After the listener svc_sock be freed, and before invoking svc_tcp_accept()
for the established child sock, there is a window that the newsock
retaining a freed listener svc_sock in sk_user_data which cloning from
parent. In the race windows if data is received on the newsock, we will
observe use-after-free report in svc_tcp_listen_data_ready().
Reproduce by two tasks:
1. while :; do rpc.nfsd 0 ; rpc.nfsd; done
2. while :; do echo "" | ncat -4 127.0.0.1 2049 ; done
KASAN report:
==================================================================
BUG: KASAN: slab-use-after-free in svc_tcp_listen_data_ready+0x1cf/0x1f0 [sunrpc]
Read of size 8 at addr ffff888139d96228 by task nc/102553
CPU: 7 PID: 102553 Comm: nc Not tainted 6.3.0+ #18
Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 11/12/2020
Call Trace:
<IRQ>
dump_stack_lvl+0x33/0x50
print_address_description.constprop.0+0x27/0x310
print_report+0x3e/0x70
kasan_report+0xae/0xe0
svc_tcp_listen_data_ready+0x1cf/0x1f0 [sunrpc]
tcp_data_queue+0x9f4/0x20e0
tcp_rcv_established+0x666/0x1f60
tcp_v4_do_rcv+0x51c/0x850
tcp_v4_rcv+0x23fc/0x2e80
ip_protocol_deliver_rcu+0x62/0x300
ip_local_deliver_finish+0x267/0x350
ip_local_deliver+0x18b/0x2d0
ip_rcv+0x2fb/0x370
__netif_receive_skb_one_core+0x166/0x1b0
process_backlog+0x24c/0x5e0
__napi_poll+0xa2/0x500
net_rx_action+0x854/0xc90
__do_softirq+0x1bb/0x5de
do_softirq+0xcb/0x100
</IRQ>
<TASK>
...
</TASK>
Allocated by task 102371:
kasan_save_stack+0x1e/0x40
kasan_set_track+0x21/0x30
__kasan_kmalloc+0x7b/0x90
svc_setup_socket+0x52/0x4f0 [sunrpc]
svc_addsock+0x20d/0x400 [sunrpc]
__write_ports_addfd+0x209/0x390 [nfsd]
write_ports+0x239/0x2c0 [nfsd]
nfsctl_transaction_write+0xac/0x110 [nfsd]
vfs_write+0x1c3/0xae0
ksys_write+0xed/0x1c0
do_syscall_64+0x38/0x90
entry_SYSCALL_64_after_hwframe+0x72/0xdc
Freed by task 102551:
kasan_save_stack+0x1e/0x40
kasan_set_track+0x21/0x30
kasan_save_free_info+0x2a/0x50
__kasan_slab_free+0x106/0x190
__kmem_cache_free+0x133/0x270
svc_xprt_free+0x1e2/0x350 [sunrpc]
svc_xprt_destroy_all+0x25a/0x440 [sunrpc]
nfsd_put+0x125/0x240 [nfsd]
nfsd_svc+0x2cb/0x3c0 [nfsd]
write_threads+0x1ac/0x2a0 [nfsd]
nfsctl_transaction_write+0xac/0x110 [nfsd]
vfs_write+0x1c3/0xae0
ksys_write+0xed/0x1c0
do_syscall_64+0x38/0x90
entry_SYSCALL_64_after_hwframe+0x72/0xdc
Fix the UAF by simply doing nothing in svc_tcp_listen_data_ready()
if state != TCP_LISTEN, that will avoid dereferencing svsk for all
child socket.
Link: https://lore.kernel.org/lkml/20230507091131.23540-1-dinghui@sangfor.com.cn/
Fixes: fa9251afc33c ("SUNRPC: Call the default socket callbacks instead of open coding")
Signed-off-by: Ding Hui <dinghui(a)sangfor.com.cn>
Cc: <stable(a)vger.kernel.org>
---
net/sunrpc/svcsock.c | 23 +++++++++++------------
1 file changed, 11 insertions(+), 12 deletions(-)
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index a51c9b989d58..9aca6e1e78e4 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -825,12 +825,6 @@ static void svc_tcp_listen_data_ready(struct sock *sk)
trace_sk_data_ready(sk);
- if (svsk) {
- /* Refer to svc_setup_socket() for details. */
- rmb();
- svsk->sk_odata(sk);
- }
-
/*
* This callback may called twice when a new connection
* is established as a child socket inherits everything
@@ -839,13 +833,18 @@ static void svc_tcp_listen_data_ready(struct sock *sk)
* when one of child sockets become ESTABLISHED.
* 2) data_ready method of the child socket may be called
* when it receives data before the socket is accepted.
- * In case of 2, we should ignore it silently.
+ * In case of 2, we should ignore it silently and DO NOT
+ * dereference svsk.
*/
- if (sk->sk_state == TCP_LISTEN) {
- if (svsk) {
- set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
- svc_xprt_enqueue(&svsk->sk_xprt);
- }
+ if (sk->sk_state != TCP_LISTEN)
+ return;
+
+ if (svsk) {
+ /* Refer to svc_setup_socket() for details. */
+ rmb();
+ svsk->sk_odata(sk);
+ set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);
+ svc_xprt_enqueue(&svsk->sk_xprt);
}
}
--
2.17.1
Implementation Note at the end of PCIe r6.0.1 sec 7.5.3.7 recommends
handling LTSSM race to ensure link retraining acquires correct
parameters from the LNKCTL register. According to the implementation
note, LTSSM might transition into Recovery or Configuration state
independently of the driver requesting it, and if retraining due to
such an event is still ongoing, the value written into the LNKCTL
register might not be considered by the link retraining.
Ensure link training bit is clear before toggling link retraining bit
to meet the requirements of the Implementation Note.
Fixes: 7d715a6c1ae5 ("PCI: add PCI Express ASPM support")
Suggested-by: Lukas Wunner <lukas(a)wunner.de>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen(a)linux.intel.com>
Reviewed-by: Lukas Wunner <lukas(a)wunner.de>
Cc: stable(a)vger.kernel.org
---
drivers/pci/pcie/aspm.c | 37 +++++++++++++++++++++++++++----------
1 file changed, 27 insertions(+), 10 deletions(-)
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index 66d7514ca111..dde1ef13d0d1 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -193,12 +193,37 @@ static void pcie_clkpm_cap_init(struct pcie_link_state *link, int blacklist)
link->clkpm_disable = blacklist ? 1 : 0;
}
+static bool pcie_wait_for_retrain(struct pci_dev *pdev)
+{
+ unsigned long end_jiffies;
+ u16 reg16;
+
+ /* Wait for link training end. Break out after waiting for timeout */
+ end_jiffies = jiffies + LINK_RETRAIN_TIMEOUT;
+ do {
+ pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, ®16);
+ if (!(reg16 & PCI_EXP_LNKSTA_LT))
+ break;
+ msleep(1);
+ } while (time_before(jiffies, end_jiffies));
+
+ return !(reg16 & PCI_EXP_LNKSTA_LT);
+}
+
static bool pcie_retrain_link(struct pcie_link_state *link)
{
struct pci_dev *parent = link->pdev;
- unsigned long end_jiffies;
u16 reg16;
+ /*
+ * Ensure the updated LNKCTL parameters are used during link
+ * training by checking that there is no ongoing link training to
+ * avoid LTSSM race as recommended in Implementation Note at the end
+ * of PCIe r6.0.1 sec 7.5.3.7.
+ */
+ if (!pcie_wait_for_retrain(parent))
+ return false;
+
pcie_capability_read_word(parent, PCI_EXP_LNKCTL, ®16);
reg16 |= PCI_EXP_LNKCTL_RL;
pcie_capability_write_word(parent, PCI_EXP_LNKCTL, reg16);
@@ -212,15 +237,7 @@ static bool pcie_retrain_link(struct pcie_link_state *link)
pcie_capability_write_word(parent, PCI_EXP_LNKCTL, reg16);
}
- /* Wait for link training end. Break out after waiting for timeout */
- end_jiffies = jiffies + LINK_RETRAIN_TIMEOUT;
- do {
- pcie_capability_read_word(parent, PCI_EXP_LNKSTA, ®16);
- if (!(reg16 & PCI_EXP_LNKSTA_LT))
- break;
- msleep(1);
- } while (time_before(jiffies, end_jiffies));
- return !(reg16 & PCI_EXP_LNKSTA_LT);
+ return pcie_wait_for_retrain(parent);
}
/*
--
2.30.2
Dear,
Please grant me the permission to share important discussion with you.
I am looking forward to hearing from you at your earliest convenience.
Best Regards.
Mrs. Nina Coulibaly
Dzień dobry,
chciałbym poinformować Państwa o możliwości pozyskania nowych zleceń ze strony www.
Widzimy zainteresowanie potencjalnych Klientów Państwa firmą, dlatego chętnie pomożemy Państwu dotrzeć z ofertą do większego grona odbiorców poprzez efektywne metody pozycjonowania strony w Google.
Czy mógłbym liczyć na kontakt zwrotny?
Pozdrawiam serdecznie,
Wiktor Nurek
Currently, due to the sequential use of min_t() and clamp_t() macros,
in cdc_ncm_check_tx_max(), if dwNtbOutMaxSize is not set, the logic
sets tx_max to 0. This is then used to allocate the data area of the
SKB requested later in cdc_ncm_fill_tx_frame().
This does not cause an issue presently because when memory is
allocated during initialisation phase of SKB creation, more memory
(512b) is allocated than is required for the SKB headers alone (320b),
leaving some space (512b - 320b = 192b) for CDC data (172b).
However, if more elements (for example 3 x u64 = [24b]) were added to
one of the SKB header structs, say 'struct skb_shared_info',
increasing its original size (320b [320b aligned]) to something larger
(344b [384b aligned]), then suddenly the CDC data (172b) no longer
fits in the spare SKB data area (512b - 384b = 128b).
Consequently the SKB bounds checking semantics fails and panics:
skbuff: skb_over_panic: text:ffffffff830a5b5f len:184 put:172 \
head:ffff888119227c00 data:ffff888119227c00 tail:0xb8 end:0x80 dev:<NULL>
------------[ cut here ]------------
kernel BUG at net/core/skbuff.c:110!
RIP: 0010:skb_panic+0x14f/0x160 net/core/skbuff.c:106
<snip>
Call Trace:
<IRQ>
skb_over_panic+0x2c/0x30 net/core/skbuff.c:115
skb_put+0x205/0x210 net/core/skbuff.c:1877
skb_put_zero include/linux/skbuff.h:2270 [inline]
cdc_ncm_ndp16 drivers/net/usb/cdc_ncm.c:1116 [inline]
cdc_ncm_fill_tx_frame+0x127f/0x3d50 drivers/net/usb/cdc_ncm.c:1293
cdc_ncm_tx_fixup+0x98/0xf0 drivers/net/usb/cdc_ncm.c:1514
By overriding the max value with the default CDC_NCM_NTB_MAX_SIZE_TX
when not offered through the system provided params, we ensure enough
data space is allocated to handle the CDC data, meaning no crash will
occur.
Cc: stable(a)vger.kernel.org
Cc: Oliver Neukum <oliver(a)neukum.org>
Cc: "David S. Miller" <davem(a)davemloft.net>
Cc: Jakub Kicinski <kuba(a)kernel.org>
Cc: linux-usb(a)vger.kernel.org
Cc: netdev(a)vger.kernel.org
Cc: linux-kernel(a)vger.kernel.org
Fixes: 289507d3364f9 ("net: cdc_ncm: use sysfs for rx/tx aggregation tuning")
Signed-off-by: Lee Jones <lee.jones(a)linaro.org>
---
drivers/net/usb/cdc_ncm.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 24753a4da7e60..e303b522efb50 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -181,6 +181,8 @@ static u32 cdc_ncm_check_tx_max(struct usbnet *dev, u32 new_tx)
min = ctx->max_datagram_size + ctx->max_ndp_size + sizeof(struct usb_cdc_ncm_nth32);
max = min_t(u32, CDC_NCM_NTB_MAX_SIZE_TX, le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize));
+ if (max == 0)
+ max = CDC_NCM_NTB_MAX_SIZE_TX; /* dwNtbOutMaxSize not set */
/* some devices set dwNtbOutMaxSize too low for the above default */
min = min(min, max);
--
2.34.0.384.gca35af8252-goog
From: Xiubo Li <xiubli(a)redhat.com>
When the MClientSnap reqeust's op is not CEPH_SNAP_OP_SPLIT the
request may still contain a list of 'split_realms', and we need
to skip it anyway. Or it will be parsed as a corrupt snaptrace.
Cc: stable(a)vger.kernel.org
Cc: Frank Schilder <frans(a)dtu.dk>
Reported-by: Frank Schilder <frans(a)dtu.dk>
URL: https://tracker.ceph.com/issues/61200
Signed-off-by: Xiubo Li <xiubli(a)redhat.com>
---
fs/ceph/snap.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 0e59e95a96d9..d95dfe16b624 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -1114,6 +1114,9 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc,
continue;
adjust_snap_realm_parent(mdsc, child, realm->ino);
}
+ } else {
+ p += sizeof(u64) * num_split_inos;
+ p += sizeof(u64) * num_split_realms;
}
/*
--
2.40.1