From: Hannes Reinecke hare@suse.de

commit 023358b136d490ca91735ac6490db3741af5a8bd upstream.

Gcc-9 complains for a memset across pointer boundaries, which happens as the code tries to allocate a flexible array on the stack. Turns out we cannot do this without relying on gcc-isms, so with this patch we'll embed the fc_rport_priv structure into fcoe_rport, can use the normal 'container_of' outcast, and will only have to do a memset over one structure.

Signed-off-by: Hannes Reinecke hare@suse.de Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/scsi/fcoe/fcoe_ctlr.c | 51 ++++++++++++++++-------------------------- drivers/scsi/libfc/fc_rport.c | 5 +++- include/scsi/libfcoe.h | 1 3 files changed, 25 insertions(+), 32 deletions(-)

--- a/drivers/scsi/fcoe/fcoe_ctlr.c +++ b/drivers/scsi/fcoe/fcoe_ctlr.c @@ -2017,7 +2017,7 @@ EXPORT_SYMBOL_GPL(fcoe_wwn_from_mac); */ static inline struct fcoe_rport *fcoe_ctlr_rport(struct fc_rport_priv *rdata) { - return (struct fcoe_rport *)(rdata + 1); + return container_of(rdata, struct fcoe_rport, rdata); }

/** @@ -2281,7 +2281,7 @@ static void fcoe_ctlr_vn_start(struct fc */ static int fcoe_ctlr_vn_parse(struct fcoe_ctlr *fip, struct sk_buff *skb, - struct fc_rport_priv *rdata) + struct fcoe_rport *frport) { struct fip_header *fiph; struct fip_desc *desc = NULL; @@ -2289,16 +2289,12 @@ static int fcoe_ctlr_vn_parse(struct fco struct fip_wwn_desc *wwn = NULL; struct fip_vn_desc *vn = NULL; struct fip_size_desc *size = NULL; - struct fcoe_rport *frport; size_t rlen; size_t dlen; u32 desc_mask = 0; u32 dtype; u8 sub;

- memset(rdata, 0, sizeof(*rdata) + sizeof(*frport)); - frport = fcoe_ctlr_rport(rdata); - fiph = (struct fip_header *)skb->data; frport->flags = ntohs(fiph->fip_flags);

@@ -2361,15 +2357,17 @@ static int fcoe_ctlr_vn_parse(struct fco if (dlen != sizeof(struct fip_wwn_desc)) goto len_err; wwn = (struct fip_wwn_desc *)desc; - rdata->ids.node_name = get_unaligned_be64(&wwn->fd_wwn); + frport->rdata.ids.node_name = + get_unaligned_be64(&wwn->fd_wwn); break; case FIP_DT_VN_ID: if (dlen != sizeof(struct fip_vn_desc)) goto len_err; vn = (struct fip_vn_desc *)desc; memcpy(frport->vn_mac, vn->fd_mac, ETH_ALEN); - rdata->ids.port_id = ntoh24(vn->fd_fc_id); - rdata->ids.port_name = get_unaligned_be64(&vn->fd_wwpn); + frport->rdata.ids.port_id = ntoh24(vn->fd_fc_id); + frport->rdata.ids.port_name = + get_unaligned_be64(&vn->fd_wwpn); break; case FIP_DT_FC4F: if (dlen != sizeof(struct fip_fc4_feat)) @@ -2750,10 +2748,7 @@ static int fcoe_ctlr_vn_recv(struct fcoe { struct fip_header *fiph; enum fip_vn2vn_subcode sub; - struct { - struct fc_rport_priv rdata; - struct fcoe_rport frport; - } buf; + struct fcoe_rport frport = { }; int rc, vlan_id = 0;

fiph = (struct fip_header *)skb->data; @@ -2769,7 +2764,7 @@ static int fcoe_ctlr_vn_recv(struct fcoe goto drop; }

- rc = fcoe_ctlr_vn_parse(fip, skb, &buf.rdata); + rc = fcoe_ctlr_vn_parse(fip, skb, &frport); if (rc) { LIBFCOE_FIP_DBG(fip, "vn_recv vn_parse error %d\n", rc); goto drop; @@ -2778,19 +2773,19 @@ static int fcoe_ctlr_vn_recv(struct fcoe mutex_lock(&fip->ctlr_mutex); switch (sub) { case FIP_SC_VN_PROBE_REQ: - fcoe_ctlr_vn_probe_req(fip, &buf.rdata); + fcoe_ctlr_vn_probe_req(fip, &frport.rdata); break; case FIP_SC_VN_PROBE_REP: - fcoe_ctlr_vn_probe_reply(fip, &buf.rdata); + fcoe_ctlr_vn_probe_reply(fip, &frport.rdata); break; case FIP_SC_VN_CLAIM_NOTIFY: - fcoe_ctlr_vn_claim_notify(fip, &buf.rdata); + fcoe_ctlr_vn_claim_notify(fip, &frport.rdata); break; case FIP_SC_VN_CLAIM_REP: - fcoe_ctlr_vn_claim_resp(fip, &buf.rdata); + fcoe_ctlr_vn_claim_resp(fip, &frport.rdata); break; case FIP_SC_VN_BEACON: - fcoe_ctlr_vn_beacon(fip, &buf.rdata); + fcoe_ctlr_vn_beacon(fip, &frport.rdata); break; default: LIBFCOE_FIP_DBG(fip, "vn_recv unknown subcode %d\n", sub); @@ -2814,22 +2809,18 @@ drop: */ static int fcoe_ctlr_vlan_parse(struct fcoe_ctlr *fip, struct sk_buff *skb, - struct fc_rport_priv *rdata) + struct fcoe_rport *frport) { struct fip_header *fiph; struct fip_desc *desc = NULL; struct fip_mac_desc *macd = NULL; struct fip_wwn_desc *wwn = NULL; - struct fcoe_rport *frport; size_t rlen; size_t dlen; u32 desc_mask = 0; u32 dtype; u8 sub;

- memset(rdata, 0, sizeof(*rdata) + sizeof(*frport)); - frport = fcoe_ctlr_rport(rdata); - fiph = (struct fip_header *)skb->data; frport->flags = ntohs(fiph->fip_flags);

@@ -2883,7 +2874,8 @@ static int fcoe_ctlr_vlan_parse(struct f if (dlen != sizeof(struct fip_wwn_desc)) goto len_err; wwn = (struct fip_wwn_desc *)desc; - rdata->ids.node_name = get_unaligned_be64(&wwn->fd_wwn); + frport->rdata.ids.node_name = + get_unaligned_be64(&wwn->fd_wwn); break; default: LIBFCOE_FIP_DBG(fip, "unexpected descriptor type %x " @@ -2994,22 +2986,19 @@ static int fcoe_ctlr_vlan_recv(struct fc { struct fip_header *fiph; enum fip_vlan_subcode sub; - struct { - struct fc_rport_priv rdata; - struct fcoe_rport frport; - } buf; + struct fcoe_rport frport = { }; int rc;

fiph = (struct fip_header *)skb->data; sub = fiph->fip_subcode; - rc = fcoe_ctlr_vlan_parse(fip, skb, &buf.rdata); + rc = fcoe_ctlr_vlan_parse(fip, skb, &frport); if (rc) { LIBFCOE_FIP_DBG(fip, "vlan_recv vlan_parse error %d\n", rc); goto drop; } mutex_lock(&fip->ctlr_mutex); if (sub == FIP_SC_VL_REQ) - fcoe_ctlr_vlan_disc_reply(fip, &buf.rdata); + fcoe_ctlr_vlan_disc_reply(fip, &frport.rdata); mutex_unlock(&fip->ctlr_mutex);

drop: --- a/drivers/scsi/libfc/fc_rport.c +++ b/drivers/scsi/libfc/fc_rport.c @@ -140,6 +140,7 @@ EXPORT_SYMBOL(fc_rport_lookup); struct fc_rport_priv *fc_rport_create(struct fc_lport *lport, u32 port_id) { struct fc_rport_priv *rdata; + size_t rport_priv_size = sizeof(*rdata);

lockdep_assert_held(&lport->disc.disc_mutex);

@@ -147,7 +148,9 @@ struct fc_rport_priv *fc_rport_create(st if (rdata) return rdata;

- rdata = kzalloc(sizeof(*rdata) + lport->rport_priv_size, GFP_KERNEL); + if (lport->rport_priv_size > 0) + rport_priv_size = lport->rport_priv_size; + rdata = kzalloc(rport_priv_size, GFP_KERNEL); if (!rdata) return NULL;

--- a/include/scsi/libfcoe.h +++ b/include/scsi/libfcoe.h @@ -241,6 +241,7 @@ struct fcoe_fcf { * @vn_mac: VN_Node assigned MAC address for data */ struct fcoe_rport { + struct fc_rport_priv rdata; unsigned long time; u16 fcoe_len; u16 flags;

commit 3451a495ef244a88ed6317a035299d835554d579 upstream.

Add an additional bit flag to the device_private struct named "dead".

This additional flag provides a guarantee that when a device_del is executed on a given interface an async worker will not attempt to attach the driver following the earlier device_del call. Previously this guarantee was not present and could result in the device_del call attempting to remove a driver from an interface only to have the async worker attempt to probe the driver later when it finally completes the asynchronous probe call.

One additional change added was that I pulled the check for dev->driver out of the __device_attach_driver call and instead placed it in the __device_attach_async_helper call. This was motivated by the fact that the only other caller of this, __device_attach, had already taken the device_lock() and checked for dev->driver. Instead of testing for this twice in this path it makes more sense to just consolidate the dev->dead and dev->driver checks together into one set of checks.

Reviewed-by: Dan Williams dan.j.williams@intel.com Reviewed-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Alexander Duyck alexander.h.duyck@linux.intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/base/base.h | 4 ++++ drivers/base/core.c | 11 +++++++++++ drivers/base/dd.c | 22 +++++++++++----------- 3 files changed, 26 insertions(+), 11 deletions(-)

diff --git a/drivers/base/base.h b/drivers/base/base.h index 7a419a7a6235b..559b047de9f75 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -66,6 +66,9 @@ struct driver_private { * probed first. * @device - pointer back to the struct device that this structure is * associated with. + * @dead - This device is currently either in the process of or has been + * removed from the system. Any asynchronous events scheduled for this + * device should exit without taking any action. * * Nothing outside of the driver core should ever touch these fields. */ @@ -76,6 +79,7 @@ struct device_private { struct klist_node knode_bus; struct list_head deferred_probe; struct device *device; + u8 dead:1; }; #define to_device_private_parent(obj) \ container_of(obj, struct device_private, knode_parent) diff --git a/drivers/base/core.c b/drivers/base/core.c index 92e2c32c22270..37a90d72f3736 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2050,6 +2050,17 @@ void device_del(struct device *dev) struct kobject *glue_dir = NULL; struct class_interface *class_intf;

+ /* + * Hold the device lock and set the "dead" flag to guarantee that + * the update behavior is consistent with the other bitfields near + * it and that we cannot have an asynchronous probe routine trying + * to run while we are tearing out the bus/class/sysfs from + * underneath the device. + */ + device_lock(dev); + dev->p->dead = true; + device_unlock(dev); + /* Notify clients of device removal. This call must come * before dpm_sysfs_remove(). */ diff --git a/drivers/base/dd.c b/drivers/base/dd.c index d48b310c47603..11d24a552ee49 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -725,15 +725,6 @@ static int __device_attach_driver(struct device_driver *drv, void *_data) bool async_allowed; int ret;

- /* - * Check if device has already been claimed. This may - * happen with driver loading, device discovery/registration, - * and deferred probe processing happens all at once with - * multiple threads. - */ - if (dev->driver) - return -EBUSY; - ret = driver_match_device(drv, dev); if (ret == 0) { /* no match */ @@ -768,6 +759,15 @@ static void __device_attach_async_helper(void *_dev, async_cookie_t cookie)

device_lock(dev);

+ /* + * Check if device has already been removed or claimed. This may + * happen with driver loading, device discovery/registration, + * and deferred probe processing happens all at once with + * multiple threads. + */ + if (dev->p->dead || dev->driver) + goto out_unlock; + if (dev->parent) pm_runtime_get_sync(dev->parent);

@@ -778,7 +778,7 @@ static void __device_attach_async_helper(void *_dev, async_cookie_t cookie)

if (dev->parent) pm_runtime_put(dev->parent); - +out_unlock: device_unlock(dev);

put_device(dev); @@ -891,7 +891,7 @@ static int __driver_attach(struct device *dev, void *data) if (dev->parent && dev->bus->need_parent_lock) device_lock(dev->parent); device_lock(dev); - if (!dev->driver) + if (!dev->p->dead && !dev->driver) driver_probe_device(drv, dev); device_unlock(dev); if (dev->parent && dev->bus->need_parent_lock)

commit 8aac0e2338916e273ccbd438a2b7a1e8c61749f5 upstream.

A multithreaded namespace creation/destruction stress test currently fails with signatures like the following:

sysfs group 'power' not found for kobject 'dax1.1' RIP: 0010:sysfs_remove_group+0x76/0x80 Call Trace: device_del+0x73/0x370 device_unregister+0x16/0x50 nd_async_device_unregister+0x1e/0x30 [libnvdimm] async_run_entry_fn+0x39/0x160 process_one_work+0x23c/0x5e0 worker_thread+0x3c/0x390

BUG: kernel NULL pointer dereference, address: 0000000000000020 RIP: 0010:klist_put+0x1b/0x6c Call Trace: klist_del+0xe/0x10 device_del+0x8a/0x2c9 ? __switch_to_asm+0x34/0x70 ? __switch_to_asm+0x40/0x70 device_unregister+0x44/0x4f nd_async_device_unregister+0x22/0x2d [libnvdimm] async_run_entry_fn+0x47/0x15a process_one_work+0x1a2/0x2eb worker_thread+0x1b8/0x26e

Use the kill_device() helper to atomically resolve the race of multiple threads issuing kill, device_unregister(), requests.

Reported-by: Jane Chu jane.chu@oracle.com Reported-by: Erwin Tsaur erwin.tsaur@oracle.com Fixes: 4d88a97aa9e8 ("libnvdimm, nvdimm: dimm driver and base libnvdimm device-driver...") Cc: stable@vger.kernel.org Link: https://github.com/pmem/ndctl/issues/96 Tested-by: Tested-by: Jane Chu jane.chu@oracle.com Link: https://lore.kernel.org/r/156341207846.292348.10435719262819764054.stgit@dwi... Signed-off-by: Dan Williams dan.j.williams@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvdimm/bus.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+)

diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index ee39e2c1644ae..11cfd23e5aff7 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -528,13 +528,38 @@ EXPORT_SYMBOL(nd_device_register);

void nd_device_unregister(struct device *dev, enum nd_async_mode mode) { + bool killed; + switch (mode) { case ND_ASYNC: + /* + * In the async case this is being triggered with the + * device lock held and the unregistration work needs to + * be moved out of line iff this is thread has won the + * race to schedule the deletion. + */ + if (!kill_device(dev)) + return; + get_device(dev); async_schedule_domain(nd_async_device_unregister, dev, &nd_async_domain); break; case ND_SYNC: + /* + * In the sync case the device is being unregistered due + * to a state change of the parent. Claim the kill state + * to synchronize against other unregistration requests, + * or otherwise let the async path handle it if the + * unregistration was already queued. + */ + device_lock(dev); + killed = kill_device(dev); + device_unlock(dev); + + if (!killed) + return; + nd_synchronize(); device_unregister(dev); break;

commit 6de5d06e657acdbcf9637dac37916a4a5309e0f4 upstream.

In preparation for not holding a lock over the execution of nd_ioctl(), update the implementation to allow multiple threads to be attempting ioctls at the same time. The bus lock still prevents multiple in-flight ->ndctl() invocations from corrupting each other's state, but static global staging buffers are moved to the heap.

Reported-by: Vishal Verma vishal.l.verma@intel.com Reviewed-by: Vishal Verma vishal.l.verma@intel.com Tested-by: Vishal Verma vishal.l.verma@intel.com Link: https://lore.kernel.org/r/156341208947.292348.10560140326807607481.stgit@dwi... Signed-off-by: Dan Williams dan.j.williams@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvdimm/bus.c | 59 +++++++++++++++++++++++++++----------------- 1 file changed, 37 insertions(+), 22 deletions(-)

diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 11cfd23e5aff7..5abcdb4faa644 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -951,20 +951,19 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, int read_only, unsigned int ioctl_cmd, unsigned long arg) { struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc; - static char out_env[ND_CMD_MAX_ENVELOPE]; - static char in_env[ND_CMD_MAX_ENVELOPE]; const struct nd_cmd_desc *desc = NULL; unsigned int cmd = _IOC_NR(ioctl_cmd); struct device *dev = &nvdimm_bus->dev; void __user *p = (void __user *) arg; + char *out_env = NULL, *in_env = NULL; const char *cmd_name, *dimm_name; u32 in_len = 0, out_len = 0; unsigned int func = cmd; unsigned long cmd_mask; struct nd_cmd_pkg pkg; int rc, i, cmd_rc; + void *buf = NULL; u64 buf_len = 0; - void *buf;

if (nvdimm) { desc = nd_cmd_dimm_desc(cmd); @@ -1004,6 +1003,9 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, }

/* process an input envelope */ + in_env = kzalloc(ND_CMD_MAX_ENVELOPE, GFP_KERNEL); + if (!in_env) + return -ENOMEM; for (i = 0; i < desc->in_num; i++) { u32 in_size, copy;

@@ -1011,14 +1013,17 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, if (in_size == UINT_MAX) { dev_err(dev, "%s:%s unknown input size cmd: %s field: %d\n", __func__, dimm_name, cmd_name, i); - return -ENXIO; + rc = -ENXIO; + goto out; } - if (in_len < sizeof(in_env)) - copy = min_t(u32, sizeof(in_env) - in_len, in_size); + if (in_len < ND_CMD_MAX_ENVELOPE) + copy = min_t(u32, ND_CMD_MAX_ENVELOPE - in_len, in_size); else copy = 0; - if (copy && copy_from_user(&in_env[in_len], p + in_len, copy)) - return -EFAULT; + if (copy && copy_from_user(&in_env[in_len], p + in_len, copy)) { + rc = -EFAULT; + goto out; + } in_len += in_size; }

@@ -1030,6 +1035,12 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, }

/* process an output envelope */ + out_env = kzalloc(ND_CMD_MAX_ENVELOPE, GFP_KERNEL); + if (!out_env) { + rc = -ENOMEM; + goto out; + } + for (i = 0; i < desc->out_num; i++) { u32 out_size = nd_cmd_out_size(nvdimm, cmd, desc, i, (u32 *) in_env, (u32 *) out_env, 0); @@ -1038,15 +1049,18 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, if (out_size == UINT_MAX) { dev_dbg(dev, "%s unknown output size cmd: %s field: %d\n", dimm_name, cmd_name, i); - return -EFAULT; + rc = -EFAULT; + goto out; } - if (out_len < sizeof(out_env)) - copy = min_t(u32, sizeof(out_env) - out_len, out_size); + if (out_len < ND_CMD_MAX_ENVELOPE) + copy = min_t(u32, ND_CMD_MAX_ENVELOPE - out_len, out_size); else copy = 0; if (copy && copy_from_user(&out_env[out_len], - p + in_len + out_len, copy)) - return -EFAULT; + p + in_len + out_len, copy)) { + rc = -EFAULT; + goto out; + } out_len += out_size; }

@@ -1054,12 +1068,15 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, if (buf_len > ND_IOCTL_MAX_BUFLEN) { dev_dbg(dev, "%s cmd: %s buf_len: %llu > %d\n", dimm_name, cmd_name, buf_len, ND_IOCTL_MAX_BUFLEN); - return -EINVAL; + rc = -EINVAL; + goto out; }

buf = vmalloc(buf_len); - if (!buf) - return -ENOMEM; + if (!buf) { + rc = -ENOMEM; + goto out; + }

if (copy_from_user(buf, p, buf_len)) { rc = -EFAULT; @@ -1081,17 +1098,15 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, nvdimm_account_cleared_poison(nvdimm_bus, clear_err->address, clear_err->cleared); } - nvdimm_bus_unlock(&nvdimm_bus->dev);

if (copy_to_user(p, buf, buf_len)) rc = -EFAULT;

- vfree(buf); - return rc; - - out_unlock: +out_unlock: nvdimm_bus_unlock(&nvdimm_bus->dev); - out: +out: + kfree(in_env); + kfree(out_env); vfree(buf); return rc; }

From: Aaron Armstrong Skomra skomra@gmail.com

commit 693c3dab4e50403f91bca4b52fc6d8562a3180f6 upstream.

The bit indicating BTN_6 on this device is overshifted by 2 bits, resulting in the incorrect button being reported.

Also fix copy-paste mistake in comments.

Signed-off-by: Aaron Armstrong Skomra aaron.skomra@wacom.com Reviewed-by: Ping Cheng ping.cheng@wacom.com Link: https://github.com/linuxwacom/xf86-input-wacom/issues/71 Fixes: c7f0522a1ad1 ("HID: wacom: Slim down wacom_intuos_pad processing") Cc: stable@vger.kernel.org # v4.5+ Signed-off-by: Jiri Kosina jkosina@suse.cz Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/hid/wacom_wac.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-)

--- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -537,14 +537,14 @@ static int wacom_intuos_pad(struct wacom */ buttons = (data[4] << 1) | (data[3] & 0x01); } else if (features->type == CINTIQ_COMPANION_2) { - /* d-pad right -> data[4] & 0x10 - * d-pad up -> data[4] & 0x20 - * d-pad left -> data[4] & 0x40 - * d-pad down -> data[4] & 0x80 - * d-pad center -> data[3] & 0x01 + /* d-pad right -> data[2] & 0x10 + * d-pad up -> data[2] & 0x20 + * d-pad left -> data[2] & 0x40 + * d-pad down -> data[2] & 0x80 + * d-pad center -> data[1] & 0x01 */ buttons = ((data[2] >> 4) << 7) | - ((data[1] & 0x04) << 6) | + ((data[1] & 0x04) << 4) | ((data[2] & 0x0F) << 2) | (data[1] & 0x03); } else if (features->type >= INTUOS5S && features->type <= INTUOSPL) {

From: Greg Kroah-Hartman gregkh@linuxfoundation.org

Like commit 641114d2af31 ("RDMA: Directly cast the sockaddr union to sockaddr") we need to quiet gcc 9 from warning about this crazy union. That commit did not fix all of the warnings in 4.19 and older kernels because the logic in roce_resolve_route_from_path() was rewritten between 4.19 and 5.2 when that change happened.

Cc: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/infiniband/core/sa_query.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-)

--- a/drivers/infiniband/core/sa_query.c +++ b/drivers/infiniband/core/sa_query.c @@ -1232,7 +1232,6 @@ static int roce_resolve_route_from_path( { struct rdma_dev_addr dev_addr = {}; union { - struct sockaddr _sockaddr; struct sockaddr_in _sockaddr_in; struct sockaddr_in6 _sockaddr_in6; } sgid_addr, dgid_addr; @@ -1249,12 +1248,12 @@ static int roce_resolve_route_from_path( */ dev_addr.net = &init_net;

- rdma_gid2ip(&sgid_addr._sockaddr, &rec->sgid); - rdma_gid2ip(&dgid_addr._sockaddr, &rec->dgid); + rdma_gid2ip((struct sockaddr *)&sgid_addr, &rec->sgid); + rdma_gid2ip((struct sockaddr *)&dgid_addr, &rec->dgid);

/* validate the route */ - ret = rdma_resolve_ip_route(&sgid_addr._sockaddr, - &dgid_addr._sockaddr, &dev_addr); + ret = rdma_resolve_ip_route((struct sockaddr *)&sgid_addr, + (struct sockaddr *)&dgid_addr, &dev_addr); if (ret) return ret;

From: Sudarsana Reddy Kalluru skalluru@marvell.com

[ Upstream commit d1f0b5dce8fda09a7f5f04c1878f181d548e42f5 ]

Commit 3968d38917eb ("bnx2x: Fix Multi-Cos.") which enabled multi-cos feature after prolonged time in driver added some regression causing numerous issues (sudden reboots, tx timeout etc.) reported by customers. We plan to backout this commit and submit proper fix once we have root cause of issues reported with this feature enabled.

Fixes: 3968d38917eb ("bnx2x: Fix Multi-Cos.") Signed-off-by: Sudarsana Reddy Kalluru skalluru@marvell.com Signed-off-by: Manish Chopra manishc@marvell.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -1936,8 +1936,7 @@ u16 bnx2x_select_queue(struct net_device }

/* select a non-FCoE queue */ - return fallback(dev, skb, NULL) % - (BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos); + return fallback(dev, skb, NULL) % (BNX2X_NUM_ETH_QUEUES(bp)); }

void bnx2x_set_num_queues(struct bnx2x *bp)

From: Haishuang Yan yanhaishuang@cmss.chinamobile.com

[ Upstream commit 3bc817d665ac6d9de89f59df522ad86f5b5dfc03 ]

Since ip6_tnl_parse_tlv_enc_lim() can call pskb_may_pull() which may change skb->data, so we need to re-load ipv6h at the right place.

Fixes: 898b29798e36 ("ip6_gre: Refactor ip6gre xmit codes") Cc: William Tu u9012063@gmail.com Signed-off-by: Haishuang Yan yanhaishuang@cmss.chinamobile.com Acked-by: William Tu u9012063@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv6/ip6_gre.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -680,12 +680,13 @@ static int prepare_ip6gre_xmit_ipv6(stru struct flowi6 *fl6, __u8 *dsfield, int *encap_limit) { - struct ipv6hdr *ipv6h = ipv6_hdr(skb); + struct ipv6hdr *ipv6h; struct ip6_tnl *t = netdev_priv(dev); __u16 offset;

offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb)); /* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */ + ipv6h = ipv6_hdr(skb);

if (offset > 0) { struct ipv6_tlv_tnl_enc_lim *tel;

From: Haishuang Yan yanhaishuang@cmss.chinamobile.com

[ Upstream commit 47d858d0bdcd47cc1c6c9eeca91b091dd9e55637 ]

We need the same checks introduced by commit cb9f1b783850 ("ip: validate header length on virtual device xmit") for ipip tunnel.

Fixes: cb9f1b783850b ("ip: validate header length on virtual device xmit") Signed-off-by: Haishuang Yan yanhaishuang@cmss.chinamobile.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/ipip.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -281,6 +281,9 @@ static netdev_tx_t ipip_tunnel_xmit(stru const struct iphdr *tiph = &tunnel->parms.iph; u8 ipproto;

+ if (!pskb_inet_may_pull(skb)) + goto tx_error; + switch (skb->protocol) { case htons(ETH_P_IP): ipproto = IPPROTO_IPIP;

From: Matteo Croce mcroce@redhat.com

[ Upstream commit 944a83a2669ae8aa2c7664e79376ca7468eb0a2b ]

mvpp2 uses a delayed workqueue to gather traffic statistics. On module removal the workqueue can be destroyed before calling cancel_delayed_work_sync() on its works. Fix it by moving the destroy_workqueue() call after mvpp2_port_remove(). Also remove an unneeded call to flush_workqueue()

# rmmod mvpp2 [ 2743.311722] mvpp2 f4000000.ethernet eth1: phy link down 10gbase-kr/10Gbps/Full [ 2743.320063] mvpp2 f4000000.ethernet eth1: Link is Down [ 2743.572263] mvpp2 f4000000.ethernet eth2: phy link down sgmii/1Gbps/Full [ 2743.580076] mvpp2 f4000000.ethernet eth2: Link is Down [ 2744.102169] mvpp2 f2000000.ethernet eth0: phy link down 10gbase-kr/10Gbps/Full [ 2744.110441] mvpp2 f2000000.ethernet eth0: Link is Down [ 2744.115614] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 [ 2744.115615] Mem abort info: [ 2744.115616] ESR = 0x96000005 [ 2744.115617] Exception class = DABT (current EL), IL = 32 bits [ 2744.115618] SET = 0, FnV = 0 [ 2744.115619] EA = 0, S1PTW = 0 [ 2744.115620] Data abort info: [ 2744.115621] ISV = 0, ISS = 0x00000005 [ 2744.115622] CM = 0, WnR = 0 [ 2744.115624] user pgtable: 4k pages, 39-bit VAs, pgdp=0000000422681000 [ 2744.115626] [0000000000000000] pgd=0000000000000000, pud=0000000000000000 [ 2744.115630] Internal error: Oops: 96000005 [#1] SMP [ 2744.115632] Modules linked in: mvpp2(-) algif_hash af_alg nls_iso8859_1 nls_cp437 vfat fat xhci_plat_hcd m25p80 spi_nor xhci_hcd mtd usbcore i2c_mv64xxx sfp usb_common marvell10g phy_generic spi_orion mdio_i2c i2c_core mvmdio phylink sbsa_gwdt ip_tables x_tables autofs4 [last unloaded: mvpp2] [ 2744.115654] CPU: 3 PID: 8357 Comm: kworker/3:2 Not tainted 5.3.0-rc2 #1 [ 2744.115655] Hardware name: Marvell 8040 MACCHIATOBin Double-shot (DT) [ 2744.115665] Workqueue: events_power_efficient phylink_resolve [phylink] [ 2744.115669] pstate: a0000085 (NzCv daIf -PAN -UAO) [ 2744.115675] pc : __queue_work+0x9c/0x4d8 [ 2744.115677] lr : __queue_work+0x170/0x4d8 [ 2744.115678] sp : ffffff801001bd50 [ 2744.115680] x29: ffffff801001bd50 x28: ffffffc422597600 [ 2744.115684] x27: ffffff80109ae6f0 x26: ffffff80108e4018 [ 2744.115688] x25: 0000000000000003 x24: 0000000000000004 [ 2744.115691] x23: ffffff80109ae6e0 x22: 0000000000000017 [ 2744.115694] x21: ffffffc42c030000 x20: ffffffc42209e8f8 [ 2744.115697] x19: 0000000000000000 x18: 0000000000000000 [ 2744.115699] x17: 0000000000000000 x16: 0000000000000000 [ 2744.115701] x15: 0000000000000010 x14: ffffffffffffffff [ 2744.115702] x13: ffffff8090e2b95f x12: ffffff8010e2b967 [ 2744.115704] x11: ffffff8010906000 x10: 0000000000000040 [ 2744.115706] x9 : ffffff80109223b8 x8 : ffffff80109223b0 [ 2744.115707] x7 : ffffffc42bc00068 x6 : 0000000000000000 [ 2744.115709] x5 : ffffffc42bc00000 x4 : 0000000000000000 [ 2744.115710] x3 : 0000000000000000 x2 : 0000000000000000 [ 2744.115712] x1 : 0000000000000008 x0 : ffffffc42c030000 [ 2744.115714] Call trace: [ 2744.115716] __queue_work+0x9c/0x4d8 [ 2744.115718] delayed_work_timer_fn+0x28/0x38 [ 2744.115722] call_timer_fn+0x3c/0x180 [ 2744.115723] expire_timers+0x60/0x168 [ 2744.115724] run_timer_softirq+0xbc/0x1e8 [ 2744.115727] __do_softirq+0x128/0x320 [ 2744.115731] irq_exit+0xa4/0xc0 [ 2744.115734] __handle_domain_irq+0x70/0xc0 [ 2744.115735] gic_handle_irq+0x58/0xa8 [ 2744.115737] el1_irq+0xb8/0x140 [ 2744.115738] console_unlock+0x3a0/0x568 [ 2744.115740] vprintk_emit+0x200/0x2a0 [ 2744.115744] dev_vprintk_emit+0x1c8/0x1e4 [ 2744.115747] dev_printk_emit+0x6c/0x7c [ 2744.115751] __netdev_printk+0x104/0x1d8 [ 2744.115752] netdev_printk+0x60/0x70 [ 2744.115756] phylink_resolve+0x38c/0x3c8 [phylink] [ 2744.115758] process_one_work+0x1f8/0x448 [ 2744.115760] worker_thread+0x54/0x500 [ 2744.115762] kthread+0x12c/0x130 [ 2744.115764] ret_from_fork+0x10/0x1c [ 2744.115768] Code: aa1403e0 97fffbbe aa0003f5 b4000700 (f9400261)

Fixes: 118d6298f6f0 ("net: mvpp2: add ethtool GOP statistics") Signed-off-by: Lorenzo Bianconi lorenzo@kernel.org Signed-off-by: Matteo Croce mcroce@redhat.com Acked-by: Antoine Tenart antoine.tenart@bootlin.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)

--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -5358,9 +5358,6 @@ static int mvpp2_remove(struct platform_

mvpp2_dbgfs_cleanup(priv);

- flush_workqueue(priv->stats_queue); - destroy_workqueue(priv->stats_queue); - fwnode_for_each_available_child_node(fwnode, port_fwnode) { if (priv->port_list[i]) { mutex_destroy(&priv->port_list[i]->gather_stats_lock); @@ -5369,6 +5366,8 @@ static int mvpp2_remove(struct platform_ i++; }

+ destroy_workqueue(priv->stats_queue); + for (i = 0; i < MVPP2_BM_POOLS_NUM; i++) { struct mvpp2_bm_pool *bm_pool = &priv->bm_pools[i];

From: Nikolay Aleksandrov nikolay@cumulusnetworks.com

[ Upstream commit d7bae09fa008c6c9a489580db0a5a12063b97f97 ]

On initialization failure we have to delete the local fdb which was inserted due to the default pvid creation. This problem has been present since the inception of default_pvid. Note that currently there are 2 cases: 1) in br_dev_init() when br_multicast_init() fails 2) if register_netdevice() fails after calling ndo_init()

This patch takes care of both since br_vlan_flush() is called on both occasions. Also the new fdb delete would be a no-op on normal bridge device destruction since the local fdb would've been already flushed by br_dev_delete(). This is not an issue for ports since nbp_vlan_init() is called last when adding a port thus nothing can fail after it.

Reported-by: syzbot+88533dc8b582309bf3ee@syzkaller.appspotmail.com Fixes: 5be5a2df40f0 ("bridge: Add filtering support for default_pvid") Signed-off-by: Nikolay Aleksandrov nikolay@cumulusnetworks.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/bridge/br_vlan.c | 5 +++++ 1 file changed, 5 insertions(+)

--- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -677,6 +677,11 @@ void br_vlan_flush(struct net_bridge *br

ASSERT_RTNL();

+ /* delete auto-added default pvid local fdb before flushing vlans + * otherwise it will be leaked on bridge device init failure + */ + br_fdb_delete_by_port(br, NULL, 0, 1); + vg = br_vlan_group(br); __vlan_flush(vg); RCU_INIT_POINTER(br->vlgrp, NULL);

From: Jiri Pirko jiri@mellanox.com

[ Upstream commit 55b40dbf0e76b4bfb9d8b3a16a0208640a9a45df ]

Commit aca51397d014 ("netns: Fix arbitrary net_device-s corruptions on net_ns stop.") introduced a possibility to hit a BUG in case device is returning back to init_net and two following conditions are met: 1) dev->ifindex value is used in a name of another "dev%d" device in init_net. 2) dev->name is used by another device in init_net.

Under real life circumstances this is hard to get. Therefore this has been present happily for over 10 years. To reproduce:

$ ip a 1: lo: <LOOPBACK,UP,LOWER_UP> mtu 65536 qdisc noqueue state UNKNOWN group default qlen 1000 link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00 inet 127.0.0.1/8 scope host lo valid_lft forever preferred_lft forever inet6 ::1/128 scope host valid_lft forever preferred_lft forever 2: dummy0: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN group default qlen 1000 link/ether 86:89:3f:86:61:29 brd ff:ff:ff:ff:ff:ff 3: enp0s2: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN group default qlen 1000 link/ether 52:54:00:12:34:56 brd ff:ff:ff:ff:ff:ff $ ip netns add ns1 $ ip -n ns1 link add dummy1ns1 type dummy $ ip -n ns1 link add dummy2ns1 type dummy $ ip link set enp0s2 netns ns1 $ ip -n ns1 link set enp0s2 name dummy0 [ 100.858894] virtio_net virtio0 dummy0: renamed from enp0s2 $ ip link add dev4 type dummy $ ip -n ns1 a 1: lo: <LOOPBACK> mtu 65536 qdisc noop state DOWN group default qlen 1000 link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00 2: dummy1ns1: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN group default qlen 1000 link/ether 16:63:4c:38:3e:ff brd ff:ff:ff:ff:ff:ff 3: dummy2ns1: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN group default qlen 1000 link/ether aa:9e:86:dd:6b:5d brd ff:ff:ff:ff:ff:ff 4: dummy0: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN group default qlen 1000 link/ether 52:54:00:12:34:56 brd ff:ff:ff:ff:ff:ff $ ip a 1: lo: <LOOPBACK,UP,LOWER_UP> mtu 65536 qdisc noqueue state UNKNOWN group default qlen 1000 link/loopback 00:00:00:00:00:00 brd 00:00:00:00:00:00 inet 127.0.0.1/8 scope host lo valid_lft forever preferred_lft forever inet6 ::1/128 scope host valid_lft forever preferred_lft forever 2: dummy0: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN group default qlen 1000 link/ether 86:89:3f:86:61:29 brd ff:ff:ff:ff:ff:ff 4: dev4: <BROADCAST,NOARP> mtu 1500 qdisc noop state DOWN group default qlen 1000 link/ether 5a:e1:4a:b6:ec:f8 brd ff:ff:ff:ff:ff:ff $ ip netns del ns1 [ 158.717795] default_device_exit: failed to move dummy0 to init_net: -17 [ 158.719316] ------------[ cut here ]------------ [ 158.720591] kernel BUG at net/core/dev.c:9824! [ 158.722260] invalid opcode: 0000 [#1] SMP KASAN PTI [ 158.723728] CPU: 0 PID: 56 Comm: kworker/u2:1 Not tainted 5.3.0-rc1+ #18 [ 158.725422] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014 [ 158.727508] Workqueue: netns cleanup_net [ 158.728915] RIP: 0010:default_device_exit.cold+0x1d/0x1f [ 158.730683] Code: 84 e8 18 c9 3e fe 0f 0b e9 70 90 ff ff e8 36 e4 52 fe 89 d9 4c 89 e2 48 c7 c6 80 d6 25 84 48 c7 c7 20 c0 25 84 e8 f4 c8 3e [ 158.736854] RSP: 0018:ffff8880347e7b90 EFLAGS: 00010282 [ 158.738752] RAX: 000000000000003b RBX: 00000000ffffffef RCX: 0000000000000000 [ 158.741369] RDX: 0000000000000000 RSI: ffffffff8128013d RDI: ffffed10068fcf64 [ 158.743418] RBP: ffff888033550170 R08: 000000000000003b R09: fffffbfff0b94b9c [ 158.745626] R10: fffffbfff0b94b9b R11: ffffffff85ca5cdf R12: ffff888032f28000 [ 158.748405] R13: dffffc0000000000 R14: ffff8880335501b8 R15: 1ffff110068fcf72 [ 158.750638] FS: 0000000000000000(0000) GS:ffff888036000000(0000) knlGS:0000000000000000 [ 158.752944] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 158.755245] CR2: 00007fe8b45d21d0 CR3: 00000000340b4005 CR4: 0000000000360ef0 [ 158.757654] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 158.760012] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 158.762758] Call Trace: [ 158.763882] ? dev_change_net_namespace+0xbb0/0xbb0 [ 158.766148] ? devlink_nl_cmd_set_doit+0x520/0x520 [ 158.768034] ? dev_change_net_namespace+0xbb0/0xbb0 [ 158.769870] ops_exit_list.isra.0+0xa8/0x150 [ 158.771544] cleanup_net+0x446/0x8f0 [ 158.772945] ? unregister_pernet_operations+0x4a0/0x4a0 [ 158.775294] process_one_work+0xa1a/0x1740 [ 158.776896] ? pwq_dec_nr_in_flight+0x310/0x310 [ 158.779143] ? do_raw_spin_lock+0x11b/0x280 [ 158.780848] worker_thread+0x9e/0x1060 [ 158.782500] ? process_one_work+0x1740/0x1740 [ 158.784454] kthread+0x31b/0x420 [ 158.786082] ? __kthread_create_on_node+0x3f0/0x3f0 [ 158.788286] ret_from_fork+0x3a/0x50 [ 158.789871] ---[ end trace defd6c657c71f936 ]--- [ 158.792273] RIP: 0010:default_device_exit.cold+0x1d/0x1f [ 158.795478] Code: 84 e8 18 c9 3e fe 0f 0b e9 70 90 ff ff e8 36 e4 52 fe 89 d9 4c 89 e2 48 c7 c6 80 d6 25 84 48 c7 c7 20 c0 25 84 e8 f4 c8 3e [ 158.804854] RSP: 0018:ffff8880347e7b90 EFLAGS: 00010282 [ 158.807865] RAX: 000000000000003b RBX: 00000000ffffffef RCX: 0000000000000000 [ 158.811794] RDX: 0000000000000000 RSI: ffffffff8128013d RDI: ffffed10068fcf64 [ 158.816652] RBP: ffff888033550170 R08: 000000000000003b R09: fffffbfff0b94b9c [ 158.820930] R10: fffffbfff0b94b9b R11: ffffffff85ca5cdf R12: ffff888032f28000 [ 158.825113] R13: dffffc0000000000 R14: ffff8880335501b8 R15: 1ffff110068fcf72 [ 158.829899] FS: 0000000000000000(0000) GS:ffff888036000000(0000) knlGS:0000000000000000 [ 158.834923] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 158.838164] CR2: 00007fe8b45d21d0 CR3: 00000000340b4005 CR4: 0000000000360ef0 [ 158.841917] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 158.845149] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400

Fix this by checking if a device with the same name exists in init_net and fallback to original code - dev%d to allocate name - in case it does.

This was found using syzkaller.

Fixes: aca51397d014 ("netns: Fix arbitrary net_device-s corruptions on net_ns stop.") Signed-off-by: Jiri Pirko jiri@mellanox.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/core/dev.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/net/core/dev.c +++ b/net/core/dev.c @@ -9510,6 +9510,8 @@ static void __net_exit default_device_ex

/* Push remaining network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); + if (__dev_get_by_name(&init_net, fb_name)) + snprintf(fb_name, IFNAMSIZ, "dev%%d"); err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { pr_emerg("%s: failed to move %s to init_net: %d\n",

From: Mark Zhang markz@mellanox.com

[ Upstream commit 08aa5e7da6bce1a1963f63cf32c2e7ad434ad578 ]

When lag is active, which is controlled by the bonded mlx5e netdev, mlx5 interface unregestering must happen in the reverse order where rdma is unregistered (unloaded) first, to guarantee all references to the lag context in hardware is removed, then remove mlx5e netdev interface which will cleanup the lag context from hardware.

Without this fix during destroy of LAG interface, we observed following errors: * mlx5_cmd_check:752:(pid 12556): DESTROY_LAG(0x843) op_mod(0x0) failed, status bad parameter(0x3), syndrome (0xe4ac33) * mlx5_cmd_check:752:(pid 12556): DESTROY_LAG(0x843) op_mod(0x0) failed, status bad parameter(0x3), syndrome (0xa5aee8).

Fixes: a31208b1e11d ("net/mlx5_core: New init and exit flow for mlx5_core") Reviewed-by: Parav Pandit parav@mellanox.com Reviewed-by: Leon Romanovsky leonro@mellanox.com Signed-off-by: Mark Zhang markz@mellanox.com Signed-off-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlx5/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -307,7 +307,7 @@ void mlx5_unregister_device(struct mlx5_ struct mlx5_interface *intf;

mutex_lock(&mlx5_intf_mutex); - list_for_each_entry(intf, &intf_list, list) + list_for_each_entry_reverse(intf, &intf_list, list) mlx5_remove_device(intf, priv); list_del(&priv->dev_list); mutex_unlock(&mlx5_intf_mutex);

From: Subash Abhinov Kasiviswanathan subashab@codeaurora.org

[ Upstream commit a7cf3d24ee6081930feb4c830a7f6f16ebe31c49 ]

The udp_ip4_ind bit is set only for IPv4 UDP non-fragmented packets so that the hardware can flip the checksum to 0xFFFF if the computed checksum is 0 per RFC768.

However, this bit had to be set for IPv6 UDP non fragmented packets as well per hardware requirements. Otherwise, IPv6 UDP packets with computed checksum as 0 were transmitted by hardware and were dropped in the network.

In addition to setting this bit for IPv6 UDP, the field is also appropriately renamed to udp_ind as part of this change.

Fixes: 5eb5f8608ef1 ("net: qualcomm: rmnet: Add support for TX checksum offload") Cc: Sean Tranchetti stranche@codeaurora.org Signed-off-by: Subash Abhinov Kasiviswanathan subashab@codeaurora.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h | 2 +- drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c | 13 +++++++++---- 2 files changed, 10 insertions(+), 5 deletions(-)

--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h @@ -59,7 +59,7 @@ struct rmnet_map_dl_csum_trailer { struct rmnet_map_ul_csum_header { __be16 csum_start_offset; u16 csum_insert_offset:14; - u16 udp_ip4_ind:1; + u16 udp_ind:1; u16 csum_enabled:1; } __aligned(1);

--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c @@ -215,9 +215,9 @@ rmnet_map_ipv4_ul_csum_header(void *iphd ul_header->csum_insert_offset = skb->csum_offset; ul_header->csum_enabled = 1; if (ip4h->protocol == IPPROTO_UDP) - ul_header->udp_ip4_ind = 1; + ul_header->udp_ind = 1; else - ul_header->udp_ip4_ind = 0; + ul_header->udp_ind = 0;

/* Changing remaining fields to network order */ hdr++; @@ -248,6 +248,7 @@ rmnet_map_ipv6_ul_csum_header(void *ip6h struct rmnet_map_ul_csum_header *ul_header, struct sk_buff *skb) { + struct ipv6hdr *ip6h = (struct ipv6hdr *)ip6hdr; __be16 *hdr = (__be16 *)ul_header, offset;

offset = htons((__force u16)(skb_transport_header(skb) - @@ -255,7 +256,11 @@ rmnet_map_ipv6_ul_csum_header(void *ip6h ul_header->csum_start_offset = offset; ul_header->csum_insert_offset = skb->csum_offset; ul_header->csum_enabled = 1; - ul_header->udp_ip4_ind = 0; + + if (ip6h->nexthdr == IPPROTO_UDP) + ul_header->udp_ind = 1; + else + ul_header->udp_ind = 0;

/* Changing remaining fields to network order */ hdr++; @@ -428,7 +433,7 @@ sw_csum: ul_header->csum_start_offset = 0; ul_header->csum_insert_offset = 0; ul_header->csum_enabled = 0; - ul_header->udp_ip4_ind = 0; + ul_header->udp_ind = 0;

priv->stats.csum_sw++; }

From: Roman Mashak mrv@mojatatu.com

[ Upstream commit b35475c5491a14c8ce7a5046ef7bcda8a860581a ]

Add get_fill_size() routine used to calculate the action size when building a batch of events.

Fixes: c7e2b9689 ("sched: introduce vlan action") Signed-off-by: Roman Mashak mrv@mojatatu.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sched/act_vlan.c | 9 +++++++++ 1 file changed, 9 insertions(+)

--- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -296,6 +296,14 @@ static int tcf_vlan_search(struct net *n return tcf_idr_search(tn, a, index); }

+static size_t tcf_vlan_get_fill_size(const struct tc_action *act) +{ + return nla_total_size(sizeof(struct tc_vlan)) + + nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_ID */ + + nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_PROTOCOL */ + + nla_total_size(sizeof(u8)); /* TCA_VLAN_PUSH_VLAN_PRIORITY */ +} + static struct tc_action_ops act_vlan_ops = { .kind = "vlan", .type = TCA_ACT_VLAN, @@ -305,6 +313,7 @@ static struct tc_action_ops act_vlan_ops .init = tcf_vlan_init, .cleanup = tcf_vlan_cleanup, .walk = tcf_vlan_walker, + .get_fill_size = tcf_vlan_get_fill_size, .lookup = tcf_vlan_search, .size = sizeof(struct tcf_vlan), };

From: Ursula Braun ubraun@linux.ibm.com

[ Upstream commit f9cedf1a9b1cdcfb0c52edb391d01771e43994a4 ]

The setsockopts options TCP_NODELAY and TCP_CORK may schedule the tx worker. Make sure the socket is not yet moved into SMC_CLOSED state (for instance by a shutdown SHUT_RDWR call).

Reported-by: syzbot+92209502e7aab127c75f@syzkaller.appspotmail.com Reported-by: syzbot+b972214bb803a343f4fe@syzkaller.appspotmail.com Fixes: 01d2f7e2cdd31 ("net/smc: sockopts TCP_NODELAY and TCP_CORK") Signed-off-by: Ursula Braun ubraun@linux.ibm.com Signed-off-by: Karsten Graul kgraul@linux.ibm.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/smc/af_smc.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

--- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1680,14 +1680,18 @@ static int smc_setsockopt(struct socket } break; case TCP_NODELAY: - if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) { + if (sk->sk_state != SMC_INIT && + sk->sk_state != SMC_LISTEN && + sk->sk_state != SMC_CLOSED) { if (val && !smc->use_fallback) mod_delayed_work(system_wq, &smc->conn.tx_work, 0); } break; case TCP_CORK: - if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) { + if (sk->sk_state != SMC_INIT && + sk->sk_state != SMC_LISTEN && + sk->sk_state != SMC_CLOSED) { if (!val && !smc->use_fallback) mod_delayed_work(system_wq, &smc->conn.tx_work, 0);

From: Claudiu Manoil claudiu.manoil@nxp.com

[ Upstream commit c5d139697d5d9ecf9c7cd92d7d7838a173508900 ]

Make sure the delayed work for stats update is not pending before wq destruction. This fixes the module unload path. The issue is there since day 1.

Fixes: a556c76adc05 ("net: mscc: Add initial Ocelot switch support")

Signed-off-by: Claudiu Manoil claudiu.manoil@nxp.com Reviewed-by: Alexandre Belloni alexandre.belloni@bootlin.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mscc/ocelot.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1767,6 +1767,7 @@ EXPORT_SYMBOL(ocelot_init);

void ocelot_deinit(struct ocelot *ocelot) { + cancel_delayed_work(&ocelot->stats_work); destroy_workqueue(ocelot->stats_queue); mutex_destroy(&ocelot->stats_lock); }

From: Alexis Bauvin abauvin@scaleway.com

[ Upstream commit 4b663366246be1d1d4b1b8b01245b2e88ad9e706 ]

- v1 -> v2: Move skb_set_owner_w to __tun_build_skb to reduce patch size

Small packets going out of a tap device go through an optimized code path that uses build_skb() rather than sock_alloc_send_pskb(). The latter calls skb_set_owner_w(), but the small packet code path does not.

The net effect is that small packets are not owned by the userland application's socket (e.g. QEMU), while large packets are. This can be seen with a TCP session, where packets are not owned when the window size is small enough (around PAGE_SIZE), while they are once the window grows (note that this requires the host to support virtio tso for the guest to offload segmentation). All this leads to inconsistent behaviour in the kernel, especially on netfilter modules that uses sk->socket (e.g. xt_owner).

Fixes: 66ccbc9c87c2 ("tap: use build_skb() for small packet") Signed-off-by: Alexis Bauvin abauvin@scaleway.com Acked-by: Jason Wang jasowang@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/tun.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1682,6 +1682,7 @@ static struct sk_buff *tun_build_skb(str

skb_reserve(skb, pad - delta); skb_put(skb, len); + skb_set_owner_w(skb, tfile->socket.sk); get_page(alloc_frag->page); alloc_frag->offset += buflen;

From: Ariel Levkovich lariel@mellanox.com

[ Upstream commit 90bb769291161cf25a818d69cf608c181654473e ]

This patch prevents a race between user invoked cached counters query and a neighbor last usage updater.

The cached flow counter stats can be queried by calling "mlx5_fc_query_cached" which provides the number of bytes and packets that passed via this flow since the last time this counter was queried. It does so by reducting the last saved stats from the current, cached stats and then updating the last saved stats with the cached stats. It also provide the lastuse value for that flow.

Since "mlx5e_tc_update_neigh_used_value" needs to retrieve the last usage time of encapsulation flows, it calls the flow counter query method periodically and async to user queries of the flow counter using cls_flower. This call is causing the driver to update the last reported bytes and packets from the cache and therefore, future user queries of the flow stats will return lower than expected number for bytes and packets since the last saved stats in the driver was updated async to the last saved stats in cls_flower.

This causes wrong stats presentation of encapsulation flows to user.

Since the neighbor usage updater only needs the lastuse stats from the cached counter, the fix is to use a dedicated lastuse query call that returns the lastuse value without synching between the cached stats and the last saved stats.

Fixes: f6dfb4c3f216 ("net/mlx5e: Update neighbour 'used' state using HW flow rules counters") Signed-off-by: Ariel Levkovich lariel@mellanox.com Reviewed-by: Roi Dayan roid@mellanox.com Signed-off-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c | 5 +++++ include/linux/mlx5/fs.h | 1 + 3 files changed, 8 insertions(+), 2 deletions(-)

--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -992,13 +992,13 @@ void mlx5e_tc_encap_flows_del(struct mlx void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe) { struct mlx5e_neigh *m_neigh = &nhe->m_neigh; - u64 bytes, packets, lastuse = 0; struct mlx5e_tc_flow *flow; struct mlx5e_encap_entry *e; struct mlx5_fc *counter; struct neigh_table *tbl; bool neigh_used = false; struct neighbour *n; + u64 lastuse;

if (m_neigh->family == AF_INET) tbl = &arp_tbl; @@ -1015,7 +1015,7 @@ void mlx5e_tc_update_neigh_used_value(st list_for_each_entry(flow, &e->flows, encap) { if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) { counter = mlx5_flow_rule_counter(flow->rule[0]); - mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse); + lastuse = mlx5_fc_query_lastuse(counter); if (time_after((unsigned long)lastuse, nhe->reported_lastuse)) { neigh_used = true; break; --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -321,6 +321,11 @@ int mlx5_fc_query(struct mlx5_core_dev * } EXPORT_SYMBOL(mlx5_fc_query);

+u64 mlx5_fc_query_lastuse(struct mlx5_fc *counter) +{ + return counter->cache.lastuse; +} + void mlx5_fc_query_cached(struct mlx5_fc *counter, u64 *bytes, u64 *packets, u64 *lastuse) { --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -188,6 +188,7 @@ int mlx5_modify_rule_destination(struct struct mlx5_fc *mlx5_flow_rule_counter(struct mlx5_flow_handle *handler); struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging); void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter); +u64 mlx5_fc_query_lastuse(struct mlx5_fc *counter); void mlx5_fc_query_cached(struct mlx5_fc *counter, u64 *bytes, u64 *packets, u64 *lastuse); int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter,

From: Arnd Bergmann arnd@arndb.de

[ Upstream commit 055d88242a6046a1ceac3167290f054c72571cd9 ]

Support for handling the PPPOEIOCSFWD ioctl in compat mode was added in linux-2.5.69 along with hundreds of other commands, but was always broken sincen only the structure is compatible, but the command number is not, due to the size being sizeof(size_t), or at first sizeof(sizeof((struct sockaddr_pppox)), which is different on 64-bit architectures.

Guillaume Nault adds:

And the implementation was broken until 2016 (see 29e73269aa4d ("pppoe: fix reference counting in PPPoE proxy")), and nobody ever noticed. I should probably have removed this ioctl entirely instead of fixing it. Clearly, it has never been used.

Fix it by adding a compat_ioctl handler for all pppoe variants that translates the command number and then calls the regular ioctl function.

All other ioctl commands handled by pppoe are compatible between 32-bit and 64-bit, and require compat_ptr() conversion.

This should apply to all stable kernels.

Acked-by: Guillaume Nault g.nault@alphalink.fr Signed-off-by: Arnd Bergmann arnd@arndb.de Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ppp/pppoe.c | 3 +++ drivers/net/ppp/pppox.c | 13 +++++++++++++ drivers/net/ppp/pptp.c | 3 +++ fs/compat_ioctl.c | 3 --- include/linux/if_pppox.h | 3 +++ net/l2tp/l2tp_ppp.c | 3 +++ 6 files changed, 25 insertions(+), 3 deletions(-)

--- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -1120,6 +1120,9 @@ static const struct proto_ops pppoe_ops .recvmsg = pppoe_recvmsg, .mmap = sock_no_mmap, .ioctl = pppox_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = pppox_compat_ioctl, +#endif };

static const struct pppox_proto pppoe_proto = { --- a/drivers/net/ppp/pppox.c +++ b/drivers/net/ppp/pppox.c @@ -22,6 +22,7 @@ #include <linux/string.h> #include <linux/module.h> #include <linux/kernel.h> +#include <linux/compat.h> #include <linux/errno.h> #include <linux/netdevice.h> #include <linux/net.h> @@ -103,6 +104,18 @@ int pppox_ioctl(struct socket *sock, uns

EXPORT_SYMBOL(pppox_ioctl);

+#ifdef CONFIG_COMPAT +int pppox_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +{ + if (cmd == PPPOEIOCSFWD32) + cmd = PPPOEIOCSFWD; + + return pppox_ioctl(sock, cmd, (unsigned long)compat_ptr(arg)); +} + +EXPORT_SYMBOL(pppox_compat_ioctl); +#endif + static int pppox_create(struct net *net, struct socket *sock, int protocol, int kern) { --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -633,6 +633,9 @@ static const struct proto_ops pptp_ops = .recvmsg = sock_no_recvmsg, .mmap = sock_no_mmap, .ioctl = pppox_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = pppox_compat_ioctl, +#endif };

static const struct pppox_proto pppox_pptp_proto = { --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -894,9 +894,6 @@ COMPATIBLE_IOCTL(PPPIOCDISCONN) COMPATIBLE_IOCTL(PPPIOCATTCHAN) COMPATIBLE_IOCTL(PPPIOCGCHAN) COMPATIBLE_IOCTL(PPPIOCGL2TPSTATS) -/* PPPOX */ -COMPATIBLE_IOCTL(PPPOEIOCSFWD) -COMPATIBLE_IOCTL(PPPOEIOCDFWD) /* Big A */ /* sparc only */ /* Big Q for sound/OSS */ --- a/include/linux/if_pppox.h +++ b/include/linux/if_pppox.h @@ -84,6 +84,9 @@ extern int register_pppox_proto(int prot extern void unregister_pppox_proto(int proto_num); extern void pppox_unbind_sock(struct sock *sk);/* delete ppp-channel binding */ extern int pppox_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); +extern int pppox_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); + +#define PPPOEIOCSFWD32 _IOW(0xB1 ,0, compat_size_t)

/* PPPoX socket states */ enum { --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1686,6 +1686,9 @@ static const struct proto_ops pppol2tp_o .recvmsg = pppol2tp_recvmsg, .mmap = sock_no_mmap, .ioctl = pppox_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = pppox_compat_ioctl, +#endif };

static const struct pppox_proto pppol2tp_proto = {

From: Tejun Heo tj@kernel.org

commit b636fd38dc40113f853337a7d2a6885ad23b8811 upstream.

When a task is moved out of a cset, task iterators pointing to the task are advanced using the normal css_task_iter_advance() call. This is fine but we'll be tracking dying tasks on csets and thus moving tasks from cset->tasks to (to be added) cset->dying_tasks. When we remove a task from cset->tasks, if we advance the iterators, they may move over to the next cset before we had the chance to add the task back on the dying list, which can allow the task to escape iteration.

This patch separates out skipping from advancing. Skipping only moves the affected iterators to the next pointer rather than fully advancing it and the following advancing will recognize that the cursor has already been moved forward and do the rest of advancing. This ensures that when a task moves from one list to another in its cset, as long as it moves in the right direction, it's always visible to iteration.

This doesn't cause any visible behavior changes.

Signed-off-by: Tejun Heo tj@kernel.org Cc: Oleg Nesterov oleg@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- include/linux/cgroup.h | 3 ++ kernel/cgroup/cgroup.c | 60 +++++++++++++++++++++++++++++-------------------- 2 files changed, 39 insertions(+), 24 deletions(-)

--- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -43,6 +43,9 @@ /* walk all threaded css_sets in the domain */ #define CSS_TASK_ITER_THREADED (1U << 1)

+/* internal flags */ +#define CSS_TASK_ITER_SKIPPED (1U << 16) + /* a css_task_iter should be treated as an opaque object */ struct css_task_iter { struct cgroup_subsys *ss; --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -212,7 +212,8 @@ static struct cftype cgroup_base_files[]

static int cgroup_apply_control(struct cgroup *cgrp); static void cgroup_finalize_control(struct cgroup *cgrp, int ret); -static void css_task_iter_advance(struct css_task_iter *it); +static void css_task_iter_skip(struct css_task_iter *it, + struct task_struct *task); static int cgroup_destroy_locked(struct cgroup *cgrp); static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, struct cgroup_subsys *ss); @@ -775,6 +776,21 @@ static void css_set_update_populated(str cgroup_update_populated(link->cgrp, populated); }

+/* + * @task is leaving, advance task iterators which are pointing to it so + * that they can resume at the next position. Advancing an iterator might + * remove it from the list, use safe walk. See css_task_iter_skip() for + * details. + */ +static void css_set_skip_task_iters(struct css_set *cset, + struct task_struct *task) +{ + struct css_task_iter *it, *pos; + + list_for_each_entry_safe(it, pos, &cset->task_iters, iters_node) + css_task_iter_skip(it, task); +} + /** * css_set_move_task - move a task from one css_set to another * @task: task being moved @@ -800,22 +816,9 @@ static void css_set_move_task(struct tas css_set_update_populated(to_cset, true);

if (from_cset) { - struct css_task_iter *it, *pos; - WARN_ON_ONCE(list_empty(&task->cg_list));

- /* - * @task is leaving, advance task iterators which are - * pointing to it so that they can resume at the next - * position. Advancing an iterator might remove it from - * the list, use safe walk. See css_task_iter_advance*() - * for details. - */ - list_for_each_entry_safe(it, pos, &from_cset->task_iters, - iters_node) - if (it->task_pos == &task->cg_list) - css_task_iter_advance(it); - + css_set_skip_task_iters(from_cset, task); list_del_init(&task->cg_list); if (!css_set_populated(from_cset)) css_set_update_populated(from_cset, false); @@ -4183,10 +4186,19 @@ static void css_task_iter_advance_css_se list_add(&it->iters_node, &cset->task_iters); }

-static void css_task_iter_advance(struct css_task_iter *it) +static void css_task_iter_skip(struct css_task_iter *it, + struct task_struct *task) { - struct list_head *next; + lockdep_assert_held(&css_set_lock); + + if (it->task_pos == &task->cg_list) { + it->task_pos = it->task_pos->next; + it->flags |= CSS_TASK_ITER_SKIPPED; + } +}

+static void css_task_iter_advance(struct css_task_iter *it) +{ lockdep_assert_held(&css_set_lock); repeat: if (it->task_pos) { @@ -4195,15 +4207,15 @@ repeat: * consumed first and then ->mg_tasks. After ->mg_tasks, * we move onto the next cset. */ - next = it->task_pos->next; - - if (next == it->tasks_head) - next = it->mg_tasks_head->next; + if (it->flags & CSS_TASK_ITER_SKIPPED) + it->flags &= ~CSS_TASK_ITER_SKIPPED; + else + it->task_pos = it->task_pos->next;

- if (next == it->mg_tasks_head) + if (it->task_pos == it->tasks_head) + it->task_pos = it->mg_tasks_head->next; + if (it->task_pos == it->mg_tasks_head) css_task_iter_advance_css_set(it); - else - it->task_pos = next; } else { /* called from start, proceed to the first cset */ css_task_iter_advance_css_set(it);

From: Tejun Heo tj@kernel.org

commit cee0c33c546a93957a52ae9ab6bebadbee765ec5 upstream.

b636fd38dc40 ("cgroup: Implement css_task_iter_skip()") introduced css_task_iter_skip() which is used to fix task iterations skipping dying threadgroup leaders with live threads. Skipping is implemented as a subportion of full advancing but css_task_iter_next() forgot to fully advance a skipped iterator before determining the next task to visit causing it to return invalid task pointers.

Fix it by making css_task_iter_next() fully advance the iterator if it has been skipped since the previous iteration.

Signed-off-by: Tejun Heo tj@kernel.org Reported-by: syzbot Link: http://lkml.kernel.org/r/00000000000097025d058a7fd785@google.com Fixes: b636fd38dc40 ("cgroup: Implement css_task_iter_skip()") Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- kernel/cgroup/cgroup.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4303,6 +4303,10 @@ struct task_struct *css_task_iter_next(s

spin_lock_irq(&css_set_lock);

+ /* @it may be half-advanced by skips, finish advancing */ + if (it->flags & CSS_TASK_ITER_SKIPPED) + css_task_iter_advance(it); + if (it->task_pos) { it->cur_task = list_entry(it->task_pos, struct task_struct, cg_list);

From: Lukas Wunner lukas@wunner.de

commit 8d8bef50365847134b51c1ec46786bc2873e4e47 upstream.

Commit 6935224da248 ("spi: bcm2835: enable support of 3-wire mode") added 3-wire support to the BCM2835 SPI driver by setting the REN bit (Read Enable) in the CS register when receiving data. The REN bit puts the transmitter in high-impedance state. The driver recognizes that data is to be received by checking whether the rx_buf of a transfer is non-NULL.

Commit 3ecd37edaa2a ("spi: bcm2835: enable dma modes for transfers meeting certain conditions") subsequently broke 3-wire support because it set the SPI_MASTER_MUST_RX flag which causes spi_map_msg() to replace rx_buf with a dummy buffer if it is NULL. As a result, rx_buf is *always* non-NULL if DMA is enabled.

Reinstate 3-wire support by not only checking whether rx_buf is non-NULL, but also checking that it is not the dummy buffer.

Fixes: 3ecd37edaa2a ("spi: bcm2835: enable dma modes for transfers meeting certain conditions") Reported-by: Nuno Sá nuno.sa@analog.com Signed-off-by: Lukas Wunner lukas@wunner.de Cc: stable@vger.kernel.org # v4.2+ Cc: Martin Sperl kernel@martin.sperl.org Acked-by: Stefan Wahren wahrenst@gmx.net Link: https://lore.kernel.org/r/328318841455e505370ef8ecad97b646c033dc8a.156214852... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/spi/spi-bcm2835.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/spi/spi-bcm2835.c +++ b/drivers/spi/spi-bcm2835.c @@ -554,7 +554,8 @@ static int bcm2835_spi_transfer_one(stru bcm2835_wr(bs, BCM2835_SPI_CLK, cdiv);

/* handle all the 3-wire mode */ - if ((spi->mode & SPI_3WIRE) && (tfr->rx_buf)) + if (spi->mode & SPI_3WIRE && tfr->rx_buf && + tfr->rx_buf != master->dummy_rx) cs |= BCM2835_SPI_CS_REN; else cs &= ~BCM2835_SPI_CS_REN;