From 954a03be033c7cef80ddc232e7cbdb17df735663 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Fri, 1 Mar 2019 11:20:17 -0800 Subject: iommu/arm-smmu: Break insecure users by disabling bypass by default If you're bisecting why your peripherals stopped working, it's probably this CL. Specifically if you see this in your dmesg: Unexpected global fault, this could be serious ...then it's almost certainly this CL. Running your IOMMU-enabled peripherals with the IOMMU in bypass mode is insecure and effectively disables the protection they provide. There are few reasons to allow unmatched stream bypass, and even fewer good ones. This patch starts the transition over to make it much harder to run your system insecurely. Expected steps: 1. By default disable bypass (so anyone insecure will notice) but make it easy for someone to re-enable bypass with just a KConfig change. That's this patch. 2. After people have had a little time to come to grips with the fact that they need to set their IOMMUs properly and have had time to dig into how to do this, the KConfig will be eliminated and bypass will simply be disabled. Folks who are truly upset and still haven't fixed their system can either figure out how to add 'arm-smmu.disable_bypass=n' to their command line or revert the patch in their own private kernel. Of course these folks will be less secure. Suggested-by: Robin Murphy Reviewed-by: Marc Gonzalez Tested-by: Marc Gonzalez Signed-off-by: Douglas Anderson Signed-off-by: Will Deacon --- drivers/iommu/Kconfig | 25 +++++++++++++++++++++++++ drivers/iommu/arm-smmu.c | 3 ++- 2 files changed, 27 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 6f07f3b21816..15b831113ded 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -359,6 +359,31 @@ config ARM_SMMU Say Y here if your SoC includes an IOMMU device implementing the ARM SMMU architecture. +config ARM_SMMU_DISABLE_BYPASS_BY_DEFAULT + bool "Default to disabling bypass on ARM SMMU v1 and v2" + depends on ARM_SMMU + default y + help + Say Y here to (by default) 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. + + Any old kernels that existed before this KConfig was + introduced would default to _allowing_ bypass (AKA the + equivalent of NO for this config). However the default for + this option is YES because the old behavior is insecure. + + There are few reasons to allow unmatched stream bypass, and + even fewer good ones. If saying YES here breaks your board + you should work on fixing your board. This KConfig option + is expected to be removed in the future and we'll simply + hardcode the bypass disable in the code. + + NOTE: the kernel command line parameter + 'arm-smmu.disable_bypass' will continue to override this + config. + config ARM_SMMU_V3 bool "ARM Ltd. System MMU Version 3 (SMMUv3) Support" depends on ARM64 diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 045d93884164..930c07635956 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -110,7 +110,8 @@ static int force_stage; module_param(force_stage, int, S_IRUGO); MODULE_PARM_DESC(force_stage, "Force SMMU mappings to be installed at a particular stage of translation. A value of '1' or '2' forces the corresponding stage. All other values are ignored (i.e. no stage is forced). Note that selecting a specific stage will disable support for nested translation."); -static bool disable_bypass; +static bool disable_bypass = + IS_ENABLED(CONFIG_ARM_SMMU_DISABLE_BYPASS_BY_DEFAULT); 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."); -- cgit v1.2.3-59-g8ed1b From 6e1ffbb7c2ab80df54ecbb01cf3d2c64aafed74a Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Wed, 17 Apr 2019 19:24:40 +0100 Subject: PCI: Move ATS declarations outside of CONFIG_PCI At the moment, the ATS functions are only defined when CONFIG_PCI is enabled. Since we're about to use them in the Arm SMMUv3 driver, which could be built with CONFIG_PCI disabled, and they are already guarded by CONFIG_PCI_ATS which depends on CONFIG_PCI, move the definitions outside of CONFIG_PCI. Acked-by: Bjorn Helgaas Signed-off-by: Jean-Philippe Brucker Signed-off-by: Will Deacon --- include/linux/pci.h | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) diff --git a/include/linux/pci.h b/include/linux/pci.h index 77448215ef5b..169c6a18d0b0 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1521,21 +1521,6 @@ static inline void pcie_ecrc_get_policy(char *str) { } bool pci_ats_disabled(void); -#ifdef CONFIG_PCI_ATS -/* Address Translation Service */ -void pci_ats_init(struct pci_dev *dev); -int pci_enable_ats(struct pci_dev *dev, int ps); -void pci_disable_ats(struct pci_dev *dev); -int pci_ats_queue_depth(struct pci_dev *dev); -int pci_ats_page_aligned(struct pci_dev *dev); -#else -static inline void pci_ats_init(struct pci_dev *d) { } -static inline int pci_enable_ats(struct pci_dev *d, int ps) { return -ENODEV; } -static inline void pci_disable_ats(struct pci_dev *d) { } -static inline int pci_ats_queue_depth(struct pci_dev *d) { return -ENODEV; } -static inline int pci_ats_page_aligned(struct pci_dev *dev) { return 0; } -#endif - #ifdef CONFIG_PCIE_PTM int pci_enable_ptm(struct pci_dev *dev, u8 *granularity); #else @@ -1730,6 +1715,21 @@ static inline const struct pci_device_id *pci_match_id(const struct pci_device_i { return NULL; } #endif /* CONFIG_PCI */ +#ifdef CONFIG_PCI_ATS +/* Address Translation Service */ +void pci_ats_init(struct pci_dev *dev); +int pci_enable_ats(struct pci_dev *dev, int ps); +void pci_disable_ats(struct pci_dev *dev); +int pci_ats_queue_depth(struct pci_dev *dev); +int pci_ats_page_aligned(struct pci_dev *dev); +#else +static inline void pci_ats_init(struct pci_dev *d) { } +static inline int pci_enable_ats(struct pci_dev *d, int ps) { return -ENODEV; } +static inline void pci_disable_ats(struct pci_dev *d) { } +static inline int pci_ats_queue_depth(struct pci_dev *d) { return -ENODEV; } +static inline int pci_ats_page_aligned(struct pci_dev *dev) { return 0; } +#endif + /* Include architecture-dependent settings and functions */ #include -- cgit v1.2.3-59-g8ed1b From b9ae16d80a357c88fcb7ff6831cfdc196f0a34dd Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Wed, 17 Apr 2019 19:24:41 +0100 Subject: PCI: Add a stub for pci_ats_disabled() Currently pci_ats_disabled() is only defined when CONFIG_PCI is enabled. Since we're about to use the function in the Arm SMMUv3 driver, which could be built with CONFIG_PCI disabled, add a definition of pci_ats_disabled() for !CONFIG_PCI. Acked-by: Bjorn Helgaas Signed-off-by: Jean-Philippe Brucker Signed-off-by: Will Deacon --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/pci.h b/include/linux/pci.h index 169c6a18d0b0..61d7cd888bad 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1713,6 +1713,7 @@ static inline int pci_irqd_intx_xlate(struct irq_domain *d, static inline const struct pci_device_id *pci_match_id(const struct pci_device_id *ids, struct pci_dev *dev) { return NULL; } +static inline bool pci_ats_disabled(void) { return true; } #endif /* CONFIG_PCI */ #ifdef CONFIG_PCI_ATS -- cgit v1.2.3-59-g8ed1b From 5702ee24182f9b3e33476b74b5c92a4f913ad9bd Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Wed, 17 Apr 2019 19:24:42 +0100 Subject: ACPI/IORT: Check ATS capability in root complex nodes Root complex node in IORT has a bit telling whether it supports ATS or not. Store this bit in the IOMMU fwspec when setting up a device, so it can be accessed later by an IOMMU driver. In the future we'll probably want to store this bit at the host bridge or SMMU rather than in each endpoint. Acked-by: Lorenzo Pieralisi Signed-off-by: Jean-Philippe Brucker Signed-off-by: Will Deacon --- drivers/acpi/arm64/iort.c | 11 +++++++++++ include/linux/iommu.h | 4 ++++ 2 files changed, 15 insertions(+) diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index e48894e002ba..4000902e57f0 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -1028,6 +1028,14 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size) dev_dbg(dev, "dma_pfn_offset(%#08llx)\n", offset); } +static bool iort_pci_rc_supports_ats(struct acpi_iort_node *node) +{ + struct acpi_iort_root_complex *pci_rc; + + pci_rc = (struct acpi_iort_root_complex *)node->node_data; + return pci_rc->ats_attribute & ACPI_IORT_ATS_SUPPORTED; +} + /** * iort_iommu_configure - Set-up IOMMU configuration for a device. * @@ -1063,6 +1071,9 @@ const struct iommu_ops *iort_iommu_configure(struct device *dev) info.node = node; err = pci_for_each_dma_alias(to_pci_dev(dev), iort_pci_iommu_init, &info); + + if (!err && iort_pci_rc_supports_ats(node)) + dev->iommu_fwspec->flags |= IOMMU_FWSPEC_PCI_RC_ATS; } else { int i = 0; diff --git a/include/linux/iommu.h b/include/linux/iommu.h index ffbbc7e39cee..6c1b4c900191 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -392,10 +392,14 @@ struct iommu_fwspec { const struct iommu_ops *ops; struct fwnode_handle *iommu_fwnode; void *iommu_priv; + u32 flags; unsigned int num_ids; u32 ids[1]; }; +/* ATS is supported */ +#define IOMMU_FWSPEC_PCI_RC_ATS (1 << 0) + int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode, const struct iommu_ops *ops); void iommu_fwspec_free(struct device *dev); -- cgit v1.2.3-59-g8ed1b From b54f4260c7df878c231e7b3a3687636d74d83c8f Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Wed, 17 Apr 2019 19:24:43 +0100 Subject: iommu/arm-smmu-v3: Rename arm_smmu_master_data to arm_smmu_master The arm_smmu_master_data structure already represents more than just the firmware data associated to a master, and will be used extensively to represent a device's state when implementing more SMMU features. Rename the structure to arm_smmu_master. Signed-off-by: Jean-Philippe Brucker Signed-off-by: Will Deacon --- drivers/iommu/arm-smmu-v3.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index d3880010c6cf..50cb037f3d8a 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -591,7 +591,7 @@ struct arm_smmu_device { }; /* SMMU private data for each master */ -struct arm_smmu_master_data { +struct arm_smmu_master { struct arm_smmu_device *smmu; struct arm_smmu_strtab_ent ste; }; @@ -1691,7 +1691,7 @@ static __le64 *arm_smmu_get_step_for_sid(struct arm_smmu_device *smmu, u32 sid) static void arm_smmu_install_ste_for_dev(struct iommu_fwspec *fwspec) { int i, j; - struct arm_smmu_master_data *master = fwspec->iommu_priv; + struct arm_smmu_master *master = fwspec->iommu_priv; struct arm_smmu_device *smmu = master->smmu; for (i = 0; i < fwspec->num_ids; ++i) { @@ -1712,7 +1712,7 @@ static void arm_smmu_install_ste_for_dev(struct iommu_fwspec *fwspec) static void arm_smmu_detach_dev(struct device *dev) { struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); - struct arm_smmu_master_data *master = fwspec->iommu_priv; + struct arm_smmu_master *master = fwspec->iommu_priv; master->ste.assigned = false; arm_smmu_install_ste_for_dev(fwspec); @@ -1724,7 +1724,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); struct arm_smmu_device *smmu; struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); - struct arm_smmu_master_data *master; + struct arm_smmu_master *master; struct arm_smmu_strtab_ent *ste; if (!fwspec) @@ -1860,7 +1860,7 @@ static int arm_smmu_add_device(struct device *dev) { int i, ret; struct arm_smmu_device *smmu; - struct arm_smmu_master_data *master; + struct arm_smmu_master *master; struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); struct iommu_group *group; @@ -1913,7 +1913,7 @@ static int arm_smmu_add_device(struct device *dev) static void arm_smmu_remove_device(struct device *dev) { struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); - struct arm_smmu_master_data *master; + struct arm_smmu_master *master; struct arm_smmu_device *smmu; if (!fwspec || fwspec->ops != &arm_smmu_ops) -- cgit v1.2.3-59-g8ed1b From bcecaee434733d98a9e7a45834f7439b64142eb3 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Wed, 17 Apr 2019 19:24:44 +0100 Subject: iommu/arm-smmu-v3: Store SteamIDs in master Simplify the attach/detach code a bit by keeping a pointer to the stream IDs in the master structure. Although not completely obvious here, it does make the subsequent support for ATS, PRI and PASID a bit simpler. Signed-off-by: Jean-Philippe Brucker Signed-off-by: Will Deacon --- drivers/iommu/arm-smmu-v3.c | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 50cb037f3d8a..25ba546cae7f 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -594,6 +594,8 @@ struct arm_smmu_device { struct arm_smmu_master { struct arm_smmu_device *smmu; struct arm_smmu_strtab_ent ste; + u32 *sids; + unsigned int num_sids; }; /* SMMU private data for an IOMMU domain */ @@ -1688,19 +1690,18 @@ static __le64 *arm_smmu_get_step_for_sid(struct arm_smmu_device *smmu, u32 sid) return step; } -static void arm_smmu_install_ste_for_dev(struct iommu_fwspec *fwspec) +static void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master) { int i, j; - struct arm_smmu_master *master = fwspec->iommu_priv; struct arm_smmu_device *smmu = master->smmu; - for (i = 0; i < fwspec->num_ids; ++i) { - u32 sid = fwspec->ids[i]; + for (i = 0; i < master->num_sids; ++i) { + u32 sid = master->sids[i]; __le64 *step = arm_smmu_get_step_for_sid(smmu, sid); /* Bridged PCI devices may end up with duplicated IDs */ for (j = 0; j < i; j++) - if (fwspec->ids[j] == sid) + if (master->sids[j] == sid) break; if (j < i) continue; @@ -1709,13 +1710,10 @@ static void arm_smmu_install_ste_for_dev(struct iommu_fwspec *fwspec) } } -static void arm_smmu_detach_dev(struct device *dev) +static void arm_smmu_detach_dev(struct arm_smmu_master *master) { - struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); - struct arm_smmu_master *master = fwspec->iommu_priv; - master->ste.assigned = false; - arm_smmu_install_ste_for_dev(fwspec); + arm_smmu_install_ste_for_dev(master); } static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) @@ -1736,7 +1734,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) /* Already attached to a different domain? */ if (ste->assigned) - arm_smmu_detach_dev(dev); + arm_smmu_detach_dev(master); mutex_lock(&smmu_domain->init_mutex); @@ -1770,7 +1768,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) ste->s2_cfg = &smmu_domain->s2_cfg; } - arm_smmu_install_ste_for_dev(fwspec); + arm_smmu_install_ste_for_dev(master); out_unlock: mutex_unlock(&smmu_domain->init_mutex); return ret; @@ -1883,12 +1881,14 @@ static int arm_smmu_add_device(struct device *dev) return -ENOMEM; master->smmu = smmu; + master->sids = fwspec->ids; + master->num_sids = fwspec->num_ids; fwspec->iommu_priv = master; } /* Check the SIDs are in range of the SMMU and our stream table */ - for (i = 0; i < fwspec->num_ids; i++) { - u32 sid = fwspec->ids[i]; + for (i = 0; i < master->num_sids; i++) { + u32 sid = master->sids[i]; if (!arm_smmu_sid_in_range(smmu, sid)) return -ERANGE; @@ -1922,7 +1922,7 @@ static void arm_smmu_remove_device(struct device *dev) master = fwspec->iommu_priv; smmu = master->smmu; if (master && master->ste.assigned) - arm_smmu_detach_dev(dev); + arm_smmu_detach_dev(master); iommu_group_remove_device(dev); iommu_device_unlink(&smmu->iommu, dev); kfree(master); -- cgit v1.2.3-59-g8ed1b From 8be39a1a04c1491a6a408c1549dfd4e191f3a287 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Wed, 17 Apr 2019 19:24:45 +0100 Subject: iommu/arm-smmu-v3: Add a master->domain pointer As we're going to track domain-master links more closely for ATS and CD invalidation, add pointer to the attached domain in struct arm_smmu_master. As a result, arm_smmu_strtab_ent is redundant and can be removed. Signed-off-by: Jean-Philippe Brucker Signed-off-by: Will Deacon --- drivers/iommu/arm-smmu-v3.c | 92 ++++++++++++++++++++++----------------------- 1 file changed, 45 insertions(+), 47 deletions(-) diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 25ba546cae7f..7b425483f4b6 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -505,19 +505,6 @@ struct arm_smmu_s2_cfg { u64 vtcr; }; -struct arm_smmu_strtab_ent { - /* - * An STE is "assigned" if the master emitting the corresponding SID - * is attached to a domain. The behaviour of an unassigned STE is - * determined by the disable_bypass parameter, whereas an assigned - * STE behaves according to s1_cfg/s2_cfg, which themselves are - * configured according to the domain type. - */ - bool assigned; - struct arm_smmu_s1_cfg *s1_cfg; - struct arm_smmu_s2_cfg *s2_cfg; -}; - struct arm_smmu_strtab_cfg { __le64 *strtab; dma_addr_t strtab_dma; @@ -593,7 +580,7 @@ struct arm_smmu_device { /* SMMU private data for each master */ struct arm_smmu_master { struct arm_smmu_device *smmu; - struct arm_smmu_strtab_ent ste; + struct arm_smmu_domain *domain; u32 *sids; unsigned int num_sids; }; @@ -1087,8 +1074,8 @@ static void arm_smmu_sync_ste_for_sid(struct arm_smmu_device *smmu, u32 sid) arm_smmu_cmdq_issue_sync(smmu); } -static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, - __le64 *dst, struct arm_smmu_strtab_ent *ste) +static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid, + __le64 *dst) { /* * This is hideously complicated, but we only really care about @@ -1108,6 +1095,10 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, */ u64 val = le64_to_cpu(dst[0]); bool ste_live = false; + struct arm_smmu_device *smmu = NULL; + struct arm_smmu_s1_cfg *s1_cfg = NULL; + struct arm_smmu_s2_cfg *s2_cfg = NULL; + struct arm_smmu_domain *smmu_domain = NULL; struct arm_smmu_cmdq_ent prefetch_cmd = { .opcode = CMDQ_OP_PREFETCH_CFG, .prefetch = { @@ -1115,6 +1106,25 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, }, }; + if (master) { + smmu_domain = master->domain; + smmu = master->smmu; + } + + if (smmu_domain) { + switch (smmu_domain->stage) { + case ARM_SMMU_DOMAIN_S1: + s1_cfg = &smmu_domain->s1_cfg; + break; + case ARM_SMMU_DOMAIN_S2: + case ARM_SMMU_DOMAIN_NESTED: + s2_cfg = &smmu_domain->s2_cfg; + break; + default: + break; + } + } + if (val & STRTAB_STE_0_V) { switch (FIELD_GET(STRTAB_STE_0_CFG, val)) { case STRTAB_STE_0_CFG_BYPASS: @@ -1135,8 +1145,8 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, val = STRTAB_STE_0_V; /* Bypass/fault */ - if (!ste->assigned || !(ste->s1_cfg || ste->s2_cfg)) { - if (!ste->assigned && disable_bypass) + if (!smmu_domain || !(s1_cfg || s2_cfg)) { + if (!smmu_domain && disable_bypass) val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_ABORT); else val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_BYPASS); @@ -1154,7 +1164,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, return; } - if (ste->s1_cfg) { + if (s1_cfg) { BUG_ON(ste_live); dst[1] = cpu_to_le64( FIELD_PREP(STRTAB_STE_1_S1CIR, STRTAB_STE_1_S1C_CACHE_WBRA) | @@ -1169,22 +1179,22 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, !(smmu->features & ARM_SMMU_FEAT_STALL_FORCE)) dst[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD); - val |= (ste->s1_cfg->cdptr_dma & STRTAB_STE_0_S1CTXPTR_MASK) | + val |= (s1_cfg->cdptr_dma & STRTAB_STE_0_S1CTXPTR_MASK) | FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S1_TRANS); } - if (ste->s2_cfg) { + if (s2_cfg) { BUG_ON(ste_live); dst[2] = cpu_to_le64( - FIELD_PREP(STRTAB_STE_2_S2VMID, ste->s2_cfg->vmid) | - FIELD_PREP(STRTAB_STE_2_VTCR, ste->s2_cfg->vtcr) | + FIELD_PREP(STRTAB_STE_2_S2VMID, s2_cfg->vmid) | + FIELD_PREP(STRTAB_STE_2_VTCR, s2_cfg->vtcr) | #ifdef __BIG_ENDIAN STRTAB_STE_2_S2ENDI | #endif STRTAB_STE_2_S2PTW | STRTAB_STE_2_S2AA64 | STRTAB_STE_2_S2R); - dst[3] = cpu_to_le64(ste->s2_cfg->vttbr & STRTAB_STE_3_S2TTB_MASK); + dst[3] = cpu_to_le64(s2_cfg->vttbr & STRTAB_STE_3_S2TTB_MASK); val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S2_TRANS); } @@ -1201,10 +1211,9 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, static void arm_smmu_init_bypass_stes(u64 *strtab, unsigned int nent) { unsigned int i; - struct arm_smmu_strtab_ent ste = { .assigned = false }; for (i = 0; i < nent; ++i) { - arm_smmu_write_strtab_ent(NULL, -1, strtab, &ste); + arm_smmu_write_strtab_ent(NULL, -1, strtab); strtab += STRTAB_STE_DWORDS; } } @@ -1706,13 +1715,16 @@ static void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master) if (j < i) continue; - arm_smmu_write_strtab_ent(smmu, sid, step, &master->ste); + arm_smmu_write_strtab_ent(master, sid, step); } } static void arm_smmu_detach_dev(struct arm_smmu_master *master) { - master->ste.assigned = false; + if (!master->domain) + return; + + master->domain = NULL; arm_smmu_install_ste_for_dev(master); } @@ -1723,18 +1735,14 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) struct arm_smmu_device *smmu; struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); struct arm_smmu_master *master; - struct arm_smmu_strtab_ent *ste; if (!fwspec) return -ENOENT; master = fwspec->iommu_priv; smmu = master->smmu; - ste = &master->ste; - /* Already attached to a different domain? */ - if (ste->assigned) - arm_smmu_detach_dev(master); + arm_smmu_detach_dev(master); mutex_lock(&smmu_domain->init_mutex); @@ -1754,19 +1762,10 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) goto out_unlock; } - ste->assigned = true; + master->domain = smmu_domain; - if (smmu_domain->stage == ARM_SMMU_DOMAIN_BYPASS) { - ste->s1_cfg = NULL; - ste->s2_cfg = NULL; - } else if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) { - ste->s1_cfg = &smmu_domain->s1_cfg; - ste->s2_cfg = NULL; - arm_smmu_write_ctx_desc(smmu, ste->s1_cfg); - } else { - ste->s1_cfg = NULL; - ste->s2_cfg = &smmu_domain->s2_cfg; - } + if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) + arm_smmu_write_ctx_desc(smmu, &smmu_domain->s1_cfg); arm_smmu_install_ste_for_dev(master); out_unlock: @@ -1921,8 +1920,7 @@ static void arm_smmu_remove_device(struct device *dev) master = fwspec->iommu_priv; smmu = master->smmu; - if (master && master->ste.assigned) - arm_smmu_detach_dev(master); + arm_smmu_detach_dev(master); iommu_group_remove_device(dev); iommu_device_unlink(&smmu->iommu, dev); kfree(master); -- cgit v1.2.3-59-g8ed1b From 2a7e62f51696ad476b7fb8157d73307e20257df7 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Wed, 17 Apr 2019 19:24:46 +0100 Subject: iommu/arm-smmu-v3: Link domains and devices When removing a mapping from a domain, we need to send an invalidation to all devices that might have stored it in their Address Translation Cache (ATC). In addition when updating the context descriptor of a live domain, we'll need to send invalidations for all devices attached to it. Maintain a list of devices in each domain, protected by a spinlock. It is updated every time we attach or detach devices to and from domains. It needs to be a spinlock because we'll invalidate ATC entries from within hardirq-safe contexts, but it may be possible to relax the read side with RCU later. Signed-off-by: Jean-Philippe Brucker Signed-off-by: Will Deacon --- drivers/iommu/arm-smmu-v3.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 7b425483f4b6..3e7198ee9530 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -581,6 +581,7 @@ struct arm_smmu_device { struct arm_smmu_master { struct arm_smmu_device *smmu; struct arm_smmu_domain *domain; + struct list_head domain_head; u32 *sids; unsigned int num_sids; }; @@ -607,6 +608,9 @@ struct arm_smmu_domain { }; struct iommu_domain domain; + + struct list_head devices; + spinlock_t devices_lock; }; struct arm_smmu_option_prop { @@ -1504,6 +1508,9 @@ static struct iommu_domain *arm_smmu_domain_alloc(unsigned type) } mutex_init(&smmu_domain->init_mutex); + INIT_LIST_HEAD(&smmu_domain->devices); + spin_lock_init(&smmu_domain->devices_lock); + return &smmu_domain->domain; } @@ -1721,9 +1728,16 @@ static void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master) static void arm_smmu_detach_dev(struct arm_smmu_master *master) { - if (!master->domain) + unsigned long flags; + struct arm_smmu_domain *smmu_domain = master->domain; + + if (!smmu_domain) return; + spin_lock_irqsave(&smmu_domain->devices_lock, flags); + list_del(&master->domain_head); + spin_unlock_irqrestore(&smmu_domain->devices_lock, flags); + master->domain = NULL; arm_smmu_install_ste_for_dev(master); } @@ -1731,6 +1745,7 @@ static void arm_smmu_detach_dev(struct arm_smmu_master *master) static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) { int ret = 0; + unsigned long flags; struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); struct arm_smmu_device *smmu; struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); @@ -1764,6 +1779,10 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) master->domain = smmu_domain; + spin_lock_irqsave(&smmu_domain->devices_lock, flags); + list_add(&master->domain_head, &smmu_domain->devices); + spin_unlock_irqrestore(&smmu_domain->devices_lock, flags); + if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) arm_smmu_write_ctx_desc(smmu, &smmu_domain->s1_cfg); -- cgit v1.2.3-59-g8ed1b From 9ce27afc0830fca07daa3baeb4da44423b0673ef Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Wed, 17 Apr 2019 19:24:47 +0100 Subject: iommu/arm-smmu-v3: Add support for PCI ATS PCIe devices can implement their own TLB, named Address Translation Cache (ATC). Enable Address Translation Service (ATS) for devices that support it and send them invalidation requests whenever we invalidate the IOTLBs. ATC invalidation is allowed to take up to 90 seconds, according to the PCIe spec, so it is possible to get a SMMU command queue timeout during normal operations. However we expect implementations to complete invalidation in reasonable time. We only enable ATS for "trusted" devices, and currently rely on the pci_dev->untrusted bit. For ATS we have to trust that: (a) The device doesn't issue "translated" memory requests for addresses that weren't returned by the SMMU in a Translation Completion. In particular, if we give control of a device or device partition to a VM or userspace, software cannot program the device to access arbitrary "translated" addresses. (b) The device follows permissions granted by the SMMU in a Translation Completion. If the device requested read+write permission and only got read, then it doesn't write. (c) The device doesn't send Translated transactions for an address that was invalidated by an ATC invalidation. Note that the PCIe specification explicitly requires all of these, so we can assume that implementations will cleanly shield ATCs from software. All ATS translated requests still go through the SMMU, to walk the stream table and check that the device is actually allowed to send translated requests. Signed-off-by: Jean-Philippe Brucker Signed-off-by: Will Deacon --- drivers/iommu/arm-smmu-v3.c | 201 ++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 195 insertions(+), 6 deletions(-) diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 3e7198ee9530..3bde137a3755 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include @@ -86,6 +87,7 @@ #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) @@ -294,6 +296,7 @@ #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_0_OP GENMASK_ULL(7, 0) #define CMDQ_0_SSV (1UL << 11) @@ -312,6 +315,12 @@ #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) @@ -433,6 +442,16 @@ struct arm_smmu_cmdq_ent { 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; @@ -580,10 +599,12 @@ struct arm_smmu_device { /* 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 :1; }; /* SMMU private data for an IOMMU domain */ @@ -813,6 +834,14 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent) case CMDQ_OP_TLBI_S12_VMALL: cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid); break; + case CMDQ_OP_ATC_INV: + cmd[0] |= FIELD_PREP(CMDQ_0_SSV, ent->substream_valid); + cmd[0] |= FIELD_PREP(CMDQ_ATC_0_GLOBAL, ent->atc.global); + cmd[0] |= FIELD_PREP(CMDQ_ATC_0_SSID, ent->atc.ssid); + cmd[0] |= FIELD_PREP(CMDQ_ATC_0_SID, ent->atc.sid); + cmd[1] |= FIELD_PREP(CMDQ_ATC_1_SIZE, ent->atc.size); + cmd[1] |= ent->atc.addr & CMDQ_ATC_1_ADDR_MASK; + break; case CMDQ_OP_PRI_RESP: cmd[0] |= FIELD_PREP(CMDQ_0_SSV, ent->substream_valid); cmd[0] |= FIELD_PREP(CMDQ_PRI_0_SSID, ent->pri.ssid); @@ -857,6 +886,7 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu) [CMDQ_ERR_CERROR_NONE_IDX] = "No error", [CMDQ_ERR_CERROR_ILL_IDX] = "Illegal command", [CMDQ_ERR_CERROR_ABT_IDX] = "Abort on command fetch", + [CMDQ_ERR_CERROR_ATC_INV_IDX] = "ATC invalidate timeout", }; int i; @@ -876,6 +906,14 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu) dev_err(smmu->dev, "retrying command fetch\n"); case CMDQ_ERR_CERROR_NONE_IDX: return; + case CMDQ_ERR_CERROR_ATC_INV_IDX: + /* + * ATC Invalidation Completion timeout. CONS is still pointing + * at the CMD_SYNC. Attempt to complete other pending commands + * by repeating the CMD_SYNC, though we might well end up back + * here since the ATC invalidation may still be pending. + */ + return; case CMDQ_ERR_CERROR_ILL_IDX: /* Fallthrough */ default: @@ -992,7 +1030,7 @@ static int __arm_smmu_cmdq_issue_sync(struct arm_smmu_device *smmu) return ret; } -static void arm_smmu_cmdq_issue_sync(struct arm_smmu_device *smmu) +static int arm_smmu_cmdq_issue_sync(struct arm_smmu_device *smmu) { int ret; bool msi = (smmu->features & ARM_SMMU_FEAT_MSI) && @@ -1002,6 +1040,7 @@ static void arm_smmu_cmdq_issue_sync(struct arm_smmu_device *smmu) : __arm_smmu_cmdq_issue_sync(smmu); if (ret) dev_err_ratelimited(smmu->dev, "CMD_SYNC timeout\n"); + return ret; } /* Context descriptor manipulation functions */ @@ -1174,9 +1213,6 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid, FIELD_PREP(STRTAB_STE_1_S1CIR, STRTAB_STE_1_S1C_CACHE_WBRA) | FIELD_PREP(STRTAB_STE_1_S1COR, STRTAB_STE_1_S1C_CACHE_WBRA) | FIELD_PREP(STRTAB_STE_1_S1CSH, ARM_SMMU_SH_ISH) | -#ifdef CONFIG_PCI_ATS - FIELD_PREP(STRTAB_STE_1_EATS, STRTAB_STE_1_EATS_TRANS) | -#endif FIELD_PREP(STRTAB_STE_1_STRW, STRTAB_STE_1_STRW_NSEL1)); if (smmu->features & ARM_SMMU_FEAT_STALLS && @@ -1203,6 +1239,10 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid, val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S2_TRANS); } + if (master->ats_enabled) + dst[1] |= cpu_to_le64(FIELD_PREP(STRTAB_STE_1_EATS, + STRTAB_STE_1_EATS_TRANS)); + arm_smmu_sync_ste_for_sid(smmu, sid); dst[0] = cpu_to_le64(val); arm_smmu_sync_ste_for_sid(smmu, sid); @@ -1405,6 +1445,96 @@ static irqreturn_t arm_smmu_combined_irq_handler(int irq, void *dev) return IRQ_WAKE_THREAD; } +static void +arm_smmu_atc_inv_to_cmd(int ssid, unsigned long iova, size_t size, + struct arm_smmu_cmdq_ent *cmd) +{ + size_t log2_span; + size_t span_mask; + /* ATC invalidates are always on 4096-bytes pages */ + size_t inval_grain_shift = 12; + unsigned long page_start, page_end; + + *cmd = (struct arm_smmu_cmdq_ent) { + .opcode = CMDQ_OP_ATC_INV, + .substream_valid = !!ssid, + .atc.ssid = ssid, + }; + + if (!size) { + cmd->atc.size = ATC_INV_SIZE_ALL; + return; + } + + page_start = iova >> inval_grain_shift; + page_end = (iova + size - 1) >> inval_grain_shift; + + /* + * In an ATS Invalidate Request, the address must be aligned on the + * range size, which must be a power of two number of page sizes. We + * thus have to choose between grossly over-invalidating the region, or + * splitting the invalidation into multiple commands. For simplicity + * we'll go with the first solution, but should refine it in the future + * if multiple commands are shown to be more efficient. + * + * Find the smallest power of two that covers the range. The most + * significant differing bit between the start and end addresses, + * fls(start ^ end), indicates the required span. For example: + * + * We want to invalidate pages [8; 11]. This is already the ideal range: + * x = 0b1000 ^ 0b1011 = 0b11 + * span = 1 << fls(x) = 4 + * + * To invalidate pages [7; 10], we need to invalidate [0; 15]: + * x = 0b0111 ^ 0b1010 = 0b1101 + * span = 1 << fls(x) = 16 + */ + log2_span = fls_long(page_start ^ page_end); + span_mask = (1ULL << log2_span) - 1; + + page_start &= ~span_mask; + + cmd->atc.addr = page_start << inval_grain_shift; + cmd->atc.size = log2_span; +} + +static int arm_smmu_atc_inv_master(struct arm_smmu_master *master, + struct arm_smmu_cmdq_ent *cmd) +{ + int i; + + if (!master->ats_enabled) + return 0; + + for (i = 0; i < master->num_sids; i++) { + cmd->atc.sid = master->sids[i]; + arm_smmu_cmdq_issue_cmd(master->smmu, cmd); + } + + return arm_smmu_cmdq_issue_sync(master->smmu); +} + +static int arm_smmu_atc_inv_domain(struct arm_smmu_domain *smmu_domain, + int ssid, unsigned long iova, size_t size) +{ + int ret = 0; + unsigned long flags; + struct arm_smmu_cmdq_ent cmd; + struct arm_smmu_master *master; + + if (!(smmu_domain->smmu->features & ARM_SMMU_FEAT_ATS)) + return 0; + + arm_smmu_atc_inv_to_cmd(ssid, iova, size, &cmd); + + spin_lock_irqsave(&smmu_domain->devices_lock, flags); + list_for_each_entry(master, &smmu_domain->devices, domain_head) + ret |= arm_smmu_atc_inv_master(master, &cmd); + spin_unlock_irqrestore(&smmu_domain->devices_lock, flags); + + return ret ? -ETIMEDOUT : 0; +} + /* IO_PGTABLE API */ static void arm_smmu_tlb_sync(void *cookie) { @@ -1726,6 +1856,42 @@ static void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master) } } +static int arm_smmu_enable_ats(struct arm_smmu_master *master) +{ + int ret; + size_t stu; + struct pci_dev *pdev; + struct arm_smmu_device *smmu = master->smmu; + struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(master->dev); + + if (!(smmu->features & ARM_SMMU_FEAT_ATS) || !dev_is_pci(master->dev) || + !(fwspec->flags & IOMMU_FWSPEC_PCI_RC_ATS) || pci_ats_disabled()) + return -ENXIO; + + pdev = to_pci_dev(master->dev); + if (pdev->untrusted) + return -EPERM; + + /* Smallest Translation Unit: log2 of the smallest supported granule */ + stu = __ffs(smmu->pgsize_bitmap); + + ret = pci_enable_ats(pdev, stu); + if (ret) + return ret; + + master->ats_enabled = true; + return 0; +} + +static void arm_smmu_disable_ats(struct arm_smmu_master *master) +{ + if (!master->ats_enabled || !dev_is_pci(master->dev)) + return; + + pci_disable_ats(to_pci_dev(master->dev)); + master->ats_enabled = false; +} + static void arm_smmu_detach_dev(struct arm_smmu_master *master) { unsigned long flags; @@ -1740,6 +1906,9 @@ static void arm_smmu_detach_dev(struct arm_smmu_master *master) master->domain = NULL; arm_smmu_install_ste_for_dev(master); + + /* Disabling ATS invalidates all ATC entries */ + arm_smmu_disable_ats(master); } static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) @@ -1783,6 +1952,9 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) list_add(&master->domain_head, &smmu_domain->devices); spin_unlock_irqrestore(&smmu_domain->devices_lock, flags); + if (smmu_domain->stage != ARM_SMMU_DOMAIN_BYPASS) + arm_smmu_enable_ats(master); + if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) arm_smmu_write_ctx_desc(smmu, &smmu_domain->s1_cfg); @@ -1806,12 +1978,18 @@ static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova, static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size) { - struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops; + int ret; + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); + struct io_pgtable_ops *ops = smmu_domain->pgtbl_ops; if (!ops) return 0; - return ops->unmap(ops, iova, size); + ret = ops->unmap(ops, iova, size); + if (ret && arm_smmu_atc_inv_domain(smmu_domain, 0, iova, size)) + return 0; + + return ret; } static void arm_smmu_flush_iotlb_all(struct iommu_domain *domain) @@ -1898,6 +2076,7 @@ static int arm_smmu_add_device(struct device *dev) if (!master) return -ENOMEM; + master->dev = dev; master->smmu = smmu; master->sids = fwspec->ids; master->num_sids = fwspec->num_ids; @@ -2564,6 +2743,16 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass) } } + if (smmu->features & ARM_SMMU_FEAT_ATS) { + enables |= CR0_ATSCHK; + ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0, + ARM_SMMU_CR0ACK); + if (ret) { + dev_err(smmu->dev, "failed to enable ATS check\n"); + return ret; + } + } + ret = arm_smmu_setup_irqs(smmu); if (ret) { dev_err(smmu->dev, "failed to setup irqs\n"); -- cgit v1.2.3-59-g8ed1b From b2fc9b4b7ff4e6d237b0118e98573c9153363ecd Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Wed, 17 Apr 2019 19:24:48 +0100 Subject: iommu/arm-smmu-v3: Disable tagged pointers The ARM architecture has a "Top Byte Ignore" (TBI) option that makes the MMU mask out bits [63:56] of an address, allowing a userspace application to store data in its pointers. This option is incompatible with PCI ATS. If TBI is enabled in the SMMU and userspace triggers DMA transactions on tagged pointers, the endpoint might create ATC entries for addresses that include a tag. Software would then have to send ATC invalidation packets for each 255 possible alias of an address, or just wipe the whole address space. This is not a viable option, so disable TBI. The impact of this change is unclear, since there are very few users of tagged pointers, much less SVA. But the requirement introduced by this patch doesn't seem excessive: a userspace application using both tagged pointers and SVA should now sanitize addresses (clear the tag) before using them for device DMA. Signed-off-by: Jean-Philippe Brucker Signed-off-by: Will Deacon --- drivers/iommu/arm-smmu-v3.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 3bde137a3755..99b83fda11e4 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -1057,7 +1057,6 @@ static u64 arm_smmu_cpu_tcr_to_cd(u64 tcr) val |= ARM_SMMU_TCR2CD(tcr, EPD0); val |= ARM_SMMU_TCR2CD(tcr, EPD1); val |= ARM_SMMU_TCR2CD(tcr, IPS); - val |= ARM_SMMU_TCR2CD(tcr, TBI0); return val; } -- cgit v1.2.3-59-g8ed1b From 3f54c447df34ff9efac7809a4a80fd3208efc619 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 23 Apr 2019 11:59:36 +0100 Subject: iommu/arm-smmu-v3: Don't disable SMMU in kdump kernel Disabling the SMMU when probing from within a kdump kernel so that all incoming transactions are terminated can prevent the core of the crashed kernel from being transferred off the machine if all I/O devices are behind the SMMU. Instead, continue to probe the SMMU after it is disabled so that we can reinitialise it entirely and re-attach the DMA masters as they are reset. Since the kdump kernel may not have drivers for all of the active DMA masters, we suppress fault reporting to avoid spamming the console and swamping the IRQ threads. Reported-by: "Leizhen (ThunderTown)" Tested-by: "Leizhen (ThunderTown)" Tested-by: Bhupesh Sharma Signed-off-by: Will Deacon --- drivers/iommu/arm-smmu-v3.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 99b83fda11e4..4d5a694f02c2 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -2649,13 +2649,9 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass) /* Clear CR0 and sync (disables SMMU and queue processing) */ reg = readl_relaxed(smmu->base + ARM_SMMU_CR0); if (reg & CR0_SMMUEN) { - if (is_kdump_kernel()) { - arm_smmu_update_gbpa(smmu, GBPA_ABORT, 0); - arm_smmu_device_disable(smmu); - return -EBUSY; - } - dev_warn(smmu->dev, "SMMU currently enabled! Resetting...\n"); + WARN_ON(is_kdump_kernel() && !disable_bypass); + arm_smmu_update_gbpa(smmu, GBPA_ABORT, 0); } ret = arm_smmu_device_disable(smmu); @@ -2758,6 +2754,8 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass) return ret; } + if (is_kdump_kernel()) + enables &= ~(CR0_EVTQEN | CR0_PRIQEN); /* Enable the SMMU interface, or ensure bypass */ if (!bypass || disable_bypass) { -- cgit v1.2.3-59-g8ed1b From bc580b56cb7888d1f09fff8a50270228fb834ae8 Mon Sep 17 00:00:00 2001 From: Vivek Gautam Date: Mon, 22 Apr 2019 12:40:36 +0530 Subject: iommu/arm-smmu: Log CBFRSYNRA register on context fault Bits[15:0] in CBFRSYNRA register contain information about StreamID of the incoming transaction that generated the fault. Dump CBFRSYNRA register to get this info. This is specially useful in a distributed SMMU architecture where multiple masters are connected to the SMMU. SID information helps to quickly identify the faulting master device. Reviewed-by: Bjorn Andersson Reviewed-by: Robin Murphy Acked-by: Ard Biesheuvel Signed-off-by: Vivek Gautam Signed-off-by: Will Deacon --- drivers/iommu/arm-smmu-regs.h | 2 ++ drivers/iommu/arm-smmu.c | 8 +++++--- 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/arm-smmu-regs.h b/drivers/iommu/arm-smmu-regs.h index a1226e4ab5f8..e9132a926761 100644 --- a/drivers/iommu/arm-smmu-regs.h +++ b/drivers/iommu/arm-smmu-regs.h @@ -147,6 +147,8 @@ enum arm_smmu_s2cr_privcfg { #define CBAR_IRPTNDX_SHIFT 24 #define CBAR_IRPTNDX_MASK 0xff +#define ARM_SMMU_GR1_CBFRSYNRA(n) (0x400 + ((n) << 2)) + #define ARM_SMMU_GR1_CBA2R(n) (0x800 + ((n) << 2)) #define CBA2R_RW64_32BIT (0 << 0) #define CBA2R_RW64_64BIT (1 << 0) diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 930c07635956..5e54cc0a28b3 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -570,12 +570,13 @@ static const struct iommu_gather_ops arm_smmu_s2_tlb_ops_v1 = { static irqreturn_t arm_smmu_context_fault(int irq, void *dev) { - u32 fsr, fsynr; + u32 fsr, fsynr, cbfrsynra; unsigned long iova; struct iommu_domain *domain = dev; struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); struct arm_smmu_cfg *cfg = &smmu_domain->cfg; struct arm_smmu_device *smmu = smmu_domain->smmu; + void __iomem *gr1_base = ARM_SMMU_GR1(smmu); void __iomem *cb_base; cb_base = ARM_SMMU_CB(smmu, cfg->cbndx); @@ -586,10 +587,11 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev) fsynr = readl_relaxed(cb_base + ARM_SMMU_CB_FSYNR0); iova = readq_relaxed(cb_base + ARM_SMMU_CB_FAR); + cbfrsynra = readl_relaxed(gr1_base + ARM_SMMU_GR1_CBFRSYNRA(cfg->cbndx)); dev_err_ratelimited(smmu->dev, - "Unhandled context fault: fsr=0x%x, iova=0x%08lx, fsynr=0x%x, cb=%d\n", - fsr, iova, fsynr, cfg->cbndx); + "Unhandled context fault: fsr=0x%x, iova=0x%08lx, fsynr=0x%x, cbfrsynra=0x%x, cb=%d\n", + fsr, iova, fsynr, cbfrsynra, cfg->cbndx); writel(fsr, cb_base + ARM_SMMU_CB_FSR); return IRQ_HANDLED; -- cgit v1.2.3-59-g8ed1b