6.1.95-rc1 review
Subsystems (5)
Greg Kroah-Hartman
maintainerPATCH 1/217 wifi: mac80211: mesh: Fix leak of mesh_preq_queue objects
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Nicolas Escande <[email protected]>
[ Upstream commit b7d7f11a291830fdf69d3301075dd0fb347ced84 ]
The hwmp code use objects of type mesh_preq_queue, added to a list in ieee80211_if_mesh, to keep track of mpath we need to resolve. If the mpath gets deleted, ex mesh interface is removed, the entries in that list will never get cleaned. Fix this by flushing all corresponding items of the preq_queue in mesh_path_flush_pending().
This should take care of KASAN reports like this:
unreferenced object 0xffff00000668d800 (size 128):
comm "kworker/u8:4", pid 67, jiffies 4295419552 (age 1836.444s) hex dump (first 32 bytes):
00 1f 05 09 00 00 ff ff 00 d5 68 06 00 00 ff ff ..........h.....
8e 97 ea eb 3e b8 01 00 00 00 00 00 00 00 00 00 ....>...........
backtrace:
[<000000007302a0b6>] __kmem_cache_alloc_node+0x1e0/0x35c
[<00000000049bd418>] kmalloc_trace+0x34/0x80
[<0000000000d792bb>] mesh_queue_preq+0x44/0x2a8
[<00000000c99c3696>] mesh_nexthop_resolve+0x198/0x19c
[<00000000926bf598>] ieee80211_xmit+0x1d0/0x1f4
[<00000000fc8c2284>] __ieee80211_subif_start_xmit+0x30c/0x764
[<000000005926ee38>] ieee80211_subif_start_xmit+0x9c/0x7a4
[<000000004c86e916>] dev_hard_start_xmit+0x174/0x440
[<0000000023495647>] __dev_queue_xmit+0xe24/0x111c
[<00000000cfe9ca78>] batadv_send_skb_packet+0x180/0x1e4
[<000000007bacc5d5>] batadv_v_elp_periodic_work+0x2f4/0x508
[<00000000adc3cd94>] process_one_work+0x4b8/0xa1c
[<00000000b36425d1>] worker_thread+0x9c/0x634
[<0000000005852dd5>] kthread+0x1bc/0x1c4
[<000000005fccd770>] ret_from_fork+0x10/0x20
unreferenced object 0xffff000009051f00 (size 128):
comm "kworker/u8:4", pid 67, jiffies 4295419553 (age 1836.440s)
hex dump (first 32 bytes):
90 d6 92 0d 00 00 ff ff 00 d8 68 06 00 00 ff ff ..........h.....
36 27 92 e4 02 e0 01 00 00 58 79 06 00 00 ff ff 6'.......Xy.....
backtrace:
[<000000007302a0b6>] __kmem_cache_alloc_node+0x1e0/0x35c
[<00000000049bd418>] kmalloc_trace+0x34/0x80
[<0000000000d792bb>] mesh_queue_preq+0x44/0x2a8
[<00000000c99c3696>] mesh_nexthop_resolve+0x198/0x19c
[<00000000926bf598>] ieee80211_xmit+0x1d0/0x1f4
[<00000000fc8c2284>] __ieee80211_subif_start_xmit+0x30c/0x764
[<000000005926ee38>] ieee80211_subif_start_xmit+0x9c/0x7a4
[<000000004c86e916>] dev_hard_start_xmit+0x174/0x440
[<0000000023495647>] __dev_queue_xmit+0xe24/0x111c
[<00000000cfe9ca78>] batadv_send_skb_packet+0x180/0x1e4
[<000000007bacc5d5>] batadv_v_elp_periodic_work+0x2f4/0x508
[<00000000adc3cd94>] process_one_work+0x4b8/0xa1c
[<00000000b36425d1>] worker_thread+0x9c/0x634
[<0000000005852dd5>] kthread+0x1bc/0x1c4
[<000000005fccd770>] ret_from_fork+0x10/0x20--- net/mac80211/mesh_pathtbl.c | 13 +++++++++++++ 1 file changed, 13 insertions(+)
net/mac80211/mesh_pathtbl.c +13 -0
@@ -723,10 +723,23 @@ void mesh_path_discard_frame(struct ieee80211_sub_if_data *sdata,*/ void mesh_path_flush_pending (struct mesh_path *mpath) { +struct ieee80211_sub_if_data *sdata = mpath->sdata; +struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; +struct mesh_preq_queue *preq, *tmp;struct sk_buff *skb;while ((skb =skb_dequeue (&mpath->frame_queue)) !=NULL )mesh_path_discard_frame (mpath->sdata, skb); + +spin_lock_bh (&ifmsh->mesh_preq_queue_lock); +list_for_each_entry_safe (preq, tmp, &ifmsh->preq_queue.list, list) { +if (ether_addr_equal (mpath->dst, preq->dst)) { +list_del (&preq->list); +kfree (preq); + --ifmsh->preq_queue_len; + } + } +spin_unlock_bh (&ifmsh->mesh_preq_queue_lock); }/**
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 10/217 wifi: mac80211: correctly parse Spatial Reuse Parameter Set element
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Lingbo Kong <[email protected]>
[ Upstream commit a26d8dc5227f449a54518a8b40733a54c6600a8b ]
Currently, the way of parsing Spatial Reuse Parameter Set element is incorrect and some members of struct ieee80211_he_obss_pd are not assigned.
To address this issue, it must be parsed in the order of the elements of Spatial Reuse Parameter Set defined in the IEEE Std 802.11ax specification.
The diagram of the Spatial Reuse Parameter Set element (IEEE Std 802.11ax -2021-9.4.2.252).
-------------------------------------------------------------------------
| | | | |Non-SRG| SRG | SRG | SRG | SRG | |Element|Length| Element | SR |OBSS PD|OBSS PD|OBSS PD| BSS |Partial| | ID | | ID |Control| Max | Min | Max |Color | BSSID | | | |Extension| | Offset| Offset|Offset |Bitmap|Bitmap |
-------------------------------------------------------------------------
--- net/mac80211/he.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)
net/mac80211/he.c +8 -2
@@ -231,15 +231,21 @@ ieee80211_he_spr_ie_to_bss_conf(struct ieee80211_vif *vif,if (!he_spr_ie_elem)return ; + + he_obss_pd->sr_ctrl = he_spr_ie_elem->he_sr_control; data = he_spr_ie_elem->optional;if (he_spr_ie_elem->he_sr_control &IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT ) - data++; + he_obss_pd->non_srg_max_offset = *data++; +if (he_spr_ie_elem->he_sr_control &IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT ) { - he_obss_pd->max_offset = *data++; he_obss_pd->min_offset = *data++; + he_obss_pd->max_offset = *data++; +memcpy (he_obss_pd->bss_color_bitmap, data,8 ); + data +=8 ; +memcpy (he_obss_pd->partial_bssid_bitmap, data,8 ); he_obss_pd->enable = true; } }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 11/217 ax25: Fix refcount imbalance on inbound connections
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Lars Kellogg-Stedman <[email protected]>
[ Upstream commit 3c34fb0bd4a4237592c5ecb5b2e2531900c55774 ]
When releasing a socket in ax25_release(), we call netdev_put() to decrease the refcount on the associated ax.25 device. However, the execution path for accepting an incoming connection never calls netdev_hold(). This imbalance leads to refcount errors, and ultimately to kernel crashes.
A typical call trace for the above situation will start with one of the following errors:
refcount_t: decrement hit 0; leaking memory.
refcount_t: underflow; use-after-free.
And will then have a trace like:
Call Trace:
<TASK>
? show_regs+0x64/0x70
? __warn+0x83/0x120
? refcount_warn_saturate+0xb2/0x100
? report_bug+0x158/0x190
? prb_read_valid+0x20/0x30
? handle_bug+0x3e/0x70
? exc_invalid_op+0x1c/0x70
? asm_exc_invalid_op+0x1f/0x30
? refcount_warn_saturate+0xb2/0x100
? refcount_warn_saturate+0xb2/0x100
ax25_release+0x2ad/0x360
__sock_release+0x35/0xa0
sock_close+0x19/0x20
[...]On reboot (or any attempt to remove the interface), the kernel gets stuck in an infinite loop:
unregister_netdevice: waiting for ax0 to become free. Usage count = 0
This patch corrects these issues by ensuring that we call netdev_hold() and ax25_dev_hold() for new connections in ax25_accept(). This makes the logic leading to ax25_accept() match the logic for ax25_bind(): in both cases we increment the refcount, which is ultimately decremented in ax25_release().
--- net/ax25/af_ax25.c | 6 ++++++ 1 file changed, 6 insertions(+)
net/ax25/af_ax25.c +6 -0
@@ -1378,8 +1378,10 @@ static int ax25_accept(struct socket *sock, struct socket *newsock, int flags, {struct sk_buff *skb;struct sock *newsk; +ax25_dev *ax25_dev;DEFINE_WAIT (wait);struct sock *sk; +ax25_cb *ax25;int err =0 ;if (sock->state !=SS_UNCONNECTED )
@@ -1434,6 +1436,10 @@ static int ax25_accept(struct socket *sock, struct socket *newsock, int flags,kfree_skb (skb);sk_acceptq_removed (sk); newsock->state =SS_CONNECTED ; + ax25 =sk_to_ax25 (newsk); + ax25_dev = ax25->ax25_dev; +netdev_hold (ax25_dev->dev, &ax25->dev_tracker,GFP_ATOMIC ); +ax25_dev_hold (ax25_dev); out:release_sock (sk);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 12/217 ax25: Replace kfree() in ax25_dev_free() with ax25_dev_put()
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Duoming Zhou <[email protected]>
[ Upstream commit 166fcf86cd34e15c7f383eda4642d7a212393008 ]
The object "ax25_dev" is managed by reference counting. Thus it should not be directly released by kfree(), replace with ax25_dev_put().
--- net/ax25/ax25_dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/ax25/ax25_dev.c +1 -1
@@ -193,7 +193,7 @@ void __exit ax25_dev_free(void)list_for_each_entry_safe (s, n, &ax25_dev_list, list) {netdev_put (s->dev, &s->dev_tracker);list_del (&s->list); -kfree (s); +ax25_dev_put (s); }spin_unlock_bh (&ax25_dev_lock); }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 13/217 net/ncsi: Simplify Kconfig/dts control flow
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Peter Delevoryas <[email protected]>
[ Upstream commit c797ce168930ce3d62a9b7fc4d7040963ee6a01e ]
Background:
1. CONFIG_NCSI_OEM_CMD_KEEP_PHY
If this is enabled, we send an extra OEM Intel command in the probe sequence immediately after discovering a channel (e.g. after "Clear Initial State").
2. CONFIG_NCSI_OEM_CMD_GET_MAC
If this is enabled, we send one of 3 OEM "Get MAC Address" commands from Broadcom, Mellanox (Nvidida), and Intel in the *configuration* sequence for a channel.
3. mellanox,multi-host (or mlx,multi-host)
Introduced by this patch:
https://lore.kernel.org/all/[email protected]/
Which was actually originally from [email protected]:
https://github.com/facebook/openbmc-linux/commit/9f132a10ec48db84613519258cd8a317fb9c8f1b
Cosmo claimed that the Nvidia ConnectX-4 and ConnectX-6 NIC's don't respond to Get Version ID, et. al in the probe sequence unless you send the Set MC Affinity command first.
Problem Statement:
We've been using a combination of #ifdef code blocks and IS_ENABLED() conditions to conditionally send these OEM commands.
It makes adding any new code around these commands hard to understand.
Solution:
In this patch, I just want to remove the conditionally compiled blocks of code, and always use IS_ENABLED(...) to do dynamic control flow.
I don't think the small amount of code this adds to non-users of the OEM Kconfigs is a big deal.
Stable-dep-of: e85e271dec02 ("net/ncsi: Fix the multi thread manner of NCSI driver")
--- net/ncsi/ncsi-manage.c | 20 +++----------------- 1 file changed, 3 insertions(+), 17 deletions(-)
net/ncsi/ncsi-manage.c +3 -17
@@ -689,8 +689,6 @@ static int set_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc,return 0 ; } -#if IS_ENABLED (CONFIG_NCSI_OEM_CMD_KEEP_PHY ) -static int ncsi_oem_keep_phy_intel (struct ncsi_cmd_arg *nca) {unsigned char data[NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN ];
@@ -716,10 +714,6 @@ static int ncsi_oem_keep_phy_intel(struct ncsi_cmd_arg *nca)return ret; } -#endif - -#if IS_ENABLED (CONFIG_NCSI_OEM_CMD_GET_MAC ) -/* NCSI OEM Command APIs */ static int ncsi_oem_gma_handler_bcm (struct ncsi_cmd_arg *nca) {
@@ -856,8 +850,6 @@ static int ncsi_gma_handler(struct ncsi_cmd_arg *nca, unsigned int mf_id)return nch->handler (nca); } -#endif /* CONFIG_NCSI_OEM_CMD_GET_MAC */ -/* Determine if a given channel from the channel_queue should be used for Tx */ static bool ncsi_channel_is_tx (struct ncsi_dev_priv *ndp,struct ncsi_channel *nc)
@@ -1039,20 +1031,18 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp) goto error; } - nd->state = ncsi_dev_state_config_oem_gma; + nd->state =IS_ENABLED (CONFIG_NCSI_OEM_CMD_GET_MAC ) + ? ncsi_dev_state_config_oem_gma + : ncsi_dev_state_config_clear_vids;break ;case ncsi_dev_state_config_oem_gma: nd->state = ncsi_dev_state_config_clear_vids; - ret =-1 ; -#if IS_ENABLED (CONFIG_NCSI_OEM_CMD_GET_MAC ) nca.type =NCSI_PKT_CMD_OEM ; nca.package = np->id; nca.channel = nc->id; ndp->pending_req_num =1 ; ret =ncsi_gma_handler (&nca, nc->version.mf_id); -#endif /* CONFIG_NCSI_OEM_CMD_GET_MAC */ -if (ret <0 )schedule_work (&ndp->work);
@@ -1404,7 +1394,6 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp)schedule_work (&ndp->work);break ; -#if IS_ENABLED (CONFIG_NCSI_OEM_CMD_GET_MAC )case ncsi_dev_state_probe_mlx_gma: ndp->pending_req_num =1 ;
@@ -1429,7 +1418,6 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) nd->state = ncsi_dev_state_probe_cis;break ; -#endif /* CONFIG_NCSI_OEM_CMD_GET_MAC */ case ncsi_dev_state_probe_cis: ndp->pending_req_num =NCSI_RESERVED_CHANNEL ;
@@ -1447,7 +1435,6 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp)if (IS_ENABLED (CONFIG_NCSI_OEM_CMD_KEEP_PHY )) nd->state = ncsi_dev_state_probe_keep_phy;break ; -#if IS_ENABLED (CONFIG_NCSI_OEM_CMD_KEEP_PHY )case ncsi_dev_state_probe_keep_phy: ndp->pending_req_num =1 ;
@@ -1460,7 +1447,6 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) nd->state = ncsi_dev_state_probe_gvi;break ; -#endif /* CONFIG_NCSI_OEM_CMD_KEEP_PHY */ case ncsi_dev_state_probe_gvi:case ncsi_dev_state_probe_gc:case ncsi_dev_state_probe_gls:
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 14/217 net/ncsi: Fix the multi thread manner of NCSI driver
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: DelphineCCChiu <[email protected]>
[ Upstream commit e85e271dec0270982afed84f70dc37703fcc1d52 ]
Currently NCSI driver will send several NCSI commands back to back without waiting the response of previous NCSI command or timeout in some state when NIC have multi channel. This operation against the single thread manner defined by NCSI SPEC(section 6.3.2.3 in DSP0222_1.1.1)
According to NCSI SPEC(section 6.2.13.1 in DSP0222_1.1.1), we should probe one channel at a time by sending NCSI commands (Clear initial state, Get version ID, Get capabilities...), than repeat this steps until the max number of channels which we got from NCSI command (Get capabilities) has been probed.
--- net/ncsi/internal.h | 2 ++ net/ncsi/ncsi-manage.c | 73 +++++++++++++++++++++--------------------- net/ncsi/ncsi-rsp.c | 4 ++- 3 files changed, 41 insertions(+), 38 deletions(-)
net/ncsi/internal.h +2 -0
@@ -325,6 +325,7 @@ struct ncsi_dev_priv {spinlock_t lock;/* Protect the NCSI device */ unsigned int package_probe_id;/* Current ID during probe */ unsigned int package_num;/* Number of packages */ +unsigned int channel_probe_id;/* Current cahnnel ID during probe */ struct list_head packages;/* List of packages */ struct ncsi_channel *hot_channel;/* Channel was ever active */ struct ncsi_request requests[256 ];/* Request table */
@@ -343,6 +344,7 @@ struct ncsi_dev_priv {bool multi_package;/* Enable multiple packages */ bool mlx_multi_host;/* Enable multi host Mellanox */ u32 package_whitelist;/* Packages to configure */ +unsigned char channel_count;/* Num of channels to probe */ };struct ncsi_cmd_arg {
net/ncsi/ncsi-manage.c +36 -37
128 lines not on this page · raw message
net/ncsi/ncsi-rsp.c +3 -1
@@ -795,12 +795,13 @@ static int ncsi_rsp_handler_gc(struct ncsi_request *nr)struct ncsi_rsp_gc_pkt *rsp;struct ncsi_dev_priv *ndp = nr->ndp;struct ncsi_channel *nc; +struct ncsi_package *np;size_t size;/* Find the channel */ rsp = (struct ncsi_rsp_gc_pkt *)skb_network_header (nr->rsp);ncsi_find_package_and_channel (ndp, rsp->rsp.common.channel, -NULL , &nc); + &np, &nc);if (!nc)return -ENODEV ;
@@ -835,6 +836,7 @@ static int ncsi_rsp_handler_gc(struct ncsi_request *nr)*/ nc->vlan_filter.bitmap =U64_MAX ; nc->vlan_filter.n_vids = rsp->vlan_cnt; + np->ndp->channel_count = rsp->channel_cnt;return 0 ; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 15/217 ipv6: ioam: block BH from ioam6_output()
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Eric Dumazet <[email protected]>
[ Upstream commit 2fe40483ec257de2a0d819ef88e3e76c7e261319 ]
As explained in commit 1378817486d6 ("tipc: block BH before using dst_cache"), net/core/dst_cache.c helpers need to be called with BH disabled.
Disabling preemption in ioam6_output() is not good enough, because ioam6_output() is called from process context, lwtunnel_output() only uses rcu_read_lock().
We might be interrupted by a softirq, re-enter ioam6_output() and corrupt dst_cache data structures.
Fix the race by using local_bh_disable() instead of preempt_disable().
--- net/ipv6/ioam6_iptunnel.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
net/ipv6/ioam6_iptunnel.c +4 -4
@@ -351,9 +351,9 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb) goto drop;if (!ipv6_addr_equal (&orig_daddr, &ipv6_hdr (skb)->daddr)) { -preempt_disable (); +local_bh_disable (); dst =dst_cache_get (&ilwt->cache); -preempt_enable (); +local_bh_enable ();if (unlikely (!dst)) {struct ipv6hdr *hdr =ipv6_hdr (skb);
@@ -373,9 +373,9 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb) goto drop; } -preempt_disable (); +local_bh_disable ();dst_cache_set_ip6 (&ilwt->cache, dst, &fl6.saddr); -preempt_enable (); +local_bh_enable (); }skb_dst_drop (skb);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 16/217 ipv6: sr: block BH in seg6_output_core() and seg6_input_core()
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Eric Dumazet <[email protected]>
[ Upstream commit c0b98ac1cc104f48763cdb27b1e9ac25fd81fc90 ]
As explained in commit 1378817486d6 ("tipc: block BH before using dst_cache"), net/core/dst_cache.c helpers need to be called with BH disabled.
Disabling preemption in seg6_output_core() is not good enough, because seg6_output_core() is called from process context, lwtunnel_output() only uses rcu_read_lock().
We might be interrupted by a softirq, re-enter seg6_output_core() and corrupt dst_cache data structures.
Fix the race by using local_bh_disable() instead of preempt_disable().
Apply a similar change in seg6_input_core().
--- net/ipv6/seg6_iptunnel.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-)
net/ipv6/seg6_iptunnel.c +6 -8
@@ -464,9 +464,8 @@ static int seg6_input_core(struct net *net, struct sock *sk, slwt =seg6_lwt_lwtunnel (orig_dst->lwtstate); -preempt_disable (); +local_bh_disable (); dst =dst_cache_get (&slwt->cache); -preempt_enable ();skb_dst_drop (skb);
@@ -474,14 +473,13 @@ static int seg6_input_core(struct net *net, struct sock *sk,ip6_route_input (skb); dst =skb_dst (skb);if (!dst->error) { -preempt_disable ();dst_cache_set_ip6 (&slwt->cache, dst, &ipv6_hdr (skb)->saddr); -preempt_enable (); } }else {skb_dst_set (skb, dst); } +local_bh_enable (); err =skb_cow_head (skb,LL_RESERVED_SPACE (dst->dev));if (unlikely (err))
@@ -537,9 +535,9 @@ static int seg6_output_core(struct net *net, struct sock *sk, slwt =seg6_lwt_lwtunnel (orig_dst->lwtstate); -preempt_disable (); +local_bh_disable (); dst =dst_cache_get (&slwt->cache); -preempt_enable (); +local_bh_enable ();if (unlikely (!dst)) {struct ipv6hdr *hdr =ipv6_hdr (skb);
@@ -559,9 +557,9 @@ static int seg6_output_core(struct net *net, struct sock *sk, goto drop; } -preempt_disable (); +local_bh_disable ();dst_cache_set_ip6 (&slwt->cache, dst, &fl6.saddr); -preempt_enable (); +local_bh_enable (); }skb_dst_drop (skb);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 17/217 bpf: Set run context for rawtp test_run callback
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jiri Olsa <[email protected]>
[ Upstream commit d0d1df8ba18abc57f28fb3bc053b2bf319367f2c ]
syzbot reported crash when rawtp program executed through the test_run interface calls bpf_get_attach_cookie helper or any other helper that touches task->bpf_ctx pointer.
Setting the run context (task->bpf_ctx pointer) for test_run callback.
--- net/bpf/test_run.c | 6 ++++++ 1 file changed, 6 insertions(+)
net/bpf/test_run.c +6 -0
@@ -841,10 +841,16 @@ static void __bpf_prog_test_run_raw_tp(void *data) {struct bpf_raw_tp_test_run_info *info = data; +struct bpf_trace_run_ctx run_ctx = {}; +struct bpf_run_ctx *old_run_ctx; + + old_run_ctx =bpf_set_run_ctx (&run_ctx.run_ctx);rcu_read_lock (); info->retval =bpf_prog_run (info->prog, info->ctx);rcu_read_unlock (); + +bpf_reset_run_ctx (old_run_ctx); } int bpf_prog_test_run_raw_tp(struct bpf_prog *prog,
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 18/217 octeontx2-af: Always allocate PF entries from low prioriy zone
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Subbaraya Sundeep <[email protected]>
[ Upstream commit 8b0f7410942cdc420c4557eda02bfcdf60ccec17 ]
PF mcam entries has to be at low priority always so that VF can install longest prefix match rules at higher priority. This was taken care currently but when priority allocation wrt reference entry is requested then entries are allocated from mid-zone instead of low priority zone. Fix this and always allocate entries from low priority zone for PFs.
--- .../ethernet/marvell/octeontx2/af/rvu_npc.c | 33 ++++++++++++------- 1 file changed, 22 insertions(+), 11 deletions(-)
drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +22 -11
@@ -2506,7 +2506,17 @@ static int npc_mcam_alloc_entries(struct npc_mcam *mcam, u16 pcifunc,* - when available free entries are less. * Lower priority ones out of avaialble free entries are always * chosen when 'high vs low' question arises. +* +* For a VF base MCAM match rule is set by its PF. And all the +* further MCAM rules installed by VF on its own are +* concatenated with the base rule set by its PF. Hence PF entries +* should be at lower priority compared to VF entries. Otherwise +* base rule is hit always and rules installed by VF will be of +* no use. Hence if the request is from PF then allocate low +* priority entries. */ +if (!(pcifunc &RVU_PFVF_FUNC_MASK )) + goto lprio_alloc;/* Get the search range for priority allocation request */ if (req->priority) {
@@ -2515,17 +2525,6 @@ static int npc_mcam_alloc_entries(struct npc_mcam *mcam, u16 pcifunc, goto alloc; } -/* For a VF base MCAM match rule is set by its PF. And all the -* further MCAM rules installed by VF on its own are -* concatenated with the base rule set by its PF. Hence PF entries -* should be at lower priority compared to VF entries. Otherwise -* base rule is hit always and rules installed by VF will be of -* no use. Hence if the request is from PF and NOT a priority -* allocation request then allocate low priority entries. -*/ -if (!(pcifunc &RVU_PFVF_FUNC_MASK )) - goto lprio_alloc; -/* Find out the search range for non-priority allocation request * * Get MCAM free entry count in middle zone.
@@ -2555,6 +2554,18 @@ static int npc_mcam_alloc_entries(struct npc_mcam *mcam, u16 pcifunc, reverse = true; start =0 ; end = mcam->bmap_entries; +/* Ensure PF requests are always at bottom and if PF requests +* for higher/lower priority entry wrt reference entry then +* honour that criteria and start search for entries from bottom +* and not in mid zone. +*/ +if (!(pcifunc &RVU_PFVF_FUNC_MASK ) && + req->priority ==NPC_MCAM_HIGHER_PRIO ) + end = req->ref_entry; + +if (!(pcifunc &RVU_PFVF_FUNC_MASK ) && + req->priority ==NPC_MCAM_LOWER_PRIO ) + start = req->ref_entry; } alloc:
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 19/217 net/smc: avoid overwriting when adjusting sock bufsizes
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Wen Gu <[email protected]>
[ Upstream commit fb0aa0781a5f457e3864da68af52c3b1f4f7fd8f ]
When copying smc settings to clcsock, avoid setting clcsock's sk_sndbuf to sysctl_tcp_wmem[1], since this may overwrite the value set by tcp_sndbuf_expand() in TCP connection establishment.
And the other setting sk_{snd|rcv}buf to sysctl value in smc_adjust_sock_bufsizes() can also be omitted since the initialization of smc sock and clcsock has set sk_{snd|rcv}buf to smc.sysctl_{w|r}mem or ipv4_sysctl_tcp_{w|r}mem[1].
--- net/smc/af_smc.c | 22 ++-------------------- 1 file changed, 2 insertions(+), 20 deletions(-)
net/smc/af_smc.c +2 -20
@@ -462,29 +462,11 @@ static int smc_bind(struct socket *sock, struct sockaddr *uaddr,static void smc_adjust_sock_bufsizes (struct sock *nsk,struct sock *osk,unsigned long mask) { -struct net *nnet =sock_net (nsk); - nsk->sk_userlocks = osk->sk_userlocks; -if (osk->sk_userlocks &SOCK_SNDBUF_LOCK ) { +if (osk->sk_userlocks &SOCK_SNDBUF_LOCK ) nsk->sk_sndbuf = osk->sk_sndbuf; - }else { -if (mask ==SK_FLAGS_SMC_TO_CLC ) -WRITE_ONCE (nsk->sk_sndbuf, -READ_ONCE (nnet->ipv4.sysctl_tcp_wmem[1 ])); -else -WRITE_ONCE (nsk->sk_sndbuf, -2 *READ_ONCE (nnet->smc.sysctl_wmem)); - } -if (osk->sk_userlocks &SOCK_RCVBUF_LOCK ) { +if (osk->sk_userlocks &SOCK_RCVBUF_LOCK ) nsk->sk_rcvbuf = osk->sk_rcvbuf; - }else { -if (mask ==SK_FLAGS_SMC_TO_CLC ) -WRITE_ONCE (nsk->sk_rcvbuf, -READ_ONCE (nnet->ipv4.sysctl_tcp_rmem[1 ])); -else -WRITE_ONCE (nsk->sk_rcvbuf, -2 *READ_ONCE (nnet->smc.sysctl_rmem)); - } } static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk,
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 2/217 wifi: mac80211: Fix deadlock in ieee80211_sta_ps_deliver_wakeup()
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Remi Pommarel <[email protected]>
[ Upstream commit 44c06bbde6443de206b30f513100b5670b23fc5e ]
The ieee80211_sta_ps_deliver_wakeup() function takes sta->ps_lock to synchronizes with ieee80211_tx_h_unicast_ps_buf() which is called from softirq context. However using only spin_lock() to get sta->ps_lock in ieee80211_sta_ps_deliver_wakeup() does not prevent softirq to execute on this same CPU, to run ieee80211_tx_h_unicast_ps_buf() and try to take this same lock ending in deadlock. Below is an example of rcu stall that arises in such situation.
rcu: INFO: rcu_sched self-detected stall on CPU rcu: 2-....: (42413413 ticks this GP) idle=b154/1/0x4000000000000000 softirq=1763/1765 fqs=21206996 rcu: (t=42586894 jiffies g=2057 q=362405 ncpus=4) CPU: 2 PID: 719 Comm: wpa_supplicant Tainted: G W 6.4.0-02158-g1b062f552873 #742 Hardware name: RPT (r1) (DT) pstate: 00000005 (nzcv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : queued_spin_lock_slowpath+0x58/0x2d0 lr : invoke_tx_handlers_early+0x5b4/0x5c0 sp : ffff00001ef64660 x29: ffff00001ef64660 x28: ffff000009bc1070 x27: ffff000009bc0ad8 x26: ffff000009bc0900 x25: ffff00001ef647a8 x24: 0000000000000000 x23: ffff000009bc0900 x22: ffff000009bc0900 x21: ffff00000ac0e000 x20: ffff00000a279e00 x19: ffff00001ef646e8 x18: 0000000000000000 x17: ffff800016468000 x16: ffff00001ef608c0 x15: 0010533c93f64f80 x14: 0010395c9faa3946 x13: 0000000000000000 x12: 00000000fa83b2da x11: 000000012edeceea x10: ffff0000010fbe00 x9 : 0000000000895440 x8 : 000000000010533c x7 : ffff00000ad8b740 x6 : ffff00000c350880 x5 : 0000000000000007 x4 : 0000000000000001 x3 : 0000000000000000 x2 : 0000000000000000 x1 : 0000000000000001 x0 : ffff00000ac0e0e8 Call trace: queued_spin_lock_slowpath+0x58/0x2d0 ieee80211_tx+0x80/0x12c ieee80211_tx_pending+0x110/0x278 tasklet_action_common.constprop.0+0x10c/0x144 tasklet_action+0x20/0x28 _stext+0x11c/0x284 ____do_softirq+0xc/0x14 call_on_irq_stack+0x24/0x34 do_softirq_own_stack+0x18/0x20 do_softirq+0x74/0x7c __local_bh_enable_ip+0xa0/0xa4 _ieee80211_wake_txqs+0x3b0/0x4b8 __ieee80211_wake_queue+0x12c/0x168 ieee80211_add_pending_skbs+0xec/0x138 ieee80211_sta_ps_deliver_wakeup+0x2a4/0x480 ieee80211_mps_sta_status_update.part.0+0xd8/0x11c ieee80211_mps_sta_status_update+0x18/0x24 sta_apply_parameters+0x3bc/0x4c0 ieee80211_change_station+0x1b8/0x2dc nl80211_set_station+0x444/0x49c genl_family_rcv_msg_doit.isra.0+0xa4/0xfc genl_rcv_msg+0x1b0/0x244 netlink_rcv_skb+0x38/0x10c genl_rcv+0x34/0x48 netlink_unicast+0x254/0x2bc netlink_sendmsg+0x190/0x3b4 ____sys_sendmsg+0x1e8/0x218 ___sys_sendmsg+0x68/0x8c __sys_sendmsg+0x44/0x84 __arm64_sys_sendmsg+0x20/0x28 do_el0_svc+0x6c/0xe8 el0_svc+0x14/0x48 el0t_64_sync_handler+0xb0/0xb4 el0t_64_sync+0x14c/0x150
Using spin_lock_bh()/spin_unlock_bh() instead prevents softirq to raise on the same CPU that is holding the lock.
--- net/mac80211/sta_info.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
net/mac80211/sta_info.c +2 -2
@@ -1555,7 +1555,7 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)skb_queue_head_init (&pending);/* sync with ieee80211_tx_h_unicast_ps_buf */ -spin_lock (&sta->ps_lock); +spin_lock_bh (&sta->ps_lock);/* Send all buffered frames to the station */ for (ac =0 ; ac <IEEE80211_NUM_ACS ; ac++) {int count =skb_queue_len (&pending), tmp;
@@ -1584,7 +1584,7 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)*/ clear_sta_flag (sta,WLAN_STA_PSPOLL );clear_sta_flag (sta,WLAN_STA_UAPSD ); -spin_unlock (&sta->ps_lock); +spin_unlock_bh (&sta->ps_lock);atomic_dec (&ps->num_sta_ps);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 20/217 net: sched: sch_multiq: fix possible OOB write in multiq_tune()
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Hangyu Hua <[email protected]>
[ Upstream commit affc18fdc694190ca7575b9a86632a73b9fe043d ]
q->bands will be assigned to qopt->bands to execute subsequent code logic after kmalloc. So the old q->bands should not be used in kmalloc. Otherwise, an out-of-bounds write will occur.
--- net/sched/sch_multiq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/sched/sch_multiq.c +1 -1
@@ -185,7 +185,7 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt, qopt->bands =qdisc_dev (sch)->real_num_tx_queues; - removed =kmalloc (sizeof (*removed) * (q->max_bands - q->bands), + removed =kmalloc (sizeof (*removed) * (q->max_bands - qopt->bands),GFP_KERNEL );if (!removed)return -ENOMEM ;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 21/217 vxlan: Fix regression when dropping packets due to invalid src addresses
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Daniel Borkmann <[email protected]>
[ Upstream commit 1cd4bc987abb2823836cbb8f887026011ccddc8a ]
Commit f58f45c1e5b9 ("vxlan: drop packets from invalid src-address") has recently been added to vxlan mainly in the context of source address snooping/learning so that when it is enabled, an entry in the FDB is not being created for an invalid address for the corresponding tunnel endpoint.
Before commit f58f45c1e5b9 vxlan was similarly behaving as geneve in that it passed through whichever macs were set in the L2 header. It turns out that this change in behavior breaks setups, for example, Cilium with netkit in L3 mode for Pods as well as tunnel mode has been passing before the change in f58f45c1e5b9 for both vxlan and geneve. After mentioned change it is only passing for geneve as in case of vxlan packets are dropped due to vxlan_set_mac() returning false as source and destination macs are zero which for E/W traffic via tunnel is totally fine.
Fix it by only opting into the is_valid_ether_addr() check in vxlan_set_mac() when in fact source address snooping/learning is actually enabled in vxlan. This is done by moving the check into vxlan_snoop(). With this change, the Cilium connectivity test suite passes again for both tunnel flavors.
--- drivers/net/vxlan/vxlan_core.c | 4 ++++ 1 file changed, 4 insertions(+)
drivers/net/vxlan/vxlan_core.c +4 -0
@@ -1493,6 +1493,10 @@ static bool vxlan_snoop(struct net_device *dev,struct vxlan_fdb *f;u32 ifindex =0 ; +/* Ignore packets from invalid src-address */ +if (!is_valid_ether_addr (src_mac)) +return true; +#if IS_ENABLED (CONFIG_IPV6 )if (src_ip->sa.sa_family ==AF_INET6 && (ipv6_addr_type (&src_ip->sin6.sin6_addr) &IPV6_ADDR_LINKLOCAL ))
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 22/217 tcp: count CLOSE-WAIT sockets for TCP_MIB_CURRESTAB
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jason Xing <[email protected]>
[ Upstream commit a46d0ea5c94205f40ecf912d1bb7806a8a64704f ]
According to RFC 1213, we should also take CLOSE-WAIT sockets into consideration:
"tcpCurrEstab OBJECT-TYPE
...
The number of TCP connections for which the current state is either ESTABLISHED or CLOSE- WAIT."
After this, CurrEstab counter will display the total number of ESTABLISHED and CLOSE-WAIT sockets.
The logic of counting
When we increment the counter?
a) if we change the state to ESTABLISHED.
b) if we change the state from SYN-RECEIVED to CLOSE-WAIT.
When we decrement the counter?
a) if the socket leaves ESTABLISHED and will never go into CLOSE-WAIT, say, on the client side, changing from ESTABLISHED to FIN-WAIT-1.
b) if the socket leaves CLOSE-WAIT, say, on the server side, changing from CLOSE-WAIT to LAST-ACK.
Please note: there are two chances that old state of socket can be changed to CLOSE-WAIT in tcp_fin(). One is SYN-RECV, the other is ESTABLISHED. So we have to take care of the former case.
--- net/ipv4/tcp.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)
net/ipv4/tcp.c +5 -1
@@ -2758,6 +2758,10 @@ void tcp_set_state(struct sock *sk, int state)if (oldstate !=TCP_ESTABLISHED )TCP_INC_STATS (sock_net (sk),TCP_MIB_CURRESTAB );break ; +case TCP_CLOSE_WAIT : +if (oldstate ==TCP_SYN_RECV ) +TCP_INC_STATS (sock_net (sk),TCP_MIB_CURRESTAB ); +break ;case TCP_CLOSE :if (oldstate ==TCP_CLOSE_WAIT || oldstate ==TCP_ESTABLISHED )
@@ -2769,7 +2773,7 @@ void tcp_set_state(struct sock *sk, int state)inet_put_port (sk); fallthrough;default : -if (oldstate ==TCP_ESTABLISHED ) +if (oldstate ==TCP_ESTABLISHED || oldstate ==TCP_CLOSE_WAIT )TCP_DEC_STATS (sock_net (sk),TCP_MIB_CURRESTAB ); }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 23/217 net/mlx5: Stop waiting for PCI up if teardown was triggered
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Moshe Shemesh <[email protected]>
[ Upstream commit 8ff38e730c3f5ee717f25365ef8aa4739562d567 ]
If driver teardown is called while PCI is turned off, there is a race between health recovery and teardown. If health recovery already started it will wait 60 sec trying to see if PCI gets back and it can recover, but actually there is no need to wait anymore once teardown was called.
Use the MLX5_BREAK_FW_WAIT flag which is set on driver teardown to break waiting for PCI up.
Stable-dep-of: 33afbfcc105a ("net/mlx5: Stop waiting for PCI if pci channel is offline")
--- drivers/net/ethernet/mellanox/mlx5/core/health.c | 4 ++++ 1 file changed, 4 insertions(+)
drivers/net/ethernet/mellanox/mlx5/core/health.c +4 -0
@@ -325,6 +325,10 @@ int mlx5_health_wait_pci_up(struct mlx5_core_dev *dev)while (sensor_pci_not_working (dev)) {if (time_after (jiffies, end))return -ETIMEDOUT ; +if (test_bit (MLX5_BREAK_FW_WAIT , &dev->intf_state)) { +mlx5_core_warn (dev,"device is being removed, stop waiting for PCI\n" ); +return -ENODEV ; + }msleep (100 ); }return 0 ;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 24/217 net/mlx5: Stop waiting for PCI if pci channel is offline
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Moshe Shemesh <[email protected]>
[ Upstream commit 33afbfcc105a572159750f2ebee834a8a70fdd96 ]
In case pci channel becomes offline the driver should not wait for PCI reads during health dump and recovery flow. The driver has timeout for each of these loops trying to read PCI, so it would fail anyway. However, in case of recovery waiting till timeout may cause the pci error_detected() callback fail to meet pci_dpc_recovered() wait timeout.
--- drivers/net/ethernet/mellanox/mlx5/core/fw.c | 4 ++++ drivers/net/ethernet/mellanox/mlx5/core/health.c | 8 ++++++++ drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c | 4 ++++ 3 files changed, 16 insertions(+)
drivers/net/ethernet/mellanox/mlx5/core/fw.c +4 -0
@@ -379,6 +379,10 @@ int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev)do {if (mlx5_get_nic_state (dev) ==MLX5_NIC_IFC_DISABLED )break ; +if (pci_channel_offline (dev->pdev)) { +mlx5_core_err (dev,"PCI channel offline, stop waiting for NIC IFC\n" ); +return -EACCES ; + }cond_resched (); }while (!time_after (jiffies, end));
drivers/net/ethernet/mellanox/mlx5/core/health.c +8 -0
@@ -260,6 +260,10 @@ void mlx5_error_sw_reset(struct mlx5_core_dev *dev)do {if (mlx5_get_nic_state (dev) ==MLX5_NIC_IFC_DISABLED )break ; +if (pci_channel_offline (dev->pdev)) { +mlx5_core_err (dev,"PCI channel offline, stop waiting for NIC IFC\n" ); + goto unlock; + }msleep (20 ); }while (!time_after (jiffies, end));
@@ -329,6 +333,10 @@ int mlx5_health_wait_pci_up(struct mlx5_core_dev *dev)mlx5_core_warn (dev,"device is being removed, stop waiting for PCI\n" );return -ENODEV ; } +if (pci_channel_offline (dev->pdev)) { +mlx5_core_err (dev,"PCI channel offline, stop waiting for PCI\n" ); +return -EACCES ; + }msleep (100 ); }return 0 ;
drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c +4 -0
@@ -74,6 +74,10 @@ int mlx5_vsc_gw_lock(struct mlx5_core_dev *dev) ret = -EBUSY ; goto pci_unlock; } +if (pci_channel_offline (dev->pdev)) { + ret = -EACCES ; + goto pci_unlock; + }/* Check if semaphore is already locked */ ret =vsc_read (dev,VSC_SEMAPHORE_OFFSET , &lock_val);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 25/217 net/mlx5: Split function_setup() to enable and open functions
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Shay Drory <[email protected]>
[ Upstream commit 2059cf51f318681a4cdd3eb1a01a2d62b6a9c442 ]
mlx5_cmd_init_hca() is taking ~0.2 seconds. In case of a user who desire to disable some of the SF aux devices, and with large scale-1K SFs for example, this user will waste more than 3 minutes on mlx5_cmd_init_hca() which isn't needed at this stage.
Downstream patch will change SFs which are probe over the E-switch, local SFs, to be probed without any aux dev. In order to support this, split function_setup() to avoid executing mlx5_cmd_init_hca().
Stable-dep-of: c8b3f38d2dae ("net/mlx5: Always stop health timer during driver removal")
--- .../net/ethernet/mellanox/mlx5/core/main.c | 83 +++++++++++++------ 1 file changed, 58 insertions(+), 25 deletions(-)
drivers/net/ethernet/mellanox/mlx5/core/main.c +58 -25
@@ -1093,7 +1093,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)mlx5_devcom_unregister_device (dev->priv.devcom); } -static int mlx5_function_setup (struct mlx5_core_dev *dev,bool boot,u64 timeout) +static int mlx5_function_enable (struct mlx5_core_dev *dev,bool boot,u64 timeout) {int err;
@@ -1158,28 +1158,56 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot, u64 timeout goto reclaim_boot_pages; } +return 0 ; + +reclaim_boot_pages: +mlx5_reclaim_startup_pages (dev); +err_disable_hca: +mlx5_core_disable_hca (dev,0 ); +stop_health_poll: +mlx5_stop_health_poll (dev, boot); +err_cmd_cleanup: +mlx5_cmd_set_state (dev,MLX5_CMDIF_STATE_DOWN ); +mlx5_cmd_cleanup (dev); + +return err; +} + +static void mlx5_function_disable (struct mlx5_core_dev *dev,bool boot) +{ +mlx5_reclaim_startup_pages (dev); +mlx5_core_disable_hca (dev,0 ); +mlx5_stop_health_poll (dev, boot); +mlx5_cmd_set_state (dev,MLX5_CMDIF_STATE_DOWN ); +mlx5_cmd_cleanup (dev); +} + +static int mlx5_function_open (struct mlx5_core_dev *dev) +{ +int err; + err =set_hca_ctrl (dev);if (err) {mlx5_core_err (dev,"set_hca_ctrl failed\n" ); - goto reclaim_boot_pages; +return err; } err =set_hca_cap (dev);if (err) {mlx5_core_err (dev,"set_hca_cap failed\n" ); - goto reclaim_boot_pages; +return err; } err =mlx5_satisfy_startup_pages (dev,0 );if (err) {mlx5_core_err (dev,"failed to allocate init pages\n" ); - goto reclaim_boot_pages; +return err; } err =mlx5_cmd_init_hca (dev, sw_owner_id);if (err) {mlx5_core_err (dev,"init hca failed\n" ); - goto reclaim_boot_pages; +return err; }mlx5_set_driver_version (dev);
@@ -1187,26 +1215,13 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot, u64 timeout err =mlx5_query_hca_caps (dev);if (err) {mlx5_core_err (dev,"query hca failed\n" ); - goto reclaim_boot_pages; +return err; }mlx5_start_health_fw_log_up (dev); -return 0 ; - -reclaim_boot_pages: -mlx5_reclaim_startup_pages (dev); -err_disable_hca: -mlx5_core_disable_hca (dev,0 ); -stop_health_poll: -mlx5_stop_health_poll (dev, boot); -err_cmd_cleanup: -mlx5_cmd_set_state (dev,MLX5_CMDIF_STATE_DOWN ); -mlx5_cmd_cleanup (dev); - -return err; } -static int mlx5_function_teardown (struct mlx5_core_dev *dev,bool boot) +static int mlx5_function_close (struct mlx5_core_dev *dev) {int err;
@@ -1215,15 +1230,33 @@ static int mlx5_function_teardown(struct mlx5_core_dev *dev, bool boot)mlx5_core_err (dev,"tear_down_hca failed, skip cleanup\n" );return err; } -mlx5_reclaim_startup_pages (dev); -mlx5_core_disable_hca (dev,0 ); -mlx5_stop_health_poll (dev, boot); -mlx5_cmd_set_state (dev,MLX5_CMDIF_STATE_DOWN ); -mlx5_cmd_cleanup (dev);return 0 ; } +static int mlx5_function_setup (struct mlx5_core_dev *dev,bool boot,u64 timeout) +{ +int err; + + err =mlx5_function_enable (dev, boot, timeout); +if (err) +return err; + + err =mlx5_function_open (dev); +if (err) +mlx5_function_disable (dev, boot); +return err; +} + +static int mlx5_function_teardown (struct mlx5_core_dev *dev,bool boot) +{ +int err =mlx5_function_close (dev); + +if (!err) +mlx5_function_disable (dev, boot); +return err; +} +static int mlx5_load (struct mlx5_core_dev *dev) {int err;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 26/217 net/mlx5: Always stop health timer during driver removal
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Shay Drory <[email protected]>
[ Upstream commit c8b3f38d2dae0397944814d691a419c451f9906f ]
Currently, if teardown_hca fails to execute during driver removal, mlx5 does not stop the health timer. Afterwards, mlx5 continue with driver teardown. This may lead to a UAF bug, which results in page fault Oops[1], since the health timer invokes after resources were freed.
Hence, stop the health monitor even if teardown_hca fails.
[1]mlx5_core 0000:18:00.0: E-Switch: Unload vfs: mode(LEGACY), nvfs(0), necvfs(0), active vports(0) mlx5_core 0000:18:00.0: E-Switch: Disable: mode(LEGACY), nvfs(0), necvfs(0), active vports(0) mlx5_core 0000:18:00.0: E-Switch: Disable: mode(LEGACY), nvfs(0), necvfs(0), active vports(0) mlx5_core 0000:18:00.0: E-Switch: cleanupmlx5_core 0000:18:00.0: wait_func:1155:(pid 1967079): TEARDOWN_HCA(0x103) timeout. Will cause a leak of a command resource mlx5_core 0000:18:00.0: mlx5_function_close:1288:(pid 1967079): tear_down_hca failed, skip cleanup
BUG: unable to handle page fault for address: ffffa26487064230 PGD 100c00067 P4D 100c00067 PUD 100e5a067 PMD 105ed7067 PTE 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 0 PID: 0 Comm: swapper/0 Tainted: G OE ------- --- 6.7.0-68.fc38.x86_64 #1 Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.02.01.0013.121520200651 12/15/2020 RIP: 0010:ioread32be+0x34/0x60 RSP: 0018:ffffa26480003e58 EFLAGS: 00010292 RAX: ffffa26487064200 RBX: ffff9042d08161a0 RCX: ffff904c108222c0 RDX: 000000010bbf1b80 RSI: ffffffffc055ddb0 RDI: ffffa26487064230 RBP: ffff9042d08161a0 R08: 0000000000000022 R09: ffff904c108222e8 R10: 0000000000000004 R11: 0000000000000441 R12: ffffffffc055ddb0 R13: ffffa26487064200 R14: ffffa26480003f00 R15: ffff904c108222c0 FS: 0000000000000000(0000) GS:ffff904c10800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffa26487064230 CR3: 00000002c4420006 CR4: 00000000007706f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: <IRQ> ? __die+0x23/0x70 ? page_fault_oops+0x171/0x4e0 ? exc_page_fault+0x175/0x180 ? asm_exc_page_fault+0x26/0x30 ? __pfx_poll_health+0x10/0x10 [mlx5_core] ? __pfx_poll_health+0x10/0x10 [mlx5_core] ? ioread32be+0x34/0x60 mlx5_health_check_fatal_sensors+0x20/0x100 [mlx5_core] ? __pfx_poll_health+0x10/0x10 [mlx5_core] poll_health+0x42/0x230 [mlx5_core] ? __next_timer_interrupt+0xbc/0x110 ? __pfx_poll_health+0x10/0x10 [mlx5_core] call_timer_fn+0x21/0x130 ? __pfx_poll_health+0x10/0x10 [mlx5_core] __run_timers+0x222/0x2c0 run_timer_softirq+0x1d/0x40 __do_softirq+0xc9/0x2c8 __irq_exit_rcu+0xa6/0xc0 sysvec_apic_timer_interrupt+0x72/0x90 </IRQ> <TASK> asm_sysvec_apic_timer_interrupt+0x1a/0x20 RIP: 0010:cpuidle_enter_state+0xcc/0x440 ? cpuidle_enter_state+0xbd/0x440 cpuidle_enter+0x2d/0x40 do_idle+0x20d/0x270 cpu_startup_entry+0x2a/0x30 rest_init+0xd0/0xd0 arch_call_rest_init+0xe/0x30 start_kernel+0x709/0xa90 x86_64_start_reservations+0x18/0x30 x86_64_start_kernel+0x96/0xa0 secondary_startup_64_no_verify+0x18f/0x19b ---[ end trace 0000000000000000 ]---
--- drivers/net/ethernet/mellanox/mlx5/core/main.c | 3 +++ 1 file changed, 3 insertions(+)
drivers/net/ethernet/mellanox/mlx5/core/main.c +3 -0
@@ -1254,6 +1254,9 @@ static int mlx5_function_teardown(struct mlx5_core_dev *dev, bool boot)if (!err)mlx5_function_disable (dev, boot); +else +mlx5_stop_health_poll (dev, boot); +return err; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 27/217 net/mlx5: Fix tainted pointer delete is case of flow rules creation fail
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Aleksandr Mishin <[email protected]>
[ Upstream commit 229bedbf62b13af5aba6525ad10b62ad38d9ccb5 ]
In case of flow rule creation fail in mlx5_lag_create_port_sel_table(), instead of previously created rules, the tainted pointer is deleted deveral times.
Fix this bug by using correct flow rules pointers.
Found by Linux Verification Center (linuxtesting.org) with SVACE.
--- drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)
drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c +6 -2
@@ -88,9 +88,13 @@ static int mlx5_lag_create_port_sel_table(struct mlx5_lag *ldev, &dest, 1);if (IS_ERR (lag_definer->rules[idx])) { err =PTR_ERR (lag_definer->rules[idx]); -while (i--) -while (j--) +do { +while (j--) { + idx = i * ldev->buckets + j;mlx5_del_flow_rules (lag_definer->rules[idx]); + } + j = ldev->buckets; + }while (i--); goto destroy_fg; } }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 28/217 net/sched: taprio: always validate TCA_TAPRIO_ATTR_PRIOMAP
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Eric Dumazet <[email protected]>
[ Upstream commit f921a58ae20852d188f70842431ce6519c4fdc36 ]
If one TCA_TAPRIO_ATTR_PRIOMAP attribute has been provided, taprio_parse_mqprio_opt() must validate it, or userspace can inject arbitrary data to the kernel, the second time taprio_change() is called.
First call (with valid attributes) sets dev->num_tc to a non zero value.
Second call (with arbitrary mqprio attributes)
returns early from taprio_parse_mqprio_opt()
and bad things can happen.
--- net/sched/sch_taprio.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-)
net/sched/sch_taprio.c +6 -9
@@ -938,16 +938,13 @@ static int taprio_parse_mqprio_opt(struct net_device *dev, {int i, j; -if (!qopt && !dev->num_tc) { -NL_SET_ERR_MSG (extack,"'mqprio' configuration is necessary" ); -return -EINVAL ; - } - -/* If num_tc is already set, it means that the user already -* configured the mqprio part -*/ -if (dev->num_tc) +if (!qopt) { +if (!dev->num_tc) { +NL_SET_ERR_MSG (extack,"'mqprio' configuration is necessary" ); +return -EINVAL ; + }return 0 ; + }/* Verify num_tc is not out of max range */ if (qopt->num_tc >TC_MAX_QUEUE ) {
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 29/217 ptp: Fix error message on failed pin verification
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Karol Kolacinski <[email protected]>
[ Upstream commit 323a359f9b077f382f4483023d096a4d316fd135 ]
On failed verification of PTP clock pin, error message prints channel number instead of pin index after "pin", which is incorrect.
Fix error message by adding channel number to the message and printing pin number instead of channel number.
--- drivers/ptp/ptp_chardev.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/ptp/ptp_chardev.c +2 -1
@@ -84,7 +84,8 @@ int ptp_set_pinfunc(struct ptp_clock *ptp, unsigned int pin, }if (info->verify (info, pin, func, chan)) { -pr_err ("driver cannot use function %u on pin %u\n" , func, chan); +pr_err ("driver cannot use function %u and channel %u on pin %u\n" , + func, chan, pin);return -EOPNOTSUPP ; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 3/217 wifi: cfg80211: fully move wiphy work to unbound workqueue
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Johannes Berg <[email protected]>
[ Upstream commit e296c95eac655008d5a709b8cf54d0018da1c916 ]
Previously I had moved the wiphy work to the unbound system workqueue, but missed that when it restarts and during resume it was still using the normal system workqueue. Fix that.
--- net/wireless/core.c | 2 +- net/wireless/sysfs.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-)
net/wireless/core.c +1 -1
@@ -427,7 +427,7 @@ static void cfg80211_wiphy_work(struct work_struct *work)if (wk) {list_del_init (&wk->entry);if (!list_empty (&rdev->wiphy_work_list)) -schedule_work (work); +queue_work (system_unbound_wq, work);spin_unlock_irq (&rdev->wiphy_work_lock); wk->func (&rdev->wiphy, wk);
net/wireless/sysfs.c +2 -2
@@ -5,7 +5,7 @@* * Copyright 2005-2006 Jiri Benc <[email protected]> * Copyright 2006 Johannes Berg <[email protected]> -* Copyright (C) 2020-2021, 2023 Intel Corporation +* Copyright (C) 2020-2021, 2023-2024 Intel Corporation */ #include <linux/device.h>
@@ -137,7 +137,7 @@ static int wiphy_resume(struct device *dev)if (rdev->wiphy.registered && rdev->ops->resume) ret =rdev_resume (rdev); rdev->suspended = false; -schedule_work (&rdev->wiphy_work); +queue_work (system_unbound_wq, &rdev->wiphy_work);wiphy_unlock (&rdev->wiphy);if (ret)
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 30/217 ice: fix iteration of TLVs in Preserved Fields Area
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jacob Keller <[email protected]>
[ Upstream commit 03e4a092be8ce3de7c1baa7ae14e68b64e3ea644 ]
The ice_get_pfa_module_tlv() function iterates over the Type-Length-Value structures in the Preserved Fields Area (PFA) of the NVM. This is used by the driver to access data such as the Part Board Assembly identifier.
The function uses simple logic to iterate over the PFA. First, the pointer to the PFA in the NVM is read. Then the total length of the PFA is read from the first word.
A pointer to the first TLV is initialized, and a simple loop iterates over each TLV. The pointer is moved forward through the NVM until it exceeds the PFA area.
The logic seems sound, but it is missing a key detail. The Preserved Fields Area length includes one additional final word. This is documented in the device data sheet as a dummy word which contains 0xFFFF. All NVMs have this extra word.
If the driver tries to scan for a TLV that is not in the PFA, it will read past the size of the PFA. It reads and interprets the last dummy word of the PFA as a TLV with type 0xFFFF. It then reads the word following the PFA as a length.
The PFA resides within the Shadow RAM portion of the NVM, which is relatively small. All of its offsets are within a 16-bit size. The PFA pointer and TLV pointer are stored by the driver as 16-bit values.
In almost all cases, the word following the PFA will be such that interpreting it as a length will result in 16-bit arithmetic overflow. Once overflowed, the new next_tlv value is now below the maximum offset of the PFA. Thus, the driver will continue to iterate the data as TLVs. In the worst case, the driver hits on a sequence of reads which loop back to reading the same offsets in an endless loop.
To fix this, we need to correct the loop iteration check to account for this extra word at the end of the PFA. This alone is sufficient to resolve the known cases of this issue in the field. However, it is plausible that an NVM could be misconfigured or have corrupt data which results in the same kind of overflow. Protect against this by using check_add_overflow when calculating both the maximum offset of the TLVs, and when calculating the next_tlv offset at the end of each loop iteration. This ensures that the driver will not get stuck in an infinite loop when scanning the PFA.
--- drivers/net/ethernet/intel/ice/ice_nvm.c | 28 ++++++++++++++++++------ 1 file changed, 21 insertions(+), 7 deletions(-)
drivers/net/ethernet/intel/ice/ice_nvm.c +21 -7
@@ -441,8 +441,7 @@ int ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16 *module_tlv_len, u16 module_type) { - u16 pfa_len, pfa_ptr; -u16 next_tlv; + u16 pfa_len, pfa_ptr, next_tlv, max_tlv;int status; status =ice_read_sr_word (hw,ICE_SR_PFA_PTR , &pfa_ptr);
@@ -455,11 +454,23 @@ ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16 *module_tlv_len,ice_debug (hw,ICE_DBG_INIT ,"Failed to read PFA length.\n" );return status; } + +/* The Preserved Fields Area contains a sequence of Type-Length-Value +* structures which define its contents. The PFA length includes all +* of the TLVs, plus the initial length word itself, *and* one final +* word at the end after all of the TLVs. +*/ +if (check_add_overflow (pfa_ptr, pfa_len -1 , &max_tlv)) { +dev_warn (ice_hw_to_dev (hw),"PFA starts at offset %u. PFA length of %u caused 16-bit arithmetic overflow.\n" , + pfa_ptr, pfa_len); +return -EINVAL ; + } +/* Starting with first TLV after PFA length, iterate through the list * of TLVs to find the requested one. */ next_tlv = pfa_ptr +1 ; -while (next_tlv < pfa_ptr + pfa_len) { +while (next_tlv < max_tlv) {u16 tlv_sub_module_type;u16 tlv_len;
@@ -483,10 +494,13 @@ ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16 *module_tlv_len, }return -EINVAL ; } -/* Check next TLV, i.e. current TLV pointer + length + 2 words -* (for current TLV's type and length) -*/ - next_tlv = next_tlv + tlv_len +2 ; + +if (check_add_overflow (next_tlv,2 , &next_tlv) || +check_add_overflow (next_tlv, tlv_len, &next_tlv)) { +dev_warn (ice_hw_to_dev (hw),"TLV of type %u and length 0x%04x caused 16-bit arithmetic overflow. The PFA starts at 0x%04x and has length of 0x%04x\n" , + tlv_sub_module_type, tlv_len, pfa_ptr, pfa_len); +return -EINVAL ; + } }/* Module does not exist */ return -ENOENT ;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 31/217 ice: Introduce new parameters in ice_sched_node
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Michal Wilczynski <[email protected]>
[ Upstream commit 16dfa49406bc5e1f4cbb115027cbd719d7e6c930 ]
To support new devlink-rate API ice_sched_node struct needs to store a number of additional parameters. This includes tx_max, tx_share, tx_weight, and tx_priority.
Add new fields to ice_sched_node struct. Add new functions to configure the hardware with new parameters. Introduce new xarray to identify nodes uniquely.
Stable-dep-of: adbf5a42341f ("ice: remove af_xdp_zc_qps bitmap")
--- .../net/ethernet/intel/ice/ice_adminq_cmd.h | 4 +- drivers/net/ethernet/intel/ice/ice_common.c | 3 + drivers/net/ethernet/intel/ice/ice_sched.c | 81 +++++++++++++++++-- drivers/net/ethernet/intel/ice/ice_sched.h | 27 +++++++ drivers/net/ethernet/intel/ice/ice_type.h | 8 ++ 5 files changed, 116 insertions(+), 7 deletions(-)
drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +2 -2
@@ -848,9 +848,9 @@ struct ice_aqc_txsched_elem {u8 generic;#define ICE_AQC_ELEM_GENERIC_MODE_M 0x1#define ICE_AQC_ELEM_GENERIC_PRIO_S 0x1 -#define ICE_AQC_ELEM_GENERIC_PRIO_M (0x7 << ICE_AQC_ELEM_GENERIC_PRIO_S) +#define ICE_AQC_ELEM_GENERIC_PRIO_M GENMASK(3, 1)#define ICE_AQC_ELEM_GENERIC_SP_S 0x4 -#define ICE_AQC_ELEM_GENERIC_SP_M (0x1 << ICE_AQC_ELEM_GENERIC_SP_S) +#define ICE_AQC_ELEM_GENERIC_SP_M GENMASK(4, 4)#define ICE_AQC_ELEM_GENERIC_ADJUST_VAL_S 0x5#define ICE_AQC_ELEM_GENERIC_ADJUST_VAL_M \ (0x3 << ICE_AQC_ELEM_GENERIC_ADJUST_VAL_S)
drivers/net/ethernet/intel/ice/ice_common.c +3 -0
@@ -1105,6 +1105,9 @@ int ice_init_hw(struct ice_hw *hw) hw->evb_veb = true; +/* init xarray for identifying scheduling nodes uniquely */ +xa_init_flags (&hw->port_info->sched_node_ids,XA_FLAGS_ALLOC ); +/* Query the allocated resources for Tx scheduler */ status =ice_sched_query_res_alloc (hw);if (status) {
drivers/net/ethernet/intel/ice/ice_sched.c +76 -5
135 lines not on this page · raw message
drivers/net/ethernet/intel/ice/ice_sched.h +27 -0
@@ -6,6 +6,8 @@#include "ice_common.h" +#define SCHED_NODE_NAME_MAX_LEN 32 +#define ICE_QGRP_LAYER_OFFSET 2#define ICE_VSI_LAYER_OFFSET 4#define ICE_AGG_LAYER_OFFSET 6
@@ -69,6 +71,28 @@ int ice_aq_query_sched_elems(struct ice_hw *hw, u16 elems_req, struct ice_aqc_txsched_elem_data *buf, u16 buf_size, u16 *elems_ret, struct ice_sq_cd *cd); + +int +ice_sched_set_node_bw_lmt (struct ice_port_info *pi,struct ice_sched_node *node, +enum ice_rl_type rl_type,u32 bw); + +int +ice_sched_set_node_bw (struct ice_port_info *pi,struct ice_sched_node *node, +enum ice_rl_type rl_type,u32 bw,u8 layer_num); + +int +ice_sched_add_elems (struct ice_port_info *pi,struct ice_sched_node *tc_node, +struct ice_sched_node *parent,u8 layer,u16 num_nodes, +u16 *num_nodes_added,u32 *first_node_teid); + +int +ice_sched_move_nodes (struct ice_port_info *pi,struct ice_sched_node *parent, +u16 num_items,u32 *list); + +int ice_sched_set_node_priority (struct ice_port_info *pi,struct ice_sched_node *node, +u16 priority); +int ice_sched_set_node_weight (struct ice_port_info *pi,struct ice_sched_node *node,u16 weight); +int ice_sched_init_port (struct ice_port_info *pi);int ice_sched_query_res_alloc (struct ice_hw *hw);void ice_sched_get_psm_clk_freq (struct ice_hw *hw);
@@ -82,6 +106,9 @@ ice_sched_find_node_by_teid(struct ice_sched_node *start_node, u32 teid);int ice_sched_add_node (struct ice_port_info *pi,u8 layer,struct ice_aqc_txsched_elem_data *info); +void +ice_sched_update_parent (struct ice_sched_node *new_parent, +struct ice_sched_node *node);void ice_free_sched_node (struct ice_port_info *pi,struct ice_sched_node *node);struct ice_sched_node *ice_sched_get_tc_node (struct ice_port_info *pi,u8 tc); struct ice_sched_node *
drivers/net/ethernet/intel/ice/ice_type.h +8 -0
@@ -524,7 +524,14 @@ struct ice_sched_node {struct ice_sched_node *sibling;/* next sibling in the same layer */ struct ice_sched_node **children;struct ice_aqc_txsched_elem_data info; +char *name; +struct devlink_rate *rate_node; +u64 tx_max; +u64 tx_share;u32 agg_id;/* aggregator group ID */ +u32 id; +u32 tx_priority; +u32 tx_weight;u16 vsi_handle;u8 in_use;/* suspended or in use */ u8 tx_sched_layer;/* Logical Layer (1-9) */
@@ -706,6 +713,7 @@ struct ice_port_info {/* List contain profile ID(s) and other params per layer */ struct list_head rl_prof_list[ICE_AQC_TOPO_MAX_LEVEL_NUM ];struct ice_qos_cfg qos_cfg; +struct xarray sched_node_ids; u8 is_vf:1; };
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 4/217 wifi: cfg80211: Lock wiphy in cfg80211_get_station
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Remi Pommarel <[email protected]>
[ Upstream commit 642f89daa34567d02f312d03e41523a894906dae ]
Wiphy should be locked before calling rdev_get_station() (see lockdep assert in ieee80211_get_station()).
This fixes the following kernel NULL dereference:
Unable to handle kernel NULL pointer dereference at virtual address 0000000000000050 Mem abort info: ESR = 0x0000000096000006 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x06: level 2 translation fault Data abort info: ISV = 0, ISS = 0x00000006 CM = 0, WnR = 0 user pgtable: 4k pages, 48-bit VAs, pgdp=0000000003001000 [0000000000000050] pgd=0800000002dca003, p4d=0800000002dca003, pud=08000000028e9003, pmd=0000000000000000 Internal error: Oops: 0000000096000006 [#1] SMP Modules linked in: netconsole dwc3_meson_g12a dwc3_of_simple dwc3 ip_gre gre ath10k_pci ath10k_core ath9k ath9k_common ath9k_hw ath CPU: 0 PID: 1091 Comm: kworker/u8:0 Not tainted 6.4.0-02144-g565f9a3a7911-dirty #705 Hardware name: RPT (r1) (DT) Workqueue: bat_events batadv_v_elp_throughput_metric_update pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : ath10k_sta_statistics+0x10/0x2dc [ath10k_core] lr : sta_set_sinfo+0xcc/0xbd4 sp : ffff000007b43ad0 x29: ffff000007b43ad0 x28: ffff0000071fa900 x27: ffff00000294ca98 x26: ffff000006830880 x25: ffff000006830880 x24: ffff00000294c000 x23: 0000000000000001 x22: ffff000007b43c90 x21: ffff800008898acc x20: ffff00000294c6e8 x19: ffff000007b43c90 x18: 0000000000000000 x17: 445946354d552d78 x16: 62661f7200000000 x15: 57464f445946354d x14: 0000000000000000 x13: 00000000000000e3 x12: d5f0acbcebea978e x11: 00000000000000e3 x10: 000000010048fe41 x9 : 0000000000000000 x8 : ffff000007b43d90 x7 : 000000007a1e2125 x6 : 0000000000000000 x5 : ffff0000024e0900 x4 : ffff800000a0250c x3 : ffff000007b43c90 x2 : ffff00000294ca98 x1 : ffff000006831920 x0 : 0000000000000000 Call trace: ath10k_sta_statistics+0x10/0x2dc [ath10k_core] sta_set_sinfo+0xcc/0xbd4 ieee80211_get_station+0x2c/0x44 cfg80211_get_station+0x80/0x154 batadv_v_elp_get_throughput+0x138/0x1fc batadv_v_elp_throughput_metric_update+0x1c/0xa4 process_one_work+0x1ec/0x414 worker_thread+0x70/0x46c kthread+0xdc/0xe0 ret_from_fork+0x10/0x20 Code: a9bb7bfd 910003fd a90153f3 f9411c40 (f9402814)
This happens because STA has time to disconnect and reconnect before batadv_v_elp_throughput_metric_update() delayed work gets scheduled. In this situation, ath10k_sta_state() can be in the middle of resetting arsta data when the work queue get chance to be scheduled and ends up accessing it. Locking wiphy prevents that.
--- net/wireless/util.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)
net/wireless/util.c +6 -1
@@ -2202,6 +2202,7 @@ int cfg80211_get_station(struct net_device *dev, const u8 *mac_addr, {struct cfg80211_registered_device *rdev;struct wireless_dev *wdev; +int ret; wdev = dev->ieee80211_ptr;if (!wdev)
@@ -2213,7 +2214,11 @@ int cfg80211_get_station(struct net_device *dev, const u8 *mac_addr,memset (sinfo,0 ,sizeof (*sinfo)); -return rdev_get_station (rdev, dev, mac_addr, sinfo); +wiphy_lock (&rdev->wiphy); + ret =rdev_get_station (rdev, dev, mac_addr, sinfo); +wiphy_unlock (&rdev->wiphy); + +return ret; }EXPORT_SYMBOL (cfg80211_get_station);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 5/217 wifi: cfg80211: pmsr: use correct nla_get_uX functions
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Lin Ma <[email protected]>
[ Upstream commit ab904521f4de52fef4f179d2dfc1877645ef5f5c ]
The commit 9bb7e0f24e7e ("cfg80211: add peer measurement with FTM initiator API") defines four attributes NL80211_PMSR_FTM_REQ_ATTR_ {NUM_BURSTS_EXP}/{BURST_PERIOD}/{BURST_DURATION}/{FTMS_PER_BURST} in following ways.
static const struct nla_policy
nl80211_pmsr_ftm_req_attr_policy[NL80211_PMSR_FTM_REQ_ATTR_MAX + 1] = {
...
[NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP] =
NLA_POLICY_MAX(NLA_U8, 15),
[NL80211_PMSR_FTM_REQ_ATTR_BURST_PERIOD] = { .type = NLA_U16 },
[NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION] =
NLA_POLICY_MAX(NLA_U8, 15),
[NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST] =
NLA_POLICY_MAX(NLA_U8, 31),
...
};That is, those attributes are expected to be NLA_U8 and NLA_U16 types. However, the consumers of these attributes in pmsr_parse_ftm blindly all use nla_get_u32, which is incorrect and causes functionality issues on little-endian platforms. Hence, fix them with the correct nla_get_u8 and nla_get_u16 functions.
--- net/wireless/pmsr.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
net/wireless/pmsr.c +4 -4
@@ -56,7 +56,7 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, out->ftm.burst_period =0 ;if (tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_PERIOD ]) out->ftm.burst_period = -nla_get_u32 (tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_PERIOD ]); +nla_get_u16 (tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_PERIOD ]); out->ftm.asap = !!tb[NL80211_PMSR_FTM_REQ_ATTR_ASAP ];if (out->ftm.asap && !capa->ftm.asap) {
@@ -75,7 +75,7 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, out->ftm.num_bursts_exp =0 ;if (tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP ]) out->ftm.num_bursts_exp = -nla_get_u32 (tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP ]); +nla_get_u8 (tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP ]);if (capa->ftm.max_bursts_exponent >=0 && out->ftm.num_bursts_exp > capa->ftm.max_bursts_exponent) {
@@ -88,7 +88,7 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, out->ftm.burst_duration =15 ;if (tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION ]) out->ftm.burst_duration = -nla_get_u32 (tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION ]); +nla_get_u8 (tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION ]); out->ftm.ftms_per_burst =0 ;if (tb[NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST ])
@@ -107,7 +107,7 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, out->ftm.ftmr_retries =3 ;if (tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES ]) out->ftm.ftmr_retries = -nla_get_u32 (tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES ]); +nla_get_u8 (tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES ]); out->ftm.request_lci = !!tb[NL80211_PMSR_FTM_REQ_ATTR_REQUEST_LCI ];if (out->ftm.request_lci && !capa->ftm.request_lci) {
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 6/217 wifi: iwlwifi: mvm: revert gen2 TX A-MPDU size to 64
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Johannes Berg <[email protected]>
[ Upstream commit 4a7aace2899711592327463c1a29ffee44fcc66e ]
We don't actually support >64 even for HE devices, so revert back to 64. This fixes an issue where the session is refused because the queue is configured differently from the actual session later.
--- drivers/net/wireless/intel/iwlwifi/mvm/rs.h | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-)
drivers/net/wireless/intel/iwlwifi/mvm/rs.h +2 -7
@@ -123,13 +123,8 @@ enum {#define LINK_QUAL_AGG_FRAME_LIMIT_DEF (63)#define LINK_QUAL_AGG_FRAME_LIMIT_MAX (63) -/* -* FIXME - various places in firmware API still use u8, -* e.g. LQ command and SCD config command. -* This should be 256 instead. -*/ -#define LINK_QUAL_AGG_FRAME_LIMIT_GEN2_DEF (255) -#define LINK_QUAL_AGG_FRAME_LIMIT_GEN2_MAX (255) +#define LINK_QUAL_AGG_FRAME_LIMIT_GEN2_DEF (64) +#define LINK_QUAL_AGG_FRAME_LIMIT_GEN2_MAX (64)#define LINK_QUAL_AGG_FRAME_LIMIT_MIN (0)#define LQ_SIZE 2/* 2 mode tables: "Active" and "Search" */
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 7/217 wifi: iwlwifi: dbg_ini: move iwl_dbg_tlv_free outside of debugfs ifdef
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Shahar S Matityahu <[email protected]>
[ Upstream commit 87821b67dea87addbc4ab093ba752753b002176a ]
The driver should call iwl_dbg_tlv_free even if debugfs is not defined since ini mode does not depend on debugfs ifdef.
--- drivers/net/wireless/intel/iwlwifi/iwl-drv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/wireless/intel/iwlwifi/iwl-drv.c +1 -1
@@ -1750,8 +1750,8 @@ struct iwl_drv *iwl_drv_start(struct iwl_trans *trans) err_fw:#ifdef CONFIG_IWLWIFI_DEBUGFS debugfs_remove_recursive (drv->dbgfs_drv); -iwl_dbg_tlv_free (drv->trans);#endif +iwl_dbg_tlv_free (drv->trans);kfree (drv); err:return ERR_PTR (ret);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 8/217 wifi: iwlwifi: mvm: check n_ssids before accessing the ssids
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Miri Korenblit <[email protected]>
[ Upstream commit 60d62757df30b74bf397a2847a6db7385c6ee281 ]
In some versions of cfg80211, the ssids poinet might be a valid one even though n_ssids is 0. Accessing the pointer in this case will cuase an out-of-bound access. Fix this by checking n_ssids first.
--- drivers/net/wireless/intel/iwlwifi/mvm/scan.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/net/wireless/intel/iwlwifi/mvm/scan.c +2 -2
@@ -1298,7 +1298,7 @@ static void iwl_mvm_scan_umac_dwell(struct iwl_mvm *mvm,if (IWL_MVM_ADWELL_MAX_BUDGET ) cmd->v7.adwell_max_budget =cpu_to_le16 (IWL_MVM_ADWELL_MAX_BUDGET ); -else if (params->ssids && params->ssids[0 ].ssid_len) +else if (params->n_ssids && params->ssids[0 ].ssid_len) cmd->v7.adwell_max_budget =cpu_to_le16 (IWL_SCAN_ADWELL_MAX_BUDGET_DIRECTED_SCAN );else
@@ -1400,7 +1400,7 @@ iwl_mvm_scan_umac_dwell_v11(struct iwl_mvm *mvm,if (IWL_MVM_ADWELL_MAX_BUDGET ) general_params->adwell_max_budget =cpu_to_le16 (IWL_MVM_ADWELL_MAX_BUDGET ); -else if (params->ssids && params->ssids[0 ].ssid_len) +else if (params->n_ssids && params->ssids[0 ].ssid_len) general_params->adwell_max_budget =cpu_to_le16 (IWL_SCAN_ADWELL_MAX_BUDGET_DIRECTED_SCAN );else
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 9/217 wifi: iwlwifi: mvm: dont read past the mfuart notifcation
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Emmanuel Grumbach <[email protected]>
[ Upstream commit 4bb95f4535489ed830cf9b34b0a891e384d1aee4 ]
In case the firmware sends a notification that claims it has more data than it has, we will read past that was allocated for the notification. Remove the print of the buffer, we won't see it by default. If needed, we can see the content with tracing.
This was reported by KFENCE.
--- drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 10 ---------- 1 file changed, 10 deletions(-)
drivers/net/wireless/intel/iwlwifi/mvm/fw.c +0 -10
@@ -91,20 +91,10 @@ void iwl_mvm_mfu_assert_dump_notif(struct iwl_mvm *mvm, {struct iwl_rx_packet *pkt =rxb_addr (rxb);struct iwl_mfu_assert_dump_notif *mfu_dump_notif = (void *)pkt->data; -__le32 *dump_data = mfu_dump_notif->data; -int n_words =le32_to_cpu (mfu_dump_notif->data_size) /sizeof (__le32); -int i;if (mfu_dump_notif->index_num ==0 )IWL_INFO (mvm,"MFUART assert id 0x%x occurred\n" ,le32_to_cpu (mfu_dump_notif->assert_id)); - -for (i =0 ; i < n_words; i++) -IWL_DEBUG_INFO (mvm, -"MFUART assert dump, dword %u: 0x%08x\n" , -le16_to_cpu (mfu_dump_notif->index_num) * - n_words + i, -le32_to_cpu (dump_data[i])); } static bool iwl_alive_fn(struct iwl_notif_wait_data *notif_wait,
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainercover 6.1.95-rc1 review
This is the start of the stable review cycle for the 6.1.95 release. There are 217 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Fri, 21 Jun 2024 12:55:11 +0000. Anything received after that time might be too late.
The whole patch series can be found in one patch at:
https://www.kernel.org/pub/linux/kernel/v6.x/stable-review/patch-6.1.95-rc1.gz
or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-6.1.y
and the diffstat can be found below.
thanks,
greg k-h
-------------
Pseudo-Shortlog of commits:
Greg Kroah-Hartman <[email protected]>
Linux 6.1.95-rc1
Oleg Nesterov <[email protected]>
zap_pid_ns_processes: clear TIF_NOTIFY_SIGNAL along with TIF_SIGPENDING
Jean Delvare <[email protected]>
i2c: designware: Fix the functionality flags of the slave-only interface
Jean Delvare <[email protected]>
i2c: at91: Fix the functionality flags of the slave-only interface
Yongzhi Liu <[email protected]>
misc: microchip: pci1xxxx: Fix a memory leak in the error handling of gp_aux_bus_probe()
Shichao Lai <[email protected]>
usb-storage: alauda: Check whether the media is initialized
Andy Shevchenko <[email protected]>
serial: core: Add UPIO_UNKNOWN constant for unknown port type
Jisheng Zhang <[email protected]>
serial: 8250_dw: fall back to poll if there's no interrupt
Sicong Huang <[email protected]>
greybus: Fix use-after-free bug in gb_interface_release due to race condition.
Johan Hovold <[email protected]>
Bluetooth: qca: generalise device address check
Johan Hovold <[email protected]>
Bluetooth: qca: fix wcn3991 device address check
David Howells <[email protected]>
cachefiles, erofs: Fix NULL deref in when cachefiles is not doing ondemand-mode
Beleswar Padhi <[email protected]>
remoteproc: k3-r5: Jump to error handling labels in start/stop errors
Sam James <[email protected]>
Revert "fork: defer linking file vma until vma is fully initialized"
YonglongLi <[email protected]>
mptcp: pm: update add_addr counters after connect
Doug Brown <[email protected]>
serial: 8250_pxa: Configure tx_loadsz to match FIFO IRQ level
Miaohe Lin <[email protected]>
mm/memory-failure: fix handling of dissolved but not taken off from buddy pages
Miaohe Lin <[email protected]>
mm/huge_memory: don't unpoison huge_zero_folio
Oleg Nesterov <[email protected]>
tick/nohz_full: Don't abuse smp_call_function_single() in tick_setup_device()
Ryusuke Konishi <[email protected]>
nilfs2: fix potential kernel bug due to lack of writeback flag waiting
Filipe Manana <[email protected]>
btrfs: zoned: fix use-after-free due to race with dev replace
Christoph Hellwig <[email protected]>
btrfs: zoned: factor out DUP bg handling from btrfs_load_block_group_zone_info
Christoph Hellwig <[email protected]>
btrfs: zoned: factor out single bg handling from btrfs_load_block_group_zone_info
Christoph Hellwig <[email protected]>
btrfs: zoned: factor out per-zone logic from btrfs_load_block_group_zone_info
Christoph Hellwig <[email protected]>
btrfs: zoned: introduce a zone_info struct in btrfs_load_block_group_zone_info
Alexander Shishkin <[email protected]>
intel_th: pci: Add Lunar Lake support
Alexander Shishkin <[email protected]>
intel_th: pci: Add Meteor Lake-S support
Alexander Shishkin <[email protected]>
intel_th: pci: Add Sapphire Rapids SOC support
Alexander Shishkin <[email protected]>
intel_th: pci: Add Granite Rapids SOC support
Alexander Shishkin <[email protected]>
intel_th: pci: Add Granite Rapids support
Vidya Srinivas <[email protected]>
drm/i915/dpt: Make DPT object unshrinkable
Chris Wilson <[email protected]>
drm/i915/gt: Disarm breadcrumbs if engines are already idle
Nam Cao <[email protected]>
riscv: rewrite __kernel_map_pages() to fix sleeping in invalid context
Beleswar Padhi <[email protected]>
remoteproc: k3-r5: Do not allow core1 to power up before core0 via sysfs
Apurva Nandan <[email protected]>
remoteproc: k3-r5: Wait for core0 power-up before powering up core1
Nuno Sa <[email protected]>
dmaengine: axi-dmac: fix possible race in remove()
Rick Wertenbroek <[email protected]>
PCI: rockchip-ep: Remove wrong mask on subsys_vendor_id
Su Yue <[email protected]>
ocfs2: fix races between hole punching and AIO+DIO
Su Yue <[email protected]>
ocfs2: use coarse time for new created files
Rik van Riel <[email protected]>
fs/proc: fix softlockup in __read_vmcore
Trond Myklebust <[email protected]>
knfsd: LOOKUP can return an illegal error value
Vamshi Gajjela <[email protected]>
spmi: hisi-spmi-controller: Do not override device identifier
Hagar Gamal Halim Hemdan <[email protected]>
vmci: prevent speculation leaks by sanitizing event in event_deliver()
Thadeu Lima de Souza Cascardo <[email protected]>
sock_map: avoid race between sock_map_close and sk_psock_put
Damien Le Moal <[email protected]>
null_blk: Print correct max open zones limit in null_init_zoned_dev()
Steven Rostedt (Google) <[email protected]>
tracing/selftests: Fix kprobe event name test for .isra. functions
Nam Cao <[email protected]>
riscv: fix overlap of allocated page and PTR_ERR
Haifeng Xu <[email protected]>
perf/core: Fix missing wakeup when waiting for context reference
Yazen Ghannam <[email protected]>
x86/amd_nb: Check for invalid SMN reads
Hagar Hemdan <[email protected]>
irqchip/gic-v3-its: Fix potential race condition in its_vlpi_prop_update()
YonglongLi <[email protected]>
mptcp: pm: inc RmAddr MIB counter once per RM_ADDR ID
Paolo Abeni <[email protected]>
mptcp: ensure snd_una is properly initialized on connect
Marek Szyprowski <[email protected]>
drm/exynos: hdmi: report safe 640x480 mode as a fallback when no EDID found
Jani Nikula <[email protected]>
drm/exynos/vidi: fix memory leak in .get_modes()
Dirk Behme <[email protected]>
drivers: core: synchronize really_probe() and dev_uevent()
Jean-Baptiste Maneyrol <[email protected]>
iio: imu: inv_icm42600: delete unneeded update watermark call
Marc Ferland <[email protected]>
iio: dac: ad5592r: fix temperature channel scaling value
David Lechner <[email protected]>
iio: adc: ad9467: fix scan type sign
Benjamin Segall <[email protected]>
x86/boot: Don't add the EFI stub to targets, again
Yongzhi Liu <[email protected]>
misc: microchip: pci1xxxx: fix double free in the error handling of gp_aux_bus_probe()
Aleksandr Mishin <[email protected]>
bnxt_en: Adjust logging of firmware messages in case of released token in __hwrm_send()
Rao Shoaib <[email protected]>
af_unix: Read with MSG_PEEK loops if the first unread byte is OOB
Taehee Yoo <[email protected]>
ionic: fix use after netif_napi_del()
Nikolay Aleksandrov <[email protected]>
net: bridge: mst: fix suspicious rcu usage in br_mst_set_state
Nikolay Aleksandrov <[email protected]>
net: bridge: mst: pass vlan group directly to br_mst_vlan_set_state
Petr Pavlu <[email protected]>
net/ipv6: Fix the RT cache flush via sysctl using a previous delay
Daniel Wagner <[email protected]>
nvmet-passthru: propagate status from id override functions
Xiaolei Wang <[email protected]>
net: stmmac: replace priv->speed with the portTransmitRate from the tc-cbs parameters
Joshua Washington <[email protected]>
gve: ignore nonrelevant GSO type bits when processing TSO headers
Kory Maincent <[email protected]>
net: pse-pd: Use EOPNOTSUPP error code instead of ENOTSUPP
Jozsef Kadlecsik <[email protected]>
netfilter: ipset: Fix race between namespace cleanup and gc in the list:set type
Luiz Augusto von Dentz <[email protected]>
Bluetooth: L2CAP: Fix rejecting L2CAP_CONN_PARAM_UPDATE_REQ
Gal Pressman <[email protected]>
net/mlx5e: Fix features validation check for tunneled UDP (non-VXLAN) packets
Gal Pressman <[email protected]>
geneve: Fix incorrect inner network header offset when innerprotoinherit is set
Eric Dumazet <[email protected]>
tcp: fix race in tcp_v6_syn_recv_sock()
Adam Miotk <[email protected]>
drm/bridge/panel: Fix runtime warning on panel bridge release
Amjad Ouled-Ameur <[email protected]>
drm/komeda: check for error-valued pointer
Aleksandr Mishin <[email protected]>
liquidio: Adjust a NULL pointer handling path in lio_vf_rep_copy_packet
Jie Wang <[email protected]>
net: hns3: add cond_resched() to hns3 ring buffer init process
Yonglong Liu <[email protected]>
net: hns3: fix kernel crash problem in concurrent scenario
Csókás, Bence <[email protected]>
net: sfp: Always call sfp_sm_mod_remove() on remove
Ian Forbes <[email protected]>
drm/vmwgfx: Remove STDU logic from generic mode_valid function
Ian Forbes <[email protected]>
drm/vmwgfx: 3D disabled should not effect STDU memory limits
Ian Forbes <[email protected]>
drm/vmwgfx: Filter modes which exceed graphics memory
Martin Krastev <[email protected]>
drm/vmwgfx: Refactor drm connector probing for display modes
Zack Rusin <[email protected]>
drm/vmwgfx: Port the framebuffer code to drm fb helpers
José Expósito <[email protected]>
HID: logitech-dj: Fix memory leak in logi_dj_recv_switch_to_dj_mode()
Kun(llfl) <[email protected]>
iommu/amd: Fix sysfs leak in iommu init
Nikita Zhandarovich <[email protected]>
HID: core: remove unnecessary WARN_ON() in implement()
Matthias Schiffer <[email protected]>
gpio: tqmx86: fix broken IRQ_TYPE_EDGE_BOTH interrupt type
Matthias Schiffer <[email protected]>
gpio: tqmx86: store IRQ trigger type and unmask status separately
Linus Walleij <[email protected]>
gpio: tqmx86: Convert to immutable irq_chip
Matthias Schiffer <[email protected]>
gpio: tqmx86: introduce shadow register for GPIO output value
Andrei Coardos <[email protected]>
gpio: tqmx86: remove unneeded call to platform_set_drvdata()
Gregor Herburger <[email protected]>
gpio: tqmx86: fix typo in Kconfig label
Armin Wolf <[email protected]>
platform/x86: dell-smbios: Fix wrong token data in sysfs
NeilBrown <[email protected]>
NFS: add barriers when testing for NFS_FSDATA_BLOCKED
Chen Hanxiao <[email protected]>
SUNRPC: return proper error from gss_wrap_req_priv
Olga Kornievskaia <[email protected]>
NFSv4.1 enforce rootpath check in fs_location query
Samuel Holland <[email protected]>
clk: sifive: Do not register clkdevs for PRCI clocks
Masami Hiramatsu (Google) <[email protected]>
selftests/ftrace: Fix to check required event file
Baokun Li <[email protected]>
cachefiles: flush all requests after setting CACHEFILES_DEAD
Baokun Li <[email protected]>
cachefiles: defer exposing anon_fd until after copy_to_user() succeeds
Baokun Li <[email protected]>
cachefiles: never get a new anonymous fd if ondemand_id is valid
Baokun Li <[email protected]>
cachefiles: remove err_put_fd label in cachefiles_ondemand_daemon_read()
Baokun Li <[email protected]>
cachefiles: fix slab-use-after-free in cachefiles_ondemand_daemon_read()
Baokun Li <[email protected]>
cachefiles: fix slab-use-after-free in cachefiles_ondemand_get_fd()
Jia Zhu <[email protected]>
cachefiles: add restore command to recover inflight ondemand read requests
Baokun Li <[email protected]>
cachefiles: add spin_lock for cachefiles_ondemand_info
Jia Zhu <[email protected]>
cachefiles: resend an open request if the read request's object is closed
Jia Zhu <[email protected]>
cachefiles: extract ondemand info field from cachefiles_object
Jia Zhu <[email protected]>
cachefiles: introduce object ondemand state
Baokun Li <[email protected]>
cachefiles: remove requests from xarray during flushing requests
Baokun Li <[email protected]>
cachefiles: add output string to cachefiles_obj_[get|put]_ondemand_fd
Dave Jiang <[email protected]>
cxl/test: Add missing vmalloc.h for tools/testing/cxl/test/mem.c
Dmitry Torokhov <[email protected]>
Input: try trimming too long modalias strings
Michael Ellerman <[email protected]>
powerpc/uaccess: Fix build errors seen with GCC 13/14
Ziwei Xiao <[email protected]>
gve: Clear napi->skb before dev_kfree_skb_any()
Martin K. Petersen <[email protected]>
scsi: sd: Use READ(16) when reading block zero on large capacity disks
Breno Leitao <[email protected]>
scsi: mpt3sas: Avoid test/set_bit() operating in non-allocated memory
Damien Le Moal <[email protected]>
scsi: mpi3mr: Fix ATA NCQ priority support
Aapo Vienamo <[email protected]>
thunderbolt: debugfs: Fix margin debugfs node creation condition
Kuangyi Chiang <[email protected]>
xhci: Apply broken streams quirk to Etron EJ188 xHCI host
Hector Martin <[email protected]>
xhci: Handle TD clearing for multiple streams case
Kuangyi Chiang <[email protected]>
xhci: Apply reset resume quirk to Etron EJ188 xHCI host
Mathias Nyman <[email protected]>
xhci: Set correct transferred length for cancelled bulk transfers
Greg Kroah-Hartman <[email protected]>
jfs: xattr: fix buffer overflow for invalid xattr
Mickaël Salaün <[email protected]>
landlock: Fix d_parent walk
Ilpo Järvinen <[email protected]>
tty: n_tty: Fix buffer offsets when lookahead is used
Tomas Winkler <[email protected]>
mei: me: release irq in mei_me_pci_resume error path
Kyle Tso <[email protected]>
usb: typec: tcpm: Ignore received Hard Reset in TOGGLING state
Amit Sunil Dhamne <[email protected]>
usb: typec: tcpm: fix use-after-free case in tcpm_register_source_caps
John Ernberg <[email protected]>
USB: xen-hcd: Traverse host/ when CONFIG_USB_XEN_HCD is selected
Alan Stern <[email protected]>
USB: class: cdc-wdm: Fix CPU lockup caused by excessive log messages
Jens Axboe <[email protected]>
io_uring: check for non-NULL file pointer in io_file_can_poll()
Ryusuke Konishi <[email protected]>
nilfs2: fix nilfs_empty_dir() misjudgment and long loop on I/O errors
Matthew Wilcox (Oracle) <[email protected]>
nilfs2: return the mapped address from nilfs_get_page()
Filipe Manana <[email protected]>
btrfs: fix leak of qgroup extent records after transaction abort
Filipe Manana <[email protected]>
btrfs: make btrfs_destroy_delayed_refs() return void
Filipe Manana <[email protected]>
btrfs: remove unnecessary prototype declarations at disk-io.c
Dmitry Baryshkov <[email protected]>
wifi: ath10k: fix QCOM_RPROC_COMMON dependency
Dev Jain <[email protected]>
selftests/mm: compaction_test: fix bogus test success on Aarch64
Mark Brown <[email protected]>
selftests/mm: log a consistent test name for check_compaction
Muhammad Usama Anjum <[email protected]>
selftests/mm: conform test to TAP format output
Dev Jain <[email protected]>
selftests/mm: compaction_test: fix incorrect write of zero to nr_hugepages
Hailong.Liu <[email protected]>
mm/vmalloc: fix vmalloc which may return null if called with __GFP_NOFAIL
Michal Hocko <[email protected]>
mm, vmalloc: fix high order __GFP_NOFAIL allocations
Hamish Martin <[email protected]>
i2c: acpi: Unbind mux adapters before delete
Russell King (Oracle) <[email protected]>
i2c: add fwnode APIs
Johan Hovold <[email protected]>
HID: i2c-hid: elan: fix reset suspend current leakage
Cong Yang <[email protected]>
HID: i2c-hid: elan: Add ili9882t timing
Gabor Juhos <[email protected]>
firmware: qcom_scm: disable clocks if qcom_scm_bw_enable() fails
Uwe Kleine-König <[email protected]>
mmc: davinci: Don't strip remove function when driver is builtin
Hugo Villeneuve <[email protected]>
serial: sc16is7xx: fix bug in sc16is7xx_set_baud() when using prescaler
Hugo Villeneuve <[email protected]>
serial: sc16is7xx: replace hardcoded divisor value with BIT() macro
Thomas Weißschuh <[email protected]>
misc/pvpanic-pci: register attributes via pci_driver
Thomas Weißschuh <[email protected]>
misc/pvpanic: deduplicate common code
Volodymyr Babchuk <[email protected]>
arm64: dts: qcom: sa8155p-adp: fix SDHC2 CD pin configuration
Krzysztof Kozlowski <[email protected]>
arm64: dts: qcom: sm8150: align TLMM pin configuration with DT schema
Hersen Wu <[email protected]>
drm/amd/display: Fix incorrect DSC instance for MST
Alexey Kodanev <[email protected]>
drm/amd/display: drop unnecessary NULL checks in debugfs
Max Filippov <[email protected]>
xtensa: fix MAKE_PC_FROM_RA second argument
Randy Dunlap <[email protected]>
xtensa: stacktrace: include <asm/ftrace.h> for prototype
Hans de Goede <[email protected]>
iio: accel: mxc4005: Reset chip on probe() and resume()
Luca Ceresoli <[email protected]>
iio: accel: mxc4005: allow module autoloading via OF compatible
Wesley Cheng <[email protected]>
usb: gadget: f_fs: Fix race between aio_cancel() and AIO request complete
John Keeping <[email protected]>
usb: gadget: f_fs: use io_data->status consistently
Qu Wenruo <[email protected]>
btrfs: fix wrong block_start calculation for btrfs_drop_extent_map_range()
Johan Hovold <[email protected]>
Bluetooth: qca: fix invalid device address check
Eric Dumazet <[email protected]>
ipv6: fix possible race in __fib6_drop_pcpu_from()
Kuniyuki Iwashima <[email protected]>
af_unix: Annotate data-race of sk->sk_shutdown in sk_diag_fill().
Kuniyuki Iwashima <[email protected]>
af_unix: Use skb_queue_len_lockless() in sk_diag_show_rqlen().
Kuniyuki Iwashima <[email protected]>
af_unix: Use skb_queue_empty_lockless() in unix_release_sock().
Eric Dumazet <[email protected]>
af_unix: annotate lockless accesses to sk->sk_err
Kuniyuki Iwashima <[email protected]>
af_unix: Use unix_recvq_full_lockless() in unix_stream_connect().
Kuniyuki Iwashima <[email protected]>
af_unix: Annotate data-race of net->unx.sysctl_max_dgram_qlen.
Kuniyuki Iwashima <[email protected]>
af_unix: Annotate data-races around sk->sk_state in UNIX_DIAG.
Kuniyuki Iwashima <[email protected]>
af_unix: Annotate data-race of sk->sk_state in unix_stream_read_skb().
Kuniyuki Iwashima <[email protected]>
af_unix: Annotate data-races around sk->sk_state in sendmsg() and recvmsg().
Kuniyuki Iwashima <[email protected]>
af_unix: Annotate data-race of sk->sk_state in unix_stream_connect().
Kuniyuki Iwashima <[email protected]>
af_unix: Annotate data-races around sk->sk_state in unix_write_space() and poll().
Kuniyuki Iwashima <[email protected]>
af_unix: Annotate data-race of sk->sk_state in unix_inq_len().
Kuniyuki Iwashima <[email protected]>
af_unix: Annodate data-races around sk->sk_state for writers.
Kuniyuki Iwashima <[email protected]>
af_unix: Set sk->sk_state under unix_state_lock() for truly disconencted peer.
Aleksandr Mishin <[email protected]>
net: wwan: iosm: Fix tainted pointer delete is case of region creation fail
Larysa Zaremba <[email protected]>
ice: remove af_xdp_zc_qps bitmap
Przemek Kitszel <[email protected]>
ice: remove null checks before devm_kfree() calls
Michal Wilczynski <[email protected]>
ice: Introduce new parameters in ice_sched_node
Jacob Keller <[email protected]>
ice: fix iteration of TLVs in Preserved Fields Area
Karol Kolacinski <[email protected]>
ptp: Fix error message on failed pin verification
Eric Dumazet <[email protected]>
net/sched: taprio: always validate TCA_TAPRIO_ATTR_PRIOMAP
Aleksandr Mishin <[email protected]>
net/mlx5: Fix tainted pointer delete is case of flow rules creation fail
Shay Drory <[email protected]>
net/mlx5: Always stop health timer during driver removal
Shay Drory <[email protected]>
net/mlx5: Split function_setup() to enable and open functions
Moshe Shemesh <[email protected]>
net/mlx5: Stop waiting for PCI if pci channel is offline
Moshe Shemesh <[email protected]>
net/mlx5: Stop waiting for PCI up if teardown was triggered
Jason Xing <[email protected]>
tcp: count CLOSE-WAIT sockets for TCP_MIB_CURRESTAB
Daniel Borkmann <[email protected]>
vxlan: Fix regression when dropping packets due to invalid src addresses
Hangyu Hua <[email protected]>
net: sched: sch_multiq: fix possible OOB write in multiq_tune()
Wen Gu <[email protected]>
net/smc: avoid overwriting when adjusting sock bufsizes
Subbaraya Sundeep <[email protected]>
octeontx2-af: Always allocate PF entries from low prioriy zone
Jiri Olsa <[email protected]>
bpf: Set run context for rawtp test_run callback
Eric Dumazet <[email protected]>
ipv6: sr: block BH in seg6_output_core() and seg6_input_core()
Eric Dumazet <[email protected]>
ipv6: ioam: block BH from ioam6_output()
DelphineCCChiu <[email protected]>
net/ncsi: Fix the multi thread manner of NCSI driver
Peter Delevoryas <[email protected]>
net/ncsi: Simplify Kconfig/dts control flow
Duoming Zhou <[email protected]>
ax25: Replace kfree() in ax25_dev_free() with ax25_dev_put()
Lars Kellogg-Stedman <[email protected]>
ax25: Fix refcount imbalance on inbound connections
Lingbo Kong <[email protected]>
wifi: mac80211: correctly parse Spatial Reuse Parameter Set element
Emmanuel Grumbach <[email protected]>
wifi: iwlwifi: mvm: don't read past the mfuart notifcation
Miri Korenblit <[email protected]>
wifi: iwlwifi: mvm: check n_ssids before accessing the ssids
Shahar S Matityahu <[email protected]>
wifi: iwlwifi: dbg_ini: move iwl_dbg_tlv_free outside of debugfs ifdef
Johannes Berg <[email protected]>
wifi: iwlwifi: mvm: revert gen2 TX A-MPDU size to 64
Lin Ma <[email protected]>
wifi: cfg80211: pmsr: use correct nla_get_uX functions
Remi Pommarel <[email protected]>
wifi: cfg80211: Lock wiphy in cfg80211_get_station
Johannes Berg <[email protected]>
wifi: cfg80211: fully move wiphy work to unbound workqueue
Remi Pommarel <[email protected]>
wifi: mac80211: Fix deadlock in ieee80211_sta_ps_deliver_wakeup()
Nicolas Escande <[email protected]>
wifi: mac80211: mesh: Fix leak of mesh_preq_queue objects
-------------
Diffstat:
Makefile | 4 +- arch/arm64/boot/dts/qcom/sa8155p-adp.dts | 86 +-- .../boot/dts/qcom/sm8150-microsoft-surface-duo.dts | 2 +- arch/arm64/boot/dts/qcom/sm8150.dtsi | 376 ++++------ arch/powerpc/include/asm/uaccess.h | 15 +- arch/riscv/mm/init.c | 21 +- arch/riscv/mm/pageattr.c | 28 +- arch/x86/boot/compressed/Makefile | 4 +- arch/x86/kernel/amd_nb.c | 9 +- arch/xtensa/include/asm/processor.h | 8 +- arch/xtensa/include/asm/ptrace.h | 2 +- arch/xtensa/kernel/process.c | 5 +- arch/xtensa/kernel/stacktrace.c | 4 +- drivers/base/core.c | 3 + drivers/block/null_blk/zoned.c | 2 +- drivers/bluetooth/btqca.c | 46 +- drivers/bluetooth/btqca.h | 2 + drivers/bluetooth/hci_qca.c | 2 - drivers/clk/sifive/sifive-prci.c | 8 - drivers/dma/dma-axi-dmac.c | 2 +- drivers/firmware/qcom_scm.c | 18 +- drivers/gpio/Kconfig | 2 +- drivers/gpio/gpio-tqmx86.c | 136 +++- .../drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c | 120 ++- .../drm/arm/display/komeda/komeda_pipeline_state.c | 2 +- drivers/gpu/drm/bridge/panel.c | 7 +- drivers/gpu/drm/exynos/exynos_drm_vidi.c | 7 +- drivers/gpu/drm/exynos/exynos_hdmi.c | 7 +- drivers/gpu/drm/i915/gem/i915_gem_object.h | 4 +- drivers/gpu/drm/i915/gt/intel_breadcrumbs.c | 15 +- drivers/gpu/drm/vmwgfx/Kconfig | 7 - drivers/gpu/drm/vmwgfx/Makefile | 2 - drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 65 +- drivers/gpu/drm/vmwgfx/vmwgfx_drv.h | 38 +- drivers/gpu/drm/vmwgfx/vmwgfx_fb.c | 831 --------------------- drivers/gpu/drm/vmwgfx/vmwgfx_kms.c | 353 +++------ drivers/gpu/drm/vmwgfx/vmwgfx_kms.h | 13 +- drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c | 5 +- drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c | 5 +- drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c | 47 +- drivers/greybus/interface.c | 1 + drivers/hid/hid-core.c | 1 - drivers/hid/hid-logitech-dj.c | 4 +- drivers/hid/i2c-hid/i2c-hid-of-elan.c | 103 ++- drivers/hwtracing/intel_th/pci.c | 25 + drivers/i2c/busses/i2c-at91-slave.c | 3 +- drivers/i2c/busses/i2c-designware-slave.c | 2 +- drivers/i2c/i2c-core-acpi.c | 30 +- drivers/i2c/i2c-core-base.c | 98 +++ drivers/i2c/i2c-core-of.c | 66 -- drivers/iio/accel/mxc4005.c | 76 ++ drivers/iio/adc/ad9467.c | 4 +- drivers/iio/dac/ad5592r-base.c | 2 +- drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c | 4 - drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c | 4 - drivers/input/input.c | 104 ++- drivers/iommu/amd/init.c | 9 + drivers/irqchip/irq-gic-v3-its.c | 44 +- drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gp.c | 9 +- drivers/misc/mei/pci-me.c | 4 +- drivers/misc/pvpanic/pvpanic-mmio.c | 58 +- drivers/misc/pvpanic/pvpanic-pci.c | 60 +- drivers/misc/pvpanic/pvpanic.c | 76 +- drivers/misc/pvpanic/pvpanic.h | 10 +- drivers/misc/vmw_vmci/vmci_event.c | 6 +- drivers/mmc/host/davinci_mmc.c | 4 +- drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c | 2 +- drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c | 11 +- drivers/net/ethernet/google/gve/gve_rx_dqo.c | 8 +- drivers/net/ethernet/google/gve/gve_tx_dqo.c | 20 +- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 4 + drivers/net/ethernet/hisilicon/hns3/hns3_enet.h | 2 + .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 21 +- drivers/net/ethernet/intel/ice/ice.h | 32 +- drivers/net/ethernet/intel/ice/ice_adminq_cmd.h | 4 +- drivers/net/ethernet/intel/ice/ice_common.c | 9 +- drivers/net/ethernet/intel/ice/ice_controlq.c | 3 +- drivers/net/ethernet/intel/ice/ice_flow.c | 23 +- drivers/net/ethernet/intel/ice/ice_lib.c | 46 +- drivers/net/ethernet/intel/ice/ice_nvm.c | 28 +- drivers/net/ethernet/intel/ice/ice_sched.c | 90 ++- drivers/net/ethernet/intel/ice/ice_sched.h | 27 + drivers/net/ethernet/intel/ice/ice_switch.c | 19 +- drivers/net/ethernet/intel/ice/ice_type.h | 8 + drivers/net/ethernet/intel/ice/ice_xsk.c | 13 +- .../net/ethernet/marvell/octeontx2/af/rvu_npc.c | 33 +- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 3 +- drivers/net/ethernet/mellanox/mlx5/core/fw.c | 4 + drivers/net/ethernet/mellanox/mlx5/core/health.c | 12 + .../net/ethernet/mellanox/mlx5/core/lag/port_sel.c | 8 +- .../net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c | 4 + drivers/net/ethernet/mellanox/mlx5/core/main.c | 116 ++- drivers/net/ethernet/pensando/ionic/ionic_lif.c | 4 +- drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c | 25 +- drivers/net/geneve.c | 10 +- drivers/net/phy/sfp.c | 3 +- drivers/net/vxlan/vxlan_core.c | 4 + drivers/net/wireless/ath/ath10k/Kconfig | 1 + drivers/net/wireless/intel/iwlwifi/iwl-drv.c | 2 +- drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 10 - drivers/net/wireless/intel/iwlwifi/mvm/rs.h | 9 +- drivers/net/wireless/intel/iwlwifi/mvm/scan.c | 4 +- drivers/net/wwan/iosm/iosm_ipc_devlink.c | 2 +- drivers/nvme/target/passthru.c | 6 +- drivers/pci/controller/pcie-rockchip-ep.c | 6 +- drivers/platform/x86/dell/dell-smbios-base.c | 92 +-- drivers/ptp/ptp_chardev.c | 3 +- drivers/remoteproc/ti_k3_r5_remoteproc.c | 58 +- drivers/scsi/mpi3mr/mpi3mr_app.c | 62 ++ drivers/scsi/mpt3sas/mpt3sas_base.c | 19 + drivers/scsi/mpt3sas/mpt3sas_base.h | 3 - drivers/scsi/mpt3sas/mpt3sas_ctl.c | 4 +- drivers/scsi/mpt3sas/mpt3sas_scsih.c | 23 - drivers/scsi/scsi_transport_sas.c | 23 + drivers/scsi/sd.c | 17 +- drivers/spmi/hisi-spmi-controller.c | 1 - drivers/thunderbolt/debugfs.c | 5 +- drivers/tty/n_tty.c | 22 +- drivers/tty/serial/8250/8250_dw.c | 5 +- drivers/tty/serial/8250/8250_pxa.c | 1 + drivers/tty/serial/sc16is7xx.c | 25 +- drivers/usb/Makefile | 1 + drivers/usb/class/cdc-wdm.c | 4 +- drivers/usb/gadget/function/f_fs.c | 9 +- drivers/usb/host/xhci-pci.c | 7 + drivers/usb/host/xhci-ring.c | 59 +- drivers/usb/host/xhci.h | 1 + drivers/usb/storage/alauda.c | 9 +- drivers/usb/typec/tcpm/tcpm.c | 5 +- fs/btrfs/disk-io.c | 26 +- fs/btrfs/extent_map.c | 2 +- fs/btrfs/zoned.c | 330 ++++---- fs/cachefiles/daemon.c | 4 +- fs/cachefiles/interface.c | 7 +- fs/cachefiles/internal.h | 52 +- fs/cachefiles/ondemand.c | 324 ++++++-- fs/jfs/xattr.c | 4 +- fs/nfs/dir.c | 47 +- fs/nfs/nfs4proc.c | 23 +- fs/nfsd/nfsfh.c | 4 +- fs/nilfs2/dir.c | 59 +- fs/nilfs2/segment.c | 3 + fs/ocfs2/file.c | 2 + fs/ocfs2/namei.c | 2 +- fs/proc/vmcore.c | 2 + include/linux/i2c.h | 26 +- include/linux/pse-pd/pse.h | 4 +- include/linux/serial_core.h | 1 + include/net/bluetooth/hci_core.h | 36 +- include/net/ip_tunnels.h | 5 +- include/scsi/scsi_transport_sas.h | 2 + include/trace/events/cachefiles.h | 8 +- io_uring/kbuf.c | 3 +- kernel/events/core.c | 13 + kernel/fork.c | 18 +- kernel/pid_namespace.c | 1 + kernel/time/tick-common.c | 42 +- mm/memory-failure.c | 11 +- mm/vmalloc.c | 29 +- net/ax25/af_ax25.c | 6 + net/ax25/ax25_dev.c | 2 +- net/bluetooth/l2cap_core.c | 8 +- net/bpf/test_run.c | 6 + net/bridge/br_mst.c | 13 +- net/core/sock_map.c | 16 +- net/ipv4/tcp.c | 6 +- net/ipv6/ioam6_iptunnel.c | 8 +- net/ipv6/ip6_fib.c | 6 +- net/ipv6/route.c | 5 +- net/ipv6/seg6_iptunnel.c | 14 +- net/ipv6/tcp_ipv6.c | 3 +- net/mac80211/he.c | 10 +- net/mac80211/mesh_pathtbl.c | 13 + net/mac80211/sta_info.c | 4 +- net/mptcp/pm_netlink.c | 21 +- net/mptcp/protocol.c | 1 + net/ncsi/internal.h | 2 + net/ncsi/ncsi-manage.c | 95 +-- net/ncsi/ncsi-rsp.c | 4 +- net/netfilter/ipset/ip_set_core.c | 93 ++- net/netfilter/ipset/ip_set_list_set.c | 30 +- net/sched/sch_multiq.c | 2 +- net/sched/sch_taprio.c | 15 +- net/smc/af_smc.c | 22 +- net/sunrpc/auth_gss/auth_gss.c | 4 +- net/unix/af_unix.c | 109 ++- net/unix/diag.c | 12 +- net/wireless/core.c | 2 +- net/wireless/pmsr.c | 8 +- net/wireless/sysfs.c | 4 +- net/wireless/util.c | 7 +- security/landlock/fs.c | 13 +- tools/testing/cxl/test/mem.c | 1 + .../ftrace/test.d/dynevent/test_duplicates.tc | 2 +- .../ftrace/test.d/kprobe/kprobe_eventname.tc | 3 +- tools/testing/selftests/net/mptcp/mptcp_join.sh | 5 +- tools/testing/selftests/vm/compaction_test.c | 108 +-- 197 files changed, 2950 insertions(+), 3037 deletions(-)
Greg Kroah-Hartman
maintainerPATCH 33/217 ice: remove af_xdp_zc_qps bitmap
6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Larysa Zaremba <[email protected]>
[ Upstream commit adbf5a42341f6ea038d3626cd4437d9f0ad0b2dd ]
Referenced commit has introduced a bitmap to distinguish between ZC and copy-mode AF_XDP queues, because xsk_get_pool_from_qid() does not do this for us.
The bitmap would be especially useful when restoring previous state after rebuild, if only it was not reallocated in the process. This leads to e.g. xdpsock dying after changing number of queues.
Instead of preserving the bitmap during the rebuild, remove it completely and distinguish between ZC and copy-mode queues based on the presence of a device associated with the pool.
--- drivers/net/ethernet/intel/ice/ice.h | 32 ++++++++++++++++-------- drivers/net/ethernet/intel/ice/ice_lib.c | 8 ------ drivers/net/ethernet/intel/ice/ice_xsk.c | 13 +++++----- 3 files changed, 27 insertions(+), 26 deletions(-)
drivers/net/ethernet/intel/ice/ice.h +21 -11
@@ -388,7 +388,6 @@ struct ice_vsi {struct ice_tc_cfg tc_cfg;struct bpf_prog *xdp_prog;struct ice_tx_ring **xdp_rings;/* XDP ring array */ -unsigned long *af_xdp_zc_qps;/* tracks AF_XDP ZC enabled qps */ u16 num_xdp_txq;/* Used XDP queues */ u8 xdp_mapping_mode;/* ICE_MAP_MODE_[CONTIG|SCATTER] */
@@ -688,6 +687,25 @@ static inline void ice_set_ring_xdp(struct ice_tx_ring *ring) ring->flags |=ICE_TX_FLAGS_RING_XDP ; } +/** +* ice_get_xp_from_qid - get ZC XSK buffer pool bound to a queue ID +* @vsi: pointer to VSI +* @qid: index of a queue to look at XSK buff pool presence +* +* Return: A pointer to xsk_buff_pool structure if there is a buffer pool +* attached and configured as zero-copy, NULL otherwise. +*/ +static inline struct xsk_buff_pool *ice_get_xp_from_qid (struct ice_vsi *vsi, +u16 qid) +{ +struct xsk_buff_pool *pool =xsk_get_pool_from_qid (vsi->netdev, qid); + +if (!ice_is_xdp_ena_vsi (vsi)) +return NULL ; + +return (pool && pool->dev) ? pool :NULL ; +} +/** * ice_xsk_pool - get XSK buffer pool bound to a ring * @ring: Rx ring to use
@@ -700,10 +718,7 @@ static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_rx_ring *ring)struct ice_vsi *vsi = ring->vsi;u16 qid = ring->q_index; -if (!ice_is_xdp_ena_vsi (vsi) || !test_bit (qid, vsi->af_xdp_zc_qps)) -return NULL ; - -return xsk_get_pool_from_qid (vsi->netdev, qid); +return ice_get_xp_from_qid (vsi, qid); }/**
@@ -728,12 +743,7 @@ static inline void ice_tx_xsk_pool(struct ice_vsi *vsi, u16 qid)if (!ring)return ; -if (!ice_is_xdp_ena_vsi (vsi) || !test_bit (qid, vsi->af_xdp_zc_qps)) { - ring->xsk_pool =NULL ; -return ; - } - - ring->xsk_pool =xsk_get_pool_from_qid (vsi->netdev, qid); + ring->xsk_pool =ice_get_xp_from_qid (vsi, qid); }/**
drivers/net/ethernet/intel/ice/ice_lib.c +0 -8
@@ -117,14 +117,8 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi)if (!vsi->q_vectors) goto err_vectors; - vsi->af_xdp_zc_qps =bitmap_zalloc (max_t (int, vsi->alloc_txq, vsi->alloc_rxq),GFP_KERNEL ); -if (!vsi->af_xdp_zc_qps) - goto err_zc_qps; -return 0 ; -err_zc_qps: -devm_kfree (dev, vsi->q_vectors); err_vectors:devm_kfree (dev, vsi->rxq_map); err_rxq_map:
@@ -320,8 +314,6 @@ static void ice_vsi_free_arrays(struct ice_vsi *vsi) dev =ice_pf_to_dev (pf); -bitmap_free (vsi->af_xdp_zc_qps); - vsi->af_xdp_zc_qps =NULL ;/* free the ring and vector containers */ devm_kfree (dev, vsi->q_vectors); vsi->q_vectors =NULL ;
drivers/net/ethernet/intel/ice/ice_xsk.c +6 -7
@@ -281,7 +281,6 @@ static int ice_xsk_pool_disable(struct ice_vsi *vsi, u16 qid)if (!pool)return -EINVAL ; -clear_bit (qid, vsi->af_xdp_zc_qps);xsk_pool_dma_unmap (pool,ICE_RX_DMA_ATTR );return 0 ;
@@ -312,8 +311,6 @@ ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)if (err)return err; -set_bit (qid, vsi->af_xdp_zc_qps); -return 0 ; }
@@ -361,11 +358,13 @@ ice_realloc_rx_xdp_bufs(struct ice_rx_ring *rx_ring, bool pool_present)int ice_realloc_zc_buf (struct ice_vsi *vsi,bool zc) {struct ice_rx_ring *rx_ring; -unsigned long q; +uint i; + +ice_for_each_rxq (vsi, i) { + rx_ring = vsi->rx_rings[i]; +if (!rx_ring->xsk_pool) +continue ; -for_each_set_bit (q, vsi->af_xdp_zc_qps, -max_t (int, vsi->alloc_txq, vsi->alloc_rxq)) { - rx_ring = vsi->rx_rings[q];if (ice_realloc_rx_xdp_bufs (rx_ring, zc))return -ENOMEM ; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 42/217 af_unix: Annotate data-races around sk->sk_state in UNIX_DIAG.
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kuniyuki Iwashima <[email protected]>
[ Upstream commit 0aa3be7b3e1f8f997312cc4705f8165e02806f8f ]
While dumping AF_UNIX sockets via UNIX_DIAG, sk->sk_state is read locklessly.
Let's use READ_ONCE() there.
Note that the result could be inconsistent if the socket is dumped during the state change. This is common for other SOCK_DIAG and similar interfaces.
--- net/unix/diag.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
net/unix/diag.c +4 -4
@@ -65,7 +65,7 @@ static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb)u32 *buf;int i; -if (sk->sk_state ==TCP_LISTEN ) { +if (READ_ONCE (sk->sk_state) ==TCP_LISTEN ) {spin_lock (&sk->sk_receive_queue.lock); attr = nla_reserve(nlskb, UNIX_DIAG_ICONS,
@@ -103,7 +103,7 @@ static int sk_diag_show_rqlen(struct sock *sk, struct sk_buff *nlskb) {struct unix_diag_rqlen rql; -if (sk->sk_state ==TCP_LISTEN ) { +if (READ_ONCE (sk->sk_state) ==TCP_LISTEN ) { rql.udiag_rqueue = sk->sk_receive_queue.qlen; rql.udiag_wqueue = sk->sk_max_ack_backlog; }else {
@@ -136,7 +136,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r rep =nlmsg_data (nlh); rep->udiag_family =AF_UNIX ; rep->udiag_type = sk->sk_type; - rep->udiag_state = sk->sk_state; + rep->udiag_state =READ_ONCE (sk->sk_state); rep->pad =0 ; rep->udiag_ino = sk_ino;sock_diag_save_cookie (sk, rep->udiag_cookie);
@@ -215,7 +215,7 @@ static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)sk_for_each (sk, &net->unx.table.buckets[slot]) {if (num < s_num) goto next; -if (!(req->udiag_states & (1 << sk->sk_state))) +if (!(req->udiag_states & (1 <<READ_ONCE (sk->sk_state)))) goto next; if (sk_diag_dump(sk, skb, req, sk_user_ns(skb->sk), NETLINK_CB(cb->skb).portid,
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 43/217 af_unix: Annotate data-race of net->unx.sysctl_max_dgram_qlen.
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kuniyuki Iwashima <[email protected]>
[ Upstream commit bd9f2d05731f6a112d0c7391a0d537bfc588dbe6 ]
net->unx.sysctl_max_dgram_qlen is exposed as a sysctl knob and can be changed concurrently.
Let's use READ_ONCE() in unix_create1().
--- net/unix/af_unix.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/unix/af_unix.c +1 -1
@@ -966,7 +966,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern, sk->sk_hash =unix_unbound_hash (sk); sk->sk_allocation =GFP_KERNEL_ACCOUNT ; sk->sk_write_space = unix_write_space; - sk->sk_max_ack_backlog = net->unx.sysctl_max_dgram_qlen; + sk->sk_max_ack_backlog =READ_ONCE (net->unx.sysctl_max_dgram_qlen); sk->sk_destruct = unix_sock_destructor; u =unix_sk (sk); u->inflight =0 ;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 44/217 af_unix: Use unix_recvq_full_lockless() in unix_stream_connect().
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kuniyuki Iwashima <[email protected]>
[ Upstream commit 45d872f0e65593176d880ec148f41ad7c02e40a7 ]
Once sk->sk_state is changed to TCP_LISTEN, it never changes.
unix_accept() takes advantage of this characteristics; it does not hold the listener's unix_state_lock() and only acquires recvq lock to pop one skb.
It means unix_state_lock() does not prevent the queue length from changing in unix_stream_connect().
Thus, we need to use unix_recvq_full_lockless() to avoid data-race.
Now we remove unix_recvq_full() as no one uses it.
Note that we can remove READ_ONCE() for sk->sk_max_ack_backlog in unix_recvq_full_lockless() because of the following reasons:
(1) For SOCK_DGRAM, it is a written-once field in unix_create1()
(2) For SOCK_STREAM and SOCK_SEQPACKET, it is changed under the listener's unix_state_lock() in unix_listen(), and we hold the lock in unix_stream_connect()
--- net/unix/af_unix.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-)
net/unix/af_unix.c +2 -8
@@ -221,15 +221,9 @@ static inline int unix_may_send(struct sock *sk, struct sock *osk)return unix_peer (osk) ==NULL ||unix_our_peer (sk, osk); } -static inline int unix_recvq_full (const struct sock *sk) -{ -return skb_queue_len (&sk->sk_receive_queue) > sk->sk_max_ack_backlog; -} -static inline int unix_recvq_full_lockless (const struct sock *sk) { -return skb_queue_len_lockless (&sk->sk_receive_queue) > -READ_ONCE (sk->sk_max_ack_backlog); +return skb_queue_len_lockless (&sk->sk_receive_queue) > sk->sk_max_ack_backlog; }struct sock *unix_peer_get (struct sock *s)
@@ -1527,7 +1521,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,if (other->sk_shutdown &RCV_SHUTDOWN ) goto out_unlock; -if (unix_recvq_full (other)) { +if (unix_recvq_full_lockless (other)) { err = -EAGAIN ;if (!timeo) goto out_unlock;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 45/217 af_unix: annotate lockless accesses to sk->sk_err
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Eric Dumazet <[email protected]>
[ Upstream commit cc04410af7de348234ac36a5f50c4ce416efdb4b ]
unix_poll() and unix_dgram_poll() read sk->sk_err
without any lock held.
Add relevant READ_ONCE()/WRITE_ONCE() annotations.
Stable-dep-of: 83690b82d228 ("af_unix: Use skb_queue_empty_lockless() in unix_release_sock().")
--- net/unix/af_unix.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)
net/unix/af_unix.c +5 -4
@@ -548,7 +548,7 @@ static void unix_dgram_disconnected(struct sock *sk, struct sock *other)* when peer was not connected to us. */ if (!sock_flag (other,SOCK_DEAD ) &&unix_peer (other) == sk) { - other->sk_err =ECONNRESET ; +WRITE_ONCE (other->sk_err,ECONNRESET );sk_error_report (other); } }
@@ -620,7 +620,7 @@ static void unix_release_sock(struct sock *sk, int embrion)/* No more writes */ WRITE_ONCE (skpair->sk_shutdown,SHUTDOWN_MASK );if (!skb_queue_empty (&sk->sk_receive_queue) || embrion) - skpair->sk_err =ECONNRESET ; +WRITE_ONCE (skpair->sk_err,ECONNRESET );unix_state_unlock (skpair); skpair->sk_state_change (skpair);sk_wake_async (skpair,SOCK_WAKE_WAITD ,POLL_HUP );
@@ -3181,7 +3181,7 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa state =READ_ONCE (sk->sk_state);/* exceptional events? */ -if (sk->sk_err) +if (READ_ONCE (sk->sk_err)) mask |=EPOLLERR ;if (shutdown ==SHUTDOWN_MASK ) mask |=EPOLLHUP ;
@@ -3228,7 +3228,8 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, state =READ_ONCE (sk->sk_state);/* exceptional events? */ -if (sk->sk_err || !skb_queue_empty_lockless (&sk->sk_error_queue)) +if (READ_ONCE (sk->sk_err) || + !skb_queue_empty_lockless (&sk->sk_error_queue)) mask |=EPOLLERR | (sock_flag (sk,SOCK_SELECT_ERR_QUEUE ) ?EPOLLPRI :0 );
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 46/217 af_unix: Use skb_queue_empty_lockless() in unix_release_sock().
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kuniyuki Iwashima <[email protected]>
[ Upstream commit 83690b82d228b3570565ebd0b41873933238b97f ]
If the socket type is SOCK_STREAM or SOCK_SEQPACKET, unix_release_sock() checks the length of the peer socket's recvq under unix_state_lock().
However, unix_stream_read_generic() calls skb_unlink() after releasing the lock. Also, for SOCK_SEQPACKET, __skb_try_recv_datagram() unlinks skb without unix_state_lock().
Thues, unix_state_lock() does not protect qlen.
Let's use skb_queue_empty_lockless() in unix_release_sock().
--- net/unix/af_unix.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/unix/af_unix.c +1 -1
@@ -619,7 +619,7 @@ static void unix_release_sock(struct sock *sk, int embrion)unix_state_lock (skpair);/* No more writes */ WRITE_ONCE (skpair->sk_shutdown,SHUTDOWN_MASK ); -if (!skb_queue_empty (&sk->sk_receive_queue) || embrion) +if (!skb_queue_empty_lockless (&sk->sk_receive_queue) || embrion)WRITE_ONCE (skpair->sk_err,ECONNRESET );unix_state_unlock (skpair); skpair->sk_state_change (skpair);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 47/217 af_unix: Use skb_queue_len_lockless() in sk_diag_show_rqlen().
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kuniyuki Iwashima <[email protected]>
[ Upstream commit 5d915e584d8408211d4567c22685aae8820bfc55 ]
We can dump the socket queue length via UNIX_DIAG by specifying UDIAG_SHOW_RQLEN.
If sk->sk_state is TCP_LISTEN, we return the recv queue length, but here we do not hold recvq lock.
Let's use skb_queue_len_lockless() in sk_diag_show_rqlen().
--- net/unix/diag.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/unix/diag.c +1 -1
@@ -104,7 +104,7 @@ static int sk_diag_show_rqlen(struct sock *sk, struct sk_buff *nlskb)struct unix_diag_rqlen rql;if (READ_ONCE (sk->sk_state) ==TCP_LISTEN ) { - rql.udiag_rqueue = sk->sk_receive_queue.qlen; + rql.udiag_rqueue =skb_queue_len_lockless (&sk->sk_receive_queue); rql.udiag_wqueue = sk->sk_max_ack_backlog; }else { rql.udiag_rqueue = (u32 )unix_inq_len (sk);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 48/217 af_unix: Annotate data-race of sk->sk_shutdown in sk_diag_fill().
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kuniyuki Iwashima <[email protected]>
[ Upstream commit efaf24e30ec39ebbea9112227485805a48b0ceb1 ]
While dumping sockets via UNIX_DIAG, we do not hold unix_state_lock().
Let's use READ_ONCE() to read sk->sk_shutdown.
--- net/unix/diag.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/unix/diag.c +1 -1
@@ -165,7 +165,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r sock_diag_put_meminfo(sk, skb, UNIX_DIAG_MEMINFO)) goto out_nlmsg_trim; -if (nla_put_u8 (skb,UNIX_DIAG_SHUTDOWN , sk->sk_shutdown)) +if (nla_put_u8 (skb,UNIX_DIAG_SHUTDOWN ,READ_ONCE (sk->sk_shutdown))) goto out_nlmsg_trim; if ((req->udiag_show & UDIAG_SHOW_UID) &&
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 49/217 ipv6: fix possible race in __fib6_drop_pcpu_from()
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Eric Dumazet <[email protected]>
[ Upstream commit b01e1c030770ff3b4fe37fc7cc6bca03f594133f ]
syzbot found a race in __fib6_drop_pcpu_from() [1]
If compiler reads more than once (*ppcpu_rt), second read could read NULL, if another cpu clears the value in rt6_get_pcpu_route().
Add a READ_ONCE() to prevent this race.
Also add rcu_read_lock()/rcu_read_unlock() because we rely on RCU protection while dereferencing pcpu_rt.
[1]
Oops: general protection fault, probably for non-canonical address 0xdffffc0000000012: 0000 [#1] PREEMPT SMP KASAN PTI KASAN: null-ptr-deref in range [0x0000000000000090-0x0000000000000097] CPU: 0 PID: 7543 Comm: kworker/u8:17 Not tainted 6.10.0-rc1-syzkaller-00013-g2bfcfd584ff5 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/02/2024 Workqueue: netns cleanup_net RIP: 0010:__fib6_drop_pcpu_from.part.0+0x10a/0x370 net/ipv6/ip6_fib.c:984 Code: f8 48 c1 e8 03 80 3c 28 00 0f 85 16 02 00 00 4d 8b 3f 4d 85 ff 74 31 e8 74 a7 fa f7 49 8d bf 90 00 00 00 48 89 f8 48 c1 e8 03 <80> 3c 28 00 0f 85 1e 02 00 00 49 8b 87 90 00 00 00 48 8b 0c 24 48 RSP: 0018:ffffc900040df070 EFLAGS: 00010206 RAX: 0000000000000012 RBX: 0000000000000001 RCX: ffffffff89932e16 RDX: ffff888049dd1e00 RSI: ffffffff89932d7c RDI: 0000000000000091 RBP: dffffc0000000000 R08: 0000000000000005 R09: 0000000000000007 R10: 0000000000000001 R11: 0000000000000006 R12: ffff88807fa080b8 R13: fffffbfff1a9a07d R14: ffffed100ff41022 R15: 0000000000000001 FS: 0000000000000000(0000) GS:ffff8880b9200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000001b32c26000 CR3: 000000005d56e000 CR4: 00000000003526f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> __fib6_drop_pcpu_from net/ipv6/ip6_fib.c:966 [inline] fib6_drop_pcpu_from net/ipv6/ip6_fib.c:1027 [inline] fib6_purge_rt+0x7f2/0x9f0 net/ipv6/ip6_fib.c:1038 fib6_del_route net/ipv6/ip6_fib.c:1998 [inline] fib6_del+0xa70/0x17b0 net/ipv6/ip6_fib.c:2043 fib6_clean_node+0x426/0x5b0 net/ipv6/ip6_fib.c:2205 fib6_walk_continue+0x44f/0x8d0 net/ipv6/ip6_fib.c:2127 fib6_walk+0x182/0x370 net/ipv6/ip6_fib.c:2175 fib6_clean_tree+0xd7/0x120 net/ipv6/ip6_fib.c:2255 __fib6_clean_all+0x100/0x2d0 net/ipv6/ip6_fib.c:2271 rt6_sync_down_dev net/ipv6/route.c:4906 [inline] rt6_disable_ip+0x7ed/0xa00 net/ipv6/route.c:4911 addrconf_ifdown.isra.0+0x117/0x1b40 net/ipv6/addrconf.c:3855 addrconf_notify+0x223/0x19e0 net/ipv6/addrconf.c:3778 notifier_call_chain+0xb9/0x410 kernel/notifier.c:93 call_netdevice_notifiers_info+0xbe/0x140 net/core/dev.c:1992 call_netdevice_notifiers_extack net/core/dev.c:2030 [inline] call_netdevice_notifiers net/core/dev.c:2044 [inline] dev_close_many+0x333/0x6a0 net/core/dev.c:1585 unregister_netdevice_many_notify+0x46d/0x19f0 net/core/dev.c:11193 unregister_netdevice_many net/core/dev.c:11276 [inline] default_device_exit_batch+0x85b/0xae0 net/core/dev.c:11759 ops_exit_list+0x128/0x180 net/core/net_namespace.c:178 cleanup_net+0x5b7/0xbf0 net/core/net_namespace.c:640 process_one_work+0x9fb/0x1b60 kernel/workqueue.c:3231 process_scheduled_works kernel/workqueue.c:3312 [inline] worker_thread+0x6c8/0xf70 kernel/workqueue.c:3393 kthread+0x2c1/0x3a0 kernel/kthread.c:389 ret_from_fork+0x45/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244
--- net/ipv6/ip6_fib.c | 6 +++++- net/ipv6/route.c | 1 + 2 files changed, 6 insertions(+), 1 deletion(-)
net/ipv6/ip6_fib.c +5 -1
@@ -962,6 +962,7 @@ static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh,if (!fib6_nh->rt6i_pcpu)return ; +rcu_read_lock ();/* release the reference to this fib entry from * all of its cached pcpu routes */
@@ -970,7 +971,9 @@ static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh,struct rt6_info *pcpu_rt; ppcpu_rt =per_cpu_ptr (fib6_nh->rt6i_pcpu, cpu); - pcpu_rt = *ppcpu_rt; + +/* Paired with xchg() in rt6_get_pcpu_route() */ + pcpu_rt =READ_ONCE (*ppcpu_rt);/* only dropping the 'from' reference if the cached route * is using 'match'. The cached pcpu_rt->from only changes
@@ -984,6 +987,7 @@ static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh,fib6_info_release (from); } } +rcu_read_unlock (); }struct fib6_nh_pcpu_arg {
net/ipv6/route.c +1 -0
@@ -1401,6 +1401,7 @@ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res)struct rt6_info *prev, **p; p =this_cpu_ptr (res->nh->rt6i_pcpu); +/* Paired with READ_ONCE() in __fib6_drop_pcpu_from() */ prev =xchg (p,NULL );if (prev) {dst_dev_put (&prev->dst);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 50/217 Bluetooth: qca: fix invalid device address check
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Johan Hovold <[email protected]>
[ Upstream commit 32868e126c78876a8a5ddfcb6ac8cb2fffcf4d27 ]
Qualcomm Bluetooth controllers may not have been provisioned with a valid device address and instead end up using the default address 00:00:00:00:5a:ad.
This was previously believed to be due to lack of persistent storage for the address but it may also be due to integrators opting to not use the on-chip OTP memory and instead store the address elsewhere (e.g. in storage managed by secure world firmware).
According to Qualcomm, at least WCN6750, WCN6855 and WCN7850 have on-chip OTP storage for the address.
As the device type alone cannot be used to determine when the address is valid, instead read back the address during setup() and only set the HCI_QUIRK_USE_BDADDR_PROPERTY flag when needed.
This specifically makes sure that controllers that have been provisioned with an address do not start as unconfigured.
--- drivers/bluetooth/btqca.c | 38 +++++++++++++++++++++++++++++++++++++ drivers/bluetooth/hci_qca.c | 2 -- 2 files changed, 38 insertions(+), 2 deletions(-)
drivers/bluetooth/btqca.c +38 -0
@@ -15,6 +15,8 @@#define VERSION "0.1" +#define QCA_BDADDR_DEFAULT (&(bdaddr_t) {{ 0xad, 0x5a, 0x00, 0x00, 0x00, 0x00 }}) +int qca_read_soc_version (struct hci_dev *hdev,struct qca_btsoc_version *ver,enum qca_btsoc_type soc_type) {
@@ -682,6 +684,38 @@ int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr) }EXPORT_SYMBOL_GPL (qca_set_bdaddr_rome); +static int qca_check_bdaddr (struct hci_dev *hdev) +{ +struct hci_rp_read_bd_addr *bda; +struct sk_buff *skb; +int err; + +if (bacmp (&hdev->public_addr,BDADDR_ANY )) +return 0 ; + + skb =__hci_cmd_sync (hdev,HCI_OP_READ_BD_ADDR ,0 ,NULL , +HCI_INIT_TIMEOUT ); +if (IS_ERR (skb)) { + err =PTR_ERR (skb); +bt_dev_err (hdev,"Failed to read device address (%d)" , err); +return err; + } + +if (skb->len !=sizeof (*bda)) { +bt_dev_err (hdev,"Device address length mismatch" ); +kfree_skb (skb); +return -EIO ; + } + + bda = (struct hci_rp_read_bd_addr *)skb->data; +if (!bacmp (&bda->bdaddr,QCA_BDADDR_DEFAULT )) +set_bit (HCI_QUIRK_USE_BDADDR_PROPERTY , &hdev->quirks); + +kfree_skb (skb); + +return 0 ; +} +static void qca_generate_hsp_nvm_name (char *fwname,size_t max_size,struct qca_btsoc_version ver,u8 rom_ver,u16 bid) {
@@ -888,6 +922,10 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,break ; } + err =qca_check_bdaddr (hdev); +if (err) +return err; +bt_dev_info (hdev,"QCA setup on UART is completed" );return 0 ;
drivers/bluetooth/hci_qca.c +0 -2
@@ -1853,8 +1853,6 @@ static int qca_setup(struct hci_uart *hu)case QCA_WCN6750 :case QCA_WCN6855 :case QCA_WCN7850 : -set_bit (HCI_QUIRK_USE_BDADDR_PROPERTY , &hdev->quirks); - qcadev =serdev_device_get_drvdata (hu->serdev);if (qcadev->bdaddr_property_broken)set_bit (HCI_QUIRK_BDADDR_PROPERTY_BROKEN , &hdev->quirks);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 51/217 btrfs: fix wrong block_start calculation for btrfs_drop_extent_map_range()
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Qu Wenruo <[email protected]>
[ Upstream commit fe1c6c7acce10baf9521d6dccc17268d91ee2305 ]
[BUG]
During my extent_map cleanup/refactor, with extra sanity checks, extent-map-tests::test_case_7() would not pass the checks.
The problem is, after btrfs_drop_extent_map_range(), the resulted extent_map has a @block_start way too large.
Meanwhile my btrfs_file_extent_item based members are returning a correct @disk_bytenr/@offset combination.
The extent map layout looks like this:
0 16K 32K 48K
| PINNED | | Regular |The regular em at [32K, 48K) also has 32K @block_start.
Then drop range [0, 36K), which should shrink the regular one to be [36K, 48K).
However the @block_start is incorrect, we expect 32K + 4K, but got 52K.
[CAUSE]
Inside btrfs_drop_extent_map_range() function, if we hit an extent_map that covers the target range but is still beyond it, we need to split that extent map into half:
|<-- drop range -->| |<----- existing extent_map --->|
And if the extent map is not compressed, we need to forward extent_map::block_start by the difference between the end of drop range and the extent map start.
However in that particular case, the difference is calculated using (start + len - em->start).
The problem is @start can be modified if the drop range covers any pinned extent.
This leads to wrong calculation, and would be caught by my later extent_map sanity checks, which checks the em::block_start against btrfs_file_extent_item::disk_bytenr + btrfs_file_extent_item::offset.
This is a regression caused by commit c962098ca4af ("btrfs: fix incorrect splitting in btrfs_drop_extent_map_range"), which removed the @len update for pinned extents.
[FIX]
Fix it by avoiding using @start completely, and use @end - em->start instead, which @end is exclusive bytenr number.
And update the test case to verify the @block_start to prevent such problem from happening.
Thankfully this is not going to lead to any data corruption, as IO path does not utilize btrfs_drop_extent_map_range() with @skip_pinned set.
So this fix is only here for the sake of consistency/correctness.
--- fs/btrfs/extent_map.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
fs/btrfs/extent_map.c +1 -1
@@ -867,7 +867,7 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end, split->block_len = em->block_len; split->orig_start = em->orig_start; }else { -const u64 diff = start + len - em->start; +const u64 diff = end - em->start; split->block_len = split->len; split->block_start += diff;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 34/217 net: wwan: iosm: Fix tainted pointer delete is case of region creation fail
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Aleksandr Mishin <[email protected]>
[ Upstream commit b0c9a26435413b81799047a7be53255640432547 ]
In case of region creation fail in ipc_devlink_create_region(), previously created regions delete process starts from tainted pointer which actually holds error code value.
Fix this bug by decreasing region index before delete.
Found by Linux Verification Center (linuxtesting.org) with SVACE.
--- drivers/net/wwan/iosm/iosm_ipc_devlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/wwan/iosm/iosm_ipc_devlink.c +1 -1
@@ -210,7 +210,7 @@ static int ipc_devlink_create_region(struct iosm_devlink *devlink) rc =PTR_ERR (devlink->cd_regions[i]);dev_err (devlink->dev,"Devlink region fail,err %d" , rc);/* Delete previously created regions */ -for ( ; i >=0 ; i--) +for (i--; i >=0 ; i--)devlink_region_destroy (devlink->cd_regions[i]); goto region_create_fail; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 52/217 usb: gadget: f_fs: use io_data->status consistently
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: John Keeping <[email protected]>
[ Upstream commit b566d38857fcb6777f25b674b90a831eec0817a2 ]
Commit fb1f16d74e26 ("usb: gadget: f_fs: change ep->status safe in ffs_epfile_io()") added a new ffs_io_data::status field to fix lifetime issues in synchronous requests.
While there are no similar lifetime issues for asynchronous requests (the separate ep member in ffs_io_data avoids them) using the status field means the USB request can be freed earlier and that there is more consistency between the synchronous and asynchronous I/O paths.
Stable-dep-of: 24729b307eef ("usb: gadget: f_fs: Fix race between aio_cancel() and AIO request complete")
--- drivers/usb/gadget/function/f_fs.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
drivers/usb/gadget/function/f_fs.c +4 -4
@@ -830,8 +830,7 @@ static void ffs_user_copy_worker(struct work_struct *work) { struct ffs_io_data *io_data = container_of(work, struct ffs_io_data, work); -int ret = io_data->req->status ? io_data->req->status : - io_data->req->actual; +int ret = io_data->status;bool kiocb_has_eventfd = io_data->kiocb->ki_flags &IOCB_EVENTFD ;if (io_data->read && ret >0 ) {
@@ -845,8 +844,6 @@ static void ffs_user_copy_worker(struct work_struct *work)if (io_data->ffs->ffs_eventfd && !kiocb_has_eventfd)eventfd_signal (io_data->ffs->ffs_eventfd,1 ); -usb_ep_free_request (io_data->ep, io_data->req); -if (io_data->read)kfree (io_data->to_free);ffs_free_buffer (io_data);
@@ -861,6 +858,9 @@ static void ffs_epfile_async_io_complete(struct usb_ep *_ep,ENTER (); + io_data->status = req->status ? req->status : req->actual; +usb_ep_free_request (_ep, req); +INIT_WORK (&io_data->work, ffs_user_copy_worker);queue_work (ffs->io_completion_wq, &io_data->work); }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 53/217 usb: gadget: f_fs: Fix race between aio_cancel() and AIO request complete
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Wesley Cheng <[email protected]>
[ Upstream commit 24729b307eefcd7c476065cd7351c1a018082c19 ]
FFS based applications can utilize the aio_cancel() callback to dequeue pending USB requests submitted to the UDC. There is a scenario where the FFS application issues an AIO cancel call, while the UDC is handling a soft disconnect. For a DWC3 based implementation, the callstack looks like the following:
DWC3 Gadget FFS Applicationdwc3_gadget_soft_disconnect() ...
--> dwc3_stop_active_transfers()
--> dwc3_gadget_giveback(-ESHUTDOWN)
--> ffs_epfile_async_io_complete() ffs_aio_cancel()
--> usb_ep_free_request() --> usb_ep_dequeue()There is currently no locking implemented between the AIO completion handler and AIO cancel, so the issue occurs if the completion routine is running in parallel to an AIO cancel call coming from the FFS application. As the completion call frees the USB request (io_data->req) the FFS application is also referencing it for the usb_ep_dequeue() call. This can lead to accessing a stale/hanging pointer.
commit b566d38857fc ("usb: gadget: f_fs: use io_data->status consistently") relocated the usb_ep_free_request() into ffs_epfile_async_io_complete(). However, in order to properly implement locking to mitigate this issue, the spinlock can't be added to ffs_epfile_async_io_complete(), as usb_ep_dequeue() (if successfully dequeuing a USB request) will call the function driver's completion handler in the same context. Hence, leading into a deadlock.
Fix this issue by moving the usb_ep_free_request() back to ffs_user_copy_worker(), and ensuring that it explicitly sets io_data->req to NULL after freeing it within the ffs->eps_lock. This resolves the race condition above, as the ffs_aio_cancel() routine will not continue attempting to dequeue a request that has already been freed, or the ffs_user_copy_work() not freeing the USB request until the AIO cancel is done referencing it.
This fix depends on
commit b566d38857fc ("usb: gadget: f_fs: use io_data->status consistently")
--- drivers/usb/gadget/function/f_fs.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)
drivers/usb/gadget/function/f_fs.c +6 -1
@@ -832,6 +832,7 @@ static void ffs_user_copy_worker(struct work_struct *work) work);int ret = io_data->status;bool kiocb_has_eventfd = io_data->kiocb->ki_flags &IOCB_EVENTFD ; +unsigned long flags;if (io_data->read && ret >0 ) {kthread_use_mm (io_data->mm);
@@ -844,6 +845,11 @@ static void ffs_user_copy_worker(struct work_struct *work)if (io_data->ffs->ffs_eventfd && !kiocb_has_eventfd)eventfd_signal (io_data->ffs->ffs_eventfd,1 ); +spin_lock_irqsave (&io_data->ffs->eps_lock, flags); +usb_ep_free_request (io_data->ep, io_data->req); + io_data->req =NULL ; +spin_unlock_irqrestore (&io_data->ffs->eps_lock, flags); +if (io_data->read)kfree (io_data->to_free);ffs_free_buffer (io_data);
@@ -859,7 +865,6 @@ static void ffs_epfile_async_io_complete(struct usb_ep *_ep,ENTER (); io_data->status = req->status ? req->status : req->actual; -usb_ep_free_request (_ep, req);INIT_WORK (&io_data->work, ffs_user_copy_worker);queue_work (ffs->io_completion_wq, &io_data->work);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 54/217 iio: accel: mxc4005: allow module autoloading via OF compatible
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Luca Ceresoli <[email protected]>
[ Upstream commit 4d7c16d08d248952c116f2eb9b7b5abc43a19688 ]
Add OF device table with compatible strings to allow automatic module loading.
Stable-dep-of: 6b8cffdc4a31 ("iio: accel: mxc4005: Reset chip on probe() and resume()")
--- drivers/iio/accel/mxc4005.c | 8 ++++++++ 1 file changed, 8 insertions(+)
drivers/iio/accel/mxc4005.c +8 -0
@@ -487,6 +487,13 @@ static const struct acpi_device_id mxc4005_acpi_match[] = { };MODULE_DEVICE_TABLE (acpi, mxc4005_acpi_match); +static const struct of_device_id mxc4005_of_match[] = { + { .compatible ="memsic,mxc4005" , }, + { .compatible ="memsic,mxc6655" , }, + { }, +}; +MODULE_DEVICE_TABLE (of, mxc4005_of_match); +static const struct i2c_device_id mxc4005_id[] = { {"mxc4005" ,0 }, {"mxc6655" ,0 },
@@ -498,6 +505,7 @@ static struct i2c_driver mxc4005_driver = { .driver = { .name = MXC4005_DRV_NAME, .acpi_match_table = ACPI_PTR(mxc4005_acpi_match), + .of_match_table = mxc4005_of_match, }, .probe = mxc4005_probe, .id_table = mxc4005_id,
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 55/217 iio: accel: mxc4005: Reset chip on probe() and resume()
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Hans de Goede <[email protected]>
[ Upstream commit 6b8cffdc4a31e4a72f75ecd1bc13fbf0dafee390 ]
On some designs the chip is not properly reset when powered up at boot or after a suspend/resume cycle.
Use the sw-reset feature to ensure that the chip is in a clean state after probe() / resume() and in the case of resume() restore the settings (scale, trigger-enabled).
--- drivers/iio/accel/mxc4005.c | 68 +++++++++++++++++++++++++++++++++++++ 1 file changed, 68 insertions(+)
drivers/iio/accel/mxc4005.c +68 -0
@@ -5,6 +5,7 @@* Copyright (c) 2014, Intel Corporation. */ +#include <linux/delay.h> #include <linux/module.h> #include <linux/i2c.h> #include <linux/iio/iio.h>
@@ -36,6 +37,7 @@#define MXC4005_REG_INT_CLR1 0x01#define MXC4005_REG_INT_CLR1_BIT_DRDYC 0x01 +#define MXC4005_REG_INT_CLR1_SW_RST 0x10#define MXC4005_REG_CONTROL 0x0D#define MXC4005_REG_CONTROL_MASK_FSR GENMASK(6, 5)
@@ -43,6 +45,9 @@#define MXC4005_REG_DEVICE_ID 0x0E +/* Datasheet does not specify a reset time, this is a conservative guess */ +#define MXC4005_RESET_TIME_US 2000 +enum mxc4005_axis {AXIS_X ,AXIS_Y ,
@@ -66,6 +71,8 @@ struct mxc4005_data {s64 timestamp__aligned(8) ; } scan;bool trigger_enabled; +unsigned int control; +unsigned int int_mask1; };/*
@@ -349,6 +356,7 @@ static int mxc4005_set_trigger_state(struct iio_trigger *trig,return ret; } + data->int_mask1 = val; data->trigger_enabled = state;mutex_unlock (&data->mutex);
@@ -384,6 +392,13 @@ static int mxc4005_chip_init(struct mxc4005_data *data)dev_dbg (data->dev,"MXC4005 chip id %02x\n" , reg); + ret =regmap_write (data->regmap,MXC4005_REG_INT_CLR1 , +MXC4005_REG_INT_CLR1_SW_RST ); +if (ret <0 ) +return dev_err_probe (data->dev, ret,"resetting chip\n" ); + +fsleep (MXC4005_RESET_TIME_US ); + ret =regmap_write (data->regmap,MXC4005_REG_INT_MASK0 ,0 );if (ret <0 )return dev_err_probe (data->dev, ret,"writing INT_MASK0\n" );
@@ -480,6 +495,58 @@ static int mxc4005_probe(struct i2c_client *client,return devm_iio_device_register (&client->dev, indio_dev); } +static int mxc4005_suspend (struct device *dev) +{ +struct iio_dev *indio_dev =dev_get_drvdata (dev); +struct mxc4005_data *data =iio_priv (indio_dev); +int ret; + +/* Save control to restore it on resume */ + ret =regmap_read (data->regmap,MXC4005_REG_CONTROL , &data->control); +if (ret <0 ) +dev_err (data->dev,"failed to read reg_control\n" ); + +return ret; +} + +static int mxc4005_resume (struct device *dev) +{ +struct iio_dev *indio_dev =dev_get_drvdata (dev); +struct mxc4005_data *data =iio_priv (indio_dev); +int ret; + + ret =regmap_write (data->regmap,MXC4005_REG_INT_CLR1 , +MXC4005_REG_INT_CLR1_SW_RST ); +if (ret) { +dev_err (data->dev,"failed to reset chip: %d\n" , ret); +return ret; + } + +fsleep (MXC4005_RESET_TIME_US ); + + ret =regmap_write (data->regmap,MXC4005_REG_CONTROL , data->control); +if (ret) { +dev_err (data->dev,"failed to restore control register\n" ); +return ret; + } + + ret =regmap_write (data->regmap,MXC4005_REG_INT_MASK0 ,0 ); +if (ret) { +dev_err (data->dev,"failed to restore interrupt 0 mask\n" ); +return ret; + } + + ret =regmap_write (data->regmap,MXC4005_REG_INT_MASK1 , data->int_mask1); +if (ret) { +dev_err (data->dev,"failed to restore interrupt 1 mask\n" ); +return ret; + } + +return 0 ; +} + +static DEFINE_SIMPLE_DEV_PM_OPS(mxc4005_pm_ops, mxc4005_suspend, mxc4005_resume); +static const struct acpi_device_id mxc4005_acpi_match[] = { {"MXC4005" ,0 }, {"MXC6655" ,0 },
@@ -506,6 +573,7 @@ static struct i2c_driver mxc4005_driver = { .name = MXC4005_DRV_NAME, .acpi_match_table = ACPI_PTR(mxc4005_acpi_match), .of_match_table = mxc4005_of_match, + .pm = pm_sleep_ptr(&mxc4005_pm_ops), }, .probe = mxc4005_probe, .id_table = mxc4005_id,
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 56/217 xtensa: stacktrace: include <asm/ftrace.h> for prototype
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Randy Dunlap <[email protected]>
[ Upstream commit 1b6ceeb99ee05eb2c62a9e5512623e63cf8490ba ]
Use <asm/ftrace.h> to prevent a build warning:
arch/xtensa/kernel/stacktrace.c:263:15: warning: no previous prototype for 'return_address' [-Wmissing-prototypes]
263 | unsigned long return_address(unsigned level)
Message-Id: <[email protected]>
Stable-dep-of: 0e60f0b75884 ("xtensa: fix MAKE_PC_FROM_RA second argument")
--- arch/xtensa/kernel/stacktrace.c | 1 + 1 file changed, 1 insertion(+)
arch/xtensa/kernel/stacktrace.c +1 -0
@@ -12,6 +12,7 @@#include <linux/sched.h> #include <linux/stacktrace.h> +#include <asm/ftrace.h> #include <asm/stacktrace.h> #include <asm/traps.h> #include <linux/uaccess.h>
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 57/217 xtensa: fix MAKE_PC_FROM_RA second argument
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Max Filippov <[email protected]>
[ Upstream commit 0e60f0b75884677fb9f4f2ad40d52b43451564d5 ]
Xtensa has two-argument MAKE_PC_FROM_RA macro to convert a0 to an actual return address because when windowed ABI is used call{,x}{4,8,12} opcodes stuff encoded window size into the top 2 bits of the register that becomes a return address in the called function. Second argument of that macro is supposed to be an address having these 2 topmost bits set correctly, but the comment suggested that that could be the stack address. However the stack doesn't have to be in the same 1GByte region as the code, especially in noMMU XIP configurations.
Fix the comment and use either _text or regs->pc as the second argument for the MAKE_PC_FROM_RA macro.
--- arch/xtensa/include/asm/processor.h | 8 ++++---- arch/xtensa/include/asm/ptrace.h | 2 +- arch/xtensa/kernel/process.c | 5 +++-- arch/xtensa/kernel/stacktrace.c | 3 ++- 4 files changed, 10 insertions(+), 8 deletions(-)
arch/xtensa/include/asm/processor.h +4 -4
@@ -113,9 +113,9 @@#define MAKE_RA_FOR_CALL (ra,ws) (((ra) & 0x3fffffff) | (ws) << 30)/* Convert return address to a valid pc -* Note: We assume that the stack pointer is in the same 1GB ranges as the ra +* Note: 'text' is the address within the same 1GB range as the ra */ -#define MAKE_PC_FROM_RA (ra,sp) (((ra) & 0x3fffffff) | ((sp) & 0xc0000000)) +#define MAKE_PC_FROM_RA (ra, text) (((ra) & 0x3fffffff) | ((unsigned long)(text) & 0xc0000000))#elif defined(__XTENSA_CALL0_ABI__)
@@ -125,9 +125,9 @@#define MAKE_RA_FOR_CALL (ra, ws) (ra)/* Convert return address to a valid pc -* Note: We assume that the stack pointer is in the same 1GB ranges as the ra +* Note: 'text' is not used as 'ra' is always the full address */ -#define MAKE_PC_FROM_RA (ra, sp) (ra) +#define MAKE_PC_FROM_RA (ra, text) (ra)#else #error Unsupported Xtensa ABI
arch/xtensa/include/asm/ptrace.h +1 -1
@@ -87,7 +87,7 @@ struct pt_regs {# define user_mode (regs) (((regs)->ps & 0x00000020)!=0)# define instruction_pointer (regs) ((regs)->pc)# define return_pointer (regs) (MAKE_PC_FROM_RA((regs)->areg[0], \ - (regs)->areg[1])) + (regs)->pc))# ifndef CONFIG_SMP # define profile_pc (regs) instruction_pointer(regs)
arch/xtensa/kernel/process.c +3 -2
@@ -47,6 +47,7 @@#include <asm/asm-offsets.h> #include <asm/regs.h> #include <asm/hw_breakpoint.h> +#include <asm/sections.h> #include <asm/traps.h> extern void ret_from_fork (void );
@@ -379,7 +380,7 @@ unsigned long __get_wchan(struct task_struct *p)int count =0 ; sp = p->thread.sp; - pc =MAKE_PC_FROM_RA (p->thread.ra, p->thread.sp); + pc =MAKE_PC_FROM_RA (p->thread.ra, _text); do { if (sp < stack_page + sizeof(struct task_struct) ||
@@ -391,7 +392,7 @@ unsigned long __get_wchan(struct task_struct *p)/* Stack layout: sp-4: ra, sp-3: sp' */ - pc =MAKE_PC_FROM_RA (SPILL_SLOT (sp,0 ), sp); + pc =MAKE_PC_FROM_RA (SPILL_SLOT (sp,0 ), _text); sp =SPILL_SLOT (sp,1 ); }while (count++ <16 );return 0 ;
arch/xtensa/kernel/stacktrace.c +2 -1
@@ -13,6 +13,7 @@#include <linux/stacktrace.h> #include <asm/ftrace.h> +#include <asm/sections.h> #include <asm/stacktrace.h> #include <asm/traps.h> #include <linux/uaccess.h>
@@ -189,7 +190,7 @@ void walk_stackframe(unsigned long *sp,if (a1 <= (unsigned long )sp)break ; - frame.pc =MAKE_PC_FROM_RA (a0, a1); + frame.pc =MAKE_PC_FROM_RA (a0, _text); frame.sp = a1;if (fn (&frame, data))
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 58/217 drm/amd/display: drop unnecessary NULL checks in debugfs
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Alexey Kodanev <[email protected]>
[ Upstream commit f8e12e770e8049917f82387033b3cf44bc43b915 ]
pipe_ctx pointer cannot be NULL when getting the address of an element of the pipe_ctx array. Moreover, the MAX_PIPES is defined as 6, so pipe_ctx is not NULL after the loop either.
Detected using the static analysis tool - Svace.
Stable-dep-of: 892b41b16f61 ("drm/amd/display: Fix incorrect DSC instance for MST")
--- .../amd/display/amdgpu_dm/amdgpu_dm_debugfs.c | 72 +++++-------------- 1 file changed, 16 insertions(+), 56 deletions(-)
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c +16 -56
@@ -1369,16 +1369,11 @@ static ssize_t dp_dsc_clock_en_read(struct file *f, char __user *buf,for (i =0 ; i <MAX_PIPES ; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; -if (pipe_ctx && pipe_ctx->stream && +if (pipe_ctx->stream && pipe_ctx->stream->link == aconnector->dc_link)break ; } -if (!pipe_ctx) { -kfree (rd_buf); -return -ENXIO ; - } - dsc = pipe_ctx->stream_res.dsc;if (dsc) dsc->funcs->dsc_read_state (dsc, &dsc_state);
@@ -1475,12 +1470,12 @@ static ssize_t dp_dsc_clock_en_write(struct file *f, const char __user *buf,for (i =0 ; i <MAX_PIPES ; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; -if (pipe_ctx && pipe_ctx->stream && +if (pipe_ctx->stream && pipe_ctx->stream->link == aconnector->dc_link)break ; } -if (!pipe_ctx || !pipe_ctx->stream) +if (!pipe_ctx->stream) goto done;// Get CRTC state
@@ -1560,16 +1555,11 @@ static ssize_t dp_dsc_slice_width_read(struct file *f, char __user *buf,for (i =0 ; i <MAX_PIPES ; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; -if (pipe_ctx && pipe_ctx->stream && +if (pipe_ctx->stream && pipe_ctx->stream->link == aconnector->dc_link)break ; } -if (!pipe_ctx) { -kfree (rd_buf); -return -ENXIO ; - } - dsc = pipe_ctx->stream_res.dsc;if (dsc) dsc->funcs->dsc_read_state (dsc, &dsc_state);
@@ -1664,12 +1654,12 @@ static ssize_t dp_dsc_slice_width_write(struct file *f, const char __user *buf,for (i =0 ; i <MAX_PIPES ; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; -if (pipe_ctx && pipe_ctx->stream && +if (pipe_ctx->stream && pipe_ctx->stream->link == aconnector->dc_link)break ; } -if (!pipe_ctx || !pipe_ctx->stream) +if (!pipe_ctx->stream) goto done;// Safely get CRTC state
@@ -1749,16 +1739,11 @@ static ssize_t dp_dsc_slice_height_read(struct file *f, char __user *buf,for (i =0 ; i <MAX_PIPES ; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; -if (pipe_ctx && pipe_ctx->stream && +if (pipe_ctx->stream && pipe_ctx->stream->link == aconnector->dc_link)break ; } -if (!pipe_ctx) { -kfree (rd_buf); -return -ENXIO ; - } - dsc = pipe_ctx->stream_res.dsc;if (dsc) dsc->funcs->dsc_read_state (dsc, &dsc_state);
@@ -1853,12 +1838,12 @@ static ssize_t dp_dsc_slice_height_write(struct file *f, const char __user *buf,for (i =0 ; i <MAX_PIPES ; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; -if (pipe_ctx && pipe_ctx->stream && +if (pipe_ctx->stream && pipe_ctx->stream->link == aconnector->dc_link)break ; } -if (!pipe_ctx || !pipe_ctx->stream) +if (!pipe_ctx->stream) goto done;// Get CRTC state
@@ -1934,16 +1919,11 @@ static ssize_t dp_dsc_bits_per_pixel_read(struct file *f, char __user *buf,for (i =0 ; i <MAX_PIPES ; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; -if (pipe_ctx && pipe_ctx->stream && +if (pipe_ctx->stream && pipe_ctx->stream->link == aconnector->dc_link)break ; } -if (!pipe_ctx) { -kfree (rd_buf); -return -ENXIO ; - } - dsc = pipe_ctx->stream_res.dsc;if (dsc) dsc->funcs->dsc_read_state (dsc, &dsc_state);
@@ -2035,12 +2015,12 @@ static ssize_t dp_dsc_bits_per_pixel_write(struct file *f, const char __user *bufor (i =0 ; i <MAX_PIPES ; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; -if (pipe_ctx && pipe_ctx->stream && +if (pipe_ctx->stream && pipe_ctx->stream->link == aconnector->dc_link)break ; } -if (!pipe_ctx || !pipe_ctx->stream) +if (!pipe_ctx->stream) goto done;// Get CRTC state
@@ -2114,16 +2094,11 @@ static ssize_t dp_dsc_pic_width_read(struct file *f, char __user *buf,for (i =0 ; i <MAX_PIPES ; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; -if (pipe_ctx && pipe_ctx->stream && +if (pipe_ctx->stream && pipe_ctx->stream->link == aconnector->dc_link)break ; } -if (!pipe_ctx) { -kfree (rd_buf); -return -ENXIO ; - } - dsc = pipe_ctx->stream_res.dsc;if (dsc) dsc->funcs->dsc_read_state (dsc, &dsc_state);
@@ -2175,16 +2150,11 @@ static ssize_t dp_dsc_pic_height_read(struct file *f, char __user *buf,for (i =0 ; i <MAX_PIPES ; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; -if (pipe_ctx && pipe_ctx->stream && +if (pipe_ctx->stream && pipe_ctx->stream->link == aconnector->dc_link)break ; } -if (!pipe_ctx) { -kfree (rd_buf); -return -ENXIO ; - } - dsc = pipe_ctx->stream_res.dsc;if (dsc) dsc->funcs->dsc_read_state (dsc, &dsc_state);
@@ -2251,16 +2221,11 @@ static ssize_t dp_dsc_chunk_size_read(struct file *f, char __user *buf,for (i =0 ; i <MAX_PIPES ; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; -if (pipe_ctx && pipe_ctx->stream && +if (pipe_ctx->stream && pipe_ctx->stream->link == aconnector->dc_link)break ; } -if (!pipe_ctx) { -kfree (rd_buf); -return -ENXIO ; - } - dsc = pipe_ctx->stream_res.dsc;if (dsc) dsc->funcs->dsc_read_state (dsc, &dsc_state);
@@ -2327,16 +2292,11 @@ static ssize_t dp_dsc_slice_bpg_offset_read(struct file *f, char __user *buf,for (i =0 ; i <MAX_PIPES ; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i]; -if (pipe_ctx && pipe_ctx->stream && +if (pipe_ctx->stream && pipe_ctx->stream->link == aconnector->dc_link)break ; } -if (!pipe_ctx) { -kfree (rd_buf); -return -ENXIO ; - } - dsc = pipe_ctx->stream_res.dsc;if (dsc) dsc->funcs->dsc_read_state (dsc, &dsc_state);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 59/217 drm/amd/display: Fix incorrect DSC instance for MST
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Hersen Wu <[email protected]>
[ Upstream commit 892b41b16f6163e6556545835abba668fcab4eea ]
[Why] DSC debugfs, such as dp_dsc_clock_en_read, use aconnector->dc_link to find pipe_ctx for display. Displays connected to MST hub share the same dc_link. DSC instance is from pipe_ctx. This causes incorrect DSC instance for display connected to MST hub.
[How] Add aconnector->sink check to find pipe_ctx.
--- .../amd/display/amdgpu_dm/amdgpu_dm_debugfs.c | 48 ++++++++++++++----- 1 file changed, 36 insertions(+), 12 deletions(-)
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c +36 -12
@@ -1370,7 +1370,9 @@ static ssize_t dp_dsc_clock_en_read(struct file *f, char __user *buf,for (i =0 ; i <MAX_PIPES ; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink)break ; }
@@ -1471,7 +1473,9 @@ static ssize_t dp_dsc_clock_en_write(struct file *f, const char __user *buf,for (i =0 ; i <MAX_PIPES ; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink)break ; }
@@ -1556,7 +1560,9 @@ static ssize_t dp_dsc_slice_width_read(struct file *f, char __user *buf,for (i =0 ; i <MAX_PIPES ; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink)break ; }
@@ -1655,7 +1661,9 @@ static ssize_t dp_dsc_slice_width_write(struct file *f, const char __user *buf,for (i =0 ; i <MAX_PIPES ; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink)break ; }
@@ -1740,7 +1748,9 @@ static ssize_t dp_dsc_slice_height_read(struct file *f, char __user *buf,for (i =0 ; i <MAX_PIPES ; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink)break ; }
@@ -1839,7 +1849,9 @@ static ssize_t dp_dsc_slice_height_write(struct file *f, const char __user *buf,for (i =0 ; i <MAX_PIPES ; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink)break ; }
@@ -1920,7 +1932,9 @@ static ssize_t dp_dsc_bits_per_pixel_read(struct file *f, char __user *buf,for (i =0 ; i <MAX_PIPES ; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink)break ; }
@@ -2016,7 +2030,9 @@ static ssize_t dp_dsc_bits_per_pixel_write(struct file *f, const char __user *bufor (i =0 ; i <MAX_PIPES ; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink)break ; }
@@ -2095,7 +2111,9 @@ static ssize_t dp_dsc_pic_width_read(struct file *f, char __user *buf,for (i =0 ; i <MAX_PIPES ; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink)break ; }
@@ -2151,7 +2169,9 @@ static ssize_t dp_dsc_pic_height_read(struct file *f, char __user *buf,for (i =0 ; i <MAX_PIPES ; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink)break ; }
@@ -2222,7 +2242,9 @@ static ssize_t dp_dsc_chunk_size_read(struct file *f, char __user *buf,for (i =0 ; i <MAX_PIPES ; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink)break ; }
@@ -2293,7 +2315,9 @@ static ssize_t dp_dsc_slice_bpg_offset_read(struct file *f, char __user *buf,for (i =0 ; i <MAX_PIPES ; i++) { pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];if (pipe_ctx->stream && - pipe_ctx->stream->link == aconnector->dc_link) + pipe_ctx->stream->link == aconnector->dc_link && + pipe_ctx->stream->sink && + pipe_ctx->stream->sink == aconnector->dc_sink)break ; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 60/217 arm64: dts: qcom: sm8150: align TLMM pin configuration with DT schema
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Krzysztof Kozlowski <[email protected]>
[ Upstream commit 028fe09cda0a0d568e6a7d65b0336d32600b480c ]
DT schema expects TLMM pin configuration nodes to be named with '-state' suffix and their optional children with '-pins' suffix.
Stable-dep-of: 819fe8c96a51 ("arm64: dts: qcom: sa8155p-adp: fix SDHC2 CD pin configuration")
--- arch/arm64/boot/dts/qcom/sa8155p-adp.dts | 60 ++- .../dts/qcom/sm8150-microsoft-surface-duo.dts | 2 +- arch/arm64/boot/dts/qcom/sm8150.dtsi | 376 ++++++------------ 3 files changed, 157 insertions(+), 281 deletions(-)
arch/arm64/boot/dts/qcom/sa8155p-adp.dts +28 -32
@@ -488,26 +488,26 @@ &pcie1_phy { &tlmm { gpio-reserved-ranges = <0 4>; - sdc2_on: sdc2_on { - clk { + sdc2_on: sdc2-on-state { + clk-pins { pins = "sdc2_clk"; bias-disable; /* No pull */ drive-strength = <16>; /* 16 MA */ }; - cmd { + cmd-pins { pins = "sdc2_cmd"; bias-pull-up; /* pull up */ drive-strength = <16>; /* 16 MA */ }; - data { + data-pins { pins = "sdc2_data"; bias-pull-up; /* pull up */ drive-strength = <16>; /* 16 MA */ }; - sd-cd { + sd-cd-pins { pins = "gpio96"; function = "gpio"; bias-pull-up; /* pull up */
@@ -515,26 +515,26 @@ sd-cd { }; }; - sdc2_off: sdc2_off { - clk { + sdc2_off: sdc2-off-state { + clk-pins { pins = "sdc2_clk"; bias-disable; /* No pull */ drive-strength = <2>; /* 2 MA */ }; - cmd { + cmd-pins { pins = "sdc2_cmd"; bias-pull-up; /* pull up */ drive-strength = <2>; /* 2 MA */ }; - data { + data-pins { pins = "sdc2_data"; bias-pull-up; /* pull up */ drive-strength = <2>; /* 2 MA */ }; - sd-cd { + sd-cd-pins { pins = "gpio96"; function = "gpio"; bias-pull-up; /* pull up */
@@ -542,66 +542,62 @@ sd-cd { }; }; - usb2phy_ac_en1_default: usb2phy_ac_en1_default { - mux { - pins = "gpio113"; - function = "usb2phy_ac"; - bias-disable; - drive-strength = <2>; - }; + usb2phy_ac_en1_default: usb2phy-ac-en1-default-state { + pins = "gpio113"; + function = "usb2phy_ac"; + bias-disable; + drive-strength = <2>; }; - usb2phy_ac_en2_default: usb2phy_ac_en2_default { - mux { - pins = "gpio123"; - function = "usb2phy_ac"; - bias-disable; - drive-strength = <2>; - }; + usb2phy_ac_en2_default: usb2phy-ac-en2-default-state { + pins = "gpio123"; + function = "usb2phy_ac"; + bias-disable; + drive-strength = <2>; }; - ethernet_defaults: ethernet-defaults { - mdc { + ethernet_defaults: ethernet-defaults-state { + mdc-pins { pins = "gpio7"; function = "rgmii"; bias-pull-up; }; - mdio { + mdio-pins { pins = "gpio59"; function = "rgmii"; bias-pull-up; }; - rgmii-rx { + rgmii-rx-pins { pins = "gpio117", "gpio118", "gpio119", "gpio120", "gpio115", "gpio116"; function = "rgmii"; bias-disable; drive-strength = <2>; }; - rgmii-tx { + rgmii-tx-pins { pins = "gpio122", "gpio4", "gpio5", "gpio6", "gpio114", "gpio121"; function = "rgmii"; bias-pull-up; drive-strength = <16>; }; - phy-intr { + phy-intr-pins { pins = "gpio124"; function = "emac_phy"; bias-disable; drive-strength = <8>; }; - pps { + pps-pins { pins = "gpio81"; function = "emac_pps"; bias-disable; drive-strength = <8>; }; - phy-reset { + phy-reset-pins { pins = "gpio79"; function = "gpio"; bias-pull-up;
arch/arm64/boot/dts/qcom/sm8150-microsoft-surface-duo.dts +1 -1
@@ -475,7 +475,7 @@ &pon_resin { &tlmm { gpio-reserved-ranges = <126 4>; - da7280_intr_default: da7280-intr-default { + da7280_intr_default: da7280-intr-default-state { pins = "gpio42"; function = "gpio"; bias-pull-up;
arch/arm64/boot/dts/qcom/sm8150.dtsi +128 -248
572 lines not on this page · raw message
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 61/217 arm64: dts: qcom: sa8155p-adp: fix SDHC2 CD pin configuration
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Volodymyr Babchuk <[email protected]>
[ Upstream commit 819fe8c96a5172dfd960e5945e8f00f8fed32953 ]
There are two issues with SDHC2 configuration for SA8155P-ADP, which prevent use of SDHC2 and causes issues with ethernet:
- Card Detect pin for SHDC2 on SA8155P-ADP is connected to gpio4 of PMM8155AU_1, not to SoC itself. SoC's gpio4 is used for DWMAC TX. If sdhc driver probes after dwmac driver, it reconfigures gpio4 and this breaks Ethernet MAC.
- pinctrl configuration mentions gpio96 as CD pin. It seems it was copied from some SM8150 example, because as mentioned above, correct CD pin is gpio4 on PMM8155AU_1.
This patch fixes both mentioned issues by providing correct pin handle and pinctrl configuration.
--- arch/arm64/boot/dts/qcom/sa8155p-adp.dts | 30 ++++++++++-------------- 1 file changed, 13 insertions(+), 17 deletions(-)
arch/arm64/boot/dts/qcom/sa8155p-adp.dts +13 -17
@@ -372,6 +372,16 @@ rgmii_phy: phy@7 { }; }; +&pmm8155au_1_gpios { + pmm8155au_1_sdc2_cd: sdc2-cd-default-state { + pins = "gpio4"; + function = "normal"; + input-enable; + bias-pull-up; + power-source = <0>; + }; +}; + &qupv3_id_1 { status = "okay"; };
@@ -389,10 +399,10 @@ &remoteproc_cdsp { &sdhc_2 { status = "okay"; - cd-gpios = <&tlmm 4 GPIO_ACTIVE_LOW>; + cd-gpios = <&pmm8155au_1_gpios 4 GPIO_ACTIVE_LOW>; pinctrl-names = "default", "sleep"; - pinctrl-0 = <&sdc2_on>; - pinctrl-1 = <&sdc2_off>; + pinctrl-0 = <&sdc2_on &pmm8155au_1_sdc2_cd>; + pinctrl-1 = <&sdc2_off &pmm8155au_1_sdc2_cd>; vqmmc-supply = <&vreg_l13c_2p96>; /* IO line power */ vmmc-supply = <&vreg_l17a_2p96>; /* Card power line */ bus-width = <4>;
@@ -506,13 +516,6 @@ data-pins { bias-pull-up; /* pull up */ drive-strength = <16>; /* 16 MA */ }; - - sd-cd-pins { - pins = "gpio96"; - function = "gpio"; - bias-pull-up; /* pull up */ - drive-strength = <2>; /* 2 MA */ - }; }; sdc2_off: sdc2-off-state {
@@ -533,13 +536,6 @@ data-pins { bias-pull-up; /* pull up */ drive-strength = <2>; /* 2 MA */ }; - - sd-cd-pins { - pins = "gpio96"; - function = "gpio"; - bias-pull-up; /* pull up */ - drive-strength = <2>; /* 2 MA */ - }; }; usb2phy_ac_en1_default: usb2phy-ac-en1-default-state {
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 35/217 af_unix: Set sk->sk_state under unix_state_lock() for truly disconencted peer.
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kuniyuki Iwashima <[email protected]>
[ Upstream commit 26bfb8b57063f52b867f9b6c8d1742fcb5bd656c ]
When a SOCK_DGRAM socket connect()s to another socket, the both sockets' sk->sk_state are changed to TCP_ESTABLISHED so that we can register them to BPF SOCKMAP.
When the socket disconnects from the peer by connect(AF_UNSPEC), the state is set back to TCP_CLOSE.
Then, the peer's state is also set to TCP_CLOSE, but the update is done locklessly and unconditionally.
Let's say socket A connect()ed to B, B connect()ed to C, and A disconnects from B.
After the first two connect()s, all three sockets' sk->sk_state are TCP_ESTABLISHED:
$ ss -xa Netid State Recv-Q Send-Q Local Address:Port Peer Address:PortProcess u_dgr ESTAB 0 0 @A 641 * 642 u_dgr ESTAB 0 0 @B 642 * 643 u_dgr ESTAB 0 0 @C 643 * 0
And after the disconnect, B's state is TCP_CLOSE even though it's still connected to C and C's state is TCP_ESTABLISHED.
$ ss -xa Netid State Recv-Q Send-Q Local Address:Port Peer Address:PortProcess u_dgr UNCONN 0 0 @A 641 * 0 u_dgr UNCONN 0 0 @B 642 * 643 u_dgr ESTAB 0 0 @C 643 * 0
In this case, we cannot register B to SOCKMAP.
So, when a socket disconnects from the peer, we should not set TCP_CLOSE to the peer if the peer is connected to yet another socket, and this must be done under unix_state_lock().
Note that we use WRITE_ONCE() for sk->sk_state as there are many lockless readers. These data-races will be fixed in the following patches.
--- net/unix/af_unix.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)
net/unix/af_unix.c +8 -2
@@ -558,7 +558,6 @@ static void unix_dgram_disconnected(struct sock *sk, struct sock *other)sk_error_report (other); } } - other->sk_state =TCP_CLOSE ; }static void unix_sock_destructor (struct sock *sk)
@@ -1412,8 +1411,15 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr,unix_state_double_unlock (sk, other); -if (other != old_peer) +if (other != old_peer) {unix_dgram_disconnected (sk, old_peer); + +unix_state_lock (old_peer); +if (!unix_peer (old_peer)) +WRITE_ONCE (old_peer->sk_state,TCP_CLOSE ); +unix_state_unlock (old_peer); + } +sock_put (old_peer); }else {unix_peer (sk) = other;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 62/217 misc/pvpanic: deduplicate common code
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Thomas Weißschuh <[email protected]>
[ Upstream commit c1426d392aebc51da4944d950d89e483e43f6f14 ]
pvpanic-mmio.c and pvpanic-pci.c share a lot of code. Refactor it into pvpanic.c where it doesn't have to be kept in sync manually and where the core logic can be understood more easily.
No functional change.
Stable-dep-of: ee59be35d7a8 ("misc/pvpanic-pci: register attributes via pci_driver")
--- drivers/misc/pvpanic/pvpanic-mmio.c | 58 +--------------------- drivers/misc/pvpanic/pvpanic-pci.c | 58 +--------------------- drivers/misc/pvpanic/pvpanic.c | 76 ++++++++++++++++++++++++++++- drivers/misc/pvpanic/pvpanic.h | 10 +--- 4 files changed, 80 insertions(+), 122 deletions(-)
drivers/misc/pvpanic/pvpanic-mmio.c +2 -56
@@ -24,52 +24,9 @@ MODULE_AUTHOR("Hu Tao <[email protected]>");MODULE_DESCRIPTION ("pvpanic-mmio device driver" );MODULE_LICENSE ("GPL" ); -static ssize_t capability_show (struct device *dev,struct device_attribute *attr,char *buf) -{ -struct pvpanic_instance *pi =dev_get_drvdata (dev); - -return sysfs_emit (buf,"%x\n" , pi->capability); -} -static DEVICE_ATTR_RO (capability); - -static ssize_t events_show (struct device *dev,struct device_attribute *attr,char *buf) -{ -struct pvpanic_instance *pi =dev_get_drvdata (dev); - -return sysfs_emit (buf,"%x\n" , pi->events); -} - -static ssize_t events_store (struct device *dev,struct device_attribute *attr, -const char *buf,size_t count) -{ -struct pvpanic_instance *pi =dev_get_drvdata (dev); -unsigned int tmp; -int err; - - err =kstrtouint (buf,16 , &tmp); -if (err) -return err; - -if ((tmp & pi->capability) != tmp) -return -EINVAL ; - - pi->events = tmp; - -return count; -} -static DEVICE_ATTR_RW (events); - -static struct attribute *pvpanic_mmio_dev_attrs[] = { - &dev_attr_capability.attr, - &dev_attr_events.attr, -NULL -}; -ATTRIBUTE_GROUPS (pvpanic_mmio_dev); -static int pvpanic_mmio_probe (struct platform_device *pdev) {struct device *dev = &pdev->dev; -struct pvpanic_instance *pi;struct resource *res;void __iomem *base;
@@ -92,18 +49,7 @@ static int pvpanic_mmio_probe(struct platform_device *pdev)return -EINVAL ; } - pi =devm_kmalloc (dev,sizeof (*pi),GFP_KERNEL ); -if (!pi) -return -ENOMEM ; - - pi->base = base; - pi->capability =PVPANIC_PANICKED |PVPANIC_CRASH_LOADED ; - -/* initialize capability by RDPT */ - pi->capability &=ioread8 (base); - pi->events = pi->capability; - -return devm_pvpanic_probe (dev, pi); +return devm_pvpanic_probe (dev, base); }static const struct of_device_id pvpanic_mmio_match[] = {
@@ -123,7 +69,7 @@ static struct platform_driver pvpanic_mmio_driver = { .name = "pvpanic-mmio", .of_match_table = pvpanic_mmio_match, .acpi_match_table = pvpanic_device_ids, - .dev_groups = pvpanic_mmio_dev_groups, + .dev_groups = pvpanic_dev_groups, }, .probe = pvpanic_mmio_probe, };
drivers/misc/pvpanic/pvpanic-pci.c +2 -56
78 lines not on this page · raw message
drivers/misc/pvpanic/pvpanic.c +74 -2
97 lines not on this page · raw message
drivers/misc/pvpanic/pvpanic.h +2 -8
@@ -8,13 +8,7 @@#ifndef PVPANIC_H_ #define PVPANIC_H_ -struct pvpanic_instance { -void __iomem *base; -unsigned int capability; -unsigned int events; -struct list_head list; -}; - -int devm_pvpanic_probe (struct device *dev,struct pvpanic_instance *pi); +int devm_pvpanic_probe (struct device *dev,void __iomem *base); +extern const struct attribute_group *pvpanic_dev_groups[];#endif /* PVPANIC_H_ */
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 63/217 misc/pvpanic-pci: register attributes via pci_driver
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Thomas Weißschuh <[email protected]>
[ Upstream commit ee59be35d7a8be7fcaa2d61fb89734ab5c25e4ee ]
In __pci_register_driver(), the pci core overwrites the dev_groups field of the embedded struct device_driver with the dev_groups from the outer struct pci_driver unconditionally.
Set dev_groups in the pci_driver to make sure it is used.
This was broken since the introduction of pvpanic-pci.
--- drivers/misc/pvpanic/pvpanic-pci.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)
drivers/misc/pvpanic/pvpanic-pci.c +1 -3
@@ -48,8 +48,6 @@ static struct pci_driver pvpanic_pci_driver = { .name = "pvpanic-pci", .id_table = pvpanic_pci_id_tbl, .probe = pvpanic_pci_probe, - .driver = { - .dev_groups = pvpanic_dev_groups, - }, + .dev_groups = pvpanic_dev_groups, };module_pci_driver (pvpanic_pci_driver);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 64/217 serial: sc16is7xx: replace hardcoded divisor value with BIT() macro
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Hugo Villeneuve <[email protected]>
[ Upstream commit 2e57cefc4477659527f7adab1f87cdbf60ef1ae6 ]
To better show why the limit is what it is, since we have only 16 bits for the divisor.
Stable-dep-of: 8492bd91aa05 ("serial: sc16is7xx: fix bug in sc16is7xx_set_baud() when using prescaler")
--- drivers/tty/serial/sc16is7xx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/tty/serial/sc16is7xx.c +1 -1
@@ -489,7 +489,7 @@ static int sc16is7xx_set_baud(struct uart_port *port, int baud)u8 prescaler =0 ;unsigned long clk = port->uartclk, div = clk /16 / baud; -if (div >0xffff ) { +if (div >=BIT (16 )) { prescaler =SC16IS7XX_MCR_CLKSEL_BIT ; div /=4 ; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 36/217 af_unix: Annodate data-races around sk->sk_state for writers.
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kuniyuki Iwashima <[email protected]>
[ Upstream commit 942238f9735a4a4ebf8274b218d9a910158941d1 ]
sk->sk_state is changed under unix_state_lock(), but it's read locklessly in many places.
This patch adds WRITE_ONCE() on the writer side.
We will add READ_ONCE() to the lockless readers in the following patches.
--- net/unix/af_unix.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-)
net/unix/af_unix.c +8 -6
@@ -604,7 +604,7 @@ static void unix_release_sock(struct sock *sk, int embrion) u->path.dentry =NULL ; u->path.mnt =NULL ; state = sk->sk_state; - sk->sk_state =TCP_CLOSE ; +WRITE_ONCE (sk->sk_state,TCP_CLOSE ); skpair =unix_peer (sk);unix_peer (sk) =NULL ;
@@ -726,7 +726,8 @@ static int unix_listen(struct socket *sock, int backlog)if (backlog > sk->sk_max_ack_backlog)wake_up_interruptible_all (&u->peer_wait); sk->sk_max_ack_backlog = backlog; - sk->sk_state =TCP_LISTEN ; +WRITE_ONCE (sk->sk_state,TCP_LISTEN ); +/* set credentials so connect can copy them */ init_peercred (sk); err =0 ;
@@ -1389,7 +1390,8 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr,if (err) goto out_unlock; - sk->sk_state = other->sk_state =TCP_ESTABLISHED ; +WRITE_ONCE (sk->sk_state,TCP_ESTABLISHED ); +WRITE_ONCE (other->sk_state,TCP_ESTABLISHED ); }else {/* * 1003.1g breaking connected state with AF_UNSPEC
@@ -1406,7 +1408,7 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr,unix_peer (sk) = other;if (!other) - sk->sk_state =TCP_CLOSE ; +WRITE_ONCE (sk->sk_state,TCP_CLOSE );unix_dgram_peer_wake_disconnect_wakeup (sk, old_peer);unix_state_double_unlock (sk, other);
@@ -1620,7 +1622,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,copy_peercred (sk, other); sock->state =SS_CONNECTED ; - sk->sk_state =TCP_ESTABLISHED ; +WRITE_ONCE (sk->sk_state,TCP_ESTABLISHED );sock_hold (newsk);smp_mb__after_atomic ();/* sock_hold() does an atomic_inc() */
@@ -2015,7 +2017,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,unix_peer (sk) =NULL ;unix_dgram_peer_wake_disconnect_wakeup (sk, other); - sk->sk_state =TCP_CLOSE ; +WRITE_ONCE (sk->sk_state,TCP_CLOSE );unix_state_unlock (sk);unix_dgram_disconnected (sk, other);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 37/217 af_unix: Annotate data-race of sk->sk_state in unix_inq_len().
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kuniyuki Iwashima <[email protected]>
[ Upstream commit 3a0f38eb285c8c2eead4b3230c7ac2983707599d ]
ioctl(SIOCINQ) calls unix_inq_len() that checks sk->sk_state first and returns -EINVAL if it's TCP_LISTEN.
Then, for SOCK_STREAM sockets, unix_inq_len() returns the number of bytes in recvq.
However, unix_inq_len() does not hold unix_state_lock(), and the concurrent listen() might change the state after checking sk->sk_state.
If the race occurs, 0 is returned for the listener, instead of -EINVAL, because the length of skb with embryo is 0.
We could hold unix_state_lock() in unix_inq_len(), but it's overkill given the result is true for pre-listen() TCP_CLOSE state.
So, let's use READ_ONCE() for sk->sk_state in unix_inq_len().
--- net/unix/af_unix.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/unix/af_unix.c +1 -1
@@ -3068,7 +3068,7 @@ long unix_inq_len(struct sock *sk)struct sk_buff *skb;long amount =0 ; -if (sk->sk_state ==TCP_LISTEN ) +if (READ_ONCE (sk->sk_state) ==TCP_LISTEN )return -EINVAL ;spin_lock (&sk->sk_receive_queue.lock);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 38/217 af_unix: Annotate data-races around sk->sk_state in unix_write_space() and poll().
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kuniyuki Iwashima <[email protected]>
[ Upstream commit eb0718fb3e97ad0d6f4529b810103451c90adf94 ]
unix_poll() and unix_dgram_poll() read sk->sk_state locklessly and calls unix_writable() which also reads sk->sk_state without holding unix_state_lock().
Let's use READ_ONCE() in unix_poll() and unix_dgram_poll() and pass it to unix_writable().
While at it, we remove TCP_SYN_SENT check in unix_dgram_poll() as that state does not exist for AF_UNIX socket since the code was added.
--- net/unix/af_unix.c | 25 ++++++++++++------------- 1 file changed, 12 insertions(+), 13 deletions(-)
net/unix/af_unix.c +12 -13
@@ -518,9 +518,9 @@ static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other)return 0 ; } -static int unix_writable (const struct sock *sk) +static int unix_writable (const struct sock *sk,unsigned char state) { -return sk->sk_state !=TCP_LISTEN && +return state !=TCP_LISTEN && (refcount_read (&sk->sk_wmem_alloc) <<2 ) <= sk->sk_sndbuf; }
@@ -529,7 +529,7 @@ static void unix_write_space(struct sock *sk)struct socket_wq *wq;rcu_read_lock (); -if (unix_writable (sk)) { +if (unix_writable (sk,READ_ONCE (sk->sk_state))) { wq =rcu_dereference (sk->sk_wq);if (skwq_has_sleeper (wq)) wake_up_interruptible_sync_poll(&wq->wait,
@@ -3180,12 +3180,14 @@ static int unix_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned lonstatic __poll_t unix_poll (struct file *file,struct socket *sock,poll_table *wait) {struct sock *sk = sock->sk; +unsigned char state;__poll_t mask;u8 shutdown;sock_poll_wait (file, sock, wait); mask =0 ; shutdown =READ_ONCE (sk->sk_shutdown); + state =READ_ONCE (sk->sk_state);/* exceptional events? */ if (sk->sk_err)
@@ -3207,14 +3209,14 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa/* Connection-based need to check for termination and startup */ if ((sk->sk_type ==SOCK_STREAM || sk->sk_type ==SOCK_SEQPACKET ) && - sk->sk_state ==TCP_CLOSE ) + state ==TCP_CLOSE ) mask |=EPOLLHUP ;/* * we set writable also when the other side has shut down the * connection. This prevents stuck sockets. */ -if (unix_writable (sk)) +if (unix_writable (sk, state)) mask |=EPOLLOUT |EPOLLWRNORM |EPOLLWRBAND ;return mask;
@@ -3225,12 +3227,14 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, {struct sock *sk = sock->sk, *other;unsigned int writable; +unsigned char state;__poll_t mask;u8 shutdown;sock_poll_wait (file, sock, wait); mask =0 ; shutdown =READ_ONCE (sk->sk_shutdown); + state =READ_ONCE (sk->sk_state);/* exceptional events? */ if (sk->sk_err || !skb_queue_empty_lockless (&sk->sk_error_queue))
@@ -3249,19 +3253,14 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, mask |=EPOLLIN |EPOLLRDNORM ;/* Connection-based need to check for termination and startup */ -if (sk->sk_type ==SOCK_SEQPACKET ) { -if (sk->sk_state ==TCP_CLOSE ) - mask |=EPOLLHUP ; -/* connection hasn't started yet? */ -if (sk->sk_state ==TCP_SYN_SENT ) -return mask; - } +if (sk->sk_type ==SOCK_SEQPACKET && state ==TCP_CLOSE ) + mask |=EPOLLHUP ;/* No write status requested, avoid expensive OUT tests. */ if (!(poll_requested_events (wait) & (EPOLLWRBAND |EPOLLWRNORM |EPOLLOUT )))return mask; - writable =unix_writable (sk); + writable =unix_writable (sk, state);if (writable) {unix_state_lock (sk);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 39/217 af_unix: Annotate data-race of sk->sk_state in unix_stream_connect().
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kuniyuki Iwashima <[email protected]>
[ Upstream commit a9bf9c7dc6a5899c01cb8f6e773a66315a5cd4b7 ]
As small optimisation, unix_stream_connect() prefetches the client's sk->sk_state without unix_state_lock() and checks if it's TCP_CLOSE.
Later, sk->sk_state is checked again under unix_state_lock().
Let's use READ_ONCE() for the first check and TCP_CLOSE directly for the second check.
--- net/unix/af_unix.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-)
net/unix/af_unix.c +2 -5
@@ -1469,7 +1469,6 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,struct sk_buff *skb =NULL ;long timeo;int err; -int st; err =unix_validate_addr (sunaddr, addr_len);if (err)
@@ -1553,9 +1552,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,Well, and we have to recheck the state after socket locked. */ - st = sk->sk_state; - -switch (st) { +switch (READ_ONCE (sk->sk_state)) {case TCP_CLOSE :/* This is ok... continue with connect */ break ;
@@ -1570,7 +1567,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,unix_state_lock_nested (sk,U_LOCK_SECOND ); -if (sk->sk_state != st) { +if (sk->sk_state !=TCP_CLOSE ) {unix_state_unlock (sk);unix_state_unlock (other);sock_put (other);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 40/217 af_unix: Annotate data-races around sk->sk_state in sendmsg() and recvmsg().
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kuniyuki Iwashima <[email protected]>
[ Upstream commit 8a34d4e8d9742a24f74998f45a6a98edd923319b ]
The following functions read sk->sk_state locklessly and proceed only if the state is TCP_ESTABLISHED.
* unix_stream_sendmsg
* unix_stream_read_generic
* unix_seqpacket_sendmsg
* unix_seqpacket_recvmsg
Let's use READ_ONCE() there.
--- net/unix/af_unix.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
net/unix/af_unix.c +4 -4
@@ -2190,7 +2190,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, }if (msg->msg_namelen) { - err = sk->sk_state ==TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP ; + err =READ_ONCE (sk->sk_state) ==TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP ; goto out_err; }else { err = -ENOTCONN ;
@@ -2402,7 +2402,7 @@ static int unix_seqpacket_sendmsg(struct socket *sock, struct msghdr *msg,if (err)return err; -if (sk->sk_state !=TCP_ESTABLISHED ) +if (READ_ONCE (sk->sk_state) !=TCP_ESTABLISHED )return -ENOTCONN ;if (msg->msg_namelen)
@@ -2416,7 +2416,7 @@ static int unix_seqpacket_recvmsg(struct socket *sock, struct msghdr *msg, {struct sock *sk = sock->sk; -if (sk->sk_state !=TCP_ESTABLISHED ) +if (READ_ONCE (sk->sk_state) !=TCP_ESTABLISHED )return -ENOTCONN ;return unix_dgram_recvmsg (sock, msg, size, flags);
@@ -2740,7 +2740,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state,size_t size = state->size;unsigned int last_len; -if (unlikely (sk->sk_state !=TCP_ESTABLISHED )) { +if (unlikely (READ_ONCE (sk->sk_state) !=TCP_ESTABLISHED )) { err = -EINVAL ; goto out; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 41/217 af_unix: Annotate data-race of sk->sk_state in unix_stream_read_skb().
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kuniyuki Iwashima <[email protected]>
[ Upstream commit af4c733b6b1aded4dc808fafece7dfe6e9d2ebb3 ]
unix_stream_read_skb() is called from sk->sk_data_ready() context where unix_state_lock() is not held.
Let's use READ_ONCE() there.
--- net/unix/af_unix.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/unix/af_unix.c +1 -1
@@ -2716,7 +2716,7 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,static int unix_stream_read_skb (struct sock *sk,skb_read_actor_t recv_actor) { -if (unlikely (sk->sk_state !=TCP_ESTABLISHED )) +if (unlikely (READ_ONCE (sk->sk_state) !=TCP_ESTABLISHED ))return -ENOTCONN ;return unix_read_skb (sk, recv_actor);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 32/217 ice: remove null checks before devm_kfree() calls
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Przemek Kitszel <[email protected]>
[ Upstream commit ad667d626825383b626ad6ed38d6205618abb115 ]
We all know they are redundant.
Stable-dep-of: adbf5a42341f ("ice: remove af_xdp_zc_qps bitmap")
--- drivers/net/ethernet/intel/ice/ice_common.c | 6 +-- drivers/net/ethernet/intel/ice/ice_controlq.c | 3 +- drivers/net/ethernet/intel/ice/ice_flow.c | 23 ++-------- drivers/net/ethernet/intel/ice/ice_lib.c | 42 +++++++------------ drivers/net/ethernet/intel/ice/ice_sched.c | 11 ++--- drivers/net/ethernet/intel/ice/ice_switch.c | 19 +++------ 6 files changed, 29 insertions(+), 75 deletions(-)
drivers/net/ethernet/intel/ice/ice_common.c +2 -4
@@ -789,8 +789,7 @@ static void ice_cleanup_fltr_mgmt_struct(struct ice_hw *hw)devm_kfree (ice_hw_to_dev (hw), lst_itr); } } -if (recps[i].root_buf) -devm_kfree (ice_hw_to_dev (hw), recps[i].root_buf); +devm_kfree (ice_hw_to_dev (hw), recps[i].root_buf); }ice_rm_all_sw_replay_rule_info (hw);devm_kfree (ice_hw_to_dev (hw), sw->recp_list);
@@ -986,8 +985,7 @@ static int ice_cfg_fw_log(struct ice_hw *hw, bool enable) } out: -if (data) -devm_kfree (ice_hw_to_dev (hw), data); +devm_kfree (ice_hw_to_dev (hw), data);return status; }
drivers/net/ethernet/intel/ice/ice_controlq.c +1 -2
@@ -339,8 +339,7 @@ do { \ } \ } \/* free the buffer info list */ \ -if ((qi)->ring.cmd_buf) \ -devm_kfree (ice_hw_to_dev (hw), (qi)->ring.cmd_buf); \ +devm_kfree (ice_hw_to_dev (hw), (qi)->ring.cmd_buf); \/* free DMA head */ \devm_kfree (ice_hw_to_dev (hw), (qi)->ring.dma_head); \ }while (0 )
drivers/net/ethernet/intel/ice/ice_flow.c +3 -20
@@ -1303,23 +1303,6 @@ ice_flow_find_prof_id(struct ice_hw *hw, enum ice_block blk, u64 prof_id)return NULL ; } -/** -* ice_dealloc_flow_entry - Deallocate flow entry memory -* @hw: pointer to the HW struct -* @entry: flow entry to be removed -*/ -static void -ice_dealloc_flow_entry (struct ice_hw *hw,struct ice_flow_entry *entry) -{ -if (!entry) -return ; - -if (entry->entry) -devm_kfree (ice_hw_to_dev (hw), entry->entry); - -devm_kfree (ice_hw_to_dev (hw), entry); -} -/** * ice_flow_rem_entry_sync - Remove a flow entry * @hw: pointer to the HW struct
@@ -1335,7 +1318,8 @@ ice_flow_rem_entry_sync(struct ice_hw *hw, enum ice_block __always_unused blk,list_del (&entry->l_entry); -ice_dealloc_flow_entry (hw, entry); +devm_kfree (ice_hw_to_dev (hw), entry->entry); +devm_kfree (ice_hw_to_dev (hw), entry);return 0 ; }
@@ -1662,8 +1646,7 @@ ice_flow_add_entry(struct ice_hw *hw, enum ice_block blk, u64 prof_id, out:if (status && e) { -if (e->entry) -devm_kfree (ice_hw_to_dev (hw), e->entry); +devm_kfree (ice_hw_to_dev (hw), e->entry);devm_kfree (ice_hw_to_dev (hw), e); }
drivers/net/ethernet/intel/ice/ice_lib.c +14 -28
55 lines not on this page · raw message
drivers/net/ethernet/intel/ice/ice_sched.c +3 -8
@@ -353,10 +353,7 @@ void ice_free_sched_node(struct ice_port_info *pi, struct ice_sched_node *node) node->sibling; } -/* leaf nodes have no children */ -if (node->children) -devm_kfree (ice_hw_to_dev (hw), node->children); - +devm_kfree (ice_hw_to_dev (hw), node->children);kfree (node->name);xa_erase (&pi->sched_node_ids, node->id);devm_kfree (ice_hw_to_dev (hw), node);
@@ -854,10 +851,8 @@ void ice_sched_cleanup_all(struct ice_hw *hw)if (!hw)return ; -if (hw->layer_info) { -devm_kfree (ice_hw_to_dev (hw), hw->layer_info); - hw->layer_info =NULL ; - } +devm_kfree (ice_hw_to_dev (hw), hw->layer_info); + hw->layer_info =NULL ;ice_sched_clear_port (hw->port_info);
drivers/net/ethernet/intel/ice/ice_switch.c +6 -13
@@ -1636,21 +1636,16 @@ ice_save_vsi_ctx(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi)*/ static void ice_clear_vsi_q_ctx (struct ice_hw *hw,u16 vsi_handle) { -struct ice_vsi_ctx *vsi; +struct ice_vsi_ctx *vsi =ice_get_vsi_ctx (hw, vsi_handle);u8 i; - vsi =ice_get_vsi_ctx (hw, vsi_handle);if (!vsi)return ;ice_for_each_traffic_class (i) { -if (vsi->lan_q_ctx[i]) { -devm_kfree (ice_hw_to_dev (hw), vsi->lan_q_ctx[i]); - vsi->lan_q_ctx[i] =NULL ; - } -if (vsi->rdma_q_ctx[i]) { -devm_kfree (ice_hw_to_dev (hw), vsi->rdma_q_ctx[i]); - vsi->rdma_q_ctx[i] =NULL ; - } +devm_kfree (ice_hw_to_dev (hw), vsi->lan_q_ctx[i]); + vsi->lan_q_ctx[i] =NULL ; +devm_kfree (ice_hw_to_dev (hw), vsi->rdma_q_ctx[i]); + vsi->rdma_q_ctx[i] =NULL ; } }
@@ -5525,9 +5520,7 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups,devm_kfree (ice_hw_to_dev (hw), fvit); } -if (rm->root_buf) -devm_kfree (ice_hw_to_dev (hw), rm->root_buf); - +devm_kfree (ice_hw_to_dev (hw), rm->root_buf);kfree (rm); err_free_lkup_exts:
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 66/217 mmc: davinci: Dont strip remove function when driver is builtin
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Uwe Kleine-König <[email protected]>
[ Upstream commit 55c421b364482b61c4c45313a535e61ed5ae4ea3 ]
Using __exit for the remove function results in the remove callback being discarded with CONFIG_MMC_DAVINCI=y. When such a device gets unbound (e.g. using sysfs or hotplug), the driver is just removed without the cleanup being performed. This results in resource leaks. Fix it by compiling in the remove callback unconditionally.
This also fixes a W=1 modpost warning:
WARNING: modpost: drivers/mmc/host/davinci_mmc: section mismatch in
reference: davinci_mmcsd_driver+0x10 (section: .data) -> davinci_mmcsd_remove (section: .exit.text)
--- drivers/mmc/host/davinci_mmc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/mmc/host/davinci_mmc.c +2 -2
@@ -1345,7 +1345,7 @@ static int davinci_mmcsd_probe(struct platform_device *pdev)return ret; } -static int __exit davinci_mmcsd_remove(struct platform_device *pdev) +static int davinci_mmcsd_remove (struct platform_device *pdev) {struct mmc_davinci_host *host =platform_get_drvdata (pdev);
@@ -1402,7 +1402,7 @@ static struct platform_driver davinci_mmcsd_driver = { .of_match_table = davinci_mmc_dt_ids, }, .probe = davinci_mmcsd_probe, - .remove = __exit_p(davinci_mmcsd_remove), + .remove = davinci_mmcsd_remove, .id_table = davinci_mmc_devtype, };
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 75/217 selftests/mm: conform test to TAP format output
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Muhammad Usama Anjum <[email protected]>
[ Upstream commit 9a21701edc41465de56f97914741bfb7bfc2517d ]
Conform the layout, informational and status messages to TAP. No functional change is intended other than the layout of output messages.
Stable-dep-of: d4202e66a4b1 ("selftests/mm: compaction_test: fix bogus test success on Aarch64")
--- tools/testing/selftests/vm/compaction_test.c | 91 ++++++++++---------- 1 file changed, 44 insertions(+), 47 deletions(-)
tools/testing/selftests/vm/compaction_test.c +44 -47
@@ -33,7 +33,7 @@ int read_memory_info(unsigned long *memfree, unsigned long *hugepagesize)FILE *cmdfile =popen (cmd,"r" );if (!(fgets (buffer,sizeof (buffer), cmdfile))) { -perror ("Failed to read meminfo\n" ); +ksft_print_msg ("Failed to read meminfo: %s\n" ,strerror (errno));return -1 ; }
@@ -44,7 +44,7 @@ int read_memory_info(unsigned long *memfree, unsigned long *hugepagesize) cmdfile =popen (cmd,"r" );if (!(fgets (buffer,sizeof (buffer), cmdfile))) { -perror ("Failed to read meminfo\n" ); +ksft_print_msg ("Failed to read meminfo: %s\n" ,strerror (errno));return -1 ; }
@@ -62,14 +62,14 @@ int prereq(void) fd =open ("/proc/sys/vm/compact_unevictable_allowed" ,O_RDONLY |O_NONBLOCK );if (fd <0 ) { -perror ("Failed to open\n" -"/proc/sys/vm/compact_unevictable_allowed\n" ); +ksft_print_msg ("Failed to open /proc/sys/vm/compact_unevictable_allowed: %s\n" , +strerror (errno));return -1 ; }if (read (fd, &allowed,sizeof (char )) !=sizeof (char )) { -perror ("Failed to read from\n" -"/proc/sys/vm/compact_unevictable_allowed\n" ); +ksft_print_msg ("Failed to read from /proc/sys/vm/compact_unevictable_allowed: %s\n" , +strerror (errno));close (fd);return -1 ; }
@@ -78,12 +78,13 @@ int prereq(void)if (allowed =='1' )return 0 ; +ksft_print_msg ("Compaction isn't allowed\n" );return -1 ; }int check_compaction (unsigned long mem_free,unsigned int hugepage_size) { -int fd; +int fd, ret =-1 ;int compaction_index =0 ;char initial_nr_hugepages[10 ] = {0 };char nr_hugepages[10 ] = {0 };
@@ -94,12 +95,14 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) fd =open ("/proc/sys/vm/nr_hugepages" ,O_RDWR |O_NONBLOCK );if (fd <0 ) { -perror ("Failed to open /proc/sys/vm/nr_hugepages" ); +ksft_test_result_fail ("Failed to open /proc/sys/vm/nr_hugepages: %s\n" , +strerror (errno));return -1 ; }if (read (fd, initial_nr_hugepages,sizeof (initial_nr_hugepages)) <=0 ) { -perror ("Failed to read from /proc/sys/vm/nr_hugepages" ); +ksft_test_result_fail ("Failed to read from /proc/sys/vm/nr_hugepages: %s\n" , +strerror (errno)); goto close_fd; }
@@ -107,7 +110,8 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size)/* Start with the initial condition of 0 huge pages*/ if (write (fd,"0" ,sizeof (char )) !=sizeof (char )) { -perror ("Failed to write 0 to /proc/sys/vm/nr_hugepages\n" ); +ksft_test_result_fail ("Failed to write 0 to /proc/sys/vm/nr_hugepages: %s\n" , +strerror (errno)); goto close_fd; }
@@ -116,14 +120,16 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size)/* Request a large number of huge pages. The Kernel will allocate as much as it can */ if (write (fd,"100000" , (6 *sizeof (char ))) != (6 *sizeof (char ))) { -perror ("Failed to write 100000 to /proc/sys/vm/nr_hugepages\n" ); +ksft_test_result_fail ("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n" , +strerror (errno)); goto close_fd; }lseek (fd,0 ,SEEK_SET );if (read (fd, nr_hugepages,sizeof (nr_hugepages)) <=0 ) { -perror ("Failed to re-read from /proc/sys/vm/nr_hugepages\n" ); +ksft_test_result_fail ("Failed to re-read from /proc/sys/vm/nr_hugepages: %s\n" , +strerror (errno)); goto close_fd; }
@@ -131,67 +137,58 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size)huge pages */ compaction_index = mem_free/(atoi (nr_hugepages) * hugepage_size); -if (compaction_index >3 ) { -printf ("No of huge pages allocated = %d\n" , - (atoi (nr_hugepages))); -fprintf (stderr,"ERROR: Less that 1/%d of memory is available\n" -"as huge pages\n" , compaction_index); - goto close_fd; - } - -printf ("No of huge pages allocated = %d\n" , - (atoi (nr_hugepages))); -lseek (fd,0 ,SEEK_SET );if (write (fd, initial_nr_hugepages,strlen (initial_nr_hugepages)) !=strlen (initial_nr_hugepages)) { -perror ("Failed to write value to /proc/sys/vm/nr_hugepages\n" ); +ksft_test_result_fail ("Failed to write value to /proc/sys/vm/nr_hugepages: %s\n" , +strerror (errno)); goto close_fd; } -close (fd); -return 0 ; +if (compaction_index >3 ) { +ksft_print_msg ("ERROR: Less that 1/%d of memory is available\n" +"as huge pages\n" , compaction_index); +ksft_test_result_fail ("No of huge pages allocated = %d\n" , (atoi (nr_hugepages))); + goto close_fd; + } + +ksft_test_result_pass ("Memory compaction succeeded. No of huge pages allocated = %d\n" , + (atoi (nr_hugepages))); + ret =0 ; close_fd:close (fd); -printf ("Not OK. Compaction test failed." ); -return -1 ; +return ret; }int main (int argc,char **argv) {struct rlimit lim; -struct map_list *list, *entry; +struct map_list *list =NULL , *entry;size_t page_size, i;void *map =NULL ;unsigned long mem_free =0 ;unsigned long hugepage_size =0 ;long mem_fragmentable_MB =0 ; -if (prereq () !=0 ) { -printf ("Either the sysctl compact_unevictable_allowed is not\n" -"set to 1 or couldn't read the proc file.\n" -"Skipping the test\n" ); -return KSFT_SKIP ; - } +ksft_print_header (); + +if (prereq () !=0 ) +return ksft_exit_pass (); + +ksft_set_plan (1 ); lim.rlim_cur =RLIM_INFINITY ; lim.rlim_max =RLIM_INFINITY ; -if (setrlimit (RLIMIT_MEMLOCK , &lim)) { -perror ("Failed to set rlimit:\n" ); -return -1 ; - } +if (setrlimit (RLIMIT_MEMLOCK , &lim)) +ksft_exit_fail_msg ("Failed to set rlimit: %s\n" ,strerror (errno)); page_size =getpagesize (); - list =NULL ; - -if (read_memory_info (&mem_free, &hugepage_size) !=0 ) { -printf ("ERROR: Cannot read meminfo\n" ); -return -1 ; - } +if (read_memory_info (&mem_free, &hugepage_size) !=0 ) +ksft_exit_fail_msg ("Failed to get meminfo\n" ); mem_fragmentable_MB = mem_free *0.8 /1024 ;
@@ -227,7 +224,7 @@ int main(int argc, char **argv) }if (check_compaction (mem_free, hugepage_size) ==0 ) -return 0 ; +return ksft_exit_pass (); -return -1 ; +return ksft_exit_fail (); }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 76/217 selftests/mm: log a consistent test name for check_compaction
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Mark Brown <[email protected]>
[ Upstream commit f3b7568c49420d2dcd251032c9ca1e069ec8a6c9 ]
Every test result report in the compaction test prints a distinct log messae, and some of the reports print a name that varies at runtime. This causes problems for automation since a lot of automation software uses the printed string as the name of the test, if the name varies from run to run and from pass to fail then the automation software can't identify that a test changed result or that the same tests are being run.
Refactor the logging to use a consistent name when printing the result of the test, printing the existing messages as diagnostic information instead so they are still available for people trying to interpret the results.
Stable-dep-of: d4202e66a4b1 ("selftests/mm: compaction_test: fix bogus test success on Aarch64")
--- tools/testing/selftests/vm/compaction_test.c | 35 +++++++++++--------- 1 file changed, 19 insertions(+), 16 deletions(-)
tools/testing/selftests/vm/compaction_test.c +19 -16
@@ -95,14 +95,15 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) fd =open ("/proc/sys/vm/nr_hugepages" ,O_RDWR |O_NONBLOCK );if (fd <0 ) { -ksft_test_result_fail ("Failed to open /proc/sys/vm/nr_hugepages: %s\n" , -strerror (errno)); -return -1 ; +ksft_print_msg ("Failed to open /proc/sys/vm/nr_hugepages: %s\n" , +strerror (errno)); + ret =-1 ; + goto out; }if (read (fd, initial_nr_hugepages,sizeof (initial_nr_hugepages)) <=0 ) { -ksft_test_result_fail ("Failed to read from /proc/sys/vm/nr_hugepages: %s\n" , -strerror (errno)); +ksft_print_msg ("Failed to read from /proc/sys/vm/nr_hugepages: %s\n" , +strerror (errno)); goto close_fd; }
@@ -110,8 +111,8 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size)/* Start with the initial condition of 0 huge pages*/ if (write (fd,"0" ,sizeof (char )) !=sizeof (char )) { -ksft_test_result_fail ("Failed to write 0 to /proc/sys/vm/nr_hugepages: %s\n" , -strerror (errno)); +ksft_print_msg ("Failed to write 0 to /proc/sys/vm/nr_hugepages: %s\n" , +strerror (errno)); goto close_fd; }
@@ -120,16 +121,16 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size)/* Request a large number of huge pages. The Kernel will allocate as much as it can */ if (write (fd,"100000" , (6 *sizeof (char ))) != (6 *sizeof (char ))) { -ksft_test_result_fail ("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n" , -strerror (errno)); +ksft_print_msg ("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n" , +strerror (errno)); goto close_fd; }lseek (fd,0 ,SEEK_SET );if (read (fd, nr_hugepages,sizeof (nr_hugepages)) <=0 ) { -ksft_test_result_fail ("Failed to re-read from /proc/sys/vm/nr_hugepages: %s\n" , -strerror (errno)); +ksft_print_msg ("Failed to re-read from /proc/sys/vm/nr_hugepages: %s\n" , +strerror (errno)); goto close_fd; }
@@ -141,24 +142,26 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size)if (write (fd, initial_nr_hugepages,strlen (initial_nr_hugepages)) !=strlen (initial_nr_hugepages)) { -ksft_test_result_fail ("Failed to write value to /proc/sys/vm/nr_hugepages: %s\n" , -strerror (errno)); +ksft_print_msg ("Failed to write value to /proc/sys/vm/nr_hugepages: %s\n" , +strerror (errno)); goto close_fd; } +ksft_print_msg ("Number of huge pages allocated = %d\n" , +atoi (nr_hugepages)); +if (compaction_index >3 ) {ksft_print_msg ("ERROR: Less that 1/%d of memory is available\n" "as huge pages\n" , compaction_index); -ksft_test_result_fail ("No of huge pages allocated = %d\n" , (atoi (nr_hugepages))); goto close_fd; } -ksft_test_result_pass ("Memory compaction succeeded. No of huge pages allocated = %d\n" , - (atoi (nr_hugepages))); ret =0 ; close_fd:close (fd); + out: +ksft_test_result (ret ==0 ,"check_compaction\n" );return ret; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 77/217 selftests/mm: compaction_test: fix bogus test success on Aarch64
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Dev Jain <[email protected]>
[ Upstream commit d4202e66a4b1fe6968f17f9f09bbc30d08f028a1 ]
Patch series "Fixes for compaction_test", v2.
The compaction_test memory selftest introduces fragmentation in memory and then tries to allocate as many hugepages as possible. This series addresses some problems.
On Aarch64, if nr_hugepages == 0, then the test trivially succeeds since compaction_index becomes 0, which is less than 3, due to no division by zero exception being raised. We fix that by checking for division by zero.
Secondly, correctly set the number of hugepages to zero before trying to set a large number of them.
Now, consider a situation in which, at the start of the test, a non-zero number of hugepages have been already set (while running the entire selftests/mm suite, or manually by the admin). The test operates on 80% of memory to avoid OOM-killer invocation, and because some memory is already blocked by hugepages, it would increase the chance of OOM-killing. Also, since mem_free used in check_compaction() is the value before we set nr_hugepages to zero, the chance that the compaction_index will be small is very high if the preset nr_hugepages was high, leading to a bogus test success.
This patch (of 3):
Currently, if at runtime we are not able to allocate a huge page, the test will trivially pass on Aarch64 due to no exception being raised on division by zero while computing compaction_index. Fix that by checking for nr_hugepages == 0. Anyways, in general, avoid a division by zero by exiting the program beforehand. While at it, fix a typo, and handle the case where the number of hugepages may overflow an integer.
--- tools/testing/selftests/vm/compaction_test.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-)
tools/testing/selftests/vm/compaction_test.c +13 -7
@@ -82,12 +82,13 @@ int prereq(void)return -1 ; } -int check_compaction (unsigned long mem_free,unsigned int hugepage_size) +int check_compaction (unsigned long mem_free,unsigned long hugepage_size) { +unsigned long nr_hugepages_ul;int fd, ret =-1 ;int compaction_index =0 ; -char initial_nr_hugepages[10 ] = {0 }; -char nr_hugepages[10 ] = {0 }; +char initial_nr_hugepages[20 ] = {0 }; +char nr_hugepages[20 ] = {0 };/* We want to test with 80% of available memory. Else, OOM killer comes in to play */
@@ -136,7 +137,12 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size)/* We should have been able to request at least 1/3 rd of the memory in huge pages */ - compaction_index = mem_free/(atoi (nr_hugepages) * hugepage_size); + nr_hugepages_ul =strtoul (nr_hugepages,NULL ,10 ); +if (!nr_hugepages_ul) { +ksft_print_msg ("ERROR: No memory is available as huge pages\n" ); + goto close_fd; + } + compaction_index = mem_free/(nr_hugepages_ul * hugepage_size);lseek (fd,0 ,SEEK_SET );
@@ -147,11 +153,11 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) goto close_fd; } -ksft_print_msg ("Number of huge pages allocated = %d\n" , -atoi (nr_hugepages)); +ksft_print_msg ("Number of huge pages allocated = %lu\n" , + nr_hugepages_ul);if (compaction_index >3 ) { -ksft_print_msg ("ERROR: Less that 1/%d of memory is available\n" +ksft_print_msg ("ERROR: Less than 1/%d of memory is available\n" "as huge pages\n" , compaction_index); goto close_fd; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 78/217 wifi: ath10k: fix QCOM_RPROC_COMMON dependency
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Dmitry Baryshkov <[email protected]>
[ Upstream commit 21ae74e1bf18331ae5e279bd96304b3630828009 ]
If ath10k_snoc is built-in, while Qualcomm remoteprocs are built as modules, compilation fails with:
/usr/bin/aarch64-linux-gnu-ld: drivers/net/wireless/ath/ath10k/snoc.o: in function `ath10k_modem_init':drivers/net/wireless/ath/ath10k/snoc.c:1534: undefined reference to qcom_register_ssr_notifier' /usr/bin/aarch64-linux-gnu-ld: drivers/net/wireless/ath/ath10k/snoc.o: in function ath10k_modem_deinit':drivers/net/wireless/ath/ath10k/snoc.c:1551: undefined reference to `qcom_unregister_ssr_notifier'
Add corresponding dependency to ATH10K_SNOC Kconfig entry so that it's built as module if QCOM_RPROC_COMMON is built as module too.
--- drivers/net/wireless/ath/ath10k/Kconfig | 1 + 1 file changed, 1 insertion(+)
drivers/net/wireless/ath/ath10k/Kconfig +1 -0
@@ -44,6 +44,7 @@ config ATH10K_SNOC tristate "Qualcomm ath10k SNOC support" depends on ATH10K depends on ARCH_QCOM || COMPILE_TEST + depends on QCOM_RPROC_COMMON || QCOM_RPROC_COMMON=n select QCOM_SCM select QCOM_QMI_HELPERS help
Greg Kroah-Hartman
maintainerPATCH 79/217 btrfs: remove unnecessary prototype declarations at disk-io.c
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Filipe Manana <[email protected]>
[ Upstream commit 184533e3618f4d0b382c1ef3de0ce34e849005d7 ]
We have a few static functions at disk-io.c for which we have a forward declaration of their prototype, but it's not needed because all those functions are defined before they are called, so remove them.
Stable-dep-of: fb33eb2ef0d8 ("btrfs: fix leak of qgroup extent records after transaction abort")
--- fs/btrfs/disk-io.c | 9 --------- 1 file changed, 9 deletions(-)
fs/btrfs/disk-io.c +0 -9
@@ -51,15 +51,6 @@ BTRFS_SUPER_FLAG_METADUMP |\ BTRFS_SUPER_FLAG_METADUMP_V2) -static void btrfs_destroy_ordered_extents (struct btrfs_root *root); -static int btrfs_destroy_delayed_refs (struct btrfs_transaction *trans, -struct btrfs_fs_info *fs_info); -static void btrfs_destroy_delalloc_inodes (struct btrfs_root *root); -static int btrfs_destroy_marked_extents (struct btrfs_fs_info *fs_info, -struct extent_io_tree *dirty_pages, -int mark); -static int btrfs_destroy_pinned_extent (struct btrfs_fs_info *fs_info, -struct extent_io_tree *pinned_extents);static int btrfs_cleanup_transaction (struct btrfs_fs_info *fs_info);static void btrfs_error_commit_super (struct btrfs_fs_info *fs_info);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 80/217 btrfs: make btrfs_destroy_delayed_refs() return void
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Filipe Manana <[email protected]>
[ Upstream commit 99f09ce309b8307ce8dca209f936e99a7c332214 ]
btrfs_destroy_delayed_refs() always returns 0 and its single caller does not check its return value, as it also returns void, and so does the callers' caller and so on. This is because we are in the transaction abort path, where we have no way to deal with errors (we are in a critical situation) and all cleanup of resources works in a best effort fashion. So make btrfs_destroy_delayed_refs() return void.
Stable-dep-of: fb33eb2ef0d8 ("btrfs: fix leak of qgroup extent records after transaction abort")
--- fs/btrfs/disk-io.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-)
fs/btrfs/disk-io.c +3 -6
@@ -4939,13 +4939,12 @@ static void btrfs_destroy_all_ordered_extents(struct btrfs_fs_info *fs_info)btrfs_wait_ordered_roots (fs_info,U64_MAX ,0 , (u64)-1 ); } -static int btrfs_destroy_delayed_refs (struct btrfs_transaction *trans, -struct btrfs_fs_info *fs_info) +static void btrfs_destroy_delayed_refs (struct btrfs_transaction *trans, +struct btrfs_fs_info *fs_info) {struct rb_node *node;struct btrfs_delayed_ref_root *delayed_refs;struct btrfs_delayed_ref_node *ref; -int ret =0 ; delayed_refs = &trans->delayed_refs;
@@ -4953,7 +4952,7 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,if (atomic_read (&delayed_refs->num_entries) ==0 ) {spin_unlock (&delayed_refs->lock);btrfs_debug (fs_info,"delayed_refs has NO entry" ); -return ret; +return ; }while ((node =rb_first_cached (&delayed_refs->href_root)) !=NULL ) {
@@ -5015,8 +5014,6 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,btrfs_qgroup_destroy_extent_records (trans);spin_unlock (&delayed_refs->lock); - -return ret; }static void btrfs_destroy_delalloc_inodes (struct btrfs_root *root)
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 81/217 btrfs: fix leak of qgroup extent records after transaction abort
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Filipe Manana <[email protected]>
[ Upstream commit fb33eb2ef0d88e75564983ef057b44c5b7e4fded ]
Qgroup extent records are created when delayed ref heads are created and then released after accounting extents at btrfs_qgroup_account_extents(), called during the transaction commit path.
If a transaction is aborted we free the qgroup records by calling btrfs_qgroup_destroy_extent_records() at btrfs_destroy_delayed_refs(), unless we don't have delayed references. We are incorrectly assuming that no delayed references means we don't have qgroup extents records.
We can currently have no delayed references because we ran them all during a transaction commit and the transaction was aborted after that due to some error in the commit path.
So fix this by ensuring we btrfs_qgroup_destroy_extent_records() at btrfs_destroy_delayed_refs() even if we don't have any delayed references.
--- fs/btrfs/disk-io.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-)
fs/btrfs/disk-io.c +1 -9
@@ -4943,18 +4943,10 @@ static void btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, struct btrfs_fs_info *fs_info) {struct rb_node *node; -struct btrfs_delayed_ref_root *delayed_refs; +struct btrfs_delayed_ref_root *delayed_refs = &trans->delayed_refs;struct btrfs_delayed_ref_node *ref; - delayed_refs = &trans->delayed_refs; -spin_lock (&delayed_refs->lock); -if (atomic_read (&delayed_refs->num_entries) ==0 ) { -spin_unlock (&delayed_refs->lock); -btrfs_debug (fs_info,"delayed_refs has NO entry" ); -return ; - } -while ((node =rb_first_cached (&delayed_refs->href_root)) !=NULL ) {struct btrfs_delayed_ref_head *head;struct rb_node *n;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 82/217 nilfs2: return the mapped address from nilfs_get_page()
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Matthew Wilcox (Oracle) <[email protected]>
[ Upstream commit 09a46acb3697e50548bb265afa1d79163659dd85 ]
In prepartion for switching from kmap() to kmap_local(), return the kmap address from nilfs_get_page() instead of having the caller look up page_address().
Stable-dep-of: 7373a51e7998 ("nilfs2: fix nilfs_empty_dir() misjudgment and long loop on I/O errors")
--- fs/nilfs2/dir.c | 57 +++++++++++++++++++++++-------------------------- 1 file changed, 27 insertions(+), 30 deletions(-)
fs/nilfs2/dir.c +27 -30
@@ -186,19 +186,24 @@ static bool nilfs_check_page(struct page *page)return false; } -static struct page *nilfs_get_page (struct inode *dir,unsigned long n) +static void *nilfs_get_page (struct inode *dir,unsigned long n, +struct page **pagep) {struct address_space *mapping = dir->i_mapping;struct page *page =read_mapping_page (mapping, n,NULL ); +void *kaddr; -if (!IS_ERR (page)) { -kmap (page); -if (unlikely (!PageChecked (page))) { -if (!nilfs_check_page (page)) - goto fail; - } +if (IS_ERR (page)) +return page; + + kaddr =kmap (page); +if (unlikely (!PageChecked (page))) { +if (!nilfs_check_page (page)) + goto fail; } -return page; + + *pagep = page; +return kaddr; fail:nilfs_put_page (page);
@@ -275,14 +280,14 @@ static int nilfs_readdir(struct file *file, struct dir_context *ctx)for ( ; n < npages; n++, offset =0 ) {char *kaddr, *limit;struct nilfs_dir_entry *de; -struct page *page =nilfs_get_page (inode, n); +struct page *page; -if (IS_ERR (page)) { + kaddr =nilfs_get_page (inode, n, &page); +if (IS_ERR (kaddr)) {nilfs_error (sb,"bad page in #%lu" , inode->i_ino); ctx->pos +=PAGE_SIZE - offset;return -EIO ; } - kaddr =page_address (page); de = (struct nilfs_dir_entry *)(kaddr + offset); limit = kaddr +nilfs_last_byte (inode, n) -NILFS_DIR_REC_LEN (1 );
@@ -345,11 +350,9 @@ nilfs_find_entry(struct inode *dir, const struct qstr *qstr, start =0 ; n = start; do { - char *kaddr; + char *kaddr = nilfs_get_page(dir, n, &page); - page = nilfs_get_page(dir, n); - if (!IS_ERR(page)) { - kaddr = page_address(page); + if (!IS_ERR(kaddr)) { de = (struct nilfs_dir_entry *)kaddr; kaddr += nilfs_last_byte(dir, n) - reclen; while ((char *) de <= kaddr) {
@@ -387,15 +390,11 @@ nilfs_find_entry(struct inode *dir, const struct qstr *qstr,struct nilfs_dir_entry *nilfs_dotdot (struct inode *dir,struct page **p) { -struct page *page =nilfs_get_page (dir,0 ); -struct nilfs_dir_entry *de =NULL ; +struct nilfs_dir_entry *de =nilfs_get_page (dir,0 , p); -if (!IS_ERR (page)) { - de =nilfs_next_entry ( - (struct nilfs_dir_entry *)page_address (page)); - *p = page; - } -return de; +if (IS_ERR (de)) +return NULL ; +return nilfs_next_entry (de); }ino_t nilfs_inode_by_name (struct inode *dir,const struct qstr *qstr)
@@ -459,12 +458,11 @@ int nilfs_add_link(struct dentry *dentry, struct inode *inode)for (n =0 ; n <= npages; n++) {char *dir_end; - page =nilfs_get_page (dir, n); - err =PTR_ERR (page); -if (IS_ERR (page)) + kaddr =nilfs_get_page (dir, n, &page); + err =PTR_ERR (kaddr); +if (IS_ERR (kaddr)) goto out;lock_page (page); - kaddr =page_address (page); dir_end = kaddr +nilfs_last_byte (dir, n); de = (struct nilfs_dir_entry *)kaddr; kaddr +=PAGE_SIZE - reclen;
@@ -627,11 +625,10 @@ int nilfs_empty_dir(struct inode *inode)char *kaddr;struct nilfs_dir_entry *de; - page =nilfs_get_page (inode, i); -if (IS_ERR (page)) + kaddr =nilfs_get_page (inode, i, &page); +if (IS_ERR (kaddr))continue ; - kaddr =page_address (page); de = (struct nilfs_dir_entry *)kaddr; kaddr +=nilfs_last_byte (inode, i) -NILFS_DIR_REC_LEN (1 );
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 83/217 nilfs2: fix nilfs_empty_dir() misjudgment and long loop on I/O errors
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ryusuke Konishi <[email protected]>
[ Upstream commit 7373a51e7998b508af7136530f3a997b286ce81c ]
The error handling in nilfs_empty_dir() when a directory folio/page read fails is incorrect, as in the old ext2 implementation, and if the folio/page cannot be read or nilfs_check_folio() fails, it will falsely determine the directory as empty and corrupt the file system.
In addition, since nilfs_empty_dir() does not immediately return on a failed folio/page read, but continues to loop, this can cause a long loop with I/O if i_size of the directory's inode is also corrupted, causing the log writer thread to wait and hang, as reported by syzbot.
Fix these issues by making nilfs_empty_dir() immediately return a false value (0) if it fails to get a directory folio/page.
--- fs/nilfs2/dir.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
fs/nilfs2/dir.c +1 -1
@@ -627,7 +627,7 @@ int nilfs_empty_dir(struct inode *inode) kaddr =nilfs_get_page (inode, i, &page);if (IS_ERR (kaddr)) -continue ; +return 0 ; de = (struct nilfs_dir_entry *)kaddr; kaddr +=nilfs_last_byte (inode, i) -NILFS_DIR_REC_LEN (1 );
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 84/217 io_uring: check for non-NULL file pointer in io_file_can_poll()
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jens Axboe <[email protected]>
commit 5fc16fa5f13b3c06fdb959ef262050bd810416a2 upstream.
In earlier kernels, it was possible to trigger a NULL pointer dereference off the forced async preparation path, if no file had been assigned. The trace leading to that looks as follows:
BUG: kernel NULL pointer dereference, address: 00000000000000b0 PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP CPU: 67 PID: 1633 Comm: buf-ring-invali Not tainted 6.8.0-rc3+ #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS unknown 2/2/2022 RIP: 0010:io_buffer_select+0xc3/0x210 Code: 00 00 48 39 d1 0f 82 ae 00 00 00 48 81 4b 48 00 00 01 00 48 89 73 70 0f b7 50 0c 66 89 53 42 85 ed 0f 85 d2 00 00 00 48 8b 13 <48> 8b 92 b0 00 00 00 48 83 7a 40 00 0f 84 21 01 00 00 4c 8b 20 5b RSP: 0018:ffffb7bec38c7d88 EFLAGS: 00010246 RAX: ffff97af2be61000 RBX: ffff97af234f1700 RCX: 0000000000000040 RDX: 0000000000000000 RSI: ffff97aecfb04820 RDI: ffff97af234f1700 RBP: 0000000000000000 R08: 0000000000200030 R09: 0000000000000020 R10: ffffb7bec38c7dc8 R11: 000000000000c000 R12: ffffb7bec38c7db8 R13: ffff97aecfb05800 R14: ffff97aecfb05800 R15: ffff97af2be5e000 FS: 00007f852f74b740(0000) GS:ffff97b1eeec0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000000b0 CR3: 000000016deab005 CR4: 0000000000370ef0 Call Trace: <TASK> ? __die+0x1f/0x60 ? page_fault_oops+0x14d/0x420 ? do_user_addr_fault+0x61/0x6a0 ? exc_page_fault+0x6c/0x150 ? asm_exc_page_fault+0x22/0x30 ? io_buffer_select+0xc3/0x210 __io_import_iovec+0xb5/0x120 io_readv_prep_async+0x36/0x70 io_queue_sqe_fallback+0x20/0x260 io_submit_sqes+0x314/0x630 __do_sys_io_uring_enter+0x339/0xbc0 ? __do_sys_io_uring_register+0x11b/0xc50 ? vm_mmap_pgoff+0xce/0x160 do_syscall_64+0x5f/0x180 entry_SYSCALL_64_after_hwframe+0x46/0x4e RIP: 0033:0x55e0a110a67e Code: ba cc 00 00 00 45 31 c0 44 0f b6 92 d0 00 00 00 31 d2 41 b9 08 00 00 00 41 83 e2 01 41 c1 e2 04 41 09 c2 b8 aa 01 00 00 0f 05 <c3> 90 89 30 eb a9 0f 1f 40 00 48 8b 42 20 8b 00 a8 06 75 af 85 f6
because the request is marked forced ASYNC and has a bad file fd, and hence takes the forced async prep path.
Current kernels with the request async prep cleaned up can no longer hit this issue, but for ease of backporting, let's add this safety check in here too as it really doesn't hurt. For both cases, this will inevitably end with a CQE posted with -EBADF.
--- io_uring/kbuf.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
io_uring/kbuf.c +2 -1
@@ -154,7 +154,8 @@ static void __user *io_ring_buffer_selec req->buf_list = bl; req->buf_index = buf->bid; -if (issue_flags &IO_URING_F_UNLOCKED || !file_can_poll (req->file)) { +if (issue_flags &IO_URING_F_UNLOCKED || + (req->file && !file_can_poll (req->file))) {/* * If we came in unlocked, we have no choice but to consume the * buffer here, otherwise nothing ensures that the buffer won't
Greg Kroah-Hartman
maintainerPATCH 67/217 firmware: qcom_scm: disable clocks if qcom_scm_bw_enable() fails
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Gabor Juhos <[email protected]>
[ Upstream commit 0c50b7fcf2773b4853e83fc15aba1a196ba95966 ]
There are several functions which are calling qcom_scm_bw_enable() then returns immediately if the call fails and leaves the clocks enabled.
Change the code of these functions to disable clocks when the qcom_scm_bw_enable() call fails. This also fixes a possible dma buffer leak in the qcom_scm_pas_init_image() function.
Compile tested only due to lack of hardware with interconnect support.
--- drivers/firmware/qcom_scm.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-)
drivers/firmware/qcom_scm.c +12 -6
@@ -495,13 +495,14 @@ int qcom_scm_pas_init_image(u32 peripheral, const void *metadata, size_t size, ret =qcom_scm_bw_enable ();if (ret) -return ret; + goto disable_clk; desc.args[1 ] = mdata_phys; ret =qcom_scm_call (__scm->dev, &desc, &res); -qcom_scm_bw_disable (); + +disable_clk:qcom_scm_clk_disable (); out:
@@ -563,10 +564,12 @@ int qcom_scm_pas_mem_setup(u32 peripheral, phys_addr_t addr, phys_addr_t size) ret =qcom_scm_bw_enable ();if (ret) -return ret; + goto disable_clk; ret =qcom_scm_call (__scm->dev, &desc, &res);qcom_scm_bw_disable (); + +disable_clk:qcom_scm_clk_disable ();return ret ? : res.result[0 ];
@@ -598,10 +601,12 @@ int qcom_scm_pas_auth_and_reset(u32 peripheral) ret =qcom_scm_bw_enable ();if (ret) -return ret; + goto disable_clk; ret =qcom_scm_call (__scm->dev, &desc, &res);qcom_scm_bw_disable (); + +disable_clk:qcom_scm_clk_disable ();return ret ? : res.result[0 ];
@@ -632,11 +637,12 @@ int qcom_scm_pas_shutdown(u32 peripheral) ret =qcom_scm_bw_enable ();if (ret) -return ret; + goto disable_clk; ret =qcom_scm_call (__scm->dev, &desc, &res); -qcom_scm_bw_disable (); + +disable_clk:qcom_scm_clk_disable ();return ret ? : res.result[0 ];
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 85/217 USB: class: cdc-wdm: Fix CPU lockup caused by excessive log messages
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Alan Stern <[email protected]>
commit 22f00812862564b314784167a89f27b444f82a46 upstream.
The syzbot fuzzer found that the interrupt-URB completion callback in the cdc-wdm driver was taking too long, and the driver's immediate resubmission of interrupt URBs with -EPROTO status combined with the dummy-hcd emulation to cause a CPU lockup:
cdc_wdm 1-1:1.0: nonzero urb status received: -71cdc_wdm 1-1:1.0: wdm_int_callback - 0 bytes
watchdog: BUG: soft lockup - CPU#0 stuck for 26s! [syz-executor782:6625] CPU#0 Utilization every 4s during lockup: #1: 98% system, 0% softirq, 3% hardirq, 0% idle #2: 98% system, 0% softirq, 3% hardirq, 0% idle #3: 98% system, 0% softirq, 3% hardirq, 0% idle #4: 98% system, 0% softirq, 3% hardirq, 0% idle #5: 98% system, 1% softirq, 3% hardirq, 0% idle Modules linked in: irq event stamp: 73096 hardirqs last enabled at (73095): [<ffff80008037bc00>] console_emit_next_record kernel/printk/printk.c:2935 [inline] hardirqs last enabled at (73095): [<ffff80008037bc00>] console_flush_all+0x650/0xb74 kernel/printk/printk.c:2994 hardirqs last disabled at (73096): [<ffff80008af10b00>] __el1_irq arch/arm64/kernel/entry-common.c:533 [inline] hardirqs last disabled at (73096): [<ffff80008af10b00>] el1_interrupt+0x24/0x68 arch/arm64/kernel/entry-common.c:551 softirqs last enabled at (73048): [<ffff8000801ea530>] softirq_handle_end kernel/softirq.c:400 [inline] softirqs last enabled at (73048): [<ffff8000801ea530>] handle_softirqs+0xa60/0xc34 kernel/softirq.c:582 softirqs last disabled at (73043): [<ffff800080020de8>] __do_softirq+0x14/0x20 kernel/softirq.c:588 CPU: 0 PID: 6625 Comm: syz-executor782 Tainted: G W 6.10.0-rc2-syzkaller-g8867bbd4a056 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/02/2024
Testing showed that the problem did not occur if the two error messages -- the first two lines above -- were removed; apparently adding material to the kernel log takes a surprisingly large amount of time.
In any case, the best approach for preventing these lockups and to avoid spamming the log with thousands of error messages per second is to ratelimit the two dev_err() calls. Therefore we replace them with dev_err_ratelimited().
--- drivers/usb/class/cdc-wdm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/usb/class/cdc-wdm.c +2 -2
@@ -266,14 +266,14 @@ static void wdm_int_callback(struct urbdev_err (&desc->intf->dev,"Stall on int endpoint\n" ); goto sw;/* halt is cleared in work */ default : -dev_err (&desc->intf->dev, +dev_err_ratelimited (&desc->intf->dev,"nonzero urb status received: %d\n" , status);break ; } }if (urb->actual_length <sizeof (struct usb_cdc_notification )) { -dev_err (&desc->intf->dev,"wdm_int_callback - %d bytes\n" , +dev_err_ratelimited (&desc->intf->dev,"wdm_int_callback - %d bytes\n" , urb->actual_length); goto exit; }
Greg Kroah-Hartman
maintainerPATCH 86/217 USB: xen-hcd: Traverse host/ when CONFIG_USB_XEN_HCD is selected
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: John Ernberg <[email protected]>
commit 8475ffcfb381a77075562207ce08552414a80326 upstream.
If no other USB HCDs are selected when compiling a small pure virutal machine, the Xen HCD driver cannot be built.
Fix it by traversing down host/ if CONFIG_USB_XEN_HCD is selected.
--- drivers/usb/Makefile | 1 + 1 file changed, 1 insertion(+)
drivers/usb/Makefile +1 -0
@@ -34,6 +34,7 @@ obj-$(CONFIG_USB_R8A66597_HCD) += host/ obj-$(CONFIG_USB_FSL_USB2) += host/ obj-$(CONFIG_USB_FOTG210_HCD) += host/ obj-$(CONFIG_USB_MAX3421_HCD) += host/ +obj-$(CONFIG_USB_XEN_HCD) += host/ obj-$(CONFIG_USB_C67X00_HCD) += c67x00/
Greg Kroah-Hartman
maintainerPATCH 87/217 usb: typec: tcpm: fix use-after-free case in tcpm_register_source_caps
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Amit Sunil Dhamne <[email protected]>
commit e7e921918d905544500ca7a95889f898121ba886 upstream.
There could be a potential use-after-free case in tcpm_register_source_caps(). This could happen when:
* new (say invalid) source caps are advertised
* the existing source caps are unregistered
* tcpm_register_source_caps() returns with an error as usb_power_delivery_register_capabilities() fails
This causes port->partner_source_caps to hold on to the now freed source caps.
Reset port->partner_source_caps value to NULL after unregistering existing source caps.
--- drivers/usb/typec/tcpm/tcpm.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/usb/typec/tcpm/tcpm.c +3 -1
@@ -2430,8 +2430,10 @@ static int tcpm_register_sink_caps(strucmemcpy (caps.pdo, port->sink_caps,sizeof (u32) * port->nr_sink_caps); caps.role =TYPEC_SINK ; -if (cap) +if (cap) {usb_power_delivery_unregister_capabilities (cap); + port->partner_source_caps =NULL ; + } cap =usb_power_delivery_register_capabilities (port->partner_pd, &caps);if (IS_ERR (cap))
Greg Kroah-Hartman
maintainerPATCH 88/217 usb: typec: tcpm: Ignore received Hard Reset in TOGGLING state
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kyle Tso <[email protected]>
commit fc8fb9eea94d8f476e15f3a4a7addeb16b3b99d6 upstream.
Similar to what fixed in Commit a6fe37f428c1 ("usb: typec: tcpm: Skip hard reset when in error recovery"), the handling of the received Hard Reset has to be skipped during TOGGLING state.
[ 4086.021288] VBUS off [ 4086.021295] pending state change SNK_READY -> SNK_UNATTACHED @ 650 ms [rev2 NONE_AMS] [ 4086.022113] VBUS VSAFE0V [ 4086.022117] state change SNK_READY -> SNK_UNATTACHED [rev2 NONE_AMS] [ 4086.022447] VBUS off [ 4086.022450] state change SNK_UNATTACHED -> SNK_UNATTACHED [rev2 NONE_AMS] [ 4086.023060] VBUS VSAFE0V [ 4086.023064] state change SNK_UNATTACHED -> SNK_UNATTACHED [rev2 NONE_AMS] [ 4086.023070] disable BIST MODE TESTDATA [ 4086.023766] disable vbus discharge ret:0 [ 4086.023911] Setting usb_comm capable false [ 4086.028874] Setting voltage/current limit 0 mV 0 mA [ 4086.028888] polarity 0 [ 4086.030305] Requesting mux state 0, usb-role 0, orientation 0 [ 4086.033539] Start toggling [ 4086.038496] state change SNK_UNATTACHED -> TOGGLING [rev2 NONE_AMS]
// This Hard Reset is unexpected
[ 4086.038499] Received hard reset [ 4086.038501] state change TOGGLING -> HARD_RESET_START [rev2 HARD_RESET]
--- drivers/usb/typec/tcpm/tcpm.c | 1 + 1 file changed, 1 insertion(+)
drivers/usb/typec/tcpm/tcpm.c +1 -0
@@ -5448,6 +5448,7 @@ static void _tcpm_pd_hard_reset(struct t port->tcpc->set_bist_data (port->tcpc, false);switch (port->state) { +case TOGGLING :case ERROR_RECOVERY :case PORT_RESET :case PORT_RESET_WAIT_OFF :
Greg Kroah-Hartman
maintainerPATCH 89/217 mei: me: release irq in mei_me_pci_resume error path
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Tomas Winkler <[email protected]>
commit 283cb234ef95d94c61f59e1cd070cd9499b51292 upstream.
The mei_me_pci_resume doesn't release irq on the error path, in case mei_start() fails.
--- drivers/misc/mei/pci-me.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/misc/mei/pci-me.c +3 -1
@@ -394,8 +394,10 @@ static int mei_me_pci_resume(struct devi } err =mei_restart (dev); -if (err) +if (err) { +free_irq (pdev->irq, dev);return err; + }/* Start timer if stopped in suspend */ schedule_delayed_work (&dev->timer_work,HZ );
Greg Kroah-Hartman
maintainerPATCH 90/217 tty: n_tty: Fix buffer offsets when lookahead is used
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ilpo Järvinen <[email protected]>
commit b19ab7ee2c4c1ec5f27c18413c3ab63907f7d55c upstream.
When lookahead has "consumed" some characters (la_count > 0), n_tty_receive_buf_standard() and n_tty_receive_buf_closing() for characters beyond the la_count are given wrong cp/fp offsets which leads to duplicating and losing some characters.
If la_count > 0, correct buffer pointers and make count consistent too (the latter is not strictly necessary to fix the issue but seems more logical to adjust all variables immediately to keep state consistent).
--- drivers/tty/n_tty.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-)
drivers/tty/n_tty.c +16 -6
@@ -1602,15 +1602,25 @@ static void __receive_buf(struct tty_strelse if (ldata->raw || (L_EXTPROC (tty) && !preops))n_tty_receive_buf_raw (tty, cp, fp, count);else if (tty->closing && !L_EXTPROC (tty)) { -if (la_count >0 ) +if (la_count >0 ) {n_tty_receive_buf_closing (tty, cp, fp, la_count, true); -if (count > la_count) -n_tty_receive_buf_closing (tty, cp, fp, count - la_count, false); + cp += la_count; +if (fp) + fp += la_count; + count -= la_count; + } +if (count >0 ) +n_tty_receive_buf_closing (tty, cp, fp, count, false); }else { -if (la_count >0 ) +if (la_count >0 ) {n_tty_receive_buf_standard (tty, cp, fp, la_count, true); -if (count > la_count) -n_tty_receive_buf_standard (tty, cp, fp, count - la_count, false); + cp += la_count; +if (fp) + fp += la_count; + count -= la_count; + } +if (count >0 ) +n_tty_receive_buf_standard (tty, cp, fp, count, false);flush_echoes (tty);if (tty->ops->flush_chars)
Greg Kroah-Hartman
maintainerPATCH 91/217 landlock: Fix d_parent walk
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Mickaël Salaün <[email protected]>
commit 88da52ccd66e65f2e63a6c35c9dff55d448ef4dc upstream.
The WARN_ON_ONCE() in collect_domain_accesses() can be triggered when trying to link a root mount point. This cannot work in practice because this directory is mounted, but the VFS check is done after the call to security_path_link().
Do not use source directory's d_parent when the source directory is the mount point.
--- security/landlock/fs.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-)
security/landlock/fs.c +11 -2
@@ -824,6 +824,7 @@ static int current_check_refer_path(strubool allow_parent1, allow_parent2;access_mask_t access_request_parent1, access_request_parent2;struct path mnt_dir; +struct dentry *old_parent;layer_mask_t layer_masks_parent1[LANDLOCK_NUM_ACCESS_FS ] = {}, layer_masks_parent2[LANDLOCK_NUM_ACCESS_FS ] = {};
@@ -870,9 +871,17 @@ static int current_check_refer_path(stru mnt_dir.mnt = new_dir->mnt; mnt_dir.dentry = new_dir->mnt->mnt_root; +/* +* old_dentry may be the root of the common mount point and +* !IS_ROOT(old_dentry) at the same time (e.g. with open_tree() and +* OPEN_TREE_CLONE). We do not need to call dget(old_parent) because +* we keep a reference to old_dentry. +*/ + old_parent = (old_dentry == mnt_dir.dentry) ? old_dentry : + old_dentry->d_parent; +/* new_dir->dentry is equal to new_dentry->d_parent */ - allow_parent1 =collect_domain_accesses (dom, mnt_dir.dentry, - old_dentry->d_parent, + allow_parent1 =collect_domain_accesses (dom, mnt_dir.dentry, old_parent, &layer_masks_parent1); allow_parent2 =collect_domain_accesses ( dom, mnt_dir.dentry, new_dir->dentry, &layer_masks_parent2);
Greg Kroah-Hartman
maintainerPATCH 92/217 jfs: xattr: fix buffer overflow for invalid xattr
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Greg Kroah-Hartman <[email protected]>
commit 7c55b78818cfb732680c4a72ab270cc2d2ee3d0f upstream.
When an xattr size is not what is expected, it is printed out to the kernel log in hex format as a form of debugging. But when that xattr size is bigger than the expected size, printing it out can cause an access off the end of the buffer.
Fix this all up by properly restricting the size of the debug hex dump in the kernel log.
--- fs/jfs/xattr.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
fs/jfs/xattr.c +3 -1
@@ -557,9 +557,11 @@ static int ea_get(struct inode *inode, s size_check:if (EALIST_SIZE (ea_buf->xattr) != ea_size) { +int size =min_t (int,EALIST_SIZE (ea_buf->xattr), ea_size); +printk (KERN_ERR "ea_get: invalid extended attribute\n" );print_hex_dump (KERN_ERR ,"" ,DUMP_PREFIX_ADDRESS ,16 ,1 , - ea_buf->xattr, ea_size,1 ); + ea_buf->xattr, size,1 );ea_release (inode, ea_buf); rc = -EIO ; goto clean_up;
Greg Kroah-Hartman
maintainerPATCH 93/217 xhci: Set correct transferred length for cancelled bulk transfers
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Mathias Nyman <[email protected]>
commit f0260589b439e2637ad54a2b25f00a516ef28a57 upstream.
The transferred length is set incorrectly for cancelled bulk transfer TDs in case the bulk transfer ring stops on the last transfer block with a 'Stop - Length Invalid' completion code.
length essentially ends up being set to the requested length:urb->actual_length = urb->transfer_buffer_length
Length for 'Stop - Length Invalid' cases should be the sum of all TRB transfer block lengths up to the one the ring stopped on, _excluding_ the one stopped on.
Fix this by always summing up TRB lengths for 'Stop - Length Invalid' bulk cases.
This issue was discovered by Alan Stern while debugging
https://bugzilla.kernel.org/show_bug.cgi?id=218890, but does not solve that bug. Issue is older than 4.10 kernel but fix won't apply to those due to major reworks in that area.
--- drivers/usb/host/xhci-ring.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)
drivers/usb/host/xhci-ring.c +2 -3
@@ -2506,9 +2506,8 @@ static int process_bulk_intr_td(struct x goto finish_td;case COMP_STOPPED_LENGTH_INVALID :/* stopped on ep trb with invalid length, exclude it */ - ep_trb_len =0 ; - remaining =0 ; -break ; + td->urb->actual_length =sum_trb_lengths (xhci, ep_ring, ep_trb); + goto finish_td;case COMP_USB_TRANSACTION_ERROR : if (xhci->quirks & XHCI_NO_SOFT_RETRY || (ep->err_count++ > MAX_SOFT_RETRY) ||
Greg Kroah-Hartman
maintainerPATCH 94/217 xhci: Apply reset resume quirk to Etron EJ188 xHCI host
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kuangyi Chiang <[email protected]>
commit 17bd54555c2aaecfdb38e2734149f684a73fa584 upstream.
As described in commit c877b3b2ad5c ("xhci: Add reset on resume quirk for asrock p67 host"), EJ188 have the same issue as EJ168, where completely dies on resume. So apply XHCI_RESET_ON_RESUME quirk to EJ188 as well.
--- drivers/usb/host/xhci-pci.c | 5 +++++ 1 file changed, 5 insertions(+)
drivers/usb/host/xhci-pci.c +5 -0
@@ -36,6 +36,7 @@#define PCI_VENDOR_ID_ETRON 0x1b6f#define PCI_DEVICE_ID_EJ168 0x7023 +#define PCI_DEVICE_ID_EJ188 0x7052#define PCI_DEVICE_ID_INTEL_LYNXPOINT_XHCI 0x8c31#define PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI 0x9c31
@@ -275,6 +276,10 @@ static void xhci_pci_quirks(struct devic xhci->quirks |=XHCI_TRUST_TX_LENGTH ; xhci->quirks |=XHCI_BROKEN_STREAMS ; } +if (pdev->vendor ==PCI_VENDOR_ID_ETRON && + pdev->device ==PCI_DEVICE_ID_EJ188 ) + xhci->quirks |=XHCI_RESET_ON_RESUME ; +if (pdev->vendor ==PCI_VENDOR_ID_RENESAS && pdev->device ==0x0014 ) { xhci->quirks |=XHCI_TRUST_TX_LENGTH ;
Greg Kroah-Hartman
maintainerPATCH 68/217 HID: i2c-hid: elan: Add ili9882t timing
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Cong Yang <[email protected]>
[ Upstream commit f2f43bf15d7aa3286eced18d5199ee579e2c2614 ]
The ili9882t is a TDDI IC (Touch with Display Driver). The datasheet specifies there should be 60ms between touch SDA sleep and panel RESX. Doug's series[1] allows panels and touchscreens to power on/off together, so we can add the 65 ms delay in i2c_hid_core_suspend before panel_unprepare.
Because ili9882t touchscrgeen is a panel follower, and needs to use vccio-supply instead of vcc33-supply, so set it NULL to ili9882t_chip_data, then not use vcc33 regulator.
[1]: https://lore.kernel.org/all/[email protected]
Stable-dep-of: 0eafc58f2194 ("HID: i2c-hid: elan: fix reset suspend current leakage")
--- drivers/hid/i2c-hid/i2c-hid-of-elan.c | 50 ++++++++++++++++++++------- 1 file changed, 38 insertions(+), 12 deletions(-)
drivers/hid/i2c-hid/i2c-hid-of-elan.c +38 -12
@@ -18,9 +18,11 @@#include "i2c-hid.h" struct elan_i2c_hid_chip_data { -unsigned int post_gpio_reset_delay_ms; +unsigned int post_gpio_reset_on_delay_ms; +unsigned int post_gpio_reset_off_delay_ms;unsigned int post_power_delay_ms;u16 hid_descriptor_address; +const char *main_supply_name; };struct i2c_hid_of_elan {
@@ -38,9 +40,11 @@ static int elan_i2c_hid_power_up(struct i2chid_ops *ops) container_of(ops, struct i2c_hid_of_elan, ops);int ret; - ret =regulator_enable (ihid_elan->vcc33); -if (ret) -return ret; +if (ihid_elan->vcc33) { + ret =regulator_enable (ihid_elan->vcc33); +if (ret) +return ret; + } ret =regulator_enable (ihid_elan->vccio);if (ret) {
@@ -52,8 +56,8 @@ static int elan_i2c_hid_power_up(struct i2chid_ops *ops)msleep (ihid_elan->chip_data->post_power_delay_ms);gpiod_set_value_cansleep (ihid_elan->reset_gpio,0 ); -if (ihid_elan->chip_data->post_gpio_reset_delay_ms) -msleep (ihid_elan->chip_data->post_gpio_reset_delay_ms); +if (ihid_elan->chip_data->post_gpio_reset_on_delay_ms) +msleep (ihid_elan->chip_data->post_gpio_reset_on_delay_ms);return 0 ; }
@@ -64,8 +68,12 @@ static void elan_i2c_hid_power_down(struct i2chid_ops *ops) container_of(ops, struct i2c_hid_of_elan, ops);gpiod_set_value_cansleep (ihid_elan->reset_gpio,1 ); +if (ihid_elan->chip_data->post_gpio_reset_off_delay_ms) +msleep (ihid_elan->chip_data->post_gpio_reset_off_delay_ms); +regulator_disable (ihid_elan->vccio); -regulator_disable (ihid_elan->vcc33); +if (ihid_elan->vcc33) +regulator_disable (ihid_elan->vcc33); } static int i2c_hid_of_elan_probe(struct i2c_client *client,
@@ -90,24 +98,42 @@ static int i2c_hid_of_elan_probe(struct i2c_client *client,if (IS_ERR (ihid_elan->vccio))return PTR_ERR (ihid_elan->vccio); - ihid_elan->vcc33 =devm_regulator_get (&client->dev,"vcc33" ); -if (IS_ERR (ihid_elan->vcc33)) -return PTR_ERR (ihid_elan->vcc33); - ihid_elan->chip_data =device_get_match_data (&client->dev); +if (ihid_elan->chip_data->main_supply_name) { + ihid_elan->vcc33 =devm_regulator_get (&client->dev, + ihid_elan->chip_data->main_supply_name); +if (IS_ERR (ihid_elan->vcc33)) +return PTR_ERR (ihid_elan->vcc33); + } +return i2c_hid_core_probe (client, &ihid_elan->ops, ihid_elan->chip_data->hid_descriptor_address,0 ); }static const struct elan_i2c_hid_chip_data elan_ekth6915_chip_data = { .post_power_delay_ms =1 , - .post_gpio_reset_delay_ms =300 , + .post_gpio_reset_on_delay_ms =300 , + .hid_descriptor_address =0x0001 , + .main_supply_name ="vcc33" , +}; + +static const struct elan_i2c_hid_chip_data ilitek_ili9882t_chip_data = { + .post_power_delay_ms =1 , + .post_gpio_reset_on_delay_ms =200 , + .post_gpio_reset_off_delay_ms =65 , .hid_descriptor_address =0x0001 , +/* +* this touchscreen is tightly integrated with the panel and assumes +* that the relevant power rails (other than the IO rail) have already +* been turned on by the panel driver because we're a panel follower. +*/ + .main_supply_name =NULL , };static const struct of_device_id elan_i2c_hid_of_match[] = { { .compatible ="elan,ekth6915" , .data = &elan_ekth6915_chip_data }, + { .compatible ="ilitek,ili9882t" , .data = &ilitek_ili9882t_chip_data }, { } };MODULE_DEVICE_TABLE (of, elan_i2c_hid_of_match);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 95/217 xhci: Handle TD clearing for multiple streams case
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Hector Martin <[email protected]>
commit 5ceac4402f5d975e5a01c806438eb4e554771577 upstream.
When multiple streams are in use, multiple TDs might be in flight when an endpoint is stopped. We need to issue a Set TR Dequeue Pointer for each, to ensure everything is reset properly and the caches cleared. Change the logic so that any N>1 TDs found active for different streams are deferred until after the first one is processed, calling xhci_invalidate_cancelled_tds() again from xhci_handle_cmd_set_deq() to queue another command until we are done with all of them. Also change the error/"should never happen" paths to ensure we at least clear any affected TDs, even if we can't issue a command to clear the hardware cache, and complain loudly with an xhci_warn() if this ever happens.
This problem case dates back to commit e9df17eb1408 ("USB: xhci: Correct assumptions about number of rings per endpoint.") early on in the XHCI driver's life, when stream support was first added.
It was then identified but not fixed nor made into a warning in commit 674f8438c121 ("xhci: split handling halted endpoints into two steps"), which added a FIXME comment for the problem case (without materially changing the behavior as far as I can tell, though the new logic made the problem more obvious).
Then later, in commit 94f339147fc3 ("xhci: Fix failure to give back some cached cancelled URBs."), it was acknowledged again.
[Mathias: commit 94f339147fc3 ("xhci: Fix failure to give back some cached cancelled URBs.") was a targeted regression fix to the previously mentioned patch. Users reported issues with usb stuck after unmounting/disconnecting UAS devices. This rolled back the TD clearing of multiple streams to its original state.]
Apparently the commit author was aware of the problem (yet still chose to submit it): It was still mentioned as a FIXME, an xhci_dbg() was added to log the problem condition, and the remaining issue was mentioned in the commit description. The choice of making the log type xhci_dbg() for what is, at this point, a completely unhandled and known broken condition is puzzling and unfortunate, as it guarantees that no actual users would see the log in production, thereby making it nigh undebuggable (indeed, even if you turn on DEBUG, the message doesn't really hint at there being a problem at all).
It took me *months* of random xHC crashes to finally find a reliable repro and be able to do a deep dive debug session, which could all have been avoided had this unhandled, broken condition been actually reported with a warning, as it should have been as a bug intentionally left in unfixed (never mind that it shouldn't have been left in at all).
Quoted 2 lines
Another fix to solve clearing the caches of all stream rings with cancelled TDs is needed, but not as urgent.
3 years after that statement and 14 years after the original bug was introduced, I think it's finally time to fix it. And maybe next time let's not leave bugs unfixed (that are actually worse than the original bug), and let's actually get people to review kernel commits please.
Fixes xHC crashes and IOMMU faults with UAS devices when handling errors/faults. Easiest repro is to use hdparm to mark an early sector (e.g. 1024) on a disk as bad, then cat /dev/sdX > /dev/null in a loop. At least in the case of JMicron controllers, the read errors end up having to cancel two TDs (for two queued requests to different streams) and the one that didn't get cleared properly ends up faulting the xHC entirely when it tries to access DMA pages that have since been unmapped, referred to by the stale TDs. This normally happens quickly (after two or three loops). After this fix, I left the cat in a loop running overnight and experienced no xHC failures, with all read errors recovered properly. Repro'd and tested on an Apple M1 Mac Mini (dwc3 host).
On systems without an IOMMU, this bug would instead silently corrupt freed memory, making this a security bug (even on systems with IOMMUs this could silently corrupt memory belonging to other USB devices on the same controller, so it's still a security bug). Given that the kernel autoprobes partition tables, I'm pretty sure a malicious USB device pretending to be a UAS device and reporting an error with the right timing could deliberately trigger a UAF and write to freed memory, with no user action.
[Mathias: Commit message and code comment edit, original at:]
https://lore.kernel.org/linux-usb/[email protected]/
--- drivers/usb/host/xhci-ring.c | 54 ++++++++++++++++++++++++++++++++++--------- drivers/usb/host/xhci.h | 1 2 files changed, 44 insertions(+), 11 deletions(-)
drivers/usb/host/xhci-ring.c +43 -11
@@ -987,13 +987,27 @@ static int xhci_invalidate_cancelled_tdsbreak ;case TD_DIRTY :/* TD is cached, clear it */ case TD_HALTED : +case TD_CLEARING_CACHE_DEFERRED : +if (cached_td) { +if (cached_td->urb->stream_id != td->urb->stream_id) { +/* Multiple streams case, defer move dq */ +xhci_dbg (xhci, +"Move dq deferred: stream %u URB %p\n" , + td->urb->stream_id, td->urb); + td->cancel_status =TD_CLEARING_CACHE_DEFERRED ; +break ; + } + +/* Should never happen, but clear the TD if it does */ +xhci_warn (xhci, +"Found multiple active URBs %p and %p in stream %u?\n" , + td->urb, cached_td->urb, + td->urb->stream_id); +td_to_noop (xhci, ring, cached_td, false); + cached_td->cancel_status =TD_CLEARED ; + } + td->cancel_status =TD_CLEARING_CACHE ; -if (cached_td) -/* FIXME stream case, several stopped rings */ -xhci_dbg (xhci, -"Move dq past stream %u URB %p instead of stream %u URB %p\n" , - td->urb->stream_id, td->urb, - cached_td->urb->stream_id, cached_td->urb); cached_td = td;break ; }
@@ -1013,10 +1027,16 @@ static int xhci_invalidate_cancelled_tdsif (err) {/* Failed to move past cached td, just set cached TDs to no-op */ list_for_each_entry_safe (td, tmp_td, &ep->cancelled_td_list, cancelled_td_list) { -if (td->cancel_status !=TD_CLEARING_CACHE ) +/* +* Deferred TDs need to have the deq pointer set after the above command +* completes, so if that failed we just give up on all of them (and +* complain loudly since this could cause issues due to caching). +*/ +if (td->cancel_status !=TD_CLEARING_CACHE && + td->cancel_status !=TD_CLEARING_CACHE_DEFERRED )continue ; -xhci_dbg (xhci,"Failed to clear cancelled cached URB %p, mark clear anyway\n" , - td->urb); +xhci_warn (xhci,"Failed to clear cancelled cached URB %p, mark clear anyway\n" , + td->urb);td_to_noop (xhci, ring, td, false); td->cancel_status =TD_CLEARED ; }
@@ -1304,6 +1324,7 @@ static void xhci_handle_cmd_set_deq(strustruct xhci_ep_ctx *ep_ctx;struct xhci_slot_ctx *slot_ctx;struct xhci_td *td, *tmp_td; +bool deferred = false; ep_index =TRB_TO_EP_INDEX (le32_to_cpu (trb->generic.field[3 ])); stream_id =TRB_TO_STREAM_ID (le32_to_cpu (trb->generic.field[2 ]));
@@ -1390,6 +1411,8 @@ static void xhci_handle_cmd_set_deq(struxhci_dbg (ep->xhci,"%s: Giveback cancelled URB %p TD\n" , __func__, td->urb);xhci_td_cleanup (ep->xhci, td, ep_ring, td->status); + }else if (td->cancel_status ==TD_CLEARING_CACHE_DEFERRED ) { + deferred = true; }else {xhci_dbg (ep->xhci,"%s: Keep cancelled URB %p TD as cancel_status is %d\n" , __func__, td->urb, td->cancel_status);
@@ -1399,8 +1422,17 @@ cleanup: ep->ep_state &= ~SET_DEQ_PENDING ; ep->queued_deq_seg =NULL ; ep->queued_deq_ptr =NULL ; -/* Restart any rings with pending URBs */ -ring_doorbell_for_active_rings (xhci, slot_id, ep_index); + +if (deferred) { +/* We have more streams to clear */ +xhci_dbg (ep->xhci,"%s: Pending TDs to clear, continuing with invalidation\n" , + __func__); +xhci_invalidate_cancelled_tds (ep); + }else { +/* Restart any rings with pending URBs */ +xhci_dbg (ep->xhci,"%s: All TDs cleared, ring doorbell\n" , __func__); +ring_doorbell_for_active_rings (xhci, slot_id, ep_index); + } } static void xhci_handle_cmd_reset_ep(struct xhci_hcd *xhci, int slot_id,
drivers/usb/host/xhci.h +1 -0
@@ -1556,6 +1556,7 @@ enum xhci_cancelled_td_status {TD_DIRTY =0 ,TD_HALTED ,TD_CLEARING_CACHE , +TD_CLEARING_CACHE_DEFERRED , TD_CLEARED, };
Greg Kroah-Hartman
maintainerPATCH 96/217 xhci: Apply broken streams quirk to Etron EJ188 xHCI host
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kuangyi Chiang <[email protected]>
commit 91f7a1524a92c70ffe264db8bdfa075f15bbbeb9 upstream.
As described in commit 8f873c1ff4ca ("xhci: Blacklist using streams on the Etron EJ168 controller"), EJ188 have the same issue as EJ168, where Streams do not work reliable on EJ188. So apply XHCI_BROKEN_STREAMS quirk to EJ188 as well.
--- drivers/usb/host/xhci-pci.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/usb/host/xhci-pci.c +3 -1
@@ -277,8 +277,10 @@ static void xhci_pci_quirks(struct devic xhci->quirks |=XHCI_BROKEN_STREAMS ; }if (pdev->vendor ==PCI_VENDOR_ID_ETRON && - pdev->device ==PCI_DEVICE_ID_EJ188 ) + pdev->device ==PCI_DEVICE_ID_EJ188 ) { xhci->quirks |=XHCI_RESET_ON_RESUME ; + xhci->quirks |=XHCI_BROKEN_STREAMS ; + }if (pdev->vendor ==PCI_VENDOR_ID_RENESAS && pdev->device ==0x0014 ) {
Greg Kroah-Hartman
maintainerPATCH 97/217 thunderbolt: debugfs: Fix margin debugfs node creation condition
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Aapo Vienamo <[email protected]>
commit 985cfe501b74f214905ab4817acee0df24627268 upstream.
The margin debugfs node controls the "Enable Margin Test" field of the lane margining operations. This field selects between either low or high voltage margin values for voltage margin test or left or right timing margin values for timing margin test.
According to the USB4 specification, whether or not the "Enable Margin Test" control applies, depends on the values of the "Independent High/Low Voltage Margin" or "Independent Left/Right Timing Margin" capability fields for voltage and timing margin tests respectively. The pre-existing condition enabled the debugfs node also in the case where both low/high or left/right margins are returned, which is incorrect. This change only enables the debugfs node in question, if the specific required capability values are met.
--- drivers/thunderbolt/debugfs.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
drivers/thunderbolt/debugfs.c +3 -2
@@ -927,8 +927,9 @@ static void margining_port_init(struct tdebugfs_create_file ("run" ,0600 , dir, port, &margining_run_fops);debugfs_create_file ("results" ,0600 , dir, port, &margining_results_fops);debugfs_create_file ("test" ,0600 , dir, port, &margining_test_fops); -if (independent_voltage_margins (usb4) || - (supports_time (usb4) &&independent_time_margins (usb4))) +if (independent_voltage_margins (usb4) ==USB4_MARGIN_CAP_0_VOLTAGE_HL || + (supports_time (usb4) && +independent_time_margins (usb4) ==USB4_MARGIN_CAP_1_TIME_LR ))debugfs_create_file ("margin" ,0600 , dir, port, &margining_margin_fops); }
Greg Kroah-Hartman
maintainerPATCH 98/217 scsi: mpi3mr: Fix ATA NCQ priority support
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Damien Le Moal <[email protected]>
commit 90e6f08915ec6efe46570420412a65050ec826b2 upstream.
The function mpi3mr_qcmd() of the mpi3mr driver is able to indicate to the HBA if a read or write command directed at an ATA device should be translated to an NCQ read/write command with the high prioiryt bit set when the request uses the RT priority class and the user has enabled NCQ priority through sysfs.
However, unlike the mpt3sas driver, the mpi3mr driver does not define the sas_ncq_prio_supported and sas_ncq_prio_enable sysfs attributes, so the ncq_prio_enable field of struct mpi3mr_sdev_priv_data is never actually set and NCQ Priority cannot ever be used.
Fix this by defining these missing atributes to allow a user to check if an ATA device supports NCQ priority and to enable/disable the use of NCQ priority. To do this, lift the function scsih_ncq_prio_supp() out of the mpt3sas driver and make it the generic SCSI SAS transport function sas_ata_ncq_prio_supported(). Nothing in that function is hardware specific, so this function can be used in both the mpt3sas driver and the mpi3mr driver.
--- drivers/scsi/mpi3mr/mpi3mr_app.c | 62 +++++++++++++++++++++++++++++++++++ drivers/scsi/mpt3sas/mpt3sas_base.h | 3 - drivers/scsi/mpt3sas/mpt3sas_ctl.c | 4 +- drivers/scsi/mpt3sas/mpt3sas_scsih.c | 23 ------------ drivers/scsi/scsi_transport_sas.c | 23 ++++++++++++ include/scsi/scsi_transport_sas.h | 2 + 6 files changed, 89 insertions(+), 28 deletions(-)
drivers/scsi/mpi3mr/mpi3mr_app.c +62 -0
@@ -1851,10 +1851,72 @@ persistent_id_show(struct device *dev, s }static DEVICE_ATTR_RO (persistent_id); +/** +* sas_ncq_prio_supported_show - Indicate if device supports NCQ priority +* @dev: pointer to embedded device +* @attr: sas_ncq_prio_supported attribute descriptor +* @buf: the buffer returned +* +* A sysfs 'read-only' sdev attribute, only works with SATA devices +*/ +static ssize_t +sas_ncq_prio_supported_show (struct device *dev, +struct device_attribute *attr,char *buf) +{ +struct scsi_device *sdev =to_scsi_device (dev); + +return sysfs_emit (buf,"%d\n" ,sas_ata_ncq_prio_supported (sdev)); +} +static DEVICE_ATTR_RO (sas_ncq_prio_supported); + +/** +* sas_ncq_prio_enable_show - send prioritized io commands to device +* @dev: pointer to embedded device +* @attr: sas_ncq_prio_enable attribute descriptor +* @buf: the buffer returned +* +* A sysfs 'read/write' sdev attribute, only works with SATA devices +*/ +static ssize_t +sas_ncq_prio_enable_show (struct device *dev, +struct device_attribute *attr,char *buf) +{ +struct scsi_device *sdev =to_scsi_device (dev); +struct mpi3mr_sdev_priv_data *sdev_priv_data = sdev->hostdata; + +if (!sdev_priv_data) +return 0 ; + +return sysfs_emit (buf,"%d\n" , sdev_priv_data->ncq_prio_enable); +} + +static ssize_t +sas_ncq_prio_enable_store (struct device *dev, +struct device_attribute *attr, +const char *buf,size_t count) +{ +struct scsi_device *sdev =to_scsi_device (dev); +struct mpi3mr_sdev_priv_data *sdev_priv_data = sdev->hostdata; +bool ncq_prio_enable =0 ; + +if (kstrtobool (buf, &ncq_prio_enable)) +return -EINVAL ; + +if (!sas_ata_ncq_prio_supported (sdev)) +return -EINVAL ; + + sdev_priv_data->ncq_prio_enable = ncq_prio_enable; + +return strlen (buf); +} +static DEVICE_ATTR_RW (sas_ncq_prio_enable); +static struct attribute *mpi3mr_dev_attrs[] = { &dev_attr_sas_address.attr, &dev_attr_device_handle.attr, &dev_attr_persistent_id.attr, + &dev_attr_sas_ncq_prio_supported.attr, + &dev_attr_sas_ncq_prio_enable.attr,NULL , };
drivers/scsi/mpt3sas/mpt3sas_base.h +0 -3
@@ -2045,9 +2045,6 @@ void mpt3sas_setup_direct_io(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd, struct _raid_device *raid_device, Mpi25SCSIIORequest_t *mpi_request); -/* NCQ Prio Handling Check */ -bool scsih_ncq_prio_supp (struct scsi_device *sdev); -void mpt3sas_setup_debugfs (struct MPT3SAS_ADAPTER *ioc);void mpt3sas_destroy_debugfs (struct MPT3SAS_ADAPTER *ioc);void mpt3sas_init_debugfs (void );
drivers/scsi/mpt3sas/mpt3sas_ctl.c +2 -2
@@ -4034,7 +4034,7 @@ sas_ncq_prio_supported_show(struct devic {struct scsi_device *sdev =to_scsi_device (dev); -return sysfs_emit (buf,"%d\n" ,scsih_ncq_prio_supp (sdev)); +return sysfs_emit (buf,"%d\n" ,sas_ata_ncq_prio_supported (sdev)); }static DEVICE_ATTR_RO (sas_ncq_prio_supported);
@@ -4069,7 +4069,7 @@ sas_ncq_prio_enable_store(struct deviceif (kstrtobool (buf, &ncq_prio_enable))return -EINVAL ; -if (!scsih_ncq_prio_supp (sdev)) +if (!sas_ata_ncq_prio_supported (sdev))return -EINVAL ; sas_device_priv_data->ncq_prio_enable = ncq_prio_enable;
drivers/scsi/mpt3sas/mpt3sas_scsih.c +0 -23
@@ -12591,29 +12591,6 @@ scsih_pci_mmio_enabled(struct pci_dev *preturn PCI_ERS_RESULT_RECOVERED ; } -/** -* scsih_ncq_prio_supp - Check for NCQ command priority support -* @sdev: scsi device struct -* -* This is called when a user indicates they would like to enable -* ncq command priorities. This works only on SATA devices. -*/ -bool scsih_ncq_prio_supp (struct scsi_device *sdev) -{ -struct scsi_vpd *vpd; -bool ncq_prio_supp = false; - -rcu_read_lock (); - vpd =rcu_dereference (sdev->vpd_pg89); -if (!vpd || vpd->len <214 ) - goto out; - - ncq_prio_supp = (vpd->data[213 ] >>4 ) &1 ; -out: -rcu_read_unlock (); - -return ncq_prio_supp; -}/* * The pci device ids are defined in mpi/mpi2_cnfg.h. */
drivers/scsi/scsi_transport_sas.c +23 -0
@@ -416,6 +416,29 @@ unsigned int sas_is_tlr_enabled(struct s }EXPORT_SYMBOL_GPL (sas_is_tlr_enabled); +/** +* sas_ata_ncq_prio_supported - Check for ATA NCQ command priority support +* @sdev: SCSI device +* +* Check if an ATA device supports NCQ priority using VPD page 89h (ATA +* Information). Since this VPD page is implemented only for ATA devices, +* this function always returns false for SCSI devices. +*/ +bool sas_ata_ncq_prio_supported (struct scsi_device *sdev) +{ +struct scsi_vpd *vpd; +bool ncq_prio_supported = false; + +rcu_read_lock (); + vpd =rcu_dereference (sdev->vpd_pg89); +if (vpd && vpd->len >=214 ) + ncq_prio_supported = (vpd->data[213 ] >>4 ) &1 ; +rcu_read_unlock (); + +return ncq_prio_supported; +} +EXPORT_SYMBOL_GPL (sas_ata_ncq_prio_supported); +/* * SAS Phy attributes */
include/scsi/scsi_transport_sas.h +2 -0
@@ -200,6 +200,8 @@ unsigned int sas_is_tlr_enabled(struct svoid sas_disable_tlr (struct scsi_device *);void sas_enable_tlr (struct scsi_device *); +bool sas_ata_ncq_prio_supported (struct scsi_device *sdev); +extern struct sas_rphy *sas_end_device_alloc (struct sas_port *);extern struct sas_rphy *sas_expander_alloc (struct sas_port *,enum sas_device_type );void sas_rphy_free (struct sas_rphy *);
Greg Kroah-Hartman
maintainerPATCH 69/217 HID: i2c-hid: elan: fix reset suspend current leakage
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Johan Hovold <[email protected]>
[ Upstream commit 0eafc58f2194dbd01d4be40f99a697681171995b ]
The Elan eKTH5015M touch controller found on the Lenovo ThinkPad X13s shares the VCC33 supply with other peripherals that may remain powered during suspend (e.g. when enabled as wakeup sources).
The reset line is also wired so that it can be left deasserted when the supply is off.
This is important as it avoids holding the controller in reset for extended periods of time when it remains powered, which can lead to increased power consumption, and also avoids leaking current through the X13s reset circuitry during suspend (and after driver unbind).
Use the new 'no-reset-on-power-off' devicetree property to determine when reset needs to be asserted on power down.
Notably this also avoids wasting power on machine variants without a touchscreen for which the driver would otherwise exit probe with reset asserted.
--- drivers/hid/i2c-hid/i2c-hid-of-elan.c | 59 +++++++++++++++++++++------ 1 file changed, 47 insertions(+), 12 deletions(-)
drivers/hid/i2c-hid/i2c-hid-of-elan.c +47 -12
@@ -31,6 +31,7 @@ struct i2c_hid_of_elan {struct regulator *vcc33;struct regulator *vccio;struct gpio_desc *reset_gpio; +bool no_reset_on_power_off;const struct elan_i2c_hid_chip_data *chip_data; };
@@ -40,17 +41,17 @@ static int elan_i2c_hid_power_up(struct i2chid_ops *ops) container_of(ops, struct i2c_hid_of_elan, ops);int ret; +gpiod_set_value_cansleep (ihid_elan->reset_gpio,1 ); +if (ihid_elan->vcc33) { ret =regulator_enable (ihid_elan->vcc33);if (ret) -return ret; + goto err_deassert_reset; } ret =regulator_enable (ihid_elan->vccio); -if (ret) { -regulator_disable (ihid_elan->vcc33); -return ret; - } +if (ret) + goto err_disable_vcc33;if (ihid_elan->chip_data->post_power_delay_ms)msleep (ihid_elan->chip_data->post_power_delay_ms);
@@ -60,6 +61,15 @@ static int elan_i2c_hid_power_up(struct i2chid_ops *ops)msleep (ihid_elan->chip_data->post_gpio_reset_on_delay_ms);return 0 ; + +err_disable_vcc33: +if (ihid_elan->vcc33) +regulator_disable (ihid_elan->vcc33); +err_deassert_reset: +if (ihid_elan->no_reset_on_power_off) +gpiod_set_value_cansleep (ihid_elan->reset_gpio,0 ); + +return ret; }static void elan_i2c_hid_power_down (struct i2chid_ops *ops)
@@ -67,7 +77,14 @@ static void elan_i2c_hid_power_down(struct i2chid_ops *ops)struct i2c_hid_of_elan *ihid_elan = container_of(ops, struct i2c_hid_of_elan, ops); -gpiod_set_value_cansleep (ihid_elan->reset_gpio,1 ); +/* +* Do not assert reset when the hardware allows for it to remain +* deasserted regardless of the state of the (shared) power supply to +* avoid wasting power when the supply is left on. +*/ +if (!ihid_elan->no_reset_on_power_off) +gpiod_set_value_cansleep (ihid_elan->reset_gpio,1 ); +if (ihid_elan->chip_data->post_gpio_reset_off_delay_ms)msleep (ihid_elan->chip_data->post_gpio_reset_off_delay_ms);
@@ -80,6 +97,7 @@ static int i2c_hid_of_elan_probe(struct i2c_client *client, const struct i2c_device_id *id) {struct i2c_hid_of_elan *ihid_elan; +int ret; ihid_elan =devm_kzalloc (&client->dev,sizeof (*ihid_elan),GFP_KERNEL );if (!ihid_elan)
@@ -94,21 +112,38 @@ static int i2c_hid_of_elan_probe(struct i2c_client *client,if (IS_ERR (ihid_elan->reset_gpio))return PTR_ERR (ihid_elan->reset_gpio); + ihid_elan->no_reset_on_power_off =of_property_read_bool (client->dev.of_node, +"no-reset-on-power-off" ); + ihid_elan->vccio =devm_regulator_get (&client->dev,"vccio" ); -if (IS_ERR (ihid_elan->vccio)) -return PTR_ERR (ihid_elan->vccio); +if (IS_ERR (ihid_elan->vccio)) { + ret =PTR_ERR (ihid_elan->vccio); + goto err_deassert_reset; + } ihid_elan->chip_data =device_get_match_data (&client->dev);if (ihid_elan->chip_data->main_supply_name) { ihid_elan->vcc33 =devm_regulator_get (&client->dev, ihid_elan->chip_data->main_supply_name); -if (IS_ERR (ihid_elan->vcc33)) -return PTR_ERR (ihid_elan->vcc33); +if (IS_ERR (ihid_elan->vcc33)) { + ret =PTR_ERR (ihid_elan->vcc33); + goto err_deassert_reset; + } } -return i2c_hid_core_probe (client, &ihid_elan->ops, - ihid_elan->chip_data->hid_descriptor_address,0 ); + ret =i2c_hid_core_probe (client, &ihid_elan->ops, + ihid_elan->chip_data->hid_descriptor_address,0 ); +if (ret) + goto err_deassert_reset; + +return 0 ; + +err_deassert_reset: +if (ihid_elan->no_reset_on_power_off) +gpiod_set_value_cansleep (ihid_elan->reset_gpio,0 ); + +return ret; }static const struct elan_i2c_hid_chip_data elan_ekth6915_chip_data = {
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 70/217 i2c: add fwnode APIs
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Russell King (Oracle) <[email protected]>
[ Upstream commit 373c612d72461ddaea223592df31e62c934aae61 ]
Add fwnode APIs for finding and getting I2C adapters, which will be used by the SFP code. These are passed the fwnode corresponding to the adapter, and return the I2C adapter. It is the responsibility of the caller to find the appropriate fwnode.
We keep the DT and ACPI interfaces, but where appropriate, recode them to use the fwnode interfaces internally.
Stable-dep-of: 3f858bbf04db ("i2c: acpi: Unbind mux adapters before delete")
--- drivers/i2c/i2c-core-acpi.c | 13 +---- drivers/i2c/i2c-core-base.c | 98 +++++++++++++++++++++++++++++++++++++ drivers/i2c/i2c-core-of.c | 66 ------------------------- include/linux/i2c.h | 24 +++++++-- 4 files changed, 120 insertions(+), 81 deletions(-)
drivers/i2c/i2c-core-acpi.c +1 -12
@@ -442,18 +442,7 @@ EXPORT_SYMBOL_GPL(i2c_acpi_find_adapter_by_handle);static struct i2c_client *i2c_acpi_find_client_by_adev (struct acpi_device *adev) { -struct device *dev; -struct i2c_client *client; - - dev =bus_find_device_by_acpi_dev (&i2c_bus_type, adev); -if (!dev) -return NULL ; - - client =i2c_verify_client (dev); -if (!client) -put_device (dev); - -return client; +return i2c_find_device_by_fwnode (acpi_fwnode_handle (adev)); } static int i2c_acpi_notify(struct notifier_block *nb, unsigned long value,
drivers/i2c/i2c-core-base.c +98 -0
110 lines not on this page · raw message
drivers/i2c/i2c-core-of.c +0 -66
72 lines not on this page · raw message
include/linux/i2c.h +21 -3
@@ -964,15 +964,33 @@ int i2c_handle_smbus_host_notify(struct i2c_adapter *adap, unsigned short addr);#endif /* I2C */ +/* must call put_device() when done with returned i2c_client device */ +struct i2c_client *i2c_find_device_by_fwnode (struct fwnode_handle *fwnode); + +/* must call put_device() when done with returned i2c_adapter device */ +struct i2c_adapter *i2c_find_adapter_by_fwnode (struct fwnode_handle *fwnode); + +/* must call i2c_put_adapter() when done with returned i2c_adapter device */ +struct i2c_adapter *i2c_get_adapter_by_fwnode (struct fwnode_handle *fwnode); +#if IS_ENABLED (CONFIG_OF )/* must call put_device() when done with returned i2c_client device */ -struct i2c_client *of_find_i2c_device_by_node (struct device_node *node); +static inline struct i2c_client *of_find_i2c_device_by_node (struct device_node *node) +{ +return i2c_find_device_by_fwnode (of_fwnode_handle (node)); +}/* must call put_device() when done with returned i2c_adapter device */ -struct i2c_adapter *of_find_i2c_adapter_by_node (struct device_node *node); +static inline struct i2c_adapter *of_find_i2c_adapter_by_node (struct device_node *node) +{ +return i2c_find_adapter_by_fwnode (of_fwnode_handle (node)); +}/* must call i2c_put_adapter() when done with returned i2c_adapter device */ -struct i2c_adapter *of_get_i2c_adapter_by_node (struct device_node *node); +static inline struct i2c_adapter *of_get_i2c_adapter_by_node (struct device_node *node) +{ +return i2c_get_adapter_by_fwnode (of_fwnode_handle (node)); +}const struct of_device_id *i2c_of_match_device(const struct of_device_id *matches,
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 71/217 i2c: acpi: Unbind mux adapters before delete
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Hamish Martin <[email protected]>
[ Upstream commit 3f858bbf04dbac934ac279aaee05d49eb9910051 ]
There is an issue with ACPI overlay table removal specifically related to I2C multiplexers.
Consider an ACPI SSDT Overlay that defines a PCA9548 I2C mux on an existing I2C bus. When this table is loaded we see the creation of a device for the overall PCA9548 chip and 8 further devices - one i2c_adapter each for the mux channels. These are all bound to their ACPI equivalents via an eventual invocation of acpi_bind_one().
When we unload the SSDT overlay we run into the problem. The ACPI devices are deleted as normal via acpi_device_del_work_fn() and the acpi_device_del_list.
However, the following warning and stack trace is output as the deletion does not go smoothly:
------------[ cut here ]------------ kernfs: can not remove 'physical_node', no directory WARNING: CPU: 1 PID: 11 at fs/kernfs/dir.c:1674 kernfs_remove_by_name_ns+0xb9/0xc0 Modules linked in: CPU: 1 PID: 11 Comm: kworker/u128:0 Not tainted 6.8.0-rc6+ #1 Hardware name: congatec AG conga-B7E3/conga-B7E3, BIOS 5.13 05/16/2023 Workqueue: kacpi_hotplug acpi_device_del_work_fn RIP: 0010:kernfs_remove_by_name_ns+0xb9/0xc0 Code: e4 00 48 89 ef e8 07 71 db ff 5b b8 fe ff ff ff 5d 41 5c 41 5d e9 a7 55 e4 00 0f 0b eb a6 48 c7 c7 f0 38 0d 9d e8 97 0a d5 ff <0f> 0b eb dc 0f 1f 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 RSP: 0018:ffff9f864008fb28 EFLAGS: 00010286 RAX: 0000000000000000 RBX: ffff8ef90a8d4940 RCX: 0000000000000000 RDX: ffff8f000e267d10 RSI: ffff8f000e25c780 RDI: ffff8f000e25c780 RBP: ffff8ef9186f9870 R08: 0000000000013ffb R09: 00000000ffffbfff R10: 00000000ffffbfff R11: ffff8f000e0a0000 R12: ffff9f864008fb50 R13: ffff8ef90c93dd60 R14: ffff8ef9010d0958 R15: ffff8ef9186f98c8 FS: 0000000000000000(0000) GS:ffff8f000e240000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f48f5253a08 CR3: 00000003cb82e000 CR4: 00000000003506f0 Call Trace: <TASK> ? kernfs_remove_by_name_ns+0xb9/0xc0 ? __warn+0x7c/0x130 ? kernfs_remove_by_name_ns+0xb9/0xc0 ? report_bug+0x171/0x1a0 ? handle_bug+0x3c/0x70 ? exc_invalid_op+0x17/0x70 ? asm_exc_invalid_op+0x1a/0x20 ? kernfs_remove_by_name_ns+0xb9/0xc0 ? kernfs_remove_by_name_ns+0xb9/0xc0 acpi_unbind_one+0x108/0x180 device_del+0x18b/0x490 ? srso_return_thunk+0x5/0x5f ? srso_return_thunk+0x5/0x5f device_unregister+0xd/0x30 i2c_del_adapter.part.0+0x1bf/0x250 i2c_mux_del_adapters+0xa1/0xe0 i2c_device_remove+0x1e/0x80 device_release_driver_internal+0x19a/0x200 bus_remove_device+0xbf/0x100 device_del+0x157/0x490 ? __pfx_device_match_fwnode+0x10/0x10 ? srso_return_thunk+0x5/0x5f device_unregister+0xd/0x30 i2c_acpi_notify+0x10f/0x140 notifier_call_chain+0x58/0xd0 blocking_notifier_call_chain+0x3a/0x60 acpi_device_del_work_fn+0x85/0x1d0 process_one_work+0x134/0x2f0 worker_thread+0x2f0/0x410 ? __pfx_worker_thread+0x10/0x10 kthread+0xe3/0x110 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x2f/0x50 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1b/0x30 </TASK> ---[ end trace 0000000000000000 ]---
...
repeated 7 more times, 1 for each channel of the mux
...
The issue is that the binding of the ACPI devices to their peer I2C adapters is not correctly cleaned up. Digging deeper into the issue we see that the deletion order is such that the ACPI devices matching the mux channel i2c adapters are deleted first during the SSDT overlay removal. For each of the channels we see a call to i2c_acpi_notify() with ACPI_RECONFIG_DEVICE_REMOVE but, because these devices are not actually i2c_clients, nothing is done for them.
Later on, after each of the mux channels has been dealt with, we come to delete the i2c_client representing the PCA9548 device. This is the call stack we see above, whereby the kernel cleans up the i2c_client including destruction of the mux and its channel adapters. At this point we do attempt to unbind from the ACPI peers but those peers no longer exist and so we hit the kernfs errors.
The fix is to augment i2c_acpi_notify() to handle i2c_adapters. But, given that the life cycle of the adapters is linked to the i2c_client, instead of deleting the i2c_adapters during the i2c_acpi_notify(), we just trigger unbinding of the ACPI device from the adapter device, and allow the clean up of the adapter to continue in the way it always has.
--- drivers/i2c/i2c-core-acpi.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-)
drivers/i2c/i2c-core-acpi.c +15 -4
@@ -445,6 +445,11 @@ static struct i2c_client *i2c_acpi_find_client_by_adev(struct acpi_device *adev)return i2c_find_device_by_fwnode (acpi_fwnode_handle (adev)); } +static struct i2c_adapter *i2c_acpi_find_adapter_by_adev (struct acpi_device *adev) +{ +return i2c_find_adapter_by_fwnode (acpi_fwnode_handle (adev)); +} +static int i2c_acpi_notify (struct notifier_block *nb,unsigned long value,void *arg) {
@@ -471,11 +476,17 @@ static int i2c_acpi_notify(struct notifier_block *nb, unsigned long value,break ; client =i2c_acpi_find_client_by_adev (adev); -if (!client) -break ; +if (client) { +i2c_unregister_device (client); +put_device (&client->dev); + } + + adapter =i2c_acpi_find_adapter_by_adev (adev); +if (adapter) { +acpi_unbind_one (&adapter->dev); +put_device (&adapter->dev); + } -i2c_unregister_device (client); -put_device (&client->dev);break ; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 72/217 mm, vmalloc: fix high order __GFP_NOFAIL allocations
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Michal Hocko <[email protected]>
[ Upstream commit e9c3cda4d86e56bf7fe403729f38c4f0f65d3860 ]
Gao Xiang has reported that the page allocator complains about high order __GFP_NOFAIL request coming from the vmalloc core:
__alloc_pages+0x1cb/0x5b0 mm/page_alloc.c:5549 alloc_pages+0x1aa/0x270 mm/mempolicy.c:2286 vm_area_alloc_pages mm/vmalloc.c:2989 [inline] __vmalloc_area_node mm/vmalloc.c:3057 [inline] __vmalloc_node_range+0x978/0x13c0 mm/vmalloc.c:3227 kvmalloc_node+0x156/0x1a0 mm/util.c:606 kvmalloc include/linux/slab.h:737 [inline] kvmalloc_array include/linux/slab.h:755 [inline] kvcalloc include/linux/slab.h:760 [inline]
it seems that I have completely missed high order allocation backing vmalloc areas case when implementing __GFP_NOFAIL support. This means that [k]vmalloc at al. can allocate higher order allocations with __GFP_NOFAIL which can trigger OOM killer for non-costly orders easily or cause a lot of reclaim/compaction activity if those requests cannot be satisfied.
Fix the issue by falling back to zero order allocations for __GFP_NOFAIL requests if the high order request fails.
Stable-dep-of: 8e0545c83d67 ("mm/vmalloc: fix vmalloc which may return null if called with __GFP_NOFAIL")
--- mm/vmalloc.c | 28 +++++++++++++++++++++++----- 1 file changed, 23 insertions(+), 5 deletions(-)
mm/vmalloc.c +23 -5
@@ -2923,6 +2923,8 @@ vm_area_alloc_pages(gfp_t gfp, int nid, unsigned int order, unsigned int nr_pages, struct page **pages) { unsigned int nr_allocated = 0; +gfp_t alloc_gfp = gfp; +bool nofail = false;struct page *page;int i;
@@ -2933,6 +2935,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid,* more permissive. */ if (!order) { +/* bulk allocator doesn't support nofail req. officially */ gfp_t bulk_gfp = gfp & ~__GFP_NOFAIL;while (nr_allocated < nr_pages) {
@@ -2971,20 +2974,35 @@ vm_area_alloc_pages(gfp_t gfp, int nid,if (nr != nr_pages_request)break ; } + }else if (gfp & __GFP_NOFAIL) { +/* +* Higher order nofail allocations are really expensive and +* potentially dangerous (pre-mature OOM, disruptive reclaim +* and compaction etc. +*/ + alloc_gfp &= ~__GFP_NOFAIL; + nofail = true; }/* High-order pages or fallback path if "bulk" fails. */ -while (nr_allocated < nr_pages) {if (fatal_signal_pending (current))break ;if (nid ==NUMA_NO_NODE ) - page =alloc_pages (gfp, order); + page =alloc_pages (alloc_gfp, order);else - page =alloc_pages_node (nid, gfp, order); -if (unlikely (!page)) -break ; + page =alloc_pages_node (nid, alloc_gfp, order); +if (unlikely (!page)) { +if (!nofail) +break ; + +/* fall back to the zero order allocations */ + alloc_gfp |= __GFP_NOFAIL; + order =0 ; +continue ; + } +/* * Higher order allocations must be able to be treated as * indepdenent small pages by callers (as they can with
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 73/217 mm/vmalloc: fix vmalloc which may return null if called with __GFP_NOFAIL
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Hailong.Liu <[email protected]>
[ Upstream commit 8e0545c83d672750632f46e3f9ad95c48c91a0fc ]
commit a421ef303008 ("mm: allow !GFP_KERNEL allocations for kvmalloc") includes support for __GFP_NOFAIL, but it presents a conflict with commit dd544141b9eb ("vmalloc: back off when the current task is OOM-killed"). A possible scenario is as follows:
process-a__vmalloc_node_range(GFP_KERNEL | __GFP_NOFAIL)
__vmalloc_area_node()
vm_area_alloc_pages()
--> oom-killer send SIGKILL to process-a
if (fatal_signal_pending(current)) break;--> return NULL;
To fix this, do not check fatal_signal_pending() in vm_area_alloc_pages() if __GFP_NOFAIL set.
This issue occurred during OPLUS KASAN TEST. Below is part of the log -> oom-killer sends signal to process
[65731.222840] [ T1308] oom-kill:constraint=CONSTRAINT_NONE,nodemask=(null),cpuset=/,mems_allowed=0,global_oom,task_memcg=/apps/uid_10198,task=gs.intelligence,pid=32454,uid=10198
[65731.259685] [T32454] Call trace: [65731.259698] [T32454] dump_backtrace+0xf4/0x118 [65731.259734] [T32454] show_stack+0x18/0x24 [65731.259756] [T32454] dump_stack_lvl+0x60/0x7c [65731.259781] [T32454] dump_stack+0x18/0x38 [65731.259800] [T32454] mrdump_common_die+0x250/0x39c [mrdump] [65731.259936] [T32454] ipanic_die+0x20/0x34 [mrdump] [65731.260019] [T32454] atomic_notifier_call_chain+0xb4/0xfc [65731.260047] [T32454] notify_die+0x114/0x198 [65731.260073] [T32454] die+0xf4/0x5b4 [65731.260098] [T32454] die_kernel_fault+0x80/0x98 [65731.260124] [T32454] __do_kernel_fault+0x160/0x2a8 [65731.260146] [T32454] do_bad_area+0x68/0x148 [65731.260174] [T32454] do_mem_abort+0x151c/0x1b34 [65731.260204] [T32454] el1_abort+0x3c/0x5c [65731.260227] [T32454] el1h_64_sync_handler+0x54/0x90 [65731.260248] [T32454] el1h_64_sync+0x68/0x6c
[65731.260269] [T32454] z_erofs_decompress_queue+0x7f0/0x2258 --> be->decompressed_pages = kvcalloc(be->nr_pages, sizeof(struct page *), GFP_KERNEL | __GFP_NOFAIL); kernel panic by NULL pointer dereference. erofs assume kvmalloc with __GFP_NOFAIL never return NULL. [65731.260293] [T32454] z_erofs_runqueue+0xf30/0x104c [65731.260314] [T32454] z_erofs_readahead+0x4f0/0x968 [65731.260339] [T32454] read_pages+0x170/0xadc [65731.260364] [T32454] page_cache_ra_unbounded+0x874/0xf30 [65731.260388] [T32454] page_cache_ra_order+0x24c/0x714 [65731.260411] [T32454] filemap_fault+0xbf0/0x1a74 [65731.260437] [T32454] __do_fault+0xd0/0x33c [65731.260462] [T32454] handle_mm_fault+0xf74/0x3fe0 [65731.260486] [T32454] do_mem_abort+0x54c/0x1b34 [65731.260509] [T32454] el0_da+0x44/0x94 [65731.260531] [T32454] el0t_64_sync_handler+0x98/0xb4 [65731.260553] [T32454] el0t_64_sync+0x198/0x19c
--- mm/vmalloc.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)
mm/vmalloc.c +2 -3
@@ -2924,7 +2924,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid, {unsigned int nr_allocated =0 ;gfp_t alloc_gfp = gfp; -bool nofail = false; +bool nofail = gfp & __GFP_NOFAIL;struct page *page;int i;
@@ -2981,12 +2981,11 @@ vm_area_alloc_pages(gfp_t gfp, int nid,* and compaction etc. */ alloc_gfp &= ~__GFP_NOFAIL; - nofail = true; }/* High-order pages or fallback path if "bulk" fails. */ while (nr_allocated < nr_pages) { -if (fatal_signal_pending (current)) +if (!nofail &&fatal_signal_pending (current))break ;if (nid ==NUMA_NO_NODE )
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 74/217 selftests/mm: compaction_test: fix incorrect write of zero to nr_hugepages
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Dev Jain <[email protected]>
[ Upstream commit 9ad665ef55eaad1ead1406a58a34f615a7c18b5e ]
Currently, the test tries to set nr_hugepages to zero, but that is not actually done because the file offset is not reset after read(). Fix that using lseek().
--- tools/testing/selftests/vm/compaction_test.c | 2 ++ 1 file changed, 2 insertions(+)
tools/testing/selftests/vm/compaction_test.c +2 -0
@@ -103,6 +103,8 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) goto close_fd; } +lseek (fd,0 ,SEEK_SET ); +/* Start with the initial condition of 0 huge pages*/ if (write (fd,"0" ,sizeof (char )) !=sizeof (char )) {perror ("Failed to write 0 to /proc/sys/vm/nr_hugepages\n" );
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 65/217 serial: sc16is7xx: fix bug in sc16is7xx_set_baud() when using prescaler
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Hugo Villeneuve <[email protected]>
[ Upstream commit 8492bd91aa055907c67ef04f2b56f6dadd1f44bf ]
When using a high speed clock with a low baud rate, the 4x prescaler is automatically selected if required. In that case, sc16is7xx_set_baud() properly configures the chip registers, but returns an incorrect baud rate by not taking into account the prescaler value. This incorrect baud rate is then fed to uart_update_timeout().
For example, with an input clock of 80MHz, and a selected baud rate of 50, sc16is7xx_set_baud() will return 200 instead of 50.
Fix this by first changing the prescaler variable to hold the selected prescaler value instead of the MCR bitfield. Then properly take into account the selected prescaler value in the return value computation.
Also add better documentation about the divisor value computation.
--- drivers/tty/serial/sc16is7xx.c | 23 ++++++++++++++++++----- 1 file changed, 18 insertions(+), 5 deletions(-)
drivers/tty/serial/sc16is7xx.c +18 -5
@@ -482,16 +482,28 @@ static bool sc16is7xx_regmap_noinc(struct device *dev, unsigned int reg)return reg ==SC16IS7XX_RHR_REG ; } +/* +* Configure programmable baud rate generator (divisor) according to the +* desired baud rate. +* +* From the datasheet, the divisor is computed according to: +* +* XTAL1 input frequency +* ----------------------- +* prescaler +* divisor = --------------------------- +* baud-rate x sampling-rate +*/ static int sc16is7xx_set_baud (struct uart_port *port,int baud) {struct sc16is7xx_one *one =to_sc16is7xx_one (port, port);u8 lcr; -u8 prescaler =0 ; +unsigned int prescaler =1 ;unsigned long clk = port->uartclk, div = clk /16 / baud;if (div >=BIT (16 )) { - prescaler =SC16IS7XX_MCR_CLKSEL_BIT ; - div /=4 ; + prescaler =4 ; + div /= prescaler; }/* In an amazing feat of design, the Enhanced Features Register shares
@@ -528,9 +540,10 @@ static int sc16is7xx_set_baud(struct uart_port *port, int baud)mutex_unlock (&one->efr_lock); +/* If bit MCR_CLKSEL is set, the divide by 4 prescaler is activated. */ sc16is7xx_port_update (port,SC16IS7XX_MCR_REG ,SC16IS7XX_MCR_CLKSEL_BIT , - prescaler); + prescaler ==1 ?0 :SC16IS7XX_MCR_CLKSEL_BIT );/* Open the LCR divisors for configuration */ sc16is7xx_port_write(port, SC16IS7XX_LCR_REG,
@@ -545,7 +558,7 @@ static int sc16is7xx_set_baud(struct uart_port *port, int baud)/* Put LCR back to the normal mode */ sc16is7xx_port_write (port,SC16IS7XX_LCR_REG , lcr); -return DIV_ROUND_CLOSEST (clk /16 , div); +return DIV_ROUND_CLOSEST ((clk / prescaler) /16 , div); } static void sc16is7xx_handle_rx(struct uart_port *port, unsigned int rxlen,
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 100/217 scsi: sd: Use READ(16) when reading block zero on large capacity disks
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Martin K. Petersen <[email protected]>
commit 7926d51f73e0434a6250c2fd1a0555f98d9a62da upstream.
Commit 321da3dc1f3c ("scsi: sd: usb_storage: uas: Access media prior to querying device properties") triggered a read to LBA 0 before attempting to inquire about device characteristics. This was done because some protocol bridge devices will return generic values until an attached storage device's media has been accessed.
Pierre Tomon reported that this change caused problems on a large capacity external drive connected via a bridge device. The bridge in question does not appear to implement the READ(10) command.
Issue a READ(16) instead of READ(10) when a device has been identified as preferring 16-byte commands (use_16_for_rw heuristic).
--- drivers/scsi/sd.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-)
drivers/scsi/sd.c +12 -5
@@ -3288,16 +3288,23 @@ static bool sd_validate_opt_xfer_size(ststatic void sd_read_block_zero (struct scsi_disk *sdkp) { -unsigned int buf_len = sdkp->device->sector_size; -char *buffer, cmd[10 ] = { }; +struct scsi_device *sdev = sdkp->device; +unsigned int buf_len = sdev->sector_size; +u8 *buffer, cmd[16 ] = { }; buffer =kmalloc (buf_len,GFP_KERNEL );if (!buffer)return ; - cmd[0 ] =READ_10 ; -put_unaligned_be32 (0 , &cmd[2 ]);/* Logical block address 0 */ -put_unaligned_be16 (1 , &cmd[7 ]);/* Transfer 1 logical block */ +if (sdev->use_16_for_rw) { + cmd[0 ] =READ_16 ; +put_unaligned_be64 (0 , &cmd[2 ]);/* Logical block address 0 */ +put_unaligned_be32 (1 , &cmd[10 ]);/* Transfer 1 logical block */ + }else { + cmd[0 ] =READ_10 ; +put_unaligned_be32 (0 , &cmd[2 ]);/* Logical block address 0 */ +put_unaligned_be16 (1 , &cmd[7 ]);/* Transfer 1 logical block */ + }scsi_execute_req (sdkp->device, cmd,DMA_FROM_DEVICE , buffer, buf_len,NULL ,SD_TIMEOUT , sdkp->max_retries,NULL );
Greg Kroah-Hartman
maintainerPATCH 109/217 cachefiles: resend an open request if the read requests object is closed
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jia Zhu <[email protected]>
[ Upstream commit 0a7e54c1959c0feb2de23397ec09c7692364313e ]
When an anonymous fd is closed by user daemon, if there is a new read request for this file comes up, the anonymous fd should be re-opened to handle that read request rather than fail it directly.
1. Introduce reopening state for objects that are closed but have inflight/subsequent read requests.
2. No longer flush READ requests but only CLOSE requests when anonymous fd is closed.
3. Enqueue the reopen work to workqueue, thus user daemon could get rid of daemon_read context and handle that request smoothly. Otherwise, the user daemon will send a reopen request and wait for itself to process the request.
Stable-dep-of: 0a790040838c ("cachefiles: add spin_lock for cachefiles_ondemand_info")
--- fs/cachefiles/internal.h | 3 ++ fs/cachefiles/ondemand.c | 98 ++++++++++++++++++++++++++++------------ 2 files changed, 72 insertions(+), 29 deletions(-)
fs/cachefiles/internal.h +3 -0
@@ -47,9 +47,11 @@ struct cachefiles_volume {enum cachefiles_object_state {CACHEFILES_ONDEMAND_OBJSTATE_CLOSE ,/* Anonymous fd closed by daemon or initial state */ CACHEFILES_ONDEMAND_OBJSTATE_OPEN ,/* Anonymous fd associated with object is available */ +CACHEFILES_ONDEMAND_OBJSTATE_REOPENING ,/* Object that was closed and is being reopened. */ };struct cachefiles_ondemand_info { +struct work_struct ondemand_work;int ondemand_id;enum cachefiles_object_state state;struct cachefiles_object *object;
@@ -326,6 +328,7 @@ cachefiles_ondemand_set_object_##_state(struct cachefiles_object *object) \CACHEFILES_OBJECT_STATE_FUNCS (open,OPEN );CACHEFILES_OBJECT_STATE_FUNCS (close,CLOSE ); +CACHEFILES_OBJECT_STATE_FUNCS (reopening,REOPENING );#else static inline ssize_t cachefiles_ondemand_daemon_read (struct cachefiles_cache *cache,char __user *_buffer,size_t buflen)
fs/cachefiles/ondemand.c +69 -29
194 lines not on this page · raw message
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 110/217 cachefiles: add spin_lock for cachefiles_ondemand_info
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Baokun Li <[email protected]>
[ Upstream commit 0a790040838c736495d5afd6b2d636f159f817f1 ]
The following concurrency may cause a read request to fail to be completed and result in a hung:
t1 | t2
---------------------------------------------------------
cachefiles_ondemand_copen
req = xa_erase(&cache->reqs, id)// Anon fd is maliciously closed.cachefiles_ondemand_fd_release
xa_lock(&cache->reqs)
cachefiles_ondemand_set_object_close(object)
xa_unlock(&cache->reqs)
cachefiles_ondemand_set_object_open
// No one will ever close it again.cachefiles_ondemand_daemon_read
cachefiles_ondemand_select_req
// Get a read req but its fd is already closed.
// The daemon can't issue a cread ioctl with an closed fd, then hung.
So add spin_lock for cachefiles_ondemand_info to protect ondemand_id and state, thus we can avoid the above problem in cachefiles_ondemand_copen() by using ondemand_id to determine if fd has been closed.
--- fs/cachefiles/internal.h | 1 + fs/cachefiles/ondemand.c | 35 ++++++++++++++++++++++++++++++++++- 2 files changed, 35 insertions(+), 1 deletion(-)
fs/cachefiles/internal.h +1 -0
@@ -55,6 +55,7 @@ struct cachefiles_ondemand_info {int ondemand_id;enum cachefiles_object_state state;struct cachefiles_object *object; +spinlock_t lock; };/*
fs/cachefiles/ondemand.c +34 -1
@@ -10,13 +10,16 @@ static int cachefiles_ondemand_fd_release(struct inode *inode,struct cachefiles_object *object = file->private_data;struct cachefiles_cache *cache = object->volume->cache;struct cachefiles_ondemand_info *info = object->ondemand; -int object_id = info->ondemand_id; +int object_id;struct cachefiles_req *req;XA_STATE (xas, &cache->reqs,0 );xa_lock (&cache->reqs); +spin_lock (&info->lock); + object_id = info->ondemand_id; info->ondemand_id =CACHEFILES_ONDEMAND_ID_CLOSED ;cachefiles_ondemand_set_object_close (object); +spin_unlock (&info->lock);/* Only flush CACHEFILES_REQ_NEW marked req to avoid race with daemon_read */ xas_for_each_marked (&xas, req,ULONG_MAX ,CACHEFILES_REQ_NEW ) {
@@ -116,6 +119,7 @@ int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args) {struct cachefiles_req *req;struct fscache_cookie *cookie; +struct cachefiles_ondemand_info *info;char *pid, *psize;unsigned long id;long size;
@@ -166,6 +170,33 @@ int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args) goto out; } + info = req->object->ondemand; +spin_lock (&info->lock); +/* +* The anonymous fd was closed before copen ? Fail the request. +* +* t1 | t2 +* --------------------------------------------------------- +* cachefiles_ondemand_copen +* req = xa_erase(&cache->reqs, id) +* // Anon fd is maliciously closed. +* cachefiles_ondemand_fd_release +* xa_lock(&cache->reqs) +* cachefiles_ondemand_set_object_close(object) +* xa_unlock(&cache->reqs) +* cachefiles_ondemand_set_object_open +* // No one will ever close it again. +* cachefiles_ondemand_daemon_read +* cachefiles_ondemand_select_req +* +* Get a read req but its fd is already closed. The daemon can't +* issue a cread ioctl with an closed fd, then hung. +*/ +if (info->ondemand_id ==CACHEFILES_ONDEMAND_ID_CLOSED ) { +spin_unlock (&info->lock); + req->error = -EBADFD ; + goto out; + } cookie = req->object->cookie; cookie->object_size = size;if (size)
@@ -175,6 +206,7 @@ int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args)trace_cachefiles_ondemand_copen (req->object, id, size);cachefiles_ondemand_set_object_open (req->object); +spin_unlock (&info->lock);wake_up_all (&cache->daemon_pollwq); out:
@@ -552,6 +584,7 @@ int cachefiles_ondemand_init_obj_info(struct cachefiles_object *object,return -ENOMEM ; object->ondemand->object = object; +spin_lock_init (&object->ondemand->lock);INIT_WORK (&object->ondemand->ondemand_work, ondemand_object_worker);return 0 ; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 111/217 cachefiles: add restore command to recover inflight ondemand read requests
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jia Zhu <[email protected]>
[ Upstream commit e73fa11a356ca0905c3cc648eaacc6f0f2d2c8b3 ]
Previously, in ondemand read scenario, if the anonymous fd was closed by user daemon, inflight and subsequent read requests would return EIO. As long as the device connection is not released, user daemon can hold and restore inflight requests by setting the request flag to CACHEFILES_REQ_NEW.
Stable-dep-of: 4b4391e77a6b ("cachefiles: defer exposing anon_fd until after copy_to_user() succeeds")
--- fs/cachefiles/daemon.c | 1 + fs/cachefiles/internal.h | 3 +++ fs/cachefiles/ondemand.c | 23 +++++++++++++++++++++++ 3 files changed, 27 insertions(+)
fs/cachefiles/daemon.c +1 -0
@@ -77,6 +77,7 @@ static const struct cachefiles_daemon_cmd cachefiles_daemon_cmds[] = { { "tag", cachefiles_daemon_tag }, #ifdef CONFIG_CACHEFILES_ONDEMAND { "copen", cachefiles_ondemand_copen }, + { "restore", cachefiles_ondemand_restore }, #endif { "", NULL } };
fs/cachefiles/internal.h +3 -0
@@ -304,6 +304,9 @@ extern ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,extern int cachefiles_ondemand_copen (struct cachefiles_cache *cache,char *args); +extern int cachefiles_ondemand_restore (struct cachefiles_cache *cache, +char *args); +extern int cachefiles_ondemand_init_object (struct cachefiles_object *object);extern void cachefiles_ondemand_clean_object (struct cachefiles_object *object);
fs/cachefiles/ondemand.c +23 -0
@@ -214,6 +214,29 @@ int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args)return ret; } +int cachefiles_ondemand_restore (struct cachefiles_cache *cache,char *args) +{ +struct cachefiles_req *req; + +XA_STATE (xas, &cache->reqs,0 ); + +if (!test_bit (CACHEFILES_ONDEMAND_MODE , &cache->flags)) +return -EOPNOTSUPP ; + +/* +* Reset the requests to CACHEFILES_REQ_NEW state, so that the +* requests have been processed halfway before the crash of the +* user daemon could be reprocessed after the recovery. +*/ +xas_lock (&xas); +xas_for_each (&xas, req,ULONG_MAX ) +xas_set_mark (&xas,CACHEFILES_REQ_NEW ); +xas_unlock (&xas); + +wake_up_all (&cache->daemon_pollwq); +return 0 ; +} +static int cachefiles_ondemand_get_fd (struct cachefiles_req *req) {struct cachefiles_object *object;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 112/217 cachefiles: fix slab-use-after-free in cachefiles_ondemand_get_fd()
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Baokun Li <[email protected]>
[ Upstream commit de3e26f9e5b76fc628077578c001c4a51bf54d06 ]
We got the following issue in a fuzz test of randomly issuing the restore command:
==================================================================
BUG: KASAN: slab-use-after-free in cachefiles_ondemand_daemon_read+0x609/0xab0 Write of size 4 at addr ffff888109164a80 by task ondemand-04-dae/4962 CPU: 11 PID: 4962 Comm: ondemand-04-dae Not tainted 6.8.0-rc7-dirty #542 Call Trace: kasan_report+0x94/0xc0 cachefiles_ondemand_daemon_read+0x609/0xab0 vfs_read+0x169/0xb50 ksys_read+0xf5/0x1e0 Allocated by task 626: __kmalloc+0x1df/0x4b0 cachefiles_ondemand_send_req+0x24d/0x690 cachefiles_create_tmpfile+0x249/0xb30 cachefiles_create_file+0x6f/0x140 cachefiles_look_up_object+0x29c/0xa60 cachefiles_lookup_cookie+0x37d/0xca0 fscache_cookie_state_machine+0x43c/0x1230 [...] Freed by task 626: kfree+0xf1/0x2c0 cachefiles_ondemand_send_req+0x568/0x690 cachefiles_create_tmpfile+0x249/0xb30 cachefiles_create_file+0x6f/0x140 cachefiles_look_up_object+0x29c/0xa60 cachefiles_lookup_cookie+0x37d/0xca0 fscache_cookie_state_machine+0x43c/0x1230 [...] ==================================================================
Following is the process that triggers the issue:
mount | daemon_thread1 | daemon_thread2
------------------------------------------------------------
cachefiles_ondemand_init_object
cachefiles_ondemand_send_req
REQ_A = kzalloc(sizeof(*req) + data_len)
wait_for_completion(&REQ_A->done)
cachefiles_daemon_read
cachefiles_ondemand_daemon_read
REQ_A = cachefiles_ondemand_select_req
cachefiles_ondemand_get_fd
copy_to_user(_buffer, msg, n)
process_open_req(REQ_A)
------ restore ------
cachefiles_ondemand_restore
xas_for_each(&xas, req, ULONG_MAX)
xas_set_mark(&xas, CACHEFILES_REQ_NEW);
cachefiles_daemon_read
cachefiles_ondemand_daemon_read
REQ_A = cachefiles_ondemand_select_req
write(devfd, ("copen %u,%llu", msg->msg_id, size));
cachefiles_ondemand_copen
xa_erase(&cache->reqs, id)
complete(&REQ_A->done)
kfree(REQ_A)
cachefiles_ondemand_get_fd(REQ_A)
fd = get_unused_fd_flags
file = anon_inode_getfile
fd_install(fd, file)
load = (void *)REQ_A->msg.data;
load->fd = fd;
// load UAF !!!This issue is caused by issuing a restore command when the daemon is still alive, which results in a request being processed multiple times thus triggering a UAF. So to avoid this problem, add an additional reference count to cachefiles_req, which is held while waiting and reading, and then released when the waiting and reading is over.
Note that since there is only one reference count for waiting, we need to avoid the same request being completed multiple times, so we can only complete the request if it is successfully removed from the xarray.
Stable-dep-of: 4b4391e77a6b ("cachefiles: defer exposing anon_fd until after copy_to_user() succeeds")
--- fs/cachefiles/internal.h | 1 + fs/cachefiles/ondemand.c | 23 +++++++++++++++++++---- 2 files changed, 20 insertions(+), 4 deletions(-)
fs/cachefiles/internal.h +1 -0
@@ -139,6 +139,7 @@ static inline bool cachefiles_in_ondemand_mode(struct cachefiles_cache *cache)struct cachefiles_req {struct cachefiles_object *object;struct completion done; +refcount_t ref;int error;struct cachefiles_msg msg; };
fs/cachefiles/ondemand.c +19 -4
@@ -4,6 +4,12 @@#include <linux/uio.h> #include "internal.h" +static inline void cachefiles_req_put (struct cachefiles_req *req) +{ +if (refcount_dec_and_test (&req->ref)) +kfree (req); +} +static int cachefiles_ondemand_fd_release (struct inode *inode,struct file *file) {
@@ -362,6 +368,7 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,xas_clear_mark (&xas,CACHEFILES_REQ_NEW ); cache->req_id_next = xas.xa_index +1 ; +refcount_inc (&req->ref);xa_unlock (&cache->reqs); id = xas.xa_index;
@@ -388,15 +395,22 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,complete (&req->done); } +cachefiles_req_put (req);return n; err_put_fd:if (msg->opcode ==CACHEFILES_OP_OPEN )close_fd (((struct cachefiles_open *)msg->data)->fd); error: -xa_erase (&cache->reqs, id); - req->error = ret; -complete (&req->done); +xas_reset (&xas); +xas_lock (&xas); +if (xas_load (&xas) == req) { + req->error = ret; +complete (&req->done); +xas_store (&xas,NULL ); + } +xas_unlock (&xas); +cachefiles_req_put (req);return ret; }
@@ -427,6 +441,7 @@ static int cachefiles_ondemand_send_req(struct cachefiles_object *object, goto out; } +refcount_set (&req->ref,1 ); req->object = object;init_completion (&req->done); req->msg.opcode = opcode;
@@ -488,7 +503,7 @@ static int cachefiles_ondemand_send_req(struct cachefiles_object *object,wake_up_all (&cache->daemon_pollwq);wait_for_completion (&req->done); ret = req->error; -kfree (req); +cachefiles_req_put (req);return ret; out:/* Reset the object to close state in error handling path.
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 113/217 cachefiles: fix slab-use-after-free in cachefiles_ondemand_daemon_read()
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Baokun Li <[email protected]>
[ Upstream commit da4a827416066191aafeeccee50a8836a826ba10 ]
We got the following issue in a fuzz test of randomly issuing the restore command:
==================================================================
BUG: KASAN: slab-use-after-free in cachefiles_ondemand_daemon_read+0xb41/0xb60 Read of size 8 at addr ffff888122e84088 by task ondemand-04-dae/963 CPU: 13 PID: 963 Comm: ondemand-04-dae Not tainted 6.8.0-dirty #564 Call Trace: kasan_report+0x93/0xc0 cachefiles_ondemand_daemon_read+0xb41/0xb60 vfs_read+0x169/0xb50 ksys_read+0xf5/0x1e0 Allocated by task 116: kmem_cache_alloc+0x140/0x3a0 cachefiles_lookup_cookie+0x140/0xcd0 fscache_cookie_state_machine+0x43c/0x1230 [...] Freed by task 792: kmem_cache_free+0xfe/0x390 cachefiles_put_object+0x241/0x480 fscache_cookie_state_machine+0x5c8/0x1230 [...] ==================================================================
Following is the process that triggers the issue:
mount | daemon_thread1 | daemon_thread2
------------------------------------------------------------cachefiles_withdraw_cookie
cachefiles_ondemand_clean_object(object)
cachefiles_ondemand_send_req
REQ_A = kzalloc(sizeof(*req) + data_len)
wait_for_completion(&REQ_A->done)
cachefiles_daemon_read
cachefiles_ondemand_daemon_read
REQ_A = cachefiles_ondemand_select_req
msg->object_id = req->object->ondemand->ondemand_id
------ restore ------
cachefiles_ondemand_restore
xas_for_each(&xas, req, ULONG_MAX)
xas_set_mark(&xas, CACHEFILES_REQ_NEW)
cachefiles_daemon_read
cachefiles_ondemand_daemon_read
REQ_A = cachefiles_ondemand_select_req
copy_to_user(_buffer, msg, n)
xa_erase(&cache->reqs, id)
complete(&REQ_A->done)
------ close(fd) ------
cachefiles_ondemand_fd_release
cachefiles_put_object
cachefiles_put_object
kmem_cache_free(cachefiles_object_jar, object)
REQ_A->object->ondemand->ondemand_id
// object UAF !!!When we see the request within xa_lock, req->object must not have been freed yet, so grab the reference count of object before xa_unlock to avoid the above issue.
Stable-dep-of: 4b4391e77a6b ("cachefiles: defer exposing anon_fd until after copy_to_user() succeeds")
--- fs/cachefiles/ondemand.c | 3 +++ include/trace/events/cachefiles.h | 6 +++++- 2 files changed, 8 insertions(+), 1 deletion(-)
fs/cachefiles/ondemand.c +3 -0
@@ -369,6 +369,7 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,xas_clear_mark (&xas,CACHEFILES_REQ_NEW ); cache->req_id_next = xas.xa_index +1 ;refcount_inc (&req->ref); +cachefiles_grab_object (req->object, cachefiles_obj_get_read_req);xa_unlock (&cache->reqs); id = xas.xa_index;
@@ -389,6 +390,7 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, goto err_put_fd; } +cachefiles_put_object (req->object, cachefiles_obj_put_read_req);/* CLOSE request has no reply */ if (msg->opcode ==CACHEFILES_OP_CLOSE ) {xa_erase (&cache->reqs, id);
@@ -402,6 +404,7 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,if (msg->opcode ==CACHEFILES_OP_OPEN )close_fd (((struct cachefiles_open *)msg->data)->fd); error: +cachefiles_put_object (req->object, cachefiles_obj_put_read_req);xas_reset (&xas);xas_lock (&xas);if (xas_load (&xas) == req) {
include/trace/events/cachefiles.h +5 -1
@@ -33,6 +33,8 @@ enum cachefiles_obj_ref_trace { cachefiles_obj_see_withdrawal, cachefiles_obj_get_ondemand_fd, cachefiles_obj_put_ondemand_fd, + cachefiles_obj_get_read_req, + cachefiles_obj_put_read_req, }; enum fscache_why_object_killed {
@@ -129,7 +131,9 @@ enum cachefiles_error_trace { EM(cachefiles_obj_see_withdraw_cookie, "SEE withdraw_cookie") \ EM(cachefiles_obj_see_withdrawal, "SEE withdrawal") \ EM(cachefiles_obj_get_ondemand_fd, "GET ondemand_fd") \ - E_(cachefiles_obj_put_ondemand_fd, "PUT ondemand_fd") + EM(cachefiles_obj_put_ondemand_fd, "PUT ondemand_fd") \ + EM(cachefiles_obj_get_read_req, "GET read_req") \ + E_(cachefiles_obj_put_read_req, "PUT read_req")#define cachefiles_coherency_traces \ EM(cachefiles_coherency_check_aux, "BAD aux ") \
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 114/217 cachefiles: remove err_put_fd label in cachefiles_ondemand_daemon_read()
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Baokun Li <[email protected]>
[ Upstream commit 3e6d704f02aa4c50c7bc5fe91a4401df249a137b ]
The err_put_fd label is only used once, so remove it to make the code more readable. In addition, the logic for deleting error request and CLOSE request is merged to simplify the code.
Stable-dep-of: 4b4391e77a6b ("cachefiles: defer exposing anon_fd until after copy_to_user() succeeds")
--- fs/cachefiles/ondemand.c | 45 ++++++++++++++-------------------------- 1 file changed, 16 insertions(+), 29 deletions(-)
fs/cachefiles/ondemand.c +16 -29
@@ -337,7 +337,6 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, {struct cachefiles_req *req;struct cachefiles_msg *msg; -unsigned long id =0 ;size_t n;int ret =0 ;XA_STATE (xas, &cache->reqs, cache->req_id_next);
@@ -372,49 +371,37 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,cachefiles_grab_object (req->object, cachefiles_obj_get_read_req);xa_unlock (&cache->reqs); - id = xas.xa_index; -if (msg->opcode ==CACHEFILES_OP_OPEN ) { ret =cachefiles_ondemand_get_fd (req);if (ret) {cachefiles_ondemand_set_object_close (req->object); - goto error; + goto out; } } - msg->msg_id = id; + msg->msg_id = xas.xa_index; msg->object_id = req->object->ondemand->ondemand_id;if (copy_to_user (_buffer, msg, n) !=0 ) { ret = -EFAULT ; - goto err_put_fd; - } - -cachefiles_put_object (req->object, cachefiles_obj_put_read_req); -/* CLOSE request has no reply */ -if (msg->opcode ==CACHEFILES_OP_CLOSE ) { -xa_erase (&cache->reqs, id); -complete (&req->done); +if (msg->opcode ==CACHEFILES_OP_OPEN ) +close_fd (((struct cachefiles_open *)msg->data)->fd); } - -cachefiles_req_put (req); -return n; - -err_put_fd: -if (msg->opcode ==CACHEFILES_OP_OPEN ) -close_fd (((struct cachefiles_open *)msg->data)->fd); -error: +out:cachefiles_put_object (req->object, cachefiles_obj_put_read_req); -xas_reset (&xas); -xas_lock (&xas); -if (xas_load (&xas) == req) { - req->error = ret; -complete (&req->done); -xas_store (&xas,NULL ); +/* Remove error request and CLOSE request has no reply */ +if (ret || msg->opcode ==CACHEFILES_OP_CLOSE ) { +xas_reset (&xas); +xas_lock (&xas); +if (xas_load (&xas) == req) { + req->error = ret; +complete (&req->done); +xas_store (&xas,NULL ); + } +xas_unlock (&xas); } -xas_unlock (&xas);cachefiles_req_put (req); -return ret; +return ret ? ret : n; }typedef int (*init_req_fn )(struct cachefiles_req *req,void *private);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 115/217 cachefiles: never get a new anonymous fd if ondemand_id is valid
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Baokun Li <[email protected]>
[ Upstream commit 4988e35e95fc938bdde0e15880fe72042fc86acf ]
Now every time the daemon reads an open request, it gets a new anonymous fd and ondemand_id. With the introduction of "restore", it is possible to read the same open request more than once, and therefore an object can have more than one anonymous fd.
If the anonymous fd is not unique, the following concurrencies will result in an fd leak:
t1 | t2 | t3
------------------------------------------------------------
cachefiles_ondemand_init_object
cachefiles_ondemand_send_req
REQ_A = kzalloc(sizeof(*req) + data_len)
wait_for_completion(&REQ_A->done)
cachefiles_daemon_read
cachefiles_ondemand_daemon_read
REQ_A = cachefiles_ondemand_select_req
cachefiles_ondemand_get_fd
load->fd = fd0
ondemand_id = object_id0
------ restore ------
cachefiles_ondemand_restore
// restore REQ_A
cachefiles_daemon_read
cachefiles_ondemand_daemon_read
REQ_A = cachefiles_ondemand_select_req
cachefiles_ondemand_get_fd
load->fd = fd1
ondemand_id = object_id1
process_open_req(REQ_A)
write(devfd, ("copen %u,%llu", msg->msg_id, size))
cachefiles_ondemand_copen
xa_erase(&cache->reqs, id)
complete(&REQ_A->done)
kfree(REQ_A)
process_open_req(REQ_A)
// copen fails due to no req
// daemon close(fd1)
cachefiles_ondemand_fd_release
// set object closed
-- umount --
cachefiles_withdraw_cookie
cachefiles_ondemand_clean_object
cachefiles_ondemand_init_close_req
if (!cachefiles_ondemand_object_is_open(object))
return -ENOENT;
// The fd0 is not closed until the daemon exits.However, the anonymous fd holds the reference count of the object and the object holds the reference count of the cookie. So even though the cookie has been relinquished, it will not be unhashed and freed until the daemon exits.
In fscache_hash_cookie(), when the same cookie is found in the hash list, if the cookie is set with the FSCACHE_COOKIE_RELINQUISHED bit, then the new cookie waits for the old cookie to be unhashed, while the old cookie is waiting for the leaked fd to be closed, if the daemon does not exit in time it will trigger a hung task.
To avoid this, allocate a new anonymous fd only if no anonymous fd has been allocated (ondemand_id == 0) or if the previously allocated anonymous fd has been closed (ondemand_id == -1). Moreover, returns an error if ondemand_id is valid, letting the daemon know that the current userland restore logic is abnormal and needs to be checked.
Stable-dep-of: 4b4391e77a6b ("cachefiles: defer exposing anon_fd until after copy_to_user() succeeds")
--- fs/cachefiles/ondemand.c | 34 ++++++++++++++++++++++++++++------ 1 file changed, 28 insertions(+), 6 deletions(-)
fs/cachefiles/ondemand.c +28 -6
@@ -14,11 +14,18 @@ static int cachefiles_ondemand_fd_release(struct inode *inode, struct file *file) {struct cachefiles_object *object = file->private_data; -struct cachefiles_cache *cache = object->volume->cache; -struct cachefiles_ondemand_info *info = object->ondemand; +struct cachefiles_cache *cache; +struct cachefiles_ondemand_info *info;int object_id;struct cachefiles_req *req; -XA_STATE (xas, &cache->reqs,0 ); +XA_STATE (xas,NULL ,0 ); + +if (!object) +return 0 ; + + info = object->ondemand; + cache = object->volume->cache; + xas.xa = &cache->reqs;xa_lock (&cache->reqs);spin_lock (&info->lock);
@@ -275,22 +282,39 @@ static int cachefiles_ondemand_get_fd(struct cachefiles_req *req) goto err_put_fd; } +spin_lock (&object->ondemand->lock); +if (object->ondemand->ondemand_id >0 ) { +spin_unlock (&object->ondemand->lock); +/* Pair with check in cachefiles_ondemand_fd_release(). */ + file->private_data =NULL ; + ret = -EEXIST ; + goto err_put_file; + } + file->f_mode |=FMODE_PWRITE |FMODE_LSEEK ;fd_install (fd, file); load = (void *)req->msg.data; load->fd = fd; object->ondemand->ondemand_id = object_id; +spin_unlock (&object->ondemand->lock);cachefiles_get_unbind_pincount (cache);trace_cachefiles_ondemand_open (object, &req->msg, load);return 0 ; +err_put_file: +fput (file); err_put_fd:put_unused_fd (fd); err_free_id:xa_erase (&cache->ondemand_ids, object_id); err: +spin_lock (&object->ondemand->lock); +/* Avoid marking an opened object as closed. */ +if (object->ondemand->ondemand_id <=0 ) +cachefiles_ondemand_set_object_close (object); +spin_unlock (&object->ondemand->lock);cachefiles_put_object (object, cachefiles_obj_put_ondemand_fd);return ret; }
@@ -373,10 +397,8 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,if (msg->opcode ==CACHEFILES_OP_OPEN ) { ret =cachefiles_ondemand_get_fd (req); -if (ret) { -cachefiles_ondemand_set_object_close (req->object); +if (ret) goto out; - } } msg->msg_id = xas.xa_index;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 116/217 cachefiles: defer exposing anon_fd until after copy_to_user() succeeds
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Baokun Li <[email protected]>
[ Upstream commit 4b4391e77a6bf24cba2ef1590e113d9b73b11039 ]
After installing the anonymous fd, we can now see it in userland and close it. However, at this point we may not have gotten the reference count of the cache, but we will put it during colse fd, so this may cause a cache UAF.
So grab the cache reference count before fd_install(). In addition, by kernel convention, fd is taken over by the user land after fd_install(), and the kernel should not call close_fd() after that, i.e., it should call fd_install() after everything is ready, thus fd_install() is called after copy_to_user() succeeds.
--- fs/cachefiles/ondemand.c | 53 +++++++++++++++++++++++++--------------- 1 file changed, 33 insertions(+), 20 deletions(-)
fs/cachefiles/ondemand.c +33 -20
@@ -4,6 +4,11 @@#include <linux/uio.h> #include "internal.h" +struct ondemand_anon_file { +struct file *file; +int fd; +}; +static inline void cachefiles_req_put (struct cachefiles_req *req) {if (refcount_dec_and_test (&req->ref))
@@ -250,14 +255,14 @@ int cachefiles_ondemand_restore(struct cachefiles_cache *cache, char *args)return 0 ; } -static int cachefiles_ondemand_get_fd (struct cachefiles_req *req) +static int cachefiles_ondemand_get_fd (struct cachefiles_req *req, +struct ondemand_anon_file *anon_file) {struct cachefiles_object *object;struct cachefiles_cache *cache;struct cachefiles_open *load; -struct file *file;u32 object_id; -int ret, fd; +int ret; object =cachefiles_grab_object (req->object, cachefiles_obj_get_ondemand_fd);
@@ -269,16 +274,16 @@ static int cachefiles_ondemand_get_fd(struct cachefiles_req *req)if (ret <0 ) goto err; - fd =get_unused_fd_flags (O_WRONLY ); -if (fd <0 ) { - ret = fd; + anon_file->fd =get_unused_fd_flags (O_WRONLY ); +if (anon_file->fd <0 ) { + ret = anon_file->fd; goto err_free_id; } - file =anon_inode_getfile ("[cachefiles]" , &cachefiles_ondemand_fd_fops, - object,O_WRONLY ); -if (IS_ERR (file)) { - ret =PTR_ERR (file); + anon_file->file =anon_inode_getfile ("[cachefiles]" , + &cachefiles_ondemand_fd_fops, object,O_WRONLY ); +if (IS_ERR (anon_file->file)) { + ret =PTR_ERR (anon_file->file); goto err_put_fd; }
@@ -286,16 +291,15 @@ static int cachefiles_ondemand_get_fd(struct cachefiles_req *req)if (object->ondemand->ondemand_id >0 ) {spin_unlock (&object->ondemand->lock);/* Pair with check in cachefiles_ondemand_fd_release(). */ - file->private_data =NULL ; + anon_file->file->private_data =NULL ; ret = -EEXIST ; goto err_put_file; } - file->f_mode |=FMODE_PWRITE |FMODE_LSEEK ; -fd_install (fd, file); + anon_file->file->f_mode |=FMODE_PWRITE |FMODE_LSEEK ; load = (void *)req->msg.data; - load->fd = fd; + load->fd = anon_file->fd; object->ondemand->ondemand_id = object_id;spin_unlock (&object->ondemand->lock);
@@ -304,9 +308,11 @@ static int cachefiles_ondemand_get_fd(struct cachefiles_req *req)return 0 ; err_put_file: -fput (file); +fput (anon_file->file); + anon_file->file =NULL ; err_put_fd: -put_unused_fd (fd); +put_unused_fd (anon_file->fd); + anon_file->fd = ret; err_free_id:xa_erase (&cache->ondemand_ids, object_id); err:
@@ -363,6 +369,7 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,struct cachefiles_msg *msg;size_t n;int ret =0 ; +struct ondemand_anon_file anon_file;XA_STATE (xas, &cache->reqs, cache->req_id_next);xa_lock (&cache->reqs);
@@ -396,7 +403,7 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,xa_unlock (&cache->reqs);if (msg->opcode ==CACHEFILES_OP_OPEN ) { - ret =cachefiles_ondemand_get_fd (req); + ret =cachefiles_ondemand_get_fd (req, &anon_file);if (ret) goto out; }
@@ -404,10 +411,16 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, msg->msg_id = xas.xa_index; msg->object_id = req->object->ondemand->ondemand_id; -if (copy_to_user (_buffer, msg, n) !=0 ) { +if (copy_to_user (_buffer, msg, n) !=0 ) ret = -EFAULT ; -if (msg->opcode ==CACHEFILES_OP_OPEN ) -close_fd (((struct cachefiles_open *)msg->data)->fd); + +if (msg->opcode ==CACHEFILES_OP_OPEN ) { +if (ret <0 ) { +fput (anon_file.file); +put_unused_fd (anon_file.fd); + goto out; + } +fd_install (anon_file.fd, anon_file.file); } out:cachefiles_put_object (req->object, cachefiles_obj_put_read_req);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 117/217 cachefiles: flush all requests after setting CACHEFILES_DEAD
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Baokun Li <[email protected]>
[ Upstream commit 85e833cd7243bda7285492b0653c3abb1e2e757b ]
In ondemand mode, when the daemon is processing an open request, if the kernel flags the cache as CACHEFILES_DEAD, the cachefiles_daemon_write() will always return -EIO, so the daemon can't pass the copen to the kernel. Then the kernel process that is waiting for the copen triggers a hung_task.
Since the DEAD state is irreversible, it can only be exited by closing /dev/cachefiles. Therefore, after calling cachefiles_io_error() to mark the cache as CACHEFILES_DEAD, if in ondemand mode, flush all requests to avoid the above hungtask. We may still be able to read some of the cached data before closing the fd of /dev/cachefiles.
Note that this relies on the patch that adds reference counting to the req, otherwise it may UAF.
--- fs/cachefiles/daemon.c | 2 +- fs/cachefiles/internal.h | 3 +++ 2 files changed, 4 insertions(+), 1 deletion(-)
fs/cachefiles/daemon.c +1 -1
@@ -133,7 +133,7 @@ static int cachefiles_daemon_open(struct inode *inode, struct file *file)return 0 ; } -static void cachefiles_flush_reqs (struct cachefiles_cache *cache) +void cachefiles_flush_reqs (struct cachefiles_cache *cache) {struct xarray *xa = &cache->reqs;struct cachefiles_req *req;
fs/cachefiles/internal.h +3 -0
@@ -188,6 +188,7 @@ extern int cachefiles_has_space(struct cachefiles_cache *cache,* daemon.c */ extern const struct file_operations cachefiles_daemon_fops; +extern void cachefiles_flush_reqs (struct cachefiles_cache *cache);extern void cachefiles_get_unbind_pincount (struct cachefiles_cache *cache);extern void cachefiles_put_unbind_pincount (struct cachefiles_cache *cache);
@@ -414,6 +415,8 @@ do { \ pr_err("I/O Error: " FMT"\n", ##__VA_ARGS__); \fscache_io_error ((___cache)->cache); \set_bit (CACHEFILES_DEAD , &(___cache)->flags); \ +if (cachefiles_in_ondemand_mode (___cache)) \ +cachefiles_flush_reqs (___cache); \ } while (0)#define cachefiles_io_error_obj (object,FMT , ...) \
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 118/217 selftests/ftrace: Fix to check required event file
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Masami Hiramatsu (Google) <[email protected]>
[ Upstream commit f6c3c83db1d939ebdb8c8922748ae647d8126d91 ]
The dynevent/test_duplicates.tc test case uses syscalls/sys_enter_openat event for defining eprobe on it. Since this syscalls events depend on CONFIG_FTRACE_SYSCALLS=y, if it is not set, the test will fail.
Add the event file to required line so that the test will return unsupported result.
--- .../testing/selftests/ftrace/test.d/dynevent/test_duplicates.tc | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/testing/selftests/ftrace/test.d/dynevent/test_duplicates.tc +1 -1
@@ -1,7 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # description: Generic dynamic event - check if duplicate events are caught -# requires: dynamic_events "e[:[<group>/][<event>]] <attached-group>.<attached-event> [<args>]":README +# requires: dynamic_events "e[:[<group>/][<event>]] <attached-group>.<attached-event> [<args>]":README events/syscalls/sys_enter_openat echo 0 > events/enable
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 101/217 gve: Clear napi->skb before dev_kfree_skb_any()
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ziwei Xiao <[email protected]>
commit 6f4d93b78ade0a4c2cafd587f7b429ce95abb02e upstream.
gve_rx_free_skb incorrectly leaves napi->skb referencing an skb after it is freed with dev_kfree_skb_any(). This can result in a subsequent call to napi_get_frags returning a dangling pointer.
Fix this by clearing napi->skb before the skb is freed.
--- drivers/net/ethernet/google/gve/gve_rx_dqo.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)
drivers/net/ethernet/google/gve/gve_rx_dqo.c +5 -3
@@ -465,11 +465,13 @@ static void gve_rx_skb_hash(struct sk_buskb_set_hash (skb,le32_to_cpu (compl_desc->hash), hash_type); } -static void gve_rx_free_skb (struct gve_rx_ring *rx) +static void gve_rx_free_skb (struct napi_struct *napi,struct gve_rx_ring *rx) {if (!rx->ctx.skb_head)return ; +if (rx->ctx.skb_head == napi->skb) + napi->skb =NULL ;dev_kfree_skb_any (rx->ctx.skb_head); rx->ctx.skb_head =NULL ; rx->ctx.skb_tail =NULL ;
@@ -693,7 +695,7 @@ int gve_rx_poll_dqo(struct gve_notify_bl err =gve_rx_dqo (napi, rx, compl_desc, rx->q_num);if (err <0 ) { -gve_rx_free_skb (rx); +gve_rx_free_skb (napi, rx);u64_stats_update_begin (&rx->statss);if (err == -ENOMEM ) rx->rx_skb_alloc_fail++;
@@ -736,7 +738,7 @@ int gve_rx_poll_dqo(struct gve_notify_bl/* gve_rx_complete_skb() will consume skb if successful */ if (gve_rx_complete_skb (rx, napi, compl_desc, feat) !=0 ) { -gve_rx_free_skb (rx); +gve_rx_free_skb (napi, rx);u64_stats_update_begin (&rx->statss); rx->rx_desc_err_dropped_pkt++;u64_stats_update_end (&rx->statss);
Greg Kroah-Hartman
maintainerPATCH 119/217 clk: sifive: Do not register clkdevs for PRCI clocks
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Samuel Holland <[email protected]>
[ Upstream commit 2607133196c35f31892ee199ce7ffa717bea4ad1 ]
These clkdevs were unnecessary, because systems using this driver always look up clocks using the devicetree. And as Russell King points out[1], since the provided device name was truncated, lookups via clkdev would never match.
Recently, commit 8d532528ff6a ("clkdev: report over-sized strings when creating clkdev entries") caused clkdev registration to fail due to the truncation, and this now prevents the driver from probing. Fix the driver by removing the clkdev registration.
--- drivers/clk/sifive/sifive-prci.c | 8 -------- 1 file changed, 8 deletions(-)
drivers/clk/sifive/sifive-prci.c +0 -8
@@ -4,7 +4,6 @@* Copyright (C) 2020 Zong Li */ -#include <linux/clkdev.h> #include <linux/delay.h> #include <linux/io.h> #include <linux/of_device.h>
@@ -536,13 +535,6 @@ static int __prci_register_clocks(struct device *dev, struct __prci_data *pd,return r; } - r =clk_hw_register_clkdev (&pic->hw, pic->name,dev_name (dev)); -if (r) { -dev_warn (dev,"Failed to register clkdev for %s: %d\n" , - init.name, r); -return r; - } - pd->hw_clks.hws[i] = &pic->hw; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 120/217 NFSv4.1 enforce rootpath check in fs_location query
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Olga Kornievskaia <[email protected]>
[ Upstream commit 28568c906c1bb5f7560e18082ed7d6295860f1c2 ]
In commit 4ca9f31a2be66 ("NFSv4.1 test and add 4.1 trunking transport"), we introduce the ability to query the NFS server for possible trunking locations of the existing filesystem. However, we never checked the returned file system path for these alternative locations. According to the RFC, the server can say that the filesystem currently known under "fs_root" of fs_location also resides under these server locations under the following "rootpath" pathname. The client cannot handle trunking a filesystem that reside under different location under different paths other than what the main path is. This patch enforces the check that fs_root path and rootpath path in fs_location reply is the same.
--- fs/nfs/nfs4proc.c | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-)
fs/nfs/nfs4proc.c +22 -1
@@ -4009,6 +4009,23 @@ static void test_fs_location_for_trunking(struct nfs4_fs_location *location, } } +static bool _is_same_nfs4_pathname (struct nfs4_pathname *path1, +struct nfs4_pathname *path2) +{ +int i; + +if (path1->ncomponents != path2->ncomponents) +return false; +for (i =0 ; i < path1->ncomponents; i++) { +if (path1->components[i].len != path2->components[i].len) +return false; +if (memcmp (path1->components[i].data, path2->components[i].data, + path1->components[i].len)) +return false; + } +return true; +} +static int _nfs4_discover_trunking (struct nfs_server *server,struct nfs_fh *fhandle) {
@@ -4042,9 +4059,13 @@ static int _nfs4_discover_trunking(struct nfs_server *server,if (status) goto out_free_3; -for (i =0 ; i < locations->nlocations; i++) +for (i =0 ; i < locations->nlocations; i++) { +if (!_is_same_nfs4_pathname (&locations->fs_path, + &locations->locations[i].rootpath)) +continue ;test_fs_location_for_trunking (&locations->locations[i], clp, server); + } out_free_3:kfree (locations->fattr); out_free_2:
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 121/217 SUNRPC: return proper error from gss_wrap_req_priv
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Chen Hanxiao <[email protected]>
[ Upstream commit 33c94d7e3cb84f6d130678d6d59ba475a6c489cf ]
don't return 0 if snd_buf->len really greater than snd_buf->buflen
--- net/sunrpc/auth_gss/auth_gss.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
net/sunrpc/auth_gss/auth_gss.c +3 -1
@@ -1858,8 +1858,10 @@ gss_wrap_req_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx, offset = (u8 *)p - (u8 *)snd_buf->head[0 ].iov_base; maj_stat =gss_wrap (ctx->gc_gss_ctx, offset, snd_buf, inpages);/* slack space should prevent this ever happening: */ -if (unlikely (snd_buf->len > snd_buf->buflen)) +if (unlikely (snd_buf->len > snd_buf->buflen)) { + status = -EIO ; goto wrap_failed; + }/* We're assuming that when GSS_S_CONTEXT_EXPIRED, the encryption was * done anyway, so it's safe to put the request on the wire: */ if (maj_stat ==GSS_S_CONTEXT_EXPIRED )
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 122/217 NFS: add barriers when testing for NFS_FSDATA_BLOCKED
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: NeilBrown <[email protected]>
[ Upstream commit 99bc9f2eb3f79a2b4296d9bf43153e1d10ca50d3 ]
dentry->d_fsdata is set to NFS_FSDATA_BLOCKED while unlinking or renaming-over a file to ensure that no open succeeds while the NFS operation progressed on the server.
Setting dentry->d_fsdata to NFS_FSDATA_BLOCKED is done under ->d_lock after checking the refcount is not elevated. Any attempt to open the file (through that name) will go through lookp_open() which will take ->d_lock while incrementing the refcount, we can be sure that once the new value is set, __nfs_lookup_revalidate() *will* see the new value and will block.
We don't have any locking guarantee that when we set ->d_fsdata to NULL, the wait_var_event() in __nfs_lookup_revalidate() will notice. wait/wake primitives do NOT provide barriers to guarantee order. We must use smp_load_acquire() in wait_var_event() to ensure we look at an up-to-date value, and must use smp_store_release() before wake_up_var().
This patch adds those barrier functions and factors out block_revalidate() and unblock_revalidate() far clarity.
There is also a hypothetical bug in that if memory allocation fails (which never happens in practice) we might leave ->d_fsdata locked. This patch adds the missing call to unblock_revalidate().
--- fs/nfs/dir.c | 47 ++++++++++++++++++++++++++++++++--------------- 1 file changed, 32 insertions(+), 15 deletions(-)
fs/nfs/dir.c +32 -15
@@ -1792,9 +1792,10 @@ __nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags,if (parent !=READ_ONCE (dentry->d_parent))return -ECHILD ; }else { -/* Wait for unlink to complete */ +/* Wait for unlink to complete - see unblock_revalidate() */ wait_var_event (&dentry->d_fsdata, - dentry->d_fsdata !=NFS_FSDATA_BLOCKED ); +smp_load_acquire (&dentry->d_fsdata) + !=NFS_FSDATA_BLOCKED ); parent =dget_parent (dentry); ret =reval (d_inode (parent), dentry, flags);dput (parent);
@@ -1807,6 +1808,29 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)return __nfs_lookup_revalidate (dentry, flags, nfs_do_lookup_revalidate); } +static void block_revalidate (struct dentry *dentry) +{ +/* old devname - just in case */ +kfree (dentry->d_fsdata); + +/* Any new reference that could lead to an open +* will take ->d_lock in lookup_open() -> d_lookup(). +* Holding this lock ensures we cannot race with +* __nfs_lookup_revalidate() and removes and need +* for further barriers. +*/ +lockdep_assert_held (&dentry->d_lock); + + dentry->d_fsdata =NFS_FSDATA_BLOCKED ; +} + +static void unblock_revalidate (struct dentry *dentry) +{ +/* store_release ensures wait_var_event() sees the update */ +smp_store_release (&dentry->d_fsdata,NULL ); +wake_up_var (&dentry->d_fsdata); +} +/* * A weaker form of d_revalidate for revalidating just the d_inode(dentry) * when we don't really care about the dentry name. This is called when a
@@ -2489,15 +2513,12 @@ int nfs_unlink(struct inode *dir, struct dentry *dentry)spin_unlock (&dentry->d_lock); goto out; } -/* old devname */ -kfree (dentry->d_fsdata); - dentry->d_fsdata =NFS_FSDATA_BLOCKED ; +block_revalidate (dentry);spin_unlock (&dentry->d_lock); error =nfs_safe_remove (dentry);nfs_dentry_remove_handle_error (dir, dentry, error); - dentry->d_fsdata =NULL ; -wake_up_var (&dentry->d_fsdata); +unblock_revalidate (dentry); out:trace_nfs_unlink_exit (dir, dentry, error);return error;
@@ -2609,8 +2630,7 @@ nfs_unblock_rename(struct rpc_task *task, struct nfs_renamedata *data) {struct dentry *new_dentry = data->new_dentry; - new_dentry->d_fsdata =NULL ; -wake_up_var (&new_dentry->d_fsdata); +unblock_revalidate (new_dentry); }/*
@@ -2672,11 +2692,6 @@ int nfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir,if (WARN_ON (new_dentry->d_flags &DCACHE_NFSFS_RENAMED ) ||WARN_ON (new_dentry->d_fsdata ==NFS_FSDATA_BLOCKED )) goto out; -if (new_dentry->d_fsdata) { -/* old devname */ -kfree (new_dentry->d_fsdata); - new_dentry->d_fsdata =NULL ; - }spin_lock (&new_dentry->d_lock);if (d_count (new_dentry) >2 ) {
@@ -2698,7 +2713,7 @@ int nfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, new_dentry = dentry; new_inode =NULL ; }else { - new_dentry->d_fsdata =NFS_FSDATA_BLOCKED ; +block_revalidate (new_dentry); must_unblock = true;spin_unlock (&new_dentry->d_lock); }
@@ -2710,6 +2725,8 @@ int nfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, task =nfs_async_rename (old_dir, new_dir, old_dentry, new_dentry, must_unblock ? nfs_unblock_rename :NULL );if (IS_ERR (task)) { +if (must_unblock) +unblock_revalidate (new_dentry); error =PTR_ERR (task); goto out; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 123/217 platform/x86: dell-smbios: Fix wrong token data in sysfs
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Armin Wolf <[email protected]>
[ Upstream commit 1981b296f858010eae409548fd297659b2cc570e ]
When reading token data from sysfs on my Inspiron 3505, the token locations and values are wrong. This happens because match_attribute() blindly assumes that all entries in da_tokens have an associated entry in token_attrs.
This however is not true as soon as da_tokens[] contains zeroed token entries. Those entries are being skipped when initialising token_attrs, breaking the core assumption of match_attribute().
Fix this by defining an extra struct for each pair of token attributes and use container_of() to retrieve token information.
Tested on a Dell Inspiron 3050.
--- drivers/platform/x86/dell/dell-smbios-base.c | 92 ++++++++------------ 1 file changed, 36 insertions(+), 56 deletions(-)
drivers/platform/x86/dell/dell-smbios-base.c +36 -56
@@ -11,6 +11,7 @@*/ #define pr_fmt (fmt) KBUILD_MODNAME ": " fmt +#include <linux/container_of.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/capability.h>
@@ -25,11 +26,16 @@ static u32 da_supported_commands;static int da_num_tokens;static struct platform_device *platform_device;static struct calling_interface_token *da_tokens; -static struct device_attribute *token_location_attrs; -static struct device_attribute *token_value_attrs; +static struct token_sysfs_data *token_entries;static struct attribute **token_attrs;static DEFINE_MUTEX (smbios_mutex); +struct token_sysfs_data { +struct device_attribute location_attr; +struct device_attribute value_attr; +struct calling_interface_token *token; +}; +struct smbios_device {struct list_head list;struct device *device;
@@ -416,47 +422,26 @@ static void __init find_tokens(const struct dmi_header *dm, void *dummy) } } -static int match_attribute (struct device *dev, -struct device_attribute *attr) -{ -int i; - -for (i =0 ; i < da_num_tokens *2 ; i++) { -if (!token_attrs[i]) -continue ; -if (strcmp (token_attrs[i]->name, attr->attr.name) ==0 ) -return i/2 ; - } -dev_dbg (dev,"couldn't match: %s\n" , attr->attr.name); -return -EINVAL ; -} -static ssize_t location_show (struct device *dev,struct device_attribute *attr,char *buf) { -int i; + struct token_sysfs_data *data = container_of(attr, struct token_sysfs_data, location_attr);if (!capable (CAP_SYS_ADMIN ))return -EPERM ; - i =match_attribute (dev, attr); -if (i >0 ) -return sysfs_emit (buf,"%08x" , da_tokens[i].location); -return 0 ; +return sysfs_emit (buf,"%08x" , data->token->location); }static ssize_t value_show (struct device *dev,struct device_attribute *attr,char *buf) { -int i; + struct token_sysfs_data *data = container_of(attr, struct token_sysfs_data, value_attr);if (!capable (CAP_SYS_ADMIN ))return -EPERM ; - i =match_attribute (dev, attr); -if (i >0 ) -return sysfs_emit (buf,"%08x" , da_tokens[i].value); -return 0 ; +return sysfs_emit (buf,"%08x" , data->token->value); }static struct attribute_group smbios_attribute_group = {
@@ -473,22 +458,15 @@ static int build_tokens_sysfs(struct platform_device *dev) {char *location_name;char *value_name; -size_t size;int ret;int i, j; -/* (number of tokens + 1 for null terminated */ - size =sizeof (struct device_attribute ) * (da_num_tokens +1 ); - token_location_attrs =kzalloc (size,GFP_KERNEL ); -if (!token_location_attrs) + token_entries =kcalloc (da_num_tokens,sizeof (*token_entries),GFP_KERNEL ); +if (!token_entries)return -ENOMEM ; - token_value_attrs =kzalloc (size,GFP_KERNEL ); -if (!token_value_attrs) - goto out_allocate_value;/* need to store both location and value + terminator*/ - size =sizeof (struct attribute *) * ((2 * da_num_tokens) +1 ); - token_attrs =kzalloc (size,GFP_KERNEL ); + token_attrs =kcalloc ((2 * da_num_tokens) +1 ,sizeof (*token_attrs),GFP_KERNEL );if (!token_attrs) goto out_allocate_attrs;
@@ -496,27 +474,32 @@ static int build_tokens_sysfs(struct platform_device *dev)/* skip empty */ if (da_tokens[i].tokenID ==0 )continue ; + + token_entries[i].token = &da_tokens[i]; +/* add location */ location_name =kasprintf (GFP_KERNEL ,"%04x_location" , da_tokens[i].tokenID);if (location_name ==NULL ) goto out_unwind_strings; -sysfs_attr_init (&token_location_attrs[i].attr); - token_location_attrs[i].attr.name = location_name; - token_location_attrs[i].attr.mode =0444 ; - token_location_attrs[i].show = location_show; - token_attrs[j++] = &token_location_attrs[i].attr; + +sysfs_attr_init (&token_entries[i].location_attr.attr); + token_entries[i].location_attr.attr.name = location_name; + token_entries[i].location_attr.attr.mode =0444 ; + token_entries[i].location_attr.show = location_show; + token_attrs[j++] = &token_entries[i].location_attr.attr;/* add value */ value_name =kasprintf (GFP_KERNEL ,"%04x_value" , da_tokens[i].tokenID);if (value_name ==NULL ) goto loop_fail_create_value; -sysfs_attr_init (&token_value_attrs[i].attr); - token_value_attrs[i].attr.name = value_name; - token_value_attrs[i].attr.mode =0444 ; - token_value_attrs[i].show = value_show; - token_attrs[j++] = &token_value_attrs[i].attr; + +sysfs_attr_init (&token_entries[i].value_attr.attr); + token_entries[i].value_attr.attr.name = value_name; + token_entries[i].value_attr.attr.mode =0444 ; + token_entries[i].value_attr.show = value_show; + token_attrs[j++] = &token_entries[i].value_attr.attr;continue ; loop_fail_create_value:
@@ -532,14 +515,12 @@ static int build_tokens_sysfs(struct platform_device *dev) out_unwind_strings:while (i--) { -kfree (token_location_attrs[i].attr.name); -kfree (token_value_attrs[i].attr.name); +kfree (token_entries[i].location_attr.attr.name); +kfree (token_entries[i].value_attr.attr.name); }kfree (token_attrs); out_allocate_attrs: -kfree (token_value_attrs); -out_allocate_value: -kfree (token_location_attrs); +kfree (token_entries);return -ENOMEM ; }
@@ -551,12 +532,11 @@ static void free_group(struct platform_device *pdev)sysfs_remove_group (&pdev->dev.kobj, &smbios_attribute_group);for (i =0 ; i < da_num_tokens; i++) { -kfree (token_location_attrs[i].attr.name); -kfree (token_value_attrs[i].attr.name); +kfree (token_entries[i].location_attr.attr.name); +kfree (token_entries[i].value_attr.attr.name); }kfree (token_attrs); -kfree (token_value_attrs); -kfree (token_location_attrs); +kfree (token_entries); }static int __init dell_smbios_init (void )
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 124/217 gpio: tqmx86: fix typo in Kconfig label
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Gregor Herburger <[email protected]>
[ Upstream commit 8c219e52ca4d9a67cd6a7074e91bf29b55edc075 ]
Fix description for GPIO_TQMX86 from QTMX86 to TQMx86.
--- drivers/gpio/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpio/Kconfig +1 -1
@@ -1416,7 +1416,7 @@ config GPIO_TPS68470 are "output only" GPIOs. config GPIO_TQMX86 - tristate "TQ-Systems QTMX86 GPIO" + tristate "TQ-Systems TQMx86 GPIO" depends on MFD_TQMX86 || COMPILE_TEST depends on HAS_IOPORT_MAP select GPIOLIB_IRQCHIP
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 125/217 gpio: tqmx86: remove unneeded call to platform_set_drvdata()
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Andrei Coardos <[email protected]>
[ Upstream commit 0a5e9306b812fe3517548fab92b3d3d6ce7576e5 ]
This function call was found to be unnecessary as there is no equivalent platform_get_drvdata() call to access the private data of the driver. Also, the private data is defined in this driver, so there is no risk of it being accessed outside of this driver file.
Stable-dep-of: 9d6a811b522b ("gpio: tqmx86: introduce shadow register for GPIO output value")
--- drivers/gpio/gpio-tqmx86.c | 2 -- 1 file changed, 2 deletions(-)
drivers/gpio/gpio-tqmx86.c +0 -2
@@ -259,8 +259,6 @@ static int tqmx86_gpio_probe(struct platform_device *pdev)tqmx86_gpio_write (gpio, (u8 )~TQMX86_DIR_INPUT_MASK ,TQMX86_GPIODD ); -platform_set_drvdata (pdev, gpio); - chip = &gpio->chip; chip->label ="gpio-tqmx86" ; chip->owner =THIS_MODULE ;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 126/217 gpio: tqmx86: introduce shadow register for GPIO output value
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Matthias Schiffer <[email protected]>
[ Upstream commit 9d6a811b522ba558bcb4ec01d12e72a0af8e9f6e ]
The TQMx86 GPIO controller uses the same register address for input and output data. Reading the register will always return current inputs rather than the previously set outputs (regardless of the current direction setting). Therefore, using a RMW pattern does not make sense when setting output values. Instead, the previously set output register value needs to be stored as a shadow register.
As there is no reliable way to get the current output values from the hardware, also initialize all channels to 0, to ensure that stored and actual output values match. This should usually not have any effect in practise, as the TQMx86 UEFI sets all outputs to 0 during boot.
Also prepare for extension of the driver to more than 8 GPIOs by using DECLARE_BITMAP.
--- drivers/gpio/gpio-tqmx86.c | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-)
drivers/gpio/gpio-tqmx86.c +11 -7
@@ -6,6 +6,7 @@* Vadim V.Vlasov <[email protected]> */ +#include <linux/bitmap.h> #include <linux/bitops.h> #include <linux/errno.h> #include <linux/gpio/driver.h>
@@ -38,6 +39,7 @@ struct tqmx86_gpio_data {void __iomem *io_base;int irq;raw_spinlock_t spinlock; +DECLARE_BITMAP (output,TQMX86_NGPIO );u8 irq_type[TQMX86_NGPI ]; };
@@ -64,15 +66,10 @@ static void tqmx86_gpio_set(struct gpio_chip *chip, unsigned int offset, {struct tqmx86_gpio_data *gpio =gpiochip_get_data (chip);unsigned long flags; -u8 val;raw_spin_lock_irqsave (&gpio->spinlock, flags); - val =tqmx86_gpio_read (gpio,TQMX86_GPIOD ); -if (value) - val |=BIT (offset); -else - val &= ~BIT (offset); -tqmx86_gpio_write (gpio, val,TQMX86_GPIOD ); +__assign_bit (offset, gpio->output, value); +tqmx86_gpio_write (gpio,bitmap_get_value8 (gpio->output,0 ),TQMX86_GPIOD );raw_spin_unlock_irqrestore (&gpio->spinlock, flags); }
@@ -259,6 +256,13 @@ static int tqmx86_gpio_probe(struct platform_device *pdev)tqmx86_gpio_write (gpio, (u8 )~TQMX86_DIR_INPUT_MASK ,TQMX86_GPIODD ); +/* +* Reading the previous output state is not possible with TQMx86 hardware. +* Initialize all outputs to 0 to have a defined state that matches the +* shadow register. +*/ +tqmx86_gpio_write (gpio,0 ,TQMX86_GPIOD ); + chip = &gpio->chip; chip->label ="gpio-tqmx86" ; chip->owner =THIS_MODULE ;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 127/217 gpio: tqmx86: Convert to immutable irq_chip
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Linus Walleij <[email protected]>
[ Upstream commit 8e43827b6ae727a745ce7a8cc19184b28905a965 ]
Convert the driver to immutable irq-chip with a bit of intuition.
Stable-dep-of: 08af509efdf8 ("gpio: tqmx86: store IRQ trigger type and unmask status separately")
--- drivers/gpio/gpio-tqmx86.c | 28 ++++++++++++++++++++-------- 1 file changed, 20 insertions(+), 8 deletions(-)
drivers/gpio/gpio-tqmx86.c +20 -8
@@ -16,6 +16,7 @@#include <linux/module.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> +#include <linux/seq_file.h> #include <linux/slab.h> #define TQMX86_NGPIO 8
@@ -35,7 +36,6 @@struct tqmx86_gpio_data {struct gpio_chip chip; -struct irq_chip irq_chip;void __iomem *io_base;int irq;raw_spinlock_t spinlock;
@@ -119,6 +119,7 @@ static void tqmx86_gpio_irq_mask(struct irq_data *data) gpiic &= ~mask;tqmx86_gpio_write (gpio, gpiic,TQMX86_GPIIC );raw_spin_unlock_irqrestore (&gpio->spinlock, flags); +gpiochip_disable_irq (&gpio->chip,irqd_to_hwirq (data)); }static void tqmx86_gpio_irq_unmask (struct irq_data *data)
@@ -131,6 +132,7 @@ static void tqmx86_gpio_irq_unmask(struct irq_data *data) mask =TQMX86_GPII_MASK << (offset *TQMX86_GPII_BITS ); +gpiochip_enable_irq (&gpio->chip,irqd_to_hwirq (data));raw_spin_lock_irqsave (&gpio->spinlock, flags); gpiic =tqmx86_gpio_read (gpio,TQMX86_GPIIC ); gpiic &= ~mask;
@@ -223,6 +225,22 @@ static void tqmx86_init_irq_valid_mask(struct gpio_chip *chip,clear_bit (3 , valid_mask); } +static void tqmx86_gpio_irq_print_chip (struct irq_data *d,struct seq_file *p) +{ +struct gpio_chip *gc =irq_data_get_irq_chip_data (d); + +seq_printf (p, gc->label); +} + +static const struct irq_chip tqmx86_gpio_irq_chip = { + .irq_mask = tqmx86_gpio_irq_mask, + .irq_unmask = tqmx86_gpio_irq_unmask, + .irq_set_type = tqmx86_gpio_irq_set_type, + .irq_print_chip = tqmx86_gpio_irq_print_chip, + .flags =IRQCHIP_IMMUTABLE , +GPIOCHIP_IRQ_RESOURCE_HELPERS , +}; +static int tqmx86_gpio_probe (struct platform_device *pdev) {struct device *dev = &pdev->dev;
@@ -279,14 +297,8 @@ static int tqmx86_gpio_probe(struct platform_device *pdev)pm_runtime_enable (&pdev->dev);if (irq >0 ) { -struct irq_chip *irq_chip = &gpio->irq_chip;u8 irq_status; - irq_chip->name = chip->label; - irq_chip->irq_mask = tqmx86_gpio_irq_mask; - irq_chip->irq_unmask = tqmx86_gpio_irq_unmask; - irq_chip->irq_set_type = tqmx86_gpio_irq_set_type; -/* Mask all interrupts */ tqmx86_gpio_write (gpio,0 ,TQMX86_GPIIC );
@@ -295,7 +307,7 @@ static int tqmx86_gpio_probe(struct platform_device *pdev)tqmx86_gpio_write (gpio, irq_status,TQMX86_GPIIS ); girq = &chip->irq; - girq->chip = irq_chip; +gpio_irq_chip_set_chip (girq, &tqmx86_gpio_irq_chip); girq->parent_handler = tqmx86_gpio_irq_handler; girq->num_parents =1 ; girq->parents = devm_kcalloc(&pdev->dev, 1,
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 128/217 gpio: tqmx86: store IRQ trigger type and unmask status separately
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Matthias Schiffer <[email protected]>
[ Upstream commit 08af509efdf8dad08e972b48de0e2c2a7919ea8b ]
irq_set_type() should not implicitly unmask the IRQ.
All accesses to the interrupt configuration register are moved to a new helper tqmx86_gpio_irq_config(). We also introduce the new rule that accessing irq_type must happen while locked, which will become significant for fixing EDGE_BOTH handling.
--- drivers/gpio/gpio-tqmx86.c | 48 ++++++++++++++++++++++---------------- 1 file changed, 28 insertions(+), 20 deletions(-)
drivers/gpio/gpio-tqmx86.c +28 -20
@@ -29,15 +29,19 @@#define TQMX86_GPIIC 3/* GPI Interrupt Configuration Register */ #define TQMX86_GPIIS 4/* GPI Interrupt Status Register */ +#define TQMX86_GPII_NONE 0#define TQMX86_GPII_FALLING BIT(0)#define TQMX86_GPII_RISING BIT(1)#define TQMX86_GPII_MASK (BIT(0) | BIT(1))#define TQMX86_GPII_BITS 2 +/* Stored in irq_type with GPII bits */ +#define TQMX86_INT_UNMASKED BIT(2)struct tqmx86_gpio_data {struct gpio_chip chip;void __iomem *io_base;int irq; +/* Lock must be held for accessing output and irq_type fields */ raw_spinlock_t spinlock; DECLARE_BITMAP(output, TQMX86_NGPIO);u8 irq_type[TQMX86_NGPI ];
@@ -104,21 +108,32 @@ static int tqmx86_gpio_get_direction(struct gpio_chip *chip,return GPIO_LINE_DIRECTION_OUT ; } +static void tqmx86_gpio_irq_config (struct tqmx86_gpio_data *gpio,int offset) + __must_hold(&gpio->spinlock) +{ +u8 type =TQMX86_GPII_NONE , gpiic; + +if (gpio->irq_type[offset] &TQMX86_INT_UNMASKED ) + type = gpio->irq_type[offset] &TQMX86_GPII_MASK ; + + gpiic =tqmx86_gpio_read (gpio,TQMX86_GPIIC ); + gpiic &= ~(TQMX86_GPII_MASK << (offset *TQMX86_GPII_BITS )); + gpiic |= type << (offset *TQMX86_GPII_BITS ); +tqmx86_gpio_write (gpio, gpiic,TQMX86_GPIIC ); +} +static void tqmx86_gpio_irq_mask (struct irq_data *data) {unsigned int offset = (data->hwirq -TQMX86_NGPO );struct tqmx86_gpio_data *gpio =gpiochip_get_data (irq_data_get_irq_chip_data (data));unsigned long flags; -u8 gpiic, mask; - - mask =TQMX86_GPII_MASK << (offset *TQMX86_GPII_BITS );raw_spin_lock_irqsave (&gpio->spinlock, flags); - gpiic =tqmx86_gpio_read (gpio,TQMX86_GPIIC ); - gpiic &= ~mask; -tqmx86_gpio_write (gpio, gpiic,TQMX86_GPIIC ); + gpio->irq_type[offset] &= ~TQMX86_INT_UNMASKED ; +tqmx86_gpio_irq_config (gpio, offset);raw_spin_unlock_irqrestore (&gpio->spinlock, flags); +gpiochip_disable_irq (&gpio->chip,irqd_to_hwirq (data)); }
@@ -128,16 +143,12 @@ static void tqmx86_gpio_irq_unmask(struct irq_data *data)struct tqmx86_gpio_data *gpio =gpiochip_get_data (irq_data_get_irq_chip_data (data));unsigned long flags; -u8 gpiic, mask; - - mask =TQMX86_GPII_MASK << (offset *TQMX86_GPII_BITS );gpiochip_enable_irq (&gpio->chip,irqd_to_hwirq (data)); +raw_spin_lock_irqsave (&gpio->spinlock, flags); - gpiic =tqmx86_gpio_read (gpio,TQMX86_GPIIC ); - gpiic &= ~mask; - gpiic |= gpio->irq_type[offset] << (offset *TQMX86_GPII_BITS ); -tqmx86_gpio_write (gpio, gpiic,TQMX86_GPIIC ); + gpio->irq_type[offset] |=TQMX86_INT_UNMASKED ; +tqmx86_gpio_irq_config (gpio, offset);raw_spin_unlock_irqrestore (&gpio->spinlock, flags); }
@@ -148,7 +159,7 @@ static int tqmx86_gpio_irq_set_type(struct irq_data *data, unsigned int type)unsigned int offset = (data->hwirq -TQMX86_NGPO );unsigned int edge_type = type &IRQF_TRIGGER_MASK ;unsigned long flags; -u8 new_type, gpiic; +u8 new_type;switch (edge_type) {case IRQ_TYPE_EDGE_RISING :
@@ -164,13 +175,10 @@ static int tqmx86_gpio_irq_set_type(struct irq_data *data, unsigned int type)return -EINVAL ;/* not supported */ } - gpio->irq_type[offset] = new_type; -raw_spin_lock_irqsave (&gpio->spinlock, flags); - gpiic =tqmx86_gpio_read (gpio,TQMX86_GPIIC ); - gpiic &= ~((TQMX86_GPII_MASK ) << (offset *TQMX86_GPII_BITS )); - gpiic |= new_type << (offset *TQMX86_GPII_BITS ); -tqmx86_gpio_write (gpio, gpiic,TQMX86_GPIIC ); + gpio->irq_type[offset] &= ~TQMX86_GPII_MASK ; + gpio->irq_type[offset] |= new_type; +tqmx86_gpio_irq_config (gpio, offset);raw_spin_unlock_irqrestore (&gpio->spinlock, flags);return 0 ;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 102/217 powerpc/uaccess: Fix build errors seen with GCC 13/14
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Michael Ellerman <[email protected]>
commit 2d43cc701b96f910f50915ac4c2a0cae5deb734c upstream.
Building ppc64le_defconfig with GCC 14 fails with assembler errors:
CC fs/readdir.o
/tmp/ccdQn0mD.s: Assembler messages:
/tmp/ccdQn0mD.s:212: Error: operand out of domain (18 is not a multiple of 4) /tmp/ccdQn0mD.s:226: Error: operand out of domain (18 is not a multiple of 4) ... [6 lines]
/tmp/ccdQn0mD.s:1699: Error: operand out of domain (18 is not a multiple of 4)
A snippet of the asm shows:
# ../fs/readdir.c:210: unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end);
ld 9,0(29) # MEM[(u64 *)name_38(D) + _88 * 1], MEM[(u64 *)name_38(D) + _88 * 1]
# 210 "../fs/readdir.c" 1
1: std 9,18(8) # put_user # *__pus_addr_52, MEM[(u64 *)name_38(D) + _88 * 1]The 'std' instruction requires a 4-byte aligned displacement because it is a DS-form instruction, and as the assembler says, 18 is not a multiple of 4.
A similar error is seen with GCC 13 and CONFIG_UBSAN_SIGNED_WRAP=y.
The fix is to change the constraint on the memory operand to put_user(), from "m" which is a general memory reference to "YZ".
The "Z" constraint is documented in the GCC manual PowerPC machine constraints, and specifies a "memory operand accessed with indexed or indirect addressing". "Y" is not documented in the manual but specifies a "memory operand for a DS-form instruction". Using both allows the compiler to generate a DS-form "std" or X-form "stdx" as appropriate.
The change has to be conditional on CONFIG_PPC_KERNEL_PREFIXED because the "Y" constraint does not guarantee 4-byte alignment when prefixed instructions are enabled.
Unfortunately clang doesn't support the "Y" constraint so that has to be behind an ifdef.
Although the build error is only seen with GCC 13/14, that appears to just be luck. The constraint has been incorrect since it was first added.
--- arch/powerpc/include/asm/uaccess.h | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-)
arch/powerpc/include/asm/uaccess.h +13 -2
@@ -80,9 +80,20 @@ __pu_failed: \ : \ : label) +#ifdef CONFIG_CC_IS_CLANG +#define DS_FORM_CONSTRAINT "Z<>" +#else +#define DS_FORM_CONSTRAINT "YZ<>" +#endif +#ifdef __powerpc64__ -#define __put_user_asm2_goto (x, ptr, label) \ - __put_user_asm_goto(x, ptr, label, "std") +#define __put_user_asm2_goto (x, addr, label) \ + asm goto ("1: std%U1%X1 %0,%1 # put_user\n" \ + EX_TABLE(1b, %l2) \ + : \ + : "r" (x), DS_FORM_CONSTRAINT (*addr) \ + : \ + : label)#else /* __powerpc64__ */ #define __put_user_asm2_goto (x, addr, label) \ asm goto( \
Greg Kroah-Hartman
maintainerPATCH 129/217 gpio: tqmx86: fix broken IRQ_TYPE_EDGE_BOTH interrupt type
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Matthias Schiffer <[email protected]>
[ Upstream commit 90dd7de4ef7ba584823dfbeba834c2919a4bb55b ]
The TQMx86 GPIO controller only supports falling and rising edge triggers, but not both. Fix this by implementing a software both-edge mode that toggles the edge type after every interrupt.
--- drivers/gpio/gpio-tqmx86.c | 46 ++++++++++++++++++++++++++++++++++---- 1 file changed, 42 insertions(+), 4 deletions(-)
drivers/gpio/gpio-tqmx86.c +42 -4
@@ -32,6 +32,10 @@#define TQMX86_GPII_NONE 0#define TQMX86_GPII_FALLING BIT(0)#define TQMX86_GPII_RISING BIT(1) +/* Stored in irq_type as a trigger type, but not actually valid as a register +* value, so the name doesn't use "GPII" +*/ +#define TQMX86_INT_BOTH (BIT(0) | BIT(1))#define TQMX86_GPII_MASK (BIT(0) | BIT(1))#define TQMX86_GPII_BITS 2/* Stored in irq_type with GPII bits */
@@ -113,9 +117,15 @@ static void tqmx86_gpio_irq_config(struct tqmx86_gpio_data *gpio, int offset) {u8 type =TQMX86_GPII_NONE , gpiic; -if (gpio->irq_type[offset] &TQMX86_INT_UNMASKED ) +if (gpio->irq_type[offset] &TQMX86_INT_UNMASKED ) { type = gpio->irq_type[offset] &TQMX86_GPII_MASK ; +if (type ==TQMX86_INT_BOTH ) + type =tqmx86_gpio_get (&gpio->chip, offset +TQMX86_NGPO ) + ?TQMX86_GPII_FALLING + :TQMX86_GPII_RISING ; + } + gpiic =tqmx86_gpio_read (gpio,TQMX86_GPIIC ); gpiic &= ~(TQMX86_GPII_MASK << (offset *TQMX86_GPII_BITS )); gpiic |= type << (offset *TQMX86_GPII_BITS );
@@ -169,7 +179,7 @@ static int tqmx86_gpio_irq_set_type(struct irq_data *data, unsigned int type) new_type =TQMX86_GPII_FALLING ;break ;case IRQ_TYPE_EDGE_BOTH : - new_type =TQMX86_GPII_FALLING |TQMX86_GPII_RISING ; + new_type =TQMX86_INT_BOTH ;break ;default :return -EINVAL ;/* not supported */
@@ -189,8 +199,8 @@ static void tqmx86_gpio_irq_handler(struct irq_desc *desc)struct gpio_chip *chip =irq_desc_get_handler_data (desc);struct tqmx86_gpio_data *gpio =gpiochip_get_data (chip);struct irq_chip *irq_chip =irq_desc_get_chip (desc); -unsigned long irq_bits; -int i =0 ; +unsigned long irq_bits, flags; +int i;u8 irq_status;chained_irq_enter (irq_chip, desc);
@@ -199,6 +209,34 @@ static void tqmx86_gpio_irq_handler(struct irq_desc *desc)tqmx86_gpio_write (gpio, irq_status,TQMX86_GPIIS ); irq_bits = irq_status; + +raw_spin_lock_irqsave (&gpio->spinlock, flags); +for_each_set_bit (i, &irq_bits,TQMX86_NGPI ) { +/* +* Edge-both triggers are implemented by flipping the edge +* trigger after each interrupt, as the controller only supports +* either rising or falling edge triggers, but not both. +* +* Internally, the TQMx86 GPIO controller has separate status +* registers for rising and falling edge interrupts. GPIIC +* configures which bits from which register are visible in the +* interrupt status register GPIIS and defines what triggers the +* parent IRQ line. Writing to GPIIS always clears both rising +* and falling interrupt flags internally, regardless of the +* currently configured trigger. +* +* In consequence, we can cleanly implement the edge-both +* trigger in software by first clearing the interrupt and then +* setting the new trigger based on the current GPIO input in +* tqmx86_gpio_irq_config() - even if an edge arrives between +* reading the input and setting the trigger, we will have a new +* interrupt pending. +*/ +if ((gpio->irq_type[i] &TQMX86_GPII_MASK ) ==TQMX86_INT_BOTH ) +tqmx86_gpio_irq_config (gpio, i); + } +raw_spin_unlock_irqrestore (&gpio->spinlock, flags); +for_each_set_bit (i, &irq_bits,TQMX86_NGPI )generic_handle_domain_irq (gpio->chip.irq.domain, i +TQMX86_NGPO );
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 130/217 HID: core: remove unnecessary WARN_ON() in implement()
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Nikita Zhandarovich <[email protected]>
[ Upstream commit 4aa2dcfbad538adf7becd0034a3754e1bd01b2b5 ]
Syzkaller hit a warning [1] in a call to implement() when trying to write a value into a field of smaller size in an output report.
Since implement() already has a warn message printed out with the help of hid_warn() and value in question gets trimmed with:
... value &= m; ...
WARN_ON may be considered superfluous. Remove it to suppress future syzkaller triggers.
[1]
WARNING: CPU: 0 PID: 5084 at drivers/hid/hid-core.c:1451 implement drivers/hid/hid-core.c:1451 [inline] WARNING: CPU: 0 PID: 5084 at drivers/hid/hid-core.c:1451 hid_output_report+0x548/0x760 drivers/hid/hid-core.c:1863 Modules linked in: CPU: 0 PID: 5084 Comm: syz-executor424 Not tainted 6.9.0-rc7-syzkaller-00183-gcf87f46fd34d #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/02/2024 RIP: 0010:implement drivers/hid/hid-core.c:1451 [inline] RIP: 0010:hid_output_report+0x548/0x760 drivers/hid/hid-core.c:1863 ... Call Trace: <TASK> __usbhid_submit_report drivers/hid/usbhid/hid-core.c:591 [inline] usbhid_submit_report+0x43d/0x9e0 drivers/hid/usbhid/hid-core.c:636 hiddev_ioctl+0x138b/0x1f00 drivers/hid/usbhid/hiddev.c:726 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:904 [inline] __se_sys_ioctl+0xfc/0x170 fs/ioctl.c:890 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf5/0x240 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f
...
--- drivers/hid/hid-core.c | 1 - 1 file changed, 1 deletion(-)
drivers/hid/hid-core.c +0 -1
@@ -1451,7 +1451,6 @@ static void implement(const struct hid_device *hid, u8 *report,hid_warn (hid,"%s() called with too large value %d (n: %d)! (%s)\n" , __func__, value, n, current->comm); -WARN_ON (1 ); value &= m; } }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 131/217 iommu/amd: Fix sysfs leak in iommu init
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kun(llfl) <[email protected]>
[ Upstream commit a295ec52c8624883885396fde7b4df1a179627c3 ]
During the iommu initialization, iommu_init_pci() adds sysfs nodes. However, these nodes aren't remove in free_iommu_resources() subsequently.
--- drivers/iommu/amd/init.c | 9 +++++++++ 1 file changed, 9 insertions(+)
drivers/iommu/amd/init.c +9 -0
@@ -1655,8 +1655,17 @@ static void __init free_pci_segments(void) } } +static void __init free_sysfs (struct amd_iommu *iommu) +{ +if (iommu->iommu.dev) { +iommu_device_unregister (&iommu->iommu); +iommu_device_sysfs_remove (&iommu->iommu); + } +} +static void __init free_iommu_one (struct amd_iommu *iommu) { +free_sysfs (iommu);free_cwwb_sem (iommu);free_command_buffer (iommu);free_event_buffer (iommu);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 132/217 HID: logitech-dj: Fix memory leak in logi_dj_recv_switch_to_dj_mode()
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: José Expósito <[email protected]>
[ Upstream commit ce3af2ee95170b7d9e15fff6e500d67deab1e7b3 ]
Fix a memory leak on logi_dj_recv_send_report() error path.
--- drivers/hid/hid-logitech-dj.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/hid/hid-logitech-dj.c +3 -1
@@ -1284,8 +1284,10 @@ static int logi_dj_recv_switch_to_dj_mode(struct dj_receiver_dev *djrcv_dev,*/ msleep (50 ); -if (retval) +if (retval) { +kfree (dj_report);return retval; + } }/*
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 103/217 Input: try trimming too long modalias strings
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Dmitry Torokhov <[email protected]>
commit 0774d19038c496f0c3602fb505c43e1b2d8eed85 upstream.
If an input device declares too many capability bits then modalias string for such device may become too long and not fit into uevent buffer, resulting in failure of sending said uevent. This, in turn, may prevent userspace from recognizing existence of such devices.
This is typically not a concern for real hardware devices as they have limited number of keys, but happen with synthetic devices such as ones created by xen-kbdfront driver, which creates devices as being capable of delivering all possible keys, since it doesn't know what keys the backend may produce.
To deal with such devices input core will attempt to trim key data, in the hope that the rest of modalias string will fit in the given buffer. When trimming key data it will indicate that it is not complete by placing "+," sign, resulting in conversions like this:
old: k71,72,73,74,78,7A,7B,7C,7D,8E,9E,A4,AD,E0,E1,E4,F8,174,
new: k71,72,73,74,78,7A,7B,7C,+,
This should allow existing udev rules continue to work with existing devices, and will also allow writing more complex rules that would recognize trimmed modalias and check input device characteristics by other means (for example by parsing KEY= data in uevent or parsing input device sysfs attributes).
Note that the driver core may try adding more uevent environment variables once input core is done adding its own, so when forming modalias we can not use the entire available buffer, so we reduce it by somewhat an arbitrary amount (96 bytes).
--- drivers/input/input.c | 104 ++++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 89 insertions(+), 15 deletions(-)
drivers/input/input.c +89 -15
@@ -1374,19 +1374,19 @@ static int input_print_modalias_bits(cha char name, unsigned long *bm, unsigned int min_bit, unsigned int max_bit) { - int len = 0, i; + int bit = min_bit; +int len =0 ; len +=snprintf (buf,max (size,0 ),"%c" , name); -for (i = min_bit; i < max_bit; i++) -if (bm[BIT_WORD (i)] &BIT_MASK (i)) - len +=snprintf (buf + len,max (size - len,0 ),"%X," , i); +for_each_set_bit_from (bit, bm, max_bit) + len +=snprintf (buf + len,max (size - len,0 ),"%X," , bit);return len; } -static int input_print_modalias (char *buf,int size,struct input_dev *id, -int add_cr) +static int input_print_modalias_parts (char *buf,int size,int full_len, +struct input_dev *id) { -int len; +int len, klen, remainder, space; len = snprintf(buf, max(size, 0), "input:b%04Xv%04Xp%04Xe%04X-",
@@ -1395,8 +1395,48 @@ static int input_print_modalias(char *bu len +=input_print_modalias_bits (buf + len, size - len,'e' , id->evbit,0 ,EV_MAX ); - len +=input_print_modalias_bits (buf + len, size - len, + +/* +* Calculate the remaining space in the buffer making sure we +* have place for the terminating 0. +*/ + space =max (size - (len +1 ),0 ); + + klen =input_print_modalias_bits (buf + len, size - len,'k' , id->keybit,KEY_MIN_INTERESTING ,KEY_MAX ); + len += klen; + +/* +* If we have more data than we can fit in the buffer, check +* if we can trim key data to fit in the rest. We will indicate +* that key data is incomplete by adding "+" sign at the end, like +* this: * "k1,2,3,45,+,". +* +* Note that we shortest key info (if present) is "k+," so we +* can only try to trim if key data is longer than that. +*/ +if (full_len && size < full_len +1 && klen >3 ) { + remainder = full_len - len; +/* +* We can only trim if we have space for the remainder +* and also for at least "k+," which is 3 more characters. +*/ +if (remainder <= space -3 ) { +/* +* We are guaranteed to have 'k' in the buffer, so +* we need at least 3 additional bytes for storing +* "+," in addition to the remainder. +*/ +for (int i = size -1 - remainder -3 ; i >=0 ; i--) { +if (buf[i] =='k' || buf[i] ==',' ) { +strcpy (buf + i +1 ,"+," ); + len = i +3 ;/* Not counting '\0' */ +break ; + } + } + } + } + len +=input_print_modalias_bits (buf + len, size - len,'r' , id->relbit,0 ,REL_MAX ); len += input_print_modalias_bits(buf + len, size - len,
@@ -1412,12 +1452,25 @@ static int input_print_modalias(char *bu len +=input_print_modalias_bits (buf + len, size - len,'w' , id->swbit,0 ,SW_MAX ); -if (add_cr) - len +=snprintf (buf + len,max (size - len,0 ),"\n" ); -return len; } +static int input_print_modalias (char *buf,int size,struct input_dev *id) +{ +int full_len; + +/* +* Printing is done in 2 passes: first one figures out total length +* needed for the modalias string, second one will try to trim key +* data in case when buffer is too small for the entire modalias. +* If the buffer is too small regardless, it will fill as much as it +* can (without trimming key data) into the buffer and leave it to +* the caller to figure out what to do with the result. +*/ + full_len =input_print_modalias_parts (NULL ,0 ,0 , id); +return input_print_modalias_parts (buf, size, full_len, id); +} +static ssize_t input_dev_show_modalias (struct device *dev,struct device_attribute *attr,char *buf)
@@ -1425,7 +1478,9 @@ static ssize_t input_dev_show_modalias(sstruct input_dev *id =to_input_dev (dev);ssize_t len; - len =input_print_modalias (buf,PAGE_SIZE , id,1 ); + len =input_print_modalias (buf,PAGE_SIZE , id); +if (len <PAGE_SIZE -2 ) + len +=snprintf (buf + len,PAGE_SIZE - len,"\n" );return min_t (int, len,PAGE_SIZE ); }
@@ -1637,6 +1692,23 @@ static int input_add_uevent_bm_var(strucreturn 0 ; } +/* +* This is a pretty gross hack. When building uevent data the driver core +* may try adding more environment variables to kobj_uevent_env without +* telling us, so we have no idea how much of the buffer we can use to +* avoid overflows/-ENOMEM elsewhere. To work around this let's artificially +* reduce amount of memory we will use for the modalias environment variable. +* +* The potential additions are: +* +* SEQNUM=18446744073709551615 - (%llu - 28 bytes) +* HOME=/ (6 bytes) +* PATH=/sbin:/bin:/usr/sbin:/usr/bin (34 bytes) +* +* 68 bytes total. Allow extra buffer - 96 bytes +*/ +#define UEVENT_ENV_EXTRA_LEN 96 +static int input_add_uevent_modalias_var (struct kobj_uevent_env *env,struct input_dev *dev) {
@@ -1646,9 +1718,11 @@ static int input_add_uevent_modalias_varreturn -ENOMEM ; len =input_print_modalias (&env->buf[env->buflen -1 ], -sizeof (env->buf) - env->buflen, - dev,0 ); -if (len >= (sizeof (env->buf) - env->buflen)) + (int )sizeof (env->buf) - env->buflen - +UEVENT_ENV_EXTRA_LEN , + dev); +if (len >= ((int )sizeof (env->buf) - env->buflen - +UEVENT_ENV_EXTRA_LEN ))return -ENOMEM ; env->buflen += len;
Greg Kroah-Hartman
maintainerPATCH 104/217 cxl/test: Add missing vmalloc.h for tools/testing/cxl/test/mem.c
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Dave Jiang <[email protected]>
[ Upstream commit d55510527153d17a3af8cc2df69c04f95ae1350d ]
tools/testing/cxl/test/mem.c uses vmalloc() and vfree() but does not include linux/vmalloc.h. Kernel v6.10 made changes that causes the currently included headers not depend on vmalloc.h and therefore mem.c can no longer compile. Add linux/vmalloc.h to fix compile issue.
CC [M] tools/testing/cxl/test/mem.otools/testing/cxl/test/mem.c: In function ‘label_area_release’:tools/testing/cxl/test/mem.c:1428:9: error: implicit declaration of function ‘vfree’; did you mean ‘kvfree’? [-Werror=implicit-function-declaration]
1428 | vfree(lsa);
| ^~~~~
| kvfree
tools/testing/cxl/test/mem.c: In function ‘cxl_mock_mem_probe’:
tools/testing/cxl/test/mem.c:1466:22: error: implicit declaration of function ‘vmalloc’; did you mean ‘kmalloc’? [-Werror=implicit-function-declaration]
1466 | mdata->lsa = vmalloc(LSA_SIZE);
| ^~~~~~~
| kmalloc--- tools/testing/cxl/test/mem.c | 1 + 1 file changed, 1 insertion(+)
tools/testing/cxl/test/mem.c +1 -0
@@ -3,6 +3,7 @@#include <linux/platform_device.h> #include <linux/mod_devicetable.h> +#include <linux/vmalloc.h> #include <linux/module.h> #include <linux/delay.h> #include <linux/sizes.h>
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 105/217 cachefiles: add output string to cachefiles_obj_[get|put]_ondemand_fd
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Baokun Li <[email protected]>
[ Upstream commit cc5ac966f26193ab185cc43d64d9f1ae998ccb6e ]
This lets us see the correct trace output.
--- include/trace/events/cachefiles.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
include/trace/events/cachefiles.h +3 -1
@@ -127,7 +127,9 @@ enum cachefiles_error_trace { EM(cachefiles_obj_see_lookup_cookie, "SEE lookup_cookie") \ EM(cachefiles_obj_see_lookup_failed, "SEE lookup_failed") \ EM(cachefiles_obj_see_withdraw_cookie, "SEE withdraw_cookie") \ - E_(cachefiles_obj_see_withdrawal, "SEE withdrawal") + EM(cachefiles_obj_see_withdrawal, "SEE withdrawal") \ + EM(cachefiles_obj_get_ondemand_fd, "GET ondemand_fd") \ + E_(cachefiles_obj_put_ondemand_fd, "PUT ondemand_fd")#define cachefiles_coherency_traces \ EM(cachefiles_coherency_check_aux, "BAD aux ") \
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 106/217 cachefiles: remove requests from xarray during flushing requests
In reply to Greg Kroah-Hartman6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Baokun Li <[email protected]>
[ Upstream commit 0fc75c5940fa634d84e64c93bfc388e1274ed013 ]
Even with CACHEFILES_DEAD set, we can still read the requests, so in the following concurrency the request may be used after it has been freed:
mount | daemon_thread1 | daemon_thread2
------------------------------------------------------------
cachefiles_ondemand_init_object
cachefiles_ondemand_send_req
REQ_A = kzalloc(sizeof(*req) + data_len)
wait_for_completion(&REQ_A->done)
cachefiles_daemon_read
cachefiles_ondemand_daemon_read
// close dev fd
cachefiles_flush_reqs
complete(&REQ_A->done)
kfree(REQ_A)
xa_lock(&cache->reqs);
cachefiles_ondemand_select_req
req->msg.opcode != CACHEFILES_OP_READ
// req use-after-free !!!
xa_unlock(&cache->reqs);
xa_destroy(&cache->reqs)Hence remove requests from cache->reqs when flushing them to avoid accessing freed requests.
--- fs/cachefiles/daemon.c | 1 + 1 file changed, 1 insertion(+)
fs/cachefiles/daemon.c +1 -0
@@ -158,6 +158,7 @@ static void cachefiles_flush_reqs(struct cachefiles_cache *cache)xa_for_each (xa, index, req) { req->error = -EIO ;complete (&req->done); +__xa_erase (xa, index); }xa_unlock (xa);
Signature · 1 line
2.43.0