From 32e92d9f6f876721cc4f565f8369d542b6266380 Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 3 Feb 2022 17:59:20 +0800 Subject: [PATCH] iommu/iova: Separate out rcache init Currently the rcache structures are allocated for all IOVA domains, even if they do not use "fast" alloc+free interface. This is wasteful of memory. In addition, fails in init_iova_rcaches() are not handled safely, which is less than ideal. Make "fast" users call a separate rcache init explicitly, which includes error checking. Signed-off-by: John Garry Reviewed-by: Robin Murphy Acked-by: Michael S. Tsirkin Link: https://lore.kernel.org/r/1643882360-241739-1-git-send-email-john.garry@huawei.com Signed-off-by: Joerg Roedel --- drivers/iommu/dma-iommu.c | 4 ++ drivers/iommu/iova.c | 73 +++++++++++++++++++++++++++++------- drivers/vdpa/vdpa_user/iova_domain.c | 11 ++++++ include/linux/iova.h | 15 ++------ 4 files changed, 77 insertions(+), 26 deletions(-) diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index d85d54f..b220349 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -525,6 +525,7 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base, struct iommu_dma_cookie *cookie = domain->iova_cookie; unsigned long order, base_pfn; struct iova_domain *iovad; + int ret; if (!cookie || cookie->type != IOMMU_DMA_IOVA_COOKIE) return -EINVAL; @@ -559,6 +560,9 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base, } init_iova_domain(iovad, 1UL << order, base_pfn); + ret = iova_domain_init_rcaches(iovad); + if (ret) + return ret; /* If the FQ fails we can simply fall back to strict mode */ if (domain->type == IOMMU_DOMAIN_DMA_FQ && iommu_dma_init_fq(domain)) diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index b28c943..7e9c3a9 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -15,13 +15,14 @@ /* The anchor node sits above the top of the usable address space */ #define IOVA_ANCHOR ~0UL +#define IOVA_RANGE_CACHE_MAX_SIZE 6 /* log of max cached IOVA range size (in pages) */ + static bool iova_rcache_insert(struct iova_domain *iovad, unsigned long pfn, unsigned long size); static unsigned long iova_rcache_get(struct iova_domain *iovad, unsigned long size, unsigned long limit_pfn); -static void init_iova_rcaches(struct iova_domain *iovad); static void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad); static void free_iova_rcaches(struct iova_domain *iovad); @@ -64,8 +65,6 @@ init_iova_domain(struct iova_domain *iovad, unsigned long granule, iovad->anchor.pfn_lo = iovad->anchor.pfn_hi = IOVA_ANCHOR; rb_link_node(&iovad->anchor.node, NULL, &iovad->rbroot.rb_node); rb_insert_color(&iovad->anchor.node, &iovad->rbroot); - cpuhp_state_add_instance_nocalls(CPUHP_IOMMU_IOVA_DEAD, &iovad->cpuhp_dead); - init_iova_rcaches(iovad); } EXPORT_SYMBOL_GPL(init_iova_domain); @@ -488,6 +487,13 @@ free_iova_fast(struct iova_domain *iovad, unsigned long pfn, unsigned long size) } EXPORT_SYMBOL_GPL(free_iova_fast); +static void iova_domain_free_rcaches(struct iova_domain *iovad) +{ + cpuhp_state_remove_instance_nocalls(CPUHP_IOMMU_IOVA_DEAD, + &iovad->cpuhp_dead); + free_iova_rcaches(iovad); +} + /** * put_iova_domain - destroys the iova domain * @iovad: - iova domain in question. @@ -497,9 +503,9 @@ void put_iova_domain(struct iova_domain *iovad) { struct iova *iova, *tmp; - cpuhp_state_remove_instance_nocalls(CPUHP_IOMMU_IOVA_DEAD, - &iovad->cpuhp_dead); - free_iova_rcaches(iovad); + if (iovad->rcaches) + iova_domain_free_rcaches(iovad); + rbtree_postorder_for_each_entry_safe(iova, tmp, &iovad->rbroot, node) free_iova_mem(iova); } @@ -608,6 +614,7 @@ EXPORT_SYMBOL_GPL(reserve_iova); */ #define IOVA_MAG_SIZE 128 +#define MAX_GLOBAL_MAGS 32 /* magazines per bin */ struct iova_magazine { unsigned long size; @@ -620,6 +627,13 @@ struct iova_cpu_rcache { struct iova_magazine *prev; }; +struct iova_rcache { + spinlock_t lock; + unsigned long depot_size; + struct iova_magazine *depot[MAX_GLOBAL_MAGS]; + struct iova_cpu_rcache __percpu *cpu_rcaches; +}; + static struct iova_magazine *iova_magazine_alloc(gfp_t flags) { return kzalloc(sizeof(struct iova_magazine), flags); @@ -693,28 +707,54 @@ static void iova_magazine_push(struct iova_magazine *mag, unsigned long pfn) mag->pfns[mag->size++] = pfn; } -static void init_iova_rcaches(struct iova_domain *iovad) +int iova_domain_init_rcaches(struct iova_domain *iovad) { - struct iova_cpu_rcache *cpu_rcache; - struct iova_rcache *rcache; unsigned int cpu; - int i; + int i, ret; + + iovad->rcaches = kcalloc(IOVA_RANGE_CACHE_MAX_SIZE, + sizeof(struct iova_rcache), + GFP_KERNEL); + if (!iovad->rcaches) + return -ENOMEM; for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) { + struct iova_cpu_rcache *cpu_rcache; + struct iova_rcache *rcache; + rcache = &iovad->rcaches[i]; spin_lock_init(&rcache->lock); rcache->depot_size = 0; - rcache->cpu_rcaches = __alloc_percpu(sizeof(*cpu_rcache), cache_line_size()); - if (WARN_ON(!rcache->cpu_rcaches)) - continue; + rcache->cpu_rcaches = __alloc_percpu(sizeof(*cpu_rcache), + cache_line_size()); + if (!rcache->cpu_rcaches) { + ret = -ENOMEM; + goto out_err; + } for_each_possible_cpu(cpu) { cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu); + spin_lock_init(&cpu_rcache->lock); cpu_rcache->loaded = iova_magazine_alloc(GFP_KERNEL); cpu_rcache->prev = iova_magazine_alloc(GFP_KERNEL); + if (!cpu_rcache->loaded || !cpu_rcache->prev) { + ret = -ENOMEM; + goto out_err; + } } } + + ret = cpuhp_state_add_instance_nocalls(CPUHP_IOMMU_IOVA_DEAD, + &iovad->cpuhp_dead); + if (ret) + goto out_err; + return 0; + +out_err: + free_iova_rcaches(iovad); + return ret; } +EXPORT_SYMBOL_GPL(iova_domain_init_rcaches); /* * Try inserting IOVA range starting with 'iova_pfn' into 'rcache', and @@ -831,7 +871,7 @@ static unsigned long iova_rcache_get(struct iova_domain *iovad, { unsigned int log_size = order_base_2(size); - if (log_size >= IOVA_RANGE_CACHE_MAX_SIZE) + if (log_size >= IOVA_RANGE_CACHE_MAX_SIZE || !iovad->rcaches) return 0; return __iova_rcache_get(&iovad->rcaches[log_size], limit_pfn - size); @@ -849,6 +889,8 @@ static void free_iova_rcaches(struct iova_domain *iovad) for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) { rcache = &iovad->rcaches[i]; + if (!rcache->cpu_rcaches) + break; for_each_possible_cpu(cpu) { cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu); iova_magazine_free(cpu_rcache->loaded); @@ -858,6 +900,9 @@ static void free_iova_rcaches(struct iova_domain *iovad) for (j = 0; j < rcache->depot_size; ++j) iova_magazine_free(rcache->depot[j]); } + + kfree(iovad->rcaches); + iovad->rcaches = NULL; } /* diff --git a/drivers/vdpa/vdpa_user/iova_domain.c b/drivers/vdpa/vdpa_user/iova_domain.c index 2b1143f..22f7d43 100644 --- a/drivers/vdpa/vdpa_user/iova_domain.c +++ b/drivers/vdpa/vdpa_user/iova_domain.c @@ -480,6 +480,7 @@ vduse_domain_create(unsigned long iova_limit, size_t bounce_size) struct file *file; struct vduse_bounce_map *map; unsigned long pfn, bounce_pfns; + int ret; bounce_pfns = PAGE_ALIGN(bounce_size) >> PAGE_SHIFT; if (iova_limit <= bounce_size) @@ -513,10 +514,20 @@ vduse_domain_create(unsigned long iova_limit, size_t bounce_size) spin_lock_init(&domain->iotlb_lock); init_iova_domain(&domain->stream_iovad, PAGE_SIZE, IOVA_START_PFN); + ret = iova_domain_init_rcaches(&domain->stream_iovad); + if (ret) + goto err_iovad_stream; init_iova_domain(&domain->consistent_iovad, PAGE_SIZE, bounce_pfns); + ret = iova_domain_init_rcaches(&domain->consistent_iovad); + if (ret) + goto err_iovad_consistent; return domain; +err_iovad_consistent: + put_iova_domain(&domain->stream_iovad); +err_iovad_stream: + fput(file); err_file: vfree(domain->bounce_maps); err_map: diff --git a/include/linux/iova.h b/include/linux/iova.h index cea79cb..320a70e 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -21,18 +21,8 @@ struct iova { unsigned long pfn_lo; /* Lowest allocated pfn */ }; -struct iova_magazine; -struct iova_cpu_rcache; -#define IOVA_RANGE_CACHE_MAX_SIZE 6 /* log of max cached IOVA range size (in pages) */ -#define MAX_GLOBAL_MAGS 32 /* magazines per bin */ - -struct iova_rcache { - spinlock_t lock; - unsigned long depot_size; - struct iova_magazine *depot[MAX_GLOBAL_MAGS]; - struct iova_cpu_rcache __percpu *cpu_rcaches; -}; +struct iova_rcache; /* holds all the iova translations for a domain */ struct iova_domain { @@ -46,7 +36,7 @@ struct iova_domain { unsigned long max32_alloc_size; /* Size of last failed allocation */ struct iova anchor; /* rbtree lookup anchor */ - struct iova_rcache rcaches[IOVA_RANGE_CACHE_MAX_SIZE]; /* IOVA range caches */ + struct iova_rcache *rcaches; struct hlist_node cpuhp_dead; }; @@ -102,6 +92,7 @@ struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo, unsigned long pfn_hi); void init_iova_domain(struct iova_domain *iovad, unsigned long granule, unsigned long start_pfn); +int iova_domain_init_rcaches(struct iova_domain *iovad); struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn); void put_iova_domain(struct iova_domain *iovad); #else -- 2.7.4