* [PATCH net-next 01/24] sctp: introduce SCTP_FUTURE/CURRENT/ALL_ASSOC
From: Xin Long @ 2019-01-28 7:08 UTC (permalink / raw)
To: network dev, linux-sctp; +Cc: Marcelo Ricardo Leitner, Neil Horman, davem
In-Reply-To: <cover.1548659198.git.lucien.xin@gmail.com>
This patch is to add 3 constants SCTP_FUTURE_ASSOC,
SCTP_CURRENT_ASSOC and SCTP_ALL_ASSOC for reserved
assoc_ids, as defined in rfc6458#section-7.2.
And add the process for them when doing lookup and
inserting in sctp_id2assoc and sctp_assoc_set_id.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
---
include/uapi/linux/sctp.h | 4 ++++
net/sctp/associola.c | 7 +++++--
net/sctp/socket.c | 2 +-
3 files changed, 10 insertions(+), 3 deletions(-)
diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index d584073..b8f2c4d 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -59,6 +59,10 @@
typedef __s32 sctp_assoc_t;
+#define SCTP_FUTURE_ASSOC 0
+#define SCTP_CURRENT_ASSOC 1
+#define SCTP_ALL_ASSOC 2
+
/* The following symbols come from the Sockets API Extensions for
* SCTP <draft-ietf-tsvwg-sctpsocket-07.txt>.
*/
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 201c888..b99f163 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1651,8 +1651,11 @@ int sctp_assoc_set_id(struct sctp_association *asoc, gfp_t gfp)
if (preload)
idr_preload(gfp);
spin_lock_bh(&sctp_assocs_id_lock);
- /* 0 is not a valid assoc_id, must be >= 1 */
- ret = idr_alloc_cyclic(&sctp_assocs_id, asoc, 1, 0, GFP_NOWAIT);
+ /* 0, 1, 2 are used as SCTP_FUTURE_ASSOC, SCTP_CURRENT_ASSOC and
+ * SCTP_ALL_ASSOC, so an available id must be > SCTP_ALL_ASSOC.
+ */
+ ret = idr_alloc_cyclic(&sctp_assocs_id, asoc, SCTP_ALL_ASSOC + 1, 0,
+ GFP_NOWAIT);
spin_unlock_bh(&sctp_assocs_id_lock);
if (preload)
idr_preload_end();
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index f93c3cf..a52d132 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -248,7 +248,7 @@ struct sctp_association *sctp_id2assoc(struct sock *sk, sctp_assoc_t id)
}
/* Otherwise this is a UDP-style socket. */
- if (!id || (id == (sctp_assoc_t)-1))
+ if (id <= SCTP_ALL_ASSOC)
return NULL;
spin_lock_bh(&sctp_assocs_id_lock);
--
2.1.0
^ permalink raw reply related
* [PATCH net-next 00/24] sctp: support SCTP_FUTURE/CURRENT/ALL_ASSOC
From: Xin Long @ 2019-01-28 7:08 UTC (permalink / raw)
To: network dev, linux-sctp; +Cc: Marcelo Ricardo Leitner, Neil Horman, davem
This patchset adds the support for 3 assoc_id constants: SCTP_FUTURE_ASSOC
SCTP_CURRENT_ASSOC, SCTP_ALL_ASSOC, described in rfc6458#section-7.2:
All socket options set on a one-to-one style listening socket also
apply to all future accepted sockets. For one-to-many style sockets,
often a socket option will pass a structure that includes an assoc_id
field. This field can be filled with the association identifier of a
particular association and unless otherwise specified can be filled
with one of the following constants:
SCTP_FUTURE_ASSOC: Specifies that only future associations created
after this socket option will be affected by this call.
SCTP_CURRENT_ASSOC: Specifies that only currently existing
associations will be affected by this call, and future
associations will still receive the previous default value.
SCTP_ALL_ASSOC: Specifies that all current and future associations
will be affected by this call.
The functions for many other sockopts that use assoc_id also need to be
updated accordingly.
Xin Long (24):
sctp: introduce SCTP_FUTURE/CURRENT/ALL_ASSOC
sctp: use SCTP_FUTURE_ASSOC for SCTP_PEER_ADDR_PARAMS sockopt
sctp: use SCTP_FUTURE_ASSOC for SCTP_RTOINFO sockopt
sctp: use SCTP_FUTURE_ASSOC for SCTP_ASSOCINFO sockopt
sctp: use SCTP_FUTURE_ASSOC for SCTP_MAXSEG sockopt
sctp: use SCTP_FUTURE_ASSOC for SCTP_LOCAL_AUTH_CHUNKS sockopt
sctp: add SCTP_FUTURE_ASSOC for SCTP_PEER_ADDR_THLDS sockopt
sctp: use SCTP_FUTURE_ASSOC for SCTP_PR_SUPPORTED sockopt
sctp: use SCTP_FUTURE_ASSOC for SCTP_RECONFIG_SUPPORTED sockopt
sctp: use SCTP_FUTURE_ASSOC for SCTP_INTERLEAVING_SUPPORTED sockopt
sctp: add SCTP_CURRENT_ASSOC for SCTP_STREAM_SCHEDULER_VALUE sockopt
sctp: use SCTP_FUTURE_ASSOC and add SCTP_CURRENT_ASSOC for
SCTP_DELAYED_SACK sockopt
sctp: use SCTP_FUTURE_ASSOC and add SCTP_CURRENT_ASSOC for
SCTP_DEFAULT_SEND_PARAM sockopt
sctp: use SCTP_FUTURE_ASSOC and add SCTP_CURRENT_ASSOC for
SCTP_DEFAULT_SNDINFO sockopt
sctp: use SCTP_FUTURE_ASSOC and add SCTP_CURRENT_ASSOC for
SCTP_CONTEXT sockopt
sctp: use SCTP_FUTURE_ASSOC and add SCTP_CURRENT_ASSOC for
SCTP_MAX_BURST sockopt
sctp: use SCTP_FUTURE_ASSOC and add SCTP_CURRENT_ASSOC for
SCTP_AUTH_KEY sockopt
sctp: use SCTP_FUTURE_ASSOC and add SCTP_CURRENT_ASSOC for
SCTP_AUTH_ACTIVE_KEY sockopt
sctp: use SCTP_FUTURE_ASSOC and add SCTP_CURRENT_ASSOC for
SCTP_AUTH_DELETE_KEY sockopt
sctp: use SCTP_FUTURE_ASSOC and add SCTP_CURRENT_ASSOC for
SCTP_AUTH_DEACTIVATE_KEY sockopt
sctp: use SCTP_FUTURE_ASSOC and add SCTP_CURRENT_ASSOC for
SCTP_DEFAULT_PRINFO sockopt
sctp: use SCTP_FUTURE_ASSOC and add SCTP_CURRENT_ASSOC for
SCTP_ENABLE_STREAM_RESET sockopt
sctp: use SCTP_FUTURE_ASSOC and add SCTP_CURRENT_ASSOC for SCTP_EVENT
sockopt
sctp: add SCTP_FUTURE_ASOC and SCTP_CURRENT_ASSOC for
SCTP_STREAM_SCHEDULER sockopt
include/net/sctp/structs.h | 4 +
include/uapi/linux/sctp.h | 4 +
net/sctp/associola.c | 9 +-
net/sctp/outqueue.c | 2 +-
net/sctp/socket.c | 773 ++++++++++++++++++++++++++++++---------------
5 files changed, 525 insertions(+), 267 deletions(-)
--
2.1.0
^ permalink raw reply
* Re: [PATCH] : net : hso : unregister_netdev only if it has been registered
From: Greg KH @ 2019-01-28 7:07 UTC (permalink / raw)
To: Yavuz, Tuba; +Cc: netdev@vger.kernel.org
In-Reply-To: <1548620073263.88642@ece.ufl.edu>
On Sun, Jan 27, 2019 at 08:14:33PM +0000, Yavuz, Tuba wrote:
>
> On an error path inside the hso_create_net_device function of the hso
> driver, hso_free_net_device gets called. This causes potentially a
> negative reference count in the net device if register_netdev has not
> been called yet as hso_free_net_device calls unregister_netdev
> regardless. I think the driver should distinguish these cases and call
> unregister_netdev only if register_netdev has been called.
>
>
> Reported-by: Tuba Yavuz <tuba@ece.ufl.edu>
> Signed-off-by: Tuba Yavuz <tuba@ece.ufl.edu>
No need for a reported-by if you wrote the patch and sign off on it.
> ---
>
>
> --- drivers/net/usb/hso.c.orig 2019-01-27 14:45:58.232683119 -0500
> +++ drivers/net/usb/hso.c 2019-01-27 14:47:43.592683629 -0500
Your patches need to be one more level deep. Please see the
documentatino for how to do this, git should also create this
automatically correctly for you.
thanks,
greg k-h
^ permalink raw reply
* [PATCH net] vhost: fix OOB in get_rx_bufs()
From: Jason Wang @ 2019-01-28 7:05 UTC (permalink / raw)
To: mst, jasowang, stefanha; +Cc: kvm, virtualization, netdev, linux-kernel
After batched used ring updating was introduced in commit e2b3b35eb989
("vhost_net: batch used ring update in rx"). We tend to batch heads in
vq->heads for more than one packet. But the quota passed to
get_rx_bufs() was not correctly limited, which can result a OOB write
in vq->heads.
headcount = get_rx_bufs(vq, vq->heads + nvq->done_idx,
vhost_len, &in, vq_log, &log,
likely(mergeable) ? UIO_MAXIOV : 1);
UIO_MAXIOV was still used which is wrong since we could have batched
used in vq->heads, this will cause OOB if the next buffer needs more
than 960 (1024 (UIO_MAXIOV) - 64 (VHOST_NET_BATCH)) heads after we've
batched 64 (VHOST_NET_BATCH) heads:
=============================================================================
BUG kmalloc-8k (Tainted: G B ): Redzone overwritten
-----------------------------------------------------------------------------
INFO: 0x00000000fd93b7a2-0x00000000f0713384. First byte 0xa9 instead of 0xcc
INFO: Allocated in alloc_pd+0x22/0x60 age=3933677 cpu=2 pid=2674
kmem_cache_alloc_trace+0xbb/0x140
alloc_pd+0x22/0x60
gen8_ppgtt_create+0x11d/0x5f0
i915_ppgtt_create+0x16/0x80
i915_gem_create_context+0x248/0x390
i915_gem_context_create_ioctl+0x4b/0xe0
drm_ioctl_kernel+0xa5/0xf0
drm_ioctl+0x2ed/0x3a0
do_vfs_ioctl+0x9f/0x620
ksys_ioctl+0x6b/0x80
__x64_sys_ioctl+0x11/0x20
do_syscall_64+0x43/0xf0
entry_SYSCALL_64_after_hwframe+0x44/0xa9
INFO: Slab 0x00000000d13e87af objects=3 used=3 fp=0x (null) flags=0x200000000010201
INFO: Object 0x0000000003278802 @offset=17064 fp=0x00000000e2e6652b
Fixing this by allocating UIO_MAXIOV + VHOST_NET_BATCH iovs for
vhost-net. This is done through set the limitation through
vhost_dev_init(), then set_owner can allocate the number of iov in a
per device manner.
This fixes CVE-2018-16880.
Fixes: e2b3b35eb989 ("vhost_net: batch used ring update in rx")
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
drivers/vhost/net.c | 3 ++-
drivers/vhost/scsi.c | 2 +-
drivers/vhost/vhost.c | 7 ++++---
drivers/vhost/vhost.h | 4 +++-
drivers/vhost/vsock.c | 2 +-
5 files changed, 11 insertions(+), 7 deletions(-)
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index bca86bf7189f..df51a35cf537 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -1337,7 +1337,8 @@ static int vhost_net_open(struct inode *inode, struct file *f)
n->vqs[i].rx_ring = NULL;
vhost_net_buf_init(&n->vqs[i].rxq);
}
- vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX);
+ vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX,
+ UIO_MAXIOV + VHOST_NET_BATCH);
vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, EPOLLOUT, dev);
vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, EPOLLIN, dev);
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 344684f3e2e4..23593cb23dd0 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1627,7 +1627,7 @@ static int vhost_scsi_open(struct inode *inode, struct file *f)
vqs[i] = &vs->vqs[i].vq;
vs->vqs[i].vq.handle_kick = vhost_scsi_handle_kick;
}
- vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ);
+ vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ, UIO_MAXIOV);
vhost_scsi_init_inflight(vs, NULL);
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 15a216cdd507..24a129fcdd61 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -390,9 +390,9 @@ static long vhost_dev_alloc_iovecs(struct vhost_dev *dev)
vq->indirect = kmalloc_array(UIO_MAXIOV,
sizeof(*vq->indirect),
GFP_KERNEL);
- vq->log = kmalloc_array(UIO_MAXIOV, sizeof(*vq->log),
+ vq->log = kmalloc_array(dev->iov_limit, sizeof(*vq->log),
GFP_KERNEL);
- vq->heads = kmalloc_array(UIO_MAXIOV, sizeof(*vq->heads),
+ vq->heads = kmalloc_array(dev->iov_limit, sizeof(*vq->heads),
GFP_KERNEL);
if (!vq->indirect || !vq->log || !vq->heads)
goto err_nomem;
@@ -414,7 +414,7 @@ static void vhost_dev_free_iovecs(struct vhost_dev *dev)
}
void vhost_dev_init(struct vhost_dev *dev,
- struct vhost_virtqueue **vqs, int nvqs)
+ struct vhost_virtqueue **vqs, int nvqs, int iov_limit)
{
struct vhost_virtqueue *vq;
int i;
@@ -427,6 +427,7 @@ void vhost_dev_init(struct vhost_dev *dev,
dev->iotlb = NULL;
dev->mm = NULL;
dev->worker = NULL;
+ dev->iov_limit = iov_limit;
init_llist_head(&dev->work_list);
init_waitqueue_head(&dev->wait);
INIT_LIST_HEAD(&dev->read_list);
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 1b675dad5e05..9490e7ddb340 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -170,9 +170,11 @@ struct vhost_dev {
struct list_head read_list;
struct list_head pending_list;
wait_queue_head_t wait;
+ int iov_limit;
};
-void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs, int nvqs);
+void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs,
+ int nvqs, int iov_limit);
long vhost_dev_set_owner(struct vhost_dev *dev);
bool vhost_dev_has_owner(struct vhost_dev *dev);
long vhost_dev_check_owner(struct vhost_dev *);
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 3fbc068eaa9b..bb5fc0e9fbc2 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -531,7 +531,7 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
vsock->vqs[VSOCK_VQ_TX].handle_kick = vhost_vsock_handle_tx_kick;
vsock->vqs[VSOCK_VQ_RX].handle_kick = vhost_vsock_handle_rx_kick;
- vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs));
+ vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs), UIO_MAXIOV);
file->private_data = vsock;
spin_lock_init(&vsock->send_pkt_list_lock);
--
2.17.1
^ permalink raw reply related
* Re: [PATCH] net: stmmac: dwmac-rk: fix error handling in rk_gmac_powerup()
From: David Miller @ 2019-01-28 7:04 UTC (permalink / raw)
To: khoroshilov
Cc: david.wu, peppe.cavallaro, joabreu, netdev, linux-arm-kernel,
linux-kernel, ldv-project
In-Reply-To: <1548532137-15618-1-git-send-email-khoroshilov@ispras.ru>
From: Alexey Khoroshilov <khoroshilov@ispras.ru>
Date: Sat, 26 Jan 2019 22:48:57 +0300
> If phy_power_on() fails in rk_gmac_powerup(), clocks are left enabled.
>
> Found by Linux Driver Verification project (linuxtesting.org).
>
> Signed-off-by: Alexey Khoroshilov <khoroshilov@ispras.ru>
Applied, thank you.
^ permalink raw reply
* Re: [PATCH net 0/3] net: hns: code optimizations & bugfixes for HNS driver
From: David Miller @ 2019-01-28 7:02 UTC (permalink / raw)
To: lipeng321; +Cc: netdev, linux-kernel, linuxarm, yisen.zhuang, salil.mehta
In-Reply-To: <1548494307-63594-1-git-send-email-lipeng321@huawei.com>
From: Peng Li <lipeng321@huawei.com>
Date: Sat, 26 Jan 2019 17:18:24 +0800
> This patchset includes bugfixes and code optimizations for the HNS
> ethernet controller driver
Series applied, thank you.
There are only bug fixes in here, so please do not use the word
"optimizations" in such situations.
Thanks.
^ permalink raw reply
* Re: [PATCH] Revert "net: phy: marvell: avoid pause mode on SGMII-to-Copper for 88e151x"
From: David Miller @ 2019-01-28 7:00 UTC (permalink / raw)
To: rmk+kernel; +Cc: andrew, f.fainelli, hkallweit1, netdev
In-Reply-To: <E1gnAtB-0002Cz-Tr@rmk-PC.armlinux.org.uk>
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Fri, 25 Jan 2019 23:27:57 +0000
> This reverts commit 6623c0fba10ef45b64ca213ad5dec926f37fa9a0.
>
> The original diagnosis was incorrect: it appears that the NIC had
> PHY polling mode enabled, which meant that it overwrote the PHYs
> advertisement register during negotiation.
>
> Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
The code in the 'net' tree has the linkmode_clear_bit() etc. changes
that were done to this driver, so the pause variable is not there
and the pause bits are adjusted using that helper.
Please respin this against current sources so that it actually
applies.
Thank you.
^ permalink raw reply
* [PATCH 2/2] iwlwifi: Use struct_size() in kzalloc
From: YueHaibing @ 2019-01-28 6:44 UTC (permalink / raw)
To: johannes.berg, emmanuel.grumbach, luciano.coelho, linuxwifi,
kvalo
Cc: linux-kernel, netdev, linux-wireless, YueHaibing
In-Reply-To: <20190128064432.17576-1-yuehaibing@huawei.com>
Use struct_size() in kzalloc instead of the 'regd_to_copy'
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
---
drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c | 8 +++-----
1 file changed, 3 insertions(+), 5 deletions(-)
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index 569cc50..cb9e722 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -1093,7 +1093,7 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
const u8 *nvm_chan = cfg->nvm_type == IWL_NVM_EXT ?
iwl_ext_nvm_channels : iwl_nvm_channels;
struct ieee80211_regdomain *regd, *copy_rd;
- int size_of_regd, regd_to_copy;
+ int size_of_regd;
struct ieee80211_reg_rule *rule;
struct regdb_ptrs *regdb_ptrs;
enum nl80211_band band;
@@ -1193,10 +1193,8 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
* Narrow down regdom for unused regulatory rules to prevent hole
* between reg rules to wmm rules.
*/
- regd_to_copy = sizeof(struct ieee80211_regdomain) +
- valid_rules * sizeof(struct ieee80211_reg_rule);
-
- copy_rd = kmemdup(regd, regd_to_copy, GFP_KERNEL);
+ copy_rd = kmemdup(regd, struct_size(regd, reg_rules, valid_rules),
+ GFP_KERNEL);
if (!copy_rd)
copy_rd = ERR_PTR(-ENOMEM);
--
2.7.4
^ permalink raw reply related
* [PATCH 1/2] iwlwifi: Use kmemdup instead of duplicating its function
From: YueHaibing @ 2019-01-28 6:44 UTC (permalink / raw)
To: johannes.berg, emmanuel.grumbach, luciano.coelho, linuxwifi,
kvalo
Cc: linux-kernel, netdev, linux-wireless, YueHaibing
In-Reply-To: <20190128064432.17576-1-yuehaibing@huawei.com>
Use kmemdup rather than duplicating its implementation
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
---
drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c | 8 ++------
1 file changed, 2 insertions(+), 6 deletions(-)
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index d9afedc..569cc50 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -1196,13 +1196,9 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
regd_to_copy = sizeof(struct ieee80211_regdomain) +
valid_rules * sizeof(struct ieee80211_reg_rule);
- copy_rd = kzalloc(regd_to_copy, GFP_KERNEL);
- if (!copy_rd) {
+ copy_rd = kmemdup(regd, regd_to_copy, GFP_KERNEL);
+ if (!copy_rd)
copy_rd = ERR_PTR(-ENOMEM);
- goto out;
- }
-
- memcpy(copy_rd, regd, regd_to_copy);
out:
kfree(regdb_ptrs);
--
2.7.4
^ permalink raw reply related
* [PATCH 0/2] cleanup for iwlwifi
From: YueHaibing @ 2019-01-28 6:44 UTC (permalink / raw)
To: johannes.berg, emmanuel.grumbach, luciano.coelho, linuxwifi,
kvalo
Cc: linux-kernel, netdev, linux-wireless, YueHaibing
YueHaibing (2):
iwlwifi: Use kmemdup instead of duplicating its function
iwlwifi: Use struct_size() in kzalloc
drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c | 14 ++++----------
1 file changed, 4 insertions(+), 10 deletions(-)
--
2.7.4
^ permalink raw reply
* Re: Packets being dropped somewhere in the kernel, between iptables and packet capture layers
From: Florian Westphal @ 2019-01-28 6:21 UTC (permalink / raw)
To: Niklas Hambüchen; +Cc: netdev
In-Reply-To: <19e1b7a2-00b2-3656-309c-0586e990007b@nh2.me>
Niklas Hambüchen <mail@nh2.me> wrote:
> I'm sending this to netdev@vger.kernel.org even though http://vger.kernel.org/lkml/ still suggests linux-net@vger.kernel.org, because the latter seems to be inactive since 2011 and full of spam, and I got "unresolvable address" for it. Perhaps somebody should update the page that recommends it.
> Nevertheless, please let me know if here is the wrong place.
This problem is known; I asked for test feedback on this patch but never
got a response:
netfilter: nf_nat: return the same reply tuple for matching CTs
It is possible that two concurrent packets originating from the same
socket of a connection-less protocol (e.g. UDP) can end up having
different IP_CT_DIR_REPLY tuples which results in one of the packets
being dropped.
To illustrate this, consider the following simplified scenario:
1. No DNAT/SNAT/MASQUEARADE rules are installed, but the nf_nat module
is loaded.
2. Packet A and B are sent at the same time from two different threads
via the same UDP socket which hasn't been used before (=no CT has
been created before). Both packets have the same IP_CT_DIR_ORIGINAL
tuple.
3. CT of A has been created and confirmed, afterwards get_unique_tuple
is called for B. Because IP_CT_DIR_REPLY tuple (the inverse of
the IP_CT_DIR_ORIGINAL tuple) is already taken by the A's confirmed
CT (nf_nat_used_tuple finds it), get_unique_tuple calls UDP's
unique_tuple which returns a different IP_CT_DIR_REPLY tuple (usually
with src port = 1024)
4. B's CT cannot get confirmed in __nf_conntrack_confirm due to
the found IP_CT_DIR_ORIGINAL tuple of A and the different
IP_CT_DIR_REPLY tuples, thus the packet B gets dropped.
This patch modifies nf_conntrack_tuple_taken so it doesn't consider
colliding reply tuples if the IP_CT_DIR_ORIGINAL tuples are equal.
Then, at insert time, either clash resolution is possible (new packet
has the existing/older conntrack assigned to it), or it has to be
dropped.
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 741b533148ba..07847a612adf 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1007,6 +1007,22 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
}
if (nf_ct_key_equal(h, tuple, zone, net)) {
+ /* If the origin tuples are identical, we can ignore
+ * this clashing entry: they refer to the same flow.
+ * Do not apply nat clash resolution in this case and
+ * let nf_ct_resolve_clash() deal with this.
+ *
+ * This can happen with UDP in particular, e.g. when
+ * more than one packet is sent from same socket in
+ * different threads.
+ *
+ * We would now mangle our entry and would then have to
+ * discard it at conntrack confirm time.
+ */
+ if (nf_ct_tuple_equal(&ignored_conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
+ &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple))
+ continue;
+
NF_CT_STAT_INC_ATOMIC(net, found);
rcu_read_unlock();
return 1;
^ permalink raw reply related
* Re: [PATCH net-next v2] net: l2tp: fix reading optional fields of L2TPv3
From: Jacob Wen @ 2019-01-28 6:15 UTC (permalink / raw)
To: Guillaume Nault; +Cc: netdev, eric.dumazet
In-Reply-To: <20190124160107.GA6470@localhost.localdomain>
On 1/25/19 12:01 AM, Guillaume Nault wrote:
> On Thu, Jan 24, 2019 at 03:49:17PM +0800, Jacob Wen wrote:
>> Use pskb_may_pull() to make sure the optional fields are in skb linear
>> parts, so we can safely read them later.
>>
>> It's easy to reproduce the issue with a net driver that supports paged
>> skb data. Just create a L2TPv3 over IP tunnel and then generates some
>> network traffic.
>> Once reproduced, rx err in /sys/kernel/debug/l2tp/tunnels will increase.
>>
>> Signed-off-by: Jacob Wen <jian.w.wen@oracle.com>
>> ---
>> Changes in v2:
>> 1. Only fix L2TPv3 to make code simple.
>> To fix both L2TPv3 and L2TPv2, we'd better refactor l2tp_recv_common.
>> It's complicated to do so.
>>
> Yes, the L2TP data path definitely needs some care. But for a one-off
> patch like this, it'd probably make more sense to respect the current
> code structure instead of adding yet more special cases.
Agree. I didn't give l2tp_udp_recv_core enough attention.
> I mean, l2tp_recv_common() assumes that it can safely access the L2TP
> header: pskb_may_pull() is done in l2tp_udp_recv_core() (which probably
> should pull more bytes in case the length field is present BTW).
Yes. Two more bytes are required for L2TPv2.
> It's up to l2tp_ip (and l2tp_ip6) to respect this requirement, so that's
> where pskb_may_pull() should be done. Yes it'd be better to linearise
> data close to the place we access them, but that'd be long term
> refactoring. If we don't have the resources to do that, let's just, at
> least keep some consistency.
I will send a new patch.
Thanks.
--
Jacob
^ permalink raw reply
* Re: [PATCH] iwlwifi: Use kmemdup instead of duplicating its function
From: YueHaibing @ 2019-01-28 5:58 UTC (permalink / raw)
To: Joe Perches, johannes.berg, emmanuel.grumbach, luciano.coelho,
linuxwifi, kvalo
Cc: linux-kernel, netdev, linux-wireless
In-Reply-To: <0c2c9ef717676371950942b08556d0e0196559de.camel@perches.com>
On 2019/1/27 5:24, Joe Perches wrote:
> On Sat, 2019-01-26 at 20:42 +0800, YueHaibing wrote:
>> Use kmemdup rather than duplicating its implementation
> []
>> diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
> []
>> @@ -1196,13 +1196,9 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
>> regd_to_copy = sizeof(struct ieee80211_regdomain) +
>> valid_rules * sizeof(struct ieee80211_reg_rule);
>> - copy_rd = kzalloc(regd_to_copy, GFP_KERNEL);
>> - if (!copy_rd) {
>> + copy_rd = kmemdup(regd, regd_to_copy, GFP_KERNEL);
>
> This should probably be
>
> copy_rd = kmemdup(regd, struct_size(regd, reg_rules, valid_rules),
> GFP_KERNEL);
>
Yes, So also can remove 'regd_to_copy', I will do it in a new patch
Thanks!
>> + if (!copy_rd)
>> copy_rd = ERR_PTR(-ENOMEM);
>> - goto out;
>> - }
>> -
>> - memcpy(copy_rd, regd, regd_to_copy);
>>
>> out:
>> kfree(regdb_ptrs);
>
>
> .
>
^ permalink raw reply
* Re: [PATCH bpf-next v2 0/3] selftests: bpf: break up test_verifier
From: Alexei Starovoitov @ 2019-01-28 5:57 UTC (permalink / raw)
To: Jakub Kicinski; +Cc: Daniel Borkmann, netdev
In-Reply-To: <20190127205413.231fcc05@cakuba.hsd1.ca.comcast.net>
On Sun, Jan 27, 2019 at 08:54:13PM -0800, Jakub Kicinski wrote:
> On Sun, 27 Jan 2019 12:56:39 -0800, Alexei Starovoitov wrote:
> > On Sun, Jan 27, 2019 at 10:33 AM Jakub Kicinski wrote:
> > >
> > > Looks like v2 just applies cleanly again, should I repost?
> >
> > v2 set:
> > https://patchwork.ozlabs.org/series/88320/mbox/
> > doesn't apply cleanly.
> > Pls report.
>
> I rebased and regenerated but the patches came out identical :(
>
> Then I tried to apply and it does:
>
> $ git fetch bpf-next
> $ git checkout bpf-next/master
> $ git log --oneline | head -1
> ae575c8a9868 Merge branch 'jmp32-insns'
> $ git am /tmp/selftests-bpf-break-up-test_verifier.patch
> Applying: selftests: bpf: prepare for break up of verifier tests
> Applying: selftests: bpf: break up test_verifier
> Applying: selftests: bpf: break up the rest of test_verifier
> $ md5sum /tmp/selftests-bpf-break-up-test_verifier.patch
> 70ebd5f1162605b71851b129230cd19e /tmp/selftests-bpf-break-up-test_verifier.patch
>
> Could you double check? Maybe its something with my tree :S
My tripple check failed.
Turned out that the eariler attempt to merge it created
selftests/bpf/verifier/ directory with .gitignore file inside it
and 'git am --abort' and 'git rebase --hard' kept it in place.
(since .gitignore was there)
'git' wasn't very helpful with the following message either:
----
Applying: selftests: bpf: prepare for break up of verifier tests
error: sha1 information is lacking or useless (tools/testing/selftests/bpf/Makefile).
error: could not build fake ancestor
Patch failed at 0001 selftests: bpf: prepare for break up of verifier tests
----
But the odds were in my favor tonight :)
Applied to bpf-next. Thanks!
^ permalink raw reply
* [PATCH] bpf/core.c - silence warning messages
From: valdis.kletnieks @ 2019-01-28 4:11 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann; +Cc: netdev, linux-kernel
Compiling kernel/bpf/core.c with W=1 causes a flood of warnings:
kernel/bpf/core.c:1198:65: warning: initialized field overwritten [-Woverride-init]
1198 | #define BPF_INSN_3_TBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = true
| ^~~~
kernel/bpf/core.c:1087:2: note: in expansion of macro 'BPF_INSN_3_TBL'
1087 | INSN_3(ALU, ADD, X), \
| ^~~~~~
kernel/bpf/core.c:1202:3: note: in expansion of macro 'BPF_INSN_MAP'
1202 | BPF_INSN_MAP(BPF_INSN_2_TBL, BPF_INSN_3_TBL),
| ^~~~~~~~~~~~
kernel/bpf/core.c:1198:65: note: (near initialization for 'public_insntable[12]')
1198 | #define BPF_INSN_3_TBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = true
| ^~~~
kernel/bpf/core.c:1087:2: note: in expansion of macro 'BPF_INSN_3_TBL'
1087 | INSN_3(ALU, ADD, X), \
| ^~~~~~
kernel/bpf/core.c:1202:3: note: in expansion of macro 'BPF_INSN_MAP'
1202 | BPF_INSN_MAP(BPF_INSN_2_TBL, BPF_INSN_3_TBL),
| ^~~~~~~~~~~~
98 copies of the above.
The attached patch silences the warnings, because we *know* we're overwriting
the default initializer. That leaves bpf/core.c with only 6 other warnings,
which become more visible in comparison.
Signed-off-by: Valdis Kletnieks <valdis.kletnieks@vt.edu>
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 4c2fa3ac56f6..2606665f2cb5 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -21,3 +21,4 @@ obj-$(CONFIG_CGROUP_BPF) += cgroup.o
ifeq ($(CONFIG_INET),y)
obj-$(CONFIG_BPF_SYSCALL) += reuseport_array.o
endif
+CFLAGS_core.o += $(call cc-disable-warning, override-init)
^ permalink raw reply related
* Re: [PATCH iproute2-next] Introduce ip-brctl shell script
From: Roopa Prabhu @ 2019-01-28 5:08 UTC (permalink / raw)
To: Stefano Brivio
Cc: Nikolay Aleksandrov, David Ahern, Phil Sutter, Eric Garver,
Tomas Dolezal, Stephen Hemminger, Lennert Buytenhek, netdev
In-Reply-To: <20190125110543.35693aee@elisabeth>
On Fri, Jan 25, 2019 at 2:05 AM Stefano Brivio <sbrivio@redhat.com> wrote:
>
> Hi Roopa,
>
> On Wed, 23 Jan 2019 08:33:27 -0800
> Roopa Prabhu <roopa@cumulusnetworks.com> wrote:
>
> > On Wed, Jan 23, 2019 at 7:09 AM Nikolay Aleksandrov
> > <nikolay@cumulusnetworks.com> wrote:
> >
> > > Hi,
> > > IMO the effort should be towards improving iproute2 to be
> > > easier to use and more intuitive. We should be pushing people to
> > > use the new tools instead of trying to find workarounds to keep the
> > > old tools alive. I do like to idea of deprecating bridge-utils, but
> > > I think it should be done via improving ip/bridge enough to be
> > > pleasant to use. We will have to maintain this compatibility layer
> > > forever if it gets accepted and we'll never get rid of brctl this
> > > way.
> >
> > +1, we should move people away from brtcl. there is enough confusion
> > among users looking at bridge attributes.,
> >
> > ip -d link show
> > bridge -d link show
> > brctl
>
> Why is this confusing? One can simply pick the most appropriate tool.
>
> > Adding a 4th one to the list is not going to ease the confusion.
>
> Why do you say I'm adding a fourth (I guess) tool? I'm replacing the
> third one.
I know. But the first two commands were supposed to replace the third
one already.
and they should be. So, I think its better to fix the first two
instead of introducing another one.
>
> > We should try to make the 'ip -d link show and bridge -d link show'
> > outputs better. Any suggestions there from people will be useful.
>
> To be honest, I don't see any problem with them -- they just do
> different things.
Can we extend 'bridge' tool with extra options to provide a summary
view of all bridges like brctl ?
Its supposed to be the netlink based tool for all bridging and hence
could be a good replacement for all brctl users.
^ permalink raw reply
* Re: [PATCH net-next v7 0/8] devlink: Add configuration parameters support for devlink_port
From: David Miller @ 2019-01-28 3:45 UTC (permalink / raw)
To: mkubecek; +Cc: jakub.kicinski, netdev, vasundhara-v.volam, michael.chan, jiri
In-Reply-To: <20190127230730.GF24651@unicorn.suse.cz>
From: Michal Kubecek <mkubecek@suse.cz>
Date: Mon, 28 Jan 2019 00:07:30 +0100
> What I like is that this approach would not require knowing (or
> rather guessing) which attributes are going to allow persistent
> settings in the future.
+1
^ permalink raw reply
* Re: [PATCH net-next v2 0/2] mv88e6xxx DSA suspend to RAM support
From: David Miller @ 2019-01-28 3:44 UTC (permalink / raw)
To: andrew
Cc: miquel.raynal, vivien.didelot, f.fainelli, netdev, linux-kernel,
thomas.petazzoni, gregory.clement, antoine.tenart,
maxime.chevallier, nadavh
In-Reply-To: <20190127214652.GB32046@lunn.ch>
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 27 Jan 2019 22:46:52 +0100
> I think you are replying to the wrong patch? This comment fits to
>
> https://www.spinics.net/lists/netdev/msg546662.html
I noticed that right after I hit send, you are right.
Sorry for the confusion.
> Although i don't like it, i think for the moment we are going to have
> to accept the proposed fix.
Indeed.
^ permalink raw reply
* [PATCH v5 bpf-next 8/9] libbpf: introduce bpf_map_lookup_elem_flags()
From: Alexei Starovoitov @ 2019-01-28 2:54 UTC (permalink / raw)
To: davem
Cc: daniel, peterz, jannh, paulmck, will.deacon, mingo, netdev,
kernel-team
In-Reply-To: <20190128025426.370004-1-ast@kernel.org>
Introduce
int bpf_map_lookup_elem_flags(int fd, const void *key, void *value, __u64 flags)
helper to lookup array/hash/cgroup_local_storage elements with BPF_F_LOCK flag.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
tools/lib/bpf/bpf.c | 13 +++++++++++++
tools/lib/bpf/bpf.h | 2 ++
tools/lib/bpf/libbpf.map | 1 +
3 files changed, 16 insertions(+)
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 3caaa3428774..d55a77a05d5f 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -357,6 +357,19 @@ int bpf_map_lookup_elem(int fd, const void *key, void *value)
return sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
}
+int bpf_map_lookup_elem_flags(int fd, const void *key, void *value, __u64 flags)
+{
+ union bpf_attr attr;
+
+ bzero(&attr, sizeof(attr));
+ attr.map_fd = fd;
+ attr.key = ptr_to_u64(key);
+ attr.value = ptr_to_u64(value);
+ attr.flags = flags;
+
+ return sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
+}
+
int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value)
{
union bpf_attr attr;
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 8f09de482839..ed09eed2dc3b 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -110,6 +110,8 @@ LIBBPF_API int bpf_map_update_elem(int fd, const void *key, const void *value,
__u64 flags);
LIBBPF_API int bpf_map_lookup_elem(int fd, const void *key, void *value);
+LIBBPF_API int bpf_map_lookup_elem_flags(int fd, const void *key, void *value,
+ __u64 flags);
LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key,
void *value);
LIBBPF_API int bpf_map_delete_elem(int fd, const void *key);
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 266bc95d0142..f6f96fc38c50 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -130,4 +130,5 @@ LIBBPF_0.0.2 {
bpf_probe_helper;
bpf_probe_map_type;
bpf_probe_prog_type;
+ bpf_map_lookup_elem_flags;
} LIBBPF_0.0.1;
--
2.20.0
^ permalink raw reply related
* [PATCH v5 bpf-next 7/9] tools/bpf: sync uapi/bpf.h
From: Alexei Starovoitov @ 2019-01-28 2:54 UTC (permalink / raw)
To: davem
Cc: daniel, peterz, jannh, paulmck, will.deacon, mingo, netdev,
kernel-team
add BPF_F_LOCK definition to tools/include/uapi/linux/bpf.h
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
tools/include/uapi/linux/bpf.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 86f7c438d40f..1777fa0c61e4 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -267,6 +267,7 @@ enum bpf_attach_type {
#define BPF_ANY 0 /* create new element or update existing */
#define BPF_NOEXIST 1 /* create new element if it didn't exist */
#define BPF_EXIST 2 /* update existing element */
+#define BPF_F_LOCK 4 /* spin_lock-ed map_lookup/map_update */
/* flags for BPF_MAP_CREATE command */
#define BPF_F_NO_PREALLOC (1U << 0)
--
2.20.0
^ permalink raw reply related
* [PATCH v5 bpf-next 9/9] selftests/bpf: test for BPF_F_LOCK
From: Alexei Starovoitov @ 2019-01-28 2:50 UTC (permalink / raw)
To: davem
Cc: daniel, peterz, jannh, paulmck, will.deacon, mingo, netdev,
kernel-team
In-Reply-To: <20190128025010.342241-1-ast@kernel.org>
Add C based test that runs 4 bpf programs in parallel
that update the same hash and array maps.
And another 2 threads that read from these two maps
via lookup(key, value, BPF_F_LOCK) api
to make sure the user space sees consistent value in both
hash and array elements while user space races with kernel bpf progs.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
tools/testing/selftests/bpf/Makefile | 2 +-
tools/testing/selftests/bpf/test_map_lock.c | 66 ++++++++++++++++++
tools/testing/selftests/bpf/test_progs.c | 74 +++++++++++++++++++++
3 files changed, 141 insertions(+), 1 deletion(-)
create mode 100644 tools/testing/selftests/bpf/test_map_lock.c
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 48eb9ecd2015..51e0717542b6 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -35,7 +35,7 @@ BPF_OBJ_FILES = \
sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \
test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o test_xdp_vlan.o \
- xdp_dummy.o test_map_in_map.o test_spin_lock.o
+ xdp_dummy.o test_map_in_map.o test_spin_lock.o test_map_lock.o
# Objects are built with default compilation flags and with sub-register
# code-gen enabled.
diff --git a/tools/testing/selftests/bpf/test_map_lock.c b/tools/testing/selftests/bpf/test_map_lock.c
new file mode 100644
index 000000000000..af8cc68ed2f9
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_map_lock.c
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include <linux/bpf.h>
+#include <linux/version.h>
+#include "bpf_helpers.h"
+
+#define VAR_NUM 16
+
+struct hmap_elem {
+ struct bpf_spin_lock lock;
+ int var[VAR_NUM];
+};
+
+struct bpf_map_def SEC("maps") hash_map = {
+ .type = BPF_MAP_TYPE_HASH,
+ .key_size = sizeof(int),
+ .value_size = sizeof(struct hmap_elem),
+ .max_entries = 1,
+};
+
+BPF_ANNOTATE_KV_PAIR(hash_map, int, struct hmap_elem);
+
+struct array_elem {
+ struct bpf_spin_lock lock;
+ int var[VAR_NUM];
+};
+
+struct bpf_map_def SEC("maps") array_map = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(int),
+ .value_size = sizeof(struct array_elem),
+ .max_entries = 1,
+};
+
+BPF_ANNOTATE_KV_PAIR(array_map, int, struct array_elem);
+
+SEC("map_lock_demo")
+int bpf_map_lock_test(struct __sk_buff *skb)
+{
+ struct hmap_elem zero = {}, *val;
+ int rnd = bpf_get_prandom_u32();
+ int key = 0, err = 1, i;
+ struct array_elem *q;
+
+ val = bpf_map_lookup_elem(&hash_map, &key);
+ if (!val)
+ goto err;
+ /* spin_lock in hash map */
+ bpf_spin_lock(&val->lock);
+ for (i = 0; i < VAR_NUM; i++)
+ val->var[i] = rnd;
+ bpf_spin_unlock(&val->lock);
+
+ /* spin_lock in array */
+ q = bpf_map_lookup_elem(&array_map, &key);
+ if (!q)
+ goto err;
+ bpf_spin_lock(&q->lock);
+ for (i = 0; i < VAR_NUM; i++)
+ q->var[i] = rnd;
+ bpf_spin_unlock(&q->lock);
+ err = 0;
+err:
+ return err;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 6425e95c3f16..1427338f14a2 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -1922,6 +1922,79 @@ static void test_spin_lock(void)
bpf_object__close(obj);
}
+static void *parallel_map_access(void *arg)
+{
+ int err, map_fd = *(u32 *) arg;
+ int vars[17], i, j, rnd, key = 0;
+
+ for (i = 0; i < 10000; i++) {
+ err = bpf_map_lookup_elem_flags(map_fd, &key, vars, BPF_F_LOCK);
+ if (err) {
+ printf("lookup failed\n");
+ error_cnt++;
+ goto out;
+ }
+ if (vars[0] != 0) {
+ printf("lookup #%d var[0]=%d\n", i, vars[0]);
+ error_cnt++;
+ goto out;
+ }
+ rnd = vars[1];
+ for (j = 2; j < 17; j++) {
+ if (vars[j] == rnd)
+ continue;
+ printf("lookup #%d var[1]=%d var[%d]=%d\n",
+ i, rnd, j, vars[j]);
+ error_cnt++;
+ goto out;
+ }
+ }
+out:
+ pthread_exit(arg);
+}
+
+static void test_map_lock(void)
+{
+ const char *file = "./test_map_lock.o";
+ int prog_fd, map_fd[2], vars[17] = {};
+ pthread_t thread_id[6];
+ struct bpf_object *obj;
+ int err = 0, key = 0, i;
+ void *ret;
+
+ err = bpf_prog_load(file, BPF_PROG_TYPE_CGROUP_SKB, &obj, &prog_fd);
+ if (err) {
+ printf("test_map_lock:bpf_prog_load errno %d\n", errno);
+ goto close_prog;
+ }
+ map_fd[0] = bpf_find_map(__func__, obj, "hash_map");
+ if (map_fd[0] < 0)
+ goto close_prog;
+ map_fd[1] = bpf_find_map(__func__, obj, "array_map");
+ if (map_fd[1] < 0)
+ goto close_prog;
+
+ bpf_map_update_elem(map_fd[0], &key, vars, BPF_F_LOCK);
+
+ for (i = 0; i < 4; i++)
+ assert(pthread_create(&thread_id[i], NULL,
+ ¶llel_bpf_prog_test_run, &prog_fd) == 0);
+ for (i = 4; i < 6; i++)
+ assert(pthread_create(&thread_id[i], NULL,
+ ¶llel_map_access, &map_fd[i - 4]) == 0);
+ for (i = 0; i < 4; i++)
+ assert(pthread_join(thread_id[i], &ret) == 0 &&
+ ret == (void *)&prog_fd);
+ for (i = 4; i < 6; i++)
+ assert(pthread_join(thread_id[i], &ret) == 0 &&
+ ret == (void *)&map_fd[i - 4]);
+ goto close_prog_noerr;
+close_prog:
+ error_cnt++;
+close_prog_noerr:
+ bpf_object__close(obj);
+}
+
int main(void)
{
srand(time(NULL));
@@ -1950,6 +2023,7 @@ int main(void)
test_queue_stack_map(QUEUE);
test_queue_stack_map(STACK);
test_spin_lock();
+ test_map_lock();
printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt);
return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS;
--
2.20.0
^ permalink raw reply related
* [PATCH v5 bpf-next 4/9] selftests/bpf: add bpf_spin_lock tests
From: Alexei Starovoitov @ 2019-01-28 2:50 UTC (permalink / raw)
To: davem
Cc: daniel, peterz, jannh, paulmck, will.deacon, mingo, netdev,
kernel-team
In-Reply-To: <20190128025010.342241-1-ast@kernel.org>
add bpf_spin_lock tests to test_verifier.c that don't require
latest llvm with BTF support
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
tools/testing/selftests/bpf/test_verifier.c | 459 +++++++++++++++++++-
1 file changed, 458 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 1df757645a9a..680c8db49d5c 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -32,6 +32,7 @@
#include <linux/bpf_perf_event.h>
#include <linux/bpf.h>
#include <linux/if_ether.h>
+#include <linux/btf.h>
#include <bpf/bpf.h>
@@ -49,7 +50,7 @@
#define MAX_INSNS BPF_MAXINSNS
#define MAX_FIXUPS 8
-#define MAX_NR_MAPS 13
+#define MAX_NR_MAPS 14
#define MAX_TEST_RUNS 8
#define POINTER_VALUE 0xcafe4all
#define TEST_DATA_LEN 64
@@ -76,6 +77,7 @@ struct bpf_test {
int fixup_map_in_map[MAX_FIXUPS];
int fixup_cgroup_storage[MAX_FIXUPS];
int fixup_percpu_cgroup_storage[MAX_FIXUPS];
+ int fixup_map_spin_lock[MAX_FIXUPS];
const char *errstr;
const char *errstr_unpriv;
uint32_t retval, retval_unpriv, insn_processed;
@@ -16533,6 +16535,361 @@ static struct bpf_test tests[] = {
.result = ACCEPT,
.retval = 2,
},
+ {
+ "spin_lock: test1 success",
+ .insns = {
+ BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_spin_lock),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_spin_unlock),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_spin_lock = { 3 },
+ .result = ACCEPT,
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "",
+ .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+ },
+ {
+ "spin_lock: test2 direct ld/st",
+ .insns = {
+ BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_spin_lock),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_spin_unlock),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_spin_lock = { 3 },
+ .result = REJECT,
+ .errstr = "cannot be accessed directly",
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "",
+ .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+ },
+ {
+ "spin_lock: test3 direct ld/st",
+ .insns = {
+ BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_spin_lock),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, 1),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_spin_unlock),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_spin_lock = { 3 },
+ .result = REJECT,
+ .errstr = "cannot be accessed directly",
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "",
+ .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+ },
+ {
+ "spin_lock: test4 direct ld/st",
+ .insns = {
+ BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_spin_lock),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
+ BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_6, 3),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_spin_unlock),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_spin_lock = { 3 },
+ .result = REJECT,
+ .errstr = "cannot be accessed directly",
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "",
+ .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+ },
+ {
+ "spin_lock: test5 call within a locked region",
+ .insns = {
+ BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_spin_lock),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_get_prandom_u32),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_spin_unlock),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_spin_lock = { 3 },
+ .result = REJECT,
+ .errstr = "calls are not allowed",
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "",
+ .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+ },
+ {
+ "spin_lock: test6 missing unlock",
+ .insns = {
+ BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_spin_lock),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_spin_unlock),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_spin_lock = { 3 },
+ .result = REJECT,
+ .errstr = "unlock is missing",
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "",
+ .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+ },
+ {
+ "spin_lock: test7 unlock without lock",
+ .insns = {
+ BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_spin_lock),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_spin_unlock),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_spin_lock = { 3 },
+ .result = REJECT,
+ .errstr = "without taking a lock",
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "",
+ .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+ },
+ {
+ "spin_lock: test8 double lock",
+ .insns = {
+ BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_spin_lock),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_spin_lock),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_spin_unlock),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_spin_lock = { 3 },
+ .result = REJECT,
+ .errstr = "calls are not allowed",
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "",
+ .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+ },
+ {
+ "spin_lock: test9 different lock",
+ .insns = {
+ BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_spin_lock),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_spin_unlock),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_spin_lock = { 3, 11 },
+ .result = REJECT,
+ .errstr = "unlock of different lock",
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "",
+ .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+ },
+ {
+ "spin_lock: test10 lock in subprog without unlock",
+ .insns = {
+ BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 5),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_spin_unlock),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_spin_lock),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_spin_lock = { 3 },
+ .result = REJECT,
+ .errstr = "unlock is missing",
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "",
+ .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+ },
+ {
+ "spin_lock: test11 ld_abs under lock",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_spin_lock),
+ BPF_LD_ABS(BPF_B, 0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_spin_unlock),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_spin_lock = { 4 },
+ .result = REJECT,
+ .errstr = "inside bpf_spin_lock",
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ },
};
static int probe_filter_length(const struct bpf_insn *fp)
@@ -16663,6 +17020,98 @@ static int create_cgroup_storage(bool percpu)
return fd;
}
+#define BTF_INFO_ENC(kind, kind_flag, vlen) \
+ ((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN))
+#define BTF_TYPE_ENC(name, info, size_or_type) \
+ (name), (info), (size_or_type)
+#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \
+ ((encoding) << 24 | (bits_offset) << 16 | (nr_bits))
+#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \
+ BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \
+ BTF_INT_ENC(encoding, bits_offset, bits)
+#define BTF_MEMBER_ENC(name, type, bits_offset) \
+ (name), (type), (bits_offset)
+
+struct btf_raw_data {
+ __u32 raw_types[64];
+ const char *str_sec;
+ __u32 str_sec_size;
+};
+
+/* struct bpf_spin_lock {
+ * int val;
+ * };
+ * struct val {
+ * int cnt;
+ * struct bpf_spin_lock l;
+ * };
+ */
+static const char btf_str_sec[] = "\0bpf_spin_lock\0val\0cnt\0l";
+static __u32 btf_raw_types[] = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ /* struct bpf_spin_lock */ /* [2] */
+ BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), 4),
+ BTF_MEMBER_ENC(15, 1, 0), /* int val; */
+ /* struct val */ /* [3] */
+ BTF_TYPE_ENC(15, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8),
+ BTF_MEMBER_ENC(19, 1, 0), /* int cnt; */
+ BTF_MEMBER_ENC(23, 2, 32),/* struct bpf_spin_lock l; */
+};
+
+static int load_btf(void)
+{
+ struct btf_header hdr = {
+ .magic = BTF_MAGIC,
+ .version = BTF_VERSION,
+ .hdr_len = sizeof(struct btf_header),
+ .type_len = sizeof(btf_raw_types),
+ .str_off = sizeof(btf_raw_types),
+ .str_len = sizeof(btf_str_sec),
+ };
+ void *ptr, *raw_btf;
+ int btf_fd;
+
+ ptr = raw_btf = malloc(sizeof(hdr) + sizeof(btf_raw_types) +
+ sizeof(btf_str_sec));
+
+ memcpy(ptr, &hdr, sizeof(hdr));
+ ptr += sizeof(hdr);
+ memcpy(ptr, btf_raw_types, hdr.type_len);
+ ptr += hdr.type_len;
+ memcpy(ptr, btf_str_sec, hdr.str_len);
+ ptr += hdr.str_len;
+
+ btf_fd = bpf_load_btf(raw_btf, ptr - raw_btf, 0, 0, 0);
+ free(raw_btf);
+ if (btf_fd < 0)
+ return -1;
+ return btf_fd;
+}
+
+static int create_map_spin_lock(void)
+{
+ struct bpf_create_map_attr attr = {
+ .name = "test_map",
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .key_size = 4,
+ .value_size = 8,
+ .max_entries = 1,
+ .btf_key_type_id = 1,
+ .btf_value_type_id = 3,
+ };
+ int fd, btf_fd;
+
+ btf_fd = load_btf();
+ if (btf_fd < 0)
+ return -1;
+ attr.btf_fd = btf_fd;
+ fd = bpf_create_map_xattr(&attr);
+ if (fd < 0)
+ printf("Failed to create map with spin_lock\n");
+ return fd;
+}
+
static char bpf_vlog[UINT_MAX >> 8];
static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
@@ -16681,6 +17130,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
int *fixup_map_in_map = test->fixup_map_in_map;
int *fixup_cgroup_storage = test->fixup_cgroup_storage;
int *fixup_percpu_cgroup_storage = test->fixup_percpu_cgroup_storage;
+ int *fixup_map_spin_lock = test->fixup_map_spin_lock;
if (test->fill_helper)
test->fill_helper(test);
@@ -16797,6 +17247,13 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
fixup_map_stacktrace++;
} while (*fixup_map_stacktrace);
}
+ if (*fixup_map_spin_lock) {
+ map_fds[13] = create_map_spin_lock();
+ do {
+ prog[*fixup_map_spin_lock].imm = map_fds[13];
+ fixup_map_spin_lock++;
+ } while (*fixup_map_spin_lock);
+ }
}
static int set_admin(bool admin)
--
2.20.0
^ permalink raw reply related
* [PATCH v5 bpf-next 1/9] bpf: introduce bpf_spin_lock
From: Alexei Starovoitov @ 2019-01-28 2:50 UTC (permalink / raw)
To: davem
Cc: daniel, peterz, jannh, paulmck, will.deacon, mingo, netdev,
kernel-team
In-Reply-To: <20190128025010.342241-1-ast@kernel.org>
Introduce 'struct bpf_spin_lock' and bpf_spin_lock/unlock() helpers to let
bpf program serialize access to other variables.
Example:
struct hash_elem {
int cnt;
struct bpf_spin_lock lock;
};
struct hash_elem * val = bpf_map_lookup_elem(&hash_map, &key);
if (val) {
bpf_spin_lock(&val->lock);
val->cnt++;
bpf_spin_unlock(&val->lock);
}
Restrictions and safety checks:
- bpf_spin_lock is only allowed inside HASH and ARRAY maps.
- BTF description of the map is mandatory for safety analysis.
- bpf program can take one bpf_spin_lock at a time, since two or more can
cause dead locks.
- only one 'struct bpf_spin_lock' is allowed per map element.
It drastically simplifies implementation yet allows bpf program to use
any number of bpf_spin_locks.
- when bpf_spin_lock is taken the calls (either bpf2bpf or helpers) are not allowed.
- bpf program must bpf_spin_unlock() before return.
- bpf program can access 'struct bpf_spin_lock' only via
bpf_spin_lock()/bpf_spin_unlock() helpers.
- load/store into 'struct bpf_spin_lock lock;' field is not allowed.
- to use bpf_spin_lock() helper the BTF description of map value must be
a struct and have 'struct bpf_spin_lock anyname;' field at the top level.
Nested lock inside another struct is not allowed.
- syscall map_lookup doesn't copy bpf_spin_lock field to user space.
- syscall map_update and program map_update do not update bpf_spin_lock field.
- bpf_spin_lock cannot be on the stack or inside networking packet.
bpf_spin_lock can only be inside HASH or ARRAY map value.
- bpf_spin_lock is available to root only and to all program types.
- bpf_spin_lock is not allowed in inner maps of map-in-map.
- ld_abs is not allowed inside spin_lock-ed region.
- tracing progs cannot use bpf_spin_lock yet due to insufficient preemption checks
- socket filter progs cannot use bpf_spin_lock due to missing preempt_disable
Implementation details:
- on !SMP bpf_spin_lock() becomes nop
- on architectures that don't support queued_spin_lock trivial lock is used.
Note that arch_spin_lock cannot be used, since not all archs agree that
zero == unlocked and sizeof(arch_spinlock_t) != sizeof(__u32).
- presence of bpf_spin_lock inside map value could have been indicated via
extra flag during map_create, but specifying it via BTF is cleaner.
It provides introspection for map key/value and reduces user coding mistakes.
Next steps:
- allow bpf_spin_lock in other map types (like cgroup local storage)
- introduce BPF_F_LOCK flag for bpf_map_update() syscall and helper
to request kernel to grab bpf_spin_lock before rewriting the value.
That will serialize access to map elements.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
include/linux/bpf.h | 37 +++++++-
include/linux/bpf_verifier.h | 1 +
include/linux/btf.h | 1 +
include/uapi/linux/bpf.h | 7 +-
kernel/bpf/arraymap.c | 7 +-
kernel/bpf/btf.c | 42 +++++++++
kernel/bpf/core.c | 2 +
kernel/bpf/hashtab.c | 21 +++--
kernel/bpf/helpers.c | 57 ++++++++++++
kernel/bpf/map_in_map.c | 5 ++
kernel/bpf/syscall.c | 21 ++++-
kernel/bpf/verifier.c | 169 ++++++++++++++++++++++++++++++++++-
net/core/filter.c | 16 +++-
13 files changed, 360 insertions(+), 26 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 3851529062ec..ee0352bd728f 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -72,14 +72,15 @@ struct bpf_map {
u32 value_size;
u32 max_entries;
u32 map_flags;
- u32 pages;
+ int spin_lock_off; /* >=0 valid offset, <0 error */
u32 id;
int numa_node;
u32 btf_key_type_id;
u32 btf_value_type_id;
struct btf *btf;
+ u32 pages;
bool unpriv_array;
- /* 55 bytes hole */
+ /* 51 bytes hole */
/* The 3rd and 4th cacheline with misc members to avoid false sharing
* particularly with refcounting.
@@ -91,6 +92,34 @@ struct bpf_map {
char name[BPF_OBJ_NAME_LEN];
};
+static inline bool map_value_has_spin_lock(const struct bpf_map *map)
+{
+ return map->spin_lock_off >= 0;
+}
+
+static inline void check_and_init_map_lock(struct bpf_map *map, void *dst)
+{
+ if (likely(!map_value_has_spin_lock(map)))
+ return;
+ *(struct bpf_spin_lock *)(dst + map->spin_lock_off) =
+ (struct bpf_spin_lock){};
+}
+
+/* copy everything but bpf_spin_lock */
+static inline void copy_map_value(struct bpf_map *map, void *dst, void *src)
+{
+ if (unlikely(map_value_has_spin_lock(map))) {
+ u32 off = map->spin_lock_off;
+
+ memcpy(dst, src, off);
+ memcpy(dst + off + sizeof(struct bpf_spin_lock),
+ src + off + sizeof(struct bpf_spin_lock),
+ map->value_size - off - sizeof(struct bpf_spin_lock));
+ } else {
+ memcpy(dst, src, map->value_size);
+ }
+}
+
struct bpf_offload_dev;
struct bpf_offloaded_map;
@@ -162,6 +191,7 @@ enum bpf_arg_type {
ARG_PTR_TO_CTX, /* pointer to context */
ARG_ANYTHING, /* any (initialized) argument is ok */
ARG_PTR_TO_SOCKET, /* pointer to bpf_sock */
+ ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */
};
/* type of values returned from helper functions */
@@ -876,7 +906,8 @@ extern const struct bpf_func_proto bpf_msg_redirect_hash_proto;
extern const struct bpf_func_proto bpf_msg_redirect_map_proto;
extern const struct bpf_func_proto bpf_sk_redirect_hash_proto;
extern const struct bpf_func_proto bpf_sk_redirect_map_proto;
-
+extern const struct bpf_func_proto bpf_spin_lock_proto;
+extern const struct bpf_func_proto bpf_spin_unlock_proto;
extern const struct bpf_func_proto bpf_get_local_storage_proto;
/* Shared helpers among cBPF and eBPF. */
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 0620e418dde5..69f7a3449eda 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -148,6 +148,7 @@ struct bpf_verifier_state {
/* call stack tracking */
struct bpf_func_state *frame[MAX_CALL_FRAMES];
u32 curframe;
+ u32 active_spin_lock;
bool speculative;
};
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 12502e25e767..455d31b55828 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -50,6 +50,7 @@ u32 btf_id(const struct btf *btf);
bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
const struct btf_member *m,
u32 expected_offset, u32 expected_size);
+int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t);
#ifdef CONFIG_BPF_SYSCALL
const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 60b99b730a41..86f7c438d40f 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2422,7 +2422,9 @@ union bpf_attr {
FN(map_peek_elem), \
FN(msg_push_data), \
FN(msg_pop_data), \
- FN(rc_pointer_rel),
+ FN(rc_pointer_rel), \
+ FN(spin_lock), \
+ FN(spin_unlock),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
@@ -3056,4 +3058,7 @@ struct bpf_line_info {
__u32 line_col;
};
+struct bpf_spin_lock {
+ __u32 val;
+};
#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 25632a75d630..d6d979910a2a 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -270,9 +270,10 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
memcpy(this_cpu_ptr(array->pptrs[index & array->index_mask]),
value, map->value_size);
else
- memcpy(array->value +
- array->elem_size * (index & array->index_mask),
- value, map->value_size);
+ copy_map_value(map,
+ array->value +
+ array->elem_size * (index & array->index_mask),
+ value);
return 0;
}
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 022ef9ca1296..03b1a7a6195c 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -355,6 +355,11 @@ static bool btf_type_is_struct(const struct btf_type *t)
return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION;
}
+static bool __btf_type_is_struct(const struct btf_type *t)
+{
+ return BTF_INFO_KIND(t->info) == BTF_KIND_STRUCT;
+}
+
static bool btf_type_is_array(const struct btf_type *t)
{
return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY;
@@ -2045,6 +2050,43 @@ static void btf_struct_log(struct btf_verifier_env *env,
btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t));
}
+/* find 'struct bpf_spin_lock' in map value.
+ * return >= 0 offset if found
+ * and < 0 in case of error
+ */
+int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t)
+{
+ const struct btf_member *member;
+ u32 i, off = -ENOENT;
+
+ if (!__btf_type_is_struct(t))
+ return -EINVAL;
+
+ for_each_member(i, t, member) {
+ const struct btf_type *member_type = btf_type_by_id(btf,
+ member->type);
+ if (!__btf_type_is_struct(member_type))
+ continue;
+ if (member_type->size != sizeof(struct bpf_spin_lock))
+ continue;
+ if (strcmp(__btf_name_by_offset(btf, member_type->name_off),
+ "bpf_spin_lock"))
+ continue;
+ if (off != -ENOENT)
+ /* only one 'struct bpf_spin_lock' is allowed */
+ return -E2BIG;
+ off = btf_member_bit_offset(t, member);
+ if (off % 8)
+ /* valid C code cannot generate such BTF */
+ return -EINVAL;
+ off /= 8;
+ if (off % __alignof__(struct bpf_spin_lock))
+ /* valid struct bpf_spin_lock will be 4 byte aligned */
+ return -EINVAL;
+ }
+ return off;
+}
+
static void btf_struct_seq_show(const struct btf *btf, const struct btf_type *t,
u32 type_id, void *data, u8 bits_offset,
struct seq_file *m)
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index a7bcb23bee84..550d9f9298f3 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2001,6 +2001,8 @@ const struct bpf_func_proto bpf_map_delete_elem_proto __weak;
const struct bpf_func_proto bpf_map_push_elem_proto __weak;
const struct bpf_func_proto bpf_map_pop_elem_proto __weak;
const struct bpf_func_proto bpf_map_peek_elem_proto __weak;
+const struct bpf_func_proto bpf_spin_lock_proto __weak;
+const struct bpf_func_proto bpf_spin_unlock_proto __weak;
const struct bpf_func_proto bpf_get_prandom_u32_proto __weak;
const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak;
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 4b7c76765d9d..6d3b22c5ad68 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -718,21 +718,12 @@ static bool fd_htab_map_needs_adjust(const struct bpf_htab *htab)
BITS_PER_LONG == 64;
}
-static u32 htab_size_value(const struct bpf_htab *htab, bool percpu)
-{
- u32 size = htab->map.value_size;
-
- if (percpu || fd_htab_map_needs_adjust(htab))
- size = round_up(size, 8);
- return size;
-}
-
static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
void *value, u32 key_size, u32 hash,
bool percpu, bool onallcpus,
struct htab_elem *old_elem)
{
- u32 size = htab_size_value(htab, percpu);
+ u32 size = htab->map.value_size;
bool prealloc = htab_is_prealloc(htab);
struct htab_elem *l_new, **pl_new;
void __percpu *pptr;
@@ -770,10 +761,13 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
l_new = ERR_PTR(-ENOMEM);
goto dec_count;
}
+ check_and_init_map_lock(&htab->map,
+ l_new->key + round_up(key_size, 8));
}
memcpy(l_new->key, key, key_size);
if (percpu) {
+ size = round_up(size, 8);
if (prealloc) {
pptr = htab_elem_get_ptr(l_new, key_size);
} else {
@@ -791,8 +785,13 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
if (!prealloc)
htab_elem_set_ptr(l_new, key_size, pptr);
- } else {
+ } else if (fd_htab_map_needs_adjust(htab)) {
+ size = round_up(size, 8);
memcpy(l_new->key + round_up(key_size, 8), value, size);
+ } else {
+ copy_map_value(&htab->map,
+ l_new->key + round_up(key_size, 8),
+ value);
}
l_new->hash = hash;
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index a74972b07e74..e1d6aefbab50 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -221,6 +221,63 @@ const struct bpf_func_proto bpf_get_current_comm_proto = {
.arg2_type = ARG_CONST_SIZE,
};
+#ifndef CONFIG_QUEUED_SPINLOCKS
+struct dumb_spin_lock {
+ atomic_t val;
+};
+#endif
+
+notrace BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock)
+{
+#if defined(CONFIG_SMP)
+#ifdef CONFIG_QUEUED_SPINLOCKS
+ struct qspinlock *qlock = (void *)lock;
+
+ BUILD_BUG_ON(sizeof(*qlock) != sizeof(*lock));
+ queued_spin_lock(qlock);
+#else
+ struct dumb_spin_lock *qlock = (void *)lock;
+
+ BUILD_BUG_ON(sizeof(*qlock) != sizeof(*lock));
+ do {
+ while (atomic_read(&qlock->val) != 0)
+ cpu_relax();
+ } while (atomic_cmpxchg(&qlock->val, 0, 1) != 0);
+#endif
+#endif
+ return 0;
+}
+
+const struct bpf_func_proto bpf_spin_lock_proto = {
+ .func = bpf_spin_lock,
+ .gpl_only = false,
+ .ret_type = RET_VOID,
+ .arg1_type = ARG_PTR_TO_SPIN_LOCK,
+};
+
+notrace BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock)
+{
+#if defined(CONFIG_SMP)
+#ifdef CONFIG_QUEUED_SPINLOCKS
+ struct qspinlock *qlock = (void *)lock;
+
+ queued_spin_unlock(qlock);
+#else
+ struct dumb_spin_lock *qlock = (void *)lock;
+
+ atomic_set_release(&qlock->val, 0);
+#endif
+#endif
+ return 0;
+}
+
+const struct bpf_func_proto bpf_spin_unlock_proto = {
+ .func = bpf_spin_unlock,
+ .gpl_only = false,
+ .ret_type = RET_VOID,
+ .arg1_type = ARG_PTR_TO_SPIN_LOCK,
+};
+
#ifdef CONFIG_CGROUPS
BPF_CALL_0(bpf_get_current_cgroup_id)
{
diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
index 99d243e1ad6e..920eff1b677b 100644
--- a/kernel/bpf/map_in_map.c
+++ b/kernel/bpf/map_in_map.c
@@ -36,6 +36,11 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
return ERR_PTR(-EINVAL);
}
+ if (map_value_has_spin_lock(inner_map)) {
+ fdput(f);
+ return ERR_PTR(-ENOTSUPP);
+ }
+
inner_map_meta = kzalloc(sizeof(*inner_map_meta), GFP_USER);
if (!inner_map_meta) {
fdput(f);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index b155cd17c1bd..ebf0a673cb83 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -463,7 +463,7 @@ int map_check_no_btf(const struct bpf_map *map,
return -ENOTSUPP;
}
-static int map_check_btf(const struct bpf_map *map, const struct btf *btf,
+static int map_check_btf(struct bpf_map *map, const struct btf *btf,
u32 btf_key_id, u32 btf_value_id)
{
const struct btf_type *key_type, *value_type;
@@ -478,6 +478,21 @@ static int map_check_btf(const struct bpf_map *map, const struct btf *btf,
if (!value_type || value_size != map->value_size)
return -EINVAL;
+ map->spin_lock_off = btf_find_spin_lock(btf, value_type);
+
+ if (map_value_has_spin_lock(map)) {
+ if (map->map_type != BPF_MAP_TYPE_HASH &&
+ map->map_type != BPF_MAP_TYPE_ARRAY)
+ return -ENOTSUPP;
+ if (map->spin_lock_off + sizeof(struct bpf_spin_lock) >
+ map->value_size) {
+ WARN_ONCE(1,
+ "verifier bug spin_lock_off %d value_size %d\n",
+ map->spin_lock_off, map->value_size);
+ return -EFAULT;
+ }
+ }
+
if (map->ops->map_check_btf)
ret = map->ops->map_check_btf(map, btf, key_type, value_type);
@@ -542,6 +557,8 @@ static int map_create(union bpf_attr *attr)
map->btf = btf;
map->btf_key_type_id = attr->btf_key_type_id;
map->btf_value_type_id = attr->btf_value_type_id;
+ } else {
+ map->spin_lock_off = -EINVAL;
}
err = security_bpf_map_alloc(map);
@@ -740,7 +757,7 @@ static int map_lookup_elem(union bpf_attr *attr)
err = -ENOENT;
} else {
err = 0;
- memcpy(value, ptr, value_size);
+ copy_map_value(map, value, ptr);
}
rcu_read_unlock();
}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 8c1c21cd50b4..b6af9d2cb236 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -213,6 +213,7 @@ struct bpf_call_arg_meta {
s64 msize_smax_value;
u64 msize_umax_value;
int ptr_id;
+ int func_id;
};
static DEFINE_MUTEX(bpf_verifier_lock);
@@ -351,6 +352,12 @@ static bool reg_is_refcounted(const struct bpf_reg_state *reg)
return type_is_refcounted(reg->type);
}
+static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
+{
+ return reg->type == PTR_TO_MAP_VALUE &&
+ map_value_has_spin_lock(reg->map_ptr);
+}
+
static bool reg_is_refcounted_or_null(const struct bpf_reg_state *reg)
{
return type_is_refcounted_or_null(reg->type);
@@ -712,6 +719,7 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
}
dst_state->speculative = src->speculative;
dst_state->curframe = src->curframe;
+ dst_state->active_spin_lock = src->active_spin_lock;
for (i = 0; i <= src->curframe; i++) {
dst = dst_state->frame[i];
if (!dst) {
@@ -1483,6 +1491,21 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
if (err)
verbose(env, "R%d max value is outside of the array range\n",
regno);
+
+ if (map_value_has_spin_lock(reg->map_ptr)) {
+ u32 lock = reg->map_ptr->spin_lock_off;
+
+ /* if any part of struct bpf_spin_lock can be touched by
+ * load/store reject this program
+ */
+ if ((reg->smin_value + off <= lock &&
+ lock < reg->umax_value + off + size) ||
+ (reg->smin_value + off < lock + sizeof(struct bpf_spin_lock) &&
+ lock + sizeof(struct bpf_spin_lock) <= reg->umax_value + off + size)) {
+ verbose(env, "bpf_spin_lock cannot be accessed directly by load/store\n");
+ return -EACCES;
+ }
+ }
return err;
}
@@ -2192,6 +2215,91 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
}
}
+/* Implementation details:
+ * bpf_map_lookup returns PTR_TO_MAP_VALUE_OR_NULL
+ * Two bpf_map_lookups (even with the same key) will have different reg->id.
+ * For traditional PTR_TO_MAP_VALUE the verifier clears reg->id after
+ * value_or_null->value transition, since the verifier only cares about
+ * the range of access to valid map value pointer and doesn't care about actual
+ * address of the map element.
+ * For maps with 'struct bpf_spin_lock' inside map value the verifier keeps
+ * reg->id > 0 after value_or_null->value transition. By doing so
+ * two bpf_map_lookups will be considered two different pointers that
+ * point to different bpf_spin_locks.
+ * The verifier allows taking only one bpf_spin_lock at a time to avoid
+ * dead-locks.
+ * Since only one bpf_spin_lock is allowed the checks are simpler than
+ * reg_is_refcounted() logic. The verifier needs to remember only
+ * one spin_lock instead of array of acquired_refs.
+ * cur_state->active_spin_lock remembers which map value element got locked
+ * and clears it after bpf_spin_unlock.
+ */
+static int process_spin_lock(struct bpf_verifier_env *env, int regno,
+ bool is_lock)
+{
+ struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno];
+ struct bpf_verifier_state *cur = env->cur_state;
+ bool is_const = tnum_is_const(reg->var_off);
+ struct bpf_map *map = reg->map_ptr;
+ u64 val = reg->var_off.value;
+
+ if (reg->type != PTR_TO_MAP_VALUE) {
+ verbose(env, "R%d is not a pointer to map_value\n", regno);
+ return -EINVAL;
+ }
+ if (!is_const) {
+ verbose(env,
+ "R%d doesn't have constant offset. bpf_spin_lock has to be at the constant offset\n",
+ regno);
+ return -EINVAL;
+ }
+ if (!map->btf) {
+ verbose(env,
+ "map '%s' has to have BTF in order to use bpf_spin_lock\n",
+ map->name);
+ return -EINVAL;
+ }
+ if (!map_value_has_spin_lock(map)) {
+ if (map->spin_lock_off == -E2BIG)
+ verbose(env,
+ "map '%s' has more than one 'struct bpf_spin_lock'\n",
+ map->name);
+ else if (map->spin_lock_off == -ENOENT)
+ verbose(env,
+ "map '%s' doesn't have 'struct bpf_spin_lock'\n",
+ map->name);
+ else
+ verbose(env,
+ "map '%s' is not a struct type or bpf_spin_lock is mangled\n",
+ map->name);
+ return -EINVAL;
+ }
+ if (map->spin_lock_off != val + reg->off) {
+ verbose(env, "off %lld doesn't point to 'struct bpf_spin_lock'\n",
+ val + reg->off);
+ return -EINVAL;
+ }
+ if (is_lock) {
+ if (cur->active_spin_lock) {
+ verbose(env,
+ "Locking two bpf_spin_locks are not allowed\n");
+ return -EINVAL;
+ }
+ cur->active_spin_lock = reg->id;
+ } else {
+ if (!cur->active_spin_lock) {
+ verbose(env, "bpf_spin_unlock without taking a lock\n");
+ return -EINVAL;
+ }
+ if (cur->active_spin_lock != reg->id) {
+ verbose(env, "bpf_spin_unlock of different lock\n");
+ return -EINVAL;
+ }
+ cur->active_spin_lock = 0;
+ }
+ return 0;
+}
+
static bool arg_type_is_mem_ptr(enum bpf_arg_type type)
{
return type == ARG_PTR_TO_MEM ||
@@ -2268,6 +2376,17 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
return -EFAULT;
}
meta->ptr_id = reg->id;
+ } else if (arg_type == ARG_PTR_TO_SPIN_LOCK) {
+ if (meta->func_id == BPF_FUNC_spin_lock) {
+ if (process_spin_lock(env, regno, true))
+ return -EACCES;
+ } else if (meta->func_id == BPF_FUNC_spin_unlock) {
+ if (process_spin_lock(env, regno, false))
+ return -EACCES;
+ } else {
+ verbose(env, "verifier internal error\n");
+ return -EFAULT;
+ }
} else if (arg_type_is_mem_ptr(arg_type)) {
expected_type = PTR_TO_STACK;
/* One exception here. In case function allows for NULL to be
@@ -2887,6 +3006,7 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
return err;
}
+ meta.func_id = func_id;
/* check args */
err = check_func_arg(env, BPF_REG_1, fn->arg1_type, &meta);
if (err)
@@ -4473,7 +4593,8 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state,
} else if (reg->type == PTR_TO_SOCKET_OR_NULL) {
reg->type = PTR_TO_SOCKET;
}
- if (is_null || !reg_is_refcounted(reg)) {
+ if (is_null || !(reg_is_refcounted(reg) ||
+ reg_may_point_to_spin_lock(reg))) {
/* We don't need id from this point onwards anymore,
* thus we should better reset it, so that state
* pruning has chances to take effect.
@@ -4871,6 +4992,11 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
return err;
}
+ if (env->cur_state->active_spin_lock) {
+ verbose(env, "BPF_LD_[ABS|IND] cannot be used inside bpf_spin_lock-ed region\n");
+ return -EINVAL;
+ }
+
if (regs[BPF_REG_6].type != PTR_TO_CTX) {
verbose(env,
"at the time of BPF_LD_ABS|IND R6 != pointer to skb\n");
@@ -5607,8 +5733,11 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
case PTR_TO_MAP_VALUE:
/* If the new min/max/var_off satisfy the old ones and
* everything else matches, we are OK.
- * We don't care about the 'id' value, because nothing
- * uses it for PTR_TO_MAP_VALUE (only for ..._OR_NULL)
+ * 'id' is not compared, since it's only used for maps with
+ * bpf_spin_lock inside map element and in such cases if
+ * the rest of the prog is valid for one map element then
+ * it's valid for all map elements regardless of the key
+ * used in bpf_map_lookup()
*/
return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 &&
range_within(rold, rcur) &&
@@ -5811,6 +5940,9 @@ static bool states_equal(struct bpf_verifier_env *env,
if (old->speculative && !cur->speculative)
return false;
+ if (old->active_spin_lock != cur->active_spin_lock)
+ return false;
+
/* for states to be equal callsites have to be the same
* and all frame states need to be equivalent
*/
@@ -6229,6 +6361,12 @@ static int do_check(struct bpf_verifier_env *env)
return -EINVAL;
}
+ if (env->cur_state->active_spin_lock &&
+ (insn->src_reg == BPF_PSEUDO_CALL ||
+ insn->imm != BPF_FUNC_spin_unlock)) {
+ verbose(env, "function calls are not allowed while holding a lock\n");
+ return -EINVAL;
+ }
if (insn->src_reg == BPF_PSEUDO_CALL)
err = check_func_call(env, insn, &env->insn_idx);
else
@@ -6259,6 +6397,11 @@ static int do_check(struct bpf_verifier_env *env)
return -EINVAL;
}
+ if (env->cur_state->active_spin_lock) {
+ verbose(env, "bpf_spin_unlock is missing\n");
+ return -EINVAL;
+ }
+
if (state->curframe) {
/* exit from nested function */
env->prev_insn_idx = env->insn_idx;
@@ -6356,6 +6499,19 @@ static int check_map_prealloc(struct bpf_map *map)
!(map->map_flags & BPF_F_NO_PREALLOC);
}
+static bool is_tracing_prog_type(enum bpf_prog_type type)
+{
+ switch (type) {
+ case BPF_PROG_TYPE_KPROBE:
+ case BPF_PROG_TYPE_TRACEPOINT:
+ case BPF_PROG_TYPE_PERF_EVENT:
+ case BPF_PROG_TYPE_RAW_TRACEPOINT:
+ return true;
+ default:
+ return false;
+ }
+}
+
static int check_map_prog_compatibility(struct bpf_verifier_env *env,
struct bpf_map *map,
struct bpf_prog *prog)
@@ -6378,6 +6534,13 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
}
}
+ if ((is_tracing_prog_type(prog->type) ||
+ prog->type == BPF_PROG_TYPE_SOCKET_FILTER) &&
+ map_value_has_spin_lock(map)) {
+ verbose(env, "tracing progs cannot use bpf_spin_lock yet\n");
+ return -EINVAL;
+ }
+
if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) &&
!bpf_offload_prog_map_match(prog, map)) {
verbose(env, "offload device mismatch between prog and map\n");
diff --git a/net/core/filter.c b/net/core/filter.c
index 8e587dd1da20..9cde260d5022 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5306,10 +5306,20 @@ bpf_base_func_proto(enum bpf_func_id func_id)
return &bpf_tail_call_proto;
case BPF_FUNC_ktime_get_ns:
return &bpf_ktime_get_ns_proto;
+ default:
+ break;
+ }
+
+ if (!capable(CAP_SYS_ADMIN))
+ return NULL;
+
+ switch (func_id) {
+ case BPF_FUNC_spin_lock:
+ return &bpf_spin_lock_proto;
+ case BPF_FUNC_spin_unlock:
+ return &bpf_spin_unlock_proto;
case BPF_FUNC_trace_printk:
- if (capable(CAP_SYS_ADMIN))
- return bpf_get_trace_printk_proto();
- /* else: fall through */
+ return bpf_get_trace_printk_proto();
default:
return NULL;
}
--
2.20.0
^ permalink raw reply related
* [PATCH v5 bpf-next 0/9] introduce bpf_spin_lock
From: Alexei Starovoitov @ 2019-01-28 2:50 UTC (permalink / raw)
To: davem
Cc: daniel, peterz, jannh, paulmck, will.deacon, mingo, netdev,
kernel-team
Many algorithms need to read and modify several variables atomically.
Until now it was hard to impossible to implement such algorithms in BPF.
Hence introduce support for bpf_spin_lock.
The api consists of 'struct bpf_spin_lock' that should be placed
inside hash/array/cgroup_local_storage element
and bpf_spin_lock/unlock() helper function.
Example:
struct hash_elem {
int cnt;
struct bpf_spin_lock lock;
};
struct hash_elem * val = bpf_map_lookup_elem(&hash_map, &key);
if (val) {
bpf_spin_lock(&val->lock);
val->cnt++;
bpf_spin_unlock(&val->lock);
}
and BPF_F_LOCK flag for lookup/update bpf syscall commands that
allows user space to read/write map elements under lock.
Together these primitives allow race free access to map elements
from bpf programs and from user space.
Key restriction: root only.
Key requirement: maps must be annotated with BTF.
This concept was discussed at Linux Plumbers Conference 2018.
Thank you everyone who participated and helped to iron out details
of api and implementation.
Patch 1: bpf_spin_lock support in the verifier, BTF, hash, array.
Patch 2: bpf_spin_lock in cgroup local storage.
Patches 3,4,5: tests
Patch 6: BPF_F_LOCK flag to lookup/update
Patches 7,8,9: tests
v4->v5:
- disallow bpf_spin_lock for tracing progs due to insufficient preemption checks
- socket filter progs cannot use bpf_spin_lock due to missing preempt_disable
The preemption related fixes will be submitted separately.
Eventually bpf_spin_lock will be available for tracing progs as well.
Never to NMI progs.
- fix atomic_set_release. Spotted by Peter.
- fixed hash_of_maps
v3->v4:
- fix BPF_EXIST | BPF_NOEXIST check patch 6. Spotted by Jakub. Thanks!
- rebase
v2->v3:
- fixed build on ia64 and archs where qspinlock is not supported
- fixed missing lock init during lookup w/o BPF_F_LOCK. Spotted by Martin
v1->v2:
- addressed several issues spotted by Daniel and Martin in patch 1
- added test11 to patch 4 as suggested by Daniel
Alexei Starovoitov (9):
bpf: introduce bpf_spin_lock
bpf: add support for bpf_spin_lock to cgroup local storage
tools/bpf: sync include/uapi/linux/bpf.h
selftests/bpf: add bpf_spin_lock tests
selftests/bpf: add bpf_spin_lock C test
bpf: introduce BPF_F_LOCK flag
tools/bpf: sync uapi/bpf.h
libbpf: introduce bpf_map_lookup_elem_flags()
selftests/bpf: test for BPF_F_LOCK
include/linux/bpf.h | 39 +-
include/linux/bpf_verifier.h | 1 +
include/linux/btf.h | 1 +
include/uapi/linux/bpf.h | 8 +-
kernel/bpf/arraymap.c | 23 +-
kernel/bpf/btf.c | 42 ++
kernel/bpf/core.c | 2 +
kernel/bpf/hashtab.c | 63 ++-
kernel/bpf/helpers.c | 71 +++
kernel/bpf/local_storage.c | 16 +-
kernel/bpf/map_in_map.c | 5 +
kernel/bpf/syscall.c | 45 +-
kernel/bpf/verifier.c | 171 ++++++-
net/core/filter.c | 16 +-
tools/include/uapi/linux/bpf.h | 8 +-
tools/lib/bpf/bpf.c | 13 +
tools/lib/bpf/bpf.h | 2 +
tools/lib/bpf/libbpf.map | 1 +
tools/testing/selftests/bpf/Makefile | 2 +-
tools/testing/selftests/bpf/bpf_helpers.h | 4 +
tools/testing/selftests/bpf/test_map_lock.c | 66 +++
tools/testing/selftests/bpf/test_progs.c | 117 ++++-
tools/testing/selftests/bpf/test_spin_lock.c | 108 +++++
tools/testing/selftests/bpf/test_verifier.c | 459 ++++++++++++++++++-
24 files changed, 1244 insertions(+), 39 deletions(-)
create mode 100644 tools/testing/selftests/bpf/test_map_lock.c
create mode 100644 tools/testing/selftests/bpf/test_spin_lock.c
--
2.20.0
^ permalink raw reply
* [PATCH v5 bpf-next 6/9] bpf: introduce BPF_F_LOCK flag
From: Alexei Starovoitov @ 2019-01-28 2:50 UTC (permalink / raw)
To: davem
Cc: daniel, peterz, jannh, paulmck, will.deacon, mingo, netdev,
kernel-team
In-Reply-To: <20190128025010.342241-1-ast@kernel.org>
Introduce BPF_F_LOCK flag for map_lookup and map_update syscall commands
and for map_update() helper function.
In all these cases take a lock of existing element (which was provided
in BTF description) before copying (in or out) the rest of map value.
Implementation details that are part of uapi:
Array:
The array map takes the element lock for lookup/update.
Hash:
hash map also takes the lock for lookup/update and tries to avoid the bucket lock.
If old element exists it takes the element lock and updates the element in place.
If element doesn't exist it allocates new one and inserts into hash table
while holding the bucket lock.
In rare case the hashmap has to take both the bucket lock and the element lock
to update old value in place.
Cgroup local storage:
It is similar to array. update in place and lookup are done with lock taken.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
include/linux/bpf.h | 2 ++
include/uapi/linux/bpf.h | 1 +
kernel/bpf/arraymap.c | 24 ++++++++++++++--------
kernel/bpf/hashtab.c | 42 +++++++++++++++++++++++++++++++++++---
kernel/bpf/helpers.c | 14 +++++++++++++
kernel/bpf/local_storage.c | 14 ++++++++++++-
kernel/bpf/syscall.c | 25 +++++++++++++++++++++--
7 files changed, 108 insertions(+), 14 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index ee0352bd728f..34a517137b63 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -119,6 +119,8 @@ static inline void copy_map_value(struct bpf_map *map, void *dst, void *src)
memcpy(dst, src, map->value_size);
}
}
+void copy_map_value_locked(struct bpf_map *map, void *dst, void *src,
+ bool lock_src);
struct bpf_offload_dev;
struct bpf_offloaded_map;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 86f7c438d40f..1777fa0c61e4 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -267,6 +267,7 @@ enum bpf_attach_type {
#define BPF_ANY 0 /* create new element or update existing */
#define BPF_NOEXIST 1 /* create new element if it didn't exist */
#define BPF_EXIST 2 /* update existing element */
+#define BPF_F_LOCK 4 /* spin_lock-ed map_lookup/map_update */
/* flags for BPF_MAP_CREATE command */
#define BPF_F_NO_PREALLOC (1U << 0)
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index d6d979910a2a..c72e0d8e1e65 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -253,8 +253,9 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
+ char *val;
- if (unlikely(map_flags > BPF_EXIST))
+ if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST))
/* unknown flags */
return -EINVAL;
@@ -262,18 +263,25 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
/* all elements were pre-allocated, cannot insert a new one */
return -E2BIG;
- if (unlikely(map_flags == BPF_NOEXIST))
+ if (unlikely(map_flags & BPF_NOEXIST))
/* all elements already exist */
return -EEXIST;
- if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
+ if (unlikely((map_flags & BPF_F_LOCK) &&
+ !map_value_has_spin_lock(map)))
+ return -EINVAL;
+
+ if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
memcpy(this_cpu_ptr(array->pptrs[index & array->index_mask]),
value, map->value_size);
- else
- copy_map_value(map,
- array->value +
- array->elem_size * (index & array->index_mask),
- value);
+ } else {
+ val = array->value +
+ array->elem_size * (index & array->index_mask);
+ if (map_flags & BPF_F_LOCK)
+ copy_map_value_locked(map, val, value, false);
+ else
+ copy_map_value(map, val, value);
+ }
return 0;
}
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 6d3b22c5ad68..937776531998 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -804,11 +804,11 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old,
u64 map_flags)
{
- if (l_old && map_flags == BPF_NOEXIST)
+ if (l_old && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST)
/* elem already exists */
return -EEXIST;
- if (!l_old && map_flags == BPF_EXIST)
+ if (!l_old && (map_flags & ~BPF_F_LOCK) == BPF_EXIST)
/* elem doesn't exist, cannot update it */
return -ENOENT;
@@ -827,7 +827,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
u32 key_size, hash;
int ret;
- if (unlikely(map_flags > BPF_EXIST))
+ if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST))
/* unknown flags */
return -EINVAL;
@@ -840,6 +840,28 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
b = __select_bucket(htab, hash);
head = &b->head;
+ if (unlikely(map_flags & BPF_F_LOCK)) {
+ if (unlikely(!map_value_has_spin_lock(map)))
+ return -EINVAL;
+ /* find an element without taking the bucket lock */
+ l_old = lookup_nulls_elem_raw(head, hash, key, key_size,
+ htab->n_buckets);
+ ret = check_flags(htab, l_old, map_flags);
+ if (ret)
+ return ret;
+ if (l_old) {
+ /* grab the element lock and update value in place */
+ copy_map_value_locked(map,
+ l_old->key + round_up(key_size, 8),
+ value, false);
+ return 0;
+ }
+ /* fall through, grab the bucket lock and lookup again.
+ * 99.9% chance that the element won't be found,
+ * but second lookup under lock has to be done.
+ */
+ }
+
/* bpf_map_update_elem() can be called in_irq() */
raw_spin_lock_irqsave(&b->lock, flags);
@@ -849,6 +871,20 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
if (ret)
goto err;
+ if (unlikely(l_old && (map_flags & BPF_F_LOCK))) {
+ /* first lookup without the bucket lock didn't find the element,
+ * but second lookup with the bucket lock found it.
+ * This case is highly unlikely, but has to be dealt with:
+ * grab the element lock in addition to the bucket lock
+ * and update element in place
+ */
+ copy_map_value_locked(map,
+ l_old->key + round_up(key_size, 8),
+ value, false);
+ ret = 0;
+ goto err;
+ }
+
l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false,
l_old);
if (IS_ERR(l_new)) {
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index e1d6aefbab50..9186ac509606 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -278,6 +278,20 @@ const struct bpf_func_proto bpf_spin_unlock_proto = {
.arg1_type = ARG_PTR_TO_SPIN_LOCK,
};
+void copy_map_value_locked(struct bpf_map *map, void *dst, void *src,
+ bool lock_src)
+{
+ struct bpf_spin_lock *lock;
+
+ if (lock_src)
+ lock = src + map->spin_lock_off;
+ else
+ lock = dst + map->spin_lock_off;
+ ____bpf_spin_lock(lock);
+ copy_map_value(map, dst, src);
+ ____bpf_spin_unlock(lock);
+}
+
#ifdef CONFIG_CGROUPS
BPF_CALL_0(bpf_get_current_cgroup_id)
{
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 0295427f06e2..6b572e2de7fb 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -131,7 +131,14 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key,
struct bpf_cgroup_storage *storage;
struct bpf_storage_buffer *new;
- if (flags != BPF_ANY && flags != BPF_EXIST)
+ if (unlikely(flags & ~(BPF_F_LOCK | BPF_EXIST | BPF_NOEXIST)))
+ return -EINVAL;
+
+ if (unlikely(flags & BPF_NOEXIST))
+ return -EINVAL;
+
+ if (unlikely((flags & BPF_F_LOCK) &&
+ !map_value_has_spin_lock(map)))
return -EINVAL;
storage = cgroup_storage_lookup((struct bpf_cgroup_storage_map *)map,
@@ -139,6 +146,11 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key,
if (!storage)
return -ENOENT;
+ if (flags & BPF_F_LOCK) {
+ copy_map_value_locked(map, storage->buf->data, value, false);
+ return 0;
+ }
+
new = kmalloc_node(sizeof(struct bpf_storage_buffer) +
map->value_size,
__GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index b29e6dc44650..0834958f1dc4 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -682,7 +682,7 @@ static void *__bpf_copy_key(void __user *ukey, u64 key_size)
}
/* last field in 'union bpf_attr' used by this command */
-#define BPF_MAP_LOOKUP_ELEM_LAST_FIELD value
+#define BPF_MAP_LOOKUP_ELEM_LAST_FIELD flags
static int map_lookup_elem(union bpf_attr *attr)
{
@@ -698,6 +698,9 @@ static int map_lookup_elem(union bpf_attr *attr)
if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM))
return -EINVAL;
+ if (attr->flags & ~BPF_F_LOCK)
+ return -EINVAL;
+
f = fdget(ufd);
map = __bpf_map_get(f);
if (IS_ERR(map))
@@ -708,6 +711,12 @@ static int map_lookup_elem(union bpf_attr *attr)
goto err_put;
}
+ if ((attr->flags & BPF_F_LOCK) &&
+ !map_value_has_spin_lock(map)) {
+ err = -EINVAL;
+ goto err_put;
+ }
+
key = __bpf_copy_key(ukey, map->key_size);
if (IS_ERR(key)) {
err = PTR_ERR(key);
@@ -758,7 +767,13 @@ static int map_lookup_elem(union bpf_attr *attr)
err = -ENOENT;
} else {
err = 0;
- copy_map_value(map, value, ptr);
+ if (attr->flags & BPF_F_LOCK)
+ /* lock 'ptr' and copy everything but lock */
+ copy_map_value_locked(map, value, ptr, true);
+ else
+ copy_map_value(map, value, ptr);
+ /* mask lock, since value wasn't zero inited */
+ check_and_init_map_lock(map, value);
}
rcu_read_unlock();
}
@@ -818,6 +833,12 @@ static int map_update_elem(union bpf_attr *attr)
goto err_put;
}
+ if ((attr->flags & BPF_F_LOCK) &&
+ !map_value_has_spin_lock(map)) {
+ err = -EINVAL;
+ goto err_put;
+ }
+
key = __bpf_copy_key(ukey, map->key_size);
if (IS_ERR(key)) {
err = PTR_ERR(key);
--
2.20.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox