On 2022-01-26 13:55, John Garry wrote:
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
Mangled patch? (no "---" separator here)
Overall this looks great, just a few comments further down...
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 3a46f2cc9e5d..dd066d990809 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 b28c9435b898..d3adc6ea5710 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(>anchor.node, NULL, >rbroot.rb_node);
rb_insert_color(>anchor.node, >rbroot);
- cpuhp_state_add_instance_nocalls(CPUHP_IOMMU_IOVA_DEAD,
>cpuhp_dead);
- init_iova_rcaches(iovad);
}
EXPORT_SYMBOL_GPL(init_iova_domain);
@@ -497,9 +496,9 @@ void put_iova_domain(struct iova_domain *iovad)
{
struct iova *iova, *tmp;
- cpuhp_state_remove_instance_nocalls(CPUHP_IOMMU_IOVA_DEAD,
- >cpuhp_dead);
- free_iova_rcaches(iovad);
+ if (iovad->rcaches)
+ iova_domain_free_rcaches(iovad);
+
rbtree_postorder_for_each_entry_safe(iova, tmp, >rbroot, node)
free_iova_mem(iova);
}
@@ -608,6 +607,7 @@ 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 +620,13 @@ 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 +700,62 @@ 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 = >rcaches[i];
spin_lock_init(>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 =