6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Remi Pommarel repk@triplefau.lt

[ 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.

Fixes: 1d147bfa6429 ("mac80211: fix AP powersave TX vs. wakeup race") Signed-off-by: Remi Pommarel repk@triplefau.lt Link: https://msgid.link/8e36fe07d0fbc146f89196cd47a53c8a0afe84aa.1716910344.git.r... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/mac80211/sta_info.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index c61eb867bb4a7..984f8f67492fd 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1709,7 +1709,7 @@ 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; @@ -1738,7 +1738,7 @@ 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);

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Remi Pommarel repk@triplefau.lt

[ 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.

Fixes: 7406353d43c8 ("cfg80211: implement cfg80211_get_station cfg80211 API") Signed-off-by: Remi Pommarel repk@triplefau.lt Reviewed-by: Nicolas Escande nico.escande@gmail.com Acked-by: Antonio Quartulli a@unstable.cc Link: https://msgid.link/983b24a6a176e0800c01aedcd74480d9b551cb13.1716046653.git.r... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/wireless/util.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/wireless/util.c b/net/wireless/util.c index 9aa7bdce20b26..57ea6d5b092d4 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -2399,6 +2399,7 @@ 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) @@ -2410,7 +2411,11 @@ 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);

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Miri Korenblit miriam.rachel.korenblit@intel.com

[ Upstream commit 92158790ce4391ce4c35d8dfbce759195e4724cb ]

The initialization of this worker moved to iwl_mvm_mac_init_mvmvif but we removed only from the pre-MLD version of the add_interface callback. Remove it also from the MLD version.

Fixes: 0bcc2155983e ("wifi: iwlwifi: mvm: init vif works only once") Signed-off-by: Miri Korenblit miriam.rachel.korenblit@intel.com Reviewed-by: Johannes Berg johannes.berg@intel.com Link: https://msgid.link/20240512152312.4f15b41604f0.Iec912158e5a706175531d3736d77... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c | 2 -- 1 file changed, 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c index aef8824469e1e..4d9a872818a52 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c @@ -73,8 +73,6 @@ static int iwl_mvm_mld_mac_add_interface(struct ieee80211_hw *hw, goto out_free_bf;

iwl_mvm_tcm_add_vif(mvm, vif); - INIT_DELAYED_WORK(&mvmvif->csa_work, - iwl_mvm_channel_switch_disconnect_wk);

if (vif->type == NL80211_IFTYPE_MONITOR) { mvm->monitor_on = true;

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Mordechay Goodstein mordechay.goodstein@intel.com

[ Upstream commit 0f2e9f6f21d1ff292363cdfb5bc4d492eeaff76e ]

In the driver we only use skb_put* for adding data to the skb, hence data never moves and skb_reset_mac_haeder would set mac_header to the first time data was added and not to mac80211 header, fix this my using the actual len of bytes added for setting the mac header.

Fixes: 3f7a9d577d47 ("wifi: iwlwifi: mvm: simplify by using SKB MAC header pointer") Signed-off-by: Mordechay Goodstein mordechay.goodstein@intel.com Reviewed-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Miri Korenblit miriam.rachel.korenblit@intel.com Link: https://msgid.link/20240510170500.12f2de2909c3.I72a819b96f2fe55bde192a8fd31a... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index e9360b555ac93..8cff24d5f5f40 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -2730,8 +2730,11 @@ void iwl_mvm_rx_monitor_no_data(struct iwl_mvm *mvm, struct napi_struct *napi, * * We mark it as mac header, for upper layers to know where * all radio tap header ends. + * + * Since data doesn't move data while putting data on skb and that is + * the only way we use, data + len is the next place that hdr would be put */ - skb_reset_mac_header(skb); + skb_set_mac_header(skb, skb->len);

/* * Override the nss from the rx_vec since the rate_n_flags has

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Miri Korenblit miriam.rachel.korenblit@intel.com

[ 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.

Fixes: c1a7515393e4 ("iwlwifi: mvm: add adaptive dwell support") Signed-off-by: Miri Korenblit miriam.rachel.korenblit@intel.com Reviewed-by: Ilan Peer ilan.peer@intel.com Reviewed-by: Johannes Berg johannes.berg@intel.com Link: https://msgid.link/20240513132416.6e4d1762bf0d.I5a0e6cc8f02050a766db704d1559... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/intel/iwlwifi/mvm/scan.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c index 03ec900a33433..0841f1d6dc475 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c @@ -1304,7 +1304,7 @@ 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 @@ -1406,7 +1406,7 @@ 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

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Lingbo Kong quic_lingbok@quicinc.com

[ 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 | -------------------------------------------------------------------------

Fixes: 1ced169cc1c2 ("mac80211: allow setting spatial reuse parameters from bss_conf") Signed-off-by: Lingbo Kong quic_lingbok@quicinc.com Link: https://msgid.link/20240516021854.5682-3-quic_lingbok@quicinc.com Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/mac80211/he.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/he.c b/net/mac80211/he.c index 9f5ffdc9db284..ecbb042dd0433 100644 --- a/net/mac80211/he.c +++ b/net/mac80211/he.c @@ -230,15 +230,21 @@ 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; } }

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Yong-Xuan Wang yongxuan.wang@sifive.com

[ Upstream commit 2d707b4e37f9b0c37b8b2392f91b04c5b63ea538 ]

When the maximum hart number within groups is 1, hart-index-bit is set to 0. Consequently, there is no need to restore the hart ID from IMSIC addresses and hart-index-bit settings. Currently, QEMU and kvmtool do not pass correct hart-index-bit values when the maximum hart number is a power of 2, thereby avoiding this issue. Corresponding patches for QEMU and kvmtool will also be dispatched.

Fixes: 89d01306e34d ("RISC-V: KVM: Implement device interface for AIA irqchip") Signed-off-by: Yong-Xuan Wang yongxuan.wang@sifive.com Reviewed-by: Andrew Jones ajones@ventanamicro.com Link: https://lore.kernel.org/r/20240415064905.25184-1-yongxuan.wang@sifive.com Signed-off-by: Anup Patel anup@brainfault.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/riscv/kvm/aia_device.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/kvm/aia_device.c b/arch/riscv/kvm/aia_device.c index 0eb689351b7d0..5cd407c6a8e4f 100644 --- a/arch/riscv/kvm/aia_device.c +++ b/arch/riscv/kvm/aia_device.c @@ -237,10 +237,11 @@ static gpa_t aia_imsic_ppn(struct kvm_aia *aia, gpa_t addr)

static u32 aia_imsic_hart_index(struct kvm_aia *aia, gpa_t addr) { - u32 hart, group = 0; + u32 hart = 0, group = 0;

- hart = (addr >> (aia->nr_guest_bits + IMSIC_MMIO_PAGE_SHIFT)) & - GENMASK_ULL(aia->nr_hart_bits - 1, 0); + if (aia->nr_hart_bits) + hart = (addr >> (aia->nr_guest_bits + IMSIC_MMIO_PAGE_SHIFT)) & + GENMASK_ULL(aia->nr_hart_bits - 1, 0); if (aia->nr_group_bits) group = (addr >> aia->nr_group_shift) & GENMASK_ULL(aia->nr_group_bits - 1, 0);

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Lars Kellogg-Stedman lars@oddbit.com

[ 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().

Fixes: 9fd75b66b8f6 ("ax25: Fix refcount leaks caused by ax25_cb_del()") Signed-off-by: Lars Kellogg-Stedman lars@oddbit.com Tested-by: Duoming Zhou duoming@zju.edu.cn Tested-by: Dan Cross crossd@gmail.com Tested-by: Chris Maness christopher.maness@gmail.com Reviewed-by: Dan Carpenter dan.carpenter@linaro.org Link: https://lore.kernel.org/r/20240529210242.3346844-2-lars@oddbit.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/ax25/af_ax25.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 9d11d26e46c0e..26a3095bec462 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -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);

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Peter Delevoryas peter@pjd.dev

[ 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/20200108234341.2590674-1-vijaykhemka@fb.com/

Which was actually originally from cosmo.chou@quantatw.com:

https://github.com/facebook/openbmc-linux/commit/9f132a10ec48db84613519258cd...

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.

Signed-off-by: Peter Delevoryas peter@pjd.dev Signed-off-by: David S. Miller davem@davemloft.net Stable-dep-of: e85e271dec02 ("net/ncsi: Fix the multi thread manner of NCSI driver") Signed-off-by: Sasha Levin sashal@kernel.org --- net/ncsi/ncsi-manage.c | 20 +++----------------- 1 file changed, 3 insertions(+), 17 deletions(-)

diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index d9da942ad53dd..f3d7fe86fea13 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -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:

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tristram Ha tristram.ha@microchip.com

[ Upstream commit 6149db4997f582e958da675092f21c666e3b67b7 ]

When the PHY is powered up after powered down most of the registers are reset, so the PHY setup code needs to be done again. In addition the interrupt register will need to be setup again so that link status indication works again.

Fixes: 26dd2974c5b5 ("net: phy: micrel: Move KSZ9477 errata fixes to PHY driver") Signed-off-by: Tristram Ha tristram.ha@microchip.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/phy/micrel.c | 62 ++++++++++++++++++++++++++++++++++++---- 1 file changed, 56 insertions(+), 6 deletions(-)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index fc31fcfb0cdb4..048704758b150 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -1821,7 +1821,7 @@ static const struct ksz9477_errata_write ksz9477_errata_writes[] = { {0x1c, 0x20, 0xeeee}, };

-static int ksz9477_config_init(struct phy_device *phydev) +static int ksz9477_phy_errata(struct phy_device *phydev) { int err; int i; @@ -1849,16 +1849,30 @@ static int ksz9477_config_init(struct phy_device *phydev) return err; }

+ err = genphy_restart_aneg(phydev); + if (err) + return err; + + return err; +} + +static int ksz9477_config_init(struct phy_device *phydev) +{ + int err; + + /* Only KSZ9897 family of switches needs this fix. */ + if ((phydev->phy_id & 0xf) == 1) { + err = ksz9477_phy_errata(phydev); + if (err) + return err; + } + /* According to KSZ9477 Errata DS80000754C (Module 4) all EEE modes * in this switch shall be regarded as broken. */ if (phydev->dev_flags & MICREL_NO_EEE) phydev->eee_broken_modes = -1;

- err = genphy_restart_aneg(phydev); - if (err) - return err; - return kszphy_config_init(phydev); }

@@ -1967,6 +1981,42 @@ static int kszphy_resume(struct phy_device *phydev) return 0; }

+static int ksz9477_resume(struct phy_device *phydev) +{ + int ret; + + /* No need to initialize registers if not powered down. */ + ret = phy_read(phydev, MII_BMCR); + if (ret < 0) + return ret; + if (!(ret & BMCR_PDOWN)) + return 0; + + genphy_resume(phydev); + + /* After switching from power-down to normal mode, an internal global + * reset is automatically generated. Wait a minimum of 1 ms before + * read/write access to the PHY registers. + */ + usleep_range(1000, 2000); + + /* Only KSZ9897 family of switches needs this fix. */ + if ((phydev->phy_id & 0xf) == 1) { + ret = ksz9477_phy_errata(phydev); + if (ret) + return ret; + } + + /* Enable PHY Interrupts */ + if (phy_interrupt_is_valid(phydev)) { + phydev->interrupts = PHY_INTERRUPT_ENABLED; + if (phydev->drv->config_intr) + phydev->drv->config_intr(phydev); + } + + return 0; +} + static int kszphy_probe(struct phy_device *phydev) { const struct kszphy_type *type = phydev->drv->driver_data; @@ -4916,7 +4966,7 @@ static struct phy_driver ksphy_driver[] = { .config_intr = kszphy_config_intr, .handle_interrupt = kszphy_handle_interrupt, .suspend = genphy_suspend, - .resume = genphy_resume, + .resume = ksz9477_resume, .get_features = ksz9477_get_features, } };

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hou Tao houtao1@huawei.com

[ Upstream commit af66bfd3c8538ed21cf72af18426fc4a408665cf ]

When removing the inner map from the outer map, the inner map will be freed after one RCU grace period and one RCU tasks trace grace period, so it is certain that the bpf program, which may access the inner map, has exited before the inner map is freed.

However there is no need to wait for one RCU tasks trace grace period if the outer map is only accessed by non-sleepable program. So adding sleepable_refcnt in bpf_map and increasing sleepable_refcnt when adding the outer map into env->used_maps for sleepable program. Although the max number of bpf program is INT_MAX - 1, the number of bpf programs which are being loaded may be greater than INT_MAX, so using atomic64_t instead of atomic_t for sleepable_refcnt. When removing the inner map from the outer map, using sleepable_refcnt to decide whether or not a RCU tasks trace grace period is needed before freeing the inner map.

Signed-off-by: Hou Tao houtao1@huawei.com Link: https://lore.kernel.org/r/20231204140425.1480317-6-houtao@huaweicloud.com Signed-off-by: Alexei Starovoitov ast@kernel.org Stable-dep-of: 2884dc7d08d9 ("bpf: Fix a potential use-after-free in bpf_link_free()") Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/bpf.h | 2 ++ kernel/bpf/core.c | 4 ++++ kernel/bpf/map_in_map.c | 14 +++++++++----- kernel/bpf/syscall.c | 8 ++++++++ kernel/bpf/verifier.c | 4 +++- 5 files changed, 26 insertions(+), 6 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 2ebb5d4d43dc6..e4cd28c38b825 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -296,6 +296,8 @@ struct bpf_map { bool bypass_spec_v1; bool frozen; /* write-once; write-protected by freeze_mutex */ bool free_after_mult_rcu_gp; + bool free_after_rcu_gp; + atomic64_t sleepable_refcnt; s64 __percpu *elem_count; };

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 1333273a71ded..05445a4d55181 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2673,12 +2673,16 @@ void __bpf_free_used_maps(struct bpf_prog_aux *aux, struct bpf_map **used_maps, u32 len) { struct bpf_map *map; + bool sleepable; u32 i;

+ sleepable = aux->sleepable; for (i = 0; i < len; i++) { map = used_maps[i]; if (map->ops->map_poke_untrack) map->ops->map_poke_untrack(map, aux); + if (sleepable) + atomic64_dec(&map->sleepable_refcnt); bpf_map_put(map); } } diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index 3248ff5d81617..8ef269e66ba50 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -131,12 +131,16 @@ void bpf_map_fd_put_ptr(struct bpf_map *map, void *ptr, bool need_defer) { struct bpf_map *inner_map = ptr;

- /* The inner map may still be used by both non-sleepable and sleepable - * bpf program, so free it after one RCU grace period and one tasks - * trace RCU grace period. + /* Defer the freeing of inner map according to the sleepable attribute + * of bpf program which owns the outer map, so unnecessary waiting for + * RCU tasks trace grace period can be avoided. */ - if (need_defer) - WRITE_ONCE(inner_map->free_after_mult_rcu_gp, true); + if (need_defer) { + if (atomic64_read(&map->sleepable_refcnt)) + WRITE_ONCE(inner_map->free_after_mult_rcu_gp, true); + else + WRITE_ONCE(inner_map->free_after_rcu_gp, true); + } bpf_map_put(inner_map); }

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index e886157a9efbb..e9a68c6043ce5 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -753,8 +753,11 @@ void bpf_map_put(struct bpf_map *map) /* bpf_map_free_id() must be called first */ bpf_map_free_id(map);

+ WARN_ON_ONCE(atomic64_read(&map->sleepable_refcnt)); if (READ_ONCE(map->free_after_mult_rcu_gp)) call_rcu_tasks_trace(&map->rcu, bpf_map_free_mult_rcu_gp); + else if (READ_ONCE(map->free_after_rcu_gp)) + call_rcu(&map->rcu, bpf_map_free_rcu_gp); else bpf_map_free_in_work(map); } @@ -5358,6 +5361,11 @@ static int bpf_prog_bind_map(union bpf_attr *attr) goto out_unlock; }

+ /* The bpf program will not access the bpf map, but for the sake of + * simplicity, increase sleepable_refcnt for sleepable program as well. + */ + if (prog->aux->sleepable) + atomic64_inc(&map->sleepable_refcnt); memcpy(used_maps_new, used_maps_old, sizeof(used_maps_old[0]) * prog->aux->used_map_cnt); used_maps_new[prog->aux->used_map_cnt] = map; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 24d7a32f1710e..ec0464c075bb4 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -17732,10 +17732,12 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) return -E2BIG; }

+ if (env->prog->aux->sleepable) + atomic64_inc(&map->sleepable_refcnt); /* hold the map. If the program is rejected by verifier, * the map will be released by release_maps() or it * will be used by the valid program until it's unloaded - * and all maps are released in free_used_maps() + * and all maps are released in bpf_free_used_maps() */ bpf_map_inc(map);

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ravi Bangoria ravi.bangoria@amd.com

[ Upstream commit d922056215617eedfbdbc29fe49953423686fe5e ]

As documented in APM[1], LBR Virtualization must be enabled for SEV-ES guests. So, prevent SEV-ES guests when LBRV support is missing.

[1]: AMD64 Architecture Programmer's Manual Pub. 40332, Rev. 4.07 - June 2023, Vol 2, 15.35.2 Enabling SEV-ES. https://bugzilla.kernel.org/attachment.cgi?id=304653

Fixes: 376c6d285017 ("KVM: SVM: Provide support for SEV-ES vCPU creation/loading") Signed-off-by: Ravi Bangoria ravi.bangoria@amd.com Message-ID: 20240531044644.768-3-ravi.bangoria@amd.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kvm/svm/sev.c | 6 ++++++ arch/x86/kvm/svm/svm.c | 16 +++++++--------- arch/x86/kvm/svm/svm.h | 1 + 3 files changed, 14 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index c5845f31c34dc..0e643d7a06d9e 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2264,6 +2264,12 @@ void __init sev_hardware_setup(void) if (!boot_cpu_has(X86_FEATURE_SEV_ES)) goto out;

+ if (!lbrv) { + WARN_ONCE(!boot_cpu_has(X86_FEATURE_LBRV), + "LBRV must be present for SEV-ES support"); + goto out; + } + /* Has the system been allocated ASIDs for SEV-ES? */ if (min_sev_asid == 1) goto out; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 1efbe8b33f6a1..9e084e22a12f7 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -214,7 +214,7 @@ int vgif = true; module_param(vgif, int, 0444);

/* enable/disable LBR virtualization */ -static int lbrv = true; +int lbrv = true; module_param(lbrv, int, 0444);

static int tsc_scaling = true; @@ -5248,6 +5248,12 @@ static __init int svm_hardware_setup(void)

nrips = nrips && boot_cpu_has(X86_FEATURE_NRIPS);

+ if (lbrv) { + if (!boot_cpu_has(X86_FEATURE_LBRV)) + lbrv = false; + else + pr_info("LBR virtualization supported\n"); + } /* * Note, SEV setup consumes npt_enabled and enable_mmio_caching (which * may be modified by svm_adjust_mmio_mask()), as well as nrips. @@ -5301,14 +5307,6 @@ static __init int svm_hardware_setup(void) svm_x86_ops.set_vnmi_pending = NULL; }

- - if (lbrv) { - if (!boot_cpu_has(X86_FEATURE_LBRV)) - lbrv = false; - else - pr_info("LBR virtualization supported\n"); - } - if (!enable_pmu) pr_info("PMU virtualization is disabled\n");

diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index be67ab7fdd104..53bc4b0e388be 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -39,6 +39,7 @@ extern int vgif; extern bool intercept_smi; extern bool x2avic_enabled; extern bool vnmi; +extern int lbrv;

/* * Clean bits in VMCB.

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ravi Bangoria ravi.bangoria@amd.com

[ Upstream commit b7e4be0a224fe5c6be30c1c8bdda8d2317ad6ba4 ]

As documented in APM[1], LBR Virtualization must be enabled for SEV-ES guests. Although KVM currently enforces LBRV for SEV-ES guests, there are multiple issues with it:

o MSR_IA32_DEBUGCTLMSR is still intercepted. Since MSR_IA32_DEBUGCTLMSR interception is used to dynamically toggle LBRV for performance reasons, this can be fatal for SEV-ES guests. For ex SEV-ES guest on Zen3:

[guest ~]# wrmsr 0x1d9 0x4 KVM: entry failed, hardware error 0xffffffff EAX=00000004 EBX=00000000 ECX=000001d9 EDX=00000000

Fix this by never intercepting MSR_IA32_DEBUGCTLMSR for SEV-ES guests. No additional save/restore logic is required since MSR_IA32_DEBUGCTLMSR is of swap type A.

o KVM will disable LBRV if userspace sets MSR_IA32_DEBUGCTLMSR before the VMSA is encrypted. Fix this by moving LBRV enablement code post VMSA encryption.

[1]: AMD64 Architecture Programmer's Manual Pub. 40332, Rev. 4.07 - June 2023, Vol 2, 15.35.2 Enabling SEV-ES. https://bugzilla.kernel.org/attachment.cgi?id=304653

Fixes: 376c6d285017 ("KVM: SVM: Provide support for SEV-ES vCPU creation/loading") Co-developed-by: Nikunj A Dadhania nikunj@amd.com Signed-off-by: Nikunj A Dadhania nikunj@amd.com Signed-off-by: Ravi Bangoria ravi.bangoria@amd.com Message-ID: 20240531044644.768-4-ravi.bangoria@amd.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kvm/svm/sev.c | 13 ++++++++----- arch/x86/kvm/svm/svm.c | 8 +++++++- arch/x86/kvm/svm/svm.h | 3 ++- 3 files changed, 17 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index f809dcfacc8a3..99e72b8a96ac0 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -664,6 +664,14 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu, return ret;

vcpu->arch.guest_state_protected = true; + + /* + * SEV-ES guest mandates LBR Virtualization to be _always_ ON. Enable it + * only after setting guest_state_protected because KVM_SET_MSRS allows + * dynamic toggling of LBRV (for performance reason) on write access to + * MSR_IA32_DEBUGCTLMSR when guest_state_protected is not set. + */ + svm_enable_lbrv(vcpu); return 0; }

@@ -3035,7 +3043,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) struct kvm_vcpu *vcpu = &svm->vcpu;

svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ES_ENABLE; - svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK;

/* * An SEV-ES guest requires a VMSA area that is a separate from the @@ -3087,10 +3094,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) /* Clear intercepts on selected MSRs */ set_msr_interception(vcpu, svm->msrpm, MSR_EFER, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_CR_PAT, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1); }

void sev_init_vmcb(struct vcpu_svm *svm) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 08f1397138c80..e3c2acc1adc73 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -99,6 +99,7 @@ static const struct svm_direct_access_msrs { { .index = MSR_IA32_SPEC_CTRL, .always = false }, { .index = MSR_IA32_PRED_CMD, .always = false }, { .index = MSR_IA32_FLUSH_CMD, .always = false }, + { .index = MSR_IA32_DEBUGCTLMSR, .always = false }, { .index = MSR_IA32_LASTBRANCHFROMIP, .always = false }, { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, { .index = MSR_IA32_LASTINTFROMIP, .always = false }, @@ -1008,7 +1009,7 @@ void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb) vmcb_mark_dirty(to_vmcb, VMCB_LBR); }

-static void svm_enable_lbrv(struct kvm_vcpu *vcpu) +void svm_enable_lbrv(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu);

@@ -1018,6 +1019,9 @@ static void svm_enable_lbrv(struct kvm_vcpu *vcpu) set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1);

+ if (sev_es_guest(vcpu->kvm)) + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_DEBUGCTLMSR, 1, 1); + /* Move the LBR msrs to the vmcb02 so that the guest can see them. */ if (is_guest_mode(vcpu)) svm_copy_lbrs(svm->vmcb, svm->vmcb01.ptr); @@ -1027,6 +1031,8 @@ static void svm_disable_lbrv(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu);

+ KVM_BUG_ON(sev_es_guest(vcpu->kvm), vcpu->kvm); + svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK; set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index fb0ac8497fb20..37ada9808d9b5 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -30,7 +30,7 @@ #define IOPM_SIZE PAGE_SIZE * 3 #define MSRPM_SIZE PAGE_SIZE * 2

-#define MAX_DIRECT_ACCESS_MSRS 47 +#define MAX_DIRECT_ACCESS_MSRS 48 #define MSRPM_OFFSETS 32 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; extern bool npt_enabled; @@ -542,6 +542,7 @@ u32 *svm_vcpu_alloc_msrpm(void); void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm); void svm_vcpu_free_msrpm(u32 *msrpm); void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb); +void svm_enable_lbrv(struct kvm_vcpu *vcpu); void svm_update_lbrv(struct kvm_vcpu *vcpu);

int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer);

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet edumazet@google.com

[ 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().

Fixes: 8cb3bf8bff3c ("ipv6: ioam: Add support for the ip6ip6 encapsulation") Signed-off-by: Eric Dumazet edumazet@google.com Cc: Justin Iurman justin.iurman@uliege.be Acked-by: Paolo Abeni pabeni@redhat.com Link: https://lore.kernel.org/r/20240531132636.2637995-2-edumazet@google.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv6/ioam6_iptunnel.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c index f6f5b83dd954d..a5cfc5b0b206b 100644 --- a/net/ipv6/ioam6_iptunnel.c +++ b/net/ipv6/ioam6_iptunnel.c @@ -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);

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jakub Kicinski kuba@kernel.org

[ Upstream commit a535d59432370343058755100ee75ab03c0e3f91 ]

For TLS offload we mark packets with skb->decrypted to make sure they don't escape the host without getting encrypted first. The crypto state lives in the socket, so it may get detached by a call to skb_orphan(). As a safety check - the egress path drops all packets with skb->decrypted and no "crypto-safe" socket.

The skb marking was added to sendpage only (and not sendmsg), because tls_device injected data into the TCP stack using sendpage. This special case was missed when sendpage got folded into sendmsg.

Fixes: c5c37af6ecad ("tcp: Convert do_tcp_sendpages() to use MSG_SPLICE_PAGES") Signed-off-by: Jakub Kicinski kuba@kernel.org Reviewed-by: Eric Dumazet edumazet@google.com Link: https://lore.kernel.org/r/20240530232607.82686-1-kuba@kernel.org Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/tcp.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7bf774bdb9386..a9b33135513d8 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1158,6 +1158,9 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)

process_backlog++;

+#ifdef CONFIG_SKB_DECRYPTED + skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED); +#endif tcp_skb_entail(sk, skb); copy = size_goal;

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Subbaraya Sundeep sbhatta@marvell.com

[ 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.

Fixes: 7df5b4b260dd ("octeontx2-af: Allocate low priority entries for PF") Signed-off-by: Subbaraya Sundeep sbhatta@marvell.com Reviewed-by: Jacob Keller jacob.e.keller@intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- .../ethernet/marvell/octeontx2/af/rvu_npc.c | 33 ++++++++++++------- 1 file changed, 22 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 91a4ea529d077..00ef6d201b973 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -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:

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tristram Ha tristram.ha@microchip.com

[ Upstream commit 0a8d3f2e3e8d8aea8af017e14227b91d5989b696 ]

KSZ8061 needs to write to a MMD register at driver initialization to fix an errata. This worked in 5.0 kernel but not in newer kernels. The issue is the main phylib code no longer resets PHY at the very beginning. Calling phy resuming code later will reset the chip if it is already powered down at the beginning. This wipes out the MMD register write. Solution is to implement a phy resume function for KSZ8061 to take care of this problem.

Fixes: 232ba3a51cc2 ("net: phy: Micrel KSZ8061: link failure after cable connect") Signed-off-by: Tristram Ha tristram.ha@microchip.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/phy/micrel.c | 42 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 41 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 048704758b150..366ae22534373 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -770,6 +770,17 @@ static int ksz8061_config_init(struct phy_device *phydev) { int ret;

+ /* Chip can be powered down by the bootstrap code. */ + ret = phy_read(phydev, MII_BMCR); + if (ret < 0) + return ret; + if (ret & BMCR_PDOWN) { + ret = phy_write(phydev, MII_BMCR, ret & ~BMCR_PDOWN); + if (ret < 0) + return ret; + usleep_range(1000, 2000); + } + ret = phy_write_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_DEVID1, 0xB61A); if (ret) return ret; @@ -2017,6 +2028,35 @@ static int ksz9477_resume(struct phy_device *phydev) return 0; }

+static int ksz8061_resume(struct phy_device *phydev) +{ + int ret; + + /* This function can be called twice when the Ethernet device is on. */ + ret = phy_read(phydev, MII_BMCR); + if (ret < 0) + return ret; + if (!(ret & BMCR_PDOWN)) + return 0; + + genphy_resume(phydev); + usleep_range(1000, 2000); + + /* Re-program the value after chip is reset. */ + ret = phy_write_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_DEVID1, 0xB61A); + if (ret) + return ret; + + /* Enable PHY Interrupts */ + if (phy_interrupt_is_valid(phydev)) { + phydev->interrupts = PHY_INTERRUPT_ENABLED; + if (phydev->drv->config_intr) + phydev->drv->config_intr(phydev); + } + + return 0; +} + static int kszphy_probe(struct phy_device *phydev) { const struct kszphy_type *type = phydev->drv->driver_data; @@ -4812,7 +4852,7 @@ static struct phy_driver ksphy_driver[] = { .config_intr = kszphy_config_intr, .handle_interrupt = kszphy_handle_interrupt, .suspend = kszphy_suspend, - .resume = kszphy_resume, + .resume = ksz8061_resume, }, { .phy_id = PHY_ID_KSZ9021, .phy_id_mask = 0x000ffffe,

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Daniel Borkmann daniel@iogearbox.net

[ 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.

Fixes: f58f45c1e5b9 ("vxlan: drop packets from invalid src-address") Signed-off-by: Daniel Borkmann daniel@iogearbox.net Cc: David Bauer mail@david-bauer.net Cc: Ido Schimmel idosch@nvidia.com Cc: Nikolay Aleksandrov razor@blackwall.org Cc: Martin KaFai Lau martin.lau@kernel.org Reviewed-by: Ido Schimmel idosch@nvidia.com Reviewed-by: Nikolay Aleksandrov razor@blackwall.org Reviewed-by: David Bauer mail@david-bauer.net Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/vxlan/vxlan_core.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index c24ff08abe0da..8268fa331826e 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -1446,6 +1446,10 @@ 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))

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jason Xing kernelxing@tencent.com

[ Upstream commit 9633e9377e6af0244f7381e86b9aac5276f5be97 ]

Like previous patch does in TCP, we need to adhere to RFC 1213:

"tcpCurrEstab OBJECT-TYPE ... The number of TCP connections for which the current state is either ESTABLISHED or CLOSE- WAIT."

So let's consider CLOSE-WAIT sockets.

The logic of counting When we increment the counter? a) Only if we change the state to ESTABLISHED.

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.

Fixes: d9cd27b8cd19 ("mptcp: add CurrEstab MIB counter support") Signed-off-by: Jason Xing kernelxing@tencent.com Reviewed-by: Matthieu Baerts (NGI0) matttbe@kernel.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/mptcp/protocol.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 618d80112d1e2..4ace52e4211ad 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2873,9 +2873,14 @@ void mptcp_set_state(struct sock *sk, int state) if (oldstate != TCP_ESTABLISHED) MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB); break; - + case TCP_CLOSE_WAIT: + /* Unlike TCP, MPTCP sk would not have the TCP_SYN_RECV state: + * MPTCP "accepted" sockets will be created later on. So no + * transition from TCP_SYN_RECV to TCP_CLOSE_WAIT. + */ + break; default: - if (oldstate == TCP_ESTABLISHED) + if (oldstate == TCP_ESTABLISHED || oldstate == TCP_CLOSE_WAIT) MPTCP_DEC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB); }

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Shay Drory shayd@nvidia.com

[ 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: cleanup mlx5_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 ]---

Fixes: 9b98d395b85d ("net/mlx5: Start health poll at earlier stage of driver load") Signed-off-by: Shay Drory shayd@nvidia.com Reviewed-by: Moshe Shemesh moshe@nvidia.com Signed-off-by: Tariq Toukan tariqt@nvidia.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 9710ddac1f1a8..2237b3d01e0e5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1287,6 +1287,9 @@ 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; }

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet edumazet@google.com

[ 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.

Fixes: a3d43c0d56f1 ("taprio: Add support adding an admin schedule") Reported-by: Noam Rathaus noamr@ssd-disclosure.com Signed-off-by: Eric Dumazet edumazet@google.com Acked-by: Vinicius Costa Gomes vinicius.gomes@intel.com Reviewed-by: Vladimir Oltean vladimir.oltean@nxp.com Link: https://lore.kernel.org/r/20240604181511.769870-1-edumazet@google.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/sched/sch_taprio.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index a315748a5e531..418d4a846d04a 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1186,16 +1186,13 @@ static int taprio_parse_mqprio_opt(struct net_device *dev, { bool allow_overlapping_txqs = TXTIME_ASSIST_IS_ENABLED(taprio_flags);

- 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; + }

/* taprio imposes that traffic classes map 1:n to tx queues */ if (qopt->num_tc > dev->num_tx_queues) {

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jacob Keller jacob.e.keller@intel.com

[ 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.

Fixes: e961b679fb0b ("ice: add board identifier info to devlink .info_get") Co-developed-by: Paul Greenwalt paul.greenwalt@intel.com Signed-off-by: Paul Greenwalt paul.greenwalt@intel.com Reviewed-by: Przemek Kitszel przemyslaw.kitszel@intel.com Tested-by: Pucha Himasekhar Reddy himasekharx.reddy.pucha@intel.com Signed-off-by: Jacob Keller jacob.e.keller@intel.com Link: https://lore.kernel.org/r/20240603-net-2024-05-30-intel-net-fixes-v2-1-e3563... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/ice/ice_nvm.c | 28 ++++++++++++++++++------ 1 file changed, 21 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c index f6f52a2480662..2fb43cded572c 100644 --- a/drivers/net/ethernet/intel/ice/ice_nvm.c +++ b/drivers/net/ethernet/intel/ice/ice_nvm.c @@ -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;

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Larysa Zaremba larysa.zaremba@intel.com

[ Upstream commit 744d197162c2070a6045a71e2666ed93a57cc65d ]

Commit 6624e780a577 ("ice: split ice_vsi_setup into smaller functions") has placed ice_vsi_free_q_vectors() after ice_destroy_xdp_rings() in the rebuild process. The behaviour of the XDP rings config functions is context-dependent, so the change of order has led to ice_destroy_xdp_rings() doing additional work and removing XDP prog, when it was supposed to be preserved.

Also, dependency on the PF state reset flags creates an additional, fortunately less common problem:

* PFR is requested e.g. by tx_timeout handler * .ndo_bpf() is asked to delete the program, calls ice_destroy_xdp_rings(), but reset flag is set, so rings are destroyed without deleting the program * ice_vsi_rebuild tries to delete non-existent XDP rings, because the program is still on the VSI * system crashes

With a similar race, when requested to attach a program, ice_prepare_xdp_rings() can actually skip setting the program in the VSI and nevertheless report success.

Instead of reverting to the old order of function calls, add an enum argument to both ice_prepare_xdp_rings() and ice_destroy_xdp_rings() in order to distinguish between calls from rebuild and .ndo_bpf().

Fixes: efc2214b6047 ("ice: Add support for XDP") Reviewed-by: Igor Bagnucki igor.bagnucki@intel.com Signed-off-by: Larysa Zaremba larysa.zaremba@intel.com Reviewed-by: Simon Horman horms@kernel.org Tested-by: Chandan Kumar Rout chandanx.rout@intel.com Signed-off-by: Jacob Keller jacob.e.keller@intel.com Link: https://lore.kernel.org/r/20240603-net-2024-05-30-intel-net-fixes-v2-4-e3563... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/ice/ice.h | 11 +++++++++-- drivers/net/ethernet/intel/ice/ice_lib.c | 5 +++-- drivers/net/ethernet/intel/ice/ice_main.c | 22 ++++++++++++---------- 3 files changed, 24 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index cf00eaa3e9955..c7962f322db2d 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -892,9 +892,16 @@ int ice_down(struct ice_vsi *vsi); int ice_down_up(struct ice_vsi *vsi); int ice_vsi_cfg_lan(struct ice_vsi *vsi); struct ice_vsi *ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi); + +enum ice_xdp_cfg { + ICE_XDP_CFG_FULL, /* Fully apply new config in .ndo_bpf() */ + ICE_XDP_CFG_PART, /* Save/use part of config in VSI rebuild */ +}; + int ice_vsi_determine_xdp_res(struct ice_vsi *vsi); -int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog); -int ice_destroy_xdp_rings(struct ice_vsi *vsi); +int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog, + enum ice_xdp_cfg cfg_type); +int ice_destroy_xdp_rings(struct ice_vsi *vsi, enum ice_xdp_cfg cfg_type); int ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags); diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 5a7ba0355d338..13ca3342a0cea 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -2462,7 +2462,8 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) ret = ice_vsi_determine_xdp_res(vsi); if (ret) goto unroll_vector_base; - ret = ice_prepare_xdp_rings(vsi, vsi->xdp_prog); + ret = ice_prepare_xdp_rings(vsi, vsi->xdp_prog, + ICE_XDP_CFG_PART); if (ret) goto unroll_vector_base; } @@ -2613,7 +2614,7 @@ void ice_vsi_decfg(struct ice_vsi *vsi) /* return value check can be skipped here, it always returns * 0 if reset is in progress */ - ice_destroy_xdp_rings(vsi); + ice_destroy_xdp_rings(vsi, ICE_XDP_CFG_PART);

ice_vsi_clear_rings(vsi); ice_vsi_free_q_vectors(vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 8ebb6517f6b96..5d71febdcd4dd 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2657,10 +2657,12 @@ static void ice_vsi_assign_bpf_prog(struct ice_vsi *vsi, struct bpf_prog *prog) * ice_prepare_xdp_rings - Allocate, configure and setup Tx rings for XDP * @vsi: VSI to bring up Tx rings used by XDP * @prog: bpf program that will be assigned to VSI + * @cfg_type: create from scratch or restore the existing configuration * * Return 0 on success and negative value on error */ -int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) +int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog, + enum ice_xdp_cfg cfg_type) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; int xdp_rings_rem = vsi->num_xdp_txq; @@ -2736,7 +2738,7 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) * taken into account at the end of ice_vsi_rebuild, where * ice_cfg_vsi_lan is being called */ - if (ice_is_reset_in_progress(pf->state)) + if (cfg_type == ICE_XDP_CFG_PART) return 0;

/* tell the Tx scheduler that right now we have @@ -2788,22 +2790,21 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) /** * ice_destroy_xdp_rings - undo the configuration made by ice_prepare_xdp_rings * @vsi: VSI to remove XDP rings + * @cfg_type: disable XDP permanently or allow it to be restored later * * Detach XDP rings from irq vectors, clean up the PF bitmap and free * resources */ -int ice_destroy_xdp_rings(struct ice_vsi *vsi) +int ice_destroy_xdp_rings(struct ice_vsi *vsi, enum ice_xdp_cfg cfg_type) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; struct ice_pf *pf = vsi->back; int i, v_idx;

/* q_vectors are freed in reset path so there's no point in detaching - * rings; in case of rebuild being triggered not from reset bits - * in pf->state won't be set, so additionally check first q_vector - * against NULL + * rings */ - if (ice_is_reset_in_progress(pf->state) || !vsi->q_vectors[0]) + if (cfg_type == ICE_XDP_CFG_PART) goto free_qmap;

ice_for_each_q_vector(vsi, v_idx) { @@ -2844,7 +2845,7 @@ int ice_destroy_xdp_rings(struct ice_vsi *vsi) if (static_key_enabled(&ice_xdp_locking_key)) static_branch_dec(&ice_xdp_locking_key);

- if (ice_is_reset_in_progress(pf->state) || !vsi->q_vectors[0]) + if (cfg_type == ICE_XDP_CFG_PART) return 0;

ice_vsi_assign_bpf_prog(vsi, NULL); @@ -2955,7 +2956,8 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, if (xdp_ring_err) { NL_SET_ERR_MSG_MOD(extack, "Not enough Tx resources for XDP"); } else { - xdp_ring_err = ice_prepare_xdp_rings(vsi, prog); + xdp_ring_err = ice_prepare_xdp_rings(vsi, prog, + ICE_XDP_CFG_FULL); if (xdp_ring_err) NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Tx resources failed"); } @@ -2966,7 +2968,7 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Rx resources failed"); } else if (ice_is_xdp_ena_vsi(vsi) && !prog) { xdp_features_clear_redirect_target(vsi->netdev); - xdp_ring_err = ice_destroy_xdp_rings(vsi); + xdp_ring_err = ice_destroy_xdp_rings(vsi, ICE_XDP_CFG_FULL); if (xdp_ring_err) NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx resources failed"); /* reallocate Rx queues that were used for zero-copy */

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kuniyuki Iwashima kuniyu@amazon.com

[ 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.

Fixes: 83301b5367a9 ("af_unix: Set TCP_ESTABLISHED for datagram sockets too") Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/unix/af_unix.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index d01314dc86ecb..348f9e34f6696 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -571,7 +571,6 @@ 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) @@ -1434,8 +1433,15 @@ 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;

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kuniyuki Iwashima kuniyu@amazon.com

[ 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().

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/unix/af_unix.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index bd2af62f58605..8d0918a112a9d 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2983,7 +2983,7 @@ 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);

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kuniyuki Iwashima kuniyu@amazon.com

[ 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.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/unix/af_unix.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 4a43091c95419..53d67d540a574 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1491,7 +1491,6 @@ 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) @@ -1577,9 +1576,7 @@ 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; @@ -1594,7 +1591,7 @@ 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);

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kuniyuki Iwashima kuniyu@amazon.com

[ 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.

Fixes: 77462de14a43 ("af_unix: Add read_sock for stream socket types") Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/unix/af_unix.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index dfa013283f478..2299a464c602e 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2630,7 +2630,7 @@ 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);

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kuniyuki Iwashima kuniyu@amazon.com

[ Upstream commit b0632e53e0da8054e36bc973f0eec69d30f1b7c6 ]

sk_setsockopt() changes sk->sk_sndbuf under lock_sock(), but it's not used in af_unix.c.

Let's use READ_ONCE() to read sk->sk_sndbuf in unix_writable(), unix_dgram_sendmsg(), and unix_stream_sendmsg().

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/unix/af_unix.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 2299a464c602e..4640497c29da4 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -534,7 +534,7 @@ static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other) static int unix_writable(const struct sock *sk, unsigned char state) { return state != TCP_LISTEN && - (refcount_read(&sk->sk_wmem_alloc) << 2) <= sk->sk_sndbuf; + (refcount_read(&sk->sk_wmem_alloc) << 2) <= READ_ONCE(sk->sk_sndbuf); }

static void unix_write_space(struct sock *sk) @@ -1944,7 +1944,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, }

err = -EMSGSIZE; - if (len > sk->sk_sndbuf - 32) + if (len > READ_ONCE(sk->sk_sndbuf) - 32) goto out;

if (len > SKB_MAX_ALLOC) { @@ -2223,7 +2223,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, &err, 0); } else { /* Keep two messages in the pipe so it schedules better */ - size = min_t(int, size, (sk->sk_sndbuf >> 1) - 64); + size = min_t(int, size, (READ_ONCE(sk->sk_sndbuf) >> 1) - 64);

/* allow fallback to order-0 allocations */ size = min_t(int, size, SKB_MAX_HEAD(0) + UNIX_SKB_FRAGS_SZ);

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kuniyuki Iwashima kuniyu@amazon.com

[ 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()

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/unix/af_unix.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 2b35c517be718..ea68472847cae 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -222,15 +222,9 @@ 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) @@ -1551,7 +1545,7 @@ 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;

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kuniyuki Iwashima kuniyu@amazon.com

[ 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().

Fixes: c9da99e6475f ("unix_diag: Fixup RQLEN extension report") Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/unix/diag.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/unix/diag.c b/net/unix/diag.c index 9151c72e742fc..fc56244214c30 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -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);

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet edumazet@google.com

[ 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

Fixes: d52d3997f843 ("ipv6: Create percpu rt6_info") Signed-off-by: Eric Dumazet edumazet@google.com Cc: Martin KaFai Lau kafai@fb.com Link: https://lore.kernel.org/r/20240604193549.981839-1-edumazet@google.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv6/ip6_fib.c | 6 +++++- net/ipv6/route.c | 1 + 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 8184076a3924e..4356806b52bd5 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -961,6 +961,7 @@ 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 */ @@ -969,7 +970,9 @@ 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 @@ -983,6 +986,7 @@ static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh, fib6_info_release(from); } } + rcu_read_unlock(); }

struct fib6_nh_pcpu_arg { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index c48eaa7c23401..0a37f04177337 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1399,6 +1399,7 @@ 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);

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Namjae Jeon linkinjeon@kernel.org

[ Upstream commit d1c189c6cb8b0fb7b5ee549237d27889c40c2f8b ]

lease break wait for lease break acknowledgment. rwsem is more suitable than unlock while traversing the list for parent lease break in ->m_op_list.

Cc: stable@vger.kernel.org Signed-off-by: Namjae Jeon linkinjeon@kernel.org Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/smb/server/oplock.c | 30 +++++++++++------------------- fs/smb/server/smb2pdu.c | 4 ++-- fs/smb/server/smb_common.c | 4 ++-- fs/smb/server/vfs_cache.c | 28 ++++++++++++++-------------- fs/smb/server/vfs_cache.h | 2 +- 5 files changed, 30 insertions(+), 38 deletions(-)

diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 7d17a14378e33..a8f52c4ebbdad 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -207,9 +207,9 @@ static void opinfo_add(struct oplock_info *opinfo) { struct ksmbd_inode *ci = opinfo->o_fp->f_ci;

- write_lock(&ci->m_lock); + down_write(&ci->m_lock); list_add_rcu(&opinfo->op_entry, &ci->m_op_list); - write_unlock(&ci->m_lock); + up_write(&ci->m_lock); }

static void opinfo_del(struct oplock_info *opinfo) @@ -221,9 +221,9 @@ static void opinfo_del(struct oplock_info *opinfo) lease_del_list(opinfo); write_unlock(&lease_list_lock); } - write_lock(&ci->m_lock); + down_write(&ci->m_lock); list_del_rcu(&opinfo->op_entry); - write_unlock(&ci->m_lock); + up_write(&ci->m_lock); }

static unsigned long opinfo_count(struct ksmbd_file *fp) @@ -526,21 +526,18 @@ static struct oplock_info *same_client_has_lease(struct ksmbd_inode *ci, * Compare lease key and client_guid to know request from same owner * of same client */ - read_lock(&ci->m_lock); + down_read(&ci->m_lock); list_for_each_entry(opinfo, &ci->m_op_list, op_entry) { if (!opinfo->is_lease || !opinfo->conn) continue; - read_unlock(&ci->m_lock); lease = opinfo->o_lease;

ret = compare_guid_key(opinfo, client_guid, lctx->lease_key); if (ret) { m_opinfo = opinfo; /* skip upgrading lease about breaking lease */ - if (atomic_read(&opinfo->breaking_cnt)) { - read_lock(&ci->m_lock); + if (atomic_read(&opinfo->breaking_cnt)) continue; - }

/* upgrading lease */ if ((atomic_read(&ci->op_count) + @@ -570,9 +567,8 @@ static struct oplock_info *same_client_has_lease(struct ksmbd_inode *ci, lease_none_upgrade(opinfo, lctx->req_state); } } - read_lock(&ci->m_lock); } - read_unlock(&ci->m_lock); + up_read(&ci->m_lock);

return m_opinfo; } @@ -1119,7 +1115,7 @@ void smb_send_parent_lease_break_noti(struct ksmbd_file *fp, if (!p_ci) return;

- read_lock(&p_ci->m_lock); + down_read(&p_ci->m_lock); list_for_each_entry(opinfo, &p_ci->m_op_list, op_entry) { if (opinfo->conn == NULL || !opinfo->is_lease) continue; @@ -1137,13 +1133,11 @@ void smb_send_parent_lease_break_noti(struct ksmbd_file *fp, continue; }

- read_unlock(&p_ci->m_lock); oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE); opinfo_conn_put(opinfo); - read_lock(&p_ci->m_lock); } } - read_unlock(&p_ci->m_lock); + up_read(&p_ci->m_lock);

ksmbd_inode_put(p_ci); } @@ -1164,7 +1158,7 @@ void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp) if (!p_ci) return;

- read_lock(&p_ci->m_lock); + down_read(&p_ci->m_lock); list_for_each_entry(opinfo, &p_ci->m_op_list, op_entry) { if (opinfo->conn == NULL || !opinfo->is_lease) continue; @@ -1178,13 +1172,11 @@ void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp) atomic_dec(&opinfo->conn->r_count); continue; } - read_unlock(&p_ci->m_lock); oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE); opinfo_conn_put(opinfo); - read_lock(&p_ci->m_lock); } } - read_unlock(&p_ci->m_lock); + up_read(&p_ci->m_lock);

ksmbd_inode_put(p_ci); } diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 6a15c5d64f415..8df93c9d4ee41 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -3376,9 +3376,9 @@ int smb2_open(struct ksmbd_work *work) * after daccess, saccess, attrib_only, and stream are * initialized. */ - write_lock(&fp->f_ci->m_lock); + down_write(&fp->f_ci->m_lock); list_add(&fp->node, &fp->f_ci->m_fp_list); - write_unlock(&fp->f_ci->m_lock); + up_write(&fp->f_ci->m_lock);

/* Check delete pending among previous fp before oplock break */ if (ksmbd_inode_pending_delete(fp)) { diff --git a/fs/smb/server/smb_common.c b/fs/smb/server/smb_common.c index fcaf373cc0080..474dadf6b7b8b 100644 --- a/fs/smb/server/smb_common.c +++ b/fs/smb/server/smb_common.c @@ -646,7 +646,7 @@ int ksmbd_smb_check_shared_mode(struct file *filp, struct ksmbd_file *curr_fp) * Lookup fp in master fp list, and check desired access and * shared mode between previous open and current open. */ - read_lock(&curr_fp->f_ci->m_lock); + down_read(&curr_fp->f_ci->m_lock); list_for_each_entry(prev_fp, &curr_fp->f_ci->m_fp_list, node) { if (file_inode(filp) != file_inode(prev_fp->filp)) continue; @@ -722,7 +722,7 @@ int ksmbd_smb_check_shared_mode(struct file *filp, struct ksmbd_file *curr_fp) break; } } - read_unlock(&curr_fp->f_ci->m_lock); + up_read(&curr_fp->f_ci->m_lock);

return rc; } diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 030f70700036c..6cb599cd287ee 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -165,7 +165,7 @@ static int ksmbd_inode_init(struct ksmbd_inode *ci, struct ksmbd_file *fp) ci->m_fattr = 0; INIT_LIST_HEAD(&ci->m_fp_list); INIT_LIST_HEAD(&ci->m_op_list); - rwlock_init(&ci->m_lock); + init_rwsem(&ci->m_lock); ci->m_de = fp->filp->f_path.dentry; return 0; } @@ -261,14 +261,14 @@ static void __ksmbd_inode_close(struct ksmbd_file *fp) }

if (atomic_dec_and_test(&ci->m_count)) { - write_lock(&ci->m_lock); + down_write(&ci->m_lock); if (ci->m_flags & (S_DEL_ON_CLS | S_DEL_PENDING)) { ci->m_flags &= ~(S_DEL_ON_CLS | S_DEL_PENDING); - write_unlock(&ci->m_lock); + up_write(&ci->m_lock); ksmbd_vfs_unlink(filp); - write_lock(&ci->m_lock); + down_write(&ci->m_lock); } - write_unlock(&ci->m_lock); + up_write(&ci->m_lock);

ksmbd_inode_free(ci); } @@ -289,9 +289,9 @@ static void __ksmbd_remove_fd(struct ksmbd_file_table *ft, struct ksmbd_file *fp if (!has_file_id(fp->volatile_id)) return;

- write_lock(&fp->f_ci->m_lock); + down_write(&fp->f_ci->m_lock); list_del_init(&fp->node); - write_unlock(&fp->f_ci->m_lock); + up_write(&fp->f_ci->m_lock);

write_lock(&ft->lock); idr_remove(ft->idr, fp->volatile_id); @@ -523,17 +523,17 @@ struct ksmbd_file *ksmbd_lookup_fd_inode(struct dentry *dentry) if (!ci) return NULL;

- read_lock(&ci->m_lock); + down_read(&ci->m_lock); list_for_each_entry(lfp, &ci->m_fp_list, node) { if (inode == file_inode(lfp->filp)) { atomic_dec(&ci->m_count); lfp = ksmbd_fp_get(lfp); - read_unlock(&ci->m_lock); + up_read(&ci->m_lock); return lfp; } } atomic_dec(&ci->m_count); - read_unlock(&ci->m_lock); + up_read(&ci->m_lock); return NULL; }

@@ -705,13 +705,13 @@ static bool session_fd_check(struct ksmbd_tree_connect *tcon,

conn = fp->conn; ci = fp->f_ci; - write_lock(&ci->m_lock); + down_write(&ci->m_lock); list_for_each_entry_rcu(op, &ci->m_op_list, op_entry) { if (op->conn != conn) continue; op->conn = NULL; } - write_unlock(&ci->m_lock); + up_write(&ci->m_lock);

fp->conn = NULL; fp->tcon = NULL; @@ -801,13 +801,13 @@ int ksmbd_reopen_durable_fd(struct ksmbd_work *work, struct ksmbd_file *fp) fp->tcon = work->tcon;

ci = fp->f_ci; - write_lock(&ci->m_lock); + down_write(&ci->m_lock); list_for_each_entry_rcu(op, &ci->m_op_list, op_entry) { if (op->conn) continue; op->conn = fp->conn; } - write_unlock(&ci->m_lock); + up_write(&ci->m_lock);

__open_id(&work->sess->file_table, fp, OPEN_ID_TYPE_VOLATILE_ID); if (!has_file_id(fp->volatile_id)) { diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index ed44fb4e18e79..5a225e7055f19 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -47,7 +47,7 @@ struct stream { };

struct ksmbd_inode { - rwlock_t m_lock; + struct rw_semaphore m_lock; atomic_t m_count; atomic_t op_count; /* opinfo count for streams */

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Matthew Wilcox (Oracle) willy@infradead.org

[ Upstream commit b6fd410c32f1a66a52a42d6aae1ab7b011b74547 ]

This function was already explicitly calling compound_head(); unfortunately the compiler can't know that and elide the redundant calls to compound_head() buried in page_mapping(), unlock_page(), etc. Switch to using a folio, which does let us elide these calls.

Link: https://lkml.kernel.org/r/20231117161447.2461643-5-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) willy@infradead.org Cc: Naoya Horiguchi naoya.horiguchi@nec.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Stable-dep-of: 8cf360b9d6a8 ("mm/memory-failure: fix handling of dissolved but not taken off from buddy pages") Signed-off-by: Sasha Levin sashal@kernel.org --- mm/memory-failure.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 5378edad9df8f..9c27ec0a27a30 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1193,25 +1193,25 @@ static int me_swapcache_clean(struct page_state *ps, struct page *p) */ static int me_huge_page(struct page_state *ps, struct page *p) { + struct folio *folio = page_folio(p); int res; - struct page *hpage = compound_head(p); struct address_space *mapping; bool extra_pins = false;

- mapping = page_mapping(hpage); + mapping = folio_mapping(folio); if (mapping) { - res = truncate_error_page(hpage, page_to_pfn(p), mapping); + res = truncate_error_page(&folio->page, page_to_pfn(p), mapping); /* The page is kept in page cache. */ extra_pins = true; - unlock_page(hpage); + folio_unlock(folio); } else { - unlock_page(hpage); + folio_unlock(folio); /* * migration entry prevents later access on error hugepage, * so we can free and dissolve it into buddy to save healthy * subpages. */ - put_page(hpage); + folio_put(folio); if (__page_handle_poison(p) >= 0) { page_ref_inc(p); res = MF_RECOVERED;

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Muhammad Usama Anjum usama.anjum@collabora.com

[ Upstream commit 9a21701edc41465de56f97914741bfb7bfc2517d ]

Conform the layout, informational and status messages to TAP. No functional change is intended other than the layout of output messages.

Link: https://lkml.kernel.org/r/20240101083614.1076768-1-usama.anjum@collabora.com Signed-off-by: Muhammad Usama Anjum usama.anjum@collabora.com Cc: Shuah Khan shuah@kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Stable-dep-of: d4202e66a4b1 ("selftests/mm: compaction_test: fix bogus test success on Aarch64") Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/mm/compaction_test.c | 91 ++++++++++---------- 1 file changed, 44 insertions(+), 47 deletions(-)

diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c index 55dec92e1e58c..f81931c1f8386 100644 --- a/tools/testing/selftests/mm/compaction_test.c +++ b/tools/testing/selftests/mm/compaction_test.c @@ -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(); }

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Yu Chien Peter Lin peterlin@andestech.com

[ Upstream commit 96303bcb401c21dc1426d8d9bb1fc74aae5c02a9 ]

Currently, the implementation of the RISC-V INTC driver uses the interrupt cause as the hardware interrupt number, with a maximum of 64 interrupts. However, the platform can expand the interrupt number further for custom local interrupts.

To fully utilize the available local interrupt sources, switch to using irq_domain_create_tree() that creates the radix tree map, add global variables (riscv_intc_nr_irqs, riscv_intc_custom_base and riscv_intc_custom_nr_irqs) to determine the valid range of local interrupt number (hwirq).

Signed-off-by: Yu Chien Peter Lin peterlin@andestech.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Randolph randolph@andestech.com Reviewed-by: Anup Patel anup@brainfault.org Reviewed-by: Atish Patra atishp@rivosinc.com Link: https://lore.kernel.org/r/20240222083946.3977135-3-peterlin@andestech.com Stable-dep-of: 0110c4b11047 ("irqchip/riscv-intc: Prevent memory leak when riscv_intc_init_common() fails") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/irqchip/irq-riscv-intc.c | 26 +++++++++++++++++++------- 1 file changed, 19 insertions(+), 7 deletions(-)

diff --git a/drivers/irqchip/irq-riscv-intc.c b/drivers/irqchip/irq-riscv-intc.c index e8d01b14ccdde..684875c397280 100644 --- a/drivers/irqchip/irq-riscv-intc.c +++ b/drivers/irqchip/irq-riscv-intc.c @@ -19,15 +19,16 @@ #include <linux/smp.h>

static struct irq_domain *intc_domain; +static unsigned int riscv_intc_nr_irqs __ro_after_init = BITS_PER_LONG; +static unsigned int riscv_intc_custom_base __ro_after_init = BITS_PER_LONG; +static unsigned int riscv_intc_custom_nr_irqs __ro_after_init;

static asmlinkage void riscv_intc_irq(struct pt_regs *regs) { unsigned long cause = regs->cause & ~CAUSE_IRQ_FLAG;

- if (unlikely(cause >= BITS_PER_LONG)) - panic("unexpected interrupt cause"); - - generic_handle_domain_irq(intc_domain, cause); + if (generic_handle_domain_irq(intc_domain, cause)) + pr_warn_ratelimited("Failed to handle interrupt (cause: %ld)\n", cause); }

/* @@ -93,6 +94,14 @@ static int riscv_intc_domain_alloc(struct irq_domain *domain, if (ret) return ret;

+ /* + * Only allow hwirq for which we have corresponding standard or + * custom interrupt enable register. + */ + if ((hwirq >= riscv_intc_nr_irqs && hwirq < riscv_intc_custom_base) || + (hwirq >= riscv_intc_custom_base + riscv_intc_custom_nr_irqs)) + return -EINVAL; + for (i = 0; i < nr_irqs; i++) { ret = riscv_intc_domain_map(domain, virq + i, hwirq + i); if (ret) @@ -117,8 +126,7 @@ static int __init riscv_intc_init_common(struct fwnode_handle *fn) { int rc;

- intc_domain = irq_domain_create_linear(fn, BITS_PER_LONG, - &riscv_intc_domain_ops, NULL); + intc_domain = irq_domain_create_tree(fn, &riscv_intc_domain_ops, NULL); if (!intc_domain) { pr_err("unable to add IRQ domain\n"); return -ENXIO; @@ -132,7 +140,11 @@ static int __init riscv_intc_init_common(struct fwnode_handle *fn)

riscv_set_intc_hwnode_fn(riscv_intc_hwnode);

- pr_info("%d local interrupts mapped\n", BITS_PER_LONG); + pr_info("%d local interrupts mapped\n", riscv_intc_nr_irqs); + if (riscv_intc_custom_nr_irqs) { + pr_info("%d custom local interrupts mapped\n", + riscv_intc_custom_nr_irqs); + }

return 0; }

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sunil V L sunilvl@ventanamicro.com

[ Upstream commit 0110c4b110477bb1f19b0d02361846be7ab08300 ]

When riscv_intc_init_common() fails, the firmware node allocated is not freed. Add the missing free().

Fixes: 7023b9d83f03 ("irqchip/riscv-intc: Add ACPI support") Signed-off-by: Sunil V L sunilvl@ventanamicro.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Anup Patel anup@brainfault.org Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20240527081113.616189-1-sunilvl@ventanamicro.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/irqchip/irq-riscv-intc.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/irqchip/irq-riscv-intc.c b/drivers/irqchip/irq-riscv-intc.c index 0cd6b48a5dbf9..627beae9649a2 100644 --- a/drivers/irqchip/irq-riscv-intc.c +++ b/drivers/irqchip/irq-riscv-intc.c @@ -232,8 +232,9 @@ IRQCHIP_DECLARE(andes, "andestech,cpu-intc", riscv_intc_init); static int __init riscv_intc_acpi_init(union acpi_subtable_headers *header, const unsigned long end) { - struct fwnode_handle *fn; struct acpi_madt_rintc *rintc; + struct fwnode_handle *fn; + int rc;

rintc = (struct acpi_madt_rintc *)header;

@@ -252,7 +253,11 @@ static int __init riscv_intc_acpi_init(union acpi_subtable_headers *header, return -ENOMEM; }

- return riscv_intc_init_common(fn, &riscv_intc_chip); + rc = riscv_intc_init_common(fn, &riscv_intc_chip); + if (rc) + irq_domain_free_fwnode(fn); + + return rc; }

IRQCHIP_ACPI_DECLARE(riscv_intc, ACPI_MADT_TYPE_RINTC, NULL,

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andrii Nakryiko andrii@kernel.org

[ Upstream commit 46ba0e49b64232adac35a2bc892f1710c5b0fb7f ]

Current implementation of PID filtering logic for multi-uprobes in uprobe_prog_run() is filtering down to exact *thread*, while the intent for PID filtering it to filter by *process* instead. The check in uprobe_prog_run() also differs from the analogous one in uprobe_multi_link_filter() for some reason. The latter is correct, checking task->mm, not the task itself.

Fix the check in uprobe_prog_run() to perform the same task->mm check.

While doing this, we also update get_pid_task() use to use PIDTYPE_TGID type of lookup, given the intent is to get a representative task of an entire process. This doesn't change behavior, but seems more logical. It would hold task group leader task now, not any random thread task.

Last but not least, given multi-uprobe support is half-broken due to this PID filtering logic (depending on whether PID filtering is important or not), we need to make it easy for user space consumers (including libbpf) to easily detect whether PID filtering logic was already fixed.

We do it here by adding an early check on passed pid parameter. If it's negative (and so has no chance of being a valid PID), we return -EINVAL. Previous behavior would eventually return -ESRCH ("No process found"), given there can't be any process with negative PID. This subtle change won't make any practical change in behavior, but will allow applications to detect PID filtering fixes easily. Libbpf fixes take advantage of this in the next patch.

Cc: stable@vger.kernel.org Acked-by: Jiri Olsa jolsa@kernel.org Fixes: b733eeade420 ("bpf: Add pid filter support for uprobe_multi link") Signed-off-by: Andrii Nakryiko andrii@kernel.org Link: https://lore.kernel.org/r/20240521163401.3005045-2-andrii@kernel.org Signed-off-by: Alexei Starovoitov ast@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/trace/bpf_trace.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 8edbafe0d4cdf..cc29bf49f7159 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -3099,7 +3099,7 @@ static int uprobe_prog_run(struct bpf_uprobe *uprobe, struct bpf_run_ctx *old_run_ctx; int err = 0;

- if (link->task && current != link->task) + if (link->task && current->mm != link->task->mm) return 0;

if (sleepable) @@ -3200,8 +3200,9 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr upath = u64_to_user_ptr(attr->link_create.uprobe_multi.path); uoffsets = u64_to_user_ptr(attr->link_create.uprobe_multi.offsets); cnt = attr->link_create.uprobe_multi.cnt; + pid = attr->link_create.uprobe_multi.pid;

- if (!upath || !uoffsets || !cnt) + if (!upath || !uoffsets || !cnt || pid < 0) return -EINVAL; if (cnt > MAX_UPROBE_MULTI_CNT) return -E2BIG; @@ -3225,10 +3226,9 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr goto error_path_put; }

- pid = attr->link_create.uprobe_multi.pid; if (pid) { rcu_read_lock(); - task = get_pid_task(find_vpid(pid), PIDTYPE_PID); + task = get_pid_task(find_vpid(pid), PIDTYPE_TGID); rcu_read_unlock(); if (!task) { err = -ESRCH;

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ryusuke Konishi konishi.ryusuke@gmail.com

[ 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.

Link: https://lkml.kernel.org/r/20240604134255.7165-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi konishi.ryusuke@gmail.com Reported-by: syzbot+c8166c541d3971bf6c87@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=c8166c541d3971bf6c87 Fixes: 2ba466d74ed7 ("nilfs2: directory entry operations") Tested-by: Ryusuke Konishi konishi.ryusuke@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nilfs2/dir.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index c6b88be8a9d73..23a8357f127bc 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -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);

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jens Axboe axboe@kernel.dk

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.

Cc: stable@vger.kernel.org Fixes: a76c0b31eef5 ("io_uring: commit non-pollable provided mapped buffers upfront") Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- io_uring/kbuf.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -168,7 +168,8 @@ 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

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: John Ernberg john.ernberg@actia.se

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.

Fixes: 494ed3997d75 ("usb: Introduce Xen pvUSB frontend (xen hcd)") Cc: stable@vger.kernel.org # v5.17+ Signed-off-by: John Ernberg john.ernberg@actia.se Link: https://lore.kernel.org/r/20240517114345.1190755-1-john.ernberg@actia.se Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/Makefile | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/usb/Makefile +++ b/drivers/usb/Makefile @@ -35,6 +35,7 @@ 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/

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kyle Tso kyletso@google.com

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]

Fixes: f0690a25a140 ("staging: typec: USB Type-C Port Manager (tcpm)") Cc: stable@vger.kernel.org Signed-off-by: Kyle Tso kyletso@google.com Reviewed-by: Heikki Krogerus heikki.krogerus@linux.intel.com Link: https://lore.kernel.org/r/20240520154858.1072347-1-kyletso@google.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/typec/tcpm/tcpm.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -5415,6 +5415,7 @@ 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:

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ilpo Järvinen ilpo.jarvinen@linux.intel.com

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).

Reported-by: Vadym Krevs vkrevs@yahoo.com Fixes: 6bb6fa6908eb ("tty: Implement lookahead to process XON/XOFF timely") Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218834 Tested-by: Vadym Krevs vkrevs@yahoo.com Cc: stable@vger.kernel.org Signed-off-by: Ilpo Järvinen ilpo.jarvinen@linux.intel.com Link: https://lore.kernel.org/r/20240514140429.12087-1-ilpo.jarvinen@linux.intel.c... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/tty/n_tty.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-)

--- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -1624,15 +1624,25 @@ static void __receive_buf(struct tty_str else 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)

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Mickaël Salaün mic@digikod.net

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.

Cc: Günther Noack gnoack@google.com Cc: Paul Moore paul@paul-moore.com Cc: stable@vger.kernel.org Reported-by: syzbot+bf4903dc7e12b18ebc87@syzkaller.appspotmail.com Fixes: b91c3e4ea756 ("landlock: Add support for file reparenting with LANDLOCK_ACCESS_FS_REFER") Closes: https://lore.kernel.org/r/000000000000553d3f0618198200@google.com Link: https://lore.kernel.org/r/20240516181935.1645983-2-mic@digikod.net [mic: Fix commit message] Signed-off-by: Mickaël Salaün mic@digikod.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- security/landlock/fs.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-)

--- a/security/landlock/fs.c +++ b/security/landlock/fs.c @@ -820,6 +820,7 @@ static int current_check_refer_path(stru bool 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] = {};

@@ -867,9 +868,17 @@ 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);

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Mathias Nyman mathias.nyman@linux.intel.com

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.

Tested-by: Pierre Tomon pierretom+12@ik.me Cc: stable@vger.kernel.org # v4.10+ Cc: Alan Stern stern@rowland.harvard.edu Signed-off-by: Mathias Nyman mathias.nyman@linux.intel.com Link: https://lore.kernel.org/r/20240611120610.3264502-2-mathias.nyman@linux.intel... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/host/xhci-ring.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)

--- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -2525,9 +2525,8 @@ 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) ||

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hector Martin marcan@marcan.st

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).

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/20240524-xhci-streams-v1-1-6b1f13819bea@ma...

Fixes: e9df17eb1408 ("USB: xhci: Correct assumptions about number of rings per endpoint.") Fixes: 94f339147fc3 ("xhci: Fix failure to give back some cached cancelled URBs.") Fixes: 674f8438c121 ("xhci: split handling halted endpoints into two steps") Cc: stable@vger.kernel.org Cc: security@kernel.org Reviewed-by: Neal Gompa neal@gompa.dev Signed-off-by: Hector Martin marcan@marcan.st Signed-off-by: Mathias Nyman mathias.nyman@linux.intel.com Link: https://lore.kernel.org/r/20240611120610.3264502-5-mathias.nyman@linux.intel... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/host/xhci-ring.c | 54 ++++++++++++++++++++++++++++++++++--------- drivers/usb/host/xhci.h | 1 2 files changed, 44 insertions(+), 11 deletions(-)

--- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -1027,13 +1027,27 @@ static int xhci_invalidate_cancelled_tds break; 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; } @@ -1053,10 +1067,16 @@ static int xhci_invalidate_cancelled_tds if (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; } @@ -1334,6 +1354,7 @@ static void xhci_handle_cmd_set_deq(stru struct 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])); @@ -1420,6 +1441,8 @@ static void xhci_handle_cmd_set_deq(stru xhci_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); @@ -1429,8 +1452,17 @@ 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, --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1559,6 +1559,7 @@ enum xhci_cancelled_td_status { TD_DIRTY = 0, TD_HALTED, TD_CLEARING_CACHE, + TD_CLEARING_CACHE_DEFERRED, TD_CLEARED, };

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Aapo Vienamo aapo.vienamo@linux.intel.com

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.

Signed-off-by: Aapo Vienamo aapo.vienamo@linux.intel.com Fixes: d0f1e0c2a699 ("thunderbolt: Add support for receiver lane margining") Cc: stable@vger.kernel.org Signed-off-by: Mika Westerberg mika.westerberg@linux.intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/thunderbolt/debugfs.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

--- a/drivers/thunderbolt/debugfs.c +++ b/drivers/thunderbolt/debugfs.c @@ -943,8 +943,9 @@ static void margining_port_init(struct t debugfs_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); }

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Damien Le Moal dlemoal@kernel.org

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.

Reported-by: Scott McCoy scott.mccoy@wdc.com Fixes: 023ab2a9b4ed ("scsi: mpi3mr: Add support for queue command processing") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal dlemoal@kernel.org Link: https://lore.kernel.org/r/20240611083435.92961-1-dlemoal@kernel.org Reviewed-by: Niklas Cassel cassel@kernel.org Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- 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(-)

--- a/drivers/scsi/mpi3mr/mpi3mr_app.c +++ b/drivers/scsi/mpi3mr/mpi3mr_app.c @@ -1854,10 +1854,72 @@ 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, };

--- a/drivers/scsi/mpt3sas/mpt3sas_base.h +++ b/drivers/scsi/mpt3sas/mpt3sas_base.h @@ -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); --- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c +++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c @@ -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 device if (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; --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -12590,29 +12590,6 @@ scsih_pci_mmio_enabled(struct pci_dev *p return 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. */ --- a/drivers/scsi/scsi_transport_sas.c +++ b/drivers/scsi/scsi_transport_sas.c @@ -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 */ --- a/include/scsi/scsi_transport_sas.h +++ b/include/scsi/scsi_transport_sas.h @@ -200,6 +200,8 @@ unsigned int sas_is_tlr_enabled(struct s void 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 *);

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Martin K. Petersen martin.petersen@oracle.com

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).

Link: https://bugzilla.kernel.org/show_bug.cgi?id=218890 Link: https://lore.kernel.org/r/70dd7ae0-b6b1-48e1-bb59-53b7c7f18274@rowland.harva... Link: https://lore.kernel.org/r/20240605022521.3960956-1-martin.petersen@oracle.co... Fixes: 321da3dc1f3c ("scsi: sd: usb_storage: uas: Access media prior to querying device properties") Cc: stable@vger.kernel.org Reported-by: Pierre Tomon pierretom+12@ik.me Suggested-by: Alan Stern stern@rowland.harvard.edu Tested-by: Pierre Tomon pierretom+12@ik.me Reviewed-by: Bart Van Assche bvanassche@acm.org Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/scsi/sd.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-)

--- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3406,16 +3406,23 @@ static bool sd_validate_opt_xfer_size(st

static 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_cmd(sdkp->device, cmd, REQ_OP_DRV_IN, buffer, buf_len, SD_TIMEOUT, sdkp->max_retries, NULL);

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Michael Ellerman mpe@ellerman.id.au

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.

Fixes: c20beffeec3c ("powerpc/uaccess: Use flexible addressing with __put_user()/__get_user()") Cc: stable@vger.kernel.org # v5.10+ Suggested-by: Kewen Lin linkw@gcc.gnu.org Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://msgid.link/20240529123029.146953-1-mpe@ellerman.id.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/include/asm/uaccess.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+)

--- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -92,9 +92,25 @@ __pu_failed: \ : label) #endif

+#ifdef CONFIG_CC_IS_CLANG +#define DS_FORM_CONSTRAINT "Z<>" +#else +#define DS_FORM_CONSTRAINT "YZ<>" +#endif + #ifdef __powerpc64__ +#ifdef CONFIG_PPC_KERNEL_PREFIXED #define __put_user_asm2_goto(x, ptr, label) \ __put_user_asm_goto(x, ptr, label, "std") +#else +#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) +#endif // CONFIG_PPC_KERNEL_PREFIXED #else /* __powerpc64__ */ #define __put_user_asm2_goto(x, addr, label) \ asm goto( \

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Dave Jiang dave.jiang@intel.com

[ 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.o tools/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

Fixes: 7d3eb23c4ccf ("tools/testing/cxl: Introduce a mock memory device + driver") Reviewed-by: Dan Williams dan.j.williams@intel.com Reviewed-by: Alison Schofield alison.schofield@intel.com Link: https://lore.kernel.org/r/20240528225551.1025977-1-dave.jiang@intel.com Signed-off-by: Dave Jiang dave.jiang@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/cxl/test/mem.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index 68118c37f0b56..0ed100617d993 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -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>

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Baokun Li libaokun1@huawei.com

[ Upstream commit cc5ac966f26193ab185cc43d64d9f1ae998ccb6e ]

This lets us see the correct trace output.

Fixes: c8383054506c ("cachefiles: notify the user daemon when looking up cookie") Signed-off-by: Baokun Li libaokun1@huawei.com Link: https://lore.kernel.org/r/20240522114308.2402121-2-libaokun@huaweicloud.com Acked-by: Jeff Layton jlayton@kernel.org Reviewed-by: Jingbo Xu jefflexu@linux.alibaba.com Signed-off-by: Christian Brauner brauner@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/trace/events/cachefiles.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index cf4b98b9a9edc..e3213af847cdf 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -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 ") \

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jia Zhu zhujia.zj@bytedance.com

[ Upstream commit 357a18d033143617e9c7d420c8f0dd4cbab5f34d ]

Previously, @ondemand_id field was used not only to identify ondemand state of the object, but also to represent the index of the xarray. This commit introduces @state field to decouple the role of @ondemand_id and adds helpers to access it.

Signed-off-by: Jia Zhu zhujia.zj@bytedance.com Link: https://lore.kernel.org/r/20231120041422.75170-2-zhujia.zj@bytedance.com Reviewed-by: Jingbo Xu jefflexu@linux.alibaba.com Reviewed-by: David Howells dhowells@redhat.com Signed-off-by: Christian Brauner brauner@kernel.org Stable-dep-of: 0a790040838c ("cachefiles: add spin_lock for cachefiles_ondemand_info") Signed-off-by: Sasha Levin sashal@kernel.org --- fs/cachefiles/internal.h | 21 +++++++++++++++++++++ fs/cachefiles/ondemand.c | 21 +++++++++------------ 2 files changed, 30 insertions(+), 12 deletions(-)

diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index 2ad58c4652084..00beedeaec183 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -44,6 +44,11 @@ struct cachefiles_volume { struct dentry *fanout[256]; /* Fanout subdirs */ };

+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 */ +}; + /* * Backing file state. */ @@ -62,6 +67,7 @@ struct cachefiles_object { #define CACHEFILES_OBJECT_USING_TMPFILE 0 /* Have an unlinked tmpfile */ #ifdef CONFIG_CACHEFILES_ONDEMAND int ondemand_id; + enum cachefiles_object_state state; #endif };

@@ -296,6 +302,21 @@ extern void cachefiles_ondemand_clean_object(struct cachefiles_object *object); extern int cachefiles_ondemand_read(struct cachefiles_object *object, loff_t pos, size_t len);

+#define CACHEFILES_OBJECT_STATE_FUNCS(_state, _STATE) \ +static inline bool \ +cachefiles_ondemand_object_is_##_state(const struct cachefiles_object *object) \ +{ \ + return object->state == CACHEFILES_ONDEMAND_OBJSTATE_##_STATE; \ +} \ + \ +static inline void \ +cachefiles_ondemand_set_object_##_state(struct cachefiles_object *object) \ +{ \ + object->state = CACHEFILES_ONDEMAND_OBJSTATE_##_STATE; \ +} + +CACHEFILES_OBJECT_STATE_FUNCS(open, OPEN); +CACHEFILES_OBJECT_STATE_FUNCS(close, CLOSE); #else static inline ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, char __user *_buffer, size_t buflen) diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c index 0254ed39f68ce..90456b8a4b3e0 100644 --- a/fs/cachefiles/ondemand.c +++ b/fs/cachefiles/ondemand.c @@ -15,6 +15,7 @@ static int cachefiles_ondemand_fd_release(struct inode *inode,

xa_lock(&cache->reqs); object->ondemand_id = CACHEFILES_ONDEMAND_ID_CLOSED; + cachefiles_ondemand_set_object_close(object);

/* * Flush all pending READ requests since their completion depends on @@ -176,6 +177,8 @@ int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args) set_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); trace_cachefiles_ondemand_copen(req->object, id, size);

+ cachefiles_ondemand_set_object_open(req->object); + out: complete(&req->done); return ret; @@ -363,7 +366,8 @@ static int cachefiles_ondemand_send_req(struct cachefiles_object *object, /* coupled with the barrier in cachefiles_flush_reqs() */ smp_mb();

- if (opcode != CACHEFILES_OP_OPEN && object->ondemand_id <= 0) { + if (opcode != CACHEFILES_OP_OPEN && + !cachefiles_ondemand_object_is_open(object)) { WARN_ON_ONCE(object->ondemand_id == 0); xas_unlock(&xas); ret = -EIO; @@ -430,18 +434,11 @@ static int cachefiles_ondemand_init_close_req(struct cachefiles_req *req, void *private) { struct cachefiles_object *object = req->object; - int object_id = object->ondemand_id;

- /* - * It's possible that object id is still 0 if the cookie looking up - * phase failed before OPEN request has ever been sent. Also avoid - * sending CLOSE request for CACHEFILES_ONDEMAND_ID_CLOSED, which means - * anon_fd has already been closed. - */ - if (object_id <= 0) + if (!cachefiles_ondemand_object_is_open(object)) return -ENOENT;

- req->msg.object_id = object_id; + req->msg.object_id = object->ondemand_id; trace_cachefiles_ondemand_close(object, &req->msg); return 0; } @@ -460,7 +457,7 @@ static int cachefiles_ondemand_init_read_req(struct cachefiles_req *req, int object_id = object->ondemand_id;

/* Stop enqueuing requests when daemon has closed anon_fd. */ - if (object_id <= 0) { + if (!cachefiles_ondemand_object_is_open(object)) { WARN_ON_ONCE(object_id == 0); pr_info_once("READ: anonymous fd closed prematurely.\n"); return -EIO; @@ -485,7 +482,7 @@ int cachefiles_ondemand_init_object(struct cachefiles_object *object) * creating a new tmpfile as the cache file. Reuse the previously * allocated object ID if any. */ - if (object->ondemand_id > 0) + if (cachefiles_ondemand_object_is_open(object)) return 0;

volume_key_size = volume->key[0] + 1;

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jia Zhu zhujia.zj@bytedance.com

[ 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.

Signed-off-by: Jia Zhu zhujia.zj@bytedance.com Link: https://lore.kernel.org/r/20231120041422.75170-4-zhujia.zj@bytedance.com Reviewed-by: Jingbo Xu jefflexu@linux.alibaba.com Reviewed-by: David Howells dhowells@redhat.com Signed-off-by: Christian Brauner brauner@kernel.org Stable-dep-of: 0a790040838c ("cachefiles: add spin_lock for cachefiles_ondemand_info") Signed-off-by: Sasha Levin sashal@kernel.org --- fs/cachefiles/internal.h | 3 ++ fs/cachefiles/ondemand.c | 98 ++++++++++++++++++++++++++++------------ 2 files changed, 72 insertions(+), 29 deletions(-)

diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index b0fe76964bc0d..b9a90f1a0c015 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -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) diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c index deb7e3007aa1d..8e130de952f7d 100644 --- a/fs/cachefiles/ondemand.c +++ b/fs/cachefiles/ondemand.c @@ -18,14 +18,10 @@ static int cachefiles_ondemand_fd_release(struct inode *inode, info->ondemand_id = CACHEFILES_ONDEMAND_ID_CLOSED; cachefiles_ondemand_set_object_close(object);

- /* - * Flush all pending READ requests since their completion depends on - * anon_fd. - */ - xas_for_each(&xas, req, ULONG_MAX) { + /* Only flush CACHEFILES_REQ_NEW marked req to avoid race with daemon_read */ + xas_for_each_marked(&xas, req, ULONG_MAX, CACHEFILES_REQ_NEW) { if (req->msg.object_id == object_id && - req->msg.opcode == CACHEFILES_OP_READ) { - req->error = -EIO; + req->msg.opcode == CACHEFILES_OP_CLOSE) { complete(&req->done); xas_store(&xas, NULL); } @@ -179,6 +175,7 @@ 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); + wake_up_all(&cache->daemon_pollwq);

out: complete(&req->done); @@ -222,7 +219,6 @@ static int cachefiles_ondemand_get_fd(struct cachefiles_req *req)

load = (void *)req->msg.data; load->fd = fd; - req->msg.object_id = object_id; object->ondemand->ondemand_id = object_id;

cachefiles_get_unbind_pincount(cache); @@ -238,6 +234,43 @@ static int cachefiles_ondemand_get_fd(struct cachefiles_req *req) return ret; }

+static void ondemand_object_worker(struct work_struct *work) +{ + struct cachefiles_ondemand_info *info = + container_of(work, struct cachefiles_ondemand_info, ondemand_work); + + cachefiles_ondemand_init_object(info->object); +} + +/* + * If there are any inflight or subsequent READ requests on the + * closed object, reopen it. + * Skip read requests whose related object is reopening. + */ +static struct cachefiles_req *cachefiles_ondemand_select_req(struct xa_state *xas, + unsigned long xa_max) +{ + struct cachefiles_req *req; + struct cachefiles_object *object; + struct cachefiles_ondemand_info *info; + + xas_for_each_marked(xas, req, xa_max, CACHEFILES_REQ_NEW) { + if (req->msg.opcode != CACHEFILES_OP_READ) + return req; + object = req->object; + info = object->ondemand; + if (cachefiles_ondemand_object_is_close(object)) { + cachefiles_ondemand_set_object_reopening(object); + queue_work(fscache_wq, &info->ondemand_work); + continue; + } + if (cachefiles_ondemand_object_is_reopening(object)) + continue; + return req; + } + return NULL; +} + ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, char __user *_buffer, size_t buflen) { @@ -248,16 +281,16 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, int ret = 0; XA_STATE(xas, &cache->reqs, cache->req_id_next);

+ xa_lock(&cache->reqs); /* * Cyclically search for a request that has not ever been processed, * to prevent requests from being processed repeatedly, and make * request distribution fair. */ - xa_lock(&cache->reqs); - req = xas_find_marked(&xas, UINT_MAX, CACHEFILES_REQ_NEW); + req = cachefiles_ondemand_select_req(&xas, ULONG_MAX); if (!req && cache->req_id_next > 0) { xas_set(&xas, 0); - req = xas_find_marked(&xas, cache->req_id_next - 1, CACHEFILES_REQ_NEW); + req = cachefiles_ondemand_select_req(&xas, cache->req_id_next - 1); } if (!req) { xa_unlock(&cache->reqs); @@ -277,14 +310,18 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache, xa_unlock(&cache->reqs);

id = xas.xa_index; - msg->msg_id = id;

if (msg->opcode == CACHEFILES_OP_OPEN) { ret = cachefiles_ondemand_get_fd(req); - if (ret) + if (ret) { + cachefiles_ondemand_set_object_close(req->object); goto error; + } }

+ msg->msg_id = id; + msg->object_id = req->object->ondemand->ondemand_id; + if (copy_to_user(_buffer, msg, n) != 0) { ret = -EFAULT; goto err_put_fd; @@ -317,19 +354,23 @@ static int cachefiles_ondemand_send_req(struct cachefiles_object *object, void *private) { struct cachefiles_cache *cache = object->volume->cache; - struct cachefiles_req *req; + struct cachefiles_req *req = NULL; XA_STATE(xas, &cache->reqs, 0); int ret;

if (!test_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags)) return 0;

- if (test_bit(CACHEFILES_DEAD, &cache->flags)) - return -EIO; + if (test_bit(CACHEFILES_DEAD, &cache->flags)) { + ret = -EIO; + goto out; + }

req = kzalloc(sizeof(*req) + data_len, GFP_KERNEL); - if (!req) - return -ENOMEM; + if (!req) { + ret = -ENOMEM; + goto out; + }

req->object = object; init_completion(&req->done); @@ -367,7 +408,7 @@ static int cachefiles_ondemand_send_req(struct cachefiles_object *object, /* coupled with the barrier in cachefiles_flush_reqs() */ smp_mb();

- if (opcode != CACHEFILES_OP_OPEN && + if (opcode == CACHEFILES_OP_CLOSE && !cachefiles_ondemand_object_is_open(object)) { WARN_ON_ONCE(object->ondemand->ondemand_id == 0); xas_unlock(&xas); @@ -392,7 +433,15 @@ 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); + return ret; out: + /* Reset the object to close state in error handling path. + * If error occurs after creating the anonymous fd, + * cachefiles_ondemand_fd_release() will set object to close. + */ + if (opcode == CACHEFILES_OP_OPEN) + cachefiles_ondemand_set_object_close(object); kfree(req); return ret; } @@ -439,7 +488,6 @@ static int cachefiles_ondemand_init_close_req(struct cachefiles_req *req, if (!cachefiles_ondemand_object_is_open(object)) return -ENOENT;

- req->msg.object_id = object->ondemand->ondemand_id; trace_cachefiles_ondemand_close(object, &req->msg); return 0; } @@ -455,16 +503,7 @@ static int cachefiles_ondemand_init_read_req(struct cachefiles_req *req, struct cachefiles_object *object = req->object; struct cachefiles_read *load = (void *)req->msg.data; struct cachefiles_read_ctx *read_ctx = private; - int object_id = object->ondemand->ondemand_id; - - /* Stop enqueuing requests when daemon has closed anon_fd. */ - if (!cachefiles_ondemand_object_is_open(object)) { - WARN_ON_ONCE(object_id == 0); - pr_info_once("READ: anonymous fd closed prematurely.\n"); - return -EIO; - }

- req->msg.object_id = object_id; load->off = read_ctx->off; load->len = read_ctx->len; trace_cachefiles_ondemand_read(object, &req->msg, load); @@ -513,6 +552,7 @@ int cachefiles_ondemand_init_obj_info(struct cachefiles_object *object, return -ENOMEM;

object->ondemand->object = object; + INIT_WORK(&object->ondemand->ondemand_work, ondemand_object_worker); return 0; }

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jia Zhu zhujia.zj@bytedance.com

[ 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.

Suggested-by: Gao Xiang hsiangkao@linux.alibaba.com Signed-off-by: Jia Zhu zhujia.zj@bytedance.com Signed-off-by: Xin Yin yinxin.x@bytedance.com Link: https://lore.kernel.org/r/20231120041422.75170-6-zhujia.zj@bytedance.com Reviewed-by: Jingbo Xu jefflexu@linux.alibaba.com Reviewed-by: David Howells dhowells@redhat.com Signed-off-by: Christian Brauner brauner@kernel.org Stable-dep-of: 4b4391e77a6b ("cachefiles: defer exposing anon_fd until after copy_to_user() succeeds") Signed-off-by: Sasha Levin sashal@kernel.org --- fs/cachefiles/daemon.c | 1 + fs/cachefiles/internal.h | 3 +++ fs/cachefiles/ondemand.c | 23 +++++++++++++++++++++++ 3 files changed, 27 insertions(+)

diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index 7d1f456e376dd..26b487e112596 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -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 } }; diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index 33fe418aca770..361356d0e866a 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -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);

diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c index 8118649d30727..6d8f7f01a73ac 100644 --- a/fs/cachefiles/ondemand.c +++ b/fs/cachefiles/ondemand.c @@ -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;

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Baokun Li libaokun1@huawei.com

[ 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.

Fixes: 0a7e54c1959c ("cachefiles: resend an open request if the read request's object is closed") Signed-off-by: Baokun Li libaokun1@huawei.com Link: https://lore.kernel.org/r/20240522114308.2402121-5-libaokun@huaweicloud.com Acked-by: Jeff Layton jlayton@kernel.org Reviewed-by: Jia Zhu zhujia.zj@bytedance.com Reviewed-by: Jingbo Xu jefflexu@linux.alibaba.com Signed-off-by: Christian Brauner brauner@kernel.org Stable-dep-of: 4b4391e77a6b ("cachefiles: defer exposing anon_fd until after copy_to_user() succeeds") Signed-off-by: Sasha Levin sashal@kernel.org --- fs/cachefiles/ondemand.c | 3 +++ include/trace/events/cachefiles.h | 6 +++++- 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c index f8d0a01795702..fd73811c7ce4f 100644 --- a/fs/cachefiles/ondemand.c +++ b/fs/cachefiles/ondemand.c @@ -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) { diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index e3213af847cdf..7d931db02b934 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -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 ") \

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Baokun Li libaokun1@huawei.com

[ 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.

Fixes: c8383054506c ("cachefiles: notify the user daemon when looking up cookie") Signed-off-by: Baokun Li libaokun1@huawei.com Link: https://lore.kernel.org/r/20240522114308.2402121-9-libaokun@huaweicloud.com Acked-by: Jeff Layton jlayton@kernel.org Signed-off-by: Christian Brauner brauner@kernel.org Stable-dep-of: 4b4391e77a6b ("cachefiles: defer exposing anon_fd until after copy_to_user() succeeds") Signed-off-by: Sasha Levin sashal@kernel.org --- fs/cachefiles/ondemand.c | 34 ++++++++++++++++++++++++++++------ 1 file changed, 28 insertions(+), 6 deletions(-)

diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c index 99b4bffad4a4f..773c3b407a33b 100644 --- a/fs/cachefiles/ondemand.c +++ b/fs/cachefiles/ondemand.c @@ -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;

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Baokun Li libaokun1@huawei.com

[ 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.

Fixes: c8383054506c ("cachefiles: notify the user daemon when looking up cookie") Signed-off-by: Baokun Li libaokun1@huawei.com Link: https://lore.kernel.org/r/20240522114308.2402121-12-libaokun@huaweicloud.com Acked-by: Jeff Layton jlayton@kernel.org Signed-off-by: Christian Brauner brauner@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/cachefiles/daemon.c | 2 +- fs/cachefiles/internal.h | 3 +++ 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index 26b487e112596..b9945e4f697be 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -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; diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index 28799c8e2c6f6..3eea52462fc87 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -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, ...) \

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Samuel Holland samuel.holland@sifive.com

[ 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.

Link: https://lore.kernel.org/linux-clk/ZkfYqj+OcAxd9O2t@shell.armlinux.org.uk/ [1] Fixes: 30b8e27e3b58 ("clk: sifive: add a driver for the SiFive FU540 PRCI IP block") Fixes: 8d532528ff6a ("clkdev: report over-sized strings when creating clkdev entries") Reported-by: Guenter Roeck linux@roeck-us.net Closes: https://lore.kernel.org/linux-clk/7eda7621-0dde-4153-89e4-172e4c095d01@roeck... Suggested-by: Russell King linux@armlinux.org.uk Signed-off-by: Samuel Holland samuel.holland@sifive.com Link: https://lore.kernel.org/r/20240528001432.1200403-1-samuel.holland@sifive.com Signed-off-by: Stephen Boyd sboyd@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/clk/sifive/sifive-prci.c | 8 -------- 1 file changed, 8 deletions(-)

diff --git a/drivers/clk/sifive/sifive-prci.c b/drivers/clk/sifive/sifive-prci.c index af81eb835bc23..b1be6a2d24aa9 100644 --- a/drivers/clk/sifive/sifive-prci.c +++ b/drivers/clk/sifive/sifive-prci.c @@ -4,7 +4,6 @@ * Copyright (C) 2020 Zong Li */

-#include <linux/clkdev.h> #include <linux/delay.h> #include <linux/io.h> #include <linux/of.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; }

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Chen Hanxiao chenhx.fnst@fujitsu.com

[ Upstream commit 33c94d7e3cb84f6d130678d6d59ba475a6c489cf ]

don't return 0 if snd_buf->len really greater than snd_buf->buflen

Signed-off-by: Chen Hanxiao chenhx.fnst@fujitsu.com Fixes: 0c77668ddb4e ("SUNRPC: Introduce trace points in rpc_auth_gss.ko") Reviewed-by: Benjamin Coddington bcodding@redhat.com Reviewed-by: Chuck Lever chuck.lever@oracle.com Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/sunrpc/auth_gss/auth_gss.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 1af71fbb0d805..00753bc5f1b14 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -1875,8 +1875,10 @@ 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)

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Masami Hiramatsu (Google) mhiramat@kernel.org

[ Upstream commit 0f42bdf59b4e428485aa922bef871bfa6cc505e0 ]

Commit eb50d0f250e9 ("selftests/ftrace: Choose target function for filter test from samples") choose the target function from samples, but sometimes this test failes randomly because the target function does not hit at the next time. So retry getting samples up to 10 times.

Fixes: eb50d0f250e9 ("selftests/ftrace: Choose target function for filter test from samples") Signed-off-by: Masami Hiramatsu (Google) mhiramat@kernel.org Signed-off-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- .../test.d/filter/event-filter-function.tc | 20 ++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc index 3f74c09c56b62..118247b8dd84d 100644 --- a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc +++ b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc @@ -10,7 +10,6 @@ fail() { #msg }

sample_events() { - echo > trace echo 1 > events/kmem/kmem_cache_free/enable echo 1 > tracing_on ls > /dev/null @@ -22,6 +21,7 @@ echo 0 > tracing_on echo 0 > events/enable

echo "Get the most frequently calling function" +echo > trace sample_events

target_func=`cat trace | grep -o 'call_site=([^+]*)' | sed 's/call_site=//' | sort | uniq -c | sort | tail -n 1 | sed 's/^[ 0-9]*//'` @@ -32,7 +32,16 @@ echo > trace

echo "Test event filter function name" echo "call_site.function == $target_func" > events/kmem/kmem_cache_free/filter + +sample_events +max_retry=10 +while [ `grep kmem_cache_free trace| wc -l` -eq 0 ]; do sample_events +max_retry=$((max_retry - 1)) +if [ $max_retry -eq 0 ]; then + exit_fail +fi +done

hitcnt=`grep kmem_cache_free trace| grep $target_func | wc -l` misscnt=`grep kmem_cache_free trace| grep -v $target_func | wc -l` @@ -49,7 +58,16 @@ address=`grep " ${target_func}$" /proc/kallsyms | cut -d' ' -f1`

echo "Test event filter function address" echo "call_site.function == 0x$address" > events/kmem/kmem_cache_free/filter +echo > trace +sample_events +max_retry=10 +while [ `grep kmem_cache_free trace| wc -l` -eq 0 ]; do sample_events +max_retry=$((max_retry - 1)) +if [ $max_retry -eq 0 ]; then + exit_fail +fi +done

hitcnt=`grep kmem_cache_free trace| grep $target_func | wc -l` misscnt=`grep kmem_cache_free trace| grep -v $target_func | wc -l`

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Chen Ni nichen@iscas.ac.cn

[ Upstream commit 629f2b4e05225e53125aaf7ff0b87d5d53897128 ]

Add check for the return value of of_drm_get_panel_orientation() and return the error if it fails in order to catch the error.

Fixes: b27c0f6d208d ("drm/panel: sitronix-st7789v: add panel orientation support") Signed-off-by: Chen Ni nichen@iscas.ac.cn Reviewed-by: Michael Riesch michael.riesch@wolfvision.net Acked-by: Jessica Zhang quic_jesszhan@quicinc.com Link: https://lore.kernel.org/r/20240528030832.2529471-1-nichen@iscas.ac.cn Signed-off-by: Neil Armstrong neil.armstrong@linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20240528030832.2529471-1-niche... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/panel/panel-sitronix-st7789v.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c index e8f385b9c6182..28bfc48a91272 100644 --- a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c +++ b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c @@ -643,7 +643,9 @@ static int st7789v_probe(struct spi_device *spi) if (ret) return dev_err_probe(dev, ret, "Failed to get backlight\n");

- of_drm_get_panel_orientation(spi->dev.of_node, &ctx->orientation); + ret = of_drm_get_panel_orientation(spi->dev.of_node, &ctx->orientation); + if (ret) + return dev_err_probe(&spi->dev, ret, "Failed to get orientation\n");

drm_panel_add(&ctx->panel);

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Gregor Herburger gregor.herburger@tq-group.com

[ Upstream commit 8c219e52ca4d9a67cd6a7074e91bf29b55edc075 ]

Fix description for GPIO_TQMX86 from QTMX86 to TQMx86.

Fixes: b868db94a6a7 ("gpio: tqmx86: Add GPIO from for this IO controller") Signed-off-by: Gregor Herburger gregor.herburger@tq-group.com Signed-off-by: Matthias Schiffer matthias.schiffer@ew.tq-group.com Reviewed-by: Andrew Lunn andrew@lunn.ch Link: https://lore.kernel.org/r/e0e38c9944ad6d281d9a662a45d289b88edc808e.171706399... Signed-off-by: Bartosz Golaszewski bartosz.golaszewski@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpio/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index d56b835359d3b..ebd4e113dc265 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -1507,7 +1507,7 @@ 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

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Matthias Schiffer matthias.schiffer@ew.tq-group.com

[ 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.

Fixes: b868db94a6a7 ("gpio: tqmx86: Add GPIO from for this IO controller") Signed-off-by: Matthias Schiffer matthias.schiffer@ew.tq-group.com Link: https://lore.kernel.org/r/6aa4f207f77cb58ef64ffb947e91949b0f753ccd.171706399... Signed-off-by: Bartosz Golaszewski bartosz.golaszewski@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpio/gpio-tqmx86.c | 48 ++++++++++++++++++++++---------------- 1 file changed, 28 insertions(+), 20 deletions(-)

diff --git a/drivers/gpio/gpio-tqmx86.c b/drivers/gpio/gpio-tqmx86.c index b7e2dbbdc4ebe..7e428c872a257 100644 --- a/drivers/gpio/gpio-tqmx86.c +++ b/drivers/gpio/gpio-tqmx86.c @@ -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;

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nikita Zhandarovich n.zhandarovich@fintech.ru

[ 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 ...

Fixes: 95d1c8951e5b ("HID: simplify implement() a bit") Reported-by: syzbot+5186630949e3c55f0799@syzkaller.appspotmail.com Suggested-by: Alan Stern stern@rowland.harvard.edu Signed-off-by: Nikita Zhandarovich n.zhandarovich@fintech.ru Signed-off-by: Jiri Kosina jkosina@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hid/hid-core.c | 1 - 1 file changed, 1 deletion(-)

diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index e0181218ad857..85ddeb13a3fae 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1448,7 +1448,6 @@ 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; } }

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Lu Baolu baolu.lu@linux.intel.com

[ Upstream commit 89e8a2366e3bce584b6c01549d5019c5cda1205e ]

iommu_sva_bind_device() should return either a sva bond handle or an ERR_PTR value in error cases. Existing drivers (idxd and uacce) only check the return value with IS_ERR(). This could potentially lead to a kernel NULL pointer dereference issue if the function returns NULL instead of an error pointer.

In reality, this doesn't cause any problems because iommu_sva_bind_device() only returns NULL when the kernel is not configured with CONFIG_IOMMU_SVA. In this case, iommu_dev_enable_feature(dev, IOMMU_DEV_FEAT_SVA) will return an error, and the device drivers won't call iommu_sva_bind_device() at all.

Fixes: 26b25a2b98e4 ("iommu: Bind process address spaces to devices") Signed-off-by: Lu Baolu baolu.lu@linux.intel.com Reviewed-by: Jean-Philippe Brucker jean-philippe@linaro.org Reviewed-by: Kevin Tian kevin.tian@intel.com Reviewed-by: Vasant Hegde vasant.hegde@amd.com Link: https://lore.kernel.org/r/20240528042528.71396-1-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel jroedel@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/iommu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 0225cf7445de2..b6ef263e85c06 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -1199,7 +1199,7 @@ u32 iommu_sva_get_pasid(struct iommu_sva *handle); static inline struct iommu_sva * iommu_sva_bind_device(struct device *dev, struct mm_struct *mm) { - return NULL; + return ERR_PTR(-ENODEV); }

static inline void iommu_sva_unbind_device(struct iommu_sva *handle)

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Su Hui suhui@nfschina.com

[ Upstream commit 91215f70ea8541e9011c0b48f8b59b9e0ce6953b ]

Clang static checker (scan-build) warning: o_uring/io-wq.c:line 1051, column 3 The expression is an uninitialized value. The computed value will also be garbage.

'match.nr_pending' is used in io_acct_cancel_pending_work(), but it is not fully initialized. Change the order of assignment for 'match' to fix this problem.

Fixes: 42abc95f05bf ("io-wq: decouple work_list protection from the big wqe->lock") Signed-off-by: Su Hui suhui@nfschina.com Link: https://lore.kernel.org/r/20240604121242.2661244-1-suhui@nfschina.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- io_uring/io-wq.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index 4a07742349048..8a99aabcac2c3 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -929,7 +929,11 @@ void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work) { struct io_wq_acct *acct = io_work_get_acct(wq, work); unsigned long work_flags = work->flags; - struct io_cb_cancel_data match; + struct io_cb_cancel_data match = { + .fn = io_wq_work_match_item, + .data = work, + .cancel_all = false, + }; bool do_create;

/* @@ -967,10 +971,6 @@ void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work) raw_spin_unlock(&wq->lock);

/* fatal condition, failed to create the first worker */ - match.fn = io_wq_work_match_item, - match.data = work, - match.cancel_all = false, - io_acct_cancel_pending_work(wq, acct, &match); } }

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Martin Krastev martin.krastev@broadcom.com

[ Upstream commit 935f795045a6f9b13d28d46ebdad04bfea8750dd ]

Implement drm_connector_helper_funcs.mode_valid and .get_modes, replacing custom drm_connector_funcs.fill_modes code with drm_helper_probe_single_connector_modes; for STDU, LDU & SOU display units.

Signed-off-by: Martin Krastev martin.krastev@broadcom.com Reviewed-by: Zack Rusin zack.rusin@broadcom.com Signed-off-by: Zack Rusin zack.rusin@broadcom.com Link: https://patchwork.freedesktop.org/patch/msgid/20240126200804.732454-2-zack.r... Stable-dep-of: 426826933109 ("drm/vmwgfx: Filter modes which exceed graphics memory") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/vmwgfx/vmwgfx_kms.c | 272 +++++++++------------------ drivers/gpu/drm/vmwgfx/vmwgfx_kms.h | 6 +- drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c | 5 +- drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c | 5 +- drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c | 4 +- 5 files changed, 101 insertions(+), 191 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index a884072851322..59de170a31853 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -35,6 +35,7 @@ #include <drm/drm_fourcc.h> #include <drm/drm_rect.h> #include <drm/drm_sysfs.h> +#include <drm/drm_edid.h>

void vmw_du_cleanup(struct vmw_display_unit *du) { @@ -2279,107 +2280,6 @@ vmw_du_connector_detect(struct drm_connector *connector, bool force) connector_status_connected : connector_status_disconnected); }

-static struct drm_display_mode vmw_kms_connector_builtin[] = { - /* 640x480@60Hz */ - { DRM_MODE("640x480", DRM_MODE_TYPE_DRIVER, 25175, 640, 656, - 752, 800, 0, 480, 489, 492, 525, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC) }, - /* 800x600@60Hz */ - { DRM_MODE("800x600", DRM_MODE_TYPE_DRIVER, 40000, 800, 840, - 968, 1056, 0, 600, 601, 605, 628, 0, - DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1024x768@60Hz */ - { DRM_MODE("1024x768", DRM_MODE_TYPE_DRIVER, 65000, 1024, 1048, - 1184, 1344, 0, 768, 771, 777, 806, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC) }, - /* 1152x864@75Hz */ - { DRM_MODE("1152x864", DRM_MODE_TYPE_DRIVER, 108000, 1152, 1216, - 1344, 1600, 0, 864, 865, 868, 900, 0, - DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1280x720@60Hz */ - { DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 74500, 1280, 1344, - 1472, 1664, 0, 720, 723, 728, 748, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1280x768@60Hz */ - { DRM_MODE("1280x768", DRM_MODE_TYPE_DRIVER, 79500, 1280, 1344, - 1472, 1664, 0, 768, 771, 778, 798, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1280x800@60Hz */ - { DRM_MODE("1280x800", DRM_MODE_TYPE_DRIVER, 83500, 1280, 1352, - 1480, 1680, 0, 800, 803, 809, 831, 0, - DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_NVSYNC) }, - /* 1280x960@60Hz */ - { DRM_MODE("1280x960", DRM_MODE_TYPE_DRIVER, 108000, 1280, 1376, - 1488, 1800, 0, 960, 961, 964, 1000, 0, - DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1280x1024@60Hz */ - { DRM_MODE("1280x1024", DRM_MODE_TYPE_DRIVER, 108000, 1280, 1328, - 1440, 1688, 0, 1024, 1025, 1028, 1066, 0, - DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1360x768@60Hz */ - { DRM_MODE("1360x768", DRM_MODE_TYPE_DRIVER, 85500, 1360, 1424, - 1536, 1792, 0, 768, 771, 777, 795, 0, - DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1440x1050@60Hz */ - { DRM_MODE("1400x1050", DRM_MODE_TYPE_DRIVER, 121750, 1400, 1488, - 1632, 1864, 0, 1050, 1053, 1057, 1089, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1440x900@60Hz */ - { DRM_MODE("1440x900", DRM_MODE_TYPE_DRIVER, 106500, 1440, 1520, - 1672, 1904, 0, 900, 903, 909, 934, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1600x1200@60Hz */ - { DRM_MODE("1600x1200", DRM_MODE_TYPE_DRIVER, 162000, 1600, 1664, - 1856, 2160, 0, 1200, 1201, 1204, 1250, 0, - DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1680x1050@60Hz */ - { DRM_MODE("1680x1050", DRM_MODE_TYPE_DRIVER, 146250, 1680, 1784, - 1960, 2240, 0, 1050, 1053, 1059, 1089, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1792x1344@60Hz */ - { DRM_MODE("1792x1344", DRM_MODE_TYPE_DRIVER, 204750, 1792, 1920, - 2120, 2448, 0, 1344, 1345, 1348, 1394, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1853x1392@60Hz */ - { DRM_MODE("1856x1392", DRM_MODE_TYPE_DRIVER, 218250, 1856, 1952, - 2176, 2528, 0, 1392, 1393, 1396, 1439, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1920x1080@60Hz */ - { DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 173000, 1920, 2048, - 2248, 2576, 0, 1080, 1083, 1088, 1120, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1920x1200@60Hz */ - { DRM_MODE("1920x1200", DRM_MODE_TYPE_DRIVER, 193250, 1920, 2056, - 2256, 2592, 0, 1200, 1203, 1209, 1245, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 1920x1440@60Hz */ - { DRM_MODE("1920x1440", DRM_MODE_TYPE_DRIVER, 234000, 1920, 2048, - 2256, 2600, 0, 1440, 1441, 1444, 1500, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 2560x1440@60Hz */ - { DRM_MODE("2560x1440", DRM_MODE_TYPE_DRIVER, 241500, 2560, 2608, - 2640, 2720, 0, 1440, 1443, 1448, 1481, 0, - DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_NVSYNC) }, - /* 2560x1600@60Hz */ - { DRM_MODE("2560x1600", DRM_MODE_TYPE_DRIVER, 348500, 2560, 2752, - 3032, 3504, 0, 1600, 1603, 1609, 1658, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) }, - /* 2880x1800@60Hz */ - { DRM_MODE("2880x1800", DRM_MODE_TYPE_DRIVER, 337500, 2880, 2928, - 2960, 3040, 0, 1800, 1803, 1809, 1852, 0, - DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_NVSYNC) }, - /* 3840x2160@60Hz */ - { DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 533000, 3840, 3888, - 3920, 4000, 0, 2160, 2163, 2168, 2222, 0, - DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_NVSYNC) }, - /* 3840x2400@60Hz */ - { DRM_MODE("3840x2400", DRM_MODE_TYPE_DRIVER, 592250, 3840, 3888, - 3920, 4000, 0, 2400, 2403, 2409, 2469, 0, - DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_NVSYNC) }, - /* Terminate */ - { DRM_MODE("", 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) }, -}; - /** * vmw_guess_mode_timing - Provide fake timings for a * 60Hz vrefresh mode. @@ -2401,88 +2301,6 @@ void vmw_guess_mode_timing(struct drm_display_mode *mode) }

-int vmw_du_connector_fill_modes(struct drm_connector *connector, - uint32_t max_width, uint32_t max_height) -{ - struct vmw_display_unit *du = vmw_connector_to_du(connector); - struct drm_device *dev = connector->dev; - struct vmw_private *dev_priv = vmw_priv(dev); - struct drm_display_mode *mode = NULL; - struct drm_display_mode *bmode; - struct drm_display_mode prefmode = { DRM_MODE("preferred", - DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) - }; - int i; - u32 assumed_bpp = 4; - - if (dev_priv->assume_16bpp) - assumed_bpp = 2; - - max_width = min(max_width, dev_priv->texture_max_width); - max_height = min(max_height, dev_priv->texture_max_height); - - /* - * For STDU extra limit for a mode on SVGA_REG_SCREENTARGET_MAX_WIDTH/ - * HEIGHT registers. - */ - if (dev_priv->active_display_unit == vmw_du_screen_target) { - max_width = min(max_width, dev_priv->stdu_max_width); - max_height = min(max_height, dev_priv->stdu_max_height); - } - - /* Add preferred mode */ - mode = drm_mode_duplicate(dev, &prefmode); - if (!mode) - return 0; - mode->hdisplay = du->pref_width; - mode->vdisplay = du->pref_height; - vmw_guess_mode_timing(mode); - drm_mode_set_name(mode); - - if (vmw_kms_validate_mode_vram(dev_priv, - mode->hdisplay * assumed_bpp, - mode->vdisplay)) { - drm_mode_probed_add(connector, mode); - } else { - drm_mode_destroy(dev, mode); - mode = NULL; - } - - if (du->pref_mode) { - list_del_init(&du->pref_mode->head); - drm_mode_destroy(dev, du->pref_mode); - } - - /* mode might be null here, this is intended */ - du->pref_mode = mode; - - for (i = 0; vmw_kms_connector_builtin[i].type != 0; i++) { - bmode = &vmw_kms_connector_builtin[i]; - if (bmode->hdisplay > max_width || - bmode->vdisplay > max_height) - continue; - - if (!vmw_kms_validate_mode_vram(dev_priv, - bmode->hdisplay * assumed_bpp, - bmode->vdisplay)) - continue; - - mode = drm_mode_duplicate(dev, bmode); - if (!mode) - return 0; - - drm_mode_probed_add(connector, mode); - } - - drm_connector_list_update(connector); - /* Move the prefered mode first, help apps pick the right mode. */ - drm_mode_sort(&connector->modes); - - return 1; -} - /** * vmw_kms_update_layout_ioctl - Handler for DRM_VMW_UPDATE_LAYOUT ioctl * @dev: drm device for the ioctl @@ -3023,3 +2841,91 @@ int vmw_du_helper_plane_update(struct vmw_du_update_plane *update) vmw_validation_unref_lists(&val_ctx); return ret; } + +/** + * vmw_connector_mode_valid - implements drm_connector_helper_funcs.mode_valid callback + * + * @connector: the drm connector, part of a DU container + * @mode: drm mode to check + * + * Returns MODE_OK on success, or a drm_mode_status error code. + */ +enum drm_mode_status vmw_connector_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) +{ + struct drm_device *dev = connector->dev; + struct vmw_private *dev_priv = vmw_priv(dev); + u32 max_width = dev_priv->texture_max_width; + u32 max_height = dev_priv->texture_max_height; + u32 assumed_cpp = 4; + + if (dev_priv->assume_16bpp) + assumed_cpp = 2; + + if (dev_priv->active_display_unit == vmw_du_screen_target) { + max_width = min(dev_priv->stdu_max_width, max_width); + max_height = min(dev_priv->stdu_max_height, max_height); + } + + if (max_width < mode->hdisplay) + return MODE_BAD_HVALUE; + + if (max_height < mode->vdisplay) + return MODE_BAD_VVALUE; + + if (!vmw_kms_validate_mode_vram(dev_priv, + mode->hdisplay * assumed_cpp, + mode->vdisplay)) + return MODE_MEM; + + return MODE_OK; +} + +/** + * vmw_connector_get_modes - implements drm_connector_helper_funcs.get_modes callback + * + * @connector: the drm connector, part of a DU container + * + * Returns the number of added modes. + */ +int vmw_connector_get_modes(struct drm_connector *connector) +{ + struct vmw_display_unit *du = vmw_connector_to_du(connector); + struct drm_device *dev = connector->dev; + struct vmw_private *dev_priv = vmw_priv(dev); + struct drm_display_mode *mode = NULL; + struct drm_display_mode prefmode = { DRM_MODE("preferred", + DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC) + }; + u32 max_width; + u32 max_height; + u32 num_modes; + + /* Add preferred mode */ + mode = drm_mode_duplicate(dev, &prefmode); + if (!mode) + return 0; + + mode->hdisplay = du->pref_width; + mode->vdisplay = du->pref_height; + vmw_guess_mode_timing(mode); + drm_mode_set_name(mode); + + drm_mode_probed_add(connector, mode); + drm_dbg_kms(dev, "preferred mode " DRM_MODE_FMT "\n", DRM_MODE_ARG(mode)); + + /* Probe connector for all modes not exceeding our geom limits */ + max_width = dev_priv->texture_max_width; + max_height = dev_priv->texture_max_height; + + if (dev_priv->active_display_unit == vmw_du_screen_target) { + max_width = min(dev_priv->stdu_max_width, max_width); + max_height = min(dev_priv->stdu_max_height, max_height); + } + + num_modes = 1 + drm_add_modes_noedid(connector, max_width, max_height); + + return num_modes; +} diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h index 9fda4f4ec7a97..19a843da87b78 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h @@ -378,7 +378,6 @@ struct vmw_display_unit { unsigned pref_width; unsigned pref_height; bool pref_active; - struct drm_display_mode *pref_mode;

/* * Gui positioning @@ -428,8 +427,6 @@ void vmw_du_connector_save(struct drm_connector *connector); void vmw_du_connector_restore(struct drm_connector *connector); enum drm_connector_status vmw_du_connector_detect(struct drm_connector *connector, bool force); -int vmw_du_connector_fill_modes(struct drm_connector *connector, - uint32_t max_width, uint32_t max_height); int vmw_kms_helper_dirty(struct vmw_private *dev_priv, struct vmw_framebuffer *framebuffer, const struct drm_clip_rect *clips, @@ -438,6 +435,9 @@ int vmw_kms_helper_dirty(struct vmw_private *dev_priv, int num_clips, int increment, struct vmw_kms_dirty *dirty); +enum drm_mode_status vmw_connector_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode); +int vmw_connector_get_modes(struct drm_connector *connector);

void vmw_kms_helper_validation_finish(struct vmw_private *dev_priv, struct drm_file *file_priv, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c index a82fa97003705..c4db4aecca6c3 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c @@ -304,7 +304,7 @@ static void vmw_ldu_connector_destroy(struct drm_connector *connector) static const struct drm_connector_funcs vmw_legacy_connector_funcs = { .dpms = vmw_du_connector_dpms, .detect = vmw_du_connector_detect, - .fill_modes = vmw_du_connector_fill_modes, + .fill_modes = drm_helper_probe_single_connector_modes, .destroy = vmw_ldu_connector_destroy, .reset = vmw_du_connector_reset, .atomic_duplicate_state = vmw_du_connector_duplicate_state, @@ -313,6 +313,8 @@ static const struct drm_connector_funcs vmw_legacy_connector_funcs = {

static const struct drm_connector_helper_funcs vmw_ldu_connector_helper_funcs = { + .get_modes = vmw_connector_get_modes, + .mode_valid = vmw_connector_mode_valid };

static int vmw_kms_ldu_do_bo_dirty(struct vmw_private *dev_priv, @@ -449,7 +451,6 @@ static int vmw_ldu_init(struct vmw_private *dev_priv, unsigned unit) ldu->base.pref_active = (unit == 0); ldu->base.pref_width = dev_priv->initial_width; ldu->base.pref_height = dev_priv->initial_height; - ldu->base.pref_mode = NULL;

/* * Remove this after enabling atomic because property values can diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c index 556a403b7eb56..30c3ad27b6629 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c @@ -347,7 +347,7 @@ static void vmw_sou_connector_destroy(struct drm_connector *connector) static const struct drm_connector_funcs vmw_sou_connector_funcs = { .dpms = vmw_du_connector_dpms, .detect = vmw_du_connector_detect, - .fill_modes = vmw_du_connector_fill_modes, + .fill_modes = drm_helper_probe_single_connector_modes, .destroy = vmw_sou_connector_destroy, .reset = vmw_du_connector_reset, .atomic_duplicate_state = vmw_du_connector_duplicate_state, @@ -357,6 +357,8 @@ static const struct drm_connector_funcs vmw_sou_connector_funcs = {

static const struct drm_connector_helper_funcs vmw_sou_connector_helper_funcs = { + .get_modes = vmw_connector_get_modes, + .mode_valid = vmw_connector_mode_valid };

@@ -826,7 +828,6 @@ static int vmw_sou_init(struct vmw_private *dev_priv, unsigned unit) sou->base.pref_active = (unit == 0); sou->base.pref_width = dev_priv->initial_width; sou->base.pref_height = dev_priv->initial_height; - sou->base.pref_mode = NULL;

/* * Remove this after enabling atomic because property values can diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c index ba0c0e12cfe9d..12d623ee59c25 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c @@ -830,7 +830,7 @@ static void vmw_stdu_connector_destroy(struct drm_connector *connector) static const struct drm_connector_funcs vmw_stdu_connector_funcs = { .dpms = vmw_du_connector_dpms, .detect = vmw_du_connector_detect, - .fill_modes = vmw_du_connector_fill_modes, + .fill_modes = drm_helper_probe_single_connector_modes, .destroy = vmw_stdu_connector_destroy, .reset = vmw_du_connector_reset, .atomic_duplicate_state = vmw_du_connector_duplicate_state, @@ -840,6 +840,8 @@ static const struct drm_connector_funcs vmw_stdu_connector_funcs = {

static const struct drm_connector_helper_funcs vmw_stdu_connector_helper_funcs = { + .get_modes = vmw_connector_get_modes, + .mode_valid = vmw_connector_mode_valid };

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ian Forbes ian.forbes@broadcom.com

[ Upstream commit fb5e19d2dd03eb995ccd468d599b2337f7f66555 ]

This limit became a hard cap starting with the change referenced below. Surface creation on the device will fail if the requested size is larger than this limit so altering the value arbitrarily will expose modes that are too large for the device's hard limits.

Fixes: 7ebb47c9f9ab ("drm/vmwgfx: Read new register for GB memory when available")

Signed-off-by: Ian Forbes ian.forbes@broadcom.com Signed-off-by: Zack Rusin zack.rusin@broadcom.com Link: https://patchwork.freedesktop.org/patch/msgid/20240521184720.767-3-ian.forbe... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 7 ------- 1 file changed, 7 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 58fb40c93100a..bea576434e475 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -956,13 +956,6 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id) vmw_read(dev_priv, SVGA_REG_SUGGESTED_GBOBJECT_MEM_SIZE_KB);

- /* - * Workaround for low memory 2D VMs to compensate for the - * allocation taken by fbdev - */ - if (!(dev_priv->capabilities & SVGA_CAP_3D)) - mem_size *= 3; - dev_priv->max_mob_pages = mem_size * 1024 / PAGE_SIZE; dev_priv->max_primary_mem = vmw_read(dev_priv, SVGA_REG_MAX_PRIMARY_MEM);

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ian Forbes ian.forbes@broadcom.com

[ Upstream commit 5703fc058efdafcdd6b70776ee562478f0753acb ]

These pointers are frequently the same and memcmp does not compare the pointers before comparing their contents so this was wasting cycles comparing 16 KiB of memory which will always be equal.

Fixes: bb6780aa5a1d ("drm/vmwgfx: Diff cursors when using cmds") Signed-off-by: Ian Forbes ian.forbes@broadcom.com Signed-off-by: Zack Rusin zack.rusin@broadcom.com Link: https://patchwork.freedesktop.org/patch/msgid/20240328190716.27367-1-ian.for... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/vmwgfx/vmwgfx_kms.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 93e2a27daed0c..08f2470edab27 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -216,7 +216,7 @@ static bool vmw_du_cursor_plane_has_changed(struct vmw_plane_state *old_vps, new_image = vmw_du_cursor_plane_acquire_image(new_vps);

changed = false; - if (old_image && new_image) + if (old_image && new_image && old_image != new_image) changed = memcmp(old_image, new_image, size) != 0;

return changed;

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Masahiro Yamada masahiroy@kernel.org

[ Upstream commit 9185afeac2a3dcce8300a5684291a43c2838cfd6 ]

Building with W=1 incorrectly emits the following warning:

WARNING: modpost: missing MODULE_DESCRIPTION() in vmlinux.o

This check should apply only to modules.

Fixes: 1fffe7a34c89 ("script: modpost: emit a warning when the description is missing") Signed-off-by: Masahiro Yamada masahiroy@kernel.org Reviewed-by: Vincenzo Palazzo vincenzopalazzodev@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- scripts/mod/modpost.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 269bd79bcd9ad..828d5cc367169 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -1684,10 +1684,11 @@ static void read_symbols(const char *modname) namespace = get_next_modinfo(&info, "import_ns", namespace); } + + if (extra_warn && !get_modinfo(&info, "description")) + warn("missing MODULE_DESCRIPTION() in %s\n", modname); }

- if (extra_warn && !get_modinfo(&info, "description")) - warn("missing MODULE_DESCRIPTION() in %s\n", modname); for (sym = info.symtab_start; sym < info.symtab_stop; sym++) { symname = remove_dot(info.strtab + sym->st_name);

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Yonglong Liu liuyonglong@huawei.com

[ Upstream commit 12cda920212a49fa22d9e8b9492ac4ea013310a4 ]

When link status change, the nic driver need to notify the roce driver to handle this event, but at this time, the roce driver may uninit, then cause kernel crash.

To fix the problem, when link status change, need to check whether the roce registered, and when uninit, need to wait link update finish.

Fixes: 45e92b7e4e27 ("net: hns3: add calling roce callback function when link status change") Signed-off-by: Yonglong Liu liuyonglong@huawei.com Signed-off-by: Jijie Shao shaojijie@huawei.com Reviewed-by: Simon Horman horms@kernel.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- .../hisilicon/hns3/hns3pf/hclge_main.c | 21 ++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 14713454e0d82..c8059d96f64be 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -3031,9 +3031,7 @@ static void hclge_push_link_status(struct hclge_dev *hdev)

static void hclge_update_link_status(struct hclge_dev *hdev) { - struct hnae3_handle *rhandle = &hdev->vport[0].roce; struct hnae3_handle *handle = &hdev->vport[0].nic; - struct hnae3_client *rclient = hdev->roce_client; struct hnae3_client *client = hdev->nic_client; int state; int ret; @@ -3057,8 +3055,15 @@ static void hclge_update_link_status(struct hclge_dev *hdev)

client->ops->link_status_change(handle, state); hclge_config_mac_tnl_int(hdev, state); - if (rclient && rclient->ops->link_status_change) - rclient->ops->link_status_change(rhandle, state); + + if (test_bit(HCLGE_STATE_ROCE_REGISTERED, &hdev->state)) { + struct hnae3_handle *rhandle = &hdev->vport[0].roce; + struct hnae3_client *rclient = hdev->roce_client; + + if (rclient && rclient->ops->link_status_change) + rclient->ops->link_status_change(rhandle, + state); + }

hclge_push_link_status(hdev); } @@ -11233,6 +11238,12 @@ static int hclge_init_client_instance(struct hnae3_client *client, return ret; }

+static bool hclge_uninit_need_wait(struct hclge_dev *hdev) +{ + return test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) || + test_bit(HCLGE_STATE_LINK_UPDATING, &hdev->state); +} + static void hclge_uninit_client_instance(struct hnae3_client *client, struct hnae3_ae_dev *ae_dev) { @@ -11241,7 +11252,7 @@ static void hclge_uninit_client_instance(struct hnae3_client *client,

if (hdev->roce_client) { clear_bit(HCLGE_STATE_ROCE_REGISTERED, &hdev->state); - while (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) + while (hclge_uninit_need_wait(hdev)) msleep(HCLGE_WAIT_RESET_DONE);

hdev->roce_client->ops->uninit_instance(&vport->roce, 0);

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Aleksandr Mishin amishin@t-argos.ru

[ Upstream commit c44711b78608c98a3e6b49ce91678cd0917d5349 ]

In lio_vf_rep_copy_packet() pg_info->page is compared to a NULL value, but then it is unconditionally passed to skb_add_rx_frag() which looks strange and could lead to null pointer dereference.

lio_vf_rep_copy_packet() call trace looks like: octeon_droq_process_packets octeon_droq_fast_process_packets octeon_droq_dispatch_pkt octeon_create_recv_info ...search in the dispatch_list... ->disp_fn(rdisp->rinfo, ...) lio_vf_rep_pkt_recv(struct octeon_recv_info *recv_info, ...) In this path there is no code which sets pg_info->page to NULL. So this check looks unneeded and doesn't solve potential problem. But I guess the author had reason to add a check and I have no such card and can't do real test. In addition, the code in the function liquidio_push_packet() in liquidio/lio_core.c does exactly the same.

Based on this, I consider the most acceptable compromise solution to adjust this issue by moving skb_add_rx_frag() into conditional scope.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Fixes: 1f233f327913 ("liquidio: switchdev support for LiquidIO NIC") Signed-off-by: Aleksandr Mishin amishin@t-argos.ru Reviewed-by: Simon Horman horms@kernel.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c index 600de587d7a98..e70b9ccca380e 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c @@ -272,13 +272,12 @@ lio_vf_rep_copy_packet(struct octeon_device *oct, pg_info->page_offset; memcpy(skb->data, va, MIN_SKB_SIZE); skb_put(skb, MIN_SKB_SIZE); + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, + pg_info->page, + pg_info->page_offset + MIN_SKB_SIZE, + len - MIN_SKB_SIZE, + LIO_RXBUFFER_SZ); } - - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, - pg_info->page, - pg_info->page_offset + MIN_SKB_SIZE, - len - MIN_SKB_SIZE, - LIO_RXBUFFER_SZ); } else { struct octeon_skb_page_info *pg_info = ((struct octeon_skb_page_info *)(skb->cb));

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Amjad Ouled-Ameur amjad.ouled-ameur@arm.com

[ Upstream commit b880018edd3a577e50366338194dee9b899947e0 ]

komeda_pipeline_get_state() may return an error-valued pointer, thus check the pointer for negative or null value before dereferencing.

Fixes: 502932a03fce ("drm/komeda: Add the initial scaler support for CORE") Signed-off-by: Amjad Ouled-Ameur amjad.ouled-ameur@arm.com Signed-off-by: Maxime Ripard mripard@kernel.org Link: https://patchwork.freedesktop.org/patch/msgid/20240610102056.40406-1-amjad.o... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c index f3e744172673c..f4e76b46ca327 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c @@ -259,7 +259,7 @@ komeda_component_get_avail_scaler(struct komeda_component *c, u32 avail_scalers;

pipe_st = komeda_pipeline_get_state(c->pipeline, state); - if (!pipe_st) + if (IS_ERR_OR_NULL(pipe_st)) return NULL;

avail_scalers = (pipe_st->active_comps & KOMEDA_PIPELINE_SCALERS) ^