From: Chuck Lever chuck.lever@oracle.com
Backport the set of upstream patches that cap the number of concurrent background NFSv4.2 COPY operations.
Chuck Lever (4): NFSD: Async COPY result needs to return a write verifier NFSD: Limit the number of concurrent async COPY operations NFSD: Initialize struct nfsd4_copy earlier NFSD: Never decrement pending_async_copies on error
Dai Ngo (1): NFSD: initialize copy->cp_clp early in nfsd4_copy for use by trace point
fs/nfsd/netns.h | 1 + fs/nfsd/nfs4proc.c | 36 +++++++++++++++++------------------- fs/nfsd/nfs4state.c | 1 + fs/nfsd/xdr4.h | 1 + 4 files changed, 20 insertions(+), 19 deletions(-)
From: Dai Ngo dai.ngo@oracle.com
[ Upstream commit 15d1975b7279693d6f09398e0e2e31aca2310275 ]
Prepare for adding server copy trace points.
Signed-off-by: Dai Ngo dai.ngo@oracle.com Tested-by: Chen Hanxiao chenhx.fnst@fujitsu.com Stable-dep-of: 9ed666eba4e0 ("NFSD: Async COPY result needs to return a write verifier") Signed-off-by: Chuck Lever chuck.lever@oracle.com --- fs/nfsd/nfs4proc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 11dcf3debb1d..2b1fcf5b6bf8 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1769,6 +1769,7 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __be32 status; struct nfsd4_copy *async_copy = NULL;
+ copy->cp_clp = cstate->clp; if (nfsd4_ssc_is_inter(copy)) { if (!inter_copy_offload_enable || nfsd4_copy_is_sync(copy)) { status = nfserr_notsupp; @@ -1783,7 +1784,6 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return status; }
- copy->cp_clp = cstate->clp; memcpy(©->fh, &cstate->current_fh.fh_handle, sizeof(struct knfsd_fh)); if (nfsd4_copy_is_async(copy)) {
From: Chuck Lever chuck.lever@oracle.com
[ Upstream commit 9ed666eba4e0a2bb8ffaa3739d830b64d4f2aaad ]
Currently, when NFSD handles an asynchronous COPY, it returns a zero write verifier, relying on the subsequent CB_OFFLOAD callback to pass the write verifier and a stable_how4 value to the client.
However, if the CB_OFFLOAD never arrives at the client (for example, if a network partition occurs just as the server sends the CB_OFFLOAD operation), the client will never receive this verifier. Thus, if the client sends a follow-up COMMIT, there is no way for the client to assess the COMMIT result.
The usual recovery for a missing CB_OFFLOAD is for the client to send an OFFLOAD_STATUS operation, but that operation does not carry a write verifier in its result. Neither does it carry a stable_how4 value, so the client /must/ send a COMMIT in this case -- which will always fail because currently there's still no write verifier in the COPY result.
Thus the server needs to return a normal write verifier in its COPY result even if the COPY operation is to be performed asynchronously.
If the server recognizes the callback stateid in subsequent OFFLOAD_STATUS operations, then obviously it has not restarted, and the write verifier the client received in the COPY result is still valid and can be used to assess a COMMIT of the copied data, if one is needed.
Reviewed-by: Jeff Layton jlayton@kernel.org [ cel: adjusted to apply to origin/linux-5.15.y ] Signed-off-by: Chuck Lever chuck.lever@oracle.com --- fs/nfsd/nfs4proc.c | 25 +++++++++---------------- 1 file changed, 9 insertions(+), 16 deletions(-)
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 2b1fcf5b6bf8..08d90e0e8fae 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -718,15 +718,6 @@ nfsd4_access(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, &access->ac_supported); }
-static void gen_boot_verifier(nfs4_verifier *verifier, struct net *net) -{ - __be32 *verf = (__be32 *)verifier->data; - - BUILD_BUG_ON(2*sizeof(*verf) != sizeof(verifier->data)); - - nfsd_copy_write_verifier(verf, net_generic(net, nfsd_net_id)); -} - static __be32 nfsd4_commit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) @@ -1594,7 +1585,6 @@ static void nfsd4_init_copy_res(struct nfsd4_copy *copy, bool sync) test_bit(NFSD4_COPY_F_COMMITTED, ©->cp_flags) ? NFS_FILE_SYNC : NFS_UNSTABLE; nfsd4_copy_set_sync(copy, sync); - gen_boot_verifier(©->cp_res.wr_verifier, copy->cp_clp->net); }
static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy, @@ -1765,9 +1755,14 @@ static __be32 nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { - struct nfsd4_copy *copy = &u->copy; - __be32 status; + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); struct nfsd4_copy *async_copy = NULL; + struct nfsd4_copy *copy = &u->copy; + struct nfsd42_write_res *result; + __be32 status; + + result = ©->cp_res; + nfsd_copy_write_verifier((__be32 *)&result->wr_verifier.data, nn);
copy->cp_clp = cstate->clp; if (nfsd4_ssc_is_inter(copy)) { @@ -1787,8 +1782,6 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, memcpy(©->fh, &cstate->current_fh.fh_handle, sizeof(struct knfsd_fh)); if (nfsd4_copy_is_async(copy)) { - struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); - status = nfserrno(-ENOMEM); async_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL); if (!async_copy) @@ -1800,8 +1793,8 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out_err; if (!nfs4_init_copy_state(nn, copy)) goto out_err; - memcpy(©->cp_res.cb_stateid, ©->cp_stateid.cs_stid, - sizeof(copy->cp_res.cb_stateid)); + memcpy(&result->cb_stateid, ©->cp_stateid.cs_stid, + sizeof(result->cb_stateid)); dup_copy_fields(copy, async_copy); async_copy->copy_task = kthread_create(nfsd4_do_async_copy, async_copy, "%s", "copy thread");
From: Chuck Lever chuck.lever@oracle.com
[ Upstream commit aadc3bbea163b6caaaebfdd2b6c4667fbc726752 ]
Nothing appears to limit the number of concurrent async COPY operations that clients can start. In addition, AFAICT each async COPY can copy an unlimited number of 4MB chunks, so can run for a long time. Thus IMO async COPY can become a DoS vector.
Add a restriction mechanism that bounds the number of concurrent background COPY operations. Start simple and try to be fair -- this patch implements a per-namespace limit.
An async COPY request that occurs while this limit is exceeded gets NFS4ERR_DELAY. The requesting client can choose to send the request again after a delay or fall back to a traditional read/write style copy.
If there is need to make the mechanism more sophisticated, we can visit that in future patches.
Cc: stable@vger.kernel.org Reviewed-by: Jeff Layton jlayton@kernel.org Link: https://nvd.nist.gov/vuln/detail/CVE-2024-49974 Signed-off-by: Chuck Lever chuck.lever@oracle.com --- fs/nfsd/netns.h | 1 + fs/nfsd/nfs4proc.c | 11 +++++++++-- fs/nfsd/nfs4state.c | 1 + fs/nfsd/xdr4.h | 1 + 4 files changed, 12 insertions(+), 2 deletions(-)
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 548422b24a7d..41c750f34473 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -152,6 +152,7 @@ struct nfsd_net { u32 s2s_cp_cl_id; struct idr s2s_cp_stateids; spinlock_t s2s_cp_lock; + atomic_t pending_async_copies;
/* * Version information diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 08d90e0e8fae..54f43501fed9 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1244,6 +1244,7 @@ static void nfs4_put_copy(struct nfsd4_copy *copy) { if (!refcount_dec_and_test(©->refcount)) return; + atomic_dec(©->cp_nn->pending_async_copies); kfree(copy->cp_src); kfree(copy); } @@ -1782,10 +1783,16 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, memcpy(©->fh, &cstate->current_fh.fh_handle, sizeof(struct knfsd_fh)); if (nfsd4_copy_is_async(copy)) { - status = nfserrno(-ENOMEM); async_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL); if (!async_copy) goto out_err; + async_copy->cp_nn = nn; + /* Arbitrary cap on number of pending async copy operations */ + if (atomic_inc_return(&nn->pending_async_copies) > + (int)rqstp->rq_pool->sp_nrthreads) { + atomic_dec(&nn->pending_async_copies); + goto out_err; + } INIT_LIST_HEAD(&async_copy->copies); refcount_set(&async_copy->refcount, 1); async_copy->cp_src = kmalloc(sizeof(*async_copy->cp_src), GFP_KERNEL); @@ -1824,7 +1831,7 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, } if (async_copy) cleanup_async_copy(async_copy); - status = nfserrno(-ENOMEM); + status = nfserr_jukebox; goto out; }
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 5ab3045c649f..a7016f738647 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -8079,6 +8079,7 @@ static int nfs4_state_create_net(struct net *net) spin_lock_init(&nn->client_lock); spin_lock_init(&nn->s2s_cp_lock); idr_init(&nn->s2s_cp_stateids); + atomic_set(&nn->pending_async_copies, 0);
spin_lock_init(&nn->blocked_locks_lock); INIT_LIST_HEAD(&nn->blocked_locks_lru); diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 510978e602da..9bd1ade6ba54 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -574,6 +574,7 @@ struct nfsd4_copy { struct nfsd4_ssc_umount_item *ss_nsui; struct nfs_fh c_fh; nfs4_stateid stateid; + struct nfsd_net *cp_nn; };
static inline void nfsd4_copy_set_sync(struct nfsd4_copy *copy, bool sync)
From: Chuck Lever chuck.lever@oracle.com
[ Upstream commit 63fab04cbd0f96191b6e5beedc3b643b01c15889 ]
Ensure the refcount and async_copies fields are initialized early. cleanup_async_copy() will reference these fields if an error occurs in nfsd4_copy(). If they are not correctly initialized, at the very least, a refcount underflow occurs.
Reported-by: Olga Kornievskaia okorniev@redhat.com Fixes: aadc3bbea163 ("NFSD: Limit the number of concurrent async COPY operations") Reviewed-by: Jeff Layton jlayton@kernel.org Tested-by: Olga Kornievskaia okorniev@redhat.com Signed-off-by: Chuck Lever chuck.lever@oracle.com --- fs/nfsd/nfs4proc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 54f43501fed9..6267a41092ae 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1787,14 +1787,14 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (!async_copy) goto out_err; async_copy->cp_nn = nn; + INIT_LIST_HEAD(&async_copy->copies); + refcount_set(&async_copy->refcount, 1); /* Arbitrary cap on number of pending async copy operations */ if (atomic_inc_return(&nn->pending_async_copies) > (int)rqstp->rq_pool->sp_nrthreads) { atomic_dec(&nn->pending_async_copies); goto out_err; } - INIT_LIST_HEAD(&async_copy->copies); - refcount_set(&async_copy->refcount, 1); async_copy->cp_src = kmalloc(sizeof(*async_copy->cp_src), GFP_KERNEL); if (!async_copy->cp_src) goto out_err;
From: Chuck Lever chuck.lever@oracle.com
[ Upstream commit 8286f8b622990194207df9ab852e0f87c60d35e9 ]
The error flow in nfsd4_copy() calls cleanup_async_copy(), which already decrements nn->pending_async_copies.
Reported-by: Olga Kornievskaia okorniev@redhat.com Fixes: aadc3bbea163 ("NFSD: Limit the number of concurrent async COPY operations") Signed-off-by: Chuck Lever chuck.lever@oracle.com --- fs/nfsd/nfs4proc.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 6267a41092ae..0b698e25826f 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1791,10 +1791,8 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, refcount_set(&async_copy->refcount, 1); /* Arbitrary cap on number of pending async copy operations */ if (atomic_inc_return(&nn->pending_async_copies) > - (int)rqstp->rq_pool->sp_nrthreads) { - atomic_dec(&nn->pending_async_copies); + (int)rqstp->rq_pool->sp_nrthreads) goto out_err; - } async_copy->cp_src = kmalloc(sizeof(*async_copy->cp_src), GFP_KERNEL); if (!async_copy->cp_src) goto out_err;
linux-stable-mirror@lists.linaro.org
-
cel＠kernel.org