From d2f85a263883b679f87ed8f911746105658e9c47 Mon Sep 17 00:00:00 2001 From: Yi Liu Date: Thu, 28 Mar 2024 05:29:58 -0700 Subject: iommu: Pass domain to remove_dev_pasid() op Existing remove_dev_pasid() callbacks of the underlying iommu drivers get the attached domain from the group->pasid_array. However, the domain stored in group->pasid_array is not always correct in all scenarios. A wrong domain may result in failure in remove_dev_pasid() callback. To avoid such problems, it is more reliable to pass the domain to the remove_dev_pasid() op. Suggested-by: Jason Gunthorpe Signed-off-by: Yi Liu Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20240328122958.83332-3-yi.l.liu@intel.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 2e925b5eba53..40dd439307e8 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -578,7 +578,8 @@ struct iommu_ops { struct iommu_page_response *msg); int (*def_domain_type)(struct device *dev); - void (*remove_dev_pasid)(struct device *dev, ioasid_t pasid); + void (*remove_dev_pasid)(struct device *dev, ioasid_t pasid, + struct iommu_domain *domain); const struct iommu_domain_ops *default_domain_ops; unsigned long pgsize_bitmap; -- cgit v1.2.3 From bd3520a93a84cd8c3897283e5891a9106fcf5acc Mon Sep 17 00:00:00 2001 From: Pasha Tatashin Date: Sat, 13 Apr 2024 00:25:21 +0000 Subject: iommu: observability of the IOMMU allocations Add NR_IOMMU_PAGES into node_stat_item that counts number of pages that are allocated by the IOMMU subsystem. The allocations can be view per-node via: /sys/devices/system/node/nodeN/vmstat. For example: $ grep iommu /sys/devices/system/node/node*/vmstat /sys/devices/system/node/node0/vmstat:nr_iommu_pages 106025 /sys/devices/system/node/node1/vmstat:nr_iommu_pages 3464 The value is in page-count, therefore, in the above example the iommu allocations amount to ~428M. Signed-off-by: Pasha Tatashin Acked-by: David Rientjes Tested-by: Bagas Sanjaya Link: https://lore.kernel.org/r/20240413002522.1101315-11-pasha.tatashin@soleen.com Signed-off-by: Joerg Roedel --- include/linux/mmzone.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index c11b7cde81ef..be17195f6f86 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -206,6 +206,9 @@ enum node_stat_item { #endif NR_PAGETABLE, /* used for pagetables */ NR_SECONDARY_PAGETABLE, /* secondary pagetables, e.g. KVM pagetables */ +#ifdef CONFIG_IOMMU_SUPPORT + NR_IOMMU_PAGES, /* # of pages allocated by IOMMU */ +#endif #ifdef CONFIG_SWAP NR_SWAPCACHE, #endif -- cgit v1.2.3 From 212c5c078d83d780cf2873ca931df135771e8bb7 Mon Sep 17 00:00:00 2001 From: Pasha Tatashin Date: Sat, 13 Apr 2024 00:25:22 +0000 Subject: iommu: account IOMMU allocated memory In order to be able to limit the amount of memory that is allocated by IOMMU subsystem, the memory must be accounted. Account IOMMU as part of the secondary pagetables as it was discussed at LPC. The value of SecPageTables now contains mmeory allocation by IOMMU and KVM. There is a difference between GFP_ACCOUNT and what NR_IOMMU_PAGES shows. GFP_ACCOUNT is set only where it makes sense to charge to user processes, i.e. IOMMU Page Tables, but there more IOMMU shared data that should not really be charged to a specific process. Signed-off-by: Pasha Tatashin Acked-by: David Rientjes Tested-by: Bagas Sanjaya Link: https://lore.kernel.org/r/20240413002522.1101315-12-pasha.tatashin@soleen.com Signed-off-by: Joerg Roedel --- include/linux/mmzone.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index be17195f6f86..8f9c9590a42c 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -205,7 +205,7 @@ enum node_stat_item { NR_KERNEL_SCS_KB, /* measured in KiB */ #endif NR_PAGETABLE, /* used for pagetables */ - NR_SECONDARY_PAGETABLE, /* secondary pagetables, e.g. KVM pagetables */ + NR_SECONDARY_PAGETABLE, /* secondary pagetables, KVM & IOMMU */ #ifdef CONFIG_IOMMU_SUPPORT NR_IOMMU_PAGES, /* # of pages allocated by IOMMU */ #endif -- cgit v1.2.3 From d74169ceb0d2e32438946a2f1f9fc8c803304bd6 Mon Sep 17 00:00:00 2001 From: Dimitri Sivanich Date: Wed, 24 Apr 2024 15:16:29 +0800 Subject: iommu/vt-d: Allocate DMAR fault interrupts locally The Intel IOMMU code currently tries to allocate all DMAR fault interrupt vectors on the boot cpu. On large systems with high DMAR counts this results in vector exhaustion, and most of the vectors are not initially allocated socket local. Instead, have a cpu on each node do the vector allocation for the DMARs on that node. The boot cpu still does the allocation for its node during its boot sequence. Signed-off-by: Dimitri Sivanich Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/Zfydpp2Hm+as16TY@hpe.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- include/linux/dmar.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/dmar.h b/include/linux/dmar.h index e34b601b71fd..499bb2c63483 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -117,7 +117,7 @@ extern int dmar_remove_dev_scope(struct dmar_pci_notify_info *info, int count); /* Intel IOMMU detection */ void detect_intel_iommu(void); -extern int enable_drhd_fault_handling(void); +extern int enable_drhd_fault_handling(unsigned int cpu); extern int dmar_device_add(acpi_handle handle); extern int dmar_device_remove(acpi_handle handle); -- cgit v1.2.3 From 621b7e54f288c5e4e32d1dd81a926b8ecb547c60 Mon Sep 17 00:00:00 2001 From: Jingqi Liu Date: Wed, 24 Apr 2024 15:16:31 +0800 Subject: iommu/vt-d: Remove private data use in fault message According to Intel VT-d specification revision 4.0, "Private Data" field has been removed from Page Request/Response. Since the private data field is not used in fault message, remove the related definitions in page request descriptor and remove the related code in page request/response handler, as Intel hasn't shipped any products which support private data in the page request message. Signed-off-by: Jingqi Liu Link: https://lore.kernel.org/r/20240308103811.76744-3-Jingqi.liu@intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 2e925b5eba53..e6549bdfaed9 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -69,8 +69,7 @@ enum iommu_fault_type { struct iommu_fault_page_request { #define IOMMU_FAULT_PAGE_REQUEST_PASID_VALID (1 << 0) #define IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE (1 << 1) -#define IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA (1 << 2) -#define IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID (1 << 3) +#define IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID (1 << 2) u32 flags; u32 pasid; u32 grpid; -- cgit v1.2.3 From 65442507026a79e2de8014880e6ba376b8b44584 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 24 Apr 2024 15:16:43 +0800 Subject: iommu: Add ops->domain_alloc_sva() Make a new op that receives the device and the mm_struct that the SVA domain should be created for. Unlike domain_alloc_paging() the dev argument is never NULL here. This allows drivers to fully initialize the SVA domain and allocate the mmu_notifier during allocation. It allows the notifier lifetime to follow the lifetime of the iommu_domain. Since we have only one call site, upgrade the new op to return ERR_PTR instead of NULL. Signed-off-by: Jason Gunthorpe Signed-off-by: Vasant Hegde Reviewed-by: Tina Zhang Link: https://lore.kernel.org/r/20240311090843.133455-15-vasant.hegde@amd.com Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20240416080656.60968-12-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index e6549bdfaed9..f4cdffa985e4 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -517,6 +517,7 @@ static inline int __iommu_copy_struct_from_user_array( * Upon failure, ERR_PTR must be returned. * @domain_alloc_paging: Allocate an iommu_domain that can be used for * UNMANAGED, DMA, and DMA_FQ domain types. + * @domain_alloc_sva: Allocate an iommu_domain for Shared Virtual Addressing. * @probe_device: Add device to iommu driver handling * @release_device: Remove device from iommu driver handling * @probe_finalize: Do final setup work after the device is added to an IOMMU @@ -557,6 +558,8 @@ struct iommu_ops { struct device *dev, u32 flags, struct iommu_domain *parent, const struct iommu_user_data *user_data); struct iommu_domain *(*domain_alloc_paging)(struct device *dev); + struct iommu_domain *(*domain_alloc_sva)(struct device *dev, + struct mm_struct *mm); struct iommu_device *(*probe_device)(struct device *dev); void (*release_device)(struct device *dev); -- cgit v1.2.3 From 91cfd679f9e8b9a7bf2f26adf66eff99dbe2026b Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Fri, 19 Apr 2024 17:54:42 +0100 Subject: ACPI/IORT: Handle memory address size limits as limits Return the Root Complex/Named Component memory address size limit as an inclusive limit value, rather than an exclusive size. This saves having to fudge an off-by-one for the 64-bit case, and simplifies our caller. Acked-by: Hanjun Guo Reviewed-by: Jason Gunthorpe Tested-by: Hanjun Guo Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/284ae9fbadb12f2e3b5a30cd4d037d0e6843a8f4.1713523152.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- include/linux/acpi_iort.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index 1cb65592c95d..d4ed5622cf2b 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -39,7 +39,7 @@ void iort_get_rmr_sids(struct fwnode_handle *iommu_fwnode, void iort_put_rmr_sids(struct fwnode_handle *iommu_fwnode, struct list_head *head); /* IOMMU interface */ -int iort_dma_get_ranges(struct device *dev, u64 *size); +int iort_dma_get_ranges(struct device *dev, u64 *limit); int iort_iommu_configure_id(struct device *dev, const u32 *id_in); void iort_iommu_get_resv_regions(struct device *dev, struct list_head *head); phys_addr_t acpi_iort_dma_get_max_cpu_address(void); @@ -55,7 +55,7 @@ void iort_get_rmr_sids(struct fwnode_handle *iommu_fwnode, struct list_head *hea static inline void iort_put_rmr_sids(struct fwnode_handle *iommu_fwnode, struct list_head *head) { } /* IOMMU interface */ -static inline int iort_dma_get_ranges(struct device *dev, u64 *size) +static inline int iort_dma_get_ranges(struct device *dev, u64 *limit) { return -ENODEV; } static inline int iort_iommu_configure_id(struct device *dev, const u32 *id_in) { return -ENODEV; } -- cgit v1.2.3 From fece6530bf4b59b01a476a12851e07751e73d69f Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Fri, 19 Apr 2024 17:54:43 +0100 Subject: dma-mapping: Add helpers for dma_range_map bounds Several places want to compute the lower and/or upper bounds of a dma_range_map, so let's factor that out into reusable helpers. Acked-by: Rob Herring Reviewed-by: Christoph Hellwig Reviewed-by: Hanjun Guo # For arm64 Reviewed-by: Jason Gunthorpe Tested-by: Hanjun Guo Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/45ec52f033ec4dfb364e23f48abaf787f612fa53.1713523152.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- include/linux/dma-direct.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 3eb3589ff43e..edbe13d00776 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -54,6 +54,24 @@ static inline phys_addr_t translate_dma_to_phys(struct device *dev, return (phys_addr_t)-1; } +static inline dma_addr_t dma_range_map_min(const struct bus_dma_region *map) +{ + dma_addr_t ret = (dma_addr_t)U64_MAX; + + for (; map->size; map++) + ret = min(ret, map->dma_start); + return ret; +} + +static inline dma_addr_t dma_range_map_max(const struct bus_dma_region *map) +{ + dma_addr_t ret = 0; + + for (; map->size; map++) + ret = max(ret, map->dma_start + map->size - 1); + return ret; +} + #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA #include #ifndef phys_to_dma_unencrypted -- cgit v1.2.3 From b67483b3c44eaef2f771fa4c712e13f452675a67 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Fri, 19 Apr 2024 17:54:45 +0100 Subject: iommu/dma: Centralise iommu_setup_dma_ops() It's somewhat hard to see, but arm64's arch_setup_dma_ops() should only ever call iommu_setup_dma_ops() after a successful iommu_probe_device(), which means there should be no harm in achieving the same order of operations by running it off the back of iommu_probe_device() itself. This then puts it in line with the x86 and s390 .probe_finalize bodges, letting us pull it all into the main flow properly. As a bonus this lets us fold in and de-scope the PCI workaround setup as well. At this point we can also then pull the call up inside the group mutex, and avoid having to think about whether iommu_group_store_type() could theoretically race and free the domain if iommu_setup_dma_ops() ran just *before* iommu_device_use_default_domain() claims it... Furthermore we replace one .probe_finalize call completely, since the only remaining implementations are now one which only needs to run once for the initial boot-time probe, and two which themselves render that path unreachable. This leaves us a big step closer to realistically being able to unpick the variety of different things that iommu_setup_dma_ops() has been muddling together, and further streamline iommu-dma into core API flows in future. Reviewed-by: Lu Baolu # For Intel IOMMU Reviewed-by: Jason Gunthorpe Tested-by: Hanjun Guo Signed-off-by: Robin Murphy Acked-by: Catalin Marinas Link: https://lore.kernel.org/r/bebea331c1d688b34d9862eefd5ede47503961b8.1713523152.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 40dd439307e8..86f0bff3cc95 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -1446,9 +1446,6 @@ static inline void iommu_debugfs_setup(void) {} #ifdef CONFIG_IOMMU_DMA #include -/* Setup call for arch DMA mapping code */ -void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit); - int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base); int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr); @@ -1459,10 +1456,6 @@ void iommu_dma_compose_msi_msg(struct msi_desc *desc, struct msi_msg *msg); struct msi_desc; struct msi_msg; -static inline void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit) -{ -} - static inline int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base) { return -ENODEV; -- cgit v1.2.3 From f091e93306e0429ebb7589b9874590b6a9705e64 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Fri, 19 Apr 2024 17:54:46 +0100 Subject: dma-mapping: Simplify arch_setup_dma_ops() The dma_base, size and iommu arguments are only used by ARM, and can now easily be deduced from the device itself, so there's no need to pass them through the callchain as well. Acked-by: Rob Herring Reviewed-by: Christoph Hellwig Reviewed-by: Michael Kelley # For Hyper-V Reviewed-by: Jason Gunthorpe Tested-by: Hanjun Guo Signed-off-by: Robin Murphy Acked-by: Catalin Marinas Link: https://lore.kernel.org/r/5291c2326eab405b1aa7693aa964e8d3cb7193de.1713523152.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- include/linux/dma-map-ops.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 4abc60f04209..ed89e1ce0114 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -426,11 +426,9 @@ bool arch_dma_unmap_sg_direct(struct device *dev, struct scatterlist *sg, #endif #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS -void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, - bool coherent); +void arch_setup_dma_ops(struct device *dev, bool coherent); #else -static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base, - u64 size, bool coherent) +static inline void arch_setup_dma_ops(struct device *dev, bool coherent) { } #endif /* CONFIG_ARCH_HAS_SETUP_DMA_OPS */ -- cgit v1.2.3 From 80af5a45202422db957549a241e00bf4d4e0ce89 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 18 Apr 2024 10:33:59 +0000 Subject: iommu: Add ops->domain_alloc_sva() Make a new op that receives the device and the mm_struct that the SVA domain should be created for. Unlike domain_alloc_paging() the dev argument is never NULL here. This allows drivers to fully initialize the SVA domain and allocate the mmu_notifier during allocation. It allows the notifier lifetime to follow the lifetime of the iommu_domain. Since we have only one call site, upgrade the new op to return ERR_PTR instead of NULL. Signed-off-by: Jason Gunthorpe [Removed smmu3 related changes - Vasant] Signed-off-by: Vasant Hegde Reviewed-by: Tina Zhang Link: https://lore.kernel.org/r/20240418103400.6229-15-vasant.hegde@amd.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 2e925b5eba53..8aabe83af8f2 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -518,6 +518,7 @@ static inline int __iommu_copy_struct_from_user_array( * Upon failure, ERR_PTR must be returned. * @domain_alloc_paging: Allocate an iommu_domain that can be used for * UNMANAGED, DMA, and DMA_FQ domain types. + * @domain_alloc_sva: Allocate an iommu_domain for Shared Virtual Addressing. * @probe_device: Add device to iommu driver handling * @release_device: Remove device from iommu driver handling * @probe_finalize: Do final setup work after the device is added to an IOMMU @@ -558,6 +559,8 @@ struct iommu_ops { struct device *dev, u32 flags, struct iommu_domain *parent, const struct iommu_user_data *user_data); struct iommu_domain *(*domain_alloc_paging)(struct device *dev); + struct iommu_domain *(*domain_alloc_sva)(struct device *dev, + struct mm_struct *mm); struct iommu_device *(*probe_device)(struct device *dev); void (*release_device)(struct device *dev); -- cgit v1.2.3