Re: [PATCH RESEND v5 2/5] iova: Allow rcache range upper limit to be flexible

[Leizhen (ThunderTown)]

On 2022/4/4 19:27, John Garry wrote:
> Some low-level drivers 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.
> 
> Delete macro IOVA_RANGE_CACHE_MAX_SIZE in case it's reused by mistake.
> 
> [0] https://lore.kernel.org/linux-iommu/20210129092120.1482-1-thunder.leizhen@xxxxxxxxxx/
> 
> Signed-off-by: John Garry <john.garry@xxxxxxxxxx>
> ---
>  drivers/iommu/iova.c | 20 ++++++++++----------
>  include/linux/iova.h |  3 +++
>  2 files changed, 13 insertions(+), 10 deletions(-)
> 
> diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
> index db77aa675145..5c22b9187b79 100644
> --- a/drivers/iommu/iova.c
> +++ b/drivers/iommu/iova.c
> @@ -15,8 +15,6 @@
>  /* 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);
> @@ -443,7 +441,7 @@ alloc_iova_fast(struct iova_domain *iovad, unsigned long size,
>  	 * rounding up anything cacheable to make sure that can't happen. The
>  	 * order of the unadjusted size will still match upon freeing.
>  	 */
> -	if (size < (1 << (IOVA_RANGE_CACHE_MAX_SIZE - 1)))
> +	if (size < (1 << (iovad->rcache_max_size - 1)))
>  		size = roundup_pow_of_two(size);
>  
>  	iova_pfn = iova_rcache_get(iovad, size, limit_pfn + 1);
> @@ -713,13 +711,15 @@ int iova_domain_init_rcaches(struct iova_domain *iovad)
>  	unsigned int cpu;
>  	int i, ret;
>  
> -	iovad->rcaches = kcalloc(IOVA_RANGE_CACHE_MAX_SIZE,
> +	iovad->rcache_max_size = 6; /* Arbitrarily high default */

It would be better to assign this constant value to iovad->rcache_max_size in init_iova_domain().

> +
> +	iovad->rcaches = kcalloc(iovad->rcache_max_size,
>  				 sizeof(struct iova_rcache),
>  				 GFP_KERNEL);
>  	if (!iovad->rcaches)
>  		return -ENOMEM;
>  
> -	for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
> +	for (i = 0; i < iovad->rcache_max_size; ++i) {
>  		struct iova_cpu_rcache *cpu_rcache;
>  		struct iova_rcache *rcache;
>  
> @@ -816,7 +816,7 @@ 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);
> @@ -872,7 +872,7 @@ 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 || !iovad->rcaches)
> +	if (log_size >= iovad->rcache_max_size || !iovad->rcaches)
>  		return 0;
>  
>  	return __iova_rcache_get(&iovad->rcaches[log_size], limit_pfn - size);
> @@ -888,7 +888,7 @@ 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];
>  		if (!rcache->cpu_rcaches)
>  			break;
> @@ -916,7 +916,7 @@ 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);
> @@ -935,7 +935,7 @@ 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) {
> diff --git a/include/linux/iova.h b/include/linux/iova.h
> index 320a70e40233..02f7222fa85a 100644
> --- a/include/linux/iova.h
> +++ b/include/linux/iova.h
> @@ -38,6 +38,9 @@ struct iova_domain {
>  
>  	struct iova_rcache	*rcaches;
>  	struct hlist_node	cpuhp_dead;
> +
> +	/* log of max cached IOVA range size (in pages) */
> +	unsigned long	rcache_max_size;
>  };
>  
>  static inline unsigned long iova_size(struct iova *iova)
> 

-- 
Regards,
  Zhen Lei