From 05f80300dc8bcfe8566b36256d01482cae5afa02 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Fri, 21 Jul 2017 13:12:38 +0100 Subject: iommu: Finish making iommu_group support mandatory Now that all the drivers properly implementing the IOMMU API support groups (I'm ignoring the etnaviv GPU MMUs which seemingly only do just enough to convince the ARM DMA mapping ops), we can remove the FIXME workarounds from the core code. In the process, it also seems logical to make the .device_group callback non-optional for drivers calling iommu_group_get_for_dev() - the current callers all implement it anyway, and it doesn't make sense for any future callers not to either. Signed-off-by: Robin Murphy Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 19 ++++--------------- 1 file changed, 4 insertions(+), 15 deletions(-) (limited to 'drivers/iommu/iommu.c') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 3f6ea160afed..af69bf7e035a 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1005,11 +1005,10 @@ struct iommu_group *iommu_group_get_for_dev(struct device *dev) if (group) return group; - group = ERR_PTR(-EINVAL); - - if (ops && ops->device_group) - group = ops->device_group(dev); + if (!ops) + return ERR_PTR(-EINVAL); + group = ops->device_group(dev); if (WARN_ON_ONCE(group == NULL)) return ERR_PTR(-EINVAL); @@ -1298,12 +1297,8 @@ int iommu_attach_device(struct iommu_domain *domain, struct device *dev) int ret; group = iommu_group_get(dev); - /* FIXME: Remove this when groups a mandatory for iommu drivers */ - if (group == NULL) - return __iommu_attach_device(domain, dev); - /* - * We have a group - lock it to make sure the device-count doesn't + * Lock the group to make sure the device-count doesn't * change while we are attaching */ mutex_lock(&group->mutex); @@ -1336,9 +1331,6 @@ void iommu_detach_device(struct iommu_domain *domain, struct device *dev) struct iommu_group *group; group = iommu_group_get(dev); - /* FIXME: Remove this when groups a mandatory for iommu drivers */ - if (group == NULL) - return __iommu_detach_device(domain, dev); mutex_lock(&group->mutex); if (iommu_group_device_count(group) != 1) { @@ -1360,9 +1352,6 @@ struct iommu_domain *iommu_get_domain_for_dev(struct device *dev) struct iommu_group *group; group = iommu_group_get(dev); - /* FIXME: Remove this when groups a mandatory for iommu drivers */ - if (group == NULL) - return NULL; domain = group->domain; -- cgit v1.2.3 From e01d1913b0d0817191418381a6fcebaa01abde2a Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 9 Aug 2017 16:33:40 +0800 Subject: iommu: Add is_attach_deferred call-back to iommu-ops This new call-back will be used to check if the domain attach need be deferred for now. If yes, the domain attach/detach will return directly. Signed-off-by: Baoquan He Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 8 ++++++++ include/linux/iommu.h | 1 + 2 files changed, 9 insertions(+) (limited to 'drivers/iommu/iommu.c') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 3f6ea160afed..86581b115b92 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1283,6 +1283,10 @@ static int __iommu_attach_device(struct iommu_domain *domain, struct device *dev) { int ret; + if ((domain->ops->is_attach_deferred != NULL) && + domain->ops->is_attach_deferred(domain, dev)) + return 0; + if (unlikely(domain->ops->attach_dev == NULL)) return -ENODEV; @@ -1324,6 +1328,10 @@ EXPORT_SYMBOL_GPL(iommu_attach_device); static void __iommu_detach_device(struct iommu_domain *domain, struct device *dev) { + if ((domain->ops->is_attach_deferred != NULL) && + domain->ops->is_attach_deferred(domain, dev)) + return; + if (unlikely(domain->ops->detach_dev == NULL)) return; diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 2cb54adc4a33..63983c9e6c3a 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -225,6 +225,7 @@ struct iommu_ops { u32 (*domain_get_windows)(struct iommu_domain *domain); int (*of_xlate)(struct device *dev, struct of_phandle_args *args); + bool (*is_attach_deferred)(struct iommu_domain *domain, struct device *dev); unsigned long pgsize_bitmap; }; -- cgit v1.2.3 From 1464d0b1defe421aef8c8877e19c7ae011e32eb9 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Thu, 17 Aug 2017 11:40:08 +0100 Subject: iommu: Avoid NULL group dereference The recently-removed FIXME in iommu_get_domain_for_dev() turns out to have been a little misleading, since that check is still worthwhile even when groups *are* universal. We have a few IOMMU-aware drivers which only care whether their device is already attached to an existing domain or not, for which the previous behaviour of iommu_get_domain_for_dev() was ideal, and who now crash if their device does not have an IOMMU. With IOMMU groups now serving as a reliable indicator of whether a device has an IOMMU or not (barring false-positives from VFIO no-IOMMU mode), drivers could arguably do this: group = iommu_group_get(dev); if (group) { domain = iommu_get_domain_for_dev(dev); iommu_group_put(group); } However, rather than duplicate that code across multiple callsites, particularly when it's still only the domain they care about, let's skip straight to the next step and factor out the check into the common place it applies - in iommu_get_domain_for_dev() itself. Sure, it ends up looking rather familiar, but now it's backed by the reasoning of having a robust API able to do the expected thing for all devices regardless. Fixes: 05f80300dc8b ("iommu: Finish making iommu_group support mandatory") Reported-by: Shawn Lin Signed-off-by: Robin Murphy Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers/iommu/iommu.c') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index af69bf7e035a..5499a0387349 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1352,6 +1352,8 @@ struct iommu_domain *iommu_get_domain_for_dev(struct device *dev) struct iommu_group *group; group = iommu_group_get(dev); + if (!group) + return NULL; domain = group->domain; -- cgit v1.2.3 From add02cfdc9bc2987b0121861d5bb0c7392865be9 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 23 Aug 2017 15:50:04 +0200 Subject: iommu: Introduce Interface for IOMMU TLB Flushing With the current IOMMU-API the hardware TLBs have to be flushed in every iommu_ops->unmap() call-back. For unmapping large amounts of address space, like it happens when a KVM domain with assigned devices is destroyed, this causes thousands of unnecessary TLB flushes in the IOMMU hardware because the unmap call-back runs for every unmapped physical page. With the TLB Flush Interface and the new iommu_unmap_fast() function introduced here the need to clean the hardware TLBs is removed from the unmapping code-path. Users of iommu_unmap_fast() have to explicitly call the TLB-Flush functions to sync the page-table changes to the hardware. Three functions for TLB-Flushes are introduced: * iommu_flush_tlb_all() - Flushes all TLB entries associated with that domain. TLBs entries are flushed when this function returns. * iommu_tlb_range_add() - This will add a given range to the flush queue for this domain. * iommu_tlb_sync() - Flushes all queued ranges from the hardware TLBs. Returns when the flush is finished. The semantic of this interface is intentionally similar to the iommu_gather_ops from the io-pgtable code. Cc: Alex Williamson Cc: Will Deacon Cc: Robin Murphy Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 32 ++++++++++++++++++++++++++++---- include/linux/iommu.h | 50 +++++++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 77 insertions(+), 5 deletions(-) (limited to 'drivers/iommu/iommu.c') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 5499a0387349..31c2b1dc8cfd 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -527,6 +527,8 @@ static int iommu_group_create_direct_mappings(struct iommu_group *group, } + iommu_flush_tlb_all(domain); + out: iommu_put_resv_regions(dev, &mappings); @@ -1547,13 +1549,16 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova, } EXPORT_SYMBOL_GPL(iommu_map); -size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size) +static size_t __iommu_unmap(struct iommu_domain *domain, + unsigned long iova, size_t size, + bool sync) { + const struct iommu_ops *ops = domain->ops; size_t unmapped_page, unmapped = 0; - unsigned int min_pagesz; unsigned long orig_iova = iova; + unsigned int min_pagesz; - if (unlikely(domain->ops->unmap == NULL || + if (unlikely(ops->unmap == NULL || domain->pgsize_bitmap == 0UL)) return -ENODEV; @@ -1583,10 +1588,13 @@ size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size) while (unmapped < size) { size_t pgsize = iommu_pgsize(domain, iova, size - unmapped); - unmapped_page = domain->ops->unmap(domain, iova, pgsize); + unmapped_page = ops->unmap(domain, iova, pgsize); if (!unmapped_page) break; + if (sync && ops->iotlb_range_add) + ops->iotlb_range_add(domain, iova, pgsize); + pr_debug("unmapped: iova 0x%lx size 0x%zx\n", iova, unmapped_page); @@ -1594,11 +1602,27 @@ size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size) unmapped += unmapped_page; } + if (sync && ops->iotlb_sync) + ops->iotlb_sync(domain); + trace_unmap(orig_iova, size, unmapped); return unmapped; } + +size_t iommu_unmap(struct iommu_domain *domain, + unsigned long iova, size_t size) +{ + return __iommu_unmap(domain, iova, size, true); +} EXPORT_SYMBOL_GPL(iommu_unmap); +size_t iommu_unmap_fast(struct iommu_domain *domain, + unsigned long iova, size_t size) +{ + return __iommu_unmap(domain, iova, size, false); +} +EXPORT_SYMBOL_GPL(iommu_unmap_fast); + size_t default_iommu_map_sg(struct iommu_domain *domain, unsigned long iova, struct scatterlist *sg, unsigned int nents, int prot) { diff --git a/include/linux/iommu.h b/include/linux/iommu.h index f1ce8e517d8d..50be4fd338e4 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -167,6 +167,10 @@ struct iommu_resv_region { * @map: map a physically contiguous memory region to an iommu domain * @unmap: unmap a physically contiguous memory region from an iommu domain * @map_sg: map a scatter-gather list of physically contiguous memory chunks + * @flush_tlb_all: Synchronously flush all hardware TLBs for this domain + * @tlb_range_add: Add a given iova range to the flush queue for this domain + * @tlb_sync: Flush all queued ranges from the hardware TLBs and empty flush + * queue * to an iommu domain * @iova_to_phys: translate iova to physical address * @add_device: add device to iommu grouping @@ -199,6 +203,10 @@ struct iommu_ops { size_t size); size_t (*map_sg)(struct iommu_domain *domain, unsigned long iova, struct scatterlist *sg, unsigned int nents, int prot); + void (*flush_iotlb_all)(struct iommu_domain *domain); + void (*iotlb_range_add)(struct iommu_domain *domain, + unsigned long iova, size_t size); + void (*iotlb_sync)(struct iommu_domain *domain); phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova); int (*add_device)(struct device *dev); void (*remove_device)(struct device *dev); @@ -286,7 +294,9 @@ extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot); extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, - size_t size); + size_t size); +extern size_t iommu_unmap_fast(struct iommu_domain *domain, + unsigned long iova, size_t size); extern size_t default_iommu_map_sg(struct iommu_domain *domain, unsigned long iova, struct scatterlist *sg,unsigned int nents, int prot); @@ -343,6 +353,25 @@ 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) +{ + if (domain->ops->flush_iotlb_all) + domain->ops->flush_iotlb_all(domain); +} + +static inline void iommu_tlb_range_add(struct iommu_domain *domain, + unsigned long iova, size_t size) +{ + if (domain->ops->iotlb_range_add) + domain->ops->iotlb_range_add(domain, iova, size); +} + +static inline void iommu_tlb_sync(struct iommu_domain *domain) +{ + if (domain->ops->iotlb_sync) + domain->ops->iotlb_sync(domain); +} + static inline size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, struct scatterlist *sg, unsigned int nents, int prot) @@ -436,6 +465,12 @@ static inline int iommu_unmap(struct iommu_domain *domain, unsigned long iova, return -ENODEV; } +static inline int iommu_unmap_fast(struct iommu_domain *domain, unsigned long iova, + int gfp_order) +{ + return -ENODEV; +} + static inline size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, struct scatterlist *sg, unsigned int nents, int prot) @@ -443,6 +478,19 @@ static inline size_t iommu_map_sg(struct iommu_domain *domain, return -ENODEV; } +static inline void iommu_flush_tlb_all(struct iommu_domain *domain) +{ +} + +static inline void iommu_tlb_range_add(struct iommu_domain *domain, + unsigned long iova, size_t size) +{ +} + +static inline void iommu_tlb_sync(struct iommu_domain *domain) +{ +} + static inline int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr, phys_addr_t paddr, u64 size, int prot) -- cgit v1.2.3