From 95b18ef9c69157ded5ece1136377cf8123b597f0 Mon Sep 17 00:00:00 2001 From: Pasha Tatashin Date: Sat, 13 Apr 2024 00:25:13 +0000 Subject: iommu/dma: use iommu_put_pages_list() to releae freelist Free the IOMMU page tables via iommu_put_pages_list(). The page tables were allocated via iommu_alloc_* functions in architecture specific places, but are released in dma-iommu if the freelist is gathered during map/unmap operations into iommu_iotlb_gather data structure. Currently, only iommu/intel that does that. Signed-off-by: Pasha Tatashin Acked-by: David Rientjes Link: https://lore.kernel.org/r/20240413002522.1101315-3-pasha.tatashin@soleen.com Signed-off-by: Joerg Roedel --- drivers/iommu/dma-iommu.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'drivers/iommu/dma-iommu.c') diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index e4cb26f6a943..16a7c4a4f3db 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -32,6 +32,7 @@ #include #include "dma-iommu.h" +#include "iommu-pages.h" struct iommu_dma_msi_page { struct list_head list; @@ -156,7 +157,7 @@ static void fq_ring_free_locked(struct iommu_dma_cookie *cookie, struct iova_fq if (fq->entries[idx].counter >= counter) break; - put_pages_list(&fq->entries[idx].freelist); + iommu_put_pages_list(&fq->entries[idx].freelist); free_iova_fast(&cookie->iovad, fq->entries[idx].iova_pfn, fq->entries[idx].pages); @@ -254,7 +255,7 @@ static void iommu_dma_free_fq_single(struct iova_fq *fq) int idx; fq_ring_for_each(idx, fq) - put_pages_list(&fq->entries[idx].freelist); + iommu_put_pages_list(&fq->entries[idx].freelist); vfree(fq); } @@ -267,7 +268,7 @@ static void iommu_dma_free_fq_percpu(struct iova_fq __percpu *percpu_fq) struct iova_fq *fq = per_cpu_ptr(percpu_fq, cpu); fq_ring_for_each(idx, fq) - put_pages_list(&fq->entries[idx].freelist); + iommu_put_pages_list(&fq->entries[idx].freelist); } free_percpu(percpu_fq); -- cgit v1.2.3 From ad4750b07d3462ce29a0c9b1e88b2a1f9795290e Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Fri, 19 Apr 2024 17:54:44 +0100 Subject: iommu/dma: Make limit checks self-contained It's now easy to retrieve the device's DMA limits if we want to check them against the domain aperture, so do that ourselves instead of relying on them being passed through the callchain. Reviewed-by: Jason Gunthorpe Tested-by: Hanjun Guo Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/e28a114243d1e79eb3609aded034f8529521333f.1713523152.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- drivers/iommu/dma-iommu.c | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-) (limited to 'drivers/iommu/dma-iommu.c') diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index e4cb26f6a943..c827ed690f1f 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -660,19 +660,16 @@ static void iommu_dma_init_options(struct iommu_dma_options *options, /** * iommu_dma_init_domain - Initialise a DMA mapping domain * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie() - * @base: IOVA at which the mappable address space starts - * @limit: Last address of the IOVA space * @dev: Device the domain is being initialised for * - * @base and @limit + 1 should be exact multiples of IOMMU page granularity to - * avoid rounding surprises. If necessary, we reserve the page at address 0 + * If the geometry and dma_range_map include address 0, we reserve that page * to ensure it is an invalid IOVA. It is safe to reinitialise a domain, but * any change which could make prior IOVAs invalid will fail. */ -static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base, - dma_addr_t limit, struct device *dev) +static int iommu_dma_init_domain(struct iommu_domain *domain, struct device *dev) { struct iommu_dma_cookie *cookie = domain->iova_cookie; + const struct bus_dma_region *map = dev->dma_range_map; unsigned long order, base_pfn; struct iova_domain *iovad; int ret; @@ -684,18 +681,18 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base, /* Use the smallest supported page size for IOVA granularity */ order = __ffs(domain->pgsize_bitmap); - base_pfn = max_t(unsigned long, 1, base >> order); + base_pfn = 1; /* Check the domain allows at least some access to the device... */ - if (domain->geometry.force_aperture) { + if (map) { + dma_addr_t base = dma_range_map_min(map); if (base > domain->geometry.aperture_end || - limit < domain->geometry.aperture_start) { + dma_range_map_max(map) < domain->geometry.aperture_start) { pr_warn("specified DMA range outside IOMMU capability\n"); return -EFAULT; } /* ...then finally give it a kicking to make sure it fits */ - base_pfn = max_t(unsigned long, base_pfn, - domain->geometry.aperture_start >> order); + base_pfn = max(base, domain->geometry.aperture_start) >> order; } /* start_pfn is always nonzero for an already-initialised domain */ @@ -1760,7 +1757,7 @@ void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit) * underlying IOMMU driver needs to support via the dma-iommu layer. */ if (iommu_is_dma_domain(domain)) { - if (iommu_dma_init_domain(domain, dma_base, dma_limit, dev)) + if (iommu_dma_init_domain(domain, dev)) goto out_err; dev->dma_ops = &iommu_dma_ops; } -- 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 --- arch/arm64/mm/dma-mapping.c | 2 -- drivers/iommu/amd/iommu.c | 8 -------- drivers/iommu/dma-iommu.c | 18 ++++++------------ drivers/iommu/dma-iommu.h | 14 ++++++-------- drivers/iommu/intel/iommu.c | 7 ------- drivers/iommu/iommu.c | 20 +++++++------------- drivers/iommu/s390-iommu.c | 6 ------ drivers/iommu/virtio-iommu.c | 10 ---------- include/linux/iommu.h | 7 ------- 9 files changed, 19 insertions(+), 73 deletions(-) (limited to 'drivers/iommu/dma-iommu.c') diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 61886e43e3a1..313d8938a2f0 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -58,8 +58,6 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, ARCH_DMA_MINALIGN, cls); dev->dma_coherent = coherent; - if (device_iommu_mapped(dev)) - iommu_setup_dma_ops(dev, dma_base, dma_base + size - 1); xen_setup_dma_ops(dev); } diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index d35c1b8c8e65..085abf098fa9 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -2175,13 +2175,6 @@ static struct iommu_device *amd_iommu_probe_device(struct device *dev) return iommu_dev; } -static void amd_iommu_probe_finalize(struct device *dev) -{ - /* Domains are initialized for this device - have a look what we ended up with */ - set_dma_ops(dev, NULL); - iommu_setup_dma_ops(dev, 0, U64_MAX); -} - static void amd_iommu_release_device(struct device *dev) { struct amd_iommu *iommu; @@ -2784,7 +2777,6 @@ const struct iommu_ops amd_iommu_ops = { .domain_alloc_user = amd_iommu_domain_alloc_user, .probe_device = amd_iommu_probe_device, .release_device = amd_iommu_release_device, - .probe_finalize = amd_iommu_probe_finalize, .device_group = amd_iommu_device_group, .get_resv_regions = amd_iommu_get_resv_regions, .is_attach_deferred = amd_iommu_is_attach_deferred, diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index c827ed690f1f..bc1490bd4f7a 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -1741,25 +1741,20 @@ static const struct dma_map_ops iommu_dma_ops = { .max_mapping_size = iommu_dma_max_mapping_size, }; -/* - * The IOMMU core code allocates the default DMA domain, which the underlying - * IOMMU driver needs to support via the dma-iommu layer. - */ -void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit) +void iommu_setup_dma_ops(struct device *dev) { struct iommu_domain *domain = iommu_get_domain_for_dev(dev); - if (!domain) - goto out_err; + if (dev_is_pci(dev)) + dev->iommu->pci_32bit_workaround = !iommu_dma_forcedac; - /* - * The IOMMU core code allocates the default DMA domain, which the - * underlying IOMMU driver needs to support via the dma-iommu layer. - */ if (iommu_is_dma_domain(domain)) { if (iommu_dma_init_domain(domain, dev)) goto out_err; dev->dma_ops = &iommu_dma_ops; + } else if (dev->dma_ops == &iommu_dma_ops) { + /* Clean up if we've switched *from* a DMA domain */ + dev->dma_ops = NULL; } return; @@ -1767,7 +1762,6 @@ out_err: pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n", dev_name(dev)); } -EXPORT_SYMBOL_GPL(iommu_setup_dma_ops); static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev, phys_addr_t msi_addr, struct iommu_domain *domain) diff --git a/drivers/iommu/dma-iommu.h b/drivers/iommu/dma-iommu.h index c829f1f82a99..c12d63457c76 100644 --- a/drivers/iommu/dma-iommu.h +++ b/drivers/iommu/dma-iommu.h @@ -9,6 +9,8 @@ #ifdef CONFIG_IOMMU_DMA +void iommu_setup_dma_ops(struct device *dev); + int iommu_get_dma_cookie(struct iommu_domain *domain); void iommu_put_dma_cookie(struct iommu_domain *domain); @@ -17,13 +19,13 @@ int iommu_dma_init_fq(struct iommu_domain *domain); void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list); extern bool iommu_dma_forcedac; -static inline void iommu_dma_set_pci_32bit_workaround(struct device *dev) -{ - dev->iommu->pci_32bit_workaround = !iommu_dma_forcedac; -} #else /* CONFIG_IOMMU_DMA */ +static inline void iommu_setup_dma_ops(struct device *dev) +{ +} + static inline int iommu_dma_init_fq(struct iommu_domain *domain) { return -EINVAL; @@ -42,9 +44,5 @@ static inline void iommu_dma_get_resv_regions(struct device *dev, struct list_he { } -static inline void iommu_dma_set_pci_32bit_workaround(struct device *dev) -{ -} - #endif /* CONFIG_IOMMU_DMA */ #endif /* __DMA_IOMMU_H */ diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 45c75a8a0ef5..64adfdadeb49 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4349,12 +4349,6 @@ static void intel_iommu_release_device(struct device *dev) set_dma_ops(dev, NULL); } -static void intel_iommu_probe_finalize(struct device *dev) -{ - set_dma_ops(dev, NULL); - iommu_setup_dma_ops(dev, 0, U64_MAX); -} - static void intel_iommu_get_resv_regions(struct device *device, struct list_head *head) { @@ -4834,7 +4828,6 @@ const struct iommu_ops intel_iommu_ops = { .domain_alloc = intel_iommu_domain_alloc, .domain_alloc_user = intel_iommu_domain_alloc_user, .probe_device = intel_iommu_probe_device, - .probe_finalize = intel_iommu_probe_finalize, .release_device = intel_iommu_release_device, .get_resv_regions = intel_iommu_get_resv_regions, .device_group = intel_iommu_device_group, diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 3183b0ed4cdb..9df7cc75c1bc 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -581,10 +581,11 @@ static int __iommu_probe_device(struct device *dev, struct list_head *group_list if (list_empty(&group->entry)) list_add_tail(&group->entry, group_list); } - mutex_unlock(&group->mutex); - if (dev_is_pci(dev)) - iommu_dma_set_pci_32bit_workaround(dev); + if (group->default_domain) + iommu_setup_dma_ops(dev); + + mutex_unlock(&group->mutex); return 0; @@ -1828,6 +1829,8 @@ int bus_iommu_probe(const struct bus_type *bus) mutex_unlock(&group->mutex); return ret; } + for_each_group_device(group, gdev) + iommu_setup_dma_ops(gdev->dev); mutex_unlock(&group->mutex); /* @@ -3066,18 +3069,9 @@ static ssize_t iommu_group_store_type(struct iommu_group *group, if (ret) goto out_unlock; - /* - * Release the mutex here because ops->probe_finalize() call-back of - * some vendor IOMMU drivers calls arm_iommu_attach_device() which - * in-turn might call back into IOMMU core code, where it tries to take - * group->mutex, resulting in a deadlock. - */ - mutex_unlock(&group->mutex); - /* Make sure dma_ops is appropriatley set */ for_each_group_device(group, gdev) - iommu_group_do_probe_finalize(gdev->dev); - return count; + iommu_setup_dma_ops(gdev->dev); out_unlock: mutex_unlock(&group->mutex); diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c index 9a5196f523de..d8eaa7ea380b 100644 --- a/drivers/iommu/s390-iommu.c +++ b/drivers/iommu/s390-iommu.c @@ -695,11 +695,6 @@ static size_t s390_iommu_unmap_pages(struct iommu_domain *domain, return size; } -static void s390_iommu_probe_finalize(struct device *dev) -{ - iommu_setup_dma_ops(dev, 0, U64_MAX); -} - struct zpci_iommu_ctrs *zpci_get_iommu_ctrs(struct zpci_dev *zdev) { if (!zdev || !zdev->s390_domain) @@ -785,7 +780,6 @@ static const struct iommu_ops s390_iommu_ops = { .capable = s390_iommu_capable, .domain_alloc_paging = s390_domain_alloc_paging, .probe_device = s390_iommu_probe_device, - .probe_finalize = s390_iommu_probe_finalize, .release_device = s390_iommu_release_device, .device_group = generic_device_group, .pgsize_bitmap = SZ_4K, diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index 04048f64a2c0..8e776f6c6e35 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -1025,15 +1025,6 @@ err_free_dev: return ERR_PTR(ret); } -static void viommu_probe_finalize(struct device *dev) -{ -#ifndef CONFIG_ARCH_HAS_SETUP_DMA_OPS - /* First clear the DMA ops in case we're switching from a DMA domain */ - set_dma_ops(dev, NULL); - iommu_setup_dma_ops(dev, 0, U64_MAX); -#endif -} - static void viommu_release_device(struct device *dev) { struct viommu_endpoint *vdev = dev_iommu_priv_get(dev); @@ -1073,7 +1064,6 @@ static struct iommu_ops viommu_ops = { .capable = viommu_capable, .domain_alloc = viommu_domain_alloc, .probe_device = viommu_probe_device, - .probe_finalize = viommu_probe_finalize, .release_device = viommu_release_device, .device_group = viommu_device_group, .get_resv_regions = viommu_get_resv_regions, 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