From: Jakub Kicinski <kuba@kernel.org>
Date: Sun, 26 Nov 2023 15:07:37 -0800
Subject: net: page_pool: report when page pool was destroyed
Patch-mainline: v6.8-rc1
Git-commit: 69cb4952b6f6a226c1c0a7ca400398aaa8f75cf2
References: jsc#PED-7574
Report when page pool was destroyed. Together with the inflight
/ memory use reporting this can serve as a replacement for the
warning about leaked page pools we currently print to dmesg.
Example output for a fake leaked page pool using some hacks
in netdevsim (one "live" pool, and one "leaked" on the same dev):
$ ./cli.py --no-schema --spec netlink/specs/netdev.yaml \
--dump page-pool-get
[{'id': 2, 'ifindex': 3},
{'id': 1, 'ifindex': 3, 'destroyed': 133, 'inflight': 1}]
Tested-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
Documentation/netlink/specs/netdev.yaml | 13 +++++++++++++
include/net/page_pool/types.h | 1 +
include/uapi/linux/netdev.h | 1 +
net/core/page_pool.c | 1 +
net/core/page_pool_priv.h | 1 +
net/core/page_pool_user.c | 12 ++++++++++++
6 files changed, 29 insertions(+)
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -127,6 +127,18 @@ attribute-sets:
type: uint
doc: |
Amount of memory held by inflight pages.
+ -
+ name: detach-time
+ type: uint
+ doc: |
+ Seconds in CLOCK_BOOTTIME of when Page Pool was detached by
+ the driver. Once detached Page Pool can no longer be used to
+ allocate memory.
+ Page Pools wait for all the memory allocated from them to be freed
+ before truly disappearing. "Detached" Page Pools cannot be
+ "re-attached", they are just waiting to disappear.
+ Attribute is absent if Page Pool has not been detached, and
+ can still be used to allocate new memory.
operations:
list:
@@ -178,6 +190,7 @@ operations:
- napi-id
- inflight
- inflight-mem
+ - detach-time
dump:
reply: *pp-reply
config-cond: page-pool
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -193,6 +193,7 @@ struct page_pool {
/* User-facing fields, protected by page_pools_lock */
struct {
struct hlist_node list;
+ u64 detach_time;
u32 napi_id;
u32 id;
} user;
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -70,6 +70,7 @@ enum {
NETDEV_A_PAGE_POOL_NAPI_ID,
NETDEV_A_PAGE_POOL_INFLIGHT,
NETDEV_A_PAGE_POOL_INFLIGHT_MEM,
+ NETDEV_A_PAGE_POOL_DETACH_TIME,
__NETDEV_A_PAGE_POOL_MAX,
NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1)
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -953,6 +953,7 @@ void page_pool_destroy(struct page_pool
if (!page_pool_release(pool))
return;
+ page_pool_detached(pool);
pool->defer_start = jiffies;
pool->defer_warn = jiffies + DEFER_WARN_INTERVAL;
--- a/net/core/page_pool_priv.h
+++ b/net/core/page_pool_priv.h
@@ -6,6 +6,7 @@
s32 page_pool_inflight(const struct page_pool *pool, bool strict);
int page_pool_list(struct page_pool *pool);
+void page_pool_detached(struct page_pool *pool);
void page_pool_unlist(struct page_pool *pool);
#endif
--- a/net/core/page_pool_user.c
+++ b/net/core/page_pool_user.c
@@ -134,6 +134,10 @@ page_pool_nl_fill(struct sk_buff *rsp, c
nla_put_uint(rsp, NETDEV_A_PAGE_POOL_INFLIGHT_MEM,
inflight * refsz))
goto err_cancel;
+ if (pool->user.detach_time &&
+ nla_put_uint(rsp, NETDEV_A_PAGE_POOL_DETACH_TIME,
+ pool->user.detach_time))
+ goto err_cancel;
genlmsg_end(rsp, hdr);
@@ -219,6 +223,14 @@ err_unlock:
return err;
}
+void page_pool_detached(struct page_pool *pool)
+{
+ mutex_lock(&page_pools_lock);
+ pool->user.detach_time = ktime_get_boottime_seconds();
+ netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_CHANGE_NTF);
+ mutex_unlock(&page_pools_lock);
+}
+
void page_pool_unlist(struct page_pool *pool)
{
mutex_lock(&page_pools_lock);