From: Steffen Klassert steffen.klassert@secunet.com
[ Upstream commit 07bf7908950a8b14e81aa1807e3c667eab39287a ]
We don't validate the address prefix lengths in the xfrm selector we got from userspace. This can lead to undefined behaviour in the address matching functions if the prefix is too big for the given address family. Fix this by checking the prefixes and refuse SA/policy insertation when a prefix is invalid.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Air Icy icytxw@gmail.com Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/xfrm/xfrm_user.c | 12 ++++++++++++ 1 file changed, 12 insertions(+)
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 5554d28a32eb..4292347bf45e 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -151,10 +151,16 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, err = -EINVAL; switch (p->family) { case AF_INET: + if (p->sel.prefixlen_d > 32 || p->sel.prefixlen_s > 32) + goto out; + break;
case AF_INET6: #if IS_ENABLED(CONFIG_IPV6) + if (p->sel.prefixlen_d > 128 || p->sel.prefixlen_s > 128) + goto out; + break; #else err = -EAFNOSUPPORT; @@ -1353,10 +1359,16 @@ static int verify_newpolicy_info(struct xfrm_userpolicy_info *p)
switch (p->sel.family) { case AF_INET: + if (p->sel.prefixlen_d > 32 || p->sel.prefixlen_s > 32) + return -EINVAL; + break;
case AF_INET6: #if IS_ENABLED(CONFIG_IPV6) + if (p->sel.prefixlen_d > 128 || p->sel.prefixlen_s > 128) + return -EINVAL; + break; #else return -EAFNOSUPPORT;
From: Thadeu Lima de Souza Cascardo cascardo@canonical.com
[ Upstream commit 215ab0f021c9fea3c18b75e7d522400ee6a49990 ]
After commit d6990976af7c5d8f55903bfb4289b6fb030bf754 ("vti6: fix PMTU caching and reporting on xmit"), some too big skbs might be potentially passed down to __xfrm6_output, causing it to fail to transmit but not free the skb, causing a leak of skb, and consequentially a leak of dst references.
After running pmtu.sh, that shows as failure to unregister devices in a namespace:
[ 311.397671] unregister_netdevice: waiting for veth_b to become free. Usage count = 1
The fix is to call kfree_skb in case of transmit failures.
Fixes: dd767856a36e ("xfrm6: Don't call icmpv6_send on local error") Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Reviewed-by: Sabrina Dubroca sd@queasysnail.net Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv6/xfrm6_output.c | 2 ++ 1 file changed, 2 insertions(+)
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 8ae87d4ec5ff..29dae7f2ff14 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -170,9 +170,11 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
if (toobig && xfrm6_local_dontfrag(skb)) { xfrm6_local_rxpmtu(skb, mtu); + kfree_skb(skb); return -EMSGSIZE; } else if (!skb->ignore_df && toobig && skb->sk) { xfrm_local_error(skb, mtu); + kfree_skb(skb); return -EMSGSIZE; }
From: Sowmini Varadhan sowmini.varadhan@oracle.com
[ Upstream commit bfc0698bebcb16d19ecfc89574ad4d696955e5d3 ]
A policy may have been set up with multiple transforms (e.g., ESP and ipcomp). In this situation, the ingress IPsec processing iterates in xfrm_input() and applies each transform in turn, processing the nexthdr to find any additional xfrm that may apply.
This patch resets the transport header back to network header only after the last transformation so that subsequent xfrms can find the correct transport header.
Fixes: 7785bba299a8 ("esp: Add a software GRO codepath") Suggested-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sowmini Varadhan sowmini.varadhan@oracle.com Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/xfrm4_input.c | 1 + net/ipv4/xfrm4_mode_transport.c | 4 +--- net/ipv6/xfrm6_input.c | 1 + net/ipv6/xfrm6_mode_transport.c | 4 +--- 4 files changed, 4 insertions(+), 6 deletions(-)
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index bcfc00e88756..f8de2482a529 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -67,6 +67,7 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async)
if (xo && (xo->flags & XFRM_GRO)) { skb_mac_header_rebuild(skb); + skb_reset_transport_header(skb); return 0; }
diff --git a/net/ipv4/xfrm4_mode_transport.c b/net/ipv4/xfrm4_mode_transport.c index 3d36644890bb..1ad2c2c4e250 100644 --- a/net/ipv4/xfrm4_mode_transport.c +++ b/net/ipv4/xfrm4_mode_transport.c @@ -46,7 +46,6 @@ static int xfrm4_transport_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb) { int ihl = skb->data - skb_transport_header(skb); - struct xfrm_offload *xo = xfrm_offload(skb);
if (skb->transport_header != skb->network_header) { memmove(skb_transport_header(skb), @@ -54,8 +53,7 @@ static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb) skb->network_header = skb->transport_header; } ip_hdr(skb)->tot_len = htons(skb->len + ihl); - if (!xo || !(xo->flags & XFRM_GRO)) - skb_reset_transport_header(skb); + skb_reset_transport_header(skb); return 0; }
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 841f4a07438e..9ef490dddcea 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -59,6 +59,7 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async)
if (xo && (xo->flags & XFRM_GRO)) { skb_mac_header_rebuild(skb); + skb_reset_transport_header(skb); return -1; }
diff --git a/net/ipv6/xfrm6_mode_transport.c b/net/ipv6/xfrm6_mode_transport.c index 9ad07a91708e..3c29da5defe6 100644 --- a/net/ipv6/xfrm6_mode_transport.c +++ b/net/ipv6/xfrm6_mode_transport.c @@ -51,7 +51,6 @@ static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb) { int ihl = skb->data - skb_transport_header(skb); - struct xfrm_offload *xo = xfrm_offload(skb);
if (skb->transport_header != skb->network_header) { memmove(skb_transport_header(skb), @@ -60,8 +59,7 @@ static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb) } ipv6_hdr(skb)->payload_len = htons(skb->len + ihl - sizeof(struct ipv6hdr)); - if (!xo || !(xo->flags & XFRM_GRO)) - skb_reset_transport_header(skb); + skb_reset_transport_header(skb); return 0; }
From: Sowmini Varadhan sowmini.varadhan@oracle.com
[ Upstream commit 782710e333a526780d65918d669cb96646983ba2 ]
We only support one offloaded xfrm (we do not have devices that can handle more than one offload), so reset crypto_done in xfrm_input() when iterating over multiple transforms in xfrm_input, so that we can invoke the appropriate x->type->input for the non-offloaded transforms
Fixes: d77e38e612a0 ("xfrm: Add an IPsec hardware offloading API") Signed-off-by: Sowmini Varadhan sowmini.varadhan@oracle.com Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/xfrm/xfrm_input.c | 1 + 1 file changed, 1 insertion(+)
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 9f492dc417d5..8e75319dd9c0 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -453,6 +453,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); goto drop; } + crypto_done = false; } while (!err);
err = xfrm_rcv_cb(skb, family, x->type->proto, 0);
From: Andrei Otcheretianski andrei.otcheretianski@intel.com
[ Upstream commit 8682250b3c1b75a45feb7452bc413d004cfe3778 ]
If a frame is dropped for any reason, mac80211 wouldn't report the TX status back to user space.
As the user space may rely on the TX_STATUS to kick its state machines, resends etc, it's better to just report this frame as not acked instead.
Signed-off-by: Andrei Otcheretianski andrei.otcheretianski@intel.com Signed-off-by: Luca Coelho luciano.coelho@intel.com Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/mac80211/status.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-)
diff --git a/net/mac80211/status.c b/net/mac80211/status.c index da7427a41529..ccac205e5853 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -470,11 +470,6 @@ static void ieee80211_report_ack_skb(struct ieee80211_local *local, if (!skb) return;
- if (dropped) { - dev_kfree_skb_any(skb); - return; - } - if (info->flags & IEEE80211_TX_INTFL_NL80211_FRAME_TX) { u64 cookie = IEEE80211_SKB_CB(skb)->ack.cookie; struct ieee80211_sub_if_data *sdata; @@ -495,6 +490,8 @@ static void ieee80211_report_ack_skb(struct ieee80211_local *local, } rcu_read_unlock();
+ dev_kfree_skb_any(skb); + } else if (dropped) { dev_kfree_skb_any(skb); } else { /* consumes skb */
From: Andrei Otcheretianski andrei.otcheretianski@intel.com
[ Upstream commit 24f33e64fcd0d50a4b1a8e5b41bd0257aa66b0e8 ]
Core regulatory hints didn't set wiphy_idx to WIPHY_IDX_INVALID. Since the regulatory request is zeroed, wiphy_idx was always implicitly set to 0. This resulted in updating only phy #0. Fix that.
Fixes: 806a9e39670b ("cfg80211: make regulatory_request use wiphy_idx instead of wiphy") Signed-off-by: Andrei Otcheretianski andrei.otcheretianski@intel.com Signed-off-by: Luca Coelho luciano.coelho@intel.com [add fixes tag] Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/wireless/reg.c | 1 + 1 file changed, 1 insertion(+)
diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 6e94f6934a0e..6f032c7b8732 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2384,6 +2384,7 @@ static int regulatory_hint_core(const char *alpha2) request->alpha2[0] = alpha2[0]; request->alpha2[1] = alpha2[1]; request->initiator = NL80211_REGDOM_SET_BY_CORE; + request->wiphy_idx = WIPHY_IDX_INVALID;
queue_regulatory_request(request);
From: Bob Copeland me@bobcopeland.com
[ Upstream commit 6eae4a6c2be387fec41b0d2782c4fffb57159498 ]
In our environment running lots of mesh nodes, we are seeing the pending queue hang periodically, with the debugfs queues file showing lines such as:
00: 0x00000000/348
i.e. there are a large number of frames but no stop reason set.
One way this could happen is if queue processing from the pending tasklet exited early without processing all frames, and without having some future event (incoming frame, stop reason flag, ...) to reschedule it.
Exactly this can occur today if ieee80211_tx() returns false due to packet drops or power-save buffering in the tx handlers. In the past, this function would return true in such cases, and the change to false doesn't seem to be intentional. Fix this case by reverting to the previous behavior.
Fixes: bb42f2d13ffc ("mac80211: Move reorder-sensitive TX handlers to after TXQ dequeue") Signed-off-by: Bob Copeland bobcopeland@fb.com Acked-by: Toke Høiland-Jørgensen toke@toke.dk Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/mac80211/tx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index d8fddd88bf46..a17a56032a21 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1837,7 +1837,7 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata, sdata->vif.hw_queue[skb_get_queue_mapping(skb)];
if (invoke_tx_handlers_early(&tx)) - return false; + return true;
if (ieee80211_queue_skb(local, sdata, tx.sta, tx.skb)) return true;
From: Jouni Malinen jouni@codeaurora.org
[ Upstream commit 119f94a6fefcc76d47075b83d2b73d04c895df78 ]
cfg80211_get_bss_channel() is used to update the RX channel based on the available frame payload information (channel number from DSSS Parameter Set element or HT Operation element). This is needed on 2.4 GHz channels where frames may be received on neighboring channels due to overlapping frequency range.
This might of some use on the 5 GHz band in some corner cases, but things are more complex there since there is no n:1 or 1:n mapping between channel numbers and frequencies due to multiple different starting frequencies in different operating classes. This could result in ieee80211_channel_to_frequency() returning incorrect frequency and ieee80211_get_channel() returning incorrect channel information (or indication of no match). In the previous implementation, this could result in some scan results being dropped completely, e.g., for the 4.9 GHz channels. That prevented connection to such BSSs.
Fix this by using the driver-provided channel pointer if ieee80211_get_channel() does not find matching channel data for the channel number in the frame payload and if the scan is done with 5 MHz or 10 MHz channel bandwidth. While doing this, also add comments describing what the function is trying to achieve to make it easier to understand what happens here and why.
Signed-off-by: Jouni Malinen jouni@codeaurora.org Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/wireless/scan.c | 58 ++++++++++++++++++++++++++++++++++++++------- 1 file changed, 49 insertions(+), 9 deletions(-)
diff --git a/net/wireless/scan.c b/net/wireless/scan.c index f6c5fe482506..5ed0ed0559dc 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1055,13 +1055,23 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, return NULL; }
+/* + * Update RX channel information based on the available frame payload + * information. This is mainly for the 2.4 GHz band where frames can be received + * from neighboring channels and the Beacon frames use the DSSS Parameter Set + * element to indicate the current (transmitting) channel, but this might also + * be needed on other bands if RX frequency does not match with the actual + * operating channel of a BSS. + */ static struct ieee80211_channel * cfg80211_get_bss_channel(struct wiphy *wiphy, const u8 *ie, size_t ielen, - struct ieee80211_channel *channel) + struct ieee80211_channel *channel, + enum nl80211_bss_scan_width scan_width) { const u8 *tmp; u32 freq; int channel_number = -1; + struct ieee80211_channel *alt_channel;
tmp = cfg80211_find_ie(WLAN_EID_DS_PARAMS, ie, ielen); if (tmp && tmp[1] == 1) { @@ -1075,16 +1085,45 @@ cfg80211_get_bss_channel(struct wiphy *wiphy, const u8 *ie, size_t ielen, } }
- if (channel_number < 0) + if (channel_number < 0) { + /* No channel information in frame payload */ return channel; + }
freq = ieee80211_channel_to_frequency(channel_number, channel->band); - channel = ieee80211_get_channel(wiphy, freq); - if (!channel) - return NULL; - if (channel->flags & IEEE80211_CHAN_DISABLED) + alt_channel = ieee80211_get_channel(wiphy, freq); + if (!alt_channel) { + if (channel->band == NL80211_BAND_2GHZ) { + /* + * Better not allow unexpected channels when that could + * be going beyond the 1-11 range (e.g., discovering + * BSS on channel 12 when radio is configured for + * channel 11. + */ + return NULL; + } + + /* No match for the payload channel number - ignore it */ + return channel; + } + + if (scan_width == NL80211_BSS_CHAN_WIDTH_10 || + scan_width == NL80211_BSS_CHAN_WIDTH_5) { + /* + * Ignore channel number in 5 and 10 MHz channels where there + * may not be an n:1 or 1:n mapping between frequencies and + * channel numbers. + */ + return channel; + } + + /* + * Use the channel determined through the payload channel number + * instead of the RX channel reported by the driver. + */ + if (alt_channel->flags & IEEE80211_CHAN_DISABLED) return NULL; - return channel; + return alt_channel; }
/* Returned bss is reference counted and must be cleaned up appropriately. */ @@ -1109,7 +1148,8 @@ cfg80211_inform_bss_data(struct wiphy *wiphy, (data->signal < 0 || data->signal > 100))) return NULL;
- channel = cfg80211_get_bss_channel(wiphy, ie, ielen, data->chan); + channel = cfg80211_get_bss_channel(wiphy, ie, ielen, data->chan, + data->scan_width); if (!channel) return NULL;
@@ -1207,7 +1247,7 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, return NULL;
channel = cfg80211_get_bss_channel(wiphy, mgmt->u.beacon.variable, - ielen, data->chan); + ielen, data->chan, data->scan_width); if (!channel) return NULL;
From: Johannes Berg johannes.berg@intel.com
[ Upstream commit cb59bc14e830028d2244861216df038165d7625d ]
If the TDLS setup happens over a connection to an AP that doesn't have QoS, we nevertheless assign a non-zero TID (skb->priority) and queue mapping, which may confuse us or drivers later.
Fix it by just assigning the special skb->priority and then using ieee80211_select_queue() just like other data frames would go through.
Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/mac80211/tdls.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index 91093d4a2f84..6e7aa65cf345 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -16,6 +16,7 @@ #include "ieee80211_i.h" #include "driver-ops.h" #include "rate.h" +#include "wme.h"
/* give usermode some time for retries in setting up the TDLS session */ #define TDLS_PEER_SETUP_TIMEOUT (15 * HZ) @@ -1006,14 +1007,13 @@ ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev, switch (action_code) { case WLAN_TDLS_SETUP_REQUEST: case WLAN_TDLS_SETUP_RESPONSE: - skb_set_queue_mapping(skb, IEEE80211_AC_BK); - skb->priority = 2; + skb->priority = 256 + 2; break; default: - skb_set_queue_mapping(skb, IEEE80211_AC_VI); - skb->priority = 5; + skb->priority = 256 + 5; break; } + skb_set_queue_mapping(skb, ieee80211_select_queue(sdata, skb));
/* * Set the WLAN_TDLS_TEARDOWN flag to indicate a teardown in progress.
From: Yuan-Chi Pang fu3mo6goo@gmail.com
[ Upstream commit c42055105785580563535e6d3143cad95c7ac7ee ]
TX status reporting to ieee80211s is through ieee80211s_update_metric. There are two problems about ieee80211s_update_metric:
1. The purpose is to estimate the fail probability to a specific link. No need to restrict to data frame.
2. Current implementation does not work if wireless driver does not pass tx_status with skb.
Fix this by removing ieee80211_is_data condition, passing ieee80211_tx_status directly to ieee80211s_update_metric, and putting it in both __ieee80211_tx_status and ieee80211_tx_status_ext.
Signed-off-by: Yuan-Chi Pang fu3mo6goo@gmail.com Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/mac80211/mesh.h | 3 ++- net/mac80211/mesh_hwmp.c | 9 +++------ net/mac80211/status.c | 4 +++- 3 files changed, 8 insertions(+), 8 deletions(-)
diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index 7e5f271e3c30..4f1c61637ce3 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -217,7 +217,8 @@ void mesh_rmc_free(struct ieee80211_sub_if_data *sdata); int mesh_rmc_init(struct ieee80211_sub_if_data *sdata); void ieee80211s_init(void); void ieee80211s_update_metric(struct ieee80211_local *local, - struct sta_info *sta, struct sk_buff *skb); + struct sta_info *sta, + struct ieee80211_tx_status *st); void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata); void ieee80211_mesh_teardown_sdata(struct ieee80211_sub_if_data *sdata); int ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata); diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 055ea36ff27b..fab0764c315f 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -295,15 +295,12 @@ int mesh_path_error_tx(struct ieee80211_sub_if_data *sdata, }
void ieee80211s_update_metric(struct ieee80211_local *local, - struct sta_info *sta, struct sk_buff *skb) + struct sta_info *sta, + struct ieee80211_tx_status *st) { - struct ieee80211_tx_info *txinfo = IEEE80211_SKB_CB(skb); - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; + struct ieee80211_tx_info *txinfo = st->info; int failed;
- if (!ieee80211_is_data(hdr->frame_control)) - return; - failed = !(txinfo->flags & IEEE80211_TX_STAT_ACK);
/* moving average, scaled to 100. diff --git a/net/mac80211/status.c b/net/mac80211/status.c index ccac205e5853..bdf131ed5ce8 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -797,7 +797,7 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw,
rate_control_tx_status(local, sband, status); if (ieee80211_vif_is_mesh(&sta->sdata->vif)) - ieee80211s_update_metric(local, sta, skb); + ieee80211s_update_metric(local, sta, status);
if (!(info->flags & IEEE80211_TX_CTL_INJECTED) && acked) ieee80211_frame_acked(sta, skb); @@ -958,6 +958,8 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, }
rate_control_tx_status(local, sband, status); + if (ieee80211_vif_is_mesh(&sta->sdata->vif)) + ieee80211s_update_metric(local, sta, status); }
if (acked || noack_success) {
From: Steffen Klassert steffen.klassert@secunet.com
[ Upstream commit 9e1437937807b0122e8da1ca8765be2adca9aee6 ]
Since commit 222d7dbd258d ("net: prevent dst uses after free") skb_dst_force() might clear the dst_entry attached to the skb. The xfrm code don't expect this to happen, so we crash with a NULL pointer dereference in this case. Fix it by checking skb_dst(skb) for NULL after skb_dst_force() and drop the packet in cast the dst_entry was cleared.
Fixes: 222d7dbd258d ("net: prevent dst uses after free") Reported-by: Tobias Hommel netdev-list@genoetigt.de Reported-by: Kristian Evensen kristian.evensen@gmail.com Reported-by: Wolfgang Walter linux@stwm.de Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/xfrm/xfrm_output.c | 4 ++++ net/xfrm/xfrm_policy.c | 4 ++++ 2 files changed, 8 insertions(+)
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 35610cc881a9..c47660fba498 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -101,6 +101,10 @@ static int xfrm_output_one(struct sk_buff *skb, int err) spin_unlock_bh(&x->lock);
skb_dst_force(skb); + if (!skb_dst(skb)) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR); + goto error_nolock; + }
if (xfrm_offload(skb)) { x->type_offload->encap(x, skb); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 2fb7a78308e1..37c32e73aaef 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2550,6 +2550,10 @@ int __xfrm_route_forward(struct sk_buff *skb, unsigned short family) }
skb_dst_force(skb); + if (!skb_dst(skb)) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMFWDHDRERROR); + return 0; + }
dst = xfrm_lookup(net, skb_dst(skb), &fl, NULL, XFRM_LOOKUP_QUEUE); if (IS_ERR(dst)) {
From: Thomas Petazzoni thomas.petazzoni@free-electrons.com
[ Upstream commit 3a58ac65e2d7969bcdf1b6acb70fa4d12a88e53e ]
IO_SPACE_LIMIT is the ending address of the PCI IO space, i.e something like 0xfffff (and not 0x100000).
Therefore, when offset = 0xf0000 is passed as argument, this function fails even though the offset + SZ_64K fits below the IO_SPACE_LIMIT. This makes the last chunk of 64 KB of the I/O space not usable as it cannot be mapped.
This patch fixes that by substracing 1 to offset + SZ_64K, so that we compare the addrss of the last byte of the I/O space against IO_SPACE_LIMIT instead of the address of the first byte of what is after the I/O space.
Fixes: c2794437091a4 ("ARM: Add fixed PCI i/o mapping") Signed-off-by: Thomas Petazzoni thomas.petazzoni@bootlin.com Acked-by: Nicolas Pitre nico@linaro.org Signed-off-by: Russell King rmk+kernel@armlinux.org.uk Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/mm/ioremap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index fc91205ff46c..5bf9443cfbaa 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -473,7 +473,7 @@ void pci_ioremap_set_mem_type(int mem_type)
int pci_ioremap_io(unsigned int offset, phys_addr_t phys_addr) { - BUG_ON(offset + SZ_64K > IO_SPACE_LIMIT); + BUG_ON(offset + SZ_64K - 1 > IO_SPACE_LIMIT);
return ioremap_page_range(PCI_IO_VIRT_BASE + offset, PCI_IO_VIRT_BASE + offset + SZ_64K,
From: Sean Tranchetti stranche@codeaurora.org
[ Upstream commit 32bf94fb5c2ec4ec842152d0e5937cd4bb6738fa ]
XFRM mode parameters passed as part of the user templates in the IP_XFRM_POLICY are never properly validated. Passing values other than valid XFRM modes can cause stack-out-of-bounds reads to occur later in the XFRM processing:
[ 140.535608] ================================================================ [ 140.543058] BUG: KASAN: stack-out-of-bounds in xfrm_state_find+0x17e4/0x1cc4 [ 140.550306] Read of size 4 at addr ffffffc0238a7a58 by task repro/5148 [ 140.557369] [ 140.558927] Call trace: [ 140.558936] dump_backtrace+0x0/0x388 [ 140.558940] show_stack+0x24/0x30 [ 140.558946] __dump_stack+0x24/0x2c [ 140.558949] dump_stack+0x8c/0xd0 [ 140.558956] print_address_description+0x74/0x234 [ 140.558960] kasan_report+0x240/0x264 [ 140.558963] __asan_report_load4_noabort+0x2c/0x38 [ 140.558967] xfrm_state_find+0x17e4/0x1cc4 [ 140.558971] xfrm_resolve_and_create_bundle+0x40c/0x1fb8 [ 140.558975] xfrm_lookup+0x238/0x1444 [ 140.558977] xfrm_lookup_route+0x48/0x11c [ 140.558984] ip_route_output_flow+0x88/0xc4 [ 140.558991] raw_sendmsg+0xa74/0x266c [ 140.558996] inet_sendmsg+0x258/0x3b0 [ 140.559002] sock_sendmsg+0xbc/0xec [ 140.559005] SyS_sendto+0x3a8/0x5a8 [ 140.559008] el0_svc_naked+0x34/0x38 [ 140.559009] [ 140.592245] page dumped because: kasan: bad access detected [ 140.597981] page_owner info is not active (free page?) [ 140.603267] [ 140.653503] ================================================================
Signed-off-by: Sean Tranchetti stranche@codeaurora.org Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/xfrm/xfrm_user.c | 3 +++ 1 file changed, 3 insertions(+)
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 4292347bf45e..4e8319766f2b 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1449,6 +1449,9 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family) (ut[i].family != prev_family)) return -EINVAL;
+ if (ut[i].mode >= XFRM_MODE_MAX) + return -EINVAL; + prev_family = ut[i].family;
switch (ut[i].family) {
From: David Ahern dsahern@gmail.com
[ Upstream commit a173f066c7cfc031acb8f541708041e009fc9812 ]
For starters, the bridge netfilter code registers operations that are invoked any time nh_hook is called. Specifically, ip_sabotage_in watches for nested calls for NF_INET_PRE_ROUTING when a bridge is in the stack.
Packet wise, the bridge netfilter hook runs first. br_nf_pre_routing allocates nf_bridge, sets in_prerouting to 1 and calls NF_HOOK for NF_INET_PRE_ROUTING. It's finish function, br_nf_pre_routing_finish, then resets in_prerouting flag to 0 and the packet continues up the stack. The packet eventually makes it to the VRF driver and it invokes nf_hook for NF_INET_PRE_ROUTING in case any rules have been added against the vrf device.
Because of the registered operations the call to nf_hook causes ip_sabotage_in to be invoked. That function sees the nf_bridge on the skb and that in_prerouting is not set. Thinking it is an invalid nested call it steals (drops) the packet.
Update ip_sabotage_in to recognize that the bridge or one of its upper devices (e.g., vlan) can be enslaved to a VRF (L3 master device) and allow the packet to go through the nf_hook a second time.
Fixes: 73e20b761acf ("net: vrf: Add support for PREROUTING rules on vrf device") Reported-by: D'Souza, Nelson ndsouza@ciena.com Signed-off-by: David Ahern dsahern@gmail.com Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/bridge/br_netfilter_hooks.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index c2eea1b8737a..7582f28ab306 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -832,7 +832,8 @@ static unsigned int ip_sabotage_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - if (skb->nf_bridge && !skb->nf_bridge->in_prerouting) { + if (skb->nf_bridge && !skb->nf_bridge->in_prerouting && + !netif_is_l3_master(skb->dev)) { state->okfn(state->net, state->sk, skb); return NF_STOLEN; }
From: Steve Capper steve.capper@arm.com
[ Upstream commit 469ed9d823b7d240d6b9574f061ded7c3834c167 ]
In the contiguous bit hugetlb break-before-make code we assume that all hugetlb pages are young.
In fact, remove_migration_pte is able to place an old hugetlb pte so this assumption is not valid.
This patch fixes the contiguous hugetlb scanning code to preserve young ptes.
Fixes: d8bdcff28764 ("arm64: hugetlb: Add break-before-make logic for contiguous entries") Signed-off-by: Steve Capper steve.capper@arm.com Signed-off-by: Will Deacon will.deacon@arm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/mm/hugetlbpage.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-)
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 6cb0fa92a651..9f6ae9686dac 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -118,11 +118,14 @@ static pte_t get_clear_flush(struct mm_struct *mm,
/* * If HW_AFDBM is enabled, then the HW could turn on - * the dirty bit for any page in the set, so check - * them all. All hugetlb entries are already young. + * the dirty or accessed bit for any page in the set, + * so check them all. */ if (pte_dirty(pte)) orig_pte = pte_mkdirty(orig_pte); + + if (pte_young(pte)) + orig_pte = pte_mkyoung(orig_pte); }
if (valid) @@ -347,10 +350,13 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma, if (!pte_same(orig_pte, pte)) changed = 1;
- /* Make sure we don't lose the dirty state */ + /* Make sure we don't lose the dirty or young state */ if (pte_dirty(orig_pte)) pte = pte_mkdirty(pte);
+ if (pte_young(orig_pte)) + pte = pte_mkyoung(pte); + hugeprot = pte_pgprot(pte); for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) set_pte_at(vma->vm_mm, addr, ptep, pfn_pte(pfn, hugeprot));
From: Florian Fainelli f.fainelli@gmail.com
[ Upstream commit 3ab97942d0213b6583a5408630a8cbbfbf54730f ]
A number of our interrupts were incorrectly specified, fix both the PPI and SPI interrupts to be correct.
Fixes: b5762cacc411 ("ARM: bcm63138: add NAND DT support") Fixes: 46d4bca0445a ("ARM: BCM63XX: add BCM63138 minimal Device Tree") Signed-off-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/bcm63138.dtsi | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-)
diff --git a/arch/arm/boot/dts/bcm63138.dtsi b/arch/arm/boot/dts/bcm63138.dtsi index 43ee992ccdcf..6df61518776f 100644 --- a/arch/arm/boot/dts/bcm63138.dtsi +++ b/arch/arm/boot/dts/bcm63138.dtsi @@ -106,21 +106,23 @@ global_timer: timer@1e200 { compatible = "arm,cortex-a9-global-timer"; reg = <0x1e200 0x20>; - interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>; clocks = <&axi_clk>; };
local_timer: local-timer@1e600 { compatible = "arm,cortex-a9-twd-timer"; reg = <0x1e600 0x20>; - interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) | + IRQ_TYPE_EDGE_RISING)>; clocks = <&axi_clk>; };
twd_watchdog: watchdog@1e620 { compatible = "arm,cortex-a9-twd-wdt"; reg = <0x1e620 0x20>; - interrupts = <GIC_PPI 14 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) | + IRQ_TYPE_LEVEL_HIGH)>; };
armpll: armpll { @@ -158,7 +160,7 @@ serial0: serial@600 { compatible = "brcm,bcm6345-uart"; reg = <0x600 0x1b>; - interrupts = <GIC_SPI 32 0>; + interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>; clocks = <&periph_clk>; clock-names = "periph"; status = "disabled"; @@ -167,7 +169,7 @@ serial1: serial@620 { compatible = "brcm,bcm6345-uart"; reg = <0x620 0x1b>; - interrupts = <GIC_SPI 33 0>; + interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>; clocks = <&periph_clk>; clock-names = "periph"; status = "disabled"; @@ -180,7 +182,7 @@ reg = <0x2000 0x600>, <0xf0 0x10>; reg-names = "nand", "nand-int-base"; status = "disabled"; - interrupts = <GIC_SPI 38 0>; + interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "nand"; };
From: Michal Simek michal.simek@xilinx.com
[ Upstream commit e1e5d8a9fe737d94ccc0ccbaf0c97f69a8f3e000 ]
Clear ADDR64 dma bit in DMACFG register in case that HW_DMA_CAP_64B is not detected on 64bit system. The issue was observed when bootloader(u-boot) does not check macb feature at DCFG6 register (DAW64_OFFSET) and enabling 64bit dma support by default. Then macb driver is reading DMACFG register back and only adding 64bit dma configuration but not cleaning it out.
Signed-off-by: Michal Simek michal.simek@xilinx.com Acked-by: Nicolas Ferre nicolas.ferre@microchip.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/cadence/macb_main.c | 1 + 1 file changed, 1 insertion(+)
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index c1787be6a258..aaf450e2ecc5 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -2000,6 +2000,7 @@ static void macb_configure_dma(struct macb *bp) else dmacfg &= ~GEM_BIT(TXCOEN);
+ dmacfg &= ~GEM_BIT(ADDR64); #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT if (bp->hw_dma_cap & HW_DMA_CAP_64B) dmacfg |= GEM_BIT(ADDR64);
From: Yunsheng Lin linyunsheng@huawei.com
[ Upstream commit 2e9361efa707e186d91b938e44f9e326725259f7 ]
If SMMU is on, there is more likely that skb_shinfo(skb)->frags[i] can not send by a single BD. when this happen, the hns_nic_net_xmit_hw function map the whole data in a frags using skb_frag_dma_map, but unmap each BD' data individually when tx is done, which causes problem when SMMU is on.
This patch fixes this problem by ummapping the whole data in a frags when tx is done.
Signed-off-by: Yunsheng Lin linyunsheng@huawei.com Signed-off-by: Peng Li lipeng321@huawei.com Reviewed-by: Yisen Zhuang yisen.zhuang@huawei.com Signed-off-by: Salil Mehta salil.mehta@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/hisilicon/hns/hnae.c | 2 +- drivers/net/ethernet/hisilicon/hns/hns_enet.c | 30 ++++++++++++------- 2 files changed, 20 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c index a051e582d541..79d03f8ee7b1 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.c +++ b/drivers/net/ethernet/hisilicon/hns/hnae.c @@ -84,7 +84,7 @@ static void hnae_unmap_buffer(struct hnae_ring *ring, struct hnae_desc_cb *cb) if (cb->type == DESC_TYPE_SKB) dma_unmap_single(ring_to_dev(ring), cb->dma, cb->length, ring_to_dma_dir(ring)); - else + else if (cb->length) dma_unmap_page(ring_to_dev(ring), cb->dma, cb->length, ring_to_dma_dir(ring)); } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 07d6a9cf2c55..4faadc3ffe8c 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -40,9 +40,9 @@ #define SKB_TMP_LEN(SKB) \ (((SKB)->transport_header - (SKB)->mac_header) + tcp_hdrlen(SKB))
-static void fill_v2_desc(struct hnae_ring *ring, void *priv, - int size, dma_addr_t dma, int frag_end, - int buf_num, enum hns_desc_type type, int mtu) +static void fill_v2_desc_hw(struct hnae_ring *ring, void *priv, int size, + int send_sz, dma_addr_t dma, int frag_end, + int buf_num, enum hns_desc_type type, int mtu) { struct hnae_desc *desc = &ring->desc[ring->next_to_use]; struct hnae_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use]; @@ -64,7 +64,7 @@ static void fill_v2_desc(struct hnae_ring *ring, void *priv, desc_cb->type = type;
desc->addr = cpu_to_le64(dma); - desc->tx.send_size = cpu_to_le16((u16)size); + desc->tx.send_size = cpu_to_le16((u16)send_sz);
/* config bd buffer end */ hnae_set_bit(rrcfv, HNSV2_TXD_VLD_B, 1); @@ -133,6 +133,14 @@ static void fill_v2_desc(struct hnae_ring *ring, void *priv, ring_ptr_move_fw(ring, next_to_use); }
+static void fill_v2_desc(struct hnae_ring *ring, void *priv, + int size, dma_addr_t dma, int frag_end, + int buf_num, enum hns_desc_type type, int mtu) +{ + fill_v2_desc_hw(ring, priv, size, size, dma, frag_end, + buf_num, type, mtu); +} + static const struct acpi_device_id hns_enet_acpi_match[] = { { "HISI00C1", 0 }, { "HISI00C2", 0 }, @@ -289,15 +297,15 @@ static void fill_tso_desc(struct hnae_ring *ring, void *priv,
/* when the frag size is bigger than hardware, split this frag */ for (k = 0; k < frag_buf_num; k++) - fill_v2_desc(ring, priv, - (k == frag_buf_num - 1) ? + fill_v2_desc_hw(ring, priv, k == 0 ? size : 0, + (k == frag_buf_num - 1) ? sizeoflast : BD_MAX_SEND_SIZE, - dma + BD_MAX_SEND_SIZE * k, - frag_end && (k == frag_buf_num - 1) ? 1 : 0, - buf_num, - (type == DESC_TYPE_SKB && !k) ? + dma + BD_MAX_SEND_SIZE * k, + frag_end && (k == frag_buf_num - 1) ? 1 : 0, + buf_num, + (type == DESC_TYPE_SKB && !k) ? DESC_TYPE_SKB : DESC_TYPE_PAGE, - mtu); + mtu); }
netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev,
From: Alexandre Belloni alexandre.belloni@bootlin.com
[ Upstream commit 64e9e22e68512da8df3c9a7430f07621e48db3c2 ]
If the qman driver didn't probe, calling qman_alloc_fqid_range, qman_alloc_pool_range or qman_alloc_cgrid_range (as done in dpaa_eth) will pass a NULL pointer to gen_pool_alloc, leading to a NULL pointer dereference.
Signed-off-by: Alexandre Belloni alexandre.belloni@bootlin.com Reviewed-by: Roy Pledge roy.pledge@nxp.com Signed-off-by: Li Yang leoyang.li@nxp.com (cherry picked from commit f72487a2788aa70c3aee1d0ebd5470de9bac953a) Signed-off-by: Olof Johansson olof@lixom.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/soc/fsl/qbman/qman.c | 3 +++ 1 file changed, 3 insertions(+)
diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c index 0c6065dba48a..4f27e95efcdd 100644 --- a/drivers/soc/fsl/qbman/qman.c +++ b/drivers/soc/fsl/qbman/qman.c @@ -2699,6 +2699,9 @@ static int qman_alloc_range(struct gen_pool *p, u32 *result, u32 cnt) { unsigned long addr;
+ if (!p) + return -ENODEV; + addr = gen_pool_alloc(p, cnt); if (!addr) return -ENOMEM;
From: Zhao Qiang qiang.zhao@nxp.com
[ Upstream commit 96fc74333f84cfdf8d434c6c07254e215e2aad00 ]
There is a copy and paste bug so we accidentally use the RX_ shift when we're in TX_ mode.
Fixes: bb8b2062aff3 ("fsl/qe: setup clock source for TDM mode") Signed-off-by: Dan Carpenter dan.carpenter@oracle.com Signed-off-by: Zhao Qiang qiang.zhao@nxp.com Signed-off-by: Li Yang leoyang.li@nxp.com (cherry picked from commit 3cb31b634052ed458922e0c8e2b4b093d7fb60b9) Signed-off-by: Olof Johansson olof@lixom.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/soc/fsl/qe/ucc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/soc/fsl/qe/ucc.c b/drivers/soc/fsl/qe/ucc.c index c646d8713861..681f7d4b7724 100644 --- a/drivers/soc/fsl/qe/ucc.c +++ b/drivers/soc/fsl/qe/ucc.c @@ -626,7 +626,7 @@ static u32 ucc_get_tdm_sync_shift(enum comm_dir mode, u32 tdm_num) { u32 shift;
- shift = (mode == COMM_DIR_RX) ? RX_SYNC_SHIFT_BASE : RX_SYNC_SHIFT_BASE; + shift = (mode == COMM_DIR_RX) ? RX_SYNC_SHIFT_BASE : TX_SYNC_SHIFT_BASE; shift -= tdm_num * 2;
return shift;
From: Masashi Honma masashi.honma@gmail.com
[ Upstream commit 30fe6d50eb088783c8729c7d930f65296b2b3fa7 ]
Use array_index_nospec() to sanitize ridx with respect to speculation.
Signed-off-by: Masashi Honma masashi.honma@gmail.com Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/wireless/nl80211.c | 1 + 1 file changed, 1 insertion(+)
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 3de415bca391..5e7c9b361e8a 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3480,6 +3480,7 @@ static bool ht_rateset_to_mask(struct ieee80211_supported_band *sband, return false;
/* check availability */ + ridx = array_index_nospec(ridx, IEEE80211_HT_MCS_MASK_LEN); if (sband->ht_cap.mcs.rx_mask[ridx] & rbit) mcs[ridx] |= rbit; else
From: Martin Willi martin@strongswan.org
[ Upstream commit 28ef8b49a338dc1844e86b7954cfffc7dfa2660a ]
The allocation of hwsim radio identifiers uses a post-increment from 0, so the first radio has idx 0. This idx is explicitly excluded from multicast announcements ever since, but it is unclear why.
Drop that idx check and announce the first radio as well. This makes userspace happy if it relies on these events.
Signed-off-by: Martin Willi martin@strongswan.org Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/mac80211_hwsim.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index aafa7aa18fbd..477f9f2f6626 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -2730,8 +2730,7 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, list_add_tail(&data->list, &hwsim_radios); spin_unlock_bh(&hwsim_radio_lock);
- if (idx > 0) - hwsim_mcast_new_radio(idx, info, param); + hwsim_mcast_new_radio(idx, info, param);
return idx;
From: Matias Karhumaa matias.karhumaa@gmail.com
[ Upstream commit cb28c306b93b71f2741ce1a5a66289db26715f4d ]
In case unpair_device() was called through mgmt interface at the same time when pairing was in progress, Bluetooth kernel module crash was seen.
[ 600.351225] general protection fault: 0000 [#1] SMP PTI [ 600.351235] CPU: 1 PID: 11096 Comm: btmgmt Tainted: G OE 4.19.0-rc1+ #1 [ 600.351238] Hardware name: Dell Inc. Latitude E5440/08RCYC, BIOS A18 05/14/2017 [ 600.351272] RIP: 0010:smp_chan_destroy.isra.10+0xce/0x2c0 [bluetooth] [ 600.351276] Code: c0 0f 84 b4 01 00 00 80 78 28 04 0f 84 53 01 00 00 4d 85 ed 0f 85 ab 00 00 00 48 8b 08 48 8b 50 08 be 10 00 00 00 48 89 51 08 <48> 89 0a 48 b9 00 02 00 00 00 00 ad de 48 89 48 08 48 8b 83 00 01 [ 600.351279] RSP: 0018:ffffa9be839b3b50 EFLAGS: 00010246 [ 600.351282] RAX: ffff9c999ac565a0 RBX: ffff9c9996e98c00 RCX: ffff9c999aa28b60 [ 600.351285] RDX: dead000000000200 RSI: 0000000000000010 RDI: ffff9c999e403500 [ 600.351287] RBP: ffffa9be839b3b70 R08: 0000000000000000 R09: ffffffff92a25c00 [ 600.351290] R10: ffffa9be839b3ae8 R11: 0000000000000001 R12: ffff9c995375b800 [ 600.351292] R13: 0000000000000000 R14: ffff9c99619a5000 R15: ffff9c9962a01c00 [ 600.351295] FS: 00007fb2be27c700(0000) GS:ffff9c999e880000(0000) knlGS:0000000000000000 [ 600.351298] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 600.351300] CR2: 00007fb2bdadbad0 CR3: 000000041c328001 CR4: 00000000001606e0 [ 600.351302] Call Trace: [ 600.351325] smp_failure+0x4f/0x70 [bluetooth] [ 600.351345] smp_cancel_pairing+0x74/0x80 [bluetooth] [ 600.351370] unpair_device+0x1c1/0x330 [bluetooth] [ 600.351399] hci_sock_sendmsg+0x960/0x9f0 [bluetooth] [ 600.351409] ? apparmor_socket_sendmsg+0x1e/0x20 [ 600.351417] sock_sendmsg+0x3e/0x50 [ 600.351422] sock_write_iter+0x85/0xf0 [ 600.351429] do_iter_readv_writev+0x12b/0x1b0 [ 600.351434] do_iter_write+0x87/0x1a0 [ 600.351439] vfs_writev+0x98/0x110 [ 600.351443] ? ep_poll+0x16d/0x3d0 [ 600.351447] ? ep_modify+0x73/0x170 [ 600.351451] do_writev+0x61/0xf0 [ 600.351455] ? do_writev+0x61/0xf0 [ 600.351460] __x64_sys_writev+0x1c/0x20 [ 600.351465] do_syscall_64+0x5a/0x110 [ 600.351471] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 600.351474] RIP: 0033:0x7fb2bdb62fe0 [ 600.351477] Code: 73 01 c3 48 8b 0d b8 6e 2c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 0f 1f 44 00 00 83 3d 69 c7 2c 00 00 75 10 b8 14 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 de 80 01 00 48 89 04 24 [ 600.351479] RSP: 002b:00007ffe062cb8f8 EFLAGS: 00000246 ORIG_RAX: 0000000000000014 [ 600.351484] RAX: ffffffffffffffda RBX: 000000000255b3d0 RCX: 00007fb2bdb62fe0 [ 600.351487] RDX: 0000000000000001 RSI: 00007ffe062cb920 RDI: 0000000000000004 [ 600.351490] RBP: 00007ffe062cb920 R08: 000000000255bd80 R09: 0000000000000000 [ 600.351494] R10: 0000000000000353 R11: 0000000000000246 R12: 0000000000000001 [ 600.351497] R13: 00007ffe062cbbe0 R14: 0000000000000000 R15: 0000000000000000 [ 600.351501] Modules linked in: algif_hash algif_skcipher af_alg cmac ipt_MASQUERADE nf_conntrack_netlink nfnetlink xfrm_user xfrm_algo iptable_nat nf_nat_ipv4 xt_addrtype iptable_filter ip_tables xt_conntrack x_tables nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 libcrc32c br_netfilter bridge stp llc overlay arc4 nls_iso8859_1 dm_crypt intel_rapl x86_pkg_temp_thermal intel_powerclamp coretemp dell_laptop kvm_intel crct10dif_pclmul dell_smm_hwmon crc32_pclmul ghash_clmulni_intel pcbc aesni_intel aes_x86_64 crypto_simd cryptd glue_helper intel_cstate intel_rapl_perf uvcvideo videobuf2_vmalloc videobuf2_memops videobuf2_v4l2 videobuf2_common videodev media hid_multitouch input_leds joydev serio_raw dell_wmi snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_codec_generic dell_smbios dcdbas sparse_keymap [ 600.351569] snd_hda_intel btusb snd_hda_codec btrtl btbcm btintel snd_hda_core bluetooth(OE) snd_hwdep snd_pcm iwlmvm ecdh_generic wmi_bmof dell_wmi_descriptor snd_seq_midi mac80211 snd_seq_midi_event lpc_ich iwlwifi snd_rawmidi snd_seq snd_seq_device snd_timer cfg80211 snd soundcore mei_me mei dell_rbtn dell_smo8800 mac_hid parport_pc ppdev lp parport autofs4 hid_generic usbhid hid i915 nouveau kvmgt vfio_mdev mdev vfio_iommu_type1 vfio kvm irqbypass i2c_algo_bit ttm drm_kms_helper syscopyarea sysfillrect sysimgblt mxm_wmi psmouse ahci sdhci_pci cqhci libahci fb_sys_fops sdhci drm e1000e video wmi [ 600.351637] ---[ end trace e49e9f1df09c94fb ]--- [ 600.351664] RIP: 0010:smp_chan_destroy.isra.10+0xce/0x2c0 [bluetooth] [ 600.351666] Code: c0 0f 84 b4 01 00 00 80 78 28 04 0f 84 53 01 00 00 4d 85 ed 0f 85 ab 00 00 00 48 8b 08 48 8b 50 08 be 10 00 00 00 48 89 51 08 <48> 89 0a 48 b9 00 02 00 00 00 00 ad de 48 89 48 08 48 8b 83 00 01 [ 600.351669] RSP: 0018:ffffa9be839b3b50 EFLAGS: 00010246 [ 600.351672] RAX: ffff9c999ac565a0 RBX: ffff9c9996e98c00 RCX: ffff9c999aa28b60 [ 600.351674] RDX: dead000000000200 RSI: 0000000000000010 RDI: ffff9c999e403500 [ 600.351676] RBP: ffffa9be839b3b70 R08: 0000000000000000 R09: ffffffff92a25c00 [ 600.351679] R10: ffffa9be839b3ae8 R11: 0000000000000001 R12: ffff9c995375b800 [ 600.351681] R13: 0000000000000000 R14: ffff9c99619a5000 R15: ffff9c9962a01c00 [ 600.351684] FS: 00007fb2be27c700(0000) GS:ffff9c999e880000(0000) knlGS:0000000000000000 [ 600.351686] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 600.351689] CR2: 00007fb2bdadbad0 CR3: 000000041c328001 CR4: 00000000001606e0
Crash happened because list_del_rcu() was called twice for smp->ltk. This was possible if unpair_device was called right after ltk was generated but before keys were distributed.
In this commit smp_cancel_pairing was refactored to cancel pairing if it is in progress and otherwise just removes keys. Once keys are removed from rcu list, pointers to smp context's keys are set to NULL to make sure removed list items are not accessed later.
This commit also adjusts the functionality of mgmt unpair_device() little bit. Previously pairing was canceled only if pairing was in state that keys were already generated. With this commit unpair_device() cancels pairing already in earlier states.
Bug was found by fuzzing kernel SMP implementation using Synopsys Defensics.
Reported-by: Pekka Oikarainen pekka.oikarainen@synopsys.com Signed-off-by: Matias Karhumaa matias.karhumaa@gmail.com Signed-off-by: Johan Hedberg johan.hedberg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/bluetooth/mgmt.c | 7 ++----- net/bluetooth/smp.c | 29 +++++++++++++++++++++++++---- net/bluetooth/smp.h | 3 ++- 3 files changed, 29 insertions(+), 10 deletions(-)
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 1fba2a03f8ae..ba24f613c0fc 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -2298,9 +2298,8 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data, /* LE address type */ addr_type = le_addr_type(cp->addr.type);
- hci_remove_irk(hdev, &cp->addr.bdaddr, addr_type); - - err = hci_remove_ltk(hdev, &cp->addr.bdaddr, addr_type); + /* Abort any ongoing SMP pairing. Removes ltk and irk if they exist. */ + err = smp_cancel_and_remove_pairing(hdev, &cp->addr.bdaddr, addr_type); if (err < 0) { err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE, MGMT_STATUS_NOT_PAIRED, &rp, @@ -2314,8 +2313,6 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data, goto done; }
- /* Abort any ongoing SMP pairing */ - smp_cancel_pairing(conn);
/* Defer clearing up the connection parameters until closing to * give a chance of keeping them if a repairing happens. diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index a27704ff13a9..dbcc439fc78b 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -2410,30 +2410,51 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) return ret; }
-void smp_cancel_pairing(struct hci_conn *hcon) +int smp_cancel_and_remove_pairing(struct hci_dev *hdev, bdaddr_t *bdaddr, + u8 addr_type) { - struct l2cap_conn *conn = hcon->l2cap_data; + struct hci_conn *hcon; + struct l2cap_conn *conn; struct l2cap_chan *chan; struct smp_chan *smp; + int err; + + err = hci_remove_ltk(hdev, bdaddr, addr_type); + hci_remove_irk(hdev, bdaddr, addr_type); + + hcon = hci_conn_hash_lookup_le(hdev, bdaddr, addr_type); + if (!hcon) + goto done;
+ conn = hcon->l2cap_data; if (!conn) - return; + goto done;
chan = conn->smp; if (!chan) - return; + goto done;
l2cap_chan_lock(chan);
smp = chan->data; if (smp) { + /* Set keys to NULL to make sure smp_failure() does not try to + * remove and free already invalidated rcu list entries. */ + smp->ltk = NULL; + smp->slave_ltk = NULL; + smp->remote_irk = NULL; + if (test_bit(SMP_FLAG_COMPLETE, &smp->flags)) smp_failure(conn, 0); else smp_failure(conn, SMP_UNSPECIFIED); + err = 0; }
l2cap_chan_unlock(chan); + +done: + return err; }
static int smp_cmd_encrypt_info(struct l2cap_conn *conn, struct sk_buff *skb) diff --git a/net/bluetooth/smp.h b/net/bluetooth/smp.h index 0ff6247eaa6c..121edadd5f8d 100644 --- a/net/bluetooth/smp.h +++ b/net/bluetooth/smp.h @@ -181,7 +181,8 @@ enum smp_key_pref { };
/* SMP Commands */ -void smp_cancel_pairing(struct hci_conn *hcon); +int smp_cancel_and_remove_pairing(struct hci_dev *hdev, bdaddr_t *bdaddr, + u8 addr_type); bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level, enum smp_key_pref key_pref); int smp_conn_security(struct hci_conn *hcon, __u8 sec_level);
From: Lubomir Rintel lkundrak@v3.sk
[ Upstream commit d85536cde91fcfed6fb8d983783bd2b92c843939 ]
Add missing prepare/unprepare operations for fbi->clk, this fixes following kernel warning:
------------[ cut here ]------------ WARNING: CPU: 0 PID: 1 at drivers/clk/clk.c:874 clk_core_enable+0x2c/0x1b0 Enabling unprepared disp0_clk Modules linked in: CPU: 0 PID: 1 Comm: swapper Not tainted 4.18.0-rc8-00032-g02b43ddd4f21-dirty #25 Hardware name: Marvell MMP2 (Device Tree Support) [<c010f7cc>] (unwind_backtrace) from [<c010cc6c>] (show_stack+0x10/0x14) [<c010cc6c>] (show_stack) from [<c011dab4>] (__warn+0xd8/0xf0) [<c011dab4>] (__warn) from [<c011db10>] (warn_slowpath_fmt+0x44/0x6c) [<c011db10>] (warn_slowpath_fmt) from [<c043898c>] (clk_core_enable+0x2c/0x1b0) [<c043898c>] (clk_core_enable) from [<c0439ec8>] (clk_core_enable_lock+0x18/0x2c) [<c0439ec8>] (clk_core_enable_lock) from [<c0436698>] (pxa168fb_probe+0x464/0x6ac) [<c0436698>] (pxa168fb_probe) from [<c04779a0>] (platform_drv_probe+0x48/0x94) [<c04779a0>] (platform_drv_probe) from [<c0475bec>] (driver_probe_device+0x328/0x470) [<c0475bec>] (driver_probe_device) from [<c0475de4>] (__driver_attach+0xb0/0x124) [<c0475de4>] (__driver_attach) from [<c0473c38>] (bus_for_each_dev+0x64/0xa0) [<c0473c38>] (bus_for_each_dev) from [<c0474ee0>] (bus_add_driver+0x1b8/0x230) [<c0474ee0>] (bus_add_driver) from [<c0476a20>] (driver_register+0xac/0xf0) [<c0476a20>] (driver_register) from [<c0102dd4>] (do_one_initcall+0xb8/0x1f0) [<c0102dd4>] (do_one_initcall) from [<c0b010a0>] (kernel_init_freeable+0x294/0x2e0) [<c0b010a0>] (kernel_init_freeable) from [<c07e9eb8>] (kernel_init+0x8/0x10c) [<c07e9eb8>] (kernel_init) from [<c01010e8>] (ret_from_fork+0x14/0x2c) Exception stack(0xd008bfb0 to 0xd008bff8) bfa0: 00000000 00000000 00000000 00000000 bfc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 bfe0: 00000000 00000000 00000000 00000000 00000013 00000000 ---[ end trace c0af40f9e2ed7cb4 ]---
Signed-off-by: Lubomir Rintel lkundrak@v3.sk [b.zolnierkie: enhance patch description a bit] Signed-off-by: Bartlomiej Zolnierkiewicz b.zolnierkie@samsung.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/video/fbdev/pxa168fb.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/video/fbdev/pxa168fb.c b/drivers/video/fbdev/pxa168fb.c index def3a501acd6..d059d04c63ac 100644 --- a/drivers/video/fbdev/pxa168fb.c +++ b/drivers/video/fbdev/pxa168fb.c @@ -712,7 +712,7 @@ static int pxa168fb_probe(struct platform_device *pdev) /* * enable controller clock */ - clk_enable(fbi->clk); + clk_prepare_enable(fbi->clk);
pxa168fb_set_par(info);
@@ -767,7 +767,7 @@ static int pxa168fb_probe(struct platform_device *pdev) failed_free_cmap: fb_dealloc_cmap(&info->cmap); failed_free_clk: - clk_disable(fbi->clk); + clk_disable_unprepare(fbi->clk); failed_free_fbmem: dma_free_coherent(fbi->dev, info->fix.smem_len, info->screen_base, fbi->fb_start_dma); @@ -807,7 +807,7 @@ static int pxa168fb_remove(struct platform_device *pdev) dma_free_wc(fbi->dev, PAGE_ALIGN(info->fix.smem_len), info->screen_base, info->fix.smem_start);
- clk_disable(fbi->clk); + clk_disable_unprepare(fbi->clk);
framebuffer_release(info);
From: Nathan Chancellor natechancellor@gmail.com
[ Upstream commit a898fba32229efd5e6b6154f83fa86a7145156b9 ]
Clang warns when one enumerated type is implicitly converted to another.
drivers/net/ethernet/qlogic/qed/qed_sp_commands.c:163:25: warning: implicit conversion from enumeration type 'enum tunnel_clss' to different enumeration type 'enum qed_tunn_clss' [-Wenum-conversion] p_tun->vxlan.tun_cls = type; ~ ^~~~ drivers/net/ethernet/qlogic/qed/qed_sp_commands.c:165:26: warning: implicit conversion from enumeration type 'enum tunnel_clss' to different enumeration type 'enum qed_tunn_clss' [-Wenum-conversion] p_tun->l2_gre.tun_cls = type; ~ ^~~~ drivers/net/ethernet/qlogic/qed/qed_sp_commands.c:167:26: warning: implicit conversion from enumeration type 'enum tunnel_clss' to different enumeration type 'enum qed_tunn_clss' [-Wenum-conversion] p_tun->ip_gre.tun_cls = type; ~ ^~~~ drivers/net/ethernet/qlogic/qed/qed_sp_commands.c:169:29: warning: implicit conversion from enumeration type 'enum tunnel_clss' to different enumeration type 'enum qed_tunn_clss' [-Wenum-conversion] p_tun->l2_geneve.tun_cls = type; ~ ^~~~ drivers/net/ethernet/qlogic/qed/qed_sp_commands.c:171:29: warning: implicit conversion from enumeration type 'enum tunnel_clss' to different enumeration type 'enum qed_tunn_clss' [-Wenum-conversion] p_tun->ip_geneve.tun_cls = type; ~ ^~~~ 5 warnings generated.
Avoid this by changing type to an int.
Link: https://github.com/ClangBuiltLinux/linux/issues/125 Signed-off-by: Nathan Chancellor natechancellor@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/qlogic/qed/qed_sp_commands.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c index 46d0c3cb83a5..d7c5965328be 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c @@ -154,7 +154,7 @@ qed_set_pf_update_tunn_mode(struct qed_tunnel_info *p_tun, static void qed_set_tunn_cls_info(struct qed_tunnel_info *p_tun, struct qed_tunnel_info *p_src) { - enum tunnel_clss type; + int type;
p_tun->b_update_rx_cls = p_src->b_update_rx_cls; p_tun->b_update_tx_cls = p_src->b_update_tx_cls;
From: Nathan Chancellor natechancellor@gmail.com
[ Upstream commit db803f36e56f23b5a2266807e190d1dc11554d54 ]
Clang complains when one enumerated type is implicitly converted to another.
drivers/net/ethernet/qlogic/qed/qed_vf.c:686:6: warning: implicit conversion from enumeration type 'enum qed_tunn_mode' to different enumeration type 'enum qed_tunn_clss' [-Wenum-conversion] QED_MODE_L2GENEVE_TUNN, ^~~~~~~~~~~~~~~~~~~~~~
Update mask's parameter to expect qed_tunn_mode, which is what was intended.
Link: https://github.com/ClangBuiltLinux/linux/issues/125 Signed-off-by: Nathan Chancellor natechancellor@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/qlogic/qed/qed_vf.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c index 6eb85db69f9a..b8b1a791a4fa 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.c +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c @@ -572,7 +572,7 @@ int qed_vf_hw_prepare(struct qed_hwfn *p_hwfn) static void __qed_vf_prep_tunn_req_tlv(struct vfpf_update_tunn_param_tlv *p_req, struct qed_tunn_update_type *p_src, - enum qed_tunn_clss mask, u8 *p_cls) + enum qed_tunn_mode mask, u8 *p_cls) { if (p_src->b_update_mode) { p_req->tun_mode_update_mask |= BIT(mask); @@ -587,7 +587,7 @@ __qed_vf_prep_tunn_req_tlv(struct vfpf_update_tunn_param_tlv *p_req, static void qed_vf_prep_tunn_req_tlv(struct vfpf_update_tunn_param_tlv *p_req, struct qed_tunn_update_type *p_src, - enum qed_tunn_clss mask, + enum qed_tunn_mode mask, u8 *p_cls, struct qed_tunn_update_udp_port *p_port, u8 *p_update_port, u16 *p_udp_port) {
From: Nathan Chancellor natechancellor@gmail.com
[ Upstream commit d3a315795b4ce8b105a64a90699103121bde04a8 ]
Clang warns when one enumerated type is implicitly converted to another.
drivers/net/ethernet/qlogic/qed/qed_roce.c:153:12: warning: implicit conversion from enumeration type 'enum roce_mode' to different enumeration type 'enum roce_flavor' [-Wenum-conversion] flavor = ROCE_V2_IPV6; ~ ^~~~~~~~~~~~ drivers/net/ethernet/qlogic/qed/qed_roce.c:156:12: warning: implicit conversion from enumeration type 'enum roce_mode' to different enumeration type 'enum roce_flavor' [-Wenum-conversion] flavor = MAX_ROCE_MODE; ~ ^~~~~~~~~~~~~ 2 warnings generated.
Use the appropriate values from the expected type, roce_flavor:
ROCE_V2_IPV6 = RROCE_IPV6 = 2 MAX_ROCE_MODE = MAX_ROCE_FLAVOR = 3
While we're add it, ditch the local variable flavor, we can just return the value directly from the switch statement.
Link: https://github.com/ClangBuiltLinux/linux/issues/125 Signed-off-by: Nathan Chancellor natechancellor@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/qlogic/qed/qed_roce.c | 15 ++++----------- 1 file changed, 4 insertions(+), 11 deletions(-)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c index fb7c2d1562ae..bedbf840fd7d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_roce.c +++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c @@ -129,23 +129,16 @@ static void qed_rdma_copy_gids(struct qed_rdma_qp *qp, __le32 *src_gid,
static enum roce_flavor qed_roce_mode_to_flavor(enum roce_mode roce_mode) { - enum roce_flavor flavor; - switch (roce_mode) { case ROCE_V1: - flavor = PLAIN_ROCE; - break; + return PLAIN_ROCE; case ROCE_V2_IPV4: - flavor = RROCE_IPV4; - break; + return RROCE_IPV4; case ROCE_V2_IPV6: - flavor = ROCE_V2_IPV6; - break; + return RROCE_IPV6; default: - flavor = MAX_ROCE_MODE; - break; + return MAX_ROCE_FLAVOR; } - return flavor; }
void qed_roce_free_cid_pair(struct qed_hwfn *p_hwfn, u16 cid)
From: Mahesh Bandewar maheshb@google.com
[ Upstream commit 6a9e461f6fe4434e6172304b69774daff9a3ac4c ]
Commit b89f04c61efe ("bonding: deliver link-local packets with skb->dev set to link that packets arrived on") changed the behavior of how link-local-multicast packets are processed. The change in the behavior broke some legacy use cases where these packets are expected to arrive on bonding master device also.
This patch passes the packet to the stack with the link it arrived on as well as passes to the bonding-master device to preserve the legacy use case.
Fixes: b89f04c61efe ("bonding: deliver link-local packets with skb->dev set to link that packets arrived on") Reported-by: Michal Soltys soltys@ziu.info Signed-off-by: Mahesh Bandewar maheshb@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/bonding/bond_main.c | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 15aedb64a02b..4cee9c5b2d5f 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1176,9 +1176,26 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb) } }
- /* don't change skb->dev for link-local packets */ - if (is_link_local_ether_addr(eth_hdr(skb)->h_dest)) + /* Link-local multicast packets should be passed to the + * stack on the link they arrive as well as pass them to the + * bond-master device. These packets are mostly usable when + * stack receives it with the link on which they arrive + * (e.g. LLDP) they also must be available on master. Some of + * the use cases include (but are not limited to): LLDP agents + * that must be able to operate both on enslaved interfaces as + * well as on bonds themselves; linux bridges that must be able + * to process/pass BPDUs from attached bonds when any kind of + * STP version is enabled on the network. + */ + if (is_link_local_ether_addr(eth_hdr(skb)->h_dest)) { + struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); + + if (nskb) { + nskb->dev = bond->dev; + netif_rx(nskb); + } return RX_HANDLER_PASS; + } if (bond_should_deliver_exact_match(skb, slave, bond)) return RX_HANDLER_EXACT;
From: Mahesh Bandewar maheshb@google.com
[ Upstream commit d4859d749aa7090ffb743d15648adb962a1baeae ]
Syzkaller reported this on a slightly older kernel but it's still applicable to the current kernel -
====================================================== WARNING: possible circular locking dependency detected 4.18.0-next-20180823+ #46 Not tainted ------------------------------------------------------ syz-executor4/26841 is trying to acquire lock: 00000000dd41ef48 ((wq_completion)bond_dev->name){+.+.}, at: flush_workqueue+0x2db/0x1e10 kernel/workqueue.c:2652
but task is already holding lock: 00000000768ab431 (rtnl_mutex){+.+.}, at: rtnl_lock net/core/rtnetlink.c:77 [inline] 00000000768ab431 (rtnl_mutex){+.+.}, at: rtnetlink_rcv_msg+0x412/0xc30 net/core/rtnetlink.c:4708
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #2 (rtnl_mutex){+.+.}: __mutex_lock_common kernel/locking/mutex.c:925 [inline] __mutex_lock+0x171/0x1700 kernel/locking/mutex.c:1073 mutex_lock_nested+0x16/0x20 kernel/locking/mutex.c:1088 rtnl_lock+0x17/0x20 net/core/rtnetlink.c:77 bond_netdev_notify drivers/net/bonding/bond_main.c:1310 [inline] bond_netdev_notify_work+0x44/0xd0 drivers/net/bonding/bond_main.c:1320 process_one_work+0xc73/0x1aa0 kernel/workqueue.c:2153 worker_thread+0x189/0x13c0 kernel/workqueue.c:2296 kthread+0x35a/0x420 kernel/kthread.c:246 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:415
-> #1 ((work_completion)(&(&nnw->work)->work)){+.+.}: process_one_work+0xc0b/0x1aa0 kernel/workqueue.c:2129 worker_thread+0x189/0x13c0 kernel/workqueue.c:2296 kthread+0x35a/0x420 kernel/kthread.c:246 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:415
-> #0 ((wq_completion)bond_dev->name){+.+.}: lock_acquire+0x1e4/0x4f0 kernel/locking/lockdep.c:3901 flush_workqueue+0x30a/0x1e10 kernel/workqueue.c:2655 drain_workqueue+0x2a9/0x640 kernel/workqueue.c:2820 destroy_workqueue+0xc6/0x9d0 kernel/workqueue.c:4155 __alloc_workqueue_key+0xef9/0x1190 kernel/workqueue.c:4138 bond_init+0x269/0x940 drivers/net/bonding/bond_main.c:4734 register_netdevice+0x337/0x1100 net/core/dev.c:8410 bond_newlink+0x49/0xa0 drivers/net/bonding/bond_netlink.c:453 rtnl_newlink+0xef4/0x1d50 net/core/rtnetlink.c:3099 rtnetlink_rcv_msg+0x46e/0xc30 net/core/rtnetlink.c:4711 netlink_rcv_skb+0x172/0x440 net/netlink/af_netlink.c:2454 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:4729 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x5a0/0x760 net/netlink/af_netlink.c:1343 netlink_sendmsg+0xa18/0xfc0 net/netlink/af_netlink.c:1908 sock_sendmsg_nosec net/socket.c:622 [inline] sock_sendmsg+0xd5/0x120 net/socket.c:632 ___sys_sendmsg+0x7fd/0x930 net/socket.c:2115 __sys_sendmsg+0x11d/0x290 net/socket.c:2153 __do_sys_sendmsg net/socket.c:2162 [inline] __se_sys_sendmsg net/socket.c:2160 [inline] __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2160 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe
other info that might help us debug this:
Chain exists of: (wq_completion)bond_dev->name --> (work_completion)(&(&nnw->work)->work) --> rtnl_mutex
Possible unsafe locking scenario:
CPU0 CPU1 ---- ---- lock(rtnl_mutex); lock((work_completion)(&(&nnw->work)->work)); lock(rtnl_mutex); lock((wq_completion)bond_dev->name);
*** DEADLOCK ***
1 lock held by syz-executor4/26841:
stack backtrace: CPU: 1 PID: 26841 Comm: syz-executor4 Not tainted 4.18.0-next-20180823+ #46 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1c9/0x2b4 lib/dump_stack.c:113 print_circular_bug.isra.34.cold.55+0x1bd/0x27d kernel/locking/lockdep.c:1222 check_prev_add kernel/locking/lockdep.c:1862 [inline] check_prevs_add kernel/locking/lockdep.c:1975 [inline] validate_chain kernel/locking/lockdep.c:2416 [inline] __lock_acquire+0x3449/0x5020 kernel/locking/lockdep.c:3412 lock_acquire+0x1e4/0x4f0 kernel/locking/lockdep.c:3901 flush_workqueue+0x30a/0x1e10 kernel/workqueue.c:2655 drain_workqueue+0x2a9/0x640 kernel/workqueue.c:2820 destroy_workqueue+0xc6/0x9d0 kernel/workqueue.c:4155 __alloc_workqueue_key+0xef9/0x1190 kernel/workqueue.c:4138 bond_init+0x269/0x940 drivers/net/bonding/bond_main.c:4734 register_netdevice+0x337/0x1100 net/core/dev.c:8410 bond_newlink+0x49/0xa0 drivers/net/bonding/bond_netlink.c:453 rtnl_newlink+0xef4/0x1d50 net/core/rtnetlink.c:3099 rtnetlink_rcv_msg+0x46e/0xc30 net/core/rtnetlink.c:4711 netlink_rcv_skb+0x172/0x440 net/netlink/af_netlink.c:2454 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:4729 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x5a0/0x760 net/netlink/af_netlink.c:1343 netlink_sendmsg+0xa18/0xfc0 net/netlink/af_netlink.c:1908 sock_sendmsg_nosec net/socket.c:622 [inline] sock_sendmsg+0xd5/0x120 net/socket.c:632 ___sys_sendmsg+0x7fd/0x930 net/socket.c:2115 __sys_sendmsg+0x11d/0x290 net/socket.c:2153 __do_sys_sendmsg net/socket.c:2162 [inline] __se_sys_sendmsg net/socket.c:2160 [inline] __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2160 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x457089 Code: fd b4 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 cb b4 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f2df20a5c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007f2df20a66d4 RCX: 0000000000457089 RDX: 0000000000000000 RSI: 0000000020000180 RDI: 0000000000000003 RBP: 0000000000930140 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff R13: 00000000004d40b8 R14: 00000000004c8ad8 R15: 0000000000000001
Signed-off-by: Mahesh Bandewar maheshb@google.com Signed-off-by: David S. Miller davem@davemloft.net
Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/bonding/bond_main.c | 43 +++++++++++++-------------------- include/net/bonding.h | 7 +----- 2 files changed, 18 insertions(+), 32 deletions(-)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 4cee9c5b2d5f..b880126e616b 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -210,6 +210,7 @@ static void bond_get_stats(struct net_device *bond_dev, static void bond_slave_arr_handler(struct work_struct *work); static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act, int mod); +static void bond_netdev_notify_work(struct work_struct *work);
/*---------------------------- General routines -----------------------------*/
@@ -1271,6 +1272,8 @@ static struct slave *bond_alloc_slave(struct bonding *bond) return NULL; } } + INIT_DELAYED_WORK(&slave->notify_work, bond_netdev_notify_work); + return slave; }
@@ -1278,6 +1281,7 @@ static void bond_free_slave(struct slave *slave) { struct bonding *bond = bond_get_bond_by_slave(slave);
+ cancel_delayed_work_sync(&slave->notify_work); if (BOND_MODE(bond) == BOND_MODE_8023AD) kfree(SLAVE_AD_INFO(slave));
@@ -1299,39 +1303,26 @@ static void bond_fill_ifslave(struct slave *slave, struct ifslave *info) info->link_failure_count = slave->link_failure_count; }
-static void bond_netdev_notify(struct net_device *dev, - struct netdev_bonding_info *info) -{ - rtnl_lock(); - netdev_bonding_info_change(dev, info); - rtnl_unlock(); -} - static void bond_netdev_notify_work(struct work_struct *_work) { - struct netdev_notify_work *w = - container_of(_work, struct netdev_notify_work, work.work); + struct slave *slave = container_of(_work, struct slave, + notify_work.work); + + if (rtnl_trylock()) { + struct netdev_bonding_info binfo;
- bond_netdev_notify(w->dev, &w->bonding_info); - dev_put(w->dev); - kfree(w); + bond_fill_ifslave(slave, &binfo.slave); + bond_fill_ifbond(slave->bond, &binfo.master); + netdev_bonding_info_change(slave->dev, &binfo); + rtnl_unlock(); + } else { + queue_delayed_work(slave->bond->wq, &slave->notify_work, 1); + } }
void bond_queue_slave_event(struct slave *slave) { - struct bonding *bond = slave->bond; - struct netdev_notify_work *nnw = kzalloc(sizeof(*nnw), GFP_ATOMIC); - - if (!nnw) - return; - - dev_hold(slave->dev); - nnw->dev = slave->dev; - bond_fill_ifslave(slave, &nnw->bonding_info.slave); - bond_fill_ifbond(bond, &nnw->bonding_info.master); - INIT_DELAYED_WORK(&nnw->work, bond_netdev_notify_work); - - queue_delayed_work(slave->bond->wq, &nnw->work, 0); + queue_delayed_work(slave->bond->wq, &slave->notify_work, 0); }
void bond_lower_state_changed(struct slave *slave) diff --git a/include/net/bonding.h b/include/net/bonding.h index 73799da57400..04008209506a 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -139,12 +139,6 @@ struct bond_parm_tbl { int mode; };
-struct netdev_notify_work { - struct delayed_work work; - struct net_device *dev; - struct netdev_bonding_info bonding_info; -}; - struct slave { struct net_device *dev; /* first - useful for panic debug */ struct bonding *bond; /* our master */ @@ -172,6 +166,7 @@ struct slave { #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *np; #endif + struct delayed_work notify_work; struct kobject kobj; struct rtnl_link_stats64 slave_stats; };
From: Nathan Chancellor natechancellor@gmail.com
[ Upstream commit 1c492a9d55ba99079210ed901dd8a5423f980487 ]
Clang warns when a constant is used in a boolean context as it thinks a bitwise operation may have been intended.
drivers/net/ethernet/qlogic/qed/qed_vf.c:415:27: warning: use of logical '&&' with constant operand [-Wconstant-logical-operand] if (!p_iov->b_pre_fp_hsi && ^ drivers/net/ethernet/qlogic/qed/qed_vf.c:415:27: note: use '&' for a bitwise operation if (!p_iov->b_pre_fp_hsi && ^~ & drivers/net/ethernet/qlogic/qed/qed_vf.c:415:27: note: remove constant to silence this warning if (!p_iov->b_pre_fp_hsi && ~^~ 1 warning generated.
This has been here since commit 1fe614d10f45 ("qed: Relax VF firmware requirements") and I am not entirely sure why since 0 isn't a special case. Just remove the statement causing Clang to warn since it isn't required.
Link: https://github.com/ClangBuiltLinux/linux/issues/126 Signed-off-by: Nathan Chancellor natechancellor@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/qlogic/qed/qed_vf.c | 1 - 1 file changed, 1 deletion(-)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c index b8b1a791a4fa..dd8ebf6d380f 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.c +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c @@ -413,7 +413,6 @@ static int qed_vf_pf_acquire(struct qed_hwfn *p_hwfn) }
if (!p_iov->b_pre_fp_hsi && - ETH_HSI_VER_MINOR && (resp->pfdev_info.minor_fp_hsi < ETH_HSI_VER_MINOR)) { DP_INFO(p_hwfn, "PF is using older fastpath HSI; %02x.%02x is configured\n",
From: Nathan Chancellor natechancellor@gmail.com
[ Upstream commit 77f2d753819b7d50c16abfb778caf1fe075faed0 ]
Clang warns when one enumerated type is implicitly converted to another.
drivers/net/ethernet/qlogic/qed/qed_iwarp.c:1713:25: warning: implicit conversion from enumeration type 'enum tcp_ip_version' to different enumeration type 'enum qed_tcp_ip_version' [-Wenum-conversion] cm_info->ip_version = TCP_IPV4; ~ ^~~~~~~~ drivers/net/ethernet/qlogic/qed/qed_iwarp.c:1733:25: warning: implicit conversion from enumeration type 'enum tcp_ip_version' to different enumeration type 'enum qed_tcp_ip_version' [-Wenum-conversion] cm_info->ip_version = TCP_IPV6; ~ ^~~~~~~~ 2 warnings generated.
Use the appropriate values from the expected type, qed_tcp_ip_version:
TCP_IPV4 = QED_TCP_IPV4 = 0 TCP_IPV6 = QED_TCP_IPV6 = 1
Link: https://github.com/ClangBuiltLinux/linux/issues/125 Signed-off-by: Nathan Chancellor natechancellor@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/qlogic/qed/qed_iwarp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index e41f28602535..eb666877d1aa 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -1672,7 +1672,7 @@ qed_iwarp_parse_rx_pkt(struct qed_hwfn *p_hwfn,
cm_info->local_ip[0] = ntohl(iph->daddr); cm_info->remote_ip[0] = ntohl(iph->saddr); - cm_info->ip_version = TCP_IPV4; + cm_info->ip_version = QED_TCP_IPV4;
ip_hlen = (iph->ihl) * sizeof(u32); *payload_len = ntohs(iph->tot_len) - ip_hlen; @@ -1692,7 +1692,7 @@ qed_iwarp_parse_rx_pkt(struct qed_hwfn *p_hwfn, cm_info->remote_ip[i] = ntohl(ip6h->saddr.in6_u.u6_addr32[i]); } - cm_info->ip_version = TCP_IPV6; + cm_info->ip_version = QED_TCP_IPV6;
ip_hlen = sizeof(*ip6h); *payload_len = ntohs(ip6h->payload_len);
From: Michael Chan michael.chan@broadcom.com
[ Upstream commit 73f21c653f930f438d53eed29b5e4c65c8a0f906 ]
The current netpoll implementation in the bnxt_en driver has problems that may miss TX completion events. bnxt_poll_work() in effect is only handling at most 1 TX packet before exiting. In addition, there may be in flight TX completions that ->poll() may miss even after we fix bnxt_poll_work() to handle all visible TX completions. netpoll may not call ->poll() again and HW may not generate IRQ because the driver does not ARM the IRQ when the budget (0 for netpoll) is reached.
We fix it by handling all TX completions and to always ARM the IRQ when we exit ->poll() with 0 budget.
Also, the logic to ACK the completion ring in case it is almost filled with TX completions need to be adjusted to take care of the 0 budget case, as discussed with Eric Dumazet edumazet@google.com
Reported-by: Song Liu songliubraving@fb.com Reviewed-by: Song Liu songliubraving@fb.com Tested-by: Song Liu songliubraving@fb.com Signed-off-by: Michael Chan michael.chan@broadcom.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 937db8019289..a741c0648b25 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1864,8 +1864,11 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget) if (TX_CMP_TYPE(txcmp) == CMP_TYPE_TX_L2_CMP) { tx_pkts++; /* return full budget so NAPI will complete. */ - if (unlikely(tx_pkts > bp->tx_wake_thresh)) + if (unlikely(tx_pkts > bp->tx_wake_thresh)) { rx_pkts = budget; + raw_cons = NEXT_RAW_CMP(raw_cons); + break; + } } else if ((TX_CMP_TYPE(txcmp) & 0x30) == 0x10) { if (likely(budget)) rc = bnxt_rx_pkt(bp, bnapi, &raw_cons, &event); @@ -1893,7 +1896,7 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget) } raw_cons = NEXT_RAW_CMP(raw_cons);
- if (rx_pkts == budget) + if (rx_pkts && rx_pkts == budget) break; }
@@ -2007,8 +2010,12 @@ static int bnxt_poll(struct napi_struct *napi, int budget) while (1) { work_done += bnxt_poll_work(bp, bnapi, budget - work_done);
- if (work_done >= budget) + if (work_done >= budget) { + if (!budget) + BNXT_CP_DB_REARM(cpr->cp_doorbell, + cpr->cp_raw_cons); break; + }
if (!bnxt_has_work(bp, cpr)) { if (napi_complete_done(napi, work_done))
From: Masashi Honma masashi.honma@gmail.com
[ Upstream commit 1222a16014888ed9733c11e221730d4a8196222b ]
Use array_index_nospec() to sanitize i with respect to speculation.
Note that the user doesn't control i directly, but can make it out of bounds by not finding a threshold in the array.
Signed-off-by: Masashi Honma masashi.honma@gmail.com [add note about user control, as explained by Masashi] Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/wireless/nl80211.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-)
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 5e7c9b361e8a..46e9812d13c0 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -9720,7 +9720,7 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev = dev->ieee80211_ptr; s32 last, low, high; u32 hyst; - int i, n; + int i, n, low_index; int err;
/* RSSI reporting disabled? */ @@ -9757,10 +9757,19 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, if (last < wdev->cqm_config->rssi_thresholds[i]) break;
- low = i > 0 ? - (wdev->cqm_config->rssi_thresholds[i - 1] - hyst) : S32_MIN; - high = i < n ? - (wdev->cqm_config->rssi_thresholds[i] + hyst - 1) : S32_MAX; + low_index = i - 1; + if (low_index >= 0) { + low_index = array_index_nospec(low_index, n); + low = wdev->cqm_config->rssi_thresholds[low_index] - hyst; + } else { + low = S32_MIN; + } + if (i < n) { + i = array_index_nospec(i, n); + high = wdev->cqm_config->rssi_thresholds[i] + hyst - 1; + } else { + high = S32_MAX; + }
return rdev_set_cqm_rssi_range_config(rdev, dev, low, high); }
From: Florian Fainelli f.fainelli@gmail.com
[ Upstream commit c4ce446e33d7a0e978256ac6fea4c80e59d9de5f ]
The driver currently silently accepts unsupported Wake-on-LAN modes (other than WAKE_PHY or WAKE_MAGIC) without reporting that to the user, which is confusing.
Fixes: 2e55cc7210fe ("[PATCH] USB: usbnet (3/9) module for ASIX Ethernet adapters") Signed-off-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/usb/asix_common.c | 3 +++ 1 file changed, 3 insertions(+)
diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c index 522d2900cd1d..e9fcf6ef716a 100644 --- a/drivers/net/usb/asix_common.c +++ b/drivers/net/usb/asix_common.c @@ -607,6 +607,9 @@ int asix_set_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo) struct usbnet *dev = netdev_priv(net); u8 opt = 0;
+ if (wolinfo->wolopts & ~(WAKE_PHY | WAKE_MAGIC)) + return -EINVAL; + if (wolinfo->wolopts & WAKE_PHY) opt |= AX_MONITOR_LINK; if (wolinfo->wolopts & WAKE_MAGIC)
From: Florian Fainelli f.fainelli@gmail.com
[ Upstream commit 5ba6b4aa9a410c5e2c6417df52b5e2118ea9b467 ]
The driver currently silently accepts unsupported Wake-on-LAN modes (other than WAKE_PHY or WAKE_MAGIC) without reporting that to the user, which is confusing.
Fixes: e2ca90c276e1 ("ax88179_178a: ASIX AX88179_178A USB 3.0/2.0 to gigabit ethernet adapter driver") Signed-off-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/usb/ax88179_178a.c | 3 +++ 1 file changed, 3 insertions(+)
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index f32261ecd215..0f69b77e8502 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -566,6 +566,9 @@ ax88179_set_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo) struct usbnet *dev = netdev_priv(net); u8 opt = 0;
+ if (wolinfo->wolopts & ~(WAKE_PHY | WAKE_MAGIC)) + return -EINVAL; + if (wolinfo->wolopts & WAKE_PHY) opt |= AX_MONITOR_MODE_RWLC; if (wolinfo->wolopts & WAKE_MAGIC)
From: Florian Fainelli f.fainelli@gmail.com
[ Upstream commit eb9ad088f96653a26b340f7c447c44cf023d5cdc ]
The driver supports a fair amount of Wake-on-LAN modes, but is not checking that the user specified one that is supported.
Fixes: 55d7de9de6c3 ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet device driver") Signed-off-by: Florian Fainelli f.fainelli@gmail.com Reviewed-by: Woojung Huh Woojung.Huh@Microchip.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/usb/lan78xx.c | 17 ++++------------- 1 file changed, 4 insertions(+), 13 deletions(-)
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 9e3f632e22f1..00ddcaf09014 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -1375,19 +1375,10 @@ static int lan78xx_set_wol(struct net_device *netdev, if (ret < 0) return ret;
- pdata->wol = 0; - if (wol->wolopts & WAKE_UCAST) - pdata->wol |= WAKE_UCAST; - if (wol->wolopts & WAKE_MCAST) - pdata->wol |= WAKE_MCAST; - if (wol->wolopts & WAKE_BCAST) - pdata->wol |= WAKE_BCAST; - if (wol->wolopts & WAKE_MAGIC) - pdata->wol |= WAKE_MAGIC; - if (wol->wolopts & WAKE_PHY) - pdata->wol |= WAKE_PHY; - if (wol->wolopts & WAKE_ARP) - pdata->wol |= WAKE_ARP; + if (wol->wolopts & ~WAKE_ALL) + return -EINVAL; + + pdata->wol = wol->wolopts;
device_set_wakeup_enable(&dev->udev->dev, (bool)wol->wolopts);
From: Florian Fainelli f.fainelli@gmail.com
[ Upstream commit c5cb93e994ffb43b7b3b1ff10b9f928f54574a36 ]
The driver currently silently accepts unsupported Wake-on-LAN modes (other than WAKE_PHY or WAKE_MAGIC) without reporting that to the user, which is confusing.
Fixes: 19a38d8e0aa3 ("USB2NET : SR9800 : One chip USB2.0 USB2NET SR9800 Device Driver Support") Signed-off-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/usb/sr9800.c | 3 +++ 1 file changed, 3 insertions(+)
diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c index 9277a0f228df..35f39f23d881 100644 --- a/drivers/net/usb/sr9800.c +++ b/drivers/net/usb/sr9800.c @@ -421,6 +421,9 @@ sr_set_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo) struct usbnet *dev = netdev_priv(net); u8 opt = 0;
+ if (wolinfo->wolopts & ~(WAKE_PHY | WAKE_MAGIC)) + return -EINVAL; + if (wolinfo->wolopts & WAKE_PHY) opt |= SR_MONITOR_LINK; if (wolinfo->wolopts & WAKE_MAGIC)
From: Florian Fainelli f.fainelli@gmail.com
[ Upstream commit f2750df1548bd8a2b060eb609fc43ca82811af4c ]
The driver does not check for Wake-on-LAN modes specified by an user, but will conditionally set the device as wake-up enabled or not based on that, which could be a very confusing user experience.
Fixes: 21ff2e8976b1 ("r8152: support WOL") Signed-off-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/usb/r8152.c | 3 +++ 1 file changed, 3 insertions(+)
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 0fa64cc1a011..66beff4d7646 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -4497,6 +4497,9 @@ static int rtl8152_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) if (!rtl_can_wakeup(tp)) return -EOPNOTSUPP;
+ if (wol->wolopts & ~WAKE_ANY) + return -EINVAL; + ret = usb_autopm_get_interface(tp->intf); if (ret < 0) goto out_set_wol;
From: Florian Fainelli f.fainelli@gmail.com
[ Upstream commit 9c734b2769a73eea2e9e9767c0e0bf839ff23679 ]
The driver does not check for Wake-on-LAN modes specified by an user, but will conditionally set the device as wake-up enabled or not based on that, which could be a very confusing user experience.
Fixes: 6c636503260d ("smsc75xx: add wol magic packet support") Signed-off-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/usb/smsc75xx.c | 3 +++ 1 file changed, 3 insertions(+)
diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index 05553d252446..e5a4cbb366dc 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -731,6 +731,9 @@ static int smsc75xx_ethtool_set_wol(struct net_device *net, struct smsc75xx_priv *pdata = (struct smsc75xx_priv *)(dev->data[0]); int ret;
+ if (wolinfo->wolopts & ~SUPPORTED_WAKE) + return -EINVAL; + pdata->wolopts = wolinfo->wolopts & SUPPORTED_WAKE;
ret = device_set_wakeup_enable(&dev->udev->dev, pdata->wolopts);
From: Florian Fainelli f.fainelli@gmail.com
[ Upstream commit c530c471ba37bdd9fe1c7185b01455c00ae606fb ]
The driver does not check for Wake-on-LAN modes specified by an user, but will conditionally set the device as wake-up enabled or not based on that, which could be a very confusing user experience.
Fixes: e0e474a83c18 ("smsc95xx: add wol magic packet support") Signed-off-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/usb/smsc95xx.c | 3 +++ 1 file changed, 3 insertions(+)
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 309b88acd3d0..99e684e39d35 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -774,6 +774,9 @@ static int smsc95xx_ethtool_set_wol(struct net_device *net, struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]); int ret;
+ if (wolinfo->wolopts & ~SUPPORTED_WAKE) + return -EINVAL; + pdata->wolopts = wolinfo->wolopts & SUPPORTED_WAKE;
ret = device_set_wakeup_enable(&dev->udev->dev, pdata->wolopts);
From: Shahed Shaikh shahed.shaikh@cavium.com
[ Upstream commit c333fa0c4f220f8f7ea5acd6b0ebf3bf13fd684d ]
In regular NIC transmission flow, driver always configures MAC using Tx queue zero descriptor as a part of MAC learning flow. But with multi Tx queue supported NIC, regular transmission can occur on any non-zero Tx queue and from that context it uses Tx queue zero descriptor to configure MAC, at the same time TX queue zero could be used by another CPU for regular transmission which could lead to Tx queue zero descriptor corruption and cause FW abort.
This patch fixes this in such a way that driver always configures learned MAC address from the same Tx queue which is used for regular transmission.
Fixes: 7e2cf4feba05 ("qlcnic: change driver hardware interface mechanism") Signed-off-by: Shahed Shaikh shahed.shaikh@cavium.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/qlogic/qlcnic/qlcnic.h | 8 +++++--- drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c | 3 ++- drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h | 3 ++- drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h | 3 ++- drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c | 12 ++++++------ 5 files changed, 17 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h index 81312924df14..0c443ea98479 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h @@ -1800,7 +1800,8 @@ struct qlcnic_hardware_ops { int (*config_loopback) (struct qlcnic_adapter *, u8); int (*clear_loopback) (struct qlcnic_adapter *, u8); int (*config_promisc_mode) (struct qlcnic_adapter *, u32); - void (*change_l2_filter) (struct qlcnic_adapter *, u64 *, u16); + void (*change_l2_filter)(struct qlcnic_adapter *adapter, u64 *addr, + u16 vlan, struct qlcnic_host_tx_ring *tx_ring); int (*get_board_info) (struct qlcnic_adapter *); void (*set_mac_filter_count) (struct qlcnic_adapter *); void (*free_mac_list) (struct qlcnic_adapter *); @@ -2064,9 +2065,10 @@ static inline int qlcnic_nic_set_promisc(struct qlcnic_adapter *adapter, }
static inline void qlcnic_change_filter(struct qlcnic_adapter *adapter, - u64 *addr, u16 id) + u64 *addr, u16 vlan, + struct qlcnic_host_tx_ring *tx_ring) { - adapter->ahw->hw_ops->change_l2_filter(adapter, addr, id); + adapter->ahw->hw_ops->change_l2_filter(adapter, addr, vlan, tx_ring); }
static inline int qlcnic_get_board_info(struct qlcnic_adapter *adapter) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c index 46b0372dd032..1fc84d8f891b 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c @@ -2134,7 +2134,8 @@ int qlcnic_83xx_sre_macaddr_change(struct qlcnic_adapter *adapter, u8 *addr, }
void qlcnic_83xx_change_l2_filter(struct qlcnic_adapter *adapter, u64 *addr, - u16 vlan_id) + u16 vlan_id, + struct qlcnic_host_tx_ring *tx_ring) { u8 mac[ETH_ALEN]; memcpy(&mac, addr, ETH_ALEN); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h index b75a81246856..73fe2f64491d 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h @@ -550,7 +550,8 @@ int qlcnic_83xx_wrt_reg_indirect(struct qlcnic_adapter *, ulong, u32); int qlcnic_83xx_nic_set_promisc(struct qlcnic_adapter *, u32); int qlcnic_83xx_config_hw_lro(struct qlcnic_adapter *, int); int qlcnic_83xx_config_rss(struct qlcnic_adapter *, int); -void qlcnic_83xx_change_l2_filter(struct qlcnic_adapter *, u64 *, u16); +void qlcnic_83xx_change_l2_filter(struct qlcnic_adapter *adapter, u64 *addr, + u16 vlan, struct qlcnic_host_tx_ring *ring); int qlcnic_83xx_get_pci_info(struct qlcnic_adapter *, struct qlcnic_pci_info *); int qlcnic_83xx_set_nic_info(struct qlcnic_adapter *, struct qlcnic_info *); void qlcnic_83xx_initialize_nic(struct qlcnic_adapter *, int); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h index 4bb33af8e2b3..56a3bd9e37dc 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h @@ -173,7 +173,8 @@ int qlcnic_82xx_napi_add(struct qlcnic_adapter *adapter, struct net_device *netdev); void qlcnic_82xx_get_beacon_state(struct qlcnic_adapter *); void qlcnic_82xx_change_filter(struct qlcnic_adapter *adapter, - u64 *uaddr, u16 vlan_id); + u64 *uaddr, u16 vlan_id, + struct qlcnic_host_tx_ring *tx_ring); int qlcnic_82xx_config_intr_coalesce(struct qlcnic_adapter *, struct ethtool_coalesce *); int qlcnic_82xx_set_rx_coalesce(struct qlcnic_adapter *); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c index 84dd83031a1b..9647578cbe6a 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c @@ -268,13 +268,12 @@ static void qlcnic_add_lb_filter(struct qlcnic_adapter *adapter, }
void qlcnic_82xx_change_filter(struct qlcnic_adapter *adapter, u64 *uaddr, - u16 vlan_id) + u16 vlan_id, struct qlcnic_host_tx_ring *tx_ring) { struct cmd_desc_type0 *hwdesc; struct qlcnic_nic_req *req; struct qlcnic_mac_req *mac_req; struct qlcnic_vlan_req *vlan_req; - struct qlcnic_host_tx_ring *tx_ring = adapter->tx_ring; u32 producer; u64 word;
@@ -301,7 +300,8 @@ void qlcnic_82xx_change_filter(struct qlcnic_adapter *adapter, u64 *uaddr,
static void qlcnic_send_filter(struct qlcnic_adapter *adapter, struct cmd_desc_type0 *first_desc, - struct sk_buff *skb) + struct sk_buff *skb, + struct qlcnic_host_tx_ring *tx_ring) { struct vlan_ethhdr *vh = (struct vlan_ethhdr *)(skb->data); struct ethhdr *phdr = (struct ethhdr *)(skb->data); @@ -335,7 +335,7 @@ static void qlcnic_send_filter(struct qlcnic_adapter *adapter, tmp_fil->vlan_id == vlan_id) { if (jiffies > (QLCNIC_READD_AGE * HZ + tmp_fil->ftime)) qlcnic_change_filter(adapter, &src_addr, - vlan_id); + vlan_id, tx_ring); tmp_fil->ftime = jiffies; return; } @@ -350,7 +350,7 @@ static void qlcnic_send_filter(struct qlcnic_adapter *adapter, if (!fil) return;
- qlcnic_change_filter(adapter, &src_addr, vlan_id); + qlcnic_change_filter(adapter, &src_addr, vlan_id, tx_ring); fil->ftime = jiffies; fil->vlan_id = vlan_id; memcpy(fil->faddr, &src_addr, ETH_ALEN); @@ -766,7 +766,7 @@ netdev_tx_t qlcnic_xmit_frame(struct sk_buff *skb, struct net_device *netdev) }
if (adapter->drv_mac_learn) - qlcnic_send_filter(adapter, first_desc, skb); + qlcnic_send_filter(adapter, first_desc, skb, tx_ring);
tx_ring->tx_stats.tx_bytes += skb->len; tx_ring->tx_stats.xmit_called++;
From: Edgar Cherkasov echerkasov@dev.rtsoft.ru
[ Upstream commit 08d9db00fe0e300d6df976e6c294f974988226dd ]
The i2c-scmi driver crashes when the SMBus Write Block transaction is executed:
WARNING: CPU: 9 PID: 2194 at mm/page_alloc.c:3931 __alloc_pages_slowpath+0x9db/0xec0 Call Trace: ? get_page_from_freelist+0x49d/0x11f0 ? alloc_pages_current+0x6a/0xe0 ? new_slab+0x499/0x690 __alloc_pages_nodemask+0x265/0x280 alloc_pages_current+0x6a/0xe0 kmalloc_order+0x18/0x40 kmalloc_order_trace+0x24/0xb0 ? acpi_ut_allocate_object_desc_dbg+0x62/0x10c __kmalloc+0x203/0x220 acpi_os_allocate_zeroed+0x34/0x36 acpi_ut_copy_eobject_to_iobject+0x266/0x31e acpi_evaluate_object+0x166/0x3b2 acpi_smbus_cmi_access+0x144/0x530 [i2c_scmi] i2c_smbus_xfer+0xda/0x370 i2cdev_ioctl_smbus+0x1bd/0x270 i2cdev_ioctl+0xaa/0x250 do_vfs_ioctl+0xa4/0x600 SyS_ioctl+0x79/0x90 do_syscall_64+0x73/0x130 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 ACPI Error: Evaluating _SBW: 4 (20170831/smbus_cmi-185)
This problem occurs because the length of ACPI Buffer object is not defined/initialized in the code before a corresponding ACPI method is called. The obvious patch below fixes this issue.
Signed-off-by: Edgar Cherkasov echerkasov@dev.rtsoft.ru Acked-by: Viktor Krasnov vkrasnov@dev.rtsoft.ru Acked-by: Michael Brunner Michael.Brunner@kontron.com Signed-off-by: Wolfram Sang wsa@the-dreams.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/i2c/busses/i2c-scmi.c | 1 + 1 file changed, 1 insertion(+)
diff --git a/drivers/i2c/busses/i2c-scmi.c b/drivers/i2c/busses/i2c-scmi.c index 7aa7b9cb6203..efefcfa24a4c 100644 --- a/drivers/i2c/busses/i2c-scmi.c +++ b/drivers/i2c/busses/i2c-scmi.c @@ -152,6 +152,7 @@ acpi_smbus_cmi_access(struct i2c_adapter *adap, u16 addr, unsigned short flags, mt_params[3].type = ACPI_TYPE_INTEGER; mt_params[3].integer.value = len; mt_params[4].type = ACPI_TYPE_BUFFER; + mt_params[4].buffer.length = len; mt_params[4].buffer.pointer = data->block + 1; } break;
From: Yu Zhao yuzhao@google.com
[ Upstream commit 1db58529454742f67ebd96e3588315e880b72837 ]
reg_process_hint_country_ie() can free regulatory_request and return REG_REQ_ALREADY_SET. We shouldn't use regulatory_request after it's called. KASAN error was observed when this happens.
BUG: KASAN: use-after-free in reg_process_hint+0x839/0x8aa [cfg80211] Read of size 4 at addr ffff8800c430d434 by task kworker/1:3/89 <snipped> Workqueue: events reg_todo [cfg80211] Call Trace: dump_stack+0xc1/0x10c ? _atomic_dec_and_lock+0x1ad/0x1ad ? _raw_spin_lock_irqsave+0xa0/0xd2 print_address_description+0x86/0x26f ? reg_process_hint+0x839/0x8aa [cfg80211] kasan_report+0x241/0x29b reg_process_hint+0x839/0x8aa [cfg80211] reg_todo+0x204/0x5b9 [cfg80211] process_one_work+0x55f/0x8d0 ? worker_detach_from_pool+0x1b5/0x1b5 ? _raw_spin_unlock_irq+0x65/0xdd ? _raw_spin_unlock_irqrestore+0xf3/0xf3 worker_thread+0x5dd/0x841 ? kthread_parkme+0x1d/0x1d kthread+0x270/0x285 ? pr_cont_work+0xe3/0xe3 ? rcu_read_unlock_sched_notrace+0xca/0xca ret_from_fork+0x22/0x40
Allocated by task 2718: set_track+0x63/0xfa __kmalloc+0x119/0x1ac regulatory_hint_country_ie+0x38/0x329 [cfg80211] __cfg80211_connect_result+0x854/0xadd [cfg80211] cfg80211_rx_assoc_resp+0x3bc/0x4f0 [cfg80211] smsc95xx v1.0.6 ieee80211_sta_rx_queued_mgmt+0x1803/0x7ed5 [mac80211] ieee80211_iface_work+0x411/0x696 [mac80211] process_one_work+0x55f/0x8d0 worker_thread+0x5dd/0x841 kthread+0x270/0x285 ret_from_fork+0x22/0x40
Freed by task 89: set_track+0x63/0xfa kasan_slab_free+0x6a/0x87 kfree+0xdc/0x470 reg_process_hint+0x31e/0x8aa [cfg80211] reg_todo+0x204/0x5b9 [cfg80211] process_one_work+0x55f/0x8d0 worker_thread+0x5dd/0x841 kthread+0x270/0x285 ret_from_fork+0x22/0x40 <snipped>
Signed-off-by: Yu Zhao yuzhao@google.com Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/wireless/reg.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 6f032c7b8732..bd91de416035 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2170,11 +2170,12 @@ static void reg_process_hint(struct regulatory_request *reg_request) { struct wiphy *wiphy = NULL; enum reg_request_treatment treatment; + enum nl80211_reg_initiator initiator = reg_request->initiator;
if (reg_request->wiphy_idx != WIPHY_IDX_INVALID) wiphy = wiphy_idx_to_wiphy(reg_request->wiphy_idx);
- switch (reg_request->initiator) { + switch (initiator) { case NL80211_REGDOM_SET_BY_CORE: treatment = reg_process_hint_core(reg_request); break; @@ -2192,7 +2193,7 @@ static void reg_process_hint(struct regulatory_request *reg_request) treatment = reg_process_hint_country_ie(wiphy, reg_request); break; default: - WARN(1, "invalid initiator %d\n", reg_request->initiator); + WARN(1, "invalid initiator %d\n", initiator); goto out_free; }
@@ -2207,7 +2208,7 @@ static void reg_process_hint(struct regulatory_request *reg_request) */ if (treatment == REG_REQ_ALREADY_SET && wiphy && wiphy->regulatory_flags & REGULATORY_STRICT_REG) { - wiphy_update_regulatory(wiphy, reg_request->initiator); + wiphy_update_regulatory(wiphy, initiator); wiphy_all_share_dfs_chan_state(wiphy); reg_check_channels(); }
From: Eran Ben Elisha eranbe@mellanox.com
[ Upstream commit 11aa5800ed66ed0415b7509f02881c76417d212a ]
The code that deals with eswitch vport bw guarantee was going beyond the eswitch vport array limit, fix that. This was pointed out by the kernel address sanitizer (KASAN).
The error from KASAN log: [2018-09-15 15:04:45] BUG: KASAN: slab-out-of-bounds in mlx5_eswitch_set_vport_rate+0x8c1/0xae0 [mlx5_core]
Fixes: c9497c98901c ("net/mlx5: Add support for setting VF min rate") Signed-off-by: Eran Ben Elisha eranbe@mellanox.com Reviewed-by: Or Gerlitz ogerlitz@mellanox.com Signed-off-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index de72b66df3e5..1af9894abd95 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1922,7 +1922,7 @@ static u32 calculate_vports_min_rate_divider(struct mlx5_eswitch *esw) u32 max_guarantee = 0; int i;
- for (i = 0; i <= esw->total_vports; i++) { + for (i = 0; i < esw->total_vports; i++) { evport = &esw->vports[i]; if (!evport->enabled || evport->info.min_rate < max_guarantee) continue; @@ -1942,7 +1942,7 @@ static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider) int err; int i;
- for (i = 0; i <= esw->total_vports; i++) { + for (i = 0; i < esw->total_vports; i++) { evport = &esw->vports[i]; if (!evport->enabled) continue;
From: Jianbo Liu jianbol@mellanox.com
[ Upstream commit cee26487620bc9bc3c7db21b6984d91f7bae12ae ]
In flow steering, if asked to, the hardware matches on the first ethertype which is not vlan. It's possible to set a rule as follows, which is meant to match on untagged packet, but will match on a vlan packet: tc filter add dev eth0 parent ffff: protocol ip flower ...
To avoid this for packets with single tag, we set vlan masks to tell hardware to check the tags for every matched packet.
Fixes: 095b6cfd69ce ('net/mlx5e: Add TC vlan match parsing') Signed-off-by: Jianbo Liu jianbol@mellanox.com Reviewed-by: Or Gerlitz ogerlitz@mellanox.com Signed-off-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 3 +++ 1 file changed, 3 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index e28f9dab9ceb..9e0be077df9c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -864,6 +864,9 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_prio, mask->vlan_priority); MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_prio, key->vlan_priority); } + } else { + MLX5_SET(fte_match_set_lyr_2_4, headers_c, svlan_tag, 1); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, cvlan_tag, 1); }
if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
From: Peter Zijlstra peterz@infradead.org
[ Upstream commit a9f9772114c8b07ae75bcb3654bd017461248095 ]
When we unregister a PMU, we fail to serialize the @pmu_idr properly. Fix that by doing the entire thing under pmu_lock.
Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Arnaldo Carvalho de Melo acme@redhat.com Cc: Jiri Olsa jolsa@redhat.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Stephane Eranian eranian@google.com Cc: Thomas Gleixner tglx@linutronix.de Cc: Vince Weaver vincent.weaver@maine.edu Fixes: 2e80a82a49c4 ("perf: Dynamic pmu types") Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/events/core.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-)
diff --git a/kernel/events/core.c b/kernel/events/core.c index 4dbce29a9313..ee1c07c0b833 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -9020,9 +9020,7 @@ static void free_pmu_context(struct pmu *pmu) if (pmu->task_ctx_nr > perf_invalid_context) return;
- mutex_lock(&pmus_lock); free_percpu(pmu->pmu_cpu_context); - mutex_unlock(&pmus_lock); }
/* @@ -9278,12 +9276,8 @@ EXPORT_SYMBOL_GPL(perf_pmu_register);
void perf_pmu_unregister(struct pmu *pmu) { - int remove_device; - mutex_lock(&pmus_lock); - remove_device = pmu_bus_running; list_del_rcu(&pmu->entry); - mutex_unlock(&pmus_lock);
/* * We dereference the pmu list under both SRCU and regular RCU, so @@ -9295,13 +9289,14 @@ void perf_pmu_unregister(struct pmu *pmu) free_percpu(pmu->pmu_disable_count); if (pmu->type >= PERF_TYPE_MAX) idr_remove(&pmu_idr, pmu->type); - if (remove_device) { + if (pmu_bus_running) { if (pmu->nr_addr_filters) device_remove_file(pmu->dev, &dev_attr_nr_addr_filters); device_del(pmu->dev); put_device(pmu->dev); } free_pmu_context(pmu); + mutex_unlock(&pmus_lock); } EXPORT_SYMBOL_GPL(perf_pmu_unregister);
From: Jiri Olsa jolsa@redhat.com
[ Upstream commit cd6fb677ce7e460c25bdd66f689734102ec7d642 ]
Some of the scheduling tracepoints allow the perf_tp_event code to write to ring buffer under different cpu than the code is running on.
This results in corrupted ring buffer data demonstrated in following perf commands:
# perf record -e 'sched:sched_switch,sched:sched_wakeup' perf bench sched messaging # Running 'sched/messaging' benchmark: # 20 sender and receiver processes per group # 10 groups == 400 processes run
Total time: 0.383 [sec] [ perf record: Woken up 8 times to write data ] 0x42b890 [0]: failed to process type: -1765585640 [ perf record: Captured and wrote 4.825 MB perf.data (29669 samples) ]
# perf report --stdio 0x42b890 [0]: failed to process type: -1765585640
The reason for the corruption are some of the scheduling tracepoints, that have __perf_task dfined and thus allow to store data to another cpu ring buffer:
sched_waking sched_wakeup sched_wakeup_new sched_stat_wait sched_stat_sleep sched_stat_iowait sched_stat_blocked
The perf_tp_event function first store samples for current cpu related events defined for tracepoint:
hlist_for_each_entry_rcu(event, head, hlist_entry) perf_swevent_event(event, count, &data, regs);
And then iterates events of the 'task' and store the sample for any task's event that passes tracepoint checks:
ctx = rcu_dereference(task->perf_event_ctxp[perf_sw_context]);
list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { if (event->attr.type != PERF_TYPE_TRACEPOINT) continue; if (event->attr.config != entry->type) continue;
perf_swevent_event(event, count, &data, regs); }
Above code can race with same code running on another cpu, ending up with 2 cpus trying to store under the same ring buffer, which is specifically not allowed.
This patch prevents the problem, by allowing only events with the same current cpu to receive the event.
NOTE: this requires the use of (per-task-)per-cpu buffers for this feature to work; perf-record does this.
Signed-off-by: Jiri Olsa jolsa@kernel.org [peterz: small edits to Changelog] Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Andrew Vagin avagin@openvz.org Cc: Arnaldo Carvalho de Melo acme@kernel.org Cc: Arnaldo Carvalho de Melo acme@redhat.com Cc: Jiri Olsa jolsa@redhat.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Stephane Eranian eranian@google.com Cc: Thomas Gleixner tglx@linutronix.de Cc: Vince Weaver vincent.weaver@maine.edu Fixes: e6dab5ffab59 ("perf/trace: Add ability to set a target task for events") Link: http://lkml.kernel.org/r/20180923161343.GB15054@krava Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/events/core.c | 2 ++ 1 file changed, 2 insertions(+)
diff --git a/kernel/events/core.c b/kernel/events/core.c index ee1c07c0b833..991af683ef9e 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8058,6 +8058,8 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, goto unlock;
list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { + if (event->cpu != smp_processor_id()) + continue; if (event->attr.type != PERF_TYPE_TRACEPOINT) continue; if (event->attr.config != entry->type)
From: Kan Liang kan.liang@linux.intel.com
[ Upstream commit 9d92cfeaf5215158d26d2991be7f7ff865cb98f3 ]
The counters on M3UPI Link 0 and Link 3 don't count properly, and writing 0 to these counters may causes system crash on some machines.
The PCI BDF addresses of the M3UPI in the current code are incorrect.
The correct addresses should be:
D18:F1 0x204D D18:F2 0x204E D18:F5 0x204D
Signed-off-by: Kan Liang kan.liang@linux.intel.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Arnaldo Carvalho de Melo acme@redhat.com Cc: Jiri Olsa jolsa@redhat.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Stephane Eranian eranian@google.com Cc: Thomas Gleixner tglx@linutronix.de Cc: Vince Weaver vincent.weaver@maine.edu Fixes: cd34cd97b7b4 ("perf/x86/intel/uncore: Add Skylake server uncore support") Link: http://lkml.kernel.org/r/1537538826-55489-1-git-send-email-kan.liang@linux.i... Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/events/intel/uncore_snbep.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 2dae3f585c01..a68aba8a482f 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -3807,16 +3807,16 @@ static const struct pci_device_id skx_uncore_pci_ids[] = { .driver_data = UNCORE_PCI_DEV_FULL_DATA(21, 5, SKX_PCI_UNCORE_M2PCIE, 3), }, { /* M3UPI0 Link 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C), - .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 0, SKX_PCI_UNCORE_M3UPI, 0), + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 1, SKX_PCI_UNCORE_M3UPI, 0), }, { /* M3UPI0 Link 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D), - .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 1, SKX_PCI_UNCORE_M3UPI, 1), + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204E), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 2, SKX_PCI_UNCORE_M3UPI, 1), }, { /* M3UPI1 Link 2 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204C), - .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 4, SKX_PCI_UNCORE_M3UPI, 2), + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x204D), + .driver_data = UNCORE_PCI_DEV_FULL_DATA(18, 5, SKX_PCI_UNCORE_M3UPI, 2), }, { /* end: all zeroes */ } };
From: "Natarajan, Janakarajan" Janakarajan.Natarajan@amd.com
[ Upstream commit d7cbbe49a9304520181fb8c9272d1327deec8453 ]
In Family 17h, some L3 Cache Performance events require the ThreadMask and SliceMask to be set. For other events, these fields do not affect the count either way.
Set ThreadMask and SliceMask to 0xFF and 0xF respectively.
Signed-off-by: Janakarajan Natarajan Janakarajan.Natarajan@amd.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Arnaldo Carvalho de Melo acme@kernel.org Cc: Arnaldo Carvalho de Melo acme@redhat.com Cc: Borislav Petkov bp@alien8.de Cc: H . Peter Anvin hpa@zytor.com Cc: Jiri Olsa jolsa@redhat.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Stephane Eranian eranian@google.com Cc: Suravee Suravee.Suthikulpanit@amd.com Cc: Thomas Gleixner tglx@linutronix.de Cc: Vince Weaver vincent.weaver@maine.edu Link: http://lkml.kernel.org/r/Message-ID: Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/events/amd/uncore.c | 10 ++++++++++ arch/x86/include/asm/perf_event.h | 8 ++++++++ 2 files changed, 18 insertions(+)
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index f5cbbba99283..4e1d7483b78c 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -35,6 +35,7 @@
static int num_counters_llc; static int num_counters_nb; +static bool l3_mask;
static HLIST_HEAD(uncore_unused_list);
@@ -208,6 +209,13 @@ static int amd_uncore_event_init(struct perf_event *event) hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB; hwc->idx = -1;
+ /* + * SliceMask and ThreadMask need to be set for certain L3 events in + * Family 17h. For other events, the two fields do not affect the count. + */ + if (l3_mask) + hwc->config |= (AMD64_L3_SLICE_MASK | AMD64_L3_THREAD_MASK); + if (event->cpu < 0) return -EINVAL;
@@ -542,6 +550,7 @@ static int __init amd_uncore_init(void) amd_llc_pmu.name = "amd_l3"; format_attr_event_df.show = &event_show_df; format_attr_event_l3.show = &event_show_l3; + l3_mask = true; } else { num_counters_nb = NUM_COUNTERS_NB; num_counters_llc = NUM_COUNTERS_L2; @@ -549,6 +558,7 @@ static int __init amd_uncore_init(void) amd_llc_pmu.name = "amd_l2"; format_attr_event_df = format_attr_event; format_attr_event_l3 = format_attr_event; + l3_mask = false; }
amd_nb_pmu.attr_groups = amd_uncore_attr_groups_df; diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 12f54082f4c8..78241b736f2a 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -46,6 +46,14 @@ #define INTEL_ARCH_EVENT_MASK \ (ARCH_PERFMON_EVENTSEL_UMASK | ARCH_PERFMON_EVENTSEL_EVENT)
+#define AMD64_L3_SLICE_SHIFT 48 +#define AMD64_L3_SLICE_MASK \ + ((0xFULL) << AMD64_L3_SLICE_SHIFT) + +#define AMD64_L3_THREAD_SHIFT 56 +#define AMD64_L3_THREAD_MASK \ + ((0xFFULL) << AMD64_L3_THREAD_SHIFT) + #define X86_RAW_EVENT_MASK \ (ARCH_PERFMON_EVENTSEL_EVENT | \ ARCH_PERFMON_EVENTSEL_UMASK | \
From: Rickard x Andersson rickaran@axis.com
[ Upstream commit 657ade07df72847f591ccdb36bd9b91ed0edbac3 ]
During certain heavy network loads TX could time out with TX ring dump. TX is sometimes never restarted after reaching "tx_stop_threshold" because function "fec_enet_tx_queue" only tests the first queue.
In addition the TX timeout callback function failed to recover because it also operated only on the first queue.
Signed-off-by: Rickard x Andersson rickaran@axis.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/freescale/fec_main.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index eb2ea231c7ca..8bfa6ef826a9 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1155,7 +1155,7 @@ static void fec_enet_timeout_work(struct work_struct *work) napi_disable(&fep->napi); netif_tx_lock_bh(ndev); fec_restart(ndev); - netif_wake_queue(ndev); + netif_tx_wake_all_queues(ndev); netif_tx_unlock_bh(ndev); napi_enable(&fep->napi); } @@ -1270,7 +1270,7 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id)
/* Since we have freed up a buffer, the ring is no longer full */ - if (netif_queue_stopped(ndev)) { + if (netif_tx_queue_stopped(nq)) { entries_free = fec_enet_get_free_txdesc_num(txq); if (entries_free >= txq->tx_wake_threshold) netif_tx_wake_queue(nq); @@ -1747,7 +1747,7 @@ static void fec_enet_adjust_link(struct net_device *ndev) napi_disable(&fep->napi); netif_tx_lock_bh(ndev); fec_restart(ndev); - netif_wake_queue(ndev); + netif_tx_wake_all_queues(ndev); netif_tx_unlock_bh(ndev); napi_enable(&fep->napi); } @@ -2249,7 +2249,7 @@ static int fec_enet_set_pauseparam(struct net_device *ndev, napi_disable(&fep->napi); netif_tx_lock_bh(ndev); fec_restart(ndev); - netif_wake_queue(ndev); + netif_tx_wake_all_queues(ndev); netif_tx_unlock_bh(ndev); napi_enable(&fep->napi); }
From: "Maciej W. Rozycki" macro@linux-mips.org
[ Upstream commit fe3a83af6a50199bf250fa331e94216912f79395 ]
Fix a commit 4bcc595ccd80 ("printk: reinstate KERN_CONT for printing continuation lines") regression with the `declance' driver, which caused the adapter identification message to be split between two lines, e.g.:
declance.c: v0.011 by Linux MIPS DECstation task force tc6: PMAD-AA , addr = 08:00:2b:1b:2a:6a, irq = 14 tc6: registered as eth0.
Address that properly, by printing identification with a single call, making the messages now look like:
declance.c: v0.011 by Linux MIPS DECstation task force tc6: PMAD-AA, addr = 08:00:2b:1b:2a:6a, irq = 14 tc6: registered as eth0.
Signed-off-by: Maciej W. Rozycki macro@linux-mips.org Fixes: 4bcc595ccd80 ("printk: reinstate KERN_CONT for printing continuation lines") Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/amd/declance.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/amd/declance.c b/drivers/net/ethernet/amd/declance.c index 82cc81385033..c7cde58feaf7 100644 --- a/drivers/net/ethernet/amd/declance.c +++ b/drivers/net/ethernet/amd/declance.c @@ -1029,6 +1029,7 @@ static int dec_lance_probe(struct device *bdev, const int type) int i, ret; unsigned long esar_base; unsigned char *esar; + const char *desc;
if (dec_lance_debug && version_printed++ == 0) printk(version); @@ -1214,19 +1215,20 @@ static int dec_lance_probe(struct device *bdev, const int type) */ switch (type) { case ASIC_LANCE: - printk("%s: IOASIC onboard LANCE", name); + desc = "IOASIC onboard LANCE"; break; case PMAD_LANCE: - printk("%s: PMAD-AA", name); + desc = "PMAD-AA"; break; case PMAX_LANCE: - printk("%s: PMAX onboard LANCE", name); + desc = "PMAX onboard LANCE"; break; } for (i = 0; i < 6; i++) dev->dev_addr[i] = esar[i * 4];
- printk(", addr = %pM, irq = %d\n", dev->dev_addr, dev->irq); + printk("%s: %s, addr = %pM, irq = %d\n", + name, desc, dev->dev_addr, dev->irq);
dev->netdev_ops = &lance_netdev_ops; dev->watchdog_timeo = 5*HZ;
From: Jakub Kicinski jakub.kicinski@netronome.com
[ Upstream commit ff58e2df62ce29d0552278c290ae494b30fe0c6f ]
When FW floods the driver with control messages try to exit the cmsg processing loop every now and then to avoid soft lockups. Cmsg processing is generally very lightweight so 512 seems like a reasonable budget, which should not be exceeded under normal conditions.
Fixes: 77ece8d5f196 ("nfp: add control vNIC datapath") Signed-off-by: Jakub Kicinski jakub.kicinski@netronome.com Reviewed-by: Simon Horman simon.horman@netronome.com Tested-by: Pieter Jansen van Vuuren pieter.jansenvanvuuren@netronome.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/ethernet/netronome/nfp/nfp_net_common.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 56751990bcee..6df2c8b2ce6f 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -2058,14 +2058,17 @@ nfp_ctrl_rx_one(struct nfp_net *nn, struct nfp_net_dp *dp, return true; }
-static void nfp_ctrl_rx(struct nfp_net_r_vector *r_vec) +static bool nfp_ctrl_rx(struct nfp_net_r_vector *r_vec) { struct nfp_net_rx_ring *rx_ring = r_vec->rx_ring; struct nfp_net *nn = r_vec->nfp_net; struct nfp_net_dp *dp = &nn->dp; + unsigned int budget = 512;
- while (nfp_ctrl_rx_one(nn, dp, r_vec, rx_ring)) + while (nfp_ctrl_rx_one(nn, dp, r_vec, rx_ring) && budget--) continue; + + return budget; }
static void nfp_ctrl_poll(unsigned long arg) @@ -2077,9 +2080,13 @@ static void nfp_ctrl_poll(unsigned long arg) __nfp_ctrl_tx_queued(r_vec); spin_unlock_bh(&r_vec->lock);
- nfp_ctrl_rx(r_vec); - - nfp_net_irq_unmask(r_vec->nfp_net, r_vec->irq_entry); + if (nfp_ctrl_rx(r_vec)) { + nfp_net_irq_unmask(r_vec->nfp_net, r_vec->irq_entry); + } else { + tasklet_schedule(&r_vec->tasklet); + nn_dp_warn(&r_vec->nfp_net->dp, + "control message budget exceeded!\n"); + } }
/* Setup and Configuration
From: Mahesh Bandewar maheshb@google.com
[ Upstream commit 0f3b914c9cfcd7bbedd445dc4ac5dd999fa213c2 ]
RX queue config for bonding master could be different from its slave device(s). With the commit 6a9e461f6fe4 ("bonding: pass link-local packets to bonding master also."), the packet is reinjected into stack with skb->dev as bonding master. This potentially triggers the message:
"bondX received packet on queue Y, but number of RX queues is Z"
whenever the queue that packet is received on is higher than the numrxqueues on bonding master (Y > Z).
Fixes: 6a9e461f6fe4 ("bonding: pass link-local packets to bonding master also.") Reported-by: John Sperbeck jsperbeck@google.com Signed-off-by: Eric Dumazet edumazet@google.com Signed-off-by: Mahesh Bandewar maheshb@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/bonding/bond_main.c | 1 + 1 file changed, 1 insertion(+)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index b880126e616b..cf64a365362b 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1193,6 +1193,7 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
if (nskb) { nskb->dev = bond->dev; + nskb->queue_mapping = 0; netif_rx(nskb); } return RX_HANDLER_PASS;
From: Sean Tranchetti stranche@codeaurora.org
[ Upstream commit a07f388e2cde2be74b263f85df6f672fea0305a1 ]
RMNET RX handler was processing invalid packets that were originally sent on the real device and were looped back via dev_loopback_xmit(). This was detected using syzkaller.
Fixes: ceed73a2cf4a ("drivers: net: ethernet: qualcomm: rmnet: Initial implementation") Signed-off-by: Sean Tranchetti stranche@codeaurora.org Signed-off-by: Subash Abhinov Kasiviswanathan subashab@codeaurora.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c | 3 +++ 1 file changed, 3 insertions(+)
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c index 929fb8d96ec0..8d979fef5fc7 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c @@ -205,6 +205,9 @@ rx_handler_result_t rmnet_rx_handler(struct sk_buff **pskb) if (!skb) return RX_HANDLER_CONSUMED;
+ if (skb->pkt_type == PACKET_LOOPBACK) + return RX_HANDLER_PASS; + dev = skb->dev; port = rmnet_get_port(dev);
From: Guenter Roeck linux@roeck-us.net
[ Upstream commit e4a02ed2aaf447fa849e3254bfdb3b9b01e1e520 ]
If CONFIG_WW_MUTEX_SELFTEST=y is enabled, booting an image in an arm64 virtual machine results in the following traceback if 8 CPUs are enabled:
DEBUG_LOCKS_WARN_ON(__owner_task(owner) != current) WARNING: CPU: 2 PID: 537 at kernel/locking/mutex.c:1033 __mutex_unlock_slowpath+0x1a8/0x2e0 ... Call trace: __mutex_unlock_slowpath() ww_mutex_unlock() test_cycle_work() process_one_work() worker_thread() kthread() ret_from_fork()
If requesting b_mutex fails with -EDEADLK, the error variable is reassigned to the return value from calling ww_mutex_lock on a_mutex again. If this call fails, a_mutex is not locked. It is, however, unconditionally unlocked subsequently, causing the reported warning. Fix the problem by using two error variables.
With this change, the selftest still fails as follows:
cyclic deadlock not resolved, ret[7/8] = -35
However, the traceback is gone.
Signed-off-by: Guenter Roeck linux@roeck-us.net Cc: Chris Wilson chris@chris-wilson.co.uk Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Cc: Will Deacon will.deacon@arm.com Fixes: d1b42b800e5d0 ("locking/ww_mutex: Add kselftests for resolving ww_mutex cyclic deadlocks") Link: http://lkml.kernel.org/r/1538516929-9734-1-git-send-email-linux@roeck-us.net Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/locking/test-ww_mutex.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)
diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c index 0e4cd64ad2c0..654977862b06 100644 --- a/kernel/locking/test-ww_mutex.c +++ b/kernel/locking/test-ww_mutex.c @@ -260,7 +260,7 @@ static void test_cycle_work(struct work_struct *work) { struct test_cycle *cycle = container_of(work, typeof(*cycle), work); struct ww_acquire_ctx ctx; - int err; + int err, erra = 0;
ww_acquire_init(&ctx, &ww_class); ww_mutex_lock(&cycle->a_mutex, &ctx); @@ -270,17 +270,19 @@ static void test_cycle_work(struct work_struct *work)
err = ww_mutex_lock(cycle->b_mutex, &ctx); if (err == -EDEADLK) { + err = 0; ww_mutex_unlock(&cycle->a_mutex); ww_mutex_lock_slow(cycle->b_mutex, &ctx); - err = ww_mutex_lock(&cycle->a_mutex, &ctx); + erra = ww_mutex_lock(&cycle->a_mutex, &ctx); }
if (!err) ww_mutex_unlock(cycle->b_mutex); - ww_mutex_unlock(&cycle->a_mutex); + if (!erra) + ww_mutex_unlock(&cycle->a_mutex); ww_acquire_fini(&ctx);
- cycle->result = err; + cycle->result = err ?: erra; }
static int __test_cycle(unsigned int nthreads)
From: Yu Zhao yuzhao@google.com
[ Upstream commit f7b2a56e1f3dcbdb4cf09b2b63e859ffe0e09df8 ]
Cancel pending work before freeing smsc75xx private data structure during binding. This fixes the following crash in the driver:
BUG: unable to handle kernel NULL pointer dereference at 0000000000000050 IP: mutex_lock+0x2b/0x3f <snipped> Workqueue: events smsc75xx_deferred_multicast_write [smsc75xx] task: ffff8caa83e85700 task.stack: ffff948b80518000 RIP: 0010:mutex_lock+0x2b/0x3f <snipped> Call Trace: smsc75xx_deferred_multicast_write+0x40/0x1af [smsc75xx] process_one_work+0x18d/0x2fc worker_thread+0x1a2/0x269 ? pr_cont_work+0x58/0x58 kthread+0xfa/0x10a ? pr_cont_work+0x58/0x58 ? rcu_read_unlock_sched_notrace+0x48/0x48 ret_from_fork+0x22/0x40
Signed-off-by: Yu Zhao yuzhao@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/usb/smsc75xx.c | 1 + 1 file changed, 1 insertion(+)
diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index e5a4cbb366dc..ec287c9741e8 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -1520,6 +1520,7 @@ static void smsc75xx_unbind(struct usbnet *dev, struct usb_interface *intf) { struct smsc75xx_priv *pdata = (struct smsc75xx_priv *)(dev->data[0]); if (pdata) { + cancel_work_sync(&pdata->set_multicast); netif_dbg(dev, ifdown, dev->net, "free pdata\n"); kfree(pdata); pdata = NULL;
From: Davide Caratti dcaratti@redhat.com
[ Upstream commit 2d52527e80c2dc0c5f43f50adf183781262ec565 ]
the be2net implementation of .ndo_tunnel_{add,del}() changes the value of NETIF_F_GSO_UDP_TUNNEL bit in 'features' and 'hw_features', but it forgets to call netdev_features_change(). Moreover, ethtool setting for that bit can potentially be reverted after a tunnel is added or removed.
GSO already does software segmentation when 'hw_enc_features' is 0, even if VXLAN offload is turned on. In addition, commit 096de2f83ebc ("benet: stricter vxlan offloading check in be_features_check") avoids hardware segmentation of non-VXLAN tunneled packets, or VXLAN packets having wrong destination port. So, it's safe to avoid flipping the above feature on addition/deletion of VXLAN tunnels.
Fixes: 630f4b70567f ("be2net: Export tunnel offloads only when a VxLAN tunnel is created") Signed-off-by: Davide Caratti dcaratti@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/emulex/benet/be_main.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 7e2b70c2bba3..39f399741647 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -3900,8 +3900,6 @@ static int be_enable_vxlan_offloads(struct be_adapter *adapter) netdev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_UDP_TUNNEL; - netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL; - netdev->features |= NETIF_F_GSO_UDP_TUNNEL;
dev_info(dev, "Enabled VxLAN offloads for UDP port %d\n", be16_to_cpu(port)); @@ -3923,8 +3921,6 @@ static void be_disable_vxlan_offloads(struct be_adapter *adapter) adapter->vxlan_port = 0;
netdev->hw_enc_features = 0; - netdev->hw_features &= ~(NETIF_F_GSO_UDP_TUNNEL); - netdev->features &= ~(NETIF_F_GSO_UDP_TUNNEL); }
static void be_calculate_vf_res(struct be_adapter *adapter, u16 num_vfs, @@ -5215,6 +5211,7 @@ static void be_netdev_init(struct net_device *netdev) struct be_adapter *adapter = netdev_priv(netdev);
netdev->hw_features |= NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 | + NETIF_F_GSO_UDP_TUNNEL | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX; if ((be_if_cap_flags(adapter) & BE_IF_FLAGS_RSS))
From: Wenwen Wang wang6495@umn.edu
[ Upstream commit 2c05d88818ab6571816b93edce4d53703870d7ae ]
In cxgb_extension_ioctl(), the command of the ioctl is firstly copied from the user-space buffer 'useraddr' to 'cmd' and checked through the switch statement. If the command is not as expected, an error code EOPNOTSUPP is returned. In the following execution, i.e., the cases of the switch statement, the whole buffer of 'useraddr' is copied again to a specific data structure, according to what kind of command is requested. However, after the second copy, there is no re-check on the newly-copied command. Given that the buffer 'useraddr' is in the user space, a malicious user can race to change the command between the two copies. By doing so, the attacker can supply malicious data to the kernel and cause undefined behavior.
This patch adds a re-check in each case of the switch statement if there is a second copy in that case, to re-check whether the command obtained in the second copy is the same as the one in the first copy. If not, an error code EINVAL is returned.
Signed-off-by: Wenwen Wang wang6495@umn.edu Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+)
diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index bf291e90cdb0..79053d2ce7a3 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -2159,6 +2159,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EPERM; if (copy_from_user(&t, useraddr, sizeof(t))) return -EFAULT; + if (t.cmd != CHELSIO_SET_QSET_PARAMS) + return -EINVAL; if (t.qset_idx >= SGE_QSETS) return -EINVAL; if (!in_range(t.intr_lat, 0, M_NEWTIMER) || @@ -2258,6 +2260,9 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) if (copy_from_user(&t, useraddr, sizeof(t))) return -EFAULT;
+ if (t.cmd != CHELSIO_GET_QSET_PARAMS) + return -EINVAL; + /* Display qsets for all ports when offload enabled */ if (test_bit(OFFLOAD_DEVMAP_BIT, &adapter->open_device_map)) { q1 = 0; @@ -2303,6 +2308,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EBUSY; if (copy_from_user(&edata, useraddr, sizeof(edata))) return -EFAULT; + if (edata.cmd != CHELSIO_SET_QSET_NUM) + return -EINVAL; if (edata.val < 1 || (edata.val > 1 && !(adapter->flags & USING_MSIX))) return -EINVAL; @@ -2343,6 +2350,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EPERM; if (copy_from_user(&t, useraddr, sizeof(t))) return -EFAULT; + if (t.cmd != CHELSIO_LOAD_FW) + return -EINVAL; /* Check t.len sanity ? */ fw_data = memdup_user(useraddr + sizeof(t), t.len); if (IS_ERR(fw_data)) @@ -2366,6 +2375,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EBUSY; if (copy_from_user(&m, useraddr, sizeof(m))) return -EFAULT; + if (m.cmd != CHELSIO_SETMTUTAB) + return -EINVAL; if (m.nmtus != NMTUS) return -EINVAL; if (m.mtus[0] < 81) /* accommodate SACK */ @@ -2407,6 +2418,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EBUSY; if (copy_from_user(&m, useraddr, sizeof(m))) return -EFAULT; + if (m.cmd != CHELSIO_SET_PM) + return -EINVAL; if (!is_power_of_2(m.rx_pg_sz) || !is_power_of_2(m.tx_pg_sz)) return -EINVAL; /* not power of 2 */ @@ -2440,6 +2453,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EIO; /* need the memory controllers */ if (copy_from_user(&t, useraddr, sizeof(t))) return -EFAULT; + if (t.cmd != CHELSIO_GET_MEM) + return -EINVAL; if ((t.addr & 7) || (t.len & 7)) return -EINVAL; if (t.mem_id == MEM_CM) @@ -2492,6 +2507,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) return -EAGAIN; if (copy_from_user(&t, useraddr, sizeof(t))) return -EFAULT; + if (t.cmd != CHELSIO_SET_TRACE_FILTER) + return -EINVAL;
tp = (const struct trace_params *)&t.sip; if (t.config_tx)
From: Wenwen Wang wang6495@umn.edu
[ Upstream commit 0781168e23a2fc8dceb989f11fc5b39b3ccacc35 ]
In yam_ioctl(), the concrete ioctl command is firstly copied from the user-space buffer 'ifr->ifr_data' to 'ioctl_cmd' and checked through the following switch statement. If the command is not as expected, an error code EINVAL is returned. In the following execution the buffer 'ifr->ifr_data' is copied again in the cases of the switch statement to specific data structures according to what kind of ioctl command is requested. However, after the second copy, no re-check is enforced on the newly-copied command. Given that the buffer 'ifr->ifr_data' is in the user space, a malicious user can race to change the command between the two copies. This way, the attacker can inject inconsistent data and cause undefined behavior.
This patch adds a re-check in each case of the switch statement if there is a second copy in that case, to re-check whether the command obtained in the second copy is the same as the one in the first copy. If not, an error code EINVAL will be returned.
Signed-off-by: Wenwen Wang wang6495@umn.edu Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/hamradio/yam.c | 4 ++++ 1 file changed, 4 insertions(+)
diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c index 7a7c5224a336..16a6e1193912 100644 --- a/drivers/net/hamradio/yam.c +++ b/drivers/net/hamradio/yam.c @@ -980,6 +980,8 @@ static int yam_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) sizeof(struct yamdrv_ioctl_mcs)); if (IS_ERR(ym)) return PTR_ERR(ym); + if (ym->cmd != SIOCYAMSMCS) + return -EINVAL; if (ym->bitrate > YAM_MAXBITRATE) { kfree(ym); return -EINVAL; @@ -995,6 +997,8 @@ static int yam_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (copy_from_user(&yi, ifr->ifr_data, sizeof(struct yamdrv_ioctl_cfg))) return -EFAULT;
+ if (yi.cmd != SIOCYAMSCFG) + return -EINVAL; if ((yi.cfg.mask & YAM_IOBASE) && netif_running(dev)) return -EINVAL; /* Cannot change this parameter when up */ if ((yi.cfg.mask & YAM_IRQ) && netif_running(dev))
From: Larry Chen lchen@suse.com
[ Upstream commit 69eb7765b9c6902444c89c54e7043242faf981e5 ]
ocfs2_duplicate_clusters_by_page() may crash if one of the extent's pages is dirty. When a page has not been written back, it is still in dirty state. If ocfs2_duplicate_clusters_by_page() is called against the dirty page, the crash happens.
To fix this bug, we can just unlock the page and wait until the page until its not dirty.
The following is the backtrace:
kernel BUG at /root/code/ocfs2/refcounttree.c:2961! [exception RIP: ocfs2_duplicate_clusters_by_page+822] __ocfs2_move_extent+0x80/0x450 [ocfs2] ? __ocfs2_claim_clusters+0x130/0x250 [ocfs2] ocfs2_defrag_extent+0x5b8/0x5e0 [ocfs2] __ocfs2_move_extents_range+0x2a4/0x470 [ocfs2] ocfs2_move_extents+0x180/0x3b0 [ocfs2] ? ocfs2_wait_for_recovery+0x13/0x70 [ocfs2] ocfs2_ioctl_move_extents+0x133/0x2d0 [ocfs2] ocfs2_ioctl+0x253/0x640 [ocfs2] do_vfs_ioctl+0x90/0x5f0 SyS_ioctl+0x74/0x80 do_syscall_64+0x74/0x140 entry_SYSCALL_64_after_hwframe+0x3d/0xa2
Once we find the page is dirty, we do not wait until it's clean, rather we use write_one_page() to write it back
Link: http://lkml.kernel.org/r/20180829074740.9438-1-lchen@suse.com [lchen@suse.com: update comments] Link: http://lkml.kernel.org/r/20180830075041.14879-1-lchen@suse.com [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Larry Chen lchen@suse.com Acked-by: Changwei Ge ge.changwei@h3c.com Cc: Mark Fasheh mark@fasheh.com Cc: Joel Becker jlbec@evilplan.org Cc: Junxiao Bi junxiao.bi@oracle.com Cc: Joseph Qi jiangqi903@gmail.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ocfs2/refcounttree.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-)
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 1b1283f07941..824f407df1db 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -2946,6 +2946,7 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle, if (map_end & (PAGE_SIZE - 1)) to = map_end & (PAGE_SIZE - 1);
+retry: page = find_or_create_page(mapping, page_index, GFP_NOFS); if (!page) { ret = -ENOMEM; @@ -2954,11 +2955,18 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle, }
/* - * In case PAGE_SIZE <= CLUSTER_SIZE, This page - * can't be dirtied before we CoW it out. + * In case PAGE_SIZE <= CLUSTER_SIZE, we do not expect a dirty + * page, so write it back. */ - if (PAGE_SIZE <= OCFS2_SB(sb)->s_clustersize) - BUG_ON(PageDirty(page)); + if (PAGE_SIZE <= OCFS2_SB(sb)->s_clustersize) { + if (PageDirty(page)) { + /* + * write_on_page will unlock the page on return + */ + ret = write_one_page(page); + goto retry; + } + }
if (!PageUptodate(page)) { ret = block_read_full_page(page, ocfs2_get_block);
From: Jann Horn jannh@google.com
[ Upstream commit 28e2c4bb99aa40f9d5f07ac130cbc4da0ea93079 ]
7a9cdebdcc17 ("mm: get rid of vmacache_flush_all() entirely") removed the VMACACHE_FULL_FLUSHES statistics, but didn't remove the corresponding entry in vmstat_text. This causes an out-of-bounds access in vmstat_show().
Luckily this only affects kernels with CONFIG_DEBUG_VM_VMACACHE=y, which is probably very rare.
Link: http://lkml.kernel.org/r/20181001143138.95119-1-jannh@google.com Fixes: 7a9cdebdcc17 ("mm: get rid of vmacache_flush_all() entirely") Signed-off-by: Jann Horn jannh@google.com Reviewed-by: Kees Cook keescook@chromium.org Reviewed-by: Andrew Morton akpm@linux-foundation.org Acked-by: Michal Hocko mhocko@suse.com Acked-by: Roman Gushchin guro@fb.com Cc: Davidlohr Bueso dave@stgolabs.net Cc: Oleg Nesterov oleg@redhat.com Cc: Christoph Lameter clameter@sgi.com Cc: Kemi Wang kemi.wang@intel.com Cc: Andy Lutomirski luto@kernel.org Cc: Ingo Molnar mingo@kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- mm/vmstat.c | 1 - 1 file changed, 1 deletion(-)
diff --git a/mm/vmstat.c b/mm/vmstat.c index 2bdc962b2dfe..50b4c11fb612 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1214,7 +1214,6 @@ const char * const vmstat_text[] = { #ifdef CONFIG_DEBUG_VM_VMACACHE "vmacache_find_calls", "vmacache_find_hits", - "vmacache_full_flushes", #endif #ifdef CONFIG_SWAP "swap_ra",
linux-stable-mirror@lists.linaro.org
-
Sasha Levin