[PATCH] kernel/resource: optimize find_next_iomem_res
From: Chia-I Wu
Date: Fri May 31 2024 - 01:37:26 EST
We can skip children resources when the parent resource does not cover
the range.
This should help vmf_insert_* users on x86, such as several DRM drivers.
On my AMD Ryzen 5 7520C, when streaming data from cpu memory into amdgpu
bo, the throughput goes from 5.1GB/s to 6.6GB/s. perf report says
34.69%--__do_fault
34.60%--amdgpu_gem_fault
34.00%--ttm_bo_vm_fault_reserved
32.95%--vmf_insert_pfn_prot
25.89%--track_pfn_insert
24.35%--lookup_memtype
21.77%--pat_pagerange_is_ram
20.80%--walk_system_ram_range
17.42%--find_next_iomem_res
before this change, and
26.67%--__do_fault
26.57%--amdgpu_gem_fault
25.83%--ttm_bo_vm_fault_reserved
24.40%--vmf_insert_pfn_prot
14.30%--track_pfn_insert
12.20%--lookup_memtype
9.34%--pat_pagerange_is_ram
8.22%--walk_system_ram_range
5.09%--find_next_iomem_res
after.
Signed-off-by: Chia-I Wu <olvaffe@xxxxxxxxx>
---
kernel/resource.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/kernel/resource.c b/kernel/resource.c
index fcbca39dbc450..19b84b4f9a577 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -326,6 +326,7 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end,
unsigned long flags, unsigned long desc,
struct resource *res)
{
+ bool skip_children = false;
struct resource *p;
if (!res)
@@ -336,7 +337,7 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end,
read_lock(&resource_lock);
- for_each_resource(&iomem_resource, p, false) {
+ for_each_resource(&iomem_resource, p, skip_children) {
/* If we passed the resource we are looking for, stop */
if (p->start > end) {
p = NULL;
@@ -344,8 +345,11 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end,
}
/* Skip until we find a range that matches what we look for */
- if (p->end < start)
+ if (p->end < start) {
+ skip_children = true;
continue;
+ }
+ skip_children = false;
if ((p->flags & flags) != flags)
continue;
--
2.45.1.288.g0e0cd299f1-goog