net: page_pool: record pools per netdev

Link the page pools with netdevs. This needs to be netns compatible
so we have two options. Either we record the pools per netns and
have to worry about moving them as the netdev gets moved.
Or we record them directly on the netdev so they move with the netdev
without any extra work.

Implement the latter option. Since pools may outlast netdev we need
a place to store orphans. In time honored tradition use loopback
for this purpose.

Reviewed-by: Mina Almasry <almasrymina@google.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>
This commit is contained in:
Jakub Kicinski 2023-11-26 15:07:30 -08:00 committed by Paolo Abeni
parent f17c69649c
commit 083772c9f9
5 changed files with 114 additions and 0 deletions

View file

@ -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) \

View file

@ -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)

View file

@ -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))

View file

@ -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;
@ -189,6 +192,7 @@ struct page_pool {
struct page_pool_params_slow slow;
/* User-facing fields, protected by page_pools_lock */
struct {
struct hlist_node list;
u32 id;
} user;
};

View file

@ -1,14 +1,31 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/mutex.h>
#include <linux/netdevice.h>
#include <linux/xarray.h>
#include <net/net_debug.h>
#include <net/page_pool/types.h>
#include "page_pool_priv.h"
static DEFINE_XARRAY_FLAGS(page_pools, XA_FLAGS_ALLOC1);
/* Protects: page_pools, netdevice->page_pools, pool->slow.netdev, pool->user.
* Ordering: inside rtnl_lock
*/
static DEFINE_MUTEX(page_pools_lock);
/* Page pools are only reachable from user space (via netlink) if they are
* linked to a netdev at creation time. Following page pool "visibility"
* states are possible:
* - normal
* - user.list: linked to real netdev, netdev: real netdev
* - orphaned - real netdev has disappeared
* - user.list: linked to lo, netdev: lo
* - invisible - either (a) created without netdev linking, (b) unlisted due
* to error, or (c) the entire namespace which owned this pool disappeared
* - user.list: unhashed, netdev: unknown
*/
int page_pool_list(struct page_pool *pool)
{
static u32 id_alloc_next;
@ -20,6 +37,10 @@ int page_pool_list(struct page_pool *pool)
if (err < 0)
goto err_unlock;
if (pool->slow.netdev)
hlist_add_head(&pool->user.list,
&pool->slow.netdev->page_pools);
mutex_unlock(&page_pools_lock);
return 0;
@ -32,5 +53,68 @@ void page_pool_unlist(struct page_pool *pool)
{
mutex_lock(&page_pools_lock);
xa_erase(&page_pools, pool->user.id);
hlist_del(&pool->user.list);
mutex_unlock(&page_pools_lock);
}
static void page_pool_unreg_netdev_wipe(struct net_device *netdev)
{
struct page_pool *pool;
struct hlist_node *n;
mutex_lock(&page_pools_lock);
hlist_for_each_entry_safe(pool, n, &netdev->page_pools, user.list) {
hlist_del_init(&pool->user.list);
pool->slow.netdev = NET_PTR_POISON;
}
mutex_unlock(&page_pools_lock);
}
static void page_pool_unreg_netdev(struct net_device *netdev)
{
struct page_pool *pool, *last;
struct net_device *lo;
lo = dev_net(netdev)->loopback_dev;
mutex_lock(&page_pools_lock);
last = NULL;
hlist_for_each_entry(pool, &netdev->page_pools, user.list) {
pool->slow.netdev = lo;
last = pool;
}
if (last)
hlist_splice_init(&netdev->page_pools, &last->user.list,
&lo->page_pools);
mutex_unlock(&page_pools_lock);
}
static int
page_pool_netdevice_event(struct notifier_block *nb,
unsigned long event, void *ptr)
{
struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
if (event != NETDEV_UNREGISTER)
return NOTIFY_DONE;
if (hlist_empty(&netdev->page_pools))
return NOTIFY_OK;
if (netdev->ifindex != LOOPBACK_IFINDEX)
page_pool_unreg_netdev(netdev);
else
page_pool_unreg_netdev_wipe(netdev);
return NOTIFY_OK;
}
static struct notifier_block page_pool_netdevice_nb = {
.notifier_call = page_pool_netdevice_event,
};
static int __init page_pool_user_init(void)
{
return register_netdevice_notifier(&page_pool_netdevice_nb);
}
subsys_initcall(page_pool_user_init);