From: Vijayanand Jitta <[email protected]>
When ever a new iova alloc request comes iova is always searched
from the cached node and the nodes which are previous to cached
node. So, even if there is free iova space available in the nodes
which are next to the cached node iova allocation can still fail
because of this approach.
Consider the following sequence of iova alloc and frees on
1GB of iova space
1) alloc - 500MB
2) alloc - 12MB
3) alloc - 499MB
4) free - 12MB which was allocated in step 2
5) alloc - 13MB
After the above sequence we will have 12MB of free iova space and
cached node will be pointing to the iova pfn of last alloc of 13MB
which will be the lowest iova pfn of that iova space. Now if we get an
alloc request of 2MB we just search from cached node and then look
for lower iova pfn's for free iova and as they aren't any, iova alloc
fails though there is 12MB of free iova space.
To avoid such iova search failures do a retry from the last rb tree node
when iova search fails, this will search the entire tree and get an iova
if its available.
Signed-off-by: Vijayanand Jitta <[email protected]>
Reviewed-by: Robin Murphy <[email protected]>
---
drivers/iommu/iova.c | 23 +++++++++++++++++------
1 file changed, 17 insertions(+), 6 deletions(-)
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index 30d969a..c3a1a8e 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -184,8 +184,9 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
struct rb_node *curr, *prev;
struct iova *curr_iova;
unsigned long flags;
- unsigned long new_pfn;
+ unsigned long new_pfn, retry_pfn;
unsigned long align_mask = ~0UL;
+ unsigned long high_pfn = limit_pfn, low_pfn = iovad->start_pfn;
if (size_aligned)
align_mask <<= fls_long(size - 1);
@@ -198,15 +199,25 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
curr = __get_cached_rbnode(iovad, limit_pfn);
curr_iova = rb_entry(curr, struct iova, node);
+ retry_pfn = curr_iova->pfn_hi + 1;
+
+retry:
do {
- limit_pfn = min(limit_pfn, curr_iova->pfn_lo);
- new_pfn = (limit_pfn - size) & align_mask;
+ high_pfn = min(high_pfn, curr_iova->pfn_lo);
+ new_pfn = (high_pfn - size) & align_mask;
prev = curr;
curr = rb_prev(curr);
curr_iova = rb_entry(curr, struct iova, node);
- } while (curr && new_pfn <= curr_iova->pfn_hi);
-
- if (limit_pfn < size || new_pfn < iovad->start_pfn) {
+ } while (curr && new_pfn <= curr_iova->pfn_hi && new_pfn >= low_pfn);
+
+ if (high_pfn < size || new_pfn < low_pfn) {
+ if (low_pfn == iovad->start_pfn && retry_pfn < limit_pfn) {
+ high_pfn = limit_pfn;
+ low_pfn = retry_pfn;
+ curr = &iovad->anchor.node;
+ curr_iova = rb_entry(curr, struct iova, node);
+ goto retry;
+ }
iovad->max32_alloc_size = size;
goto iova32_full;
}
--
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum, hosted by The Linux Foundation
2.7.4
From: Vijayanand Jitta <[email protected]>
When ever an iova alloc request fails we free the iova
ranges present in the percpu iova rcaches and then retry
but the global iova rcache is not freed as a result we could
still see iova alloc failure even after retry as global
rcache is holding the iova's which can cause fragmentation.
So, free the global iova rcache as well and then go for the
retry.
Signed-off-by: Vijayanand Jitta <[email protected]>
---
drivers/iommu/iova.c | 23 +++++++++++++++++++++++
1 file changed, 23 insertions(+)
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index c3a1a8e..faf9b13 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -25,6 +25,7 @@ static void init_iova_rcaches(struct iova_domain *iovad);
static void free_iova_rcaches(struct iova_domain *iovad);
static void fq_destroy_all_entries(struct iova_domain *iovad);
static void fq_flush_timeout(struct timer_list *t);
+static void free_global_cached_iovas(struct iova_domain *iovad);
void
init_iova_domain(struct iova_domain *iovad, unsigned long granule,
@@ -442,6 +443,7 @@ alloc_iova_fast(struct iova_domain *iovad, unsigned long size,
flush_rcache = false;
for_each_online_cpu(cpu)
free_cpu_cached_iovas(cpu, iovad);
+ free_global_cached_iovas(iovad);
goto retry;
}
@@ -1057,5 +1059,26 @@ void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad)
}
}
+/*
+ * free all the IOVA ranges of global cache
+ */
+static void free_global_cached_iovas(struct iova_domain *iovad)
+{
+ struct iova_rcache *rcache;
+ unsigned long flags;
+ int i, j;
+
+ for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
+ rcache = &iovad->rcaches[i];
+ spin_lock_irqsave(&rcache->lock, flags);
+ for (j = 0; j < rcache->depot_size; ++j) {
+ iova_magazine_free_pfns(rcache->depot[j], iovad);
+ iova_magazine_free(rcache->depot[j]);
+ rcache->depot[j] = NULL;
+ }
+ rcache->depot_size = 0;
+ spin_unlock_irqrestore(&rcache->lock, flags);
+ }
+}
MODULE_AUTHOR("Anil S Keshavamurthy <[email protected]>");
MODULE_LICENSE("GPL");
--
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum, hosted by The Linux Foundation
2.7.4
On 9/30/2020 1:14 PM, [email protected] wrote:
> From: Vijayanand Jitta <[email protected]>
>
> When ever an iova alloc request fails we free the iova
> ranges present in the percpu iova rcaches and then retry
> but the global iova rcache is not freed as a result we could
> still see iova alloc failure even after retry as global
> rcache is holding the iova's which can cause fragmentation.
> So, free the global iova rcache as well and then go for the
> retry.
>
> Signed-off-by: Vijayanand Jitta <[email protected]>
> ---
> drivers/iommu/iova.c | 23 +++++++++++++++++++++++
> 1 file changed, 23 insertions(+)
>
> diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
> index c3a1a8e..faf9b13 100644
> --- a/drivers/iommu/iova.c
> +++ b/drivers/iommu/iova.c
> @@ -25,6 +25,7 @@ static void init_iova_rcaches(struct iova_domain *iovad);
> static void free_iova_rcaches(struct iova_domain *iovad);
> static void fq_destroy_all_entries(struct iova_domain *iovad);
> static void fq_flush_timeout(struct timer_list *t);
> +static void free_global_cached_iovas(struct iova_domain *iovad);
>
> void
> init_iova_domain(struct iova_domain *iovad, unsigned long granule,
> @@ -442,6 +443,7 @@ alloc_iova_fast(struct iova_domain *iovad, unsigned long size,
> flush_rcache = false;
> for_each_online_cpu(cpu)
> free_cpu_cached_iovas(cpu, iovad);
> + free_global_cached_iovas(iovad);
> goto retry;
> }
>
> @@ -1057,5 +1059,26 @@ void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad)
> }
> }
>
> +/*
> + * free all the IOVA ranges of global cache
> + */
> +static void free_global_cached_iovas(struct iova_domain *iovad)
> +{
> + struct iova_rcache *rcache;
> + unsigned long flags;
> + int i, j;
> +
> + for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
> + rcache = &iovad->rcaches[i];
> + spin_lock_irqsave(&rcache->lock, flags);
> + for (j = 0; j < rcache->depot_size; ++j) {
> + iova_magazine_free_pfns(rcache->depot[j], iovad);
> + iova_magazine_free(rcache->depot[j]);
> + rcache->depot[j] = NULL;
> + }
> + rcache->depot_size = 0;
> + spin_unlock_irqrestore(&rcache->lock, flags);
> + }
> +}
> MODULE_AUTHOR("Anil S Keshavamurthy <[email protected]>");
> MODULE_LICENSE("GPL");
>
Gentle ping.
Thanks,
Vijay
--
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a
member of Code Aurora Forum, hosted by The Linux Foundation
On 9/30/2020 1:14 PM, [email protected] wrote:
> From: Vijayanand Jitta <[email protected]>
>
> When ever a new iova alloc request comes iova is always searched
> from the cached node and the nodes which are previous to cached
> node. So, even if there is free iova space available in the nodes
> which are next to the cached node iova allocation can still fail
> because of this approach.
>
> Consider the following sequence of iova alloc and frees on
> 1GB of iova space
>
> 1) alloc - 500MB
> 2) alloc - 12MB
> 3) alloc - 499MB
> 4) free - 12MB which was allocated in step 2
> 5) alloc - 13MB
>
> After the above sequence we will have 12MB of free iova space and
> cached node will be pointing to the iova pfn of last alloc of 13MB
> which will be the lowest iova pfn of that iova space. Now if we get an
> alloc request of 2MB we just search from cached node and then look
> for lower iova pfn's for free iova and as they aren't any, iova alloc
> fails though there is 12MB of free iova space.
>
> To avoid such iova search failures do a retry from the last rb tree node
> when iova search fails, this will search the entire tree and get an iova
> if its available.
>
> Signed-off-by: Vijayanand Jitta <[email protected]>
> Reviewed-by: Robin Murphy <[email protected]>
> ---
> drivers/iommu/iova.c | 23 +++++++++++++++++------
> 1 file changed, 17 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
> index 30d969a..c3a1a8e 100644
> --- a/drivers/iommu/iova.c
> +++ b/drivers/iommu/iova.c
> @@ -184,8 +184,9 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
> struct rb_node *curr, *prev;
> struct iova *curr_iova;
> unsigned long flags;
> - unsigned long new_pfn;
> + unsigned long new_pfn, retry_pfn;
> unsigned long align_mask = ~0UL;
> + unsigned long high_pfn = limit_pfn, low_pfn = iovad->start_pfn;
>
> if (size_aligned)
> align_mask <<= fls_long(size - 1);
> @@ -198,15 +199,25 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
>
> curr = __get_cached_rbnode(iovad, limit_pfn);
> curr_iova = rb_entry(curr, struct iova, node);
> + retry_pfn = curr_iova->pfn_hi + 1;
> +
> +retry:
> do {
> - limit_pfn = min(limit_pfn, curr_iova->pfn_lo);
> - new_pfn = (limit_pfn - size) & align_mask;
> + high_pfn = min(high_pfn, curr_iova->pfn_lo);
> + new_pfn = (high_pfn - size) & align_mask;
> prev = curr;
> curr = rb_prev(curr);
> curr_iova = rb_entry(curr, struct iova, node);
> - } while (curr && new_pfn <= curr_iova->pfn_hi);
> -
> - if (limit_pfn < size || new_pfn < iovad->start_pfn) {
> + } while (curr && new_pfn <= curr_iova->pfn_hi && new_pfn >= low_pfn);
> +
> + if (high_pfn < size || new_pfn < low_pfn) {
> + if (low_pfn == iovad->start_pfn && retry_pfn < limit_pfn) {
> + high_pfn = limit_pfn;
> + low_pfn = retry_pfn;
> + curr = &iovad->anchor.node;
> + curr_iova = rb_entry(curr, struct iova, node);
> + goto retry;
> + }
> iovad->max32_alloc_size = size;
> goto iova32_full;
> }
>
Gentle ping.
Thanks,
Vijay
--
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a
member of Code Aurora Forum, hosted by The Linux Foundation
On 2020-09-30 08:44, [email protected] wrote:
> From: Vijayanand Jitta <[email protected]>
>
> When ever an iova alloc request fails we free the iova
> ranges present in the percpu iova rcaches and then retry
> but the global iova rcache is not freed as a result we could
> still see iova alloc failure even after retry as global
> rcache is holding the iova's which can cause fragmentation.
> So, free the global iova rcache as well and then go for the
> retry.
This looks reasonable to me - it's mildly annoying that we end up with
so many similar-looking functions, but the necessary differences are
right down in the middle of the loops so nothing can reasonably be
factored out :(
Reviewed-by: Robin Murphy <[email protected]>
> Signed-off-by: Vijayanand Jitta <[email protected]>
> ---
> drivers/iommu/iova.c | 23 +++++++++++++++++++++++
> 1 file changed, 23 insertions(+)
>
> diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
> index c3a1a8e..faf9b13 100644
> --- a/drivers/iommu/iova.c
> +++ b/drivers/iommu/iova.c
> @@ -25,6 +25,7 @@ static void init_iova_rcaches(struct iova_domain *iovad);
> static void free_iova_rcaches(struct iova_domain *iovad);
> static void fq_destroy_all_entries(struct iova_domain *iovad);
> static void fq_flush_timeout(struct timer_list *t);
> +static void free_global_cached_iovas(struct iova_domain *iovad);
>
> void
> init_iova_domain(struct iova_domain *iovad, unsigned long granule,
> @@ -442,6 +443,7 @@ alloc_iova_fast(struct iova_domain *iovad, unsigned long size,
> flush_rcache = false;
> for_each_online_cpu(cpu)
> free_cpu_cached_iovas(cpu, iovad);
> + free_global_cached_iovas(iovad);
> goto retry;
> }
>
> @@ -1057,5 +1059,26 @@ void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad)
> }
> }
>
> +/*
> + * free all the IOVA ranges of global cache
> + */
> +static void free_global_cached_iovas(struct iova_domain *iovad)
> +{
> + struct iova_rcache *rcache;
> + unsigned long flags;
> + int i, j;
> +
> + for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
> + rcache = &iovad->rcaches[i];
> + spin_lock_irqsave(&rcache->lock, flags);
> + for (j = 0; j < rcache->depot_size; ++j) {
> + iova_magazine_free_pfns(rcache->depot[j], iovad);
> + iova_magazine_free(rcache->depot[j]);
> + rcache->depot[j] = NULL;
> + }
> + rcache->depot_size = 0;
> + spin_unlock_irqrestore(&rcache->lock, flags);
> + }
> +}
> MODULE_AUTHOR("Anil S Keshavamurthy <[email protected]>");
> MODULE_LICENSE("GPL");
>
On 03/11/2020 12:35, Robin Murphy wrote:
> On 2020-09-30 08:44, [email protected] wrote:
>> From: Vijayanand Jitta <[email protected]>
>>
>> When ever an iova alloc request fails we free the iova
>> ranges present in the percpu iova rcaches and then retry
>> but the global iova rcache is not freed as a result we could
>> still see iova alloc failure even after retry as global
>> rcache is holding the iova's which can cause fragmentation.
>> So, free the global iova rcache as well and then go for the
>> retry.
>
If we do clear all the CPU rcaches, it would nice to have something
immediately available to replenish, i.e. use the global rcache, instead
of flushing it, if that is not required...
> This looks reasonable to me - it's mildly annoying that we end up with
> so many similar-looking functions,
Well I did add a function to clear all CPU rcaches here, if you would
like to check:
https://lore.kernel.org/linux-iommu/[email protected]/
> but the necessary differences are
> right down in the middle of the loops so nothing can reasonably be
> factored out :(
>
> Reviewed-by: Robin Murphy <[email protected]>
>
>> Signed-off-by: Vijayanand Jitta <[email protected]>
>> ---
>> drivers/iommu/iova.c | 23 +++++++++++++++++++++++
>> 1 file changed, 23 insertions(+)
>>
>> diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
>> index c3a1a8e..faf9b13 100644
>> --- a/drivers/iommu/iova.c
>> +++ b/drivers/iommu/iova.c
>> @@ -25,6 +25,7 @@ static void init_iova_rcaches(struct iova_domain
>> *iovad);
>> static void free_iova_rcaches(struct iova_domain *iovad);
>> static void fq_destroy_all_entries(struct iova_domain *iovad);
>> static void fq_flush_timeout(struct timer_list *t);
>> +static void free_global_cached_iovas(struct iova_domain *iovad);
a thought: It would be great if the file could be rearranged at some
point where we don't require so many forward declarations.
>> void
>> init_iova_domain(struct iova_domain *iovad, unsigned long granule,
>> @@ -442,6 +443,7 @@ alloc_iova_fast(struct iova_domain *iovad,
>> unsigned long size,
>> flush_rcache = false;
>> for_each_online_cpu(cpu)
>> free_cpu_cached_iovas(cpu, iovad);
>> + free_global_cached_iovas(iovad);
>> goto retry;
>> }
>> @@ -1057,5 +1059,26 @@ void free_cpu_cached_iovas(unsigned int cpu,
>> struct iova_domain *iovad)
>> }
>> }
>> +/*
>> + * free all the IOVA ranges of global cache
>> + */
>> +static void free_global_cached_iovas(struct iova_domain *iovad)
>> +{
>> + struct iova_rcache *rcache;
>> + unsigned long flags;
>> + int i, j;
>> +
>> + for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
>> + rcache = &iovad->rcaches[i];
>> + spin_lock_irqsave(&rcache->lock, flags);
>> + for (j = 0; j < rcache->depot_size; ++j) {
>> + iova_magazine_free_pfns(rcache->depot[j], iovad);
>> + iova_magazine_free(rcache->depot[j]);
>> + rcache->depot[j] = NULL;
I don't think that NULLify is strictly necessary
>> + }
>> + rcache->depot_size = 0;
>> + spin_unlock_irqrestore(&rcache->lock, flags);
>> + }
>> +}
>> MODULE_AUTHOR("Anil S Keshavamurthy <[email protected]>");
>> MODULE_LICENSE("GPL");
>>
> _______________________________________________
> iommu mailing list
> [email protected]
> https://lists.linuxfoundation.org/mailman/listinfo/iommu
> .
On 2020-11-03 14:31, John Garry wrote:
> On 03/11/2020 12:35, Robin Murphy wrote:
>> On 2020-09-30 08:44, [email protected] wrote:
>>> From: Vijayanand Jitta <[email protected]>
>>>
>>> When ever an iova alloc request fails we free the iova
>>> ranges present in the percpu iova rcaches and then retry
>>> but the global iova rcache is not freed as a result we could
>>> still see iova alloc failure even after retry as global
>>> rcache is holding the iova's which can cause fragmentation.
>>> So, free the global iova rcache as well and then go for the
>>> retry.
>>
>
> If we do clear all the CPU rcaches, it would nice to have something
> immediately available to replenish, i.e. use the global rcache, instead
> of flushing it, if that is not required...
If we've reached the point of clearing *any* caches, though, I think any
hope of maintaining performance is already long gone. We've walked the
rbtree for the entire address space and found that it's still too full
to allocate from; we're teetering on the brink of hard failure and this
is a last-ditch attempt to claw back as much as possible in the hope
that it gives us a usable space.
TBH I'm not entirely sure what allocation pattern was expected by the
original code such that purging only some of the caches made sense, nor
what kind of pattern leads to lots of smaller IOVAs being allocated,
freed, and never reused to the point of blocking larger allocations, but
either way the reasoning does at least seem to hold up in abstract.
>> This looks reasonable to me - it's mildly annoying that we end up with
>> so many similar-looking functions,
>
> Well I did add a function to clear all CPU rcaches here, if you would
> like to check:
>
> https://lore.kernel.org/linux-iommu/[email protected]/
I was thinking more of the way free_iova_rcaches(),
free_cpu_cached_iovas(), and free_global_cached_iovas() all look pretty
much the same shape at a glance.
>> but the necessary differences are right down in the middle of the
>> loops so nothing can reasonably be factored out :(
>>
>> Reviewed-by: Robin Murphy <[email protected]>
>>
>>> Signed-off-by: Vijayanand Jitta <[email protected]>
>>> ---
>>> drivers/iommu/iova.c | 23 +++++++++++++++++++++++
>>> 1 file changed, 23 insertions(+)
>>>
>>> diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
>>> index c3a1a8e..faf9b13 100644
>>> --- a/drivers/iommu/iova.c
>>> +++ b/drivers/iommu/iova.c
>>> @@ -25,6 +25,7 @@ static void init_iova_rcaches(struct iova_domain
>>> *iovad);
>>> static void free_iova_rcaches(struct iova_domain *iovad);
>>> static void fq_destroy_all_entries(struct iova_domain *iovad);
>>> static void fq_flush_timeout(struct timer_list *t);
>>> +static void free_global_cached_iovas(struct iova_domain *iovad);
>
> a thought: It would be great if the file could be rearranged at some
> point where we don't require so many forward declarations.
>
>>> void
>>> init_iova_domain(struct iova_domain *iovad, unsigned long granule,
>>> @@ -442,6 +443,7 @@ alloc_iova_fast(struct iova_domain *iovad,
>>> unsigned long size,
>>> flush_rcache = false;
>>> for_each_online_cpu(cpu)
>>> free_cpu_cached_iovas(cpu, iovad);
>>> + free_global_cached_iovas(iovad);
>>> goto retry;
>>> }
>>> @@ -1057,5 +1059,26 @@ void free_cpu_cached_iovas(unsigned int cpu,
>>> struct iova_domain *iovad)
>>> }
>>> }
>>> +/*
>>> + * free all the IOVA ranges of global cache
>>> + */
>>> +static void free_global_cached_iovas(struct iova_domain *iovad)
>>> +{
>>> + struct iova_rcache *rcache;
>>> + unsigned long flags;
>>> + int i, j;
>>> +
>>> + for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
>>> + rcache = &iovad->rcaches[i];
>>> + spin_lock_irqsave(&rcache->lock, flags);
>>> + for (j = 0; j < rcache->depot_size; ++j) {
>>> + iova_magazine_free_pfns(rcache->depot[j], iovad);
>>> + iova_magazine_free(rcache->depot[j]);
>>> + rcache->depot[j] = NULL;
>
> I don't think that NULLify is strictly necessary
True, we don't explicitly clear depot entries in __iova_rcache_get() for
normal operation, so there's not much point in doing so here.
Robin.
>>> + }
>>> + rcache->depot_size = 0;
>>> + spin_unlock_irqrestore(&rcache->lock, flags);
>>> + }
>>> +}
>>> MODULE_AUTHOR("Anil S Keshavamurthy
>>> <[email protected]>");
>>> MODULE_LICENSE("GPL");
>>>
>> _______________________________________________
>> iommu mailing list
>> [email protected]
>> https://lists.linuxfoundation.org/mailman/listinfo/iommu
>> .
>
On 03/11/2020 15:59, Robin Murphy wrote:
>>>> alloc failure even after retry as global
>>>> rcache is holding the iova's which can cause fragmentation.
>>>> So, free the global iova rcache as well and then go for the
>>>> retry.
>>>
>>
>> If we do clear all the CPU rcaches, it would nice to have something
>> immediately available to replenish, i.e. use the global rcache,
>> instead of flushing it, if that is not required...
>
> If we've reached the point of clearing *any* caches, though, I think any
> hope of maintaining performance is already long gone. We've walked the
> rbtree for the entire address space and found that it's still too full
> to allocate from; we're teetering on the brink of hard failure and this
> is a last-ditch attempt to claw back as much as possible in the hope
> that it gives us a usable space. >
> TBH I'm not entirely sure what allocation pattern was expected by the
> original code such that purging only some of the caches made sense,
I'd say that the assumption is that once the CPU rcaches are flushed,
then we should have space again. No need to go any further.
> nor
> what kind of pattern leads to lots of smaller IOVAs being allocated,
> freed, and never reused to the point of blocking larger allocations, but
> either way the reasoning does at least seem to hold up in abstract.
Ok, but I'd like to see that hard failure (if you get my meaning).
Flushing the depot rcache may be papering over some other bug.
Either way, I don't feel to strongly, so if you're happy then I won't
try to block, so [apart from comment, below]:
Acked-by: John Garry <[email protected]>
>
>>> This looks reasonable to me - it's mildly annoying that we end up
>>> with so many similar-looking functions,
>>
>> Well I did add a function to clear all CPU rcaches here, if you would
>> like to check:
>>
>> https://lore.kernel.org/linux-iommu/[email protected]/
>
>
> I was thinking more of the way free_iova_rcaches(),
> free_cpu_cached_iovas(), and free_global_cached_iovas() all look pretty
> much the same shape at a glance.
>
>>> but the necessary differences are right down in the middle of the
>>> loops so nothing can reasonably be factored out :(
>>>
>>> Reviewed-by: Robin Murphy <[email protected]>
>>>
>>>> Signed-off-by: Vijayanand Jitta <[email protected]>
>>>> ---
>>>> drivers/iommu/iova.c | 23 +++++++++++++++++++++++
>>>> 1 file changed, 23 insertions(+)
>>>>
>>>> diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
>>>> index c3a1a8e..faf9b13 100644
>>>> --- a/drivers/iommu/iova.c
>>>> +++ b/drivers/iommu/iova.c
>>>> @@ -25,6 +25,7 @@ static void init_iova_rcaches(struct iova_domain
>>>> *iovad);
>>>> static void free_iova_rcaches(struct iova_domain *iovad);
>>>> static void fq_destroy_all_entries(struct iova_domain *iovad);
>>>> static void fq_flush_timeout(struct timer_list *t);
>>>> +static void free_global_cached_iovas(struct iova_domain *iovad);
>>
>> a thought: It would be great if the file could be rearranged at some
>> point where we don't require so many forward declarations.
>>
>>>> void
>>>> init_iova_domain(struct iova_domain *iovad, unsigned long granule,
>>>> @@ -442,6 +443,7 @@ alloc_iova_fast(struct iova_domain *iovad,
>>>> unsigned long size,
>>>> flush_rcache = false;
>>>> for_each_online_cpu(cpu)
>>>> free_cpu_cached_iovas(cpu, iovad);
>>>> + free_global_cached_iovas(iovad);
>>>> goto retry;
>>>> }
>>>> @@ -1057,5 +1059,26 @@ void free_cpu_cached_iovas(unsigned int cpu,
>>>> struct iova_domain *iovad)
>>>> }
>>>> }
>>>> +/*
>>>> + * free all the IOVA ranges of global cache
>>>> + */
>>>> +static void free_global_cached_iovas(struct iova_domain *iovad)
>>>> +{
>>>> + struct iova_rcache *rcache;
>>>> + unsigned long flags;
>>>> + int i, j;
>>>> +
>>>> + for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
>>>> + rcache = &iovad->rcaches[i];
>>>> + spin_lock_irqsave(&rcache->lock, flags);
>>>> + for (j = 0; j < rcache->depot_size; ++j) {
>>>> + iova_magazine_free_pfns(rcache->depot[j], iovad);
>>>> + iova_magazine_free(rcache->depot[j]);
>>>> + rcache->depot[j] = NULL;
>>
>> I don't think that NULLify is strictly necessary
>
> True, we don't explicitly clear depot entries in __iova_rcache_get() for
> normal operation, so there's not much point in doing so here.
Right, so for consistency, I think that it would be nice not to NULLify,
for consistency.
>
> Robin.
On Wed, 30 Sep 2020 13:14:23 +0530, [email protected] wrote:
> When ever a new iova alloc request comes iova is always searched
> from the cached node and the nodes which are previous to cached
> node. So, even if there is free iova space available in the nodes
> which are next to the cached node iova allocation can still fail
> because of this approach.
>
> Consider the following sequence of iova alloc and frees on
> 1GB of iova space
>
> [...]
Applied to arm64 (for-next/iommu/iova), thanks!
[1/2] iommu/iova: Retry from last rb tree node if iova search fails
https://git.kernel.org/arm64/c/4e89dce72521
[2/2] iommu/iova: Free global iova rcache on iova alloc failure
https://git.kernel.org/arm64/c/6fa3525b455a
Cheers,
--
Will
https://fixes.arm64.dev
https://next.arm64.dev
https://will.arm64.dev