From 1369459b2e219a6f4c861404c4f195cd81dcbb40 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 23 Jan 2023 16:35:54 -0400 Subject: iommu: Add a gfp parameter to iommu_map() The internal mechanisms support this, but instead of exposting the gfp to the caller it wrappers it into iommu_map() and iommu_map_atomic() Fix this instead of adding more variants for GFP_KERNEL_ACCOUNT. Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe Reviewed-by: Mathieu Poirier Link: https://lore.kernel.org/r/1-v3-76b587fe28df+6e3-iommu_map_gfp_jgg@nvidia.com Signed-off-by: Joerg Roedel --- arch/arm/mm/dma-mapping.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index c135f6e37a00..8bc01071474a 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -984,7 +984,8 @@ __iommu_create_mapping(struct device *dev, struct page **pages, size_t size, len = (j - i) << PAGE_SHIFT; ret = iommu_map(mapping->domain, iova, phys, len, - __dma_info_to_prot(DMA_BIDIRECTIONAL, attrs)); + __dma_info_to_prot(DMA_BIDIRECTIONAL, attrs), + GFP_KERNEL); if (ret < 0) goto fail; iova += len; @@ -1207,7 +1208,8 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg, prot = __dma_info_to_prot(dir, attrs); - ret = iommu_map(mapping->domain, iova, phys, len, prot); + ret = iommu_map(mapping->domain, iova, phys, len, prot, + GFP_KERNEL); if (ret < 0) goto fail; count += len >> PAGE_SHIFT; @@ -1379,7 +1381,8 @@ static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page, prot = __dma_info_to_prot(dir, attrs); - ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, prot); + ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, + prot, GFP_KERNEL); if (ret < 0) goto fail; @@ -1443,7 +1446,7 @@ static dma_addr_t arm_iommu_map_resource(struct device *dev, prot = __dma_info_to_prot(dir, attrs) | IOMMU_MMIO; - ret = iommu_map(mapping->domain, dma_addr, addr, len, prot); + ret = iommu_map(mapping->domain, dma_addr, addr, len, prot, GFP_KERNEL); if (ret < 0) goto fail; -- cgit v1.2.3 From d3b82825217aab0ed56e2426a0d07af2e2ebd7df Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 23 Jan 2023 16:36:02 -0400 Subject: iommu/s390: Push the gfp parameter to the kmem_cache_alloc()'s dma_alloc_cpu_table() and dma_alloc_page_table() are eventually called by iommufd through s390_iommu_map_pages() and it should not be forced to atomic. Thread the gfp parameter through the call chain starting from s390_iommu_map_pages(). Reviewed-by: Niklas Schnelle Reviewed-by: Matthew Rosato Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/9-v3-76b587fe28df+6e3-iommu_map_gfp_jgg@nvidia.com Signed-off-by: Joerg Roedel --- arch/s390/include/asm/pci_dma.h | 5 +++-- arch/s390/pci/pci_dma.c | 31 +++++++++++++++++-------------- drivers/iommu/s390-iommu.c | 15 +++++++++------ 3 files changed, 29 insertions(+), 22 deletions(-) (limited to 'arch') diff --git a/arch/s390/include/asm/pci_dma.h b/arch/s390/include/asm/pci_dma.h index 91e63426bdc5..7119c04c51c5 100644 --- a/arch/s390/include/asm/pci_dma.h +++ b/arch/s390/include/asm/pci_dma.h @@ -186,9 +186,10 @@ static inline unsigned long *get_st_pto(unsigned long entry) /* Prototypes */ void dma_free_seg_table(unsigned long); -unsigned long *dma_alloc_cpu_table(void); +unsigned long *dma_alloc_cpu_table(gfp_t gfp); void dma_cleanup_tables(unsigned long *); -unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr); +unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr, + gfp_t gfp); void dma_update_cpu_trans(unsigned long *entry, phys_addr_t page_addr, int flags); extern const struct dma_map_ops s390_pci_dma_ops; diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index ea478d11fbd1..2f6d05d6da4f 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -27,11 +27,11 @@ static int zpci_refresh_global(struct zpci_dev *zdev) zdev->iommu_pages * PAGE_SIZE); } -unsigned long *dma_alloc_cpu_table(void) +unsigned long *dma_alloc_cpu_table(gfp_t gfp) { unsigned long *table, *entry; - table = kmem_cache_alloc(dma_region_table_cache, GFP_ATOMIC); + table = kmem_cache_alloc(dma_region_table_cache, gfp); if (!table) return NULL; @@ -45,11 +45,11 @@ static void dma_free_cpu_table(void *table) kmem_cache_free(dma_region_table_cache, table); } -static unsigned long *dma_alloc_page_table(void) +static unsigned long *dma_alloc_page_table(gfp_t gfp) { unsigned long *table, *entry; - table = kmem_cache_alloc(dma_page_table_cache, GFP_ATOMIC); + table = kmem_cache_alloc(dma_page_table_cache, gfp); if (!table) return NULL; @@ -63,7 +63,7 @@ static void dma_free_page_table(void *table) kmem_cache_free(dma_page_table_cache, table); } -static unsigned long *dma_get_seg_table_origin(unsigned long *rtep) +static unsigned long *dma_get_seg_table_origin(unsigned long *rtep, gfp_t gfp) { unsigned long old_rte, rte; unsigned long *sto; @@ -72,7 +72,7 @@ static unsigned long *dma_get_seg_table_origin(unsigned long *rtep) if (reg_entry_isvalid(rte)) { sto = get_rt_sto(rte); } else { - sto = dma_alloc_cpu_table(); + sto = dma_alloc_cpu_table(gfp); if (!sto) return NULL; @@ -90,7 +90,7 @@ static unsigned long *dma_get_seg_table_origin(unsigned long *rtep) return sto; } -static unsigned long *dma_get_page_table_origin(unsigned long *step) +static unsigned long *dma_get_page_table_origin(unsigned long *step, gfp_t gfp) { unsigned long old_ste, ste; unsigned long *pto; @@ -99,7 +99,7 @@ static unsigned long *dma_get_page_table_origin(unsigned long *step) if (reg_entry_isvalid(ste)) { pto = get_st_pto(ste); } else { - pto = dma_alloc_page_table(); + pto = dma_alloc_page_table(gfp); if (!pto) return NULL; set_st_pto(&ste, virt_to_phys(pto)); @@ -116,18 +116,19 @@ static unsigned long *dma_get_page_table_origin(unsigned long *step) return pto; } -unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr) +unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr, + gfp_t gfp) { unsigned long *sto, *pto; unsigned int rtx, sx, px; rtx = calc_rtx(dma_addr); - sto = dma_get_seg_table_origin(&rto[rtx]); + sto = dma_get_seg_table_origin(&rto[rtx], gfp); if (!sto) return NULL; sx = calc_sx(dma_addr); - pto = dma_get_page_table_origin(&sto[sx]); + pto = dma_get_page_table_origin(&sto[sx], gfp); if (!pto) return NULL; @@ -170,7 +171,8 @@ static int __dma_update_trans(struct zpci_dev *zdev, phys_addr_t pa, return -EINVAL; for (i = 0; i < nr_pages; i++) { - entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr); + entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr, + GFP_ATOMIC); if (!entry) { rc = -ENOMEM; goto undo_cpu_trans; @@ -186,7 +188,8 @@ undo_cpu_trans: while (i-- > 0) { page_addr -= PAGE_SIZE; dma_addr -= PAGE_SIZE; - entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr); + entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr, + GFP_ATOMIC); if (!entry) break; dma_update_cpu_trans(entry, page_addr, flags); @@ -576,7 +579,7 @@ int zpci_dma_init_device(struct zpci_dev *zdev) spin_lock_init(&zdev->iommu_bitmap_lock); - zdev->dma_table = dma_alloc_cpu_table(); + zdev->dma_table = dma_alloc_cpu_table(GFP_ATOMIC); if (!zdev->dma_table) { rc = -ENOMEM; goto out; diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c index ed33c6cce083..654ec4411fe3 100644 --- a/drivers/iommu/s390-iommu.c +++ b/drivers/iommu/s390-iommu.c @@ -52,7 +52,7 @@ static struct iommu_domain *s390_domain_alloc(unsigned domain_type) if (!s390_domain) return NULL; - s390_domain->dma_table = dma_alloc_cpu_table(); + s390_domain->dma_table = dma_alloc_cpu_table(GFP_ATOMIC); if (!s390_domain->dma_table) { kfree(s390_domain); return NULL; @@ -260,7 +260,8 @@ static void s390_iommu_iotlb_sync_map(struct iommu_domain *domain, static int s390_iommu_validate_trans(struct s390_domain *s390_domain, phys_addr_t pa, dma_addr_t dma_addr, - unsigned long nr_pages, int flags) + unsigned long nr_pages, int flags, + gfp_t gfp) { phys_addr_t page_addr = pa & PAGE_MASK; unsigned long *entry; @@ -268,7 +269,8 @@ static int s390_iommu_validate_trans(struct s390_domain *s390_domain, int rc; for (i = 0; i < nr_pages; i++) { - entry = dma_walk_cpu_trans(s390_domain->dma_table, dma_addr); + entry = dma_walk_cpu_trans(s390_domain->dma_table, dma_addr, + gfp); if (unlikely(!entry)) { rc = -ENOMEM; goto undo_cpu_trans; @@ -284,7 +286,7 @@ undo_cpu_trans: while (i-- > 0) { dma_addr -= PAGE_SIZE; entry = dma_walk_cpu_trans(s390_domain->dma_table, - dma_addr); + dma_addr, gfp); if (!entry) break; dma_update_cpu_trans(entry, 0, ZPCI_PTE_INVALID); @@ -301,7 +303,8 @@ static int s390_iommu_invalidate_trans(struct s390_domain *s390_domain, int rc = 0; for (i = 0; i < nr_pages; i++) { - entry = dma_walk_cpu_trans(s390_domain->dma_table, dma_addr); + entry = dma_walk_cpu_trans(s390_domain->dma_table, dma_addr, + GFP_ATOMIC); if (unlikely(!entry)) { rc = -EINVAL; break; @@ -339,7 +342,7 @@ static int s390_iommu_map_pages(struct iommu_domain *domain, flags |= ZPCI_TABLE_PROTECTED; rc = s390_iommu_validate_trans(s390_domain, paddr, iova, - pgcount, flags); + pgcount, flags, gfp); if (!rc) *mapped = size; -- cgit v1.2.3 From 429f27e36874e34727a1f8495be2ea3a7060732c Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 23 Jan 2023 16:36:03 -0400 Subject: iommu/s390: Use GFP_KERNEL in sleepable contexts These contexts are sleepable, so use the proper annotation. The GFP_ATOMIC was added mechanically in the prior patches. Reviewed-by: Niklas Schnelle Reviewed-by: Matthew Rosato Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/10-v3-76b587fe28df+6e3-iommu_map_gfp_jgg@nvidia.com Signed-off-by: Joerg Roedel --- arch/s390/pci/pci_dma.c | 2 +- drivers/iommu/s390-iommu.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index 2f6d05d6da4f..2d9b01d7ca4c 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -579,7 +579,7 @@ int zpci_dma_init_device(struct zpci_dev *zdev) spin_lock_init(&zdev->iommu_bitmap_lock); - zdev->dma_table = dma_alloc_cpu_table(GFP_ATOMIC); + zdev->dma_table = dma_alloc_cpu_table(GFP_KERNEL); if (!zdev->dma_table) { rc = -ENOMEM; goto out; diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c index 654ec4411fe3..7dcfffed260e 100644 --- a/drivers/iommu/s390-iommu.c +++ b/drivers/iommu/s390-iommu.c @@ -52,7 +52,7 @@ static struct iommu_domain *s390_domain_alloc(unsigned domain_type) if (!s390_domain) return NULL; - s390_domain->dma_table = dma_alloc_cpu_table(GFP_ATOMIC); + s390_domain->dma_table = dma_alloc_cpu_table(GFP_KERNEL); if (!s390_domain->dma_table) { kfree(s390_domain); return NULL; -- cgit v1.2.3