From: NeilBrown neilb@suse.com

[ Upstream commit dce2630c7da73b0634686bca557cc8945cc450c8 ]

There are 2 comments in the NFSv4 code which suggest that SIGLOST should possibly be sent to a process. In these cases a lock has been lost. The current practice is to set NFS_LOCK_LOST so that read/write returns EIO when a lock is lost. So change these comments to code when sets NFS_LOCK_LOST.

One case is when lock recovery after apparent server restart fails with NFS4ERR_DENIED, NFS4ERR_RECLAIM_BAD, or NFS4ERRO_RECLAIM_CONFLICT. The other case is when a lock attempt as part of lease recovery fails with NFS4ERR_DENIED.

In an ideal world, these should not happen. However I have a packet trace showing an NFSv4.1 session getting NFS4ERR_BADSESSION after an extended network parition. The NFSv4.1 client treats this like server reboot until/unless it get NFS4ERR_NO_GRACE, in which case it switches over to "nograce" recovery mode. In this network trace, the client attempts to recover a lock and the server (incorrectly) reports NFS4ERR_DENIED rather than NFS4ERR_NO_GRACE. This leads to the ineffective comment and the client then continues to write using the OPEN stateid.

Signed-off-by: NeilBrown neilb@suse.com Signed-off-by: Trond Myklebust trond.myklebust@primarydata.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- fs/nfs/nfs4proc.c | 12 ++++++++---- fs/nfs/nfs4state.c | 5 ++++- 2 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 56fa5a16e097..083802f7a1e9 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2019,7 +2019,7 @@ static int nfs4_open_reclaim(struct nfs4_state_owner *sp, struct nfs4_state *sta return ret; }

-static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct nfs4_state *state, const nfs4_stateid *stateid, int err) +static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct nfs4_state *state, const nfs4_stateid *stateid, struct file_lock *fl, int err) { switch (err) { default: @@ -2066,7 +2066,11 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct return -EAGAIN; case -ENOMEM: case -NFS4ERR_DENIED: - /* kill_proc(fl->fl_pid, SIGLOST, 1); */ + if (fl) { + struct nfs4_lock_state *lsp = fl->fl_u.nfs4_fl.owner; + if (lsp) + set_bit(NFS_LOCK_LOST, &lsp->ls_flags); + } return 0; } return err; @@ -2102,7 +2106,7 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, err = nfs4_open_recover_helper(opendata, FMODE_READ); } nfs4_opendata_put(opendata); - return nfs4_handle_delegation_recall_error(server, state, stateid, err); + return nfs4_handle_delegation_recall_error(server, state, stateid, NULL, err); }

static void nfs4_open_confirm_prepare(struct rpc_task *task, void *calldata) @@ -6739,7 +6743,7 @@ int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, if (err != 0) return err; err = _nfs4_do_setlk(state, F_SETLK, fl, NFS_LOCK_NEW); - return nfs4_handle_delegation_recall_error(server, state, stateid, err); + return nfs4_handle_delegation_recall_error(server, state, stateid, fl, err); }

struct nfs_release_lockowner_data { diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index e4f4a09ed9f4..91a4d4eeb235 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1482,6 +1482,7 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_ struct inode *inode = state->inode; struct nfs_inode *nfsi = NFS_I(inode); struct file_lock *fl; + struct nfs4_lock_state *lsp; int status = 0; struct file_lock_context *flctx = inode->i_flctx; struct list_head *list; @@ -1522,7 +1523,9 @@ restart: case -NFS4ERR_DENIED: case -NFS4ERR_RECLAIM_BAD: case -NFS4ERR_RECLAIM_CONFLICT: - /* kill_proc(fl->fl_pid, SIGLOST, 1); */ + lsp = fl->fl_u.nfs4_fl.owner; + if (lsp) + set_bit(NFS_LOCK_LOST, &lsp->ls_flags); status = 0; } spin_lock(&flctx->flc_lock);

From: Marek Szyprowski m.szyprowski@samsung.com

[ Upstream commit 0c4c5860e9983eb3da7a3d73ca987643c3ed034b ]

Initialize data->config_lock mutex before it is used by the driver code.

This fixes following warning on Odroid XU3 boards:

INFO: trying to register non-static key. the code is fine but needs lockdep annotation. turning off the locking correctness validator. CPU: 5 PID: 1 Comm: swapper/0 Not tainted 4.15.0-rc7-next-20180115-00001-gb75575dee3f2 #107 Hardware name: SAMSUNG EXYNOS (Flattened Device Tree) [<c0111504>] (unwind_backtrace) from [<c010dbec>] (show_stack+0x10/0x14) [<c010dbec>] (show_stack) from [<c09b3f74>] (dump_stack+0x90/0xc8) [<c09b3f74>] (dump_stack) from [<c0179528>] (register_lock_class+0x1c0/0x59c) [<c0179528>] (register_lock_class) from [<c017bd1c>] (__lock_acquire+0x78/0x1850) [<c017bd1c>] (__lock_acquire) from [<c017de30>] (lock_acquire+0xc8/0x2b8) [<c017de30>] (lock_acquire) from [<c09ca59c>] (__mutex_lock+0x60/0xa0c) [<c09ca59c>] (__mutex_lock) from [<c09cafd0>] (mutex_lock_nested+0x1c/0x24) [<c09cafd0>] (mutex_lock_nested) from [<c068b0d0>] (ina2xx_set_shunt+0x70/0xb0) [<c068b0d0>] (ina2xx_set_shunt) from [<c068b218>] (ina2xx_probe+0x88/0x1b0) [<c068b218>] (ina2xx_probe) from [<c0673d90>] (i2c_device_probe+0x1e0/0x2d0) [<c0673d90>] (i2c_device_probe) from [<c053a268>] (driver_probe_device+0x2b8/0x4a0) [<c053a268>] (driver_probe_device) from [<c053a54c>] (__driver_attach+0xfc/0x120) [<c053a54c>] (__driver_attach) from [<c05384cc>] (bus_for_each_dev+0x58/0x7c) [<c05384cc>] (bus_for_each_dev) from [<c0539590>] (bus_add_driver+0x174/0x250) [<c0539590>] (bus_add_driver) from [<c053b5e0>] (driver_register+0x78/0xf4) [<c053b5e0>] (driver_register) from [<c0675ef0>] (i2c_register_driver+0x38/0xa8) [<c0675ef0>] (i2c_register_driver) from [<c0102b40>] (do_one_initcall+0x48/0x18c) [<c0102b40>] (do_one_initcall) from [<c0e00df0>] (kernel_init_freeable+0x110/0x1d4) [<c0e00df0>] (kernel_init_freeable) from [<c09c8120>] (kernel_init+0x8/0x114) [<c09c8120>] (kernel_init) from [<c01010b4>] (ret_from_fork+0x14/0x20)

Fixes: 5d389b125186 ("hwmon: (ina2xx) Make calibration register value fixed") Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/hwmon/ina2xx.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/hwmon/ina2xx.c b/drivers/hwmon/ina2xx.c index 62e38fa8cda2..a55823b52b2f 100644 --- a/drivers/hwmon/ina2xx.c +++ b/drivers/hwmon/ina2xx.c @@ -438,6 +438,7 @@ static int ina2xx_probe(struct i2c_client *client,

/* set the device type */ data->config = &ina2xx_config[chip]; + mutex_init(&data->config_lock);

if (of_property_read_u32(dev->of_node, "shunt-resistor", &val) < 0) { struct ina2xx_platform_data *pdata = dev_get_platdata(dev); @@ -467,8 +468,6 @@ static int ina2xx_probe(struct i2c_client *client, return -ENODEV; }

- mutex_init(&data->config_lock); - data->groups[group++] = &ina2xx_group; if (id->driver_data == ina226) data->groups[group++] = &ina226_group;

From: Jon Maloy jon.maloy@ericsson.com

[ Upstream commit febafc8455fdbb0ba53d596075068a683b75f355 ]

In commit d12d2e12cec2 "tipc: send out join messages as soon as new member is discovered") we added a call to the function tipc_group_join() without considering the case that the preceding tipc_sk_publish() might have failed, and the group item already deleted.

We fix this by returning from tipc_sk_join() directly after the failed tipc_sk_publish.

Reported-by: syzbot+e3eeae78ea88b8d6d858@syzkaller.appspotmail.com Signed-off-by: Jon Maloy jon.maloy@ericsson.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- net/tipc/socket.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 3b4084480377..8efd2e42de30 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2759,6 +2759,7 @@ static int tipc_sk_join(struct tipc_sock *tsk, struct tipc_group_req *mreq) if (rc) { tipc_group_delete(net, grp); tsk->group = NULL; + return rc; }

/* Eliminate any risk that a broadcast overtakes the sent JOIN */

From: Dan Carpenter dan.carpenter@oracle.com

[ Upstream commit 123af9043e93cb6f235207d260d50f832cdb5439 ]

The loop timeout doesn't work because it's a post op and ends with "tmo" set to -1. I changed it from a post-op to a pre-op and I changed the initial the starting value from 5 to 6 so we still iterate 5 times. I left the other as it was because it's a large number.

Fixes: b3c70c9ea62a ("ASoC: Alchemy AC97C/I2SC audio support") Signed-off-by: Dan Carpenter dan.carpenter@oracle.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- sound/soc/au1x/ac97c.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/sound/soc/au1x/ac97c.c b/sound/soc/au1x/ac97c.c index 29a97d52e8ad..66d6c52e7761 100644 --- a/sound/soc/au1x/ac97c.c +++ b/sound/soc/au1x/ac97c.c @@ -91,8 +91,8 @@ static unsigned short au1xac97c_ac97_read(struct snd_ac97 *ac97, do { mutex_lock(&ctx->lock);

- tmo = 5; - while ((RD(ctx, AC97_STATUS) & STAT_CP) && tmo--) + tmo = 6; + while ((RD(ctx, AC97_STATUS) & STAT_CP) && --tmo) udelay(21); /* wait an ac97 frame time */ if (!tmo) { pr_debug("ac97rd timeout #1\n"); @@ -105,7 +105,7 @@ static unsigned short au1xac97c_ac97_read(struct snd_ac97 *ac97, * poll, Forrest, poll... */ tmo = 0x10000; - while ((RD(ctx, AC97_STATUS) & STAT_CP) && tmo--) + while ((RD(ctx, AC97_STATUS) & STAT_CP) && --tmo) asm volatile ("nop"); data = RD(ctx, AC97_CMDRESP);

From: Parav Pandit parav@mellanox.com

[ Upstream commit a6532e7139660c103dda181aa5b2c734aa26ed6c ]

iWARP does not use rdma_ah_attr_type, and for this reason we do not have a RDMA_AH_ATTR_TYPE_IWARP. rdma_ah_find_type should not even be called on iwarp ports and for clarity it shouldn't have a special test for iWarp.

This changes the result from RDMA_AH_ATTR_TYPE_ROCE to RDMA_AH_ATTR_TYPE_IB when wrongly called on an iWarp port.

Fixes: 44c58487d51a ("IB/core: Define 'ib' and 'roce' rdma_ah_attr types") Signed-off-by: Parav Pandit parav@mellanox.com Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- include/rdma/ib_verbs.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 0d6a110dae7c..20ebf9061962 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -3793,8 +3793,7 @@ static inline void rdma_ah_set_grh(struct rdma_ah_attr *attr, static inline enum rdma_ah_attr_type rdma_ah_find_type(struct ib_device *dev, u32 port_num) { - if ((rdma_protocol_roce(dev, port_num)) || - (rdma_protocol_iwarp(dev, port_num))) + if (rdma_protocol_roce(dev, port_num)) return RDMA_AH_ATTR_TYPE_ROCE; else if ((rdma_protocol_ib(dev, port_num)) && (rdma_cap_opa_ah(dev, port_num)))

From: Subash Abhinov Kasiviswanathan subashab@codeaurora.org

[ Upstream commit 83f1999caeb14e15df205e80d210699951733287 ]

ipv6_defrag pulls network headers before fragment header. In case of an error, the netfilter layer is currently dropping these packets. This results in failure of some IPv6 standards tests which passed on older kernels due to the netfilter framework using cloning.

The test case run here is a check for ICMPv6 error message replies when some invalid IPv6 fragments are sent. This specific test case is listed in https://www.ipv6ready.org/docs/Core_Conformance_Latest.pdf in the Extension Header Processing Order section.

A packet with unrecognized option Type 11 is sent and the test expects an ICMP error in line with RFC2460 section 4.2 -

11 - discard the packet and, only if the packet's Destination Address was not a multicast address, send an ICMP Parameter Problem, Code 2, message to the packet's Source Address, pointing to the unrecognized Option Type.

Since netfilter layer now drops all invalid IPv6 frag packets, we no longer see the ICMP error message and fail the test case.

To fix this, save the transport header. If defrag is unable to process the packet due to RFC2460, restore the transport header and allow packet to be processed by stack. There is no change for other packet processing paths.

Tested by confirming that stack sends an ICMP error when it receives these packets. Also tested that fragmented ICMP pings succeed.

v1->v2: Instead of cloning always, save the transport_header and restore it in case of this specific error. Update the title and commit message accordingly.

Signed-off-by: Subash Abhinov Kasiviswanathan subashab@codeaurora.org Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- net/ipv6/netfilter/nf_conntrack_reasm.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 977d8900cfd1..ce53dcfda88a 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -231,7 +231,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,

if ((unsigned int)end > IPV6_MAXPLEN) { pr_debug("offset is too large.\n"); - return -1; + return -EINVAL; }

ecn = ip6_frag_ecn(ipv6_hdr(skb)); @@ -264,7 +264,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, * this case. -DaveM */ pr_debug("end of fragment not rounded to 8 bytes.\n"); - return -1; + return -EPROTO; } if (end > fq->q.len) { /* Some bits beyond end -> corruption. */ @@ -358,7 +358,7 @@ found: discard_fq: inet_frag_kill(&fq->q, &nf_frags); err: - return -1; + return -EINVAL; }

/* @@ -567,6 +567,7 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff)

int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) { + u16 savethdr = skb->transport_header; struct net_device *dev = skb->dev; int fhoff, nhoff, ret; struct frag_hdr *fhdr; @@ -600,8 +601,12 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)

spin_lock_bh(&fq->q.lock);

- if (nf_ct_frag6_queue(fq, skb, fhdr, nhoff) < 0) { - ret = -EINVAL; + ret = nf_ct_frag6_queue(fq, skb, fhdr, nhoff); + if (ret < 0) { + if (ret == -EPROTO) { + skb->transport_header = savethdr; + ret = 0; + } goto out_unlock; }

From: Hans de Goede hdegoede@redhat.com

[ Upstream commit 4d6bde512a86c32df3a1f289d2b4cd04b17758d1 ]

On some Dell XPS models WMI events of type 0x0000 reporting a keycode of 0xe00c get reported when the brightness of the LCD panel changes.

This leads to us reporting false-positive kbd_led change events to userspace which in turn leads to the kbd backlight OSD showing when it should not.

We already read the current keyboard backlight brightness value when reporting events because the led_classdev_notify_brightness_hw_changed API requires this. Compare this value to the last known value and filter out duplicate events, fixing this.

Note the fixed issue is esp. a problem on XPS models with an ambient light sensor and automatic brightness adjustments turned on, this causes the kbd backlight OSD to show all the time there.

BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=1514969 Fixes: 9c656b0799 ("platform/x86: dell-*: Call new led hw_changed API ...") Acked-by: Pali Rohár pali.rohar@gmail.com Signed-off-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/platform/x86/dell-laptop.c | 24 ++++++++++++++++++++++-- 1 file changed, 22 insertions(+), 2 deletions(-)

diff --git a/drivers/platform/x86/dell-laptop.c b/drivers/platform/x86/dell-laptop.c index c864430b9fcf..8ddb309cfc85 100644 --- a/drivers/platform/x86/dell-laptop.c +++ b/drivers/platform/x86/dell-laptop.c @@ -1149,6 +1149,7 @@ static u8 kbd_previous_mode_bit;

static bool kbd_led_present; static DEFINE_MUTEX(kbd_led_mutex); +static enum led_brightness kbd_led_level;

/* * NOTE: there are three ways to set the keyboard backlight level. @@ -1971,6 +1972,7 @@ static enum led_brightness kbd_led_level_get(struct led_classdev *led_cdev) static int kbd_led_level_set(struct led_classdev *led_cdev, enum led_brightness value) { + enum led_brightness new_value = value; struct kbd_state state; struct kbd_state new_state; u16 num; @@ -2000,6 +2002,9 @@ static int kbd_led_level_set(struct led_classdev *led_cdev, }

out: + if (ret == 0) + kbd_led_level = new_value; + mutex_unlock(&kbd_led_mutex); return ret; } @@ -2027,6 +2032,9 @@ static int __init kbd_led_init(struct device *dev) if (kbd_led.max_brightness) kbd_led.max_brightness--; } + + kbd_led_level = kbd_led_level_get(NULL); + ret = led_classdev_register(dev, &kbd_led); if (ret) kbd_led_present = false; @@ -2051,13 +2059,25 @@ static void kbd_led_exit(void) static int dell_laptop_notifier_call(struct notifier_block *nb, unsigned long action, void *data) { + bool changed = false; + enum led_brightness new_kbd_led_level; + switch (action) { case DELL_LAPTOP_KBD_BACKLIGHT_BRIGHTNESS_CHANGED: if (!kbd_led_present) break;

- led_classdev_notify_brightness_hw_changed(&kbd_led, - kbd_led_level_get(&kbd_led)); + mutex_lock(&kbd_led_mutex); + new_kbd_led_level = kbd_led_level_get(&kbd_led); + if (kbd_led_level != new_kbd_led_level) { + kbd_led_level = new_kbd_led_level; + changed = true; + } + mutex_unlock(&kbd_led_mutex); + + if (changed) + led_classdev_notify_brightness_hw_changed(&kbd_led, + kbd_led_level); break; }

From: Chuck Lever chuck.lever@oracle.com

[ Upstream commit d698c4a02ee02053bbebe051322ff427a2dad56a ]

The backchannel code uses rpcrdma_recv_buffer_put to add new reps to the free rep list. This also decrements rb_recv_count, which spoofs the receive overrun logic in rpcrdma_buffer_get_rep.

Commit 9b06688bc3b9 ("xprtrdma: Fix additional uses of spin_lock_irqsave(rb_lock)") replaced the original open-coded list_add with a call to rpcrdma_recv_buffer_put(), but then a year later, commit 05c974669ece ("xprtrdma: Fix receive buffer accounting") added rep accounting to rpcrdma_recv_buffer_put. It was an oversight to let the backchannel continue to use this function.

The fix this, let's combine the "add to free list" logic with rpcrdma_create_rep.

Also, do not allocate RPCRDMA_MAX_BC_REQUESTS rpcrdma_reps in rpcrdma_buffer_create and then allocate additional rpcrdma_reps in rpcrdma_bc_setup_reps. Allocating the extra reps during backchannel set-up is sufficient.

Fixes: 05c974669ece ("xprtrdma: Fix receive buffer accounting") Signed-off-by: Chuck Lever chuck.lever@oracle.com Signed-off-by: Anna Schumaker Anna.Schumaker@Netapp.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- net/sunrpc/xprtrdma/backchannel.c | 12 ++---------- net/sunrpc/xprtrdma/verbs.c | 32 +++++++++++++++++++------------- net/sunrpc/xprtrdma/xprt_rdma.h | 2 +- 3 files changed, 22 insertions(+), 24 deletions(-)

diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index 8b818bb3518a..256c67b433c1 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -74,21 +74,13 @@ out_fail: static int rpcrdma_bc_setup_reps(struct rpcrdma_xprt *r_xprt, unsigned int count) { - struct rpcrdma_rep *rep; int rc = 0;

while (count--) { - rep = rpcrdma_create_rep(r_xprt); - if (IS_ERR(rep)) { - pr_err("RPC: %s: reply buffer alloc failed\n", - __func__); - rc = PTR_ERR(rep); + rc = rpcrdma_create_rep(r_xprt); + if (rc) break; - } - - rpcrdma_recv_buffer_put(rep); } - return rc; }

diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 8cd7ee4fa0cd..371fbd9b55bb 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -1093,10 +1093,17 @@ rpcrdma_create_req(struct rpcrdma_xprt *r_xprt) return req; }

-struct rpcrdma_rep * +/** + * rpcrdma_create_rep - Allocate an rpcrdma_rep object + * @r_xprt: controlling transport + * + * Returns 0 on success or a negative errno on failure. + */ +int rpcrdma_create_rep(struct rpcrdma_xprt *r_xprt) { struct rpcrdma_create_data_internal *cdata = &r_xprt->rx_data; + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; struct rpcrdma_rep *rep; int rc;

@@ -1121,12 +1128,18 @@ rpcrdma_create_rep(struct rpcrdma_xprt *r_xprt) rep->rr_recv_wr.wr_cqe = &rep->rr_cqe; rep->rr_recv_wr.sg_list = &rep->rr_rdmabuf->rg_iov; rep->rr_recv_wr.num_sge = 1; - return rep; + + spin_lock(&buf->rb_lock); + list_add(&rep->rr_list, &buf->rb_recv_bufs); + spin_unlock(&buf->rb_lock); + return 0;

out_free: kfree(rep); out: - return ERR_PTR(rc); + dprintk("RPC: %s: reply buffer %d alloc failed\n", + __func__, rc); + return rc; }

int @@ -1167,17 +1180,10 @@ rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) }

INIT_LIST_HEAD(&buf->rb_recv_bufs); - for (i = 0; i < buf->rb_max_requests + RPCRDMA_MAX_BC_REQUESTS; i++) { - struct rpcrdma_rep *rep; - - rep = rpcrdma_create_rep(r_xprt); - if (IS_ERR(rep)) { - dprintk("RPC: %s: reply buffer %d alloc failed\n", - __func__, i); - rc = PTR_ERR(rep); + for (i = 0; i <= buf->rb_max_requests; i++) { + rc = rpcrdma_create_rep(r_xprt); + if (rc) goto out; - } - list_add(&rep->rr_list, &buf->rb_recv_bufs); }

rc = rpcrdma_sendctxs_create(r_xprt); diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 1342f743f1c4..3b63e61feae2 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -564,8 +564,8 @@ int rpcrdma_ep_post_recv(struct rpcrdma_ia *, struct rpcrdma_rep *); * Buffer calls - xprtrdma/verbs.c */ struct rpcrdma_req *rpcrdma_create_req(struct rpcrdma_xprt *); -struct rpcrdma_rep *rpcrdma_create_rep(struct rpcrdma_xprt *); void rpcrdma_destroy_req(struct rpcrdma_req *); +int rpcrdma_create_rep(struct rpcrdma_xprt *r_xprt); int rpcrdma_buffer_create(struct rpcrdma_xprt *); void rpcrdma_buffer_destroy(struct rpcrdma_buffer *); struct rpcrdma_sendctx *rpcrdma_sendctx_get_locked(struct rpcrdma_buffer *buf);

From: "Steven Rostedt (VMware)" rostedt@goodmis.org

[ Upstream commit dbdda842fe96f8932bae554f0adf463c27c42bc7 ]

This patch implements what I discussed in Kernel Summit. I added lockdep annotation (hopefully correctly), and it hasn't had any splats (since I fixed some bugs in the first iterations). It did catch problems when I had the owner covering too much. But now that the owner is only set when actively calling the consoles, lockdep has stayed quiet.

Here's the design again:

I added a "console_owner" which is set to a task that is actively writing to the consoles. It is *not* the same as the owner of the console_lock. It is only set when doing the calls to the console functions. It is protected by a console_owner_lock which is a raw spin lock.

There is a console_waiter. This is set when there is an active console owner that is not current, and waiter is not set. This too is protected by console_owner_lock.

In printk() when it tries to write to the consoles, we have:

if (console_trylock()) console_unlock();

Now I added an else, which will check if there is an active owner, and no current waiter. If that is the case, then console_waiter is set, and the task goes into a spin until it is no longer set.

When the active console owner finishes writing the current message to the consoles, it grabs the console_owner_lock and sees if there is a waiter, and clears console_owner.

If there is a waiter, then it breaks out of the loop, clears the waiter flag (because that will release the waiter from its spin), and exits. Note, it does *not* release the console semaphore. Because it is a semaphore, there is no owner. Another task may release it. This means that the waiter is guaranteed to be the new console owner! Which it becomes.

Then the waiter calls console_unlock() and continues to write to the consoles.

If another task comes along and does a printk() it too can become the new waiter, and we wash rinse and repeat!

By Petr Mladek about possible new deadlocks:

The thing is that we move console_sem only to printk() call that normally calls console_unlock() as well. It means that the transferred owner should not bring new type of dependencies. As Steven said somewhere: "If there is a deadlock, it was there even before."

We could look at it from this side. The possible deadlock would look like:

CPU0 CPU1

console_unlock()

console_owner = current;

spin_lockA() printk() spin = true; while (...)

call_console_drivers() spin_lockA()

This would be a deadlock. CPU0 would wait for the lock A. While CPU1 would own the lockA and would wait for CPU0 to finish calling the console drivers and pass the console_sem owner.

But if the above is true than the following scenario was already possible before:

CPU0

spin_lockA() printk() console_unlock() call_console_drivers() spin_lockA()

By other words, this deadlock was there even before. Such deadlocks are prevented by using printk_deferred() in the sections guarded by the lock A.

By Steven Rostedt:

To demonstrate the issue, this module has been shown to lock up a system with 4 CPUs and a slow console (like a serial console). It is also able to lock up a 8 CPU system with only a fast (VGA) console, by passing in "loops=100". The changes in this commit prevent this module from locking up the system.

#include <linux/module.h> #include <linux/delay.h> #include <linux/sched.h> #include <linux/mutex.h> #include <linux/workqueue.h> #include <linux/hrtimer.h>

static bool stop_testing; static unsigned int loops = 1;

static void preempt_printk_workfn(struct work_struct *work) { int i;

while (!READ_ONCE(stop_testing)) { for (i = 0; i < loops && !READ_ONCE(stop_testing); i++) { preempt_disable(); pr_emerg("%5d%-75s\n", smp_processor_id(), " XXX NOPREEMPT"); preempt_enable(); } msleep(1); } }

static struct work_struct __percpu *works;

static void finish(void) { int cpu;

WRITE_ONCE(stop_testing, true); for_each_online_cpu(cpu) flush_work(per_cpu_ptr(works, cpu)); free_percpu(works); }

static int __init test_init(void) { int cpu;

works = alloc_percpu(struct work_struct); if (!works) return -ENOMEM;

/* * This is just a test module. This will break if you * do any CPU hot plugging between loading and * unloading the module. */

for_each_online_cpu(cpu) { struct work_struct *work = per_cpu_ptr(works, cpu);

INIT_WORK(work, &preempt_printk_workfn); schedule_work_on(cpu, work); }

return 0; }

static void __exit test_exit(void) { finish(); }

module_param(loops, uint, 0); module_init(test_init); module_exit(test_exit); MODULE_LICENSE("GPL");

Link: http://lkml.kernel.org/r/20180110132418.7080-2-pmladek@suse.com Cc: akpm@linux-foundation.org Cc: linux-mm@kvack.org Cc: Cong Wang xiyou.wangcong@gmail.com Cc: Dave Hansen dave.hansen@intel.com Cc: Johannes Weiner hannes@cmpxchg.org Cc: Mel Gorman mgorman@suse.de Cc: Michal Hocko mhocko@kernel.org Cc: Vlastimil Babka vbabka@suse.cz Cc: Peter Zijlstra peterz@infradead.org Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Jan Kara jack@suse.cz Cc: Mathieu Desnoyers mathieu.desnoyers@efficios.com Cc: Tetsuo Handa penguin-kernel@I-love.SAKURA.ne.jp Cc: Byungchul Park byungchul.park@lge.com Cc: Tejun Heo tj@kernel.org Cc: Pavel Machek pavel@ucw.cz Cc: linux-kernel@vger.kernel.org Signed-off-by: Steven Rostedt (VMware) rostedt@goodmis.org [pmladek@suse.com: Commit message about possible deadlocks] Acked-by: Sergey Senozhatsky sergey.senozhatsky@gmail.com Signed-off-by: Petr Mladek pmladek@suse.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- kernel/printk/printk.c | 108 ++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 107 insertions(+), 1 deletion(-)

diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index b9006617710f..7e6459abba43 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -86,8 +86,15 @@ EXPORT_SYMBOL_GPL(console_drivers); static struct lockdep_map console_lock_dep_map = { .name = "console_lock" }; +static struct lockdep_map console_owner_dep_map = { + .name = "console_owner" +}; #endif

+static DEFINE_RAW_SPINLOCK(console_owner_lock); +static struct task_struct *console_owner; +static bool console_waiter; + enum devkmsg_log_bits { __DEVKMSG_LOG_BIT_ON = 0, __DEVKMSG_LOG_BIT_OFF, @@ -1753,8 +1760,56 @@ asmlinkage int vprintk_emit(int facility, int level, * semaphore. The release will print out buffers and wake up * /dev/kmsg and syslog() users. */ - if (console_trylock()) + if (console_trylock()) { console_unlock(); + } else { + struct task_struct *owner = NULL; + bool waiter; + bool spin = false; + + printk_safe_enter_irqsave(flags); + + raw_spin_lock(&console_owner_lock); + owner = READ_ONCE(console_owner); + waiter = READ_ONCE(console_waiter); + if (!waiter && owner && owner != current) { + WRITE_ONCE(console_waiter, true); + spin = true; + } + raw_spin_unlock(&console_owner_lock); + + /* + * If there is an active printk() writing to the + * consoles, instead of having it write our data too, + * see if we can offload that load from the active + * printer, and do some printing ourselves. + * Go into a spin only if there isn't already a waiter + * spinning, and there is an active printer, and + * that active printer isn't us (recursive printk?). + */ + if (spin) { + /* We spin waiting for the owner to release us */ + spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_); + /* Owner will clear console_waiter on hand off */ + while (READ_ONCE(console_waiter)) + cpu_relax(); + + spin_release(&console_owner_dep_map, 1, _THIS_IP_); + printk_safe_exit_irqrestore(flags); + + /* + * The owner passed the console lock to us. + * Since we did not spin on console lock, annotate + * this as a trylock. Otherwise lockdep will + * complain. + */ + mutex_acquire(&console_lock_dep_map, 0, 1, _THIS_IP_); + console_unlock(); + printk_safe_enter_irqsave(flags); + } + printk_safe_exit_irqrestore(flags); + + } }

return printed_len; @@ -2141,6 +2196,7 @@ void console_unlock(void) static u64 seen_seq; unsigned long flags; bool wake_klogd = false; + bool waiter = false; bool do_cond_resched, retry;

if (console_suspended) { @@ -2229,14 +2285,64 @@ skip: console_seq++; raw_spin_unlock(&logbuf_lock);

+ /* + * While actively printing out messages, if another printk() + * were to occur on another CPU, it may wait for this one to + * finish. This task can not be preempted if there is a + * waiter waiting to take over. + */ + raw_spin_lock(&console_owner_lock); + console_owner = current; + raw_spin_unlock(&console_owner_lock); + + /* The waiter may spin on us after setting console_owner */ + spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_); + stop_critical_timings(); /* don't trace print latency */ call_console_drivers(ext_text, ext_len, text, len); start_critical_timings(); + + raw_spin_lock(&console_owner_lock); + waiter = READ_ONCE(console_waiter); + console_owner = NULL; + raw_spin_unlock(&console_owner_lock); + + /* + * If there is a waiter waiting for us, then pass the + * rest of the work load over to that waiter. + */ + if (waiter) + break; + + /* There was no waiter, and nothing will spin on us here */ + spin_release(&console_owner_dep_map, 1, _THIS_IP_); + printk_safe_exit_irqrestore(flags);

if (do_cond_resched) cond_resched(); } + + /* + * If there is an active waiter waiting on the console_lock. + * Pass off the printing to the waiter, and the waiter + * will continue printing on its CPU, and when all writing + * has finished, the last printer will wake up klogd. + */ + if (waiter) { + WRITE_ONCE(console_waiter, false); + /* The waiter is now free to continue */ + spin_release(&console_owner_dep_map, 1, _THIS_IP_); + /* + * Hand off console_lock to waiter. The waiter will perform + * the up(). After this, the waiter is the console_lock owner. + */ + mutex_release(&console_lock_dep_map, 1, _THIS_IP_); + printk_safe_exit_irqrestore(flags); + /* Note, if waiter is set, logbuf_lock is not held */ + return; + } + console_locked = 0;

/* Release the exclusive_console once it is used */

From: Alex Williamson alex.williamson@redhat.com

[ Upstream commit aa008206634363ef800fbd5f0262016c9ff81dea ]

The Marvell 9128 is the original device generating bug 42679, from which many other Marvell DMA alias quirks have been sourced, but we didn't have positive confirmation of the fix on 9128 until now.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=42679 Link: https://www.spinics.net/lists/kvm/msg161459.html Reported-by: Binarus lists@binarus.de Tested-by: Binarus lists@binarus.de Signed-off-by: Alex Williamson alex.williamson@redhat.com Signed-off-by: Bjorn Helgaas bhelgaas@google.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/pci/quirks.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index a2f18c4a0346..9481c153d675 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -3886,6 +3886,8 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9120, quirk_dma_func1_alias); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9123, quirk_dma_func1_alias); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9128, + quirk_dma_func1_alias); /* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c14 */ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9130, quirk_dma_func1_alias);

From: Dmitry Torokhov dmitry.torokhov@gmail.com

[ Upstream commit 2bc4298f59d2f15175bb568e2d356b5912d0cdd9 ]

When Synaptics protocol is disabled, we still need to try and detect the hardware, so we can switch to SMBus device if SMbus is detected, or we know that it is Synaptics device and reset it properly for the bare PS/2 protocol.

Fixes: c378b5119eb0 ("Input: psmouse - factor out common protocol probing code") Reported-by: Matteo Croce mcroce@redhat.com Tested-by: Matteo Croce mcroce@redhat.com Signed-off-by: Dmitry Torokhov dmitry.torokhov@gmail.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/input/mouse/psmouse-base.c | 34 +++++++++++++++++++++------------- 1 file changed, 21 insertions(+), 13 deletions(-)

diff --git a/drivers/input/mouse/psmouse-base.c b/drivers/input/mouse/psmouse-base.c index 6a5649e52eed..8ac9e03c05b4 100644 --- a/drivers/input/mouse/psmouse-base.c +++ b/drivers/input/mouse/psmouse-base.c @@ -975,6 +975,21 @@ static void psmouse_apply_defaults(struct psmouse *psmouse) psmouse->pt_deactivate = NULL; }

+static bool psmouse_do_detect(int (*detect)(struct psmouse *, bool), + struct psmouse *psmouse, bool allow_passthrough, + bool set_properties) +{ + if (psmouse->ps2dev.serio->id.type == SERIO_PS_PSTHRU && + !allow_passthrough) { + return false; + } + + if (set_properties) + psmouse_apply_defaults(psmouse); + + return detect(psmouse, set_properties) == 0; +} + static bool psmouse_try_protocol(struct psmouse *psmouse, enum psmouse_type type, unsigned int *max_proto, @@ -986,15 +1001,8 @@ static bool psmouse_try_protocol(struct psmouse *psmouse, if (!proto) return false;

- if (psmouse->ps2dev.serio->id.type == SERIO_PS_PSTHRU && - !proto->try_passthru) { - return false; - } - - if (set_properties) - psmouse_apply_defaults(psmouse); - - if (proto->detect(psmouse, set_properties) != 0) + if (!psmouse_do_detect(proto->detect, psmouse, proto->try_passthru, + set_properties)) return false;

if (set_properties && proto->init && init_allowed) { @@ -1027,8 +1035,8 @@ static int psmouse_extensions(struct psmouse *psmouse, * Always check for focaltech, this is safe as it uses pnp-id * matching. */ - if (psmouse_try_protocol(psmouse, PSMOUSE_FOCALTECH, - &max_proto, set_properties, false)) { + if (psmouse_do_detect(focaltech_detect, + psmouse, false, set_properties)) { if (max_proto > PSMOUSE_IMEX && IS_ENABLED(CONFIG_MOUSE_PS2_FOCALTECH) && (!set_properties || focaltech_init(psmouse) == 0)) { @@ -1074,8 +1082,8 @@ static int psmouse_extensions(struct psmouse *psmouse, * probing for IntelliMouse. */ if (max_proto > PSMOUSE_PS2 && - psmouse_try_protocol(psmouse, PSMOUSE_SYNAPTICS, &max_proto, - set_properties, false)) { + psmouse_do_detect(synaptics_detect, + psmouse, false, set_properties)) { synaptics_hardware = true;

if (max_proto > PSMOUSE_IMEX) {

From: Mustafa Ismail mustafa.ismail@intel.com

[ Upstream commit f20d429511affab6a2a9129f46042f43e6ffe396 ]

The iWARP Exception Queue (IEQ) resources are not freed when a QP is destroyed. Fix this by freeing IEQ resources when freeing QP resources.

Fixes: d37498417947 ("i40iw: add files for iwarp interface") Signed-off-by: Mustafa Ismail mustafa.ismail@intel.com Signed-off-by: Shiraz Saleem shiraz.saleem@intel.com Signed-off-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/infiniband/hw/i40iw/i40iw_puda.c | 3 +-- drivers/infiniband/hw/i40iw/i40iw_puda.h | 1 + drivers/infiniband/hw/i40iw/i40iw_verbs.c | 1 + 3 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/hw/i40iw/i40iw_puda.c b/drivers/infiniband/hw/i40iw/i40iw_puda.c index 796a815b53fd..266c5952ba92 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_puda.c +++ b/drivers/infiniband/hw/i40iw/i40iw_puda.c @@ -48,7 +48,6 @@ static void i40iw_ieq_tx_compl(struct i40iw_sc_vsi *vsi, void *sqwrid); static void i40iw_ilq_putback_rcvbuf(struct i40iw_sc_qp *qp, u32 wqe_idx); static enum i40iw_status_code i40iw_puda_replenish_rq(struct i40iw_puda_rsrc *rsrc, bool initial); -static void i40iw_ieq_cleanup_qp(struct i40iw_puda_rsrc *ieq, struct i40iw_sc_qp *qp); /** * i40iw_puda_get_listbuf - get buffer from puda list * @list: list to use for buffers (ILQ or IEQ) @@ -1483,7 +1482,7 @@ static void i40iw_ieq_tx_compl(struct i40iw_sc_vsi *vsi, void *sqwrid) * @ieq: ieq resource * @qp: all pending fpdu buffers */ -static void i40iw_ieq_cleanup_qp(struct i40iw_puda_rsrc *ieq, struct i40iw_sc_qp *qp) +void i40iw_ieq_cleanup_qp(struct i40iw_puda_rsrc *ieq, struct i40iw_sc_qp *qp) { struct i40iw_puda_buf *buf; struct i40iw_pfpdu *pfpdu = &qp->pfpdu; diff --git a/drivers/infiniband/hw/i40iw/i40iw_puda.h b/drivers/infiniband/hw/i40iw/i40iw_puda.h index 660aa3edae56..53a7d58c84b5 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_puda.h +++ b/drivers/infiniband/hw/i40iw/i40iw_puda.h @@ -184,4 +184,5 @@ enum i40iw_status_code i40iw_cqp_qp_create_cmd(struct i40iw_sc_dev *dev, struct enum i40iw_status_code i40iw_cqp_cq_create_cmd(struct i40iw_sc_dev *dev, struct i40iw_sc_cq *cq); void i40iw_cqp_qp_destroy_cmd(struct i40iw_sc_dev *dev, struct i40iw_sc_qp *qp); void i40iw_cqp_cq_destroy_cmd(struct i40iw_sc_dev *dev, struct i40iw_sc_cq *cq); +void i40iw_ieq_cleanup_qp(struct i40iw_puda_rsrc *ieq, struct i40iw_sc_qp *qp); #endif diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index 3c6f3ce88f89..6aa613835405 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -412,6 +412,7 @@ void i40iw_free_qp_resources(struct i40iw_device *iwdev, { struct i40iw_pbl *iwpbl = &iwqp->iwpbl;

+ i40iw_ieq_cleanup_qp(iwdev->vsi.ieq, &iwqp->sc_qp); i40iw_dealloc_push_page(iwdev, &iwqp->sc_qp); if (qp_num) i40iw_free_resource(iwdev, iwdev->allocated_qps, qp_num);

From: "himanshu.madhani@cavium.com" himanshu.madhani@cavium.com

[ Upstream commit 7ac0c332f96bb9688560726f5e80c097ed8de59a ]

This patch fixes following Smatch warning:

drivers/scsi/qla2xxx/qla_init.c:130 qla2x00_async_iocb_timeout() error: we previously assumed 'fcport' could be null (see line 107)

Fixes: 5c25d451163c ("scsi: qla2xxx: Fix NULL pointer access for fcport structure") Reported by: Dan Carpenter dan.carpenter@oracle.com Signed-off-by: Quinn Tran quinn.tran@cavium.com Signed-off-by: Himanshu Madhani himanshu.madhani@cavium.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/scsi/qla2xxx/qla_init.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 7b44a2c68a45..e05438d1da20 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -115,6 +115,8 @@ qla2x00_async_iocb_timeout(void *data)

switch (sp->type) { case SRB_LOGIN_CMD: + if (!fcport) + break; /* Retry as needed. */ lio->u.logio.data[0] = MBS_COMMAND_ERROR; lio->u.logio.data[1] = lio->u.logio.flags & SRB_LOGIN_RETRIED ? @@ -128,6 +130,8 @@ qla2x00_async_iocb_timeout(void *data) qla24xx_handle_plogi_done_event(fcport->vha, &ea); break; case SRB_LOGOUT_CMD: + if (!fcport) + break; qlt_logo_completion_handler(fcport, QLA_FUNCTION_TIMEOUT); break; case SRB_CT_PTHRU_CMD:

From: "Steven Rostedt (VMware)" rostedt@goodmis.org

[ Upstream commit 38d70b7ca1769f26c0b79f3c08ff2cc949712b59 ]

When processing %pX in pretty_print(), simplify the logic slightly by incrementing the ptr to the format string if isalnum(ptr[1]) is true. This follows the logic a bit more closely to what is in the kernel.

Also, this fixes a small bug where %pF was not giving the offset of the function.

Signed-off-by: Steven Rostedt rostedt@goodmis.org Acked-by: Namhyung Kim namhyung@kernel.org Cc: Andrew Morton akpm@linux-foundation.org Link: http://lkml.kernel.org/r/20180112004822.260262257@goodmis.org Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- tools/lib/traceevent/event-parse.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 7ce724fc0544..9a17bc27296e 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -4949,21 +4949,22 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event else ls = 2;

- if (*(ptr+1) == 'F' || *(ptr+1) == 'f' || - *(ptr+1) == 'S' || *(ptr+1) == 's') { + if (isalnum(ptr[1])) ptr++; + + if (*ptr == 'F' || *ptr == 'f' || + *ptr == 'S' || *ptr == 's') { show_func = *ptr; - } else if (*(ptr+1) == 'M' || *(ptr+1) == 'm') { - print_mac_arg(s, *(ptr+1), data, size, event, arg); - ptr++; + } else if (*ptr == 'M' || *ptr == 'm') { + print_mac_arg(s, *ptr, data, size, event, arg); arg = arg->next; break; - } else if (*(ptr+1) == 'I' || *(ptr+1) == 'i') { + } else if (*ptr == 'I' || *ptr == 'i') { int n;

- n = print_ip_arg(s, ptr+1, data, size, event, arg); + n = print_ip_arg(s, ptr, data, size, event, arg); if (n > 0) { - ptr += n; + ptr += n - 1; arg = arg->next; break; }

From: "Steven Rostedt (VMware)" rostedt@goodmis.org

[ Upstream commit d777f8de99b05d399c0e4e51cdce016f26bd971b ]

If a field is a dynamic string, get_field_str() returned just the offset/size value and not the string. Have it parse the offset/size correctly to return the actual string. Otherwise filtering fails when trying to filter fields that are dynamic strings.

Reported-by: Gopanapalli Pradeep prap_hai@yahoo.com Signed-off-by: Steven Rostedt rostedt@goodmis.org Acked-by: Namhyung Kim namhyung@kernel.org Cc: Andrew Morton akpm@linux-foundation.org Link: http://lkml.kernel.org/r/20180112004823.146333275@goodmis.org Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- tools/lib/traceevent/parse-filter.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c index 315df0a70265..7b664fd1ebe8 100644 --- a/tools/lib/traceevent/parse-filter.c +++ b/tools/lib/traceevent/parse-filter.c @@ -1879,17 +1879,25 @@ static const char *get_field_str(struct filter_arg *arg, struct pevent_record *r struct pevent *pevent; unsigned long long addr; const char *val = NULL; + unsigned int size; char hex[64];

/* If the field is not a string convert it */ if (arg->str.field->flags & FIELD_IS_STRING) { val = record->data + arg->str.field->offset; + size = arg->str.field->size; + + if (arg->str.field->flags & FIELD_IS_DYNAMIC) { + addr = *(unsigned int *)val; + val = record->data + (addr & 0xffff); + size = addr >> 16; + }

/* * We need to copy the data since we can't be sure the field * is null terminated. */ - if (*(val + arg->str.field->size - 1)) { + if (*(val + size - 1)) { /* copy it */ memcpy(arg->str.buffer, val, arg->str.field->size); /* the buffer is already NULL terminated */

From: Robin Murphy robin.murphy@arm.com

[ Upstream commit dc98b8480d8a68c2ce9aa28b9f0d714fd258bc0b ]

Removing the early device registration hook overlooked the fact that it only ran conditionally on a compatible device being present in the DT. With exynos_iommu_init() now running as an unconditional initcall, problems arise on non-Exynos systems when other IOMMU drivers find themselves unable to install their ops on the platform bus, or at worst the Exynos ops get called with someone else's domain and all hell breaks loose.

The global ops/cache setup could probably all now be triggered from the first IOMMU probe, as with dma_dev assigment, but for the time being the simplest fix is to resurrect the logic from commit a7b67cd5d9af ("iommu/exynos: Play nice in multi-platform builds") to explicitly check the DT for the presence of an Exynos IOMMU before trying anything.

Fixes: 928055a01b3f ("iommu/exynos: Remove custom platform device registration code") Signed-off-by: Robin Murphy robin.murphy@arm.com Acked-by: Marek Szyprowski m.szyprowski@samsung.com Signed-off-by: Joerg Roedel jroedel@suse.de Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/iommu/exynos-iommu.c | 7 +++++++ 1 file changed, 7 insertions(+)

diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index 79c45650f8de..736d4552d96f 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -1353,8 +1353,15 @@ static const struct iommu_ops exynos_iommu_ops = {

static int __init exynos_iommu_init(void) { + struct device_node *np; int ret;

+ np = of_find_matching_node(NULL, sysmmu_of_match); + if (!np) + return 0; + + of_node_put(np); + lv2table_kmem_cache = kmem_cache_create("exynos-iommu-lv2table", LV2TABLE_SIZE, LV2TABLE_SIZE, 0, NULL); if (!lv2table_kmem_cache) {

From: Peter Xu peterx@redhat.com

[ Upstream commit 9d2e6505f6d6934e681aed502f566198cb25c74a ]

after commit a1ddcbe93010 ("iommu/vt-d: Pass dmar_domain directly into iommu_flush_iotlb_psi", 2015-08-12), we have domain pointer as parameter to iommu_flush_iotlb_psi(), so no need to fetch it from cache again.

More importantly, a NULL reference pointer bug is reported on RHEL7 (and it can be reproduced on some old upstream kernels too, e.g., v4.13) by unplugging an 40g nic from a VM (hard to test unplug on real host, but it should be the same):

https://bugzilla.redhat.com/show_bug.cgi?id=1531367

[ 24.391863] pciehp 0000:00:03.0:pcie004: Slot(0): Attention button pressed [ 24.393442] pciehp 0000:00:03.0:pcie004: Slot(0): Powering off due to button press [ 29.721068] i40evf 0000:01:00.0: Unable to send opcode 2 to PF, err I40E_ERR_QUEUE_EMPTY, aq_err OK [ 29.783557] iommu: Removing device 0000:01:00.0 from group 3 [ 29.784662] BUG: unable to handle kernel NULL pointer dereference at 0000000000000304 [ 29.785817] IP: iommu_flush_iotlb_psi+0xcf/0x120 [ 29.786486] PGD 0 [ 29.786487] P4D 0 [ 29.786812] [ 29.787390] Oops: 0000 [#1] SMP [ 29.787876] Modules linked in: ip6t_rpfilter ip6t_REJECT nf_reject_ipv6 xt_conntrack ip_set nfnetlink ebtable_nat ebtable_broute bridge stp llc ip6table_ng [ 29.795371] CPU: 0 PID: 156 Comm: kworker/0:2 Not tainted 4.13.0 #14 [ 29.796366] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.11.0-1.el7 04/01/2014 [ 29.797593] Workqueue: pciehp-0 pciehp_power_thread [ 29.798328] task: ffff94f5745b4a00 task.stack: ffffb326805ac000 [ 29.799178] RIP: 0010:iommu_flush_iotlb_psi+0xcf/0x120 [ 29.799919] RSP: 0018:ffffb326805afbd0 EFLAGS: 00010086 [ 29.800666] RAX: ffff94f5bc56e800 RBX: 0000000000000000 RCX: 0000000200000025 [ 29.801667] RDX: ffff94f5bc56e000 RSI: 0000000000000082 RDI: 0000000000000000 [ 29.802755] RBP: ffffb326805afbf8 R08: 0000000000000000 R09: ffff94f5bc86bbf0 [ 29.803772] R10: ffffb326805afba8 R11: 00000000000ffdc4 R12: ffff94f5bc86a400 [ 29.804789] R13: 0000000000000000 R14: 00000000ffdc4000 R15: 0000000000000000 [ 29.805792] FS: 0000000000000000(0000) GS:ffff94f5bfc00000(0000) knlGS:0000000000000000 [ 29.806923] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 29.807736] CR2: 0000000000000304 CR3: 000000003499d000 CR4: 00000000000006f0 [ 29.808747] Call Trace: [ 29.809156] flush_unmaps_timeout+0x126/0x1c0 [ 29.809800] domain_exit+0xd6/0x100 [ 29.810322] device_notifier+0x6b/0x70 [ 29.810902] notifier_call_chain+0x4a/0x70 [ 29.812822] __blocking_notifier_call_chain+0x47/0x60 [ 29.814499] blocking_notifier_call_chain+0x16/0x20 [ 29.816137] device_del+0x233/0x320 [ 29.817588] pci_remove_bus_device+0x6f/0x110 [ 29.819133] pci_stop_and_remove_bus_device+0x1a/0x20 [ 29.820817] pciehp_unconfigure_device+0x7a/0x1d0 [ 29.822434] pciehp_disable_slot+0x52/0xe0 [ 29.823931] pciehp_power_thread+0x8a/0xa0 [ 29.825411] process_one_work+0x18c/0x3a0 [ 29.826875] worker_thread+0x4e/0x3b0 [ 29.828263] kthread+0x109/0x140 [ 29.829564] ? process_one_work+0x3a0/0x3a0 [ 29.831081] ? kthread_park+0x60/0x60 [ 29.832464] ret_from_fork+0x25/0x30 [ 29.833794] Code: 85 ed 74 0b 5b 41 5c 41 5d 41 5e 41 5f 5d c3 49 8b 54 24 60 44 89 f8 0f b6 c4 48 8b 04 c2 48 85 c0 74 49 45 0f b6 ff 4a 8b 3c f8 <80> bf [ 29.838514] RIP: iommu_flush_iotlb_psi+0xcf/0x120 RSP: ffffb326805afbd0 [ 29.840362] CR2: 0000000000000304 [ 29.841716] ---[ end trace b10ec0d6900868d3 ]---

This patch fixes that problem if applied to v4.13 kernel.

The bug does not exist on latest upstream kernel since it's fixed as a side effect of commit 13cf01744608 ("iommu/vt-d: Make use of iova deferred flushing", 2017-08-15). But IMHO it's still good to have this patch upstream.

CC: Alex Williamson alex.williamson@redhat.com Signed-off-by: Peter Xu peterx@redhat.com Fixes: a1ddcbe93010 ("iommu/vt-d: Pass dmar_domain directly into iommu_flush_iotlb_psi") Reviewed-by: Alex Williamson alex.williamson@redhat.com Signed-off-by: Joerg Roedel jroedel@suse.de Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/iommu/intel-iommu.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 4a2de34895ec..869f37d1f3b7 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -1601,8 +1601,7 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu, * flush. However, device IOTLB doesn't need to be flushed in this case. */ if (!cap_caching_mode(iommu->cap) || !map) - iommu_flush_dev_iotlb(get_iommu_domain(iommu, did), - addr, mask); + iommu_flush_dev_iotlb(domain, addr, mask); }

static void iommu_flush_iova(struct iova_domain *iovad)

From: Ming Lei ming.lei@redhat.com

[ Upstream commit 050af08ffb1b62af69196d61c22a0755f9a3cdbd ]

blk-mq will rerun queue via RESTART or dispatch wake after one request is completed, so not necessary to wait random time for requeuing, we should trust blk-mq to do it.

More importantly, we need to return BLK_STS_RESOURCE to blk-mq so that dequeuing from the I/O scheduler can be stopped, this results in improved I/O merging.

Signed-off-by: Ming Lei ming.lei@redhat.com Signed-off-by: Mike Snitzer snitzer@redhat.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/md/dm-mpath.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 025e033ecb78..a3223c8fbaac 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -534,8 +534,20 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq, if (queue_dying) { atomic_inc(&m->pg_init_in_progress); activate_or_offline_path(pgpath); + return DM_MAPIO_DELAY_REQUEUE; } - return DM_MAPIO_DELAY_REQUEUE; + + /* + * blk-mq's SCHED_RESTART can cover this requeue, so we + * needn't deal with it by DELAY_REQUEUE. More importantly, + * we have to return DM_MAPIO_REQUEUE so that blk-mq can + * get the queue busy feedback (via BLK_STS_RESOURCE), + * otherwise I/O merging can suffer. + */ + if (q->mq_ops) + return DM_MAPIO_REQUEUE; + else + return DM_MAPIO_DELAY_REQUEUE; } clone->bio = clone->biotail = NULL; clone->rq_disk = bdev->bd_disk;

From: James Smart jsmart2021@gmail.com

[ Upstream commit d625d05ef0f0914a706d824fab85472a42be6659 ]

When connectivity is lost to a device, the association is terminated and the blk-mq queues are quiesced/stopped. When connectivity is re-established, they are resumed.

If an admin command is received while connectivity is list, the ioctl queues the command on the admin_q and the command stalls (the thread issuing the ioctl hangs/waits). if the connectivity is lost long enough such that the controller is then deleted, the delete code makes its calls to initiate the delete, which then expects the core layer to call the transport when all references are removed and the controller can be freed. Unfortunately, nothing in this path dequeued the admin command, so a reference sits outstanding and things stop, hanging the delete indefinitely.

Correct by unquiescing the admin queue in the delete association. This means any admin command (which should only be from an ioctl) issued after connectivity is lost will detect the controller is in a reconnecting state and will (fast) fail the command. Thus, a pending reference can no longer be created. Once connectivity is re-established, a new ioctl/admin command would see proper device state and function again.

Signed-off-by: James Smart james.smart@broadcom.com Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/nvme/host/fc.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 794e66e4aa20..8f9ddd0e392c 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2921,6 +2921,9 @@ nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl) __nvme_fc_delete_hw_queue(ctrl, &ctrl->queues[0], 0); nvme_fc_free_queue(&ctrl->queues[0]);

+ /* re-enable the admin_q so anything new can fast fail */ + blk_mq_unquiesce_queue(ctrl->ctrl.admin_q); + nvme_fc_ctlr_inactive_on_rport(ctrl); }

From: Martin Blumenstingl martin.blumenstingl@googlemail.com

[ Upstream commit fb7d38a70e1d8ffd54f7a7464dcc4889d7e490ad ]

On Meson8b the only valid input clock is MPLL2. The bootloader configures that to run at 500002394Hz which cannot be divided evenly down to 125MHz using the m250_div clock. Currently the common clock framework chooses a m250_div of 2 - with the internal fixed "divide by 10" this results in a RGMII TX clock of 125001197Hz (120Hz above the requested 125MHz).

Letting the common clock framework propagate the rate changes up to the parent of m250_mux allows us to get the best possible clock rate. With this patch the common clock framework calculates a rate of very-close-to-250MHz (249999701Hz to be exact) for the MPLL2 clock (which is the mux input). Dividing that by 2 (which is an internal, fixed divider for the RGMII TX clock) gives us an RGMII TX clock of 124999850Hz (which is only 150Hz off the requested 125MHz, compared to 1197Hz based on the MPLL2 rate set by u-boot and the Amlogic GPL kernel sources).

SoCs from the Meson GX series are not affected by this change because the input clock is FCLK_DIV2 whose rate cannot be changed (which is fine since it's running at 1GHz, so it's already a multiple of 250MHz and 125MHz).

Fixes: 566e8251625304 ("net: stmmac: add a glue driver for the Amlogic Meson 8b / GXBB DWMAC") Suggested-by: Jerome Brunet jbrunet@baylibre.com Signed-off-by: Martin Blumenstingl martin.blumenstingl@googlemail.com Reviewed-by: Jerome Brunet jbrunet@baylibre.com Tested-by: Jerome Brunet jbrunet@baylibre.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c index 157e12e15f28..8be4b32544ef 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c @@ -116,7 +116,7 @@ static int meson8b_init_clk(struct meson8b_dwmac *dwmac) snprintf(clk_name, sizeof(clk_name), "%s#m250_sel", dev_name(dev)); init.name = clk_name; init.ops = &clk_mux_ops; - init.flags = 0; + init.flags = CLK_SET_RATE_PARENT; init.parent_names = mux_parent_names; init.num_parents = MUX_CLK_NUM_PARENTS;

From: Matthias Reichl hias@horus.com

[ Upstream commit 8d5737a5f53902a916ee1e1cb248c9b8b883b2ea ]

If bcm2835 is configured as bitclock master calling hw_params() after prepare() fails with EBUSY. This also makes it impossible to use bcm2835 in full duplex mode.

The error is caused by the split clock setup: clk_set_rate is called in hw_params, clk_prepare_enable in prepare. As hw_params doesn't check if the clock was already enabled clk_set_rate fails with EBUSY.

Fix this by moving clock startup from prepare to hw_params and let hw_params properly deal with an already set up or enabled clock.

Signed-off-by: Matthias Reichl hias@horus.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- sound/soc/bcm/bcm2835-i2s.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-)

diff --git a/sound/soc/bcm/bcm2835-i2s.c b/sound/soc/bcm/bcm2835-i2s.c index 2e449d7173fc..d5f73a8ab893 100644 --- a/sound/soc/bcm/bcm2835-i2s.c +++ b/sound/soc/bcm/bcm2835-i2s.c @@ -130,6 +130,7 @@ struct bcm2835_i2s_dev { struct regmap *i2s_regmap; struct clk *clk; bool clk_prepared; + int clk_rate; };

static void bcm2835_i2s_start_clock(struct bcm2835_i2s_dev *dev) @@ -419,10 +420,19 @@ static int bcm2835_i2s_hw_params(struct snd_pcm_substream *substream, }

/* Clock should only be set up here if CPU is clock master */ - if (bit_clock_master) { - ret = clk_set_rate(dev->clk, bclk_rate); - if (ret) - return ret; + if (bit_clock_master && + (!dev->clk_prepared || dev->clk_rate != bclk_rate)) { + if (dev->clk_prepared) + bcm2835_i2s_stop_clock(dev); + + if (dev->clk_rate != bclk_rate) { + ret = clk_set_rate(dev->clk, bclk_rate); + if (ret) + return ret; + dev->clk_rate = bclk_rate; + } + + bcm2835_i2s_start_clock(dev); }

/* Setup the frame format */ @@ -618,8 +628,6 @@ static int bcm2835_i2s_prepare(struct snd_pcm_substream *substream, struct bcm2835_i2s_dev *dev = snd_soc_dai_get_drvdata(dai); uint32_t cs_reg;

- bcm2835_i2s_start_clock(dev); - /* * Clear both FIFOs if the one that should be started * is not empty at the moment. This should only happen

From: Jan Chochol jan@chochol.info

[ Upstream commit cbebc6ef4fc830f4040d4140bf53484812d5d5d9 ]

Since commit 57e62324e469 ("NFS: Store the legacy idmapper result in the keyring") nfs_idmap_cache_timeout changed units from jiffies to seconds. Unfortunately sysctl interface was not updated accordingly.

As a effect updating /proc/sys/fs/nfs/idmap_cache_timeout with some value will incorrectly multiply this value by HZ. Also reading /proc/sys/fs/nfs/idmap_cache_timeout will show real value divided by HZ.

Fixes: 57e62324e469 ("NFS: Store the legacy idmapper result in the keyring") Signed-off-by: Jan Chochol jan@chochol.info Signed-off-by: Trond Myklebust trond.myklebust@primarydata.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- fs/nfs/nfs4sysctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/nfs/nfs4sysctl.c b/fs/nfs/nfs4sysctl.c index 0d91d84e5822..c394e4447100 100644 --- a/fs/nfs/nfs4sysctl.c +++ b/fs/nfs/nfs4sysctl.c @@ -32,7 +32,7 @@ static struct ctl_table nfs4_cb_sysctls[] = { .data = &nfs_idmap_cache_timeout, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec_jiffies, + .proc_handler = proc_dointvec, }, { } };

From: Maarten ter Huurne maarten@treewalker.org

[ Upstream commit 1f7412e0e2f327fe7dc5a0c2fc36d7b319d05d47 ]

According to config2, the associativity would be 5-ways, but the documentation states 4-ways, which also matches the documented L2 cache size of 256 kB.

Signed-off-by: Maarten ter Huurne maarten@treewalker.org Reviewed-by: James Hogan jhogan@kernel.org Cc: Ralf Baechle ralf@linux-mips.org Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/18488/ Signed-off-by: James Hogan jhogan@kernel.org Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- arch/mips/mm/sc-mips.c | 9 +++++++++ 1 file changed, 9 insertions(+)

diff --git a/arch/mips/mm/sc-mips.c b/arch/mips/mm/sc-mips.c index 548acb7f8557..394673991bab 100644 --- a/arch/mips/mm/sc-mips.c +++ b/arch/mips/mm/sc-mips.c @@ -16,6 +16,7 @@ #include <asm/mmu_context.h> #include <asm/r4kcache.h> #include <asm/mips-cps.h> +#include <asm/bootinfo.h>

/* * MIPS32/MIPS64 L2 cache handling @@ -220,6 +221,14 @@ static inline int __init mips_sc_probe(void) else return 0;

+ /* + * According to config2 it would be 5-ways, but that is contradicted + * by all documentation. + */ + if (current_cpu_type() == CPU_JZRISC && + mips_machtype == MACH_INGENIC_JZ4770) + c->scache.ways = 4; + c->scache.waysize = c->scache.sets * c->scache.linesz; c->scache.waybit = __ffs(c->scache.waysize);

From: Niklas Cassel niklas.cassel@axis.com

[ Upstream commit 80db6f08b7af93eddc9487535e6150b220262637 ]

Some hardware can operate in either "host" or "endpoint" mode, which means there can be both a host bridge driver and an endpoint driver for the same device. Those drivers share a lot of code, so sometimes they live in the same source file.

The host bridge driver requires CONFIG_PCI=y because it enumerates PCI devices below the bridge using the PCI core. The endpoint driver does not require CONFIG_PCI=y because it runs in an embedded kernel on the other side of the device, e.g., on an adapter card.

pci-dra7xx.c contains both host and endpoint drivers. If we select only the endpoint driver (CONFIG_PCI=n and CONFIG_PCI_DRA7XX_EP=y), the unneeded host driver is still compiled. It references pci_irqd_intx_xlate(), which is not present when CONFIG_PCI=n, which causes this error:

drivers/pci/dwc/pci-dra7xx.c:229:11: error: 'pci_irqd_intx_xlate' undeclared here (not in a function)

Add a dummy pci_irqd_intx_xlate() for the CONFIG_PCI=n case.

[bhelgaas: changelog] Signed-off-by: Niklas Cassel niklas.cassel@axis.com Signed-off-by: Bjorn Helgaas bhelgaas@google.com Acked-by: Arnd Bergmann arnd@arndb.de Acked-by: Lorenzo Pieralisi lorenzo.pieralisi@arm.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- include/linux/pci.h | 7 +++++++ 1 file changed, 7 insertions(+)

diff --git a/include/linux/pci.h b/include/linux/pci.h index c170c9250c8b..f69944699317 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1686,6 +1686,13 @@ static inline int pci_get_new_domain_nr(void) { return -ENOSYS; } #define dev_is_pf(d) (false) static inline bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags) { return false; } +static inline int pci_irqd_intx_xlate(struct irq_domain *d, + struct device_node *node, + const u32 *intspec, + unsigned int intsize, + unsigned long *out_hwirq, + unsigned int *out_type) +{ return -EINVAL; } #endif /* CONFIG_PCI */

/* Include architecture-dependent settings and functions */

From: Vladimir Murzin vladimir.murzin@arm.com

[ Upstream commit 636e645f1f2a5826beacd23548696f1655b0b5d8 ]

adjust_lowmem_bounds() called twice which can lead to stalled data (i.e. subreg) value in mem[] array after the first call.

Zero out mem[] array before we allocate MPU regions for memory.

Fixes: 5c9d9a1b3a54 ("ARM: 8712/1: NOMMU: Use more MPU regions to cover memory") Signed-off-by: Vladimir Murzin vladimir.murzin@arm.com Signed-off-by: Russell King rmk+kernel@armlinux.org.uk Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- arch/arm/mm/pmsa-v7.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/arch/arm/mm/pmsa-v7.c b/arch/arm/mm/pmsa-v7.c index 976df60ac426..f65c01fba9f4 100644 --- a/arch/arm/mm/pmsa-v7.c +++ b/arch/arm/mm/pmsa-v7.c @@ -6,6 +6,7 @@

#include <linux/bitops.h> #include <linux/memblock.h> +#include <linux/string.h>

#include <asm/cacheflush.h> #include <asm/cp15.h> @@ -296,6 +297,7 @@ void __init adjust_lowmem_bounds_mpu(void) } }

+ memset(mem, 0, sizeof(mem)); num = allocate_region(mem_start, specified_mem_size, mem_max_regions, mem);

for (i = 0; i < num; i++) {

From: Ulf Magnusson ulfalizer@gmail.com

[ Upstream commit 0724a7c32a54e3e50d28e19e30c59014f61d4e2c ]

If a 'mainmenu' entry appeared in the Kconfig files, two things would leak:

- The 'struct property' allocated for the default "Linux Kernel Configuration" prompt.

- The string for the T_WORD/T_WORD_QUOTE prompt after the T_MAINMENU token, allocated on the heap in zconf.l.

To fix it, introduce a new 'no_mainmenu_stmt' nonterminal that matches if there's no 'mainmenu' and adds the default prompt. That means the prompt only gets allocated once regardless of whether there's a 'mainmenu' statement or not, and managing it becomes simple.

Summary from Valgrind on 'menuconfig' (ARCH=x86) before the fix:

LEAK SUMMARY: definitely lost: 344,568 bytes in 14,352 blocks ...

Summary after the fix:

LEAK SUMMARY: definitely lost: 344,440 bytes in 14,350 blocks ...

Signed-off-by: Ulf Magnusson ulfalizer@gmail.com Signed-off-by: Masahiro Yamada yamada.masahiro@socionext.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- scripts/kconfig/zconf.y | 33 ++++++++++++++++++++++++--------- 1 file changed, 24 insertions(+), 9 deletions(-)

diff --git a/scripts/kconfig/zconf.y b/scripts/kconfig/zconf.y index c8f396c3b190..20d9caa4be99 100644 --- a/scripts/kconfig/zconf.y +++ b/scripts/kconfig/zconf.y @@ -108,7 +108,27 @@ static struct menu *current_menu, *current_entry; %% input: nl start | start;

-start: mainmenu_stmt stmt_list | stmt_list; +start: mainmenu_stmt stmt_list | no_mainmenu_stmt stmt_list; + +/* mainmenu entry */ + +mainmenu_stmt: T_MAINMENU prompt nl +{ + menu_add_prompt(P_MENU, $2, NULL); +}; + +/* Default main menu, if there's no mainmenu entry */ + +no_mainmenu_stmt: /* empty */ +{ + /* + * Hack: Keep the main menu title on the heap so we can safely free it + * later regardless of whether it comes from the 'prompt' in + * mainmenu_stmt or here + */ + menu_add_prompt(P_MENU, strdup("Linux Kernel Configuration"), NULL); +}; +

stmt_list: /* empty */ @@ -351,13 +371,6 @@ if_block: | if_block choice_stmt ;

-/* mainmenu entry */ - -mainmenu_stmt: T_MAINMENU prompt nl -{ - menu_add_prompt(P_MENU, $2, NULL); -}; - /* menu entry */

menu: T_MENU prompt T_EOL @@ -502,6 +515,7 @@ word_opt: /* empty */ { $$ = NULL; }

void conf_parse(const char *name) { + const char *tmp; struct symbol *sym; int i;

@@ -509,7 +523,6 @@ void conf_parse(const char *name)

sym_init(); _menu_init(); - rootmenu.prompt = menu_add_prompt(P_MENU, "Linux Kernel Configuration", NULL);

if (getenv("ZCONF_DEBUG")) zconfdebug = 1; @@ -519,8 +532,10 @@ void conf_parse(const char *name) if (!modules_sym) modules_sym = sym_find( "n" );

+ tmp = rootmenu.prompt->text; rootmenu.prompt->text = _(rootmenu.prompt->text); rootmenu.prompt->text = sym_expand_string_value(rootmenu.prompt->text); + free((char*)tmp);

menu_finalize(&rootmenu); for_all_symbols(i, sym) {

From: Ulf Magnusson ulfalizer@gmail.com

[ Upstream commit 5b1374b3b3c2fc4f63a398adfa446fb8eff791a4 ]

Only the E_NOT operand and not the E_NOT node itself was freed, due to accidentally returning too early in expr_free(). Outline of leak:

switch (e->type) { ... case E_NOT: expr_free(e->left.expr); return; ... } *Never reached, 'e' leaked* free(e);

Fix by changing the 'return' to a 'break'.

Summary from Valgrind on 'menuconfig' (ARCH=x86) before the fix:

LEAK SUMMARY: definitely lost: 44,448 bytes in 1,852 blocks ...

Summary after the fix:

LEAK SUMMARY: definitely lost: 1,608 bytes in 67 blocks ...

Signed-off-by: Ulf Magnusson ulfalizer@gmail.com Signed-off-by: Masahiro Yamada yamada.masahiro@socionext.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- scripts/kconfig/expr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/kconfig/expr.c b/scripts/kconfig/expr.c index 8cee597d33a5..ee23ebc881a6 100644 --- a/scripts/kconfig/expr.c +++ b/scripts/kconfig/expr.c @@ -113,7 +113,7 @@ void expr_free(struct expr *e) break; case E_NOT: expr_free(e->left.expr); - return; + break; case E_EQUAL: case E_GEQ: case E_GTH:

From: Nicholas Piggin npiggin@gmail.com

[ Upstream commit 35adacd6fc48d658419522f192a3c8b2785612da ]

Platforms with a panic handler that halts the system can have problems getting kernel messages out, because the panic notifiers are called before kernel/panic.c does its flushing of printk buffers an console etc.

This was attempted to be solved with commit a3b2cb30f252 ("powerpc: Do not call ppc_md.panic in fadump panic notifier"), but that wasn't the right approach and caused other problems, and was reverted by commit ab9dbf771ff9.

Instead, the powernv shutdown paths have already had a similar problem, fixed by taking the message flushing sequence from kernel/panic.c. That's a little bit ugly, but while we have the code duplicated, it will work for this case as well. So have ppc panic handlers do the same flushing before they terminate.

Without this patch, a qemu pseries_le_defconfig guest stops silently when issued the nmi command when xmon is off and no crash dumpers enabled. Afterwards, an oops is printed by each CPU as expected.

Fixes: ab9dbf771ff9 ("Revert "powerpc: Do not call ppc_md.panic in fadump panic notifier"") Signed-off-by: Nicholas Piggin npiggin@gmail.com Reviewed-by: David Gibson david@gibson.dropbear.id.au Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- arch/powerpc/include/asm/bug.h | 3 ++- arch/powerpc/kernel/traps.c | 24 ++++++++++++++++++++++++ arch/powerpc/platforms/powernv/opal.c | 18 ++++-------------- arch/powerpc/platforms/ps3/setup.c | 1 + arch/powerpc/platforms/pseries/setup.c | 8 +++++++- 5 files changed, 38 insertions(+), 16 deletions(-)

diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h index 3c04249bcf39..bca101ee1f32 100644 --- a/arch/powerpc/include/asm/bug.h +++ b/arch/powerpc/include/asm/bug.h @@ -135,7 +135,8 @@ extern void bad_page_fault(struct pt_regs *, unsigned long, int); extern void _exception(int, struct pt_regs *, int, unsigned long); extern void die(const char *, struct pt_regs *, long); extern bool die_will_crash(void); - +extern void panic_flush_kmsg_start(void); +extern void panic_flush_kmsg_end(void); #endif /* !__ASSEMBLY__ */

#endif /* __KERNEL__ */ diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 109989676776..37c1ea9b0642 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -38,6 +38,8 @@ #include <linux/ratelimit.h> #include <linux/context_tracking.h> #include <linux/smp.h> +#include <linux/console.h> +#include <linux/kmsg_dump.h>

#include <asm/emulated_ops.h> #include <asm/pgtable.h> @@ -142,6 +144,28 @@ static int die_owner = -1; static unsigned int die_nest_count; static int die_counter;

+extern void panic_flush_kmsg_start(void) +{ + /* + * These are mostly taken from kernel/panic.c, but tries to do + * relatively minimal work. Don't use delay functions (TB may + * be broken), don't crash dump (need to set a firmware log), + * don't run notifiers. We do want to get some information to + * Linux console. + */ + console_verbose(); + bust_spinlocks(1); +} + +extern void panic_flush_kmsg_end(void) +{ + printk_safe_flush_on_panic(); + kmsg_dump(KMSG_DUMP_PANIC); + bust_spinlocks(0); + debug_locks_off(); + console_flush_on_panic(); +} + static unsigned long oops_begin(struct pt_regs *regs) { int cpu; diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 041ddbd1fc57..c23a9cca6268 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -461,24 +461,14 @@ static int opal_recover_mce(struct pt_regs *regs,

void pnv_platform_error_reboot(struct pt_regs *regs, const char *msg) { - /* - * This is mostly taken from kernel/panic.c, but tries to do - * relatively minimal work. Don't use delay functions (TB may - * be broken), don't crash dump (need to set a firmware log), - * don't run notifiers. We do want to get some information to - * Linux console. - */ - console_verbose(); - bust_spinlocks(1); + panic_flush_kmsg_start(); + pr_emerg("Hardware platform error: %s\n", msg); if (regs) show_regs(regs); smp_send_stop(); - printk_safe_flush_on_panic(); - kmsg_dump(KMSG_DUMP_PANIC); - bust_spinlocks(0); - debug_locks_off(); - console_flush_on_panic(); + + panic_flush_kmsg_end();

/* * Don't bother to shut things down because this will diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c index 6244bc849469..77a37520068d 100644 --- a/arch/powerpc/platforms/ps3/setup.c +++ b/arch/powerpc/platforms/ps3/setup.c @@ -113,6 +113,7 @@ static void ps3_panic(char *str) printk(" System does not reboot automatically.\n"); printk(" Please press POWER button.\n"); printk("\n"); + panic_flush_kmsg_end();

while(1) lv1_pause(1); diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index ae4f596273b5..69d11ecd45e1 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -533,6 +533,12 @@ static void __init pSeries_setup_arch(void) ppc_md.pcibios_root_bridge_prepare = pseries_root_bridge_prepare; }

+static void pseries_panic(char *str) +{ + panic_flush_kmsg_end(); + rtas_os_term(str); +} + static int __init pSeries_init_panel(void) { /* Manually leave the kernel version on the panel. */ @@ -761,7 +767,7 @@ define_machine(pseries) { .pcibios_fixup = pSeries_final_fixup, .restart = rtas_restart, .halt = rtas_halt, - .panic = rtas_os_term, + .panic = pseries_panic, .get_boot_time = rtas_get_boot_time, .get_rtc_time = rtas_get_rtc_time, .set_rtc_time = rtas_set_rtc_time,

From: "weiyongjun (A)" weiyongjun1@huawei.com

[ Upstream commit 0ddcff49b672239dda94d70d0fcf50317a9f4b51 ]

'hwname' is malloced in hwsim_new_radio_nl() and should be freed before leaving from the error handling cases, otherwise it will cause memory leak.

Fixes: ff4dd73dd2b4 ("mac80211_hwsim: check HWSIM_ATTR_RADIO_NAME length") Signed-off-by: Wei Yongjun weiyongjun1@huawei.com Reviewed-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/net/wireless/mac80211_hwsim.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 731d59ee6efe..479250bca605 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -3155,8 +3155,10 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info) if (info->attrs[HWSIM_ATTR_REG_CUSTOM_REG]) { u32 idx = nla_get_u32(info->attrs[HWSIM_ATTR_REG_CUSTOM_REG]);

- if (idx >= ARRAY_SIZE(hwsim_world_regdom_custom)) + if (idx >= ARRAY_SIZE(hwsim_world_regdom_custom)) { + kfree(hwname); return -EINVAL; + } param.regd = hwsim_world_regdom_custom[idx]; }

From: Liu Bo bo.li.liu@oracle.com

[ Upstream commit 762221f095e3932669093466aaf4b85ed9ad2ac1 ]

The raid6 corruption is that, suppose that all disks can be read without problems and if the content that was read out doesn't match its checksum, currently for raid6 btrfs at most retries twice,

- the 1st retry is to rebuild with all other stripes, it'll eventually be a raid5 xor rebuild, - if the 1st fails, the 2nd retry will deliberately fail parity p so that it will do raid6 style rebuild,

however, the chances are that another non-parity stripe content also has something corrupted, so that the above retries are not able to return correct content.

We've fixed normal reads to rebuild raid6 correctly with more retries in Patch "Btrfs: make raid6 rebuild retry more"[1], this is to fix scrub to do the exactly same rebuild process.

[1]: https://patchwork.kernel.org/patch/10091755/

Signed-off-by: Liu Bo bo.li.liu@oracle.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- fs/btrfs/raid56.c | 18 ++++++++++++++---- fs/btrfs/volumes.c | 9 ++++++++- 2 files changed, 22 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 8a3e42412506..025e69c57cbd 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -2170,11 +2170,21 @@ int raid56_parity_recover(struct btrfs_fs_info *fs_info, struct bio *bio, }

/* - * reconstruct from the q stripe if they are - * asking for mirror 3 + * Loop retry: + * for 'mirror == 2', reconstruct from all other stripes. + * for 'mirror_num > 2', select a stripe to fail on every retry. */ - if (mirror_num == 3) - rbio->failb = rbio->real_stripes - 2; + if (mirror_num > 2) { + /* + * 'mirror == 3' is to fail the p stripe and + * reconstruct from the q stripe. 'mirror > 3' is to + * fail a data stripe and reconstruct from p+q stripe. + */ + rbio->failb = rbio->real_stripes - (mirror_num - 1); + ASSERT(rbio->failb > 0); + if (rbio->failb <= rbio->faila) + rbio->failb--; + }

ret = lock_stripe_add(rbio);

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 6631f48c6a11..82cdd9d74f04 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -5105,7 +5105,14 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len) else if (map->type & BTRFS_BLOCK_GROUP_RAID5) ret = 2; else if (map->type & BTRFS_BLOCK_GROUP_RAID6) - ret = 3; + /* + * There could be two corrupted data stripes, we need + * to loop retry in order to rebuild the correct data. + * + * Fail a stripe at a time on every retry except the + * stripe under reconstruction. + */ + ret = map->num_stripes; else ret = 1; free_extent_map(em);

From: Anand Jain Anand.Jain@oracle.com

[ Upstream commit 6f794e3c5c8f8fdd3b5bb20d9ded894e685b5bbe ]

It appears from the original commit [1] that there isn't any design specific reason not to fail the mount instead of just warning. This patch will change it to fail.

[1] commit 319e4d0661e5323c9f9945f0f8fb5905e5fe74c3 btrfs: Enhance super validation check

Fixes: 319e4d0661e5323 ("btrfs: Enhance super validation check") Signed-off-by: Anand Jain anand.jain@oracle.com Reviewed-by: Qu Wenruo wqu@suse.com Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- fs/btrfs/disk-io.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index a8ecccfc36de..3353d3de726a 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3910,9 +3910,11 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info) btrfs_err(fs_info, "no valid FS found"); ret = -EINVAL; } - if (btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP) - btrfs_warn(fs_info, "unrecognized super flag: %llu", + if (btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP) { + btrfs_err(fs_info, "unrecognized or unsupported super flag: %llu", btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP); + ret = -EINVAL; + } if (btrfs_super_root_level(sb) >= BTRFS_MAX_LEVEL) { btrfs_err(fs_info, "tree_root level too big: %d >= %d", btrfs_super_root_level(sb), BTRFS_MAX_LEVEL);

From: Liu Bo bo.li.liu@oracle.com

[ Upstream commit 7583d8d088ff2c323b1d4f15b191ca2c23d32558 ]

Before rbio_orig_end_io() goes to free rbio, rbio may get merged with more bios from other rbios and rbio->bio_list becomes non-empty, in that case, these newly merged bios don't end properly.

Once unlock_stripe() is done, rbio->bio_list will not be updated any more and we can call bio_endio() on all queued bios.

It should only happen in error-out cases, the normal path of recover and full stripe write have already set RBIO_RMW_LOCKED_BIT to disable merge before doing IO, so rbio_orig_end_io() called by them doesn't have the above issue.

Reported-by: Jérôme Carretero cJ-ko@zougloub.eu Signed-off-by: Liu Bo bo.li.liu@oracle.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- fs/btrfs/raid56.c | 37 +++++++++++++++++++++++++------------ 1 file changed, 25 insertions(+), 12 deletions(-)

diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 025e69c57cbd..19e12964aa6d 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -858,10 +858,17 @@ static void __free_raid_bio(struct btrfs_raid_bio *rbio) kfree(rbio); }

-static void free_raid_bio(struct btrfs_raid_bio *rbio) +static void rbio_endio_bio_list(struct bio *cur, blk_status_t err) { - unlock_stripe(rbio); - __free_raid_bio(rbio); + struct bio *next; + + while (cur) { + next = cur->bi_next; + cur->bi_next = NULL; + cur->bi_status = err; + bio_endio(cur); + cur = next; + } }

/* @@ -871,20 +878,26 @@ static void free_raid_bio(struct btrfs_raid_bio *rbio) static void rbio_orig_end_io(struct btrfs_raid_bio *rbio, blk_status_t err) { struct bio *cur = bio_list_get(&rbio->bio_list); - struct bio *next; + struct bio *extra;

if (rbio->generic_bio_cnt) btrfs_bio_counter_sub(rbio->fs_info, rbio->generic_bio_cnt);

- free_raid_bio(rbio); + /* + * At this moment, rbio->bio_list is empty, however since rbio does not + * always have RBIO_RMW_LOCKED_BIT set and rbio is still linked on the + * hash list, rbio may be merged with others so that rbio->bio_list + * becomes non-empty. + * Once unlock_stripe() is done, rbio->bio_list will not be updated any + * more and we can call bio_endio() on all queued bios. + */ + unlock_stripe(rbio); + extra = bio_list_get(&rbio->bio_list); + __free_raid_bio(rbio);

- while (cur) { - next = cur->bi_next; - cur->bi_next = NULL; - cur->bi_status = err; - bio_endio(cur); - cur = next; - } + rbio_endio_bio_list(cur, err); + if (extra) + rbio_endio_bio_list(extra, err); }

/*

From: Sheng Yong shengyong1@huawei.com

[ Upstream commit a9d572c7550044d5b217b5287d99a2e6d34b97b0 ]

When io_bits is set, GCing encrypted block may hit the following hungtask. Since io_bits requires aligned block address, f2fs_submit_page_write may return -EAGAIN if new_blkaddr does not satisify io_bits alignment. As a result, the encrypted page will never be writtenback.

This patch makes move_data_block aware the EAGAIN error and cancel the writeback.

[ 246.751371] INFO: task kworker/u4:4:797 blocked for more than 90 seconds. [ 246.752423] Not tainted 4.15.0-rc4+ #11 [ 246.754176] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 246.755336] kworker/u4:4 D25448 797 2 0x80000000 [ 246.755597] Workqueue: writeback wb_workfn (flush-7:0) [ 246.755616] Call Trace: [ 246.755695] ? __schedule+0x322/0xa90 [ 246.755761] ? blk_init_request_from_bio+0x120/0x120 [ 246.755773] ? pci_mmcfg_check_reserved+0xb0/0xb0 [ 246.755801] ? __radix_tree_create+0x19e/0x200 [ 246.755813] ? delete_node+0x136/0x370 [ 246.755838] schedule+0x43/0xc0 [ 246.755904] io_schedule+0x17/0x40 [ 246.755939] wait_on_page_bit_common+0x17b/0x240 [ 246.755950] ? wake_page_function+0xa0/0xa0 [ 246.755961] ? add_to_page_cache_lru+0x160/0x160 [ 246.755972] ? page_cache_tree_insert+0x170/0x170 [ 246.755983] ? __lru_cache_add+0x96/0xb0 [ 246.756086] __filemap_fdatawait_range+0x14f/0x1c0 [ 246.756097] ? wait_on_page_bit_common+0x240/0x240 [ 246.756120] ? __wake_up_locked_key_bookmark+0x20/0x20 [ 246.756167] ? wait_on_all_pages_writeback+0xc9/0x100 [ 246.756179] ? __remove_ino_entry+0x120/0x120 [ 246.756192] ? wait_woken+0x100/0x100 [ 246.756204] filemap_fdatawait_range+0x9/0x20 [ 246.756216] write_checkpoint+0x18a1/0x1f00 [ 246.756254] ? blk_get_request+0x10/0x10 [ 246.756265] ? cpumask_next_and+0x43/0x60 [ 246.756279] ? f2fs_sync_inode_meta+0x160/0x160 [ 246.756289] ? remove_element.isra.4+0xa0/0xa0 [ 246.756300] ? __put_compound_page+0x40/0x40 [ 246.756310] ? f2fs_sync_fs+0xec/0x1c0 [ 246.756320] ? f2fs_sync_fs+0x120/0x1c0 [ 246.756329] f2fs_sync_fs+0x120/0x1c0 [ 246.756357] ? trace_event_raw_event_f2fs__page+0x260/0x260 [ 246.756393] ? ata_build_rw_tf+0x173/0x410 [ 246.756397] f2fs_balance_fs_bg+0x198/0x390 [ 246.756405] ? drop_inmem_page+0x230/0x230 [ 246.756415] ? ahci_qc_prep+0x1bb/0x2e0 [ 246.756418] ? ahci_qc_issue+0x1df/0x290 [ 246.756422] ? __accumulate_pelt_segments+0x42/0xd0 [ 246.756426] ? f2fs_write_node_pages+0xd1/0x380 [ 246.756429] f2fs_write_node_pages+0xd1/0x380 [ 246.756437] ? sync_node_pages+0x8f0/0x8f0 [ 246.756440] ? update_curr+0x53/0x220 [ 246.756444] ? __accumulate_pelt_segments+0xa2/0xd0 [ 246.756448] ? __update_load_avg_se.isra.39+0x349/0x360 [ 246.756452] ? do_writepages+0x2a/0xa0 [ 246.756456] do_writepages+0x2a/0xa0 [ 246.756460] __writeback_single_inode+0x70/0x490 [ 246.756463] ? check_preempt_wakeup+0x199/0x310 [ 246.756467] writeback_sb_inodes+0x2a2/0x660 [ 246.756471] ? is_empty_dir_inode+0x40/0x40 [ 246.756474] ? __writeback_single_inode+0x490/0x490 [ 246.756477] ? string+0xbf/0xf0 [ 246.756480] ? down_read_trylock+0x35/0x60 [ 246.756484] __writeback_inodes_wb+0x9f/0xf0 [ 246.756488] wb_writeback+0x41d/0x4b0 [ 246.756492] ? writeback_inodes_wb.constprop.55+0x150/0x150 [ 246.756498] ? set_worker_desc+0xf7/0x130 [ 246.756502] ? current_is_workqueue_rescuer+0x60/0x60 [ 246.756511] ? _find_next_bit+0x2c/0xa0 [ 246.756514] ? wb_workfn+0x400/0x5d0 [ 246.756518] wb_workfn+0x400/0x5d0 [ 246.756521] ? finish_task_switch+0xdf/0x2a0 [ 246.756525] ? inode_wait_for_writeback+0x30/0x30 [ 246.756529] process_one_work+0x3a7/0x6f0 [ 246.756533] worker_thread+0x82/0x750 [ 246.756537] kthread+0x16f/0x1c0 [ 246.756541] ? trace_event_raw_event_workqueue_work+0x110/0x110 [ 246.756544] ? kthread_create_worker_on_cpu+0xb0/0xb0 [ 246.756548] ret_from_fork+0x1f/0x30

Signed-off-by: Sheng Yong shengyong1@huawei.com Reviewed-by: Chao Yu yuchao0@huawei.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- fs/f2fs/gc.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index d844dcb80570..bab49a270401 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -686,7 +686,12 @@ static void move_data_block(struct inode *inode, block_t bidx, fio.op = REQ_OP_WRITE; fio.op_flags = REQ_SYNC; fio.new_blkaddr = newaddr; - f2fs_submit_page_write(&fio); + err = f2fs_submit_page_write(&fio); + if (err) { + if (PageWriteback(fio.encrypted_page)) + end_page_writeback(fio.encrypted_page); + goto put_page_out; + }

f2fs_update_iostat(fio.sbi, FS_GC_DATA_IO, F2FS_BLKSIZE);

From: Xose Vazquez Perez xose.vazquez@gmail.com

[ Upstream commit 3f884a0a8bdf28cfd1e9987d54d83350096cdd46 ]

Replace "" with NULL for product revision level, and merge TEXEL duplicate entries.

Cc: Hannes Reinecke hare@suse.de Cc: Martin K. Petersen martin.petersen@oracle.com Cc: James E.J. Bottomley jejb@linux.vnet.ibm.com Cc: SCSI ML linux-scsi@vger.kernel.org Signed-off-by: Xose Vazquez Perez xose.vazquez@gmail.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/scsi/scsi_devinfo.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c index 0a17b9e5dc35..6d976db33d9f 100644 --- a/drivers/scsi/scsi_devinfo.c +++ b/drivers/scsi/scsi_devinfo.c @@ -108,8 +108,8 @@ static struct { * seagate controller, which causes SCSI code to reset bus. */ {"HP", "C1750A", "3226", BLIST_NOLUN}, /* scanjet iic */ - {"HP", "C1790A", "", BLIST_NOLUN}, /* scanjet iip */ - {"HP", "C2500A", "", BLIST_NOLUN}, /* scanjet iicx */ + {"HP", "C1790A", NULL, BLIST_NOLUN}, /* scanjet iip */ + {"HP", "C2500A", NULL, BLIST_NOLUN}, /* scanjet iicx */ {"MEDIAVIS", "CDR-H93MV", "1.31", BLIST_NOLUN}, /* locks up */ {"MICROTEK", "ScanMaker II", "5.61", BLIST_NOLUN}, /* responds to all lun */ {"MITSUMI", "CD-R CR-2201CS", "6119", BLIST_NOLUN}, /* locks up */ @@ -119,7 +119,7 @@ static struct { {"QUANTUM", "FIREBALL ST4.3S", "0F0C", BLIST_NOLUN}, /* locks up */ {"RELISYS", "Scorpio", NULL, BLIST_NOLUN}, /* responds to all lun */ {"SANKYO", "CP525", "6.64", BLIST_NOLUN}, /* causes failed REQ SENSE, extra reset */ - {"TEXEL", "CD-ROM", "1.06", BLIST_NOLUN}, + {"TEXEL", "CD-ROM", "1.06", BLIST_NOLUN | BLIST_BORKEN}, {"transtec", "T5008", "0001", BLIST_NOREPORTLUN }, {"YAMAHA", "CDR100", "1.00", BLIST_NOLUN}, /* locks up */ {"YAMAHA", "CDR102", "1.00", BLIST_NOLUN}, /* locks up */ @@ -255,7 +255,6 @@ static struct { {"ST650211", "CF", NULL, BLIST_RETRY_HWERROR}, {"SUN", "T300", "*", BLIST_SPARSELUN}, {"SUN", "T4", "*", BLIST_SPARSELUN}, - {"TEXEL", "CD-ROM", "1.06", BLIST_BORKEN}, {"Tornado-", "F4", "*", BLIST_NOREPORTLUN}, {"TOSHIBA", "CDROM", NULL, BLIST_ISROM}, {"TOSHIBA", "CD-ROM", NULL, BLIST_ISROM},

From: Andi Shyti andi.shyti@samsung.com

[ Upstream commit cba04cdf437d745fac85220d1d692a9ae23d7004 ]

The interrupt is requested before the device is powered on and it's value in some cases cannot be reliable. It happens on some devices that an interrupt is generated as soon as requested before having the chance to disable the irq.

Set the irq flag as IRQ_NOAUTOEN before requesting it.

This patch mutes the error:

stmfts 2-0049: failed to read events: -11

received sometimes during boot time.

Signed-off-by: Andi Shyti andi.shyti@samsung.com Signed-off-by: Dmitry Torokhov dmitry.torokhov@gmail.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/input/touchscreen/stmfts.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/input/touchscreen/stmfts.c b/drivers/input/touchscreen/stmfts.c index 2a123e20a42e..efdb1a75a163 100644 --- a/drivers/input/touchscreen/stmfts.c +++ b/drivers/input/touchscreen/stmfts.c @@ -682,6 +682,14 @@ static int stmfts_probe(struct i2c_client *client,

input_set_drvdata(sdata->input, sdata);

+ /* + * stmfts_power_on expects interrupt to be disabled, but + * at this point the device is still off and I do not trust + * the status of the irq line that can generate some spurious + * interrupts. To be on the safe side it's better to not enable + * the interrupts during their request. + */ + irq_set_status_flags(client->irq, IRQ_NOAUTOEN); err = devm_request_threaded_irq(&client->dev, client->irq, NULL, stmfts_irq_handler, IRQF_ONESHOT, @@ -689,9 +697,6 @@ static int stmfts_probe(struct i2c_client *client, if (err) return err;

- /* stmfts_power_on expects interrupt to be disabled */ - disable_irq(client->irq); - dev_dbg(&client->dev, "initializing ST-Microelectronics FTS...\n");

err = stmfts_power_on(sdata);

From: Wei Yongjun weiyongjun1@huawei.com

[ Upstream commit e58decc9c51eb61697aba35ba8eda33f4b80552d ]

Fix to return error code -EINVAL instead of 0 when num_vfs above limit_vfs, as done elsewhere in this function.

Fixes: 0dc786219186 ("nfp: handle SR-IOV already enabled when driver is probing") Signed-off-by: Wei Yongjun weiyongjun1@huawei.com Acked-by: Jakub Kicinski jakub.kicinski@netronome.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/net/ethernet/netronome/nfp/nfp_main.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c index 35eaccbece36..2222577bdcf3 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c @@ -518,6 +518,7 @@ static int nfp_pci_probe(struct pci_dev *pdev, dev_err(&pdev->dev, "Error: %d VFs already enabled, but loaded FW can only support %d\n", pf->num_vfs, pf->limit_vfs); + err = -EINVAL; goto err_fw_unload; }

From: Alexei Starovoitov ast@kernel.org

[ Upstream commit 8e6875250a1189e0d8db8b05e18abe63c2744521 ]

The test incorrectly doing mkdir /mnt/cgroup-test-work-dirtest-bpf-based-device-cgroup instead of mkdir /mnt/cgroup-test-work-dir/test-bpf-based-device-cgroup

somehow such mkdir succeeds and new directory appears: /mnt/cgroup-test-work-dir/cgroup-test-work-dirtest-bpf-based-device-cgroup

Later cleanup via nftw("/mnt/cgroup-test-work-dir", ...); doesn't walk this directory. "rmdir /mnt/cgroup-test-work-dir" succeeds, but bpf program and dangling cgroup stays in memory. That's a separate issue on a cgroup side. For now fix the test.

Fixes: 37f1ba0909df ("selftests/bpf: add a test for device cgroup controller") Signed-off-by: Alexei Starovoitov ast@kernel.org Signed-off-by: Daniel Borkmann daniel@iogearbox.net Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- tools/testing/selftests/bpf/test_dev_cgroup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/test_dev_cgroup.c b/tools/testing/selftests/bpf/test_dev_cgroup.c index 02c85d6c89b0..070bc3c9a873 100644 --- a/tools/testing/selftests/bpf/test_dev_cgroup.c +++ b/tools/testing/selftests/bpf/test_dev_cgroup.c @@ -19,7 +19,7 @@

#define DEV_CGROUP_PROG "./dev_cgroup.o"

-#define TEST_CGROUP "test-bpf-based-device-cgroup/" +#define TEST_CGROUP "/test-bpf-based-device-cgroup/"

int main(int argc, char **argv) {

From: Avinash Dayanand avinash.dayanand@intel.com

[ Upstream commit 06aa040f039404a0039a5158cd12f41187487a1f ]

When a host disables and enables a PF device, all the associated VFs are removed and added back in. It also generates a PFR which in turn resets all the connected VFs. This behaviour is different from that of Linux guest on Linux host. Hence we end up in a situation where there's a PFR and device removal at the same time. And watchdog doesn't have a clue about this and schedules a reset_task. This patch adds code to send signal to reset_task that the device is currently being removed.

Signed-off-by: Avinash Dayanand avinash.dayanand@intel.com Tested-by: Andrew Bowers andrewx.bowers@intel.com Signed-off-by: Jeff Kirsher jeffrey.t.kirsher@intel.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/net/ethernet/intel/i40evf/i40evf.h | 1 + drivers/net/ethernet/intel/i40evf/i40evf_main.c | 9 ++++++++- 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h index de0af521d602..ecf752cb8772 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf.h +++ b/drivers/net/ethernet/intel/i40evf/i40evf.h @@ -187,6 +187,7 @@ enum i40evf_state_t { enum i40evf_critical_section_t { __I40EVF_IN_CRITICAL_TASK, /* cannot be interrupted */ __I40EVF_IN_CLIENT_TASK, + __I40EVF_IN_REMOVE_TASK, /* device being removed */ };

/* board specific private data structure */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index 7b2a4eba92e2..1fe466c7849a 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -1855,6 +1855,12 @@ static void i40evf_reset_task(struct work_struct *work) u32 reg_val; int i = 0, err;

+ /* When device is being removed it doesn't make sense to run the reset + * task, just return in such a case. + */ + if (test_bit(__I40EVF_IN_REMOVE_TASK, &adapter->crit_section)) + return; + while (test_and_set_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section)) usleep_range(500, 1000); @@ -3066,7 +3072,8 @@ static void i40evf_remove(struct pci_dev *pdev) struct i40evf_mac_filter *f, *ftmp; struct i40e_hw *hw = &adapter->hw; int err; - + /* Indicate we are in remove and not to run reset_task */ + set_bit(__I40EVF_IN_REMOVE_TASK, &adapter->crit_section); cancel_delayed_work_sync(&adapter->init_task); cancel_work_sync(&adapter->reset_task); cancel_delayed_work_sync(&adapter->client_task);

From: Amritha Nambiar amritha.nambiar@intel.com

[ Upstream commit bbf0bdd41fbf71a008325bdcf0df63ab088bf532 ]

Fix recreating the channel VSIs during the reset flow to reconfigure the Tx rings and the queue context associated with the channel VSI. Also update the next_base_queue for the VSI while rebuilding the channel VSIs after a reset.

Signed-off-by: Amritha Nambiar amritha.nambiar@intel.com Tested-by: Andrew Bowers andrewx.bowers@intel.com Signed-off-by: Jeff Kirsher jeffrey.t.kirsher@intel.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/net/ethernet/intel/i40e/i40e_main.c | 11 +++++++++++ 1 file changed, 11 insertions(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index af792112a2d3..973bad818e81 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -9077,6 +9077,17 @@ static int i40e_rebuild_channels(struct i40e_vsi *vsi) vsi->uplink_seid); return ret; } + /* Reconfigure TX queues using QTX_CTL register */ + ret = i40e_channel_config_tx_ring(vsi->back, vsi, ch); + if (ret) { + dev_info(&vsi->back->pdev->dev, + "failed to configure TX rings for channel %u\n", + ch->seid); + return ret; + } + /* update 'next_base_queue' */ + vsi->next_base_queue = vsi->next_base_queue + + ch->num_queue_pairs; if (ch->max_tx_rate) { u64 credits = ch->max_tx_rate;

From: David Hildenbrand david@redhat.com

[ Upstream commit b3ecd4aa8632a86428605ab73393d14779019d82 ]

Another VCPU might try to modify the SCB while we are creating the shadow SCB. In general this is no problem - unless the compiler decides to not load values once, but e.g. twice.

For us, this is only relevant when checking/working with such values. E.g. the prefix value, the mso, state of transactional execution and addresses of satellite blocks.

E.g. if we blindly forward values (e.g. general purpose registers or execution controls after masking), we don't care.

Leaving unpin_blocks() untouched for now, will handle it separately.

The worst thing right now that I can see would be a missed prefix un/remap (mso, prefix, tx) or using wrong guest addresses. Nothing critical, but let's try to avoid unpredictable behavior.

Signed-off-by: David Hildenbrand david@redhat.com Message-Id: 20180116171526.12343-2-david@redhat.com Reviewed-by: Christian Borntraeger borntraeger@de.ibm.com Acked-by: Cornelia Huck cohuck@redhat.com Signed-off-by: Christian Borntraeger borntraeger@de.ibm.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- arch/s390/kvm/vsie.c | 50 +++++++++++++++++++++++++++++++------------------- 1 file changed, 31 insertions(+), 19 deletions(-)

diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index 751348348477..11fc525e6e7f 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -28,7 +28,11 @@ struct vsie_page { * the same offset as that in struct sie_page! */ struct mcck_volatile_info mcck_info; /* 0x0200 */ - /* the pinned originial scb */ + /* + * The pinned original scb. Be aware that other VCPUs can modify + * it while we read from it. Values that are used for conditions or + * are reused conditionally, should be accessed via READ_ONCE. + */ struct kvm_s390_sie_block *scb_o; /* 0x0218 */ /* the shadow gmap in use by the vsie_page */ struct gmap *gmap; /* 0x0220 */ @@ -140,12 +144,13 @@ static int shadow_crycb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) { struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s; struct kvm_s390_sie_block *scb_o = vsie_page->scb_o; - u32 crycb_addr = scb_o->crycbd & 0x7ffffff8U; + const uint32_t crycbd_o = READ_ONCE(scb_o->crycbd); + const u32 crycb_addr = crycbd_o & 0x7ffffff8U; unsigned long *b1, *b2; u8 ecb3_flags;

scb_s->crycbd = 0; - if (!(scb_o->crycbd & vcpu->arch.sie_block->crycbd & CRYCB_FORMAT1)) + if (!(crycbd_o & vcpu->arch.sie_block->crycbd & CRYCB_FORMAT1)) return 0; /* format-1 is supported with message-security-assist extension 3 */ if (!test_kvm_facility(vcpu->kvm, 76)) @@ -183,12 +188,15 @@ static void prepare_ibc(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) { struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s; struct kvm_s390_sie_block *scb_o = vsie_page->scb_o; + /* READ_ONCE does not work on bitfields - use a temporary variable */ + const uint32_t __new_ibc = scb_o->ibc; + const uint32_t new_ibc = READ_ONCE(__new_ibc) & 0x0fffU; __u64 min_ibc = (sclp.ibc >> 16) & 0x0fffU;

scb_s->ibc = 0; /* ibc installed in g2 and requested for g3 */ - if (vcpu->kvm->arch.model.ibc && (scb_o->ibc & 0x0fffU)) { - scb_s->ibc = scb_o->ibc & 0x0fffU; + if (vcpu->kvm->arch.model.ibc && new_ibc) { + scb_s->ibc = new_ibc; /* takte care of the minimum ibc level of the machine */ if (scb_s->ibc < min_ibc) scb_s->ibc = min_ibc; @@ -259,6 +267,10 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) { struct kvm_s390_sie_block *scb_o = vsie_page->scb_o; struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s; + /* READ_ONCE does not work on bitfields - use a temporary variable */ + const uint32_t __new_prefix = scb_o->prefix; + const uint32_t new_prefix = READ_ONCE(__new_prefix); + const bool wants_tx = READ_ONCE(scb_o->ecb) & ECB_TE; bool had_tx = scb_s->ecb & ECB_TE; unsigned long new_mso = 0; int rc; @@ -306,14 +318,14 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) scb_s->icpua = scb_o->icpua;

if (!(atomic_read(&scb_s->cpuflags) & CPUSTAT_SM)) - new_mso = scb_o->mso & 0xfffffffffff00000UL; + new_mso = READ_ONCE(scb_o->mso) & 0xfffffffffff00000UL; /* if the hva of the prefix changes, we have to remap the prefix */ - if (scb_s->mso != new_mso || scb_s->prefix != scb_o->prefix) + if (scb_s->mso != new_mso || scb_s->prefix != new_prefix) prefix_unmapped(vsie_page); /* SIE will do mso/msl validity and exception checks for us */ scb_s->msl = scb_o->msl & 0xfffffffffff00000UL; scb_s->mso = new_mso; - scb_s->prefix = scb_o->prefix; + scb_s->prefix = new_prefix;

/* We have to definetly flush the tlb if this scb never ran */ if (scb_s->ihcpu != 0xffffU) @@ -325,11 +337,11 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_ESOP)) scb_s->ecb |= scb_o->ecb & ECB_HOSTPROTINT; /* transactional execution */ - if (test_kvm_facility(vcpu->kvm, 73)) { + if (test_kvm_facility(vcpu->kvm, 73) && wants_tx) { /* remap the prefix is tx is toggled on */ - if ((scb_o->ecb & ECB_TE) && !had_tx) + if (!had_tx) prefix_unmapped(vsie_page); - scb_s->ecb |= scb_o->ecb & ECB_TE; + scb_s->ecb |= ECB_TE; } /* branch prediction */ if (test_kvm_facility(vcpu->kvm, 82)) @@ -539,9 +551,9 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) gpa_t gpa; int rc = 0;

- gpa = scb_o->scaol & ~0xfUL; + gpa = READ_ONCE(scb_o->scaol) & ~0xfUL; if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_64BSCAO)) - gpa |= (u64) scb_o->scaoh << 32; + gpa |= (u64) READ_ONCE(scb_o->scaoh) << 32; if (gpa) { if (!(gpa & ~0x1fffUL)) rc = set_validity_icpt(scb_s, 0x0038U); @@ -561,7 +573,7 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) scb_s->scaol = (u32)(u64)hpa; }

- gpa = scb_o->itdba & ~0xffUL; + gpa = READ_ONCE(scb_o->itdba) & ~0xffUL; if (gpa && (scb_s->ecb & ECB_TE)) { if (!(gpa & ~0x1fffU)) { rc = set_validity_icpt(scb_s, 0x0080U); @@ -576,7 +588,7 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) scb_s->itdba = hpa; }

- gpa = scb_o->gvrd & ~0x1ffUL; + gpa = READ_ONCE(scb_o->gvrd) & ~0x1ffUL; if (gpa && (scb_s->eca & ECA_VX) && !(scb_s->ecd & ECD_HOSTREGMGMT)) { if (!(gpa & ~0x1fffUL)) { rc = set_validity_icpt(scb_s, 0x1310U); @@ -594,7 +606,7 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) scb_s->gvrd = hpa; }

- gpa = scb_o->riccbd & ~0x3fUL; + gpa = READ_ONCE(scb_o->riccbd) & ~0x3fUL; if (gpa && (scb_s->ecb3 & ECB3_RI)) { if (!(gpa & ~0x1fffUL)) { rc = set_validity_icpt(scb_s, 0x0043U); @@ -612,8 +624,8 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) if ((scb_s->ecb & ECB_GS) && !(scb_s->ecd & ECD_HOSTREGMGMT)) { unsigned long sdnxc;

- gpa = scb_o->sdnxo & ~0xfUL; - sdnxc = scb_o->sdnxo & 0xfUL; + gpa = READ_ONCE(scb_o->sdnxo) & ~0xfUL; + sdnxc = READ_ONCE(scb_o->sdnxo) & 0xfUL; if (!gpa || !(gpa & ~0x1fffUL)) { rc = set_validity_icpt(scb_s, 0x10b0U); goto unpin; @@ -778,7 +790,7 @@ static void retry_vsie_icpt(struct vsie_page *vsie_page) static int handle_stfle(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) { struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s; - __u32 fac = vsie_page->scb_o->fac & 0x7ffffff8U; + __u32 fac = READ_ONCE(vsie_page->scb_o->fac) & 0x7ffffff8U;

if (fac && test_kvm_facility(vcpu->kvm, 7)) { retry_vsie_icpt(vsie_page);

From: Eryu Guan eguan@redhat.com

[ Upstream commit 6b136a24b05c81a24e0b648a4bd938bcd0c4f69e ]

Attributes that only implement .seq_ops are read-only, any write to them should be rejected. But currently kernel would crash when writing to such debugfs entries, e.g.

chmod +w /sys/kernel/debug/block/<dev>/requeue_list echo 0 > /sys/kernel/debug/block/<dev>/requeue_list chmod -w /sys/kernel/debug/block/<dev>/requeue_list

Fix it by returning -EPERM in blk_mq_debugfs_write() when writing to such attributes.

Cc: Ming Lei ming.lei@redhat.com Signed-off-by: Eryu Guan eguan@redhat.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- block/blk-mq-debugfs.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index b56a4f35720d..54bd8c31b822 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -703,7 +703,11 @@ static ssize_t blk_mq_debugfs_write(struct file *file, const char __user *buf, const struct blk_mq_debugfs_attr *attr = m->private; void *data = d_inode(file->f_path.dentry->d_parent)->i_private;

- if (!attr->write) + /* + * Attributes that only implement .seq_ops are read-only and 'attr' is + * the same with 'data' in this case. + */ + if (attr == data || !attr->write) return -EPERM;

return attr->write(data, buf, count, ppos);

From: Corinna Vinschen vinschen@redhat.com

[ Upstream commit 177132df5e45b134c147f419f567a3b56aafaf2b ]

Before libvirt modifies the MAC address and vlan tag for an SRIOV VF for use by a virtual machine (either using vfio device assignment or macvtap passthru mode), it saves the current MAC address and vlan tag so that it can reset them to their original value when the guest is done. Libvirt can't leave the VF MAC set to the value used by the now-defunct guest since it may be started again later using a different VF, but it certainly shouldn't just pick any random value, either. So it saves the state of everything prior to using the VF, and resets it to that.

The igb driver initializes the MAC addresses of all VFs to 00:00:00:00:00:00, and reports that when asked (via an RTM_GETLINK netlink message, also visible in the list of VFs in the output of "ip link show"). But when libvirt attempts to restore the MAC address back to 00:00:00:00:00:00 (using an RTM_SETLINK netlink message) the kernel responds with "Invalid argument".

Forbidding a reset back to the original value leaves the VF MAC at the value set for the now-defunct virtual machine. Especially on a system with NetworkManager enabled, this has very bad consequences, since NetworkManager forces all interfacess to be IFF_UP all the time - if the same virtual machine is restarted using a different VF (or even on a different host), there will be multiple interfaces watching for traffic with the same MAC address.

To allow libvirt to revert to the original state, we need a way to remove the administrative set MAC on a VF, to allow normal host operation again, and to reset/overwrite the VF MAC via VF netdev.

This patch implements the outlined scenario by allowing to set the VF MAC to 00:00:00:00:00:00 via RTM_SETLINK on the PF. igb_ndo_set_vf_mac resets the IGB_VF_FLAG_PF_SET_MAC flag to 0, so it's possible to reset the VF MAC back to the original value via the VF netdev.

Note: Recent patches to libvirt allow for a workaround if the NIC isn't capable of resetting the administrative MAC back to all 0, but in theory the NIC should allow resetting the MAC in the first place.

Signed-off-by: Corinna Vinschen vinschen@redhat.com Tested-by: Aaron Brown arron.f.brown@intel.com Signed-off-by: Jeff Kirsher jeffrey.t.kirsher@intel.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/net/ethernet/intel/igb/igb_main.c | 42 +++++++++++++++++++++++-------- 1 file changed, 31 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index c69a5b3ae8c8..13dd7d2d90fe 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -8718,7 +8718,8 @@ static void igb_rar_set_index(struct igb_adapter *adapter, u32 index)

/* Indicate to hardware the Address is Valid. */ if (adapter->mac_table[index].state & IGB_MAC_STATE_IN_USE) { - rar_high |= E1000_RAH_AV; + if (is_valid_ether_addr(addr)) + rar_high |= E1000_RAH_AV;

if (hw->mac.type == e1000_82575) rar_high |= E1000_RAH_POOL_1 * @@ -8756,17 +8757,36 @@ static int igb_set_vf_mac(struct igb_adapter *adapter, static int igb_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) { struct igb_adapter *adapter = netdev_priv(netdev); - if (!is_valid_ether_addr(mac) || (vf >= adapter->vfs_allocated_count)) + + if (vf >= adapter->vfs_allocated_count) + return -EINVAL; + + /* Setting the VF MAC to 0 reverts the IGB_VF_FLAG_PF_SET_MAC + * flag and allows to overwrite the MAC via VF netdev. This + * is necessary to allow libvirt a way to restore the original + * MAC after unbinding vfio-pci and reloading igbvf after shutting + * down a VM. + */ + if (is_zero_ether_addr(mac)) { + adapter->vf_data[vf].flags &= ~IGB_VF_FLAG_PF_SET_MAC; + dev_info(&adapter->pdev->dev, + "remove administratively set MAC on VF %d\n", + vf); + } else if (is_valid_ether_addr(mac)) { + adapter->vf_data[vf].flags |= IGB_VF_FLAG_PF_SET_MAC; + dev_info(&adapter->pdev->dev, "setting MAC %pM on VF %d\n", + mac, vf); + dev_info(&adapter->pdev->dev, + "Reload the VF driver to make this change effective."); + /* Generate additional warning if PF is down */ + if (test_bit(__IGB_DOWN, &adapter->state)) { + dev_warn(&adapter->pdev->dev, + "The VF MAC address has been set, but the PF device is not up.\n"); + dev_warn(&adapter->pdev->dev, + "Bring the PF device up before attempting to use the VF device.\n"); + } + } else { return -EINVAL; - adapter->vf_data[vf].flags |= IGB_VF_FLAG_PF_SET_MAC; - dev_info(&adapter->pdev->dev, "setting MAC %pM on VF %d\n", mac, vf); - dev_info(&adapter->pdev->dev, - "Reload the VF driver to make this change effective."); - if (test_bit(__IGB_DOWN, &adapter->state)) { - dev_warn(&adapter->pdev->dev, - "The VF MAC address has been set, but the PF device is not up.\n"); - dev_warn(&adapter->pdev->dev, - "Bring the PF device up before attempting to use the VF device.\n"); } return igb_set_vf_mac(adapter, vf, mac); }

From: Daniel Hua daniel.hua@ni.com

[ Upstream commit 3a53285228165225a7f76c7d5ff1ddc0213ce0e4 ]

Problem description: After ethernet cable connect and disconnect for several iterations on a device with i210, tx timestamp will stop being put into the socket.

Steps to reproduce: 1. Setup a device with i210 and wire it to a 802.1AS capable switch ( Extreme Networks Summit x440 is used in our case) 2. Have the gptp daemon running on the device and make sure it is synced with the switch 3. Have the switch disable and enable the port, wait for the device gets resynced with the switch 4. Iterates step 3 until the device is not albe to get resynced 5. Review the log in dmesg and you will see warning message "igb : clearing Tx timestamp hang"

Root cause: If ptp_tx_work() gets scheduled just before the port gets disabled, a LINK DOWN event will be processed before ptp_tx_work(), which may cause timeout in ptp_tx_work(). In the timeout logic, the TSYNCTXCTL's TXTT bit (Transmit timestamp valid bit) is not cleared, causing no new timestamp loaded to TXSTMP register. Consequently therefore, no new interrupt is triggerred by TSICR.TXTS bit and no more Tx timestamp send to the socket.

Signed-off-by: Daniel Hua daniel.hua@ni.com Tested-by: Aaron Brown aaron.f.brown@intel.com Signed-off-by: Jeff Kirsher jeffrey.t.kirsher@intel.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/net/ethernet/intel/igb/igb_ptp.c | 9 +++++++++ 1 file changed, 9 insertions(+)

diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 841c2a083349..0746b19ec6d3 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -643,6 +643,10 @@ static void igb_ptp_tx_work(struct work_struct *work) adapter->ptp_tx_skb = NULL; clear_bit_unlock(__IGB_PTP_TX_IN_PROGRESS, &adapter->state); adapter->tx_hwtstamp_timeouts++; + /* Clear the tx valid bit in TSYNCTXCTL register to enable + * interrupt + */ + rd32(E1000_TXSTMPH); dev_warn(&adapter->pdev->dev, "clearing Tx timestamp hang\n"); return; } @@ -717,6 +721,7 @@ void igb_ptp_rx_hang(struct igb_adapter *adapter) */ void igb_ptp_tx_hang(struct igb_adapter *adapter) { + struct e1000_hw *hw = &adapter->hw; bool timeout = time_is_before_jiffies(adapter->ptp_tx_start + IGB_PTP_TX_TIMEOUT);

@@ -736,6 +741,10 @@ void igb_ptp_tx_hang(struct igb_adapter *adapter) adapter->ptp_tx_skb = NULL; clear_bit_unlock(__IGB_PTP_TX_IN_PROGRESS, &adapter->state); adapter->tx_hwtstamp_timeouts++; + /* Clear the tx valid bit in TSYNCTXCTL register to enable + * interrupt + */ + rd32(E1000_TXSTMPH); dev_warn(&adapter->pdev->dev, "clearing Tx timestamp hang\n"); } }

From: Vitaly Kuznetsov vkuznets@redhat.com

[ Upstream commit 617ab45c9a8900e64a78b43696c02598b8cad68b ]

When hypercall-based TLB flush was enabled for Hyper-V guests PCID feature was deliberately suppressed as a precaution: back then PCID was never exposed to Hyper-V guests and it wasn't clear what will happen if some day it becomes available. The day came and PCID/INVPCID features are already exposed on certain Hyper-V hosts.

From TLFS (as of 5.0b) it is unclear how TLB flush hypercalls combine with

PCID. In particular the usage of PCID is per-cpu based: the same mm gets different CR3 values on different CPUs. If the hypercall does exact matching this will fail. However, this is not the case. David Zhang explains:

"In practice, the AddressSpace argument is ignored on any VM that supports PCIDs.

Architecturally, the AddressSpace argument must match the CR3 with PCID bits stripped out (i.e., the low 12 bits of AddressSpace should be 0 in long mode). The flush hypercalls flush all PCIDs for the specified AddressSpace."

With this, PCID can be enabled.

Signed-off-by: Vitaly Kuznetsov vkuznets@redhat.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Cc: David Zhang dazhan@microsoft.com Cc: Stephen Hemminger sthemmin@microsoft.com Cc: Haiyang Zhang haiyangz@microsoft.com Cc: "Michael Kelley (EOSG)" Michael.H.Kelley@microsoft.com Cc: Andy Lutomirski luto@kernel.org Cc: devel@linuxdriverproject.org Cc: "K. Y. Srinivasan" kys@microsoft.com Cc: Aditya Bhandari adityabh@microsoft.com Link: https://lkml.kernel.org/r/20180124103629.29980-1-vkuznets@redhat.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- arch/x86/hyperv/mmu.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c index 9cc9e1c1e2db..56c9ebac946f 100644 --- a/arch/x86/hyperv/mmu.c +++ b/arch/x86/hyperv/mmu.c @@ -137,7 +137,12 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus, }

if (info->mm) { + /* + * AddressSpace argument must match the CR3 with PCID bits + * stripped out. + */ flush->address_space = virt_to_phys(info->mm->pgd); + flush->address_space &= CR3_ADDR_MASK; flush->flags = 0; } else { flush->address_space = 0; @@ -219,7 +224,12 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, }

if (info->mm) { + /* + * AddressSpace argument must match the CR3 with PCID bits + * stripped out. + */ flush->address_space = virt_to_phys(info->mm->pgd); + flush->address_space &= CR3_ADDR_MASK; flush->flags = 0; } else { flush->address_space = 0; @@ -278,8 +288,6 @@ void hyperv_setup_mmu_ops(void) if (!(ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED)) return;

- setup_clear_cpu_cap(X86_FEATURE_PCID); - if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) { pr_info("Using hypercall for remote TLB flush\n"); pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others;

From: Aaron Sierra asierra@xes-inc.com

[ Upstream commit c7e1b4059075c9e8eed101d7cc5da43e95eb5e18 ]

Exar sleep wake-up handling has been done on a per-channel basis by virtue of INT0 being accessible from each channel's address space. I believe this was initially done out of necessity, but now that Exar devices have their own driver, we can do things more efficiently by registering a dedicated INT0 handler at the PCI device level.

I see this change providing the following benefits:

1. If more than one port is active, eliminates the redundant bus cycles for reading INT0 on every interrupt. 2. This note associated with hooking in the per-channel handler in 8250_port.c is resolved: /* Fixme: probably not the best place for this */

Cc: Matt Schulte matts@commtech-fastcom.com Signed-off-by: Aaron Sierra asierra@xes-inc.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/tty/serial/8250/8250_exar.c | 34 ++++++++++++++++++++++++++++++---- drivers/tty/serial/8250/8250_port.c | 26 -------------------------- 2 files changed, 30 insertions(+), 30 deletions(-)

diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c index a402878c9f30..38af306ca0e8 100644 --- a/drivers/tty/serial/8250/8250_exar.c +++ b/drivers/tty/serial/8250/8250_exar.c @@ -34,6 +34,7 @@ #define PCI_DEVICE_ID_EXAR_XR17V4358 0x4358 #define PCI_DEVICE_ID_EXAR_XR17V8358 0x8358

+#define UART_EXAR_INT0 0x80 #define UART_EXAR_8XMODE 0x88 /* 8X sampling rate select */

#define UART_EXAR_FCTR 0x08 /* Feature Control Register */ @@ -121,6 +122,7 @@ struct exar8250_board { struct exar8250 { unsigned int nr; struct exar8250_board *board; + void __iomem *virt; int line[0]; };

@@ -131,12 +133,9 @@ static int default_setup(struct exar8250 *priv, struct pci_dev *pcidev, const struct exar8250_board *board = priv->board; unsigned int bar = 0;

- if (!pcim_iomap_table(pcidev)[bar] && !pcim_iomap(pcidev, bar, 0)) - return -ENOMEM; - port->port.iotype = UPIO_MEM; port->port.mapbase = pci_resource_start(pcidev, bar) + offset; - port->port.membase = pcim_iomap_table(pcidev)[bar] + offset; + port->port.membase = priv->virt + offset; port->port.regshift = board->reg_shift;

return 0; @@ -420,6 +419,25 @@ static void pci_xr17v35x_exit(struct pci_dev *pcidev) port->port.private_data = NULL; }

+/* + * These Exar UARTs have an extra interrupt indicator that could fire for a + * few interrupts that are not presented/cleared through IIR. One of which is + * a wakeup interrupt when coming out of sleep. These interrupts are only + * cleared by reading global INT0 or INT1 registers as interrupts are + * associated with channel 0. The INT[3:0] registers _are_ accessible from each + * channel's address space, but for the sake of bus efficiency we register a + * dedicated handler at the PCI device level to handle them. + */ +static irqreturn_t exar_misc_handler(int irq, void *data) +{ + struct exar8250 *priv = data; + + /* Clear all PCI interrupts by reading INT0. No effect on IIR */ + ioread8(priv->virt + UART_EXAR_INT0); + + return IRQ_HANDLED; +} + static int exar_pci_probe(struct pci_dev *pcidev, const struct pci_device_id *ent) { @@ -448,6 +466,9 @@ exar_pci_probe(struct pci_dev *pcidev, const struct pci_device_id *ent) return -ENOMEM;

priv->board = board; + priv->virt = pcim_iomap(pcidev, bar, 0); + if (!priv->virt) + return -ENOMEM;

pci_set_master(pcidev);

@@ -461,6 +482,11 @@ exar_pci_probe(struct pci_dev *pcidev, const struct pci_device_id *ent) uart.port.irq = pci_irq_vector(pcidev, 0); uart.port.dev = &pcidev->dev;

+ rc = devm_request_irq(&pcidev->dev, uart.port.irq, exar_misc_handler, + IRQF_SHARED, "exar_uart", priv); + if (rc) + return rc; + for (i = 0; i < nr_ports && i < maxnr; i++) { rc = board->setup(priv, pcidev, &uart, i); if (rc) { diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 11434551ac0a..1328c7e70108 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -441,7 +441,6 @@ static void io_serial_out(struct uart_port *p, int offset, int value) }

static int serial8250_default_handle_irq(struct uart_port *port); -static int exar_handle_irq(struct uart_port *port);

static void set_io_from_upio(struct uart_port *p) { @@ -1883,26 +1882,6 @@ static int serial8250_default_handle_irq(struct uart_port *port) return ret; }

-/* - * These Exar UARTs have an extra interrupt indicator that could - * fire for a few unimplemented interrupts. One of which is a - * wakeup event when coming out of sleep. Put this here just - * to be on the safe side that these interrupts don't go unhandled. - */ -static int exar_handle_irq(struct uart_port *port) -{ - unsigned int iir = serial_port_in(port, UART_IIR); - int ret = 0; - - if (((port->type == PORT_XR17V35X) || (port->type == PORT_XR17D15X)) && - serial_port_in(port, UART_EXAR_INT0) != 0) - ret = 1; - - ret |= serial8250_handle_irq(port, iir); - - return ret; -} - /* * Newer 16550 compatible parts such as the SC16C650 & Altera 16550 Soft IP * have a programmable TX threshold that triggers the THRE interrupt in @@ -3067,11 +3046,6 @@ static void serial8250_config_port(struct uart_port *port, int flags) if (port->type == PORT_UNKNOWN) serial8250_release_std_resource(up);

- /* Fixme: probably not the best place for this */ - if ((port->type == PORT_XR17V35X) || - (port->type == PORT_XR17D15X)) - port->handle_irq = exar_handle_irq; - register_dev_spec_attr_grp(up); up->fcr = uart_config[up->port.type].fcr; }

From: Jason Gunthorpe jgg@mellanox.com

[ Upstream commit 3624a8f02568f08aef299d3b117f2226f621177d ]

Returning EOPNOTSUPP is problematic because it can also be returned by the method function, and we use it in quite a few places in drivers these days.

Instead, dedicate EPROTONOSUPPORT to indicate that the ioctl framework is enabled but the requested object and method are not supported by the kernel. No other case will return this code, and it lets userspace know to fall back to write().

grep says we do not use it today in drivers/infiniband subsystem.

Signed-off-by: Jason Gunthorpe jgg@mellanox.com Reviewed-by: Matan Barak matanb@mellanox.com Signed-off-by: Doug Ledford dledford@redhat.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/infiniband/core/uverbs_ioctl.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/drivers/infiniband/core/uverbs_ioctl.c b/drivers/infiniband/core/uverbs_ioctl.c index 71ff2644e053..d96dc1d17be1 100644 --- a/drivers/infiniband/core/uverbs_ioctl.c +++ b/drivers/infiniband/core/uverbs_ioctl.c @@ -243,16 +243,13 @@ static long ib_uverbs_cmd_verbs(struct ib_device *ib_dev, size_t ctx_size; uintptr_t data[UVERBS_OPTIMIZE_USING_STACK_SZ / sizeof(uintptr_t)];

- if (hdr->reserved) - return -EINVAL; - object_spec = uverbs_get_object(ib_dev, hdr->object_id); if (!object_spec) - return -EOPNOTSUPP; + return -EPROTONOSUPPORT;

method_spec = uverbs_get_method(object_spec, hdr->method_id); if (!method_spec) - return -EOPNOTSUPP; + return -EPROTONOSUPPORT;

if ((method_spec->flags & UVERBS_ACTION_FLAG_CREATE_ROOT) ^ !file->ucontext) return -EINVAL; @@ -305,6 +302,16 @@ static long ib_uverbs_cmd_verbs(struct ib_device *ib_dev,

err = uverbs_handle_method(buf, ctx->uattrs, hdr->num_attrs, ib_dev, file, method_spec, ctx->uverbs_attr_bundle); + + /* + * EPROTONOSUPPORT is ONLY to be returned if the ioctl framework can + * not invoke the method because the request is not supported. No + * other cases should return this code. + */ + if (unlikely(err == -EPROTONOSUPPORT)) { + WARN_ON_ONCE(err == -EPROTONOSUPPORT); + err = -EINVAL; + } out: if (ctx != (void *)data) kfree(ctx); @@ -341,7 +348,7 @@ long ib_uverbs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) }

if (hdr.reserved) { - err = -EOPNOTSUPP; + err = -EPROTONOSUPPORT; goto out; }

From: Jake Daryll Obina jake.obina@gmail.com

[ Upstream commit 5bdd0c6f89fba430e18d636493398389dadc3b17 ]

If jffs2_iget() fails for a newly-allocated inode, jffs2_do_clear_inode() can get called twice in the error handling path, the first call in jffs2_iget() itself and the second through iget_failed(). This can result to a use-after-free error in the second jffs2_do_clear_inode() call, such as shown by the oops below wherein the second jffs2_do_clear_inode() call was trying to free node fragments that were already freed in the first jffs2_do_clear_inode() call.

[ 78.178860] jffs2: error: (1904) jffs2_do_read_inode_internal: CRC failed for read_inode of inode 24 at physical location 0x1fc00c [ 78.178914] Unable to handle kernel paging request at virtual address 6b6b6b6b6b6b6b7b [ 78.185871] pgd = ffffffc03a567000 [ 78.188794] [6b6b6b6b6b6b6b7b] *pgd=0000000000000000, *pud=0000000000000000 [ 78.194968] Internal error: Oops: 96000004 [#1] PREEMPT SMP ... [ 78.513147] PC is at rb_first_postorder+0xc/0x28 [ 78.516503] LR is at jffs2_kill_fragtree+0x28/0x90 [jffs2] [ 78.520672] pc : [<ffffff8008323d28>] lr : [<ffffff8000eb1cc8>] pstate: 60000105 [ 78.526757] sp : ffffff800cea38f0 [ 78.528753] x29: ffffff800cea38f0 x28: ffffffc01f3f8e80 [ 78.532754] x27: 0000000000000000 x26: ffffff800cea3c70 [ 78.536756] x25: 00000000dc67c8ae x24: ffffffc033d6945d [ 78.540759] x23: ffffffc036811740 x22: ffffff800891a5b8 [ 78.544760] x21: 0000000000000000 x20: 0000000000000000 [ 78.548762] x19: ffffffc037d48910 x18: ffffff800891a588 [ 78.552764] x17: 0000000000000800 x16: 0000000000000c00 [ 78.556766] x15: 0000000000000010 x14: 6f2065646f6e695f [ 78.560767] x13: 6461657220726f66 x12: 2064656c69616620 [ 78.564769] x11: 435243203a6c616e x10: 7265746e695f6564 [ 78.568771] x9 : 6f6e695f64616572 x8 : ffffffc037974038 [ 78.572774] x7 : bbbbbbbbbbbbbbbb x6 : 0000000000000008 [ 78.576775] x5 : 002f91d85bd44a2f x4 : 0000000000000000 [ 78.580777] x3 : 0000000000000000 x2 : 000000403755e000 [ 78.584779] x1 : 6b6b6b6b6b6b6b6b x0 : 6b6b6b6b6b6b6b6b ... [ 79.038551] [<ffffff8008323d28>] rb_first_postorder+0xc/0x28 [ 79.042962] [<ffffff8000eb5578>] jffs2_do_clear_inode+0x88/0x100 [jffs2] [ 79.048395] [<ffffff8000eb9ddc>] jffs2_evict_inode+0x3c/0x48 [jffs2] [ 79.053443] [<ffffff8008201ca8>] evict+0xb0/0x168 [ 79.056835] [<ffffff8008202650>] iput+0x1c0/0x200 [ 79.060228] [<ffffff800820408c>] iget_failed+0x30/0x3c [ 79.064097] [<ffffff8000eba0c0>] jffs2_iget+0x2d8/0x360 [jffs2] [ 79.068740] [<ffffff8000eb0a60>] jffs2_lookup+0xe8/0x130 [jffs2] [ 79.073434] [<ffffff80081f1a28>] lookup_slow+0x118/0x190 [ 79.077435] [<ffffff80081f4708>] walk_component+0xfc/0x28c [ 79.081610] [<ffffff80081f4dd0>] path_lookupat+0x84/0x108 [ 79.085699] [<ffffff80081f5578>] filename_lookup+0x88/0x100 [ 79.089960] [<ffffff80081f572c>] user_path_at_empty+0x58/0x6c [ 79.094396] [<ffffff80081ebe14>] vfs_statx+0xa4/0x114 [ 79.098138] [<ffffff80081ec44c>] SyS_newfstatat+0x58/0x98 [ 79.102227] [<ffffff800808354c>] __sys_trace_return+0x0/0x4 [ 79.106489] Code: d65f03c0 f9400001 b40000e1 aa0103e0 (f9400821)

The jffs2_do_clear_inode() call in jffs2_iget() is unnecessary since iget_failed() will eventually call jffs2_do_clear_inode() if needed, so just remove it.

Fixes: 5451f79f5f81 ("iget: stop JFFS2 from using iget() and read_inode()") Reviewed-by: Richard Weinberger richard@nod.at Signed-off-by: Jake Daryll Obina jake.obina@gmail.com Signed-off-by: Al Viro viro@zeniv.linux.org.uk Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- fs/jffs2/fs.c | 1 - 1 file changed, 1 deletion(-)

diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index d8c274d39ddb..eab04eca95a3 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -362,7 +362,6 @@ error_io: ret = -EIO; error: mutex_unlock(&f->sem); - jffs2_do_clear_inode(c, f); iget_failed(inode); return ERR_PTR(ret); }

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

[ Upstream commit 02b4016bfe43d2d5ed043be7ffa56cda6a4d1100 ]

When implementing support for IP_USER_FLOW filters, we correctly programmed a filter for both the non fragmented IPv4/Other filter, as well as the fragmented IPv4 filters. However, we did not properly program the input set for fragmented IPv4 PCTYPE. This meant that the filters would almost certainly not match, unless the user specified all of the flow types.

Add support to program the fragmented IPv4 filter input set. Since we always program these filters together, we'll assume that the two input sets must match, and will thus always program the input sets to the same value.

Signed-off-by: Jacob Keller jacob.e.keller@intel.com Tested-by: Andrew Bowers andrewx.bowers@intel.com Signed-off-by: Jeff Kirsher jeffrey.t.kirsher@intel.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 10 ++++++++++ drivers/net/ethernet/intel/i40e/i40e_main.c | 3 +++ 2 files changed, 13 insertions(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 5f6cf7212d4f..28daf7e7ccbe 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -3800,6 +3800,16 @@ static int i40e_check_fdir_input_set(struct i40e_vsi *vsi,

i40e_write_fd_input_set(pf, index, new_mask);

+ /* IP_USER_FLOW filters match both IPv4/Other and IPv4/Fragmented + * frames. If we're programming the input set for IPv4/Other, we also + * need to program the IPv4/Fragmented input set. Since we don't have + * separate support, we'll always assume and enforce that the two flow + * types must have matching input sets. + */ + if (index == I40E_FILTER_PCTYPE_NONF_IPV4_OTHER) + i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_FRAG_IPV4, + new_mask); + /* Add the new offset and update table, if necessary */ if (new_flex_offset) { err = i40e_add_flex_offset(&pf->l4_flex_pit_list, src_offset, diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 973bad818e81..2d9a50c82141 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -7744,6 +7744,9 @@ static void i40e_fdir_filter_exit(struct i40e_pf *pf) /* Reprogram the default input set for Other/IPv4 */ i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_OTHER, I40E_L3_SRC_MASK | I40E_L3_DST_MASK); + + i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_FRAG_IPV4, + I40E_L3_SRC_MASK | I40E_L3_DST_MASK); }

/**

From: Mickaël Salaün mic@digikod.net

[ Upstream commit c25ef6a5e62fa212d298ce24995ce239f29b5f96 ]

Do not build lib/bpf/bpf.o with this Makefile but use the one from the library directory. This avoid making a buggy bpf.o file (e.g. missing symbols).

This patch is useful if some code (e.g. Landlock tests) needs both the bpf.o (from tools/lib/bpf) and the bpf_load.o (from samples/bpf).

Signed-off-by: Mickaël Salaün mic@digikod.net Cc: Alexei Starovoitov ast@kernel.org Cc: Daniel Borkmann daniel@iogearbox.net Signed-off-by: Daniel Borkmann daniel@iogearbox.net Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- samples/bpf/Makefile | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index adeaa1302f34..961b45c5eee0 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -192,13 +192,16 @@ CLANG_ARCH_ARGS = -target $(ARCH) endif

# Trick to allow make to be run from this directory -all: +all: $(LIBBPF) $(MAKE) -C ../../ $(CURDIR)/

clean: $(MAKE) -C ../../ M=$(CURDIR) clean @rm -f *~

+$(LIBBPF): FORCE + $(MAKE) -C $(dir $@) $(notdir $@) + $(obj)/syscall_nrs.s: $(src)/syscall_nrs.c $(call if_changed_dep,cc_s_c)

From: Michael Bringmann mwb@linux.vnet.ibm.com

[ Upstream commit ea05ba7c559c8e5a5946c3a94a2a266e9a6680a6 ]

This patch fixes some problems encountered at runtime with configurations that support memory-less nodes, or that hot-add CPUs into nodes that are memoryless during system execution after boot. The problems of interest include:

* Nodes known to powerpc to be memoryless at boot, but to have CPUs in them are allowed to be 'possible' and 'online'. Memory allocations for those nodes are taken from another node that does have memory until and if memory is hot-added to the node.

* Nodes which have no resources assigned at boot, but which may still be referenced subsequently by affinity or associativity attributes, are kept in the list of 'possible' nodes for powerpc. Hot-add of memory or CPUs to the system can reference these nodes and bring them online instead of redirecting the references to one of the set of nodes known to have memory at boot.

Note that this software operates under the context of CPU hotplug. We are not doing memory hotplug in this code, but rather updating the kernel's CPU topology (i.e. arch_update_cpu_topology / numa_update_cpu_topology). We are initializing a node that may be used by CPUs or memory before it can be referenced as invalid by a CPU hotplug operation. CPU hotplug operations are protected by a range of APIs including cpu_maps_update_begin/cpu_maps_update_done, cpus_read/write_lock / cpus_read/write_unlock, device locks, and more. Memory hotplug operations, including try_online_node, are protected by mem_hotplug_begin/mem_hotplug_done, device locks, and more. In the case of CPUs being hot-added to a previously memoryless node, the try_online_node operation occurs wholly within the CPU locks with no overlap. Using HMC hot-add/hot-remove operations, we have been able to add and remove CPUs to any possible node without failures. HMC operations involve a degree self-serialization, though.

Signed-off-by: Michael Bringmann mwb@linux.vnet.ibm.com Reviewed-by: Nathan Fontenot nfont@linux.vnet.ibm.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- arch/powerpc/mm/numa.c | 47 +++++++++++++++++++++++++++++++++++++---------- 1 file changed, 37 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 87323354b247..c6ec7ea312e8 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -546,7 +546,7 @@ static int numa_setup_cpu(unsigned long lcpu) nid = of_node_to_nid_single(cpu);

out_present: - if (nid < 0 || !node_online(nid)) + if (nid < 0 || !node_possible(nid)) nid = first_online_node;

map_cpu_to_node(lcpu, nid); @@ -905,10 +905,8 @@ static void __init find_possible_nodes(void) goto out;

for (i = 0; i < numnodes; i++) { - if (!node_possible(i)) { - setup_node_data(i, 0, 0); + if (!node_possible(i)) node_set(i, node_possible_map); - } }

out: @@ -1304,6 +1302,40 @@ static long vphn_get_associativity(unsigned long cpu, return rc; }

+static inline int find_and_online_cpu_nid(int cpu) +{ + __be32 associativity[VPHN_ASSOC_BUFSIZE] = {0}; + int new_nid; + + /* Use associativity from first thread for all siblings */ + vphn_get_associativity(cpu, associativity); + new_nid = associativity_to_nid(associativity); + if (new_nid < 0 || !node_possible(new_nid)) + new_nid = first_online_node; + + if (NODE_DATA(new_nid) == NULL) { +#ifdef CONFIG_MEMORY_HOTPLUG + /* + * Need to ensure that NODE_DATA is initialized for a node from + * available memory (see memblock_alloc_try_nid). If unable to + * init the node, then default to nearest node that has memory + * installed. + */ + if (try_online_node(new_nid)) + new_nid = first_online_node; +#else + /* + * Default to using the nearest node that has memory installed. + * Otherwise, it would be necessary to patch the kernel MM code + * to deal with more memoryless-node error conditions. + */ + new_nid = first_online_node; +#endif + } + + return new_nid; +} + /* * Update the CPU maps and sysfs entries for a single CPU when its NUMA * characteristics change. This function doesn't perform any locking and is @@ -1371,7 +1403,6 @@ int numa_update_cpu_topology(bool cpus_locked) { unsigned int cpu, sibling, changed = 0; struct topology_update_data *updates, *ud; - __be32 associativity[VPHN_ASSOC_BUFSIZE] = {0}; cpumask_t updated_cpus; struct device *dev; int weight, new_nid, i = 0; @@ -1409,11 +1440,7 @@ int numa_update_cpu_topology(bool cpus_locked) continue; }

- /* Use associativity from first thread for all siblings */ - vphn_get_associativity(cpu, associativity); - new_nid = associativity_to_nid(associativity); - if (new_nid < 0 || !node_online(new_nid)) - new_nid = first_online_node; + new_nid = find_and_online_cpu_nid(cpu);

if (new_nid == numa_cpu_lookup_table[cpu]) { cpumask_andnot(&cpu_associativity_changes_mask,

From: Logan Gunthorpe logang@deltatee.com

[ Upstream commit cbd27448faff4843ac4b66cc71445a10623ff48d ]

When using the max_mw_size parameter of ntb_transport to limit the size of the Memory windows, communication cannot be established and the queues freeze.

This is because the mw_size that's reported to the peer is correctly limited but the size used locally is not. So the MW is initialized with a buffer smaller than the window but the TX side is using the full window. This means the TX side will be writing to a region of the window that points nowhere.

This is easily fixed by applying the same limit to tx_size in ntb_transport_init_queue().

Fixes: e26a5843f7f5 ("NTB: Split ntb_hw_intel and ntb_transport drivers") Signed-off-by: Logan Gunthorpe logang@deltatee.com Acked-by: Allen Hubbe Allen.Hubbe@dell.com Cc: Dave Jiang dave.jiang@intel.com Signed-off-by: Jon Mason jdmason@kudzu.us Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/ntb/ntb_transport.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index 045e3dd4750e..9878c48826e3 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -1003,6 +1003,9 @@ static int ntb_transport_init_queue(struct ntb_transport_ctx *nt, mw_base = nt->mw_vec[mw_num].phys_addr; mw_size = nt->mw_vec[mw_num].phys_size;

+ if (max_mw_size && mw_size > max_mw_size) + mw_size = max_mw_size; + tx_size = (unsigned int)mw_size / num_qps_mw; qp_offset = tx_size * (qp_num / mw_count);

From: Logan Gunthorpe logang@deltatee.com

[ Upstream commit 1e2fd202f8593985cdadca32e0c322f98e7fe7cb ]

With Switchtec hardware, the buffer used for a memory window must be aligned to its size (the hardware only replaces the lower bits). In certain circumstances dma_alloc_coherent() will not provide a buffer that adheres to this requirement like when using the CMA and CONFIG_CMA_ALIGNMENT is set lower than the buffer size.

When we get an unaligned buffer mw_set_trans() should return an error. We also log an error so we know the cause of the problem.

Signed-off-by: Logan Gunthorpe logang@deltatee.com Signed-off-by: Jon Mason jdmason@kudzu.us Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/ntb/hw/mscc/ntb_hw_switchtec.c | 13 +++++++++++++ 1 file changed, 13 insertions(+)

diff --git a/drivers/ntb/hw/mscc/ntb_hw_switchtec.c b/drivers/ntb/hw/mscc/ntb_hw_switchtec.c index ca0334a6b759..fc9ce0a31c04 100644 --- a/drivers/ntb/hw/mscc/ntb_hw_switchtec.c +++ b/drivers/ntb/hw/mscc/ntb_hw_switchtec.c @@ -315,6 +315,19 @@ static int switchtec_ntb_mw_set_trans(struct ntb_dev *ntb, int pidx, int widx, if (xlate_pos < 12) return -EINVAL;

+ if (!IS_ALIGNED(addr, BIT_ULL(xlate_pos))) { + /* + * In certain circumstances we can get a buffer that is + * not aligned to its size. (Most of the time + * dma_alloc_coherent ensures this). This can happen when + * using large buffers allocated by the CMA + * (see CMA_CONFIG_ALIGNMENT) + */ + dev_err(&sndev->stdev->dev, + "ERROR: Memory window address is not aligned to it's size!\n"); + return -EINVAL; + } + rc = switchtec_ntb_part_op(sndev, ctl, NTB_CTRL_PART_OP_LOCK, NTB_CTRL_PART_STATUS_LOCKED); if (rc)

From: Thomas Falcon tlfalcon@linux.vnet.ibm.com

[ Upstream commit f813614f531114db796ad66ced75c5dc8db7aa3a ]

Wait for a response from the VNIC server before exiting after setting the MAC address. The resolves an issue with bonding a VNIC client in ALB or TLB modes. The bonding driver was changing the MAC address more rapidly than the device could respond, causing the following errors.

"bond0: the hw address of slave eth2 is in use by the bond; couldn't find a slave with a free hw address to give it (this should not have happened)"

If the function waits until the change is finalized, these errors are avoided.

Signed-off-by: Thomas Falcon tlfalcon@linux.vnet.ibm.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/net/ethernet/ibm/ibmvnic.c | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index b65f5f3ac034..d4e87333bac2 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1543,15 +1543,19 @@ static int __ibmvnic_set_mac(struct net_device *netdev, struct sockaddr *p) crq.change_mac_addr.first = IBMVNIC_CRQ_CMD; crq.change_mac_addr.cmd = CHANGE_MAC_ADDR; ether_addr_copy(&crq.change_mac_addr.mac_addr[0], addr->sa_data); + + init_completion(&adapter->fw_done); ibmvnic_send_crq(adapter, &crq); + wait_for_completion(&adapter->fw_done); /* netdev->dev_addr is changed in handle_change_mac_rsp function */ - return 0; + return adapter->fw_done_rc ? -EIO : 0; }

static int ibmvnic_set_mac(struct net_device *netdev, void *p) { struct ibmvnic_adapter *adapter = netdev_priv(netdev); struct sockaddr *addr = p; + int rc;

if (adapter->state == VNIC_PROBED) { memcpy(&adapter->desired.mac, addr, sizeof(struct sockaddr)); @@ -1559,9 +1563,9 @@ static int ibmvnic_set_mac(struct net_device *netdev, void *p) return 0; }

- __ibmvnic_set_mac(netdev, addr); + rc = __ibmvnic_set_mac(netdev, addr);

- return 0; + return rc; }

/** @@ -3558,8 +3562,8 @@ static void handle_error_indication(union ibmvnic_crq *crq, ibmvnic_reset(adapter, VNIC_RESET_NON_FATAL); }

-static void handle_change_mac_rsp(union ibmvnic_crq *crq, - struct ibmvnic_adapter *adapter) +static int handle_change_mac_rsp(union ibmvnic_crq *crq, + struct ibmvnic_adapter *adapter) { struct net_device *netdev = adapter->netdev; struct device *dev = &adapter->vdev->dev; @@ -3568,10 +3572,13 @@ static void handle_change_mac_rsp(union ibmvnic_crq *crq, rc = crq->change_mac_addr_rsp.rc.code; if (rc) { dev_err(dev, "Error %ld in CHANGE_MAC_ADDR_RSP\n", rc); - return; + goto out; } memcpy(netdev->dev_addr, &crq->change_mac_addr_rsp.mac_addr[0], ETH_ALEN); +out: + complete(&adapter->fw_done); + return rc; }

static void handle_request_cap_rsp(union ibmvnic_crq *crq, @@ -4031,7 +4038,7 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq, break; case CHANGE_MAC_ADDR_RSP: netdev_dbg(netdev, "Got MAC address change Response\n"); - handle_change_mac_rsp(crq, adapter); + adapter->fw_done_rc = handle_change_mac_rsp(crq, adapter); break; case ERROR_INDICATION: netdev_dbg(netdev, "Got Error Indication\n");

From: Dmitry Vyukov dvyukov@google.com

[ Upstream commit 1e98ffea5a8935ec040ab72299e349cb44b8defd ]

Several netfilter matches and targets put kernel pointers into info objects, but don't set usersize in descriptors. This leads to kernel pointer leaks if a match/target is set and then read back to userspace.

Properly set usersize for these matches/targets.

Found with manual code inspection.

Fixes: ec2318904965 ("xtables: extend matches and targets with .usersize") Signed-off-by: Dmitry Vyukov dvyukov@google.com Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- net/netfilter/xt_IDLETIMER.c | 1 + net/netfilter/xt_LED.c | 1 + net/netfilter/xt_limit.c | 3 +-- net/netfilter/xt_nfacct.c | 1 + net/netfilter/xt_statistic.c | 1 + 5 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index 18b7412ab99a..1ac6600bfafd 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -255,6 +255,7 @@ static struct xt_target idletimer_tg __read_mostly = { .family = NFPROTO_UNSPEC, .target = idletimer_tg_target, .targetsize = sizeof(struct idletimer_tg_info), + .usersize = offsetof(struct idletimer_tg_info, timer), .checkentry = idletimer_tg_checkentry, .destroy = idletimer_tg_destroy, .me = THIS_MODULE, diff --git a/net/netfilter/xt_LED.c b/net/netfilter/xt_LED.c index 18d3af5e1098..0fb2133165aa 100644 --- a/net/netfilter/xt_LED.c +++ b/net/netfilter/xt_LED.c @@ -198,6 +198,7 @@ static struct xt_target led_tg_reg __read_mostly = { .family = NFPROTO_UNSPEC, .target = led_tg, .targetsize = sizeof(struct xt_led_info), + .usersize = offsetof(struct xt_led_info, internal_data), .checkentry = led_tg_check, .destroy = led_tg_destroy, .me = THIS_MODULE, diff --git a/net/netfilter/xt_limit.c b/net/netfilter/xt_limit.c index d27b5f1ea619..61403b77361c 100644 --- a/net/netfilter/xt_limit.c +++ b/net/netfilter/xt_limit.c @@ -193,9 +193,8 @@ static struct xt_match limit_mt_reg __read_mostly = { .compatsize = sizeof(struct compat_xt_rateinfo), .compat_from_user = limit_mt_compat_from_user, .compat_to_user = limit_mt_compat_to_user, -#else - .usersize = offsetof(struct xt_rateinfo, prev), #endif + .usersize = offsetof(struct xt_rateinfo, prev), .me = THIS_MODULE, };

diff --git a/net/netfilter/xt_nfacct.c b/net/netfilter/xt_nfacct.c index cc0518fe598e..6f92d25590a8 100644 --- a/net/netfilter/xt_nfacct.c +++ b/net/netfilter/xt_nfacct.c @@ -62,6 +62,7 @@ static struct xt_match nfacct_mt_reg __read_mostly = { .match = nfacct_mt, .destroy = nfacct_mt_destroy, .matchsize = sizeof(struct xt_nfacct_match_info), + .usersize = offsetof(struct xt_nfacct_match_info, nfacct), .me = THIS_MODULE, };

diff --git a/net/netfilter/xt_statistic.c b/net/netfilter/xt_statistic.c index 11de55e7a868..8710fdba2ae2 100644 --- a/net/netfilter/xt_statistic.c +++ b/net/netfilter/xt_statistic.c @@ -84,6 +84,7 @@ static struct xt_match xt_statistic_mt_reg __read_mostly = { .checkentry = statistic_mt_check, .destroy = statistic_mt_destroy, .matchsize = sizeof(struct xt_statistic_info), + .usersize = offsetof(struct xt_statistic_info, master), .me = THIS_MODULE, };

From: "Gustavo A. R. Silva" gustavo@embeddedor.com

[ Upstream commit e4823fbd229bfbba368b40cdadb8f4eeb20604cc ]

Add suffix ULL to constant 80000 in order to avoid a potential integer overflow and give the compiler complete information about the proper arithmetic to use. Notice that this constant is used in a context that expects an expression of type u64.

The current cast to u64 effectively applies to the whole expression as an argument of type u64 to be passed to div64_u64, but it does not prevent it from being evaluated using 32-bit arithmetic instead of 64-bit arithmetic.

Also, once the expression is properly evaluated using 64-bit arithmentic, there is no need for the parentheses and the external cast to u64.

Addresses-Coverity-ID: 1357588 ("Unintentional integer overflow") Signed-off-by: Gustavo A. R. Silva gustavo@embeddedor.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- net/ipv4/tcp_nv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_nv.c b/net/ipv4/tcp_nv.c index 0b5a05bd82e3..d18f4672beae 100644 --- a/net/ipv4/tcp_nv.c +++ b/net/ipv4/tcp_nv.c @@ -364,7 +364,7 @@ static void tcpnv_acked(struct sock *sk, const struct ack_sample *sample) */ cwnd_by_slope = (u32) div64_u64(((u64)ca->nv_rtt_max_rate) * ca->nv_min_rtt, - (u64)(80000 * tp->mss_cache)); + 80000ULL * tp->mss_cache); max_win = cwnd_by_slope + nv_pad;

/* If cwnd > max_win, decrease cwnd

From: Jan H. Schönherr jschoenh@amazon.de

[ Upstream commit ee190ca6516bc8257e3d36187ca6f0f71a9ec477 ]

follow_pte_pmd() can theoretically return after having acquired a PMD lock, even when DAX was not compiled with CONFIG_FS_DAX_PMD.

Release the PMD lock unconditionally.

Link: http://lkml.kernel.org/r/20180118133839.20587-1-jschoenh@amazon.de Fixes: f729c8c9b24f ("dax: wrprotect pmd_t in dax_mapping_entry_mkclean") Signed-off-by: Jan H. Schönherr jschoenh@amazon.de Reviewed-by: Ross Zwisler ross.zwisler@linux.intel.com Reviewed-by: Andrew Morton akpm@linux-foundation.org Cc: Matthew Wilcox mawilcox@microsoft.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- fs/dax.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/dax.c b/fs/dax.c index 95981591977a..c2ebf10b70da 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -636,8 +636,8 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping, pmd = pmd_mkclean(pmd); set_pmd_at(vma->vm_mm, address, pmdp, pmd); unlock_pmd: - spin_unlock(ptl); #endif + spin_unlock(ptl); } else { if (pfn != pte_pfn(*ptep)) goto unlock_pte;

From: piaojun piaojun@huawei.com

[ Upstream commit 025bcbde3634b2c9b316f227fed13ad6ad6817fb ]

If metadata is corrupted such as 'invalid inode block', we will get failed by calling 'mount()' and then set filesystem readonly as below:

ocfs2_mount ocfs2_initialize_super ocfs2_init_global_system_inodes ocfs2_iget ocfs2_read_locked_inode ocfs2_validate_inode_block ocfs2_error ocfs2_handle_error ocfs2_set_ro_flag(osb, 0); // set readonly

In this situation we need return -EROFS to 'mount.ocfs2', so that user can fix it by fsck. And then mount again. In addition, 'mount.ocfs2' should be updated correspondingly as it only return 1 for all errno. And I will post a patch for 'mount.ocfs2' too.

Link: http://lkml.kernel.org/r/5A4302FA.2010606@huawei.com Signed-off-by: Jun Piao piaojun@huawei.com Reviewed-by: Alex Chen alex.chen@huawei.com Reviewed-by: Joseph Qi jiangqi903@gmail.com Reviewed-by: Changwei Ge ge.changwei@h3c.com Reviewed-by: Gang He ghe@suse.com Cc: Mark Fasheh mfasheh@versity.com Cc: Joel Becker jlbec@evilplan.org Cc: Junxiao Bi junxiao.bi@oracle.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- fs/ocfs2/super.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 80efa5699fb0..63b3fa519758 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -474,9 +474,8 @@ static int ocfs2_init_global_system_inodes(struct ocfs2_super *osb) new = ocfs2_get_system_file_inode(osb, i, osb->slot_num); if (!new) { ocfs2_release_system_inodes(osb); - status = -EINVAL; + status = ocfs2_is_soft_readonly(osb) ? -EROFS : -EINVAL; mlog_errno(status); - /* FIXME: Should ERROR_RO_FS */ mlog(ML_ERROR, "Unable to load system inode %d, " "possibly corrupt fs?", i); goto bail; @@ -505,7 +504,7 @@ static int ocfs2_init_local_system_inodes(struct ocfs2_super *osb) new = ocfs2_get_system_file_inode(osb, i, osb->slot_num); if (!new) { ocfs2_release_system_inodes(osb); - status = -EINVAL; + status = ocfs2_is_soft_readonly(osb) ? -EROFS : -EINVAL; mlog(ML_ERROR, "status=%d, sysfile=%d, slot=%d\n", status, i, osb->slot_num); goto bail;

From: piaojun piaojun@huawei.com

[ Upstream commit d984187e3a1ad7d12447a7ab2c43ce3717a2b5b3 ]

We should not reuse the dirty bh in jbd2 directly due to the following situation:

1. When removing extent rec, we will dirty the bhs of extent rec and truncate log at the same time, and hand them over to jbd2.

2. The bhs are submitted to jbd2 area successfully.

3. The write-back thread of device help flush the bhs to disk but encounter write error due to abnormal storage link.

4. After a while the storage link become normal. Truncate log flush worker triggered by the next space reclaiming found the dirty bh of truncate log and clear its 'BH_Write_EIO' and then set it uptodate in __ocfs2_journal_access():

ocfs2_truncate_log_worker ocfs2_flush_truncate_log __ocfs2_flush_truncate_log ocfs2_replay_truncate_records ocfs2_journal_access_di __ocfs2_journal_access // here we clear io_error and set 'tl_bh' uptodata.

5. Then jbd2 will flush the bh of truncate log to disk, but the bh of extent rec is still in error state, and unfortunately nobody will take care of it.

6. At last the space of extent rec was not reduced, but truncate log flush worker have given it back to globalalloc. That will cause duplicate cluster problem which could be identified by fsck.ocfs2.

Sadly we can hardly revert this but set fs read-only in case of ruining atomicity and consistency of space reclaim.

Link: http://lkml.kernel.org/r/5A6E8092.8090701@huawei.com Fixes: acf8fdbe6afb ("ocfs2: do not BUG if buffer not uptodate in __ocfs2_journal_access") Signed-off-by: Jun Piao piaojun@huawei.com Reviewed-by: Yiwen Jiang jiangyiwen@huawei.com Reviewed-by: Changwei Ge ge.changwei@h3c.com Cc: Mark Fasheh mfasheh@versity.com Cc: Joel Becker jlbec@evilplan.org Cc: Junxiao Bi junxiao.bi@oracle.com Cc: Joseph Qi jiangqi903@gmail.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- fs/ocfs2/journal.c | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 36304434eacf..e5dcea6cee5f 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -666,23 +666,24 @@ static int __ocfs2_journal_access(handle_t *handle, /* we can safely remove this assertion after testing. */ if (!buffer_uptodate(bh)) { mlog(ML_ERROR, "giving me a buffer that's not uptodate!\n"); - mlog(ML_ERROR, "b_blocknr=%llu\n", - (unsigned long long)bh->b_blocknr); + mlog(ML_ERROR, "b_blocknr=%llu, b_state=0x%lx\n", + (unsigned long long)bh->b_blocknr, bh->b_state);

lock_buffer(bh); /* - * A previous attempt to write this buffer head failed. - * Nothing we can do but to retry the write and hope for - * the best. + * A previous transaction with a couple of buffer heads fail + * to checkpoint, so all the bhs are marked as BH_Write_EIO. + * For current transaction, the bh is just among those error + * bhs which previous transaction handle. We can't just clear + * its BH_Write_EIO and reuse directly, since other bhs are + * not written to disk yet and that will cause metadata + * inconsistency. So we should set fs read-only to avoid + * further damage. */ if (buffer_write_io_error(bh) && !buffer_uptodate(bh)) { - clear_buffer_write_io_error(bh); - set_buffer_uptodate(bh); - } - - if (!buffer_uptodate(bh)) { unlock_buffer(bh); - return -EIO; + return ocfs2_error(osb->sb, "A previous attempt to " + "write this buffer head failed\n"); } unlock_buffer(bh); }

From: Yisheng Xie xieyisheng1@huawei.com

[ Upstream commit 0486a38bcc4749808edbc848f1bcf232042770fc ]

As in manpage of migrate_pages, the errno should be set to EINVAL when none of the node IDs specified by new_nodes are on-line and allowed by the process's current cpuset context, or none of the specified nodes contain memory. However, when test by following case:

new_nodes = 0; old_nodes = 0xf; ret = migrate_pages(pid, old_nodes, new_nodes, MAX);

The ret will be 0 and no errno is set. As the new_nodes is empty, we should expect EINVAL as documented.

To fix the case like above, this patch check whether target nodes AND current task_nodes is empty, and then check whether AND node_states[N_MEMORY] is empty.

Link: http://lkml.kernel.org/r/1510882624-44342-4-git-send-email-xieyisheng1@huawe... Signed-off-by: Yisheng Xie xieyisheng1@huawei.com Acked-by: Vlastimil Babka vbabka@suse.cz Cc: Andi Kleen ak@linux.intel.com Cc: Chris Salls salls@cs.ucsb.edu Cc: Christopher Lameter cl@linux.com Cc: David Rientjes rientjes@google.com Cc: Ingo Molnar mingo@kernel.org Cc: Naoya Horiguchi n-horiguchi@ah.jp.nec.com Cc: Tan Xiaojun tanxiaojun@huawei.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- mm/mempolicy.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/mm/mempolicy.c b/mm/mempolicy.c index c9b807eca74c..277b6454954e 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1435,10 +1435,14 @@ SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode, goto out_put; }

- if (!nodes_subset(*new, node_states[N_MEMORY])) { - err = -EINVAL; + task_nodes = cpuset_mems_allowed(current); + nodes_and(*new, *new, task_nodes); + if (nodes_empty(*new)) + goto out_put; + + nodes_and(*new, *new, node_states[N_MEMORY]); + if (nodes_empty(*new)) goto out_put; - }

err = security_task_movememory(task); if (err)

From: Nitin Gupta nitin.m.gupta@oracle.com

[ Upstream commit a8e654f01cb725d0bfd741ebca1bf4c9337969cc ]

It's required to avoid losing dirty and accessed bits.

[akpm@linux-foundation.org: add a `do' to the do-while loop] Link: http://lkml.kernel.org/r/20171213105756.69879-9-kirill.shutemov@linux.intel.... Signed-off-by: Nitin Gupta nitin.m.gupta@oracle.com Signed-off-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Cc: David Miller davem@davemloft.net Cc: Vlastimil Babka vbabka@suse.cz Cc: Andrea Arcangeli aarcange@redhat.com Cc: Michal Hocko mhocko@kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- arch/sparc/include/asm/pgtable_64.h | 2 +- arch/sparc/mm/tlb.c | 23 ++++++++++++++++++----- 2 files changed, 19 insertions(+), 6 deletions(-)

diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 9937c5ff94a9..339920fdf9ed 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -1010,7 +1010,7 @@ void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd);

#define __HAVE_ARCH_PMDP_INVALIDATE -extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, +extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp);

#define __HAVE_ARCH_PGTABLE_DEPOSIT diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c index 4ae86bc0d35c..847ddffbf38a 100644 --- a/arch/sparc/mm/tlb.c +++ b/arch/sparc/mm/tlb.c @@ -219,17 +219,28 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, } }

+static inline pmd_t pmdp_establish(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, pmd_t pmd) +{ + pmd_t old; + + do { + old = *pmdp; + } while (cmpxchg64(&pmdp->pmd, old.pmd, pmd.pmd) != old.pmd); + + return old; +} + /* * This routine is only called when splitting a THP */ -void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, +pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { - pmd_t entry = *pmdp; - - pmd_val(entry) &= ~_PAGE_VALID; + pmd_t old, entry;

- set_pmd_at(vma->vm_mm, address, pmdp, entry); + entry = __pmd(pmd_val(*pmdp) & ~_PAGE_VALID); + old = pmdp_establish(vma, address, pmdp, entry); flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);

/* @@ -240,6 +251,8 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, if ((pmd_val(entry) & _PAGE_PMD_HUGE) && !is_huge_zero_page(pmd_page(entry))) (vma->vm_mm)->context.thp_pte_count--; + + return old; }

void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,

From: Mel Gorman mgorman@techsingularity.net

[ Upstream commit 69d763fc6d3aee787a3e8c8c35092b4f4960fa5d ]

Minchan Kim asked the following question -- what locks protects address_space destroying when race happens between inode trauncation and __isolate_lru_page? Jan Kara clarified by describing the race as follows

CPU1 CPU2

truncate(inode) __isolate_lru_page() ... truncate_inode_page(mapping, page); delete_from_page_cache(page) spin_lock_irqsave(&mapping->tree_lock, flags); __delete_from_page_cache(page, NULL) page_cache_tree_delete(..) ... mapping = page_mapping(page); page->mapping = NULL; ... spin_unlock_irqrestore(&mapping->tree_lock, flags); page_cache_free_page(mapping, page) put_page(page) if (put_page_testzero(page)) -> false - inode now has no pages and can be freed including embedded address_space

if (mapping && !mapping->a_ops->migratepage) - we've dereferenced mapping which is potentially already free.

The race is theoretically possible but unlikely. Before the delete_from_page_cache, truncate_cleanup_page is called so the page is likely to be !PageDirty or PageWriteback which gets skipped by the only caller that checks the mappping in __isolate_lru_page. Even if the race occurs, a substantial amount of work has to happen during a tiny window with no preemption but it could potentially be done using a virtual machine to artifically slow one CPU or halt it during the critical window.

This patch should eliminate the race with truncation by try-locking the page before derefencing mapping and aborting if the lock was not acquired. There was a suggestion from Huang Ying to use RCU as a side-effect to prevent mapping being freed. However, I do not like the solution as it's an unconventional means of preserving a mapping and it's not a context where rcu_read_lock is obviously protecting rcu data.

Link: http://lkml.kernel.org/r/20180104102512.2qos3h5vqzeisrek@techsingularity.net Fixes: c82449352854 ("mm: compaction: make isolate_lru_page() filter-aware again") Signed-off-by: Mel Gorman mgorman@techsingularity.net Acked-by: Minchan Kim minchan@kernel.org Cc: "Huang, Ying" ying.huang@intel.com Cc: Jan Kara jack@suse.cz Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- mm/vmscan.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c index 503fa224c6b6..ff9066d096c1 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1436,14 +1436,24 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode)

if (PageDirty(page)) { struct address_space *mapping; + bool migrate_dirty;

/* * Only pages without mappings or that have a * ->migratepage callback are possible to migrate - * without blocking + * without blocking. However, we can be racing with + * truncation so it's necessary to lock the page + * to stabilise the mapping as truncation holds + * the page lock until after the page is removed + * from the page cache. */ + if (!trylock_page(page)) + return ret; + mapping = page_mapping(page); - if (mapping && !mapping->a_ops->migratepage) + migrate_dirty = mapping && mapping->a_ops->migratepage; + unlock_page(page); + if (!migrate_dirty) return ret; } }

From: Desnes Augusto Nunes do Rosario desnesn@linux.vnet.ibm.com

[ Upstream commit a107311d7fdf6b826f3737c4a90fd0e0046e7a3a ]

Older versions of VIOS servers do not send the firmware level in the VPD buffer for the ibmvnic driver. Thus, not only the current message is mis- leading but the firmware version in the ethtool will be NULL. Therefore, this patch fixes the firmware string and its warning.

Fixes: 4e6759be28e4 ("ibmvnic: Feature implementation of VPD for the ibmvnic driver") Signed-off-by: Desnes A. Nunes do Rosario desnesn@linux.vnet.ibm.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/net/ethernet/ibm/ibmvnic.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index d4e87333bac2..4ba49a98c689 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -3294,7 +3294,11 @@ static void handle_vpd_rsp(union ibmvnic_crq *crq, */ substr = strnstr(adapter->vpd->buff, "RM", adapter->vpd->len); if (!substr) { - dev_info(dev, "No FW level provided by VPD\n"); + dev_info(dev, "Warning - No FW level has been provided in the VPD buffer by the VIOS Server\n"); + ptr = strncpy((char *)adapter->fw_version, "N/A", + 3 * sizeof(char)); + if (!ptr) + dev_err(dev, "Failed to inform that firmware version is unavailable to the adapter\n"); goto complete; }

From: "Michael J. Ruhl" michael.j.ruhl@intel.com

[ Upstream commit 82a979265638c505e12fbe7ba40980dc0901436d ]

The pci_request_irq() interfaces always adds the IRQF_SHARED bit to all IRQ requests.

When the kernel is built with CONFIG_DEBUG_SHIRQ config flag, if the IRQF_SHARED bit is set, a call to the IRQ handler is made from the __free_irq() function. This is testing a race condition between the IRQ cleanup and an IRQ racing the cleanup. The HFI driver should be able to handle this race, but does not.

This race can cause traces that start with this footprint:

BUG: unable to handle kernel NULL pointer dereference at (null) Call Trace: <hfi1 irq handler> ... __free_irq+0x1b3/0x2d0 free_irq+0x35/0x70 pci_free_irq+0x1c/0x30 clean_up_interrupts+0x53/0xf0 [hfi1] hfi1_start_cleanup+0x122/0x190 [hfi1] postinit_cleanup+0x1d/0x280 [hfi1] remove_one+0x233/0x250 [hfi1] pci_device_remove+0x39/0xc0

Export IRQ cleanup function so it can be called from other modules.

Using the exported cleanup function:

Re-order the driver cleanup code to clean up IRQ resources before other resources, eliminating the race.

Re-order error path for init so that the race does not occur.

Reduce severity on spurious error message for SDMA IRQs to info.

Reviewed-by: Alex Estrin alex.estrin@intel.com Reviewed-by: Patel Jay P jay.p.patel@intel.com Reviewed-by: Mike Marciniszyn mike.marciniszyn@intel.com Signed-off-by: Michael J. Ruhl michael.j.ruhl@intel.com Signed-off-by: Dennis Dalessandro dennis.dalessandro@intel.com Signed-off-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/infiniband/hw/hfi1/chip.c | 18 ++++++++++++------ drivers/infiniband/hw/hfi1/hfi.h | 1 + drivers/infiniband/hw/hfi1/init.c | 4 +++- 3 files changed, 16 insertions(+), 7 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 4f057e8ffe50..a7a5d19b1fe4 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -8263,8 +8263,8 @@ static irqreturn_t sdma_interrupt(int irq, void *data) /* handle the interrupt(s) */ sdma_engine_interrupt(sde, status); } else { - dd_dev_err_ratelimited(dd, "SDMA engine %u interrupt, but no status bits set\n", - sde->this_idx); + dd_dev_info_ratelimited(dd, "SDMA engine %u interrupt, but no status bits set\n", + sde->this_idx); } return IRQ_HANDLED; } @@ -12984,7 +12984,14 @@ static void disable_intx(struct pci_dev *pdev) pci_intx(pdev, 0); }

-static void clean_up_interrupts(struct hfi1_devdata *dd) +/** + * hfi1_clean_up_interrupts() - Free all IRQ resources + * @dd: valid device data data structure + * + * Free the MSI or INTx IRQs and assoicated PCI resources, + * if they have been allocated. + */ +void hfi1_clean_up_interrupts(struct hfi1_devdata *dd) { int i;

@@ -13345,7 +13352,7 @@ static int set_up_interrupts(struct hfi1_devdata *dd) return 0;

fail: - clean_up_interrupts(dd); + hfi1_clean_up_interrupts(dd); return ret; }

@@ -14772,7 +14779,6 @@ void hfi1_start_cleanup(struct hfi1_devdata *dd) aspm_exit(dd); free_cntrs(dd); free_rcverr(dd); - clean_up_interrupts(dd); finish_chip_resources(dd); }

@@ -15229,7 +15235,7 @@ bail_free_rcverr: bail_free_cntrs: free_cntrs(dd); bail_clear_intr: - clean_up_interrupts(dd); + hfi1_clean_up_interrupts(dd); bail_cleanup: hfi1_pcie_ddcleanup(dd); bail_free: diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h index 8ce9118d4a7f..3c3f71d7919d 100644 --- a/drivers/infiniband/hw/hfi1/hfi.h +++ b/drivers/infiniband/hw/hfi1/hfi.h @@ -1957,6 +1957,7 @@ void hfi1_verbs_unregister_sysfs(struct hfi1_devdata *dd); int qsfp_dump(struct hfi1_pportdata *ppd, char *buf, int len);

int hfi1_pcie_init(struct pci_dev *pdev, const struct pci_device_id *ent); +void hfi1_clean_up_interrupts(struct hfi1_devdata *dd); void hfi1_pcie_cleanup(struct pci_dev *pdev); int hfi1_pcie_ddinit(struct hfi1_devdata *dd, struct pci_dev *pdev); void hfi1_pcie_ddcleanup(struct hfi1_devdata *); diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c index 8e3b3e7d829a..117a74f22670 100644 --- a/drivers/infiniband/hw/hfi1/init.c +++ b/drivers/infiniband/hw/hfi1/init.c @@ -1058,8 +1058,9 @@ static void shutdown_device(struct hfi1_devdata *dd) } dd->flags &= ~HFI1_INITTED;

- /* mask interrupts, but not errors */ + /* mask and clean up interrupts, but not errors */ set_intr_state(dd, 0); + hfi1_clean_up_interrupts(dd);

for (pidx = 0; pidx < dd->num_pports; ++pidx) { ppd = dd->pport + pidx; @@ -1702,6 +1703,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) dd_dev_err(dd, "Failed to create /dev devices: %d\n", -j);

if (initfail || ret) { + hfi1_clean_up_interrupts(dd); stop_timers(dd); flush_workqueue(ib_wq); for (pidx = 0; pidx < dd->num_pports; ++pidx) {

From: Alex Estrin alex.estrin@intel.com

[ Upstream commit 2b1e7fe16124e86ee9242aeeee859c79a843e3a2 ]

The dd refcount is speculatively incremented prior to allocating the fd memory with kzalloc(). If that kzalloc() failed the dd refcount leaks. Increment refcount on kzalloc success.

Fixes: e11ffbd57520 ("IB/hfi1: Do not free hfi1 cdev parent structure early") Reviewed-by: Michael J Ruhl michael.j.ruhl@intel.com Signed-off-by: Alex Estrin alex.estrin@intel.com Signed-off-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/infiniband/hw/hfi1/file_ops.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index 1df7da47f431..acf0ba56c309 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -196,9 +196,6 @@ static int hfi1_file_open(struct inode *inode, struct file *fp) if (!atomic_inc_not_zero(&dd->user_refcount)) return -ENXIO;

- /* Just take a ref now. Not all opens result in a context assign */ - kobject_get(&dd->kobj); - /* The real work is performed later in assign_ctxt() */

fd = kzalloc(sizeof(*fd), GFP_KERNEL); @@ -208,6 +205,7 @@ static int hfi1_file_open(struct inode *inode, struct file *fp) fd->mm = current->mm; mmgrab(fd->mm); fd->dd = dd; + kobject_get(&fd->dd->kobj); fp->private_data = fd; } else { fp->private_data = NULL;

From: Alex Estrin alex.estrin@intel.com

[ Upstream commit 1029361084d18cc270f64dfd39529fafa10cfe01 ]

On reboot SM can program port pkey table before ipoib registered its event handler, which could result in missing pkey event and leave root interface with initial pkey value from index 0.

Since OPA port starts with invalid pkey in index 0, root interface will fail to initialize and stay down with no-carrier flag.

For IB ipoib interface may end up with pkey different from value opensm put in pkey table idx 0, resulting in connectivity issues (different mcast groups, for example).

Close the window by calling event handler after registration to make sure ipoib pkey is in sync with port pkey table.

Reviewed-by: Mike Marciniszyn mike.marciniszyn@intel.com Reviewed-by: Ira Weiny ira.weiny@intel.com Signed-off-by: Alex Estrin alex.estrin@intel.com Signed-off-by: Dennis Dalessandro dennis.dalessandro@intel.com Signed-off-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/infiniband/ulp/ipoib/ipoib_main.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 160c5d9bca4c..4e75848f7a35 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -2287,6 +2287,9 @@ static struct net_device *ipoib_add_port(const char *format, priv->ca, ipoib_event); ib_register_event_handler(&priv->event_handler);

+ /* call event handler to ensure pkey in sync */ + queue_work(ipoib_workqueue, &priv->flush_heavy); + result = register_netdev(priv->dev); if (result) { printk(KERN_WARNING "%s: couldn't register ipoib port %d; error %d\n",

From: Karol Herbst kherbst@redhat.com

[ Upstream commit fe9748b7b41cee11f8db57fb8b20bc540a33102a ]

Fixes failure to compile with recent envyas as a result of the 'movw' alias being removed for v5.

A bit of history:

v3 only has a 16-bit sign-extended immediate mov op. In order to set the high bits, there's a separate 'sethi' op. envyas validates that the value passed to mov(imm) is between -0x8000 and 0x7fff. In order to simplify macros that load both the low and high word, a 'movw' alias was added which takes an unsigned 16-bit immediate. However the actual hardware op still sign extends.

v5 has a full 32-bit immediate mov op. The v3 16-bit immediate mov op is gone (loads 0 into the dst reg). However due to a bug in envyas, the movw alias still existed, and selected the no-longer-present v3 16-bit immediate mov op. As a result usage of movw on v5 is the same as mov with a 0x0 argument.

The proper fix throughout is to only ever use the 'movw' alias in combination with 'sethi'. Anything else should get the sign-extended validation to ensure that the intended value ends up in the destination register.

Changes in fuc3 binaries is the result of a different encoding being selected for a mov with an 8-bit value.

v2: added commit message written by Ilia, thanks for that! v3: messed up rebasing, now it should apply

Signed-off-by: Karol Herbst kherbst@redhat.com Signed-off-by: Ben Skeggs bskeggs@redhat.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- .../drm/nouveau/nvkm/subdev/pmu/fuc/gf100.fuc3.h | 746 +++++++-------- .../drm/nouveau/nvkm/subdev/pmu/fuc/gk208.fuc5.h | 802 ++++++++-------- .../drm/nouveau/nvkm/subdev/pmu/fuc/gt215.fuc3.h | 1006 ++++++++++---------- .../gpu/drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc | 30 +- 4 files changed, 1292 insertions(+), 1292 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gf100.fuc3.h b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gf100.fuc3.h index 53d01fb00a8b..1dbe593e5960 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gf100.fuc3.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gf100.fuc3.h @@ -47,8 +47,8 @@ static uint32_t gf100_pmu_data[] = { 0x00000000, 0x00000000, 0x584d454d, - 0x00000756, - 0x00000748, + 0x00000754, + 0x00000746, 0x00000000, 0x00000000, 0x00000000, @@ -69,8 +69,8 @@ static uint32_t gf100_pmu_data[] = { 0x00000000, 0x00000000, 0x46524550, - 0x0000075a, 0x00000758, + 0x00000756, 0x00000000, 0x00000000, 0x00000000, @@ -91,8 +91,8 @@ static uint32_t gf100_pmu_data[] = { 0x00000000, 0x00000000, 0x5f433249, - 0x00000b8a, - 0x00000a2d, + 0x00000b88, + 0x00000a2b, 0x00000000, 0x00000000, 0x00000000, @@ -113,8 +113,8 @@ static uint32_t gf100_pmu_data[] = { 0x00000000, 0x00000000, 0x54534554, - 0x00000bb3, - 0x00000b8c, + 0x00000bb1, + 0x00000b8a, 0x00000000, 0x00000000, 0x00000000, @@ -135,8 +135,8 @@ static uint32_t gf100_pmu_data[] = { 0x00000000, 0x00000000, 0x454c4449, - 0x00000bbf, 0x00000bbd, + 0x00000bbb, 0x00000000, 0x00000000, 0x00000000, @@ -237,19 +237,19 @@ static uint32_t gf100_pmu_data[] = { 0x000005d3, 0x00000003, 0x00000002, - 0x0000069d, + 0x0000069b, 0x00040004, 0x00000000, - 0x000006b9, + 0x000006b7, 0x00010005, 0x00000000, - 0x000006d6, + 0x000006d4, 0x00010006, 0x00000000, 0x0000065b, 0x00000007, 0x00000000, - 0x000006e1, + 0x000006df, /* 0x03c4: memx_func_tail */ /* 0x03c4: memx_ts_start */ 0x00000000, @@ -1373,432 +1373,432 @@ static uint32_t gf100_pmu_code[] = { /* 0x065b: memx_func_wait_vblank */ 0x9800f840, 0x66b00016, - 0x130bf400, + 0x120bf400, 0xf40166b0, 0x0ef4060b, /* 0x066d: memx_func_wait_vblank_head1 */ - 0x2077f12e, - 0x070ef400, -/* 0x0674: memx_func_wait_vblank_head0 */ - 0x000877f1, -/* 0x0678: memx_func_wait_vblank_0 */ - 0x07c467f1, - 0xcf0664b6, - 0x67fd0066, - 0xf31bf404, -/* 0x0688: memx_func_wait_vblank_1 */ - 0x07c467f1, - 0xcf0664b6, - 0x67fd0066, - 0xf30bf404, -/* 0x0698: memx_func_wait_vblank_fini */ - 0xf80410b6, -/* 0x069d: memx_func_wr32 */ - 0x00169800, - 0xb6011598, - 0x60f90810, - 0xd0fc50f9, - 0x21f4e0fc, - 0x0242b640, - 0xf8e91bf4, -/* 0x06b9: memx_func_wait */ - 0x2c87f000, - 0xcf0684b6, - 0x1e980088, - 0x011d9800, - 0x98021c98, - 0x10b6031b, - 0xa321f410, -/* 0x06d6: memx_func_delay */ - 0x1e9800f8, - 0x0410b600, - 0xf87e21f4, -/* 0x06e1: memx_func_train */ -/* 0x06e3: memx_exec */ - 0xf900f800, - 0xb9d0f9e0, - 0xb2b902c1, -/* 0x06ed: memx_exec_next */ - 0x00139802, - 0xe70410b6, - 0xe701f034, - 0xb601e033, - 0x30f00132, - 0xde35980c, - 0x12b855f9, - 0xe41ef406, - 0x98f10b98, - 0xcbbbf20c, - 0xc4b7f102, - 0x06b4b607, - 0xfc00bbcf, - 0xf5e0fcd0, - 0xf8033621, -/* 0x0729: memx_info */ - 0x01c67000, -/* 0x072f: memx_info_data */ - 0xf10e0bf4, - 0xf103ccc7, - 0xf40800b7, -/* 0x073a: memx_info_train */ - 0xc7f10b0e, - 0xb7f10bcc, -/* 0x0742: memx_info_send */ - 0x21f50100, - 0x00f80336, -/* 0x0748: memx_recv */ - 0xf401d6b0, - 0xd6b0980b, - 0xd80bf400, -/* 0x0756: memx_init */ - 0x00f800f8, -/* 0x0758: perf_recv */ -/* 0x075a: perf_init */ + 0x2077f02c, +/* 0x0673: memx_func_wait_vblank_head0 */ + 0xf0060ef4, +/* 0x0676: memx_func_wait_vblank_0 */ + 0x67f10877, + 0x64b607c4, + 0x0066cf06, + 0xf40467fd, +/* 0x0686: memx_func_wait_vblank_1 */ + 0x67f1f31b, + 0x64b607c4, + 0x0066cf06, + 0xf40467fd, +/* 0x0696: memx_func_wait_vblank_fini */ + 0x10b6f30b, +/* 0x069b: memx_func_wr32 */ + 0x9800f804, + 0x15980016, + 0x0810b601, + 0x50f960f9, + 0xe0fcd0fc, + 0xb64021f4, + 0x1bf40242, +/* 0x06b7: memx_func_wait */ + 0xf000f8e9, + 0x84b62c87, + 0x0088cf06, + 0x98001e98, + 0x1c98011d, + 0x031b9802, + 0xf41010b6, + 0x00f8a321, +/* 0x06d4: memx_func_delay */ + 0xb6001e98, + 0x21f40410, +/* 0x06df: memx_func_train */ + 0xf800f87e, +/* 0x06e1: memx_exec */ + 0xf9e0f900, + 0x02c1b9d0, +/* 0x06eb: memx_exec_next */ + 0x9802b2b9, + 0x10b60013, + 0xf034e704, + 0xe033e701, + 0x0132b601, + 0x980c30f0, + 0x55f9de35, + 0xf40612b8, + 0x0b98e41e, + 0xf20c98f1, + 0xf102cbbb, + 0xb607c4b7, + 0xbbcf06b4, + 0xfcd0fc00, + 0x3621f5e0, +/* 0x0727: memx_info */ + 0x7000f803, + 0x0bf401c6, +/* 0x072d: memx_info_data */ + 0xccc7f10e, + 0x00b7f103, + 0x0b0ef408, +/* 0x0738: memx_info_train */ + 0x0bccc7f1, + 0x0100b7f1, +/* 0x0740: memx_info_send */ + 0x033621f5, +/* 0x0746: memx_recv */ + 0xd6b000f8, + 0x980bf401, + 0xf400d6b0, + 0x00f8d80b, +/* 0x0754: memx_init */ +/* 0x0756: perf_recv */ 0x00f800f8, -/* 0x075c: i2c_drive_scl */ - 0xf40036b0, - 0x07f1110b, - 0x04b607e0, - 0x0001d006, - 0x00f804bd, -/* 0x0770: i2c_drive_scl_lo */ - 0x07e407f1, - 0xd00604b6, - 0x04bd0001, -/* 0x077e: i2c_drive_sda */ +/* 0x0758: perf_init */ +/* 0x075a: i2c_drive_scl */ 0x36b000f8, 0x110bf400, 0x07e007f1, 0xd00604b6, - 0x04bd0002, -/* 0x0792: i2c_drive_sda_lo */ + 0x04bd0001, +/* 0x076e: i2c_drive_scl_lo */ 0x07f100f8, 0x04b607e4, + 0x0001d006, + 0x00f804bd, +/* 0x077c: i2c_drive_sda */ + 0xf40036b0, + 0x07f1110b, + 0x04b607e0, 0x0002d006, 0x00f804bd, -/* 0x07a0: i2c_sense_scl */ - 0xf10132f4, - 0xb607c437, - 0x33cf0634, - 0x0431fd00, - 0xf4060bf4, -/* 0x07b6: i2c_sense_scl_done */ - 0x00f80131, -/* 0x07b8: i2c_sense_sda */ - 0xf10132f4, - 0xb607c437, - 0x33cf0634, - 0x0432fd00, - 0xf4060bf4, -/* 0x07ce: i2c_sense_sda_done */ - 0x00f80131, -/* 0x07d0: i2c_raise_scl */ - 0x47f140f9, - 0x37f00898, - 0x5c21f501, -/* 0x07dd: i2c_raise_scl_wait */ - 0xe8e7f107, - 0x7e21f403, - 0x07a021f5, - 0xb60901f4, - 0x1bf40142, -/* 0x07f1: i2c_raise_scl_done */ - 0xf840fcef, -/* 0x07f5: i2c_start */ - 0xa021f500, - 0x0d11f407, - 0x07b821f5, - 0xf40611f4, -/* 0x0806: i2c_start_rep */ - 0x37f0300e, - 0x5c21f500, - 0x0137f007, - 0x077e21f5, - 0xb60076bb, - 0x50f90465, - 0xbb046594, - 0x50bd0256, - 0xfc0475fd, - 0xd021f550, - 0x0464b607, -/* 0x0833: i2c_start_send */ - 0xf01f11f4, +/* 0x0790: i2c_drive_sda_lo */ + 0x07e407f1, + 0xd00604b6, + 0x04bd0002, +/* 0x079e: i2c_sense_scl */ + 0x32f400f8, + 0xc437f101, + 0x0634b607, + 0xfd0033cf, + 0x0bf40431, + 0x0131f406, +/* 0x07b4: i2c_sense_scl_done */ +/* 0x07b6: i2c_sense_sda */ + 0x32f400f8, + 0xc437f101, + 0x0634b607, + 0xfd0033cf, + 0x0bf40432, + 0x0131f406, +/* 0x07cc: i2c_sense_sda_done */ +/* 0x07ce: i2c_raise_scl */ + 0x40f900f8, + 0x089847f1, + 0xf50137f0, +/* 0x07db: i2c_raise_scl_wait */ + 0xf1075a21, + 0xf403e8e7, + 0x21f57e21, + 0x01f4079e, + 0x0142b609, +/* 0x07ef: i2c_raise_scl_done */ + 0xfcef1bf4, +/* 0x07f3: i2c_start */ + 0xf500f840, + 0xf4079e21, + 0x21f50d11, + 0x11f407b6, + 0x300ef406, +/* 0x0804: i2c_start_rep */ + 0xf50037f0, + 0xf0075a21, + 0x21f50137, + 0x76bb077c, + 0x0465b600, + 0x659450f9, + 0x0256bb04, + 0x75fd50bd, + 0xf550fc04, + 0xb607ce21, + 0x11f40464, +/* 0x0831: i2c_start_send */ + 0x0037f01f, + 0x077c21f5, + 0x1388e7f1, + 0xf07e21f4, 0x21f50037, - 0xe7f1077e, + 0xe7f1075a, 0x21f41388, - 0x0037f07e, - 0x075c21f5, - 0x1388e7f1, -/* 0x084f: i2c_start_out */ - 0xf87e21f4, -/* 0x0851: i2c_stop */ - 0x0037f000, - 0x075c21f5, - 0xf50037f0, - 0xf1077e21, - 0xf403e8e7, - 0x37f07e21, - 0x5c21f501, - 0x88e7f107, - 0x7e21f413, +/* 0x084d: i2c_start_out */ +/* 0x084f: i2c_stop */ + 0xf000f87e, + 0x21f50037, + 0x37f0075a, + 0x7c21f500, + 0xe8e7f107, + 0x7e21f403, 0xf50137f0, - 0xf1077e21, + 0xf1075a21, 0xf41388e7, - 0x00f87e21, -/* 0x0884: i2c_bitw */ - 0x077e21f5, - 0x03e8e7f1, - 0xbb7e21f4, - 0x65b60076, - 0x9450f904, - 0x56bb0465, - 0xfd50bd02, - 0x50fc0475, - 0x07d021f5, - 0xf40464b6, - 0xe7f11811, - 0x21f41388, - 0x0037f07e, - 0x075c21f5, - 0x1388e7f1, -/* 0x08c3: i2c_bitw_out */ - 0xf87e21f4, -/* 0x08c5: i2c_bitr */ - 0x0137f000, - 0x077e21f5, - 0x03e8e7f1, - 0xbb7e21f4, - 0x65b60076, - 0x9450f904, - 0x56bb0465, - 0xfd50bd02, - 0x50fc0475, - 0x07d021f5, - 0xf40464b6, - 0x21f51b11, - 0x37f007b8, - 0x5c21f500, + 0x37f07e21, + 0x7c21f501, 0x88e7f107, 0x7e21f413, - 0xf4013cf0, -/* 0x090a: i2c_bitr_done */ - 0x00f80131, -/* 0x090c: i2c_get_byte */ - 0xf00057f0, -/* 0x0912: i2c_get_byte_next */ - 0x54b60847, - 0x0076bb01, +/* 0x0882: i2c_bitw */ + 0x21f500f8, + 0xe7f1077c, + 0x21f403e8, + 0x0076bb7e, 0xf90465b6, 0x04659450, 0xbd0256bb, 0x0475fd50, 0x21f550fc, - 0x64b608c5, - 0x2b11f404, - 0xb60553fd, - 0x1bf40142, - 0x0137f0d8, - 0xb60076bb, - 0x50f90465, - 0xbb046594, - 0x50bd0256, - 0xfc0475fd, - 0x8421f550, - 0x0464b608, -/* 0x095c: i2c_get_byte_done */ -/* 0x095e: i2c_put_byte */ - 0x47f000f8, -/* 0x0961: i2c_put_byte_next */ - 0x0142b608, - 0xbb3854ff, + 0x64b607ce, + 0x1811f404, + 0x1388e7f1, + 0xf07e21f4, + 0x21f50037, + 0xe7f1075a, + 0x21f41388, +/* 0x08c1: i2c_bitw_out */ +/* 0x08c3: i2c_bitr */ + 0xf000f87e, + 0x21f50137, + 0xe7f1077c, + 0x21f403e8, + 0x0076bb7e, + 0xf90465b6, + 0x04659450, + 0xbd0256bb, + 0x0475fd50, + 0x21f550fc, + 0x64b607ce, + 0x1b11f404, + 0x07b621f5, + 0xf50037f0, + 0xf1075a21, + 0xf41388e7, + 0x3cf07e21, + 0x0131f401, +/* 0x0908: i2c_bitr_done */ +/* 0x090a: i2c_get_byte */ + 0x57f000f8, + 0x0847f000, +/* 0x0910: i2c_get_byte_next */ + 0xbb0154b6, 0x65b60076, 0x9450f904, 0x56bb0465, 0xfd50bd02, 0x50fc0475, - 0x088421f5, + 0x08c321f5, 0xf40464b6, - 0x46b03411, - 0xd81bf400, - 0xb60076bb, - 0x50f90465, - 0xbb046594, - 0x50bd0256, - 0xfc0475fd, - 0xc521f550, - 0x0464b608, - 0xbb0f11f4, - 0x36b00076, - 0x061bf401, -/* 0x09b7: i2c_put_byte_done */ - 0xf80132f4, -/* 0x09b9: i2c_addr */ - 0x0076bb00, + 0x53fd2b11, + 0x0142b605, + 0xf0d81bf4, + 0x76bb0137, + 0x0465b600, + 0x659450f9, + 0x0256bb04, + 0x75fd50bd, + 0xf550fc04, + 0xb6088221, +/* 0x095a: i2c_get_byte_done */ + 0x00f80464, +/* 0x095c: i2c_put_byte */ +/* 0x095f: i2c_put_byte_next */ + 0xb60847f0, + 0x54ff0142, + 0x0076bb38, 0xf90465b6, 0x04659450, 0xbd0256bb, 0x0475fd50, 0x21f550fc, - 0x64b607f5, - 0x2911f404, - 0x012ec3e7, - 0xfd0134b6, - 0x76bb0553, + 0x64b60882, + 0x3411f404, + 0xf40046b0, + 0x76bbd81b, 0x0465b600, 0x659450f9, 0x0256bb04, 0x75fd50bd, 0xf550fc04, - 0xb6095e21, -/* 0x09fe: i2c_addr_done */ - 0x00f80464, -/* 0x0a00: i2c_acquire_addr */ - 0xb6f8cec7, - 0xe0b702e4, - 0xee980d1c, -/* 0x0a0f: i2c_acquire */ - 0xf500f800, - 0xf40a0021, - 0xd9f00421, - 0x4021f403, -/* 0x0a1e: i2c_release */ - 0x21f500f8, - 0x21f40a00, - 0x03daf004, - 0xf84021f4, -/* 0x0a2d: i2c_recv */ - 0x0132f400, - 0xb6f8c1c7, - 0x16b00214, - 0x3a1ff528, - 0xf413a001, - 0x0032980c, - 0x0ccc13a0, - 0xf4003198, - 0xd0f90231, - 0xd0f9e0f9, - 0x000067f1, - 0x100063f1, - 0xbb016792, + 0xb608c321, + 0x11f40464, + 0x0076bb0f, + 0xf40136b0, + 0x32f4061b, +/* 0x09b5: i2c_put_byte_done */ +/* 0x09b7: i2c_addr */ + 0xbb00f801, 0x65b60076, 0x9450f904, 0x56bb0465, 0xfd50bd02, 0x50fc0475, - 0x0a0f21f5, - 0xfc0464b6, - 0x00d6b0d0, - 0x00b31bf5, - 0xbb0057f0, - 0x65b60076, - 0x9450f904, - 0x56bb0465, - 0xfd50bd02, - 0x50fc0475, - 0x09b921f5, - 0xf50464b6, - 0xc700d011, - 0x76bbe0c5, - 0x0465b600, - 0x659450f9, - 0x0256bb04, - 0x75fd50bd, - 0xf550fc04, - 0xb6095e21, - 0x11f50464, - 0x57f000ad, + 0x07f321f5, + 0xf40464b6, + 0xc3e72911, + 0x34b6012e, + 0x0553fd01, + 0xb60076bb, + 0x50f90465, + 0xbb046594, + 0x50bd0256, + 0xfc0475fd, + 0x5c21f550, + 0x0464b609, +/* 0x09fc: i2c_addr_done */ +/* 0x09fe: i2c_acquire_addr */ + 0xcec700f8, + 0x02e4b6f8, + 0x0d1ce0b7, + 0xf800ee98, +/* 0x0a0d: i2c_acquire */ + 0xfe21f500, + 0x0421f409, + 0xf403d9f0, + 0x00f84021, +/* 0x0a1c: i2c_release */ + 0x09fe21f5, + 0xf00421f4, + 0x21f403da, +/* 0x0a2b: i2c_recv */ + 0xf400f840, + 0xc1c70132, + 0x0214b6f8, + 0xf52816b0, + 0xa0013a1f, + 0x980cf413, + 0x13a00032, + 0x31980ccc, + 0x0231f400, + 0xe0f9d0f9, + 0x67f1d0f9, + 0x63f10000, + 0x67921000, 0x0076bb01, 0xf90465b6, 0x04659450, 0xbd0256bb, 0x0475fd50, 0x21f550fc, - 0x64b609b9, - 0x8a11f504, + 0x64b60a0d, + 0xb0d0fc04, + 0x1bf500d6, + 0x57f000b3, 0x0076bb00, 0xf90465b6, 0x04659450, 0xbd0256bb, 0x0475fd50, 0x21f550fc, - 0x64b6090c, - 0x6a11f404, - 0xbbe05bcb, + 0x64b609b7, + 0xd011f504, + 0xe0c5c700, + 0xb60076bb, + 0x50f90465, + 0xbb046594, + 0x50bd0256, + 0xfc0475fd, + 0x5c21f550, + 0x0464b609, + 0x00ad11f5, + 0xbb0157f0, 0x65b60076, 0x9450f904, 0x56bb0465, 0xfd50bd02, 0x50fc0475, - 0x085121f5, - 0xb90464b6, - 0x74bd025b, -/* 0x0b33: i2c_recv_not_rd08 */ - 0xb0430ef4, - 0x1bf401d6, - 0x0057f03d, - 0x09b921f5, - 0xc73311f4, - 0x21f5e0c5, - 0x11f4095e, - 0x0057f029, - 0x09b921f5, - 0xc71f11f4, - 0x21f5e0b5, - 0x11f4095e, - 0x5121f515, - 0xc774bd08, - 0x1bf408c5, - 0x0232f409, -/* 0x0b73: i2c_recv_not_wr08 */ -/* 0x0b73: i2c_recv_done */ - 0xc7030ef4, - 0x21f5f8ce, - 0xe0fc0a1e, - 0x12f4d0fc, - 0x027cb90a, - 0x033621f5, -/* 0x0b88: i2c_recv_exit */ -/* 0x0b8a: i2c_init */ - 0x00f800f8, -/* 0x0b8c: test_recv */ - 0x05d817f1, + 0x09b721f5, + 0xf50464b6, + 0xbb008a11, + 0x65b60076, + 0x9450f904, + 0x56bb0465, + 0xfd50bd02, + 0x50fc0475, + 0x090a21f5, + 0xf40464b6, + 0x5bcb6a11, + 0x0076bbe0, + 0xf90465b6, + 0x04659450, + 0xbd0256bb, + 0x0475fd50, + 0x21f550fc, + 0x64b6084f, + 0x025bb904, + 0x0ef474bd, +/* 0x0b31: i2c_recv_not_rd08 */ + 0x01d6b043, + 0xf03d1bf4, + 0x21f50057, + 0x11f409b7, + 0xe0c5c733, + 0x095c21f5, + 0xf02911f4, + 0x21f50057, + 0x11f409b7, + 0xe0b5c71f, + 0x095c21f5, + 0xf51511f4, + 0xbd084f21, + 0x08c5c774, + 0xf4091bf4, + 0x0ef40232, +/* 0x0b71: i2c_recv_not_wr08 */ +/* 0x0b71: i2c_recv_done */ + 0xf8cec703, + 0x0a1c21f5, + 0xd0fce0fc, + 0xb90a12f4, + 0x21f5027c, +/* 0x0b86: i2c_recv_exit */ + 0x00f80336, +/* 0x0b88: i2c_init */ +/* 0x0b8a: test_recv */ + 0x17f100f8, + 0x14b605d8, + 0x0011cf06, + 0xf10110b6, + 0xb605d807, + 0x01d00604, + 0xf104bd00, + 0xf1d900e7, + 0xf5134fe3, + 0xf8025621, +/* 0x0bb1: test_init */ + 0x00e7f100, + 0x5621f508, +/* 0x0bbb: idle_recv */ + 0xf800f802, +/* 0x0bbd: idle */ + 0x0031f400, + 0x05d417f1, 0xcf0614b6, 0x10b60011, - 0xd807f101, + 0xd407f101, 0x0604b605, 0xbd0001d0, - 0x00e7f104, - 0x4fe3f1d9, - 0x5621f513, -/* 0x0bb3: test_init */ - 0xf100f802, - 0xf50800e7, - 0xf8025621, -/* 0x0bbd: idle_recv */ -/* 0x0bbf: idle */ - 0xf400f800, - 0x17f10031, - 0x14b605d4, - 0x0011cf06, - 0xf10110b6, - 0xb605d407, - 0x01d00604, -/* 0x0bdb: idle_loop */ - 0xf004bd00, - 0x32f45817, -/* 0x0be1: idle_proc */ -/* 0x0be1: idle_proc_exec */ - 0xb910f902, - 0x21f5021e, - 0x10fc033f, - 0xf40911f4, - 0x0ef40231, -/* 0x0bf5: idle_proc_next */ - 0x5810b6ef, - 0xf4061fb8, - 0x02f4e61b, - 0x0028f4dd, - 0x00bb0ef4, +/* 0x0bd9: idle_loop */ + 0x5817f004, +/* 0x0bdf: idle_proc */ +/* 0x0bdf: idle_proc_exec */ + 0xf90232f4, + 0x021eb910, + 0x033f21f5, + 0x11f410fc, + 0x0231f409, +/* 0x0bf3: idle_proc_next */ + 0xb6ef0ef4, + 0x1fb85810, + 0xe61bf406, + 0xf4dd02f4, + 0x0ef40028, + 0x000000bb, 0x00000000, 0x00000000, 0x00000000, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gk208.fuc5.h b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gk208.fuc5.h index c4edbc79e41a..e0222cb832fb 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gk208.fuc5.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gk208.fuc5.h @@ -47,8 +47,8 @@ static uint32_t gk208_pmu_data[] = { 0x00000000, 0x00000000, 0x584d454d, - 0x000005f3, - 0x000005e5, + 0x000005ee, + 0x000005e0, 0x00000000, 0x00000000, 0x00000000, @@ -69,8 +69,8 @@ static uint32_t gk208_pmu_data[] = { 0x00000000, 0x00000000, 0x46524550, - 0x000005f7, - 0x000005f5, + 0x000005f2, + 0x000005f0, 0x00000000, 0x00000000, 0x00000000, @@ -91,8 +91,8 @@ static uint32_t gk208_pmu_data[] = { 0x00000000, 0x00000000, 0x5f433249, - 0x000009f8, - 0x000008a2, + 0x000009f3, + 0x0000089d, 0x00000000, 0x00000000, 0x00000000, @@ -113,8 +113,8 @@ static uint32_t gk208_pmu_data[] = { 0x00000000, 0x00000000, 0x54534554, - 0x00000a16, - 0x000009fa, + 0x00000a11, + 0x000009f5, 0x00000000, 0x00000000, 0x00000000, @@ -135,8 +135,8 @@ static uint32_t gk208_pmu_data[] = { 0x00000000, 0x00000000, 0x454c4449, - 0x00000a21, - 0x00000a1f, + 0x00000a1c, + 0x00000a1a, 0x00000000, 0x00000000, 0x00000000, @@ -234,22 +234,22 @@ static uint32_t gk208_pmu_data[] = { /* 0x037c: memx_func_next */ 0x00000002, 0x00000000, - 0x000004cf, + 0x000004cc, 0x00000003, 0x00000002, - 0x00000546, + 0x00000541, 0x00040004, 0x00000000, - 0x00000563, + 0x0000055e, 0x00010005, 0x00000000, - 0x0000057d, + 0x00000578, 0x00010006, 0x00000000, - 0x00000541, + 0x0000053c, 0x00000007, 0x00000000, - 0x00000589, + 0x00000584, /* 0x03c4: memx_func_tail */ /* 0x03c4: memx_ts_start */ 0x00000000, @@ -1239,454 +1239,454 @@ static uint32_t gk208_pmu_code[] = { 0x0001f604, 0x00f804bd, /* 0x045c: memx_func_enter */ - 0x162067f1, - 0xf55d77f1, - 0x047e6eb2, - 0xd8b20000, - 0xf90487fd, - 0xfc80f960, - 0x7ee0fcd0, - 0x0700002d, - 0x7e6eb2fe, + 0x47162046, + 0x6eb2f55d, + 0x0000047e, + 0x87fdd8b2, + 0xf960f904, + 0xfcd0fc80, + 0x002d7ee0, + 0xb2fe0700, + 0x00047e6e, + 0xfdd8b200, + 0x60f90487, + 0xd0fc80f9, + 0x2d7ee0fc, + 0xf0460000, + 0x7e6eb226, 0xb2000004, 0x0487fdd8, 0x80f960f9, 0xe0fcd0fc, 0x00002d7e, - 0x26f067f1, - 0x047e6eb2, - 0xd8b20000, - 0xf90487fd, - 0xfc80f960, - 0x7ee0fcd0, - 0x0600002d, - 0x07e04004, - 0xbd0006f6, -/* 0x04b9: memx_func_enter_wait */ - 0x07c04604, - 0xf00066cf, - 0x0bf40464, - 0xcf2c06f7, - 0x06b50066, -/* 0x04cf: memx_func_leave */ - 0x0600f8f1, - 0x0066cf2c, - 0x06f206b5, - 0x07e44004, - 0xbd0006f6, -/* 0x04e1: memx_func_leave_wait */ - 0x07c04604, - 0xf00066cf, - 0x1bf40464, - 0xf067f1f7, + 0xe0400406, + 0x0006f607, +/* 0x04b6: memx_func_enter_wait */ + 0xc04604bd, + 0x0066cf07, + 0xf40464f0, + 0x2c06f70b, + 0xb50066cf, + 0x00f8f106, +/* 0x04cc: memx_func_leave */ + 0x66cf2c06, + 0xf206b500, + 0xe4400406, + 0x0006f607, +/* 0x04de: memx_func_leave_wait */ + 0xc04604bd, + 0x0066cf07, + 0xf40464f0, + 0xf046f71b, 0xb2010726, 0x00047e6e, 0xfdd8b200, 0x60f90587, 0xd0fc80f9, 0x2d7ee0fc, - 0x67f10000, - 0x6eb21620, - 0x0000047e, - 0x87fdd8b2, - 0xf960f905, - 0xfcd0fc80, - 0x002d7ee0, - 0x0aa24700, - 0x047e6eb2, - 0xd8b20000, - 0xf90587fd, - 0xfc80f960, - 0x7ee0fcd0, - 0xf800002d, -/* 0x0541: memx_func_wait_vblank */ + 0x20460000, + 0x7e6eb216, + 0xb2000004, + 0x0587fdd8, + 0x80f960f9, + 0xe0fcd0fc, + 0x00002d7e, + 0xb20aa247, + 0x00047e6e, + 0xfdd8b200, + 0x60f90587, + 0xd0fc80f9, + 0x2d7ee0fc, + 0x00f80000, +/* 0x053c: memx_func_wait_vblank */ + 0xf80410b6, +/* 0x0541: memx_func_wr32 */ + 0x00169800, + 0xb6011598, + 0x60f90810, + 0xd0fc50f9, + 0x2d7ee0fc, + 0x42b60000, + 0xe81bf402, +/* 0x055e: memx_func_wait */ + 0x2c0800f8, + 0x980088cf, + 0x1d98001e, + 0x021c9801, + 0xb6031b98, + 0x747e1010, + 0x00f80000, +/* 0x0578: memx_func_delay */ + 0xb6001e98, + 0x587e0410, + 0x00f80000, +/* 0x0584: memx_func_train */ +/* 0x0586: memx_exec */ + 0xe0f900f8, + 0xc1b2d0f9, +/* 0x058e: memx_exec_next */ + 0x1398b2b2, 0x0410b600, -/* 0x0546: memx_func_wr32 */ - 0x169800f8, - 0x01159800, - 0xf90810b6, - 0xfc50f960, + 0x01f034e7, + 0x01e033e7, + 0xf00132b6, + 0x35980c30, + 0xa655f9de, + 0xe51ef412, + 0x98f10b98, + 0xcbbbf20c, + 0x07c44b02, + 0xfc00bbcf, 0x7ee0fcd0, - 0xb600002d, - 0x1bf40242, -/* 0x0563: memx_func_wait */ - 0x0800f8e8, - 0x0088cf2c, - 0x98001e98, - 0x1c98011d, - 0x031b9802, - 0x7e1010b6, - 0xf8000074, -/* 0x057d: memx_func_delay */ - 0x001e9800, - 0x7e0410b6, - 0xf8000058, -/* 0x0589: memx_func_train */ -/* 0x058b: memx_exec */ - 0xf900f800, - 0xb2d0f9e0, -/* 0x0593: memx_exec_next */ - 0x98b2b2c1, - 0x10b60013, - 0xf034e704, - 0xe033e701, - 0x0132b601, - 0x980c30f0, - 0x55f9de35, - 0x1ef412a6, - 0xf10b98e5, - 0xbbf20c98, - 0xc44b02cb, - 0x00bbcf07, - 0xe0fcd0fc, - 0x00029f7e, -/* 0x05ca: memx_info */ - 0xc67000f8, - 0x0c0bf401, -/* 0x05d0: memx_info_data */ - 0x4b03cc4c, - 0x0ef40800, -/* 0x05d9: memx_info_train */ - 0x0bcc4c09, -/* 0x05df: memx_info_send */ - 0x7e01004b, 0xf800029f, -/* 0x05e5: memx_recv */ - 0x01d6b000, - 0xb0a30bf4, - 0x0bf400d6, -/* 0x05f3: memx_init */ - 0xf800f8dc, -/* 0x05f5: perf_recv */ -/* 0x05f7: perf_init */ - 0xf800f800, -/* 0x05f9: i2c_drive_scl */ - 0x0036b000, - 0x400d0bf4, - 0x01f607e0, - 0xf804bd00, -/* 0x0609: i2c_drive_scl_lo */ - 0x07e44000, - 0xbd0001f6, -/* 0x0613: i2c_drive_sda */ - 0xb000f804, - 0x0bf40036, - 0x07e0400d, - 0xbd0002f6, -/* 0x0623: i2c_drive_sda_lo */ - 0x4000f804, - 0x02f607e4, - 0xf804bd00, -/* 0x062d: i2c_sense_scl */ - 0x0132f400, - 0xcf07c443, - 0x31fd0033, - 0x060bf404, -/* 0x063f: i2c_sense_scl_done */ - 0xf80131f4, -/* 0x0641: i2c_sense_sda */ - 0x0132f400, - 0xcf07c443, - 0x32fd0033, - 0x060bf404, -/* 0x0653: i2c_sense_sda_done */ - 0xf80131f4, -/* 0x0655: i2c_raise_scl */ - 0x4440f900, - 0x01030898, - 0x0005f97e, -/* 0x0660: i2c_raise_scl_wait */ - 0x7e03e84e, - 0x7e000058, - 0xf400062d, - 0x42b60901, - 0xef1bf401, -/* 0x0674: i2c_raise_scl_done */ - 0x00f840fc, -/* 0x0678: i2c_start */ - 0x00062d7e, - 0x7e0d11f4, - 0xf4000641, - 0x0ef40611, -/* 0x0689: i2c_start_rep */ - 0x7e00032e, - 0x030005f9, - 0x06137e01, +/* 0x05c5: memx_info */ + 0x01c67000, +/* 0x05cb: memx_info_data */ + 0x4c0c0bf4, + 0x004b03cc, + 0x090ef408, +/* 0x05d4: memx_info_train */ + 0x4b0bcc4c, +/* 0x05da: memx_info_send */ + 0x9f7e0100, + 0x00f80002, +/* 0x05e0: memx_recv */ + 0xf401d6b0, + 0xd6b0a30b, + 0xdc0bf400, +/* 0x05ee: memx_init */ + 0x00f800f8, +/* 0x05f0: perf_recv */ +/* 0x05f2: perf_init */ + 0x00f800f8, +/* 0x05f4: i2c_drive_scl */ + 0xf40036b0, + 0xe0400d0b, + 0x0001f607, + 0x00f804bd, +/* 0x0604: i2c_drive_scl_lo */ + 0xf607e440, + 0x04bd0001, +/* 0x060e: i2c_drive_sda */ + 0x36b000f8, + 0x0d0bf400, + 0xf607e040, + 0x04bd0002, +/* 0x061e: i2c_drive_sda_lo */ + 0xe44000f8, + 0x0002f607, + 0x00f804bd, +/* 0x0628: i2c_sense_scl */ + 0x430132f4, + 0x33cf07c4, + 0x0431fd00, + 0xf4060bf4, +/* 0x063a: i2c_sense_scl_done */ + 0x00f80131, +/* 0x063c: i2c_sense_sda */ + 0x430132f4, + 0x33cf07c4, + 0x0432fd00, + 0xf4060bf4, +/* 0x064e: i2c_sense_sda_done */ + 0x00f80131, +/* 0x0650: i2c_raise_scl */ + 0x984440f9, + 0x7e010308, +/* 0x065b: i2c_raise_scl_wait */ + 0x4e0005f4, + 0x587e03e8, + 0x287e0000, + 0x01f40006, + 0x0142b609, +/* 0x066f: i2c_raise_scl_done */ + 0xfcef1bf4, +/* 0x0673: i2c_start */ + 0x7e00f840, + 0xf4000628, + 0x3c7e0d11, + 0x11f40006, + 0x2e0ef406, +/* 0x0684: i2c_start_rep */ + 0xf47e0003, + 0x01030005, + 0x00060e7e, + 0xb60076bb, + 0x50f90465, + 0xbb046594, + 0x50bd0256, + 0xfc0475fd, + 0x06507e50, + 0x0464b600, +/* 0x06af: i2c_start_send */ + 0x031d11f4, + 0x060e7e00, + 0x13884e00, + 0x0000587e, + 0xf47e0003, + 0x884e0005, + 0x00587e13, +/* 0x06c9: i2c_start_out */ +/* 0x06cb: i2c_stop */ + 0x0300f800, + 0x05f47e00, + 0x7e000300, + 0x4e00060e, + 0x587e03e8, + 0x01030000, + 0x0005f47e, + 0x7e13884e, + 0x03000058, + 0x060e7e01, + 0x13884e00, + 0x0000587e, +/* 0x06fa: i2c_bitw */ + 0x0e7e00f8, + 0xe84e0006, + 0x00587e03, 0x0076bb00, 0xf90465b6, 0x04659450, 0xbd0256bb, 0x0475fd50, - 0x557e50fc, + 0x507e50fc, 0x64b60006, - 0x1d11f404, -/* 0x06b4: i2c_start_send */ - 0x137e0003, - 0x884e0006, - 0x00587e13, - 0x7e000300, - 0x4e0005f9, - 0x587e1388, -/* 0x06ce: i2c_start_out */ - 0x00f80000, -/* 0x06d0: i2c_stop */ - 0xf97e0003, - 0x00030005, - 0x0006137e, - 0x7e03e84e, + 0x1711f404, + 0x7e13884e, 0x03000058, - 0x05f97e01, + 0x05f47e00, 0x13884e00, 0x0000587e, - 0x137e0103, - 0x884e0006, - 0x00587e13, -/* 0x06ff: i2c_bitw */ - 0x7e00f800, - 0x4e000613, - 0x587e03e8, - 0x76bb0000, +/* 0x0738: i2c_bitw_out */ +/* 0x073a: i2c_bitr */ + 0x010300f8, + 0x00060e7e, + 0x7e03e84e, + 0xbb000058, + 0x65b60076, + 0x9450f904, + 0x56bb0465, + 0xfd50bd02, + 0x50fc0475, + 0x0006507e, + 0xf40464b6, + 0x3c7e1a11, + 0x00030006, + 0x0005f47e, + 0x7e13884e, + 0xf0000058, + 0x31f4013c, +/* 0x077d: i2c_bitr_done */ +/* 0x077f: i2c_get_byte */ + 0x0500f801, +/* 0x0783: i2c_get_byte_next */ + 0xb6080400, + 0x76bb0154, 0x0465b600, 0x659450f9, 0x0256bb04, 0x75fd50bd, 0x7e50fc04, - 0xb6000655, + 0xb600073a, 0x11f40464, - 0x13884e17, - 0x0000587e, - 0xf97e0003, - 0x884e0005, - 0x00587e13, -/* 0x073d: i2c_bitw_out */ -/* 0x073f: i2c_bitr */ - 0x0300f800, - 0x06137e01, - 0x03e84e00, - 0x0000587e, + 0x0553fd2a, + 0xf40142b6, + 0x0103d81b, 0xb60076bb, 0x50f90465, 0xbb046594, 0x50bd0256, 0xfc0475fd, - 0x06557e50, + 0x06fa7e50, 0x0464b600, - 0x7e1a11f4, - 0x03000641, - 0x05f97e00, - 0x13884e00, - 0x0000587e, - 0xf4013cf0, -/* 0x0782: i2c_bitr_done */ - 0x00f80131, -/* 0x0784: i2c_get_byte */ - 0x08040005, -/* 0x0788: i2c_get_byte_next */ - 0xbb0154b6, - 0x65b60076, - 0x9450f904, - 0x56bb0465, - 0xfd50bd02, - 0x50fc0475, - 0x00073f7e, - 0xf40464b6, - 0x53fd2a11, - 0x0142b605, - 0x03d81bf4, - 0x0076bb01, - 0xf90465b6, - 0x04659450, - 0xbd0256bb, - 0x0475fd50, - 0xff7e50fc, - 0x64b60006, -/* 0x07d1: i2c_get_byte_done */ -/* 0x07d3: i2c_put_byte */ - 0x0400f804, -/* 0x07d5: i2c_put_byte_next */ - 0x0142b608, - 0xbb3854ff, +/* 0x07cc: i2c_get_byte_done */ +/* 0x07ce: i2c_put_byte */ + 0x080400f8, +/* 0x07d0: i2c_put_byte_next */ + 0xff0142b6, + 0x76bb3854, + 0x0465b600, + 0x659450f9, + 0x0256bb04, + 0x75fd50bd, + 0x7e50fc04, + 0xb60006fa, + 0x11f40464, + 0x0046b034, + 0xbbd81bf4, 0x65b60076, 0x9450f904, 0x56bb0465, 0xfd50bd02, 0x50fc0475, - 0x0006ff7e, + 0x00073a7e, 0xf40464b6, - 0x46b03411, - 0xd81bf400, + 0x76bb0f11, + 0x0136b000, + 0xf4061bf4, +/* 0x0826: i2c_put_byte_done */ + 0x00f80132, +/* 0x0828: i2c_addr */ 0xb60076bb, 0x50f90465, 0xbb046594, 0x50bd0256, 0xfc0475fd, - 0x073f7e50, + 0x06737e50, 0x0464b600, - 0xbb0f11f4, - 0x36b00076, - 0x061bf401, -/* 0x082b: i2c_put_byte_done */ - 0xf80132f4, -/* 0x082d: i2c_addr */ - 0x0076bb00, + 0xe72911f4, + 0xb6012ec3, + 0x53fd0134, + 0x0076bb05, 0xf90465b6, 0x04659450, 0xbd0256bb, 0x0475fd50, - 0x787e50fc, - 0x64b60006, - 0x2911f404, - 0x012ec3e7, - 0xfd0134b6, - 0x76bb0553, - 0x0465b600, - 0x659450f9, - 0x0256bb04, - 0x75fd50bd, - 0x7e50fc04, - 0xb60007d3, -/* 0x0872: i2c_addr_done */ - 0x00f80464, -/* 0x0874: i2c_acquire_addr */ - 0xb6f8cec7, - 0xe0b705e4, - 0x00f8d014, -/* 0x0880: i2c_acquire */ - 0x0008747e, + 0xce7e50fc, + 0x64b60007, +/* 0x086d: i2c_addr_done */ +/* 0x086f: i2c_acquire_addr */ + 0xc700f804, + 0xe4b6f8ce, + 0x14e0b705, +/* 0x087b: i2c_acquire */ + 0x7e00f8d0, + 0x7e00086f, + 0xf0000004, + 0x2d7e03d9, + 0x00f80000, +/* 0x088c: i2c_release */ + 0x00086f7e, 0x0000047e, - 0x7e03d9f0, + 0x7e03daf0, 0xf800002d, -/* 0x0891: i2c_release */ - 0x08747e00, - 0x00047e00, - 0x03daf000, - 0x00002d7e, -/* 0x08a2: i2c_recv */ - 0x32f400f8, - 0xf8c1c701, - 0xb00214b6, - 0x1ff52816, - 0x13b80134, - 0x98000cf4, - 0x13b80032, - 0x98000ccc, - 0x31f40031, - 0xf9d0f902, - 0xd6d0f9e0, - 0x10000000, - 0xbb016792, - 0x65b60076, - 0x9450f904, - 0x56bb0465, - 0xfd50bd02, - 0x50fc0475, - 0x0008807e, - 0xfc0464b6, - 0x00d6b0d0, - 0x00b01bf5, - 0x76bb0005, +/* 0x089d: i2c_recv */ + 0x0132f400, + 0xb6f8c1c7, + 0x16b00214, + 0x341ff528, + 0xf413b801, + 0x3298000c, + 0xcc13b800, + 0x3198000c, + 0x0231f400, + 0xe0f9d0f9, + 0x00d6d0f9, + 0x92100000, + 0x76bb0167, 0x0465b600, 0x659450f9, 0x0256bb04, 0x75fd50bd, 0x7e50fc04, - 0xb600082d, - 0x11f50464, - 0xc5c700cc, - 0x0076bbe0, - 0xf90465b6, - 0x04659450, - 0xbd0256bb, - 0x0475fd50, - 0xd37e50fc, - 0x64b60007, - 0xa911f504, - 0xbb010500, - 0x65b60076, - 0x9450f904, - 0x56bb0465, - 0xfd50bd02, - 0x50fc0475, - 0x00082d7e, - 0xf50464b6, - 0xbb008711, - 0x65b60076, - 0x9450f904, - 0x56bb0465, - 0xfd50bd02, - 0x50fc0475, - 0x0007847e, - 0xf40464b6, - 0x5bcb6711, - 0x0076bbe0, + 0xb600087b, + 0xd0fc0464, + 0xf500d6b0, + 0x0500b01b, + 0x0076bb00, 0xf90465b6, 0x04659450, 0xbd0256bb, 0x0475fd50, - 0xd07e50fc, - 0x64b60006, - 0xbd5bb204, - 0x410ef474, -/* 0x09a4: i2c_recv_not_rd08 */ - 0xf401d6b0, - 0x00053b1b, - 0x00082d7e, - 0xc73211f4, - 0xd37ee0c5, - 0x11f40007, - 0x7e000528, - 0xf400082d, - 0xb5c71f11, - 0x07d37ee0, - 0x1511f400, - 0x0006d07e, - 0xc5c774bd, - 0x091bf408, - 0xf40232f4, -/* 0x09e2: i2c_recv_not_wr08 */ -/* 0x09e2: i2c_recv_done */ - 0xcec7030e, - 0x08917ef8, - 0xfce0fc00, - 0x0912f4d0, - 0x9f7e7cb2, -/* 0x09f6: i2c_recv_exit */ - 0x00f80002, -/* 0x09f8: i2c_init */ -/* 0x09fa: test_recv */ - 0x584100f8, - 0x0011cf04, - 0x400110b6, - 0x01f60458, - 0xde04bd00, - 0x134fd900, - 0x0001de7e, -/* 0x0a16: test_init */ - 0x004e00f8, - 0x01de7e08, -/* 0x0a1f: idle_recv */ + 0x287e50fc, + 0x64b60008, + 0xcc11f504, + 0xe0c5c700, + 0xb60076bb, + 0x50f90465, + 0xbb046594, + 0x50bd0256, + 0xfc0475fd, + 0x07ce7e50, + 0x0464b600, + 0x00a911f5, + 0x76bb0105, + 0x0465b600, + 0x659450f9, + 0x0256bb04, + 0x75fd50bd, + 0x7e50fc04, + 0xb6000828, + 0x11f50464, + 0x76bb0087, + 0x0465b600, + 0x659450f9, + 0x0256bb04, + 0x75fd50bd, + 0x7e50fc04, + 0xb600077f, + 0x11f40464, + 0xe05bcb67, + 0xb60076bb, + 0x50f90465, + 0xbb046594, + 0x50bd0256, + 0xfc0475fd, + 0x06cb7e50, + 0x0464b600, + 0x74bd5bb2, +/* 0x099f: i2c_recv_not_rd08 */ + 0xb0410ef4, + 0x1bf401d6, + 0x7e00053b, + 0xf4000828, + 0xc5c73211, + 0x07ce7ee0, + 0x2811f400, + 0x287e0005, + 0x11f40008, + 0xe0b5c71f, + 0x0007ce7e, + 0x7e1511f4, + 0xbd0006cb, + 0x08c5c774, + 0xf4091bf4, + 0x0ef40232, +/* 0x09dd: i2c_recv_not_wr08 */ +/* 0x09dd: i2c_recv_done */ + 0xf8cec703, + 0x00088c7e, + 0xd0fce0fc, + 0xb20912f4, + 0x029f7e7c, +/* 0x09f1: i2c_recv_exit */ +/* 0x09f3: i2c_init */ 0xf800f800, -/* 0x0a21: idle */ - 0x0031f400, - 0xcf045441, - 0x10b60011, - 0x04544001, - 0xbd0001f6, -/* 0x0a35: idle_loop */ - 0xf4580104, -/* 0x0a3a: idle_proc */ -/* 0x0a3a: idle_proc_exec */ - 0x10f90232, - 0xa87e1eb2, - 0x10fc0002, - 0xf40911f4, - 0x0ef40231, -/* 0x0a4d: idle_proc_next */ - 0x5810b6f0, - 0x1bf41fa6, - 0xe002f4e8, - 0xf40028f4, - 0x0000c60e, +/* 0x09f5: test_recv */ + 0x04584100, + 0xb60011cf, + 0x58400110, + 0x0001f604, + 0x00de04bd, + 0x7e134fd9, + 0xf80001de, +/* 0x0a11: test_init */ + 0x08004e00, + 0x0001de7e, +/* 0x0a1a: idle_recv */ + 0x00f800f8, +/* 0x0a1c: idle */ + 0x410031f4, + 0x11cf0454, + 0x0110b600, + 0xf6045440, + 0x04bd0001, +/* 0x0a30: idle_loop */ + 0x32f45801, +/* 0x0a35: idle_proc */ +/* 0x0a35: idle_proc_exec */ + 0xb210f902, + 0x02a87e1e, + 0xf410fc00, + 0x31f40911, + 0xf00ef402, +/* 0x0a48: idle_proc_next */ + 0xa65810b6, + 0xe81bf41f, + 0xf4e002f4, + 0x0ef40028, + 0x000000c6, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gt215.fuc3.h b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gt215.fuc3.h index 6a2572e8945a..defddf5957ee 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gt215.fuc3.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gt215.fuc3.h @@ -47,8 +47,8 @@ static uint32_t gt215_pmu_data[] = { 0x00000000, 0x00000000, 0x584d454d, - 0x0000083a, - 0x0000082c, + 0x00000833, + 0x00000825, 0x00000000, 0x00000000, 0x00000000, @@ -69,8 +69,8 @@ static uint32_t gt215_pmu_data[] = { 0x00000000, 0x00000000, 0x46524550, - 0x0000083e, - 0x0000083c, + 0x00000837, + 0x00000835, 0x00000000, 0x00000000, 0x00000000, @@ -91,8 +91,8 @@ static uint32_t gt215_pmu_data[] = { 0x00000000, 0x00000000, 0x5f433249, - 0x00000c6e, - 0x00000b11, + 0x00000c67, + 0x00000b0a, 0x00000000, 0x00000000, 0x00000000, @@ -113,8 +113,8 @@ static uint32_t gt215_pmu_data[] = { 0x00000000, 0x00000000, 0x54534554, - 0x00000c97, - 0x00000c70, + 0x00000c90, + 0x00000c69, 0x00000000, 0x00000000, 0x00000000, @@ -135,8 +135,8 @@ static uint32_t gt215_pmu_data[] = { 0x00000000, 0x00000000, 0x454c4449, - 0x00000ca3, - 0x00000ca1, + 0x00000c9c, + 0x00000c9a, 0x00000000, 0x00000000, 0x00000000, @@ -234,22 +234,22 @@ static uint32_t gt215_pmu_data[] = { /* 0x037c: memx_func_next */ 0x00000002, 0x00000000, - 0x000005a0, + 0x0000059f, 0x00000003, 0x00000002, - 0x00000632, + 0x0000062f, 0x00040004, 0x00000000, - 0x0000064e, + 0x0000064b, 0x00010005, 0x00000000, - 0x0000066b, + 0x00000668, 0x00010006, 0x00000000, - 0x000005f0, + 0x000005ef, 0x00000007, 0x00000000, - 0x00000676, + 0x00000673, /* 0x03c4: memx_func_tail */ /* 0x03c4: memx_ts_start */ 0x00000000, @@ -1305,560 +1305,560 @@ static uint32_t gt215_pmu_code[] = { 0x67f102d7, 0x63f1fffc, 0x76fdffff, - 0x0267f104, - 0x0576fd00, - 0x70f980f9, - 0xe0fcd0fc, - 0xf04021f4, + 0x0267f004, + 0xf90576fd, + 0xfc70f980, + 0xf4e0fcd0, + 0x67f04021, + 0xe007f104, + 0x0604b607, + 0xbd0006d0, +/* 0x0581: memx_func_enter_wait */ + 0xc067f104, + 0x0664b607, + 0xf00066cf, + 0x0bf40464, + 0x2c67f0f3, + 0xcf0664b6, + 0x06800066, +/* 0x059f: memx_func_leave */ + 0xf000f8f1, + 0x64b62c67, + 0x0066cf06, + 0xf0f20680, 0x07f10467, - 0x04b607e0, + 0x04b607e4, 0x0006d006, -/* 0x0582: memx_func_enter_wait */ +/* 0x05ba: memx_func_leave_wait */ 0x67f104bd, 0x64b607c0, 0x0066cf06, 0xf40464f0, - 0x67f0f30b, - 0x0664b62c, - 0x800066cf, - 0x00f8f106, -/* 0x05a0: memx_func_leave */ - 0xb62c67f0, - 0x66cf0664, - 0xf2068000, - 0xf10467f0, - 0xb607e407, - 0x06d00604, -/* 0x05bb: memx_func_leave_wait */ - 0xf104bd00, - 0xb607c067, - 0x66cf0664, - 0x0464f000, - 0xf1f31bf4, - 0xb9161087, - 0x21f4028e, - 0x02d7b904, - 0xffcc67f1, - 0xffff63f1, - 0xf90476fd, - 0xfc70f980, - 0xf4e0fcd0, - 0x00f84021, -/* 0x05f0: memx_func_wait_vblank */ - 0xb0001698, - 0x0bf40066, - 0x0166b013, - 0xf4060bf4, -/* 0x0602: memx_func_wait_vblank_head1 */ - 0x77f12e0e, - 0x0ef40020, -/* 0x0609: memx_func_wait_vblank_head0 */ - 0x0877f107, -/* 0x060d: memx_func_wait_vblank_0 */ - 0xc467f100, - 0x0664b607, - 0xfd0066cf, - 0x1bf40467, -/* 0x061d: memx_func_wait_vblank_1 */ - 0xc467f1f3, - 0x0664b607, - 0xfd0066cf, - 0x0bf40467, -/* 0x062d: memx_func_wait_vblank_fini */ - 0x0410b6f3, -/* 0x0632: memx_func_wr32 */ - 0x169800f8, - 0x01159800, - 0xf90810b6, - 0xfc50f960, - 0xf4e0fcd0, - 0x42b64021, - 0xe91bf402, -/* 0x064e: memx_func_wait */ - 0x87f000f8, - 0x0684b62c, - 0x980088cf, - 0x1d98001e, - 0x021c9801, - 0xb6031b98, - 0x21f41010, -/* 0x066b: memx_func_delay */ - 0x9800f8a3, - 0x10b6001e, - 0x7e21f404, -/* 0x0676: memx_func_train */ - 0x57f100f8, - 0x77f10003, - 0x97f10000, - 0x93f00000, - 0x029eb970, - 0xb90421f4, - 0xe7f102d8, - 0x21f42710, -/* 0x0695: memx_func_train_loop_outer */ - 0x0158e07e, - 0x0083f101, - 0xe097f102, - 0x1193f011, - 0x80f990f9, + 0x87f1f31b, + 0x8eb91610, + 0x0421f402, + 0xf102d7b9, + 0xf1ffcc67, + 0xfdffff63, + 0x80f90476, + 0xd0fc70f9, + 0x21f4e0fc, +/* 0x05ef: memx_func_wait_vblank */ + 0x9800f840, + 0x66b00016, + 0x120bf400, + 0xf40166b0, + 0x0ef4060b, +/* 0x0601: memx_func_wait_vblank_head1 */ + 0x2077f02c, +/* 0x0607: memx_func_wait_vblank_head0 */ + 0xf0060ef4, +/* 0x060a: memx_func_wait_vblank_0 */ + 0x67f10877, + 0x64b607c4, + 0x0066cf06, + 0xf40467fd, +/* 0x061a: memx_func_wait_vblank_1 */ + 0x67f1f31b, + 0x64b607c4, + 0x0066cf06, + 0xf40467fd, +/* 0x062a: memx_func_wait_vblank_fini */ + 0x10b6f30b, +/* 0x062f: memx_func_wr32 */ + 0x9800f804, + 0x15980016, + 0x0810b601, + 0x50f960f9, 0xe0fcd0fc, - 0xf94021f4, - 0x0067f150, -/* 0x06b5: memx_func_train_loop_inner */ - 0x1187f100, - 0x9068ff11, - 0xfd109894, - 0x97f10589, - 0x93f00720, - 0xf990f910, - 0xfcd0fc80, - 0x4021f4e0, - 0x008097f1, - 0xb91093f0, - 0x21f4029e, - 0x02d8b904, - 0xf92088c5, + 0xb64021f4, + 0x1bf40242, +/* 0x064b: memx_func_wait */ + 0xf000f8e9, + 0x84b62c87, + 0x0088cf06, + 0x98001e98, + 0x1c98011d, + 0x031b9802, + 0xf41010b6, + 0x00f8a321, +/* 0x0668: memx_func_delay */ + 0xb6001e98, + 0x21f40410, +/* 0x0673: memx_func_train */ + 0xf000f87e, + 0x77f00357, + 0x0097f100, + 0x7093f000, + 0xf4029eb9, + 0xd8b90421, + 0x10e7f102, + 0x7e21f427, +/* 0x0690: memx_func_train_loop_outer */ + 0x010158e0, + 0x020083f1, + 0x11e097f1, + 0xf91193f0, + 0xfc80f990, + 0xf4e0fcd0, + 0x50f94021, +/* 0x06af: memx_func_train_loop_inner */ + 0xf10067f0, + 0xff111187, + 0x98949068, + 0x0589fd10, + 0x072097f1, + 0xf91093f0, 0xfc80f990, 0xf4e0fcd0, 0x97f14021, - 0x93f0053c, - 0x0287f110, - 0x0083f130, - 0xf990f980, + 0x93f00080, + 0x029eb910, + 0xb90421f4, + 0x88c502d8, + 0xf990f920, 0xfcd0fc80, 0x4021f4e0, - 0x0560e7f1, - 0xf110e3f0, - 0xf10000d7, - 0x908000d3, - 0xb7f100dc, - 0xb3f08480, - 0xa321f41e, - 0x000057f1, - 0xffff97f1, - 0x830093f1, -/* 0x0734: memx_func_train_loop_4x */ - 0x0080a7f1, - 0xb910a3f0, - 0x21f402ae, - 0x02d8b904, - 0xffdfb7f1, - 0xffffb3f1, - 0xf9048bfd, - 0xfc80f9a0, + 0x053c97f1, + 0xf11093f0, + 0xf1300287, + 0xf9800083, + 0xfc80f990, 0xf4e0fcd0, - 0xa7f14021, - 0xa3f0053c, - 0x0287f110, - 0x0083f130, - 0xf9a0f980, - 0xfcd0fc80, - 0x4021f4e0, - 0x0560e7f1, - 0xf110e3f0, - 0xf10000d7, - 0xb98000d3, - 0xb7f102dc, - 0xb3f02710, - 0xa321f400, - 0xf402eeb9, - 0xddb90421, - 0x949dff02, + 0xe7f14021, + 0xe3f00560, + 0x00d7f110, + 0x00d3f100, + 0x00dc9080, + 0x8480b7f1, + 0xf41eb3f0, + 0x57f0a321, + 0xff97f100, + 0x0093f1ff, +/* 0x072d: memx_func_train_loop_4x */ + 0x80a7f183, + 0x10a3f000, + 0xf402aeb9, + 0xd8b90421, + 0xdfb7f102, + 0xffb3f1ff, + 0x048bfdff, + 0x80f9a0f9, + 0xe0fcd0fc, + 0xf14021f4, + 0xf0053ca7, + 0x87f110a3, + 0x83f13002, + 0xa0f98000, + 0xd0fc80f9, + 0x21f4e0fc, + 0x60e7f140, + 0x10e3f005, + 0x0000d7f1, + 0x8000d3f1, + 0xf102dcb9, + 0xf02710b7, + 0x21f400b3, + 0x02eeb9a3, + 0xb90421f4, + 0x9dff02dd, + 0x0150b694, + 0xf4045670, + 0x7aa0921e, + 0xa9800bcc, + 0x0160b600, + 0x700470b6, + 0x1ef51066, + 0x50fcff01, 0x700150b6, - 0x1ef40456, - 0xcc7aa092, - 0x00a9800b, - 0xb60160b6, - 0x66700470, - 0x001ef510, - 0xb650fcff, - 0x56700150, - 0xd41ef507, -/* 0x07c7: memx_exec */ - 0xf900f8fe, - 0xb9d0f9e0, - 0xb2b902c1, -/* 0x07d1: memx_exec_next */ - 0x00139802, - 0xe70410b6, - 0xe701f034, - 0xb601e033, - 0x30f00132, - 0xde35980c, - 0x12b855f9, - 0xe41ef406, - 0x98f10b98, - 0xcbbbf20c, - 0xc4b7f102, - 0x06b4b607, - 0xfc00bbcf, - 0xf5e0fcd0, + 0x1ef50756, + 0x00f8fed6, +/* 0x07c0: memx_exec */ + 0xd0f9e0f9, + 0xb902c1b9, +/* 0x07ca: memx_exec_next */ + 0x139802b2, + 0x0410b600, + 0x01f034e7, + 0x01e033e7, + 0xf00132b6, + 0x35980c30, + 0xb855f9de, + 0x1ef40612, + 0xf10b98e4, + 0xbbf20c98, + 0xb7f102cb, + 0xb4b607c4, + 0x00bbcf06, + 0xe0fcd0fc, + 0x033621f5, +/* 0x0806: memx_info */ + 0xc67000f8, + 0x0e0bf401, +/* 0x080c: memx_info_data */ + 0x03ccc7f1, + 0x0800b7f1, +/* 0x0817: memx_info_train */ + 0xf10b0ef4, + 0xf10bccc7, +/* 0x081f: memx_info_send */ + 0xf50100b7, 0xf8033621, -/* 0x080d: memx_info */ - 0x01c67000, -/* 0x0813: memx_info_data */ - 0xf10e0bf4, - 0xf103ccc7, - 0xf40800b7, -/* 0x081e: memx_info_train */ - 0xc7f10b0e, - 0xb7f10bcc, -/* 0x0826: memx_info_send */ - 0x21f50100, - 0x00f80336, -/* 0x082c: memx_recv */ - 0xf401d6b0, - 0xd6b0980b, - 0xd80bf400, -/* 0x083a: memx_init */ - 0x00f800f8, -/* 0x083c: perf_recv */ -/* 0x083e: perf_init */ - 0x00f800f8, -/* 0x0840: i2c_drive_scl */ - 0xf40036b0, - 0x07f1110b, - 0x04b607e0, - 0x0001d006, - 0x00f804bd, -/* 0x0854: i2c_drive_scl_lo */ - 0x07e407f1, - 0xd00604b6, - 0x04bd0001, -/* 0x0862: i2c_drive_sda */ - 0x36b000f8, - 0x110bf400, - 0x07e007f1, - 0xd00604b6, - 0x04bd0002, -/* 0x0876: i2c_drive_sda_lo */ - 0x07f100f8, - 0x04b607e4, - 0x0002d006, - 0x00f804bd, -/* 0x0884: i2c_sense_scl */ - 0xf10132f4, - 0xb607c437, - 0x33cf0634, - 0x0431fd00, - 0xf4060bf4, -/* 0x089a: i2c_sense_scl_done */ - 0x00f80131, -/* 0x089c: i2c_sense_sda */ - 0xf10132f4, - 0xb607c437, - 0x33cf0634, - 0x0432fd00, - 0xf4060bf4, -/* 0x08b2: i2c_sense_sda_done */ - 0x00f80131, -/* 0x08b4: i2c_raise_scl */ - 0x47f140f9, - 0x37f00898, - 0x4021f501, -/* 0x08c1: i2c_raise_scl_wait */ +/* 0x0825: memx_recv */ + 0x01d6b000, + 0xb0980bf4, + 0x0bf400d6, +/* 0x0833: memx_init */ + 0xf800f8d8, +/* 0x0835: perf_recv */ +/* 0x0837: perf_init */ + 0xf800f800, +/* 0x0839: i2c_drive_scl */ + 0x0036b000, + 0xf1110bf4, + 0xb607e007, + 0x01d00604, + 0xf804bd00, +/* 0x084d: i2c_drive_scl_lo */ + 0xe407f100, + 0x0604b607, + 0xbd0001d0, +/* 0x085b: i2c_drive_sda */ + 0xb000f804, + 0x0bf40036, + 0xe007f111, + 0x0604b607, + 0xbd0002d0, +/* 0x086f: i2c_drive_sda_lo */ + 0xf100f804, + 0xb607e407, + 0x02d00604, + 0xf804bd00, +/* 0x087d: i2c_sense_scl */ + 0x0132f400, + 0x07c437f1, + 0xcf0634b6, + 0x31fd0033, + 0x060bf404, +/* 0x0893: i2c_sense_scl_done */ + 0xf80131f4, +/* 0x0895: i2c_sense_sda */ + 0x0132f400, + 0x07c437f1, + 0xcf0634b6, + 0x32fd0033, + 0x060bf404, +/* 0x08ab: i2c_sense_sda_done */ + 0xf80131f4, +/* 0x08ad: i2c_raise_scl */ + 0xf140f900, + 0xf0089847, + 0x21f50137, +/* 0x08ba: i2c_raise_scl_wait */ + 0xe7f10839, + 0x21f403e8, + 0x7d21f57e, + 0x0901f408, + 0xf40142b6, +/* 0x08ce: i2c_raise_scl_done */ + 0x40fcef1b, +/* 0x08d2: i2c_start */ + 0x21f500f8, + 0x11f4087d, + 0x9521f50d, + 0x0611f408, +/* 0x08e3: i2c_start_rep */ + 0xf0300ef4, + 0x21f50037, + 0x37f00839, + 0x5b21f501, + 0x0076bb08, + 0xf90465b6, + 0x04659450, + 0xbd0256bb, + 0x0475fd50, + 0x21f550fc, + 0x64b608ad, + 0x1f11f404, +/* 0x0910: i2c_start_send */ + 0xf50037f0, + 0xf1085b21, + 0xf41388e7, + 0x37f07e21, + 0x3921f500, + 0x88e7f108, + 0x7e21f413, +/* 0x092c: i2c_start_out */ +/* 0x092e: i2c_stop */ + 0x37f000f8, + 0x3921f500, + 0x0037f008, + 0x085b21f5, + 0x03e8e7f1, + 0xf07e21f4, + 0x21f50137, + 0xe7f10839, + 0x21f41388, + 0x0137f07e, + 0x085b21f5, + 0x1388e7f1, + 0xf87e21f4, +/* 0x0961: i2c_bitw */ + 0x5b21f500, 0xe8e7f108, 0x7e21f403, - 0x088421f5, - 0xb60901f4, - 0x1bf40142, -/* 0x08d5: i2c_raise_scl_done */ - 0xf840fcef, -/* 0x08d9: i2c_start */ - 0x8421f500, - 0x0d11f408, - 0x089c21f5, - 0xf40611f4, -/* 0x08ea: i2c_start_rep */ - 0x37f0300e, - 0x4021f500, - 0x0137f008, - 0x086221f5, 0xb60076bb, 0x50f90465, 0xbb046594, 0x50bd0256, 0xfc0475fd, - 0xb421f550, + 0xad21f550, 0x0464b608, -/* 0x0917: i2c_start_send */ - 0xf01f11f4, - 0x21f50037, - 0xe7f10862, - 0x21f41388, - 0x0037f07e, - 0x084021f5, - 0x1388e7f1, -/* 0x0933: i2c_start_out */ - 0xf87e21f4, -/* 0x0935: i2c_stop */ - 0x0037f000, - 0x084021f5, - 0xf50037f0, - 0xf1086221, - 0xf403e8e7, + 0xf11811f4, + 0xf41388e7, 0x37f07e21, - 0x4021f501, + 0x3921f500, 0x88e7f108, 0x7e21f413, - 0xf50137f0, - 0xf1086221, - 0xf41388e7, - 0x00f87e21, -/* 0x0968: i2c_bitw */ - 0x086221f5, - 0x03e8e7f1, - 0xbb7e21f4, - 0x65b60076, - 0x9450f904, - 0x56bb0465, - 0xfd50bd02, - 0x50fc0475, - 0x08b421f5, - 0xf40464b6, - 0xe7f11811, +/* 0x09a0: i2c_bitw_out */ +/* 0x09a2: i2c_bitr */ + 0x37f000f8, + 0x5b21f501, + 0xe8e7f108, + 0x7e21f403, + 0xb60076bb, + 0x50f90465, + 0xbb046594, + 0x50bd0256, + 0xfc0475fd, + 0xad21f550, + 0x0464b608, + 0xf51b11f4, + 0xf0089521, + 0x21f50037, + 0xe7f10839, 0x21f41388, - 0x0037f07e, - 0x084021f5, - 0x1388e7f1, -/* 0x09a7: i2c_bitw_out */ - 0xf87e21f4, -/* 0x09a9: i2c_bitr */ - 0x0137f000, - 0x086221f5, - 0x03e8e7f1, - 0xbb7e21f4, - 0x65b60076, - 0x9450f904, - 0x56bb0465, - 0xfd50bd02, - 0x50fc0475, - 0x08b421f5, - 0xf40464b6, - 0x21f51b11, - 0x37f0089c, - 0x4021f500, - 0x88e7f108, - 0x7e21f413, - 0xf4013cf0, -/* 0x09ee: i2c_bitr_done */ - 0x00f80131, -/* 0x09f0: i2c_get_byte */ - 0xf00057f0, -/* 0x09f6: i2c_get_byte_next */ - 0x54b60847, + 0x013cf07e, +/* 0x09e7: i2c_bitr_done */ + 0xf80131f4, +/* 0x09e9: i2c_get_byte */ + 0x0057f000, +/* 0x09ef: i2c_get_byte_next */ + 0xb60847f0, + 0x76bb0154, + 0x0465b600, + 0x659450f9, + 0x0256bb04, + 0x75fd50bd, + 0xf550fc04, + 0xb609a221, + 0x11f40464, + 0x0553fd2b, + 0xf40142b6, + 0x37f0d81b, 0x0076bb01, 0xf90465b6, 0x04659450, 0xbd0256bb, 0x0475fd50, 0x21f550fc, - 0x64b609a9, - 0x2b11f404, - 0xb60553fd, - 0x1bf40142, - 0x0137f0d8, - 0xb60076bb, - 0x50f90465, - 0xbb046594, - 0x50bd0256, - 0xfc0475fd, - 0x6821f550, - 0x0464b609, -/* 0x0a40: i2c_get_byte_done */ -/* 0x0a42: i2c_put_byte */ - 0x47f000f8, -/* 0x0a45: i2c_put_byte_next */ - 0x0142b608, - 0xbb3854ff, - 0x65b60076, - 0x9450f904, - 0x56bb0465, - 0xfd50bd02, - 0x50fc0475, - 0x096821f5, - 0xf40464b6, - 0x46b03411, - 0xd81bf400, + 0x64b60961, +/* 0x0a39: i2c_get_byte_done */ +/* 0x0a3b: i2c_put_byte */ + 0xf000f804, +/* 0x0a3e: i2c_put_byte_next */ + 0x42b60847, + 0x3854ff01, 0xb60076bb, 0x50f90465, 0xbb046594, 0x50bd0256, 0xfc0475fd, - 0xa921f550, + 0x6121f550, 0x0464b609, - 0xbb0f11f4, - 0x36b00076, - 0x061bf401, -/* 0x0a9b: i2c_put_byte_done */ - 0xf80132f4, -/* 0x0a9d: i2c_addr */ - 0x0076bb00, + 0xb03411f4, + 0x1bf40046, + 0x0076bbd8, 0xf90465b6, 0x04659450, 0xbd0256bb, 0x0475fd50, 0x21f550fc, - 0x64b608d9, - 0x2911f404, - 0x012ec3e7, - 0xfd0134b6, - 0x76bb0553, + 0x64b609a2, + 0x0f11f404, + 0xb00076bb, + 0x1bf40136, + 0x0132f406, +/* 0x0a94: i2c_put_byte_done */ +/* 0x0a96: i2c_addr */ + 0x76bb00f8, 0x0465b600, 0x659450f9, 0x0256bb04, 0x75fd50bd, 0xf550fc04, - 0xb60a4221, -/* 0x0ae2: i2c_addr_done */ - 0x00f80464, -/* 0x0ae4: i2c_acquire_addr */ - 0xb6f8cec7, - 0xe0b702e4, - 0xee980d1c, -/* 0x0af3: i2c_acquire */ - 0xf500f800, - 0xf40ae421, - 0xd9f00421, - 0x4021f403, -/* 0x0b02: i2c_release */ - 0x21f500f8, - 0x21f40ae4, - 0x03daf004, - 0xf84021f4, -/* 0x0b11: i2c_recv */ - 0x0132f400, - 0xb6f8c1c7, - 0x16b00214, - 0x3a1ff528, - 0xf413a001, - 0x0032980c, - 0x0ccc13a0, - 0xf4003198, - 0xd0f90231, - 0xd0f9e0f9, - 0x000067f1, - 0x100063f1, - 0xbb016792, + 0xb608d221, + 0x11f40464, + 0x2ec3e729, + 0x0134b601, + 0xbb0553fd, 0x65b60076, 0x9450f904, 0x56bb0465, 0xfd50bd02, 0x50fc0475, - 0x0af321f5, - 0xfc0464b6, - 0x00d6b0d0, - 0x00b31bf5, - 0xbb0057f0, + 0x0a3b21f5, +/* 0x0adb: i2c_addr_done */ + 0xf80464b6, +/* 0x0add: i2c_acquire_addr */ + 0xf8cec700, + 0xb702e4b6, + 0x980d1ce0, + 0x00f800ee, +/* 0x0aec: i2c_acquire */ + 0x0add21f5, + 0xf00421f4, + 0x21f403d9, +/* 0x0afb: i2c_release */ + 0xf500f840, + 0xf40add21, + 0xdaf00421, + 0x4021f403, +/* 0x0b0a: i2c_recv */ + 0x32f400f8, + 0xf8c1c701, + 0xb00214b6, + 0x1ff52816, + 0x13a0013a, + 0x32980cf4, + 0xcc13a000, + 0x0031980c, + 0xf90231f4, + 0xf9e0f9d0, + 0x0067f1d0, + 0x0063f100, + 0x01679210, + 0xb60076bb, + 0x50f90465, + 0xbb046594, + 0x50bd0256, + 0xfc0475fd, + 0xec21f550, + 0x0464b60a, + 0xd6b0d0fc, + 0xb31bf500, + 0x0057f000, + 0xb60076bb, + 0x50f90465, + 0xbb046594, + 0x50bd0256, + 0xfc0475fd, + 0x9621f550, + 0x0464b60a, + 0x00d011f5, + 0xbbe0c5c7, 0x65b60076, 0x9450f904, 0x56bb0465, 0xfd50bd02, 0x50fc0475, - 0x0a9d21f5, + 0x0a3b21f5, 0xf50464b6, - 0xc700d011, - 0x76bbe0c5, + 0xf000ad11, + 0x76bb0157, 0x0465b600, 0x659450f9, 0x0256bb04, 0x75fd50bd, 0xf550fc04, - 0xb60a4221, + 0xb60a9621, 0x11f50464, - 0x57f000ad, - 0x0076bb01, - 0xf90465b6, - 0x04659450, - 0xbd0256bb, - 0x0475fd50, - 0x21f550fc, - 0x64b60a9d, - 0x8a11f504, - 0x0076bb00, - 0xf90465b6, - 0x04659450, - 0xbd0256bb, - 0x0475fd50, - 0x21f550fc, - 0x64b609f0, - 0x6a11f404, - 0xbbe05bcb, - 0x65b60076, - 0x9450f904, - 0x56bb0465, - 0xfd50bd02, - 0x50fc0475, - 0x093521f5, - 0xb90464b6, - 0x74bd025b, -/* 0x0c17: i2c_recv_not_rd08 */ - 0xb0430ef4, - 0x1bf401d6, - 0x0057f03d, - 0x0a9d21f5, - 0xc73311f4, - 0x21f5e0c5, - 0x11f40a42, - 0x0057f029, - 0x0a9d21f5, - 0xc71f11f4, - 0x21f5e0b5, - 0x11f40a42, - 0x3521f515, - 0xc774bd09, - 0x1bf408c5, - 0x0232f409, -/* 0x0c57: i2c_recv_not_wr08 */ -/* 0x0c57: i2c_recv_done */ - 0xc7030ef4, - 0x21f5f8ce, - 0xe0fc0b02, - 0x12f4d0fc, - 0x027cb90a, - 0x033621f5, -/* 0x0c6c: i2c_recv_exit */ -/* 0x0c6e: i2c_init */ + 0x76bb008a, + 0x0465b600, + 0x659450f9, + 0x0256bb04, + 0x75fd50bd, + 0xf550fc04, + 0xb609e921, + 0x11f40464, + 0xe05bcb6a, + 0xb60076bb, + 0x50f90465, + 0xbb046594, + 0x50bd0256, + 0xfc0475fd, + 0x2e21f550, + 0x0464b609, + 0xbd025bb9, + 0x430ef474, +/* 0x0c10: i2c_recv_not_rd08 */ + 0xf401d6b0, + 0x57f03d1b, + 0x9621f500, + 0x3311f40a, + 0xf5e0c5c7, + 0xf40a3b21, + 0x57f02911, + 0x9621f500, + 0x1f11f40a, + 0xf5e0b5c7, + 0xf40a3b21, + 0x21f51511, + 0x74bd092e, + 0xf408c5c7, + 0x32f4091b, + 0x030ef402, +/* 0x0c50: i2c_recv_not_wr08 */ +/* 0x0c50: i2c_recv_done */ + 0xf5f8cec7, + 0xfc0afb21, + 0xf4d0fce0, + 0x7cb90a12, + 0x3621f502, +/* 0x0c65: i2c_recv_exit */ +/* 0x0c67: i2c_init */ + 0xf800f803, +/* 0x0c69: test_recv */ + 0xd817f100, + 0x0614b605, + 0xb60011cf, + 0x07f10110, + 0x04b605d8, + 0x0001d006, + 0xe7f104bd, + 0xe3f1d900, + 0x21f5134f, + 0x00f80256, +/* 0x0c90: test_init */ + 0x0800e7f1, + 0x025621f5, +/* 0x0c9a: idle_recv */ 0x00f800f8, -/* 0x0c70: test_recv */ - 0x05d817f1, - 0xcf0614b6, - 0x10b60011, - 0xd807f101, - 0x0604b605, - 0xbd0001d0, - 0x00e7f104, - 0x4fe3f1d9, - 0x5621f513, -/* 0x0c97: test_init */ - 0xf100f802, - 0xf50800e7, - 0xf8025621, -/* 0x0ca1: idle_recv */ -/* 0x0ca3: idle */ - 0xf400f800, - 0x17f10031, - 0x14b605d4, - 0x0011cf06, - 0xf10110b6, - 0xb605d407, - 0x01d00604, -/* 0x0cbf: idle_loop */ - 0xf004bd00, - 0x32f45817, -/* 0x0cc5: idle_proc */ -/* 0x0cc5: idle_proc_exec */ - 0xb910f902, - 0x21f5021e, - 0x10fc033f, - 0xf40911f4, - 0x0ef40231, -/* 0x0cd9: idle_proc_next */ - 0x5810b6ef, - 0xf4061fb8, - 0x02f4e61b, - 0x0028f4dd, - 0x00bb0ef4, +/* 0x0c9c: idle */ + 0xf10031f4, + 0xb605d417, + 0x11cf0614, + 0x0110b600, + 0x05d407f1, + 0xd00604b6, + 0x04bd0001, +/* 0x0cb8: idle_loop */ + 0xf45817f0, +/* 0x0cbe: idle_proc */ +/* 0x0cbe: idle_proc_exec */ + 0x10f90232, + 0xf5021eb9, + 0xfc033f21, + 0x0911f410, + 0xf40231f4, +/* 0x0cd2: idle_proc_next */ + 0x10b6ef0e, + 0x061fb858, + 0xf4e61bf4, + 0x28f4dd02, + 0xbb0ef400, + 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc index ec03f9a4290b..1663bf943d77 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc @@ -82,15 +82,15 @@ memx_train_tail: // $r0 - zero memx_func_enter: #if NVKM_PPWR_CHIPSET == GT215 - movw $r8 0x1610 + mov $r8 0x1610 nv_rd32($r7, $r8) imm32($r6, 0xfffffffc) and $r7 $r6 - movw $r6 0x2 + mov $r6 0x2 or $r7 $r6 nv_wr32($r8, $r7) #else - movw $r6 0x001620 + mov $r6 0x001620 imm32($r7, ~0x00000aa2); nv_rd32($r8, $r6) and $r8 $r7 @@ -101,7 +101,7 @@ memx_func_enter: and $r8 $r7 nv_wr32($r6, $r8)

- movw $r6 0x0026f0 + mov $r6 0x0026f0 nv_rd32($r8, $r6) and $r8 $r7 nv_wr32($r6, $r8) @@ -136,19 +136,19 @@ memx_func_leave: bra nz #memx_func_leave_wait

#if NVKM_PPWR_CHIPSET == GT215 - movw $r8 0x1610 + mov $r8 0x1610 nv_rd32($r7, $r8) imm32($r6, 0xffffffcc) and $r7 $r6 nv_wr32($r8, $r7) #else - movw $r6 0x0026f0 + mov $r6 0x0026f0 imm32($r7, 0x00000001) nv_rd32($r8, $r6) or $r8 $r7 nv_wr32($r6, $r8)

- movw $r6 0x001620 + mov $r6 0x001620 nv_rd32($r8, $r6) or $r8 $r7 nv_wr32($r6, $r8) @@ -177,11 +177,11 @@ memx_func_wait_vblank: bra #memx_func_wait_vblank_fini

memx_func_wait_vblank_head1: - movw $r7 0x20 + mov $r7 0x20 bra #memx_func_wait_vblank_0

memx_func_wait_vblank_head0: - movw $r7 0x8 + mov $r7 0x8

memx_func_wait_vblank_0: nv_iord($r6, NV_PPWR_INPUT) @@ -273,13 +273,13 @@ memx_func_train: // $r5 - outer loop counter // $r6 - inner loop counter // $r7 - entry counter (#memx_train_head + $r7) - movw $r5 0x3 - movw $r7 0x0 + mov $r5 0x3 + mov $r7 0x0

// Read random memory to wake up... things imm32($r9, 0x700000) nv_rd32($r8,$r9) - movw $r14 0x2710 + mov $r14 0x2710 call(nsec)

memx_func_train_loop_outer: @@ -289,9 +289,9 @@ memx_func_train: nv_wr32($r9, $r8) push $r5

- movw $r6 0x0 + mov $r6 0x0 memx_func_train_loop_inner: - movw $r8 0x1111 + mov $r8 0x1111 mulu $r9 $r6 $r8 shl b32 $r8 $r9 0x10 or $r8 $r9 @@ -315,7 +315,7 @@ memx_func_train:

// $r5 - inner inner loop counter // $r9 - result - movw $r5 0 + mov $r5 0 imm32($r9, 0x8300ffff) memx_func_train_loop_4x: imm32($r10, 0x100080)

From: Michal Hocko mhocko@kernel.org

[ Upstream commit 0537250fdc6c876ed4cbbe874c739aebef493ee2 ]

syzbot has noticed that xt_alloc_table_info can allocate a lot of memory. This is an admin only interface but an admin in a namespace is sufficient as well. eacd86ca3b03 ("net/netfilter/x_tables.c: use kvmalloc() in xt_alloc_table_info()") has changed the opencoded kmalloc->vmalloc fallback into kvmalloc. It has dropped __GFP_NORETRY on the way because vmalloc has simply never fully supported __GFP_NORETRY semantic. This is still the case because e.g. page tables backing the vmalloc area are hardcoded GFP_KERNEL.

Revert back to __GFP_NORETRY as a poors man defence against excessively large allocation request here. We will not rule out the OOM killer completely but __GFP_NORETRY should at least stop the large request in most cases.

[akpm@linux-foundation.org: coding-style fixes] Fixes: eacd86ca3b03 ("net/netfilter/x_tables.c: use kvmalloc() in xt_alloc_tableLink: http://lkml.kernel.org/r/20180130140104.GE21609@dhcp22.suse.cz Signed-off-by: Michal Hocko mhocko@suse.com Acked-by: Florian Westphal fw@strlen.de Reviewed-by: Andrew Morton akpm@linux-foundation.org Cc: David S. Miller davem@davemloft.net Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- net/netfilter/x_tables.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index d7070d18db20..d4442aa8fd54 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1008,7 +1008,12 @@ struct xt_table_info *xt_alloc_table_info(unsigned int size) if ((size >> PAGE_SHIFT) + 2 > totalram_pages) return NULL;

- info = kvmalloc(sz, GFP_KERNEL); + /* __GFP_NORETRY is not fully supported by kvmalloc but it should + * work reasonably well if sz is too large and bail out rather + * than shoot all processes down before realizing there is nothing + * more to reclaim. + */ + info = kvmalloc(sz, GFP_KERNEL | __GFP_NORETRY); if (!info) return NULL;

From: Nikolay Borisov nborisov@suse.com

[ Upstream commit 952bd3db0dada9994fa7edd891178075abcc045d ]

Running generic/019 with qgroups on the scratch device enabled is almost guaranteed to trigger the BUG_ON in btrfs_free_tree_block. It's supposed to trigger only on -ENOMEM, in reality, however, it's possible to get -EIO from btrfs_qgroup_trace_extent_post. This function just finds the roots of the extent being tracked and sets the qrecord->old_roots list. If this operation fails nothing critical happens except the quota accounting can be considered wrong. In such case just set the INCONSISTENT flag for the quota and print a warning, rather than killing off the system. Additionally, it's possible to trigger a BUG_ON in btrfs_truncate_inode_items as well.

Signed-off-by: Nikolay Borisov nborisov@suse.com Reviewed-by: Qu Wenruo wqu@suse.com [ error message adjustments ] Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- fs/btrfs/delayed-ref.c | 3 ++- fs/btrfs/qgroup.c | 9 +++++++-- 2 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 83be8f9fd906..fa552a5ac103 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -821,7 +821,8 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info, spin_unlock(&delayed_refs->lock);

if (qrecord_inserted) - return btrfs_qgroup_trace_extent_post(fs_info, record); + btrfs_qgroup_trace_extent_post(fs_info, record); + return 0;

free_head_ref: diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 168fd03ca3ac..388731481e9d 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1442,8 +1442,13 @@ int btrfs_qgroup_trace_extent_post(struct btrfs_fs_info *fs_info, int ret;

ret = btrfs_find_all_roots(NULL, fs_info, bytenr, 0, &old_root, false); - if (ret < 0) - return ret; + if (ret < 0) { + fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; + btrfs_warn(fs_info, +"error accounting new delayed refs extent (err code: %d), quota inconsistent", + ret); + return 0; + }

/* * Here we don't need to get the lock of

From: Arnd Bergmann arnd@arndb.de

[ Upstream commit ebfc15019cfa72496c674ffcb0b8ef10790dcddc ]

In some configurations, 'partial' does not get initialized, as shown by this gcc-8 warning:

arch/x86/kernel/dumpstack.c: In function 'show_trace_log_lvl': arch/x86/kernel/dumpstack.c:156:4: error: 'partial' may be used uninitialized in this function [-Werror=maybe-uninitialized] show_regs_if_on_stack(&stack_info, regs, partial); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

This initializes it to false, to get the previous behavior in this case.

Fixes: a9cdbe72c4e8 ("x86/dumpstack: Fix partial register dumps") Signed-off-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Thomas Gleixner tglx@linutronix.de Cc: Andi Kleen ak@linux.intel.com Cc: Nicolas Pitre nico@linaro.org Cc: Peter Zijlstra peterz@infradead.org Cc: Dave Hansen dave.hansen@linux.intel.com Cc: Andy Lutomirski luto@kernel.org Cc: Josh Poimboeuf jpoimboe@redhat.com Cc: Borislav Petkov bpetkov@suse.de Cc: Vlastimil Babka vbabka@suse.cz Link: https://lkml.kernel.org/r/20180202145634.200291-1-arnd@arndb.de Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- arch/x86/kernel/dumpstack.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index afbecff161d1..a2d8a3908670 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -109,7 +109,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, struct stack_info stack_info = {0}; unsigned long visit_mask = 0; int graph_idx = 0; - bool partial; + bool partial = false;

printk("%sCall Trace:\n", log_lvl);

From: Chen Yu yu.c.chen@intel.com

[ Upstream commit ba1edb9a5125a617d612f98eead14b9b84e75c3a ]

The following warning was triggered after resumed from S3 - if all the nonboot CPUs were put offline before suspend:

[ 1840.329515] unchecked MSR access error: RDMSR from 0x771 at rIP: 0xffffffff86061e3a (native_read_msr+0xa/0x30) [ 1840.329516] Call Trace: [ 1840.329521] __rdmsr_on_cpu+0x33/0x50 [ 1840.329525] generic_exec_single+0x81/0xb0 [ 1840.329527] smp_call_function_single+0xd2/0x100 [ 1840.329530] ? acpi_ds_result_pop+0xdd/0xf2 [ 1840.329532] ? acpi_ds_create_operand+0x215/0x23c [ 1840.329534] rdmsrl_on_cpu+0x57/0x80 [ 1840.329536] ? cpumask_next+0x1b/0x20 [ 1840.329538] ? rdmsrl_on_cpu+0x57/0x80 [ 1840.329541] intel_pstate_update_perf_limits+0xf3/0x220 [ 1840.329544] ? notifier_call_chain+0x4a/0x70 [ 1840.329546] intel_pstate_set_policy+0x4e/0x150 [ 1840.329548] cpufreq_set_policy+0xcd/0x2f0 [ 1840.329550] cpufreq_update_policy+0xb2/0x130 [ 1840.329552] ? cpufreq_update_policy+0x130/0x130 [ 1840.329556] acpi_processor_ppc_has_changed+0x65/0x80 [ 1840.329558] acpi_processor_notify+0x80/0x100 [ 1840.329561] acpi_ev_notify_dispatch+0x44/0x5c [ 1840.329563] acpi_os_execute_deferred+0x14/0x20 [ 1840.329565] process_one_work+0x193/0x3c0 [ 1840.329567] worker_thread+0x35/0x3b0 [ 1840.329569] kthread+0x125/0x140 [ 1840.329571] ? process_one_work+0x3c0/0x3c0 [ 1840.329572] ? kthread_park+0x60/0x60 [ 1840.329575] ? do_syscall_64+0x67/0x180 [ 1840.329577] ret_from_fork+0x25/0x30 [ 1840.329585] unchecked MSR access error: WRMSR to 0x774 (tried to write 0x0000000000000000) at rIP: 0xffffffff86061f78 (native_write_msr+0x8/0x30) [ 1840.329586] Call Trace: [ 1840.329587] __wrmsr_on_cpu+0x37/0x40 [ 1840.329589] generic_exec_single+0x81/0xb0 [ 1840.329592] smp_call_function_single+0xd2/0x100 [ 1840.329594] ? acpi_ds_create_operand+0x215/0x23c [ 1840.329595] ? cpumask_next+0x1b/0x20 [ 1840.329597] wrmsrl_on_cpu+0x57/0x70 [ 1840.329598] ? rdmsrl_on_cpu+0x57/0x80 [ 1840.329599] ? wrmsrl_on_cpu+0x57/0x70 [ 1840.329602] intel_pstate_hwp_set+0xd3/0x150 [ 1840.329604] intel_pstate_set_policy+0x119/0x150 [ 1840.329606] cpufreq_set_policy+0xcd/0x2f0 [ 1840.329607] cpufreq_update_policy+0xb2/0x130 [ 1840.329610] ? cpufreq_update_policy+0x130/0x130 [ 1840.329613] acpi_processor_ppc_has_changed+0x65/0x80 [ 1840.329615] acpi_processor_notify+0x80/0x100 [ 1840.329617] acpi_ev_notify_dispatch+0x44/0x5c [ 1840.329619] acpi_os_execute_deferred+0x14/0x20 [ 1840.329620] process_one_work+0x193/0x3c0 [ 1840.329622] worker_thread+0x35/0x3b0 [ 1840.329624] kthread+0x125/0x140 [ 1840.329625] ? process_one_work+0x3c0/0x3c0 [ 1840.329626] ? kthread_park+0x60/0x60 [ 1840.329628] ? do_syscall_64+0x67/0x180 [ 1840.329631] ret_from_fork+0x25/0x30

This is because if there's only one online CPU, the MSR_PM_ENABLE (package wide)can not be enabled after resumed, due to intel_pstate_hwp_enable() will only be invoked on AP's online process after resumed - if there's no AP online, the HWP remains disabled after resumed (BIOS has disabled it in S3). Then if there comes a _PPC change notification which touches HWP register during this stage, the warning is triggered.

Since we don't call acpi_processor_register_performance() when HWP is enabled, the pr->performance will be NULL. When this is NULL we don't need to do _PPC change notification.

Reported-by: Doug Smythies dsmythies@telus.net Suggested-by: Srinivas Pandruvada srinivas.pandruvada@linux.intel.com Signed-off-by: Yu Chen yu.c.chen@intel.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/acpi/processor_perflib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c index 18b72eec3507..c7cf48ad5cb9 100644 --- a/drivers/acpi/processor_perflib.c +++ b/drivers/acpi/processor_perflib.c @@ -159,7 +159,7 @@ void acpi_processor_ppc_has_changed(struct acpi_processor *pr, int event_flag) { int ret;

- if (ignore_ppc) { + if (ignore_ppc || !pr->performance) { /* * Only when it is notification event, the _OST object * will be evaluated. Otherwise it is skipped.

From: Yonghong Song yhs@fb.com

[ Upstream commit 09584b406742413ac4c8d7e030374d4daa045b69 ]

With CONFIG_BPF_JIT_ALWAYS_ON is defined in the config file, tools/testing/selftests/bpf/test_kmod.sh failed like below: [root@localhost bpf]# ./test_kmod.sh sysctl: setting key "net.core.bpf_jit_enable": Invalid argument [ JIT enabled:0 hardened:0 ] [ 132.175681] test_bpf: #297 BPF_MAXINSNS: Jump, gap, jump, ... FAIL to prog_create err=-524 len=4096 [ 132.458834] test_bpf: Summary: 348 PASSED, 1 FAILED, [340/340 JIT'ed] [ JIT enabled:1 hardened:0 ] [ 133.456025] test_bpf: #297 BPF_MAXINSNS: Jump, gap, jump, ... FAIL to prog_create err=-524 len=4096 [ 133.730935] test_bpf: Summary: 348 PASSED, 1 FAILED, [340/340 JIT'ed] [ JIT enabled:1 hardened:1 ] [ 134.769730] test_bpf: #297 BPF_MAXINSNS: Jump, gap, jump, ... FAIL to prog_create err=-524 len=4096 [ 135.050864] test_bpf: Summary: 348 PASSED, 1 FAILED, [340/340 JIT'ed] [ JIT enabled:1 hardened:2 ] [ 136.442882] test_bpf: #297 BPF_MAXINSNS: Jump, gap, jump, ... FAIL to prog_create err=-524 len=4096 [ 136.821810] test_bpf: Summary: 348 PASSED, 1 FAILED, [340/340 JIT'ed] [root@localhost bpf]#

The test_kmod.sh load/remove test_bpf.ko multiple times with different settings for sysctl net.core.bpf_jit_{enable,harden}. The failed test #297 of test_bpf.ko is designed such that JIT always fails.

Commit 290af86629b2 (bpf: introduce BPF_JIT_ALWAYS_ON config) introduced the following tightening logic: ... if (!bpf_prog_is_dev_bound(fp->aux)) { fp = bpf_int_jit_compile(fp); #ifdef CONFIG_BPF_JIT_ALWAYS_ON if (!fp->jited) { *err = -ENOTSUPP; return fp; } #endif ... With this logic, Test #297 always gets return value -ENOTSUPP when CONFIG_BPF_JIT_ALWAYS_ON is defined, causing the test failure.

This patch fixed the failure by marking Test #297 as expected failure when CONFIG_BPF_JIT_ALWAYS_ON is defined.

Fixes: 290af86629b2 (bpf: introduce BPF_JIT_ALWAYS_ON config) Signed-off-by: Yonghong Song yhs@fb.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- lib/test_bpf.c | 31 ++++++++++++++++++++++++++----- 1 file changed, 26 insertions(+), 5 deletions(-)

diff --git a/lib/test_bpf.c b/lib/test_bpf.c index f369889e521d..8076e693f86e 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -83,6 +83,7 @@ struct bpf_test { __u32 result; } test[MAX_SUBTESTS]; int (*fill_helper)(struct bpf_test *self); + int expected_errcode; /* used when FLAG_EXPECTED_FAIL is set in the aux */ __u8 frag_data[MAX_DATA]; int stack_depth; /* for eBPF only, since tests don't call verifier */ }; @@ -2022,7 +2023,9 @@ static struct bpf_test tests[] = { }, CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL, { }, - { } + { }, + .fill_helper = NULL, + .expected_errcode = -EINVAL, }, { "check: div_k_0", @@ -2032,7 +2035,9 @@ static struct bpf_test tests[] = { }, CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL, { }, - { } + { }, + .fill_helper = NULL, + .expected_errcode = -EINVAL, }, { "check: unknown insn", @@ -2043,7 +2048,9 @@ static struct bpf_test tests[] = { }, CLASSIC | FLAG_EXPECTED_FAIL, { }, - { } + { }, + .fill_helper = NULL, + .expected_errcode = -EINVAL, }, { "check: out of range spill/fill", @@ -2053,7 +2060,9 @@ static struct bpf_test tests[] = { }, CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL, { }, - { } + { }, + .fill_helper = NULL, + .expected_errcode = -EINVAL, }, { "JUMPS + HOLES", @@ -2145,6 +2154,8 @@ static struct bpf_test tests[] = { CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL, { }, { }, + .fill_helper = NULL, + .expected_errcode = -EINVAL, }, { "check: LDX + RET X", @@ -2155,6 +2166,8 @@ static struct bpf_test tests[] = { CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL, { }, { }, + .fill_helper = NULL, + .expected_errcode = -EINVAL, }, { /* Mainly checking JIT here. */ "M[]: alt STX + LDX", @@ -2329,6 +2342,8 @@ static struct bpf_test tests[] = { CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL, { }, { }, + .fill_helper = NULL, + .expected_errcode = -EINVAL, }, { /* Passes checker but fails during runtime. */ "LD [SKF_AD_OFF-1]", @@ -5391,6 +5406,7 @@ static struct bpf_test tests[] = { { }, { }, .fill_helper = bpf_fill_maxinsns4, + .expected_errcode = -EINVAL, }, { /* Mainly checking JIT here. */ "BPF_MAXINSNS: Very long jump", @@ -5446,10 +5462,15 @@ static struct bpf_test tests[] = { { "BPF_MAXINSNS: Jump, gap, jump, ...", { }, +#ifdef CONFIG_BPF_JIT_ALWAYS_ON + CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL, +#else CLASSIC | FLAG_NO_DATA, +#endif { }, { { 0, 0xababcbac } }, .fill_helper = bpf_fill_maxinsns11, + .expected_errcode = -ENOTSUPP, }, { "BPF_MAXINSNS: ld_abs+get_processor_id", @@ -6236,7 +6257,7 @@ static struct bpf_prog *generate_filter(int which, int *err)

*err = bpf_prog_create(&fp, &fprog); if (tests[which].aux & FLAG_EXPECTED_FAIL) { - if (*err == -EINVAL) { + if (*err == tests[which].expected_errcode) { pr_cont("PASS\n"); /* Verifier rejected filter as expected. */ *err = 0;

From: James Hogan jhogan@kernel.org

[ Upstream commit 9a9ab3078e2744a1a55163cfaec73a5798aae33e ]

We now have a platform (Ranchu) in the "generic" platform which matches based on the FDT compatible string using mips_machine_is_compatible(), however that function doesn't stop at a blank struct of_device_id::compatible as that is an array in the struct, not a pointer to a string.

Fix the loop completion to check the first byte of the compatible array rather than the address of the compatible array in the struct.

Fixes: eed0eabd12ef ("MIPS: generic: Introduce generic DT-based board support") Signed-off-by: James Hogan jhogan@kernel.org Reviewed-by: Paul Burton paul.burton@mips.com Reviewed-by: Matt Redfearn matt.redfearn@mips.com Cc: Ralf Baechle ralf@linux-mips.org Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/18580/ Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- arch/mips/include/asm/machine.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/include/asm/machine.h b/arch/mips/include/asm/machine.h index e0d9b373d415..f83879dadd1e 100644 --- a/arch/mips/include/asm/machine.h +++ b/arch/mips/include/asm/machine.h @@ -52,7 +52,7 @@ mips_machine_is_compatible(const struct mips_machine *mach, const void *fdt) if (!mach->matches) return NULL;

- for (match = mach->matches; match->compatible; match++) { + for (match = mach->matches; match->compatible[0]; match++) { if (fdt_node_check_compatible(fdt, 0, match->compatible) == 0) return match; }

From: Jiri Olsa jolsa@kernel.org

[ Upstream commit f290aa1ffa45ed7e37599840878b4dae68269ee1 ]

Stephan reported we don't unset PERIOD sample type when --no-period is specified. Adding the unset check and reset PERIOD if --no-period is specified.

Committer notes:

Check the sample_type, it shouldn't have PERF_SAMPLE_PERIOD there when --no-period is used.

Before:

# perf record --no-period sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.018 MB perf.data (7 samples) ] # perf evlist -v cycles:ppp: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, precise_ip: 3, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 #

After:

[root@jouet ~]# perf record --no-period sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.019 MB perf.data (17 samples) ] [root@jouet ~]# perf evlist -v cycles:ppp: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, precise_ip: 3, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 [root@jouet ~]#

Reported-by: Stephane Eranian eranian@google.com Signed-off-by: Jiri Olsa jolsa@kernel.org Tested-by: Arnaldo Carvalho de Melo acme@redhat.com Tested-by: Stephane Eranian eranian@google.com Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Andi Kleen ak@linux.intel.com Cc: David Ahern dsahern@gmail.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Link: http://lkml.kernel.org/r/20180201083812.11359-3-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- tools/perf/builtin-record.c | 3 ++- tools/perf/perf.h | 1 + tools/perf/util/evsel.c | 11 ++++++++--- 3 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 003255910c05..2ccb709c0b08 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1533,7 +1533,8 @@ static struct option __record_options[] = { OPT_BOOLEAN_SET('T', "timestamp", &record.opts.sample_time, &record.opts.sample_time_set, "Record the sample timestamps"), - OPT_BOOLEAN('P', "period", &record.opts.period, "Record the sample period"), + OPT_BOOLEAN_SET('P', "period", &record.opts.period, &record.opts.period_set, + "Record the sample period"), OPT_BOOLEAN('n', "no-samples", &record.opts.no_samples, "don't sample"), OPT_BOOLEAN_SET('N', "no-buildid-cache", &record.no_buildid_cache, diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 2357f4ccc9c7..cfe46236a5e5 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -50,6 +50,7 @@ struct record_opts { bool sample_time_set; bool sample_cpu; bool period; + bool period_set; bool running_time; bool full_auxtrace; bool auxtrace_snapshot_mode; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 784d852c91cc..d23a8c51b307 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -948,9 +948,6 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, if (target__has_cpu(&opts->target) || opts->sample_cpu) perf_evsel__set_sample_bit(evsel, CPU);

- if (opts->period) - perf_evsel__set_sample_bit(evsel, PERIOD); - /* * When the user explicitly disabled time don't force it here. */ @@ -1052,6 +1049,14 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, apply_config_terms(evsel, opts);

evsel->ignore_missing_thread = opts->ignore_missing_thread; + + /* The --period option takes the precedence. */ + if (opts->period_set) { + if (opts->period) + perf_evsel__set_sample_bit(evsel, PERIOD); + else + perf_evsel__reset_sample_bit(evsel, PERIOD); + } }

static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)

From: Ross Lagerwall ross.lagerwall@citrix.com

[ Upstream commit f599c64fdf7d9c108e8717fb04bc41c680120da4 ]

When a netfront device is set up it registers a netdev fairly early on, before it has set up the queues and is actually usable. A userspace tool like NetworkManager will immediately try to open it and access its state as soon as it appears. The bug can be reproduced by hotplugging VIFs until the VM runs out of grant refs. It registers the netdev but fails to set up any queues (since there are no more grant refs). In the meantime, NetworkManager opens the device and the kernel crashes trying to access the queues (of which there are none).

Fix this in two ways: * For initial setup, register the netdev much later, after the queues are setup. This avoids the race entirely. * During a suspend/resume cycle, the frontend reconnects to the backend and the queues are recreated. It is possible (though highly unlikely) to race with something opening the device and accessing the queues after they have been destroyed but before they have been recreated. Extend the region covered by the rtnl semaphore to protect against this race. There is a possibility that we fail to recreate the queues so check for this in the open function.

Signed-off-by: Ross Lagerwall ross.lagerwall@citrix.com Reviewed-by: Boris Ostrovsky boris.ostrovsky@oracle.com Signed-off-by: Juergen Gross jgross@suse.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/net/xen-netfront.c | 46 ++++++++++++++++++++++++---------------------- 1 file changed, 24 insertions(+), 22 deletions(-)

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 9bd7ddeeb6a5..8328d395e332 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -351,6 +351,9 @@ static int xennet_open(struct net_device *dev) unsigned int i = 0; struct netfront_queue *queue = NULL;

+ if (!np->queues) + return -ENODEV; + for (i = 0; i < num_queues; ++i) { queue = &np->queues[i]; napi_enable(&queue->napi); @@ -1358,18 +1361,8 @@ static int netfront_probe(struct xenbus_device *dev, #ifdef CONFIG_SYSFS info->netdev->sysfs_groups[0] = &xennet_dev_group; #endif - err = register_netdev(info->netdev); - if (err) { - pr_warn("%s: register_netdev err=%d\n", __func__, err); - goto fail; - }

return 0; - - fail: - xennet_free_netdev(netdev); - dev_set_drvdata(&dev->dev, NULL); - return err; }

static void xennet_end_access(int ref, void *page) @@ -1737,8 +1730,6 @@ static void xennet_destroy_queues(struct netfront_info *info) { unsigned int i;

- rtnl_lock(); - for (i = 0; i < info->netdev->real_num_tx_queues; i++) { struct netfront_queue *queue = &info->queues[i];

@@ -1747,8 +1738,6 @@ static void xennet_destroy_queues(struct netfront_info *info) netif_napi_del(&queue->napi); }

- rtnl_unlock(); - kfree(info->queues); info->queues = NULL; } @@ -1764,8 +1753,6 @@ static int xennet_create_queues(struct netfront_info *info, if (!info->queues) return -ENOMEM;

- rtnl_lock(); - for (i = 0; i < *num_queues; i++) { struct netfront_queue *queue = &info->queues[i];

@@ -1774,7 +1761,7 @@ static int xennet_create_queues(struct netfront_info *info,

ret = xennet_init_queue(queue); if (ret < 0) { - dev_warn(&info->netdev->dev, + dev_warn(&info->xbdev->dev, "only created %d queues\n", i); *num_queues = i; break; @@ -1788,10 +1775,8 @@ static int xennet_create_queues(struct netfront_info *info,

netif_set_real_num_tx_queues(info->netdev, *num_queues);

- rtnl_unlock(); - if (*num_queues == 0) { - dev_err(&info->netdev->dev, "no queues\n"); + dev_err(&info->xbdev->dev, "no queues\n"); return -EINVAL; } return 0; @@ -1828,6 +1813,7 @@ static int talk_to_netback(struct xenbus_device *dev, goto out; }

+ rtnl_lock(); if (info->queues) xennet_destroy_queues(info);

@@ -1838,6 +1824,7 @@ static int talk_to_netback(struct xenbus_device *dev, info->queues = NULL; goto out; } + rtnl_unlock();

/* Create shared ring, alloc event channel -- for each queue */ for (i = 0; i < num_queues; ++i) { @@ -1934,8 +1921,10 @@ abort_transaction_no_dev_fatal: xenbus_transaction_end(xbt, 1); destroy_ring: xennet_disconnect_backend(info); + rtnl_lock(); xennet_destroy_queues(info); out: + rtnl_unlock(); device_unregister(&dev->dev); return err; } @@ -1965,6 +1954,15 @@ static int xennet_connect(struct net_device *dev) netdev_update_features(dev); rtnl_unlock();

+ if (dev->reg_state == NETREG_UNINITIALIZED) { + err = register_netdev(dev); + if (err) { + pr_warn("%s: register_netdev err=%d\n", __func__, err); + device_unregister(&np->xbdev->dev); + return err; + } + } + /* * All public and private state should now be sane. Get * ready to start sending and receiving packets and give the driver @@ -2150,10 +2148,14 @@ static int xennet_remove(struct xenbus_device *dev)

xennet_disconnect_backend(info);

- unregister_netdev(info->netdev); + if (info->netdev->reg_state == NETREG_REGISTERED) + unregister_netdev(info->netdev);

- if (info->queues) + if (info->queues) { + rtnl_lock(); xennet_destroy_queues(info); + rtnl_unlock(); + } xennet_free_netdev(info->netdev);

return 0;

From: Ross Lagerwall ross.lagerwall@citrix.com

[ Upstream commit 3ac7292a25db1c607a50752055a18aba32ac2176 ]

The page given to gnttab_end_foreign_access() to free could be a compound page so use put_page() instead of free_page() since it can handle both compound and single pages correctly.

This bug was discovered when migrating a Xen VM with several VIFs and CONFIG_DEBUG_VM enabled. It hits a BUG usually after fewer than 10 iterations. All netfront devices disconnect from the backend during a suspend/resume and this will call gnttab_end_foreign_access() if a netfront queue has an outstanding skb. The mismatch between calling get_page() and free_page() on a compound page causes a reference counting error which is detected when DEBUG_VM is enabled.

Signed-off-by: Ross Lagerwall ross.lagerwall@citrix.com Reviewed-by: Boris Ostrovsky boris.ostrovsky@oracle.com Signed-off-by: Juergen Gross jgross@suse.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/xen/grant-table.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index f45114fd8e1e..27be107d6480 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -382,7 +382,7 @@ static void gnttab_handle_deferred(struct timer_list *unused) if (entry->page) { pr_debug("freeing g.e. %#x (pfn %#lx)\n", entry->ref, page_to_pfn(entry->page)); - __free_page(entry->page); + put_page(entry->page); } else pr_info("freeing g.e. %#x\n", entry->ref); kfree(entry); @@ -438,7 +438,7 @@ void gnttab_end_foreign_access(grant_ref_t ref, int readonly, if (gnttab_end_foreign_access_ref(ref, readonly)) { put_free_entry(ref); if (page != 0) - free_page(page); + put_page(virt_to_page(page)); } else gnttab_add_deferred(ref, readonly, page ? virt_to_page(page) : NULL);

From: Guanglei Li guanglei.li@oracle.com

[ Upstream commit 2c0aa08631b86a4678dbc93b9caa5248014b4458 ]

Scenario: 1. Port down and do fail over 2. Ap do rds_bind syscall

PID: 47039 TASK: ffff89887e2fe640 CPU: 47 COMMAND: "kworker/u:6" #0 [ffff898e35f159f0] machine_kexec at ffffffff8103abf9 #1 [ffff898e35f15a60] crash_kexec at ffffffff810b96e3 #2 [ffff898e35f15b30] oops_end at ffffffff8150f518 #3 [ffff898e35f15b60] no_context at ffffffff8104854c #4 [ffff898e35f15ba0] __bad_area_nosemaphore at ffffffff81048675 #5 [ffff898e35f15bf0] bad_area_nosemaphore at ffffffff810487d3 #6 [ffff898e35f15c00] do_page_fault at ffffffff815120b8 #7 [ffff898e35f15d10] page_fault at ffffffff8150ea95 [exception RIP: unknown or invalid address] RIP: 0000000000000000 RSP: ffff898e35f15dc8 RFLAGS: 00010282 RAX: 00000000fffffffe RBX: ffff889b77f6fc00 RCX:ffffffff81c99d88 RDX: 0000000000000000 RSI: ffff896019ee08e8 RDI:ffff889b77f6fc00 RBP: ffff898e35f15df0 R8: ffff896019ee08c8 R9:0000000000000000 R10: 0000000000000400 R11: 0000000000000000 R12:ffff896019ee08c0 R13: ffff889b77f6fe68 R14: ffffffff81c99d80 R15: ffffffffa022a1e0 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018 #8 [ffff898e35f15dc8] cma_ndev_work_handler at ffffffffa022a228 [rdma_cm] #9 [ffff898e35f15df8] process_one_work at ffffffff8108a7c6 #10 [ffff898e35f15e58] worker_thread at ffffffff8108bda0 #11 [ffff898e35f15ee8] kthread at ffffffff81090fe6

PID: 45659 TASK: ffff880d313d2500 CPU: 31 COMMAND: "oracle_45659_ap" #0 [ffff881024ccfc98] __schedule at ffffffff8150bac4 #1 [ffff881024ccfd40] schedule at ffffffff8150c2cf #2 [ffff881024ccfd50] __mutex_lock_slowpath at ffffffff8150cee7 #3 [ffff881024ccfdc0] mutex_lock at ffffffff8150cdeb #4 [ffff881024ccfde0] rdma_destroy_id at ffffffffa022a027 [rdma_cm] #5 [ffff881024ccfe10] rds_ib_laddr_check at ffffffffa0357857 [rds_rdma] #6 [ffff881024ccfe50] rds_trans_get_preferred at ffffffffa0324c2a [rds] #7 [ffff881024ccfe80] rds_bind at ffffffffa031d690 [rds] #8 [ffff881024ccfeb0] sys_bind at ffffffff8142a670

PID: 45659 PID: 47039 rds_ib_laddr_check /* create id_priv with a null event_handler */ rdma_create_id rdma_bind_addr cma_acquire_dev /* add id_priv to cma_dev->id_list */ cma_attach_to_dev cma_ndev_work_handler /* event_hanlder is null */ id_priv->id.event_handler

Signed-off-by: Guanglei Li guanglei.li@oracle.com Signed-off-by: Honglei Wang honglei.wang@oracle.com Reviewed-by: Junxiao Bi junxiao.bi@oracle.com Reviewed-by: Yanjun Zhu yanjun.zhu@oracle.com Reviewed-by: Leon Romanovsky leonro@mellanox.com Acked-by: Santosh Shilimkar santosh.shilimkar@oracle.com Acked-by: Doug Ledford dledford@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- net/rds/ib.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/rds/ib.c b/net/rds/ib.c index 36dd2099048a..04da68e5dbe6 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -347,7 +347,8 @@ static int rds_ib_laddr_check(struct net *net, __be32 addr) /* Create a CMA ID and try to bind it. This catches both * IB and iWARP capable NICs. */ - cm_id = rdma_create_id(&init_net, NULL, NULL, RDMA_PS_TCP, IB_QPT_RC); + cm_id = rdma_create_id(&init_net, rds_rdma_cm_event_handler, + NULL, RDMA_PS_TCP, IB_QPT_RC); if (IS_ERR(cm_id)) return PTR_ERR(cm_id);

From: Alexey Dobriyan adobriyan@gmail.com

[ Upstream commit ac7f1061c2c11bb8936b1b6a94cdb48de732f7a4 ]

Current code does:

if (sscanf(dentry->d_name.name, "%lx-%lx", start, end) != 2)

However sscanf() is broken garbage.

It silently accepts whitespace between format specifiers (did you know that?).

It silently accepts valid strings which result in integer overflow.

Do not use sscanf() for any even remotely reliable parsing code.

OK # readlink '/proc/1/map_files/55a23af39000-55a23b05b000' /lib/systemd/systemd

broken # readlink '/proc/1/map_files/ 55a23af39000-55a23b05b000' /lib/systemd/systemd

broken # readlink '/proc/1/map_files/55a23af39000-55a23b05b000 ' /lib/systemd/systemd

very broken # readlink '/proc/1/map_files/1000000000000000055a23af39000-55a23b05b000' /lib/systemd/systemd

Andrei said:

: This patch breaks criu. It was a bug in criu. And this bug is on a minor : path, which works when memfd_create() isn't available. It is a reason why : I ask to not backport this patch to stable kernels. : : In CRIU this bug can be triggered, only if this patch will be backported : to a kernel which version is lower than v3.16.

Link: http://lkml.kernel.org/r/20171120212706.GA14325@avx2 Signed-off-by: Alexey Dobriyan adobriyan@gmail.com Cc: Pavel Emelyanov xemul@openvz.org Cc: Andrei Vagin avagin@virtuozzo.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- fs/proc/base.c | 29 ++++++++++++++++++++++++++++- 1 file changed, 28 insertions(+), 1 deletion(-)

diff --git a/fs/proc/base.c b/fs/proc/base.c index 60316b52d659..7165e7419bd0 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -100,6 +100,8 @@ #include "internal.h" #include "fd.h"

+#include "../../lib/kstrtox.h" + /* NOTE: * Implementing inode permission operations in /proc is almost * certainly an error. Permission checks need to happen during @@ -1907,8 +1909,33 @@ end_instantiate: static int dname_to_vma_addr(struct dentry *dentry, unsigned long *start, unsigned long *end) { - if (sscanf(dentry->d_name.name, "%lx-%lx", start, end) != 2) + const char *str = dentry->d_name.name; + unsigned long long sval, eval; + unsigned int len; + + len = _parse_integer(str, 16, &sval); + if (len & KSTRTOX_OVERFLOW) + return -EINVAL; + if (sval != (unsigned long)sval) + return -EINVAL; + str += len; + + if (*str != '-') return -EINVAL; + str++; + + len = _parse_integer(str, 16, &eval); + if (len & KSTRTOX_OVERFLOW) + return -EINVAL; + if (eval != (unsigned long)eval) + return -EINVAL; + str += len; + + if (*str != '\0') + return -EINVAL; + + *start = sval; + *end = eval;

return 0; }

From: Ulf Hansson ulf.hansson@linaro.org

[ Upstream commit a3381e3a65cbaf612c8f584906c4dba27e84267c ]

Commit b539cc82d493 (PM / Domains: Ignore domain-idle-states that are not compatible), made it possible to ignore non-compatible domain-idle-states OF nodes. However, in case that happens while doing the OF parsing, the number of elements in the allocated array would exceed the numbers actually needed, thus wasting memory.

Fix this by pre-iterating the genpd OF node and counting the number of compatible domain-idle-states nodes, before doing the allocation. While doing this, it makes sense to rework the code a bit to avoid open coding, of parts responsible for the OF node iteration.

Let's also take the opportunity to clarify the function header for of_genpd_parse_idle_states(), about what is being returned in case of errors.

Fixes: b539cc82d493 (PM / Domains: Ignore domain-idle-states that are not compatible) Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Reviewed-by: Lina Iyer ilina@codeaurora.org Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/base/power/domain.c | 76 +++++++++++++++++++++++++++------------------ 1 file changed, 45 insertions(+), 31 deletions(-)

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 0c80bea05bcb..69520ad6f169 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -2293,6 +2293,38 @@ static int genpd_parse_state(struct genpd_power_state *genpd_state, return 0; }

+static int genpd_iterate_idle_states(struct device_node *dn, + struct genpd_power_state *states) +{ + int ret; + struct of_phandle_iterator it; + struct device_node *np; + int i = 0; + + ret = of_count_phandle_with_args(dn, "domain-idle-states", NULL); + if (ret <= 0) + return ret; + + /* Loop over the phandles until all the requested entry is found */ + of_for_each_phandle(&it, ret, dn, "domain-idle-states", NULL, 0) { + np = it.node; + if (!of_match_node(idle_state_match, np)) + continue; + if (states) { + ret = genpd_parse_state(&states[i], np); + if (ret) { + pr_err("Parsing idle state node %pOF failed with err %d\n", + np, ret); + of_node_put(np); + return ret; + } + } + i++; + } + + return i; +} + /** * of_genpd_parse_idle_states: Return array of idle states for the genpd. * @@ -2302,49 +2334,31 @@ static int genpd_parse_state(struct genpd_power_state *genpd_state, * * Returns the device states parsed from the OF node. The memory for the states * is allocated by this function and is the responsibility of the caller to - * free the memory after use. + * free the memory after use. If no domain idle states is found it returns + * -EINVAL and in case of errors, a negative error code. */ int of_genpd_parse_idle_states(struct device_node *dn, struct genpd_power_state **states, int *n) { struct genpd_power_state *st; - struct device_node *np; - int i = 0; - int err, ret; - int count; - struct of_phandle_iterator it; - const struct of_device_id *match_id; + int ret;

- count = of_count_phandle_with_args(dn, "domain-idle-states", NULL); - if (count <= 0) - return -EINVAL; + ret = genpd_iterate_idle_states(dn, NULL); + if (ret <= 0) + return ret < 0 ? ret : -EINVAL;

- st = kcalloc(count, sizeof(*st), GFP_KERNEL); + st = kcalloc(ret, sizeof(*st), GFP_KERNEL); if (!st) return -ENOMEM;

- /* Loop over the phandles until all the requested entry is found */ - of_for_each_phandle(&it, err, dn, "domain-idle-states", NULL, 0) { - np = it.node; - match_id = of_match_node(idle_state_match, np); - if (!match_id) - continue; - ret = genpd_parse_state(&st[i++], np); - if (ret) { - pr_err - ("Parsing idle state node %pOF failed with err %d\n", - np, ret); - of_node_put(np); - kfree(st); - return ret; - } + ret = genpd_iterate_idle_states(dn, st); + if (ret <= 0) { + kfree(st); + return ret < 0 ? ret : -EINVAL; }

- *n = i; - if (!i) - kfree(st); - else - *states = st; + *states = st; + *n = ret;

return 0; }

From: Tang Junhui tang.junhui@zte.com.cn

[ Upstream commit 682811b3ce1a5a4e20d700939a9042f01dbc66c4 ]

After long time running of random small IO writing, I reboot the machine, and after the machine power on, I found bcache got stuck, the stack is: [root@ceph153 ~]# cat /proc/2510/task/*/stack [<ffffffffa06b2455>] closure_sync+0x25/0x90 [bcache] [<ffffffffa06b6be8>] bch_journal+0x118/0x2b0 [bcache] [<ffffffffa06b6dc7>] bch_journal_meta+0x47/0x70 [bcache] [<ffffffffa06be8f7>] bch_prio_write+0x237/0x340 [bcache] [<ffffffffa06a8018>] bch_allocator_thread+0x3c8/0x3d0 [bcache] [<ffffffff810a631f>] kthread+0xcf/0xe0 [<ffffffff8164c318>] ret_from_fork+0x58/0x90 [<ffffffffffffffff>] 0xffffffffffffffff [root@ceph153 ~]# cat /proc/2038/task/*/stack [<ffffffffa06b1abd>] __bch_btree_map_nodes+0x12d/0x150 [bcache] [<ffffffffa06b1bd1>] bch_btree_insert+0xf1/0x170 [bcache] [<ffffffffa06b637f>] bch_journal_replay+0x13f/0x230 [bcache] [<ffffffffa06c75fe>] run_cache_set+0x79a/0x7c2 [bcache] [<ffffffffa06c0cf8>] register_bcache+0xd48/0x1310 [bcache] [<ffffffff812f702f>] kobj_attr_store+0xf/0x20 [<ffffffff8125b216>] sysfs_write_file+0xc6/0x140 [<ffffffff811dfbfd>] vfs_write+0xbd/0x1e0 [<ffffffff811e069f>] SyS_write+0x7f/0xe0 [<ffffffff8164c3c9>] system_call_fastpath+0x16/0x1 The stack shows the register thread and allocator thread were getting stuck when registering cache device.

I reboot the machine several times, the issue always exsit in this machine.

I debug the code, and found the call trace as bellow: register_bcache() ==>run_cache_set() ==>bch_journal_replay() ==>bch_btree_insert() ==>__bch_btree_map_nodes() ==>btree_insert_fn() ==>btree_split() //node need split ==>btree_check_reserve() In btree_check_reserve(), It will check if there is enough buckets of RESERVE_BTREE type, since allocator thread did not work yet, so no buckets of RESERVE_BTREE type allocated, so the register thread waits on c->btree_cache_wait, and goes to sleep.

Then the allocator thread initialized, the call trace is bellow: bch_allocator_thread() ==>bch_prio_write() ==>bch_journal_meta() ==>bch_journal() ==>journal_wait_for_write() In journal_wait_for_write(), It will check if journal is full by journal_full(), but the long time random small IO writing causes the exhaustion of journal buckets(journal.blocks_free=0), In order to release the journal buckets, the allocator calls btree_flush_write() to flush keys to btree nodes, and waits on c->journal.wait until btree nodes writing over or there has already some journal buckets space, then the allocator thread goes to sleep. but in btree_flush_write(), since bch_journal_replay() is not finished, so no btree nodes have journal (condition "if (btree_current_write(b)->journal)" never satisfied), so we got no btree node to flush, no journal bucket released, and allocator sleep all the times.

Through the above analysis, we can see that: 1) Register thread wait for allocator thread to allocate buckets of RESERVE_BTREE type; 2) Alloctor thread wait for register thread to replay journal, so it can flush btree nodes and get journal bucket. then they are all got stuck by waiting for each other.

Hua Rui provided a patch for me, by allocating some buckets of RESERVE_BTREE type in advance, so the register thread can get bucket when btree node splitting and no need to waiting for the allocator thread. I tested it, it has effect, and register thread run a step forward, but finally are still got stuck, the reason is only 8 bucket of RESERVE_BTREE type were allocated, and in bch_journal_replay(), after 2 btree nodes splitting, only 4 bucket of RESERVE_BTREE type left, then btree_check_reserve() is not satisfied anymore, so it goes to sleep again, and in the same time, alloctor thread did not flush enough btree nodes to release a journal bucket, so they all got stuck again.

So we need to allocate more buckets of RESERVE_BTREE type in advance, but how much is enough? By experience and test, I think it should be as much as journal buckets. Then I modify the code as this patch, and test in the machine, and it works.

This patch modified base on Hua Rui’s patch, and allocate more buckets of RESERVE_BTREE type in advance to avoid register thread and allocate thread going to wait for each other.

[patch v2] ca->sb.njournal_buckets would be 0 in the first time after cache creation, and no journal exists, so just 8 btree buckets is OK.

Signed-off-by: Hua Rui huarui.dev@gmail.com Signed-off-by: Tang Junhui tang.junhui@zte.com.cn Reviewed-by: Michael Lyle mlyle@lyle.org Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/md/bcache/btree.c | 9 ++++++--- drivers/md/bcache/super.c | 13 ++++++++++++- 2 files changed, 18 insertions(+), 4 deletions(-)

diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 81e8dc3dbe5e..45561f28e58a 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -1871,14 +1871,17 @@ void bch_initial_gc_finish(struct cache_set *c) */ for_each_cache(ca, c, i) { for_each_bucket(b, ca) { - if (fifo_full(&ca->free[RESERVE_PRIO])) + if (fifo_full(&ca->free[RESERVE_PRIO]) && + fifo_full(&ca->free[RESERVE_BTREE])) break;

if (bch_can_invalidate_bucket(ca, b) && !GC_MARK(b)) { __bch_invalidate_one_bucket(ca, b); - fifo_push(&ca->free[RESERVE_PRIO], - b - ca->buckets); + if (!fifo_push(&ca->free[RESERVE_PRIO], + b - ca->buckets)) + fifo_push(&ca->free[RESERVE_BTREE], + b - ca->buckets); } } } diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 14bdaf1cef2c..a7fcc51d44e9 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1833,6 +1833,7 @@ void bch_cache_release(struct kobject *kobj) static int cache_alloc(struct cache *ca) { size_t free; + size_t btree_buckets; struct bucket *b;

__module_get(THIS_MODULE); @@ -1840,9 +1841,19 @@ static int cache_alloc(struct cache *ca)

bio_init(&ca->journal.bio, ca->journal.bio.bi_inline_vecs, 8);

+ /* + * when ca->sb.njournal_buckets is not zero, journal exists, + * and in bch_journal_replay(), tree node may split, + * so bucket of RESERVE_BTREE type is needed, + * the worst situation is all journal buckets are valid journal, + * and all the keys need to replay, + * so the number of RESERVE_BTREE type buckets should be as much + * as journal buckets + */ + btree_buckets = ca->sb.njournal_buckets ?: 8; free = roundup_pow_of_two(ca->sb.nbuckets) >> 10;

- if (!init_fifo(&ca->free[RESERVE_BTREE], 8, GFP_KERNEL) || + if (!init_fifo(&ca->free[RESERVE_BTREE], btree_buckets, GFP_KERNEL) || !init_fifo_exact(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) || !init_fifo(&ca->free[RESERVE_MOVINGGC], free, GFP_KERNEL) || !init_fifo(&ca->free[RESERVE_NONE], free, GFP_KERNEL) ||

From: Tang Junhui tang.junhui@zte.com.cn

[ Upstream commit 7f4fc93d4713394ee8f1cd44c238e046e11b4f15 ]

I attach a back-end device to a cache set, and the cache set is not registered yet, this back-end device did not attach successfully, and no error returned: [root]# echo 87859280-fec6-4bcc-20df7ca8f86b > /sys/block/sde/bcache/attach [root]#

In sysfs_attach(), the return value "v" is initialized to "size" in the beginning, and if no cache set exist in bch_cache_sets, the "v" value would not change any more, and return to sysfs, sysfs regard it as success since the "size" is a positive number.

This patch fixes this issue by assigning "v" with "-ENOENT" in the initialization.

Signed-off-by: Tang Junhui tang.junhui@zte.com.cn Reviewed-by: Michael Lyle mlyle@lyle.org Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- drivers/md/bcache/sysfs.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index c54028b92bc0..6316399aa230 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -195,7 +195,7 @@ STORE(__cached_dev) { struct cached_dev *dc = container_of(kobj, struct cached_dev, disk.kobj); - ssize_t v = size; + ssize_t v; struct cache_set *c; struct kobj_uevent_env *env;

@@ -272,6 +272,7 @@ STORE(__cached_dev) if (bch_parse_uuid(buf, set_uuid) < 16) return -EINVAL;

+ v = -ENOENT; list_for_each_entry(c, &bch_cache_sets, list) { v = bch_cached_dev_attach(dc, c, set_uuid); if (!v) @@ -279,7 +280,7 @@ STORE(__cached_dev) }

pr_err("Can't attach %s: cache set not found", buf); - size = v; + return v; }

if (attr == &sysfs_detach && dc->disk.c)

From: "Md. Islam" mislam4@kent.edu

[ Upstream commit 043e337f555e610ad8237fd23522d97c968d72b9 ]

In Kernel 4.15.0+, Netem does not work properly.

Netem setup:

tc qdisc add dev h1-eth0 root handle 1: netem delay 10ms 2ms

Result:

PING 172.16.101.2 (172.16.101.2) 56(84) bytes of data. 64 bytes from 172.16.101.2: icmp_seq=1 ttl=64 time=22.8 ms 64 bytes from 172.16.101.2: icmp_seq=2 ttl=64 time=10.9 ms 64 bytes from 172.16.101.2: icmp_seq=3 ttl=64 time=10.9 ms 64 bytes from 172.16.101.2: icmp_seq=5 ttl=64 time=11.4 ms 64 bytes from 172.16.101.2: icmp_seq=6 ttl=64 time=11.8 ms 64 bytes from 172.16.101.2: icmp_seq=4 ttl=64 time=4303 ms 64 bytes from 172.16.101.2: icmp_seq=10 ttl=64 time=11.2 ms 64 bytes from 172.16.101.2: icmp_seq=11 ttl=64 time=10.3 ms 64 bytes from 172.16.101.2: icmp_seq=7 ttl=64 time=4304 ms 64 bytes from 172.16.101.2: icmp_seq=8 ttl=64 time=4303 ms

Patch:

(rnd % (2 * sigma)) - sigma was overflowing s32. After applying the patch, I found following output which is desirable.

PING 172.16.101.2 (172.16.101.2) 56(84) bytes of data. 64 bytes from 172.16.101.2: icmp_seq=1 ttl=64 time=21.1 ms 64 bytes from 172.16.101.2: icmp_seq=2 ttl=64 time=8.46 ms 64 bytes from 172.16.101.2: icmp_seq=3 ttl=64 time=9.00 ms 64 bytes from 172.16.101.2: icmp_seq=4 ttl=64 time=11.8 ms 64 bytes from 172.16.101.2: icmp_seq=5 ttl=64 time=8.36 ms 64 bytes from 172.16.101.2: icmp_seq=6 ttl=64 time=11.8 ms 64 bytes from 172.16.101.2: icmp_seq=7 ttl=64 time=8.11 ms 64 bytes from 172.16.101.2: icmp_seq=8 ttl=64 time=10.0 ms 64 bytes from 172.16.101.2: icmp_seq=9 ttl=64 time=11.3 ms 64 bytes from 172.16.101.2: icmp_seq=10 ttl=64 time=11.5 ms 64 bytes from 172.16.101.2: icmp_seq=11 ttl=64 time=10.2 ms

Reviewed-by: Stephen Hemminger stephen@networkplumber.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- net/sched/sch_netem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 2aeca57f9bd0..73c4bea821cb 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -327,7 +327,7 @@ static s64 tabledist(s64 mu, s32 sigma,

/* default uniform distribution */ if (dist == NULL) - return (rnd % (2 * sigma)) - sigma + mu; + return ((rnd % (2 * sigma)) + mu) - sigma;

t = dist->table[rnd % dist->size]; x = (sigma % NETEM_DIST_SCALE) * t;

From: "Steven Rostedt (VMware)" rostedt@goodmis.org

[ Upstream commit 97fe22adf33f06519bfdf7dad33bcd562e366c8f ]

Al Viro discovered a bug in the glob ftrace filtering code where "*a*b" is treated the same as "a*b", and functions that would be selected by "*a*b" but not "a*b" are not selected with "*a*b".

Add tests for patterns "*a*b" and "a*b*" to the glob selftest.

Link: http://lkml.kernel.org/r/20180127170748.GF13338@ZenIV.linux.org.uk

Cc: Shuah Khan shuah@kernel.org Acked-by: Masami Hiramatsu mhiramat@kernel.org Signed-off-by: Steven Rostedt (VMware) rostedt@goodmis.org Signed-off-by: Sasha Levin alexander.levin@microsoft.com --- tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc index 589d52b211b7..27a54a17da65 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc @@ -29,6 +29,12 @@ ftrace_filter_check '*schedule*' '^.*schedule.*$' # filter by *, end match ftrace_filter_check 'schedule*' '^schedule.*$'

+# filter by *mid*end +ftrace_filter_check '*aw*lock' '.*aw.*lock$' + +# filter by start*mid* +ftrace_filter_check 'mutex*try*' '^mutex.*try.*' + # Advanced full-glob matching feature is recently supported. # Skip the tests if we are sure the kernel does not support it. if grep -q 'accepts: .* glob-matching-pattern' README ; then