summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
authorPaolo Abeni <pabeni@redhat.com>2023-11-28 17:48:42 +0300
committerPaolo Abeni <pabeni@redhat.com>2023-11-28 17:48:43 +0300
commita379972973a80924b1d03443e20f113ff76a94c7 (patch)
tree03d795a2591a1f3ce239993abf09790f3bc8a799 /include
parenta214724554aee8f6a5953dccab51ceff448c08cd (diff)
parent637567e4a3ef6f6a5ffa48781207d270265f7e68 (diff)
downloadlinux-a379972973a80924b1d03443e20f113ff76a94c7.tar.xz
Merge branch 'net-page_pool-add-netlink-based-introspection'
Jakub Kicinski says: ==================== net: page_pool: add netlink-based introspection We recently started to deploy newer kernels / drivers at Meta, making significant use of page pools for the first time. We immediately run into page pool leaks both real and false positive warnings. As Eric pointed out/predicted there's no guarantee that applications will read / close their sockets so a page pool page may be stuck in a socket (but not leaked) forever. This happens a lot in our fleet. Most of these are obviously due to application bugs but we should not be printing kernel warnings due to minor application resource leaks. Conversely the page pool memory may get leaked at runtime, and we have no way to detect / track that, unless someone reconfigures the NIC and destroys the page pools which leaked the pages. The solution presented here is to expose the memory use of page pools via netlink. This allows for continuous monitoring of memory used by page pools, regardless if they were destroyed or not. Sample in patch 15 can print the memory use and recycling efficiency: $ ./page-pool eth0[2] page pools: 10 (zombies: 0) refs: 41984 bytes: 171966464 (refs: 0 bytes: 0) recycling: 90.3% (alloc: 656:397681 recycle: 89652:270201) v4: - use dev_net(netdev)->loopback_dev - extend inflight doc v3: https://lore.kernel.org/all/20231122034420.1158898-1-kuba@kernel.org/ - ID is still here, can't decide if it matters - rename destroyed -> detach-time, good enough? - fix build for netsec v2: https://lore.kernel.org/r/20231121000048.789613-1-kuba@kernel.org - hopefully fix build with PAGE_POOL=n v1: https://lore.kernel.org/all/20231024160220.3973311-1-kuba@kernel.org/ - The main change compared to the RFC is that the API now exposes outstanding references and byte counts even for "live" page pools. The warning is no longer printed if page pool is accessible via netlink. RFC: https://lore.kernel.org/all/20230816234303.3786178-1-kuba@kernel.org/ ==================== Link: https://lore.kernel.org/r/20231126230740.2148636-1-kuba@kernel.org Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Diffstat (limited to 'include')
-rw-r--r--include/linux/list.h20
-rw-r--r--include/linux/netdevice.h4
-rw-r--r--include/linux/poison.h2
-rw-r--r--include/net/page_pool/helpers.h8
-rw-r--r--include/net/page_pool/types.h10
-rw-r--r--include/uapi/linux/netdev.h36
6 files changed, 74 insertions, 6 deletions
diff --git a/include/linux/list.h b/include/linux/list.h
index 1837caedf723..059aa1fff41e 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -1119,6 +1119,26 @@ static inline void hlist_move_list(struct hlist_head *old,
old->first = NULL;
}
+/**
+ * hlist_splice_init() - move all entries from one list to another
+ * @from: hlist_head from which entries will be moved
+ * @last: last entry on the @from list
+ * @to: hlist_head to which entries will be moved
+ *
+ * @to can be empty, @from must contain at least @last.
+ */
+static inline void hlist_splice_init(struct hlist_head *from,
+ struct hlist_node *last,
+ struct hlist_head *to)
+{
+ if (to->first)
+ to->first->pprev = &last->next;
+ last->next = to->first;
+ to->first = from->first;
+ from->first->pprev = &to->first;
+ from->first = NULL;
+}
+
#define hlist_entry(ptr, type, member) container_of(ptr,type,member)
#define hlist_for_each(pos, head) \
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index e87caa81f70c..998c7aaa98b8 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2447,6 +2447,10 @@ struct net_device {
#if IS_ENABLED(CONFIG_DPLL)
struct dpll_pin *dpll_pin;
#endif
+#if IS_ENABLED(CONFIG_PAGE_POOL)
+ /** @page_pools: page pools created for this netdevice */
+ struct hlist_head page_pools;
+#endif
};
#define to_net_dev(d) container_of(d, struct net_device, dev)
diff --git a/include/linux/poison.h b/include/linux/poison.h
index 851a855d3868..27a7dad17eef 100644
--- a/include/linux/poison.h
+++ b/include/linux/poison.h
@@ -83,6 +83,8 @@
/********** net/core/skbuff.c **********/
#define SKB_LIST_POISON_NEXT ((void *)(0x800 + POISON_POINTER_DELTA))
+/********** net/ **********/
+#define NET_PTR_POISON ((void *)(0x801 + POISON_POINTER_DELTA))
/********** kernel/bpf/ **********/
#define BPF_PTR_POISON ((void *)(0xeB9FUL + POISON_POINTER_DELTA))
diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h
index 4ebd544ae977..7dc65774cde5 100644
--- a/include/net/page_pool/helpers.h
+++ b/include/net/page_pool/helpers.h
@@ -55,16 +55,12 @@
#include <net/page_pool/types.h>
#ifdef CONFIG_PAGE_POOL_STATS
+/* Deprecated driver-facing API, use netlink instead */
int page_pool_ethtool_stats_get_count(void);
u8 *page_pool_ethtool_stats_get_strings(u8 *data);
u64 *page_pool_ethtool_stats_get(u64 *data, void *stats);
-/*
- * Drivers that wish to harvest page pool stats and report them to users
- * (perhaps via ethtool, debugfs, or another mechanism) can allocate a
- * struct page_pool_stats call page_pool_get_stats to get stats for the specified pool.
- */
-bool page_pool_get_stats(struct page_pool *pool,
+bool page_pool_get_stats(const struct page_pool *pool,
struct page_pool_stats *stats);
#else
static inline int page_pool_ethtool_stats_get_count(void)
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index e1bb92c192de..ac286ea8ce2d 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -5,6 +5,7 @@
#include <linux/dma-direction.h>
#include <linux/ptr_ring.h>
+#include <linux/types.h>
#define PP_FLAG_DMA_MAP BIT(0) /* Should page_pool do the DMA
* map/unmap
@@ -48,6 +49,7 @@ struct pp_alloc_cache {
* @pool_size: size of the ptr_ring
* @nid: NUMA node id to allocate from pages from
* @dev: device, for DMA pre-mapping purposes
+ * @netdev: netdev this pool will serve (leave as NULL if none or multiple)
* @napi: NAPI which is the sole consumer of pages, otherwise NULL
* @dma_dir: DMA mapping direction
* @max_len: max DMA sync memory size for PP_FLAG_DMA_SYNC_DEV
@@ -66,6 +68,7 @@ struct page_pool_params {
unsigned int offset;
);
struct_group_tagged(page_pool_params_slow, slow,
+ struct net_device *netdev;
/* private: used by test code only */
void (*init_callback)(struct page *page, void *arg);
void *init_arg;
@@ -187,6 +190,13 @@ struct page_pool {
/* Slow/Control-path information follows */
struct page_pool_params_slow slow;
+ /* User-facing fields, protected by page_pools_lock */
+ struct {
+ struct hlist_node list;
+ u64 detach_time;
+ u32 napi_id;
+ u32 id;
+ } user;
};
struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp);
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 2943a151d4f1..2b37233e00c0 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -65,15 +65,51 @@ enum {
};
enum {
+ NETDEV_A_PAGE_POOL_ID = 1,
+ NETDEV_A_PAGE_POOL_IFINDEX,
+ 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)
+};
+
+enum {
+ NETDEV_A_PAGE_POOL_STATS_INFO = 1,
+ NETDEV_A_PAGE_POOL_STATS_ALLOC_FAST = 8,
+ NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW,
+ NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW_HIGH_ORDER,
+ NETDEV_A_PAGE_POOL_STATS_ALLOC_EMPTY,
+ NETDEV_A_PAGE_POOL_STATS_ALLOC_REFILL,
+ NETDEV_A_PAGE_POOL_STATS_ALLOC_WAIVE,
+ NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHED,
+ NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHE_FULL,
+ NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING,
+ NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING_FULL,
+ NETDEV_A_PAGE_POOL_STATS_RECYCLE_RELEASED_REFCNT,
+
+ __NETDEV_A_PAGE_POOL_STATS_MAX,
+ NETDEV_A_PAGE_POOL_STATS_MAX = (__NETDEV_A_PAGE_POOL_STATS_MAX - 1)
+};
+
+enum {
NETDEV_CMD_DEV_GET = 1,
NETDEV_CMD_DEV_ADD_NTF,
NETDEV_CMD_DEV_DEL_NTF,
NETDEV_CMD_DEV_CHANGE_NTF,
+ NETDEV_CMD_PAGE_POOL_GET,
+ NETDEV_CMD_PAGE_POOL_ADD_NTF,
+ NETDEV_CMD_PAGE_POOL_DEL_NTF,
+ NETDEV_CMD_PAGE_POOL_CHANGE_NTF,
+ NETDEV_CMD_PAGE_POOL_STATS_GET,
__NETDEV_CMD_MAX,
NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
};
#define NETDEV_MCGRP_MGMT "mgmt"
+#define NETDEV_MCGRP_PAGE_POOL "page-pool"
#endif /* _UAPI_LINUX_NETDEV_H */