From f53dd97874e6d916ce7d3a487a1073ef5c10e153 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 27 Jul 2020 20:18:42 +0200 Subject: iommu/mediatek: 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/mtk_iommu.c:833:34: warning: 'mtk_iommu_of_ids' defined but not used [-Wunused-const-variable=] 833 | static const struct of_device_id mtk_iommu_of_ids[] = { Reported-by: kernel test robot Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20200727181842.8441-1-krzk@kernel.org Signed-off-by: Joerg Roedel --- drivers/iommu/mtk_iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 785b228d39a6..b99c2b4b48ca 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -843,7 +843,7 @@ static struct platform_driver mtk_iommu_driver = { .remove = mtk_iommu_remove, .driver = { .name = "mtk-iommu", - .of_match_table = of_match_ptr(mtk_iommu_of_ids), + .of_match_table = mtk_iommu_of_ids, .pm = &mtk_iommu_pm_ops, } }; -- cgit v1.2.3-58-ga151 From 9bdc2ef69ce2cd244e806c9f3f8f5c0948dc64b7 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 27 Jul 2020 20:36:31 +0200 Subject: iommu/amd: Add missing function prototypes to fix -Wmissing-prototypes Few exported functions from AMD IOMMU driver are missing prototypes. They have declaration in arch/x86/events/amd/iommu.h but this file cannot be included in the driver. Add prototypes to fix W=1 warnings like: drivers/iommu/amd/init.c:3066:19: warning: no previous prototype for 'get_amd_iommu' [-Wmissing-prototypes] 3066 | struct amd_iommu *get_amd_iommu(unsigned int idx) Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20200727183631.16744-1-krzk@kernel.org Signed-off-by: Joerg Roedel --- drivers/iommu/amd/amd_iommu.h | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h index 57309716fd18..0781b7112467 100644 --- a/drivers/iommu/amd/amd_iommu.h +++ b/drivers/iommu/amd/amd_iommu.h @@ -41,6 +41,15 @@ extern int amd_iommu_guest_ir; struct iommu_domain; extern bool amd_iommu_v2_supported(void); +extern struct amd_iommu *get_amd_iommu(unsigned int idx); +extern u8 amd_iommu_pc_get_max_banks(unsigned int idx); +extern bool amd_iommu_pc_supported(void); +extern u8 amd_iommu_pc_get_max_counters(unsigned int idx); +extern int amd_iommu_pc_get_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, + u8 fxn, u64 *value); +extern int amd_iommu_pc_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, + u8 fxn, u64 *value); + extern int amd_iommu_register_ppr_notifier(struct notifier_block *nb); extern int amd_iommu_unregister_ppr_notifier(struct notifier_block *nb); extern void amd_iommu_domain_direct_map(struct iommu_domain *dom); -- cgit v1.2.3-58-ga151 From 06ce8a62ce81f47542043d93b64a4be106e98106 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 28 Jul 2020 19:08:57 +0200 Subject: iommu/amd: Fix kerneldoc comments Fix W=1 compile warnings (invalid kerneldoc): drivers/iommu/amd/init.c:1586: warning: Function parameter or member 'ivrs' not described in 'get_highest_supported_ivhd_type' drivers/iommu/amd/init.c:1938: warning: Function parameter or member 'iommu' not described in 'iommu_update_intcapxt' Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20200728170859.28143-1-krzk@kernel.org Signed-off-by: Joerg Roedel --- drivers/iommu/amd/init.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index c652f16eb702..908d8e89764c 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -1578,7 +1578,7 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h) /** * get_highest_supported_ivhd_type - Look up the appropriate IVHD type - * @ivrs Pointer to the IVRS header + * @ivrs: Pointer to the IVRS header * * This function search through all IVDB of the maximum supported IVHD */ @@ -1929,7 +1929,7 @@ static int iommu_setup_msi(struct amd_iommu *iommu) #define XT_INT_VEC(x) (((x) & 0xFFULL) << 32) #define XT_INT_DEST_HI(x) ((((x) >> 24) & 0xFFULL) << 56) -/** +/* * Setup the IntCapXT registers with interrupt routing information * based on the PCI MSI capability block registers, accessed via * MMIO MSI address low/hi and MSI data registers. -- cgit v1.2.3-58-ga151 From 3207fa325ad77f00e83aaaeca5ca79fa234528f1 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 28 Jul 2020 19:08:58 +0200 Subject: iommu/vt-d: Drop kerneldoc marker from regular comment Fix W=1 compile warnings (invalid kerneldoc): drivers/iommu/intel/dmar.c:389: warning: Function parameter or member 'header' not described in 'dmar_parse_one_drhd' Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20200728170859.28143-2-krzk@kernel.org Signed-off-by: Joerg Roedel --- drivers/iommu/intel/dmar.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 93e6345f3414..ba47edf03941 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -380,7 +380,7 @@ dmar_find_dmaru(struct acpi_dmar_hardware_unit *drhd) return NULL; } -/** +/* * dmar_parse_one_drhd - parses exactly one DMA remapping hardware definition * structure which uniquely represent one DMA remapping hardware unit * present in the platform -- cgit v1.2.3-58-ga151 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(-) 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 v1.2.3-58-ga151 From 002957020e52cfcad538e3dff26969d1cf8a2556 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Thu, 6 Aug 2020 17:54:02 +0200 Subject: iommu/tegra-smmu: Set IOMMU group name Set the name of static IOMMU groups to help with debugging. Signed-off-by: Thierry Reding Link: https://lore.kernel.org/r/20200806155404.3936074-2-thierry.reding@gmail.com Signed-off-by: Joerg Roedel --- drivers/iommu/tegra-smmu.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index 124c8848ab7e..1ffdafe892d9 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -847,6 +847,7 @@ static struct iommu_group *tegra_smmu_group_get(struct tegra_smmu *smmu, return NULL; } + iommu_group_set_name(group->group, soc->name); list_add_tail(&group->list, &smmu->groups); mutex_unlock(&smmu->lock); -- cgit v1.2.3-58-ga151 From 5b30fbfa2aa5c068444d576b1c87b2bd1bddf0ba Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Thu, 6 Aug 2020 17:54:03 +0200 Subject: iommu/tegra-smmu: Balance IOMMU group reference count For groups that are shared between multiple devices, care must be taken to acquire a reference for each device, otherwise the IOMMU core ends up dropping the last reference too early, which will cause the group to be released while consumers may still be thinking that they're holding a reference to it. Signed-off-by: Thierry Reding Link: https://lore.kernel.org/r/20200806155404.3936074-3-thierry.reding@gmail.com Signed-off-by: Joerg Roedel --- drivers/iommu/tegra-smmu.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index 1ffdafe892d9..c439c0929ef8 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -818,6 +818,7 @@ static struct iommu_group *tegra_smmu_group_get(struct tegra_smmu *smmu, { const struct tegra_smmu_group_soc *soc; struct tegra_smmu_group *group; + struct iommu_group *grp; soc = tegra_smmu_find_group(smmu, swgroup); if (!soc) @@ -827,8 +828,9 @@ static struct iommu_group *tegra_smmu_group_get(struct tegra_smmu *smmu, list_for_each_entry(group, &smmu->groups, list) if (group->soc == soc) { + grp = iommu_group_ref_get(group->group); mutex_unlock(&smmu->lock); - return group->group; + return grp; } group = devm_kzalloc(smmu->dev, sizeof(*group), GFP_KERNEL); -- cgit v1.2.3-58-ga151 From 1ea5440e36a792d01aae0b22159e0a13b33589fe Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Thu, 6 Aug 2020 17:54:04 +0200 Subject: iommu/tegra-smmu: Prune IOMMU group when it is released In order to share groups between multiple devices we keep track of them in a per-SMMU list. When an IOMMU group is released, a dangling pointer to it stays around in that list. Fix this by implementing an IOMMU data release callback for groups where the dangling pointer can be removed. Signed-off-by: Thierry Reding Link: https://lore.kernel.org/r/20200806155404.3936074-4-thierry.reding@gmail.com Signed-off-by: Joerg Roedel --- drivers/iommu/tegra-smmu.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index c439c0929ef8..2574e716086b 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -19,6 +19,7 @@ struct tegra_smmu_group { struct list_head list; + struct tegra_smmu *smmu; const struct tegra_smmu_group_soc *soc; struct iommu_group *group; }; @@ -813,6 +814,16 @@ tegra_smmu_find_group(struct tegra_smmu *smmu, unsigned int swgroup) return NULL; } +static void tegra_smmu_group_release(void *iommu_data) +{ + struct tegra_smmu_group *group = iommu_data; + struct tegra_smmu *smmu = group->smmu; + + mutex_lock(&smmu->lock); + list_del(&group->list); + mutex_unlock(&smmu->lock); +} + static struct iommu_group *tegra_smmu_group_get(struct tegra_smmu *smmu, unsigned int swgroup) { @@ -840,6 +851,7 @@ static struct iommu_group *tegra_smmu_group_get(struct tegra_smmu *smmu, } INIT_LIST_HEAD(&group->list); + group->smmu = smmu; group->soc = soc; group->group = iommu_group_alloc(); @@ -849,6 +861,7 @@ static struct iommu_group *tegra_smmu_group_get(struct tegra_smmu *smmu, return NULL; } + iommu_group_set_iommudata(group->group, group, tegra_smmu_group_release); iommu_group_set_name(group->group, soc->name); list_add_tail(&group->list, &smmu->groups); mutex_unlock(&smmu->lock); -- cgit v1.2.3-58-ga151 From a6271ec8eede356aad1c44e8417eede03f5a92fe Mon Sep 17 00:00:00 2001 From: Lad Prabhakar Date: Sun, 9 Aug 2020 20:35:27 +0100 Subject: dt-bindings: iommu: renesas,ipmmu-vmsa: Sort compatible string in increasing number of the SoC Sort the items in the compatible string list in increasing number of SoC. Signed-off-by: Lad Prabhakar Reviewed-by: Geert Uytterhoeven Acked-by: Rob Herring Link: https://lore.kernel.org/r/20200809193527.19659-1-prabhakar.mahadev-lad.rj@bp.renesas.com Signed-off-by: Joerg Roedel --- Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml b/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml index 6bfa090fd73a..9ada67b1f5f4 100644 --- a/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml +++ b/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml @@ -32,8 +32,8 @@ properties: - enum: - renesas,ipmmu-r8a774a1 # RZ/G2M - renesas,ipmmu-r8a774b1 # RZ/G2N - - renesas,ipmmu-r8a774e1 # RZ/G2H - renesas,ipmmu-r8a774c0 # RZ/G2E + - renesas,ipmmu-r8a774e1 # RZ/G2H - renesas,ipmmu-r8a7795 # R-Car H3 - renesas,ipmmu-r8a7796 # R-Car M3-W - renesas,ipmmu-r8a77961 # R-Car M3-W+ -- cgit v1.2.3-58-ga151 From aae4c8e27bd7567132bb931488e2faf1a57c66e9 Mon Sep 17 00:00:00 2001 From: Tom Murphy Date: Mon, 17 Aug 2020 22:00:49 +0100 Subject: iommu: Rename iommu_tlb_* functions to iommu_iotlb_* To keep naming consistent we should stick with *iotlb*. This patch renames a few remaining functions. Signed-off-by: Tom Murphy Link: https://lore.kernel.org/r/20200817210051.13546-1-murphyt7@tcd.ie Signed-off-by: Joerg Roedel --- drivers/iommu/dma-iommu.c | 2 +- drivers/iommu/iommu.c | 4 ++-- drivers/vfio/vfio_iommu_type1.c | 2 +- include/linux/io-pgtable.h | 2 +- include/linux/iommu.h | 10 +++++----- 5 files changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 5141d49a046b..3afd076e9f36 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -471,7 +471,7 @@ static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr, WARN_ON(unmapped != size); if (!cookie->fq_domain) - iommu_tlb_sync(domain, &iotlb_gather); + iommu_iotlb_sync(domain, &iotlb_gather); iommu_dma_free_iova(cookie, dma_addr, size); } diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 609bd25bf154..6c14c88cd525 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -762,7 +762,7 @@ static int iommu_create_device_direct_mappings(struct iommu_group *group, } - iommu_flush_tlb_all(domain); + iommu_flush_iotlb_all(domain); out: iommu_put_resv_regions(dev, &mappings); @@ -2316,7 +2316,7 @@ size_t iommu_unmap(struct iommu_domain *domain, iommu_iotlb_gather_init(&iotlb_gather); ret = __iommu_unmap(domain, iova, size, &iotlb_gather); - iommu_tlb_sync(domain, &iotlb_gather); + iommu_iotlb_sync(domain, &iotlb_gather); return ret; } diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 5fbf0c1f7433..c255a6683f31 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -774,7 +774,7 @@ static long vfio_sync_unpin(struct vfio_dma *dma, struct vfio_domain *domain, long unlocked = 0; struct vfio_regions *entry, *next; - iommu_tlb_sync(domain->domain, iotlb_gather); + iommu_iotlb_sync(domain->domain, iotlb_gather); list_for_each_entry_safe(entry, next, regions, list) { unlocked += vfio_unpin_pages_remote(dma, diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 23285ba645db..4cde111e425b 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -31,7 +31,7 @@ enum io_pgtable_fmt { * single page. IOMMUs that cannot batch TLB invalidation * operations efficiently will typically issue them here, but * others may decide to update the iommu_iotlb_gather structure - * and defer the invalidation until iommu_tlb_sync() instead. + * and defer the invalidation until iommu_iotlb_sync() instead. * * Note that these can all be called in atomic context and must therefore * not block. diff --git a/include/linux/iommu.h b/include/linux/iommu.h index fee209efb756..2ad26d8b4ab9 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -514,13 +514,13 @@ extern void iommu_domain_window_disable(struct iommu_domain *domain, u32 wnd_nr) extern int report_iommu_fault(struct iommu_domain *domain, struct device *dev, unsigned long iova, int flags); -static inline void iommu_flush_tlb_all(struct iommu_domain *domain) +static inline void iommu_flush_iotlb_all(struct iommu_domain *domain) { if (domain->ops->flush_iotlb_all) domain->ops->flush_iotlb_all(domain); } -static inline void iommu_tlb_sync(struct iommu_domain *domain, +static inline void iommu_iotlb_sync(struct iommu_domain *domain, struct iommu_iotlb_gather *iotlb_gather) { if (domain->ops->iotlb_sync) @@ -543,7 +543,7 @@ static inline void iommu_iotlb_gather_add_page(struct iommu_domain *domain, if (gather->pgsize != size || end < gather->start || start > gather->end) { if (gather->pgsize) - iommu_tlb_sync(domain, gather); + iommu_iotlb_sync(domain, gather); gather->pgsize = size; } @@ -725,11 +725,11 @@ static inline size_t iommu_map_sg_atomic(struct iommu_domain *domain, return 0; } -static inline void iommu_flush_tlb_all(struct iommu_domain *domain) +static inline void iommu_flush_iotlb_all(struct iommu_domain *domain) { } -static inline void iommu_tlb_sync(struct iommu_domain *domain, +static inline void iommu_iotlb_sync(struct iommu_domain *domain, struct iommu_iotlb_gather *iotlb_gather) { } -- cgit v1.2.3-58-ga151 From d88f7e028d5eab908d29197297f5ae2ca460e17a Mon Sep 17 00:00:00 2001 From: Lad Prabhakar Date: Tue, 25 Aug 2020 15:18:04 +0100 Subject: dt-bindings: iommu: renesas,ipmmu-vmsa: Add r8a7742 support Document RZ/G1H (R8A7742) SoC bindings. No driver change is needed due to the fallback compatible value "renesas,ipmmu-vmsa". Signed-off-by: Lad Prabhakar Reviewed-by: Chris Paterson Reviewed-by: Yoshihiro Shimoda Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20200825141805.27105-2-prabhakar.mahadev-lad.rj@bp.renesas.com Signed-off-by: Joerg Roedel --- Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml b/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml index 9ada67b1f5f4..cde1afa8dfd6 100644 --- a/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml +++ b/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml @@ -20,6 +20,7 @@ properties: - items: - enum: - renesas,ipmmu-r8a73a4 # R-Mobile APE6 + - renesas,ipmmu-r8a7742 # RZ/G1H - renesas,ipmmu-r8a7743 # RZ/G1M - renesas,ipmmu-r8a7744 # RZ/G1N - renesas,ipmmu-r8a7745 # RZ/G1E -- cgit v1.2.3-58-ga151 From 78aa219022f636f2adda9eb12be0a04b6907a4e0 Mon Sep 17 00:00:00 2001 From: Lad Prabhakar Date: Tue, 25 Aug 2020 15:18:05 +0100 Subject: ARM: dts: r8a7742: Add IPMMU DT nodes Add the five IPMMU instances found in the r8a7742 to DT with a disabled status. Signed-off-by: Lad Prabhakar Reviewed-by: Chris Paterson Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20200825141805.27105-3-prabhakar.mahadev-lad.rj@bp.renesas.com Signed-off-by: Joerg Roedel --- arch/arm/boot/dts/r8a7742.dtsi | 48 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) diff --git a/arch/arm/boot/dts/r8a7742.dtsi b/arch/arm/boot/dts/r8a7742.dtsi index 9743b4242801..0240d017c90d 100644 --- a/arch/arm/boot/dts/r8a7742.dtsi +++ b/arch/arm/boot/dts/r8a7742.dtsi @@ -386,6 +386,54 @@ #thermal-sensor-cells = <0>; }; + ipmmu_sy0: iommu@e6280000 { + compatible = "renesas,ipmmu-r8a7742", + "renesas,ipmmu-vmsa"; + reg = <0 0xe6280000 0 0x1000>; + interrupts = , + ; + #iommu-cells = <1>; + status = "disabled"; + }; + + ipmmu_sy1: iommu@e6290000 { + compatible = "renesas,ipmmu-r8a7742", + "renesas,ipmmu-vmsa"; + reg = <0 0xe6290000 0 0x1000>; + interrupts = ; + #iommu-cells = <1>; + status = "disabled"; + }; + + ipmmu_ds: iommu@e6740000 { + compatible = "renesas,ipmmu-r8a7742", + "renesas,ipmmu-vmsa"; + reg = <0 0xe6740000 0 0x1000>; + interrupts = , + ; + #iommu-cells = <1>; + status = "disabled"; + }; + + ipmmu_mp: iommu@ec680000 { + compatible = "renesas,ipmmu-r8a7742", + "renesas,ipmmu-vmsa"; + reg = <0 0xec680000 0 0x1000>; + interrupts = ; + #iommu-cells = <1>; + status = "disabled"; + }; + + ipmmu_mx: iommu@fe951000 { + compatible = "renesas,ipmmu-r8a7742", + "renesas,ipmmu-vmsa"; + reg = <0 0xfe951000 0 0x1000>; + interrupts = , + ; + #iommu-cells = <1>; + status = "disabled"; + }; + icram0: sram@e63a0000 { compatible = "mmio-sram"; reg = <0 0xe63a0000 0 0x12000>; -- cgit v1.2.3-58-ga151 From 4604393ca0c6e4a73c04798c3f1d9878e70b7251 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Thu, 3 Sep 2020 12:34:04 +0100 Subject: iommu/dma: Remove broken huge page handling The attempt to handle huge page allocations was originally added since the comments around stripping __GFP_COMP in other implementations were nonsensical, and we naively assumed that split_huge_page() could simply be called equivalently to split_page(). It turns out that this doesn't actually work correctly, so just get rid of it - there's little point going to the effort of allocating huge pages if we're only going to split them anyway. Reported-by: Roman Gushchin Signed-off-by: Robin Murphy Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/e287dbe69aa0933abafd97c80631940fd188ddd1.1599132844.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- drivers/iommu/dma-iommu.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 3afd076e9f36..79b4d1073dcb 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -524,6 +524,9 @@ static struct page **__iommu_dma_alloc_pages(struct device *dev, /* IOMMU can map any pages, so himem can also be used here */ gfp |= __GFP_NOWARN | __GFP_HIGHMEM; + /* It makes no sense to muck about with huge pages */ + gfp &= ~__GFP_COMP; + while (count) { struct page *page = NULL; unsigned int order_size; @@ -544,15 +547,9 @@ static struct page **__iommu_dma_alloc_pages(struct device *dev, page = alloc_pages_node(nid, alloc_flags, order); if (!page) continue; - if (!order) - break; - if (!PageCompound(page)) { + if (order) split_page(page, order); - break; - } else if (!split_huge_page(page)) { - break; - } - __free_pages(page, order); + break; } if (!page) { __iommu_dma_free_pages(pages, i); -- cgit v1.2.3-58-ga151 From ba328f82613260a098de7b4aff58743cd8733507 Mon Sep 17 00:00:00 2001 From: Yuqi Jin Date: Thu, 27 Aug 2020 16:43:54 +0800 Subject: iommu/iova: Replace cmpxchg with xchg in queue_iova The performance of the atomic_xchg is better than atomic_cmpxchg because no comparison is required. While the value of @fq_timer_on can only be 0 or 1. Let's use atomic_xchg instead of atomic_cmpxchg here because we only need to check that the value changes from 0 to 1 or from 1 to 1. Signed-off-by: Yuqi Jin Signed-off-by: Shaokun Zhang Reviewed-by: Robin Murphy Cc: Joerg Roedel Link: https://lore.kernel.org/r/1598517834-30275-1-git-send-email-zhangshaokun@hisilicon.com Signed-off-by: Joerg Roedel --- drivers/iommu/iova.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index 45a251da5453..30d969a4c5fd 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -579,7 +579,7 @@ void queue_iova(struct iova_domain *iovad, /* Avoid false sharing as much as possible. */ if (!atomic_read(&iovad->fq_timer_on) && - !atomic_cmpxchg(&iovad->fq_timer_on, 0, 1)) + !atomic_xchg(&iovad->fq_timer_on, 1)) mod_timer(&iovad->fq_timer, jiffies + msecs_to_jiffies(IOVA_FQ_TIMEOUT)); } -- cgit v1.2.3-58-ga151 From c7eb900f5f45eeab1ea1bed997a2a12d8b5907bc Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 28 Aug 2020 19:12:11 +0300 Subject: iommu/vt-d: Move intel_iommu_gfx_mapped to Intel IOMMU header Static analyzer is not happy about intel_iommu_gfx_mapped declaration: .../drivers/iommu/intel/iommu.c:364:5: warning: symbol 'intel_iommu_gfx_mapped' was not declared. Should it be static? Move its declaration to Intel IOMMU header file. Signed-off-by: Andy Shevchenko Reviewed-by: Lu Baolu Link: https://lore.kernel.org/r/20200828161212.71294-1-andriy.shevchenko@linux.intel.com Signed-off-by: Joerg Roedel --- include/drm/intel-gtt.h | 5 +---- include/linux/intel-iommu.h | 1 + 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/include/drm/intel-gtt.h b/include/drm/intel-gtt.h index 71d81923e6b0..abfefaaf897a 100644 --- a/include/drm/intel-gtt.h +++ b/include/drm/intel-gtt.h @@ -5,6 +5,7 @@ #define _DRM_INTEL_GTT_H #include +#include #include void intel_gtt_get(u64 *gtt_total, @@ -33,8 +34,4 @@ void intel_gtt_clear_range(unsigned int first_entry, unsigned int num_entries); /* flag for GFDT type */ #define AGP_USER_CACHED_MEMORY_GFDT (1 << 3) -#ifdef CONFIG_INTEL_IOMMU -extern int intel_iommu_gfx_mapped; -#endif - #endif diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index b1ed2f25f7c0..6a3ddaabf3f5 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -792,6 +792,7 @@ extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu); extern int dmar_disabled; extern int intel_iommu_enabled; extern int intel_iommu_tboot_noforce; +extern int intel_iommu_gfx_mapped; #else static inline int iommu_calculate_agaw(struct intel_iommu *iommu) { -- cgit v1.2.3-58-ga151 From c2c59456e1fcad3f464761c5839399176e3a934a Mon Sep 17 00:00:00 2001 From: Miles Chen Date: Fri, 4 Sep 2020 18:40:38 +0800 Subject: iommu/mediatek: Check 4GB mode by reading infracfg In previous discussion [1] and [2], we found that it is risky to use max_pfn or totalram_pages to tell if 4GB mode is enabled. Check 4GB mode by reading infracfg register, remove the usage of the un-exported symbol max_pfn. This is a step towards building mtk_iommu as a kernel module. [1] https://lore.kernel.org/lkml/20200603161132.2441-1-miles.chen@mediatek.com/ [2] https://lore.kernel.org/lkml/20200604080120.2628-1-miles.chen@mediatek.com/ [3] https://lore.kernel.org/lkml/20200715205120.GA778876@bogus/ Cc: Mike Rapoport Cc: David Hildenbrand Cc: Yong Wu Cc: Yingjoe Chen Cc: Christoph Hellwig Cc: Rob Herring Cc: Matthias Brugger Cc: Joerg Roedel Reviewed-by: Matthias Brugger Signed-off-by: Miles Chen Link: https://lore.kernel.org/r/20200904104038.4979-1-miles.chen@mediatek.com Signed-off-by: Joerg Roedel --- drivers/iommu/mtk_iommu.c | 33 ++++++++++++++++++++++++++++----- include/linux/soc/mediatek/infracfg.h | 3 +++ 2 files changed, 31 insertions(+), 5 deletions(-) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index b99c2b4b48ca..94f676659ed5 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -3,7 +3,6 @@ * Copyright (c) 2015-2016 MediaTek Inc. * Author: Yong Wu */ -#include #include #include #include @@ -15,13 +14,16 @@ #include #include #include +#include #include #include #include #include #include +#include #include #include +#include #include #include @@ -640,8 +642,11 @@ static int mtk_iommu_probe(struct platform_device *pdev) struct resource *res; resource_size_t ioaddr; struct component_match *match = NULL; + struct regmap *infracfg; void *protect; int i, larb_nr, ret; + u32 val; + char *p; data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); if (!data) @@ -655,10 +660,28 @@ static int mtk_iommu_probe(struct platform_device *pdev) return -ENOMEM; data->protect_base = ALIGN(virt_to_phys(protect), MTK_PROTECT_PA_ALIGN); - /* Whether the current dram is over 4GB */ - data->enable_4GB = !!(max_pfn > (BIT_ULL(32) >> PAGE_SHIFT)); - if (!MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_4GB_MODE)) - data->enable_4GB = false; + if (MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_4GB_MODE)) { + switch (data->plat_data->m4u_plat) { + case M4U_MT2712: + p = "mediatek,mt2712-infracfg"; + break; + case M4U_MT8173: + p = "mediatek,mt8173-infracfg"; + break; + default: + p = NULL; + } + + infracfg = syscon_regmap_lookup_by_compatible(p); + + if (IS_ERR(infracfg)) + return PTR_ERR(infracfg); + + ret = regmap_read(infracfg, REG_INFRA_MISC, &val); + if (ret) + return ret; + data->enable_4GB = !!(val & F_DDR_4GB_SUPPORT_EN); + } res = platform_get_resource(pdev, IORESOURCE_MEM, 0); data->base = devm_ioremap_resource(dev, res); diff --git a/include/linux/soc/mediatek/infracfg.h b/include/linux/soc/mediatek/infracfg.h index fd25f0148566..233463d789c6 100644 --- a/include/linux/soc/mediatek/infracfg.h +++ b/include/linux/soc/mediatek/infracfg.h @@ -32,6 +32,9 @@ #define MT7622_TOP_AXI_PROT_EN_WB (BIT(2) | BIT(6) | \ BIT(7) | BIT(8)) +#define REG_INFRA_MISC 0xf00 +#define F_DDR_4GB_SUPPORT_EN BIT(13) + int mtk_infracfg_set_bus_protection(struct regmap *infracfg, u32 mask, bool reg_update); int mtk_infracfg_clear_bus_protection(struct regmap *infracfg, u32 mask, -- cgit v1.2.3-58-ga151 From 03c7b78b0b780ac7600641e9a59ae0610679122b Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 4 Sep 2020 13:39:06 +0200 Subject: iommu/sun50i: Fix set-but-not-used variable warning Fix the following warning the the SUN50I driver: drivers/iommu/sun50i-iommu.c: In function 'sun50i_iommu_irq': drivers/iommu/sun50i-iommu.c:890:14: warning: variable 'iova' set but not used [-Wunused-but-set-variable] 890 | phys_addr_t iova; | ^~~~ Reported-by: kernel test robot Signed-off-by: Joerg Roedel Link: https://lore.kernel.org/r/20200904113906.3906-1-joro@8bytes.org Signed-off-by: Joerg Roedel --- drivers/iommu/sun50i-iommu.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/iommu/sun50i-iommu.c b/drivers/iommu/sun50i-iommu.c index 3b1bf2fb94f5..ea6db1341916 100644 --- a/drivers/iommu/sun50i-iommu.c +++ b/drivers/iommu/sun50i-iommu.c @@ -881,7 +881,6 @@ static phys_addr_t sun50i_iommu_handle_perm_irq(struct sun50i_iommu *iommu) static irqreturn_t sun50i_iommu_irq(int irq, void *dev_id) { struct sun50i_iommu *iommu = dev_id; - phys_addr_t iova; u32 status; spin_lock(&iommu->iommu_lock); @@ -893,15 +892,15 @@ static irqreturn_t sun50i_iommu_irq(int irq, void *dev_id) } if (status & IOMMU_INT_INVALID_L2PG) - iova = sun50i_iommu_handle_pt_irq(iommu, - IOMMU_INT_ERR_ADDR_L2_REG, - IOMMU_L2PG_INT_REG); + sun50i_iommu_handle_pt_irq(iommu, + IOMMU_INT_ERR_ADDR_L2_REG, + IOMMU_L2PG_INT_REG); else if (status & IOMMU_INT_INVALID_L1PG) - iova = sun50i_iommu_handle_pt_irq(iommu, - IOMMU_INT_ERR_ADDR_L1_REG, - IOMMU_L1PG_INT_REG); + sun50i_iommu_handle_pt_irq(iommu, + IOMMU_INT_ERR_ADDR_L1_REG, + IOMMU_L1PG_INT_REG); else - iova = sun50i_iommu_handle_perm_irq(iommu); + sun50i_iommu_handle_perm_irq(iommu); iommu_write(iommu, IOMMU_INT_CLR_REG, status); -- cgit v1.2.3-58-ga151 From 404d0b308e4f730b1c9b2f33e84a6f7069db94c5 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Tue, 1 Sep 2020 23:37:30 +0300 Subject: iommu/tegra-smmu: Add locking around mapping operations The mapping operations of the Tegra SMMU driver are subjected to a race condition issues because SMMU Address Space isn't allocated and freed atomically, while it should be. This patch makes the mapping operations atomic, it fixes an accidentally released Host1x Address Space problem which happens while running multiple graphics tests in parallel on Tegra30, i.e. by having multiple threads racing with each other in the Host1x's submission and completion code paths, performing IOVA mappings and unmappings in parallel. Signed-off-by: Dmitry Osipenko Tested-by: Thierry Reding Acked-by: Thierry Reding Link: https://lore.kernel.org/r/20200901203730.27865-1-digetx@gmail.com Signed-off-by: Joerg Roedel --- drivers/iommu/tegra-smmu.c | 95 ++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 84 insertions(+), 11 deletions(-) diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index 2574e716086b..046add7acb61 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include @@ -50,6 +51,7 @@ struct tegra_smmu_as { struct iommu_domain domain; struct tegra_smmu *smmu; unsigned int use_count; + spinlock_t lock; u32 *count; struct page **pts; struct page *pd; @@ -309,6 +311,8 @@ static struct iommu_domain *tegra_smmu_domain_alloc(unsigned type) return NULL; } + spin_lock_init(&as->lock); + /* setup aperture */ as->domain.geometry.aperture_start = 0; as->domain.geometry.aperture_end = 0xffffffff; @@ -570,19 +574,14 @@ static u32 *tegra_smmu_pte_lookup(struct tegra_smmu_as *as, unsigned long iova, } static u32 *as_get_pte(struct tegra_smmu_as *as, dma_addr_t iova, - dma_addr_t *dmap) + dma_addr_t *dmap, struct page *page) { unsigned int pde = iova_pd_index(iova); struct tegra_smmu *smmu = as->smmu; if (!as->pts[pde]) { - struct page *page; dma_addr_t dma; - page = alloc_page(GFP_KERNEL | __GFP_DMA | __GFP_ZERO); - if (!page) - return NULL; - dma = dma_map_page(smmu->dev, page, 0, SMMU_SIZE_PT, DMA_TO_DEVICE); if (dma_mapping_error(smmu->dev, dma)) { @@ -656,15 +655,61 @@ static void tegra_smmu_set_pte(struct tegra_smmu_as *as, unsigned long iova, smmu_flush(smmu); } -static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot, gfp_t gfp) +static struct page *as_get_pde_page(struct tegra_smmu_as *as, + unsigned long iova, gfp_t gfp, + unsigned long *flags) +{ + unsigned int pde = iova_pd_index(iova); + struct page *page = as->pts[pde]; + + /* at first check whether allocation needs to be done at all */ + if (page) + return page; + + /* + * In order to prevent exhaustion of the atomic memory pool, we + * allocate page in a sleeping context if GFP flags permit. Hence + * spinlock needs to be unlocked and re-locked after allocation. + */ + if (!(gfp & __GFP_ATOMIC)) + spin_unlock_irqrestore(&as->lock, *flags); + + page = alloc_page(gfp | __GFP_DMA | __GFP_ZERO); + + if (!(gfp & __GFP_ATOMIC)) + spin_lock_irqsave(&as->lock, *flags); + + /* + * In a case of blocking allocation, a concurrent mapping may win + * the PDE allocation. In this case the allocated page isn't needed + * if allocation succeeded and the allocation failure isn't fatal. + */ + if (as->pts[pde]) { + if (page) + __free_page(page); + + page = as->pts[pde]; + } + + return page; +} + +static int +__tegra_smmu_map(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, int prot, gfp_t gfp, + unsigned long *flags) { struct tegra_smmu_as *as = to_smmu_as(domain); dma_addr_t pte_dma; + struct page *page; u32 pte_attrs; u32 *pte; - pte = as_get_pte(as, iova, &pte_dma); + page = as_get_pde_page(as, iova, gfp, flags); + if (!page) + return -ENOMEM; + + pte = as_get_pte(as, iova, &pte_dma, page); if (!pte) return -ENOMEM; @@ -686,8 +731,9 @@ static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova, return 0; } -static size_t tegra_smmu_unmap(struct iommu_domain *domain, unsigned long iova, - size_t size, struct iommu_iotlb_gather *gather) +static size_t +__tegra_smmu_unmap(struct iommu_domain *domain, unsigned long iova, + size_t size, struct iommu_iotlb_gather *gather) { struct tegra_smmu_as *as = to_smmu_as(domain); dma_addr_t pte_dma; @@ -703,6 +749,33 @@ static size_t tegra_smmu_unmap(struct iommu_domain *domain, unsigned long iova, return size; } +static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) +{ + struct tegra_smmu_as *as = to_smmu_as(domain); + unsigned long flags; + int ret; + + spin_lock_irqsave(&as->lock, flags); + ret = __tegra_smmu_map(domain, iova, paddr, size, prot, gfp, &flags); + spin_unlock_irqrestore(&as->lock, flags); + + return ret; +} + +static size_t tegra_smmu_unmap(struct iommu_domain *domain, unsigned long iova, + size_t size, struct iommu_iotlb_gather *gather) +{ + struct tegra_smmu_as *as = to_smmu_as(domain); + unsigned long flags; + + spin_lock_irqsave(&as->lock, flags); + size = __tegra_smmu_unmap(domain, iova, size, gather); + spin_unlock_irqrestore(&as->lock, flags); + + return size; +} + static phys_addr_t tegra_smmu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) { -- cgit v1.2.3-58-ga151 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(-) 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 v1.2.3-58-ga151 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(-) 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 v1.2.3-58-ga151 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(-) 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 v1.2.3-58-ga151 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(-) 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 v1.2.3-58-ga151 From f7f842cc1fe8a9be1916aa0ff8a52f08389bf394 Mon Sep 17 00:00:00 2001 From: Fabien Parent Date: Mon, 7 Sep 2020 12:16:47 +0200 Subject: dt-bindings: iommu: Add binding for MediaTek MT8167 IOMMU This commit adds IOMMU binding documentation and larb port definitions for the MT8167 SoC. Signed-off-by: Fabien Parent Acked-by: Rob Herring Link: https://lore.kernel.org/r/20200907101649.1573134-1-fparent@baylibre.com Signed-off-by: Joerg Roedel --- .../devicetree/bindings/iommu/mediatek,iommu.txt | 2 + include/dt-bindings/memory/mt8167-larb-port.h | 51 ++++++++++++++++++++++ 2 files changed, 53 insertions(+) create mode 100644 include/dt-bindings/memory/mt8167-larb-port.h diff --git a/Documentation/devicetree/bindings/iommu/mediatek,iommu.txt b/Documentation/devicetree/bindings/iommu/mediatek,iommu.txt index c1ccd8582eb2..ac949f7fe3d4 100644 --- a/Documentation/devicetree/bindings/iommu/mediatek,iommu.txt +++ b/Documentation/devicetree/bindings/iommu/mediatek,iommu.txt @@ -61,6 +61,7 @@ Required properties: "mediatek,mt6779-m4u" for mt6779 which uses generation two m4u HW. "mediatek,mt7623-m4u", "mediatek,mt2701-m4u" for mt7623 which uses generation one m4u HW. + "mediatek,mt8167-m4u" for mt8167 which uses generation two m4u HW. "mediatek,mt8173-m4u" for mt8173 which uses generation two m4u HW. "mediatek,mt8183-m4u" for mt8183 which uses generation two m4u HW. - reg : m4u register base and size. @@ -80,6 +81,7 @@ Required properties: dt-binding/memory/mt2701-larb-port.h for mt2701, mt7623 dt-binding/memory/mt2712-larb-port.h for mt2712, dt-binding/memory/mt6779-larb-port.h for mt6779, + dt-binding/memory/mt8167-larb-port.h for mt8167, dt-binding/memory/mt8173-larb-port.h for mt8173, and dt-binding/memory/mt8183-larb-port.h for mt8183. diff --git a/include/dt-bindings/memory/mt8167-larb-port.h b/include/dt-bindings/memory/mt8167-larb-port.h new file mode 100644 index 000000000000..000fb299a408 --- /dev/null +++ b/include/dt-bindings/memory/mt8167-larb-port.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2020 MediaTek Inc. + * Copyright (c) 2020 BayLibre, SAS + * Author: Honghui Zhang + * Author: Fabien Parent + */ +#ifndef __DTS_IOMMU_PORT_MT8167_H +#define __DTS_IOMMU_PORT_MT8167_H + +#define MTK_M4U_ID(larb, port) (((larb) << 5) | (port)) + +#define M4U_LARB0_ID 0 +#define M4U_LARB1_ID 1 +#define M4U_LARB2_ID 2 + +/* larb0 */ +#define M4U_PORT_DISP_OVL0 MTK_M4U_ID(M4U_LARB0_ID, 0) +#define M4U_PORT_DISP_RDMA0 MTK_M4U_ID(M4U_LARB0_ID, 1) +#define M4U_PORT_DISP_WDMA0 MTK_M4U_ID(M4U_LARB0_ID, 2) +#define M4U_PORT_DISP_RDMA1 MTK_M4U_ID(M4U_LARB0_ID, 3) +#define M4U_PORT_MDP_RDMA MTK_M4U_ID(M4U_LARB0_ID, 4) +#define M4U_PORT_MDP_WDMA MTK_M4U_ID(M4U_LARB0_ID, 5) +#define M4U_PORT_MDP_WROT MTK_M4U_ID(M4U_LARB0_ID, 6) +#define M4U_PORT_DISP_FAKE MTK_M4U_ID(M4U_LARB0_ID, 7) + +/* larb1*/ +#define M4U_PORT_CAM_IMGO MTK_M4U_ID(M4U_LARB1_ID, 0) +#define M4U_PORT_CAM_IMG2O MTK_M4U_ID(M4U_LARB1_ID, 1) +#define M4U_PORT_CAM_LSCI MTK_M4U_ID(M4U_LARB1_ID, 2) +#define M4U_PORT_CAM_ESFKO MTK_M4U_ID(M4U_LARB1_ID, 3) +#define M4U_PORT_CAM_AAO MTK_M4U_ID(M4U_LARB1_ID, 4) +#define M4U_PORT_VENC_REC MTK_M4U_ID(M4U_LARB1_ID, 5) +#define M4U_PORT_VENC_BSDMA MTK_M4U_ID(M4U_LARB1_ID, 6) +#define M4U_PORT_VENC_RD_COMV MTK_M4U_ID(M4U_LARB1_ID, 7) +#define M4U_PORT_CAM_IMGI MTK_M4U_ID(M4U_LARB1_ID, 8) +#define M4U_PORT_VENC_CUR_LUMA MTK_M4U_ID(M4U_LARB1_ID, 9) +#define M4U_PORT_VENC_CUR_CHROMA MTK_M4U_ID(M4U_LARB1_ID, 10) +#define M4U_PORT_VENC_REF_LUMA MTK_M4U_ID(M4U_LARB1_ID, 11) +#define M4U_PORT_VENC_REF_CHROMA MTK_M4U_ID(M4U_LARB1_ID, 12) + +/* larb2*/ +#define M4U_PORT_HW_VDEC_MC_EXT MTK_M4U_ID(M4U_LARB2_ID, 0) +#define M4U_PORT_HW_VDEC_PP_EXT MTK_M4U_ID(M4U_LARB2_ID, 1) +#define M4U_PORT_HW_VDEC_VLD_EXT MTK_M4U_ID(M4U_LARB2_ID, 2) +#define M4U_PORT_HW_VDEC_AVC_MV_EXT MTK_M4U_ID(M4U_LARB2_ID, 3) +#define M4U_PORT_HW_VDEC_PRED_RD_EXT MTK_M4U_ID(M4U_LARB2_ID, 4) +#define M4U_PORT_HW_VDEC_PRED_WR_EXT MTK_M4U_ID(M4U_LARB2_ID, 5) +#define M4U_PORT_HW_VDEC_PPWRAP_EXT MTK_M4U_ID(M4U_LARB2_ID, 6) + +#endif -- cgit v1.2.3-58-ga151 From d1b5ef0054c6b7443f5e9d3e7c3b7879499b7f95 Mon Sep 17 00:00:00 2001 From: Fabien Parent Date: Mon, 7 Sep 2020 12:16:48 +0200 Subject: iommu/mediatek: Add flag for legacy ivrp paddr Add a new flag in order to select which IVRP_PADDR format is used by an SoC. Signed-off-by: Fabien Parent Reviewed-by: Yong Wu Reviewed-by: Matthias Brugger Link: https://lore.kernel.org/r/20200907101649.1573134-2-fparent@baylibre.com Signed-off-by: Joerg Roedel --- drivers/iommu/mtk_iommu.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 94f676659ed5..655afcb8b624 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -118,6 +118,7 @@ #define OUT_ORDER_WR_EN BIT(4) #define HAS_SUB_COMM BIT(5) #define WR_THROT_EN BIT(6) +#define HAS_LEGACY_IVRP_PADDR BIT(7) #define MTK_IOMMU_HAS_FLAG(pdata, _x) \ ((((pdata)->flags) & (_x)) == (_x)) @@ -584,7 +585,7 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data) F_INT_PRETETCH_TRANSATION_FIFO_FAULT; writel_relaxed(regval, data->base + REG_MMU_INT_MAIN_CONTROL); - if (data->plat_data->m4u_plat == M4U_MT8173) + if (MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_LEGACY_IVRP_PADDR)) regval = (data->protect_base >> 1) | (data->enable_4GB << 31); else regval = lower_32_bits(data->protect_base) | @@ -841,7 +842,8 @@ static const struct mtk_iommu_plat_data mt6779_data = { static const struct mtk_iommu_plat_data mt8173_data = { .m4u_plat = M4U_MT8173, - .flags = HAS_4GB_MODE | HAS_BCLK | RESET_AXI, + .flags = HAS_4GB_MODE | HAS_BCLK | RESET_AXI | + HAS_LEGACY_IVRP_PADDR, .inv_sel_reg = REG_MMU_INV_SEL_GEN1, .larbid_remap = {{0}, {1}, {2}, {3}, {4}, {5}}, /* Linear mapping. */ }; -- cgit v1.2.3-58-ga151 From 3c213562fb3eba5c27032da219346e73cd240f9b Mon Sep 17 00:00:00 2001 From: Fabien Parent Date: Mon, 7 Sep 2020 12:16:49 +0200 Subject: iommu/mediatek: Add support for MT8167 Add support for the IOMMU on MT8167 Signed-off-by: Fabien Parent Reviewed-by: Yong Wu Link: https://lore.kernel.org/r/20200907101649.1573134-3-fparent@baylibre.com Signed-off-by: Joerg Roedel --- drivers/iommu/mtk_iommu.c | 8 ++++++++ drivers/iommu/mtk_iommu.h | 1 + 2 files changed, 9 insertions(+) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 655afcb8b624..c072cee532c2 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -840,6 +840,13 @@ static const struct mtk_iommu_plat_data mt6779_data = { .larbid_remap = {{0}, {1}, {2}, {3}, {5}, {7, 8}, {10}, {9}}, }; +static const struct mtk_iommu_plat_data mt8167_data = { + .m4u_plat = M4U_MT8167, + .flags = RESET_AXI | HAS_LEGACY_IVRP_PADDR, + .inv_sel_reg = REG_MMU_INV_SEL_GEN1, + .larbid_remap = {{0}, {1}, {2}}, /* Linear mapping. */ +}; + static const struct mtk_iommu_plat_data mt8173_data = { .m4u_plat = M4U_MT8173, .flags = HAS_4GB_MODE | HAS_BCLK | RESET_AXI | @@ -858,6 +865,7 @@ static const struct mtk_iommu_plat_data mt8183_data = { static const struct of_device_id mtk_iommu_of_ids[] = { { .compatible = "mediatek,mt2712-m4u", .data = &mt2712_data}, { .compatible = "mediatek,mt6779-m4u", .data = &mt6779_data}, + { .compatible = "mediatek,mt8167-m4u", .data = &mt8167_data}, { .compatible = "mediatek,mt8173-m4u", .data = &mt8173_data}, { .compatible = "mediatek,mt8183-m4u", .data = &mt8183_data}, {} diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h index 122925dbe547..df32b3e3408b 100644 --- a/drivers/iommu/mtk_iommu.h +++ b/drivers/iommu/mtk_iommu.h @@ -39,6 +39,7 @@ enum mtk_iommu_plat { M4U_MT2701, M4U_MT2712, M4U_MT6779, + M4U_MT8167, M4U_MT8173, M4U_MT8183, }; -- cgit v1.2.3-58-ga151 From d714aaa71594a4869b75689a32b23858e4021173 Mon Sep 17 00:00:00 2001 From: Lad Prabhakar Date: Fri, 11 Sep 2020 11:19:12 +0100 Subject: iommu/renesas: Update help description for IPMMU_VMSA config ipmmu-vmsa driver is also used on Renesas RZ/G{1,2} Soc's, update the same to reflect the help description for IPMMU_VMSA config. Signed-off-by: Lad Prabhakar Reviewed-by: Chris Paterson Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20200911101912.20701-1-prabhakar.mahadev-lad.rj@bp.renesas.com Signed-off-by: Joerg Roedel --- drivers/iommu/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index bef5d75e306b..d8f71bf31786 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -232,7 +232,7 @@ config IPMMU_VMSA select ARM_DMA_USE_IOMMU help Support for the Renesas VMSA-compatible IPMMU found in the R-Mobile - APE6, R-Car Gen2, and R-Car Gen3 SoCs. + APE6, R-Car Gen{2,3} and RZ/G{1,2} SoCs. If unsure, say N. -- cgit v1.2.3-58-ga151 From ce433d0f7063ab68de3a998de722d28f7a46d2a1 Mon Sep 17 00:00:00 2001 From: Alex Dewar Date: Fri, 11 Sep 2020 14:53:25 +0100 Subject: iommu/pamu: Replace use of kzfree with kfree_sensitive kzfree() is effectively deprecated as of commit 453431a54934 ("mm, treewide: rename kzfree() to kfree_sensitive()") and is now simply an alias for kfree_sensitive(). So just replace it with kfree_sensitive(). Signed-off-by: Alex Dewar Link: https://lore.kernel.org/r/20200911135325.66156-1-alex.dewar90@gmail.com Signed-off-by: Joerg Roedel --- drivers/iommu/fsl_pamu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/fsl_pamu.c b/drivers/iommu/fsl_pamu.c index 099a11a35fb9..b9a974d97831 100644 --- a/drivers/iommu/fsl_pamu.c +++ b/drivers/iommu/fsl_pamu.c @@ -1174,7 +1174,7 @@ error: if (irq != NO_IRQ) free_irq(irq, data); - kzfree(data); + kfree_sensitive(data); if (pamu_regs) iounmap(pamu_regs); -- cgit v1.2.3-58-ga151 From d5c152c3409ac1982a9277d8d344e073eda17e78 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Thu, 17 Sep 2020 04:31:54 -0700 Subject: iommu/tegra-smmu: Fix tlb_mask The "num_tlb_lines" might not be a power-of-2 value, being 48 on Tegra210 for example. So the current way of calculating tlb_mask using the num_tlb_lines is not correct: tlb_mask=0x5f in case of num_tlb_lines=48, which will trim a setting of 0x30 (48) to 0x10. Signed-off-by: Nicolin Chen Acked-by: Thierry Reding Link: https://lore.kernel.org/r/20200917113155.13438-2-nicoleotsuka@gmail.com Signed-off-by: Joerg Roedel --- drivers/iommu/tegra-smmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index 046add7acb61..9bfff94ca348 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -1111,7 +1111,7 @@ struct tegra_smmu *tegra_smmu_probe(struct device *dev, smmu->pfn_mask = BIT_MASK(mc->soc->num_address_bits - PAGE_SHIFT) - 1; dev_dbg(dev, "address bits: %u, PFN mask: %#lx\n", mc->soc->num_address_bits, smmu->pfn_mask); - smmu->tlb_mask = (smmu->soc->num_tlb_lines << 1) - 1; + smmu->tlb_mask = (1 << fls(smmu->soc->num_tlb_lines)) - 1; dev_dbg(dev, "TLB lines: %u, mask: %#lx\n", smmu->soc->num_tlb_lines, smmu->tlb_mask); -- cgit v1.2.3-58-ga151 From 675d12acb66bb190d32a3fae187e379f01cbd8ce Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Thu, 17 Sep 2020 04:31:55 -0700 Subject: memory: tegra: Correct num_tlb_lines for tegra210 According to Tegra210 TRM, the default value of TLB_ACTIVE_LINES field of register MC_SMMU_TLB_CONFIG_0 is 0x30. So num_tlb_lines should be 48 (0x30) rather than 32 (0x20). Signed-off-by: Nicolin Chen Acked-by: Thierry Reding Link: https://lore.kernel.org/r/20200917113155.13438-3-nicoleotsuka@gmail.com Signed-off-by: Joerg Roedel --- drivers/memory/tegra/tegra210.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/memory/tegra/tegra210.c b/drivers/memory/tegra/tegra210.c index cc0482434c75..7212d1d7b348 100644 --- a/drivers/memory/tegra/tegra210.c +++ b/drivers/memory/tegra/tegra210.c @@ -1073,7 +1073,7 @@ static const struct tegra_smmu_soc tegra210_smmu_soc = { .num_groups = ARRAY_SIZE(tegra210_groups), .supports_round_robin_arbitration = true, .supports_request_limit = true, - .num_tlb_lines = 32, + .num_tlb_lines = 48, .num_asids = 128, }; -- cgit v1.2.3-58-ga151 From b34e9b0de3c4117e70f09ae354d763cc4dd85bdf Mon Sep 17 00:00:00 2001 From: Tom Murphy Date: Thu, 10 Sep 2020 13:25:38 +0100 Subject: iommu/dma: Handle init_iova_flush_queue() failure in dma-iommu path The init_iova_flush_queue() function can fail if we run out of memory. Fall back to noflush queue if it fails. Signed-off-by: Tom Murphy Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/20200910122539.3662-1-murphyt7@tcd.ie Signed-off-by: Joerg Roedel --- drivers/iommu/dma-iommu.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 79b4d1073dcb..cd6e3c70ebb3 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -343,8 +343,11 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base, if (!cookie->fq_domain && !iommu_domain_get_attr(domain, DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE, &attr) && attr) { - cookie->fq_domain = domain; - init_iova_flush_queue(iovad, iommu_dma_flush_iotlb_all, NULL); + if (init_iova_flush_queue(iovad, iommu_dma_flush_iotlb_all, + NULL)) + pr_warn("iova flush queue initialization failed\n"); + else + cookie->fq_domain = domain; } if (!dev) -- cgit v1.2.3-58-ga151 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(-) 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 v1.2.3-58-ga151 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(-) 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 v1.2.3-58-ga151 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(-) 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 v1.2.3-58-ga151 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(-) 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 v1.2.3-58-ga151 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(-) 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 v1.2.3-58-ga151 From d2ef0962492c3be3563e53a431c285678849b3c1 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 22 Sep 2020 14:08:43 +0800 Subject: iommu/vt-d: Use device numa domain if RHSA is missing If there are multiple NUMA domains but the RHSA is missing in ACPI/DMAR table, we could default to the device NUMA domain as fall back. Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Cc: Jacob Pan Cc: Kevin Tian Cc: Ashok Raj Link: https://lore.kernel.org/r/20200904010303.2961-1-baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20200922060843.31546-2-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 37 +++++++++++++++++++++++++++++++++++-- 1 file changed, 35 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index f8177c59d229..077b69ff680b 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -700,12 +700,47 @@ static int domain_update_iommu_superpage(struct dmar_domain *domain, return fls(mask); } +static int domain_update_device_node(struct dmar_domain *domain) +{ + struct device_domain_info *info; + int nid = NUMA_NO_NODE; + + assert_spin_locked(&device_domain_lock); + + if (list_empty(&domain->devices)) + return NUMA_NO_NODE; + + list_for_each_entry(info, &domain->devices, link) { + if (!info->dev) + continue; + + /* + * There could possibly be multiple device numa nodes as devices + * within the same domain may sit behind different IOMMUs. There + * isn't perfect answer in such situation, so we select first + * come first served policy. + */ + nid = dev_to_node(info->dev); + if (nid != NUMA_NO_NODE) + break; + } + + return nid; +} + /* Some capabilities may be different across iommus */ static void domain_update_iommu_cap(struct dmar_domain *domain) { domain_update_iommu_coherency(domain); domain->iommu_snooping = domain_update_iommu_snooping(NULL); domain->iommu_superpage = domain_update_iommu_superpage(domain, NULL); + + /* + * If RHSA is missing, we should default to the device numa domain + * as fall back. + */ + if (domain->nid == NUMA_NO_NODE) + domain->nid = domain_update_device_node(domain); } struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus, @@ -5085,8 +5120,6 @@ static struct iommu_domain *intel_iommu_domain_alloc(unsigned type) if (type == IOMMU_DOMAIN_DMA) intel_init_iova_domain(dmar_domain); - domain_update_iommu_cap(dmar_domain); - domain = &dmar_domain->domain; domain->geometry.aperture_start = 0; domain->geometry.aperture_end = -- cgit v1.2.3-58-ga151 From 82fa58e81d9edc77182aaba4110c3124481e6704 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Fri, 11 Sep 2020 00:16:41 -0700 Subject: iommu/tegra-smmu: Do not use PAGE_SHIFT and PAGE_MASK PAGE_SHIFT and PAGE_MASK are defined corresponding to the page size for CPU virtual addresses, which means PAGE_SHIFT could be a number other than 12, but tegra-smmu maintains fixed 4KB IOVA pages and has fixed [21:12] bit range for PTE entries. So this patch replaces all PAGE_SHIFT/PAGE_MASK references with the macros defined with SMMU_PTE_SHIFT. Signed-off-by: Nicolin Chen Acked-by: Thierry Reding Link: https://lore.kernel.org/r/20200911071643.17212-2-nicoleotsuka@gmail.com Signed-off-by: Joerg Roedel --- drivers/iommu/tegra-smmu.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index 9bfff94ca348..bd473e085aac 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -130,6 +130,11 @@ static inline u32 smmu_readl(struct tegra_smmu *smmu, unsigned long offset) #define SMMU_PDE_SHIFT 22 #define SMMU_PTE_SHIFT 12 +#define SMMU_PAGE_MASK (~(SMMU_SIZE_PT-1)) +#define SMMU_OFFSET_IN_PAGE(x) ((unsigned long)(x) & ~SMMU_PAGE_MASK) +#define SMMU_PFN_PHYS(x) ((phys_addr_t)(x) << SMMU_PTE_SHIFT) +#define SMMU_PHYS_PFN(x) ((unsigned long)((x) >> SMMU_PTE_SHIFT)) + #define SMMU_PD_READABLE (1 << 31) #define SMMU_PD_WRITABLE (1 << 30) #define SMMU_PD_NONSECURE (1 << 29) @@ -644,7 +649,7 @@ static void tegra_smmu_set_pte(struct tegra_smmu_as *as, unsigned long iova, u32 *pte, dma_addr_t pte_dma, u32 val) { struct tegra_smmu *smmu = as->smmu; - unsigned long offset = offset_in_page(pte); + unsigned long offset = SMMU_OFFSET_IN_PAGE(pte); *pte = val; @@ -726,7 +731,7 @@ __tegra_smmu_map(struct iommu_domain *domain, unsigned long iova, pte_attrs |= SMMU_PTE_WRITABLE; tegra_smmu_set_pte(as, iova, pte, pte_dma, - __phys_to_pfn(paddr) | pte_attrs); + SMMU_PHYS_PFN(paddr) | pte_attrs); return 0; } @@ -790,7 +795,7 @@ static phys_addr_t tegra_smmu_iova_to_phys(struct iommu_domain *domain, pfn = *pte & as->smmu->pfn_mask; - return PFN_PHYS(pfn); + return SMMU_PFN_PHYS(pfn); } static struct tegra_smmu *tegra_smmu_find(struct device_node *np) @@ -1108,7 +1113,8 @@ struct tegra_smmu *tegra_smmu_probe(struct device *dev, smmu->dev = dev; smmu->mc = mc; - smmu->pfn_mask = BIT_MASK(mc->soc->num_address_bits - PAGE_SHIFT) - 1; + smmu->pfn_mask = + BIT_MASK(mc->soc->num_address_bits - SMMU_PTE_SHIFT) - 1; dev_dbg(dev, "address bits: %u, PFN mask: %#lx\n", mc->soc->num_address_bits, smmu->pfn_mask); smmu->tlb_mask = (1 << fls(smmu->soc->num_tlb_lines)) - 1; -- cgit v1.2.3-58-ga151 From 4fba98859b819961d8e1fe862b79052ff4b687b8 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Fri, 11 Sep 2020 00:16:42 -0700 Subject: iommu/tegra-smmu: Fix iova->phys translation IOVA might not be always 4KB aligned. So tegra_smmu_iova_to_phys function needs to add on the lower 12-bit offset from input iova. Signed-off-by: Nicolin Chen Acked-by: Thierry Reding Link: https://lore.kernel.org/r/20200911071643.17212-3-nicoleotsuka@gmail.com Signed-off-by: Joerg Roedel --- drivers/iommu/tegra-smmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index bd473e085aac..e6d142458950 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -795,7 +795,7 @@ static phys_addr_t tegra_smmu_iova_to_phys(struct iommu_domain *domain, pfn = *pte & as->smmu->pfn_mask; - return SMMU_PFN_PHYS(pfn); + return SMMU_PFN_PHYS(pfn) + SMMU_OFFSET_IN_PAGE(iova); } static struct tegra_smmu *tegra_smmu_find(struct device_node *np) -- cgit v1.2.3-58-ga151 From 21d3c0402a396f8db9856792193f5e1ee1818aa7 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Fri, 11 Sep 2020 00:16:43 -0700 Subject: iommu/tegra-smmu: Allow to group clients in same swgroup There can be clients using the same swgroup in DT, for example i2c0 and i2c1. The current driver will add them to separate IOMMU groups, though it has implemented device_group() callback which is to group devices using different swgroups like DC and DCB. All clients having the same swgroup should be also added to the same IOMMU group so as to share an asid. Otherwise, the asid register may get overwritten every time a new device is attached. Signed-off-by: Nicolin Chen Acked-by: Thierry Reding Link: https://lore.kernel.org/r/20200911071643.17212-4-nicoleotsuka@gmail.com Signed-off-by: Joerg Roedel --- drivers/iommu/tegra-smmu.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index e6d142458950..0becdbfea306 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -23,6 +23,7 @@ struct tegra_smmu_group { struct tegra_smmu *smmu; const struct tegra_smmu_group_soc *soc; struct iommu_group *group; + unsigned int swgroup; }; struct tegra_smmu { @@ -909,14 +910,14 @@ static struct iommu_group *tegra_smmu_group_get(struct tegra_smmu *smmu, struct tegra_smmu_group *group; struct iommu_group *grp; + /* Find group_soc associating with swgroup */ soc = tegra_smmu_find_group(smmu, swgroup); - if (!soc) - return NULL; mutex_lock(&smmu->lock); + /* Find existing iommu_group associating with swgroup or group_soc */ list_for_each_entry(group, &smmu->groups, list) - if (group->soc == soc) { + if ((group->swgroup == swgroup) || (soc && group->soc == soc)) { grp = iommu_group_ref_get(group->group); mutex_unlock(&smmu->lock); return grp; @@ -929,6 +930,7 @@ static struct iommu_group *tegra_smmu_group_get(struct tegra_smmu *smmu, } INIT_LIST_HEAD(&group->list); + group->swgroup = swgroup; group->smmu = smmu; group->soc = soc; @@ -940,7 +942,8 @@ static struct iommu_group *tegra_smmu_group_get(struct tegra_smmu *smmu, } iommu_group_set_iommudata(group->group, group, tegra_smmu_group_release); - iommu_group_set_name(group->group, soc->name); + if (soc) + iommu_group_set_name(group->group, soc->name); list_add_tail(&group->list, &smmu->groups); mutex_unlock(&smmu->lock); -- cgit v1.2.3-58-ga151 From c69d89aff393a212b9635c95990173b48d8bd74d Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Wed, 23 Sep 2020 12:13:45 +0000 Subject: iommu/amd: Use 4K page for completion wait write-back semaphore IOMMU SNP support requires the completion wait write-back semaphore to be implemented using a 4K-aligned page, where the page address is to be programmed into the newly introduced MMIO base/range registers. This new scheme uses a per-iommu atomic variable to store the current semaphore value, which is incremented for every completion wait command. Since this new scheme is also compatible with non-SNP mode, generalize the driver to use 4K page for completion-wait semaphore in both modes. Signed-off-by: Suravee Suthikulpanit Cc: Brijesh Singh Link: https://lore.kernel.org/r/20200923121347.25365-2-suravee.suthikulpanit@amd.com Signed-off-by: Joerg Roedel --- drivers/iommu/amd/amd_iommu_types.h | 3 ++- drivers/iommu/amd/init.c | 18 ++++++++++++++++++ drivers/iommu/amd/iommu.c | 23 +++++++++++------------ 3 files changed, 31 insertions(+), 13 deletions(-) diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 30a5d412255a..4c80483e78ec 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -595,7 +595,8 @@ struct amd_iommu { #endif u32 flags; - volatile u64 __aligned(8) cmd_sem; + volatile u64 *cmd_sem; + u64 cmd_sem_val; #ifdef CONFIG_AMD_IOMMU_DEBUGFS /* DebugFS Info */ diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 908d8e89764c..35f220704bef 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -813,6 +813,19 @@ static int iommu_init_ga(struct amd_iommu *iommu) return ret; } +static int __init alloc_cwwb_sem(struct amd_iommu *iommu) +{ + iommu->cmd_sem = (void *)get_zeroed_page(GFP_KERNEL); + + return iommu->cmd_sem ? 0 : -ENOMEM; +} + +static void __init free_cwwb_sem(struct amd_iommu *iommu) +{ + if (iommu->cmd_sem) + free_page((unsigned long)iommu->cmd_sem); +} + static void iommu_enable_xt(struct amd_iommu *iommu) { #ifdef CONFIG_IRQ_REMAP @@ -1395,6 +1408,7 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu, static void __init free_iommu_one(struct amd_iommu *iommu) { + free_cwwb_sem(iommu); free_command_buffer(iommu); free_event_buffer(iommu); free_ppr_log(iommu); @@ -1481,6 +1495,7 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h) int ret; raw_spin_lock_init(&iommu->lock); + iommu->cmd_sem_val = 0; /* Add IOMMU to internal data structures */ list_add_tail(&iommu->list, &amd_iommu_list); @@ -1541,6 +1556,9 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h) if (!iommu->mmio_base) return -ENOMEM; + if (alloc_cwwb_sem(iommu)) + return -ENOMEM; + if (alloc_command_buffer(iommu)) return -ENOMEM; diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index ba9f3dbc5b94..a23e14e8a942 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -792,11 +792,11 @@ irqreturn_t amd_iommu_int_handler(int irq, void *data) * ****************************************************************************/ -static int wait_on_sem(volatile u64 *sem) +static int wait_on_sem(struct amd_iommu *iommu, u64 data) { int i = 0; - while (*sem == 0 && i < LOOP_TIMEOUT) { + while (*iommu->cmd_sem != data && i < LOOP_TIMEOUT) { udelay(1); i += 1; } @@ -827,16 +827,16 @@ static void copy_cmd_to_buffer(struct amd_iommu *iommu, writel(tail, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET); } -static void build_completion_wait(struct iommu_cmd *cmd, u64 address) +static void build_completion_wait(struct iommu_cmd *cmd, + struct amd_iommu *iommu, + u64 data) { - u64 paddr = iommu_virt_to_phys((void *)address); - - WARN_ON(address & 0x7ULL); + u64 paddr = iommu_virt_to_phys((void *)iommu->cmd_sem); memset(cmd, 0, sizeof(*cmd)); cmd->data[0] = lower_32_bits(paddr) | CMD_COMPL_WAIT_STORE_MASK; cmd->data[1] = upper_32_bits(paddr); - cmd->data[2] = 1; + cmd->data[2] = data; CMD_SET_TYPE(cmd, CMD_COMPL_WAIT); } @@ -1045,22 +1045,21 @@ static int iommu_completion_wait(struct amd_iommu *iommu) struct iommu_cmd cmd; unsigned long flags; int ret; + u64 data; if (!iommu->need_sync) return 0; - - build_completion_wait(&cmd, (u64)&iommu->cmd_sem); - raw_spin_lock_irqsave(&iommu->lock, flags); - iommu->cmd_sem = 0; + data = ++iommu->cmd_sem_val; + build_completion_wait(&cmd, iommu, data); ret = __iommu_queue_command_sync(iommu, &cmd, false); if (ret) goto out_unlock; - ret = wait_on_sem(&iommu->cmd_sem); + ret = wait_on_sem(iommu, data); out_unlock: raw_spin_unlock_irqrestore(&iommu->lock, flags); -- cgit v1.2.3-58-ga151 From 2818de6e87defc3103fd86bf6357658f7d2a661a Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Wed, 23 Sep 2020 12:13:46 +0000 Subject: iommu/amd: Add support for RMP_PAGE_FAULT and RMP_HW_ERR IOMMU SNP support introduces two new IOMMU events: * RMP Page Fault event * RMP Hardware Error event Hence, add reporting functions for these events. Signed-off-by: Suravee Suthikulpanit Cc: Brijesh Singh Link: https://lore.kernel.org/r/20200923121347.25365-3-suravee.suthikulpanit@amd.com Signed-off-by: Joerg Roedel --- drivers/iommu/amd/amd_iommu_types.h | 2 ++ drivers/iommu/amd/iommu.c | 67 +++++++++++++++++++++++++++++++++++++ 2 files changed, 69 insertions(+) diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 4c80483e78ec..1e7966c73707 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -128,6 +128,8 @@ #define EVENT_TYPE_IOTLB_INV_TO 0x7 #define EVENT_TYPE_INV_DEV_REQ 0x8 #define EVENT_TYPE_INV_PPR_REQ 0x9 +#define EVENT_TYPE_RMP_FAULT 0xd +#define EVENT_TYPE_RMP_HW_ERR 0xe #define EVENT_DEVID_MASK 0xffff #define EVENT_DEVID_SHIFT 0 #define EVENT_DOMID_MASK_LO 0xffff diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index a23e14e8a942..292467e90b4f 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -486,6 +486,67 @@ static void dump_command(unsigned long phys_addr) pr_err("CMD[%d]: %08x\n", i, cmd->data[i]); } +static void amd_iommu_report_rmp_hw_error(volatile u32 *event) +{ + struct iommu_dev_data *dev_data = NULL; + int devid, vmg_tag, flags; + struct pci_dev *pdev; + u64 spa; + + devid = (event[0] >> EVENT_DEVID_SHIFT) & EVENT_DEVID_MASK; + vmg_tag = (event[1]) & 0xFFFF; + flags = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK; + spa = ((u64)event[3] << 32) | (event[2] & 0xFFFFFFF8); + + pdev = pci_get_domain_bus_and_slot(0, PCI_BUS_NUM(devid), + devid & 0xff); + if (pdev) + dev_data = dev_iommu_priv_get(&pdev->dev); + + if (dev_data && __ratelimit(&dev_data->rs)) { + pci_err(pdev, "Event logged [RMP_HW_ERROR vmg_tag=0x%04x, spa=0x%llx, flags=0x%04x]\n", + vmg_tag, spa, flags); + } else { + pr_err_ratelimited("Event logged [RMP_HW_ERROR device=%02x:%02x.%x, vmg_tag=0x%04x, spa=0x%llx, flags=0x%04x]\n", + PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid), + vmg_tag, spa, flags); + } + + if (pdev) + pci_dev_put(pdev); +} + +static void amd_iommu_report_rmp_fault(volatile u32 *event) +{ + struct iommu_dev_data *dev_data = NULL; + int devid, flags_rmp, vmg_tag, flags; + struct pci_dev *pdev; + u64 gpa; + + devid = (event[0] >> EVENT_DEVID_SHIFT) & EVENT_DEVID_MASK; + flags_rmp = (event[0] >> EVENT_FLAGS_SHIFT) & 0xFF; + vmg_tag = (event[1]) & 0xFFFF; + flags = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK; + gpa = ((u64)event[3] << 32) | event[2]; + + pdev = pci_get_domain_bus_and_slot(0, PCI_BUS_NUM(devid), + devid & 0xff); + if (pdev) + dev_data = dev_iommu_priv_get(&pdev->dev); + + if (dev_data && __ratelimit(&dev_data->rs)) { + pci_err(pdev, "Event logged [RMP_PAGE_FAULT vmg_tag=0x%04x, gpa=0x%llx, flags_rmp=0x%04x, flags=0x%04x]\n", + vmg_tag, gpa, flags_rmp, flags); + } else { + pr_err_ratelimited("Event logged [RMP_PAGE_FAULT device=%02x:%02x.%x, vmg_tag=0x%04x, gpa=0x%llx, flags_rmp=0x%04x, flags=0x%04x]\n", + PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid), + vmg_tag, gpa, flags_rmp, flags); + } + + if (pdev) + pci_dev_put(pdev); +} + static void amd_iommu_report_page_fault(u16 devid, u16 domain_id, u64 address, int flags) { @@ -577,6 +638,12 @@ retry: PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid), pasid, address, flags); break; + case EVENT_TYPE_RMP_FAULT: + amd_iommu_report_rmp_fault(event); + break; + case EVENT_TYPE_RMP_HW_ERR: + amd_iommu_report_rmp_hw_error(event); + break; case EVENT_TYPE_INV_PPR_REQ: pasid = PPR_PASID(*((u64 *)__evt)); tag = event[1] & 0x03FF; -- cgit v1.2.3-58-ga151 From 54ce12e02e44feffa6de4f3a069b7d5c7262a966 Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Wed, 23 Sep 2020 12:13:47 +0000 Subject: iommu/amd: Re-purpose Exclusion range registers to support SNP CWWB When the IOMMU SNP support bit is set in the IOMMU Extended Features register, hardware re-purposes the following registers: 1. IOMMU Exclusion Base register (MMIO offset 0020h) to Completion Wait Write-Back (CWWB) Base register 2. IOMMU Exclusion Range Limit (MMIO offset 0028h) to Completion Wait Write-Back (CWWB) Range Limit register and requires the IOMMU CWWB semaphore base and range to be programmed in the register offset 0020h and 0028h accordingly. Signed-off-by: Suravee Suthikulpanit Cc: Brijesh Singh Link: https://lore.kernel.org/r/20200923121347.25365-4-suravee.suthikulpanit@amd.com Signed-off-by: Joerg Roedel --- drivers/iommu/amd/amd_iommu_types.h | 1 + drivers/iommu/amd/init.c | 26 ++++++++++++++++++++++++++ 2 files changed, 27 insertions(+) diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 1e7966c73707..f696ac7c5f89 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -93,6 +93,7 @@ #define FEATURE_PC (1ULL<<9) #define FEATURE_GAM_VAPIC (1ULL<<21) #define FEATURE_EPHSUP (1ULL<<50) +#define FEATURE_SNP (1ULL<<63) #define FEATURE_PASID_SHIFT 32 #define FEATURE_PASID_MASK (0x1fULL << FEATURE_PASID_SHIFT) diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 35f220704bef..662b01eaf0f2 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -359,6 +359,29 @@ static void iommu_set_exclusion_range(struct amd_iommu *iommu) &entry, sizeof(entry)); } +static void iommu_set_cwwb_range(struct amd_iommu *iommu) +{ + u64 start = iommu_virt_to_phys((void *)iommu->cmd_sem); + u64 entry = start & PM_ADDR_MASK; + + if (!iommu_feature(iommu, FEATURE_SNP)) + return; + + /* Note: + * Re-purpose Exclusion base/limit registers for Completion wait + * write-back base/limit. + */ + memcpy_toio(iommu->mmio_base + MMIO_EXCL_BASE_OFFSET, + &entry, sizeof(entry)); + + /* Note: + * Default to 4 Kbytes, which can be specified by setting base + * address equal to the limit address. + */ + memcpy_toio(iommu->mmio_base + MMIO_EXCL_LIMIT_OFFSET, + &entry, sizeof(entry)); +} + /* Programs the physical address of the device table into the IOMMU hardware */ static void iommu_set_device_table(struct amd_iommu *iommu) { @@ -1884,6 +1907,9 @@ static int __init amd_iommu_init_pci(void) ret = iommu_init_pci(iommu); if (ret) break; + + /* Need to setup range after PCI init */ + iommu_set_cwwb_range(iommu); } /* -- cgit v1.2.3-58-ga151 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(-) 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 v1.2.3-58-ga151 From 7cef39ddba73077ef00de24c9f6bfc216658fafe Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Fri, 18 Sep 2020 12:18:45 +0200 Subject: iommu/io-pgtable-arm: Move some definitions to a header Extract some of the most generic TCR defines, so they can be reused by the page table sharing code. Signed-off-by: Jean-Philippe Brucker Reviewed-by: Jonathan Cameron Acked-by: Will Deacon Link: https://lore.kernel.org/r/20200918101852.582559-6-jean-philippe@linaro.org Signed-off-by: Will Deacon --- MAINTAINERS | 3 +-- drivers/iommu/io-pgtable-arm.c | 27 ++------------------------- drivers/iommu/io-pgtable-arm.h | 30 ++++++++++++++++++++++++++++++ 3 files changed, 33 insertions(+), 27 deletions(-) create mode 100644 drivers/iommu/io-pgtable-arm.h diff --git a/MAINTAINERS b/MAINTAINERS index e4647c84c987..d02d6e63577b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1506,8 +1506,7 @@ L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: Documentation/devicetree/bindings/iommu/arm,smmu* F: drivers/iommu/arm/ -F: drivers/iommu/io-pgtable-arm-v7s.c -F: drivers/iommu/io-pgtable-arm.c +F: drivers/iommu/io-pgtable-arm* ARM SUB-ARCHITECTURES L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index dc7bcf858b6d..534810b6be77 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -20,6 +20,8 @@ #include +#include "io-pgtable-arm.h" + #define ARM_LPAE_MAX_ADDR_BITS 52 #define ARM_LPAE_S2_MAX_CONCAT_PAGES 16 #define ARM_LPAE_MAX_LEVELS 4 @@ -100,23 +102,6 @@ #define ARM_LPAE_PTE_MEMATTR_DEV (((arm_lpae_iopte)0x1) << 2) /* Register bits */ -#define ARM_LPAE_TCR_TG0_4K 0 -#define ARM_LPAE_TCR_TG0_64K 1 -#define ARM_LPAE_TCR_TG0_16K 2 - -#define ARM_LPAE_TCR_TG1_16K 1 -#define ARM_LPAE_TCR_TG1_4K 2 -#define ARM_LPAE_TCR_TG1_64K 3 - -#define ARM_LPAE_TCR_SH_NS 0 -#define ARM_LPAE_TCR_SH_OS 2 -#define ARM_LPAE_TCR_SH_IS 3 - -#define ARM_LPAE_TCR_RGN_NC 0 -#define ARM_LPAE_TCR_RGN_WBWA 1 -#define ARM_LPAE_TCR_RGN_WT 2 -#define ARM_LPAE_TCR_RGN_WB 3 - #define ARM_LPAE_VTCR_SL0_MASK 0x3 #define ARM_LPAE_TCR_T0SZ_SHIFT 0 @@ -124,14 +109,6 @@ #define ARM_LPAE_VTCR_PS_SHIFT 16 #define ARM_LPAE_VTCR_PS_MASK 0x7 -#define ARM_LPAE_TCR_PS_32_BIT 0x0ULL -#define ARM_LPAE_TCR_PS_36_BIT 0x1ULL -#define ARM_LPAE_TCR_PS_40_BIT 0x2ULL -#define ARM_LPAE_TCR_PS_42_BIT 0x3ULL -#define ARM_LPAE_TCR_PS_44_BIT 0x4ULL -#define ARM_LPAE_TCR_PS_48_BIT 0x5ULL -#define ARM_LPAE_TCR_PS_52_BIT 0x6ULL - #define ARM_LPAE_MAIR_ATTR_SHIFT(n) ((n) << 3) #define ARM_LPAE_MAIR_ATTR_MASK 0xff #define ARM_LPAE_MAIR_ATTR_DEVICE 0x04 diff --git a/drivers/iommu/io-pgtable-arm.h b/drivers/iommu/io-pgtable-arm.h new file mode 100644 index 000000000000..ba7cfdf7afa0 --- /dev/null +++ b/drivers/iommu/io-pgtable-arm.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef IO_PGTABLE_ARM_H_ +#define IO_PGTABLE_ARM_H_ + +#define ARM_LPAE_TCR_TG0_4K 0 +#define ARM_LPAE_TCR_TG0_64K 1 +#define ARM_LPAE_TCR_TG0_16K 2 + +#define ARM_LPAE_TCR_TG1_16K 1 +#define ARM_LPAE_TCR_TG1_4K 2 +#define ARM_LPAE_TCR_TG1_64K 3 + +#define ARM_LPAE_TCR_SH_NS 0 +#define ARM_LPAE_TCR_SH_OS 2 +#define ARM_LPAE_TCR_SH_IS 3 + +#define ARM_LPAE_TCR_RGN_NC 0 +#define ARM_LPAE_TCR_RGN_WBWA 1 +#define ARM_LPAE_TCR_RGN_WT 2 +#define ARM_LPAE_TCR_RGN_WB 3 + +#define ARM_LPAE_TCR_PS_32_BIT 0x0ULL +#define ARM_LPAE_TCR_PS_36_BIT 0x1ULL +#define ARM_LPAE_TCR_PS_40_BIT 0x2ULL +#define ARM_LPAE_TCR_PS_42_BIT 0x3ULL +#define ARM_LPAE_TCR_PS_44_BIT 0x4ULL +#define ARM_LPAE_TCR_PS_48_BIT 0x5ULL +#define ARM_LPAE_TCR_PS_52_BIT 0x6ULL + +#endif /* IO_PGTABLE_ARM_H_ */ -- cgit v1.2.3-58-ga151 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 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 v1.2.3-58-ga151 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 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 v1.2.3-58-ga151 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(-) 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 v1.2.3-58-ga151 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(+) 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 v1.2.3-58-ga151 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(+) 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 v1.2.3-58-ga151 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(-) 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 v1.2.3-58-ga151 From d0023e3ee28d12b2b0af4856c405f3d13fb59d1c Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Fri, 25 Sep 2020 09:32:42 -0700 Subject: docs: IOMMU user API IOMMU UAPI is newly introduced to support communications between guest virtual IOMMU and host IOMMU. There has been lots of discussions on how it should work with VFIO UAPI and userspace in general. This document is intended to clarify the UAPI design and usage. The mechanics of how future extensions should be achieved are also covered in this documentation. Signed-off-by: Liu Yi L Signed-off-by: Jacob Pan Reviewed-by: Eric Auger Cc: linux-api@vger.kernel.org Cc: Jonathan Corbet Cc: linux-doc@vger.kernel.org Link: https://lore.kernel.org/r/1601051567-54787-2-git-send-email-jacob.jun.pan@linux.intel.com Signed-off-by: Joerg Roedel --- Documentation/userspace-api/iommu.rst | 209 ++++++++++++++++++++++++++++++++++ MAINTAINERS | 1 + 2 files changed, 210 insertions(+) create mode 100644 Documentation/userspace-api/iommu.rst diff --git a/Documentation/userspace-api/iommu.rst b/Documentation/userspace-api/iommu.rst new file mode 100644 index 000000000000..d3108c1519d5 --- /dev/null +++ b/Documentation/userspace-api/iommu.rst @@ -0,0 +1,209 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. iommu: + +===================================== +IOMMU Userspace API +===================================== + +IOMMU UAPI is used for virtualization cases where communications are +needed between physical and virtual IOMMU drivers. For baremetal +usage, the IOMMU is a system device which does not need to communicate +with userspace directly. + +The primary use cases are guest Shared Virtual Address (SVA) and +guest IO virtual address (IOVA), wherein the vIOMMU implementation +relies on the physical IOMMU and for this reason requires interactions +with the host driver. + +.. contents:: :local: + +Functionalities +=============== +Communications of user and kernel involve both directions. The +supported user-kernel APIs are as follows: + +1. Bind/Unbind guest PASID (e.g. Intel VT-d) +2. Bind/Unbind guest PASID table (e.g. ARM SMMU) +3. Invalidate IOMMU caches upon guest requests +4. Report errors to the guest and serve page requests + +Requirements +============ +The IOMMU UAPIs are generic and extensible to meet the following +requirements: + +1. Emulated and para-virtualised vIOMMUs +2. Multiple vendors (Intel VT-d, ARM SMMU, etc.) +3. Extensions to the UAPI shall not break existing userspace + +Interfaces +========== +Although the data structures defined in IOMMU UAPI are self-contained, +there are no user API functions introduced. Instead, IOMMU UAPI is +designed to work with existing user driver frameworks such as VFIO. + +Extension Rules & Precautions +----------------------------- +When IOMMU UAPI gets extended, the data structures can *only* be +modified in two ways: + +1. Adding new fields by re-purposing the padding[] field. No size change. +2. Adding new union members at the end. May increase the structure sizes. + +No new fields can be added *after* the variable sized union in that it +will break backward compatibility when offset moves. A new flag must +be introduced whenever a change affects the structure using either +method. The IOMMU driver processes the data based on flags which +ensures backward compatibility. + +Version field is only reserved for the unlikely event of UAPI upgrade +at its entirety. + +It's *always* the caller's responsibility to indicate the size of the +structure passed by setting argsz appropriately. +Though at the same time, argsz is user provided data which is not +trusted. The argsz field allows the user app to indicate how much data +it is providing; it's still the kernel's responsibility to validate +whether it's correct and sufficient for the requested operation. + +Compatibility Checking +---------------------- +When IOMMU UAPI extension results in some structure size increase, +IOMMU UAPI code shall handle the following cases: + +1. User and kernel has exact size match +2. An older user with older kernel header (smaller UAPI size) running on a + newer kernel (larger UAPI size) +3. A newer user with newer kernel header (larger UAPI size) running + on an older kernel. +4. A malicious/misbehaving user passing illegal/invalid size but within + range. The data may contain garbage. + +Feature Checking +---------------- +While launching a guest with vIOMMU, it is strongly advised to check +the compatibility upfront, as some subsequent errors happening during +vIOMMU operation, such as cache invalidation failures cannot be nicely +escalated to the guest due to IOMMU specifications. This can lead to +catastrophic failures for the users. + +User applications such as QEMU are expected to import kernel UAPI +headers. Backward compatibility is supported per feature flags. +For example, an older QEMU (with older kernel header) can run on newer +kernel. Newer QEMU (with new kernel header) may refuse to initialize +on an older kernel if new feature flags are not supported by older +kernel. Simply recompiling existing code with newer kernel header should +not be an issue in that only existing flags are used. + +IOMMU vendor driver should report the below features to IOMMU UAPI +consumers (e.g. via VFIO). + +1. IOMMU_NESTING_FEAT_SYSWIDE_PASID +2. IOMMU_NESTING_FEAT_BIND_PGTBL +3. IOMMU_NESTING_FEAT_BIND_PASID_TABLE +4. IOMMU_NESTING_FEAT_CACHE_INVLD +5. IOMMU_NESTING_FEAT_PAGE_REQUEST + +Take VFIO as example, upon request from VFIO userspace (e.g. QEMU), +VFIO kernel code shall query IOMMU vendor driver for the support of +the above features. Query result can then be reported back to the +userspace caller. Details can be found in +Documentation/driver-api/vfio.rst. + + +Data Passing Example with VFIO +------------------------------ +As the ubiquitous userspace driver framework, VFIO is already IOMMU +aware and shares many key concepts such as device model, group, and +protection domain. Other user driver frameworks can also be extended +to support IOMMU UAPI but it is outside the scope of this document. + +In this tight-knit VFIO-IOMMU interface, the ultimate consumer of the +IOMMU UAPI data is the host IOMMU driver. VFIO facilitates user-kernel +transport, capability checking, security, and life cycle management of +process address space ID (PASID). + +VFIO layer conveys the data structures down to the IOMMU driver. It +follows the pattern below:: + + struct { + __u32 argsz; + __u32 flags; + __u8 data[]; + }; + +Here data[] contains the IOMMU UAPI data structures. VFIO has the +freedom to bundle the data as well as parse data size based on its own flags. + +In order to determine the size and feature set of the user data, argsz +and flags (or the equivalent) are also embedded in the IOMMU UAPI data +structures. + +A "__u32 argsz" field is *always* at the beginning of each structure. + +For example: +:: + + struct iommu_cache_invalidate_info { + __u32 argsz; + #define IOMMU_CACHE_INVALIDATE_INFO_VERSION_1 1 + __u32 version; + /* IOMMU paging structure cache */ + #define IOMMU_CACHE_INV_TYPE_IOTLB (1 << 0) /* IOMMU IOTLB */ + #define IOMMU_CACHE_INV_TYPE_DEV_IOTLB (1 << 1) /* Device IOTLB */ + #define IOMMU_CACHE_INV_TYPE_PASID (1 << 2) /* PASID cache */ + #define IOMMU_CACHE_INV_TYPE_NR (3) + __u8 cache; + __u8 granularity; + __u8 padding[6]; + union { + struct iommu_inv_pasid_info pasid_info; + struct iommu_inv_addr_info addr_info; + } granu; + }; + +VFIO is responsible for checking its own argsz and flags. It then +invokes appropriate IOMMU UAPI functions. The user pointers are passed +to the IOMMU layer for further processing. The responsibilities are +divided as follows: + +- Generic IOMMU layer checks argsz range based on UAPI data in the + current kernel version. + +- Generic IOMMU layer checks content of the UAPI data for non-zero + reserved bits in flags, padding fields, and unsupported version. + This is to ensure not breaking userspace in the future when these + fields or flags are used. + +- Vendor IOMMU driver checks argsz based on vendor flags. UAPI data + is consumed based on flags. Vendor driver has access to + unadulterated argsz value in case of vendor specific future + extensions. Currently, it does not perform the copy_from_user() + itself. A __user pointer can be provided in some future scenarios + where there's vendor data outside of the structure definition. + +IOMMU code treats UAPI data in two categories: + +- structure contains vendor data + (Example: iommu_uapi_cache_invalidate()) + +- structure contains only generic data + (Example: iommu_uapi_sva_bind_gpasid()) + + + +Sharing UAPI with in-kernel users +--------------------------------- +For UAPIs that are shared with in-kernel users, a wrapper function is +provided to distinguish the callers. For example, + +Userspace caller :: + + int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, + struct device *dev, + void __user *udata) + +In-kernel caller :: + + int iommu_sva_unbind_gpasid(struct iommu_domain *domain, + struct device *dev, ioasid_t ioasid); diff --git a/MAINTAINERS b/MAINTAINERS index e4647c84c987..7d89d8d5ea77 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9101,6 +9101,7 @@ L: iommu@lists.linux-foundation.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git F: Documentation/devicetree/bindings/iommu/ +F: Documentation/userspace-api/iommu.rst F: drivers/iommu/ F: include/linux/iommu.h F: include/linux/iova.h -- cgit v1.2.3-58-ga151 From 1e6aaae93e9ddb9dc664993eb949b1da94cab3a5 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Fri, 25 Sep 2020 09:32:43 -0700 Subject: iommu/uapi: Add argsz for user filled data As IOMMU UAPI gets extended, user data size may increase. To support backward compatibiliy, this patch introduces a size field to each UAPI data structures. It is *always* the responsibility for the user to fill in the correct size. Padding fields are adjusted to ensure 8 byte alignment. Specific scenarios for user data handling are documented in: Documentation/userspace-api/iommu.rst As there is no current users of the API, struct version is not incremented. Signed-off-by: Liu Yi L Signed-off-by: Jacob Pan Reviewed-by: Eric Auger Link: https://lore.kernel.org/r/1601051567-54787-3-git-send-email-jacob.jun.pan@linux.intel.com Signed-off-by: Joerg Roedel --- include/uapi/linux/iommu.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h index c2b2caf9ed41..b42acc8fe007 100644 --- a/include/uapi/linux/iommu.h +++ b/include/uapi/linux/iommu.h @@ -139,6 +139,7 @@ enum iommu_page_response_code { /** * struct iommu_page_response - Generic page response information + * @argsz: User filled size of this data * @version: API version of this structure * @flags: encodes whether the corresponding fields are valid * (IOMMU_FAULT_PAGE_RESPONSE_* values) @@ -147,6 +148,7 @@ enum iommu_page_response_code { * @code: response code from &enum iommu_page_response_code */ struct iommu_page_response { + __u32 argsz; #define IOMMU_PAGE_RESP_VERSION_1 1 __u32 version; #define IOMMU_PAGE_RESP_PASID_VALID (1 << 0) @@ -222,6 +224,7 @@ struct iommu_inv_pasid_info { /** * struct iommu_cache_invalidate_info - First level/stage invalidation * information + * @argsz: User filled size of this data * @version: API version of this structure * @cache: bitfield that allows to select which caches to invalidate * @granularity: defines the lowest granularity used for the invalidation: @@ -250,6 +253,7 @@ struct iommu_inv_pasid_info { * must support the used granularity. */ struct iommu_cache_invalidate_info { + __u32 argsz; #define IOMMU_CACHE_INVALIDATE_INFO_VERSION_1 1 __u32 version; /* IOMMU paging structure cache */ @@ -259,7 +263,7 @@ struct iommu_cache_invalidate_info { #define IOMMU_CACHE_INV_TYPE_NR (3) __u8 cache; __u8 granularity; - __u8 padding[2]; + __u8 padding[6]; union { struct iommu_inv_pasid_info pasid_info; struct iommu_inv_addr_info addr_info; @@ -296,6 +300,7 @@ struct iommu_gpasid_bind_data_vtd { /** * struct iommu_gpasid_bind_data - Information about device and guest PASID binding + * @argsz: User filled size of this data * @version: Version of this data structure * @format: PASID table entry format * @flags: Additional information on guest bind request @@ -313,17 +318,18 @@ struct iommu_gpasid_bind_data_vtd { * PASID to host PASID based on this bind data. */ struct iommu_gpasid_bind_data { + __u32 argsz; #define IOMMU_GPASID_BIND_VERSION_1 1 __u32 version; #define IOMMU_PASID_FORMAT_INTEL_VTD 1 __u32 format; + __u32 addr_width; #define IOMMU_SVA_GPASID_VAL (1 << 0) /* guest PASID valid */ __u64 flags; __u64 gpgd; __u64 hpasid; __u64 gpasid; - __u32 addr_width; - __u8 padding[12]; + __u8 padding[8]; /* Vendor specific data */ union { struct iommu_gpasid_bind_data_vtd vtd; -- cgit v1.2.3-58-ga151 From 8d3bb3b8cbf2ffb3ef73720a48b3445518dcdb55 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Fri, 25 Sep 2020 09:32:44 -0700 Subject: iommu/uapi: Use named union for user data IOMMU UAPI data size is filled by the user space which must be validated by the kernel. To ensure backward compatibility, user data can only be extended by either re-purpose padding bytes or extend the variable sized union at the end. No size change is allowed before the union. Therefore, the minimum size is the offset of the union. To use offsetof() on the union, we must make it named. Signed-off-by: Jacob Pan Reviewed-by: Lu Baolu Reviewed-by: Eric Auger Link: https://lore.kernel.org/linux-iommu/20200611145518.0c2817d6@x1.home/ Link: https://lore.kernel.org/r/1601051567-54787-4-git-send-email-jacob.jun.pan@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 22 +++++++++++----------- drivers/iommu/intel/svm.c | 2 +- include/uapi/linux/iommu.h | 4 ++-- 3 files changed, 14 insertions(+), 14 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index f8177c59d229..f1c66c94be55 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -5424,8 +5424,8 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev, /* Size is only valid in address selective invalidation */ if (inv_info->granularity == IOMMU_INV_GRANU_ADDR) - size = to_vtd_size(inv_info->addr_info.granule_size, - inv_info->addr_info.nb_granules); + size = to_vtd_size(inv_info->granu.addr_info.granule_size, + inv_info->granu.addr_info.nb_granules); for_each_set_bit(cache_type, (unsigned long *)&inv_info->cache, @@ -5446,20 +5446,20 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev, * granularity. */ if (inv_info->granularity == IOMMU_INV_GRANU_PASID && - (inv_info->pasid_info.flags & IOMMU_INV_PASID_FLAGS_PASID)) - pasid = inv_info->pasid_info.pasid; + (inv_info->granu.pasid_info.flags & IOMMU_INV_PASID_FLAGS_PASID)) + pasid = inv_info->granu.pasid_info.pasid; else if (inv_info->granularity == IOMMU_INV_GRANU_ADDR && - (inv_info->addr_info.flags & IOMMU_INV_ADDR_FLAGS_PASID)) - pasid = inv_info->addr_info.pasid; + (inv_info->granu.addr_info.flags & IOMMU_INV_ADDR_FLAGS_PASID)) + pasid = inv_info->granu.addr_info.pasid; switch (BIT(cache_type)) { case IOMMU_CACHE_INV_TYPE_IOTLB: /* HW will ignore LSB bits based on address mask */ if (inv_info->granularity == IOMMU_INV_GRANU_ADDR && size && - (inv_info->addr_info.addr & ((BIT(VTD_PAGE_SHIFT + size)) - 1))) { + (inv_info->granu.addr_info.addr & ((BIT(VTD_PAGE_SHIFT + size)) - 1))) { pr_err_ratelimited("User address not aligned, 0x%llx, size order %llu\n", - inv_info->addr_info.addr, size); + inv_info->granu.addr_info.addr, size); } /* @@ -5467,9 +5467,9 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev, * We use npages = -1 to indicate that. */ qi_flush_piotlb(iommu, did, pasid, - mm_to_dma_pfn(inv_info->addr_info.addr), + mm_to_dma_pfn(inv_info->granu.addr_info.addr), (granu == QI_GRAN_NONG_PASID) ? -1 : 1 << size, - inv_info->addr_info.flags & IOMMU_INV_ADDR_FLAGS_LEAF); + inv_info->granu.addr_info.flags & IOMMU_INV_ADDR_FLAGS_LEAF); if (!info->ats_enabled) break; @@ -5492,7 +5492,7 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev, size = 64 - VTD_PAGE_SHIFT; addr = 0; } else if (inv_info->granularity == IOMMU_INV_GRANU_ADDR) { - addr = inv_info->addr_info.addr; + addr = inv_info->granu.addr_info.addr; } if (info->ats_enabled) diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index 95c3164a2302..99353d6468fa 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -370,7 +370,7 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev, spin_lock(&iommu->lock); ret = intel_pasid_setup_nested(iommu, dev, (pgd_t *)(uintptr_t)data->gpgd, - data->hpasid, &data->vtd, dmar_domain, + data->hpasid, &data->vendor.vtd, dmar_domain, data->addr_width); spin_unlock(&iommu->lock); if (ret) { diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h index b42acc8fe007..5946779ac1f9 100644 --- a/include/uapi/linux/iommu.h +++ b/include/uapi/linux/iommu.h @@ -267,7 +267,7 @@ struct iommu_cache_invalidate_info { union { struct iommu_inv_pasid_info pasid_info; struct iommu_inv_addr_info addr_info; - }; + } granu; }; /** @@ -333,7 +333,7 @@ struct iommu_gpasid_bind_data { /* Vendor specific data */ union { struct iommu_gpasid_bind_data_vtd vtd; - }; + } vendor; }; #endif /* _UAPI_IOMMU_H */ -- cgit v1.2.3-58-ga151 From 23cc3493b5e107b8deb697cf3157a07276b5eff7 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Fri, 25 Sep 2020 09:32:45 -0700 Subject: iommu/uapi: Rename uapi functions User APIs such as iommu_sva_unbind_gpasid() may also be used by the kernel. Since we introduced user pointer to the UAPI functions, in-kernel callers cannot share the same APIs. In-kernel callers are also trusted, there is no need to validate the data. We plan to have two flavors of the same API functions, one called through ioctls, carrying a user pointer and one called directly with valid IOMMU UAPI structs. To differentiate both, let's rename existing functions with an iommu_uapi_ prefix. Suggested-by: Alex Williamson Signed-off-by: Jacob Pan Reviewed-by: Eric Auger Link: https://lore.kernel.org/r/1601051567-54787-5-git-send-email-jacob.jun.pan@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 18 +++++++++--------- include/linux/iommu.h | 31 ++++++++++++++++--------------- 2 files changed, 25 insertions(+), 24 deletions(-) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 6c14c88cd525..e412a0abfefa 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1961,35 +1961,35 @@ out_unlock: } EXPORT_SYMBOL_GPL(iommu_attach_device); -int iommu_cache_invalidate(struct iommu_domain *domain, struct device *dev, - struct iommu_cache_invalidate_info *inv_info) +int iommu_uapi_cache_invalidate(struct iommu_domain *domain, struct device *dev, + struct iommu_cache_invalidate_info *inv_info) { if (unlikely(!domain->ops->cache_invalidate)) return -ENODEV; return domain->ops->cache_invalidate(domain, dev, inv_info); } -EXPORT_SYMBOL_GPL(iommu_cache_invalidate); +EXPORT_SYMBOL_GPL(iommu_uapi_cache_invalidate); -int iommu_sva_bind_gpasid(struct iommu_domain *domain, - struct device *dev, struct iommu_gpasid_bind_data *data) +int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, + struct device *dev, struct iommu_gpasid_bind_data *data) { if (unlikely(!domain->ops->sva_bind_gpasid)) return -ENODEV; return domain->ops->sva_bind_gpasid(domain, dev, data); } -EXPORT_SYMBOL_GPL(iommu_sva_bind_gpasid); +EXPORT_SYMBOL_GPL(iommu_uapi_sva_bind_gpasid); -int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev, - ioasid_t pasid) +int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev, + ioasid_t pasid) { if (unlikely(!domain->ops->sva_unbind_gpasid)) return -ENODEV; return domain->ops->sva_unbind_gpasid(dev, pasid); } -EXPORT_SYMBOL_GPL(iommu_sva_unbind_gpasid); +EXPORT_SYMBOL_GPL(iommu_uapi_sva_unbind_gpasid); static void __iommu_detach_device(struct iommu_domain *domain, struct device *dev) diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 2ad26d8b4ab9..d18de2afa6fb 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -424,13 +424,13 @@ extern int iommu_attach_device(struct iommu_domain *domain, struct device *dev); extern void iommu_detach_device(struct iommu_domain *domain, struct device *dev); -extern int iommu_cache_invalidate(struct iommu_domain *domain, - struct device *dev, - struct iommu_cache_invalidate_info *inv_info); -extern int iommu_sva_bind_gpasid(struct iommu_domain *domain, - struct device *dev, struct iommu_gpasid_bind_data *data); -extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain, - struct device *dev, ioasid_t pasid); +extern int iommu_uapi_cache_invalidate(struct iommu_domain *domain, + struct device *dev, + struct iommu_cache_invalidate_info *inv_info); +extern int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, + struct device *dev, struct iommu_gpasid_bind_data *data); +extern int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, + struct device *dev, ioasid_t pasid); extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); extern struct iommu_domain *iommu_get_dma_domain(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, @@ -1032,21 +1032,22 @@ static inline int iommu_sva_get_pasid(struct iommu_sva *handle) return IOMMU_PASID_INVALID; } -static inline int -iommu_cache_invalidate(struct iommu_domain *domain, - struct device *dev, - struct iommu_cache_invalidate_info *inv_info) +static inline int iommu_uapi_cache_invalidate(struct iommu_domain *domain, + struct device *dev, + struct iommu_cache_invalidate_info *inv_info) { return -ENODEV; } -static inline int iommu_sva_bind_gpasid(struct iommu_domain *domain, - struct device *dev, struct iommu_gpasid_bind_data *data) + +static inline int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, + struct device *dev, + struct iommu_gpasid_bind_data *data) { return -ENODEV; } -static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain, - struct device *dev, int pasid) +static inline int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, + struct device *dev, int pasid) { return -ENODEV; } -- cgit v1.2.3-58-ga151 From d90573812eea63c6bc8ab8a38f661b4c27c3cdc0 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Fri, 25 Sep 2020 09:32:46 -0700 Subject: iommu/uapi: Handle data and argsz filled by users IOMMU user APIs are responsible for processing user data. This patch changes the interface such that user pointers can be passed into IOMMU code directly. Separate kernel APIs without user pointers are introduced for in-kernel users of the UAPI functionality. IOMMU UAPI data has a user filled argsz field which indicates the data length of the structure. User data is not trusted, argsz must be validated based on the current kernel data size, mandatory data size, and feature flags. User data may also be extended, resulting in possible argsz increase. Backward compatibility is ensured based on size and flags (or the functional equivalent fields) checking. This patch adds sanity checks in the IOMMU layer. In addition to argsz, reserved/unused fields in padding, flags, and version are also checked. Details are documented in Documentation/userspace-api/iommu.rst Signed-off-by: Liu Yi L Signed-off-by: Jacob Pan Reviewed-by: Jean-Philippe Brucker Reviewed-by: Eric Auger Link: https://lore.kernel.org/r/1601051567-54787-6-git-send-email-jacob.jun.pan@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 194 +++++++++++++++++++++++++++++++++++++++++++-- include/linux/iommu.h | 28 ++++--- include/uapi/linux/iommu.h | 1 + 3 files changed, 207 insertions(+), 16 deletions(-) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index e412a0abfefa..6d847027d35e 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1961,34 +1961,214 @@ out_unlock: } EXPORT_SYMBOL_GPL(iommu_attach_device); +/* + * Check flags and other user provided data for valid combinations. We also + * make sure no reserved fields or unused flags are set. This is to ensure + * not breaking userspace in the future when these fields or flags are used. + */ +static int iommu_check_cache_invl_data(struct iommu_cache_invalidate_info *info) +{ + u32 mask; + int i; + + if (info->version != IOMMU_CACHE_INVALIDATE_INFO_VERSION_1) + return -EINVAL; + + mask = (1 << IOMMU_CACHE_INV_TYPE_NR) - 1; + if (info->cache & ~mask) + return -EINVAL; + + if (info->granularity >= IOMMU_INV_GRANU_NR) + return -EINVAL; + + switch (info->granularity) { + case IOMMU_INV_GRANU_ADDR: + if (info->cache & IOMMU_CACHE_INV_TYPE_PASID) + return -EINVAL; + + mask = IOMMU_INV_ADDR_FLAGS_PASID | + IOMMU_INV_ADDR_FLAGS_ARCHID | + IOMMU_INV_ADDR_FLAGS_LEAF; + + if (info->granu.addr_info.flags & ~mask) + return -EINVAL; + break; + case IOMMU_INV_GRANU_PASID: + mask = IOMMU_INV_PASID_FLAGS_PASID | + IOMMU_INV_PASID_FLAGS_ARCHID; + if (info->granu.pasid_info.flags & ~mask) + return -EINVAL; + + break; + case IOMMU_INV_GRANU_DOMAIN: + if (info->cache & IOMMU_CACHE_INV_TYPE_DEV_IOTLB) + return -EINVAL; + break; + default: + return -EINVAL; + } + + /* Check reserved padding fields */ + for (i = 0; i < sizeof(info->padding); i++) { + if (info->padding[i]) + return -EINVAL; + } + + return 0; +} + int iommu_uapi_cache_invalidate(struct iommu_domain *domain, struct device *dev, - struct iommu_cache_invalidate_info *inv_info) + void __user *uinfo) { + struct iommu_cache_invalidate_info inv_info = { 0 }; + u32 minsz; + int ret; + if (unlikely(!domain->ops->cache_invalidate)) return -ENODEV; - return domain->ops->cache_invalidate(domain, dev, inv_info); + /* + * No new spaces can be added before the variable sized union, the + * minimum size is the offset to the union. + */ + minsz = offsetof(struct iommu_cache_invalidate_info, granu); + + /* Copy minsz from user to get flags and argsz */ + if (copy_from_user(&inv_info, uinfo, minsz)) + return -EFAULT; + + /* Fields before the variable size union are mandatory */ + if (inv_info.argsz < minsz) + return -EINVAL; + + /* PASID and address granu require additional info beyond minsz */ + if (inv_info.granularity == IOMMU_INV_GRANU_PASID && + inv_info.argsz < offsetofend(struct iommu_cache_invalidate_info, granu.pasid_info)) + return -EINVAL; + + if (inv_info.granularity == IOMMU_INV_GRANU_ADDR && + inv_info.argsz < offsetofend(struct iommu_cache_invalidate_info, granu.addr_info)) + return -EINVAL; + + /* + * User might be using a newer UAPI header which has a larger data + * size, we shall support the existing flags within the current + * size. Copy the remaining user data _after_ minsz but not more + * than the current kernel supported size. + */ + if (copy_from_user((void *)&inv_info + minsz, uinfo + minsz, + min_t(u32, inv_info.argsz, sizeof(inv_info)) - minsz)) + return -EFAULT; + + /* Now the argsz is validated, check the content */ + ret = iommu_check_cache_invl_data(&inv_info); + if (ret) + return ret; + + return domain->ops->cache_invalidate(domain, dev, &inv_info); } EXPORT_SYMBOL_GPL(iommu_uapi_cache_invalidate); -int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, - struct device *dev, struct iommu_gpasid_bind_data *data) +static int iommu_check_bind_data(struct iommu_gpasid_bind_data *data) +{ + u32 mask; + int i; + + if (data->version != IOMMU_GPASID_BIND_VERSION_1) + return -EINVAL; + + /* Check the range of supported formats */ + if (data->format >= IOMMU_PASID_FORMAT_LAST) + return -EINVAL; + + /* Check all flags */ + mask = IOMMU_SVA_GPASID_VAL; + if (data->flags & ~mask) + return -EINVAL; + + /* Check reserved padding fields */ + for (i = 0; i < sizeof(data->padding); i++) { + if (data->padding[i]) + return -EINVAL; + } + + return 0; +} + +static int iommu_sva_prepare_bind_data(void __user *udata, + struct iommu_gpasid_bind_data *data) +{ + u32 minsz; + + /* + * No new spaces can be added before the variable sized union, the + * minimum size is the offset to the union. + */ + minsz = offsetof(struct iommu_gpasid_bind_data, vendor); + + /* Copy minsz from user to get flags and argsz */ + if (copy_from_user(data, udata, minsz)) + return -EFAULT; + + /* Fields before the variable size union are mandatory */ + if (data->argsz < minsz) + return -EINVAL; + /* + * User might be using a newer UAPI header, we shall let IOMMU vendor + * driver decide on what size it needs. Since the guest PASID bind data + * can be vendor specific, larger argsz could be the result of extension + * for one vendor but it should not affect another vendor. + * Copy the remaining user data _after_ minsz + */ + if (copy_from_user((void *)data + minsz, udata + minsz, + min_t(u32, data->argsz, sizeof(*data)) - minsz)) + return -EFAULT; + + return iommu_check_bind_data(data); +} + +int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, struct device *dev, + void __user *udata) { + struct iommu_gpasid_bind_data data = { 0 }; + int ret; + if (unlikely(!domain->ops->sva_bind_gpasid)) return -ENODEV; - return domain->ops->sva_bind_gpasid(domain, dev, data); + ret = iommu_sva_prepare_bind_data(udata, &data); + if (ret) + return ret; + + return domain->ops->sva_bind_gpasid(domain, dev, &data); } EXPORT_SYMBOL_GPL(iommu_uapi_sva_bind_gpasid); -int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev, - ioasid_t pasid) +int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev, + ioasid_t pasid) { if (unlikely(!domain->ops->sva_unbind_gpasid)) return -ENODEV; return domain->ops->sva_unbind_gpasid(dev, pasid); } +EXPORT_SYMBOL_GPL(iommu_sva_unbind_gpasid); + +int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev, + void __user *udata) +{ + struct iommu_gpasid_bind_data data = { 0 }; + int ret; + + if (unlikely(!domain->ops->sva_bind_gpasid)) + return -ENODEV; + + ret = iommu_sva_prepare_bind_data(udata, &data); + if (ret) + return ret; + + return iommu_sva_unbind_gpasid(domain, dev, data.hpasid); +} EXPORT_SYMBOL_GPL(iommu_uapi_sva_unbind_gpasid); static void __iommu_detach_device(struct iommu_domain *domain, diff --git a/include/linux/iommu.h b/include/linux/iommu.h index d18de2afa6fb..82876f682367 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -426,11 +426,14 @@ extern void iommu_detach_device(struct iommu_domain *domain, struct device *dev); extern int iommu_uapi_cache_invalidate(struct iommu_domain *domain, struct device *dev, - struct iommu_cache_invalidate_info *inv_info); + void __user *uinfo); + extern int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, - struct device *dev, struct iommu_gpasid_bind_data *data); + struct device *dev, void __user *udata); extern int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, - struct device *dev, ioasid_t pasid); + struct device *dev, void __user *udata); +extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain, + struct device *dev, ioasid_t pasid); extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); extern struct iommu_domain *iommu_get_dma_domain(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, @@ -1032,22 +1035,29 @@ static inline int iommu_sva_get_pasid(struct iommu_sva *handle) return IOMMU_PASID_INVALID; } -static inline int iommu_uapi_cache_invalidate(struct iommu_domain *domain, - struct device *dev, - struct iommu_cache_invalidate_info *inv_info) +static inline int +iommu_uapi_cache_invalidate(struct iommu_domain *domain, + struct device *dev, + struct iommu_cache_invalidate_info *inv_info) { return -ENODEV; } static inline int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, - struct device *dev, - struct iommu_gpasid_bind_data *data) + struct device *dev, void __user *udata) { return -ENODEV; } static inline int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, - struct device *dev, int pasid) + struct device *dev, void __user *udata) +{ + return -ENODEV; +} + +static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain, + struct device *dev, + ioasid_t pasid) { return -ENODEV; } diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h index 5946779ac1f9..66d4ca40b40f 100644 --- a/include/uapi/linux/iommu.h +++ b/include/uapi/linux/iommu.h @@ -322,6 +322,7 @@ struct iommu_gpasid_bind_data { #define IOMMU_GPASID_BIND_VERSION_1 1 __u32 version; #define IOMMU_PASID_FORMAT_INTEL_VTD 1 +#define IOMMU_PASID_FORMAT_LAST 2 __u32 format; __u32 addr_width; #define IOMMU_SVA_GPASID_VAL (1 << 0) /* guest PASID valid */ -- cgit v1.2.3-58-ga151 From 6278eecba31f3983fe2743fc01b198433aa18247 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Fri, 25 Sep 2020 09:32:47 -0700 Subject: iommu/vt-d: Check UAPI data processed by IOMMU core IOMMU generic layer already does sanity checks on UAPI data for version match and argsz range based on generic information. This patch adjusts the following data checking responsibilities: - removes the redundant version check from VT-d driver - removes the check for vendor specific data size - adds check for the use of reserved/undefined flags Signed-off-by: Jacob Pan Reviewed-by: Eric Auger Link: https://lore.kernel.org/r/1601051567-54787-7-git-send-email-jacob.jun.pan@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 3 +-- drivers/iommu/intel/svm.c | 11 +++++++++-- include/uapi/linux/iommu.h | 1 + 3 files changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index f1c66c94be55..cae400b6807e 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -5398,8 +5398,7 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev, int ret = 0; u64 size = 0; - if (!inv_info || !dmar_domain || - inv_info->version != IOMMU_CACHE_INVALIDATE_INFO_VERSION_1) + if (!inv_info || !dmar_domain) return -EINVAL; if (!dev || !dev_is_pci(dev)) diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index 99353d6468fa..0cb9a15f1112 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -284,8 +284,15 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev, if (WARN_ON(!iommu) || !data) return -EINVAL; - if (data->version != IOMMU_GPASID_BIND_VERSION_1 || - data->format != IOMMU_PASID_FORMAT_INTEL_VTD) + if (data->format != IOMMU_PASID_FORMAT_INTEL_VTD) + return -EINVAL; + + /* IOMMU core ensures argsz is more than the start of the union */ + if (data->argsz < offsetofend(struct iommu_gpasid_bind_data, vendor.vtd)) + return -EINVAL; + + /* Make sure no undefined flags are used in vendor data */ + if (data->vendor.vtd.flags & ~(IOMMU_SVA_VTD_GPASID_LAST - 1)) return -EINVAL; if (!dev_is_pci(dev)) diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h index 66d4ca40b40f..e1d9e75f2c94 100644 --- a/include/uapi/linux/iommu.h +++ b/include/uapi/linux/iommu.h @@ -288,6 +288,7 @@ struct iommu_gpasid_bind_data_vtd { #define IOMMU_SVA_VTD_GPASID_PWT (1 << 3) /* page-level write through */ #define IOMMU_SVA_VTD_GPASID_EMTE (1 << 4) /* extended mem type enable */ #define IOMMU_SVA_VTD_GPASID_CD (1 << 5) /* PASID-level cache disable */ +#define IOMMU_SVA_VTD_GPASID_LAST (1 << 6) __u64 flags; __u32 pat; __u32 emt; -- cgit v1.2.3-58-ga151 From c40aaaac1018ff1382f2d35df5129a6bcea3df6b Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 24 Sep 2020 15:08:42 +0100 Subject: iommu/vt-d: Gracefully handle DMAR units with no supported address widths Instead of bailing out completely, such a unit can still be used for interrupt remapping. Signed-off-by: David Woodhouse Reviewed-by: Lu Baolu Link: https://lore.kernel.org/linux-iommu/549928db2de6532117f36c9c810373c14cf76f51.camel@infradead.org/ Signed-off-by: Joerg Roedel --- drivers/iommu/intel/dmar.c | 46 +++++++++++++++++++++++++++++++--------------- 1 file changed, 31 insertions(+), 15 deletions(-) diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index ba47edf03941..54d790f75824 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -1024,8 +1024,8 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd) { struct intel_iommu *iommu; u32 ver, sts; - int agaw = 0; - int msagaw = 0; + int agaw = -1; + int msagaw = -1; int err; if (!drhd->reg_base_addr) { @@ -1050,17 +1050,28 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd) } err = -EINVAL; - agaw = iommu_calculate_agaw(iommu); - if (agaw < 0) { - pr_err("Cannot get a valid agaw for iommu (seq_id = %d)\n", - iommu->seq_id); - goto err_unmap; - } - msagaw = iommu_calculate_max_sagaw(iommu); - if (msagaw < 0) { - pr_err("Cannot get a valid max agaw for iommu (seq_id = %d)\n", - iommu->seq_id); - goto err_unmap; + if (cap_sagaw(iommu->cap) == 0) { + pr_info("%s: No supported address widths. Not attempting DMA translation.\n", + iommu->name); + drhd->ignored = 1; + } + + if (!drhd->ignored) { + agaw = iommu_calculate_agaw(iommu); + if (agaw < 0) { + pr_err("Cannot get a valid agaw for iommu (seq_id = %d)\n", + iommu->seq_id); + drhd->ignored = 1; + } + } + if (!drhd->ignored) { + msagaw = iommu_calculate_max_sagaw(iommu); + if (msagaw < 0) { + pr_err("Cannot get a valid max agaw for iommu (seq_id = %d)\n", + iommu->seq_id); + drhd->ignored = 1; + agaw = -1; + } } iommu->agaw = agaw; iommu->msagaw = msagaw; @@ -1087,7 +1098,12 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd) raw_spin_lock_init(&iommu->register_lock); - if (intel_iommu_enabled) { + /* + * This is only for hotplug; at boot time intel_iommu_enabled won't + * be set yet. When intel_iommu_init() runs, it registers the units + * present at boot time, then sets intel_iommu_enabled. + */ + if (intel_iommu_enabled && !drhd->ignored) { err = iommu_device_sysfs_add(&iommu->iommu, NULL, intel_iommu_groups, "%s", iommu->name); @@ -1117,7 +1133,7 @@ error: static void free_iommu(struct intel_iommu *iommu) { - if (intel_iommu_enabled) { + if (intel_iommu_enabled && iommu->iommu.ops) { iommu_device_unregister(&iommu->iommu); iommu_device_sysfs_remove(&iommu->iommu); } -- cgit v1.2.3-58-ga151