From: Michael Grzeschik m.grzeschik@pengutronix.de

[ Upstream commit e192cc7b52399d1b073f88cd3ba128b74d3a57f1 ]

This patch adds the extra function __dwc3_stop_active_transfer to consolidate the same codepath.

Signed-off-by: Michael Grzeschik m.grzeschik@pengutronix.de Link: https://lore.kernel.org/r/20220306211251.2281335-3-m.grzeschik@pengutronix.d... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Stable-dep-of: d8a2bb4eb758 ("usb: dwc3: gadget: Add 1ms delay after end transfer command without IOC") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/usb/dwc3/gadget.c | 69 +++++++++++++++++++++------------------ 1 file changed, 37 insertions(+), 32 deletions(-)

diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index a0100d26de8e1..1689c09b937ae 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1639,6 +1639,40 @@ static int __dwc3_gadget_get_frame(struct dwc3 *dwc) return DWC3_DSTS_SOFFN(reg); }

+/** + * __dwc3_stop_active_transfer - stop the current active transfer + * @dep: isoc endpoint + * @force: set forcerm bit in the command + * @interrupt: command complete interrupt after End Transfer command + * + * When setting force, the ForceRM bit will be set. In that case + * the controller won't update the TRB progress on command + * completion. It also won't clear the HWO bit in the TRB. + * The command will also not complete immediately in that case. + */ +static int __dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, bool interrupt) +{ + struct dwc3_gadget_ep_cmd_params params; + u32 cmd; + int ret; + + cmd = DWC3_DEPCMD_ENDTRANSFER; + cmd |= force ? DWC3_DEPCMD_HIPRI_FORCERM : 0; + cmd |= interrupt ? DWC3_DEPCMD_CMDIOC : 0; + cmd |= DWC3_DEPCMD_PARAM(dep->resource_index); + memset(&params, 0, sizeof(params)); + ret = dwc3_send_gadget_ep_cmd(dep, cmd, &params); + WARN_ON_ONCE(ret); + dep->resource_index = 0; + + if (!interrupt) + dep->flags &= ~DWC3_EP_TRANSFER_STARTED; + else if (!ret) + dep->flags |= DWC3_EP_END_TRANSFER_PENDING; + + return ret; +} + /** * dwc3_gadget_start_isoc_quirk - workaround invalid frame number * @dep: isoc endpoint @@ -1808,21 +1842,8 @@ static int __dwc3_gadget_start_isoc(struct dwc3_ep *dep) * status, issue END_TRANSFER command and retry on the next XferNotReady * event. */ - if (ret == -EAGAIN) { - struct dwc3_gadget_ep_cmd_params params; - u32 cmd; - - cmd = DWC3_DEPCMD_ENDTRANSFER | - DWC3_DEPCMD_CMDIOC | - DWC3_DEPCMD_PARAM(dep->resource_index); - - dep->resource_index = 0; - memset(&params, 0, sizeof(params)); - - ret = dwc3_send_gadget_ep_cmd(dep, cmd, &params); - if (!ret) - dep->flags |= DWC3_EP_END_TRANSFER_PENDING; - } + if (ret == -EAGAIN) + ret = __dwc3_stop_active_transfer(dep, false, true);

return ret; } @@ -3605,10 +3626,6 @@ static void dwc3_reset_gadget(struct dwc3 *dwc) static void dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, bool interrupt) { - struct dwc3_gadget_ep_cmd_params params; - u32 cmd; - int ret; - if (!(dep->flags & DWC3_EP_TRANSFER_STARTED) || (dep->flags & DWC3_EP_END_TRANSFER_PENDING)) return; @@ -3640,19 +3657,7 @@ static void dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, * This mode is NOT available on the DWC_usb31 IP. */

- cmd = DWC3_DEPCMD_ENDTRANSFER; - cmd |= force ? DWC3_DEPCMD_HIPRI_FORCERM : 0; - cmd |= interrupt ? DWC3_DEPCMD_CMDIOC : 0; - cmd |= DWC3_DEPCMD_PARAM(dep->resource_index); - memset(&params, 0, sizeof(params)); - ret = dwc3_send_gadget_ep_cmd(dep, cmd, &params); - WARN_ON_ONCE(ret); - dep->resource_index = 0; - - if (!interrupt) - dep->flags &= ~DWC3_EP_TRANSFER_STARTED; - else - dep->flags |= DWC3_EP_END_TRANSFER_PENDING; + __dwc3_stop_active_transfer(dep, force, interrupt); }

static void dwc3_clear_stall_all_ep(struct dwc3 *dwc)

From: Anders Roxell anders.roxell@linaro.org

[ Upstream commit 6fcd4267a840d0536b8e5334ad5f31e4105fce85 ]

Building kcsan_test with structleak plugin enabled makes the stack frame size to grow.

kernel/kcsan/kcsan_test.c:704:1: error: the frame size of 3296 bytes is larger than 2048 bytes [-Werror=frame-larger-than=]

Turn off the structleak plugin checks for kcsan_test.

Link: https://lkml.kernel.org/r/20221128104358.2660634-1-anders.roxell@linaro.org Signed-off-by: Anders Roxell anders.roxell@linaro.org Suggested-by: Arnd Bergmann arnd@arndb.de Acked-by: Marco Elver elver@google.com Cc: Arnd Bergmann arnd@arndb.de Cc: David Gow davidgow@google.com Cc: Jason A. Donenfeld Jason@zx2c4.com Cc: Kees Cook keescook@chromium.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Stable-dep-of: 5eb39cde1e24 ("kcsan: avoid passing -g for test") Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/kcsan/Makefile | 1 + 1 file changed, 1 insertion(+)

diff --git a/kernel/kcsan/Makefile b/kernel/kcsan/Makefile index c2bb07f5bcc72..5936288ee938b 100644 --- a/kernel/kcsan/Makefile +++ b/kernel/kcsan/Makefile @@ -14,4 +14,5 @@ obj-y := core.o debugfs.o report.o obj-$(CONFIG_KCSAN_SELFTEST) += selftest.o

CFLAGS_kcsan_test.o := $(CFLAGS_KCSAN) -g -fno-omit-frame-pointer +CFLAGS_kcsan_test.o += $(DISABLE_STRUCTLEAK_PLUGIN) obj-$(CONFIG_KCSAN_KUNIT_TEST) += kcsan_test.o

From: Namjae Jeon linkinjeon@kernel.org

[ Upstream commit be6f42fad5f5fd1fea9d562df82c38ad6ed3bfe9 ]

Steve reported that inactive sessions are terminated after a few seconds. ksmbd terminate when receiving -EAGAIN error from kernel_recvmsg(). -EAGAIN means there is no data available in timeout. So ksmbd should keep connection with unlimited retries instead of terminating inactive sessions.

Cc: stable@vger.kernel.org Reported-by: Steve French stfrench@microsoft.com 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/ksmbd/connection.c | 4 ++-- fs/ksmbd/connection.h | 3 ++- fs/ksmbd/transport_rdma.c | 2 +- fs/ksmbd/transport_tcp.c | 35 +++++++++++++++++++++++------------ 4 files changed, 28 insertions(+), 16 deletions(-)

diff --git a/fs/ksmbd/connection.c b/fs/ksmbd/connection.c index 6105649b4ebb0..610abaadbb677 100644 --- a/fs/ksmbd/connection.c +++ b/fs/ksmbd/connection.c @@ -292,7 +292,7 @@ int ksmbd_conn_handler_loop(void *p) kvfree(conn->request_buf); conn->request_buf = NULL;

- size = t->ops->read(t, hdr_buf, sizeof(hdr_buf)); + size = t->ops->read(t, hdr_buf, sizeof(hdr_buf), -1); if (size != sizeof(hdr_buf)) break;

@@ -335,7 +335,7 @@ int ksmbd_conn_handler_loop(void *p) * We already read 4 bytes to find out PDU size, now * read in PDU */ - size = t->ops->read(t, conn->request_buf + 4, pdu_size); + size = t->ops->read(t, conn->request_buf + 4, pdu_size, 2); if (size < 0) { pr_err("sock_read failed: %d\n", size); break; diff --git a/fs/ksmbd/connection.h b/fs/ksmbd/connection.h index 8694aef482c1a..4b15c5e673d92 100644 --- a/fs/ksmbd/connection.h +++ b/fs/ksmbd/connection.h @@ -122,7 +122,8 @@ struct ksmbd_conn_ops { struct ksmbd_transport_ops { int (*prepare)(struct ksmbd_transport *t); void (*disconnect)(struct ksmbd_transport *t); - int (*read)(struct ksmbd_transport *t, char *buf, unsigned int size); + int (*read)(struct ksmbd_transport *t, char *buf, + unsigned int size, int max_retries); int (*writev)(struct ksmbd_transport *t, struct kvec *iovs, int niov, int size, bool need_invalidate_rkey, unsigned int remote_key); diff --git a/fs/ksmbd/transport_rdma.c b/fs/ksmbd/transport_rdma.c index 9d67419929d6c..9ca29cdb7898f 100644 --- a/fs/ksmbd/transport_rdma.c +++ b/fs/ksmbd/transport_rdma.c @@ -663,7 +663,7 @@ static int smb_direct_post_recv(struct smb_direct_transport *t, }

static int smb_direct_read(struct ksmbd_transport *t, char *buf, - unsigned int size) + unsigned int size, int unused) { struct smb_direct_recvmsg *recvmsg; struct smb_direct_data_transfer *data_transfer; diff --git a/fs/ksmbd/transport_tcp.c b/fs/ksmbd/transport_tcp.c index e0ca6cc04b91c..d1d7954368a56 100644 --- a/fs/ksmbd/transport_tcp.c +++ b/fs/ksmbd/transport_tcp.c @@ -291,16 +291,18 @@ static int ksmbd_tcp_run_kthread(struct interface *iface)

/** * ksmbd_tcp_readv() - read data from socket in given iovec - * @t: TCP transport instance - * @iov_orig: base IO vector - * @nr_segs: number of segments in base iov - * @to_read: number of bytes to read from socket + * @t: TCP transport instance + * @iov_orig: base IO vector + * @nr_segs: number of segments in base iov + * @to_read: number of bytes to read from socket + * @max_retries: maximum retry count * * Return: on success return number of bytes read from socket, * otherwise return error number */ static int ksmbd_tcp_readv(struct tcp_transport *t, struct kvec *iov_orig, - unsigned int nr_segs, unsigned int to_read) + unsigned int nr_segs, unsigned int to_read, + int max_retries) { int length = 0; int total_read; @@ -308,7 +310,6 @@ static int ksmbd_tcp_readv(struct tcp_transport *t, struct kvec *iov_orig, struct msghdr ksmbd_msg; struct kvec *iov; struct ksmbd_conn *conn = KSMBD_TRANS(t)->conn; - int max_retry = 2;

iov = get_conn_iovec(t, nr_segs); if (!iov) @@ -335,14 +336,23 @@ static int ksmbd_tcp_readv(struct tcp_transport *t, struct kvec *iov_orig, } else if (conn->status == KSMBD_SESS_NEED_RECONNECT) { total_read = -EAGAIN; break; - } else if ((length == -ERESTARTSYS || length == -EAGAIN) && - max_retry) { + } else if (length == -ERESTARTSYS || length == -EAGAIN) { + /* + * If max_retries is negative, Allow unlimited + * retries to keep connection with inactive sessions. + */ + if (max_retries == 0) { + total_read = length; + break; + } else if (max_retries > 0) { + max_retries--; + } + usleep_range(1000, 2000); length = 0; - max_retry--; continue; } else if (length <= 0) { - total_read = -EAGAIN; + total_read = length; break; } } @@ -358,14 +368,15 @@ static int ksmbd_tcp_readv(struct tcp_transport *t, struct kvec *iov_orig, * Return: on success return number of bytes read from socket, * otherwise return error number */ -static int ksmbd_tcp_read(struct ksmbd_transport *t, char *buf, unsigned int to_read) +static int ksmbd_tcp_read(struct ksmbd_transport *t, char *buf, + unsigned int to_read, int max_retries) { struct kvec iov;

iov.iov_base = buf; iov.iov_len = to_read;

- return ksmbd_tcp_readv(TCP_TRANS(t), &iov, 1, to_read); + return ksmbd_tcp_readv(TCP_TRANS(t), &iov, 1, to_read, max_retries); }

static int ksmbd_tcp_writev(struct ksmbd_transport *t, struct kvec *iov,

From: Herbert Xu herbert@gondor.apana.org.au

[ Upstream commit 8222d5910dae08213b6d9d4bc9a7f8502855e624 ]

When copying data to user-space we should ensure that only valid data is copied over. Padding in structures may be filled with random (possibly sensitve) data and should never be given directly to user-space.

This patch fixes the copying of xfrm algorithms and the encap template in xfrm_user so that padding is zeroed.

Reported-by: syzbot+fa5414772d5c445dac3c@syzkaller.appspotmail.com Reported-by: Hyunwoo Kim v4bel@theori.io Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Reviewed-by: Sabrina Dubroca sd@queasysnail.net Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/xfrm/xfrm_user.c | 45 ++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 41 insertions(+), 4 deletions(-)

diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 5fba82757ce5e..eb0952dbf4236 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -906,7 +906,9 @@ static int copy_to_user_aead(struct xfrm_algo_aead *aead, struct sk_buff *skb) return -EMSGSIZE;

ap = nla_data(nla); - memcpy(ap, aead, sizeof(*aead)); + strscpy_pad(ap->alg_name, aead->alg_name, sizeof(ap->alg_name)); + ap->alg_key_len = aead->alg_key_len; + ap->alg_icv_len = aead->alg_icv_len;

if (redact_secret && aead->alg_key_len) memset(ap->alg_key, 0, (aead->alg_key_len + 7) / 8); @@ -926,7 +928,8 @@ static int copy_to_user_ealg(struct xfrm_algo *ealg, struct sk_buff *skb) return -EMSGSIZE;

ap = nla_data(nla); - memcpy(ap, ealg, sizeof(*ealg)); + strscpy_pad(ap->alg_name, ealg->alg_name, sizeof(ap->alg_name)); + ap->alg_key_len = ealg->alg_key_len;

if (redact_secret && ealg->alg_key_len) memset(ap->alg_key, 0, (ealg->alg_key_len + 7) / 8); @@ -937,6 +940,40 @@ static int copy_to_user_ealg(struct xfrm_algo *ealg, struct sk_buff *skb) return 0; }

+static int copy_to_user_calg(struct xfrm_algo *calg, struct sk_buff *skb) +{ + struct nlattr *nla = nla_reserve(skb, XFRMA_ALG_COMP, sizeof(*calg)); + struct xfrm_algo *ap; + + if (!nla) + return -EMSGSIZE; + + ap = nla_data(nla); + strscpy_pad(ap->alg_name, calg->alg_name, sizeof(ap->alg_name)); + ap->alg_key_len = 0; + + return 0; +} + +static int copy_to_user_encap(struct xfrm_encap_tmpl *ep, struct sk_buff *skb) +{ + struct nlattr *nla = nla_reserve(skb, XFRMA_ENCAP, sizeof(*ep)); + struct xfrm_encap_tmpl *uep; + + if (!nla) + return -EMSGSIZE; + + uep = nla_data(nla); + memset(uep, 0, sizeof(*uep)); + + uep->encap_type = ep->encap_type; + uep->encap_sport = ep->encap_sport; + uep->encap_dport = ep->encap_dport; + uep->encap_oa = ep->encap_oa; + + return 0; +} + static int xfrm_smark_put(struct sk_buff *skb, struct xfrm_mark *m) { int ret = 0; @@ -992,12 +1029,12 @@ static int copy_to_user_state_extra(struct xfrm_state *x, goto out; } if (x->calg) { - ret = nla_put(skb, XFRMA_ALG_COMP, sizeof(*(x->calg)), x->calg); + ret = copy_to_user_calg(x->calg, skb); if (ret) goto out; } if (x->encap) { - ret = nla_put(skb, XFRMA_ENCAP, sizeof(*x->encap), x->encap); + ret = copy_to_user_encap(x->encap, skb); if (ret) goto out; }

From: NeilBrown neilb@suse.de

[ Upstream commit 3bc57292278a0b6ac4656cad94c14f2453344b57 ]

slot_store() uses kstrtouint() to get a slot number, but stores the result in an "int" variable (by casting a pointer). This can result in a negative slot number if the unsigned int value is very large.

A negative number means that the slot is empty, but setting a negative slot number this way will not remove the device from the array. I don't think this is a serious problem, but it could cause confusion and it is best to fix it.

Reported-by: Dan Carpenter error27@gmail.com Signed-off-by: NeilBrown neilb@suse.de Signed-off-by: Song Liu song@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/md/md.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/md/md.c b/drivers/md/md.c index 9e54b865f30da..bd0c9dfac9815 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -3189,6 +3189,9 @@ slot_store(struct md_rdev *rdev, const char *buf, size_t len) err = kstrtouint(buf, 10, (unsigned int *)&slot); if (err < 0) return err; + if (slot < 0) + /* overflow */ + return -ENOSPC; } if (rdev->mddev->pers && slot == -1) { /* Setting 'slot' on an active array requires also

From: Kristian Overskeid koverskeid@gmail.com

[ Upstream commit 28e8cabe80f3e6e3c98121576eda898eeb20f1b1 ]

If no frames has been exchanged with a node for HSR_NODE_FORGET_TIME, the node will be deleted from the node_db list. If a frame is sent to the node after it is deleted, a netdev_err message for each slave interface is produced. This should not happen with dan nodes because of supervision frames, but can happen often with san nodes, which clutters the kernel log. Since the hsr protocol does not support sans, this is only relevant for the prp protocol.

Signed-off-by: Kristian Overskeid koverskeid@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/hsr/hsr_framereg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 414bf4d3d3c92..44eb9c9f80ee9 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -385,7 +385,7 @@ void hsr_addr_subst_dest(struct hsr_node *node_src, struct sk_buff *skb, node_dst = find_node_by_addr_A(&port->hsr->node_db, eth_hdr(skb)->h_dest); if (!node_dst) { - if (net_ratelimit()) + if (net_ratelimit() && port->hsr->prot_version != PRP_V1) netdev_err(skb->dev, "%s: Unknown node\n", __func__); return; }

From: Kuninori Morimoto kuninori.morimoto.gx@renesas.com

[ Upstream commit 98e5eb110095ec77cb6d775051d181edbf9cd3cf ]

tuning_ctl_set() might have buffer overrun at (X) if it didn't break from loop by matching (A).

static int tuning_ctl_set(...) { for (i = 0; i < TUNING_CTLS_COUNT; i++) (A) if (nid == ca0132_tuning_ctls[i].nid) break;

snd_hda_power_up(...); (X) dspio_set_param(..., ca0132_tuning_ctls[i].mid, ...); snd_hda_power_down(...); ^

return 1; }

We will get below error by cppcheck

sound/pci/hda/patch_ca0132.c:4229:2: note: After for loop, i has value 12 for (i = 0; i < TUNING_CTLS_COUNT; i++) ^ sound/pci/hda/patch_ca0132.c:4234:43: note: Array index out of bounds dspio_set_param(codec, ca0132_tuning_ctls[i].mid, 0x20, ^ This patch cares non match case.

Signed-off-by: Kuninori Morimoto kuninori.morimoto.gx@renesas.com Link: https://lore.kernel.org/r/87sfe9eap7.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/pci/hda/patch_ca0132.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index c0cb6e49a9b65..2646663e03426 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -4231,8 +4231,10 @@ static int tuning_ctl_set(struct hda_codec *codec, hda_nid_t nid,

for (i = 0; i < TUNING_CTLS_COUNT; i++) if (nid == ca0132_tuning_ctls[i].nid) - break; + goto found;

+ return -EINVAL; +found: snd_hda_power_up(codec); dspio_set_param(codec, ca0132_tuning_ctls[i].mid, 0x20, ca0132_tuning_ctls[i].req,

From: Linus Torvalds torvalds@linux-foundation.org

[ Upstream commit 6015b1aca1a233379625385feb01dd014aca60b5 ]

The getaffinity() system call uses 'cpumask_size()' to decide how big the CPU mask is - so far so good. It is indeed the allocation size of a cpumask.

But the code also assumes that the whole allocation is initialized without actually doing so itself. That's wrong, because we might have fixed-size allocations (making copying and clearing more efficient), but not all of it is then necessarily used if 'nr_cpu_ids' is smaller.

Having checked other users of 'cpumask_size()', they all seem to be ok, either using it purely for the allocation size, or explicitly zeroing the cpumask before using the size in bytes to copy it.

See for example the ublk_ctrl_get_queue_affinity() function that uses the proper 'zalloc_cpumask_var()' to make sure that the whole mask is cleared, whether the storage is on the stack or if it was an external allocation.

Fix this by just zeroing the allocation before using it. Do the same for the compat version of sched_getaffinity(), which had the same logic.

Also, for consistency, make sched_getaffinity() use 'cpumask_bits()' to access the bits. For a cpumask_var_t, it ends up being a pointer to the same data either way, but it's just a good idea to treat it like you would a 'cpumask_t'. The compat case already did that.

Reported-by: Ryan Roberts ryan.roberts@arm.com Link: https://lore.kernel.org/lkml/7d026744-6bd6-6827-0471-b5e8eae0be3f@arm.com/ Cc: Yury Norov yury.norov@gmail.com Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/compat.c | 2 +- kernel/sched/core.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/compat.c b/kernel/compat.c index 55551989d9da5..fb50f29d9b361 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -152,7 +152,7 @@ COMPAT_SYSCALL_DEFINE3(sched_getaffinity, compat_pid_t, pid, unsigned int, len, if (len & (sizeof(compat_ulong_t)-1)) return -EINVAL;

- if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM;

ret = sched_getaffinity(pid, mask); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 0c72459d5f42a..acf7c09c9152f 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -8185,14 +8185,14 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, if (len & (sizeof(unsigned long)-1)) return -EINVAL;

- if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM;

ret = sched_getaffinity(pid, mask); if (ret == 0) { unsigned int retlen = min(len, cpumask_size());

- if (copy_to_user(user_mask_ptr, mask, retlen)) + if (copy_to_user(user_mask_ptr, cpumask_bits(mask), retlen)) ret = -EFAULT; else ret = retlen;

From: Wei Chen harperchen1110@gmail.com

[ Upstream commit d823685486a3446d061fed7c7d2f80af984f119a ]

Variable var->pixclock is controlled by user and can be assigned to zero. Without proper check, divide by zero would occur in intelfbhw_validate_mode and intelfbhw_mode_to_hw.

Error out if var->pixclock is zero.

Signed-off-by: Wei Chen harperchen1110@gmail.com Signed-off-by: Helge Deller deller@gmx.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/video/fbdev/intelfb/intelfbdrv.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/video/fbdev/intelfb/intelfbdrv.c b/drivers/video/fbdev/intelfb/intelfbdrv.c index a9579964eaba8..8a703adfa9360 100644 --- a/drivers/video/fbdev/intelfb/intelfbdrv.c +++ b/drivers/video/fbdev/intelfb/intelfbdrv.c @@ -1214,6 +1214,9 @@ static int intelfb_check_var(struct fb_var_screeninfo *var,

dinfo = GET_DINFO(info);

+ if (!var->pixclock) + return -EINVAL; + /* update the pitch */ if (intelfbhw_validate_mode(dinfo, var) != 0) return -EINVAL;

From: Wei Chen harperchen1110@gmail.com

[ Upstream commit 44a3b36b42acfc433aaaf526191dd12fbb919fdb ]

var->pixclock can be assigned to zero by user. Without proper check, divide by zero would occur when invoking macro PICOS2KHZ in au1200fb_fb_check_var.

Error out if var->pixclock is zero.

Signed-off-by: Wei Chen harperchen1110@gmail.com Signed-off-by: Helge Deller deller@gmx.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/video/fbdev/au1200fb.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/video/fbdev/au1200fb.c b/drivers/video/fbdev/au1200fb.c index c00e01a173685..a8a0a448cdb5e 100644 --- a/drivers/video/fbdev/au1200fb.c +++ b/drivers/video/fbdev/au1200fb.c @@ -1040,6 +1040,9 @@ static int au1200fb_fb_check_var(struct fb_var_screeninfo *var, u32 pixclock; int screen_size, plane;

+ if (!var->pixclock) + return -EINVAL; + plane = fbdev->plane;

/* Make sure that the mode respect all LCD controller and

From: Antti Laakso antti.laakso@intel.com

[ Upstream commit 92c25393586ac799b9b7d9e50434f3c44a7622c4 ]

The "excursion to minimum" information is in bit2 in HWP_STATUS MSR. Fix the bitmask used for decoding the register.

Signed-off-by: Antti Laakso antti.laakso@intel.com Reviewed-by: Artem Bityutskiy artem.bityutskiy@linux.intel.com Signed-off-by: Len Brown len.brown@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/power/x86/turbostat/turbostat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 84b8a35c91972..a3197efe52c63 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -4241,7 +4241,7 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p)

fprintf(outf, "cpu%d: MSR_HWP_STATUS: 0x%08llx " "(%sGuaranteed_Perf_Change, %sExcursion_Min)\n", - cpu, msr, ((msr) & 0x1) ? "" : "No-", ((msr) & 0x2) ? "" : "No-"); + cpu, msr, ((msr) & 0x1) ? "" : "No-", ((msr) & 0x4) ? "" : "No-");

return 0; }

From: Harshit Mogalapalli harshit.m.mogalapalli@oracle.com

[ Upstream commit 748b2f5e82d17480404b3e2895388fc2925f7caf ]

mac_len is of type unsigned, which can never be less than zero.

mac_len = ieee802154_hdr_peek_addrs(skb, &header); if (mac_len < 0) return mac_len;

Change this to type int as ieee802154_hdr_peek_addrs() can return negative integers, this is found by static analysis with smatch.

Fixes: 6c993779ea1d ("ca8210: fix mac_len negative array access") Signed-off-by: Harshit Mogalapalli harshit.m.mogalapalli@oracle.com Acked-by: Alexander Aring aahringo@redhat.com Reviewed-by: Simon Horman simon.horman@corigine.com Link: https://lore.kernel.org/r/20230306191824.4115839-1-harshit.m.mogalapalli@ora... Signed-off-by: Stefan Schmidt stefan@datenfreihafen.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ieee802154/ca8210.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c index e2322bc3a4e9a..5834d3ed6dcf5 100644 --- a/drivers/net/ieee802154/ca8210.c +++ b/drivers/net/ieee802154/ca8210.c @@ -1945,10 +1945,9 @@ static int ca8210_skb_tx( struct ca8210_priv *priv ) { - int status; struct ieee802154_hdr header = { }; struct secspec secspec; - unsigned int mac_len; + int mac_len, status;

dev_dbg(&priv->spi->dev, "%s called\n", __func__);

From: Takashi Iwai tiwai@suse.de

[ Upstream commit 8c721c53dda512fdd48eb24d6d99e56deee57898 ]

The recent support of low latency playback in USB-audio driver made the snd_usb_queue_pending_output_urbs() function to be called via PCM ack ops. In the new code path, the function is performed already in the PCM stream lock. The problem is that, when an XRUN is detected, the function calls snd_pcm_xrun() to notify, but snd_pcm_xrun() is supposed to be called only outside the stream lock. As a result, it leads to a deadlock of PCM stream locking.

For avoiding such a recursive locking, this patch adds an additional check to the code paths in PCM core that call the ack callback; now it checks the error code from the callback, and if it's -EPIPE, the XRUN is handled in the PCM core side gracefully. Along with it, the USB-audio driver code is changed to follow that, i.e. -EPIPE is returned instead of the explicit snd_pcm_xrun() call when the function is performed already in the stream lock.

Fixes: d5f871f89e21 ("ALSA: usb-audio: Improved lowlatency playback support") Reported-and-tested-by: John Keeping john@metanate.com Link: https://lore.kernel.org/r/20230317195128.3911155-1-john@metanate.com Reviewed-by: Jaroslav Kysela perex@perex.cz Reviewed-by; Takashi Sakamoto o-takashi@sakamocchi.jp Link: https://lore.kernel.org/r/20230320142838.494-1-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/core/pcm_lib.c | 2 ++ sound/usb/endpoint.c | 22 ++++++++++++++-------- sound/usb/endpoint.h | 4 ++-- sound/usb/pcm.c | 2 +- 4 files changed, 19 insertions(+), 11 deletions(-)

diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index 491064f55515b..8947c988b6d34 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -2137,6 +2137,8 @@ int pcm_lib_apply_appl_ptr(struct snd_pcm_substream *substream, ret = substream->ops->ack(substream); if (ret < 0) { runtime->control->appl_ptr = old_appl_ptr; + if (ret == -EPIPE) + __snd_pcm_xrun(substream); return ret; } } diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c index 092350eb5f4e3..6c7d842d04965 100644 --- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -444,8 +444,8 @@ static void push_back_to_ready_list(struct snd_usb_endpoint *ep, * This function is used both for implicit feedback endpoints and in low- * latency playback mode. */ -void snd_usb_queue_pending_output_urbs(struct snd_usb_endpoint *ep, - bool in_stream_lock) +int snd_usb_queue_pending_output_urbs(struct snd_usb_endpoint *ep, + bool in_stream_lock) { bool implicit_fb = snd_usb_endpoint_implicit_feedback_sink(ep);

@@ -469,7 +469,7 @@ void snd_usb_queue_pending_output_urbs(struct snd_usb_endpoint *ep, spin_unlock_irqrestore(&ep->lock, flags);

if (ctx == NULL) - return; + break;

/* copy over the length information */ if (implicit_fb) { @@ -484,11 +484,14 @@ void snd_usb_queue_pending_output_urbs(struct snd_usb_endpoint *ep, break; if (err < 0) { /* push back to ready list again for -EAGAIN */ - if (err == -EAGAIN) + if (err == -EAGAIN) { push_back_to_ready_list(ep, ctx); - else + break; + } + + if (!in_stream_lock) notify_xrun(ep); - return; + return -EPIPE; }

err = usb_submit_urb(ctx->urb, GFP_ATOMIC); @@ -496,13 +499,16 @@ void snd_usb_queue_pending_output_urbs(struct snd_usb_endpoint *ep, usb_audio_err(ep->chip, "Unable to submit urb #%d: %d at %s\n", ctx->index, err, __func__); - notify_xrun(ep); - return; + if (!in_stream_lock) + notify_xrun(ep); + return -EPIPE; }

set_bit(ctx->index, &ep->active_mask); atomic_inc(&ep->submitted_urbs); } + + return 0; }

/* diff --git a/sound/usb/endpoint.h b/sound/usb/endpoint.h index 6a9af04cf175a..daa7ba063d858 100644 --- a/sound/usb/endpoint.h +++ b/sound/usb/endpoint.h @@ -49,7 +49,7 @@ int snd_usb_endpoint_implicit_feedback_sink(struct snd_usb_endpoint *ep); int snd_usb_endpoint_next_packet_size(struct snd_usb_endpoint *ep, struct snd_urb_ctx *ctx, int idx, unsigned int avail); -void snd_usb_queue_pending_output_urbs(struct snd_usb_endpoint *ep, - bool in_stream_lock); +int snd_usb_queue_pending_output_urbs(struct snd_usb_endpoint *ep, + bool in_stream_lock);

#endif /* __USBAUDIO_ENDPOINT_H */ diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index 87a30be643242..de0964dbf7a91 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -1557,7 +1557,7 @@ static int snd_usb_pcm_playback_ack(struct snd_pcm_substream *substream) * outputs here */ if (!ep->active_mask) - snd_usb_queue_pending_output_urbs(ep, true); + return snd_usb_queue_pending_output_urbs(ep, true); return 0; }

From: Mark Pearson mpearson-lenovo@squebb.ca

[ Upstream commit 45e21289bfc6e257885514790a8a8887da822d40 ]

firmware-attributes class requires that possible values are delimited using ';' but the Lenovo firmware uses ',' instead. Parse string and replace where appropriate.

Suggested-by: Thomas Weißschuh linux@weissschuh.net Fixes: a40cd7ef22fb ("platform/x86: think-lmi: Add WMI interface support on Lenovo platforms") Signed-off-by: Mark Pearson mpearson-lenovo@squebb.ca Link: https://lore.kernel.org/r/20230320003221.561750-2-mpearson-lenovo@squebb.ca Reviewed-by: Thomas Weißschuh linux@weissschuh.net Reviewed-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/platform/x86/think-lmi.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c index 0c166b4fa7167..f10fe5ffe47df 100644 --- a/drivers/platform/x86/think-lmi.c +++ b/drivers/platform/x86/think-lmi.c @@ -538,7 +538,7 @@ static ssize_t type_show(struct kobject *kobj, struct kobj_attribute *attr,

if (setting->possible_values) { /* Figure out what setting type is as BIOS does not return this */ - if (strchr(setting->possible_values, ',')) + if (strchr(setting->possible_values, ';')) return sysfs_emit(buf, "enumeration\n"); } /* Anything else is going to be a string */ @@ -934,6 +934,13 @@ static int tlmi_analyze(void) pr_info("Error retrieving possible values for %d : %s\n", i, setting->display_name); } + /* + * firmware-attributes requires that possible_values are separated by ';' but + * Lenovo FW uses ','. Replace appropriately. + */ + if (setting->possible_values) + strreplace(setting->possible_values, ',', ';'); + kobject_init(&setting->kobj, &tlmi_attr_setting_ktype); tlmi_priv.setting[i] = setting; kfree(item);

From: Mark Pearson mpearson-lenovo@squebb.ca

[ Upstream commit 8a02d70679fc1c434401863333c8ea7dbf201494 ]

ThinkStation platforms don't support the API to return possible_values but instead embed it in the settings string.

Try and extract this information and set the possible_values attribute appropriately.

Fixes: a40cd7ef22fb ("platform/x86: think-lmi: Add WMI interface support on Lenovo platforms") Signed-off-by: Mark Pearson mpearson-lenovo@squebb.ca Link: https://lore.kernel.org/r/20230320003221.561750-4-mpearson-lenovo@squebb.ca Reviewed-by: Thomas Weißschuh linux@weissschuh.net Reviewed-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/platform/x86/think-lmi.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+)

diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c index b7428f5ec4c4c..c9ed2644bb8a6 100644 --- a/drivers/platform/x86/think-lmi.c +++ b/drivers/platform/x86/think-lmi.c @@ -943,6 +943,26 @@ static int tlmi_analyze(void) if (ret || !setting->possible_values) pr_info("Error retrieving possible values for %d : %s\n", i, setting->display_name); + } else { + /* + * Older Thinkstations don't support the bios_selections API. + * Instead they store this as a [Optional:Option1,Option2] section of the + * name string. + * Try and pull that out if it's available. + */ + char *item, *optstart, *optend; + + if (!tlmi_setting(setting->index, &item, LENOVO_BIOS_SETTING_GUID)) { + optstart = strstr(item, "[Optional:"); + if (optstart) { + optstart += strlen("[Optional:"); + optend = strstr(optstart, "]"); + if (optend) + setting->possible_values = + kstrndup(optstart, optend - optstart, + GFP_KERNEL); + } + } } /* * firmware-attributes requires that possible_values are separated by ';' but

From: Siddharth Kawar Siddharth.Kawar@microsoft.com

[ Upstream commit 943d045a6d796175e5d08f9973953b1d2c07d797 ]

NFS server Duplicate Request Cache (DRC) algorithms rely on NFS clients reconnecting using the same local TCP port. Unique NFS operations are identified by the per-TCP connection set of XIDs. This prevents file corruption when non-idempotent NFS operations are retried.

Currently, NFS client TCP connections are using different local TCP ports when reconnecting to NFS servers.

After an NFS server initiates shutdown of the TCP connection, the NFS client's TCP socket is set to NULL after the socket state has reached TCP_LAST_ACK(9). When reconnecting, the new socket attempts to reuse the same local port but fails with EADDRNOTAVAIL (99). This forces the socket to use a different local TCP port to reconnect to the remote NFS server.

State Transition and Events: TCP_CLOSE_WAIT(8) TCP_LAST_ACK(9) connect(fail EADDRNOTAVAIL(99)) TCP_CLOSE(7) bind on new port connect success

dmesg excerpts showing reconnect switching from TCP local port of 926 to 763 after commit 7c81e6a9d75b: [13354.947854] NFS call mkdir testW ... [13405.654781] RPC: xs_tcp_state_change client 00000000037d0f03... [13405.654813] RPC: state 8 conn 1 dead 0 zapped 1 sk_shutdown 1 [13405.654826] RPC: xs_data_ready... [13405.654892] RPC: xs_tcp_state_change client 00000000037d0f03... [13405.654895] RPC: state 9 conn 0 dead 0 zapped 1 sk_shutdown 3 [13405.654899] RPC: xs_tcp_state_change client 00000000037d0f03... [13405.654900] RPC: state 9 conn 0 dead 0 zapped 1 sk_shutdown 3 [13405.654950] RPC: xs_connect scheduled xprt 00000000037d0f03 [13405.654975] RPC: xs_bind 0.0.0.0:926: ok (0) [13405.654980] RPC: worker connecting xprt 00000000037d0f03 via tcp to 10.101.6.228 (port 2049) [13405.654991] RPC: 00000000037d0f03 connect status 99 connected 0 sock state 7 [13405.655001] RPC: xs_tcp_state_change client 00000000037d0f03... [13405.655002] RPC: state 7 conn 0 dead 0 zapped 1 sk_shutdown 3 [13405.655024] RPC: xs_connect scheduled xprt 00000000037d0f03 [13405.655038] RPC: xs_bind 0.0.0.0:763: ok (0) [13405.655041] RPC: worker connecting xprt 00000000037d0f03 via tcp to 10.101.6.228 (port 2049) [13405.655065] RPC: 00000000037d0f03 connect status 115 connected 0 sock state 2

State Transition and Events with patch applied: TCP_CLOSE_WAIT(8) TCP_LAST_ACK(9) TCP_CLOSE(7) connect(reuse of port succeeds)

dmesg excerpts showing reconnect on same TCP local port of 936 with patch applied: [ 257.139935] NFS: mkdir(0:59/560857152), testQ [ 257.139937] NFS call mkdir testQ ... [ 307.822702] RPC: state 8 conn 1 dead 0 zapped 1 sk_shutdown 1 [ 307.822714] RPC: xs_data_ready... [ 307.822817] RPC: xs_tcp_state_change client 00000000ce702f14... [ 307.822821] RPC: state 9 conn 0 dead 0 zapped 1 sk_shutdown 3 [ 307.822825] RPC: xs_tcp_state_change client 00000000ce702f14... [ 307.822826] RPC: state 9 conn 0 dead 0 zapped 1 sk_shutdown 3 [ 307.823606] RPC: xs_tcp_state_change client 00000000ce702f14... [ 307.823609] RPC: state 7 conn 0 dead 0 zapped 1 sk_shutdown 3 [ 307.823629] RPC: xs_tcp_state_change client 00000000ce702f14... [ 307.823632] RPC: state 7 conn 0 dead 0 zapped 1 sk_shutdown 3 [ 307.823676] RPC: xs_connect scheduled xprt 00000000ce702f14 [ 307.823704] RPC: xs_bind 0.0.0.0:936: ok (0) [ 307.823709] RPC: worker connecting xprt 00000000ce702f14 via tcp to 10.101.1.30 (port 2049) [ 307.823748] RPC: 00000000ce702f14 connect status 115 connected 0 sock state 2 ... [ 314.916193] RPC: state 7 conn 0 dead 0 zapped 1 sk_shutdown 3 [ 314.916251] RPC: xs_connect scheduled xprt 00000000ce702f14 [ 314.916282] RPC: xs_bind 0.0.0.0:936: ok (0) [ 314.916292] RPC: worker connecting xprt 00000000ce702f14 via tcp to 10.101.1.30 (port 2049) [ 314.916342] RPC: 00000000ce702f14 connect status 115 connected 0 sock state 2

Fixes: 7c81e6a9d75b ("SUNRPC: Tweak TCP socket shutdown in the RPC client") Signed-off-by: Siddharth Rajendra Kawar sikawar@microsoft.com Signed-off-by: Anna Schumaker Anna.Schumaker@Netapp.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/sunrpc/xprtsock.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 897dfce7dd271..bf801adff63db 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2140,6 +2140,7 @@ static void xs_tcp_shutdown(struct rpc_xprt *xprt) switch (skst) { case TCP_FIN_WAIT1: case TCP_FIN_WAIT2: + case TCP_LAST_ACK: break; case TCP_ESTABLISHED: case TCP_CLOSE_WAIT:

From: Tomas Henzl thenzl@redhat.com

[ Upstream commit 2309df27111a51734cb9240b4d3c25f2f3c6ab06 ]

When a physical disk is attached directly "without JBOD MAP support" (see megasas_get_tm_devhandle()) then there is no real error handling in the driver. Return FAILED instead of SUCCESS.

Fixes: 18365b138508 ("megaraid_sas: Task management support") Signed-off-by: Tomas Henzl thenzl@redhat.com Link: https://lore.kernel.org/r/20230324150134.14696-1-thenzl@redhat.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/megaraid/megaraid_sas_fusion.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c index 056837849ead5..c254254aa72f8 100644 --- a/drivers/scsi/megaraid/megaraid_sas_fusion.c +++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c @@ -4737,7 +4737,7 @@ int megasas_task_abort_fusion(struct scsi_cmnd *scmd) devhandle = megasas_get_tm_devhandle(scmd->device);

if (devhandle == (u16)ULONG_MAX) { - ret = SUCCESS; + ret = FAILED; sdev_printk(KERN_INFO, scmd->device, "task abort issued for invalid devhandle\n"); mutex_unlock(&instance->reset_mutex); @@ -4807,7 +4807,7 @@ int megasas_reset_target_fusion(struct scsi_cmnd *scmd) devhandle = megasas_get_tm_devhandle(scmd->device);

if (devhandle == (u16)ULONG_MAX) { - ret = SUCCESS; + ret = FAILED; sdev_printk(KERN_INFO, scmd->device, "target reset issued for invalid devhandle\n"); mutex_unlock(&instance->reset_mutex);

From: SongJingyi u201912584@hust.edu.cn

[ Upstream commit f33642224e38d7e0d59336e10e7b4e370b1c4506 ]

Smatch complains that: drivers/ptp/ptp_qoriq.c ptp_qoriq_probe() warn: 'base' from ioremap() not released.

Fix this by revising the parameter from 'ptp_qoriq->base' to 'base'. This is only a bug if ptp_qoriq_init() returns on the first -ENODEV error path. For other error paths ptp_qoriq->base and base are the same. And this change makes the code more readable.

Fixes: 7f4399ba405b ("ptp_qoriq: fix NULL access if ptp dt node missing") Signed-off-by: SongJingyi u201912584@hust.edu.cn Reviewed-by: Dan Carpenter error27@gmail.com Reviewed-by: Dongliang Mu dzm91@hust.edu.cn Link: https://lore.kernel.org/r/20230324031406.1895159-1-u201912584@hust.edu.cn Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/ptp/ptp_qoriq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c index 08f4cf0ad9e3c..8fa9772acf79b 100644 --- a/drivers/ptp/ptp_qoriq.c +++ b/drivers/ptp/ptp_qoriq.c @@ -601,7 +601,7 @@ static int ptp_qoriq_probe(struct platform_device *dev) return 0;

no_clock: - iounmap(ptp_qoriq->base); + iounmap(base); no_ioremap: release_resource(ptp_qoriq->rsrc); no_resource:

From: ChunHao Lin hau@realtek.com

[ Upstream commit 33189f0a94b9639c058781fcf82e4ea3803b1682 ]

When link speed is 10 Mbps and temperature is under -20°C, RTL8168H and RTL8107E may have rx crc error. Disable phy 10 Mbps pll off to fix this issue.

Fixes: 6e1d0b898818 ("r8169:add support for RTL8168H and RTL8107E") Signed-off-by: ChunHao Lin hau@realtek.com Reviewed-by: Heiner Kallweit hkallweit1@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/realtek/r8169_phy_config.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/realtek/r8169_phy_config.c b/drivers/net/ethernet/realtek/r8169_phy_config.c index 50f0f621b1aa8..a84fd859aec9b 100644 --- a/drivers/net/ethernet/realtek/r8169_phy_config.c +++ b/drivers/net/ethernet/realtek/r8169_phy_config.c @@ -970,6 +970,9 @@ static void rtl8168h_2_hw_phy_config(struct rtl8169_private *tp, /* disable phy pfm mode */ phy_modify_paged(phydev, 0x0a44, 0x11, BIT(7), 0);

+ /* disable 10m pll off */ + phy_modify_paged(phydev, 0x0a43, 0x10, BIT(0), 0); + rtl8168g_disable_aldps(phydev); rtl8168g_config_eee_phy(phydev); }

From: Faicker Mo faicker.mo@ucloud.cn

[ Upstream commit e3cbdcb0fbb61045ef3ce0e072927cc41737f787 ]

The failover txq is inited as 16 queues. when a packet is transmitted from the failover device firstly, the failover device will select the queue which is returned from the primary device if the primary device is UP and running. If the primary device txq is bigger than the default 16, it can lead to the following warning: eth0 selects TX queue 18, but real number of TX queues is 16

The warning backtrace is: [ 32.146376] CPU: 18 PID: 9134 Comm: chronyd Tainted: G E 6.2.8-1.el7.centos.x86_64 #1 [ 32.147175] Hardware name: Red Hat KVM, BIOS 1.10.2-3.el7_4.1 04/01/2014 [ 32.147730] Call Trace: [ 32.147971] <TASK> [ 32.148183] dump_stack_lvl+0x48/0x70 [ 32.148514] dump_stack+0x10/0x20 [ 32.148820] netdev_core_pick_tx+0xb1/0xe0 [ 32.149180] __dev_queue_xmit+0x529/0xcf0 [ 32.149533] ? __check_object_size.part.0+0x21c/0x2c0 [ 32.149967] ip_finish_output2+0x278/0x560 [ 32.150327] __ip_finish_output+0x1fe/0x2f0 [ 32.150690] ip_finish_output+0x2a/0xd0 [ 32.151032] ip_output+0x7a/0x110 [ 32.151337] ? __pfx_ip_finish_output+0x10/0x10 [ 32.151733] ip_local_out+0x5e/0x70 [ 32.152054] ip_send_skb+0x19/0x50 [ 32.152366] udp_send_skb.isra.0+0x163/0x3a0 [ 32.152736] udp_sendmsg+0xba8/0xec0 [ 32.153060] ? __folio_memcg_unlock+0x25/0x60 [ 32.153445] ? __pfx_ip_generic_getfrag+0x10/0x10 [ 32.153854] ? sock_has_perm+0x85/0xa0 [ 32.154190] inet_sendmsg+0x6d/0x80 [ 32.154508] ? inet_sendmsg+0x6d/0x80 [ 32.154838] sock_sendmsg+0x62/0x70 [ 32.155152] ____sys_sendmsg+0x134/0x290 [ 32.155499] ___sys_sendmsg+0x81/0xc0 [ 32.155828] ? _get_random_bytes.part.0+0x79/0x1a0 [ 32.156240] ? ip4_datagram_release_cb+0x5f/0x1e0 [ 32.156649] ? get_random_u16+0x69/0xf0 [ 32.156989] ? __fget_light+0xcf/0x110 [ 32.157326] __sys_sendmmsg+0xc4/0x210 [ 32.157657] ? __sys_connect+0xb7/0xe0 [ 32.157995] ? __audit_syscall_entry+0xce/0x140 [ 32.158388] ? syscall_trace_enter.isra.0+0x12c/0x1a0 [ 32.158820] __x64_sys_sendmmsg+0x24/0x30 [ 32.159171] do_syscall_64+0x38/0x90 [ 32.159493] entry_SYSCALL_64_after_hwframe+0x72/0xdc

Fix that by reducing txq number as the non-existent primary-dev does.

Fixes: cfc80d9a1163 ("net: Introduce net_failover driver") Signed-off-by: Faicker Mo faicker.mo@ucloud.cn Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/net_failover.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c index 2a4892402ed8c..16b36e9563607 100644 --- a/drivers/net/net_failover.c +++ b/drivers/net/net_failover.c @@ -130,14 +130,10 @@ static u16 net_failover_select_queue(struct net_device *dev, txq = ops->ndo_select_queue(primary_dev, skb, sb_dev); else txq = netdev_pick_tx(primary_dev, skb, NULL); - - qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping; - - return txq; + } else { + txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : 0; }

- txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : 0; - /* Save the original txq to restore before passing to the driver */ qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping;

From: Imre Deak imre.deak@intel.com

[ Upstream commit 38c583019484f190d5b33f59b8ae810e6b1763c6 ]

The commit renaming icl_tc_phy_is_in_safe_mode() to icl_tc_phy_take_ownership() didn't flip the function's return value accordingly, fix this up.

This didn't cause an actual problem besides state check errors, since the function is only used during HW readout.

Cc: José Roberto de Souza jose.souza@intel.com Fixes: f53979d68a77 ("drm/i915/display/tc: Rename safe_mode functions ownership") Reviewed-by: José Roberto de Souza jose.souza@intel.com Reviewed-by: Ville Syrjälä ville.syrjala@linux.intel.com Signed-off-by: Imre Deak imre.deak@intel.com Link: https://patchwork.freedesktop.org/patch/msgid/20230316131724.359612-4-imre.d... (cherry picked from commit f2c7959dda614d9b7c6a41510492de39d31705ec) Signed-off-by: Jani Nikula jani.nikula@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/i915/display/intel_tc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c index 0e885440be242..1b5b4d252d5b8 100644 --- a/drivers/gpu/drm/i915/display/intel_tc.c +++ b/drivers/gpu/drm/i915/display/intel_tc.c @@ -386,9 +386,9 @@ static bool icl_tc_phy_is_owned(struct intel_digital_port *dig_port) PORT_TX_DFLEXDPCSSS(dig_port->tc_phy_fia)); if (val == 0xffffffff) { drm_dbg_kms(&i915->drm, - "Port %s: PHY in TCCOLD, assume safe mode\n", + "Port %s: PHY in TCCOLD, assume not owned\n", dig_port->tc_port_name); - return true; + return false; }

return val & DP_PHY_MODE_STATUS_NOT_SAFE(dig_port->tc_phy_fia_idx);

From: Ivan Orlov ivan.orlov0322@gmail.com

[ Upstream commit 2b4c99f7d9a57ecd644eda9b1fb0a1072414959f ]

Syzkaller reported the following issue:

===================================================== BUG: KMSAN: uninit-value in aio_rw_done fs/aio.c:1520 [inline] BUG: KMSAN: uninit-value in aio_write+0x899/0x950 fs/aio.c:1600 aio_rw_done fs/aio.c:1520 [inline] aio_write+0x899/0x950 fs/aio.c:1600 io_submit_one+0x1d1c/0x3bf0 fs/aio.c:2019 __do_sys_io_submit fs/aio.c:2078 [inline] __se_sys_io_submit+0x293/0x770 fs/aio.c:2048 __x64_sys_io_submit+0x92/0xd0 fs/aio.c:2048 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd

Uninit was created at: slab_post_alloc_hook mm/slab.h:766 [inline] slab_alloc_node mm/slub.c:3452 [inline] __kmem_cache_alloc_node+0x71f/0xce0 mm/slub.c:3491 __do_kmalloc_node mm/slab_common.c:967 [inline] __kmalloc+0x11d/0x3b0 mm/slab_common.c:981 kmalloc_array include/linux/slab.h:636 [inline] bcm_tx_setup+0x80e/0x29d0 net/can/bcm.c:930 bcm_sendmsg+0x3a2/0xce0 net/can/bcm.c:1351 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg net/socket.c:734 [inline] sock_write_iter+0x495/0x5e0 net/socket.c:1108 call_write_iter include/linux/fs.h:2189 [inline] aio_write+0x63a/0x950 fs/aio.c:1600 io_submit_one+0x1d1c/0x3bf0 fs/aio.c:2019 __do_sys_io_submit fs/aio.c:2078 [inline] __se_sys_io_submit+0x293/0x770 fs/aio.c:2048 __x64_sys_io_submit+0x92/0xd0 fs/aio.c:2048 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd

CPU: 1 PID: 5034 Comm: syz-executor350 Not tainted 6.2.0-rc6-syzkaller-80422-geda666ff2276 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/12/2023 =====================================================

We can follow the call chain and find that 'bcm_tx_setup' function calls 'memcpy_from_msg' to copy some content to the newly allocated frame of 'op->frames'. After that the 'len' field of copied structure being compared with some constant value (64 or 8). However, if 'memcpy_from_msg' returns an error, we will compare some uninitialized memory. This triggers 'uninit-value' issue.

This patch will add 'memcpy_from_msg' possible errors processing to avoid uninit-value issue.

Tested via syzkaller

Reported-by: syzbot+c9bfd85eca611ebf5db1@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=47f897f8ad958bbde5790ebf389b5e7e0a34508... Signed-off-by: Ivan Orlov ivan.orlov0322@gmail.com Fixes: 6f3b911d5f29b ("can: bcm: add support for CAN FD frames") Acked-by: Oliver Hartkopp socketcan@hartkopp.net Link: https://lore.kernel.org/all/20230314120445.12407-1-ivan.orlov0322@gmail.com Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Sasha Levin sashal@kernel.org --- net/can/bcm.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/net/can/bcm.c b/net/can/bcm.c index aab3a18f4a90f..5727a073189b2 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -936,6 +936,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,

cf = op->frames + op->cfsiz * i; err = memcpy_from_msg((u8 *)cf, msg, op->cfsiz); + if (err < 0) + goto free_op;

if (op->flags & CAN_FD_FRAME) { if (cf->len > 64) @@ -945,12 +947,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, err = -EINVAL; }

- if (err < 0) { - if (op->frames != &op->sframe) - kfree(op->frames); - kfree(op); - return err; - } + if (err < 0) + goto free_op;

if (msg_head->flags & TX_CP_CAN_ID) { /* copy can_id into frame */ @@ -1021,6 +1019,12 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, bcm_tx_start_timer(op);

return msg_head->nframes * op->cfsiz + MHSIZ; + +free_op: + if (op->frames != &op->sframe) + kfree(op->frames); + kfree(op); + return err; }

/*

From: Christoph Hellwig hch@lst.de

[ Upstream commit 498ef5c777d9c89693b70cc453b40c392120ea1b ]

Currently, udev change event is generated for a loop device before the device is ready for IO. Due to serialization on lo->lo_mutex in lo_open() this does not matter because anybody is able to open the device and do IO only after the configuration is finished. However this synchronization in lo_open() is going away so make sure userspace reacting to the change event will see the new device state by generating the event only when the device is setup.

Signed-off-by: Christoph Hellwig hch@lst.de Reviewed-by: Jan Kara jack@suse.cz Link: https://lore.kernel.org/r/20220330052917.2566582-13-hch@lst.de Signed-off-by: Jens Axboe axboe@kernel.dk Stable-dep-of: bb430b694226 ("loop: LOOP_CONFIGURE: send uevents for partitions") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/block/loop.c | 25 +++++++++++++++++++++---- 1 file changed, 21 insertions(+), 4 deletions(-)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 07cf7a35ae502..032862cce6e4e 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -736,6 +736,10 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,

if (!file) return -EBADF; + + /* suppress uevents while reconfiguring the device */ + dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 1); + is_loop = is_loop_device(file); error = loop_global_lock_killable(lo, is_loop); if (error) @@ -790,13 +794,18 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, fput(old_file); if (partscan) loop_reread_partitions(lo); - return 0; + + error = 0; +done: + /* enable and uncork uevent now that we are done */ + dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0); + return error;

out_err: loop_global_unlock(lo, is_loop); out_putf: fput(file); - return error; + goto done; }

/* loop sysfs attributes */ @@ -1203,6 +1212,9 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, /* This is safe, since we have a reference from open(). */ __module_get(THIS_MODULE);

+ /* suppress uevents while reconfiguring the device */ + dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 1); + /* * If we don't hold exclusive handle for the device, upgrade to it * here to avoid changing device under exclusive owner. @@ -1309,7 +1321,12 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, loop_reread_partitions(lo); if (!(mode & FMODE_EXCL)) bd_abort_claiming(bdev, loop_configure); - return 0; + + error = 0; +done: + /* enable and uncork uevent now that we are done */ + dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0); + return error;

out_unlock: loop_global_unlock(lo, is_loop); @@ -1320,7 +1337,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, fput(file); /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); - return error; + goto done; }

static int __loop_clr_fd(struct loop_device *lo, bool release)

From: Sven Auhagen sven.auhagen@voleatech.de

[ Upstream commit 9a251cae51d57289908222e6c322ca61fccc25fd ]

Add missing IP Fragmentation Flag.

Fixes: f9358e12a0af ("net: mvpp2: split ingress traffic into multiple flows") Signed-off-by: Sven Auhagen sven.auhagen@voleatech.de Reviewed-by: Marcin Wojtas mw@semihalf.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/ethernet/marvell/mvpp2/mvpp2_cls.c | 30 +++++++++++-------- 1 file changed, 18 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c index 41d935d1aaf6f..40aeaa7bd739f 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c @@ -62,35 +62,38 @@ static const struct mvpp2_cls_flow cls_flows[MVPP2_N_PRS_FLOWS] = { MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_FRAG_UNTAG, MVPP22_CLS_HEK_IP4_2T, MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4 | - MVPP2_PRS_RI_L4_TCP, + MVPP2_PRS_RI_IP_FRAG_TRUE | MVPP2_PRS_RI_L4_TCP, MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),

MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_FRAG_UNTAG, MVPP22_CLS_HEK_IP4_2T, MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT | - MVPP2_PRS_RI_L4_TCP, + MVPP2_PRS_RI_IP_FRAG_TRUE | MVPP2_PRS_RI_L4_TCP, MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),

MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_FRAG_UNTAG, MVPP22_CLS_HEK_IP4_2T, MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER | - MVPP2_PRS_RI_L4_TCP, + MVPP2_PRS_RI_IP_FRAG_TRUE | MVPP2_PRS_RI_L4_TCP, MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),

/* TCP over IPv4 flows, fragmented, with vlan tag */ MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_FRAG_TAG, MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_TAGGED, - MVPP2_PRS_RI_L3_IP4 | MVPP2_PRS_RI_L4_TCP, + MVPP2_PRS_RI_L3_IP4 | MVPP2_PRS_RI_IP_FRAG_TRUE | + MVPP2_PRS_RI_L4_TCP, MVPP2_PRS_IP_MASK),

MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_FRAG_TAG, MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_TAGGED, - MVPP2_PRS_RI_L3_IP4_OPT | MVPP2_PRS_RI_L4_TCP, + MVPP2_PRS_RI_L3_IP4_OPT | MVPP2_PRS_RI_IP_FRAG_TRUE | + MVPP2_PRS_RI_L4_TCP, MVPP2_PRS_IP_MASK),

MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_FRAG_TAG, MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_TAGGED, - MVPP2_PRS_RI_L3_IP4_OTHER | MVPP2_PRS_RI_L4_TCP, + MVPP2_PRS_RI_L3_IP4_OTHER | MVPP2_PRS_RI_IP_FRAG_TRUE | + MVPP2_PRS_RI_L4_TCP, MVPP2_PRS_IP_MASK),

/* UDP over IPv4 flows, Not fragmented, no vlan tag */ @@ -132,35 +135,38 @@ static const struct mvpp2_cls_flow cls_flows[MVPP2_N_PRS_FLOWS] = { MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_FRAG_UNTAG, MVPP22_CLS_HEK_IP4_2T, MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4 | - MVPP2_PRS_RI_L4_UDP, + MVPP2_PRS_RI_IP_FRAG_TRUE | MVPP2_PRS_RI_L4_UDP, MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),

MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_FRAG_UNTAG, MVPP22_CLS_HEK_IP4_2T, MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT | - MVPP2_PRS_RI_L4_UDP, + MVPP2_PRS_RI_IP_FRAG_TRUE | MVPP2_PRS_RI_L4_UDP, MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),

MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_FRAG_UNTAG, MVPP22_CLS_HEK_IP4_2T, MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER | - MVPP2_PRS_RI_L4_UDP, + MVPP2_PRS_RI_IP_FRAG_TRUE | MVPP2_PRS_RI_L4_UDP, MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),

/* UDP over IPv4 flows, fragmented, with vlan tag */ MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_FRAG_TAG, MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_TAGGED, - MVPP2_PRS_RI_L3_IP4 | MVPP2_PRS_RI_L4_UDP, + MVPP2_PRS_RI_L3_IP4 | MVPP2_PRS_RI_IP_FRAG_TRUE | + MVPP2_PRS_RI_L4_UDP, MVPP2_PRS_IP_MASK),

MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_FRAG_TAG, MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_TAGGED, - MVPP2_PRS_RI_L3_IP4_OPT | MVPP2_PRS_RI_L4_UDP, + MVPP2_PRS_RI_L3_IP4_OPT | MVPP2_PRS_RI_IP_FRAG_TRUE | + MVPP2_PRS_RI_L4_UDP, MVPP2_PRS_IP_MASK),

MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_FRAG_TAG, MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_TAGGED, - MVPP2_PRS_RI_L3_IP4_OTHER | MVPP2_PRS_RI_L4_UDP, + MVPP2_PRS_RI_L3_IP4_OTHER | MVPP2_PRS_RI_IP_FRAG_TRUE | + MVPP2_PRS_RI_L4_UDP, MVPP2_PRS_IP_MASK),

/* TCP over IPv6 flows, not fragmented, no vlan tag */

From: Sven Auhagen sven.auhagen@voleatech.de

[ Upstream commit 031a416c2170866be5132ae42e14453d669b0cb1 ]

In PPPoE add all IPv4 header option length to the parser and adjust the L3 and L4 offset accordingly. Currently the L4 match does not work with PPPoE and all packets are matched as L3 IP4 OPT.

Fixes: 3f518509dedc ("ethernet: Add new driver for Marvell Armada 375 network unit") Signed-off-by: Sven Auhagen sven.auhagen@voleatech.de Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/ethernet/marvell/mvpp2/mvpp2_prs.c | 82 ++++++++----------- 1 file changed, 34 insertions(+), 48 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c index 34d2714205977..a8188b972ccbc 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c @@ -1607,59 +1607,45 @@ static int mvpp2_prs_vlan_init(struct platform_device *pdev, struct mvpp2 *priv) static int mvpp2_prs_pppoe_init(struct mvpp2 *priv) { struct mvpp2_prs_entry pe; - int tid; - - /* IPv4 over PPPoE with options */ - tid = mvpp2_prs_tcam_first_free(priv, MVPP2_PE_FIRST_FREE_TID, - MVPP2_PE_LAST_FREE_TID); - if (tid < 0) - return tid; - - memset(&pe, 0, sizeof(pe)); - mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_PPPOE); - pe.index = tid; - - mvpp2_prs_match_etype(&pe, 0, PPP_IP); - - mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_IP4); - mvpp2_prs_sram_ri_update(&pe, MVPP2_PRS_RI_L3_IP4_OPT, - MVPP2_PRS_RI_L3_PROTO_MASK); - /* goto ipv4 dest-address (skip eth_type + IP-header-size - 4) */ - mvpp2_prs_sram_shift_set(&pe, MVPP2_ETH_TYPE_LEN + - sizeof(struct iphdr) - 4, - MVPP2_PRS_SRAM_OP_SEL_SHIFT_ADD); - /* Set L3 offset */ - mvpp2_prs_sram_offset_set(&pe, MVPP2_PRS_SRAM_UDF_TYPE_L3, - MVPP2_ETH_TYPE_LEN, - MVPP2_PRS_SRAM_OP_SEL_UDF_ADD); - - /* Update shadow table and hw entry */ - mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_PPPOE); - mvpp2_prs_hw_write(priv, &pe); + int tid, ihl;

- /* IPv4 over PPPoE without options */ - tid = mvpp2_prs_tcam_first_free(priv, MVPP2_PE_FIRST_FREE_TID, - MVPP2_PE_LAST_FREE_TID); - if (tid < 0) - return tid; + /* IPv4 over PPPoE with header length >= 5 */ + for (ihl = MVPP2_PRS_IPV4_IHL_MIN; ihl <= MVPP2_PRS_IPV4_IHL_MAX; ihl++) { + tid = mvpp2_prs_tcam_first_free(priv, MVPP2_PE_FIRST_FREE_TID, + MVPP2_PE_LAST_FREE_TID); + if (tid < 0) + return tid;

- pe.index = tid; + memset(&pe, 0, sizeof(pe)); + mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_PPPOE); + pe.index = tid;

- mvpp2_prs_tcam_data_byte_set(&pe, MVPP2_ETH_TYPE_LEN, - MVPP2_PRS_IPV4_HEAD | - MVPP2_PRS_IPV4_IHL_MIN, - MVPP2_PRS_IPV4_HEAD_MASK | - MVPP2_PRS_IPV4_IHL_MASK); + mvpp2_prs_match_etype(&pe, 0, PPP_IP); + mvpp2_prs_tcam_data_byte_set(&pe, MVPP2_ETH_TYPE_LEN, + MVPP2_PRS_IPV4_HEAD | ihl, + MVPP2_PRS_IPV4_HEAD_MASK | + MVPP2_PRS_IPV4_IHL_MASK);

- /* Clear ri before updating */ - pe.sram[MVPP2_PRS_SRAM_RI_WORD] = 0x0; - pe.sram[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0; - mvpp2_prs_sram_ri_update(&pe, MVPP2_PRS_RI_L3_IP4, - MVPP2_PRS_RI_L3_PROTO_MASK); + mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_IP4); + mvpp2_prs_sram_ri_update(&pe, MVPP2_PRS_RI_L3_IP4, + MVPP2_PRS_RI_L3_PROTO_MASK); + /* goto ipv4 dst-address (skip eth_type + IP-header-size - 4) */ + mvpp2_prs_sram_shift_set(&pe, MVPP2_ETH_TYPE_LEN + + sizeof(struct iphdr) - 4, + MVPP2_PRS_SRAM_OP_SEL_SHIFT_ADD); + /* Set L3 offset */ + mvpp2_prs_sram_offset_set(&pe, MVPP2_PRS_SRAM_UDF_TYPE_L3, + MVPP2_ETH_TYPE_LEN, + MVPP2_PRS_SRAM_OP_SEL_UDF_ADD); + /* Set L4 offset */ + mvpp2_prs_sram_offset_set(&pe, MVPP2_PRS_SRAM_UDF_TYPE_L4, + MVPP2_ETH_TYPE_LEN + (ihl * 4), + MVPP2_PRS_SRAM_OP_SEL_UDF_ADD);

- /* Update shadow table and hw entry */ - mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_PPPOE); - mvpp2_prs_hw_write(priv, &pe); + /* Update shadow table and hw entry */ + mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_PPPOE); + mvpp2_prs_hw_write(priv, &pe); + }

/* IPv6 over PPPoE */ tid = mvpp2_prs_tcam_first_free(priv, MVPP2_PE_FIRST_FREE_TID,

From: Junfeng Guo junfeng.guo@intel.com

[ Upstream commit 29486b6df3e6a63b57d1ed1dce06051267282ff4 ]

Add profile conflict check while adding some FDIR rules to avoid unexpected flow behavior, rules may have conflict including: IPv4 <---> {IPv4_UDP, IPv4_TCP, IPv4_SCTP} IPv6 <---> {IPv6_UDP, IPv6_TCP, IPv6_SCTP}

For example, when we create an FDIR rule for IPv4, this rule will work on packets including IPv4, IPv4_UDP, IPv4_TCP and IPv4_SCTP. But if we then create an FDIR rule for IPv4_UDP and then destroy it, the first FDIR rule for IPv4 cannot work on pkt IPv4_UDP then.

To prevent this unexpected behavior, we add restriction in software when creating FDIR rules by adding necessary profile conflict check.

Fixes: 1f7ea1cd6a37 ("ice: Enable FDIR Configure for AVF") Signed-off-by: Junfeng Guo junfeng.guo@intel.com Tested-by: Rafal Romanowski rafal.romanowski@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../ethernet/intel/ice/ice_virtchnl_fdir.c | 73 +++++++++++++++++++ 1 file changed, 73 insertions(+)

diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c index eee180d8c0247..4b738f7391097 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c @@ -731,6 +731,72 @@ static void ice_vc_fdir_rem_prof_all(struct ice_vf *vf) } }

+/** + * ice_vc_fdir_has_prof_conflict + * @vf: pointer to the VF structure + * @conf: FDIR configuration for each filter + * + * Check if @conf has conflicting profile with existing profiles + * + * Return: true on success, and false on error. + */ +static bool +ice_vc_fdir_has_prof_conflict(struct ice_vf *vf, + struct virtchnl_fdir_fltr_conf *conf) +{ + struct ice_fdir_fltr *desc; + + list_for_each_entry(desc, &vf->fdir.fdir_rule_list, fltr_node) { + struct virtchnl_fdir_fltr_conf *existing_conf; + enum ice_fltr_ptype flow_type_a, flow_type_b; + struct ice_fdir_fltr *a, *b; + + existing_conf = to_fltr_conf_from_desc(desc); + a = &existing_conf->input; + b = &conf->input; + flow_type_a = a->flow_type; + flow_type_b = b->flow_type; + + /* No need to compare two rules with different tunnel types or + * with the same protocol type. + */ + if (existing_conf->ttype != conf->ttype || + flow_type_a == flow_type_b) + continue; + + switch (flow_type_a) { + case ICE_FLTR_PTYPE_NONF_IPV4_UDP: + case ICE_FLTR_PTYPE_NONF_IPV4_TCP: + case ICE_FLTR_PTYPE_NONF_IPV4_SCTP: + if (flow_type_b == ICE_FLTR_PTYPE_NONF_IPV4_OTHER) + return true; + break; + case ICE_FLTR_PTYPE_NONF_IPV4_OTHER: + if (flow_type_b == ICE_FLTR_PTYPE_NONF_IPV4_UDP || + flow_type_b == ICE_FLTR_PTYPE_NONF_IPV4_TCP || + flow_type_b == ICE_FLTR_PTYPE_NONF_IPV4_SCTP) + return true; + break; + case ICE_FLTR_PTYPE_NONF_IPV6_UDP: + case ICE_FLTR_PTYPE_NONF_IPV6_TCP: + case ICE_FLTR_PTYPE_NONF_IPV6_SCTP: + if (flow_type_b == ICE_FLTR_PTYPE_NONF_IPV6_OTHER) + return true; + break; + case ICE_FLTR_PTYPE_NONF_IPV6_OTHER: + if (flow_type_b == ICE_FLTR_PTYPE_NONF_IPV6_UDP || + flow_type_b == ICE_FLTR_PTYPE_NONF_IPV6_TCP || + flow_type_b == ICE_FLTR_PTYPE_NONF_IPV6_SCTP) + return true; + break; + default: + break; + } + } + + return false; +} + /** * ice_vc_fdir_write_flow_prof * @vf: pointer to the VF structure @@ -871,6 +937,13 @@ ice_vc_fdir_config_input_set(struct ice_vf *vf, struct virtchnl_fdir_add *fltr, enum ice_fltr_ptype flow; int ret;

+ ret = ice_vc_fdir_has_prof_conflict(vf, conf); + if (ret) { + dev_dbg(dev, "Found flow profile conflict for VF %d\n", + vf->vf_id); + return ret; + } + flow = input->flow_type; ret = ice_vc_fdir_alloc_prof(vf, flow); if (ret) {

From: Tasos Sahanidis tasos@tasossah.com

[ Upstream commit f33fc1576757741479452255132d6e3aaf558ffe ]

snd_card_ymfpci_remove() was removed in commit c6e6bb5eab74 ("ALSA: ymfpci: Allocate resources with device-managed APIs"), but the call to snd_card_new() was not replaced with snd_devm_card_new().

Since there was no longer a call to snd_card_free, unloading the module would eventually result in Oops:

[697561.532887] BUG: unable to handle page fault for address: ffffffffc0924480 [697561.532893] #PF: supervisor read access in kernel mode [697561.532896] #PF: error_code(0x0000) - not-present page [697561.532899] PGD ae1e15067 P4D ae1e15067 PUD ae1e17067 PMD 11a8f5067 PTE 0 [697561.532905] Oops: 0000 [#1] PREEMPT SMP NOPTI [697561.532909] CPU: 21 PID: 5080 Comm: wireplumber Tainted: G W OE 6.2.7 #1 [697561.532914] Hardware name: System manufacturer System Product Name/TUF GAMING X570-PLUS, BIOS 4408 10/28/2022 [697561.532916] RIP: 0010:try_module_get.part.0+0x1a/0xe0 [697561.532924] Code: 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 55 48 89 e5 41 55 41 54 49 89 fc bf 01 00 00 00 e8 56 3c f8 ff <41> 83 3c 24 02 0f 84 96 00 00 00 41 8b 84 24 30 03 00 00 85 c0 0f [697561.532927] RSP: 0018:ffffbe9b858c3bd8 EFLAGS: 00010246 [697561.532930] RAX: ffff9815d14f1900 RBX: ffff9815c14e6000 RCX: 0000000000000000 [697561.532933] RDX: 0000000000000000 RSI: ffffffffc055092c RDI: ffffffffb3778c1a [697561.532935] RBP: ffffbe9b858c3be8 R08: 0000000000000040 R09: ffff981a1a741380 [697561.532937] R10: ffffbe9b858c3c80 R11: 00000009d56533a6 R12: ffffffffc0924480 [697561.532939] R13: ffff9823439d8500 R14: 0000000000000025 R15: ffff9815cd109f80 [697561.532942] FS: 00007f13084f1f80(0000) GS:ffff9824aef40000(0000) knlGS:0000000000000000 [697561.532945] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [697561.532947] CR2: ffffffffc0924480 CR3: 0000000145344000 CR4: 0000000000350ee0 [697561.532949] Call Trace: [697561.532951] <TASK> [697561.532955] try_module_get+0x13/0x30 [697561.532960] snd_ctl_open+0x61/0x1c0 [snd] [697561.532976] snd_open+0xb4/0x1e0 [snd] [697561.532989] chrdev_open+0xc7/0x240 [697561.532995] ? fsnotify_perm.part.0+0x6e/0x160 [697561.533000] ? __pfx_chrdev_open+0x10/0x10 [697561.533005] do_dentry_open+0x169/0x440 [697561.533009] vfs_open+0x2d/0x40 [697561.533012] path_openat+0xa9d/0x10d0 [697561.533017] ? debug_smp_processor_id+0x17/0x20 [697561.533022] ? trigger_load_balance+0x65/0x370 [697561.533026] do_filp_open+0xb2/0x160 [697561.533032] ? _raw_spin_unlock+0x19/0x40 [697561.533036] ? alloc_fd+0xa9/0x190 [697561.533040] do_sys_openat2+0x9f/0x160 [697561.533044] __x64_sys_openat+0x55/0x90 [697561.533048] do_syscall_64+0x3b/0x90 [697561.533052] entry_SYSCALL_64_after_hwframe+0x72/0xdc [697561.533056] RIP: 0033:0x7f1308a40db4 [697561.533059] Code: 24 20 eb 8f 66 90 44 89 54 24 0c e8 46 68 f8 ff 44 8b 54 24 0c 44 89 e2 48 89 ee 41 89 c0 bf 9c ff ff ff b8 01 01 00 00 0f 05 <48> 3d 00 f0 ff ff 77 32 44 89 c7 89 44 24 0c e8 78 68 f8 ff 8b 44 [697561.533062] RSP: 002b:00007ffcce664450 EFLAGS: 00000293 ORIG_RAX: 0000000000000101 [697561.533066] RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f1308a40db4 [697561.533068] RDX: 0000000000080000 RSI: 00007ffcce664690 RDI: 00000000ffffff9c [697561.533070] RBP: 00007ffcce664690 R08: 0000000000000000 R09: 0000000000000012 [697561.533072] R10: 0000000000000000 R11: 0000000000000293 R12: 0000000000080000 [697561.533074] R13: 00007f13054b069b R14: 0000565209f83200 R15: 0000000000000000 [697561.533078] </TASK>

Fixes: c6e6bb5eab74 ("ALSA: ymfpci: Allocate resources with device-managed APIs") Signed-off-by: Tasos Sahanidis tasos@tasossah.com Link: https://lore.kernel.org/r/20230329032422.170024-1-tasos@tasossah.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/pci/ymfpci/ymfpci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/pci/ymfpci/ymfpci.c b/sound/pci/ymfpci/ymfpci.c index 1e198e4d57b8d..82d4e0fda91be 100644 --- a/sound/pci/ymfpci/ymfpci.c +++ b/sound/pci/ymfpci/ymfpci.c @@ -170,7 +170,7 @@ static int snd_card_ymfpci_probe(struct pci_dev *pci, return -ENOENT; }

- err = snd_card_new(&pci->dev, index[dev], id[dev], THIS_MODULE, + err = snd_devm_card_new(&pci->dev, index[dev], id[dev], THIS_MODULE, sizeof(*chip), &card); if (err < 0) return err;

From: Alex Elder elder@linaro.org

[ Upstream commit 6c75dc94f2b27fff57b305af9236eea181a00b6c ]

In gsi_trans_pool_init_dma(), the total size of a pool of memory used for DMA transactions is calculated. However the calculation is done incorrectly.

For 4KB pages, this total size is currently always more than one page, and as a result, the calculation produces a positive (though incorrect) total size. The code still works in this case; we just end up with fewer DMA pool entries than we intended.

Bjorn Andersson tested booting a kernel with 16KB pages, and hit a null pointer derereference in sg_alloc_append_table_from_pages(), descending from gsi_trans_pool_init_dma(). The cause of this was that a 16KB total size was going to be allocated, and with 16KB pages the order of that allocation is 0. The total_size calculation yielded 0, which eventually led to the crash.

Correcting the total_size calculation fixes the problem.

Reported-by: Bjorn Andersson quic_bjorande@quicinc.com Tested-by: Bjorn Andersson quic_bjorande@quicinc.com Fixes: 9dd441e4ed57 ("soc: qcom: ipa: GSI transactions") Reviewed-by: Mark Bloch mbloch@nvidia.com Signed-off-by: Alex Elder elder@linaro.org Reviewed-by: Leon Romanovsky leonro@nvidia.com Link: https://lore.kernel.org/r/20230328162751.2861791-1-elder@linaro.org Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ipa/gsi_trans.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ipa/gsi_trans.c b/drivers/net/ipa/gsi_trans.c index 1544564bc2835..d709e69181959 100644 --- a/drivers/net/ipa/gsi_trans.c +++ b/drivers/net/ipa/gsi_trans.c @@ -155,7 +155,7 @@ int gsi_trans_pool_init_dma(struct device *dev, struct gsi_trans_pool *pool, * gsi_trans_pool_exit_dma() can assume the total allocated * size is exactly (count * size). */ - total_size = get_order(total_size) << PAGE_SHIFT; + total_size = PAGE_SIZE << get_order(total_size);

virt = dma_alloc_coherent(dev, total_size, &addr, GFP_KERNEL); if (!virt)

From: Kalesh AP kalesh-anakkur.purayil@broadcom.com

[ Upstream commit 83714dc3db0e4a088673601bc8099b079bc1a077 ]

When the selftest command fails, driver is not reporting the failure by updating the "test->flags" when bnxt_close_nic() fails.

Fixes: eb51365846bc ("bnxt_en: Add basic ethtool -t selftest support.") Reviewed-by: Pavan Chebbi pavan.chebbi@broadcom.com Reviewed-by: Somnath Kotur somnath.kotur@broadcom.com Signed-off-by: Kalesh AP kalesh-anakkur.purayil@broadcom.com Signed-off-by: Michael Chan michael.chan@broadcom.com Reviewed-by: Simon Horman simon.horman@corigine.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 586311a271f21..9ac5f63784960 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -3504,6 +3504,7 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest, bnxt_ulp_stop(bp); rc = bnxt_close_nic(bp, true, false); if (rc) { + etest->flags |= ETH_TEST_FL_FAILED; bnxt_ulp_start(bp, rc); return; }

From: Michael Chan michael.chan@broadcom.com

[ Upstream commit 581bce7bcb7e7f100908728e7b292e266c76895b ]

bnxt_fw_to_ethtool_speed() is missing the case statement for 200G link speed reported by firmware. As a result, ethtool will report unknown speed when the firmware reports 200G link speed.

Fixes: 532262ba3b84 ("bnxt_en: ethtool: support PAM4 link speeds up to 200G") Signed-off-by: Michael Chan michael.chan@broadcom.com Reviewed-by: Simon Horman simon.horman@corigine.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/broadcom/bnxt/bnxt.h | 1 + drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 2 ++ 2 files changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index e5874c829226e..ae4695fc067d5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1202,6 +1202,7 @@ struct bnxt_link_info { #define BNXT_LINK_SPEED_40GB PORT_PHY_QCFG_RESP_LINK_SPEED_40GB #define BNXT_LINK_SPEED_50GB PORT_PHY_QCFG_RESP_LINK_SPEED_50GB #define BNXT_LINK_SPEED_100GB PORT_PHY_QCFG_RESP_LINK_SPEED_100GB +#define BNXT_LINK_SPEED_200GB PORT_PHY_QCFG_RESP_LINK_SPEED_200GB u16 support_speeds; u16 support_pam4_speeds; u16 auto_link_speeds; /* fw adv setting */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 9ac5f63784960..bc9812a0a91c3 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -1670,6 +1670,8 @@ u32 bnxt_fw_to_ethtool_speed(u16 fw_link_speed) return SPEED_50000; case BNXT_LINK_SPEED_100GB: return SPEED_100000; + case BNXT_LINK_SPEED_200GB: + return SPEED_200000; default: return SPEED_UNKNOWN; }

From: Felix Fietkau nbd@nbd.name

[ Upstream commit 8c1cb87c2a5c29da416848451a687473f379611c ]

Since we call flow_block_cb_decref on FLOW_BLOCK_UNBIND, we also need to call flow_block_cb_incref for a newly allocated cb. Also fix the accidentally inverted refcount check on unbind.

Fixes: 502e84e2382d ("net: ethernet: mtk_eth_soc: add flow offloading support") Reviewed-by: Simon Horman simon.horman@corigine.com Signed-off-by: Felix Fietkau nbd@nbd.name Reviewed-by: Leon Romanovsky leonro@nvidia.com Link: https://lore.kernel.org/r/20230330120840.52079-1-nbd@nbd.name Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mediatek/mtk_ppe_offload.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c index 7bb1f20002b58..7c5403c010715 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c @@ -462,6 +462,7 @@ mtk_eth_setup_tc_block(struct net_device *dev, struct flow_block_offload *f) if (IS_ERR(block_cb)) return PTR_ERR(block_cb);

+ flow_block_cb_incref(block_cb); flow_block_cb_add(block_cb, f); list_add_tail(&block_cb->driver_list, &block_cb_list); return 0; @@ -470,7 +471,7 @@ mtk_eth_setup_tc_block(struct net_device *dev, struct flow_block_offload *f) if (!block_cb) return -ENOENT;

- if (flow_block_cb_decref(block_cb)) { + if (!flow_block_cb_decref(block_cb)) { flow_block_cb_remove(block_cb, f); list_del(&block_cb->driver_list); }

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

[ Upstream commit bfd3c6b9fa4a1dc78139dd1621d5bea321ffa69d ]

The VT-d spec states (in section 11.4.2) that hardware implementations reporting second-stage translation support (SSTS) field as Clear also report the SAGAW field as 0. Fix an inappropriate check in alloc_iommu().

Fixes: 792fb43ce2c9 ("iommu/vt-d: Enable Intel IOMMU scalable mode by default") Suggested-by: Raghunathan Srinivasan raghunathan.srinivasan@intel.com Reviewed-by: Kevin Tian kevin.tian@intel.com Signed-off-by: Jacob Pan jacob.jun.pan@linux.intel.com Signed-off-by: Lu Baolu baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20230318024824.124542-1-baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20230329134721.469447-3-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel jroedel@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/iommu/intel/dmar.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index bff2420fc3e14..7c20083d4a798 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -1080,7 +1080,8 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd) }

err = -EINVAL; - if (cap_sagaw(iommu->cap) == 0) { + if (!cap_sagaw(iommu->cap) && + (!ecap_smts(iommu->ecap) || ecap_slts(iommu->ecap))) { pr_info("%s: No supported address widths. Not attempting DMA translation.\n", iommu->name); drhd->ignored = 1;

From: Jason A. Donenfeld Jason@zx2c4.com

commit 8980f190947ba29f23110408e712444884b74251 upstream.

The recent change of -funsigned-char causes additions of negative numbers to become additions of large positive numbers, leading to wrong calculations of mouse movement. Change these casts to be explicitly signed, to take into account negative offsets.

Fixes: 3bc753c06dd0 ("kbuild: treat char as always unsigned") Signed-off-by: Jason A. Donenfeld Jason@zx2c4.com Reviewed-by: Hans de Goede hdegoede@redhat.com Cc: stable@vger.kernel.org Link: https://bugzilla.kernel.org/show_bug.cgi?id=217211 Link: https://lore.kernel.org/r/20230318133010.1285202-1-Jason@zx2c4.com Signed-off-by: Dmitry Torokhov dmitry.torokhov@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/input/mouse/focaltech.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

--- a/drivers/input/mouse/focaltech.c +++ b/drivers/input/mouse/focaltech.c @@ -202,8 +202,8 @@ static void focaltech_process_rel_packet state->pressed = packet[0] >> 7; finger1 = ((packet[0] >> 4) & 0x7) - 1; if (finger1 < FOC_MAX_FINGERS) { - state->fingers[finger1].x += (char)packet[1]; - state->fingers[finger1].y += (char)packet[2]; + state->fingers[finger1].x += (s8)packet[1]; + state->fingers[finger1].y += (s8)packet[2]; } else { psmouse_err(psmouse, "First finger in rel packet invalid: %d\n", finger1); @@ -218,8 +218,8 @@ static void focaltech_process_rel_packet */ finger2 = ((packet[3] >> 4) & 0x7) - 1; if (finger2 < FOC_MAX_FINGERS) { - state->fingers[finger2].x += (char)packet[4]; - state->fingers[finger2].y += (char)packet[5]; + state->fingers[finger2].x += (s8)packet[4]; + state->fingers[finger2].y += (s8)packet[5]; } }

From: David Disseldorp ddiss@suse.de

commit 179a88a8558bbf42991d361595281f3e45d7edfc upstream.

When compiled with CONFIG_CIFS_DFS_UPCALL disabled, cifs_dfs_d_automount is NULL. cifs.ko logic for mapping CIFS_FATTR_DFS_REFERRAL attributes to S_AUTOMOUNT and corresponding dentry flags is retained regardless of CONFIG_CIFS_DFS_UPCALL, leading to a NULL pointer dereference in VFS follow_automount() when traversing a DFS referral link: BUG: kernel NULL pointer dereference, address: 0000000000000000 ... Call Trace: <TASK> __traverse_mounts+0xb5/0x220 ? cifs_revalidate_mapping+0x65/0xc0 [cifs] step_into+0x195/0x610 ? lookup_fast+0xe2/0xf0 path_lookupat+0x64/0x140 filename_lookup+0xc2/0x140 ? __create_object+0x299/0x380 ? kmem_cache_alloc+0x119/0x220 ? user_path_at_empty+0x31/0x50 user_path_at_empty+0x31/0x50 __x64_sys_chdir+0x2a/0xd0 ? exit_to_user_mode_prepare+0xca/0x100 do_syscall_64+0x42/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc

This fix adds an inline cifs_dfs_d_automount() {return -EREMOTE} handler when CONFIG_CIFS_DFS_UPCALL is disabled. An alternative would be to avoid flagging S_AUTOMOUNT, etc. without CONFIG_CIFS_DFS_UPCALL. This approach was chosen as it provides more control over the error path.

Signed-off-by: David Disseldorp ddiss@suse.de Cc: stable@vger.kernel.org Reviewed-by: Paulo Alcantara (SUSE) pc@manguebit.com Reviewed-by: Ronnie Sahlberg lsahlber@redhat.com Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/cifs/cifsfs.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

--- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -118,7 +118,10 @@ extern const struct dentry_operations ci #ifdef CONFIG_CIFS_DFS_UPCALL extern struct vfsmount *cifs_dfs_d_automount(struct path *path); #else -#define cifs_dfs_d_automount NULL +static inline struct vfsmount *cifs_dfs_d_automount(struct path *path) +{ + return ERR_PTR(-EREMOTE); +} #endif

/* Functions related to symlinks */

From: Filipe Manana fdmanana@suse.com

commit 2f1a6be12ab6c8470d5776e68644726c94257c54 upstream.

The quota assign ioctl can currently run in parallel with a quota disable ioctl call. The assign ioctl uses the quota root, while the disable ioctl frees that root, and therefore we can have a use-after-free triggered in the assign ioctl, leading to a trace like the following when KASAN is enabled:

[672.723][T736] BUG: KASAN: slab-use-after-free in btrfs_search_slot+0x2962/0x2db0 [672.723][T736] Read of size 8 at addr ffff888022ec0208 by task btrfs_search_sl/27736 [672.724][T736] [672.725][T736] CPU: 1 PID: 27736 Comm: btrfs_search_sl Not tainted 6.3.0-rc3 #37 [672.723][T736] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 [672.727][T736] Call Trace: [672.728][T736] <TASK> [672.728][T736] dump_stack_lvl+0xd9/0x150 [672.725][T736] print_report+0xc1/0x5e0 [672.720][T736] ? __virt_addr_valid+0x61/0x2e0 [672.727][T736] ? __phys_addr+0xc9/0x150 [672.725][T736] ? btrfs_search_slot+0x2962/0x2db0 [672.722][T736] kasan_report+0xc0/0xf0 [672.729][T736] ? btrfs_search_slot+0x2962/0x2db0 [672.724][T736] btrfs_search_slot+0x2962/0x2db0 [672.723][T736] ? fs_reclaim_acquire+0xba/0x160 [672.722][T736] ? split_leaf+0x13d0/0x13d0 [672.726][T736] ? rcu_is_watching+0x12/0xb0 [672.723][T736] ? kmem_cache_alloc+0x338/0x3c0 [672.722][T736] update_qgroup_status_item+0xf7/0x320 [672.724][T736] ? add_qgroup_rb+0x3d0/0x3d0 [672.739][T736] ? do_raw_spin_lock+0x12d/0x2b0 [672.730][T736] ? spin_bug+0x1d0/0x1d0 [672.737][T736] btrfs_run_qgroups+0x5de/0x840 [672.730][T736] ? btrfs_qgroup_rescan_worker+0xa70/0xa70 [672.738][T736] ? __del_qgroup_relation+0x4ba/0xe00 [672.738][T736] btrfs_ioctl+0x3d58/0x5d80 [672.735][T736] ? tomoyo_path_number_perm+0x16a/0x550 [672.737][T736] ? tomoyo_execute_permission+0x4a0/0x4a0 [672.731][T736] ? btrfs_ioctl_get_supported_features+0x50/0x50 [672.737][T736] ? __sanitizer_cov_trace_switch+0x54/0x90 [672.734][T736] ? do_vfs_ioctl+0x132/0x1660 [672.730][T736] ? vfs_fileattr_set+0xc40/0xc40 [672.730][T736] ? _raw_spin_unlock_irq+0x2e/0x50 [672.732][T736] ? sigprocmask+0xf2/0x340 [672.737][T736] ? __fget_files+0x26a/0x480 [672.732][T736] ? bpf_lsm_file_ioctl+0x9/0x10 [672.738][T736] ? btrfs_ioctl_get_supported_features+0x50/0x50 [672.736][T736] __x64_sys_ioctl+0x198/0x210 [672.736][T736] do_syscall_64+0x39/0xb0 [672.731][T736] entry_SYSCALL_64_after_hwframe+0x63/0xcd [672.739][T736] RIP: 0033:0x4556ad [672.742][T736] </TASK> [672.743][T736] [672.748][T736] Allocated by task 27677: [672.743][T736] kasan_save_stack+0x22/0x40 [672.741][T736] kasan_set_track+0x25/0x30 [672.741][T736] __kasan_kmalloc+0xa4/0xb0 [672.749][T736] btrfs_alloc_root+0x48/0x90 [672.746][T736] btrfs_create_tree+0x146/0xa20 [672.744][T736] btrfs_quota_enable+0x461/0x1d20 [672.743][T736] btrfs_ioctl+0x4a1c/0x5d80 [672.747][T736] __x64_sys_ioctl+0x198/0x210 [672.749][T736] do_syscall_64+0x39/0xb0 [672.744][T736] entry_SYSCALL_64_after_hwframe+0x63/0xcd [672.756][T736] [672.757][T736] Freed by task 27677: [672.759][T736] kasan_save_stack+0x22/0x40 [672.759][T736] kasan_set_track+0x25/0x30 [672.756][T736] kasan_save_free_info+0x2e/0x50 [672.751][T736] ____kasan_slab_free+0x162/0x1c0 [672.758][T736] slab_free_freelist_hook+0x89/0x1c0 [672.752][T736] __kmem_cache_free+0xaf/0x2e0 [672.752][T736] btrfs_put_root+0x1ff/0x2b0 [672.759][T736] btrfs_quota_disable+0x80a/0xbc0 [672.752][T736] btrfs_ioctl+0x3e5f/0x5d80 [672.756][T736] __x64_sys_ioctl+0x198/0x210 [672.753][T736] do_syscall_64+0x39/0xb0 [672.765][T736] entry_SYSCALL_64_after_hwframe+0x63/0xcd [672.769][T736] [672.768][T736] The buggy address belongs to the object at ffff888022ec0000 [672.768][T736] which belongs to the cache kmalloc-4k of size 4096 [672.769][T736] The buggy address is located 520 bytes inside of [672.769][T736] freed 4096-byte region [ffff888022ec0000, ffff888022ec1000) [672.760][T736] [672.764][T736] The buggy address belongs to the physical page: [672.761][T736] page:ffffea00008bb000 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x22ec0 [672.766][T736] head:ffffea00008bb000 order:3 entire_mapcount:0 nr_pages_mapped:0 pincount:0 [672.779][T736] flags: 0xfff00000010200(slab|head|node=0|zone=1|lastcpupid=0x7ff) [672.770][T736] raw: 00fff00000010200 ffff888012842140 ffffea000054ba00 dead000000000002 [672.770][T736] raw: 0000000000000000 0000000000040004 00000001ffffffff 0000000000000000 [672.771][T736] page dumped because: kasan: bad access detected [672.778][T736] page_owner tracks the page as allocated [672.777][T736] page last allocated via order 3, migratetype Unmovable, gfp_mask 0xd2040(__GFP_IO|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC), pid 88 [672.779][T736] get_page_from_freelist+0x119c/0x2d50 [672.779][T736] __alloc_pages+0x1cb/0x4a0 [672.776][T736] alloc_pages+0x1aa/0x270 [672.773][T736] allocate_slab+0x260/0x390 [672.771][T736] ___slab_alloc+0xa9a/0x13e0 [672.778][T736] __slab_alloc.constprop.0+0x56/0xb0 [672.771][T736] __kmem_cache_alloc_node+0x136/0x320 [672.789][T736] __kmalloc+0x4e/0x1a0 [672.783][T736] tomoyo_realpath_from_path+0xc3/0x600 [672.781][T736] tomoyo_path_perm+0x22f/0x420 [672.782][T736] tomoyo_path_unlink+0x92/0xd0 [672.780][T736] security_path_unlink+0xdb/0x150 [672.788][T736] do_unlinkat+0x377/0x680 [672.788][T736] __x64_sys_unlink+0xca/0x110 [672.789][T736] do_syscall_64+0x39/0xb0 [672.783][T736] entry_SYSCALL_64_after_hwframe+0x63/0xcd [672.784][T736] page last free stack trace: [672.787][T736] free_pcp_prepare+0x4e5/0x920 [672.787][T736] free_unref_page+0x1d/0x4e0 [672.784][T736] __unfreeze_partials+0x17c/0x1a0 [672.797][T736] qlist_free_all+0x6a/0x180 [672.796][T736] kasan_quarantine_reduce+0x189/0x1d0 [672.797][T736] __kasan_slab_alloc+0x64/0x90 [672.793][T736] kmem_cache_alloc+0x17c/0x3c0 [672.799][T736] getname_flags.part.0+0x50/0x4e0 [672.799][T736] getname_flags+0x9e/0xe0 [672.792][T736] vfs_fstatat+0x77/0xb0 [672.791][T736] __do_sys_newlstat+0x84/0x100 [672.798][T736] do_syscall_64+0x39/0xb0 [672.796][T736] entry_SYSCALL_64_after_hwframe+0x63/0xcd [672.790][T736] [672.791][T736] Memory state around the buggy address: [672.799][T736] ffff888022ec0100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [672.805][T736] ffff888022ec0180: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [672.802][T736] >ffff888022ec0200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [672.809][T736] ^ [672.809][T736] ffff888022ec0280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [672.809][T736] ffff888022ec0300: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

Fix this by having the qgroup assign ioctl take the qgroup ioctl mutex before calling btrfs_run_qgroups(), which is what all qgroup ioctls should call.

Reported-by: butt3rflyh4ck butterflyhuangxx@gmail.com Link: https://lore.kernel.org/linux-btrfs/CAFcO6XN3VD8ogmHwqRk4kbiwtpUSNySu2VAxN8w... CC: stable@vger.kernel.org # 5.10+ Reviewed-by: Qu Wenruo wqu@suse.com Signed-off-by: Filipe Manana fdmanana@suse.com Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/btrfs/ioctl.c | 2 ++ fs/btrfs/qgroup.c | 11 ++++++++++- 2 files changed, 12 insertions(+), 1 deletion(-)

--- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4267,7 +4267,9 @@ static long btrfs_ioctl_qgroup_assign(st }

/* update qgroup status and info */ + mutex_lock(&fs_info->qgroup_ioctl_lock); err = btrfs_run_qgroups(trans); + mutex_unlock(&fs_info->qgroup_ioctl_lock); if (err < 0) btrfs_handle_fs_error(fs_info, err, "failed to update qgroup status and info"); --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -2752,13 +2752,22 @@ cleanup: }

/* - * called from commit_transaction. Writes all changed qgroups to disk. + * Writes all changed qgroups to disk. + * Called by the transaction commit path and the qgroup assign ioctl. */ int btrfs_run_qgroups(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; int ret = 0;

+ /* + * In case we are called from the qgroup assign ioctl, assert that we + * are holding the qgroup_ioctl_lock, otherwise we can race with a quota + * disable operation (ioctl) and access a freed quota root. + */ + if (trans->transaction->state != TRANS_STATE_COMMIT_DOING) + lockdep_assert_held(&fs_info->qgroup_ioctl_lock); + if (!fs_info->quota_root) return ret;

From: Damien Le Moal damien.lemoal@opensource.wdc.com

commit c1976bd8f23016d8706973908f2bb0ac0d852a8f upstream.

When a direct append write is executed, the append offset may correspond to the last page of a sequential file inode which might have been cached already by buffered reads, page faults with mmap-read or non-direct readahead. To ensure that the on-disk and cached data is consistant for such last cached page, make sure to always invalidate it in zonefs_file_dio_append(). If the invalidation fails, return -EBUSY to userspace to differentiate from IO errors.

This invalidation will always be a no-op when the FS block size (device zone write granularity) is equal to the page size (e.g. 4K).

Reported-by: Hans Holmberg Hans.Holmberg@wdc.com Fixes: 02ef12a663c7 ("zonefs: use REQ_OP_ZONE_APPEND for sync DIO") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal damien.lemoal@opensource.wdc.com Reviewed-by: Christoph Hellwig hch@lst.de Reviewed-by: Johannes Thumshirn johannes.thumshirn@wdc.com Tested-by: Hans Holmberg hans.holmberg@wdc.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/zonefs/super.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+)

--- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -736,6 +736,7 @@ static ssize_t zonefs_file_dio_append(st struct zonefs_inode_info *zi = ZONEFS_I(inode); struct block_device *bdev = inode->i_sb->s_bdev; unsigned int max = bdev_max_zone_append_sectors(bdev); + pgoff_t start, end; struct bio *bio; ssize_t size; int nr_pages; @@ -744,6 +745,19 @@ static ssize_t zonefs_file_dio_append(st max = ALIGN_DOWN(max << SECTOR_SHIFT, inode->i_sb->s_blocksize); iov_iter_truncate(from, max);

+ /* + * If the inode block size (zone write granularity) is smaller than the + * page size, we may be appending data belonging to the last page of the + * inode straddling inode->i_size, with that page already cached due to + * a buffered read or readahead. So make sure to invalidate that page. + * This will always be a no-op for the case where the block size is + * equal to the page size. + */ + start = iocb->ki_pos >> PAGE_SHIFT; + end = (iocb->ki_pos + iov_iter_count(from) - 1) >> PAGE_SHIFT; + if (invalidate_inode_pages2_range(inode->i_mapping, start, end)) + return -EBUSY; + nr_pages = iov_iter_npages(from, BIO_MAX_VECS); if (!nr_pages) return 0;

From: Juergen Gross jgross@suse.com

commit 05310f31ca74673a96567fb14637b7d5d6c82ea5 upstream.

Fix xenvif_get_requests() not to do grant copy operations across local page boundaries. This requires to double the maximum number of copy operations per queue, as each copy could now be split into 2.

Make sure that struct xenvif_tx_cb doesn't grow too large.

Cc: stable@vger.kernel.org Fixes: ad7f402ae4f4 ("xen/netback: Ensure protocol headers don't fall in the non-linear area") Signed-off-by: Juergen Gross jgross@suse.com Reviewed-by: Paul Durrant paul@xen.org Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/xen-netback/common.h | 2 +- drivers/net/xen-netback/netback.c | 25 +++++++++++++++++++++++-- 2 files changed, 24 insertions(+), 3 deletions(-)

--- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -166,7 +166,7 @@ struct xenvif_queue { /* Per-queue data struct pending_tx_info pending_tx_info[MAX_PENDING_REQS]; grant_handle_t grant_tx_handle[MAX_PENDING_REQS];

- struct gnttab_copy tx_copy_ops[MAX_PENDING_REQS]; + struct gnttab_copy tx_copy_ops[2 * MAX_PENDING_REQS]; struct gnttab_map_grant_ref tx_map_ops[MAX_PENDING_REQS]; struct gnttab_unmap_grant_ref tx_unmap_ops[MAX_PENDING_REQS]; /* passed to gnttab_[un]map_refs with pages under (un)mapping */ --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -334,6 +334,7 @@ static int xenvif_count_requests(struct struct xenvif_tx_cb { u16 copy_pending_idx[XEN_NETBK_LEGACY_SLOTS_MAX + 1]; u8 copy_count; + u32 split_mask; };

#define XENVIF_TX_CB(skb) ((struct xenvif_tx_cb *)(skb)->cb) @@ -361,6 +362,8 @@ static inline struct sk_buff *xenvif_all struct sk_buff *skb = alloc_skb(size + NET_SKB_PAD + NET_IP_ALIGN, GFP_ATOMIC | __GFP_NOWARN); + + BUILD_BUG_ON(sizeof(*XENVIF_TX_CB(skb)) > sizeof(skb->cb)); if (unlikely(skb == NULL)) return NULL;

@@ -396,11 +399,13 @@ static void xenvif_get_requests(struct x nr_slots = shinfo->nr_frags + 1;

copy_count(skb) = 0; + XENVIF_TX_CB(skb)->split_mask = 0;

/* Create copy ops for exactly data_len bytes into the skb head. */ __skb_put(skb, data_len); while (data_len > 0) { int amount = data_len > txp->size ? txp->size : data_len; + bool split = false;

cop->source.u.ref = txp->gref; cop->source.domid = queue->vif->domid; @@ -413,6 +418,13 @@ static void xenvif_get_requests(struct x cop->dest.u.gmfn = virt_to_gfn(skb->data + skb_headlen(skb) - data_len);

+ /* Don't cross local page boundary! */ + if (cop->dest.offset + amount > XEN_PAGE_SIZE) { + amount = XEN_PAGE_SIZE - cop->dest.offset; + XENVIF_TX_CB(skb)->split_mask |= 1U << copy_count(skb); + split = true; + } + cop->len = amount; cop->flags = GNTCOPY_source_gref;

@@ -420,7 +432,8 @@ static void xenvif_get_requests(struct x pending_idx = queue->pending_ring[index]; callback_param(queue, pending_idx).ctx = NULL; copy_pending_idx(skb, copy_count(skb)) = pending_idx; - copy_count(skb)++; + if (!split) + copy_count(skb)++;

cop++; data_len -= amount; @@ -441,7 +454,8 @@ static void xenvif_get_requests(struct x nr_slots--; } else { /* The copy op partially covered the tx_request. - * The remainder will be mapped. + * The remainder will be mapped or copied in the next + * iteration. */ txp->offset += amount; txp->size -= amount; @@ -539,6 +553,13 @@ static int xenvif_tx_check_gop(struct xe pending_idx = copy_pending_idx(skb, i);

newerr = (*gopp_copy)->status; + + /* Split copies need to be handled together. */ + if (XENVIF_TX_CB(skb)->split_mask & (1U << i)) { + (*gopp_copy)++; + if (!newerr) + newerr = (*gopp_copy)->status; + } if (likely(!newerr)) { /* The first frag might still have this slot mapped */ if (i < copy_count(skb) - 1 || !sharedslot)

From: Kornel Dulęba korneld@chromium.org

commit b26cd9325be4c1fcd331b77f10acb627c560d4d7 upstream.

This fixes a similar problem to the one observed in: commit 4e5a04be88fe ("pinctrl: amd: disable and mask interrupts on probe").

On some systems, during suspend/resume cycle firmware leaves an interrupt enabled on a pin that is not used by the kernel. This confuses the AMD pinctrl driver and causes spurious interrupts.

The driver already has logic to detect if a pin is used by the kernel. Leverage it to re-initialize interrupt fields of a pin only if it's not used by us.

Cc: stable@vger.kernel.org Fixes: dbad75dd1f25 ("pinctrl: add AMD GPIO driver support.") Signed-off-by: Kornel Dulęba korneld@chromium.org Link: https://lore.kernel.org/r/20230320093259.845178-1-korneld@chromium.org Signed-off-by: Linus Walleij linus.walleij@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/pinctrl/pinctrl-amd.c | 36 ++++++++++++++++++++---------------- 1 file changed, 20 insertions(+), 16 deletions(-)

--- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -863,32 +863,34 @@ static const struct pinconf_ops amd_pinc .pin_config_group_set = amd_pinconf_group_set, };

-static void amd_gpio_irq_init(struct amd_gpio *gpio_dev) +static void amd_gpio_irq_init_pin(struct amd_gpio *gpio_dev, int pin) { - struct pinctrl_desc *desc = gpio_dev->pctrl->desc; + const struct pin_desc *pd; unsigned long flags; u32 pin_reg, mask; - int i;

mask = BIT(WAKE_CNTRL_OFF_S0I3) | BIT(WAKE_CNTRL_OFF_S3) | BIT(INTERRUPT_MASK_OFF) | BIT(INTERRUPT_ENABLE_OFF) | BIT(WAKE_CNTRL_OFF_S4);

- for (i = 0; i < desc->npins; i++) { - int pin = desc->pins[i].number; - const struct pin_desc *pd = pin_desc_get(gpio_dev->pctrl, pin); - - if (!pd) - continue; + pd = pin_desc_get(gpio_dev->pctrl, pin); + if (!pd) + return;

- raw_spin_lock_irqsave(&gpio_dev->lock, flags); + raw_spin_lock_irqsave(&gpio_dev->lock, flags); + pin_reg = readl(gpio_dev->base + pin * 4); + pin_reg &= ~mask; + writel(pin_reg, gpio_dev->base + pin * 4); + raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); +}

- pin_reg = readl(gpio_dev->base + i * 4); - pin_reg &= ~mask; - writel(pin_reg, gpio_dev->base + i * 4); +static void amd_gpio_irq_init(struct amd_gpio *gpio_dev) +{ + struct pinctrl_desc *desc = gpio_dev->pctrl->desc; + int i;

- raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); - } + for (i = 0; i < desc->npins; i++) + amd_gpio_irq_init_pin(gpio_dev, i); }

#ifdef CONFIG_PM_SLEEP @@ -941,8 +943,10 @@ static int amd_gpio_resume(struct device for (i = 0; i < desc->npins; i++) { int pin = desc->pins[i].number;

- if (!amd_gpio_should_save(gpio_dev, pin)) + if (!amd_gpio_should_save(gpio_dev, pin)) { + amd_gpio_irq_init_pin(gpio_dev, pin); continue; + }

raw_spin_lock_irqsave(&gpio_dev->lock, flags); gpio_dev->saved_regs[i] |= readl(gpio_dev->base + pin * 4) & PIN_IRQ_PENDING;

From: Jens Axboe axboe@kernel.dk

commit fd7276189450110ed835eb0a334e62d2f1c4e3be upstream.

powerpc sets up PF_KTHREAD and PF_IO_WORKER with a NULL pt_regs, which from my (arguably very short) checking is not commonly done for other archs. This is fine, except when PF_IO_WORKER's have been created and the task does something that causes a coredump to be generated. Then we get this crash:

Kernel attempted to read user page (160) - exploit attempt? (uid: 1000) BUG: Kernel NULL pointer dereference on read at 0x00000160 Faulting instruction address: 0xc0000000000c3a60 Oops: Kernel access of bad area, sig: 11 [#1] LE PAGE_SIZE=64K MMU=Radix SMP NR_CPUS=32 NUMA pSeries Modules linked in: bochs drm_vram_helper drm_kms_helper xts binfmt_misc ecb ctr syscopyarea sysfillrect cbc sysimgblt drm_ttm_helper aes_generic ttm sg libaes evdev joydev virtio_balloon vmx_crypto gf128mul drm dm_mod fuse loop configfs drm_panel_orientation_quirks ip_tables x_tables autofs4 hid_generic usbhid hid xhci_pci xhci_hcd usbcore usb_common sd_mod CPU: 1 PID: 1982 Comm: ppc-crash Not tainted 6.3.0-rc2+ #88 Hardware name: IBM pSeries (emulated by qemu) POWER9 (raw) 0x4e1202 0xf000005 of:SLOF,HEAD hv:linux,kvm pSeries NIP: c0000000000c3a60 LR: c000000000039944 CTR: c0000000000398e0 REGS: c0000000041833b0 TRAP: 0300 Not tainted (6.3.0-rc2+) MSR: 800000000280b033 <SF,VEC,VSX,EE,FP,ME,IR,DR,RI,LE> CR: 88082828 XER: 200400f8 ... NIP memcpy_power7+0x200/0x7d0 LR ppr_get+0x64/0xb0 Call Trace: ppr_get+0x40/0xb0 (unreliable) __regset_get+0x180/0x1f0 regset_get_alloc+0x64/0x90 elf_core_dump+0xb98/0x1b60 do_coredump+0x1c34/0x24a0 get_signal+0x71c/0x1410 do_notify_resume+0x140/0x6f0 interrupt_exit_user_prepare_main+0x29c/0x320 interrupt_exit_user_prepare+0x6c/0xa0 interrupt_return_srr_user+0x8/0x138

Because ppr_get() is trying to copy from a PF_IO_WORKER with a NULL pt_regs.

Check for a valid pt_regs in both ppc_get/ppr_set, and return an error if not set. The actual error value doesn't seem to be important here, so just pick -EINVAL.

Fixes: fa439810cc1b ("powerpc/ptrace: Enable support for NT_PPPC_TAR, NT_PPC_PPR, NT_PPC_DSCR") Cc: stable@vger.kernel.org # v4.8+ Signed-off-by: Jens Axboe axboe@kernel.dk [mpe: Trim oops in change log, add Fixes & Cc stable] Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://msgid.link/d9f63344-fe7c-56ae-b420-4a1a04a2ae4c@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/kernel/ptrace/ptrace-view.c | 6 ++++++ 1 file changed, 6 insertions(+)

--- a/arch/powerpc/kernel/ptrace/ptrace-view.c +++ b/arch/powerpc/kernel/ptrace/ptrace-view.c @@ -290,6 +290,9 @@ static int gpr_set(struct task_struct *t static int ppr_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { + if (!target->thread.regs) + return -EINVAL; + return membuf_write(&to, &target->thread.regs->ppr, sizeof(u64)); }

@@ -297,6 +300,9 @@ static int ppr_set(struct task_struct *t unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { + if (!target->thread.regs) + return -EINVAL; + return user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.regs->ppr, 0, sizeof(u64)); }

From: Takashi Iwai tiwai@suse.de

commit b871cb971c683f7f212e7ca3c9a6709a75785116 upstream.

The recent commit f83bb2592482 ("ALSA: hda/conexant: Add quirk for LENOVO 20149 Notebook model") introduced a quirk for the device with 17aa:3977, but this caused a regression on another model (Lenovo Ideadpad U31) with the very same PCI SSID. And, through skimming over the net, it seems that this PCI SSID is used for multiple different models, so it's no good idea to apply the quirk with the SSID.

Although we may take a different ID check (e.g. the codec SSID instead of the PCI SSID), unfortunately, the original patch author couldn't identify the hardware details any longer as the machine was returned, and we can't develop the further proper fix.

In this patch, instead, we partially revert the change so that the quirk won't be applied as default for addressing the regression. Meanwhile, the quirk function itself is kept, and it's now made to be applicable via the explicit model=lenovo-20149 option.

Fixes: f83bb2592482 ("ALSA: hda/conexant: Add quirk for LENOVO 20149 Notebook model") Reported-by: Jetro Jormalainen jje-lxkl@jetro.fi Link: https://lore.kernel.org/r/20230308215009.4d3e58a6@mopti Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230320140954.31154-1-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/pci/hda/patch_conexant.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

--- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -980,7 +980,10 @@ static const struct snd_pci_quirk cxt506 SND_PCI_QUIRK(0x17aa, 0x3905, "Lenovo G50-30", CXT_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x17aa, 0x390b, "Lenovo G50-80", CXT_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x17aa, 0x3975, "Lenovo U300s", CXT_FIXUP_STEREO_DMIC), - SND_PCI_QUIRK(0x17aa, 0x3977, "Lenovo IdeaPad U310", CXT_PINCFG_LENOVO_NOTEBOOK), + /* NOTE: we'd need to extend the quirk for 17aa:3977 as the same + * PCI SSID is used on multiple Lenovo models + */ + SND_PCI_QUIRK(0x17aa, 0x3977, "Lenovo IdeaPad U310", CXT_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x17aa, 0x3978, "Lenovo G50-70", CXT_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x17aa, 0x397b, "Lenovo S205", CXT_FIXUP_STEREO_DMIC), SND_PCI_QUIRK_VENDOR(0x17aa, "Thinkpad", CXT_FIXUP_THINKPAD_ACPI), @@ -1003,6 +1006,7 @@ static const struct hda_model_fixup cxt5 { .id = CXT_FIXUP_MUTE_LED_GPIO, .name = "mute-led-gpio" }, { .id = CXT_FIXUP_HP_ZBOOK_MUTE_LED, .name = "hp-zbook-mute-led" }, { .id = CXT_FIXUP_HP_MIC_NO_PRESENCE, .name = "hp-mic-fix" }, + { .id = CXT_PINCFG_LENOVO_NOTEBOOK, .name = "lenovo-20149" }, {} };

From: Tim Crawford tcrawford@system76.com

commit b7a5822810c4398515300d614d988cf638adecad upstream.

Add the audio quirk for some of Clevo's latest RPL laptops:

- NP50RNJS (ALC256) - NP70SNE (ALC256) - PD50SNE (ALC1220) - PE60RNE (ALC1220)

Co-authored-by: Jeremy Soller jeremy@system76.com Signed-off-by: Tim Crawford tcrawford@system76.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230317141825.11807-1-tcrawford@system76.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/pci/hda/patch_realtek.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2625,6 +2625,7 @@ static const struct snd_pci_quirk alc882 SND_PCI_QUIRK(0x1558, 0x65e5, "Clevo PC50D[PRS](?:-D|-G)?", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x65f1, "Clevo PC50HS", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x65f5, "Clevo PD50PN[NRT]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), + SND_PCI_QUIRK(0x1558, 0x66a2, "Clevo PE60RNE", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x67d1, "Clevo PB71[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x67e1, "Clevo PB71[DE][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x67e5, "Clevo PC70D[PRS](?:-D|-G)?", ALC1220_FIXUP_CLEVO_PB51ED_PINS), @@ -2645,6 +2646,7 @@ static const struct snd_pci_quirk alc882 SND_PCI_QUIRK(0x1558, 0x96e1, "Clevo P960[ER][CDFN]-K", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x97e1, "Clevo P970[ER][CDFN]", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x97e2, "Clevo P970RC-M", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0xd502, "Clevo PD50SNE", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD), SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD), SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Y530", ALC882_FIXUP_LENOVO_Y530), @@ -9201,6 +9203,7 @@ static const struct snd_pci_quirk alc269 SND_PCI_QUIRK(0x1558, 0x5101, "Clevo S510WU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x5157, "Clevo W517GU1", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x51a1, "Clevo NS50MU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x5630, "Clevo NP50RNJS", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x70a1, "Clevo NB70T[HJK]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x70b3, "Clevo NK70SB", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x70f2, "Clevo NH79EPY", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), @@ -9235,6 +9238,7 @@ static const struct snd_pci_quirk alc269 SND_PCI_QUIRK(0x1558, 0x971d, "Clevo N970T[CDF]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0xa500, "Clevo NL5[03]RU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0xa600, "Clevo NL50NU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0xa671, "Clevo NP70SN[CDE]", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0xb018, "Clevo NP50D[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0xb019, "Clevo NH77D[BE]Q", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0xb022, "Clevo NH77D[DC][QW]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),

From: Max Filippov jcmvbkbc@gmail.com

commit 1d3b7a788ca7435156809a6bd5b20c95b2370d45 upstream.

show_stack dumps raw stack contents which may trigger an unnecessary KASAN report. Fix it by copying stack contents to a temporary buffer with __memcpy and then printing that buffer instead of passing stack pointer directly to the print_hex_dump.

Cc: stable@vger.kernel.org Signed-off-by: Max Filippov jcmvbkbc@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/xtensa/kernel/traps.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-)

--- a/arch/xtensa/kernel/traps.c +++ b/arch/xtensa/kernel/traps.c @@ -510,7 +510,7 @@ static size_t kstack_depth_to_print = CO

void show_stack(struct task_struct *task, unsigned long *sp, const char *loglvl) { - size_t len; + size_t len, off = 0;

if (!sp) sp = stack_pointer(task); @@ -519,9 +519,17 @@ void show_stack(struct task_struct *task kstack_depth_to_print * STACK_DUMP_ENTRY_SIZE);

printk("%sStack:\n", loglvl); - print_hex_dump(loglvl, " ", DUMP_PREFIX_NONE, - STACK_DUMP_LINE_SIZE, STACK_DUMP_ENTRY_SIZE, - sp, len, false); + while (off < len) { + u8 line[STACK_DUMP_LINE_SIZE]; + size_t line_len = len - off > STACK_DUMP_LINE_SIZE ? + STACK_DUMP_LINE_SIZE : len - off; + + __memcpy(line, (u8 *)sp + off, line_len); + print_hex_dump(loglvl, " ", DUMP_PREFIX_NONE, + STACK_DUMP_LINE_SIZE, STACK_DUMP_ENTRY_SIZE, + line, line_len, false); + off += STACK_DUMP_LINE_SIZE; + } show_trace(task, sp, loglvl); }

From: Lucas Stach l.stach@pengutronix.de

commit 963b2e8c428f79489ceeb058e8314554ec9cbe6f upstream.

drm_gem_prime_mmap() takes a reference on the GEM object, but before that drm_gem_mmap_obj() already takes a reference, which will be leaked as only one reference is dropped when the mapping is closed. Drop the extra reference when dma_buf_mmap() succeeds.

Cc: stable@vger.kernel.org Signed-off-by: Lucas Stach l.stach@pengutronix.de Reviewed-by: Christian Gmeiner christian.gmeiner@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-)

--- a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c @@ -88,7 +88,15 @@ static void *etnaviv_gem_prime_vmap_impl static int etnaviv_gem_prime_mmap_obj(struct etnaviv_gem_object *etnaviv_obj, struct vm_area_struct *vma) { - return dma_buf_mmap(etnaviv_obj->base.dma_buf, vma, 0); + int ret; + + ret = dma_buf_mmap(etnaviv_obj->base.dma_buf, vma, 0); + if (!ret) { + /* Drop the reference acquired by drm_gem_mmap_obj(). */ + drm_gem_object_put(&etnaviv_obj->base); + } + + return ret; }

static const struct etnaviv_gem_ops etnaviv_gem_prime_ops = {

From: Marc Zyngier maz@kernel.org

commit e86fc1a3a3e9b4850fe74d738e3cfcf4297d8bba upstream.

We walk the userspace PTs to discover what mapping size was used there. However, this can race against the userspace tables being freed, and we end-up in the weeds.

Thankfully, the mm code is being generous and will IPI us when doing so. So let's implement our part of the bargain and disable interrupts around the walk. This ensures that nothing terrible happens during that time.

We still need to handle the removal of the page tables before the walk. For that, allow get_user_mapping_size() to return an error, and make sure this error can be propagated all the way to the the exit handler.

Signed-off-by: Marc Zyngier maz@kernel.org Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230316174546.3777507-2-maz@kernel.org Signed-off-by: Oliver Upton oliver.upton@linux.dev Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm64/kvm/mmu.c | 45 ++++++++++++++++++++++++++++++++++++++------- 1 file changed, 38 insertions(+), 7 deletions(-)

--- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -468,14 +468,33 @@ static int get_user_mapping_size(struct CONFIG_PGTABLE_LEVELS), .mm_ops = &kvm_user_mm_ops, }; + unsigned long flags; kvm_pte_t pte = 0; /* Keep GCC quiet... */ u32 level = ~0; int ret;

+ /* + * Disable IRQs so that we hazard against a concurrent + * teardown of the userspace page tables (which relies on + * IPI-ing threads). + */ + local_irq_save(flags); ret = kvm_pgtable_get_leaf(&pgt, addr, &pte, &level); - VM_BUG_ON(ret); - VM_BUG_ON(level >= KVM_PGTABLE_MAX_LEVELS); - VM_BUG_ON(!(pte & PTE_VALID)); + local_irq_restore(flags); + + if (ret) + return ret; + + /* + * Not seeing an error, but not updating level? Something went + * deeply wrong... + */ + if (WARN_ON(level >= KVM_PGTABLE_MAX_LEVELS)) + return -EFAULT; + + /* Oops, the userspace PTs are gone... Replay the fault */ + if (!kvm_pte_valid(pte)) + return -EAGAIN;

return BIT(ARM64_HW_PGTABLE_LEVEL_SHIFT(level)); } @@ -826,7 +845,7 @@ static bool fault_supports_stage2_huge_m * * Returns the size of the mapping. */ -static unsigned long +static long transparent_hugepage_adjust(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned long hva, kvm_pfn_t *pfnp, phys_addr_t *ipap) @@ -838,8 +857,15 @@ transparent_hugepage_adjust(struct kvm * * sure that the HVA and IPA are sufficiently aligned and that the * block map is contained within the memslot. */ - if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE) && - get_user_mapping_size(kvm, hva) >= PMD_SIZE) { + if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE)) { + int sz = get_user_mapping_size(kvm, hva); + + if (sz < 0) + return sz; + + if (sz < PMD_SIZE) + return PAGE_SIZE; + /* * The address we faulted on is backed by a transparent huge * page. However, because we map the compound huge page and @@ -957,7 +983,7 @@ static int user_mem_abort(struct kvm_vcp kvm_pfn_t pfn; bool logging_active = memslot_is_logging(memslot); unsigned long fault_level = kvm_vcpu_trap_get_fault_level(vcpu); - unsigned long vma_pagesize, fault_granule; + long vma_pagesize, fault_granule; enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R; struct kvm_pgtable *pgt;

@@ -1104,6 +1130,11 @@ static int user_mem_abort(struct kvm_vcp vma_pagesize = transparent_hugepage_adjust(kvm, memslot, hva, &pfn, &fault_ipa); + + if (vma_pagesize < 0) { + ret = vma_pagesize; + goto out_unlock; + } }

if (fault_status != FSC_PERM && !device && kvm_has_mte(kvm)) {

From: Sean Christopherson seanjc@google.com

commit 98c25ead5eda5e9d41abe57839ad3e8caf19500c upstream.

Handle the switch to/from the hypervisor/software timer when a vCPU is blocking in common x86 instead of in VMX. Even though VMX is the only user of a hypervisor timer, the logic and all functions involved are generic x86 (unless future CPUs do something completely different and implement a hypervisor timer that runs regardless of mode).

Handling the switch in common x86 will allow for the elimination of the pre/post_blocks hooks, and also lets KVM switch back to the hypervisor timer if and only if it was in use (without additional params). Add a comment explaining why the switch cannot be deferred to kvm_sched_out() or kvm_vcpu_block().

Signed-off-by: Sean Christopherson seanjc@google.com Reviewed-by: Maxim Levitsky mlevitsk@redhat.com Message-Id: 20211208015236.1616697-8-seanjc@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com [ta: Fix conflicts in vmx_pre_block and vmx_post_block as per Paolo's suggestion. Add Reported-by and Link tags.] Reported-by: syzbot+b6a74be92b5063a0f1ff@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=489beb3d76ef14cc6cd18125782dc6f86051a60... Tested-by: Tudor Ambarus tudor.ambarus@linaro.org Signed-off-by: Tudor Ambarus tudor.ambarus@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/vmx/vmx.c | 6 ------ arch/x86/kvm/x86.c | 21 +++++++++++++++++++++ 2 files changed, 21 insertions(+), 6 deletions(-)

--- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -7597,17 +7597,11 @@ static int vmx_pre_block(struct kvm_vcpu if (pi_pre_block(vcpu)) return 1;

- if (kvm_lapic_hv_timer_in_use(vcpu)) - kvm_lapic_switch_to_sw_timer(vcpu); - return 0; }

static void vmx_post_block(struct kvm_vcpu *vcpu) { - if (kvm_x86_ops.set_hv_timer) - kvm_lapic_switch_to_hv_timer(vcpu); - pi_post_block(vcpu); }

--- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -10043,12 +10043,28 @@ out:

static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) { + bool hv_timer; + if (!kvm_arch_vcpu_runnable(vcpu) && (!kvm_x86_ops.pre_block || static_call(kvm_x86_pre_block)(vcpu) == 0)) { + /* + * Switch to the software timer before halt-polling/blocking as + * the guest's timer may be a break event for the vCPU, and the + * hypervisor timer runs only when the CPU is in guest mode. + * Switch before halt-polling so that KVM recognizes an expired + * timer before blocking. + */ + hv_timer = kvm_lapic_hv_timer_in_use(vcpu); + if (hv_timer) + kvm_lapic_switch_to_sw_timer(vcpu); + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); kvm_vcpu_block(vcpu); vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);

+ if (hv_timer) + kvm_lapic_switch_to_hv_timer(vcpu); + if (kvm_x86_ops.post_block) static_call(kvm_x86_post_block)(vcpu);

@@ -10287,6 +10303,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_v r = -EINTR; goto out; } + /* + * It should be impossible for the hypervisor timer to be in + * use before KVM has ever run the vCPU. + */ + WARN_ON_ONCE(kvm_lapic_hv_timer_in_use(vcpu)); kvm_vcpu_block(vcpu); if (kvm_apic_accept_events(vcpu) < 0) { r = 0;

From: Sean Christopherson seanjc@google.com

commit 97a71c444a147ae41c7d0ab5b3d855d7f762f3ed upstream.

Purge the "highest ISR" cache when updating APICv state on a vCPU. The cache must not be used when APICv is active as hardware may emulate EOIs (and other operations) without exiting to KVM.

This fixes a bug where KVM will effectively block IRQs in perpetuity due to the "highest ISR" never getting reset if APICv is activated on a vCPU while an IRQ is in-service. Hardware emulates the EOI and KVM never gets a chance to update its cache.

Fixes: b26a695a1d78 ("kvm: lapic: Introduce APICv update helper function") Cc: stable@vger.kernel.org Cc: Suravee Suthikulpanit suravee.suthikulpanit@amd.com Cc: Maxim Levitsky mlevitsk@redhat.com Reviewed-by: Paolo Bonzini pbonzini@redhat.com Reviewed-by: Maxim Levitsky mlevitsk@redhat.com Signed-off-by: Sean Christopherson seanjc@google.com Message-Id: 20230106011306.85230-3-seanjc@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Alejandro Jimenez alejandro.j.jimenez@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/lapic.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2316,6 +2316,7 @@ void kvm_apic_update_apicv(struct kvm_vc apic->irr_pending = (apic_search_irr(apic) != -1); apic->isr_count = count_vectors(apic->regs + APIC_ISR); } + apic->highest_isr_cache = -1; } EXPORT_SYMBOL_GPL(kvm_apic_update_apicv);

@@ -2368,7 +2369,6 @@ void kvm_lapic_reset(struct kvm_vcpu *vc kvm_lapic_set_reg(apic, APIC_TMR + 0x10 * i, 0); } kvm_apic_update_apicv(vcpu); - apic->highest_isr_cache = -1; update_divide_count(apic); atomic_set(&apic->lapic_timer.pending, 0);

@@ -2638,7 +2638,6 @@ int kvm_apic_set_state(struct kvm_vcpu * __start_apic_timer(apic, APIC_TMCCT); kvm_lapic_set_reg(apic, APIC_TMCCT, 0); kvm_apic_update_apicv(vcpu); - apic->highest_isr_cache = -1; if (vcpu->arch.apicv_active) { static_call(kvm_x86_apicv_post_state_restore)(vcpu); static_call(kvm_x86_hwapic_irr_update)(vcpu,

From: Eduard Zingerman eddyz87@gmail.com

[ Upstream commit d503f1176b14f722a40ea5110312614982f9a80b ]

Structures with zero regular fields but some padding constitute a special case in btf_dump.c:btf_dump_emit_struct_def with regards to newline before closing '}'.

Signed-off-by: Eduard Zingerman eddyz87@gmail.com Signed-off-by: Andrii Nakryiko andrii@kernel.org Link: https://lore.kernel.org/bpf/20221001104425.415768-2-eddyz87@gmail.com Stable-dep-of: ea2ce1ba99aa ("libbpf: Fix BTF-to-C converter's padding logic") Signed-off-by: Sasha Levin sashal@kernel.org --- .../selftests/bpf/progs/btf_dump_test_case_padding.c | 9 +++++++++ 1 file changed, 9 insertions(+)

diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c index 35c512818a56b..db5458da61826 100644 --- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c @@ -102,12 +102,21 @@ struct zone { struct zone_padding __pad__; };

+/* ----- START-EXPECTED-OUTPUT ----- */ +struct padding_wo_named_members { + long: 64; + long: 64; +}; + +/* ------ END-EXPECTED-OUTPUT ------ */ + int f(struct { struct padded_implicitly _1; struct padded_explicitly _2; struct padded_a_lot _3; struct padded_cache_line _4; struct zone _5; + struct padding_wo_named_members _6; } *_) { return 0;

From: Andrii Nakryiko andrii@kernel.org

[ Upstream commit b148c8b9b926e257a59c8eb2cd6fa3adfd443254 ]

Add few hand-crafted cases and few randomized cases found using script from [0] that tests btf_dump's padding logic.

[0] https://lore.kernel.org/bpf/85f83c333f5355c8ac026f835b18d15060725fcb.camel@e...

Signed-off-by: Andrii Nakryiko andrii@kernel.org Signed-off-by: Daniel Borkmann daniel@iogearbox.net Link: https://lore.kernel.org/bpf/20221212211505.558851-7-andrii@kernel.org Stable-dep-of: 4fb877aaa179 ("libbpf: Fix btf_dump's packed struct determination") Signed-off-by: Sasha Levin sashal@kernel.org --- .../bpf/progs/btf_dump_test_case_packing.c | 61 +++++++++- .../bpf/progs/btf_dump_test_case_padding.c | 104 ++++++++++++++++++ 2 files changed, 164 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c index 1cef3bec1dc7f..3f7755247591c 100644 --- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c @@ -58,7 +58,64 @@ union jump_code_union { } __attribute__((packed)); };

-/*------ END-EXPECTED-OUTPUT ------ */ +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *struct nested_packed_but_aligned_struct { + * int x1; + * int x2; + *}; + * + *struct outer_implicitly_packed_struct { + * char y1; + * struct nested_packed_but_aligned_struct y2; + *} __attribute__((packed)); + * + */ +/* ------ END-EXPECTED-OUTPUT ------ */ + +struct nested_packed_but_aligned_struct { + int x1; + int x2; +} __attribute__((packed)); + +struct outer_implicitly_packed_struct { + char y1; + struct nested_packed_but_aligned_struct y2; +}; +/* ----- START-EXPECTED-OUTPUT ----- */ +/* + *struct usb_ss_ep_comp_descriptor { + * char: 8; + * char bDescriptorType; + * char bMaxBurst; + * short wBytesPerInterval; + *}; + * + *struct usb_host_endpoint { + * long: 64; + * char: 8; + * struct usb_ss_ep_comp_descriptor ss_ep_comp; + * long: 0; + *} __attribute__((packed)); + * + */ +/* ------ END-EXPECTED-OUTPUT ------ */ + +struct usb_ss_ep_comp_descriptor { + char: 8; + char bDescriptorType; + char bMaxBurst; + int: 0; + short wBytesPerInterval; +} __attribute__((packed)); + +struct usb_host_endpoint { + long: 64; + char: 8; + struct usb_ss_ep_comp_descriptor ss_ep_comp; + long: 0; +}; +

int f(struct { struct packed_trailing_space _1; @@ -69,6 +126,8 @@ int f(struct { union union_is_never_packed _6; union union_does_not_need_packing _7; union jump_code_union _8; + struct outer_implicitly_packed_struct _9; + struct usb_host_endpoint _10; } *_) { return 0; diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c index 28833f2694e9c..0b3cdffbfcf71 100644 --- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c @@ -128,6 +128,98 @@ struct padding_weird_2 { char: 8; };

+/* ----- START-EXPECTED-OUTPUT ----- */ +struct exact_1byte { + char x; +}; + +struct padded_1byte { + char: 8; +}; + +struct exact_2bytes { + short x; +}; + +struct padded_2bytes { + short: 16; +}; + +struct exact_4bytes { + int x; +}; + +struct padded_4bytes { + int: 32; +}; + +struct exact_8bytes { + long x; +}; + +struct padded_8bytes { + long: 64; +}; + +struct ff_periodic_effect { + int: 32; + short magnitude; + long: 0; + short phase; + long: 0; + int: 32; + int custom_len; + short *custom_data; +}; + +struct ib_wc { + long: 64; + long: 64; + int: 32; + int byte_len; + void *qp; + union {} ex; + long: 64; + int slid; + int wc_flags; + long: 64; + char smac[6]; + long: 0; + char network_hdr_type; +}; + +struct acpi_object_method { + long: 64; + char: 8; + char type; + short reference_count; + char flags; + short: 0; + char: 8; + char sync_level; + long: 64; + void *node; + void *aml_start; + union {} dispatch; + long: 64; + int aml_length; +}; + +struct nested_unpacked { + int x; +}; + +struct nested_packed { + struct nested_unpacked a; + char c; +} __attribute__((packed)); + +struct outer_mixed_but_unpacked { + struct nested_packed b1; + short a1; + struct nested_packed b2; +}; + /* ------ END-EXPECTED-OUTPUT ------ */

int f(struct { @@ -139,6 +231,18 @@ int f(struct { struct padding_wo_named_members _6; struct padding_weird_1 _7; struct padding_weird_2 _8; + struct exact_1byte _100; + struct padded_1byte _101; + struct exact_2bytes _102; + struct padded_2bytes _103; + struct exact_4bytes _104; + struct padded_4bytes _105; + struct exact_8bytes _106; + struct padded_8bytes _107; + struct ff_periodic_effect _200; + struct ib_wc _201; + struct acpi_object_method _202; + struct outer_mixed_but_unpacked _203; } *_) { return 0;

From: Matthieu Baerts matthieu.baerts@tessares.net

commit 1b0120e4db0bf2838d1ce741195ce4b7cc100b91 upstream.

Recently, when automatically merging -net and net-next in MPTCP devel tree, our CI reported [1] a conflict in hsr, the same as the one reported by Stephen in netdev [2].

When looking at the conflict, I noticed it is in fact the v1 [3] that has been applied in -net and the v2 [4] in net-next. Maybe the v1 was applied by accident.

As mentioned by Jakub Kicinski [5], the new condition makes more sense before the net_ratelimit(), not to update net_ratelimit's state which is unnecessary if we're not going to print either way.

Here, this modification applies the v2 but in -net.

Link: https://github.com/multipath-tcp/mptcp_net-next/actions/runs/4423171069 [1] Link: https://lore.kernel.org/netdev/20230315100914.53fc1760@canb.auug.org.au/ [2] Link: https://lore.kernel.org/netdev/20230307133229.127442-1-koverskeid@gmail.com/ [3] Link: https://lore.kernel.org/netdev/20230309092302.179586-1-koverskeid@gmail.com/ [4] Link: https://lore.kernel.org/netdev/20230308232001.2fb62013@kernel.org/ [5] Fixes: 28e8cabe80f3 ("net: hsr: Don't log netdev_err message on unknown prp dst node") Signed-off-by: Matthieu Baerts matthieu.baerts@tessares.net Reviewed-by: Steen Hegelund Steen.Hegelund@microchip.com Link: https://lore.kernel.org/r/20230315-net-20230315-hsr_framereg-ratelimit-v1-1-... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/hsr/hsr_framereg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -385,7 +385,7 @@ void hsr_addr_subst_dest(struct hsr_node node_dst = find_node_by_addr_A(&port->hsr->node_db, eth_hdr(skb)->h_dest); if (!node_dst) { - if (net_ratelimit() && port->hsr->prot_version != PRP_V1) + if (port->hsr->prot_version != PRP_V1 && net_ratelimit()) netdev_err(skb->dev, "%s: Unknown node\n", __func__); return; }