From: Alistair Popple <apopple@nvidia.com>
To: linux-mm@kvack.org, cgroups@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, jgg@nvidia.com,
jhubbard@nvidia.com, tjmercier@google.com, hannes@cmpxchg.org,
surenb@google.com, mkoutny@suse.com, daniel@ffwll.ch,
Alistair Popple <apopple@nvidia.com>,
netdev@vger.kernel.org, linux-rdma@vger.kernel.org,
rds-devel@oss.oracle.com
Subject: [RFC PATCH 10/19] net: skb: Switch to using vm_account
Date: Tue, 24 Jan 2023 16:42:39 +1100 [thread overview]
Message-ID: <9b54eef0b41b678cc5f318bd5ae0917bba5b8e21.1674538665.git-series.apopple@nvidia.com> (raw)
In-Reply-To: <cover.f52b9eb2792bccb8a9ecd6bc95055705cfe2ae03.1674538665.git-series.apopple@nvidia.com>
Switch to using vm_account to charge pinned pages. This will allow a
future change to charge the pinned pages to a cgroup to limit the
overall number of pinned pages in the system.
Signed-off-by: Alistair Popple <apopple@nvidia.com>
Cc: linux-kernel@vger.kernel.org
Cc: netdev@vger.kernel.org
Cc: linux-rdma@vger.kernel.org
Cc: rds-devel@oss.oracle.com
---
include/linux/skbuff.h | 6 ++---
include/net/sock.h | 2 ++-
net/core/skbuff.c | 47 +++++++++++++++----------------------------
net/rds/message.c | 9 +++++---
4 files changed, 28 insertions(+), 36 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 4c84924..c956405 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -554,7 +554,6 @@ struct ubuf_info_msgzc {
};
struct mmpin {
- struct user_struct *user;
unsigned int num_pg;
} mmp;
};
@@ -563,8 +562,9 @@ struct ubuf_info_msgzc {
#define uarg_to_msgzc(ubuf_ptr) container_of((ubuf_ptr), struct ubuf_info_msgzc, \
ubuf)
-int mm_account_pinned_pages(struct mmpin *mmp, size_t size);
-void mm_unaccount_pinned_pages(struct mmpin *mmp);
+int mm_account_pinned_pages(struct vm_account *vm_account, struct mmpin *mmp,
+ size_t size);
+void mm_unaccount_pinned_pages(struct vm_account *vm_account, struct mmpin *mmp);
/* This data is invariant across clones and lives at
* the end of the header data, ie. at skb->end.
diff --git a/include/net/sock.h b/include/net/sock.h
index dcd72e6..bc3a868 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -334,6 +334,7 @@ struct sk_filter;
* @sk_security: used by security modules
* @sk_mark: generic packet mark
* @sk_cgrp_data: cgroup data for this cgroup
+ * @sk_vm_account: data for pinned memory accounting
* @sk_memcg: this socket's memory cgroup association
* @sk_write_pending: a write to stream socket waits to start
* @sk_state_change: callback to indicate change in the state of the sock
@@ -523,6 +524,7 @@ struct sock {
void *sk_security;
#endif
struct sock_cgroup_data sk_cgrp_data;
+ struct vm_account sk_vm_account;
struct mem_cgroup *sk_memcg;
void (*sk_state_change)(struct sock *sk);
void (*sk_data_ready)(struct sock *sk);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 4a0eb55..bed3fc9 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1309,42 +1309,25 @@ struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src)
}
EXPORT_SYMBOL_GPL(skb_morph);
-int mm_account_pinned_pages(struct mmpin *mmp, size_t size)
+int mm_account_pinned_pages(struct vm_account *vm_account, struct mmpin *mmp,
+ size_t size)
{
- unsigned long max_pg, num_pg, new_pg, old_pg;
- struct user_struct *user;
-
- if (capable(CAP_IPC_LOCK) || !size)
- return 0;
+ unsigned int num_pg;
num_pg = (size >> PAGE_SHIFT) + 2; /* worst case */
- max_pg = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
- user = mmp->user ? : current_user();
+ if (vm_account_pinned(vm_account, num_pg))
+ return -ENOBUFS;
- old_pg = atomic_long_read(&user->locked_vm);
- do {
- new_pg = old_pg + num_pg;
- if (new_pg > max_pg)
- return -ENOBUFS;
- } while (!atomic_long_try_cmpxchg(&user->locked_vm, &old_pg, new_pg));
-
- if (!mmp->user) {
- mmp->user = get_uid(user);
- mmp->num_pg = num_pg;
- } else {
- mmp->num_pg += num_pg;
- }
+ mmp->num_pg += num_pg;
return 0;
}
EXPORT_SYMBOL_GPL(mm_account_pinned_pages);
-void mm_unaccount_pinned_pages(struct mmpin *mmp)
+void mm_unaccount_pinned_pages(struct vm_account *vm_account, struct mmpin *mmp)
{
- if (mmp->user) {
- atomic_long_sub(mmp->num_pg, &mmp->user->locked_vm);
- free_uid(mmp->user);
- }
+ vm_unaccount_pinned(vm_account, mmp->num_pg);
+ vm_account_release(vm_account);
}
EXPORT_SYMBOL_GPL(mm_unaccount_pinned_pages);
@@ -1361,9 +1344,12 @@ static struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size)
BUILD_BUG_ON(sizeof(*uarg) > sizeof(skb->cb));
uarg = (void *)skb->cb;
- uarg->mmp.user = NULL;
+ uarg->mmp.num_pg = 0;
+ vm_account_init(&sk->sk_vm_account, current,
+ current_user(), VM_ACCOUNT_USER);
- if (mm_account_pinned_pages(&uarg->mmp, size)) {
+ if (mm_account_pinned_pages(&sk->sk_vm_account, &uarg->mmp, size)) {
+ vm_account_release(&sk->sk_vm_account);
kfree_skb(skb);
return NULL;
}
@@ -1416,7 +1402,8 @@ struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
next = (u32)atomic_read(&sk->sk_zckey);
if ((u32)(uarg_zc->id + uarg_zc->len) == next) {
- if (mm_account_pinned_pages(&uarg_zc->mmp, size))
+ if (mm_account_pinned_pages(&sk->sk_vm_account,
+ &uarg_zc->mmp, size))
return NULL;
uarg_zc->len++;
uarg_zc->bytelen = bytelen;
@@ -1466,7 +1453,7 @@ static void __msg_zerocopy_callback(struct ubuf_info_msgzc *uarg)
u32 lo, hi;
u16 len;
- mm_unaccount_pinned_pages(&uarg->mmp);
+ mm_unaccount_pinned_pages(&sk->sk_vm_account, &uarg->mmp);
/* if !len, there was only 1 call, and it was aborted
* so do not queue a completion notification
diff --git a/net/rds/message.c b/net/rds/message.c
index b47e4f0..2138a70 100644
--- a/net/rds/message.c
+++ b/net/rds/message.c
@@ -99,7 +99,7 @@ static void rds_rm_zerocopy_callback(struct rds_sock *rs,
struct list_head *head;
unsigned long flags;
- mm_unaccount_pinned_pages(&znotif->z_mmp);
+ mm_unaccount_pinned_pages(&rs->rs_sk.sk_vm_account, &znotif->z_mmp);
q = &rs->rs_zcookie_queue;
spin_lock_irqsave(&q->lock, flags);
head = &q->zcookie_head;
@@ -367,6 +367,7 @@ static int rds_message_zcopy_from_user(struct rds_message *rm, struct iov_iter *
int ret = 0;
int length = iov_iter_count(from);
struct rds_msg_zcopy_info *info;
+ struct vm_account *vm_account = &rm->m_rs->rs_sk.sk_vm_account;
rm->m_inc.i_hdr.h_len = cpu_to_be32(iov_iter_count(from));
@@ -380,7 +381,9 @@ static int rds_message_zcopy_from_user(struct rds_message *rm, struct iov_iter *
return -ENOMEM;
INIT_LIST_HEAD(&info->rs_zcookie_next);
rm->data.op_mmp_znotifier = &info->znotif;
- if (mm_account_pinned_pages(&rm->data.op_mmp_znotifier->z_mmp,
+ vm_account_init(vm_account, current, current_user(), VM_ACCOUNT_USER);
+ if (mm_account_pinned_pages(vm_account,
+ &rm->data.op_mmp_znotifier->z_mmp,
length)) {
ret = -ENOMEM;
goto err;
@@ -399,7 +402,7 @@ static int rds_message_zcopy_from_user(struct rds_message *rm, struct iov_iter *
for (i = 0; i < rm->data.op_nents; i++)
put_page(sg_page(&rm->data.op_sg[i]));
mmp = &rm->data.op_mmp_znotifier->z_mmp;
- mm_unaccount_pinned_pages(mmp);
+ mm_unaccount_pinned_pages(vm_account, mmp);
ret = -EFAULT;
goto err;
}
--
git-series 0.9.1
next prev parent reply other threads:[~2023-01-24 5:56 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-01-24 5:42 [RFC PATCH 00/19] mm: Introduce a cgroup to limit the amount of locked and pinned memory Alistair Popple
2023-01-24 5:42 ` [RFC PATCH 01/19] mm: Introduce vm_account Alistair Popple
2023-01-24 6:29 ` Christoph Hellwig
2023-01-24 14:32 ` Jason Gunthorpe
2023-01-30 11:36 ` Alistair Popple
2023-01-31 14:00 ` David Hildenbrand
2023-01-24 5:42 ` [RFC PATCH 02/19] drivers/vhost: Convert to use vm_account Alistair Popple
2023-01-24 5:55 ` Michael S. Tsirkin
2023-01-30 10:43 ` Alistair Popple
2023-01-24 14:34 ` Jason Gunthorpe
2023-01-24 5:42 ` [RFC PATCH 03/19] drivers/vdpa: Convert vdpa to use the new vm_structure Alistair Popple
2023-01-24 14:35 ` Jason Gunthorpe
2023-01-24 5:42 ` [RFC PATCH 04/19] infiniband/umem: Convert to use vm_account Alistair Popple
2023-01-24 5:42 ` [RFC PATCH 05/19] RMDA/siw: " Alistair Popple
2023-01-24 14:37 ` Jason Gunthorpe
2023-01-24 15:22 ` Bernard Metzler
2023-01-24 15:56 ` Bernard Metzler
2023-01-30 11:34 ` Alistair Popple
2023-01-30 13:27 ` Bernard Metzler
2023-01-24 5:42 ` [RFC PATCH 06/19] RDMA/usnic: convert " Alistair Popple
2023-01-24 14:41 ` Jason Gunthorpe
2023-01-30 11:10 ` Alistair Popple
2023-01-24 5:42 ` [RFC PATCH 07/19] vfio/type1: Charge pinned pages to pinned_vm instead of locked_vm Alistair Popple
2023-01-24 5:42 ` [RFC PATCH 08/19] vfio/spapr_tce: Convert accounting to pinned_vm Alistair Popple
2023-01-24 5:42 ` [RFC PATCH 09/19] io_uring: convert to use vm_account Alistair Popple
2023-01-24 14:44 ` Jason Gunthorpe
2023-01-30 11:12 ` Alistair Popple
2023-01-30 13:21 ` Jason Gunthorpe
2023-01-24 5:42 ` Alistair Popple [this message]
2023-01-24 14:51 ` [RFC PATCH 10/19] net: skb: Switch to using vm_account Jason Gunthorpe
2023-01-30 11:17 ` Alistair Popple
2023-02-06 4:36 ` Alistair Popple
2023-02-06 13:14 ` Jason Gunthorpe
2023-01-24 5:42 ` [RFC PATCH 11/19] xdp: convert to use vm_account Alistair Popple
2023-01-24 5:42 ` [RFC PATCH 12/19] kvm/book3s_64_vio: Convert account_locked_vm() to vm_account_pinned() Alistair Popple
2023-01-24 5:42 ` [RFC PATCH 13/19] fpga: dfl: afu: convert to use vm_account Alistair Popple
2023-01-24 5:42 ` [RFC PATCH 14/19] mm: Introduce a cgroup for pinned memory Alistair Popple
2023-01-27 21:44 ` Tejun Heo
2023-01-30 13:20 ` Jason Gunthorpe
2023-01-24 5:42 ` [RFC PATCH 15/19] mm/util: Extend vm_account to charge pages against the pin cgroup Alistair Popple
2023-01-24 5:42 ` [RFC PATCH 16/19] mm/util: Refactor account_locked_vm Alistair Popple
2023-01-24 5:42 ` [RFC PATCH 17/19] mm: Convert mmap and mlock to use account_locked_vm Alistair Popple
2023-01-24 5:42 ` [RFC PATCH 18/19] mm/mmap: Charge locked memory to pins cgroup Alistair Popple
2023-01-24 5:42 ` [RFC PATCH 19/19] selftests/vm: Add pins-cgroup selftest for mlock/mmap Alistair Popple
2023-01-24 18:26 ` [RFC PATCH 00/19] mm: Introduce a cgroup to limit the amount of locked and pinned memory Yosry Ahmed
2023-01-31 0:54 ` Alistair Popple
2023-01-31 5:14 ` Yosry Ahmed
2023-01-31 11:22 ` Alistair Popple
2023-01-31 19:49 ` Yosry Ahmed
2023-01-24 20:12 ` Jason Gunthorpe
2023-01-31 13:57 ` David Hildenbrand
2023-01-31 14:03 ` Jason Gunthorpe
2023-01-31 14:06 ` David Hildenbrand
2023-01-31 14:10 ` Jason Gunthorpe
2023-01-31 14:15 ` David Hildenbrand
2023-01-31 14:21 ` Jason Gunthorpe
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=9b54eef0b41b678cc5f318bd5ae0917bba5b8e21.1674538665.git-series.apopple@nvidia.com \
--to=apopple@nvidia.com \
--cc=cgroups@vger.kernel.org \
--cc=daniel@ffwll.ch \
--cc=hannes@cmpxchg.org \
--cc=jgg@nvidia.com \
--cc=jhubbard@nvidia.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-rdma@vger.kernel.org \
--cc=mkoutny@suse.com \
--cc=netdev@vger.kernel.org \
--cc=rds-devel@oss.oracle.com \
--cc=surenb@google.com \
--cc=tjmercier@google.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).