@@ -432,7 +432,7 @@ static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain,
* rounding up anything cacheable to make sure that can't happen. The
* order of the unadjusted size will still match upon freeing.
*/
- if (iova_len < (1 << (IOVA_RANGE_CACHE_MAX_SIZE - 1)))
+ if (iova_len < (1 << (iovad->rcache_max_size - 1)))
iova_len = roundup_pow_of_two(iova_len);
dma_limit = min_not_zero(dma_limit, dev->bus_dma_limit);
@@ -15,6 +15,8 @@
/* 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);
@@ -877,7 +879,14 @@ static void init_iova_rcaches(struct iova_domain *iovad)
unsigned int cpu;
int i;
- for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
+ iovad->rcache_max_size = IOVA_RANGE_CACHE_MAX_SIZE;
+
+ iovad->rcaches = kcalloc(iovad->rcache_max_size,
+ sizeof(*iovad->rcaches), GFP_KERNEL);
+ if (!iovad->rcaches)
+ return;
+
+ for (i = 0; i < iovad->rcache_max_size; ++i) {
rcache = &iovad->rcaches[i];
spin_lock_init(&rcache->lock);
rcache->depot_size = 0;
@@ -952,7 +961,7 @@ static bool iova_rcache_insert(struct iova_domain *iovad, unsigned long pfn,
{
unsigned int log_size = order_base_2(size);
- if (log_size >= IOVA_RANGE_CACHE_MAX_SIZE)
+ if (log_size >= iovad->rcache_max_size)
return false;
return __iova_rcache_insert(iovad, &iovad->rcaches[log_size], pfn);
@@ -1008,7 +1017,7 @@ 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 >= iovad->rcache_max_size)
return 0;
return __iova_rcache_get(&iovad->rcaches[log_size], limit_pfn - size);
@@ -1024,7 +1033,7 @@ static void free_iova_rcaches(struct iova_domain *iovad)
unsigned int cpu;
int i, j;
- for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
+ for (i = 0; i < iovad->rcache_max_size; ++i) {
rcache = &iovad->rcaches[i];
for_each_possible_cpu(cpu) {
cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu);
@@ -1035,6 +1044,8 @@ 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);
}
/*
@@ -1047,7 +1058,7 @@ static void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad)
unsigned long flags;
int i;
- for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
+ for (i = 0; i < iovad->rcache_max_size; ++i) {
rcache = &iovad->rcaches[i];
cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu);
spin_lock_irqsave(&cpu_rcache->lock, flags);
@@ -1066,7 +1077,7 @@ static void free_global_cached_iovas(struct iova_domain *iovad)
unsigned long flags;
int i, j;
- for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
+ for (i = 0; i < iovad->rcache_max_size; ++i) {
rcache = &iovad->rcaches[i];
spin_lock_irqsave(&rcache->lock, flags);
for (j = 0; j < rcache->depot_size; ++j) {
@@ -25,7 +25,6 @@ struct iova {
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 {
@@ -74,6 +73,7 @@ struct iova_domain {
unsigned long start_pfn; /* Lower limit for this domain */
unsigned long dma_32bit_pfn;
unsigned long max32_alloc_size; /* Size of last failed allocation */
+ unsigned long rcache_max_size; /* Upper limit of cached IOVA RANGE */
struct iova_fq __percpu *fq; /* Flush Queue */
atomic64_t fq_flush_start_cnt; /* Number of TLB flushes that
@@ -83,7 +83,6 @@ struct iova_domain {
have been finished */
struct iova anchor; /* rbtree lookup anchor */
- struct iova_rcache rcaches[IOVA_RANGE_CACHE_MAX_SIZE]; /* IOVA range caches */
iova_flush_cb flush_cb; /* Call-Back function to flush IOMMU
TLBs */
@@ -96,6 +95,7 @@ struct iova_domain {
atomic_t fq_timer_on; /* 1 when timer is active, 0
when not */
struct hlist_node cpuhp_dead;
+ struct iova_rcache *rcaches; /* IOVA range caches */
};
static inline unsigned long iova_size(struct iova *iova)
Some LLDs may request DMA mappings whose IOVA length exceeds that of the current rcache upper limit. This means that allocations for those IOVAs will never be cached, and always must be allocated and freed from the RB tree per DMA mapping cycle. This has a significant effect on performance, more so since commit 4e89dce72521 ("iommu/iova: Retry from last rb tree node if iova search fails"), as discussed at [0]. As a first step towards allowing the rcache range upper limit be configured, hold this value in the IOVA rcache structure, and allocate the rcaches separately. [0] https://lore.kernel.org/linux-iommu/20210129092120.1482-1-thunder.leizhen@huawei.com/ Signed-off-by: John Garry <john.garry@huawei.com> --- drivers/iommu/dma-iommu.c | 2 +- drivers/iommu/iova.c | 23 +++++++++++++++++------ include/linux/iova.h | 4 ++-- 3 files changed, 20 insertions(+), 9 deletions(-) -- 2.26.2