, &pgtbl_cfg); + if (ret) + goto out_clear_smmu; + } + if (smmu_domain->non_strict) pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_NON_STRICT; diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.h b/drivers/iommu/arm/arm-smmu/arm-smmu.h index d890a4a968e8..83294516ac08 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.h +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.h @@ -386,7 +386,8 @@ struct arm_smmu_impl { u64 val); int (*cfg_probe)(struct arm_smmu_device *smmu); int (*reset)(struct arm_smmu_device *smmu); - int (*init_context)(struct arm_smmu_domain *smmu_domain); + int (*init_context)(struct arm_smmu_domain *smmu_domain, + struct io_pgtable_cfg *cfg); void (*tlb_sync)(struct arm_smmu_device *smmu, int page, int sync, int status); int (*def_domain_type)(struct device *dev); -- cgit v1.2.3 From 67f1a7a314a2c29832ae604f839653408492ee5d Mon Sep 17 00:00:00 2001 From: Jordan Crouse Date: Sat, 5 Sep 2020 13:04:19 -0700 Subject: iommu/arm-smmu: Add support for split pagetables Enable TTBR1 for a context bank if IO_PGTABLE_QUIRK_ARM_TTBR1 is selected by the io-pgtable configuration. Signed-off-by: Jordan Crouse Signed-off-by: Rob Clark Reviewed-by: Bjorn Andersson Signed-off-by: Will Deacon --- drivers/iommu/arm/arm-smmu/arm-smmu.c | 19 +++++++++++++++---- drivers/iommu/arm/arm-smmu/arm-smmu.h | 25 +++++++++++++++++++------ 2 files changed, 34 insertions(+), 10 deletions(-) (limited to 'drivers/iommu/arm') diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c index 37d8d49299b4..8e884e58f208 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c @@ -552,11 +552,15 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain, cb->ttbr[0] = pgtbl_cfg->arm_v7s_cfg.ttbr; cb->ttbr[1] = 0; } else { - cb->ttbr[0] = pgtbl_cfg->arm_lpae_s1_cfg.ttbr; - cb->ttbr[0] |= FIELD_PREP(ARM_SMMU_TTBRn_ASID, - cfg->asid); + cb->ttbr[0] = FIELD_PREP(ARM_SMMU_TTBRn_ASID, + cfg->asid); cb->ttbr[1] = FIELD_PREP(ARM_SMMU_TTBRn_ASID, cfg->asid); + + if (pgtbl_cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1) + cb->ttbr[1] |= pgtbl_cfg->arm_lpae_s1_cfg.ttbr; + else + cb->ttbr[0] |= pgtbl_cfg->arm_lpae_s1_cfg.ttbr; } } else { cb->ttbr[0] = pgtbl_cfg->arm_lpae_s2_cfg.vttbr; @@ -822,7 +826,14 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain, /* Update the domain's page sizes to reflect the page table format */ domain->pgsize_bitmap = pgtbl_cfg.pgsize_bitmap; - domain->geometry.aperture_end = (1UL << ias) - 1; + + if (pgtbl_cfg.quirks & IO_PGTABLE_QUIRK_ARM_TTBR1) { + domain->geometry.aperture_start = ~0UL << ias; + domain->geometry.aperture_end = ~0UL; + } else { + domain->geometry.aperture_end = (1UL << ias) - 1; + } + domain->geometry.force_aperture = true; /* Initialise the context bank with our page table cfg */ diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.h b/drivers/iommu/arm/arm-smmu/arm-smmu.h index 83294516ac08..f3e456893f28 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.h +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.h @@ -169,10 +169,12 @@ enum arm_smmu_cbar_type { #define ARM_SMMU_CB_TCR 0x30 #define ARM_SMMU_TCR_EAE BIT(31) #define ARM_SMMU_TCR_EPD1 BIT(23) +#define ARM_SMMU_TCR_A1 BIT(22) #define ARM_SMMU_TCR_TG0 GENMASK(15, 14) #define ARM_SMMU_TCR_SH0 GENMASK(13, 12) #define ARM_SMMU_TCR_ORGN0 GENMASK(11, 10) #define ARM_SMMU_TCR_IRGN0 GENMASK(9, 8) +#define ARM_SMMU_TCR_EPD0 BIT(7) #define ARM_SMMU_TCR_T0SZ GENMASK(5, 0) #define ARM_SMMU_VTCR_RES1 BIT(31) @@ -350,12 +352,23 @@ struct arm_smmu_domain { static inline u32 arm_smmu_lpae_tcr(struct io_pgtable_cfg *cfg) { - return ARM_SMMU_TCR_EPD1 | - FIELD_PREP(ARM_SMMU_TCR_TG0, cfg->arm_lpae_s1_cfg.tcr.tg) | - FIELD_PREP(ARM_SMMU_TCR_SH0, cfg->arm_lpae_s1_cfg.tcr.sh) | - FIELD_PREP(ARM_SMMU_TCR_ORGN0, cfg->arm_lpae_s1_cfg.tcr.orgn) | - FIELD_PREP(ARM_SMMU_TCR_IRGN0, cfg->arm_lpae_s1_cfg.tcr.irgn) | - FIELD_PREP(ARM_SMMU_TCR_T0SZ, cfg->arm_lpae_s1_cfg.tcr.tsz); + u32 tcr = FIELD_PREP(ARM_SMMU_TCR_TG0, cfg->arm_lpae_s1_cfg.tcr.tg) | + FIELD_PREP(ARM_SMMU_TCR_SH0, cfg->arm_lpae_s1_cfg.tcr.sh) | + FIELD_PREP(ARM_SMMU_TCR_ORGN0, cfg->arm_lpae_s1_cfg.tcr.orgn) | + FIELD_PREP(ARM_SMMU_TCR_IRGN0, cfg->arm_lpae_s1_cfg.tcr.irgn) | + FIELD_PREP(ARM_SMMU_TCR_T0SZ, cfg->arm_lpae_s1_cfg.tcr.tsz); + + /* + * When TTBR1 is selected shift the TCR fields by 16 bits and disable + * translation in TTBR0 + */ + if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1) { + tcr = (tcr << 16) & ~ARM_SMMU_TCR_A1; + tcr |= ARM_SMMU_TCR_EPD0; + } else + tcr |= ARM_SMMU_TCR_EPD1; + + return tcr; } static inline u32 arm_smmu_lpae_tcr2(struct io_pgtable_cfg *cfg) -- cgit v1.2.3 From 556db53a71e0e0bcfb30b4d8e4fdd7bb49951b99 Mon Sep 17 00:00:00 2001 From: Jordan Crouse Date: Sat, 5 Sep 2020 13:04:20 -0700 Subject: iommu/arm-smmu: Prepare for the adreno-smmu implementation Do a bit of prep work to add the upcoming adreno-smmu implementation. Add an hook to allow the implementation to choose which context banks to allocate. Move some of the common structs to arm-smmu.h in anticipation of them being used by the implementations and update some of the existing hooks to pass more information that the implementation will need. These modifications will be used by the upcoming Adreno SMMU implementation to identify the GPU device and properly configure it for pagetable switching. Co-developed-by: Rob Clark Signed-off-by: Jordan Crouse Signed-off-by: Rob Clark Reviewed-by: Bjorn Andersson Signed-off-by: Will Deacon --- drivers/iommu/arm/arm-smmu/arm-smmu-impl.c | 2 +- drivers/iommu/arm/arm-smmu/arm-smmu.c | 74 +++++++++--------------------- drivers/iommu/arm/arm-smmu/arm-smmu.h | 52 ++++++++++++++++++++- 3 files changed, 73 insertions(+), 55 deletions(-) (limited to 'drivers/iommu/arm') diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c index a9861dcd0884..88f17cc33023 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c @@ -69,7 +69,7 @@ static int cavium_cfg_probe(struct arm_smmu_device *smmu) } static int cavium_init_context(struct arm_smmu_domain *smmu_domain, - struct io_pgtable_cfg *pgtbl_cfg) + struct io_pgtable_cfg *pgtbl_cfg, struct device *dev) { struct cavium_smmu *cs = container_of(smmu_domain->smmu, struct cavium_smmu, smmu); diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c index 8e884e58f208..dad7fa86fbd4 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c @@ -65,41 +65,10 @@ module_param(disable_bypass, bool, S_IRUGO); MODULE_PARM_DESC(disable_bypass, "Disable bypass streams such that incoming transactions from devices that are not attached to an iommu domain will report an abort back to the device and will not be allowed to pass through the SMMU."); -struct arm_smmu_s2cr { - struct iommu_group *group; - int count; - enum arm_smmu_s2cr_type type; - enum arm_smmu_s2cr_privcfg privcfg; - u8 cbndx; -}; - #define s2cr_init_val (struct arm_smmu_s2cr){ \ .type = disable_bypass ? S2CR_TYPE_FAULT : S2CR_TYPE_BYPASS, \ } -struct arm_smmu_smr { - u16 mask; - u16 id; - bool valid; -}; - -struct arm_smmu_cb { - u64 ttbr[2]; - u32 tcr[2]; - u32 mair[2]; - struct arm_smmu_cfg *cfg; -}; - -struct arm_smmu_master_cfg { - struct arm_smmu_device *smmu; - s16 smendx[]; -}; -#define INVALID_SMENDX -1 -#define cfg_smendx(cfg, fw, i) \ - (i >= fw->num_ids ? INVALID_SMENDX : cfg->smendx[i]) -#define for_each_cfg_sme(cfg, fw, i, idx) \ - for (i = 0; idx = cfg_smendx(cfg, fw, i), i < fw->num_ids; ++i) - static bool using_legacy_binding, using_generic_binding; static inline int arm_smmu_rpm_get(struct arm_smmu_device *smmu) @@ -234,19 +203,6 @@ static int arm_smmu_register_legacy_master(struct device *dev, } #endif /* CONFIG_ARM_SMMU_LEGACY_DT_BINDINGS */ -static int __arm_smmu_alloc_bitmap(unsigned long *map, int start, int end) -{ - int idx; - - do { - idx = find_next_zero_bit(map, end, start); - if (idx == end) - return -ENOSPC; - } while (test_and_set_bit(idx, map)); - - return idx; -} - static void __arm_smmu_free_bitmap(unsigned long *map, int idx) { clear_bit(idx, map); @@ -578,7 +534,7 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain, } } -static void arm_smmu_write_context_bank(struct arm_smmu_device *smmu, int idx) +void arm_smmu_write_context_bank(struct arm_smmu_device *smmu, int idx) { u32 reg; bool stage1; @@ -664,8 +620,19 @@ static void arm_smmu_write_context_bank(struct arm_smmu_device *smmu, int idx) arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_SCTLR, reg); } +static int arm_smmu_alloc_context_bank(struct arm_smmu_domain *smmu_domain, + struct arm_smmu_device *smmu, + struct device *dev, unsigned int start) +{ + if (smmu->impl && smmu->impl->alloc_context_bank) + return smmu->impl->alloc_context_bank(smmu_domain, smmu, dev, start); + + return __arm_smmu_alloc_bitmap(smmu->context_map, start, smmu->num_context_banks); +} + static int arm_smmu_init_domain_context(struct iommu_domain *domain, - struct arm_smmu_device *smmu) + struct arm_smmu_device *smmu, + struct device *dev) { int irq, start, ret = 0; unsigned long ias, oas; @@ -780,10 +747,13 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain, ret = -EINVAL; goto out_unlock; } - ret = __arm_smmu_alloc_bitmap(smmu->context_map, start, - smmu->num_context_banks); - if (ret < 0) + + ret = arm_smmu_alloc_context_bank(smmu_domain, smmu, dev, start); + if (ret < 0) { goto out_unlock; + } + + smmu_domain->smmu = smmu; cfg->cbndx = ret; if (smmu->version < ARM_SMMU_V2) { @@ -798,8 +768,6 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain, else cfg->asid = cfg->cbndx; - smmu_domain->smmu = smmu; - pgtbl_cfg = (struct io_pgtable_cfg) { .pgsize_bitmap = smmu->pgsize_bitmap, .ias = ias, @@ -810,7 +778,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain, }; if (smmu->impl && smmu->impl->init_context) { - ret = smmu->impl->init_context(smmu_domain, &pgtbl_cfg); + ret = smmu->impl->init_context(smmu_domain, &pgtbl_cfg, dev); if (ret) goto out_clear_smmu; } @@ -1194,7 +1162,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) return ret; /* Ensure that the domain is finalised */ - ret = arm_smmu_init_domain_context(domain, smmu); + ret = arm_smmu_init_domain_context(domain, smmu, dev); if (ret < 0) goto rpm_put; diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.h b/drivers/iommu/arm/arm-smmu/arm-smmu.h index f3e456893f28..9aaacc906597 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.h +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.h @@ -256,6 +256,21 @@ enum arm_smmu_implementation { QCOM_SMMUV2, }; +struct arm_smmu_s2cr { + struct iommu_group *group; + int count; + enum arm_smmu_s2cr_type type; + enum arm_smmu_s2cr_privcfg privcfg; + u8 cbndx; +}; + +struct arm_smmu_smr { + u16 mask; + u16 id; + bool valid; + bool pinned; +}; + struct arm_smmu_device { struct device *dev; @@ -331,6 +346,13 @@ struct arm_smmu_cfg { }; #define ARM_SMMU_INVALID_IRPTNDX 0xff +struct arm_smmu_cb { + u64 ttbr[2]; + u32 tcr[2]; + u32 mair[2]; + struct arm_smmu_cfg *cfg; +}; + enum arm_smmu_domain_stage { ARM_SMMU_DOMAIN_S1 = 0, ARM_SMMU_DOMAIN_S2, @@ -350,6 +372,11 @@ struct arm_smmu_domain { struct iommu_domain domain; }; +struct arm_smmu_master_cfg { + struct arm_smmu_device *smmu; + s16 smendx[]; +}; + static inline u32 arm_smmu_lpae_tcr(struct io_pgtable_cfg *cfg) { u32 tcr = FIELD_PREP(ARM_SMMU_TCR_TG0, cfg->arm_lpae_s1_cfg.tcr.tg) | @@ -400,14 +427,36 @@ struct arm_smmu_impl { int (*cfg_probe)(struct arm_smmu_device *smmu); int (*reset)(struct arm_smmu_device *smmu); int (*init_context)(struct arm_smmu_domain *smmu_domain, - struct io_pgtable_cfg *cfg); + struct io_pgtable_cfg *cfg, struct device *dev); void (*tlb_sync)(struct arm_smmu_device *smmu, int page, int sync, int status); int (*def_domain_type)(struct device *dev); irqreturn_t (*global_fault)(int irq, void *dev); irqreturn_t (*context_fault)(int irq, void *dev); + int (*alloc_context_bank)(struct arm_smmu_domain *smmu_domain, + struct arm_smmu_device *smmu, + struct device *dev, int start); }; +#define INVALID_SMENDX -1 +#define cfg_smendx(cfg, fw, i) \ + (i >= fw->num_ids ? INVALID_SMENDX : cfg->smendx[i]) +#define for_each_cfg_sme(cfg, fw, i, idx) \ + for (i = 0; idx = cfg_smendx(cfg, fw, i), i < fw->num_ids; ++i) + +static inline int __arm_smmu_alloc_bitmap(unsigned long *map, int start, int end) +{ + int idx; + + do { + idx = find_next_zero_bit(map, end, start); + if (idx == end) + return -ENOSPC; + } while (test_and_set_bit(idx, map)); + + return idx; +} + static inline void __iomem *arm_smmu_page(struct arm_smmu_device *smmu, int n) { return smmu->base + (n << smmu->pgshift); @@ -472,6 +521,7 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu); struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu); struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu); +void arm_smmu_write_context_bank(struct arm_smmu_device *smmu, int idx); int arm_mmu500_reset(struct arm_smmu_device *smmu); #endif /* _ARM_SMMU_H */ -- cgit v1.2.3 From 1226fa0e541c89af22683676b9829fce849efe31 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Sat, 5 Sep 2020 13:04:21 -0700 Subject: iommu/arm-smmu: Constify some helpers Sprinkle a few `const`s where helpers don't need write access. Signed-off-by: Rob Clark Reviewed-by: Bjorn Andersson Signed-off-by: Will Deacon --- drivers/iommu/arm/arm-smmu/arm-smmu.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'drivers/iommu/arm') diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.h b/drivers/iommu/arm/arm-smmu/arm-smmu.h index 9aaacc906597..1a746476927c 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.h +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.h @@ -377,7 +377,7 @@ struct arm_smmu_master_cfg { s16 smendx[]; }; -static inline u32 arm_smmu_lpae_tcr(struct io_pgtable_cfg *cfg) +static inline u32 arm_smmu_lpae_tcr(const struct io_pgtable_cfg *cfg) { u32 tcr = FIELD_PREP(ARM_SMMU_TCR_TG0, cfg->arm_lpae_s1_cfg.tcr.tg) | FIELD_PREP(ARM_SMMU_TCR_SH0, cfg->arm_lpae_s1_cfg.tcr.sh) | @@ -398,13 +398,13 @@ static inline u32 arm_smmu_lpae_tcr(struct io_pgtable_cfg *cfg) return tcr; } -static inline u32 arm_smmu_lpae_tcr2(struct io_pgtable_cfg *cfg) +static inline u32 arm_smmu_lpae_tcr2(const struct io_pgtable_cfg *cfg) { return FIELD_PREP(ARM_SMMU_TCR2_PASIZE, cfg->arm_lpae_s1_cfg.tcr.ips) | FIELD_PREP(ARM_SMMU_TCR2_SEP, ARM_SMMU_TCR2_SEP_UPSTREAM); } -static inline u32 arm_smmu_lpae_vtcr(struct io_pgtable_cfg *cfg) +static inline u32 arm_smmu_lpae_vtcr(const struct io_pgtable_cfg *cfg) { return ARM_SMMU_VTCR_RES1 | FIELD_PREP(ARM_SMMU_VTCR_PS, cfg->arm_lpae_s2_cfg.vtcr.ps) | -- cgit v1.2.3 From a76a37777f2c936b1f046bfc0c5982c958b16bfe Mon Sep 17 00:00:00 2001 From: Zhou Wang Date: Mon, 28 Sep 2020 16:32:02 +0800 Subject: iommu/arm-smmu-v3: Ensure queue is read after updating prod pointer Reading the 'prod' MMIO register in order to determine whether or not there is valid data beyond 'cons' for a given queue does not provide sufficient dependency ordering, as the resulting access is address dependent only on 'cons' and can therefore be speculated ahead of time, potentially allowing stale data to be read by the CPU. Use readl() instead of readl_relaxed() when updating the shadow copy of the 'prod' pointer, so that all speculated memory reads from the corresponding queue can occur only from valid slots. Signed-off-by: Zhou Wang Link: https://lore.kernel.org/r/1601281922-117296-1-git-send-email-wangzhou1@hisilicon.com [will: Use readl() instead of explicit barrier. Update 'cons' side to match.] Signed-off-by: Will Deacon --- arch/arm64/include/asm/barrier.h | 1 + arch/arm64/include/asm/io.h | 1 + drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 11 +++++++++-- 3 files changed, 11 insertions(+), 2 deletions(-) (limited to 'drivers/iommu/arm') diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index fb4c27506ef4..c3009b0e5239 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -45,6 +45,7 @@ #define rmb() dsb(ld) #define wmb() dsb(st) +#define dma_mb() dmb(osh) #define dma_rmb() dmb(oshld) #define dma_wmb() dmb(oshst) diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index ff50dd731852..fd172c41df90 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -110,6 +110,7 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) #define __io_par(v) __iormb(v) #define __iowmb() dma_wmb() +#define __iomb() dma_mb() /* * Relaxed I/O memory access primitives. These follow the Device memory diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index 3063aeb38063..1ffec08d345a 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -810,7 +810,7 @@ static void queue_sync_cons_out(struct arm_smmu_queue *q) * Ensure that all CPU accesses (reads and writes) to the queue * are complete before we update the cons pointer. */ - mb(); + __iomb(); writel_relaxed(q->llq.cons, q->cons_reg); } @@ -822,8 +822,15 @@ static void queue_inc_cons(struct arm_smmu_ll_queue *q) static int queue_sync_prod_in(struct arm_smmu_queue *q) { + u32 prod; int ret = 0; - u32 prod = readl_relaxed(q->prod_reg); + + /* + * We can't use the _relaxed() variant here, as we must prevent + * speculative reads of the queue before we have determined that + * prod has indeed moved. + */ + prod = readl(q->prod_reg); if (Q_OVF(prod) != Q_OVF(q->llq.prod)) ret = -EOVERFLOW; -- cgit v1.2.3 From e881e7839fba8a8452459a656eca90340cc34a2e Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Fri, 18 Sep 2020 12:18:47 +0200 Subject: iommu/arm-smmu-v3: Move definitions to a header Allow sharing structure definitions with the upcoming SVA support for Arm SMMUv3, by moving them to a separate header. We could surgically extract only what is needed but keeping all definitions in one place looks nicer. Signed-off-by: Jean-Philippe Brucker Reviewed-by: Eric Auger Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/20200918101852.582559-8-jean-philippe@linaro.org Signed-off-by: Will Deacon --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 661 +-------------------------- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 676 ++++++++++++++++++++++++++++ 2 files changed, 677 insertions(+), 660 deletions(-) create mode 100644 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h (limited to 'drivers/iommu/arm') diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index 1ffec08d345a..b0d26c9f577d 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -11,7 +11,6 @@ #include #include -#include #include #include #include @@ -19,7 +18,6 @@ #include #include #include -#include #include #include #include @@ -33,385 +31,7 @@ #include -/* MMIO registers */ -#define ARM_SMMU_IDR0 0x0 -#define IDR0_ST_LVL GENMASK(28, 27) -#define IDR0_ST_LVL_2LVL 1 -#define IDR0_STALL_MODEL GENMASK(25, 24) -#define IDR0_STALL_MODEL_STALL 0 -#define IDR0_STALL_MODEL_FORCE 2 -#define IDR0_TTENDIAN GENMASK(22, 21) -#define IDR0_TTENDIAN_MIXED 0 -#define IDR0_TTENDIAN_LE 2 -#define IDR0_TTENDIAN_BE 3 -#define IDR0_CD2L (1 << 19) -#define IDR0_VMID16 (1 << 18) -#define IDR0_PRI (1 << 16) -#define IDR0_SEV (1 << 14) -#define IDR0_MSI (1 << 13) -#define IDR0_ASID16 (1 << 12) -#define IDR0_ATS (1 << 10) -#define IDR0_HYP (1 << 9) -#define IDR0_COHACC (1 << 4) -#define IDR0_TTF GENMASK(3, 2) -#define IDR0_TTF_AARCH64 2 -#define IDR0_TTF_AARCH32_64 3 -#define IDR0_S1P (1 << 1) -#define IDR0_S2P (1 << 0) - -#define ARM_SMMU_IDR1 0x4 -#define IDR1_TABLES_PRESET (1 << 30) -#define IDR1_QUEUES_PRESET (1 << 29) -#define IDR1_REL (1 << 28) -#define IDR1_CMDQS GENMASK(25, 21) -#define IDR1_EVTQS GENMASK(20, 16) -#define IDR1_PRIQS GENMASK(15, 11) -#define IDR1_SSIDSIZE GENMASK(10, 6) -#define IDR1_SIDSIZE GENMASK(5, 0) - -#define ARM_SMMU_IDR3 0xc -#define IDR3_RIL (1 << 10) - -#define ARM_SMMU_IDR5 0x14 -#define IDR5_STALL_MAX GENMASK(31, 16) -#define IDR5_GRAN64K (1 << 6) -#define IDR5_GRAN16K (1 << 5) -#define IDR5_GRAN4K (1 << 4) -#define IDR5_OAS GENMASK(2, 0) -#define IDR5_OAS_32_BIT 0 -#define IDR5_OAS_36_BIT 1 -#define IDR5_OAS_40_BIT 2 -#define IDR5_OAS_42_BIT 3 -#define IDR5_OAS_44_BIT 4 -#define IDR5_OAS_48_BIT 5 -#define IDR5_OAS_52_BIT 6 -#define IDR5_VAX GENMASK(11, 10) -#define IDR5_VAX_52_BIT 1 - -#define ARM_SMMU_CR0 0x20 -#define CR0_ATSCHK (1 << 4) -#define CR0_CMDQEN (1 << 3) -#define CR0_EVTQEN (1 << 2) -#define CR0_PRIQEN (1 << 1) -#define CR0_SMMUEN (1 << 0) - -#define ARM_SMMU_CR0ACK 0x24 - -#define ARM_SMMU_CR1 0x28 -#define CR1_TABLE_SH GENMASK(11, 10) -#define CR1_TABLE_OC GENMASK(9, 8) -#define CR1_TABLE_IC GENMASK(7, 6) -#define CR1_QUEUE_SH GENMASK(5, 4) -#define CR1_QUEUE_OC GENMASK(3, 2) -#define CR1_QUEUE_IC GENMASK(1, 0) -/* CR1 cacheability fields don't quite follow the usual TCR-style encoding */ -#define CR1_CACHE_NC 0 -#define CR1_CACHE_WB 1 -#define CR1_CACHE_WT 2 - -#define ARM_SMMU_CR2 0x2c -#define CR2_PTM (1 << 2) -#define CR2_RECINVSID (1 << 1) -#define CR2_E2H (1 << 0) - -#define ARM_SMMU_GBPA 0x44 -#define GBPA_UPDATE (1 << 31) -#define GBPA_ABORT (1 << 20) - -#define ARM_SMMU_IRQ_CTRL 0x50 -#define IRQ_CTRL_EVTQ_IRQEN (1 << 2) -#define IRQ_CTRL_PRIQ_IRQEN (1 << 1) -#define IRQ_CTRL_GERROR_IRQEN (1 << 0) - -#define ARM_SMMU_IRQ_CTRLACK 0x54 - -#define ARM_SMMU_GERROR 0x60 -#define GERROR_SFM_ERR (1 << 8) -#define GERROR_MSI_GERROR_ABT_ERR (1 << 7) -#define GERROR_MSI_PRIQ_ABT_ERR (1 << 6) -#define GERROR_MSI_EVTQ_ABT_ERR (1 << 5) -#define GERROR_MSI_CMDQ_ABT_ERR (1 << 4) -#define GERROR_PRIQ_ABT_ERR (1 << 3) -#define GERROR_EVTQ_ABT_ERR (1 << 2) -#define GERROR_CMDQ_ERR (1 << 0) -#define GERROR_ERR_MASK 0xfd - -#define ARM_SMMU_GERRORN 0x64 - -#define ARM_SMMU_GERROR_IRQ_CFG0 0x68 -#define ARM_SMMU_GERROR_IRQ_CFG1 0x70 -#define ARM_SMMU_GERROR_IRQ_CFG2 0x74 - -#define ARM_SMMU_STRTAB_BASE 0x80 -#define STRTAB_BASE_RA (1UL << 62) -#define STRTAB_BASE_ADDR_MASK GENMASK_ULL(51, 6) - -#define ARM_SMMU_STRTAB_BASE_CFG 0x88 -#define STRTAB_BASE_CFG_FMT GENMASK(17, 16) -#define STRTAB_BASE_CFG_FMT_LINEAR 0 -#define STRTAB_BASE_CFG_FMT_2LVL 1 -#define STRTAB_BASE_CFG_SPLIT GENMASK(10, 6) -#define STRTAB_BASE_CFG_LOG2SIZE GENMASK(5, 0) - -#define ARM_SMMU_CMDQ_BASE 0x90 -#define ARM_SMMU_CMDQ_PROD 0x98 -#define ARM_SMMU_CMDQ_CONS 0x9c - -#define ARM_SMMU_EVTQ_BASE 0xa0 -#define ARM_SMMU_EVTQ_PROD 0x100a8 -#define ARM_SMMU_EVTQ_CONS 0x100ac -#define ARM_SMMU_EVTQ_IRQ_CFG0 0xb0 -#define ARM_SMMU_EVTQ_IRQ_CFG1 0xb8 -#define ARM_SMMU_EVTQ_IRQ_CFG2 0xbc - -#define ARM_SMMU_PRIQ_BASE 0xc0 -#define ARM_SMMU_PRIQ_PROD 0x100c8 -#define ARM_SMMU_PRIQ_CONS 0x100cc -#define ARM_SMMU_PRIQ_IRQ_CFG0 0xd0 -#define ARM_SMMU_PRIQ_IRQ_CFG1 0xd8 -#define ARM_SMMU_PRIQ_IRQ_CFG2 0xdc - -#define ARM_SMMU_REG_SZ 0xe00 - -/* Common MSI config fields */ -#define MSI_CFG0_ADDR_MASK GENMASK_ULL(51, 2) -#define MSI_CFG2_SH GENMASK(5, 4) -#define MSI_CFG2_MEMATTR GENMASK(3, 0) - -/* Common memory attribute values */ -#define ARM_SMMU_SH_NSH 0 -#define ARM_SMMU_SH_OSH 2 -#define ARM_SMMU_SH_ISH 3 -#define ARM_SMMU_MEMATTR_DEVICE_nGnRE 0x1 -#define ARM_SMMU_MEMATTR_OIWB 0xf - -#define Q_IDX(llq, p) ((p) & ((1 << (llq)->max_n_shift) - 1)) -#define Q_WRP(llq, p) ((p) & (1 << (llq)->max_n_shift)) -#define Q_OVERFLOW_FLAG (1U << 31) -#define Q_OVF(p) ((p) & Q_OVERFLOW_FLAG) -#define Q_ENT(q, p) ((q)->base + \ - Q_IDX(&((q)->llq), p) * \ - (q)->ent_dwords) - -#define Q_BASE_RWA (1UL << 62) -#define Q_BASE_ADDR_MASK GENMASK_ULL(51, 5) -#define Q_BASE_LOG2SIZE GENMASK(4, 0) - -/* Ensure DMA allocations are naturally aligned */ -#ifdef CONFIG_CMA_ALIGNMENT -#define Q_MAX_SZ_SHIFT (PAGE_SHIFT + CONFIG_CMA_ALIGNMENT) -#else -#define Q_MAX_SZ_SHIFT (PAGE_SHIFT + MAX_ORDER - 1) -#endif - -/* - * Stream table. - * - * Linear: Enough to cover 1 << IDR1.SIDSIZE entries - * 2lvl: 128k L1 entries, - * 256 lazy entries per table (each table covers a PCI bus) - */ -#define STRTAB_L1_SZ_SHIFT 20 -#define STRTAB_SPLIT 8 - -#define STRTAB_L1_DESC_DWORDS 1 -#define STRTAB_L1_DESC_SPAN GENMASK_ULL(4, 0) -#define STRTAB_L1_DESC_L2PTR_MASK GENMASK_ULL(51, 6) - -#define STRTAB_STE_DWORDS 8 -#define STRTAB_STE_0_V (1UL << 0) -#define STRTAB_STE_0_CFG GENMASK_ULL(3, 1) -#define STRTAB_STE_0_CFG_ABORT 0 -#define STRTAB_STE_0_CFG_BYPASS 4 -#define STRTAB_STE_0_CFG_S1_TRANS 5 -#define STRTAB_STE_0_CFG_S2_TRANS 6 - -#define STRTAB_STE_0_S1FMT GENMASK_ULL(5, 4) -#define STRTAB_STE_0_S1FMT_LINEAR 0 -#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) - -#define STRTAB_STE_1_S1DSS GENMASK_ULL(1, 0) -#define STRTAB_STE_1_S1DSS_TERMINATE 0x0 -#define STRTAB_STE_1_S1DSS_BYPASS 0x1 -#define STRTAB_STE_1_S1DSS_SSID0 0x2 - -#define STRTAB_STE_1_S1C_CACHE_NC 0UL -#define STRTAB_STE_1_S1C_CACHE_WBRA 1UL -#define STRTAB_STE_1_S1C_CACHE_WT 2UL -#define STRTAB_STE_1_S1C_CACHE_WB 3UL -#define STRTAB_STE_1_S1CIR GENMASK_ULL(3, 2) -#define STRTAB_STE_1_S1COR GENMASK_ULL(5, 4) -#define STRTAB_STE_1_S1CSH GENMASK_ULL(7, 6) - -#define STRTAB_STE_1_S1STALLD (1UL << 27) - -#define STRTAB_STE_1_EATS GENMASK_ULL(29, 28) -#define STRTAB_STE_1_EATS_ABT 0UL -#define STRTAB_STE_1_EATS_TRANS 1UL -#define STRTAB_STE_1_EATS_S1CHK 2UL - -#define STRTAB_STE_1_STRW GENMASK_ULL(31, 30) -#define STRTAB_STE_1_STRW_NSEL1 0UL -#define STRTAB_STE_1_STRW_EL2 2UL - -#define STRTAB_STE_1_SHCFG GENMASK_ULL(45, 44) -#define STRTAB_STE_1_SHCFG_INCOMING 1UL - -#define STRTAB_STE_2_S2VMID GENMASK_ULL(15, 0) -#define STRTAB_STE_2_VTCR GENMASK_ULL(50, 32) -#define STRTAB_STE_2_VTCR_S2T0SZ GENMASK_ULL(5, 0) -#define STRTAB_STE_2_VTCR_S2SL0 GENMASK_ULL(7, 6) -#define STRTAB_STE_2_VTCR_S2IR0 GENMASK_ULL(9, 8) -#define STRTAB_STE_2_VTCR_S2OR0 GENMASK_ULL(11, 10) -#define STRTAB_STE_2_VTCR_S2SH0 GENMASK_ULL(13, 12) -#define STRTAB_STE_2_VTCR_S2TG GENMASK_ULL(15, 14) -#define STRTAB_STE_2_VTCR_S2PS GENMASK_ULL(18, 16) -#define STRTAB_STE_2_S2AA64 (1UL << 51) -#define STRTAB_STE_2_S2ENDI (1UL << 52) -#define STRTAB_STE_2_S2PTW (1UL << 54) -#define STRTAB_STE_2_S2R (1UL << 58) - -#define STRTAB_STE_3_S2TTB_MASK GENMASK_ULL(51, 4) - -/* - * Context descriptors. - * - * Linear: when less than 1024 SSIDs are supported - * 2lvl: at most 1024 L1 entries, - * 1024 lazy entries per table. - */ -#define CTXDESC_SPLIT 10 -#define CTXDESC_L2_ENTRIES (1 << CTXDESC_SPLIT) - -#define CTXDESC_L1_DESC_DWORDS 1 -#define CTXDESC_L1_DESC_V (1UL << 0) -#define CTXDESC_L1_DESC_L2PTR_MASK GENMASK_ULL(51, 12) - -#define CTXDESC_CD_DWORDS 8 -#define CTXDESC_CD_0_TCR_T0SZ GENMASK_ULL(5, 0) -#define CTXDESC_CD_0_TCR_TG0 GENMASK_ULL(7, 6) -#define CTXDESC_CD_0_TCR_IRGN0 GENMASK_ULL(9, 8) -#define CTXDESC_CD_0_TCR_ORGN0 GENMASK_ULL(11, 10) -#define CTXDESC_CD_0_TCR_SH0 GENMASK_ULL(13, 12) -#define CTXDESC_CD_0_TCR_EPD0 (1ULL << 14) -#define CTXDESC_CD_0_TCR_EPD1 (1ULL << 30) - -#define CTXDESC_CD_0_ENDI (1UL << 15) -#define CTXDESC_CD_0_V (1UL << 31) - -#define CTXDESC_CD_0_TCR_IPS GENMASK_ULL(34, 32) -#define CTXDESC_CD_0_TCR_TBI0 (1ULL << 38) - -#define CTXDESC_CD_0_AA64 (1UL << 41) -#define CTXDESC_CD_0_S (1UL << 44) -#define CTXDESC_CD_0_R (1UL << 45) -#define CTXDESC_CD_0_A (1UL << 46) -#define CTXDESC_CD_0_ASET (1UL << 47) -#define CTXDESC_CD_0_ASID GENMASK_ULL(63, 48) - -#define CTXDESC_CD_1_TTB0_MASK GENMASK_ULL(51, 4) - -/* - * When the SMMU only supports linear context descriptor tables, pick a - * reasonable size limit (64kB). - */ -#define CTXDESC_LINEAR_CDMAX ilog2(SZ_64K / (CTXDESC_CD_DWORDS << 3)) - -/* Command queue */ -#define CMDQ_ENT_SZ_SHIFT 4 -#define CMDQ_ENT_DWORDS ((1 << CMDQ_ENT_SZ_SHIFT) >> 3) -#define CMDQ_MAX_SZ_SHIFT (Q_MAX_SZ_SHIFT - CMDQ_ENT_SZ_SHIFT) - -#define CMDQ_CONS_ERR GENMASK(30, 24) -#define CMDQ_ERR_CERROR_NONE_IDX 0 -#define CMDQ_ERR_CERROR_ILL_IDX 1 -#define CMDQ_ERR_CERROR_ABT_IDX 2 -#define CMDQ_ERR_CERROR_ATC_INV_IDX 3 - -#define CMDQ_PROD_OWNED_FLAG Q_OVERFLOW_FLAG - -/* - * This is used to size the command queue and therefore must be at least - * BITS_PER_LONG so that the valid_map works correctly (it relies on the - * total number of queue entries being a multiple of BITS_PER_LONG). - */ -#define CMDQ_BATCH_ENTRIES BITS_PER_LONG - -#define CMDQ_0_OP GENMASK_ULL(7, 0) -#define CMDQ_0_SSV (1UL << 11) - -#define CMDQ_PREFETCH_0_SID GENMASK_ULL(63, 32) -#define CMDQ_PREFETCH_1_SIZE GENMASK_ULL(4, 0) -#define CMDQ_PREFETCH_1_ADDR_MASK GENMASK_ULL(63, 12) - -#define CMDQ_CFGI_0_SSID GENMASK_ULL(31, 12) -#define CMDQ_CFGI_0_SID GENMASK_ULL(63, 32) -#define CMDQ_CFGI_1_LEAF (1UL << 0) -#define CMDQ_CFGI_1_RANGE GENMASK_ULL(4, 0) - -#define CMDQ_TLBI_0_NUM GENMASK_ULL(16, 12) -#define CMDQ_TLBI_RANGE_NUM_MAX 31 -#define CMDQ_TLBI_0_SCALE GENMASK_ULL(24, 20) -#define CMDQ_TLBI_0_VMID GENMASK_ULL(47, 32) -#define CMDQ_TLBI_0_ASID GENMASK_ULL(63, 48) -#define CMDQ_TLBI_1_LEAF (1UL << 0) -#define CMDQ_TLBI_1_TTL GENMASK_ULL(9, 8) -#define CMDQ_TLBI_1_TG GENMASK_ULL(11, 10) -#define CMDQ_TLBI_1_VA_MASK GENMASK_ULL(63, 12) -#define CMDQ_TLBI_1_IPA_MASK GENMASK_ULL(51, 12) - -#define CMDQ_ATC_0_SSID GENMASK_ULL(31, 12) -#define CMDQ_ATC_0_SID GENMASK_ULL(63, 32) -#define CMDQ_ATC_0_GLOBAL (1UL << 9) -#define CMDQ_ATC_1_SIZE GENMASK_ULL(5, 0) -#define CMDQ_ATC_1_ADDR_MASK GENMASK_ULL(63, 12) - -#define CMDQ_PRI_0_SSID GENMASK_ULL(31, 12) -#define CMDQ_PRI_0_SID GENMASK_ULL(63, 32) -#define CMDQ_PRI_1_GRPID GENMASK_ULL(8, 0) -#define CMDQ_PRI_1_RESP GENMASK_ULL(13, 12) - -#define CMDQ_SYNC_0_CS GENMASK_ULL(13, 12) -#define CMDQ_SYNC_0_CS_NONE 0 -#define CMDQ_SYNC_0_CS_IRQ 1 -#define CMDQ_SYNC_0_CS_SEV 2 -#define CMDQ_SYNC_0_MSH GENMASK_ULL(23, 22) -#define CMDQ_SYNC_0_MSIATTR GENMASK_ULL(27, 24) -#define CMDQ_SYNC_0_MSIDATA GENMASK_ULL(63, 32) -#define CMDQ_SYNC_1_MSIADDR_MASK GENMASK_ULL(51, 2) - -/* Event queue */ -#define EVTQ_ENT_SZ_SHIFT 5 -#define EVTQ_ENT_DWORDS ((1 << EVTQ_ENT_SZ_SHIFT) >> 3) -#define EVTQ_MAX_SZ_SHIFT (Q_MAX_SZ_SHIFT - EVTQ_ENT_SZ_SHIFT) - -#define EVTQ_0_ID GENMASK_ULL(7, 0) - -/* PRI queue */ -#define PRIQ_ENT_SZ_SHIFT 4 -#define PRIQ_ENT_DWORDS ((1 << PRIQ_ENT_SZ_SHIFT) >> 3) -#define PRIQ_MAX_SZ_SHIFT (Q_MAX_SZ_SHIFT - PRIQ_ENT_SZ_SHIFT) - -#define PRIQ_0_SID GENMASK_ULL(31, 0) -#define PRIQ_0_SSID GENMASK_ULL(51, 32) -#define PRIQ_0_PERM_PRIV (1UL << 58) -#define PRIQ_0_PERM_EXEC (1UL << 59) -#define PRIQ_0_PERM_READ (1UL << 60) -#define PRIQ_0_PERM_WRITE (1UL << 61) -#define PRIQ_0_PRG_LAST (1UL << 62) -#define PRIQ_0_SSID_V (1UL << 63) - -#define PRIQ_1_PRG_IDX GENMASK_ULL(8, 0) -#define PRIQ_1_ADDR_MASK GENMASK_ULL(63, 12) - -/* High-level queue structures */ -#define ARM_SMMU_POLL_TIMEOUT_US 1000000 /* 1s! */ -#define ARM_SMMU_POLL_SPIN_COUNT 10 - -#define MSI_IOVA_BASE 0x8000000 -#define MSI_IOVA_LENGTH 0x100000 +#include "arm-smmu-v3.h" static bool disable_bypass = 1; module_param(disable_bypass, bool, 0444); @@ -423,12 +43,6 @@ module_param(disable_msipolling, bool, 0444); MODULE_PARM_DESC(disable_msipolling, "Disable MSI-based polling for CMD_SYNC completion."); -enum pri_resp { - PRI_RESP_DENY = 0, - PRI_RESP_FAIL = 1, - PRI_RESP_SUCC = 2, -}; - enum arm_smmu_msi_index { EVTQ_MSI_INDEX, GERROR_MSI_INDEX, @@ -454,279 +68,6 @@ static phys_addr_t arm_smmu_msi_cfg[ARM_SMMU_MAX_MSIS][3] = { }, }; -struct arm_smmu_cmdq_ent { - /* Common fields */ - u8 opcode; - bool substream_valid; - - /* Command-specific fields */ - union { - #define CMDQ_OP_PREFETCH_CFG 0x1 - struct { - u32 sid; - u8 size; - u64 addr; - } prefetch; - - #define CMDQ_OP_CFGI_STE 0x3 - #define CMDQ_OP_CFGI_ALL 0x4 - #define CMDQ_OP_CFGI_CD 0x5 - #define CMDQ_OP_CFGI_CD_ALL 0x6 - struct { - u32 sid; - u32 ssid; - union { - bool leaf; - u8 span; - }; - } cfgi; - - #define CMDQ_OP_TLBI_NH_ASID 0x11 - #define CMDQ_OP_TLBI_NH_VA 0x12 - #define CMDQ_OP_TLBI_EL2_ALL 0x20 - #define CMDQ_OP_TLBI_S12_VMALL 0x28 - #define CMDQ_OP_TLBI_S2_IPA 0x2a - #define CMDQ_OP_TLBI_NSNH_ALL 0x30 - struct { - u8 num; - u8 scale; - u16 asid; - u16 vmid; - bool leaf; - u8 ttl; - u8 tg; - u64 addr; - } tlbi; - - #define CMDQ_OP_ATC_INV 0x40 - #define ATC_INV_SIZE_ALL 52 - struct { - u32 sid; - u32 ssid; - u64 addr; - u8 size; - bool global; - } atc; - - #define CMDQ_OP_PRI_RESP 0x41 - struct { - u32 sid; - u32 ssid; - u16 grpid; - enum pri_resp resp; - } pri; - - #define CMDQ_OP_CMD_SYNC 0x46 - struct { - u64 msiaddr; - } sync; - }; -}; - -struct arm_smmu_ll_queue { - union { - u64 val; - struct { - u32 prod; - u32 cons; - }; - struct { - atomic_t prod; - atomic_t cons; - } atomic; - u8 __pad[SMP_CACHE_BYTES]; - } ____cacheline_aligned_in_smp; - u32 max_n_shift; -}; - -struct arm_smmu_queue { - struct arm_smmu_ll_queue llq; - int irq; /* Wired interrupt */ - - __le64 *base; - dma_addr_t base_dma; - u64 q_base; - - size_t ent_dwords; - - u32 __iomem *prod_reg; - u32 __iomem *cons_reg; -}; - -struct arm_smmu_queue_poll { - ktime_t timeout; - unsigned int delay; - unsigned int spin_cnt; - bool wfe; -}; - -struct arm_smmu_cmdq { - struct arm_smmu_queue q; - atomic_long_t *valid_map; - atomic_t owner_prod; - atomic_t lock; -}; - -struct arm_smmu_cmdq_batch { - u64 cmds[CMDQ_BATCH_ENTRIES * CMDQ_ENT_DWORDS]; - int num; -}; - -struct arm_smmu_evtq { - struct arm_smmu_queue q; - u32 max_stalls; -}; - -struct arm_smmu_priq { - struct arm_smmu_queue q; -}; - -/* High-level stream table and context descriptor structures */ -struct arm_smmu_strtab_l1_desc { - u8 span; - - __le64 *l2ptr; - dma_addr_t l2ptr_dma; -}; - -struct arm_smmu_ctx_desc { - u16 asid; - u64 ttbr; - u64 tcr; - u64 mair; -}; - -struct arm_smmu_l1_ctx_desc { - __le64 *l2ptr; - dma_addr_t l2ptr_dma; -}; - -struct arm_smmu_ctx_desc_cfg { - __le64 *cdtab; - dma_addr_t cdtab_dma; - struct arm_smmu_l1_ctx_desc *l1_desc; - unsigned int num_l1_ents; -}; - -struct arm_smmu_s1_cfg { - struct arm_smmu_ctx_desc_cfg cdcfg; - struct arm_smmu_ctx_desc cd; - u8 s1fmt; - u8 s1cdmax; -}; - -struct arm_smmu_s2_cfg { - u16 vmid; - u64 vttbr; - u64 vtcr; -}; - -struct arm_smmu_strtab_cfg { - __le64 *strtab; - dma_addr_t strtab_dma; - struct arm_smmu_strtab_l1_desc *l1_desc; - unsigned int num_l1_ents; - - u64 strtab_base; - u32 strtab_base_cfg; -}; - -/* An SMMUv3 instance */ -struct arm_smmu_device { - struct device *dev; - void __iomem *base; - void __iomem *page1; - -#define ARM_SMMU_FEAT_2_LVL_STRTAB (1 << 0) -#define ARM_SMMU_FEAT_2_LVL_CDTAB (1 << 1) -#define ARM_SMMU_FEAT_TT_LE (1 << 2) -#define ARM_SMMU_FEAT_TT_BE (1 << 3) -#define ARM_SMMU_FEAT_PRI (1 << 4) -#define ARM_SMMU_FEAT_ATS (1 << 5) -#define ARM_SMMU_FEAT_SEV (1 << 6) -#define ARM_SMMU_FEAT_MSI (1 << 7) -#define ARM_SMMU_FEAT_COHERENCY (1 << 8) -#define ARM_SMMU_FEAT_TRANS_S1 (1 << 9) -#define ARM_SMMU_FEAT_TRANS_S2 (1 << 10) -#define ARM_SMMU_FEAT_STALLS (1 << 11) -#define ARM_SMMU_FEAT_HYP (1 << 12) -#define ARM_SMMU_FEAT_STALL_FORCE (1 << 13) -#define ARM_SMMU_FEAT_VAX (1 << 14) -#define ARM_SMMU_FEAT_RANGE_INV (1 << 15) - u32 features; - -#define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0) -#define ARM_SMMU_OPT_PAGE0_REGS_ONLY (1 << 1) -#define ARM_SMMU_OPT_MSIPOLL (1 << 2) - u32 options; - - struct arm_smmu_cmdq cmdq; - struct arm_smmu_evtq evtq; - struct arm_smmu_priq priq; - - int gerr_irq; - int combined_irq; - - unsigned long ias; /* IPA */ - unsigned long oas; /* PA */ - unsigned long pgsize_bitmap; - -#define ARM_SMMU_MAX_ASIDS (1 << 16) - unsigned int asid_bits; - -#define ARM_SMMU_MAX_VMIDS (1 << 16) - unsigned int vmid_bits; - DECLARE_BITMAP(vmid_map, ARM_SMMU_MAX_VMIDS); - - unsigned int ssid_bits; - unsigned int sid_bits; - - struct arm_smmu_strtab_cfg strtab_cfg; - - /* IOMMU core code handle */ - struct iommu_device iommu; -}; - -/* SMMU private data for each master */ -struct arm_smmu_master { - struct arm_smmu_device *smmu; - struct device *dev; - struct arm_smmu_domain *domain; - struct list_head domain_head; - u32 *sids; - unsigned int num_sids; - bool ats_enabled; - unsigned int ssid_bits; -}; - -/* SMMU private data for an IOMMU domain */ -enum arm_smmu_domain_stage { - ARM_SMMU_DOMAIN_S1 = 0, - ARM_SMMU_DOMAIN_S2, - ARM_SMMU_DOMAIN_NESTED, - ARM_SMMU_DOMAIN_BYPASS, -}; - -struct arm_smmu_domain { - struct arm_smmu_device *smmu; - struct mutex init_mutex; /* Protects smmu pointer */ - - struct io_pgtable_ops *pgtbl_ops; - bool non_strict; - atomic_t nr_ats_masters; - - enum arm_smmu_domain_stage stage; - union { - struct arm_smmu_s1_cfg s1_cfg; - struct arm_smmu_s2_cfg s2_cfg; - }; - - struct iommu_domain domain; - - struct list_head devices; - spinlock_t devices_lock; -}; - struct arm_smmu_option_prop { u32 opt; const char *prop; diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h new file mode 100644 index 000000000000..c4c0c1345834 --- /dev/null +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -0,0 +1,676 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * IOMMU API for ARM architected SMMUv3 implementations. + * + * Copyright (C) 2015 ARM Limited + */ + +#ifndef _ARM_SMMU_V3_H +#define _ARM_SMMU_V3_H + +#include +#include +#include +#include +#include + +/* MMIO registers */ +#define ARM_SMMU_IDR0 0x0 +#define IDR0_ST_LVL GENMASK(28, 27) +#define IDR0_ST_LVL_2LVL 1 +#define IDR0_STALL_MODEL GENMASK(25, 24) +#define IDR0_STALL_MODEL_STALL 0 +#define IDR0_STALL_MODEL_FORCE 2 +#define IDR0_TTENDIAN GENMASK(22, 21) +#define IDR0_TTENDIAN_MIXED 0 +#define IDR0_TTENDIAN_LE 2 +#define IDR0_TTENDIAN_BE 3 +#define IDR0_CD2L (1 << 19) +#define IDR0_VMID16 (1 << 18) +#define IDR0_PRI (1 << 16) +#define IDR0_SEV (1 << 14) +#define IDR0_MSI (1 << 13) +#define IDR0_ASID16 (1 << 12) +#define IDR0_ATS (1 << 10) +#define IDR0_HYP (1 << 9) +#define IDR0_COHACC (1 << 4) +#define IDR0_TTF GENMASK(3, 2) +#define IDR0_TTF_AARCH64 2 +#define IDR0_TTF_AARCH32_64 3 +#define IDR0_S1P (1 << 1) +#define IDR0_S2P (1 << 0) + +#define ARM_SMMU_IDR1 0x4 +#define IDR1_TABLES_PRESET (1 << 30) +#define IDR1_QUEUES_PRESET (1 << 29) +#define IDR1_REL (1 << 28) +#define IDR1_CMDQS GENMASK(25, 21) +#define IDR1_EVTQS GENMASK(20, 16) +#define IDR1_PRIQS GENMASK(15, 11) +#define IDR1_SSIDSIZE GENMASK(10, 6) +#define IDR1_SIDSIZE GENMASK(5, 0) + +#define ARM_SMMU_IDR3 0xc +#define IDR3_RIL (1 << 10) + +#define ARM_SMMU_IDR5 0x14 +#define IDR5_STALL_MAX GENMASK(31, 16) +#define IDR5_GRAN64K (1 << 6) +#define IDR5_GRAN16K (1 << 5) +#define IDR5_GRAN4K (1 << 4) +#define IDR5_OAS GENMASK(2, 0) +#define IDR5_OAS_32_BIT 0 +#define IDR5_OAS_36_BIT 1 +#define IDR5_OAS_40_BIT 2 +#define IDR5_OAS_42_BIT 3 +#define IDR5_OAS_44_BIT 4 +#define IDR5_OAS_48_BIT 5 +#define IDR5_OAS_52_BIT 6 +#define IDR5_VAX GENMASK(11, 10) +#define IDR5_VAX_52_BIT 1 + +#define ARM_SMMU_CR0 0x20 +#define CR0_ATSCHK (1 << 4) +#define CR0_CMDQEN (1 << 3) +#define CR0_EVTQEN (1 << 2) +#define CR0_PRIQEN (1 << 1) +#define CR0_SMMUEN (1 << 0) + +#define ARM_SMMU_CR0ACK 0x24 + +#define ARM_SMMU_CR1 0x28 +#define CR1_TABLE_SH GENMASK(11, 10) +#define CR1_TABLE_OC GENMASK(9, 8) +#define CR1_TABLE_IC GENMASK(7, 6) +#define CR1_QUEUE_SH GENMASK(5, 4) +#define CR1_QUEUE_OC GENMASK(3, 2) +#define CR1_QUEUE_IC GENMASK(1, 0) +/* CR1 cacheability fields don't quite follow the usual TCR-style encoding */ +#define CR1_CACHE_NC 0 +#define CR1_CACHE_WB 1 +#define CR1_CACHE_WT 2 + +#define ARM_SMMU_CR2 0x2c +#define CR2_PTM (1 << 2) +#define CR2_RECINVSID (1 << 1) +#define CR2_E2H (1 << 0) + +#define ARM_SMMU_GBPA 0x44 +#define GBPA_UPDATE (1 << 31) +#define GBPA_ABORT (1 << 20) + +#define ARM_SMMU_IRQ_CTRL 0x50 +#define IRQ_CTRL_EVTQ_IRQEN (1 << 2) +#define IRQ_CTRL_PRIQ_IRQEN (1 << 1) +#define IRQ_CTRL_GERROR_IRQEN (1 << 0) + +#define ARM_SMMU_IRQ_CTRLACK 0x54 + +#define ARM_SMMU_GERROR 0x60 +#define GERROR_SFM_ERR (1 << 8) +#define GERROR_MSI_GERROR_ABT_ERR (1 << 7) +#define GERROR_MSI_PRIQ_ABT_ERR (1 << 6) +#define GERROR_MSI_EVTQ_ABT_ERR (1 << 5) +#define GERROR_MSI_CMDQ_ABT_ERR (1 << 4) +#define GERROR_PRIQ_ABT_ERR (1 << 3) +#define GERROR_EVTQ_ABT_ERR (1 << 2) +#define GERROR_CMDQ_ERR (1 << 0) +#define GERROR_ERR_MASK 0xfd + +#define ARM_SMMU_GERRORN 0x64 + +#define ARM_SMMU_GERROR_IRQ_CFG0 0x68 +#define ARM_SMMU_GERROR_IRQ_CFG1 0x70 +#define ARM_SMMU_GERROR_IRQ_CFG2 0x74 + +#define ARM_SMMU_STRTAB_BASE 0x80 +#define STRTAB_BASE_RA (1UL << 62) +#define STRTAB_BASE_ADDR_MASK GENMASK_ULL(51, 6) + +#define ARM_SMMU_STRTAB_BASE_CFG 0x88 +#define STRTAB_BASE_CFG_FMT GENMASK(17, 16) +#define STRTAB_BASE_CFG_FMT_LINEAR 0 +#define STRTAB_BASE_CFG_FMT_2LVL 1 +#define STRTAB_BASE_CFG_SPLIT GENMASK(10, 6) +#define STRTAB_BASE_CFG_LOG2SIZE GENMASK(5, 0) + +#define ARM_SMMU_CMDQ_BASE 0x90 +#define ARM_SMMU_CMDQ_PROD 0x98 +#define ARM_SMMU_CMDQ_CONS 0x9c + +#define ARM_SMMU_EVTQ_BASE 0xa0 +#define ARM_SMMU_EVTQ_PROD 0x100a8 +#define ARM_SMMU_EVTQ_CONS 0x100ac +#define ARM_SMMU_EVTQ_IRQ_CFG0 0xb0 +#define ARM_SMMU_EVTQ_IRQ_CFG1 0xb8 +#define ARM_SMMU_EVTQ_IRQ_CFG2 0xbc + +#define ARM_SMMU_PRIQ_BASE 0xc0 +#define ARM_SMMU_PRIQ_PROD 0x100c8 +#define ARM_SMMU_PRIQ_CONS 0x100cc +#define ARM_SMMU_PRIQ_IRQ_CFG0 0xd0 +#define ARM_SMMU_PRIQ_IRQ_CFG1 0xd8 +#define ARM_SMMU_PRIQ_IRQ_CFG2 0xdc + +#define ARM_SMMU_REG_SZ 0xe00 + +/* Common MSI config fields */ +#define MSI_CFG0_ADDR_MASK GENMASK_ULL(51, 2) +#define MSI_CFG2_SH GENMASK(5, 4) +#define MSI_CFG2_MEMATTR GENMASK(3, 0) + +/* Common memory attribute values */ +#define ARM_SMMU_SH_NSH 0 +#define ARM_SMMU_SH_OSH 2 +#define ARM_SMMU_SH_ISH 3 +#define ARM_SMMU_MEMATTR_DEVICE_nGnRE 0x1 +#define ARM_SMMU_MEMATTR_OIWB 0xf + +#define Q_IDX(llq, p) ((p) & ((1 << (llq)->max_n_shift) - 1)) +#define Q_WRP(llq, p) ((p) & (1 << (llq)->max_n_shift)) +#define Q_OVERFLOW_FLAG (1U << 31) +#define Q_OVF(p) ((p) & Q_OVERFLOW_FLAG) +#define Q_ENT(q, p) ((q)->base + \ + Q_IDX(&((q)->llq), p) * \ + (q)->ent_dwords) + +#define Q_BASE_RWA (1UL << 62) +#define Q_BASE_ADDR_MASK GENMASK_ULL(51, 5) +#define Q_BASE_LOG2SIZE GENMASK(4, 0) + +/* Ensure DMA allocations are naturally aligned */ +#ifdef CONFIG_CMA_ALIGNMENT +#define Q_MAX_SZ_SHIFT (PAGE_SHIFT + CONFIG_CMA_ALIGNMENT) +#else +#define Q_MAX_SZ_SHIFT (PAGE_SHIFT + MAX_ORDER - 1) +#endif + +/* + * Stream table. + * + * Linear: Enough to cover 1 << IDR1.SIDSIZE entries + * 2lvl: 128k L1 entries, + * 256 lazy entries per table (each table covers a PCI bus) + */ +#define STRTAB_L1_SZ_SHIFT 20 +#define STRTAB_SPLIT 8 + +#define STRTAB_L1_DESC_DWORDS 1 +#define STRTAB_L1_DESC_SPAN GENMASK_ULL(4, 0) +#define STRTAB_L1_DESC_L2PTR_MASK GENMASK_ULL(51, 6) + +#define STRTAB_STE_DWORDS 8 +#define STRTAB_STE_0_V (1UL << 0) +#define STRTAB_STE_0_CFG GENMASK_ULL(3, 1) +#define STRTAB_STE_0_CFG_ABORT 0 +#define STRTAB_STE_0_CFG_BYPASS 4 +#define STRTAB_STE_0_CFG_S1_TRANS 5 +#define STRTAB_STE_0_CFG_S2_TRANS 6 + +#define STRTAB_STE_0_S1FMT GENMASK_ULL(5, 4) +#define STRTAB_STE_0_S1FMT_LINEAR 0 +#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) + +#define STRTAB_STE_1_S1DSS GENMASK_ULL(1, 0) +#define STRTAB_STE_1_S1DSS_TERMINATE 0x0 +#define STRTAB_STE_1_S1DSS_BYPASS 0x1 +#define STRTAB_STE_1_S1DSS_SSID0 0x2 + +#define STRTAB_STE_1_S1C_CACHE_NC 0UL +#define STRTAB_STE_1_S1C_CACHE_WBRA 1UL +#define STRTAB_STE_1_S1C_CACHE_WT 2UL +#define STRTAB_STE_1_S1C_CACHE_WB 3UL +#define STRTAB_STE_1_S1CIR GENMASK_ULL(3, 2) +#define STRTAB_STE_1_S1COR GENMASK_ULL(5, 4) +#define STRTAB_STE_1_S1CSH GENMASK_ULL(7, 6) + +#define STRTAB_STE_1_S1STALLD (1UL << 27) + +#define STRTAB_STE_1_EATS GENMASK_ULL(29, 28) +#define STRTAB_STE_1_EATS_ABT 0UL +#define STRTAB_STE_1_EATS_TRANS 1UL +#define STRTAB_STE_1_EATS_S1CHK 2UL + +#define STRTAB_STE_1_STRW GENMASK_ULL(31, 30) +#define STRTAB_STE_1_STRW_NSEL1 0UL +#define STRTAB_STE_1_STRW_EL2 2UL + +#define STRTAB_STE_1_SHCFG GENMASK_ULL(45, 44) +#define STRTAB_STE_1_SHCFG_INCOMING 1UL + +#define STRTAB_STE_2_S2VMID GENMASK_ULL(15, 0) +#define STRTAB_STE_2_VTCR GENMASK_ULL(50, 32) +#define STRTAB_STE_2_VTCR_S2T0SZ GENMASK_ULL(5, 0) +#define STRTAB_STE_2_VTCR_S2SL0 GENMASK_ULL(7, 6) +#define STRTAB_STE_2_VTCR_S2IR0 GENMASK_ULL(9, 8) +#define STRTAB_STE_2_VTCR_S2OR0 GENMASK_ULL(11, 10) +#define STRTAB_STE_2_VTCR_S2SH0 GENMASK_ULL(13, 12) +#define STRTAB_STE_2_VTCR_S2TG GENMASK_ULL(15, 14) +#define STRTAB_STE_2_VTCR_S2PS GENMASK_ULL(18, 16) +#define STRTAB_STE_2_S2AA64 (1UL << 51) +#define STRTAB_STE_2_S2ENDI (1UL << 52) +#define STRTAB_STE_2_S2PTW (1UL << 54) +#define STRTAB_STE_2_S2R (1UL << 58) + +#define STRTAB_STE_3_S2TTB_MASK GENMASK_ULL(51, 4) + +/* + * Context descriptors. + * + * Linear: when less than 1024 SSIDs are supported + * 2lvl: at most 1024 L1 entries, + * 1024 lazy entries per table. + */ +#define CTXDESC_SPLIT 10 +#define CTXDESC_L2_ENTRIES (1 << CTXDESC_SPLIT) + +#define CTXDESC_L1_DESC_DWORDS 1 +#define CTXDESC_L1_DESC_V (1UL << 0) +#define CTXDESC_L1_DESC_L2PTR_MASK GENMASK_ULL(51, 12) + +#define CTXDESC_CD_DWORDS 8 +#define CTXDESC_CD_0_TCR_T0SZ GENMASK_ULL(5, 0) +#define CTXDESC_CD_0_TCR_TG0 GENMASK_ULL(7, 6) +#define CTXDESC_CD_0_TCR_IRGN0 GENMASK_ULL(9, 8) +#define CTXDESC_CD_0_TCR_ORGN0 GENMASK_ULL(11, 10) +#define CTXDESC_CD_0_TCR_SH0 GENMASK_ULL(13, 12) +#define CTXDESC_CD_0_TCR_EPD0 (1ULL << 14) +#define CTXDESC_CD_0_TCR_EPD1 (1ULL << 30) + +#define CTXDESC_CD_0_ENDI (1UL << 15) +#define CTXDESC_CD_0_V (1UL << 31) + +#define CTXDESC_CD_0_TCR_IPS GENMASK_ULL(34, 32) +#define CTXDESC_CD_0_TCR_TBI0 (1ULL << 38) + +#define CTXDESC_CD_0_AA64 (1UL << 41) +#define CTXDESC_CD_0_S (1UL << 44) +#define CTXDESC_CD_0_R (1UL << 45) +#define CTXDESC_CD_0_A (1UL << 46) +#define CTXDESC_CD_0_ASET (1UL << 47) +#define CTXDESC_CD_0_ASID GENMASK_ULL(63, 48) + +#define CTXDESC_CD_1_TTB0_MASK GENMASK_ULL(51, 4) + +/* + * When the SMMU only supports linear context descriptor tables, pick a + * reasonable size limit (64kB). + */ +#define CTXDESC_LINEAR_CDMAX ilog2(SZ_64K / (CTXDESC_CD_DWORDS << 3)) + +/* Command queue */ +#define CMDQ_ENT_SZ_SHIFT 4 +#define CMDQ_ENT_DWORDS ((1 << CMDQ_ENT_SZ_SHIFT) >> 3) +#define CMDQ_MAX_SZ_SHIFT (Q_MAX_SZ_SHIFT - CMDQ_ENT_SZ_SHIFT) + +#define CMDQ_CONS_ERR GENMASK(30, 24) +#define CMDQ_ERR_CERROR_NONE_IDX 0 +#define CMDQ_ERR_CERROR_ILL_IDX 1 +#define CMDQ_ERR_CERROR_ABT_IDX 2 +#define CMDQ_ERR_CERROR_ATC_INV_IDX 3 + +#define CMDQ_PROD_OWNED_FLAG Q_OVERFLOW_FLAG + +/* + * This is used to size the command queue and therefore must be at least + * BITS_PER_LONG so that the valid_map works correctly (it relies on the + * total number of queue entries being a multiple of BITS_PER_LONG). + */ +#define CMDQ_BATCH_ENTRIES BITS_PER_LONG + +#define CMDQ_0_OP GENMASK_ULL(7, 0) +#define CMDQ_0_SSV (1UL << 11) + +#define CMDQ_PREFETCH_0_SID GENMASK_ULL(63, 32) +#define CMDQ_PREFETCH_1_SIZE GENMASK_ULL(4, 0) +#define CMDQ_PREFETCH_1_ADDR_MASK GENMASK_ULL(63, 12) + +#define CMDQ_CFGI_0_SSID GENMASK_ULL(31, 12) +#define CMDQ_CFGI_0_SID GENMASK_ULL(63, 32) +#define CMDQ_CFGI_1_LEAF (1UL << 0) +#define CMDQ_CFGI_1_RANGE GENMASK_ULL(4, 0) + +#define CMDQ_TLBI_0_NUM GENMASK_ULL(16, 12) +#define CMDQ_TLBI_RANGE_NUM_MAX 31 +#define CMDQ_TLBI_0_SCALE GENMASK_ULL(24, 20) +#define CMDQ_TLBI_0_VMID GENMASK_ULL(47, 32) +#define CMDQ_TLBI_0_ASID GENMASK_ULL(63, 48) +#define CMDQ_TLBI_1_LEAF (1UL << 0) +#define CMDQ_TLBI_1_TTL GENMASK_ULL(9, 8) +#define CMDQ_TLBI_1_TG GENMASK_ULL(11, 10) +#define CMDQ_TLBI_1_VA_MASK GENMASK_ULL(63, 12) +#define CMDQ_TLBI_1_IPA_MASK GENMASK_ULL(51, 12) + +#define CMDQ_ATC_0_SSID GENMASK_ULL(31, 12) +#define CMDQ_ATC_0_SID GENMASK_ULL(63, 32) +#define CMDQ_ATC_0_GLOBAL (1UL << 9) +#define CMDQ_ATC_1_SIZE GENMASK_ULL(5, 0) +#define CMDQ_ATC_1_ADDR_MASK GENMASK_ULL(63, 12) + +#define CMDQ_PRI_0_SSID GENMASK_ULL(31, 12) +#define CMDQ_PRI_0_SID GENMASK_ULL(63, 32) +#define CMDQ_PRI_1_GRPID GENMASK_ULL(8, 0) +#define CMDQ_PRI_1_RESP GENMASK_ULL(13, 12) + +#define CMDQ_SYNC_0_CS GENMASK_ULL(13, 12) +#define CMDQ_SYNC_0_CS_NONE 0 +#define CMDQ_SYNC_0_CS_IRQ 1 +#define CMDQ_SYNC_0_CS_SEV 2 +#define CMDQ_SYNC_0_MSH GENMASK_ULL(23, 22) +#define CMDQ_SYNC_0_MSIATTR GENMASK_ULL(27, 24) +#define CMDQ_SYNC_0_MSIDATA GENMASK_ULL(63, 32) +#define CMDQ_SYNC_1_MSIADDR_MASK GENMASK_ULL(51, 2) + +/* Event queue */ +#define EVTQ_ENT_SZ_SHIFT 5 +#define EVTQ_ENT_DWORDS ((1 << EVTQ_ENT_SZ_SHIFT) >> 3) +#define EVTQ_MAX_SZ_SHIFT (Q_MAX_SZ_SHIFT - EVTQ_ENT_SZ_SHIFT) + +#define EVTQ_0_ID GENMASK_ULL(7, 0) + +/* PRI queue */ +#define PRIQ_ENT_SZ_SHIFT 4 +#define PRIQ_ENT_DWORDS ((1 << PRIQ_ENT_SZ_SHIFT) >> 3) +#define PRIQ_MAX_SZ_SHIFT (Q_MAX_SZ_SHIFT - PRIQ_ENT_SZ_SHIFT) + +#define PRIQ_0_SID GENMASK_ULL(31, 0) +#define PRIQ_0_SSID GENMASK_ULL(51, 32) +#define PRIQ_0_PERM_PRIV (1UL << 58) +#define PRIQ_0_PERM_EXEC (1UL << 59) +#define PRIQ_0_PERM_READ (1UL << 60) +#define PRIQ_0_PERM_WRITE (1UL << 61) +#define PRIQ_0_PRG_LAST (1UL << 62) +#define PRIQ_0_SSID_V (1UL << 63) + +#define PRIQ_1_PRG_IDX GENMASK_ULL(8, 0) +#define PRIQ_1_ADDR_MASK GENMASK_ULL(63, 12) + +/* High-level queue structures */ +#define ARM_SMMU_POLL_TIMEOUT_US 1000000 /* 1s! */ +#define ARM_SMMU_POLL_SPIN_COUNT 10 + +#define MSI_IOVA_BASE 0x8000000 +#define MSI_IOVA_LENGTH 0x100000 + +enum pri_resp { + PRI_RESP_DENY = 0, + PRI_RESP_FAIL = 1, + PRI_RESP_SUCC = 2, +}; + +struct arm_smmu_cmdq_ent { + /* Common fields */ + u8 opcode; + bool substream_valid; + + /* Command-specific fields */ + union { + #define CMDQ_OP_PREFETCH_CFG 0x1 + struct { + u32 sid; + u8 size; + u64 addr; + } prefetch; + + #define CMDQ_OP_CFGI_STE 0x3 + #define CMDQ_OP_CFGI_ALL 0x4 + #define CMDQ_OP_CFGI_CD 0x5 + #define CMDQ_OP_CFGI_CD_ALL 0x6 + struct { + u32 sid; + u32 ssid; + union { + bool leaf; + u8 span; + }; + } cfgi; + + #define CMDQ_OP_TLBI_NH_ASID 0x11 + #define CMDQ_OP_TLBI_NH_VA 0x12 + #define CMDQ_OP_TLBI_EL2_ALL 0x20 + #define CMDQ_OP_TLBI_S12_VMALL 0x28 + #define CMDQ_OP_TLBI_S2_IPA 0x2a + #define CMDQ_OP_TLBI_NSNH_ALL 0x30 + struct { + u8 num; + u8 scale; + u16 asid; + u16 vmid; + bool leaf; + u8 ttl; + u8 tg; + u64 addr; + } tlbi; + + #define CMDQ_OP_ATC_INV 0x40 + #define ATC_INV_SIZE_ALL 52 + struct { + u32 sid; + u32 ssid; + u64 addr; + u8 size; + bool global; + } atc; + + #define CMDQ_OP_PRI_RESP 0x41 + struct { + u32 sid; + u32 ssid; + u16 grpid; + enum pri_resp resp; + } pri; + + #define CMDQ_OP_CMD_SYNC 0x46 + struct { + u64 msiaddr; + } sync; + }; +}; + +struct arm_smmu_ll_queue { + union { + u64 val; + struct { + u32 prod; + u32 cons; + }; + struct { + atomic_t prod; + atomic_t cons; + } atomic; + u8 __pad[SMP_CACHE_BYTES]; + } ____cacheline_aligned_in_smp; + u32 max_n_shift; +}; + +struct arm_smmu_queue { + struct arm_smmu_ll_queue llq; + int irq; /* Wired interrupt */ + + __le64 *base; + dma_addr_t base_dma; + u64 q_base; + + size_t ent_dwords; + + u32 __iomem *prod_reg; + u32 __iomem *cons_reg; +}; + +struct arm_smmu_queue_poll { + ktime_t timeout; + unsigned int delay; + unsigned int spin_cnt; + bool wfe; +}; + +struct arm_smmu_cmdq { + struct arm_smmu_queue q; + atomic_long_t *valid_map; + atomic_t owner_prod; + atomic_t lock; +}; + +struct arm_smmu_cmdq_batch { + u64 cmds[CMDQ_BATCH_ENTRIES * CMDQ_ENT_DWORDS]; + int num; +}; + +struct arm_smmu_evtq { + struct arm_smmu_queue q; + u32 max_stalls; +}; + +struct arm_smmu_priq { + struct arm_smmu_queue q; +}; + +/* High-level stream table and context descriptor structures */ +struct arm_smmu_strtab_l1_desc { + u8 span; + + __le64 *l2ptr; + dma_addr_t l2ptr_dma; +}; + +struct arm_smmu_ctx_desc { + u16 asid; + u64 ttbr; + u64 tcr; + u64 mair; +}; + +struct arm_smmu_l1_ctx_desc { + __le64 *l2ptr; + dma_addr_t l2ptr_dma; +}; + +struct arm_smmu_ctx_desc_cfg { + __le64 *cdtab; + dma_addr_t cdtab_dma; + struct arm_smmu_l1_ctx_desc *l1_desc; + unsigned int num_l1_ents; +}; + +struct arm_smmu_s1_cfg { + struct arm_smmu_ctx_desc_cfg cdcfg; + struct arm_smmu_ctx_desc cd; + u8 s1fmt; + u8 s1cdmax; +}; + +struct arm_smmu_s2_cfg { + u16 vmid; + u64 vttbr; + u64 vtcr; +}; + +struct arm_smmu_strtab_cfg { + __le64 *strtab; + dma_addr_t strtab_dma; + struct arm_smmu_strtab_l1_desc *l1_desc; + unsigned int num_l1_ents; + + u64 strtab_base; + u32 strtab_base_cfg; +}; + +/* An SMMUv3 instance */ +struct arm_smmu_device { + struct device *dev; + void __iomem *base; + void __iomem *page1; + +#define ARM_SMMU_FEAT_2_LVL_STRTAB (1 << 0) +#define ARM_SMMU_FEAT_2_LVL_CDTAB (1 << 1) +#define ARM_SMMU_FEAT_TT_LE (1 << 2) +#define ARM_SMMU_FEAT_TT_BE (1 << 3) +#define ARM_SMMU_FEAT_PRI (1 << 4) +#define ARM_SMMU_FEAT_ATS (1 << 5) +#define ARM_SMMU_FEAT_SEV (1 << 6) +#define ARM_SMMU_FEAT_MSI (1 << 7) +#define ARM_SMMU_FEAT_COHERENCY (1 << 8) +#define ARM_SMMU_FEAT_TRANS_S1 (1 << 9) +#define ARM_SMMU_FEAT_TRANS_S2 (1 << 10) +#define ARM_SMMU_FEAT_STALLS (1 << 11) +#define ARM_SMMU_FEAT_HYP (1 << 12) +#define ARM_SMMU_FEAT_STALL_FORCE (1 << 13) +#define ARM_SMMU_FEAT_VAX (1 << 14) +#define ARM_SMMU_FEAT_RANGE_INV (1 << 15) + u32 features; + +#define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0) +#define ARM_SMMU_OPT_PAGE0_REGS_ONLY (1 << 1) +#define ARM_SMMU_OPT_MSIPOLL (1 << 2) + u32 options; + + struct arm_smmu_cmdq cmdq; + struct arm_smmu_evtq evtq; + struct arm_smmu_priq priq; + + int gerr_irq; + int combined_irq; + + unsigned long ias; /* IPA */ + unsigned long oas; /* PA */ + unsigned long pgsize_bitmap; + +#define ARM_SMMU_MAX_ASIDS (1 << 16) + unsigned int asid_bits; + +#define ARM_SMMU_MAX_VMIDS (1 << 16) + unsigned int vmid_bits; + DECLARE_BITMAP(vmid_map, ARM_SMMU_MAX_VMIDS); + + unsigned int ssid_bits; + unsigned int sid_bits; + + struct arm_smmu_strtab_cfg strtab_cfg; + + /* IOMMU core code handle */ + struct iommu_device iommu; +}; + +/* SMMU private data for each master */ +struct arm_smmu_master { + struct arm_smmu_device *smmu; + struct device *dev; + struct arm_smmu_domain *domain; + struct list_head domain_head; + u32 *sids; + unsigned int num_sids; + bool ats_enabled; + unsigned int ssid_bits; +}; + +/* SMMU private data for an IOMMU domain */ +enum arm_smmu_domain_stage { + ARM_SMMU_DOMAIN_S1 = 0, + ARM_SMMU_DOMAIN_S2, + ARM_SMMU_DOMAIN_NESTED, + ARM_SMMU_DOMAIN_BYPASS, +}; + +struct arm_smmu_domain { + struct arm_smmu_device *smmu; + struct mutex init_mutex; /* Protects smmu pointer */ + + struct io_pgtable_ops *pgtbl_ops; + bool non_strict; + atomic_t nr_ats_masters; + + enum arm_smmu_domain_stage stage; + union { + struct arm_smmu_s1_cfg s1_cfg; + struct arm_smmu_s2_cfg s2_cfg; + }; + + struct iommu_domain domain; + + struct list_head devices; + spinlock_t devices_lock; +}; + +#endif /* _ARM_SMMU_V3_H */ -- cgit v1.2.3 From 3f1ce8e85ee06dbe6a8b2e037e9b35f6b32e9ab3 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Fri, 18 Sep 2020 12:18:48 +0200 Subject: iommu/arm-smmu-v3: Share process page tables With Shared Virtual Addressing (SVA), we need to mirror CPU TTBR, TCR, MAIR and ASIDs in SMMU contexts. Each SMMU has a single ASID space split into two sets, shared and private. Shared ASIDs correspond to those obtained from the arch ASID allocator, and private ASIDs are used for "classic" map/unmap DMA. A possible conflict happens when trying to use a shared ASID that has already been allocated for private use by the SMMU driver. This will be addressed in a later patch by replacing the private ASID. At the moment we return -EBUSY. Each mm_struct shared with the SMMU will have a single context descriptor. Add a refcount to keep track of this. It will be protected by the global SVA lock. Introduce a new arm-smmu-v3-sva.c file and the CONFIG_ARM_SMMU_V3_SVA option to let users opt in SVA support. Signed-off-by: Jean-Philippe Brucker Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/20200918101852.582559-9-jean-philippe@linaro.org Signed-off-by: Will Deacon --- drivers/iommu/Kconfig | 10 ++ drivers/iommu/arm/arm-smmu-v3/Makefile | 5 +- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c | 123 ++++++++++++++++++++++++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 34 +++++-- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 8 ++ 5 files changed, 172 insertions(+), 8 deletions(-) create mode 100644 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c (limited to 'drivers/iommu/arm') diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index bef5d75e306b..82fa56238c96 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -308,6 +308,16 @@ config ARM_SMMU_V3 Say Y here if your system includes an IOMMU device implementing the ARM SMMUv3 architecture. +config ARM_SMMU_V3_SVA + bool "Shared Virtual Addressing support for the ARM SMMUv3" + depends on ARM_SMMU_V3 + help + Support for sharing process address spaces with devices using the + SMMUv3. + + Say Y here if your system supports SVA extensions such as PCIe PASID + and PRI. + config S390_IOMMU def_bool y if S390 && PCI depends on S390 && PCI diff --git a/drivers/iommu/arm/arm-smmu-v3/Makefile b/drivers/iommu/arm/arm-smmu-v3/Makefile index 569e24e9f162..54feb1ecccad 100644 --- a/drivers/iommu/arm/arm-smmu-v3/Makefile +++ b/drivers/iommu/arm/arm-smmu-v3/Makefile @@ -1,2 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o +obj-$(CONFIG_ARM_SMMU_V3) += arm_smmu_v3.o +arm_smmu_v3-objs-y += arm-smmu-v3.o +arm_smmu_v3-objs-$(CONFIG_ARM_SMMU_V3_SVA) += arm-smmu-v3-sva.o +arm_smmu_v3-objs := $(arm_smmu_v3-objs-y) diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c new file mode 100644 index 000000000000..6c1113059632 --- /dev/null +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c @@ -0,0 +1,123 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Implementation of the IOMMU SVA API for the ARM SMMUv3 + */ + +#include +#include +#include + +#include "arm-smmu-v3.h" +#include "../../io-pgtable-arm.h" + +static struct arm_smmu_ctx_desc * +arm_smmu_share_asid(struct mm_struct *mm, u16 asid) +{ + struct arm_smmu_ctx_desc *cd; + + cd = xa_load(&arm_smmu_asid_xa, asid); + if (!cd) + return NULL; + + if (cd->mm) { + if (WARN_ON(cd->mm != mm)) + return ERR_PTR(-EINVAL); + /* All devices bound to this mm use the same cd struct. */ + refcount_inc(&cd->refs); + return cd; + } + + /* Ouch, ASID is already in use for a private cd. */ + return ERR_PTR(-EBUSY); +} + +__maybe_unused +static struct arm_smmu_ctx_desc *arm_smmu_alloc_shared_cd(struct mm_struct *mm) +{ + u16 asid; + int err = 0; + u64 tcr, par, reg; + struct arm_smmu_ctx_desc *cd; + struct arm_smmu_ctx_desc *ret = NULL; + + asid = arm64_mm_context_get(mm); + if (!asid) + return ERR_PTR(-ESRCH); + + cd = kzalloc(sizeof(*cd), GFP_KERNEL); + if (!cd) { + err = -ENOMEM; + goto out_put_context; + } + + refcount_set(&cd->refs, 1); + + mutex_lock(&arm_smmu_asid_lock); + ret = arm_smmu_share_asid(mm, asid); + if (ret) { + mutex_unlock(&arm_smmu_asid_lock); + goto out_free_cd; + } + + err = xa_insert(&arm_smmu_asid_xa, asid, cd, GFP_KERNEL); + mutex_unlock(&arm_smmu_asid_lock); + + if (err) + goto out_free_asid; + + tcr = FIELD_PREP(CTXDESC_CD_0_TCR_T0SZ, 64ULL - vabits_actual) | + FIELD_PREP(CTXDESC_CD_0_TCR_IRGN0, ARM_LPAE_TCR_RGN_WBWA) | + FIELD_PREP(CTXDESC_CD_0_TCR_ORGN0, ARM_LPAE_TCR_RGN_WBWA) | + FIELD_PREP(CTXDESC_CD_0_TCR_SH0, ARM_LPAE_TCR_SH_IS) | + CTXDESC_CD_0_TCR_EPD1 | CTXDESC_CD_0_AA64; + + switch (PAGE_SIZE) { + case SZ_4K: + tcr |= FIELD_PREP(CTXDESC_CD_0_TCR_TG0, ARM_LPAE_TCR_TG0_4K); + break; + case SZ_16K: + tcr |= FIELD_PREP(CTXDESC_CD_0_TCR_TG0, ARM_LPAE_TCR_TG0_16K); + break; + case SZ_64K: + tcr |= FIELD_PREP(CTXDESC_CD_0_TCR_TG0, ARM_LPAE_TCR_TG0_64K); + break; + default: + WARN_ON(1); + err = -EINVAL; + goto out_free_asid; + } + + reg = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); + par = cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR0_PARANGE_SHIFT); + tcr |= FIELD_PREP(CTXDESC_CD_0_TCR_IPS, par); + + cd->ttbr = virt_to_phys(mm->pgd); + cd->tcr = tcr; + /* + * MAIR value is pretty much constant and global, so we can just get it + * from the current CPU register + */ + cd->mair = read_sysreg(mair_el1); + cd->asid = asid; + cd->mm = mm; + + return cd; + +out_free_asid: + arm_smmu_free_asid(cd); +out_free_cd: + kfree(cd); +out_put_context: + arm64_mm_context_put(mm); + return err < 0 ? ERR_PTR(err) : ret; +} + +__maybe_unused +static void arm_smmu_free_shared_cd(struct arm_smmu_ctx_desc *cd) +{ + if (arm_smmu_free_asid(cd)) { + /* Unpin ASID */ + arm64_mm_context_put(cd->mm); + kfree(cd); + } +} diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index b0d26c9f577d..e10648634ec2 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -73,7 +73,8 @@ struct arm_smmu_option_prop { const char *prop; }; -static DEFINE_XARRAY_ALLOC1(asid_xa); +DEFINE_XARRAY_ALLOC1(arm_smmu_asid_xa); +DEFINE_MUTEX(arm_smmu_asid_lock); static struct arm_smmu_option_prop arm_smmu_options[] = { { ARM_SMMU_OPT_SKIP_PREFETCH, "hisilicon,broken-prefetch-cmd" }, @@ -1013,7 +1014,8 @@ static int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, #ifdef __BIG_ENDIAN CTXDESC_CD_0_ENDI | #endif - CTXDESC_CD_0_R | CTXDESC_CD_0_A | CTXDESC_CD_0_ASET | + CTXDESC_CD_0_R | CTXDESC_CD_0_A | + (cd->mm ? 0 : CTXDESC_CD_0_ASET) | CTXDESC_CD_0_AA64 | FIELD_PREP(CTXDESC_CD_0_ASID, cd->asid) | CTXDESC_CD_0_V; @@ -1117,12 +1119,20 @@ static void arm_smmu_free_cd_tables(struct arm_smmu_domain *smmu_domain) cdcfg->cdtab = NULL; } -static void arm_smmu_free_asid(struct arm_smmu_ctx_desc *cd) +bool arm_smmu_free_asid(struct arm_smmu_ctx_desc *cd) { + bool free; + struct arm_smmu_ctx_desc *old_cd; + if (!cd->asid) - return; + return false; - xa_erase(&asid_xa, cd->asid); + free = refcount_dec_and_test(&cd->refs); + if (free) { + old_cd = xa_erase(&arm_smmu_asid_xa, cd->asid); + WARN_ON(old_cd != cd); + } + return free; } /* Stream table manipulation functions */ @@ -1810,9 +1820,12 @@ 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; + /* Prevent SVA from touching the CD while we're freeing it */ + mutex_lock(&arm_smmu_asid_lock); if (cfg->cdcfg.cdtab) arm_smmu_free_cd_tables(smmu_domain); arm_smmu_free_asid(&cfg->cd); + mutex_unlock(&arm_smmu_asid_lock); } else { struct arm_smmu_s2_cfg *cfg = &smmu_domain->s2_cfg; if (cfg->vmid) @@ -1832,10 +1845,14 @@ static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain, struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg; typeof(&pgtbl_cfg->arm_lpae_s1_cfg.tcr) tcr = &pgtbl_cfg->arm_lpae_s1_cfg.tcr; - ret = xa_alloc(&asid_xa, &asid, &cfg->cd, + refcount_set(&cfg->cd.refs, 1); + + /* Prevent SVA from modifying the ASID until it is written to the CD */ + mutex_lock(&arm_smmu_asid_lock); + ret = xa_alloc(&arm_smmu_asid_xa, &asid, &cfg->cd, XA_LIMIT(1, (1 << smmu->asid_bits) - 1), GFP_KERNEL); if (ret) - return ret; + goto out_unlock; cfg->s1cdmax = master->ssid_bits; @@ -1863,12 +1880,15 @@ static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain, if (ret) goto out_free_cd_tables; + mutex_unlock(&arm_smmu_asid_lock); return 0; out_free_cd_tables: arm_smmu_free_cd_tables(smmu_domain); out_free_asid: arm_smmu_free_asid(&cfg->cd); +out_unlock: + mutex_unlock(&arm_smmu_asid_lock); return ret; } diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h index c4c0c1345834..9aecd9fd3af7 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -540,6 +540,9 @@ struct arm_smmu_ctx_desc { u64 ttbr; u64 tcr; u64 mair; + + refcount_t refs; + struct mm_struct *mm; }; struct arm_smmu_l1_ctx_desc { @@ -673,4 +676,9 @@ struct arm_smmu_domain { spinlock_t devices_lock; }; +extern struct xarray arm_smmu_asid_xa; +extern struct mutex arm_smmu_asid_lock; + +bool arm_smmu_free_asid(struct arm_smmu_ctx_desc *cd); + #endif /* _ARM_SMMU_V3_H */ -- cgit v1.2.3 From 3e63033675c9b1e79b14655481a8c4ecaf23821f Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Fri, 18 Sep 2020 12:18:49 +0200 Subject: iommu/arm-smmu-v3: Seize private ASID The SMMU has a single ASID space, the union of shared and private ASID sets. This means that the SMMU driver competes with the arch allocator for ASIDs. Shared ASIDs are those of Linux processes, allocated by the arch, and contribute in broadcast TLB maintenance. Private ASIDs are allocated by the SMMU driver and used for "classic" map/unmap DMA. They require command-queue TLB invalidations. When we pin down an mm_context and get an ASID that is already in use by the SMMU, it belongs to a private context. We used to simply abort the bind, but this is unfair to users that would be unable to bind a few seemingly random processes. Try to allocate a new private ASID for the context, and make the old ASID shared. Signed-off-by: Jean-Philippe Brucker Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/20200918101852.582559-10-jean-philippe@linaro.org Signed-off-by: Will Deacon --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c | 35 +++++++++++++++++++++++-- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 34 +++++++++++++++--------- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 3 +++ 3 files changed, 57 insertions(+), 15 deletions(-) (limited to 'drivers/iommu/arm') diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c index 6c1113059632..ef3fcfa72187 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c @@ -10,10 +10,18 @@ #include "arm-smmu-v3.h" #include "../../io-pgtable-arm.h" +/* + * Check if the CPU ASID is available on the SMMU side. If a private context + * descriptor is using it, try to replace it. + */ static struct arm_smmu_ctx_desc * arm_smmu_share_asid(struct mm_struct *mm, u16 asid) { + int ret; + u32 new_asid; struct arm_smmu_ctx_desc *cd; + struct arm_smmu_device *smmu; + struct arm_smmu_domain *smmu_domain; cd = xa_load(&arm_smmu_asid_xa, asid); if (!cd) @@ -27,8 +35,31 @@ arm_smmu_share_asid(struct mm_struct *mm, u16 asid) return cd; } - /* Ouch, ASID is already in use for a private cd. */ - return ERR_PTR(-EBUSY); + smmu_domain = container_of(cd, struct arm_smmu_domain, s1_cfg.cd); + smmu = smmu_domain->smmu; + + ret = xa_alloc(&arm_smmu_asid_xa, &new_asid, cd, + XA_LIMIT(1, (1 << smmu->asid_bits) - 1), GFP_KERNEL); + if (ret) + return ERR_PTR(-ENOSPC); + /* + * Race with unmap: TLB invalidations will start targeting the new ASID, + * which isn't assigned yet. We'll do an invalidate-all on the old ASID + * later, so it doesn't matter. + */ + cd->asid = new_asid; + /* + * Update ASID and invalidate CD in all associated masters. There will + * be some overlap between use of both ASIDs, until we invalidate the + * TLB. + */ + arm_smmu_write_ctx_desc(smmu_domain, 0, cd); + + /* Invalidate TLB entries previously associated with that context */ + arm_smmu_tlb_inv_asid(smmu, asid); + + xa_erase(&arm_smmu_asid_xa, asid); + return NULL; } __maybe_unused diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index e10648634ec2..14108f1cd2ea 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -882,6 +882,17 @@ static int arm_smmu_cmdq_batch_submit(struct arm_smmu_device *smmu, } /* Context descriptor manipulation functions */ +void arm_smmu_tlb_inv_asid(struct arm_smmu_device *smmu, u16 asid) +{ + struct arm_smmu_cmdq_ent cmd = { + .opcode = CMDQ_OP_TLBI_NH_ASID, + .tlbi.asid = asid, + }; + + arm_smmu_cmdq_issue_cmd(smmu, &cmd); + arm_smmu_cmdq_issue_sync(smmu); +} + static void arm_smmu_sync_cd(struct arm_smmu_domain *smmu_domain, int ssid, bool leaf) { @@ -962,8 +973,8 @@ static __le64 *arm_smmu_get_cd_ptr(struct arm_smmu_domain *smmu_domain, return l1_desc->l2ptr + idx * CTXDESC_CD_DWORDS; } -static int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, - int ssid, struct arm_smmu_ctx_desc *cd) +int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid, + struct arm_smmu_ctx_desc *cd) { /* * This function handles the following cases: @@ -1619,15 +1630,6 @@ static void arm_smmu_tlb_inv_context(void *cookie) struct arm_smmu_device *smmu = smmu_domain->smmu; struct arm_smmu_cmdq_ent cmd; - if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) { - cmd.opcode = CMDQ_OP_TLBI_NH_ASID; - cmd.tlbi.asid = smmu_domain->s1_cfg.cd.asid; - cmd.tlbi.vmid = 0; - } else { - cmd.opcode = CMDQ_OP_TLBI_S12_VMALL; - cmd.tlbi.vmid = smmu_domain->s2_cfg.vmid; - } - /* * NOTE: when io-pgtable is in non-strict mode, we may get here with * PTEs previously cleared by unmaps on the current CPU not yet visible @@ -1635,8 +1637,14 @@ static void arm_smmu_tlb_inv_context(void *cookie) * insertion to guarantee those are observed before the TLBI. Do be * careful, 007. */ - arm_smmu_cmdq_issue_cmd(smmu, &cmd); - arm_smmu_cmdq_issue_sync(smmu); + if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) { + arm_smmu_tlb_inv_asid(smmu, smmu_domain->s1_cfg.cd.asid); + } else { + cmd.opcode = CMDQ_OP_TLBI_S12_VMALL; + cmd.tlbi.vmid = smmu_domain->s2_cfg.vmid; + arm_smmu_cmdq_issue_cmd(smmu, &cmd); + arm_smmu_cmdq_issue_sync(smmu); + } arm_smmu_atc_inv_domain(smmu_domain, 0, 0, 0); } diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h index 9aecd9fd3af7..1529714ce006 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -679,6 +679,9 @@ struct arm_smmu_domain { extern struct xarray arm_smmu_asid_xa; extern struct mutex arm_smmu_asid_lock; +int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid, + struct arm_smmu_ctx_desc *cd); +void arm_smmu_tlb_inv_asid(struct arm_smmu_device *smmu, u16 asid); bool arm_smmu_free_asid(struct arm_smmu_ctx_desc *cd); #endif /* _ARM_SMMU_V3_H */ -- cgit v1.2.3 From d744f9e6c222c8086376bc56c86e4380595350bd Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Fri, 18 Sep 2020 12:18:50 +0200 Subject: iommu/arm-smmu-v3: Check for SVA features Aggregate all sanity-checks for sharing CPU page tables with the SMMU under a single ARM_SMMU_FEAT_SVA bit. For PCIe SVA, users also need to check FEAT_ATS and FEAT_PRI. For platform SVA, they will have to check FEAT_STALLS. Introduce ARM_SMMU_FEAT_BTM (Broadcast TLB Maintenance), but don't enable it at the moment. Since the entire VMID space is shared with the CPU, enabling DVM (by clearing SMMU_CR2.PTM) could result in over-invalidation and affect performance of stage-2 mappings. Signed-off-by: Jean-Philippe Brucker Reviewed-by: Jonathan Cameron Cc: Suzuki K Poulose Link: https://lore.kernel.org/r/20200918101852.582559-11-jean-philippe@linaro.org Signed-off-by: Will Deacon --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c | 45 +++++++++++++++++++++++++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 3 ++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 10 ++++++ 3 files changed, 58 insertions(+) (limited to 'drivers/iommu/arm') diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c index ef3fcfa72187..cb94c0924196 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c @@ -152,3 +152,48 @@ static void arm_smmu_free_shared_cd(struct arm_smmu_ctx_desc *cd) kfree(cd); } } + +bool arm_smmu_sva_supported(struct arm_smmu_device *smmu) +{ + unsigned long reg, fld; + unsigned long oas; + unsigned long asid_bits; + u32 feat_mask = ARM_SMMU_FEAT_BTM | ARM_SMMU_FEAT_COHERENCY; + + if (vabits_actual == 52) + feat_mask |= ARM_SMMU_FEAT_VAX; + + if ((smmu->features & feat_mask) != feat_mask) + return false; + + if (!(smmu->pgsize_bitmap & PAGE_SIZE)) + return false; + + /* + * Get the smallest PA size of all CPUs (sanitized by cpufeature). We're + * not even pretending to support AArch32 here. Abort if the MMU outputs + * addresses larger than what we support. + */ + reg = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); + fld = cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR0_PARANGE_SHIFT); + oas = id_aa64mmfr0_parange_to_phys_shift(fld); + if (smmu->oas < oas) + return false; + + /* We can support bigger ASIDs than the CPU, but not smaller */ + fld = cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR0_ASID_SHIFT); + asid_bits = fld ? 16 : 8; + if (smmu->asid_bits < asid_bits) + return false; + + /* + * See max_pinned_asids in arch/arm64/mm/context.c. The following is + * generally the maximum number of bindable processes. + */ + if (arm64_kernel_unmapped_at_el0()) + asid_bits--; + dev_dbg(smmu->dev, "%d shared contexts\n", (1 << asid_bits) - + num_possible_cpus() - 2); + + return true; +} diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index 14108f1cd2ea..cc02d6d815e6 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -3274,6 +3274,9 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) smmu->ias = max(smmu->ias, smmu->oas); + if (arm_smmu_sva_supported(smmu)) + smmu->features |= ARM_SMMU_FEAT_SVA; + dev_info(smmu->dev, "ias %lu-bit, oas %lu-bit (features 0x%08x)\n", smmu->ias, smmu->oas, smmu->features); return 0; diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h index 1529714ce006..454a935de445 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -602,6 +602,8 @@ struct arm_smmu_device { #define ARM_SMMU_FEAT_STALL_FORCE (1 << 13) #define ARM_SMMU_FEAT_VAX (1 << 14) #define ARM_SMMU_FEAT_RANGE_INV (1 << 15) +#define ARM_SMMU_FEAT_BTM (1 << 16) +#define ARM_SMMU_FEAT_SVA (1 << 17) u32 features; #define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0) @@ -684,4 +686,12 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid, void arm_smmu_tlb_inv_asid(struct arm_smmu_device *smmu, u16 asid); bool arm_smmu_free_asid(struct arm_smmu_ctx_desc *cd); +#ifdef CONFIG_ARM_SMMU_V3_SVA +bool arm_smmu_sva_supported(struct arm_smmu_device *smmu); +#else /* CONFIG_ARM_SMMU_V3_SVA */ +static inline bool arm_smmu_sva_supported(struct arm_smmu_device *smmu) +{ + return false; +} +#endif /* CONFIG_ARM_SMMU_V3_SVA */ #endif /* _ARM_SMMU_V3_H */ -- cgit v1.2.3 From f534d98b9d27053279da015d0187a09e3a090ccd Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Fri, 18 Sep 2020 12:18:51 +0200 Subject: iommu/arm-smmu-v3: Add SVA device feature Implement the IOMMU device feature callbacks to support the SVA feature. At the moment dev_has_feat() returns false since I/O Page Faults and BTM aren't yet implemented. Signed-off-by: Jean-Philippe Brucker Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/20200918101852.582559-12-jean-philippe@linaro.org Signed-off-by: Will Deacon --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c | 49 +++++++++++++++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 79 +++++++++++++++++++++++++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 26 ++++++++ 3 files changed, 154 insertions(+) (limited to 'drivers/iommu/arm') diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c index cb94c0924196..9255c9600fb8 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c @@ -10,6 +10,8 @@ #include "arm-smmu-v3.h" #include "../../io-pgtable-arm.h" +static DEFINE_MUTEX(sva_lock); + /* * Check if the CPU ASID is available on the SMMU side. If a private context * descriptor is using it, try to replace it. @@ -197,3 +199,50 @@ bool arm_smmu_sva_supported(struct arm_smmu_device *smmu) return true; } + +static bool arm_smmu_iopf_supported(struct arm_smmu_master *master) +{ + return false; +} + +bool arm_smmu_master_sva_supported(struct arm_smmu_master *master) +{ + if (!(master->smmu->features & ARM_SMMU_FEAT_SVA)) + return false; + + /* SSID and IOPF support are mandatory for the moment */ + return master->ssid_bits && arm_smmu_iopf_supported(master); +} + +bool arm_smmu_master_sva_enabled(struct arm_smmu_master *master) +{ + bool enabled; + + mutex_lock(&sva_lock); + enabled = master->sva_enabled; + mutex_unlock(&sva_lock); + return enabled; +} + +int arm_smmu_master_enable_sva(struct arm_smmu_master *master) +{ + mutex_lock(&sva_lock); + master->sva_enabled = true; + mutex_unlock(&sva_lock); + + return 0; +} + +int arm_smmu_master_disable_sva(struct arm_smmu_master *master) +{ + mutex_lock(&sva_lock); + if (!list_empty(&master->bonds)) { + dev_err(master->dev, "cannot disable SVA, device is bound\n"); + mutex_unlock(&sva_lock); + return -EBUSY; + } + master->sva_enabled = false; + mutex_unlock(&sva_lock); + + return 0; +} diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index cc02d6d815e6..e634bbe60573 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -2176,6 +2176,16 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) master = dev_iommu_priv_get(dev); smmu = master->smmu; + /* + * Checking that SVA is disabled ensures that this device isn't bound to + * any mm, and can be safely detached from its old domain. Bonds cannot + * be removed concurrently since we're holding the group mutex. + */ + if (arm_smmu_master_sva_enabled(master)) { + dev_err(dev, "cannot attach - SVA enabled\n"); + return -EBUSY; + } + arm_smmu_detach_dev(master); mutex_lock(&smmu_domain->init_mutex); @@ -2323,6 +2333,7 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev) master->smmu = smmu; master->sids = fwspec->ids; master->num_sids = fwspec->num_ids; + INIT_LIST_HEAD(&master->bonds); dev_iommu_priv_set(dev, master); /* Check the SIDs are in range of the SMMU and our stream table */ @@ -2375,6 +2386,7 @@ static void arm_smmu_release_device(struct device *dev) return; master = dev_iommu_priv_get(dev); + WARN_ON(arm_smmu_master_sva_enabled(master)); arm_smmu_detach_dev(master); arm_smmu_disable_pasid(master); kfree(master); @@ -2492,6 +2504,69 @@ static void arm_smmu_get_resv_regions(struct device *dev, iommu_dma_get_resv_regions(dev, head); } +static bool arm_smmu_dev_has_feature(struct device *dev, + enum iommu_dev_features feat) +{ + struct arm_smmu_master *master = dev_iommu_priv_get(dev); + + if (!master) + return false; + + switch (feat) { + case IOMMU_DEV_FEAT_SVA: + return arm_smmu_master_sva_supported(master); + default: + return false; + } +} + +static bool arm_smmu_dev_feature_enabled(struct device *dev, + enum iommu_dev_features feat) +{ + struct arm_smmu_master *master = dev_iommu_priv_get(dev); + + if (!master) + return false; + + switch (feat) { + case IOMMU_DEV_FEAT_SVA: + return arm_smmu_master_sva_enabled(master); + default: + return false; + } +} + +static int arm_smmu_dev_enable_feature(struct device *dev, + enum iommu_dev_features feat) +{ + if (!arm_smmu_dev_has_feature(dev, feat)) + return -ENODEV; + + if (arm_smmu_dev_feature_enabled(dev, feat)) + return -EBUSY; + + switch (feat) { + case IOMMU_DEV_FEAT_SVA: + return arm_smmu_master_enable_sva(dev_iommu_priv_get(dev)); + default: + return -EINVAL; + } +} + +static int arm_smmu_dev_disable_feature(struct device *dev, + enum iommu_dev_features feat) +{ + if (!arm_smmu_dev_feature_enabled(dev, feat)) + return -EINVAL; + + switch (feat) { + case IOMMU_DEV_FEAT_SVA: + return arm_smmu_master_disable_sva(dev_iommu_priv_get(dev)); + default: + return -EINVAL; + } +} + static struct iommu_ops arm_smmu_ops = { .capable = arm_smmu_capable, .domain_alloc = arm_smmu_domain_alloc, @@ -2510,6 +2585,10 @@ static struct iommu_ops arm_smmu_ops = { .of_xlate = arm_smmu_of_xlate, .get_resv_regions = arm_smmu_get_resv_regions, .put_resv_regions = generic_iommu_put_resv_regions, + .dev_has_feat = arm_smmu_dev_has_feature, + .dev_feat_enabled = arm_smmu_dev_feature_enabled, + .dev_enable_feat = arm_smmu_dev_enable_feature, + .dev_disable_feat = arm_smmu_dev_disable_feature, .pgsize_bitmap = -1UL, /* Restricted during device attach */ }; diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h index 454a935de445..d4b7f40ccb02 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -647,6 +647,8 @@ struct arm_smmu_master { u32 *sids; unsigned int num_sids; bool ats_enabled; + bool sva_enabled; + struct list_head bonds; unsigned int ssid_bits; }; @@ -688,10 +690,34 @@ bool arm_smmu_free_asid(struct arm_smmu_ctx_desc *cd); #ifdef CONFIG_ARM_SMMU_V3_SVA bool arm_smmu_sva_supported(struct arm_smmu_device *smmu); +bool arm_smmu_master_sva_supported(struct arm_smmu_master *master); +bool arm_smmu_master_sva_enabled(struct arm_smmu_master *master); +int arm_smmu_master_enable_sva(struct arm_smmu_master *master); +int arm_smmu_master_disable_sva(struct arm_smmu_master *master); #else /* CONFIG_ARM_SMMU_V3_SVA */ static inline bool arm_smmu_sva_supported(struct arm_smmu_device *smmu) { return false; } + +static inline bool arm_smmu_master_sva_supported(struct arm_smmu_master *master) +{ + return false; +} + +static inline bool arm_smmu_master_sva_enabled(struct arm_smmu_master *master) +{ + return false; +} + +static inline int arm_smmu_master_enable_sva(struct arm_smmu_master *master) +{ + return -ENODEV; +} + +static inline int arm_smmu_master_disable_sva(struct arm_smmu_master *master) +{ + return -ENODEV; +} #endif /* CONFIG_ARM_SMMU_V3_SVA */ #endif /* _ARM_SMMU_V3_H */ -- cgit v1.2.3 From e2eae09939a89e0994f7965ba3c676a5eac8b4b0 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Tue, 29 Sep 2020 09:40:37 +0800 Subject: iommu/qcom: add missing put_device() call in qcom_iommu_of_xlate() if of_find_device_by_node() succeed, qcom_iommu_of_xlate() doesn't have a corresponding put_device(). Thus add put_device() to fix the exception handling for this function implementation. Fixes: 0ae349a0f33f ("iommu/qcom: Add qcom_iommu") Acked-by: Rob Clark Signed-off-by: Yu Kuai Link: https://lore.kernel.org/r/20200929014037.2436663-1-yukuai3@huawei.com Signed-off-by: Will Deacon --- drivers/iommu/arm/arm-smmu/qcom_iommu.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'drivers/iommu/arm') diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c index af6bec3ace00..ef3dd32aa6d9 100644 --- a/drivers/iommu/arm/arm-smmu/qcom_iommu.c +++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c @@ -584,8 +584,10 @@ static int qcom_iommu_of_xlate(struct device *dev, struct of_phandle_args *args) * index into qcom_iommu->ctxs: */ if (WARN_ON(asid < 1) || - WARN_ON(asid > qcom_iommu->num_ctxs)) + WARN_ON(asid > qcom_iommu->num_ctxs)) { + put_device(&iommu_pdev->dev); return -EINVAL; + } if (!dev_iommu_priv_get(dev)) { dev_iommu_priv_set(dev, qcom_iommu); @@ -594,8 +596,10 @@ static int qcom_iommu_of_xlate(struct device *dev, struct of_phandle_args *args) * multiple different iommu devices. Multiple context * banks are ok, but multiple devices are not: */ - if (WARN_ON(qcom_iommu != dev_iommu_priv_get(dev))) + if (WARN_ON(qcom_iommu != dev_iommu_priv_get(dev))) { + put_device(&iommu_pdev->dev); return -EINVAL; + } } return iommu_fwspec_add_ids(dev, &asid, 1); -- cgit v1.2.3