From mboxrd@z Thu Jan 1 00:00:00 1970 From: Willem de Bruijn Subject: [PATCH net-next v4 7/9] sock: ulimit on MSG_ZEROCOPY pages Date: Thu, 3 Aug 2017 16:29:43 -0400 Message-ID: <20170803202945.70750-8-willemdebruijn.kernel@gmail.com> References: <20170803202945.70750-1-willemdebruijn.kernel@gmail.com> Return-path: In-Reply-To: <20170803202945.70750-1-willemdebruijn.kernel@gmail.com> Sender: netdev-owner@vger.kernel.org To: netdev@vger.kernel.org Cc: davem@davemloft.net, linux-api@vger.kernel.org, Willem de Bruijn List-Id: linux-api@vger.kernel.org From: Willem de Bruijn Bound the number of pages that a user may pin. Follow the lead of perf tools to maintain a per-user bound on memory locked pages commit 789f90fcf6b0 ("perf_counter: per user mlock gift") Signed-off-by: Willem de Bruijn --- include/linux/sched/user.h | 3 ++- include/linux/skbuff.h | 5 +++++ net/core/skbuff.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 55 insertions(+), 1 deletion(-) diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index 5d5415e129d4..3c07e4135127 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -36,7 +36,8 @@ struct user_struct { struct hlist_node uidhash_node; kuid_t uid; -#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) +#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \ + defined(CONFIG_NET) atomic_long_t locked_vm; #endif }; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f5bdd93a87da..8c0708d2e5e6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -457,6 +457,11 @@ struct ubuf_info { }; }; atomic_t refcnt; + + struct mmpin { + struct user_struct *user; + unsigned int num_pg; + } mmp; }; #define skb_uarg(SKB) ((struct ubuf_info *)(skb_shinfo(SKB)->destructor_arg)) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index dcee0f64f1fa..42b62c716a33 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -897,6 +897,44 @@ struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src) } EXPORT_SYMBOL_GPL(skb_morph); +static int mm_account_pinned_pages(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; + + num_pg = (size >> PAGE_SHIFT) + 2; /* worst case */ + max_pg = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + user = mmp->user ? : current_user(); + + do { + old_pg = atomic_long_read(&user->locked_vm); + new_pg = old_pg + num_pg; + if (new_pg > max_pg) + return -ENOBUFS; + } while (atomic_long_cmpxchg(&user->locked_vm, old_pg, new_pg) != + old_pg); + + if (!mmp->user) { + mmp->user = get_uid(user); + mmp->num_pg = num_pg; + } else { + mmp->num_pg += num_pg; + } + + return 0; +} + +static void mm_unaccount_pinned_pages(struct mmpin *mmp) +{ + if (mmp->user) { + atomic_long_sub(mmp->num_pg, &mmp->user->locked_vm); + free_uid(mmp->user); + } +} + struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size) { struct ubuf_info *uarg; @@ -913,6 +951,12 @@ struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size) BUILD_BUG_ON(sizeof(*uarg) > sizeof(skb->cb)); uarg = (void *)skb->cb; + uarg->mmp.user = NULL; + + if (mm_account_pinned_pages(&uarg->mmp, size)) { + kfree_skb(skb); + return NULL; + } uarg->callback = sock_zerocopy_callback; uarg->id = ((u32)atomic_inc_return(&sk->sk_zckey)) - 1; @@ -956,6 +1000,8 @@ struct ubuf_info *sock_zerocopy_realloc(struct sock *sk, size_t size, next = (u32)atomic_read(&sk->sk_zckey); if ((u32)(uarg->id + uarg->len) == next) { + if (mm_account_pinned_pages(&uarg->mmp, size)) + return NULL; uarg->len++; uarg->bytelen = bytelen; atomic_set(&sk->sk_zckey, ++next); @@ -1038,6 +1084,8 @@ EXPORT_SYMBOL_GPL(sock_zerocopy_callback); void sock_zerocopy_put(struct ubuf_info *uarg) { if (uarg && atomic_dec_and_test(&uarg->refcnt)) { + mm_unaccount_pinned_pages(&uarg->mmp); + if (uarg->callback) uarg->callback(uarg, uarg->zerocopy); else -- 2.14.0.rc1.383.gd1ce394fe2-goog